diff options
author | Donald Stufft <donald@stufft.io> | 2016-10-30 01:35:28 -0400 |
---|---|---|
committer | GitHub <noreply@github.com> | 2016-10-30 01:35:28 -0400 |
commit | c8e8a99b7a6f9404536bc9d895a1a42a060f7f91 (patch) | |
tree | 6821e51d5b5835702e958e29fc3df74ac41c8bc2 | |
parent | 22f2e01be5cd64d7db524e1ab5931fdc98521cfb (diff) | |
download | pip-c8e8a99b7a6f9404536bc9d895a1a42a060f7f91.tar.gz |
Upgrade Dependencies (#4038)
* Upgrade distlib to 0.2.4
* Upgrade distro to 1.0.0
* Upgrade html5lib to 1.0b10
* Upgrade requests to 2.11.1
* Upgrade CacheControl to 0.11.7
* Upgrade ipaddress to 1.0.17
* Upgrade pyparsing to 2.1.10
* Upgrade packaging to 16.8
* Add webencodings 0.5
* Add ordereddict 1.1
96 files changed, 7077 insertions, 2557 deletions
diff --git a/pip/_vendor/README.rst b/pip/_vendor/README.rst index 4a27bf09c..855b174f7 100644 --- a/pip/_vendor/README.rst +++ b/pip/_vendor/README.rst @@ -106,6 +106,7 @@ Modifications * CacheControl has been modified to import its dependencies from pip._vendor * packaging has been modified to import its dependencies from pip._vendor * requests has been modified *not* to optionally load any C dependencies. +* Modified distro to delay importing argparse to avoid errors on 2.6 Debundling diff --git a/pip/_vendor/cachecontrol/__init__.py b/pip/_vendor/cachecontrol/__init__.py index 724e220dc..ec9da2e37 100644 --- a/pip/_vendor/cachecontrol/__init__.py +++ b/pip/_vendor/cachecontrol/__init__.py @@ -4,7 +4,7 @@ Make it easy to import from cachecontrol without long namespaces. """ __author__ = 'Eric Larson' __email__ = 'eric@ionrock.org' -__version__ = '0.11.6' +__version__ = '0.11.7' from .wrapper import CacheControl from .adapter import CacheControlAdapter diff --git a/pip/_vendor/cachecontrol/adapter.py b/pip/_vendor/cachecontrol/adapter.py index 74589e00c..23488566b 100644 --- a/pip/_vendor/cachecontrol/adapter.py +++ b/pip/_vendor/cachecontrol/adapter.py @@ -1,3 +1,4 @@ +import types import functools from pip._vendor.requests.adapters import HTTPAdapter @@ -55,6 +56,10 @@ class CacheControlAdapter(HTTPAdapter): cached response """ if not from_cache and request.method == 'GET': + # Check for any heuristics that might update headers + # before trying to cache. + if self.heuristic: + response = self.heuristic.apply(response) # apply any expiration heuristics if response.status == 304: @@ -82,11 +87,6 @@ class CacheControlAdapter(HTTPAdapter): elif response.status == 301: self.controller.cache_response(request, response) else: - # Check for any heuristics that might update headers - # before trying to cache. - if self.heuristic: - response = self.heuristic.apply(response) - # Wrap the response file with a wrapper that will cache the # response when the stream has been consumed. response._fp = CallbackFileWrapper( @@ -97,6 +97,14 @@ class CacheControlAdapter(HTTPAdapter): response, ) ) + if response.chunked: + super_update_chunk_length = response._update_chunk_length + + def _update_chunk_length(self): + super_update_chunk_length() + if self.chunk_left == 0: + self._fp._close() + response._update_chunk_length = types.MethodType(_update_chunk_length, response) resp = super(CacheControlAdapter, self).build_response( request, response diff --git a/pip/_vendor/cachecontrol/controller.py b/pip/_vendor/cachecontrol/controller.py index 6e591f8b0..5eb961f85 100644 --- a/pip/_vendor/cachecontrol/controller.py +++ b/pip/_vendor/cachecontrol/controller.py @@ -290,7 +290,7 @@ class CacheController(object): elif 'date' in response_headers: # cache when there is a max-age > 0 if cc and cc.get('max-age'): - if int(cc['max-age']) > 0: + if cc['max-age'].isdigit() and int(cc['max-age']) > 0: logger.debug('Caching b/c date exists and max-age > 0') self.cache.set( cache_url, diff --git a/pip/_vendor/cachecontrol/filewrapper.py b/pip/_vendor/cachecontrol/filewrapper.py index 4b91bce04..f1e1ce055 100644 --- a/pip/_vendor/cachecontrol/filewrapper.py +++ b/pip/_vendor/cachecontrol/filewrapper.py @@ -45,19 +45,34 @@ class CallbackFileWrapper(object): # TODO: Add some logging here... return False + def _close(self): + if self.__callback: + self.__callback(self.__buf.getvalue()) + + # We assign this to None here, because otherwise we can get into + # really tricky problems where the CPython interpreter dead locks + # because the callback is holding a reference to something which + # has a __del__ method. Setting this to None breaks the cycle + # and allows the garbage collector to do it's thing normally. + self.__callback = None + def read(self, amt=None): data = self.__fp.read(amt) self.__buf.write(data) + if self.__is_fp_closed(): + self._close() + return data + + def _safe_read(self, amt): + data = self.__fp._safe_read(amt) + if amt == 2 and data == b'\r\n': + # urllib executes this read to toss the CRLF at the end + # of the chunk. + return data + + self.__buf.write(data) if self.__is_fp_closed(): - if self.__callback: - self.__callback(self.__buf.getvalue()) - - # We assign this to None here, because otherwise we can get into - # really tricky problems where the CPython interpreter dead locks - # because the callback is holding a reference to something which - # has a __del__ method. Setting this to None breaks the cycle - # and allows the garbage collector to do it's thing normally. - self.__callback = None + self._close() return data diff --git a/pip/_vendor/cachecontrol/serialize.py b/pip/_vendor/cachecontrol/serialize.py index ffbfbf6f8..8f9c589f2 100644 --- a/pip/_vendor/cachecontrol/serialize.py +++ b/pip/_vendor/cachecontrol/serialize.py @@ -134,6 +134,12 @@ class Serializer(object): body_raw = cached["response"].pop("body") + headers = CaseInsensitiveDict(data=cached['response']['headers']) + if headers.get('transfer-encoding', '') == 'chunked': + headers.pop('transfer-encoding') + + cached['response']['headers'] = headers + try: body = io.BytesIO(body_raw) except TypeError: diff --git a/pip/_vendor/distlib/__init__.py b/pip/_vendor/distlib/__init__.py index 7026860f1..d186b0a36 100644 --- a/pip/_vendor/distlib/__init__.py +++ b/pip/_vendor/distlib/__init__.py @@ -6,7 +6,7 @@ # import logging -__version__ = '0.2.3' +__version__ = '0.2.4' class DistlibException(Exception): pass diff --git a/pip/_vendor/distlib/_backport/shutil.py b/pip/_vendor/distlib/_backport/shutil.py index 9e2e234d4..159e49ee8 100644 --- a/pip/_vendor/distlib/_backport/shutil.py +++ b/pip/_vendor/distlib/_backport/shutil.py @@ -55,8 +55,8 @@ class ReadError(EnvironmentError): """Raised when an archive cannot be read""" class RegistryError(Exception): - """Raised when a registery operation with the archiving - and unpacking registeries fails""" + """Raised when a registry operation with the archiving + and unpacking registries fails""" try: @@ -648,7 +648,7 @@ def register_unpack_format(name, extensions, function, extra_args=None, _UNPACK_FORMATS[name] = extensions, function, extra_args, description def unregister_unpack_format(name): - """Removes the pack format from the registery.""" + """Removes the pack format from the registry.""" del _UNPACK_FORMATS[name] def _ensure_directory(path): diff --git a/pip/_vendor/distlib/_backport/tarfile.py b/pip/_vendor/distlib/_backport/tarfile.py index 0580fb795..d66d85663 100644 --- a/pip/_vendor/distlib/_backport/tarfile.py +++ b/pip/_vendor/distlib/_backport/tarfile.py @@ -331,7 +331,7 @@ class ExtractError(TarError): """General exception for extract errors.""" pass class ReadError(TarError): - """Exception for unreadble tar archives.""" + """Exception for unreadable tar archives.""" pass class CompressionError(TarError): """Exception for unavailable compression methods.""" diff --git a/pip/_vendor/distlib/compat.py b/pip/_vendor/distlib/compat.py index 069ec7796..2b198dd57 100644 --- a/pip/_vendor/distlib/compat.py +++ b/pip/_vendor/distlib/compat.py @@ -10,6 +10,11 @@ import os import re import sys +try: + import ssl +except ImportError: + ssl = None + if sys.version_info[0] < 3: # pragma: no cover from StringIO import StringIO string_types = basestring, @@ -30,8 +35,10 @@ if sys.version_info[0] < 3: # pragma: no cover import urllib2 from urllib2 import (Request, urlopen, URLError, HTTPError, HTTPBasicAuthHandler, HTTPPasswordMgr, - HTTPSHandler, HTTPHandler, HTTPRedirectHandler, + HTTPHandler, HTTPRedirectHandler, build_opener) + if ssl: + from urllib2 import HTTPSHandler import httplib import xmlrpclib import Queue as queue @@ -66,8 +73,10 @@ else: # pragma: no cover from urllib.request import (urlopen, urlretrieve, Request, url2pathname, pathname2url, HTTPBasicAuthHandler, HTTPPasswordMgr, - HTTPSHandler, HTTPHandler, HTTPRedirectHandler, + HTTPHandler, HTTPRedirectHandler, build_opener) + if ssl: + from urllib.request import HTTPSHandler from urllib.error import HTTPError, URLError, ContentTooShortError import http.client as httplib import urllib.request as urllib2 @@ -101,7 +110,7 @@ except ImportError: # pragma: no cover wildcards = leftmost.count('*') if wildcards > max_wildcards: # Issue #17980: avoid denials of service by refusing more - # than one wildcard per fragment. A survery of established + # than one wildcard per fragment. A survey of established # policy among SSL implementations showed it to be a # reasonable choice. raise CertificateError( @@ -366,7 +375,7 @@ except ImportError: # pragma: no cover def detect_encoding(readline): """ The detect_encoding() function is used to detect the encoding that should - be used to decode a Python source file. It requires one argment, readline, + be used to decode a Python source file. It requires one argument, readline, in the same way as the tokenize() generator. It will call readline a maximum of twice, and return the encoding used diff --git a/pip/_vendor/distlib/database.py b/pip/_vendor/distlib/database.py index 7bc191447..c31442640 100644 --- a/pip/_vendor/distlib/database.py +++ b/pip/_vendor/distlib/database.py @@ -1308,5 +1308,5 @@ def make_dist(name, version, **kwargs): md = Metadata(**kwargs) md.name = name md.version = version - md.summary = summary or 'Plaeholder for summary' + md.summary = summary or 'Placeholder for summary' return Distribution(md) diff --git a/pip/_vendor/distlib/index.py b/pip/_vendor/distlib/index.py index 73037c97b..6803dd283 100644 --- a/pip/_vendor/distlib/index.py +++ b/pip/_vendor/distlib/index.py @@ -51,7 +51,9 @@ class PackageIndex(object): self.gpg_home = None self.rpc_proxy = None with open(os.devnull, 'w') as sink: - for s in ('gpg2', 'gpg'): + # Use gpg by default rather than gpg2, as gpg2 insists on + # prompting for passwords + for s in ('gpg', 'gpg2'): try: rc = subprocess.check_call([s, '--version'], stdout=sink, stderr=sink) @@ -74,7 +76,7 @@ class PackageIndex(object): def read_configuration(self): """ Read the PyPI access configuration as supported by distutils, getting - PyPI to do the acutal work. This populates ``username``, ``password``, + PyPI to do the actual work. This populates ``username``, ``password``, ``realm`` and ``url`` attributes from the configuration. """ # get distutils to do the work @@ -276,7 +278,7 @@ class PackageIndex(object): sha256_digest = hashlib.sha256(file_data).hexdigest() d.update({ ':action': 'file_upload', - 'protcol_version': '1', + 'protocol_version': '1', 'filetype': filetype, 'pyversion': pyversion, 'md5_digest': md5_digest, diff --git a/pip/_vendor/distlib/locators.py b/pip/_vendor/distlib/locators.py index 1e1463820..14789ef5d 100644 --- a/pip/_vendor/distlib/locators.py +++ b/pip/_vendor/distlib/locators.py @@ -21,13 +21,13 @@ import zlib from . import DistlibException from .compat import (urljoin, urlparse, urlunparse, url2pathname, pathname2url, queue, quote, unescape, string_types, build_opener, - HTTPRedirectHandler as BaseRedirectHandler, + HTTPRedirectHandler as BaseRedirectHandler, text_type, Request, HTTPError, URLError) from .database import Distribution, DistributionPath, make_dist from .metadata import Metadata from .util import (cached_property, parse_credentials, ensure_slash, split_filename, get_project_data, parse_requirement, - parse_name_and_version, ServerProxy) + parse_name_and_version, ServerProxy, normalize_name) from .version import get_scheme, UnsupportedVersionError from .wheel import Wheel, is_compatible @@ -113,6 +113,28 @@ class Locator(object): # is set from the requirement passed to locate(). See issue #18 for # why this can be useful to know. self.matcher = None + self.errors = queue.Queue() + + def get_errors(self): + """ + Return any errors which have occurred. + """ + result = [] + while not self.errors.empty(): # pragma: no cover + try: + e = self.errors.get(False) + result.append(e) + except self.errors.Empty: + continue + self.errors.task_done() + return result + + def clear_errors(self): + """ + Clear any errors which may have been logged. + """ + # Just get the errors and throw them away + self.get_errors() def clear_cache(self): self._cache.clear() @@ -155,6 +177,7 @@ class Locator(object): elif name in self._cache: result = self._cache[name] else: + self.clear_errors() result = self._get_project(name) self._cache[name] = result return result @@ -210,14 +233,7 @@ class Locator(object): "filename" and "url"; otherwise, None is returned. """ def same_project(name1, name2): - name1, name2 = name1.lower(), name2.lower() - if name1 == name2: - result = True - else: - # distribute replaces '-' by '_' in project names, so it - # can tell where the version starts in a filename. - result = name1.replace('_', '-') == name2.replace('_', '-') - return result + return normalize_name(name1) == normalize_name(name2) result = None scheme, netloc, path, params, query, frag = urlparse(url) @@ -250,7 +266,7 @@ class Locator(object): 'python-version': ', '.join( ['.'.join(list(v[2:])) for v in wheel.pyver]), } - except Exception as e: + except Exception as e: # pragma: no cover logger.warning('invalid path for wheel: %s', path) elif path.endswith(self.downloadable_extensions): path = filename = posixpath.basename(path) @@ -489,6 +505,7 @@ class PyPIJSONLocator(Locator): # result['urls'].setdefault(md.version, set()).add(url) # result['digests'][url] = self._get_digest(info) except Exception as e: + self.errors.put(text_type(e)) logger.exception('JSON fetch failed: %s', e) return result @@ -714,6 +731,8 @@ class SimpleScrapingLocator(Locator): self._should_queue(link, url, rel)): logger.debug('Queueing %s from %s', link, url) self._to_fetch.put(link) + except Exception as e: # pragma: no cover + self.errors.put(text_type(e)) finally: # always do this, to avoid hangs :-) self._to_fetch.task_done() diff --git a/pip/_vendor/distlib/manifest.py b/pip/_vendor/distlib/manifest.py index 21cff45e3..9f0336453 100644 --- a/pip/_vendor/distlib/manifest.py +++ b/pip/_vendor/distlib/manifest.py @@ -12,6 +12,7 @@ import fnmatch import logging import os import re +import sys from . import DistlibException from .compat import fsdecode @@ -26,6 +27,12 @@ logger = logging.getLogger(__name__) _COLLAPSE_PATTERN = re.compile('\\\w*\n', re.M) _COMMENTED_LINE = re.compile('#.*?(?=\n)|\n(?=$)', re.M | re.S) +# +# Due to the different results returned by fnmatch.translate, we need +# to do slightly different processing for Python 2.7 and 3.2 ... this needed +# to be brought in for Python 3.6 onwards. +# +_PYTHON_VERSION = sys.version_info[:2] class Manifest(object): """A list of files built by on exploring the filesystem and filtered by @@ -322,24 +329,43 @@ class Manifest(object): else: return pattern + if _PYTHON_VERSION > (3, 2): + # ditch start and end characters + start, _, end = self._glob_to_re('_').partition('_') + if pattern: pattern_re = self._glob_to_re(pattern) + if _PYTHON_VERSION > (3, 2): + assert pattern_re.startswith(start) and pattern_re.endswith(end) else: pattern_re = '' base = re.escape(os.path.join(self.base, '')) if prefix is not None: # ditch end of pattern character - empty_pattern = self._glob_to_re('') - prefix_re = self._glob_to_re(prefix)[:-len(empty_pattern)] + if _PYTHON_VERSION <= (3, 2): + empty_pattern = self._glob_to_re('') + prefix_re = self._glob_to_re(prefix)[:-len(empty_pattern)] + else: + prefix_re = self._glob_to_re(prefix) + assert prefix_re.startswith(start) and prefix_re.endswith(end) + prefix_re = prefix_re[len(start): len(prefix_re) - len(end)] sep = os.sep if os.sep == '\\': sep = r'\\' - pattern_re = '^' + base + sep.join((prefix_re, - '.*' + pattern_re)) - else: # no prefix -- respect anchor flag + if _PYTHON_VERSION <= (3, 2): + pattern_re = '^' + base + sep.join((prefix_re, + '.*' + pattern_re)) + else: + pattern_re = pattern_re[len(start): len(pattern_re) - len(end)] + pattern_re = r'%s%s%s%s.*%s%s' % (start, base, prefix_re, sep, + pattern_re, end) + else: # no prefix -- respect anchor flag if anchor: - pattern_re = '^' + base + pattern_re + if _PYTHON_VERSION <= (3, 2): + pattern_re = '^' + base + pattern_re + else: + pattern_re = r'%s%s%s' % (start, base, pattern_re[len(start):]) return re.compile(pattern_re) diff --git a/pip/_vendor/distlib/metadata.py b/pip/_vendor/distlib/metadata.py index 71525dd9e..75bfd68ec 100644 --- a/pip/_vendor/distlib/metadata.py +++ b/pip/_vendor/distlib/metadata.py @@ -444,16 +444,16 @@ class LegacyMetadata(object): # check that the values are valid if not scheme.is_valid_matcher(v.split(';')[0]): logger.warning( - '%r: %r is not valid (field %r)', + "'%s': '%s' is not valid (field '%s')", project_name, v, name) # FIXME this rejects UNKNOWN, is that right? elif name in _VERSIONS_FIELDS and value is not None: if not scheme.is_valid_constraint_list(value): - logger.warning('%r: %r is not a valid version (field %r)', + logger.warning("'%s': '%s' is not a valid version (field '%s')", project_name, value, name) elif name in _VERSION_FIELDS and value is not None: if not scheme.is_valid_version(value): - logger.warning('%r: %r is not a valid version (field %r)', + logger.warning("'%s': '%s' is not a valid version (field '%s')", project_name, value, name) if name in _UNICODEFIELDS: @@ -531,7 +531,7 @@ class LegacyMetadata(object): for field in fields: value = self.get(field, None) if value is not None and not controller(value): - warnings.append('Wrong value for %r: %s' % (field, value)) + warnings.append("Wrong value for '%s': %s" % (field, value)) return missing, warnings @@ -766,6 +766,8 @@ class Metadata(object): result = d.get(key, value) else: d = d.get('python.exports') + if not d: + d = self._data.get('python.exports') if d: result = d.get(key, value) if result is sentinel: @@ -784,8 +786,8 @@ class Metadata(object): if (scheme or self.scheme) not in exclusions: m = pattern.match(value) if not m: - raise MetadataInvalidError('%r is an invalid value for ' - 'the %r property' % (value, + raise MetadataInvalidError("'%s' is an invalid value for " + "the '%s' property" % (value, key)) def __setattr__(self, key, value): diff --git a/pip/_vendor/distlib/resources.py b/pip/_vendor/distlib/resources.py index 9dd8ca016..f07cde259 100644 --- a/pip/_vendor/distlib/resources.py +++ b/pip/_vendor/distlib/resources.py @@ -289,9 +289,14 @@ _finder_registry = { } try: - import _frozen_importlib - _finder_registry[_frozen_importlib.SourceFileLoader] = ResourceFinder - _finder_registry[_frozen_importlib.FileFinder] = ResourceFinder + # In Python 3.6, _frozen_importlib -> _frozen_importlib_external + try: + import _frozen_importlib_external as _fi + except ImportError: + import _frozen_importlib as _fi + _finder_registry[_fi.SourceFileLoader] = ResourceFinder + _finder_registry[_fi.FileFinder] = ResourceFinder + del _fi except (ImportError, AttributeError): pass diff --git a/pip/_vendor/distlib/scripts.py b/pip/_vendor/distlib/scripts.py index c9996d598..792fc2e1f 100644 --- a/pip/_vendor/distlib/scripts.py +++ b/pip/_vendor/distlib/scripts.py @@ -52,7 +52,7 @@ if __name__ == '__main__': return result try: - sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0]) func = _resolve('%(module)s', '%(func)s') rc = func() # None interpreted as 0 diff --git a/pip/_vendor/distlib/t32.exe b/pip/_vendor/distlib/t32.exe Binary files differindex e0168c22c..836211d84 100644 --- a/pip/_vendor/distlib/t32.exe +++ b/pip/_vendor/distlib/t32.exe diff --git a/pip/_vendor/distlib/t64.exe b/pip/_vendor/distlib/t64.exe Binary files differindex 29a1fd6cc..a401b59d6 100644 --- a/pip/_vendor/distlib/t64.exe +++ b/pip/_vendor/distlib/t64.exe diff --git a/pip/_vendor/distlib/util.py b/pip/_vendor/distlib/util.py index 7e209ec2d..604f20cd3 100644 --- a/pip/_vendor/distlib/util.py +++ b/pip/_vendor/distlib/util.py @@ -15,7 +15,10 @@ import py_compile import re import shutil import socket -import ssl +try: + import ssl +except ImportError: # pragma: no cover + ssl = None import subprocess import sys import tarfile @@ -24,17 +27,16 @@ import textwrap try: import threading -except ImportError: +except ImportError: # pragma: no cover import dummy_threading as threading import time from . import DistlibException from .compat import (string_types, text_type, shutil, raw_input, StringIO, cache_from_source, urlopen, urljoin, httplib, xmlrpclib, - splittype, HTTPHandler, HTTPSHandler as BaseHTTPSHandler, - BaseConfigurator, valid_ident, Container, configparser, - URLError, match_hostname, CertificateError, ZipFile, - fsdecode) + splittype, HTTPHandler, BaseConfigurator, valid_ident, + Container, configparser, URLError, ZipFile, fsdecode, + unquote) logger = logging.getLogger(__name__) @@ -540,7 +542,7 @@ class ExportEntry(object): def value(self): return resolve(self.prefix, self.suffix) - def __repr__(self): + def __repr__(self): # pragma: no cover return '<ExportEntry %s = %s:%s %s>' % (self.name, self.prefix, self.suffix, self.flags) @@ -567,8 +569,8 @@ def get_export_entry(specification): if not m: result = None if '[' in specification or ']' in specification: - raise DistlibException('Invalid specification ' - '%r' % specification) + raise DistlibException("Invalid specification " + "'%s'" % specification) else: d = m.groupdict() name = d['name'] @@ -578,14 +580,14 @@ def get_export_entry(specification): prefix, suffix = path, None else: if colons != 1: - raise DistlibException('Invalid specification ' - '%r' % specification) + raise DistlibException("Invalid specification " + "'%s'" % specification) prefix, suffix = path.split(':') flags = d['flags'] if flags is None: if '[' in specification or ']' in specification: - raise DistlibException('Invalid specification ' - '%r' % specification) + raise DistlibException("Invalid specification " + "'%s'" % specification) flags = [] else: flags = [f.strip() for f in flags.split(',')] @@ -696,6 +698,7 @@ def split_filename(filename, project_name=None): """ result = None pyver = None + filename = unquote(filename).replace(' ', '-') m = PYTHON_VERSION.search(filename) if m: pyver = m.group(1) @@ -804,7 +807,7 @@ class Cache(object): """ # we use 'isdir' instead of 'exists', because we want to # fail if there's a file with that name - if not os.path.isdir(base): + if not os.path.isdir(base): # pragma: no cover os.makedirs(base) if (os.stat(base).st_mode & 0o77) != 0: logger.warning('Directory \'%s\' is not private', base) @@ -940,12 +943,12 @@ class Sequencer(object): try: preds = self._preds[succ] succs = self._succs[pred] - except KeyError: + except KeyError: # pragma: no cover raise ValueError('%r not a successor of anything' % succ) try: preds.remove(pred) succs.remove(succ) - except KeyError: + except KeyError: # pragma: no cover raise ValueError('%r not a successor of %r' % (succ, pred)) def is_step(self, step): @@ -1071,7 +1074,7 @@ def unarchive(archive_filename, dest_dir, format=None, check=True): elif archive_filename.endswith('.tar'): format = 'tar' mode = 'r' - else: + else: # pragma: no cover raise ValueError('Unknown format for %r' % archive_filename) try: if format == 'zip': @@ -1257,99 +1260,102 @@ def _iglob(path_glob): for fn in _iglob(os.path.join(path, radical)): yield fn +if ssl: + from .compat import (HTTPSHandler as BaseHTTPSHandler, match_hostname, + CertificateError) # # HTTPSConnection which verifies certificates/matches domains # -class HTTPSConnection(httplib.HTTPSConnection): - ca_certs = None # set this to the path to the certs file (.pem) - check_domain = True # only used if ca_certs is not None - - # noinspection PyPropertyAccess - def connect(self): - sock = socket.create_connection((self.host, self.port), self.timeout) - if getattr(self, '_tunnel_host', False): - self.sock = sock - self._tunnel() - - if not hasattr(ssl, 'SSLContext'): - # For 2.x - if self.ca_certs: - cert_reqs = ssl.CERT_REQUIRED - else: - cert_reqs = ssl.CERT_NONE - self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, - cert_reqs=cert_reqs, - ssl_version=ssl.PROTOCOL_SSLv23, - ca_certs=self.ca_certs) - else: - context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) - context.options |= ssl.OP_NO_SSLv2 - if self.cert_file: - context.load_cert_chain(self.cert_file, self.key_file) - kwargs = {} + class HTTPSConnection(httplib.HTTPSConnection): + ca_certs = None # set this to the path to the certs file (.pem) + check_domain = True # only used if ca_certs is not None + + # noinspection PyPropertyAccess + def connect(self): + sock = socket.create_connection((self.host, self.port), self.timeout) + if getattr(self, '_tunnel_host', False): + self.sock = sock + self._tunnel() + + if not hasattr(ssl, 'SSLContext'): + # For 2.x + if self.ca_certs: + cert_reqs = ssl.CERT_REQUIRED + else: + cert_reqs = ssl.CERT_NONE + self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, + cert_reqs=cert_reqs, + ssl_version=ssl.PROTOCOL_SSLv23, + ca_certs=self.ca_certs) + else: # pragma: no cover + context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + context.options |= ssl.OP_NO_SSLv2 + if self.cert_file: + context.load_cert_chain(self.cert_file, self.key_file) + kwargs = {} + if self.ca_certs: + context.verify_mode = ssl.CERT_REQUIRED + context.load_verify_locations(cafile=self.ca_certs) + if getattr(ssl, 'HAS_SNI', False): + kwargs['server_hostname'] = self.host + self.sock = context.wrap_socket(sock, **kwargs) + if self.ca_certs and self.check_domain: + try: + match_hostname(self.sock.getpeercert(), self.host) + logger.debug('Host verified: %s', self.host) + except CertificateError: # pragma: no cover + self.sock.shutdown(socket.SHUT_RDWR) + self.sock.close() + raise + + class HTTPSHandler(BaseHTTPSHandler): + def __init__(self, ca_certs, check_domain=True): + BaseHTTPSHandler.__init__(self) + self.ca_certs = ca_certs + self.check_domain = check_domain + + def _conn_maker(self, *args, **kwargs): + """ + This is called to create a connection instance. Normally you'd + pass a connection class to do_open, but it doesn't actually check for + a class, and just expects a callable. As long as we behave just as a + constructor would have, we should be OK. If it ever changes so that + we *must* pass a class, we'll create an UnsafeHTTPSConnection class + which just sets check_domain to False in the class definition, and + choose which one to pass to do_open. + """ + result = HTTPSConnection(*args, **kwargs) if self.ca_certs: - context.verify_mode = ssl.CERT_REQUIRED - context.load_verify_locations(cafile=self.ca_certs) - if getattr(ssl, 'HAS_SNI', False): - kwargs['server_hostname'] = self.host - self.sock = context.wrap_socket(sock, **kwargs) - if self.ca_certs and self.check_domain: - try: - match_hostname(self.sock.getpeercert(), self.host) - logger.debug('Host verified: %s', self.host) - except CertificateError: - self.sock.shutdown(socket.SHUT_RDWR) - self.sock.close() - raise - -class HTTPSHandler(BaseHTTPSHandler): - def __init__(self, ca_certs, check_domain=True): - BaseHTTPSHandler.__init__(self) - self.ca_certs = ca_certs - self.check_domain = check_domain - - def _conn_maker(self, *args, **kwargs): - """ - This is called to create a connection instance. Normally you'd - pass a connection class to do_open, but it doesn't actually check for - a class, and just expects a callable. As long as we behave just as a - constructor would have, we should be OK. If it ever changes so that - we *must* pass a class, we'll create an UnsafeHTTPSConnection class - which just sets check_domain to False in the class definition, and - choose which one to pass to do_open. - """ - result = HTTPSConnection(*args, **kwargs) - if self.ca_certs: - result.ca_certs = self.ca_certs - result.check_domain = self.check_domain - return result - - def https_open(self, req): - try: - return self.do_open(self._conn_maker, req) - except URLError as e: - if 'certificate verify failed' in str(e.reason): - raise CertificateError('Unable to verify server certificate ' - 'for %s' % req.host) - else: - raise + result.ca_certs = self.ca_certs + result.check_domain = self.check_domain + return result -# -# To prevent against mixing HTTP traffic with HTTPS (examples: A Man-In-The- -# Middle proxy using HTTP listens on port 443, or an index mistakenly serves -# HTML containing a http://xyz link when it should be https://xyz), -# you can use the following handler class, which does not allow HTTP traffic. -# -# It works by inheriting from HTTPHandler - so build_opener won't add a -# handler for HTTP itself. -# -class HTTPSOnlyHandler(HTTPSHandler, HTTPHandler): - def http_open(self, req): - raise URLError('Unexpected HTTP request on what should be a secure ' - 'connection: %s' % req) + def https_open(self, req): + try: + return self.do_open(self._conn_maker, req) + except URLError as e: + if 'certificate verify failed' in str(e.reason): + raise CertificateError('Unable to verify server certificate ' + 'for %s' % req.host) + else: + raise + + # + # To prevent against mixing HTTP traffic with HTTPS (examples: A Man-In-The- + # Middle proxy using HTTP listens on port 443, or an index mistakenly serves + # HTML containing a http://xyz link when it should be https://xyz), + # you can use the following handler class, which does not allow HTTP traffic. + # + # It works by inheriting from HTTPHandler - so build_opener won't add a + # handler for HTTP itself. + # + class HTTPSOnlyHandler(HTTPSHandler, HTTPHandler): + def http_open(self, req): + raise URLError('Unexpected HTTP request on what should be a secure ' + 'connection: %s' % req) # # XML-RPC with timeouts @@ -1365,11 +1371,12 @@ if _ver_info == (2, 6): self._setup(self._connection_class(host, port, **kwargs)) - class HTTPS(httplib.HTTPS): - def __init__(self, host='', port=None, **kwargs): - if port == 0: # 0 means use port 0, not the default port - port = None - self._setup(self._connection_class(host, port, **kwargs)) + if ssl: + class HTTPS(httplib.HTTPS): + def __init__(self, host='', port=None, **kwargs): + if port == 0: # 0 means use port 0, not the default port + port = None + self._setup(self._connection_class(host, port, **kwargs)) class Transport(xmlrpclib.Transport): @@ -1388,25 +1395,26 @@ class Transport(xmlrpclib.Transport): result = self._connection[1] return result -class SafeTransport(xmlrpclib.SafeTransport): - def __init__(self, timeout, use_datetime=0): - self.timeout = timeout - xmlrpclib.SafeTransport.__init__(self, use_datetime) - - def make_connection(self, host): - h, eh, kwargs = self.get_host_info(host) - if not kwargs: - kwargs = {} - kwargs['timeout'] = self.timeout - if _ver_info == (2, 6): - result = HTTPS(host, None, **kwargs) - else: - if not self._connection or host != self._connection[0]: - self._extra_headers = eh - self._connection = host, httplib.HTTPSConnection(h, None, - **kwargs) - result = self._connection[1] - return result +if ssl: + class SafeTransport(xmlrpclib.SafeTransport): + def __init__(self, timeout, use_datetime=0): + self.timeout = timeout + xmlrpclib.SafeTransport.__init__(self, use_datetime) + + def make_connection(self, host): + h, eh, kwargs = self.get_host_info(host) + if not kwargs: + kwargs = {} + kwargs['timeout'] = self.timeout + if _ver_info == (2, 6): + result = HTTPS(host, None, **kwargs) + else: + if not self._connection or host != self._connection[0]: + self._extra_headers = eh + self._connection = host, httplib.HTTPSConnection(h, None, + **kwargs) + result = self._connection[1] + return result class ServerProxy(xmlrpclib.ServerProxy): @@ -1595,3 +1603,9 @@ class SubprocessMixin(object): elif self.verbose: sys.stderr.write('done.\n') return p + + +def normalize_name(name): + """Normalize a python package name a la PEP 503""" + # https://www.python.org/dev/peps/pep-0503/#normalized-names + return re.sub('[-_.]+', '-', name).lower() diff --git a/pip/_vendor/distlib/version.py b/pip/_vendor/distlib/version.py index d3dcfa006..48c17c0a6 100644 --- a/pip/_vendor/distlib/version.py +++ b/pip/_vendor/distlib/version.py @@ -137,7 +137,7 @@ class Matcher(object): Check if the provided version matches the constraints. :param version: The version to match against this instance. - :type version: Strring or :class:`Version` instance. + :type version: String or :class:`Version` instance. """ if isinstance(version, string_types): version = self.version_class(version) @@ -265,7 +265,7 @@ class NormalizedVersion(Version): TODO: fill this out Bad: - 1 # mininum two numbers + 1 # minimum two numbers 1.2a # release level must have a release serial 1.2.3b """ @@ -494,7 +494,7 @@ def _suggest_normalized_version(s): rs = re.sub(r"dev$", r"dev0", rs) # if we have something like "b-2" or "a.2" at the end of the - # version, that is pobably beta, alpha, etc + # version, that is probably beta, alpha, etc # let's remove the dash or dot rs = re.sub(r"([abc]|rc)[\-\.](\d+)$", r"\1\2", rs) diff --git a/pip/_vendor/distlib/w32.exe b/pip/_vendor/distlib/w32.exe Binary files differindex f27573a1e..85a90a5f5 100644 --- a/pip/_vendor/distlib/w32.exe +++ b/pip/_vendor/distlib/w32.exe diff --git a/pip/_vendor/distlib/w64.exe b/pip/_vendor/distlib/w64.exe Binary files differindex fd37d9ee4..b3aea316f 100644 --- a/pip/_vendor/distlib/w64.exe +++ b/pip/_vendor/distlib/w64.exe diff --git a/pip/_vendor/distro.py b/pip/_vendor/distro.py index 4fd4be89f..68fef0ac2 100644 --- a/pip/_vendor/distro.py +++ b/pip/_vendor/distro.py @@ -31,11 +31,14 @@ more information. import os import re import sys +import json import shlex +import logging import subprocess -from pip._vendor import six +if not sys.platform.startswith('linux'): + raise ImportError('Unsupported platform: {0}'.format(sys.platform)) _UNIXCONFDIR = '/etc' _OS_RELEASE_BASENAME = 'os-release' @@ -47,8 +50,7 @@ _OS_RELEASE_BASENAME = 'os-release' #: with blanks translated to underscores. #: #: * Value: Normalized value. -NORMALIZED_OS_ID = { -} +NORMALIZED_OS_ID = {} #: Translation table for normalizing the "Distributor ID" attribute returned by #: the lsb_release command, for use by the :func:`distro.id` method. @@ -73,21 +75,22 @@ NORMALIZED_DISTRO_ID = { 'redhat': 'rhel', # RHEL 6.x, 7.x } - # Pattern for content of distro release file (reversed) _DISTRO_RELEASE_CONTENT_REVERSED_PATTERN = re.compile( r'(?:[^)]*\)(.*)\()? *(?:STL )?([\d.+\-a-z]*\d) *(?:esaeler *)?(.+)') # Pattern for base file name of distro release file _DISTRO_RELEASE_BASENAME_PATTERN = re.compile( - r'(\w+)[-_](release|version)') + r'(\w+)[-_](release|version)$') # Base file names to be ignored when searching for distro release file -_DISTRO_RELEASE_IGNORE_BASENAMES = [ +_DISTRO_RELEASE_IGNORE_BASENAMES = ( 'debian_version', - 'system-release', - _OS_RELEASE_BASENAME -] + 'lsb-release', + 'oem-release', + _OS_RELEASE_BASENAME, + 'system-release' +) def linux_distribution(full_distribution_name=True): @@ -115,7 +118,7 @@ def linux_distribution(full_distribution_name=True): method normalizes the distro ID string to a reliable machine-readable value for a number of popular Linux distributions. """ - return _distroi.linux_distribution(full_distribution_name) + return _distro.linux_distribution(full_distribution_name) def id(): @@ -190,7 +193,7 @@ def id(): command, with ID values that differ from what was previously determined from the distro release file name. """ - return _distroi.id() + return _distro.id() def name(pretty=False): @@ -229,7 +232,7 @@ def name(pretty=False): with the value of the pretty version ("<version_id>" and "<codename>" fields) of the distro release file, if available. """ - return _distroi.name(pretty) + return _distro.name(pretty) def version(pretty=False, best=False): @@ -273,7 +276,7 @@ def version(pretty=False, best=False): the lsb_release command, if it follows the format of the distro release files. """ - return _distroi.version(pretty, best) + return _distro.version(pretty, best) def version_parts(best=False): @@ -290,7 +293,7 @@ def version_parts(best=False): For a description of the *best* parameter, see the :func:`distro.version` method. """ - return _distroi.version_parts(best) + return _distro.version_parts(best) def major_version(best=False): @@ -303,7 +306,7 @@ def major_version(best=False): For a description of the *best* parameter, see the :func:`distro.version` method. """ - return _distroi.major_version(best) + return _distro.major_version(best) def minor_version(best=False): @@ -316,7 +319,7 @@ def minor_version(best=False): For a description of the *best* parameter, see the :func:`distro.version` method. """ - return _distroi.minor_version(best) + return _distro.minor_version(best) def build_number(best=False): @@ -329,7 +332,7 @@ def build_number(best=False): For a description of the *best* parameter, see the :func:`distro.version` method. """ - return _distroi.build_number(best) + return _distro.build_number(best) def like(): @@ -346,7 +349,7 @@ def like(): `os-release man page <http://www.freedesktop.org/software/systemd/man/os-release.html>`_. """ - return _distroi.like() + return _distro.like() def codename(): @@ -370,7 +373,7 @@ def codename(): * the value of the "<codename>" field of the distro release file. """ - return _distroi.codename() + return _distro.codename() def info(pretty=False, best=False): @@ -414,7 +417,7 @@ def info(pretty=False, best=False): For a description of the *pretty* and *best* parameters, see the :func:`distro.version` method. """ - return _distroi.info(pretty, best) + return _distro.info(pretty, best) def os_release_info(): @@ -424,7 +427,7 @@ def os_release_info(): See `os-release file`_ for details about these information items. """ - return _distroi.os_release_info() + return _distro.os_release_info() def lsb_release_info(): @@ -435,7 +438,7 @@ def lsb_release_info(): See `lsb_release command output`_ for details about these information items. """ - return _distroi.lsb_release_info() + return _distro.lsb_release_info() def distro_release_info(): @@ -445,7 +448,7 @@ def distro_release_info(): See `distro release file`_ for details about these information items. """ - return _distroi.distro_release_info() + return _distro.distro_release_info() def os_release_attr(attribute): @@ -464,7 +467,7 @@ def os_release_attr(attribute): See `os-release file`_ for details about these information items. """ - return _distroi.os_release_attr(attribute) + return _distro.os_release_attr(attribute) def lsb_release_attr(attribute): @@ -484,7 +487,7 @@ def lsb_release_attr(attribute): See `lsb_release command output`_ for details about these information items. """ - return _distroi.lsb_release_attr(attribute) + return _distro.lsb_release_attr(attribute) def distro_release_attr(attribute): @@ -503,7 +506,7 @@ def distro_release_attr(attribute): See `distro release file`_ for details about these information items. """ - return _distroi.distro_release_attr(attribute) + return _distro.distro_release_attr(attribute) class LinuxDistribution(object): @@ -625,20 +628,22 @@ class LinuxDistribution(object): For details, see :func:`distro.id`. """ + + def normalize(distro_id, table): + distro_id = distro_id.lower().replace(' ', '_') + return table.get(distro_id, distro_id) + distro_id = self.os_release_attr('id') if distro_id: - distro_id = distro_id.lower().replace(' ', '_') - return NORMALIZED_OS_ID.get(distro_id, distro_id) + return normalize(distro_id, NORMALIZED_OS_ID) distro_id = self.lsb_release_attr('distributor_id') if distro_id: - distro_id = distro_id.lower().replace(' ', '_') - return NORMALIZED_LSB_ID.get(distro_id, distro_id) + return normalize(distro_id, NORMALIZED_LSB_ID) distro_id = self.distro_release_attr('id') if distro_id: - distro_id = distro_id.lower().replace(' ', '_') - return NORMALIZED_DISTRO_ID.get(distro_id, distro_id) + return normalize(distro_id, NORMALIZED_DISTRO_ID) return '' @@ -703,12 +708,12 @@ class LinuxDistribution(object): """ version_str = self.version(best=best) if version_str: - g = re.compile(r'(\d+)\.?(\d+)?\.?(\d+)?') - m = g.match(version_str) - if m: - major, minor, build_number = m.groups() - return (major, minor or '', build_number or '') - return ('', '', '') + version_regex = re.compile(r'(\d+)\.?(\d+)?\.?(\d+)?') + matches = version_regex.match(version_str) + if matches: + major, minor, build_number = matches.groups() + return major, minor or '', build_number or '' + return '', '', '' def major_version(self, best=False): """ @@ -836,8 +841,8 @@ class LinuxDistribution(object): A dictionary containing all information items. """ if os.path.isfile(self.os_release_file): - with open(self.os_release_file, 'r') as f: - return self._parse_os_release_content(f) + with open(self.os_release_file) as release_file: + return self._parse_os_release_content(release_file) return {} @staticmethod @@ -865,7 +870,7 @@ class LinuxDistribution(object): # string. This causes a UnicodeDecodeError to be raised when the # parsed content is a unicode object. The following fix resolves that # (... but it should be fixed in shlex...): - if sys.version_info[0] == 2 and isinstance(lexer.wordchars, str): + if sys.version_info[0] == 2 and isinstance(lexer.wordchars, bytes): lexer.wordchars = lexer.wordchars.decode('iso-8859-1') tokens = list(lexer) @@ -878,7 +883,7 @@ class LinuxDistribution(object): # * commands or their arguments (not allowed in os-release) if '=' in token: k, v = token.split('=', 1) - if isinstance(v, six.binary_type): + if isinstance(v, bytes): v = v.decode('utf-8') props[k.lower()] = v if k == 'VERSION': @@ -908,23 +913,26 @@ class LinuxDistribution(object): A dictionary containing all information items. """ cmd = 'lsb_release -a' - p = subprocess.Popen( + process = subprocess.Popen( cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE) - out, err = p.communicate() - rc = p.returncode - if rc == 0: - content = out.decode('ascii').splitlines() + stdout, stderr = process.communicate() + stdout, stderr = stdout.decode('ascii'), stderr.decode('ascii') + code = process.returncode + if code == 0: + content = stdout.splitlines() return self._parse_lsb_release_content(content) - elif rc == 127: # Command not found + elif code == 127: # Command not found return {} else: - if sys.version_info[0:2] >= (2, 7): - raise subprocess.CalledProcessError(rc, cmd, err) - else: - raise subprocess.CalledProcessError(rc, cmd) + if sys.version_info[:2] >= (3, 5): + raise subprocess.CalledProcessError(code, cmd, stdout, stderr) + elif sys.version_info[:2] >= (2, 7): + raise subprocess.CalledProcessError(code, cmd, stdout) + elif sys.version_info[:2] == (2, 6): + raise subprocess.CalledProcessError(code, cmd) @staticmethod def _parse_lsb_release_content(lines): @@ -942,7 +950,7 @@ class LinuxDistribution(object): """ props = {} for line in lines: - if isinstance(line, six.binary_type): + if isinstance(line, bytes): line = line.decode('utf-8') kv = line.strip('\n').split(':', 1) if len(kv) != 2: @@ -1005,7 +1013,7 @@ class LinuxDistribution(object): A dictionary containing all information items. """ if os.path.isfile(filepath): - with open(filepath, 'r') as fp: + with open(filepath) as fp: # Only parse the first line. For instance, on SLES there # are multiple lines. We don't want them... return self._parse_distro_release_content(fp.readline()) @@ -1023,18 +1031,52 @@ class LinuxDistribution(object): Returns: A dictionary containing all information items. """ - if isinstance(line, six.binary_type): + if isinstance(line, bytes): line = line.decode('utf-8') - m = _DISTRO_RELEASE_CONTENT_REVERSED_PATTERN.match( + matches = _DISTRO_RELEASE_CONTENT_REVERSED_PATTERN.match( line.strip()[::-1]) distro_info = {} - if m: - distro_info['name'] = m.group(3)[::-1] # regexp ensures non-None - if m.group(2): - distro_info['version_id'] = m.group(2)[::-1] - if m.group(1): - distro_info['codename'] = m.group(1)[::-1] + if matches: + # regexp ensures non-None + distro_info['name'] = matches.group(3)[::-1] + if matches.group(2): + distro_info['version_id'] = matches.group(2)[::-1] + if matches.group(1): + distro_info['codename'] = matches.group(1)[::-1] + elif line: + distro_info['name'] = line.strip() return distro_info -_distroi = LinuxDistribution() +_distro = LinuxDistribution() + + +def main(): + import argparse + + logger = logging.getLogger(__name__) + logger.setLevel(logging.DEBUG) + logger.addHandler(logging.StreamHandler(sys.stdout)) + + parser = argparse.ArgumentParser(description="Linux distro info tool") + parser.add_argument( + '--json', + '-j', + help="Output in machine readable format", + action="store_true") + args = parser.parse_args() + + if args.json: + logger.info(json.dumps(info())) + else: + logger.info('Name: {0}'.format(name(pretty=True))) + distribution_version = version(pretty=True) + if distribution_version: + logger.info('Version: {0}'.format(distribution_version)) + distribution_codename = codename() + if distribution_codename: + logger.info('Codename: {0}'.format(distribution_codename)) + + +if __name__ == '__main__': + main() diff --git a/pip/_vendor/html5lib/__init__.py b/pip/_vendor/html5lib/__init__.py index 9484fdc9b..7427eb126 100644 --- a/pip/_vendor/html5lib/__init__.py +++ b/pip/_vendor/html5lib/__init__.py @@ -22,4 +22,4 @@ __all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder", "getTreeWalker", "serialize"] # this has to be at the top level, see how setup.py parses this -__version__ = "1.0b8" +__version__ = "1.0b10" diff --git a/pip/_vendor/html5lib/ihatexml.py b/pip/_vendor/html5lib/_ihatexml.py index 0fc79308e..d6d1d6fb7 100644 --- a/pip/_vendor/html5lib/ihatexml.py +++ b/pip/_vendor/html5lib/_ihatexml.py @@ -175,9 +175,9 @@ def escapeRegexp(string): return string # output from the above -nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') +nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa -nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') +nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa # Simpler things nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\-\'()+,./:=?;!*#@$_%]") @@ -186,7 +186,7 @@ nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\-\'()+,./:=?;!*#@$_%]") class InfosetFilter(object): replacementRegexp = re.compile(r"U[\dA-F]{5,5}") - def __init__(self, replaceChars=None, + def __init__(self, dropXmlnsLocalName=False, dropXmlnsAttrNs=False, preventDoubleDashComments=False, @@ -217,7 +217,7 @@ class InfosetFilter(object): else: return self.toXmlName(name) - def coerceElement(self, name, namespace=None): + def coerceElement(self, name): return self.toXmlName(name) def coerceComment(self, data): @@ -225,11 +225,14 @@ class InfosetFilter(object): while "--" in data: warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning) data = data.replace("--", "- -") + if data.endswith("-"): + warnings.warn("Comments cannot end in a dash", DataLossWarning) + data += " " return data def coerceCharacters(self, data): if self.replaceFormFeedCharacters: - for i in range(data.count("\x0C")): + for _ in range(data.count("\x0C")): warnings.warn("Text cannot contain U+000C", DataLossWarning) data = data.replace("\x0C", " ") # Other non-xml characters diff --git a/pip/_vendor/html5lib/inputstream.py b/pip/_vendor/html5lib/_inputstream.py index ac0c5e53a..7c5639ff8 100644 --- a/pip/_vendor/html5lib/inputstream.py +++ b/pip/_vendor/html5lib/_inputstream.py @@ -1,13 +1,16 @@ from __future__ import absolute_import, division, unicode_literals -from pip._vendor.six import text_type -from pip._vendor.six.moves import http_client + +from pip._vendor.six import text_type, binary_type +from pip._vendor.six.moves import http_client, urllib import codecs import re +from pip._vendor import webencodings + from .constants import EOF, spaceCharacters, asciiLetters, asciiUppercase -from .constants import encodings, ReparseException -from . import utils +from .constants import ReparseException +from . import _utils from io import StringIO @@ -16,12 +19,6 @@ try: except ImportError: BytesIO = StringIO -try: - from io import BufferedIOBase -except ImportError: - class BufferedIOBase(object): - pass - # Non-unicode versions of constants for use in the pre-parser spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters]) asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters]) @@ -29,15 +26,17 @@ asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase spacesAngleBrackets = spaceCharactersBytes | frozenset([b">", b"<"]) -invalid_unicode_no_surrogate = "[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]" +invalid_unicode_no_surrogate = "[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]" # noqa -if utils.supports_lone_surrogates: +if _utils.supports_lone_surrogates: # Use one extra step of indirection and create surrogates with - # unichr. Not using this indirection would introduce an illegal + # eval. Not using this indirection would introduce an illegal # unicode literal on platforms not supporting such lone # surrogates. - invalid_unicode_re = re.compile(invalid_unicode_no_surrogate + - eval('"\\uD800-\\uDFFF"')) + assert invalid_unicode_no_surrogate[-1] == "]" and invalid_unicode_no_surrogate.count("]") == 1 + invalid_unicode_re = re.compile(invalid_unicode_no_surrogate[:-1] + + eval('"\\uD800-\\uDFFF"') + # pylint:disable=eval-used + "]") else: invalid_unicode_re = re.compile(invalid_unicode_no_surrogate) @@ -129,10 +128,13 @@ class BufferedStream(object): return b"".join(rv) -def HTMLInputStream(source, encoding=None, parseMeta=True, chardet=True): - if isinstance(source, http_client.HTTPResponse): - # Work around Python bug #20007: read(0) closes the connection. - # http://bugs.python.org/issue20007 +def HTMLInputStream(source, **kwargs): + # Work around Python bug #20007: read(0) closes the connection. + # http://bugs.python.org/issue20007 + if (isinstance(source, http_client.HTTPResponse) or + # Also check for addinfourl wrapping HTTPResponse + (isinstance(source, urllib.response.addbase) and + isinstance(source.fp, http_client.HTTPResponse))): isUnicode = False elif hasattr(source, "read"): isUnicode = isinstance(source.read(0), text_type) @@ -140,12 +142,13 @@ def HTMLInputStream(source, encoding=None, parseMeta=True, chardet=True): isUnicode = isinstance(source, text_type) if isUnicode: - if encoding is not None: - raise TypeError("Cannot explicitly set an encoding with a unicode string") + encodings = [x for x in kwargs if x.endswith("_encoding")] + if encodings: + raise TypeError("Cannot set an encoding with a unicode input, set %r" % encodings) - return HTMLUnicodeInputStream(source) + return HTMLUnicodeInputStream(source, **kwargs) else: - return HTMLBinaryInputStream(source, encoding, parseMeta, chardet) + return HTMLBinaryInputStream(source, **kwargs) class HTMLUnicodeInputStream(object): @@ -171,27 +174,21 @@ class HTMLUnicodeInputStream(object): regardless of any BOM or later declaration (such as in a meta element) - parseMeta - Look for a <meta> element containing encoding information - """ - if not utils.supports_lone_surrogates: + if not _utils.supports_lone_surrogates: # Such platforms will have already checked for such # surrogate errors, so no need to do this checking. self.reportCharacterErrors = None - self.replaceCharactersRegexp = None elif len("\U0010FFFF") == 1: self.reportCharacterErrors = self.characterErrorsUCS4 - self.replaceCharactersRegexp = re.compile(eval('"[\\uD800-\\uDFFF]"')) else: self.reportCharacterErrors = self.characterErrorsUCS2 - self.replaceCharactersRegexp = re.compile( - eval('"([\\uD800-\\uDBFF](?![\\uDC00-\\uDFFF])|(?<![\\uD800-\\uDBFF])[\\uDC00-\\uDFFF])"')) # List of where new lines occur self.newLines = [0] - self.charEncoding = ("utf-8", "certain") + self.charEncoding = (lookupEncoding("utf-8"), "certain") self.dataStream = self.openStream(source) self.reset() @@ -284,10 +281,7 @@ class HTMLUnicodeInputStream(object): if self.reportCharacterErrors: self.reportCharacterErrors(data) - # Replace invalid characters - # Note U+0000 is dealt with in the tokenizer - data = self.replaceCharactersRegexp.sub("\ufffd", data) - + # Replace invalid characters data = data.replace("\r\n", "\n") data = data.replace("\r", "\n") @@ -297,7 +291,7 @@ class HTMLUnicodeInputStream(object): return True def characterErrorsUCS4(self, data): - for i in range(len(invalid_unicode_re.findall(data))): + for _ in range(len(invalid_unicode_re.findall(data))): self.errors.append("invalid-codepoint") def characterErrorsUCS2(self, data): @@ -310,9 +304,9 @@ class HTMLUnicodeInputStream(object): codepoint = ord(match.group()) pos = match.start() # Pretty sure there should be endianness issues here - if utils.isSurrogatePair(data[pos:pos + 2]): + if _utils.isSurrogatePair(data[pos:pos + 2]): # We have a surrogate pair! - char_val = utils.surrogatePairToCodepoint(data[pos:pos + 2]) + char_val = _utils.surrogatePairToCodepoint(data[pos:pos + 2]) if char_val in non_bmp_invalid_codepoints: self.errors.append("invalid-codepoint") skip = True @@ -395,7 +389,9 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): """ - def __init__(self, source, encoding=None, parseMeta=True, chardet=True): + def __init__(self, source, override_encoding=None, transport_encoding=None, + same_origin_parent_encoding=None, likely_encoding=None, + default_encoding="windows-1252", useChardet=True): """Initialises the HTMLInputStream. HTMLInputStream(source, [encoding]) -> Normalized stream from source @@ -408,8 +404,6 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): regardless of any BOM or later declaration (such as in a meta element) - parseMeta - Look for a <meta> element containing encoding information - """ # Raw Stream - for unicode objects this will encode to utf-8 and set # self.charEncoding as appropriate @@ -417,27 +411,28 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): HTMLUnicodeInputStream.__init__(self, self.rawStream) - self.charEncoding = (codecName(encoding), "certain") - # Encoding Information # Number of bytes to use when looking for a meta element with # encoding information - self.numBytesMeta = 512 + self.numBytesMeta = 1024 # Number of bytes to use when using detecting encoding using chardet self.numBytesChardet = 100 - # Encoding to use if no other information can be found - self.defaultEncoding = "windows-1252" + # Things from args + self.override_encoding = override_encoding + self.transport_encoding = transport_encoding + self.same_origin_parent_encoding = same_origin_parent_encoding + self.likely_encoding = likely_encoding + self.default_encoding = default_encoding - # Detect encoding iff no explicit "transport level" encoding is supplied - if (self.charEncoding[0] is None): - self.charEncoding = self.detectEncoding(parseMeta, chardet) + # Determine encoding + self.charEncoding = self.determineEncoding(useChardet) + assert self.charEncoding[0] is not None # Call superclass self.reset() def reset(self): - self.dataStream = codecs.getreader(self.charEncoding[0])(self.rawStream, - 'replace') + self.dataStream = self.charEncoding[0].codec_info.streamreader(self.rawStream, 'replace') HTMLUnicodeInputStream.reset(self) def openStream(self, source): @@ -454,29 +449,50 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): try: stream.seek(stream.tell()) - except: + except: # pylint:disable=bare-except stream = BufferedStream(stream) return stream - def detectEncoding(self, parseMeta=True, chardet=True): - # First look for a BOM + def determineEncoding(self, chardet=True): + # BOMs take precedence over everything # This will also read past the BOM if present - encoding = self.detectBOM() - confidence = "certain" - # If there is no BOM need to look for meta elements with encoding - # information - if encoding is None and parseMeta: - encoding = self.detectEncodingMeta() - confidence = "tentative" - # Guess with chardet, if avaliable - if encoding is None and chardet: - confidence = "tentative" + charEncoding = self.detectBOM(), "certain" + if charEncoding[0] is not None: + return charEncoding + + # If we've been overriden, we've been overriden + charEncoding = lookupEncoding(self.override_encoding), "certain" + if charEncoding[0] is not None: + return charEncoding + + # Now check the transport layer + charEncoding = lookupEncoding(self.transport_encoding), "certain" + if charEncoding[0] is not None: + return charEncoding + + # Look for meta elements with encoding information + charEncoding = self.detectEncodingMeta(), "tentative" + if charEncoding[0] is not None: + return charEncoding + + # Parent document encoding + charEncoding = lookupEncoding(self.same_origin_parent_encoding), "tentative" + if charEncoding[0] is not None and not charEncoding[0].name.startswith("utf-16"): + return charEncoding + + # "likely" encoding + charEncoding = lookupEncoding(self.likely_encoding), "tentative" + if charEncoding[0] is not None: + return charEncoding + + # Guess with chardet, if available + if chardet: try: - try: - from charade.universaldetector import UniversalDetector - except ImportError: - from chardet.universaldetector import UniversalDetector + from chardet.universaldetector import UniversalDetector + except ImportError: + pass + else: buffers = [] detector = UniversalDetector() while not detector.done: @@ -487,36 +503,33 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): buffers.append(buffer) detector.feed(buffer) detector.close() - encoding = detector.result['encoding'] + encoding = lookupEncoding(detector.result['encoding']) self.rawStream.seek(0) - except ImportError: - pass - # If all else fails use the default encoding - if encoding is None: - confidence = "tentative" - encoding = self.defaultEncoding + if encoding is not None: + return encoding, "tentative" - # Substitute for equivalent encodings: - encodingSub = {"iso-8859-1": "windows-1252"} + # Try the default encoding + charEncoding = lookupEncoding(self.default_encoding), "tentative" + if charEncoding[0] is not None: + return charEncoding - if encoding.lower() in encodingSub: - encoding = encodingSub[encoding.lower()] - - return encoding, confidence + # Fallback to html5lib's default if even that hasn't worked + return lookupEncoding("windows-1252"), "tentative" def changeEncoding(self, newEncoding): assert self.charEncoding[1] != "certain" - newEncoding = codecName(newEncoding) - if newEncoding in ("utf-16", "utf-16-be", "utf-16-le"): - newEncoding = "utf-8" + newEncoding = lookupEncoding(newEncoding) if newEncoding is None: return + if newEncoding.name in ("utf-16be", "utf-16le"): + newEncoding = lookupEncoding("utf-8") + assert newEncoding is not None elif newEncoding == self.charEncoding[0]: self.charEncoding = (self.charEncoding[0], "certain") else: self.rawStream.seek(0) - self.reset() self.charEncoding = (newEncoding, "certain") + self.reset() raise ReparseException("Encoding changed from %s to %s" % (self.charEncoding[0], newEncoding)) def detectBOM(self): @@ -525,8 +538,8 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): encoding otherwise return None""" bomDict = { codecs.BOM_UTF8: 'utf-8', - codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be', - codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be' + codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be', + codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be' } # Go to beginning of file and read in 4 bytes @@ -546,9 +559,12 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): # Set the read position past the BOM if one was found, otherwise # set it to the start of the stream - self.rawStream.seek(encoding and seek or 0) - - return encoding + if encoding: + self.rawStream.seek(seek) + return lookupEncoding(encoding) + else: + self.rawStream.seek(0) + return None def detectEncodingMeta(self): """Report the encoding declared by the meta element @@ -559,8 +575,8 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream): self.rawStream.seek(0) encoding = parser.getEncoding() - if encoding in ("utf-16", "utf-16-be", "utf-16-le"): - encoding = "utf-8" + if encoding is not None and encoding.name in ("utf-16be", "utf-16le"): + encoding = lookupEncoding("utf-8") return encoding @@ -574,6 +590,7 @@ class EncodingBytes(bytes): return bytes.__new__(self, value.lower()) def __init__(self, value): + # pylint:disable=unused-argument self._position = -1 def __iter__(self): @@ -684,7 +701,7 @@ class EncodingParser(object): (b"<!", self.handleOther), (b"<?", self.handleOther), (b"<", self.handlePossibleStartTag)) - for byte in self.data: + for _ in self.data: keepParsing = True for key, method in methodDispatch: if self.data.matchBytes(key): @@ -723,7 +740,7 @@ class EncodingParser(object): return False elif attr[0] == b"charset": tentativeEncoding = attr[1] - codec = codecName(tentativeEncoding) + codec = lookupEncoding(tentativeEncoding) if codec is not None: self.encoding = codec return False @@ -731,7 +748,7 @@ class EncodingParser(object): contentParser = ContentAttrParser(EncodingBytes(attr[1])) tentativeEncoding = contentParser.parse() if tentativeEncoding is not None: - codec = codecName(tentativeEncoding) + codec = lookupEncoding(tentativeEncoding) if codec is not None: if hasPragma: self.encoding = codec @@ -888,16 +905,19 @@ class ContentAttrParser(object): return None -def codecName(encoding): +def lookupEncoding(encoding): """Return the python codec name corresponding to an encoding or None if the string doesn't correspond to a valid encoding.""" - if isinstance(encoding, bytes): + if isinstance(encoding, binary_type): try: encoding = encoding.decode("ascii") except UnicodeDecodeError: return None - if encoding: - canonicalName = ascii_punctuation_re.sub("", encoding).lower() - return encodings.get(canonicalName, None) + + if encoding is not None: + try: + return webencodings.lookup(encoding) + except AttributeError: + return None else: return None diff --git a/pip/_vendor/html5lib/tokenizer.py b/pip/_vendor/html5lib/_tokenizer.py index 797745787..178f6e7fa 100644 --- a/pip/_vendor/html5lib/tokenizer.py +++ b/pip/_vendor/html5lib/_tokenizer.py @@ -1,9 +1,6 @@ from __future__ import absolute_import, division, unicode_literals -try: - chr = unichr # flake8: noqa -except NameError: - pass +from pip._vendor.six import unichr as chr from collections import deque @@ -14,9 +11,9 @@ from .constants import digits, hexDigits, EOF from .constants import tokenTypes, tagTokenTypes from .constants import replacementCharacters -from .inputstream import HTMLInputStream +from ._inputstream import HTMLInputStream -from .trie import Trie +from ._trie import Trie entitiesTrie = Trie(entities) @@ -34,16 +31,11 @@ class HTMLTokenizer(object): Points to HTMLInputStream object. """ - def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, - lowercaseElementName=True, lowercaseAttrName=True, parser=None): + def __init__(self, stream, parser=None, **kwargs): - self.stream = HTMLInputStream(stream, encoding, parseMeta, useChardet) + self.stream = HTMLInputStream(stream, **kwargs) self.parser = parser - # Perform case conversions? - self.lowercaseElementName = lowercaseElementName - self.lowercaseAttrName = lowercaseAttrName - # Setup the initial tokenizer state self.escapeFlag = False self.lastFourChars = [] @@ -147,8 +139,8 @@ class HTMLTokenizer(object): output = "&" charStack = [self.stream.char()] - if (charStack[0] in spaceCharacters or charStack[0] in (EOF, "<", "&") - or (allowedChar is not None and allowedChar == charStack[0])): + if (charStack[0] in spaceCharacters or charStack[0] in (EOF, "<", "&") or + (allowedChar is not None and allowedChar == charStack[0])): self.stream.unget(charStack[0]) elif charStack[0] == "#": @@ -235,8 +227,7 @@ class HTMLTokenizer(object): token = self.currentToken # Add token to the queue to be yielded if (token["type"] in tagTokenTypes): - if self.lowercaseElementName: - token["name"] = token["name"].translate(asciiUpper2Lower) + token["name"] = token["name"].translate(asciiUpper2Lower) if token["type"] == tokenTypes["EndTag"]: if token["data"]: self.tokenQueue.append({"type": tokenTypes["ParseError"], @@ -921,10 +912,9 @@ class HTMLTokenizer(object): # Attributes are not dropped at this stage. That happens when the # start tag token is emitted so values can still be safely appended # to attributes, but we do want to report the parse error in time. - if self.lowercaseAttrName: - self.currentToken["data"][-1][0] = ( - self.currentToken["data"][-1][0].translate(asciiUpper2Lower)) - for name, value in self.currentToken["data"][:-1]: + self.currentToken["data"][-1][0] = ( + self.currentToken["data"][-1][0].translate(asciiUpper2Lower)) + for name, _ in self.currentToken["data"][:-1]: if self.currentToken["data"][-1][0] == name: self.tokenQueue.append({"type": tokenTypes["ParseError"], "data": "duplicate-attribute"}) @@ -1716,11 +1706,11 @@ class HTMLTokenizer(object): else: data.append(char) - data = "".join(data) + data = "".join(data) # pylint:disable=redefined-variable-type # Deal with null here rather than in the parser nullCount = data.count("\u0000") if nullCount > 0: - for i in range(nullCount): + for _ in range(nullCount): self.tokenQueue.append({"type": tokenTypes["ParseError"], "data": "invalid-codepoint"}) data = data.replace("\u0000", "\uFFFD") diff --git a/pip/_vendor/html5lib/trie/__init__.py b/pip/_vendor/html5lib/_trie/__init__.py index a8cca8a9a..a5ba4bf12 100644 --- a/pip/_vendor/html5lib/trie/__init__.py +++ b/pip/_vendor/html5lib/_trie/__init__.py @@ -4,9 +4,11 @@ from .py import Trie as PyTrie Trie = PyTrie +# pylint:disable=wrong-import-position try: from .datrie import Trie as DATrie except ImportError: pass else: Trie = DATrie +# pylint:enable=wrong-import-position diff --git a/pip/_vendor/html5lib/trie/_base.py b/pip/_vendor/html5lib/_trie/_base.py index 724486b16..25eece46e 100644 --- a/pip/_vendor/html5lib/trie/_base.py +++ b/pip/_vendor/html5lib/_trie/_base.py @@ -7,7 +7,8 @@ class Trie(Mapping): """Abstract base class for tries""" def keys(self, prefix=None): - keys = super().keys() + # pylint:disable=arguments-differ + keys = super(Trie, self).keys() if prefix is None: return set(keys) diff --git a/pip/_vendor/html5lib/trie/datrie.py b/pip/_vendor/html5lib/_trie/datrie.py index e2e5f8662..e2e5f8662 100644 --- a/pip/_vendor/html5lib/trie/datrie.py +++ b/pip/_vendor/html5lib/_trie/datrie.py diff --git a/pip/_vendor/html5lib/trie/py.py b/pip/_vendor/html5lib/_trie/py.py index c178b219d..c178b219d 100644 --- a/pip/_vendor/html5lib/trie/py.py +++ b/pip/_vendor/html5lib/_trie/py.py diff --git a/pip/_vendor/html5lib/utils.py b/pip/_vendor/html5lib/_utils.py index 85f1459d0..55d674753 100644 --- a/pip/_vendor/html5lib/utils.py +++ b/pip/_vendor/html5lib/_utils.py @@ -1,5 +1,6 @@ from __future__ import absolute_import, division, unicode_literals +import sys from types import ModuleType from pip._vendor.six import text_type @@ -12,9 +13,11 @@ except ImportError: __all__ = ["default_etree", "MethodDispatcher", "isSurrogatePair", "surrogatePairToCodepoint", "moduleFactoryFactory", - "supports_lone_surrogates"] + "supports_lone_surrogates", "PY27"] +PY27 = sys.version_info[0] == 2 and sys.version_info[1] >= 7 + # Platforms not supporting lone surrogates (\uD800-\uDFFF) should be # caught by the below test. In general this would be any platform # using UTF-16 as its encoding of unicode strings, such as @@ -22,12 +25,12 @@ __all__ = ["default_etree", "MethodDispatcher", "isSurrogatePair", # surrogates, and there is no mechanism to further escape such # escapes. try: - _x = eval('"\\uD800"') + _x = eval('"\\uD800"') # pylint:disable=eval-used if not isinstance(_x, text_type): # We need this with u"" because of http://bugs.jython.org/issue2039 - _x = eval('u"\\uD800"') + _x = eval('u"\\uD800"') # pylint:disable=eval-used assert isinstance(_x, text_type) -except: +except: # pylint:disable=bare-except supports_lone_surrogates = False else: supports_lone_surrogates = True @@ -52,19 +55,20 @@ class MethodDispatcher(dict): # anything here. _dictEntries = [] for name, value in items: - if type(name) in (list, tuple, frozenset, set): + if isinstance(name, (list, tuple, frozenset, set)): for item in name: _dictEntries.append((item, value)) else: _dictEntries.append((name, value)) dict.__init__(self, _dictEntries) + assert len(self) == len(_dictEntries) self.default = None def __getitem__(self, key): return dict.get(self, key, self.default) -# Some utility functions to dal with weirdness around UCS2 vs UCS4 +# Some utility functions to deal with weirdness around UCS2 vs UCS4 # python builds def isSurrogatePair(data): @@ -91,13 +95,33 @@ def moduleFactoryFactory(factory): else: name = b"_%s_factory" % baseModule.__name__ - if name in moduleCache: - return moduleCache[name] - else: + kwargs_tuple = tuple(kwargs.items()) + + try: + return moduleCache[name][args][kwargs_tuple] + except KeyError: mod = ModuleType(name) objs = factory(baseModule, *args, **kwargs) mod.__dict__.update(objs) - moduleCache[name] = mod + if "name" not in moduleCache: + moduleCache[name] = {} + if "args" not in moduleCache[name]: + moduleCache[name][args] = {} + if "kwargs" not in moduleCache[name][args]: + moduleCache[name][args][kwargs_tuple] = {} + moduleCache[name][args][kwargs_tuple] = mod return mod return moduleFactory + + +def memoize(func): + cache = {} + + def wrapped(*args, **kwargs): + key = (tuple(args), tuple(kwargs.items())) + if key not in cache: + cache[key] = func(*args, **kwargs) + return cache[key] + + return wrapped diff --git a/pip/_vendor/html5lib/constants.py b/pip/_vendor/html5lib/constants.py index d938e0ae6..9e7541d38 100644 --- a/pip/_vendor/html5lib/constants.py +++ b/pip/_vendor/html5lib/constants.py @@ -283,6 +283,12 @@ E = { "Element %(name)s not allowed in a non-html context", "unexpected-end-tag-before-html": "Unexpected end tag (%(name)s) before html.", + "unexpected-inhead-noscript-tag": + "Element %(name)s not allowed in a inhead-noscript context", + "eof-in-head-noscript": + "Unexpected end of file. Expected inhead-noscript content", + "char-in-head-noscript": + "Unexpected non-space character. Expected inhead-noscript content", "XXX-undefined-error": "Undefined error (this sucks and should be fixed)", } @@ -431,6 +437,73 @@ mathmlTextIntegrationPointElements = frozenset([ (namespaces["mathml"], "mtext") ]) +adjustSVGAttributes = { + "attributename": "attributeName", + "attributetype": "attributeType", + "basefrequency": "baseFrequency", + "baseprofile": "baseProfile", + "calcmode": "calcMode", + "clippathunits": "clipPathUnits", + "contentscripttype": "contentScriptType", + "contentstyletype": "contentStyleType", + "diffuseconstant": "diffuseConstant", + "edgemode": "edgeMode", + "externalresourcesrequired": "externalResourcesRequired", + "filterres": "filterRes", + "filterunits": "filterUnits", + "glyphref": "glyphRef", + "gradienttransform": "gradientTransform", + "gradientunits": "gradientUnits", + "kernelmatrix": "kernelMatrix", + "kernelunitlength": "kernelUnitLength", + "keypoints": "keyPoints", + "keysplines": "keySplines", + "keytimes": "keyTimes", + "lengthadjust": "lengthAdjust", + "limitingconeangle": "limitingConeAngle", + "markerheight": "markerHeight", + "markerunits": "markerUnits", + "markerwidth": "markerWidth", + "maskcontentunits": "maskContentUnits", + "maskunits": "maskUnits", + "numoctaves": "numOctaves", + "pathlength": "pathLength", + "patterncontentunits": "patternContentUnits", + "patterntransform": "patternTransform", + "patternunits": "patternUnits", + "pointsatx": "pointsAtX", + "pointsaty": "pointsAtY", + "pointsatz": "pointsAtZ", + "preservealpha": "preserveAlpha", + "preserveaspectratio": "preserveAspectRatio", + "primitiveunits": "primitiveUnits", + "refx": "refX", + "refy": "refY", + "repeatcount": "repeatCount", + "repeatdur": "repeatDur", + "requiredextensions": "requiredExtensions", + "requiredfeatures": "requiredFeatures", + "specularconstant": "specularConstant", + "specularexponent": "specularExponent", + "spreadmethod": "spreadMethod", + "startoffset": "startOffset", + "stddeviation": "stdDeviation", + "stitchtiles": "stitchTiles", + "surfacescale": "surfaceScale", + "systemlanguage": "systemLanguage", + "tablevalues": "tableValues", + "targetx": "targetX", + "targety": "targetY", + "textlength": "textLength", + "viewbox": "viewBox", + "viewtarget": "viewTarget", + "xchannelselector": "xChannelSelector", + "ychannelselector": "yChannelSelector", + "zoomandpan": "zoomAndPan" +} + +adjustMathMLAttributes = {"definitionurl": "definitionURL"} + adjustForeignAttributes = { "xlink:actuate": ("xlink", "actuate", namespaces["xlink"]), "xlink:arcrole": ("xlink", "arcrole", namespaces["xlink"]), @@ -2813,7 +2886,6 @@ replacementCharacters = { 0x0d: "\u000D", 0x80: "\u20AC", 0x81: "\u0081", - 0x81: "\u0081", 0x82: "\u201A", 0x83: "\u0192", 0x84: "\u201E", @@ -2846,235 +2918,6 @@ replacementCharacters = { 0x9F: "\u0178", } -encodings = { - '437': 'cp437', - '850': 'cp850', - '852': 'cp852', - '855': 'cp855', - '857': 'cp857', - '860': 'cp860', - '861': 'cp861', - '862': 'cp862', - '863': 'cp863', - '865': 'cp865', - '866': 'cp866', - '869': 'cp869', - 'ansix341968': 'ascii', - 'ansix341986': 'ascii', - 'arabic': 'iso8859-6', - 'ascii': 'ascii', - 'asmo708': 'iso8859-6', - 'big5': 'big5', - 'big5hkscs': 'big5hkscs', - 'chinese': 'gbk', - 'cp037': 'cp037', - 'cp1026': 'cp1026', - 'cp154': 'ptcp154', - 'cp367': 'ascii', - 'cp424': 'cp424', - 'cp437': 'cp437', - 'cp500': 'cp500', - 'cp775': 'cp775', - 'cp819': 'windows-1252', - 'cp850': 'cp850', - 'cp852': 'cp852', - 'cp855': 'cp855', - 'cp857': 'cp857', - 'cp860': 'cp860', - 'cp861': 'cp861', - 'cp862': 'cp862', - 'cp863': 'cp863', - 'cp864': 'cp864', - 'cp865': 'cp865', - 'cp866': 'cp866', - 'cp869': 'cp869', - 'cp936': 'gbk', - 'cpgr': 'cp869', - 'cpis': 'cp861', - 'csascii': 'ascii', - 'csbig5': 'big5', - 'cseuckr': 'cp949', - 'cseucpkdfmtjapanese': 'euc_jp', - 'csgb2312': 'gbk', - 'cshproman8': 'hp-roman8', - 'csibm037': 'cp037', - 'csibm1026': 'cp1026', - 'csibm424': 'cp424', - 'csibm500': 'cp500', - 'csibm855': 'cp855', - 'csibm857': 'cp857', - 'csibm860': 'cp860', - 'csibm861': 'cp861', - 'csibm863': 'cp863', - 'csibm864': 'cp864', - 'csibm865': 'cp865', - 'csibm866': 'cp866', - 'csibm869': 'cp869', - 'csiso2022jp': 'iso2022_jp', - 'csiso2022jp2': 'iso2022_jp_2', - 'csiso2022kr': 'iso2022_kr', - 'csiso58gb231280': 'gbk', - 'csisolatin1': 'windows-1252', - 'csisolatin2': 'iso8859-2', - 'csisolatin3': 'iso8859-3', - 'csisolatin4': 'iso8859-4', - 'csisolatin5': 'windows-1254', - 'csisolatin6': 'iso8859-10', - 'csisolatinarabic': 'iso8859-6', - 'csisolatincyrillic': 'iso8859-5', - 'csisolatingreek': 'iso8859-7', - 'csisolatinhebrew': 'iso8859-8', - 'cskoi8r': 'koi8-r', - 'csksc56011987': 'cp949', - 'cspc775baltic': 'cp775', - 'cspc850multilingual': 'cp850', - 'cspc862latinhebrew': 'cp862', - 'cspc8codepage437': 'cp437', - 'cspcp852': 'cp852', - 'csptcp154': 'ptcp154', - 'csshiftjis': 'shift_jis', - 'csunicode11utf7': 'utf-7', - 'cyrillic': 'iso8859-5', - 'cyrillicasian': 'ptcp154', - 'ebcdiccpbe': 'cp500', - 'ebcdiccpca': 'cp037', - 'ebcdiccpch': 'cp500', - 'ebcdiccphe': 'cp424', - 'ebcdiccpnl': 'cp037', - 'ebcdiccpus': 'cp037', - 'ebcdiccpwt': 'cp037', - 'ecma114': 'iso8859-6', - 'ecma118': 'iso8859-7', - 'elot928': 'iso8859-7', - 'eucjp': 'euc_jp', - 'euckr': 'cp949', - 'extendedunixcodepackedformatforjapanese': 'euc_jp', - 'gb18030': 'gb18030', - 'gb2312': 'gbk', - 'gb231280': 'gbk', - 'gbk': 'gbk', - 'greek': 'iso8859-7', - 'greek8': 'iso8859-7', - 'hebrew': 'iso8859-8', - 'hproman8': 'hp-roman8', - 'hzgb2312': 'hz', - 'ibm037': 'cp037', - 'ibm1026': 'cp1026', - 'ibm367': 'ascii', - 'ibm424': 'cp424', - 'ibm437': 'cp437', - 'ibm500': 'cp500', - 'ibm775': 'cp775', - 'ibm819': 'windows-1252', - 'ibm850': 'cp850', - 'ibm852': 'cp852', - 'ibm855': 'cp855', - 'ibm857': 'cp857', - 'ibm860': 'cp860', - 'ibm861': 'cp861', - 'ibm862': 'cp862', - 'ibm863': 'cp863', - 'ibm864': 'cp864', - 'ibm865': 'cp865', - 'ibm866': 'cp866', - 'ibm869': 'cp869', - 'iso2022jp': 'iso2022_jp', - 'iso2022jp2': 'iso2022_jp_2', - 'iso2022kr': 'iso2022_kr', - 'iso646irv1991': 'ascii', - 'iso646us': 'ascii', - 'iso88591': 'windows-1252', - 'iso885910': 'iso8859-10', - 'iso8859101992': 'iso8859-10', - 'iso885911987': 'windows-1252', - 'iso885913': 'iso8859-13', - 'iso885914': 'iso8859-14', - 'iso8859141998': 'iso8859-14', - 'iso885915': 'iso8859-15', - 'iso885916': 'iso8859-16', - 'iso8859162001': 'iso8859-16', - 'iso88592': 'iso8859-2', - 'iso885921987': 'iso8859-2', - 'iso88593': 'iso8859-3', - 'iso885931988': 'iso8859-3', - 'iso88594': 'iso8859-4', - 'iso885941988': 'iso8859-4', - 'iso88595': 'iso8859-5', - 'iso885951988': 'iso8859-5', - 'iso88596': 'iso8859-6', - 'iso885961987': 'iso8859-6', - 'iso88597': 'iso8859-7', - 'iso885971987': 'iso8859-7', - 'iso88598': 'iso8859-8', - 'iso885981988': 'iso8859-8', - 'iso88599': 'windows-1254', - 'iso885991989': 'windows-1254', - 'isoceltic': 'iso8859-14', - 'isoir100': 'windows-1252', - 'isoir101': 'iso8859-2', - 'isoir109': 'iso8859-3', - 'isoir110': 'iso8859-4', - 'isoir126': 'iso8859-7', - 'isoir127': 'iso8859-6', - 'isoir138': 'iso8859-8', - 'isoir144': 'iso8859-5', - 'isoir148': 'windows-1254', - 'isoir149': 'cp949', - 'isoir157': 'iso8859-10', - 'isoir199': 'iso8859-14', - 'isoir226': 'iso8859-16', - 'isoir58': 'gbk', - 'isoir6': 'ascii', - 'koi8r': 'koi8-r', - 'koi8u': 'koi8-u', - 'korean': 'cp949', - 'ksc5601': 'cp949', - 'ksc56011987': 'cp949', - 'ksc56011989': 'cp949', - 'l1': 'windows-1252', - 'l10': 'iso8859-16', - 'l2': 'iso8859-2', - 'l3': 'iso8859-3', - 'l4': 'iso8859-4', - 'l5': 'windows-1254', - 'l6': 'iso8859-10', - 'l8': 'iso8859-14', - 'latin1': 'windows-1252', - 'latin10': 'iso8859-16', - 'latin2': 'iso8859-2', - 'latin3': 'iso8859-3', - 'latin4': 'iso8859-4', - 'latin5': 'windows-1254', - 'latin6': 'iso8859-10', - 'latin8': 'iso8859-14', - 'latin9': 'iso8859-15', - 'ms936': 'gbk', - 'mskanji': 'shift_jis', - 'pt154': 'ptcp154', - 'ptcp154': 'ptcp154', - 'r8': 'hp-roman8', - 'roman8': 'hp-roman8', - 'shiftjis': 'shift_jis', - 'tis620': 'cp874', - 'unicode11utf7': 'utf-7', - 'us': 'ascii', - 'usascii': 'ascii', - 'utf16': 'utf-16', - 'utf16be': 'utf-16-be', - 'utf16le': 'utf-16-le', - 'utf8': 'utf-8', - 'windows1250': 'cp1250', - 'windows1251': 'cp1251', - 'windows1252': 'cp1252', - 'windows1253': 'cp1253', - 'windows1254': 'cp1254', - 'windows1255': 'cp1255', - 'windows1256': 'cp1256', - 'windows1257': 'cp1257', - 'windows1258': 'cp1258', - 'windows936': 'gbk', - 'x-x-big5': 'big5'} - tokenTypes = { "Doctype": 0, "Characters": 1, diff --git a/pip/_vendor/html5lib/filters/alphabeticalattributes.py b/pip/_vendor/html5lib/filters/alphabeticalattributes.py index fed6996c1..4795baecc 100644 --- a/pip/_vendor/html5lib/filters/alphabeticalattributes.py +++ b/pip/_vendor/html5lib/filters/alphabeticalattributes.py @@ -1,6 +1,6 @@ from __future__ import absolute_import, division, unicode_literals -from . import _base +from . import base try: from collections import OrderedDict @@ -8,9 +8,9 @@ except ImportError: from ordereddict import OrderedDict -class Filter(_base.Filter): +class Filter(base.Filter): def __iter__(self): - for token in _base.Filter.__iter__(self): + for token in base.Filter.__iter__(self): if token["type"] in ("StartTag", "EmptyTag"): attrs = OrderedDict() for name, value in sorted(token["data"].items(), diff --git a/pip/_vendor/html5lib/filters/_base.py b/pip/_vendor/html5lib/filters/base.py index c7dbaed0f..c7dbaed0f 100644 --- a/pip/_vendor/html5lib/filters/_base.py +++ b/pip/_vendor/html5lib/filters/base.py diff --git a/pip/_vendor/html5lib/filters/inject_meta_charset.py b/pip/_vendor/html5lib/filters/inject_meta_charset.py index ca33b70b5..2059ec861 100644 --- a/pip/_vendor/html5lib/filters/inject_meta_charset.py +++ b/pip/_vendor/html5lib/filters/inject_meta_charset.py @@ -1,11 +1,11 @@ from __future__ import absolute_import, division, unicode_literals -from . import _base +from . import base -class Filter(_base.Filter): +class Filter(base.Filter): def __init__(self, source, encoding): - _base.Filter.__init__(self, source) + base.Filter.__init__(self, source) self.encoding = encoding def __iter__(self): @@ -13,7 +13,7 @@ class Filter(_base.Filter): meta_found = (self.encoding is None) pending = [] - for token in _base.Filter.__iter__(self): + for token in base.Filter.__iter__(self): type = token["type"] if type == "StartTag": if token["name"].lower() == "head": diff --git a/pip/_vendor/html5lib/filters/lint.py b/pip/_vendor/html5lib/filters/lint.py index 8884696dc..3b892c860 100644 --- a/pip/_vendor/html5lib/filters/lint.py +++ b/pip/_vendor/html5lib/filters/lint.py @@ -1,90 +1,81 @@ from __future__ import absolute_import, division, unicode_literals -from . import _base -from ..constants import cdataElements, rcdataElements, voidElements +from pip._vendor.six import text_type + +from . import base +from ..constants import namespaces, voidElements from ..constants import spaceCharacters spaceCharacters = "".join(spaceCharacters) -class LintError(Exception): - pass - +class Filter(base.Filter): + def __init__(self, source, require_matching_tags=True): + super(Filter, self).__init__(source) + self.require_matching_tags = require_matching_tags -class Filter(_base.Filter): def __iter__(self): open_elements = [] - contentModelFlag = "PCDATA" - for token in _base.Filter.__iter__(self): + for token in base.Filter.__iter__(self): type = token["type"] if type in ("StartTag", "EmptyTag"): + namespace = token["namespace"] name = token["name"] - if contentModelFlag != "PCDATA": - raise LintError("StartTag not in PCDATA content model flag: %(tag)s" % {"tag": name}) - if not isinstance(name, str): - raise LintError("Tag name is not a string: %(tag)r" % {"tag": name}) - if not name: - raise LintError("Empty tag name") - if type == "StartTag" and name in voidElements: - raise LintError("Void element reported as StartTag token: %(tag)s" % {"tag": name}) - elif type == "EmptyTag" and name not in voidElements: - raise LintError("Non-void element reported as EmptyTag token: %(tag)s" % {"tag": token["name"]}) - if type == "StartTag": - open_elements.append(name) - for name, value in token["data"]: - if not isinstance(name, str): - raise LintError("Attribute name is not a string: %(name)r" % {"name": name}) - if not name: - raise LintError("Empty attribute name") - if not isinstance(value, str): - raise LintError("Attribute value is not a string: %(value)r" % {"value": value}) - if name in cdataElements: - contentModelFlag = "CDATA" - elif name in rcdataElements: - contentModelFlag = "RCDATA" - elif name == "plaintext": - contentModelFlag = "PLAINTEXT" + assert namespace is None or isinstance(namespace, text_type) + assert namespace != "" + assert isinstance(name, text_type) + assert name != "" + assert isinstance(token["data"], dict) + if (not namespace or namespace == namespaces["html"]) and name in voidElements: + assert type == "EmptyTag" + else: + assert type == "StartTag" + if type == "StartTag" and self.require_matching_tags: + open_elements.append((namespace, name)) + for (namespace, name), value in token["data"].items(): + assert namespace is None or isinstance(namespace, text_type) + assert namespace != "" + assert isinstance(name, text_type) + assert name != "" + assert isinstance(value, text_type) elif type == "EndTag": + namespace = token["namespace"] name = token["name"] - if not isinstance(name, str): - raise LintError("Tag name is not a string: %(tag)r" % {"tag": name}) - if not name: - raise LintError("Empty tag name") - if name in voidElements: - raise LintError("Void element reported as EndTag token: %(tag)s" % {"tag": name}) - start_name = open_elements.pop() - if start_name != name: - raise LintError("EndTag (%(end)s) does not match StartTag (%(start)s)" % {"end": name, "start": start_name}) - contentModelFlag = "PCDATA" + assert namespace is None or isinstance(namespace, text_type) + assert namespace != "" + assert isinstance(name, text_type) + assert name != "" + if (not namespace or namespace == namespaces["html"]) and name in voidElements: + assert False, "Void element reported as EndTag token: %(tag)s" % {"tag": name} + elif self.require_matching_tags: + start = open_elements.pop() + assert start == (namespace, name) elif type == "Comment": - if contentModelFlag != "PCDATA": - raise LintError("Comment not in PCDATA content model flag") + data = token["data"] + assert isinstance(data, text_type) elif type in ("Characters", "SpaceCharacters"): data = token["data"] - if not isinstance(data, str): - raise LintError("Attribute name is not a string: %(name)r" % {"name": data}) - if not data: - raise LintError("%(type)s token with empty data" % {"type": type}) + assert isinstance(data, text_type) + assert data != "" if type == "SpaceCharacters": - data = data.strip(spaceCharacters) - if data: - raise LintError("Non-space character(s) found in SpaceCharacters token: %(token)r" % {"token": data}) + assert data.strip(spaceCharacters) == "" elif type == "Doctype": name = token["name"] - if contentModelFlag != "PCDATA": - raise LintError("Doctype not in PCDATA content model flag: %(name)s" % {"name": name}) - if not isinstance(name, str): - raise LintError("Tag name is not a string: %(tag)r" % {"tag": name}) - # XXX: what to do with token["data"] ? + assert name is None or isinstance(name, text_type) + assert token["publicId"] is None or isinstance(name, text_type) + assert token["systemId"] is None or isinstance(name, text_type) + + elif type == "Entity": + assert isinstance(token["name"], text_type) - elif type in ("ParseError", "SerializeError"): - pass + elif type == "SerializerError": + assert isinstance(token["data"], text_type) else: - raise LintError("Unknown token type: %(type)s" % {"type": type}) + assert False, "Unknown token type: %(type)s" % {"type": type} yield token diff --git a/pip/_vendor/html5lib/filters/optionaltags.py b/pip/_vendor/html5lib/filters/optionaltags.py index fefe0b309..f6edb7341 100644 --- a/pip/_vendor/html5lib/filters/optionaltags.py +++ b/pip/_vendor/html5lib/filters/optionaltags.py @@ -1,9 +1,9 @@ from __future__ import absolute_import, division, unicode_literals -from . import _base +from . import base -class Filter(_base.Filter): +class Filter(base.Filter): def slider(self): previous1 = previous2 = None for token in self.source: @@ -11,7 +11,8 @@ class Filter(_base.Filter): yield previous2, previous1, token previous2 = previous1 previous1 = token - yield previous2, previous1, None + if previous1 is not None: + yield previous2, previous1, None def __iter__(self): for previous, token, next in self.slider(): @@ -58,7 +59,7 @@ class Filter(_base.Filter): elif tagname == 'colgroup': # A colgroup element's start tag may be omitted if the first thing # inside the colgroup element is a col element, and if the element - # is not immediately preceeded by another colgroup element whose + # is not immediately preceded by another colgroup element whose # end tag has been omitted. if type in ("StartTag", "EmptyTag"): # XXX: we do not look at the preceding event, so instead we never @@ -70,7 +71,7 @@ class Filter(_base.Filter): elif tagname == 'tbody': # A tbody element's start tag may be omitted if the first thing # inside the tbody element is a tr element, and if the element is - # not immediately preceeded by a tbody, thead, or tfoot element + # not immediately preceded by a tbody, thead, or tfoot element # whose end tag has been omitted. if type == "StartTag": # omit the thead and tfoot elements' end tag when they are diff --git a/pip/_vendor/html5lib/filters/sanitizer.py b/pip/_vendor/html5lib/filters/sanitizer.py index b206b54e7..026748d2e 100644 --- a/pip/_vendor/html5lib/filters/sanitizer.py +++ b/pip/_vendor/html5lib/filters/sanitizer.py @@ -1,12 +1,865 @@ from __future__ import absolute_import, division, unicode_literals -from . import _base -from ..sanitizer import HTMLSanitizerMixin +import re +from xml.sax.saxutils import escape, unescape +from pip._vendor.six.moves import urllib_parse as urlparse + +from . import base +from ..constants import namespaces, prefixes + +__all__ = ["Filter"] + + +allowed_elements = frozenset(( + (namespaces['html'], 'a'), + (namespaces['html'], 'abbr'), + (namespaces['html'], 'acronym'), + (namespaces['html'], 'address'), + (namespaces['html'], 'area'), + (namespaces['html'], 'article'), + (namespaces['html'], 'aside'), + (namespaces['html'], 'audio'), + (namespaces['html'], 'b'), + (namespaces['html'], 'big'), + (namespaces['html'], 'blockquote'), + (namespaces['html'], 'br'), + (namespaces['html'], 'button'), + (namespaces['html'], 'canvas'), + (namespaces['html'], 'caption'), + (namespaces['html'], 'center'), + (namespaces['html'], 'cite'), + (namespaces['html'], 'code'), + (namespaces['html'], 'col'), + (namespaces['html'], 'colgroup'), + (namespaces['html'], 'command'), + (namespaces['html'], 'datagrid'), + (namespaces['html'], 'datalist'), + (namespaces['html'], 'dd'), + (namespaces['html'], 'del'), + (namespaces['html'], 'details'), + (namespaces['html'], 'dfn'), + (namespaces['html'], 'dialog'), + (namespaces['html'], 'dir'), + (namespaces['html'], 'div'), + (namespaces['html'], 'dl'), + (namespaces['html'], 'dt'), + (namespaces['html'], 'em'), + (namespaces['html'], 'event-source'), + (namespaces['html'], 'fieldset'), + (namespaces['html'], 'figcaption'), + (namespaces['html'], 'figure'), + (namespaces['html'], 'footer'), + (namespaces['html'], 'font'), + (namespaces['html'], 'form'), + (namespaces['html'], 'header'), + (namespaces['html'], 'h1'), + (namespaces['html'], 'h2'), + (namespaces['html'], 'h3'), + (namespaces['html'], 'h4'), + (namespaces['html'], 'h5'), + (namespaces['html'], 'h6'), + (namespaces['html'], 'hr'), + (namespaces['html'], 'i'), + (namespaces['html'], 'img'), + (namespaces['html'], 'input'), + (namespaces['html'], 'ins'), + (namespaces['html'], 'keygen'), + (namespaces['html'], 'kbd'), + (namespaces['html'], 'label'), + (namespaces['html'], 'legend'), + (namespaces['html'], 'li'), + (namespaces['html'], 'm'), + (namespaces['html'], 'map'), + (namespaces['html'], 'menu'), + (namespaces['html'], 'meter'), + (namespaces['html'], 'multicol'), + (namespaces['html'], 'nav'), + (namespaces['html'], 'nextid'), + (namespaces['html'], 'ol'), + (namespaces['html'], 'output'), + (namespaces['html'], 'optgroup'), + (namespaces['html'], 'option'), + (namespaces['html'], 'p'), + (namespaces['html'], 'pre'), + (namespaces['html'], 'progress'), + (namespaces['html'], 'q'), + (namespaces['html'], 's'), + (namespaces['html'], 'samp'), + (namespaces['html'], 'section'), + (namespaces['html'], 'select'), + (namespaces['html'], 'small'), + (namespaces['html'], 'sound'), + (namespaces['html'], 'source'), + (namespaces['html'], 'spacer'), + (namespaces['html'], 'span'), + (namespaces['html'], 'strike'), + (namespaces['html'], 'strong'), + (namespaces['html'], 'sub'), + (namespaces['html'], 'sup'), + (namespaces['html'], 'table'), + (namespaces['html'], 'tbody'), + (namespaces['html'], 'td'), + (namespaces['html'], 'textarea'), + (namespaces['html'], 'time'), + (namespaces['html'], 'tfoot'), + (namespaces['html'], 'th'), + (namespaces['html'], 'thead'), + (namespaces['html'], 'tr'), + (namespaces['html'], 'tt'), + (namespaces['html'], 'u'), + (namespaces['html'], 'ul'), + (namespaces['html'], 'var'), + (namespaces['html'], 'video'), + (namespaces['mathml'], 'maction'), + (namespaces['mathml'], 'math'), + (namespaces['mathml'], 'merror'), + (namespaces['mathml'], 'mfrac'), + (namespaces['mathml'], 'mi'), + (namespaces['mathml'], 'mmultiscripts'), + (namespaces['mathml'], 'mn'), + (namespaces['mathml'], 'mo'), + (namespaces['mathml'], 'mover'), + (namespaces['mathml'], 'mpadded'), + (namespaces['mathml'], 'mphantom'), + (namespaces['mathml'], 'mprescripts'), + (namespaces['mathml'], 'mroot'), + (namespaces['mathml'], 'mrow'), + (namespaces['mathml'], 'mspace'), + (namespaces['mathml'], 'msqrt'), + (namespaces['mathml'], 'mstyle'), + (namespaces['mathml'], 'msub'), + (namespaces['mathml'], 'msubsup'), + (namespaces['mathml'], 'msup'), + (namespaces['mathml'], 'mtable'), + (namespaces['mathml'], 'mtd'), + (namespaces['mathml'], 'mtext'), + (namespaces['mathml'], 'mtr'), + (namespaces['mathml'], 'munder'), + (namespaces['mathml'], 'munderover'), + (namespaces['mathml'], 'none'), + (namespaces['svg'], 'a'), + (namespaces['svg'], 'animate'), + (namespaces['svg'], 'animateColor'), + (namespaces['svg'], 'animateMotion'), + (namespaces['svg'], 'animateTransform'), + (namespaces['svg'], 'clipPath'), + (namespaces['svg'], 'circle'), + (namespaces['svg'], 'defs'), + (namespaces['svg'], 'desc'), + (namespaces['svg'], 'ellipse'), + (namespaces['svg'], 'font-face'), + (namespaces['svg'], 'font-face-name'), + (namespaces['svg'], 'font-face-src'), + (namespaces['svg'], 'g'), + (namespaces['svg'], 'glyph'), + (namespaces['svg'], 'hkern'), + (namespaces['svg'], 'linearGradient'), + (namespaces['svg'], 'line'), + (namespaces['svg'], 'marker'), + (namespaces['svg'], 'metadata'), + (namespaces['svg'], 'missing-glyph'), + (namespaces['svg'], 'mpath'), + (namespaces['svg'], 'path'), + (namespaces['svg'], 'polygon'), + (namespaces['svg'], 'polyline'), + (namespaces['svg'], 'radialGradient'), + (namespaces['svg'], 'rect'), + (namespaces['svg'], 'set'), + (namespaces['svg'], 'stop'), + (namespaces['svg'], 'svg'), + (namespaces['svg'], 'switch'), + (namespaces['svg'], 'text'), + (namespaces['svg'], 'title'), + (namespaces['svg'], 'tspan'), + (namespaces['svg'], 'use'), +)) + +allowed_attributes = frozenset(( + # HTML attributes + (None, 'abbr'), + (None, 'accept'), + (None, 'accept-charset'), + (None, 'accesskey'), + (None, 'action'), + (None, 'align'), + (None, 'alt'), + (None, 'autocomplete'), + (None, 'autofocus'), + (None, 'axis'), + (None, 'background'), + (None, 'balance'), + (None, 'bgcolor'), + (None, 'bgproperties'), + (None, 'border'), + (None, 'bordercolor'), + (None, 'bordercolordark'), + (None, 'bordercolorlight'), + (None, 'bottompadding'), + (None, 'cellpadding'), + (None, 'cellspacing'), + (None, 'ch'), + (None, 'challenge'), + (None, 'char'), + (None, 'charoff'), + (None, 'choff'), + (None, 'charset'), + (None, 'checked'), + (None, 'cite'), + (None, 'class'), + (None, 'clear'), + (None, 'color'), + (None, 'cols'), + (None, 'colspan'), + (None, 'compact'), + (None, 'contenteditable'), + (None, 'controls'), + (None, 'coords'), + (None, 'data'), + (None, 'datafld'), + (None, 'datapagesize'), + (None, 'datasrc'), + (None, 'datetime'), + (None, 'default'), + (None, 'delay'), + (None, 'dir'), + (None, 'disabled'), + (None, 'draggable'), + (None, 'dynsrc'), + (None, 'enctype'), + (None, 'end'), + (None, 'face'), + (None, 'for'), + (None, 'form'), + (None, 'frame'), + (None, 'galleryimg'), + (None, 'gutter'), + (None, 'headers'), + (None, 'height'), + (None, 'hidefocus'), + (None, 'hidden'), + (None, 'high'), + (None, 'href'), + (None, 'hreflang'), + (None, 'hspace'), + (None, 'icon'), + (None, 'id'), + (None, 'inputmode'), + (None, 'ismap'), + (None, 'keytype'), + (None, 'label'), + (None, 'leftspacing'), + (None, 'lang'), + (None, 'list'), + (None, 'longdesc'), + (None, 'loop'), + (None, 'loopcount'), + (None, 'loopend'), + (None, 'loopstart'), + (None, 'low'), + (None, 'lowsrc'), + (None, 'max'), + (None, 'maxlength'), + (None, 'media'), + (None, 'method'), + (None, 'min'), + (None, 'multiple'), + (None, 'name'), + (None, 'nohref'), + (None, 'noshade'), + (None, 'nowrap'), + (None, 'open'), + (None, 'optimum'), + (None, 'pattern'), + (None, 'ping'), + (None, 'point-size'), + (None, 'poster'), + (None, 'pqg'), + (None, 'preload'), + (None, 'prompt'), + (None, 'radiogroup'), + (None, 'readonly'), + (None, 'rel'), + (None, 'repeat-max'), + (None, 'repeat-min'), + (None, 'replace'), + (None, 'required'), + (None, 'rev'), + (None, 'rightspacing'), + (None, 'rows'), + (None, 'rowspan'), + (None, 'rules'), + (None, 'scope'), + (None, 'selected'), + (None, 'shape'), + (None, 'size'), + (None, 'span'), + (None, 'src'), + (None, 'start'), + (None, 'step'), + (None, 'style'), + (None, 'summary'), + (None, 'suppress'), + (None, 'tabindex'), + (None, 'target'), + (None, 'template'), + (None, 'title'), + (None, 'toppadding'), + (None, 'type'), + (None, 'unselectable'), + (None, 'usemap'), + (None, 'urn'), + (None, 'valign'), + (None, 'value'), + (None, 'variable'), + (None, 'volume'), + (None, 'vspace'), + (None, 'vrml'), + (None, 'width'), + (None, 'wrap'), + (namespaces['xml'], 'lang'), + # MathML attributes + (None, 'actiontype'), + (None, 'align'), + (None, 'columnalign'), + (None, 'columnalign'), + (None, 'columnalign'), + (None, 'columnlines'), + (None, 'columnspacing'), + (None, 'columnspan'), + (None, 'depth'), + (None, 'display'), + (None, 'displaystyle'), + (None, 'equalcolumns'), + (None, 'equalrows'), + (None, 'fence'), + (None, 'fontstyle'), + (None, 'fontweight'), + (None, 'frame'), + (None, 'height'), + (None, 'linethickness'), + (None, 'lspace'), + (None, 'mathbackground'), + (None, 'mathcolor'), + (None, 'mathvariant'), + (None, 'mathvariant'), + (None, 'maxsize'), + (None, 'minsize'), + (None, 'other'), + (None, 'rowalign'), + (None, 'rowalign'), + (None, 'rowalign'), + (None, 'rowlines'), + (None, 'rowspacing'), + (None, 'rowspan'), + (None, 'rspace'), + (None, 'scriptlevel'), + (None, 'selection'), + (None, 'separator'), + (None, 'stretchy'), + (None, 'width'), + (None, 'width'), + (namespaces['xlink'], 'href'), + (namespaces['xlink'], 'show'), + (namespaces['xlink'], 'type'), + # SVG attributes + (None, 'accent-height'), + (None, 'accumulate'), + (None, 'additive'), + (None, 'alphabetic'), + (None, 'arabic-form'), + (None, 'ascent'), + (None, 'attributeName'), + (None, 'attributeType'), + (None, 'baseProfile'), + (None, 'bbox'), + (None, 'begin'), + (None, 'by'), + (None, 'calcMode'), + (None, 'cap-height'), + (None, 'class'), + (None, 'clip-path'), + (None, 'color'), + (None, 'color-rendering'), + (None, 'content'), + (None, 'cx'), + (None, 'cy'), + (None, 'd'), + (None, 'dx'), + (None, 'dy'), + (None, 'descent'), + (None, 'display'), + (None, 'dur'), + (None, 'end'), + (None, 'fill'), + (None, 'fill-opacity'), + (None, 'fill-rule'), + (None, 'font-family'), + (None, 'font-size'), + (None, 'font-stretch'), + (None, 'font-style'), + (None, 'font-variant'), + (None, 'font-weight'), + (None, 'from'), + (None, 'fx'), + (None, 'fy'), + (None, 'g1'), + (None, 'g2'), + (None, 'glyph-name'), + (None, 'gradientUnits'), + (None, 'hanging'), + (None, 'height'), + (None, 'horiz-adv-x'), + (None, 'horiz-origin-x'), + (None, 'id'), + (None, 'ideographic'), + (None, 'k'), + (None, 'keyPoints'), + (None, 'keySplines'), + (None, 'keyTimes'), + (None, 'lang'), + (None, 'marker-end'), + (None, 'marker-mid'), + (None, 'marker-start'), + (None, 'markerHeight'), + (None, 'markerUnits'), + (None, 'markerWidth'), + (None, 'mathematical'), + (None, 'max'), + (None, 'min'), + (None, 'name'), + (None, 'offset'), + (None, 'opacity'), + (None, 'orient'), + (None, 'origin'), + (None, 'overline-position'), + (None, 'overline-thickness'), + (None, 'panose-1'), + (None, 'path'), + (None, 'pathLength'), + (None, 'points'), + (None, 'preserveAspectRatio'), + (None, 'r'), + (None, 'refX'), + (None, 'refY'), + (None, 'repeatCount'), + (None, 'repeatDur'), + (None, 'requiredExtensions'), + (None, 'requiredFeatures'), + (None, 'restart'), + (None, 'rotate'), + (None, 'rx'), + (None, 'ry'), + (None, 'slope'), + (None, 'stemh'), + (None, 'stemv'), + (None, 'stop-color'), + (None, 'stop-opacity'), + (None, 'strikethrough-position'), + (None, 'strikethrough-thickness'), + (None, 'stroke'), + (None, 'stroke-dasharray'), + (None, 'stroke-dashoffset'), + (None, 'stroke-linecap'), + (None, 'stroke-linejoin'), + (None, 'stroke-miterlimit'), + (None, 'stroke-opacity'), + (None, 'stroke-width'), + (None, 'systemLanguage'), + (None, 'target'), + (None, 'text-anchor'), + (None, 'to'), + (None, 'transform'), + (None, 'type'), + (None, 'u1'), + (None, 'u2'), + (None, 'underline-position'), + (None, 'underline-thickness'), + (None, 'unicode'), + (None, 'unicode-range'), + (None, 'units-per-em'), + (None, 'values'), + (None, 'version'), + (None, 'viewBox'), + (None, 'visibility'), + (None, 'width'), + (None, 'widths'), + (None, 'x'), + (None, 'x-height'), + (None, 'x1'), + (None, 'x2'), + (namespaces['xlink'], 'actuate'), + (namespaces['xlink'], 'arcrole'), + (namespaces['xlink'], 'href'), + (namespaces['xlink'], 'role'), + (namespaces['xlink'], 'show'), + (namespaces['xlink'], 'title'), + (namespaces['xlink'], 'type'), + (namespaces['xml'], 'base'), + (namespaces['xml'], 'lang'), + (namespaces['xml'], 'space'), + (None, 'y'), + (None, 'y1'), + (None, 'y2'), + (None, 'zoomAndPan'), +)) + +attr_val_is_uri = frozenset(( + (None, 'href'), + (None, 'src'), + (None, 'cite'), + (None, 'action'), + (None, 'longdesc'), + (None, 'poster'), + (None, 'background'), + (None, 'datasrc'), + (None, 'dynsrc'), + (None, 'lowsrc'), + (None, 'ping'), + (namespaces['xlink'], 'href'), + (namespaces['xml'], 'base'), +)) + +svg_attr_val_allows_ref = frozenset(( + (None, 'clip-path'), + (None, 'color-profile'), + (None, 'cursor'), + (None, 'fill'), + (None, 'filter'), + (None, 'marker'), + (None, 'marker-start'), + (None, 'marker-mid'), + (None, 'marker-end'), + (None, 'mask'), + (None, 'stroke'), +)) + +svg_allow_local_href = frozenset(( + (None, 'altGlyph'), + (None, 'animate'), + (None, 'animateColor'), + (None, 'animateMotion'), + (None, 'animateTransform'), + (None, 'cursor'), + (None, 'feImage'), + (None, 'filter'), + (None, 'linearGradient'), + (None, 'pattern'), + (None, 'radialGradient'), + (None, 'textpath'), + (None, 'tref'), + (None, 'set'), + (None, 'use') +)) + +allowed_css_properties = frozenset(( + 'azimuth', + 'background-color', + 'border-bottom-color', + 'border-collapse', + 'border-color', + 'border-left-color', + 'border-right-color', + 'border-top-color', + 'clear', + 'color', + 'cursor', + 'direction', + 'display', + 'elevation', + 'float', + 'font', + 'font-family', + 'font-size', + 'font-style', + 'font-variant', + 'font-weight', + 'height', + 'letter-spacing', + 'line-height', + 'overflow', + 'pause', + 'pause-after', + 'pause-before', + 'pitch', + 'pitch-range', + 'richness', + 'speak', + 'speak-header', + 'speak-numeral', + 'speak-punctuation', + 'speech-rate', + 'stress', + 'text-align', + 'text-decoration', + 'text-indent', + 'unicode-bidi', + 'vertical-align', + 'voice-family', + 'volume', + 'white-space', + 'width', +)) + +allowed_css_keywords = frozenset(( + 'auto', + 'aqua', + 'black', + 'block', + 'blue', + 'bold', + 'both', + 'bottom', + 'brown', + 'center', + 'collapse', + 'dashed', + 'dotted', + 'fuchsia', + 'gray', + 'green', + '!important', + 'italic', + 'left', + 'lime', + 'maroon', + 'medium', + 'none', + 'navy', + 'normal', + 'nowrap', + 'olive', + 'pointer', + 'purple', + 'red', + 'right', + 'solid', + 'silver', + 'teal', + 'top', + 'transparent', + 'underline', + 'white', + 'yellow', +)) + +allowed_svg_properties = frozenset(( + 'fill', + 'fill-opacity', + 'fill-rule', + 'stroke', + 'stroke-width', + 'stroke-linecap', + 'stroke-linejoin', + 'stroke-opacity', +)) + +allowed_protocols = frozenset(( + 'ed2k', + 'ftp', + 'http', + 'https', + 'irc', + 'mailto', + 'news', + 'gopher', + 'nntp', + 'telnet', + 'webcal', + 'xmpp', + 'callto', + 'feed', + 'urn', + 'aim', + 'rsync', + 'tag', + 'ssh', + 'sftp', + 'rtsp', + 'afs', + 'data', +)) + +allowed_content_types = frozenset(( + 'image/png', + 'image/jpeg', + 'image/gif', + 'image/webp', + 'image/bmp', + 'text/plain', +)) + + +data_content_type = re.compile(r''' + ^ + # Match a content type <application>/<type> + (?P<content_type>[-a-zA-Z0-9.]+/[-a-zA-Z0-9.]+) + # Match any character set and encoding + (?:(?:;charset=(?:[-a-zA-Z0-9]+)(?:;(?:base64))?) + |(?:;(?:base64))?(?:;charset=(?:[-a-zA-Z0-9]+))?) + # Assume the rest is data + ,.* + $ + ''', + re.VERBOSE) + + +class Filter(base.Filter): + """ sanitization of XHTML+MathML+SVG and of inline style attributes.""" + def __init__(self, + source, + allowed_elements=allowed_elements, + allowed_attributes=allowed_attributes, + allowed_css_properties=allowed_css_properties, + allowed_css_keywords=allowed_css_keywords, + allowed_svg_properties=allowed_svg_properties, + allowed_protocols=allowed_protocols, + allowed_content_types=allowed_content_types, + attr_val_is_uri=attr_val_is_uri, + svg_attr_val_allows_ref=svg_attr_val_allows_ref, + svg_allow_local_href=svg_allow_local_href): + super(Filter, self).__init__(source) + self.allowed_elements = allowed_elements + self.allowed_attributes = allowed_attributes + self.allowed_css_properties = allowed_css_properties + self.allowed_css_keywords = allowed_css_keywords + self.allowed_svg_properties = allowed_svg_properties + self.allowed_protocols = allowed_protocols + self.allowed_content_types = allowed_content_types + self.attr_val_is_uri = attr_val_is_uri + self.svg_attr_val_allows_ref = svg_attr_val_allows_ref + self.svg_allow_local_href = svg_allow_local_href -class Filter(_base.Filter, HTMLSanitizerMixin): def __iter__(self): - for token in _base.Filter.__iter__(self): + for token in base.Filter.__iter__(self): token = self.sanitize_token(token) if token: yield token + + # Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and + # stripping out all # attributes not in ALLOWED_ATTRIBUTES. Style + # attributes are parsed, and a restricted set, # specified by + # ALLOWED_CSS_PROPERTIES and ALLOWED_CSS_KEYWORDS, are allowed through. + # attributes in ATTR_VAL_IS_URI are scanned, and only URI schemes specified + # in ALLOWED_PROTOCOLS are allowed. + # + # sanitize_html('<script> do_nasty_stuff() </script>') + # => <script> do_nasty_stuff() </script> + # sanitize_html('<a href="javascript: sucker();">Click here for $100</a>') + # => <a>Click here for $100</a> + def sanitize_token(self, token): + + # accommodate filters which use token_type differently + token_type = token["type"] + if token_type in ("StartTag", "EndTag", "EmptyTag"): + name = token["name"] + namespace = token["namespace"] + if ((namespace, name) in self.allowed_elements or + (namespace is None and + (namespaces["html"], name) in self.allowed_elements)): + return self.allowed_token(token) + else: + return self.disallowed_token(token) + elif token_type == "Comment": + pass + else: + return token + + def allowed_token(self, token): + if "data" in token: + attrs = token["data"] + attr_names = set(attrs.keys()) + + # Remove forbidden attributes + for to_remove in (attr_names - self.allowed_attributes): + del token["data"][to_remove] + attr_names.remove(to_remove) + + # Remove attributes with disallowed URL values + for attr in (attr_names & self.attr_val_is_uri): + assert attr in attrs + # I don't have a clue where this regexp comes from or why it matches those + # characters, nor why we call unescape. I just know it's always been here. + # Should you be worried by this comment in a sanitizer? Yes. On the other hand, all + # this will do is remove *more* than it otherwise would. + val_unescaped = re.sub("[`\x00-\x20\x7f-\xa0\s]+", '', + unescape(attrs[attr])).lower() + # remove replacement characters from unescaped characters + val_unescaped = val_unescaped.replace("\ufffd", "") + try: + uri = urlparse.urlparse(val_unescaped) + except ValueError: + uri = None + del attrs[attr] + if uri and uri.scheme: + if uri.scheme not in self.allowed_protocols: + del attrs[attr] + if uri.scheme == 'data': + m = data_content_type.match(uri.path) + if not m: + del attrs[attr] + elif m.group('content_type') not in self.allowed_content_types: + del attrs[attr] + + for attr in self.svg_attr_val_allows_ref: + if attr in attrs: + attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)', + ' ', + unescape(attrs[attr])) + if (token["name"] in self.svg_allow_local_href and + (namespaces['xlink'], 'href') in attrs and re.search('^\s*[^#\s].*', + attrs[(namespaces['xlink'], 'href')])): + del attrs[(namespaces['xlink'], 'href')] + if (None, 'style') in attrs: + attrs[(None, 'style')] = self.sanitize_css(attrs[(None, 'style')]) + token["data"] = attrs + return token + + def disallowed_token(self, token): + token_type = token["type"] + if token_type == "EndTag": + token["data"] = "</%s>" % token["name"] + elif token["data"]: + assert token_type in ("StartTag", "EmptyTag") + attrs = [] + for (ns, name), v in token["data"].items(): + attrs.append(' %s="%s"' % (name if ns is None else "%s:%s" % (prefixes[ns], name), escape(v))) + token["data"] = "<%s%s>" % (token["name"], ''.join(attrs)) + else: + token["data"] = "<%s>" % token["name"] + if token.get("selfClosing"): + token["data"] = token["data"][:-1] + "/>" + + token["type"] = "Characters" + + del token["name"] + return token + + def sanitize_css(self, style): + # disallow urls + style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style) + + # gauntlet + if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style): + return '' + if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style): + return '' + + clean = [] + for prop, value in re.findall("([-\w]+)\s*:\s*([^:;]*)", style): + if not value: + continue + if prop.lower() in self.allowed_css_properties: + clean.append(prop + ': ' + value + ';') + elif prop.split('-')[0].lower() in ['background', 'border', 'margin', + 'padding']: + for keyword in value.split(): + if keyword not in self.allowed_css_keywords and \ + not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword): # noqa + break + else: + clean.append(prop + ': ' + value + ';') + elif prop.lower() in self.allowed_svg_properties: + clean.append(prop + ': ' + value + ';') + + return ' '.join(clean) diff --git a/pip/_vendor/html5lib/filters/whitespace.py b/pip/_vendor/html5lib/filters/whitespace.py index dfc60eebd..892105287 100644 --- a/pip/_vendor/html5lib/filters/whitespace.py +++ b/pip/_vendor/html5lib/filters/whitespace.py @@ -2,20 +2,20 @@ from __future__ import absolute_import, division, unicode_literals import re -from . import _base +from . import base from ..constants import rcdataElements, spaceCharacters spaceCharacters = "".join(spaceCharacters) SPACES_REGEX = re.compile("[%s]+" % spaceCharacters) -class Filter(_base.Filter): +class Filter(base.Filter): spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements)) def __iter__(self): preserve = 0 - for token in _base.Filter.__iter__(self): + for token in base.Filter.__iter__(self): type = token["type"] if type == "StartTag" \ and (preserve or token["name"] in self.spacePreserveElements): diff --git a/pip/_vendor/html5lib/html5parser.py b/pip/_vendor/html5lib/html5parser.py index 40f3d093e..f7043cb19 100644 --- a/pip/_vendor/html5lib/html5parser.py +++ b/pip/_vendor/html5lib/html5parser.py @@ -1,39 +1,44 @@ from __future__ import absolute_import, division, unicode_literals -from pip._vendor.six import with_metaclass +from pip._vendor.six import with_metaclass, viewkeys, PY3 import types -from . import inputstream -from . import tokenizer +try: + from collections import OrderedDict +except ImportError: + from pip._vendor.ordereddict import OrderedDict + +from . import _inputstream +from . import _tokenizer from . import treebuilders -from .treebuilders._base import Marker - -from . import utils -from . import constants -from .constants import spaceCharacters, asciiUpper2Lower -from .constants import specialElements -from .constants import headingElements -from .constants import cdataElements, rcdataElements -from .constants import tokenTypes, ReparseException, namespaces -from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements -from .constants import adjustForeignAttributes as adjustForeignAttributesMap -from .constants import E - - -def parse(doc, treebuilder="etree", encoding=None, - namespaceHTMLElements=True): +from .treebuilders.base import Marker + +from . import _utils +from .constants import ( + spaceCharacters, asciiUpper2Lower, + specialElements, headingElements, cdataElements, rcdataElements, + tokenTypes, tagTokenTypes, + namespaces, + htmlIntegrationPointElements, mathmlTextIntegrationPointElements, + adjustForeignAttributes as adjustForeignAttributesMap, + adjustMathMLAttributes, adjustSVGAttributes, + E, + ReparseException +) + + +def parse(doc, treebuilder="etree", namespaceHTMLElements=True, **kwargs): """Parse a string or file-like object into a tree""" tb = treebuilders.getTreeBuilder(treebuilder) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) - return p.parse(doc, encoding=encoding) + return p.parse(doc, **kwargs) -def parseFragment(doc, container="div", treebuilder="etree", encoding=None, - namespaceHTMLElements=True): +def parseFragment(doc, container="div", treebuilder="etree", namespaceHTMLElements=True, **kwargs): tb = treebuilders.getTreeBuilder(treebuilder) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) - return p.parseFragment(doc, container=container, encoding=encoding) + return p.parseFragment(doc, container=container, **kwargs) def method_decorator_metaclass(function): @@ -52,18 +57,13 @@ class HTMLParser(object): """HTML parser. Generates a tree structure from a stream of (possibly malformed) HTML""" - def __init__(self, tree=None, tokenizer=tokenizer.HTMLTokenizer, - strict=False, namespaceHTMLElements=True, debug=False): + def __init__(self, tree=None, strict=False, namespaceHTMLElements=True, debug=False): """ strict - raise an exception when a parse error is encountered tree - a treebuilder class controlling the type of tree that will be returned. Built in treebuilders can be accessed through html5lib.treebuilders.getTreeBuilder(treeType) - - tokenizer - a class that provides a stream of tokens to the treebuilder. - This may be replaced for e.g. a sanitizer which converts some tags to - text """ # Raise an exception on the first error encountered @@ -72,29 +72,24 @@ class HTMLParser(object): if tree is None: tree = treebuilders.getTreeBuilder("etree") self.tree = tree(namespaceHTMLElements) - self.tokenizer_class = tokenizer self.errors = [] self.phases = dict([(name, cls(self, self.tree)) for name, cls in getPhases(debug).items()]) - def _parse(self, stream, innerHTML=False, container="div", - encoding=None, parseMeta=True, useChardet=True, **kwargs): + def _parse(self, stream, innerHTML=False, container="div", scripting=False, **kwargs): self.innerHTMLMode = innerHTML self.container = container - self.tokenizer = self.tokenizer_class(stream, encoding=encoding, - parseMeta=parseMeta, - useChardet=useChardet, - parser=self, **kwargs) + self.scripting = scripting + self.tokenizer = _tokenizer.HTMLTokenizer(stream, parser=self, **kwargs) self.reset() - while True: - try: - self.mainLoop() - break - except ReparseException: - self.reset() + try: + self.mainLoop() + except ReparseException: + self.reset() + self.mainLoop() def reset(self): self.tree.reset() @@ -121,7 +116,7 @@ class HTMLParser(object): self.phase.insertHtmlElement() self.resetInsertionMode() else: - self.innerHTML = False + self.innerHTML = False # pylint:disable=redefined-variable-type self.phase = self.phases["initial"] self.lastPhase = None @@ -139,7 +134,7 @@ class HTMLParser(object): """ if not hasattr(self, 'tokenizer'): return None - return self.tokenizer.stream.charEncoding[0] + return self.tokenizer.stream.charEncoding[0].name def isHTMLIntegrationPoint(self, element): if (element.name == "annotation-xml" and @@ -164,8 +159,10 @@ class HTMLParser(object): ParseErrorToken = tokenTypes["ParseError"] for token in self.normalizedTokens(): + prev_token = None new_token = token while new_token is not None: + prev_token = new_token currentNode = self.tree.openElements[-1] if self.tree.openElements else None currentNodeNamespace = currentNode.namespace if currentNode else None currentNodeName = currentNode.name if currentNode else None @@ -184,6 +181,7 @@ class HTMLParser(object): type in (CharactersToken, SpaceCharactersToken))) or (currentNodeNamespace == namespaces["mathml"] and currentNodeName == "annotation-xml" and + type == StartTagToken and token["name"] == "svg") or (self.isHTMLIntegrationPoint(currentNode) and type in (StartTagToken, CharactersToken, SpaceCharactersToken))): @@ -204,10 +202,10 @@ class HTMLParser(object): elif type == DoctypeToken: new_token = phase.processDoctype(new_token) - if (type == StartTagToken and token["selfClosing"] - and not token["selfClosingAcknowledged"]): + if (type == StartTagToken and prev_token["selfClosing"] and + not prev_token["selfClosingAcknowledged"]): self.parseError("non-void-element-with-trailing-solidus", - {"name": token["name"]}) + {"name": prev_token["name"]}) # When the loop finishes it's EOF reprocess = True @@ -222,7 +220,7 @@ class HTMLParser(object): for token in self.tokenizer: yield self.normalizeToken(token) - def parse(self, stream, encoding=None, parseMeta=True, useChardet=True): + def parse(self, stream, *args, **kwargs): """Parse a HTML document into a well-formed tree stream - a filelike object or string containing the HTML to be parsed @@ -231,13 +229,13 @@ class HTMLParser(object): the encoding. If specified, that encoding will be used, regardless of any BOM or later declaration (such as in a meta element) + + scripting - treat noscript elements as if javascript was turned on """ - self._parse(stream, innerHTML=False, encoding=encoding, - parseMeta=parseMeta, useChardet=useChardet) + self._parse(stream, False, None, *args, **kwargs) return self.tree.getDocument() - def parseFragment(self, stream, container="div", encoding=None, - parseMeta=False, useChardet=True): + def parseFragment(self, stream, *args, **kwargs): """Parse a HTML fragment into a well-formed tree fragment container - name of the element we're setting the innerHTML property @@ -249,12 +247,16 @@ class HTMLParser(object): the encoding. If specified, that encoding will be used, regardless of any BOM or later declaration (such as in a meta element) + + scripting - treat noscript elements as if javascript was turned on """ - self._parse(stream, True, container=container, encoding=encoding) + self._parse(stream, True, *args, **kwargs) return self.tree.getFragment() - def parseError(self, errorcode="XXX-undefined-error", datavars={}): + def parseError(self, errorcode="XXX-undefined-error", datavars=None): # XXX The idea is to make errorcode mandatory. + if datavars is None: + datavars = {} self.errors.append((self.tokenizer.stream.position(), errorcode, datavars)) if self.strict: raise ParseError(E[errorcode] % datavars) @@ -263,98 +265,25 @@ class HTMLParser(object): """ HTML5 specific normalizations to the token stream """ if token["type"] == tokenTypes["StartTag"]: - token["data"] = dict(token["data"][::-1]) + raw = token["data"] + token["data"] = OrderedDict(raw) + if len(raw) > len(token["data"]): + # we had some duplicated attribute, fix so first wins + token["data"].update(raw[::-1]) return token def adjustMathMLAttributes(self, token): - replacements = {"definitionurl": "definitionURL"} - for k, v in replacements.items(): - if k in token["data"]: - token["data"][v] = token["data"][k] - del token["data"][k] + adjust_attributes(token, adjustMathMLAttributes) def adjustSVGAttributes(self, token): - replacements = { - "attributename": "attributeName", - "attributetype": "attributeType", - "basefrequency": "baseFrequency", - "baseprofile": "baseProfile", - "calcmode": "calcMode", - "clippathunits": "clipPathUnits", - "contentscripttype": "contentScriptType", - "contentstyletype": "contentStyleType", - "diffuseconstant": "diffuseConstant", - "edgemode": "edgeMode", - "externalresourcesrequired": "externalResourcesRequired", - "filterres": "filterRes", - "filterunits": "filterUnits", - "glyphref": "glyphRef", - "gradienttransform": "gradientTransform", - "gradientunits": "gradientUnits", - "kernelmatrix": "kernelMatrix", - "kernelunitlength": "kernelUnitLength", - "keypoints": "keyPoints", - "keysplines": "keySplines", - "keytimes": "keyTimes", - "lengthadjust": "lengthAdjust", - "limitingconeangle": "limitingConeAngle", - "markerheight": "markerHeight", - "markerunits": "markerUnits", - "markerwidth": "markerWidth", - "maskcontentunits": "maskContentUnits", - "maskunits": "maskUnits", - "numoctaves": "numOctaves", - "pathlength": "pathLength", - "patterncontentunits": "patternContentUnits", - "patterntransform": "patternTransform", - "patternunits": "patternUnits", - "pointsatx": "pointsAtX", - "pointsaty": "pointsAtY", - "pointsatz": "pointsAtZ", - "preservealpha": "preserveAlpha", - "preserveaspectratio": "preserveAspectRatio", - "primitiveunits": "primitiveUnits", - "refx": "refX", - "refy": "refY", - "repeatcount": "repeatCount", - "repeatdur": "repeatDur", - "requiredextensions": "requiredExtensions", - "requiredfeatures": "requiredFeatures", - "specularconstant": "specularConstant", - "specularexponent": "specularExponent", - "spreadmethod": "spreadMethod", - "startoffset": "startOffset", - "stddeviation": "stdDeviation", - "stitchtiles": "stitchTiles", - "surfacescale": "surfaceScale", - "systemlanguage": "systemLanguage", - "tablevalues": "tableValues", - "targetx": "targetX", - "targety": "targetY", - "textlength": "textLength", - "viewbox": "viewBox", - "viewtarget": "viewTarget", - "xchannelselector": "xChannelSelector", - "ychannelselector": "yChannelSelector", - "zoomandpan": "zoomAndPan" - } - for originalName in list(token["data"].keys()): - if originalName in replacements: - svgName = replacements[originalName] - token["data"][svgName] = token["data"][originalName] - del token["data"][originalName] + adjust_attributes(token, adjustSVGAttributes) def adjustForeignAttributes(self, token): - replacements = adjustForeignAttributesMap - - for originalName in token["data"].keys(): - if originalName in replacements: - foreignName = replacements[originalName] - token["data"][foreignName] = token["data"][originalName] - del token["data"][originalName] + adjust_attributes(token, adjustForeignAttributesMap) def reparseTokenNormal(self, token): + # pylint:disable=unused-argument self.parser.phase() def resetInsertionMode(self): @@ -419,11 +348,12 @@ class HTMLParser(object): self.phase = self.phases["text"] +@_utils.memoize def getPhases(debug): def log(function): """Logger that records which phase processes each token""" type_names = dict((value, key) for key, value in - constants.tokenTypes.items()) + tokenTypes.items()) def wrapped(self, *args, **kwargs): if function.__name__.startswith("process") and len(args) > 0: @@ -432,7 +362,7 @@ def getPhases(debug): info = {"type": type_names[token['type']]} except: raise - if token['type'] in constants.tagTokenTypes: + if token['type'] in tagTokenTypes: info["name"] = token['name'] self.parser.log.append((self.parser.tokenizer.state.__name__, @@ -451,6 +381,7 @@ def getPhases(debug): else: return type + # pylint:disable=unused-argument class Phase(with_metaclass(getMetaclass(debug, log))): """Base class for helper object that implements each phase of processing """ @@ -517,77 +448,76 @@ def getPhases(debug): if publicId != "": publicId = publicId.translate(asciiUpper2Lower) - if (not correct or token["name"] != "html" - or publicId.startswith( - ("+//silmaril//dtd html pro v0r11 19970101//", - "-//advasoft ltd//dtd html 3.0 aswedit + extensions//", - "-//as//dtd html 3.0 aswedit + extensions//", - "-//ietf//dtd html 2.0 level 1//", - "-//ietf//dtd html 2.0 level 2//", - "-//ietf//dtd html 2.0 strict level 1//", - "-//ietf//dtd html 2.0 strict level 2//", - "-//ietf//dtd html 2.0 strict//", - "-//ietf//dtd html 2.0//", - "-//ietf//dtd html 2.1e//", - "-//ietf//dtd html 3.0//", - "-//ietf//dtd html 3.2 final//", - "-//ietf//dtd html 3.2//", - "-//ietf//dtd html 3//", - "-//ietf//dtd html level 0//", - "-//ietf//dtd html level 1//", - "-//ietf//dtd html level 2//", - "-//ietf//dtd html level 3//", - "-//ietf//dtd html strict level 0//", - "-//ietf//dtd html strict level 1//", - "-//ietf//dtd html strict level 2//", - "-//ietf//dtd html strict level 3//", - "-//ietf//dtd html strict//", - "-//ietf//dtd html//", - "-//metrius//dtd metrius presentational//", - "-//microsoft//dtd internet explorer 2.0 html strict//", - "-//microsoft//dtd internet explorer 2.0 html//", - "-//microsoft//dtd internet explorer 2.0 tables//", - "-//microsoft//dtd internet explorer 3.0 html strict//", - "-//microsoft//dtd internet explorer 3.0 html//", - "-//microsoft//dtd internet explorer 3.0 tables//", - "-//netscape comm. corp.//dtd html//", - "-//netscape comm. corp.//dtd strict html//", - "-//o'reilly and associates//dtd html 2.0//", - "-//o'reilly and associates//dtd html extended 1.0//", - "-//o'reilly and associates//dtd html extended relaxed 1.0//", - "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//", - "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//", - "-//spyglass//dtd html 2.0 extended//", - "-//sq//dtd html 2.0 hotmetal + extensions//", - "-//sun microsystems corp.//dtd hotjava html//", - "-//sun microsystems corp.//dtd hotjava strict html//", - "-//w3c//dtd html 3 1995-03-24//", - "-//w3c//dtd html 3.2 draft//", - "-//w3c//dtd html 3.2 final//", - "-//w3c//dtd html 3.2//", - "-//w3c//dtd html 3.2s draft//", - "-//w3c//dtd html 4.0 frameset//", - "-//w3c//dtd html 4.0 transitional//", - "-//w3c//dtd html experimental 19960712//", - "-//w3c//dtd html experimental 970421//", - "-//w3c//dtd w3 html//", - "-//w3o//dtd w3 html 3.0//", - "-//webtechs//dtd mozilla html 2.0//", - "-//webtechs//dtd mozilla html//")) - or publicId in - ("-//w3o//dtd w3 html strict 3.0//en//", - "-/w3c/dtd html 4.0 transitional/en", - "html") - or publicId.startswith( - ("-//w3c//dtd html 4.01 frameset//", - "-//w3c//dtd html 4.01 transitional//")) and - systemId is None - or systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"): + if (not correct or token["name"] != "html" or + publicId.startswith( + ("+//silmaril//dtd html pro v0r11 19970101//", + "-//advasoft ltd//dtd html 3.0 aswedit + extensions//", + "-//as//dtd html 3.0 aswedit + extensions//", + "-//ietf//dtd html 2.0 level 1//", + "-//ietf//dtd html 2.0 level 2//", + "-//ietf//dtd html 2.0 strict level 1//", + "-//ietf//dtd html 2.0 strict level 2//", + "-//ietf//dtd html 2.0 strict//", + "-//ietf//dtd html 2.0//", + "-//ietf//dtd html 2.1e//", + "-//ietf//dtd html 3.0//", + "-//ietf//dtd html 3.2 final//", + "-//ietf//dtd html 3.2//", + "-//ietf//dtd html 3//", + "-//ietf//dtd html level 0//", + "-//ietf//dtd html level 1//", + "-//ietf//dtd html level 2//", + "-//ietf//dtd html level 3//", + "-//ietf//dtd html strict level 0//", + "-//ietf//dtd html strict level 1//", + "-//ietf//dtd html strict level 2//", + "-//ietf//dtd html strict level 3//", + "-//ietf//dtd html strict//", + "-//ietf//dtd html//", + "-//metrius//dtd metrius presentational//", + "-//microsoft//dtd internet explorer 2.0 html strict//", + "-//microsoft//dtd internet explorer 2.0 html//", + "-//microsoft//dtd internet explorer 2.0 tables//", + "-//microsoft//dtd internet explorer 3.0 html strict//", + "-//microsoft//dtd internet explorer 3.0 html//", + "-//microsoft//dtd internet explorer 3.0 tables//", + "-//netscape comm. corp.//dtd html//", + "-//netscape comm. corp.//dtd strict html//", + "-//o'reilly and associates//dtd html 2.0//", + "-//o'reilly and associates//dtd html extended 1.0//", + "-//o'reilly and associates//dtd html extended relaxed 1.0//", + "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//", + "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//", + "-//spyglass//dtd html 2.0 extended//", + "-//sq//dtd html 2.0 hotmetal + extensions//", + "-//sun microsystems corp.//dtd hotjava html//", + "-//sun microsystems corp.//dtd hotjava strict html//", + "-//w3c//dtd html 3 1995-03-24//", + "-//w3c//dtd html 3.2 draft//", + "-//w3c//dtd html 3.2 final//", + "-//w3c//dtd html 3.2//", + "-//w3c//dtd html 3.2s draft//", + "-//w3c//dtd html 4.0 frameset//", + "-//w3c//dtd html 4.0 transitional//", + "-//w3c//dtd html experimental 19960712//", + "-//w3c//dtd html experimental 970421//", + "-//w3c//dtd w3 html//", + "-//w3o//dtd w3 html 3.0//", + "-//webtechs//dtd mozilla html 2.0//", + "-//webtechs//dtd mozilla html//")) or + publicId in ("-//w3o//dtd w3 html strict 3.0//en//", + "-/w3c/dtd html 4.0 transitional/en", + "html") or + publicId.startswith( + ("-//w3c//dtd html 4.01 frameset//", + "-//w3c//dtd html 4.01 transitional//")) and + systemId is None or + systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"): self.parser.compatMode = "quirks" elif (publicId.startswith( ("-//w3c//dtd xhtml 1.0 frameset//", - "-//w3c//dtd xhtml 1.0 transitional//")) - or publicId.startswith( + "-//w3c//dtd xhtml 1.0 transitional//")) or + publicId.startswith( ("-//w3c//dtd html 4.01 frameset//", "-//w3c//dtd html 4.01 transitional//")) and systemId is not None): @@ -660,13 +590,13 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ (("head", "body", "html", "br"), self.endTagImplyHead) ]) self.endTagHandler.default = self.endTagOther @@ -706,10 +636,11 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("title", self.startTagTitle), - (("noscript", "noframes", "style"), self.startTagNoScriptNoFramesStyle), + (("noframes", "style"), self.startTagNoFramesStyle), + ("noscript", self.startTagNoscript), ("script", self.startTagScript), (("base", "basefont", "bgsound", "command", "link"), self.startTagBaseLinkCommand), @@ -718,7 +649,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self. endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("head", self.endTagHead), (("br", "html", "body"), self.endTagHtmlBodyBr) ]) @@ -760,18 +691,25 @@ def getPhases(debug): # the abstract Unicode string, and just use the # ContentAttrParser on that, but using UTF-8 allows all chars # to be encoded and as a ASCII-superset works. - data = inputstream.EncodingBytes(attributes["content"].encode("utf-8")) - parser = inputstream.ContentAttrParser(data) + data = _inputstream.EncodingBytes(attributes["content"].encode("utf-8")) + parser = _inputstream.ContentAttrParser(data) codec = parser.parse() self.parser.tokenizer.stream.changeEncoding(codec) def startTagTitle(self, token): self.parser.parseRCDataRawtext(token, "RCDATA") - def startTagNoScriptNoFramesStyle(self, token): + def startTagNoFramesStyle(self, token): # Need to decide whether to implement the scripting-disabled case self.parser.parseRCDataRawtext(token, "RAWTEXT") + def startTagNoscript(self, token): + if self.parser.scripting: + self.parser.parseRCDataRawtext(token, "RAWTEXT") + else: + self.tree.insertElement(token) + self.parser.phase = self.parser.phases["inHeadNoscript"] + def startTagScript(self, token): self.tree.insertElement(token) self.parser.tokenizer.state = self.parser.tokenizer.scriptDataState @@ -797,15 +735,75 @@ def getPhases(debug): def anythingElse(self): self.endTagHead(impliedTagToken("head")) - # XXX If we implement a parser for which scripting is disabled we need to - # implement this phase. - # - # class InHeadNoScriptPhase(Phase): + class InHeadNoscriptPhase(Phase): + def __init__(self, parser, tree): + Phase.__init__(self, parser, tree) + + self.startTagHandler = _utils.MethodDispatcher([ + ("html", self.startTagHtml), + (("basefont", "bgsound", "link", "meta", "noframes", "style"), self.startTagBaseLinkCommand), + (("head", "noscript"), self.startTagHeadNoscript), + ]) + self.startTagHandler.default = self.startTagOther + + self.endTagHandler = _utils.MethodDispatcher([ + ("noscript", self.endTagNoscript), + ("br", self.endTagBr), + ]) + self.endTagHandler.default = self.endTagOther + + def processEOF(self): + self.parser.parseError("eof-in-head-noscript") + self.anythingElse() + return True + + def processComment(self, token): + return self.parser.phases["inHead"].processComment(token) + + def processCharacters(self, token): + self.parser.parseError("char-in-head-noscript") + self.anythingElse() + return token + + def processSpaceCharacters(self, token): + return self.parser.phases["inHead"].processSpaceCharacters(token) + + def startTagHtml(self, token): + return self.parser.phases["inBody"].processStartTag(token) + + def startTagBaseLinkCommand(self, token): + return self.parser.phases["inHead"].processStartTag(token) + + def startTagHeadNoscript(self, token): + self.parser.parseError("unexpected-start-tag", {"name": token["name"]}) + + def startTagOther(self, token): + self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]}) + self.anythingElse() + return token + + def endTagNoscript(self, token): + node = self.parser.tree.openElements.pop() + assert node.name == "noscript", "Expected noscript got %s" % node.name + self.parser.phase = self.parser.phases["inHead"] + + def endTagBr(self, token): + self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]}) + self.anythingElse() + return token + + def endTagOther(self, token): + self.parser.parseError("unexpected-end-tag", {"name": token["name"]}) + + def anythingElse(self): + # Caller must raise parse error first! + self.endTagNoscript(impliedTagToken("noscript")) + class AfterHeadPhase(Phase): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("body", self.startTagBody), ("frameset", self.startTagFrameset), @@ -815,8 +813,8 @@ def getPhases(debug): ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"), - self.endTagHtmlBodyBr)]) + self.endTagHandler = _utils.MethodDispatcher([(("body", "html", "br"), + self.endTagHtmlBodyBr)]) self.endTagHandler.default = self.endTagOther def processEOF(self): @@ -874,10 +872,10 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - # Keep a ref to this for special handling of whitespace in <pre> - self.processSpaceCharactersNonPre = self.processSpaceCharacters + # Set this to the default handler + self.processSpaceCharacters = self.processSpaceCharactersNonPre - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), (("base", "basefont", "bgsound", "command", "link", "meta", "script", "style", "title"), @@ -885,7 +883,7 @@ def getPhases(debug): ("body", self.startTagBody), ("frameset", self.startTagFrameset), (("address", "article", "aside", "blockquote", "center", "details", - "details", "dir", "div", "dl", "fieldset", "figcaption", "figure", + "dir", "div", "dl", "fieldset", "figcaption", "figure", "footer", "header", "hgroup", "main", "menu", "nav", "ol", "p", "section", "summary", "ul"), self.startTagCloseP), @@ -911,7 +909,8 @@ def getPhases(debug): ("isindex", self.startTagIsIndex), ("textarea", self.startTagTextarea), ("iframe", self.startTagIFrame), - (("noembed", "noframes", "noscript"), self.startTagRawtext), + ("noscript", self.startTagNoscript), + (("noembed", "noframes"), self.startTagRawtext), ("select", self.startTagSelect), (("rp", "rt"), self.startTagRpRt), (("option", "optgroup"), self.startTagOpt), @@ -923,7 +922,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("body", self.endTagBody), ("html", self.endTagHtml), (("address", "article", "aside", "blockquote", "button", "center", @@ -942,17 +941,9 @@ def getPhases(debug): self.endTagHandler.default = self.endTagOther def isMatchingFormattingElement(self, node1, node2): - if node1.name != node2.name or node1.namespace != node2.namespace: - return False - elif len(node1.attributes) != len(node2.attributes): - return False - else: - attributes1 = sorted(node1.attributes.items()) - attributes2 = sorted(node2.attributes.items()) - for attr1, attr2 in zip(attributes1, attributes2): - if attr1 != attr2: - return False - return True + return (node1.name == node2.name and + node1.namespace == node2.namespace and + node1.attributes == node2.attributes) # helper def addFormattingElement(self, token): @@ -988,8 +979,8 @@ def getPhases(debug): data = token["data"] self.processSpaceCharacters = self.processSpaceCharactersNonPre if (data.startswith("\n") and - self.tree.openElements[-1].name in ("pre", "listing", "textarea") - and not self.tree.openElements[-1].hasContent()): + self.tree.openElements[-1].name in ("pre", "listing", "textarea") and + not self.tree.openElements[-1].hasContent()): data = data[1:] if data: self.tree.reconstructActiveFormattingElements() @@ -1007,7 +998,7 @@ def getPhases(debug): for char in token["data"]])): self.parser.framesetOK = False - def processSpaceCharacters(self, token): + def processSpaceCharactersNonPre(self, token): self.tree.reconstructActiveFormattingElements() self.tree.insertText(token["data"]) @@ -1016,8 +1007,8 @@ def getPhases(debug): def startTagBody(self, token): self.parser.parseError("unexpected-start-tag", {"name": "body"}) - if (len(self.tree.openElements) == 1 - or self.tree.openElements[1].name != "body"): + if (len(self.tree.openElements) == 1 or + self.tree.openElements[1].name != "body"): assert self.parser.innerHTML else: self.parser.framesetOK = False @@ -1232,6 +1223,12 @@ def getPhases(debug): self.parser.framesetOK = False self.startTagRawtext(token) + def startTagNoscript(self, token): + if self.parser.scripting: + self.startTagRawtext(token) + else: + self.startTagOther(token) + def startTagRawtext(self, token): """iframe, noembed noframes, noscript(if scripting enabled)""" self.parser.parseRCDataRawtext(token, "RAWTEXT") @@ -1327,7 +1324,7 @@ def getPhases(debug): # Not sure this is the correct name for the parse error self.parser.parseError( "expected-one-end-tag-but-got-another", - {"expectedName": "body", "gotName": node.name}) + {"gotName": "body", "expectedName": node.name}) break self.parser.phase = self.parser.phases["afterBody"] @@ -1595,9 +1592,9 @@ def getPhases(debug): class TextPhase(Phase): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([]) + self.startTagHandler = _utils.MethodDispatcher([]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("script", self.endTagScript)]) self.endTagHandler.default = self.endTagOther @@ -1629,7 +1626,7 @@ def getPhases(debug): # http://www.whatwg.org/specs/web-apps/current-work/#in-table def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("caption", self.startTagCaption), ("colgroup", self.startTagColgroup), @@ -1643,7 +1640,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("table", self.endTagTable), (("body", "caption", "col", "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr"), self.endTagIgnore) @@ -1820,14 +1817,14 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), (("caption", "col", "colgroup", "tbody", "td", "tfoot", "th", "thead", "tr"), self.startTagTableElement) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("caption", self.endTagCaption), ("table", self.endTagTable), (("body", "col", "colgroup", "html", "tbody", "td", "tfoot", "th", @@ -1892,13 +1889,13 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("col", self.startTagCol) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("colgroup", self.endTagColgroup), ("col", self.endTagCol) ]) @@ -1926,6 +1923,7 @@ def getPhases(debug): def startTagCol(self, token): self.tree.insertElement(token) self.tree.openElements.pop() + token["selfClosingAcknowledged"] = True def startTagOther(self, token): ignoreEndTag = self.ignoreEndTagColgroup() @@ -1955,7 +1953,7 @@ def getPhases(debug): # http://www.whatwg.org/specs/web-apps/current-work/#in-table0 def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("tr", self.startTagTr), (("td", "th"), self.startTagTableCell), @@ -1964,7 +1962,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ (("tbody", "tfoot", "thead"), self.endTagTableRowGroup), ("table", self.endTagTable), (("body", "caption", "col", "colgroup", "html", "td", "th", @@ -2053,7 +2051,7 @@ def getPhases(debug): # http://www.whatwg.org/specs/web-apps/current-work/#in-row def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), (("td", "th"), self.startTagTableCell), (("caption", "col", "colgroup", "tbody", "tfoot", "thead", @@ -2061,7 +2059,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("tr", self.endTagTr), ("table", self.endTagTable), (("tbody", "tfoot", "thead"), self.endTagTableRowGroup), @@ -2142,14 +2140,14 @@ def getPhases(debug): # http://www.whatwg.org/specs/web-apps/current-work/#in-cell def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), (("caption", "col", "colgroup", "tbody", "td", "tfoot", "th", "thead", "tr"), self.startTagTableOther) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ (("td", "th"), self.endTagTableCell), (("body", "caption", "col", "colgroup", "html"), self.endTagIgnore), (("table", "tbody", "tfoot", "thead", "tr"), self.endTagImply) @@ -2218,7 +2216,7 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("option", self.startTagOption), ("optgroup", self.startTagOptgroup), @@ -2228,7 +2226,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("option", self.endTagOption), ("optgroup", self.endTagOptgroup), ("select", self.endTagSelect) @@ -2318,13 +2316,13 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ (("caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th"), self.startTagTable) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ (("caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th"), self.endTagTable) ]) @@ -2445,7 +2443,7 @@ def getPhases(debug): def processEndTag(self, token): nodeIndex = len(self.tree.openElements) - 1 node = self.tree.openElements[-1] - if node.name != token["name"]: + if node.name.translate(asciiUpper2Lower) != token["name"]: self.parser.parseError("unexpected-end-tag", {"name": token["name"]}) while True: @@ -2472,12 +2470,12 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([("html", self.endTagHtml)]) + self.endTagHandler = _utils.MethodDispatcher([("html", self.endTagHtml)]) self.endTagHandler.default = self.endTagOther def processEOF(self): @@ -2520,7 +2518,7 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("frameset", self.startTagFrameset), ("frame", self.startTagFrame), @@ -2528,7 +2526,7 @@ def getPhases(debug): ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("frameset", self.endTagFrameset) ]) self.endTagHandler.default = self.endTagOther @@ -2564,7 +2562,7 @@ def getPhases(debug): self.tree.openElements.pop() if (not self.parser.innerHTML and self.tree.openElements[-1].name != "frameset"): - # If we're not in innerHTML mode and the the current node is not a + # If we're not in innerHTML mode and the current node is not a # "frameset" element (anymore) then switch. self.parser.phase = self.parser.phases["afterFrameset"] @@ -2577,13 +2575,13 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("noframes", self.startTagNoframes) ]) self.startTagHandler.default = self.startTagOther - self.endTagHandler = utils.MethodDispatcher([ + self.endTagHandler = _utils.MethodDispatcher([ ("html", self.endTagHtml) ]) self.endTagHandler.default = self.endTagOther @@ -2613,7 +2611,7 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml) ]) self.startTagHandler.default = self.startTagOther @@ -2651,7 +2649,7 @@ def getPhases(debug): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) - self.startTagHandler = utils.MethodDispatcher([ + self.startTagHandler = _utils.MethodDispatcher([ ("html", self.startTagHtml), ("noframes", self.startTagNoFrames) ]) @@ -2682,13 +2680,14 @@ def getPhases(debug): def processEndTag(self, token): self.parser.parseError("expected-eof-but-got-end-tag", {"name": token["name"]}) + # pylint:enable=unused-argument return { "initial": InitialPhase, "beforeHtml": BeforeHtmlPhase, "beforeHead": BeforeHeadPhase, "inHead": InHeadPhase, - # XXX "inHeadNoscript": InHeadNoScriptPhase, + "inHeadNoscript": InHeadNoscriptPhase, "afterHead": AfterHeadPhase, "inBody": InBodyPhase, "text": TextPhase, @@ -2711,6 +2710,16 @@ def getPhases(debug): } +def adjust_attributes(token, replacements): + if PY3 or _utils.PY27: + needs_adjustment = viewkeys(token['data']) & viewkeys(replacements) + else: + needs_adjustment = frozenset(token['data']) & frozenset(replacements) + if needs_adjustment: + token['data'] = OrderedDict((replacements.get(k, k), v) + for k, v in token['data'].items()) + + def impliedTagToken(name, type="EndTag", attributes=None, selfClosing=False): if attributes is None: diff --git a/pip/_vendor/html5lib/sanitizer.py b/pip/_vendor/html5lib/sanitizer.py deleted file mode 100644 index b714e8c9e..000000000 --- a/pip/_vendor/html5lib/sanitizer.py +++ /dev/null @@ -1,300 +0,0 @@ -from __future__ import absolute_import, division, unicode_literals - -import re -from xml.sax.saxutils import escape, unescape -from six.moves import urllib_parse as urlparse - -from .tokenizer import HTMLTokenizer -from .constants import tokenTypes - - -content_type_rgx = re.compile(r''' - ^ - # Match a content type <application>/<type> - (?P<content_type>[-a-zA-Z0-9.]+/[-a-zA-Z0-9.]+) - # Match any character set and encoding - (?:(?:;charset=(?:[-a-zA-Z0-9]+)(?:;(?:base64))?) - |(?:;(?:base64))?(?:;charset=(?:[-a-zA-Z0-9]+))?) - # Assume the rest is data - ,.* - $ - ''', - re.VERBOSE) - - -class HTMLSanitizerMixin(object): - """ sanitization of XHTML+MathML+SVG and of inline style attributes.""" - - acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', - 'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button', - 'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup', - 'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn', - 'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset', - 'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1', - 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins', - 'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter', - 'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option', - 'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select', - 'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong', - 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot', - 'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video'] - - mathml_elements = ['maction', 'math', 'merror', 'mfrac', 'mi', - 'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom', - 'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub', - 'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder', - 'munderover', 'none'] - - svg_elements = ['a', 'animate', 'animateColor', 'animateMotion', - 'animateTransform', 'clipPath', 'circle', 'defs', 'desc', 'ellipse', - 'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern', - 'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph', - 'mpath', 'path', 'polygon', 'polyline', 'radialGradient', 'rect', - 'set', 'stop', 'svg', 'switch', 'text', 'title', 'tspan', 'use'] - - acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey', - 'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis', - 'background', 'balance', 'bgcolor', 'bgproperties', 'border', - 'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding', - 'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff', - 'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color', - 'cols', 'colspan', 'compact', 'contenteditable', 'controls', 'coords', - 'data', 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default', - 'delay', 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end', - 'face', 'for', 'form', 'frame', 'galleryimg', 'gutter', 'headers', - 'height', 'hidefocus', 'hidden', 'high', 'href', 'hreflang', 'hspace', - 'icon', 'id', 'inputmode', 'ismap', 'keytype', 'label', 'leftspacing', - 'lang', 'list', 'longdesc', 'loop', 'loopcount', 'loopend', - 'loopstart', 'low', 'lowsrc', 'max', 'maxlength', 'media', 'method', - 'min', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'open', - 'optimum', 'pattern', 'ping', 'point-size', 'poster', 'pqg', 'preload', - 'prompt', 'radiogroup', 'readonly', 'rel', 'repeat-max', 'repeat-min', - 'replace', 'required', 'rev', 'rightspacing', 'rows', 'rowspan', - 'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start', - 'step', 'style', 'summary', 'suppress', 'tabindex', 'target', - 'template', 'title', 'toppadding', 'type', 'unselectable', 'usemap', - 'urn', 'valign', 'value', 'variable', 'volume', 'vspace', 'vrml', - 'width', 'wrap', 'xml:lang'] - - mathml_attributes = ['actiontype', 'align', 'columnalign', 'columnalign', - 'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth', - 'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence', - 'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace', - 'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize', - 'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines', - 'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection', - 'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show', - 'xlink:type', 'xmlns', 'xmlns:xlink'] - - svg_attributes = ['accent-height', 'accumulate', 'additive', 'alphabetic', - 'arabic-form', 'ascent', 'attributeName', 'attributeType', - 'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height', - 'class', 'clip-path', 'color', 'color-rendering', 'content', 'cx', - 'cy', 'd', 'dx', 'dy', 'descent', 'display', 'dur', 'end', 'fill', - 'fill-opacity', 'fill-rule', 'font-family', 'font-size', - 'font-stretch', 'font-style', 'font-variant', 'font-weight', 'from', - 'fx', 'fy', 'g1', 'g2', 'glyph-name', 'gradientUnits', 'hanging', - 'height', 'horiz-adv-x', 'horiz-origin-x', 'id', 'ideographic', 'k', - 'keyPoints', 'keySplines', 'keyTimes', 'lang', 'marker-end', - 'marker-mid', 'marker-start', 'markerHeight', 'markerUnits', - 'markerWidth', 'mathematical', 'max', 'min', 'name', 'offset', - 'opacity', 'orient', 'origin', 'overline-position', - 'overline-thickness', 'panose-1', 'path', 'pathLength', 'points', - 'preserveAspectRatio', 'r', 'refX', 'refY', 'repeatCount', - 'repeatDur', 'requiredExtensions', 'requiredFeatures', 'restart', - 'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 'stop-color', - 'stop-opacity', 'strikethrough-position', 'strikethrough-thickness', - 'stroke', 'stroke-dasharray', 'stroke-dashoffset', 'stroke-linecap', - 'stroke-linejoin', 'stroke-miterlimit', 'stroke-opacity', - 'stroke-width', 'systemLanguage', 'target', 'text-anchor', 'to', - 'transform', 'type', 'u1', 'u2', 'underline-position', - 'underline-thickness', 'unicode', 'unicode-range', 'units-per-em', - 'values', 'version', 'viewBox', 'visibility', 'width', 'widths', 'x', - 'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole', - 'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type', - 'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y', - 'y1', 'y2', 'zoomAndPan'] - - attr_val_is_uri = ['href', 'src', 'cite', 'action', 'longdesc', 'poster', 'background', 'datasrc', - 'dynsrc', 'lowsrc', 'ping', 'poster', 'xlink:href', 'xml:base'] - - svg_attr_val_allows_ref = ['clip-path', 'color-profile', 'cursor', 'fill', - 'filter', 'marker', 'marker-start', 'marker-mid', 'marker-end', - 'mask', 'stroke'] - - svg_allow_local_href = ['altGlyph', 'animate', 'animateColor', - 'animateMotion', 'animateTransform', 'cursor', 'feImage', 'filter', - 'linearGradient', 'pattern', 'radialGradient', 'textpath', 'tref', - 'set', 'use'] - - acceptable_css_properties = ['azimuth', 'background-color', - 'border-bottom-color', 'border-collapse', 'border-color', - 'border-left-color', 'border-right-color', 'border-top-color', 'clear', - 'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font', - 'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight', - 'height', 'letter-spacing', 'line-height', 'overflow', 'pause', - 'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness', - 'speak', 'speak-header', 'speak-numeral', 'speak-punctuation', - 'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent', - 'unicode-bidi', 'vertical-align', 'voice-family', 'volume', - 'white-space', 'width'] - - acceptable_css_keywords = ['auto', 'aqua', 'black', 'block', 'blue', - 'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed', - 'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left', - 'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive', - 'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top', - 'transparent', 'underline', 'white', 'yellow'] - - acceptable_svg_properties = ['fill', 'fill-opacity', 'fill-rule', - 'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin', - 'stroke-opacity'] - - acceptable_protocols = ['ed2k', 'ftp', 'http', 'https', 'irc', - 'mailto', 'news', 'gopher', 'nntp', 'telnet', 'webcal', - 'xmpp', 'callto', 'feed', 'urn', 'aim', 'rsync', 'tag', - 'ssh', 'sftp', 'rtsp', 'afs', 'data'] - - acceptable_content_types = ['image/png', 'image/jpeg', 'image/gif', 'image/webp', 'image/bmp', 'text/plain'] - - # subclasses may define their own versions of these constants - allowed_elements = acceptable_elements + mathml_elements + svg_elements - allowed_attributes = acceptable_attributes + mathml_attributes + svg_attributes - allowed_css_properties = acceptable_css_properties - allowed_css_keywords = acceptable_css_keywords - allowed_svg_properties = acceptable_svg_properties - allowed_protocols = acceptable_protocols - allowed_content_types = acceptable_content_types - - # Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and - # stripping out all # attributes not in ALLOWED_ATTRIBUTES. Style - # attributes are parsed, and a restricted set, # specified by - # ALLOWED_CSS_PROPERTIES and ALLOWED_CSS_KEYWORDS, are allowed through. - # attributes in ATTR_VAL_IS_URI are scanned, and only URI schemes specified - # in ALLOWED_PROTOCOLS are allowed. - # - # sanitize_html('<script> do_nasty_stuff() </script>') - # => <script> do_nasty_stuff() </script> - # sanitize_html('<a href="javascript: sucker();">Click here for $100</a>') - # => <a>Click here for $100</a> - def sanitize_token(self, token): - - # accommodate filters which use token_type differently - token_type = token["type"] - if token_type in list(tokenTypes.keys()): - token_type = tokenTypes[token_type] - - if token_type in (tokenTypes["StartTag"], tokenTypes["EndTag"], - tokenTypes["EmptyTag"]): - if token["name"] in self.allowed_elements: - return self.allowed_token(token, token_type) - else: - return self.disallowed_token(token, token_type) - elif token_type == tokenTypes["Comment"]: - pass - else: - return token - - def allowed_token(self, token, token_type): - if "data" in token: - attrs = dict([(name, val) for name, val in - token["data"][::-1] - if name in self.allowed_attributes]) - for attr in self.attr_val_is_uri: - if attr not in attrs: - continue - val_unescaped = re.sub("[`\000-\040\177-\240\s]+", '', - unescape(attrs[attr])).lower() - # remove replacement characters from unescaped characters - val_unescaped = val_unescaped.replace("\ufffd", "") - try: - uri = urlparse.urlparse(val_unescaped) - except ValueError: - uri = None - del attrs[attr] - if uri and uri.scheme: - if uri.scheme not in self.allowed_protocols: - del attrs[attr] - if uri.scheme == 'data': - m = content_type_rgx.match(uri.path) - if not m: - del attrs[attr] - elif m.group('content_type') not in self.allowed_content_types: - del attrs[attr] - - for attr in self.svg_attr_val_allows_ref: - if attr in attrs: - attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)', - ' ', - unescape(attrs[attr])) - if (token["name"] in self.svg_allow_local_href and - 'xlink:href' in attrs and re.search('^\s*[^#\s].*', - attrs['xlink:href'])): - del attrs['xlink:href'] - if 'style' in attrs: - attrs['style'] = self.sanitize_css(attrs['style']) - token["data"] = [[name, val] for name, val in list(attrs.items())] - return token - - def disallowed_token(self, token, token_type): - if token_type == tokenTypes["EndTag"]: - token["data"] = "</%s>" % token["name"] - elif token["data"]: - attrs = ''.join([' %s="%s"' % (k, escape(v)) for k, v in token["data"]]) - token["data"] = "<%s%s>" % (token["name"], attrs) - else: - token["data"] = "<%s>" % token["name"] - if token.get("selfClosing"): - token["data"] = token["data"][:-1] + "/>" - - if token["type"] in list(tokenTypes.keys()): - token["type"] = "Characters" - else: - token["type"] = tokenTypes["Characters"] - - del token["name"] - return token - - def sanitize_css(self, style): - # disallow urls - style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style) - - # gauntlet - if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style): - return '' - if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style): - return '' - - clean = [] - for prop, value in re.findall("([-\w]+)\s*:\s*([^:;]*)", style): - if not value: - continue - if prop.lower() in self.allowed_css_properties: - clean.append(prop + ': ' + value + ';') - elif prop.split('-')[0].lower() in ['background', 'border', 'margin', - 'padding']: - for keyword in value.split(): - if keyword not in self.acceptable_css_keywords and \ - not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword): - break - else: - clean.append(prop + ': ' + value + ';') - elif prop.lower() in self.allowed_svg_properties: - clean.append(prop + ': ' + value + ';') - - return ' '.join(clean) - - -class HTMLSanitizer(HTMLTokenizer, HTMLSanitizerMixin): - def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, - lowercaseElementName=False, lowercaseAttrName=False, parser=None): - # Change case matching defaults as we only output lowercase html anyway - # This solution doesn't seem ideal... - HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet, - lowercaseElementName, lowercaseAttrName, parser=parser) - - def __iter__(self): - for token in HTMLTokenizer.__iter__(self): - token = self.sanitize_token(token) - if token: - yield token diff --git a/pip/_vendor/html5lib/serializer/htmlserializer.py b/pip/_vendor/html5lib/serializer.py index 01d9c5ff6..2fb348151 100644 --- a/pip/_vendor/html5lib/serializer/htmlserializer.py +++ b/pip/_vendor/html5lib/serializer.py @@ -1,79 +1,87 @@ from __future__ import absolute_import, division, unicode_literals from pip._vendor.six import text_type -try: - from functools import reduce -except ImportError: - pass +import re + +from codecs import register_error, xmlcharrefreplace_errors -from ..constants import voidElements, booleanAttributes, spaceCharacters -from ..constants import rcdataElements, entities, xmlEntities -from .. import utils +from .constants import voidElements, booleanAttributes, spaceCharacters +from .constants import rcdataElements, entities, xmlEntities +from . import treewalkers, _utils from xml.sax.saxutils import escape -spaceCharacters = "".join(spaceCharacters) - -try: - from codecs import register_error, xmlcharrefreplace_errors -except ImportError: - unicode_encode_errors = "strict" -else: - unicode_encode_errors = "htmlentityreplace" - - encode_entity_map = {} - is_ucs4 = len("\U0010FFFF") == 1 - for k, v in list(entities.items()): - # skip multi-character entities - if ((is_ucs4 and len(v) > 1) or - (not is_ucs4 and len(v) > 2)): - continue - if v != "&": - if len(v) == 2: - v = utils.surrogatePairToCodepoint(v) - else: - v = ord(v) - if v not in encode_entity_map or k.islower(): - # prefer < over < and similarly for &, >, etc. - encode_entity_map[v] = k - - def htmlentityreplace_errors(exc): - if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)): - res = [] - codepoints = [] - skip = False - for i, c in enumerate(exc.object[exc.start:exc.end]): - if skip: - skip = False - continue - index = i + exc.start - if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]): - codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2]) - skip = True - else: - codepoint = ord(c) - codepoints.append(codepoint) - for cp in codepoints: - e = encode_entity_map.get(cp) - if e: - res.append("&") - res.append(e) - if not e.endswith(";"): - res.append(";") - else: - res.append("&#x%s;" % (hex(cp)[2:])) - return ("".join(res), exc.end) +_quoteAttributeSpecChars = "".join(spaceCharacters) + "\"'=<>`" +_quoteAttributeSpec = re.compile("[" + _quoteAttributeSpecChars + "]") +_quoteAttributeLegacy = re.compile("[" + _quoteAttributeSpecChars + + "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n" + "\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15" + "\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" + "\x20\x2f\x60\xa0\u1680\u180e\u180f\u2000" + "\u2001\u2002\u2003\u2004\u2005\u2006\u2007" + "\u2008\u2009\u200a\u2028\u2029\u202f\u205f" + "\u3000]") + + +_encode_entity_map = {} +_is_ucs4 = len("\U0010FFFF") == 1 +for k, v in list(entities.items()): + # skip multi-character entities + if ((_is_ucs4 and len(v) > 1) or + (not _is_ucs4 and len(v) > 2)): + continue + if v != "&": + if len(v) == 2: + v = _utils.surrogatePairToCodepoint(v) else: - return xmlcharrefreplace_errors(exc) + v = ord(v) + if v not in _encode_entity_map or k.islower(): + # prefer < over < and similarly for &, >, etc. + _encode_entity_map[v] = k + + +def htmlentityreplace_errors(exc): + if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)): + res = [] + codepoints = [] + skip = False + for i, c in enumerate(exc.object[exc.start:exc.end]): + if skip: + skip = False + continue + index = i + exc.start + if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]): + codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2]) + skip = True + else: + codepoint = ord(c) + codepoints.append(codepoint) + for cp in codepoints: + e = _encode_entity_map.get(cp) + if e: + res.append("&") + res.append(e) + if not e.endswith(";"): + res.append(";") + else: + res.append("&#x%s;" % (hex(cp)[2:])) + return ("".join(res), exc.end) + else: + return xmlcharrefreplace_errors(exc) + +register_error("htmlentityreplace", htmlentityreplace_errors) - register_error(unicode_encode_errors, htmlentityreplace_errors) - del register_error +def serialize(input, tree="etree", encoding=None, **serializer_opts): + # XXX: Should we cache this? + walker = treewalkers.getTreeWalker(tree) + s = HTMLSerializer(**serializer_opts) + return s.render(walker(input), encoding) class HTMLSerializer(object): # attribute quoting options - quote_attr_values = False + quote_attr_values = "legacy" # be secure by default quote_char = '"' use_best_quote_char = True @@ -109,9 +117,9 @@ class HTMLSerializer(object): inject_meta_charset=True|False Whether it insert a meta element to define the character set of the document. - quote_attr_values=True|False + quote_attr_values="legacy"|"spec"|"always" Whether to quote attribute values that don't require quoting - per HTML5 parsing rules. + per legacy browser behaviour, when required by the standard, or always. quote_char=u'"'|u"'" Use given quote character for attribute quoting. Default is to use double quote unless attribute value contains a double quote, @@ -147,6 +155,9 @@ class HTMLSerializer(object): .. _html5lib user documentation: http://code.google.com/p/html5lib/wiki/UserDocumentation """ + unexpected_args = frozenset(kwargs) - frozenset(self.options) + if len(unexpected_args) > 0: + raise TypeError("__init__() got an unexpected keyword argument '%s'" % next(iter(unexpected_args))) if 'quote_char' in kwargs: self.use_best_quote_char = False for attr in self.options: @@ -157,7 +168,7 @@ class HTMLSerializer(object): def encode(self, string): assert(isinstance(string, text_type)) if self.encoding: - return string.encode(self.encoding, unicode_encode_errors) + return string.encode(self.encoding, "htmlentityreplace") else: return string @@ -169,28 +180,30 @@ class HTMLSerializer(object): return string def serialize(self, treewalker, encoding=None): + # pylint:disable=too-many-nested-blocks self.encoding = encoding in_cdata = False self.errors = [] if encoding and self.inject_meta_charset: - from ..filters.inject_meta_charset import Filter + from .filters.inject_meta_charset import Filter treewalker = Filter(treewalker, encoding) + # Alphabetical attributes is here under the assumption that none of + # the later filters add or change order of attributes; it needs to be + # before the sanitizer so escaped elements come out correctly + if self.alphabetical_attributes: + from .filters.alphabeticalattributes import Filter + treewalker = Filter(treewalker) # WhitespaceFilter should be used before OptionalTagFilter # for maximum efficiently of this latter filter if self.strip_whitespace: - from ..filters.whitespace import Filter + from .filters.whitespace import Filter treewalker = Filter(treewalker) if self.sanitize: - from ..filters.sanitizer import Filter + from .filters.sanitizer import Filter treewalker = Filter(treewalker) if self.omit_optional_tags: - from ..filters.optionaltags import Filter - treewalker = Filter(treewalker) - # Alphabetical attributes must be last, as other filters - # could add attributes and alter the order - if self.alphabetical_attributes: - from ..filters.alphabeticalattributes import Filter + from .filters.optionaltags import Filter treewalker = Filter(treewalker) for token in treewalker: @@ -229,7 +242,7 @@ class HTMLSerializer(object): in_cdata = True elif in_cdata: self.serializeError("Unexpected child element of a CDATA element") - for (attr_namespace, attr_name), attr_value in token["data"].items(): + for (_, attr_name), attr_value in token["data"].items(): # TODO: Add namespace support here k = attr_name v = attr_value @@ -237,14 +250,18 @@ class HTMLSerializer(object): yield self.encodeStrict(k) if not self.minimize_boolean_attributes or \ - (k not in booleanAttributes.get(name, tuple()) - and k not in booleanAttributes.get("", tuple())): + (k not in booleanAttributes.get(name, tuple()) and + k not in booleanAttributes.get("", tuple())): yield self.encodeStrict("=") - if self.quote_attr_values or not v: + if self.quote_attr_values == "always" or len(v) == 0: quote_attr = True + elif self.quote_attr_values == "spec": + quote_attr = _quoteAttributeSpec.search(v) is not None + elif self.quote_attr_values == "legacy": + quote_attr = _quoteAttributeLegacy.search(v) is not None else: - quote_attr = reduce(lambda x, y: x or (y in v), - spaceCharacters + ">\"'=", False) + raise ValueError("quote_attr_values must be one of: " + "'always', 'spec', or 'legacy'") v = v.replace("&", "&") if self.escape_lt_in_attrs: v = v.replace("<", "<") @@ -312,6 +329,6 @@ class HTMLSerializer(object): raise SerializeError -def SerializeError(Exception): +class SerializeError(Exception): """Error in serialized tree""" pass diff --git a/pip/_vendor/html5lib/serializer/__init__.py b/pip/_vendor/html5lib/serializer/__init__.py deleted file mode 100644 index 8380839a6..000000000 --- a/pip/_vendor/html5lib/serializer/__init__.py +++ /dev/null @@ -1,16 +0,0 @@ -from __future__ import absolute_import, division, unicode_literals - -from .. import treewalkers - -from .htmlserializer import HTMLSerializer - - -def serialize(input, tree="etree", format="html", encoding=None, - **serializer_opts): - # XXX: Should we cache this? - walker = treewalkers.getTreeWalker(tree) - if format == "html": - s = HTMLSerializer(**serializer_opts) - else: - raise ValueError("type must be html") - return s.render(walker(input), encoding) diff --git a/pip/_vendor/html5lib/treeadapters/__init__.py b/pip/_vendor/html5lib/treeadapters/__init__.py index e69de29bb..4f9784660 100644 --- a/pip/_vendor/html5lib/treeadapters/__init__.py +++ b/pip/_vendor/html5lib/treeadapters/__init__.py @@ -0,0 +1,12 @@ +from __future__ import absolute_import, division, unicode_literals + +from . import sax + +__all__ = ["sax"] + +try: + from . import genshi # noqa +except ImportError: + pass +else: + __all__.append("genshi") diff --git a/pip/_vendor/html5lib/treeadapters/genshi.py b/pip/_vendor/html5lib/treeadapters/genshi.py new file mode 100644 index 000000000..04e316df5 --- /dev/null +++ b/pip/_vendor/html5lib/treeadapters/genshi.py @@ -0,0 +1,47 @@ +from __future__ import absolute_import, division, unicode_literals + +from genshi.core import QName, Attrs +from genshi.core import START, END, TEXT, COMMENT, DOCTYPE + + +def to_genshi(walker): + text = [] + for token in walker: + type = token["type"] + if type in ("Characters", "SpaceCharacters"): + text.append(token["data"]) + elif text: + yield TEXT, "".join(text), (None, -1, -1) + text = [] + + if type in ("StartTag", "EmptyTag"): + if token["namespace"]: + name = "{%s}%s" % (token["namespace"], token["name"]) + else: + name = token["name"] + attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value) + for attr, value in token["data"].items()]) + yield (START, (QName(name), attrs), (None, -1, -1)) + if type == "EmptyTag": + type = "EndTag" + + if type == "EndTag": + if token["namespace"]: + name = "{%s}%s" % (token["namespace"], token["name"]) + else: + name = token["name"] + + yield END, QName(name), (None, -1, -1) + + elif type == "Comment": + yield COMMENT, token["data"], (None, -1, -1) + + elif type == "Doctype": + yield DOCTYPE, (token["name"], token["publicId"], + token["systemId"]), (None, -1, -1) + + else: + pass # FIXME: What to do? + + if text: + yield TEXT, "".join(text), (None, -1, -1) diff --git a/pip/_vendor/html5lib/treebuilders/__init__.py b/pip/_vendor/html5lib/treebuilders/__init__.py index 6a6b2a4c4..e23288474 100644 --- a/pip/_vendor/html5lib/treebuilders/__init__.py +++ b/pip/_vendor/html5lib/treebuilders/__init__.py @@ -28,7 +28,7 @@ to the format used in the unittests from __future__ import absolute_import, division, unicode_literals -from ..utils import default_etree +from .._utils import default_etree treeBuilderCache = {} diff --git a/pip/_vendor/html5lib/treebuilders/_base.py b/pip/_vendor/html5lib/treebuilders/base.py index 970c9adb6..9798f7cfb 100644 --- a/pip/_vendor/html5lib/treebuilders/_base.py +++ b/pip/_vendor/html5lib/treebuilders/base.py @@ -126,6 +126,7 @@ class TreeBuilder(object): commentClass - the class to use for comments doctypeClass - the class to use for doctypes """ + # pylint:disable=not-callable # Document class documentClass = None @@ -166,12 +167,17 @@ class TreeBuilder(object): # If we pass a node in we match that. if we pass a string # match any node with that name exactNode = hasattr(target, "nameTuple") + if not exactNode: + if isinstance(target, text_type): + target = (namespaces["html"], target) + assert isinstance(target, tuple) listElements, invert = listElementsMap[variant] for node in reversed(self.openElements): - if (node.name == target and not exactNode or - node == target and exactNode): + if exactNode and node == target: + return True + elif not exactNode and node.nameTuple == target: return True elif (invert ^ (node.nameTuple in listElements)): return False @@ -353,8 +359,8 @@ class TreeBuilder(object): def generateImpliedEndTags(self, exclude=None): name = self.openElements[-1].name # XXX td, th and tr are not actually needed - if (name in frozenset(("dd", "dt", "li", "option", "optgroup", "p", "rp", "rt")) - and name != exclude): + if (name in frozenset(("dd", "dt", "li", "option", "optgroup", "p", "rp", "rt")) and + name != exclude): self.openElements.pop() # XXX This is not entirely what the specification says. We should # investigate it more closely. diff --git a/pip/_vendor/html5lib/treebuilders/dom.py b/pip/_vendor/html5lib/treebuilders/dom.py index 234233b79..dcfac220b 100644 --- a/pip/_vendor/html5lib/treebuilders/dom.py +++ b/pip/_vendor/html5lib/treebuilders/dom.py @@ -1,54 +1,62 @@ from __future__ import absolute_import, division, unicode_literals +from collections import MutableMapping from xml.dom import minidom, Node import weakref -from . import _base +from . import base from .. import constants from ..constants import namespaces -from ..utils import moduleFactoryFactory +from .._utils import moduleFactoryFactory def getDomBuilder(DomImplementation): Dom = DomImplementation - class AttrList(object): + class AttrList(MutableMapping): def __init__(self, element): self.element = element def __iter__(self): - return list(self.element.attributes.items()).__iter__() + return iter(self.element.attributes.keys()) def __setitem__(self, name, value): - self.element.setAttribute(name, value) + if isinstance(name, tuple): + raise NotImplementedError + else: + attr = self.element.ownerDocument.createAttribute(name) + attr.value = value + self.element.attributes[name] = attr def __len__(self): - return len(list(self.element.attributes.items())) + return len(self.element.attributes) def items(self): - return [(item[0], item[1]) for item in - list(self.element.attributes.items())] + return list(self.element.attributes.items()) - def keys(self): - return list(self.element.attributes.keys()) + def values(self): + return list(self.element.attributes.values()) def __getitem__(self, name): - return self.element.getAttribute(name) + if isinstance(name, tuple): + raise NotImplementedError + else: + return self.element.attributes[name].value - def __contains__(self, name): + def __delitem__(self, name): if isinstance(name, tuple): raise NotImplementedError else: - return self.element.hasAttribute(name) + del self.element.attributes[name] - class NodeBuilder(_base.Node): + class NodeBuilder(base.Node): def __init__(self, element): - _base.Node.__init__(self, element.nodeName) + base.Node.__init__(self, element.nodeName) self.element = element - namespace = property(lambda self: hasattr(self.element, "namespaceURI") - and self.element.namespaceURI or None) + namespace = property(lambda self: hasattr(self.element, "namespaceURI") and + self.element.namespaceURI or None) def appendChild(self, node): node.parent = self @@ -109,7 +117,7 @@ def getDomBuilder(DomImplementation): nameTuple = property(getNameTuple) - class TreeBuilder(_base.TreeBuilder): + class TreeBuilder(base.TreeBuilder): # pylint:disable=unused-variable def documentClass(self): self.dom = Dom.getDOMImplementation().createDocument(None, None, None) return weakref.proxy(self) @@ -149,15 +157,16 @@ def getDomBuilder(DomImplementation): return self.dom def getFragment(self): - return _base.TreeBuilder.getFragment(self).element + return base.TreeBuilder.getFragment(self).element def insertText(self, data, parent=None): data = data if parent != self: - _base.TreeBuilder.insertText(self, data, parent) + base.TreeBuilder.insertText(self, data, parent) else: # HACK: allow text nodes as children of the document node if hasattr(self.dom, '_child_node_types'): + # pylint:disable=protected-access if Node.TEXT_NODE not in self.dom._child_node_types: self.dom._child_node_types = list(self.dom._child_node_types) self.dom._child_node_types.append(Node.TEXT_NODE) diff --git a/pip/_vendor/html5lib/treebuilders/etree.py b/pip/_vendor/html5lib/treebuilders/etree.py index 48fead7e2..0dedf4416 100644 --- a/pip/_vendor/html5lib/treebuilders/etree.py +++ b/pip/_vendor/html5lib/treebuilders/etree.py @@ -1,13 +1,15 @@ from __future__ import absolute_import, division, unicode_literals +# pylint:disable=protected-access + from pip._vendor.six import text_type import re -from . import _base -from .. import ihatexml +from . import base +from .. import _ihatexml from .. import constants from ..constants import namespaces -from ..utils import moduleFactoryFactory +from .._utils import moduleFactoryFactory tag_regexp = re.compile("{([^}]*)}(.*)") @@ -16,7 +18,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False): ElementTree = ElementTreeImplementation ElementTreeCommentType = ElementTree.Comment("asd").tag - class Element(_base.Node): + class Element(base.Node): def __init__(self, name, namespace=None): self._name = name self._namespace = namespace @@ -98,6 +100,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False): node.parent = self def removeChild(self, node): + self._childNodes.remove(node) self._element.remove(node._element) node.parent = None @@ -139,7 +142,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False): if self._element.text is not None: newParent._element.text += self._element.text self._element.text = "" - _base.Node.reparentChildren(self, newParent) + base.Node.reparentChildren(self, newParent) class Comment(Element): def __init__(self, data): @@ -253,10 +256,10 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False): return "\n".join(rv) - def tostring(element): + def tostring(element): # pylint:disable=unused-variable """Serialize an element and its child nodes to a string""" rv = [] - filter = ihatexml.InfosetFilter() + filter = _ihatexml.InfosetFilter() def serializeElement(element): if isinstance(element, ElementTree.ElementTree): @@ -307,7 +310,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False): return "".join(rv) - class TreeBuilder(_base.TreeBuilder): + class TreeBuilder(base.TreeBuilder): # pylint:disable=unused-variable documentClass = Document doctypeClass = DocumentType elementClass = Element @@ -329,7 +332,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False): return self.document._element.find("html") def getFragment(self): - return _base.TreeBuilder.getFragment(self)._element + return base.TreeBuilder.getFragment(self)._element return locals() diff --git a/pip/_vendor/html5lib/treebuilders/etree_lxml.py b/pip/_vendor/html5lib/treebuilders/etree_lxml.py index 35d08efaa..908820c08 100644 --- a/pip/_vendor/html5lib/treebuilders/etree_lxml.py +++ b/pip/_vendor/html5lib/treebuilders/etree_lxml.py @@ -10,16 +10,17 @@ When any of these things occur, we emit a DataLossWarning """ from __future__ import absolute_import, division, unicode_literals +# pylint:disable=protected-access import warnings import re import sys -from . import _base +from . import base from ..constants import DataLossWarning from .. import constants from . import etree as etree_builders -from .. import ihatexml +from .. import _ihatexml import lxml.etree as etree @@ -53,8 +54,7 @@ class Document(object): def testSerializer(element): rv = [] - finalText = None - infosetFilter = ihatexml.InfosetFilter() + infosetFilter = _ihatexml.InfosetFilter(preventDoubleDashComments=True) def serializeElement(element, indent=0): if not hasattr(element, "tag"): @@ -79,7 +79,7 @@ def testSerializer(element): next_element = next_element.getnext() elif isinstance(element, str) or isinstance(element, bytes): # Text in a fragment - assert isinstance(element, str) or sys.version_info.major == 2 + assert isinstance(element, str) or sys.version_info[0] == 2 rv.append("|%s\"%s\"" % (' ' * indent, element)) else: # Fragment case @@ -128,16 +128,12 @@ def testSerializer(element): rv.append("|%s\"%s\"" % (' ' * (indent - 2), element.tail)) serializeElement(element, 0) - if finalText is not None: - rv.append("|%s\"%s\"" % (' ' * 2, finalText)) - return "\n".join(rv) def tostring(element): """Serialize an element and its child nodes to a string""" rv = [] - finalText = None def serializeElement(element): if not hasattr(element, "tag"): @@ -173,13 +169,10 @@ def tostring(element): serializeElement(element) - if finalText is not None: - rv.append("%s\"" % (' ' * 2, finalText)) - return "".join(rv) -class TreeBuilder(_base.TreeBuilder): +class TreeBuilder(base.TreeBuilder): documentClass = Document doctypeClass = DocumentType elementClass = None @@ -189,13 +182,15 @@ class TreeBuilder(_base.TreeBuilder): def __init__(self, namespaceHTMLElements, fullTree=False): builder = etree_builders.getETreeModule(etree, fullTree=fullTree) - infosetFilter = self.infosetFilter = ihatexml.InfosetFilter() + infosetFilter = self.infosetFilter = _ihatexml.InfosetFilter(preventDoubleDashComments=True) self.namespaceHTMLElements = namespaceHTMLElements class Attributes(dict): - def __init__(self, element, value={}): + def __init__(self, element, value=None): + if value is None: + value = {} self._element = element - dict.__init__(self, value) + dict.__init__(self, value) # pylint:disable=non-parent-init-called for key, value in self.items(): if isinstance(key, tuple): name = "{%s}%s" % (key[2], infosetFilter.coerceAttribute(key[1])) @@ -257,12 +252,12 @@ class TreeBuilder(_base.TreeBuilder): data = property(_getData, _setData) self.elementClass = Element - self.commentClass = builder.Comment + self.commentClass = Comment # self.fragmentClass = builder.DocumentFragment - _base.TreeBuilder.__init__(self, namespaceHTMLElements) + base.TreeBuilder.__init__(self, namespaceHTMLElements) def reset(self): - _base.TreeBuilder.reset(self) + base.TreeBuilder.reset(self) self.insertComment = self.insertCommentInitial self.initial_comments = [] self.doctype = None @@ -303,19 +298,21 @@ class TreeBuilder(_base.TreeBuilder): self.doctype = doctype def insertCommentInitial(self, data, parent=None): + assert parent is None or parent is self.document + assert self.document._elementTree is None self.initial_comments.append(data) def insertCommentMain(self, data, parent=None): if (parent == self.document and self.document._elementTree.getroot()[-1].tag == comment_type): - warnings.warn("lxml cannot represent adjacent comments beyond the root elements", DataLossWarning) + warnings.warn("lxml cannot represent adjacent comments beyond the root elements", DataLossWarning) super(TreeBuilder, self).insertComment(data, parent) def insertRoot(self, token): """Create the document root""" # Because of the way libxml2 works, it doesn't seem to be possible to # alter information like the doctype after the tree has been parsed. - # Therefore we need to use the built-in parser to create our iniial + # Therefore we need to use the built-in parser to create our initial # tree, after which we can add elements like normal docStr = "" if self.doctype: @@ -344,7 +341,8 @@ class TreeBuilder(_base.TreeBuilder): # Append the initial comments: for comment_token in self.initial_comments: - root.addprevious(etree.Comment(comment_token["data"])) + comment = self.commentClass(comment_token["data"]) + root.addprevious(comment._element) # Create the root document and add the ElementTree to it self.document = self.documentClass() diff --git a/pip/_vendor/html5lib/treewalkers/__init__.py b/pip/_vendor/html5lib/treewalkers/__init__.py index 20b91b114..9e19a5595 100644 --- a/pip/_vendor/html5lib/treewalkers/__init__.py +++ b/pip/_vendor/html5lib/treewalkers/__init__.py @@ -10,13 +10,10 @@ returning an iterator generating tokens. from __future__ import absolute_import, division, unicode_literals -__all__ = ["getTreeWalker", "pprint", "dom", "etree", "genshistream", "lxmletree", - "pulldom"] - -import sys - from .. import constants -from ..utils import default_etree +from .._utils import default_etree + +__all__ = ["getTreeWalker", "pprint", "dom", "etree", "genshi", "etree_lxml"] treeWalkerCache = {} @@ -24,34 +21,33 @@ treeWalkerCache = {} def getTreeWalker(treeType, implementation=None, **kwargs): """Get a TreeWalker class for various types of tree with built-in support - treeType - the name of the tree type required (case-insensitive). Supported - values are: + Args: + treeType (str): the name of the tree type required (case-insensitive). + Supported values are: - "dom" - The xml.dom.minidom DOM implementation - "pulldom" - The xml.dom.pulldom event stream - "etree" - A generic walker for tree implementations exposing an - elementtree-like interface (known to work with - ElementTree, cElementTree and lxml.etree). - "lxml" - Optimized walker for lxml.etree - "genshi" - a Genshi stream + - "dom": The xml.dom.minidom DOM implementation + - "etree": A generic walker for tree implementations exposing an + elementtree-like interface (known to work with + ElementTree, cElementTree and lxml.etree). + - "lxml": Optimized walker for lxml.etree + - "genshi": a Genshi stream - implementation - (Currently applies to the "etree" tree type only). A module - implementing the tree type e.g. xml.etree.ElementTree or - cElementTree.""" + Implementation: A module implementing the tree type e.g. + xml.etree.ElementTree or cElementTree (Currently applies to the + "etree" tree type only). + """ treeType = treeType.lower() if treeType not in treeWalkerCache: - if treeType in ("dom", "pulldom"): - name = "%s.%s" % (__name__, treeType) - __import__(name) - mod = sys.modules[name] - treeWalkerCache[treeType] = mod.TreeWalker + if treeType == "dom": + from . import dom + treeWalkerCache[treeType] = dom.TreeWalker elif treeType == "genshi": - from . import genshistream - treeWalkerCache[treeType] = genshistream.TreeWalker + from . import genshi + treeWalkerCache[treeType] = genshi.TreeWalker elif treeType == "lxml": - from . import lxmletree - treeWalkerCache[treeType] = lxmletree.TreeWalker + from . import etree_lxml + treeWalkerCache[treeType] = etree_lxml.TreeWalker elif treeType == "etree": from . import etree if implementation is None: diff --git a/pip/_vendor/html5lib/treewalkers/_base.py b/pip/_vendor/html5lib/treewalkers/base.py index 42a59a4bf..36e1ba242 100644 --- a/pip/_vendor/html5lib/treewalkers/_base.py +++ b/pip/_vendor/html5lib/treewalkers/base.py @@ -1,11 +1,11 @@ from __future__ import absolute_import, division, unicode_literals -from pip._vendor.six import text_type, string_types + +from xml.dom import Node +from ..constants import namespaces, voidElements, spaceCharacters __all__ = ["DOCUMENT", "DOCTYPE", "TEXT", "ELEMENT", "COMMENT", "ENTITY", "UNKNOWN", "TreeWalker", "NonRecursiveTreeWalker"] -from xml.dom import Node - DOCUMENT = Node.DOCUMENT_NODE DOCTYPE = Node.DOCUMENT_TYPE_NODE TEXT = Node.TEXT_NODE @@ -14,28 +14,9 @@ COMMENT = Node.COMMENT_NODE ENTITY = Node.ENTITY_NODE UNKNOWN = "<#UNKNOWN#>" -from ..constants import voidElements, spaceCharacters spaceCharacters = "".join(spaceCharacters) -def to_text(s, blank_if_none=True): - """Wrapper around six.text_type to convert None to empty string""" - if s is None: - if blank_if_none: - return "" - else: - return None - elif isinstance(s, text_type): - return s - else: - return text_type(s) - - -def is_text_or_none(string): - """Wrapper around isinstance(string_types) or is None""" - return string is None or isinstance(string, string_types) - - class TreeWalker(object): def __init__(self, tree): self.tree = tree @@ -47,47 +28,25 @@ class TreeWalker(object): return {"type": "SerializeError", "data": msg} def emptyTag(self, namespace, name, attrs, hasChildren=False): - assert namespace is None or isinstance(namespace, string_types), type(namespace) - assert isinstance(name, string_types), type(name) - assert all((namespace is None or isinstance(namespace, string_types)) and - isinstance(name, string_types) and - isinstance(value, string_types) - for (namespace, name), value in attrs.items()) - - yield {"type": "EmptyTag", "name": to_text(name, False), - "namespace": to_text(namespace), + yield {"type": "EmptyTag", "name": name, + "namespace": namespace, "data": attrs} if hasChildren: yield self.error("Void element has children") def startTag(self, namespace, name, attrs): - assert namespace is None or isinstance(namespace, string_types), type(namespace) - assert isinstance(name, string_types), type(name) - assert all((namespace is None or isinstance(namespace, string_types)) and - isinstance(name, string_types) and - isinstance(value, string_types) - for (namespace, name), value in attrs.items()) - return {"type": "StartTag", - "name": text_type(name), - "namespace": to_text(namespace), - "data": dict(((to_text(namespace, False), to_text(name)), - to_text(value, False)) - for (namespace, name), value in attrs.items())} + "name": name, + "namespace": namespace, + "data": attrs} def endTag(self, namespace, name): - assert namespace is None or isinstance(namespace, string_types), type(namespace) - assert isinstance(name, string_types), type(namespace) - return {"type": "EndTag", - "name": to_text(name, False), - "namespace": to_text(namespace), - "data": {}} + "name": name, + "namespace": namespace} def text(self, data): - assert isinstance(data, string_types), type(data) - - data = to_text(data) + data = data middle = data.lstrip(spaceCharacters) left = data[:len(data) - len(middle)] if left: @@ -101,25 +60,16 @@ class TreeWalker(object): yield {"type": "SpaceCharacters", "data": right} def comment(self, data): - assert isinstance(data, string_types), type(data) - - return {"type": "Comment", "data": text_type(data)} - - def doctype(self, name, publicId=None, systemId=None, correct=True): - assert is_text_or_none(name), type(name) - assert is_text_or_none(publicId), type(publicId) - assert is_text_or_none(systemId), type(systemId) + return {"type": "Comment", "data": data} + def doctype(self, name, publicId=None, systemId=None): return {"type": "Doctype", - "name": to_text(name), - "publicId": to_text(publicId), - "systemId": to_text(systemId), - "correct": to_text(correct)} + "name": name, + "publicId": publicId, + "systemId": systemId} def entity(self, name): - assert isinstance(name, string_types), type(name) - - return {"type": "Entity", "name": text_type(name)} + return {"type": "Entity", "name": name} def unknown(self, nodeType): return self.error("Unknown node type: " + nodeType) @@ -154,7 +104,7 @@ class NonRecursiveTreeWalker(TreeWalker): elif type == ELEMENT: namespace, name, attributes, hasChildren = details - if name in voidElements: + if (not namespace or namespace == namespaces["html"]) and name in voidElements: for token in self.emptyTag(namespace, name, attributes, hasChildren): yield token @@ -187,7 +137,7 @@ class NonRecursiveTreeWalker(TreeWalker): type, details = details[0], details[1:] if type == ELEMENT: namespace, name, attributes, hasChildren = details - if name not in voidElements: + if (namespace and namespace != namespaces["html"]) or name not in voidElements: yield self.endTag(namespace, name) if self.tree is currentNode: currentNode = None diff --git a/pip/_vendor/html5lib/treewalkers/dom.py b/pip/_vendor/html5lib/treewalkers/dom.py index ac4dcf31b..b0c89b001 100644 --- a/pip/_vendor/html5lib/treewalkers/dom.py +++ b/pip/_vendor/html5lib/treewalkers/dom.py @@ -2,16 +2,16 @@ from __future__ import absolute_import, division, unicode_literals from xml.dom import Node -from . import _base +from . import base -class TreeWalker(_base.NonRecursiveTreeWalker): +class TreeWalker(base.NonRecursiveTreeWalker): def getNodeDetails(self, node): if node.nodeType == Node.DOCUMENT_TYPE_NODE: - return _base.DOCTYPE, node.name, node.publicId, node.systemId + return base.DOCTYPE, node.name, node.publicId, node.systemId elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE): - return _base.TEXT, node.nodeValue + return base.TEXT, node.nodeValue elif node.nodeType == Node.ELEMENT_NODE: attrs = {} @@ -21,17 +21,17 @@ class TreeWalker(_base.NonRecursiveTreeWalker): attrs[(attr.namespaceURI, attr.localName)] = attr.value else: attrs[(None, attr.name)] = attr.value - return (_base.ELEMENT, node.namespaceURI, node.nodeName, + return (base.ELEMENT, node.namespaceURI, node.nodeName, attrs, node.hasChildNodes()) elif node.nodeType == Node.COMMENT_NODE: - return _base.COMMENT, node.nodeValue + return base.COMMENT, node.nodeValue elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE): - return (_base.DOCUMENT,) + return (base.DOCUMENT,) else: - return _base.UNKNOWN, node.nodeType + return base.UNKNOWN, node.nodeType def getFirstChild(self, node): return node.firstChild diff --git a/pip/_vendor/html5lib/treewalkers/etree.py b/pip/_vendor/html5lib/treewalkers/etree.py index 716342551..d9ae3cccd 100644 --- a/pip/_vendor/html5lib/treewalkers/etree.py +++ b/pip/_vendor/html5lib/treewalkers/etree.py @@ -10,10 +10,10 @@ except ImportError: import re -from pip._vendor.six import text_type +from pip._vendor. import string_types -from . import _base -from ..utils import moduleFactoryFactory +from . import base +from .._utils import moduleFactoryFactory tag_regexp = re.compile("{([^}]*)}(.*)") @@ -22,7 +22,7 @@ def getETreeBuilder(ElementTreeImplementation): ElementTree = ElementTreeImplementation ElementTreeCommentType = ElementTree.Comment("asd").tag - class TreeWalker(_base.NonRecursiveTreeWalker): + class TreeWalker(base.NonRecursiveTreeWalker): # pylint:disable=unused-variable """Given the particular ElementTree representation, this implementation, to avoid using recursion, returns "nodes" as tuples with the following content: @@ -38,9 +38,9 @@ def getETreeBuilder(ElementTreeImplementation): """ def getNodeDetails(self, node): if isinstance(node, tuple): # It might be the root Element - elt, key, parents, flag = node + elt, _, _, flag = node if flag in ("text", "tail"): - return _base.TEXT, getattr(elt, flag) + return base.TEXT, getattr(elt, flag) else: node = elt @@ -48,14 +48,14 @@ def getETreeBuilder(ElementTreeImplementation): node = node.getroot() if node.tag in ("DOCUMENT_ROOT", "DOCUMENT_FRAGMENT"): - return (_base.DOCUMENT,) + return (base.DOCUMENT,) elif node.tag == "<!DOCTYPE>": - return (_base.DOCTYPE, node.text, + return (base.DOCTYPE, node.text, node.get("publicId"), node.get("systemId")) elif node.tag == ElementTreeCommentType: - return _base.COMMENT, node.text + return base.COMMENT, node.text else: assert isinstance(node.tag, string_types), type(node.tag) @@ -73,7 +73,7 @@ def getETreeBuilder(ElementTreeImplementation): attrs[(match.group(1), match.group(2))] = value else: attrs[(None, name)] = value - return (_base.ELEMENT, namespace, tag, + return (base.ELEMENT, namespace, tag, attrs, len(node) or node.text) def getFirstChild(self, node): @@ -129,6 +129,7 @@ def getETreeBuilder(ElementTreeImplementation): if not parents: return parent else: + assert list(parents[-1]).count(parent) == 1 return parent, list(parents[-1]).index(parent), parents, None return locals() diff --git a/pip/_vendor/html5lib/treewalkers/lxmletree.py b/pip/_vendor/html5lib/treewalkers/etree_lxml.py index a4854869d..e81ddf33b 100644 --- a/pip/_vendor/html5lib/treewalkers/lxmletree.py +++ b/pip/_vendor/html5lib/treewalkers/etree_lxml.py @@ -4,9 +4,9 @@ from pip._vendor.six import text_type from lxml import etree from ..treebuilders.etree import tag_regexp -from . import _base +from . import base -from .. import ihatexml +from .. import _ihatexml def ensure_str(s): @@ -15,20 +15,27 @@ def ensure_str(s): elif isinstance(s, text_type): return s else: - return s.decode("utf-8", "strict") + return s.decode("ascii", "strict") class Root(object): def __init__(self, et): self.elementtree = et self.children = [] - if et.docinfo.internalDTD: - self.children.append(Doctype(self, - ensure_str(et.docinfo.root_name), - ensure_str(et.docinfo.public_id), - ensure_str(et.docinfo.system_url))) - root = et.getroot() - node = root + + try: + if et.docinfo.internalDTD: + self.children.append(Doctype(self, + ensure_str(et.docinfo.root_name), + ensure_str(et.docinfo.public_id), + ensure_str(et.docinfo.system_url))) + except AttributeError: + pass + + try: + node = et.getroot() + except AttributeError: + node = et while node.getprevious() is not None: node = node.getprevious() @@ -115,35 +122,38 @@ class FragmentWrapper(object): return len(self.obj) -class TreeWalker(_base.NonRecursiveTreeWalker): +class TreeWalker(base.NonRecursiveTreeWalker): def __init__(self, tree): - if hasattr(tree, "getroot"): - tree = Root(tree) - elif isinstance(tree, list): + # pylint:disable=redefined-variable-type + if isinstance(tree, list): + self.fragmentChildren = set(tree) tree = FragmentRoot(tree) - _base.NonRecursiveTreeWalker.__init__(self, tree) - self.filter = ihatexml.InfosetFilter() + else: + self.fragmentChildren = set() + tree = Root(tree) + base.NonRecursiveTreeWalker.__init__(self, tree) + self.filter = _ihatexml.InfosetFilter() def getNodeDetails(self, node): if isinstance(node, tuple): # Text node node, key = node assert key in ("text", "tail"), "Text nodes are text or tail, found %s" % key - return _base.TEXT, ensure_str(getattr(node, key)) + return base.TEXT, ensure_str(getattr(node, key)) elif isinstance(node, Root): - return (_base.DOCUMENT,) + return (base.DOCUMENT,) elif isinstance(node, Doctype): - return _base.DOCTYPE, node.name, node.public_id, node.system_id + return base.DOCTYPE, node.name, node.public_id, node.system_id elif isinstance(node, FragmentWrapper) and not hasattr(node, "tag"): - return _base.TEXT, node.obj + return base.TEXT, ensure_str(node.obj) elif node.tag == etree.Comment: - return _base.COMMENT, ensure_str(node.text) + return base.COMMENT, ensure_str(node.text) elif node.tag == etree.Entity: - return _base.ENTITY, ensure_str(node.text)[1:-1] # strip &; + return base.ENTITY, ensure_str(node.text)[1:-1] # strip &; else: # This is assumed to be an ordinary element @@ -162,7 +172,7 @@ class TreeWalker(_base.NonRecursiveTreeWalker): attrs[(match.group(1), match.group(2))] = value else: attrs[(None, name)] = value - return (_base.ELEMENT, namespace, self.filter.fromXmlName(tag), + return (base.ELEMENT, namespace, self.filter.fromXmlName(tag), attrs, len(node) > 0 or node.text) def getFirstChild(self, node): @@ -197,5 +207,7 @@ class TreeWalker(_base.NonRecursiveTreeWalker): if key == "text": return node # else: fallback to "normal" processing + elif node in self.fragmentChildren: + return None return node.getparent() diff --git a/pip/_vendor/html5lib/treewalkers/genshistream.py b/pip/_vendor/html5lib/treewalkers/genshi.py index f559c45d0..7483be27d 100644 --- a/pip/_vendor/html5lib/treewalkers/genshistream.py +++ b/pip/_vendor/html5lib/treewalkers/genshi.py @@ -4,12 +4,12 @@ from genshi.core import QName from genshi.core import START, END, XML_NAMESPACE, DOCTYPE, TEXT from genshi.core import START_NS, END_NS, START_CDATA, END_CDATA, PI, COMMENT -from . import _base +from . import base from ..constants import voidElements, namespaces -class TreeWalker(_base.TreeWalker): +class TreeWalker(base.TreeWalker): def __iter__(self): # Buffer the events so we can pass in the following one previous = None @@ -25,7 +25,7 @@ class TreeWalker(_base.TreeWalker): yield token def tokens(self, event, next): - kind, data, pos = event + kind, data, _ = event if kind == START: tag, attribs = data name = tag.localname @@ -39,8 +39,8 @@ class TreeWalker(_base.TreeWalker): if namespace == namespaces["html"] and name in voidElements: for token in self.emptyTag(namespace, name, converted_attribs, - not next or next[0] != END - or next[1] != tag): + not next or next[0] != END or + next[1] != tag): yield token else: yield self.startTag(namespace, name, converted_attribs) @@ -48,7 +48,7 @@ class TreeWalker(_base.TreeWalker): elif kind == END: name = data.localname namespace = data.namespace - if name not in voidElements: + if namespace != namespaces["html"] or name not in voidElements: yield self.endTag(namespace, name) elif kind == COMMENT: diff --git a/pip/_vendor/html5lib/treewalkers/pulldom.py b/pip/_vendor/html5lib/treewalkers/pulldom.py deleted file mode 100644 index 0b0f515fe..000000000 --- a/pip/_vendor/html5lib/treewalkers/pulldom.py +++ /dev/null @@ -1,63 +0,0 @@ -from __future__ import absolute_import, division, unicode_literals - -from xml.dom.pulldom import START_ELEMENT, END_ELEMENT, \ - COMMENT, IGNORABLE_WHITESPACE, CHARACTERS - -from . import _base - -from ..constants import voidElements - - -class TreeWalker(_base.TreeWalker): - def __iter__(self): - ignore_until = None - previous = None - for event in self.tree: - if previous is not None and \ - (ignore_until is None or previous[1] is ignore_until): - if previous[1] is ignore_until: - ignore_until = None - for token in self.tokens(previous, event): - yield token - if token["type"] == "EmptyTag": - ignore_until = previous[1] - previous = event - if ignore_until is None or previous[1] is ignore_until: - for token in self.tokens(previous, None): - yield token - elif ignore_until is not None: - raise ValueError("Illformed DOM event stream: void element without END_ELEMENT") - - def tokens(self, event, next): - type, node = event - if type == START_ELEMENT: - name = node.nodeName - namespace = node.namespaceURI - attrs = {} - for attr in list(node.attributes.keys()): - attr = node.getAttributeNode(attr) - attrs[(attr.namespaceURI, attr.localName)] = attr.value - if name in voidElements: - for token in self.emptyTag(namespace, - name, - attrs, - not next or next[1] is not node): - yield token - else: - yield self.startTag(namespace, name, attrs) - - elif type == END_ELEMENT: - name = node.nodeName - namespace = node.namespaceURI - if name not in voidElements: - yield self.endTag(namespace, name) - - elif type == COMMENT: - yield self.comment(node.nodeValue) - - elif type in (IGNORABLE_WHITESPACE, CHARACTERS): - for token in self.text(node.nodeValue): - yield token - - else: - yield self.unknown(type) diff --git a/pip/_vendor/ipaddress.py b/pip/_vendor/ipaddress.py index 7657fc8fb..9cf71a744 100644 --- a/pip/_vendor/ipaddress.py +++ b/pip/_vendor/ipaddress.py @@ -14,7 +14,7 @@ from __future__ import unicode_literals import itertools import struct -__version__ = '1.0.16' +__version__ = '1.0.17' # Compatibility functions _compat_int_types = (int,) @@ -759,12 +759,12 @@ class _BaseNetwork(_IPAddressBase): broadcast = int(self.broadcast_address) if n >= 0: if network + n > broadcast: - raise IndexError + raise IndexError('address out of range') return self._address_class(network + n) else: n += 1 if broadcast + n < network: - raise IndexError + raise IndexError('address out of range') return self._address_class(broadcast + n) def __lt__(self, other): @@ -866,21 +866,21 @@ class _BaseNetwork(_IPAddressBase): addr1 = ip_network('192.0.2.0/28') addr2 = ip_network('192.0.2.1/32') - addr1.address_exclude(addr2) = + list(addr1.address_exclude(addr2)) = [IPv4Network('192.0.2.0/32'), IPv4Network('192.0.2.2/31'), - IPv4Network('192.0.2.4/30'), IPv4Network('192.0.2.8/29')] + IPv4Network('192.0.2.4/30'), IPv4Network('192.0.2.8/29')] or IPv6: addr1 = ip_network('2001:db8::1/32') addr2 = ip_network('2001:db8::1/128') - addr1.address_exclude(addr2) = + list(addr1.address_exclude(addr2)) = [ip_network('2001:db8::1/128'), - ip_network('2001:db8::2/127'), - ip_network('2001:db8::4/126'), - ip_network('2001:db8::8/125'), - ... - ip_network('2001:db8:8000::/33')] + ip_network('2001:db8::2/127'), + ip_network('2001:db8::4/126'), + ip_network('2001:db8::8/125'), + ... + ip_network('2001:db8:8000::/33')] Args: other: An IPv4Network or IPv6Network object of the same type. @@ -1039,7 +1039,7 @@ class _BaseNetwork(_IPAddressBase): new_prefixlen, self)) start = int(self.network_address) - end = int(self.broadcast_address) + end = int(self.broadcast_address) + 1 step = (int(self.hostmask) + 1) >> prefixlen_diff for new_addr in _compat_range(start, end, step): current = self.__class__((new_addr, new_prefixlen)) @@ -1436,6 +1436,12 @@ class IPv4Address(_BaseV4, _BaseAddress): return any(self in net for net in self._constants._private_networks) @property + def is_global(self): + return ( + self not in self._constants._public_network and + not self.is_private) + + @property def is_multicast(self): """Test if the address is reserved for multicast use. @@ -1682,6 +1688,8 @@ class _IPv4Constants(object): _multicast_network = IPv4Network('224.0.0.0/4') + _public_network = IPv4Network('100.64.0.0/10') + _private_networks = [ IPv4Network('0.0.0.0/8'), IPv4Network('10.0.0.0/8'), diff --git a/pip/_vendor/ordereddict.py b/pip/_vendor/ordereddict.py new file mode 100644 index 000000000..7242b5060 --- /dev/null +++ b/pip/_vendor/ordereddict.py @@ -0,0 +1,127 @@ +# Copyright (c) 2009 Raymond Hettinger +# +# 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. + +from UserDict import DictMixin + +class OrderedDict(dict, DictMixin): + + def __init__(self, *args, **kwds): + if len(args) > 1: + raise TypeError('expected at most 1 arguments, got %d' % len(args)) + try: + self.__end + except AttributeError: + self.clear() + self.update(*args, **kwds) + + def clear(self): + self.__end = end = [] + end += [None, end, end] # sentinel node for doubly linked list + self.__map = {} # key --> [key, prev, next] + dict.clear(self) + + def __setitem__(self, key, value): + if key not in self: + end = self.__end + curr = end[1] + curr[2] = end[1] = self.__map[key] = [key, curr, end] + dict.__setitem__(self, key, value) + + def __delitem__(self, key): + dict.__delitem__(self, key) + key, prev, next = self.__map.pop(key) + prev[2] = next + next[1] = prev + + def __iter__(self): + end = self.__end + curr = end[2] + while curr is not end: + yield curr[0] + curr = curr[2] + + def __reversed__(self): + end = self.__end + curr = end[1] + while curr is not end: + yield curr[0] + curr = curr[1] + + def popitem(self, last=True): + if not self: + raise KeyError('dictionary is empty') + if last: + key = reversed(self).next() + else: + key = iter(self).next() + value = self.pop(key) + return key, value + + def __reduce__(self): + items = [[k, self[k]] for k in self] + tmp = self.__map, self.__end + del self.__map, self.__end + inst_dict = vars(self).copy() + self.__map, self.__end = tmp + if inst_dict: + return (self.__class__, (items,), inst_dict) + return self.__class__, (items,) + + def keys(self): + return list(self) + + setdefault = DictMixin.setdefault + update = DictMixin.update + pop = DictMixin.pop + values = DictMixin.values + items = DictMixin.items + iterkeys = DictMixin.iterkeys + itervalues = DictMixin.itervalues + iteritems = DictMixin.iteritems + + def __repr__(self): + if not self: + return '%s()' % (self.__class__.__name__,) + return '%s(%r)' % (self.__class__.__name__, self.items()) + + def copy(self): + return self.__class__(self) + + @classmethod + def fromkeys(cls, iterable, value=None): + d = cls() + for key in iterable: + d[key] = value + return d + + def __eq__(self, other): + if isinstance(other, OrderedDict): + if len(self) != len(other): + return False + for p, q in zip(self.items(), other.items()): + if p != q: + return False + return True + return dict.__eq__(self, other) + + def __ne__(self, other): + return not self == other diff --git a/pip/_vendor/packaging/__about__.py b/pip/_vendor/packaging/__about__.py index c21a758b8..95d330ef8 100644 --- a/pip/_vendor/packaging/__about__.py +++ b/pip/_vendor/packaging/__about__.py @@ -12,7 +12,7 @@ __title__ = "packaging" __summary__ = "Core utilities for Python packages" __uri__ = "https://github.com/pypa/packaging" -__version__ = "16.7" +__version__ = "16.8" __author__ = "Donald Stufft and individual contributors" __email__ = "donald@stufft.io" diff --git a/pip/_vendor/packaging/markers.py b/pip/_vendor/packaging/markers.py index 919524353..f9ca1ffa3 100644 --- a/pip/_vendor/packaging/markers.py +++ b/pip/_vendor/packaging/markers.py @@ -54,13 +54,26 @@ class Node(object): def __repr__(self): return "<{0}({1!r})>".format(self.__class__.__name__, str(self)) + def serialize(self): + raise NotImplementedError + class Variable(Node): - pass + + def serialize(self): + return str(self) class Value(Node): - pass + + def serialize(self): + return '"{0}"'.format(self) + + +class Op(Node): + + def serialize(self): + return str(self) VARIABLE = ( @@ -105,6 +118,7 @@ VERSION_CMP = ( ) MARKER_OP = VERSION_CMP | L("not in") | L("in") +MARKER_OP.setParseAction(lambda s, l, t: Op(t[0])) MARKER_VALUE = QuotedString("'") | QuotedString('"') MARKER_VALUE.setParseAction(lambda s, l, t: Value(t[0])) @@ -151,7 +165,7 @@ def _format_marker(marker, first=True): else: return "(" + " ".join(inner) + ")" elif isinstance(marker, tuple): - return '{0} {1} "{2}"'.format(*marker) + return " ".join([m.serialize() for m in marker]) else: return marker @@ -170,13 +184,13 @@ _operators = { def _eval_op(lhs, op, rhs): try: - spec = Specifier("".join([op, rhs])) + spec = Specifier("".join([op.serialize(), rhs])) except InvalidSpecifier: pass else: return spec.contains(lhs) - oper = _operators.get(op) + oper = _operators.get(op.serialize()) if oper is None: raise UndefinedComparison( "Undefined {0!r} on {1!r} and {2!r}.".format(op, lhs, rhs) diff --git a/pip/_vendor/pyparsing.py b/pip/_vendor/pyparsing.py index 56f196637..cb46d411a 100644 --- a/pip/_vendor/pyparsing.py +++ b/pip/_vendor/pyparsing.py @@ -1,6 +1,6 @@ # module pyparsing.py # -# Copyright (c) 2003-2015 Paul T. McGuire +# Copyright (c) 2003-2016 Paul T. McGuire # # Permission is hereby granted, free of charge, to any person obtaining # a copy of this software and associated documentation files (the @@ -31,15 +31,18 @@ vs. the traditional lex/yacc approach, or the use of regular expressions. With 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>!"}):: +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 ) + "!" + greet = Word(alphas) + "," + Word(alphas) + "!" hello = "Hello, World!" - print (hello, "->", greet.parseString( hello )) + print (hello, "->", greet.parseString(hello)) The program outputs the following:: @@ -48,7 +51,7 @@ The program outputs the following:: The Python representation of the grammar is quite readable, owing to the self-explanatory class names, and the use of '+', '|' and '^' operators. -The parsed results returned from C{parseString()} can be accessed as a nested list, a dictionary, or an +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: @@ -57,8 +60,8 @@ The pyparsing module handles some of the problems that are typically vexing when - embedded comments """ -__version__ = "2.1.1" -__versionTime__ = "21 Mar 2016 05:04 UTC" +__version__ = "2.1.10" +__versionTime__ = "07 Oct 2016 01:31 UTC" __author__ = "Paul McGuire <ptmcg@users.sourceforge.net>" import string @@ -70,9 +73,22 @@ import re import sre_constants import collections import pprint -import functools -import itertools import traceback +import types +from datetime import datetime + +try: + from _thread import RLock +except ImportError: + from threading import RLock + +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__ ) ) @@ -94,9 +110,11 @@ __all__ = [ 'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd', 'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute', 'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation','locatedExpr', 'withClass', +'CloseMatch', 'tokenMap', 'pyparsing_common', ] -PY_3 = sys.version.startswith('3') +system_version = tuple(sys.version_info)[:3] +PY_3 = system_version[0] == 3 if PY_3: _MAX_INT = sys.maxsize basestring = str @@ -174,6 +192,15 @@ class ParseBaseException(Exception): 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: @@ -209,11 +236,23 @@ class ParseBaseException(Exception): 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 + """ + 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 @@ -223,12 +262,10 @@ class ParseFatalException(ParseBaseException): pass class ParseSyntaxException(ParseFatalException): - """just like C{L{ParseFatalException}}, but thrown internally when an - C{L{ErrorStop<And._ErrorStop>}} ('-' operator) indicates that parsing is to stop immediately because - an unbacktrackable syntax error has been found""" - def __init__(self, pe): - super(ParseSyntaxException, self).__init__( - pe.pstr, pe.loc, pe.msg, pe.parserElement) + """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 @@ -244,7 +281,7 @@ class ParseSyntaxException(ParseFatalException): #~ self.reparseLoc = restartLoc class RecursiveGrammarException(Exception): - """exception thrown by C{validate()} if the grammar could be improperly recursive""" + """exception thrown by L{ParserElement.validate} if the grammar could be improperly recursive""" def __init__( self, parseElementList ): self.parseElementTrace = parseElementList @@ -257,16 +294,49 @@ class _ParseResultsWithOffset(object): def __getitem__(self,i): return self.tup[i] def __repr__(self): - return repr(self.tup) + 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: + """ + 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>}) - """ + - 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 @@ -351,11 +421,6 @@ class ParseResults(object): removed = list(range(*i.indices(mylen))) removed.reverse() # fixup indices in token dictionary - #~ for name in self.__tokdict: - #~ occurrences = self.__tokdict[name] - #~ for j in removed: - #~ for k, (value, position) in enumerate(occurrences): - #~ occurrences[k] = _ParseResultsWithOffset(value, position - (position > j)) for name,occurrences in self.__tokdict.items(): for j in removed: for k, (value, position) in enumerate(occurrences): @@ -371,35 +436,48 @@ class ParseResults(object): __nonzero__ = __bool__ def __iter__( self ): return iter( self.__toklist ) def __reversed__( self ): return iter( self.__toklist[::-1] ) - def iterkeys( self ): - """Returns all named result keys.""" + def _iterkeys( self ): if hasattr(self.__tokdict, "iterkeys"): return self.__tokdict.iterkeys() else: return iter(self.__tokdict) - def itervalues( self ): - """Returns all named result values.""" - return (self[k] for k in self.iterkeys()) + def _itervalues( self ): + return (self[k] for k in self._iterkeys()) - def iteritems( self ): - return ((k, self[k]) for k in self.iterkeys()) + def _iteritems( self ): + return ((k, self[k]) for k in self._iterkeys()) if PY_3: - keys = iterkeys - values = itervalues - items = iteritems + 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.""" + """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.""" + """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 keys and values as a list of tuples.""" + """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 ): @@ -408,14 +486,39 @@ class ParseResults(object): 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().""" + """ + 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(): @@ -435,39 +538,83 @@ class ParseResults(object): 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.""" + """ + 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.""" + """ + 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 in self.__tokdict: - #~ occurrences = self.__tokdict[name] - #~ for k, (value, position) in enumerate(occurrences): - #~ occurrences[k] = _ParseResultsWithOffset(value, position + (position > index)) 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.""" + """ + 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.""" + """ + 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.""" + """ + Clear all elements and results names. + """ del self.__toklist[:] self.__tokdict.clear() @@ -532,11 +679,40 @@ class ParseResults(object): return out def asList( self ): - """Returns the parse results as a nested list of matching tokens, all converted to strings.""" + """ + 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.""" + """ + 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: @@ -554,7 +730,9 @@ class ParseResults(object): return dict((k,toItem(v)) for k,v in item_fn()) def copy( self ): - """Returns a new copy of a C{ParseResults} object.""" + """ + Returns a new copy of a C{ParseResults} object. + """ ret = ParseResults( self.__toklist ) ret.__tokdict = self.__tokdict.copy() ret.__parent = self.__parent @@ -563,7 +741,9 @@ class ParseResults(object): return ret def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ): - """Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.""" + """ + (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() @@ -629,7 +809,27 @@ class ParseResults(object): return None def getName(self): - """Returns the results name for this token expression.""" + """ + 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: @@ -640,45 +840,77 @@ class ParseResults(object): return None elif (len(self) == 1 and len(self.__tokdict) == 1 and - self.__tokdict.values()[0][0][1] in (0,-1)): - return self.__tokdict.keys()[0] + 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): - """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.""" + 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 self.haskeys(): - items = sorted(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) ) + 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(_ustr(v)) - else: - out.append(_ustr(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))) + 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})""" + """ + 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 @@ -721,7 +953,7 @@ def col (loc,strg): positions within the parsed string. """ s = strg - return 1 if loc<len(s) and s[loc] == '\n' else loc - s.rfind("\n", 0, loc) + 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. @@ -786,10 +1018,35 @@ def _trim_arity(func, maxargs=2): 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.filename, frame_summary.lineno)] + def extract_tb(tb, limit=0): + frames = traceback.extract_tb(tb, limit=limit) + frame_summary = frames[-1] + return [(frame_summary.filename, frame_summary.lineno)] + 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]:]) #~@$^*)+_(&%#!=-`~;:"[]{} + ret = func(*args[limit[0]:]) foundArity[0] = True return ret except TypeError: @@ -799,8 +1056,7 @@ def _trim_arity(func, maxargs=2): else: try: tb = sys.exc_info()[-1] - exc_source_line = traceback.extract_tb(tb)[-1][-1] - if not exc_source_line.endswith('#~@$^*)+_(&%#!=-`~;:"[]{}'): + if not extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth: raise finally: del tb @@ -809,6 +1065,16 @@ def _trim_arity(func, maxargs=2): 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): @@ -818,7 +1084,16 @@ class ParserElement(object): @staticmethod def setDefaultWhitespaceChars( chars ): - """Overrides the default whitespace 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 @@ -826,8 +1101,22 @@ class ParserElement(object): 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 + ParserElement._literalStringClass = cls def __init__( self, savelist=False ): self.parseAction = list() @@ -853,8 +1142,21 @@ class ParserElement(object): 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.""" + """ + 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[:] @@ -863,7 +1165,13 @@ class ParserElement(object): return cpy def setName( self, name ): - """Define name for this expression, for use in debugging.""" + """ + 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"): @@ -871,15 +1179,24 @@ class ParserElement(object): 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__>}. + """ + 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("*"): @@ -908,42 +1225,76 @@ class ParserElement(object): return self def setParseAction( self, *fns, **kwargs ): - """Define action 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. - - 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. - """ + """ + Define action 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 parse action to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}.""" + """ + Add parse action 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>}. Optional keyword argument C{message} can - be used to define a custom message to be used in the raised exception.""" - msg = kwargs.get("message") or "failed user-defined condition" + 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 ParseException(s,l,msg) - return t + raise exc_type(s,l,msg) self.parseAction.append(pa) self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False) return self @@ -1079,42 +1430,123 @@ class ParserElement(object): 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() + + self.get = types.MethodType(get, self) + self.set = types.MethodType(set, self) + self.clear = types.MethodType(clear, 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 + if len(cache) > size: + cache.popitem(False) + + def clear(self): + cache.clear() + + self.get = types.MethodType(get, self) + self.set = types.MethodType(set, self) + self.clear = types.MethodType(clear, 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 + if len(cache) > size: + cache.pop(key_fifo.popleft(), None) + key_fifo.append(key) + + def clear(self): + cache.clear() + key_fifo.clear() + + self.get = types.MethodType(get, self) + self.set = types.MethodType(set, self) + self.clear = types.MethodType(clear, 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 ): - lookup = (self,instring,loc,callPreParse,doActions) - if lookup in ParserElement._exprArgCache: - value = ParserElement._exprArgCache[ lookup ] - if isinstance(value, Exception): - raise value - return (value[0],value[1].copy()) - else: - try: - value = self._parseNoCache( instring, loc, doActions, callPreParse ) - ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy()) - return value - except ParseBaseException as pe: - pe.__traceback__ = None - ParserElement._exprArgCache[ lookup ] = pe - raise + 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 - # argument cache for optimizing repeated calls when backtracking through recursive expressions - _exprArgCache = {} @staticmethod def resetCache(): - ParserElement._exprArgCache.clear() + ParserElement.packrat_cache.clear() + ParserElement.packrat_cache_stats[:] = [0] * len(ParserElement.packrat_cache_stats) _packratEnabled = False @staticmethod - def enablePackrat(): + 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 @@ -1123,32 +1555,45 @@ class ParserElement(object): 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} + """ + 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: @@ -1174,14 +1619,35 @@ class ParserElement(object): 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.""" + """ + 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: @@ -1224,12 +1690,22 @@ class ParserElement(object): 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.""" + """ + 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 @@ -1257,9 +1733,18 @@ class ParserElement(object): 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. + """ + 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")) + prints:: + ['More', 'Iron', 'Lead', 'Gold', 'I'] """ try: return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ]) @@ -1270,10 +1755,42 @@ class ParserElement(object): # 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}}""" + """ + 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 ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1281,9 +1798,11 @@ class ParserElement(object): return And( [ self, other ] ) def __radd__(self, other ): - """Implementation of + operator when left operand is not a C{L{ParserElement}}""" + """ + Implementation of + operator when left operand is not a C{L{ParserElement}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1291,9 +1810,11 @@ class ParserElement(object): return other + self def __sub__(self, other): - """Implementation of - operator, returns C{L{And}} with error stop""" + """ + Implementation of - operator, returns C{L{And}} with error stop + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1301,9 +1822,11 @@ class ParserElement(object): return And( [ self, And._ErrorStop(), other ] ) def __rsub__(self, other ): - """Implementation of - operator when left operand is not a C{L{ParserElement}}""" + """ + Implementation of - operator when left operand is not a C{L{ParserElement}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1311,24 +1834,24 @@ class ParserElement(object): 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 + """ + 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)} + - 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} - + - 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 @@ -1382,9 +1905,11 @@ class ParserElement(object): return self.__mul__(other) def __or__(self, other ): - """Implementation of | operator - returns C{L{MatchFirst}}""" + """ + Implementation of | operator - returns C{L{MatchFirst}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1392,9 +1917,11 @@ class ParserElement(object): return MatchFirst( [ self, other ] ) def __ror__(self, other ): - """Implementation of | operator when left operand is not a C{L{ParserElement}}""" + """ + Implementation of | operator when left operand is not a C{L{ParserElement}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1402,9 +1929,11 @@ class ParserElement(object): return other | self def __xor__(self, other ): - """Implementation of ^ operator - returns C{L{Or}}""" + """ + Implementation of ^ operator - returns C{L{Or}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1412,9 +1941,11 @@ class ParserElement(object): return Or( [ self, other ] ) def __rxor__(self, other ): - """Implementation of ^ operator when left operand is not a C{L{ParserElement}}""" + """ + Implementation of ^ operator when left operand is not a C{L{ParserElement}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1422,9 +1953,11 @@ class ParserElement(object): return other ^ self def __and__(self, other ): - """Implementation of & operator - returns C{L{Each}}""" + """ + Implementation of & operator - returns C{L{Each}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1432,9 +1965,11 @@ class ParserElement(object): return Each( [ self, other ] ) def __rand__(self, other ): - """Implementation of & operator when left operand is not a C{L{ParserElement}}""" + """ + Implementation of & operator when left operand is not a C{L{ParserElement}} + """ if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) @@ -1442,41 +1977,49 @@ class ParserElement(object): return other & self def __invert__( self ): - """Implementation of ~ operator - returns C{L{NotAny}}""" + """ + Implementation of ~ operator - returns C{L{NotAny}} + """ return NotAny( self ) def __call__(self, name=None): - """Shortcut for C{L{setResultsName}}, with C{listAllMatches=default}:: - userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno") - could be written as:: - userdata = Word(alphas)("name") + Word(nums+"-")("socsecno") - - If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be - passed as C{True}. + """ + 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}}. - """ + 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. + """ + 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. + """ + 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 + """ + Overrides the default whitespace chars """ self.skipWhitespace = True self.whiteChars = chars @@ -1484,16 +2027,26 @@ class ParserElement(object): 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.""" + """ + 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. + """ + 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) @@ -1506,7 +2059,9 @@ class ParserElement(object): return self def setDebugActions( self, startAction, successAction, exceptionAction ): - """Enable display of debugging messages while doing pattern matching.""" + """ + Enable display of debugging messages while doing pattern matching. + """ self.debugActions = (startAction or _defaultStartDebugAction, successAction or _defaultSuccessDebugAction, exceptionAction or _defaultExceptionDebugAction) @@ -1514,8 +2069,40 @@ class ParserElement(object): 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.""" + """ + 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: @@ -1537,20 +2124,22 @@ class ParserElement(object): pass def validate( self, validateTrace=[] ): - """Check defined expressions for valid structure, check for infinite recursive definitions.""" + """ + 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. + """ + 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: - f = open(file_or_filename, "r") - file_contents = f.read() - f.close() + with open(file_or_filename, "r") as f: + file_contents = f.read() try: return self.parseString(file_contents, parseAll) except ParseBaseException as exc: @@ -1564,11 +2153,7 @@ class ParserElement(object): if isinstance(other, ParserElement): return self is other or vars(self) == vars(other) elif isinstance(other, basestring): - try: - self.parseString(_ustr(other), parseAll=True) - return True - except ParseBaseException: - return False + return self.matches(other) else: return super(ParserElement,self)==other @@ -1584,40 +2169,169 @@ class ParserElement(object): def __rne__(self,other): return not (self == other) - def runTests(self, tests, parseAll=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. + 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: - - tests - a list of separate test strings, or a multiline string of test strings - - parseAll - (default=False) - flag to pass to C{L{parseString}} when running tests + 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 = map(str.strip, tests.splitlines()) + tests = list(map(str.strip, tests.rstrip().splitlines())) + if isinstance(comment, basestring): + comment = Literal(comment) + allResults = [] + comments = [] + success = True for t in tests: - out = [t] + 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: - out.append(self.parseString(t, parseAll=parseAll).dump()) - except ParseException as pe: + 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) + '^') + out.append(' '*(col(pe.loc,t)-1) + '^' + fatal) else: - out.append(' '*pe.loc + '^') - out.append(str(pe)) - out.append('') - print('\n'.join(out)) + 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.""" + """ + 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.""" + """ + An empty token, will always match. + """ def __init__( self ): super(Empty,self).__init__() self.name = "Empty" @@ -1626,7 +2340,9 @@ class Empty(Token): class NoMatch(Token): - """A token that will never match.""" + """ + A token that will never match. + """ def __init__( self ): super(NoMatch,self).__init__() self.name = "NoMatch" @@ -1639,7 +2355,19 @@ class NoMatch(Token): class Literal(Token): - """Token to exactly match a specified string.""" + """ + 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 @@ -1665,22 +2393,31 @@ class Literal(Token): return loc+self.matchLen, self.match raise ParseException(instring, loc, self.errmsg, self) _L = Literal -ParserElement.literalStringClass = 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}}:: - Literal("if") will match the leading C{'if'} in C{'ifAndOnlyIf'}. - 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}. + """ + 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=DEFAULT_KEYWORD_CHARS, caseless=False ): + 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: @@ -1724,9 +2461,15 @@ class Keyword(Token): 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. + """ + 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() ) @@ -1741,7 +2484,15 @@ class CaselessLiteral(Literal): raise ParseException(instring, loc, self.errmsg, self) class CaselessKeyword(Keyword): - def __init__( self, matchString, identChars=Keyword.DEFAULT_KEYWORD_CHARS ): + """ + 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 ): @@ -1750,17 +2501,113 @@ class CaselessKeyword(Keyword): 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. + """ + 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__() @@ -1813,7 +2660,7 @@ class Word(Token): self.reString = r"\b"+self.reString+r"\b" try: self.re = re.compile( self.reString ) - except: + except Exception: self.re = None def parseImpl( self, instring, loc, doActions=True ): @@ -1854,7 +2701,7 @@ class Word(Token): def __str__( self ): try: return super(Word,self).__str__() - except: + except Exception: pass @@ -1875,8 +2722,17 @@ class Word(Token): class Regex(Token): - """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. + """ + 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): @@ -1929,7 +2785,7 @@ class Regex(Token): def __str__( self ): try: return super(Regex,self).__str__() - except: + except Exception: pass if self.strRepr is None: @@ -1939,18 +2795,31 @@ class Regex(Token): class QuotedString(Token): - """Token for matching strings that are delimited by quoting characters. + 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): - r"""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=None) - - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=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}) - """ super(QuotedString,self).__init__() # remove white space from quote chars - wont work anyway @@ -2053,7 +2922,7 @@ class QuotedString(Token): def __str__( self ): try: return super(QuotedString,self).__str__() - except: + except Exception: pass if self.strRepr is None: @@ -2063,11 +2932,20 @@ class QuotedString(Token): class CharsNotIn(Token): - """Token for matching words composed of characters *not* in a given set. - 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. + """ + 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__() @@ -2113,7 +2991,7 @@ class CharsNotIn(Token): def __str__( self ): try: return super(CharsNotIn, self).__str__() - except: + except Exception: pass if self.strRepr is None: @@ -2125,11 +3003,13 @@ class CharsNotIn(Token): 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.""" + """ + 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>", @@ -2181,7 +3061,9 @@ class _PositionToken(Token): self.mayIndexError = False class GoToColumn(_PositionToken): - """Token to advance to a specific column of input text; useful for tabular report scraping.""" + """ + 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 @@ -2203,28 +3085,41 @@ class GoToColumn(_PositionToken): 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""" + """ + 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.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) self.errmsg = "Expected start of line" - def preParse( self, instring, loc ): - preloc = super(LineStart,self).preParse(instring,loc) - if instring[preloc] == "\n": - loc += 1 - return loc - def parseImpl( self, instring, loc, doActions=True ): - if not( loc==0 or - (loc == self.preParse( instring, 0 )) or - (instring[loc-1] == "\n") ): #col(loc, instring) != 1: - raise ParseException(instring, loc, self.errmsg, self) - return loc, [] + 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""" + """ + 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","") ) @@ -2242,7 +3137,9 @@ class LineEnd(_PositionToken): raise ParseException(instring, loc, self.errmsg, self) class StringStart(_PositionToken): - """Matches if current position is at the beginning of the parse string""" + """ + 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" @@ -2255,7 +3152,9 @@ class StringStart(_PositionToken): return loc, [] class StringEnd(_PositionToken): - """Matches if current position is at the end of the parse string""" + """ + 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" @@ -2271,11 +3170,12 @@ class StringEnd(_PositionToken): 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. + """ + 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__() @@ -2290,11 +3190,12 @@ class WordStart(_PositionToken): 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. + """ + 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__() @@ -2312,18 +3213,21 @@ class WordEnd(_PositionToken): class ParseExpression(ParserElement): - """Abstract subclass of ParserElement, for combining and post-processing parsed tokens.""" + """ + 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 = [ Literal( exprs ) ] - elif isinstance( exprs, collections.Sequence ): + self.exprs = [ ParserElement._literalStringClass( exprs ) ] + elif isinstance( exprs, collections.Iterable ): + exprs = list(exprs) # if sequence of strings provided, wrap with Literal if all(isinstance(expr, basestring) for expr in exprs): - exprs = map(Literal, exprs) + exprs = map(ParserElement._literalStringClass, exprs) self.exprs = list(exprs) else: try: @@ -2364,7 +3268,7 @@ class ParseExpression(ParserElement): def __str__( self ): try: return super(ParseExpression,self).__str__() - except: + except Exception: pass if self.strRepr is None: @@ -2421,9 +3325,19 @@ class ParseExpression(ParserElement): 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. + """ + 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): @@ -2455,9 +3369,9 @@ class And(ParseExpression): raise except ParseBaseException as pe: pe.__traceback__ = None - raise ParseSyntaxException(pe) + raise ParseSyntaxException._from_exception(pe) except IndexError: - raise ParseSyntaxException( ParseException(instring, len(instring), self.errmsg, self) ) + raise ParseSyntaxException(instring, len(instring), self.errmsg, self) else: loc, exprtokens = e._parse( instring, loc, doActions ) if exprtokens or exprtokens.haskeys(): @@ -2466,7 +3380,7 @@ class And(ParseExpression): def __iadd__(self, other ): if isinstance( other, basestring ): - other = Literal( other ) + other = ParserElement._literalStringClass( other ) return self.append( other ) #And( [ self, other ] ) def checkRecursion( self, parseElementList ): @@ -2487,9 +3401,18 @@ class And(ParseExpression): 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. + """ + 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) @@ -2538,7 +3461,7 @@ class Or(ParseExpression): def __ixor__(self, other ): if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) return self.append( other ) #Or( [ self, other ] ) def __str__( self ): @@ -2557,9 +3480,21 @@ class Or(ParseExpression): 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. + """ + 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) @@ -2594,7 +3529,7 @@ class MatchFirst(ParseExpression): def __ior__(self, other ): if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) + other = ParserElement._literalStringClass( other ) return self.append( other ) #MatchFirst( [ self, other ] ) def __str__( self ): @@ -2613,9 +3548,58 @@ class MatchFirst(ParseExpression): 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. + """ + 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) @@ -2669,17 +3653,7 @@ class Each(ParseExpression): loc,results = e._parse(instring,loc,doActions) resultlist.append(results) - finalResults = ParseResults() - for r in resultlist: - dups = {} - for k in r.keys(): - if k in finalResults: - tmp = ParseResults(finalResults[k]) - tmp += ParseResults(r[k]) - dups[k] = tmp - finalResults += ParseResults(r) - for k,v in dups.items(): - finalResults[k] = v + finalResults = sum(resultlist, ParseResults([])) return loc, finalResults def __str__( self ): @@ -2698,11 +3672,16 @@ class Each(ParseExpression): class ParseElementEnhance(ParserElement): - """Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.""" + """ + 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 ): - expr = Literal(expr) + 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: @@ -2761,7 +3740,7 @@ class ParseElementEnhance(ParserElement): def __str__( self ): try: return super(ParseElementEnhance,self).__str__() - except: + except Exception: pass if self.strRepr is None and self.expr is not None: @@ -2770,10 +3749,22 @@ class ParseElementEnhance(ParserElement): class FollowedBy(ParseElementEnhance): - """Lookahead matching of the given parse expression. C{FollowedBy} - does *not* advance the parsing position within the input string, it only + """ + 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.""" + 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 @@ -2784,11 +3775,16 @@ class FollowedBy(ParseElementEnhance): class NotAny(ParseElementEnhance): - """Lookahead to disallow matching with the given parse expression. C{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, C{NotAny} does *not* skip over leading whitespace. C{NotAny} - always returns a null token list. May be constructed using the '~' operator.""" + """ + 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() @@ -2810,21 +3806,13 @@ class NotAny(ParseElementEnhance): return self.strRepr - -class OneOrMore(ParseElementEnhance): - """Repetition of one or more of the given expression. - - Parameters: - - expr - expression that must match one or more times - - stopOn - (default=None) - expression for a terminating sentinel - (only required if the sentinel would ordinarily match the repetition - expression) - """ +class _MultipleMatch(ParseElementEnhance): def __init__( self, expr, stopOn=None): - super(OneOrMore, self).__init__(expr) + super(_MultipleMatch, self).__init__(expr) + self.saveAsList = True ender = stopOn if isinstance(ender, basestring): - ender = Literal(ender) + ender = ParserElement._literalStringClass(ender) self.not_ender = ~ender if ender is not None else None def parseImpl( self, instring, loc, doActions=True ): @@ -2855,6 +3843,32 @@ class OneOrMore(ParseElementEnhance): 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"): @@ -2865,19 +3879,17 @@ class OneOrMore(ParseElementEnhance): return self.strRepr - def setResultsName( self, name, listAllMatches=False ): - ret = super(OneOrMore,self).setResultsName(name,listAllMatches) - ret.saveAsList = True - return ret - -class ZeroOrMore(OneOrMore): - """Optional repetition of zero or more of the given expression. +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=None) - expression for a terminating sentinel + 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) @@ -2907,15 +3919,43 @@ class _NullToken(object): _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. + """ + 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 @@ -2943,17 +3983,59 @@ class Optional(ParseElementEnhance): return self.strRepr class SkipTo(ParseElementEnhance): - """Token for skipping over all undefined text until the matched expression is found. + """ + 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=False) if True, the target expression is also parsed + 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=None) used to define grammars (typically quoted strings and + - ignore - (default=C{None}) used to define grammars (typically quoted strings and comments) that might contain false matches to the target expression - - failOn - (default=None) define expressions that are not allowed to be + - 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 ) @@ -2963,7 +4045,7 @@ class SkipTo(ParseElementEnhance): self.includeMatch = include self.asList = False if isinstance(failOn, basestring): - self.failOn = Literal(failOn) + self.failOn = ParserElement._literalStringClass(failOn) else: self.failOn = failOn self.errmsg = "No match found for "+_ustr(self.expr) @@ -3016,26 +4098,30 @@ class SkipTo(ParseElementEnhance): 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. + """ + 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) + other = ParserElement._literalStringClass(other) self.expr = other self.strRepr = None self.mayIndexError = self.expr.mayIndexError @@ -3097,15 +4183,29 @@ class _ForwardNoRecurse(Forward): return "..." class TokenConverter(ParseElementEnhance): - """Abstract subclass of C{ParseExpression}, for converting parsed results.""" + """ + 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. + """ + 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 ) @@ -3135,7 +4235,19 @@ class Combine(TokenConverter): 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.""" + """ + 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 @@ -3144,9 +4256,40 @@ class Group(TokenConverter): 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. + """ + 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 ) @@ -3178,7 +4321,24 @@ class Dict(TokenConverter): class Suppress(TokenConverter): - """Converter for ignoring the results of a parsed expression.""" + """ + 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 [] @@ -3187,7 +4347,9 @@ class Suppress(TokenConverter): class OnlyOnce(object): - """Wrapper for parse actions, to ensure they are only called once.""" + """ + Wrapper for parse actions, to ensure they are only called once. + """ def __init__(self, methodCall): self.callable = _trim_arity(methodCall) self.called = False @@ -3201,20 +4363,39 @@ class OnlyOnce(object): self.called = False def traceParseAction(f): - """Decorator for debugging parse actions.""" + """ + 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.func_name + 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, %s)\n" % (thisFunc,line(l,s),l,t) ) + 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: %s)\n" % (thisFunc,ret) ) + sys.stderr.write( "<<leaving %s (ret: %r)\n" % (thisFunc,ret) ) return ret try: z.__name__ = f.__name__ @@ -3226,12 +4407,17 @@ def traceParseAction(f): # 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. + """ + 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: @@ -3240,11 +4426,22 @@ def delimitedList( expr, delim=",", combine=False ): 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. + """ + 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): @@ -3269,16 +4466,17 @@ def _flatten(L): 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 *not* use with packrat parsing enabled. + """ + 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): @@ -3296,17 +4494,18 @@ def matchPreviousLiteral(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 *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 *not* use with packrat parsing enabled. + """ + 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() @@ -3331,16 +4530,27 @@ def _escapeRegexRangeChars(s): 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 list of string literals - - caseless - (default=False) - treat all literals as caseless - - useRegex - (default=True) - as an optimization, will generate a Regex + """ + 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() ) @@ -3354,12 +4564,10 @@ def oneOf( strs, caseless=False, useRegex=True ): symbols = [] if isinstance(strs,basestring): symbols = strs.split() - elif isinstance(strs, collections.Sequence): - symbols = list(strs[:]) - elif isinstance(strs, _generatorType): + elif isinstance(strs, collections.Iterable): symbols = list(strs) else: - warnings.warn("Invalid argument to oneOf, expected string or list", + warnings.warn("Invalid argument to oneOf, expected string or iterable", SyntaxWarning, stacklevel=2) if not symbols: return NoMatch() @@ -3386,7 +4594,7 @@ def oneOf( strs, caseless=False, useRegex=True ): 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: + except Exception: warnings.warn("Exception creating Regex for oneOf, building MatchFirst", SyntaxWarning, stacklevel=2) @@ -3395,27 +4603,64 @@ def oneOf( strs, caseless=False, useRegex=True ): 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. + """ + 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. + """ + 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.""" + 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 @@ -3426,22 +4671,35 @@ def originalTextFor(expr, asString=True): 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.""" + """ + 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}} + """ + 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")) @@ -3462,31 +4720,33 @@ _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 \- 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_$', etc.) + r""" + Helper to easily define string ranges for use in Word construction. Borrows + syntax from regexp '[]' string range definitions:: + srange("[0-9]") -> "0123456789" + srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" + srange("[a-z$_]") -> "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: + except Exception: return "" def matchOnlyAtCol(n): - """Helper method for defining parse actions that require matching at a specific - column in the input text. + """ + 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: @@ -3494,26 +4754,83 @@ def matchOnlyAtCol(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>}()}. + """ + 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. - To use, add this parse action to quoted string using:: - quotedString.setParseAction( removeQuotes ) + """ + 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 upcaseTokens(s,l,t): - """Helper parse action to convert tokens to upper case.""" - return [ tt.upper() for tt in map(_ustr,t) ] +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 -def downcaseTokens(s,l,t): - """Helper parse action to convert tokens to lower case.""" - return [ tt.lower() for tt in map(_ustr,t) ] +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): @@ -3544,33 +4861,83 @@ def _makeTags(tagStr, xml): return openTag, closeTag def makeHTMLTags(tagStr): - """Helper to construct opening and closing tag expressions for HTML, given a tag name""" + """ + 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""" + """ + 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 + """ + 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. + - 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. - """ + 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: @@ -3587,9 +4954,37 @@ def withAttribute(*args,**attrDict): 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. - """ + """ + 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}) @@ -3598,30 +4993,63 @@ 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. - - 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) - - lpar - expression for matching left-parentheses (default=Suppress('(')) - - rpar - expression for matching right-parentheses (default=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) + - 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 ) @@ -3670,33 +5098,73 @@ def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ): lastExpr = thisExpr ret <<= lastExpr return ret + operatorPrecedence = infixNotation +"""(Deprecated) Former name of C{L{infixNotation}}, will be dropped in a future release.""" -dblQuotedString = Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*"').setName("string enclosed in double quotes") -sglQuotedString = Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*'").setName("string enclosed in single quotes") -quotedString = Regex(r'''(?:"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*")|(?:'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*')''').setName("quotedString using single or double quotes") +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="("); 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) - - ignoreExpr - expression for ignoring opening and closing delimiters (default=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. + """ + 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") @@ -3731,20 +5199,82 @@ def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.cop 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. + """ + 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 + Parameters: + - blockStatementExpr - expression defining syntax of statement that is repeated within the indented block - - indentStack - list created by caller to manage indentation stack + - 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 + - indent - boolean indicating whether block must be indented beyond the the current level; set to False for block of left-most statements - (default=True) - - A valid block must contain at least one C{blockStatement}. + (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 @@ -3793,45 +5323,374 @@ def replaceHTMLEntity(t): 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 = Regex(r"/\*(?:[^*]*\*+)+?/").setName("C style comment") +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|.)*").setName("// comment") -cppStyleComment = Regex(r"/(?:\*(?:[^*]*\*+)+?/|/[^\n]*(?:\n[^\n]*)*?(?:(?<!\\)|\Z))").setName("C++ style comment") +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") - tableName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) - tableNameList = Group( delimitedList( tableName ) ).setName("tables") - simpleSQL = ( selectToken + \ - ( '*' | columnNameList ).setResultsName( "columns" ) + \ - fromToken + \ - tableNameList.setResultsName( "tables" ) ) - - simpleSQL.runTests("""\ - SELECT * from XYZZY, ABC - select * from SYS.XYZZY - Select A from Sys.dual - Select AA,BB,CC from Sys.dual - Select A, B, C from Sys.dual - Select A, B, C from Sys.dual - Xelect A, B, C from Sys.dual - Select A, B, C frox Sys.dual - Select - Select ^^^ frox Sys.dual - Select A, B, C from Sys.dual, Table2""") + 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/pip/_vendor/requests/__init__.py b/pip/_vendor/requests/__init__.py index 103d9fd8d..44f68361d 100644 --- a/pip/_vendor/requests/__init__.py +++ b/pip/_vendor/requests/__init__.py @@ -38,12 +38,11 @@ is at <http://python-requests.org>. :copyright: (c) 2016 by Kenneth Reitz. :license: Apache 2.0, see LICENSE for more details. - """ __title__ = 'requests' -__version__ = '2.10.0' -__build__ = 0x021000 +__version__ = '2.11.1' +__build__ = 0x021101 __author__ = 'Kenneth Reitz' __license__ = 'Apache 2.0' __copyright__ = 'Copyright 2016 Kenneth Reitz' @@ -85,7 +84,5 @@ except ImportError: logging.getLogger(__name__).addHandler(NullHandler()) -import warnings - # FileModeWarnings go off per the default. warnings.simplefilter('default', FileModeWarning, append=True) diff --git a/pip/_vendor/requests/adapters.py b/pip/_vendor/requests/adapters.py index 23e448f42..4a4c4e0e0 100644 --- a/pip/_vendor/requests/adapters.py +++ b/pip/_vendor/requests/adapters.py @@ -54,10 +54,24 @@ class BaseAdapter(object): def __init__(self): super(BaseAdapter, self).__init__() - def send(self): + def send(self, request, stream=False, timeout=None, verify=True, + cert=None, proxies=None): + """Sends PreparedRequest object. Returns Response object. + + :param request: The :class:`PreparedRequest <PreparedRequest>` being sent. + :param stream: (optional) Whether to stream the request content. + :param timeout: (optional) How long to wait for the server to send + data before giving up, as a float, or a :ref:`(connect timeout, + read timeout) <timeouts>` tuple. + :type timeout: float or tuple + :param verify: (optional) Whether to verify SSL certificates. + :param cert: (optional) Any user-provided SSL certificate to be trusted. + :param proxies: (optional) The proxies dictionary to apply to the request. + """ raise NotImplementedError def close(self): + """Cleans up adapter specific items.""" raise NotImplementedError @@ -154,6 +168,7 @@ class HTTPAdapter(BaseAdapter): :param proxy: The proxy to return a urllib3 ProxyManager for. :param proxy_kwargs: Extra keyword arguments used to configure the Proxy Manager. :returns: ProxyManager + :rtype: requests.packages.urllib3.ProxyManager """ if proxy in self.proxy_manager: manager = self.proxy_manager[proxy] @@ -230,6 +245,7 @@ class HTTPAdapter(BaseAdapter): :param req: The :class:`PreparedRequest <PreparedRequest>` used to generate the response. :param resp: The urllib3 response object. + :rtype: requests.Response """ response = Response() @@ -265,6 +281,7 @@ class HTTPAdapter(BaseAdapter): :param url: The URL to connect to. :param proxies: (optional) A Requests-style dictionary of proxies used on this request. + :rtype: requests.packages.urllib3.ConnectionPool """ proxy = select_proxy(url, proxies) @@ -302,6 +319,7 @@ class HTTPAdapter(BaseAdapter): :param request: The :class:`PreparedRequest <PreparedRequest>` being sent. :param proxies: A dictionary of schemes or schemes and hosts to proxy URLs. + :rtype: str """ proxy = select_proxy(request.url, proxies) scheme = urlparse(request.url).scheme @@ -343,6 +361,7 @@ class HTTPAdapter(BaseAdapter): :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`. :param proxies: The url of the proxy being used for this request. + :rtype: dict """ headers = {} username, password = get_auth_from_url(proxy) @@ -365,6 +384,7 @@ class HTTPAdapter(BaseAdapter): :param verify: (optional) Whether to verify SSL certificates. :param cert: (optional) Any user-provided SSL certificate to be trusted. :param proxies: (optional) The proxies dictionary to apply to the request. + :rtype: requests.Response """ conn = self.get_connection(request.url, proxies) diff --git a/pip/_vendor/requests/api.py b/pip/_vendor/requests/api.py index c2068d0ed..580b3f353 100644 --- a/pip/_vendor/requests/api.py +++ b/pip/_vendor/requests/api.py @@ -8,7 +8,6 @@ This module implements the Requests API. :copyright: (c) 2012 by Kenneth Reitz. :license: Apache2, see LICENSE for more details. - """ from . import sessions diff --git a/pip/_vendor/requests/auth.py b/pip/_vendor/requests/auth.py index 73f8e9da8..49bcb24a4 100644 --- a/pip/_vendor/requests/auth.py +++ b/pip/_vendor/requests/auth.py @@ -43,6 +43,7 @@ class AuthBase(object): class HTTPBasicAuth(AuthBase): """Attaches HTTP Basic Authentication to the given Request object.""" + def __init__(self, username, password): self.username = username self.password = password @@ -63,6 +64,7 @@ class HTTPBasicAuth(AuthBase): class HTTPProxyAuth(HTTPBasicAuth): """Attaches HTTP Proxy Authentication to a given Request object.""" + def __call__(self, r): r.headers['Proxy-Authorization'] = _basic_auth_str(self.username, self.password) return r @@ -70,6 +72,7 @@ class HTTPProxyAuth(HTTPBasicAuth): class HTTPDigestAuth(AuthBase): """Attaches HTTP Digest Authentication to the given Request object.""" + def __init__(self, username, password): self.username = username self.password = password @@ -87,6 +90,9 @@ class HTTPDigestAuth(AuthBase): self._thread_local.num_401_calls = None def build_digest_header(self, method, url): + """ + :rtype: str + """ realm = self._thread_local.chal['realm'] nonce = self._thread_local.chal['nonce'] @@ -179,7 +185,11 @@ class HTTPDigestAuth(AuthBase): self._thread_local.num_401_calls = 1 def handle_401(self, r, **kwargs): - """Takes the given response and tries digest-auth, if needed.""" + """ + Takes the given response and tries digest-auth, if needed. + + :rtype: requests.Response + """ if self._thread_local.pos is not None: # Rewind the file position indicator of the body to where diff --git a/pip/_vendor/requests/certs.py b/pip/_vendor/requests/certs.py index 07e647507..f922b99d7 100644 --- a/pip/_vendor/requests/certs.py +++ b/pip/_vendor/requests/certs.py @@ -2,8 +2,8 @@ # -*- coding: utf-8 -*- """ -certs.py -~~~~~~~~ +requests.certs +~~~~~~~~~~~~~~ This module returns the preferred default CA certificate bundle. diff --git a/pip/_vendor/requests/compat.py b/pip/_vendor/requests/compat.py index eb7a4bfda..353ec29e4 100644 --- a/pip/_vendor/requests/compat.py +++ b/pip/_vendor/requests/compat.py @@ -1,7 +1,11 @@ # -*- coding: utf-8 -*- """ -pythoncompat +requests.compat +~~~~~~~~~~~~~~~ + +This module handles import compatibility issues between Python 2 and +Python 3. """ from .packages import chardet diff --git a/pip/_vendor/requests/cookies.py b/pip/_vendor/requests/cookies.py index eee5168f2..41a2fde14 100644 --- a/pip/_vendor/requests/cookies.py +++ b/pip/_vendor/requests/cookies.py @@ -1,6 +1,9 @@ # -*- coding: utf-8 -*- """ +requests.cookies +~~~~~~~~~~~~~~~~ + Compatibility code to be able to use `cookielib.CookieJar` with requests. requests.utils imports from here, so be careful with imports. @@ -131,7 +134,11 @@ def extract_cookies_to_jar(jar, request, response): def get_cookie_header(jar, request): - """Produce an appropriate Cookie header string to be sent with `request`, or None.""" + """ + Produce an appropriate Cookie header string to be sent with `request`, or None. + + :rtype: str + """ r = MockRequest(request) jar.add_cookie_header(r) return r.get_new_headers().get('Cookie') @@ -158,7 +165,8 @@ def remove_cookie_by_name(cookiejar, name, domain=None, path=None): class CookieConflictError(RuntimeError): """There are two cookies that meet the criteria specified in the cookie jar. - Use .get and .set and include domain and path args in order to be more specific.""" + Use .get and .set and include domain and path args in order to be more specific. + """ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): @@ -178,12 +186,14 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): .. warning:: dictionary operations that are normally O(1) may be O(n). """ + def get(self, name, default=None, domain=None, path=None): """Dict-like get() that also supports optional domain and path args in order to resolve naming collisions from using one cookie jar over multiple domains. - .. warning:: operation is O(n), not O(1).""" + .. warning:: operation is O(n), not O(1). + """ try: return self._find_no_duplicates(name, domain, path) except KeyError: @@ -192,7 +202,8 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): def set(self, name, value, **kwargs): """Dict-like set() that also supports optional domain and path args in order to resolve naming collisions from using one cookie jar over - multiple domains.""" + multiple domains. + """ # support client code that unsets cookies by assignment of a None value: if value is None: remove_cookie_by_name(self, name, domain=kwargs.get('domain'), path=kwargs.get('path')) @@ -207,37 +218,54 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): def iterkeys(self): """Dict-like iterkeys() that returns an iterator of names of cookies - from the jar. See itervalues() and iteritems().""" + from the jar. + + .. seealso:: itervalues() and iteritems(). + """ for cookie in iter(self): yield cookie.name def keys(self): """Dict-like keys() that returns a list of names of cookies from the - jar. See values() and items().""" + jar. + + .. seealso:: values() and items(). + """ return list(self.iterkeys()) def itervalues(self): """Dict-like itervalues() that returns an iterator of values of cookies - from the jar. See iterkeys() and iteritems().""" + from the jar. + + .. seealso:: iterkeys() and iteritems(). + """ for cookie in iter(self): yield cookie.value def values(self): """Dict-like values() that returns a list of values of cookies from the - jar. See keys() and items().""" + jar. + + .. seealso:: keys() and items(). + """ return list(self.itervalues()) def iteritems(self): """Dict-like iteritems() that returns an iterator of name-value tuples - from the jar. See iterkeys() and itervalues().""" + from the jar. + + .. seealso:: iterkeys() and itervalues(). + """ for cookie in iter(self): yield cookie.name, cookie.value def items(self): """Dict-like items() that returns a list of name-value tuples from the - jar. See keys() and values(). Allows client-code to call - ``dict(RequestsCookieJar)`` and get a vanilla python dict of key value - pairs.""" + jar. Allows client-code to call ``dict(RequestsCookieJar)`` and get a + vanilla python dict of key value pairs. + + .. seealso:: keys() and values(). + """ return list(self.iteritems()) def list_domains(self): @@ -258,7 +286,10 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): def multiple_domains(self): """Returns True if there are multiple domains in the jar. - Returns False otherwise.""" + Returns False otherwise. + + :rtype: bool + """ domains = [] for cookie in iter(self): if cookie.domain is not None and cookie.domain in domains: @@ -269,7 +300,10 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): def get_dict(self, domain=None, path=None): """Takes as an argument an optional domain and path and returns a plain old Python dict of name-value pairs of cookies that meet the - requirements.""" + requirements. + + :rtype: dict + """ dictionary = {} for cookie in iter(self): if (domain is None or cookie.domain == domain) and (path is None @@ -288,20 +322,21 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): exception if there are more than one cookie with name. In that case, use the more explicit get() method instead. - .. warning:: operation is O(n), not O(1).""" - + .. warning:: operation is O(n), not O(1). + """ return self._find_no_duplicates(name) def __setitem__(self, name, value): """Dict-like __setitem__ for compatibility with client code. Throws exception if there is already a cookie of that name in the jar. In that - case, use the more explicit set() method instead.""" - + case, use the more explicit set() method instead. + """ self.set(name, value) def __delitem__(self, name): """Deletes a cookie given a name. Wraps ``cookielib.CookieJar``'s - ``remove_cookie_by_name()``.""" + ``remove_cookie_by_name()``. + """ remove_cookie_by_name(self, name) def set_cookie(self, cookie, *args, **kwargs): @@ -318,11 +353,17 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): super(RequestsCookieJar, self).update(other) def _find(self, name, domain=None, path=None): - """Requests uses this method internally to get cookie values. Takes as - args name and optional domain and path. Returns a cookie.value. If - there are conflicting cookies, _find arbitrarily chooses one. See - _find_no_duplicates if you want an exception thrown if there are - conflicting cookies.""" + """Requests uses this method internally to get cookie values. + + If there are conflicting cookies, _find arbitrarily chooses one. + See _find_no_duplicates if you want an exception thrown if there are + conflicting cookies. + + :param name: a string containing name of cookie + :param domain: (optional) string containing domain of cookie + :param path: (optional) string containing path of cookie + :return: cookie.value + """ for cookie in iter(self): if cookie.name == name: if domain is None or cookie.domain == domain: @@ -333,10 +374,16 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): def _find_no_duplicates(self, name, domain=None, path=None): """Both ``__get_item__`` and ``get`` call this function: it's never - used elsewhere in Requests. Takes as args name and optional domain and - path. Returns a cookie.value. Throws KeyError if cookie is not found - and CookieConflictError if there are multiple cookies that match name - and optionally domain and path.""" + used elsewhere in Requests. + + :param name: a string containing name of cookie + :param domain: (optional) string containing domain of cookie + :param path: (optional) string containing path of cookie + :raises KeyError: if cookie is not found + :raises CookieConflictError: if there are multiple cookies + that match name and optionally domain and path + :return: cookie.value + """ toReturn = None for cookie in iter(self): if cookie.name == name: diff --git a/pip/_vendor/requests/exceptions.py b/pip/_vendor/requests/exceptions.py index ba0b910e3..b89e0cc62 100644 --- a/pip/_vendor/requests/exceptions.py +++ b/pip/_vendor/requests/exceptions.py @@ -5,19 +5,17 @@ requests.exceptions ~~~~~~~~~~~~~~~~~~~ This module contains the set of Requests' exceptions. - """ from .packages.urllib3.exceptions import HTTPError as BaseHTTPError class RequestException(IOError): """There was an ambiguous exception that occurred while handling your - request.""" + request. + """ def __init__(self, *args, **kwargs): - """ - Initialize RequestException with `request` and `response` objects. - """ + """Initialize RequestException with `request` and `response` objects.""" response = kwargs.pop('response', None) self.response = response self.request = kwargs.pop('request', None) @@ -80,7 +78,11 @@ class InvalidSchema(RequestException, ValueError): class InvalidURL(RequestException, ValueError): - """ The URL provided was somehow invalid. """ + """The URL provided was somehow invalid.""" + + +class InvalidHeader(RequestException, ValueError): + """The header value provided was somehow invalid.""" class ChunkedEncodingError(RequestException): @@ -108,7 +110,5 @@ class RequestsWarning(Warning): class FileModeWarning(RequestsWarning, DeprecationWarning): - """ - A file was opened in text mode, but Requests determined its binary length. - """ + """A file was opened in text mode, but Requests determined its binary length.""" pass diff --git a/pip/_vendor/requests/hooks.py b/pip/_vendor/requests/hooks.py index 9da94366d..32b32de75 100644 --- a/pip/_vendor/requests/hooks.py +++ b/pip/_vendor/requests/hooks.py @@ -10,10 +10,10 @@ Available hooks: ``response``: The response generated from a Request. - """ HOOKS = ['response'] + def default_hooks(): return dict((event, []) for event in HOOKS) diff --git a/pip/_vendor/requests/models.py b/pip/_vendor/requests/models.py index fe4bec1bd..11434ef46 100644 --- a/pip/_vendor/requests/models.py +++ b/pip/_vendor/requests/models.py @@ -27,7 +27,8 @@ from .exceptions import ( from .utils import ( guess_filename, get_auth_from_url, requote_uri, stream_decode_response_unicode, to_key_val_list, parse_header_links, - iter_slices, guess_json_utf, super_len, to_native_string) + iter_slices, guess_json_utf, super_len, to_native_string, + check_header_validity) from .compat import ( cookielib, urlunparse, urlsplit, urlencode, str, bytes, StringIO, is_py2, chardet, builtin_str, basestring) @@ -37,11 +38,11 @@ from .status_codes import codes #: The set of HTTP status codes that indicate an automatically #: processable redirect. REDIRECT_STATI = ( - codes.moved, # 301 - codes.found, # 302 - codes.other, # 303 - codes.temporary_redirect, # 307 - codes.permanent_redirect, # 308 + codes.moved, # 301 + codes.found, # 302 + codes.other, # 303 + codes.temporary_redirect, # 307 + codes.permanent_redirect, # 308 ) DEFAULT_REDIRECT_LIMIT = 30 @@ -107,7 +108,6 @@ class RequestEncodingMixin(object): if parameters are supplied as a dict. The tuples may be 2-tuples (filename, fileobj), 3-tuples (filename, fileobj, contentype) or 4-tuples (filename, fileobj, contentype, custom_headers). - """ if (not files): raise ValueError("Files must be provided.") @@ -206,8 +206,8 @@ class Request(RequestHooksMixin): >>> req = requests.Request('GET', 'http://httpbin.org/get') >>> req.prepare() <PreparedRequest [GET]> - """ + def __init__(self, method=None, url=None, headers=None, files=None, data=None, params=None, auth=None, cookies=None, hooks=None, json=None): @@ -269,7 +269,6 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin): >>> s = requests.Session() >>> s.send(r) <Response [200]> - """ def __init__(self): @@ -403,10 +402,13 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin): def prepare_headers(self, headers): """Prepares the given HTTP headers.""" + self.headers = CaseInsensitiveDict() if headers: - self.headers = CaseInsensitiveDict((to_native_string(name), value) for name, value in headers.items()) - else: - self.headers = CaseInsensitiveDict() + for header in headers.items(): + # Raise exception on invalid header value. + check_header_validity(header) + name, value = header + self.headers[to_native_string(name)] = value def prepare_body(self, data, files, json=None): """Prepares the given HTTP body data.""" @@ -420,8 +422,12 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin): length = None if not data and json is not None: + # urllib3 requires a bytes-like body. Python 2's json.dumps + # provides this natively, but Python 3 gives a Unicode string. content_type = 'application/json' body = complexjson.dumps(json) + if not isinstance(body, bytes): + body = body.encode('utf-8') is_stream = all([ hasattr(data, '__iter__'), @@ -508,8 +514,8 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin): can only be called once for the life of the :class:`PreparedRequest <PreparedRequest>` object. Any subsequent calls to ``prepare_cookies`` will have no actual effect, unless the "Cookie" - header is removed beforehand.""" - + header is removed beforehand. + """ if isinstance(cookies, cookielib.CookieJar): self._cookies = cookies else: @@ -653,6 +659,12 @@ class Response(object): read into memory. This is not necessarily the length of each item returned as decoding can take place. + chunk_size must be of type int or None. A value of None will + function differently depending on the value of `stream`. + stream=True will read data as it arrives in whatever size the + chunks are received. If stream=False, data is returned as + a single chunk. + If decode_unicode is True, content will be decoded using the best available encoding based on the response. """ @@ -681,6 +693,8 @@ class Response(object): if self._content_consumed and isinstance(self._content, bool): raise StreamConsumedError() + elif chunk_size is not None and not isinstance(chunk_size, int): + raise TypeError("chunk_size must be an int, it is instead a %s." % type(chunk_size)) # simulate reading small chunks of the content reused_chunks = iter_slices(self._content, chunk_size) @@ -792,7 +806,7 @@ class Response(object): :param \*\*kwargs: Optional arguments that ``json.loads`` takes. """ - if not self.encoding and len(self.content) > 3: + if not self.encoding and self.content and len(self.content) > 3: # No encoding set. JSON RFC 4627 section 3 states we should expect # UTF-8, -16 or -32. Detect which one to use; If the detection or # decoding fails, fall back to `self.text` (using chardet to make @@ -833,12 +847,16 @@ class Response(object): """Raises stored :class:`HTTPError`, if one occurred.""" http_error_msg = '' + if isinstance(self.reason, bytes): + reason = self.reason.decode('utf-8', 'ignore') + else: + reason = self.reason if 400 <= self.status_code < 500: - http_error_msg = '%s Client Error: %s for url: %s' % (self.status_code, self.reason, self.url) + http_error_msg = u'%s Client Error: %s for url: %s' % (self.status_code, reason, self.url) elif 500 <= self.status_code < 600: - http_error_msg = '%s Server Error: %s for url: %s' % (self.status_code, self.reason, self.url) + http_error_msg = u'%s Server Error: %s for url: %s' % (self.status_code, reason, self.url) if http_error_msg: raise HTTPError(http_error_msg, response=self) @@ -850,6 +868,6 @@ class Response(object): *Note: Should not normally need to be called explicitly.* """ if not self._content_consumed: - return self.raw.close() + self.raw.close() return self.raw.release_conn() diff --git a/pip/_vendor/requests/packages/urllib3/__init__.py b/pip/_vendor/requests/packages/urllib3/__init__.py index 73668991f..c35367422 100644 --- a/pip/_vendor/requests/packages/urllib3/__init__.py +++ b/pip/_vendor/requests/packages/urllib3/__init__.py @@ -32,7 +32,7 @@ except ImportError: __author__ = 'Andrey Petrov (andrey.petrov@shazow.net)' __license__ = 'MIT' -__version__ = '1.15.1' +__version__ = '1.16' __all__ = ( 'HTTPConnectionPool', diff --git a/pip/_vendor/requests/packages/urllib3/connectionpool.py b/pip/_vendor/requests/packages/urllib3/connectionpool.py index 3fcfb1201..ab634cb4b 100644 --- a/pip/_vendor/requests/packages/urllib3/connectionpool.py +++ b/pip/_vendor/requests/packages/urllib3/connectionpool.py @@ -90,7 +90,7 @@ class ConnectionPool(object): # Return False to re-raise any potential exceptions return False - def close(): + def close(self): """ Close all pooled connections and disable the pool. """ @@ -163,6 +163,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): scheme = 'http' ConnectionCls = HTTPConnection + ResponseCls = HTTPResponse def __init__(self, host, port=None, strict=False, timeout=Timeout.DEFAULT_TIMEOUT, maxsize=1, block=False, @@ -383,8 +384,13 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): try: try: # Python 2.7, use buffering of HTTP responses httplib_response = conn.getresponse(buffering=True) - except TypeError: # Python 2.6 and older - httplib_response = conn.getresponse() + except TypeError: # Python 2.6 and older, Python 3 + try: + httplib_response = conn.getresponse() + except Exception as e: + # Remove the TypeError from the exception chain in Python 3; + # otherwise it looks like a programming error was the cause. + six.raise_from(e, None) except (SocketTimeout, BaseSSLError, SocketError) as e: self._raise_timeout(err=e, url=url, timeout_value=read_timeout) raise @@ -545,6 +551,17 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): conn = None + # Track whether `conn` needs to be released before + # returning/raising/recursing. Update this variable if necessary, and + # leave `release_conn` constant throughout the function. That way, if + # the function recurses, the original value of `release_conn` will be + # passed down into the recursive call, and its value will be respected. + # + # See issue #651 [1] for details. + # + # [1] <https://github.com/shazow/urllib3/issues/651> + release_this_conn = release_conn + # Merge the proxy headers. Only do this in HTTP. We have to copy the # headers dict so we can safely change it without those changes being # reflected in anyone else's copy. @@ -584,10 +601,10 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): response_conn = conn if not release_conn else None # Import httplib's response into our own wrapper object - response = HTTPResponse.from_httplib(httplib_response, - pool=self, - connection=response_conn, - **response_kw) + response = self.ResponseCls.from_httplib(httplib_response, + pool=self, + connection=response_conn, + **response_kw) # Everything went great! clean_exit = True @@ -633,9 +650,9 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): # Close the connection, set the variable to None, and make sure # we put the None back in the pool to avoid leaking it. conn = conn and conn.close() - release_conn = True + release_this_conn = True - if release_conn: + if release_this_conn: # Put the connection back to be reused. If the connection is # expired then it will be None, which will get replaced with a # fresh connection during _get_conn. @@ -817,7 +834,7 @@ class HTTPSConnectionPool(HTTPConnectionPool): warnings.warn(( 'Unverified HTTPS request is being made. ' 'Adding certificate verification is strongly advised. See: ' - 'https://urllib3.readthedocs.org/en/latest/security.html'), + 'https://urllib3.readthedocs.io/en/latest/security.html'), InsecureRequestWarning) diff --git a/pip/_vendor/requests/packages/urllib3/contrib/appengine.py b/pip/_vendor/requests/packages/urllib3/contrib/appengine.py index f4289c0ff..1579476c3 100644 --- a/pip/_vendor/requests/packages/urllib3/contrib/appengine.py +++ b/pip/_vendor/requests/packages/urllib3/contrib/appengine.py @@ -70,7 +70,7 @@ class AppEngineManager(RequestMethods): warnings.warn( "urllib3 is using URLFetch on Google App Engine sandbox instead " "of sockets. To use sockets directly instead of URLFetch see " - "https://urllib3.readthedocs.org/en/latest/contrib.html.", + "https://urllib3.readthedocs.io/en/latest/contrib.html.", AppEnginePlatformWarning) RequestMethods.__init__(self, headers) diff --git a/pip/_vendor/requests/packages/urllib3/contrib/socks.py b/pip/_vendor/requests/packages/urllib3/contrib/socks.py index 3748fee53..81970fa60 100644 --- a/pip/_vendor/requests/packages/urllib3/contrib/socks.py +++ b/pip/_vendor/requests/packages/urllib3/contrib/socks.py @@ -26,7 +26,7 @@ except ImportError: warnings.warn(( 'SOCKS support in urllib3 requires the installation of optional ' 'dependencies: specifically, PySocks. For more information, see ' - 'https://urllib3.readthedocs.org/en/latest/contrib.html#socks-proxies' + 'https://urllib3.readthedocs.io/en/latest/contrib.html#socks-proxies' ), DependencyWarning ) diff --git a/pip/_vendor/requests/packages/urllib3/packages/six.py b/pip/_vendor/requests/packages/urllib3/packages/six.py index 27d80112b..190c0239c 100644 --- a/pip/_vendor/requests/packages/urllib3/packages/six.py +++ b/pip/_vendor/requests/packages/urllib3/packages/six.py @@ -1,34 +1,41 @@ """Utilities for writing code that runs on Python 2 and 3""" -#Copyright (c) 2010-2011 Benjamin Peterson - -#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. - +# Copyright (c) 2010-2015 Benjamin Peterson +# +# 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. + +from __future__ import absolute_import + +import functools +import itertools import operator import sys import types __author__ = "Benjamin Peterson <benjamin@python.org>" -__version__ = "1.2.0" # Revision 41c74fef2ded +__version__ = "1.10.0" -# True if we are running on Python 3. +# Useful for very coarse version differentiation. +PY2 = sys.version_info[0] == 2 PY3 = sys.version_info[0] == 3 +PY34 = sys.version_info[0:2] >= (3, 4) if PY3: string_types = str, @@ -51,6 +58,7 @@ else: else: # It's possible to have sizeof(long) != sizeof(Py_ssize_t). class X(object): + def __len__(self): return 1 << 31 try: @@ -61,7 +69,7 @@ else: else: # 64-bit MAXSIZE = int((1 << 63) - 1) - del X + del X def _add_doc(func, doc): @@ -82,9 +90,13 @@ class _LazyDescr(object): def __get__(self, obj, tp): result = self._resolve() - setattr(obj, self.name, result) - # This is a bit ugly, but it avoids running this again. - delattr(tp, self.name) + setattr(obj, self.name, result) # Invokes __set__. + try: + # This is a bit ugly, but it avoids running this again by + # removing this descriptor. + delattr(obj.__class__, self.name) + except AttributeError: + pass return result @@ -102,6 +114,27 @@ class MovedModule(_LazyDescr): def _resolve(self): return _import_module(self.mod) + def __getattr__(self, attr): + _module = self._resolve() + value = getattr(_module, attr) + setattr(self, attr, value) + return value + + +class _LazyModule(types.ModuleType): + + def __init__(self, name): + super(_LazyModule, self).__init__(name) + self.__doc__ = self.__class__.__doc__ + + def __dir__(self): + attrs = ["__doc__", "__name__"] + attrs += [attr.name for attr in self._moved_attributes] + return attrs + + # Subclasses should override this + _moved_attributes = [] + class MovedAttribute(_LazyDescr): @@ -128,30 +161,111 @@ class MovedAttribute(_LazyDescr): return getattr(module, self.attr) +class _SixMetaPathImporter(object): + + """ + A meta path importer to import six.moves and its submodules. + + This class implements a PEP302 finder and loader. It should be compatible + with Python 2.5 and all existing versions of Python3 + """ + + def __init__(self, six_module_name): + self.name = six_module_name + self.known_modules = {} + + def _add_module(self, mod, *fullnames): + for fullname in fullnames: + self.known_modules[self.name + "." + fullname] = mod + + def _get_module(self, fullname): + return self.known_modules[self.name + "." + fullname] + + def find_module(self, fullname, path=None): + if fullname in self.known_modules: + return self + return None + + def __get_module(self, fullname): + try: + return self.known_modules[fullname] + except KeyError: + raise ImportError("This loader does not know module " + fullname) + + def load_module(self, fullname): + try: + # in case of a reload + return sys.modules[fullname] + except KeyError: + pass + mod = self.__get_module(fullname) + if isinstance(mod, MovedModule): + mod = mod._resolve() + else: + mod.__loader__ = self + sys.modules[fullname] = mod + return mod + + def is_package(self, fullname): + """ + Return true, if the named module is a package. + + We need this method to get correct spec objects with + Python 3.4 (see PEP451) + """ + return hasattr(self.__get_module(fullname), "__path__") + + def get_code(self, fullname): + """Return None + + Required, if is_package is implemented""" + self.__get_module(fullname) # eventually raises ImportError + return None + get_source = get_code # same as get_code + +_importer = _SixMetaPathImporter(__name__) + + +class _MovedItems(_LazyModule): -class _MovedItems(types.ModuleType): """Lazy loading of moved objects""" + __path__ = [] # mark as package _moved_attributes = [ MovedAttribute("cStringIO", "cStringIO", "io", "StringIO"), MovedAttribute("filter", "itertools", "builtins", "ifilter", "filter"), + MovedAttribute("filterfalse", "itertools", "itertools", "ifilterfalse", "filterfalse"), MovedAttribute("input", "__builtin__", "builtins", "raw_input", "input"), + MovedAttribute("intern", "__builtin__", "sys"), MovedAttribute("map", "itertools", "builtins", "imap", "map"), - MovedAttribute("reload_module", "__builtin__", "imp", "reload"), + MovedAttribute("getcwd", "os", "os", "getcwdu", "getcwd"), + MovedAttribute("getcwdb", "os", "os", "getcwd", "getcwdb"), + MovedAttribute("range", "__builtin__", "builtins", "xrange", "range"), + MovedAttribute("reload_module", "__builtin__", "importlib" if PY34 else "imp", "reload"), MovedAttribute("reduce", "__builtin__", "functools"), + MovedAttribute("shlex_quote", "pipes", "shlex", "quote"), MovedAttribute("StringIO", "StringIO", "io"), + MovedAttribute("UserDict", "UserDict", "collections"), + MovedAttribute("UserList", "UserList", "collections"), + MovedAttribute("UserString", "UserString", "collections"), MovedAttribute("xrange", "__builtin__", "builtins", "xrange", "range"), MovedAttribute("zip", "itertools", "builtins", "izip", "zip"), - + MovedAttribute("zip_longest", "itertools", "itertools", "izip_longest", "zip_longest"), MovedModule("builtins", "__builtin__"), MovedModule("configparser", "ConfigParser"), MovedModule("copyreg", "copy_reg"), + MovedModule("dbm_gnu", "gdbm", "dbm.gnu"), + MovedModule("_dummy_thread", "dummy_thread", "_dummy_thread"), MovedModule("http_cookiejar", "cookielib", "http.cookiejar"), MovedModule("http_cookies", "Cookie", "http.cookies"), MovedModule("html_entities", "htmlentitydefs", "html.entities"), MovedModule("html_parser", "HTMLParser", "html.parser"), MovedModule("http_client", "httplib", "http.client"), + MovedModule("email_mime_multipart", "email.MIMEMultipart", "email.mime.multipart"), + MovedModule("email_mime_nonmultipart", "email.MIMENonMultipart", "email.mime.nonmultipart"), + MovedModule("email_mime_text", "email.MIMEText", "email.mime.text"), + MovedModule("email_mime_base", "email.MIMEBase", "email.mime.base"), MovedModule("BaseHTTPServer", "BaseHTTPServer", "http.server"), MovedModule("CGIHTTPServer", "CGIHTTPServer", "http.server"), MovedModule("SimpleHTTPServer", "SimpleHTTPServer", "http.server"), @@ -159,12 +273,14 @@ _moved_attributes = [ MovedModule("queue", "Queue"), MovedModule("reprlib", "repr"), MovedModule("socketserver", "SocketServer"), + MovedModule("_thread", "thread", "_thread"), MovedModule("tkinter", "Tkinter"), MovedModule("tkinter_dialog", "Dialog", "tkinter.dialog"), MovedModule("tkinter_filedialog", "FileDialog", "tkinter.filedialog"), MovedModule("tkinter_scrolledtext", "ScrolledText", "tkinter.scrolledtext"), MovedModule("tkinter_simpledialog", "SimpleDialog", "tkinter.simpledialog"), MovedModule("tkinter_tix", "Tix", "tkinter.tix"), + MovedModule("tkinter_ttk", "ttk", "tkinter.ttk"), MovedModule("tkinter_constants", "Tkconstants", "tkinter.constants"), MovedModule("tkinter_dnd", "Tkdnd", "tkinter.dnd"), MovedModule("tkinter_colorchooser", "tkColorChooser", @@ -176,14 +292,195 @@ _moved_attributes = [ MovedModule("tkinter_messagebox", "tkMessageBox", "tkinter.messagebox"), MovedModule("tkinter_tksimpledialog", "tkSimpleDialog", "tkinter.simpledialog"), + MovedModule("urllib_parse", __name__ + ".moves.urllib_parse", "urllib.parse"), + MovedModule("urllib_error", __name__ + ".moves.urllib_error", "urllib.error"), + MovedModule("urllib", __name__ + ".moves.urllib", __name__ + ".moves.urllib"), MovedModule("urllib_robotparser", "robotparser", "urllib.robotparser"), - MovedModule("winreg", "_winreg"), + MovedModule("xmlrpc_client", "xmlrpclib", "xmlrpc.client"), + MovedModule("xmlrpc_server", "SimpleXMLRPCServer", "xmlrpc.server"), ] +# Add windows specific modules. +if sys.platform == "win32": + _moved_attributes += [ + MovedModule("winreg", "_winreg"), + ] + for attr in _moved_attributes: setattr(_MovedItems, attr.name, attr) + if isinstance(attr, MovedModule): + _importer._add_module(attr, "moves." + attr.name) del attr -moves = sys.modules[__name__ + ".moves"] = _MovedItems("moves") +_MovedItems._moved_attributes = _moved_attributes + +moves = _MovedItems(__name__ + ".moves") +_importer._add_module(moves, "moves") + + +class Module_six_moves_urllib_parse(_LazyModule): + + """Lazy loading of moved objects in six.moves.urllib_parse""" + + +_urllib_parse_moved_attributes = [ + MovedAttribute("ParseResult", "urlparse", "urllib.parse"), + MovedAttribute("SplitResult", "urlparse", "urllib.parse"), + MovedAttribute("parse_qs", "urlparse", "urllib.parse"), + MovedAttribute("parse_qsl", "urlparse", "urllib.parse"), + MovedAttribute("urldefrag", "urlparse", "urllib.parse"), + MovedAttribute("urljoin", "urlparse", "urllib.parse"), + MovedAttribute("urlparse", "urlparse", "urllib.parse"), + MovedAttribute("urlsplit", "urlparse", "urllib.parse"), + MovedAttribute("urlunparse", "urlparse", "urllib.parse"), + MovedAttribute("urlunsplit", "urlparse", "urllib.parse"), + MovedAttribute("quote", "urllib", "urllib.parse"), + MovedAttribute("quote_plus", "urllib", "urllib.parse"), + MovedAttribute("unquote", "urllib", "urllib.parse"), + MovedAttribute("unquote_plus", "urllib", "urllib.parse"), + MovedAttribute("urlencode", "urllib", "urllib.parse"), + MovedAttribute("splitquery", "urllib", "urllib.parse"), + MovedAttribute("splittag", "urllib", "urllib.parse"), + MovedAttribute("splituser", "urllib", "urllib.parse"), + MovedAttribute("uses_fragment", "urlparse", "urllib.parse"), + MovedAttribute("uses_netloc", "urlparse", "urllib.parse"), + MovedAttribute("uses_params", "urlparse", "urllib.parse"), + MovedAttribute("uses_query", "urlparse", "urllib.parse"), + MovedAttribute("uses_relative", "urlparse", "urllib.parse"), +] +for attr in _urllib_parse_moved_attributes: + setattr(Module_six_moves_urllib_parse, attr.name, attr) +del attr + +Module_six_moves_urllib_parse._moved_attributes = _urllib_parse_moved_attributes + +_importer._add_module(Module_six_moves_urllib_parse(__name__ + ".moves.urllib_parse"), + "moves.urllib_parse", "moves.urllib.parse") + + +class Module_six_moves_urllib_error(_LazyModule): + + """Lazy loading of moved objects in six.moves.urllib_error""" + + +_urllib_error_moved_attributes = [ + MovedAttribute("URLError", "urllib2", "urllib.error"), + MovedAttribute("HTTPError", "urllib2", "urllib.error"), + MovedAttribute("ContentTooShortError", "urllib", "urllib.error"), +] +for attr in _urllib_error_moved_attributes: + setattr(Module_six_moves_urllib_error, attr.name, attr) +del attr + +Module_six_moves_urllib_error._moved_attributes = _urllib_error_moved_attributes + +_importer._add_module(Module_six_moves_urllib_error(__name__ + ".moves.urllib.error"), + "moves.urllib_error", "moves.urllib.error") + + +class Module_six_moves_urllib_request(_LazyModule): + + """Lazy loading of moved objects in six.moves.urllib_request""" + + +_urllib_request_moved_attributes = [ + MovedAttribute("urlopen", "urllib2", "urllib.request"), + MovedAttribute("install_opener", "urllib2", "urllib.request"), + MovedAttribute("build_opener", "urllib2", "urllib.request"), + MovedAttribute("pathname2url", "urllib", "urllib.request"), + MovedAttribute("url2pathname", "urllib", "urllib.request"), + MovedAttribute("getproxies", "urllib", "urllib.request"), + MovedAttribute("Request", "urllib2", "urllib.request"), + MovedAttribute("OpenerDirector", "urllib2", "urllib.request"), + MovedAttribute("HTTPDefaultErrorHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPRedirectHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPCookieProcessor", "urllib2", "urllib.request"), + MovedAttribute("ProxyHandler", "urllib2", "urllib.request"), + MovedAttribute("BaseHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPPasswordMgr", "urllib2", "urllib.request"), + MovedAttribute("HTTPPasswordMgrWithDefaultRealm", "urllib2", "urllib.request"), + MovedAttribute("AbstractBasicAuthHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPBasicAuthHandler", "urllib2", "urllib.request"), + MovedAttribute("ProxyBasicAuthHandler", "urllib2", "urllib.request"), + MovedAttribute("AbstractDigestAuthHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPDigestAuthHandler", "urllib2", "urllib.request"), + MovedAttribute("ProxyDigestAuthHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPSHandler", "urllib2", "urllib.request"), + MovedAttribute("FileHandler", "urllib2", "urllib.request"), + MovedAttribute("FTPHandler", "urllib2", "urllib.request"), + MovedAttribute("CacheFTPHandler", "urllib2", "urllib.request"), + MovedAttribute("UnknownHandler", "urllib2", "urllib.request"), + MovedAttribute("HTTPErrorProcessor", "urllib2", "urllib.request"), + MovedAttribute("urlretrieve", "urllib", "urllib.request"), + MovedAttribute("urlcleanup", "urllib", "urllib.request"), + MovedAttribute("URLopener", "urllib", "urllib.request"), + MovedAttribute("FancyURLopener", "urllib", "urllib.request"), + MovedAttribute("proxy_bypass", "urllib", "urllib.request"), +] +for attr in _urllib_request_moved_attributes: + setattr(Module_six_moves_urllib_request, attr.name, attr) +del attr + +Module_six_moves_urllib_request._moved_attributes = _urllib_request_moved_attributes + +_importer._add_module(Module_six_moves_urllib_request(__name__ + ".moves.urllib.request"), + "moves.urllib_request", "moves.urllib.request") + + +class Module_six_moves_urllib_response(_LazyModule): + + """Lazy loading of moved objects in six.moves.urllib_response""" + + +_urllib_response_moved_attributes = [ + MovedAttribute("addbase", "urllib", "urllib.response"), + MovedAttribute("addclosehook", "urllib", "urllib.response"), + MovedAttribute("addinfo", "urllib", "urllib.response"), + MovedAttribute("addinfourl", "urllib", "urllib.response"), +] +for attr in _urllib_response_moved_attributes: + setattr(Module_six_moves_urllib_response, attr.name, attr) +del attr + +Module_six_moves_urllib_response._moved_attributes = _urllib_response_moved_attributes + +_importer._add_module(Module_six_moves_urllib_response(__name__ + ".moves.urllib.response"), + "moves.urllib_response", "moves.urllib.response") + + +class Module_six_moves_urllib_robotparser(_LazyModule): + + """Lazy loading of moved objects in six.moves.urllib_robotparser""" + + +_urllib_robotparser_moved_attributes = [ + MovedAttribute("RobotFileParser", "robotparser", "urllib.robotparser"), +] +for attr in _urllib_robotparser_moved_attributes: + setattr(Module_six_moves_urllib_robotparser, attr.name, attr) +del attr + +Module_six_moves_urllib_robotparser._moved_attributes = _urllib_robotparser_moved_attributes + +_importer._add_module(Module_six_moves_urllib_robotparser(__name__ + ".moves.urllib.robotparser"), + "moves.urllib_robotparser", "moves.urllib.robotparser") + + +class Module_six_moves_urllib(types.ModuleType): + + """Create a six.moves.urllib namespace that resembles the Python 3 namespace""" + __path__ = [] # mark as package + parse = _importer._get_module("moves.urllib_parse") + error = _importer._get_module("moves.urllib_error") + request = _importer._get_module("moves.urllib_request") + response = _importer._get_module("moves.urllib_response") + robotparser = _importer._get_module("moves.urllib_robotparser") + + def __dir__(self): + return ['parse', 'error', 'request', 'response', 'robotparser'] + +_importer._add_module(Module_six_moves_urllib(__name__ + ".moves.urllib"), + "moves.urllib") def add_move(move): @@ -206,22 +503,18 @@ if PY3: _meth_func = "__func__" _meth_self = "__self__" + _func_closure = "__closure__" _func_code = "__code__" _func_defaults = "__defaults__" - - _iterkeys = "keys" - _itervalues = "values" - _iteritems = "items" + _func_globals = "__globals__" else: _meth_func = "im_func" _meth_self = "im_self" + _func_closure = "func_closure" _func_code = "func_code" _func_defaults = "func_defaults" - - _iterkeys = "iterkeys" - _itervalues = "itervalues" - _iteritems = "iteritems" + _func_globals = "func_globals" try: @@ -232,18 +525,33 @@ except NameError: next = advance_iterator +try: + callable = callable +except NameError: + def callable(obj): + return any("__call__" in klass.__dict__ for klass in type(obj).__mro__) + + if PY3: def get_unbound_function(unbound): return unbound - Iterator = object + create_bound_method = types.MethodType - def callable(obj): - return any("__call__" in klass.__dict__ for klass in type(obj).__mro__) + def create_unbound_method(func, cls): + return func + + Iterator = object else: def get_unbound_function(unbound): return unbound.im_func + def create_bound_method(func, obj): + return types.MethodType(func, obj, obj.__class__) + + def create_unbound_method(func, cls): + return types.MethodType(func, None, cls) + class Iterator(object): def next(self): @@ -256,90 +564,179 @@ _add_doc(get_unbound_function, get_method_function = operator.attrgetter(_meth_func) get_method_self = operator.attrgetter(_meth_self) +get_function_closure = operator.attrgetter(_func_closure) get_function_code = operator.attrgetter(_func_code) get_function_defaults = operator.attrgetter(_func_defaults) +get_function_globals = operator.attrgetter(_func_globals) + + +if PY3: + def iterkeys(d, **kw): + return iter(d.keys(**kw)) + + def itervalues(d, **kw): + return iter(d.values(**kw)) + + def iteritems(d, **kw): + return iter(d.items(**kw)) + + def iterlists(d, **kw): + return iter(d.lists(**kw)) + + viewkeys = operator.methodcaller("keys") + + viewvalues = operator.methodcaller("values") + + viewitems = operator.methodcaller("items") +else: + def iterkeys(d, **kw): + return d.iterkeys(**kw) + def itervalues(d, **kw): + return d.itervalues(**kw) -def iterkeys(d): - """Return an iterator over the keys of a dictionary.""" - return iter(getattr(d, _iterkeys)()) + def iteritems(d, **kw): + return d.iteritems(**kw) -def itervalues(d): - """Return an iterator over the values of a dictionary.""" - return iter(getattr(d, _itervalues)()) + def iterlists(d, **kw): + return d.iterlists(**kw) -def iteritems(d): - """Return an iterator over the (key, value) pairs of a dictionary.""" - return iter(getattr(d, _iteritems)()) + viewkeys = operator.methodcaller("viewkeys") + + viewvalues = operator.methodcaller("viewvalues") + + viewitems = operator.methodcaller("viewitems") + +_add_doc(iterkeys, "Return an iterator over the keys of a dictionary.") +_add_doc(itervalues, "Return an iterator over the values of a dictionary.") +_add_doc(iteritems, + "Return an iterator over the (key, value) pairs of a dictionary.") +_add_doc(iterlists, + "Return an iterator over the (key, [values]) pairs of a dictionary.") if PY3: def b(s): return s.encode("latin-1") + def u(s): return s - if sys.version_info[1] <= 1: - def int2byte(i): - return bytes((i,)) - else: - # This is about 2x faster than the implementation above on 3.2+ - int2byte = operator.methodcaller("to_bytes", 1, "big") + unichr = chr + import struct + int2byte = struct.Struct(">B").pack + del struct + byte2int = operator.itemgetter(0) + indexbytes = operator.getitem + iterbytes = iter import io StringIO = io.StringIO BytesIO = io.BytesIO + _assertCountEqual = "assertCountEqual" + if sys.version_info[1] <= 1: + _assertRaisesRegex = "assertRaisesRegexp" + _assertRegex = "assertRegexpMatches" + else: + _assertRaisesRegex = "assertRaisesRegex" + _assertRegex = "assertRegex" else: def b(s): return s + # Workaround for standalone backslash + def u(s): - return unicode(s, "unicode_escape") + return unicode(s.replace(r'\\', r'\\\\'), "unicode_escape") + unichr = unichr int2byte = chr + + def byte2int(bs): + return ord(bs[0]) + + def indexbytes(buf, i): + return ord(buf[i]) + iterbytes = functools.partial(itertools.imap, ord) import StringIO StringIO = BytesIO = StringIO.StringIO + _assertCountEqual = "assertItemsEqual" + _assertRaisesRegex = "assertRaisesRegexp" + _assertRegex = "assertRegexpMatches" _add_doc(b, """Byte literal""") _add_doc(u, """Text literal""") -if PY3: - import builtins - exec_ = getattr(builtins, "exec") +def assertCountEqual(self, *args, **kwargs): + return getattr(self, _assertCountEqual)(*args, **kwargs) + +def assertRaisesRegex(self, *args, **kwargs): + return getattr(self, _assertRaisesRegex)(*args, **kwargs) + + +def assertRegex(self, *args, **kwargs): + return getattr(self, _assertRegex)(*args, **kwargs) + + +if PY3: + exec_ = getattr(moves.builtins, "exec") def reraise(tp, value, tb=None): + if value is None: + value = tp() if value.__traceback__ is not tb: raise value.with_traceback(tb) raise value - - print_ = getattr(builtins, "print") - del builtins - else: - def exec_(code, globs=None, locs=None): + def exec_(_code_, _globs_=None, _locs_=None): """Execute code in a namespace.""" - if globs is None: + if _globs_ is None: frame = sys._getframe(1) - globs = frame.f_globals - if locs is None: - locs = frame.f_locals + _globs_ = frame.f_globals + if _locs_ is None: + _locs_ = frame.f_locals del frame - elif locs is None: - locs = globs - exec("""exec code in globs, locs""") - + elif _locs_ is None: + _locs_ = _globs_ + exec("""exec _code_ in _globs_, _locs_""") exec_("""def reraise(tp, value, tb=None): raise tp, value, tb """) +if sys.version_info[:2] == (3, 2): + exec_("""def raise_from(value, from_value): + if from_value is None: + raise value + raise value from from_value +""") +elif sys.version_info[:2] > (3, 2): + exec_("""def raise_from(value, from_value): + raise value from from_value +""") +else: + def raise_from(value, from_value): + raise value + + +print_ = getattr(moves.builtins, "print", None) +if print_ is None: def print_(*args, **kwargs): - """The new-style print function.""" + """The new-style print function for Python 2.4 and 2.5.""" fp = kwargs.pop("file", sys.stdout) if fp is None: return + def write(data): if not isinstance(data, basestring): data = str(data) + # If the file has an encoding, encode unicode with it. + if (isinstance(fp, file) and + isinstance(data, unicode) and + fp.encoding is not None): + errors = getattr(fp, "errors", None) + if errors is None: + errors = "strict" + data = data.encode(fp.encoding, errors) fp.write(data) want_unicode = False sep = kwargs.pop("sep", None) @@ -376,10 +773,96 @@ else: write(sep) write(arg) write(end) +if sys.version_info[:2] < (3, 3): + _print = print_ + + def print_(*args, **kwargs): + fp = kwargs.get("file", sys.stdout) + flush = kwargs.pop("flush", False) + _print(*args, **kwargs) + if flush and fp is not None: + fp.flush() _add_doc(reraise, """Reraise an exception.""") +if sys.version_info[0:2] < (3, 4): + def wraps(wrapped, assigned=functools.WRAPPER_ASSIGNMENTS, + updated=functools.WRAPPER_UPDATES): + def wrapper(f): + f = functools.wraps(wrapped, assigned, updated)(f) + f.__wrapped__ = wrapped + return f + return wrapper +else: + wraps = functools.wraps + -def with_metaclass(meta, base=object): +def with_metaclass(meta, *bases): """Create a base class with a metaclass.""" - return meta("NewBase", (base,), {}) + # This requires a bit of explanation: the basic idea is to make a dummy + # metaclass for one level of class instantiation that replaces itself with + # the actual metaclass. + class metaclass(meta): + + def __new__(cls, name, this_bases, d): + return meta(name, bases, d) + return type.__new__(metaclass, 'temporary_class', (), {}) + + +def add_metaclass(metaclass): + """Class decorator for creating a class with a metaclass.""" + def wrapper(cls): + orig_vars = cls.__dict__.copy() + slots = orig_vars.get('__slots__') + if slots is not None: + if isinstance(slots, str): + slots = [slots] + for slots_var in slots: + orig_vars.pop(slots_var) + orig_vars.pop('__dict__', None) + orig_vars.pop('__weakref__', None) + return metaclass(cls.__name__, cls.__bases__, orig_vars) + return wrapper + + +def python_2_unicode_compatible(klass): + """ + A decorator that defines __unicode__ and __str__ methods under Python 2. + Under Python 3 it does nothing. + + To support Python 2 and 3 with a single code base, define a __str__ method + returning text and apply this decorator to the class. + """ + if PY2: + if '__str__' not in klass.__dict__: + raise ValueError("@python_2_unicode_compatible cannot be applied " + "to %s because it doesn't define __str__()." % + klass.__name__) + klass.__unicode__ = klass.__str__ + klass.__str__ = lambda self: self.__unicode__().encode('utf-8') + return klass + + +# Complete the moves implementation. +# This code is at the end of this module to speed up module loading. +# Turn this module into a package. +__path__ = [] # required for PEP 302 and PEP 451 +__package__ = __name__ # see PEP 366 @ReservedAssignment +if globals().get("__spec__") is not None: + __spec__.submodule_search_locations = [] # PEP 451 @UndefinedVariable +# Remove other six meta path importers, since they cause problems. This can +# happen if six is removed from sys.modules and then reloaded. (Setuptools does +# this for some reason.) +if sys.meta_path: + for i, importer in enumerate(sys.meta_path): + # Here's some real nastiness: Another "instance" of the six module might + # be floating around. Therefore, we can't use isinstance() to check for + # the six meta path importer, since the other six instance will have + # inserted an importer with different class. + if (type(importer).__name__ == "_SixMetaPathImporter" and + importer.name == __name__): + del sys.meta_path[i] + break + del i, importer +# Finally, add the importer to the meta path import hook. +sys.meta_path.append(_importer) diff --git a/pip/_vendor/requests/packages/urllib3/poolmanager.py b/pip/_vendor/requests/packages/urllib3/poolmanager.py index 1023dcba3..7ed00b1ce 100644 --- a/pip/_vendor/requests/packages/urllib3/poolmanager.py +++ b/pip/_vendor/requests/packages/urllib3/poolmanager.py @@ -1,4 +1,6 @@ from __future__ import absolute_import +import collections +import functools import logging try: # Python 3 @@ -23,6 +25,59 @@ log = logging.getLogger(__name__) SSL_KEYWORDS = ('key_file', 'cert_file', 'cert_reqs', 'ca_certs', 'ssl_version', 'ca_cert_dir') +# The base fields to use when determining what pool to get a connection from; +# these do not rely on the ``connection_pool_kw`` and can be determined by the +# URL and potentially the ``urllib3.connection.port_by_scheme`` dictionary. +# +# All custom key schemes should include the fields in this key at a minimum. +BasePoolKey = collections.namedtuple('BasePoolKey', ('scheme', 'host', 'port')) + +# The fields to use when determining what pool to get a HTTP and HTTPS +# connection from. All additional fields must be present in the PoolManager's +# ``connection_pool_kw`` instance variable. +HTTPPoolKey = collections.namedtuple( + 'HTTPPoolKey', BasePoolKey._fields + ('timeout', 'retries', 'strict', + 'block', 'source_address') +) +HTTPSPoolKey = collections.namedtuple( + 'HTTPSPoolKey', HTTPPoolKey._fields + SSL_KEYWORDS +) + + +def _default_key_normalizer(key_class, request_context): + """ + Create a pool key of type ``key_class`` for a request. + + According to RFC 3986, both the scheme and host are case-insensitive. + Therefore, this function normalizes both before constructing the pool + key for an HTTPS request. If you wish to change this behaviour, provide + alternate callables to ``key_fn_by_scheme``. + + :param key_class: + The class to use when constructing the key. This should be a namedtuple + with the ``scheme`` and ``host`` keys at a minimum. + + :param request_context: + A dictionary-like object that contain the context for a request. + It should contain a key for each field in the :class:`HTTPPoolKey` + """ + context = {} + for key in key_class._fields: + context[key] = request_context.get(key) + context['scheme'] = context['scheme'].lower() + context['host'] = context['host'].lower() + return key_class(**context) + + +# A dictionary that maps a scheme to a callable that creates a pool key. +# This can be used to alter the way pool keys are constructed, if desired. +# Each PoolManager makes a copy of this dictionary so they can be configured +# globally here, or individually on the instance. +key_fn_by_scheme = { + 'http': functools.partial(_default_key_normalizer, HTTPPoolKey), + 'https': functools.partial(_default_key_normalizer, HTTPSPoolKey), +} + pool_classes_by_scheme = { 'http': HTTPConnectionPool, 'https': HTTPSConnectionPool, @@ -65,8 +120,10 @@ class PoolManager(RequestMethods): self.pools = RecentlyUsedContainer(num_pools, dispose_func=lambda p: p.close()) - # Locally set the pool classes so other PoolManagers can override them. + # Locally set the pool classes and keys so other PoolManagers can + # override them. self.pool_classes_by_scheme = pool_classes_by_scheme + self.key_fn_by_scheme = key_fn_by_scheme.copy() def __enter__(self): return self @@ -113,10 +170,36 @@ class PoolManager(RequestMethods): if not host: raise LocationValueError("No host specified.") - scheme = scheme or 'http' - port = port or port_by_scheme.get(scheme, 80) - pool_key = (scheme, host, port) + request_context = self.connection_pool_kw.copy() + request_context['scheme'] = scheme or 'http' + if not port: + port = port_by_scheme.get(request_context['scheme'].lower(), 80) + request_context['port'] = port + request_context['host'] = host + + return self.connection_from_context(request_context) + def connection_from_context(self, request_context): + """ + Get a :class:`ConnectionPool` based on the request context. + + ``request_context`` must at least contain the ``scheme`` key and its + value must be a key in ``key_fn_by_scheme`` instance variable. + """ + scheme = request_context['scheme'].lower() + pool_key_constructor = self.key_fn_by_scheme[scheme] + pool_key = pool_key_constructor(request_context) + + return self.connection_from_pool_key(pool_key) + + def connection_from_pool_key(self, pool_key): + """ + Get a :class:`ConnectionPool` based on the provided pool key. + + ``pool_key`` should be a namedtuple that only contains immutable + objects. At a minimum it must have the ``scheme``, ``host``, and + ``port`` fields. + """ with self.pools.lock: # If the scheme, host, or port doesn't match existing open # connections, open a new ConnectionPool. @@ -125,7 +208,7 @@ class PoolManager(RequestMethods): return pool # Make a fresh ConnectionPool of the desired type - pool = self._new_pool(scheme, host, port) + pool = self._new_pool(pool_key.scheme, pool_key.host, pool_key.port) self.pools[pool_key] = pool return pool diff --git a/pip/_vendor/requests/packages/urllib3/response.py b/pip/_vendor/requests/packages/urllib3/response.py index ac1b2f19e..556790327 100644 --- a/pip/_vendor/requests/packages/urllib3/response.py +++ b/pip/_vendor/requests/packages/urllib3/response.py @@ -165,6 +165,10 @@ class HTTPResponse(io.IOBase): if self._fp: return self.read(cache_content=True) + @property + def connection(self): + return self._connection + def tell(self): """ Obtain the number of bytes pulled over the wire so far. May differ from diff --git a/pip/_vendor/requests/packages/urllib3/util/connection.py b/pip/_vendor/requests/packages/urllib3/util/connection.py index 01a4812f2..5e761352f 100644 --- a/pip/_vendor/requests/packages/urllib3/util/connection.py +++ b/pip/_vendor/requests/packages/urllib3/util/connection.py @@ -46,6 +46,8 @@ def is_connection_dropped(conn): # Platform-specific # This function is copied from socket.py in the Python 2.7 standard # library test suite. Added to its signature is only `socket_options`. +# One additional modification is that we avoid binding to IPv6 servers +# discovered in DNS if the system doesn't have IPv6 functionality. def create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None, socket_options=None): """Connect to *address* and return the socket object. @@ -64,14 +66,19 @@ def create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, if host.startswith('['): host = host.strip('[]') err = None - for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM): + + # Using the value from allowed_gai_family() in the context of getaddrinfo lets + # us select whether to work with IPv4 DNS records, IPv6 records, or both. + # The original create_connection function always returns all records. + family = allowed_gai_family() + + for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM): af, socktype, proto, canonname, sa = res sock = None try: sock = socket.socket(af, socktype, proto) # If provided, set socket level options before connecting. - # This is the only addition urllib3 makes to this function. _set_socket_options(sock, socket_options) if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT: @@ -99,3 +106,39 @@ def _set_socket_options(sock, options): for opt in options: sock.setsockopt(*opt) + + +def allowed_gai_family(): + """This function is designed to work in the context of + getaddrinfo, where family=socket.AF_UNSPEC is the default and + will perform a DNS search for both IPv6 and IPv4 records.""" + + family = socket.AF_INET + if HAS_IPV6: + family = socket.AF_UNSPEC + return family + + +def _has_ipv6(host): + """ Returns True if the system can bind an IPv6 address. """ + sock = None + has_ipv6 = False + + if socket.has_ipv6: + # has_ipv6 returns true if cPython was compiled with IPv6 support. + # It does not tell us if the system has IPv6 support enabled. To + # determine that we must bind to an IPv6 address. + # https://github.com/shazow/urllib3/pull/611 + # https://bugs.python.org/issue658327 + try: + sock = socket.socket(socket.AF_INET6) + sock.bind((host, 0)) + has_ipv6 = True + except Exception: + pass + + if sock: + sock.close() + return has_ipv6 + +HAS_IPV6 = _has_ipv6('::1') diff --git a/pip/_vendor/requests/packages/urllib3/util/retry.py b/pip/_vendor/requests/packages/urllib3/util/retry.py index 2d3aa20d0..d379833c5 100644 --- a/pip/_vendor/requests/packages/urllib3/util/retry.py +++ b/pip/_vendor/requests/packages/urllib3/util/retry.py @@ -80,21 +80,27 @@ class Retry(object): Set of uppercased HTTP method verbs that we should retry on. By default, we only retry on methods which are considered to be - indempotent (multiple requests with the same parameters end with the + idempotent (multiple requests with the same parameters end with the same state). See :attr:`Retry.DEFAULT_METHOD_WHITELIST`. + Set to a ``False`` value to retry on any verb. + :param iterable status_forcelist: - A set of HTTP status codes that we should force a retry on. + A set of integer HTTP status codes that we should force a retry on. + A retry is initiated if the request method is in ``method_whitelist`` + and the response status code is in ``status_forcelist``. By default, this is disabled with ``None``. :param float backoff_factor: - A backoff factor to apply between attempts. urllib3 will sleep for:: + A backoff factor to apply between attempts after the second try + (most errors are resolved immediately by a second try without a + delay). urllib3 will sleep for:: {backoff factor} * (2 ^ ({number of total retries} - 1)) seconds. If the backoff_factor is 0.1, then :func:`.sleep` will sleep - for [0.1s, 0.2s, 0.4s, ...] between retries. It will never be longer + for [0.0s, 0.2s, 0.4s, ...] between retries. It will never be longer than :attr:`Retry.BACKOFF_MAX`. By default, backoff is disabled (set to 0). diff --git a/pip/_vendor/requests/packages/urllib3/util/ssl_.py b/pip/_vendor/requests/packages/urllib3/util/ssl_.py index e8d9e7d29..4a64d7ef9 100644 --- a/pip/_vendor/requests/packages/urllib3/util/ssl_.py +++ b/pip/_vendor/requests/packages/urllib3/util/ssl_.py @@ -117,7 +117,7 @@ except ImportError: 'urllib3 from configuring SSL appropriately and may cause ' 'certain SSL connections to fail. You can upgrade to a newer ' 'version of Python to solve this. For more information, see ' - 'https://urllib3.readthedocs.org/en/latest/security.html' + 'https://urllib3.readthedocs.io/en/latest/security.html' '#insecureplatformwarning.', InsecurePlatformWarning ) @@ -313,7 +313,7 @@ def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None, 'This may cause the server to present an incorrect TLS ' 'certificate, which can cause validation failures. You can upgrade to ' 'a newer version of Python to solve this. For more information, see ' - 'https://urllib3.readthedocs.org/en/latest/security.html' + 'https://urllib3.readthedocs.io/en/latest/security.html' '#snimissingwarning.', SNIMissingWarning ) diff --git a/pip/_vendor/requests/sessions.py b/pip/_vendor/requests/sessions.py index 45be9733e..bcbcc880f 100644 --- a/pip/_vendor/requests/sessions.py +++ b/pip/_vendor/requests/sessions.py @@ -6,7 +6,6 @@ requests.session This module provides a Session object to manage and persist settings across requests (cookies, auth, proxies). - """ import os from collections import Mapping @@ -40,9 +39,8 @@ REDIRECT_CACHE_SIZE = 1000 def merge_setting(request_setting, session_setting, dict_class=OrderedDict): - """ - Determines appropriate setting for a given request, taking into account the - explicit setting on that request, and the setting in the session. If a + """Determines appropriate setting for a given request, taking into account + the explicit setting on that request, and the setting in the session. If a setting is a dictionary, they will be merged together using `dict_class` """ @@ -72,8 +70,7 @@ def merge_setting(request_setting, session_setting, dict_class=OrderedDict): def merge_hooks(request_hooks, session_hooks, dict_class=OrderedDict): - """ - Properly merges both requests and session hooks. + """Properly merges both requests and session hooks. This is necessary because when request_hooks == {'response': []}, the merge breaks Session hooks entirely. @@ -143,9 +140,10 @@ class SessionRedirectMixin(object): # https://github.com/kennethreitz/requests/issues/1084 if resp.status_code not in (codes.temporary_redirect, codes.permanent_redirect): - if 'Content-Length' in prepared_request.headers: - del prepared_request.headers['Content-Length'] - + # https://github.com/kennethreitz/requests/issues/3490 + purged_headers = ('Content-Length', 'Content-Type', 'Transfer-Encoding') + for header in purged_headers: + prepared_request.headers.pop(header, None) prepared_request.body = None headers = prepared_request.headers @@ -185,8 +183,7 @@ class SessionRedirectMixin(object): yield resp def rebuild_auth(self, prepared_request, response): - """ - When being redirected we may want to strip authentication from the + """When being redirected we may want to strip authentication from the request to avoid leaking credentials. This method intelligently removes and reapplies authentication where possible to avoid credential loss. """ @@ -195,7 +192,7 @@ class SessionRedirectMixin(object): if 'Authorization' in headers: # If we get redirected to a new host, we should strip out any - # authentication headers. + # authentication headers. original_parsed = urlparse(response.request.url) redirect_parsed = urlparse(url) @@ -210,8 +207,7 @@ class SessionRedirectMixin(object): return def rebuild_proxies(self, prepared_request, proxies): - """ - This method re-evaluates the proxy configuration by considering the + """This method re-evaluates the proxy configuration by considering the environment variables. If we are redirected to a URL covered by NO_PROXY, we strip the proxy configuration. Otherwise, we set missing proxy keys for this URL (in case they were stripped by a previous @@ -219,6 +215,8 @@ class SessionRedirectMixin(object): This method also replaces the Proxy-Authorization header where necessary. + + :rtype: dict """ headers = prepared_request.headers url = prepared_request.url @@ -228,10 +226,10 @@ class SessionRedirectMixin(object): if self.trust_env and not should_bypass_proxies(url): environ_proxies = get_environ_proxies(url) - proxy = environ_proxies.get(scheme) + proxy = environ_proxies.get('all', environ_proxies.get(scheme)) if proxy: - new_proxies.setdefault(scheme, environ_proxies[scheme]) + new_proxies.setdefault(scheme, proxy) if 'Proxy-Authorization' in headers: del headers['Proxy-Authorization'] @@ -329,6 +327,8 @@ class Session(SessionRedirectMixin): #: Maximum number of redirects allowed. If the request exceeds this #: limit, a :class:`TooManyRedirects` exception is raised. + #: This defaults to requests.models.DEFAULT_REDIRECT_LIMIT, which is + #: 30. self.max_redirects = DEFAULT_REDIRECT_LIMIT #: Trust environment settings for proxy configuration, default @@ -363,6 +363,7 @@ class Session(SessionRedirectMixin): :param request: :class:`Request` instance to prepare with this session's settings. + :rtype: requests.PreparedRequest """ cookies = request.cookies or {} @@ -374,7 +375,6 @@ class Session(SessionRedirectMixin): merged_cookies = merge_cookies( merge_cookies(RequestsCookieJar(), self.cookies), cookies) - # Set environment's basic authentication if not explicitly set. auth = request.auth if self.trust_env and not auth and not self.auth: @@ -444,7 +444,7 @@ class Session(SessionRedirectMixin): :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. :rtype: requests.Response - """ + """ # Create the Request. req = Request( method = method.upper(), @@ -481,6 +481,7 @@ class Session(SessionRedirectMixin): :param url: URL for the new :class:`Request` object. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ kwargs.setdefault('allow_redirects', True) @@ -491,6 +492,7 @@ class Session(SessionRedirectMixin): :param url: URL for the new :class:`Request` object. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ kwargs.setdefault('allow_redirects', True) @@ -501,6 +503,7 @@ class Session(SessionRedirectMixin): :param url: URL for the new :class:`Request` object. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ kwargs.setdefault('allow_redirects', False) @@ -513,6 +516,7 @@ class Session(SessionRedirectMixin): :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param json: (optional) json to send in the body of the :class:`Request`. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ return self.request('POST', url, data=data, json=json, **kwargs) @@ -523,6 +527,7 @@ class Session(SessionRedirectMixin): :param url: URL for the new :class:`Request` object. :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ return self.request('PUT', url, data=data, **kwargs) @@ -533,6 +538,7 @@ class Session(SessionRedirectMixin): :param url: URL for the new :class:`Request` object. :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ return self.request('PATCH', url, data=data, **kwargs) @@ -542,12 +548,17 @@ class Session(SessionRedirectMixin): :param url: URL for the new :class:`Request` object. :param \*\*kwargs: Optional arguments that ``request`` takes. + :rtype: requests.Response """ return self.request('DELETE', url, **kwargs) def send(self, request, **kwargs): - """Send a given PreparedRequest.""" + """ + Send a given PreparedRequest. + + :rtype: requests.Response + """ # Set defaults that the hooks can utilize to ensure they always have # the correct parameters to reproduce the previous request. kwargs.setdefault('stream', self.stream) @@ -619,7 +630,11 @@ class Session(SessionRedirectMixin): return r def merge_environment_settings(self, url, proxies, stream, verify, cert): - """Check the environment and merge it with some settings.""" + """ + Check the environment and merge it with some settings. + + :rtype: dict + """ # Gather clues from the surrounding environment. if self.trust_env: # Set environment's proxies. @@ -643,7 +658,11 @@ class Session(SessionRedirectMixin): 'cert': cert} def get_adapter(self, url): - """Returns the appropriate connection adapter for the given URL.""" + """ + Returns the appropriate connection adapter for the given URL. + + :rtype: requests.adapters.BaseAdapter + """ for (prefix, adapter) in self.adapters.items(): if url.lower().startswith(prefix): @@ -660,8 +679,8 @@ class Session(SessionRedirectMixin): def mount(self, prefix, adapter): """Registers a connection adapter to a prefix. - Adapters are sorted in descending order by key length.""" - + Adapters are sorted in descending order by key length. + """ self.adapters[prefix] = adapter keys_to_move = [k for k in self.adapters if len(k) < len(prefix)] @@ -684,6 +703,10 @@ class Session(SessionRedirectMixin): def session(): - """Returns a :class:`Session` for context-management.""" + """ + Returns a :class:`Session` for context-management. + + :rtype: Session + """ return Session() diff --git a/pip/_vendor/requests/status_codes.py b/pip/_vendor/requests/status_codes.py index 0137c91d9..db2986bb1 100644 --- a/pip/_vendor/requests/status_codes.py +++ b/pip/_vendor/requests/status_codes.py @@ -31,7 +31,7 @@ _codes = { 306: ('switch_proxy',), 307: ('temporary_redirect', 'temporary_moved', 'temporary'), 308: ('permanent_redirect', - 'resume_incomplete', 'resume',), # These 2 to be removed in 3.0 + 'resume_incomplete', 'resume',), # These 2 to be removed in 3.0 # Client Error. 400: ('bad_request', 'bad'), diff --git a/pip/_vendor/requests/structures.py b/pip/_vendor/requests/structures.py index 991056e47..05d2b3f57 100644 --- a/pip/_vendor/requests/structures.py +++ b/pip/_vendor/requests/structures.py @@ -5,7 +5,6 @@ requests.structures ~~~~~~~~~~~~~~~~~~~ Data structures that power Requests. - """ import collections @@ -14,8 +13,7 @@ from .compat import OrderedDict class CaseInsensitiveDict(collections.MutableMapping): - """ - A case-insensitive ``dict``-like object. + """A case-insensitive ``dict``-like object. Implements all methods and operations of ``collections.MutableMapping`` as well as dict's ``copy``. Also @@ -39,8 +37,8 @@ class CaseInsensitiveDict(collections.MutableMapping): If the constructor, ``.update``, or equality comparison operations are given keys that have equal ``.lower()``s, the behavior is undefined. - """ + def __init__(self, data=None, **kwargs): self._store = OrderedDict() if data is None: @@ -87,6 +85,7 @@ class CaseInsensitiveDict(collections.MutableMapping): def __repr__(self): return str(dict(self.items())) + class LookupDict(dict): """Dictionary lookup object.""" diff --git a/pip/_vendor/requests/utils.py b/pip/_vendor/requests/utils.py index c08448ccb..dfeb77d9d 100644 --- a/pip/_vendor/requests/utils.py +++ b/pip/_vendor/requests/utils.py @@ -6,7 +6,6 @@ requests.utils This module provides utility functions that are used within Requests that are also useful for external consumption. - """ import cgi @@ -27,7 +26,7 @@ from .compat import (quote, urlparse, bytes, str, OrderedDict, unquote, is_py2, basestring) from .cookies import RequestsCookieJar, cookiejar_from_dict from .structures import CaseInsensitiveDict -from .exceptions import InvalidURL, FileModeWarning +from .exceptions import InvalidURL, InvalidHeader, FileModeWarning _hush_pyflakes = (RequestsCookieJar,) @@ -165,6 +164,8 @@ def from_key_val_list(value): ValueError: need more than 1 value to unpack >>> from_key_val_list({'key': 'val'}) OrderedDict([('key', 'val')]) + + :rtype: OrderedDict """ if value is None: return None @@ -187,6 +188,8 @@ def to_key_val_list(value): [('key', 'val')] >>> to_key_val_list('string') ValueError: cannot encode objects that are not 2-tuples. + + :rtype: list """ if value is None: return None @@ -222,6 +225,7 @@ def parse_list_header(value): :param value: a string with a list header. :return: :class:`list` + :rtype: list """ result = [] for item in _parse_list_header(value): @@ -252,6 +256,7 @@ def parse_dict_header(value): :param value: a string with a dict header. :return: :class:`dict` + :rtype: dict """ result = {} for item in _parse_list_header(value): @@ -272,6 +277,7 @@ def unquote_header_value(value, is_filename=False): using for quoting. :param value: the header value to unquote. + :rtype: str """ if value and value[0] == value[-1] == '"': # this is not the real unquoting, but fixing this so that the @@ -294,6 +300,7 @@ def dict_from_cookiejar(cj): """Returns a key/value dictionary from a CookieJar. :param cj: CookieJar object to extract cookies from. + :rtype: dict """ cookie_dict = {} @@ -309,6 +316,7 @@ def add_dict_to_cookiejar(cj, cookie_dict): :param cj: CookieJar to insert cookies into. :param cookie_dict: Dict of key/values to insert into CookieJar. + :rtype: CookieJar """ cj2 = cookiejar_from_dict(cookie_dict) @@ -340,6 +348,7 @@ def get_encoding_from_headers(headers): """Returns encodings from given HTTP Header Dict. :param headers: dictionary to extract encoding from. + :rtype: str """ content_type = headers.get('content-type') @@ -377,6 +386,8 @@ def stream_decode_response_unicode(iterator, r): def iter_slices(string, slice_length): """Iterate over slices of a string.""" pos = 0 + if slice_length is None or slice_length <= 0: + slice_length = len(string) while pos < len(string): yield string[pos:pos + slice_length] pos += slice_length @@ -392,6 +403,7 @@ def get_unicode_from_response(r): 1. charset from content-type 2. fall back and replace all unicode characters + :rtype: str """ warnings.warn(( 'In requests 3.0, get_unicode_from_response will be removed. For ' @@ -426,6 +438,8 @@ UNRESERVED_SET = frozenset( def unquote_unreserved(uri): """Un-escape any percent-escape sequences in a URI that are unreserved characters. This leaves all reserved, illegal and non-ASCII bytes encoded. + + :rtype: str """ parts = uri.split('%') for i in range(1, len(parts)): @@ -450,6 +464,8 @@ def requote_uri(uri): This function passes the given URI through an unquote/quote cycle to ensure that it is fully and consistently quoted. + + :rtype: str """ safe_with_percent = "!#$%&'()*+,/:;=?@[]~" safe_without_percent = "!#$&'()*+,/:;=?@[]~" @@ -466,10 +482,12 @@ def requote_uri(uri): def address_in_network(ip, net): - """ - This function allows you to check if on IP belongs to a network subnet + """This function allows you to check if on IP belongs to a network subnet + Example: returns True if ip = 192.168.1.1 and net = 192.168.1.0/24 returns False if ip = 192.168.1.1 and net = 192.168.100.0/24 + + :rtype: bool """ ipaddr = struct.unpack('=L', socket.inet_aton(ip))[0] netaddr, bits = net.split('/') @@ -479,15 +497,20 @@ def address_in_network(ip, net): def dotted_netmask(mask): - """ - Converts mask from /xx format to xxx.xxx.xxx.xxx + """Converts mask from /xx format to xxx.xxx.xxx.xxx + Example: if mask is 24 function returns 255.255.255.0 + + :rtype: str """ bits = 0xffffffff ^ (1 << 32 - mask) - 1 return socket.inet_ntoa(struct.pack('>I', bits)) def is_ipv4_address(string_ip): + """ + :rtype: bool + """ try: socket.inet_aton(string_ip) except socket.error: @@ -496,7 +519,11 @@ def is_ipv4_address(string_ip): def is_valid_cidr(string_network): - """Very simple check of the cidr format in no_proxy variable""" + """ + Very simple check of the cidr format in no_proxy variable. + + :rtype: bool + """ if string_network.count('/') == 1: try: mask = int(string_network.split('/')[1]) @@ -518,6 +545,8 @@ def is_valid_cidr(string_network): def should_bypass_proxies(url): """ Returns whether we should bypass proxies or not. + + :rtype: bool """ get_proxy = lambda k: os.environ.get(k) or os.environ.get(k.upper()) @@ -539,6 +568,10 @@ def should_bypass_proxies(url): if is_valid_cidr(proxy_ip): if address_in_network(ip, proxy_ip): return True + elif ip == proxy_ip: + # If no_proxy ip was defined in plain IP notation instead of cidr notation & + # matches the IP of the index + return True else: for host in no_proxy: if netloc.endswith(host) or netloc.split(':')[0].endswith(host): @@ -564,7 +597,11 @@ def should_bypass_proxies(url): def get_environ_proxies(url): - """Return a dict of environment proxies.""" + """ + Return a dict of environment proxies. + + :rtype: dict + """ if should_bypass_proxies(url): return {} else: @@ -580,20 +617,36 @@ def select_proxy(url, proxies): proxies = proxies or {} urlparts = urlparse(url) if urlparts.hostname is None: - proxy = None - else: - proxy = proxies.get(urlparts.scheme+'://'+urlparts.hostname) - if proxy is None: - proxy = proxies.get(urlparts.scheme) + return proxies.get('all', proxies.get(urlparts.scheme)) + + proxy_keys = [ + 'all://' + urlparts.hostname, + 'all', + urlparts.scheme + '://' + urlparts.hostname, + urlparts.scheme, + ] + proxy = None + for proxy_key in proxy_keys: + if proxy_key in proxies: + proxy = proxies[proxy_key] + break + return proxy def default_user_agent(name="python-requests"): - """Return a string representing the default user agent.""" + """ + Return a string representing the default user agent. + + :rtype: str + """ return '%s/%s' % (name, __version__) def default_headers(): + """ + :rtype: requests.structures.CaseInsensitiveDict + """ return CaseInsensitiveDict({ 'User-Agent': default_user_agent(), 'Accept-Encoding': ', '.join(('gzip', 'deflate')), @@ -607,6 +660,7 @@ def parse_header_links(value): i.e. Link: <http:/.../front.jpeg>; rel=front; type="image/jpeg",<http://.../back.jpeg>; rel=back;type="image/jpeg" + :rtype: list """ links = [] @@ -641,6 +695,9 @@ _null3 = _null * 3 def guess_json_utf(data): + """ + :rtype: str + """ # JSON always starts with two ASCII characters, so detection is as # easy as counting the nulls and from their location and count # determine the encoding. Also detect a BOM, if present. @@ -671,7 +728,10 @@ def guess_json_utf(data): def prepend_scheme_if_needed(url, new_scheme): """Given a URL that may or may not have a scheme, prepend the given scheme. - Does not replace a present scheme with the one provided as an argument.""" + Does not replace a present scheme with the one provided as an argument. + + :rtype: str + """ scheme, netloc, path, params, query, fragment = urlparse(url, new_scheme) # urlparse is a finicky beast, and sometimes decides that there isn't a @@ -685,7 +745,10 @@ def prepend_scheme_if_needed(url, new_scheme): def get_auth_from_url(url): """Given a url with authentication components, extract them into a tuple of - username,password.""" + username,password. + + :rtype: (str,str) + """ parsed = urlparse(url) try: @@ -697,10 +760,9 @@ def get_auth_from_url(url): def to_native_string(string, encoding='ascii'): - """ - Given a string object, regardless of type, returns a representation of that - string in the native string type, encoding and decoding where necessary. - This assumes ASCII unless told otherwise. + """Given a string object, regardless of type, returns a representation of + that string in the native string type, encoding and decoding where + necessary. This assumes ASCII unless told otherwise. """ if isinstance(string, builtin_str): out = string @@ -713,9 +775,36 @@ def to_native_string(string, encoding='ascii'): return out +# Moved outside of function to avoid recompile every call +_CLEAN_HEADER_REGEX_BYTE = re.compile(b'^\\S[^\\r\\n]*$|^$') +_CLEAN_HEADER_REGEX_STR = re.compile(r'^\S[^\r\n]*$|^$') + +def check_header_validity(header): + """Verifies that header value is a string which doesn't contain + leading whitespace or return characters. This prevents unintended + header injection. + + :param header: tuple, in the format (name, value). + """ + name, value = header + + if isinstance(value, bytes): + pat = _CLEAN_HEADER_REGEX_BYTE + else: + pat = _CLEAN_HEADER_REGEX_STR + try: + if not pat.match(value): + raise InvalidHeader("Invalid return character or leading space in header: %s" % name) + except TypeError: + raise InvalidHeader("Header value %s must be of type str or bytes, " + "not %s" % (value, type(value))) + + def urldefragauth(url): """ - Given a url remove the fragment and the authentication part + Given a url remove the fragment and the authentication part. + + :rtype: str """ scheme, netloc, path, params, query, fragment = urlparse(url) diff --git a/pip/_vendor/vendor.txt b/pip/_vendor/vendor.txt index f82b97d13..b744fc7bf 100644 --- a/pip/_vendor/vendor.txt +++ b/pip/_vendor/vendor.txt @@ -1,13 +1,15 @@ -distlib==0.2.3 -distro==0.6.0 -html5lib==1.0b8 +distlib==0.2.4 +distro==1.0.0 +html5lib==1.0b10 six==1.10.0 colorama==0.3.7 -requests==2.10.0 -CacheControl==0.11.6 +requests==2.11.1 +CacheControl==0.11.7 lockfile==0.12.2 +ordereddict==1.1 # Only needed on 2.6 progress==1.2 -ipaddress==1.0.16 # Only needed on 2.6 and 2.7 -packaging==16.7 -pyparsing==2.1.1 +ipaddress==1.0.17 # Only needed on 2.6 and 2.7 +packaging==16.8 +pyparsing==2.1.10 retrying==1.3.3 +webencodings==0.5 diff --git a/pip/_vendor/webencodings/__init__.py b/pip/_vendor/webencodings/__init__.py new file mode 100644 index 000000000..03d5d3576 --- /dev/null +++ b/pip/_vendor/webencodings/__init__.py @@ -0,0 +1,342 @@ +# coding: utf8 +""" + + webencodings + ~~~~~~~~~~~~ + + This is a Python implementation of the `WHATWG Encoding standard + <http://encoding.spec.whatwg.org/>`. See README for details. + + :copyright: Copyright 2012 by Simon Sapin + :license: BSD, see LICENSE for details. + +""" + +from __future__ import unicode_literals + +import codecs + +from .labels import LABELS + + +VERSION = '0.5' + + +# Some names in Encoding are not valid Python aliases. Remap these. +PYTHON_NAMES = { + 'iso-8859-8-i': 'iso-8859-8', + 'x-mac-cyrillic': 'mac-cyrillic', + 'macintosh': 'mac-roman', + 'windows-874': 'cp874'} + +CACHE = {} + + +def ascii_lower(string): + r"""Transform (only) ASCII letters to lower case: A-Z is mapped to a-z. + + :param string: An Unicode string. + :returns: A new Unicode string. + + This is used for `ASCII case-insensitive + <http://encoding.spec.whatwg.org/#ascii-case-insensitive>`_ + matching of encoding labels. + The same matching is also used, among other things, + for `CSS keywords <http://dev.w3.org/csswg/css-values/#keywords>`_. + + This is different from the :meth:`~py:str.lower` method of Unicode strings + which also affect non-ASCII characters, + sometimes mapping them into the ASCII range: + + >>> keyword = u'Bac\N{KELVIN SIGN}ground' + >>> assert keyword.lower() == u'background' + >>> assert ascii_lower(keyword) != keyword.lower() + >>> assert ascii_lower(keyword) == u'bac\N{KELVIN SIGN}ground' + + """ + # This turns out to be faster than unicode.translate() + return string.encode('utf8').lower().decode('utf8') + + +def lookup(label): + """ + Look for an encoding by its label. + This is the spec’s `get an encoding + <http://encoding.spec.whatwg.org/#concept-encoding-get>`_ algorithm. + Supported labels are listed there. + + :param label: A string. + :returns: + An :class:`Encoding` object, or :obj:`None` for an unknown label. + + """ + # Only strip ASCII whitespace: U+0009, U+000A, U+000C, U+000D, and U+0020. + label = ascii_lower(label.strip('\t\n\f\r ')) + name = LABELS.get(label) + if name is None: + return None + encoding = CACHE.get(name) + if encoding is None: + if name == 'x-user-defined': + from .x_user_defined import codec_info + else: + python_name = PYTHON_NAMES.get(name, name) + # Any python_name value that gets to here should be valid. + codec_info = codecs.lookup(python_name) + encoding = Encoding(name, codec_info) + CACHE[name] = encoding + return encoding + + +def _get_encoding(encoding_or_label): + """ + Accept either an encoding object or label. + + :param encoding: An :class:`Encoding` object or a label string. + :returns: An :class:`Encoding` object. + :raises: :exc:`~exceptions.LookupError` for an unknown label. + + """ + if hasattr(encoding_or_label, 'codec_info'): + return encoding_or_label + + encoding = lookup(encoding_or_label) + if encoding is None: + raise LookupError('Unknown encoding label: %r' % encoding_or_label) + return encoding + + +class Encoding(object): + """Reresents a character encoding such as UTF-8, + that can be used for decoding or encoding. + + .. attribute:: name + + Canonical name of the encoding + + .. attribute:: codec_info + + The actual implementation of the encoding, + a stdlib :class:`~codecs.CodecInfo` object. + See :func:`codecs.register`. + + """ + def __init__(self, name, codec_info): + self.name = name + self.codec_info = codec_info + + def __repr__(self): + return '<Encoding %s>' % self.name + + +#: The UTF-8 encoding. Should be used for new content and formats. +UTF8 = lookup('utf-8') + +_UTF16LE = lookup('utf-16le') +_UTF16BE = lookup('utf-16be') + + +def decode(input, fallback_encoding, errors='replace'): + """ + Decode a single string. + + :param input: A byte string + :param fallback_encoding: + An :class:`Encoding` object or a label string. + The encoding to use if :obj:`input` does note have a BOM. + :param errors: Type of error handling. See :func:`codecs.register`. + :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. + :return: + A ``(output, encoding)`` tuple of an Unicode string + and an :obj:`Encoding`. + + """ + # Fail early if `encoding` is an invalid label. + fallback_encoding = _get_encoding(fallback_encoding) + bom_encoding, input = _detect_bom(input) + encoding = bom_encoding or fallback_encoding + return encoding.codec_info.decode(input, errors)[0], encoding + + +def _detect_bom(input): + """Return (bom_encoding, input), with any BOM removed from the input.""" + if input.startswith(b'\xFF\xFE'): + return _UTF16LE, input[2:] + if input.startswith(b'\xFE\xFF'): + return _UTF16BE, input[2:] + if input.startswith(b'\xEF\xBB\xBF'): + return UTF8, input[3:] + return None, input + + +def encode(input, encoding=UTF8, errors='strict'): + """ + Encode a single string. + + :param input: An Unicode string. + :param encoding: An :class:`Encoding` object or a label string. + :param errors: Type of error handling. See :func:`codecs.register`. + :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. + :return: A byte string. + + """ + return _get_encoding(encoding).codec_info.encode(input, errors)[0] + + +def iter_decode(input, fallback_encoding, errors='replace'): + """ + "Pull"-based decoder. + + :param input: + An iterable of byte strings. + + The input is first consumed just enough to determine the encoding + based on the precense of a BOM, + then consumed on demand when the return value is. + :param fallback_encoding: + An :class:`Encoding` object or a label string. + The encoding to use if :obj:`input` does note have a BOM. + :param errors: Type of error handling. See :func:`codecs.register`. + :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. + :returns: + An ``(output, encoding)`` tuple. + :obj:`output` is an iterable of Unicode strings, + :obj:`encoding` is the :obj:`Encoding` that is being used. + + """ + + decoder = IncrementalDecoder(fallback_encoding, errors) + generator = _iter_decode_generator(input, decoder) + encoding = next(generator) + return generator, encoding + + +def _iter_decode_generator(input, decoder): + """Return a generator that first yields the :obj:`Encoding`, + then yields output chukns as Unicode strings. + + """ + decode = decoder.decode + input = iter(input) + for chunck in input: + output = decode(chunck) + if output: + assert decoder.encoding is not None + yield decoder.encoding + yield output + break + else: + # Input exhausted without determining the encoding + output = decode(b'', final=True) + assert decoder.encoding is not None + yield decoder.encoding + if output: + yield output + return + + for chunck in input: + output = decode(chunck) + if output: + yield output + output = decode(b'', final=True) + if output: + yield output + + +def iter_encode(input, encoding=UTF8, errors='strict'): + """ + “Pull”-based encoder. + + :param input: An iterable of Unicode strings. + :param encoding: An :class:`Encoding` object or a label string. + :param errors: Type of error handling. See :func:`codecs.register`. + :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. + :returns: An iterable of byte strings. + + """ + # Fail early if `encoding` is an invalid label. + encode = IncrementalEncoder(encoding, errors).encode + return _iter_encode_generator(input, encode) + + +def _iter_encode_generator(input, encode): + for chunck in input: + output = encode(chunck) + if output: + yield output + output = encode('', final=True) + if output: + yield output + + +class IncrementalDecoder(object): + """ + “Push”-based decoder. + + :param fallback_encoding: + An :class:`Encoding` object or a label string. + The encoding to use if :obj:`input` does note have a BOM. + :param errors: Type of error handling. See :func:`codecs.register`. + :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. + + """ + def __init__(self, fallback_encoding, errors='replace'): + # Fail early if `encoding` is an invalid label. + self._fallback_encoding = _get_encoding(fallback_encoding) + self._errors = errors + self._buffer = b'' + self._decoder = None + #: The actual :class:`Encoding` that is being used, + #: or :obj:`None` if that is not determined yet. + #: (Ie. if there is not enough input yet to determine + #: if there is a BOM.) + self.encoding = None # Not known yet. + + def decode(self, input, final=False): + """Decode one chunk of the input. + + :param input: A byte string. + :param final: + Indicate that no more input is available. + Must be :obj:`True` if this is the last call. + :returns: An Unicode string. + + """ + decoder = self._decoder + if decoder is not None: + return decoder(input, final) + + input = self._buffer + input + encoding, input = _detect_bom(input) + if encoding is None: + if len(input) < 3 and not final: # Not enough data yet. + self._buffer = input + return '' + else: # No BOM + encoding = self._fallback_encoding + decoder = encoding.codec_info.incrementaldecoder(self._errors).decode + self._decoder = decoder + self.encoding = encoding + return decoder(input, final) + + +class IncrementalEncoder(object): + """ + “Push”-based encoder. + + :param encoding: An :class:`Encoding` object or a label string. + :param errors: Type of error handling. See :func:`codecs.register`. + :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. + + .. method:: encode(input, final=False) + + :param input: An Unicode string. + :param final: + Indicate that no more input is available. + Must be :obj:`True` if this is the last call. + :returns: A byte string. + + """ + def __init__(self, encoding=UTF8, errors='strict'): + encoding = _get_encoding(encoding) + self.encode = encoding.codec_info.incrementalencoder(errors).encode diff --git a/pip/_vendor/webencodings/labels.py b/pip/_vendor/webencodings/labels.py new file mode 100644 index 000000000..29cbf91ef --- /dev/null +++ b/pip/_vendor/webencodings/labels.py @@ -0,0 +1,231 @@ +""" + + webencodings.labels + ~~~~~~~~~~~~~~~~~~~ + + Map encoding labels to their name. + + :copyright: Copyright 2012 by Simon Sapin + :license: BSD, see LICENSE for details. + +""" + +# XXX Do not edit! +# This file is automatically generated by mklabels.py + +LABELS = { + 'unicode-1-1-utf-8': 'utf-8', + 'utf-8': 'utf-8', + 'utf8': 'utf-8', + '866': 'ibm866', + 'cp866': 'ibm866', + 'csibm866': 'ibm866', + 'ibm866': 'ibm866', + 'csisolatin2': 'iso-8859-2', + 'iso-8859-2': 'iso-8859-2', + 'iso-ir-101': 'iso-8859-2', + 'iso8859-2': 'iso-8859-2', + 'iso88592': 'iso-8859-2', + 'iso_8859-2': 'iso-8859-2', + 'iso_8859-2:1987': 'iso-8859-2', + 'l2': 'iso-8859-2', + 'latin2': 'iso-8859-2', + 'csisolatin3': 'iso-8859-3', + 'iso-8859-3': 'iso-8859-3', + 'iso-ir-109': 'iso-8859-3', + 'iso8859-3': 'iso-8859-3', + 'iso88593': 'iso-8859-3', + 'iso_8859-3': 'iso-8859-3', + 'iso_8859-3:1988': 'iso-8859-3', + 'l3': 'iso-8859-3', + 'latin3': 'iso-8859-3', + 'csisolatin4': 'iso-8859-4', + 'iso-8859-4': 'iso-8859-4', + 'iso-ir-110': 'iso-8859-4', + 'iso8859-4': 'iso-8859-4', + 'iso88594': 'iso-8859-4', + 'iso_8859-4': 'iso-8859-4', + 'iso_8859-4:1988': 'iso-8859-4', + 'l4': 'iso-8859-4', + 'latin4': 'iso-8859-4', + 'csisolatincyrillic': 'iso-8859-5', + 'cyrillic': 'iso-8859-5', + 'iso-8859-5': 'iso-8859-5', + 'iso-ir-144': 'iso-8859-5', + 'iso8859-5': 'iso-8859-5', + 'iso88595': 'iso-8859-5', + 'iso_8859-5': 'iso-8859-5', + 'iso_8859-5:1988': 'iso-8859-5', + 'arabic': 'iso-8859-6', + 'asmo-708': 'iso-8859-6', + 'csiso88596e': 'iso-8859-6', + 'csiso88596i': 'iso-8859-6', + 'csisolatinarabic': 'iso-8859-6', + 'ecma-114': 'iso-8859-6', + 'iso-8859-6': 'iso-8859-6', + 'iso-8859-6-e': 'iso-8859-6', + 'iso-8859-6-i': 'iso-8859-6', + 'iso-ir-127': 'iso-8859-6', + 'iso8859-6': 'iso-8859-6', + 'iso88596': 'iso-8859-6', + 'iso_8859-6': 'iso-8859-6', + 'iso_8859-6:1987': 'iso-8859-6', + 'csisolatingreek': 'iso-8859-7', + 'ecma-118': 'iso-8859-7', + 'elot_928': 'iso-8859-7', + 'greek': 'iso-8859-7', + 'greek8': 'iso-8859-7', + 'iso-8859-7': 'iso-8859-7', + 'iso-ir-126': 'iso-8859-7', + 'iso8859-7': 'iso-8859-7', + 'iso88597': 'iso-8859-7', + 'iso_8859-7': 'iso-8859-7', + 'iso_8859-7:1987': 'iso-8859-7', + 'sun_eu_greek': 'iso-8859-7', + 'csiso88598e': 'iso-8859-8', + 'csisolatinhebrew': 'iso-8859-8', + 'hebrew': 'iso-8859-8', + 'iso-8859-8': 'iso-8859-8', + 'iso-8859-8-e': 'iso-8859-8', + 'iso-ir-138': 'iso-8859-8', + 'iso8859-8': 'iso-8859-8', + 'iso88598': 'iso-8859-8', + 'iso_8859-8': 'iso-8859-8', + 'iso_8859-8:1988': 'iso-8859-8', + 'visual': 'iso-8859-8', + 'csiso88598i': 'iso-8859-8-i', + 'iso-8859-8-i': 'iso-8859-8-i', + 'logical': 'iso-8859-8-i', + 'csisolatin6': 'iso-8859-10', + 'iso-8859-10': 'iso-8859-10', + 'iso-ir-157': 'iso-8859-10', + 'iso8859-10': 'iso-8859-10', + 'iso885910': 'iso-8859-10', + 'l6': 'iso-8859-10', + 'latin6': 'iso-8859-10', + 'iso-8859-13': 'iso-8859-13', + 'iso8859-13': 'iso-8859-13', + 'iso885913': 'iso-8859-13', + 'iso-8859-14': 'iso-8859-14', + 'iso8859-14': 'iso-8859-14', + 'iso885914': 'iso-8859-14', + 'csisolatin9': 'iso-8859-15', + 'iso-8859-15': 'iso-8859-15', + 'iso8859-15': 'iso-8859-15', + 'iso885915': 'iso-8859-15', + 'iso_8859-15': 'iso-8859-15', + 'l9': 'iso-8859-15', + 'iso-8859-16': 'iso-8859-16', + 'cskoi8r': 'koi8-r', + 'koi': 'koi8-r', + 'koi8': 'koi8-r', + 'koi8-r': 'koi8-r', + 'koi8_r': 'koi8-r', + 'koi8-u': 'koi8-u', + 'csmacintosh': 'macintosh', + 'mac': 'macintosh', + 'macintosh': 'macintosh', + 'x-mac-roman': 'macintosh', + 'dos-874': 'windows-874', + 'iso-8859-11': 'windows-874', + 'iso8859-11': 'windows-874', + 'iso885911': 'windows-874', + 'tis-620': 'windows-874', + 'windows-874': 'windows-874', + 'cp1250': 'windows-1250', + 'windows-1250': 'windows-1250', + 'x-cp1250': 'windows-1250', + 'cp1251': 'windows-1251', + 'windows-1251': 'windows-1251', + 'x-cp1251': 'windows-1251', + 'ansi_x3.4-1968': 'windows-1252', + 'ascii': 'windows-1252', + 'cp1252': 'windows-1252', + 'cp819': 'windows-1252', + 'csisolatin1': 'windows-1252', + 'ibm819': 'windows-1252', + 'iso-8859-1': 'windows-1252', + 'iso-ir-100': 'windows-1252', + 'iso8859-1': 'windows-1252', + 'iso88591': 'windows-1252', + 'iso_8859-1': 'windows-1252', + 'iso_8859-1:1987': 'windows-1252', + 'l1': 'windows-1252', + 'latin1': 'windows-1252', + 'us-ascii': 'windows-1252', + 'windows-1252': 'windows-1252', + 'x-cp1252': 'windows-1252', + 'cp1253': 'windows-1253', + 'windows-1253': 'windows-1253', + 'x-cp1253': 'windows-1253', + 'cp1254': 'windows-1254', + 'csisolatin5': 'windows-1254', + 'iso-8859-9': 'windows-1254', + 'iso-ir-148': 'windows-1254', + 'iso8859-9': 'windows-1254', + 'iso88599': 'windows-1254', + 'iso_8859-9': 'windows-1254', + 'iso_8859-9:1989': 'windows-1254', + 'l5': 'windows-1254', + 'latin5': 'windows-1254', + 'windows-1254': 'windows-1254', + 'x-cp1254': 'windows-1254', + 'cp1255': 'windows-1255', + 'windows-1255': 'windows-1255', + 'x-cp1255': 'windows-1255', + 'cp1256': 'windows-1256', + 'windows-1256': 'windows-1256', + 'x-cp1256': 'windows-1256', + 'cp1257': 'windows-1257', + 'windows-1257': 'windows-1257', + 'x-cp1257': 'windows-1257', + 'cp1258': 'windows-1258', + 'windows-1258': 'windows-1258', + 'x-cp1258': 'windows-1258', + 'x-mac-cyrillic': 'x-mac-cyrillic', + 'x-mac-ukrainian': 'x-mac-cyrillic', + 'chinese': 'gbk', + 'csgb2312': 'gbk', + 'csiso58gb231280': 'gbk', + 'gb2312': 'gbk', + 'gb_2312': 'gbk', + 'gb_2312-80': 'gbk', + 'gbk': 'gbk', + 'iso-ir-58': 'gbk', + 'x-gbk': 'gbk', + 'gb18030': 'gb18030', + 'hz-gb-2312': 'hz-gb-2312', + 'big5': 'big5', + 'big5-hkscs': 'big5', + 'cn-big5': 'big5', + 'csbig5': 'big5', + 'x-x-big5': 'big5', + 'cseucpkdfmtjapanese': 'euc-jp', + 'euc-jp': 'euc-jp', + 'x-euc-jp': 'euc-jp', + 'csiso2022jp': 'iso-2022-jp', + 'iso-2022-jp': 'iso-2022-jp', + 'csshiftjis': 'shift_jis', + 'ms_kanji': 'shift_jis', + 'shift-jis': 'shift_jis', + 'shift_jis': 'shift_jis', + 'sjis': 'shift_jis', + 'windows-31j': 'shift_jis', + 'x-sjis': 'shift_jis', + 'cseuckr': 'euc-kr', + 'csksc56011987': 'euc-kr', + 'euc-kr': 'euc-kr', + 'iso-ir-149': 'euc-kr', + 'korean': 'euc-kr', + 'ks_c_5601-1987': 'euc-kr', + 'ks_c_5601-1989': 'euc-kr', + 'ksc5601': 'euc-kr', + 'ksc_5601': 'euc-kr', + 'windows-949': 'euc-kr', + 'csiso2022kr': 'iso-2022-kr', + 'iso-2022-kr': 'iso-2022-kr', + 'utf-16be': 'utf-16be', + 'utf-16': 'utf-16le', + 'utf-16le': 'utf-16le', + 'x-user-defined': 'x-user-defined', +} diff --git a/pip/_vendor/webencodings/mklabels.py b/pip/_vendor/webencodings/mklabels.py new file mode 100644 index 000000000..295dc928b --- /dev/null +++ b/pip/_vendor/webencodings/mklabels.py @@ -0,0 +1,59 @@ +""" + + webencodings.mklabels + ~~~~~~~~~~~~~~~~~~~~~ + + Regenarate the webencodings.labels module. + + :copyright: Copyright 2012 by Simon Sapin + :license: BSD, see LICENSE for details. + +""" + +import json +try: + from urllib import urlopen +except ImportError: + from urllib.request import urlopen + + +def assert_lower(string): + assert string == string.lower() + return string + + +def generate(url): + parts = ['''\ +""" + + webencodings.labels + ~~~~~~~~~~~~~~~~~~~ + + Map encoding labels to their name. + + :copyright: Copyright 2012 by Simon Sapin + :license: BSD, see LICENSE for details. + +""" + +# XXX Do not edit! +# This file is automatically generated by mklabels.py + +LABELS = { +'''] + labels = [ + (repr(assert_lower(label)).lstrip('u'), + repr(encoding['name']).lstrip('u')) + for category in json.loads(urlopen(url).read().decode('ascii')) + for encoding in category['encodings'] + for label in encoding['labels']] + max_len = max(len(label) for label, name in labels) + parts.extend( + ' %s:%s %s,\n' % (label, ' ' * (max_len - len(label)), name) + for label, name in labels) + parts.append('}') + return ''.join(parts) + + +if __name__ == '__main__': + print(generate('http://encoding.spec.whatwg.org/encodings.json')) diff --git a/pip/_vendor/webencodings/tests.py b/pip/_vendor/webencodings/tests.py new file mode 100644 index 000000000..b8c5653ec --- /dev/null +++ b/pip/_vendor/webencodings/tests.py @@ -0,0 +1,153 @@ +# coding: utf8 +""" + + webencodings.tests + ~~~~~~~~~~~~~~~~~~ + + A basic test suite for Encoding. + + :copyright: Copyright 2012 by Simon Sapin + :license: BSD, see LICENSE for details. + +""" + +from __future__ import unicode_literals + +from . import (lookup, LABELS, decode, encode, iter_decode, iter_encode, + IncrementalDecoder, IncrementalEncoder, UTF8) + + +def assert_raises(exception, function, *args, **kwargs): + try: + function(*args, **kwargs) + except exception: + return + else: # pragma: no cover + raise AssertionError('Did not raise %s.' % exception) + + +def test_labels(): + assert lookup('utf-8').name == 'utf-8' + assert lookup('Utf-8').name == 'utf-8' + assert lookup('UTF-8').name == 'utf-8' + assert lookup('utf8').name == 'utf-8' + assert lookup('utf8').name == 'utf-8' + assert lookup('utf8 ').name == 'utf-8' + assert lookup(' \r\nutf8\t').name == 'utf-8' + assert lookup('u8') is None # Python label. + assert lookup('utf-8 ') is None # Non-ASCII white space. + + assert lookup('US-ASCII').name == 'windows-1252' + assert lookup('iso-8859-1').name == 'windows-1252' + assert lookup('latin1').name == 'windows-1252' + assert lookup('LATIN1').name == 'windows-1252' + assert lookup('latin-1') is None + assert lookup('LATİN1') is None # ASCII-only case insensitivity. + + +def test_all_labels(): + for label in LABELS: + assert decode(b'', label) == ('', lookup(label)) + assert encode('', label) == b'' + for repeat in [0, 1, 12]: + output, _ = iter_decode([b''] * repeat, label) + assert list(output) == [] + assert list(iter_encode([''] * repeat, label)) == [] + decoder = IncrementalDecoder(label) + assert decoder.decode(b'') == '' + assert decoder.decode(b'', final=True) == '' + encoder = IncrementalEncoder(label) + assert encoder.encode('') == b'' + assert encoder.encode('', final=True) == b'' + # All encoding names are valid labels too: + for name in set(LABELS.values()): + assert lookup(name).name == name + + +def test_invalid_label(): + assert_raises(LookupError, decode, b'\xEF\xBB\xBF\xc3\xa9', 'invalid') + assert_raises(LookupError, encode, 'é', 'invalid') + assert_raises(LookupError, iter_decode, [], 'invalid') + assert_raises(LookupError, iter_encode, [], 'invalid') + assert_raises(LookupError, IncrementalDecoder, 'invalid') + assert_raises(LookupError, IncrementalEncoder, 'invalid') + + +def test_decode(): + assert decode(b'\x80', 'latin1') == ('€', lookup('latin1')) + assert decode(b'\x80', lookup('latin1')) == ('€', lookup('latin1')) + assert decode(b'\xc3\xa9', 'utf8') == ('é', lookup('utf8')) + assert decode(b'\xc3\xa9', UTF8) == ('é', lookup('utf8')) + assert decode(b'\xc3\xa9', 'ascii') == ('é', lookup('ascii')) + assert decode(b'\xEF\xBB\xBF\xc3\xa9', 'ascii') == ('é', lookup('utf8')) # UTF-8 with BOM + + assert decode(b'\xFE\xFF\x00\xe9', 'ascii') == ('é', lookup('utf-16be')) # UTF-16-BE with BOM + assert decode(b'\xFF\xFE\xe9\x00', 'ascii') == ('é', lookup('utf-16le')) # UTF-16-LE with BOM + assert decode(b'\xFE\xFF\xe9\x00', 'ascii') == ('\ue900', lookup('utf-16be')) + assert decode(b'\xFF\xFE\x00\xe9', 'ascii') == ('\ue900', lookup('utf-16le')) + + assert decode(b'\x00\xe9', 'UTF-16BE') == ('é', lookup('utf-16be')) + assert decode(b'\xe9\x00', 'UTF-16LE') == ('é', lookup('utf-16le')) + assert decode(b'\xe9\x00', 'UTF-16') == ('é', lookup('utf-16le')) + + assert decode(b'\xe9\x00', 'UTF-16BE') == ('\ue900', lookup('utf-16be')) + assert decode(b'\x00\xe9', 'UTF-16LE') == ('\ue900', lookup('utf-16le')) + assert decode(b'\x00\xe9', 'UTF-16') == ('\ue900', lookup('utf-16le')) + + +def test_encode(): + assert encode('é', 'latin1') == b'\xe9' + assert encode('é', 'utf8') == b'\xc3\xa9' + assert encode('é', 'utf8') == b'\xc3\xa9' + assert encode('é', 'utf-16') == b'\xe9\x00' + assert encode('é', 'utf-16le') == b'\xe9\x00' + assert encode('é', 'utf-16be') == b'\x00\xe9' + + +def test_iter_decode(): + def iter_decode_to_string(input, fallback_encoding): + output, _encoding = iter_decode(input, fallback_encoding) + return ''.join(output) + assert iter_decode_to_string([], 'latin1') == '' + assert iter_decode_to_string([b''], 'latin1') == '' + assert iter_decode_to_string([b'\xe9'], 'latin1') == 'é' + assert iter_decode_to_string([b'hello'], 'latin1') == 'hello' + assert iter_decode_to_string([b'he', b'llo'], 'latin1') == 'hello' + assert iter_decode_to_string([b'hell', b'o'], 'latin1') == 'hello' + assert iter_decode_to_string([b'\xc3\xa9'], 'latin1') == 'é' + assert iter_decode_to_string([b'\xEF\xBB\xBF\xc3\xa9'], 'latin1') == 'é' + assert iter_decode_to_string([ + b'\xEF\xBB\xBF', b'\xc3', b'\xa9'], 'latin1') == 'é' + assert iter_decode_to_string([ + b'\xEF\xBB\xBF', b'a', b'\xc3'], 'latin1') == 'a\uFFFD' + assert iter_decode_to_string([ + b'', b'\xEF', b'', b'', b'\xBB\xBF\xc3', b'\xa9'], 'latin1') == 'é' + assert iter_decode_to_string([b'\xEF\xBB\xBF'], 'latin1') == '' + assert iter_decode_to_string([b'\xEF\xBB'], 'latin1') == 'ï»' + assert iter_decode_to_string([b'\xFE\xFF\x00\xe9'], 'latin1') == 'é' + assert iter_decode_to_string([b'\xFF\xFE\xe9\x00'], 'latin1') == 'é' + assert iter_decode_to_string([ + b'', b'\xFF', b'', b'', b'\xFE\xe9', b'\x00'], 'latin1') == 'é' + assert iter_decode_to_string([ + b'', b'h\xe9', b'llo'], 'x-user-defined') == 'h\uF7E9llo' + + +def test_iter_encode(): + assert b''.join(iter_encode([], 'latin1')) == b'' + assert b''.join(iter_encode([''], 'latin1')) == b'' + assert b''.join(iter_encode(['é'], 'latin1')) == b'\xe9' + assert b''.join(iter_encode(['', 'é', '', ''], 'latin1')) == b'\xe9' + assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16')) == b'\xe9\x00' + assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16le')) == b'\xe9\x00' + assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16be')) == b'\x00\xe9' + assert b''.join(iter_encode([ + '', 'h\uF7E9', '', 'llo'], 'x-user-defined')) == b'h\xe9llo' + + +def test_x_user_defined(): + encoded = b'2,\x0c\x0b\x1aO\xd9#\xcb\x0f\xc9\xbbt\xcf\xa8\xca' + decoded = '2,\x0c\x0b\x1aO\uf7d9#\uf7cb\x0f\uf7c9\uf7bbt\uf7cf\uf7a8\uf7ca' + encoded = b'aa' + decoded = 'aa' + assert decode(encoded, 'x-user-defined') == (decoded, lookup('x-user-defined')) + assert encode(decoded, 'x-user-defined') == encoded diff --git a/pip/_vendor/webencodings/x_user_defined.py b/pip/_vendor/webencodings/x_user_defined.py new file mode 100644 index 000000000..f0daa11a7 --- /dev/null +++ b/pip/_vendor/webencodings/x_user_defined.py @@ -0,0 +1,325 @@ +# coding: utf8 +""" + + webencodings.x_user_defined + ~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + An implementation of the x-user-defined encoding. + + :copyright: Copyright 2012 by Simon Sapin + :license: BSD, see LICENSE for details. + +""" + +from __future__ import unicode_literals + +import codecs + + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self, input, errors='strict'): + return codecs.charmap_encode(input, errors, encoding_table) + + def decode(self, input, errors='strict'): + return codecs.charmap_decode(input, errors, decoding_table) + + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input, self.errors, encoding_table)[0] + + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input, self.errors, decoding_table)[0] + + +class StreamWriter(Codec, codecs.StreamWriter): + pass + + +class StreamReader(Codec, codecs.StreamReader): + pass + + +### encodings module API + +codec_info = codecs.CodecInfo( + name='x-user-defined', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, +) + + +### Decoding Table + +# Python 3: +# for c in range(256): print(' %r' % chr(c if c < 128 else c + 0xF700)) +decoding_table = ( + '\x00' + '\x01' + '\x02' + '\x03' + '\x04' + '\x05' + '\x06' + '\x07' + '\x08' + '\t' + '\n' + '\x0b' + '\x0c' + '\r' + '\x0e' + '\x0f' + '\x10' + '\x11' + '\x12' + '\x13' + '\x14' + '\x15' + '\x16' + '\x17' + '\x18' + '\x19' + '\x1a' + '\x1b' + '\x1c' + '\x1d' + '\x1e' + '\x1f' + ' ' + '!' + '"' + '#' + '$' + '%' + '&' + "'" + '(' + ')' + '*' + '+' + ',' + '-' + '.' + '/' + '0' + '1' + '2' + '3' + '4' + '5' + '6' + '7' + '8' + '9' + ':' + ';' + '<' + '=' + '>' + '?' + '@' + 'A' + 'B' + 'C' + 'D' + 'E' + 'F' + 'G' + 'H' + 'I' + 'J' + 'K' + 'L' + 'M' + 'N' + 'O' + 'P' + 'Q' + 'R' + 'S' + 'T' + 'U' + 'V' + 'W' + 'X' + 'Y' + 'Z' + '[' + '\\' + ']' + '^' + '_' + '`' + 'a' + 'b' + 'c' + 'd' + 'e' + 'f' + 'g' + 'h' + 'i' + 'j' + 'k' + 'l' + 'm' + 'n' + 'o' + 'p' + 'q' + 'r' + 's' + 't' + 'u' + 'v' + 'w' + 'x' + 'y' + 'z' + '{' + '|' + '}' + '~' + '\x7f' + '\uf780' + '\uf781' + '\uf782' + '\uf783' + '\uf784' + '\uf785' + '\uf786' + '\uf787' + '\uf788' + '\uf789' + '\uf78a' + '\uf78b' + '\uf78c' + '\uf78d' + '\uf78e' + '\uf78f' + '\uf790' + '\uf791' + '\uf792' + '\uf793' + '\uf794' + '\uf795' + '\uf796' + '\uf797' + '\uf798' + '\uf799' + '\uf79a' + '\uf79b' + '\uf79c' + '\uf79d' + '\uf79e' + '\uf79f' + '\uf7a0' + '\uf7a1' + '\uf7a2' + '\uf7a3' + '\uf7a4' + '\uf7a5' + '\uf7a6' + '\uf7a7' + '\uf7a8' + '\uf7a9' + '\uf7aa' + '\uf7ab' + '\uf7ac' + '\uf7ad' + '\uf7ae' + '\uf7af' + '\uf7b0' + '\uf7b1' + '\uf7b2' + '\uf7b3' + '\uf7b4' + '\uf7b5' + '\uf7b6' + '\uf7b7' + '\uf7b8' + '\uf7b9' + '\uf7ba' + '\uf7bb' + '\uf7bc' + '\uf7bd' + '\uf7be' + '\uf7bf' + '\uf7c0' + '\uf7c1' + '\uf7c2' + '\uf7c3' + '\uf7c4' + '\uf7c5' + '\uf7c6' + '\uf7c7' + '\uf7c8' + '\uf7c9' + '\uf7ca' + '\uf7cb' + '\uf7cc' + '\uf7cd' + '\uf7ce' + '\uf7cf' + '\uf7d0' + '\uf7d1' + '\uf7d2' + '\uf7d3' + '\uf7d4' + '\uf7d5' + '\uf7d6' + '\uf7d7' + '\uf7d8' + '\uf7d9' + '\uf7da' + '\uf7db' + '\uf7dc' + '\uf7dd' + '\uf7de' + '\uf7df' + '\uf7e0' + '\uf7e1' + '\uf7e2' + '\uf7e3' + '\uf7e4' + '\uf7e5' + '\uf7e6' + '\uf7e7' + '\uf7e8' + '\uf7e9' + '\uf7ea' + '\uf7eb' + '\uf7ec' + '\uf7ed' + '\uf7ee' + '\uf7ef' + '\uf7f0' + '\uf7f1' + '\uf7f2' + '\uf7f3' + '\uf7f4' + '\uf7f5' + '\uf7f6' + '\uf7f7' + '\uf7f8' + '\uf7f9' + '\uf7fa' + '\uf7fb' + '\uf7fc' + '\uf7fd' + '\uf7fe' + '\uf7ff' +) + +### Encoding table +encoding_table = codecs.charmap_build(decoding_table) diff --git a/pip/index.py b/pip/index.py index feb9f582b..b1d08f59d 100644 --- a/pip/index.py +++ b/pip/index.py @@ -727,7 +727,7 @@ class HTMLPage(object): self.content = content self.parsed = html5lib.parse( self.content, - encoding=encoding, + transport_encoding=encoding, namespaceHTMLElements=False, ) self.url = url diff --git a/tests/unit/test_index.py b/tests/unit/test_index.py index 625b38d6a..f25a0c4f8 100644 --- a/tests/unit/test_index.py +++ b/tests/unit/test_index.py @@ -90,18 +90,18 @@ class TestLink(object): @pytest.mark.parametrize( ("html", "url", "expected"), [ - ("<html></html>", "https://example.com/", "https://example.com/"), + (b"<html></html>", "https://example.com/", "https://example.com/"), ( - "<html><head>" - "<base href=\"https://foo.example.com/\">" - "</head></html>", + b"<html><head>" + b"<base href=\"https://foo.example.com/\">" + b"</head></html>", "https://example.com/", "https://foo.example.com/", ), ( - "<html><head>" - "<base><base href=\"https://foo.example.com/\">" - "</head></html>", + b"<html><head>" + b"<base><base href=\"https://foo.example.com/\">" + b"</head></html>", "https://example.com/", "https://foo.example.com/", ), |