summaryrefslogtreecommitdiff
path: root/Tools/c-analyzer/c_analyzer_common
diff options
context:
space:
mode:
Diffstat (limited to 'Tools/c-analyzer/c_analyzer_common')
-rw-r--r--Tools/c-analyzer/c_analyzer_common/__init__.py19
-rw-r--r--Tools/c-analyzer/c_analyzer_common/_generate.py328
-rw-r--r--Tools/c-analyzer/c_analyzer_common/files.py138
-rw-r--r--Tools/c-analyzer/c_analyzer_common/info.py69
-rw-r--r--Tools/c-analyzer/c_analyzer_common/known.py74
-rw-r--r--Tools/c-analyzer/c_analyzer_common/util.py243
6 files changed, 0 insertions, 871 deletions
diff --git a/Tools/c-analyzer/c_analyzer_common/__init__.py b/Tools/c-analyzer/c_analyzer_common/__init__.py
deleted file mode 100644
index 888b16ff41..0000000000
--- a/Tools/c-analyzer/c_analyzer_common/__init__.py
+++ /dev/null
@@ -1,19 +0,0 @@
-import os.path
-
-
-PKG_ROOT = os.path.dirname(__file__)
-DATA_DIR = os.path.dirname(PKG_ROOT)
-REPO_ROOT = os.path.dirname(
- os.path.dirname(DATA_DIR))
-
-SOURCE_DIRS = [os.path.join(REPO_ROOT, name) for name in [
- 'Include',
- 'Python',
- 'Parser',
- 'Objects',
- 'Modules',
- ]]
-
-
-# Clean up the namespace.
-del os
diff --git a/Tools/c-analyzer/c_analyzer_common/_generate.py b/Tools/c-analyzer/c_analyzer_common/_generate.py
deleted file mode 100644
index 9b2fc9edb5..0000000000
--- a/Tools/c-analyzer/c_analyzer_common/_generate.py
+++ /dev/null
@@ -1,328 +0,0 @@
-# The code here consists of hacks for pre-populating the known.tsv file.
-
-from c_parser.preprocessor import _iter_clean_lines
-from c_parser.naive import (
- iter_variables, parse_variable_declaration, find_variables,
- )
-from c_parser.info import Variable
-
-from . import SOURCE_DIRS, REPO_ROOT
-from .known import DATA_FILE as KNOWN_FILE, HEADER as KNOWN_HEADER
-from .info import UNKNOWN, ID
-from .util import write_tsv
-from .files import iter_cpython_files
-
-
-POTS = ('char ', 'wchar_t ', 'int ', 'Py_ssize_t ')
-POTS += tuple('const ' + v for v in POTS)
-STRUCTS = ('PyTypeObject', 'PyObject', 'PyMethodDef', 'PyModuleDef', 'grammar')
-
-
-def _parse_global(line, funcname=None):
- line = line.strip()
- if line.startswith('static '):
- if '(' in line and '[' not in line and ' = ' not in line:
- return None, None
- name, decl = parse_variable_declaration(line)
- elif line.startswith(('Py_LOCAL(', 'Py_LOCAL_INLINE(')):
- name, decl = parse_variable_declaration(line)
- elif line.startswith('_Py_static_string('):
- decl = line.strip(';').strip()
- name = line.split('(')[1].split(',')[0].strip()
- elif line.startswith('_Py_IDENTIFIER('):
- decl = line.strip(';').strip()
- name = 'PyId_' + line.split('(')[1].split(')')[0].strip()
- elif funcname:
- return None, None
-
- # global-only
- elif line.startswith('PyAPI_DATA('): # only in .h files
- name, decl = parse_variable_declaration(line)
- elif line.startswith('extern '): # only in .h files
- name, decl = parse_variable_declaration(line)
- elif line.startswith('PyDoc_VAR('):
- decl = line.strip(';').strip()
- name = line.split('(')[1].split(')')[0].strip()
- elif line.startswith(POTS): # implied static
- if '(' in line and '[' not in line and ' = ' not in line:
- return None, None
- name, decl = parse_variable_declaration(line)
- elif line.startswith(STRUCTS) and line.endswith(' = {'): # implied static
- name, decl = parse_variable_declaration(line)
- elif line.startswith(STRUCTS) and line.endswith(' = NULL;'): # implied static
- name, decl = parse_variable_declaration(line)
- elif line.startswith('struct '):
- if not line.endswith(' = {'):
- return None, None
- if not line.partition(' ')[2].startswith(STRUCTS):
- return None, None
- # implied static
- name, decl = parse_variable_declaration(line)
-
- # file-specific
- elif line.startswith(('SLOT1BINFULL(', 'SLOT1BIN(')):
- # Objects/typeobject.c
- funcname = line.split('(')[1].split(',')[0]
- return [
- ('op_id', funcname, '_Py_static_string(op_id, OPSTR)'),
- ('rop_id', funcname, '_Py_static_string(op_id, OPSTR)'),
- ]
- elif line.startswith('WRAP_METHOD('):
- # Objects/weakrefobject.c
- funcname, name = (v.strip() for v in line.split('(')[1].split(')')[0].split(','))
- return [
- ('PyId_' + name, funcname, f'_Py_IDENTIFIER({name})'),
- ]
-
- else:
- return None, None
- return name, decl
-
-
-def _pop_cached(varcache, filename, funcname, name, *,
- _iter_variables=iter_variables,
- ):
- # Look for the file.
- try:
- cached = varcache[filename]
- except KeyError:
- cached = varcache[filename] = {}
- for variable in _iter_variables(filename,
- parse_variable=_parse_global,
- ):
- variable._isglobal = True
- cached[variable.id] = variable
- for var in cached:
- print(' ', var)
-
- # Look for the variable.
- if funcname == UNKNOWN:
- for varid in cached:
- if varid.name == name:
- break
- else:
- return None
- return cached.pop(varid)
- else:
- return cached.pop((filename, funcname, name), None)
-
-
-def find_matching_variable(varid, varcache, allfilenames, *,
- _pop_cached=_pop_cached,
- ):
- if varid.filename and varid.filename != UNKNOWN:
- filenames = [varid.filename]
- else:
- filenames = allfilenames
- for filename in filenames:
- variable = _pop_cached(varcache, filename, varid.funcname, varid.name)
- if variable is not None:
- return variable
- else:
- if varid.filename and varid.filename != UNKNOWN and varid.funcname is None:
- for filename in allfilenames:
- if not filename.endswith('.h'):
- continue
- variable = _pop_cached(varcache, filename, None, varid.name)
- if variable is not None:
- return variable
- return None
-
-
-MULTILINE = {
- # Python/Python-ast.c
- 'Load_singleton': 'PyObject *',
- 'Store_singleton': 'PyObject *',
- 'Del_singleton': 'PyObject *',
- 'AugLoad_singleton': 'PyObject *',
- 'AugStore_singleton': 'PyObject *',
- 'Param_singleton': 'PyObject *',
- 'And_singleton': 'PyObject *',
- 'Or_singleton': 'PyObject *',
- 'Add_singleton': 'static PyObject *',
- 'Sub_singleton': 'static PyObject *',
- 'Mult_singleton': 'static PyObject *',
- 'MatMult_singleton': 'static PyObject *',
- 'Div_singleton': 'static PyObject *',
- 'Mod_singleton': 'static PyObject *',
- 'Pow_singleton': 'static PyObject *',
- 'LShift_singleton': 'static PyObject *',
- 'RShift_singleton': 'static PyObject *',
- 'BitOr_singleton': 'static PyObject *',
- 'BitXor_singleton': 'static PyObject *',
- 'BitAnd_singleton': 'static PyObject *',
- 'FloorDiv_singleton': 'static PyObject *',
- 'Invert_singleton': 'static PyObject *',
- 'Not_singleton': 'static PyObject *',
- 'UAdd_singleton': 'static PyObject *',
- 'USub_singleton': 'static PyObject *',
- 'Eq_singleton': 'static PyObject *',
- 'NotEq_singleton': 'static PyObject *',
- 'Lt_singleton': 'static PyObject *',
- 'LtE_singleton': 'static PyObject *',
- 'Gt_singleton': 'static PyObject *',
- 'GtE_singleton': 'static PyObject *',
- 'Is_singleton': 'static PyObject *',
- 'IsNot_singleton': 'static PyObject *',
- 'In_singleton': 'static PyObject *',
- 'NotIn_singleton': 'static PyObject *',
- # Python/symtable.c
- 'top': 'static identifier ',
- 'lambda': 'static identifier ',
- 'genexpr': 'static identifier ',
- 'listcomp': 'static identifier ',
- 'setcomp': 'static identifier ',
- 'dictcomp': 'static identifier ',
- '__class__': 'static identifier ',
- # Python/compile.c
- '__doc__': 'static PyObject *',
- '__annotations__': 'static PyObject *',
- # Objects/floatobject.c
- 'double_format': 'static float_format_type ',
- 'float_format': 'static float_format_type ',
- 'detected_double_format': 'static float_format_type ',
- 'detected_float_format': 'static float_format_type ',
- # Parser/listnode.c
- 'level': 'static int ',
- 'atbol': 'static int ',
- # Python/dtoa.c
- 'private_mem': 'static double private_mem[PRIVATE_mem]',
- 'pmem_next': 'static double *',
- # Modules/_weakref.c
- 'weakref_functions': 'static PyMethodDef ',
-}
-INLINE = {
- # Modules/_tracemalloc.c
- 'allocators': 'static struct { PyMemAllocatorEx mem; PyMemAllocatorEx raw; PyMemAllocatorEx obj; } ',
- # Modules/faulthandler.c
- 'fatal_error': 'static struct { int enabled; PyObject *file; int fd; int all_threads; PyInterpreterState *interp; void *exc_handler; } ',
- 'thread': 'static struct { PyObject *file; int fd; PY_TIMEOUT_T timeout_us; int repeat; PyInterpreterState *interp; int exit; char *header; size_t header_len; PyThread_type_lock cancel_event; PyThread_type_lock running; } ',
- # Modules/signalmodule.c
- 'Handlers': 'static volatile struct { _Py_atomic_int tripped; PyObject *func; } Handlers[NSIG]',
- 'wakeup': 'static volatile struct { SOCKET_T fd; int warn_on_full_buffer; int use_send; } ',
- # Python/dynload_shlib.c
- 'handles': 'static struct { dev_t dev; ino_t ino; void *handle; } handles[128]',
- # Objects/obmalloc.c
- '_PyMem_Debug': 'static struct { debug_alloc_api_t raw; debug_alloc_api_t mem; debug_alloc_api_t obj; } ',
- # Python/bootstrap_hash.c
- 'urandom_cache': 'static struct { int fd; dev_t st_dev; ino_t st_ino; } ',
- }
-FUNC = {
- # Objects/object.c
- '_Py_abstract_hack': 'Py_ssize_t (*_Py_abstract_hack)(PyObject *)',
- # Parser/myreadline.c
- 'PyOS_InputHook': 'int (*PyOS_InputHook)(void)',
- # Python/pylifecycle.c
- '_PyOS_mystrnicmp_hack': 'int (*_PyOS_mystrnicmp_hack)(const char *, const char *, Py_ssize_t)',
- # Parser/myreadline.c
- 'PyOS_ReadlineFunctionPointer': 'char *(*PyOS_ReadlineFunctionPointer)(FILE *, FILE *, const char *)',
- }
-IMPLIED = {
- # Objects/boolobject.c
- '_Py_FalseStruct': 'static struct _longobject ',
- '_Py_TrueStruct': 'static struct _longobject ',
- # Modules/config.c
- '_PyImport_Inittab': 'struct _inittab _PyImport_Inittab[]',
- }
-GLOBALS = {}
-GLOBALS.update(MULTILINE)
-GLOBALS.update(INLINE)
-GLOBALS.update(FUNC)
-GLOBALS.update(IMPLIED)
-
-LOCALS = {
- 'buildinfo': ('Modules/getbuildinfo.c',
- 'Py_GetBuildInfo',
- 'static char buildinfo[50 + sizeof(GITVERSION) + ((sizeof(GITTAG) > sizeof(GITBRANCH)) ? sizeof(GITTAG) : sizeof(GITBRANCH))]'),
- 'methods': ('Python/codecs.c',
- '_PyCodecRegistry_Init',
- 'static struct { char *name; PyMethodDef def; } methods[]'),
- }
-
-
-def _known(symbol):
- if symbol.funcname:
- if symbol.funcname != UNKNOWN or symbol.filename != UNKNOWN:
- raise KeyError(symbol.name)
- filename, funcname, decl = LOCALS[symbol.name]
- varid = ID(filename, funcname, symbol.name)
- elif not symbol.filename or symbol.filename == UNKNOWN:
- raise KeyError(symbol.name)
- else:
- varid = symbol.id
- try:
- decl = GLOBALS[symbol.name]
- except KeyError:
-
- if symbol.name.endswith('_methods'):
- decl = 'static PyMethodDef '
- elif symbol.filename == 'Objects/exceptions.c' and symbol.name.startswith(('PyExc_', '_PyExc_')):
- decl = 'static PyTypeObject '
- else:
- raise
- if symbol.name not in decl:
- decl = decl + symbol.name
- return Variable(varid, 'static', decl)
-
-
-def known_row(varid, decl):
- return (
- varid.filename,
- varid.funcname or '-',
- varid.name,
- 'variable',
- decl,
- )
-
-
-def known_rows(symbols, *,
- cached=True,
- _get_filenames=iter_cpython_files,
- _find_match=find_matching_variable,
- _find_symbols=find_variables,
- _as_known=known_row,
- ):
- filenames = list(_get_filenames())
- cache = {}
- if cached:
- for symbol in symbols:
- try:
- found = _known(symbol)
- except KeyError:
- found = _find_match(symbol, cache, filenames)
- if found is None:
- found = Variable(symbol.id, UNKNOWN, UNKNOWN)
- yield _as_known(found.id, found.vartype)
- else:
- raise NotImplementedError # XXX incorporate KNOWN
- for variable in _find_symbols(symbols, filenames,
- srccache=cache,
- parse_variable=_parse_global,
- ):
- #variable = variable._replace(
- # filename=os.path.relpath(variable.filename, REPO_ROOT))
- if variable.funcname == UNKNOWN:
- print(variable)
- if variable.vartype== UNKNOWN:
- print(variable)
- yield _as_known(variable.id, variable.vartype)
-
-
-def generate(symbols, filename=None, *,
- _generate_rows=known_rows,
- _write_tsv=write_tsv,
- ):
- if not filename:
- filename = KNOWN_FILE + '.new'
-
- rows = _generate_rows(symbols)
- _write_tsv(filename, KNOWN_HEADER, rows)
-
-
-if __name__ == '__main__':
- from c_symbols import binary
- symbols = binary.iter_symbols(
- binary.PYTHON,
- find_local_symbol=None,
- )
- generate(symbols)
diff --git a/Tools/c-analyzer/c_analyzer_common/files.py b/Tools/c-analyzer/c_analyzer_common/files.py
deleted file mode 100644
index b3cd16c8dc..0000000000
--- a/Tools/c-analyzer/c_analyzer_common/files.py
+++ /dev/null
@@ -1,138 +0,0 @@
-import glob
-import os
-import os.path
-
-from . import SOURCE_DIRS, REPO_ROOT
-
-
-C_SOURCE_SUFFIXES = ('.c', '.h')
-
-
-def _walk_tree(root, *,
- _walk=os.walk,
- ):
- # A wrapper around os.walk that resolves the filenames.
- for parent, _, names in _walk(root):
- for name in names:
- yield os.path.join(parent, name)
-
-
-def walk_tree(root, *,
- suffix=None,
- walk=_walk_tree,
- ):
- """Yield each file in the tree under the given directory name.
-
- If "suffix" is provided then only files with that suffix will
- be included.
- """
- if suffix and not isinstance(suffix, str):
- raise ValueError('suffix must be a string')
-
- for filename in walk(root):
- if suffix and not filename.endswith(suffix):
- continue
- yield filename
-
-
-def glob_tree(root, *,
- suffix=None,
- _glob=glob.iglob,
- ):
- """Yield each file in the tree under the given directory name.
-
- If "suffix" is provided then only files with that suffix will
- be included.
- """
- suffix = suffix or ''
- if not isinstance(suffix, str):
- raise ValueError('suffix must be a string')
-
- for filename in _glob(f'{root}/*{suffix}'):
- yield filename
- for filename in _glob(f'{root}/**/*{suffix}'):
- yield filename
-
-
-def iter_files(root, suffix=None, relparent=None, *,
- get_files=os.walk,
- _glob=glob_tree,
- _walk=walk_tree,
- ):
- """Yield each file in the tree under the given directory name.
-
- If "root" is a non-string iterable then do the same for each of
- those trees.
-
- If "suffix" is provided then only files with that suffix will
- be included.
-
- if "relparent" is provided then it is used to resolve each
- filename as a relative path.
- """
- if not isinstance(root, str):
- roots = root
- for root in roots:
- yield from iter_files(root, suffix, relparent,
- get_files=get_files,
- _glob=_glob, _walk=_walk)
- return
-
- # Use the right "walk" function.
- if get_files in (glob.glob, glob.iglob, glob_tree):
- get_files = _glob
- else:
- _files = _walk_tree if get_files in (os.walk, walk_tree) else get_files
- get_files = (lambda *a, **k: _walk(*a, walk=_files, **k))
-
- # Handle a single suffix.
- if suffix and not isinstance(suffix, str):
- filenames = get_files(root)
- suffix = tuple(suffix)
- else:
- filenames = get_files(root, suffix=suffix)
- suffix = None
-
- for filename in filenames:
- if suffix and not isinstance(suffix, str): # multiple suffixes
- if not filename.endswith(suffix):
- continue
- if relparent:
- filename = os.path.relpath(filename, relparent)
- yield filename
-
-
-def iter_files_by_suffix(root, suffixes, relparent=None, *,
- walk=walk_tree,
- _iter_files=iter_files,
- ):
- """Yield each file in the tree that has the given suffixes.
-
- Unlike iter_files(), the results are in the original suffix order.
- """
- if isinstance(suffixes, str):
- suffixes = [suffixes]
- # XXX Ignore repeated suffixes?
- for suffix in suffixes:
- yield from _iter_files(root, suffix, relparent)
-
-
-def iter_cpython_files(*,
- walk=walk_tree,
- _files=iter_files_by_suffix,
- ):
- """Yield each file in the tree for each of the given directory names."""
- excludedtrees = [
- os.path.join('Include', 'cpython', ''),
- ]
- def is_excluded(filename):
- for root in excludedtrees:
- if filename.startswith(root):
- return True
- return False
- for filename in _files(SOURCE_DIRS, C_SOURCE_SUFFIXES, REPO_ROOT,
- walk=walk,
- ):
- if is_excluded(filename):
- continue
- yield filename
diff --git a/Tools/c-analyzer/c_analyzer_common/info.py b/Tools/c-analyzer/c_analyzer_common/info.py
deleted file mode 100644
index e217380406..0000000000
--- a/Tools/c-analyzer/c_analyzer_common/info.py
+++ /dev/null
@@ -1,69 +0,0 @@
-from collections import namedtuple
-import re
-
-from .util import classonly, _NTBase
-
-
-UNKNOWN = '???'
-
-NAME_RE = re.compile(r'^([a-zA-Z]|_\w*[a-zA-Z]\w*|[a-zA-Z]\w*)$')
-
-
-class ID(_NTBase, namedtuple('ID', 'filename funcname name')):
- """A unique ID for a single symbol or declaration."""
-
- __slots__ = ()
- # XXX Add optional conditions (tuple of strings) field.
- #conditions = Slot()
-
- @classonly
- def from_raw(cls, raw):
- if not raw:
- return None
- if isinstance(raw, str):
- return cls(None, None, raw)
- try:
- name, = raw
- filename = None
- except ValueError:
- try:
- filename, name = raw
- except ValueError:
- return super().from_raw(raw)
- return cls(filename, None, name)
-
- def __new__(cls, filename, funcname, name):
- self = super().__new__(
- cls,
- filename=str(filename) if filename else None,
- funcname=str(funcname) if funcname else None,
- name=str(name) if name else None,
- )
- #cls.conditions.set(self, tuple(str(s) if s else None
- # for s in conditions or ()))
- return self
-
- def validate(self):
- """Fail if the object is invalid (i.e. init with bad data)."""
- if not self.name:
- raise TypeError('missing name')
- else:
- if not NAME_RE.match(self.name):
- raise ValueError(
- f'name must be an identifier, got {self.name!r}')
-
- # Symbols from a binary might not have filename/funcname info.
-
- if self.funcname:
- if not self.filename:
- raise TypeError('missing filename')
- if not NAME_RE.match(self.funcname) and self.funcname != UNKNOWN:
- raise ValueError(
- f'name must be an identifier, got {self.funcname!r}')
-
- # XXX Require the filename (at least UNKONWN)?
- # XXX Check the filename?
-
- @property
- def islocal(self):
- return self.funcname is not None
diff --git a/Tools/c-analyzer/c_analyzer_common/known.py b/Tools/c-analyzer/c_analyzer_common/known.py
deleted file mode 100644
index dec1e1d2e0..0000000000
--- a/Tools/c-analyzer/c_analyzer_common/known.py
+++ /dev/null
@@ -1,74 +0,0 @@
-import csv
-import os.path
-
-from c_parser.info import Variable
-
-from . import DATA_DIR
-from .info import ID, UNKNOWN
-from .util import read_tsv
-
-
-DATA_FILE = os.path.join(DATA_DIR, 'known.tsv')
-
-COLUMNS = ('filename', 'funcname', 'name', 'kind', 'declaration')
-HEADER = '\t'.join(COLUMNS)
-
-
-# XXX need tests:
-# * from_file()
-
-def from_file(infile, *,
- _read_tsv=read_tsv,
- ):
- """Return the info for known declarations in the given file."""
- known = {
- 'variables': {},
- #'types': {},
- #'constants': {},
- #'macros': {},
- }
- for row in _read_tsv(infile, HEADER):
- filename, funcname, name, kind, declaration = row
- if not funcname or funcname == '-':
- funcname = None
- id = ID(filename, funcname, name)
- if kind == 'variable':
- values = known['variables']
- if funcname:
- storage = _get_storage(declaration) or 'local'
- else:
- storage = _get_storage(declaration) or 'implicit'
- value = Variable(id, storage, declaration)
- else:
- raise ValueError(f'unsupported kind in row {row}')
- value.validate()
-# if value.name == 'id' and declaration == UNKNOWN:
-# # None of these are variables.
-# declaration = 'int id';
-# else:
-# value.validate()
- values[id] = value
- return known
-
-
-def _get_storage(decl):
- # statics
- if decl.startswith('static '):
- return 'static'
- if decl.startswith(('Py_LOCAL(', 'Py_LOCAL_INLINE(')):
- return 'static'
- if decl.startswith(('_Py_IDENTIFIER(', '_Py_static_string(')):
- return 'static'
- if decl.startswith('PyDoc_VAR('):
- return 'static'
- if decl.startswith(('SLOT1BINFULL(', 'SLOT1BIN(')):
- return 'static'
- if decl.startswith('WRAP_METHOD('):
- return 'static'
- # public extern
- if decl.startswith('extern '):
- return 'extern'
- if decl.startswith('PyAPI_DATA('):
- return 'extern'
- # implicit or local
- return None
diff --git a/Tools/c-analyzer/c_analyzer_common/util.py b/Tools/c-analyzer/c_analyzer_common/util.py
deleted file mode 100644
index 43d0bb6e66..0000000000
--- a/Tools/c-analyzer/c_analyzer_common/util.py
+++ /dev/null
@@ -1,243 +0,0 @@
-import csv
-import subprocess
-
-
-_NOT_SET = object()
-
-
-def run_cmd(argv, **kwargs):
- proc = subprocess.run(
- argv,
- #capture_output=True,
- #stderr=subprocess.STDOUT,
- stdout=subprocess.PIPE,
- text=True,
- check=True,
- **kwargs
- )
- return proc.stdout
-
-
-def read_tsv(infile, header, *,
- _open=open,
- _get_reader=csv.reader,
- ):
- """Yield each row of the given TSV (tab-separated) file."""
- if isinstance(infile, str):
- with _open(infile, newline='') as infile:
- yield from read_tsv(infile, header,
- _open=_open,
- _get_reader=_get_reader,
- )
- return
- lines = iter(infile)
-
- # Validate the header.
- try:
- actualheader = next(lines).strip()
- except StopIteration:
- actualheader = ''
- if actualheader != header:
- raise ValueError(f'bad header {actualheader!r}')
-
- for row in _get_reader(lines, delimiter='\t'):
- yield tuple(v.strip() for v in row)
-
-
-def write_tsv(outfile, header, rows, *,
- _open=open,
- _get_writer=csv.writer,
- ):
- """Write each of the rows to the given TSV (tab-separated) file."""
- if isinstance(outfile, str):
- with _open(outfile, 'w', newline='') as outfile:
- return write_tsv(outfile, header, rows,
- _open=_open,
- _get_writer=_get_writer,
- )
-
- if isinstance(header, str):
- header = header.split('\t')
- writer = _get_writer(outfile, delimiter='\t')
- writer.writerow(header)
- for row in rows:
- writer.writerow('' if v is None else str(v)
- for v in row)
-
-
-class Slot:
- """A descriptor that provides a slot.
-
- This is useful for types that can't have slots via __slots__,
- e.g. tuple subclasses.
- """
-
- __slots__ = ('initial', 'default', 'readonly', 'instances', 'name')
-
- def __init__(self, initial=_NOT_SET, *,
- default=_NOT_SET,
- readonly=False,
- ):
- self.initial = initial
- self.default = default
- self.readonly = readonly
-
- # The instance cache is not inherently tied to the normal
- # lifetime of the instances. So must do something in order to
- # avoid keeping the instances alive by holding a reference here.
- # Ideally we would use weakref.WeakValueDictionary to do this.
- # However, most builtin types do not support weakrefs. So
- # instead we monkey-patch __del__ on the attached class to clear
- # the instance.
- self.instances = {}
- self.name = None
-
- def __set_name__(self, cls, name):
- if self.name is not None:
- raise TypeError('already used')
- self.name = name
- try:
- slotnames = cls.__slot_names__
- except AttributeError:
- slotnames = cls.__slot_names__ = []
- slotnames.append(name)
- self._ensure___del__(cls, slotnames)
-
- def __get__(self, obj, cls):
- if obj is None: # called on the class
- return self
- try:
- value = self.instances[id(obj)]
- except KeyError:
- if self.initial is _NOT_SET:
- value = self.default
- else:
- value = self.initial
- self.instances[id(obj)] = value
- if value is _NOT_SET:
- raise AttributeError(self.name)
- # XXX Optionally make a copy?
- return value
-
- def __set__(self, obj, value):
- if self.readonly:
- raise AttributeError(f'{self.name} is readonly')
- # XXX Optionally coerce?
- self.instances[id(obj)] = value
-
- def __delete__(self, obj):
- if self.readonly:
- raise AttributeError(f'{self.name} is readonly')
- self.instances[id(obj)] = self.default # XXX refleak?
-
- def _ensure___del__(self, cls, slotnames): # See the comment in __init__().
- try:
- old___del__ = cls.__del__
- except AttributeError:
- old___del__ = (lambda s: None)
- else:
- if getattr(old___del__, '_slotted', False):
- return
-
- def __del__(_self):
- for name in slotnames:
- delattr(_self, name)
- old___del__(_self)
- __del__._slotted = True
- cls.__del__ = __del__
-
- def set(self, obj, value):
- """Update the cached value for an object.
-
- This works even if the descriptor is read-only. This is
- particularly useful when initializing the object (e.g. in
- its __new__ or __init__).
- """
- self.instances[id(obj)] = value
-
-
-class classonly:
- """A non-data descriptor that makes a value only visible on the class.
-
- This is like the "classmethod" builtin, but does not show up on
- instances of the class. It may be used as a decorator.
- """
-
- def __init__(self, value):
- self.value = value
- self.getter = classmethod(value).__get__
- self.name = None
-
- def __set_name__(self, cls, name):
- if self.name is not None:
- raise TypeError('already used')
- self.name = name
-
- def __get__(self, obj, cls):
- if obj is not None:
- raise AttributeError(self.name)
- # called on the class
- return self.getter(None, cls)
-
-
-class _NTBase:
-
- __slots__ = ()
-
- @classonly
- def from_raw(cls, raw):
- if not raw:
- return None
- elif isinstance(raw, cls):
- return raw
- elif isinstance(raw, str):
- return cls.from_string(raw)
- else:
- if hasattr(raw, 'items'):
- return cls(**raw)
- try:
- args = tuple(raw)
- except TypeError:
- pass
- else:
- return cls(*args)
- raise NotImplementedError
-
- @classonly
- def from_string(cls, value):
- """Return a new instance based on the given string."""
- raise NotImplementedError
-
- @classmethod
- def _make(cls, iterable): # The default _make() is not subclass-friendly.
- return cls.__new__(cls, *iterable)
-
- # XXX Always validate?
- #def __init__(self, *args, **kwargs):
- # self.validate()
-
- # XXX The default __repr__() is not subclass-friendly (where the name changes).
- #def __repr__(self):
- # _, _, sig = super().__repr__().partition('(')
- # return f'{self.__class__.__name__}({sig}'
-
- # To make sorting work with None:
- def __lt__(self, other):
- try:
- return super().__lt__(other)
- except TypeError:
- if None in self:
- return True
- elif None in other:
- return False
- else:
- raise
-
- def validate(self):
- return
-
- # XXX Always validate?
- #def _replace(self, **kwargs):
- # obj = super()._replace(**kwargs)
- # obj.validate()
- # return obj