diff options
| author | Jason R. Coombs <jaraco@jaraco.com> | 2023-01-14 11:13:55 -0500 |
|---|---|---|
| committer | Jason R. Coombs <jaraco@jaraco.com> | 2023-01-14 11:13:55 -0500 |
| commit | 245da5441248eeb2d575034d04cbc241bf545161 (patch) | |
| tree | d76526e1461252cc1119cd9482a64ef1e75f7838 /pkg_resources | |
| parent | d7b783a4b8b01e58135e40bd9a1db8a82c090982 (diff) | |
| parent | 82eee6a998251b33ab3984f39b25c27ca72ba8b0 (diff) | |
| download | python-setuptools-git-245da5441248eeb2d575034d04cbc241bf545161.tar.gz | |
Merge branch 'main' into debt/remove-legacy-version
Diffstat (limited to 'pkg_resources')
105 files changed, 15483 insertions, 7691 deletions
diff --git a/pkg_resources/__init__.py b/pkg_resources/__init__.py index e7e31b9f..7b3b4e33 100644 --- a/pkg_resources/__init__.py +++ b/pkg_resources/__init__.py @@ -53,8 +53,10 @@ except NameError: # capture these to bypass sandboxing from os import utime + try: from os import mkdir, rename, unlink + WRITE_SUPPORT = True except ImportError: # no write support, probably under GAE @@ -65,6 +67,7 @@ from os.path import isdir, split try: import importlib.machinery as importlib_machinery + # access attribute to force import under delayed import mechanisms. importlib_machinery.__name__ except ImportError: @@ -76,12 +79,14 @@ from pkg_resources.extern.jaraco.text import ( join_continuation, ) -from pkg_resources.extern import appdirs +from pkg_resources.extern import platformdirs from pkg_resources.extern import packaging + __import__('pkg_resources.extern.packaging.version') __import__('pkg_resources.extern.packaging.specifiers') __import__('pkg_resources.extern.packaging.requirements') __import__('pkg_resources.extern.packaging.markers') +__import__('pkg_resources.extern.packaging.utils') if sys.version_info < (3, 5): raise RuntimeError("Python 3.5 or later is required") @@ -186,51 +191,87 @@ def get_supported_platform(): __all__ = [ # Basic resource access and distribution/entry point discovery - 'require', 'run_script', 'get_provider', 'get_distribution', - 'load_entry_point', 'get_entry_map', 'get_entry_info', + 'require', + 'run_script', + 'get_provider', + 'get_distribution', + 'load_entry_point', + 'get_entry_map', + 'get_entry_info', 'iter_entry_points', - 'resource_string', 'resource_stream', 'resource_filename', - 'resource_listdir', 'resource_exists', 'resource_isdir', - + 'resource_string', + 'resource_stream', + 'resource_filename', + 'resource_listdir', + 'resource_exists', + 'resource_isdir', # Environmental control - 'declare_namespace', 'working_set', 'add_activation_listener', - 'find_distributions', 'set_extraction_path', 'cleanup_resources', + 'declare_namespace', + 'working_set', + 'add_activation_listener', + 'find_distributions', + 'set_extraction_path', + 'cleanup_resources', 'get_default_cache', - # Primary implementation classes - 'Environment', 'WorkingSet', 'ResourceManager', - 'Distribution', 'Requirement', 'EntryPoint', - + 'Environment', + 'WorkingSet', + 'ResourceManager', + 'Distribution', + 'Requirement', + 'EntryPoint', # Exceptions - 'ResolutionError', 'VersionConflict', 'DistributionNotFound', - 'UnknownExtra', 'ExtractionError', - + 'ResolutionError', + 'VersionConflict', + 'DistributionNotFound', + 'UnknownExtra', + 'ExtractionError', # Warnings 'PEP440Warning', - # Parsing functions and string utilities - 'parse_requirements', 'parse_version', 'safe_name', 'safe_version', - 'get_platform', 'compatible_platforms', 'yield_lines', 'split_sections', - 'safe_extra', 'to_filename', 'invalid_marker', 'evaluate_marker', - + 'parse_requirements', + 'parse_version', + 'safe_name', + 'safe_version', + 'get_platform', + 'compatible_platforms', + 'yield_lines', + 'split_sections', + 'safe_extra', + 'to_filename', + 'invalid_marker', + 'evaluate_marker', # filesystem utilities - 'ensure_directory', 'normalize_path', - + 'ensure_directory', + 'normalize_path', # Distribution "precedence" constants - 'EGG_DIST', 'BINARY_DIST', 'SOURCE_DIST', 'CHECKOUT_DIST', 'DEVELOP_DIST', - + 'EGG_DIST', + 'BINARY_DIST', + 'SOURCE_DIST', + 'CHECKOUT_DIST', + 'DEVELOP_DIST', # "Provider" interfaces, implementations, and registration/lookup APIs - 'IMetadataProvider', 'IResourceProvider', 'FileMetadata', - 'PathMetadata', 'EggMetadata', 'EmptyProvider', 'empty_provider', - 'NullProvider', 'EggProvider', 'DefaultProvider', 'ZipProvider', - 'register_finder', 'register_namespace_handler', 'register_loader_type', - 'fixup_namespace_packages', 'get_importer', - + 'IMetadataProvider', + 'IResourceProvider', + 'FileMetadata', + 'PathMetadata', + 'EggMetadata', + 'EmptyProvider', + 'empty_provider', + 'NullProvider', + 'EggProvider', + 'DefaultProvider', + 'ZipProvider', + 'register_finder', + 'register_namespace_handler', + 'register_loader_type', + 'fixup_namespace_packages', + 'get_importer', # Warnings 'PkgResourcesDeprecationWarning', - # Deprecated/backward compatibility only - 'run_main', 'AvailableDistributions', + 'run_main', + 'AvailableDistributions', ] @@ -289,8 +330,10 @@ class ContextualVersionConflict(VersionConflict): class DistributionNotFound(ResolutionError): """A requested distribution was not found""" - _template = ("The '{self.req}' distribution was not found " - "and is required by {self.requirers_str}") + _template = ( + "The '{self.req}' distribution was not found " + "and is required by {self.requirers_str}" + ) @property def req(self): @@ -384,7 +427,8 @@ def get_build_platform(): version = _macos_vers() machine = os.uname()[4].replace(" ", "_") return "macosx-%d.%d-%s" % ( - int(version[0]), int(version[1]), + int(version[0]), + int(version[1]), _macos_arch(machine), ) except ValueError: @@ -425,15 +469,18 @@ def compatible_platforms(provided, required): if provDarwin: dversion = int(provDarwin.group(1)) macosversion = "%s.%s" % (reqMac.group(1), reqMac.group(2)) - if dversion == 7 and macosversion >= "10.3" or \ - dversion == 8 and macosversion >= "10.4": + if ( + dversion == 7 + and macosversion >= "10.3" + or dversion == 8 + and macosversion >= "10.4" + ): return True # egg isn't macOS or legacy darwin return False # are they the same major version and machine type? - if provMac.group(1) != reqMac.group(1) or \ - provMac.group(3) != reqMac.group(3): + if provMac.group(1) != reqMac.group(1) or provMac.group(3) != reqMac.group(3): return False # is the required OS major update >= the provided one? @@ -495,8 +542,8 @@ class IMetadataProvider: def get_metadata_lines(name): """Yield named metadata resource as list of non-blank non-comment lines - Leading and trailing whitespace is stripped from each line, and lines - with ``#`` as the first non-blank character are omitted.""" + Leading and trailing whitespace is stripped from each line, and lines + with ``#`` as the first non-blank character are omitted.""" def metadata_isdir(name): """Is the named metadata a directory? (like ``os.path.isdir()``)""" @@ -544,6 +591,7 @@ class WorkingSet: self.entries = [] self.entry_keys = {} self.by_key = {} + self.normalized_to_canonical_keys = {} self.callbacks = [] if entries is None: @@ -624,6 +672,14 @@ class WorkingSet: is returned. """ dist = self.by_key.get(req.key) + + if dist is None: + canonical_key = self.normalized_to_canonical_keys.get(req.key) + + if canonical_key is not None: + req.key = canonical_key + dist = self.by_key.get(canonical_key) + if dist is not None and dist not in req: # XXX add more info raise VersionConflict(dist, req) @@ -692,6 +748,8 @@ class WorkingSet: return self.by_key[dist.key] = dist + normalized_name = packaging.utils.canonicalize_name(dist.key) + self.normalized_to_canonical_keys[normalized_name] = dist.key if dist.key not in keys: keys.append(dist.key) if dist.key not in keys2: @@ -699,8 +757,14 @@ class WorkingSet: self._added_new(dist) # FIXME: 'WorkingSet.resolve' is too complex (11) - def resolve(self, requirements, env=None, installer=None, # noqa: C901 - replace_conflicting=False, extras=None): + def resolve( # noqa: C901 + self, + requirements, + env=None, + installer=None, + replace_conflicting=False, + extras=None, + ): """List all distributions needed to (recursively) meet `requirements` `requirements` must be a sequence of ``Requirement`` objects. `env`, @@ -765,8 +829,7 @@ class WorkingSet: env = Environment([]) ws = WorkingSet([]) dist = best[req.key] = env.best_match( - req, ws, installer, - replace_conflicting=replace_conflicting + req, ws, installer, replace_conflicting=replace_conflicting ) if dist is None: requirers = required_by.get(req, None) @@ -791,8 +854,7 @@ class WorkingSet: # return list of distros to activate return to_activate - def find_plugins( - self, plugin_env, full_env=None, installer=None, fallback=True): + def find_plugins(self, plugin_env, full_env=None, installer=None, fallback=True): """Find all activatable distributions in `plugin_env` Example usage:: @@ -911,15 +973,19 @@ class WorkingSet: def __getstate__(self): return ( - self.entries[:], self.entry_keys.copy(), self.by_key.copy(), - self.callbacks[:] + self.entries[:], + self.entry_keys.copy(), + self.by_key.copy(), + self.normalized_to_canonical_keys.copy(), + self.callbacks[:], ) - def __setstate__(self, e_k_b_c): - entries, keys, by_key, callbacks = e_k_b_c + def __setstate__(self, e_k_b_n_c): + entries, keys, by_key, normalized_to_canonical_keys, callbacks = e_k_b_n_c self.entries = entries[:] self.entry_keys = keys.copy() self.by_key = by_key.copy() + self.normalized_to_canonical_keys = normalized_to_canonical_keys.copy() self.callbacks = callbacks[:] @@ -947,8 +1013,8 @@ class Environment: """Searchable snapshot of distributions on a search path""" def __init__( - self, search_path=None, platform=get_supported_platform(), - python=PY_MAJOR): + self, search_path=None, platform=get_supported_platform(), python=PY_MAJOR + ): """Snapshot distributions available on a search path Any distributions found on `search_path` are added to the environment. @@ -1015,16 +1081,14 @@ class Environment: return self._distmap.get(distribution_key, []) def add(self, dist): - """Add `dist` if we ``can_add()`` it and it has not already been added - """ + """Add `dist` if we ``can_add()`` it and it has not already been added""" if self.can_add(dist) and dist.has_version(): dists = self._distmap.setdefault(dist.key, []) if dist not in dists: dists.append(dist) dists.sort(key=operator.attrgetter('hashcmp'), reverse=True) - def best_match( - self, req, working_set, installer=None, replace_conflicting=False): + def best_match(self, req, working_set, installer=None, replace_conflicting=False): """Find distribution best matching `req` and usable on `working_set` This calls the ``find(req)`` method of the `working_set` to see if a @@ -1111,6 +1175,7 @@ class ExtractionError(RuntimeError): class ResourceManager: """Manage resource extraction and packages""" + extraction_path = None def __init__(self): @@ -1122,9 +1187,7 @@ class ResourceManager: def resource_isdir(self, package_or_requirement, resource_name): """Is the named resource an existing directory?""" - return get_provider(package_or_requirement).resource_isdir( - resource_name - ) + return get_provider(package_or_requirement).resource_isdir(resource_name) def resource_filename(self, package_or_requirement, resource_name): """Return a true filesystem path for specified resource""" @@ -1146,9 +1209,7 @@ class ResourceManager: def resource_listdir(self, package_or_requirement, resource_name): """List the contents of the named resource directory""" - return get_provider(package_or_requirement).resource_listdir( - resource_name - ) + return get_provider(package_or_requirement).resource_listdir(resource_name) def extraction_error(self): """Give an error message for problems extracting file(s)""" @@ -1156,7 +1217,8 @@ class ResourceManager: old_exc = sys.exc_info()[1] cache_path = self.extraction_path or get_default_cache() - tmpl = textwrap.dedent(""" + tmpl = textwrap.dedent( + """ Can't extract file(s) to egg cache The following error occurred while trying to extract file(s) @@ -1171,7 +1233,8 @@ class ResourceManager: Perhaps your account does not have write access to this directory? You can change the cache directory by setting the PYTHON_EGG_CACHE environment variable to point to an accessible directory. - """).lstrip() + """ + ).lstrip() err = ExtractionError(tmpl.format(**locals())) err.manager = self err.cache_path = cache_path @@ -1270,9 +1333,7 @@ class ResourceManager: ``cleanup_resources()``.) """ if self.cached_files: - raise ValueError( - "Can't change extraction path, files already extracted" - ) + raise ValueError("Can't change extraction path, files already extracted") self.extraction_path = path @@ -1296,9 +1357,8 @@ def get_default_cache(): or a platform-relevant user cache dir for an app named "Python-Eggs". """ - return ( - os.environ.get('PYTHON_EGG_CACHE') - or appdirs.user_cache_dir(appname='Python-Eggs') + return os.environ.get('PYTHON_EGG_CACHE') or platformdirs.user_cache_dir( + appname='Python-Eggs' ) @@ -1435,8 +1495,9 @@ class NullProvider: script = 'scripts/' + script_name if not self.has_metadata(script): raise ResolutionError( - "Script {script!r} not found in metadata at {self.egg_info!r}" - .format(**locals()), + "Script {script!r} not found in metadata at {self.egg_info!r}".format( + **locals() + ), ) script_text = self.get_metadata(script).replace('\r\n', '\n') script_text = script_text.replace('\r', '\n') @@ -1449,8 +1510,12 @@ class NullProvider: exec(code, namespace, namespace) else: from linecache import cache + cache[script_filename] = ( - len(script_text), 0, script_text.split('\n'), script_filename + len(script_text), + 0, + script_text.split('\n'), + script_filename, ) script_code = compile(script_text, script_filename, 'exec') exec(script_code, namespace, namespace) @@ -1530,9 +1595,9 @@ is not allowed. AttributeError: ... """ invalid = ( - os.path.pardir in path.split(posixpath.sep) or - posixpath.isabs(path) or - ntpath.isabs(path) + os.path.pardir in path.split(posixpath.sep) + or posixpath.isabs(path) + or ntpath.isabs(path) ) if not invalid: return @@ -1614,7 +1679,10 @@ class DefaultProvider(EggProvider): @classmethod def _register(cls): - loader_names = 'SourceFileLoader', 'SourcelessFileLoader', + loader_names = ( + 'SourceFileLoader', + 'SourcelessFileLoader', + ) for name in loader_names: loader_cls = getattr(importlib_machinery, name, type(None)) register_loader_type(loader_cls, cls) @@ -1674,6 +1742,7 @@ class MemoizedZipManifests(ZipManifests): """ Memoized zipfile manifests. """ + manifest_mod = collections.namedtuple('manifest_mod', 'manifest mtime') def load(self, path): @@ -1707,20 +1776,16 @@ class ZipProvider(EggProvider): if fspath == self.loader.archive: return '' if fspath.startswith(self.zip_pre): - return fspath[len(self.zip_pre):] - raise AssertionError( - "%s is not a subpath of %s" % (fspath, self.zip_pre) - ) + return fspath[len(self.zip_pre) :] + raise AssertionError("%s is not a subpath of %s" % (fspath, self.zip_pre)) def _parts(self, zip_path): # Convert a zipfile subpath into an egg-relative path part list. # pseudo-fs path fspath = self.zip_pre + zip_path if fspath.startswith(self.egg_root + os.sep): - return fspath[len(self.egg_root) + 1:].split(os.sep) - raise AssertionError( - "%s is not a subpath of %s" % (fspath, self.egg_root) - ) + return fspath[len(self.egg_root) + 1 :].split(os.sep) + raise AssertionError("%s is not a subpath of %s" % (fspath, self.egg_root)) @property def zipinfo(self): @@ -1753,22 +1818,19 @@ class ZipProvider(EggProvider): if zip_path in self._index(): for name in self._index()[zip_path]: - last = self._extract_resource( - manager, os.path.join(zip_path, name) - ) + last = self._extract_resource(manager, os.path.join(zip_path, name)) # return the extracted directory name return os.path.dirname(last) timestamp, size = self._get_date_and_size(self.zipinfo[zip_path]) if not WRITE_SUPPORT: - raise IOError('"os.rename" and "os.unlink" are not supported ' - 'on this platform') + raise IOError( + '"os.rename" and "os.unlink" are not supported ' 'on this platform' + ) try: - real_path = manager.get_cache_path( - self.egg_name, self._parts(zip_path) - ) + real_path = manager.get_cache_path(self.egg_name, self._parts(zip_path)) if self._is_current(real_path, zip_path): return real_path @@ -2010,16 +2072,12 @@ def find_on_path(importer, path_item, only=False): if _is_unpacked_egg(path_item): yield Distribution.from_filename( - path_item, metadata=PathMetadata( - path_item, os.path.join(path_item, 'EGG-INFO') - ) + path_item, + metadata=PathMetadata(path_item, os.path.join(path_item, 'EGG-INFO')), ) return - entries = ( - os.path.join(path_item, child) - for child in safe_listdir(path_item) - ) + entries = (os.path.join(path_item, child) for child in safe_listdir(path_item)) # scan for .egg and .egg-info in directory for entry in sorted(entries): @@ -2033,19 +2091,18 @@ def dist_factory(path_item, entry, only): """Return a dist_factory for the given entry.""" lower = entry.lower() is_egg_info = lower.endswith('.egg-info') - is_dist_info = ( - lower.endswith('.dist-info') and - os.path.isdir(os.path.join(path_item, entry)) + is_dist_info = lower.endswith('.dist-info') and os.path.isdir( + os.path.join(path_item, entry) ) is_meta = is_egg_info or is_dist_info return ( distributions_from_metadata - if is_meta else - find_distributions - if not only and _is_egg_path(entry) else - resolve_egg_link - if not only and lower.endswith('.egg-link') else - NoDists() + if is_meta + else find_distributions + if not only and _is_egg_path(entry) + else resolve_egg_link + if not only and lower.endswith('.egg-link') + else NoDists() ) @@ -2057,6 +2114,7 @@ class NoDists: >>> list(NoDists()('anything')) [] """ + def __bool__(self): return False @@ -2091,7 +2149,10 @@ def distributions_from_metadata(path): metadata = FileMetadata(path) entry = os.path.basename(path) yield Distribution.from_location( - root, entry, metadata, precedence=DEVELOP_DIST, + root, + entry, + metadata, + precedence=DEVELOP_DIST, ) @@ -2113,8 +2174,7 @@ def resolve_egg_link(path): """ referenced_paths = non_empty_lines(path) resolved_paths = ( - os.path.join(os.path.dirname(path), ref) - for ref in referenced_paths + os.path.join(os.path.dirname(path), ref) for ref in referenced_paths ) dist_groups = map(find_distributions, resolved_paths) return next(dist_groups, ()) @@ -2293,8 +2353,7 @@ register_namespace_handler(object, null_ns_handler) def normalize_path(filename): """Normalize a file/dir name for comparison purposes""" - return os.path.normcase(os.path.realpath(os.path.normpath( - _cygwin_patch(filename)))) + return os.path.normcase(os.path.realpath(os.path.normpath(_cygwin_patch(filename)))) def _cygwin_patch(filename): # pragma: nocover @@ -2325,9 +2384,9 @@ def _is_egg_path(path): def _is_zip_egg(path): return ( - path.lower().endswith('.egg') and - os.path.isfile(path) and - zipfile.is_zipfile(path) + path.lower().endswith('.egg') + and os.path.isfile(path) + and zipfile.is_zipfile(path) ) @@ -2335,9 +2394,8 @@ def _is_unpacked_egg(path): """ Determine if given path appears to be an unpacked egg. """ - return ( - path.lower().endswith('.egg') and - os.path.isfile(os.path.join(path, 'EGG-INFO', 'PKG-INFO')) + return path.lower().endswith('.egg') and os.path.isfile( + os.path.join(path, 'EGG-INFO', 'PKG-INFO') ) @@ -2501,8 +2559,10 @@ def _version_from_file(lines): Given an iterable of lines from a Metadata file, return the value of the Version field, if present, or None otherwise. """ + def is_version_line(line): return line.lower().startswith('version:') + version_lines = filter(is_version_line, lines) line = next(iter(version_lines), '') _, _, value = line.partition(':') @@ -2511,12 +2571,19 @@ def _version_from_file(lines): class Distribution: """Wrap an actual or potential sys.path entry w/metadata""" + PKG_INFO = 'PKG-INFO' def __init__( - self, location=None, metadata=None, project_name=None, - version=None, py_version=PY_MAJOR, platform=None, - precedence=EGG_DIST): + self, + location=None, + metadata=None, + project_name=None, + version=None, + py_version=PY_MAJOR, + platform=None, + precedence=EGG_DIST, + ): self.project_name = safe_name(project_name or 'Unknown') if version is not None: self._version = safe_version(version) @@ -2539,8 +2606,13 @@ class Distribution: 'name', 'ver', 'pyver', 'plat' ) return cls( - location, metadata, project_name=project_name, version=version, - py_version=py_version, platform=platform, **kw + location, + metadata, + project_name=project_name, + version=version, + py_version=py_version, + platform=platform, + **kw, )._reload_version() def _reload_version(self): @@ -2608,9 +2680,9 @@ class Distribution: version = self._get_version() if version is None: path = self._get_metadata_path_for_display(self.PKG_INFO) - msg = ( - "Missing 'Version:' header and/or {} file at path: {}" - ).format(self.PKG_INFO, path) + msg = ("Missing 'Version:' header and/or {} file at path: {}").format( + self.PKG_INFO, path + ) raise ValueError(msg, self) from e return version @@ -2639,8 +2711,7 @@ class Distribution: reqs = dm.pop(extra) new_extra, _, marker = extra.partition(':') fails_marker = marker and ( - invalid_marker(marker) - or not evaluate_marker(marker) + invalid_marker(marker) or not evaluate_marker(marker) ) if fails_marker: reqs = [] @@ -2712,8 +2783,9 @@ class Distribution: def egg_name(self): """Return what this distribution's standard .egg filename should be""" filename = "%s-%s-py%s" % ( - to_filename(self.project_name), to_filename(self.version), - self.py_version or PY_MAJOR + to_filename(self.project_name), + to_filename(self.version), + self.py_version or PY_MAJOR, ) if self.platform: @@ -2743,17 +2815,13 @@ class Distribution: def __dir__(self): return list( set(super(Distribution, self).__dir__()) - | set( - attr for attr in self._provider.__dir__() - if not attr.startswith('_') - ) + | set(attr for attr in self._provider.__dir__() if not attr.startswith('_')) ) @classmethod def from_filename(cls, filename, metadata=None, **kw): return cls.from_location( - _normalize_cached(filename), os.path.basename(filename), metadata, - **kw + _normalize_cached(filename), os.path.basename(filename), metadata, **kw ) def as_requirement(self): @@ -2865,14 +2933,18 @@ class Distribution: nsp = dict.fromkeys(self._get_metadata('namespace_packages.txt')) loc = normalize_path(self.location) for modname in self._get_metadata('top_level.txt'): - if (modname not in sys.modules or modname in nsp - or modname in _namespace_packages): + if ( + modname not in sys.modules + or modname in nsp + or modname in _namespace_packages + ): continue if modname in ('pkg_resources', 'setuptools', 'site'): continue fn = getattr(sys.modules[modname], '__file__', None) - if fn and (normalize_path(fn).startswith(loc) or - fn.startswith(self.location)): + if fn and ( + normalize_path(fn).startswith(loc) or fn.startswith(self.location) + ): continue issue_warning( "Module %s was already imported from %s, but %s is being added" @@ -2924,6 +2996,7 @@ class DistInfoDistribution(Distribution): Wrap an actual or potential sys.path entry w/metadata, .dist-info style. """ + PKG_INFO = 'METADATA' EQEQ = re.compile(r"([\(,])\s*(\d.*?)\s*([,\)])") @@ -3009,8 +3082,7 @@ class Requirement(packaging.requirements.Requirement): self.unsafe_name = self.name project_name = safe_name(self.name) self.project_name, self.key = project_name, project_name.lower() - self.specs = [ - (spec.operator, spec.version) for spec in self.specifier] + self.specs = [(spec.operator, spec.version) for spec in self.specifier] self.extras = tuple(map(safe_extra, self.extras)) self.hashCmp = ( self.key, @@ -3022,10 +3094,7 @@ class Requirement(packaging.requirements.Requirement): self.__hash = hash(self.hashCmp) def __eq__(self, other): - return ( - isinstance(other, Requirement) and - self.hashCmp == other.hashCmp - ) + return isinstance(other, Requirement) and self.hashCmp == other.hashCmp def __ne__(self, other): return not self == other @@ -3050,7 +3119,7 @@ class Requirement(packaging.requirements.Requirement): @staticmethod def parse(s): - req, = parse_requirements(s) + (req,) = parse_requirements(s) return req @@ -3188,10 +3257,7 @@ def _initialize_master_working_set(): # ensure that all distributions added to the working set in the future # (e.g. by calling ``require()``) will get activated as well, # with higher priority (replace=True). - tuple( - dist.activate(replace=False) - for dist in working_set - ) + tuple(dist.activate(replace=False) for dist in working_set) add_activation_listener( lambda dist: dist.activate(replace=True), existing=False, diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/DESCRIPTION.rst b/pkg_resources/_vendor/appdirs-1.4.3.dist-info/DESCRIPTION.rst deleted file mode 100644 index c605ec26..00000000 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/DESCRIPTION.rst +++ /dev/null @@ -1,227 +0,0 @@ - -.. image:: https://secure.travis-ci.org/ActiveState/appdirs.png - :target: http://travis-ci.org/ActiveState/appdirs - -the problem -=========== - -What directory should your app use for storing user data? If running on Mac OS X, you -should use:: - - ~/Library/Application Support/<AppName> - -If on Windows (at least English Win XP) that should be:: - - C:\Documents and Settings\<User>\Application Data\Local Settings\<AppAuthor>\<AppName> - -or possibly:: - - C:\Documents and Settings\<User>\Application Data\<AppAuthor>\<AppName> - -for `roaming profiles <http://bit.ly/9yl3b6>`_ but that is another story. - -On Linux (and other Unices) the dir, according to the `XDG -spec <http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html>`_, is:: - - ~/.local/share/<AppName> - - -``appdirs`` to the rescue -========================= - -This kind of thing is what the ``appdirs`` module is for. ``appdirs`` will -help you choose an appropriate: - -- user data dir (``user_data_dir``) -- user config dir (``user_config_dir``) -- user cache dir (``user_cache_dir``) -- site data dir (``site_data_dir``) -- site config dir (``site_config_dir``) -- user log dir (``user_log_dir``) - -and also: - -- is a single module so other Python packages can include their own private copy -- is slightly opinionated on the directory names used. Look for "OPINION" in - documentation and code for when an opinion is being applied. - - -some example output -=================== - -On Mac OS X:: - - >>> from appdirs import * - >>> appname = "SuperApp" - >>> appauthor = "Acme" - >>> user_data_dir(appname, appauthor) - '/Users/trentm/Library/Application Support/SuperApp' - >>> site_data_dir(appname, appauthor) - '/Library/Application Support/SuperApp' - >>> user_cache_dir(appname, appauthor) - '/Users/trentm/Library/Caches/SuperApp' - >>> user_log_dir(appname, appauthor) - '/Users/trentm/Library/Logs/SuperApp' - -On Windows 7:: - - >>> from appdirs import * - >>> appname = "SuperApp" - >>> appauthor = "Acme" - >>> user_data_dir(appname, appauthor) - 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp' - >>> user_data_dir(appname, appauthor, roaming=True) - 'C:\\Users\\trentm\\AppData\\Roaming\\Acme\\SuperApp' - >>> user_cache_dir(appname, appauthor) - 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Cache' - >>> user_log_dir(appname, appauthor) - 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Logs' - -On Linux:: - - >>> from appdirs import * - >>> appname = "SuperApp" - >>> appauthor = "Acme" - >>> user_data_dir(appname, appauthor) - '/home/trentm/.local/share/SuperApp - >>> site_data_dir(appname, appauthor) - '/usr/local/share/SuperApp' - >>> site_data_dir(appname, appauthor, multipath=True) - '/usr/local/share/SuperApp:/usr/share/SuperApp' - >>> user_cache_dir(appname, appauthor) - '/home/trentm/.cache/SuperApp' - >>> user_log_dir(appname, appauthor) - '/home/trentm/.cache/SuperApp/log' - >>> user_config_dir(appname) - '/home/trentm/.config/SuperApp' - >>> site_config_dir(appname) - '/etc/xdg/SuperApp' - >>> os.environ['XDG_CONFIG_DIRS'] = '/etc:/usr/local/etc' - >>> site_config_dir(appname, multipath=True) - '/etc/SuperApp:/usr/local/etc/SuperApp' - - -``AppDirs`` for convenience -=========================== - -:: - - >>> from appdirs import AppDirs - >>> dirs = AppDirs("SuperApp", "Acme") - >>> dirs.user_data_dir - '/Users/trentm/Library/Application Support/SuperApp' - >>> dirs.site_data_dir - '/Library/Application Support/SuperApp' - >>> dirs.user_cache_dir - '/Users/trentm/Library/Caches/SuperApp' - >>> dirs.user_log_dir - '/Users/trentm/Library/Logs/SuperApp' - - - -Per-version isolation -===================== - -If you have multiple versions of your app in use that you want to be -able to run side-by-side, then you may want version-isolation for these -dirs:: - - >>> from appdirs import AppDirs - >>> dirs = AppDirs("SuperApp", "Acme", version="1.0") - >>> dirs.user_data_dir - '/Users/trentm/Library/Application Support/SuperApp/1.0' - >>> dirs.site_data_dir - '/Library/Application Support/SuperApp/1.0' - >>> dirs.user_cache_dir - '/Users/trentm/Library/Caches/SuperApp/1.0' - >>> dirs.user_log_dir - '/Users/trentm/Library/Logs/SuperApp/1.0' - - - -appdirs Changelog -================= - -appdirs 1.4.3 -------------- -- [PR #76] Python 3.6 invalid escape sequence deprecation fixes -- Fix for Python 3.6 support - -appdirs 1.4.2 -------------- -- [PR #84] Allow installing without setuptools -- [PR #86] Fix string delimiters in setup.py description -- Add Python 3.6 support - -appdirs 1.4.1 -------------- -- [issue #38] Fix _winreg import on Windows Py3 -- [issue #55] Make appname optional - -appdirs 1.4.0 -------------- -- [PR #42] AppAuthor is now optional on Windows -- [issue 41] Support Jython on Windows, Mac, and Unix-like platforms. Windows - support requires `JNA <https://github.com/twall/jna>`_. -- [PR #44] Fix incorrect behaviour of the site_config_dir method - -appdirs 1.3.0 -------------- -- [Unix, issue 16] Conform to XDG standard, instead of breaking it for - everybody -- [Unix] Removes gratuitous case mangling of the case, since \*nix-es are - usually case sensitive, so mangling is not wise -- [Unix] Fixes the utterly wrong behaviour in ``site_data_dir``, return result - based on XDG_DATA_DIRS and make room for respecting the standard which - specifies XDG_DATA_DIRS is a multiple-value variable -- [Issue 6] Add ``*_config_dir`` which are distinct on nix-es, according to - XDG specs; on Windows and Mac return the corresponding ``*_data_dir`` - -appdirs 1.2.0 -------------- - -- [Unix] Put ``user_log_dir`` under the *cache* dir on Unix. Seems to be more - typical. -- [issue 9] Make ``unicode`` work on py3k. - -appdirs 1.1.0 -------------- - -- [issue 4] Add ``AppDirs.user_log_dir``. -- [Unix, issue 2, issue 7] appdirs now conforms to `XDG base directory spec - <http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html>`_. -- [Mac, issue 5] Fix ``site_data_dir()`` on Mac. -- [Mac] Drop use of 'Carbon' module in favour of hardcoded paths; supports - Python3 now. -- [Windows] Append "Cache" to ``user_cache_dir`` on Windows by default. Use - ``opinion=False`` option to disable this. -- Add ``appdirs.AppDirs`` convenience class. Usage: - - >>> dirs = AppDirs("SuperApp", "Acme", version="1.0") - >>> dirs.user_data_dir - '/Users/trentm/Library/Application Support/SuperApp/1.0' - -- [Windows] Cherry-pick Komodo's change to downgrade paths to the Windows short - paths if there are high bit chars. -- [Linux] Change default ``user_cache_dir()`` on Linux to be singular, e.g. - "~/.superapp/cache". -- [Windows] Add ``roaming`` option to ``user_data_dir()`` (for use on Windows only) - and change the default ``user_data_dir`` behaviour to use a *non*-roaming - profile dir (``CSIDL_LOCAL_APPDATA`` instead of ``CSIDL_APPDATA``). Why? Because - a large roaming profile can cause login speed issues. The "only syncs on - logout" behaviour can cause surprises in appdata info. - - -appdirs 1.0.1 (never released) ------------------------------- - -Started this changelog 27 July 2010. Before that this module originated in the -`Komodo <http://www.activestate.com/komodo>`_ product as ``applib.py`` and then -as `applib/location.py -<http://github.com/ActiveState/applib/blob/master/applib/location.py>`_ (used by -`PyPM <http://code.activestate.com/pypm/>`_ in `ActivePython -<http://www.activestate.com/activepython>`_). This is basically a fork of -applib.py 1.0.1 and applib/location.py 1.0.1. - - - diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/METADATA b/pkg_resources/_vendor/appdirs-1.4.3.dist-info/METADATA deleted file mode 100644 index 69ddf934..00000000 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/METADATA +++ /dev/null @@ -1,254 +0,0 @@ -Metadata-Version: 2.0 -Name: appdirs -Version: 1.4.3 -Summary: A small Python module for determining appropriate platform-specific dirs, e.g. a "user data dir". -Home-page: http://github.com/ActiveState/appdirs -Author: Trent Mick; Sridhar Ratnakumar; Jeff Rouse -Author-email: trentm@gmail.com; github@srid.name; jr@its.to -License: MIT -Keywords: application directory log cache user -Platform: UNKNOWN -Classifier: Development Status :: 4 - Beta -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Operating System :: OS Independent -Classifier: Programming Language :: Python :: 2 -Classifier: Programming Language :: Python :: 2.6 -Classifier: Programming Language :: Python :: 2.7 -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3.2 -Classifier: Programming Language :: Python :: 3.3 -Classifier: Programming Language :: Python :: 3.4 -Classifier: Programming Language :: Python :: 3.5 -Classifier: Programming Language :: Python :: 3.6 -Classifier: Programming Language :: Python :: Implementation :: PyPy -Classifier: Programming Language :: Python :: Implementation :: CPython -Classifier: Topic :: Software Development :: Libraries :: Python Modules - - -.. image:: https://secure.travis-ci.org/ActiveState/appdirs.png - :target: http://travis-ci.org/ActiveState/appdirs - -the problem -=========== - -What directory should your app use for storing user data? If running on Mac OS X, you -should use:: - - ~/Library/Application Support/<AppName> - -If on Windows (at least English Win XP) that should be:: - - C:\Documents and Settings\<User>\Application Data\Local Settings\<AppAuthor>\<AppName> - -or possibly:: - - C:\Documents and Settings\<User>\Application Data\<AppAuthor>\<AppName> - -for `roaming profiles <http://bit.ly/9yl3b6>`_ but that is another story. - -On Linux (and other Unices) the dir, according to the `XDG -spec <http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html>`_, is:: - - ~/.local/share/<AppName> - - -``appdirs`` to the rescue -========================= - -This kind of thing is what the ``appdirs`` module is for. ``appdirs`` will -help you choose an appropriate: - -- user data dir (``user_data_dir``) -- user config dir (``user_config_dir``) -- user cache dir (``user_cache_dir``) -- site data dir (``site_data_dir``) -- site config dir (``site_config_dir``) -- user log dir (``user_log_dir``) - -and also: - -- is a single module so other Python packages can include their own private copy -- is slightly opinionated on the directory names used. Look for "OPINION" in - documentation and code for when an opinion is being applied. - - -some example output -=================== - -On Mac OS X:: - - >>> from appdirs import * - >>> appname = "SuperApp" - >>> appauthor = "Acme" - >>> user_data_dir(appname, appauthor) - '/Users/trentm/Library/Application Support/SuperApp' - >>> site_data_dir(appname, appauthor) - '/Library/Application Support/SuperApp' - >>> user_cache_dir(appname, appauthor) - '/Users/trentm/Library/Caches/SuperApp' - >>> user_log_dir(appname, appauthor) - '/Users/trentm/Library/Logs/SuperApp' - -On Windows 7:: - - >>> from appdirs import * - >>> appname = "SuperApp" - >>> appauthor = "Acme" - >>> user_data_dir(appname, appauthor) - 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp' - >>> user_data_dir(appname, appauthor, roaming=True) - 'C:\\Users\\trentm\\AppData\\Roaming\\Acme\\SuperApp' - >>> user_cache_dir(appname, appauthor) - 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Cache' - >>> user_log_dir(appname, appauthor) - 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Logs' - -On Linux:: - - >>> from appdirs import * - >>> appname = "SuperApp" - >>> appauthor = "Acme" - >>> user_data_dir(appname, appauthor) - '/home/trentm/.local/share/SuperApp - >>> site_data_dir(appname, appauthor) - '/usr/local/share/SuperApp' - >>> site_data_dir(appname, appauthor, multipath=True) - '/usr/local/share/SuperApp:/usr/share/SuperApp' - >>> user_cache_dir(appname, appauthor) - '/home/trentm/.cache/SuperApp' - >>> user_log_dir(appname, appauthor) - '/home/trentm/.cache/SuperApp/log' - >>> user_config_dir(appname) - '/home/trentm/.config/SuperApp' - >>> site_config_dir(appname) - '/etc/xdg/SuperApp' - >>> os.environ['XDG_CONFIG_DIRS'] = '/etc:/usr/local/etc' - >>> site_config_dir(appname, multipath=True) - '/etc/SuperApp:/usr/local/etc/SuperApp' - - -``AppDirs`` for convenience -=========================== - -:: - - >>> from appdirs import AppDirs - >>> dirs = AppDirs("SuperApp", "Acme") - >>> dirs.user_data_dir - '/Users/trentm/Library/Application Support/SuperApp' - >>> dirs.site_data_dir - '/Library/Application Support/SuperApp' - >>> dirs.user_cache_dir - '/Users/trentm/Library/Caches/SuperApp' - >>> dirs.user_log_dir - '/Users/trentm/Library/Logs/SuperApp' - - - -Per-version isolation -===================== - -If you have multiple versions of your app in use that you want to be -able to run side-by-side, then you may want version-isolation for these -dirs:: - - >>> from appdirs import AppDirs - >>> dirs = AppDirs("SuperApp", "Acme", version="1.0") - >>> dirs.user_data_dir - '/Users/trentm/Library/Application Support/SuperApp/1.0' - >>> dirs.site_data_dir - '/Library/Application Support/SuperApp/1.0' - >>> dirs.user_cache_dir - '/Users/trentm/Library/Caches/SuperApp/1.0' - >>> dirs.user_log_dir - '/Users/trentm/Library/Logs/SuperApp/1.0' - - - -appdirs Changelog -================= - -appdirs 1.4.3 -------------- -- [PR #76] Python 3.6 invalid escape sequence deprecation fixes -- Fix for Python 3.6 support - -appdirs 1.4.2 -------------- -- [PR #84] Allow installing without setuptools -- [PR #86] Fix string delimiters in setup.py description -- Add Python 3.6 support - -appdirs 1.4.1 -------------- -- [issue #38] Fix _winreg import on Windows Py3 -- [issue #55] Make appname optional - -appdirs 1.4.0 -------------- -- [PR #42] AppAuthor is now optional on Windows -- [issue 41] Support Jython on Windows, Mac, and Unix-like platforms. Windows - support requires `JNA <https://github.com/twall/jna>`_. -- [PR #44] Fix incorrect behaviour of the site_config_dir method - -appdirs 1.3.0 -------------- -- [Unix, issue 16] Conform to XDG standard, instead of breaking it for - everybody -- [Unix] Removes gratuitous case mangling of the case, since \*nix-es are - usually case sensitive, so mangling is not wise -- [Unix] Fixes the utterly wrong behaviour in ``site_data_dir``, return result - based on XDG_DATA_DIRS and make room for respecting the standard which - specifies XDG_DATA_DIRS is a multiple-value variable -- [Issue 6] Add ``*_config_dir`` which are distinct on nix-es, according to - XDG specs; on Windows and Mac return the corresponding ``*_data_dir`` - -appdirs 1.2.0 -------------- - -- [Unix] Put ``user_log_dir`` under the *cache* dir on Unix. Seems to be more - typical. -- [issue 9] Make ``unicode`` work on py3k. - -appdirs 1.1.0 -------------- - -- [issue 4] Add ``AppDirs.user_log_dir``. -- [Unix, issue 2, issue 7] appdirs now conforms to `XDG base directory spec - <http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html>`_. -- [Mac, issue 5] Fix ``site_data_dir()`` on Mac. -- [Mac] Drop use of 'Carbon' module in favour of hardcoded paths; supports - Python3 now. -- [Windows] Append "Cache" to ``user_cache_dir`` on Windows by default. Use - ``opinion=False`` option to disable this. -- Add ``appdirs.AppDirs`` convenience class. Usage: - - >>> dirs = AppDirs("SuperApp", "Acme", version="1.0") - >>> dirs.user_data_dir - '/Users/trentm/Library/Application Support/SuperApp/1.0' - -- [Windows] Cherry-pick Komodo's change to downgrade paths to the Windows short - paths if there are high bit chars. -- [Linux] Change default ``user_cache_dir()`` on Linux to be singular, e.g. - "~/.superapp/cache". -- [Windows] Add ``roaming`` option to ``user_data_dir()`` (for use on Windows only) - and change the default ``user_data_dir`` behaviour to use a *non*-roaming - profile dir (``CSIDL_LOCAL_APPDATA`` instead of ``CSIDL_APPDATA``). Why? Because - a large roaming profile can cause login speed issues. The "only syncs on - logout" behaviour can cause surprises in appdata info. - - -appdirs 1.0.1 (never released) ------------------------------- - -Started this changelog 27 July 2010. Before that this module originated in the -`Komodo <http://www.activestate.com/komodo>`_ product as ``applib.py`` and then -as `applib/location.py -<http://github.com/ActiveState/applib/blob/master/applib/location.py>`_ (used by -`PyPM <http://code.activestate.com/pypm/>`_ in `ActivePython -<http://www.activestate.com/activepython>`_). This is basically a fork of -applib.py 1.0.1 and applib/location.py 1.0.1. - - - diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/RECORD b/pkg_resources/_vendor/appdirs-1.4.3.dist-info/RECORD deleted file mode 100644 index 3f45ff59..00000000 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/RECORD +++ /dev/null @@ -1,10 +0,0 @@ -__pycache__/appdirs.cpython-310.pyc,,
-appdirs-1.4.3.dist-info/DESCRIPTION.rst,sha256=77Fe8OIOLSjDSNdLiL5xywMKO-AGE42rdXkqKo4Ee-k,7531
-appdirs-1.4.3.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-appdirs-1.4.3.dist-info/METADATA,sha256=3IFw6jTfImdOqsCb2GYvVR157tL7KEzfRAszn382csk,8773
-appdirs-1.4.3.dist-info/RECORD,,
-appdirs-1.4.3.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-appdirs-1.4.3.dist-info/WHEEL,sha256=o2k-Qa-RMNIJmUdIc7KU6VWR_ErNRbWNlxDIpl7lm34,110
-appdirs-1.4.3.dist-info/metadata.json,sha256=fL_Q-GuFJu3PJxMrwU7SdsI8RGqjIfi2AvouCSF5DSA,1359
-appdirs-1.4.3.dist-info/top_level.txt,sha256=nKncE8CUqZERJ6VuQWL4_bkunSPDNfn7KZqb4Tr5YEM,8
-appdirs.py,sha256=MievUEuv3l_mQISH5SF0shDk_BNhHHzYiAPrT3ITN4I,24701
diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/WHEEL b/pkg_resources/_vendor/appdirs-1.4.3.dist-info/WHEEL deleted file mode 100644 index 8b6dd1b5..00000000 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/WHEEL +++ /dev/null @@ -1,6 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.29.0) -Root-Is-Purelib: true -Tag: py2-none-any -Tag: py3-none-any - diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/metadata.json b/pkg_resources/_vendor/appdirs-1.4.3.dist-info/metadata.json deleted file mode 100644 index da1e5f3a..00000000 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"classifiers": ["Development Status :: 4 - Beta", "Intended Audience :: Developers", "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python :: 2", "Programming Language :: Python :: 2.6", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.2", "Programming Language :: Python :: 3.3", "Programming Language :: Python :: 3.4", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: Implementation :: PyPy", "Programming Language :: Python :: Implementation :: CPython", "Topic :: Software Development :: Libraries :: Python Modules"], "extensions": {"python.details": {"contacts": [{"email": "trentm@gmail.com; github@srid.name; jr@its.to", "name": "Trent Mick; Sridhar Ratnakumar; Jeff Rouse", "role": "author"}], "document_names": {"description": "DESCRIPTION.rst"}, "project_urls": {"Home": "http://github.com/ActiveState/appdirs"}}}, "generator": "bdist_wheel (0.29.0)", "keywords": ["application", "directory", "log", "cache", "user"], "license": "MIT", "metadata_version": "2.0", "name": "appdirs", "summary": "A small Python module for determining appropriate platform-specific dirs, e.g. a \"user data dir\".", "test_requires": [{"requires": []}], "version": "1.4.3"}
\ No newline at end of file diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/top_level.txt b/pkg_resources/_vendor/appdirs-1.4.3.dist-info/top_level.txt deleted file mode 100644 index d64bc321..00000000 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -appdirs diff --git a/pkg_resources/_vendor/appdirs.py b/pkg_resources/_vendor/appdirs.py deleted file mode 100644 index ae67001a..00000000 --- a/pkg_resources/_vendor/appdirs.py +++ /dev/null @@ -1,608 +0,0 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- -# Copyright (c) 2005-2010 ActiveState Software Inc. -# Copyright (c) 2013 Eddy Petrișor - -"""Utilities for determining application-specific dirs. - -See <http://github.com/ActiveState/appdirs> for details and usage. -""" -# Dev Notes: -# - MSDN on where to store app data files: -# http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120 -# - Mac OS X: http://developer.apple.com/documentation/MacOSX/Conceptual/BPFileSystem/index.html -# - XDG spec for Un*x: http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html - -__version_info__ = (1, 4, 3) -__version__ = '.'.join(map(str, __version_info__)) - - -import sys -import os - -PY3 = sys.version_info[0] == 3 - -if PY3: - unicode = str - -if sys.platform.startswith('java'): - import platform - os_name = platform.java_ver()[3][0] - if os_name.startswith('Windows'): # "Windows XP", "Windows 7", etc. - system = 'win32' - elif os_name.startswith('Mac'): # "Mac OS X", etc. - system = 'darwin' - else: # "Linux", "SunOS", "FreeBSD", etc. - # Setting this to "linux2" is not ideal, but only Windows or Mac - # are actually checked for and the rest of the module expects - # *sys.platform* style strings. - system = 'linux2' -else: - system = sys.platform - - - -def user_data_dir(appname=None, appauthor=None, version=None, roaming=False): - r"""Return full path to the user-specific data dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "roaming" (boolean, default False) can be set True to use the Windows - roaming appdata directory. That means that for users on a Windows - network setup for roaming profiles, this user data will be - sync'd on login. See - <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> - for a discussion of issues. - - Typical user data directories are: - Mac OS X: ~/Library/Application Support/<AppName> - Unix: ~/.local/share/<AppName> # or in $XDG_DATA_HOME, if defined - Win XP (not roaming): C:\Documents and Settings\<username>\Application Data\<AppAuthor>\<AppName> - Win XP (roaming): C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName> - Win 7 (not roaming): C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName> - Win 7 (roaming): C:\Users\<username>\AppData\Roaming\<AppAuthor>\<AppName> - - For Unix, we follow the XDG spec and support $XDG_DATA_HOME. - That means, by default "~/.local/share/<AppName>". - """ - if system == "win32": - if appauthor is None: - appauthor = appname - const = roaming and "CSIDL_APPDATA" or "CSIDL_LOCAL_APPDATA" - path = os.path.normpath(_get_win_folder(const)) - if appname: - if appauthor is not False: - path = os.path.join(path, appauthor, appname) - else: - path = os.path.join(path, appname) - elif system == 'darwin': - path = os.path.expanduser('~/Library/Application Support/') - if appname: - path = os.path.join(path, appname) - else: - path = os.getenv('XDG_DATA_HOME', os.path.expanduser("~/.local/share")) - if appname: - path = os.path.join(path, appname) - if appname and version: - path = os.path.join(path, version) - return path - - -def site_data_dir(appname=None, appauthor=None, version=None, multipath=False): - r"""Return full path to the user-shared data dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "multipath" is an optional parameter only applicable to *nix - which indicates that the entire list of data dirs should be - returned. By default, the first item from XDG_DATA_DIRS is - returned, or '/usr/local/share/<AppName>', - if XDG_DATA_DIRS is not set - - Typical site data directories are: - Mac OS X: /Library/Application Support/<AppName> - Unix: /usr/local/share/<AppName> or /usr/share/<AppName> - Win XP: C:\Documents and Settings\All Users\Application Data\<AppAuthor>\<AppName> - Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.) - Win 7: C:\ProgramData\<AppAuthor>\<AppName> # Hidden, but writeable on Win 7. - - For Unix, this is using the $XDG_DATA_DIRS[0] default. - - WARNING: Do not use this on Windows. See the Vista-Fail note above for why. - """ - if system == "win32": - if appauthor is None: - appauthor = appname - path = os.path.normpath(_get_win_folder("CSIDL_COMMON_APPDATA")) - if appname: - if appauthor is not False: - path = os.path.join(path, appauthor, appname) - else: - path = os.path.join(path, appname) - elif system == 'darwin': - path = os.path.expanduser('/Library/Application Support') - if appname: - path = os.path.join(path, appname) - else: - # XDG default for $XDG_DATA_DIRS - # only first, if multipath is False - path = os.getenv('XDG_DATA_DIRS', - os.pathsep.join(['/usr/local/share', '/usr/share'])) - pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)] - if appname: - if version: - appname = os.path.join(appname, version) - pathlist = [os.sep.join([x, appname]) for x in pathlist] - - if multipath: - path = os.pathsep.join(pathlist) - else: - path = pathlist[0] - return path - - if appname and version: - path = os.path.join(path, version) - return path - - -def user_config_dir(appname=None, appauthor=None, version=None, roaming=False): - r"""Return full path to the user-specific config dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "roaming" (boolean, default False) can be set True to use the Windows - roaming appdata directory. That means that for users on a Windows - network setup for roaming profiles, this user data will be - sync'd on login. See - <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> - for a discussion of issues. - - Typical user config directories are: - Mac OS X: same as user_data_dir - Unix: ~/.config/<AppName> # or in $XDG_CONFIG_HOME, if defined - Win *: same as user_data_dir - - For Unix, we follow the XDG spec and support $XDG_CONFIG_HOME. - That means, by default "~/.config/<AppName>". - """ - if system in ["win32", "darwin"]: - path = user_data_dir(appname, appauthor, None, roaming) - else: - path = os.getenv('XDG_CONFIG_HOME', os.path.expanduser("~/.config")) - if appname: - path = os.path.join(path, appname) - if appname and version: - path = os.path.join(path, version) - return path - - -def site_config_dir(appname=None, appauthor=None, version=None, multipath=False): - r"""Return full path to the user-shared data dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "multipath" is an optional parameter only applicable to *nix - which indicates that the entire list of config dirs should be - returned. By default, the first item from XDG_CONFIG_DIRS is - returned, or '/etc/xdg/<AppName>', if XDG_CONFIG_DIRS is not set - - Typical site config directories are: - Mac OS X: same as site_data_dir - Unix: /etc/xdg/<AppName> or $XDG_CONFIG_DIRS[i]/<AppName> for each value in - $XDG_CONFIG_DIRS - Win *: same as site_data_dir - Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.) - - For Unix, this is using the $XDG_CONFIG_DIRS[0] default, if multipath=False - - WARNING: Do not use this on Windows. See the Vista-Fail note above for why. - """ - if system in ["win32", "darwin"]: - path = site_data_dir(appname, appauthor) - if appname and version: - path = os.path.join(path, version) - else: - # XDG default for $XDG_CONFIG_DIRS - # only first, if multipath is False - path = os.getenv('XDG_CONFIG_DIRS', '/etc/xdg') - pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)] - if appname: - if version: - appname = os.path.join(appname, version) - pathlist = [os.sep.join([x, appname]) for x in pathlist] - - if multipath: - path = os.pathsep.join(pathlist) - else: - path = pathlist[0] - return path - - -def user_cache_dir(appname=None, appauthor=None, version=None, opinion=True): - r"""Return full path to the user-specific cache dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "opinion" (boolean) can be False to disable the appending of - "Cache" to the base app data dir for Windows. See - discussion below. - - Typical user cache directories are: - Mac OS X: ~/Library/Caches/<AppName> - Unix: ~/.cache/<AppName> (XDG default) - Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Cache - Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Cache - - On Windows the only suggestion in the MSDN docs is that local settings go in - the `CSIDL_LOCAL_APPDATA` directory. This is identical to the non-roaming - app data dir (the default returned by `user_data_dir` above). Apps typically - put cache data somewhere *under* the given dir here. Some examples: - ...\Mozilla\Firefox\Profiles\<ProfileName>\Cache - ...\Acme\SuperApp\Cache\1.0 - OPINION: This function appends "Cache" to the `CSIDL_LOCAL_APPDATA` value. - This can be disabled with the `opinion=False` option. - """ - if system == "win32": - if appauthor is None: - appauthor = appname - path = os.path.normpath(_get_win_folder("CSIDL_LOCAL_APPDATA")) - if appname: - if appauthor is not False: - path = os.path.join(path, appauthor, appname) - else: - path = os.path.join(path, appname) - if opinion: - path = os.path.join(path, "Cache") - elif system == 'darwin': - path = os.path.expanduser('~/Library/Caches') - if appname: - path = os.path.join(path, appname) - else: - path = os.getenv('XDG_CACHE_HOME', os.path.expanduser('~/.cache')) - if appname: - path = os.path.join(path, appname) - if appname and version: - path = os.path.join(path, version) - return path - - -def user_state_dir(appname=None, appauthor=None, version=None, roaming=False): - r"""Return full path to the user-specific state dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "roaming" (boolean, default False) can be set True to use the Windows - roaming appdata directory. That means that for users on a Windows - network setup for roaming profiles, this user data will be - sync'd on login. See - <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> - for a discussion of issues. - - Typical user state directories are: - Mac OS X: same as user_data_dir - Unix: ~/.local/state/<AppName> # or in $XDG_STATE_HOME, if defined - Win *: same as user_data_dir - - For Unix, we follow this Debian proposal <https://wiki.debian.org/XDGBaseDirectorySpecification#state> - to extend the XDG spec and support $XDG_STATE_HOME. - - That means, by default "~/.local/state/<AppName>". - """ - if system in ["win32", "darwin"]: - path = user_data_dir(appname, appauthor, None, roaming) - else: - path = os.getenv('XDG_STATE_HOME', os.path.expanduser("~/.local/state")) - if appname: - path = os.path.join(path, appname) - if appname and version: - path = os.path.join(path, version) - return path - - -def user_log_dir(appname=None, appauthor=None, version=None, opinion=True): - r"""Return full path to the user-specific log dir for this application. - - "appname" is the name of application. - If None, just the system directory is returned. - "appauthor" (only used on Windows) is the name of the - appauthor or distributing body for this application. Typically - it is the owning company name. This falls back to appname. You may - pass False to disable it. - "version" is an optional version path element to append to the - path. You might want to use this if you want multiple versions - of your app to be able to run independently. If used, this - would typically be "<major>.<minor>". - Only applied when appname is present. - "opinion" (boolean) can be False to disable the appending of - "Logs" to the base app data dir for Windows, and "log" to the - base cache dir for Unix. See discussion below. - - Typical user log directories are: - Mac OS X: ~/Library/Logs/<AppName> - Unix: ~/.cache/<AppName>/log # or under $XDG_CACHE_HOME if defined - Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Logs - Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Logs - - On Windows the only suggestion in the MSDN docs is that local settings - go in the `CSIDL_LOCAL_APPDATA` directory. (Note: I'm interested in - examples of what some windows apps use for a logs dir.) - - OPINION: This function appends "Logs" to the `CSIDL_LOCAL_APPDATA` - value for Windows and appends "log" to the user cache dir for Unix. - This can be disabled with the `opinion=False` option. - """ - if system == "darwin": - path = os.path.join( - os.path.expanduser('~/Library/Logs'), - appname) - elif system == "win32": - path = user_data_dir(appname, appauthor, version) - version = False - if opinion: - path = os.path.join(path, "Logs") - else: - path = user_cache_dir(appname, appauthor, version) - version = False - if opinion: - path = os.path.join(path, "log") - if appname and version: - path = os.path.join(path, version) - return path - - -class AppDirs(object): - """Convenience wrapper for getting application dirs.""" - def __init__(self, appname=None, appauthor=None, version=None, - roaming=False, multipath=False): - self.appname = appname - self.appauthor = appauthor - self.version = version - self.roaming = roaming - self.multipath = multipath - - @property - def user_data_dir(self): - return user_data_dir(self.appname, self.appauthor, - version=self.version, roaming=self.roaming) - - @property - def site_data_dir(self): - return site_data_dir(self.appname, self.appauthor, - version=self.version, multipath=self.multipath) - - @property - def user_config_dir(self): - return user_config_dir(self.appname, self.appauthor, - version=self.version, roaming=self.roaming) - - @property - def site_config_dir(self): - return site_config_dir(self.appname, self.appauthor, - version=self.version, multipath=self.multipath) - - @property - def user_cache_dir(self): - return user_cache_dir(self.appname, self.appauthor, - version=self.version) - - @property - def user_state_dir(self): - return user_state_dir(self.appname, self.appauthor, - version=self.version) - - @property - def user_log_dir(self): - return user_log_dir(self.appname, self.appauthor, - version=self.version) - - -#---- internal support stuff - -def _get_win_folder_from_registry(csidl_name): - """This is a fallback technique at best. I'm not sure if using the - registry for this guarantees us the correct answer for all CSIDL_* - names. - """ - if PY3: - import winreg as _winreg - else: - import _winreg - - shell_folder_name = { - "CSIDL_APPDATA": "AppData", - "CSIDL_COMMON_APPDATA": "Common AppData", - "CSIDL_LOCAL_APPDATA": "Local AppData", - }[csidl_name] - - key = _winreg.OpenKey( - _winreg.HKEY_CURRENT_USER, - r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders" - ) - dir, type = _winreg.QueryValueEx(key, shell_folder_name) - return dir - - -def _get_win_folder_with_pywin32(csidl_name): - from win32com.shell import shellcon, shell - dir = shell.SHGetFolderPath(0, getattr(shellcon, csidl_name), 0, 0) - # Try to make this a unicode path because SHGetFolderPath does - # not return unicode strings when there is unicode data in the - # path. - try: - dir = unicode(dir) - - # Downgrade to short path name if have highbit chars. See - # <http://bugs.activestate.com/show_bug.cgi?id=85099>. - has_high_char = False - for c in dir: - if ord(c) > 255: - has_high_char = True - break - if has_high_char: - try: - import win32api - dir = win32api.GetShortPathName(dir) - except ImportError: - pass - except UnicodeError: - pass - return dir - - -def _get_win_folder_with_ctypes(csidl_name): - import ctypes - - csidl_const = { - "CSIDL_APPDATA": 26, - "CSIDL_COMMON_APPDATA": 35, - "CSIDL_LOCAL_APPDATA": 28, - }[csidl_name] - - buf = ctypes.create_unicode_buffer(1024) - ctypes.windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf) - - # Downgrade to short path name if have highbit chars. See - # <http://bugs.activestate.com/show_bug.cgi?id=85099>. - has_high_char = False - for c in buf: - if ord(c) > 255: - has_high_char = True - break - if has_high_char: - buf2 = ctypes.create_unicode_buffer(1024) - if ctypes.windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024): - buf = buf2 - - return buf.value - -def _get_win_folder_with_jna(csidl_name): - import array - from com.sun import jna - from com.sun.jna.platform import win32 - - buf_size = win32.WinDef.MAX_PATH * 2 - buf = array.zeros('c', buf_size) - shell = win32.Shell32.INSTANCE - shell.SHGetFolderPath(None, getattr(win32.ShlObj, csidl_name), None, win32.ShlObj.SHGFP_TYPE_CURRENT, buf) - dir = jna.Native.toString(buf.tostring()).rstrip("\0") - - # Downgrade to short path name if have highbit chars. See - # <http://bugs.activestate.com/show_bug.cgi?id=85099>. - has_high_char = False - for c in dir: - if ord(c) > 255: - has_high_char = True - break - if has_high_char: - buf = array.zeros('c', buf_size) - kernel = win32.Kernel32.INSTANCE - if kernel.GetShortPathName(dir, buf, buf_size): - dir = jna.Native.toString(buf.tostring()).rstrip("\0") - - return dir - -if system == "win32": - try: - import win32com.shell - _get_win_folder = _get_win_folder_with_pywin32 - except ImportError: - try: - from ctypes import windll - _get_win_folder = _get_win_folder_with_ctypes - except ImportError: - try: - import com.sun.jna - _get_win_folder = _get_win_folder_with_jna - except ImportError: - _get_win_folder = _get_win_folder_from_registry - - -#---- self test code - -if __name__ == "__main__": - appname = "MyApp" - appauthor = "MyCompany" - - props = ("user_data_dir", - "user_config_dir", - "user_cache_dir", - "user_state_dir", - "user_log_dir", - "site_data_dir", - "site_config_dir") - - print("-- app dirs %s --" % __version__) - - print("-- app dirs (with optional 'version')") - dirs = AppDirs(appname, appauthor, version="1.0") - for prop in props: - print("%s: %s" % (prop, getattr(dirs, prop))) - - print("\n-- app dirs (without optional 'version')") - dirs = AppDirs(appname, appauthor) - for prop in props: - print("%s: %s" % (prop, getattr(dirs, prop))) - - print("\n-- app dirs (without optional 'appauthor')") - dirs = AppDirs(appname) - for prop in props: - print("%s: %s" % (prop, getattr(dirs, prop))) - - print("\n-- app dirs (with disabled 'appauthor')") - dirs = AppDirs(appname, appauthor=False) - for prop in props: - print("%s: %s" % (prop, getattr(dirs, prop))) diff --git a/pkg_resources/_vendor/importlib_resources-5.4.0.dist-info/RECORD b/pkg_resources/_vendor/importlib_resources-5.4.0.dist-info/RECORD index 7a68a2f2..7f579ddb 100644 --- a/pkg_resources/_vendor/importlib_resources-5.4.0.dist-info/RECORD +++ b/pkg_resources/_vendor/importlib_resources-5.4.0.dist-info/RECORD @@ -6,15 +6,15 @@ importlib_resources-5.4.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeR importlib_resources-5.4.0.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
importlib_resources-5.4.0.dist-info/top_level.txt,sha256=fHIjHU1GZwAjvcydpmUnUrTnbvdiWjG4OEVZK8by0TQ,20
importlib_resources/__init__.py,sha256=zuA0lbRgtVVCcAztM0z5LuBiOCV9L_3qtI6mW2p5xAg,525
-importlib_resources/__pycache__/__init__.cpython-310.pyc,,
-importlib_resources/__pycache__/_adapters.cpython-310.pyc,,
-importlib_resources/__pycache__/_common.cpython-310.pyc,,
-importlib_resources/__pycache__/_compat.cpython-310.pyc,,
-importlib_resources/__pycache__/_itertools.cpython-310.pyc,,
-importlib_resources/__pycache__/_legacy.cpython-310.pyc,,
-importlib_resources/__pycache__/abc.cpython-310.pyc,,
-importlib_resources/__pycache__/readers.cpython-310.pyc,,
-importlib_resources/__pycache__/simple.cpython-310.pyc,,
+importlib_resources/__pycache__/__init__.cpython-311.pyc,,
+importlib_resources/__pycache__/_adapters.cpython-311.pyc,,
+importlib_resources/__pycache__/_common.cpython-311.pyc,,
+importlib_resources/__pycache__/_compat.cpython-311.pyc,,
+importlib_resources/__pycache__/_itertools.cpython-311.pyc,,
+importlib_resources/__pycache__/_legacy.cpython-311.pyc,,
+importlib_resources/__pycache__/abc.cpython-311.pyc,,
+importlib_resources/__pycache__/readers.cpython-311.pyc,,
+importlib_resources/__pycache__/simple.cpython-311.pyc,,
importlib_resources/_adapters.py,sha256=o51tP2hpVtohP33gSYyAkGNpLfYDBqxxYsadyiRZi1E,4504
importlib_resources/_common.py,sha256=iIxAaQhotSh6TLLUEfL_ynU2fzEeyHMz9JcL46mUhLg,2741
importlib_resources/_compat.py,sha256=3LpkIfeN9x4oXjRea5TxZP5VYhPlzuVRhGe-hEv-S0s,2704
@@ -25,34 +25,34 @@ importlib_resources/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU, importlib_resources/readers.py,sha256=_9QLGQ5AzrED3PY8S2Zf8V6yLR0-nqqYqtQmgleDJzY,3566
importlib_resources/simple.py,sha256=xt0qhXbwt3bZ86zuaaKbTiE9A0mDbwu0saRjUq_pcY0,2836
importlib_resources/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/__pycache__/__init__.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/_compat.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_compatibilty_files.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_contents.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_files.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_open.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_path.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_read.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_reader.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/test_resource.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/update-zips.cpython-310.pyc,,
-importlib_resources/tests/__pycache__/util.cpython-310.pyc,,
+importlib_resources/tests/__pycache__/__init__.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/_compat.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_compatibilty_files.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_contents.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_files.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_open.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_path.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_read.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_reader.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/test_resource.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/update-zips.cpython-311.pyc,,
+importlib_resources/tests/__pycache__/util.cpython-311.pyc,,
importlib_resources/tests/_compat.py,sha256=QGI_4p0DXybypoYvw0kr3jfQqvls3p8u4wy4Wvf0Z_o,435
importlib_resources/tests/data01/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/data01/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/data01/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/data01/binary.file,sha256=BU7ewdAhH2JP7Qy8qdT5QAsOSRxDdCryxbCr6_DJkNg,4
importlib_resources/tests/data01/subdirectory/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/data01/subdirectory/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/data01/subdirectory/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/data01/subdirectory/binary.file,sha256=BU7ewdAhH2JP7Qy8qdT5QAsOSRxDdCryxbCr6_DJkNg,4
importlib_resources/tests/data01/utf-16.file,sha256=t5q9qhxX0rYqItBOM8D3ylwG-RHrnOYteTLtQr6sF7g,44
importlib_resources/tests/data01/utf-8.file,sha256=kwWgYG4yQ-ZF2X_WA66EjYPmxJRn-w8aSOiS9e8tKYY,20
importlib_resources/tests/data02/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/data02/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/data02/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/data02/one/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/data02/one/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/data02/one/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/data02/one/resource1.txt,sha256=10flKac7c-XXFzJ3t-AB5MJjlBy__dSZvPE_dOm2q6U,13
importlib_resources/tests/data02/two/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/data02/two/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/data02/two/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/data02/two/resource2.txt,sha256=lt2jbN3TMn9QiFKM832X39bU_62UptDdUkoYzkvEbl0,13
importlib_resources/tests/namespacedata01/binary.file,sha256=BU7ewdAhH2JP7Qy8qdT5QAsOSRxDdCryxbCr6_DJkNg,4
importlib_resources/tests/namespacedata01/utf-16.file,sha256=t5q9qhxX0rYqItBOM8D3ylwG-RHrnOYteTLtQr6sF7g,44
@@ -68,8 +68,8 @@ importlib_resources/tests/test_resource.py,sha256=DqfLNc9kaN5obqxU8kn0sRUWMf9Myg importlib_resources/tests/update-zips.py,sha256=x3iJVqWnMM5qp4Oob2Pl3o6Yi03sUjEv_5Wf-UCg3ps,1415
importlib_resources/tests/util.py,sha256=X1j-0C96pu3_tmtJuLhzfBfcfMenOphDLkxtCt5j7t4,5309
importlib_resources/tests/zipdata01/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/zipdata01/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/zipdata01/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/zipdata01/ziptestdata.zip,sha256=z5Of4dsv3T0t-46B0MsVhxlhsPGMz28aUhJDWpj3_oY,876
importlib_resources/tests/zipdata02/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-importlib_resources/tests/zipdata02/__pycache__/__init__.cpython-310.pyc,,
+importlib_resources/tests/zipdata02/__pycache__/__init__.cpython-311.pyc,,
importlib_resources/tests/zipdata02/ziptestdata.zip,sha256=ydI-_j-xgQ7tDxqBp9cjOqXBGxUp6ZBbwVJu6Xj-nrY,698
diff --git a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/RECORD b/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/RECORD deleted file mode 100644 index f40d48c7..00000000 --- a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/RECORD +++ /dev/null @@ -1,8 +0,0 @@ -jaraco.context-4.1.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-jaraco.context-4.1.1.dist-info/LICENSE,sha256=2z8CRrH5J48VhFuZ_sR4uLUG63ZIeZNyL4xuJUKF-vg,1050
-jaraco.context-4.1.1.dist-info/METADATA,sha256=bvqDGCk6Z7TkohUqr5XZm19SbF9mVxrtXjN6uF_BAMQ,2031
-jaraco.context-4.1.1.dist-info/RECORD,,
-jaraco.context-4.1.1.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
-jaraco.context-4.1.1.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7
-jaraco/__pycache__/context.cpython-310.pyc,,
-jaraco/context.py,sha256=7X1tpCLc5EN45iWGzGcsH0Unx62REIkvtRvglj0SiUA,5420
diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/INSTALLER b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/INSTALLER index a1b589e3..a1b589e3 100644 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/INSTALLER +++ b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/INSTALLER diff --git a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/LICENSE b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/LICENSE index 353924be..353924be 100644 --- a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/LICENSE +++ b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/LICENSE diff --git a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/METADATA b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/METADATA index 908711b7..34d372e7 100644 --- a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/METADATA +++ b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/METADATA @@ -1,39 +1,37 @@ Metadata-Version: 2.1 Name: jaraco.context -Version: 4.1.1 +Version: 4.2.0 Summary: Context managers by jaraco Home-page: https://github.com/jaraco/jaraco.context Author: Jason R. Coombs Author-email: jaraco@jaraco.com -License: UNKNOWN -Platform: UNKNOWN Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: MIT License Classifier: Programming Language :: Python :: 3 Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.6 +Requires-Python: >=3.7 License-File: LICENSE Provides-Extra: docs -Requires-Dist: sphinx ; extra == 'docs' -Requires-Dist: jaraco.packaging (>=8.2) ; extra == 'docs' +Requires-Dist: sphinx (>=3.5) ; extra == 'docs' +Requires-Dist: jaraco.packaging (>=9) ; extra == 'docs' Requires-Dist: rst.linker (>=1.9) ; extra == 'docs' +Requires-Dist: furo ; extra == 'docs' +Requires-Dist: jaraco.tidelift (>=1.4) ; extra == 'docs' Provides-Extra: testing Requires-Dist: pytest (>=6) ; extra == 'testing' Requires-Dist: pytest-checkdocs (>=2.4) ; extra == 'testing' Requires-Dist: pytest-flake8 ; extra == 'testing' +Requires-Dist: flake8 (<5) ; extra == 'testing' Requires-Dist: pytest-cov ; extra == 'testing' -Requires-Dist: pytest-enabler (>=1.0.1) ; extra == 'testing' +Requires-Dist: pytest-enabler (>=1.3) ; extra == 'testing' Requires-Dist: pytest-black (>=0.3.7) ; (platform_python_implementation != "PyPy") and extra == 'testing' -Requires-Dist: pytest-mypy ; (platform_python_implementation != "PyPy") and extra == 'testing' +Requires-Dist: pytest-mypy (>=0.9.1) ; (platform_python_implementation != "PyPy") and extra == 'testing' .. image:: https://img.shields.io/pypi/v/jaraco.context.svg - :target: `PyPI link`_ + :target: https://pypi.org/project/jaraco.context .. image:: https://img.shields.io/pypi/pyversions/jaraco.context.svg - :target: `PyPI link`_ - -.. _PyPI link: https://pypi.org/project/jaraco.context .. image:: https://github.com/jaraco/jaraco.context/workflows/tests/badge.svg :target: https://github.com/jaraco/jaraco.context/actions?query=workflow%3A%22tests%22 @@ -46,7 +44,24 @@ Requires-Dist: pytest-mypy ; (platform_python_implementation != "PyPy") and extr .. image:: https://readthedocs.org/projects/jaracocontext/badge/?version=latest :target: https://jaracocontext.readthedocs.io/en/latest/?badge=latest -.. image:: https://img.shields.io/badge/skeleton-2021-informational +.. image:: https://img.shields.io/badge/skeleton-2022-informational :target: https://blog.jaraco.com/skeleton +.. image:: https://tidelift.com/badges/package/pypi/jaraco.context + :target: https://tidelift.com/subscription/pkg/pypi-jaraco.context?utm_source=pypi-jaraco.context&utm_medium=readme + +For Enterprise +============== + +Available as part of the Tidelift Subscription. + +This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. + +`Learn more <https://tidelift.com/subscription/pkg/pypi-jaraco.context?utm_source=pypi-jaraco.context&utm_medium=referral&utm_campaign=github>`_. + +Security Contact +================ +To report a security vulnerability, please use the +`Tidelift security contact <https://tidelift.com/security>`_. +Tidelift will coordinate the fix and disclosure. diff --git a/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/RECORD b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/RECORD new file mode 100644 index 00000000..a34ec80e --- /dev/null +++ b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/RECORD @@ -0,0 +1,8 @@ +jaraco.context-4.2.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+jaraco.context-4.2.0.dist-info/LICENSE,sha256=2z8CRrH5J48VhFuZ_sR4uLUG63ZIeZNyL4xuJUKF-vg,1050
+jaraco.context-4.2.0.dist-info/METADATA,sha256=6gWxpGoBWTzl4e8J1HisvNsL79YB4t1DG7ziQj-0k9Y,2883
+jaraco.context-4.2.0.dist-info/RECORD,,
+jaraco.context-4.2.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+jaraco.context-4.2.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7
+jaraco/__pycache__/context.cpython-311.pyc,,
+jaraco/context.py,sha256=NvdB7ArVCDrhtexOnOwSv4ScDuueGbf9LRiOSCqPn6Y,6488
diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/WHEEL b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/WHEEL index 5bad85fd..57e3d840 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/WHEEL +++ b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/WHEEL @@ -1,5 +1,5 @@ Wheel-Version: 1.0 -Generator: bdist_wheel (0.37.0) +Generator: bdist_wheel (0.38.4) Root-Is-Purelib: true Tag: py3-none-any diff --git a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/top_level.txt b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/top_level.txt index f6205a5f..f6205a5f 100644 --- a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/top_level.txt +++ b/pkg_resources/_vendor/jaraco.context-4.2.0.dist-info/top_level.txt diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/RECORD b/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/RECORD deleted file mode 100644 index fbda3d1f..00000000 --- a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/RECORD +++ /dev/null @@ -1,8 +0,0 @@ -jaraco.functools-3.5.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-jaraco.functools-3.5.0.dist-info/LICENSE,sha256=2z8CRrH5J48VhFuZ_sR4uLUG63ZIeZNyL4xuJUKF-vg,1050
-jaraco.functools-3.5.0.dist-info/METADATA,sha256=cE9C7u9bo_GjLAuw4nML67a25kUaPDiHn4j03lG4jd0,2276
-jaraco.functools-3.5.0.dist-info/RECORD,,
-jaraco.functools-3.5.0.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
-jaraco.functools-3.5.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7
-jaraco/__pycache__/functools.cpython-310.pyc,,
-jaraco/functools.py,sha256=PtEHbXZstgVJrwje4GvJOsz5pEbgslOcgEn2EJNpr2c,13494
diff --git a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/INSTALLER b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/INSTALLER index a1b589e3..a1b589e3 100644 --- a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/INSTALLER +++ b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/INSTALLER diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/LICENSE b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/LICENSE index 353924be..353924be 100644 --- a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/LICENSE +++ b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/LICENSE diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/METADATA b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/METADATA index 12dfbdd0..fa8f0211 100644 --- a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/METADATA +++ b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/METADATA @@ -1,12 +1,10 @@ Metadata-Version: 2.1 Name: jaraco.functools -Version: 3.5.0 +Version: 3.5.2 Summary: Functools like those found in stdlib Home-page: https://github.com/jaraco/jaraco.functools Author: Jason R. Coombs Author-email: jaraco@jaraco.com -License: UNKNOWN -Platform: UNKNOWN Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: MIT License @@ -16,18 +14,20 @@ Requires-Python: >=3.7 License-File: LICENSE Requires-Dist: more-itertools Provides-Extra: docs -Requires-Dist: sphinx ; extra == 'docs' -Requires-Dist: jaraco.packaging (>=8.2) ; extra == 'docs' +Requires-Dist: sphinx (>=3.5) ; extra == 'docs' +Requires-Dist: jaraco.packaging (>=9) ; extra == 'docs' Requires-Dist: rst.linker (>=1.9) ; extra == 'docs' +Requires-Dist: jaraco.tidelift (>=1.4) ; extra == 'docs' Provides-Extra: testing Requires-Dist: pytest (>=6) ; extra == 'testing' Requires-Dist: pytest-checkdocs (>=2.4) ; extra == 'testing' Requires-Dist: pytest-flake8 ; extra == 'testing' +Requires-Dist: flake8 (<5) ; extra == 'testing' Requires-Dist: pytest-cov ; extra == 'testing' -Requires-Dist: pytest-enabler (>=1.0.1) ; extra == 'testing' +Requires-Dist: pytest-enabler (>=1.3) ; extra == 'testing' Requires-Dist: jaraco.classes ; extra == 'testing' Requires-Dist: pytest-black (>=0.3.7) ; (platform_python_implementation != "PyPy") and extra == 'testing' -Requires-Dist: pytest-mypy ; (platform_python_implementation != "PyPy") and extra == 'testing' +Requires-Dist: pytest-mypy (>=0.9.1) ; (platform_python_implementation != "PyPy") and extra == 'testing' .. image:: https://img.shields.io/pypi/v/jaraco.functools.svg :target: `PyPI link`_ @@ -50,9 +50,26 @@ Requires-Dist: pytest-mypy ; (platform_python_implementation != "PyPy") and extr .. image:: https://readthedocs.org/projects/jaracofunctools/badge/?version=latest :target: https://jaracofunctools.readthedocs.io/en/latest/?badge=latest -.. image:: https://img.shields.io/badge/skeleton-2021-informational +.. image:: https://img.shields.io/badge/skeleton-2022-informational :target: https://blog.jaraco.com/skeleton +.. image:: https://tidelift.com/badges/package/pypi/jaraco.functools + :target: https://tidelift.com/subscription/pkg/pypi-jaraco.functools?utm_source=pypi-jaraco.functools&utm_medium=readme + Additional functools in the spirit of stdlib's functools. +For Enterprise +============== + +Available as part of the Tidelift Subscription. + +This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. + +`Learn more <https://tidelift.com/subscription/pkg/pypi-jaraco.functools?utm_source=pypi-jaraco.functools&utm_medium=referral&utm_campaign=github>`_. + +Security Contact +================ +To report a security vulnerability, please use the +`Tidelift security contact <https://tidelift.com/security>`_. +Tidelift will coordinate the fix and disclosure. diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/RECORD b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/RECORD new file mode 100644 index 00000000..127b8267 --- /dev/null +++ b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/RECORD @@ -0,0 +1,8 @@ +jaraco.functools-3.5.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+jaraco.functools-3.5.2.dist-info/LICENSE,sha256=2z8CRrH5J48VhFuZ_sR4uLUG63ZIeZNyL4xuJUKF-vg,1050
+jaraco.functools-3.5.2.dist-info/METADATA,sha256=ZIViwS4ZOmaWwA5ArwZ_xXQGR9WDnUSzx-0MO5kGPi8,3154
+jaraco.functools-3.5.2.dist-info/RECORD,,
+jaraco.functools-3.5.2.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+jaraco.functools-3.5.2.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7
+jaraco/__pycache__/functools.cpython-311.pyc,,
+jaraco/functools.py,sha256=PtEHbXZstgVJrwje4GvJOsz5pEbgslOcgEn2EJNpr2c,13494
diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/WHEEL b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/WHEEL index 5bad85fd..becc9a66 100644 --- a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/WHEEL +++ b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/WHEEL @@ -1,5 +1,5 @@ Wheel-Version: 1.0 -Generator: bdist_wheel (0.37.0) +Generator: bdist_wheel (0.37.1) Root-Is-Purelib: true Tag: py3-none-any diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/top_level.txt b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/top_level.txt index f6205a5f..f6205a5f 100644 --- a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/top_level.txt +++ b/pkg_resources/_vendor/jaraco.functools-3.5.2.dist-info/top_level.txt diff --git a/pkg_resources/_vendor/jaraco.text-3.7.0.dist-info/RECORD b/pkg_resources/_vendor/jaraco.text-3.7.0.dist-info/RECORD index 916ad7d3..dd471b07 100644 --- a/pkg_resources/_vendor/jaraco.text-3.7.0.dist-info/RECORD +++ b/pkg_resources/_vendor/jaraco.text-3.7.0.dist-info/RECORD @@ -7,4 +7,4 @@ jaraco.text-3.7.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FG jaraco.text-3.7.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7
jaraco/text/Lorem ipsum.txt,sha256=N_7c_79zxOufBY9HZ3yzMgOkNv-TkOTTio4BydrSjgs,1335
jaraco/text/__init__.py,sha256=I56MW2ZFwPrYXIxzqxMBe2A1t-T4uZBgEgAKe9-JoqM,15538
-jaraco/text/__pycache__/__init__.cpython-310.pyc,,
+jaraco/text/__pycache__/__init__.cpython-311.pyc,,
diff --git a/pkg_resources/_vendor/jaraco/context.py b/pkg_resources/_vendor/jaraco/context.py index 87a4e3dc..818f16f3 100644 --- a/pkg_resources/_vendor/jaraco/context.py +++ b/pkg_resources/_vendor/jaraco/context.py @@ -211,3 +211,43 @@ class suppress(contextlib.suppress, contextlib.ContextDecorator): ... {}[''] >>> key_error() """ + + +class on_interrupt(contextlib.ContextDecorator): + """ + Replace a KeyboardInterrupt with SystemExit(1) + + >>> def do_interrupt(): + ... raise KeyboardInterrupt() + >>> on_interrupt('error')(do_interrupt)() + Traceback (most recent call last): + ... + SystemExit: 1 + >>> on_interrupt('error', code=255)(do_interrupt)() + Traceback (most recent call last): + ... + SystemExit: 255 + >>> on_interrupt('suppress')(do_interrupt)() + >>> with __import__('pytest').raises(KeyboardInterrupt): + ... on_interrupt('ignore')(do_interrupt)() + """ + + def __init__( + self, + action='error', + # py3.7 compat + # /, + code=1, + ): + self.action = action + self.code = code + + def __enter__(self): + return self + + def __exit__(self, exctype, excinst, exctb): + if exctype is not KeyboardInterrupt or self.action == 'ignore': + return + elif self.action == 'error': + raise SystemExit(self.code) from excinst + return self.action == 'suppress' diff --git a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/RECORD b/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/RECORD deleted file mode 100644 index 44847291..00000000 --- a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/RECORD +++ /dev/null @@ -1,16 +0,0 @@ -more_itertools-8.12.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-more_itertools-8.12.0.dist-info/LICENSE,sha256=CfHIyelBrz5YTVlkHqm4fYPAyw_QB-te85Gn4mQ8GkY,1053
-more_itertools-8.12.0.dist-info/METADATA,sha256=QCCEcisEPr7iSfBIKCukhP-FbG9ehMK8tDIliZ3FBDc,39405
-more_itertools-8.12.0.dist-info/RECORD,,
-more_itertools-8.12.0.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
-more_itertools-8.12.0.dist-info/top_level.txt,sha256=fAuqRXu9LPhxdB9ujJowcFOu1rZ8wzSpOW9_jlKis6M,15
-more_itertools/__init__.py,sha256=ZQYu_9H6stSG7viUgT32TFqslqcZwq82kWRZooKiI8Y,83
-more_itertools/__init__.pyi,sha256=5B3eTzON1BBuOLob1vCflyEb2lSd6usXQQ-Cv-hXkeA,43
-more_itertools/__pycache__/__init__.cpython-310.pyc,,
-more_itertools/__pycache__/more.cpython-310.pyc,,
-more_itertools/__pycache__/recipes.cpython-310.pyc,,
-more_itertools/more.py,sha256=jSrvV9BK-XKa4x7MPPp9yWYRDtRgR5h7yryEqHMU4mg,132578
-more_itertools/more.pyi,sha256=kWOkRKx0V8ZwC1D2j0c0DUfy56dazzpmRcm5ZuY_aqo,20006
-more_itertools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-more_itertools/recipes.py,sha256=N6aCDwoIPvE-aiqpGU-nbFwqiM3X8MKRcxBM84naW88,18410
-more_itertools/recipes.pyi,sha256=Lx3vb0p_vY7rF8MQuguvOcVaS9qd1WRL8JO_qVo7hiY,3925
diff --git a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/top_level.txt b/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/top_level.txt deleted file mode 100644 index a5035bef..00000000 --- a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -more_itertools diff --git a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/INSTALLER b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/INSTALLER index a1b589e3..a1b589e3 100644 --- a/pkg_resources/_vendor/jaraco.functools-3.5.0.dist-info/INSTALLER +++ b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/INSTALLER diff --git a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/LICENSE b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/LICENSE index 0a523bec..0a523bec 100644 --- a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/LICENSE +++ b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/LICENSE diff --git a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/METADATA b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/METADATA index 9efacdd7..bd988923 100644 --- a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/METADATA +++ b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/METADATA @@ -1,29 +1,26 @@ Metadata-Version: 2.1 Name: more-itertools -Version: 8.12.0 +Version: 9.0.0 Summary: More routines for operating on iterables, beyond itertools -Home-page: https://github.com/more-itertools/more-itertools -Author: Erik Rose -Author-email: erikrose@grinchcentral.com -License: MIT -Keywords: itertools,iterator,iteration,filter,peek,peekable,collate,chunk,chunked -Platform: UNKNOWN +Keywords: itertools,iterator,iteration,filter,peek,peekable,chunk,chunked +Author-email: Erik Rose <erikrose@grinchcentral.com> +Requires-Python: >=3.7 +Description-Content-Type: text/x-rst Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: Natural Language :: English Classifier: License :: OSI Approved :: MIT License Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3.6 Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: 3.8 Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Programming Language :: Python :: 3.11 Classifier: Programming Language :: Python :: 3 :: Only Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Topic :: Software Development :: Libraries -Requires-Python: >=3.5 -Description-Content-Type: text/x-rst -License-File: LICENSE +Project-URL: Homepage, https://github.com/more-itertools/more-itertools ============== More Itertools @@ -40,7 +37,9 @@ Python iterables. +------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ | Grouping | `chunked <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.chunked>`_, | | | `ichunked <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.ichunked>`_, | +| | `chunked_even <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.chunked_even>`_, | | | `sliced <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.sliced>`_, | +| | `constrained_batches <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.constrained_batches>`_, | | | `distribute <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.distribute>`_, | | | `divide <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.divide>`_, | | | `split_at <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.split_at>`_, | @@ -50,6 +49,7 @@ Python iterables. | | `split_when <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.split_when>`_, | | | `bucket <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.bucket>`_, | | | `unzip <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.unzip>`_, | +| | `batched <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.batched>`_, | | | `grouper <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.grouper>`_, | | | `partition <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.partition>`_ | +------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ @@ -64,11 +64,13 @@ Python iterables. | | `windowed_complete <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.windowed_complete>`_, | | | `pairwise <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.pairwise>`_, | | | `triplewise <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.triplewise>`_, | -| | `sliding_window <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.sliding_window>`_ | +| | `sliding_window <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.sliding_window>`_, | +| | `subslices <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.subslices>`_ | +------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ | Augmenting | `count_cycle <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.count_cycle>`_, | | | `intersperse <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.intersperse>`_, | | | `padded <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.padded>`_, | +| | `repeat_each <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.repeat_each>`_, | | | `mark_ends <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.mark_ends>`_, | | | `repeat_last <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.repeat_last>`_, | | | `adjacent <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.adjacent>`_, | @@ -103,7 +105,8 @@ Python iterables. | | `all_unique <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.all_unique>`_, | | | `minmax <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.minmax>`_, | | | `first_true <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.first_true>`_, | -| | `quantify <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.quantify>`_ | +| | `quantify <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.quantify>`_, | +| | `iequals <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.iequals>`_ | +------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ | Selecting | `islice_extended <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.islice_extended>`_, | | | `first <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.first>`_, | @@ -125,7 +128,8 @@ Python iterables. | | `unique_everseen <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertoo ls.unique_everseen>`_, | | | `unique_justseen <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.unique_justseen>`_, | | | `duplicates_everseen <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.duplicates_everseen>`_, | -| | `duplicates_justseen <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.duplicates_justseen>`_ | +| | `duplicates_justseen <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.duplicates_justseen>`_, | +| | `longest_common_prefix <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.longest_common_prefix>`_ | +------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ | Combinatorics | `distinct_permutations <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.distinct_permutations>`_, | | | `distinct_combinations <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.distinct_combinations>`_, | @@ -161,9 +165,12 @@ Python iterables. | | `make_decorator <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.make_decorator>`_, | | | `SequenceView <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.SequenceView>`_, | | | `time_limited <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.time_limited>`_, | +| | `map_if <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.map_if>`_, | | | `consume <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.consume>`_, | | | `tabulate <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.tabulate>`_, | | | `repeatfunc <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.repeatfunc>`_ | +| | `polynomial_from_roots <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.polynomial_from_roots>`_ | +| | `sieve <https://more-itertools.readthedocs.io/en/stable/api.html#more_itertools.sieve>`_ | +------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ @@ -230,292 +237,5 @@ repository. Thanks for contributing! Version History =============== - - :noindex: - -8.12.0 ------- - -* Bug fixes - * Some documentation issues were fixed (thanks to Masynchin, spookylukey, astrojuanlu, and stephengmatthews) - * Python 3.5 support was temporarily restored (thanks to mattbonnell) - -8.11.0 ------- - -* New functions - * The before_and_after, sliding_window, and triplewise recipes from the Python 3.10 docs were added - * duplicates_everseen and duplicates_justseen (thanks to OrBin and DavidPratt512) - * minmax (thanks to Ricocotam, MSeifert04, and ruancomelli) - * strictly_n (thanks to hwalinga and NotWearingPants) - * unique_in_window - -* Changes to existing functions - * groupby_transform had its type stub improved (thanks to mjk4 and ruancomelli) - * is_sorted now accepts a ``strict`` parameter (thanks to Dutcho and ruancomelli) - * zip_broadcast was updated to fix a bug (thanks to kalekundert) - -8.10.0 ------- - -* Changes to existing functions - * The type stub for iter_except was improved (thanks to MarcinKonowalczyk) - -* Other changes: - * Type stubs now ship with the source release (thanks to saaketp) - * The Sphinx docs were improved (thanks to MarcinKonowalczyk) - -8.9.0 ------ - -* New functions - * interleave_evenly (thanks to mbugert) - * repeat_each (thanks to FinalSh4re) - * chunked_even (thanks to valtron) - * map_if (thanks to sassbalint) - * zip_broadcast (thanks to kalekundert) - -* Changes to existing functions - * The type stub for chunked was improved (thanks to PhilMacKay) - * The type stubs for zip_equal and `zip_offset` were improved (thanks to maffoo) - * Building Sphinx docs locally was improved (thanks to MarcinKonowalczyk) - -8.8.0 ------ - -* New functions - * countable (thanks to krzysieq) - -* Changes to existing functions - * split_before was updated to handle empy collections (thanks to TiunovNN) - * unique_everseen got a performance boost (thanks to Numerlor) - * The type hint for value_chain was corrected (thanks to vr2262) - -8.7.0 ------ - -* New functions - * convolve (from the Python itertools docs) - * product_index, combination_index, and permutation_index (thanks to N8Brooks) - * value_chain (thanks to jenstroeger) - -* Changes to existing functions - * distinct_combinations now uses a non-recursive algorithm (thanks to knutdrand) - * pad_none is now the preferred name for padnone, though the latter remains available. - * pairwise will now use the Python standard library implementation on Python 3.10+ - * sort_together now accepts a ``key`` argument (thanks to brianmaissy) - * seekable now has a ``peek`` method, and can indicate whether the iterator it's wrapping is exhausted (thanks to gsakkis) - * time_limited can now indicate whether its iterator has expired (thanks to roysmith) - * The implementation of unique_everseen was improved (thanks to plammens) - -* Other changes: - * Various documentation updates (thanks to cthoyt, Evantm, and cyphase) - -8.6.0 ------ - -* New itertools - * all_unique (thanks to brianmaissy) - * nth_product and nth_permutation (thanks to N8Brooks) - -* Changes to existing itertools - * chunked and sliced now accept a ``strict`` parameter (thanks to shlomif and jtwool) - -* Other changes - * Python 3.5 has reached its end of life and is no longer supported. - * Python 3.9 is officially supported. - * Various documentation fixes (thanks to timgates42) - -8.5.0 ------ - -* New itertools - * windowed_complete (thanks to MarcinKonowalczyk) - -* Changes to existing itertools: - * The is_sorted implementation was improved (thanks to cool-RR) - * The groupby_transform now accepts a ``reducefunc`` parameter. - * The last implementation was improved (thanks to brianmaissy) - -* Other changes - * Various documentation fixes (thanks to craigrosie, samuelstjean, PiCT0) - * The tests for distinct_combinations were improved (thanks to Minabsapi) - * Automated tests now run on GitHub Actions. All commits now check: - * That unit tests pass - * That the examples in docstrings work - * That test coverage remains high (using `coverage`) - * For linting errors (using `flake8`) - * For consistent style (using `black`) - * That the type stubs work (using `mypy`) - * That the docs build correctly (using `sphinx`) - * That packages build correctly (using `twine`) - -8.4.0 ------ - -* New itertools - * mark_ends (thanks to kalekundert) - * is_sorted - -* Changes to existing itertools: - * islice_extended can now be used with real slices (thanks to cool-RR) - * The implementations for filter_except and map_except were improved (thanks to SergBobrovsky) - -* Other changes - * Automated tests now enforce code style (using `black <https://github.com/psf/black>`__) - * The various signatures of islice_extended and numeric_range now appear in the docs (thanks to dsfulf) - * The test configuration for mypy was updated (thanks to blueyed) - - -8.3.0 ------ - -* New itertools - * zip_equal (thanks to frankier and alexmojaki) - -* Changes to existing itertools: - * split_at, split_before, split_after, and split_when all got a ``maxsplit`` paramter (thanks to jferard and ilai-deutel) - * split_at now accepts a ``keep_separator`` parameter (thanks to jferard) - * distinct_permutations can now generate ``r``-length permutations (thanks to SergBobrovsky and ilai-deutel) - * The windowed implementation was improved (thanks to SergBobrovsky) - * The spy implementation was improved (thanks to has2k1) - -* Other changes - * Type stubs are now tested with ``stubtest`` (thanks to ilai-deutel) - * Tests now run with ``python -m unittest`` instead of ``python setup.py test`` (thanks to jdufresne) - -8.2.0 ------ - -* Bug fixes - * The .pyi files for typing were updated. (thanks to blueyed and ilai-deutel) - -* Changes to existing itertools: - * numeric_range now behaves more like the built-in range. (thanks to jferard) - * bucket now allows for enumerating keys. (thanks to alexchandel) - * sliced now should now work for numpy arrays. (thanks to sswingle) - * seekable now has a ``maxlen`` parameter. - -8.1.0 ------ - -* Bug fixes - * partition works with ``pred=None`` again. (thanks to MSeifert04) - -* New itertools - * sample (thanks to tommyod) - * nth_or_last (thanks to d-ryzhikov) - -* Changes to existing itertools: - * The implementation for divide was improved. (thanks to jferard) - -8.0.2 ------ - -* Bug fixes - * The type stub files are now part of the wheel distribution (thanks to keisheiled) - -8.0.1 ------ - -* Bug fixes - * The type stub files now work for functions imported from the - root package (thanks to keisheiled) - -8.0.0 ------ - -* New itertools and other additions - * This library now ships type hints for use with mypy. - (thanks to ilai-deutel for the implementation, and to gabbard and fmagin for assistance) - * split_when (thanks to jferard) - * repeat_last (thanks to d-ryzhikov) - -* Changes to existing itertools: - * The implementation for set_partitions was improved. (thanks to jferard) - * partition was optimized for expensive predicates. (thanks to stevecj) - * unique_everseen and groupby_transform were re-factored. (thanks to SergBobrovsky) - * The implementation for difference was improved. (thanks to Jabbey92) - -* Other changes - * Python 3.4 has reached its end of life and is no longer supported. - * Python 3.8 is officially supported. (thanks to jdufresne) - * The ``collate`` function has been deprecated. - It raises a ``DeprecationWarning`` if used, and will be removed in a future release. - * one and only now provide more informative error messages. (thanks to gabbard) - * Unit tests were moved outside of the main package (thanks to jdufresne) - * Various documentation fixes (thanks to kriomant, gabbard, jdufresne) - - -7.2.0 ------ - -* New itertools - * distinct_combinations - * set_partitions (thanks to kbarrett) - * filter_except - * map_except - -7.1.0 ------ - -* New itertools - * ichunked (thanks davebelais and youtux) - * only (thanks jaraco) - -* Changes to existing itertools: - * numeric_range now supports ranges specified by - ``datetime.datetime`` and ``datetime.timedelta`` objects (thanks to MSeifert04 for tests). - * difference now supports an *initial* keyword argument. - - -* Other changes - * Various documentation fixes (thanks raimon49, pylang) - -7.0.0 ------ - -* New itertools: - * time_limited - * partitions (thanks to rominf and Saluev) - * substrings_indexes (thanks to rominf) - -* Changes to existing itertools: - * collapse now treats ``bytes`` objects the same as ``str`` objects. (thanks to Sweenpet) - -The major version update is due to the change in the default behavior of -collapse. It now treats ``bytes`` objects the same as ``str`` objects. -This aligns its behavior with always_iterable. - -.. code-block:: python - - >>> from more_itertools import collapse - >>> iterable = [[1, 2], b'345', [6]] - >>> print(list(collapse(iterable))) - [1, 2, b'345', 6] - -6.0.0 ------ - -* Major changes: - * Python 2.7 is no longer supported. The 5.0.0 release will be the last - version targeting Python 2.7. - * All future releases will target the active versions of Python 3. - As of 2019, those are Python 3.4 and above. - * The ``six`` library is no longer a dependency. - * The accumulate function is no longer part of this library. You - may import a better version from the standard ``itertools`` module. - -* Changes to existing itertools: - * The order of the parameters in grouper have changed to match - the latest recipe in the itertools documentation. Use of the old order - will be supported in this release, but emit a ``DeprecationWarning``. - The legacy behavior will be dropped in a future release. (thanks to jaraco) - * distinct_permutations was improved (thanks to jferard - see also `permutations with unique values <https://stackoverflow.com/questions/6284396/permutations-with-unique-values>`_ at StackOverflow.) - * An unused parameter was removed from substrings. (thanks to pylang) - -* Other changes: - * The docs for unique_everseen were improved. (thanks to jferard and MSeifert04) - * Several Python 2-isms were removed. (thanks to jaraco, MSeifert04, and hugovk) - +The version history can be found in `documentation <https://more-itertools.readthedocs.io/en/stable/versions.html>`_. diff --git a/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/RECORD b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/RECORD new file mode 100644 index 00000000..4ae7d821 --- /dev/null +++ b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/RECORD @@ -0,0 +1,15 @@ +more_itertools-9.0.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+more_itertools-9.0.0.dist-info/LICENSE,sha256=CfHIyelBrz5YTVlkHqm4fYPAyw_QB-te85Gn4mQ8GkY,1053
+more_itertools-9.0.0.dist-info/METADATA,sha256=o71Ks93mbZ7709yvfFg09Vxgj-8t2ZZaYIyUprS8GHw,31266
+more_itertools-9.0.0.dist-info/RECORD,,
+more_itertools-9.0.0.dist-info/WHEEL,sha256=4TfKIB_xu-04bc2iKz6_zFt-gEFEEDU_31HGhqzOCE8,81
+more_itertools/__init__.py,sha256=5PNQMpy400s5GB3jcWwzje0RCw8k0bvU9W_C49V0fd0,148
+more_itertools/__init__.pyi,sha256=5B3eTzON1BBuOLob1vCflyEb2lSd6usXQQ-Cv-hXkeA,43
+more_itertools/__pycache__/__init__.cpython-311.pyc,,
+more_itertools/__pycache__/more.cpython-311.pyc,,
+more_itertools/__pycache__/recipes.cpython-311.pyc,,
+more_itertools/more.py,sha256=FmmtkT-j69qILkxEELk5ZRoZK8St1Vg_fOGW0sTFd7g,133336
+more_itertools/more.pyi,sha256=hbf2oqg56wctXwf6yM1B0QLWqsNyDrqtX2znvQRAe3Q,20297
+more_itertools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+more_itertools/recipes.py,sha256=ZX4-2IfbZKlPIVaDITH2buX_fPuMDe1EVc6e2XSsCz8,22975
+more_itertools/recipes.pyi,sha256=NA6qqcKMbQ2fly9hCyCzMcx46Tn9TLl-9mFnZsRytZM,3851
diff --git a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/WHEEL b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/WHEEL index 5bad85fd..668ba4d0 100644 --- a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/WHEEL +++ b/pkg_resources/_vendor/more_itertools-9.0.0.dist-info/WHEEL @@ -1,5 +1,4 @@ Wheel-Version: 1.0 -Generator: bdist_wheel (0.37.0) +Generator: flit 3.7.1 Root-Is-Purelib: true Tag: py3-none-any - diff --git a/pkg_resources/_vendor/more_itertools/__init__.py b/pkg_resources/_vendor/more_itertools/__init__.py index ea38bef1..557bfc20 100644 --- a/pkg_resources/_vendor/more_itertools/__init__.py +++ b/pkg_resources/_vendor/more_itertools/__init__.py @@ -1,4 +1,6 @@ +"""More routines for operating on iterables, beyond itertools""" + from .more import * # noqa from .recipes import * # noqa -__version__ = '8.12.0' +__version__ = '9.0.0' diff --git a/pkg_resources/_vendor/more_itertools/more.py b/pkg_resources/_vendor/more_itertools/more.py index 6b6a5cab..0b29fca0 100644..100755 --- a/pkg_resources/_vendor/more_itertools/more.py +++ b/pkg_resources/_vendor/more_itertools/more.py @@ -3,7 +3,7 @@ import warnings from collections import Counter, defaultdict, deque, abc from collections.abc import Sequence from functools import partial, reduce, wraps -from heapq import merge, heapify, heapreplace, heappop +from heapq import heapify, heapreplace, heappop from itertools import ( chain, compress, @@ -26,12 +26,16 @@ from sys import hexversion, maxsize from time import monotonic from .recipes import ( + _marker, + _zip_equal, + UnequalIterablesError, consume, flatten, pairwise, powerset, take, unique_everseen, + all_equal, ) __all__ = [ @@ -48,9 +52,9 @@ __all__ = [ 'chunked_even', 'circular_shifts', 'collapse', - 'collate', 'combination_index', 'consecutive_groups', + 'constrained_batches', 'consumer', 'count_cycle', 'countable', @@ -66,6 +70,7 @@ __all__ = [ 'first', 'groupby_transform', 'ichunked', + 'iequals', 'ilen', 'interleave', 'interleave_evenly', @@ -76,6 +81,7 @@ __all__ = [ 'iterate', 'last', 'locate', + 'longest_common_prefix', 'lstrip', 'make_decorator', 'map_except', @@ -132,9 +138,6 @@ __all__ = [ ] -_marker = object() - - def chunked(iterable, n, strict=False): """Break *iterable* into lists of length *n*: @@ -409,44 +412,6 @@ class peekable: return self._cache[index] -def collate(*iterables, **kwargs): - """Return a sorted merge of the items from each of several already-sorted - *iterables*. - - >>> list(collate('ACDZ', 'AZ', 'JKL')) - ['A', 'A', 'C', 'D', 'J', 'K', 'L', 'Z', 'Z'] - - Works lazily, keeping only the next value from each iterable in memory. Use - :func:`collate` to, for example, perform a n-way mergesort of items that - don't fit in memory. - - If a *key* function is specified, the iterables will be sorted according - to its result: - - >>> key = lambda s: int(s) # Sort by numeric value, not by string - >>> list(collate(['1', '10'], ['2', '11'], key=key)) - ['1', '2', '10', '11'] - - - If the *iterables* are sorted in descending order, set *reverse* to - ``True``: - - >>> list(collate([5, 3, 1], [4, 2, 0], reverse=True)) - [5, 4, 3, 2, 1, 0] - - If the elements of the passed-in iterables are out of order, you might get - unexpected results. - - On Python 3.5+, this function is an alias for :func:`heapq.merge`. - - """ - warnings.warn( - "collate is no longer part of more_itertools, use heapq.merge", - DeprecationWarning, - ) - return merge(*iterables, **kwargs) - - def consumer(func): """Decorator that automatically advances a PEP-342-style "reverse iterator" to its first yield point so you don't have to call ``next()`` on it @@ -872,7 +837,9 @@ def windowed(seq, n, fillvalue=None, step=1): yield tuple(window) size = len(window) - if size < n: + if size == 0: + return + elif size < n: yield tuple(chain(window, repeat(fillvalue, n - size))) elif 0 < i < min(step, n): window += (fillvalue,) * i @@ -1645,45 +1612,6 @@ def stagger(iterable, offsets=(-1, 0, 1), longest=False, fillvalue=None): ) -class UnequalIterablesError(ValueError): - def __init__(self, details=None): - msg = 'Iterables have different lengths' - if details is not None: - msg += (': index 0 has length {}; index {} has length {}').format( - *details - ) - - super().__init__(msg) - - -def _zip_equal_generator(iterables): - for combo in zip_longest(*iterables, fillvalue=_marker): - for val in combo: - if val is _marker: - raise UnequalIterablesError() - yield combo - - -def _zip_equal(*iterables): - # Check whether the iterables are all the same size. - try: - first_size = len(iterables[0]) - for i, it in enumerate(iterables[1:], 1): - size = len(it) - if size != first_size: - break - else: - # If we didn't break out, we can use the built-in zip. - return zip(*iterables) - - # If we did break out, there was a mismatch. - raise UnequalIterablesError(details=(first_size, i, size)) - # If any one of the iterables didn't have a length, start reading - # them until one runs out. - except TypeError: - return _zip_equal_generator(iterables) - - def zip_equal(*iterables): """``zip`` the input *iterables* together, but raise ``UnequalIterablesError`` if they aren't all the same length. @@ -1825,7 +1753,7 @@ def unzip(iterable): of the zipped *iterable*. The ``i``-th iterable contains the ``i``-th element from each element - of the zipped iterable. The first element is used to to determine the + of the zipped iterable. The first element is used to determine the length of the remaining elements. >>> iterable = [('a', 1), ('b', 2), ('c', 3), ('d', 4)] @@ -2375,6 +2303,16 @@ def locate(iterable, pred=bool, window_size=None): return compress(count(), starmap(pred, it)) +def longest_common_prefix(iterables): + """Yield elements of the longest common prefix amongst given *iterables*. + + >>> ''.join(longest_common_prefix(['abcd', 'abc', 'abf'])) + 'ab' + + """ + return (c[0] for c in takewhile(all_equal, zip(*iterables))) + + def lstrip(iterable, pred): """Yield the items from *iterable*, but strip any from the beginning for which *pred* returns ``True``. @@ -2683,7 +2621,7 @@ def difference(iterable, func=sub, *, initial=None): if initial is not None: first = [] - return chain(first, starmap(func, zip(b, a))) + return chain(first, map(func, b, a)) class SequenceView(Sequence): @@ -3326,6 +3264,27 @@ def only(iterable, default=None, too_long=None): return first_value +class _IChunk: + def __init__(self, iterable, n): + self._it = islice(iterable, n) + self._cache = deque() + + def fill_cache(self): + self._cache.extend(self._it) + + def __iter__(self): + return self + + def __next__(self): + try: + return next(self._it) + except StopIteration: + if self._cache: + return self._cache.popleft() + else: + raise + + def ichunked(iterable, n): """Break *iterable* into sub-iterables with *n* elements each. :func:`ichunked` is like :func:`chunked`, but it yields iterables @@ -3347,20 +3306,39 @@ def ichunked(iterable, n): [8, 9, 10, 11] """ - source = iter(iterable) - + source = peekable(iter(iterable)) + ichunk_marker = object() while True: # Check to see whether we're at the end of the source iterable - item = next(source, _marker) - if item is _marker: + item = source.peek(ichunk_marker) + if item is ichunk_marker: return - # Clone the source and yield an n-length slice - source, it = tee(chain([item], source)) - yield islice(it, n) + chunk = _IChunk(source, n) + yield chunk + + # Advance the source iterable and fill previous chunk's cache + chunk.fill_cache() + + +def iequals(*iterables): + """Return ``True`` if all given *iterables* are equal to each other, + which means that they contain the same elements in the same order. - # Advance the source iterable - consume(source, n) + The function is useful for comparing iterables of different data types + or iterables that do not support equality checks. + + >>> iequals("abc", ['a', 'b', 'c'], ('a', 'b', 'c'), iter("abc")) + True + + >>> iequals("abc", "acb") + False + + Not to be confused with :func:`all_equals`, which checks whether all + elements of iterable are equal to each other. + + """ + return all(map(all_equal, zip_longest(*iterables, fillvalue=object()))) def distinct_combinations(iterable, r): @@ -3655,7 +3633,9 @@ class callback_iter: self._aborted = False self._future = None self._wait_seconds = wait_seconds - self._executor = __import__("concurrent.futures").futures.ThreadPoolExecutor(max_workers=1) + # Lazily import concurrent.future + self._executor = __import__( + ).futures.__import__("concurrent.futures").futures.ThreadPoolExecutor(max_workers=1) self._iterator = self._reader() def __enter__(self): @@ -3960,7 +3940,7 @@ def combination_index(element, iterable): n, _ = last(pool, default=(n, None)) - # Python versiosn below 3.8 don't have math.comb + # Python versions below 3.8 don't have math.comb index = 1 for i, j in enumerate(reversed(indexes), start=1): j = n - j @@ -4113,7 +4093,7 @@ def zip_broadcast(*objects, scalar_types=(str, bytes), strict=False): If the *strict* keyword argument is ``True``, then ``UnequalIterablesError`` will be raised if any of the iterables have - different lengthss. + different lengths. """ def is_scalar(obj): @@ -4314,3 +4294,53 @@ def minmax(iterable_or_value, *others, key=None, default=_marker): hi, hi_key = y, y_key return lo, hi + + +def constrained_batches( + iterable, max_size, max_count=None, get_len=len, strict=True +): + """Yield batches of items from *iterable* with a combined size limited by + *max_size*. + + >>> iterable = [b'12345', b'123', b'12345678', b'1', b'1', b'12', b'1'] + >>> list(constrained_batches(iterable, 10)) + [(b'12345', b'123'), (b'12345678', b'1', b'1'), (b'12', b'1')] + + If a *max_count* is supplied, the number of items per batch is also + limited: + + >>> iterable = [b'12345', b'123', b'12345678', b'1', b'1', b'12', b'1'] + >>> list(constrained_batches(iterable, 10, max_count = 2)) + [(b'12345', b'123'), (b'12345678', b'1'), (b'1', b'12'), (b'1',)] + + If a *get_len* function is supplied, use that instead of :func:`len` to + determine item size. + + If *strict* is ``True``, raise ``ValueError`` if any single item is bigger + than *max_size*. Otherwise, allow single items to exceed *max_size*. + """ + if max_size <= 0: + raise ValueError('maximum size must be greater than zero') + + batch = [] + batch_size = 0 + batch_count = 0 + for item in iterable: + item_len = get_len(item) + if strict and item_len > max_size: + raise ValueError('item size exceeds maximum size') + + reached_count = batch_count == max_count + reached_size = item_len + batch_size > max_size + if batch_count and (reached_size or reached_count): + yield tuple(batch) + batch.clear() + batch_size = 0 + batch_count = 0 + + batch.append(item) + batch_size += item_len + batch_count += 1 + + if batch: + yield tuple(batch) diff --git a/pkg_resources/_vendor/more_itertools/more.pyi b/pkg_resources/_vendor/more_itertools/more.pyi index fe7d4bdd..1413fae7 100644 --- a/pkg_resources/_vendor/more_itertools/more.pyi +++ b/pkg_resources/_vendor/more_itertools/more.pyi @@ -72,7 +72,6 @@ class peekable(Generic[_T], Iterator[_T]): @overload def __getitem__(self, index: slice) -> List[_T]: ... -def collate(*iterables: Iterable[_T], **kwargs: Any) -> Iterable[_T]: ... def consumer(func: _GenFn) -> _GenFn: ... def ilen(iterable: Iterable[object]) -> int: ... def iterate(func: Callable[[_T], _T], start: _T) -> Iterator[_T]: ... @@ -179,7 +178,7 @@ def padded( iterable: Iterable[_T], *, n: Optional[int] = ..., - next_multiple: bool = ... + next_multiple: bool = ..., ) -> Iterator[Optional[_T]]: ... @overload def padded( @@ -225,7 +224,7 @@ def zip_equal( __iter1: Iterable[_T], __iter2: Iterable[_T], __iter3: Iterable[_T], - *iterables: Iterable[_T] + *iterables: Iterable[_T], ) -> Iterator[Tuple[_T, ...]]: ... @overload def zip_offset( @@ -233,7 +232,7 @@ def zip_offset( *, offsets: _SizedIterable[int], longest: bool = ..., - fillvalue: None = None + fillvalue: None = None, ) -> Iterator[Tuple[Optional[_T1]]]: ... @overload def zip_offset( @@ -242,7 +241,7 @@ def zip_offset( *, offsets: _SizedIterable[int], longest: bool = ..., - fillvalue: None = None + fillvalue: None = None, ) -> Iterator[Tuple[Optional[_T1], Optional[_T2]]]: ... @overload def zip_offset( @@ -252,7 +251,7 @@ def zip_offset( *iterables: Iterable[_T], offsets: _SizedIterable[int], longest: bool = ..., - fillvalue: None = None + fillvalue: None = None, ) -> Iterator[Tuple[Optional[_T], ...]]: ... @overload def zip_offset( @@ -420,7 +419,7 @@ def difference( iterable: Iterable[_T], func: Callable[[_T, _T], _U] = ..., *, - initial: None = ... + initial: None = ..., ) -> Iterator[Union[_T, _U]]: ... @overload def difference( @@ -529,12 +528,12 @@ def distinct_combinations( def filter_except( validator: Callable[[Any], object], iterable: Iterable[_T], - *exceptions: Type[BaseException] + *exceptions: Type[BaseException], ) -> Iterator[_T]: ... def map_except( function: Callable[[Any], _U], iterable: Iterable[_T], - *exceptions: Type[BaseException] + *exceptions: Type[BaseException], ) -> Iterator[_U]: ... def map_if( iterable: Iterable[Any], @@ -610,7 +609,7 @@ def zip_broadcast( scalar_types: Union[ type, Tuple[Union[type, Tuple[Any, ...]], ...], None ] = ..., - strict: bool = ... + strict: bool = ..., ) -> Iterable[Tuple[_T, ...]]: ... def unique_in_window( iterable: Iterable[_T], n: int, key: Optional[Callable[[_T], _U]] = ... @@ -640,7 +639,7 @@ def minmax( iterable_or_value: Iterable[_SupportsLessThanT], *, key: None = None, - default: _U + default: _U, ) -> Union[_U, Tuple[_SupportsLessThanT, _SupportsLessThanT]]: ... @overload def minmax( @@ -653,12 +652,23 @@ def minmax( def minmax( iterable_or_value: _SupportsLessThanT, __other: _SupportsLessThanT, - *others: _SupportsLessThanT + *others: _SupportsLessThanT, ) -> Tuple[_SupportsLessThanT, _SupportsLessThanT]: ... @overload def minmax( iterable_or_value: _T, __other: _T, *others: _T, - key: Callable[[_T], _SupportsLessThan] + key: Callable[[_T], _SupportsLessThan], ) -> Tuple[_T, _T]: ... +def longest_common_prefix( + iterables: Iterable[Iterable[_T]], +) -> Iterator[_T]: ... +def iequals(*iterables: Iterable[object]) -> bool: ... +def constrained_batches( + iterable: Iterable[object], + max_size: int, + max_count: Optional[int] = ..., + get_len: Callable[[_T], object] = ..., + strict: bool = ..., +) -> Iterator[Tuple[_T]]: ... diff --git a/pkg_resources/_vendor/more_itertools/recipes.py b/pkg_resources/_vendor/more_itertools/recipes.py index a2596423..85796207 100644 --- a/pkg_resources/_vendor/more_itertools/recipes.py +++ b/pkg_resources/_vendor/more_itertools/recipes.py @@ -7,11 +7,16 @@ Some backward-compatible usability improvements have been made. .. [1] http://docs.python.org/library/itertools.html#recipes """ -import warnings +import math +import operator + from collections import deque +from collections.abc import Sized +from functools import reduce from itertools import ( chain, combinations, + compress, count, cycle, groupby, @@ -21,11 +26,11 @@ from itertools import ( tee, zip_longest, ) -import operator from random import randrange, sample, choice __all__ = [ 'all_equal', + 'batched', 'before_and_after', 'consume', 'convolve', @@ -41,6 +46,7 @@ __all__ = [ 'pad_none', 'pairwise', 'partition', + 'polynomial_from_roots', 'powerset', 'prepend', 'quantify', @@ -50,7 +56,9 @@ __all__ = [ 'random_product', 'repeatfunc', 'roundrobin', + 'sieve', 'sliding_window', + 'subslices', 'tabulate', 'tail', 'take', @@ -59,6 +67,8 @@ __all__ = [ 'unique_justseen', ] +_marker = object() + def take(n, iterable): """Return first *n* items of the iterable as a list. @@ -102,7 +112,14 @@ def tail(n, iterable): ['E', 'F', 'G'] """ - return iter(deque(iterable, maxlen=n)) + # If the given iterable has a length, then we can use islice to get its + # final elements. Note that if the iterable is not actually Iterable, + # either islice or deque will throw a TypeError. This is why we don't + # check if it is Iterable. + if isinstance(iterable, Sized): + yield from islice(iterable, max(0, len(iterable) - n), None) + else: + yield from iter(deque(iterable, maxlen=n)) def consume(iterator, n=None): @@ -284,20 +301,83 @@ else: pairwise.__doc__ = _pairwise.__doc__ -def grouper(iterable, n, fillvalue=None): - """Collect data into fixed-length chunks or blocks. +class UnequalIterablesError(ValueError): + def __init__(self, details=None): + msg = 'Iterables have different lengths' + if details is not None: + msg += (': index 0 has length {}; index {} has length {}').format( + *details + ) + + super().__init__(msg) + + +def _zip_equal_generator(iterables): + for combo in zip_longest(*iterables, fillvalue=_marker): + for val in combo: + if val is _marker: + raise UnequalIterablesError() + yield combo + + +def _zip_equal(*iterables): + # Check whether the iterables are all the same size. + try: + first_size = len(iterables[0]) + for i, it in enumerate(iterables[1:], 1): + size = len(it) + if size != first_size: + break + else: + # If we didn't break out, we can use the built-in zip. + return zip(*iterables) - >>> list(grouper('ABCDEFG', 3, 'x')) + # If we did break out, there was a mismatch. + raise UnequalIterablesError(details=(first_size, i, size)) + # If any one of the iterables didn't have a length, start reading + # them until one runs out. + except TypeError: + return _zip_equal_generator(iterables) + + +def grouper(iterable, n, incomplete='fill', fillvalue=None): + """Group elements from *iterable* into fixed-length groups of length *n*. + + >>> list(grouper('ABCDEF', 3)) + [('A', 'B', 'C'), ('D', 'E', 'F')] + + The keyword arguments *incomplete* and *fillvalue* control what happens for + iterables whose length is not a multiple of *n*. + + When *incomplete* is `'fill'`, the last group will contain instances of + *fillvalue*. + + >>> list(grouper('ABCDEFG', 3, incomplete='fill', fillvalue='x')) [('A', 'B', 'C'), ('D', 'E', 'F'), ('G', 'x', 'x')] + When *incomplete* is `'ignore'`, the last group will not be emitted. + + >>> list(grouper('ABCDEFG', 3, incomplete='ignore', fillvalue='x')) + [('A', 'B', 'C'), ('D', 'E', 'F')] + + When *incomplete* is `'strict'`, a subclass of `ValueError` will be raised. + + >>> it = grouper('ABCDEFG', 3, incomplete='strict') + >>> list(it) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + UnequalIterablesError + """ - if isinstance(iterable, int): - warnings.warn( - "grouper expects iterable as first parameter", DeprecationWarning - ) - n, iterable = iterable, n args = [iter(iterable)] * n - return zip_longest(fillvalue=fillvalue, *args) + if incomplete == 'fill': + return zip_longest(*args, fillvalue=fillvalue) + if incomplete == 'strict': + return _zip_equal(*args) + if incomplete == 'ignore': + return zip(*args) + else: + raise ValueError('Expected fill, strict, or ignore') def roundrobin(*iterables): @@ -658,11 +738,12 @@ def before_and_after(predicate, it): transition.append(elem) return - def remainder_iterator(): - yield from transition - yield from it + # Note: this is different from itertools recipes to allow nesting + # before_and_after remainders into before_and_after again. See tests + # for an example. + remainder_iterator = chain(transition, it) - return true_iterator(), remainder_iterator() + return true_iterator(), remainder_iterator def triplewise(iterable): @@ -696,3 +777,65 @@ def sliding_window(iterable, n): for x in it: window.append(x) yield tuple(window) + + +def subslices(iterable): + """Return all contiguous non-empty subslices of *iterable*. + + >>> list(subslices('ABC')) + [['A'], ['A', 'B'], ['A', 'B', 'C'], ['B'], ['B', 'C'], ['C']] + + This is similar to :func:`substrings`, but emits items in a different + order. + """ + seq = list(iterable) + slices = starmap(slice, combinations(range(len(seq) + 1), 2)) + return map(operator.getitem, repeat(seq), slices) + + +def polynomial_from_roots(roots): + """Compute a polynomial's coefficients from its roots. + + >>> roots = [5, -4, 3] # (x - 5) * (x + 4) * (x - 3) + >>> polynomial_from_roots(roots) # x^3 - 4 * x^2 - 17 * x + 60 + [1, -4, -17, 60] + """ + # Use math.prod for Python 3.8+, + prod = getattr(math, 'prod', lambda x: reduce(operator.mul, x, 1)) + roots = list(map(operator.neg, roots)) + return [ + sum(map(prod, combinations(roots, k))) for k in range(len(roots) + 1) + ] + + +def sieve(n): + """Yield the primes less than n. + + >>> list(sieve(30)) + [2, 3, 5, 7, 11, 13, 17, 19, 23, 29] + """ + isqrt = getattr(math, 'isqrt', lambda x: int(math.sqrt(x))) + limit = isqrt(n) + 1 + data = bytearray([1]) * n + data[:2] = 0, 0 + for p in compress(range(limit), data): + data[p + p : n : p] = bytearray(len(range(p + p, n, p))) + + return compress(count(), data) + + +def batched(iterable, n): + """Batch data into lists of length *n*. The last batch may be shorter. + + >>> list(batched('ABCDEFG', 3)) + [['A', 'B', 'C'], ['D', 'E', 'F'], ['G']] + + This recipe is from the ``itertools`` docs. This library also provides + :func:`chunked`, which has a different implementation. + """ + it = iter(iterable) + while True: + batch = list(islice(it, n)) + if not batch: + break + yield batch diff --git a/pkg_resources/_vendor/more_itertools/recipes.pyi b/pkg_resources/_vendor/more_itertools/recipes.pyi index 4648a41b..29415c5a 100644 --- a/pkg_resources/_vendor/more_itertools/recipes.pyi +++ b/pkg_resources/_vendor/more_itertools/recipes.pyi @@ -6,6 +6,7 @@ from typing import ( Iterator, List, Optional, + Sequence, Tuple, TypeVar, Union, @@ -39,21 +40,11 @@ def repeatfunc( func: Callable[..., _U], times: Optional[int] = ..., *args: Any ) -> Iterator[_U]: ... def pairwise(iterable: Iterable[_T]) -> Iterator[Tuple[_T, _T]]: ... -@overload def grouper( - iterable: Iterable[_T], n: int -) -> Iterator[Tuple[Optional[_T], ...]]: ... -@overload -def grouper( - iterable: Iterable[_T], n: int, fillvalue: _U -) -> Iterator[Tuple[Union[_T, _U], ...]]: ... -@overload -def grouper( # Deprecated interface - iterable: int, n: Iterable[_T] -) -> Iterator[Tuple[Optional[_T], ...]]: ... -@overload -def grouper( # Deprecated interface - iterable: int, n: Iterable[_T], fillvalue: _U + iterable: Iterable[_T], + n: int, + incomplete: str = ..., + fillvalue: _U = ..., ) -> Iterator[Tuple[Union[_T, _U], ...]]: ... def roundrobin(*iterables: Iterable[_T]) -> Iterator[_T]: ... def partition( @@ -110,3 +101,10 @@ def triplewise(iterable: Iterable[_T]) -> Iterator[Tuple[_T, _T, _T]]: ... def sliding_window( iterable: Iterable[_T], n: int ) -> Iterator[Tuple[_T, ...]]: ... +def subslices(iterable: Iterable[_T]) -> Iterator[List[_T]]: ... +def polynomial_from_roots(roots: Sequence[int]) -> List[int]: ... +def sieve(n: int) -> Iterator[int]: ... +def batched( + iterable: Iterable[_T], + n: int, +) -> Iterator[List[_T]]: ... diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/RECORD b/pkg_resources/_vendor/packaging-21.2.dist-info/RECORD deleted file mode 100644 index ed2291ac..00000000 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/RECORD +++ /dev/null @@ -1,32 +0,0 @@ -packaging-21.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-packaging-21.2.dist-info/LICENSE,sha256=ytHvW9NA1z4HS6YU0m996spceUDD2MNIUuZcSQlobEg,197
-packaging-21.2.dist-info/LICENSE.APACHE,sha256=DVQuDIgE45qn836wDaWnYhSdxoLXgpRRKH4RuTjpRZQ,10174
-packaging-21.2.dist-info/LICENSE.BSD,sha256=tw5-m3QvHMb5SLNMFqo5_-zpQZY2S8iP8NIYDwAo-sU,1344
-packaging-21.2.dist-info/METADATA,sha256=N4A8uSYrQwV9byem7YuI9OtVkbqiNzFlDhcDVT-suAo,14754
-packaging-21.2.dist-info/RECORD,,
-packaging-21.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-packaging-21.2.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
-packaging-21.2.dist-info/top_level.txt,sha256=zFdHrhWnPslzsiP455HutQsqPB6v0KCtNUMtUtrefDw,10
-packaging/__about__.py,sha256=IIRHpOsJlJSgkjq1UoeBoMTqhvNp3gN9FyMb5Kf8El4,661
-packaging/__init__.py,sha256=b9Kk5MF7KxhhLgcDmiUWukN-LatWFxPdNug0joPhHSk,497
-packaging/__pycache__/__about__.cpython-310.pyc,,
-packaging/__pycache__/__init__.cpython-310.pyc,,
-packaging/__pycache__/_manylinux.cpython-310.pyc,,
-packaging/__pycache__/_musllinux.cpython-310.pyc,,
-packaging/__pycache__/_structures.cpython-310.pyc,,
-packaging/__pycache__/markers.cpython-310.pyc,,
-packaging/__pycache__/requirements.cpython-310.pyc,,
-packaging/__pycache__/specifiers.cpython-310.pyc,,
-packaging/__pycache__/tags.cpython-310.pyc,,
-packaging/__pycache__/utils.cpython-310.pyc,,
-packaging/__pycache__/version.cpython-310.pyc,,
-packaging/_manylinux.py,sha256=XcbiXB-qcjv3bcohp6N98TMpOP4_j3m-iOA8ptK2GWY,11488
-packaging/_musllinux.py,sha256=z5yeG1ygOPx4uUyLdqj-p8Dk5UBb5H_b0NIjW9yo8oA,4378
-packaging/_structures.py,sha256=TMiAgFbdUOPmIfDIfiHc3KFhSJ8kMjof2QS5I-2NyQ8,1629
-packaging/markers.py,sha256=Fygi3_eZnjQ-3VJizW5AhI5wvo0Hb6RMk4DidsKpOC0,8475
-packaging/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-packaging/requirements.py,sha256=rjaGRCMepZS1mlYMjJ5Qh6rfq3gtsCRQUQmftGZ_bu8,4664
-packaging/specifiers.py,sha256=MZ-fYcNL3u7pNrt-6g2EQO7AbRXkjc-SPEYwXMQbLmc,30964
-packaging/tags.py,sha256=vGybAUQYlPKMcukzX_2e65fmafnFFuMbD25naYTEwtc,15710
-packaging/utils.py,sha256=dJjeat3BS-TYn1RrUFVwufUMasbtzLfYRoy_HXENeFQ,4200
-packaging/version.py,sha256=_fLRNrFrxYcHVfyo8vk9j8s6JM8N_xsSxVFr6RJyco8,14665
diff --git a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/INSTALLER b/pkg_resources/_vendor/packaging-21.3.dist-info/INSTALLER index a1b589e3..a1b589e3 100644 --- a/pkg_resources/_vendor/more_itertools-8.12.0.dist-info/INSTALLER +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/INSTALLER diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/LICENSE b/pkg_resources/_vendor/packaging-21.3.dist-info/LICENSE index 6f62d44e..6f62d44e 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/LICENSE +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/LICENSE diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/LICENSE.APACHE b/pkg_resources/_vendor/packaging-21.3.dist-info/LICENSE.APACHE index f433b1a5..f433b1a5 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/LICENSE.APACHE +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/LICENSE.APACHE diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/LICENSE.BSD b/pkg_resources/_vendor/packaging-21.3.dist-info/LICENSE.BSD index 42ce7b75..42ce7b75 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/LICENSE.BSD +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/LICENSE.BSD diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/METADATA b/pkg_resources/_vendor/packaging-21.3.dist-info/METADATA index e8ff54d7..358ace53 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/METADATA +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/METADATA @@ -1,6 +1,6 @@ Metadata-Version: 2.1 Name: packaging -Version: 21.2 +Version: 21.3 Summary: Core utilities for Python packages Home-page: https://github.com/pypa/packaging Author: Donald Stufft and individual contributors @@ -26,7 +26,7 @@ Description-Content-Type: text/x-rst License-File: LICENSE License-File: LICENSE.APACHE License-File: LICENSE.BSD -Requires-Dist: pyparsing (<3,>=2.0.2) +Requires-Dist: pyparsing (!=3.0.5,>=2.0.2) packaging ========= @@ -105,6 +105,13 @@ recent changes and project history. Changelog --------- +21.3 - 2021-11-17 +~~~~~~~~~~~~~~~~~ + +* Add a ``pp3-none-any`` tag (`#311 <https://github.com/pypa/packaging/issues/311>`__) +* Replace the blank pyparsing 3 exclusion with a 3.0.5 exclusion (`#481 <https://github.com/pypa/packaging/issues/481>`__, `#486 <https://github.com/pypa/packaging/issues/486>`__) +* Fix a spelling mistake (`#479 <https://github.com/pypa/packaging/issues/479>`__) + 21.2 - 2021-10-29 ~~~~~~~~~~~~~~~~~ diff --git a/pkg_resources/_vendor/packaging-21.3.dist-info/RECORD b/pkg_resources/_vendor/packaging-21.3.dist-info/RECORD new file mode 100644 index 00000000..77b1ed96 --- /dev/null +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/RECORD @@ -0,0 +1,32 @@ +packaging-21.3.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+packaging-21.3.dist-info/LICENSE,sha256=ytHvW9NA1z4HS6YU0m996spceUDD2MNIUuZcSQlobEg,197
+packaging-21.3.dist-info/LICENSE.APACHE,sha256=DVQuDIgE45qn836wDaWnYhSdxoLXgpRRKH4RuTjpRZQ,10174
+packaging-21.3.dist-info/LICENSE.BSD,sha256=tw5-m3QvHMb5SLNMFqo5_-zpQZY2S8iP8NIYDwAo-sU,1344
+packaging-21.3.dist-info/METADATA,sha256=KuKIy6qDLP3svIt6ejCbxBDhvq11ebkgUN55MeyKFyc,15147
+packaging-21.3.dist-info/RECORD,,
+packaging-21.3.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+packaging-21.3.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
+packaging-21.3.dist-info/top_level.txt,sha256=zFdHrhWnPslzsiP455HutQsqPB6v0KCtNUMtUtrefDw,10
+packaging/__about__.py,sha256=ugASIO2w1oUyH8_COqQ2X_s0rDhjbhQC3yJocD03h2c,661
+packaging/__init__.py,sha256=b9Kk5MF7KxhhLgcDmiUWukN-LatWFxPdNug0joPhHSk,497
+packaging/__pycache__/__about__.cpython-311.pyc,,
+packaging/__pycache__/__init__.cpython-311.pyc,,
+packaging/__pycache__/_manylinux.cpython-311.pyc,,
+packaging/__pycache__/_musllinux.cpython-311.pyc,,
+packaging/__pycache__/_structures.cpython-311.pyc,,
+packaging/__pycache__/markers.cpython-311.pyc,,
+packaging/__pycache__/requirements.cpython-311.pyc,,
+packaging/__pycache__/specifiers.cpython-311.pyc,,
+packaging/__pycache__/tags.cpython-311.pyc,,
+packaging/__pycache__/utils.cpython-311.pyc,,
+packaging/__pycache__/version.cpython-311.pyc,,
+packaging/_manylinux.py,sha256=XcbiXB-qcjv3bcohp6N98TMpOP4_j3m-iOA8ptK2GWY,11488
+packaging/_musllinux.py,sha256=_KGgY_qc7vhMGpoqss25n2hiLCNKRtvz9mCrS7gkqyc,4378
+packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431
+packaging/markers.py,sha256=Fygi3_eZnjQ-3VJizW5AhI5wvo0Hb6RMk4DidsKpOC0,8475
+packaging/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+packaging/requirements.py,sha256=rjaGRCMepZS1mlYMjJ5Qh6rfq3gtsCRQUQmftGZ_bu8,4664
+packaging/specifiers.py,sha256=LRQ0kFsHrl5qfcFNEEJrIFYsnIHQUJXY9fIsakTrrqE,30110
+packaging/tags.py,sha256=lmsnGNiJ8C4D_Pf9PbM0qgbZvD9kmB9lpZBQUZa3R_Y,15699
+packaging/utils.py,sha256=dJjeat3BS-TYn1RrUFVwufUMasbtzLfYRoy_HXENeFQ,4200
+packaging/version.py,sha256=_fLRNrFrxYcHVfyo8vk9j8s6JM8N_xsSxVFr6RJyco8,14665
diff --git a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/REQUESTED b/pkg_resources/_vendor/packaging-21.3.dist-info/REQUESTED index e69de29b..e69de29b 100644 --- a/pkg_resources/_vendor/appdirs-1.4.3.dist-info/REQUESTED +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/REQUESTED diff --git a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/WHEEL b/pkg_resources/_vendor/packaging-21.3.dist-info/WHEEL index 5bad85fd..5bad85fd 100644 --- a/pkg_resources/_vendor/jaraco.context-4.1.1.dist-info/WHEEL +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/WHEEL diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/top_level.txt b/pkg_resources/_vendor/packaging-21.3.dist-info/top_level.txt index 748809f7..748809f7 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/top_level.txt +++ b/pkg_resources/_vendor/packaging-21.3.dist-info/top_level.txt diff --git a/pkg_resources/_vendor/packaging/__about__.py b/pkg_resources/_vendor/packaging/__about__.py index c359122f..3551bc2d 100644 --- a/pkg_resources/_vendor/packaging/__about__.py +++ b/pkg_resources/_vendor/packaging/__about__.py @@ -17,7 +17,7 @@ __title__ = "packaging" __summary__ = "Core utilities for Python packages" __uri__ = "https://github.com/pypa/packaging" -__version__ = "21.2" +__version__ = "21.3" __author__ = "Donald Stufft and individual contributors" __email__ = "donald@stufft.io" diff --git a/pkg_resources/_vendor/packaging/_musllinux.py b/pkg_resources/_vendor/packaging/_musllinux.py index 85450faf..8ac3059b 100644 --- a/pkg_resources/_vendor/packaging/_musllinux.py +++ b/pkg_resources/_vendor/packaging/_musllinux.py @@ -98,7 +98,7 @@ def _get_musl_version(executable: str) -> Optional[_MuslVersion]: with contextlib.ExitStack() as stack: try: f = stack.enter_context(open(executable, "rb")) - except IOError: + except OSError: return None ld = _parse_ld_musl_from_elf(f) if not ld: diff --git a/pkg_resources/_vendor/packaging/_structures.py b/pkg_resources/_vendor/packaging/_structures.py index 95154975..90a6465f 100644 --- a/pkg_resources/_vendor/packaging/_structures.py +++ b/pkg_resources/_vendor/packaging/_structures.py @@ -19,9 +19,6 @@ class InfinityType: def __eq__(self, other: object) -> bool: return isinstance(other, self.__class__) - def __ne__(self, other: object) -> bool: - return not isinstance(other, self.__class__) - def __gt__(self, other: object) -> bool: return True @@ -51,9 +48,6 @@ class NegativeInfinityType: def __eq__(self, other: object) -> bool: return isinstance(other, self.__class__) - def __ne__(self, other: object) -> bool: - return not isinstance(other, self.__class__) - def __gt__(self, other: object) -> bool: return False diff --git a/pkg_resources/_vendor/packaging/specifiers.py b/pkg_resources/_vendor/packaging/specifiers.py index ce66bd4a..0e218a6f 100644 --- a/pkg_resources/_vendor/packaging/specifiers.py +++ b/pkg_resources/_vendor/packaging/specifiers.py @@ -57,13 +57,6 @@ class BaseSpecifier(metaclass=abc.ABCMeta): objects are equal. """ - @abc.abstractmethod - def __ne__(self, other: object) -> bool: - """ - Returns a boolean representing whether or not the two Specifier like - objects are not equal. - """ - @abc.abstractproperty def prereleases(self) -> Optional[bool]: """ @@ -119,7 +112,7 @@ class _IndividualSpecifier(BaseSpecifier): else "" ) - return "<{}({!r}{})>".format(self.__class__.__name__, str(self), pre) + return f"<{self.__class__.__name__}({str(self)!r}{pre})>" def __str__(self) -> str: return "{}{}".format(*self._spec) @@ -142,17 +135,6 @@ class _IndividualSpecifier(BaseSpecifier): return self._canonical_spec == other._canonical_spec - def __ne__(self, other: object) -> bool: - if isinstance(other, str): - try: - other = self.__class__(str(other)) - except InvalidSpecifier: - return NotImplemented - elif not isinstance(other, self.__class__): - return NotImplemented - - return self._spec != other._spec - def _get_operator(self, op: str) -> CallableOperator: operator_callable: CallableOperator = getattr( self, f"_compare_{self._operators[op]}" @@ -667,7 +649,7 @@ class SpecifierSet(BaseSpecifier): else "" ) - return "<SpecifierSet({!r}{})>".format(str(self), pre) + return f"<SpecifierSet({str(self)!r}{pre})>" def __str__(self) -> str: return ",".join(sorted(str(s) for s in self._specs)) @@ -706,14 +688,6 @@ class SpecifierSet(BaseSpecifier): return self._specs == other._specs - def __ne__(self, other: object) -> bool: - if isinstance(other, (str, _IndividualSpecifier)): - other = SpecifierSet(str(other)) - elif not isinstance(other, SpecifierSet): - return NotImplemented - - return self._specs != other._specs - def __len__(self) -> int: return len(self._specs) diff --git a/pkg_resources/_vendor/packaging/tags.py b/pkg_resources/_vendor/packaging/tags.py index e65890a9..9a3d25a7 100644 --- a/pkg_resources/_vendor/packaging/tags.py +++ b/pkg_resources/_vendor/packaging/tags.py @@ -90,7 +90,7 @@ class Tag: return f"{self._interpreter}-{self._abi}-{self._platform}" def __repr__(self) -> str: - return "<{self} @ {self_id}>".format(self=self, self_id=id(self)) + return f"<{self} @ {id(self)}>" def parse_tag(tag: str) -> FrozenSet[Tag]: @@ -192,7 +192,7 @@ def cpython_tags( if not python_version: python_version = sys.version_info[:2] - interpreter = "cp{}".format(_version_nodot(python_version[:2])) + interpreter = f"cp{_version_nodot(python_version[:2])}" if abis is None: if len(python_version) > 1: @@ -268,11 +268,11 @@ def _py_interpreter_range(py_version: PythonVersion) -> Iterator[str]: all previous versions of that major version. """ if len(py_version) > 1: - yield "py{version}".format(version=_version_nodot(py_version[:2])) - yield "py{major}".format(major=py_version[0]) + yield f"py{_version_nodot(py_version[:2])}" + yield f"py{py_version[0]}" if len(py_version) > 1: for minor in range(py_version[1] - 1, -1, -1): - yield "py{version}".format(version=_version_nodot((py_version[0], minor))) + yield f"py{_version_nodot((py_version[0], minor))}" def compatible_tags( @@ -481,4 +481,7 @@ def sys_tags(*, warn: bool = False) -> Iterator[Tag]: else: yield from generic_tags() - yield from compatible_tags() + if interp_name == "pp": + yield from compatible_tags(interpreter="pp3") + else: + yield from compatible_tags() diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/INSTALLER b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/INSTALLER index a1b589e3..a1b589e3 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/INSTALLER +++ b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/INSTALLER diff --git a/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/METADATA b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/METADATA new file mode 100644 index 00000000..608afde3 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/METADATA @@ -0,0 +1,253 @@ +Metadata-Version: 2.1 +Name: platformdirs +Version: 2.6.2 +Summary: A small Python package for determining appropriate platform-specific dirs, e.g. a "user data dir". +Project-URL: Documentation, https://platformdirs.readthedocs.io +Project-URL: Homepage, https://github.com/platformdirs/platformdirs +Project-URL: Source, https://github.com/platformdirs/platformdirs +Project-URL: Tracker, https://github.com/platformdirs/platformdirs/issues +Maintainer-email: Bernát Gábor <gaborjbernat@gmail.com>, Julian Berman <Julian@GrayVines.com>, Ofek Lev <oss@ofek.dev>, Ronny Pfannschmidt <opensource@ronnypfannschmidt.de> +License-File: LICENSE +Keywords: application,cache,directory,log,user +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: License :: OSI Approved :: MIT License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3 :: Only +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Programming Language :: Python :: 3.11 +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Topic :: Software Development :: Libraries :: Python Modules +Requires-Python: >=3.7 +Requires-Dist: typing-extensions>=4.4; python_version < '3.8' +Provides-Extra: docs +Requires-Dist: furo>=2022.12.7; extra == 'docs' +Requires-Dist: proselint>=0.13; extra == 'docs' +Requires-Dist: sphinx-autodoc-typehints>=1.19.5; extra == 'docs' +Requires-Dist: sphinx>=5.3; extra == 'docs' +Provides-Extra: test +Requires-Dist: appdirs==1.4.4; extra == 'test' +Requires-Dist: covdefaults>=2.2.2; extra == 'test' +Requires-Dist: pytest-cov>=4; extra == 'test' +Requires-Dist: pytest-mock>=3.10; extra == 'test' +Requires-Dist: pytest>=7.2; extra == 'test' +Description-Content-Type: text/x-rst + +The problem +=========== + +.. image:: https://github.com/platformdirs/platformdirs/workflows/Test/badge.svg + :target: https://github.com/platformdirs/platformdirs/actions?query=workflow%3ATest + +When writing desktop application, finding the right location to store user data +and configuration varies per platform. Even for single-platform apps, there +may by plenty of nuances in figuring out the right location. + +For example, if running on macOS, you should use:: + + ~/Library/Application Support/<AppName> + +If on Windows (at least English Win XP) that should be:: + + C:\Documents and Settings\<User>\Application Data\Local Settings\<AppAuthor>\<AppName> + +or possibly:: + + C:\Documents and Settings\<User>\Application Data\<AppAuthor>\<AppName> + +for `roaming profiles <https://docs.microsoft.com/en-us/previous-versions/windows/it-pro/windows-vista/cc766489(v=ws.10)>`_ but that is another story. + +On Linux (and other Unices), according to the `XDG Basedir Spec`_, it should be:: + + ~/.local/share/<AppName> + +.. _XDG Basedir Spec: https://specifications.freedesktop.org/basedir-spec/basedir-spec-latest.html + +``platformdirs`` to the rescue +============================== + +This kind of thing is what the ``platformdirs`` package is for. +``platformdirs`` will help you choose an appropriate: + +- user data dir (``user_data_dir``) +- user config dir (``user_config_dir``) +- user cache dir (``user_cache_dir``) +- site data dir (``site_data_dir``) +- site config dir (``site_config_dir``) +- user log dir (``user_log_dir``) +- user documents dir (``user_documents_dir``) +- user runtime dir (``user_runtime_dir``) + +And also: + +- Is slightly opinionated on the directory names used. Look for "OPINION" in + documentation and code for when an opinion is being applied. + +Example output +============== + +On macOS: + +.. code-block:: pycon + + >>> from platformdirs import * + >>> appname = "SuperApp" + >>> appauthor = "Acme" + >>> user_data_dir(appname, appauthor) + '/Users/trentm/Library/Application Support/SuperApp' + >>> site_data_dir(appname, appauthor) + '/Library/Application Support/SuperApp' + >>> user_cache_dir(appname, appauthor) + '/Users/trentm/Library/Caches/SuperApp' + >>> user_log_dir(appname, appauthor) + '/Users/trentm/Library/Logs/SuperApp' + >>> user_documents_dir() + '/Users/trentm/Documents' + >>> user_runtime_dir(appname, appauthor) + '/Users/trentm/Library/Caches/TemporaryItems/SuperApp' + +On Windows 7: + +.. code-block:: pycon + + >>> from platformdirs import * + >>> appname = "SuperApp" + >>> appauthor = "Acme" + >>> user_data_dir(appname, appauthor) + 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp' + >>> user_data_dir(appname, appauthor, roaming=True) + 'C:\\Users\\trentm\\AppData\\Roaming\\Acme\\SuperApp' + >>> user_cache_dir(appname, appauthor) + 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Cache' + >>> user_log_dir(appname, appauthor) + 'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Logs' + >>> user_documents_dir() + 'C:\\Users\\trentm\\Documents' + >>> user_runtime_dir(appname, appauthor) + 'C:\\Users\\trentm\\AppData\\Local\\Temp\\Acme\\SuperApp' + +On Linux: + +.. code-block:: pycon + + >>> from platformdirs import * + >>> appname = "SuperApp" + >>> appauthor = "Acme" + >>> user_data_dir(appname, appauthor) + '/home/trentm/.local/share/SuperApp' + >>> site_data_dir(appname, appauthor) + '/usr/local/share/SuperApp' + >>> site_data_dir(appname, appauthor, multipath=True) + '/usr/local/share/SuperApp:/usr/share/SuperApp' + >>> user_cache_dir(appname, appauthor) + '/home/trentm/.cache/SuperApp' + >>> user_log_dir(appname, appauthor) + '/home/trentm/.cache/SuperApp/log' + >>> user_config_dir(appname) + '/home/trentm/.config/SuperApp' + >>> user_documents_dir() + '/home/trentm/Documents' + >>> user_runtime_dir(appname, appauthor) + '/run/user/{os.getuid()}/SuperApp' + >>> site_config_dir(appname) + '/etc/xdg/SuperApp' + >>> os.environ["XDG_CONFIG_DIRS"] = "/etc:/usr/local/etc" + >>> site_config_dir(appname, multipath=True) + '/etc/SuperApp:/usr/local/etc/SuperApp' + +On Android:: + + >>> from platformdirs import * + >>> appname = "SuperApp" + >>> appauthor = "Acme" + >>> user_data_dir(appname, appauthor) + '/data/data/com.myApp/files/SuperApp' + >>> user_cache_dir(appname, appauthor) + '/data/data/com.myApp/cache/SuperApp' + >>> user_log_dir(appname, appauthor) + '/data/data/com.myApp/cache/SuperApp/log' + >>> user_config_dir(appname) + '/data/data/com.myApp/shared_prefs/SuperApp' + >>> user_documents_dir() + '/storage/emulated/0/Documents' + >>> user_runtime_dir(appname, appauthor) + '/data/data/com.myApp/cache/SuperApp/tmp' + +Note: Some android apps like Termux and Pydroid are used as shells. These +apps are used by the end user to emulate Linux environment. Presence of +``SHELL`` environment variable is used by Platformdirs to differentiate +between general android apps and android apps used as shells. Shell android +apps also support ``XDG_*`` environment variables. + + +``PlatformDirs`` for convenience +================================ + +.. code-block:: pycon + + >>> from platformdirs import PlatformDirs + >>> dirs = PlatformDirs("SuperApp", "Acme") + >>> dirs.user_data_dir + '/Users/trentm/Library/Application Support/SuperApp' + >>> dirs.site_data_dir + '/Library/Application Support/SuperApp' + >>> dirs.user_cache_dir + '/Users/trentm/Library/Caches/SuperApp' + >>> dirs.user_log_dir + '/Users/trentm/Library/Logs/SuperApp' + >>> dirs.user_documents_dir + '/Users/trentm/Documents' + >>> dirs.user_runtime_dir + '/Users/trentm/Library/Caches/TemporaryItems/SuperApp' + +Per-version isolation +===================== + +If you have multiple versions of your app in use that you want to be +able to run side-by-side, then you may want version-isolation for these +dirs:: + + >>> from platformdirs import PlatformDirs + >>> dirs = PlatformDirs("SuperApp", "Acme", version="1.0") + >>> dirs.user_data_dir + '/Users/trentm/Library/Application Support/SuperApp/1.0' + >>> dirs.site_data_dir + '/Library/Application Support/SuperApp/1.0' + >>> dirs.user_cache_dir + '/Users/trentm/Library/Caches/SuperApp/1.0' + >>> dirs.user_log_dir + '/Users/trentm/Library/Logs/SuperApp/1.0' + >>> dirs.user_documents_dir + '/Users/trentm/Documents' + >>> dirs.user_runtime_dir + '/Users/trentm/Library/Caches/TemporaryItems/SuperApp/1.0' + +Be wary of using this for configuration files though; you'll need to handle +migrating configuration files manually. + +Why this Fork? +============== + +This repository is a friendly fork of the wonderful work started by +`ActiveState <https://github.com/ActiveState/appdirs>`_ who created +``appdirs``, this package's ancestor. + +Maintaining an open source project is no easy task, particularly +from within an organization, and the Python community is indebted +to ``appdirs`` (and to Trent Mick and Jeff Rouse in particular) for +creating an incredibly useful simple module, as evidenced by the wide +number of users it has attracted over the years. + +Nonetheless, given the number of long-standing open issues +and pull requests, and no clear path towards `ensuring +that maintenance of the package would continue or grow +<https://github.com/ActiveState/appdirs/issues/79>`_, this fork was +created. + +Contributions are most welcome. diff --git a/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/RECORD b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/RECORD new file mode 100644 index 00000000..843a5baf --- /dev/null +++ b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/RECORD @@ -0,0 +1,23 @@ +platformdirs-2.6.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+platformdirs-2.6.2.dist-info/METADATA,sha256=rDoFsb9-2tVym02IIeYCoKgGaCpY2v8xw8WWXywxhIM,9502
+platformdirs-2.6.2.dist-info/RECORD,,
+platformdirs-2.6.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+platformdirs-2.6.2.dist-info/WHEEL,sha256=NaLmgHHW_f9jTvv_wRh9vcK7c7EK9o5fwsIXMOzoGgM,87
+platformdirs-2.6.2.dist-info/licenses/LICENSE,sha256=KeD9YukphQ6G6yjD_czwzv30-pSHkBHP-z0NS-1tTbY,1089
+platformdirs/__init__.py,sha256=td0a-fHENmnG8ess2WRoysKv9ud5j6TQ-p_iUM_uE18,12864
+platformdirs/__main__.py,sha256=VsC0t5m-6f0YVr96PVks93G3EDF8MSNY4KpUMvPahDA,1164
+platformdirs/__pycache__/__init__.cpython-311.pyc,,
+platformdirs/__pycache__/__main__.cpython-311.pyc,,
+platformdirs/__pycache__/android.cpython-311.pyc,,
+platformdirs/__pycache__/api.cpython-311.pyc,,
+platformdirs/__pycache__/macos.cpython-311.pyc,,
+platformdirs/__pycache__/unix.cpython-311.pyc,,
+platformdirs/__pycache__/version.cpython-311.pyc,,
+platformdirs/__pycache__/windows.cpython-311.pyc,,
+platformdirs/android.py,sha256=GKizhyS7ESRiU67u8UnBJLm46goau9937EchXWbPBlk,4068
+platformdirs/api.py,sha256=MXKHXOL3eh_-trSok-JUTjAR_zjmmKF3rjREVABjP8s,4910
+platformdirs/macos.py,sha256=-3UXQewbT0yMhMdkzRXfXGAntmLIH7Qt4a9Hlf8I5_Y,2655
+platformdirs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+platformdirs/unix.py,sha256=P-WQjSSieE38DXjMDa1t4XHnKJQ5idEaKT0PyXwm8KQ,6911
+platformdirs/version.py,sha256=qaN-fw_htIgKUVXoAuAEVgKxQu3tZ9qE2eiKkWIS7LA,160
+platformdirs/windows.py,sha256=LOrXLgI0CjQldDo2zhOZYGYZ6g4e_cJOCB_pF9aMRWQ,6596
diff --git a/pkg_resources/_vendor/packaging-21.2.dist-info/REQUESTED b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/REQUESTED index e69de29b..e69de29b 100644 --- a/pkg_resources/_vendor/packaging-21.2.dist-info/REQUESTED +++ b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/REQUESTED diff --git a/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/WHEEL b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/WHEEL new file mode 100644 index 00000000..6d803659 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/WHEEL @@ -0,0 +1,4 @@ +Wheel-Version: 1.0 +Generator: hatchling 1.11.1 +Root-Is-Purelib: true +Tag: py3-none-any diff --git a/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/licenses/LICENSE b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/licenses/LICENSE new file mode 100644 index 00000000..f35fed91 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs-2.6.2.dist-info/licenses/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2010-202x The platformdirs developers + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/pkg_resources/_vendor/platformdirs/__init__.py b/pkg_resources/_vendor/platformdirs/__init__.py new file mode 100644 index 00000000..aef2821b --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/__init__.py @@ -0,0 +1,342 @@ +""" +Utilities for determining application-specific dirs. See <https://github.com/platformdirs/platformdirs> for details and +usage. +""" +from __future__ import annotations + +import os +import sys +from pathlib import Path + +if sys.version_info >= (3, 8): # pragma: no cover (py38+) + from typing import Literal +else: # pragma: no cover (py38+) + from ..typing_extensions import Literal + +from .api import PlatformDirsABC +from .version import __version__ +from .version import __version_tuple__ as __version_info__ + + +def _set_platform_dir_class() -> type[PlatformDirsABC]: + if sys.platform == "win32": + from .windows import Windows as Result + elif sys.platform == "darwin": + from .macos import MacOS as Result + else: + from .unix import Unix as Result + + if os.getenv("ANDROID_DATA") == "/data" and os.getenv("ANDROID_ROOT") == "/system": + + if os.getenv("SHELL") or os.getenv("PREFIX"): + return Result + + from .android import _android_folder + + if _android_folder() is not None: + from .android import Android + + return Android # return to avoid redefinition of result + + return Result + + +PlatformDirs = _set_platform_dir_class() #: Currently active platform +AppDirs = PlatformDirs #: Backwards compatibility with appdirs + + +def user_data_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param roaming: See `roaming <platformdirs.api.PlatformDirsABC.version>`. + :returns: data directory tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, roaming=roaming).user_data_dir + + +def site_data_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + multipath: bool = False, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param multipath: See `roaming <platformdirs.api.PlatformDirsABC.multipath>`. + :returns: data directory shared by users + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, multipath=multipath).site_data_dir + + +def user_config_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param roaming: See `roaming <platformdirs.api.PlatformDirsABC.version>`. + :returns: config directory tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, roaming=roaming).user_config_dir + + +def site_config_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + multipath: bool = False, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param multipath: See `roaming <platformdirs.api.PlatformDirsABC.multipath>`. + :returns: config directory shared by the users + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, multipath=multipath).site_config_dir + + +def user_cache_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + opinion: bool = True, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param opinion: See `roaming <platformdirs.api.PlatformDirsABC.opinion>`. + :returns: cache directory tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, opinion=opinion).user_cache_dir + + +def user_state_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param roaming: See `roaming <platformdirs.api.PlatformDirsABC.version>`. + :returns: state directory tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, roaming=roaming).user_state_dir + + +def user_log_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + opinion: bool = True, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param opinion: See `roaming <platformdirs.api.PlatformDirsABC.opinion>`. + :returns: log directory tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, opinion=opinion).user_log_dir + + +def user_documents_dir() -> str: + """ + :returns: documents directory tied to the user + """ + return PlatformDirs().user_documents_dir + + +def user_runtime_dir( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + opinion: bool = True, +) -> str: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param opinion: See `opinion <platformdirs.api.PlatformDirsABC.opinion>`. + :returns: runtime directory tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, opinion=opinion).user_runtime_dir + + +def user_data_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param roaming: See `roaming <platformdirs.api.PlatformDirsABC.version>`. + :returns: data path tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, roaming=roaming).user_data_path + + +def site_data_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + multipath: bool = False, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param multipath: See `multipath <platformdirs.api.PlatformDirsABC.multipath>`. + :returns: data path shared by users + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, multipath=multipath).site_data_path + + +def user_config_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param roaming: See `roaming <platformdirs.api.PlatformDirsABC.version>`. + :returns: config path tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, roaming=roaming).user_config_path + + +def site_config_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + multipath: bool = False, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param multipath: See `roaming <platformdirs.api.PlatformDirsABC.multipath>`. + :returns: config path shared by the users + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, multipath=multipath).site_config_path + + +def user_cache_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + opinion: bool = True, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param opinion: See `roaming <platformdirs.api.PlatformDirsABC.opinion>`. + :returns: cache path tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, opinion=opinion).user_cache_path + + +def user_state_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param roaming: See `roaming <platformdirs.api.PlatformDirsABC.version>`. + :returns: state path tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, roaming=roaming).user_state_path + + +def user_log_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + opinion: bool = True, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param opinion: See `roaming <platformdirs.api.PlatformDirsABC.opinion>`. + :returns: log path tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, opinion=opinion).user_log_path + + +def user_documents_path() -> Path: + """ + :returns: documents path tied to the user + """ + return PlatformDirs().user_documents_path + + +def user_runtime_path( + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + opinion: bool = True, +) -> Path: + """ + :param appname: See `appname <platformdirs.api.PlatformDirsABC.appname>`. + :param appauthor: See `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`. + :param version: See `version <platformdirs.api.PlatformDirsABC.version>`. + :param opinion: See `opinion <platformdirs.api.PlatformDirsABC.opinion>`. + :returns: runtime path tied to the user + """ + return PlatformDirs(appname=appname, appauthor=appauthor, version=version, opinion=opinion).user_runtime_path + + +__all__ = [ + "__version__", + "__version_info__", + "PlatformDirs", + "AppDirs", + "PlatformDirsABC", + "user_data_dir", + "user_config_dir", + "user_cache_dir", + "user_state_dir", + "user_log_dir", + "user_documents_dir", + "user_runtime_dir", + "site_data_dir", + "site_config_dir", + "user_data_path", + "user_config_path", + "user_cache_path", + "user_state_path", + "user_log_path", + "user_documents_path", + "user_runtime_path", + "site_data_path", + "site_config_path", +] diff --git a/pkg_resources/_vendor/platformdirs/__main__.py b/pkg_resources/_vendor/platformdirs/__main__.py new file mode 100644 index 00000000..0fc1edd5 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/__main__.py @@ -0,0 +1,46 @@ +from __future__ import annotations + +from platformdirs import PlatformDirs, __version__ + +PROPS = ( + "user_data_dir", + "user_config_dir", + "user_cache_dir", + "user_state_dir", + "user_log_dir", + "user_documents_dir", + "user_runtime_dir", + "site_data_dir", + "site_config_dir", +) + + +def main() -> None: + app_name = "MyApp" + app_author = "MyCompany" + + print(f"-- platformdirs {__version__} --") + + print("-- app dirs (with optional 'version')") + dirs = PlatformDirs(app_name, app_author, version="1.0") + for prop in PROPS: + print(f"{prop}: {getattr(dirs, prop)}") + + print("\n-- app dirs (without optional 'version')") + dirs = PlatformDirs(app_name, app_author) + for prop in PROPS: + print(f"{prop}: {getattr(dirs, prop)}") + + print("\n-- app dirs (without optional 'appauthor')") + dirs = PlatformDirs(app_name) + for prop in PROPS: + print(f"{prop}: {getattr(dirs, prop)}") + + print("\n-- app dirs (with disabled 'appauthor')") + dirs = PlatformDirs(app_name, appauthor=False) + for prop in PROPS: + print(f"{prop}: {getattr(dirs, prop)}") + + +if __name__ == "__main__": + main() diff --git a/pkg_resources/_vendor/platformdirs/android.py b/pkg_resources/_vendor/platformdirs/android.py new file mode 100644 index 00000000..eda80935 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/android.py @@ -0,0 +1,120 @@ +from __future__ import annotations + +import os +import re +import sys +from functools import lru_cache +from typing import cast + +from .api import PlatformDirsABC + + +class Android(PlatformDirsABC): + """ + Follows the guidance `from here <https://android.stackexchange.com/a/216132>`_. Makes use of the + `appname <platformdirs.api.PlatformDirsABC.appname>` and + `version <platformdirs.api.PlatformDirsABC.version>`. + """ + + @property + def user_data_dir(self) -> str: + """:return: data directory tied to the user, e.g. ``/data/user/<userid>/<packagename>/files/<AppName>``""" + return self._append_app_name_and_version(cast(str, _android_folder()), "files") + + @property + def site_data_dir(self) -> str: + """:return: data directory shared by users, same as `user_data_dir`""" + return self.user_data_dir + + @property + def user_config_dir(self) -> str: + """ + :return: config directory tied to the user, e.g. ``/data/user/<userid>/<packagename>/shared_prefs/<AppName>`` + """ + return self._append_app_name_and_version(cast(str, _android_folder()), "shared_prefs") + + @property + def site_config_dir(self) -> str: + """:return: config directory shared by the users, same as `user_config_dir`""" + return self.user_config_dir + + @property + def user_cache_dir(self) -> str: + """:return: cache directory tied to the user, e.g. e.g. ``/data/user/<userid>/<packagename>/cache/<AppName>``""" + return self._append_app_name_and_version(cast(str, _android_folder()), "cache") + + @property + def user_state_dir(self) -> str: + """:return: state directory tied to the user, same as `user_data_dir`""" + return self.user_data_dir + + @property + def user_log_dir(self) -> str: + """ + :return: log directory tied to the user, same as `user_cache_dir` if not opinionated else ``log`` in it, + e.g. ``/data/user/<userid>/<packagename>/cache/<AppName>/log`` + """ + path = self.user_cache_dir + if self.opinion: + path = os.path.join(path, "log") + return path + + @property + def user_documents_dir(self) -> str: + """ + :return: documents directory tied to the user e.g. ``/storage/emulated/0/Documents`` + """ + return _android_documents_folder() + + @property + def user_runtime_dir(self) -> str: + """ + :return: runtime directory tied to the user, same as `user_cache_dir` if not opinionated else ``tmp`` in it, + e.g. ``/data/user/<userid>/<packagename>/cache/<AppName>/tmp`` + """ + path = self.user_cache_dir + if self.opinion: + path = os.path.join(path, "tmp") + return path + + +@lru_cache(maxsize=1) +def _android_folder() -> str | None: + """:return: base folder for the Android OS or None if cannot be found""" + try: + # First try to get path to android app via pyjnius + from jnius import autoclass + + Context = autoclass("android.content.Context") # noqa: N806 + result: str | None = Context.getFilesDir().getParentFile().getAbsolutePath() + except Exception: + # if fails find an android folder looking path on the sys.path + pattern = re.compile(r"/data/(data|user/\d+)/(.+)/files") + for path in sys.path: + if pattern.match(path): + result = path.split("/files")[0] + break + else: + result = None + return result + + +@lru_cache(maxsize=1) +def _android_documents_folder() -> str: + """:return: documents folder for the Android OS""" + # Get directories with pyjnius + try: + from jnius import autoclass + + Context = autoclass("android.content.Context") # noqa: N806 + Environment = autoclass("android.os.Environment") # noqa: N806 + documents_dir: str = Context.getExternalFilesDir(Environment.DIRECTORY_DOCUMENTS).getAbsolutePath() + except Exception: + documents_dir = "/storage/emulated/0/Documents" + + return documents_dir + + +__all__ = [ + "Android", +] diff --git a/pkg_resources/_vendor/platformdirs/api.py b/pkg_resources/_vendor/platformdirs/api.py new file mode 100644 index 00000000..6f6e2c2c --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/api.py @@ -0,0 +1,156 @@ +from __future__ import annotations + +import os +import sys +from abc import ABC, abstractmethod +from pathlib import Path + +if sys.version_info >= (3, 8): # pragma: no branch + from typing import Literal # pragma: no cover + + +class PlatformDirsABC(ABC): + """ + Abstract base class for platform directories. + """ + + def __init__( + self, + appname: str | None = None, + appauthor: str | None | Literal[False] = None, + version: str | None = None, + roaming: bool = False, + multipath: bool = False, + opinion: bool = True, + ): + """ + Create a new platform directory. + + :param appname: See `appname`. + :param appauthor: See `appauthor`. + :param version: See `version`. + :param roaming: See `roaming`. + :param multipath: See `multipath`. + :param opinion: See `opinion`. + """ + self.appname = appname #: The name of application. + self.appauthor = appauthor + """ + The name of the app author or distributing body for this application. Typically, it is the owning company name. + Defaults to `appname`. You may pass ``False`` to disable it. + """ + self.version = version + """ + An optional version path element to append to the path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this would typically be ``<major>.<minor>``. + """ + self.roaming = roaming + """ + Whether to use the roaming appdata directory on Windows. That means that for users on a Windows network setup + for roaming profiles, this user data will be synced on login (see + `here <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>`_). + """ + self.multipath = multipath + """ + An optional parameter only applicable to Unix/Linux which indicates that the entire list of data dirs should be + returned. By default, the first item would only be returned. + """ + self.opinion = opinion #: A flag to indicating to use opinionated values. + + def _append_app_name_and_version(self, *base: str) -> str: + params = list(base[1:]) + if self.appname: + params.append(self.appname) + if self.version: + params.append(self.version) + return os.path.join(base[0], *params) + + @property + @abstractmethod + def user_data_dir(self) -> str: + """:return: data directory tied to the user""" + + @property + @abstractmethod + def site_data_dir(self) -> str: + """:return: data directory shared by users""" + + @property + @abstractmethod + def user_config_dir(self) -> str: + """:return: config directory tied to the user""" + + @property + @abstractmethod + def site_config_dir(self) -> str: + """:return: config directory shared by the users""" + + @property + @abstractmethod + def user_cache_dir(self) -> str: + """:return: cache directory tied to the user""" + + @property + @abstractmethod + def user_state_dir(self) -> str: + """:return: state directory tied to the user""" + + @property + @abstractmethod + def user_log_dir(self) -> str: + """:return: log directory tied to the user""" + + @property + @abstractmethod + def user_documents_dir(self) -> str: + """:return: documents directory tied to the user""" + + @property + @abstractmethod + def user_runtime_dir(self) -> str: + """:return: runtime directory tied to the user""" + + @property + def user_data_path(self) -> Path: + """:return: data path tied to the user""" + return Path(self.user_data_dir) + + @property + def site_data_path(self) -> Path: + """:return: data path shared by users""" + return Path(self.site_data_dir) + + @property + def user_config_path(self) -> Path: + """:return: config path tied to the user""" + return Path(self.user_config_dir) + + @property + def site_config_path(self) -> Path: + """:return: config path shared by the users""" + return Path(self.site_config_dir) + + @property + def user_cache_path(self) -> Path: + """:return: cache path tied to the user""" + return Path(self.user_cache_dir) + + @property + def user_state_path(self) -> Path: + """:return: state path tied to the user""" + return Path(self.user_state_dir) + + @property + def user_log_path(self) -> Path: + """:return: log path tied to the user""" + return Path(self.user_log_dir) + + @property + def user_documents_path(self) -> Path: + """:return: documents path tied to the user""" + return Path(self.user_documents_dir) + + @property + def user_runtime_path(self) -> Path: + """:return: runtime path tied to the user""" + return Path(self.user_runtime_dir) diff --git a/pkg_resources/_vendor/platformdirs/macos.py b/pkg_resources/_vendor/platformdirs/macos.py new file mode 100644 index 00000000..a01337c7 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/macos.py @@ -0,0 +1,64 @@ +from __future__ import annotations + +import os + +from .api import PlatformDirsABC + + +class MacOS(PlatformDirsABC): + """ + Platform directories for the macOS operating system. Follows the guidance from `Apple documentation + <https://developer.apple.com/library/archive/documentation/FileManagement/Conceptual/FileSystemProgrammingGuide/MacOSXDirectories/MacOSXDirectories.html>`_. + Makes use of the `appname <platformdirs.api.PlatformDirsABC.appname>` and + `version <platformdirs.api.PlatformDirsABC.version>`. + """ + + @property + def user_data_dir(self) -> str: + """:return: data directory tied to the user, e.g. ``~/Library/Application Support/$appname/$version``""" + return self._append_app_name_and_version(os.path.expanduser("~/Library/Application Support/")) + + @property + def site_data_dir(self) -> str: + """:return: data directory shared by users, e.g. ``/Library/Application Support/$appname/$version``""" + return self._append_app_name_and_version("/Library/Application Support") + + @property + def user_config_dir(self) -> str: + """:return: config directory tied to the user, e.g. ``~/Library/Preferences/$appname/$version``""" + return self._append_app_name_and_version(os.path.expanduser("~/Library/Preferences/")) + + @property + def site_config_dir(self) -> str: + """:return: config directory shared by the users, e.g. ``/Library/Preferences/$appname``""" + return self._append_app_name_and_version("/Library/Preferences") + + @property + def user_cache_dir(self) -> str: + """:return: cache directory tied to the user, e.g. ``~/Library/Caches/$appname/$version``""" + return self._append_app_name_and_version(os.path.expanduser("~/Library/Caches")) + + @property + def user_state_dir(self) -> str: + """:return: state directory tied to the user, same as `user_data_dir`""" + return self.user_data_dir + + @property + def user_log_dir(self) -> str: + """:return: log directory tied to the user, e.g. ``~/Library/Logs/$appname/$version``""" + return self._append_app_name_and_version(os.path.expanduser("~/Library/Logs")) + + @property + def user_documents_dir(self) -> str: + """:return: documents directory tied to the user, e.g. ``~/Documents``""" + return os.path.expanduser("~/Documents") + + @property + def user_runtime_dir(self) -> str: + """:return: runtime directory tied to the user, e.g. ``~/Library/Caches/TemporaryItems/$appname/$version``""" + return self._append_app_name_and_version(os.path.expanduser("~/Library/Caches/TemporaryItems")) + + +__all__ = [ + "MacOS", +] diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/REQUESTED b/pkg_resources/_vendor/platformdirs/py.typed index e69de29b..e69de29b 100644 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/REQUESTED +++ b/pkg_resources/_vendor/platformdirs/py.typed diff --git a/pkg_resources/_vendor/platformdirs/unix.py b/pkg_resources/_vendor/platformdirs/unix.py new file mode 100644 index 00000000..9aca5a03 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/unix.py @@ -0,0 +1,181 @@ +from __future__ import annotations + +import os +import sys +from configparser import ConfigParser +from pathlib import Path + +from .api import PlatformDirsABC + +if sys.platform.startswith("linux"): # pragma: no branch # no op check, only to please the type checker + from os import getuid +else: + + def getuid() -> int: + raise RuntimeError("should only be used on Linux") + + +class Unix(PlatformDirsABC): + """ + On Unix/Linux, we follow the + `XDG Basedir Spec <https://specifications.freedesktop.org/basedir-spec/basedir-spec-latest.html>`_. The spec allows + overriding directories with environment variables. The examples show are the default values, alongside the name of + the environment variable that overrides them. Makes use of the + `appname <platformdirs.api.PlatformDirsABC.appname>`, + `version <platformdirs.api.PlatformDirsABC.version>`, + `multipath <platformdirs.api.PlatformDirsABC.multipath>`, + `opinion <platformdirs.api.PlatformDirsABC.opinion>`. + """ + + @property + def user_data_dir(self) -> str: + """ + :return: data directory tied to the user, e.g. ``~/.local/share/$appname/$version`` or + ``$XDG_DATA_HOME/$appname/$version`` + """ + path = os.environ.get("XDG_DATA_HOME", "") + if not path.strip(): + path = os.path.expanduser("~/.local/share") + return self._append_app_name_and_version(path) + + @property + def site_data_dir(self) -> str: + """ + :return: data directories shared by users (if `multipath <platformdirs.api.PlatformDirsABC.multipath>` is + enabled and ``XDG_DATA_DIR`` is set and a multi path the response is also a multi path separated by the OS + path separator), e.g. ``/usr/local/share/$appname/$version`` or ``/usr/share/$appname/$version`` + """ + # XDG default for $XDG_DATA_DIRS; only first, if multipath is False + path = os.environ.get("XDG_DATA_DIRS", "") + if not path.strip(): + path = f"/usr/local/share{os.pathsep}/usr/share" + return self._with_multi_path(path) + + def _with_multi_path(self, path: str) -> str: + path_list = path.split(os.pathsep) + if not self.multipath: + path_list = path_list[0:1] + path_list = [self._append_app_name_and_version(os.path.expanduser(p)) for p in path_list] + return os.pathsep.join(path_list) + + @property + def user_config_dir(self) -> str: + """ + :return: config directory tied to the user, e.g. ``~/.config/$appname/$version`` or + ``$XDG_CONFIG_HOME/$appname/$version`` + """ + path = os.environ.get("XDG_CONFIG_HOME", "") + if not path.strip(): + path = os.path.expanduser("~/.config") + return self._append_app_name_and_version(path) + + @property + def site_config_dir(self) -> str: + """ + :return: config directories shared by users (if `multipath <platformdirs.api.PlatformDirsABC.multipath>` + is enabled and ``XDG_DATA_DIR`` is set and a multi path the response is also a multi path separated by the OS + path separator), e.g. ``/etc/xdg/$appname/$version`` + """ + # XDG default for $XDG_CONFIG_DIRS only first, if multipath is False + path = os.environ.get("XDG_CONFIG_DIRS", "") + if not path.strip(): + path = "/etc/xdg" + return self._with_multi_path(path) + + @property + def user_cache_dir(self) -> str: + """ + :return: cache directory tied to the user, e.g. ``~/.cache/$appname/$version`` or + ``~/$XDG_CACHE_HOME/$appname/$version`` + """ + path = os.environ.get("XDG_CACHE_HOME", "") + if not path.strip(): + path = os.path.expanduser("~/.cache") + return self._append_app_name_and_version(path) + + @property + def user_state_dir(self) -> str: + """ + :return: state directory tied to the user, e.g. ``~/.local/state/$appname/$version`` or + ``$XDG_STATE_HOME/$appname/$version`` + """ + path = os.environ.get("XDG_STATE_HOME", "") + if not path.strip(): + path = os.path.expanduser("~/.local/state") + return self._append_app_name_and_version(path) + + @property + def user_log_dir(self) -> str: + """ + :return: log directory tied to the user, same as `user_state_dir` if not opinionated else ``log`` in it + """ + path = self.user_state_dir + if self.opinion: + path = os.path.join(path, "log") + return path + + @property + def user_documents_dir(self) -> str: + """ + :return: documents directory tied to the user, e.g. ``~/Documents`` + """ + documents_dir = _get_user_dirs_folder("XDG_DOCUMENTS_DIR") + if documents_dir is None: + documents_dir = os.environ.get("XDG_DOCUMENTS_DIR", "").strip() + if not documents_dir: + documents_dir = os.path.expanduser("~/Documents") + + return documents_dir + + @property + def user_runtime_dir(self) -> str: + """ + :return: runtime directory tied to the user, e.g. ``/run/user/$(id -u)/$appname/$version`` or + ``$XDG_RUNTIME_DIR/$appname/$version`` + """ + path = os.environ.get("XDG_RUNTIME_DIR", "") + if not path.strip(): + path = f"/run/user/{getuid()}" + return self._append_app_name_and_version(path) + + @property + def site_data_path(self) -> Path: + """:return: data path shared by users. Only return first item, even if ``multipath`` is set to ``True``""" + return self._first_item_as_path_if_multipath(self.site_data_dir) + + @property + def site_config_path(self) -> Path: + """:return: config path shared by the users. Only return first item, even if ``multipath`` is set to ``True``""" + return self._first_item_as_path_if_multipath(self.site_config_dir) + + def _first_item_as_path_if_multipath(self, directory: str) -> Path: + if self.multipath: + # If multipath is True, the first path is returned. + directory = directory.split(os.pathsep)[0] + return Path(directory) + + +def _get_user_dirs_folder(key: str) -> str | None: + """Return directory from user-dirs.dirs config file. See https://freedesktop.org/wiki/Software/xdg-user-dirs/""" + user_dirs_config_path = os.path.join(Unix().user_config_dir, "user-dirs.dirs") + if os.path.exists(user_dirs_config_path): + parser = ConfigParser() + + with open(user_dirs_config_path) as stream: + # Add fake section header, so ConfigParser doesn't complain + parser.read_string(f"[top]\n{stream.read()}") + + if key not in parser["top"]: + return None + + path = parser["top"][key].strip('"') + # Handle relative home paths + path = path.replace("$HOME", os.path.expanduser("~")) + return path + + return None + + +__all__ = [ + "Unix", +] diff --git a/pkg_resources/_vendor/platformdirs/version.py b/pkg_resources/_vendor/platformdirs/version.py new file mode 100644 index 00000000..9f6eb98e --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/version.py @@ -0,0 +1,4 @@ +# file generated by setuptools_scm +# don't change, don't track in version control +__version__ = version = '2.6.2' +__version_tuple__ = version_tuple = (2, 6, 2) diff --git a/pkg_resources/_vendor/platformdirs/windows.py b/pkg_resources/_vendor/platformdirs/windows.py new file mode 100644 index 00000000..d5c27b34 --- /dev/null +++ b/pkg_resources/_vendor/platformdirs/windows.py @@ -0,0 +1,184 @@ +from __future__ import annotations + +import ctypes +import os +import sys +from functools import lru_cache +from typing import Callable + +from .api import PlatformDirsABC + + +class Windows(PlatformDirsABC): + """`MSDN on where to store app data files + <http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120>`_. + Makes use of the + `appname <platformdirs.api.PlatformDirsABC.appname>`, + `appauthor <platformdirs.api.PlatformDirsABC.appauthor>`, + `version <platformdirs.api.PlatformDirsABC.version>`, + `roaming <platformdirs.api.PlatformDirsABC.roaming>`, + `opinion <platformdirs.api.PlatformDirsABC.opinion>`.""" + + @property + def user_data_dir(self) -> str: + """ + :return: data directory tied to the user, e.g. + ``%USERPROFILE%\\AppData\\Local\\$appauthor\\$appname`` (not roaming) or + ``%USERPROFILE%\\AppData\\Roaming\\$appauthor\\$appname`` (roaming) + """ + const = "CSIDL_APPDATA" if self.roaming else "CSIDL_LOCAL_APPDATA" + path = os.path.normpath(get_win_folder(const)) + return self._append_parts(path) + + def _append_parts(self, path: str, *, opinion_value: str | None = None) -> str: + params = [] + if self.appname: + if self.appauthor is not False: + author = self.appauthor or self.appname + params.append(author) + params.append(self.appname) + if opinion_value is not None and self.opinion: + params.append(opinion_value) + if self.version: + params.append(self.version) + return os.path.join(path, *params) + + @property + def site_data_dir(self) -> str: + """:return: data directory shared by users, e.g. ``C:\\ProgramData\\$appauthor\\$appname``""" + path = os.path.normpath(get_win_folder("CSIDL_COMMON_APPDATA")) + return self._append_parts(path) + + @property + def user_config_dir(self) -> str: + """:return: config directory tied to the user, same as `user_data_dir`""" + return self.user_data_dir + + @property + def site_config_dir(self) -> str: + """:return: config directory shared by the users, same as `site_data_dir`""" + return self.site_data_dir + + @property + def user_cache_dir(self) -> str: + """ + :return: cache directory tied to the user (if opinionated with ``Cache`` folder within ``$appname``) e.g. + ``%USERPROFILE%\\AppData\\Local\\$appauthor\\$appname\\Cache\\$version`` + """ + path = os.path.normpath(get_win_folder("CSIDL_LOCAL_APPDATA")) + return self._append_parts(path, opinion_value="Cache") + + @property + def user_state_dir(self) -> str: + """:return: state directory tied to the user, same as `user_data_dir`""" + return self.user_data_dir + + @property + def user_log_dir(self) -> str: + """ + :return: log directory tied to the user, same as `user_data_dir` if not opinionated else ``Logs`` in it + """ + path = self.user_data_dir + if self.opinion: + path = os.path.join(path, "Logs") + return path + + @property + def user_documents_dir(self) -> str: + """ + :return: documents directory tied to the user e.g. ``%USERPROFILE%\\Documents`` + """ + return os.path.normpath(get_win_folder("CSIDL_PERSONAL")) + + @property + def user_runtime_dir(self) -> str: + """ + :return: runtime directory tied to the user, e.g. + ``%USERPROFILE%\\AppData\\Local\\Temp\\$appauthor\\$appname`` + """ + path = os.path.normpath(os.path.join(get_win_folder("CSIDL_LOCAL_APPDATA"), "Temp")) + return self._append_parts(path) + + +def get_win_folder_from_env_vars(csidl_name: str) -> str: + """Get folder from environment variables.""" + if csidl_name == "CSIDL_PERSONAL": # does not have an environment name + return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Documents") + + env_var_name = { + "CSIDL_APPDATA": "APPDATA", + "CSIDL_COMMON_APPDATA": "ALLUSERSPROFILE", + "CSIDL_LOCAL_APPDATA": "LOCALAPPDATA", + }.get(csidl_name) + if env_var_name is None: + raise ValueError(f"Unknown CSIDL name: {csidl_name}") + result = os.environ.get(env_var_name) + if result is None: + raise ValueError(f"Unset environment variable: {env_var_name}") + return result + + +def get_win_folder_from_registry(csidl_name: str) -> str: + """Get folder from the registry. + + This is a fallback technique at best. I'm not sure if using the + registry for this guarantees us the correct answer for all CSIDL_* + names. + """ + shell_folder_name = { + "CSIDL_APPDATA": "AppData", + "CSIDL_COMMON_APPDATA": "Common AppData", + "CSIDL_LOCAL_APPDATA": "Local AppData", + "CSIDL_PERSONAL": "Personal", + }.get(csidl_name) + if shell_folder_name is None: + raise ValueError(f"Unknown CSIDL name: {csidl_name}") + if sys.platform != "win32": # only needed for mypy type checker to know that this code runs only on Windows + raise NotImplementedError + import winreg + + key = winreg.OpenKey(winreg.HKEY_CURRENT_USER, r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders") + directory, _ = winreg.QueryValueEx(key, shell_folder_name) + return str(directory) + + +def get_win_folder_via_ctypes(csidl_name: str) -> str: + """Get folder with ctypes.""" + csidl_const = { + "CSIDL_APPDATA": 26, + "CSIDL_COMMON_APPDATA": 35, + "CSIDL_LOCAL_APPDATA": 28, + "CSIDL_PERSONAL": 5, + }.get(csidl_name) + if csidl_const is None: + raise ValueError(f"Unknown CSIDL name: {csidl_name}") + + buf = ctypes.create_unicode_buffer(1024) + windll = getattr(ctypes, "windll") # noqa: B009 # using getattr to avoid false positive with mypy type checker + windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf) + + # Downgrade to short path name if it has highbit chars. + if any(ord(c) > 255 for c in buf): + buf2 = ctypes.create_unicode_buffer(1024) + if windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024): + buf = buf2 + + return buf.value + + +def _pick_get_win_folder() -> Callable[[str], str]: + if hasattr(ctypes, "windll"): + return get_win_folder_via_ctypes + try: + import winreg # noqa: F401 + except ImportError: + return get_win_folder_from_env_vars + else: + return get_win_folder_from_registry + + +get_win_folder = lru_cache(maxsize=None)(_pick_get_win_folder()) + +__all__ = [ + "Windows", +] diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/DESCRIPTION.rst b/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/DESCRIPTION.rst deleted file mode 100644 index e1187231..00000000 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/DESCRIPTION.rst +++ /dev/null @@ -1,3 +0,0 @@ -UNKNOWN - - diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/METADATA b/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/METADATA deleted file mode 100644 index a15c350e..00000000 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/METADATA +++ /dev/null @@ -1,30 +0,0 @@ -Metadata-Version: 2.0 -Name: pyparsing -Version: 2.2.1 -Summary: Python parsing module -Home-page: https://github.com/pyparsing/pyparsing/ -Author: Paul McGuire -Author-email: ptmcg@users.sourceforge.net -License: MIT License -Download-URL: https://pypi.org/project/pyparsing/ -Platform: UNKNOWN -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: Intended Audience :: Information Technology -Classifier: License :: OSI Approved :: MIT License -Classifier: Operating System :: OS Independent -Classifier: Programming Language :: Python -Classifier: Programming Language :: Python :: 2 -Classifier: Programming Language :: Python :: 2.6 -Classifier: Programming Language :: Python :: 2.7 -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3.3 -Classifier: Programming Language :: Python :: 3.4 -Classifier: Programming Language :: Python :: 3.5 -Classifier: Programming Language :: Python :: 3.6 -Classifier: Programming Language :: Python :: 3.7 -Requires-Python: >=2.6, !=3.0.*, !=3.1.*, !=3.2.* - -UNKNOWN - - diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/RECORD b/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/RECORD deleted file mode 100644 index 09cc30e3..00000000 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/RECORD +++ /dev/null @@ -1,11 +0,0 @@ -__pycache__/pyparsing.cpython-310.pyc,,
-pyparsing-2.2.1.dist-info/DESCRIPTION.rst,sha256=OCTuuN6LcWulhHS3d5rfjdsQtW22n7HENFRh6jC6ego,10
-pyparsing-2.2.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-pyparsing-2.2.1.dist-info/LICENSE.txt,sha256=081Pq74Spe1XdwrGkewNKSqa078kLIh7UWI-wVjdj8I,1041
-pyparsing-2.2.1.dist-info/METADATA,sha256=I0jhx9vpUYlQXjn4gVDnFFoAt3nNrxwR4iuqA_pknYs,1091
-pyparsing-2.2.1.dist-info/RECORD,,
-pyparsing-2.2.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pyparsing-2.2.1.dist-info/WHEEL,sha256=kdsN-5OJAZIiHN-iO4Rhl82KyS0bDWf4uBwMbkNafr8,110
-pyparsing-2.2.1.dist-info/metadata.json,sha256=v1_77-dSdajUZSItSJg8Ov9M713STY3PzhyrRvs1ax4,1185
-pyparsing-2.2.1.dist-info/top_level.txt,sha256=eUOjGzJVhlQ3WS2rFAy2mN3LX_7FKTM5GSJ04jfnLmU,10
-pyparsing.py,sha256=tmrp-lu-qO1i75ZzIN5A12nKRRD1Cm4Vpk-5LR9rims,232055
diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/WHEEL b/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/WHEEL deleted file mode 100644 index 7332a419..00000000 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/WHEEL +++ /dev/null @@ -1,6 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.30.0) -Root-Is-Purelib: true -Tag: py2-none-any -Tag: py3-none-any - diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/metadata.json b/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/metadata.json deleted file mode 100644 index b760b766..00000000 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"classifiers": ["Development Status :: 5 - Production/Stable", "Intended Audience :: Developers", "Intended Audience :: Information Technology", "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python", "Programming Language :: Python :: 2", "Programming Language :: Python :: 2.6", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.3", "Programming Language :: Python :: 3.4", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: 3.7"], "download_url": "https://pypi.org/project/pyparsing/", "extensions": {"python.details": {"contacts": [{"email": "ptmcg@users.sourceforge.net", "name": "Paul McGuire", "role": "author"}], "document_names": {"description": "DESCRIPTION.rst", "license": "LICENSE.txt"}, "project_urls": {"Home": "https://github.com/pyparsing/pyparsing/"}}}, "generator": "bdist_wheel (0.30.0)", "license": "MIT License", "metadata_version": "2.0", "name": "pyparsing", "requires_python": ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*", "summary": "Python parsing module", "version": "2.2.1"}
\ No newline at end of file diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/top_level.txt b/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/top_level.txt deleted file mode 100644 index 210dfec5..00000000 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -pyparsing diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/INSTALLER b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/INSTALLER index a1b589e3..a1b589e3 100644 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/INSTALLER +++ b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/INSTALLER diff --git a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/LICENSE.txt b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/LICENSE index bbc959e0..1bf98523 100644 --- a/pkg_resources/_vendor/pyparsing-2.2.1.dist-info/LICENSE.txt +++ b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/LICENSE @@ -1,18 +1,18 @@ -Permission is hereby granted, free of charge, to any person obtaining
-a copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
-
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be +included in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. diff --git a/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/METADATA b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/METADATA new file mode 100644 index 00000000..33e51941 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/METADATA @@ -0,0 +1,105 @@ +Metadata-Version: 2.1 +Name: pyparsing +Version: 3.0.9 +Summary: pyparsing module - Classes and methods to define and execute parsing grammars +Author-email: Paul McGuire <ptmcg.gm+pyparsing@gmail.com> +Requires-Python: >=3.6.8 +Description-Content-Type: text/x-rst +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: Information Technology +Classifier: License :: OSI Approved :: MIT License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.6 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Programming Language :: Python :: 3 :: Only +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Typing :: Typed +Requires-Dist: railroad-diagrams ; extra == "diagrams" +Requires-Dist: jinja2 ; extra == "diagrams" +Project-URL: Homepage, https://github.com/pyparsing/pyparsing/ +Provides-Extra: diagrams + +PyParsing -- A Python Parsing Module +==================================== + +|Build Status| |Coverage| + +Introduction +============ + +The pyparsing module is an alternative approach to creating and +executing simple grammars, vs. the traditional lex/yacc approach, or the +use of regular expressions. The pyparsing module provides a library of +classes that client code uses to construct the grammar directly in +Python code. + +*[Since first writing this description of pyparsing in late 2003, this +technique for developing parsers has become more widespread, under the +name Parsing Expression Grammars - PEGs. See more information on PEGs* +`here <https://en.wikipedia.org/wiki/Parsing_expression_grammar>`__ +*.]* + +Here is a program to parse ``"Hello, World!"`` (or any greeting of the form +``"salutation, addressee!"``): + +.. code:: python + + from pyparsing import Word, alphas + greet = Word(alphas) + "," + Word(alphas) + "!" + hello = "Hello, World!" + print(hello, "->", greet.parseString(hello)) + +The program outputs the following:: + + Hello, World! -> ['Hello', ',', 'World', '!'] + +The Python representation of the grammar is quite readable, owing to the +self-explanatory class names, and the use of '+', '|' and '^' operator +definitions. + +The parsed results returned from ``parseString()`` is a collection of type +``ParseResults``, which can be accessed as a +nested list, a dictionary, or an object with named attributes. + +The pyparsing module handles some of the problems that are typically +vexing when writing text parsers: + +- extra or missing whitespace (the above program will also handle ``"Hello,World!"``, ``"Hello , World !"``, etc.) +- quoted strings +- embedded comments + +The examples directory includes a simple SQL parser, simple CORBA IDL +parser, a config file parser, a chemical formula parser, and a four- +function algebraic notation parser, among many others. + +Documentation +============= + +There are many examples in the online docstrings of the classes +and methods in pyparsing. You can find them compiled into `online docs <https://pyparsing-docs.readthedocs.io/en/latest/>`__. Additional +documentation resources and project info are listed in the online +`GitHub wiki <https://github.com/pyparsing/pyparsing/wiki>`__. An +entire directory of examples can be found `here <https://github.com/pyparsing/pyparsing/tree/master/examples>`__. + +License +======= + +MIT License. See header of the `pyparsing.py <https://github.com/pyparsing/pyparsing/blob/master/pyparsing/__init__.py#L1-L23>`__ file. + +History +======= + +See `CHANGES <https://github.com/pyparsing/pyparsing/blob/master/CHANGES>`__ file. + +.. |Build Status| image:: https://github.com/pyparsing/pyparsing/actions/workflows/ci.yml/badge.svg + :target: https://github.com/pyparsing/pyparsing/actions/workflows/ci.yml +.. |Coverage| image:: https://codecov.io/gh/pyparsing/pyparsing/branch/master/graph/badge.svg + :target: https://codecov.io/gh/pyparsing/pyparsing + diff --git a/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/RECORD b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/RECORD new file mode 100644 index 00000000..b07b9bd0 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/RECORD @@ -0,0 +1,29 @@ +pyparsing-3.0.9.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+pyparsing-3.0.9.dist-info/LICENSE,sha256=ENUSChaAWAT_2otojCIL-06POXQbVzIGBNRVowngGXI,1023
+pyparsing-3.0.9.dist-info/METADATA,sha256=h_fpm9rwvgZsE8v5YNF4IAo-IpaFWCOfUEm5MMByIiM,4207
+pyparsing-3.0.9.dist-info/RECORD,,
+pyparsing-3.0.9.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pyparsing-3.0.9.dist-info/WHEEL,sha256=jPMR_Dzkc4X4icQtmz81lnNY_kAsfog7ry7qoRvYLXw,81
+pyparsing/__init__.py,sha256=52QH3lgPbJhba0estckoGPHRH8JvQSSCGoWiEn2m0bU,9159
+pyparsing/__pycache__/__init__.cpython-311.pyc,,
+pyparsing/__pycache__/actions.cpython-311.pyc,,
+pyparsing/__pycache__/common.cpython-311.pyc,,
+pyparsing/__pycache__/core.cpython-311.pyc,,
+pyparsing/__pycache__/exceptions.cpython-311.pyc,,
+pyparsing/__pycache__/helpers.cpython-311.pyc,,
+pyparsing/__pycache__/results.cpython-311.pyc,,
+pyparsing/__pycache__/testing.cpython-311.pyc,,
+pyparsing/__pycache__/unicode.cpython-311.pyc,,
+pyparsing/__pycache__/util.cpython-311.pyc,,
+pyparsing/actions.py,sha256=wU9i32e0y1ymxKE3OUwSHO-SFIrt1h_wv6Ws0GQjpNU,6426
+pyparsing/common.py,sha256=lFL97ooIeR75CmW5hjURZqwDCTgruqltcTCZ-ulLO2Q,12936
+pyparsing/core.py,sha256=u8GptQE_H6wMkl8OZhxeK1aAPIDXXNgwdShORBwBVS4,213310
+pyparsing/diagram/__init__.py,sha256=f_EfxahqrdkRVahmTwLJXkZ9EEDKNd-O7lBbpJYlE1g,23668
+pyparsing/diagram/__pycache__/__init__.cpython-311.pyc,,
+pyparsing/exceptions.py,sha256=3LbSafD32NYb1Tzt85GHNkhEAU1eZkTtNSk24cPMemo,9023
+pyparsing/helpers.py,sha256=QpUOjW0-psvueMwWb9bQpU2noqKCv98_wnw1VSzSdVo,39129
+pyparsing/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pyparsing/results.py,sha256=HgNvWVXBdQP-Q6PtJfoCEeOJk2nwEvG-2KVKC5sGA30,25341
+pyparsing/testing.py,sha256=7tu4Abp4uSeJV0N_yEPRmmNUhpd18ZQP3CrX41DM814,13402
+pyparsing/unicode.py,sha256=fwuhMj30SQ165Cv7HJpu-rSxGbRm93kN9L4Ei7VGc1Y,10787
+pyparsing/util.py,sha256=kq772O5YSeXOSdP-M31EWpbH_ayj7BMHImBYo9xPD5M,6805
diff --git a/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/REQUESTED b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/REQUESTED new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/REQUESTED diff --git a/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/WHEEL b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/WHEEL new file mode 100644 index 00000000..c727d148 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing-3.0.9.dist-info/WHEEL @@ -0,0 +1,4 @@ +Wheel-Version: 1.0 +Generator: flit 3.6.0 +Root-Is-Purelib: true +Tag: py3-none-any diff --git a/pkg_resources/_vendor/pyparsing.py b/pkg_resources/_vendor/pyparsing.py deleted file mode 100644 index cf75e1e5..00000000 --- a/pkg_resources/_vendor/pyparsing.py +++ /dev/null @@ -1,5742 +0,0 @@ -# module pyparsing.py
-#
-# Copyright (c) 2003-2018 Paul T. McGuire
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-#
-
-__doc__ = \
-"""
-pyparsing module - Classes and methods to define and execute parsing grammars
-=============================================================================
-
-The pyparsing module is an alternative approach to creating and executing simple grammars,
-vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you
-don't need to learn a new syntax for defining grammars or matching expressions - the parsing module
-provides a library of classes that you use to construct the grammar directly in Python.
-
-Here is a program to parse "Hello, World!" (or any greeting of the form
-C{"<salutation>, <addressee>!"}), built up using L{Word}, L{Literal}, and L{And} elements
-(L{'+'<ParserElement.__add__>} operator gives L{And} expressions, strings are auto-converted to
-L{Literal} expressions)::
-
- from pyparsing import Word, alphas
-
- # define grammar of a greeting
- greet = Word(alphas) + "," + Word(alphas) + "!"
-
- hello = "Hello, World!"
- print (hello, "->", greet.parseString(hello))
-
-The program outputs the following::
-
- Hello, World! -> ['Hello', ',', 'World', '!']
-
-The Python representation of the grammar is quite readable, owing to the self-explanatory
-class names, and the use of '+', '|' and '^' operators.
-
-The L{ParseResults} object returned from L{ParserElement.parseString<ParserElement.parseString>} can be accessed as a nested list, a dictionary, or an
-object with named attributes.
-
-The pyparsing module handles some of the problems that are typically vexing when writing text parsers:
- - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.)
- - quoted strings
- - embedded comments
-
-
-Getting Started -
------------------
-Visit the classes L{ParserElement} and L{ParseResults} to see the base classes that most other pyparsing
-classes inherit from. Use the docstrings for examples of how to:
- - construct literal match expressions from L{Literal} and L{CaselessLiteral} classes
- - construct character word-group expressions using the L{Word} class
- - see how to create repetitive expressions using L{ZeroOrMore} and L{OneOrMore} classes
- - use L{'+'<And>}, L{'|'<MatchFirst>}, L{'^'<Or>}, and L{'&'<Each>} operators to combine simple expressions into more complex ones
- - associate names with your parsed results using L{ParserElement.setResultsName}
- - find some helpful expression short-cuts like L{delimitedList} and L{oneOf}
- - find more useful common expressions in the L{pyparsing_common} namespace class
-"""
-
-__version__ = "2.2.1"
-__versionTime__ = "18 Sep 2018 00:49 UTC"
-__author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"
-
-import string
-from weakref import ref as wkref
-import copy
-import sys
-import warnings
-import re
-import sre_constants
-import collections
-import pprint
-import traceback
-import types
-from datetime import datetime
-
-try:
- from _thread import RLock
-except ImportError:
- from threading import RLock
-
-try:
- # Python 3
- from collections.abc import Iterable
- from collections.abc import MutableMapping
-except ImportError:
- # Python 2.7
- from collections import Iterable
- from collections import MutableMapping
-
-try:
- from collections import OrderedDict as _OrderedDict
-except ImportError:
- try:
- from ordereddict import OrderedDict as _OrderedDict
- except ImportError:
- _OrderedDict = None
-
-#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )
-
-__all__ = [
-'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty',
-'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal',
-'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or',
-'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException',
-'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException',
-'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter',
-'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore',
-'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col',
-'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString',
-'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums',
-'htmlComment', 'javaStyleComment', 'line', 'lineEnd', 'lineStart', 'lineno',
-'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral',
-'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables',
-'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity',
-'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd',
-'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute',
-'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation','locatedExpr', 'withClass',
-'CloseMatch', 'tokenMap', 'pyparsing_common',
-]
-
-system_version = tuple(sys.version_info)[:3]
-PY_3 = system_version[0] == 3
-if PY_3:
- _MAX_INT = sys.maxsize
- basestring = str
- unichr = chr
- _ustr = str
-
- # build list of single arg builtins, that can be used as parse actions
- singleArgBuiltins = [sum, len, sorted, reversed, list, tuple, set, any, all, min, max]
-
-else:
- _MAX_INT = sys.maxint
- range = xrange
-
- def _ustr(obj):
- """Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries
- str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It
- then < returns the unicode object | encodes it with the default encoding | ... >.
- """
- if isinstance(obj,unicode):
- return obj
-
- try:
- # If this works, then _ustr(obj) has the same behaviour as str(obj), so
- # it won't break any existing code.
- return str(obj)
-
- except UnicodeEncodeError:
- # Else encode it
- ret = unicode(obj).encode(sys.getdefaultencoding(), 'xmlcharrefreplace')
- xmlcharref = Regex(r'&#\d+;')
- xmlcharref.setParseAction(lambda t: '\\u' + hex(int(t[0][2:-1]))[2:])
- return xmlcharref.transformString(ret)
-
- # build list of single arg builtins, tolerant of Python version, that can be used as parse actions
- singleArgBuiltins = []
- import __builtin__
- for fname in "sum len sorted reversed list tuple set any all min max".split():
- try:
- singleArgBuiltins.append(getattr(__builtin__,fname))
- except AttributeError:
- continue
-
-_generatorType = type((y for y in range(1)))
-
-def _xml_escape(data):
- """Escape &, <, >, ", ', etc. in a string of data."""
-
- # ampersand must be replaced first
- from_symbols = '&><"\''
- to_symbols = ('&'+s+';' for s in "amp gt lt quot apos".split())
- for from_,to_ in zip(from_symbols, to_symbols):
- data = data.replace(from_, to_)
- return data
-
-class _Constants(object):
- pass
-
-alphas = string.ascii_uppercase + string.ascii_lowercase
-nums = "0123456789"
-hexnums = nums + "ABCDEFabcdef"
-alphanums = alphas + nums
-_bslash = chr(92)
-printables = "".join(c for c in string.printable if c not in string.whitespace)
-
-class ParseBaseException(Exception):
- """base exception class for all parsing runtime exceptions"""
- # Performance tuning: we construct a *lot* of these, so keep this
- # constructor as small and fast as possible
- def __init__( self, pstr, loc=0, msg=None, elem=None ):
- self.loc = loc
- if msg is None:
- self.msg = pstr
- self.pstr = ""
- else:
- self.msg = msg
- self.pstr = pstr
- self.parserElement = elem
- self.args = (pstr, loc, msg)
-
- @classmethod
- def _from_exception(cls, pe):
- """
- internal factory method to simplify creating one type of ParseException
- from another - avoids having __init__ signature conflicts among subclasses
- """
- return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement)
-
- def __getattr__( self, aname ):
- """supported attributes by name are:
- - lineno - returns the line number of the exception text
- - col - returns the column number of the exception text
- - line - returns the line containing the exception text
- """
- if( aname == "lineno" ):
- return lineno( self.loc, self.pstr )
- elif( aname in ("col", "column") ):
- return col( self.loc, self.pstr )
- elif( aname == "line" ):
- return line( self.loc, self.pstr )
- else:
- raise AttributeError(aname)
-
- def __str__( self ):
- return "%s (at char %d), (line:%d, col:%d)" % \
- ( self.msg, self.loc, self.lineno, self.column )
- def __repr__( self ):
- return _ustr(self)
- def markInputline( self, markerString = ">!<" ):
- """Extracts the exception line from the input string, and marks
- the location of the exception with a special symbol.
- """
- line_str = self.line
- line_column = self.column - 1
- if markerString:
- line_str = "".join((line_str[:line_column],
- markerString, line_str[line_column:]))
- return line_str.strip()
- def __dir__(self):
- return "lineno col line".split() + dir(type(self))
-
-class ParseException(ParseBaseException):
- """
- Exception thrown when parse expressions don't match class;
- supported attributes by name are:
- - lineno - returns the line number of the exception text
- - col - returns the column number of the exception text
- - line - returns the line containing the exception text
-
- Example::
- try:
- Word(nums).setName("integer").parseString("ABC")
- except ParseException as pe:
- print(pe)
- print("column: {}".format(pe.col))
-
- prints::
- Expected integer (at char 0), (line:1, col:1)
- column: 1
- """
- pass
-
-class ParseFatalException(ParseBaseException):
- """user-throwable exception thrown when inconsistent parse content
- is found; stops all parsing immediately"""
- pass
-
-class ParseSyntaxException(ParseFatalException):
- """just like L{ParseFatalException}, but thrown internally when an
- L{ErrorStop<And._ErrorStop>} ('-' operator) indicates that parsing is to stop
- immediately because an unbacktrackable syntax error has been found"""
- pass
-
-#~ class ReparseException(ParseBaseException):
- #~ """Experimental class - parse actions can raise this exception to cause
- #~ pyparsing to reparse the input string:
- #~ - with a modified input string, and/or
- #~ - with a modified start location
- #~ Set the values of the ReparseException in the constructor, and raise the
- #~ exception in a parse action to cause pyparsing to use the new string/location.
- #~ Setting the values as None causes no change to be made.
- #~ """
- #~ def __init_( self, newstring, restartLoc ):
- #~ self.newParseText = newstring
- #~ self.reparseLoc = restartLoc
-
-class RecursiveGrammarException(Exception):
- """exception thrown by L{ParserElement.validate} if the grammar could be improperly recursive"""
- def __init__( self, parseElementList ):
- self.parseElementTrace = parseElementList
-
- def __str__( self ):
- return "RecursiveGrammarException: %s" % self.parseElementTrace
-
-class _ParseResultsWithOffset(object):
- def __init__(self,p1,p2):
- self.tup = (p1,p2)
- def __getitem__(self,i):
- return self.tup[i]
- def __repr__(self):
- return repr(self.tup[0])
- def setOffset(self,i):
- self.tup = (self.tup[0],i)
-
-class ParseResults(object):
- """
- Structured parse results, to provide multiple means of access to the parsed data:
- - as a list (C{len(results)})
- - by list index (C{results[0], results[1]}, etc.)
- - by attribute (C{results.<resultsName>} - see L{ParserElement.setResultsName})
-
- Example::
- integer = Word(nums)
- date_str = (integer.setResultsName("year") + '/'
- + integer.setResultsName("month") + '/'
- + integer.setResultsName("day"))
- # equivalent form:
- # date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
-
- # parseString returns a ParseResults object
- result = date_str.parseString("1999/12/31")
-
- def test(s, fn=repr):
- print("%s -> %s" % (s, fn(eval(s))))
- test("list(result)")
- test("result[0]")
- test("result['month']")
- test("result.day")
- test("'month' in result")
- test("'minutes' in result")
- test("result.dump()", str)
- prints::
- list(result) -> ['1999', '/', '12', '/', '31']
- result[0] -> '1999'
- result['month'] -> '12'
- result.day -> '31'
- 'month' in result -> True
- 'minutes' in result -> False
- result.dump() -> ['1999', '/', '12', '/', '31']
- - day: 31
- - month: 12
- - year: 1999
- """
- def __new__(cls, toklist=None, name=None, asList=True, modal=True ):
- if isinstance(toklist, cls):
- return toklist
- retobj = object.__new__(cls)
- retobj.__doinit = True
- return retobj
-
- # Performance tuning: we construct a *lot* of these, so keep this
- # constructor as small and fast as possible
- def __init__( self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance ):
- if self.__doinit:
- self.__doinit = False
- self.__name = None
- self.__parent = None
- self.__accumNames = {}
- self.__asList = asList
- self.__modal = modal
- if toklist is None:
- toklist = []
- if isinstance(toklist, list):
- self.__toklist = toklist[:]
- elif isinstance(toklist, _generatorType):
- self.__toklist = list(toklist)
- else:
- self.__toklist = [toklist]
- self.__tokdict = dict()
-
- if name is not None and name:
- if not modal:
- self.__accumNames[name] = 0
- if isinstance(name,int):
- name = _ustr(name) # will always return a str, but use _ustr for consistency
- self.__name = name
- if not (isinstance(toklist, (type(None), basestring, list)) and toklist in (None,'',[])):
- if isinstance(toklist,basestring):
- toklist = [ toklist ]
- if asList:
- if isinstance(toklist,ParseResults):
- self[name] = _ParseResultsWithOffset(toklist.copy(),0)
- else:
- self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0)
- self[name].__name = name
- else:
- try:
- self[name] = toklist[0]
- except (KeyError,TypeError,IndexError):
- self[name] = toklist
-
- def __getitem__( self, i ):
- if isinstance( i, (int,slice) ):
- return self.__toklist[i]
- else:
- if i not in self.__accumNames:
- return self.__tokdict[i][-1][0]
- else:
- return ParseResults([ v[0] for v in self.__tokdict[i] ])
-
- def __setitem__( self, k, v, isinstance=isinstance ):
- if isinstance(v,_ParseResultsWithOffset):
- self.__tokdict[k] = self.__tokdict.get(k,list()) + [v]
- sub = v[0]
- elif isinstance(k,(int,slice)):
- self.__toklist[k] = v
- sub = v
- else:
- self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)]
- sub = v
- if isinstance(sub,ParseResults):
- sub.__parent = wkref(self)
-
- def __delitem__( self, i ):
- if isinstance(i,(int,slice)):
- mylen = len( self.__toklist )
- del self.__toklist[i]
-
- # convert int to slice
- if isinstance(i, int):
- if i < 0:
- i += mylen
- i = slice(i, i+1)
- # get removed indices
- removed = list(range(*i.indices(mylen)))
- removed.reverse()
- # fixup indices in token dictionary
- for name,occurrences in self.__tokdict.items():
- for j in removed:
- for k, (value, position) in enumerate(occurrences):
- occurrences[k] = _ParseResultsWithOffset(value, position - (position > j))
- else:
- del self.__tokdict[i]
-
- def __contains__( self, k ):
- return k in self.__tokdict
-
- def __len__( self ): return len( self.__toklist )
- def __bool__(self): return ( not not self.__toklist )
- __nonzero__ = __bool__
- def __iter__( self ): return iter( self.__toklist )
- def __reversed__( self ): return iter( self.__toklist[::-1] )
- def _iterkeys( self ):
- if hasattr(self.__tokdict, "iterkeys"):
- return self.__tokdict.iterkeys()
- else:
- return iter(self.__tokdict)
-
- def _itervalues( self ):
- return (self[k] for k in self._iterkeys())
-
- def _iteritems( self ):
- return ((k, self[k]) for k in self._iterkeys())
-
- if PY_3:
- keys = _iterkeys
- """Returns an iterator of all named result keys (Python 3.x only)."""
-
- values = _itervalues
- """Returns an iterator of all named result values (Python 3.x only)."""
-
- items = _iteritems
- """Returns an iterator of all named result key-value tuples (Python 3.x only)."""
-
- else:
- iterkeys = _iterkeys
- """Returns an iterator of all named result keys (Python 2.x only)."""
-
- itervalues = _itervalues
- """Returns an iterator of all named result values (Python 2.x only)."""
-
- iteritems = _iteritems
- """Returns an iterator of all named result key-value tuples (Python 2.x only)."""
-
- def keys( self ):
- """Returns all named result keys (as a list in Python 2.x, as an iterator in Python 3.x)."""
- return list(self.iterkeys())
-
- def values( self ):
- """Returns all named result values (as a list in Python 2.x, as an iterator in Python 3.x)."""
- return list(self.itervalues())
-
- def items( self ):
- """Returns all named result key-values (as a list of tuples in Python 2.x, as an iterator in Python 3.x)."""
- return list(self.iteritems())
-
- def haskeys( self ):
- """Since keys() returns an iterator, this method is helpful in bypassing
- code that looks for the existence of any defined results names."""
- return bool(self.__tokdict)
-
- def pop( self, *args, **kwargs):
- """
- Removes and returns item at specified index (default=C{last}).
- Supports both C{list} and C{dict} semantics for C{pop()}. If passed no
- argument or an integer argument, it will use C{list} semantics
- and pop tokens from the list of parsed tokens. If passed a
- non-integer argument (most likely a string), it will use C{dict}
- semantics and pop the corresponding value from any defined
- results names. A second default return value argument is
- supported, just as in C{dict.pop()}.
-
- Example::
- def remove_first(tokens):
- tokens.pop(0)
- print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
- print(OneOrMore(Word(nums)).addParseAction(remove_first).parseString("0 123 321")) # -> ['123', '321']
-
- label = Word(alphas)
- patt = label("LABEL") + OneOrMore(Word(nums))
- print(patt.parseString("AAB 123 321").dump())
-
- # Use pop() in a parse action to remove named result (note that corresponding value is not
- # removed from list form of results)
- def remove_LABEL(tokens):
- tokens.pop("LABEL")
- return tokens
- patt.addParseAction(remove_LABEL)
- print(patt.parseString("AAB 123 321").dump())
- prints::
- ['AAB', '123', '321']
- - LABEL: AAB
-
- ['AAB', '123', '321']
- """
- if not args:
- args = [-1]
- for k,v in kwargs.items():
- if k == 'default':
- args = (args[0], v)
- else:
- raise TypeError("pop() got an unexpected keyword argument '%s'" % k)
- if (isinstance(args[0], int) or
- len(args) == 1 or
- args[0] in self):
- index = args[0]
- ret = self[index]
- del self[index]
- return ret
- else:
- defaultvalue = args[1]
- return defaultvalue
-
- def get(self, key, defaultValue=None):
- """
- Returns named result matching the given key, or if there is no
- such name, then returns the given C{defaultValue} or C{None} if no
- C{defaultValue} is specified.
-
- Similar to C{dict.get()}.
-
- Example::
- integer = Word(nums)
- date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
-
- result = date_str.parseString("1999/12/31")
- print(result.get("year")) # -> '1999'
- print(result.get("hour", "not specified")) # -> 'not specified'
- print(result.get("hour")) # -> None
- """
- if key in self:
- return self[key]
- else:
- return defaultValue
-
- def insert( self, index, insStr ):
- """
- Inserts new element at location index in the list of parsed tokens.
-
- Similar to C{list.insert()}.
-
- Example::
- print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
-
- # use a parse action to insert the parse location in the front of the parsed results
- def insert_locn(locn, tokens):
- tokens.insert(0, locn)
- print(OneOrMore(Word(nums)).addParseAction(insert_locn).parseString("0 123 321")) # -> [0, '0', '123', '321']
- """
- self.__toklist.insert(index, insStr)
- # fixup indices in token dictionary
- for name,occurrences in self.__tokdict.items():
- for k, (value, position) in enumerate(occurrences):
- occurrences[k] = _ParseResultsWithOffset(value, position + (position > index))
-
- def append( self, item ):
- """
- Add single element to end of ParseResults list of elements.
-
- Example::
- print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
-
- # use a parse action to compute the sum of the parsed integers, and add it to the end
- def append_sum(tokens):
- tokens.append(sum(map(int, tokens)))
- print(OneOrMore(Word(nums)).addParseAction(append_sum).parseString("0 123 321")) # -> ['0', '123', '321', 444]
- """
- self.__toklist.append(item)
-
- def extend( self, itemseq ):
- """
- Add sequence of elements to end of ParseResults list of elements.
-
- Example::
- patt = OneOrMore(Word(alphas))
-
- # use a parse action to append the reverse of the matched strings, to make a palindrome
- def make_palindrome(tokens):
- tokens.extend(reversed([t[::-1] for t in tokens]))
- return ''.join(tokens)
- print(patt.addParseAction(make_palindrome).parseString("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl'
- """
- if isinstance(itemseq, ParseResults):
- self += itemseq
- else:
- self.__toklist.extend(itemseq)
-
- def clear( self ):
- """
- Clear all elements and results names.
- """
- del self.__toklist[:]
- self.__tokdict.clear()
-
- def __getattr__( self, name ):
- try:
- return self[name]
- except KeyError:
- return ""
-
- if name in self.__tokdict:
- if name not in self.__accumNames:
- return self.__tokdict[name][-1][0]
- else:
- return ParseResults([ v[0] for v in self.__tokdict[name] ])
- else:
- return ""
-
- def __add__( self, other ):
- ret = self.copy()
- ret += other
- return ret
-
- def __iadd__( self, other ):
- if other.__tokdict:
- offset = len(self.__toklist)
- addoffset = lambda a: offset if a<0 else a+offset
- otheritems = other.__tokdict.items()
- otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) )
- for (k,vlist) in otheritems for v in vlist]
- for k,v in otherdictitems:
- self[k] = v
- if isinstance(v[0],ParseResults):
- v[0].__parent = wkref(self)
-
- self.__toklist += other.__toklist
- self.__accumNames.update( other.__accumNames )
- return self
-
- def __radd__(self, other):
- if isinstance(other,int) and other == 0:
- # useful for merging many ParseResults using sum() builtin
- return self.copy()
- else:
- # this may raise a TypeError - so be it
- return other + self
-
- def __repr__( self ):
- return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) )
-
- def __str__( self ):
- return '[' + ', '.join(_ustr(i) if isinstance(i, ParseResults) else repr(i) for i in self.__toklist) + ']'
-
- def _asStringList( self, sep='' ):
- out = []
- for item in self.__toklist:
- if out and sep:
- out.append(sep)
- if isinstance( item, ParseResults ):
- out += item._asStringList()
- else:
- out.append( _ustr(item) )
- return out
-
- def asList( self ):
- """
- Returns the parse results as a nested list of matching tokens, all converted to strings.
-
- Example::
- patt = OneOrMore(Word(alphas))
- result = patt.parseString("sldkj lsdkj sldkj")
- # even though the result prints in string-like form, it is actually a pyparsing ParseResults
- print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj']
-
- # Use asList() to create an actual list
- result_list = result.asList()
- print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj']
- """
- return [res.asList() if isinstance(res,ParseResults) else res for res in self.__toklist]
-
- def asDict( self ):
- """
- Returns the named parse results as a nested dictionary.
-
- Example::
- integer = Word(nums)
- date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
-
- result = date_str.parseString('12/31/1999')
- print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]})
-
- result_dict = result.asDict()
- print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'}
-
- # even though a ParseResults supports dict-like access, sometime you just need to have a dict
- import json
- print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable
- print(json.dumps(result.asDict())) # -> {"month": "31", "day": "1999", "year": "12"}
- """
- if PY_3:
- item_fn = self.items
- else:
- item_fn = self.iteritems
-
- def toItem(obj):
- if isinstance(obj, ParseResults):
- if obj.haskeys():
- return obj.asDict()
- else:
- return [toItem(v) for v in obj]
- else:
- return obj
-
- return dict((k,toItem(v)) for k,v in item_fn())
-
- def copy( self ):
- """
- Returns a new copy of a C{ParseResults} object.
- """
- ret = ParseResults( self.__toklist )
- ret.__tokdict = self.__tokdict.copy()
- ret.__parent = self.__parent
- ret.__accumNames.update( self.__accumNames )
- ret.__name = self.__name
- return ret
-
- def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ):
- """
- (Deprecated) Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.
- """
- nl = "\n"
- out = []
- namedItems = dict((v[1],k) for (k,vlist) in self.__tokdict.items()
- for v in vlist)
- nextLevelIndent = indent + " "
-
- # collapse out indents if formatting is not desired
- if not formatted:
- indent = ""
- nextLevelIndent = ""
- nl = ""
-
- selfTag = None
- if doctag is not None:
- selfTag = doctag
- else:
- if self.__name:
- selfTag = self.__name
-
- if not selfTag:
- if namedItemsOnly:
- return ""
- else:
- selfTag = "ITEM"
-
- out += [ nl, indent, "<", selfTag, ">" ]
-
- for i,res in enumerate(self.__toklist):
- if isinstance(res,ParseResults):
- if i in namedItems:
- out += [ res.asXML(namedItems[i],
- namedItemsOnly and doctag is None,
- nextLevelIndent,
- formatted)]
- else:
- out += [ res.asXML(None,
- namedItemsOnly and doctag is None,
- nextLevelIndent,
- formatted)]
- else:
- # individual token, see if there is a name for it
- resTag = None
- if i in namedItems:
- resTag = namedItems[i]
- if not resTag:
- if namedItemsOnly:
- continue
- else:
- resTag = "ITEM"
- xmlBodyText = _xml_escape(_ustr(res))
- out += [ nl, nextLevelIndent, "<", resTag, ">",
- xmlBodyText,
- "</", resTag, ">" ]
-
- out += [ nl, indent, "</", selfTag, ">" ]
- return "".join(out)
-
- def __lookup(self,sub):
- for k,vlist in self.__tokdict.items():
- for v,loc in vlist:
- if sub is v:
- return k
- return None
-
- def getName(self):
- r"""
- Returns the results name for this token expression. Useful when several
- different expressions might match at a particular location.
-
- Example::
- integer = Word(nums)
- ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d")
- house_number_expr = Suppress('#') + Word(nums, alphanums)
- user_data = (Group(house_number_expr)("house_number")
- | Group(ssn_expr)("ssn")
- | Group(integer)("age"))
- user_info = OneOrMore(user_data)
-
- result = user_info.parseString("22 111-22-3333 #221B")
- for item in result:
- print(item.getName(), ':', item[0])
- prints::
- age : 22
- ssn : 111-22-3333
- house_number : 221B
- """
- if self.__name:
- return self.__name
- elif self.__parent:
- par = self.__parent()
- if par:
- return par.__lookup(self)
- else:
- return None
- elif (len(self) == 1 and
- len(self.__tokdict) == 1 and
- next(iter(self.__tokdict.values()))[0][1] in (0,-1)):
- return next(iter(self.__tokdict.keys()))
- else:
- return None
-
- def dump(self, indent='', depth=0, full=True):
- """
- Diagnostic method for listing out the contents of a C{ParseResults}.
- Accepts an optional C{indent} argument so that this string can be embedded
- in a nested display of other data.
-
- Example::
- integer = Word(nums)
- date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
-
- result = date_str.parseString('12/31/1999')
- print(result.dump())
- prints::
- ['12', '/', '31', '/', '1999']
- - day: 1999
- - month: 31
- - year: 12
- """
- out = []
- NL = '\n'
- out.append( indent+_ustr(self.asList()) )
- if full:
- if self.haskeys():
- items = sorted((str(k), v) for k,v in self.items())
- for k,v in items:
- if out:
- out.append(NL)
- out.append( "%s%s- %s: " % (indent,(' '*depth), k) )
- if isinstance(v,ParseResults):
- if v:
- out.append( v.dump(indent,depth+1) )
- else:
- out.append(_ustr(v))
- else:
- out.append(repr(v))
- elif any(isinstance(vv,ParseResults) for vv in self):
- v = self
- for i,vv in enumerate(v):
- if isinstance(vv,ParseResults):
- out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),vv.dump(indent,depth+1) ))
- else:
- out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),_ustr(vv)))
-
- return "".join(out)
-
- def pprint(self, *args, **kwargs):
- """
- Pretty-printer for parsed results as a list, using the C{pprint} module.
- Accepts additional positional or keyword args as defined for the
- C{pprint.pprint} method. (U{http://docs.python.org/3/library/pprint.html#pprint.pprint})
-
- Example::
- ident = Word(alphas, alphanums)
- num = Word(nums)
- func = Forward()
- term = ident | num | Group('(' + func + ')')
- func <<= ident + Group(Optional(delimitedList(term)))
- result = func.parseString("fna a,b,(fnb c,d,200),100")
- result.pprint(width=40)
- prints::
- ['fna',
- ['a',
- 'b',
- ['(', 'fnb', ['c', 'd', '200'], ')'],
- '100']]
- """
- pprint.pprint(self.asList(), *args, **kwargs)
-
- # add support for pickle protocol
- def __getstate__(self):
- return ( self.__toklist,
- ( self.__tokdict.copy(),
- self.__parent is not None and self.__parent() or None,
- self.__accumNames,
- self.__name ) )
-
- def __setstate__(self,state):
- self.__toklist = state[0]
- (self.__tokdict,
- par,
- inAccumNames,
- self.__name) = state[1]
- self.__accumNames = {}
- self.__accumNames.update(inAccumNames)
- if par is not None:
- self.__parent = wkref(par)
- else:
- self.__parent = None
-
- def __getnewargs__(self):
- return self.__toklist, self.__name, self.__asList, self.__modal
-
- def __dir__(self):
- return (dir(type(self)) + list(self.keys()))
-
-MutableMapping.register(ParseResults)
-
-def col (loc,strg):
- """Returns current column within a string, counting newlines as line separators.
- The first column is number 1.
-
- Note: the default parsing behavior is to expand tabs in the input string
- before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
- on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
- consistent view of the parsed string, the parse location, and line and column
- positions within the parsed string.
- """
- s = strg
- return 1 if 0<loc<len(s) and s[loc-1] == '\n' else loc - s.rfind("\n", 0, loc)
-
-def lineno(loc,strg):
- """Returns current line number within a string, counting newlines as line separators.
- The first line is number 1.
-
- Note: the default parsing behavior is to expand tabs in the input string
- before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
- on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
- consistent view of the parsed string, the parse location, and line and column
- positions within the parsed string.
- """
- return strg.count("\n",0,loc) + 1
-
-def line( loc, strg ):
- """Returns the line of text containing loc within a string, counting newlines as line separators.
- """
- lastCR = strg.rfind("\n", 0, loc)
- nextCR = strg.find("\n", loc)
- if nextCR >= 0:
- return strg[lastCR+1:nextCR]
- else:
- return strg[lastCR+1:]
-
-def _defaultStartDebugAction( instring, loc, expr ):
- print (("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )))
-
-def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ):
- print ("Matched " + _ustr(expr) + " -> " + str(toks.asList()))
-
-def _defaultExceptionDebugAction( instring, loc, expr, exc ):
- print ("Exception raised:" + _ustr(exc))
-
-def nullDebugAction(*args):
- """'Do-nothing' debug action, to suppress debugging output during parsing."""
- pass
-
-# Only works on Python 3.x - nonlocal is toxic to Python 2 installs
-#~ 'decorator to trim function calls to match the arity of the target'
-#~ def _trim_arity(func, maxargs=3):
- #~ if func in singleArgBuiltins:
- #~ return lambda s,l,t: func(t)
- #~ limit = 0
- #~ foundArity = False
- #~ def wrapper(*args):
- #~ nonlocal limit,foundArity
- #~ while 1:
- #~ try:
- #~ ret = func(*args[limit:])
- #~ foundArity = True
- #~ return ret
- #~ except TypeError:
- #~ if limit == maxargs or foundArity:
- #~ raise
- #~ limit += 1
- #~ continue
- #~ return wrapper
-
-# this version is Python 2.x-3.x cross-compatible
-'decorator to trim function calls to match the arity of the target'
-def _trim_arity(func, maxargs=2):
- if func in singleArgBuiltins:
- return lambda s,l,t: func(t)
- limit = [0]
- foundArity = [False]
-
- # traceback return data structure changed in Py3.5 - normalize back to plain tuples
- if system_version[:2] >= (3,5):
- def extract_stack(limit=0):
- # special handling for Python 3.5.0 - extra deep call stack by 1
- offset = -3 if system_version == (3,5,0) else -2
- frame_summary = traceback.extract_stack(limit=-offset+limit-1)[offset]
- return [frame_summary[:2]]
- def extract_tb(tb, limit=0):
- frames = traceback.extract_tb(tb, limit=limit)
- frame_summary = frames[-1]
- return [frame_summary[:2]]
- else:
- extract_stack = traceback.extract_stack
- extract_tb = traceback.extract_tb
-
- # synthesize what would be returned by traceback.extract_stack at the call to
- # user's parse action 'func', so that we don't incur call penalty at parse time
-
- LINE_DIFF = 6
- # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND
- # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!!
- this_line = extract_stack(limit=2)[-1]
- pa_call_line_synth = (this_line[0], this_line[1]+LINE_DIFF)
-
- def wrapper(*args):
- while 1:
- try:
- ret = func(*args[limit[0]:])
- foundArity[0] = True
- return ret
- except TypeError:
- # re-raise TypeErrors if they did not come from our arity testing
- if foundArity[0]:
- raise
- else:
- try:
- tb = sys.exc_info()[-1]
- if not extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth:
- raise
- finally:
- del tb
-
- if limit[0] <= maxargs:
- limit[0] += 1
- continue
- raise
-
- # copy func name to wrapper for sensible debug output
- func_name = "<parse action>"
- try:
- func_name = getattr(func, '__name__',
- getattr(func, '__class__').__name__)
- except Exception:
- func_name = str(func)
- wrapper.__name__ = func_name
-
- return wrapper
-
-class ParserElement(object):
- """Abstract base level parser element class."""
- DEFAULT_WHITE_CHARS = " \n\t\r"
- verbose_stacktrace = False
-
- @staticmethod
- def setDefaultWhitespaceChars( chars ):
- r"""
- Overrides the default whitespace chars
-
- Example::
- # default whitespace chars are space, <TAB> and newline
- OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl']
-
- # change to just treat newline as significant
- ParserElement.setDefaultWhitespaceChars(" \t")
- OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def']
- """
- ParserElement.DEFAULT_WHITE_CHARS = chars
-
- @staticmethod
- def inlineLiteralsUsing(cls):
- """
- Set class to be used for inclusion of string literals into a parser.
-
- Example::
- # default literal class used is Literal
- integer = Word(nums)
- date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
-
- date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
-
-
- # change to Suppress
- ParserElement.inlineLiteralsUsing(Suppress)
- date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
-
- date_str.parseString("1999/12/31") # -> ['1999', '12', '31']
- """
- ParserElement._literalStringClass = cls
-
- def __init__( self, savelist=False ):
- self.parseAction = list()
- self.failAction = None
- #~ self.name = "<unknown>" # don't define self.name, let subclasses try/except upcall
- self.strRepr = None
- self.resultsName = None
- self.saveAsList = savelist
- self.skipWhitespace = True
- self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
- self.copyDefaultWhiteChars = True
- self.mayReturnEmpty = False # used when checking for left-recursion
- self.keepTabs = False
- self.ignoreExprs = list()
- self.debug = False
- self.streamlined = False
- self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index
- self.errmsg = ""
- self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all)
- self.debugActions = ( None, None, None ) #custom debug actions
- self.re = None
- self.callPreparse = True # used to avoid redundant calls to preParse
- self.callDuringTry = False
-
- def copy( self ):
- """
- Make a copy of this C{ParserElement}. Useful for defining different parse actions
- for the same parsing pattern, using copies of the original parse element.
-
- Example::
- integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
- integerK = integer.copy().addParseAction(lambda toks: toks[0]*1024) + Suppress("K")
- integerM = integer.copy().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
-
- print(OneOrMore(integerK | integerM | integer).parseString("5K 100 640K 256M"))
- prints::
- [5120, 100, 655360, 268435456]
- Equivalent form of C{expr.copy()} is just C{expr()}::
- integerM = integer().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
- """
- cpy = copy.copy( self )
- cpy.parseAction = self.parseAction[:]
- cpy.ignoreExprs = self.ignoreExprs[:]
- if self.copyDefaultWhiteChars:
- cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
- return cpy
-
- def setName( self, name ):
- """
- Define name for this expression, makes debugging and exception messages clearer.
-
- Example::
- Word(nums).parseString("ABC") # -> Exception: Expected W:(0123...) (at char 0), (line:1, col:1)
- Word(nums).setName("integer").parseString("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1)
- """
- self.name = name
- self.errmsg = "Expected " + self.name
- if hasattr(self,"exception"):
- self.exception.msg = self.errmsg
- return self
-
- def setResultsName( self, name, listAllMatches=False ):
- """
- Define name for referencing matching tokens as a nested attribute
- of the returned parse results.
- NOTE: this returns a *copy* of the original C{ParserElement} object;
- this is so that the client can define a basic element, such as an
- integer, and reference it in multiple places with different names.
-
- You can also set results names using the abbreviated syntax,
- C{expr("name")} in place of C{expr.setResultsName("name")} -
- see L{I{__call__}<__call__>}.
-
- Example::
- date_str = (integer.setResultsName("year") + '/'
- + integer.setResultsName("month") + '/'
- + integer.setResultsName("day"))
-
- # equivalent form:
- date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
- """
- newself = self.copy()
- if name.endswith("*"):
- name = name[:-1]
- listAllMatches=True
- newself.resultsName = name
- newself.modalResults = not listAllMatches
- return newself
-
- def setBreak(self,breakFlag = True):
- """Method to invoke the Python pdb debugger when this element is
- about to be parsed. Set C{breakFlag} to True to enable, False to
- disable.
- """
- if breakFlag:
- _parseMethod = self._parse
- def breaker(instring, loc, doActions=True, callPreParse=True):
- import pdb
- pdb.set_trace()
- return _parseMethod( instring, loc, doActions, callPreParse )
- breaker._originalParseMethod = _parseMethod
- self._parse = breaker
- else:
- if hasattr(self._parse,"_originalParseMethod"):
- self._parse = self._parse._originalParseMethod
- return self
-
- def setParseAction( self, *fns, **kwargs ):
- """
- Define one or more actions to perform when successfully matching parse element definition.
- Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)},
- C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where:
- - s = the original string being parsed (see note below)
- - loc = the location of the matching substring
- - toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object
- If the functions in fns modify the tokens, they can return them as the return
- value from fn, and the modified list of tokens will replace the original.
- Otherwise, fn does not need to return any value.
-
- Optional keyword arguments:
- - callDuringTry = (default=C{False}) indicate if parse action should be run during lookaheads and alternate testing
-
- Note: the default parsing behavior is to expand tabs in the input string
- before starting the parsing process. See L{I{parseString}<parseString>} for more information
- on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
- consistent view of the parsed string, the parse location, and line and column
- positions within the parsed string.
-
- Example::
- integer = Word(nums)
- date_str = integer + '/' + integer + '/' + integer
-
- date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
-
- # use parse action to convert to ints at parse time
- integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
- date_str = integer + '/' + integer + '/' + integer
-
- # note that integer fields are now ints, not strings
- date_str.parseString("1999/12/31") # -> [1999, '/', 12, '/', 31]
- """
- self.parseAction = list(map(_trim_arity, list(fns)))
- self.callDuringTry = kwargs.get("callDuringTry", False)
- return self
-
- def addParseAction( self, *fns, **kwargs ):
- """
- Add one or more parse actions to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}.
-
- See examples in L{I{copy}<copy>}.
- """
- self.parseAction += list(map(_trim_arity, list(fns)))
- self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
- return self
-
- def addCondition(self, *fns, **kwargs):
- """Add a boolean predicate function to expression's list of parse actions. See
- L{I{setParseAction}<setParseAction>} for function call signatures. Unlike C{setParseAction},
- functions passed to C{addCondition} need to return boolean success/fail of the condition.
-
- Optional keyword arguments:
- - message = define a custom message to be used in the raised exception
- - fatal = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise ParseException
-
- Example::
- integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
- year_int = integer.copy()
- year_int.addCondition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later")
- date_str = year_int + '/' + integer + '/' + integer
-
- result = date_str.parseString("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), (line:1, col:1)
- """
- msg = kwargs.get("message", "failed user-defined condition")
- exc_type = ParseFatalException if kwargs.get("fatal", False) else ParseException
- for fn in fns:
- def pa(s,l,t):
- if not bool(_trim_arity(fn)(s,l,t)):
- raise exc_type(s,l,msg)
- self.parseAction.append(pa)
- self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
- return self
-
- def setFailAction( self, fn ):
- """Define action to perform if parsing fails at this expression.
- Fail acton fn is a callable function that takes the arguments
- C{fn(s,loc,expr,err)} where:
- - s = string being parsed
- - loc = location where expression match was attempted and failed
- - expr = the parse expression that failed
- - err = the exception thrown
- The function returns no value. It may throw C{L{ParseFatalException}}
- if it is desired to stop parsing immediately."""
- self.failAction = fn
- return self
-
- def _skipIgnorables( self, instring, loc ):
- exprsFound = True
- while exprsFound:
- exprsFound = False
- for e in self.ignoreExprs:
- try:
- while 1:
- loc,dummy = e._parse( instring, loc )
- exprsFound = True
- except ParseException:
- pass
- return loc
-
- def preParse( self, instring, loc ):
- if self.ignoreExprs:
- loc = self._skipIgnorables( instring, loc )
-
- if self.skipWhitespace:
- wt = self.whiteChars
- instrlen = len(instring)
- while loc < instrlen and instring[loc] in wt:
- loc += 1
-
- return loc
-
- def parseImpl( self, instring, loc, doActions=True ):
- return loc, []
-
- def postParse( self, instring, loc, tokenlist ):
- return tokenlist
-
- #~ @profile
- def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ):
- debugging = ( self.debug ) #and doActions )
-
- if debugging or self.failAction:
- #~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) ))
- if (self.debugActions[0] ):
- self.debugActions[0]( instring, loc, self )
- if callPreParse and self.callPreparse:
- preloc = self.preParse( instring, loc )
- else:
- preloc = loc
- tokensStart = preloc
- try:
- try:
- loc,tokens = self.parseImpl( instring, preloc, doActions )
- except IndexError:
- raise ParseException( instring, len(instring), self.errmsg, self )
- except ParseBaseException as err:
- #~ print ("Exception raised:", err)
- if self.debugActions[2]:
- self.debugActions[2]( instring, tokensStart, self, err )
- if self.failAction:
- self.failAction( instring, tokensStart, self, err )
- raise
- else:
- if callPreParse and self.callPreparse:
- preloc = self.preParse( instring, loc )
- else:
- preloc = loc
- tokensStart = preloc
- if self.mayIndexError or preloc >= len(instring):
- try:
- loc,tokens = self.parseImpl( instring, preloc, doActions )
- except IndexError:
- raise ParseException( instring, len(instring), self.errmsg, self )
- else:
- loc,tokens = self.parseImpl( instring, preloc, doActions )
-
- tokens = self.postParse( instring, loc, tokens )
-
- retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults )
- if self.parseAction and (doActions or self.callDuringTry):
- if debugging:
- try:
- for fn in self.parseAction:
- tokens = fn( instring, tokensStart, retTokens )
- if tokens is not None:
- retTokens = ParseResults( tokens,
- self.resultsName,
- asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
- modal=self.modalResults )
- except ParseBaseException as err:
- #~ print "Exception raised in user parse action:", err
- if (self.debugActions[2] ):
- self.debugActions[2]( instring, tokensStart, self, err )
- raise
- else:
- for fn in self.parseAction:
- tokens = fn( instring, tokensStart, retTokens )
- if tokens is not None:
- retTokens = ParseResults( tokens,
- self.resultsName,
- asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
- modal=self.modalResults )
- if debugging:
- #~ print ("Matched",self,"->",retTokens.asList())
- if (self.debugActions[1] ):
- self.debugActions[1]( instring, tokensStart, loc, self, retTokens )
-
- return loc, retTokens
-
- def tryParse( self, instring, loc ):
- try:
- return self._parse( instring, loc, doActions=False )[0]
- except ParseFatalException:
- raise ParseException( instring, loc, self.errmsg, self)
-
- def canParseNext(self, instring, loc):
- try:
- self.tryParse(instring, loc)
- except (ParseException, IndexError):
- return False
- else:
- return True
-
- class _UnboundedCache(object):
- def __init__(self):
- cache = {}
- self.not_in_cache = not_in_cache = object()
-
- def get(self, key):
- return cache.get(key, not_in_cache)
-
- def set(self, key, value):
- cache[key] = value
-
- def clear(self):
- cache.clear()
-
- def cache_len(self):
- return len(cache)
-
- self.get = types.MethodType(get, self)
- self.set = types.MethodType(set, self)
- self.clear = types.MethodType(clear, self)
- self.__len__ = types.MethodType(cache_len, self)
-
- if _OrderedDict is not None:
- class _FifoCache(object):
- def __init__(self, size):
- self.not_in_cache = not_in_cache = object()
-
- cache = _OrderedDict()
-
- def get(self, key):
- return cache.get(key, not_in_cache)
-
- def set(self, key, value):
- cache[key] = value
- while len(cache) > size:
- try:
- cache.popitem(False)
- except KeyError:
- pass
-
- def clear(self):
- cache.clear()
-
- def cache_len(self):
- return len(cache)
-
- self.get = types.MethodType(get, self)
- self.set = types.MethodType(set, self)
- self.clear = types.MethodType(clear, self)
- self.__len__ = types.MethodType(cache_len, self)
-
- else:
- class _FifoCache(object):
- def __init__(self, size):
- self.not_in_cache = not_in_cache = object()
-
- cache = {}
- key_fifo = collections.deque([], size)
-
- def get(self, key):
- return cache.get(key, not_in_cache)
-
- def set(self, key, value):
- cache[key] = value
- while len(key_fifo) > size:
- cache.pop(key_fifo.popleft(), None)
- key_fifo.append(key)
-
- def clear(self):
- cache.clear()
- key_fifo.clear()
-
- def cache_len(self):
- return len(cache)
-
- self.get = types.MethodType(get, self)
- self.set = types.MethodType(set, self)
- self.clear = types.MethodType(clear, self)
- self.__len__ = types.MethodType(cache_len, self)
-
- # argument cache for optimizing repeated calls when backtracking through recursive expressions
- packrat_cache = {} # this is set later by enabledPackrat(); this is here so that resetCache() doesn't fail
- packrat_cache_lock = RLock()
- packrat_cache_stats = [0, 0]
-
- # this method gets repeatedly called during backtracking with the same arguments -
- # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression
- def _parseCache( self, instring, loc, doActions=True, callPreParse=True ):
- HIT, MISS = 0, 1
- lookup = (self, instring, loc, callPreParse, doActions)
- with ParserElement.packrat_cache_lock:
- cache = ParserElement.packrat_cache
- value = cache.get(lookup)
- if value is cache.not_in_cache:
- ParserElement.packrat_cache_stats[MISS] += 1
- try:
- value = self._parseNoCache(instring, loc, doActions, callPreParse)
- except ParseBaseException as pe:
- # cache a copy of the exception, without the traceback
- cache.set(lookup, pe.__class__(*pe.args))
- raise
- else:
- cache.set(lookup, (value[0], value[1].copy()))
- return value
- else:
- ParserElement.packrat_cache_stats[HIT] += 1
- if isinstance(value, Exception):
- raise value
- return (value[0], value[1].copy())
-
- _parse = _parseNoCache
-
- @staticmethod
- def resetCache():
- ParserElement.packrat_cache.clear()
- ParserElement.packrat_cache_stats[:] = [0] * len(ParserElement.packrat_cache_stats)
-
- _packratEnabled = False
- @staticmethod
- def enablePackrat(cache_size_limit=128):
- """Enables "packrat" parsing, which adds memoizing to the parsing logic.
- Repeated parse attempts at the same string location (which happens
- often in many complex grammars) can immediately return a cached value,
- instead of re-executing parsing/validating code. Memoizing is done of
- both valid results and parsing exceptions.
-
- Parameters:
- - cache_size_limit - (default=C{128}) - if an integer value is provided
- will limit the size of the packrat cache; if None is passed, then
- the cache size will be unbounded; if 0 is passed, the cache will
- be effectively disabled.
-
- This speedup may break existing programs that use parse actions that
- have side-effects. For this reason, packrat parsing is disabled when
- you first import pyparsing. To activate the packrat feature, your
- program must call the class method C{ParserElement.enablePackrat()}. If
- your program uses C{psyco} to "compile as you go", you must call
- C{enablePackrat} before calling C{psyco.full()}. If you do not do this,
- Python will crash. For best results, call C{enablePackrat()} immediately
- after importing pyparsing.
-
- Example::
- import pyparsing
- pyparsing.ParserElement.enablePackrat()
- """
- if not ParserElement._packratEnabled:
- ParserElement._packratEnabled = True
- if cache_size_limit is None:
- ParserElement.packrat_cache = ParserElement._UnboundedCache()
- else:
- ParserElement.packrat_cache = ParserElement._FifoCache(cache_size_limit)
- ParserElement._parse = ParserElement._parseCache
-
- def parseString( self, instring, parseAll=False ):
- """
- Execute the parse expression with the given string.
- This is the main interface to the client code, once the complete
- expression has been built.
-
- If you want the grammar to require that the entire input string be
- successfully parsed, then set C{parseAll} to True (equivalent to ending
- the grammar with C{L{StringEnd()}}).
-
- Note: C{parseString} implicitly calls C{expandtabs()} on the input string,
- in order to report proper column numbers in parse actions.
- If the input string contains tabs and
- the grammar uses parse actions that use the C{loc} argument to index into the
- string being parsed, you can ensure you have a consistent view of the input
- string by:
- - calling C{parseWithTabs} on your grammar before calling C{parseString}
- (see L{I{parseWithTabs}<parseWithTabs>})
- - define your parse action using the full C{(s,loc,toks)} signature, and
- reference the input string using the parse action's C{s} argument
- - explictly expand the tabs in your input string before calling
- C{parseString}
-
- Example::
- Word('a').parseString('aaaaabaaa') # -> ['aaaaa']
- Word('a').parseString('aaaaabaaa', parseAll=True) # -> Exception: Expected end of text
- """
- ParserElement.resetCache()
- if not self.streamlined:
- self.streamline()
- #~ self.saveAsList = True
- for e in self.ignoreExprs:
- e.streamline()
- if not self.keepTabs:
- instring = instring.expandtabs()
- try:
- loc, tokens = self._parse( instring, 0 )
- if parseAll:
- loc = self.preParse( instring, loc )
- se = Empty() + StringEnd()
- se._parse( instring, loc )
- except ParseBaseException as exc:
- if ParserElement.verbose_stacktrace:
- raise
- else:
- # catch and re-raise exception from here, clears out pyparsing internal stack trace
- raise exc
- else:
- return tokens
-
- def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ):
- """
- Scan the input string for expression matches. Each match will return the
- matching tokens, start location, and end location. May be called with optional
- C{maxMatches} argument, to clip scanning after 'n' matches are found. If
- C{overlap} is specified, then overlapping matches will be reported.
-
- Note that the start and end locations are reported relative to the string
- being parsed. See L{I{parseString}<parseString>} for more information on parsing
- strings with embedded tabs.
-
- Example::
- source = "sldjf123lsdjjkf345sldkjf879lkjsfd987"
- print(source)
- for tokens,start,end in Word(alphas).scanString(source):
- print(' '*start + '^'*(end-start))
- print(' '*start + tokens[0])
-
- prints::
-
- sldjf123lsdjjkf345sldkjf879lkjsfd987
- ^^^^^
- sldjf
- ^^^^^^^
- lsdjjkf
- ^^^^^^
- sldkjf
- ^^^^^^
- lkjsfd
- """
- if not self.streamlined:
- self.streamline()
- for e in self.ignoreExprs:
- e.streamline()
-
- if not self.keepTabs:
- instring = _ustr(instring).expandtabs()
- instrlen = len(instring)
- loc = 0
- preparseFn = self.preParse
- parseFn = self._parse
- ParserElement.resetCache()
- matches = 0
- try:
- while loc <= instrlen and matches < maxMatches:
- try:
- preloc = preparseFn( instring, loc )
- nextLoc,tokens = parseFn( instring, preloc, callPreParse=False )
- except ParseException:
- loc = preloc+1
- else:
- if nextLoc > loc:
- matches += 1
- yield tokens, preloc, nextLoc
- if overlap:
- nextloc = preparseFn( instring, loc )
- if nextloc > loc:
- loc = nextLoc
- else:
- loc += 1
- else:
- loc = nextLoc
- else:
- loc = preloc+1
- except ParseBaseException as exc:
- if ParserElement.verbose_stacktrace:
- raise
- else:
- # catch and re-raise exception from here, clears out pyparsing internal stack trace
- raise exc
-
- def transformString( self, instring ):
- """
- Extension to C{L{scanString}}, to modify matching text with modified tokens that may
- be returned from a parse action. To use C{transformString}, define a grammar and
- attach a parse action to it that modifies the returned token list.
- Invoking C{transformString()} on a target string will then scan for matches,
- and replace the matched text patterns according to the logic in the parse
- action. C{transformString()} returns the resulting transformed string.
-
- Example::
- wd = Word(alphas)
- wd.setParseAction(lambda toks: toks[0].title())
-
- print(wd.transformString("now is the winter of our discontent made glorious summer by this sun of york."))
- Prints::
- Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York.
- """
- out = []
- lastE = 0
- # force preservation of <TAB>s, to minimize unwanted transformation of string, and to
- # keep string locs straight between transformString and scanString
- self.keepTabs = True
- try:
- for t,s,e in self.scanString( instring ):
- out.append( instring[lastE:s] )
- if t:
- if isinstance(t,ParseResults):
- out += t.asList()
- elif isinstance(t,list):
- out += t
- else:
- out.append(t)
- lastE = e
- out.append(instring[lastE:])
- out = [o for o in out if o]
- return "".join(map(_ustr,_flatten(out)))
- except ParseBaseException as exc:
- if ParserElement.verbose_stacktrace:
- raise
- else:
- # catch and re-raise exception from here, clears out pyparsing internal stack trace
- raise exc
-
- def searchString( self, instring, maxMatches=_MAX_INT ):
- """
- Another extension to C{L{scanString}}, simplifying the access to the tokens found
- to match the given parse expression. May be called with optional
- C{maxMatches} argument, to clip searching after 'n' matches are found.
-
- Example::
- # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters
- cap_word = Word(alphas.upper(), alphas.lower())
-
- print(cap_word.searchString("More than Iron, more than Lead, more than Gold I need Electricity"))
-
- # the sum() builtin can be used to merge results into a single ParseResults object
- print(sum(cap_word.searchString("More than Iron, more than Lead, more than Gold I need Electricity")))
- prints::
- [['More'], ['Iron'], ['Lead'], ['Gold'], ['I'], ['Electricity']]
- ['More', 'Iron', 'Lead', 'Gold', 'I', 'Electricity']
- """
- try:
- return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ])
- except ParseBaseException as exc:
- if ParserElement.verbose_stacktrace:
- raise
- else:
- # catch and re-raise exception from here, clears out pyparsing internal stack trace
- raise exc
-
- def split(self, instring, maxsplit=_MAX_INT, includeSeparators=False):
- """
- Generator method to split a string using the given expression as a separator.
- May be called with optional C{maxsplit} argument, to limit the number of splits;
- and the optional C{includeSeparators} argument (default=C{False}), if the separating
- matching text should be included in the split results.
-
- Example::
- punc = oneOf(list(".,;:/-!?"))
- print(list(punc.split("This, this?, this sentence, is badly punctuated!")))
- prints::
- ['This', ' this', '', ' this sentence', ' is badly punctuated', '']
- """
- splits = 0
- last = 0
- for t,s,e in self.scanString(instring, maxMatches=maxsplit):
- yield instring[last:s]
- if includeSeparators:
- yield t[0]
- last = e
- yield instring[last:]
-
- def __add__(self, other ):
- """
- Implementation of + operator - returns C{L{And}}. Adding strings to a ParserElement
- converts them to L{Literal}s by default.
-
- Example::
- greet = Word(alphas) + "," + Word(alphas) + "!"
- hello = "Hello, World!"
- print (hello, "->", greet.parseString(hello))
- Prints::
- Hello, World! -> ['Hello', ',', 'World', '!']
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return And( [ self, other ] )
-
- def __radd__(self, other ):
- """
- Implementation of + operator when left operand is not a C{L{ParserElement}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return other + self
-
- def __sub__(self, other):
- """
- Implementation of - operator, returns C{L{And}} with error stop
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return self + And._ErrorStop() + other
-
- def __rsub__(self, other ):
- """
- Implementation of - operator when left operand is not a C{L{ParserElement}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return other - self
-
- def __mul__(self,other):
- """
- Implementation of * operator, allows use of C{expr * 3} in place of
- C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer
- tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples
- may also include C{None} as in:
- - C{expr*(n,None)} or C{expr*(n,)} is equivalent
- to C{expr*n + L{ZeroOrMore}(expr)}
- (read as "at least n instances of C{expr}")
- - C{expr*(None,n)} is equivalent to C{expr*(0,n)}
- (read as "0 to n instances of C{expr}")
- - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)}
- - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)}
-
- Note that C{expr*(None,n)} does not raise an exception if
- more than n exprs exist in the input stream; that is,
- C{expr*(None,n)} does not enforce a maximum number of expr
- occurrences. If this behavior is desired, then write
- C{expr*(None,n) + ~expr}
- """
- if isinstance(other,int):
- minElements, optElements = other,0
- elif isinstance(other,tuple):
- other = (other + (None, None))[:2]
- if other[0] is None:
- other = (0, other[1])
- if isinstance(other[0],int) and other[1] is None:
- if other[0] == 0:
- return ZeroOrMore(self)
- if other[0] == 1:
- return OneOrMore(self)
- else:
- return self*other[0] + ZeroOrMore(self)
- elif isinstance(other[0],int) and isinstance(other[1],int):
- minElements, optElements = other
- optElements -= minElements
- else:
- raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1]))
- else:
- raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other))
-
- if minElements < 0:
- raise ValueError("cannot multiply ParserElement by negative value")
- if optElements < 0:
- raise ValueError("second tuple value must be greater or equal to first tuple value")
- if minElements == optElements == 0:
- raise ValueError("cannot multiply ParserElement by 0 or (0,0)")
-
- if (optElements):
- def makeOptionalList(n):
- if n>1:
- return Optional(self + makeOptionalList(n-1))
- else:
- return Optional(self)
- if minElements:
- if minElements == 1:
- ret = self + makeOptionalList(optElements)
- else:
- ret = And([self]*minElements) + makeOptionalList(optElements)
- else:
- ret = makeOptionalList(optElements)
- else:
- if minElements == 1:
- ret = self
- else:
- ret = And([self]*minElements)
- return ret
-
- def __rmul__(self, other):
- return self.__mul__(other)
-
- def __or__(self, other ):
- """
- Implementation of | operator - returns C{L{MatchFirst}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return MatchFirst( [ self, other ] )
-
- def __ror__(self, other ):
- """
- Implementation of | operator when left operand is not a C{L{ParserElement}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return other | self
-
- def __xor__(self, other ):
- """
- Implementation of ^ operator - returns C{L{Or}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return Or( [ self, other ] )
-
- def __rxor__(self, other ):
- """
- Implementation of ^ operator when left operand is not a C{L{ParserElement}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return other ^ self
-
- def __and__(self, other ):
- """
- Implementation of & operator - returns C{L{Each}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return Each( [ self, other ] )
-
- def __rand__(self, other ):
- """
- Implementation of & operator when left operand is not a C{L{ParserElement}}
- """
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- if not isinstance( other, ParserElement ):
- warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
- SyntaxWarning, stacklevel=2)
- return None
- return other & self
-
- def __invert__( self ):
- """
- Implementation of ~ operator - returns C{L{NotAny}}
- """
- return NotAny( self )
-
- def __call__(self, name=None):
- """
- Shortcut for C{L{setResultsName}}, with C{listAllMatches=False}.
-
- If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be
- passed as C{True}.
-
- If C{name} is omitted, same as calling C{L{copy}}.
-
- Example::
- # these are equivalent
- userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno")
- userdata = Word(alphas)("name") + Word(nums+"-")("socsecno")
- """
- if name is not None:
- return self.setResultsName(name)
- else:
- return self.copy()
-
- def suppress( self ):
- """
- Suppresses the output of this C{ParserElement}; useful to keep punctuation from
- cluttering up returned output.
- """
- return Suppress( self )
-
- def leaveWhitespace( self ):
- """
- Disables the skipping of whitespace before matching the characters in the
- C{ParserElement}'s defined pattern. This is normally only used internally by
- the pyparsing module, but may be needed in some whitespace-sensitive grammars.
- """
- self.skipWhitespace = False
- return self
-
- def setWhitespaceChars( self, chars ):
- """
- Overrides the default whitespace chars
- """
- self.skipWhitespace = True
- self.whiteChars = chars
- self.copyDefaultWhiteChars = False
- return self
-
- def parseWithTabs( self ):
- """
- Overrides default behavior to expand C{<TAB>}s to spaces before parsing the input string.
- Must be called before C{parseString} when the input grammar contains elements that
- match C{<TAB>} characters.
- """
- self.keepTabs = True
- return self
-
- def ignore( self, other ):
- """
- Define expression to be ignored (e.g., comments) while doing pattern
- matching; may be called repeatedly, to define multiple comment or other
- ignorable patterns.
-
- Example::
- patt = OneOrMore(Word(alphas))
- patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj']
-
- patt.ignore(cStyleComment)
- patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj', 'lskjd']
- """
- if isinstance(other, basestring):
- other = Suppress(other)
-
- if isinstance( other, Suppress ):
- if other not in self.ignoreExprs:
- self.ignoreExprs.append(other)
- else:
- self.ignoreExprs.append( Suppress( other.copy() ) )
- return self
-
- def setDebugActions( self, startAction, successAction, exceptionAction ):
- """
- Enable display of debugging messages while doing pattern matching.
- """
- self.debugActions = (startAction or _defaultStartDebugAction,
- successAction or _defaultSuccessDebugAction,
- exceptionAction or _defaultExceptionDebugAction)
- self.debug = True
- return self
-
- def setDebug( self, flag=True ):
- """
- Enable display of debugging messages while doing pattern matching.
- Set C{flag} to True to enable, False to disable.
-
- Example::
- wd = Word(alphas).setName("alphaword")
- integer = Word(nums).setName("numword")
- term = wd | integer
-
- # turn on debugging for wd
- wd.setDebug()
-
- OneOrMore(term).parseString("abc 123 xyz 890")
-
- prints::
- Match alphaword at loc 0(1,1)
- Matched alphaword -> ['abc']
- Match alphaword at loc 3(1,4)
- Exception raised:Expected alphaword (at char 4), (line:1, col:5)
- Match alphaword at loc 7(1,8)
- Matched alphaword -> ['xyz']
- Match alphaword at loc 11(1,12)
- Exception raised:Expected alphaword (at char 12), (line:1, col:13)
- Match alphaword at loc 15(1,16)
- Exception raised:Expected alphaword (at char 15), (line:1, col:16)
-
- The output shown is that produced by the default debug actions - custom debug actions can be
- specified using L{setDebugActions}. Prior to attempting
- to match the C{wd} expression, the debugging message C{"Match <exprname> at loc <n>(<line>,<col>)"}
- is shown. Then if the parse succeeds, a C{"Matched"} message is shown, or an C{"Exception raised"}
- message is shown. Also note the use of L{setName} to assign a human-readable name to the expression,
- which makes debugging and exception messages easier to understand - for instance, the default
- name created for the C{Word} expression without calling C{setName} is C{"W:(ABCD...)"}.
- """
- if flag:
- self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction )
- else:
- self.debug = False
- return self
-
- def __str__( self ):
- return self.name
-
- def __repr__( self ):
- return _ustr(self)
-
- def streamline( self ):
- self.streamlined = True
- self.strRepr = None
- return self
-
- def checkRecursion( self, parseElementList ):
- pass
-
- def validate( self, validateTrace=[] ):
- """
- Check defined expressions for valid structure, check for infinite recursive definitions.
- """
- self.checkRecursion( [] )
-
- def parseFile( self, file_or_filename, parseAll=False ):
- """
- Execute the parse expression on the given file or filename.
- If a filename is specified (instead of a file object),
- the entire file is opened, read, and closed before parsing.
- """
- try:
- file_contents = file_or_filename.read()
- except AttributeError:
- with open(file_or_filename, "r") as f:
- file_contents = f.read()
- try:
- return self.parseString(file_contents, parseAll)
- except ParseBaseException as exc:
- if ParserElement.verbose_stacktrace:
- raise
- else:
- # catch and re-raise exception from here, clears out pyparsing internal stack trace
- raise exc
-
- def __eq__(self,other):
- if isinstance(other, ParserElement):
- return self is other or vars(self) == vars(other)
- elif isinstance(other, basestring):
- return self.matches(other)
- else:
- return super(ParserElement,self)==other
-
- def __ne__(self,other):
- return not (self == other)
-
- def __hash__(self):
- return hash(id(self))
-
- def __req__(self,other):
- return self == other
-
- def __rne__(self,other):
- return not (self == other)
-
- def matches(self, testString, parseAll=True):
- """
- Method for quick testing of a parser against a test string. Good for simple
- inline microtests of sub expressions while building up larger parser.
-
- Parameters:
- - testString - to test against this expression for a match
- - parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
-
- Example::
- expr = Word(nums)
- assert expr.matches("100")
- """
- try:
- self.parseString(_ustr(testString), parseAll=parseAll)
- return True
- except ParseBaseException:
- return False
-
- def runTests(self, tests, parseAll=True, comment='#', fullDump=True, printResults=True, failureTests=False):
- """
- Execute the parse expression on a series of test strings, showing each
- test, the parsed results or where the parse failed. Quick and easy way to
- run a parse expression against a list of sample strings.
-
- Parameters:
- - tests - a list of separate test strings, or a multiline string of test strings
- - parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
- - comment - (default=C{'#'}) - expression for indicating embedded comments in the test
- string; pass None to disable comment filtering
- - fullDump - (default=C{True}) - dump results as list followed by results names in nested outline;
- if False, only dump nested list
- - printResults - (default=C{True}) prints test output to stdout
- - failureTests - (default=C{False}) indicates if these tests are expected to fail parsing
-
- Returns: a (success, results) tuple, where success indicates that all tests succeeded
- (or failed if C{failureTests} is True), and the results contain a list of lines of each
- test's output
-
- Example::
- number_expr = pyparsing_common.number.copy()
-
- result = number_expr.runTests('''
- # unsigned integer
- 100
- # negative integer
- -100
- # float with scientific notation
- 6.02e23
- # integer with scientific notation
- 1e-12
- ''')
- print("Success" if result[0] else "Failed!")
-
- result = number_expr.runTests('''
- # stray character
- 100Z
- # missing leading digit before '.'
- -.100
- # too many '.'
- 3.14.159
- ''', failureTests=True)
- print("Success" if result[0] else "Failed!")
- prints::
- # unsigned integer
- 100
- [100]
-
- # negative integer
- -100
- [-100]
-
- # float with scientific notation
- 6.02e23
- [6.02e+23]
-
- # integer with scientific notation
- 1e-12
- [1e-12]
-
- Success
-
- # stray character
- 100Z
- ^
- FAIL: Expected end of text (at char 3), (line:1, col:4)
-
- # missing leading digit before '.'
- -.100
- ^
- FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1)
-
- # too many '.'
- 3.14.159
- ^
- FAIL: Expected end of text (at char 4), (line:1, col:5)
-
- Success
-
- Each test string must be on a single line. If you want to test a string that spans multiple
- lines, create a test like this::
-
- expr.runTest(r"this is a test\\n of strings that spans \\n 3 lines")
-
- (Note that this is a raw string literal, you must include the leading 'r'.)
- """
- if isinstance(tests, basestring):
- tests = list(map(str.strip, tests.rstrip().splitlines()))
- if isinstance(comment, basestring):
- comment = Literal(comment)
- allResults = []
- comments = []
- success = True
- for t in tests:
- if comment is not None and comment.matches(t, False) or comments and not t:
- comments.append(t)
- continue
- if not t:
- continue
- out = ['\n'.join(comments), t]
- comments = []
- try:
- t = t.replace(r'\n','\n')
- result = self.parseString(t, parseAll=parseAll)
- out.append(result.dump(full=fullDump))
- success = success and not failureTests
- except ParseBaseException as pe:
- fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else ""
- if '\n' in t:
- out.append(line(pe.loc, t))
- out.append(' '*(col(pe.loc,t)-1) + '^' + fatal)
- else:
- out.append(' '*pe.loc + '^' + fatal)
- out.append("FAIL: " + str(pe))
- success = success and failureTests
- result = pe
- except Exception as exc:
- out.append("FAIL-EXCEPTION: " + str(exc))
- success = success and failureTests
- result = exc
-
- if printResults:
- if fullDump:
- out.append('')
- print('\n'.join(out))
-
- allResults.append((t, result))
-
- return success, allResults
-
-
-class Token(ParserElement):
- """
- Abstract C{ParserElement} subclass, for defining atomic matching patterns.
- """
- def __init__( self ):
- super(Token,self).__init__( savelist=False )
-
-
-class Empty(Token):
- """
- An empty token, will always match.
- """
- def __init__( self ):
- super(Empty,self).__init__()
- self.name = "Empty"
- self.mayReturnEmpty = True
- self.mayIndexError = False
-
-
-class NoMatch(Token):
- """
- A token that will never match.
- """
- def __init__( self ):
- super(NoMatch,self).__init__()
- self.name = "NoMatch"
- self.mayReturnEmpty = True
- self.mayIndexError = False
- self.errmsg = "Unmatchable token"
-
- def parseImpl( self, instring, loc, doActions=True ):
- raise ParseException(instring, loc, self.errmsg, self)
-
-
-class Literal(Token):
- """
- Token to exactly match a specified string.
-
- Example::
- Literal('blah').parseString('blah') # -> ['blah']
- Literal('blah').parseString('blahfooblah') # -> ['blah']
- Literal('blah').parseString('bla') # -> Exception: Expected "blah"
-
- For case-insensitive matching, use L{CaselessLiteral}.
-
- For keyword matching (force word break before and after the matched string),
- use L{Keyword} or L{CaselessKeyword}.
- """
- def __init__( self, matchString ):
- super(Literal,self).__init__()
- self.match = matchString
- self.matchLen = len(matchString)
- try:
- self.firstMatchChar = matchString[0]
- except IndexError:
- warnings.warn("null string passed to Literal; use Empty() instead",
- SyntaxWarning, stacklevel=2)
- self.__class__ = Empty
- self.name = '"%s"' % _ustr(self.match)
- self.errmsg = "Expected " + self.name
- self.mayReturnEmpty = False
- self.mayIndexError = False
-
- # Performance tuning: this routine gets called a *lot*
- # if this is a single character match string and the first character matches,
- # short-circuit as quickly as possible, and avoid calling startswith
- #~ @profile
- def parseImpl( self, instring, loc, doActions=True ):
- if (instring[loc] == self.firstMatchChar and
- (self.matchLen==1 or instring.startswith(self.match,loc)) ):
- return loc+self.matchLen, self.match
- raise ParseException(instring, loc, self.errmsg, self)
-_L = Literal
-ParserElement._literalStringClass = Literal
-
-class Keyword(Token):
- """
- Token to exactly match a specified string as a keyword, that is, it must be
- immediately followed by a non-keyword character. Compare with C{L{Literal}}:
- - C{Literal("if")} will match the leading C{'if'} in C{'ifAndOnlyIf'}.
- - C{Keyword("if")} will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'}
- Accepts two optional constructor arguments in addition to the keyword string:
- - C{identChars} is a string of characters that would be valid identifier characters,
- defaulting to all alphanumerics + "_" and "$"
- - C{caseless} allows case-insensitive matching, default is C{False}.
-
- Example::
- Keyword("start").parseString("start") # -> ['start']
- Keyword("start").parseString("starting") # -> Exception
-
- For case-insensitive matching, use L{CaselessKeyword}.
- """
- DEFAULT_KEYWORD_CHARS = alphanums+"_$"
-
- def __init__( self, matchString, identChars=None, caseless=False ):
- super(Keyword,self).__init__()
- if identChars is None:
- identChars = Keyword.DEFAULT_KEYWORD_CHARS
- self.match = matchString
- self.matchLen = len(matchString)
- try:
- self.firstMatchChar = matchString[0]
- except IndexError:
- warnings.warn("null string passed to Keyword; use Empty() instead",
- SyntaxWarning, stacklevel=2)
- self.name = '"%s"' % self.match
- self.errmsg = "Expected " + self.name
- self.mayReturnEmpty = False
- self.mayIndexError = False
- self.caseless = caseless
- if caseless:
- self.caselessmatch = matchString.upper()
- identChars = identChars.upper()
- self.identChars = set(identChars)
-
- def parseImpl( self, instring, loc, doActions=True ):
- if self.caseless:
- if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and
- (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and
- (loc == 0 or instring[loc-1].upper() not in self.identChars) ):
- return loc+self.matchLen, self.match
- else:
- if (instring[loc] == self.firstMatchChar and
- (self.matchLen==1 or instring.startswith(self.match,loc)) and
- (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and
- (loc == 0 or instring[loc-1] not in self.identChars) ):
- return loc+self.matchLen, self.match
- raise ParseException(instring, loc, self.errmsg, self)
-
- def copy(self):
- c = super(Keyword,self).copy()
- c.identChars = Keyword.DEFAULT_KEYWORD_CHARS
- return c
-
- @staticmethod
- def setDefaultKeywordChars( chars ):
- """Overrides the default Keyword chars
- """
- Keyword.DEFAULT_KEYWORD_CHARS = chars
-
-class CaselessLiteral(Literal):
- """
- Token to match a specified string, ignoring case of letters.
- Note: the matched results will always be in the case of the given
- match string, NOT the case of the input text.
-
- Example::
- OneOrMore(CaselessLiteral("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD', 'CMD']
-
- (Contrast with example for L{CaselessKeyword}.)
- """
- def __init__( self, matchString ):
- super(CaselessLiteral,self).__init__( matchString.upper() )
- # Preserve the defining literal.
- self.returnString = matchString
- self.name = "'%s'" % self.returnString
- self.errmsg = "Expected " + self.name
-
- def parseImpl( self, instring, loc, doActions=True ):
- if instring[ loc:loc+self.matchLen ].upper() == self.match:
- return loc+self.matchLen, self.returnString
- raise ParseException(instring, loc, self.errmsg, self)
-
-class CaselessKeyword(Keyword):
- """
- Caseless version of L{Keyword}.
-
- Example::
- OneOrMore(CaselessKeyword("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD']
-
- (Contrast with example for L{CaselessLiteral}.)
- """
- def __init__( self, matchString, identChars=None ):
- super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True )
-
- def parseImpl( self, instring, loc, doActions=True ):
- if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and
- (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ):
- return loc+self.matchLen, self.match
- raise ParseException(instring, loc, self.errmsg, self)
-
-class CloseMatch(Token):
- """
- A variation on L{Literal} which matches "close" matches, that is,
- strings with at most 'n' mismatching characters. C{CloseMatch} takes parameters:
- - C{match_string} - string to be matched
- - C{maxMismatches} - (C{default=1}) maximum number of mismatches allowed to count as a match
-
- The results from a successful parse will contain the matched text from the input string and the following named results:
- - C{mismatches} - a list of the positions within the match_string where mismatches were found
- - C{original} - the original match_string used to compare against the input string
-
- If C{mismatches} is an empty list, then the match was an exact match.
-
- Example::
- patt = CloseMatch("ATCATCGAATGGA")
- patt.parseString("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']})
- patt.parseString("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1)
-
- # exact match
- patt.parseString("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']})
-
- # close match allowing up to 2 mismatches
- patt = CloseMatch("ATCATCGAATGGA", maxMismatches=2)
- patt.parseString("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']})
- """
- def __init__(self, match_string, maxMismatches=1):
- super(CloseMatch,self).__init__()
- self.name = match_string
- self.match_string = match_string
- self.maxMismatches = maxMismatches
- self.errmsg = "Expected %r (with up to %d mismatches)" % (self.match_string, self.maxMismatches)
- self.mayIndexError = False
- self.mayReturnEmpty = False
-
- def parseImpl( self, instring, loc, doActions=True ):
- start = loc
- instrlen = len(instring)
- maxloc = start + len(self.match_string)
-
- if maxloc <= instrlen:
- match_string = self.match_string
- match_stringloc = 0
- mismatches = []
- maxMismatches = self.maxMismatches
-
- for match_stringloc,s_m in enumerate(zip(instring[loc:maxloc], self.match_string)):
- src,mat = s_m
- if src != mat:
- mismatches.append(match_stringloc)
- if len(mismatches) > maxMismatches:
- break
- else:
- loc = match_stringloc + 1
- results = ParseResults([instring[start:loc]])
- results['original'] = self.match_string
- results['mismatches'] = mismatches
- return loc, results
-
- raise ParseException(instring, loc, self.errmsg, self)
-
-
-class Word(Token):
- """
- Token for matching words composed of allowed character sets.
- Defined with string containing all allowed initial characters,
- an optional string containing allowed body characters (if omitted,
- defaults to the initial character set), and an optional minimum,
- maximum, and/or exact length. The default value for C{min} is 1 (a
- minimum value < 1 is not valid); the default values for C{max} and C{exact}
- are 0, meaning no maximum or exact length restriction. An optional
- C{excludeChars} parameter can list characters that might be found in
- the input C{bodyChars} string; useful to define a word of all printables
- except for one or two characters, for instance.
-
- L{srange} is useful for defining custom character set strings for defining
- C{Word} expressions, using range notation from regular expression character sets.
-
- A common mistake is to use C{Word} to match a specific literal string, as in
- C{Word("Address")}. Remember that C{Word} uses the string argument to define
- I{sets} of matchable characters. This expression would match "Add", "AAA",
- "dAred", or any other word made up of the characters 'A', 'd', 'r', 'e', and 's'.
- To match an exact literal string, use L{Literal} or L{Keyword}.
-
- pyparsing includes helper strings for building Words:
- - L{alphas}
- - L{nums}
- - L{alphanums}
- - L{hexnums}
- - L{alphas8bit} (alphabetic characters in ASCII range 128-255 - accented, tilded, umlauted, etc.)
- - L{punc8bit} (non-alphabetic characters in ASCII range 128-255 - currency, symbols, superscripts, diacriticals, etc.)
- - L{printables} (any non-whitespace character)
-
- Example::
- # a word composed of digits
- integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9"))
-
- # a word with a leading capital, and zero or more lowercase
- capital_word = Word(alphas.upper(), alphas.lower())
-
- # hostnames are alphanumeric, with leading alpha, and '-'
- hostname = Word(alphas, alphanums+'-')
-
- # roman numeral (not a strict parser, accepts invalid mix of characters)
- roman = Word("IVXLCDM")
-
- # any string of non-whitespace characters, except for ','
- csv_value = Word(printables, excludeChars=",")
- """
- def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ):
- super(Word,self).__init__()
- if excludeChars:
- initChars = ''.join(c for c in initChars if c not in excludeChars)
- if bodyChars:
- bodyChars = ''.join(c for c in bodyChars if c not in excludeChars)
- self.initCharsOrig = initChars
- self.initChars = set(initChars)
- if bodyChars :
- self.bodyCharsOrig = bodyChars
- self.bodyChars = set(bodyChars)
- else:
- self.bodyCharsOrig = initChars
- self.bodyChars = set(initChars)
-
- self.maxSpecified = max > 0
-
- if min < 1:
- raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted")
-
- self.minLen = min
-
- if max > 0:
- self.maxLen = max
- else:
- self.maxLen = _MAX_INT
-
- if exact > 0:
- self.maxLen = exact
- self.minLen = exact
-
- self.name = _ustr(self)
- self.errmsg = "Expected " + self.name
- self.mayIndexError = False
- self.asKeyword = asKeyword
-
- if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0):
- if self.bodyCharsOrig == self.initCharsOrig:
- self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig)
- elif len(self.initCharsOrig) == 1:
- self.reString = "%s[%s]*" % \
- (re.escape(self.initCharsOrig),
- _escapeRegexRangeChars(self.bodyCharsOrig),)
- else:
- self.reString = "[%s][%s]*" % \
- (_escapeRegexRangeChars(self.initCharsOrig),
- _escapeRegexRangeChars(self.bodyCharsOrig),)
- if self.asKeyword:
- self.reString = r"\b"+self.reString+r"\b"
- try:
- self.re = re.compile( self.reString )
- except Exception:
- self.re = None
-
- def parseImpl( self, instring, loc, doActions=True ):
- if self.re:
- result = self.re.match(instring,loc)
- if not result:
- raise ParseException(instring, loc, self.errmsg, self)
-
- loc = result.end()
- return loc, result.group()
-
- if not(instring[ loc ] in self.initChars):
- raise ParseException(instring, loc, self.errmsg, self)
-
- start = loc
- loc += 1
- instrlen = len(instring)
- bodychars = self.bodyChars
- maxloc = start + self.maxLen
- maxloc = min( maxloc, instrlen )
- while loc < maxloc and instring[loc] in bodychars:
- loc += 1
-
- throwException = False
- if loc - start < self.minLen:
- throwException = True
- if self.maxSpecified and loc < instrlen and instring[loc] in bodychars:
- throwException = True
- if self.asKeyword:
- if (start>0 and instring[start-1] in bodychars) or (loc<instrlen and instring[loc] in bodychars):
- throwException = True
-
- if throwException:
- raise ParseException(instring, loc, self.errmsg, self)
-
- return loc, instring[start:loc]
-
- def __str__( self ):
- try:
- return super(Word,self).__str__()
- except Exception:
- pass
-
-
- if self.strRepr is None:
-
- def charsAsStr(s):
- if len(s)>4:
- return s[:4]+"..."
- else:
- return s
-
- if ( self.initCharsOrig != self.bodyCharsOrig ):
- self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) )
- else:
- self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig)
-
- return self.strRepr
-
-
-class Regex(Token):
- r"""
- Token for matching strings that match a given regular expression.
- Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module.
- If the given regex contains named groups (defined using C{(?P<name>...)}), these will be preserved as
- named parse results.
-
- Example::
- realnum = Regex(r"[+-]?\d+\.\d*")
- date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)')
- # ref: http://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression
- roman = Regex(r"M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})")
- """
- compiledREtype = type(re.compile("[A-Z]"))
- def __init__( self, pattern, flags=0):
- """The parameters C{pattern} and C{flags} are passed to the C{re.compile()} function as-is. See the Python C{re} module for an explanation of the acceptable patterns and flags."""
- super(Regex,self).__init__()
-
- if isinstance(pattern, basestring):
- if not pattern:
- warnings.warn("null string passed to Regex; use Empty() instead",
- SyntaxWarning, stacklevel=2)
-
- self.pattern = pattern
- self.flags = flags
-
- try:
- self.re = re.compile(self.pattern, self.flags)
- self.reString = self.pattern
- except sre_constants.error:
- warnings.warn("invalid pattern (%s) passed to Regex" % pattern,
- SyntaxWarning, stacklevel=2)
- raise
-
- elif isinstance(pattern, Regex.compiledREtype):
- self.re = pattern
- self.pattern = \
- self.reString = str(pattern)
- self.flags = flags
-
- else:
- raise ValueError("Regex may only be constructed with a string or a compiled RE object")
-
- self.name = _ustr(self)
- self.errmsg = "Expected " + self.name
- self.mayIndexError = False
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- result = self.re.match(instring,loc)
- if not result:
- raise ParseException(instring, loc, self.errmsg, self)
-
- loc = result.end()
- d = result.groupdict()
- ret = ParseResults(result.group())
- if d:
- for k in d:
- ret[k] = d[k]
- return loc,ret
-
- def __str__( self ):
- try:
- return super(Regex,self).__str__()
- except Exception:
- pass
-
- if self.strRepr is None:
- self.strRepr = "Re:(%s)" % repr(self.pattern)
-
- return self.strRepr
-
-
-class QuotedString(Token):
- r"""
- Token for matching strings that are delimited by quoting characters.
-
- Defined with the following parameters:
- - quoteChar - string of one or more characters defining the quote delimiting string
- - escChar - character to escape quotes, typically backslash (default=C{None})
- - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=C{None})
- - multiline - boolean indicating whether quotes can span multiple lines (default=C{False})
- - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True})
- - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar)
- - convertWhitespaceEscapes - convert escaped whitespace (C{'\t'}, C{'\n'}, etc.) to actual whitespace (default=C{True})
-
- Example::
- qs = QuotedString('"')
- print(qs.searchString('lsjdf "This is the quote" sldjf'))
- complex_qs = QuotedString('{{', endQuoteChar='}}')
- print(complex_qs.searchString('lsjdf {{This is the "quote"}} sldjf'))
- sql_qs = QuotedString('"', escQuote='""')
- print(sql_qs.searchString('lsjdf "This is the quote with ""embedded"" quotes" sldjf'))
- prints::
- [['This is the quote']]
- [['This is the "quote"']]
- [['This is the quote with "embedded" quotes']]
- """
- def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None, convertWhitespaceEscapes=True):
- super(QuotedString,self).__init__()
-
- # remove white space from quote chars - wont work anyway
- quoteChar = quoteChar.strip()
- if not quoteChar:
- warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
- raise SyntaxError()
-
- if endQuoteChar is None:
- endQuoteChar = quoteChar
- else:
- endQuoteChar = endQuoteChar.strip()
- if not endQuoteChar:
- warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
- raise SyntaxError()
-
- self.quoteChar = quoteChar
- self.quoteCharLen = len(quoteChar)
- self.firstQuoteChar = quoteChar[0]
- self.endQuoteChar = endQuoteChar
- self.endQuoteCharLen = len(endQuoteChar)
- self.escChar = escChar
- self.escQuote = escQuote
- self.unquoteResults = unquoteResults
- self.convertWhitespaceEscapes = convertWhitespaceEscapes
-
- if multiline:
- self.flags = re.MULTILINE | re.DOTALL
- self.pattern = r'%s(?:[^%s%s]' % \
- ( re.escape(self.quoteChar),
- _escapeRegexRangeChars(self.endQuoteChar[0]),
- (escChar is not None and _escapeRegexRangeChars(escChar) or '') )
- else:
- self.flags = 0
- self.pattern = r'%s(?:[^%s\n\r%s]' % \
- ( re.escape(self.quoteChar),
- _escapeRegexRangeChars(self.endQuoteChar[0]),
- (escChar is not None and _escapeRegexRangeChars(escChar) or '') )
- if len(self.endQuoteChar) > 1:
- self.pattern += (
- '|(?:' + ')|(?:'.join("%s[^%s]" % (re.escape(self.endQuoteChar[:i]),
- _escapeRegexRangeChars(self.endQuoteChar[i]))
- for i in range(len(self.endQuoteChar)-1,0,-1)) + ')'
- )
- if escQuote:
- self.pattern += (r'|(?:%s)' % re.escape(escQuote))
- if escChar:
- self.pattern += (r'|(?:%s.)' % re.escape(escChar))
- self.escCharReplacePattern = re.escape(self.escChar)+"(.)"
- self.pattern += (r')*%s' % re.escape(self.endQuoteChar))
-
- try:
- self.re = re.compile(self.pattern, self.flags)
- self.reString = self.pattern
- except sre_constants.error:
- warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern,
- SyntaxWarning, stacklevel=2)
- raise
-
- self.name = _ustr(self)
- self.errmsg = "Expected " + self.name
- self.mayIndexError = False
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None
- if not result:
- raise ParseException(instring, loc, self.errmsg, self)
-
- loc = result.end()
- ret = result.group()
-
- if self.unquoteResults:
-
- # strip off quotes
- ret = ret[self.quoteCharLen:-self.endQuoteCharLen]
-
- if isinstance(ret,basestring):
- # replace escaped whitespace
- if '\\' in ret and self.convertWhitespaceEscapes:
- ws_map = {
- r'\t' : '\t',
- r'\n' : '\n',
- r'\f' : '\f',
- r'\r' : '\r',
- }
- for wslit,wschar in ws_map.items():
- ret = ret.replace(wslit, wschar)
-
- # replace escaped characters
- if self.escChar:
- ret = re.sub(self.escCharReplacePattern, r"\g<1>", ret)
-
- # replace escaped quotes
- if self.escQuote:
- ret = ret.replace(self.escQuote, self.endQuoteChar)
-
- return loc, ret
-
- def __str__( self ):
- try:
- return super(QuotedString,self).__str__()
- except Exception:
- pass
-
- if self.strRepr is None:
- self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar)
-
- return self.strRepr
-
-
-class CharsNotIn(Token):
- """
- Token for matching words composed of characters I{not} in a given set (will
- include whitespace in matched characters if not listed in the provided exclusion set - see example).
- Defined with string containing all disallowed characters, and an optional
- minimum, maximum, and/or exact length. The default value for C{min} is 1 (a
- minimum value < 1 is not valid); the default values for C{max} and C{exact}
- are 0, meaning no maximum or exact length restriction.
-
- Example::
- # define a comma-separated-value as anything that is not a ','
- csv_value = CharsNotIn(',')
- print(delimitedList(csv_value).parseString("dkls,lsdkjf,s12 34,@!#,213"))
- prints::
- ['dkls', 'lsdkjf', 's12 34', '@!#', '213']
- """
- def __init__( self, notChars, min=1, max=0, exact=0 ):
- super(CharsNotIn,self).__init__()
- self.skipWhitespace = False
- self.notChars = notChars
-
- if min < 1:
- raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted")
-
- self.minLen = min
-
- if max > 0:
- self.maxLen = max
- else:
- self.maxLen = _MAX_INT
-
- if exact > 0:
- self.maxLen = exact
- self.minLen = exact
-
- self.name = _ustr(self)
- self.errmsg = "Expected " + self.name
- self.mayReturnEmpty = ( self.minLen == 0 )
- self.mayIndexError = False
-
- def parseImpl( self, instring, loc, doActions=True ):
- if instring[loc] in self.notChars:
- raise ParseException(instring, loc, self.errmsg, self)
-
- start = loc
- loc += 1
- notchars = self.notChars
- maxlen = min( start+self.maxLen, len(instring) )
- while loc < maxlen and \
- (instring[loc] not in notchars):
- loc += 1
-
- if loc - start < self.minLen:
- raise ParseException(instring, loc, self.errmsg, self)
-
- return loc, instring[start:loc]
-
- def __str__( self ):
- try:
- return super(CharsNotIn, self).__str__()
- except Exception:
- pass
-
- if self.strRepr is None:
- if len(self.notChars) > 4:
- self.strRepr = "!W:(%s...)" % self.notChars[:4]
- else:
- self.strRepr = "!W:(%s)" % self.notChars
-
- return self.strRepr
-
-class White(Token):
- """
- Special matching class for matching whitespace. Normally, whitespace is ignored
- by pyparsing grammars. This class is included when some whitespace structures
- are significant. Define with a string containing the whitespace characters to be
- matched; default is C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments,
- as defined for the C{L{Word}} class.
- """
- whiteStrs = {
- " " : "<SPC>",
- "\t": "<TAB>",
- "\n": "<LF>",
- "\r": "<CR>",
- "\f": "<FF>",
- }
- def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0):
- super(White,self).__init__()
- self.matchWhite = ws
- self.setWhitespaceChars( "".join(c for c in self.whiteChars if c not in self.matchWhite) )
- #~ self.leaveWhitespace()
- self.name = ("".join(White.whiteStrs[c] for c in self.matchWhite))
- self.mayReturnEmpty = True
- self.errmsg = "Expected " + self.name
-
- self.minLen = min
-
- if max > 0:
- self.maxLen = max
- else:
- self.maxLen = _MAX_INT
-
- if exact > 0:
- self.maxLen = exact
- self.minLen = exact
-
- def parseImpl( self, instring, loc, doActions=True ):
- if not(instring[ loc ] in self.matchWhite):
- raise ParseException(instring, loc, self.errmsg, self)
- start = loc
- loc += 1
- maxloc = start + self.maxLen
- maxloc = min( maxloc, len(instring) )
- while loc < maxloc and instring[loc] in self.matchWhite:
- loc += 1
-
- if loc - start < self.minLen:
- raise ParseException(instring, loc, self.errmsg, self)
-
- return loc, instring[start:loc]
-
-
-class _PositionToken(Token):
- def __init__( self ):
- super(_PositionToken,self).__init__()
- self.name=self.__class__.__name__
- self.mayReturnEmpty = True
- self.mayIndexError = False
-
-class GoToColumn(_PositionToken):
- """
- Token to advance to a specific column of input text; useful for tabular report scraping.
- """
- def __init__( self, colno ):
- super(GoToColumn,self).__init__()
- self.col = colno
-
- def preParse( self, instring, loc ):
- if col(loc,instring) != self.col:
- instrlen = len(instring)
- if self.ignoreExprs:
- loc = self._skipIgnorables( instring, loc )
- while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col :
- loc += 1
- return loc
-
- def parseImpl( self, instring, loc, doActions=True ):
- thiscol = col( loc, instring )
- if thiscol > self.col:
- raise ParseException( instring, loc, "Text not in expected column", self )
- newloc = loc + self.col - thiscol
- ret = instring[ loc: newloc ]
- return newloc, ret
-
-
-class LineStart(_PositionToken):
- """
- Matches if current position is at the beginning of a line within the parse string
-
- Example::
-
- test = '''\
- AAA this line
- AAA and this line
- AAA but not this one
- B AAA and definitely not this one
- '''
-
- for t in (LineStart() + 'AAA' + restOfLine).searchString(test):
- print(t)
-
- Prints::
- ['AAA', ' this line']
- ['AAA', ' and this line']
-
- """
- def __init__( self ):
- super(LineStart,self).__init__()
- self.errmsg = "Expected start of line"
-
- def parseImpl( self, instring, loc, doActions=True ):
- if col(loc, instring) == 1:
- return loc, []
- raise ParseException(instring, loc, self.errmsg, self)
-
-class LineEnd(_PositionToken):
- """
- Matches if current position is at the end of a line within the parse string
- """
- def __init__( self ):
- super(LineEnd,self).__init__()
- self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") )
- self.errmsg = "Expected end of line"
-
- def parseImpl( self, instring, loc, doActions=True ):
- if loc<len(instring):
- if instring[loc] == "\n":
- return loc+1, "\n"
- else:
- raise ParseException(instring, loc, self.errmsg, self)
- elif loc == len(instring):
- return loc+1, []
- else:
- raise ParseException(instring, loc, self.errmsg, self)
-
-class StringStart(_PositionToken):
- """
- Matches if current position is at the beginning of the parse string
- """
- def __init__( self ):
- super(StringStart,self).__init__()
- self.errmsg = "Expected start of text"
-
- def parseImpl( self, instring, loc, doActions=True ):
- if loc != 0:
- # see if entire string up to here is just whitespace and ignoreables
- if loc != self.preParse( instring, 0 ):
- raise ParseException(instring, loc, self.errmsg, self)
- return loc, []
-
-class StringEnd(_PositionToken):
- """
- Matches if current position is at the end of the parse string
- """
- def __init__( self ):
- super(StringEnd,self).__init__()
- self.errmsg = "Expected end of text"
-
- def parseImpl( self, instring, loc, doActions=True ):
- if loc < len(instring):
- raise ParseException(instring, loc, self.errmsg, self)
- elif loc == len(instring):
- return loc+1, []
- elif loc > len(instring):
- return loc, []
- else:
- raise ParseException(instring, loc, self.errmsg, self)
-
-class WordStart(_PositionToken):
- """
- Matches if the current position is at the beginning of a Word, and
- is not preceded by any character in a given set of C{wordChars}
- (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
- use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of
- the string being parsed, or at the beginning of a line.
- """
- def __init__(self, wordChars = printables):
- super(WordStart,self).__init__()
- self.wordChars = set(wordChars)
- self.errmsg = "Not at the start of a word"
-
- def parseImpl(self, instring, loc, doActions=True ):
- if loc != 0:
- if (instring[loc-1] in self.wordChars or
- instring[loc] not in self.wordChars):
- raise ParseException(instring, loc, self.errmsg, self)
- return loc, []
-
-class WordEnd(_PositionToken):
- """
- Matches if the current position is at the end of a Word, and
- is not followed by any character in a given set of C{wordChars}
- (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
- use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of
- the string being parsed, or at the end of a line.
- """
- def __init__(self, wordChars = printables):
- super(WordEnd,self).__init__()
- self.wordChars = set(wordChars)
- self.skipWhitespace = False
- self.errmsg = "Not at the end of a word"
-
- def parseImpl(self, instring, loc, doActions=True ):
- instrlen = len(instring)
- if instrlen>0 and loc<instrlen:
- if (instring[loc] in self.wordChars or
- instring[loc-1] not in self.wordChars):
- raise ParseException(instring, loc, self.errmsg, self)
- return loc, []
-
-
-class ParseExpression(ParserElement):
- """
- Abstract subclass of ParserElement, for combining and post-processing parsed tokens.
- """
- def __init__( self, exprs, savelist = False ):
- super(ParseExpression,self).__init__(savelist)
- if isinstance( exprs, _generatorType ):
- exprs = list(exprs)
-
- if isinstance( exprs, basestring ):
- self.exprs = [ ParserElement._literalStringClass( exprs ) ]
- elif isinstance( exprs, Iterable ):
- exprs = list(exprs)
- # if sequence of strings provided, wrap with Literal
- if all(isinstance(expr, basestring) for expr in exprs):
- exprs = map(ParserElement._literalStringClass, exprs)
- self.exprs = list(exprs)
- else:
- try:
- self.exprs = list( exprs )
- except TypeError:
- self.exprs = [ exprs ]
- self.callPreparse = False
-
- def __getitem__( self, i ):
- return self.exprs[i]
-
- def append( self, other ):
- self.exprs.append( other )
- self.strRepr = None
- return self
-
- def leaveWhitespace( self ):
- """Extends C{leaveWhitespace} defined in base class, and also invokes C{leaveWhitespace} on
- all contained expressions."""
- self.skipWhitespace = False
- self.exprs = [ e.copy() for e in self.exprs ]
- for e in self.exprs:
- e.leaveWhitespace()
- return self
-
- def ignore( self, other ):
- if isinstance( other, Suppress ):
- if other not in self.ignoreExprs:
- super( ParseExpression, self).ignore( other )
- for e in self.exprs:
- e.ignore( self.ignoreExprs[-1] )
- else:
- super( ParseExpression, self).ignore( other )
- for e in self.exprs:
- e.ignore( self.ignoreExprs[-1] )
- return self
-
- def __str__( self ):
- try:
- return super(ParseExpression,self).__str__()
- except Exception:
- pass
-
- if self.strRepr is None:
- self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.exprs) )
- return self.strRepr
-
- def streamline( self ):
- super(ParseExpression,self).streamline()
-
- for e in self.exprs:
- e.streamline()
-
- # collapse nested And's of the form And( And( And( a,b), c), d) to And( a,b,c,d )
- # but only if there are no parse actions or resultsNames on the nested And's
- # (likewise for Or's and MatchFirst's)
- if ( len(self.exprs) == 2 ):
- other = self.exprs[0]
- if ( isinstance( other, self.__class__ ) and
- not(other.parseAction) and
- other.resultsName is None and
- not other.debug ):
- self.exprs = other.exprs[:] + [ self.exprs[1] ]
- self.strRepr = None
- self.mayReturnEmpty |= other.mayReturnEmpty
- self.mayIndexError |= other.mayIndexError
-
- other = self.exprs[-1]
- if ( isinstance( other, self.__class__ ) and
- not(other.parseAction) and
- other.resultsName is None and
- not other.debug ):
- self.exprs = self.exprs[:-1] + other.exprs[:]
- self.strRepr = None
- self.mayReturnEmpty |= other.mayReturnEmpty
- self.mayIndexError |= other.mayIndexError
-
- self.errmsg = "Expected " + _ustr(self)
-
- return self
-
- def setResultsName( self, name, listAllMatches=False ):
- ret = super(ParseExpression,self).setResultsName(name,listAllMatches)
- return ret
-
- def validate( self, validateTrace=[] ):
- tmp = validateTrace[:]+[self]
- for e in self.exprs:
- e.validate(tmp)
- self.checkRecursion( [] )
-
- def copy(self):
- ret = super(ParseExpression,self).copy()
- ret.exprs = [e.copy() for e in self.exprs]
- return ret
-
-class And(ParseExpression):
- """
- Requires all given C{ParseExpression}s to be found in the given order.
- Expressions may be separated by whitespace.
- May be constructed using the C{'+'} operator.
- May also be constructed using the C{'-'} operator, which will suppress backtracking.
-
- Example::
- integer = Word(nums)
- name_expr = OneOrMore(Word(alphas))
-
- expr = And([integer("id"),name_expr("name"),integer("age")])
- # more easily written as:
- expr = integer("id") + name_expr("name") + integer("age")
- """
-
- class _ErrorStop(Empty):
- def __init__(self, *args, **kwargs):
- super(And._ErrorStop,self).__init__(*args, **kwargs)
- self.name = '-'
- self.leaveWhitespace()
-
- def __init__( self, exprs, savelist = True ):
- super(And,self).__init__(exprs, savelist)
- self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs)
- self.setWhitespaceChars( self.exprs[0].whiteChars )
- self.skipWhitespace = self.exprs[0].skipWhitespace
- self.callPreparse = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- # pass False as last arg to _parse for first element, since we already
- # pre-parsed the string as part of our And pre-parsing
- loc, resultlist = self.exprs[0]._parse( instring, loc, doActions, callPreParse=False )
- errorStop = False
- for e in self.exprs[1:]:
- if isinstance(e, And._ErrorStop):
- errorStop = True
- continue
- if errorStop:
- try:
- loc, exprtokens = e._parse( instring, loc, doActions )
- except ParseSyntaxException:
- raise
- except ParseBaseException as pe:
- pe.__traceback__ = None
- raise ParseSyntaxException._from_exception(pe)
- except IndexError:
- raise ParseSyntaxException(instring, len(instring), self.errmsg, self)
- else:
- loc, exprtokens = e._parse( instring, loc, doActions )
- if exprtokens or exprtokens.haskeys():
- resultlist += exprtokens
- return loc, resultlist
-
- def __iadd__(self, other ):
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- return self.append( other ) #And( [ self, other ] )
-
- def checkRecursion( self, parseElementList ):
- subRecCheckList = parseElementList[:] + [ self ]
- for e in self.exprs:
- e.checkRecursion( subRecCheckList )
- if not e.mayReturnEmpty:
- break
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "{" + " ".join(_ustr(e) for e in self.exprs) + "}"
-
- return self.strRepr
-
-
-class Or(ParseExpression):
- """
- Requires that at least one C{ParseExpression} is found.
- If two expressions match, the expression that matches the longest string will be used.
- May be constructed using the C{'^'} operator.
-
- Example::
- # construct Or using '^' operator
-
- number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums))
- print(number.searchString("123 3.1416 789"))
- prints::
- [['123'], ['3.1416'], ['789']]
- """
- def __init__( self, exprs, savelist = False ):
- super(Or,self).__init__(exprs, savelist)
- if self.exprs:
- self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs)
- else:
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- maxExcLoc = -1
- maxException = None
- matches = []
- for e in self.exprs:
- try:
- loc2 = e.tryParse( instring, loc )
- except ParseException as err:
- err.__traceback__ = None
- if err.loc > maxExcLoc:
- maxException = err
- maxExcLoc = err.loc
- except IndexError:
- if len(instring) > maxExcLoc:
- maxException = ParseException(instring,len(instring),e.errmsg,self)
- maxExcLoc = len(instring)
- else:
- # save match among all matches, to retry longest to shortest
- matches.append((loc2, e))
-
- if matches:
- matches.sort(key=lambda x: -x[0])
- for _,e in matches:
- try:
- return e._parse( instring, loc, doActions )
- except ParseException as err:
- err.__traceback__ = None
- if err.loc > maxExcLoc:
- maxException = err
- maxExcLoc = err.loc
-
- if maxException is not None:
- maxException.msg = self.errmsg
- raise maxException
- else:
- raise ParseException(instring, loc, "no defined alternatives to match", self)
-
-
- def __ixor__(self, other ):
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- return self.append( other ) #Or( [ self, other ] )
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "{" + " ^ ".join(_ustr(e) for e in self.exprs) + "}"
-
- return self.strRepr
-
- def checkRecursion( self, parseElementList ):
- subRecCheckList = parseElementList[:] + [ self ]
- for e in self.exprs:
- e.checkRecursion( subRecCheckList )
-
-
-class MatchFirst(ParseExpression):
- """
- Requires that at least one C{ParseExpression} is found.
- If two expressions match, the first one listed is the one that will match.
- May be constructed using the C{'|'} operator.
-
- Example::
- # construct MatchFirst using '|' operator
-
- # watch the order of expressions to match
- number = Word(nums) | Combine(Word(nums) + '.' + Word(nums))
- print(number.searchString("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']]
-
- # put more selective expression first
- number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums)
- print(number.searchString("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']]
- """
- def __init__( self, exprs, savelist = False ):
- super(MatchFirst,self).__init__(exprs, savelist)
- if self.exprs:
- self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs)
- else:
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- maxExcLoc = -1
- maxException = None
- for e in self.exprs:
- try:
- ret = e._parse( instring, loc, doActions )
- return ret
- except ParseException as err:
- if err.loc > maxExcLoc:
- maxException = err
- maxExcLoc = err.loc
- except IndexError:
- if len(instring) > maxExcLoc:
- maxException = ParseException(instring,len(instring),e.errmsg,self)
- maxExcLoc = len(instring)
-
- # only got here if no expression matched, raise exception for match that made it the furthest
- else:
- if maxException is not None:
- maxException.msg = self.errmsg
- raise maxException
- else:
- raise ParseException(instring, loc, "no defined alternatives to match", self)
-
- def __ior__(self, other ):
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass( other )
- return self.append( other ) #MatchFirst( [ self, other ] )
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "{" + " | ".join(_ustr(e) for e in self.exprs) + "}"
-
- return self.strRepr
-
- def checkRecursion( self, parseElementList ):
- subRecCheckList = parseElementList[:] + [ self ]
- for e in self.exprs:
- e.checkRecursion( subRecCheckList )
-
-
-class Each(ParseExpression):
- """
- Requires all given C{ParseExpression}s to be found, but in any order.
- Expressions may be separated by whitespace.
- May be constructed using the C{'&'} operator.
-
- Example::
- color = oneOf("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN")
- shape_type = oneOf("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON")
- integer = Word(nums)
- shape_attr = "shape:" + shape_type("shape")
- posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn")
- color_attr = "color:" + color("color")
- size_attr = "size:" + integer("size")
-
- # use Each (using operator '&') to accept attributes in any order
- # (shape and posn are required, color and size are optional)
- shape_spec = shape_attr & posn_attr & Optional(color_attr) & Optional(size_attr)
-
- shape_spec.runTests('''
- shape: SQUARE color: BLACK posn: 100, 120
- shape: CIRCLE size: 50 color: BLUE posn: 50,80
- color:GREEN size:20 shape:TRIANGLE posn:20,40
- '''
- )
- prints::
- shape: SQUARE color: BLACK posn: 100, 120
- ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']]
- - color: BLACK
- - posn: ['100', ',', '120']
- - x: 100
- - y: 120
- - shape: SQUARE
-
-
- shape: CIRCLE size: 50 color: BLUE posn: 50,80
- ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']]
- - color: BLUE
- - posn: ['50', ',', '80']
- - x: 50
- - y: 80
- - shape: CIRCLE
- - size: 50
-
-
- color: GREEN size: 20 shape: TRIANGLE posn: 20,40
- ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']]
- - color: GREEN
- - posn: ['20', ',', '40']
- - x: 20
- - y: 40
- - shape: TRIANGLE
- - size: 20
- """
- def __init__( self, exprs, savelist = True ):
- super(Each,self).__init__(exprs, savelist)
- self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs)
- self.skipWhitespace = True
- self.initExprGroups = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- if self.initExprGroups:
- self.opt1map = dict((id(e.expr),e) for e in self.exprs if isinstance(e,Optional))
- opt1 = [ e.expr for e in self.exprs if isinstance(e,Optional) ]
- opt2 = [ e for e in self.exprs if e.mayReturnEmpty and not isinstance(e,Optional)]
- self.optionals = opt1 + opt2
- self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ]
- self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ]
- self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ]
- self.required += self.multirequired
- self.initExprGroups = False
- tmpLoc = loc
- tmpReqd = self.required[:]
- tmpOpt = self.optionals[:]
- matchOrder = []
-
- keepMatching = True
- while keepMatching:
- tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired
- failed = []
- for e in tmpExprs:
- try:
- tmpLoc = e.tryParse( instring, tmpLoc )
- except ParseException:
- failed.append(e)
- else:
- matchOrder.append(self.opt1map.get(id(e),e))
- if e in tmpReqd:
- tmpReqd.remove(e)
- elif e in tmpOpt:
- tmpOpt.remove(e)
- if len(failed) == len(tmpExprs):
- keepMatching = False
-
- if tmpReqd:
- missing = ", ".join(_ustr(e) for e in tmpReqd)
- raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing )
-
- # add any unmatched Optionals, in case they have default values defined
- matchOrder += [e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt]
-
- resultlist = []
- for e in matchOrder:
- loc,results = e._parse(instring,loc,doActions)
- resultlist.append(results)
-
- finalResults = sum(resultlist, ParseResults([]))
- return loc, finalResults
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "{" + " & ".join(_ustr(e) for e in self.exprs) + "}"
-
- return self.strRepr
-
- def checkRecursion( self, parseElementList ):
- subRecCheckList = parseElementList[:] + [ self ]
- for e in self.exprs:
- e.checkRecursion( subRecCheckList )
-
-
-class ParseElementEnhance(ParserElement):
- """
- Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.
- """
- def __init__( self, expr, savelist=False ):
- super(ParseElementEnhance,self).__init__(savelist)
- if isinstance( expr, basestring ):
- if issubclass(ParserElement._literalStringClass, Token):
- expr = ParserElement._literalStringClass(expr)
- else:
- expr = ParserElement._literalStringClass(Literal(expr))
- self.expr = expr
- self.strRepr = None
- if expr is not None:
- self.mayIndexError = expr.mayIndexError
- self.mayReturnEmpty = expr.mayReturnEmpty
- self.setWhitespaceChars( expr.whiteChars )
- self.skipWhitespace = expr.skipWhitespace
- self.saveAsList = expr.saveAsList
- self.callPreparse = expr.callPreparse
- self.ignoreExprs.extend(expr.ignoreExprs)
-
- def parseImpl( self, instring, loc, doActions=True ):
- if self.expr is not None:
- return self.expr._parse( instring, loc, doActions, callPreParse=False )
- else:
- raise ParseException("",loc,self.errmsg,self)
-
- def leaveWhitespace( self ):
- self.skipWhitespace = False
- self.expr = self.expr.copy()
- if self.expr is not None:
- self.expr.leaveWhitespace()
- return self
-
- def ignore( self, other ):
- if isinstance( other, Suppress ):
- if other not in self.ignoreExprs:
- super( ParseElementEnhance, self).ignore( other )
- if self.expr is not None:
- self.expr.ignore( self.ignoreExprs[-1] )
- else:
- super( ParseElementEnhance, self).ignore( other )
- if self.expr is not None:
- self.expr.ignore( self.ignoreExprs[-1] )
- return self
-
- def streamline( self ):
- super(ParseElementEnhance,self).streamline()
- if self.expr is not None:
- self.expr.streamline()
- return self
-
- def checkRecursion( self, parseElementList ):
- if self in parseElementList:
- raise RecursiveGrammarException( parseElementList+[self] )
- subRecCheckList = parseElementList[:] + [ self ]
- if self.expr is not None:
- self.expr.checkRecursion( subRecCheckList )
-
- def validate( self, validateTrace=[] ):
- tmp = validateTrace[:]+[self]
- if self.expr is not None:
- self.expr.validate(tmp)
- self.checkRecursion( [] )
-
- def __str__( self ):
- try:
- return super(ParseElementEnhance,self).__str__()
- except Exception:
- pass
-
- if self.strRepr is None and self.expr is not None:
- self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) )
- return self.strRepr
-
-
-class FollowedBy(ParseElementEnhance):
- """
- Lookahead matching of the given parse expression. C{FollowedBy}
- does I{not} advance the parsing position within the input string, it only
- verifies that the specified parse expression matches at the current
- position. C{FollowedBy} always returns a null token list.
-
- Example::
- # use FollowedBy to match a label only if it is followed by a ':'
- data_word = Word(alphas)
- label = data_word + FollowedBy(':')
- attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
-
- OneOrMore(attr_expr).parseString("shape: SQUARE color: BLACK posn: upper left").pprint()
- prints::
- [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']]
- """
- def __init__( self, expr ):
- super(FollowedBy,self).__init__(expr)
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- self.expr.tryParse( instring, loc )
- return loc, []
-
-
-class NotAny(ParseElementEnhance):
- """
- Lookahead to disallow matching with the given parse expression. C{NotAny}
- does I{not} advance the parsing position within the input string, it only
- verifies that the specified parse expression does I{not} match at the current
- position. Also, C{NotAny} does I{not} skip over leading whitespace. C{NotAny}
- always returns a null token list. May be constructed using the '~' operator.
-
- Example::
-
- """
- def __init__( self, expr ):
- super(NotAny,self).__init__(expr)
- #~ self.leaveWhitespace()
- self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs
- self.mayReturnEmpty = True
- self.errmsg = "Found unwanted token, "+_ustr(self.expr)
-
- def parseImpl( self, instring, loc, doActions=True ):
- if self.expr.canParseNext(instring, loc):
- raise ParseException(instring, loc, self.errmsg, self)
- return loc, []
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "~{" + _ustr(self.expr) + "}"
-
- return self.strRepr
-
-class _MultipleMatch(ParseElementEnhance):
- def __init__( self, expr, stopOn=None):
- super(_MultipleMatch, self).__init__(expr)
- self.saveAsList = True
- ender = stopOn
- if isinstance(ender, basestring):
- ender = ParserElement._literalStringClass(ender)
- self.not_ender = ~ender if ender is not None else None
-
- def parseImpl( self, instring, loc, doActions=True ):
- self_expr_parse = self.expr._parse
- self_skip_ignorables = self._skipIgnorables
- check_ender = self.not_ender is not None
- if check_ender:
- try_not_ender = self.not_ender.tryParse
-
- # must be at least one (but first see if we are the stopOn sentinel;
- # if so, fail)
- if check_ender:
- try_not_ender(instring, loc)
- loc, tokens = self_expr_parse( instring, loc, doActions, callPreParse=False )
- try:
- hasIgnoreExprs = (not not self.ignoreExprs)
- while 1:
- if check_ender:
- try_not_ender(instring, loc)
- if hasIgnoreExprs:
- preloc = self_skip_ignorables( instring, loc )
- else:
- preloc = loc
- loc, tmptokens = self_expr_parse( instring, preloc, doActions )
- if tmptokens or tmptokens.haskeys():
- tokens += tmptokens
- except (ParseException,IndexError):
- pass
-
- return loc, tokens
-
-class OneOrMore(_MultipleMatch):
- """
- Repetition of one or more of the given expression.
-
- Parameters:
- - expr - expression that must match one or more times
- - stopOn - (default=C{None}) - expression for a terminating sentinel
- (only required if the sentinel would ordinarily match the repetition
- expression)
-
- Example::
- data_word = Word(alphas)
- label = data_word + FollowedBy(':')
- attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
-
- text = "shape: SQUARE posn: upper left color: BLACK"
- OneOrMore(attr_expr).parseString(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']]
-
- # use stopOn attribute for OneOrMore to avoid reading label string as part of the data
- attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
- OneOrMore(attr_expr).parseString(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']]
-
- # could also be written as
- (attr_expr * (1,)).parseString(text).pprint()
- """
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "{" + _ustr(self.expr) + "}..."
-
- return self.strRepr
-
-class ZeroOrMore(_MultipleMatch):
- """
- Optional repetition of zero or more of the given expression.
-
- Parameters:
- - expr - expression that must match zero or more times
- - stopOn - (default=C{None}) - expression for a terminating sentinel
- (only required if the sentinel would ordinarily match the repetition
- expression)
-
- Example: similar to L{OneOrMore}
- """
- def __init__( self, expr, stopOn=None):
- super(ZeroOrMore,self).__init__(expr, stopOn=stopOn)
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- try:
- return super(ZeroOrMore, self).parseImpl(instring, loc, doActions)
- except (ParseException,IndexError):
- return loc, []
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "[" + _ustr(self.expr) + "]..."
-
- return self.strRepr
-
-class _NullToken(object):
- def __bool__(self):
- return False
- __nonzero__ = __bool__
- def __str__(self):
- return ""
-
-_optionalNotMatched = _NullToken()
-class Optional(ParseElementEnhance):
- """
- Optional matching of the given expression.
-
- Parameters:
- - expr - expression that must match zero or more times
- - default (optional) - value to be returned if the optional expression is not found.
-
- Example::
- # US postal code can be a 5-digit zip, plus optional 4-digit qualifier
- zip = Combine(Word(nums, exact=5) + Optional('-' + Word(nums, exact=4)))
- zip.runTests('''
- # traditional ZIP code
- 12345
-
- # ZIP+4 form
- 12101-0001
-
- # invalid ZIP
- 98765-
- ''')
- prints::
- # traditional ZIP code
- 12345
- ['12345']
-
- # ZIP+4 form
- 12101-0001
- ['12101-0001']
-
- # invalid ZIP
- 98765-
- ^
- FAIL: Expected end of text (at char 5), (line:1, col:6)
- """
- def __init__( self, expr, default=_optionalNotMatched ):
- super(Optional,self).__init__( expr, savelist=False )
- self.saveAsList = self.expr.saveAsList
- self.defaultValue = default
- self.mayReturnEmpty = True
-
- def parseImpl( self, instring, loc, doActions=True ):
- try:
- loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False )
- except (ParseException,IndexError):
- if self.defaultValue is not _optionalNotMatched:
- if self.expr.resultsName:
- tokens = ParseResults([ self.defaultValue ])
- tokens[self.expr.resultsName] = self.defaultValue
- else:
- tokens = [ self.defaultValue ]
- else:
- tokens = []
- return loc, tokens
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
-
- if self.strRepr is None:
- self.strRepr = "[" + _ustr(self.expr) + "]"
-
- return self.strRepr
-
-class SkipTo(ParseElementEnhance):
- """
- Token for skipping over all undefined text until the matched expression is found.
-
- Parameters:
- - expr - target expression marking the end of the data to be skipped
- - include - (default=C{False}) if True, the target expression is also parsed
- (the skipped text and target expression are returned as a 2-element list).
- - ignore - (default=C{None}) used to define grammars (typically quoted strings and
- comments) that might contain false matches to the target expression
- - failOn - (default=C{None}) define expressions that are not allowed to be
- included in the skipped test; if found before the target expression is found,
- the SkipTo is not a match
-
- Example::
- report = '''
- Outstanding Issues Report - 1 Jan 2000
-
- # | Severity | Description | Days Open
- -----+----------+-------------------------------------------+-----------
- 101 | Critical | Intermittent system crash | 6
- 94 | Cosmetic | Spelling error on Login ('log|n') | 14
- 79 | Minor | System slow when running too many reports | 47
- '''
- integer = Word(nums)
- SEP = Suppress('|')
- # use SkipTo to simply match everything up until the next SEP
- # - ignore quoted strings, so that a '|' character inside a quoted string does not match
- # - parse action will call token.strip() for each matched token, i.e., the description body
- string_data = SkipTo(SEP, ignore=quotedString)
- string_data.setParseAction(tokenMap(str.strip))
- ticket_expr = (integer("issue_num") + SEP
- + string_data("sev") + SEP
- + string_data("desc") + SEP
- + integer("days_open"))
-
- for tkt in ticket_expr.searchString(report):
- print tkt.dump()
- prints::
- ['101', 'Critical', 'Intermittent system crash', '6']
- - days_open: 6
- - desc: Intermittent system crash
- - issue_num: 101
- - sev: Critical
- ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14']
- - days_open: 14
- - desc: Spelling error on Login ('log|n')
- - issue_num: 94
- - sev: Cosmetic
- ['79', 'Minor', 'System slow when running too many reports', '47']
- - days_open: 47
- - desc: System slow when running too many reports
- - issue_num: 79
- - sev: Minor
- """
- def __init__( self, other, include=False, ignore=None, failOn=None ):
- super( SkipTo, self ).__init__( other )
- self.ignoreExpr = ignore
- self.mayReturnEmpty = True
- self.mayIndexError = False
- self.includeMatch = include
- self.asList = False
- if isinstance(failOn, basestring):
- self.failOn = ParserElement._literalStringClass(failOn)
- else:
- self.failOn = failOn
- self.errmsg = "No match found for "+_ustr(self.expr)
-
- def parseImpl( self, instring, loc, doActions=True ):
- startloc = loc
- instrlen = len(instring)
- expr = self.expr
- expr_parse = self.expr._parse
- self_failOn_canParseNext = self.failOn.canParseNext if self.failOn is not None else None
- self_ignoreExpr_tryParse = self.ignoreExpr.tryParse if self.ignoreExpr is not None else None
-
- tmploc = loc
- while tmploc <= instrlen:
- if self_failOn_canParseNext is not None:
- # break if failOn expression matches
- if self_failOn_canParseNext(instring, tmploc):
- break
-
- if self_ignoreExpr_tryParse is not None:
- # advance past ignore expressions
- while 1:
- try:
- tmploc = self_ignoreExpr_tryParse(instring, tmploc)
- except ParseBaseException:
- break
-
- try:
- expr_parse(instring, tmploc, doActions=False, callPreParse=False)
- except (ParseException, IndexError):
- # no match, advance loc in string
- tmploc += 1
- else:
- # matched skipto expr, done
- break
-
- else:
- # ran off the end of the input string without matching skipto expr, fail
- raise ParseException(instring, loc, self.errmsg, self)
-
- # build up return values
- loc = tmploc
- skiptext = instring[startloc:loc]
- skipresult = ParseResults(skiptext)
-
- if self.includeMatch:
- loc, mat = expr_parse(instring,loc,doActions,callPreParse=False)
- skipresult += mat
-
- return loc, skipresult
-
-class Forward(ParseElementEnhance):
- """
- Forward declaration of an expression to be defined later -
- used for recursive grammars, such as algebraic infix notation.
- When the expression is known, it is assigned to the C{Forward} variable using the '<<' operator.
-
- Note: take care when assigning to C{Forward} not to overlook precedence of operators.
- Specifically, '|' has a lower precedence than '<<', so that::
- fwdExpr << a | b | c
- will actually be evaluated as::
- (fwdExpr << a) | b | c
- thereby leaving b and c out as parseable alternatives. It is recommended that you
- explicitly group the values inserted into the C{Forward}::
- fwdExpr << (a | b | c)
- Converting to use the '<<=' operator instead will avoid this problem.
-
- See L{ParseResults.pprint} for an example of a recursive parser created using
- C{Forward}.
- """
- def __init__( self, other=None ):
- super(Forward,self).__init__( other, savelist=False )
-
- def __lshift__( self, other ):
- if isinstance( other, basestring ):
- other = ParserElement._literalStringClass(other)
- self.expr = other
- self.strRepr = None
- self.mayIndexError = self.expr.mayIndexError
- self.mayReturnEmpty = self.expr.mayReturnEmpty
- self.setWhitespaceChars( self.expr.whiteChars )
- self.skipWhitespace = self.expr.skipWhitespace
- self.saveAsList = self.expr.saveAsList
- self.ignoreExprs.extend(self.expr.ignoreExprs)
- return self
-
- def __ilshift__(self, other):
- return self << other
-
- def leaveWhitespace( self ):
- self.skipWhitespace = False
- return self
-
- def streamline( self ):
- if not self.streamlined:
- self.streamlined = True
- if self.expr is not None:
- self.expr.streamline()
- return self
-
- def validate( self, validateTrace=[] ):
- if self not in validateTrace:
- tmp = validateTrace[:]+[self]
- if self.expr is not None:
- self.expr.validate(tmp)
- self.checkRecursion([])
-
- def __str__( self ):
- if hasattr(self,"name"):
- return self.name
- return self.__class__.__name__ + ": ..."
-
- # stubbed out for now - creates awful memory and perf issues
- self._revertClass = self.__class__
- self.__class__ = _ForwardNoRecurse
- try:
- if self.expr is not None:
- retString = _ustr(self.expr)
- else:
- retString = "None"
- finally:
- self.__class__ = self._revertClass
- return self.__class__.__name__ + ": " + retString
-
- def copy(self):
- if self.expr is not None:
- return super(Forward,self).copy()
- else:
- ret = Forward()
- ret <<= self
- return ret
-
-class _ForwardNoRecurse(Forward):
- def __str__( self ):
- return "..."
-
-class TokenConverter(ParseElementEnhance):
- """
- Abstract subclass of C{ParseExpression}, for converting parsed results.
- """
- def __init__( self, expr, savelist=False ):
- super(TokenConverter,self).__init__( expr )#, savelist )
- self.saveAsList = False
-
-class Combine(TokenConverter):
- """
- Converter to concatenate all matching tokens to a single string.
- By default, the matching patterns must also be contiguous in the input string;
- this can be disabled by specifying C{'adjacent=False'} in the constructor.
-
- Example::
- real = Word(nums) + '.' + Word(nums)
- print(real.parseString('3.1416')) # -> ['3', '.', '1416']
- # will also erroneously match the following
- print(real.parseString('3. 1416')) # -> ['3', '.', '1416']
-
- real = Combine(Word(nums) + '.' + Word(nums))
- print(real.parseString('3.1416')) # -> ['3.1416']
- # no match when there are internal spaces
- print(real.parseString('3. 1416')) # -> Exception: Expected W:(0123...)
- """
- def __init__( self, expr, joinString="", adjacent=True ):
- super(Combine,self).__init__( expr )
- # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself
- if adjacent:
- self.leaveWhitespace()
- self.adjacent = adjacent
- self.skipWhitespace = True
- self.joinString = joinString
- self.callPreparse = True
-
- def ignore( self, other ):
- if self.adjacent:
- ParserElement.ignore(self, other)
- else:
- super( Combine, self).ignore( other )
- return self
-
- def postParse( self, instring, loc, tokenlist ):
- retToks = tokenlist.copy()
- del retToks[:]
- retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults)
-
- if self.resultsName and retToks.haskeys():
- return [ retToks ]
- else:
- return retToks
-
-class Group(TokenConverter):
- """
- Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.
-
- Example::
- ident = Word(alphas)
- num = Word(nums)
- term = ident | num
- func = ident + Optional(delimitedList(term))
- print(func.parseString("fn a,b,100")) # -> ['fn', 'a', 'b', '100']
-
- func = ident + Group(Optional(delimitedList(term)))
- print(func.parseString("fn a,b,100")) # -> ['fn', ['a', 'b', '100']]
- """
- def __init__( self, expr ):
- super(Group,self).__init__( expr )
- self.saveAsList = True
-
- def postParse( self, instring, loc, tokenlist ):
- return [ tokenlist ]
-
-class Dict(TokenConverter):
- """
- Converter to return a repetitive expression as a list, but also as a dictionary.
- Each element can also be referenced using the first token in the expression as its key.
- Useful for tabular report scraping when the first column can be used as a item key.
-
- Example::
- data_word = Word(alphas)
- label = data_word + FollowedBy(':')
- attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
-
- text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
- attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
-
- # print attributes as plain groups
- print(OneOrMore(attr_expr).parseString(text).dump())
-
- # instead of OneOrMore(expr), parse using Dict(OneOrMore(Group(expr))) - Dict will auto-assign names
- result = Dict(OneOrMore(Group(attr_expr))).parseString(text)
- print(result.dump())
-
- # access named fields as dict entries, or output as dict
- print(result['shape'])
- print(result.asDict())
- prints::
- ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap']
-
- [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
- - color: light blue
- - posn: upper left
- - shape: SQUARE
- - texture: burlap
- SQUARE
- {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'}
- See more examples at L{ParseResults} of accessing fields by results name.
- """
- def __init__( self, expr ):
- super(Dict,self).__init__( expr )
- self.saveAsList = True
-
- def postParse( self, instring, loc, tokenlist ):
- for i,tok in enumerate(tokenlist):
- if len(tok) == 0:
- continue
- ikey = tok[0]
- if isinstance(ikey,int):
- ikey = _ustr(tok[0]).strip()
- if len(tok)==1:
- tokenlist[ikey] = _ParseResultsWithOffset("",i)
- elif len(tok)==2 and not isinstance(tok[1],ParseResults):
- tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i)
- else:
- dictvalue = tok.copy() #ParseResults(i)
- del dictvalue[0]
- if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.haskeys()):
- tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i)
- else:
- tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i)
-
- if self.resultsName:
- return [ tokenlist ]
- else:
- return tokenlist
-
-
-class Suppress(TokenConverter):
- """
- Converter for ignoring the results of a parsed expression.
-
- Example::
- source = "a, b, c,d"
- wd = Word(alphas)
- wd_list1 = wd + ZeroOrMore(',' + wd)
- print(wd_list1.parseString(source))
-
- # often, delimiters that are useful during parsing are just in the
- # way afterward - use Suppress to keep them out of the parsed output
- wd_list2 = wd + ZeroOrMore(Suppress(',') + wd)
- print(wd_list2.parseString(source))
- prints::
- ['a', ',', 'b', ',', 'c', ',', 'd']
- ['a', 'b', 'c', 'd']
- (See also L{delimitedList}.)
- """
- def postParse( self, instring, loc, tokenlist ):
- return []
-
- def suppress( self ):
- return self
-
-
-class OnlyOnce(object):
- """
- Wrapper for parse actions, to ensure they are only called once.
- """
- def __init__(self, methodCall):
- self.callable = _trim_arity(methodCall)
- self.called = False
- def __call__(self,s,l,t):
- if not self.called:
- results = self.callable(s,l,t)
- self.called = True
- return results
- raise ParseException(s,l,"")
- def reset(self):
- self.called = False
-
-def traceParseAction(f):
- """
- Decorator for debugging parse actions.
-
- When the parse action is called, this decorator will print C{">> entering I{method-name}(line:I{current_source_line}, I{parse_location}, I{matched_tokens})".}
- When the parse action completes, the decorator will print C{"<<"} followed by the returned value, or any exception that the parse action raised.
-
- Example::
- wd = Word(alphas)
-
- @traceParseAction
- def remove_duplicate_chars(tokens):
- return ''.join(sorted(set(''.join(tokens))))
-
- wds = OneOrMore(wd).setParseAction(remove_duplicate_chars)
- print(wds.parseString("slkdjs sld sldd sdlf sdljf"))
- prints::
- >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {}))
- <<leaving remove_duplicate_chars (ret: 'dfjkls')
- ['dfjkls']
- """
- f = _trim_arity(f)
- def z(*paArgs):
- thisFunc = f.__name__
- s,l,t = paArgs[-3:]
- if len(paArgs)>3:
- thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc
- sys.stderr.write( ">>entering %s(line: '%s', %d, %r)\n" % (thisFunc,line(l,s),l,t) )
- try:
- ret = f(*paArgs)
- except Exception as exc:
- sys.stderr.write( "<<leaving %s (exception: %s)\n" % (thisFunc,exc) )
- raise
- sys.stderr.write( "<<leaving %s (ret: %r)\n" % (thisFunc,ret) )
- return ret
- try:
- z.__name__ = f.__name__
- except AttributeError:
- pass
- return z
-
-#
-# global helpers
-#
-def delimitedList( expr, delim=",", combine=False ):
- """
- Helper to define a delimited list of expressions - the delimiter defaults to ','.
- By default, the list elements and delimiters can have intervening whitespace, and
- comments, but this can be overridden by passing C{combine=True} in the constructor.
- If C{combine} is set to C{True}, the matching tokens are returned as a single token
- string, with the delimiters included; otherwise, the matching tokens are returned
- as a list of tokens, with the delimiters suppressed.
-
- Example::
- delimitedList(Word(alphas)).parseString("aa,bb,cc") # -> ['aa', 'bb', 'cc']
- delimitedList(Word(hexnums), delim=':', combine=True).parseString("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE']
- """
- dlName = _ustr(expr)+" ["+_ustr(delim)+" "+_ustr(expr)+"]..."
- if combine:
- return Combine( expr + ZeroOrMore( delim + expr ) ).setName(dlName)
- else:
- return ( expr + ZeroOrMore( Suppress( delim ) + expr ) ).setName(dlName)
-
-def countedArray( expr, intExpr=None ):
- """
- Helper to define a counted list of expressions.
- This helper defines a pattern of the form::
- integer expr expr expr...
- where the leading integer tells how many expr expressions follow.
- The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed.
-
- If C{intExpr} is specified, it should be a pyparsing expression that produces an integer value.
-
- Example::
- countedArray(Word(alphas)).parseString('2 ab cd ef') # -> ['ab', 'cd']
-
- # in this parser, the leading integer value is given in binary,
- # '10' indicating that 2 values are in the array
- binaryConstant = Word('01').setParseAction(lambda t: int(t[0], 2))
- countedArray(Word(alphas), intExpr=binaryConstant).parseString('10 ab cd ef') # -> ['ab', 'cd']
- """
- arrayExpr = Forward()
- def countFieldParseAction(s,l,t):
- n = t[0]
- arrayExpr << (n and Group(And([expr]*n)) or Group(empty))
- return []
- if intExpr is None:
- intExpr = Word(nums).setParseAction(lambda t:int(t[0]))
- else:
- intExpr = intExpr.copy()
- intExpr.setName("arrayLen")
- intExpr.addParseAction(countFieldParseAction, callDuringTry=True)
- return ( intExpr + arrayExpr ).setName('(len) ' + _ustr(expr) + '...')
-
-def _flatten(L):
- ret = []
- for i in L:
- if isinstance(i,list):
- ret.extend(_flatten(i))
- else:
- ret.append(i)
- return ret
-
-def matchPreviousLiteral(expr):
- """
- Helper to define an expression that is indirectly defined from
- the tokens matched in a previous expression, that is, it looks
- for a 'repeat' of a previous expression. For example::
- first = Word(nums)
- second = matchPreviousLiteral(first)
- matchExpr = first + ":" + second
- will match C{"1:1"}, but not C{"1:2"}. Because this matches a
- previous literal, will also match the leading C{"1:1"} in C{"1:10"}.
- If this is not desired, use C{matchPreviousExpr}.
- Do I{not} use with packrat parsing enabled.
- """
- rep = Forward()
- def copyTokenToRepeater(s,l,t):
- if t:
- if len(t) == 1:
- rep << t[0]
- else:
- # flatten t tokens
- tflat = _flatten(t.asList())
- rep << And(Literal(tt) for tt in tflat)
- else:
- rep << Empty()
- expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
- rep.setName('(prev) ' + _ustr(expr))
- return rep
-
-def matchPreviousExpr(expr):
- """
- Helper to define an expression that is indirectly defined from
- the tokens matched in a previous expression, that is, it looks
- for a 'repeat' of a previous expression. For example::
- first = Word(nums)
- second = matchPreviousExpr(first)
- matchExpr = first + ":" + second
- will match C{"1:1"}, but not C{"1:2"}. Because this matches by
- expressions, will I{not} match the leading C{"1:1"} in C{"1:10"};
- the expressions are evaluated first, and then compared, so
- C{"1"} is compared with C{"10"}.
- Do I{not} use with packrat parsing enabled.
- """
- rep = Forward()
- e2 = expr.copy()
- rep <<= e2
- def copyTokenToRepeater(s,l,t):
- matchTokens = _flatten(t.asList())
- def mustMatchTheseTokens(s,l,t):
- theseTokens = _flatten(t.asList())
- if theseTokens != matchTokens:
- raise ParseException("",0,"")
- rep.setParseAction( mustMatchTheseTokens, callDuringTry=True )
- expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
- rep.setName('(prev) ' + _ustr(expr))
- return rep
-
-def _escapeRegexRangeChars(s):
- #~ escape these chars: ^-]
- for c in r"\^-]":
- s = s.replace(c,_bslash+c)
- s = s.replace("\n",r"\n")
- s = s.replace("\t",r"\t")
- return _ustr(s)
-
-def oneOf( strs, caseless=False, useRegex=True ):
- """
- Helper to quickly define a set of alternative Literals, and makes sure to do
- longest-first testing when there is a conflict, regardless of the input order,
- but returns a C{L{MatchFirst}} for best performance.
-
- Parameters:
- - strs - a string of space-delimited literals, or a collection of string literals
- - caseless - (default=C{False}) - treat all literals as caseless
- - useRegex - (default=C{True}) - as an optimization, will generate a Regex
- object; otherwise, will generate a C{MatchFirst} object (if C{caseless=True}, or
- if creating a C{Regex} raises an exception)
-
- Example::
- comp_oper = oneOf("< = > <= >= !=")
- var = Word(alphas)
- number = Word(nums)
- term = var | number
- comparison_expr = term + comp_oper + term
- print(comparison_expr.searchString("B = 12 AA=23 B<=AA AA>12"))
- prints::
- [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']]
- """
- if caseless:
- isequal = ( lambda a,b: a.upper() == b.upper() )
- masks = ( lambda a,b: b.upper().startswith(a.upper()) )
- parseElementClass = CaselessLiteral
- else:
- isequal = ( lambda a,b: a == b )
- masks = ( lambda a,b: b.startswith(a) )
- parseElementClass = Literal
-
- symbols = []
- if isinstance(strs,basestring):
- symbols = strs.split()
- elif isinstance(strs, Iterable):
- symbols = list(strs)
- else:
- warnings.warn("Invalid argument to oneOf, expected string or iterable",
- SyntaxWarning, stacklevel=2)
- if not symbols:
- return NoMatch()
-
- i = 0
- while i < len(symbols)-1:
- cur = symbols[i]
- for j,other in enumerate(symbols[i+1:]):
- if ( isequal(other, cur) ):
- del symbols[i+j+1]
- break
- elif ( masks(cur, other) ):
- del symbols[i+j+1]
- symbols.insert(i,other)
- cur = other
- break
- else:
- i += 1
-
- if not caseless and useRegex:
- #~ print (strs,"->", "|".join( [ _escapeRegexChars(sym) for sym in symbols] ))
- try:
- if len(symbols)==len("".join(symbols)):
- return Regex( "[%s]" % "".join(_escapeRegexRangeChars(sym) for sym in symbols) ).setName(' | '.join(symbols))
- else:
- return Regex( "|".join(re.escape(sym) for sym in symbols) ).setName(' | '.join(symbols))
- except Exception:
- warnings.warn("Exception creating Regex for oneOf, building MatchFirst",
- SyntaxWarning, stacklevel=2)
-
-
- # last resort, just use MatchFirst
- return MatchFirst(parseElementClass(sym) for sym in symbols).setName(' | '.join(symbols))
-
-def dictOf( key, value ):
- """
- Helper to easily and clearly define a dictionary by specifying the respective patterns
- for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{Group}} tokens
- in the proper order. The key pattern can include delimiting markers or punctuation,
- as long as they are suppressed, thereby leaving the significant key text. The value
- pattern can include named results, so that the C{Dict} results can include named token
- fields.
-
- Example::
- text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
- attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
- print(OneOrMore(attr_expr).parseString(text).dump())
-
- attr_label = label
- attr_value = Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join)
-
- # similar to Dict, but simpler call format
- result = dictOf(attr_label, attr_value).parseString(text)
- print(result.dump())
- print(result['shape'])
- print(result.shape) # object attribute access works too
- print(result.asDict())
- prints::
- [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
- - color: light blue
- - posn: upper left
- - shape: SQUARE
- - texture: burlap
- SQUARE
- SQUARE
- {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'}
- """
- return Dict( ZeroOrMore( Group ( key + value ) ) )
-
-def originalTextFor(expr, asString=True):
- """
- Helper to return the original, untokenized text for a given expression. Useful to
- restore the parsed fields of an HTML start tag into the raw tag text itself, or to
- revert separate tokens with intervening whitespace back to the original matching
- input text. By default, returns astring containing the original parsed text.
-
- If the optional C{asString} argument is passed as C{False}, then the return value is a
- C{L{ParseResults}} containing any results names that were originally matched, and a
- single token containing the original matched text from the input string. So if
- the expression passed to C{L{originalTextFor}} contains expressions with defined
- results names, you must set C{asString} to C{False} if you want to preserve those
- results name values.
-
- Example::
- src = "this is test <b> bold <i>text</i> </b> normal text "
- for tag in ("b","i"):
- opener,closer = makeHTMLTags(tag)
- patt = originalTextFor(opener + SkipTo(closer) + closer)
- print(patt.searchString(src)[0])
- prints::
- ['<b> bold <i>text</i> </b>']
- ['<i>text</i>']
- """
- locMarker = Empty().setParseAction(lambda s,loc,t: loc)
- endlocMarker = locMarker.copy()
- endlocMarker.callPreparse = False
- matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end")
- if asString:
- extractText = lambda s,l,t: s[t._original_start:t._original_end]
- else:
- def extractText(s,l,t):
- t[:] = [s[t.pop('_original_start'):t.pop('_original_end')]]
- matchExpr.setParseAction(extractText)
- matchExpr.ignoreExprs = expr.ignoreExprs
- return matchExpr
-
-def ungroup(expr):
- """
- Helper to undo pyparsing's default grouping of And expressions, even
- if all but one are non-empty.
- """
- return TokenConverter(expr).setParseAction(lambda t:t[0])
-
-def locatedExpr(expr):
- """
- Helper to decorate a returned token with its starting and ending locations in the input string.
- This helper adds the following results names:
- - locn_start = location where matched expression begins
- - locn_end = location where matched expression ends
- - value = the actual parsed results
-
- Be careful if the input text contains C{<TAB>} characters, you may want to call
- C{L{ParserElement.parseWithTabs}}
-
- Example::
- wd = Word(alphas)
- for match in locatedExpr(wd).searchString("ljsdf123lksdjjf123lkkjj1222"):
- print(match)
- prints::
- [[0, 'ljsdf', 5]]
- [[8, 'lksdjjf', 15]]
- [[18, 'lkkjj', 23]]
- """
- locator = Empty().setParseAction(lambda s,l,t: l)
- return Group(locator("locn_start") + expr("value") + locator.copy().leaveWhitespace()("locn_end"))
-
-
-# convenience constants for positional expressions
-empty = Empty().setName("empty")
-lineStart = LineStart().setName("lineStart")
-lineEnd = LineEnd().setName("lineEnd")
-stringStart = StringStart().setName("stringStart")
-stringEnd = StringEnd().setName("stringEnd")
-
-_escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1])
-_escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16)))
-_escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8)))
-_singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | CharsNotIn(r'\]', exact=1)
-_charRange = Group(_singleChar + Suppress("-") + _singleChar)
-_reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]"
-
-def srange(s):
- r"""
- Helper to easily define string ranges for use in Word construction. Borrows
- syntax from regexp '[]' string range definitions::
- srange("[0-9]") -> "0123456789"
- srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz"
- srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_"
- The input string must be enclosed in []'s, and the returned string is the expanded
- character set joined into a single string.
- The values enclosed in the []'s may be:
- - a single character
- - an escaped character with a leading backslash (such as C{\-} or C{\]})
- - an escaped hex character with a leading C{'\x'} (C{\x21}, which is a C{'!'} character)
- (C{\0x##} is also supported for backwards compatibility)
- - an escaped octal character with a leading C{'\0'} (C{\041}, which is a C{'!'} character)
- - a range of any of the above, separated by a dash (C{'a-z'}, etc.)
- - any combination of the above (C{'aeiouy'}, C{'a-zA-Z0-9_$'}, etc.)
- """
- _expanded = lambda p: p if not isinstance(p,ParseResults) else ''.join(unichr(c) for c in range(ord(p[0]),ord(p[1])+1))
- try:
- return "".join(_expanded(part) for part in _reBracketExpr.parseString(s).body)
- except Exception:
- return ""
-
-def matchOnlyAtCol(n):
- """
- Helper method for defining parse actions that require matching at a specific
- column in the input text.
- """
- def verifyCol(strg,locn,toks):
- if col(locn,strg) != n:
- raise ParseException(strg,locn,"matched token not at column %d" % n)
- return verifyCol
-
-def replaceWith(replStr):
- """
- Helper method for common parse actions that simply return a literal value. Especially
- useful when used with C{L{transformString<ParserElement.transformString>}()}.
-
- Example::
- num = Word(nums).setParseAction(lambda toks: int(toks[0]))
- na = oneOf("N/A NA").setParseAction(replaceWith(math.nan))
- term = na | num
-
- OneOrMore(term).parseString("324 234 N/A 234") # -> [324, 234, nan, 234]
- """
- return lambda s,l,t: [replStr]
-
-def removeQuotes(s,l,t):
- """
- Helper parse action for removing quotation marks from parsed quoted strings.
-
- Example::
- # by default, quotation marks are included in parsed results
- quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"]
-
- # use removeQuotes to strip quotation marks from parsed results
- quotedString.setParseAction(removeQuotes)
- quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"]
- """
- return t[0][1:-1]
-
-def tokenMap(func, *args):
- """
- Helper to define a parse action by mapping a function to all elements of a ParseResults list.If any additional
- args are passed, they are forwarded to the given function as additional arguments after
- the token, as in C{hex_integer = Word(hexnums).setParseAction(tokenMap(int, 16))}, which will convert the
- parsed data to an integer using base 16.
-
- Example (compare the last to example in L{ParserElement.transformString}::
- hex_ints = OneOrMore(Word(hexnums)).setParseAction(tokenMap(int, 16))
- hex_ints.runTests('''
- 00 11 22 aa FF 0a 0d 1a
- ''')
-
- upperword = Word(alphas).setParseAction(tokenMap(str.upper))
- OneOrMore(upperword).runTests('''
- my kingdom for a horse
- ''')
-
- wd = Word(alphas).setParseAction(tokenMap(str.title))
- OneOrMore(wd).setParseAction(' '.join).runTests('''
- now is the winter of our discontent made glorious summer by this sun of york
- ''')
- prints::
- 00 11 22 aa FF 0a 0d 1a
- [0, 17, 34, 170, 255, 10, 13, 26]
-
- my kingdom for a horse
- ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE']
-
- now is the winter of our discontent made glorious summer by this sun of york
- ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York']
- """
- def pa(s,l,t):
- return [func(tokn, *args) for tokn in t]
-
- try:
- func_name = getattr(func, '__name__',
- getattr(func, '__class__').__name__)
- except Exception:
- func_name = str(func)
- pa.__name__ = func_name
-
- return pa
-
-upcaseTokens = tokenMap(lambda t: _ustr(t).upper())
-"""(Deprecated) Helper parse action to convert tokens to upper case. Deprecated in favor of L{pyparsing_common.upcaseTokens}"""
-
-downcaseTokens = tokenMap(lambda t: _ustr(t).lower())
-"""(Deprecated) Helper parse action to convert tokens to lower case. Deprecated in favor of L{pyparsing_common.downcaseTokens}"""
-
-def _makeTags(tagStr, xml):
- """Internal helper to construct opening and closing tag expressions, given a tag name"""
- if isinstance(tagStr,basestring):
- resname = tagStr
- tagStr = Keyword(tagStr, caseless=not xml)
- else:
- resname = tagStr.name
-
- tagAttrName = Word(alphas,alphanums+"_-:")
- if (xml):
- tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes )
- openTag = Suppress("<") + tagStr("tag") + \
- Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \
- Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
- else:
- printablesLessRAbrack = "".join(c for c in printables if c not in ">")
- tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack)
- openTag = Suppress("<") + tagStr("tag") + \
- Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \
- Optional( Suppress("=") + tagAttrValue ) ))) + \
- Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
- closeTag = Combine(_L("</") + tagStr + ">")
-
- openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % resname)
- closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("</%s>" % resname)
- openTag.tag = resname
- closeTag.tag = resname
- return openTag, closeTag
-
-def makeHTMLTags(tagStr):
- """
- Helper to construct opening and closing tag expressions for HTML, given a tag name. Matches
- tags in either upper or lower case, attributes with namespaces and with quoted or unquoted values.
-
- Example::
- text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
- # makeHTMLTags returns pyparsing expressions for the opening and closing tags as a 2-tuple
- a,a_end = makeHTMLTags("A")
- link_expr = a + SkipTo(a_end)("link_text") + a_end
-
- for link in link_expr.searchString(text):
- # attributes in the <A> tag (like "href" shown here) are also accessible as named results
- print(link.link_text, '->', link.href)
- prints::
- pyparsing -> http://pyparsing.wikispaces.com
- """
- return _makeTags( tagStr, False )
-
-def makeXMLTags(tagStr):
- """
- Helper to construct opening and closing tag expressions for XML, given a tag name. Matches
- tags only in the given upper/lower case.
-
- Example: similar to L{makeHTMLTags}
- """
- return _makeTags( tagStr, True )
-
-def withAttribute(*args,**attrDict):
- """
- Helper to create a validating parse action to be used with start tags created
- with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag
- with a required attribute value, to avoid false matches on common tags such as
- C{<TD>} or C{<DIV>}.
-
- Call C{withAttribute} with a series of attribute names and values. Specify the list
- of filter attributes names and values as:
- - keyword arguments, as in C{(align="right")}, or
- - as an explicit dict with C{**} operator, when an attribute name is also a Python
- reserved word, as in C{**{"class":"Customer", "align":"right"}}
- - a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") )
- For attribute names with a namespace prefix, you must use the second form. Attribute
- names are matched insensitive to upper/lower case.
-
- If just testing for C{class} (with or without a namespace), use C{L{withClass}}.
-
- To verify that the attribute exists, but without specifying a value, pass
- C{withAttribute.ANY_VALUE} as the value.
-
- Example::
- html = '''
- <div>
- Some text
- <div type="grid">1 4 0 1 0</div>
- <div type="graph">1,3 2,3 1,1</div>
- <div>this has no type</div>
- </div>
-
- '''
- div,div_end = makeHTMLTags("div")
-
- # only match div tag having a type attribute with value "grid"
- div_grid = div().setParseAction(withAttribute(type="grid"))
- grid_expr = div_grid + SkipTo(div | div_end)("body")
- for grid_header in grid_expr.searchString(html):
- print(grid_header.body)
-
- # construct a match with any div tag having a type attribute, regardless of the value
- div_any_type = div().setParseAction(withAttribute(type=withAttribute.ANY_VALUE))
- div_expr = div_any_type + SkipTo(div | div_end)("body")
- for div_header in div_expr.searchString(html):
- print(div_header.body)
- prints::
- 1 4 0 1 0
-
- 1 4 0 1 0
- 1,3 2,3 1,1
- """
- if args:
- attrs = args[:]
- else:
- attrs = attrDict.items()
- attrs = [(k,v) for k,v in attrs]
- def pa(s,l,tokens):
- for attrName,attrValue in attrs:
- if attrName not in tokens:
- raise ParseException(s,l,"no matching attribute " + attrName)
- if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue:
- raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" %
- (attrName, tokens[attrName], attrValue))
- return pa
-withAttribute.ANY_VALUE = object()
-
-def withClass(classname, namespace=''):
- """
- Simplified version of C{L{withAttribute}} when matching on a div class - made
- difficult because C{class} is a reserved word in Python.
-
- Example::
- html = '''
- <div>
- Some text
- <div class="grid">1 4 0 1 0</div>
- <div class="graph">1,3 2,3 1,1</div>
- <div>this <div> has no class</div>
- </div>
-
- '''
- div,div_end = makeHTMLTags("div")
- div_grid = div().setParseAction(withClass("grid"))
-
- grid_expr = div_grid + SkipTo(div | div_end)("body")
- for grid_header in grid_expr.searchString(html):
- print(grid_header.body)
-
- div_any_type = div().setParseAction(withClass(withAttribute.ANY_VALUE))
- div_expr = div_any_type + SkipTo(div | div_end)("body")
- for div_header in div_expr.searchString(html):
- print(div_header.body)
- prints::
- 1 4 0 1 0
-
- 1 4 0 1 0
- 1,3 2,3 1,1
- """
- classattr = "%s:class" % namespace if namespace else "class"
- return withAttribute(**{classattr : classname})
-
-opAssoc = _Constants()
-opAssoc.LEFT = object()
-opAssoc.RIGHT = object()
-
-def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ):
- """
- Helper method for constructing grammars of expressions made up of
- operators working in a precedence hierarchy. Operators may be unary or
- binary, left- or right-associative. Parse actions can also be attached
- to operator expressions. The generated parser will also recognize the use
- of parentheses to override operator precedences (see example below).
-
- Note: if you define a deep operator list, you may see performance issues
- when using infixNotation. See L{ParserElement.enablePackrat} for a
- mechanism to potentially improve your parser performance.
-
- Parameters:
- - baseExpr - expression representing the most basic element for the nested
- - opList - list of tuples, one for each operator precedence level in the
- expression grammar; each tuple is of the form
- (opExpr, numTerms, rightLeftAssoc, parseAction), where:
- - opExpr is the pyparsing expression for the operator;
- may also be a string, which will be converted to a Literal;
- if numTerms is 3, opExpr is a tuple of two expressions, for the
- two operators separating the 3 terms
- - numTerms is the number of terms for this operator (must
- be 1, 2, or 3)
- - rightLeftAssoc is the indicator whether the operator is
- right or left associative, using the pyparsing-defined
- constants C{opAssoc.RIGHT} and C{opAssoc.LEFT}.
- - parseAction is the parse action to be associated with
- expressions matching this operator expression (the
- parse action tuple member may be omitted); if the parse action
- is passed a tuple or list of functions, this is equivalent to
- calling C{setParseAction(*fn)} (L{ParserElement.setParseAction})
- - lpar - expression for matching left-parentheses (default=C{Suppress('(')})
- - rpar - expression for matching right-parentheses (default=C{Suppress(')')})
-
- Example::
- # simple example of four-function arithmetic with ints and variable names
- integer = pyparsing_common.signed_integer
- varname = pyparsing_common.identifier
-
- arith_expr = infixNotation(integer | varname,
- [
- ('-', 1, opAssoc.RIGHT),
- (oneOf('* /'), 2, opAssoc.LEFT),
- (oneOf('+ -'), 2, opAssoc.LEFT),
- ])
-
- arith_expr.runTests('''
- 5+3*6
- (5+3)*6
- -2--11
- ''', fullDump=False)
- prints::
- 5+3*6
- [[5, '+', [3, '*', 6]]]
-
- (5+3)*6
- [[[5, '+', 3], '*', 6]]
-
- -2--11
- [[['-', 2], '-', ['-', 11]]]
- """
- ret = Forward()
- lastExpr = baseExpr | ( lpar + ret + rpar )
- for i,operDef in enumerate(opList):
- opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4]
- termName = "%s term" % opExpr if arity < 3 else "%s%s term" % opExpr
- if arity == 3:
- if opExpr is None or len(opExpr) != 2:
- raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions")
- opExpr1, opExpr2 = opExpr
- thisExpr = Forward().setName(termName)
- if rightLeftAssoc == opAssoc.LEFT:
- if arity == 1:
- matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) )
- elif arity == 2:
- if opExpr is not None:
- matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) )
- else:
- matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) )
- elif arity == 3:
- matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \
- Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr )
- else:
- raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
- elif rightLeftAssoc == opAssoc.RIGHT:
- if arity == 1:
- # try to avoid LR with this extra test
- if not isinstance(opExpr, Optional):
- opExpr = Optional(opExpr)
- matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr )
- elif arity == 2:
- if opExpr is not None:
- matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) )
- else:
- matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) )
- elif arity == 3:
- matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \
- Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr )
- else:
- raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
- else:
- raise ValueError("operator must indicate right or left associativity")
- if pa:
- if isinstance(pa, (tuple, list)):
- matchExpr.setParseAction(*pa)
- else:
- matchExpr.setParseAction(pa)
- thisExpr <<= ( matchExpr.setName(termName) | lastExpr )
- lastExpr = thisExpr
- ret <<= lastExpr
- return ret
-
-operatorPrecedence = infixNotation
-"""(Deprecated) Former name of C{L{infixNotation}}, will be dropped in a future release."""
-
-dblQuotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"').setName("string enclosed in double quotes")
-sglQuotedString = Combine(Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("string enclosed in single quotes")
-quotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"'|
- Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("quotedString using single or double quotes")
-unicodeString = Combine(_L('u') + quotedString.copy()).setName("unicode string literal")
-
-def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()):
- """
- Helper method for defining nested lists enclosed in opening and closing
- delimiters ("(" and ")" are the default).
-
- Parameters:
- - opener - opening character for a nested list (default=C{"("}); can also be a pyparsing expression
- - closer - closing character for a nested list (default=C{")"}); can also be a pyparsing expression
- - content - expression for items within the nested lists (default=C{None})
- - ignoreExpr - expression for ignoring opening and closing delimiters (default=C{quotedString})
-
- If an expression is not provided for the content argument, the nested
- expression will capture all whitespace-delimited content between delimiters
- as a list of separate values.
-
- Use the C{ignoreExpr} argument to define expressions that may contain
- opening or closing characters that should not be treated as opening
- or closing characters for nesting, such as quotedString or a comment
- expression. Specify multiple expressions using an C{L{Or}} or C{L{MatchFirst}}.
- The default is L{quotedString}, but if no expressions are to be ignored,
- then pass C{None} for this argument.
-
- Example::
- data_type = oneOf("void int short long char float double")
- decl_data_type = Combine(data_type + Optional(Word('*')))
- ident = Word(alphas+'_', alphanums+'_')
- number = pyparsing_common.number
- arg = Group(decl_data_type + ident)
- LPAR,RPAR = map(Suppress, "()")
-
- code_body = nestedExpr('{', '}', ignoreExpr=(quotedString | cStyleComment))
-
- c_function = (decl_data_type("type")
- + ident("name")
- + LPAR + Optional(delimitedList(arg), [])("args") + RPAR
- + code_body("body"))
- c_function.ignore(cStyleComment)
-
- source_code = '''
- int is_odd(int x) {
- return (x%2);
- }
-
- int dec_to_hex(char hchar) {
- if (hchar >= '0' && hchar <= '9') {
- return (ord(hchar)-ord('0'));
- } else {
- return (10+ord(hchar)-ord('A'));
- }
- }
- '''
- for func in c_function.searchString(source_code):
- print("%(name)s (%(type)s) args: %(args)s" % func)
-
- prints::
- is_odd (int) args: [['int', 'x']]
- dec_to_hex (int) args: [['char', 'hchar']]
- """
- if opener == closer:
- raise ValueError("opening and closing strings cannot be the same")
- if content is None:
- if isinstance(opener,basestring) and isinstance(closer,basestring):
- if len(opener) == 1 and len(closer)==1:
- if ignoreExpr is not None:
- content = (Combine(OneOrMore(~ignoreExpr +
- CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1))
- ).setParseAction(lambda t:t[0].strip()))
- else:
- content = (empty.copy()+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS
- ).setParseAction(lambda t:t[0].strip()))
- else:
- if ignoreExpr is not None:
- content = (Combine(OneOrMore(~ignoreExpr +
- ~Literal(opener) + ~Literal(closer) +
- CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
- ).setParseAction(lambda t:t[0].strip()))
- else:
- content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) +
- CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
- ).setParseAction(lambda t:t[0].strip()))
- else:
- raise ValueError("opening and closing arguments must be strings if no content expression is given")
- ret = Forward()
- if ignoreExpr is not None:
- ret <<= Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) )
- else:
- ret <<= Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) )
- ret.setName('nested %s%s expression' % (opener,closer))
- return ret
-
-def indentedBlock(blockStatementExpr, indentStack, indent=True):
- """
- Helper method for defining space-delimited indentation blocks, such as
- those used to define block statements in Python source code.
-
- Parameters:
- - blockStatementExpr - expression defining syntax of statement that
- is repeated within the indented block
- - indentStack - list created by caller to manage indentation stack
- (multiple statementWithIndentedBlock expressions within a single grammar
- should share a common indentStack)
- - indent - boolean indicating whether block must be indented beyond the
- the current level; set to False for block of left-most statements
- (default=C{True})
-
- A valid block must contain at least one C{blockStatement}.
-
- Example::
- data = '''
- def A(z):
- A1
- B = 100
- G = A2
- A2
- A3
- B
- def BB(a,b,c):
- BB1
- def BBA():
- bba1
- bba2
- bba3
- C
- D
- def spam(x,y):
- def eggs(z):
- pass
- '''
-
-
- indentStack = [1]
- stmt = Forward()
-
- identifier = Word(alphas, alphanums)
- funcDecl = ("def" + identifier + Group( "(" + Optional( delimitedList(identifier) ) + ")" ) + ":")
- func_body = indentedBlock(stmt, indentStack)
- funcDef = Group( funcDecl + func_body )
-
- rvalue = Forward()
- funcCall = Group(identifier + "(" + Optional(delimitedList(rvalue)) + ")")
- rvalue << (funcCall | identifier | Word(nums))
- assignment = Group(identifier + "=" + rvalue)
- stmt << ( funcDef | assignment | identifier )
-
- module_body = OneOrMore(stmt)
-
- parseTree = module_body.parseString(data)
- parseTree.pprint()
- prints::
- [['def',
- 'A',
- ['(', 'z', ')'],
- ':',
- [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]],
- 'B',
- ['def',
- 'BB',
- ['(', 'a', 'b', 'c', ')'],
- ':',
- [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]],
- 'C',
- 'D',
- ['def',
- 'spam',
- ['(', 'x', 'y', ')'],
- ':',
- [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]]
- """
- def checkPeerIndent(s,l,t):
- if l >= len(s): return
- curCol = col(l,s)
- if curCol != indentStack[-1]:
- if curCol > indentStack[-1]:
- raise ParseFatalException(s,l,"illegal nesting")
- raise ParseException(s,l,"not a peer entry")
-
- def checkSubIndent(s,l,t):
- curCol = col(l,s)
- if curCol > indentStack[-1]:
- indentStack.append( curCol )
- else:
- raise ParseException(s,l,"not a subentry")
-
- def checkUnindent(s,l,t):
- if l >= len(s): return
- curCol = col(l,s)
- if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]):
- raise ParseException(s,l,"not an unindent")
- indentStack.pop()
-
- NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress())
- INDENT = (Empty() + Empty().setParseAction(checkSubIndent)).setName('INDENT')
- PEER = Empty().setParseAction(checkPeerIndent).setName('')
- UNDENT = Empty().setParseAction(checkUnindent).setName('UNINDENT')
- if indent:
- smExpr = Group( Optional(NL) +
- #~ FollowedBy(blockStatementExpr) +
- INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT)
- else:
- smExpr = Group( Optional(NL) +
- (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) )
- blockStatementExpr.ignore(_bslash + LineEnd())
- return smExpr.setName('indented block')
-
-alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]")
-punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]")
-
-anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:").setName('any tag'))
-_htmlEntityMap = dict(zip("gt lt amp nbsp quot apos".split(),'><& "\''))
-commonHTMLEntity = Regex('&(?P<entity>' + '|'.join(_htmlEntityMap.keys()) +");").setName("common HTML entity")
-def replaceHTMLEntity(t):
- """Helper parser action to replace common HTML entities with their special characters"""
- return _htmlEntityMap.get(t.entity)
-
-# it's easy to get these comment structures wrong - they're very common, so may as well make them available
-cStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/').setName("C style comment")
-"Comment of the form C{/* ... */}"
-
-htmlComment = Regex(r"<!--[\s\S]*?-->").setName("HTML comment")
-"Comment of the form C{<!-- ... -->}"
-
-restOfLine = Regex(r".*").leaveWhitespace().setName("rest of line")
-dblSlashComment = Regex(r"//(?:\\\n|[^\n])*").setName("// comment")
-"Comment of the form C{// ... (to end of line)}"
-
-cppStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/'| dblSlashComment).setName("C++ style comment")
-"Comment of either form C{L{cStyleComment}} or C{L{dblSlashComment}}"
-
-javaStyleComment = cppStyleComment
-"Same as C{L{cppStyleComment}}"
-
-pythonStyleComment = Regex(r"#.*").setName("Python style comment")
-"Comment of the form C{# ... (to end of line)}"
-
-_commasepitem = Combine(OneOrMore(Word(printables, excludeChars=',') +
- Optional( Word(" \t") +
- ~Literal(",") + ~LineEnd() ) ) ).streamline().setName("commaItem")
-commaSeparatedList = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("commaSeparatedList")
-"""(Deprecated) Predefined expression of 1 or more printable words or quoted strings, separated by commas.
- This expression is deprecated in favor of L{pyparsing_common.comma_separated_list}."""
-
-# some other useful expressions - using lower-case class name since we are really using this as a namespace
-class pyparsing_common:
- """
- Here are some common low-level expressions that may be useful in jump-starting parser development:
- - numeric forms (L{integers<integer>}, L{reals<real>}, L{scientific notation<sci_real>})
- - common L{programming identifiers<identifier>}
- - network addresses (L{MAC<mac_address>}, L{IPv4<ipv4_address>}, L{IPv6<ipv6_address>})
- - ISO8601 L{dates<iso8601_date>} and L{datetime<iso8601_datetime>}
- - L{UUID<uuid>}
- - L{comma-separated list<comma_separated_list>}
- Parse actions:
- - C{L{convertToInteger}}
- - C{L{convertToFloat}}
- - C{L{convertToDate}}
- - C{L{convertToDatetime}}
- - C{L{stripHTMLTags}}
- - C{L{upcaseTokens}}
- - C{L{downcaseTokens}}
-
- Example::
- pyparsing_common.number.runTests('''
- # any int or real number, returned as the appropriate type
- 100
- -100
- +100
- 3.14159
- 6.02e23
- 1e-12
- ''')
-
- pyparsing_common.fnumber.runTests('''
- # any int or real number, returned as float
- 100
- -100
- +100
- 3.14159
- 6.02e23
- 1e-12
- ''')
-
- pyparsing_common.hex_integer.runTests('''
- # hex numbers
- 100
- FF
- ''')
-
- pyparsing_common.fraction.runTests('''
- # fractions
- 1/2
- -3/4
- ''')
-
- pyparsing_common.mixed_integer.runTests('''
- # mixed fractions
- 1
- 1/2
- -3/4
- 1-3/4
- ''')
-
- import uuid
- pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
- pyparsing_common.uuid.runTests('''
- # uuid
- 12345678-1234-5678-1234-567812345678
- ''')
- prints::
- # any int or real number, returned as the appropriate type
- 100
- [100]
-
- -100
- [-100]
-
- +100
- [100]
-
- 3.14159
- [3.14159]
-
- 6.02e23
- [6.02e+23]
-
- 1e-12
- [1e-12]
-
- # any int or real number, returned as float
- 100
- [100.0]
-
- -100
- [-100.0]
-
- +100
- [100.0]
-
- 3.14159
- [3.14159]
-
- 6.02e23
- [6.02e+23]
-
- 1e-12
- [1e-12]
-
- # hex numbers
- 100
- [256]
-
- FF
- [255]
-
- # fractions
- 1/2
- [0.5]
-
- -3/4
- [-0.75]
-
- # mixed fractions
- 1
- [1]
-
- 1/2
- [0.5]
-
- -3/4
- [-0.75]
-
- 1-3/4
- [1.75]
-
- # uuid
- 12345678-1234-5678-1234-567812345678
- [UUID('12345678-1234-5678-1234-567812345678')]
- """
-
- convertToInteger = tokenMap(int)
- """
- Parse action for converting parsed integers to Python int
- """
-
- convertToFloat = tokenMap(float)
- """
- Parse action for converting parsed numbers to Python float
- """
-
- integer = Word(nums).setName("integer").setParseAction(convertToInteger)
- """expression that parses an unsigned integer, returns an int"""
-
- hex_integer = Word(hexnums).setName("hex integer").setParseAction(tokenMap(int,16))
- """expression that parses a hexadecimal integer, returns an int"""
-
- signed_integer = Regex(r'[+-]?\d+').setName("signed integer").setParseAction(convertToInteger)
- """expression that parses an integer with optional leading sign, returns an int"""
-
- fraction = (signed_integer().setParseAction(convertToFloat) + '/' + signed_integer().setParseAction(convertToFloat)).setName("fraction")
- """fractional expression of an integer divided by an integer, returns a float"""
- fraction.addParseAction(lambda t: t[0]/t[-1])
-
- mixed_integer = (fraction | signed_integer + Optional(Optional('-').suppress() + fraction)).setName("fraction or mixed integer-fraction")
- """mixed integer of the form 'integer - fraction', with optional leading integer, returns float"""
- mixed_integer.addParseAction(sum)
-
- real = Regex(r'[+-]?\d+\.\d*').setName("real number").setParseAction(convertToFloat)
- """expression that parses a floating point number and returns a float"""
-
- sci_real = Regex(r'[+-]?\d+([eE][+-]?\d+|\.\d*([eE][+-]?\d+)?)').setName("real number with scientific notation").setParseAction(convertToFloat)
- """expression that parses a floating point number with optional scientific notation and returns a float"""
-
- # streamlining this expression makes the docs nicer-looking
- number = (sci_real | real | signed_integer).streamline()
- """any numeric expression, returns the corresponding Python type"""
-
- fnumber = Regex(r'[+-]?\d+\.?\d*([eE][+-]?\d+)?').setName("fnumber").setParseAction(convertToFloat)
- """any int or real number, returned as float"""
-
- identifier = Word(alphas+'_', alphanums+'_').setName("identifier")
- """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')"""
-
- ipv4_address = Regex(r'(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}').setName("IPv4 address")
- "IPv4 address (C{0.0.0.0 - 255.255.255.255})"
-
- _ipv6_part = Regex(r'[0-9a-fA-F]{1,4}').setName("hex_integer")
- _full_ipv6_address = (_ipv6_part + (':' + _ipv6_part)*7).setName("full IPv6 address")
- _short_ipv6_address = (Optional(_ipv6_part + (':' + _ipv6_part)*(0,6)) + "::" + Optional(_ipv6_part + (':' + _ipv6_part)*(0,6))).setName("short IPv6 address")
- _short_ipv6_address.addCondition(lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8)
- _mixed_ipv6_address = ("::ffff:" + ipv4_address).setName("mixed IPv6 address")
- ipv6_address = Combine((_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).setName("IPv6 address")).setName("IPv6 address")
- "IPv6 address (long, short, or mixed form)"
-
- mac_address = Regex(r'[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}').setName("MAC address")
- "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)"
-
- @staticmethod
- def convertToDate(fmt="%Y-%m-%d"):
- """
- Helper to create a parse action for converting parsed date string to Python datetime.date
-
- Params -
- - fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%d"})
-
- Example::
- date_expr = pyparsing_common.iso8601_date.copy()
- date_expr.setParseAction(pyparsing_common.convertToDate())
- print(date_expr.parseString("1999-12-31"))
- prints::
- [datetime.date(1999, 12, 31)]
- """
- def cvt_fn(s,l,t):
- try:
- return datetime.strptime(t[0], fmt).date()
- except ValueError as ve:
- raise ParseException(s, l, str(ve))
- return cvt_fn
-
- @staticmethod
- def convertToDatetime(fmt="%Y-%m-%dT%H:%M:%S.%f"):
- """
- Helper to create a parse action for converting parsed datetime string to Python datetime.datetime
-
- Params -
- - fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%dT%H:%M:%S.%f"})
-
- Example::
- dt_expr = pyparsing_common.iso8601_datetime.copy()
- dt_expr.setParseAction(pyparsing_common.convertToDatetime())
- print(dt_expr.parseString("1999-12-31T23:59:59.999"))
- prints::
- [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)]
- """
- def cvt_fn(s,l,t):
- try:
- return datetime.strptime(t[0], fmt)
- except ValueError as ve:
- raise ParseException(s, l, str(ve))
- return cvt_fn
-
- iso8601_date = Regex(r'(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?').setName("ISO8601 date")
- "ISO8601 date (C{yyyy-mm-dd})"
-
- iso8601_datetime = Regex(r'(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?').setName("ISO8601 datetime")
- "ISO8601 datetime (C{yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)}) - trailing seconds, milliseconds, and timezone optional; accepts separating C{'T'} or C{' '}"
-
- uuid = Regex(r'[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}').setName("UUID")
- "UUID (C{xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx})"
-
- _html_stripper = anyOpenTag.suppress() | anyCloseTag.suppress()
- @staticmethod
- def stripHTMLTags(s, l, tokens):
- """
- Parse action to remove HTML tags from web page HTML source
-
- Example::
- # strip HTML links from normal text
- text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
- td,td_end = makeHTMLTags("TD")
- table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end
-
- print(table_text.parseString(text).body) # -> 'More info at the pyparsing wiki page'
- """
- return pyparsing_common._html_stripper.transformString(tokens[0])
-
- _commasepitem = Combine(OneOrMore(~Literal(",") + ~LineEnd() + Word(printables, excludeChars=',')
- + Optional( White(" \t") ) ) ).streamline().setName("commaItem")
- comma_separated_list = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("comma separated list")
- """Predefined expression of 1 or more printable words or quoted strings, separated by commas."""
-
- upcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).upper()))
- """Parse action to convert tokens to upper case."""
-
- downcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).lower()))
- """Parse action to convert tokens to lower case."""
-
-
-if __name__ == "__main__":
-
- selectToken = CaselessLiteral("select")
- fromToken = CaselessLiteral("from")
-
- ident = Word(alphas, alphanums + "_$")
-
- columnName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
- columnNameList = Group(delimitedList(columnName)).setName("columns")
- columnSpec = ('*' | columnNameList)
-
- tableName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
- tableNameList = Group(delimitedList(tableName)).setName("tables")
-
- simpleSQL = selectToken("command") + columnSpec("columns") + fromToken + tableNameList("tables")
-
- # demo runTests method, including embedded comments in test string
- simpleSQL.runTests("""
- # '*' as column list and dotted table name
- select * from SYS.XYZZY
-
- # caseless match on "SELECT", and casts back to "select"
- SELECT * from XYZZY, ABC
-
- # list of column names, and mixed case SELECT keyword
- Select AA,BB,CC from Sys.dual
-
- # multiple tables
- Select A, B, C from Sys.dual, Table2
-
- # invalid SELECT keyword - should fail
- Xelect A, B, C from Sys.dual
-
- # incomplete command - should fail
- Select
-
- # invalid column name - should fail
- Select ^^^ frox Sys.dual
-
- """)
-
- pyparsing_common.number.runTests("""
- 100
- -100
- +100
- 3.14159
- 6.02e23
- 1e-12
- """)
-
- # any int or real number, returned as float
- pyparsing_common.fnumber.runTests("""
- 100
- -100
- +100
- 3.14159
- 6.02e23
- 1e-12
- """)
-
- pyparsing_common.hex_integer.runTests("""
- 100
- FF
- """)
-
- import uuid
- pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
- pyparsing_common.uuid.runTests("""
- 12345678-1234-5678-1234-567812345678
- """)
diff --git a/pkg_resources/_vendor/pyparsing/__init__.py b/pkg_resources/_vendor/pyparsing/__init__.py new file mode 100644 index 00000000..7802ff15 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/__init__.py @@ -0,0 +1,331 @@ +# module pyparsing.py +# +# Copyright (c) 2003-2022 Paul T. McGuire +# +# Permission is hereby granted, free of charge, to any person obtaining +# a copy of this software and associated documentation files (the +# "Software"), to deal in the Software without restriction, including +# without limitation the rights to use, copy, modify, merge, publish, +# distribute, sublicense, and/or sell copies of the Software, and to +# permit persons to whom the Software is furnished to do so, subject to +# the following conditions: +# +# The above copyright notice and this permission notice shall be +# included in all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +# + +__doc__ = """ +pyparsing module - Classes and methods to define and execute parsing grammars +============================================================================= + +The pyparsing module is an alternative approach to creating and +executing simple grammars, vs. the traditional lex/yacc approach, or the +use of regular expressions. With pyparsing, you don't need to learn +a new syntax for defining grammars or matching expressions - the parsing +module provides a library of classes that you use to construct the +grammar directly in Python. + +Here is a program to parse "Hello, World!" (or any greeting of the form +``"<salutation>, <addressee>!"``), built up using :class:`Word`, +:class:`Literal`, and :class:`And` elements +(the :meth:`'+'<ParserElement.__add__>` operators create :class:`And` expressions, +and the strings are auto-converted to :class:`Literal` expressions):: + + from pyparsing import Word, alphas + + # define grammar of a greeting + greet = Word(alphas) + "," + Word(alphas) + "!" + + hello = "Hello, World!" + print(hello, "->", greet.parse_string(hello)) + +The program outputs the following:: + + Hello, World! -> ['Hello', ',', 'World', '!'] + +The Python representation of the grammar is quite readable, owing to the +self-explanatory class names, and the use of :class:`'+'<And>`, +:class:`'|'<MatchFirst>`, :class:`'^'<Or>` and :class:`'&'<Each>` operators. + +The :class:`ParseResults` object returned from +:class:`ParserElement.parseString` can be +accessed as a nested list, a dictionary, or an object with named +attributes. + +The pyparsing module handles some of the problems that are typically +vexing when writing text parsers: + + - extra or missing whitespace (the above program will also handle + "Hello,World!", "Hello , World !", etc.) + - quoted strings + - embedded comments + + +Getting Started - +----------------- +Visit the classes :class:`ParserElement` and :class:`ParseResults` to +see the base classes that most other pyparsing +classes inherit from. Use the docstrings for examples of how to: + + - construct literal match expressions from :class:`Literal` and + :class:`CaselessLiteral` classes + - construct character word-group expressions using the :class:`Word` + class + - see how to create repetitive expressions using :class:`ZeroOrMore` + and :class:`OneOrMore` classes + - use :class:`'+'<And>`, :class:`'|'<MatchFirst>`, :class:`'^'<Or>`, + and :class:`'&'<Each>` operators to combine simple expressions into + more complex ones + - associate names with your parsed results using + :class:`ParserElement.setResultsName` + - access the parsed data, which is returned as a :class:`ParseResults` + object + - find some helpful expression short-cuts like :class:`delimitedList` + and :class:`oneOf` + - find more useful common expressions in the :class:`pyparsing_common` + namespace class +""" +from typing import NamedTuple + + +class version_info(NamedTuple): + major: int + minor: int + micro: int + releaselevel: str + serial: int + + @property + def __version__(self): + return ( + "{}.{}.{}".format(self.major, self.minor, self.micro) + + ( + "{}{}{}".format( + "r" if self.releaselevel[0] == "c" else "", + self.releaselevel[0], + self.serial, + ), + "", + )[self.releaselevel == "final"] + ) + + def __str__(self): + return "{} {} / {}".format(__name__, self.__version__, __version_time__) + + def __repr__(self): + return "{}.{}({})".format( + __name__, + type(self).__name__, + ", ".join("{}={!r}".format(*nv) for nv in zip(self._fields, self)), + ) + + +__version_info__ = version_info(3, 0, 9, "final", 0) +__version_time__ = "05 May 2022 07:02 UTC" +__version__ = __version_info__.__version__ +__versionTime__ = __version_time__ +__author__ = "Paul McGuire <ptmcg.gm+pyparsing@gmail.com>" + +from .util import * +from .exceptions import * +from .actions import * +from .core import __diag__, __compat__ +from .results import * +from .core import * +from .core import _builtin_exprs as core_builtin_exprs +from .helpers import * +from .helpers import _builtin_exprs as helper_builtin_exprs + +from .unicode import unicode_set, UnicodeRangeList, pyparsing_unicode as unicode +from .testing import pyparsing_test as testing +from .common import ( + pyparsing_common as common, + _builtin_exprs as common_builtin_exprs, +) + +# define backward compat synonyms +if "pyparsing_unicode" not in globals(): + pyparsing_unicode = unicode +if "pyparsing_common" not in globals(): + pyparsing_common = common +if "pyparsing_test" not in globals(): + pyparsing_test = testing + +core_builtin_exprs += common_builtin_exprs + helper_builtin_exprs + + +__all__ = [ + "__version__", + "__version_time__", + "__author__", + "__compat__", + "__diag__", + "And", + "AtLineStart", + "AtStringStart", + "CaselessKeyword", + "CaselessLiteral", + "CharsNotIn", + "Combine", + "Dict", + "Each", + "Empty", + "FollowedBy", + "Forward", + "GoToColumn", + "Group", + "IndentedBlock", + "Keyword", + "LineEnd", + "LineStart", + "Literal", + "Located", + "PrecededBy", + "MatchFirst", + "NoMatch", + "NotAny", + "OneOrMore", + "OnlyOnce", + "OpAssoc", + "Opt", + "Optional", + "Or", + "ParseBaseException", + "ParseElementEnhance", + "ParseException", + "ParseExpression", + "ParseFatalException", + "ParseResults", + "ParseSyntaxException", + "ParserElement", + "PositionToken", + "QuotedString", + "RecursiveGrammarException", + "Regex", + "SkipTo", + "StringEnd", + "StringStart", + "Suppress", + "Token", + "TokenConverter", + "White", + "Word", + "WordEnd", + "WordStart", + "ZeroOrMore", + "Char", + "alphanums", + "alphas", + "alphas8bit", + "any_close_tag", + "any_open_tag", + "c_style_comment", + "col", + "common_html_entity", + "counted_array", + "cpp_style_comment", + "dbl_quoted_string", + "dbl_slash_comment", + "delimited_list", + "dict_of", + "empty", + "hexnums", + "html_comment", + "identchars", + "identbodychars", + "java_style_comment", + "line", + "line_end", + "line_start", + "lineno", + "make_html_tags", + "make_xml_tags", + "match_only_at_col", + "match_previous_expr", + "match_previous_literal", + "nested_expr", + "null_debug_action", + "nums", + "one_of", + "printables", + "punc8bit", + "python_style_comment", + "quoted_string", + "remove_quotes", + "replace_with", + "replace_html_entity", + "rest_of_line", + "sgl_quoted_string", + "srange", + "string_end", + "string_start", + "trace_parse_action", + "unicode_string", + "with_attribute", + "indentedBlock", + "original_text_for", + "ungroup", + "infix_notation", + "locatedExpr", + "with_class", + "CloseMatch", + "token_map", + "pyparsing_common", + "pyparsing_unicode", + "unicode_set", + "condition_as_parse_action", + "pyparsing_test", + # pre-PEP8 compatibility names + "__versionTime__", + "anyCloseTag", + "anyOpenTag", + "cStyleComment", + "commonHTMLEntity", + "countedArray", + "cppStyleComment", + "dblQuotedString", + "dblSlashComment", + "delimitedList", + "dictOf", + "htmlComment", + "javaStyleComment", + "lineEnd", + "lineStart", + "makeHTMLTags", + "makeXMLTags", + "matchOnlyAtCol", + "matchPreviousExpr", + "matchPreviousLiteral", + "nestedExpr", + "nullDebugAction", + "oneOf", + "opAssoc", + "pythonStyleComment", + "quotedString", + "removeQuotes", + "replaceHTMLEntity", + "replaceWith", + "restOfLine", + "sglQuotedString", + "stringEnd", + "stringStart", + "traceParseAction", + "unicodeString", + "withAttribute", + "indentedBlock", + "originalTextFor", + "infixNotation", + "locatedExpr", + "withClass", + "tokenMap", + "conditionAsParseAction", + "autoname_elements", +] diff --git a/pkg_resources/_vendor/pyparsing/actions.py b/pkg_resources/_vendor/pyparsing/actions.py new file mode 100644 index 00000000..f72c66e7 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/actions.py @@ -0,0 +1,207 @@ +# actions.py + +from .exceptions import ParseException +from .util import col + + +class OnlyOnce: + """ + Wrapper for parse actions, to ensure they are only called once. + """ + + def __init__(self, method_call): + from .core import _trim_arity + + self.callable = _trim_arity(method_call) + self.called = False + + def __call__(self, s, l, t): + if not self.called: + results = self.callable(s, l, t) + self.called = True + return results + raise ParseException(s, l, "OnlyOnce obj called multiple times w/out reset") + + def reset(self): + """ + Allow the associated parse action to be called once more. + """ + + self.called = False + + +def match_only_at_col(n): + """ + Helper method for defining parse actions that require matching at + a specific column in the input text. + """ + + def verify_col(strg, locn, toks): + if col(locn, strg) != n: + raise ParseException(strg, locn, "matched token not at column {}".format(n)) + + return verify_col + + +def replace_with(repl_str): + """ + Helper method for common parse actions that simply return + a literal value. Especially useful when used with + :class:`transform_string<ParserElement.transform_string>` (). + + Example:: + + num = Word(nums).set_parse_action(lambda toks: int(toks[0])) + na = one_of("N/A NA").set_parse_action(replace_with(math.nan)) + term = na | num + + term[1, ...].parse_string("324 234 N/A 234") # -> [324, 234, nan, 234] + """ + return lambda s, l, t: [repl_str] + + +def remove_quotes(s, l, t): + """ + Helper parse action for removing quotation marks from parsed + quoted strings. + + Example:: + + # by default, quotation marks are included in parsed results + quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"] + + # use remove_quotes to strip quotation marks from parsed results + quoted_string.set_parse_action(remove_quotes) + quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"] + """ + return t[0][1:-1] + + +def with_attribute(*args, **attr_dict): + """ + Helper to create a validating parse action to be used with start + tags created with :class:`make_xml_tags` or + :class:`make_html_tags`. Use ``with_attribute`` to qualify + a starting tag with a required attribute value, to avoid false + matches on common tags such as ``<TD>`` or ``<DIV>``. + + Call ``with_attribute`` with a series of attribute names and + values. Specify the list of filter attributes names and values as: + + - keyword arguments, as in ``(align="right")``, or + - as an explicit dict with ``**`` operator, when an attribute + name is also a Python reserved word, as in ``**{"class":"Customer", "align":"right"}`` + - a list of name-value tuples, as in ``(("ns1:class", "Customer"), ("ns2:align", "right"))`` + + For attribute names with a namespace prefix, you must use the second + form. Attribute names are matched insensitive to upper/lower case. + + If just testing for ``class`` (with or without a namespace), use + :class:`with_class`. + + To verify that the attribute exists, but without specifying a value, + pass ``with_attribute.ANY_VALUE`` as the value. + + Example:: + + html = ''' + <div> + Some text + <div type="grid">1 4 0 1 0</div> + <div type="graph">1,3 2,3 1,1</div> + <div>this has no type</div> + </div> + + ''' + div,div_end = make_html_tags("div") + + # only match div tag having a type attribute with value "grid" + div_grid = div().set_parse_action(with_attribute(type="grid")) + grid_expr = div_grid + SkipTo(div | div_end)("body") + for grid_header in grid_expr.search_string(html): + print(grid_header.body) + + # construct a match with any div tag having a type attribute, regardless of the value + div_any_type = div().set_parse_action(with_attribute(type=with_attribute.ANY_VALUE)) + div_expr = div_any_type + SkipTo(div | div_end)("body") + for div_header in div_expr.search_string(html): + print(div_header.body) + + prints:: + + 1 4 0 1 0 + + 1 4 0 1 0 + 1,3 2,3 1,1 + """ + if args: + attrs = args[:] + else: + attrs = attr_dict.items() + attrs = [(k, v) for k, v in attrs] + + def pa(s, l, tokens): + for attrName, attrValue in attrs: + if attrName not in tokens: + raise ParseException(s, l, "no matching attribute " + attrName) + if attrValue != with_attribute.ANY_VALUE and tokens[attrName] != attrValue: + raise ParseException( + s, + l, + "attribute {!r} has value {!r}, must be {!r}".format( + attrName, tokens[attrName], attrValue + ), + ) + + return pa + + +with_attribute.ANY_VALUE = object() + + +def with_class(classname, namespace=""): + """ + Simplified version of :class:`with_attribute` when + matching on a div class - made difficult because ``class`` is + a reserved word in Python. + + Example:: + + html = ''' + <div> + Some text + <div class="grid">1 4 0 1 0</div> + <div class="graph">1,3 2,3 1,1</div> + <div>this <div> has no class</div> + </div> + + ''' + div,div_end = make_html_tags("div") + div_grid = div().set_parse_action(with_class("grid")) + + grid_expr = div_grid + SkipTo(div | div_end)("body") + for grid_header in grid_expr.search_string(html): + print(grid_header.body) + + div_any_type = div().set_parse_action(with_class(withAttribute.ANY_VALUE)) + div_expr = div_any_type + SkipTo(div | div_end)("body") + for div_header in div_expr.search_string(html): + print(div_header.body) + + prints:: + + 1 4 0 1 0 + + 1 4 0 1 0 + 1,3 2,3 1,1 + """ + classattr = "{}:class".format(namespace) if namespace else "class" + return with_attribute(**{classattr: classname}) + + +# pre-PEP8 compatibility symbols +replaceWith = replace_with +removeQuotes = remove_quotes +withAttribute = with_attribute +withClass = with_class +matchOnlyAtCol = match_only_at_col diff --git a/pkg_resources/_vendor/pyparsing/common.py b/pkg_resources/_vendor/pyparsing/common.py new file mode 100644 index 00000000..1859fb79 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/common.py @@ -0,0 +1,424 @@ +# common.py +from .core import * +from .helpers import delimited_list, any_open_tag, any_close_tag +from datetime import datetime + + +# some other useful expressions - using lower-case class name since we are really using this as a namespace +class pyparsing_common: + """Here are some common low-level expressions that may be useful in + jump-starting parser development: + + - numeric forms (:class:`integers<integer>`, :class:`reals<real>`, + :class:`scientific notation<sci_real>`) + - common :class:`programming identifiers<identifier>` + - network addresses (:class:`MAC<mac_address>`, + :class:`IPv4<ipv4_address>`, :class:`IPv6<ipv6_address>`) + - ISO8601 :class:`dates<iso8601_date>` and + :class:`datetime<iso8601_datetime>` + - :class:`UUID<uuid>` + - :class:`comma-separated list<comma_separated_list>` + - :class:`url` + + Parse actions: + + - :class:`convertToInteger` + - :class:`convertToFloat` + - :class:`convertToDate` + - :class:`convertToDatetime` + - :class:`stripHTMLTags` + - :class:`upcaseTokens` + - :class:`downcaseTokens` + + Example:: + + pyparsing_common.number.runTests(''' + # any int or real number, returned as the appropriate type + 100 + -100 + +100 + 3.14159 + 6.02e23 + 1e-12 + ''') + + pyparsing_common.fnumber.runTests(''' + # any int or real number, returned as float + 100 + -100 + +100 + 3.14159 + 6.02e23 + 1e-12 + ''') + + pyparsing_common.hex_integer.runTests(''' + # hex numbers + 100 + FF + ''') + + pyparsing_common.fraction.runTests(''' + # fractions + 1/2 + -3/4 + ''') + + pyparsing_common.mixed_integer.runTests(''' + # mixed fractions + 1 + 1/2 + -3/4 + 1-3/4 + ''') + + import uuid + pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID)) + pyparsing_common.uuid.runTests(''' + # uuid + 12345678-1234-5678-1234-567812345678 + ''') + + prints:: + + # any int or real number, returned as the appropriate type + 100 + [100] + + -100 + [-100] + + +100 + [100] + + 3.14159 + [3.14159] + + 6.02e23 + [6.02e+23] + + 1e-12 + [1e-12] + + # any int or real number, returned as float + 100 + [100.0] + + -100 + [-100.0] + + +100 + [100.0] + + 3.14159 + [3.14159] + + 6.02e23 + [6.02e+23] + + 1e-12 + [1e-12] + + # hex numbers + 100 + [256] + + FF + [255] + + # fractions + 1/2 + [0.5] + + -3/4 + [-0.75] + + # mixed fractions + 1 + [1] + + 1/2 + [0.5] + + -3/4 + [-0.75] + + 1-3/4 + [1.75] + + # uuid + 12345678-1234-5678-1234-567812345678 + [UUID('12345678-1234-5678-1234-567812345678')] + """ + + convert_to_integer = token_map(int) + """ + Parse action for converting parsed integers to Python int + """ + + convert_to_float = token_map(float) + """ + Parse action for converting parsed numbers to Python float + """ + + integer = Word(nums).set_name("integer").set_parse_action(convert_to_integer) + """expression that parses an unsigned integer, returns an int""" + + hex_integer = ( + Word(hexnums).set_name("hex integer").set_parse_action(token_map(int, 16)) + ) + """expression that parses a hexadecimal integer, returns an int""" + + signed_integer = ( + Regex(r"[+-]?\d+") + .set_name("signed integer") + .set_parse_action(convert_to_integer) + ) + """expression that parses an integer with optional leading sign, returns an int""" + + fraction = ( + signed_integer().set_parse_action(convert_to_float) + + "/" + + signed_integer().set_parse_action(convert_to_float) + ).set_name("fraction") + """fractional expression of an integer divided by an integer, returns a float""" + fraction.add_parse_action(lambda tt: tt[0] / tt[-1]) + + mixed_integer = ( + fraction | signed_integer + Opt(Opt("-").suppress() + fraction) + ).set_name("fraction or mixed integer-fraction") + """mixed integer of the form 'integer - fraction', with optional leading integer, returns float""" + mixed_integer.add_parse_action(sum) + + real = ( + Regex(r"[+-]?(?:\d+\.\d*|\.\d+)") + .set_name("real number") + .set_parse_action(convert_to_float) + ) + """expression that parses a floating point number and returns a float""" + + sci_real = ( + Regex(r"[+-]?(?:\d+(?:[eE][+-]?\d+)|(?:\d+\.\d*|\.\d+)(?:[eE][+-]?\d+)?)") + .set_name("real number with scientific notation") + .set_parse_action(convert_to_float) + ) + """expression that parses a floating point number with optional + scientific notation and returns a float""" + + # streamlining this expression makes the docs nicer-looking + number = (sci_real | real | signed_integer).setName("number").streamline() + """any numeric expression, returns the corresponding Python type""" + + fnumber = ( + Regex(r"[+-]?\d+\.?\d*([eE][+-]?\d+)?") + .set_name("fnumber") + .set_parse_action(convert_to_float) + ) + """any int or real number, returned as float""" + + identifier = Word(identchars, identbodychars).set_name("identifier") + """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')""" + + ipv4_address = Regex( + r"(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}" + ).set_name("IPv4 address") + "IPv4 address (``0.0.0.0 - 255.255.255.255``)" + + _ipv6_part = Regex(r"[0-9a-fA-F]{1,4}").set_name("hex_integer") + _full_ipv6_address = (_ipv6_part + (":" + _ipv6_part) * 7).set_name( + "full IPv6 address" + ) + _short_ipv6_address = ( + Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) + + "::" + + Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) + ).set_name("short IPv6 address") + _short_ipv6_address.add_condition( + lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8 + ) + _mixed_ipv6_address = ("::ffff:" + ipv4_address).set_name("mixed IPv6 address") + ipv6_address = Combine( + (_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).set_name( + "IPv6 address" + ) + ).set_name("IPv6 address") + "IPv6 address (long, short, or mixed form)" + + mac_address = Regex( + r"[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}" + ).set_name("MAC address") + "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)" + + @staticmethod + def convert_to_date(fmt: str = "%Y-%m-%d"): + """ + Helper to create a parse action for converting parsed date string to Python datetime.date + + Params - + - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%d"``) + + Example:: + + date_expr = pyparsing_common.iso8601_date.copy() + date_expr.setParseAction(pyparsing_common.convertToDate()) + print(date_expr.parseString("1999-12-31")) + + prints:: + + [datetime.date(1999, 12, 31)] + """ + + def cvt_fn(ss, ll, tt): + try: + return datetime.strptime(tt[0], fmt).date() + except ValueError as ve: + raise ParseException(ss, ll, str(ve)) + + return cvt_fn + + @staticmethod + def convert_to_datetime(fmt: str = "%Y-%m-%dT%H:%M:%S.%f"): + """Helper to create a parse action for converting parsed + datetime string to Python datetime.datetime + + Params - + - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%dT%H:%M:%S.%f"``) + + Example:: + + dt_expr = pyparsing_common.iso8601_datetime.copy() + dt_expr.setParseAction(pyparsing_common.convertToDatetime()) + print(dt_expr.parseString("1999-12-31T23:59:59.999")) + + prints:: + + [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)] + """ + + def cvt_fn(s, l, t): + try: + return datetime.strptime(t[0], fmt) + except ValueError as ve: + raise ParseException(s, l, str(ve)) + + return cvt_fn + + iso8601_date = Regex( + r"(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?" + ).set_name("ISO8601 date") + "ISO8601 date (``yyyy-mm-dd``)" + + iso8601_datetime = Regex( + r"(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?" + ).set_name("ISO8601 datetime") + "ISO8601 datetime (``yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)``) - trailing seconds, milliseconds, and timezone optional; accepts separating ``'T'`` or ``' '``" + + uuid = Regex(r"[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}").set_name("UUID") + "UUID (``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``)" + + _html_stripper = any_open_tag.suppress() | any_close_tag.suppress() + + @staticmethod + def strip_html_tags(s: str, l: int, tokens: ParseResults): + """Parse action to remove HTML tags from web page HTML source + + Example:: + + # strip HTML links from normal text + text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' + td, td_end = makeHTMLTags("TD") + table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end + print(table_text.parseString(text).body) + + Prints:: + + More info at the pyparsing wiki page + """ + return pyparsing_common._html_stripper.transform_string(tokens[0]) + + _commasepitem = ( + Combine( + OneOrMore( + ~Literal(",") + + ~LineEnd() + + Word(printables, exclude_chars=",") + + Opt(White(" \t") + ~FollowedBy(LineEnd() | ",")) + ) + ) + .streamline() + .set_name("commaItem") + ) + comma_separated_list = delimited_list( + Opt(quoted_string.copy() | _commasepitem, default="") + ).set_name("comma separated list") + """Predefined expression of 1 or more printable words or quoted strings, separated by commas.""" + + upcase_tokens = staticmethod(token_map(lambda t: t.upper())) + """Parse action to convert tokens to upper case.""" + + downcase_tokens = staticmethod(token_map(lambda t: t.lower())) + """Parse action to convert tokens to lower case.""" + + # fmt: off + url = Regex( + # https://mathiasbynens.be/demo/url-regex + # https://gist.github.com/dperini/729294 + r"^" + + # protocol identifier (optional) + # short syntax // still required + r"(?:(?:(?P<scheme>https?|ftp):)?\/\/)" + + # user:pass BasicAuth (optional) + r"(?:(?P<auth>\S+(?::\S*)?)@)?" + + r"(?P<host>" + + # IP address exclusion + # private & local networks + r"(?!(?:10|127)(?:\.\d{1,3}){3})" + + r"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})" + + r"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})" + + # IP address dotted notation octets + # excludes loopback network 0.0.0.0 + # excludes reserved space >= 224.0.0.0 + # excludes network & broadcast addresses + # (first & last IP address of each class) + r"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])" + + r"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}" + + r"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))" + + r"|" + + # host & domain names, may end with dot + # can be replaced by a shortest alternative + # (?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+ + r"(?:" + + r"(?:" + + r"[a-z0-9\u00a1-\uffff]" + + r"[a-z0-9\u00a1-\uffff_-]{0,62}" + + r")?" + + r"[a-z0-9\u00a1-\uffff]\." + + r")+" + + # TLD identifier name, may end with dot + r"(?:[a-z\u00a1-\uffff]{2,}\.?)" + + r")" + + # port number (optional) + r"(:(?P<port>\d{2,5}))?" + + # resource path (optional) + r"(?P<path>\/[^?# ]*)?" + + # query string (optional) + r"(\?(?P<query>[^#]*))?" + + # fragment (optional) + r"(#(?P<fragment>\S*))?" + + r"$" + ).set_name("url") + # fmt: on + + # pre-PEP8 compatibility names + convertToInteger = convert_to_integer + convertToFloat = convert_to_float + convertToDate = convert_to_date + convertToDatetime = convert_to_datetime + stripHTMLTags = strip_html_tags + upcaseTokens = upcase_tokens + downcaseTokens = downcase_tokens + + +_builtin_exprs = [ + v for v in vars(pyparsing_common).values() if isinstance(v, ParserElement) +] diff --git a/pkg_resources/_vendor/pyparsing/core.py b/pkg_resources/_vendor/pyparsing/core.py new file mode 100644 index 00000000..9acba3f3 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/core.py @@ -0,0 +1,5814 @@ +# +# core.py +# +import os +import typing +from typing import ( + NamedTuple, + Union, + Callable, + Any, + Generator, + Tuple, + List, + TextIO, + Set, + Sequence, +) +from abc import ABC, abstractmethod +from enum import Enum +import string +import copy +import warnings +import re +import sys +from collections.abc import Iterable +import traceback +import types +from operator import itemgetter +from functools import wraps +from threading import RLock +from pathlib import Path + +from .util import ( + _FifoCache, + _UnboundedCache, + __config_flags, + _collapse_string_to_ranges, + _escape_regex_range_chars, + _bslash, + _flatten, + LRUMemo as _LRUMemo, + UnboundedMemo as _UnboundedMemo, +) +from .exceptions import * +from .actions import * +from .results import ParseResults, _ParseResultsWithOffset +from .unicode import pyparsing_unicode + +_MAX_INT = sys.maxsize +str_type: Tuple[type, ...] = (str, bytes) + +# +# Copyright (c) 2003-2022 Paul T. McGuire +# +# Permission is hereby granted, free of charge, to any person obtaining +# a copy of this software and associated documentation files (the +# "Software"), to deal in the Software without restriction, including +# without limitation the rights to use, copy, modify, merge, publish, +# distribute, sublicense, and/or sell copies of the Software, and to +# permit persons to whom the Software is furnished to do so, subject to +# the following conditions: +# +# The above copyright notice and this permission notice shall be +# included in all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +# + + +if sys.version_info >= (3, 8): + from functools import cached_property +else: + + class cached_property: + def __init__(self, func): + self._func = func + + def __get__(self, instance, owner=None): + ret = instance.__dict__[self._func.__name__] = self._func(instance) + return ret + + +class __compat__(__config_flags): + """ + A cross-version compatibility configuration for pyparsing features that will be + released in a future version. By setting values in this configuration to True, + those features can be enabled in prior versions for compatibility development + and testing. + + - ``collect_all_And_tokens`` - flag to enable fix for Issue #63 that fixes erroneous grouping + of results names when an :class:`And` expression is nested within an :class:`Or` or :class:`MatchFirst`; + maintained for compatibility, but setting to ``False`` no longer restores pre-2.3.1 + behavior + """ + + _type_desc = "compatibility" + + collect_all_And_tokens = True + + _all_names = [__ for __ in locals() if not __.startswith("_")] + _fixed_names = """ + collect_all_And_tokens + """.split() + + +class __diag__(__config_flags): + _type_desc = "diagnostic" + + warn_multiple_tokens_in_named_alternation = False + warn_ungrouped_named_tokens_in_collection = False + warn_name_set_on_empty_Forward = False + warn_on_parse_using_empty_Forward = False + warn_on_assignment_to_Forward = False + warn_on_multiple_string_args_to_oneof = False + warn_on_match_first_with_lshift_operator = False + enable_debug_on_named_expressions = False + + _all_names = [__ for __ in locals() if not __.startswith("_")] + _warning_names = [name for name in _all_names if name.startswith("warn")] + _debug_names = [name for name in _all_names if name.startswith("enable_debug")] + + @classmethod + def enable_all_warnings(cls) -> None: + for name in cls._warning_names: + cls.enable(name) + + +class Diagnostics(Enum): + """ + Diagnostic configuration (all default to disabled) + - ``warn_multiple_tokens_in_named_alternation`` - flag to enable warnings when a results + name is defined on a :class:`MatchFirst` or :class:`Or` expression with one or more :class:`And` subexpressions + - ``warn_ungrouped_named_tokens_in_collection`` - flag to enable warnings when a results + name is defined on a containing expression with ungrouped subexpressions that also + have results names + - ``warn_name_set_on_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined + with a results name, but has no contents defined + - ``warn_on_parse_using_empty_Forward`` - flag to enable warnings when a :class:`Forward` is + defined in a grammar but has never had an expression attached to it + - ``warn_on_assignment_to_Forward`` - flag to enable warnings when a :class:`Forward` is defined + but is overwritten by assigning using ``'='`` instead of ``'<<='`` or ``'<<'`` + - ``warn_on_multiple_string_args_to_oneof`` - flag to enable warnings when :class:`one_of` is + incorrectly called with multiple str arguments + - ``enable_debug_on_named_expressions`` - flag to auto-enable debug on all subsequent + calls to :class:`ParserElement.set_name` + + Diagnostics are enabled/disabled by calling :class:`enable_diag` and :class:`disable_diag`. + All warnings can be enabled by calling :class:`enable_all_warnings`. + """ + + warn_multiple_tokens_in_named_alternation = 0 + warn_ungrouped_named_tokens_in_collection = 1 + warn_name_set_on_empty_Forward = 2 + warn_on_parse_using_empty_Forward = 3 + warn_on_assignment_to_Forward = 4 + warn_on_multiple_string_args_to_oneof = 5 + warn_on_match_first_with_lshift_operator = 6 + enable_debug_on_named_expressions = 7 + + +def enable_diag(diag_enum: Diagnostics) -> None: + """ + Enable a global pyparsing diagnostic flag (see :class:`Diagnostics`). + """ + __diag__.enable(diag_enum.name) + + +def disable_diag(diag_enum: Diagnostics) -> None: + """ + Disable a global pyparsing diagnostic flag (see :class:`Diagnostics`). + """ + __diag__.disable(diag_enum.name) + + +def enable_all_warnings() -> None: + """ + Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`). + """ + __diag__.enable_all_warnings() + + +# hide abstract class +del __config_flags + + +def _should_enable_warnings( + cmd_line_warn_options: typing.Iterable[str], warn_env_var: typing.Optional[str] +) -> bool: + enable = bool(warn_env_var) + for warn_opt in cmd_line_warn_options: + w_action, w_message, w_category, w_module, w_line = (warn_opt + "::::").split( + ":" + )[:5] + if not w_action.lower().startswith("i") and ( + not (w_message or w_category or w_module) or w_module == "pyparsing" + ): + enable = True + elif w_action.lower().startswith("i") and w_module in ("pyparsing", ""): + enable = False + return enable + + +if _should_enable_warnings( + sys.warnoptions, os.environ.get("PYPARSINGENABLEALLWARNINGS") +): + enable_all_warnings() + + +# build list of single arg builtins, that can be used as parse actions +_single_arg_builtins = { + sum, + len, + sorted, + reversed, + list, + tuple, + set, + any, + all, + min, + max, +} + +_generatorType = types.GeneratorType +ParseAction = Union[ + Callable[[], Any], + Callable[[ParseResults], Any], + Callable[[int, ParseResults], Any], + Callable[[str, int, ParseResults], Any], +] +ParseCondition = Union[ + Callable[[], bool], + Callable[[ParseResults], bool], + Callable[[int, ParseResults], bool], + Callable[[str, int, ParseResults], bool], +] +ParseFailAction = Callable[[str, int, "ParserElement", Exception], None] +DebugStartAction = Callable[[str, int, "ParserElement", bool], None] +DebugSuccessAction = Callable[ + [str, int, int, "ParserElement", ParseResults, bool], None +] +DebugExceptionAction = Callable[[str, int, "ParserElement", Exception, bool], None] + + +alphas = string.ascii_uppercase + string.ascii_lowercase +identchars = pyparsing_unicode.Latin1.identchars +identbodychars = pyparsing_unicode.Latin1.identbodychars +nums = "0123456789" +hexnums = nums + "ABCDEFabcdef" +alphanums = alphas + nums +printables = "".join([c for c in string.printable if c not in string.whitespace]) + +_trim_arity_call_line: traceback.StackSummary = None + + +def _trim_arity(func, max_limit=3): + """decorator to trim function calls to match the arity of the target""" + global _trim_arity_call_line + + if func in _single_arg_builtins: + return lambda s, l, t: func(t) + + limit = 0 + found_arity = False + + def extract_tb(tb, limit=0): + frames = traceback.extract_tb(tb, limit=limit) + frame_summary = frames[-1] + return [frame_summary[:2]] + + # synthesize what would be returned by traceback.extract_stack at the call to + # user's parse action 'func', so that we don't incur call penalty at parse time + + # fmt: off + LINE_DIFF = 7 + # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND + # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!! + _trim_arity_call_line = (_trim_arity_call_line or traceback.extract_stack(limit=2)[-1]) + pa_call_line_synth = (_trim_arity_call_line[0], _trim_arity_call_line[1] + LINE_DIFF) + + def wrapper(*args): + nonlocal found_arity, limit + while 1: + try: + ret = func(*args[limit:]) + found_arity = True + return ret + except TypeError as te: + # re-raise TypeErrors if they did not come from our arity testing + if found_arity: + raise + else: + tb = te.__traceback__ + trim_arity_type_error = ( + extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth + ) + del tb + + if trim_arity_type_error: + if limit < max_limit: + limit += 1 + continue + + raise + # fmt: on + + # copy func name to wrapper for sensible debug output + # (can't use functools.wraps, since that messes with function signature) + func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) + wrapper.__name__ = func_name + wrapper.__doc__ = func.__doc__ + + return wrapper + + +def condition_as_parse_action( + fn: ParseCondition, message: str = None, fatal: bool = False +) -> ParseAction: + """ + Function to convert a simple predicate function that returns ``True`` or ``False`` + into a parse action. Can be used in places when a parse action is required + and :class:`ParserElement.add_condition` cannot be used (such as when adding a condition + to an operator level in :class:`infix_notation`). + + Optional keyword arguments: + + - ``message`` - define a custom message to be used in the raised exception + - ``fatal`` - if True, will raise :class:`ParseFatalException` to stop parsing immediately; + otherwise will raise :class:`ParseException` + + """ + msg = message if message is not None else "failed user-defined condition" + exc_type = ParseFatalException if fatal else ParseException + fn = _trim_arity(fn) + + @wraps(fn) + def pa(s, l, t): + if not bool(fn(s, l, t)): + raise exc_type(s, l, msg) + + return pa + + +def _default_start_debug_action( + instring: str, loc: int, expr: "ParserElement", cache_hit: bool = False +): + cache_hit_str = "*" if cache_hit else "" + print( + ( + "{}Match {} at loc {}({},{})\n {}\n {}^".format( + cache_hit_str, + expr, + loc, + lineno(loc, instring), + col(loc, instring), + line(loc, instring), + " " * (col(loc, instring) - 1), + ) + ) + ) + + +def _default_success_debug_action( + instring: str, + startloc: int, + endloc: int, + expr: "ParserElement", + toks: ParseResults, + cache_hit: bool = False, +): + cache_hit_str = "*" if cache_hit else "" + print("{}Matched {} -> {}".format(cache_hit_str, expr, toks.as_list())) + + +def _default_exception_debug_action( + instring: str, + loc: int, + expr: "ParserElement", + exc: Exception, + cache_hit: bool = False, +): + cache_hit_str = "*" if cache_hit else "" + print( + "{}Match {} failed, {} raised: {}".format( + cache_hit_str, expr, type(exc).__name__, exc + ) + ) + + +def null_debug_action(*args): + """'Do-nothing' debug action, to suppress debugging output during parsing.""" + + +class ParserElement(ABC): + """Abstract base level parser element class.""" + + DEFAULT_WHITE_CHARS: str = " \n\t\r" + verbose_stacktrace: bool = False + _literalStringClass: typing.Optional[type] = None + + @staticmethod + def set_default_whitespace_chars(chars: str) -> None: + r""" + Overrides the default whitespace chars + + Example:: + + # default whitespace chars are space, <TAB> and newline + Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl'] + + # change to just treat newline as significant + ParserElement.set_default_whitespace_chars(" \t") + Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def'] + """ + ParserElement.DEFAULT_WHITE_CHARS = chars + + # update whitespace all parse expressions defined in this module + for expr in _builtin_exprs: + if expr.copyDefaultWhiteChars: + expr.whiteChars = set(chars) + + @staticmethod + def inline_literals_using(cls: type) -> None: + """ + Set class to be used for inclusion of string literals into a parser. + + Example:: + + # default literal class used is Literal + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + date_str.parse_string("1999/12/31") # -> ['1999', '/', '12', '/', '31'] + + + # change to Suppress + ParserElement.inline_literals_using(Suppress) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + date_str.parse_string("1999/12/31") # -> ['1999', '12', '31'] + """ + ParserElement._literalStringClass = cls + + class DebugActions(NamedTuple): + debug_try: typing.Optional[DebugStartAction] + debug_match: typing.Optional[DebugSuccessAction] + debug_fail: typing.Optional[DebugExceptionAction] + + def __init__(self, savelist: bool = False): + self.parseAction: List[ParseAction] = list() + self.failAction: typing.Optional[ParseFailAction] = None + self.customName = None + self._defaultName = None + self.resultsName = None + self.saveAsList = savelist + self.skipWhitespace = True + self.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) + self.copyDefaultWhiteChars = True + # used when checking for left-recursion + self.mayReturnEmpty = False + self.keepTabs = False + self.ignoreExprs: List["ParserElement"] = list() + self.debug = False + self.streamlined = False + # optimize exception handling for subclasses that don't advance parse index + self.mayIndexError = True + self.errmsg = "" + # mark results names as modal (report only last) or cumulative (list all) + self.modalResults = True + # custom debug actions + self.debugActions = self.DebugActions(None, None, None) + # avoid redundant calls to preParse + self.callPreparse = True + self.callDuringTry = False + self.suppress_warnings_: List[Diagnostics] = [] + + def suppress_warning(self, warning_type: Diagnostics) -> "ParserElement": + """ + Suppress warnings emitted for a particular diagnostic on this expression. + + Example:: + + base = pp.Forward() + base.suppress_warning(Diagnostics.warn_on_parse_using_empty_Forward) + + # statement would normally raise a warning, but is now suppressed + print(base.parseString("x")) + + """ + self.suppress_warnings_.append(warning_type) + return self + + def copy(self) -> "ParserElement": + """ + Make a copy of this :class:`ParserElement`. Useful for defining + different parse actions for the same parsing pattern, using copies of + the original parse element. + + Example:: + + integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) + integerK = integer.copy().add_parse_action(lambda toks: toks[0] * 1024) + Suppress("K") + integerM = integer.copy().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") + + print((integerK | integerM | integer)[1, ...].parse_string("5K 100 640K 256M")) + + prints:: + + [5120, 100, 655360, 268435456] + + Equivalent form of ``expr.copy()`` is just ``expr()``:: + + integerM = integer().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") + """ + cpy = copy.copy(self) + cpy.parseAction = self.parseAction[:] + cpy.ignoreExprs = self.ignoreExprs[:] + if self.copyDefaultWhiteChars: + cpy.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) + return cpy + + def set_results_name( + self, name: str, list_all_matches: bool = False, *, listAllMatches: bool = False + ) -> "ParserElement": + """ + Define name for referencing matching tokens as a nested attribute + of the returned parse results. + + Normally, results names are assigned as you would assign keys in a dict: + any existing value is overwritten by later values. If it is necessary to + keep all values captured for a particular results name, call ``set_results_name`` + with ``list_all_matches`` = True. + + NOTE: ``set_results_name`` returns a *copy* of the original :class:`ParserElement` object; + this is so that the client can define a basic element, such as an + integer, and reference it in multiple places with different names. + + You can also set results names using the abbreviated syntax, + ``expr("name")`` in place of ``expr.set_results_name("name")`` + - see :class:`__call__`. If ``list_all_matches`` is required, use + ``expr("name*")``. + + Example:: + + date_str = (integer.set_results_name("year") + '/' + + integer.set_results_name("month") + '/' + + integer.set_results_name("day")) + + # equivalent form: + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + """ + listAllMatches = listAllMatches or list_all_matches + return self._setResultsName(name, listAllMatches) + + def _setResultsName(self, name, listAllMatches=False): + if name is None: + return self + newself = self.copy() + if name.endswith("*"): + name = name[:-1] + listAllMatches = True + newself.resultsName = name + newself.modalResults = not listAllMatches + return newself + + def set_break(self, break_flag: bool = True) -> "ParserElement": + """ + Method to invoke the Python pdb debugger when this element is + about to be parsed. Set ``break_flag`` to ``True`` to enable, ``False`` to + disable. + """ + if break_flag: + _parseMethod = self._parse + + def breaker(instring, loc, doActions=True, callPreParse=True): + import pdb + + # this call to pdb.set_trace() is intentional, not a checkin error + pdb.set_trace() + return _parseMethod(instring, loc, doActions, callPreParse) + + breaker._originalParseMethod = _parseMethod + self._parse = breaker + else: + if hasattr(self._parse, "_originalParseMethod"): + self._parse = self._parse._originalParseMethod + return self + + def set_parse_action(self, *fns: ParseAction, **kwargs) -> "ParserElement": + """ + Define one or more actions to perform when successfully matching parse element definition. + + Parse actions can be called to perform data conversions, do extra validation, + update external data structures, or enhance or replace the parsed tokens. + Each parse action ``fn`` is a callable method with 0-3 arguments, called as + ``fn(s, loc, toks)`` , ``fn(loc, toks)`` , ``fn(toks)`` , or just ``fn()`` , where: + + - s = the original string being parsed (see note below) + - loc = the location of the matching substring + - toks = a list of the matched tokens, packaged as a :class:`ParseResults` object + + The parsed tokens are passed to the parse action as ParseResults. They can be + modified in place using list-style append, extend, and pop operations to update + the parsed list elements; and with dictionary-style item set and del operations + to add, update, or remove any named results. If the tokens are modified in place, + it is not necessary to return them with a return statement. + + Parse actions can also completely replace the given tokens, with another ``ParseResults`` + object, or with some entirely different object (common for parse actions that perform data + conversions). A convenient way to build a new parse result is to define the values + using a dict, and then create the return value using :class:`ParseResults.from_dict`. + + If None is passed as the ``fn`` parse action, all previously added parse actions for this + expression are cleared. + + Optional keyword arguments: + + - call_during_try = (default= ``False``) indicate if parse action should be run during + lookaheads and alternate testing. For parse actions that have side effects, it is + important to only call the parse action once it is determined that it is being + called as part of a successful parse. For parse actions that perform additional + validation, then call_during_try should be passed as True, so that the validation + code is included in the preliminary "try" parses. + + Note: the default parsing behavior is to expand tabs in the input string + before starting the parsing process. See :class:`parse_string` for more + information on parsing strings containing ``<TAB>`` s, and suggested + methods to maintain a consistent view of the parsed string, the parse + location, and line and column positions within the parsed string. + + Example:: + + # parse dates in the form YYYY/MM/DD + + # use parse action to convert toks from str to int at parse time + def convert_to_int(toks): + return int(toks[0]) + + # use a parse action to verify that the date is a valid date + def is_valid_date(instring, loc, toks): + from datetime import date + year, month, day = toks[::2] + try: + date(year, month, day) + except ValueError: + raise ParseException(instring, loc, "invalid date given") + + integer = Word(nums) + date_str = integer + '/' + integer + '/' + integer + + # add parse actions + integer.set_parse_action(convert_to_int) + date_str.set_parse_action(is_valid_date) + + # note that integer fields are now ints, not strings + date_str.run_tests(''' + # successful parse - note that integer fields were converted to ints + 1999/12/31 + + # fail - invalid date + 1999/13/31 + ''') + """ + if list(fns) == [None]: + self.parseAction = [] + else: + if not all(callable(fn) for fn in fns): + raise TypeError("parse actions must be callable") + self.parseAction = [_trim_arity(fn) for fn in fns] + self.callDuringTry = kwargs.get( + "call_during_try", kwargs.get("callDuringTry", False) + ) + return self + + def add_parse_action(self, *fns: ParseAction, **kwargs) -> "ParserElement": + """ + Add one or more parse actions to expression's list of parse actions. See :class:`set_parse_action`. + + See examples in :class:`copy`. + """ + self.parseAction += [_trim_arity(fn) for fn in fns] + self.callDuringTry = self.callDuringTry or kwargs.get( + "call_during_try", kwargs.get("callDuringTry", False) + ) + return self + + def add_condition(self, *fns: ParseCondition, **kwargs) -> "ParserElement": + """Add a boolean predicate function to expression's list of parse actions. See + :class:`set_parse_action` for function call signatures. Unlike ``set_parse_action``, + functions passed to ``add_condition`` need to return boolean success/fail of the condition. + + Optional keyword arguments: + + - message = define a custom message to be used in the raised exception + - fatal = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise + ParseException + - call_during_try = boolean to indicate if this method should be called during internal tryParse calls, + default=False + + Example:: + + integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) + year_int = integer.copy() + year_int.add_condition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later") + date_str = year_int + '/' + integer + '/' + integer + + result = date_str.parse_string("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), + (line:1, col:1) + """ + for fn in fns: + self.parseAction.append( + condition_as_parse_action( + fn, message=kwargs.get("message"), fatal=kwargs.get("fatal", False) + ) + ) + + self.callDuringTry = self.callDuringTry or kwargs.get( + "call_during_try", kwargs.get("callDuringTry", False) + ) + return self + + def set_fail_action(self, fn: ParseFailAction) -> "ParserElement": + """ + Define action to perform if parsing fails at this expression. + Fail acton fn is a callable function that takes the arguments + ``fn(s, loc, expr, err)`` where: + + - s = string being parsed + - loc = location where expression match was attempted and failed + - expr = the parse expression that failed + - err = the exception thrown + + The function returns no value. It may throw :class:`ParseFatalException` + if it is desired to stop parsing immediately.""" + self.failAction = fn + return self + + def _skipIgnorables(self, instring, loc): + exprsFound = True + while exprsFound: + exprsFound = False + for e in self.ignoreExprs: + try: + while 1: + loc, dummy = e._parse(instring, loc) + exprsFound = True + except ParseException: + pass + return loc + + def preParse(self, instring, loc): + if self.ignoreExprs: + loc = self._skipIgnorables(instring, loc) + + if self.skipWhitespace: + instrlen = len(instring) + white_chars = self.whiteChars + while loc < instrlen and instring[loc] in white_chars: + loc += 1 + + return loc + + def parseImpl(self, instring, loc, doActions=True): + return loc, [] + + def postParse(self, instring, loc, tokenlist): + return tokenlist + + # @profile + def _parseNoCache( + self, instring, loc, doActions=True, callPreParse=True + ) -> Tuple[int, ParseResults]: + TRY, MATCH, FAIL = 0, 1, 2 + debugging = self.debug # and doActions) + len_instring = len(instring) + + if debugging or self.failAction: + # print("Match {} at loc {}({}, {})".format(self, loc, lineno(loc, instring), col(loc, instring))) + try: + if callPreParse and self.callPreparse: + pre_loc = self.preParse(instring, loc) + else: + pre_loc = loc + tokens_start = pre_loc + if self.debugActions.debug_try: + self.debugActions.debug_try(instring, tokens_start, self, False) + if self.mayIndexError or pre_loc >= len_instring: + try: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + except IndexError: + raise ParseException(instring, len_instring, self.errmsg, self) + else: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + except Exception as err: + # print("Exception raised:", err) + if self.debugActions.debug_fail: + self.debugActions.debug_fail( + instring, tokens_start, self, err, False + ) + if self.failAction: + self.failAction(instring, tokens_start, self, err) + raise + else: + if callPreParse and self.callPreparse: + pre_loc = self.preParse(instring, loc) + else: + pre_loc = loc + tokens_start = pre_loc + if self.mayIndexError or pre_loc >= len_instring: + try: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + except IndexError: + raise ParseException(instring, len_instring, self.errmsg, self) + else: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + + tokens = self.postParse(instring, loc, tokens) + + ret_tokens = ParseResults( + tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults + ) + if self.parseAction and (doActions or self.callDuringTry): + if debugging: + try: + for fn in self.parseAction: + try: + tokens = fn(instring, tokens_start, ret_tokens) + except IndexError as parse_action_exc: + exc = ParseException("exception raised in parse action") + raise exc from parse_action_exc + + if tokens is not None and tokens is not ret_tokens: + ret_tokens = ParseResults( + tokens, + self.resultsName, + asList=self.saveAsList + and isinstance(tokens, (ParseResults, list)), + modal=self.modalResults, + ) + except Exception as err: + # print "Exception raised in user parse action:", err + if self.debugActions.debug_fail: + self.debugActions.debug_fail( + instring, tokens_start, self, err, False + ) + raise + else: + for fn in self.parseAction: + try: + tokens = fn(instring, tokens_start, ret_tokens) + except IndexError as parse_action_exc: + exc = ParseException("exception raised in parse action") + raise exc from parse_action_exc + + if tokens is not None and tokens is not ret_tokens: + ret_tokens = ParseResults( + tokens, + self.resultsName, + asList=self.saveAsList + and isinstance(tokens, (ParseResults, list)), + modal=self.modalResults, + ) + if debugging: + # print("Matched", self, "->", ret_tokens.as_list()) + if self.debugActions.debug_match: + self.debugActions.debug_match( + instring, tokens_start, loc, self, ret_tokens, False + ) + + return loc, ret_tokens + + def try_parse(self, instring: str, loc: int, raise_fatal: bool = False) -> int: + try: + return self._parse(instring, loc, doActions=False)[0] + except ParseFatalException: + if raise_fatal: + raise + raise ParseException(instring, loc, self.errmsg, self) + + def can_parse_next(self, instring: str, loc: int) -> bool: + try: + self.try_parse(instring, loc) + except (ParseException, IndexError): + return False + else: + return True + + # cache for left-recursion in Forward references + recursion_lock = RLock() + recursion_memos: typing.Dict[ + Tuple[int, "Forward", bool], Tuple[int, Union[ParseResults, Exception]] + ] = {} + + # argument cache for optimizing repeated calls when backtracking through recursive expressions + packrat_cache = ( + {} + ) # this is set later by enabled_packrat(); this is here so that reset_cache() doesn't fail + packrat_cache_lock = RLock() + packrat_cache_stats = [0, 0] + + # this method gets repeatedly called during backtracking with the same arguments - + # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression + def _parseCache( + self, instring, loc, doActions=True, callPreParse=True + ) -> Tuple[int, ParseResults]: + HIT, MISS = 0, 1 + TRY, MATCH, FAIL = 0, 1, 2 + lookup = (self, instring, loc, callPreParse, doActions) + with ParserElement.packrat_cache_lock: + cache = ParserElement.packrat_cache + value = cache.get(lookup) + if value is cache.not_in_cache: + ParserElement.packrat_cache_stats[MISS] += 1 + try: + value = self._parseNoCache(instring, loc, doActions, callPreParse) + except ParseBaseException as pe: + # cache a copy of the exception, without the traceback + cache.set(lookup, pe.__class__(*pe.args)) + raise + else: + cache.set(lookup, (value[0], value[1].copy(), loc)) + return value + else: + ParserElement.packrat_cache_stats[HIT] += 1 + if self.debug and self.debugActions.debug_try: + try: + self.debugActions.debug_try(instring, loc, self, cache_hit=True) + except TypeError: + pass + if isinstance(value, Exception): + if self.debug and self.debugActions.debug_fail: + try: + self.debugActions.debug_fail( + instring, loc, self, value, cache_hit=True + ) + except TypeError: + pass + raise value + + loc_, result, endloc = value[0], value[1].copy(), value[2] + if self.debug and self.debugActions.debug_match: + try: + self.debugActions.debug_match( + instring, loc_, endloc, self, result, cache_hit=True + ) + except TypeError: + pass + + return loc_, result + + _parse = _parseNoCache + + @staticmethod + def reset_cache() -> None: + ParserElement.packrat_cache.clear() + ParserElement.packrat_cache_stats[:] = [0] * len( + ParserElement.packrat_cache_stats + ) + ParserElement.recursion_memos.clear() + + _packratEnabled = False + _left_recursion_enabled = False + + @staticmethod + def disable_memoization() -> None: + """ + Disables active Packrat or Left Recursion parsing and their memoization + + This method also works if neither Packrat nor Left Recursion are enabled. + This makes it safe to call before activating Packrat nor Left Recursion + to clear any previous settings. + """ + ParserElement.reset_cache() + ParserElement._left_recursion_enabled = False + ParserElement._packratEnabled = False + ParserElement._parse = ParserElement._parseNoCache + + @staticmethod + def enable_left_recursion( + cache_size_limit: typing.Optional[int] = None, *, force=False + ) -> None: + """ + Enables "bounded recursion" parsing, which allows for both direct and indirect + left-recursion. During parsing, left-recursive :class:`Forward` elements are + repeatedly matched with a fixed recursion depth that is gradually increased + until finding the longest match. + + Example:: + + import pyparsing as pp + pp.ParserElement.enable_left_recursion() + + E = pp.Forward("E") + num = pp.Word(pp.nums) + # match `num`, or `num '+' num`, or `num '+' num '+' num`, ... + E <<= E + '+' - num | num + + print(E.parse_string("1+2+3")) + + Recursion search naturally memoizes matches of ``Forward`` elements and may + thus skip reevaluation of parse actions during backtracking. This may break + programs with parse actions which rely on strict ordering of side-effects. + + Parameters: + + - cache_size_limit - (default=``None``) - memoize at most this many + ``Forward`` elements during matching; if ``None`` (the default), + memoize all ``Forward`` elements. + + Bounded Recursion parsing works similar but not identical to Packrat parsing, + thus the two cannot be used together. Use ``force=True`` to disable any + previous, conflicting settings. + """ + if force: + ParserElement.disable_memoization() + elif ParserElement._packratEnabled: + raise RuntimeError("Packrat and Bounded Recursion are not compatible") + if cache_size_limit is None: + ParserElement.recursion_memos = _UnboundedMemo() + elif cache_size_limit > 0: + ParserElement.recursion_memos = _LRUMemo(capacity=cache_size_limit) + else: + raise NotImplementedError("Memo size of %s" % cache_size_limit) + ParserElement._left_recursion_enabled = True + + @staticmethod + def enable_packrat(cache_size_limit: int = 128, *, force: bool = False) -> None: + """ + Enables "packrat" parsing, which adds memoizing to the parsing logic. + Repeated parse attempts at the same string location (which happens + often in many complex grammars) can immediately return a cached value, + instead of re-executing parsing/validating code. Memoizing is done of + both valid results and parsing exceptions. + + Parameters: + + - cache_size_limit - (default= ``128``) - if an integer value is provided + will limit the size of the packrat cache; if None is passed, then + the cache size will be unbounded; if 0 is passed, the cache will + be effectively disabled. + + This speedup may break existing programs that use parse actions that + have side-effects. For this reason, packrat parsing is disabled when + you first import pyparsing. To activate the packrat feature, your + program must call the class method :class:`ParserElement.enable_packrat`. + For best results, call ``enable_packrat()`` immediately after + importing pyparsing. + + Example:: + + import pyparsing + pyparsing.ParserElement.enable_packrat() + + Packrat parsing works similar but not identical to Bounded Recursion parsing, + thus the two cannot be used together. Use ``force=True`` to disable any + previous, conflicting settings. + """ + if force: + ParserElement.disable_memoization() + elif ParserElement._left_recursion_enabled: + raise RuntimeError("Packrat and Bounded Recursion are not compatible") + if not ParserElement._packratEnabled: + ParserElement._packratEnabled = True + if cache_size_limit is None: + ParserElement.packrat_cache = _UnboundedCache() + else: + ParserElement.packrat_cache = _FifoCache(cache_size_limit) + ParserElement._parse = ParserElement._parseCache + + def parse_string( + self, instring: str, parse_all: bool = False, *, parseAll: bool = False + ) -> ParseResults: + """ + Parse a string with respect to the parser definition. This function is intended as the primary interface to the + client code. + + :param instring: The input string to be parsed. + :param parse_all: If set, the entire input string must match the grammar. + :param parseAll: retained for pre-PEP8 compatibility, will be removed in a future release. + :raises ParseException: Raised if ``parse_all`` is set and the input string does not match the whole grammar. + :returns: the parsed data as a :class:`ParseResults` object, which may be accessed as a `list`, a `dict`, or + an object with attributes if the given parser includes results names. + + If the input string is required to match the entire grammar, ``parse_all`` flag must be set to ``True``. This + is also equivalent to ending the grammar with :class:`StringEnd`(). + + To report proper column numbers, ``parse_string`` operates on a copy of the input string where all tabs are + converted to spaces (8 spaces per tab, as per the default in ``string.expandtabs``). If the input string + contains tabs and the grammar uses parse actions that use the ``loc`` argument to index into the string + being parsed, one can ensure a consistent view of the input string by doing one of the following: + + - calling ``parse_with_tabs`` on your grammar before calling ``parse_string`` (see :class:`parse_with_tabs`), + - define your parse action using the full ``(s,loc,toks)`` signature, and reference the input string using the + parse action's ``s`` argument, or + - explicitly expand the tabs in your input string before calling ``parse_string``. + + Examples: + + By default, partial matches are OK. + + >>> res = Word('a').parse_string('aaaaabaaa') + >>> print(res) + ['aaaaa'] + + The parsing behavior varies by the inheriting class of this abstract class. Please refer to the children + directly to see more examples. + + It raises an exception if parse_all flag is set and instring does not match the whole grammar. + + >>> res = Word('a').parse_string('aaaaabaaa', parse_all=True) + Traceback (most recent call last): + ... + pyparsing.ParseException: Expected end of text, found 'b' (at char 5), (line:1, col:6) + """ + parseAll = parse_all or parseAll + + ParserElement.reset_cache() + if not self.streamlined: + self.streamline() + for e in self.ignoreExprs: + e.streamline() + if not self.keepTabs: + instring = instring.expandtabs() + try: + loc, tokens = self._parse(instring, 0) + if parseAll: + loc = self.preParse(instring, loc) + se = Empty() + StringEnd() + se._parse(instring, loc) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clearing out pyparsing internal stack trace + raise exc.with_traceback(None) + else: + return tokens + + def scan_string( + self, + instring: str, + max_matches: int = _MAX_INT, + overlap: bool = False, + *, + debug: bool = False, + maxMatches: int = _MAX_INT, + ) -> Generator[Tuple[ParseResults, int, int], None, None]: + """ + Scan the input string for expression matches. Each match will return the + matching tokens, start location, and end location. May be called with optional + ``max_matches`` argument, to clip scanning after 'n' matches are found. If + ``overlap`` is specified, then overlapping matches will be reported. + + Note that the start and end locations are reported relative to the string + being parsed. See :class:`parse_string` for more information on parsing + strings with embedded tabs. + + Example:: + + source = "sldjf123lsdjjkf345sldkjf879lkjsfd987" + print(source) + for tokens, start, end in Word(alphas).scan_string(source): + print(' '*start + '^'*(end-start)) + print(' '*start + tokens[0]) + + prints:: + + sldjf123lsdjjkf345sldkjf879lkjsfd987 + ^^^^^ + sldjf + ^^^^^^^ + lsdjjkf + ^^^^^^ + sldkjf + ^^^^^^ + lkjsfd + """ + maxMatches = min(maxMatches, max_matches) + if not self.streamlined: + self.streamline() + for e in self.ignoreExprs: + e.streamline() + + if not self.keepTabs: + instring = str(instring).expandtabs() + instrlen = len(instring) + loc = 0 + preparseFn = self.preParse + parseFn = self._parse + ParserElement.resetCache() + matches = 0 + try: + while loc <= instrlen and matches < maxMatches: + try: + preloc = preparseFn(instring, loc) + nextLoc, tokens = parseFn(instring, preloc, callPreParse=False) + except ParseException: + loc = preloc + 1 + else: + if nextLoc > loc: + matches += 1 + if debug: + print( + { + "tokens": tokens.asList(), + "start": preloc, + "end": nextLoc, + } + ) + yield tokens, preloc, nextLoc + if overlap: + nextloc = preparseFn(instring, loc) + if nextloc > loc: + loc = nextLoc + else: + loc += 1 + else: + loc = nextLoc + else: + loc = preloc + 1 + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def transform_string(self, instring: str, *, debug: bool = False) -> str: + """ + Extension to :class:`scan_string`, to modify matching text with modified tokens that may + be returned from a parse action. To use ``transform_string``, define a grammar and + attach a parse action to it that modifies the returned token list. + Invoking ``transform_string()`` on a target string will then scan for matches, + and replace the matched text patterns according to the logic in the parse + action. ``transform_string()`` returns the resulting transformed string. + + Example:: + + wd = Word(alphas) + wd.set_parse_action(lambda toks: toks[0].title()) + + print(wd.transform_string("now is the winter of our discontent made glorious summer by this sun of york.")) + + prints:: + + Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York. + """ + out: List[str] = [] + lastE = 0 + # force preservation of <TAB>s, to minimize unwanted transformation of string, and to + # keep string locs straight between transform_string and scan_string + self.keepTabs = True + try: + for t, s, e in self.scan_string(instring, debug=debug): + out.append(instring[lastE:s]) + if t: + if isinstance(t, ParseResults): + out += t.as_list() + elif isinstance(t, Iterable) and not isinstance(t, str_type): + out.extend(t) + else: + out.append(t) + lastE = e + out.append(instring[lastE:]) + out = [o for o in out if o] + return "".join([str(s) for s in _flatten(out)]) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def search_string( + self, + instring: str, + max_matches: int = _MAX_INT, + *, + debug: bool = False, + maxMatches: int = _MAX_INT, + ) -> ParseResults: + """ + Another extension to :class:`scan_string`, simplifying the access to the tokens found + to match the given parse expression. May be called with optional + ``max_matches`` argument, to clip searching after 'n' matches are found. + + Example:: + + # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters + cap_word = Word(alphas.upper(), alphas.lower()) + + print(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity")) + + # the sum() builtin can be used to merge results into a single ParseResults object + print(sum(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity"))) + + prints:: + + [['More'], ['Iron'], ['Lead'], ['Gold'], ['I'], ['Electricity']] + ['More', 'Iron', 'Lead', 'Gold', 'I', 'Electricity'] + """ + maxMatches = min(maxMatches, max_matches) + try: + return ParseResults( + [t for t, s, e in self.scan_string(instring, maxMatches, debug=debug)] + ) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def split( + self, + instring: str, + maxsplit: int = _MAX_INT, + include_separators: bool = False, + *, + includeSeparators=False, + ) -> Generator[str, None, None]: + """ + Generator method to split a string using the given expression as a separator. + May be called with optional ``maxsplit`` argument, to limit the number of splits; + and the optional ``include_separators`` argument (default= ``False``), if the separating + matching text should be included in the split results. + + Example:: + + punc = one_of(list(".,;:/-!?")) + print(list(punc.split("This, this?, this sentence, is badly punctuated!"))) + + prints:: + + ['This', ' this', '', ' this sentence', ' is badly punctuated', ''] + """ + includeSeparators = includeSeparators or include_separators + last = 0 + for t, s, e in self.scan_string(instring, max_matches=maxsplit): + yield instring[last:s] + if includeSeparators: + yield t[0] + last = e + yield instring[last:] + + def __add__(self, other) -> "ParserElement": + """ + Implementation of ``+`` operator - returns :class:`And`. Adding strings to a :class:`ParserElement` + converts them to :class:`Literal`s by default. + + Example:: + + greet = Word(alphas) + "," + Word(alphas) + "!" + hello = "Hello, World!" + print(hello, "->", greet.parse_string(hello)) + + prints:: + + Hello, World! -> ['Hello', ',', 'World', '!'] + + ``...`` may be used as a parse expression as a short form of :class:`SkipTo`. + + Literal('start') + ... + Literal('end') + + is equivalent to: + + Literal('start') + SkipTo('end')("_skipped*") + Literal('end') + + Note that the skipped text is returned with '_skipped' as a results name, + and to support having multiple skips in the same parser, the value returned is + a list of all skipped text. + """ + if other is Ellipsis: + return _PendingSkip(self) + + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return And([self, other]) + + def __radd__(self, other) -> "ParserElement": + """ + Implementation of ``+`` operator when left operand is not a :class:`ParserElement` + """ + if other is Ellipsis: + return SkipTo(self)("_skipped*") + self + + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other + self + + def __sub__(self, other) -> "ParserElement": + """ + Implementation of ``-`` operator, returns :class:`And` with error stop + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return self + And._ErrorStop() + other + + def __rsub__(self, other) -> "ParserElement": + """ + Implementation of ``-`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other - self + + def __mul__(self, other) -> "ParserElement": + """ + Implementation of ``*`` operator, allows use of ``expr * 3`` in place of + ``expr + expr + expr``. Expressions may also be multiplied by a 2-integer + tuple, similar to ``{min, max}`` multipliers in regular expressions. Tuples + may also include ``None`` as in: + - ``expr*(n, None)`` or ``expr*(n, )`` is equivalent + to ``expr*n + ZeroOrMore(expr)`` + (read as "at least n instances of ``expr``") + - ``expr*(None, n)`` is equivalent to ``expr*(0, n)`` + (read as "0 to n instances of ``expr``") + - ``expr*(None, None)`` is equivalent to ``ZeroOrMore(expr)`` + - ``expr*(1, None)`` is equivalent to ``OneOrMore(expr)`` + + Note that ``expr*(None, n)`` does not raise an exception if + more than n exprs exist in the input stream; that is, + ``expr*(None, n)`` does not enforce a maximum number of expr + occurrences. If this behavior is desired, then write + ``expr*(None, n) + ~expr`` + """ + if other is Ellipsis: + other = (0, None) + elif isinstance(other, tuple) and other[:1] == (Ellipsis,): + other = ((0,) + other[1:] + (None,))[:2] + + if isinstance(other, int): + minElements, optElements = other, 0 + elif isinstance(other, tuple): + other = tuple(o if o is not Ellipsis else None for o in other) + other = (other + (None, None))[:2] + if other[0] is None: + other = (0, other[1]) + if isinstance(other[0], int) and other[1] is None: + if other[0] == 0: + return ZeroOrMore(self) + if other[0] == 1: + return OneOrMore(self) + else: + return self * other[0] + ZeroOrMore(self) + elif isinstance(other[0], int) and isinstance(other[1], int): + minElements, optElements = other + optElements -= minElements + else: + raise TypeError( + "cannot multiply ParserElement and ({}) objects".format( + ",".join(type(item).__name__ for item in other) + ) + ) + else: + raise TypeError( + "cannot multiply ParserElement and {} objects".format( + type(other).__name__ + ) + ) + + if minElements < 0: + raise ValueError("cannot multiply ParserElement by negative value") + if optElements < 0: + raise ValueError( + "second tuple value must be greater or equal to first tuple value" + ) + if minElements == optElements == 0: + return And([]) + + if optElements: + + def makeOptionalList(n): + if n > 1: + return Opt(self + makeOptionalList(n - 1)) + else: + return Opt(self) + + if minElements: + if minElements == 1: + ret = self + makeOptionalList(optElements) + else: + ret = And([self] * minElements) + makeOptionalList(optElements) + else: + ret = makeOptionalList(optElements) + else: + if minElements == 1: + ret = self + else: + ret = And([self] * minElements) + return ret + + def __rmul__(self, other) -> "ParserElement": + return self.__mul__(other) + + def __or__(self, other) -> "ParserElement": + """ + Implementation of ``|`` operator - returns :class:`MatchFirst` + """ + if other is Ellipsis: + return _PendingSkip(self, must_skip=True) + + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return MatchFirst([self, other]) + + def __ror__(self, other) -> "ParserElement": + """ + Implementation of ``|`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other | self + + def __xor__(self, other) -> "ParserElement": + """ + Implementation of ``^`` operator - returns :class:`Or` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return Or([self, other]) + + def __rxor__(self, other) -> "ParserElement": + """ + Implementation of ``^`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other ^ self + + def __and__(self, other) -> "ParserElement": + """ + Implementation of ``&`` operator - returns :class:`Each` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return Each([self, other]) + + def __rand__(self, other) -> "ParserElement": + """ + Implementation of ``&`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other & self + + def __invert__(self) -> "ParserElement": + """ + Implementation of ``~`` operator - returns :class:`NotAny` + """ + return NotAny(self) + + # disable __iter__ to override legacy use of sequential access to __getitem__ to + # iterate over a sequence + __iter__ = None + + def __getitem__(self, key): + """ + use ``[]`` indexing notation as a short form for expression repetition: + + - ``expr[n]`` is equivalent to ``expr*n`` + - ``expr[m, n]`` is equivalent to ``expr*(m, n)`` + - ``expr[n, ...]`` or ``expr[n,]`` is equivalent + to ``expr*n + ZeroOrMore(expr)`` + (read as "at least n instances of ``expr``") + - ``expr[..., n]`` is equivalent to ``expr*(0, n)`` + (read as "0 to n instances of ``expr``") + - ``expr[...]`` and ``expr[0, ...]`` are equivalent to ``ZeroOrMore(expr)`` + - ``expr[1, ...]`` is equivalent to ``OneOrMore(expr)`` + + ``None`` may be used in place of ``...``. + + Note that ``expr[..., n]`` and ``expr[m, n]``do not raise an exception + if more than ``n`` ``expr``s exist in the input stream. If this behavior is + desired, then write ``expr[..., n] + ~expr``. + """ + + # convert single arg keys to tuples + try: + if isinstance(key, str_type): + key = (key,) + iter(key) + except TypeError: + key = (key, key) + + if len(key) > 2: + raise TypeError( + "only 1 or 2 index arguments supported ({}{})".format( + key[:5], "... [{}]".format(len(key)) if len(key) > 5 else "" + ) + ) + + # clip to 2 elements + ret = self * tuple(key[:2]) + return ret + + def __call__(self, name: str = None) -> "ParserElement": + """ + Shortcut for :class:`set_results_name`, with ``list_all_matches=False``. + + If ``name`` is given with a trailing ``'*'`` character, then ``list_all_matches`` will be + passed as ``True``. + + If ``name` is omitted, same as calling :class:`copy`. + + Example:: + + # these are equivalent + userdata = Word(alphas).set_results_name("name") + Word(nums + "-").set_results_name("socsecno") + userdata = Word(alphas)("name") + Word(nums + "-")("socsecno") + """ + if name is not None: + return self._setResultsName(name) + else: + return self.copy() + + def suppress(self) -> "ParserElement": + """ + Suppresses the output of this :class:`ParserElement`; useful to keep punctuation from + cluttering up returned output. + """ + return Suppress(self) + + def ignore_whitespace(self, recursive: bool = True) -> "ParserElement": + """ + Enables the skipping of whitespace before matching the characters in the + :class:`ParserElement`'s defined pattern. + + :param recursive: If ``True`` (the default), also enable whitespace skipping in child elements (if any) + """ + self.skipWhitespace = True + return self + + def leave_whitespace(self, recursive: bool = True) -> "ParserElement": + """ + Disables the skipping of whitespace before matching the characters in the + :class:`ParserElement`'s defined pattern. This is normally only used internally by + the pyparsing module, but may be needed in some whitespace-sensitive grammars. + + :param recursive: If true (the default), also disable whitespace skipping in child elements (if any) + """ + self.skipWhitespace = False + return self + + def set_whitespace_chars( + self, chars: Union[Set[str], str], copy_defaults: bool = False + ) -> "ParserElement": + """ + Overrides the default whitespace chars + """ + self.skipWhitespace = True + self.whiteChars = set(chars) + self.copyDefaultWhiteChars = copy_defaults + return self + + def parse_with_tabs(self) -> "ParserElement": + """ + Overrides default behavior to expand ``<TAB>`` s to spaces before parsing the input string. + Must be called before ``parse_string`` when the input grammar contains elements that + match ``<TAB>`` characters. + """ + self.keepTabs = True + return self + + def ignore(self, other: "ParserElement") -> "ParserElement": + """ + Define expression to be ignored (e.g., comments) while doing pattern + matching; may be called repeatedly, to define multiple comment or other + ignorable patterns. + + Example:: + + patt = Word(alphas)[1, ...] + patt.parse_string('ablaj /* comment */ lskjd') + # -> ['ablaj'] + + patt.ignore(c_style_comment) + patt.parse_string('ablaj /* comment */ lskjd') + # -> ['ablaj', 'lskjd'] + """ + import typing + + if isinstance(other, str_type): + other = Suppress(other) + + if isinstance(other, Suppress): + if other not in self.ignoreExprs: + self.ignoreExprs.append(other) + else: + self.ignoreExprs.append(Suppress(other.copy())) + return self + + def set_debug_actions( + self, + start_action: DebugStartAction, + success_action: DebugSuccessAction, + exception_action: DebugExceptionAction, + ) -> "ParserElement": + """ + Customize display of debugging messages while doing pattern matching: + + - ``start_action`` - method to be called when an expression is about to be parsed; + should have the signature ``fn(input_string: str, location: int, expression: ParserElement, cache_hit: bool)`` + + - ``success_action`` - method to be called when an expression has successfully parsed; + should have the signature ``fn(input_string: str, start_location: int, end_location: int, expression: ParserELement, parsed_tokens: ParseResults, cache_hit: bool)`` + + - ``exception_action`` - method to be called when expression fails to parse; + should have the signature ``fn(input_string: str, location: int, expression: ParserElement, exception: Exception, cache_hit: bool)`` + """ + self.debugActions = self.DebugActions( + start_action or _default_start_debug_action, + success_action or _default_success_debug_action, + exception_action or _default_exception_debug_action, + ) + self.debug = True + return self + + def set_debug(self, flag: bool = True) -> "ParserElement": + """ + Enable display of debugging messages while doing pattern matching. + Set ``flag`` to ``True`` to enable, ``False`` to disable. + + Example:: + + wd = Word(alphas).set_name("alphaword") + integer = Word(nums).set_name("numword") + term = wd | integer + + # turn on debugging for wd + wd.set_debug() + + term[1, ...].parse_string("abc 123 xyz 890") + + prints:: + + Match alphaword at loc 0(1,1) + Matched alphaword -> ['abc'] + Match alphaword at loc 3(1,4) + Exception raised:Expected alphaword (at char 4), (line:1, col:5) + Match alphaword at loc 7(1,8) + Matched alphaword -> ['xyz'] + Match alphaword at loc 11(1,12) + Exception raised:Expected alphaword (at char 12), (line:1, col:13) + Match alphaword at loc 15(1,16) + Exception raised:Expected alphaword (at char 15), (line:1, col:16) + + The output shown is that produced by the default debug actions - custom debug actions can be + specified using :class:`set_debug_actions`. Prior to attempting + to match the ``wd`` expression, the debugging message ``"Match <exprname> at loc <n>(<line>,<col>)"`` + is shown. Then if the parse succeeds, a ``"Matched"`` message is shown, or an ``"Exception raised"`` + message is shown. Also note the use of :class:`set_name` to assign a human-readable name to the expression, + which makes debugging and exception messages easier to understand - for instance, the default + name created for the :class:`Word` expression without calling ``set_name`` is ``"W:(A-Za-z)"``. + """ + if flag: + self.set_debug_actions( + _default_start_debug_action, + _default_success_debug_action, + _default_exception_debug_action, + ) + else: + self.debug = False + return self + + @property + def default_name(self) -> str: + if self._defaultName is None: + self._defaultName = self._generateDefaultName() + return self._defaultName + + @abstractmethod + def _generateDefaultName(self): + """ + Child classes must define this method, which defines how the ``default_name`` is set. + """ + + def set_name(self, name: str) -> "ParserElement": + """ + Define name for this expression, makes debugging and exception messages clearer. + Example:: + Word(nums).parse_string("ABC") # -> Exception: Expected W:(0-9) (at char 0), (line:1, col:1) + Word(nums).set_name("integer").parse_string("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1) + """ + self.customName = name + self.errmsg = "Expected " + self.name + if __diag__.enable_debug_on_named_expressions: + self.set_debug() + return self + + @property + def name(self) -> str: + # This will use a user-defined name if available, but otherwise defaults back to the auto-generated name + return self.customName if self.customName is not None else self.default_name + + def __str__(self) -> str: + return self.name + + def __repr__(self) -> str: + return str(self) + + def streamline(self) -> "ParserElement": + self.streamlined = True + self._defaultName = None + return self + + def recurse(self) -> Sequence["ParserElement"]: + return [] + + def _checkRecursion(self, parseElementList): + subRecCheckList = parseElementList[:] + [self] + for e in self.recurse(): + e._checkRecursion(subRecCheckList) + + def validate(self, validateTrace=None) -> None: + """ + Check defined expressions for valid structure, check for infinite recursive definitions. + """ + self._checkRecursion([]) + + def parse_file( + self, + file_or_filename: Union[str, Path, TextIO], + encoding: str = "utf-8", + parse_all: bool = False, + *, + parseAll: bool = False, + ) -> ParseResults: + """ + Execute the parse expression on the given file or filename. + If a filename is specified (instead of a file object), + the entire file is opened, read, and closed before parsing. + """ + parseAll = parseAll or parse_all + try: + file_contents = file_or_filename.read() + except AttributeError: + with open(file_or_filename, "r", encoding=encoding) as f: + file_contents = f.read() + try: + return self.parse_string(file_contents, parseAll) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def __eq__(self, other): + if self is other: + return True + elif isinstance(other, str_type): + return self.matches(other, parse_all=True) + elif isinstance(other, ParserElement): + return vars(self) == vars(other) + return False + + def __hash__(self): + return id(self) + + def matches( + self, test_string: str, parse_all: bool = True, *, parseAll: bool = True + ) -> bool: + """ + Method for quick testing of a parser against a test string. Good for simple + inline microtests of sub expressions while building up larger parser. + + Parameters: + - ``test_string`` - to test against this expression for a match + - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests + + Example:: + + expr = Word(nums) + assert expr.matches("100") + """ + parseAll = parseAll and parse_all + try: + self.parse_string(str(test_string), parse_all=parseAll) + return True + except ParseBaseException: + return False + + def run_tests( + self, + tests: Union[str, List[str]], + parse_all: bool = True, + comment: typing.Optional[Union["ParserElement", str]] = "#", + full_dump: bool = True, + print_results: bool = True, + failure_tests: bool = False, + post_parse: Callable[[str, ParseResults], str] = None, + file: typing.Optional[TextIO] = None, + with_line_numbers: bool = False, + *, + parseAll: bool = True, + fullDump: bool = True, + printResults: bool = True, + failureTests: bool = False, + postParse: Callable[[str, ParseResults], str] = None, + ) -> Tuple[bool, List[Tuple[str, Union[ParseResults, Exception]]]]: + """ + Execute the parse expression on a series of test strings, showing each + test, the parsed results or where the parse failed. Quick and easy way to + run a parse expression against a list of sample strings. + + Parameters: + - ``tests`` - a list of separate test strings, or a multiline string of test strings + - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests + - ``comment`` - (default= ``'#'``) - expression for indicating embedded comments in the test + string; pass None to disable comment filtering + - ``full_dump`` - (default= ``True``) - dump results as list followed by results names in nested outline; + if False, only dump nested list + - ``print_results`` - (default= ``True``) prints test output to stdout + - ``failure_tests`` - (default= ``False``) indicates if these tests are expected to fail parsing + - ``post_parse`` - (default= ``None``) optional callback for successful parse results; called as + `fn(test_string, parse_results)` and returns a string to be added to the test output + - ``file`` - (default= ``None``) optional file-like object to which test output will be written; + if None, will default to ``sys.stdout`` + - ``with_line_numbers`` - default= ``False``) show test strings with line and column numbers + + Returns: a (success, results) tuple, where success indicates that all tests succeeded + (or failed if ``failure_tests`` is True), and the results contain a list of lines of each + test's output + + Example:: + + number_expr = pyparsing_common.number.copy() + + result = number_expr.run_tests(''' + # unsigned integer + 100 + # negative integer + -100 + # float with scientific notation + 6.02e23 + # integer with scientific notation + 1e-12 + ''') + print("Success" if result[0] else "Failed!") + + result = number_expr.run_tests(''' + # stray character + 100Z + # missing leading digit before '.' + -.100 + # too many '.' + 3.14.159 + ''', failure_tests=True) + print("Success" if result[0] else "Failed!") + + prints:: + + # unsigned integer + 100 + [100] + + # negative integer + -100 + [-100] + + # float with scientific notation + 6.02e23 + [6.02e+23] + + # integer with scientific notation + 1e-12 + [1e-12] + + Success + + # stray character + 100Z + ^ + FAIL: Expected end of text (at char 3), (line:1, col:4) + + # missing leading digit before '.' + -.100 + ^ + FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1) + + # too many '.' + 3.14.159 + ^ + FAIL: Expected end of text (at char 4), (line:1, col:5) + + Success + + Each test string must be on a single line. If you want to test a string that spans multiple + lines, create a test like this:: + + expr.run_tests(r"this is a test\\n of strings that spans \\n 3 lines") + + (Note that this is a raw string literal, you must include the leading ``'r'``.) + """ + from .testing import pyparsing_test + + parseAll = parseAll and parse_all + fullDump = fullDump and full_dump + printResults = printResults and print_results + failureTests = failureTests or failure_tests + postParse = postParse or post_parse + if isinstance(tests, str_type): + line_strip = type(tests).strip + tests = [line_strip(test_line) for test_line in tests.rstrip().splitlines()] + if isinstance(comment, str_type): + comment = Literal(comment) + if file is None: + file = sys.stdout + print_ = file.write + + result: Union[ParseResults, Exception] + allResults = [] + comments = [] + success = True + NL = Literal(r"\n").add_parse_action(replace_with("\n")).ignore(quoted_string) + BOM = "\ufeff" + for t in tests: + if comment is not None and comment.matches(t, False) or comments and not t: + comments.append( + pyparsing_test.with_line_numbers(t) if with_line_numbers else t + ) + continue + if not t: + continue + out = [ + "\n" + "\n".join(comments) if comments else "", + pyparsing_test.with_line_numbers(t) if with_line_numbers else t, + ] + comments = [] + try: + # convert newline marks to actual newlines, and strip leading BOM if present + t = NL.transform_string(t.lstrip(BOM)) + result = self.parse_string(t, parse_all=parseAll) + except ParseBaseException as pe: + fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else "" + out.append(pe.explain()) + out.append("FAIL: " + str(pe)) + if ParserElement.verbose_stacktrace: + out.extend(traceback.format_tb(pe.__traceback__)) + success = success and failureTests + result = pe + except Exception as exc: + out.append("FAIL-EXCEPTION: {}: {}".format(type(exc).__name__, exc)) + if ParserElement.verbose_stacktrace: + out.extend(traceback.format_tb(exc.__traceback__)) + success = success and failureTests + result = exc + else: + success = success and not failureTests + if postParse is not None: + try: + pp_value = postParse(t, result) + if pp_value is not None: + if isinstance(pp_value, ParseResults): + out.append(pp_value.dump()) + else: + out.append(str(pp_value)) + else: + out.append(result.dump()) + except Exception as e: + out.append(result.dump(full=fullDump)) + out.append( + "{} failed: {}: {}".format( + postParse.__name__, type(e).__name__, e + ) + ) + else: + out.append(result.dump(full=fullDump)) + out.append("") + + if printResults: + print_("\n".join(out)) + + allResults.append((t, result)) + + return success, allResults + + def create_diagram( + self, + output_html: Union[TextIO, Path, str], + vertical: int = 3, + show_results_names: bool = False, + show_groups: bool = False, + **kwargs, + ) -> None: + """ + Create a railroad diagram for the parser. + + Parameters: + - output_html (str or file-like object) - output target for generated + diagram HTML + - vertical (int) - threshold for formatting multiple alternatives vertically + instead of horizontally (default=3) + - show_results_names - bool flag whether diagram should show annotations for + defined results names + - show_groups - bool flag whether groups should be highlighted with an unlabeled surrounding box + Additional diagram-formatting keyword arguments can also be included; + see railroad.Diagram class. + """ + + try: + from .diagram import to_railroad, railroad_to_html + except ImportError as ie: + raise Exception( + "must ``pip install pyparsing[diagrams]`` to generate parser railroad diagrams" + ) from ie + + self.streamline() + + railroad = to_railroad( + self, + vertical=vertical, + show_results_names=show_results_names, + show_groups=show_groups, + diagram_kwargs=kwargs, + ) + if isinstance(output_html, (str, Path)): + with open(output_html, "w", encoding="utf-8") as diag_file: + diag_file.write(railroad_to_html(railroad)) + else: + # we were passed a file-like object, just write to it + output_html.write(railroad_to_html(railroad)) + + setDefaultWhitespaceChars = set_default_whitespace_chars + inlineLiteralsUsing = inline_literals_using + setResultsName = set_results_name + setBreak = set_break + setParseAction = set_parse_action + addParseAction = add_parse_action + addCondition = add_condition + setFailAction = set_fail_action + tryParse = try_parse + canParseNext = can_parse_next + resetCache = reset_cache + enableLeftRecursion = enable_left_recursion + enablePackrat = enable_packrat + parseString = parse_string + scanString = scan_string + searchString = search_string + transformString = transform_string + setWhitespaceChars = set_whitespace_chars + parseWithTabs = parse_with_tabs + setDebugActions = set_debug_actions + setDebug = set_debug + defaultName = default_name + setName = set_name + parseFile = parse_file + runTests = run_tests + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class _PendingSkip(ParserElement): + # internal placeholder class to hold a place were '...' is added to a parser element, + # once another ParserElement is added, this placeholder will be replaced with a SkipTo + def __init__(self, expr: ParserElement, must_skip: bool = False): + super().__init__() + self.anchor = expr + self.must_skip = must_skip + + def _generateDefaultName(self): + return str(self.anchor + Empty()).replace("Empty", "...") + + def __add__(self, other) -> "ParserElement": + skipper = SkipTo(other).set_name("...")("_skipped*") + if self.must_skip: + + def must_skip(t): + if not t._skipped or t._skipped.as_list() == [""]: + del t[0] + t.pop("_skipped", None) + + def show_skip(t): + if t._skipped.as_list()[-1:] == [""]: + t.pop("_skipped") + t["_skipped"] = "missing <" + repr(self.anchor) + ">" + + return ( + self.anchor + skipper().add_parse_action(must_skip) + | skipper().add_parse_action(show_skip) + ) + other + + return self.anchor + skipper + other + + def __repr__(self): + return self.defaultName + + def parseImpl(self, *args): + raise Exception( + "use of `...` expression without following SkipTo target expression" + ) + + +class Token(ParserElement): + """Abstract :class:`ParserElement` subclass, for defining atomic + matching patterns. + """ + + def __init__(self): + super().__init__(savelist=False) + + def _generateDefaultName(self): + return type(self).__name__ + + +class Empty(Token): + """ + An empty token, will always match. + """ + + def __init__(self): + super().__init__() + self.mayReturnEmpty = True + self.mayIndexError = False + + +class NoMatch(Token): + """ + A token that will never match. + """ + + def __init__(self): + super().__init__() + self.mayReturnEmpty = True + self.mayIndexError = False + self.errmsg = "Unmatchable token" + + def parseImpl(self, instring, loc, doActions=True): + raise ParseException(instring, loc, self.errmsg, self) + + +class Literal(Token): + """ + Token to exactly match a specified string. + + Example:: + + Literal('blah').parse_string('blah') # -> ['blah'] + Literal('blah').parse_string('blahfooblah') # -> ['blah'] + Literal('blah').parse_string('bla') # -> Exception: Expected "blah" + + For case-insensitive matching, use :class:`CaselessLiteral`. + + For keyword matching (force word break before and after the matched string), + use :class:`Keyword` or :class:`CaselessKeyword`. + """ + + def __init__(self, match_string: str = "", *, matchString: str = ""): + super().__init__() + match_string = matchString or match_string + self.match = match_string + self.matchLen = len(match_string) + try: + self.firstMatchChar = match_string[0] + except IndexError: + raise ValueError("null string passed to Literal; use Empty() instead") + self.errmsg = "Expected " + self.name + self.mayReturnEmpty = False + self.mayIndexError = False + + # Performance tuning: modify __class__ to select + # a parseImpl optimized for single-character check + if self.matchLen == 1 and type(self) is Literal: + self.__class__ = _SingleCharLiteral + + def _generateDefaultName(self): + return repr(self.match) + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] == self.firstMatchChar and instring.startswith( + self.match, loc + ): + return loc + self.matchLen, self.match + raise ParseException(instring, loc, self.errmsg, self) + + +class _SingleCharLiteral(Literal): + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] == self.firstMatchChar: + return loc + 1, self.match + raise ParseException(instring, loc, self.errmsg, self) + + +ParserElement._literalStringClass = Literal + + +class Keyword(Token): + """ + Token to exactly match a specified string as a keyword, that is, + it must be immediately followed by a non-keyword character. Compare + with :class:`Literal`: + + - ``Literal("if")`` will match the leading ``'if'`` in + ``'ifAndOnlyIf'``. + - ``Keyword("if")`` will not; it will only match the leading + ``'if'`` in ``'if x=1'``, or ``'if(y==2)'`` + + Accepts two optional constructor arguments in addition to the + keyword string: + + - ``identChars`` is a string of characters that would be valid + identifier characters, defaulting to all alphanumerics + "_" and + "$" + - ``caseless`` allows case-insensitive matching, default is ``False``. + + Example:: + + Keyword("start").parse_string("start") # -> ['start'] + Keyword("start").parse_string("starting") # -> Exception + + For case-insensitive matching, use :class:`CaselessKeyword`. + """ + + DEFAULT_KEYWORD_CHARS = alphanums + "_$" + + def __init__( + self, + match_string: str = "", + ident_chars: typing.Optional[str] = None, + caseless: bool = False, + *, + matchString: str = "", + identChars: typing.Optional[str] = None, + ): + super().__init__() + identChars = identChars or ident_chars + if identChars is None: + identChars = Keyword.DEFAULT_KEYWORD_CHARS + match_string = matchString or match_string + self.match = match_string + self.matchLen = len(match_string) + try: + self.firstMatchChar = match_string[0] + except IndexError: + raise ValueError("null string passed to Keyword; use Empty() instead") + self.errmsg = "Expected {} {}".format(type(self).__name__, self.name) + self.mayReturnEmpty = False + self.mayIndexError = False + self.caseless = caseless + if caseless: + self.caselessmatch = match_string.upper() + identChars = identChars.upper() + self.identChars = set(identChars) + + def _generateDefaultName(self): + return repr(self.match) + + def parseImpl(self, instring, loc, doActions=True): + errmsg = self.errmsg + errloc = loc + if self.caseless: + if instring[loc : loc + self.matchLen].upper() == self.caselessmatch: + if loc == 0 or instring[loc - 1].upper() not in self.identChars: + if ( + loc >= len(instring) - self.matchLen + or instring[loc + self.matchLen].upper() not in self.identChars + ): + return loc + self.matchLen, self.match + else: + # followed by keyword char + errmsg += ", was immediately followed by keyword character" + errloc = loc + self.matchLen + else: + # preceded by keyword char + errmsg += ", keyword was immediately preceded by keyword character" + errloc = loc - 1 + # else no match just raise plain exception + + else: + if ( + instring[loc] == self.firstMatchChar + and self.matchLen == 1 + or instring.startswith(self.match, loc) + ): + if loc == 0 or instring[loc - 1] not in self.identChars: + if ( + loc >= len(instring) - self.matchLen + or instring[loc + self.matchLen] not in self.identChars + ): + return loc + self.matchLen, self.match + else: + # followed by keyword char + errmsg += ( + ", keyword was immediately followed by keyword character" + ) + errloc = loc + self.matchLen + else: + # preceded by keyword char + errmsg += ", keyword was immediately preceded by keyword character" + errloc = loc - 1 + # else no match just raise plain exception + + raise ParseException(instring, errloc, errmsg, self) + + @staticmethod + def set_default_keyword_chars(chars) -> None: + """ + Overrides the default characters used by :class:`Keyword` expressions. + """ + Keyword.DEFAULT_KEYWORD_CHARS = chars + + setDefaultKeywordChars = set_default_keyword_chars + + +class CaselessLiteral(Literal): + """ + Token to match a specified string, ignoring case of letters. + Note: the matched results will always be in the case of the given + match string, NOT the case of the input text. + + Example:: + + CaselessLiteral("CMD")[1, ...].parse_string("cmd CMD Cmd10") + # -> ['CMD', 'CMD', 'CMD'] + + (Contrast with example for :class:`CaselessKeyword`.) + """ + + def __init__(self, match_string: str = "", *, matchString: str = ""): + match_string = matchString or match_string + super().__init__(match_string.upper()) + # Preserve the defining literal. + self.returnString = match_string + self.errmsg = "Expected " + self.name + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc : loc + self.matchLen].upper() == self.match: + return loc + self.matchLen, self.returnString + raise ParseException(instring, loc, self.errmsg, self) + + +class CaselessKeyword(Keyword): + """ + Caseless version of :class:`Keyword`. + + Example:: + + CaselessKeyword("CMD")[1, ...].parse_string("cmd CMD Cmd10") + # -> ['CMD', 'CMD'] + + (Contrast with example for :class:`CaselessLiteral`.) + """ + + def __init__( + self, + match_string: str = "", + ident_chars: typing.Optional[str] = None, + *, + matchString: str = "", + identChars: typing.Optional[str] = None, + ): + identChars = identChars or ident_chars + match_string = matchString or match_string + super().__init__(match_string, identChars, caseless=True) + + +class CloseMatch(Token): + """A variation on :class:`Literal` which matches "close" matches, + that is, strings with at most 'n' mismatching characters. + :class:`CloseMatch` takes parameters: + + - ``match_string`` - string to be matched + - ``caseless`` - a boolean indicating whether to ignore casing when comparing characters + - ``max_mismatches`` - (``default=1``) maximum number of + mismatches allowed to count as a match + + The results from a successful parse will contain the matched text + from the input string and the following named results: + + - ``mismatches`` - a list of the positions within the + match_string where mismatches were found + - ``original`` - the original match_string used to compare + against the input string + + If ``mismatches`` is an empty list, then the match was an exact + match. + + Example:: + + patt = CloseMatch("ATCATCGAATGGA") + patt.parse_string("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']}) + patt.parse_string("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1) + + # exact match + patt.parse_string("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']}) + + # close match allowing up to 2 mismatches + patt = CloseMatch("ATCATCGAATGGA", max_mismatches=2) + patt.parse_string("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']}) + """ + + def __init__( + self, + match_string: str, + max_mismatches: int = None, + *, + maxMismatches: int = 1, + caseless=False, + ): + maxMismatches = max_mismatches if max_mismatches is not None else maxMismatches + super().__init__() + self.match_string = match_string + self.maxMismatches = maxMismatches + self.errmsg = "Expected {!r} (with up to {} mismatches)".format( + self.match_string, self.maxMismatches + ) + self.caseless = caseless + self.mayIndexError = False + self.mayReturnEmpty = False + + def _generateDefaultName(self): + return "{}:{!r}".format(type(self).__name__, self.match_string) + + def parseImpl(self, instring, loc, doActions=True): + start = loc + instrlen = len(instring) + maxloc = start + len(self.match_string) + + if maxloc <= instrlen: + match_string = self.match_string + match_stringloc = 0 + mismatches = [] + maxMismatches = self.maxMismatches + + for match_stringloc, s_m in enumerate( + zip(instring[loc:maxloc], match_string) + ): + src, mat = s_m + if self.caseless: + src, mat = src.lower(), mat.lower() + + if src != mat: + mismatches.append(match_stringloc) + if len(mismatches) > maxMismatches: + break + else: + loc = start + match_stringloc + 1 + results = ParseResults([instring[start:loc]]) + results["original"] = match_string + results["mismatches"] = mismatches + return loc, results + + raise ParseException(instring, loc, self.errmsg, self) + + +class Word(Token): + """Token for matching words composed of allowed character sets. + Parameters: + - ``init_chars`` - string of all characters that should be used to + match as a word; "ABC" will match "AAA", "ABAB", "CBAC", etc.; + if ``body_chars`` is also specified, then this is the string of + initial characters + - ``body_chars`` - string of characters that + can be used for matching after a matched initial character as + given in ``init_chars``; if omitted, same as the initial characters + (default=``None``) + - ``min`` - minimum number of characters to match (default=1) + - ``max`` - maximum number of characters to match (default=0) + - ``exact`` - exact number of characters to match (default=0) + - ``as_keyword`` - match as a keyword (default=``False``) + - ``exclude_chars`` - characters that might be + found in the input ``body_chars`` string but which should not be + accepted for matching ;useful to define a word of all + printables except for one or two characters, for instance + (default=``None``) + + :class:`srange` is useful for defining custom character set strings + for defining :class:`Word` expressions, using range notation from + regular expression character sets. + + A common mistake is to use :class:`Word` to match a specific literal + string, as in ``Word("Address")``. Remember that :class:`Word` + uses the string argument to define *sets* of matchable characters. + This expression would match "Add", "AAA", "dAred", or any other word + made up of the characters 'A', 'd', 'r', 'e', and 's'. To match an + exact literal string, use :class:`Literal` or :class:`Keyword`. + + pyparsing includes helper strings for building Words: + + - :class:`alphas` + - :class:`nums` + - :class:`alphanums` + - :class:`hexnums` + - :class:`alphas8bit` (alphabetic characters in ASCII range 128-255 + - accented, tilded, umlauted, etc.) + - :class:`punc8bit` (non-alphabetic characters in ASCII range + 128-255 - currency, symbols, superscripts, diacriticals, etc.) + - :class:`printables` (any non-whitespace character) + + ``alphas``, ``nums``, and ``printables`` are also defined in several + Unicode sets - see :class:`pyparsing_unicode``. + + Example:: + + # a word composed of digits + integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9")) + + # a word with a leading capital, and zero or more lowercase + capital_word = Word(alphas.upper(), alphas.lower()) + + # hostnames are alphanumeric, with leading alpha, and '-' + hostname = Word(alphas, alphanums + '-') + + # roman numeral (not a strict parser, accepts invalid mix of characters) + roman = Word("IVXLCDM") + + # any string of non-whitespace characters, except for ',' + csv_value = Word(printables, exclude_chars=",") + """ + + def __init__( + self, + init_chars: str = "", + body_chars: typing.Optional[str] = None, + min: int = 1, + max: int = 0, + exact: int = 0, + as_keyword: bool = False, + exclude_chars: typing.Optional[str] = None, + *, + initChars: typing.Optional[str] = None, + bodyChars: typing.Optional[str] = None, + asKeyword: bool = False, + excludeChars: typing.Optional[str] = None, + ): + initChars = initChars or init_chars + bodyChars = bodyChars or body_chars + asKeyword = asKeyword or as_keyword + excludeChars = excludeChars or exclude_chars + super().__init__() + if not initChars: + raise ValueError( + "invalid {}, initChars cannot be empty string".format( + type(self).__name__ + ) + ) + + initChars = set(initChars) + self.initChars = initChars + if excludeChars: + excludeChars = set(excludeChars) + initChars -= excludeChars + if bodyChars: + bodyChars = set(bodyChars) - excludeChars + self.initCharsOrig = "".join(sorted(initChars)) + + if bodyChars: + self.bodyCharsOrig = "".join(sorted(bodyChars)) + self.bodyChars = set(bodyChars) + else: + self.bodyCharsOrig = "".join(sorted(initChars)) + self.bodyChars = set(initChars) + + self.maxSpecified = max > 0 + + if min < 1: + raise ValueError( + "cannot specify a minimum length < 1; use Opt(Word()) if zero-length word is permitted" + ) + + self.minLen = min + + if max > 0: + self.maxLen = max + else: + self.maxLen = _MAX_INT + + if exact > 0: + self.maxLen = exact + self.minLen = exact + + self.errmsg = "Expected " + self.name + self.mayIndexError = False + self.asKeyword = asKeyword + + # see if we can make a regex for this Word + if " " not in self.initChars | self.bodyChars and (min == 1 and exact == 0): + if self.bodyChars == self.initChars: + if max == 0: + repeat = "+" + elif max == 1: + repeat = "" + else: + repeat = "{{{},{}}}".format( + self.minLen, "" if self.maxLen == _MAX_INT else self.maxLen + ) + self.reString = "[{}]{}".format( + _collapse_string_to_ranges(self.initChars), + repeat, + ) + elif len(self.initChars) == 1: + if max == 0: + repeat = "*" + else: + repeat = "{{0,{}}}".format(max - 1) + self.reString = "{}[{}]{}".format( + re.escape(self.initCharsOrig), + _collapse_string_to_ranges(self.bodyChars), + repeat, + ) + else: + if max == 0: + repeat = "*" + elif max == 2: + repeat = "" + else: + repeat = "{{0,{}}}".format(max - 1) + self.reString = "[{}][{}]{}".format( + _collapse_string_to_ranges(self.initChars), + _collapse_string_to_ranges(self.bodyChars), + repeat, + ) + if self.asKeyword: + self.reString = r"\b" + self.reString + r"\b" + + try: + self.re = re.compile(self.reString) + except re.error: + self.re = None + else: + self.re_match = self.re.match + self.__class__ = _WordRegex + + def _generateDefaultName(self): + def charsAsStr(s): + max_repr_len = 16 + s = _collapse_string_to_ranges(s, re_escape=False) + if len(s) > max_repr_len: + return s[: max_repr_len - 3] + "..." + else: + return s + + if self.initChars != self.bodyChars: + base = "W:({}, {})".format( + charsAsStr(self.initChars), charsAsStr(self.bodyChars) + ) + else: + base = "W:({})".format(charsAsStr(self.initChars)) + + # add length specification + if self.minLen > 1 or self.maxLen != _MAX_INT: + if self.minLen == self.maxLen: + if self.minLen == 1: + return base[2:] + else: + return base + "{{{}}}".format(self.minLen) + elif self.maxLen == _MAX_INT: + return base + "{{{},...}}".format(self.minLen) + else: + return base + "{{{},{}}}".format(self.minLen, self.maxLen) + return base + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] not in self.initChars: + raise ParseException(instring, loc, self.errmsg, self) + + start = loc + loc += 1 + instrlen = len(instring) + bodychars = self.bodyChars + maxloc = start + self.maxLen + maxloc = min(maxloc, instrlen) + while loc < maxloc and instring[loc] in bodychars: + loc += 1 + + throwException = False + if loc - start < self.minLen: + throwException = True + elif self.maxSpecified and loc < instrlen and instring[loc] in bodychars: + throwException = True + elif self.asKeyword: + if ( + start > 0 + and instring[start - 1] in bodychars + or loc < instrlen + and instring[loc] in bodychars + ): + throwException = True + + if throwException: + raise ParseException(instring, loc, self.errmsg, self) + + return loc, instring[start:loc] + + +class _WordRegex(Word): + def parseImpl(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + return loc, result.group() + + +class Char(_WordRegex): + """A short-cut class for defining :class:`Word` ``(characters, exact=1)``, + when defining a match of any single character in a string of + characters. + """ + + def __init__( + self, + charset: str, + as_keyword: bool = False, + exclude_chars: typing.Optional[str] = None, + *, + asKeyword: bool = False, + excludeChars: typing.Optional[str] = None, + ): + asKeyword = asKeyword or as_keyword + excludeChars = excludeChars or exclude_chars + super().__init__( + charset, exact=1, asKeyword=asKeyword, excludeChars=excludeChars + ) + self.reString = "[{}]".format(_collapse_string_to_ranges(self.initChars)) + if asKeyword: + self.reString = r"\b{}\b".format(self.reString) + self.re = re.compile(self.reString) + self.re_match = self.re.match + + +class Regex(Token): + r"""Token for matching strings that match a given regular + expression. Defined with string specifying the regular expression in + a form recognized by the stdlib Python `re module <https://docs.python.org/3/library/re.html>`_. + If the given regex contains named groups (defined using ``(?P<name>...)``), + these will be preserved as named :class:`ParseResults`. + + If instead of the Python stdlib ``re`` module you wish to use a different RE module + (such as the ``regex`` module), you can do so by building your ``Regex`` object with + a compiled RE that was compiled using ``regex``. + + Example:: + + realnum = Regex(r"[+-]?\d+\.\d*") + # ref: https://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression + roman = Regex(r"M{0,4}(CM|CD|D?{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})") + + # named fields in a regex will be returned as named results + date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)') + + # the Regex class will accept re's compiled using the regex module + import regex + parser = pp.Regex(regex.compile(r'[0-9]')) + """ + + def __init__( + self, + pattern: Any, + flags: Union[re.RegexFlag, int] = 0, + as_group_list: bool = False, + as_match: bool = False, + *, + asGroupList: bool = False, + asMatch: bool = False, + ): + """The parameters ``pattern`` and ``flags`` are passed + to the ``re.compile()`` function as-is. See the Python + `re module <https://docs.python.org/3/library/re.html>`_ module for an + explanation of the acceptable patterns and flags. + """ + super().__init__() + asGroupList = asGroupList or as_group_list + asMatch = asMatch or as_match + + if isinstance(pattern, str_type): + if not pattern: + raise ValueError("null string passed to Regex; use Empty() instead") + + self._re = None + self.reString = self.pattern = pattern + self.flags = flags + + elif hasattr(pattern, "pattern") and hasattr(pattern, "match"): + self._re = pattern + self.pattern = self.reString = pattern.pattern + self.flags = flags + + else: + raise TypeError( + "Regex may only be constructed with a string or a compiled RE object" + ) + + self.errmsg = "Expected " + self.name + self.mayIndexError = False + self.asGroupList = asGroupList + self.asMatch = asMatch + if self.asGroupList: + self.parseImpl = self.parseImplAsGroupList + if self.asMatch: + self.parseImpl = self.parseImplAsMatch + + @cached_property + def re(self): + if self._re: + return self._re + else: + try: + return re.compile(self.pattern, self.flags) + except re.error: + raise ValueError( + "invalid pattern ({!r}) passed to Regex".format(self.pattern) + ) + + @cached_property + def re_match(self): + return self.re.match + + @cached_property + def mayReturnEmpty(self): + return self.re_match("") is not None + + def _generateDefaultName(self): + return "Re:({})".format(repr(self.pattern).replace("\\\\", "\\")) + + def parseImpl(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = ParseResults(result.group()) + d = result.groupdict() + if d: + for k, v in d.items(): + ret[k] = v + return loc, ret + + def parseImplAsGroupList(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = result.groups() + return loc, ret + + def parseImplAsMatch(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = result + return loc, ret + + def sub(self, repl: str) -> ParserElement: + r""" + Return :class:`Regex` with an attached parse action to transform the parsed + result as if called using `re.sub(expr, repl, string) <https://docs.python.org/3/library/re.html#re.sub>`_. + + Example:: + + make_html = Regex(r"(\w+):(.*?):").sub(r"<\1>\2</\1>") + print(make_html.transform_string("h1:main title:")) + # prints "<h1>main title</h1>" + """ + if self.asGroupList: + raise TypeError("cannot use sub() with Regex(asGroupList=True)") + + if self.asMatch and callable(repl): + raise TypeError("cannot use sub() with a callable with Regex(asMatch=True)") + + if self.asMatch: + + def pa(tokens): + return tokens[0].expand(repl) + + else: + + def pa(tokens): + return self.re.sub(repl, tokens[0]) + + return self.add_parse_action(pa) + + +class QuotedString(Token): + r""" + Token for matching strings that are delimited by quoting characters. + + Defined with the following parameters: + + - ``quote_char`` - string of one or more characters defining the + quote delimiting string + - ``esc_char`` - character to re_escape quotes, typically backslash + (default= ``None``) + - ``esc_quote`` - special quote sequence to re_escape an embedded quote + string (such as SQL's ``""`` to re_escape an embedded ``"``) + (default= ``None``) + - ``multiline`` - boolean indicating whether quotes can span + multiple lines (default= ``False``) + - ``unquote_results`` - boolean indicating whether the matched text + should be unquoted (default= ``True``) + - ``end_quote_char`` - string of one or more characters defining the + end of the quote delimited string (default= ``None`` => same as + quote_char) + - ``convert_whitespace_escapes`` - convert escaped whitespace + (``'\t'``, ``'\n'``, etc.) to actual whitespace + (default= ``True``) + + Example:: + + qs = QuotedString('"') + print(qs.search_string('lsjdf "This is the quote" sldjf')) + complex_qs = QuotedString('{{', end_quote_char='}}') + print(complex_qs.search_string('lsjdf {{This is the "quote"}} sldjf')) + sql_qs = QuotedString('"', esc_quote='""') + print(sql_qs.search_string('lsjdf "This is the quote with ""embedded"" quotes" sldjf')) + + prints:: + + [['This is the quote']] + [['This is the "quote"']] + [['This is the quote with "embedded" quotes']] + """ + ws_map = ((r"\t", "\t"), (r"\n", "\n"), (r"\f", "\f"), (r"\r", "\r")) + + def __init__( + self, + quote_char: str = "", + esc_char: typing.Optional[str] = None, + esc_quote: typing.Optional[str] = None, + multiline: bool = False, + unquote_results: bool = True, + end_quote_char: typing.Optional[str] = None, + convert_whitespace_escapes: bool = True, + *, + quoteChar: str = "", + escChar: typing.Optional[str] = None, + escQuote: typing.Optional[str] = None, + unquoteResults: bool = True, + endQuoteChar: typing.Optional[str] = None, + convertWhitespaceEscapes: bool = True, + ): + super().__init__() + escChar = escChar or esc_char + escQuote = escQuote or esc_quote + unquoteResults = unquoteResults and unquote_results + endQuoteChar = endQuoteChar or end_quote_char + convertWhitespaceEscapes = ( + convertWhitespaceEscapes and convert_whitespace_escapes + ) + quote_char = quoteChar or quote_char + + # remove white space from quote chars - wont work anyway + quote_char = quote_char.strip() + if not quote_char: + raise ValueError("quote_char cannot be the empty string") + + if endQuoteChar is None: + endQuoteChar = quote_char + else: + endQuoteChar = endQuoteChar.strip() + if not endQuoteChar: + raise ValueError("endQuoteChar cannot be the empty string") + + self.quoteChar = quote_char + self.quoteCharLen = len(quote_char) + self.firstQuoteChar = quote_char[0] + self.endQuoteChar = endQuoteChar + self.endQuoteCharLen = len(endQuoteChar) + self.escChar = escChar + self.escQuote = escQuote + self.unquoteResults = unquoteResults + self.convertWhitespaceEscapes = convertWhitespaceEscapes + + sep = "" + inner_pattern = "" + + if escQuote: + inner_pattern += r"{}(?:{})".format(sep, re.escape(escQuote)) + sep = "|" + + if escChar: + inner_pattern += r"{}(?:{}.)".format(sep, re.escape(escChar)) + sep = "|" + self.escCharReplacePattern = re.escape(self.escChar) + "(.)" + + if len(self.endQuoteChar) > 1: + inner_pattern += ( + "{}(?:".format(sep) + + "|".join( + "(?:{}(?!{}))".format( + re.escape(self.endQuoteChar[:i]), + re.escape(self.endQuoteChar[i:]), + ) + for i in range(len(self.endQuoteChar) - 1, 0, -1) + ) + + ")" + ) + sep = "|" + + if multiline: + self.flags = re.MULTILINE | re.DOTALL + inner_pattern += r"{}(?:[^{}{}])".format( + sep, + _escape_regex_range_chars(self.endQuoteChar[0]), + (_escape_regex_range_chars(escChar) if escChar is not None else ""), + ) + else: + self.flags = 0 + inner_pattern += r"{}(?:[^{}\n\r{}])".format( + sep, + _escape_regex_range_chars(self.endQuoteChar[0]), + (_escape_regex_range_chars(escChar) if escChar is not None else ""), + ) + + self.pattern = "".join( + [ + re.escape(self.quoteChar), + "(?:", + inner_pattern, + ")*", + re.escape(self.endQuoteChar), + ] + ) + + try: + self.re = re.compile(self.pattern, self.flags) + self.reString = self.pattern + self.re_match = self.re.match + except re.error: + raise ValueError( + "invalid pattern {!r} passed to Regex".format(self.pattern) + ) + + self.errmsg = "Expected " + self.name + self.mayIndexError = False + self.mayReturnEmpty = True + + def _generateDefaultName(self): + if self.quoteChar == self.endQuoteChar and isinstance(self.quoteChar, str_type): + return "string enclosed in {!r}".format(self.quoteChar) + + return "quoted string, starting with {} ending with {}".format( + self.quoteChar, self.endQuoteChar + ) + + def parseImpl(self, instring, loc, doActions=True): + result = ( + instring[loc] == self.firstQuoteChar + and self.re_match(instring, loc) + or None + ) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = result.group() + + if self.unquoteResults: + + # strip off quotes + ret = ret[self.quoteCharLen : -self.endQuoteCharLen] + + if isinstance(ret, str_type): + # replace escaped whitespace + if "\\" in ret and self.convertWhitespaceEscapes: + for wslit, wschar in self.ws_map: + ret = ret.replace(wslit, wschar) + + # replace escaped characters + if self.escChar: + ret = re.sub(self.escCharReplacePattern, r"\g<1>", ret) + + # replace escaped quotes + if self.escQuote: + ret = ret.replace(self.escQuote, self.endQuoteChar) + + return loc, ret + + +class CharsNotIn(Token): + """Token for matching words composed of characters *not* in a given + set (will include whitespace in matched characters if not listed in + the provided exclusion set - see example). Defined with string + containing all disallowed characters, and an optional minimum, + maximum, and/or exact length. The default value for ``min`` is + 1 (a minimum value < 1 is not valid); the default values for + ``max`` and ``exact`` are 0, meaning no maximum or exact + length restriction. + + Example:: + + # define a comma-separated-value as anything that is not a ',' + csv_value = CharsNotIn(',') + print(delimited_list(csv_value).parse_string("dkls,lsdkjf,s12 34,@!#,213")) + + prints:: + + ['dkls', 'lsdkjf', 's12 34', '@!#', '213'] + """ + + def __init__( + self, + not_chars: str = "", + min: int = 1, + max: int = 0, + exact: int = 0, + *, + notChars: str = "", + ): + super().__init__() + self.skipWhitespace = False + self.notChars = not_chars or notChars + self.notCharsSet = set(self.notChars) + + if min < 1: + raise ValueError( + "cannot specify a minimum length < 1; use " + "Opt(CharsNotIn()) if zero-length char group is permitted" + ) + + self.minLen = min + + if max > 0: + self.maxLen = max + else: + self.maxLen = _MAX_INT + + if exact > 0: + self.maxLen = exact + self.minLen = exact + + self.errmsg = "Expected " + self.name + self.mayReturnEmpty = self.minLen == 0 + self.mayIndexError = False + + def _generateDefaultName(self): + not_chars_str = _collapse_string_to_ranges(self.notChars) + if len(not_chars_str) > 16: + return "!W:({}...)".format(self.notChars[: 16 - 3]) + else: + return "!W:({})".format(self.notChars) + + def parseImpl(self, instring, loc, doActions=True): + notchars = self.notCharsSet + if instring[loc] in notchars: + raise ParseException(instring, loc, self.errmsg, self) + + start = loc + loc += 1 + maxlen = min(start + self.maxLen, len(instring)) + while loc < maxlen and instring[loc] not in notchars: + loc += 1 + + if loc - start < self.minLen: + raise ParseException(instring, loc, self.errmsg, self) + + return loc, instring[start:loc] + + +class White(Token): + """Special matching class for matching whitespace. Normally, + whitespace is ignored by pyparsing grammars. This class is included + when some whitespace structures are significant. Define with + a string containing the whitespace characters to be matched; default + is ``" \\t\\r\\n"``. Also takes optional ``min``, + ``max``, and ``exact`` arguments, as defined for the + :class:`Word` class. + """ + + whiteStrs = { + " ": "<SP>", + "\t": "<TAB>", + "\n": "<LF>", + "\r": "<CR>", + "\f": "<FF>", + "\u00A0": "<NBSP>", + "\u1680": "<OGHAM_SPACE_MARK>", + "\u180E": "<MONGOLIAN_VOWEL_SEPARATOR>", + "\u2000": "<EN_QUAD>", + "\u2001": "<EM_QUAD>", + "\u2002": "<EN_SPACE>", + "\u2003": "<EM_SPACE>", + "\u2004": "<THREE-PER-EM_SPACE>", + "\u2005": "<FOUR-PER-EM_SPACE>", + "\u2006": "<SIX-PER-EM_SPACE>", + "\u2007": "<FIGURE_SPACE>", + "\u2008": "<PUNCTUATION_SPACE>", + "\u2009": "<THIN_SPACE>", + "\u200A": "<HAIR_SPACE>", + "\u200B": "<ZERO_WIDTH_SPACE>", + "\u202F": "<NNBSP>", + "\u205F": "<MMSP>", + "\u3000": "<IDEOGRAPHIC_SPACE>", + } + + def __init__(self, ws: str = " \t\r\n", min: int = 1, max: int = 0, exact: int = 0): + super().__init__() + self.matchWhite = ws + self.set_whitespace_chars( + "".join(c for c in self.whiteStrs if c not in self.matchWhite), + copy_defaults=True, + ) + # self.leave_whitespace() + self.mayReturnEmpty = True + self.errmsg = "Expected " + self.name + + self.minLen = min + + if max > 0: + self.maxLen = max + else: + self.maxLen = _MAX_INT + + if exact > 0: + self.maxLen = exact + self.minLen = exact + + def _generateDefaultName(self): + return "".join(White.whiteStrs[c] for c in self.matchWhite) + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] not in self.matchWhite: + raise ParseException(instring, loc, self.errmsg, self) + start = loc + loc += 1 + maxloc = start + self.maxLen + maxloc = min(maxloc, len(instring)) + while loc < maxloc and instring[loc] in self.matchWhite: + loc += 1 + + if loc - start < self.minLen: + raise ParseException(instring, loc, self.errmsg, self) + + return loc, instring[start:loc] + + +class PositionToken(Token): + def __init__(self): + super().__init__() + self.mayReturnEmpty = True + self.mayIndexError = False + + +class GoToColumn(PositionToken): + """Token to advance to a specific column of input text; useful for + tabular report scraping. + """ + + def __init__(self, colno: int): + super().__init__() + self.col = colno + + def preParse(self, instring, loc): + if col(loc, instring) != self.col: + instrlen = len(instring) + if self.ignoreExprs: + loc = self._skipIgnorables(instring, loc) + while ( + loc < instrlen + and instring[loc].isspace() + and col(loc, instring) != self.col + ): + loc += 1 + return loc + + def parseImpl(self, instring, loc, doActions=True): + thiscol = col(loc, instring) + if thiscol > self.col: + raise ParseException(instring, loc, "Text not in expected column", self) + newloc = loc + self.col - thiscol + ret = instring[loc:newloc] + return newloc, ret + + +class LineStart(PositionToken): + r"""Matches if current position is at the beginning of a line within + the parse string + + Example:: + + test = '''\ + AAA this line + AAA and this line + AAA but not this one + B AAA and definitely not this one + ''' + + for t in (LineStart() + 'AAA' + restOfLine).search_string(test): + print(t) + + prints:: + + ['AAA', ' this line'] + ['AAA', ' and this line'] + + """ + + def __init__(self): + super().__init__() + self.leave_whitespace() + self.orig_whiteChars = set() | self.whiteChars + self.whiteChars.discard("\n") + self.skipper = Empty().set_whitespace_chars(self.whiteChars) + self.errmsg = "Expected start of line" + + def preParse(self, instring, loc): + if loc == 0: + return loc + else: + ret = self.skipper.preParse(instring, loc) + if "\n" in self.orig_whiteChars: + while instring[ret : ret + 1] == "\n": + ret = self.skipper.preParse(instring, ret + 1) + return ret + + def parseImpl(self, instring, loc, doActions=True): + if col(loc, instring) == 1: + return loc, [] + raise ParseException(instring, loc, self.errmsg, self) + + +class LineEnd(PositionToken): + """Matches if current position is at the end of a line within the + parse string + """ + + def __init__(self): + super().__init__() + self.whiteChars.discard("\n") + self.set_whitespace_chars(self.whiteChars, copy_defaults=False) + self.errmsg = "Expected end of line" + + def parseImpl(self, instring, loc, doActions=True): + if loc < len(instring): + if instring[loc] == "\n": + return loc + 1, "\n" + else: + raise ParseException(instring, loc, self.errmsg, self) + elif loc == len(instring): + return loc + 1, [] + else: + raise ParseException(instring, loc, self.errmsg, self) + + +class StringStart(PositionToken): + """Matches if current position is at the beginning of the parse + string + """ + + def __init__(self): + super().__init__() + self.errmsg = "Expected start of text" + + def parseImpl(self, instring, loc, doActions=True): + if loc != 0: + # see if entire string up to here is just whitespace and ignoreables + if loc != self.preParse(instring, 0): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + +class StringEnd(PositionToken): + """ + Matches if current position is at the end of the parse string + """ + + def __init__(self): + super().__init__() + self.errmsg = "Expected end of text" + + def parseImpl(self, instring, loc, doActions=True): + if loc < len(instring): + raise ParseException(instring, loc, self.errmsg, self) + elif loc == len(instring): + return loc + 1, [] + elif loc > len(instring): + return loc, [] + else: + raise ParseException(instring, loc, self.errmsg, self) + + +class WordStart(PositionToken): + """Matches if the current position is at the beginning of a + :class:`Word`, and is not preceded by any character in a given + set of ``word_chars`` (default= ``printables``). To emulate the + ``\b`` behavior of regular expressions, use + ``WordStart(alphanums)``. ``WordStart`` will also match at + the beginning of the string being parsed, or at the beginning of + a line. + """ + + def __init__(self, word_chars: str = printables, *, wordChars: str = printables): + wordChars = word_chars if wordChars == printables else wordChars + super().__init__() + self.wordChars = set(wordChars) + self.errmsg = "Not at the start of a word" + + def parseImpl(self, instring, loc, doActions=True): + if loc != 0: + if ( + instring[loc - 1] in self.wordChars + or instring[loc] not in self.wordChars + ): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + +class WordEnd(PositionToken): + """Matches if the current position is at the end of a :class:`Word`, + and is not followed by any character in a given set of ``word_chars`` + (default= ``printables``). To emulate the ``\b`` behavior of + regular expressions, use ``WordEnd(alphanums)``. ``WordEnd`` + will also match at the end of the string being parsed, or at the end + of a line. + """ + + def __init__(self, word_chars: str = printables, *, wordChars: str = printables): + wordChars = word_chars if wordChars == printables else wordChars + super().__init__() + self.wordChars = set(wordChars) + self.skipWhitespace = False + self.errmsg = "Not at the end of a word" + + def parseImpl(self, instring, loc, doActions=True): + instrlen = len(instring) + if instrlen > 0 and loc < instrlen: + if ( + instring[loc] in self.wordChars + or instring[loc - 1] not in self.wordChars + ): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + +class ParseExpression(ParserElement): + """Abstract subclass of ParserElement, for combining and + post-processing parsed tokens. + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): + super().__init__(savelist) + self.exprs: List[ParserElement] + if isinstance(exprs, _generatorType): + exprs = list(exprs) + + if isinstance(exprs, str_type): + self.exprs = [self._literalStringClass(exprs)] + elif isinstance(exprs, ParserElement): + self.exprs = [exprs] + elif isinstance(exprs, Iterable): + exprs = list(exprs) + # if sequence of strings provided, wrap with Literal + if any(isinstance(expr, str_type) for expr in exprs): + exprs = ( + self._literalStringClass(e) if isinstance(e, str_type) else e + for e in exprs + ) + self.exprs = list(exprs) + else: + try: + self.exprs = list(exprs) + except TypeError: + self.exprs = [exprs] + self.callPreparse = False + + def recurse(self) -> Sequence[ParserElement]: + return self.exprs[:] + + def append(self, other) -> ParserElement: + self.exprs.append(other) + self._defaultName = None + return self + + def leave_whitespace(self, recursive: bool = True) -> ParserElement: + """ + Extends ``leave_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on + all contained expressions. + """ + super().leave_whitespace(recursive) + + if recursive: + self.exprs = [e.copy() for e in self.exprs] + for e in self.exprs: + e.leave_whitespace(recursive) + return self + + def ignore_whitespace(self, recursive: bool = True) -> ParserElement: + """ + Extends ``ignore_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on + all contained expressions. + """ + super().ignore_whitespace(recursive) + if recursive: + self.exprs = [e.copy() for e in self.exprs] + for e in self.exprs: + e.ignore_whitespace(recursive) + return self + + def ignore(self, other) -> ParserElement: + if isinstance(other, Suppress): + if other not in self.ignoreExprs: + super().ignore(other) + for e in self.exprs: + e.ignore(self.ignoreExprs[-1]) + else: + super().ignore(other) + for e in self.exprs: + e.ignore(self.ignoreExprs[-1]) + return self + + def _generateDefaultName(self): + return "{}:({})".format(self.__class__.__name__, str(self.exprs)) + + def streamline(self) -> ParserElement: + if self.streamlined: + return self + + super().streamline() + + for e in self.exprs: + e.streamline() + + # collapse nested :class:`And`'s of the form ``And(And(And(a, b), c), d)`` to ``And(a, b, c, d)`` + # but only if there are no parse actions or resultsNames on the nested And's + # (likewise for :class:`Or`'s and :class:`MatchFirst`'s) + if len(self.exprs) == 2: + other = self.exprs[0] + if ( + isinstance(other, self.__class__) + and not other.parseAction + and other.resultsName is None + and not other.debug + ): + self.exprs = other.exprs[:] + [self.exprs[1]] + self._defaultName = None + self.mayReturnEmpty |= other.mayReturnEmpty + self.mayIndexError |= other.mayIndexError + + other = self.exprs[-1] + if ( + isinstance(other, self.__class__) + and not other.parseAction + and other.resultsName is None + and not other.debug + ): + self.exprs = self.exprs[:-1] + other.exprs[:] + self._defaultName = None + self.mayReturnEmpty |= other.mayReturnEmpty + self.mayIndexError |= other.mayIndexError + + self.errmsg = "Expected " + str(self) + + return self + + def validate(self, validateTrace=None) -> None: + tmp = (validateTrace if validateTrace is not None else [])[:] + [self] + for e in self.exprs: + e.validate(tmp) + self._checkRecursion([]) + + def copy(self) -> ParserElement: + ret = super().copy() + ret.exprs = [e.copy() for e in self.exprs] + return ret + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_ungrouped_named_tokens_in_collection + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in self.suppress_warnings_ + ): + for e in self.exprs: + if ( + isinstance(e, ParserElement) + and e.resultsName + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in e.suppress_warnings_ + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "collides with {!r} on contained expression".format( + "warn_ungrouped_named_tokens_in_collection", + name, + type(self).__name__, + e.resultsName, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class And(ParseExpression): + """ + Requires all given :class:`ParseExpression` s to be found in the given order. + Expressions may be separated by whitespace. + May be constructed using the ``'+'`` operator. + May also be constructed using the ``'-'`` operator, which will + suppress backtracking. + + Example:: + + integer = Word(nums) + name_expr = Word(alphas)[1, ...] + + expr = And([integer("id"), name_expr("name"), integer("age")]) + # more easily written as: + expr = integer("id") + name_expr("name") + integer("age") + """ + + class _ErrorStop(Empty): + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + self.leave_whitespace() + + def _generateDefaultName(self): + return "-" + + def __init__( + self, exprs_arg: typing.Iterable[ParserElement], savelist: bool = True + ): + exprs: List[ParserElement] = list(exprs_arg) + if exprs and Ellipsis in exprs: + tmp = [] + for i, expr in enumerate(exprs): + if expr is Ellipsis: + if i < len(exprs) - 1: + skipto_arg: ParserElement = (Empty() + exprs[i + 1]).exprs[-1] + tmp.append(SkipTo(skipto_arg)("_skipped*")) + else: + raise Exception( + "cannot construct And with sequence ending in ..." + ) + else: + tmp.append(expr) + exprs[:] = tmp + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + if not isinstance(self.exprs[0], White): + self.set_whitespace_chars( + self.exprs[0].whiteChars, + copy_defaults=self.exprs[0].copyDefaultWhiteChars, + ) + self.skipWhitespace = self.exprs[0].skipWhitespace + else: + self.skipWhitespace = False + else: + self.mayReturnEmpty = True + self.callPreparse = True + + def streamline(self) -> ParserElement: + # collapse any _PendingSkip's + if self.exprs: + if any( + isinstance(e, ParseExpression) + and e.exprs + and isinstance(e.exprs[-1], _PendingSkip) + for e in self.exprs[:-1] + ): + for i, e in enumerate(self.exprs[:-1]): + if e is None: + continue + if ( + isinstance(e, ParseExpression) + and e.exprs + and isinstance(e.exprs[-1], _PendingSkip) + ): + e.exprs[-1] = e.exprs[-1] + self.exprs[i + 1] + self.exprs[i + 1] = None + self.exprs = [e for e in self.exprs if e is not None] + + super().streamline() + + # link any IndentedBlocks to the prior expression + for prev, cur in zip(self.exprs, self.exprs[1:]): + # traverse cur or any first embedded expr of cur looking for an IndentedBlock + # (but watch out for recursive grammar) + seen = set() + while cur: + if id(cur) in seen: + break + seen.add(id(cur)) + if isinstance(cur, IndentedBlock): + prev.add_parse_action( + lambda s, l, t, cur_=cur: setattr( + cur_, "parent_anchor", col(l, s) + ) + ) + break + subs = cur.recurse() + cur = next(iter(subs), None) + + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + return self + + def parseImpl(self, instring, loc, doActions=True): + # pass False as callPreParse arg to _parse for first element, since we already + # pre-parsed the string as part of our And pre-parsing + loc, resultlist = self.exprs[0]._parse( + instring, loc, doActions, callPreParse=False + ) + errorStop = False + for e in self.exprs[1:]: + # if isinstance(e, And._ErrorStop): + if type(e) is And._ErrorStop: + errorStop = True + continue + if errorStop: + try: + loc, exprtokens = e._parse(instring, loc, doActions) + except ParseSyntaxException: + raise + except ParseBaseException as pe: + pe.__traceback__ = None + raise ParseSyntaxException._from_exception(pe) + except IndexError: + raise ParseSyntaxException( + instring, len(instring), self.errmsg, self + ) + else: + loc, exprtokens = e._parse(instring, loc, doActions) + if exprtokens or exprtokens.haskeys(): + resultlist += exprtokens + return loc, resultlist + + def __iadd__(self, other): + if isinstance(other, str_type): + other = self._literalStringClass(other) + return self.append(other) # And([self, other]) + + def _checkRecursion(self, parseElementList): + subRecCheckList = parseElementList[:] + [self] + for e in self.exprs: + e._checkRecursion(subRecCheckList) + if not e.mayReturnEmpty: + break + + def _generateDefaultName(self): + inner = " ".join(str(e) for e in self.exprs) + # strip off redundant inner {}'s + while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": + inner = inner[1:-1] + return "{" + inner + "}" + + +class Or(ParseExpression): + """Requires that at least one :class:`ParseExpression` is found. If + two expressions match, the expression that matches the longest + string will be used. May be constructed using the ``'^'`` + operator. + + Example:: + + # construct Or using '^' operator + + number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums)) + print(number.search_string("123 3.1416 789")) + + prints:: + + [['123'], ['3.1416'], ['789']] + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) + else: + self.mayReturnEmpty = True + + def streamline(self) -> ParserElement: + super().streamline() + if self.exprs: + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.saveAsList = any(e.saveAsList for e in self.exprs) + self.skipWhitespace = all( + e.skipWhitespace and not isinstance(e, White) for e in self.exprs + ) + else: + self.saveAsList = False + return self + + def parseImpl(self, instring, loc, doActions=True): + maxExcLoc = -1 + maxException = None + matches = [] + fatals = [] + if all(e.callPreparse for e in self.exprs): + loc = self.preParse(instring, loc) + for e in self.exprs: + try: + loc2 = e.try_parse(instring, loc, raise_fatal=True) + except ParseFatalException as pfe: + pfe.__traceback__ = None + pfe.parserElement = e + fatals.append(pfe) + maxException = None + maxExcLoc = -1 + except ParseException as err: + if not fatals: + err.__traceback__ = None + if err.loc > maxExcLoc: + maxException = err + maxExcLoc = err.loc + except IndexError: + if len(instring) > maxExcLoc: + maxException = ParseException( + instring, len(instring), e.errmsg, self + ) + maxExcLoc = len(instring) + else: + # save match among all matches, to retry longest to shortest + matches.append((loc2, e)) + + if matches: + # re-evaluate all matches in descending order of length of match, in case attached actions + # might change whether or how much they match of the input. + matches.sort(key=itemgetter(0), reverse=True) + + if not doActions: + # no further conditions or parse actions to change the selection of + # alternative, so the first match will be the best match + best_expr = matches[0][1] + return best_expr._parse(instring, loc, doActions) + + longest = -1, None + for loc1, expr1 in matches: + if loc1 <= longest[0]: + # already have a longer match than this one will deliver, we are done + return longest + + try: + loc2, toks = expr1._parse(instring, loc, doActions) + except ParseException as err: + err.__traceback__ = None + if err.loc > maxExcLoc: + maxException = err + maxExcLoc = err.loc + else: + if loc2 >= loc1: + return loc2, toks + # didn't match as much as before + elif loc2 > longest[0]: + longest = loc2, toks + + if longest != (-1, None): + return longest + + if fatals: + if len(fatals) > 1: + fatals.sort(key=lambda e: -e.loc) + if fatals[0].loc == fatals[1].loc: + fatals.sort(key=lambda e: (-e.loc, -len(str(e.parserElement)))) + max_fatal = fatals[0] + raise max_fatal + + if maxException is not None: + maxException.msg = self.errmsg + raise maxException + else: + raise ParseException( + instring, loc, "no defined alternatives to match", self + ) + + def __ixor__(self, other): + if isinstance(other, str_type): + other = self._literalStringClass(other) + return self.append(other) # Or([self, other]) + + def _generateDefaultName(self): + return "{" + " ^ ".join(str(e) for e in self.exprs) + "}" + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_multiple_tokens_in_named_alternation + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in self.suppress_warnings_ + ): + if any( + isinstance(e, And) + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in e.suppress_warnings_ + for e in self.exprs + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "will return a list of all parsed tokens in an And alternative, " + "in prior versions only the first token was returned; enclose " + "contained argument in Group".format( + "warn_multiple_tokens_in_named_alternation", + name, + type(self).__name__, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + +class MatchFirst(ParseExpression): + """Requires that at least one :class:`ParseExpression` is found. If + more than one expression matches, the first one listed is the one that will + match. May be constructed using the ``'|'`` operator. + + Example:: + + # construct MatchFirst using '|' operator + + # watch the order of expressions to match + number = Word(nums) | Combine(Word(nums) + '.' + Word(nums)) + print(number.search_string("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']] + + # put more selective expression first + number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums) + print(number.search_string("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']] + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) + else: + self.mayReturnEmpty = True + + def streamline(self) -> ParserElement: + if self.streamlined: + return self + + super().streamline() + if self.exprs: + self.saveAsList = any(e.saveAsList for e in self.exprs) + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.skipWhitespace = all( + e.skipWhitespace and not isinstance(e, White) for e in self.exprs + ) + else: + self.saveAsList = False + self.mayReturnEmpty = True + return self + + def parseImpl(self, instring, loc, doActions=True): + maxExcLoc = -1 + maxException = None + + for e in self.exprs: + try: + return e._parse( + instring, + loc, + doActions, + ) + except ParseFatalException as pfe: + pfe.__traceback__ = None + pfe.parserElement = e + raise + except ParseException as err: + if err.loc > maxExcLoc: + maxException = err + maxExcLoc = err.loc + except IndexError: + if len(instring) > maxExcLoc: + maxException = ParseException( + instring, len(instring), e.errmsg, self + ) + maxExcLoc = len(instring) + + if maxException is not None: + maxException.msg = self.errmsg + raise maxException + else: + raise ParseException( + instring, loc, "no defined alternatives to match", self + ) + + def __ior__(self, other): + if isinstance(other, str_type): + other = self._literalStringClass(other) + return self.append(other) # MatchFirst([self, other]) + + def _generateDefaultName(self): + return "{" + " | ".join(str(e) for e in self.exprs) + "}" + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_multiple_tokens_in_named_alternation + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in self.suppress_warnings_ + ): + if any( + isinstance(e, And) + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in e.suppress_warnings_ + for e in self.exprs + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "will return a list of all parsed tokens in an And alternative, " + "in prior versions only the first token was returned; enclose " + "contained argument in Group".format( + "warn_multiple_tokens_in_named_alternation", + name, + type(self).__name__, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + +class Each(ParseExpression): + """Requires all given :class:`ParseExpression` s to be found, but in + any order. Expressions may be separated by whitespace. + + May be constructed using the ``'&'`` operator. + + Example:: + + color = one_of("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN") + shape_type = one_of("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON") + integer = Word(nums) + shape_attr = "shape:" + shape_type("shape") + posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn") + color_attr = "color:" + color("color") + size_attr = "size:" + integer("size") + + # use Each (using operator '&') to accept attributes in any order + # (shape and posn are required, color and size are optional) + shape_spec = shape_attr & posn_attr & Opt(color_attr) & Opt(size_attr) + + shape_spec.run_tests(''' + shape: SQUARE color: BLACK posn: 100, 120 + shape: CIRCLE size: 50 color: BLUE posn: 50,80 + color:GREEN size:20 shape:TRIANGLE posn:20,40 + ''' + ) + + prints:: + + shape: SQUARE color: BLACK posn: 100, 120 + ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']] + - color: BLACK + - posn: ['100', ',', '120'] + - x: 100 + - y: 120 + - shape: SQUARE + + + shape: CIRCLE size: 50 color: BLUE posn: 50,80 + ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']] + - color: BLUE + - posn: ['50', ',', '80'] + - x: 50 + - y: 80 + - shape: CIRCLE + - size: 50 + + + color: GREEN size: 20 shape: TRIANGLE posn: 20,40 + ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']] + - color: GREEN + - posn: ['20', ',', '40'] + - x: 20 + - y: 40 + - shape: TRIANGLE + - size: 20 + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = True): + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + else: + self.mayReturnEmpty = True + self.skipWhitespace = True + self.initExprGroups = True + self.saveAsList = True + + def streamline(self) -> ParserElement: + super().streamline() + if self.exprs: + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + else: + self.mayReturnEmpty = True + return self + + def parseImpl(self, instring, loc, doActions=True): + if self.initExprGroups: + self.opt1map = dict( + (id(e.expr), e) for e in self.exprs if isinstance(e, Opt) + ) + opt1 = [e.expr for e in self.exprs if isinstance(e, Opt)] + opt2 = [ + e + for e in self.exprs + if e.mayReturnEmpty and not isinstance(e, (Opt, Regex, ZeroOrMore)) + ] + self.optionals = opt1 + opt2 + self.multioptionals = [ + e.expr.set_results_name(e.resultsName, list_all_matches=True) + for e in self.exprs + if isinstance(e, _MultipleMatch) + ] + self.multirequired = [ + e.expr.set_results_name(e.resultsName, list_all_matches=True) + for e in self.exprs + if isinstance(e, OneOrMore) + ] + self.required = [ + e for e in self.exprs if not isinstance(e, (Opt, ZeroOrMore, OneOrMore)) + ] + self.required += self.multirequired + self.initExprGroups = False + + tmpLoc = loc + tmpReqd = self.required[:] + tmpOpt = self.optionals[:] + multis = self.multioptionals[:] + matchOrder = [] + + keepMatching = True + failed = [] + fatals = [] + while keepMatching: + tmpExprs = tmpReqd + tmpOpt + multis + failed.clear() + fatals.clear() + for e in tmpExprs: + try: + tmpLoc = e.try_parse(instring, tmpLoc, raise_fatal=True) + except ParseFatalException as pfe: + pfe.__traceback__ = None + pfe.parserElement = e + fatals.append(pfe) + failed.append(e) + except ParseException: + failed.append(e) + else: + matchOrder.append(self.opt1map.get(id(e), e)) + if e in tmpReqd: + tmpReqd.remove(e) + elif e in tmpOpt: + tmpOpt.remove(e) + if len(failed) == len(tmpExprs): + keepMatching = False + + # look for any ParseFatalExceptions + if fatals: + if len(fatals) > 1: + fatals.sort(key=lambda e: -e.loc) + if fatals[0].loc == fatals[1].loc: + fatals.sort(key=lambda e: (-e.loc, -len(str(e.parserElement)))) + max_fatal = fatals[0] + raise max_fatal + + if tmpReqd: + missing = ", ".join([str(e) for e in tmpReqd]) + raise ParseException( + instring, + loc, + "Missing one or more required elements ({})".format(missing), + ) + + # add any unmatched Opts, in case they have default values defined + matchOrder += [e for e in self.exprs if isinstance(e, Opt) and e.expr in tmpOpt] + + total_results = ParseResults([]) + for e in matchOrder: + loc, results = e._parse(instring, loc, doActions) + total_results += results + + return loc, total_results + + def _generateDefaultName(self): + return "{" + " & ".join(str(e) for e in self.exprs) + "}" + + +class ParseElementEnhance(ParserElement): + """Abstract subclass of :class:`ParserElement`, for combining and + post-processing parsed tokens. + """ + + def __init__(self, expr: Union[ParserElement, str], savelist: bool = False): + super().__init__(savelist) + if isinstance(expr, str_type): + if issubclass(self._literalStringClass, Token): + expr = self._literalStringClass(expr) + elif issubclass(type(self), self._literalStringClass): + expr = Literal(expr) + else: + expr = self._literalStringClass(Literal(expr)) + self.expr = expr + if expr is not None: + self.mayIndexError = expr.mayIndexError + self.mayReturnEmpty = expr.mayReturnEmpty + self.set_whitespace_chars( + expr.whiteChars, copy_defaults=expr.copyDefaultWhiteChars + ) + self.skipWhitespace = expr.skipWhitespace + self.saveAsList = expr.saveAsList + self.callPreparse = expr.callPreparse + self.ignoreExprs.extend(expr.ignoreExprs) + + def recurse(self) -> Sequence[ParserElement]: + return [self.expr] if self.expr is not None else [] + + def parseImpl(self, instring, loc, doActions=True): + if self.expr is not None: + return self.expr._parse(instring, loc, doActions, callPreParse=False) + else: + raise ParseException(instring, loc, "No expression defined", self) + + def leave_whitespace(self, recursive: bool = True) -> ParserElement: + super().leave_whitespace(recursive) + + if recursive: + self.expr = self.expr.copy() + if self.expr is not None: + self.expr.leave_whitespace(recursive) + return self + + def ignore_whitespace(self, recursive: bool = True) -> ParserElement: + super().ignore_whitespace(recursive) + + if recursive: + self.expr = self.expr.copy() + if self.expr is not None: + self.expr.ignore_whitespace(recursive) + return self + + def ignore(self, other) -> ParserElement: + if isinstance(other, Suppress): + if other not in self.ignoreExprs: + super().ignore(other) + if self.expr is not None: + self.expr.ignore(self.ignoreExprs[-1]) + else: + super().ignore(other) + if self.expr is not None: + self.expr.ignore(self.ignoreExprs[-1]) + return self + + def streamline(self) -> ParserElement: + super().streamline() + if self.expr is not None: + self.expr.streamline() + return self + + def _checkRecursion(self, parseElementList): + if self in parseElementList: + raise RecursiveGrammarException(parseElementList + [self]) + subRecCheckList = parseElementList[:] + [self] + if self.expr is not None: + self.expr._checkRecursion(subRecCheckList) + + def validate(self, validateTrace=None) -> None: + if validateTrace is None: + validateTrace = [] + tmp = validateTrace[:] + [self] + if self.expr is not None: + self.expr.validate(tmp) + self._checkRecursion([]) + + def _generateDefaultName(self): + return "{}:({})".format(self.__class__.__name__, str(self.expr)) + + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class IndentedBlock(ParseElementEnhance): + """ + Expression to match one or more expressions at a given indentation level. + Useful for parsing text where structure is implied by indentation (like Python source code). + """ + + class _Indent(Empty): + def __init__(self, ref_col: int): + super().__init__() + self.errmsg = "expected indent at column {}".format(ref_col) + self.add_condition(lambda s, l, t: col(l, s) == ref_col) + + class _IndentGreater(Empty): + def __init__(self, ref_col: int): + super().__init__() + self.errmsg = "expected indent at column greater than {}".format(ref_col) + self.add_condition(lambda s, l, t: col(l, s) > ref_col) + + def __init__( + self, expr: ParserElement, *, recursive: bool = False, grouped: bool = True + ): + super().__init__(expr, savelist=True) + # if recursive: + # raise NotImplementedError("IndentedBlock with recursive is not implemented") + self._recursive = recursive + self._grouped = grouped + self.parent_anchor = 1 + + def parseImpl(self, instring, loc, doActions=True): + # advance parse position to non-whitespace by using an Empty() + # this should be the column to be used for all subsequent indented lines + anchor_loc = Empty().preParse(instring, loc) + + # see if self.expr matches at the current location - if not it will raise an exception + # and no further work is necessary + self.expr.try_parse(instring, anchor_loc, doActions) + + indent_col = col(anchor_loc, instring) + peer_detect_expr = self._Indent(indent_col) + + inner_expr = Empty() + peer_detect_expr + self.expr + if self._recursive: + sub_indent = self._IndentGreater(indent_col) + nested_block = IndentedBlock( + self.expr, recursive=self._recursive, grouped=self._grouped + ) + nested_block.set_debug(self.debug) + nested_block.parent_anchor = indent_col + inner_expr += Opt(sub_indent + nested_block) + + inner_expr.set_name(f"inner {hex(id(inner_expr))[-4:].upper()}@{indent_col}") + block = OneOrMore(inner_expr) + + trailing_undent = self._Indent(self.parent_anchor) | StringEnd() + + if self._grouped: + wrapper = Group + else: + wrapper = lambda expr: expr + return (wrapper(block) + Optional(trailing_undent)).parseImpl( + instring, anchor_loc, doActions + ) + + +class AtStringStart(ParseElementEnhance): + """Matches if expression matches at the beginning of the parse + string:: + + AtStringStart(Word(nums)).parse_string("123") + # prints ["123"] + + AtStringStart(Word(nums)).parse_string(" 123") + # raises ParseException + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + self.callPreparse = False + + def parseImpl(self, instring, loc, doActions=True): + if loc != 0: + raise ParseException(instring, loc, "not found at string start") + return super().parseImpl(instring, loc, doActions) + + +class AtLineStart(ParseElementEnhance): + r"""Matches if an expression matches at the beginning of a line within + the parse string + + Example:: + + test = '''\ + AAA this line + AAA and this line + AAA but not this one + B AAA and definitely not this one + ''' + + for t in (AtLineStart('AAA') + restOfLine).search_string(test): + print(t) + + prints:: + + ['AAA', ' this line'] + ['AAA', ' and this line'] + + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + self.callPreparse = False + + def parseImpl(self, instring, loc, doActions=True): + if col(loc, instring) != 1: + raise ParseException(instring, loc, "not found at line start") + return super().parseImpl(instring, loc, doActions) + + +class FollowedBy(ParseElementEnhance): + """Lookahead matching of the given parse expression. + ``FollowedBy`` does *not* advance the parsing position within + the input string, it only verifies that the specified parse + expression matches at the current position. ``FollowedBy`` + always returns a null token list. If any results names are defined + in the lookahead expression, those *will* be returned for access by + name. + + Example:: + + # use FollowedBy to match a label only if it is followed by a ':' + data_word = Word(alphas) + label = data_word + FollowedBy(':') + attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + + attr_expr[1, ...].parse_string("shape: SQUARE color: BLACK posn: upper left").pprint() + + prints:: + + [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']] + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + self.mayReturnEmpty = True + + def parseImpl(self, instring, loc, doActions=True): + # by using self._expr.parse and deleting the contents of the returned ParseResults list + # we keep any named results that were defined in the FollowedBy expression + _, ret = self.expr._parse(instring, loc, doActions=doActions) + del ret[:] + + return loc, ret + + +class PrecededBy(ParseElementEnhance): + """Lookbehind matching of the given parse expression. + ``PrecededBy`` does not advance the parsing position within the + input string, it only verifies that the specified parse expression + matches prior to the current position. ``PrecededBy`` always + returns a null token list, but if a results name is defined on the + given expression, it is returned. + + Parameters: + + - expr - expression that must match prior to the current parse + location + - retreat - (default= ``None``) - (int) maximum number of characters + to lookbehind prior to the current parse location + + If the lookbehind expression is a string, :class:`Literal`, + :class:`Keyword`, or a :class:`Word` or :class:`CharsNotIn` + with a specified exact or maximum length, then the retreat + parameter is not required. Otherwise, retreat must be specified to + give a maximum number of characters to look back from + the current parse position for a lookbehind match. + + Example:: + + # VB-style variable names with type prefixes + int_var = PrecededBy("#") + pyparsing_common.identifier + str_var = PrecededBy("$") + pyparsing_common.identifier + + """ + + def __init__( + self, expr: Union[ParserElement, str], retreat: typing.Optional[int] = None + ): + super().__init__(expr) + self.expr = self.expr().leave_whitespace() + self.mayReturnEmpty = True + self.mayIndexError = False + self.exact = False + if isinstance(expr, str_type): + retreat = len(expr) + self.exact = True + elif isinstance(expr, (Literal, Keyword)): + retreat = expr.matchLen + self.exact = True + elif isinstance(expr, (Word, CharsNotIn)) and expr.maxLen != _MAX_INT: + retreat = expr.maxLen + self.exact = True + elif isinstance(expr, PositionToken): + retreat = 0 + self.exact = True + self.retreat = retreat + self.errmsg = "not preceded by " + str(expr) + self.skipWhitespace = False + self.parseAction.append(lambda s, l, t: t.__delitem__(slice(None, None))) + + def parseImpl(self, instring, loc=0, doActions=True): + if self.exact: + if loc < self.retreat: + raise ParseException(instring, loc, self.errmsg) + start = loc - self.retreat + _, ret = self.expr._parse(instring, start) + else: + # retreat specified a maximum lookbehind window, iterate + test_expr = self.expr + StringEnd() + instring_slice = instring[max(0, loc - self.retreat) : loc] + last_expr = ParseException(instring, loc, self.errmsg) + for offset in range(1, min(loc, self.retreat + 1) + 1): + try: + # print('trying', offset, instring_slice, repr(instring_slice[loc - offset:])) + _, ret = test_expr._parse( + instring_slice, len(instring_slice) - offset + ) + except ParseBaseException as pbe: + last_expr = pbe + else: + break + else: + raise last_expr + return loc, ret + + +class Located(ParseElementEnhance): + """ + Decorates a returned token with its starting and ending + locations in the input string. + + This helper adds the following results names: + + - ``locn_start`` - location where matched expression begins + - ``locn_end`` - location where matched expression ends + - ``value`` - the actual parsed results + + Be careful if the input text contains ``<TAB>`` characters, you + may want to call :class:`ParserElement.parse_with_tabs` + + Example:: + + wd = Word(alphas) + for match in Located(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): + print(match) + + prints:: + + [0, ['ljsdf'], 5] + [8, ['lksdjjf'], 15] + [18, ['lkkjj'], 23] + + """ + + def parseImpl(self, instring, loc, doActions=True): + start = loc + loc, tokens = self.expr._parse(instring, start, doActions, callPreParse=False) + ret_tokens = ParseResults([start, tokens, loc]) + ret_tokens["locn_start"] = start + ret_tokens["value"] = tokens + ret_tokens["locn_end"] = loc + if self.resultsName: + # must return as a list, so that the name will be attached to the complete group + return loc, [ret_tokens] + else: + return loc, ret_tokens + + +class NotAny(ParseElementEnhance): + """ + Lookahead to disallow matching with the given parse expression. + ``NotAny`` does *not* advance the parsing position within the + input string, it only verifies that the specified parse expression + does *not* match at the current position. Also, ``NotAny`` does + *not* skip over leading whitespace. ``NotAny`` always returns + a null token list. May be constructed using the ``'~'`` operator. + + Example:: + + AND, OR, NOT = map(CaselessKeyword, "AND OR NOT".split()) + + # take care not to mistake keywords for identifiers + ident = ~(AND | OR | NOT) + Word(alphas) + boolean_term = Opt(NOT) + ident + + # very crude boolean expression - to support parenthesis groups and + # operation hierarchy, use infix_notation + boolean_expr = boolean_term + ((AND | OR) + boolean_term)[...] + + # integers that are followed by "." are actually floats + integer = Word(nums) + ~Char(".") + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + # do NOT use self.leave_whitespace(), don't want to propagate to exprs + # self.leave_whitespace() + self.skipWhitespace = False + + self.mayReturnEmpty = True + self.errmsg = "Found unwanted token, " + str(self.expr) + + def parseImpl(self, instring, loc, doActions=True): + if self.expr.can_parse_next(instring, loc): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + def _generateDefaultName(self): + return "~{" + str(self.expr) + "}" + + +class _MultipleMatch(ParseElementEnhance): + def __init__( + self, + expr: ParserElement, + stop_on: typing.Optional[Union[ParserElement, str]] = None, + *, + stopOn: typing.Optional[Union[ParserElement, str]] = None, + ): + super().__init__(expr) + stopOn = stopOn or stop_on + self.saveAsList = True + ender = stopOn + if isinstance(ender, str_type): + ender = self._literalStringClass(ender) + self.stopOn(ender) + + def stopOn(self, ender) -> ParserElement: + if isinstance(ender, str_type): + ender = self._literalStringClass(ender) + self.not_ender = ~ender if ender is not None else None + return self + + def parseImpl(self, instring, loc, doActions=True): + self_expr_parse = self.expr._parse + self_skip_ignorables = self._skipIgnorables + check_ender = self.not_ender is not None + if check_ender: + try_not_ender = self.not_ender.tryParse + + # must be at least one (but first see if we are the stopOn sentinel; + # if so, fail) + if check_ender: + try_not_ender(instring, loc) + loc, tokens = self_expr_parse(instring, loc, doActions) + try: + hasIgnoreExprs = not not self.ignoreExprs + while 1: + if check_ender: + try_not_ender(instring, loc) + if hasIgnoreExprs: + preloc = self_skip_ignorables(instring, loc) + else: + preloc = loc + loc, tmptokens = self_expr_parse(instring, preloc, doActions) + if tmptokens or tmptokens.haskeys(): + tokens += tmptokens + except (ParseException, IndexError): + pass + + return loc, tokens + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_ungrouped_named_tokens_in_collection + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in self.suppress_warnings_ + ): + for e in [self.expr] + self.expr.recurse(): + if ( + isinstance(e, ParserElement) + and e.resultsName + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in e.suppress_warnings_ + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "collides with {!r} on contained expression".format( + "warn_ungrouped_named_tokens_in_collection", + name, + type(self).__name__, + e.resultsName, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + +class OneOrMore(_MultipleMatch): + """ + Repetition of one or more of the given expression. + + Parameters: + - expr - expression that must match one or more times + - stop_on - (default= ``None``) - expression for a terminating sentinel + (only required if the sentinel would ordinarily match the repetition + expression) + + Example:: + + data_word = Word(alphas) + label = data_word + FollowedBy(':') + attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).set_parse_action(' '.join)) + + text = "shape: SQUARE posn: upper left color: BLACK" + attr_expr[1, ...].parse_string(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']] + + # use stop_on attribute for OneOrMore to avoid reading label string as part of the data + attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + OneOrMore(attr_expr).parse_string(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']] + + # could also be written as + (attr_expr * (1,)).parse_string(text).pprint() + """ + + def _generateDefaultName(self): + return "{" + str(self.expr) + "}..." + + +class ZeroOrMore(_MultipleMatch): + """ + Optional repetition of zero or more of the given expression. + + Parameters: + - ``expr`` - expression that must match zero or more times + - ``stop_on`` - expression for a terminating sentinel + (only required if the sentinel would ordinarily match the repetition + expression) - (default= ``None``) + + Example: similar to :class:`OneOrMore` + """ + + def __init__( + self, + expr: ParserElement, + stop_on: typing.Optional[Union[ParserElement, str]] = None, + *, + stopOn: typing.Optional[Union[ParserElement, str]] = None, + ): + super().__init__(expr, stopOn=stopOn or stop_on) + self.mayReturnEmpty = True + + def parseImpl(self, instring, loc, doActions=True): + try: + return super().parseImpl(instring, loc, doActions) + except (ParseException, IndexError): + return loc, ParseResults([], name=self.resultsName) + + def _generateDefaultName(self): + return "[" + str(self.expr) + "]..." + + +class _NullToken: + def __bool__(self): + return False + + def __str__(self): + return "" + + +class Opt(ParseElementEnhance): + """ + Optional matching of the given expression. + + Parameters: + - ``expr`` - expression that must match zero or more times + - ``default`` (optional) - value to be returned if the optional expression is not found. + + Example:: + + # US postal code can be a 5-digit zip, plus optional 4-digit qualifier + zip = Combine(Word(nums, exact=5) + Opt('-' + Word(nums, exact=4))) + zip.run_tests(''' + # traditional ZIP code + 12345 + + # ZIP+4 form + 12101-0001 + + # invalid ZIP + 98765- + ''') + + prints:: + + # traditional ZIP code + 12345 + ['12345'] + + # ZIP+4 form + 12101-0001 + ['12101-0001'] + + # invalid ZIP + 98765- + ^ + FAIL: Expected end of text (at char 5), (line:1, col:6) + """ + + __optionalNotMatched = _NullToken() + + def __init__( + self, expr: Union[ParserElement, str], default: Any = __optionalNotMatched + ): + super().__init__(expr, savelist=False) + self.saveAsList = self.expr.saveAsList + self.defaultValue = default + self.mayReturnEmpty = True + + def parseImpl(self, instring, loc, doActions=True): + self_expr = self.expr + try: + loc, tokens = self_expr._parse(instring, loc, doActions, callPreParse=False) + except (ParseException, IndexError): + default_value = self.defaultValue + if default_value is not self.__optionalNotMatched: + if self_expr.resultsName: + tokens = ParseResults([default_value]) + tokens[self_expr.resultsName] = default_value + else: + tokens = [default_value] + else: + tokens = [] + return loc, tokens + + def _generateDefaultName(self): + inner = str(self.expr) + # strip off redundant inner {}'s + while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": + inner = inner[1:-1] + return "[" + inner + "]" + + +Optional = Opt + + +class SkipTo(ParseElementEnhance): + """ + Token for skipping over all undefined text until the matched + expression is found. + + Parameters: + - ``expr`` - target expression marking the end of the data to be skipped + - ``include`` - if ``True``, the target expression is also parsed + (the skipped text and target expression are returned as a 2-element + list) (default= ``False``). + - ``ignore`` - (default= ``None``) used to define grammars (typically quoted strings and + comments) that might contain false matches to the target expression + - ``fail_on`` - (default= ``None``) define expressions that are not allowed to be + included in the skipped test; if found before the target expression is found, + the :class:`SkipTo` is not a match + + Example:: + + report = ''' + Outstanding Issues Report - 1 Jan 2000 + + # | Severity | Description | Days Open + -----+----------+-------------------------------------------+----------- + 101 | Critical | Intermittent system crash | 6 + 94 | Cosmetic | Spelling error on Login ('log|n') | 14 + 79 | Minor | System slow when running too many reports | 47 + ''' + integer = Word(nums) + SEP = Suppress('|') + # use SkipTo to simply match everything up until the next SEP + # - ignore quoted strings, so that a '|' character inside a quoted string does not match + # - parse action will call token.strip() for each matched token, i.e., the description body + string_data = SkipTo(SEP, ignore=quoted_string) + string_data.set_parse_action(token_map(str.strip)) + ticket_expr = (integer("issue_num") + SEP + + string_data("sev") + SEP + + string_data("desc") + SEP + + integer("days_open")) + + for tkt in ticket_expr.search_string(report): + print tkt.dump() + + prints:: + + ['101', 'Critical', 'Intermittent system crash', '6'] + - days_open: '6' + - desc: 'Intermittent system crash' + - issue_num: '101' + - sev: 'Critical' + ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14'] + - days_open: '14' + - desc: "Spelling error on Login ('log|n')" + - issue_num: '94' + - sev: 'Cosmetic' + ['79', 'Minor', 'System slow when running too many reports', '47'] + - days_open: '47' + - desc: 'System slow when running too many reports' + - issue_num: '79' + - sev: 'Minor' + """ + + def __init__( + self, + other: Union[ParserElement, str], + include: bool = False, + ignore: bool = None, + fail_on: typing.Optional[Union[ParserElement, str]] = None, + *, + failOn: Union[ParserElement, str] = None, + ): + super().__init__(other) + failOn = failOn or fail_on + self.ignoreExpr = ignore + self.mayReturnEmpty = True + self.mayIndexError = False + self.includeMatch = include + self.saveAsList = False + if isinstance(failOn, str_type): + self.failOn = self._literalStringClass(failOn) + else: + self.failOn = failOn + self.errmsg = "No match found for " + str(self.expr) + + def parseImpl(self, instring, loc, doActions=True): + startloc = loc + instrlen = len(instring) + self_expr_parse = self.expr._parse + self_failOn_canParseNext = ( + self.failOn.canParseNext if self.failOn is not None else None + ) + self_ignoreExpr_tryParse = ( + self.ignoreExpr.tryParse if self.ignoreExpr is not None else None + ) + + tmploc = loc + while tmploc <= instrlen: + if self_failOn_canParseNext is not None: + # break if failOn expression matches + if self_failOn_canParseNext(instring, tmploc): + break + + if self_ignoreExpr_tryParse is not None: + # advance past ignore expressions + while 1: + try: + tmploc = self_ignoreExpr_tryParse(instring, tmploc) + except ParseBaseException: + break + + try: + self_expr_parse(instring, tmploc, doActions=False, callPreParse=False) + except (ParseException, IndexError): + # no match, advance loc in string + tmploc += 1 + else: + # matched skipto expr, done + break + + else: + # ran off the end of the input string without matching skipto expr, fail + raise ParseException(instring, loc, self.errmsg, self) + + # build up return values + loc = tmploc + skiptext = instring[startloc:loc] + skipresult = ParseResults(skiptext) + + if self.includeMatch: + loc, mat = self_expr_parse(instring, loc, doActions, callPreParse=False) + skipresult += mat + + return loc, skipresult + + +class Forward(ParseElementEnhance): + """ + Forward declaration of an expression to be defined later - + used for recursive grammars, such as algebraic infix notation. + When the expression is known, it is assigned to the ``Forward`` + variable using the ``'<<'`` operator. + + Note: take care when assigning to ``Forward`` not to overlook + precedence of operators. + + Specifically, ``'|'`` has a lower precedence than ``'<<'``, so that:: + + fwd_expr << a | b | c + + will actually be evaluated as:: + + (fwd_expr << a) | b | c + + thereby leaving b and c out as parseable alternatives. It is recommended that you + explicitly group the values inserted into the ``Forward``:: + + fwd_expr << (a | b | c) + + Converting to use the ``'<<='`` operator instead will avoid this problem. + + See :class:`ParseResults.pprint` for an example of a recursive + parser created using ``Forward``. + """ + + def __init__(self, other: typing.Optional[Union[ParserElement, str]] = None): + self.caller_frame = traceback.extract_stack(limit=2)[0] + super().__init__(other, savelist=False) + self.lshift_line = None + + def __lshift__(self, other): + if hasattr(self, "caller_frame"): + del self.caller_frame + if isinstance(other, str_type): + other = self._literalStringClass(other) + self.expr = other + self.mayIndexError = self.expr.mayIndexError + self.mayReturnEmpty = self.expr.mayReturnEmpty + self.set_whitespace_chars( + self.expr.whiteChars, copy_defaults=self.expr.copyDefaultWhiteChars + ) + self.skipWhitespace = self.expr.skipWhitespace + self.saveAsList = self.expr.saveAsList + self.ignoreExprs.extend(self.expr.ignoreExprs) + self.lshift_line = traceback.extract_stack(limit=2)[-2] + return self + + def __ilshift__(self, other): + return self << other + + def __or__(self, other): + caller_line = traceback.extract_stack(limit=2)[-2] + if ( + __diag__.warn_on_match_first_with_lshift_operator + and caller_line == self.lshift_line + and Diagnostics.warn_on_match_first_with_lshift_operator + not in self.suppress_warnings_ + ): + warnings.warn( + "using '<<' operator with '|' is probably an error, use '<<='", + stacklevel=2, + ) + ret = super().__or__(other) + return ret + + def __del__(self): + # see if we are getting dropped because of '=' reassignment of var instead of '<<=' or '<<' + if ( + self.expr is None + and __diag__.warn_on_assignment_to_Forward + and Diagnostics.warn_on_assignment_to_Forward not in self.suppress_warnings_ + ): + warnings.warn_explicit( + "Forward defined here but no expression attached later using '<<=' or '<<'", + UserWarning, + filename=self.caller_frame.filename, + lineno=self.caller_frame.lineno, + ) + + def parseImpl(self, instring, loc, doActions=True): + if ( + self.expr is None + and __diag__.warn_on_parse_using_empty_Forward + and Diagnostics.warn_on_parse_using_empty_Forward + not in self.suppress_warnings_ + ): + # walk stack until parse_string, scan_string, search_string, or transform_string is found + parse_fns = [ + "parse_string", + "scan_string", + "search_string", + "transform_string", + ] + tb = traceback.extract_stack(limit=200) + for i, frm in enumerate(reversed(tb), start=1): + if frm.name in parse_fns: + stacklevel = i + 1 + break + else: + stacklevel = 2 + warnings.warn( + "Forward expression was never assigned a value, will not parse any input", + stacklevel=stacklevel, + ) + if not ParserElement._left_recursion_enabled: + return super().parseImpl(instring, loc, doActions) + # ## Bounded Recursion algorithm ## + # Recursion only needs to be processed at ``Forward`` elements, since they are + # the only ones that can actually refer to themselves. The general idea is + # to handle recursion stepwise: We start at no recursion, then recurse once, + # recurse twice, ..., until more recursion offers no benefit (we hit the bound). + # + # The "trick" here is that each ``Forward`` gets evaluated in two contexts + # - to *match* a specific recursion level, and + # - to *search* the bounded recursion level + # and the two run concurrently. The *search* must *match* each recursion level + # to find the best possible match. This is handled by a memo table, which + # provides the previous match to the next level match attempt. + # + # See also "Left Recursion in Parsing Expression Grammars", Medeiros et al. + # + # There is a complication since we not only *parse* but also *transform* via + # actions: We do not want to run the actions too often while expanding. Thus, + # we expand using `doActions=False` and only run `doActions=True` if the next + # recursion level is acceptable. + with ParserElement.recursion_lock: + memo = ParserElement.recursion_memos + try: + # we are parsing at a specific recursion expansion - use it as-is + prev_loc, prev_result = memo[loc, self, doActions] + if isinstance(prev_result, Exception): + raise prev_result + return prev_loc, prev_result.copy() + except KeyError: + act_key = (loc, self, True) + peek_key = (loc, self, False) + # we are searching for the best recursion expansion - keep on improving + # both `doActions` cases must be tracked separately here! + prev_loc, prev_peek = memo[peek_key] = ( + loc - 1, + ParseException( + instring, loc, "Forward recursion without base case", self + ), + ) + if doActions: + memo[act_key] = memo[peek_key] + while True: + try: + new_loc, new_peek = super().parseImpl(instring, loc, False) + except ParseException: + # we failed before getting any match – do not hide the error + if isinstance(prev_peek, Exception): + raise + new_loc, new_peek = prev_loc, prev_peek + # the match did not get better: we are done + if new_loc <= prev_loc: + if doActions: + # replace the match for doActions=False as well, + # in case the action did backtrack + prev_loc, prev_result = memo[peek_key] = memo[act_key] + del memo[peek_key], memo[act_key] + return prev_loc, prev_result.copy() + del memo[peek_key] + return prev_loc, prev_peek.copy() + # the match did get better: see if we can improve further + else: + if doActions: + try: + memo[act_key] = super().parseImpl(instring, loc, True) + except ParseException as e: + memo[peek_key] = memo[act_key] = (new_loc, e) + raise + prev_loc, prev_peek = memo[peek_key] = new_loc, new_peek + + def leave_whitespace(self, recursive: bool = True) -> ParserElement: + self.skipWhitespace = False + return self + + def ignore_whitespace(self, recursive: bool = True) -> ParserElement: + self.skipWhitespace = True + return self + + def streamline(self) -> ParserElement: + if not self.streamlined: + self.streamlined = True + if self.expr is not None: + self.expr.streamline() + return self + + def validate(self, validateTrace=None) -> None: + if validateTrace is None: + validateTrace = [] + + if self not in validateTrace: + tmp = validateTrace[:] + [self] + if self.expr is not None: + self.expr.validate(tmp) + self._checkRecursion([]) + + def _generateDefaultName(self): + # Avoid infinite recursion by setting a temporary _defaultName + self._defaultName = ": ..." + + # Use the string representation of main expression. + retString = "..." + try: + if self.expr is not None: + retString = str(self.expr)[:1000] + else: + retString = "None" + finally: + return self.__class__.__name__ + ": " + retString + + def copy(self) -> ParserElement: + if self.expr is not None: + return super().copy() + else: + ret = Forward() + ret <<= self + return ret + + def _setResultsName(self, name, list_all_matches=False): + if ( + __diag__.warn_name_set_on_empty_Forward + and Diagnostics.warn_name_set_on_empty_Forward + not in self.suppress_warnings_ + ): + if self.expr is None: + warnings.warn( + "{}: setting results name {!r} on {} expression " + "that has no contained expression".format( + "warn_name_set_on_empty_Forward", name, type(self).__name__ + ), + stacklevel=3, + ) + + return super()._setResultsName(name, list_all_matches) + + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class TokenConverter(ParseElementEnhance): + """ + Abstract subclass of :class:`ParseExpression`, for converting parsed results. + """ + + def __init__(self, expr: Union[ParserElement, str], savelist=False): + super().__init__(expr) # , savelist) + self.saveAsList = False + + +class Combine(TokenConverter): + """Converter to concatenate all matching tokens to a single string. + By default, the matching patterns must also be contiguous in the + input string; this can be disabled by specifying + ``'adjacent=False'`` in the constructor. + + Example:: + + real = Word(nums) + '.' + Word(nums) + print(real.parse_string('3.1416')) # -> ['3', '.', '1416'] + # will also erroneously match the following + print(real.parse_string('3. 1416')) # -> ['3', '.', '1416'] + + real = Combine(Word(nums) + '.' + Word(nums)) + print(real.parse_string('3.1416')) # -> ['3.1416'] + # no match when there are internal spaces + print(real.parse_string('3. 1416')) # -> Exception: Expected W:(0123...) + """ + + def __init__( + self, + expr: ParserElement, + join_string: str = "", + adjacent: bool = True, + *, + joinString: typing.Optional[str] = None, + ): + super().__init__(expr) + joinString = joinString if joinString is not None else join_string + # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself + if adjacent: + self.leave_whitespace() + self.adjacent = adjacent + self.skipWhitespace = True + self.joinString = joinString + self.callPreparse = True + + def ignore(self, other) -> ParserElement: + if self.adjacent: + ParserElement.ignore(self, other) + else: + super().ignore(other) + return self + + def postParse(self, instring, loc, tokenlist): + retToks = tokenlist.copy() + del retToks[:] + retToks += ParseResults( + ["".join(tokenlist._asStringList(self.joinString))], modal=self.modalResults + ) + + if self.resultsName and retToks.haskeys(): + return [retToks] + else: + return retToks + + +class Group(TokenConverter): + """Converter to return the matched tokens as a list - useful for + returning tokens of :class:`ZeroOrMore` and :class:`OneOrMore` expressions. + + The optional ``aslist`` argument when set to True will return the + parsed tokens as a Python list instead of a pyparsing ParseResults. + + Example:: + + ident = Word(alphas) + num = Word(nums) + term = ident | num + func = ident + Opt(delimited_list(term)) + print(func.parse_string("fn a, b, 100")) + # -> ['fn', 'a', 'b', '100'] + + func = ident + Group(Opt(delimited_list(term))) + print(func.parse_string("fn a, b, 100")) + # -> ['fn', ['a', 'b', '100']] + """ + + def __init__(self, expr: ParserElement, aslist: bool = False): + super().__init__(expr) + self.saveAsList = True + self._asPythonList = aslist + + def postParse(self, instring, loc, tokenlist): + if self._asPythonList: + return ParseResults.List( + tokenlist.asList() + if isinstance(tokenlist, ParseResults) + else list(tokenlist) + ) + else: + return [tokenlist] + + +class Dict(TokenConverter): + """Converter to return a repetitive expression as a list, but also + as a dictionary. Each element can also be referenced using the first + token in the expression as its key. Useful for tabular report + scraping when the first column can be used as a item key. + + The optional ``asdict`` argument when set to True will return the + parsed tokens as a Python dict instead of a pyparsing ParseResults. + + Example:: + + data_word = Word(alphas) + label = data_word + FollowedBy(':') + + text = "shape: SQUARE posn: upper left color: light blue texture: burlap" + attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + + # print attributes as plain groups + print(attr_expr[1, ...].parse_string(text).dump()) + + # instead of OneOrMore(expr), parse using Dict(Group(expr)[1, ...]) - Dict will auto-assign names + result = Dict(Group(attr_expr)[1, ...]).parse_string(text) + print(result.dump()) + + # access named fields as dict entries, or output as dict + print(result['shape']) + print(result.as_dict()) + + prints:: + + ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap'] + [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] + - color: 'light blue' + - posn: 'upper left' + - shape: 'SQUARE' + - texture: 'burlap' + SQUARE + {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'} + + See more examples at :class:`ParseResults` of accessing fields by results name. + """ + + def __init__(self, expr: ParserElement, asdict: bool = False): + super().__init__(expr) + self.saveAsList = True + self._asPythonDict = asdict + + def postParse(self, instring, loc, tokenlist): + for i, tok in enumerate(tokenlist): + if len(tok) == 0: + continue + + ikey = tok[0] + if isinstance(ikey, int): + ikey = str(ikey).strip() + + if len(tok) == 1: + tokenlist[ikey] = _ParseResultsWithOffset("", i) + + elif len(tok) == 2 and not isinstance(tok[1], ParseResults): + tokenlist[ikey] = _ParseResultsWithOffset(tok[1], i) + + else: + try: + dictvalue = tok.copy() # ParseResults(i) + except Exception: + exc = TypeError( + "could not extract dict values from parsed results" + " - Dict expression must contain Grouped expressions" + ) + raise exc from None + + del dictvalue[0] + + if len(dictvalue) != 1 or ( + isinstance(dictvalue, ParseResults) and dictvalue.haskeys() + ): + tokenlist[ikey] = _ParseResultsWithOffset(dictvalue, i) + else: + tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0], i) + + if self._asPythonDict: + return [tokenlist.as_dict()] if self.resultsName else tokenlist.as_dict() + else: + return [tokenlist] if self.resultsName else tokenlist + + +class Suppress(TokenConverter): + """Converter for ignoring the results of a parsed expression. + + Example:: + + source = "a, b, c,d" + wd = Word(alphas) + wd_list1 = wd + (',' + wd)[...] + print(wd_list1.parse_string(source)) + + # often, delimiters that are useful during parsing are just in the + # way afterward - use Suppress to keep them out of the parsed output + wd_list2 = wd + (Suppress(',') + wd)[...] + print(wd_list2.parse_string(source)) + + # Skipped text (using '...') can be suppressed as well + source = "lead in START relevant text END trailing text" + start_marker = Keyword("START") + end_marker = Keyword("END") + find_body = Suppress(...) + start_marker + ... + end_marker + print(find_body.parse_string(source) + + prints:: + + ['a', ',', 'b', ',', 'c', ',', 'd'] + ['a', 'b', 'c', 'd'] + ['START', 'relevant text ', 'END'] + + (See also :class:`delimited_list`.) + """ + + def __init__(self, expr: Union[ParserElement, str], savelist: bool = False): + if expr is ...: + expr = _PendingSkip(NoMatch()) + super().__init__(expr) + + def __add__(self, other) -> "ParserElement": + if isinstance(self.expr, _PendingSkip): + return Suppress(SkipTo(other)) + other + else: + return super().__add__(other) + + def __sub__(self, other) -> "ParserElement": + if isinstance(self.expr, _PendingSkip): + return Suppress(SkipTo(other)) - other + else: + return super().__sub__(other) + + def postParse(self, instring, loc, tokenlist): + return [] + + def suppress(self) -> ParserElement: + return self + + +def trace_parse_action(f: ParseAction) -> ParseAction: + """Decorator for debugging parse actions. + + When the parse action is called, this decorator will print + ``">> entering method-name(line:<current_source_line>, <parse_location>, <matched_tokens>)"``. + When the parse action completes, the decorator will print + ``"<<"`` followed by the returned value, or any exception that the parse action raised. + + Example:: + + wd = Word(alphas) + + @trace_parse_action + def remove_duplicate_chars(tokens): + return ''.join(sorted(set(''.join(tokens)))) + + wds = wd[1, ...].set_parse_action(remove_duplicate_chars) + print(wds.parse_string("slkdjs sld sldd sdlf sdljf")) + + prints:: + + >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {})) + <<leaving remove_duplicate_chars (ret: 'dfjkls') + ['dfjkls'] + """ + f = _trim_arity(f) + + def z(*paArgs): + thisFunc = f.__name__ + s, l, t = paArgs[-3:] + if len(paArgs) > 3: + thisFunc = paArgs[0].__class__.__name__ + "." + thisFunc + sys.stderr.write( + ">>entering {}(line: {!r}, {}, {!r})\n".format(thisFunc, line(l, s), l, t) + ) + try: + ret = f(*paArgs) + except Exception as exc: + sys.stderr.write("<<leaving {} (exception: {})\n".format(thisFunc, exc)) + raise + sys.stderr.write("<<leaving {} (ret: {!r})\n".format(thisFunc, ret)) + return ret + + z.__name__ = f.__name__ + return z + + +# convenience constants for positional expressions +empty = Empty().set_name("empty") +line_start = LineStart().set_name("line_start") +line_end = LineEnd().set_name("line_end") +string_start = StringStart().set_name("string_start") +string_end = StringEnd().set_name("string_end") + +_escapedPunc = Word(_bslash, r"\[]-*.$+^?()~ ", exact=2).set_parse_action( + lambda s, l, t: t[0][1] +) +_escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").set_parse_action( + lambda s, l, t: chr(int(t[0].lstrip(r"\0x"), 16)) +) +_escapedOctChar = Regex(r"\\0[0-7]+").set_parse_action( + lambda s, l, t: chr(int(t[0][1:], 8)) +) +_singleChar = ( + _escapedPunc | _escapedHexChar | _escapedOctChar | CharsNotIn(r"\]", exact=1) +) +_charRange = Group(_singleChar + Suppress("-") + _singleChar) +_reBracketExpr = ( + Literal("[") + + Opt("^").set_results_name("negate") + + Group(OneOrMore(_charRange | _singleChar)).set_results_name("body") + + "]" +) + + +def srange(s: str) -> str: + r"""Helper to easily define string ranges for use in :class:`Word` + construction. Borrows syntax from regexp ``'[]'`` string range + definitions:: + + srange("[0-9]") -> "0123456789" + srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" + srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" + + The input string must be enclosed in []'s, and the returned string + is the expanded character set joined into a single string. The + values enclosed in the []'s may be: + + - a single character + - an escaped character with a leading backslash (such as ``\-`` + or ``\]``) + - an escaped hex character with a leading ``'\x'`` + (``\x21``, which is a ``'!'`` character) (``\0x##`` + is also supported for backwards compatibility) + - an escaped octal character with a leading ``'\0'`` + (``\041``, which is a ``'!'`` character) + - a range of any of the above, separated by a dash (``'a-z'``, + etc.) + - any combination of the above (``'aeiouy'``, + ``'a-zA-Z0-9_$'``, etc.) + """ + _expanded = ( + lambda p: p + if not isinstance(p, ParseResults) + else "".join(chr(c) for c in range(ord(p[0]), ord(p[1]) + 1)) + ) + try: + return "".join(_expanded(part) for part in _reBracketExpr.parse_string(s).body) + except Exception: + return "" + + +def token_map(func, *args) -> ParseAction: + """Helper to define a parse action by mapping a function to all + elements of a :class:`ParseResults` list. If any additional args are passed, + they are forwarded to the given function as additional arguments + after the token, as in + ``hex_integer = Word(hexnums).set_parse_action(token_map(int, 16))``, + which will convert the parsed data to an integer using base 16. + + Example (compare the last to example in :class:`ParserElement.transform_string`:: + + hex_ints = Word(hexnums)[1, ...].set_parse_action(token_map(int, 16)) + hex_ints.run_tests(''' + 00 11 22 aa FF 0a 0d 1a + ''') + + upperword = Word(alphas).set_parse_action(token_map(str.upper)) + upperword[1, ...].run_tests(''' + my kingdom for a horse + ''') + + wd = Word(alphas).set_parse_action(token_map(str.title)) + wd[1, ...].set_parse_action(' '.join).run_tests(''' + now is the winter of our discontent made glorious summer by this sun of york + ''') + + prints:: + + 00 11 22 aa FF 0a 0d 1a + [0, 17, 34, 170, 255, 10, 13, 26] + + my kingdom for a horse + ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE'] + + now is the winter of our discontent made glorious summer by this sun of york + ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York'] + """ + + def pa(s, l, t): + return [func(tokn, *args) for tokn in t] + + func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) + pa.__name__ = func_name + + return pa + + +def autoname_elements() -> None: + """ + Utility to simplify mass-naming of parser elements, for + generating railroad diagram with named subdiagrams. + """ + for name, var in sys._getframe().f_back.f_locals.items(): + if isinstance(var, ParserElement) and not var.customName: + var.set_name(name) + + +dbl_quoted_string = Combine( + Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"' +).set_name("string enclosed in double quotes") + +sgl_quoted_string = Combine( + Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'" +).set_name("string enclosed in single quotes") + +quoted_string = Combine( + Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"' + | Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'" +).set_name("quotedString using single or double quotes") + +unicode_string = Combine("u" + quoted_string.copy()).set_name("unicode string literal") + + +alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") +punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") + +# build list of built-in expressions, for future reference if a global default value +# gets updated +_builtin_exprs: List[ParserElement] = [ + v for v in vars().values() if isinstance(v, ParserElement) +] + +# backward compatibility names +tokenMap = token_map +conditionAsParseAction = condition_as_parse_action +nullDebugAction = null_debug_action +sglQuotedString = sgl_quoted_string +dblQuotedString = dbl_quoted_string +quotedString = quoted_string +unicodeString = unicode_string +lineStart = line_start +lineEnd = line_end +stringStart = string_start +stringEnd = string_end +traceParseAction = trace_parse_action diff --git a/pkg_resources/_vendor/pyparsing/diagram/__init__.py b/pkg_resources/_vendor/pyparsing/diagram/__init__.py new file mode 100644 index 00000000..89864475 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/diagram/__init__.py @@ -0,0 +1,642 @@ +import railroad +import pyparsing +import typing +from typing import ( + List, + NamedTuple, + Generic, + TypeVar, + Dict, + Callable, + Set, + Iterable, +) +from jinja2 import Template +from io import StringIO +import inspect + + +jinja2_template_source = """\ +<!DOCTYPE html> +<html> +<head> + {% if not head %} + <style type="text/css"> + .railroad-heading { + font-family: monospace; + } + </style> + {% else %} + {{ head | safe }} + {% endif %} +</head> +<body> +{{ body | safe }} +{% for diagram in diagrams %} + <div class="railroad-group"> + <h1 class="railroad-heading">{{ diagram.title }}</h1> + <div class="railroad-description">{{ diagram.text }}</div> + <div class="railroad-svg"> + {{ diagram.svg }} + </div> + </div> +{% endfor %} +</body> +</html> +""" + +template = Template(jinja2_template_source) + +# Note: ideally this would be a dataclass, but we're supporting Python 3.5+ so we can't do this yet +NamedDiagram = NamedTuple( + "NamedDiagram", + [("name", str), ("diagram", typing.Optional[railroad.DiagramItem]), ("index", int)], +) +""" +A simple structure for associating a name with a railroad diagram +""" + +T = TypeVar("T") + + +class EachItem(railroad.Group): + """ + Custom railroad item to compose a: + - Group containing a + - OneOrMore containing a + - Choice of the elements in the Each + with the group label indicating that all must be matched + """ + + all_label = "[ALL]" + + def __init__(self, *items): + choice_item = railroad.Choice(len(items) - 1, *items) + one_or_more_item = railroad.OneOrMore(item=choice_item) + super().__init__(one_or_more_item, label=self.all_label) + + +class AnnotatedItem(railroad.Group): + """ + Simple subclass of Group that creates an annotation label + """ + + def __init__(self, label: str, item): + super().__init__(item=item, label="[{}]".format(label) if label else label) + + +class EditablePartial(Generic[T]): + """ + Acts like a functools.partial, but can be edited. In other words, it represents a type that hasn't yet been + constructed. + """ + + # We need this here because the railroad constructors actually transform the data, so can't be called until the + # entire tree is assembled + + def __init__(self, func: Callable[..., T], args: list, kwargs: dict): + self.func = func + self.args = args + self.kwargs = kwargs + + @classmethod + def from_call(cls, func: Callable[..., T], *args, **kwargs) -> "EditablePartial[T]": + """ + If you call this function in the same way that you would call the constructor, it will store the arguments + as you expect. For example EditablePartial.from_call(Fraction, 1, 3)() == Fraction(1, 3) + """ + return EditablePartial(func=func, args=list(args), kwargs=kwargs) + + @property + def name(self): + return self.kwargs["name"] + + def __call__(self) -> T: + """ + Evaluate the partial and return the result + """ + args = self.args.copy() + kwargs = self.kwargs.copy() + + # This is a helpful hack to allow you to specify varargs parameters (e.g. *args) as keyword args (e.g. + # args=['list', 'of', 'things']) + arg_spec = inspect.getfullargspec(self.func) + if arg_spec.varargs in self.kwargs: + args += kwargs.pop(arg_spec.varargs) + + return self.func(*args, **kwargs) + + +def railroad_to_html(diagrams: List[NamedDiagram], **kwargs) -> str: + """ + Given a list of NamedDiagram, produce a single HTML string that visualises those diagrams + :params kwargs: kwargs to be passed in to the template + """ + data = [] + for diagram in diagrams: + if diagram.diagram is None: + continue + io = StringIO() + diagram.diagram.writeSvg(io.write) + title = diagram.name + if diagram.index == 0: + title += " (root)" + data.append({"title": title, "text": "", "svg": io.getvalue()}) + + return template.render(diagrams=data, **kwargs) + + +def resolve_partial(partial: "EditablePartial[T]") -> T: + """ + Recursively resolves a collection of Partials into whatever type they are + """ + if isinstance(partial, EditablePartial): + partial.args = resolve_partial(partial.args) + partial.kwargs = resolve_partial(partial.kwargs) + return partial() + elif isinstance(partial, list): + return [resolve_partial(x) for x in partial] + elif isinstance(partial, dict): + return {key: resolve_partial(x) for key, x in partial.items()} + else: + return partial + + +def to_railroad( + element: pyparsing.ParserElement, + diagram_kwargs: typing.Optional[dict] = None, + vertical: int = 3, + show_results_names: bool = False, + show_groups: bool = False, +) -> List[NamedDiagram]: + """ + Convert a pyparsing element tree into a list of diagrams. This is the recommended entrypoint to diagram + creation if you want to access the Railroad tree before it is converted to HTML + :param element: base element of the parser being diagrammed + :param diagram_kwargs: kwargs to pass to the Diagram() constructor + :param vertical: (optional) - int - limit at which number of alternatives should be + shown vertically instead of horizontally + :param show_results_names - bool to indicate whether results name annotations should be + included in the diagram + :param show_groups - bool to indicate whether groups should be highlighted with an unlabeled + surrounding box + """ + # Convert the whole tree underneath the root + lookup = ConverterState(diagram_kwargs=diagram_kwargs or {}) + _to_diagram_element( + element, + lookup=lookup, + parent=None, + vertical=vertical, + show_results_names=show_results_names, + show_groups=show_groups, + ) + + root_id = id(element) + # Convert the root if it hasn't been already + if root_id in lookup: + if not element.customName: + lookup[root_id].name = "" + lookup[root_id].mark_for_extraction(root_id, lookup, force=True) + + # Now that we're finished, we can convert from intermediate structures into Railroad elements + diags = list(lookup.diagrams.values()) + if len(diags) > 1: + # collapse out duplicate diags with the same name + seen = set() + deduped_diags = [] + for d in diags: + # don't extract SkipTo elements, they are uninformative as subdiagrams + if d.name == "...": + continue + if d.name is not None and d.name not in seen: + seen.add(d.name) + deduped_diags.append(d) + resolved = [resolve_partial(partial) for partial in deduped_diags] + else: + # special case - if just one diagram, always display it, even if + # it has no name + resolved = [resolve_partial(partial) for partial in diags] + return sorted(resolved, key=lambda diag: diag.index) + + +def _should_vertical( + specification: int, exprs: Iterable[pyparsing.ParserElement] +) -> bool: + """ + Returns true if we should return a vertical list of elements + """ + if specification is None: + return False + else: + return len(_visible_exprs(exprs)) >= specification + + +class ElementState: + """ + State recorded for an individual pyparsing Element + """ + + # Note: this should be a dataclass, but we have to support Python 3.5 + def __init__( + self, + element: pyparsing.ParserElement, + converted: EditablePartial, + parent: EditablePartial, + number: int, + name: str = None, + parent_index: typing.Optional[int] = None, + ): + #: The pyparsing element that this represents + self.element: pyparsing.ParserElement = element + #: The name of the element + self.name: typing.Optional[str] = name + #: The output Railroad element in an unconverted state + self.converted: EditablePartial = converted + #: The parent Railroad element, which we store so that we can extract this if it's duplicated + self.parent: EditablePartial = parent + #: The order in which we found this element, used for sorting diagrams if this is extracted into a diagram + self.number: int = number + #: The index of this inside its parent + self.parent_index: typing.Optional[int] = parent_index + #: If true, we should extract this out into a subdiagram + self.extract: bool = False + #: If true, all of this element's children have been filled out + self.complete: bool = False + + def mark_for_extraction( + self, el_id: int, state: "ConverterState", name: str = None, force: bool = False + ): + """ + Called when this instance has been seen twice, and thus should eventually be extracted into a sub-diagram + :param el_id: id of the element + :param state: element/diagram state tracker + :param name: name to use for this element's text + :param force: If true, force extraction now, regardless of the state of this. Only useful for extracting the + root element when we know we're finished + """ + self.extract = True + + # Set the name + if not self.name: + if name: + # Allow forcing a custom name + self.name = name + elif self.element.customName: + self.name = self.element.customName + else: + self.name = "" + + # Just because this is marked for extraction doesn't mean we can do it yet. We may have to wait for children + # to be added + # Also, if this is just a string literal etc, don't bother extracting it + if force or (self.complete and _worth_extracting(self.element)): + state.extract_into_diagram(el_id) + + +class ConverterState: + """ + Stores some state that persists between recursions into the element tree + """ + + def __init__(self, diagram_kwargs: typing.Optional[dict] = None): + #: A dictionary mapping ParserElements to state relating to them + self._element_diagram_states: Dict[int, ElementState] = {} + #: A dictionary mapping ParserElement IDs to subdiagrams generated from them + self.diagrams: Dict[int, EditablePartial[NamedDiagram]] = {} + #: The index of the next unnamed element + self.unnamed_index: int = 1 + #: The index of the next element. This is used for sorting + self.index: int = 0 + #: Shared kwargs that are used to customize the construction of diagrams + self.diagram_kwargs: dict = diagram_kwargs or {} + self.extracted_diagram_names: Set[str] = set() + + def __setitem__(self, key: int, value: ElementState): + self._element_diagram_states[key] = value + + def __getitem__(self, key: int) -> ElementState: + return self._element_diagram_states[key] + + def __delitem__(self, key: int): + del self._element_diagram_states[key] + + def __contains__(self, key: int): + return key in self._element_diagram_states + + def generate_unnamed(self) -> int: + """ + Generate a number used in the name of an otherwise unnamed diagram + """ + self.unnamed_index += 1 + return self.unnamed_index + + def generate_index(self) -> int: + """ + Generate a number used to index a diagram + """ + self.index += 1 + return self.index + + def extract_into_diagram(self, el_id: int): + """ + Used when we encounter the same token twice in the same tree. When this + happens, we replace all instances of that token with a terminal, and + create a new subdiagram for the token + """ + position = self[el_id] + + # Replace the original definition of this element with a regular block + if position.parent: + ret = EditablePartial.from_call(railroad.NonTerminal, text=position.name) + if "item" in position.parent.kwargs: + position.parent.kwargs["item"] = ret + elif "items" in position.parent.kwargs: + position.parent.kwargs["items"][position.parent_index] = ret + + # If the element we're extracting is a group, skip to its content but keep the title + if position.converted.func == railroad.Group: + content = position.converted.kwargs["item"] + else: + content = position.converted + + self.diagrams[el_id] = EditablePartial.from_call( + NamedDiagram, + name=position.name, + diagram=EditablePartial.from_call( + railroad.Diagram, content, **self.diagram_kwargs + ), + index=position.number, + ) + + del self[el_id] + + +def _worth_extracting(element: pyparsing.ParserElement) -> bool: + """ + Returns true if this element is worth having its own sub-diagram. Simply, if any of its children + themselves have children, then its complex enough to extract + """ + children = element.recurse() + return any(child.recurse() for child in children) + + +def _apply_diagram_item_enhancements(fn): + """ + decorator to ensure enhancements to a diagram item (such as results name annotations) + get applied on return from _to_diagram_element (we do this since there are several + returns in _to_diagram_element) + """ + + def _inner( + element: pyparsing.ParserElement, + parent: typing.Optional[EditablePartial], + lookup: ConverterState = None, + vertical: int = None, + index: int = 0, + name_hint: str = None, + show_results_names: bool = False, + show_groups: bool = False, + ) -> typing.Optional[EditablePartial]: + + ret = fn( + element, + parent, + lookup, + vertical, + index, + name_hint, + show_results_names, + show_groups, + ) + + # apply annotation for results name, if present + if show_results_names and ret is not None: + element_results_name = element.resultsName + if element_results_name: + # add "*" to indicate if this is a "list all results" name + element_results_name += "" if element.modalResults else "*" + ret = EditablePartial.from_call( + railroad.Group, item=ret, label=element_results_name + ) + + return ret + + return _inner + + +def _visible_exprs(exprs: Iterable[pyparsing.ParserElement]): + non_diagramming_exprs = ( + pyparsing.ParseElementEnhance, + pyparsing.PositionToken, + pyparsing.And._ErrorStop, + ) + return [ + e + for e in exprs + if not (e.customName or e.resultsName or isinstance(e, non_diagramming_exprs)) + ] + + +@_apply_diagram_item_enhancements +def _to_diagram_element( + element: pyparsing.ParserElement, + parent: typing.Optional[EditablePartial], + lookup: ConverterState = None, + vertical: int = None, + index: int = 0, + name_hint: str = None, + show_results_names: bool = False, + show_groups: bool = False, +) -> typing.Optional[EditablePartial]: + """ + Recursively converts a PyParsing Element to a railroad Element + :param lookup: The shared converter state that keeps track of useful things + :param index: The index of this element within the parent + :param parent: The parent of this element in the output tree + :param vertical: Controls at what point we make a list of elements vertical. If this is an integer (the default), + it sets the threshold of the number of items before we go vertical. If True, always go vertical, if False, never + do so + :param name_hint: If provided, this will override the generated name + :param show_results_names: bool flag indicating whether to add annotations for results names + :returns: The converted version of the input element, but as a Partial that hasn't yet been constructed + :param show_groups: bool flag indicating whether to show groups using bounding box + """ + exprs = element.recurse() + name = name_hint or element.customName or element.__class__.__name__ + + # Python's id() is used to provide a unique identifier for elements + el_id = id(element) + + element_results_name = element.resultsName + + # Here we basically bypass processing certain wrapper elements if they contribute nothing to the diagram + if not element.customName: + if isinstance( + element, + ( + # pyparsing.TokenConverter, + # pyparsing.Forward, + pyparsing.Located, + ), + ): + # However, if this element has a useful custom name, and its child does not, we can pass it on to the child + if exprs: + if not exprs[0].customName: + propagated_name = name + else: + propagated_name = None + + return _to_diagram_element( + element.expr, + parent=parent, + lookup=lookup, + vertical=vertical, + index=index, + name_hint=propagated_name, + show_results_names=show_results_names, + show_groups=show_groups, + ) + + # If the element isn't worth extracting, we always treat it as the first time we say it + if _worth_extracting(element): + if el_id in lookup: + # If we've seen this element exactly once before, we are only just now finding out that it's a duplicate, + # so we have to extract it into a new diagram. + looked_up = lookup[el_id] + looked_up.mark_for_extraction(el_id, lookup, name=name_hint) + ret = EditablePartial.from_call(railroad.NonTerminal, text=looked_up.name) + return ret + + elif el_id in lookup.diagrams: + # If we have seen the element at least twice before, and have already extracted it into a subdiagram, we + # just put in a marker element that refers to the sub-diagram + ret = EditablePartial.from_call( + railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"] + ) + return ret + + # Recursively convert child elements + # Here we find the most relevant Railroad element for matching pyparsing Element + # We use ``items=[]`` here to hold the place for where the child elements will go once created + if isinstance(element, pyparsing.And): + # detect And's created with ``expr*N`` notation - for these use a OneOrMore with a repeat + # (all will have the same name, and resultsName) + if not exprs: + return None + if len(set((e.name, e.resultsName) for e in exprs)) == 1: + ret = EditablePartial.from_call( + railroad.OneOrMore, item="", repeat=str(len(exprs)) + ) + elif _should_vertical(vertical, exprs): + ret = EditablePartial.from_call(railroad.Stack, items=[]) + else: + ret = EditablePartial.from_call(railroad.Sequence, items=[]) + elif isinstance(element, (pyparsing.Or, pyparsing.MatchFirst)): + if not exprs: + return None + if _should_vertical(vertical, exprs): + ret = EditablePartial.from_call(railroad.Choice, 0, items=[]) + else: + ret = EditablePartial.from_call(railroad.HorizontalChoice, items=[]) + elif isinstance(element, pyparsing.Each): + if not exprs: + return None + ret = EditablePartial.from_call(EachItem, items=[]) + elif isinstance(element, pyparsing.NotAny): + ret = EditablePartial.from_call(AnnotatedItem, label="NOT", item="") + elif isinstance(element, pyparsing.FollowedBy): + ret = EditablePartial.from_call(AnnotatedItem, label="LOOKAHEAD", item="") + elif isinstance(element, pyparsing.PrecededBy): + ret = EditablePartial.from_call(AnnotatedItem, label="LOOKBEHIND", item="") + elif isinstance(element, pyparsing.Group): + if show_groups: + ret = EditablePartial.from_call(AnnotatedItem, label="", item="") + else: + ret = EditablePartial.from_call(railroad.Group, label="", item="") + elif isinstance(element, pyparsing.TokenConverter): + ret = EditablePartial.from_call( + AnnotatedItem, label=type(element).__name__.lower(), item="" + ) + elif isinstance(element, pyparsing.Opt): + ret = EditablePartial.from_call(railroad.Optional, item="") + elif isinstance(element, pyparsing.OneOrMore): + ret = EditablePartial.from_call(railroad.OneOrMore, item="") + elif isinstance(element, pyparsing.ZeroOrMore): + ret = EditablePartial.from_call(railroad.ZeroOrMore, item="") + elif isinstance(element, pyparsing.Group): + ret = EditablePartial.from_call( + railroad.Group, item=None, label=element_results_name + ) + elif isinstance(element, pyparsing.Empty) and not element.customName: + # Skip unnamed "Empty" elements + ret = None + elif len(exprs) > 1: + ret = EditablePartial.from_call(railroad.Sequence, items=[]) + elif len(exprs) > 0 and not element_results_name: + ret = EditablePartial.from_call(railroad.Group, item="", label=name) + else: + terminal = EditablePartial.from_call(railroad.Terminal, element.defaultName) + ret = terminal + + if ret is None: + return + + # Indicate this element's position in the tree so we can extract it if necessary + lookup[el_id] = ElementState( + element=element, + converted=ret, + parent=parent, + parent_index=index, + number=lookup.generate_index(), + ) + if element.customName: + lookup[el_id].mark_for_extraction(el_id, lookup, element.customName) + + i = 0 + for expr in exprs: + # Add a placeholder index in case we have to extract the child before we even add it to the parent + if "items" in ret.kwargs: + ret.kwargs["items"].insert(i, None) + + item = _to_diagram_element( + expr, + parent=ret, + lookup=lookup, + vertical=vertical, + index=i, + show_results_names=show_results_names, + show_groups=show_groups, + ) + + # Some elements don't need to be shown in the diagram + if item is not None: + if "item" in ret.kwargs: + ret.kwargs["item"] = item + elif "items" in ret.kwargs: + # If we've already extracted the child, don't touch this index, since it's occupied by a nonterminal + ret.kwargs["items"][i] = item + i += 1 + elif "items" in ret.kwargs: + # If we're supposed to skip this element, remove it from the parent + del ret.kwargs["items"][i] + + # If all this items children are none, skip this item + if ret and ( + ("items" in ret.kwargs and len(ret.kwargs["items"]) == 0) + or ("item" in ret.kwargs and ret.kwargs["item"] is None) + ): + ret = EditablePartial.from_call(railroad.Terminal, name) + + # Mark this element as "complete", ie it has all of its children + if el_id in lookup: + lookup[el_id].complete = True + + if el_id in lookup and lookup[el_id].extract and lookup[el_id].complete: + lookup.extract_into_diagram(el_id) + if ret is not None: + ret = EditablePartial.from_call( + railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"] + ) + + return ret diff --git a/pkg_resources/_vendor/pyparsing/exceptions.py b/pkg_resources/_vendor/pyparsing/exceptions.py new file mode 100644 index 00000000..a38447bb --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/exceptions.py @@ -0,0 +1,267 @@ +# exceptions.py + +import re +import sys +import typing + +from .util import col, line, lineno, _collapse_string_to_ranges +from .unicode import pyparsing_unicode as ppu + + +class ExceptionWordUnicode(ppu.Latin1, ppu.LatinA, ppu.LatinB, ppu.Greek, ppu.Cyrillic): + pass + + +_extract_alphanums = _collapse_string_to_ranges(ExceptionWordUnicode.alphanums) +_exception_word_extractor = re.compile("([" + _extract_alphanums + "]{1,16})|.") + + +class ParseBaseException(Exception): + """base exception class for all parsing runtime exceptions""" + + # Performance tuning: we construct a *lot* of these, so keep this + # constructor as small and fast as possible + def __init__( + self, + pstr: str, + loc: int = 0, + msg: typing.Optional[str] = None, + elem=None, + ): + self.loc = loc + if msg is None: + self.msg = pstr + self.pstr = "" + else: + self.msg = msg + self.pstr = pstr + self.parser_element = self.parserElement = elem + self.args = (pstr, loc, msg) + + @staticmethod + def explain_exception(exc, depth=16): + """ + Method to take an exception and translate the Python internal traceback into a list + of the pyparsing expressions that caused the exception to be raised. + + Parameters: + + - exc - exception raised during parsing (need not be a ParseException, in support + of Python exceptions that might be raised in a parse action) + - depth (default=16) - number of levels back in the stack trace to list expression + and function names; if None, the full stack trace names will be listed; if 0, only + the failing input line, marker, and exception string will be shown + + Returns a multi-line string listing the ParserElements and/or function names in the + exception's stack trace. + """ + import inspect + from .core import ParserElement + + if depth is None: + depth = sys.getrecursionlimit() + ret = [] + if isinstance(exc, ParseBaseException): + ret.append(exc.line) + ret.append(" " * (exc.column - 1) + "^") + ret.append("{}: {}".format(type(exc).__name__, exc)) + + if depth > 0: + callers = inspect.getinnerframes(exc.__traceback__, context=depth) + seen = set() + for i, ff in enumerate(callers[-depth:]): + frm = ff[0] + + f_self = frm.f_locals.get("self", None) + if isinstance(f_self, ParserElement): + if frm.f_code.co_name not in ("parseImpl", "_parseNoCache"): + continue + if id(f_self) in seen: + continue + seen.add(id(f_self)) + + self_type = type(f_self) + ret.append( + "{}.{} - {}".format( + self_type.__module__, self_type.__name__, f_self + ) + ) + + elif f_self is not None: + self_type = type(f_self) + ret.append("{}.{}".format(self_type.__module__, self_type.__name__)) + + else: + code = frm.f_code + if code.co_name in ("wrapper", "<module>"): + continue + + ret.append("{}".format(code.co_name)) + + depth -= 1 + if not depth: + break + + return "\n".join(ret) + + @classmethod + def _from_exception(cls, pe): + """ + internal factory method to simplify creating one type of ParseException + from another - avoids having __init__ signature conflicts among subclasses + """ + return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement) + + @property + def line(self) -> str: + """ + Return the line of text where the exception occurred. + """ + return line(self.loc, self.pstr) + + @property + def lineno(self) -> int: + """ + Return the 1-based line number of text where the exception occurred. + """ + return lineno(self.loc, self.pstr) + + @property + def col(self) -> int: + """ + Return the 1-based column on the line of text where the exception occurred. + """ + return col(self.loc, self.pstr) + + @property + def column(self) -> int: + """ + Return the 1-based column on the line of text where the exception occurred. + """ + return col(self.loc, self.pstr) + + def __str__(self) -> str: + if self.pstr: + if self.loc >= len(self.pstr): + foundstr = ", found end of text" + else: + # pull out next word at error location + found_match = _exception_word_extractor.match(self.pstr, self.loc) + if found_match is not None: + found = found_match.group(0) + else: + found = self.pstr[self.loc : self.loc + 1] + foundstr = (", found %r" % found).replace(r"\\", "\\") + else: + foundstr = "" + return "{}{} (at char {}), (line:{}, col:{})".format( + self.msg, foundstr, self.loc, self.lineno, self.column + ) + + def __repr__(self): + return str(self) + + def mark_input_line(self, marker_string: str = None, *, markerString=">!<") -> str: + """ + Extracts the exception line from the input string, and marks + the location of the exception with a special symbol. + """ + markerString = marker_string if marker_string is not None else markerString + line_str = self.line + line_column = self.column - 1 + if markerString: + line_str = "".join( + (line_str[:line_column], markerString, line_str[line_column:]) + ) + return line_str.strip() + + def explain(self, depth=16) -> str: + """ + Method to translate the Python internal traceback into a list + of the pyparsing expressions that caused the exception to be raised. + + Parameters: + + - depth (default=16) - number of levels back in the stack trace to list expression + and function names; if None, the full stack trace names will be listed; if 0, only + the failing input line, marker, and exception string will be shown + + Returns a multi-line string listing the ParserElements and/or function names in the + exception's stack trace. + + Example:: + + expr = pp.Word(pp.nums) * 3 + try: + expr.parse_string("123 456 A789") + except pp.ParseException as pe: + print(pe.explain(depth=0)) + + prints:: + + 123 456 A789 + ^ + ParseException: Expected W:(0-9), found 'A' (at char 8), (line:1, col:9) + + Note: the diagnostic output will include string representations of the expressions + that failed to parse. These representations will be more helpful if you use `set_name` to + give identifiable names to your expressions. Otherwise they will use the default string + forms, which may be cryptic to read. + + Note: pyparsing's default truncation of exception tracebacks may also truncate the + stack of expressions that are displayed in the ``explain`` output. To get the full listing + of parser expressions, you may have to set ``ParserElement.verbose_stacktrace = True`` + """ + return self.explain_exception(self, depth) + + markInputline = mark_input_line + + +class ParseException(ParseBaseException): + """ + Exception thrown when a parse expression doesn't match the input string + + Example:: + + try: + Word(nums).set_name("integer").parse_string("ABC") + except ParseException as pe: + print(pe) + print("column: {}".format(pe.column)) + + prints:: + + Expected integer (at char 0), (line:1, col:1) + column: 1 + + """ + + +class ParseFatalException(ParseBaseException): + """ + User-throwable exception thrown when inconsistent parse content + is found; stops all parsing immediately + """ + + +class ParseSyntaxException(ParseFatalException): + """ + Just like :class:`ParseFatalException`, but thrown internally + when an :class:`ErrorStop<And._ErrorStop>` ('-' operator) indicates + that parsing is to stop immediately because an unbacktrackable + syntax error has been found. + """ + + +class RecursiveGrammarException(Exception): + """ + Exception thrown by :class:`ParserElement.validate` if the + grammar could be left-recursive; parser may need to enable + left recursion using :class:`ParserElement.enable_left_recursion<ParserElement.enable_left_recursion>` + """ + + def __init__(self, parseElementList): + self.parseElementTrace = parseElementList + + def __str__(self) -> str: + return "RecursiveGrammarException: {}".format(self.parseElementTrace) diff --git a/pkg_resources/_vendor/pyparsing/helpers.py b/pkg_resources/_vendor/pyparsing/helpers.py new file mode 100644 index 00000000..9588b3b7 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/helpers.py @@ -0,0 +1,1088 @@ +# helpers.py +import html.entities +import re +import typing + +from . import __diag__ +from .core import * +from .util import _bslash, _flatten, _escape_regex_range_chars + + +# +# global helpers +# +def delimited_list( + expr: Union[str, ParserElement], + delim: Union[str, ParserElement] = ",", + combine: bool = False, + min: typing.Optional[int] = None, + max: typing.Optional[int] = None, + *, + allow_trailing_delim: bool = False, +) -> ParserElement: + """Helper to define a delimited list of expressions - the delimiter + defaults to ','. By default, the list elements and delimiters can + have intervening whitespace, and comments, but this can be + overridden by passing ``combine=True`` in the constructor. If + ``combine`` is set to ``True``, the matching tokens are + returned as a single token string, with the delimiters included; + otherwise, the matching tokens are returned as a list of tokens, + with the delimiters suppressed. + + If ``allow_trailing_delim`` is set to True, then the list may end with + a delimiter. + + Example:: + + delimited_list(Word(alphas)).parse_string("aa,bb,cc") # -> ['aa', 'bb', 'cc'] + delimited_list(Word(hexnums), delim=':', combine=True).parse_string("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE'] + """ + if isinstance(expr, str_type): + expr = ParserElement._literalStringClass(expr) + + dlName = "{expr} [{delim} {expr}]...{end}".format( + expr=str(expr.copy().streamline()), + delim=str(delim), + end=" [{}]".format(str(delim)) if allow_trailing_delim else "", + ) + + if not combine: + delim = Suppress(delim) + + if min is not None: + if min < 1: + raise ValueError("min must be greater than 0") + min -= 1 + if max is not None: + if min is not None and max <= min: + raise ValueError("max must be greater than, or equal to min") + max -= 1 + delimited_list_expr = expr + (delim + expr)[min, max] + + if allow_trailing_delim: + delimited_list_expr += Opt(delim) + + if combine: + return Combine(delimited_list_expr).set_name(dlName) + else: + return delimited_list_expr.set_name(dlName) + + +def counted_array( + expr: ParserElement, + int_expr: typing.Optional[ParserElement] = None, + *, + intExpr: typing.Optional[ParserElement] = None, +) -> ParserElement: + """Helper to define a counted list of expressions. + + This helper defines a pattern of the form:: + + integer expr expr expr... + + where the leading integer tells how many expr expressions follow. + The matched tokens returns the array of expr tokens as a list - the + leading count token is suppressed. + + If ``int_expr`` is specified, it should be a pyparsing expression + that produces an integer value. + + Example:: + + counted_array(Word(alphas)).parse_string('2 ab cd ef') # -> ['ab', 'cd'] + + # in this parser, the leading integer value is given in binary, + # '10' indicating that 2 values are in the array + binary_constant = Word('01').set_parse_action(lambda t: int(t[0], 2)) + counted_array(Word(alphas), int_expr=binary_constant).parse_string('10 ab cd ef') # -> ['ab', 'cd'] + + # if other fields must be parsed after the count but before the + # list items, give the fields results names and they will + # be preserved in the returned ParseResults: + count_with_metadata = integer + Word(alphas)("type") + typed_array = counted_array(Word(alphanums), int_expr=count_with_metadata)("items") + result = typed_array.parse_string("3 bool True True False") + print(result.dump()) + + # prints + # ['True', 'True', 'False'] + # - items: ['True', 'True', 'False'] + # - type: 'bool' + """ + intExpr = intExpr or int_expr + array_expr = Forward() + + def count_field_parse_action(s, l, t): + nonlocal array_expr + n = t[0] + array_expr <<= (expr * n) if n else Empty() + # clear list contents, but keep any named results + del t[:] + + if intExpr is None: + intExpr = Word(nums).set_parse_action(lambda t: int(t[0])) + else: + intExpr = intExpr.copy() + intExpr.set_name("arrayLen") + intExpr.add_parse_action(count_field_parse_action, call_during_try=True) + return (intExpr + array_expr).set_name("(len) " + str(expr) + "...") + + +def match_previous_literal(expr: ParserElement) -> ParserElement: + """Helper to define an expression that is indirectly defined from + the tokens matched in a previous expression, that is, it looks for + a 'repeat' of a previous expression. For example:: + + first = Word(nums) + second = match_previous_literal(first) + match_expr = first + ":" + second + + will match ``"1:1"``, but not ``"1:2"``. Because this + matches a previous literal, will also match the leading + ``"1:1"`` in ``"1:10"``. If this is not desired, use + :class:`match_previous_expr`. Do *not* use with packrat parsing + enabled. + """ + rep = Forward() + + def copy_token_to_repeater(s, l, t): + if t: + if len(t) == 1: + rep << t[0] + else: + # flatten t tokens + tflat = _flatten(t.as_list()) + rep << And(Literal(tt) for tt in tflat) + else: + rep << Empty() + + expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) + rep.set_name("(prev) " + str(expr)) + return rep + + +def match_previous_expr(expr: ParserElement) -> ParserElement: + """Helper to define an expression that is indirectly defined from + the tokens matched in a previous expression, that is, it looks for + a 'repeat' of a previous expression. For example:: + + first = Word(nums) + second = match_previous_expr(first) + match_expr = first + ":" + second + + will match ``"1:1"``, but not ``"1:2"``. Because this + matches by expressions, will *not* match the leading ``"1:1"`` + in ``"1:10"``; the expressions are evaluated first, and then + compared, so ``"1"`` is compared with ``"10"``. Do *not* use + with packrat parsing enabled. + """ + rep = Forward() + e2 = expr.copy() + rep <<= e2 + + def copy_token_to_repeater(s, l, t): + matchTokens = _flatten(t.as_list()) + + def must_match_these_tokens(s, l, t): + theseTokens = _flatten(t.as_list()) + if theseTokens != matchTokens: + raise ParseException( + s, l, "Expected {}, found{}".format(matchTokens, theseTokens) + ) + + rep.set_parse_action(must_match_these_tokens, callDuringTry=True) + + expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) + rep.set_name("(prev) " + str(expr)) + return rep + + +def one_of( + strs: Union[typing.Iterable[str], str], + caseless: bool = False, + use_regex: bool = True, + as_keyword: bool = False, + *, + useRegex: bool = True, + asKeyword: bool = False, +) -> ParserElement: + """Helper to quickly define a set of alternative :class:`Literal` s, + and makes sure to do longest-first testing when there is a conflict, + regardless of the input order, but returns + a :class:`MatchFirst` for best performance. + + Parameters: + + - ``strs`` - a string of space-delimited literals, or a collection of + string literals + - ``caseless`` - treat all literals as caseless - (default= ``False``) + - ``use_regex`` - as an optimization, will + generate a :class:`Regex` object; otherwise, will generate + a :class:`MatchFirst` object (if ``caseless=True`` or ``asKeyword=True``, or if + creating a :class:`Regex` raises an exception) - (default= ``True``) + - ``as_keyword`` - enforce :class:`Keyword`-style matching on the + generated expressions - (default= ``False``) + - ``asKeyword`` and ``useRegex`` are retained for pre-PEP8 compatibility, + but will be removed in a future release + + Example:: + + comp_oper = one_of("< = > <= >= !=") + var = Word(alphas) + number = Word(nums) + term = var | number + comparison_expr = term + comp_oper + term + print(comparison_expr.search_string("B = 12 AA=23 B<=AA AA>12")) + + prints:: + + [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']] + """ + asKeyword = asKeyword or as_keyword + useRegex = useRegex and use_regex + + if ( + isinstance(caseless, str_type) + and __diag__.warn_on_multiple_string_args_to_oneof + ): + warnings.warn( + "More than one string argument passed to one_of, pass" + " choices as a list or space-delimited string", + stacklevel=2, + ) + + if caseless: + isequal = lambda a, b: a.upper() == b.upper() + masks = lambda a, b: b.upper().startswith(a.upper()) + parseElementClass = CaselessKeyword if asKeyword else CaselessLiteral + else: + isequal = lambda a, b: a == b + masks = lambda a, b: b.startswith(a) + parseElementClass = Keyword if asKeyword else Literal + + symbols: List[str] = [] + if isinstance(strs, str_type): + symbols = strs.split() + elif isinstance(strs, Iterable): + symbols = list(strs) + else: + raise TypeError("Invalid argument to one_of, expected string or iterable") + if not symbols: + return NoMatch() + + # reorder given symbols to take care to avoid masking longer choices with shorter ones + # (but only if the given symbols are not just single characters) + if any(len(sym) > 1 for sym in symbols): + i = 0 + while i < len(symbols) - 1: + cur = symbols[i] + for j, other in enumerate(symbols[i + 1 :]): + if isequal(other, cur): + del symbols[i + j + 1] + break + elif masks(cur, other): + del symbols[i + j + 1] + symbols.insert(i, other) + break + else: + i += 1 + + if useRegex: + re_flags: int = re.IGNORECASE if caseless else 0 + + try: + if all(len(sym) == 1 for sym in symbols): + # symbols are just single characters, create range regex pattern + patt = "[{}]".format( + "".join(_escape_regex_range_chars(sym) for sym in symbols) + ) + else: + patt = "|".join(re.escape(sym) for sym in symbols) + + # wrap with \b word break markers if defining as keywords + if asKeyword: + patt = r"\b(?:{})\b".format(patt) + + ret = Regex(patt, flags=re_flags).set_name(" | ".join(symbols)) + + if caseless: + # add parse action to return symbols as specified, not in random + # casing as found in input string + symbol_map = {sym.lower(): sym for sym in symbols} + ret.add_parse_action(lambda s, l, t: symbol_map[t[0].lower()]) + + return ret + + except re.error: + warnings.warn( + "Exception creating Regex for one_of, building MatchFirst", stacklevel=2 + ) + + # last resort, just use MatchFirst + return MatchFirst(parseElementClass(sym) for sym in symbols).set_name( + " | ".join(symbols) + ) + + +def dict_of(key: ParserElement, value: ParserElement) -> ParserElement: + """Helper to easily and clearly define a dictionary by specifying + the respective patterns for the key and value. Takes care of + defining the :class:`Dict`, :class:`ZeroOrMore`, and + :class:`Group` tokens in the proper order. The key pattern + can include delimiting markers or punctuation, as long as they are + suppressed, thereby leaving the significant key text. The value + pattern can include named results, so that the :class:`Dict` results + can include named token fields. + + Example:: + + text = "shape: SQUARE posn: upper left color: light blue texture: burlap" + attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + print(attr_expr[1, ...].parse_string(text).dump()) + + attr_label = label + attr_value = Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join) + + # similar to Dict, but simpler call format + result = dict_of(attr_label, attr_value).parse_string(text) + print(result.dump()) + print(result['shape']) + print(result.shape) # object attribute access works too + print(result.as_dict()) + + prints:: + + [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] + - color: 'light blue' + - posn: 'upper left' + - shape: 'SQUARE' + - texture: 'burlap' + SQUARE + SQUARE + {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'} + """ + return Dict(OneOrMore(Group(key + value))) + + +def original_text_for( + expr: ParserElement, as_string: bool = True, *, asString: bool = True +) -> ParserElement: + """Helper to return the original, untokenized text for a given + expression. Useful to restore the parsed fields of an HTML start + tag into the raw tag text itself, or to revert separate tokens with + intervening whitespace back to the original matching input text. By + default, returns astring containing the original parsed text. + + If the optional ``as_string`` argument is passed as + ``False``, then the return value is + a :class:`ParseResults` containing any results names that + were originally matched, and a single token containing the original + matched text from the input string. So if the expression passed to + :class:`original_text_for` contains expressions with defined + results names, you must set ``as_string`` to ``False`` if you + want to preserve those results name values. + + The ``asString`` pre-PEP8 argument is retained for compatibility, + but will be removed in a future release. + + Example:: + + src = "this is test <b> bold <i>text</i> </b> normal text " + for tag in ("b", "i"): + opener, closer = make_html_tags(tag) + patt = original_text_for(opener + SkipTo(closer) + closer) + print(patt.search_string(src)[0]) + + prints:: + + ['<b> bold <i>text</i> </b>'] + ['<i>text</i>'] + """ + asString = asString and as_string + + locMarker = Empty().set_parse_action(lambda s, loc, t: loc) + endlocMarker = locMarker.copy() + endlocMarker.callPreparse = False + matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") + if asString: + extractText = lambda s, l, t: s[t._original_start : t._original_end] + else: + + def extractText(s, l, t): + t[:] = [s[t.pop("_original_start") : t.pop("_original_end")]] + + matchExpr.set_parse_action(extractText) + matchExpr.ignoreExprs = expr.ignoreExprs + matchExpr.suppress_warning(Diagnostics.warn_ungrouped_named_tokens_in_collection) + return matchExpr + + +def ungroup(expr: ParserElement) -> ParserElement: + """Helper to undo pyparsing's default grouping of And expressions, + even if all but one are non-empty. + """ + return TokenConverter(expr).add_parse_action(lambda t: t[0]) + + +def locatedExpr(expr: ParserElement) -> ParserElement: + """ + (DEPRECATED - future code should use the Located class) + Helper to decorate a returned token with its starting and ending + locations in the input string. + + This helper adds the following results names: + + - ``locn_start`` - location where matched expression begins + - ``locn_end`` - location where matched expression ends + - ``value`` - the actual parsed results + + Be careful if the input text contains ``<TAB>`` characters, you + may want to call :class:`ParserElement.parseWithTabs` + + Example:: + + wd = Word(alphas) + for match in locatedExpr(wd).searchString("ljsdf123lksdjjf123lkkjj1222"): + print(match) + + prints:: + + [[0, 'ljsdf', 5]] + [[8, 'lksdjjf', 15]] + [[18, 'lkkjj', 23]] + """ + locator = Empty().set_parse_action(lambda ss, ll, tt: ll) + return Group( + locator("locn_start") + + expr("value") + + locator.copy().leaveWhitespace()("locn_end") + ) + + +def nested_expr( + opener: Union[str, ParserElement] = "(", + closer: Union[str, ParserElement] = ")", + content: typing.Optional[ParserElement] = None, + ignore_expr: ParserElement = quoted_string(), + *, + ignoreExpr: ParserElement = quoted_string(), +) -> ParserElement: + """Helper method for defining nested lists enclosed in opening and + closing delimiters (``"("`` and ``")"`` are the default). + + Parameters: + - ``opener`` - opening character for a nested list + (default= ``"("``); can also be a pyparsing expression + - ``closer`` - closing character for a nested list + (default= ``")"``); can also be a pyparsing expression + - ``content`` - expression for items within the nested lists + (default= ``None``) + - ``ignore_expr`` - expression for ignoring opening and closing delimiters + (default= :class:`quoted_string`) + - ``ignoreExpr`` - this pre-PEP8 argument is retained for compatibility + but will be removed in a future release + + If an expression is not provided for the content argument, the + nested expression will capture all whitespace-delimited content + between delimiters as a list of separate values. + + Use the ``ignore_expr`` argument to define expressions that may + contain opening or closing characters that should not be treated as + opening or closing characters for nesting, such as quoted_string or + a comment expression. Specify multiple expressions using an + :class:`Or` or :class:`MatchFirst`. The default is + :class:`quoted_string`, but if no expressions are to be ignored, then + pass ``None`` for this argument. + + Example:: + + data_type = one_of("void int short long char float double") + decl_data_type = Combine(data_type + Opt(Word('*'))) + ident = Word(alphas+'_', alphanums+'_') + number = pyparsing_common.number + arg = Group(decl_data_type + ident) + LPAR, RPAR = map(Suppress, "()") + + code_body = nested_expr('{', '}', ignore_expr=(quoted_string | c_style_comment)) + + c_function = (decl_data_type("type") + + ident("name") + + LPAR + Opt(delimited_list(arg), [])("args") + RPAR + + code_body("body")) + c_function.ignore(c_style_comment) + + source_code = ''' + int is_odd(int x) { + return (x%2); + } + + int dec_to_hex(char hchar) { + if (hchar >= '0' && hchar <= '9') { + return (ord(hchar)-ord('0')); + } else { + return (10+ord(hchar)-ord('A')); + } + } + ''' + for func in c_function.search_string(source_code): + print("%(name)s (%(type)s) args: %(args)s" % func) + + + prints:: + + is_odd (int) args: [['int', 'x']] + dec_to_hex (int) args: [['char', 'hchar']] + """ + if ignoreExpr != ignore_expr: + ignoreExpr = ignore_expr if ignoreExpr == quoted_string() else ignoreExpr + if opener == closer: + raise ValueError("opening and closing strings cannot be the same") + if content is None: + if isinstance(opener, str_type) and isinstance(closer, str_type): + if len(opener) == 1 and len(closer) == 1: + if ignoreExpr is not None: + content = Combine( + OneOrMore( + ~ignoreExpr + + CharsNotIn( + opener + closer + ParserElement.DEFAULT_WHITE_CHARS, + exact=1, + ) + ) + ).set_parse_action(lambda t: t[0].strip()) + else: + content = empty.copy() + CharsNotIn( + opener + closer + ParserElement.DEFAULT_WHITE_CHARS + ).set_parse_action(lambda t: t[0].strip()) + else: + if ignoreExpr is not None: + content = Combine( + OneOrMore( + ~ignoreExpr + + ~Literal(opener) + + ~Literal(closer) + + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) + ) + ).set_parse_action(lambda t: t[0].strip()) + else: + content = Combine( + OneOrMore( + ~Literal(opener) + + ~Literal(closer) + + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) + ) + ).set_parse_action(lambda t: t[0].strip()) + else: + raise ValueError( + "opening and closing arguments must be strings if no content expression is given" + ) + ret = Forward() + if ignoreExpr is not None: + ret <<= Group( + Suppress(opener) + ZeroOrMore(ignoreExpr | ret | content) + Suppress(closer) + ) + else: + ret <<= Group(Suppress(opener) + ZeroOrMore(ret | content) + Suppress(closer)) + ret.set_name("nested %s%s expression" % (opener, closer)) + return ret + + +def _makeTags(tagStr, xml, suppress_LT=Suppress("<"), suppress_GT=Suppress(">")): + """Internal helper to construct opening and closing tag expressions, given a tag name""" + if isinstance(tagStr, str_type): + resname = tagStr + tagStr = Keyword(tagStr, caseless=not xml) + else: + resname = tagStr.name + + tagAttrName = Word(alphas, alphanums + "_-:") + if xml: + tagAttrValue = dbl_quoted_string.copy().set_parse_action(remove_quotes) + openTag = ( + suppress_LT + + tagStr("tag") + + Dict(ZeroOrMore(Group(tagAttrName + Suppress("=") + tagAttrValue))) + + Opt("/", default=[False])("empty").set_parse_action( + lambda s, l, t: t[0] == "/" + ) + + suppress_GT + ) + else: + tagAttrValue = quoted_string.copy().set_parse_action(remove_quotes) | Word( + printables, exclude_chars=">" + ) + openTag = ( + suppress_LT + + tagStr("tag") + + Dict( + ZeroOrMore( + Group( + tagAttrName.set_parse_action(lambda t: t[0].lower()) + + Opt(Suppress("=") + tagAttrValue) + ) + ) + ) + + Opt("/", default=[False])("empty").set_parse_action( + lambda s, l, t: t[0] == "/" + ) + + suppress_GT + ) + closeTag = Combine(Literal("</") + tagStr + ">", adjacent=False) + + openTag.set_name("<%s>" % resname) + # add start<tagname> results name in parse action now that ungrouped names are not reported at two levels + openTag.add_parse_action( + lambda t: t.__setitem__( + "start" + "".join(resname.replace(":", " ").title().split()), t.copy() + ) + ) + closeTag = closeTag( + "end" + "".join(resname.replace(":", " ").title().split()) + ).set_name("</%s>" % resname) + openTag.tag = resname + closeTag.tag = resname + openTag.tag_body = SkipTo(closeTag()) + return openTag, closeTag + + +def make_html_tags( + tag_str: Union[str, ParserElement] +) -> Tuple[ParserElement, ParserElement]: + """Helper to construct opening and closing tag expressions for HTML, + given a tag name. Matches tags in either upper or lower case, + attributes with namespaces and with quoted or unquoted values. + + Example:: + + text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' + # make_html_tags returns pyparsing expressions for the opening and + # closing tags as a 2-tuple + a, a_end = make_html_tags("A") + link_expr = a + SkipTo(a_end)("link_text") + a_end + + for link in link_expr.search_string(text): + # attributes in the <A> tag (like "href" shown here) are + # also accessible as named results + print(link.link_text, '->', link.href) + + prints:: + + pyparsing -> https://github.com/pyparsing/pyparsing/wiki + """ + return _makeTags(tag_str, False) + + +def make_xml_tags( + tag_str: Union[str, ParserElement] +) -> Tuple[ParserElement, ParserElement]: + """Helper to construct opening and closing tag expressions for XML, + given a tag name. Matches tags only in the given upper/lower case. + + Example: similar to :class:`make_html_tags` + """ + return _makeTags(tag_str, True) + + +any_open_tag: ParserElement +any_close_tag: ParserElement +any_open_tag, any_close_tag = make_html_tags( + Word(alphas, alphanums + "_:").set_name("any tag") +) + +_htmlEntityMap = {k.rstrip(";"): v for k, v in html.entities.html5.items()} +common_html_entity = Regex("&(?P<entity>" + "|".join(_htmlEntityMap) + ");").set_name( + "common HTML entity" +) + + +def replace_html_entity(t): + """Helper parser action to replace common HTML entities with their special characters""" + return _htmlEntityMap.get(t.entity) + + +class OpAssoc(Enum): + LEFT = 1 + RIGHT = 2 + + +InfixNotationOperatorArgType = Union[ + ParserElement, str, Tuple[Union[ParserElement, str], Union[ParserElement, str]] +] +InfixNotationOperatorSpec = Union[ + Tuple[ + InfixNotationOperatorArgType, + int, + OpAssoc, + typing.Optional[ParseAction], + ], + Tuple[ + InfixNotationOperatorArgType, + int, + OpAssoc, + ], +] + + +def infix_notation( + base_expr: ParserElement, + op_list: List[InfixNotationOperatorSpec], + lpar: Union[str, ParserElement] = Suppress("("), + rpar: Union[str, ParserElement] = Suppress(")"), +) -> ParserElement: + """Helper method for constructing grammars of expressions made up of + operators working in a precedence hierarchy. Operators may be unary + or binary, left- or right-associative. Parse actions can also be + attached to operator expressions. The generated parser will also + recognize the use of parentheses to override operator precedences + (see example below). + + Note: if you define a deep operator list, you may see performance + issues when using infix_notation. See + :class:`ParserElement.enable_packrat` for a mechanism to potentially + improve your parser performance. + + Parameters: + - ``base_expr`` - expression representing the most basic operand to + be used in the expression + - ``op_list`` - list of tuples, one for each operator precedence level + in the expression grammar; each tuple is of the form ``(op_expr, + num_operands, right_left_assoc, (optional)parse_action)``, where: + + - ``op_expr`` is the pyparsing expression for the operator; may also + be a string, which will be converted to a Literal; if ``num_operands`` + is 3, ``op_expr`` is a tuple of two expressions, for the two + operators separating the 3 terms + - ``num_operands`` is the number of terms for this operator (must be 1, + 2, or 3) + - ``right_left_assoc`` is the indicator whether the operator is right + or left associative, using the pyparsing-defined constants + ``OpAssoc.RIGHT`` and ``OpAssoc.LEFT``. + - ``parse_action`` is the parse action to be associated with + expressions matching this operator expression (the parse action + tuple member may be omitted); if the parse action is passed + a tuple or list of functions, this is equivalent to calling + ``set_parse_action(*fn)`` + (:class:`ParserElement.set_parse_action`) + - ``lpar`` - expression for matching left-parentheses; if passed as a + str, then will be parsed as Suppress(lpar). If lpar is passed as + an expression (such as ``Literal('(')``), then it will be kept in + the parsed results, and grouped with them. (default= ``Suppress('(')``) + - ``rpar`` - expression for matching right-parentheses; if passed as a + str, then will be parsed as Suppress(rpar). If rpar is passed as + an expression (such as ``Literal(')')``), then it will be kept in + the parsed results, and grouped with them. (default= ``Suppress(')')``) + + Example:: + + # simple example of four-function arithmetic with ints and + # variable names + integer = pyparsing_common.signed_integer + varname = pyparsing_common.identifier + + arith_expr = infix_notation(integer | varname, + [ + ('-', 1, OpAssoc.RIGHT), + (one_of('* /'), 2, OpAssoc.LEFT), + (one_of('+ -'), 2, OpAssoc.LEFT), + ]) + + arith_expr.run_tests(''' + 5+3*6 + (5+3)*6 + -2--11 + ''', full_dump=False) + + prints:: + + 5+3*6 + [[5, '+', [3, '*', 6]]] + + (5+3)*6 + [[[5, '+', 3], '*', 6]] + + -2--11 + [[['-', 2], '-', ['-', 11]]] + """ + # captive version of FollowedBy that does not do parse actions or capture results names + class _FB(FollowedBy): + def parseImpl(self, instring, loc, doActions=True): + self.expr.try_parse(instring, loc) + return loc, [] + + _FB.__name__ = "FollowedBy>" + + ret = Forward() + if isinstance(lpar, str): + lpar = Suppress(lpar) + if isinstance(rpar, str): + rpar = Suppress(rpar) + + # if lpar and rpar are not suppressed, wrap in group + if not (isinstance(rpar, Suppress) and isinstance(rpar, Suppress)): + lastExpr = base_expr | Group(lpar + ret + rpar) + else: + lastExpr = base_expr | (lpar + ret + rpar) + + for i, operDef in enumerate(op_list): + opExpr, arity, rightLeftAssoc, pa = (operDef + (None,))[:4] + if isinstance(opExpr, str_type): + opExpr = ParserElement._literalStringClass(opExpr) + if arity == 3: + if not isinstance(opExpr, (tuple, list)) or len(opExpr) != 2: + raise ValueError( + "if numterms=3, opExpr must be a tuple or list of two expressions" + ) + opExpr1, opExpr2 = opExpr + term_name = "{}{} term".format(opExpr1, opExpr2) + else: + term_name = "{} term".format(opExpr) + + if not 1 <= arity <= 3: + raise ValueError("operator must be unary (1), binary (2), or ternary (3)") + + if rightLeftAssoc not in (OpAssoc.LEFT, OpAssoc.RIGHT): + raise ValueError("operator must indicate right or left associativity") + + thisExpr: Forward = Forward().set_name(term_name) + if rightLeftAssoc is OpAssoc.LEFT: + if arity == 1: + matchExpr = _FB(lastExpr + opExpr) + Group(lastExpr + opExpr[1, ...]) + elif arity == 2: + if opExpr is not None: + matchExpr = _FB(lastExpr + opExpr + lastExpr) + Group( + lastExpr + (opExpr + lastExpr)[1, ...] + ) + else: + matchExpr = _FB(lastExpr + lastExpr) + Group(lastExpr[2, ...]) + elif arity == 3: + matchExpr = _FB( + lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr + ) + Group(lastExpr + OneOrMore(opExpr1 + lastExpr + opExpr2 + lastExpr)) + elif rightLeftAssoc is OpAssoc.RIGHT: + if arity == 1: + # try to avoid LR with this extra test + if not isinstance(opExpr, Opt): + opExpr = Opt(opExpr) + matchExpr = _FB(opExpr.expr + thisExpr) + Group(opExpr + thisExpr) + elif arity == 2: + if opExpr is not None: + matchExpr = _FB(lastExpr + opExpr + thisExpr) + Group( + lastExpr + (opExpr + thisExpr)[1, ...] + ) + else: + matchExpr = _FB(lastExpr + thisExpr) + Group( + lastExpr + thisExpr[1, ...] + ) + elif arity == 3: + matchExpr = _FB( + lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr + ) + Group(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + if pa: + if isinstance(pa, (tuple, list)): + matchExpr.set_parse_action(*pa) + else: + matchExpr.set_parse_action(pa) + thisExpr <<= (matchExpr | lastExpr).setName(term_name) + lastExpr = thisExpr + ret <<= lastExpr + return ret + + +def indentedBlock(blockStatementExpr, indentStack, indent=True, backup_stacks=[]): + """ + (DEPRECATED - use IndentedBlock class instead) + Helper method for defining space-delimited indentation blocks, + such as those used to define block statements in Python source code. + + Parameters: + + - ``blockStatementExpr`` - expression defining syntax of statement that + is repeated within the indented block + - ``indentStack`` - list created by caller to manage indentation stack + (multiple ``statementWithIndentedBlock`` expressions within a single + grammar should share a common ``indentStack``) + - ``indent`` - boolean indicating whether block must be indented beyond + the current level; set to ``False`` for block of left-most statements + (default= ``True``) + + A valid block must contain at least one ``blockStatement``. + + (Note that indentedBlock uses internal parse actions which make it + incompatible with packrat parsing.) + + Example:: + + data = ''' + def A(z): + A1 + B = 100 + G = A2 + A2 + A3 + B + def BB(a,b,c): + BB1 + def BBA(): + bba1 + bba2 + bba3 + C + D + def spam(x,y): + def eggs(z): + pass + ''' + + + indentStack = [1] + stmt = Forward() + + identifier = Word(alphas, alphanums) + funcDecl = ("def" + identifier + Group("(" + Opt(delimitedList(identifier)) + ")") + ":") + func_body = indentedBlock(stmt, indentStack) + funcDef = Group(funcDecl + func_body) + + rvalue = Forward() + funcCall = Group(identifier + "(" + Opt(delimitedList(rvalue)) + ")") + rvalue << (funcCall | identifier | Word(nums)) + assignment = Group(identifier + "=" + rvalue) + stmt << (funcDef | assignment | identifier) + + module_body = stmt[1, ...] + + parseTree = module_body.parseString(data) + parseTree.pprint() + + prints:: + + [['def', + 'A', + ['(', 'z', ')'], + ':', + [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]], + 'B', + ['def', + 'BB', + ['(', 'a', 'b', 'c', ')'], + ':', + [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]], + 'C', + 'D', + ['def', + 'spam', + ['(', 'x', 'y', ')'], + ':', + [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]] + """ + backup_stacks.append(indentStack[:]) + + def reset_stack(): + indentStack[:] = backup_stacks[-1] + + def checkPeerIndent(s, l, t): + if l >= len(s): + return + curCol = col(l, s) + if curCol != indentStack[-1]: + if curCol > indentStack[-1]: + raise ParseException(s, l, "illegal nesting") + raise ParseException(s, l, "not a peer entry") + + def checkSubIndent(s, l, t): + curCol = col(l, s) + if curCol > indentStack[-1]: + indentStack.append(curCol) + else: + raise ParseException(s, l, "not a subentry") + + def checkUnindent(s, l, t): + if l >= len(s): + return + curCol = col(l, s) + if not (indentStack and curCol in indentStack): + raise ParseException(s, l, "not an unindent") + if curCol < indentStack[-1]: + indentStack.pop() + + NL = OneOrMore(LineEnd().set_whitespace_chars("\t ").suppress()) + INDENT = (Empty() + Empty().set_parse_action(checkSubIndent)).set_name("INDENT") + PEER = Empty().set_parse_action(checkPeerIndent).set_name("") + UNDENT = Empty().set_parse_action(checkUnindent).set_name("UNINDENT") + if indent: + smExpr = Group( + Opt(NL) + + INDENT + + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) + + UNDENT + ) + else: + smExpr = Group( + Opt(NL) + + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) + + Opt(UNDENT) + ) + + # add a parse action to remove backup_stack from list of backups + smExpr.add_parse_action( + lambda: backup_stacks.pop(-1) and None if backup_stacks else None + ) + smExpr.set_fail_action(lambda a, b, c, d: reset_stack()) + blockStatementExpr.ignore(_bslash + LineEnd()) + return smExpr.set_name("indented block") + + +# it's easy to get these comment structures wrong - they're very common, so may as well make them available +c_style_comment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + "*/").set_name( + "C style comment" +) +"Comment of the form ``/* ... */``" + +html_comment = Regex(r"<!--[\s\S]*?-->").set_name("HTML comment") +"Comment of the form ``<!-- ... -->``" + +rest_of_line = Regex(r".*").leave_whitespace().set_name("rest of line") +dbl_slash_comment = Regex(r"//(?:\\\n|[^\n])*").set_name("// comment") +"Comment of the form ``// ... (to end of line)``" + +cpp_style_comment = Combine( + Regex(r"/\*(?:[^*]|\*(?!/))*") + "*/" | dbl_slash_comment +).set_name("C++ style comment") +"Comment of either form :class:`c_style_comment` or :class:`dbl_slash_comment`" + +java_style_comment = cpp_style_comment +"Same as :class:`cpp_style_comment`" + +python_style_comment = Regex(r"#.*").set_name("Python style comment") +"Comment of the form ``# ... (to end of line)``" + + +# build list of built-in expressions, for future reference if a global default value +# gets updated +_builtin_exprs: List[ParserElement] = [ + v for v in vars().values() if isinstance(v, ParserElement) +] + + +# pre-PEP8 compatible names +delimitedList = delimited_list +countedArray = counted_array +matchPreviousLiteral = match_previous_literal +matchPreviousExpr = match_previous_expr +oneOf = one_of +dictOf = dict_of +originalTextFor = original_text_for +nestedExpr = nested_expr +makeHTMLTags = make_html_tags +makeXMLTags = make_xml_tags +anyOpenTag, anyCloseTag = any_open_tag, any_close_tag +commonHTMLEntity = common_html_entity +replaceHTMLEntity = replace_html_entity +opAssoc = OpAssoc +infixNotation = infix_notation +cStyleComment = c_style_comment +htmlComment = html_comment +restOfLine = rest_of_line +dblSlashComment = dbl_slash_comment +cppStyleComment = cpp_style_comment +javaStyleComment = java_style_comment +pythonStyleComment = python_style_comment diff --git a/pkg_resources/_vendor/pyparsing/py.typed b/pkg_resources/_vendor/pyparsing/py.typed new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/py.typed diff --git a/pkg_resources/_vendor/pyparsing/results.py b/pkg_resources/_vendor/pyparsing/results.py new file mode 100644 index 00000000..00c9421d --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/results.py @@ -0,0 +1,760 @@ +# results.py +from collections.abc import MutableMapping, Mapping, MutableSequence, Iterator +import pprint +from weakref import ref as wkref +from typing import Tuple, Any + +str_type: Tuple[type, ...] = (str, bytes) +_generator_type = type((_ for _ in ())) + + +class _ParseResultsWithOffset: + __slots__ = ["tup"] + + def __init__(self, p1, p2): + self.tup = (p1, p2) + + def __getitem__(self, i): + return self.tup[i] + + def __getstate__(self): + return self.tup + + def __setstate__(self, *args): + self.tup = args[0] + + +class ParseResults: + """Structured parse results, to provide multiple means of access to + the parsed data: + + - as a list (``len(results)``) + - by list index (``results[0], results[1]``, etc.) + - by attribute (``results.<results_name>`` - see :class:`ParserElement.set_results_name`) + + Example:: + + integer = Word(nums) + date_str = (integer.set_results_name("year") + '/' + + integer.set_results_name("month") + '/' + + integer.set_results_name("day")) + # equivalent form: + # date_str = (integer("year") + '/' + # + integer("month") + '/' + # + integer("day")) + + # parse_string returns a ParseResults object + result = date_str.parse_string("1999/12/31") + + def test(s, fn=repr): + print("{} -> {}".format(s, fn(eval(s)))) + test("list(result)") + test("result[0]") + test("result['month']") + test("result.day") + test("'month' in result") + test("'minutes' in result") + test("result.dump()", str) + + prints:: + + list(result) -> ['1999', '/', '12', '/', '31'] + result[0] -> '1999' + result['month'] -> '12' + result.day -> '31' + 'month' in result -> True + 'minutes' in result -> False + result.dump() -> ['1999', '/', '12', '/', '31'] + - day: '31' + - month: '12' + - year: '1999' + """ + + _null_values: Tuple[Any, ...] = (None, [], "", ()) + + __slots__ = [ + "_name", + "_parent", + "_all_names", + "_modal", + "_toklist", + "_tokdict", + "__weakref__", + ] + + class List(list): + """ + Simple wrapper class to distinguish parsed list results that should be preserved + as actual Python lists, instead of being converted to :class:`ParseResults`: + + LBRACK, RBRACK = map(pp.Suppress, "[]") + element = pp.Forward() + item = ppc.integer + element_list = LBRACK + pp.delimited_list(element) + RBRACK + + # add parse actions to convert from ParseResults to actual Python collection types + def as_python_list(t): + return pp.ParseResults.List(t.as_list()) + element_list.add_parse_action(as_python_list) + + element <<= item | element_list + + element.run_tests(''' + 100 + [2,3,4] + [[2, 1],3,4] + [(2, 1),3,4] + (2,3,4) + ''', post_parse=lambda s, r: (r[0], type(r[0]))) + + prints: + + 100 + (100, <class 'int'>) + + [2,3,4] + ([2, 3, 4], <class 'list'>) + + [[2, 1],3,4] + ([[2, 1], 3, 4], <class 'list'>) + + (Used internally by :class:`Group` when `aslist=True`.) + """ + + def __new__(cls, contained=None): + if contained is None: + contained = [] + + if not isinstance(contained, list): + raise TypeError( + "{} may only be constructed with a list," + " not {}".format(cls.__name__, type(contained).__name__) + ) + + return list.__new__(cls) + + def __new__(cls, toklist=None, name=None, **kwargs): + if isinstance(toklist, ParseResults): + return toklist + self = object.__new__(cls) + self._name = None + self._parent = None + self._all_names = set() + + if toklist is None: + self._toklist = [] + elif isinstance(toklist, (list, _generator_type)): + self._toklist = ( + [toklist[:]] + if isinstance(toklist, ParseResults.List) + else list(toklist) + ) + else: + self._toklist = [toklist] + self._tokdict = dict() + return self + + # Performance tuning: we construct a *lot* of these, so keep this + # constructor as small and fast as possible + def __init__( + self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance + ): + self._modal = modal + if name is not None and name != "": + if isinstance(name, int): + name = str(name) + if not modal: + self._all_names = {name} + self._name = name + if toklist not in self._null_values: + if isinstance(toklist, (str_type, type)): + toklist = [toklist] + if asList: + if isinstance(toklist, ParseResults): + self[name] = _ParseResultsWithOffset( + ParseResults(toklist._toklist), 0 + ) + else: + self[name] = _ParseResultsWithOffset( + ParseResults(toklist[0]), 0 + ) + self[name]._name = name + else: + try: + self[name] = toklist[0] + except (KeyError, TypeError, IndexError): + if toklist is not self: + self[name] = toklist + else: + self._name = name + + def __getitem__(self, i): + if isinstance(i, (int, slice)): + return self._toklist[i] + else: + if i not in self._all_names: + return self._tokdict[i][-1][0] + else: + return ParseResults([v[0] for v in self._tokdict[i]]) + + def __setitem__(self, k, v, isinstance=isinstance): + if isinstance(v, _ParseResultsWithOffset): + self._tokdict[k] = self._tokdict.get(k, list()) + [v] + sub = v[0] + elif isinstance(k, (int, slice)): + self._toklist[k] = v + sub = v + else: + self._tokdict[k] = self._tokdict.get(k, list()) + [ + _ParseResultsWithOffset(v, 0) + ] + sub = v + if isinstance(sub, ParseResults): + sub._parent = wkref(self) + + def __delitem__(self, i): + if isinstance(i, (int, slice)): + mylen = len(self._toklist) + del self._toklist[i] + + # convert int to slice + if isinstance(i, int): + if i < 0: + i += mylen + i = slice(i, i + 1) + # get removed indices + removed = list(range(*i.indices(mylen))) + removed.reverse() + # fixup indices in token dictionary + for name, occurrences in self._tokdict.items(): + for j in removed: + for k, (value, position) in enumerate(occurrences): + occurrences[k] = _ParseResultsWithOffset( + value, position - (position > j) + ) + else: + del self._tokdict[i] + + def __contains__(self, k) -> bool: + return k in self._tokdict + + def __len__(self) -> int: + return len(self._toklist) + + def __bool__(self) -> bool: + return not not (self._toklist or self._tokdict) + + def __iter__(self) -> Iterator: + return iter(self._toklist) + + def __reversed__(self) -> Iterator: + return iter(self._toklist[::-1]) + + def keys(self): + return iter(self._tokdict) + + def values(self): + return (self[k] for k in self.keys()) + + def items(self): + return ((k, self[k]) for k in self.keys()) + + def haskeys(self) -> bool: + """ + Since ``keys()`` returns an iterator, this method is helpful in bypassing + code that looks for the existence of any defined results names.""" + return bool(self._tokdict) + + def pop(self, *args, **kwargs): + """ + Removes and returns item at specified index (default= ``last``). + Supports both ``list`` and ``dict`` semantics for ``pop()``. If + passed no argument or an integer argument, it will use ``list`` + semantics and pop tokens from the list of parsed tokens. If passed + a non-integer argument (most likely a string), it will use ``dict`` + semantics and pop the corresponding value from any defined results + names. A second default return value argument is supported, just as in + ``dict.pop()``. + + Example:: + + numlist = Word(nums)[...] + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] + + def remove_first(tokens): + tokens.pop(0) + numlist.add_parse_action(remove_first) + print(numlist.parse_string("0 123 321")) # -> ['123', '321'] + + label = Word(alphas) + patt = label("LABEL") + Word(nums)[1, ...] + print(patt.parse_string("AAB 123 321").dump()) + + # Use pop() in a parse action to remove named result (note that corresponding value is not + # removed from list form of results) + def remove_LABEL(tokens): + tokens.pop("LABEL") + return tokens + patt.add_parse_action(remove_LABEL) + print(patt.parse_string("AAB 123 321").dump()) + + prints:: + + ['AAB', '123', '321'] + - LABEL: 'AAB' + + ['AAB', '123', '321'] + """ + if not args: + args = [-1] + for k, v in kwargs.items(): + if k == "default": + args = (args[0], v) + else: + raise TypeError( + "pop() got an unexpected keyword argument {!r}".format(k) + ) + if isinstance(args[0], int) or len(args) == 1 or args[0] in self: + index = args[0] + ret = self[index] + del self[index] + return ret + else: + defaultvalue = args[1] + return defaultvalue + + def get(self, key, default_value=None): + """ + Returns named result matching the given key, or if there is no + such name, then returns the given ``default_value`` or ``None`` if no + ``default_value`` is specified. + + Similar to ``dict.get()``. + + Example:: + + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + result = date_str.parse_string("1999/12/31") + print(result.get("year")) # -> '1999' + print(result.get("hour", "not specified")) # -> 'not specified' + print(result.get("hour")) # -> None + """ + if key in self: + return self[key] + else: + return default_value + + def insert(self, index, ins_string): + """ + Inserts new element at location index in the list of parsed tokens. + + Similar to ``list.insert()``. + + Example:: + + numlist = Word(nums)[...] + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] + + # use a parse action to insert the parse location in the front of the parsed results + def insert_locn(locn, tokens): + tokens.insert(0, locn) + numlist.add_parse_action(insert_locn) + print(numlist.parse_string("0 123 321")) # -> [0, '0', '123', '321'] + """ + self._toklist.insert(index, ins_string) + # fixup indices in token dictionary + for name, occurrences in self._tokdict.items(): + for k, (value, position) in enumerate(occurrences): + occurrences[k] = _ParseResultsWithOffset( + value, position + (position > index) + ) + + def append(self, item): + """ + Add single element to end of ``ParseResults`` list of elements. + + Example:: + + numlist = Word(nums)[...] + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] + + # use a parse action to compute the sum of the parsed integers, and add it to the end + def append_sum(tokens): + tokens.append(sum(map(int, tokens))) + numlist.add_parse_action(append_sum) + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321', 444] + """ + self._toklist.append(item) + + def extend(self, itemseq): + """ + Add sequence of elements to end of ``ParseResults`` list of elements. + + Example:: + + patt = Word(alphas)[1, ...] + + # use a parse action to append the reverse of the matched strings, to make a palindrome + def make_palindrome(tokens): + tokens.extend(reversed([t[::-1] for t in tokens])) + return ''.join(tokens) + patt.add_parse_action(make_palindrome) + print(patt.parse_string("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl' + """ + if isinstance(itemseq, ParseResults): + self.__iadd__(itemseq) + else: + self._toklist.extend(itemseq) + + def clear(self): + """ + Clear all elements and results names. + """ + del self._toklist[:] + self._tokdict.clear() + + def __getattr__(self, name): + try: + return self[name] + except KeyError: + if name.startswith("__"): + raise AttributeError(name) + return "" + + def __add__(self, other) -> "ParseResults": + ret = self.copy() + ret += other + return ret + + def __iadd__(self, other) -> "ParseResults": + if other._tokdict: + offset = len(self._toklist) + addoffset = lambda a: offset if a < 0 else a + offset + otheritems = other._tokdict.items() + otherdictitems = [ + (k, _ParseResultsWithOffset(v[0], addoffset(v[1]))) + for k, vlist in otheritems + for v in vlist + ] + for k, v in otherdictitems: + self[k] = v + if isinstance(v[0], ParseResults): + v[0]._parent = wkref(self) + + self._toklist += other._toklist + self._all_names |= other._all_names + return self + + def __radd__(self, other) -> "ParseResults": + if isinstance(other, int) and other == 0: + # useful for merging many ParseResults using sum() builtin + return self.copy() + else: + # this may raise a TypeError - so be it + return other + self + + def __repr__(self) -> str: + return "{}({!r}, {})".format(type(self).__name__, self._toklist, self.as_dict()) + + def __str__(self) -> str: + return ( + "[" + + ", ".join( + [ + str(i) if isinstance(i, ParseResults) else repr(i) + for i in self._toklist + ] + ) + + "]" + ) + + def _asStringList(self, sep=""): + out = [] + for item in self._toklist: + if out and sep: + out.append(sep) + if isinstance(item, ParseResults): + out += item._asStringList() + else: + out.append(str(item)) + return out + + def as_list(self) -> list: + """ + Returns the parse results as a nested list of matching tokens, all converted to strings. + + Example:: + + patt = Word(alphas)[1, ...] + result = patt.parse_string("sldkj lsdkj sldkj") + # even though the result prints in string-like form, it is actually a pyparsing ParseResults + print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj'] + + # Use as_list() to create an actual list + result_list = result.as_list() + print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj'] + """ + return [ + res.as_list() if isinstance(res, ParseResults) else res + for res in self._toklist + ] + + def as_dict(self) -> dict: + """ + Returns the named parse results as a nested dictionary. + + Example:: + + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + result = date_str.parse_string('12/31/1999') + print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]}) + + result_dict = result.as_dict() + print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'} + + # even though a ParseResults supports dict-like access, sometime you just need to have a dict + import json + print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable + print(json.dumps(result.as_dict())) # -> {"month": "31", "day": "1999", "year": "12"} + """ + + def to_item(obj): + if isinstance(obj, ParseResults): + return obj.as_dict() if obj.haskeys() else [to_item(v) for v in obj] + else: + return obj + + return dict((k, to_item(v)) for k, v in self.items()) + + def copy(self) -> "ParseResults": + """ + Returns a new copy of a :class:`ParseResults` object. + """ + ret = ParseResults(self._toklist) + ret._tokdict = self._tokdict.copy() + ret._parent = self._parent + ret._all_names |= self._all_names + ret._name = self._name + return ret + + def get_name(self): + r""" + Returns the results name for this token expression. Useful when several + different expressions might match at a particular location. + + Example:: + + integer = Word(nums) + ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d") + house_number_expr = Suppress('#') + Word(nums, alphanums) + user_data = (Group(house_number_expr)("house_number") + | Group(ssn_expr)("ssn") + | Group(integer)("age")) + user_info = user_data[1, ...] + + result = user_info.parse_string("22 111-22-3333 #221B") + for item in result: + print(item.get_name(), ':', item[0]) + + prints:: + + age : 22 + ssn : 111-22-3333 + house_number : 221B + """ + if self._name: + return self._name + elif self._parent: + par = self._parent() + + def find_in_parent(sub): + return next( + ( + k + for k, vlist in par._tokdict.items() + for v, loc in vlist + if sub is v + ), + None, + ) + + return find_in_parent(self) if par else None + elif ( + len(self) == 1 + and len(self._tokdict) == 1 + and next(iter(self._tokdict.values()))[0][1] in (0, -1) + ): + return next(iter(self._tokdict.keys())) + else: + return None + + def dump(self, indent="", full=True, include_list=True, _depth=0) -> str: + """ + Diagnostic method for listing out the contents of + a :class:`ParseResults`. Accepts an optional ``indent`` argument so + that this string can be embedded in a nested display of other data. + + Example:: + + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + result = date_str.parse_string('1999/12/31') + print(result.dump()) + + prints:: + + ['1999', '/', '12', '/', '31'] + - day: '31' + - month: '12' + - year: '1999' + """ + out = [] + NL = "\n" + out.append(indent + str(self.as_list()) if include_list else "") + + if full: + if self.haskeys(): + items = sorted((str(k), v) for k, v in self.items()) + for k, v in items: + if out: + out.append(NL) + out.append("{}{}- {}: ".format(indent, (" " * _depth), k)) + if isinstance(v, ParseResults): + if v: + out.append( + v.dump( + indent=indent, + full=full, + include_list=include_list, + _depth=_depth + 1, + ) + ) + else: + out.append(str(v)) + else: + out.append(repr(v)) + if any(isinstance(vv, ParseResults) for vv in self): + v = self + for i, vv in enumerate(v): + if isinstance(vv, ParseResults): + out.append( + "\n{}{}[{}]:\n{}{}{}".format( + indent, + (" " * (_depth)), + i, + indent, + (" " * (_depth + 1)), + vv.dump( + indent=indent, + full=full, + include_list=include_list, + _depth=_depth + 1, + ), + ) + ) + else: + out.append( + "\n%s%s[%d]:\n%s%s%s" + % ( + indent, + (" " * (_depth)), + i, + indent, + (" " * (_depth + 1)), + str(vv), + ) + ) + + return "".join(out) + + def pprint(self, *args, **kwargs): + """ + Pretty-printer for parsed results as a list, using the + `pprint <https://docs.python.org/3/library/pprint.html>`_ module. + Accepts additional positional or keyword args as defined for + `pprint.pprint <https://docs.python.org/3/library/pprint.html#pprint.pprint>`_ . + + Example:: + + ident = Word(alphas, alphanums) + num = Word(nums) + func = Forward() + term = ident | num | Group('(' + func + ')') + func <<= ident + Group(Optional(delimited_list(term))) + result = func.parse_string("fna a,b,(fnb c,d,200),100") + result.pprint(width=40) + + prints:: + + ['fna', + ['a', + 'b', + ['(', 'fnb', ['c', 'd', '200'], ')'], + '100']] + """ + pprint.pprint(self.as_list(), *args, **kwargs) + + # add support for pickle protocol + def __getstate__(self): + return ( + self._toklist, + ( + self._tokdict.copy(), + self._parent is not None and self._parent() or None, + self._all_names, + self._name, + ), + ) + + def __setstate__(self, state): + self._toklist, (self._tokdict, par, inAccumNames, self._name) = state + self._all_names = set(inAccumNames) + if par is not None: + self._parent = wkref(par) + else: + self._parent = None + + def __getnewargs__(self): + return self._toklist, self._name + + def __dir__(self): + return dir(type(self)) + list(self.keys()) + + @classmethod + def from_dict(cls, other, name=None) -> "ParseResults": + """ + Helper classmethod to construct a ``ParseResults`` from a ``dict``, preserving the + name-value relations as results names. If an optional ``name`` argument is + given, a nested ``ParseResults`` will be returned. + """ + + def is_iterable(obj): + try: + iter(obj) + except Exception: + return False + else: + return not isinstance(obj, str_type) + + ret = cls([]) + for k, v in other.items(): + if isinstance(v, Mapping): + ret += cls.from_dict(v, name=k) + else: + ret += cls([v], name=k, asList=is_iterable(v)) + if name is not None: + ret = cls([ret], name=name) + return ret + + asList = as_list + asDict = as_dict + getName = get_name + + +MutableMapping.register(ParseResults) +MutableSequence.register(ParseResults) diff --git a/pkg_resources/_vendor/pyparsing/testing.py b/pkg_resources/_vendor/pyparsing/testing.py new file mode 100644 index 00000000..84a0ef17 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/testing.py @@ -0,0 +1,331 @@ +# testing.py + +from contextlib import contextmanager +import typing + +from .core import ( + ParserElement, + ParseException, + Keyword, + __diag__, + __compat__, +) + + +class pyparsing_test: + """ + namespace class for classes useful in writing unit tests + """ + + class reset_pyparsing_context: + """ + Context manager to be used when writing unit tests that modify pyparsing config values: + - packrat parsing + - bounded recursion parsing + - default whitespace characters. + - default keyword characters + - literal string auto-conversion class + - __diag__ settings + + Example:: + + with reset_pyparsing_context(): + # test that literals used to construct a grammar are automatically suppressed + ParserElement.inlineLiteralsUsing(Suppress) + + term = Word(alphas) | Word(nums) + group = Group('(' + term[...] + ')') + + # assert that the '()' characters are not included in the parsed tokens + self.assertParseAndCheckList(group, "(abc 123 def)", ['abc', '123', 'def']) + + # after exiting context manager, literals are converted to Literal expressions again + """ + + def __init__(self): + self._save_context = {} + + def save(self): + self._save_context["default_whitespace"] = ParserElement.DEFAULT_WHITE_CHARS + self._save_context["default_keyword_chars"] = Keyword.DEFAULT_KEYWORD_CHARS + + self._save_context[ + "literal_string_class" + ] = ParserElement._literalStringClass + + self._save_context["verbose_stacktrace"] = ParserElement.verbose_stacktrace + + self._save_context["packrat_enabled"] = ParserElement._packratEnabled + if ParserElement._packratEnabled: + self._save_context[ + "packrat_cache_size" + ] = ParserElement.packrat_cache.size + else: + self._save_context["packrat_cache_size"] = None + self._save_context["packrat_parse"] = ParserElement._parse + self._save_context[ + "recursion_enabled" + ] = ParserElement._left_recursion_enabled + + self._save_context["__diag__"] = { + name: getattr(__diag__, name) for name in __diag__._all_names + } + + self._save_context["__compat__"] = { + "collect_all_And_tokens": __compat__.collect_all_And_tokens + } + + return self + + def restore(self): + # reset pyparsing global state + if ( + ParserElement.DEFAULT_WHITE_CHARS + != self._save_context["default_whitespace"] + ): + ParserElement.set_default_whitespace_chars( + self._save_context["default_whitespace"] + ) + + ParserElement.verbose_stacktrace = self._save_context["verbose_stacktrace"] + + Keyword.DEFAULT_KEYWORD_CHARS = self._save_context["default_keyword_chars"] + ParserElement.inlineLiteralsUsing( + self._save_context["literal_string_class"] + ) + + for name, value in self._save_context["__diag__"].items(): + (__diag__.enable if value else __diag__.disable)(name) + + ParserElement._packratEnabled = False + if self._save_context["packrat_enabled"]: + ParserElement.enable_packrat(self._save_context["packrat_cache_size"]) + else: + ParserElement._parse = self._save_context["packrat_parse"] + ParserElement._left_recursion_enabled = self._save_context[ + "recursion_enabled" + ] + + __compat__.collect_all_And_tokens = self._save_context["__compat__"] + + return self + + def copy(self): + ret = type(self)() + ret._save_context.update(self._save_context) + return ret + + def __enter__(self): + return self.save() + + def __exit__(self, *args): + self.restore() + + class TestParseResultsAsserts: + """ + A mixin class to add parse results assertion methods to normal unittest.TestCase classes. + """ + + def assertParseResultsEquals( + self, result, expected_list=None, expected_dict=None, msg=None + ): + """ + Unit test assertion to compare a :class:`ParseResults` object with an optional ``expected_list``, + and compare any defined results names with an optional ``expected_dict``. + """ + if expected_list is not None: + self.assertEqual(expected_list, result.as_list(), msg=msg) + if expected_dict is not None: + self.assertEqual(expected_dict, result.as_dict(), msg=msg) + + def assertParseAndCheckList( + self, expr, test_string, expected_list, msg=None, verbose=True + ): + """ + Convenience wrapper assert to test a parser element and input string, and assert that + the resulting ``ParseResults.asList()`` is equal to the ``expected_list``. + """ + result = expr.parse_string(test_string, parse_all=True) + if verbose: + print(result.dump()) + else: + print(result.as_list()) + self.assertParseResultsEquals(result, expected_list=expected_list, msg=msg) + + def assertParseAndCheckDict( + self, expr, test_string, expected_dict, msg=None, verbose=True + ): + """ + Convenience wrapper assert to test a parser element and input string, and assert that + the resulting ``ParseResults.asDict()`` is equal to the ``expected_dict``. + """ + result = expr.parse_string(test_string, parseAll=True) + if verbose: + print(result.dump()) + else: + print(result.as_list()) + self.assertParseResultsEquals(result, expected_dict=expected_dict, msg=msg) + + def assertRunTestResults( + self, run_tests_report, expected_parse_results=None, msg=None + ): + """ + Unit test assertion to evaluate output of ``ParserElement.runTests()``. If a list of + list-dict tuples is given as the ``expected_parse_results`` argument, then these are zipped + with the report tuples returned by ``runTests`` and evaluated using ``assertParseResultsEquals``. + Finally, asserts that the overall ``runTests()`` success value is ``True``. + + :param run_tests_report: tuple(bool, [tuple(str, ParseResults or Exception)]) returned from runTests + :param expected_parse_results (optional): [tuple(str, list, dict, Exception)] + """ + run_test_success, run_test_results = run_tests_report + + if expected_parse_results is not None: + merged = [ + (*rpt, expected) + for rpt, expected in zip(run_test_results, expected_parse_results) + ] + for test_string, result, expected in merged: + # expected should be a tuple containing a list and/or a dict or an exception, + # and optional failure message string + # an empty tuple will skip any result validation + fail_msg = next( + (exp for exp in expected if isinstance(exp, str)), None + ) + expected_exception = next( + ( + exp + for exp in expected + if isinstance(exp, type) and issubclass(exp, Exception) + ), + None, + ) + if expected_exception is not None: + with self.assertRaises( + expected_exception=expected_exception, msg=fail_msg or msg + ): + if isinstance(result, Exception): + raise result + else: + expected_list = next( + (exp for exp in expected if isinstance(exp, list)), None + ) + expected_dict = next( + (exp for exp in expected if isinstance(exp, dict)), None + ) + if (expected_list, expected_dict) != (None, None): + self.assertParseResultsEquals( + result, + expected_list=expected_list, + expected_dict=expected_dict, + msg=fail_msg or msg, + ) + else: + # warning here maybe? + print("no validation for {!r}".format(test_string)) + + # do this last, in case some specific test results can be reported instead + self.assertTrue( + run_test_success, msg=msg if msg is not None else "failed runTests" + ) + + @contextmanager + def assertRaisesParseException(self, exc_type=ParseException, msg=None): + with self.assertRaises(exc_type, msg=msg): + yield + + @staticmethod + def with_line_numbers( + s: str, + start_line: typing.Optional[int] = None, + end_line: typing.Optional[int] = None, + expand_tabs: bool = True, + eol_mark: str = "|", + mark_spaces: typing.Optional[str] = None, + mark_control: typing.Optional[str] = None, + ) -> str: + """ + Helpful method for debugging a parser - prints a string with line and column numbers. + (Line and column numbers are 1-based.) + + :param s: tuple(bool, str - string to be printed with line and column numbers + :param start_line: int - (optional) starting line number in s to print (default=1) + :param end_line: int - (optional) ending line number in s to print (default=len(s)) + :param expand_tabs: bool - (optional) expand tabs to spaces, to match the pyparsing default + :param eol_mark: str - (optional) string to mark the end of lines, helps visualize trailing spaces (default="|") + :param mark_spaces: str - (optional) special character to display in place of spaces + :param mark_control: str - (optional) convert non-printing control characters to a placeholding + character; valid values: + - "unicode" - replaces control chars with Unicode symbols, such as "␍" and "␊" + - any single character string - replace control characters with given string + - None (default) - string is displayed as-is + + :return: str - input string with leading line numbers and column number headers + """ + if expand_tabs: + s = s.expandtabs() + if mark_control is not None: + if mark_control == "unicode": + tbl = str.maketrans( + {c: u for c, u in zip(range(0, 33), range(0x2400, 0x2433))} + | {127: 0x2421} + ) + eol_mark = "" + else: + tbl = str.maketrans( + {c: mark_control for c in list(range(0, 32)) + [127]} + ) + s = s.translate(tbl) + if mark_spaces is not None and mark_spaces != " ": + if mark_spaces == "unicode": + tbl = str.maketrans({9: 0x2409, 32: 0x2423}) + s = s.translate(tbl) + else: + s = s.replace(" ", mark_spaces) + if start_line is None: + start_line = 1 + if end_line is None: + end_line = len(s) + end_line = min(end_line, len(s)) + start_line = min(max(1, start_line), end_line) + + if mark_control != "unicode": + s_lines = s.splitlines()[start_line - 1 : end_line] + else: + s_lines = [line + "␊" for line in s.split("␊")[start_line - 1 : end_line]] + if not s_lines: + return "" + + lineno_width = len(str(end_line)) + max_line_len = max(len(line) for line in s_lines) + lead = " " * (lineno_width + 1) + if max_line_len >= 99: + header0 = ( + lead + + "".join( + "{}{}".format(" " * 99, (i + 1) % 100) + for i in range(max(max_line_len // 100, 1)) + ) + + "\n" + ) + else: + header0 = "" + header1 = ( + header0 + + lead + + "".join( + " {}".format((i + 1) % 10) + for i in range(-(-max_line_len // 10)) + ) + + "\n" + ) + header2 = lead + "1234567890" * (-(-max_line_len // 10)) + "\n" + return ( + header1 + + header2 + + "\n".join( + "{:{}d}:{}{}".format(i, lineno_width, line, eol_mark) + for i, line in enumerate(s_lines, start=start_line) + ) + + "\n" + ) diff --git a/pkg_resources/_vendor/pyparsing/unicode.py b/pkg_resources/_vendor/pyparsing/unicode.py new file mode 100644 index 00000000..06526203 --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/unicode.py @@ -0,0 +1,352 @@ +# unicode.py + +import sys +from itertools import filterfalse +from typing import List, Tuple, Union + + +class _lazyclassproperty: + def __init__(self, fn): + self.fn = fn + self.__doc__ = fn.__doc__ + self.__name__ = fn.__name__ + + def __get__(self, obj, cls): + if cls is None: + cls = type(obj) + if not hasattr(cls, "_intern") or any( + cls._intern is getattr(superclass, "_intern", []) + for superclass in cls.__mro__[1:] + ): + cls._intern = {} + attrname = self.fn.__name__ + if attrname not in cls._intern: + cls._intern[attrname] = self.fn(cls) + return cls._intern[attrname] + + +UnicodeRangeList = List[Union[Tuple[int, int], Tuple[int]]] + + +class unicode_set: + """ + A set of Unicode characters, for language-specific strings for + ``alphas``, ``nums``, ``alphanums``, and ``printables``. + A unicode_set is defined by a list of ranges in the Unicode character + set, in a class attribute ``_ranges``. Ranges can be specified using + 2-tuples or a 1-tuple, such as:: + + _ranges = [ + (0x0020, 0x007e), + (0x00a0, 0x00ff), + (0x0100,), + ] + + Ranges are left- and right-inclusive. A 1-tuple of (x,) is treated as (x, x). + + A unicode set can also be defined using multiple inheritance of other unicode sets:: + + class CJK(Chinese, Japanese, Korean): + pass + """ + + _ranges: UnicodeRangeList = [] + + @_lazyclassproperty + def _chars_for_ranges(cls): + ret = [] + for cc in cls.__mro__: + if cc is unicode_set: + break + for rr in getattr(cc, "_ranges", ()): + ret.extend(range(rr[0], rr[-1] + 1)) + return [chr(c) for c in sorted(set(ret))] + + @_lazyclassproperty + def printables(cls): + "all non-whitespace characters in this range" + return "".join(filterfalse(str.isspace, cls._chars_for_ranges)) + + @_lazyclassproperty + def alphas(cls): + "all alphabetic characters in this range" + return "".join(filter(str.isalpha, cls._chars_for_ranges)) + + @_lazyclassproperty + def nums(cls): + "all numeric digit characters in this range" + return "".join(filter(str.isdigit, cls._chars_for_ranges)) + + @_lazyclassproperty + def alphanums(cls): + "all alphanumeric characters in this range" + return cls.alphas + cls.nums + + @_lazyclassproperty + def identchars(cls): + "all characters in this range that are valid identifier characters, plus underscore '_'" + return "".join( + sorted( + set( + "".join(filter(str.isidentifier, cls._chars_for_ranges)) + + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµº" + + "ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ" + + "_" + ) + ) + ) + + @_lazyclassproperty + def identbodychars(cls): + """ + all characters in this range that are valid identifier body characters, + plus the digits 0-9 + """ + return "".join( + sorted( + set( + cls.identchars + + "0123456789" + + "".join( + [c for c in cls._chars_for_ranges if ("_" + c).isidentifier()] + ) + ) + ) + ) + + +class pyparsing_unicode(unicode_set): + """ + A namespace class for defining common language unicode_sets. + """ + + # fmt: off + + # define ranges in language character sets + _ranges: UnicodeRangeList = [ + (0x0020, sys.maxunicode), + ] + + class BasicMultilingualPlane(unicode_set): + "Unicode set for the Basic Multilingual Plane" + _ranges: UnicodeRangeList = [ + (0x0020, 0xFFFF), + ] + + class Latin1(unicode_set): + "Unicode set for Latin-1 Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0020, 0x007E), + (0x00A0, 0x00FF), + ] + + class LatinA(unicode_set): + "Unicode set for Latin-A Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0100, 0x017F), + ] + + class LatinB(unicode_set): + "Unicode set for Latin-B Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0180, 0x024F), + ] + + class Greek(unicode_set): + "Unicode set for Greek Unicode Character Ranges" + _ranges: UnicodeRangeList = [ + (0x0342, 0x0345), + (0x0370, 0x0377), + (0x037A, 0x037F), + (0x0384, 0x038A), + (0x038C,), + (0x038E, 0x03A1), + (0x03A3, 0x03E1), + (0x03F0, 0x03FF), + (0x1D26, 0x1D2A), + (0x1D5E,), + (0x1D60,), + (0x1D66, 0x1D6A), + (0x1F00, 0x1F15), + (0x1F18, 0x1F1D), + (0x1F20, 0x1F45), + (0x1F48, 0x1F4D), + (0x1F50, 0x1F57), + (0x1F59,), + (0x1F5B,), + (0x1F5D,), + (0x1F5F, 0x1F7D), + (0x1F80, 0x1FB4), + (0x1FB6, 0x1FC4), + (0x1FC6, 0x1FD3), + (0x1FD6, 0x1FDB), + (0x1FDD, 0x1FEF), + (0x1FF2, 0x1FF4), + (0x1FF6, 0x1FFE), + (0x2129,), + (0x2719, 0x271A), + (0xAB65,), + (0x10140, 0x1018D), + (0x101A0,), + (0x1D200, 0x1D245), + (0x1F7A1, 0x1F7A7), + ] + + class Cyrillic(unicode_set): + "Unicode set for Cyrillic Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0400, 0x052F), + (0x1C80, 0x1C88), + (0x1D2B,), + (0x1D78,), + (0x2DE0, 0x2DFF), + (0xA640, 0xA672), + (0xA674, 0xA69F), + (0xFE2E, 0xFE2F), + ] + + class Chinese(unicode_set): + "Unicode set for Chinese Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x2E80, 0x2E99), + (0x2E9B, 0x2EF3), + (0x31C0, 0x31E3), + (0x3400, 0x4DB5), + (0x4E00, 0x9FEF), + (0xA700, 0xA707), + (0xF900, 0xFA6D), + (0xFA70, 0xFAD9), + (0x16FE2, 0x16FE3), + (0x1F210, 0x1F212), + (0x1F214, 0x1F23B), + (0x1F240, 0x1F248), + (0x20000, 0x2A6D6), + (0x2A700, 0x2B734), + (0x2B740, 0x2B81D), + (0x2B820, 0x2CEA1), + (0x2CEB0, 0x2EBE0), + (0x2F800, 0x2FA1D), + ] + + class Japanese(unicode_set): + "Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana ranges" + _ranges: UnicodeRangeList = [] + + class Kanji(unicode_set): + "Unicode set for Kanji Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x4E00, 0x9FBF), + (0x3000, 0x303F), + ] + + class Hiragana(unicode_set): + "Unicode set for Hiragana Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x3041, 0x3096), + (0x3099, 0x30A0), + (0x30FC,), + (0xFF70,), + (0x1B001,), + (0x1B150, 0x1B152), + (0x1F200,), + ] + + class Katakana(unicode_set): + "Unicode set for Katakana Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x3099, 0x309C), + (0x30A0, 0x30FF), + (0x31F0, 0x31FF), + (0x32D0, 0x32FE), + (0xFF65, 0xFF9F), + (0x1B000,), + (0x1B164, 0x1B167), + (0x1F201, 0x1F202), + (0x1F213,), + ] + + class Hangul(unicode_set): + "Unicode set for Hangul (Korean) Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x1100, 0x11FF), + (0x302E, 0x302F), + (0x3131, 0x318E), + (0x3200, 0x321C), + (0x3260, 0x327B), + (0x327E,), + (0xA960, 0xA97C), + (0xAC00, 0xD7A3), + (0xD7B0, 0xD7C6), + (0xD7CB, 0xD7FB), + (0xFFA0, 0xFFBE), + (0xFFC2, 0xFFC7), + (0xFFCA, 0xFFCF), + (0xFFD2, 0xFFD7), + (0xFFDA, 0xFFDC), + ] + + Korean = Hangul + + class CJK(Chinese, Japanese, Hangul): + "Unicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character Range" + + class Thai(unicode_set): + "Unicode set for Thai Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0E01, 0x0E3A), + (0x0E3F, 0x0E5B) + ] + + class Arabic(unicode_set): + "Unicode set for Arabic Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0600, 0x061B), + (0x061E, 0x06FF), + (0x0700, 0x077F), + ] + + class Hebrew(unicode_set): + "Unicode set for Hebrew Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0591, 0x05C7), + (0x05D0, 0x05EA), + (0x05EF, 0x05F4), + (0xFB1D, 0xFB36), + (0xFB38, 0xFB3C), + (0xFB3E,), + (0xFB40, 0xFB41), + (0xFB43, 0xFB44), + (0xFB46, 0xFB4F), + ] + + class Devanagari(unicode_set): + "Unicode set for Devanagari Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0900, 0x097F), + (0xA8E0, 0xA8FF) + ] + + # fmt: on + + +pyparsing_unicode.Japanese._ranges = ( + pyparsing_unicode.Japanese.Kanji._ranges + + pyparsing_unicode.Japanese.Hiragana._ranges + + pyparsing_unicode.Japanese.Katakana._ranges +) + +pyparsing_unicode.BMP = pyparsing_unicode.BasicMultilingualPlane + +# add language identifiers using language Unicode +pyparsing_unicode.العربية = pyparsing_unicode.Arabic +pyparsing_unicode.中文 = pyparsing_unicode.Chinese +pyparsing_unicode.кириллица = pyparsing_unicode.Cyrillic +pyparsing_unicode.Ελληνικά = pyparsing_unicode.Greek +pyparsing_unicode.עִברִית = pyparsing_unicode.Hebrew +pyparsing_unicode.日本語 = pyparsing_unicode.Japanese +pyparsing_unicode.Japanese.漢字 = pyparsing_unicode.Japanese.Kanji +pyparsing_unicode.Japanese.カタカナ = pyparsing_unicode.Japanese.Katakana +pyparsing_unicode.Japanese.ひらがな = pyparsing_unicode.Japanese.Hiragana +pyparsing_unicode.한국어 = pyparsing_unicode.Korean +pyparsing_unicode.ไทย = pyparsing_unicode.Thai +pyparsing_unicode.देवनागरी = pyparsing_unicode.Devanagari diff --git a/pkg_resources/_vendor/pyparsing/util.py b/pkg_resources/_vendor/pyparsing/util.py new file mode 100644 index 00000000..34ce092c --- /dev/null +++ b/pkg_resources/_vendor/pyparsing/util.py @@ -0,0 +1,235 @@ +# util.py +import warnings +import types +import collections +import itertools +from functools import lru_cache +from typing import List, Union, Iterable + +_bslash = chr(92) + + +class __config_flags: + """Internal class for defining compatibility and debugging flags""" + + _all_names: List[str] = [] + _fixed_names: List[str] = [] + _type_desc = "configuration" + + @classmethod + def _set(cls, dname, value): + if dname in cls._fixed_names: + warnings.warn( + "{}.{} {} is {} and cannot be overridden".format( + cls.__name__, + dname, + cls._type_desc, + str(getattr(cls, dname)).upper(), + ) + ) + return + if dname in cls._all_names: + setattr(cls, dname, value) + else: + raise ValueError("no such {} {!r}".format(cls._type_desc, dname)) + + enable = classmethod(lambda cls, name: cls._set(name, True)) + disable = classmethod(lambda cls, name: cls._set(name, False)) + + +@lru_cache(maxsize=128) +def col(loc: int, strg: str) -> int: + """ + Returns current column within a string, counting newlines as line separators. + The first column is number 1. + + Note: the default parsing behavior is to expand tabs in the input string + before starting the parsing process. See + :class:`ParserElement.parseString` for more + information on parsing strings containing ``<TAB>`` s, and suggested + methods to maintain a consistent view of the parsed string, the parse + location, and line and column positions within the parsed string. + """ + s = strg + return 1 if 0 < loc < len(s) and s[loc - 1] == "\n" else loc - s.rfind("\n", 0, loc) + + +@lru_cache(maxsize=128) +def lineno(loc: int, strg: str) -> int: + """Returns current line number within a string, counting newlines as line separators. + The first line is number 1. + + Note - the default parsing behavior is to expand tabs in the input string + before starting the parsing process. See :class:`ParserElement.parseString` + for more information on parsing strings containing ``<TAB>`` s, and + suggested methods to maintain a consistent view of the parsed string, the + parse location, and line and column positions within the parsed string. + """ + return strg.count("\n", 0, loc) + 1 + + +@lru_cache(maxsize=128) +def line(loc: int, strg: str) -> str: + """ + Returns the line of text containing loc within a string, counting newlines as line separators. + """ + last_cr = strg.rfind("\n", 0, loc) + next_cr = strg.find("\n", loc) + return strg[last_cr + 1 : next_cr] if next_cr >= 0 else strg[last_cr + 1 :] + + +class _UnboundedCache: + def __init__(self): + cache = {} + cache_get = cache.get + self.not_in_cache = not_in_cache = object() + + def get(_, key): + return cache_get(key, not_in_cache) + + def set_(_, key, value): + cache[key] = value + + def clear(_): + cache.clear() + + self.size = None + self.get = types.MethodType(get, self) + self.set = types.MethodType(set_, self) + self.clear = types.MethodType(clear, self) + + +class _FifoCache: + def __init__(self, size): + self.not_in_cache = not_in_cache = object() + cache = collections.OrderedDict() + cache_get = cache.get + + def get(_, key): + return cache_get(key, not_in_cache) + + def set_(_, key, value): + cache[key] = value + while len(cache) > size: + cache.popitem(last=False) + + def clear(_): + cache.clear() + + self.size = size + self.get = types.MethodType(get, self) + self.set = types.MethodType(set_, self) + self.clear = types.MethodType(clear, self) + + +class LRUMemo: + """ + A memoizing mapping that retains `capacity` deleted items + + The memo tracks retained items by their access order; once `capacity` items + are retained, the least recently used item is discarded. + """ + + def __init__(self, capacity): + self._capacity = capacity + self._active = {} + self._memory = collections.OrderedDict() + + def __getitem__(self, key): + try: + return self._active[key] + except KeyError: + self._memory.move_to_end(key) + return self._memory[key] + + def __setitem__(self, key, value): + self._memory.pop(key, None) + self._active[key] = value + + def __delitem__(self, key): + try: + value = self._active.pop(key) + except KeyError: + pass + else: + while len(self._memory) >= self._capacity: + self._memory.popitem(last=False) + self._memory[key] = value + + def clear(self): + self._active.clear() + self._memory.clear() + + +class UnboundedMemo(dict): + """ + A memoizing mapping that retains all deleted items + """ + + def __delitem__(self, key): + pass + + +def _escape_regex_range_chars(s: str) -> str: + # escape these chars: ^-[] + for c in r"\^-[]": + s = s.replace(c, _bslash + c) + s = s.replace("\n", r"\n") + s = s.replace("\t", r"\t") + return str(s) + + +def _collapse_string_to_ranges( + s: Union[str, Iterable[str]], re_escape: bool = True +) -> str: + def is_consecutive(c): + c_int = ord(c) + is_consecutive.prev, prev = c_int, is_consecutive.prev + if c_int - prev > 1: + is_consecutive.value = next(is_consecutive.counter) + return is_consecutive.value + + is_consecutive.prev = 0 + is_consecutive.counter = itertools.count() + is_consecutive.value = -1 + + def escape_re_range_char(c): + return "\\" + c if c in r"\^-][" else c + + def no_escape_re_range_char(c): + return c + + if not re_escape: + escape_re_range_char = no_escape_re_range_char + + ret = [] + s = "".join(sorted(set(s))) + if len(s) > 3: + for _, chars in itertools.groupby(s, key=is_consecutive): + first = last = next(chars) + last = collections.deque( + itertools.chain(iter([last]), chars), maxlen=1 + ).pop() + if first == last: + ret.append(escape_re_range_char(first)) + else: + sep = "" if ord(last) == ord(first) + 1 else "-" + ret.append( + "{}{}{}".format( + escape_re_range_char(first), sep, escape_re_range_char(last) + ) + ) + else: + ret = [escape_re_range_char(c) for c in s] + + return "".join(ret) + + +def _flatten(ll: list) -> list: + ret = [] + for i in ll: + if isinstance(i, list): + ret.extend(_flatten(i)) + else: + ret.append(i) + return ret diff --git a/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/INSTALLER b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/INSTALLER new file mode 100644 index 00000000..a1b589e3 --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/INSTALLER @@ -0,0 +1 @@ +pip diff --git a/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/LICENSE b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/LICENSE new file mode 100644 index 00000000..1df6b3b8 --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/LICENSE @@ -0,0 +1,254 @@ +A. HISTORY OF THE SOFTWARE +========================== + +Python was created in the early 1990s by Guido van Rossum at Stichting +Mathematisch Centrum (CWI, see http://www.cwi.nl) in the Netherlands +as a successor of a language called ABC. Guido remains Python's +principal author, although it includes many contributions from others. + +In 1995, Guido continued his work on Python at the Corporation for +National Research Initiatives (CNRI, see http://www.cnri.reston.va.us) +in Reston, Virginia where he released several versions of the +software. + +In May 2000, Guido and the Python core development team moved to +BeOpen.com to form the BeOpen PythonLabs team. In October of the same +year, the PythonLabs team moved to Digital Creations, which became +Zope Corporation. In 2001, the Python Software Foundation (PSF, see +https://www.python.org/psf/) was formed, a non-profit organization +created specifically to own Python-related Intellectual Property. +Zope Corporation was a sponsoring member of the PSF. + +All Python releases are Open Source (see http://www.opensource.org for +the Open Source Definition). Historically, most, but not all, Python +releases have also been GPL-compatible; the table below summarizes +the various releases. + + Release Derived Year Owner GPL- + from compatible? (1) + + 0.9.0 thru 1.2 1991-1995 CWI yes + 1.3 thru 1.5.2 1.2 1995-1999 CNRI yes + 1.6 1.5.2 2000 CNRI no + 2.0 1.6 2000 BeOpen.com no + 1.6.1 1.6 2001 CNRI yes (2) + 2.1 2.0+1.6.1 2001 PSF no + 2.0.1 2.0+1.6.1 2001 PSF yes + 2.1.1 2.1+2.0.1 2001 PSF yes + 2.1.2 2.1.1 2002 PSF yes + 2.1.3 2.1.2 2002 PSF yes + 2.2 and above 2.1.1 2001-now PSF yes + +Footnotes: + +(1) GPL-compatible doesn't mean that we're distributing Python under + the GPL. All Python licenses, unlike the GPL, let you distribute + a modified version without making your changes open source. The + GPL-compatible licenses make it possible to combine Python with + other software that is released under the GPL; the others don't. + +(2) According to Richard Stallman, 1.6.1 is not GPL-compatible, + because its license has a choice of law clause. According to + CNRI, however, Stallman's lawyer has told CNRI's lawyer that 1.6.1 + is "not incompatible" with the GPL. + +Thanks to the many outside volunteers who have worked under Guido's +direction to make these releases possible. + + +B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON +=============================================================== + +PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2 +-------------------------------------------- + +1. This LICENSE AGREEMENT is between the Python Software Foundation +("PSF"), and the Individual or Organization ("Licensee") accessing and +otherwise using this software ("Python") in source or binary form and +its associated documentation. + +2. Subject to the terms and conditions of this License Agreement, PSF hereby +grants Licensee a nonexclusive, royalty-free, world-wide license to reproduce, +analyze, test, perform and/or display publicly, prepare derivative works, +distribute, and otherwise use Python alone or in any derivative version, +provided, however, that PSF's License Agreement and PSF's notice of copyright, +i.e., "Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, +2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022 Python Software Foundation; +All Rights Reserved" are retained in Python alone or in any derivative version +prepared by Licensee. + +3. In the event Licensee prepares a derivative work that is based on +or incorporates Python or any part thereof, and wants to make +the derivative work available to others as provided herein, then +Licensee hereby agrees to include in any such work a brief summary of +the changes made to Python. + +4. PSF is making Python available to Licensee on an "AS IS" +basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR +IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND +DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS +FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT +INFRINGE ANY THIRD PARTY RIGHTS. + +5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON +FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS +A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON, +OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF. + +6. This License Agreement will automatically terminate upon a material +breach of its terms and conditions. + +7. Nothing in this License Agreement shall be deemed to create any +relationship of agency, partnership, or joint venture between PSF and +Licensee. This License Agreement does not grant permission to use PSF +trademarks or trade name in a trademark sense to endorse or promote +products or services of Licensee, or any third party. + +8. By copying, installing or otherwise using Python, Licensee +agrees to be bound by the terms and conditions of this License +Agreement. + + +BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0 +------------------------------------------- + +BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1 + +1. This LICENSE AGREEMENT is between BeOpen.com ("BeOpen"), having an +office at 160 Saratoga Avenue, Santa Clara, CA 95051, and the +Individual or Organization ("Licensee") accessing and otherwise using +this software in source or binary form and its associated +documentation ("the Software"). + +2. Subject to the terms and conditions of this BeOpen Python License +Agreement, BeOpen hereby grants Licensee a non-exclusive, +royalty-free, world-wide license to reproduce, analyze, test, perform +and/or display publicly, prepare derivative works, distribute, and +otherwise use the Software alone or in any derivative version, +provided, however, that the BeOpen Python License is retained in the +Software, alone or in any derivative version prepared by Licensee. + +3. BeOpen is making the Software available to Licensee on an "AS IS" +basis. BEOPEN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR +IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, BEOPEN MAKES NO AND +DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS +FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE WILL NOT +INFRINGE ANY THIRD PARTY RIGHTS. + +4. BEOPEN SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF THE +SOFTWARE FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS +AS A RESULT OF USING, MODIFYING OR DISTRIBUTING THE SOFTWARE, OR ANY +DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF. + +5. This License Agreement will automatically terminate upon a material +breach of its terms and conditions. + +6. This License Agreement shall be governed by and interpreted in all +respects by the law of the State of California, excluding conflict of +law provisions. Nothing in this License Agreement shall be deemed to +create any relationship of agency, partnership, or joint venture +between BeOpen and Licensee. This License Agreement does not grant +permission to use BeOpen trademarks or trade names in a trademark +sense to endorse or promote products or services of Licensee, or any +third party. As an exception, the "BeOpen Python" logos available at +http://www.pythonlabs.com/logos.html may be used according to the +permissions granted on that web page. + +7. By copying, installing or otherwise using the software, Licensee +agrees to be bound by the terms and conditions of this License +Agreement. + + +CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1 +--------------------------------------- + +1. This LICENSE AGREEMENT is between the Corporation for National +Research Initiatives, having an office at 1895 Preston White Drive, +Reston, VA 20191 ("CNRI"), and the Individual or Organization +("Licensee") accessing and otherwise using Python 1.6.1 software in +source or binary form and its associated documentation. + +2. Subject to the terms and conditions of this License Agreement, CNRI +hereby grants Licensee a nonexclusive, royalty-free, world-wide +license to reproduce, analyze, test, perform and/or display publicly, +prepare derivative works, distribute, and otherwise use Python 1.6.1 +alone or in any derivative version, provided, however, that CNRI's +License Agreement and CNRI's notice of copyright, i.e., "Copyright (c) +1995-2001 Corporation for National Research Initiatives; All Rights +Reserved" are retained in Python 1.6.1 alone or in any derivative +version prepared by Licensee. Alternately, in lieu of CNRI's License +Agreement, Licensee may substitute the following text (omitting the +quotes): "Python 1.6.1 is made available subject to the terms and +conditions in CNRI's License Agreement. This Agreement together with +Python 1.6.1 may be located on the internet using the following +unique, persistent identifier (known as a handle): 1895.22/1013. This +Agreement may also be obtained from a proxy server on the internet +using the following URL: http://hdl.handle.net/1895.22/1013". + +3. In the event Licensee prepares a derivative work that is based on +or incorporates Python 1.6.1 or any part thereof, and wants to make +the derivative work available to others as provided herein, then +Licensee hereby agrees to include in any such work a brief summary of +the changes made to Python 1.6.1. + +4. CNRI is making Python 1.6.1 available to Licensee on an "AS IS" +basis. CNRI MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR +IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, CNRI MAKES NO AND +DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS +FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT +INFRINGE ANY THIRD PARTY RIGHTS. + +5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON +1.6.1 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS +A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1, +OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF. + +6. This License Agreement will automatically terminate upon a material +breach of its terms and conditions. + +7. This License Agreement shall be governed by the federal +intellectual property law of the United States, including without +limitation the federal copyright law, and, to the extent such +U.S. federal law does not apply, by the law of the Commonwealth of +Virginia, excluding Virginia's conflict of law provisions. +Notwithstanding the foregoing, with regard to derivative works based +on Python 1.6.1 that incorporate non-separable material that was +previously distributed under the GNU General Public License (GPL), the +law of the Commonwealth of Virginia shall govern this License +Agreement only as to issues arising under or with respect to +Paragraphs 4, 5, and 7 of this License Agreement. Nothing in this +License Agreement shall be deemed to create any relationship of +agency, partnership, or joint venture between CNRI and Licensee. This +License Agreement does not grant permission to use CNRI trademarks or +trade name in a trademark sense to endorse or promote products or +services of Licensee, or any third party. + +8. By clicking on the "ACCEPT" button where indicated, or by copying, +installing or otherwise using Python 1.6.1, Licensee agrees to be +bound by the terms and conditions of this License Agreement. + + ACCEPT + + +CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2 +-------------------------------------------------- + +Copyright (c) 1991 - 1995, Stichting Mathematisch Centrum Amsterdam, +The Netherlands. All rights reserved. + +Permission to use, copy, modify, and distribute this software and its +documentation for any purpose and without fee is hereby granted, +provided that the above copyright notice appear in all copies and that +both that copyright notice and this permission notice appear in +supporting documentation, and that the name of Stichting Mathematisch +Centrum or CWI not be used in advertising or publicity pertaining to +distribution of the software without specific, written prior +permission. + +STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO +THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND +FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE +FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN +ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT +OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. diff --git a/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/METADATA b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/METADATA new file mode 100644 index 00000000..1ed963a1 --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/METADATA @@ -0,0 +1,189 @@ +Metadata-Version: 2.1 +Name: typing_extensions +Version: 4.4.0 +Summary: Backported and Experimental Type Hints for Python 3.7+ +Keywords: annotations,backport,checker,checking,function,hinting,hints,type,typechecking,typehinting,typehints,typing +Author-email: "Guido van Rossum, Jukka Lehtosalo, Łukasz Langa, Michael Lee" <levkivskyi@gmail.com> +Requires-Python: >=3.7 +Description-Content-Type: text/markdown +Classifier: Development Status :: 5 - Production/Stable +Classifier: Environment :: Console +Classifier: Intended Audience :: Developers +Classifier: License :: OSI Approved :: Python Software Foundation License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3 :: Only +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Topic :: Software Development +Project-URL: Bug Tracker, https://github.com/python/typing_extensions/issues +Project-URL: Changes, https://github.com/python/typing_extensions/blob/main/CHANGELOG.md +Project-URL: Documentation, https://typing.readthedocs.io/ +Project-URL: Home, https://github.com/python/typing_extensions +Project-URL: Q & A, https://github.com/python/typing/discussions +Project-URL: Repository, https://github.com/python/typing_extensions + +# Typing Extensions + +[](https://gitter.im/python/typing) + +## Overview + +The `typing_extensions` module serves two related purposes: + +- Enable use of new type system features on older Python versions. For example, + `typing.TypeGuard` is new in Python 3.10, but `typing_extensions` allows + users on previous Python versions to use it too. +- Enable experimentation with new type system PEPs before they are accepted and + added to the `typing` module. + +New features may be added to `typing_extensions` as soon as they are specified +in a PEP that has been added to the [python/peps](https://github.com/python/peps) +repository. If the PEP is accepted, the feature will then be added to `typing` +for the next CPython release. No typing PEP has been rejected so far, so we +haven't yet figured out how to deal with that possibility. + +Starting with version 4.0.0, `typing_extensions` uses +[Semantic Versioning](https://semver.org/). The +major version is incremented for all backwards-incompatible changes. +Therefore, it's safe to depend +on `typing_extensions` like this: `typing_extensions >=x.y, <(x+1)`, +where `x.y` is the first version that includes all features you need. + +`typing_extensions` supports Python versions 3.7 and higher. In the future, +support for older Python versions will be dropped some time after that version +reaches end of life. + +## Included items + +This module currently contains the following: + +- Experimental features + + - `override` (see PEP 698) + - The `default=` argument to `TypeVar`, `ParamSpec`, and `TypeVarTuple` (see PEP 696) + - The `infer_variance=` argument to `TypeVar` (see PEP 695) + +- In `typing` since Python 3.11 + + - `assert_never` + - `assert_type` + - `clear_overloads` + - `@dataclass_transform()` (see PEP 681) + - `get_overloads` + - `LiteralString` (see PEP 675) + - `Never` + - `NotRequired` (see PEP 655) + - `reveal_type` + - `Required` (see PEP 655) + - `Self` (see PEP 673) + - `TypeVarTuple` (see PEP 646; the `typing_extensions` version supports the `default=` argument from PEP 696) + - `Unpack` (see PEP 646) + +- In `typing` since Python 3.10 + + - `Concatenate` (see PEP 612) + - `ParamSpec` (see PEP 612; the `typing_extensions` version supports the `default=` argument from PEP 696) + - `ParamSpecArgs` (see PEP 612) + - `ParamSpecKwargs` (see PEP 612) + - `TypeAlias` (see PEP 613) + - `TypeGuard` (see PEP 647) + - `is_typeddict` + +- In `typing` since Python 3.9 + + - `Annotated` (see PEP 593) + +- In `typing` since Python 3.8 + + - `final` (see PEP 591) + - `Final` (see PEP 591) + - `Literal` (see PEP 586) + - `Protocol` (see PEP 544) + - `runtime_checkable` (see PEP 544) + - `TypedDict` (see PEP 589) + - `get_origin` (`typing_extensions` provides this function only in Python 3.7+) + - `get_args` (`typing_extensions` provides this function only in Python 3.7+) + +- In `typing` since Python 3.7 + + - `OrderedDict` + +- In `typing` since Python 3.5 or 3.6 (see [the typing documentation](https://docs.python.org/3.10/library/typing.html) for details) + + - `AsyncContextManager` + - `AsyncGenerator` + - `AsyncIterable` + - `AsyncIterator` + - `Awaitable` + - `ChainMap` + - `ClassVar` (see PEP 526) + - `ContextManager` + - `Coroutine` + - `Counter` + - `DefaultDict` + - `Deque` + - `NewType` + - `NoReturn` + - `overload` + - `Text` + - `Type` + - `TYPE_CHECKING` + - `get_type_hints` + +- The following have always been present in `typing`, but the `typing_extensions` versions provide + additional features: + + - `Any` (supports inheritance since Python 3.11) + - `NamedTuple` (supports multiple inheritance with `Generic` since Python 3.11) + - `TypeVar` (see PEPs 695 and 696) + +# Other Notes and Limitations + +Certain objects were changed after they were added to `typing`, and +`typing_extensions` provides a backport even on newer Python versions: + +- `TypedDict` does not store runtime information + about which (if any) keys are non-required in Python 3.8, and does not + honor the `total` keyword with old-style `TypedDict()` in Python + 3.9.0 and 3.9.1. `TypedDict` also does not support multiple inheritance + with `typing.Generic` on Python <3.11. +- `get_origin` and `get_args` lack support for `Annotated` in + Python 3.8 and lack support for `ParamSpecArgs` and `ParamSpecKwargs` + in 3.9. +- `@final` was changed in Python 3.11 to set the `.__final__` attribute. +- `@overload` was changed in Python 3.11 to make function overloads + introspectable at runtime. In order to access overloads with + `typing_extensions.get_overloads()`, you must use + `@typing_extensions.overload`. +- `NamedTuple` was changed in Python 3.11 to allow for multiple inheritance + with `typing.Generic`. +- Since Python 3.11, it has been possible to inherit from `Any` at + runtime. `typing_extensions.Any` also provides this capability. +- `TypeVar` gains two additional parameters, `default=` and `infer_variance=`, + in the draft PEPs 695 and 696, which are being considered for inclusion + in Python 3.12. + +There are a few types whose interface was modified between different +versions of typing. For example, `typing.Sequence` was modified to +subclass `typing.Reversible` as of Python 3.5.3. + +These changes are _not_ backported to prevent subtle compatibility +issues when mixing the differing implementations of modified classes. + +Certain types have incorrect runtime behavior due to limitations of older +versions of the typing module: + +- `ParamSpec` and `Concatenate` will not work with `get_args` and + `get_origin`. Certain PEP 612 special cases in user-defined + `Generic`s are also not available. + +These types are only guaranteed to work for static type checking. + +## Running tests + +To run tests, navigate into the appropriate source directory and run +`test_typing_extensions.py`. + diff --git a/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/RECORD b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/RECORD new file mode 100644 index 00000000..b9e1bb03 --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/RECORD @@ -0,0 +1,8 @@ +__pycache__/typing_extensions.cpython-311.pyc,,
+typing_extensions-4.4.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+typing_extensions-4.4.0.dist-info/LICENSE,sha256=x6-2XnVXB7n7kEhziaF20-09ADHVExr95FwjcV_16JE,12787
+typing_extensions-4.4.0.dist-info/METADATA,sha256=1zSh1eMLnLkLMMC6aZSGRKx3eRnivEGDFWGSVD1zqhA,7249
+typing_extensions-4.4.0.dist-info/RECORD,,
+typing_extensions-4.4.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+typing_extensions-4.4.0.dist-info/WHEEL,sha256=4TfKIB_xu-04bc2iKz6_zFt-gEFEEDU_31HGhqzOCE8,81
+typing_extensions.py,sha256=ipqWiq5AHzrwczt6c26AP05Llh6a5_GaXRpOBqbogHA,80078
diff --git a/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/REQUESTED b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/REQUESTED new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/REQUESTED diff --git a/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/WHEEL b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/WHEEL new file mode 100644 index 00000000..668ba4d0 --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions-4.4.0.dist-info/WHEEL @@ -0,0 +1,4 @@ +Wheel-Version: 1.0 +Generator: flit 3.7.1 +Root-Is-Purelib: true +Tag: py3-none-any diff --git a/pkg_resources/_vendor/typing_extensions.py b/pkg_resources/_vendor/typing_extensions.py new file mode 100644 index 00000000..ef42417c --- /dev/null +++ b/pkg_resources/_vendor/typing_extensions.py @@ -0,0 +1,2209 @@ +import abc +import collections +import collections.abc +import functools +import operator +import sys +import types as _types +import typing + + +__all__ = [ + # Super-special typing primitives. + 'Any', + 'ClassVar', + 'Concatenate', + 'Final', + 'LiteralString', + 'ParamSpec', + 'ParamSpecArgs', + 'ParamSpecKwargs', + 'Self', + 'Type', + 'TypeVar', + 'TypeVarTuple', + 'Unpack', + + # ABCs (from collections.abc). + 'Awaitable', + 'AsyncIterator', + 'AsyncIterable', + 'Coroutine', + 'AsyncGenerator', + 'AsyncContextManager', + 'ChainMap', + + # Concrete collection types. + 'ContextManager', + 'Counter', + 'Deque', + 'DefaultDict', + 'NamedTuple', + 'OrderedDict', + 'TypedDict', + + # Structural checks, a.k.a. protocols. + 'SupportsIndex', + + # One-off things. + 'Annotated', + 'assert_never', + 'assert_type', + 'clear_overloads', + 'dataclass_transform', + 'get_overloads', + 'final', + 'get_args', + 'get_origin', + 'get_type_hints', + 'IntVar', + 'is_typeddict', + 'Literal', + 'NewType', + 'overload', + 'override', + 'Protocol', + 'reveal_type', + 'runtime', + 'runtime_checkable', + 'Text', + 'TypeAlias', + 'TypeGuard', + 'TYPE_CHECKING', + 'Never', + 'NoReturn', + 'Required', + 'NotRequired', +] + +# for backward compatibility +PEP_560 = True +GenericMeta = type + +# The functions below are modified copies of typing internal helpers. +# They are needed by _ProtocolMeta and they provide support for PEP 646. + +_marker = object() + + +def _check_generic(cls, parameters, elen=_marker): + """Check correct count for parameters of a generic cls (internal helper). + This gives a nice error message in case of count mismatch. + """ + if not elen: + raise TypeError(f"{cls} is not a generic class") + if elen is _marker: + if not hasattr(cls, "__parameters__") or not cls.__parameters__: + raise TypeError(f"{cls} is not a generic class") + elen = len(cls.__parameters__) + alen = len(parameters) + if alen != elen: + if hasattr(cls, "__parameters__"): + parameters = [p for p in cls.__parameters__ if not _is_unpack(p)] + num_tv_tuples = sum(isinstance(p, TypeVarTuple) for p in parameters) + if (num_tv_tuples > 0) and (alen >= elen - num_tv_tuples): + return + raise TypeError(f"Too {'many' if alen > elen else 'few'} parameters for {cls};" + f" actual {alen}, expected {elen}") + + +if sys.version_info >= (3, 10): + def _should_collect_from_parameters(t): + return isinstance( + t, (typing._GenericAlias, _types.GenericAlias, _types.UnionType) + ) +elif sys.version_info >= (3, 9): + def _should_collect_from_parameters(t): + return isinstance(t, (typing._GenericAlias, _types.GenericAlias)) +else: + def _should_collect_from_parameters(t): + return isinstance(t, typing._GenericAlias) and not t._special + + +def _collect_type_vars(types, typevar_types=None): + """Collect all type variable contained in types in order of + first appearance (lexicographic order). For example:: + + _collect_type_vars((T, List[S, T])) == (T, S) + """ + if typevar_types is None: + typevar_types = typing.TypeVar + tvars = [] + for t in types: + if ( + isinstance(t, typevar_types) and + t not in tvars and + not _is_unpack(t) + ): + tvars.append(t) + if _should_collect_from_parameters(t): + tvars.extend([t for t in t.__parameters__ if t not in tvars]) + return tuple(tvars) + + +NoReturn = typing.NoReturn + +# Some unconstrained type variables. These are used by the container types. +# (These are not for export.) +T = typing.TypeVar('T') # Any type. +KT = typing.TypeVar('KT') # Key type. +VT = typing.TypeVar('VT') # Value type. +T_co = typing.TypeVar('T_co', covariant=True) # Any type covariant containers. +T_contra = typing.TypeVar('T_contra', contravariant=True) # Ditto contravariant. + + +if sys.version_info >= (3, 11): + from typing import Any +else: + + class _AnyMeta(type): + def __instancecheck__(self, obj): + if self is Any: + raise TypeError("typing_extensions.Any cannot be used with isinstance()") + return super().__instancecheck__(obj) + + def __repr__(self): + if self is Any: + return "typing_extensions.Any" + return super().__repr__() + + class Any(metaclass=_AnyMeta): + """Special type indicating an unconstrained type. + - Any is compatible with every type. + - Any assumed to have all methods. + - All values assumed to be instances of Any. + Note that all the above statements are true from the point of view of + static type checkers. At runtime, Any should not be used with instance + checks. + """ + def __new__(cls, *args, **kwargs): + if cls is Any: + raise TypeError("Any cannot be instantiated") + return super().__new__(cls, *args, **kwargs) + + +ClassVar = typing.ClassVar + +# On older versions of typing there is an internal class named "Final". +# 3.8+ +if hasattr(typing, 'Final') and sys.version_info[:2] >= (3, 7): + Final = typing.Final +# 3.7 +else: + class _FinalForm(typing._SpecialForm, _root=True): + + def __repr__(self): + return 'typing_extensions.' + self._name + + def __getitem__(self, parameters): + item = typing._type_check(parameters, + f'{self._name} accepts only a single type.') + return typing._GenericAlias(self, (item,)) + + Final = _FinalForm('Final', + doc="""A special typing construct to indicate that a name + cannot be re-assigned or overridden in a subclass. + For example: + + MAX_SIZE: Final = 9000 + MAX_SIZE += 1 # Error reported by type checker + + class Connection: + TIMEOUT: Final[int] = 10 + class FastConnector(Connection): + TIMEOUT = 1 # Error reported by type checker + + There is no runtime checking of these properties.""") + +if sys.version_info >= (3, 11): + final = typing.final +else: + # @final exists in 3.8+, but we backport it for all versions + # before 3.11 to keep support for the __final__ attribute. + # See https://bugs.python.org/issue46342 + def final(f): + """This decorator can be used to indicate to type checkers that + the decorated method cannot be overridden, and decorated class + cannot be subclassed. For example: + + class Base: + @final + def done(self) -> None: + ... + class Sub(Base): + def done(self) -> None: # Error reported by type checker + ... + @final + class Leaf: + ... + class Other(Leaf): # Error reported by type checker + ... + + There is no runtime checking of these properties. The decorator + sets the ``__final__`` attribute to ``True`` on the decorated object + to allow runtime introspection. + """ + try: + f.__final__ = True + except (AttributeError, TypeError): + # Skip the attribute silently if it is not writable. + # AttributeError happens if the object has __slots__ or a + # read-only property, TypeError if it's a builtin class. + pass + return f + + +def IntVar(name): + return typing.TypeVar(name) + + +# 3.8+: +if hasattr(typing, 'Literal'): + Literal = typing.Literal +# 3.7: +else: + class _LiteralForm(typing._SpecialForm, _root=True): + + def __repr__(self): + return 'typing_extensions.' + self._name + + def __getitem__(self, parameters): + return typing._GenericAlias(self, parameters) + + Literal = _LiteralForm('Literal', + doc="""A type that can be used to indicate to type checkers + that the corresponding value has a value literally equivalent + to the provided parameter. For example: + + var: Literal[4] = 4 + + The type checker understands that 'var' is literally equal to + the value 4 and no other value. + + Literal[...] cannot be subclassed. There is no runtime + checking verifying that the parameter is actually a value + instead of a type.""") + + +_overload_dummy = typing._overload_dummy # noqa + + +if hasattr(typing, "get_overloads"): # 3.11+ + overload = typing.overload + get_overloads = typing.get_overloads + clear_overloads = typing.clear_overloads +else: + # {module: {qualname: {firstlineno: func}}} + _overload_registry = collections.defaultdict( + functools.partial(collections.defaultdict, dict) + ) + + def overload(func): + """Decorator for overloaded functions/methods. + + In a stub file, place two or more stub definitions for the same + function in a row, each decorated with @overload. For example: + + @overload + def utf8(value: None) -> None: ... + @overload + def utf8(value: bytes) -> bytes: ... + @overload + def utf8(value: str) -> bytes: ... + + In a non-stub file (i.e. a regular .py file), do the same but + follow it with an implementation. The implementation should *not* + be decorated with @overload. For example: + + @overload + def utf8(value: None) -> None: ... + @overload + def utf8(value: bytes) -> bytes: ... + @overload + def utf8(value: str) -> bytes: ... + def utf8(value): + # implementation goes here + + The overloads for a function can be retrieved at runtime using the + get_overloads() function. + """ + # classmethod and staticmethod + f = getattr(func, "__func__", func) + try: + _overload_registry[f.__module__][f.__qualname__][ + f.__code__.co_firstlineno + ] = func + except AttributeError: + # Not a normal function; ignore. + pass + return _overload_dummy + + def get_overloads(func): + """Return all defined overloads for *func* as a sequence.""" + # classmethod and staticmethod + f = getattr(func, "__func__", func) + if f.__module__ not in _overload_registry: + return [] + mod_dict = _overload_registry[f.__module__] + if f.__qualname__ not in mod_dict: + return [] + return list(mod_dict[f.__qualname__].values()) + + def clear_overloads(): + """Clear all overloads in the registry.""" + _overload_registry.clear() + + +# This is not a real generic class. Don't use outside annotations. +Type = typing.Type + +# Various ABCs mimicking those in collections.abc. +# A few are simply re-exported for completeness. + + +Awaitable = typing.Awaitable +Coroutine = typing.Coroutine +AsyncIterable = typing.AsyncIterable +AsyncIterator = typing.AsyncIterator +Deque = typing.Deque +ContextManager = typing.ContextManager +AsyncContextManager = typing.AsyncContextManager +DefaultDict = typing.DefaultDict + +# 3.7.2+ +if hasattr(typing, 'OrderedDict'): + OrderedDict = typing.OrderedDict +# 3.7.0-3.7.2 +else: + OrderedDict = typing._alias(collections.OrderedDict, (KT, VT)) + +Counter = typing.Counter +ChainMap = typing.ChainMap +AsyncGenerator = typing.AsyncGenerator +NewType = typing.NewType +Text = typing.Text +TYPE_CHECKING = typing.TYPE_CHECKING + + +_PROTO_WHITELIST = ['Callable', 'Awaitable', + 'Iterable', 'Iterator', 'AsyncIterable', 'AsyncIterator', + 'Hashable', 'Sized', 'Container', 'Collection', 'Reversible', + 'ContextManager', 'AsyncContextManager'] + + +def _get_protocol_attrs(cls): + attrs = set() + for base in cls.__mro__[:-1]: # without object + if base.__name__ in ('Protocol', 'Generic'): + continue + annotations = getattr(base, '__annotations__', {}) + for attr in list(base.__dict__.keys()) + list(annotations.keys()): + if (not attr.startswith('_abc_') and attr not in ( + '__abstractmethods__', '__annotations__', '__weakref__', + '_is_protocol', '_is_runtime_protocol', '__dict__', + '__args__', '__slots__', + '__next_in_mro__', '__parameters__', '__origin__', + '__orig_bases__', '__extra__', '__tree_hash__', + '__doc__', '__subclasshook__', '__init__', '__new__', + '__module__', '_MutableMapping__marker', '_gorg')): + attrs.add(attr) + return attrs + + +def _is_callable_members_only(cls): + return all(callable(getattr(cls, attr, None)) for attr in _get_protocol_attrs(cls)) + + +def _maybe_adjust_parameters(cls): + """Helper function used in Protocol.__init_subclass__ and _TypedDictMeta.__new__. + + The contents of this function are very similar + to logic found in typing.Generic.__init_subclass__ + on the CPython main branch. + """ + tvars = [] + if '__orig_bases__' in cls.__dict__: + tvars = typing._collect_type_vars(cls.__orig_bases__) + # Look for Generic[T1, ..., Tn] or Protocol[T1, ..., Tn]. + # If found, tvars must be a subset of it. + # If not found, tvars is it. + # Also check for and reject plain Generic, + # and reject multiple Generic[...] and/or Protocol[...]. + gvars = None + for base in cls.__orig_bases__: + if (isinstance(base, typing._GenericAlias) and + base.__origin__ in (typing.Generic, Protocol)): + # for error messages + the_base = base.__origin__.__name__ + if gvars is not None: + raise TypeError( + "Cannot inherit from Generic[...]" + " and/or Protocol[...] multiple types.") + gvars = base.__parameters__ + if gvars is None: + gvars = tvars + else: + tvarset = set(tvars) + gvarset = set(gvars) + if not tvarset <= gvarset: + s_vars = ', '.join(str(t) for t in tvars if t not in gvarset) + s_args = ', '.join(str(g) for g in gvars) + raise TypeError(f"Some type variables ({s_vars}) are" + f" not listed in {the_base}[{s_args}]") + tvars = gvars + cls.__parameters__ = tuple(tvars) + + +# 3.8+ +if hasattr(typing, 'Protocol'): + Protocol = typing.Protocol +# 3.7 +else: + + def _no_init(self, *args, **kwargs): + if type(self)._is_protocol: + raise TypeError('Protocols cannot be instantiated') + + class _ProtocolMeta(abc.ABCMeta): # noqa: B024 + # This metaclass is a bit unfortunate and exists only because of the lack + # of __instancehook__. + def __instancecheck__(cls, instance): + # We need this method for situations where attributes are + # assigned in __init__. + if ((not getattr(cls, '_is_protocol', False) or + _is_callable_members_only(cls)) and + issubclass(instance.__class__, cls)): + return True + if cls._is_protocol: + if all(hasattr(instance, attr) and + (not callable(getattr(cls, attr, None)) or + getattr(instance, attr) is not None) + for attr in _get_protocol_attrs(cls)): + return True + return super().__instancecheck__(instance) + + class Protocol(metaclass=_ProtocolMeta): + # There is quite a lot of overlapping code with typing.Generic. + # Unfortunately it is hard to avoid this while these live in two different + # modules. The duplicated code will be removed when Protocol is moved to typing. + """Base class for protocol classes. Protocol classes are defined as:: + + class Proto(Protocol): + def meth(self) -> int: + ... + + Such classes are primarily used with static type checkers that recognize + structural subtyping (static duck-typing), for example:: + + class C: + def meth(self) -> int: + return 0 + + def func(x: Proto) -> int: + return x.meth() + + func(C()) # Passes static type check + + See PEP 544 for details. Protocol classes decorated with + @typing_extensions.runtime act as simple-minded runtime protocol that checks + only the presence of given attributes, ignoring their type signatures. + + Protocol classes can be generic, they are defined as:: + + class GenProto(Protocol[T]): + def meth(self) -> T: + ... + """ + __slots__ = () + _is_protocol = True + + def __new__(cls, *args, **kwds): + if cls is Protocol: + raise TypeError("Type Protocol cannot be instantiated; " + "it can only be used as a base class") + return super().__new__(cls) + + @typing._tp_cache + def __class_getitem__(cls, params): + if not isinstance(params, tuple): + params = (params,) + if not params and cls is not typing.Tuple: + raise TypeError( + f"Parameter list to {cls.__qualname__}[...] cannot be empty") + msg = "Parameters to generic types must be types." + params = tuple(typing._type_check(p, msg) for p in params) # noqa + if cls is Protocol: + # Generic can only be subscripted with unique type variables. + if not all(isinstance(p, typing.TypeVar) for p in params): + i = 0 + while isinstance(params[i], typing.TypeVar): + i += 1 + raise TypeError( + "Parameters to Protocol[...] must all be type variables." + f" Parameter {i + 1} is {params[i]}") + if len(set(params)) != len(params): + raise TypeError( + "Parameters to Protocol[...] must all be unique") + else: + # Subscripting a regular Generic subclass. + _check_generic(cls, params, len(cls.__parameters__)) + return typing._GenericAlias(cls, params) + + def __init_subclass__(cls, *args, **kwargs): + if '__orig_bases__' in cls.__dict__: + error = typing.Generic in cls.__orig_bases__ + else: + error = typing.Generic in cls.__bases__ + if error: + raise TypeError("Cannot inherit from plain Generic") + _maybe_adjust_parameters(cls) + + # Determine if this is a protocol or a concrete subclass. + if not cls.__dict__.get('_is_protocol', None): + cls._is_protocol = any(b is Protocol for b in cls.__bases__) + + # Set (or override) the protocol subclass hook. + def _proto_hook(other): + if not cls.__dict__.get('_is_protocol', None): + return NotImplemented + if not getattr(cls, '_is_runtime_protocol', False): + if sys._getframe(2).f_globals['__name__'] in ['abc', 'functools']: + return NotImplemented + raise TypeError("Instance and class checks can only be used with" + " @runtime protocols") + if not _is_callable_members_only(cls): + if sys._getframe(2).f_globals['__name__'] in ['abc', 'functools']: + return NotImplemented + raise TypeError("Protocols with non-method members" + " don't support issubclass()") + if not isinstance(other, type): + # Same error as for issubclass(1, int) + raise TypeError('issubclass() arg 1 must be a class') + for attr in _get_protocol_attrs(cls): + for base in other.__mro__: + if attr in base.__dict__: + if base.__dict__[attr] is None: + return NotImplemented + break + annotations = getattr(base, '__annotations__', {}) + if (isinstance(annotations, typing.Mapping) and + attr in annotations and + isinstance(other, _ProtocolMeta) and + other._is_protocol): + break + else: + return NotImplemented + return True + if '__subclasshook__' not in cls.__dict__: + cls.__subclasshook__ = _proto_hook + + # We have nothing more to do for non-protocols. + if not cls._is_protocol: + return + + # Check consistency of bases. + for base in cls.__bases__: + if not (base in (object, typing.Generic) or + base.__module__ == 'collections.abc' and + base.__name__ in _PROTO_WHITELIST or + isinstance(base, _ProtocolMeta) and base._is_protocol): + raise TypeError('Protocols can only inherit from other' + f' protocols, got {repr(base)}') + cls.__init__ = _no_init + + +# 3.8+ +if hasattr(typing, 'runtime_checkable'): + runtime_checkable = typing.runtime_checkable +# 3.7 +else: + def runtime_checkable(cls): + """Mark a protocol class as a runtime protocol, so that it + can be used with isinstance() and issubclass(). Raise TypeError + if applied to a non-protocol class. + + This allows a simple-minded structural check very similar to the + one-offs in collections.abc such as Hashable. + """ + if not isinstance(cls, _ProtocolMeta) or not cls._is_protocol: + raise TypeError('@runtime_checkable can be only applied to protocol classes,' + f' got {cls!r}') + cls._is_runtime_protocol = True + return cls + + +# Exists for backwards compatibility. +runtime = runtime_checkable + + +# 3.8+ +if hasattr(typing, 'SupportsIndex'): + SupportsIndex = typing.SupportsIndex +# 3.7 +else: + @runtime_checkable + class SupportsIndex(Protocol): + __slots__ = () + + @abc.abstractmethod + def __index__(self) -> int: + pass + + +if hasattr(typing, "Required"): + # The standard library TypedDict in Python 3.8 does not store runtime information + # about which (if any) keys are optional. See https://bugs.python.org/issue38834 + # The standard library TypedDict in Python 3.9.0/1 does not honour the "total" + # keyword with old-style TypedDict(). See https://bugs.python.org/issue42059 + # The standard library TypedDict below Python 3.11 does not store runtime + # information about optional and required keys when using Required or NotRequired. + # Generic TypedDicts are also impossible using typing.TypedDict on Python <3.11. + TypedDict = typing.TypedDict + _TypedDictMeta = typing._TypedDictMeta + is_typeddict = typing.is_typeddict +else: + def _check_fails(cls, other): + try: + if sys._getframe(1).f_globals['__name__'] not in ['abc', + 'functools', + 'typing']: + # Typed dicts are only for static structural subtyping. + raise TypeError('TypedDict does not support instance and class checks') + except (AttributeError, ValueError): + pass + return False + + def _dict_new(*args, **kwargs): + if not args: + raise TypeError('TypedDict.__new__(): not enough arguments') + _, args = args[0], args[1:] # allow the "cls" keyword be passed + return dict(*args, **kwargs) + + _dict_new.__text_signature__ = '($cls, _typename, _fields=None, /, **kwargs)' + + def _typeddict_new(*args, total=True, **kwargs): + if not args: + raise TypeError('TypedDict.__new__(): not enough arguments') + _, args = args[0], args[1:] # allow the "cls" keyword be passed + if args: + typename, args = args[0], args[1:] # allow the "_typename" keyword be passed + elif '_typename' in kwargs: + typename = kwargs.pop('_typename') + import warnings + warnings.warn("Passing '_typename' as keyword argument is deprecated", + DeprecationWarning, stacklevel=2) + else: + raise TypeError("TypedDict.__new__() missing 1 required positional " + "argument: '_typename'") + if args: + try: + fields, = args # allow the "_fields" keyword be passed + except ValueError: + raise TypeError('TypedDict.__new__() takes from 2 to 3 ' + f'positional arguments but {len(args) + 2} ' + 'were given') + elif '_fields' in kwargs and len(kwargs) == 1: + fields = kwargs.pop('_fields') + import warnings + warnings.warn("Passing '_fields' as keyword argument is deprecated", + DeprecationWarning, stacklevel=2) + else: + fields = None + + if fields is None: + fields = kwargs + elif kwargs: + raise TypeError("TypedDict takes either a dict or keyword arguments," + " but not both") + + ns = {'__annotations__': dict(fields)} + try: + # Setting correct module is necessary to make typed dict classes pickleable. + ns['__module__'] = sys._getframe(1).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): + pass + + return _TypedDictMeta(typename, (), ns, total=total) + + _typeddict_new.__text_signature__ = ('($cls, _typename, _fields=None,' + ' /, *, total=True, **kwargs)') + + class _TypedDictMeta(type): + def __init__(cls, name, bases, ns, total=True): + super().__init__(name, bases, ns) + + def __new__(cls, name, bases, ns, total=True): + # Create new typed dict class object. + # This method is called directly when TypedDict is subclassed, + # or via _typeddict_new when TypedDict is instantiated. This way + # TypedDict supports all three syntaxes described in its docstring. + # Subclasses and instances of TypedDict return actual dictionaries + # via _dict_new. + ns['__new__'] = _typeddict_new if name == 'TypedDict' else _dict_new + # Don't insert typing.Generic into __bases__ here, + # or Generic.__init_subclass__ will raise TypeError + # in the super().__new__() call. + # Instead, monkey-patch __bases__ onto the class after it's been created. + tp_dict = super().__new__(cls, name, (dict,), ns) + + if any(issubclass(base, typing.Generic) for base in bases): + tp_dict.__bases__ = (typing.Generic, dict) + _maybe_adjust_parameters(tp_dict) + + annotations = {} + own_annotations = ns.get('__annotations__', {}) + msg = "TypedDict('Name', {f0: t0, f1: t1, ...}); each t must be a type" + own_annotations = { + n: typing._type_check(tp, msg) for n, tp in own_annotations.items() + } + required_keys = set() + optional_keys = set() + + for base in bases: + annotations.update(base.__dict__.get('__annotations__', {})) + required_keys.update(base.__dict__.get('__required_keys__', ())) + optional_keys.update(base.__dict__.get('__optional_keys__', ())) + + annotations.update(own_annotations) + for annotation_key, annotation_type in own_annotations.items(): + annotation_origin = get_origin(annotation_type) + if annotation_origin is Annotated: + annotation_args = get_args(annotation_type) + if annotation_args: + annotation_type = annotation_args[0] + annotation_origin = get_origin(annotation_type) + + if annotation_origin is Required: + required_keys.add(annotation_key) + elif annotation_origin is NotRequired: + optional_keys.add(annotation_key) + elif total: + required_keys.add(annotation_key) + else: + optional_keys.add(annotation_key) + + tp_dict.__annotations__ = annotations + tp_dict.__required_keys__ = frozenset(required_keys) + tp_dict.__optional_keys__ = frozenset(optional_keys) + if not hasattr(tp_dict, '__total__'): + tp_dict.__total__ = total + return tp_dict + + __instancecheck__ = __subclasscheck__ = _check_fails + + TypedDict = _TypedDictMeta('TypedDict', (dict,), {}) + TypedDict.__module__ = __name__ + TypedDict.__doc__ = \ + """A simple typed name space. At runtime it is equivalent to a plain dict. + + TypedDict creates a dictionary type that expects all of its + instances to have a certain set of keys, with each key + associated with a value of a consistent type. This expectation + is not checked at runtime but is only enforced by type checkers. + Usage:: + + class Point2D(TypedDict): + x: int + y: int + label: str + + a: Point2D = {'x': 1, 'y': 2, 'label': 'good'} # OK + b: Point2D = {'z': 3, 'label': 'bad'} # Fails type check + + assert Point2D(x=1, y=2, label='first') == dict(x=1, y=2, label='first') + + The type info can be accessed via the Point2D.__annotations__ dict, and + the Point2D.__required_keys__ and Point2D.__optional_keys__ frozensets. + TypedDict supports two additional equivalent forms:: + + Point2D = TypedDict('Point2D', x=int, y=int, label=str) + Point2D = TypedDict('Point2D', {'x': int, 'y': int, 'label': str}) + + The class syntax is only supported in Python 3.6+, while two other + syntax forms work for Python 2.7 and 3.2+ + """ + + if hasattr(typing, "_TypedDictMeta"): + _TYPEDDICT_TYPES = (typing._TypedDictMeta, _TypedDictMeta) + else: + _TYPEDDICT_TYPES = (_TypedDictMeta,) + + def is_typeddict(tp): + """Check if an annotation is a TypedDict class + + For example:: + class Film(TypedDict): + title: str + year: int + + is_typeddict(Film) # => True + is_typeddict(Union[list, str]) # => False + """ + return isinstance(tp, tuple(_TYPEDDICT_TYPES)) + + +if hasattr(typing, "assert_type"): + assert_type = typing.assert_type + +else: + def assert_type(__val, __typ): + """Assert (to the type checker) that the value is of the given type. + + When the type checker encounters a call to assert_type(), it + emits an error if the value is not of the specified type:: + + def greet(name: str) -> None: + assert_type(name, str) # ok + assert_type(name, int) # type checker error + + At runtime this returns the first argument unchanged and otherwise + does nothing. + """ + return __val + + +if hasattr(typing, "Required"): + get_type_hints = typing.get_type_hints +else: + import functools + import types + + # replaces _strip_annotations() + def _strip_extras(t): + """Strips Annotated, Required and NotRequired from a given type.""" + if isinstance(t, _AnnotatedAlias): + return _strip_extras(t.__origin__) + if hasattr(t, "__origin__") and t.__origin__ in (Required, NotRequired): + return _strip_extras(t.__args__[0]) + if isinstance(t, typing._GenericAlias): + stripped_args = tuple(_strip_extras(a) for a in t.__args__) + if stripped_args == t.__args__: + return t + return t.copy_with(stripped_args) + if hasattr(types, "GenericAlias") and isinstance(t, types.GenericAlias): + stripped_args = tuple(_strip_extras(a) for a in t.__args__) + if stripped_args == t.__args__: + return t + return types.GenericAlias(t.__origin__, stripped_args) + if hasattr(types, "UnionType") and isinstance(t, types.UnionType): + stripped_args = tuple(_strip_extras(a) for a in t.__args__) + if stripped_args == t.__args__: + return t + return functools.reduce(operator.or_, stripped_args) + + return t + + def get_type_hints(obj, globalns=None, localns=None, include_extras=False): + """Return type hints for an object. + + This is often the same as obj.__annotations__, but it handles + forward references encoded as string literals, adds Optional[t] if a + default value equal to None is set and recursively replaces all + 'Annotated[T, ...]', 'Required[T]' or 'NotRequired[T]' with 'T' + (unless 'include_extras=True'). + + The argument may be a module, class, method, or function. The annotations + are returned as a dictionary. For classes, annotations include also + inherited members. + + TypeError is raised if the argument is not of a type that can contain + annotations, and an empty dictionary is returned if no annotations are + present. + + BEWARE -- the behavior of globalns and localns is counterintuitive + (unless you are familiar with how eval() and exec() work). The + search order is locals first, then globals. + + - If no dict arguments are passed, an attempt is made to use the + globals from obj (or the respective module's globals for classes), + and these are also used as the locals. If the object does not appear + to have globals, an empty dictionary is used. + + - If one dict argument is passed, it is used for both globals and + locals. + + - If two dict arguments are passed, they specify globals and + locals, respectively. + """ + if hasattr(typing, "Annotated"): + hint = typing.get_type_hints( + obj, globalns=globalns, localns=localns, include_extras=True + ) + else: + hint = typing.get_type_hints(obj, globalns=globalns, localns=localns) + if include_extras: + return hint + return {k: _strip_extras(t) for k, t in hint.items()} + + +# Python 3.9+ has PEP 593 (Annotated) +if hasattr(typing, 'Annotated'): + Annotated = typing.Annotated + # Not exported and not a public API, but needed for get_origin() and get_args() + # to work. + _AnnotatedAlias = typing._AnnotatedAlias +# 3.7-3.8 +else: + class _AnnotatedAlias(typing._GenericAlias, _root=True): + """Runtime representation of an annotated type. + + At its core 'Annotated[t, dec1, dec2, ...]' is an alias for the type 't' + with extra annotations. The alias behaves like a normal typing alias, + instantiating is the same as instantiating the underlying type, binding + it to types is also the same. + """ + def __init__(self, origin, metadata): + if isinstance(origin, _AnnotatedAlias): + metadata = origin.__metadata__ + metadata + origin = origin.__origin__ + super().__init__(origin, origin) + self.__metadata__ = metadata + + def copy_with(self, params): + assert len(params) == 1 + new_type = params[0] + return _AnnotatedAlias(new_type, self.__metadata__) + + def __repr__(self): + return (f"typing_extensions.Annotated[{typing._type_repr(self.__origin__)}, " + f"{', '.join(repr(a) for a in self.__metadata__)}]") + + def __reduce__(self): + return operator.getitem, ( + Annotated, (self.__origin__,) + self.__metadata__ + ) + + def __eq__(self, other): + if not isinstance(other, _AnnotatedAlias): + return NotImplemented + if self.__origin__ != other.__origin__: + return False + return self.__metadata__ == other.__metadata__ + + def __hash__(self): + return hash((self.__origin__, self.__metadata__)) + + class Annotated: + """Add context specific metadata to a type. + + Example: Annotated[int, runtime_check.Unsigned] indicates to the + hypothetical runtime_check module that this type is an unsigned int. + Every other consumer of this type can ignore this metadata and treat + this type as int. + + The first argument to Annotated must be a valid type (and will be in + the __origin__ field), the remaining arguments are kept as a tuple in + the __extra__ field. + + Details: + + - It's an error to call `Annotated` with less than two arguments. + - Nested Annotated are flattened:: + + Annotated[Annotated[T, Ann1, Ann2], Ann3] == Annotated[T, Ann1, Ann2, Ann3] + + - Instantiating an annotated type is equivalent to instantiating the + underlying type:: + + Annotated[C, Ann1](5) == C(5) + + - Annotated can be used as a generic type alias:: + + Optimized = Annotated[T, runtime.Optimize()] + Optimized[int] == Annotated[int, runtime.Optimize()] + + OptimizedList = Annotated[List[T], runtime.Optimize()] + OptimizedList[int] == Annotated[List[int], runtime.Optimize()] + """ + + __slots__ = () + + def __new__(cls, *args, **kwargs): + raise TypeError("Type Annotated cannot be instantiated.") + + @typing._tp_cache + def __class_getitem__(cls, params): + if not isinstance(params, tuple) or len(params) < 2: + raise TypeError("Annotated[...] should be used " + "with at least two arguments (a type and an " + "annotation).") + allowed_special_forms = (ClassVar, Final) + if get_origin(params[0]) in allowed_special_forms: + origin = params[0] + else: + msg = "Annotated[t, ...]: t must be a type." + origin = typing._type_check(params[0], msg) + metadata = tuple(params[1:]) + return _AnnotatedAlias(origin, metadata) + + def __init_subclass__(cls, *args, **kwargs): + raise TypeError( + f"Cannot subclass {cls.__module__}.Annotated" + ) + +# Python 3.8 has get_origin() and get_args() but those implementations aren't +# Annotated-aware, so we can't use those. Python 3.9's versions don't support +# ParamSpecArgs and ParamSpecKwargs, so only Python 3.10's versions will do. +if sys.version_info[:2] >= (3, 10): + get_origin = typing.get_origin + get_args = typing.get_args +# 3.7-3.9 +else: + try: + # 3.9+ + from typing import _BaseGenericAlias + except ImportError: + _BaseGenericAlias = typing._GenericAlias + try: + # 3.9+ + from typing import GenericAlias as _typing_GenericAlias + except ImportError: + _typing_GenericAlias = typing._GenericAlias + + def get_origin(tp): + """Get the unsubscripted version of a type. + + This supports generic types, Callable, Tuple, Union, Literal, Final, ClassVar + and Annotated. Return None for unsupported types. Examples:: + + get_origin(Literal[42]) is Literal + get_origin(int) is None + get_origin(ClassVar[int]) is ClassVar + get_origin(Generic) is Generic + get_origin(Generic[T]) is Generic + get_origin(Union[T, int]) is Union + get_origin(List[Tuple[T, T]][int]) == list + get_origin(P.args) is P + """ + if isinstance(tp, _AnnotatedAlias): + return Annotated + if isinstance(tp, (typing._GenericAlias, _typing_GenericAlias, _BaseGenericAlias, + ParamSpecArgs, ParamSpecKwargs)): + return tp.__origin__ + if tp is typing.Generic: + return typing.Generic + return None + + def get_args(tp): + """Get type arguments with all substitutions performed. + + For unions, basic simplifications used by Union constructor are performed. + Examples:: + get_args(Dict[str, int]) == (str, int) + get_args(int) == () + get_args(Union[int, Union[T, int], str][int]) == (int, str) + get_args(Union[int, Tuple[T, int]][str]) == (int, Tuple[str, int]) + get_args(Callable[[], T][int]) == ([], int) + """ + if isinstance(tp, _AnnotatedAlias): + return (tp.__origin__,) + tp.__metadata__ + if isinstance(tp, (typing._GenericAlias, _typing_GenericAlias)): + if getattr(tp, "_special", False): + return () + res = tp.__args__ + if get_origin(tp) is collections.abc.Callable and res[0] is not Ellipsis: + res = (list(res[:-1]), res[-1]) + return res + return () + + +# 3.10+ +if hasattr(typing, 'TypeAlias'): + TypeAlias = typing.TypeAlias +# 3.9 +elif sys.version_info[:2] >= (3, 9): + class _TypeAliasForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + @_TypeAliasForm + def TypeAlias(self, parameters): + """Special marker indicating that an assignment should + be recognized as a proper type alias definition by type + checkers. + + For example:: + + Predicate: TypeAlias = Callable[..., bool] + + It's invalid when used anywhere except as in the example above. + """ + raise TypeError(f"{self} is not subscriptable") +# 3.7-3.8 +else: + class _TypeAliasForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + TypeAlias = _TypeAliasForm('TypeAlias', + doc="""Special marker indicating that an assignment should + be recognized as a proper type alias definition by type + checkers. + + For example:: + + Predicate: TypeAlias = Callable[..., bool] + + It's invalid when used anywhere except as in the example + above.""") + + +class _DefaultMixin: + """Mixin for TypeVarLike defaults.""" + + __slots__ = () + + def __init__(self, default): + if isinstance(default, (tuple, list)): + self.__default__ = tuple((typing._type_check(d, "Default must be a type") + for d in default)) + elif default: + self.__default__ = typing._type_check(default, "Default must be a type") + else: + self.__default__ = None + + +# Add default and infer_variance parameters from PEP 696 and 695 +class TypeVar(typing.TypeVar, _DefaultMixin, _root=True): + """Type variable.""" + + __module__ = 'typing' + + def __init__(self, name, *constraints, bound=None, + covariant=False, contravariant=False, + default=None, infer_variance=False): + super().__init__(name, *constraints, bound=bound, covariant=covariant, + contravariant=contravariant) + _DefaultMixin.__init__(self, default) + self.__infer_variance__ = infer_variance + + # for pickling: + try: + def_mod = sys._getframe(1).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): + def_mod = None + if def_mod != 'typing_extensions': + self.__module__ = def_mod + + +# Python 3.10+ has PEP 612 +if hasattr(typing, 'ParamSpecArgs'): + ParamSpecArgs = typing.ParamSpecArgs + ParamSpecKwargs = typing.ParamSpecKwargs +# 3.7-3.9 +else: + class _Immutable: + """Mixin to indicate that object should not be copied.""" + __slots__ = () + + def __copy__(self): + return self + + def __deepcopy__(self, memo): + return self + + class ParamSpecArgs(_Immutable): + """The args for a ParamSpec object. + + Given a ParamSpec object P, P.args is an instance of ParamSpecArgs. + + ParamSpecArgs objects have a reference back to their ParamSpec: + + P.args.__origin__ is P + + This type is meant for runtime introspection and has no special meaning to + static type checkers. + """ + def __init__(self, origin): + self.__origin__ = origin + + def __repr__(self): + return f"{self.__origin__.__name__}.args" + + def __eq__(self, other): + if not isinstance(other, ParamSpecArgs): + return NotImplemented + return self.__origin__ == other.__origin__ + + class ParamSpecKwargs(_Immutable): + """The kwargs for a ParamSpec object. + + Given a ParamSpec object P, P.kwargs is an instance of ParamSpecKwargs. + + ParamSpecKwargs objects have a reference back to their ParamSpec: + + P.kwargs.__origin__ is P + + This type is meant for runtime introspection and has no special meaning to + static type checkers. + """ + def __init__(self, origin): + self.__origin__ = origin + + def __repr__(self): + return f"{self.__origin__.__name__}.kwargs" + + def __eq__(self, other): + if not isinstance(other, ParamSpecKwargs): + return NotImplemented + return self.__origin__ == other.__origin__ + +# 3.10+ +if hasattr(typing, 'ParamSpec'): + + # Add default Parameter - PEP 696 + class ParamSpec(typing.ParamSpec, _DefaultMixin, _root=True): + """Parameter specification variable.""" + + __module__ = 'typing' + + def __init__(self, name, *, bound=None, covariant=False, contravariant=False, + default=None): + super().__init__(name, bound=bound, covariant=covariant, + contravariant=contravariant) + _DefaultMixin.__init__(self, default) + + # for pickling: + try: + def_mod = sys._getframe(1).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): + def_mod = None + if def_mod != 'typing_extensions': + self.__module__ = def_mod + +# 3.7-3.9 +else: + + # Inherits from list as a workaround for Callable checks in Python < 3.9.2. + class ParamSpec(list, _DefaultMixin): + """Parameter specification variable. + + Usage:: + + P = ParamSpec('P') + + Parameter specification variables exist primarily for the benefit of static + type checkers. They are used to forward the parameter types of one + callable to another callable, a pattern commonly found in higher order + functions and decorators. They are only valid when used in ``Concatenate``, + or s the first argument to ``Callable``. In Python 3.10 and higher, + they are also supported in user-defined Generics at runtime. + See class Generic for more information on generic types. An + example for annotating a decorator:: + + T = TypeVar('T') + P = ParamSpec('P') + + def add_logging(f: Callable[P, T]) -> Callable[P, T]: + '''A type-safe decorator to add logging to a function.''' + def inner(*args: P.args, **kwargs: P.kwargs) -> T: + logging.info(f'{f.__name__} was called') + return f(*args, **kwargs) + return inner + + @add_logging + def add_two(x: float, y: float) -> float: + '''Add two numbers together.''' + return x + y + + Parameter specification variables defined with covariant=True or + contravariant=True can be used to declare covariant or contravariant + generic types. These keyword arguments are valid, but their actual semantics + are yet to be decided. See PEP 612 for details. + + Parameter specification variables can be introspected. e.g.: + + P.__name__ == 'T' + P.__bound__ == None + P.__covariant__ == False + P.__contravariant__ == False + + Note that only parameter specification variables defined in global scope can + be pickled. + """ + + # Trick Generic __parameters__. + __class__ = typing.TypeVar + + @property + def args(self): + return ParamSpecArgs(self) + + @property + def kwargs(self): + return ParamSpecKwargs(self) + + def __init__(self, name, *, bound=None, covariant=False, contravariant=False, + default=None): + super().__init__([self]) + self.__name__ = name + self.__covariant__ = bool(covariant) + self.__contravariant__ = bool(contravariant) + if bound: + self.__bound__ = typing._type_check(bound, 'Bound must be a type.') + else: + self.__bound__ = None + _DefaultMixin.__init__(self, default) + + # for pickling: + try: + def_mod = sys._getframe(1).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): + def_mod = None + if def_mod != 'typing_extensions': + self.__module__ = def_mod + + def __repr__(self): + if self.__covariant__: + prefix = '+' + elif self.__contravariant__: + prefix = '-' + else: + prefix = '~' + return prefix + self.__name__ + + def __hash__(self): + return object.__hash__(self) + + def __eq__(self, other): + return self is other + + def __reduce__(self): + return self.__name__ + + # Hack to get typing._type_check to pass. + def __call__(self, *args, **kwargs): + pass + + +# 3.7-3.9 +if not hasattr(typing, 'Concatenate'): + # Inherits from list as a workaround for Callable checks in Python < 3.9.2. + class _ConcatenateGenericAlias(list): + + # Trick Generic into looking into this for __parameters__. + __class__ = typing._GenericAlias + + # Flag in 3.8. + _special = False + + def __init__(self, origin, args): + super().__init__(args) + self.__origin__ = origin + self.__args__ = args + + def __repr__(self): + _type_repr = typing._type_repr + return (f'{_type_repr(self.__origin__)}' + f'[{", ".join(_type_repr(arg) for arg in self.__args__)}]') + + def __hash__(self): + return hash((self.__origin__, self.__args__)) + + # Hack to get typing._type_check to pass in Generic. + def __call__(self, *args, **kwargs): + pass + + @property + def __parameters__(self): + return tuple( + tp for tp in self.__args__ if isinstance(tp, (typing.TypeVar, ParamSpec)) + ) + + +# 3.7-3.9 +@typing._tp_cache +def _concatenate_getitem(self, parameters): + if parameters == (): + raise TypeError("Cannot take a Concatenate of no types.") + if not isinstance(parameters, tuple): + parameters = (parameters,) + if not isinstance(parameters[-1], ParamSpec): + raise TypeError("The last parameter to Concatenate should be a " + "ParamSpec variable.") + msg = "Concatenate[arg, ...]: each arg must be a type." + parameters = tuple(typing._type_check(p, msg) for p in parameters) + return _ConcatenateGenericAlias(self, parameters) + + +# 3.10+ +if hasattr(typing, 'Concatenate'): + Concatenate = typing.Concatenate + _ConcatenateGenericAlias = typing._ConcatenateGenericAlias # noqa +# 3.9 +elif sys.version_info[:2] >= (3, 9): + @_TypeAliasForm + def Concatenate(self, parameters): + """Used in conjunction with ``ParamSpec`` and ``Callable`` to represent a + higher order function which adds, removes or transforms parameters of a + callable. + + For example:: + + Callable[Concatenate[int, P], int] + + See PEP 612 for detailed information. + """ + return _concatenate_getitem(self, parameters) +# 3.7-8 +else: + class _ConcatenateForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + def __getitem__(self, parameters): + return _concatenate_getitem(self, parameters) + + Concatenate = _ConcatenateForm( + 'Concatenate', + doc="""Used in conjunction with ``ParamSpec`` and ``Callable`` to represent a + higher order function which adds, removes or transforms parameters of a + callable. + + For example:: + + Callable[Concatenate[int, P], int] + + See PEP 612 for detailed information. + """) + +# 3.10+ +if hasattr(typing, 'TypeGuard'): + TypeGuard = typing.TypeGuard +# 3.9 +elif sys.version_info[:2] >= (3, 9): + class _TypeGuardForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + @_TypeGuardForm + def TypeGuard(self, parameters): + """Special typing form used to annotate the return type of a user-defined + type guard function. ``TypeGuard`` only accepts a single type argument. + At runtime, functions marked this way should return a boolean. + + ``TypeGuard`` aims to benefit *type narrowing* -- a technique used by static + type checkers to determine a more precise type of an expression within a + program's code flow. Usually type narrowing is done by analyzing + conditional code flow and applying the narrowing to a block of code. The + conditional expression here is sometimes referred to as a "type guard". + + Sometimes it would be convenient to use a user-defined boolean function + as a type guard. Such a function should use ``TypeGuard[...]`` as its + return type to alert static type checkers to this intention. + + Using ``-> TypeGuard`` tells the static type checker that for a given + function: + + 1. The return value is a boolean. + 2. If the return value is ``True``, the type of its argument + is the type inside ``TypeGuard``. + + For example:: + + def is_str(val: Union[str, float]): + # "isinstance" type guard + if isinstance(val, str): + # Type of ``val`` is narrowed to ``str`` + ... + else: + # Else, type of ``val`` is narrowed to ``float``. + ... + + Strict type narrowing is not enforced -- ``TypeB`` need not be a narrower + form of ``TypeA`` (it can even be a wider form) and this may lead to + type-unsafe results. The main reason is to allow for things like + narrowing ``List[object]`` to ``List[str]`` even though the latter is not + a subtype of the former, since ``List`` is invariant. The responsibility of + writing type-safe type guards is left to the user. + + ``TypeGuard`` also works with type variables. For more information, see + PEP 647 (User-Defined Type Guards). + """ + item = typing._type_check(parameters, f'{self} accepts only a single type.') + return typing._GenericAlias(self, (item,)) +# 3.7-3.8 +else: + class _TypeGuardForm(typing._SpecialForm, _root=True): + + def __repr__(self): + return 'typing_extensions.' + self._name + + def __getitem__(self, parameters): + item = typing._type_check(parameters, + f'{self._name} accepts only a single type') + return typing._GenericAlias(self, (item,)) + + TypeGuard = _TypeGuardForm( + 'TypeGuard', + doc="""Special typing form used to annotate the return type of a user-defined + type guard function. ``TypeGuard`` only accepts a single type argument. + At runtime, functions marked this way should return a boolean. + + ``TypeGuard`` aims to benefit *type narrowing* -- a technique used by static + type checkers to determine a more precise type of an expression within a + program's code flow. Usually type narrowing is done by analyzing + conditional code flow and applying the narrowing to a block of code. The + conditional expression here is sometimes referred to as a "type guard". + + Sometimes it would be convenient to use a user-defined boolean function + as a type guard. Such a function should use ``TypeGuard[...]`` as its + return type to alert static type checkers to this intention. + + Using ``-> TypeGuard`` tells the static type checker that for a given + function: + + 1. The return value is a boolean. + 2. If the return value is ``True``, the type of its argument + is the type inside ``TypeGuard``. + + For example:: + + def is_str(val: Union[str, float]): + # "isinstance" type guard + if isinstance(val, str): + # Type of ``val`` is narrowed to ``str`` + ... + else: + # Else, type of ``val`` is narrowed to ``float``. + ... + + Strict type narrowing is not enforced -- ``TypeB`` need not be a narrower + form of ``TypeA`` (it can even be a wider form) and this may lead to + type-unsafe results. The main reason is to allow for things like + narrowing ``List[object]`` to ``List[str]`` even though the latter is not + a subtype of the former, since ``List`` is invariant. The responsibility of + writing type-safe type guards is left to the user. + + ``TypeGuard`` also works with type variables. For more information, see + PEP 647 (User-Defined Type Guards). + """) + + +# Vendored from cpython typing._SpecialFrom +class _SpecialForm(typing._Final, _root=True): + __slots__ = ('_name', '__doc__', '_getitem') + + def __init__(self, getitem): + self._getitem = getitem + self._name = getitem.__name__ + self.__doc__ = getitem.__doc__ + + def __getattr__(self, item): + if item in {'__name__', '__qualname__'}: + return self._name + + raise AttributeError(item) + + def __mro_entries__(self, bases): + raise TypeError(f"Cannot subclass {self!r}") + + def __repr__(self): + return f'typing_extensions.{self._name}' + + def __reduce__(self): + return self._name + + def __call__(self, *args, **kwds): + raise TypeError(f"Cannot instantiate {self!r}") + + def __or__(self, other): + return typing.Union[self, other] + + def __ror__(self, other): + return typing.Union[other, self] + + def __instancecheck__(self, obj): + raise TypeError(f"{self} cannot be used with isinstance()") + + def __subclasscheck__(self, cls): + raise TypeError(f"{self} cannot be used with issubclass()") + + @typing._tp_cache + def __getitem__(self, parameters): + return self._getitem(self, parameters) + + +if hasattr(typing, "LiteralString"): + LiteralString = typing.LiteralString +else: + @_SpecialForm + def LiteralString(self, params): + """Represents an arbitrary literal string. + + Example:: + + from typing_extensions import LiteralString + + def query(sql: LiteralString) -> ...: + ... + + query("SELECT * FROM table") # ok + query(f"SELECT * FROM {input()}") # not ok + + See PEP 675 for details. + + """ + raise TypeError(f"{self} is not subscriptable") + + +if hasattr(typing, "Self"): + Self = typing.Self +else: + @_SpecialForm + def Self(self, params): + """Used to spell the type of "self" in classes. + + Example:: + + from typing import Self + + class ReturnsSelf: + def parse(self, data: bytes) -> Self: + ... + return self + + """ + + raise TypeError(f"{self} is not subscriptable") + + +if hasattr(typing, "Never"): + Never = typing.Never +else: + @_SpecialForm + def Never(self, params): + """The bottom type, a type that has no members. + + This can be used to define a function that should never be + called, or a function that never returns:: + + from typing_extensions import Never + + def never_call_me(arg: Never) -> None: + pass + + def int_or_str(arg: int | str) -> None: + never_call_me(arg) # type checker error + match arg: + case int(): + print("It's an int") + case str(): + print("It's a str") + case _: + never_call_me(arg) # ok, arg is of type Never + + """ + + raise TypeError(f"{self} is not subscriptable") + + +if hasattr(typing, 'Required'): + Required = typing.Required + NotRequired = typing.NotRequired +elif sys.version_info[:2] >= (3, 9): + class _ExtensionsSpecialForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + @_ExtensionsSpecialForm + def Required(self, parameters): + """A special typing construct to mark a key of a total=False TypedDict + as required. For example: + + class Movie(TypedDict, total=False): + title: Required[str] + year: int + + m = Movie( + title='The Matrix', # typechecker error if key is omitted + year=1999, + ) + + There is no runtime checking that a required key is actually provided + when instantiating a related TypedDict. + """ + item = typing._type_check(parameters, f'{self._name} accepts only a single type.') + return typing._GenericAlias(self, (item,)) + + @_ExtensionsSpecialForm + def NotRequired(self, parameters): + """A special typing construct to mark a key of a TypedDict as + potentially missing. For example: + + class Movie(TypedDict): + title: str + year: NotRequired[int] + + m = Movie( + title='The Matrix', # typechecker error if key is omitted + year=1999, + ) + """ + item = typing._type_check(parameters, f'{self._name} accepts only a single type.') + return typing._GenericAlias(self, (item,)) + +else: + class _RequiredForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + def __getitem__(self, parameters): + item = typing._type_check(parameters, + f'{self._name} accepts only a single type.') + return typing._GenericAlias(self, (item,)) + + Required = _RequiredForm( + 'Required', + doc="""A special typing construct to mark a key of a total=False TypedDict + as required. For example: + + class Movie(TypedDict, total=False): + title: Required[str] + year: int + + m = Movie( + title='The Matrix', # typechecker error if key is omitted + year=1999, + ) + + There is no runtime checking that a required key is actually provided + when instantiating a related TypedDict. + """) + NotRequired = _RequiredForm( + 'NotRequired', + doc="""A special typing construct to mark a key of a TypedDict as + potentially missing. For example: + + class Movie(TypedDict): + title: str + year: NotRequired[int] + + m = Movie( + title='The Matrix', # typechecker error if key is omitted + year=1999, + ) + """) + + +if hasattr(typing, "Unpack"): # 3.11+ + Unpack = typing.Unpack +elif sys.version_info[:2] >= (3, 9): + class _UnpackSpecialForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + class _UnpackAlias(typing._GenericAlias, _root=True): + __class__ = typing.TypeVar + + @_UnpackSpecialForm + def Unpack(self, parameters): + """A special typing construct to unpack a variadic type. For example: + + Shape = TypeVarTuple('Shape') + Batch = NewType('Batch', int) + + def add_batch_axis( + x: Array[Unpack[Shape]] + ) -> Array[Batch, Unpack[Shape]]: ... + + """ + item = typing._type_check(parameters, f'{self._name} accepts only a single type.') + return _UnpackAlias(self, (item,)) + + def _is_unpack(obj): + return isinstance(obj, _UnpackAlias) + +else: + class _UnpackAlias(typing._GenericAlias, _root=True): + __class__ = typing.TypeVar + + class _UnpackForm(typing._SpecialForm, _root=True): + def __repr__(self): + return 'typing_extensions.' + self._name + + def __getitem__(self, parameters): + item = typing._type_check(parameters, + f'{self._name} accepts only a single type.') + return _UnpackAlias(self, (item,)) + + Unpack = _UnpackForm( + 'Unpack', + doc="""A special typing construct to unpack a variadic type. For example: + + Shape = TypeVarTuple('Shape') + Batch = NewType('Batch', int) + + def add_batch_axis( + x: Array[Unpack[Shape]] + ) -> Array[Batch, Unpack[Shape]]: ... + + """) + + def _is_unpack(obj): + return isinstance(obj, _UnpackAlias) + + +if hasattr(typing, "TypeVarTuple"): # 3.11+ + + # Add default Parameter - PEP 696 + class TypeVarTuple(typing.TypeVarTuple, _DefaultMixin, _root=True): + """Type variable tuple.""" + + def __init__(self, name, *, default=None): + super().__init__(name) + _DefaultMixin.__init__(self, default) + + # for pickling: + try: + def_mod = sys._getframe(1).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): + def_mod = None + if def_mod != 'typing_extensions': + self.__module__ = def_mod + +else: + class TypeVarTuple(_DefaultMixin): + """Type variable tuple. + + Usage:: + + Ts = TypeVarTuple('Ts') + + In the same way that a normal type variable is a stand-in for a single + type such as ``int``, a type variable *tuple* is a stand-in for a *tuple* + type such as ``Tuple[int, str]``. + + Type variable tuples can be used in ``Generic`` declarations. + Consider the following example:: + + class Array(Generic[*Ts]): ... + + The ``Ts`` type variable tuple here behaves like ``tuple[T1, T2]``, + where ``T1`` and ``T2`` are type variables. To use these type variables + as type parameters of ``Array``, we must *unpack* the type variable tuple using + the star operator: ``*Ts``. The signature of ``Array`` then behaves + as if we had simply written ``class Array(Generic[T1, T2]): ...``. + In contrast to ``Generic[T1, T2]``, however, ``Generic[*Shape]`` allows + us to parameterise the class with an *arbitrary* number of type parameters. + + Type variable tuples can be used anywhere a normal ``TypeVar`` can. + This includes class definitions, as shown above, as well as function + signatures and variable annotations:: + + class Array(Generic[*Ts]): + + def __init__(self, shape: Tuple[*Ts]): + self._shape: Tuple[*Ts] = shape + + def get_shape(self) -> Tuple[*Ts]: + return self._shape + + shape = (Height(480), Width(640)) + x: Array[Height, Width] = Array(shape) + y = abs(x) # Inferred type is Array[Height, Width] + z = x + x # ... is Array[Height, Width] + x.get_shape() # ... is tuple[Height, Width] + + """ + + # Trick Generic __parameters__. + __class__ = typing.TypeVar + + def __iter__(self): + yield self.__unpacked__ + + def __init__(self, name, *, default=None): + self.__name__ = name + _DefaultMixin.__init__(self, default) + + # for pickling: + try: + def_mod = sys._getframe(1).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): + def_mod = None + if def_mod != 'typing_extensions': + self.__module__ = def_mod + + self.__unpacked__ = Unpack[self] + + def __repr__(self): + return self.__name__ + + def __hash__(self): + return object.__hash__(self) + + def __eq__(self, other): + return self is other + + def __reduce__(self): + return self.__name__ + + def __init_subclass__(self, *args, **kwds): + if '_root' not in kwds: + raise TypeError("Cannot subclass special typing classes") + + +if hasattr(typing, "reveal_type"): + reveal_type = typing.reveal_type +else: + def reveal_type(__obj: T) -> T: + """Reveal the inferred type of a variable. + + When a static type checker encounters a call to ``reveal_type()``, + it will emit the inferred type of the argument:: + + x: int = 1 + reveal_type(x) + + Running a static type checker (e.g., ``mypy``) on this example + will produce output similar to 'Revealed type is "builtins.int"'. + + At runtime, the function prints the runtime type of the + argument and returns it unchanged. + + """ + print(f"Runtime type is {type(__obj).__name__!r}", file=sys.stderr) + return __obj + + +if hasattr(typing, "assert_never"): + assert_never = typing.assert_never +else: + def assert_never(__arg: Never) -> Never: + """Assert to the type checker that a line of code is unreachable. + + Example:: + + def int_or_str(arg: int | str) -> None: + match arg: + case int(): + print("It's an int") + case str(): + print("It's a str") + case _: + assert_never(arg) + + If a type checker finds that a call to assert_never() is + reachable, it will emit an error. + + At runtime, this throws an exception when called. + + """ + raise AssertionError("Expected code to be unreachable") + + +if hasattr(typing, 'dataclass_transform'): + dataclass_transform = typing.dataclass_transform +else: + def dataclass_transform( + *, + eq_default: bool = True, + order_default: bool = False, + kw_only_default: bool = False, + field_specifiers: typing.Tuple[ + typing.Union[typing.Type[typing.Any], typing.Callable[..., typing.Any]], + ... + ] = (), + **kwargs: typing.Any, + ) -> typing.Callable[[T], T]: + """Decorator that marks a function, class, or metaclass as providing + dataclass-like behavior. + + Example: + + from typing_extensions import dataclass_transform + + _T = TypeVar("_T") + + # Used on a decorator function + @dataclass_transform() + def create_model(cls: type[_T]) -> type[_T]: + ... + return cls + + @create_model + class CustomerModel: + id: int + name: str + + # Used on a base class + @dataclass_transform() + class ModelBase: ... + + class CustomerModel(ModelBase): + id: int + name: str + + # Used on a metaclass + @dataclass_transform() + class ModelMeta(type): ... + + class ModelBase(metaclass=ModelMeta): ... + + class CustomerModel(ModelBase): + id: int + name: str + + Each of the ``CustomerModel`` classes defined in this example will now + behave similarly to a dataclass created with the ``@dataclasses.dataclass`` + decorator. For example, the type checker will synthesize an ``__init__`` + method. + + The arguments to this decorator can be used to customize this behavior: + - ``eq_default`` indicates whether the ``eq`` parameter is assumed to be + True or False if it is omitted by the caller. + - ``order_default`` indicates whether the ``order`` parameter is + assumed to be True or False if it is omitted by the caller. + - ``kw_only_default`` indicates whether the ``kw_only`` parameter is + assumed to be True or False if it is omitted by the caller. + - ``field_specifiers`` specifies a static list of supported classes + or functions that describe fields, similar to ``dataclasses.field()``. + + At runtime, this decorator records its arguments in the + ``__dataclass_transform__`` attribute on the decorated object. + + See PEP 681 for details. + + """ + def decorator(cls_or_fn): + cls_or_fn.__dataclass_transform__ = { + "eq_default": eq_default, + "order_default": order_default, + "kw_only_default": kw_only_default, + "field_specifiers": field_specifiers, + "kwargs": kwargs, + } + return cls_or_fn + return decorator + + +if hasattr(typing, "override"): + override = typing.override +else: + _F = typing.TypeVar("_F", bound=typing.Callable[..., typing.Any]) + + def override(__arg: _F) -> _F: + """Indicate that a method is intended to override a method in a base class. + + Usage: + + class Base: + def method(self) -> None: ... + pass + + class Child(Base): + @override + def method(self) -> None: + super().method() + + When this decorator is applied to a method, the type checker will + validate that it overrides a method with the same name on a base class. + This helps prevent bugs that may occur when a base class is changed + without an equivalent change to a child class. + + See PEP 698 for details. + + """ + return __arg + + +# We have to do some monkey patching to deal with the dual nature of +# Unpack/TypeVarTuple: +# - We want Unpack to be a kind of TypeVar so it gets accepted in +# Generic[Unpack[Ts]] +# - We want it to *not* be treated as a TypeVar for the purposes of +# counting generic parameters, so that when we subscript a generic, +# the runtime doesn't try to substitute the Unpack with the subscripted type. +if not hasattr(typing, "TypeVarTuple"): + typing._collect_type_vars = _collect_type_vars + typing._check_generic = _check_generic + + +# Backport typing.NamedTuple as it exists in Python 3.11. +# In 3.11, the ability to define generic `NamedTuple`s was supported. +# This was explicitly disallowed in 3.9-3.10, and only half-worked in <=3.8. +if sys.version_info >= (3, 11): + NamedTuple = typing.NamedTuple +else: + def _caller(): + try: + return sys._getframe(2).f_globals.get('__name__', '__main__') + except (AttributeError, ValueError): # For platforms without _getframe() + return None + + def _make_nmtuple(name, types, module, defaults=()): + fields = [n for n, t in types] + annotations = {n: typing._type_check(t, f"field {n} annotation must be a type") + for n, t in types} + nm_tpl = collections.namedtuple(name, fields, + defaults=defaults, module=module) + nm_tpl.__annotations__ = nm_tpl.__new__.__annotations__ = annotations + # The `_field_types` attribute was removed in 3.9; + # in earlier versions, it is the same as the `__annotations__` attribute + if sys.version_info < (3, 9): + nm_tpl._field_types = annotations + return nm_tpl + + _prohibited_namedtuple_fields = typing._prohibited + _special_namedtuple_fields = frozenset({'__module__', '__name__', '__annotations__'}) + + class _NamedTupleMeta(type): + def __new__(cls, typename, bases, ns): + assert _NamedTuple in bases + for base in bases: + if base is not _NamedTuple and base is not typing.Generic: + raise TypeError( + 'can only inherit from a NamedTuple type and Generic') + bases = tuple(tuple if base is _NamedTuple else base for base in bases) + types = ns.get('__annotations__', {}) + default_names = [] + for field_name in types: + if field_name in ns: + default_names.append(field_name) + elif default_names: + raise TypeError(f"Non-default namedtuple field {field_name} " + f"cannot follow default field" + f"{'s' if len(default_names) > 1 else ''} " + f"{', '.join(default_names)}") + nm_tpl = _make_nmtuple( + typename, types.items(), + defaults=[ns[n] for n in default_names], + module=ns['__module__'] + ) + nm_tpl.__bases__ = bases + if typing.Generic in bases: + class_getitem = typing.Generic.__class_getitem__.__func__ + nm_tpl.__class_getitem__ = classmethod(class_getitem) + # update from user namespace without overriding special namedtuple attributes + for key in ns: + if key in _prohibited_namedtuple_fields: + raise AttributeError("Cannot overwrite NamedTuple attribute " + key) + elif key not in _special_namedtuple_fields and key not in nm_tpl._fields: + setattr(nm_tpl, key, ns[key]) + if typing.Generic in bases: + nm_tpl.__init_subclass__() + return nm_tpl + + def NamedTuple(__typename, __fields=None, **kwargs): + if __fields is None: + __fields = kwargs.items() + elif kwargs: + raise TypeError("Either list of fields or keywords" + " can be provided to NamedTuple, not both") + return _make_nmtuple(__typename, __fields, module=_caller()) + + NamedTuple.__doc__ = typing.NamedTuple.__doc__ + _NamedTuple = type.__new__(_NamedTupleMeta, 'NamedTuple', (), {}) + + # On 3.8+, alter the signature so that it matches typing.NamedTuple. + # The signature of typing.NamedTuple on >=3.8 is invalid syntax in Python 3.7, + # so just leave the signature as it is on 3.7. + if sys.version_info >= (3, 8): + NamedTuple.__text_signature__ = '(typename, fields=None, /, **kwargs)' + + def _namedtuple_mro_entries(bases): + assert NamedTuple in bases + return (_NamedTuple,) + + NamedTuple.__mro_entries__ = _namedtuple_mro_entries diff --git a/pkg_resources/_vendor/vendored.txt b/pkg_resources/_vendor/vendored.txt index 0128eb17..e1774da3 100644 --- a/pkg_resources/_vendor/vendored.txt +++ b/pkg_resources/_vendor/vendored.txt @@ -1,6 +1,10 @@ -packaging==21.2 -pyparsing==2.2.1 -appdirs==1.4.3 +packaging==21.3 +pyparsing==3.0.9 + +platformdirs==2.6.2 +# required for platformdirs on Python < 3.8 +typing_extensions==4.4.0 + jaraco.text==3.7.0 # required for jaraco.text on older Pythons importlib_resources==5.4.0 diff --git a/pkg_resources/_vendor/zipp-3.7.0.dist-info/RECORD b/pkg_resources/_vendor/zipp-3.7.0.dist-info/RECORD index 38d0b21a..0a88551c 100644 --- a/pkg_resources/_vendor/zipp-3.7.0.dist-info/RECORD +++ b/pkg_resources/_vendor/zipp-3.7.0.dist-info/RECORD @@ -1,4 +1,4 @@ -__pycache__/zipp.cpython-310.pyc,,
+__pycache__/zipp.cpython-311.pyc,,
zipp-3.7.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
zipp-3.7.0.dist-info/LICENSE,sha256=2z8CRrH5J48VhFuZ_sR4uLUG63ZIeZNyL4xuJUKF-vg,1050
zipp-3.7.0.dist-info/METADATA,sha256=ZLzgaXTyZX_MxTU0lcGfhdPY4CjFrT_3vyQ2Fo49pl8,2261
diff --git a/pkg_resources/extern/__init__.py b/pkg_resources/extern/__init__.py index 70897eea..bacc5d77 100644 --- a/pkg_resources/extern/__init__.py +++ b/pkg_resources/extern/__init__.py @@ -58,7 +58,8 @@ class VendorImporter: """Return a module spec for vendored names.""" return ( importlib.util.spec_from_loader(fullname, self) - if self._module_matches_namespace(fullname) else None + if self._module_matches_namespace(fullname) + else None ) def install(self): @@ -70,7 +71,11 @@ class VendorImporter: names = ( - 'packaging', 'pyparsing', 'appdirs', 'jaraco', 'importlib_resources', + 'packaging', + 'pyparsing', + 'platformdirs', + 'jaraco', + 'importlib_resources', 'more_itertools', ) VendorImporter(__name__, names).install() diff --git a/pkg_resources/tests/test_markers.py b/pkg_resources/tests/test_markers.py index 15a3b499..9306d5b3 100644 --- a/pkg_resources/tests/test_markers.py +++ b/pkg_resources/tests/test_markers.py @@ -1,4 +1,4 @@ -import mock +from unittest import mock from pkg_resources import evaluate_marker diff --git a/pkg_resources/tests/test_pkg_resources.py b/pkg_resources/tests/test_pkg_resources.py index 6518820e..684c9777 100644 --- a/pkg_resources/tests/test_pkg_resources.py +++ b/pkg_resources/tests/test_pkg_resources.py @@ -9,10 +9,7 @@ import stat import distutils.dist import distutils.command.install_egg_info -try: - from unittest import mock -except ImportError: - import mock +from unittest import mock from pkg_resources import ( DistInfoDistribution, Distribution, EggInfoDistribution, diff --git a/pkg_resources/tests/test_working_set.py b/pkg_resources/tests/test_working_set.py index db13c714..575656ee 100644 --- a/pkg_resources/tests/test_working_set.py +++ b/pkg_resources/tests/test_working_set.py @@ -42,7 +42,7 @@ def parse_distributions(s): continue fields = spec.split('\n', 1) assert 1 <= len(fields) <= 2 - name, version = fields.pop(0).split('-') + name, version = fields.pop(0).rsplit('-', 1) if fields: requires = textwrap.dedent(fields.pop(0)) metadata = Metadata(('requires.txt', requires)) @@ -465,6 +465,25 @@ def parametrize_test_working_set_resolve(*test_list): # resolved [replace conflicting] VersionConflict ''', + + ''' + # id + wanted_normalized_name_installed_canonical + + # installed + foo.bar-3.6 + + # installable + + # wanted + foo-bar==3.6 + + # resolved + foo.bar-3.6 + + # resolved [replace conflicting] + foo.bar-3.6 + ''', ) def test_working_set_resolve(installed_dists, installable_dists, requirements, replace_conflicting, resolved_dists_or_exception): |