use pkg_resources from setuptools-69.0.3

This commit is contained in:
rembo10
2024-01-18 14:56:54 +05:30
parent 3685d32a7d
commit ad6a4f570e
85 changed files with 15912 additions and 8262 deletions
@@ -1,3 +0,0 @@
This software is made available under the terms of *either* of the licenses
found in LICENSE.APACHE or LICENSE.BSD. Contributions to this software is made
under the terms of *both* these licenses.
@@ -1,177 +0,0 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
@@ -1,23 +0,0 @@
Copyright (c) Donald Stufft and individual contributors.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@@ -1,26 +0,0 @@
# This file is dual licensed under the terms of the Apache License, Version
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.
__all__ = [
"__title__",
"__summary__",
"__uri__",
"__version__",
"__author__",
"__email__",
"__license__",
"__copyright__",
]
__title__ = "packaging"
__summary__ = "Core utilities for Python packages"
__uri__ = "https://github.com/pypa/packaging"
__version__ = "21.2"
__author__ = "Donald Stufft and individual contributors"
__email__ = "donald@stufft.io"
__license__ = "BSD-2-Clause or Apache-2.0"
__copyright__ = "2014-2019 %s" % __author__
+10 -20
View File
@@ -2,24 +2,14 @@
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.
from .__about__ import (
__author__,
__copyright__,
__email__,
__license__,
__summary__,
__title__,
__uri__,
__version__,
)
__title__ = "packaging"
__summary__ = "Core utilities for Python packages"
__uri__ = "https://github.com/pypa/packaging"
__all__ = [
"__title__",
"__summary__",
"__uri__",
"__version__",
"__author__",
"__email__",
"__license__",
"__copyright__",
]
__version__ = "23.1"
__author__ = "Donald Stufft and individual contributors"
__email__ = "donald@stufft.io"
__license__ = "BSD-2-Clause or Apache-2.0"
__copyright__ = "2014-2019 %s" % __author__
@@ -0,0 +1,108 @@
"""
ELF file parser.
This provides a class ``ELFFile`` that parses an ELF executable in a similar
interface to ``ZipFile``. Only the read interface is implemented.
Based on: https://gist.github.com/lyssdod/f51579ae8d93c8657a5564aefc2ffbca
ELF header: https://refspecs.linuxfoundation.org/elf/gabi4+/ch4.eheader.html
"""
import enum
import os
import struct
from typing import IO, Optional, Tuple
class ELFInvalid(ValueError):
pass
class EIClass(enum.IntEnum):
C32 = 1
C64 = 2
class EIData(enum.IntEnum):
Lsb = 1
Msb = 2
class EMachine(enum.IntEnum):
I386 = 3
S390 = 22
Arm = 40
X8664 = 62
AArc64 = 183
class ELFFile:
"""
Representation of an ELF executable.
"""
def __init__(self, f: IO[bytes]) -> None:
self._f = f
try:
ident = self._read("16B")
except struct.error:
raise ELFInvalid("unable to parse identification")
magic = bytes(ident[:4])
if magic != b"\x7fELF":
raise ELFInvalid(f"invalid magic: {magic!r}")
self.capacity = ident[4] # Format for program header (bitness).
self.encoding = ident[5] # Data structure encoding (endianness).
try:
# e_fmt: Format for program header.
# p_fmt: Format for section header.
# p_idx: Indexes to find p_type, p_offset, and p_filesz.
e_fmt, self._p_fmt, self._p_idx = {
(1, 1): ("<HHIIIIIHHH", "<IIIIIIII", (0, 1, 4)), # 32-bit LSB.
(1, 2): (">HHIIIIIHHH", ">IIIIIIII", (0, 1, 4)), # 32-bit MSB.
(2, 1): ("<HHIQQQIHHH", "<IIQQQQQQ", (0, 2, 5)), # 64-bit LSB.
(2, 2): (">HHIQQQIHHH", ">IIQQQQQQ", (0, 2, 5)), # 64-bit MSB.
}[(self.capacity, self.encoding)]
except KeyError:
raise ELFInvalid(
f"unrecognized capacity ({self.capacity}) or "
f"encoding ({self.encoding})"
)
try:
(
_,
self.machine, # Architecture type.
_,
_,
self._e_phoff, # Offset of program header.
_,
self.flags, # Processor-specific flags.
_,
self._e_phentsize, # Size of section.
self._e_phnum, # Number of sections.
) = self._read(e_fmt)
except struct.error as e:
raise ELFInvalid("unable to parse machine and section information") from e
def _read(self, fmt: str) -> Tuple[int, ...]:
return struct.unpack(fmt, self._f.read(struct.calcsize(fmt)))
@property
def interpreter(self) -> Optional[str]:
"""
The path recorded in the ``PT_INTERP`` section header.
"""
for index in range(self._e_phnum):
self._f.seek(self._e_phoff + self._e_phentsize * index)
try:
data = self._read(self._p_fmt)
except struct.error:
continue
if data[self._p_idx[0]] != 3: # Not PT_INTERP.
continue
self._f.seek(data[self._p_idx[1]])
return os.fsdecode(self._f.read(data[self._p_idx[2]])).strip("\0")
return None
+43 -104
View File
@@ -1,121 +1,60 @@
import collections
import contextlib
import functools
import os
import re
import struct
import sys
import warnings
from typing import IO, Dict, Iterator, NamedTuple, Optional, Tuple
from typing import Dict, Generator, Iterator, NamedTuple, Optional, Tuple
from ._elffile import EIClass, EIData, ELFFile, EMachine
EF_ARM_ABIMASK = 0xFF000000
EF_ARM_ABI_VER5 = 0x05000000
EF_ARM_ABI_FLOAT_HARD = 0x00000400
# Python does not provide platform information at sufficient granularity to
# identify the architecture of the running executable in some cases, so we
# determine it dynamically by reading the information from the running
# process. This only applies on Linux, which uses the ELF format.
class _ELFFileHeader:
# https://en.wikipedia.org/wiki/Executable_and_Linkable_Format#File_header
class _InvalidELFFileHeader(ValueError):
"""
An invalid ELF file header was found.
"""
ELF_MAGIC_NUMBER = 0x7F454C46
ELFCLASS32 = 1
ELFCLASS64 = 2
ELFDATA2LSB = 1
ELFDATA2MSB = 2
EM_386 = 3
EM_S390 = 22
EM_ARM = 40
EM_X86_64 = 62
EF_ARM_ABIMASK = 0xFF000000
EF_ARM_ABI_VER5 = 0x05000000
EF_ARM_ABI_FLOAT_HARD = 0x00000400
def __init__(self, file: IO[bytes]) -> None:
def unpack(fmt: str) -> int:
try:
data = file.read(struct.calcsize(fmt))
result: Tuple[int, ...] = struct.unpack(fmt, data)
except struct.error:
raise _ELFFileHeader._InvalidELFFileHeader()
return result[0]
self.e_ident_magic = unpack(">I")
if self.e_ident_magic != self.ELF_MAGIC_NUMBER:
raise _ELFFileHeader._InvalidELFFileHeader()
self.e_ident_class = unpack("B")
if self.e_ident_class not in {self.ELFCLASS32, self.ELFCLASS64}:
raise _ELFFileHeader._InvalidELFFileHeader()
self.e_ident_data = unpack("B")
if self.e_ident_data not in {self.ELFDATA2LSB, self.ELFDATA2MSB}:
raise _ELFFileHeader._InvalidELFFileHeader()
self.e_ident_version = unpack("B")
self.e_ident_osabi = unpack("B")
self.e_ident_abiversion = unpack("B")
self.e_ident_pad = file.read(7)
format_h = "<H" if self.e_ident_data == self.ELFDATA2LSB else ">H"
format_i = "<I" if self.e_ident_data == self.ELFDATA2LSB else ">I"
format_q = "<Q" if self.e_ident_data == self.ELFDATA2LSB else ">Q"
format_p = format_i if self.e_ident_class == self.ELFCLASS32 else format_q
self.e_type = unpack(format_h)
self.e_machine = unpack(format_h)
self.e_version = unpack(format_i)
self.e_entry = unpack(format_p)
self.e_phoff = unpack(format_p)
self.e_shoff = unpack(format_p)
self.e_flags = unpack(format_i)
self.e_ehsize = unpack(format_h)
self.e_phentsize = unpack(format_h)
self.e_phnum = unpack(format_h)
self.e_shentsize = unpack(format_h)
self.e_shnum = unpack(format_h)
self.e_shstrndx = unpack(format_h)
def _get_elf_header() -> Optional[_ELFFileHeader]:
# `os.PathLike` not a generic type until Python 3.9, so sticking with `str`
# as the type for `path` until then.
@contextlib.contextmanager
def _parse_elf(path: str) -> Generator[Optional[ELFFile], None, None]:
try:
with open(sys.executable, "rb") as f:
elf_header = _ELFFileHeader(f)
except (OSError, TypeError, _ELFFileHeader._InvalidELFFileHeader):
return None
return elf_header
with open(path, "rb") as f:
yield ELFFile(f)
except (OSError, TypeError, ValueError):
yield None
def _is_linux_armhf() -> bool:
def _is_linux_armhf(executable: str) -> bool:
# hard-float ABI can be detected from the ELF header of the running
# process
# https://static.docs.arm.com/ihi0044/g/aaelf32.pdf
elf_header = _get_elf_header()
if elf_header is None:
return False
result = elf_header.e_ident_class == elf_header.ELFCLASS32
result &= elf_header.e_ident_data == elf_header.ELFDATA2LSB
result &= elf_header.e_machine == elf_header.EM_ARM
result &= (
elf_header.e_flags & elf_header.EF_ARM_ABIMASK
) == elf_header.EF_ARM_ABI_VER5
result &= (
elf_header.e_flags & elf_header.EF_ARM_ABI_FLOAT_HARD
) == elf_header.EF_ARM_ABI_FLOAT_HARD
return result
with _parse_elf(executable) as f:
return (
f is not None
and f.capacity == EIClass.C32
and f.encoding == EIData.Lsb
and f.machine == EMachine.Arm
and f.flags & EF_ARM_ABIMASK == EF_ARM_ABI_VER5
and f.flags & EF_ARM_ABI_FLOAT_HARD == EF_ARM_ABI_FLOAT_HARD
)
def _is_linux_i686() -> bool:
elf_header = _get_elf_header()
if elf_header is None:
return False
result = elf_header.e_ident_class == elf_header.ELFCLASS32
result &= elf_header.e_ident_data == elf_header.ELFDATA2LSB
result &= elf_header.e_machine == elf_header.EM_386
return result
def _is_linux_i686(executable: str) -> bool:
with _parse_elf(executable) as f:
return (
f is not None
and f.capacity == EIClass.C32
and f.encoding == EIData.Lsb
and f.machine == EMachine.I386
)
def _have_compatible_abi(arch: str) -> bool:
def _have_compatible_abi(executable: str, arch: str) -> bool:
if arch == "armv7l":
return _is_linux_armhf()
return _is_linux_armhf(executable)
if arch == "i686":
return _is_linux_i686()
return _is_linux_i686(executable)
return arch in {"x86_64", "aarch64", "ppc64", "ppc64le", "s390x"}
@@ -141,10 +80,10 @@ def _glibc_version_string_confstr() -> Optional[str]:
# platform module.
# https://github.com/python/cpython/blob/fcf1d003bf4f0100c/Lib/platform.py#L175-L183
try:
# os.confstr("CS_GNU_LIBC_VERSION") returns a string like "glibc 2.17".
version_string = os.confstr("CS_GNU_LIBC_VERSION")
# Should be a string like "glibc 2.17".
version_string: str = getattr(os, "confstr")("CS_GNU_LIBC_VERSION")
assert version_string is not None
_, version = version_string.split()
_, version = version_string.rsplit()
except (AssertionError, AttributeError, OSError, ValueError):
# os.confstr() or CS_GNU_LIBC_VERSION not available (or a bad value)...
return None
@@ -211,8 +150,8 @@ def _parse_glibc_version(version_str: str) -> Tuple[int, int]:
m = re.match(r"(?P<major>[0-9]+)\.(?P<minor>[0-9]+)", version_str)
if not m:
warnings.warn(
"Expected glibc version with 2 components major.minor,"
" got: %s" % version_str,
f"Expected glibc version with 2 components major.minor,"
f" got: {version_str}",
RuntimeWarning,
)
return -1, -1
@@ -265,7 +204,7 @@ _LEGACY_MANYLINUX_MAP = {
def platform_tags(linux: str, arch: str) -> Iterator[str]:
if not _have_compatible_abi(arch):
if not _have_compatible_abi(sys.executable, arch):
return
# Oldest glibc to be supported regardless of architecture is (2, 17).
too_old_glibc2 = _GLibCVersion(2, 16)
@@ -4,68 +4,13 @@ This module implements logic to detect if the currently running Python is
linked against musl, and what musl version is used.
"""
import contextlib
import functools
import operator
import os
import re
import struct
import subprocess
import sys
from typing import IO, Iterator, NamedTuple, Optional, Tuple
from typing import Iterator, NamedTuple, Optional
def _read_unpacked(f: IO[bytes], fmt: str) -> Tuple[int, ...]:
return struct.unpack(fmt, f.read(struct.calcsize(fmt)))
def _parse_ld_musl_from_elf(f: IO[bytes]) -> Optional[str]:
"""Detect musl libc location by parsing the Python executable.
Based on: https://gist.github.com/lyssdod/f51579ae8d93c8657a5564aefc2ffbca
ELF header: https://refspecs.linuxfoundation.org/elf/gabi4+/ch4.eheader.html
"""
f.seek(0)
try:
ident = _read_unpacked(f, "16B")
except struct.error:
return None
if ident[:4] != tuple(b"\x7fELF"): # Invalid magic, not ELF.
return None
f.seek(struct.calcsize("HHI"), 1) # Skip file type, machine, and version.
try:
# e_fmt: Format for program header.
# p_fmt: Format for section header.
# p_idx: Indexes to find p_type, p_offset, and p_filesz.
e_fmt, p_fmt, p_idx = {
1: ("IIIIHHH", "IIIIIIII", (0, 1, 4)), # 32-bit.
2: ("QQQIHHH", "IIQQQQQQ", (0, 2, 5)), # 64-bit.
}[ident[4]]
except KeyError:
return None
else:
p_get = operator.itemgetter(*p_idx)
# Find the interpreter section and return its content.
try:
_, e_phoff, _, _, _, e_phentsize, e_phnum = _read_unpacked(f, e_fmt)
except struct.error:
return None
for i in range(e_phnum + 1):
f.seek(e_phoff + e_phentsize * i)
try:
p_type, p_offset, p_filesz = p_get(_read_unpacked(f, p_fmt))
except struct.error:
return None
if p_type != 3: # Not PT_INTERP.
continue
f.seek(p_offset)
interpreter = os.fsdecode(f.read(p_filesz)).strip("\0")
if "musl" not in interpreter:
return None
return interpreter
return None
from ._elffile import ELFFile
class _MuslVersion(NamedTuple):
@@ -95,13 +40,12 @@ def _get_musl_version(executable: str) -> Optional[_MuslVersion]:
Version 1.2.2
Dynamic Program Loader
"""
with contextlib.ExitStack() as stack:
try:
f = stack.enter_context(open(executable, "rb"))
except IOError:
return None
ld = _parse_ld_musl_from_elf(f)
if not ld:
try:
with open(executable, "rb") as f:
ld = ELFFile(f).interpreter
except (OSError, TypeError, ValueError):
return None
if ld is None or "musl" not in ld:
return None
proc = subprocess.run([ld], stderr=subprocess.PIPE, universal_newlines=True)
return _parse_musl_version(proc.stderr)
@@ -0,0 +1,353 @@
"""Handwritten parser of dependency specifiers.
The docstring for each __parse_* function contains ENBF-inspired grammar representing
the implementation.
"""
import ast
from typing import Any, List, NamedTuple, Optional, Tuple, Union
from ._tokenizer import DEFAULT_RULES, Tokenizer
class Node:
def __init__(self, value: str) -> None:
self.value = value
def __str__(self) -> str:
return self.value
def __repr__(self) -> str:
return f"<{self.__class__.__name__}('{self}')>"
def serialize(self) -> str:
raise NotImplementedError
class Variable(Node):
def serialize(self) -> str:
return str(self)
class Value(Node):
def serialize(self) -> str:
return f'"{self}"'
class Op(Node):
def serialize(self) -> str:
return str(self)
MarkerVar = Union[Variable, Value]
MarkerItem = Tuple[MarkerVar, Op, MarkerVar]
# MarkerAtom = Union[MarkerItem, List["MarkerAtom"]]
# MarkerList = List[Union["MarkerList", MarkerAtom, str]]
# mypy does not support recursive type definition
# https://github.com/python/mypy/issues/731
MarkerAtom = Any
MarkerList = List[Any]
class ParsedRequirement(NamedTuple):
name: str
url: str
extras: List[str]
specifier: str
marker: Optional[MarkerList]
# --------------------------------------------------------------------------------------
# Recursive descent parser for dependency specifier
# --------------------------------------------------------------------------------------
def parse_requirement(source: str) -> ParsedRequirement:
return _parse_requirement(Tokenizer(source, rules=DEFAULT_RULES))
def _parse_requirement(tokenizer: Tokenizer) -> ParsedRequirement:
"""
requirement = WS? IDENTIFIER WS? extras WS? requirement_details
"""
tokenizer.consume("WS")
name_token = tokenizer.expect(
"IDENTIFIER", expected="package name at the start of dependency specifier"
)
name = name_token.text
tokenizer.consume("WS")
extras = _parse_extras(tokenizer)
tokenizer.consume("WS")
url, specifier, marker = _parse_requirement_details(tokenizer)
tokenizer.expect("END", expected="end of dependency specifier")
return ParsedRequirement(name, url, extras, specifier, marker)
def _parse_requirement_details(
tokenizer: Tokenizer,
) -> Tuple[str, str, Optional[MarkerList]]:
"""
requirement_details = AT URL (WS requirement_marker?)?
| specifier WS? (requirement_marker)?
"""
specifier = ""
url = ""
marker = None
if tokenizer.check("AT"):
tokenizer.read()
tokenizer.consume("WS")
url_start = tokenizer.position
url = tokenizer.expect("URL", expected="URL after @").text
if tokenizer.check("END", peek=True):
return (url, specifier, marker)
tokenizer.expect("WS", expected="whitespace after URL")
# The input might end after whitespace.
if tokenizer.check("END", peek=True):
return (url, specifier, marker)
marker = _parse_requirement_marker(
tokenizer, span_start=url_start, after="URL and whitespace"
)
else:
specifier_start = tokenizer.position
specifier = _parse_specifier(tokenizer)
tokenizer.consume("WS")
if tokenizer.check("END", peek=True):
return (url, specifier, marker)
marker = _parse_requirement_marker(
tokenizer,
span_start=specifier_start,
after=(
"version specifier"
if specifier
else "name and no valid version specifier"
),
)
return (url, specifier, marker)
def _parse_requirement_marker(
tokenizer: Tokenizer, *, span_start: int, after: str
) -> MarkerList:
"""
requirement_marker = SEMICOLON marker WS?
"""
if not tokenizer.check("SEMICOLON"):
tokenizer.raise_syntax_error(
f"Expected end or semicolon (after {after})",
span_start=span_start,
)
tokenizer.read()
marker = _parse_marker(tokenizer)
tokenizer.consume("WS")
return marker
def _parse_extras(tokenizer: Tokenizer) -> List[str]:
"""
extras = (LEFT_BRACKET wsp* extras_list? wsp* RIGHT_BRACKET)?
"""
if not tokenizer.check("LEFT_BRACKET", peek=True):
return []
with tokenizer.enclosing_tokens(
"LEFT_BRACKET",
"RIGHT_BRACKET",
around="extras",
):
tokenizer.consume("WS")
extras = _parse_extras_list(tokenizer)
tokenizer.consume("WS")
return extras
def _parse_extras_list(tokenizer: Tokenizer) -> List[str]:
"""
extras_list = identifier (wsp* ',' wsp* identifier)*
"""
extras: List[str] = []
if not tokenizer.check("IDENTIFIER"):
return extras
extras.append(tokenizer.read().text)
while True:
tokenizer.consume("WS")
if tokenizer.check("IDENTIFIER", peek=True):
tokenizer.raise_syntax_error("Expected comma between extra names")
elif not tokenizer.check("COMMA"):
break
tokenizer.read()
tokenizer.consume("WS")
extra_token = tokenizer.expect("IDENTIFIER", expected="extra name after comma")
extras.append(extra_token.text)
return extras
def _parse_specifier(tokenizer: Tokenizer) -> str:
"""
specifier = LEFT_PARENTHESIS WS? version_many WS? RIGHT_PARENTHESIS
| WS? version_many WS?
"""
with tokenizer.enclosing_tokens(
"LEFT_PARENTHESIS",
"RIGHT_PARENTHESIS",
around="version specifier",
):
tokenizer.consume("WS")
parsed_specifiers = _parse_version_many(tokenizer)
tokenizer.consume("WS")
return parsed_specifiers
def _parse_version_many(tokenizer: Tokenizer) -> str:
"""
version_many = (SPECIFIER (WS? COMMA WS? SPECIFIER)*)?
"""
parsed_specifiers = ""
while tokenizer.check("SPECIFIER"):
span_start = tokenizer.position
parsed_specifiers += tokenizer.read().text
if tokenizer.check("VERSION_PREFIX_TRAIL", peek=True):
tokenizer.raise_syntax_error(
".* suffix can only be used with `==` or `!=` operators",
span_start=span_start,
span_end=tokenizer.position + 1,
)
if tokenizer.check("VERSION_LOCAL_LABEL_TRAIL", peek=True):
tokenizer.raise_syntax_error(
"Local version label can only be used with `==` or `!=` operators",
span_start=span_start,
span_end=tokenizer.position,
)
tokenizer.consume("WS")
if not tokenizer.check("COMMA"):
break
parsed_specifiers += tokenizer.read().text
tokenizer.consume("WS")
return parsed_specifiers
# --------------------------------------------------------------------------------------
# Recursive descent parser for marker expression
# --------------------------------------------------------------------------------------
def parse_marker(source: str) -> MarkerList:
return _parse_marker(Tokenizer(source, rules=DEFAULT_RULES))
def _parse_marker(tokenizer: Tokenizer) -> MarkerList:
"""
marker = marker_atom (BOOLOP marker_atom)+
"""
expression = [_parse_marker_atom(tokenizer)]
while tokenizer.check("BOOLOP"):
token = tokenizer.read()
expr_right = _parse_marker_atom(tokenizer)
expression.extend((token.text, expr_right))
return expression
def _parse_marker_atom(tokenizer: Tokenizer) -> MarkerAtom:
"""
marker_atom = WS? LEFT_PARENTHESIS WS? marker WS? RIGHT_PARENTHESIS WS?
| WS? marker_item WS?
"""
tokenizer.consume("WS")
if tokenizer.check("LEFT_PARENTHESIS", peek=True):
with tokenizer.enclosing_tokens(
"LEFT_PARENTHESIS",
"RIGHT_PARENTHESIS",
around="marker expression",
):
tokenizer.consume("WS")
marker: MarkerAtom = _parse_marker(tokenizer)
tokenizer.consume("WS")
else:
marker = _parse_marker_item(tokenizer)
tokenizer.consume("WS")
return marker
def _parse_marker_item(tokenizer: Tokenizer) -> MarkerItem:
"""
marker_item = WS? marker_var WS? marker_op WS? marker_var WS?
"""
tokenizer.consume("WS")
marker_var_left = _parse_marker_var(tokenizer)
tokenizer.consume("WS")
marker_op = _parse_marker_op(tokenizer)
tokenizer.consume("WS")
marker_var_right = _parse_marker_var(tokenizer)
tokenizer.consume("WS")
return (marker_var_left, marker_op, marker_var_right)
def _parse_marker_var(tokenizer: Tokenizer) -> MarkerVar:
"""
marker_var = VARIABLE | QUOTED_STRING
"""
if tokenizer.check("VARIABLE"):
return process_env_var(tokenizer.read().text.replace(".", "_"))
elif tokenizer.check("QUOTED_STRING"):
return process_python_str(tokenizer.read().text)
else:
tokenizer.raise_syntax_error(
message="Expected a marker variable or quoted string"
)
def process_env_var(env_var: str) -> Variable:
if (
env_var == "platform_python_implementation"
or env_var == "python_implementation"
):
return Variable("platform_python_implementation")
else:
return Variable(env_var)
def process_python_str(python_str: str) -> Value:
value = ast.literal_eval(python_str)
return Value(str(value))
def _parse_marker_op(tokenizer: Tokenizer) -> Op:
"""
marker_op = IN | NOT IN | OP
"""
if tokenizer.check("IN"):
tokenizer.read()
return Op("in")
elif tokenizer.check("NOT"):
tokenizer.read()
tokenizer.expect("WS", expected="whitespace after 'not'")
tokenizer.expect("IN", expected="'in' after 'not'")
return Op("not in")
elif tokenizer.check("OP"):
return Op(tokenizer.read().text)
else:
return tokenizer.raise_syntax_error(
"Expected marker operator, one of "
"<=, <, !=, ==, >=, >, ~=, ===, in, not in"
)
@@ -19,9 +19,6 @@ class InfinityType:
def __eq__(self, other: object) -> bool:
return isinstance(other, self.__class__)
def __ne__(self, other: object) -> bool:
return not isinstance(other, self.__class__)
def __gt__(self, other: object) -> bool:
return True
@@ -51,9 +48,6 @@ class NegativeInfinityType:
def __eq__(self, other: object) -> bool:
return isinstance(other, self.__class__)
def __ne__(self, other: object) -> bool:
return not isinstance(other, self.__class__)
def __gt__(self, other: object) -> bool:
return False
@@ -0,0 +1,192 @@
import contextlib
import re
from dataclasses import dataclass
from typing import Dict, Iterator, NoReturn, Optional, Tuple, Union
from .specifiers import Specifier
@dataclass
class Token:
name: str
text: str
position: int
class ParserSyntaxError(Exception):
"""The provided source text could not be parsed correctly."""
def __init__(
self,
message: str,
*,
source: str,
span: Tuple[int, int],
) -> None:
self.span = span
self.message = message
self.source = source
super().__init__()
def __str__(self) -> str:
marker = " " * self.span[0] + "~" * (self.span[1] - self.span[0]) + "^"
return "\n ".join([self.message, self.source, marker])
DEFAULT_RULES: "Dict[str, Union[str, re.Pattern[str]]]" = {
"LEFT_PARENTHESIS": r"\(",
"RIGHT_PARENTHESIS": r"\)",
"LEFT_BRACKET": r"\[",
"RIGHT_BRACKET": r"\]",
"SEMICOLON": r";",
"COMMA": r",",
"QUOTED_STRING": re.compile(
r"""
(
('[^']*')
|
("[^"]*")
)
""",
re.VERBOSE,
),
"OP": r"(===|==|~=|!=|<=|>=|<|>)",
"BOOLOP": r"\b(or|and)\b",
"IN": r"\bin\b",
"NOT": r"\bnot\b",
"VARIABLE": re.compile(
r"""
\b(
python_version
|python_full_version
|os[._]name
|sys[._]platform
|platform_(release|system)
|platform[._](version|machine|python_implementation)
|python_implementation
|implementation_(name|version)
|extra
)\b
""",
re.VERBOSE,
),
"SPECIFIER": re.compile(
Specifier._operator_regex_str + Specifier._version_regex_str,
re.VERBOSE | re.IGNORECASE,
),
"AT": r"\@",
"URL": r"[^ \t]+",
"IDENTIFIER": r"\b[a-zA-Z0-9][a-zA-Z0-9._-]*\b",
"VERSION_PREFIX_TRAIL": r"\.\*",
"VERSION_LOCAL_LABEL_TRAIL": r"\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*",
"WS": r"[ \t]+",
"END": r"$",
}
class Tokenizer:
"""Context-sensitive token parsing.
Provides methods to examine the input stream to check whether the next token
matches.
"""
def __init__(
self,
source: str,
*,
rules: "Dict[str, Union[str, re.Pattern[str]]]",
) -> None:
self.source = source
self.rules: Dict[str, re.Pattern[str]] = {
name: re.compile(pattern) for name, pattern in rules.items()
}
self.next_token: Optional[Token] = None
self.position = 0
def consume(self, name: str) -> None:
"""Move beyond provided token name, if at current position."""
if self.check(name):
self.read()
def check(self, name: str, *, peek: bool = False) -> bool:
"""Check whether the next token has the provided name.
By default, if the check succeeds, the token *must* be read before
another check. If `peek` is set to `True`, the token is not loaded and
would need to be checked again.
"""
assert (
self.next_token is None
), f"Cannot check for {name!r}, already have {self.next_token!r}"
assert name in self.rules, f"Unknown token name: {name!r}"
expression = self.rules[name]
match = expression.match(self.source, self.position)
if match is None:
return False
if not peek:
self.next_token = Token(name, match[0], self.position)
return True
def expect(self, name: str, *, expected: str) -> Token:
"""Expect a certain token name next, failing with a syntax error otherwise.
The token is *not* read.
"""
if not self.check(name):
raise self.raise_syntax_error(f"Expected {expected}")
return self.read()
def read(self) -> Token:
"""Consume the next token and return it."""
token = self.next_token
assert token is not None
self.position += len(token.text)
self.next_token = None
return token
def raise_syntax_error(
self,
message: str,
*,
span_start: Optional[int] = None,
span_end: Optional[int] = None,
) -> NoReturn:
"""Raise ParserSyntaxError at the given position."""
span = (
self.position if span_start is None else span_start,
self.position if span_end is None else span_end,
)
raise ParserSyntaxError(
message,
source=self.source,
span=span,
)
@contextlib.contextmanager
def enclosing_tokens(
self, open_token: str, close_token: str, *, around: str
) -> Iterator[None]:
if self.check(open_token):
open_position = self.position
self.read()
else:
open_position = None
yield
if open_position is None:
return
if not self.check(close_token):
self.raise_syntax_error(
f"Expected matching {close_token} for {open_token}, after {around}",
span_start=open_position,
)
self.read()
+77 -129
View File
@@ -8,19 +8,17 @@ import platform
import sys
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
from pkg_resources.extern.pyparsing import ( # noqa: N817
Forward,
Group,
Literal as L,
ParseException,
ParseResults,
QuotedString,
ZeroOrMore,
stringEnd,
stringStart,
from ._parser import (
MarkerAtom,
MarkerList,
Op,
Value,
Variable,
parse_marker as _parse_marker,
)
from ._tokenizer import ParserSyntaxError
from .specifiers import InvalidSpecifier, Specifier
from .utils import canonicalize_name
__all__ = [
"InvalidMarker",
@@ -52,101 +50,24 @@ class UndefinedEnvironmentName(ValueError):
"""
class Node:
def __init__(self, value: Any) -> None:
self.value = value
def __str__(self) -> str:
return str(self.value)
def __repr__(self) -> str:
return f"<{self.__class__.__name__}('{self}')>"
def serialize(self) -> str:
raise NotImplementedError
class Variable(Node):
def serialize(self) -> str:
return str(self)
class Value(Node):
def serialize(self) -> str:
return f'"{self}"'
class Op(Node):
def serialize(self) -> str:
return str(self)
VARIABLE = (
L("implementation_version")
| L("platform_python_implementation")
| L("implementation_name")
| L("python_full_version")
| L("platform_release")
| L("platform_version")
| L("platform_machine")
| L("platform_system")
| L("python_version")
| L("sys_platform")
| L("os_name")
| L("os.name") # PEP-345
| L("sys.platform") # PEP-345
| L("platform.version") # PEP-345
| L("platform.machine") # PEP-345
| L("platform.python_implementation") # PEP-345
| L("python_implementation") # undocumented setuptools legacy
| L("extra") # PEP-508
)
ALIASES = {
"os.name": "os_name",
"sys.platform": "sys_platform",
"platform.version": "platform_version",
"platform.machine": "platform_machine",
"platform.python_implementation": "platform_python_implementation",
"python_implementation": "platform_python_implementation",
}
VARIABLE.setParseAction(lambda s, l, t: Variable(ALIASES.get(t[0], t[0])))
VERSION_CMP = (
L("===") | L("==") | L(">=") | L("<=") | L("!=") | L("~=") | L(">") | L("<")
)
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]))
BOOLOP = L("and") | L("or")
MARKER_VAR = VARIABLE | MARKER_VALUE
MARKER_ITEM = Group(MARKER_VAR + MARKER_OP + MARKER_VAR)
MARKER_ITEM.setParseAction(lambda s, l, t: tuple(t[0]))
LPAREN = L("(").suppress()
RPAREN = L(")").suppress()
MARKER_EXPR = Forward()
MARKER_ATOM = MARKER_ITEM | Group(LPAREN + MARKER_EXPR + RPAREN)
MARKER_EXPR << MARKER_ATOM + ZeroOrMore(BOOLOP + MARKER_EXPR)
MARKER = stringStart + MARKER_EXPR + stringEnd
def _coerce_parse_result(results: Union[ParseResults, List[Any]]) -> List[Any]:
if isinstance(results, ParseResults):
return [_coerce_parse_result(i) for i in results]
else:
return results
def _normalize_extra_values(results: Any) -> Any:
"""
Normalize extra values.
"""
if isinstance(results[0], tuple):
lhs, op, rhs = results[0]
if isinstance(lhs, Variable) and lhs.value == "extra":
normalized_extra = canonicalize_name(rhs.value)
rhs = Value(normalized_extra)
elif isinstance(rhs, Variable) and rhs.value == "extra":
normalized_extra = canonicalize_name(lhs.value)
lhs = Value(normalized_extra)
results[0] = lhs, op, rhs
return results
def _format_marker(
marker: Union[List[str], Tuple[Node, ...], str], first: Optional[bool] = True
marker: Union[List[str], MarkerAtom, str], first: Optional[bool] = True
) -> str:
assert isinstance(marker, (list, tuple, str))
@@ -192,7 +113,7 @@ def _eval_op(lhs: str, op: Op, rhs: str) -> bool:
except InvalidSpecifier:
pass
else:
return spec.contains(lhs)
return spec.contains(lhs, prereleases=True)
oper: Optional[Operator] = _operators.get(op.serialize())
if oper is None:
@@ -201,25 +122,19 @@ def _eval_op(lhs: str, op: Op, rhs: str) -> bool:
return oper(lhs, rhs)
class Undefined:
pass
def _normalize(*values: str, key: str) -> Tuple[str, ...]:
# PEP 685 Comparison of extra names for optional distribution dependencies
# https://peps.python.org/pep-0685/
# > When comparing extra names, tools MUST normalize the names being
# > compared using the semantics outlined in PEP 503 for names
if key == "extra":
return tuple(canonicalize_name(v) for v in values)
# other environment markers don't have such standards
return values
_undefined = Undefined()
def _get_env(environment: Dict[str, str], name: str) -> str:
value: Union[str, Undefined] = environment.get(name, _undefined)
if isinstance(value, Undefined):
raise UndefinedEnvironmentName(
f"{name!r} does not exist in evaluation environment."
)
return value
def _evaluate_markers(markers: List[Any], environment: Dict[str, str]) -> bool:
def _evaluate_markers(markers: MarkerList, environment: Dict[str, str]) -> bool:
groups: List[List[bool]] = [[]]
for marker in markers:
@@ -231,12 +146,15 @@ def _evaluate_markers(markers: List[Any], environment: Dict[str, str]) -> bool:
lhs, op, rhs = marker
if isinstance(lhs, Variable):
lhs_value = _get_env(environment, lhs.value)
environment_key = lhs.value
lhs_value = environment[environment_key]
rhs_value = rhs.value
else:
lhs_value = lhs.value
rhs_value = _get_env(environment, rhs.value)
environment_key = rhs.value
rhs_value = environment[environment_key]
lhs_value, rhs_value = _normalize(lhs_value, rhs_value, key=environment_key)
groups[-1].append(_eval_op(lhs_value, op, rhs_value))
else:
assert marker in ["and", "or"]
@@ -274,13 +192,29 @@ def default_environment() -> Dict[str, str]:
class Marker:
def __init__(self, marker: str) -> None:
# Note: We create a Marker object without calling this constructor in
# packaging.requirements.Requirement. If any additional logic is
# added here, make sure to mirror/adapt Requirement.
try:
self._markers = _coerce_parse_result(MARKER.parseString(marker))
except ParseException as e:
raise InvalidMarker(
f"Invalid marker: {marker!r}, parse error at "
f"{marker[e.loc : e.loc + 8]!r}"
)
self._markers = _normalize_extra_values(_parse_marker(marker))
# The attribute `_markers` can be described in terms of a recursive type:
# MarkerList = List[Union[Tuple[Node, ...], str, MarkerList]]
#
# For example, the following expression:
# python_version > "3.6" or (python_version == "3.6" and os_name == "unix")
#
# is parsed into:
# [
# (<Variable('python_version')>, <Op('>')>, <Value('3.6')>),
# 'and',
# [
# (<Variable('python_version')>, <Op('==')>, <Value('3.6')>),
# 'or',
# (<Variable('os_name')>, <Op('==')>, <Value('unix')>)
# ]
# ]
except ParserSyntaxError as e:
raise InvalidMarker(str(e)) from e
def __str__(self) -> str:
return _format_marker(self._markers)
@@ -288,6 +222,15 @@ class Marker:
def __repr__(self) -> str:
return f"<Marker('{self}')>"
def __hash__(self) -> int:
return hash((self.__class__.__name__, str(self)))
def __eq__(self, other: Any) -> bool:
if not isinstance(other, Marker):
return NotImplemented
return str(self) == str(other)
def evaluate(self, environment: Optional[Dict[str, str]] = None) -> bool:
"""Evaluate a marker.
@@ -298,7 +241,12 @@ class Marker:
The environment is determined from the current Python process.
"""
current_environment = default_environment()
current_environment["extra"] = ""
if environment is not None:
current_environment.update(environment)
# The API used to allow setting extra to None. We need to handle this
# case for backwards compatibility.
if current_environment["extra"] is None:
current_environment["extra"] = ""
return _evaluate_markers(self._markers, current_environment)
@@ -0,0 +1,408 @@
import email.feedparser
import email.header
import email.message
import email.parser
import email.policy
import sys
import typing
from typing import Dict, List, Optional, Tuple, Union, cast
if sys.version_info >= (3, 8): # pragma: no cover
from typing import TypedDict
else: # pragma: no cover
if typing.TYPE_CHECKING:
from typing_extensions import TypedDict
else:
try:
from typing_extensions import TypedDict
except ImportError:
class TypedDict:
def __init_subclass__(*_args, **_kwargs):
pass
# The RawMetadata class attempts to make as few assumptions about the underlying
# serialization formats as possible. The idea is that as long as a serialization
# formats offer some very basic primitives in *some* way then we can support
# serializing to and from that format.
class RawMetadata(TypedDict, total=False):
"""A dictionary of raw core metadata.
Each field in core metadata maps to a key of this dictionary (when data is
provided). The key is lower-case and underscores are used instead of dashes
compared to the equivalent core metadata field. Any core metadata field that
can be specified multiple times or can hold multiple values in a single
field have a key with a plural name.
Core metadata fields that can be specified multiple times are stored as a
list or dict depending on which is appropriate for the field. Any fields
which hold multiple values in a single field are stored as a list.
"""
# Metadata 1.0 - PEP 241
metadata_version: str
name: str
version: str
platforms: List[str]
summary: str
description: str
keywords: List[str]
home_page: str
author: str
author_email: str
license: str
# Metadata 1.1 - PEP 314
supported_platforms: List[str]
download_url: str
classifiers: List[str]
requires: List[str]
provides: List[str]
obsoletes: List[str]
# Metadata 1.2 - PEP 345
maintainer: str
maintainer_email: str
requires_dist: List[str]
provides_dist: List[str]
obsoletes_dist: List[str]
requires_python: str
requires_external: List[str]
project_urls: Dict[str, str]
# Metadata 2.0
# PEP 426 attempted to completely revamp the metadata format
# but got stuck without ever being able to build consensus on
# it and ultimately ended up withdrawn.
#
# However, a number of tools had started emiting METADATA with
# `2.0` Metadata-Version, so for historical reasons, this version
# was skipped.
# Metadata 2.1 - PEP 566
description_content_type: str
provides_extra: List[str]
# Metadata 2.2 - PEP 643
dynamic: List[str]
# Metadata 2.3 - PEP 685
# No new fields were added in PEP 685, just some edge case were
# tightened up to provide better interoptability.
_STRING_FIELDS = {
"author",
"author_email",
"description",
"description_content_type",
"download_url",
"home_page",
"license",
"maintainer",
"maintainer_email",
"metadata_version",
"name",
"requires_python",
"summary",
"version",
}
_LIST_STRING_FIELDS = {
"classifiers",
"dynamic",
"obsoletes",
"obsoletes_dist",
"platforms",
"provides",
"provides_dist",
"provides_extra",
"requires",
"requires_dist",
"requires_external",
"supported_platforms",
}
def _parse_keywords(data: str) -> List[str]:
"""Split a string of comma-separate keyboards into a list of keywords."""
return [k.strip() for k in data.split(",")]
def _parse_project_urls(data: List[str]) -> Dict[str, str]:
"""Parse a list of label/URL string pairings separated by a comma."""
urls = {}
for pair in data:
# Our logic is slightly tricky here as we want to try and do
# *something* reasonable with malformed data.
#
# The main thing that we have to worry about, is data that does
# not have a ',' at all to split the label from the Value. There
# isn't a singular right answer here, and we will fail validation
# later on (if the caller is validating) so it doesn't *really*
# matter, but since the missing value has to be an empty str
# and our return value is dict[str, str], if we let the key
# be the missing value, then they'd have multiple '' values that
# overwrite each other in a accumulating dict.
#
# The other potentional issue is that it's possible to have the
# same label multiple times in the metadata, with no solid "right"
# answer with what to do in that case. As such, we'll do the only
# thing we can, which is treat the field as unparseable and add it
# to our list of unparsed fields.
parts = [p.strip() for p in pair.split(",", 1)]
parts.extend([""] * (max(0, 2 - len(parts)))) # Ensure 2 items
# TODO: The spec doesn't say anything about if the keys should be
# considered case sensitive or not... logically they should
# be case-preserving and case-insensitive, but doing that
# would open up more cases where we might have duplicate
# entries.
label, url = parts
if label in urls:
# The label already exists in our set of urls, so this field
# is unparseable, and we can just add the whole thing to our
# unparseable data and stop processing it.
raise KeyError("duplicate labels in project urls")
urls[label] = url
return urls
def _get_payload(msg: email.message.Message, source: Union[bytes, str]) -> str:
"""Get the body of the message."""
# If our source is a str, then our caller has managed encodings for us,
# and we don't need to deal with it.
if isinstance(source, str):
payload: str = msg.get_payload()
return payload
# If our source is a bytes, then we're managing the encoding and we need
# to deal with it.
else:
bpayload: bytes = msg.get_payload(decode=True)
try:
return bpayload.decode("utf8", "strict")
except UnicodeDecodeError:
raise ValueError("payload in an invalid encoding")
# The various parse_FORMAT functions here are intended to be as lenient as
# possible in their parsing, while still returning a correctly typed
# RawMetadata.
#
# To aid in this, we also generally want to do as little touching of the
# data as possible, except where there are possibly some historic holdovers
# that make valid data awkward to work with.
#
# While this is a lower level, intermediate format than our ``Metadata``
# class, some light touch ups can make a massive difference in usability.
# Map METADATA fields to RawMetadata.
_EMAIL_TO_RAW_MAPPING = {
"author": "author",
"author-email": "author_email",
"classifier": "classifiers",
"description": "description",
"description-content-type": "description_content_type",
"download-url": "download_url",
"dynamic": "dynamic",
"home-page": "home_page",
"keywords": "keywords",
"license": "license",
"maintainer": "maintainer",
"maintainer-email": "maintainer_email",
"metadata-version": "metadata_version",
"name": "name",
"obsoletes": "obsoletes",
"obsoletes-dist": "obsoletes_dist",
"platform": "platforms",
"project-url": "project_urls",
"provides": "provides",
"provides-dist": "provides_dist",
"provides-extra": "provides_extra",
"requires": "requires",
"requires-dist": "requires_dist",
"requires-external": "requires_external",
"requires-python": "requires_python",
"summary": "summary",
"supported-platform": "supported_platforms",
"version": "version",
}
def parse_email(data: Union[bytes, str]) -> Tuple[RawMetadata, Dict[str, List[str]]]:
"""Parse a distribution's metadata.
This function returns a two-item tuple of dicts. The first dict is of
recognized fields from the core metadata specification. Fields that can be
parsed and translated into Python's built-in types are converted
appropriately. All other fields are left as-is. Fields that are allowed to
appear multiple times are stored as lists.
The second dict contains all other fields from the metadata. This includes
any unrecognized fields. It also includes any fields which are expected to
be parsed into a built-in type but were not formatted appropriately. Finally,
any fields that are expected to appear only once but are repeated are
included in this dict.
"""
raw: Dict[str, Union[str, List[str], Dict[str, str]]] = {}
unparsed: Dict[str, List[str]] = {}
if isinstance(data, str):
parsed = email.parser.Parser(policy=email.policy.compat32).parsestr(data)
else:
parsed = email.parser.BytesParser(policy=email.policy.compat32).parsebytes(data)
# We have to wrap parsed.keys() in a set, because in the case of multiple
# values for a key (a list), the key will appear multiple times in the
# list of keys, but we're avoiding that by using get_all().
for name in frozenset(parsed.keys()):
# Header names in RFC are case insensitive, so we'll normalize to all
# lower case to make comparisons easier.
name = name.lower()
# We use get_all() here, even for fields that aren't multiple use,
# because otherwise someone could have e.g. two Name fields, and we
# would just silently ignore it rather than doing something about it.
headers = parsed.get_all(name)
# The way the email module works when parsing bytes is that it
# unconditionally decodes the bytes as ascii using the surrogateescape
# handler. When you pull that data back out (such as with get_all() ),
# it looks to see if the str has any surrogate escapes, and if it does
# it wraps it in a Header object instead of returning the string.
#
# As such, we'll look for those Header objects, and fix up the encoding.
value = []
# Flag if we have run into any issues processing the headers, thus
# signalling that the data belongs in 'unparsed'.
valid_encoding = True
for h in headers:
# It's unclear if this can return more types than just a Header or
# a str, so we'll just assert here to make sure.
assert isinstance(h, (email.header.Header, str))
# If it's a header object, we need to do our little dance to get
# the real data out of it. In cases where there is invalid data
# we're going to end up with mojibake, but there's no obvious, good
# way around that without reimplementing parts of the Header object
# ourselves.
#
# That should be fine since, if mojibacked happens, this key is
# going into the unparsed dict anyways.
if isinstance(h, email.header.Header):
# The Header object stores it's data as chunks, and each chunk
# can be independently encoded, so we'll need to check each
# of them.
chunks: List[Tuple[bytes, Optional[str]]] = []
for bin, encoding in email.header.decode_header(h):
try:
bin.decode("utf8", "strict")
except UnicodeDecodeError:
# Enable mojibake.
encoding = "latin1"
valid_encoding = False
else:
encoding = "utf8"
chunks.append((bin, encoding))
# Turn our chunks back into a Header object, then let that
# Header object do the right thing to turn them into a
# string for us.
value.append(str(email.header.make_header(chunks)))
# This is already a string, so just add it.
else:
value.append(h)
# We've processed all of our values to get them into a list of str,
# but we may have mojibake data, in which case this is an unparsed
# field.
if not valid_encoding:
unparsed[name] = value
continue
raw_name = _EMAIL_TO_RAW_MAPPING.get(name)
if raw_name is None:
# This is a bit of a weird situation, we've encountered a key that
# we don't know what it means, so we don't know whether it's meant
# to be a list or not.
#
# Since we can't really tell one way or another, we'll just leave it
# as a list, even though it may be a single item list, because that's
# what makes the most sense for email headers.
unparsed[name] = value
continue
# If this is one of our string fields, then we'll check to see if our
# value is a list of a single item. If it is then we'll assume that
# it was emitted as a single string, and unwrap the str from inside
# the list.
#
# If it's any other kind of data, then we haven't the faintest clue
# what we should parse it as, and we have to just add it to our list
# of unparsed stuff.
if raw_name in _STRING_FIELDS and len(value) == 1:
raw[raw_name] = value[0]
# If this is one of our list of string fields, then we can just assign
# the value, since email *only* has strings, and our get_all() call
# above ensures that this is a list.
elif raw_name in _LIST_STRING_FIELDS:
raw[raw_name] = value
# Special Case: Keywords
# The keywords field is implemented in the metadata spec as a str,
# but it conceptually is a list of strings, and is serialized using
# ", ".join(keywords), so we'll do some light data massaging to turn
# this into what it logically is.
elif raw_name == "keywords" and len(value) == 1:
raw[raw_name] = _parse_keywords(value[0])
# Special Case: Project-URL
# The project urls is implemented in the metadata spec as a list of
# specially-formatted strings that represent a key and a value, which
# is fundamentally a mapping, however the email format doesn't support
# mappings in a sane way, so it was crammed into a list of strings
# instead.
#
# We will do a little light data massaging to turn this into a map as
# it logically should be.
elif raw_name == "project_urls":
try:
raw[raw_name] = _parse_project_urls(value)
except KeyError:
unparsed[name] = value
# Nothing that we've done has managed to parse this, so it'll just
# throw it in our unparseable data and move on.
else:
unparsed[name] = value
# We need to support getting the Description from the message payload in
# addition to getting it from the the headers. This does mean, though, there
# is the possibility of it being set both ways, in which case we put both
# in 'unparsed' since we don't know which is right.
try:
payload = _get_payload(parsed, data)
except ValueError:
unparsed.setdefault("description", []).append(
parsed.get_payload(decode=isinstance(data, bytes))
)
else:
if payload:
# Check to see if we've already got a description, if so then both
# it, and this body move to unparseable.
if "description" in raw:
description_header = cast(str, raw.pop("description"))
unparsed.setdefault("description", []).extend(
[description_header, payload]
)
elif "description" in unparsed:
unparsed["description"].append(payload)
else:
raw["description"] = payload
# We need to cast our `raw` to a metadata, because a TypedDict only support
# literal key names, but we're computing our key names on purpose, but the
# way this function is implemented, our `TypedDict` can only have valid key
# names.
return cast(RawMetadata, raw), unparsed
@@ -2,26 +2,13 @@
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.
import re
import string
import urllib.parse
from typing import List, Optional as TOptional, Set
from typing import Any, List, Optional, Set
from pkg_resources.extern.pyparsing import ( # noqa
Combine,
Literal as L,
Optional,
ParseException,
Regex,
Word,
ZeroOrMore,
originalTextFor,
stringEnd,
stringStart,
)
from .markers import MARKER_EXPR, Marker
from .specifiers import LegacySpecifier, Specifier, SpecifierSet
from ._parser import parse_requirement as _parse_requirement
from ._tokenizer import ParserSyntaxError
from .markers import Marker, _normalize_extra_values
from .specifiers import SpecifierSet
class InvalidRequirement(ValueError):
@@ -30,60 +17,6 @@ class InvalidRequirement(ValueError):
"""
ALPHANUM = Word(string.ascii_letters + string.digits)
LBRACKET = L("[").suppress()
RBRACKET = L("]").suppress()
LPAREN = L("(").suppress()
RPAREN = L(")").suppress()
COMMA = L(",").suppress()
SEMICOLON = L(";").suppress()
AT = L("@").suppress()
PUNCTUATION = Word("-_.")
IDENTIFIER_END = ALPHANUM | (ZeroOrMore(PUNCTUATION) + ALPHANUM)
IDENTIFIER = Combine(ALPHANUM + ZeroOrMore(IDENTIFIER_END))
NAME = IDENTIFIER("name")
EXTRA = IDENTIFIER
URI = Regex(r"[^ ]+")("url")
URL = AT + URI
EXTRAS_LIST = EXTRA + ZeroOrMore(COMMA + EXTRA)
EXTRAS = (LBRACKET + Optional(EXTRAS_LIST) + RBRACKET)("extras")
VERSION_PEP440 = Regex(Specifier._regex_str, re.VERBOSE | re.IGNORECASE)
VERSION_LEGACY = Regex(LegacySpecifier._regex_str, re.VERBOSE | re.IGNORECASE)
VERSION_ONE = VERSION_PEP440 ^ VERSION_LEGACY
VERSION_MANY = Combine(
VERSION_ONE + ZeroOrMore(COMMA + VERSION_ONE), joinString=",", adjacent=False
)("_raw_spec")
_VERSION_SPEC = Optional((LPAREN + VERSION_MANY + RPAREN) | VERSION_MANY)
_VERSION_SPEC.setParseAction(lambda s, l, t: t._raw_spec or "")
VERSION_SPEC = originalTextFor(_VERSION_SPEC)("specifier")
VERSION_SPEC.setParseAction(lambda s, l, t: t[1])
MARKER_EXPR = originalTextFor(MARKER_EXPR())("marker")
MARKER_EXPR.setParseAction(
lambda s, l, t: Marker(s[t._original_start : t._original_end])
)
MARKER_SEPARATOR = SEMICOLON
MARKER = MARKER_SEPARATOR + MARKER_EXPR
VERSION_AND_MARKER = VERSION_SPEC + Optional(MARKER)
URL_AND_MARKER = URL + Optional(MARKER)
NAMED_REQUIREMENT = NAME + Optional(EXTRAS) + (URL_AND_MARKER | VERSION_AND_MARKER)
REQUIREMENT = stringStart + NAMED_REQUIREMENT + stringEnd
# pkg_resources.extern.pyparsing isn't thread safe during initialization, so we do it eagerly, see
# issue #104
REQUIREMENT.parseString("x[]")
class Requirement:
"""Parse a requirement.
@@ -99,28 +32,29 @@ class Requirement:
def __init__(self, requirement_string: str) -> None:
try:
req = REQUIREMENT.parseString(requirement_string)
except ParseException as e:
raise InvalidRequirement(
f'Parse error at "{ requirement_string[e.loc : e.loc + 8]!r}": {e.msg}'
)
parsed = _parse_requirement(requirement_string)
except ParserSyntaxError as e:
raise InvalidRequirement(str(e)) from e
self.name: str = req.name
if req.url:
parsed_url = urllib.parse.urlparse(req.url)
self.name: str = parsed.name
if parsed.url:
parsed_url = urllib.parse.urlparse(parsed.url)
if parsed_url.scheme == "file":
if urllib.parse.urlunparse(parsed_url) != req.url:
if urllib.parse.urlunparse(parsed_url) != parsed.url:
raise InvalidRequirement("Invalid URL given")
elif not (parsed_url.scheme and parsed_url.netloc) or (
not parsed_url.scheme and not parsed_url.netloc
):
raise InvalidRequirement(f"Invalid URL: {req.url}")
self.url: TOptional[str] = req.url
raise InvalidRequirement(f"Invalid URL: {parsed.url}")
self.url: Optional[str] = parsed.url
else:
self.url = None
self.extras: Set[str] = set(req.extras.asList() if req.extras else [])
self.specifier: SpecifierSet = SpecifierSet(req.specifier)
self.marker: TOptional[Marker] = req.marker if req.marker else None
self.extras: Set[str] = set(parsed.extras if parsed.extras else [])
self.specifier: SpecifierSet = SpecifierSet(parsed.specifier)
self.marker: Optional[Marker] = None
if parsed.marker is not None:
self.marker = Marker.__new__(Marker)
self.marker._markers = _normalize_extra_values(parsed.marker)
def __str__(self) -> str:
parts: List[str] = [self.name]
@@ -144,3 +78,18 @@ class Requirement:
def __repr__(self) -> str:
return f"<Requirement('{self}')>"
def __hash__(self) -> int:
return hash((self.__class__.__name__, str(self)))
def __eq__(self, other: Any) -> bool:
if not isinstance(other, Requirement):
return NotImplemented
return (
self.name == other.name
and self.extras == other.extras
and self.specifier == other.specifier
and self.url == other.url
and self.marker == other.marker
)
File diff suppressed because it is too large Load Diff
+76 -14
View File
@@ -4,6 +4,7 @@
import logging
import platform
import subprocess
import sys
import sysconfig
from importlib.machinery import EXTENSION_SUFFIXES
@@ -36,7 +37,7 @@ INTERPRETER_SHORT_NAMES: Dict[str, str] = {
}
_32_BIT_INTERPRETER = sys.maxsize <= 2 ** 32
_32_BIT_INTERPRETER = sys.maxsize <= 2**32
class Tag:
@@ -90,7 +91,7 @@ class Tag:
return f"{self._interpreter}-{self._abi}-{self._platform}"
def __repr__(self) -> str:
return "<{self} @ {self_id}>".format(self=self, self_id=id(self))
return f"<{self} @ {id(self)}>"
def parse_tag(tag: str) -> FrozenSet[Tag]:
@@ -110,7 +111,7 @@ def parse_tag(tag: str) -> FrozenSet[Tag]:
def _get_config_var(name: str, warn: bool = False) -> Union[int, str, None]:
value = sysconfig.get_config_var(name)
value: Union[int, str, None] = sysconfig.get_config_var(name)
if value is None and warn:
logger.debug(
"Config variable '%s' is unset, Python ABI tag may be incorrect", name
@@ -119,7 +120,7 @@ def _get_config_var(name: str, warn: bool = False) -> Union[int, str, None]:
def _normalize_string(string: str) -> str:
return string.replace(".", "_").replace("-", "_")
return string.replace(".", "_").replace("-", "_").replace(" ", "_")
def _abi3_applies(python_version: PythonVersion) -> bool:
@@ -192,7 +193,7 @@ def cpython_tags(
if not python_version:
python_version = sys.version_info[:2]
interpreter = "cp{}".format(_version_nodot(python_version[:2]))
interpreter = f"cp{_version_nodot(python_version[:2])}"
if abis is None:
if len(python_version) > 1:
@@ -224,10 +225,45 @@ def cpython_tags(
yield Tag(interpreter, "abi3", platform_)
def _generic_abi() -> Iterator[str]:
abi = sysconfig.get_config_var("SOABI")
if abi:
yield _normalize_string(abi)
def _generic_abi() -> List[str]:
"""
Return the ABI tag based on EXT_SUFFIX.
"""
# The following are examples of `EXT_SUFFIX`.
# We want to keep the parts which are related to the ABI and remove the
# parts which are related to the platform:
# - linux: '.cpython-310-x86_64-linux-gnu.so' => cp310
# - mac: '.cpython-310-darwin.so' => cp310
# - win: '.cp310-win_amd64.pyd' => cp310
# - win: '.pyd' => cp37 (uses _cpython_abis())
# - pypy: '.pypy38-pp73-x86_64-linux-gnu.so' => pypy38_pp73
# - graalpy: '.graalpy-38-native-x86_64-darwin.dylib'
# => graalpy_38_native
ext_suffix = _get_config_var("EXT_SUFFIX", warn=True)
if not isinstance(ext_suffix, str) or ext_suffix[0] != ".":
raise SystemError("invalid sysconfig.get_config_var('EXT_SUFFIX')")
parts = ext_suffix.split(".")
if len(parts) < 3:
# CPython3.7 and earlier uses ".pyd" on Windows.
return _cpython_abis(sys.version_info[:2])
soabi = parts[1]
if soabi.startswith("cpython"):
# non-windows
abi = "cp" + soabi.split("-")[1]
elif soabi.startswith("cp"):
# windows
abi = soabi.split("-")[0]
elif soabi.startswith("pypy"):
abi = "-".join(soabi.split("-")[:2])
elif soabi.startswith("graalpy"):
abi = "-".join(soabi.split("-")[:3])
elif soabi:
# pyston, ironpython, others?
abi = soabi
else:
return []
return [_normalize_string(abi)]
def generic_tags(
@@ -251,8 +287,9 @@ def generic_tags(
interpreter = "".join([interp_name, interp_version])
if abis is None:
abis = _generic_abi()
else:
abis = list(abis)
platforms = list(platforms or platform_tags())
abis = list(abis)
if "none" not in abis:
abis.append("none")
for abi in abis:
@@ -268,11 +305,11 @@ def _py_interpreter_range(py_version: PythonVersion) -> Iterator[str]:
all previous versions of that major version.
"""
if len(py_version) > 1:
yield "py{version}".format(version=_version_nodot(py_version[:2]))
yield "py{major}".format(major=py_version[0])
yield f"py{_version_nodot(py_version[:2])}"
yield f"py{py_version[0]}"
if len(py_version) > 1:
for minor in range(py_version[1] - 1, -1, -1):
yield "py{version}".format(version=_version_nodot((py_version[0], minor)))
yield f"py{_version_nodot((py_version[0], minor))}"
def compatible_tags(
@@ -356,6 +393,22 @@ def mac_platforms(
version_str, _, cpu_arch = platform.mac_ver()
if version is None:
version = cast("MacVersion", tuple(map(int, version_str.split(".")[:2])))
if version == (10, 16):
# When built against an older macOS SDK, Python will report macOS 10.16
# instead of the real version.
version_str = subprocess.run(
[
sys.executable,
"-sS",
"-c",
"import platform; print(platform.mac_ver()[0])",
],
check=True,
env={"SYSTEM_VERSION_COMPAT": "0"},
stdout=subprocess.PIPE,
universal_newlines=True,
).stdout
version = cast("MacVersion", tuple(map(int, version_str.split(".")[:2])))
else:
version = version
if arch is None:
@@ -446,6 +499,9 @@ def platform_tags() -> Iterator[str]:
def interpreter_name() -> str:
"""
Returns the name of the running interpreter.
Some implementations have a reserved, two-letter abbreviation which will
be returned when appropriate.
"""
name = sys.implementation.name
return INTERPRETER_SHORT_NAMES.get(name) or name
@@ -481,4 +537,10 @@ def sys_tags(*, warn: bool = False) -> Iterator[Tag]:
else:
yield from generic_tags()
yield from compatible_tags()
if interp_name == "pp":
interp = "pp3"
elif interp_name == "cp":
interp = "cp" + interpreter_version(warn=warn)
else:
interp = None
yield from compatible_tags(interpreter=interp)
+8 -3
View File
@@ -35,7 +35,9 @@ def canonicalize_name(name: str) -> NormalizedName:
return cast(NormalizedName, value)
def canonicalize_version(version: Union[Version, str]) -> str:
def canonicalize_version(
version: Union[Version, str], *, strip_trailing_zero: bool = True
) -> str:
"""
This is very similar to Version.__str__, but has one subtle difference
with the way it handles the release segment.
@@ -56,8 +58,11 @@ def canonicalize_version(version: Union[Version, str]) -> str:
parts.append(f"{parsed.epoch}!")
# Release segment
# NB: This strips trailing '.0's to normalize
parts.append(re.sub(r"(\.0)+$", "", ".".join(str(x) for x in parsed.release)))
release_segment = ".".join(str(x) for x in parsed.release)
if strip_trailing_zero:
# NB: This strips trailing '.0's to normalize
release_segment = re.sub(r"(\.0)+$", "", release_segment)
parts.append(release_segment)
# Pre-release
if parsed.pre is not None:
+197 -137
View File
@@ -1,16 +1,20 @@
# This file is dual licensed under the terms of the Apache License, Version
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.
"""
.. testsetup::
from packaging.version import parse, Version
"""
import collections
import itertools
import re
import warnings
from typing import Callable, Iterator, List, Optional, SupportsInt, Tuple, Union
from typing import Any, Callable, Optional, SupportsInt, Tuple, Union
from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType
__all__ = ["parse", "Version", "LegacyVersion", "InvalidVersion", "VERSION_PATTERN"]
__all__ = ["VERSION_PATTERN", "parse", "Version", "InvalidVersion"]
InfiniteTypes = Union[InfinityType, NegativeInfinityType]
PrePostDevType = Union[InfiniteTypes, Tuple[str, int]]
@@ -29,36 +33,37 @@ LocalType = Union[
CmpKey = Tuple[
int, Tuple[int, ...], PrePostDevType, PrePostDevType, PrePostDevType, LocalType
]
LegacyCmpKey = Tuple[int, Tuple[str, ...]]
VersionComparisonMethod = Callable[
[Union[CmpKey, LegacyCmpKey], Union[CmpKey, LegacyCmpKey]], bool
]
VersionComparisonMethod = Callable[[CmpKey, CmpKey], bool]
_Version = collections.namedtuple(
"_Version", ["epoch", "release", "dev", "pre", "post", "local"]
)
def parse(version: str) -> Union["LegacyVersion", "Version"]:
def parse(version: str) -> "Version":
"""Parse the given version string.
>>> parse('1.0.dev1')
<Version('1.0.dev1')>
:param version: The version string to parse.
:raises InvalidVersion: When the version string is not a valid version.
"""
Parse the given version string and return either a :class:`Version` object
or a :class:`LegacyVersion` object depending on if the given version is
a valid PEP 440 version or a legacy version.
"""
try:
return Version(version)
except InvalidVersion:
return LegacyVersion(version)
return Version(version)
class InvalidVersion(ValueError):
"""
An invalid version was found, users should refer to PEP 440.
"""Raised when a version string is not a valid version.
>>> Version("invalid")
Traceback (most recent call last):
...
packaging.version.InvalidVersion: Invalid version: 'invalid'
"""
class _BaseVersion:
_key: Union[CmpKey, LegacyCmpKey]
_key: Tuple[Any, ...]
def __hash__(self) -> int:
return hash(self._key)
@@ -103,126 +108,9 @@ class _BaseVersion:
return self._key != other._key
class LegacyVersion(_BaseVersion):
def __init__(self, version: str) -> None:
self._version = str(version)
self._key = _legacy_cmpkey(self._version)
warnings.warn(
"Creating a LegacyVersion has been deprecated and will be "
"removed in the next major release",
DeprecationWarning,
)
def __str__(self) -> str:
return self._version
def __repr__(self) -> str:
return f"<LegacyVersion('{self}')>"
@property
def public(self) -> str:
return self._version
@property
def base_version(self) -> str:
return self._version
@property
def epoch(self) -> int:
return -1
@property
def release(self) -> None:
return None
@property
def pre(self) -> None:
return None
@property
def post(self) -> None:
return None
@property
def dev(self) -> None:
return None
@property
def local(self) -> None:
return None
@property
def is_prerelease(self) -> bool:
return False
@property
def is_postrelease(self) -> bool:
return False
@property
def is_devrelease(self) -> bool:
return False
_legacy_version_component_re = re.compile(r"(\d+ | [a-z]+ | \.| -)", re.VERBOSE)
_legacy_version_replacement_map = {
"pre": "c",
"preview": "c",
"-": "final-",
"rc": "c",
"dev": "@",
}
def _parse_version_parts(s: str) -> Iterator[str]:
for part in _legacy_version_component_re.split(s):
part = _legacy_version_replacement_map.get(part, part)
if not part or part == ".":
continue
if part[:1] in "0123456789":
# pad for numeric comparison
yield part.zfill(8)
else:
yield "*" + part
# ensure that alpha/beta/candidate are before final
yield "*final"
def _legacy_cmpkey(version: str) -> LegacyCmpKey:
# We hardcode an epoch of -1 here. A PEP 440 version can only have a epoch
# greater than or equal to 0. This will effectively put the LegacyVersion,
# which uses the defacto standard originally implemented by setuptools,
# as before all PEP 440 versions.
epoch = -1
# This scheme is taken from pkg_resources.parse_version setuptools prior to
# it's adoption of the packaging library.
parts: List[str] = []
for part in _parse_version_parts(version.lower()):
if part.startswith("*"):
# remove "-" before a prerelease tag
if part < "*final":
while parts and parts[-1] == "*final-":
parts.pop()
# remove trailing zeros from each series of numeric parts
while parts and parts[-1] == "00000000":
parts.pop()
parts.append(part)
return epoch, tuple(parts)
# Deliberately not anchored to the start and end of the string, to make it
# easier for 3rd party code to reuse
VERSION_PATTERN = r"""
_VERSION_PATTERN = r"""
v?
(?:
(?:(?P<epoch>[0-9]+)!)? # epoch
@@ -253,12 +141,56 @@ VERSION_PATTERN = r"""
(?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))? # local version
"""
VERSION_PATTERN = _VERSION_PATTERN
"""
A string containing the regular expression used to match a valid version.
The pattern is not anchored at either end, and is intended for embedding in larger
expressions (for example, matching a version number as part of a file name). The
regular expression should be compiled with the ``re.VERBOSE`` and ``re.IGNORECASE``
flags set.
:meta hide-value:
"""
class Version(_BaseVersion):
"""This class abstracts handling of a project's versions.
A :class:`Version` instance is comparison aware and can be compared and
sorted using the standard Python interfaces.
>>> v1 = Version("1.0a5")
>>> v2 = Version("1.0")
>>> v1
<Version('1.0a5')>
>>> v2
<Version('1.0')>
>>> v1 < v2
True
>>> v1 == v2
False
>>> v1 > v2
False
>>> v1 >= v2
False
>>> v1 <= v2
True
"""
_regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
_key: CmpKey
def __init__(self, version: str) -> None:
"""Initialize a Version object.
:param version:
The string representation of a version which will be parsed and normalized
before use.
:raises InvalidVersion:
If the ``version`` does not conform to PEP 440 in any way then this
exception will be raised.
"""
# Validate the version and parse it into pieces
match = self._regex.search(version)
@@ -288,9 +220,19 @@ class Version(_BaseVersion):
)
def __repr__(self) -> str:
"""A representation of the Version that shows all internal state.
>>> Version('1.0.0')
<Version('1.0.0')>
"""
return f"<Version('{self}')>"
def __str__(self) -> str:
"""A string representation of the version that can be rounded-tripped.
>>> str(Version("1.0a5"))
'1.0a5'
"""
parts = []
# Epoch
@@ -320,29 +262,80 @@ class Version(_BaseVersion):
@property
def epoch(self) -> int:
"""The epoch of the version.
>>> Version("2.0.0").epoch
0
>>> Version("1!2.0.0").epoch
1
"""
_epoch: int = self._version.epoch
return _epoch
@property
def release(self) -> Tuple[int, ...]:
"""The components of the "release" segment of the version.
>>> Version("1.2.3").release
(1, 2, 3)
>>> Version("2.0.0").release
(2, 0, 0)
>>> Version("1!2.0.0.post0").release
(2, 0, 0)
Includes trailing zeroes but not the epoch or any pre-release / development /
post-release suffixes.
"""
_release: Tuple[int, ...] = self._version.release
return _release
@property
def pre(self) -> Optional[Tuple[str, int]]:
"""The pre-release segment of the version.
>>> print(Version("1.2.3").pre)
None
>>> Version("1.2.3a1").pre
('a', 1)
>>> Version("1.2.3b1").pre
('b', 1)
>>> Version("1.2.3rc1").pre
('rc', 1)
"""
_pre: Optional[Tuple[str, int]] = self._version.pre
return _pre
@property
def post(self) -> Optional[int]:
"""The post-release number of the version.
>>> print(Version("1.2.3").post)
None
>>> Version("1.2.3.post1").post
1
"""
return self._version.post[1] if self._version.post else None
@property
def dev(self) -> Optional[int]:
"""The development number of the version.
>>> print(Version("1.2.3").dev)
None
>>> Version("1.2.3.dev1").dev
1
"""
return self._version.dev[1] if self._version.dev else None
@property
def local(self) -> Optional[str]:
"""The local version segment of the version.
>>> print(Version("1.2.3").local)
None
>>> Version("1.2.3+abc").local
'abc'
"""
if self._version.local:
return ".".join(str(x) for x in self._version.local)
else:
@@ -350,10 +343,31 @@ class Version(_BaseVersion):
@property
def public(self) -> str:
"""The public portion of the version.
>>> Version("1.2.3").public
'1.2.3'
>>> Version("1.2.3+abc").public
'1.2.3'
>>> Version("1.2.3+abc.dev1").public
'1.2.3'
"""
return str(self).split("+", 1)[0]
@property
def base_version(self) -> str:
"""The "base version" of the version.
>>> Version("1.2.3").base_version
'1.2.3'
>>> Version("1.2.3+abc").base_version
'1.2.3'
>>> Version("1!1.2.3+abc.dev1").base_version
'1!1.2.3'
The "base version" is the public version of the project without any pre or post
release markers.
"""
parts = []
# Epoch
@@ -367,26 +381,72 @@ class Version(_BaseVersion):
@property
def is_prerelease(self) -> bool:
"""Whether this version is a pre-release.
>>> Version("1.2.3").is_prerelease
False
>>> Version("1.2.3a1").is_prerelease
True
>>> Version("1.2.3b1").is_prerelease
True
>>> Version("1.2.3rc1").is_prerelease
True
>>> Version("1.2.3dev1").is_prerelease
True
"""
return self.dev is not None or self.pre is not None
@property
def is_postrelease(self) -> bool:
"""Whether this version is a post-release.
>>> Version("1.2.3").is_postrelease
False
>>> Version("1.2.3.post1").is_postrelease
True
"""
return self.post is not None
@property
def is_devrelease(self) -> bool:
"""Whether this version is a development release.
>>> Version("1.2.3").is_devrelease
False
>>> Version("1.2.3.dev1").is_devrelease
True
"""
return self.dev is not None
@property
def major(self) -> int:
"""The first item of :attr:`release` or ``0`` if unavailable.
>>> Version("1.2.3").major
1
"""
return self.release[0] if len(self.release) >= 1 else 0
@property
def minor(self) -> int:
"""The second item of :attr:`release` or ``0`` if unavailable.
>>> Version("1.2.3").minor
2
>>> Version("1").minor
0
"""
return self.release[1] if len(self.release) >= 2 else 0
@property
def micro(self) -> int:
"""The third item of :attr:`release` or ``0`` if unavailable.
>>> Version("1.2.3").micro
3
>>> Version("1").micro
0
"""
return self.release[2] if len(self.release) >= 3 else 0