CLERC/Reskreen
6
0
Fork 0
Code Issues 5 Pull Requests Actions Packages Projects 1 Releases 1 Wiki Activity

Change venv

Browse Source
This commit is contained in:
Ambulance Clerc
2023-05-31 08:31:22 +02:00
parent fb6f579089
commit fdbb52c96f
466 changed files with 25899 additions and 64721 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
venv/Lib/site-packages/pip/_vendor/__init__.py
View File

@@ -58,13 +58,11 @@ if DEBUNDLED:
sys.path[:] = glob.glob(os.path.join(WHEEL_DIR, "*.whl")) + sys.path
# Actually alias all of our vendored dependencies.
vendored("appdirs")
vendored("cachecontrol")
vendored("certifi")
vendored("colorama")
vendored("distlib")
vendored("distro")
vendored("html5lib")
vendored("six")
vendored("six.moves")
vendored("six.moves.urllib")
@@ -74,6 +72,7 @@ if DEBUNDLED:
vendored("packaging.specifiers")
vendored("pep517")
vendored("pkg_resources")
vendored("platformdirs")
vendored("progress")
vendored("requests")
vendored("requests.exceptions")
@@ -106,6 +105,16 @@ if DEBUNDLED:
vendored("requests.packages.urllib3.util.timeout")
vendored("requests.packages.urllib3.util.url")
vendored("resolvelib")
vendored("rich")
vendored("rich.console")
vendored("rich.highlighter")
vendored("rich.logging")
vendored("rich.markup")
vendored("rich.progress")
vendored("rich.segment")
vendored("rich.style")
vendored("rich.text")
vendored("rich.traceback")
vendored("tenacity")
vendored("tomli")
vendored("urllib3")

633
venv/Lib/site-packages/pip/_vendor/appdirs.py
View File

@@ -1,633 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright (c) 2005-2010 ActiveState Software Inc.
# Copyright (c) 2013 Eddy Petrișor
"""Utilities for determining application-specific dirs.
See <http://github.com/ActiveState/appdirs> for details and usage.
"""
# Dev Notes:
# - MSDN on where to store app data files:
# http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120
# - Mac OS X: http://developer.apple.com/documentation/MacOSX/Conceptual/BPFileSystem/index.html
# - XDG spec for Un*x: http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html
__version__ = "1.4.4"
__version_info__ = tuple(int(segment) for segment in __version__.split("."))
import sys
import os
PY3 = sys.version_info[0] == 3
if PY3:
unicode = str
if sys.platform.startswith('java'):
import platform
os_name = platform.java_ver()[3][0]
if os_name.startswith('Windows'): # "Windows XP", "Windows 7", etc.
system = 'win32'
elif os_name.startswith('Mac'): # "Mac OS X", etc.
system = 'darwin'
else: # "Linux", "SunOS", "FreeBSD", etc.
# Setting this to "linux2" is not ideal, but only Windows or Mac
# are actually checked for and the rest of the module expects
# *sys.platform* style strings.
system = 'linux2'
elif sys.platform == 'cli' and os.name == 'nt':
# Detect Windows in IronPython to match pip._internal.utils.compat.WINDOWS
# Discussion: <https://github.com/pypa/pip/pull/7501>
system = 'win32'
else:
system = sys.platform
def user_data_dir(appname=None, appauthor=None, version=None, roaming=False):
r"""Return full path to the user-specific data dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"roaming" (boolean, default False) can be set True to use the Windows
roaming appdata directory. That means that for users on a Windows
network setup for roaming profiles, this user data will be
sync'd on login. See
<http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
for a discussion of issues.
Typical user data directories are:
Mac OS X: ~/Library/Application Support/<AppName> # or ~/.config/<AppName>, if the other does not exist
Unix: ~/.local/share/<AppName> # or in $XDG_DATA_HOME, if defined
Win XP (not roaming): C:\Documents and Settings\<username>\Application Data\<AppAuthor>\<AppName>
Win XP (roaming): C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>
Win 7 (not roaming): C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>
Win 7 (roaming): C:\Users\<username>\AppData\Roaming\<AppAuthor>\<AppName>
For Unix, we follow the XDG spec and support $XDG_DATA_HOME.
That means, by default "~/.local/share/<AppName>".
"""
if system == "win32":
if appauthor is None:
appauthor = appname
const = roaming and "CSIDL_APPDATA" or "CSIDL_LOCAL_APPDATA"
path = os.path.normpath(_get_win_folder(const))
if appname:
if appauthor is not False:
path = os.path.join(path, appauthor, appname)
else:
path = os.path.join(path, appname)
elif system == 'darwin':
path = os.path.expanduser('~/Library/Application Support/')
if appname:
path = os.path.join(path, appname)
else:
path = os.getenv('XDG_DATA_HOME', os.path.expanduser("~/.local/share"))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
def site_data_dir(appname=None, appauthor=None, version=None, multipath=False):
r"""Return full path to the user-shared data dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"multipath" is an optional parameter only applicable to *nix
which indicates that the entire list of data dirs should be
returned. By default, the first item from XDG_DATA_DIRS is
returned, or '/usr/local/share/<AppName>',
if XDG_DATA_DIRS is not set
Typical site data directories are:
Mac OS X: /Library/Application Support/<AppName>
Unix: /usr/local/share/<AppName> or /usr/share/<AppName>
Win XP: C:\Documents and Settings\All Users\Application Data\<AppAuthor>\<AppName>
Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.)
Win 7: C:\ProgramData\<AppAuthor>\<AppName> # Hidden, but writeable on Win 7.
For Unix, this is using the $XDG_DATA_DIRS[0] default.
WARNING: Do not use this on Windows. See the Vista-Fail note above for why.
"""
if system == "win32":
if appauthor is None:
appauthor = appname
path = os.path.normpath(_get_win_folder("CSIDL_COMMON_APPDATA"))
if appname:
if appauthor is not False:
path = os.path.join(path, appauthor, appname)
else:
path = os.path.join(path, appname)
elif system == 'darwin':
path = os.path.expanduser('/Library/Application Support')
if appname:
path = os.path.join(path, appname)
else:
# XDG default for $XDG_DATA_DIRS
# only first, if multipath is False
path = os.getenv('XDG_DATA_DIRS',
os.pathsep.join(['/usr/local/share', '/usr/share']))
pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)]
if appname:
if version:
appname = os.path.join(appname, version)
pathlist = [os.path.join(x, appname) for x in pathlist]
if multipath:
path = os.pathsep.join(pathlist)
else:
path = pathlist[0]
return path
if appname and version:
path = os.path.join(path, version)
return path
def user_config_dir(appname=None, appauthor=None, version=None, roaming=False):
r"""Return full path to the user-specific config dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"roaming" (boolean, default False) can be set True to use the Windows
roaming appdata directory. That means that for users on a Windows
network setup for roaming profiles, this user data will be
sync'd on login. See
<http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
for a discussion of issues.
Typical user config directories are:
Mac OS X: same as user_data_dir
Unix: ~/.config/<AppName> # or in $XDG_CONFIG_HOME, if defined
Win *: same as user_data_dir
For Unix, we follow the XDG spec and support $XDG_CONFIG_HOME.
That means, by default "~/.config/<AppName>".
"""
if system in ["win32", "darwin"]:
path = user_data_dir(appname, appauthor, None, roaming)
else:
path = os.getenv('XDG_CONFIG_HOME', os.path.expanduser("~/.config"))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
# for the discussion regarding site_config_dir locations
# see <https://github.com/pypa/pip/issues/1733>
def site_config_dir(appname=None, appauthor=None, version=None, multipath=False):
r"""Return full path to the user-shared data dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"multipath" is an optional parameter only applicable to *nix
which indicates that the entire list of config dirs should be
returned. By default, the first item from XDG_CONFIG_DIRS is
returned, or '/etc/xdg/<AppName>', if XDG_CONFIG_DIRS is not set
Typical site config directories are:
Mac OS X: same as site_data_dir
Unix: /etc/xdg/<AppName> or $XDG_CONFIG_DIRS[i]/<AppName> for each value in
$XDG_CONFIG_DIRS
Win *: same as site_data_dir
Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.)
For Unix, this is using the $XDG_CONFIG_DIRS[0] default, if multipath=False
WARNING: Do not use this on Windows. See the Vista-Fail note above for why.
"""
if system in ["win32", "darwin"]:
path = site_data_dir(appname, appauthor)
if appname and version:
path = os.path.join(path, version)
else:
# XDG default for $XDG_CONFIG_DIRS (missing or empty)
# see <https://github.com/pypa/pip/pull/7501#discussion_r360624829>
# only first, if multipath is False
path = os.getenv('XDG_CONFIG_DIRS') or '/etc/xdg'
pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep) if x]
if appname:
if version:
appname = os.path.join(appname, version)
pathlist = [os.path.join(x, appname) for x in pathlist]
if multipath:
path = os.pathsep.join(pathlist)
else:
path = pathlist[0]
return path
def user_cache_dir(appname=None, appauthor=None, version=None, opinion=True):
r"""Return full path to the user-specific cache dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"opinion" (boolean) can be False to disable the appending of
"Cache" to the base app data dir for Windows. See
discussion below.
Typical user cache directories are:
Mac OS X: ~/Library/Caches/<AppName>
Unix: ~/.cache/<AppName> (XDG default)
Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Cache
Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Cache
On Windows the only suggestion in the MSDN docs is that local settings go in
the `CSIDL_LOCAL_APPDATA` directory. This is identical to the non-roaming
app data dir (the default returned by `user_data_dir` above). Apps typically
put cache data somewhere *under* the given dir here. Some examples:
...\Mozilla\Firefox\Profiles\<ProfileName>\Cache
...\Acme\SuperApp\Cache\1.0
OPINION: This function appends "Cache" to the `CSIDL_LOCAL_APPDATA` value.
This can be disabled with the `opinion=False` option.
"""
if system == "win32":
if appauthor is None:
appauthor = appname
path = os.path.normpath(_get_win_folder("CSIDL_LOCAL_APPDATA"))
# When using Python 2, return paths as bytes on Windows like we do on
# other operating systems. See helper function docs for more details.
if not PY3 and isinstance(path, unicode):
path = _win_path_to_bytes(path)
if appname:
if appauthor is not False:
path = os.path.join(path, appauthor, appname)
else:
path = os.path.join(path, appname)
if opinion:
path = os.path.join(path, "Cache")
elif system == 'darwin':
path = os.path.expanduser('~/Library/Caches')
if appname:
path = os.path.join(path, appname)
else:
path = os.getenv('XDG_CACHE_HOME', os.path.expanduser('~/.cache'))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
def user_state_dir(appname=None, appauthor=None, version=None, roaming=False):
r"""Return full path to the user-specific state dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"roaming" (boolean, default False) can be set True to use the Windows
roaming appdata directory. That means that for users on a Windows
network setup for roaming profiles, this user data will be
sync'd on login. See
<http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
for a discussion of issues.
Typical user state directories are:
Mac OS X: same as user_data_dir
Unix: ~/.local/state/<AppName> # or in $XDG_STATE_HOME, if defined
Win *: same as user_data_dir
For Unix, we follow this Debian proposal <https://wiki.debian.org/XDGBaseDirectorySpecification#state>
to extend the XDG spec and support $XDG_STATE_HOME.
That means, by default "~/.local/state/<AppName>".
"""
if system in ["win32", "darwin"]:
path = user_data_dir(appname, appauthor, None, roaming)
else:
path = os.getenv('XDG_STATE_HOME', os.path.expanduser("~/.local/state"))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
def user_log_dir(appname=None, appauthor=None, version=None, opinion=True):
r"""Return full path to the user-specific log dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"opinion" (boolean) can be False to disable the appending of
"Logs" to the base app data dir for Windows, and "log" to the
base cache dir for Unix. See discussion below.
Typical user log directories are:
Mac OS X: ~/Library/Logs/<AppName>
Unix: ~/.cache/<AppName>/log # or under $XDG_CACHE_HOME if defined
Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Logs
Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Logs
On Windows the only suggestion in the MSDN docs is that local settings
go in the `CSIDL_LOCAL_APPDATA` directory. (Note: I'm interested in
examples of what some windows apps use for a logs dir.)
OPINION: This function appends "Logs" to the `CSIDL_LOCAL_APPDATA`
value for Windows and appends "log" to the user cache dir for Unix.
This can be disabled with the `opinion=False` option.
"""
if system == "darwin":
path = os.path.join(
os.path.expanduser('~/Library/Logs'),
appname)
elif system == "win32":
path = user_data_dir(appname, appauthor, version)
version = False
if opinion:
path = os.path.join(path, "Logs")
else:
path = user_cache_dir(appname, appauthor, version)
version = False
if opinion:
path = os.path.join(path, "log")
if appname and version:
path = os.path.join(path, version)
return path
class AppDirs(object):
"""Convenience wrapper for getting application dirs."""
def __init__(self, appname=None, appauthor=None, version=None,
roaming=False, multipath=False):
self.appname = appname
self.appauthor = appauthor
self.version = version
self.roaming = roaming
self.multipath = multipath
@property
def user_data_dir(self):
return user_data_dir(self.appname, self.appauthor,
version=self.version, roaming=self.roaming)
@property
def site_data_dir(self):
return site_data_dir(self.appname, self.appauthor,
version=self.version, multipath=self.multipath)
@property
def user_config_dir(self):
return user_config_dir(self.appname, self.appauthor,
version=self.version, roaming=self.roaming)
@property
def site_config_dir(self):
return site_config_dir(self.appname, self.appauthor,
version=self.version, multipath=self.multipath)
@property
def user_cache_dir(self):
return user_cache_dir(self.appname, self.appauthor,
version=self.version)
@property
def user_state_dir(self):
return user_state_dir(self.appname, self.appauthor,
version=self.version)
@property
def user_log_dir(self):
return user_log_dir(self.appname, self.appauthor,
version=self.version)
#---- internal support stuff
def _get_win_folder_from_registry(csidl_name):
"""This is a fallback technique at best. I'm not sure if using the
registry for this guarantees us the correct answer for all CSIDL_*
names.
"""
if PY3:
import winreg as _winreg
else:
import _winreg
shell_folder_name = {
"CSIDL_APPDATA": "AppData",
"CSIDL_COMMON_APPDATA": "Common AppData",
"CSIDL_LOCAL_APPDATA": "Local AppData",
}[csidl_name]
key = _winreg.OpenKey(
_winreg.HKEY_CURRENT_USER,
r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders"
)
dir, type = _winreg.QueryValueEx(key, shell_folder_name)
return dir
def _get_win_folder_with_pywin32(csidl_name):
from win32com.shell import shellcon, shell
dir = shell.SHGetFolderPath(0, getattr(shellcon, csidl_name), 0, 0)
# Try to make this a unicode path because SHGetFolderPath does
# not return unicode strings when there is unicode data in the
# path.
try:
dir = unicode(dir)
# Downgrade to short path name if have highbit chars. See
# <http://bugs.activestate.com/show_bug.cgi?id=85099>.
has_high_char = False
for c in dir:
if ord(c) > 255:
has_high_char = True
break
if has_high_char:
try:
import win32api
dir = win32api.GetShortPathName(dir)
except ImportError:
pass
except UnicodeError:
pass
return dir
def _get_win_folder_with_ctypes(csidl_name):
import ctypes
csidl_const = {
"CSIDL_APPDATA": 26,
"CSIDL_COMMON_APPDATA": 35,
"CSIDL_LOCAL_APPDATA": 28,
}[csidl_name]
buf = ctypes.create_unicode_buffer(1024)
ctypes.windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf)
# Downgrade to short path name if have highbit chars. See
# <http://bugs.activestate.com/show_bug.cgi?id=85099>.
has_high_char = False
for c in buf:
if ord(c) > 255:
has_high_char = True
break
if has_high_char:
buf2 = ctypes.create_unicode_buffer(1024)
if ctypes.windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024):
buf = buf2
return buf.value
def _get_win_folder_with_jna(csidl_name):
import array
from com.sun import jna
from com.sun.jna.platform import win32
buf_size = win32.WinDef.MAX_PATH * 2
buf = array.zeros('c', buf_size)
shell = win32.Shell32.INSTANCE
shell.SHGetFolderPath(None, getattr(win32.ShlObj, csidl_name), None, win32.ShlObj.SHGFP_TYPE_CURRENT, buf)
dir = jna.Native.toString(buf.tostring()).rstrip("\0")
# Downgrade to short path name if have highbit chars. See
# <http://bugs.activestate.com/show_bug.cgi?id=85099>.
has_high_char = False
for c in dir:
if ord(c) > 255:
has_high_char = True
break
if has_high_char:
buf = array.zeros('c', buf_size)
kernel = win32.Kernel32.INSTANCE
if kernel.GetShortPathName(dir, buf, buf_size):
dir = jna.Native.toString(buf.tostring()).rstrip("\0")
return dir
if system == "win32":
try:
from ctypes import windll
_get_win_folder = _get_win_folder_with_ctypes
except ImportError:
try:
import com.sun.jna
_get_win_folder = _get_win_folder_with_jna
except ImportError:
_get_win_folder = _get_win_folder_from_registry
def _win_path_to_bytes(path):
"""Encode Windows paths to bytes. Only used on Python 2.
Motivation is to be consistent with other operating systems where paths
are also returned as bytes. This avoids problems mixing bytes and Unicode
elsewhere in the codebase. For more details and discussion see
<https://github.com/pypa/pip/issues/3463>.
If encoding using ASCII and MBCS fails, return the original Unicode path.
"""
for encoding in ('ASCII', 'MBCS'):
try:
return path.encode(encoding)
except (UnicodeEncodeError, LookupError):
pass
return path
#---- self test code
if __name__ == "__main__":
appname = "MyApp"
appauthor = "MyCompany"
props = ("user_data_dir",
"user_config_dir",
"user_cache_dir",
"user_state_dir",
"user_log_dir",
"site_data_dir",
"site_config_dir")
print("-- app dirs %s --" % __version__)
print("-- app dirs (with optional 'version')")
dirs = AppDirs(appname, appauthor, version="1.0")
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
print("\n-- app dirs (without optional 'version')")
dirs = AppDirs(appname, appauthor)
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
print("\n-- app dirs (without optional 'appauthor')")
dirs = AppDirs(appname)
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
print("\n-- app dirs (with disabled 'appauthor')")
dirs = AppDirs(appname, appauthor=False)
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))

9
venv/Lib/site-packages/pip/_vendor/cachecontrol/__init__.py
View File

@@ -1,11 +1,18 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
"""CacheControl import Interface.
Make it easy to import from cachecontrol without long namespaces.
"""
__author__ = "Eric Larson"
__email__ = "eric@ionrock.org"
__version__ = "0.12.6"
__version__ = "0.12.11"
from .wrapper import CacheControl
from .adapter import CacheControlAdapter
from .controller import CacheController
import logging
logging.getLogger(__name__).addHandler(logging.NullHandler())

4
venv/Lib/site-packages/pip/_vendor/cachecontrol/_cmd.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
import logging
from pip._vendor import requests

10
venv/Lib/site-packages/pip/_vendor/cachecontrol/adapter.py
View File

@@ -1,16 +1,20 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
import types
import functools
import zlib
from pip._vendor.requests.adapters import HTTPAdapter
from .controller import CacheController
from .controller import CacheController, PERMANENT_REDIRECT_STATUSES
from .cache import DictCache
from .filewrapper import CallbackFileWrapper
class CacheControlAdapter(HTTPAdapter):
invalidating_methods = {"PUT", "DELETE"}
invalidating_methods = {"PUT", "PATCH", "DELETE"}
def __init__(
self,
@@ -93,7 +97,7 @@ class CacheControlAdapter(HTTPAdapter):
response = cached_response
# We always cache the 301 responses
elif response.status == 301:
elif int(response.status) in PERMANENT_REDIRECT_STATUSES:
self.controller.cache_response(request, response)
else:
# Wrap the response file with a wrapper that will cache the

30
venv/Lib/site-packages/pip/_vendor/cachecontrol/cache.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
"""
The cache object API for implementing caches. The default is a thread
safe in-memory dictionary.
@@ -10,7 +14,7 @@ class BaseCache(object):
def get(self, key):
raise NotImplementedError()
def set(self, key, value):
def set(self, key, value, expires=None):
raise NotImplementedError()
def delete(self, key):
@@ -29,7 +33,7 @@ class DictCache(BaseCache):
def get(self, key):
return self.data.get(key, None)
def set(self, key, value):
def set(self, key, value, expires=None):
with self.lock:
self.data.update({key: value})
@@ -37,3 +41,25 @@ class DictCache(BaseCache):
with self.lock:
if key in self.data:
self.data.pop(key)
class SeparateBodyBaseCache(BaseCache):
"""
In this variant, the body is not stored mixed in with the metadata, but is
passed in (as a bytes-like object) in a separate call to ``set_body()``.
That is, the expected interaction pattern is::
cache.set(key, serialized_metadata)
cache.set_body(key)
Similarly, the body should be loaded separately via ``get_body()``.
"""
def set_body(self, key, body):
raise NotImplementedError()
def get_body(self, key):
"""
Return the body as file-like object.
"""
raise NotImplementedError()

11
venv/Lib/site-packages/pip/_vendor/cachecontrol/caches/__init__.py
View File

@@ -1,2 +1,9 @@
from .file_cache import FileCache # noqa
from .redis_cache import RedisCache # noqa
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
from .file_cache import FileCache, SeparateBodyFileCache
from .redis_cache import RedisCache
__all__ = ["FileCache", "SeparateBodyFileCache", "RedisCache"]

58
venv/Lib/site-packages/pip/_vendor/cachecontrol/caches/file_cache.py
View File

@@ -1,8 +1,12 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
import hashlib
import os
from textwrap import dedent
from ..cache import BaseCache
from ..cache import BaseCache, SeparateBodyBaseCache
from ..controller import CacheController
try:
@@ -53,7 +57,8 @@ def _secure_open_write(filename, fmode):
raise
class FileCache(BaseCache):
class _FileCacheMixin:
"""Shared implementation for both FileCache variants."""
def __init__(
self,
@@ -114,22 +119,27 @@ class FileCache(BaseCache):
except FileNotFoundError:
return None
def set(self, key, value):
def set(self, key, value, expires=None):
name = self._fn(key)
self._write(name, value)
def _write(self, path, data: bytes):
"""
Safely write the data to the given path.
"""
# Make sure the directory exists
try:
os.makedirs(os.path.dirname(name), self.dirmode)
os.makedirs(os.path.dirname(path), self.dirmode)
except (IOError, OSError):
pass
with self.lock_class(name) as lock:
with self.lock_class(path) as lock:
# Write our actual file
with _secure_open_write(lock.path, self.filemode) as fh:
fh.write(value)
fh.write(data)
def delete(self, key):
name = self._fn(key)
def _delete(self, key, suffix):
name = self._fn(key) + suffix
if not self.forever:
try:
os.remove(name)
@@ -137,6 +147,38 @@ class FileCache(BaseCache):
pass
class FileCache(_FileCacheMixin, BaseCache):
"""
Traditional FileCache: body is stored in memory, so not suitable for large
downloads.
"""
def delete(self, key):
self._delete(key, "")
class SeparateBodyFileCache(_FileCacheMixin, SeparateBodyBaseCache):
"""
Memory-efficient FileCache: body is stored in a separate file, reducing
peak memory usage.
"""
def get_body(self, key):
name = self._fn(key) + ".body"
try:
return open(name, "rb")
except FileNotFoundError:
return None
def set_body(self, key, body):
name = self._fn(key) + ".body"
self._write(name, body)
def delete(self, key):
self._delete(key, "")
self._delete(key, ".body")
def url_to_file_path(url, filecache):
"""Return the file cache path based on the URL.

8
venv/Lib/site-packages/pip/_vendor/cachecontrol/caches/redis_cache.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
from __future__ import division
from datetime import datetime
@@ -15,9 +19,11 @@ class RedisCache(BaseCache):
def set(self, key, value, expires=None):
if not expires:
self.conn.set(key, value)
else:
elif isinstance(expires, datetime):
expires = expires - datetime.utcnow()
self.conn.setex(key, int(expires.total_seconds()), value)
else:
self.conn.setex(key, expires, value)
def delete(self, key):
self.conn.delete(key)

5
venv/Lib/site-packages/pip/_vendor/cachecontrol/compat.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
try:
from urllib.parse import urljoin
except ImportError:
@@ -9,7 +13,6 @@ try:
except ImportError:
import pickle
# Handle the case where the requests module has been patched to not have
# urllib3 bundled as part of its source.
try:

113
venv/Lib/site-packages/pip/_vendor/cachecontrol/controller.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
"""
The httplib2 algorithms ported for use with requests.
"""
@@ -9,7 +13,7 @@ from email.utils import parsedate_tz
from pip._vendor.requests.structures import CaseInsensitiveDict
from .cache import DictCache
from .cache import DictCache, SeparateBodyBaseCache
from .serialize import Serializer
@@ -17,19 +21,20 @@ logger = logging.getLogger(__name__)
URI = re.compile(r"^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?")
PERMANENT_REDIRECT_STATUSES = (301, 308)
def parse_uri(uri):
"""Parses a URI using the regex given in Appendix B of RFC 3986.
(scheme, authority, path, query, fragment) = parse_uri(uri)
(scheme, authority, path, query, fragment) = parse_uri(uri)
"""
groups = URI.match(uri).groups()
return (groups[1], groups[3], groups[4], groups[6], groups[8])
class CacheController(object):
"""An interface to see if request should cached or not.
"""
"""An interface to see if request should cached or not."""
def __init__(
self, cache=None, cache_etags=True, serializer=None, status_codes=None
@@ -37,7 +42,7 @@ class CacheController(object):
self.cache = DictCache() if cache is None else cache
self.cache_etags = cache_etags
self.serializer = serializer or Serializer()
self.cacheable_status_codes = status_codes or (200, 203, 300, 301)
self.cacheable_status_codes = status_codes or (200, 203, 300, 301, 308)
@classmethod
def _urlnorm(cls, uri):
@@ -141,23 +146,29 @@ class CacheController(object):
logger.debug("No cache entry available")
return False
if isinstance(self.cache, SeparateBodyBaseCache):
body_file = self.cache.get_body(cache_url)
else:
body_file = None
# Check whether it can be deserialized
resp = self.serializer.loads(request, cache_data)
resp = self.serializer.loads(request, cache_data, body_file)
if not resp:
logger.warning("Cache entry deserialization failed, entry ignored")
return False
# If we have a cached 301, return it immediately. We don't
# need to test our response for other headers b/c it is
# If we have a cached permanent redirect, return it immediately. We
# don't need to test our response for other headers b/c it is
# intrinsically "cacheable" as it is Permanent.
#
# See:
# https://tools.ietf.org/html/rfc7231#section-6.4.2
#
# Client can try to refresh the value by repeating the request
# with cache busting headers as usual (ie no-cache).
if resp.status == 301:
if int(resp.status) in PERMANENT_REDIRECT_STATUSES:
msg = (
'Returning cached "301 Moved Permanently" response '
"Returning cached permanent redirect response "
"(ignoring date and etag information)"
)
logger.debug(msg)
@@ -244,6 +255,26 @@ class CacheController(object):
return new_headers
def _cache_set(self, cache_url, request, response, body=None, expires_time=None):
"""
Store the data in the cache.
"""
if isinstance(self.cache, SeparateBodyBaseCache):
# We pass in the body separately; just put a placeholder empty
# string in the metadata.
self.cache.set(
cache_url,
self.serializer.dumps(request, response, b""),
expires=expires_time,
)
self.cache.set_body(cache_url, body)
else:
self.cache.set(
cache_url,
self.serializer.dumps(request, response, body),
expires=expires_time,
)
def cache_response(self, request, response, body=None, status_codes=None):
"""
Algorithm for caching requests.
@@ -261,6 +292,11 @@ class CacheController(object):
response_headers = CaseInsensitiveDict(response.headers)
if "date" in response_headers:
date = calendar.timegm(parsedate_tz(response_headers["date"]))
else:
date = 0
# If we've been given a body, our response has a Content-Length, that
# Content-Length is valid then we can check to see if the body we've
# been given matches the expected size, and if it doesn't we'll just
@@ -304,35 +340,62 @@ class CacheController(object):
# If we've been given an etag, then keep the response
if self.cache_etags and "etag" in response_headers:
logger.debug("Caching due to etag")
self.cache.set(
cache_url, self.serializer.dumps(request, response, body=body)
)
expires_time = 0
if response_headers.get("expires"):
expires = parsedate_tz(response_headers["expires"])
if expires is not None:
expires_time = calendar.timegm(expires) - date
# Add to the cache any 301s. We do this before looking that
# the Date headers.
elif response.status == 301:
logger.debug("Caching permanant redirect")
self.cache.set(cache_url, self.serializer.dumps(request, response))
expires_time = max(expires_time, 14 * 86400)
logger.debug("etag object cached for {0} seconds".format(expires_time))
logger.debug("Caching due to etag")
self._cache_set(cache_url, request, response, body, expires_time)
# Add to the cache any permanent redirects. We do this before looking
# that the Date headers.
elif int(response.status) in PERMANENT_REDIRECT_STATUSES:
logger.debug("Caching permanent redirect")
self._cache_set(cache_url, request, response, b"")
# Add to the cache if the response headers demand it. If there
# is no date header then we can't do anything about expiring
# the cache.
elif "date" in response_headers:
date = calendar.timegm(parsedate_tz(response_headers["date"]))
# cache when there is a max-age > 0
if "max-age" in cc and cc["max-age"] > 0:
logger.debug("Caching b/c date exists and max-age > 0")
self.cache.set(
cache_url, self.serializer.dumps(request, response, body=body)
expires_time = cc["max-age"]
self._cache_set(
cache_url,
request,
response,
body,
expires_time,
)
# If the request can expire, it means we should cache it
# in the meantime.
elif "expires" in response_headers:
if response_headers["expires"]:
logger.debug("Caching b/c of expires header")
self.cache.set(
cache_url, self.serializer.dumps(request, response, body=body)
expires = parsedate_tz(response_headers["expires"])
if expires is not None:
expires_time = calendar.timegm(expires) - date
else:
expires_time = None
logger.debug(
"Caching b/c of expires header. expires in {0} seconds".format(
expires_time
)
)
self._cache_set(
cache_url,
request,
response,
body,
expires_time,
)
def update_cached_response(self, request, response):
@@ -371,6 +434,6 @@ class CacheController(object):
cached_response.status = 200
# update our cache
self.cache.set(cache_url, self.serializer.dumps(request, cached_response))
self._cache_set(cache_url, request, cached_response)
return cached_response

39
venv/Lib/site-packages/pip/_vendor/cachecontrol/filewrapper.py
View File

@@ -1,4 +1,9 @@
from io import BytesIO
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
from tempfile import NamedTemporaryFile
import mmap
class CallbackFileWrapper(object):
@@ -11,10 +16,17 @@ class CallbackFileWrapper(object):
This class uses members with a double underscore (__) leading prefix so as
not to accidentally shadow an attribute.
The data is stored in a temporary file until it is all available. As long
as the temporary files directory is disk-based (sometimes it's a
memory-backed-``tmpfs`` on Linux), data will be unloaded to disk if memory
pressure is high. For small files the disk usually won't be used at all,
it'll all be in the filesystem memory cache, so there should be no
performance impact.
"""
def __init__(self, fp, callback):
self.__buf = BytesIO()
self.__buf = NamedTemporaryFile("rb+", delete=True)
self.__fp = fp
self.__callback = callback
@@ -49,7 +61,19 @@ class CallbackFileWrapper(object):
def _close(self):
if self.__callback:
self.__callback(self.__buf.getvalue())
if self.__buf.tell() == 0:
# Empty file:
result = b""
else:
# Return the data without actually loading it into memory,
# relying on Python's buffer API and mmap(). mmap() just gives
# a view directly into the filesystem's memory cache, so it
# doesn't result in duplicate memory use.
self.__buf.seek(0, 0)
result = memoryview(
mmap.mmap(self.__buf.fileno(), 0, access=mmap.ACCESS_READ)
)
self.__callback(result)
# We assign this to None here, because otherwise we can get into
# really tricky problems where the CPython interpreter dead locks
@@ -58,9 +82,16 @@ class CallbackFileWrapper(object):
# and allows the garbage collector to do it's thing normally.
self.__callback = None
# Closing the temporary file releases memory and frees disk space.
# Important when caching big files.
self.__buf.close()
def read(self, amt=None):
data = self.__fp.read(amt)
self.__buf.write(data)
if data:
# We may be dealing with b'', a sign that things are over:
# it's passed e.g. after we've already closed self.__buf.
self.__buf.write(data)
if self.__is_fp_closed():
self._close()

4
venv/Lib/site-packages/pip/_vendor/cachecontrol/heuristics.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
import calendar
import time

52
venv/Lib/site-packages/pip/_vendor/cachecontrol/serialize.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
import base64
import io
import json
@@ -17,24 +21,18 @@ def _b64_decode_str(s):
return _b64_decode_bytes(s).decode("utf8")
class Serializer(object):
_default_body_read = object()
class Serializer(object):
def dumps(self, request, response, body=None):
response_headers = CaseInsensitiveDict(response.headers)
if body is None:
# When a body isn't passed in, we'll read the response. We
# also update the response with a new file handler to be
# sure it acts as though it was never read.
body = response.read(decode_content=False)
# NOTE: 99% sure this is dead code. I'm only leaving it
# here b/c I don't have a test yet to prove
# it. Basically, before using
# `cachecontrol.filewrapper.CallbackFileWrapper`,
# this made an effort to reset the file handle. The
# `CallbackFileWrapper` short circuits this code by
# setting the body as the content is consumed, the
# result being a `body` argument is *always* passed
# into cache_response, and in turn,
# `Serializer.dump`.
response._fp = io.BytesIO(body)
# NOTE: This is all a bit weird, but it's really important that on
@@ -46,7 +44,7 @@ class Serializer(object):
# enough to have msgpack know the difference.
data = {
u"response": {
u"body": body,
u"body": body, # Empty bytestring if body is stored separately
u"headers": dict(
(text_type(k), text_type(v)) for k, v in response.headers.items()
),
@@ -71,7 +69,7 @@ class Serializer(object):
return b",".join([b"cc=4", msgpack.dumps(data, use_bin_type=True)])
def loads(self, request, data):
def loads(self, request, data, body_file=None):
# Short circuit if we've been given an empty set of data
if not data:
return
@@ -94,14 +92,14 @@ class Serializer(object):
# Dispatch to the actual load method for the given version
try:
return getattr(self, "_loads_v{}".format(ver))(request, data)
return getattr(self, "_loads_v{}".format(ver))(request, data, body_file)
except AttributeError:
# This is a version we don't have a loads function for, so we'll
# just treat it as a miss and return None
return
def prepare_response(self, request, cached):
def prepare_response(self, request, cached, body_file=None):
"""Verify our vary headers match and construct a real urllib3
HTTPResponse object.
"""
@@ -127,7 +125,10 @@ class Serializer(object):
cached["response"]["headers"] = headers
try:
body = io.BytesIO(body_raw)
if body_file is None:
body = io.BytesIO(body_raw)
else:
body = body_file
except TypeError:
# This can happen if cachecontrol serialized to v1 format (pickle)
# using Python 2. A Python 2 str(byte string) will be unpickled as
@@ -139,21 +140,22 @@ class Serializer(object):
return HTTPResponse(body=body, preload_content=False, **cached["response"])
def _loads_v0(self, request, data):
def _loads_v0(self, request, data, body_file=None):
# The original legacy cache data. This doesn't contain enough
# information to construct everything we need, so we'll treat this as
# a miss.
return
def _loads_v1(self, request, data):
def _loads_v1(self, request, data, body_file=None):
try:
cached = pickle.loads(data)
except ValueError:
return
return self.prepare_response(request, cached)
return self.prepare_response(request, cached, body_file)
def _loads_v2(self, request, data):
def _loads_v2(self, request, data, body_file=None):
assert body_file is None
try:
cached = json.loads(zlib.decompress(data).decode("utf8"))
except (ValueError, zlib.error):
@@ -171,18 +173,18 @@ class Serializer(object):
for k, v in cached["vary"].items()
)
return self.prepare_response(request, cached)
return self.prepare_response(request, cached, body_file)
def _loads_v3(self, request, data):
def _loads_v3(self, request, data, body_file):
# Due to Python 2 encoding issues, it's impossible to know for sure
# exactly how to load v3 entries, thus we'll treat these as a miss so
# that they get rewritten out as v4 entries.
return
def _loads_v4(self, request, data):
def _loads_v4(self, request, data, body_file=None):
try:
cached = msgpack.loads(data, raw=False)
except ValueError:
return
return self.prepare_response(request, cached)
return self.prepare_response(request, cached, body_file)

4
venv/Lib/site-packages/pip/_vendor/cachecontrol/wrapper.py
View File

@@ -1,3 +1,7 @@
# SPDX-FileCopyrightText: 2015 Eric Larson
#
# SPDX-License-Identifier: Apache-2.0
from .adapter import CacheControlAdapter
from .cache import DictCache

3
venv/Lib/site-packages/pip/_vendor/certifi/__init__.py
View File

@@ -1,3 +1,4 @@
from .core import contents, where
__version__ = "2021.05.30"
__all__ = ["contents", "where"]
__version__ = "2022.12.07"

1234
venv/Lib/site-packages/pip/_vendor/certifi/cacert.pem
View File

File diff suppressed because it is too large Load Diff

86
venv/Lib/site-packages/pip/_vendor/certifi/core.py
View File

@@ -1,34 +1,20 @@
# -*- coding: utf-8 -*-
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem or its contents.
"""
import os
import sys
class _PipPatchedCertificate(Exception):
pass
if sys.version_info >= (3, 11):
try:
# Return a certificate file on disk for a standalone pip zipapp running in
# an isolated build environment to use. Passing --cert to the standalone
# pip does not work since requests calls where() unconditionally on import.
_PIP_STANDALONE_CERT = os.environ.get("_PIP_STANDALONE_CERT")
if _PIP_STANDALONE_CERT:
def where():
return _PIP_STANDALONE_CERT
raise _PipPatchedCertificate()
from importlib.resources import path as get_path, read_text
from importlib.resources import as_file, files
_CACERT_CTX = None
_CACERT_PATH = None
def where():
def where() -> str:
# This is slightly terrible, but we want to delay extracting the file
# in cases where we're inside of a zipimport situation until someone
# actually calls where(), but we don't want to re-extract the file
@@ -47,30 +33,76 @@ try:
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = as_file(files("pip._vendor.certifi").joinpath("cacert.pem"))
_CACERT_PATH = str(_CACERT_CTX.__enter__())
return _CACERT_PATH
def contents() -> str:
return files("pip._vendor.certifi").joinpath("cacert.pem").read_text(encoding="ascii")
elif sys.version_info >= (3, 7):
from importlib.resources import path as get_path, read_text
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the
# file in cases where we're inside of a zipimport situation until
# someone actually calls where(), but we don't want to re-extract
# the file on every call of where(), so we'll do it once then store
# it in a global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you
# to manage the cleanup of this file, so it doesn't actually
# return a path, it returns a context manager that will give
# you the path when you enter it and will do any cleanup when
# you leave it. In the common case of not needing a temporary
# file, it will just return the file system location and the
# __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = get_path("pip._vendor.certifi", "cacert.pem")
_CACERT_PATH = str(_CACERT_CTX.__enter__())
return _CACERT_PATH
except _PipPatchedCertificate:
pass
def contents() -> str:
return read_text("pip._vendor.certifi", "cacert.pem", encoding="ascii")
else:
import os
import types
from typing import Union
Package = Union[types.ModuleType, str]
Resource = Union[str, "os.PathLike"]
except ImportError:
# This fallback will work for Python versions prior to 3.7 that lack the
# importlib.resources module but relies on the existing `where` function
# so won't address issues with environments like PyOxidizer that don't set
# __file__ on modules.
def read_text(_module, _path, encoding="ascii"):
with open(where(), "r", encoding=encoding) as data:
def read_text(
package: Package,
resource: Resource,
encoding: str = 'utf-8',
errors: str = 'strict'
) -> str:
with open(where(), encoding=encoding) as data:
return data.read()
# If we don't have importlib.resources, then we will just do the old logic
# of assuming we're on the filesystem and munge the path directly.
def where():
def where() -> str:
f = os.path.dirname(__file__)
return os.path.join(f, "cacert.pem")
def contents():
return read_text("certifi", "cacert.pem", encoding="ascii")
def contents() -> str:
return read_text("pip._vendor.certifi", "cacert.pem", encoding="ascii")

102
venv/Lib/site-packages/pip/_vendor/chardet/__init__.py
View File

@@ -15,69 +15,101 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from typing import List, Union
from .universaldetector import UniversalDetector
from .charsetgroupprober import CharSetGroupProber
from .charsetprober import CharSetProber
from .enums import InputState
from .version import __version__, VERSION
from .resultdict import ResultDict
from .universaldetector import UniversalDetector
from .version import VERSION, __version__
__all__ = ["UniversalDetector", "detect", "detect_all", "__version__", "VERSION"]
__all__ = ['UniversalDetector', 'detect', 'detect_all', '__version__', 'VERSION']
def detect(byte_str):
def detect(
byte_str: Union[bytes, bytearray], should_rename_legacy: bool = False
) -> ResultDict:
"""
Detect the encoding of the given byte string.
:param byte_str: The byte sequence to examine.
:type byte_str: ``bytes`` or ``bytearray``
:param should_rename_legacy: Should we rename legacy encodings
to their more modern equivalents?
:type should_rename_legacy: ``bool``
"""
if not isinstance(byte_str, bytearray):
if not isinstance(byte_str, bytes):
raise TypeError('Expected object of type bytes or bytearray, got: '
'{}'.format(type(byte_str)))
else:
byte_str = bytearray(byte_str)
detector = UniversalDetector()
raise TypeError(
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
byte_str = bytearray(byte_str)
detector = UniversalDetector(should_rename_legacy=should_rename_legacy)
detector.feed(byte_str)
return detector.close()
def detect_all(byte_str):
def detect_all(
byte_str: Union[bytes, bytearray],
ignore_threshold: bool = False,
should_rename_legacy: bool = False,
) -> List[ResultDict]:
"""
Detect all the possible encodings of the given byte string.
:param byte_str: The byte sequence to examine.
:type byte_str: ``bytes`` or ``bytearray``
:param byte_str: The byte sequence to examine.
:type byte_str: ``bytes`` or ``bytearray``
:param ignore_threshold: Include encodings that are below
``UniversalDetector.MINIMUM_THRESHOLD``
in results.
:type ignore_threshold: ``bool``
:param should_rename_legacy: Should we rename legacy encodings
to their more modern equivalents?
:type should_rename_legacy: ``bool``
"""
if not isinstance(byte_str, bytearray):
if not isinstance(byte_str, bytes):
raise TypeError('Expected object of type bytes or bytearray, got: '
'{}'.format(type(byte_str)))
else:
byte_str = bytearray(byte_str)
raise TypeError(
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
byte_str = bytearray(byte_str)
detector = UniversalDetector()
detector = UniversalDetector(should_rename_legacy=should_rename_legacy)
detector.feed(byte_str)
detector.close()
if detector._input_state == InputState.HIGH_BYTE:
results = []
for prober in detector._charset_probers:
if prober.get_confidence() > detector.MINIMUM_THRESHOLD:
charset_name = prober.charset_name
lower_charset_name = prober.charset_name.lower()
if detector.input_state == InputState.HIGH_BYTE:
results: List[ResultDict] = []
probers: List[CharSetProber] = []
for prober in detector.charset_probers:
if isinstance(prober, CharSetGroupProber):
probers.extend(p for p in prober.probers)
else:
probers.append(prober)
for prober in probers:
if ignore_threshold or prober.get_confidence() > detector.MINIMUM_THRESHOLD:
charset_name = prober.charset_name or ""
lower_charset_name = charset_name.lower()
# Use Windows encoding name instead of ISO-8859 if we saw any
# extra Windows-specific bytes
if lower_charset_name.startswith('iso-8859'):
if detector._has_win_bytes:
charset_name = detector.ISO_WIN_MAP.get(lower_charset_name,
charset_name)
results.append({
'encoding': charset_name,
'confidence': prober.get_confidence(),
'language': prober.language,
})
if lower_charset_name.startswith("iso-8859") and detector.has_win_bytes:
charset_name = detector.ISO_WIN_MAP.get(
lower_charset_name, charset_name
)
# Rename legacy encodings with superset encodings if asked
if should_rename_legacy:
charset_name = detector.LEGACY_MAP.get(
charset_name.lower(), charset_name
)
results.append(
{
"encoding": charset_name,
"confidence": prober.get_confidence(),
"language": prober.language,
}
)
if len(results) > 0:
return sorted(results, key=lambda result: -result['confidence'])
return sorted(results, key=lambda result: -result["confidence"])
return [detector.result]

6
venv/Lib/site-packages/pip/_vendor/chardet/big5freq.py
View File

@@ -42,9 +42,9 @@
BIG5_TYPICAL_DISTRIBUTION_RATIO = 0.75
#Char to FreqOrder table
# Char to FreqOrder table
BIG5_TABLE_SIZE = 5376
# fmt: off
BIG5_CHAR_TO_FREQ_ORDER = (
1,1801,1506, 255,1431, 198, 9, 82, 6,5008, 177, 202,3681,1256,2821, 110, # 16
3814, 33,3274, 261, 76, 44,2114, 16,2946,2187,1176, 659,3971, 26,3451,2653, # 32
@@ -383,4 +383,4 @@ BIG5_CHAR_TO_FREQ_ORDER = (
890,3669,3943,5791,1878,3798,3439,5792,2186,2358,3440,1652,5793,5794,5795, 941, # 5360
2299, 208,3546,4161,2020, 330,4438,3944,2906,2499,3799,4439,4811,5796,5797,5798, # 5376
)
# fmt: on

12
venv/Lib/site-packages/pip/_vendor/chardet/big5prober.py
View File

@@ -25,23 +25,23 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from .chardistribution import Big5DistributionAnalysis
from .codingstatemachine import CodingStateMachine
from .mbcharsetprober import MultiByteCharSetProber
from .mbcssm import BIG5_SM_MODEL
class Big5Prober(MultiByteCharSetProber):
def __init__(self):
super(Big5Prober, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(BIG5_SM_MODEL)
self.distribution_analyzer = Big5DistributionAnalysis()
self.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "Big5"
@property
def language(self):
def language(self) -> str:
return "Chinese"

144
venv/Lib/site-packages/pip/_vendor/chardet/chardistribution.py
View File

@@ -25,40 +25,58 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .euctwfreq import (EUCTW_CHAR_TO_FREQ_ORDER, EUCTW_TABLE_SIZE,
EUCTW_TYPICAL_DISTRIBUTION_RATIO)
from .euckrfreq import (EUCKR_CHAR_TO_FREQ_ORDER, EUCKR_TABLE_SIZE,
EUCKR_TYPICAL_DISTRIBUTION_RATIO)
from .gb2312freq import (GB2312_CHAR_TO_FREQ_ORDER, GB2312_TABLE_SIZE,
GB2312_TYPICAL_DISTRIBUTION_RATIO)
from .big5freq import (BIG5_CHAR_TO_FREQ_ORDER, BIG5_TABLE_SIZE,
BIG5_TYPICAL_DISTRIBUTION_RATIO)
from .jisfreq import (JIS_CHAR_TO_FREQ_ORDER, JIS_TABLE_SIZE,
JIS_TYPICAL_DISTRIBUTION_RATIO)
from typing import Tuple, Union
from .big5freq import (
BIG5_CHAR_TO_FREQ_ORDER,
BIG5_TABLE_SIZE,
BIG5_TYPICAL_DISTRIBUTION_RATIO,
)
from .euckrfreq import (
EUCKR_CHAR_TO_FREQ_ORDER,
EUCKR_TABLE_SIZE,
EUCKR_TYPICAL_DISTRIBUTION_RATIO,
)
from .euctwfreq import (
EUCTW_CHAR_TO_FREQ_ORDER,
EUCTW_TABLE_SIZE,
EUCTW_TYPICAL_DISTRIBUTION_RATIO,
)
from .gb2312freq import (
GB2312_CHAR_TO_FREQ_ORDER,
GB2312_TABLE_SIZE,
GB2312_TYPICAL_DISTRIBUTION_RATIO,
)
from .jisfreq import (
JIS_CHAR_TO_FREQ_ORDER,
JIS_TABLE_SIZE,
JIS_TYPICAL_DISTRIBUTION_RATIO,
)
from .johabfreq import JOHAB_TO_EUCKR_ORDER_TABLE
class CharDistributionAnalysis(object):
class CharDistributionAnalysis:
ENOUGH_DATA_THRESHOLD = 1024
SURE_YES = 0.99
SURE_NO = 0.01
MINIMUM_DATA_THRESHOLD = 3
def __init__(self):
def __init__(self) -> None:
# Mapping table to get frequency order from char order (get from
# GetOrder())
self._char_to_freq_order = None
self._table_size = None # Size of above table
self._char_to_freq_order: Tuple[int, ...] = tuple()
self._table_size = 0 # Size of above table
# This is a constant value which varies from language to language,
# used in calculating confidence. See
# http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html
# for further detail.
self.typical_distribution_ratio = None
self._done = None
self._total_chars = None
self._freq_chars = None
self.typical_distribution_ratio = 0.0
self._done = False
self._total_chars = 0
self._freq_chars = 0
self.reset()
def reset(self):
def reset(self) -> None:
"""reset analyser, clear any state"""
# If this flag is set to True, detection is done and conclusion has
# been made
@@ -67,7 +85,7 @@ class CharDistributionAnalysis(object):
# The number of characters whose frequency order is less than 512
self._freq_chars = 0
def feed(self, char, char_len):
def feed(self, char: Union[bytes, bytearray], char_len: int) -> None:
"""feed a character with known length"""
if char_len == 2:
# we only care about 2-bytes character in our distribution analysis
@@ -81,7 +99,7 @@ class CharDistributionAnalysis(object):
if 512 > self._char_to_freq_order[order]:
self._freq_chars += 1
def get_confidence(self):
def get_confidence(self) -> float:
"""return confidence based on existing data"""
# if we didn't receive any character in our consideration range,
# return negative answer
@@ -89,20 +107,21 @@ class CharDistributionAnalysis(object):
return self.SURE_NO
if self._total_chars != self._freq_chars:
r = (self._freq_chars / ((self._total_chars - self._freq_chars)
* self.typical_distribution_ratio))
r = self._freq_chars / (
(self._total_chars - self._freq_chars) * self.typical_distribution_ratio
)
if r < self.SURE_YES:
return r
# normalize confidence (we don't want to be 100% sure)
return self.SURE_YES
def got_enough_data(self):
def got_enough_data(self) -> bool:
# It is not necessary to receive all data to draw conclusion.
# For charset detection, certain amount of data is enough
return self._total_chars > self.ENOUGH_DATA_THRESHOLD
def get_order(self, byte_str):
def get_order(self, _: Union[bytes, bytearray]) -> int:
# We do not handle characters based on the original encoding string,
# but convert this encoding string to a number, here called order.
# This allows multiple encodings of a language to share one frequency
@@ -111,13 +130,13 @@ class CharDistributionAnalysis(object):
class EUCTWDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
super(EUCTWDistributionAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = EUCTW_CHAR_TO_FREQ_ORDER
self._table_size = EUCTW_TABLE_SIZE
self.typical_distribution_ratio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
# for euc-TW encoding, we are interested
# first byte range: 0xc4 -- 0xfe
# second byte range: 0xa1 -- 0xfe
@@ -125,18 +144,17 @@ class EUCTWDistributionAnalysis(CharDistributionAnalysis):
first_char = byte_str[0]
if first_char >= 0xC4:
return 94 * (first_char - 0xC4) + byte_str[1] - 0xA1
else:
return -1
return -1
class EUCKRDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
super(EUCKRDistributionAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER
self._table_size = EUCKR_TABLE_SIZE
self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
# for euc-KR encoding, we are interested
# first byte range: 0xb0 -- 0xfe
# second byte range: 0xa1 -- 0xfe
@@ -144,18 +162,32 @@ class EUCKRDistributionAnalysis(CharDistributionAnalysis):
first_char = byte_str[0]
if first_char >= 0xB0:
return 94 * (first_char - 0xB0) + byte_str[1] - 0xA1
else:
return -1
return -1
class JOHABDistributionAnalysis(CharDistributionAnalysis):
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER
self._table_size = EUCKR_TABLE_SIZE
self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
first_char = byte_str[0]
if 0x88 <= first_char < 0xD4:
code = first_char * 256 + byte_str[1]
return JOHAB_TO_EUCKR_ORDER_TABLE.get(code, -1)
return -1
class GB2312DistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
super(GB2312DistributionAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = GB2312_CHAR_TO_FREQ_ORDER
self._table_size = GB2312_TABLE_SIZE
self.typical_distribution_ratio = GB2312_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
# for GB2312 encoding, we are interested
# first byte range: 0xb0 -- 0xfe
# second byte range: 0xa1 -- 0xfe
@@ -163,18 +195,17 @@ class GB2312DistributionAnalysis(CharDistributionAnalysis):
first_char, second_char = byte_str[0], byte_str[1]
if (first_char >= 0xB0) and (second_char >= 0xA1):
return 94 * (first_char - 0xB0) + second_char - 0xA1
else:
return -1
return -1
class Big5DistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
super(Big5DistributionAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = BIG5_CHAR_TO_FREQ_ORDER
self._table_size = BIG5_TABLE_SIZE
self.typical_distribution_ratio = BIG5_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
# for big5 encoding, we are interested
# first byte range: 0xa4 -- 0xfe
# second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
@@ -183,28 +214,26 @@ class Big5DistributionAnalysis(CharDistributionAnalysis):
if first_char >= 0xA4:
if second_char >= 0xA1:
return 157 * (first_char - 0xA4) + second_char - 0xA1 + 63
else:
return 157 * (first_char - 0xA4) + second_char - 0x40
else:
return -1
return 157 * (first_char - 0xA4) + second_char - 0x40
return -1
class SJISDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
super(SJISDistributionAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
self._table_size = JIS_TABLE_SIZE
self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
# for sjis encoding, we are interested
# first byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
# second byte range: 0x40 -- 0x7e, 0x81 -- oxfe
# no validation needed here. State machine has done that
first_char, second_char = byte_str[0], byte_str[1]
if (first_char >= 0x81) and (first_char <= 0x9F):
if 0x81 <= first_char <= 0x9F:
order = 188 * (first_char - 0x81)
elif (first_char >= 0xE0) and (first_char <= 0xEF):
elif 0xE0 <= first_char <= 0xEF:
order = 188 * (first_char - 0xE0 + 31)
else:
return -1
@@ -215,19 +244,18 @@ class SJISDistributionAnalysis(CharDistributionAnalysis):
class EUCJPDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
super(EUCJPDistributionAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
self._table_size = JIS_TABLE_SIZE
self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> int:
# for euc-JP encoding, we are interested
# first byte range: 0xa0 -- 0xfe
# second byte range: 0xa1 -- 0xfe
# no validation needed here. State machine has done that
char = byte_str[0]
if char >= 0xA0:
return 94 * (char - 0xA1) + byte_str[1] - 0xa1
else:
return -1
return 94 * (char - 0xA1) + byte_str[1] - 0xA1
return -1

45
venv/Lib/site-packages/pip/_vendor/chardet/charsetgroupprober.py
View File

@@ -25,29 +25,30 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .enums import ProbingState
from typing import List, Optional, Union
from .charsetprober import CharSetProber
from .enums import LanguageFilter, ProbingState
class CharSetGroupProber(CharSetProber):
def __init__(self, lang_filter=None):
super(CharSetGroupProber, self).__init__(lang_filter=lang_filter)
def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
super().__init__(lang_filter=lang_filter)
self._active_num = 0
self.probers = []
self._best_guess_prober = None
self.probers: List[CharSetProber] = []
self._best_guess_prober: Optional[CharSetProber] = None
def reset(self):
super(CharSetGroupProber, self).reset()
def reset(self) -> None:
super().reset()
self._active_num = 0
for prober in self.probers:
if prober:
prober.reset()
prober.active = True
self._active_num += 1
prober.reset()
prober.active = True
self._active_num += 1
self._best_guess_prober = None
@property
def charset_name(self):
def charset_name(self) -> Optional[str]:
if not self._best_guess_prober:
self.get_confidence()
if not self._best_guess_prober:
@@ -55,17 +56,15 @@ class CharSetGroupProber(CharSetProber):
return self._best_guess_prober.charset_name
@property
def language(self):
def language(self) -> Optional[str]:
if not self._best_guess_prober:
self.get_confidence()
if not self._best_guess_prober:
return None
return self._best_guess_prober.language
def feed(self, byte_str):
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
for prober in self.probers:
if not prober:
continue
if not prober.active:
continue
state = prober.feed(byte_str)
@@ -75,7 +74,7 @@ class CharSetGroupProber(CharSetProber):
self._best_guess_prober = prober
self._state = ProbingState.FOUND_IT
return self.state
elif state == ProbingState.NOT_ME:
if state == ProbingState.NOT_ME:
prober.active = False
self._active_num -= 1
if self._active_num <= 0:
@@ -83,22 +82,22 @@ class CharSetGroupProber(CharSetProber):
return self.state
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
state = self.state
if state == ProbingState.FOUND_IT:
return 0.99
elif state == ProbingState.NOT_ME:
if state == ProbingState.NOT_ME:
return 0.01
best_conf = 0.0
self._best_guess_prober = None
for prober in self.probers:
if not prober:
continue
if not prober.active:
self.logger.debug('%s not active', prober.charset_name)
self.logger.debug("%s not active", prober.charset_name)
continue
conf = prober.get_confidence()
self.logger.debug('%s %s confidence = %s', prober.charset_name, prober.language, conf)
self.logger.debug(
"%s %s confidence = %s", prober.charset_name, prober.language, conf
)
if best_conf < conf:
best_conf = conf
self._best_guess_prober = prober

74
venv/Lib/site-packages/pip/_vendor/chardet/charsetprober.py
View File

@@ -28,54 +28,62 @@
import logging
import re
from typing import Optional, Union
from .enums import ProbingState
from .enums import LanguageFilter, ProbingState
INTERNATIONAL_WORDS_PATTERN = re.compile(
b"[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?"
)
class CharSetProber(object):
class CharSetProber:
SHORTCUT_THRESHOLD = 0.95
def __init__(self, lang_filter=None):
self._state = None
def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
self._state = ProbingState.DETECTING
self.active = True
self.lang_filter = lang_filter
self.logger = logging.getLogger(__name__)
def reset(self):
def reset(self) -> None:
self._state = ProbingState.DETECTING
@property
def charset_name(self):
def charset_name(self) -> Optional[str]:
return None
def feed(self, buf):
pass
@property
def language(self) -> Optional[str]:
raise NotImplementedError
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
raise NotImplementedError
@property
def state(self):
def state(self) -> ProbingState:
return self._state
def get_confidence(self):
def get_confidence(self) -> float:
return 0.0
@staticmethod
def filter_high_byte_only(buf):
buf = re.sub(b'([\x00-\x7F])+', b' ', buf)
def filter_high_byte_only(buf: Union[bytes, bytearray]) -> bytes:
buf = re.sub(b"([\x00-\x7F])+", b" ", buf)
return buf
@staticmethod
def filter_international_words(buf):
def filter_international_words(buf: Union[bytes, bytearray]) -> bytearray:
"""
We define three types of bytes:
alphabet: english alphabets [a-zA-Z]
international: international characters [\x80-\xFF]
marker: everything else [^a-zA-Z\x80-\xFF]
The input buffer can be thought to contain a series of words delimited
by markers. This function works to filter all words that contain at
least one international character. All contiguous sequences of markers
are replaced by a single space ascii character.
This filter applies to all scripts which do not use English characters.
"""
filtered = bytearray()
@@ -83,8 +91,7 @@ class CharSetProber(object):
# This regex expression filters out only words that have at-least one
# international character. The word may include one marker character at
# the end.
words = re.findall(b'[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?',
buf)
words = INTERNATIONAL_WORDS_PATTERN.findall(buf)
for word in words:
filtered.extend(word[:-1])
@@ -94,20 +101,17 @@ class CharSetProber(object):
# similarly across all languages and may thus have similar
# frequencies).
last_char = word[-1:]
if not last_char.isalpha() and last_char < b'\x80':
last_char = b' '
if not last_char.isalpha() and last_char < b"\x80":
last_char = b" "
filtered.extend(last_char)
return filtered
@staticmethod
def filter_with_english_letters(buf):
def remove_xml_tags(buf: Union[bytes, bytearray]) -> bytes:
"""
Returns a copy of ``buf`` that retains only the sequences of English
alphabet and high byte characters that are not between <> characters.
Also retains English alphabet and high byte characters immediately
before occurrences of >.
This filter can be applied to all scripts which contain both English
characters and extended ASCII characters, but is currently only used by
``Latin1Prober``.
@@ -115,26 +119,24 @@ class CharSetProber(object):
filtered = bytearray()
in_tag = False
prev = 0
buf = memoryview(buf).cast("c")
for curr in range(len(buf)):
# Slice here to get bytes instead of an int with Python 3
buf_char = buf[curr:curr + 1]
# Check if we're coming out of or entering an HTML tag
if buf_char == b'>':
for curr, buf_char in enumerate(buf):
# Check if we're coming out of or entering an XML tag
# https://github.com/python/typeshed/issues/8182
if buf_char == b">": # type: ignore[comparison-overlap]
prev = curr + 1
in_tag = False
elif buf_char == b'<':
in_tag = True
# If current character is not extended-ASCII and not alphabetic...
if buf_char < b'\x80' and not buf_char.isalpha():
# ...and we're not in a tag
# https://github.com/python/typeshed/issues/8182
elif buf_char == b"<": # type: ignore[comparison-overlap]
if curr > prev and not in_tag:
# Keep everything after last non-extended-ASCII,
# non-alphabetic character
filtered.extend(buf[prev:curr])
# Output a space to delimit stretch we kept
filtered.extend(b' ')
prev = curr + 1
filtered.extend(b" ")
in_tag = True
# If we're not in a tag...
if not in_tag:

1
venv/Lib/site-packages/pip/_vendor/chardet/cli/__init__.py
View File

@@ -1 +0,0 @@

86
venv/Lib/site-packages/pip/_vendor/chardet/cli/chardetect.py
View File

@@ -12,17 +12,21 @@ If no paths are provided, it takes its input from stdin.
"""
from __future__ import absolute_import, print_function, unicode_literals
import argparse
import sys
from typing import Iterable, List, Optional
from pip._vendor.chardet import __version__
from pip._vendor.chardet.compat import PY2
from pip._vendor.chardet.universaldetector import UniversalDetector
from .. import __version__
from ..universaldetector import UniversalDetector
def description_of(lines, name='stdin'):
def description_of(
lines: Iterable[bytes],
name: str = "stdin",
minimal: bool = False,
should_rename_legacy: bool = False,
) -> Optional[str]:
"""
Return a string describing the probable encoding of a file or
list of strings.
@@ -31,8 +35,11 @@ def description_of(lines, name='stdin'):
:type lines: Iterable of bytes
:param name: Name of file or collection of lines
:type name: str
:param should_rename_legacy: Should we rename legacy encodings to
their more modern equivalents?
:type should_rename_legacy: ``bool``
"""
u = UniversalDetector()
u = UniversalDetector(should_rename_legacy=should_rename_legacy)
for line in lines:
line = bytearray(line)
u.feed(line)
@@ -41,16 +48,14 @@ def description_of(lines, name='stdin'):
break
u.close()
result = u.result
if PY2:
name = name.decode(sys.getfilesystemencoding(), 'ignore')
if result['encoding']:
return '{}: {} with confidence {}'.format(name, result['encoding'],
result['confidence'])
else:
return '{}: no result'.format(name)
if minimal:
return result["encoding"]
if result["encoding"]:
return f'{name}: {result["encoding"]} with confidence {result["confidence"]}'
return f"{name}: no result"
def main(argv=None):
def main(argv: Optional[List[str]] = None) -> None:
"""
Handles command line arguments and gets things started.
@@ -60,25 +65,48 @@ def main(argv=None):
"""
# Get command line arguments
parser = argparse.ArgumentParser(
description="Takes one or more file paths and reports their detected \
encodings")
parser.add_argument('input',
help='File whose encoding we would like to determine. \
(default: stdin)',
type=argparse.FileType('rb'), nargs='*',
default=[sys.stdin if PY2 else sys.stdin.buffer])
parser.add_argument('--version', action='version',
version='%(prog)s {}'.format(__version__))
description=(
"Takes one or more file paths and reports their detected encodings"
)
)
parser.add_argument(
"input",
help="File whose encoding we would like to determine. (default: stdin)",
type=argparse.FileType("rb"),
nargs="*",
default=[sys.stdin.buffer],
)
parser.add_argument(
"--minimal",
help="Print only the encoding to standard output",
action="store_true",
)
parser.add_argument(
"-l",
"--legacy",
help="Rename legacy encodings to more modern ones.",
action="store_true",
)
parser.add_argument(
"--version", action="version", version=f"%(prog)s {__version__}"
)
args = parser.parse_args(argv)
for f in args.input:
if f.isatty():
print("You are running chardetect interactively. Press " +
"CTRL-D twice at the start of a blank line to signal the " +
"end of your input. If you want help, run chardetect " +
"--help\n", file=sys.stderr)
print(description_of(f, f.name))
print(
"You are running chardetect interactively. Press "
"CTRL-D twice at the start of a blank line to signal the "
"end of your input. If you want help, run chardetect "
"--help\n",
file=sys.stderr,
)
print(
description_of(
f, f.name, minimal=args.minimal, should_rename_legacy=args.legacy
)
)
if __name__ == '__main__':
if __name__ == "__main__":
main()

32
venv/Lib/site-packages/pip/_vendor/chardet/codingstatemachine.py
View File

@@ -27,10 +27,11 @@
import logging
from .codingstatemachinedict import CodingStateMachineDict
from .enums import MachineState
class CodingStateMachine(object):
class CodingStateMachine:
"""
A state machine to verify a byte sequence for a particular encoding. For
each byte the detector receives, it will feed that byte to every active
@@ -52,37 +53,38 @@ class CodingStateMachine(object):
negative answer for this encoding. Detector will exclude this
encoding from consideration from here on.
"""
def __init__(self, sm):
def __init__(self, sm: CodingStateMachineDict) -> None:
self._model = sm
self._curr_byte_pos = 0
self._curr_char_len = 0
self._curr_state = None
self._curr_state = MachineState.START
self.active = True
self.logger = logging.getLogger(__name__)
self.reset()
def reset(self):
def reset(self) -> None:
self._curr_state = MachineState.START
def next_state(self, c):
def next_state(self, c: int) -> int:
# for each byte we get its class
# if it is first byte, we also get byte length
byte_class = self._model['class_table'][c]
byte_class = self._model["class_table"][c]
if self._curr_state == MachineState.START:
self._curr_byte_pos = 0
self._curr_char_len = self._model['char_len_table'][byte_class]
self._curr_char_len = self._model["char_len_table"][byte_class]
# from byte's class and state_table, we get its next state
curr_state = (self._curr_state * self._model['class_factor']
+ byte_class)
self._curr_state = self._model['state_table'][curr_state]
curr_state = self._curr_state * self._model["class_factor"] + byte_class
self._curr_state = self._model["state_table"][curr_state]
self._curr_byte_pos += 1
return self._curr_state
def get_current_charlen(self):
def get_current_charlen(self) -> int:
return self._curr_char_len
def get_coding_state_machine(self):
return self._model['name']
def get_coding_state_machine(self) -> str:
return self._model["name"]
@property
def language(self):
return self._model['language']
def language(self) -> str:
return self._model["language"]

36
venv/Lib/site-packages/pip/_vendor/chardet/compat.py
View File

@@ -1,36 +0,0 @@
######################## BEGIN LICENSE BLOCK ########################
# Contributor(s):
# Dan Blanchard
# Ian Cordasco
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
import sys
if sys.version_info < (3, 0):
PY2 = True
PY3 = False
string_types = (str, unicode)
text_type = unicode
iteritems = dict.iteritems
else:
PY2 = False
PY3 = True
string_types = (bytes, str)
text_type = str
iteritems = dict.items

8
venv/Lib/site-packages/pip/_vendor/chardet/cp949prober.py
View File

@@ -32,8 +32,8 @@ from .mbcssm import CP949_SM_MODEL
class CP949Prober(MultiByteCharSetProber):
def __init__(self):
super(CP949Prober, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(CP949_SM_MODEL)
# NOTE: CP949 is a superset of EUC-KR, so the distribution should be
# not different.
@@ -41,9 +41,9 @@ class CP949Prober(MultiByteCharSetProber):
self.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "CP949"
@property
def language(self):
def language(self) -> str:
return "Korean"

23
venv/Lib/site-packages/pip/_vendor/chardet/enums.py
View File

@@ -4,21 +4,26 @@ All of the Enums that are used throughout the chardet package.
:author: Dan Blanchard (dan.blanchard@gmail.com)
"""
from enum import Enum, Flag
class InputState(object):
class InputState:
"""
This enum represents the different states a universal detector can be in.
"""
PURE_ASCII = 0
ESC_ASCII = 1
HIGH_BYTE = 2
class LanguageFilter(object):
class LanguageFilter(Flag):
"""
This enum represents the different language filters we can apply to a
``UniversalDetector``.
"""
NONE = 0x00
CHINESE_SIMPLIFIED = 0x01
CHINESE_TRADITIONAL = 0x02
JAPANESE = 0x04
@@ -29,46 +34,50 @@ class LanguageFilter(object):
CJK = CHINESE | JAPANESE | KOREAN
class ProbingState(object):
class ProbingState(Enum):
"""
This enum represents the different states a prober can be in.
"""
DETECTING = 0
FOUND_IT = 1
NOT_ME = 2
class MachineState(object):
class MachineState:
"""
This enum represents the different states a state machine can be in.
"""
START = 0
ERROR = 1
ITS_ME = 2
class SequenceLikelihood(object):
class SequenceLikelihood:
"""
This enum represents the likelihood of a character following the previous one.
"""
NEGATIVE = 0
UNLIKELY = 1
LIKELY = 2
POSITIVE = 3
@classmethod
def get_num_categories(cls):
def get_num_categories(cls) -> int:
""":returns: The number of likelihood categories in the enum."""
return 4
class CharacterCategory(object):
class CharacterCategory:
"""
This enum represents the different categories language models for
``SingleByteCharsetProber`` put characters into.
Anything less than CONTROL is considered a letter.
"""
UNDEFINED = 255
LINE_BREAK = 254
SYMBOL = 253

45
venv/Lib/site-packages/pip/_vendor/chardet/escprober.py
View File

@@ -25,11 +25,17 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from typing import Optional, Union
from .charsetprober import CharSetProber
from .codingstatemachine import CodingStateMachine
from .enums import LanguageFilter, ProbingState, MachineState
from .escsm import (HZ_SM_MODEL, ISO2022CN_SM_MODEL, ISO2022JP_SM_MODEL,
ISO2022KR_SM_MODEL)
from .enums import LanguageFilter, MachineState, ProbingState
from .escsm import (
HZ_SM_MODEL,
ISO2022CN_SM_MODEL,
ISO2022JP_SM_MODEL,
ISO2022KR_SM_MODEL,
)
class EscCharSetProber(CharSetProber):
@@ -39,8 +45,8 @@ class EscCharSetProber(CharSetProber):
identify these encodings.
"""
def __init__(self, lang_filter=None):
super(EscCharSetProber, self).__init__(lang_filter=lang_filter)
def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
super().__init__(lang_filter=lang_filter)
self.coding_sm = []
if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
@@ -49,17 +55,15 @@ class EscCharSetProber(CharSetProber):
self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL))
if self.lang_filter & LanguageFilter.KOREAN:
self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL))
self.active_sm_count = None
self._detected_charset = None
self._detected_language = None
self._state = None
self.active_sm_count = 0
self._detected_charset: Optional[str] = None
self._detected_language: Optional[str] = None
self._state = ProbingState.DETECTING
self.reset()
def reset(self):
super(EscCharSetProber, self).reset()
def reset(self) -> None:
super().reset()
for coding_sm in self.coding_sm:
if not coding_sm:
continue
coding_sm.active = True
coding_sm.reset()
self.active_sm_count = len(self.coding_sm)
@@ -67,23 +71,20 @@ class EscCharSetProber(CharSetProber):
self._detected_language = None
@property
def charset_name(self):
def charset_name(self) -> Optional[str]:
return self._detected_charset
@property
def language(self):
def language(self) -> Optional[str]:
return self._detected_language
def get_confidence(self):
if self._detected_charset:
return 0.99
else:
return 0.00
def get_confidence(self) -> float:
return 0.99 if self._detected_charset else 0.00
def feed(self, byte_str):
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
for c in byte_str:
for coding_sm in self.coding_sm:
if not coding_sm or not coding_sm.active:
if not coding_sm.active:
continue
coding_state = coding_sm.next_state(c)
if coding_state == MachineState.ERROR:

385
venv/Lib/site-packages/pip/_vendor/chardet/escsm.py
View File

@@ -12,7 +12,7 @@
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -20,227 +20,242 @@
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .codingstatemachinedict import CodingStateMachineDict
from .enums import MachineState
# fmt: off
HZ_CLS = (
1,0,0,0,0,0,0,0, # 00 - 07
0,0,0,0,0,0,0,0, # 08 - 0f
0,0,0,0,0,0,0,0, # 10 - 17
0,0,0,1,0,0,0,0, # 18 - 1f
0,0,0,0,0,0,0,0, # 20 - 27
0,0,0,0,0,0,0,0, # 28 - 2f
0,0,0,0,0,0,0,0, # 30 - 37
0,0,0,0,0,0,0,0, # 38 - 3f
0,0,0,0,0,0,0,0, # 40 - 47
0,0,0,0,0,0,0,0, # 48 - 4f
0,0,0,0,0,0,0,0, # 50 - 57
0,0,0,0,0,0,0,0, # 58 - 5f
0,0,0,0,0,0,0,0, # 60 - 67
0,0,0,0,0,0,0,0, # 68 - 6f
0,0,0,0,0,0,0,0, # 70 - 77
0,0,0,4,0,5,2,0, # 78 - 7f
1,1,1,1,1,1,1,1, # 80 - 87
1,1,1,1,1,1,1,1, # 88 - 8f
1,1,1,1,1,1,1,1, # 90 - 97
1,1,1,1,1,1,1,1, # 98 - 9f
1,1,1,1,1,1,1,1, # a0 - a7
1,1,1,1,1,1,1,1, # a8 - af
1,1,1,1,1,1,1,1, # b0 - b7
1,1,1,1,1,1,1,1, # b8 - bf
1,1,1,1,1,1,1,1, # c0 - c7
1,1,1,1,1,1,1,1, # c8 - cf
1,1,1,1,1,1,1,1, # d0 - d7
1,1,1,1,1,1,1,1, # d8 - df
1,1,1,1,1,1,1,1, # e0 - e7
1,1,1,1,1,1,1,1, # e8 - ef
1,1,1,1,1,1,1,1, # f0 - f7
1,1,1,1,1,1,1,1, # f8 - ff
1, 0, 0, 0, 0, 0, 0, 0, # 00 - 07
0, 0, 0, 0, 0, 0, 0, 0, # 08 - 0f
0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17
0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f
0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27
0, 0, 0, 0, 0, 0, 0, 0, # 28 - 2f
0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37
0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f
0, 0, 0, 0, 0, 0, 0, 0, # 40 - 47
0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f
0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57
0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f
0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67
0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f
0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77
0, 0, 0, 4, 0, 5, 2, 0, # 78 - 7f
1, 1, 1, 1, 1, 1, 1, 1, # 80 - 87
1, 1, 1, 1, 1, 1, 1, 1, # 88 - 8f
1, 1, 1, 1, 1, 1, 1, 1, # 90 - 97
1, 1, 1, 1, 1, 1, 1, 1, # 98 - 9f
1, 1, 1, 1, 1, 1, 1, 1, # a0 - a7
1, 1, 1, 1, 1, 1, 1, 1, # a8 - af
1, 1, 1, 1, 1, 1, 1, 1, # b0 - b7
1, 1, 1, 1, 1, 1, 1, 1, # b8 - bf
1, 1, 1, 1, 1, 1, 1, 1, # c0 - c7
1, 1, 1, 1, 1, 1, 1, 1, # c8 - cf
1, 1, 1, 1, 1, 1, 1, 1, # d0 - d7
1, 1, 1, 1, 1, 1, 1, 1, # d8 - df
1, 1, 1, 1, 1, 1, 1, 1, # e0 - e7
1, 1, 1, 1, 1, 1, 1, 1, # e8 - ef
1, 1, 1, 1, 1, 1, 1, 1, # f0 - f7
1, 1, 1, 1, 1, 1, 1, 1, # f8 - ff
)
HZ_ST = (
MachineState.START,MachineState.ERROR, 3,MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,# 00-07
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,# 08-0f
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START, 4,MachineState.ERROR,# 10-17
5,MachineState.ERROR, 6,MachineState.ERROR, 5, 5, 4,MachineState.ERROR,# 18-1f
4,MachineState.ERROR, 4, 4, 4,MachineState.ERROR, 4,MachineState.ERROR,# 20-27
4,MachineState.ITS_ME,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,# 28-2f
MachineState.START, MachineState.ERROR, 3, MachineState.START, MachineState.START, MachineState.START, MachineState.ERROR, MachineState.ERROR, # 00-07
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 08-0f
MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.START, MachineState.START, 4, MachineState.ERROR, # 10-17
5, MachineState.ERROR, 6, MachineState.ERROR, 5, 5, 4, MachineState.ERROR, # 18-1f
4, MachineState.ERROR, 4, 4, 4, MachineState.ERROR, 4, MachineState.ERROR, # 20-27
4, MachineState.ITS_ME, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 28-2f
)
# fmt: on
HZ_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0)
HZ_SM_MODEL = {'class_table': HZ_CLS,
'class_factor': 6,
'state_table': HZ_ST,
'char_len_table': HZ_CHAR_LEN_TABLE,
'name': "HZ-GB-2312",
'language': 'Chinese'}
HZ_SM_MODEL: CodingStateMachineDict = {
"class_table": HZ_CLS,
"class_factor": 6,
"state_table": HZ_ST,
"char_len_table": HZ_CHAR_LEN_TABLE,
"name": "HZ-GB-2312",
"language": "Chinese",
}
# fmt: off
ISO2022CN_CLS = (
2,0,0,0,0,0,0,0, # 00 - 07
0,0,0,0,0,0,0,0, # 08 - 0f
0,0,0,0,0,0,0,0, # 10 - 17
0,0,0,1,0,0,0,0, # 18 - 1f
0,0,0,0,0,0,0,0, # 20 - 27
0,3,0,0,0,0,0,0, # 28 - 2f
0,0,0,0,0,0,0,0, # 30 - 37
0,0,0,0,0,0,0,0, # 38 - 3f
0,0,0,4,0,0,0,0, # 40 - 47
0,0,0,0,0,0,0,0, # 48 - 4f
0,0,0,0,0,0,0,0, # 50 - 57
0,0,0,0,0,0,0,0, # 58 - 5f
0,0,0,0,0,0,0,0, # 60 - 67
0,0,0,0,0,0,0,0, # 68 - 6f
0,0,0,0,0,0,0,0, # 70 - 77
0,0,0,0,0,0,0,0, # 78 - 7f
2,2,2,2,2,2,2,2, # 80 - 87
2,2,2,2,2,2,2,2, # 88 - 8f
2,2,2,2,2,2,2,2, # 90 - 97
2,2,2,2,2,2,2,2, # 98 - 9f
2,2,2,2,2,2,2,2, # a0 - a7
2,2,2,2,2,2,2,2, # a8 - af
2,2,2,2,2,2,2,2, # b0 - b7
2,2,2,2,2,2,2,2, # b8 - bf
2,2,2,2,2,2,2,2, # c0 - c7
2,2,2,2,2,2,2,2, # c8 - cf
2,2,2,2,2,2,2,2, # d0 - d7
2,2,2,2,2,2,2,2, # d8 - df
2,2,2,2,2,2,2,2, # e0 - e7
2,2,2,2,2,2,2,2, # e8 - ef
2,2,2,2,2,2,2,2, # f0 - f7
2,2,2,2,2,2,2,2, # f8 - ff
2, 0, 0, 0, 0, 0, 0, 0, # 00 - 07
0, 0, 0, 0, 0, 0, 0, 0, # 08 - 0f
0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17
0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f
0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27
0, 3, 0, 0, 0, 0, 0, 0, # 28 - 2f
0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37
0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f
0, 0, 0, 4, 0, 0, 0, 0, # 40 - 47
0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f
0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57
0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f
0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67
0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f
0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77
0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f
2, 2, 2, 2, 2, 2, 2, 2, # 80 - 87
2, 2, 2, 2, 2, 2, 2, 2, # 88 - 8f
2, 2, 2, 2, 2, 2, 2, 2, # 90 - 97
2, 2, 2, 2, 2, 2, 2, 2, # 98 - 9f
2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7
2, 2, 2, 2, 2, 2, 2, 2, # a8 - af
2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7
2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf
2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7
2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf
2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7
2, 2, 2, 2, 2, 2, 2, 2, # d8 - df
2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7
2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef
2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7
2, 2, 2, 2, 2, 2, 2, 2, # f8 - ff
)
ISO2022CN_ST = (
MachineState.START, 3,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,# 00-07
MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 08-0f
MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,# 10-17
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 4,MachineState.ERROR,# 18-1f
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 20-27
5, 6,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 28-2f
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 30-37
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,MachineState.START,# 38-3f
MachineState.START, 3, MachineState.ERROR, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 00-07
MachineState.START, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 08-0f
MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 10-17
MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 4, MachineState.ERROR, # 18-1f
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 20-27
5, 6, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 28-2f
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 30-37
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.START, # 38-3f
)
# fmt: on
ISO2022CN_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0, 0, 0, 0)
ISO2022CN_SM_MODEL = {'class_table': ISO2022CN_CLS,
'class_factor': 9,
'state_table': ISO2022CN_ST,
'char_len_table': ISO2022CN_CHAR_LEN_TABLE,
'name': "ISO-2022-CN",
'language': 'Chinese'}
ISO2022CN_SM_MODEL: CodingStateMachineDict = {
"class_table": ISO2022CN_CLS,
"class_factor": 9,
"state_table": ISO2022CN_ST,
"char_len_table": ISO2022CN_CHAR_LEN_TABLE,
"name": "ISO-2022-CN",
"language": "Chinese",
}
# fmt: off
ISO2022JP_CLS = (
2,0,0,0,0,0,0,0, # 00 - 07
0,0,0,0,0,0,2,2, # 08 - 0f
0,0,0,0,0,0,0,0, # 10 - 17
0,0,0,1,0,0,0,0, # 18 - 1f
0,0,0,0,7,0,0,0, # 20 - 27
3,0,0,0,0,0,0,0, # 28 - 2f
0,0,0,0,0,0,0,0, # 30 - 37
0,0,0,0,0,0,0,0, # 38 - 3f
6,0,4,0,8,0,0,0, # 40 - 47
0,9,5,0,0,0,0,0, # 48 - 4f
0,0,0,0,0,0,0,0, # 50 - 57
0,0,0,0,0,0,0,0, # 58 - 5f
0,0,0,0,0,0,0,0, # 60 - 67
0,0,0,0,0,0,0,0, # 68 - 6f
0,0,0,0,0,0,0,0, # 70 - 77
0,0,0,0,0,0,0,0, # 78 - 7f
2,2,2,2,2,2,2,2, # 80 - 87
2,2,2,2,2,2,2,2, # 88 - 8f
2,2,2,2,2,2,2,2, # 90 - 97
2,2,2,2,2,2,2,2, # 98 - 9f
2,2,2,2,2,2,2,2, # a0 - a7
2,2,2,2,2,2,2,2, # a8 - af
2,2,2,2,2,2,2,2, # b0 - b7
2,2,2,2,2,2,2,2, # b8 - bf
2,2,2,2,2,2,2,2, # c0 - c7
2,2,2,2,2,2,2,2, # c8 - cf
2,2,2,2,2,2,2,2, # d0 - d7
2,2,2,2,2,2,2,2, # d8 - df
2,2,2,2,2,2,2,2, # e0 - e7
2,2,2,2,2,2,2,2, # e8 - ef
2,2,2,2,2,2,2,2, # f0 - f7
2,2,2,2,2,2,2,2, # f8 - ff
2, 0, 0, 0, 0, 0, 0, 0, # 00 - 07
0, 0, 0, 0, 0, 0, 2, 2, # 08 - 0f
0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17
0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f
0, 0, 0, 0, 7, 0, 0, 0, # 20 - 27
3, 0, 0, 0, 0, 0, 0, 0, # 28 - 2f
0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37
0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f
6, 0, 4, 0, 8, 0, 0, 0, # 40 - 47
0, 9, 5, 0, 0, 0, 0, 0, # 48 - 4f
0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57
0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f
0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67
0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f
0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77
0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f
2, 2, 2, 2, 2, 2, 2, 2, # 80 - 87
2, 2, 2, 2, 2, 2, 2, 2, # 88 - 8f
2, 2, 2, 2, 2, 2, 2, 2, # 90 - 97
2, 2, 2, 2, 2, 2, 2, 2, # 98 - 9f
2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7
2, 2, 2, 2, 2, 2, 2, 2, # a8 - af
2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7
2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf
2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7
2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf
2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7
2, 2, 2, 2, 2, 2, 2, 2, # d8 - df
2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7
2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef
2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7
2, 2, 2, 2, 2, 2, 2, 2, # f8 - ff
)
ISO2022JP_ST = (
MachineState.START, 3,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,# 00-07
MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 08-0f
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,# 10-17
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,# 18-1f
MachineState.ERROR, 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 4,MachineState.ERROR,MachineState.ERROR,# 20-27
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 6,MachineState.ITS_ME,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,# 28-2f
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,# 30-37
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 38-3f
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,MachineState.START,MachineState.START,# 40-47
MachineState.START, 3, MachineState.ERROR, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 00-07
MachineState.START, MachineState.START, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 08-0f
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 10-17
MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, # 18-1f
MachineState.ERROR, 5, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 4, MachineState.ERROR, MachineState.ERROR, # 20-27
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 6, MachineState.ITS_ME, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, # 28-2f
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, # 30-37
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 38-3f
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.START, MachineState.START, # 40-47
)
# fmt: on
ISO2022JP_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
ISO2022JP_SM_MODEL = {'class_table': ISO2022JP_CLS,
'class_factor': 10,
'state_table': ISO2022JP_ST,
'char_len_table': ISO2022JP_CHAR_LEN_TABLE,
'name': "ISO-2022-JP",
'language': 'Japanese'}
ISO2022JP_SM_MODEL: CodingStateMachineDict = {
"class_table": ISO2022JP_CLS,
"class_factor": 10,
"state_table": ISO2022JP_ST,
"char_len_table": ISO2022JP_CHAR_LEN_TABLE,
"name": "ISO-2022-JP",
"language": "Japanese",
}
# fmt: off
ISO2022KR_CLS = (
2,0,0,0,0,0,0,0, # 00 - 07
0,0,0,0,0,0,0,0, # 08 - 0f
0,0,0,0,0,0,0,0, # 10 - 17
0,0,0,1,0,0,0,0, # 18 - 1f
0,0,0,0,3,0,0,0, # 20 - 27
0,4,0,0,0,0,0,0, # 28 - 2f
0,0,0,0,0,0,0,0, # 30 - 37
0,0,0,0,0,0,0,0, # 38 - 3f
0,0,0,5,0,0,0,0, # 40 - 47
0,0,0,0,0,0,0,0, # 48 - 4f
0,0,0,0,0,0,0,0, # 50 - 57
0,0,0,0,0,0,0,0, # 58 - 5f
0,0,0,0,0,0,0,0, # 60 - 67
0,0,0,0,0,0,0,0, # 68 - 6f
0,0,0,0,0,0,0,0, # 70 - 77
0,0,0,0,0,0,0,0, # 78 - 7f
2,2,2,2,2,2,2,2, # 80 - 87
2,2,2,2,2,2,2,2, # 88 - 8f
2,2,2,2,2,2,2,2, # 90 - 97
2,2,2,2,2,2,2,2, # 98 - 9f
2,2,2,2,2,2,2,2, # a0 - a7
2,2,2,2,2,2,2,2, # a8 - af
2,2,2,2,2,2,2,2, # b0 - b7
2,2,2,2,2,2,2,2, # b8 - bf
2,2,2,2,2,2,2,2, # c0 - c7
2,2,2,2,2,2,2,2, # c8 - cf
2,2,2,2,2,2,2,2, # d0 - d7
2,2,2,2,2,2,2,2, # d8 - df
2,2,2,2,2,2,2,2, # e0 - e7
2,2,2,2,2,2,2,2, # e8 - ef
2,2,2,2,2,2,2,2, # f0 - f7
2,2,2,2,2,2,2,2, # f8 - ff
2, 0, 0, 0, 0, 0, 0, 0, # 00 - 07
0, 0, 0, 0, 0, 0, 0, 0, # 08 - 0f
0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17
0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f
0, 0, 0, 0, 3, 0, 0, 0, # 20 - 27
0, 4, 0, 0, 0, 0, 0, 0, # 28 - 2f
0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37
0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f
0, 0, 0, 5, 0, 0, 0, 0, # 40 - 47
0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f
0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57
0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f
0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67
0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f
0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77
0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f
2, 2, 2, 2, 2, 2, 2, 2, # 80 - 87
2, 2, 2, 2, 2, 2, 2, 2, # 88 - 8f
2, 2, 2, 2, 2, 2, 2, 2, # 90 - 97
2, 2, 2, 2, 2, 2, 2, 2, # 98 - 9f
2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7
2, 2, 2, 2, 2, 2, 2, 2, # a8 - af
2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7
2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf
2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7
2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf
2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7
2, 2, 2, 2, 2, 2, 2, 2, # d8 - df
2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7
2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef
2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7
2, 2, 2, 2, 2, 2, 2, 2, # f8 - ff
)
ISO2022KR_ST = (
MachineState.START, 3,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,# 00-07
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,# 08-0f
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 4,MachineState.ERROR,MachineState.ERROR,# 10-17
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,# 18-1f
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.START,MachineState.START,MachineState.START,MachineState.START,# 20-27
MachineState.START, 3, MachineState.ERROR, MachineState.START, MachineState.START, MachineState.START, MachineState.ERROR, MachineState.ERROR, # 00-07
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 08-0f
MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 4, MachineState.ERROR, MachineState.ERROR, # 10-17
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 5, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 18-1f
MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 20-27
)
# fmt: on
ISO2022KR_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0)
ISO2022KR_SM_MODEL = {'class_table': ISO2022KR_CLS,
'class_factor': 6,
'state_table': ISO2022KR_ST,
'char_len_table': ISO2022KR_CHAR_LEN_TABLE,
'name': "ISO-2022-KR",
'language': 'Korean'}
ISO2022KR_SM_MODEL: CodingStateMachineDict = {
"class_table": ISO2022KR_CLS,
"class_factor": 6,
"state_table": ISO2022KR_ST,
"char_len_table": ISO2022KR_CHAR_LEN_TABLE,
"name": "ISO-2022-KR",
"language": "Korean",
}

60
venv/Lib/site-packages/pip/_vendor/chardet/eucjpprober.py
View File

@@ -25,68 +25,78 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .enums import ProbingState, MachineState
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from typing import Union
from .chardistribution import EUCJPDistributionAnalysis
from .codingstatemachine import CodingStateMachine
from .enums import MachineState, ProbingState
from .jpcntx import EUCJPContextAnalysis
from .mbcharsetprober import MultiByteCharSetProber
from .mbcssm import EUCJP_SM_MODEL
class EUCJPProber(MultiByteCharSetProber):
def __init__(self):
super(EUCJPProber, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL)
self.distribution_analyzer = EUCJPDistributionAnalysis()
self.context_analyzer = EUCJPContextAnalysis()
self.reset()
def reset(self):
super(EUCJPProber, self).reset()
def reset(self) -> None:
super().reset()
self.context_analyzer.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "EUC-JP"
@property
def language(self):
def language(self) -> str:
return "Japanese"
def feed(self, byte_str):
for i in range(len(byte_str)):
# PY3K: byte_str is a byte array, so byte_str[i] is an int, not a byte
coding_state = self.coding_sm.next_state(byte_str[i])
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
assert self.coding_sm is not None
assert self.distribution_analyzer is not None
for i, byte in enumerate(byte_str):
# PY3K: byte_str is a byte array, so byte is an int, not a byte
coding_state = self.coding_sm.next_state(byte)
if coding_state == MachineState.ERROR:
self.logger.debug('%s %s prober hit error at byte %s',
self.charset_name, self.language, i)
self.logger.debug(
"%s %s prober hit error at byte %s",
self.charset_name,
self.language,
i,
)
self._state = ProbingState.NOT_ME
break
elif coding_state == MachineState.ITS_ME:
if coding_state == MachineState.ITS_ME:
self._state = ProbingState.FOUND_IT
break
elif coding_state == MachineState.START:
if coding_state == MachineState.START:
char_len = self.coding_sm.get_current_charlen()
if i == 0:
self._last_char[1] = byte_str[0]
self._last_char[1] = byte
self.context_analyzer.feed(self._last_char, char_len)
self.distribution_analyzer.feed(self._last_char, char_len)
else:
self.context_analyzer.feed(byte_str[i - 1:i + 1],
char_len)
self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
char_len)
self.context_analyzer.feed(byte_str[i - 1 : i + 1], char_len)
self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len)
self._last_char[0] = byte_str[-1]
if self.state == ProbingState.DETECTING:
if (self.context_analyzer.got_enough_data() and
(self.get_confidence() > self.SHORTCUT_THRESHOLD)):
if self.context_analyzer.got_enough_data() and (
self.get_confidence() > self.SHORTCUT_THRESHOLD
):
self._state = ProbingState.FOUND_IT
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
assert self.distribution_analyzer is not None
context_conf = self.context_analyzer.get_confidence()
distrib_conf = self.distribution_analyzer.get_confidence()
return max(context_conf, distrib_conf)

3
venv/Lib/site-packages/pip/_vendor/chardet/euckrfreq.py
View File

@@ -43,6 +43,7 @@ EUCKR_TYPICAL_DISTRIBUTION_RATIO = 6.0
EUCKR_TABLE_SIZE = 2352
# Char to FreqOrder table ,
# fmt: off
EUCKR_CHAR_TO_FREQ_ORDER = (
13, 130, 120,1396, 481,1719,1720, 328, 609, 212,1721, 707, 400, 299,1722, 87,
1397,1723, 104, 536,1117,1203,1724,1267, 685,1268, 508,1725,1726,1727,1728,1398,
@@ -192,4 +193,4 @@ EUCKR_CHAR_TO_FREQ_ORDER = (
2629,2630,2631, 924, 648, 863, 603,2632,2633, 934,1540, 864, 865,2634, 642,1042,
670,1190,2635,2636,2637,2638, 168,2639, 652, 873, 542,1054,1541,2640,2641,2642, # 512, 256
)
# fmt: on

12
venv/Lib/site-packages/pip/_vendor/chardet/euckrprober.py
View File

@@ -25,23 +25,23 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from .chardistribution import EUCKRDistributionAnalysis
from .codingstatemachine import CodingStateMachine
from .mbcharsetprober import MultiByteCharSetProber
from .mbcssm import EUCKR_SM_MODEL
class EUCKRProber(MultiByteCharSetProber):
def __init__(self):
super(EUCKRProber, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(EUCKR_SM_MODEL)
self.distribution_analyzer = EUCKRDistributionAnalysis()
self.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "EUC-KR"
@property
def language(self):
def language(self) -> str:
return "Korean"

677
venv/Lib/site-packages/pip/_vendor/chardet/euctwfreq.py
View File

@@ -43,345 +43,346 @@
EUCTW_TYPICAL_DISTRIBUTION_RATIO = 0.75
# Char to FreqOrder table ,
# Char to FreqOrder table
EUCTW_TABLE_SIZE = 5376
# fmt: off
EUCTW_CHAR_TO_FREQ_ORDER = (
1,1800,1506, 255,1431, 198, 9, 82, 6,7310, 177, 202,3615,1256,2808, 110, # 2742
3735, 33,3241, 261, 76, 44,2113, 16,2931,2184,1176, 659,3868, 26,3404,2643, # 2758
1198,3869,3313,4060, 410,2211, 302, 590, 361,1963, 8, 204, 58,4296,7311,1931, # 2774
63,7312,7313, 317,1614, 75, 222, 159,4061,2412,1480,7314,3500,3068, 224,2809, # 2790
3616, 3, 10,3870,1471, 29,2774,1135,2852,1939, 873, 130,3242,1123, 312,7315, # 2806
4297,2051, 507, 252, 682,7316, 142,1914, 124, 206,2932, 34,3501,3173, 64, 604, # 2822
7317,2494,1976,1977, 155,1990, 645, 641,1606,7318,3405, 337, 72, 406,7319, 80, # 2838
630, 238,3174,1509, 263, 939,1092,2644, 756,1440,1094,3406, 449, 69,2969, 591, # 2854
179,2095, 471, 115,2034,1843, 60, 50,2970, 134, 806,1868, 734,2035,3407, 180, # 2870
995,1607, 156, 537,2893, 688,7320, 319,1305, 779,2144, 514,2374, 298,4298, 359, # 2886
2495, 90,2707,1338, 663, 11, 906,1099,2545, 20,2436, 182, 532,1716,7321, 732, # 2902
1376,4062,1311,1420,3175, 25,2312,1056, 113, 399, 382,1949, 242,3408,2467, 529, # 2918
3243, 475,1447,3617,7322, 117, 21, 656, 810,1297,2295,2329,3502,7323, 126,4063, # 2934
706, 456, 150, 613,4299, 71,1118,2036,4064, 145,3069, 85, 835, 486,2114,1246, # 2950
1426, 428, 727,1285,1015, 800, 106, 623, 303,1281,7324,2127,2354, 347,3736, 221, # 2966
3503,3110,7325,1955,1153,4065, 83, 296,1199,3070, 192, 624, 93,7326, 822,1897, # 2982
2810,3111, 795,2064, 991,1554,1542,1592, 27, 43,2853, 859, 139,1456, 860,4300, # 2998
437, 712,3871, 164,2392,3112, 695, 211,3017,2096, 195,3872,1608,3504,3505,3618, # 3014
3873, 234, 811,2971,2097,3874,2229,1441,3506,1615,2375, 668,2076,1638, 305, 228, # 3030
1664,4301, 467, 415,7327, 262,2098,1593, 239, 108, 300, 200,1033, 512,1247,2077, # 3046
7328,7329,2173,3176,3619,2673, 593, 845,1062,3244, 88,1723,2037,3875,1950, 212, # 3062
266, 152, 149, 468,1898,4066,4302, 77, 187,7330,3018, 37, 5,2972,7331,3876, # 3078
7332,7333, 39,2517,4303,2894,3177,2078, 55, 148, 74,4304, 545, 483,1474,1029, # 3094
1665, 217,1869,1531,3113,1104,2645,4067, 24, 172,3507, 900,3877,3508,3509,4305, # 3110
32,1408,2811,1312, 329, 487,2355,2247,2708, 784,2674, 4,3019,3314,1427,1788, # 3126
188, 109, 499,7334,3620,1717,1789, 888,1217,3020,4306,7335,3510,7336,3315,1520, # 3142
3621,3878, 196,1034, 775,7337,7338, 929,1815, 249, 439, 38,7339,1063,7340, 794, # 3158
3879,1435,2296, 46, 178,3245,2065,7341,2376,7342, 214,1709,4307, 804, 35, 707, # 3174
324,3622,1601,2546, 140, 459,4068,7343,7344,1365, 839, 272, 978,2257,2572,3409, # 3190
2128,1363,3623,1423, 697, 100,3071, 48, 70,1231, 495,3114,2193,7345,1294,7346, # 3206
2079, 462, 586,1042,3246, 853, 256, 988, 185,2377,3410,1698, 434,1084,7347,3411, # 3222
314,2615,2775,4308,2330,2331, 569,2280, 637,1816,2518, 757,1162,1878,1616,3412, # 3238
287,1577,2115, 768,4309,1671,2854,3511,2519,1321,3737, 909,2413,7348,4069, 933, # 3254
3738,7349,2052,2356,1222,4310, 765,2414,1322, 786,4311,7350,1919,1462,1677,2895, # 3270
1699,7351,4312,1424,2437,3115,3624,2590,3316,1774,1940,3413,3880,4070, 309,1369, # 3286
1130,2812, 364,2230,1653,1299,3881,3512,3882,3883,2646, 525,1085,3021, 902,2000, # 3302
1475, 964,4313, 421,1844,1415,1057,2281, 940,1364,3116, 376,4314,4315,1381, 7, # 3318
2520, 983,2378, 336,1710,2675,1845, 321,3414, 559,1131,3022,2742,1808,1132,1313, # 3334
265,1481,1857,7352, 352,1203,2813,3247, 167,1089, 420,2814, 776, 792,1724,3513, # 3350
4071,2438,3248,7353,4072,7354, 446, 229, 333,2743, 901,3739,1200,1557,4316,2647, # 3366
1920, 395,2744,2676,3740,4073,1835, 125, 916,3178,2616,4317,7355,7356,3741,7357, # 3382
7358,7359,4318,3117,3625,1133,2547,1757,3415,1510,2313,1409,3514,7360,2145, 438, # 3398
2591,2896,2379,3317,1068, 958,3023, 461, 311,2855,2677,4074,1915,3179,4075,1978, # 3414
383, 750,2745,2617,4076, 274, 539, 385,1278,1442,7361,1154,1964, 384, 561, 210, # 3430
98,1295,2548,3515,7362,1711,2415,1482,3416,3884,2897,1257, 129,7363,3742, 642, # 3446
523,2776,2777,2648,7364, 141,2231,1333, 68, 176, 441, 876, 907,4077, 603,2592, # 3462
710, 171,3417, 404, 549, 18,3118,2393,1410,3626,1666,7365,3516,4319,2898,4320, # 3478
7366,2973, 368,7367, 146, 366, 99, 871,3627,1543, 748, 807,1586,1185, 22,2258, # 3494
379,3743,3180,7368,3181, 505,1941,2618,1991,1382,2314,7369, 380,2357, 218, 702, # 3510
1817,1248,3418,3024,3517,3318,3249,7370,2974,3628, 930,3250,3744,7371, 59,7372, # 3526
585, 601,4078, 497,3419,1112,1314,4321,1801,7373,1223,1472,2174,7374, 749,1836, # 3542
690,1899,3745,1772,3885,1476, 429,1043,1790,2232,2116, 917,4079, 447,1086,1629, # 3558
7375, 556,7376,7377,2020,1654, 844,1090, 105, 550, 966,1758,2815,1008,1782, 686, # 3574
1095,7378,2282, 793,1602,7379,3518,2593,4322,4080,2933,2297,4323,3746, 980,2496, # 3590
544, 353, 527,4324, 908,2678,2899,7380, 381,2619,1942,1348,7381,1341,1252, 560, # 3606
3072,7382,3420,2856,7383,2053, 973, 886,2080, 143,4325,7384,7385, 157,3886, 496, # 3622
4081, 57, 840, 540,2038,4326,4327,3421,2117,1445, 970,2259,1748,1965,2081,4082, # 3638
3119,1234,1775,3251,2816,3629, 773,1206,2129,1066,2039,1326,3887,1738,1725,4083, # 3654
279,3120, 51,1544,2594, 423,1578,2130,2066, 173,4328,1879,7386,7387,1583, 264, # 3670
610,3630,4329,2439, 280, 154,7388,7389,7390,1739, 338,1282,3073, 693,2857,1411, # 3686
1074,3747,2440,7391,4330,7392,7393,1240, 952,2394,7394,2900,1538,2679, 685,1483, # 3702
4084,2468,1436, 953,4085,2054,4331, 671,2395, 79,4086,2441,3252, 608, 567,2680, # 3718
3422,4087,4088,1691, 393,1261,1791,2396,7395,4332,7396,7397,7398,7399,1383,1672, # 3734
3748,3182,1464, 522,1119, 661,1150, 216, 675,4333,3888,1432,3519, 609,4334,2681, # 3750
2397,7400,7401,7402,4089,3025, 0,7403,2469, 315, 231,2442, 301,3319,4335,2380, # 3766
7404, 233,4090,3631,1818,4336,4337,7405, 96,1776,1315,2082,7406, 257,7407,1809, # 3782
3632,2709,1139,1819,4091,2021,1124,2163,2778,1777,2649,7408,3074, 363,1655,3183, # 3798
7409,2975,7410,7411,7412,3889,1567,3890, 718, 103,3184, 849,1443, 341,3320,2934, # 3814
1484,7413,1712, 127, 67, 339,4092,2398, 679,1412, 821,7414,7415, 834, 738, 351, # 3830
2976,2146, 846, 235,1497,1880, 418,1992,3749,2710, 186,1100,2147,2746,3520,1545, # 3846
1355,2935,2858,1377, 583,3891,4093,2573,2977,7416,1298,3633,1078,2549,3634,2358, # 3862
78,3750,3751, 267,1289,2099,2001,1594,4094, 348, 369,1274,2194,2175,1837,4338, # 3878
1820,2817,3635,2747,2283,2002,4339,2936,2748, 144,3321, 882,4340,3892,2749,3423, # 3894
4341,2901,7417,4095,1726, 320,7418,3893,3026, 788,2978,7419,2818,1773,1327,2859, # 3910
3894,2819,7420,1306,4342,2003,1700,3752,3521,2359,2650, 787,2022, 506, 824,3636, # 3926
534, 323,4343,1044,3322,2023,1900, 946,3424,7421,1778,1500,1678,7422,1881,4344, # 3942
165, 243,4345,3637,2521, 123, 683,4096, 764,4346, 36,3895,1792, 589,2902, 816, # 3958
626,1667,3027,2233,1639,1555,1622,3753,3896,7423,3897,2860,1370,1228,1932, 891, # 3974
2083,2903, 304,4097,7424, 292,2979,2711,3522, 691,2100,4098,1115,4347, 118, 662, # 3990
7425, 611,1156, 854,2381,1316,2861, 2, 386, 515,2904,7426,7427,3253, 868,2234, # 4006
1486, 855,2651, 785,2212,3028,7428,1040,3185,3523,7429,3121, 448,7430,1525,7431, # 4022
2164,4348,7432,3754,7433,4099,2820,3524,3122, 503, 818,3898,3123,1568, 814, 676, # 4038
1444, 306,1749,7434,3755,1416,1030, 197,1428, 805,2821,1501,4349,7435,7436,7437, # 4054
1993,7438,4350,7439,7440,2195, 13,2779,3638,2980,3124,1229,1916,7441,3756,2131, # 4070
7442,4100,4351,2399,3525,7443,2213,1511,1727,1120,7444,7445, 646,3757,2443, 307, # 4086
7446,7447,1595,3186,7448,7449,7450,3639,1113,1356,3899,1465,2522,2523,7451, 519, # 4102
7452, 128,2132, 92,2284,1979,7453,3900,1512, 342,3125,2196,7454,2780,2214,1980, # 4118
3323,7455, 290,1656,1317, 789, 827,2360,7456,3758,4352, 562, 581,3901,7457, 401, # 4134
4353,2248, 94,4354,1399,2781,7458,1463,2024,4355,3187,1943,7459, 828,1105,4101, # 4150
1262,1394,7460,4102, 605,4356,7461,1783,2862,7462,2822, 819,2101, 578,2197,2937, # 4166
7463,1502, 436,3254,4103,3255,2823,3902,2905,3425,3426,7464,2712,2315,7465,7466, # 4182
2332,2067, 23,4357, 193, 826,3759,2102, 699,1630,4104,3075, 390,1793,1064,3526, # 4198
7467,1579,3076,3077,1400,7468,4105,1838,1640,2863,7469,4358,4359, 137,4106, 598, # 4214
3078,1966, 780, 104, 974,2938,7470, 278, 899, 253, 402, 572, 504, 493,1339,7471, # 4230
3903,1275,4360,2574,2550,7472,3640,3029,3079,2249, 565,1334,2713, 863, 41,7473, # 4246
7474,4361,7475,1657,2333, 19, 463,2750,4107, 606,7476,2981,3256,1087,2084,1323, # 4262
2652,2982,7477,1631,1623,1750,4108,2682,7478,2864, 791,2714,2653,2334, 232,2416, # 4278
7479,2983,1498,7480,2654,2620, 755,1366,3641,3257,3126,2025,1609, 119,1917,3427, # 4294
862,1026,4109,7481,3904,3760,4362,3905,4363,2260,1951,2470,7482,1125, 817,4110, # 4310
4111,3906,1513,1766,2040,1487,4112,3030,3258,2824,3761,3127,7483,7484,1507,7485, # 4326
2683, 733, 40,1632,1106,2865, 345,4113, 841,2524, 230,4364,2984,1846,3259,3428, # 4342
7486,1263, 986,3429,7487, 735, 879, 254,1137, 857, 622,1300,1180,1388,1562,3907, # 4358
3908,2939, 967,2751,2655,1349, 592,2133,1692,3324,2985,1994,4114,1679,3909,1901, # 4374
2185,7488, 739,3642,2715,1296,1290,7489,4115,2198,2199,1921,1563,2595,2551,1870, # 4390
2752,2986,7490, 435,7491, 343,1108, 596, 17,1751,4365,2235,3430,3643,7492,4366, # 4406
294,3527,2940,1693, 477, 979, 281,2041,3528, 643,2042,3644,2621,2782,2261,1031, # 4422
2335,2134,2298,3529,4367, 367,1249,2552,7493,3530,7494,4368,1283,3325,2004, 240, # 4438
1762,3326,4369,4370, 836,1069,3128, 474,7495,2148,2525, 268,3531,7496,3188,1521, # 4454
1284,7497,1658,1546,4116,7498,3532,3533,7499,4117,3327,2684,1685,4118, 961,1673, # 4470
2622, 190,2005,2200,3762,4371,4372,7500, 570,2497,3645,1490,7501,4373,2623,3260, # 4486
1956,4374, 584,1514, 396,1045,1944,7502,4375,1967,2444,7503,7504,4376,3910, 619, # 4502
7505,3129,3261, 215,2006,2783,2553,3189,4377,3190,4378, 763,4119,3763,4379,7506, # 4518
7507,1957,1767,2941,3328,3646,1174, 452,1477,4380,3329,3130,7508,2825,1253,2382, # 4534
2186,1091,2285,4120, 492,7509, 638,1169,1824,2135,1752,3911, 648, 926,1021,1324, # 4550
4381, 520,4382, 997, 847,1007, 892,4383,3764,2262,1871,3647,7510,2400,1784,4384, # 4566
1952,2942,3080,3191,1728,4121,2043,3648,4385,2007,1701,3131,1551, 30,2263,4122, # 4582
7511,2026,4386,3534,7512, 501,7513,4123, 594,3431,2165,1821,3535,3432,3536,3192, # 4598
829,2826,4124,7514,1680,3132,1225,4125,7515,3262,4387,4126,3133,2336,7516,4388, # 4614
4127,7517,3912,3913,7518,1847,2383,2596,3330,7519,4389, 374,3914, 652,4128,4129, # 4630
375,1140, 798,7520,7521,7522,2361,4390,2264, 546,1659, 138,3031,2445,4391,7523, # 4646
2250, 612,1848, 910, 796,3765,1740,1371, 825,3766,3767,7524,2906,2554,7525, 692, # 4662
444,3032,2624, 801,4392,4130,7526,1491, 244,1053,3033,4131,4132, 340,7527,3915, # 4678
1041,2987, 293,1168, 87,1357,7528,1539, 959,7529,2236, 721, 694,4133,3768, 219, # 4694
1478, 644,1417,3331,2656,1413,1401,1335,1389,3916,7530,7531,2988,2362,3134,1825, # 4710
730,1515, 184,2827, 66,4393,7532,1660,2943, 246,3332, 378,1457, 226,3433, 975, # 4726
3917,2944,1264,3537, 674, 696,7533, 163,7534,1141,2417,2166, 713,3538,3333,4394, # 4742
3918,7535,7536,1186, 15,7537,1079,1070,7538,1522,3193,3539, 276,1050,2716, 758, # 4758
1126, 653,2945,3263,7539,2337, 889,3540,3919,3081,2989, 903,1250,4395,3920,3434, # 4774
3541,1342,1681,1718, 766,3264, 286, 89,2946,3649,7540,1713,7541,2597,3334,2990, # 4790
7542,2947,2215,3194,2866,7543,4396,2498,2526, 181, 387,1075,3921, 731,2187,3335, # 4806
7544,3265, 310, 313,3435,2299, 770,4134, 54,3034, 189,4397,3082,3769,3922,7545, # 4822
1230,1617,1849, 355,3542,4135,4398,3336, 111,4136,3650,1350,3135,3436,3035,4137, # 4838
2149,3266,3543,7546,2784,3923,3924,2991, 722,2008,7547,1071, 247,1207,2338,2471, # 4854
1378,4399,2009, 864,1437,1214,4400, 373,3770,1142,2216, 667,4401, 442,2753,2555, # 4870
3771,3925,1968,4138,3267,1839, 837, 170,1107, 934,1336,1882,7548,7549,2118,4139, # 4886
2828, 743,1569,7550,4402,4140, 582,2384,1418,3437,7551,1802,7552, 357,1395,1729, # 4902
3651,3268,2418,1564,2237,7553,3083,3772,1633,4403,1114,2085,4141,1532,7554, 482, # 4918
2446,4404,7555,7556,1492, 833,1466,7557,2717,3544,1641,2829,7558,1526,1272,3652, # 4934
4142,1686,1794, 416,2556,1902,1953,1803,7559,3773,2785,3774,1159,2316,7560,2867, # 4950
4405,1610,1584,3036,2419,2754, 443,3269,1163,3136,7561,7562,3926,7563,4143,2499, # 4966
3037,4406,3927,3137,2103,1647,3545,2010,1872,4144,7564,4145, 431,3438,7565, 250, # 4982
97, 81,4146,7566,1648,1850,1558, 160, 848,7567, 866, 740,1694,7568,2201,2830, # 4998
3195,4147,4407,3653,1687, 950,2472, 426, 469,3196,3654,3655,3928,7569,7570,1188, # 5014
424,1995, 861,3546,4148,3775,2202,2685, 168,1235,3547,4149,7571,2086,1674,4408, # 5030
3337,3270, 220,2557,1009,7572,3776, 670,2992, 332,1208, 717,7573,7574,3548,2447, # 5046
3929,3338,7575, 513,7576,1209,2868,3339,3138,4409,1080,7577,7578,7579,7580,2527, # 5062
3656,3549, 815,1587,3930,3931,7581,3550,3439,3777,1254,4410,1328,3038,1390,3932, # 5078
1741,3933,3778,3934,7582, 236,3779,2448,3271,7583,7584,3657,3780,1273,3781,4411, # 5094
7585, 308,7586,4412, 245,4413,1851,2473,1307,2575, 430, 715,2136,2449,7587, 270, # 5110
199,2869,3935,7588,3551,2718,1753, 761,1754, 725,1661,1840,4414,3440,3658,7589, # 5126
7590, 587, 14,3272, 227,2598, 326, 480,2265, 943,2755,3552, 291, 650,1883,7591, # 5142
1702,1226, 102,1547, 62,3441, 904,4415,3442,1164,4150,7592,7593,1224,1548,2756, # 5158
391, 498,1493,7594,1386,1419,7595,2055,1177,4416, 813, 880,1081,2363, 566,1145, # 5174
4417,2286,1001,1035,2558,2599,2238, 394,1286,7596,7597,2068,7598, 86,1494,1730, # 5190
3936, 491,1588, 745, 897,2948, 843,3340,3937,2757,2870,3273,1768, 998,2217,2069, # 5206
397,1826,1195,1969,3659,2993,3341, 284,7599,3782,2500,2137,2119,1903,7600,3938, # 5222
2150,3939,4151,1036,3443,1904, 114,2559,4152, 209,1527,7601,7602,2949,2831,2625, # 5238
2385,2719,3139, 812,2560,7603,3274,7604,1559, 737,1884,3660,1210, 885, 28,2686, # 5254
3553,3783,7605,4153,1004,1779,4418,7606, 346,1981,2218,2687,4419,3784,1742, 797, # 5270
1642,3940,1933,1072,1384,2151, 896,3941,3275,3661,3197,2871,3554,7607,2561,1958, # 5286
4420,2450,1785,7608,7609,7610,3942,4154,1005,1308,3662,4155,2720,4421,4422,1528, # 5302
2600, 161,1178,4156,1982, 987,4423,1101,4157, 631,3943,1157,3198,2420,1343,1241, # 5318
1016,2239,2562, 372, 877,2339,2501,1160, 555,1934, 911,3944,7611, 466,1170, 169, # 5334
1051,2907,2688,3663,2474,2994,1182,2011,2563,1251,2626,7612, 992,2340,3444,1540, # 5350
2721,1201,2070,2401,1996,2475,7613,4424, 528,1922,2188,1503,1873,1570,2364,3342, # 5366
3276,7614, 557,1073,7615,1827,3445,2087,2266,3140,3039,3084, 767,3085,2786,4425, # 5382
1006,4158,4426,2341,1267,2176,3664,3199, 778,3945,3200,2722,1597,2657,7616,4427, # 5398
7617,3446,7618,7619,7620,3277,2689,1433,3278, 131, 95,1504,3946, 723,4159,3141, # 5414
1841,3555,2758,2189,3947,2027,2104,3665,7621,2995,3948,1218,7622,3343,3201,3949, # 5430
4160,2576, 248,1634,3785, 912,7623,2832,3666,3040,3786, 654, 53,7624,2996,7625, # 5446
1688,4428, 777,3447,1032,3950,1425,7626, 191, 820,2120,2833, 971,4429, 931,3202, # 5462
135, 664, 783,3787,1997, 772,2908,1935,3951,3788,4430,2909,3203, 282,2723, 640, # 5478
1372,3448,1127, 922, 325,3344,7627,7628, 711,2044,7629,7630,3952,2219,2787,1936, # 5494
3953,3345,2220,2251,3789,2300,7631,4431,3790,1258,3279,3954,3204,2138,2950,3955, # 5510
3956,7632,2221, 258,3205,4432, 101,1227,7633,3280,1755,7634,1391,3281,7635,2910, # 5526
2056, 893,7636,7637,7638,1402,4161,2342,7639,7640,3206,3556,7641,7642, 878,1325, # 5542
1780,2788,4433, 259,1385,2577, 744,1183,2267,4434,7643,3957,2502,7644, 684,1024, # 5558
4162,7645, 472,3557,3449,1165,3282,3958,3959, 322,2152, 881, 455,1695,1152,1340, # 5574
660, 554,2153,4435,1058,4436,4163, 830,1065,3346,3960,4437,1923,7646,1703,1918, # 5590
7647, 932,2268, 122,7648,4438, 947, 677,7649,3791,2627, 297,1905,1924,2269,4439, # 5606
2317,3283,7650,7651,4164,7652,4165, 84,4166, 112, 989,7653, 547,1059,3961, 701, # 5622
3558,1019,7654,4167,7655,3450, 942, 639, 457,2301,2451, 993,2951, 407, 851, 494, # 5638
4440,3347, 927,7656,1237,7657,2421,3348, 573,4168, 680, 921,2911,1279,1874, 285, # 5654
790,1448,1983, 719,2167,7658,7659,4441,3962,3963,1649,7660,1541, 563,7661,1077, # 5670
7662,3349,3041,3451, 511,2997,3964,3965,3667,3966,1268,2564,3350,3207,4442,4443, # 5686
7663, 535,1048,1276,1189,2912,2028,3142,1438,1373,2834,2952,1134,2012,7664,4169, # 5702
1238,2578,3086,1259,7665, 700,7666,2953,3143,3668,4170,7667,4171,1146,1875,1906, # 5718
4444,2601,3967, 781,2422, 132,1589, 203, 147, 273,2789,2402, 898,1786,2154,3968, # 5734
3969,7668,3792,2790,7669,7670,4445,4446,7671,3208,7672,1635,3793, 965,7673,1804, # 5750
2690,1516,3559,1121,1082,1329,3284,3970,1449,3794, 65,1128,2835,2913,2759,1590, # 5766
3795,7674,7675, 12,2658, 45, 976,2579,3144,4447, 517,2528,1013,1037,3209,7676, # 5782
3796,2836,7677,3797,7678,3452,7679,2602, 614,1998,2318,3798,3087,2724,2628,7680, # 5798
2580,4172, 599,1269,7681,1810,3669,7682,2691,3088, 759,1060, 489,1805,3351,3285, # 5814
1358,7683,7684,2386,1387,1215,2629,2252, 490,7685,7686,4173,1759,2387,2343,7687, # 5830
4448,3799,1907,3971,2630,1806,3210,4449,3453,3286,2760,2344, 874,7688,7689,3454, # 5846
3670,1858, 91,2914,3671,3042,3800,4450,7690,3145,3972,2659,7691,3455,1202,1403, # 5862
3801,2954,2529,1517,2503,4451,3456,2504,7692,4452,7693,2692,1885,1495,1731,3973, # 5878
2365,4453,7694,2029,7695,7696,3974,2693,1216, 237,2581,4174,2319,3975,3802,4454, # 5894
4455,2694,3560,3457, 445,4456,7697,7698,7699,7700,2761, 61,3976,3672,1822,3977, # 5910
7701, 687,2045, 935, 925, 405,2660, 703,1096,1859,2725,4457,3978,1876,1367,2695, # 5926
3352, 918,2105,1781,2476, 334,3287,1611,1093,4458, 564,3146,3458,3673,3353, 945, # 5942
2631,2057,4459,7702,1925, 872,4175,7703,3459,2696,3089, 349,4176,3674,3979,4460, # 5958
3803,4177,3675,2155,3980,4461,4462,4178,4463,2403,2046, 782,3981, 400, 251,4179, # 5974
1624,7704,7705, 277,3676, 299,1265, 476,1191,3804,2121,4180,4181,1109, 205,7706, # 5990
2582,1000,2156,3561,1860,7707,7708,7709,4464,7710,4465,2565, 107,2477,2157,3982, # 6006
3460,3147,7711,1533, 541,1301, 158, 753,4182,2872,3562,7712,1696, 370,1088,4183, # 6022
4466,3563, 579, 327, 440, 162,2240, 269,1937,1374,3461, 968,3043, 56,1396,3090, # 6038
2106,3288,3354,7713,1926,2158,4467,2998,7714,3564,7715,7716,3677,4468,2478,7717, # 6054
2791,7718,1650,4469,7719,2603,7720,7721,3983,2661,3355,1149,3356,3984,3805,3985, # 6070
7722,1076, 49,7723, 951,3211,3289,3290, 450,2837, 920,7724,1811,2792,2366,4184, # 6086
1908,1138,2367,3806,3462,7725,3212,4470,1909,1147,1518,2423,4471,3807,7726,4472, # 6102
2388,2604, 260,1795,3213,7727,7728,3808,3291, 708,7729,3565,1704,7730,3566,1351, # 6118
1618,3357,2999,1886, 944,4185,3358,4186,3044,3359,4187,7731,3678, 422, 413,1714, # 6134
3292, 500,2058,2345,4188,2479,7732,1344,1910, 954,7733,1668,7734,7735,3986,2404, # 6150
4189,3567,3809,4190,7736,2302,1318,2505,3091, 133,3092,2873,4473, 629, 31,2838, # 6166
2697,3810,4474, 850, 949,4475,3987,2955,1732,2088,4191,1496,1852,7737,3988, 620, # 6182
3214, 981,1242,3679,3360,1619,3680,1643,3293,2139,2452,1970,1719,3463,2168,7738, # 6198
3215,7739,7740,3361,1828,7741,1277,4476,1565,2047,7742,1636,3568,3093,7743, 869, # 6214
2839, 655,3811,3812,3094,3989,3000,3813,1310,3569,4477,7744,7745,7746,1733, 558, # 6230
4478,3681, 335,1549,3045,1756,4192,3682,1945,3464,1829,1291,1192, 470,2726,2107, # 6246
2793, 913,1054,3990,7747,1027,7748,3046,3991,4479, 982,2662,3362,3148,3465,3216, # 6262
3217,1946,2794,7749, 571,4480,7750,1830,7751,3570,2583,1523,2424,7752,2089, 984, # 6278
4481,3683,1959,7753,3684, 852, 923,2795,3466,3685, 969,1519, 999,2048,2320,1705, # 6294
7754,3095, 615,1662, 151, 597,3992,2405,2321,1049, 275,4482,3686,4193, 568,3687, # 6310
3571,2480,4194,3688,7755,2425,2270, 409,3218,7756,1566,2874,3467,1002, 769,2840, # 6326
194,2090,3149,3689,2222,3294,4195, 628,1505,7757,7758,1763,2177,3001,3993, 521, # 6342
1161,2584,1787,2203,2406,4483,3994,1625,4196,4197, 412, 42,3096, 464,7759,2632, # 6358
4484,3363,1760,1571,2875,3468,2530,1219,2204,3814,2633,2140,2368,4485,4486,3295, # 6374
1651,3364,3572,7760,7761,3573,2481,3469,7762,3690,7763,7764,2271,2091, 460,7765, # 6390
4487,7766,3002, 962, 588,3574, 289,3219,2634,1116, 52,7767,3047,1796,7768,7769, # 6406
7770,1467,7771,1598,1143,3691,4198,1984,1734,1067,4488,1280,3365, 465,4489,1572, # 6422
510,7772,1927,2241,1812,1644,3575,7773,4490,3692,7774,7775,2663,1573,1534,7776, # 6438
7777,4199, 536,1807,1761,3470,3815,3150,2635,7778,7779,7780,4491,3471,2915,1911, # 6454
2796,7781,3296,1122, 377,3220,7782, 360,7783,7784,4200,1529, 551,7785,2059,3693, # 6470
1769,2426,7786,2916,4201,3297,3097,2322,2108,2030,4492,1404, 136,1468,1479, 672, # 6486
1171,3221,2303, 271,3151,7787,2762,7788,2049, 678,2727, 865,1947,4493,7789,2013, # 6502
3995,2956,7790,2728,2223,1397,3048,3694,4494,4495,1735,2917,3366,3576,7791,3816, # 6518
509,2841,2453,2876,3817,7792,7793,3152,3153,4496,4202,2531,4497,2304,1166,1010, # 6534
552, 681,1887,7794,7795,2957,2958,3996,1287,1596,1861,3154, 358, 453, 736, 175, # 6550
478,1117, 905,1167,1097,7796,1853,1530,7797,1706,7798,2178,3472,2287,3695,3473, # 6566
3577,4203,2092,4204,7799,3367,1193,2482,4205,1458,2190,2205,1862,1888,1421,3298, # 6582
2918,3049,2179,3474, 595,2122,7800,3997,7801,7802,4206,1707,2636, 223,3696,1359, # 6598
751,3098, 183,3475,7803,2797,3003, 419,2369, 633, 704,3818,2389, 241,7804,7805, # 6614
7806, 838,3004,3697,2272,2763,2454,3819,1938,2050,3998,1309,3099,2242,1181,7807, # 6630
1136,2206,3820,2370,1446,4207,2305,4498,7808,7809,4208,1055,2605, 484,3698,7810, # 6646
3999, 625,4209,2273,3368,1499,4210,4000,7811,4001,4211,3222,2274,2275,3476,7812, # 6662
7813,2764, 808,2606,3699,3369,4002,4212,3100,2532, 526,3370,3821,4213, 955,7814, # 6678
1620,4214,2637,2427,7815,1429,3700,1669,1831, 994, 928,7816,3578,1260,7817,7818, # 6694
7819,1948,2288, 741,2919,1626,4215,2729,2455, 867,1184, 362,3371,1392,7820,7821, # 6710
4003,4216,1770,1736,3223,2920,4499,4500,1928,2698,1459,1158,7822,3050,3372,2877, # 6726
1292,1929,2506,2842,3701,1985,1187,2071,2014,2607,4217,7823,2566,2507,2169,3702, # 6742
2483,3299,7824,3703,4501,7825,7826, 666,1003,3005,1022,3579,4218,7827,4502,1813, # 6758
2253, 574,3822,1603, 295,1535, 705,3823,4219, 283, 858, 417,7828,7829,3224,4503, # 6774
4504,3051,1220,1889,1046,2276,2456,4004,1393,1599, 689,2567, 388,4220,7830,2484, # 6790
802,7831,2798,3824,2060,1405,2254,7832,4505,3825,2109,1052,1345,3225,1585,7833, # 6806
809,7834,7835,7836, 575,2730,3477, 956,1552,1469,1144,2323,7837,2324,1560,2457, # 6822
3580,3226,4005, 616,2207,3155,2180,2289,7838,1832,7839,3478,4506,7840,1319,3704, # 6838
3705,1211,3581,1023,3227,1293,2799,7841,7842,7843,3826, 607,2306,3827, 762,2878, # 6854
1439,4221,1360,7844,1485,3052,7845,4507,1038,4222,1450,2061,2638,4223,1379,4508, # 6870
2585,7846,7847,4224,1352,1414,2325,2921,1172,7848,7849,3828,3829,7850,1797,1451, # 6886
7851,7852,7853,7854,2922,4006,4007,2485,2346, 411,4008,4009,3582,3300,3101,4509, # 6902
1561,2664,1452,4010,1375,7855,7856, 47,2959, 316,7857,1406,1591,2923,3156,7858, # 6918
1025,2141,3102,3157, 354,2731, 884,2224,4225,2407, 508,3706, 726,3583, 996,2428, # 6934
3584, 729,7859, 392,2191,1453,4011,4510,3707,7860,7861,2458,3585,2608,1675,2800, # 6950
919,2347,2960,2348,1270,4511,4012, 73,7862,7863, 647,7864,3228,2843,2255,1550, # 6966
1346,3006,7865,1332, 883,3479,7866,7867,7868,7869,3301,2765,7870,1212, 831,1347, # 6982
4226,4512,2326,3830,1863,3053, 720,3831,4513,4514,3832,7871,4227,7872,7873,4515, # 6998
7874,7875,1798,4516,3708,2609,4517,3586,1645,2371,7876,7877,2924, 669,2208,2665, # 7014
2429,7878,2879,7879,7880,1028,3229,7881,4228,2408,7882,2256,1353,7883,7884,4518, # 7030
3158, 518,7885,4013,7886,4229,1960,7887,2142,4230,7888,7889,3007,2349,2350,3833, # 7046
516,1833,1454,4014,2699,4231,4519,2225,2610,1971,1129,3587,7890,2766,7891,2961, # 7062
1422, 577,1470,3008,1524,3373,7892,7893, 432,4232,3054,3480,7894,2586,1455,2508, # 7078
2226,1972,1175,7895,1020,2732,4015,3481,4520,7896,2733,7897,1743,1361,3055,3482, # 7094
2639,4016,4233,4521,2290, 895, 924,4234,2170, 331,2243,3056, 166,1627,3057,1098, # 7110
7898,1232,2880,2227,3374,4522, 657, 403,1196,2372, 542,3709,3375,1600,4235,3483, # 7126
7899,4523,2767,3230, 576, 530,1362,7900,4524,2533,2666,3710,4017,7901, 842,3834, # 7142
7902,2801,2031,1014,4018, 213,2700,3376, 665, 621,4236,7903,3711,2925,2430,7904, # 7158
2431,3302,3588,3377,7905,4237,2534,4238,4525,3589,1682,4239,3484,1380,7906, 724, # 7174
2277, 600,1670,7907,1337,1233,4526,3103,2244,7908,1621,4527,7909, 651,4240,7910, # 7190
1612,4241,2611,7911,2844,7912,2734,2307,3058,7913, 716,2459,3059, 174,1255,2701, # 7206
4019,3590, 548,1320,1398, 728,4020,1574,7914,1890,1197,3060,4021,7915,3061,3062, # 7222
3712,3591,3713, 747,7916, 635,4242,4528,7917,7918,7919,4243,7920,7921,4529,7922, # 7238
3378,4530,2432, 451,7923,3714,2535,2072,4244,2735,4245,4022,7924,1764,4531,7925, # 7254
4246, 350,7926,2278,2390,2486,7927,4247,4023,2245,1434,4024, 488,4532, 458,4248, # 7270
4025,3715, 771,1330,2391,3835,2568,3159,2159,2409,1553,2667,3160,4249,7928,2487, # 7286
2881,2612,1720,2702,4250,3379,4533,7929,2536,4251,7930,3231,4252,2768,7931,2015, # 7302
2736,7932,1155,1017,3716,3836,7933,3303,2308, 201,1864,4253,1430,7934,4026,7935, # 7318
7936,7937,7938,7939,4254,1604,7940, 414,1865, 371,2587,4534,4535,3485,2016,3104, # 7334
4536,1708, 960,4255, 887, 389,2171,1536,1663,1721,7941,2228,4027,2351,2926,1580, # 7350
7942,7943,7944,1744,7945,2537,4537,4538,7946,4539,7947,2073,7948,7949,3592,3380, # 7366
2882,4256,7950,4257,2640,3381,2802, 673,2703,2460, 709,3486,4028,3593,4258,7951, # 7382
1148, 502, 634,7952,7953,1204,4540,3594,1575,4541,2613,3717,7954,3718,3105, 948, # 7398
3232, 121,1745,3837,1110,7955,4259,3063,2509,3009,4029,3719,1151,1771,3838,1488, # 7414
4030,1986,7956,2433,3487,7957,7958,2093,7959,4260,3839,1213,1407,2803, 531,2737, # 7430
2538,3233,1011,1537,7960,2769,4261,3106,1061,7961,3720,3721,1866,2883,7962,2017, # 7446
120,4262,4263,2062,3595,3234,2309,3840,2668,3382,1954,4542,7963,7964,3488,1047, # 7462
2704,1266,7965,1368,4543,2845, 649,3383,3841,2539,2738,1102,2846,2669,7966,7967, # 7478
1999,7968,1111,3596,2962,7969,2488,3842,3597,2804,1854,3384,3722,7970,7971,3385, # 7494
2410,2884,3304,3235,3598,7972,2569,7973,3599,2805,4031,1460, 856,7974,3600,7975, # 7510
2885,2963,7976,2886,3843,7977,4264, 632,2510, 875,3844,1697,3845,2291,7978,7979, # 7526
4544,3010,1239, 580,4545,4265,7980, 914, 936,2074,1190,4032,1039,2123,7981,7982, # 7542
7983,3386,1473,7984,1354,4266,3846,7985,2172,3064,4033, 915,3305,4267,4268,3306, # 7558
1605,1834,7986,2739, 398,3601,4269,3847,4034, 328,1912,2847,4035,3848,1331,4270, # 7574
3011, 937,4271,7987,3602,4036,4037,3387,2160,4546,3388, 524, 742, 538,3065,1012, # 7590
7988,7989,3849,2461,7990, 658,1103, 225,3850,7991,7992,4547,7993,4548,7994,3236, # 7606
1243,7995,4038, 963,2246,4549,7996,2705,3603,3161,7997,7998,2588,2327,7999,4550, # 7622
8000,8001,8002,3489,3307, 957,3389,2540,2032,1930,2927,2462, 870,2018,3604,1746, # 7638
2770,2771,2434,2463,8003,3851,8004,3723,3107,3724,3490,3390,3725,8005,1179,3066, # 7654
8006,3162,2373,4272,3726,2541,3163,3108,2740,4039,8007,3391,1556,2542,2292, 977, # 7670
2887,2033,4040,1205,3392,8008,1765,3393,3164,2124,1271,1689, 714,4551,3491,8009, # 7686
2328,3852, 533,4273,3605,2181, 617,8010,2464,3308,3492,2310,8011,8012,3165,8013, # 7702
8014,3853,1987, 618, 427,2641,3493,3394,8015,8016,1244,1690,8017,2806,4274,4552, # 7718
8018,3494,8019,8020,2279,1576, 473,3606,4275,3395, 972,8021,3607,8022,3067,8023, # 7734
8024,4553,4554,8025,3727,4041,4042,8026, 153,4555, 356,8027,1891,2888,4276,2143, # 7750
408, 803,2352,8028,3854,8029,4277,1646,2570,2511,4556,4557,3855,8030,3856,4278, # 7766
8031,2411,3396, 752,8032,8033,1961,2964,8034, 746,3012,2465,8035,4279,3728, 698, # 7782
4558,1892,4280,3608,2543,4559,3609,3857,8036,3166,3397,8037,1823,1302,4043,2706, # 7798
3858,1973,4281,8038,4282,3167, 823,1303,1288,1236,2848,3495,4044,3398, 774,3859, # 7814
8039,1581,4560,1304,2849,3860,4561,8040,2435,2161,1083,3237,4283,4045,4284, 344, # 7830
1173, 288,2311, 454,1683,8041,8042,1461,4562,4046,2589,8043,8044,4563, 985, 894, # 7846
8045,3399,3168,8046,1913,2928,3729,1988,8047,2110,1974,8048,4047,8049,2571,1194, # 7862
425,8050,4564,3169,1245,3730,4285,8051,8052,2850,8053, 636,4565,1855,3861, 760, # 7878
1799,8054,4286,2209,1508,4566,4048,1893,1684,2293,8055,8056,8057,4287,4288,2210, # 7894
479,8058,8059, 832,8060,4049,2489,8061,2965,2490,3731, 990,3109, 627,1814,2642, # 7910
4289,1582,4290,2125,2111,3496,4567,8062, 799,4291,3170,8063,4568,2112,1737,3013, # 7926
1018, 543, 754,4292,3309,1676,4569,4570,4050,8064,1489,8065,3497,8066,2614,2889, # 7942
4051,8067,8068,2966,8069,8070,8071,8072,3171,4571,4572,2182,1722,8073,3238,3239, # 7958
1842,3610,1715, 481, 365,1975,1856,8074,8075,1962,2491,4573,8076,2126,3611,3240, # 7974
433,1894,2063,2075,8077, 602,2741,8078,8079,8080,8081,8082,3014,1628,3400,8083, # 7990
3172,4574,4052,2890,4575,2512,8084,2544,2772,8085,8086,8087,3310,4576,2891,8088, # 8006
4577,8089,2851,4578,4579,1221,2967,4053,2513,8090,8091,8092,1867,1989,8093,8094, # 8022
8095,1895,8096,8097,4580,1896,4054, 318,8098,2094,4055,4293,8099,8100, 485,8101, # 8038
938,3862, 553,2670, 116,8102,3863,3612,8103,3498,2671,2773,3401,3311,2807,8104, # 8054
3613,2929,4056,1747,2930,2968,8105,8106, 207,8107,8108,2672,4581,2514,8109,3015, # 8070
890,3614,3864,8110,1877,3732,3402,8111,2183,2353,3403,1652,8112,8113,8114, 941, # 8086
2294, 208,3499,4057,2019, 330,4294,3865,2892,2492,3733,4295,8115,8116,8117,8118, # 8102
1, 1800, 1506, 255, 1431, 198, 9, 82, 6, 7310, 177, 202, 3615, 1256, 2808, 110, # 2742
3735, 33, 3241, 261, 76, 44, 2113, 16, 2931, 2184, 1176, 659, 3868, 26, 3404, 2643, # 2758
1198, 3869, 3313, 4060, 410, 2211, 302, 590, 361, 1963, 8, 204, 58, 4296, 7311, 1931, # 2774
63, 7312, 7313, 317, 1614, 75, 222, 159, 4061, 2412, 1480, 7314, 3500, 3068, 224, 2809, # 2790
3616, 3, 10, 3870, 1471, 29, 2774, 1135, 2852, 1939, 873, 130, 3242, 1123, 312, 7315, # 2806
4297, 2051, 507, 252, 682, 7316, 142, 1914, 124, 206, 2932, 34, 3501, 3173, 64, 604, # 2822
7317, 2494, 1976, 1977, 155, 1990, 645, 641, 1606, 7318, 3405, 337, 72, 406, 7319, 80, # 2838
630, 238, 3174, 1509, 263, 939, 1092, 2644, 756, 1440, 1094, 3406, 449, 69, 2969, 591, # 2854
179, 2095, 471, 115, 2034, 1843, 60, 50, 2970, 134, 806, 1868, 734, 2035, 3407, 180, # 2870
995, 1607, 156, 537, 2893, 688, 7320, 319, 1305, 779, 2144, 514, 2374, 298, 4298, 359, # 2886
2495, 90, 2707, 1338, 663, 11, 906, 1099, 2545, 20, 2436, 182, 532, 1716, 7321, 732, # 2902
1376, 4062, 1311, 1420, 3175, 25, 2312, 1056, 113, 399, 382, 1949, 242, 3408, 2467, 529, # 2918
3243, 475, 1447, 3617, 7322, 117, 21, 656, 810, 1297, 2295, 2329, 3502, 7323, 126, 4063, # 2934
706, 456, 150, 613, 4299, 71, 1118, 2036, 4064, 145, 3069, 85, 835, 486, 2114, 1246, # 2950
1426, 428, 727, 1285, 1015, 800, 106, 623, 303, 1281, 7324, 2127, 2354, 347, 3736, 221, # 2966
3503, 3110, 7325, 1955, 1153, 4065, 83, 296, 1199, 3070, 192, 624, 93, 7326, 822, 1897, # 2982
2810, 3111, 795, 2064, 991, 1554, 1542, 1592, 27, 43, 2853, 859, 139, 1456, 860, 4300, # 2998
437, 712, 3871, 164, 2392, 3112, 695, 211, 3017, 2096, 195, 3872, 1608, 3504, 3505, 3618, # 3014
3873, 234, 811, 2971, 2097, 3874, 2229, 1441, 3506, 1615, 2375, 668, 2076, 1638, 305, 228, # 3030
1664, 4301, 467, 415, 7327, 262, 2098, 1593, 239, 108, 300, 200, 1033, 512, 1247, 2077, # 3046
7328, 7329, 2173, 3176, 3619, 2673, 593, 845, 1062, 3244, 88, 1723, 2037, 3875, 1950, 212, # 3062
266, 152, 149, 468, 1898, 4066, 4302, 77, 187, 7330, 3018, 37, 5, 2972, 7331, 3876, # 3078
7332, 7333, 39, 2517, 4303, 2894, 3177, 2078, 55, 148, 74, 4304, 545, 483, 1474, 1029, # 3094
1665, 217, 1869, 1531, 3113, 1104, 2645, 4067, 24, 172, 3507, 900, 3877, 3508, 3509, 4305, # 3110
32, 1408, 2811, 1312, 329, 487, 2355, 2247, 2708, 784, 2674, 4, 3019, 3314, 1427, 1788, # 3126
188, 109, 499, 7334, 3620, 1717, 1789, 888, 1217, 3020, 4306, 7335, 3510, 7336, 3315, 1520, # 3142
3621, 3878, 196, 1034, 775, 7337, 7338, 929, 1815, 249, 439, 38, 7339, 1063, 7340, 794, # 3158
3879, 1435, 2296, 46, 178, 3245, 2065, 7341, 2376, 7342, 214, 1709, 4307, 804, 35, 707, # 3174
324, 3622, 1601, 2546, 140, 459, 4068, 7343, 7344, 1365, 839, 272, 978, 2257, 2572, 3409, # 3190
2128, 1363, 3623, 1423, 697, 100, 3071, 48, 70, 1231, 495, 3114, 2193, 7345, 1294, 7346, # 3206
2079, 462, 586, 1042, 3246, 853, 256, 988, 185, 2377, 3410, 1698, 434, 1084, 7347, 3411, # 3222
314, 2615, 2775, 4308, 2330, 2331, 569, 2280, 637, 1816, 2518, 757, 1162, 1878, 1616, 3412, # 3238
287, 1577, 2115, 768, 4309, 1671, 2854, 3511, 2519, 1321, 3737, 909, 2413, 7348, 4069, 933, # 3254
3738, 7349, 2052, 2356, 1222, 4310, 765, 2414, 1322, 786, 4311, 7350, 1919, 1462, 1677, 2895, # 3270
1699, 7351, 4312, 1424, 2437, 3115, 3624, 2590, 3316, 1774, 1940, 3413, 3880, 4070, 309, 1369, # 3286
1130, 2812, 364, 2230, 1653, 1299, 3881, 3512, 3882, 3883, 2646, 525, 1085, 3021, 902, 2000, # 3302
1475, 964, 4313, 421, 1844, 1415, 1057, 2281, 940, 1364, 3116, 376, 4314, 4315, 1381, 7, # 3318
2520, 983, 2378, 336, 1710, 2675, 1845, 321, 3414, 559, 1131, 3022, 2742, 1808, 1132, 1313, # 3334
265, 1481, 1857, 7352, 352, 1203, 2813, 3247, 167, 1089, 420, 2814, 776, 792, 1724, 3513, # 3350
4071, 2438, 3248, 7353, 4072, 7354, 446, 229, 333, 2743, 901, 3739, 1200, 1557, 4316, 2647, # 3366
1920, 395, 2744, 2676, 3740, 4073, 1835, 125, 916, 3178, 2616, 4317, 7355, 7356, 3741, 7357, # 3382
7358, 7359, 4318, 3117, 3625, 1133, 2547, 1757, 3415, 1510, 2313, 1409, 3514, 7360, 2145, 438, # 3398
2591, 2896, 2379, 3317, 1068, 958, 3023, 461, 311, 2855, 2677, 4074, 1915, 3179, 4075, 1978, # 3414
383, 750, 2745, 2617, 4076, 274, 539, 385, 1278, 1442, 7361, 1154, 1964, 384, 561, 210, # 3430
98, 1295, 2548, 3515, 7362, 1711, 2415, 1482, 3416, 3884, 2897, 1257, 129, 7363, 3742, 642, # 3446
523, 2776, 2777, 2648, 7364, 141, 2231, 1333, 68, 176, 441, 876, 907, 4077, 603, 2592, # 3462
710, 171, 3417, 404, 549, 18, 3118, 2393, 1410, 3626, 1666, 7365, 3516, 4319, 2898, 4320, # 3478
7366, 2973, 368, 7367, 146, 366, 99, 871, 3627, 1543, 748, 807, 1586, 1185, 22, 2258, # 3494
379, 3743, 3180, 7368, 3181, 505, 1941, 2618, 1991, 1382, 2314, 7369, 380, 2357, 218, 702, # 3510
1817, 1248, 3418, 3024, 3517, 3318, 3249, 7370, 2974, 3628, 930, 3250, 3744, 7371, 59, 7372, # 3526
585, 601, 4078, 497, 3419, 1112, 1314, 4321, 1801, 7373, 1223, 1472, 2174, 7374, 749, 1836, # 3542
690, 1899, 3745, 1772, 3885, 1476, 429, 1043, 1790, 2232, 2116, 917, 4079, 447, 1086, 1629, # 3558
7375, 556, 7376, 7377, 2020, 1654, 844, 1090, 105, 550, 966, 1758, 2815, 1008, 1782, 686, # 3574
1095, 7378, 2282, 793, 1602, 7379, 3518, 2593, 4322, 4080, 2933, 2297, 4323, 3746, 980, 2496, # 3590
544, 353, 527, 4324, 908, 2678, 2899, 7380, 381, 2619, 1942, 1348, 7381, 1341, 1252, 560, # 3606
3072, 7382, 3420, 2856, 7383, 2053, 973, 886, 2080, 143, 4325, 7384, 7385, 157, 3886, 496, # 3622
4081, 57, 840, 540, 2038, 4326, 4327, 3421, 2117, 1445, 970, 2259, 1748, 1965, 2081, 4082, # 3638
3119, 1234, 1775, 3251, 2816, 3629, 773, 1206, 2129, 1066, 2039, 1326, 3887, 1738, 1725, 4083, # 3654
279, 3120, 51, 1544, 2594, 423, 1578, 2130, 2066, 173, 4328, 1879, 7386, 7387, 1583, 264, # 3670
610, 3630, 4329, 2439, 280, 154, 7388, 7389, 7390, 1739, 338, 1282, 3073, 693, 2857, 1411, # 3686
1074, 3747, 2440, 7391, 4330, 7392, 7393, 1240, 952, 2394, 7394, 2900, 1538, 2679, 685, 1483, # 3702
4084, 2468, 1436, 953, 4085, 2054, 4331, 671, 2395, 79, 4086, 2441, 3252, 608, 567, 2680, # 3718
3422, 4087, 4088, 1691, 393, 1261, 1791, 2396, 7395, 4332, 7396, 7397, 7398, 7399, 1383, 1672, # 3734
3748, 3182, 1464, 522, 1119, 661, 1150, 216, 675, 4333, 3888, 1432, 3519, 609, 4334, 2681, # 3750
2397, 7400, 7401, 7402, 4089, 3025, 0, 7403, 2469, 315, 231, 2442, 301, 3319, 4335, 2380, # 3766
7404, 233, 4090, 3631, 1818, 4336, 4337, 7405, 96, 1776, 1315, 2082, 7406, 257, 7407, 1809, # 3782
3632, 2709, 1139, 1819, 4091, 2021, 1124, 2163, 2778, 1777, 2649, 7408, 3074, 363, 1655, 3183, # 3798
7409, 2975, 7410, 7411, 7412, 3889, 1567, 3890, 718, 103, 3184, 849, 1443, 341, 3320, 2934, # 3814
1484, 7413, 1712, 127, 67, 339, 4092, 2398, 679, 1412, 821, 7414, 7415, 834, 738, 351, # 3830
2976, 2146, 846, 235, 1497, 1880, 418, 1992, 3749, 2710, 186, 1100, 2147, 2746, 3520, 1545, # 3846
1355, 2935, 2858, 1377, 583, 3891, 4093, 2573, 2977, 7416, 1298, 3633, 1078, 2549, 3634, 2358, # 3862
78, 3750, 3751, 267, 1289, 2099, 2001, 1594, 4094, 348, 369, 1274, 2194, 2175, 1837, 4338, # 3878
1820, 2817, 3635, 2747, 2283, 2002, 4339, 2936, 2748, 144, 3321, 882, 4340, 3892, 2749, 3423, # 3894
4341, 2901, 7417, 4095, 1726, 320, 7418, 3893, 3026, 788, 2978, 7419, 2818, 1773, 1327, 2859, # 3910
3894, 2819, 7420, 1306, 4342, 2003, 1700, 3752, 3521, 2359, 2650, 787, 2022, 506, 824, 3636, # 3926
534, 323, 4343, 1044, 3322, 2023, 1900, 946, 3424, 7421, 1778, 1500, 1678, 7422, 1881, 4344, # 3942
165, 243, 4345, 3637, 2521, 123, 683, 4096, 764, 4346, 36, 3895, 1792, 589, 2902, 816, # 3958
626, 1667, 3027, 2233, 1639, 1555, 1622, 3753, 3896, 7423, 3897, 2860, 1370, 1228, 1932, 891, # 3974
2083, 2903, 304, 4097, 7424, 292, 2979, 2711, 3522, 691, 2100, 4098, 1115, 4347, 118, 662, # 3990
7425, 611, 1156, 854, 2381, 1316, 2861, 2, 386, 515, 2904, 7426, 7427, 3253, 868, 2234, # 4006
1486, 855, 2651, 785, 2212, 3028, 7428, 1040, 3185, 3523, 7429, 3121, 448, 7430, 1525, 7431, # 4022
2164, 4348, 7432, 3754, 7433, 4099, 2820, 3524, 3122, 503, 818, 3898, 3123, 1568, 814, 676, # 4038
1444, 306, 1749, 7434, 3755, 1416, 1030, 197, 1428, 805, 2821, 1501, 4349, 7435, 7436, 7437, # 4054
1993, 7438, 4350, 7439, 7440, 2195, 13, 2779, 3638, 2980, 3124, 1229, 1916, 7441, 3756, 2131, # 4070
7442, 4100, 4351, 2399, 3525, 7443, 2213, 1511, 1727, 1120, 7444, 7445, 646, 3757, 2443, 307, # 4086
7446, 7447, 1595, 3186, 7448, 7449, 7450, 3639, 1113, 1356, 3899, 1465, 2522, 2523, 7451, 519, # 4102
7452, 128, 2132, 92, 2284, 1979, 7453, 3900, 1512, 342, 3125, 2196, 7454, 2780, 2214, 1980, # 4118
3323, 7455, 290, 1656, 1317, 789, 827, 2360, 7456, 3758, 4352, 562, 581, 3901, 7457, 401, # 4134
4353, 2248, 94, 4354, 1399, 2781, 7458, 1463, 2024, 4355, 3187, 1943, 7459, 828, 1105, 4101, # 4150
1262, 1394, 7460, 4102, 605, 4356, 7461, 1783, 2862, 7462, 2822, 819, 2101, 578, 2197, 2937, # 4166
7463, 1502, 436, 3254, 4103, 3255, 2823, 3902, 2905, 3425, 3426, 7464, 2712, 2315, 7465, 7466, # 4182
2332, 2067, 23, 4357, 193, 826, 3759, 2102, 699, 1630, 4104, 3075, 390, 1793, 1064, 3526, # 4198
7467, 1579, 3076, 3077, 1400, 7468, 4105, 1838, 1640, 2863, 7469, 4358, 4359, 137, 4106, 598, # 4214
3078, 1966, 780, 104, 974, 2938, 7470, 278, 899, 253, 402, 572, 504, 493, 1339, 7471, # 4230
3903, 1275, 4360, 2574, 2550, 7472, 3640, 3029, 3079, 2249, 565, 1334, 2713, 863, 41, 7473, # 4246
7474, 4361, 7475, 1657, 2333, 19, 463, 2750, 4107, 606, 7476, 2981, 3256, 1087, 2084, 1323, # 4262
2652, 2982, 7477, 1631, 1623, 1750, 4108, 2682, 7478, 2864, 791, 2714, 2653, 2334, 232, 2416, # 4278
7479, 2983, 1498, 7480, 2654, 2620, 755, 1366, 3641, 3257, 3126, 2025, 1609, 119, 1917, 3427, # 4294
862, 1026, 4109, 7481, 3904, 3760, 4362, 3905, 4363, 2260, 1951, 2470, 7482, 1125, 817, 4110, # 4310
4111, 3906, 1513, 1766, 2040, 1487, 4112, 3030, 3258, 2824, 3761, 3127, 7483, 7484, 1507, 7485, # 4326
2683, 733, 40, 1632, 1106, 2865, 345, 4113, 841, 2524, 230, 4364, 2984, 1846, 3259, 3428, # 4342
7486, 1263, 986, 3429, 7487, 735, 879, 254, 1137, 857, 622, 1300, 1180, 1388, 1562, 3907, # 4358
3908, 2939, 967, 2751, 2655, 1349, 592, 2133, 1692, 3324, 2985, 1994, 4114, 1679, 3909, 1901, # 4374
2185, 7488, 739, 3642, 2715, 1296, 1290, 7489, 4115, 2198, 2199, 1921, 1563, 2595, 2551, 1870, # 4390
2752, 2986, 7490, 435, 7491, 343, 1108, 596, 17, 1751, 4365, 2235, 3430, 3643, 7492, 4366, # 4406
294, 3527, 2940, 1693, 477, 979, 281, 2041, 3528, 643, 2042, 3644, 2621, 2782, 2261, 1031, # 4422
2335, 2134, 2298, 3529, 4367, 367, 1249, 2552, 7493, 3530, 7494, 4368, 1283, 3325, 2004, 240, # 4438
1762, 3326, 4369, 4370, 836, 1069, 3128, 474, 7495, 2148, 2525, 268, 3531, 7496, 3188, 1521, # 4454
1284, 7497, 1658, 1546, 4116, 7498, 3532, 3533, 7499, 4117, 3327, 2684, 1685, 4118, 961, 1673, # 4470
2622, 190, 2005, 2200, 3762, 4371, 4372, 7500, 570, 2497, 3645, 1490, 7501, 4373, 2623, 3260, # 4486
1956, 4374, 584, 1514, 396, 1045, 1944, 7502, 4375, 1967, 2444, 7503, 7504, 4376, 3910, 619, # 4502
7505, 3129, 3261, 215, 2006, 2783, 2553, 3189, 4377, 3190, 4378, 763, 4119, 3763, 4379, 7506, # 4518
7507, 1957, 1767, 2941, 3328, 3646, 1174, 452, 1477, 4380, 3329, 3130, 7508, 2825, 1253, 2382, # 4534
2186, 1091, 2285, 4120, 492, 7509, 638, 1169, 1824, 2135, 1752, 3911, 648, 926, 1021, 1324, # 4550
4381, 520, 4382, 997, 847, 1007, 892, 4383, 3764, 2262, 1871, 3647, 7510, 2400, 1784, 4384, # 4566
1952, 2942, 3080, 3191, 1728, 4121, 2043, 3648, 4385, 2007, 1701, 3131, 1551, 30, 2263, 4122, # 4582
7511, 2026, 4386, 3534, 7512, 501, 7513, 4123, 594, 3431, 2165, 1821, 3535, 3432, 3536, 3192, # 4598
829, 2826, 4124, 7514, 1680, 3132, 1225, 4125, 7515, 3262, 4387, 4126, 3133, 2336, 7516, 4388, # 4614
4127, 7517, 3912, 3913, 7518, 1847, 2383, 2596, 3330, 7519, 4389, 374, 3914, 652, 4128, 4129, # 4630
375, 1140, 798, 7520, 7521, 7522, 2361, 4390, 2264, 546, 1659, 138, 3031, 2445, 4391, 7523, # 4646
2250, 612, 1848, 910, 796, 3765, 1740, 1371, 825, 3766, 3767, 7524, 2906, 2554, 7525, 692, # 4662
444, 3032, 2624, 801, 4392, 4130, 7526, 1491, 244, 1053, 3033, 4131, 4132, 340, 7527, 3915, # 4678
1041, 2987, 293, 1168, 87, 1357, 7528, 1539, 959, 7529, 2236, 721, 694, 4133, 3768, 219, # 4694
1478, 644, 1417, 3331, 2656, 1413, 1401, 1335, 1389, 3916, 7530, 7531, 2988, 2362, 3134, 1825, # 4710
730, 1515, 184, 2827, 66, 4393, 7532, 1660, 2943, 246, 3332, 378, 1457, 226, 3433, 975, # 4726
3917, 2944, 1264, 3537, 674, 696, 7533, 163, 7534, 1141, 2417, 2166, 713, 3538, 3333, 4394, # 4742
3918, 7535, 7536, 1186, 15, 7537, 1079, 1070, 7538, 1522, 3193, 3539, 276, 1050, 2716, 758, # 4758
1126, 653, 2945, 3263, 7539, 2337, 889, 3540, 3919, 3081, 2989, 903, 1250, 4395, 3920, 3434, # 4774
3541, 1342, 1681, 1718, 766, 3264, 286, 89, 2946, 3649, 7540, 1713, 7541, 2597, 3334, 2990, # 4790
7542, 2947, 2215, 3194, 2866, 7543, 4396, 2498, 2526, 181, 387, 1075, 3921, 731, 2187, 3335, # 4806
7544, 3265, 310, 313, 3435, 2299, 770, 4134, 54, 3034, 189, 4397, 3082, 3769, 3922, 7545, # 4822
1230, 1617, 1849, 355, 3542, 4135, 4398, 3336, 111, 4136, 3650, 1350, 3135, 3436, 3035, 4137, # 4838
2149, 3266, 3543, 7546, 2784, 3923, 3924, 2991, 722, 2008, 7547, 1071, 247, 1207, 2338, 2471, # 4854
1378, 4399, 2009, 864, 1437, 1214, 4400, 373, 3770, 1142, 2216, 667, 4401, 442, 2753, 2555, # 4870
3771, 3925, 1968, 4138, 3267, 1839, 837, 170, 1107, 934, 1336, 1882, 7548, 7549, 2118, 4139, # 4886
2828, 743, 1569, 7550, 4402, 4140, 582, 2384, 1418, 3437, 7551, 1802, 7552, 357, 1395, 1729, # 4902
3651, 3268, 2418, 1564, 2237, 7553, 3083, 3772, 1633, 4403, 1114, 2085, 4141, 1532, 7554, 482, # 4918
2446, 4404, 7555, 7556, 1492, 833, 1466, 7557, 2717, 3544, 1641, 2829, 7558, 1526, 1272, 3652, # 4934
4142, 1686, 1794, 416, 2556, 1902, 1953, 1803, 7559, 3773, 2785, 3774, 1159, 2316, 7560, 2867, # 4950
4405, 1610, 1584, 3036, 2419, 2754, 443, 3269, 1163, 3136, 7561, 7562, 3926, 7563, 4143, 2499, # 4966
3037, 4406, 3927, 3137, 2103, 1647, 3545, 2010, 1872, 4144, 7564, 4145, 431, 3438, 7565, 250, # 4982
97, 81, 4146, 7566, 1648, 1850, 1558, 160, 848, 7567, 866, 740, 1694, 7568, 2201, 2830, # 4998
3195, 4147, 4407, 3653, 1687, 950, 2472, 426, 469, 3196, 3654, 3655, 3928, 7569, 7570, 1188, # 5014
424, 1995, 861, 3546, 4148, 3775, 2202, 2685, 168, 1235, 3547, 4149, 7571, 2086, 1674, 4408, # 5030
3337, 3270, 220, 2557, 1009, 7572, 3776, 670, 2992, 332, 1208, 717, 7573, 7574, 3548, 2447, # 5046
3929, 3338, 7575, 513, 7576, 1209, 2868, 3339, 3138, 4409, 1080, 7577, 7578, 7579, 7580, 2527, # 5062
3656, 3549, 815, 1587, 3930, 3931, 7581, 3550, 3439, 3777, 1254, 4410, 1328, 3038, 1390, 3932, # 5078
1741, 3933, 3778, 3934, 7582, 236, 3779, 2448, 3271, 7583, 7584, 3657, 3780, 1273, 3781, 4411, # 5094
7585, 308, 7586, 4412, 245, 4413, 1851, 2473, 1307, 2575, 430, 715, 2136, 2449, 7587, 270, # 5110
199, 2869, 3935, 7588, 3551, 2718, 1753, 761, 1754, 725, 1661, 1840, 4414, 3440, 3658, 7589, # 5126
7590, 587, 14, 3272, 227, 2598, 326, 480, 2265, 943, 2755, 3552, 291, 650, 1883, 7591, # 5142
1702, 1226, 102, 1547, 62, 3441, 904, 4415, 3442, 1164, 4150, 7592, 7593, 1224, 1548, 2756, # 5158
391, 498, 1493, 7594, 1386, 1419, 7595, 2055, 1177, 4416, 813, 880, 1081, 2363, 566, 1145, # 5174
4417, 2286, 1001, 1035, 2558, 2599, 2238, 394, 1286, 7596, 7597, 2068, 7598, 86, 1494, 1730, # 5190
3936, 491, 1588, 745, 897, 2948, 843, 3340, 3937, 2757, 2870, 3273, 1768, 998, 2217, 2069, # 5206
397, 1826, 1195, 1969, 3659, 2993, 3341, 284, 7599, 3782, 2500, 2137, 2119, 1903, 7600, 3938, # 5222
2150, 3939, 4151, 1036, 3443, 1904, 114, 2559, 4152, 209, 1527, 7601, 7602, 2949, 2831, 2625, # 5238
2385, 2719, 3139, 812, 2560, 7603, 3274, 7604, 1559, 737, 1884, 3660, 1210, 885, 28, 2686, # 5254
3553, 3783, 7605, 4153, 1004, 1779, 4418, 7606, 346, 1981, 2218, 2687, 4419, 3784, 1742, 797, # 5270
1642, 3940, 1933, 1072, 1384, 2151, 896, 3941, 3275, 3661, 3197, 2871, 3554, 7607, 2561, 1958, # 5286
4420, 2450, 1785, 7608, 7609, 7610, 3942, 4154, 1005, 1308, 3662, 4155, 2720, 4421, 4422, 1528, # 5302
2600, 161, 1178, 4156, 1982, 987, 4423, 1101, 4157, 631, 3943, 1157, 3198, 2420, 1343, 1241, # 5318
1016, 2239, 2562, 372, 877, 2339, 2501, 1160, 555, 1934, 911, 3944, 7611, 466, 1170, 169, # 5334
1051, 2907, 2688, 3663, 2474, 2994, 1182, 2011, 2563, 1251, 2626, 7612, 992, 2340, 3444, 1540, # 5350
2721, 1201, 2070, 2401, 1996, 2475, 7613, 4424, 528, 1922, 2188, 1503, 1873, 1570, 2364, 3342, # 5366
3276, 7614, 557, 1073, 7615, 1827, 3445, 2087, 2266, 3140, 3039, 3084, 767, 3085, 2786, 4425, # 5382
1006, 4158, 4426, 2341, 1267, 2176, 3664, 3199, 778, 3945, 3200, 2722, 1597, 2657, 7616, 4427, # 5398
7617, 3446, 7618, 7619, 7620, 3277, 2689, 1433, 3278, 131, 95, 1504, 3946, 723, 4159, 3141, # 5414
1841, 3555, 2758, 2189, 3947, 2027, 2104, 3665, 7621, 2995, 3948, 1218, 7622, 3343, 3201, 3949, # 5430
4160, 2576, 248, 1634, 3785, 912, 7623, 2832, 3666, 3040, 3786, 654, 53, 7624, 2996, 7625, # 5446
1688, 4428, 777, 3447, 1032, 3950, 1425, 7626, 191, 820, 2120, 2833, 971, 4429, 931, 3202, # 5462
135, 664, 783, 3787, 1997, 772, 2908, 1935, 3951, 3788, 4430, 2909, 3203, 282, 2723, 640, # 5478
1372, 3448, 1127, 922, 325, 3344, 7627, 7628, 711, 2044, 7629, 7630, 3952, 2219, 2787, 1936, # 5494
3953, 3345, 2220, 2251, 3789, 2300, 7631, 4431, 3790, 1258, 3279, 3954, 3204, 2138, 2950, 3955, # 5510
3956, 7632, 2221, 258, 3205, 4432, 101, 1227, 7633, 3280, 1755, 7634, 1391, 3281, 7635, 2910, # 5526
2056, 893, 7636, 7637, 7638, 1402, 4161, 2342, 7639, 7640, 3206, 3556, 7641, 7642, 878, 1325, # 5542
1780, 2788, 4433, 259, 1385, 2577, 744, 1183, 2267, 4434, 7643, 3957, 2502, 7644, 684, 1024, # 5558
4162, 7645, 472, 3557, 3449, 1165, 3282, 3958, 3959, 322, 2152, 881, 455, 1695, 1152, 1340, # 5574
660, 554, 2153, 4435, 1058, 4436, 4163, 830, 1065, 3346, 3960, 4437, 1923, 7646, 1703, 1918, # 5590
7647, 932, 2268, 122, 7648, 4438, 947, 677, 7649, 3791, 2627, 297, 1905, 1924, 2269, 4439, # 5606
2317, 3283, 7650, 7651, 4164, 7652, 4165, 84, 4166, 112, 989, 7653, 547, 1059, 3961, 701, # 5622
3558, 1019, 7654, 4167, 7655, 3450, 942, 639, 457, 2301, 2451, 993, 2951, 407, 851, 494, # 5638
4440, 3347, 927, 7656, 1237, 7657, 2421, 3348, 573, 4168, 680, 921, 2911, 1279, 1874, 285, # 5654
790, 1448, 1983, 719, 2167, 7658, 7659, 4441, 3962, 3963, 1649, 7660, 1541, 563, 7661, 1077, # 5670
7662, 3349, 3041, 3451, 511, 2997, 3964, 3965, 3667, 3966, 1268, 2564, 3350, 3207, 4442, 4443, # 5686
7663, 535, 1048, 1276, 1189, 2912, 2028, 3142, 1438, 1373, 2834, 2952, 1134, 2012, 7664, 4169, # 5702
1238, 2578, 3086, 1259, 7665, 700, 7666, 2953, 3143, 3668, 4170, 7667, 4171, 1146, 1875, 1906, # 5718
4444, 2601, 3967, 781, 2422, 132, 1589, 203, 147, 273, 2789, 2402, 898, 1786, 2154, 3968, # 5734
3969, 7668, 3792, 2790, 7669, 7670, 4445, 4446, 7671, 3208, 7672, 1635, 3793, 965, 7673, 1804, # 5750
2690, 1516, 3559, 1121, 1082, 1329, 3284, 3970, 1449, 3794, 65, 1128, 2835, 2913, 2759, 1590, # 5766
3795, 7674, 7675, 12, 2658, 45, 976, 2579, 3144, 4447, 517, 2528, 1013, 1037, 3209, 7676, # 5782
3796, 2836, 7677, 3797, 7678, 3452, 7679, 2602, 614, 1998, 2318, 3798, 3087, 2724, 2628, 7680, # 5798
2580, 4172, 599, 1269, 7681, 1810, 3669, 7682, 2691, 3088, 759, 1060, 489, 1805, 3351, 3285, # 5814
1358, 7683, 7684, 2386, 1387, 1215, 2629, 2252, 490, 7685, 7686, 4173, 1759, 2387, 2343, 7687, # 5830
4448, 3799, 1907, 3971, 2630, 1806, 3210, 4449, 3453, 3286, 2760, 2344, 874, 7688, 7689, 3454, # 5846
3670, 1858, 91, 2914, 3671, 3042, 3800, 4450, 7690, 3145, 3972, 2659, 7691, 3455, 1202, 1403, # 5862
3801, 2954, 2529, 1517, 2503, 4451, 3456, 2504, 7692, 4452, 7693, 2692, 1885, 1495, 1731, 3973, # 5878
2365, 4453, 7694, 2029, 7695, 7696, 3974, 2693, 1216, 237, 2581, 4174, 2319, 3975, 3802, 4454, # 5894
4455, 2694, 3560, 3457, 445, 4456, 7697, 7698, 7699, 7700, 2761, 61, 3976, 3672, 1822, 3977, # 5910
7701, 687, 2045, 935, 925, 405, 2660, 703, 1096, 1859, 2725, 4457, 3978, 1876, 1367, 2695, # 5926
3352, 918, 2105, 1781, 2476, 334, 3287, 1611, 1093, 4458, 564, 3146, 3458, 3673, 3353, 945, # 5942
2631, 2057, 4459, 7702, 1925, 872, 4175, 7703, 3459, 2696, 3089, 349, 4176, 3674, 3979, 4460, # 5958
3803, 4177, 3675, 2155, 3980, 4461, 4462, 4178, 4463, 2403, 2046, 782, 3981, 400, 251, 4179, # 5974
1624, 7704, 7705, 277, 3676, 299, 1265, 476, 1191, 3804, 2121, 4180, 4181, 1109, 205, 7706, # 5990
2582, 1000, 2156, 3561, 1860, 7707, 7708, 7709, 4464, 7710, 4465, 2565, 107, 2477, 2157, 3982, # 6006
3460, 3147, 7711, 1533, 541, 1301, 158, 753, 4182, 2872, 3562, 7712, 1696, 370, 1088, 4183, # 6022
4466, 3563, 579, 327, 440, 162, 2240, 269, 1937, 1374, 3461, 968, 3043, 56, 1396, 3090, # 6038
2106, 3288, 3354, 7713, 1926, 2158, 4467, 2998, 7714, 3564, 7715, 7716, 3677, 4468, 2478, 7717, # 6054
2791, 7718, 1650, 4469, 7719, 2603, 7720, 7721, 3983, 2661, 3355, 1149, 3356, 3984, 3805, 3985, # 6070
7722, 1076, 49, 7723, 951, 3211, 3289, 3290, 450, 2837, 920, 7724, 1811, 2792, 2366, 4184, # 6086
1908, 1138, 2367, 3806, 3462, 7725, 3212, 4470, 1909, 1147, 1518, 2423, 4471, 3807, 7726, 4472, # 6102
2388, 2604, 260, 1795, 3213, 7727, 7728, 3808, 3291, 708, 7729, 3565, 1704, 7730, 3566, 1351, # 6118
1618, 3357, 2999, 1886, 944, 4185, 3358, 4186, 3044, 3359, 4187, 7731, 3678, 422, 413, 1714, # 6134
3292, 500, 2058, 2345, 4188, 2479, 7732, 1344, 1910, 954, 7733, 1668, 7734, 7735, 3986, 2404, # 6150
4189, 3567, 3809, 4190, 7736, 2302, 1318, 2505, 3091, 133, 3092, 2873, 4473, 629, 31, 2838, # 6166
2697, 3810, 4474, 850, 949, 4475, 3987, 2955, 1732, 2088, 4191, 1496, 1852, 7737, 3988, 620, # 6182
3214, 981, 1242, 3679, 3360, 1619, 3680, 1643, 3293, 2139, 2452, 1970, 1719, 3463, 2168, 7738, # 6198
3215, 7739, 7740, 3361, 1828, 7741, 1277, 4476, 1565, 2047, 7742, 1636, 3568, 3093, 7743, 869, # 6214
2839, 655, 3811, 3812, 3094, 3989, 3000, 3813, 1310, 3569, 4477, 7744, 7745, 7746, 1733, 558, # 6230
4478, 3681, 335, 1549, 3045, 1756, 4192, 3682, 1945, 3464, 1829, 1291, 1192, 470, 2726, 2107, # 6246
2793, 913, 1054, 3990, 7747, 1027, 7748, 3046, 3991, 4479, 982, 2662, 3362, 3148, 3465, 3216, # 6262
3217, 1946, 2794, 7749, 571, 4480, 7750, 1830, 7751, 3570, 2583, 1523, 2424, 7752, 2089, 984, # 6278
4481, 3683, 1959, 7753, 3684, 852, 923, 2795, 3466, 3685, 969, 1519, 999, 2048, 2320, 1705, # 6294
7754, 3095, 615, 1662, 151, 597, 3992, 2405, 2321, 1049, 275, 4482, 3686, 4193, 568, 3687, # 6310
3571, 2480, 4194, 3688, 7755, 2425, 2270, 409, 3218, 7756, 1566, 2874, 3467, 1002, 769, 2840, # 6326
194, 2090, 3149, 3689, 2222, 3294, 4195, 628, 1505, 7757, 7758, 1763, 2177, 3001, 3993, 521, # 6342
1161, 2584, 1787, 2203, 2406, 4483, 3994, 1625, 4196, 4197, 412, 42, 3096, 464, 7759, 2632, # 6358
4484, 3363, 1760, 1571, 2875, 3468, 2530, 1219, 2204, 3814, 2633, 2140, 2368, 4485, 4486, 3295, # 6374
1651, 3364, 3572, 7760, 7761, 3573, 2481, 3469, 7762, 3690, 7763, 7764, 2271, 2091, 460, 7765, # 6390
4487, 7766, 3002, 962, 588, 3574, 289, 3219, 2634, 1116, 52, 7767, 3047, 1796, 7768, 7769, # 6406
7770, 1467, 7771, 1598, 1143, 3691, 4198, 1984, 1734, 1067, 4488, 1280, 3365, 465, 4489, 1572, # 6422
510, 7772, 1927, 2241, 1812, 1644, 3575, 7773, 4490, 3692, 7774, 7775, 2663, 1573, 1534, 7776, # 6438
7777, 4199, 536, 1807, 1761, 3470, 3815, 3150, 2635, 7778, 7779, 7780, 4491, 3471, 2915, 1911, # 6454
2796, 7781, 3296, 1122, 377, 3220, 7782, 360, 7783, 7784, 4200, 1529, 551, 7785, 2059, 3693, # 6470
1769, 2426, 7786, 2916, 4201, 3297, 3097, 2322, 2108, 2030, 4492, 1404, 136, 1468, 1479, 672, # 6486
1171, 3221, 2303, 271, 3151, 7787, 2762, 7788, 2049, 678, 2727, 865, 1947, 4493, 7789, 2013, # 6502
3995, 2956, 7790, 2728, 2223, 1397, 3048, 3694, 4494, 4495, 1735, 2917, 3366, 3576, 7791, 3816, # 6518
509, 2841, 2453, 2876, 3817, 7792, 7793, 3152, 3153, 4496, 4202, 2531, 4497, 2304, 1166, 1010, # 6534
552, 681, 1887, 7794, 7795, 2957, 2958, 3996, 1287, 1596, 1861, 3154, 358, 453, 736, 175, # 6550
478, 1117, 905, 1167, 1097, 7796, 1853, 1530, 7797, 1706, 7798, 2178, 3472, 2287, 3695, 3473, # 6566
3577, 4203, 2092, 4204, 7799, 3367, 1193, 2482, 4205, 1458, 2190, 2205, 1862, 1888, 1421, 3298, # 6582
2918, 3049, 2179, 3474, 595, 2122, 7800, 3997, 7801, 7802, 4206, 1707, 2636, 223, 3696, 1359, # 6598
751, 3098, 183, 3475, 7803, 2797, 3003, 419, 2369, 633, 704, 3818, 2389, 241, 7804, 7805, # 6614
7806, 838, 3004, 3697, 2272, 2763, 2454, 3819, 1938, 2050, 3998, 1309, 3099, 2242, 1181, 7807, # 6630
1136, 2206, 3820, 2370, 1446, 4207, 2305, 4498, 7808, 7809, 4208, 1055, 2605, 484, 3698, 7810, # 6646
3999, 625, 4209, 2273, 3368, 1499, 4210, 4000, 7811, 4001, 4211, 3222, 2274, 2275, 3476, 7812, # 6662
7813, 2764, 808, 2606, 3699, 3369, 4002, 4212, 3100, 2532, 526, 3370, 3821, 4213, 955, 7814, # 6678
1620, 4214, 2637, 2427, 7815, 1429, 3700, 1669, 1831, 994, 928, 7816, 3578, 1260, 7817, 7818, # 6694
7819, 1948, 2288, 741, 2919, 1626, 4215, 2729, 2455, 867, 1184, 362, 3371, 1392, 7820, 7821, # 6710
4003, 4216, 1770, 1736, 3223, 2920, 4499, 4500, 1928, 2698, 1459, 1158, 7822, 3050, 3372, 2877, # 6726
1292, 1929, 2506, 2842, 3701, 1985, 1187, 2071, 2014, 2607, 4217, 7823, 2566, 2507, 2169, 3702, # 6742
2483, 3299, 7824, 3703, 4501, 7825, 7826, 666, 1003, 3005, 1022, 3579, 4218, 7827, 4502, 1813, # 6758
2253, 574, 3822, 1603, 295, 1535, 705, 3823, 4219, 283, 858, 417, 7828, 7829, 3224, 4503, # 6774
4504, 3051, 1220, 1889, 1046, 2276, 2456, 4004, 1393, 1599, 689, 2567, 388, 4220, 7830, 2484, # 6790
802, 7831, 2798, 3824, 2060, 1405, 2254, 7832, 4505, 3825, 2109, 1052, 1345, 3225, 1585, 7833, # 6806
809, 7834, 7835, 7836, 575, 2730, 3477, 956, 1552, 1469, 1144, 2323, 7837, 2324, 1560, 2457, # 6822
3580, 3226, 4005, 616, 2207, 3155, 2180, 2289, 7838, 1832, 7839, 3478, 4506, 7840, 1319, 3704, # 6838
3705, 1211, 3581, 1023, 3227, 1293, 2799, 7841, 7842, 7843, 3826, 607, 2306, 3827, 762, 2878, # 6854
1439, 4221, 1360, 7844, 1485, 3052, 7845, 4507, 1038, 4222, 1450, 2061, 2638, 4223, 1379, 4508, # 6870
2585, 7846, 7847, 4224, 1352, 1414, 2325, 2921, 1172, 7848, 7849, 3828, 3829, 7850, 1797, 1451, # 6886
7851, 7852, 7853, 7854, 2922, 4006, 4007, 2485, 2346, 411, 4008, 4009, 3582, 3300, 3101, 4509, # 6902
1561, 2664, 1452, 4010, 1375, 7855, 7856, 47, 2959, 316, 7857, 1406, 1591, 2923, 3156, 7858, # 6918
1025, 2141, 3102, 3157, 354, 2731, 884, 2224, 4225, 2407, 508, 3706, 726, 3583, 996, 2428, # 6934
3584, 729, 7859, 392, 2191, 1453, 4011, 4510, 3707, 7860, 7861, 2458, 3585, 2608, 1675, 2800, # 6950
919, 2347, 2960, 2348, 1270, 4511, 4012, 73, 7862, 7863, 647, 7864, 3228, 2843, 2255, 1550, # 6966
1346, 3006, 7865, 1332, 883, 3479, 7866, 7867, 7868, 7869, 3301, 2765, 7870, 1212, 831, 1347, # 6982
4226, 4512, 2326, 3830, 1863, 3053, 720, 3831, 4513, 4514, 3832, 7871, 4227, 7872, 7873, 4515, # 6998
7874, 7875, 1798, 4516, 3708, 2609, 4517, 3586, 1645, 2371, 7876, 7877, 2924, 669, 2208, 2665, # 7014
2429, 7878, 2879, 7879, 7880, 1028, 3229, 7881, 4228, 2408, 7882, 2256, 1353, 7883, 7884, 4518, # 7030
3158, 518, 7885, 4013, 7886, 4229, 1960, 7887, 2142, 4230, 7888, 7889, 3007, 2349, 2350, 3833, # 7046
516, 1833, 1454, 4014, 2699, 4231, 4519, 2225, 2610, 1971, 1129, 3587, 7890, 2766, 7891, 2961, # 7062
1422, 577, 1470, 3008, 1524, 3373, 7892, 7893, 432, 4232, 3054, 3480, 7894, 2586, 1455, 2508, # 7078
2226, 1972, 1175, 7895, 1020, 2732, 4015, 3481, 4520, 7896, 2733, 7897, 1743, 1361, 3055, 3482, # 7094
2639, 4016, 4233, 4521, 2290, 895, 924, 4234, 2170, 331, 2243, 3056, 166, 1627, 3057, 1098, # 7110
7898, 1232, 2880, 2227, 3374, 4522, 657, 403, 1196, 2372, 542, 3709, 3375, 1600, 4235, 3483, # 7126
7899, 4523, 2767, 3230, 576, 530, 1362, 7900, 4524, 2533, 2666, 3710, 4017, 7901, 842, 3834, # 7142
7902, 2801, 2031, 1014, 4018, 213, 2700, 3376, 665, 621, 4236, 7903, 3711, 2925, 2430, 7904, # 7158
2431, 3302, 3588, 3377, 7905, 4237, 2534, 4238, 4525, 3589, 1682, 4239, 3484, 1380, 7906, 724, # 7174
2277, 600, 1670, 7907, 1337, 1233, 4526, 3103, 2244, 7908, 1621, 4527, 7909, 651, 4240, 7910, # 7190
1612, 4241, 2611, 7911, 2844, 7912, 2734, 2307, 3058, 7913, 716, 2459, 3059, 174, 1255, 2701, # 7206
4019, 3590, 548, 1320, 1398, 728, 4020, 1574, 7914, 1890, 1197, 3060, 4021, 7915, 3061, 3062, # 7222
3712, 3591, 3713, 747, 7916, 635, 4242, 4528, 7917, 7918, 7919, 4243, 7920, 7921, 4529, 7922, # 7238
3378, 4530, 2432, 451, 7923, 3714, 2535, 2072, 4244, 2735, 4245, 4022, 7924, 1764, 4531, 7925, # 7254
4246, 350, 7926, 2278, 2390, 2486, 7927, 4247, 4023, 2245, 1434, 4024, 488, 4532, 458, 4248, # 7270
4025, 3715, 771, 1330, 2391, 3835, 2568, 3159, 2159, 2409, 1553, 2667, 3160, 4249, 7928, 2487, # 7286
2881, 2612, 1720, 2702, 4250, 3379, 4533, 7929, 2536, 4251, 7930, 3231, 4252, 2768, 7931, 2015, # 7302
2736, 7932, 1155, 1017, 3716, 3836, 7933, 3303, 2308, 201, 1864, 4253, 1430, 7934, 4026, 7935, # 7318
7936, 7937, 7938, 7939, 4254, 1604, 7940, 414, 1865, 371, 2587, 4534, 4535, 3485, 2016, 3104, # 7334
4536, 1708, 960, 4255, 887, 389, 2171, 1536, 1663, 1721, 7941, 2228, 4027, 2351, 2926, 1580, # 7350
7942, 7943, 7944, 1744, 7945, 2537, 4537, 4538, 7946, 4539, 7947, 2073, 7948, 7949, 3592, 3380, # 7366
2882, 4256, 7950, 4257, 2640, 3381, 2802, 673, 2703, 2460, 709, 3486, 4028, 3593, 4258, 7951, # 7382
1148, 502, 634, 7952, 7953, 1204, 4540, 3594, 1575, 4541, 2613, 3717, 7954, 3718, 3105, 948, # 7398
3232, 121, 1745, 3837, 1110, 7955, 4259, 3063, 2509, 3009, 4029, 3719, 1151, 1771, 3838, 1488, # 7414
4030, 1986, 7956, 2433, 3487, 7957, 7958, 2093, 7959, 4260, 3839, 1213, 1407, 2803, 531, 2737, # 7430
2538, 3233, 1011, 1537, 7960, 2769, 4261, 3106, 1061, 7961, 3720, 3721, 1866, 2883, 7962, 2017, # 7446
120, 4262, 4263, 2062, 3595, 3234, 2309, 3840, 2668, 3382, 1954, 4542, 7963, 7964, 3488, 1047, # 7462
2704, 1266, 7965, 1368, 4543, 2845, 649, 3383, 3841, 2539, 2738, 1102, 2846, 2669, 7966, 7967, # 7478
1999, 7968, 1111, 3596, 2962, 7969, 2488, 3842, 3597, 2804, 1854, 3384, 3722, 7970, 7971, 3385, # 7494
2410, 2884, 3304, 3235, 3598, 7972, 2569, 7973, 3599, 2805, 4031, 1460, 856, 7974, 3600, 7975, # 7510
2885, 2963, 7976, 2886, 3843, 7977, 4264, 632, 2510, 875, 3844, 1697, 3845, 2291, 7978, 7979, # 7526
4544, 3010, 1239, 580, 4545, 4265, 7980, 914, 936, 2074, 1190, 4032, 1039, 2123, 7981, 7982, # 7542
7983, 3386, 1473, 7984, 1354, 4266, 3846, 7985, 2172, 3064, 4033, 915, 3305, 4267, 4268, 3306, # 7558
1605, 1834, 7986, 2739, 398, 3601, 4269, 3847, 4034, 328, 1912, 2847, 4035, 3848, 1331, 4270, # 7574
3011, 937, 4271, 7987, 3602, 4036, 4037, 3387, 2160, 4546, 3388, 524, 742, 538, 3065, 1012, # 7590
7988, 7989, 3849, 2461, 7990, 658, 1103, 225, 3850, 7991, 7992, 4547, 7993, 4548, 7994, 3236, # 7606
1243, 7995, 4038, 963, 2246, 4549, 7996, 2705, 3603, 3161, 7997, 7998, 2588, 2327, 7999, 4550, # 7622
8000, 8001, 8002, 3489, 3307, 957, 3389, 2540, 2032, 1930, 2927, 2462, 870, 2018, 3604, 1746, # 7638
2770, 2771, 2434, 2463, 8003, 3851, 8004, 3723, 3107, 3724, 3490, 3390, 3725, 8005, 1179, 3066, # 7654
8006, 3162, 2373, 4272, 3726, 2541, 3163, 3108, 2740, 4039, 8007, 3391, 1556, 2542, 2292, 977, # 7670
2887, 2033, 4040, 1205, 3392, 8008, 1765, 3393, 3164, 2124, 1271, 1689, 714, 4551, 3491, 8009, # 7686
2328, 3852, 533, 4273, 3605, 2181, 617, 8010, 2464, 3308, 3492, 2310, 8011, 8012, 3165, 8013, # 7702
8014, 3853, 1987, 618, 427, 2641, 3493, 3394, 8015, 8016, 1244, 1690, 8017, 2806, 4274, 4552, # 7718
8018, 3494, 8019, 8020, 2279, 1576, 473, 3606, 4275, 3395, 972, 8021, 3607, 8022, 3067, 8023, # 7734
8024, 4553, 4554, 8025, 3727, 4041, 4042, 8026, 153, 4555, 356, 8027, 1891, 2888, 4276, 2143, # 7750
408, 803, 2352, 8028, 3854, 8029, 4277, 1646, 2570, 2511, 4556, 4557, 3855, 8030, 3856, 4278, # 7766
8031, 2411, 3396, 752, 8032, 8033, 1961, 2964, 8034, 746, 3012, 2465, 8035, 4279, 3728, 698, # 7782
4558, 1892, 4280, 3608, 2543, 4559, 3609, 3857, 8036, 3166, 3397, 8037, 1823, 1302, 4043, 2706, # 7798
3858, 1973, 4281, 8038, 4282, 3167, 823, 1303, 1288, 1236, 2848, 3495, 4044, 3398, 774, 3859, # 7814
8039, 1581, 4560, 1304, 2849, 3860, 4561, 8040, 2435, 2161, 1083, 3237, 4283, 4045, 4284, 344, # 7830
1173, 288, 2311, 454, 1683, 8041, 8042, 1461, 4562, 4046, 2589, 8043, 8044, 4563, 985, 894, # 7846
8045, 3399, 3168, 8046, 1913, 2928, 3729, 1988, 8047, 2110, 1974, 8048, 4047, 8049, 2571, 1194, # 7862
425, 8050, 4564, 3169, 1245, 3730, 4285, 8051, 8052, 2850, 8053, 636, 4565, 1855, 3861, 760, # 7878
1799, 8054, 4286, 2209, 1508, 4566, 4048, 1893, 1684, 2293, 8055, 8056, 8057, 4287, 4288, 2210, # 7894
479, 8058, 8059, 832, 8060, 4049, 2489, 8061, 2965, 2490, 3731, 990, 3109, 627, 1814, 2642, # 7910
4289, 1582, 4290, 2125, 2111, 3496, 4567, 8062, 799, 4291, 3170, 8063, 4568, 2112, 1737, 3013, # 7926
1018, 543, 754, 4292, 3309, 1676, 4569, 4570, 4050, 8064, 1489, 8065, 3497, 8066, 2614, 2889, # 7942
4051, 8067, 8068, 2966, 8069, 8070, 8071, 8072, 3171, 4571, 4572, 2182, 1722, 8073, 3238, 3239, # 7958
1842, 3610, 1715, 481, 365, 1975, 1856, 8074, 8075, 1962, 2491, 4573, 8076, 2126, 3611, 3240, # 7974
433, 1894, 2063, 2075, 8077, 602, 2741, 8078, 8079, 8080, 8081, 8082, 3014, 1628, 3400, 8083, # 7990
3172, 4574, 4052, 2890, 4575, 2512, 8084, 2544, 2772, 8085, 8086, 8087, 3310, 4576, 2891, 8088, # 8006
4577, 8089, 2851, 4578, 4579, 1221, 2967, 4053, 2513, 8090, 8091, 8092, 1867, 1989, 8093, 8094, # 8022
8095, 1895, 8096, 8097, 4580, 1896, 4054, 318, 8098, 2094, 4055, 4293, 8099, 8100, 485, 8101, # 8038
938, 3862, 553, 2670, 116, 8102, 3863, 3612, 8103, 3498, 2671, 2773, 3401, 3311, 2807, 8104, # 8054
3613, 2929, 4056, 1747, 2930, 2968, 8105, 8106, 207, 8107, 8108, 2672, 4581, 2514, 8109, 3015, # 8070
890, 3614, 3864, 8110, 1877, 3732, 3402, 8111, 2183, 2353, 3403, 1652, 8112, 8113, 8114, 941, # 8086
2294, 208, 3499, 4057, 2019, 330, 4294, 3865, 2892, 2492, 3733, 4295, 8115, 8116, 8117, 8118, # 8102
)
# fmt: on

13
venv/Lib/site-packages/pip/_vendor/chardet/euctwprober.py
View File

@@ -25,22 +25,23 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from .chardistribution import EUCTWDistributionAnalysis
from .codingstatemachine import CodingStateMachine
from .mbcharsetprober import MultiByteCharSetProber
from .mbcssm import EUCTW_SM_MODEL
class EUCTWProber(MultiByteCharSetProber):
def __init__(self):
super(EUCTWProber, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(EUCTW_SM_MODEL)
self.distribution_analyzer = EUCTWDistributionAnalysis()
self.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "EUC-TW"
@property
def language(self):
def language(self) -> str:
return "Taiwan"

3
venv/Lib/site-packages/pip/_vendor/chardet/gb2312freq.py
View File

@@ -43,6 +43,7 @@ GB2312_TYPICAL_DISTRIBUTION_RATIO = 0.9
GB2312_TABLE_SIZE = 3760
# fmt: off
GB2312_CHAR_TO_FREQ_ORDER = (
1671, 749,1443,2364,3924,3807,2330,3921,1704,3463,2691,1511,1515, 572,3191,2205,
2361, 224,2558, 479,1711, 963,3162, 440,4060,1905,2966,2947,3580,2647,3961,3842,
@@ -280,4 +281,4 @@ GB2312_CHAR_TO_FREQ_ORDER = (
381,1638,4592,1020, 516,3214, 458, 947,4575,1432, 211,1514,2926,1865,2142, 189,
852,1221,1400,1486, 882,2299,4036, 351, 28,1122, 700,6479,6480,6481,6482,6483, #last 512
)
# fmt: on

13
venv/Lib/site-packages/pip/_vendor/chardet/gb2312prober.py
View File

@@ -25,22 +25,23 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from .chardistribution import GB2312DistributionAnalysis
from .codingstatemachine import CodingStateMachine
from .mbcharsetprober import MultiByteCharSetProber
from .mbcssm import GB2312_SM_MODEL
class GB2312Prober(MultiByteCharSetProber):
def __init__(self):
super(GB2312Prober, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(GB2312_SM_MODEL)
self.distribution_analyzer = GB2312DistributionAnalysis()
self.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "GB2312"
@property
def language(self):
def language(self) -> str:
return "Chinese"

110
venv/Lib/site-packages/pip/_vendor/chardet/hebrewprober.py
View File

@@ -25,8 +25,11 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from typing import Optional, Union
from .charsetprober import CharSetProber
from .enums import ProbingState
from .sbcharsetprober import SingleByteCharSetProber
# This prober doesn't actually recognize a language or a charset.
# It is a helper prober for the use of the Hebrew model probers
@@ -125,18 +128,20 @@ from .enums import ProbingState
# model probers scores. The answer is returned in the form of the name of the
# charset identified, either "windows-1255" or "ISO-8859-8".
class HebrewProber(CharSetProber):
SPACE = 0x20
# windows-1255 / ISO-8859-8 code points of interest
FINAL_KAF = 0xea
NORMAL_KAF = 0xeb
FINAL_MEM = 0xed
NORMAL_MEM = 0xee
FINAL_NUN = 0xef
NORMAL_NUN = 0xf0
FINAL_PE = 0xf3
NORMAL_PE = 0xf4
FINAL_TSADI = 0xf5
NORMAL_TSADI = 0xf6
FINAL_KAF = 0xEA
NORMAL_KAF = 0xEB
FINAL_MEM = 0xED
NORMAL_MEM = 0xEE
FINAL_NUN = 0xEF
NORMAL_NUN = 0xF0
FINAL_PE = 0xF3
NORMAL_PE = 0xF4
FINAL_TSADI = 0xF5
NORMAL_TSADI = 0xF6
# Minimum Visual vs Logical final letter score difference.
# If the difference is below this, don't rely solely on the final letter score
@@ -151,35 +156,44 @@ class HebrewProber(CharSetProber):
VISUAL_HEBREW_NAME = "ISO-8859-8"
LOGICAL_HEBREW_NAME = "windows-1255"
def __init__(self):
super(HebrewProber, self).__init__()
self._final_char_logical_score = None
self._final_char_visual_score = None
self._prev = None
self._before_prev = None
self._logical_prober = None
self._visual_prober = None
def __init__(self) -> None:
super().__init__()
self._final_char_logical_score = 0
self._final_char_visual_score = 0
self._prev = self.SPACE
self._before_prev = self.SPACE
self._logical_prober: Optional[SingleByteCharSetProber] = None
self._visual_prober: Optional[SingleByteCharSetProber] = None
self.reset()
def reset(self):
def reset(self) -> None:
self._final_char_logical_score = 0
self._final_char_visual_score = 0
# The two last characters seen in the previous buffer,
# mPrev and mBeforePrev are initialized to space in order to simulate
# a word delimiter at the beginning of the data
self._prev = ' '
self._before_prev = ' '
self._prev = self.SPACE
self._before_prev = self.SPACE
# These probers are owned by the group prober.
def set_model_probers(self, logicalProber, visualProber):
self._logical_prober = logicalProber
self._visual_prober = visualProber
def set_model_probers(
self,
logical_prober: SingleByteCharSetProber,
visual_prober: SingleByteCharSetProber,
) -> None:
self._logical_prober = logical_prober
self._visual_prober = visual_prober
def is_final(self, c):
return c in [self.FINAL_KAF, self.FINAL_MEM, self.FINAL_NUN,
self.FINAL_PE, self.FINAL_TSADI]
def is_final(self, c: int) -> bool:
return c in [
self.FINAL_KAF,
self.FINAL_MEM,
self.FINAL_NUN,
self.FINAL_PE,
self.FINAL_TSADI,
]
def is_non_final(self, c):
def is_non_final(self, c: int) -> bool:
# The normal Tsadi is not a good Non-Final letter due to words like
# 'lechotet' (to chat) containing an apostrophe after the tsadi. This
# apostrophe is converted to a space in FilterWithoutEnglishLetters
@@ -190,10 +204,9 @@ class HebrewProber(CharSetProber):
# for example legally end with a Non-Final Pe or Kaf. However, the
# benefit of these letters as Non-Final letters outweighs the damage
# since these words are quite rare.
return c in [self.NORMAL_KAF, self.NORMAL_MEM,
self.NORMAL_NUN, self.NORMAL_PE]
return c in [self.NORMAL_KAF, self.NORMAL_MEM, self.NORMAL_NUN, self.NORMAL_PE]
def feed(self, byte_str):
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
# Final letter analysis for logical-visual decision.
# Look for evidence that the received buffer is either logical Hebrew
# or visual Hebrew.
@@ -227,9 +240,9 @@ class HebrewProber(CharSetProber):
byte_str = self.filter_high_byte_only(byte_str)
for cur in byte_str:
if cur == ' ':
if cur == self.SPACE:
# We stand on a space - a word just ended
if self._before_prev != ' ':
if self._before_prev != self.SPACE:
# next-to-last char was not a space so self._prev is not a
# 1 letter word
if self.is_final(self._prev):
@@ -241,8 +254,11 @@ class HebrewProber(CharSetProber):
self._final_char_visual_score += 1
else:
# Not standing on a space
if ((self._before_prev == ' ') and
(self.is_final(self._prev)) and (cur != ' ')):
if (
(self._before_prev == self.SPACE)
and (self.is_final(self._prev))
and (cur != self.SPACE)
):
# case (3) [-2:space][-1:final letter][cur:not space]
self._final_char_visual_score += 1
self._before_prev = self._prev
@@ -253,7 +269,10 @@ class HebrewProber(CharSetProber):
return ProbingState.DETECTING
@property
def charset_name(self):
def charset_name(self) -> str:
assert self._logical_prober is not None
assert self._visual_prober is not None
# Make the decision: is it Logical or Visual?
# If the final letter score distance is dominant enough, rely on it.
finalsub = self._final_char_logical_score - self._final_char_visual_score
@@ -263,8 +282,9 @@ class HebrewProber(CharSetProber):
return self.VISUAL_HEBREW_NAME
# It's not dominant enough, try to rely on the model scores instead.
modelsub = (self._logical_prober.get_confidence()
- self._visual_prober.get_confidence())
modelsub = (
self._logical_prober.get_confidence() - self._visual_prober.get_confidence()
)
if modelsub > self.MIN_MODEL_DISTANCE:
return self.LOGICAL_HEBREW_NAME
if modelsub < -self.MIN_MODEL_DISTANCE:
@@ -280,13 +300,17 @@ class HebrewProber(CharSetProber):
return self.LOGICAL_HEBREW_NAME
@property
def language(self):
return 'Hebrew'
def language(self) -> str:
return "Hebrew"
@property
def state(self):
def state(self) -> ProbingState:
assert self._logical_prober is not None
assert self._visual_prober is not None
# Remain active as long as any of the model probers are active.
if (self._logical_prober.state == ProbingState.NOT_ME) and \
(self._visual_prober.state == ProbingState.NOT_ME):
if (self._logical_prober.state == ProbingState.NOT_ME) and (
self._visual_prober.state == ProbingState.NOT_ME
):
return ProbingState.NOT_ME
return ProbingState.DETECTING

4
venv/Lib/site-packages/pip/_vendor/chardet/jisfreq.py
View File

@@ -46,6 +46,7 @@ JIS_TYPICAL_DISTRIBUTION_RATIO = 3.0
# Char to FreqOrder table ,
JIS_TABLE_SIZE = 4368
# fmt: off
JIS_CHAR_TO_FREQ_ORDER = (
40, 1, 6, 182, 152, 180, 295,2127, 285, 381,3295,4304,3068,4606,3165,3510, # 16
3511,1822,2785,4607,1193,2226,5070,4608, 171,2996,1247, 18, 179,5071, 856,1661, # 32
@@ -321,5 +322,4 @@ JIS_CHAR_TO_FREQ_ORDER = (
1444,1698,2385,2251,3729,1365,2281,2235,1717,6188, 864,3841,2515, 444, 527,2767, # 4352
2922,3625, 544, 461,6189, 566, 209,2437,3398,2098,1065,2068,3331,3626,3257,2137, # 4368 #last 512
)
# fmt: on

219
venv/Lib/site-packages/pip/_vendor/chardet/jpcntx.py
View File

@@ -25,110 +25,114 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from typing import List, Tuple, Union
# This is hiragana 2-char sequence table, the number in each cell represents its frequency category
jp2CharContext = (
(0,0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,1,0,0,0,0,0,0,0,0,0,0,1),
(2,4,0,4,0,3,0,4,0,3,4,4,4,2,4,3,3,4,3,2,3,3,4,2,3,3,3,2,4,1,4,3,3,1,5,4,3,4,3,4,3,5,3,0,3,5,4,2,0,3,1,0,3,3,0,3,3,0,1,1,0,4,3,0,3,3,0,4,0,2,0,3,5,5,5,5,4,0,4,1,0,3,4),
(0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2),
(0,4,0,5,0,5,0,4,0,4,5,4,4,3,5,3,5,1,5,3,4,3,4,4,3,4,3,3,4,3,5,4,4,3,5,5,3,5,5,5,3,5,5,3,4,5,5,3,1,3,2,0,3,4,0,4,2,0,4,2,1,5,3,2,3,5,0,4,0,2,0,5,4,4,5,4,5,0,4,0,0,4,4),
(0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0),
(0,3,0,4,0,3,0,3,0,4,5,4,3,3,3,3,4,3,5,4,4,3,5,4,4,3,4,3,4,4,4,4,5,3,4,4,3,4,5,5,4,5,5,1,4,5,4,3,0,3,3,1,3,3,0,4,4,0,3,3,1,5,3,3,3,5,0,4,0,3,0,4,4,3,4,3,3,0,4,1,1,3,4),
(0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0),
(0,4,0,3,0,3,0,4,0,3,4,4,3,2,2,1,2,1,3,1,3,3,3,3,3,4,3,1,3,3,5,3,3,0,4,3,0,5,4,3,3,5,4,4,3,4,4,5,0,1,2,0,1,2,0,2,2,0,1,0,0,5,2,2,1,4,0,3,0,1,0,4,4,3,5,4,3,0,2,1,0,4,3),
(0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0),
(0,3,0,5,0,4,0,2,1,4,4,2,4,1,4,2,4,2,4,3,3,3,4,3,3,3,3,1,4,2,3,3,3,1,4,4,1,1,1,4,3,3,2,0,2,4,3,2,0,3,3,0,3,1,1,0,0,0,3,3,0,4,2,2,3,4,0,4,0,3,0,4,4,5,3,4,4,0,3,0,0,1,4),
(1,4,0,4,0,4,0,4,0,3,5,4,4,3,4,3,5,4,3,3,4,3,5,4,4,4,4,3,4,2,4,3,3,1,5,4,3,2,4,5,4,5,5,4,4,5,4,4,0,3,2,2,3,3,0,4,3,1,3,2,1,4,3,3,4,5,0,3,0,2,0,4,5,5,4,5,4,0,4,0,0,5,4),
(0,5,0,5,0,4,0,3,0,4,4,3,4,3,3,3,4,0,4,4,4,3,4,3,4,3,3,1,4,2,4,3,4,0,5,4,1,4,5,4,4,5,3,2,4,3,4,3,2,4,1,3,3,3,2,3,2,0,4,3,3,4,3,3,3,4,0,4,0,3,0,4,5,4,4,4,3,0,4,1,0,1,3),
(0,3,1,4,0,3,0,2,0,3,4,4,3,1,4,2,3,3,4,3,4,3,4,3,4,4,3,2,3,1,5,4,4,1,4,4,3,5,4,4,3,5,5,4,3,4,4,3,1,2,3,1,2,2,0,3,2,0,3,1,0,5,3,3,3,4,3,3,3,3,4,4,4,4,5,4,2,0,3,3,2,4,3),
(0,2,0,3,0,1,0,1,0,0,3,2,0,0,2,0,1,0,2,1,3,3,3,1,2,3,1,0,1,0,4,2,1,1,3,3,0,4,3,3,1,4,3,3,0,3,3,2,0,0,0,0,1,0,0,2,0,0,0,0,0,4,1,0,2,3,2,2,2,1,3,3,3,4,4,3,2,0,3,1,0,3,3),
(0,4,0,4,0,3,0,3,0,4,4,4,3,3,3,3,3,3,4,3,4,2,4,3,4,3,3,2,4,3,4,5,4,1,4,5,3,5,4,5,3,5,4,0,3,5,5,3,1,3,3,2,2,3,0,3,4,1,3,3,2,4,3,3,3,4,0,4,0,3,0,4,5,4,4,5,3,0,4,1,0,3,4),
(0,2,0,3,0,3,0,0,0,2,2,2,1,0,1,0,0,0,3,0,3,0,3,0,1,3,1,0,3,1,3,3,3,1,3,3,3,0,1,3,1,3,4,0,0,3,1,1,0,3,2,0,0,0,0,1,3,0,1,0,0,3,3,2,0,3,0,0,0,0,0,3,4,3,4,3,3,0,3,0,0,2,3),
(2,3,0,3,0,2,0,1,0,3,3,4,3,1,3,1,1,1,3,1,4,3,4,3,3,3,0,0,3,1,5,4,3,1,4,3,2,5,5,4,4,4,4,3,3,4,4,4,0,2,1,1,3,2,0,1,2,0,0,1,0,4,1,3,3,3,0,3,0,1,0,4,4,4,5,5,3,0,2,0,0,4,4),
(0,2,0,1,0,3,1,3,0,2,3,3,3,0,3,1,0,0,3,0,3,2,3,1,3,2,1,1,0,0,4,2,1,0,2,3,1,4,3,2,0,4,4,3,1,3,1,3,0,1,0,0,1,0,0,0,1,0,0,0,0,4,1,1,1,2,0,3,0,0,0,3,4,2,4,3,2,0,1,0,0,3,3),
(0,1,0,4,0,5,0,4,0,2,4,4,2,3,3,2,3,3,5,3,3,3,4,3,4,2,3,0,4,3,3,3,4,1,4,3,2,1,5,5,3,4,5,1,3,5,4,2,0,3,3,0,1,3,0,4,2,0,1,3,1,4,3,3,3,3,0,3,0,1,0,3,4,4,4,5,5,0,3,0,1,4,5),
(0,2,0,3,0,3,0,0,0,2,3,1,3,0,4,0,1,1,3,0,3,4,3,2,3,1,0,3,3,2,3,1,3,0,2,3,0,2,1,4,1,2,2,0,0,3,3,0,0,2,0,0,0,1,0,0,0,0,2,2,0,3,2,1,3,3,0,2,0,2,0,0,3,3,1,2,4,0,3,0,2,2,3),
(2,4,0,5,0,4,0,4,0,2,4,4,4,3,4,3,3,3,1,2,4,3,4,3,4,4,5,0,3,3,3,3,2,0,4,3,1,4,3,4,1,4,4,3,3,4,4,3,1,2,3,0,4,2,0,4,1,0,3,3,0,4,3,3,3,4,0,4,0,2,0,3,5,3,4,5,2,0,3,0,0,4,5),
(0,3,0,4,0,1,0,1,0,1,3,2,2,1,3,0,3,0,2,0,2,0,3,0,2,0,0,0,1,0,1,1,0,0,3,1,0,0,0,4,0,3,1,0,2,1,3,0,0,0,0,0,0,3,0,0,0,0,0,0,0,4,2,2,3,1,0,3,0,0,0,1,4,4,4,3,0,0,4,0,0,1,4),
(1,4,1,5,0,3,0,3,0,4,5,4,4,3,5,3,3,4,4,3,4,1,3,3,3,3,2,1,4,1,5,4,3,1,4,4,3,5,4,4,3,5,4,3,3,4,4,4,0,3,3,1,2,3,0,3,1,0,3,3,0,5,4,4,4,4,4,4,3,3,5,4,4,3,3,5,4,0,3,2,0,4,4),
(0,2,0,3,0,1,0,0,0,1,3,3,3,2,4,1,3,0,3,1,3,0,2,2,1,1,0,0,2,0,4,3,1,0,4,3,0,4,4,4,1,4,3,1,1,3,3,1,0,2,0,0,1,3,0,0,0,0,2,0,0,4,3,2,4,3,5,4,3,3,3,4,3,3,4,3,3,0,2,1,0,3,3),
(0,2,0,4,0,3,0,2,0,2,5,5,3,4,4,4,4,1,4,3,3,0,4,3,4,3,1,3,3,2,4,3,0,3,4,3,0,3,4,4,2,4,4,0,4,5,3,3,2,2,1,1,1,2,0,1,5,0,3,3,2,4,3,3,3,4,0,3,0,2,0,4,4,3,5,5,0,0,3,0,2,3,3),
(0,3,0,4,0,3,0,1,0,3,4,3,3,1,3,3,3,0,3,1,3,0,4,3,3,1,1,0,3,0,3,3,0,0,4,4,0,1,5,4,3,3,5,0,3,3,4,3,0,2,0,1,1,1,0,1,3,0,1,2,1,3,3,2,3,3,0,3,0,1,0,1,3,3,4,4,1,0,1,2,2,1,3),
(0,1,0,4,0,4,0,3,0,1,3,3,3,2,3,1,1,0,3,0,3,3,4,3,2,4,2,0,1,0,4,3,2,0,4,3,0,5,3,3,2,4,4,4,3,3,3,4,0,1,3,0,0,1,0,0,1,0,0,0,0,4,2,3,3,3,0,3,0,0,0,4,4,4,5,3,2,0,3,3,0,3,5),
(0,2,0,3,0,0,0,3,0,1,3,0,2,0,0,0,1,0,3,1,1,3,3,0,0,3,0,0,3,0,2,3,1,0,3,1,0,3,3,2,0,4,2,2,0,2,0,0,0,4,0,0,0,0,0,0,0,0,0,0,0,2,1,2,0,1,0,1,0,0,0,1,3,1,2,0,0,0,1,0,0,1,4),
(0,3,0,3,0,5,0,1,0,2,4,3,1,3,3,2,1,1,5,2,1,0,5,1,2,0,0,0,3,3,2,2,3,2,4,3,0,0,3,3,1,3,3,0,2,5,3,4,0,3,3,0,1,2,0,2,2,0,3,2,0,2,2,3,3,3,0,2,0,1,0,3,4,4,2,5,4,0,3,0,0,3,5),
(0,3,0,3,0,3,0,1,0,3,3,3,3,0,3,0,2,0,2,1,1,0,2,0,1,0,0,0,2,1,0,0,1,0,3,2,0,0,3,3,1,2,3,1,0,3,3,0,0,1,0,0,0,0,0,2,0,0,0,0,0,2,3,1,2,3,0,3,0,1,0,3,2,1,0,4,3,0,1,1,0,3,3),
(0,4,0,5,0,3,0,3,0,4,5,5,4,3,5,3,4,3,5,3,3,2,5,3,4,4,4,3,4,3,4,5,5,3,4,4,3,4,4,5,4,4,4,3,4,5,5,4,2,3,4,2,3,4,0,3,3,1,4,3,2,4,3,3,5,5,0,3,0,3,0,5,5,5,5,4,4,0,4,0,1,4,4),
(0,4,0,4,0,3,0,3,0,3,5,4,4,2,3,2,5,1,3,2,5,1,4,2,3,2,3,3,4,3,3,3,3,2,5,4,1,3,3,5,3,4,4,0,4,4,3,1,1,3,1,0,2,3,0,2,3,0,3,0,0,4,3,1,3,4,0,3,0,2,0,4,4,4,3,4,5,0,4,0,0,3,4),
(0,3,0,3,0,3,1,2,0,3,4,4,3,3,3,0,2,2,4,3,3,1,3,3,3,1,1,0,3,1,4,3,2,3,4,4,2,4,4,4,3,4,4,3,2,4,4,3,1,3,3,1,3,3,0,4,1,0,2,2,1,4,3,2,3,3,5,4,3,3,5,4,4,3,3,0,4,0,3,2,2,4,4),
(0,2,0,1,0,0,0,0,0,1,2,1,3,0,0,0,0,0,2,0,1,2,1,0,0,1,0,0,0,0,3,0,0,1,0,1,1,3,1,0,0,0,1,1,0,1,1,0,0,0,0,0,2,0,0,0,0,0,0,0,0,1,1,2,2,0,3,4,0,0,0,1,1,0,0,1,0,0,0,0,0,1,1),
(0,1,0,0,0,1,0,0,0,0,4,0,4,1,4,0,3,0,4,0,3,0,4,0,3,0,3,0,4,1,5,1,4,0,0,3,0,5,0,5,2,0,1,0,0,0,2,1,4,0,1,3,0,0,3,0,0,3,1,1,4,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0),
(1,4,0,5,0,3,0,2,0,3,5,4,4,3,4,3,5,3,4,3,3,0,4,3,3,3,3,3,3,2,4,4,3,1,3,4,4,5,4,4,3,4,4,1,3,5,4,3,3,3,1,2,2,3,3,1,3,1,3,3,3,5,3,3,4,5,0,3,0,3,0,3,4,3,4,4,3,0,3,0,2,4,3),
(0,1,0,4,0,0,0,0,0,1,4,0,4,1,4,2,4,0,3,0,1,0,1,0,0,0,0,0,2,0,3,1,1,1,0,3,0,0,0,1,2,1,0,0,1,1,1,1,0,1,0,0,0,1,0,0,3,0,0,0,0,3,2,0,2,2,0,1,0,0,0,2,3,2,3,3,0,0,0,0,2,1,0),
(0,5,1,5,0,3,0,3,0,5,4,4,5,1,5,3,3,0,4,3,4,3,5,3,4,3,3,2,4,3,4,3,3,0,3,3,1,4,4,3,4,4,4,3,4,5,5,3,2,3,1,1,3,3,1,3,1,1,3,3,2,4,5,3,3,5,0,4,0,3,0,4,4,3,5,3,3,0,3,4,0,4,3),
(0,5,0,5,0,3,0,2,0,4,4,3,5,2,4,3,3,3,4,4,4,3,5,3,5,3,3,1,4,0,4,3,3,0,3,3,0,4,4,4,4,5,4,3,3,5,5,3,2,3,1,2,3,2,0,1,0,0,3,2,2,4,4,3,1,5,0,4,0,3,0,4,3,1,3,2,1,0,3,3,0,3,3),
(0,4,0,5,0,5,0,4,0,4,5,5,5,3,4,3,3,2,5,4,4,3,5,3,5,3,4,0,4,3,4,4,3,2,4,4,3,4,5,4,4,5,5,0,3,5,5,4,1,3,3,2,3,3,1,3,1,0,4,3,1,4,4,3,4,5,0,4,0,2,0,4,3,4,4,3,3,0,4,0,0,5,5),
(0,4,0,4,0,5,0,1,1,3,3,4,4,3,4,1,3,0,5,1,3,0,3,1,3,1,1,0,3,0,3,3,4,0,4,3,0,4,4,4,3,4,4,0,3,5,4,1,0,3,0,0,2,3,0,3,1,0,3,1,0,3,2,1,3,5,0,3,0,1,0,3,2,3,3,4,4,0,2,2,0,4,4),
(2,4,0,5,0,4,0,3,0,4,5,5,4,3,5,3,5,3,5,3,5,2,5,3,4,3,3,4,3,4,5,3,2,1,5,4,3,2,3,4,5,3,4,1,2,5,4,3,0,3,3,0,3,2,0,2,3,0,4,1,0,3,4,3,3,5,0,3,0,1,0,4,5,5,5,4,3,0,4,2,0,3,5),
(0,5,0,4,0,4,0,2,0,5,4,3,4,3,4,3,3,3,4,3,4,2,5,3,5,3,4,1,4,3,4,4,4,0,3,5,0,4,4,4,4,5,3,1,3,4,5,3,3,3,3,3,3,3,0,2,2,0,3,3,2,4,3,3,3,5,3,4,1,3,3,5,3,2,0,0,0,0,4,3,1,3,3),
(0,1,0,3,0,3,0,1,0,1,3,3,3,2,3,3,3,0,3,0,0,0,3,1,3,0,0,0,2,2,2,3,0,0,3,2,0,1,2,4,1,3,3,0,0,3,3,3,0,1,0,0,2,1,0,0,3,0,3,1,0,3,0,0,1,3,0,2,0,1,0,3,3,1,3,3,0,0,1,1,0,3,3),
(0,2,0,3,0,2,1,4,0,2,2,3,1,1,3,1,1,0,2,0,3,1,2,3,1,3,0,0,1,0,4,3,2,3,3,3,1,4,2,3,3,3,3,1,0,3,1,4,0,1,1,0,1,2,0,1,1,0,1,1,0,3,1,3,2,2,0,1,0,0,0,2,3,3,3,1,0,0,0,0,0,2,3),
(0,5,0,4,0,5,0,2,0,4,5,5,3,3,4,3,3,1,5,4,4,2,4,4,4,3,4,2,4,3,5,5,4,3,3,4,3,3,5,5,4,5,5,1,3,4,5,3,1,4,3,1,3,3,0,3,3,1,4,3,1,4,5,3,3,5,0,4,0,3,0,5,3,3,1,4,3,0,4,0,1,5,3),
(0,5,0,5,0,4,0,2,0,4,4,3,4,3,3,3,3,3,5,4,4,4,4,4,4,5,3,3,5,2,4,4,4,3,4,4,3,3,4,4,5,5,3,3,4,3,4,3,3,4,3,3,3,3,1,2,2,1,4,3,3,5,4,4,3,4,0,4,0,3,0,4,4,4,4,4,1,0,4,2,0,2,4),
(0,4,0,4,0,3,0,1,0,3,5,2,3,0,3,0,2,1,4,2,3,3,4,1,4,3,3,2,4,1,3,3,3,0,3,3,0,0,3,3,3,5,3,3,3,3,3,2,0,2,0,0,2,0,0,2,0,0,1,0,0,3,1,2,2,3,0,3,0,2,0,4,4,3,3,4,1,0,3,0,0,2,4),
(0,0,0,4,0,0,0,0,0,0,1,0,1,0,2,0,0,0,0,0,1,0,2,0,1,0,0,0,0,0,3,1,3,0,3,2,0,0,0,1,0,3,2,0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3,4,0,2,0,0,0,0,0,0,2),
(0,2,1,3,0,2,0,2,0,3,3,3,3,1,3,1,3,3,3,3,3,3,4,2,2,1,2,1,4,0,4,3,1,3,3,3,2,4,3,5,4,3,3,3,3,3,3,3,0,1,3,0,2,0,0,1,0,0,1,0,0,4,2,0,2,3,0,3,3,0,3,3,4,2,3,1,4,0,1,2,0,2,3),
(0,3,0,3,0,1,0,3,0,2,3,3,3,0,3,1,2,0,3,3,2,3,3,2,3,2,3,1,3,0,4,3,2,0,3,3,1,4,3,3,2,3,4,3,1,3,3,1,1,0,1,1,0,1,0,1,0,1,0,0,0,4,1,1,0,3,0,3,1,0,2,3,3,3,3,3,1,0,0,2,0,3,3),
(0,0,0,0,0,0,0,0,0,0,3,0,2,0,3,0,0,0,0,0,0,0,3,0,0,0,0,0,0,0,3,0,3,0,3,1,0,1,0,1,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3,0,2,0,2,3,0,0,0,0,0,0,0,0,3),
(0,2,0,3,1,3,0,3,0,2,3,3,3,1,3,1,3,1,3,1,3,3,3,1,3,0,2,3,1,1,4,3,3,2,3,3,1,2,2,4,1,3,3,0,1,4,2,3,0,1,3,0,3,0,0,1,3,0,2,0,0,3,3,2,1,3,0,3,0,2,0,3,4,4,4,3,1,0,3,0,0,3,3),
(0,2,0,1,0,2,0,0,0,1,3,2,2,1,3,0,1,1,3,0,3,2,3,1,2,0,2,0,1,1,3,3,3,0,3,3,1,1,2,3,2,3,3,1,2,3,2,0,0,1,0,0,0,0,0,0,3,0,1,0,0,2,1,2,1,3,0,3,0,0,0,3,4,4,4,3,2,0,2,0,0,2,4),
(0,0,0,1,0,1,0,0,0,0,1,0,0,0,1,0,0,0,0,0,0,0,1,1,1,0,0,0,0,0,0,0,0,0,2,2,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,1,3,1,0,0,0,0,0,0,0,3),
(0,3,0,3,0,2,0,3,0,3,3,3,2,3,2,2,2,0,3,1,3,3,3,2,3,3,0,0,3,0,3,2,2,0,2,3,1,4,3,4,3,3,2,3,1,5,4,4,0,3,1,2,1,3,0,3,1,1,2,0,2,3,1,3,1,3,0,3,0,1,0,3,3,4,4,2,1,0,2,1,0,2,4),
(0,1,0,3,0,1,0,2,0,1,4,2,5,1,4,0,2,0,2,1,3,1,4,0,2,1,0,0,2,1,4,1,1,0,3,3,0,5,1,3,2,3,3,1,0,3,2,3,0,1,0,0,0,0,0,0,1,0,0,0,0,4,0,1,0,3,0,2,0,1,0,3,3,3,4,3,3,0,0,0,0,2,3),
(0,0,0,1,0,0,0,0,0,0,2,0,1,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,1,0,0,1,0,0,0,0,0,3),
(0,1,0,3,0,4,0,3,0,2,4,3,1,0,3,2,2,1,3,1,2,2,3,1,1,1,2,1,3,0,1,2,0,1,3,2,1,3,0,5,5,1,0,0,1,3,2,1,0,3,0,0,1,0,0,0,0,0,3,4,0,1,1,1,3,2,0,2,0,1,0,2,3,3,1,2,3,0,1,0,1,0,4),
(0,0,0,1,0,3,0,3,0,2,2,1,0,0,4,0,3,0,3,1,3,0,3,0,3,0,1,0,3,0,3,1,3,0,3,3,0,0,1,2,1,1,1,0,1,2,0,0,0,1,0,0,1,0,0,0,0,0,0,0,0,2,2,1,2,0,0,2,0,0,0,0,2,3,3,3,3,0,0,0,0,1,4),
(0,0,0,3,0,3,0,0,0,0,3,1,1,0,3,0,1,0,2,0,1,0,0,0,0,0,0,0,1,0,3,0,2,0,2,3,0,0,2,2,3,1,2,0,0,1,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3,0,0,2,0,0,0,0,2,3),
(2,4,0,5,0,5,0,4,0,3,4,3,3,3,4,3,3,3,4,3,4,4,5,4,5,5,5,2,3,0,5,5,4,1,5,4,3,1,5,4,3,4,4,3,3,4,3,3,0,3,2,0,2,3,0,3,0,0,3,3,0,5,3,2,3,3,0,3,0,3,0,3,4,5,4,5,3,0,4,3,0,3,4),
(0,3,0,3,0,3,0,3,0,3,3,4,3,2,3,2,3,0,4,3,3,3,3,3,3,3,3,0,3,2,4,3,3,1,3,4,3,4,4,4,3,4,4,3,2,4,4,1,0,2,0,0,1,1,0,2,0,0,3,1,0,5,3,2,1,3,0,3,0,1,2,4,3,2,4,3,3,0,3,2,0,4,4),
(0,3,0,3,0,1,0,0,0,1,4,3,3,2,3,1,3,1,4,2,3,2,4,2,3,4,3,0,2,2,3,3,3,0,3,3,3,0,3,4,1,3,3,0,3,4,3,3,0,1,1,0,1,0,0,0,4,0,3,0,0,3,1,2,1,3,0,4,0,1,0,4,3,3,4,3,3,0,2,0,0,3,3),
(0,3,0,4,0,1,0,3,0,3,4,3,3,0,3,3,3,1,3,1,3,3,4,3,3,3,0,0,3,1,5,3,3,1,3,3,2,5,4,3,3,4,5,3,2,5,3,4,0,1,0,0,0,0,0,2,0,0,1,1,0,4,2,2,1,3,0,3,0,2,0,4,4,3,5,3,2,0,1,1,0,3,4),
(0,5,0,4,0,5,0,2,0,4,4,3,3,2,3,3,3,1,4,3,4,1,5,3,4,3,4,0,4,2,4,3,4,1,5,4,0,4,4,4,4,5,4,1,3,5,4,2,1,4,1,1,3,2,0,3,1,0,3,2,1,4,3,3,3,4,0,4,0,3,0,4,4,4,3,3,3,0,4,2,0,3,4),
(1,4,0,4,0,3,0,1,0,3,3,3,1,1,3,3,2,2,3,3,1,0,3,2,2,1,2,0,3,1,2,1,2,0,3,2,0,2,2,3,3,4,3,0,3,3,1,2,0,1,1,3,1,2,0,0,3,0,1,1,0,3,2,2,3,3,0,3,0,0,0,2,3,3,4,3,3,0,1,0,0,1,4),
(0,4,0,4,0,4,0,0,0,3,4,4,3,1,4,2,3,2,3,3,3,1,4,3,4,0,3,0,4,2,3,3,2,2,5,4,2,1,3,4,3,4,3,1,3,3,4,2,0,2,1,0,3,3,0,0,2,0,3,1,0,4,4,3,4,3,0,4,0,1,0,2,4,4,4,4,4,0,3,2,0,3,3),
(0,0,0,1,0,4,0,0,0,0,0,0,1,1,1,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,1,0,3,2,0,0,1,0,0,0,1,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,2),
(0,2,0,3,0,4,0,4,0,1,3,3,3,0,4,0,2,1,2,1,1,1,2,0,3,1,1,0,1,0,3,1,0,0,3,3,2,0,1,1,0,0,0,0,0,1,0,2,0,2,2,0,3,1,0,0,1,0,1,1,0,1,2,0,3,0,0,0,0,1,0,0,3,3,4,3,1,0,1,0,3,0,2),
(0,0,0,3,0,5,0,0,0,0,1,0,2,0,3,1,0,1,3,0,0,0,2,0,0,0,1,0,0,0,1,1,0,0,4,0,0,0,2,3,0,1,4,1,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0,0,0,1,0,0,0,0,0,0,0,2,0,0,3,0,0,0,0,0,3),
(0,2,0,5,0,5,0,1,0,2,4,3,3,2,5,1,3,2,3,3,3,0,4,1,2,0,3,0,4,0,2,2,1,1,5,3,0,0,1,4,2,3,2,0,3,3,3,2,0,2,4,1,1,2,0,1,1,0,3,1,0,1,3,1,2,3,0,2,0,0,0,1,3,5,4,4,4,0,3,0,0,1,3),
(0,4,0,5,0,4,0,4,0,4,5,4,3,3,4,3,3,3,4,3,4,4,5,3,4,5,4,2,4,2,3,4,3,1,4,4,1,3,5,4,4,5,5,4,4,5,5,5,2,3,3,1,4,3,1,3,3,0,3,3,1,4,3,4,4,4,0,3,0,4,0,3,3,4,4,5,0,0,4,3,0,4,5),
(0,4,0,4,0,3,0,3,0,3,4,4,4,3,3,2,4,3,4,3,4,3,5,3,4,3,2,1,4,2,4,4,3,1,3,4,2,4,5,5,3,4,5,4,1,5,4,3,0,3,2,2,3,2,1,3,1,0,3,3,3,5,3,3,3,5,4,4,2,3,3,4,3,3,3,2,1,0,3,2,1,4,3),
(0,4,0,5,0,4,0,3,0,3,5,5,3,2,4,3,4,0,5,4,4,1,4,4,4,3,3,3,4,3,5,5,2,3,3,4,1,2,5,5,3,5,5,2,3,5,5,4,0,3,2,0,3,3,1,1,5,1,4,1,0,4,3,2,3,5,0,4,0,3,0,5,4,3,4,3,0,0,4,1,0,4,4),
(1,3,0,4,0,2,0,2,0,2,5,5,3,3,3,3,3,0,4,2,3,4,4,4,3,4,0,0,3,4,5,4,3,3,3,3,2,5,5,4,5,5,5,4,3,5,5,5,1,3,1,0,1,0,0,3,2,0,4,2,0,5,2,3,2,4,1,3,0,3,0,4,5,4,5,4,3,0,4,2,0,5,4),
(0,3,0,4,0,5,0,3,0,3,4,4,3,2,3,2,3,3,3,3,3,2,4,3,3,2,2,0,3,3,3,3,3,1,3,3,3,0,4,4,3,4,4,1,1,4,4,2,0,3,1,0,1,1,0,4,1,0,2,3,1,3,3,1,3,4,0,3,0,1,0,3,1,3,0,0,1,0,2,0,0,4,4),
(0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0),
(0,3,0,3,0,2,0,3,0,1,5,4,3,3,3,1,4,2,1,2,3,4,4,2,4,4,5,0,3,1,4,3,4,0,4,3,3,3,2,3,2,5,3,4,3,2,2,3,0,0,3,0,2,1,0,1,2,0,0,0,0,2,1,1,3,1,0,2,0,4,0,3,4,4,4,5,2,0,2,0,0,1,3),
(0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1,1,1,0,0,1,1,0,0,0,4,2,1,1,0,1,0,3,2,0,0,3,1,1,1,2,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3,0,1,0,0,0,2,0,0,0,1,4,0,4,2,1,0,0,0,0,0,1),
(0,0,0,0,0,0,0,0,0,1,0,1,0,0,0,0,1,0,0,0,0,0,0,1,0,1,0,0,0,0,3,1,0,0,0,2,0,2,1,0,0,1,2,1,0,1,1,0,0,3,0,0,0,0,0,0,0,0,0,0,0,1,3,1,0,0,0,0,0,1,0,0,2,1,0,0,0,0,0,0,0,0,2),
(0,4,0,4,0,4,0,3,0,4,4,3,4,2,4,3,2,0,4,4,4,3,5,3,5,3,3,2,4,2,4,3,4,3,1,4,0,2,3,4,4,4,3,3,3,4,4,4,3,4,1,3,4,3,2,1,2,1,3,3,3,4,4,3,3,5,0,4,0,3,0,4,3,3,3,2,1,0,3,0,0,3,3),
(0,4,0,3,0,3,0,3,0,3,5,5,3,3,3,3,4,3,4,3,3,3,4,4,4,3,3,3,3,4,3,5,3,3,1,3,2,4,5,5,5,5,4,3,4,5,5,3,2,2,3,3,3,3,2,3,3,1,2,3,2,4,3,3,3,4,0,4,0,2,0,4,3,2,2,1,2,0,3,0,0,4,1),
# fmt: off
jp2_char_context = (
(0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1),
(2, 4, 0, 4, 0, 3, 0, 4, 0, 3, 4, 4, 4, 2, 4, 3, 3, 4, 3, 2, 3, 3, 4, 2, 3, 3, 3, 2, 4, 1, 4, 3, 3, 1, 5, 4, 3, 4, 3, 4, 3, 5, 3, 0, 3, 5, 4, 2, 0, 3, 1, 0, 3, 3, 0, 3, 3, 0, 1, 1, 0, 4, 3, 0, 3, 3, 0, 4, 0, 2, 0, 3, 5, 5, 5, 5, 4, 0, 4, 1, 0, 3, 4),
(0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2),
(0, 4, 0, 5, 0, 5, 0, 4, 0, 4, 5, 4, 4, 3, 5, 3, 5, 1, 5, 3, 4, 3, 4, 4, 3, 4, 3, 3, 4, 3, 5, 4, 4, 3, 5, 5, 3, 5, 5, 5, 3, 5, 5, 3, 4, 5, 5, 3, 1, 3, 2, 0, 3, 4, 0, 4, 2, 0, 4, 2, 1, 5, 3, 2, 3, 5, 0, 4, 0, 2, 0, 5, 4, 4, 5, 4, 5, 0, 4, 0, 0, 4, 4),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0),
(0, 3, 0, 4, 0, 3, 0, 3, 0, 4, 5, 4, 3, 3, 3, 3, 4, 3, 5, 4, 4, 3, 5, 4, 4, 3, 4, 3, 4, 4, 4, 4, 5, 3, 4, 4, 3, 4, 5, 5, 4, 5, 5, 1, 4, 5, 4, 3, 0, 3, 3, 1, 3, 3, 0, 4, 4, 0, 3, 3, 1, 5, 3, 3, 3, 5, 0, 4, 0, 3, 0, 4, 4, 3, 4, 3, 3, 0, 4, 1, 1, 3, 4),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0),
(0, 4, 0, 3, 0, 3, 0, 4, 0, 3, 4, 4, 3, 2, 2, 1, 2, 1, 3, 1, 3, 3, 3, 3, 3, 4, 3, 1, 3, 3, 5, 3, 3, 0, 4, 3, 0, 5, 4, 3, 3, 5, 4, 4, 3, 4, 4, 5, 0, 1, 2, 0, 1, 2, 0, 2, 2, 0, 1, 0, 0, 5, 2, 2, 1, 4, 0, 3, 0, 1, 0, 4, 4, 3, 5, 4, 3, 0, 2, 1, 0, 4, 3),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0),
(0, 3, 0, 5, 0, 4, 0, 2, 1, 4, 4, 2, 4, 1, 4, 2, 4, 2, 4, 3, 3, 3, 4, 3, 3, 3, 3, 1, 4, 2, 3, 3, 3, 1, 4, 4, 1, 1, 1, 4, 3, 3, 2, 0, 2, 4, 3, 2, 0, 3, 3, 0, 3, 1, 1, 0, 0, 0, 3, 3, 0, 4, 2, 2, 3, 4, 0, 4, 0, 3, 0, 4, 4, 5, 3, 4, 4, 0, 3, 0, 0, 1, 4),
(1, 4, 0, 4, 0, 4, 0, 4, 0, 3, 5, 4, 4, 3, 4, 3, 5, 4, 3, 3, 4, 3, 5, 4, 4, 4, 4, 3, 4, 2, 4, 3, 3, 1, 5, 4, 3, 2, 4, 5, 4, 5, 5, 4, 4, 5, 4, 4, 0, 3, 2, 2, 3, 3, 0, 4, 3, 1, 3, 2, 1, 4, 3, 3, 4, 5, 0, 3, 0, 2, 0, 4, 5, 5, 4, 5, 4, 0, 4, 0, 0, 5, 4),
(0, 5, 0, 5, 0, 4, 0, 3, 0, 4, 4, 3, 4, 3, 3, 3, 4, 0, 4, 4, 4, 3, 4, 3, 4, 3, 3, 1, 4, 2, 4, 3, 4, 0, 5, 4, 1, 4, 5, 4, 4, 5, 3, 2, 4, 3, 4, 3, 2, 4, 1, 3, 3, 3, 2, 3, 2, 0, 4, 3, 3, 4, 3, 3, 3, 4, 0, 4, 0, 3, 0, 4, 5, 4, 4, 4, 3, 0, 4, 1, 0, 1, 3),
(0, 3, 1, 4, 0, 3, 0, 2, 0, 3, 4, 4, 3, 1, 4, 2, 3, 3, 4, 3, 4, 3, 4, 3, 4, 4, 3, 2, 3, 1, 5, 4, 4, 1, 4, 4, 3, 5, 4, 4, 3, 5, 5, 4, 3, 4, 4, 3, 1, 2, 3, 1, 2, 2, 0, 3, 2, 0, 3, 1, 0, 5, 3, 3, 3, 4, 3, 3, 3, 3, 4, 4, 4, 4, 5, 4, 2, 0, 3, 3, 2, 4, 3),
(0, 2, 0, 3, 0, 1, 0, 1, 0, 0, 3, 2, 0, 0, 2, 0, 1, 0, 2, 1, 3, 3, 3, 1, 2, 3, 1, 0, 1, 0, 4, 2, 1, 1, 3, 3, 0, 4, 3, 3, 1, 4, 3, 3, 0, 3, 3, 2, 0, 0, 0, 0, 1, 0, 0, 2, 0, 0, 0, 0, 0, 4, 1, 0, 2, 3, 2, 2, 2, 1, 3, 3, 3, 4, 4, 3, 2, 0, 3, 1, 0, 3, 3),
(0, 4, 0, 4, 0, 3, 0, 3, 0, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 3, 4, 2, 4, 3, 4, 3, 3, 2, 4, 3, 4, 5, 4, 1, 4, 5, 3, 5, 4, 5, 3, 5, 4, 0, 3, 5, 5, 3, 1, 3, 3, 2, 2, 3, 0, 3, 4, 1, 3, 3, 2, 4, 3, 3, 3, 4, 0, 4, 0, 3, 0, 4, 5, 4, 4, 5, 3, 0, 4, 1, 0, 3, 4),
(0, 2, 0, 3, 0, 3, 0, 0, 0, 2, 2, 2, 1, 0, 1, 0, 0, 0, 3, 0, 3, 0, 3, 0, 1, 3, 1, 0, 3, 1, 3, 3, 3, 1, 3, 3, 3, 0, 1, 3, 1, 3, 4, 0, 0, 3, 1, 1, 0, 3, 2, 0, 0, 0, 0, 1, 3, 0, 1, 0, 0, 3, 3, 2, 0, 3, 0, 0, 0, 0, 0, 3, 4, 3, 4, 3, 3, 0, 3, 0, 0, 2, 3),
(2, 3, 0, 3, 0, 2, 0, 1, 0, 3, 3, 4, 3, 1, 3, 1, 1, 1, 3, 1, 4, 3, 4, 3, 3, 3, 0, 0, 3, 1, 5, 4, 3, 1, 4, 3, 2, 5, 5, 4, 4, 4, 4, 3, 3, 4, 4, 4, 0, 2, 1, 1, 3, 2, 0, 1, 2, 0, 0, 1, 0, 4, 1, 3, 3, 3, 0, 3, 0, 1, 0, 4, 4, 4, 5, 5, 3, 0, 2, 0, 0, 4, 4),
(0, 2, 0, 1, 0, 3, 1, 3, 0, 2, 3, 3, 3, 0, 3, 1, 0, 0, 3, 0, 3, 2, 3, 1, 3, 2, 1, 1, 0, 0, 4, 2, 1, 0, 2, 3, 1, 4, 3, 2, 0, 4, 4, 3, 1, 3, 1, 3, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 4, 1, 1, 1, 2, 0, 3, 0, 0, 0, 3, 4, 2, 4, 3, 2, 0, 1, 0, 0, 3, 3),
(0, 1, 0, 4, 0, 5, 0, 4, 0, 2, 4, 4, 2, 3, 3, 2, 3, 3, 5, 3, 3, 3, 4, 3, 4, 2, 3, 0, 4, 3, 3, 3, 4, 1, 4, 3, 2, 1, 5, 5, 3, 4, 5, 1, 3, 5, 4, 2, 0, 3, 3, 0, 1, 3, 0, 4, 2, 0, 1, 3, 1, 4, 3, 3, 3, 3, 0, 3, 0, 1, 0, 3, 4, 4, 4, 5, 5, 0, 3, 0, 1, 4, 5),
(0, 2, 0, 3, 0, 3, 0, 0, 0, 2, 3, 1, 3, 0, 4, 0, 1, 1, 3, 0, 3, 4, 3, 2, 3, 1, 0, 3, 3, 2, 3, 1, 3, 0, 2, 3, 0, 2, 1, 4, 1, 2, 2, 0, 0, 3, 3, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 2, 2, 0, 3, 2, 1, 3, 3, 0, 2, 0, 2, 0, 0, 3, 3, 1, 2, 4, 0, 3, 0, 2, 2, 3),
(2, 4, 0, 5, 0, 4, 0, 4, 0, 2, 4, 4, 4, 3, 4, 3, 3, 3, 1, 2, 4, 3, 4, 3, 4, 4, 5, 0, 3, 3, 3, 3, 2, 0, 4, 3, 1, 4, 3, 4, 1, 4, 4, 3, 3, 4, 4, 3, 1, 2, 3, 0, 4, 2, 0, 4, 1, 0, 3, 3, 0, 4, 3, 3, 3, 4, 0, 4, 0, 2, 0, 3, 5, 3, 4, 5, 2, 0, 3, 0, 0, 4, 5),
(0, 3, 0, 4, 0, 1, 0, 1, 0, 1, 3, 2, 2, 1, 3, 0, 3, 0, 2, 0, 2, 0, 3, 0, 2, 0, 0, 0, 1, 0, 1, 1, 0, 0, 3, 1, 0, 0, 0, 4, 0, 3, 1, 0, 2, 1, 3, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 4, 2, 2, 3, 1, 0, 3, 0, 0, 0, 1, 4, 4, 4, 3, 0, 0, 4, 0, 0, 1, 4),
(1, 4, 1, 5, 0, 3, 0, 3, 0, 4, 5, 4, 4, 3, 5, 3, 3, 4, 4, 3, 4, 1, 3, 3, 3, 3, 2, 1, 4, 1, 5, 4, 3, 1, 4, 4, 3, 5, 4, 4, 3, 5, 4, 3, 3, 4, 4, 4, 0, 3, 3, 1, 2, 3, 0, 3, 1, 0, 3, 3, 0, 5, 4, 4, 4, 4, 4, 4, 3, 3, 5, 4, 4, 3, 3, 5, 4, 0, 3, 2, 0, 4, 4),
(0, 2, 0, 3, 0, 1, 0, 0, 0, 1, 3, 3, 3, 2, 4, 1, 3, 0, 3, 1, 3, 0, 2, 2, 1, 1, 0, 0, 2, 0, 4, 3, 1, 0, 4, 3, 0, 4, 4, 4, 1, 4, 3, 1, 1, 3, 3, 1, 0, 2, 0, 0, 1, 3, 0, 0, 0, 0, 2, 0, 0, 4, 3, 2, 4, 3, 5, 4, 3, 3, 3, 4, 3, 3, 4, 3, 3, 0, 2, 1, 0, 3, 3),
(0, 2, 0, 4, 0, 3, 0, 2, 0, 2, 5, 5, 3, 4, 4, 4, 4, 1, 4, 3, 3, 0, 4, 3, 4, 3, 1, 3, 3, 2, 4, 3, 0, 3, 4, 3, 0, 3, 4, 4, 2, 4, 4, 0, 4, 5, 3, 3, 2, 2, 1, 1, 1, 2, 0, 1, 5, 0, 3, 3, 2, 4, 3, 3, 3, 4, 0, 3, 0, 2, 0, 4, 4, 3, 5, 5, 0, 0, 3, 0, 2, 3, 3),
(0, 3, 0, 4, 0, 3, 0, 1, 0, 3, 4, 3, 3, 1, 3, 3, 3, 0, 3, 1, 3, 0, 4, 3, 3, 1, 1, 0, 3, 0, 3, 3, 0, 0, 4, 4, 0, 1, 5, 4, 3, 3, 5, 0, 3, 3, 4, 3, 0, 2, 0, 1, 1, 1, 0, 1, 3, 0, 1, 2, 1, 3, 3, 2, 3, 3, 0, 3, 0, 1, 0, 1, 3, 3, 4, 4, 1, 0, 1, 2, 2, 1, 3),
(0, 1, 0, 4, 0, 4, 0, 3, 0, 1, 3, 3, 3, 2, 3, 1, 1, 0, 3, 0, 3, 3, 4, 3, 2, 4, 2, 0, 1, 0, 4, 3, 2, 0, 4, 3, 0, 5, 3, 3, 2, 4, 4, 4, 3, 3, 3, 4, 0, 1, 3, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 4, 2, 3, 3, 3, 0, 3, 0, 0, 0, 4, 4, 4, 5, 3, 2, 0, 3, 3, 0, 3, 5),
(0, 2, 0, 3, 0, 0, 0, 3, 0, 1, 3, 0, 2, 0, 0, 0, 1, 0, 3, 1, 1, 3, 3, 0, 0, 3, 0, 0, 3, 0, 2, 3, 1, 0, 3, 1, 0, 3, 3, 2, 0, 4, 2, 2, 0, 2, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 1, 2, 0, 1, 0, 1, 0, 0, 0, 1, 3, 1, 2, 0, 0, 0, 1, 0, 0, 1, 4),
(0, 3, 0, 3, 0, 5, 0, 1, 0, 2, 4, 3, 1, 3, 3, 2, 1, 1, 5, 2, 1, 0, 5, 1, 2, 0, 0, 0, 3, 3, 2, 2, 3, 2, 4, 3, 0, 0, 3, 3, 1, 3, 3, 0, 2, 5, 3, 4, 0, 3, 3, 0, 1, 2, 0, 2, 2, 0, 3, 2, 0, 2, 2, 3, 3, 3, 0, 2, 0, 1, 0, 3, 4, 4, 2, 5, 4, 0, 3, 0, 0, 3, 5),
(0, 3, 0, 3, 0, 3, 0, 1, 0, 3, 3, 3, 3, 0, 3, 0, 2, 0, 2, 1, 1, 0, 2, 0, 1, 0, 0, 0, 2, 1, 0, 0, 1, 0, 3, 2, 0, 0, 3, 3, 1, 2, 3, 1, 0, 3, 3, 0, 0, 1, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 2, 3, 1, 2, 3, 0, 3, 0, 1, 0, 3, 2, 1, 0, 4, 3, 0, 1, 1, 0, 3, 3),
(0, 4, 0, 5, 0, 3, 0, 3, 0, 4, 5, 5, 4, 3, 5, 3, 4, 3, 5, 3, 3, 2, 5, 3, 4, 4, 4, 3, 4, 3, 4, 5, 5, 3, 4, 4, 3, 4, 4, 5, 4, 4, 4, 3, 4, 5, 5, 4, 2, 3, 4, 2, 3, 4, 0, 3, 3, 1, 4, 3, 2, 4, 3, 3, 5, 5, 0, 3, 0, 3, 0, 5, 5, 5, 5, 4, 4, 0, 4, 0, 1, 4, 4),
(0, 4, 0, 4, 0, 3, 0, 3, 0, 3, 5, 4, 4, 2, 3, 2, 5, 1, 3, 2, 5, 1, 4, 2, 3, 2, 3, 3, 4, 3, 3, 3, 3, 2, 5, 4, 1, 3, 3, 5, 3, 4, 4, 0, 4, 4, 3, 1, 1, 3, 1, 0, 2, 3, 0, 2, 3, 0, 3, 0, 0, 4, 3, 1, 3, 4, 0, 3, 0, 2, 0, 4, 4, 4, 3, 4, 5, 0, 4, 0, 0, 3, 4),
(0, 3, 0, 3, 0, 3, 1, 2, 0, 3, 4, 4, 3, 3, 3, 0, 2, 2, 4, 3, 3, 1, 3, 3, 3, 1, 1, 0, 3, 1, 4, 3, 2, 3, 4, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 4, 4, 3, 1, 3, 3, 1, 3, 3, 0, 4, 1, 0, 2, 2, 1, 4, 3, 2, 3, 3, 5, 4, 3, 3, 5, 4, 4, 3, 3, 0, 4, 0, 3, 2, 2, 4, 4),
(0, 2, 0, 1, 0, 0, 0, 0, 0, 1, 2, 1, 3, 0, 0, 0, 0, 0, 2, 0, 1, 2, 1, 0, 0, 1, 0, 0, 0, 0, 3, 0, 0, 1, 0, 1, 1, 3, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 2, 2, 0, 3, 4, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1),
(0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 4, 0, 4, 1, 4, 0, 3, 0, 4, 0, 3, 0, 4, 0, 3, 0, 3, 0, 4, 1, 5, 1, 4, 0, 0, 3, 0, 5, 0, 5, 2, 0, 1, 0, 0, 0, 2, 1, 4, 0, 1, 3, 0, 0, 3, 0, 0, 3, 1, 1, 4, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0),
(1, 4, 0, 5, 0, 3, 0, 2, 0, 3, 5, 4, 4, 3, 4, 3, 5, 3, 4, 3, 3, 0, 4, 3, 3, 3, 3, 3, 3, 2, 4, 4, 3, 1, 3, 4, 4, 5, 4, 4, 3, 4, 4, 1, 3, 5, 4, 3, 3, 3, 1, 2, 2, 3, 3, 1, 3, 1, 3, 3, 3, 5, 3, 3, 4, 5, 0, 3, 0, 3, 0, 3, 4, 3, 4, 4, 3, 0, 3, 0, 2, 4, 3),
(0, 1, 0, 4, 0, 0, 0, 0, 0, 1, 4, 0, 4, 1, 4, 2, 4, 0, 3, 0, 1, 0, 1, 0, 0, 0, 0, 0, 2, 0, 3, 1, 1, 1, 0, 3, 0, 0, 0, 1, 2, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 3, 0, 0, 0, 0, 3, 2, 0, 2, 2, 0, 1, 0, 0, 0, 2, 3, 2, 3, 3, 0, 0, 0, 0, 2, 1, 0),
(0, 5, 1, 5, 0, 3, 0, 3, 0, 5, 4, 4, 5, 1, 5, 3, 3, 0, 4, 3, 4, 3, 5, 3, 4, 3, 3, 2, 4, 3, 4, 3, 3, 0, 3, 3, 1, 4, 4, 3, 4, 4, 4, 3, 4, 5, 5, 3, 2, 3, 1, 1, 3, 3, 1, 3, 1, 1, 3, 3, 2, 4, 5, 3, 3, 5, 0, 4, 0, 3, 0, 4, 4, 3, 5, 3, 3, 0, 3, 4, 0, 4, 3),
(0, 5, 0, 5, 0, 3, 0, 2, 0, 4, 4, 3, 5, 2, 4, 3, 3, 3, 4, 4, 4, 3, 5, 3, 5, 3, 3, 1, 4, 0, 4, 3, 3, 0, 3, 3, 0, 4, 4, 4, 4, 5, 4, 3, 3, 5, 5, 3, 2, 3, 1, 2, 3, 2, 0, 1, 0, 0, 3, 2, 2, 4, 4, 3, 1, 5, 0, 4, 0, 3, 0, 4, 3, 1, 3, 2, 1, 0, 3, 3, 0, 3, 3),
(0, 4, 0, 5, 0, 5, 0, 4, 0, 4, 5, 5, 5, 3, 4, 3, 3, 2, 5, 4, 4, 3, 5, 3, 5, 3, 4, 0, 4, 3, 4, 4, 3, 2, 4, 4, 3, 4, 5, 4, 4, 5, 5, 0, 3, 5, 5, 4, 1, 3, 3, 2, 3, 3, 1, 3, 1, 0, 4, 3, 1, 4, 4, 3, 4, 5, 0, 4, 0, 2, 0, 4, 3, 4, 4, 3, 3, 0, 4, 0, 0, 5, 5),
(0, 4, 0, 4, 0, 5, 0, 1, 1, 3, 3, 4, 4, 3, 4, 1, 3, 0, 5, 1, 3, 0, 3, 1, 3, 1, 1, 0, 3, 0, 3, 3, 4, 0, 4, 3, 0, 4, 4, 4, 3, 4, 4, 0, 3, 5, 4, 1, 0, 3, 0, 0, 2, 3, 0, 3, 1, 0, 3, 1, 0, 3, 2, 1, 3, 5, 0, 3, 0, 1, 0, 3, 2, 3, 3, 4, 4, 0, 2, 2, 0, 4, 4),
(2, 4, 0, 5, 0, 4, 0, 3, 0, 4, 5, 5, 4, 3, 5, 3, 5, 3, 5, 3, 5, 2, 5, 3, 4, 3, 3, 4, 3, 4, 5, 3, 2, 1, 5, 4, 3, 2, 3, 4, 5, 3, 4, 1, 2, 5, 4, 3, 0, 3, 3, 0, 3, 2, 0, 2, 3, 0, 4, 1, 0, 3, 4, 3, 3, 5, 0, 3, 0, 1, 0, 4, 5, 5, 5, 4, 3, 0, 4, 2, 0, 3, 5),
(0, 5, 0, 4, 0, 4, 0, 2, 0, 5, 4, 3, 4, 3, 4, 3, 3, 3, 4, 3, 4, 2, 5, 3, 5, 3, 4, 1, 4, 3, 4, 4, 4, 0, 3, 5, 0, 4, 4, 4, 4, 5, 3, 1, 3, 4, 5, 3, 3, 3, 3, 3, 3, 3, 0, 2, 2, 0, 3, 3, 2, 4, 3, 3, 3, 5, 3, 4, 1, 3, 3, 5, 3, 2, 0, 0, 0, 0, 4, 3, 1, 3, 3),
(0, 1, 0, 3, 0, 3, 0, 1, 0, 1, 3, 3, 3, 2, 3, 3, 3, 0, 3, 0, 0, 0, 3, 1, 3, 0, 0, 0, 2, 2, 2, 3, 0, 0, 3, 2, 0, 1, 2, 4, 1, 3, 3, 0, 0, 3, 3, 3, 0, 1, 0, 0, 2, 1, 0, 0, 3, 0, 3, 1, 0, 3, 0, 0, 1, 3, 0, 2, 0, 1, 0, 3, 3, 1, 3, 3, 0, 0, 1, 1, 0, 3, 3),
(0, 2, 0, 3, 0, 2, 1, 4, 0, 2, 2, 3, 1, 1, 3, 1, 1, 0, 2, 0, 3, 1, 2, 3, 1, 3, 0, 0, 1, 0, 4, 3, 2, 3, 3, 3, 1, 4, 2, 3, 3, 3, 3, 1, 0, 3, 1, 4, 0, 1, 1, 0, 1, 2, 0, 1, 1, 0, 1, 1, 0, 3, 1, 3, 2, 2, 0, 1, 0, 0, 0, 2, 3, 3, 3, 1, 0, 0, 0, 0, 0, 2, 3),
(0, 5, 0, 4, 0, 5, 0, 2, 0, 4, 5, 5, 3, 3, 4, 3, 3, 1, 5, 4, 4, 2, 4, 4, 4, 3, 4, 2, 4, 3, 5, 5, 4, 3, 3, 4, 3, 3, 5, 5, 4, 5, 5, 1, 3, 4, 5, 3, 1, 4, 3, 1, 3, 3, 0, 3, 3, 1, 4, 3, 1, 4, 5, 3, 3, 5, 0, 4, 0, 3, 0, 5, 3, 3, 1, 4, 3, 0, 4, 0, 1, 5, 3),
(0, 5, 0, 5, 0, 4, 0, 2, 0, 4, 4, 3, 4, 3, 3, 3, 3, 3, 5, 4, 4, 4, 4, 4, 4, 5, 3, 3, 5, 2, 4, 4, 4, 3, 4, 4, 3, 3, 4, 4, 5, 5, 3, 3, 4, 3, 4, 3, 3, 4, 3, 3, 3, 3, 1, 2, 2, 1, 4, 3, 3, 5, 4, 4, 3, 4, 0, 4, 0, 3, 0, 4, 4, 4, 4, 4, 1, 0, 4, 2, 0, 2, 4),
(0, 4, 0, 4, 0, 3, 0, 1, 0, 3, 5, 2, 3, 0, 3, 0, 2, 1, 4, 2, 3, 3, 4, 1, 4, 3, 3, 2, 4, 1, 3, 3, 3, 0, 3, 3, 0, 0, 3, 3, 3, 5, 3, 3, 3, 3, 3, 2, 0, 2, 0, 0, 2, 0, 0, 2, 0, 0, 1, 0, 0, 3, 1, 2, 2, 3, 0, 3, 0, 2, 0, 4, 4, 3, 3, 4, 1, 0, 3, 0, 0, 2, 4),
(0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 2, 0, 0, 0, 0, 0, 1, 0, 2, 0, 1, 0, 0, 0, 0, 0, 3, 1, 3, 0, 3, 2, 0, 0, 0, 1, 0, 3, 2, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 4, 0, 2, 0, 0, 0, 0, 0, 0, 2),
(0, 2, 1, 3, 0, 2, 0, 2, 0, 3, 3, 3, 3, 1, 3, 1, 3, 3, 3, 3, 3, 3, 4, 2, 2, 1, 2, 1, 4, 0, 4, 3, 1, 3, 3, 3, 2, 4, 3, 5, 4, 3, 3, 3, 3, 3, 3, 3, 0, 1, 3, 0, 2, 0, 0, 1, 0, 0, 1, 0, 0, 4, 2, 0, 2, 3, 0, 3, 3, 0, 3, 3, 4, 2, 3, 1, 4, 0, 1, 2, 0, 2, 3),
(0, 3, 0, 3, 0, 1, 0, 3, 0, 2, 3, 3, 3, 0, 3, 1, 2, 0, 3, 3, 2, 3, 3, 2, 3, 2, 3, 1, 3, 0, 4, 3, 2, 0, 3, 3, 1, 4, 3, 3, 2, 3, 4, 3, 1, 3, 3, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 4, 1, 1, 0, 3, 0, 3, 1, 0, 2, 3, 3, 3, 3, 3, 1, 0, 0, 2, 0, 3, 3),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 2, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 3, 0, 3, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 2, 0, 2, 3, 0, 0, 0, 0, 0, 0, 0, 0, 3),
(0, 2, 0, 3, 1, 3, 0, 3, 0, 2, 3, 3, 3, 1, 3, 1, 3, 1, 3, 1, 3, 3, 3, 1, 3, 0, 2, 3, 1, 1, 4, 3, 3, 2, 3, 3, 1, 2, 2, 4, 1, 3, 3, 0, 1, 4, 2, 3, 0, 1, 3, 0, 3, 0, 0, 1, 3, 0, 2, 0, 0, 3, 3, 2, 1, 3, 0, 3, 0, 2, 0, 3, 4, 4, 4, 3, 1, 0, 3, 0, 0, 3, 3),
(0, 2, 0, 1, 0, 2, 0, 0, 0, 1, 3, 2, 2, 1, 3, 0, 1, 1, 3, 0, 3, 2, 3, 1, 2, 0, 2, 0, 1, 1, 3, 3, 3, 0, 3, 3, 1, 1, 2, 3, 2, 3, 3, 1, 2, 3, 2, 0, 0, 1, 0, 0, 0, 0, 0, 0, 3, 0, 1, 0, 0, 2, 1, 2, 1, 3, 0, 3, 0, 0, 0, 3, 4, 4, 4, 3, 2, 0, 2, 0, 0, 2, 4),
(0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 3, 1, 0, 0, 0, 0, 0, 0, 0, 3),
(0, 3, 0, 3, 0, 2, 0, 3, 0, 3, 3, 3, 2, 3, 2, 2, 2, 0, 3, 1, 3, 3, 3, 2, 3, 3, 0, 0, 3, 0, 3, 2, 2, 0, 2, 3, 1, 4, 3, 4, 3, 3, 2, 3, 1, 5, 4, 4, 0, 3, 1, 2, 1, 3, 0, 3, 1, 1, 2, 0, 2, 3, 1, 3, 1, 3, 0, 3, 0, 1, 0, 3, 3, 4, 4, 2, 1, 0, 2, 1, 0, 2, 4),
(0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 4, 2, 5, 1, 4, 0, 2, 0, 2, 1, 3, 1, 4, 0, 2, 1, 0, 0, 2, 1, 4, 1, 1, 0, 3, 3, 0, 5, 1, 3, 2, 3, 3, 1, 0, 3, 2, 3, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 4, 0, 1, 0, 3, 0, 2, 0, 1, 0, 3, 3, 3, 4, 3, 3, 0, 0, 0, 0, 2, 3),
(0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 2, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 1, 0, 0, 1, 0, 0, 0, 0, 0, 3),
(0, 1, 0, 3, 0, 4, 0, 3, 0, 2, 4, 3, 1, 0, 3, 2, 2, 1, 3, 1, 2, 2, 3, 1, 1, 1, 2, 1, 3, 0, 1, 2, 0, 1, 3, 2, 1, 3, 0, 5, 5, 1, 0, 0, 1, 3, 2, 1, 0, 3, 0, 0, 1, 0, 0, 0, 0, 0, 3, 4, 0, 1, 1, 1, 3, 2, 0, 2, 0, 1, 0, 2, 3, 3, 1, 2, 3, 0, 1, 0, 1, 0, 4),
(0, 0, 0, 1, 0, 3, 0, 3, 0, 2, 2, 1, 0, 0, 4, 0, 3, 0, 3, 1, 3, 0, 3, 0, 3, 0, 1, 0, 3, 0, 3, 1, 3, 0, 3, 3, 0, 0, 1, 2, 1, 1, 1, 0, 1, 2, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 1, 2, 0, 0, 2, 0, 0, 0, 0, 2, 3, 3, 3, 3, 0, 0, 0, 0, 1, 4),
(0, 0, 0, 3, 0, 3, 0, 0, 0, 0, 3, 1, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 0, 2, 0, 2, 3, 0, 0, 2, 2, 3, 1, 2, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 2, 0, 0, 0, 0, 2, 3),
(2, 4, 0, 5, 0, 5, 0, 4, 0, 3, 4, 3, 3, 3, 4, 3, 3, 3, 4, 3, 4, 4, 5, 4, 5, 5, 5, 2, 3, 0, 5, 5, 4, 1, 5, 4, 3, 1, 5, 4, 3, 4, 4, 3, 3, 4, 3, 3, 0, 3, 2, 0, 2, 3, 0, 3, 0, 0, 3, 3, 0, 5, 3, 2, 3, 3, 0, 3, 0, 3, 0, 3, 4, 5, 4, 5, 3, 0, 4, 3, 0, 3, 4),
(0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 3, 4, 3, 2, 3, 2, 3, 0, 4, 3, 3, 3, 3, 3, 3, 3, 3, 0, 3, 2, 4, 3, 3, 1, 3, 4, 3, 4, 4, 4, 3, 4, 4, 3, 2, 4, 4, 1, 0, 2, 0, 0, 1, 1, 0, 2, 0, 0, 3, 1, 0, 5, 3, 2, 1, 3, 0, 3, 0, 1, 2, 4, 3, 2, 4, 3, 3, 0, 3, 2, 0, 4, 4),
(0, 3, 0, 3, 0, 1, 0, 0, 0, 1, 4, 3, 3, 2, 3, 1, 3, 1, 4, 2, 3, 2, 4, 2, 3, 4, 3, 0, 2, 2, 3, 3, 3, 0, 3, 3, 3, 0, 3, 4, 1, 3, 3, 0, 3, 4, 3, 3, 0, 1, 1, 0, 1, 0, 0, 0, 4, 0, 3, 0, 0, 3, 1, 2, 1, 3, 0, 4, 0, 1, 0, 4, 3, 3, 4, 3, 3, 0, 2, 0, 0, 3, 3),
(0, 3, 0, 4, 0, 1, 0, 3, 0, 3, 4, 3, 3, 0, 3, 3, 3, 1, 3, 1, 3, 3, 4, 3, 3, 3, 0, 0, 3, 1, 5, 3, 3, 1, 3, 3, 2, 5, 4, 3, 3, 4, 5, 3, 2, 5, 3, 4, 0, 1, 0, 0, 0, 0, 0, 2, 0, 0, 1, 1, 0, 4, 2, 2, 1, 3, 0, 3, 0, 2, 0, 4, 4, 3, 5, 3, 2, 0, 1, 1, 0, 3, 4),
(0, 5, 0, 4, 0, 5, 0, 2, 0, 4, 4, 3, 3, 2, 3, 3, 3, 1, 4, 3, 4, 1, 5, 3, 4, 3, 4, 0, 4, 2, 4, 3, 4, 1, 5, 4, 0, 4, 4, 4, 4, 5, 4, 1, 3, 5, 4, 2, 1, 4, 1, 1, 3, 2, 0, 3, 1, 0, 3, 2, 1, 4, 3, 3, 3, 4, 0, 4, 0, 3, 0, 4, 4, 4, 3, 3, 3, 0, 4, 2, 0, 3, 4),
(1, 4, 0, 4, 0, 3, 0, 1, 0, 3, 3, 3, 1, 1, 3, 3, 2, 2, 3, 3, 1, 0, 3, 2, 2, 1, 2, 0, 3, 1, 2, 1, 2, 0, 3, 2, 0, 2, 2, 3, 3, 4, 3, 0, 3, 3, 1, 2, 0, 1, 1, 3, 1, 2, 0, 0, 3, 0, 1, 1, 0, 3, 2, 2, 3, 3, 0, 3, 0, 0, 0, 2, 3, 3, 4, 3, 3, 0, 1, 0, 0, 1, 4),
(0, 4, 0, 4, 0, 4, 0, 0, 0, 3, 4, 4, 3, 1, 4, 2, 3, 2, 3, 3, 3, 1, 4, 3, 4, 0, 3, 0, 4, 2, 3, 3, 2, 2, 5, 4, 2, 1, 3, 4, 3, 4, 3, 1, 3, 3, 4, 2, 0, 2, 1, 0, 3, 3, 0, 0, 2, 0, 3, 1, 0, 4, 4, 3, 4, 3, 0, 4, 0, 1, 0, 2, 4, 4, 4, 4, 4, 0, 3, 2, 0, 3, 3),
(0, 0, 0, 1, 0, 4, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 2, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 2),
(0, 2, 0, 3, 0, 4, 0, 4, 0, 1, 3, 3, 3, 0, 4, 0, 2, 1, 2, 1, 1, 1, 2, 0, 3, 1, 1, 0, 1, 0, 3, 1, 0, 0, 3, 3, 2, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 2, 2, 0, 3, 1, 0, 0, 1, 0, 1, 1, 0, 1, 2, 0, 3, 0, 0, 0, 0, 1, 0, 0, 3, 3, 4, 3, 1, 0, 1, 0, 3, 0, 2),
(0, 0, 0, 3, 0, 5, 0, 0, 0, 0, 1, 0, 2, 0, 3, 1, 0, 1, 3, 0, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 4, 0, 0, 0, 2, 3, 0, 1, 4, 1, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 3, 0, 0, 0, 0, 0, 3),
(0, 2, 0, 5, 0, 5, 0, 1, 0, 2, 4, 3, 3, 2, 5, 1, 3, 2, 3, 3, 3, 0, 4, 1, 2, 0, 3, 0, 4, 0, 2, 2, 1, 1, 5, 3, 0, 0, 1, 4, 2, 3, 2, 0, 3, 3, 3, 2, 0, 2, 4, 1, 1, 2, 0, 1, 1, 0, 3, 1, 0, 1, 3, 1, 2, 3, 0, 2, 0, 0, 0, 1, 3, 5, 4, 4, 4, 0, 3, 0, 0, 1, 3),
(0, 4, 0, 5, 0, 4, 0, 4, 0, 4, 5, 4, 3, 3, 4, 3, 3, 3, 4, 3, 4, 4, 5, 3, 4, 5, 4, 2, 4, 2, 3, 4, 3, 1, 4, 4, 1, 3, 5, 4, 4, 5, 5, 4, 4, 5, 5, 5, 2, 3, 3, 1, 4, 3, 1, 3, 3, 0, 3, 3, 1, 4, 3, 4, 4, 4, 0, 3, 0, 4, 0, 3, 3, 4, 4, 5, 0, 0, 4, 3, 0, 4, 5),
(0, 4, 0, 4, 0, 3, 0, 3, 0, 3, 4, 4, 4, 3, 3, 2, 4, 3, 4, 3, 4, 3, 5, 3, 4, 3, 2, 1, 4, 2, 4, 4, 3, 1, 3, 4, 2, 4, 5, 5, 3, 4, 5, 4, 1, 5, 4, 3, 0, 3, 2, 2, 3, 2, 1, 3, 1, 0, 3, 3, 3, 5, 3, 3, 3, 5, 4, 4, 2, 3, 3, 4, 3, 3, 3, 2, 1, 0, 3, 2, 1, 4, 3),
(0, 4, 0, 5, 0, 4, 0, 3, 0, 3, 5, 5, 3, 2, 4, 3, 4, 0, 5, 4, 4, 1, 4, 4, 4, 3, 3, 3, 4, 3, 5, 5, 2, 3, 3, 4, 1, 2, 5, 5, 3, 5, 5, 2, 3, 5, 5, 4, 0, 3, 2, 0, 3, 3, 1, 1, 5, 1, 4, 1, 0, 4, 3, 2, 3, 5, 0, 4, 0, 3, 0, 5, 4, 3, 4, 3, 0, 0, 4, 1, 0, 4, 4),
(1, 3, 0, 4, 0, 2, 0, 2, 0, 2, 5, 5, 3, 3, 3, 3, 3, 0, 4, 2, 3, 4, 4, 4, 3, 4, 0, 0, 3, 4, 5, 4, 3, 3, 3, 3, 2, 5, 5, 4, 5, 5, 5, 4, 3, 5, 5, 5, 1, 3, 1, 0, 1, 0, 0, 3, 2, 0, 4, 2, 0, 5, 2, 3, 2, 4, 1, 3, 0, 3, 0, 4, 5, 4, 5, 4, 3, 0, 4, 2, 0, 5, 4),
(0, 3, 0, 4, 0, 5, 0, 3, 0, 3, 4, 4, 3, 2, 3, 2, 3, 3, 3, 3, 3, 2, 4, 3, 3, 2, 2, 0, 3, 3, 3, 3, 3, 1, 3, 3, 3, 0, 4, 4, 3, 4, 4, 1, 1, 4, 4, 2, 0, 3, 1, 0, 1, 1, 0, 4, 1, 0, 2, 3, 1, 3, 3, 1, 3, 4, 0, 3, 0, 1, 0, 3, 1, 3, 0, 0, 1, 0, 2, 0, 0, 4, 4),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0),
(0, 3, 0, 3, 0, 2, 0, 3, 0, 1, 5, 4, 3, 3, 3, 1, 4, 2, 1, 2, 3, 4, 4, 2, 4, 4, 5, 0, 3, 1, 4, 3, 4, 0, 4, 3, 3, 3, 2, 3, 2, 5, 3, 4, 3, 2, 2, 3, 0, 0, 3, 0, 2, 1, 0, 1, 2, 0, 0, 0, 0, 2, 1, 1, 3, 1, 0, 2, 0, 4, 0, 3, 4, 4, 4, 5, 2, 0, 2, 0, 0, 1, 3),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 4, 2, 1, 1, 0, 1, 0, 3, 2, 0, 0, 3, 1, 1, 1, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 1, 0, 0, 0, 2, 0, 0, 0, 1, 4, 0, 4, 2, 1, 0, 0, 0, 0, 0, 1),
(0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 3, 1, 0, 0, 0, 2, 0, 2, 1, 0, 0, 1, 2, 1, 0, 1, 1, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 1, 0, 0, 0, 0, 0, 1, 0, 0, 2, 1, 0, 0, 0, 0, 0, 0, 0, 0, 2),
(0, 4, 0, 4, 0, 4, 0, 3, 0, 4, 4, 3, 4, 2, 4, 3, 2, 0, 4, 4, 4, 3, 5, 3, 5, 3, 3, 2, 4, 2, 4, 3, 4, 3, 1, 4, 0, 2, 3, 4, 4, 4, 3, 3, 3, 4, 4, 4, 3, 4, 1, 3, 4, 3, 2, 1, 2, 1, 3, 3, 3, 4, 4, 3, 3, 5, 0, 4, 0, 3, 0, 4, 3, 3, 3, 2, 1, 0, 3, 0, 0, 3, 3),
(0, 4, 0, 3, 0, 3, 0, 3, 0, 3, 5, 5, 3, 3, 3, 3, 4, 3, 4, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 4, 3, 5, 3, 3, 1, 3, 2, 4, 5, 5, 5, 5, 4, 3, 4, 5, 5, 3, 2, 2, 3, 3, 3, 3, 2, 3, 3, 1, 2, 3, 2, 4, 3, 3, 3, 4, 0, 4, 0, 2, 0, 4, 3, 2, 2, 1, 2, 0, 3, 0, 0, 4, 1),
)
# fmt: on
class JapaneseContextAnalysis(object):
class JapaneseContextAnalysis:
NUM_OF_CATEGORY = 6
DONT_KNOW = -1
ENOUGH_REL_THRESHOLD = 100
MAX_REL_THRESHOLD = 1000
MINIMUM_DATA_THRESHOLD = 4
def __init__(self):
self._total_rel = None
self._rel_sample = None
self._need_to_skip_char_num = None
self._last_char_order = None
self._done = None
def __init__(self) -> None:
self._total_rel = 0
self._rel_sample: List[int] = []
self._need_to_skip_char_num = 0
self._last_char_order = -1
self._done = False
self.reset()
def reset(self):
def reset(self) -> None:
self._total_rel = 0 # total sequence received
# category counters, each integer counts sequence in its category
self._rel_sample = [0] * self.NUM_OF_CATEGORY
@@ -140,7 +144,7 @@ class JapaneseContextAnalysis(object):
# been made
self._done = False
def feed(self, byte_str, num_bytes):
def feed(self, byte_str: Union[bytes, bytearray], num_bytes: int) -> None:
if self._done:
return
@@ -153,7 +157,7 @@ class JapaneseContextAnalysis(object):
# this character will simply our logic and improve performance.
i = self._need_to_skip_char_num
while i < num_bytes:
order, char_len = self.get_order(byte_str[i:i + 2])
order, char_len = self.get_order(byte_str[i : i + 2])
i += char_len
if i > num_bytes:
self._need_to_skip_char_num = i - num_bytes
@@ -164,32 +168,34 @@ class JapaneseContextAnalysis(object):
if self._total_rel > self.MAX_REL_THRESHOLD:
self._done = True
break
self._rel_sample[jp2CharContext[self._last_char_order][order]] += 1
self._rel_sample[
jp2_char_context[self._last_char_order][order]
] += 1
self._last_char_order = order
def got_enough_data(self):
def got_enough_data(self) -> bool:
return self._total_rel > self.ENOUGH_REL_THRESHOLD
def get_confidence(self):
def get_confidence(self) -> float:
# This is just one way to calculate confidence. It works well for me.
if self._total_rel > self.MINIMUM_DATA_THRESHOLD:
return (self._total_rel - self._rel_sample[0]) / self._total_rel
else:
return self.DONT_KNOW
return self.DONT_KNOW
def get_order(self, byte_str):
def get_order(self, _: Union[bytes, bytearray]) -> Tuple[int, int]:
return -1, 1
class SJISContextAnalysis(JapaneseContextAnalysis):
def __init__(self):
super(SJISContextAnalysis, self).__init__()
def __init__(self) -> None:
super().__init__()
self._charset_name = "SHIFT_JIS"
@property
def charset_name(self):
def charset_name(self) -> str:
return self._charset_name
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> Tuple[int, int]:
if not byte_str:
return -1, 1
# find out current char's byte length
@@ -209,8 +215,9 @@ class SJISContextAnalysis(JapaneseContextAnalysis):
return -1, char_len
class EUCJPContextAnalysis(JapaneseContextAnalysis):
def get_order(self, byte_str):
def get_order(self, byte_str: Union[bytes, bytearray]) -> Tuple[int, int]:
if not byte_str:
return -1, 1
# find out current char's byte length
@@ -229,5 +236,3 @@ class EUCJPContextAnalysis(JapaneseContextAnalysis):
return second_char - 0xA1, char_len
return -1, char_len

1061
venv/Lib/site-packages/pip/_vendor/chardet/langbulgarianmodel.py
View File

File diff suppressed because it is too large Load Diff

1061
venv/Lib/site-packages/pip/_vendor/chardet/langgreekmodel.py
View File

File diff suppressed because it is too large Load Diff

533
venv/Lib/site-packages/pip/_vendor/chardet/langhebrewmodel.py
View File

@@ -1,9 +1,5 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel
# 3: Positive
# 2: Likely
# 1: Unlikely
@@ -4115,269 +4111,270 @@ HEBREW_LANG_MODEL = {
# Character Mapping Table(s):
WINDOWS_1255_HEBREW_CHAR_TO_ORDER = {
0: 255, # '\x00'
1: 255, # '\x01'
2: 255, # '\x02'
3: 255, # '\x03'
4: 255, # '\x04'
5: 255, # '\x05'
6: 255, # '\x06'
7: 255, # '\x07'
8: 255, # '\x08'
9: 255, # '\t'
10: 254, # '\n'
11: 255, # '\x0b'
12: 255, # '\x0c'
13: 254, # '\r'
14: 255, # '\x0e'
15: 255, # '\x0f'
16: 255, # '\x10'
17: 255, # '\x11'
18: 255, # '\x12'
19: 255, # '\x13'
20: 255, # '\x14'
21: 255, # '\x15'
22: 255, # '\x16'
23: 255, # '\x17'
24: 255, # '\x18'
25: 255, # '\x19'
26: 255, # '\x1a'
27: 255, # '\x1b'
28: 255, # '\x1c'
29: 255, # '\x1d'
30: 255, # '\x1e'
31: 255, # '\x1f'
32: 253, # ' '
33: 253, # '!'
34: 253, # '"'
35: 253, # '#'
36: 253, # '$'
37: 253, # '%'
38: 253, # '&'
39: 253, # "'"
40: 253, # '('
41: 253, # ')'
42: 253, # '*'
43: 253, # '+'
44: 253, # ','
45: 253, # '-'
46: 253, # '.'
47: 253, # '/'
48: 252, # '0'
49: 252, # '1'
50: 252, # '2'
51: 252, # '3'
52: 252, # '4'
53: 252, # '5'
54: 252, # '6'
55: 252, # '7'
56: 252, # '8'
57: 252, # '9'
58: 253, # ':'
59: 253, # ';'
60: 253, # '<'
61: 253, # '='
62: 253, # '>'
63: 253, # '?'
64: 253, # '@'
65: 69, # 'A'
66: 91, # 'B'
67: 79, # 'C'
68: 80, # 'D'
69: 92, # 'E'
70: 89, # 'F'
71: 97, # 'G'
72: 90, # 'H'
73: 68, # 'I'
74: 111, # 'J'
75: 112, # 'K'
76: 82, # 'L'
77: 73, # 'M'
78: 95, # 'N'
79: 85, # 'O'
80: 78, # 'P'
81: 121, # 'Q'
82: 86, # 'R'
83: 71, # 'S'
84: 67, # 'T'
85: 102, # 'U'
86: 107, # 'V'
87: 84, # 'W'
88: 114, # 'X'
89: 103, # 'Y'
90: 115, # 'Z'
91: 253, # '['
92: 253, # '\\'
93: 253, # ']'
94: 253, # '^'
95: 253, # '_'
96: 253, # '`'
97: 50, # 'a'
98: 74, # 'b'
99: 60, # 'c'
100: 61, # 'd'
101: 42, # 'e'
102: 76, # 'f'
103: 70, # 'g'
104: 64, # 'h'
105: 53, # 'i'
106: 105, # 'j'
107: 93, # 'k'
108: 56, # 'l'
109: 65, # 'm'
110: 54, # 'n'
111: 49, # 'o'
112: 66, # 'p'
113: 110, # 'q'
114: 51, # 'r'
115: 43, # 's'
116: 44, # 't'
117: 63, # 'u'
118: 81, # 'v'
119: 77, # 'w'
120: 98, # 'x'
121: 75, # 'y'
122: 108, # 'z'
123: 253, # '{'
124: 253, # '|'
125: 253, # '}'
126: 253, # '~'
127: 253, # '\x7f'
128: 124, # '€'
129: 202, # None
130: 203, # '‚'
131: 204, # 'ƒ'
132: 205, # '„'
133: 40, # '…'
134: 58, # '†'
135: 206, # '‡'
136: 207, # 'ˆ'
137: 208, # '‰'
138: 209, # None
139: 210, # '‹'
140: 211, # None
141: 212, # None
142: 213, # None
143: 214, # None
144: 215, # None
145: 83, # '‘'
146: 52, # '’'
147: 47, # '“'
148: 46, # '”'
149: 72, # '•'
150: 32, # '–'
151: 94, # '—'
152: 216, # '˜'
153: 113, # '™'
154: 217, # None
155: 109, # '›'
156: 218, # None
157: 219, # None
158: 220, # None
159: 221, # None
160: 34, # '\xa0'
161: 116, # '¡'
162: 222, # '¢'
163: 118, # '£'
164: 100, # '₪'
165: 223, # '¥'
166: 224, # '¦'
167: 117, # '§'
168: 119, # '¨'
169: 104, # '©'
170: 125, # '×'
171: 225, # '«'
172: 226, # '¬'
173: 87, # '\xad'
174: 99, # '®'
175: 227, # '¯'
176: 106, # '°'
177: 122, # '±'
178: 123, # '²'
179: 228, # '³'
180: 55, # '´'
181: 229, # 'µ'
182: 230, # '¶'
183: 101, # '·'
184: 231, # '¸'
185: 232, # '¹'
186: 120, # '÷'
187: 233, # '»'
188: 48, # '¼'
189: 39, # '½'
190: 57, # '¾'
191: 234, # '¿'
192: 30, # 'ְ'
193: 59, # 'ֱ'
194: 41, # 'ֲ'
195: 88, # 'ֳ'
196: 33, # 'ִ'
197: 37, # 'ֵ'
198: 36, # 'ֶ'
199: 31, # 'ַ'
200: 29, # 'ָ'
201: 35, # 'ֹ'
202: 235, # None
203: 62, # 'ֻ'
204: 28, # 'ּ'
205: 236, # 'ֽ'
206: 126, # '־'
207: 237, # 'ֿ'
208: 238, # '׀'
209: 38, # 'ׁ'
210: 45, # 'ׂ'
211: 239, # '׃'
212: 240, # 'װ'
213: 241, # 'ױ'
214: 242, # 'ײ'
215: 243, # '׳'
216: 127, # '״'
217: 244, # None
218: 245, # None
219: 246, # None
220: 247, # None
221: 248, # None
222: 249, # None
223: 250, # None
224: 9, # 'א'
225: 8, # 'ב'
226: 20, # 'ג'
227: 16, # 'ד'
228: 3, # 'ה'
229: 2, # 'ו'
230: 24, # 'ז'
231: 14, # 'ח'
232: 22, # 'ט'
233: 1, # 'י'
234: 25, # 'ך'
235: 15, # 'כ'
236: 4, # 'ל'
237: 11, # 'ם'
238: 6, # 'מ'
239: 23, # 'ן'
240: 12, # 'נ'
241: 19, # 'ס'
242: 13, # 'ע'
243: 26, # 'ף'
244: 18, # 'פ'
245: 27, # 'ץ'
246: 21, # 'צ'
247: 17, # 'ק'
248: 7, # 'ר'
249: 10, # 'ש'
250: 5, # 'ת'
251: 251, # None
252: 252, # None
253: 128, # '\u200e'
254: 96, # '\u200f'
255: 253, # None
0: 255, # '\x00'
1: 255, # '\x01'
2: 255, # '\x02'
3: 255, # '\x03'
4: 255, # '\x04'
5: 255, # '\x05'
6: 255, # '\x06'
7: 255, # '\x07'
8: 255, # '\x08'
9: 255, # '\t'
10: 254, # '\n'
11: 255, # '\x0b'
12: 255, # '\x0c'
13: 254, # '\r'
14: 255, # '\x0e'
15: 255, # '\x0f'
16: 255, # '\x10'
17: 255, # '\x11'
18: 255, # '\x12'
19: 255, # '\x13'
20: 255, # '\x14'
21: 255, # '\x15'
22: 255, # '\x16'
23: 255, # '\x17'
24: 255, # '\x18'
25: 255, # '\x19'
26: 255, # '\x1a'
27: 255, # '\x1b'
28: 255, # '\x1c'
29: 255, # '\x1d'
30: 255, # '\x1e'
31: 255, # '\x1f'
32: 253, # ' '
33: 253, # '!'
34: 253, # '"'
35: 253, # '#'
36: 253, # '$'
37: 253, # '%'
38: 253, # '&'
39: 253, # "'"
40: 253, # '('
41: 253, # ')'
42: 253, # '*'
43: 253, # '+'
44: 253, # ','
45: 253, # '-'
46: 253, # '.'
47: 253, # '/'
48: 252, # '0'
49: 252, # '1'
50: 252, # '2'
51: 252, # '3'
52: 252, # '4'
53: 252, # '5'
54: 252, # '6'
55: 252, # '7'
56: 252, # '8'
57: 252, # '9'
58: 253, # ':'
59: 253, # ';'
60: 253, # '<'
61: 253, # '='
62: 253, # '>'
63: 253, # '?'
64: 253, # '@'
65: 69, # 'A'
66: 91, # 'B'
67: 79, # 'C'
68: 80, # 'D'
69: 92, # 'E'
70: 89, # 'F'
71: 97, # 'G'
72: 90, # 'H'
73: 68, # 'I'
74: 111, # 'J'
75: 112, # 'K'
76: 82, # 'L'
77: 73, # 'M'
78: 95, # 'N'
79: 85, # 'O'
80: 78, # 'P'
81: 121, # 'Q'
82: 86, # 'R'
83: 71, # 'S'
84: 67, # 'T'
85: 102, # 'U'
86: 107, # 'V'
87: 84, # 'W'
88: 114, # 'X'
89: 103, # 'Y'
90: 115, # 'Z'
91: 253, # '['
92: 253, # '\\'
93: 253, # ']'
94: 253, # '^'
95: 253, # '_'
96: 253, # '`'
97: 50, # 'a'
98: 74, # 'b'
99: 60, # 'c'
100: 61, # 'd'
101: 42, # 'e'
102: 76, # 'f'
103: 70, # 'g'
104: 64, # 'h'
105: 53, # 'i'
106: 105, # 'j'
107: 93, # 'k'
108: 56, # 'l'
109: 65, # 'm'
110: 54, # 'n'
111: 49, # 'o'
112: 66, # 'p'
113: 110, # 'q'
114: 51, # 'r'
115: 43, # 's'
116: 44, # 't'
117: 63, # 'u'
118: 81, # 'v'
119: 77, # 'w'
120: 98, # 'x'
121: 75, # 'y'
122: 108, # 'z'
123: 253, # '{'
124: 253, # '|'
125: 253, # '}'
126: 253, # '~'
127: 253, # '\x7f'
128: 124, # '€'
129: 202, # None
130: 203, # '‚'
131: 204, # 'ƒ'
132: 205, # '„'
133: 40, # '…'
134: 58, # '†'
135: 206, # '‡'
136: 207, # 'ˆ'
137: 208, # '‰'
138: 209, # None
139: 210, # '‹'
140: 211, # None
141: 212, # None
142: 213, # None
143: 214, # None
144: 215, # None
145: 83, # '‘'
146: 52, # '’'
147: 47, # '“'
148: 46, # '”'
149: 72, # '•'
150: 32, # '–'
151: 94, # '—'
152: 216, # '˜'
153: 113, # '™'
154: 217, # None
155: 109, # '›'
156: 218, # None
157: 219, # None
158: 220, # None
159: 221, # None
160: 34, # '\xa0'
161: 116, # '¡'
162: 222, # '¢'
163: 118, # '£'
164: 100, # '₪'
165: 223, # '¥'
166: 224, # '¦'
167: 117, # '§'
168: 119, # '¨'
169: 104, # '©'
170: 125, # '×'
171: 225, # '«'
172: 226, # '¬'
173: 87, # '\xad'
174: 99, # '®'
175: 227, # '¯'
176: 106, # '°'
177: 122, # '±'
178: 123, # '²'
179: 228, # '³'
180: 55, # '´'
181: 229, # 'µ'
182: 230, # '¶'
183: 101, # '·'
184: 231, # '¸'
185: 232, # '¹'
186: 120, # '÷'
187: 233, # '»'
188: 48, # '¼'
189: 39, # '½'
190: 57, # '¾'
191: 234, # '¿'
192: 30, # 'ְ'
193: 59, # 'ֱ'
194: 41, # 'ֲ'
195: 88, # 'ֳ'
196: 33, # 'ִ'
197: 37, # 'ֵ'
198: 36, # 'ֶ'
199: 31, # 'ַ'
200: 29, # 'ָ'
201: 35, # 'ֹ'
202: 235, # None
203: 62, # 'ֻ'
204: 28, # 'ּ'
205: 236, # 'ֽ'
206: 126, # '־'
207: 237, # 'ֿ'
208: 238, # '׀'
209: 38, # 'ׁ'
210: 45, # 'ׂ'
211: 239, # '׃'
212: 240, # 'װ'
213: 241, # 'ױ'
214: 242, # 'ײ'
215: 243, # '׳'
216: 127, # '״'
217: 244, # None
218: 245, # None
219: 246, # None
220: 247, # None
221: 248, # None
222: 249, # None
223: 250, # None
224: 9, # 'א'
225: 8, # 'ב'
226: 20, # 'ג'
227: 16, # 'ד'
228: 3, # 'ה'
229: 2, # 'ו'
230: 24, # 'ז'
231: 14, # 'ח'
232: 22, # 'ט'
233: 1, # 'י'
234: 25, # 'ך'
235: 15, # 'כ'
236: 4, # 'ל'
237: 11, # 'ם'
238: 6, # 'מ'
239: 23, # 'ן'
240: 12, # 'נ'
241: 19, # 'ס'
242: 13, # 'ע'
243: 26, # 'ף'
244: 18, # 'פ'
245: 27, # 'ץ'
246: 21, # 'צ'
247: 17, # 'ק'
248: 7, # 'ר'
249: 10, # 'ש'
250: 5, # 'ת'
251: 251, # None
252: 252, # None
253: 128, # '\u200e'
254: 96, # '\u200f'
255: 253, # None
}
WINDOWS_1255_HEBREW_MODEL = SingleByteCharSetModel(charset_name='windows-1255',
language='Hebrew',
char_to_order_map=WINDOWS_1255_HEBREW_CHAR_TO_ORDER,
language_model=HEBREW_LANG_MODEL,
typical_positive_ratio=0.984004,
keep_ascii_letters=False,
alphabet='אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ')
WINDOWS_1255_HEBREW_MODEL = SingleByteCharSetModel(
charset_name="windows-1255",
language="Hebrew",
char_to_order_map=WINDOWS_1255_HEBREW_CHAR_TO_ORDER,
language_model=HEBREW_LANG_MODEL,
typical_positive_ratio=0.984004,
keep_ascii_letters=False,
alphabet="אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ",
)

1061
venv/Lib/site-packages/pip/_vendor/chardet/langhungarianmodel.py
View File

File diff suppressed because it is too large Load Diff

3173
venv/Lib/site-packages/pip/_vendor/chardet/langrussianmodel.py
View File

File diff suppressed because it is too large Load Diff

533
venv/Lib/site-packages/pip/_vendor/chardet/langthaimodel.py
View File

@@ -1,9 +1,5 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel
# 3: Positive
# 2: Likely
# 1: Unlikely
@@ -4115,269 +4111,270 @@ THAI_LANG_MODEL = {
# Character Mapping Table(s):
TIS_620_THAI_CHAR_TO_ORDER = {
0: 255, # '\x00'
1: 255, # '\x01'
2: 255, # '\x02'
3: 255, # '\x03'
4: 255, # '\x04'
5: 255, # '\x05'
6: 255, # '\x06'
7: 255, # '\x07'
8: 255, # '\x08'
9: 255, # '\t'
10: 254, # '\n'
11: 255, # '\x0b'
12: 255, # '\x0c'
13: 254, # '\r'
14: 255, # '\x0e'
15: 255, # '\x0f'
16: 255, # '\x10'
17: 255, # '\x11'
18: 255, # '\x12'
19: 255, # '\x13'
20: 255, # '\x14'
21: 255, # '\x15'
22: 255, # '\x16'
23: 255, # '\x17'
24: 255, # '\x18'
25: 255, # '\x19'
26: 255, # '\x1a'
27: 255, # '\x1b'
28: 255, # '\x1c'
29: 255, # '\x1d'
30: 255, # '\x1e'
31: 255, # '\x1f'
32: 253, # ' '
33: 253, # '!'
34: 253, # '"'
35: 253, # '#'
36: 253, # '$'
37: 253, # '%'
38: 253, # '&'
39: 253, # "'"
40: 253, # '('
41: 253, # ')'
42: 253, # '*'
43: 253, # '+'
44: 253, # ','
45: 253, # '-'
46: 253, # '.'
47: 253, # '/'
48: 252, # '0'
49: 252, # '1'
50: 252, # '2'
51: 252, # '3'
52: 252, # '4'
53: 252, # '5'
54: 252, # '6'
55: 252, # '7'
56: 252, # '8'
57: 252, # '9'
58: 253, # ':'
59: 253, # ';'
60: 253, # '<'
61: 253, # '='
62: 253, # '>'
63: 253, # '?'
64: 253, # '@'
65: 182, # 'A'
66: 106, # 'B'
67: 107, # 'C'
68: 100, # 'D'
69: 183, # 'E'
70: 184, # 'F'
71: 185, # 'G'
72: 101, # 'H'
73: 94, # 'I'
74: 186, # 'J'
75: 187, # 'K'
76: 108, # 'L'
77: 109, # 'M'
78: 110, # 'N'
79: 111, # 'O'
80: 188, # 'P'
81: 189, # 'Q'
82: 190, # 'R'
83: 89, # 'S'
84: 95, # 'T'
85: 112, # 'U'
86: 113, # 'V'
87: 191, # 'W'
88: 192, # 'X'
89: 193, # 'Y'
90: 194, # 'Z'
91: 253, # '['
92: 253, # '\\'
93: 253, # ']'
94: 253, # '^'
95: 253, # '_'
96: 253, # '`'
97: 64, # 'a'
98: 72, # 'b'
99: 73, # 'c'
100: 114, # 'd'
101: 74, # 'e'
102: 115, # 'f'
103: 116, # 'g'
104: 102, # 'h'
105: 81, # 'i'
106: 201, # 'j'
107: 117, # 'k'
108: 90, # 'l'
109: 103, # 'm'
110: 78, # 'n'
111: 82, # 'o'
112: 96, # 'p'
113: 202, # 'q'
114: 91, # 'r'
115: 79, # 's'
116: 84, # 't'
117: 104, # 'u'
118: 105, # 'v'
119: 97, # 'w'
120: 98, # 'x'
121: 92, # 'y'
122: 203, # 'z'
123: 253, # '{'
124: 253, # '|'
125: 253, # '}'
126: 253, # '~'
127: 253, # '\x7f'
128: 209, # '\x80'
129: 210, # '\x81'
130: 211, # '\x82'
131: 212, # '\x83'
132: 213, # '\x84'
133: 88, # '\x85'
134: 214, # '\x86'
135: 215, # '\x87'
136: 216, # '\x88'
137: 217, # '\x89'
138: 218, # '\x8a'
139: 219, # '\x8b'
140: 220, # '\x8c'
141: 118, # '\x8d'
142: 221, # '\x8e'
143: 222, # '\x8f'
144: 223, # '\x90'
145: 224, # '\x91'
146: 99, # '\x92'
147: 85, # '\x93'
148: 83, # '\x94'
149: 225, # '\x95'
150: 226, # '\x96'
151: 227, # '\x97'
152: 228, # '\x98'
153: 229, # '\x99'
154: 230, # '\x9a'
155: 231, # '\x9b'
156: 232, # '\x9c'
157: 233, # '\x9d'
158: 234, # '\x9e'
159: 235, # '\x9f'
160: 236, # None
161: 5, # 'ก'
162: 30, # 'ข'
163: 237, # 'ฃ'
164: 24, # 'ค'
165: 238, # 'ฅ'
166: 75, # 'ฆ'
167: 8, # 'ง'
168: 26, # 'จ'
169: 52, # 'ฉ'
170: 34, # 'ช'
171: 51, # 'ซ'
172: 119, # 'ฌ'
173: 47, # 'ญ'
174: 58, # 'ฎ'
175: 57, # 'ฏ'
176: 49, # 'ฐ'
177: 53, # 'ฑ'
178: 55, # 'ฒ'
179: 43, # 'ณ'
180: 20, # 'ด'
181: 19, # 'ต'
182: 44, # 'ถ'
183: 14, # 'ท'
184: 48, # 'ธ'
185: 3, # 'น'
186: 17, # 'บ'
187: 25, # 'ป'
188: 39, # 'ผ'
189: 62, # 'ฝ'
190: 31, # 'พ'
191: 54, # 'ฟ'
192: 45, # 'ภ'
193: 9, # 'ม'
194: 16, # 'ย'
195: 2, # 'ร'
196: 61, # 'ฤ'
197: 15, # 'ล'
198: 239, # 'ฦ'
199: 12, # 'ว'
200: 42, # 'ศ'
201: 46, # 'ษ'
202: 18, # 'ส'
203: 21, # 'ห'
204: 76, # 'ฬ'
205: 4, # 'อ'
206: 66, # 'ฮ'
207: 63, # 'ฯ'
208: 22, # 'ะ'
209: 10, # 'ั'
210: 1, # 'า'
211: 36, # 'ำ'
212: 23, # 'ิ'
213: 13, # 'ี'
214: 40, # 'ึ'
215: 27, # 'ื'
216: 32, # 'ุ'
217: 35, # 'ู'
218: 86, # 'ฺ'
219: 240, # None
220: 241, # None
221: 242, # None
222: 243, # None
223: 244, # '฿'
224: 11, # 'เ'
225: 28, # 'แ'
226: 41, # 'โ'
227: 29, # 'ใ'
228: 33, # 'ไ'
229: 245, # 'ๅ'
230: 50, # 'ๆ'
231: 37, # '็'
232: 6, # '่'
233: 7, # '้'
234: 67, # '๊'
235: 77, # '๋'
236: 38, # '์'
237: 93, # 'ํ'
238: 246, # '๎'
239: 247, # '๏'
240: 68, # '๐'
241: 56, # '๑'
242: 59, # '๒'
243: 65, # '๓'
244: 69, # '๔'
245: 60, # '๕'
246: 70, # '๖'
247: 80, # '๗'
248: 71, # '๘'
249: 87, # '๙'
250: 248, # '๚'
251: 249, # '๛'
252: 250, # None
253: 251, # None
254: 252, # None
255: 253, # None
0: 255, # '\x00'
1: 255, # '\x01'
2: 255, # '\x02'
3: 255, # '\x03'
4: 255, # '\x04'
5: 255, # '\x05'
6: 255, # '\x06'
7: 255, # '\x07'
8: 255, # '\x08'
9: 255, # '\t'
10: 254, # '\n'
11: 255, # '\x0b'
12: 255, # '\x0c'
13: 254, # '\r'
14: 255, # '\x0e'
15: 255, # '\x0f'
16: 255, # '\x10'
17: 255, # '\x11'
18: 255, # '\x12'
19: 255, # '\x13'
20: 255, # '\x14'
21: 255, # '\x15'
22: 255, # '\x16'
23: 255, # '\x17'
24: 255, # '\x18'
25: 255, # '\x19'
26: 255, # '\x1a'
27: 255, # '\x1b'
28: 255, # '\x1c'
29: 255, # '\x1d'
30: 255, # '\x1e'
31: 255, # '\x1f'
32: 253, # ' '
33: 253, # '!'
34: 253, # '"'
35: 253, # '#'
36: 253, # '$'
37: 253, # '%'
38: 253, # '&'
39: 253, # "'"
40: 253, # '('
41: 253, # ')'
42: 253, # '*'
43: 253, # '+'
44: 253, # ','
45: 253, # '-'
46: 253, # '.'
47: 253, # '/'
48: 252, # '0'
49: 252, # '1'
50: 252, # '2'
51: 252, # '3'
52: 252, # '4'
53: 252, # '5'
54: 252, # '6'
55: 252, # '7'
56: 252, # '8'
57: 252, # '9'
58: 253, # ':'
59: 253, # ';'
60: 253, # '<'
61: 253, # '='
62: 253, # '>'
63: 253, # '?'
64: 253, # '@'
65: 182, # 'A'
66: 106, # 'B'
67: 107, # 'C'
68: 100, # 'D'
69: 183, # 'E'
70: 184, # 'F'
71: 185, # 'G'
72: 101, # 'H'
73: 94, # 'I'
74: 186, # 'J'
75: 187, # 'K'
76: 108, # 'L'
77: 109, # 'M'
78: 110, # 'N'
79: 111, # 'O'
80: 188, # 'P'
81: 189, # 'Q'
82: 190, # 'R'
83: 89, # 'S'
84: 95, # 'T'
85: 112, # 'U'
86: 113, # 'V'
87: 191, # 'W'
88: 192, # 'X'
89: 193, # 'Y'
90: 194, # 'Z'
91: 253, # '['
92: 253, # '\\'
93: 253, # ']'
94: 253, # '^'
95: 253, # '_'
96: 253, # '`'
97: 64, # 'a'
98: 72, # 'b'
99: 73, # 'c'
100: 114, # 'd'
101: 74, # 'e'
102: 115, # 'f'
103: 116, # 'g'
104: 102, # 'h'
105: 81, # 'i'
106: 201, # 'j'
107: 117, # 'k'
108: 90, # 'l'
109: 103, # 'm'
110: 78, # 'n'
111: 82, # 'o'
112: 96, # 'p'
113: 202, # 'q'
114: 91, # 'r'
115: 79, # 's'
116: 84, # 't'
117: 104, # 'u'
118: 105, # 'v'
119: 97, # 'w'
120: 98, # 'x'
121: 92, # 'y'
122: 203, # 'z'
123: 253, # '{'
124: 253, # '|'
125: 253, # '}'
126: 253, # '~'
127: 253, # '\x7f'
128: 209, # '\x80'
129: 210, # '\x81'
130: 211, # '\x82'
131: 212, # '\x83'
132: 213, # '\x84'
133: 88, # '\x85'
134: 214, # '\x86'
135: 215, # '\x87'
136: 216, # '\x88'
137: 217, # '\x89'
138: 218, # '\x8a'
139: 219, # '\x8b'
140: 220, # '\x8c'
141: 118, # '\x8d'
142: 221, # '\x8e'
143: 222, # '\x8f'
144: 223, # '\x90'
145: 224, # '\x91'
146: 99, # '\x92'
147: 85, # '\x93'
148: 83, # '\x94'
149: 225, # '\x95'
150: 226, # '\x96'
151: 227, # '\x97'
152: 228, # '\x98'
153: 229, # '\x99'
154: 230, # '\x9a'
155: 231, # '\x9b'
156: 232, # '\x9c'
157: 233, # '\x9d'
158: 234, # '\x9e'
159: 235, # '\x9f'
160: 236, # None
161: 5, # 'ก'
162: 30, # 'ข'
163: 237, # 'ฃ'
164: 24, # 'ค'
165: 238, # 'ฅ'
166: 75, # 'ฆ'
167: 8, # 'ง'
168: 26, # 'จ'
169: 52, # 'ฉ'
170: 34, # 'ช'
171: 51, # 'ซ'
172: 119, # 'ฌ'
173: 47, # 'ญ'
174: 58, # 'ฎ'
175: 57, # 'ฏ'
176: 49, # 'ฐ'
177: 53, # 'ฑ'
178: 55, # 'ฒ'
179: 43, # 'ณ'
180: 20, # 'ด'
181: 19, # 'ต'
182: 44, # 'ถ'
183: 14, # 'ท'
184: 48, # 'ธ'
185: 3, # 'น'
186: 17, # 'บ'
187: 25, # 'ป'
188: 39, # 'ผ'
189: 62, # 'ฝ'
190: 31, # 'พ'
191: 54, # 'ฟ'
192: 45, # 'ภ'
193: 9, # 'ม'
194: 16, # 'ย'
195: 2, # 'ร'
196: 61, # 'ฤ'
197: 15, # 'ล'
198: 239, # 'ฦ'
199: 12, # 'ว'
200: 42, # 'ศ'
201: 46, # 'ษ'
202: 18, # 'ส'
203: 21, # 'ห'
204: 76, # 'ฬ'
205: 4, # 'อ'
206: 66, # 'ฮ'
207: 63, # 'ฯ'
208: 22, # 'ะ'
209: 10, # 'ั'
210: 1, # 'า'
211: 36, # 'ำ'
212: 23, # 'ิ'
213: 13, # 'ี'
214: 40, # 'ึ'
215: 27, # 'ื'
216: 32, # 'ุ'
217: 35, # 'ู'
218: 86, # 'ฺ'
219: 240, # None
220: 241, # None
221: 242, # None
222: 243, # None
223: 244, # '฿'
224: 11, # 'เ'
225: 28, # 'แ'
226: 41, # 'โ'
227: 29, # 'ใ'
228: 33, # 'ไ'
229: 245, # 'ๅ'
230: 50, # 'ๆ'
231: 37, # '็'
232: 6, # '่'
233: 7, # '้'
234: 67, # '๊'
235: 77, # '๋'
236: 38, # '์'
237: 93, # 'ํ'
238: 246, # '๎'
239: 247, # '๏'
240: 68, # '๐'
241: 56, # '๑'
242: 59, # '๒'
243: 65, # '๓'
244: 69, # '๔'
245: 60, # '๕'
246: 70, # '๖'
247: 80, # '๗'
248: 71, # '๘'
249: 87, # '๙'
250: 248, # '๚'
251: 249, # '๛'
252: 250, # None
253: 251, # None
254: 252, # None
255: 253, # None
}
TIS_620_THAI_MODEL = SingleByteCharSetModel(charset_name='TIS-620',
language='Thai',
char_to_order_map=TIS_620_THAI_CHAR_TO_ORDER,
language_model=THAI_LANG_MODEL,
typical_positive_ratio=0.926386,
keep_ascii_letters=False,
alphabet='กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛')
TIS_620_THAI_MODEL = SingleByteCharSetModel(
charset_name="TIS-620",
language="Thai",
char_to_order_map=TIS_620_THAI_CHAR_TO_ORDER,
language_model=THAI_LANG_MODEL,
typical_positive_ratio=0.926386,
keep_ascii_letters=False,
alphabet="กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛",
)

533
venv/Lib/site-packages/pip/_vendor/chardet/langturkishmodel.py
View File

@@ -1,9 +1,5 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel
# 3: Positive
# 2: Likely
# 1: Unlikely
@@ -4115,269 +4111,270 @@ TURKISH_LANG_MODEL = {
# Character Mapping Table(s):
ISO_8859_9_TURKISH_CHAR_TO_ORDER = {
0: 255, # '\x00'
1: 255, # '\x01'
2: 255, # '\x02'
3: 255, # '\x03'
4: 255, # '\x04'
5: 255, # '\x05'
6: 255, # '\x06'
7: 255, # '\x07'
8: 255, # '\x08'
9: 255, # '\t'
10: 255, # '\n'
11: 255, # '\x0b'
12: 255, # '\x0c'
13: 255, # '\r'
14: 255, # '\x0e'
15: 255, # '\x0f'
16: 255, # '\x10'
17: 255, # '\x11'
18: 255, # '\x12'
19: 255, # '\x13'
20: 255, # '\x14'
21: 255, # '\x15'
22: 255, # '\x16'
23: 255, # '\x17'
24: 255, # '\x18'
25: 255, # '\x19'
26: 255, # '\x1a'
27: 255, # '\x1b'
28: 255, # '\x1c'
29: 255, # '\x1d'
30: 255, # '\x1e'
31: 255, # '\x1f'
32: 255, # ' '
33: 255, # '!'
34: 255, # '"'
35: 255, # '#'
36: 255, # '$'
37: 255, # '%'
38: 255, # '&'
39: 255, # "'"
40: 255, # '('
41: 255, # ')'
42: 255, # '*'
43: 255, # '+'
44: 255, # ','
45: 255, # '-'
46: 255, # '.'
47: 255, # '/'
48: 255, # '0'
49: 255, # '1'
50: 255, # '2'
51: 255, # '3'
52: 255, # '4'
53: 255, # '5'
54: 255, # '6'
55: 255, # '7'
56: 255, # '8'
57: 255, # '9'
58: 255, # ':'
59: 255, # ';'
60: 255, # '<'
61: 255, # '='
62: 255, # '>'
63: 255, # '?'
64: 255, # '@'
65: 23, # 'A'
66: 37, # 'B'
67: 47, # 'C'
68: 39, # 'D'
69: 29, # 'E'
70: 52, # 'F'
71: 36, # 'G'
72: 45, # 'H'
73: 53, # 'I'
74: 60, # 'J'
75: 16, # 'K'
76: 49, # 'L'
77: 20, # 'M'
78: 46, # 'N'
79: 42, # 'O'
80: 48, # 'P'
81: 69, # 'Q'
82: 44, # 'R'
83: 35, # 'S'
84: 31, # 'T'
85: 51, # 'U'
86: 38, # 'V'
87: 62, # 'W'
88: 65, # 'X'
89: 43, # 'Y'
90: 56, # 'Z'
91: 255, # '['
92: 255, # '\\'
93: 255, # ']'
94: 255, # '^'
95: 255, # '_'
96: 255, # '`'
97: 1, # 'a'
98: 21, # 'b'
99: 28, # 'c'
100: 12, # 'd'
101: 2, # 'e'
102: 18, # 'f'
103: 27, # 'g'
104: 25, # 'h'
105: 3, # 'i'
106: 24, # 'j'
107: 10, # 'k'
108: 5, # 'l'
109: 13, # 'm'
110: 4, # 'n'
111: 15, # 'o'
112: 26, # 'p'
113: 64, # 'q'
114: 7, # 'r'
115: 8, # 's'
116: 9, # 't'
117: 14, # 'u'
118: 32, # 'v'
119: 57, # 'w'
120: 58, # 'x'
121: 11, # 'y'
122: 22, # 'z'
123: 255, # '{'
124: 255, # '|'
125: 255, # '}'
126: 255, # '~'
127: 255, # '\x7f'
128: 180, # '\x80'
129: 179, # '\x81'
130: 178, # '\x82'
131: 177, # '\x83'
132: 176, # '\x84'
133: 175, # '\x85'
134: 174, # '\x86'
135: 173, # '\x87'
136: 172, # '\x88'
137: 171, # '\x89'
138: 170, # '\x8a'
139: 169, # '\x8b'
140: 168, # '\x8c'
141: 167, # '\x8d'
142: 166, # '\x8e'
143: 165, # '\x8f'
144: 164, # '\x90'
145: 163, # '\x91'
146: 162, # '\x92'
147: 161, # '\x93'
148: 160, # '\x94'
149: 159, # '\x95'
150: 101, # '\x96'
151: 158, # '\x97'
152: 157, # '\x98'
153: 156, # '\x99'
154: 155, # '\x9a'
155: 154, # '\x9b'
156: 153, # '\x9c'
157: 152, # '\x9d'
158: 151, # '\x9e'
159: 106, # '\x9f'
160: 150, # '\xa0'
161: 149, # '¡'
162: 148, # '¢'
163: 147, # '£'
164: 146, # '¤'
165: 145, # '¥'
166: 144, # '¦'
167: 100, # '§'
168: 143, # '¨'
169: 142, # '©'
170: 141, # 'ª'
171: 140, # '«'
172: 139, # '¬'
173: 138, # '\xad'
174: 137, # '®'
175: 136, # '¯'
176: 94, # '°'
177: 80, # '±'
178: 93, # '²'
179: 135, # '³'
180: 105, # '´'
181: 134, # 'µ'
182: 133, # '¶'
183: 63, # '·'
184: 132, # '¸'
185: 131, # '¹'
186: 130, # 'º'
187: 129, # '»'
188: 128, # '¼'
189: 127, # '½'
190: 126, # '¾'
191: 125, # '¿'
192: 124, # 'À'
193: 104, # 'Á'
194: 73, # 'Â'
195: 99, # 'Ã'
196: 79, # 'Ä'
197: 85, # 'Å'
198: 123, # 'Æ'
199: 54, # 'Ç'
200: 122, # 'È'
201: 98, # 'É'
202: 92, # 'Ê'
203: 121, # 'Ë'
204: 120, # 'Ì'
205: 91, # 'Í'
206: 103, # 'Î'
207: 119, # 'Ï'
208: 68, # 'Ğ'
209: 118, # 'Ñ'
210: 117, # 'Ò'
211: 97, # 'Ó'
212: 116, # 'Ô'
213: 115, # 'Õ'
214: 50, # 'Ö'
215: 90, # '×'
216: 114, # 'Ø'
217: 113, # 'Ù'
218: 112, # 'Ú'
219: 111, # 'Û'
220: 55, # 'Ü'
221: 41, # 'İ'
222: 40, # 'Ş'
223: 86, # 'ß'
224: 89, # 'à'
225: 70, # 'á'
226: 59, # 'â'
227: 78, # 'ã'
228: 71, # 'ä'
229: 82, # 'å'
230: 88, # 'æ'
231: 33, # 'ç'
232: 77, # 'è'
233: 66, # 'é'
234: 84, # 'ê'
235: 83, # 'ë'
236: 110, # 'ì'
237: 75, # 'í'
238: 61, # 'î'
239: 96, # 'ï'
240: 30, # 'ğ'
241: 67, # 'ñ'
242: 109, # 'ò'
243: 74, # 'ó'
244: 87, # 'ô'
245: 102, # 'õ'
246: 34, # 'ö'
247: 95, # '÷'
248: 81, # 'ø'
249: 108, # 'ù'
250: 76, # 'ú'
251: 72, # 'û'
252: 17, # 'ü'
253: 6, # 'ı'
254: 19, # 'ş'
255: 107, # 'ÿ'
0: 255, # '\x00'
1: 255, # '\x01'
2: 255, # '\x02'
3: 255, # '\x03'
4: 255, # '\x04'
5: 255, # '\x05'
6: 255, # '\x06'
7: 255, # '\x07'
8: 255, # '\x08'
9: 255, # '\t'
10: 255, # '\n'
11: 255, # '\x0b'
12: 255, # '\x0c'
13: 255, # '\r'
14: 255, # '\x0e'
15: 255, # '\x0f'
16: 255, # '\x10'
17: 255, # '\x11'
18: 255, # '\x12'
19: 255, # '\x13'
20: 255, # '\x14'
21: 255, # '\x15'
22: 255, # '\x16'
23: 255, # '\x17'
24: 255, # '\x18'
25: 255, # '\x19'
26: 255, # '\x1a'
27: 255, # '\x1b'
28: 255, # '\x1c'
29: 255, # '\x1d'
30: 255, # '\x1e'
31: 255, # '\x1f'
32: 255, # ' '
33: 255, # '!'
34: 255, # '"'
35: 255, # '#'
36: 255, # '$'
37: 255, # '%'
38: 255, # '&'
39: 255, # "'"
40: 255, # '('
41: 255, # ')'
42: 255, # '*'
43: 255, # '+'
44: 255, # ','
45: 255, # '-'
46: 255, # '.'
47: 255, # '/'
48: 255, # '0'
49: 255, # '1'
50: 255, # '2'
51: 255, # '3'
52: 255, # '4'
53: 255, # '5'
54: 255, # '6'
55: 255, # '7'
56: 255, # '8'
57: 255, # '9'
58: 255, # ':'
59: 255, # ';'
60: 255, # '<'
61: 255, # '='
62: 255, # '>'
63: 255, # '?'
64: 255, # '@'
65: 23, # 'A'
66: 37, # 'B'
67: 47, # 'C'
68: 39, # 'D'
69: 29, # 'E'
70: 52, # 'F'
71: 36, # 'G'
72: 45, # 'H'
73: 53, # 'I'
74: 60, # 'J'
75: 16, # 'K'
76: 49, # 'L'
77: 20, # 'M'
78: 46, # 'N'
79: 42, # 'O'
80: 48, # 'P'
81: 69, # 'Q'
82: 44, # 'R'
83: 35, # 'S'
84: 31, # 'T'
85: 51, # 'U'
86: 38, # 'V'
87: 62, # 'W'
88: 65, # 'X'
89: 43, # 'Y'
90: 56, # 'Z'
91: 255, # '['
92: 255, # '\\'
93: 255, # ']'
94: 255, # '^'
95: 255, # '_'
96: 255, # '`'
97: 1, # 'a'
98: 21, # 'b'
99: 28, # 'c'
100: 12, # 'd'
101: 2, # 'e'
102: 18, # 'f'
103: 27, # 'g'
104: 25, # 'h'
105: 3, # 'i'
106: 24, # 'j'
107: 10, # 'k'
108: 5, # 'l'
109: 13, # 'm'
110: 4, # 'n'
111: 15, # 'o'
112: 26, # 'p'
113: 64, # 'q'
114: 7, # 'r'
115: 8, # 's'
116: 9, # 't'
117: 14, # 'u'
118: 32, # 'v'
119: 57, # 'w'
120: 58, # 'x'
121: 11, # 'y'
122: 22, # 'z'
123: 255, # '{'
124: 255, # '|'
125: 255, # '}'
126: 255, # '~'
127: 255, # '\x7f'
128: 180, # '\x80'
129: 179, # '\x81'
130: 178, # '\x82'
131: 177, # '\x83'
132: 176, # '\x84'
133: 175, # '\x85'
134: 174, # '\x86'
135: 173, # '\x87'
136: 172, # '\x88'
137: 171, # '\x89'
138: 170, # '\x8a'
139: 169, # '\x8b'
140: 168, # '\x8c'
141: 167, # '\x8d'
142: 166, # '\x8e'
143: 165, # '\x8f'
144: 164, # '\x90'
145: 163, # '\x91'
146: 162, # '\x92'
147: 161, # '\x93'
148: 160, # '\x94'
149: 159, # '\x95'
150: 101, # '\x96'
151: 158, # '\x97'
152: 157, # '\x98'
153: 156, # '\x99'
154: 155, # '\x9a'
155: 154, # '\x9b'
156: 153, # '\x9c'
157: 152, # '\x9d'
158: 151, # '\x9e'
159: 106, # '\x9f'
160: 150, # '\xa0'
161: 149, # '¡'
162: 148, # '¢'
163: 147, # '£'
164: 146, # '¤'
165: 145, # '¥'
166: 144, # '¦'
167: 100, # '§'
168: 143, # '¨'
169: 142, # '©'
170: 141, # 'ª'
171: 140, # '«'
172: 139, # '¬'
173: 138, # '\xad'
174: 137, # '®'
175: 136, # '¯'
176: 94, # '°'
177: 80, # '±'
178: 93, # '²'
179: 135, # '³'
180: 105, # '´'
181: 134, # 'µ'
182: 133, # '¶'
183: 63, # '·'
184: 132, # '¸'
185: 131, # '¹'
186: 130, # 'º'
187: 129, # '»'
188: 128, # '¼'
189: 127, # '½'
190: 126, # '¾'
191: 125, # '¿'
192: 124, # 'À'
193: 104, # 'Á'
194: 73, # 'Â'
195: 99, # 'Ã'
196: 79, # 'Ä'
197: 85, # 'Å'
198: 123, # 'Æ'
199: 54, # 'Ç'
200: 122, # 'È'
201: 98, # 'É'
202: 92, # 'Ê'
203: 121, # 'Ë'
204: 120, # 'Ì'
205: 91, # 'Í'
206: 103, # 'Î'
207: 119, # 'Ï'
208: 68, # 'Ğ'
209: 118, # 'Ñ'
210: 117, # 'Ò'
211: 97, # 'Ó'
212: 116, # 'Ô'
213: 115, # 'Õ'
214: 50, # 'Ö'
215: 90, # '×'
216: 114, # 'Ø'
217: 113, # 'Ù'
218: 112, # 'Ú'
219: 111, # 'Û'
220: 55, # 'Ü'
221: 41, # 'İ'
222: 40, # 'Ş'
223: 86, # 'ß'
224: 89, # 'à'
225: 70, # 'á'
226: 59, # 'â'
227: 78, # 'ã'
228: 71, # 'ä'
229: 82, # 'å'
230: 88, # 'æ'
231: 33, # 'ç'
232: 77, # 'è'
233: 66, # 'é'
234: 84, # 'ê'
235: 83, # 'ë'
236: 110, # 'ì'
237: 75, # 'í'
238: 61, # 'î'
239: 96, # 'ï'
240: 30, # 'ğ'
241: 67, # 'ñ'
242: 109, # 'ò'
243: 74, # 'ó'
244: 87, # 'ô'
245: 102, # 'õ'
246: 34, # 'ö'
247: 95, # '÷'
248: 81, # 'ø'
249: 108, # 'ù'
250: 76, # 'ú'
251: 72, # 'û'
252: 17, # 'ü'
253: 6, # 'ı'
254: 19, # 'ş'
255: 107, # 'ÿ'
}
ISO_8859_9_TURKISH_MODEL = SingleByteCharSetModel(charset_name='ISO-8859-9',
language='Turkish',
char_to_order_map=ISO_8859_9_TURKISH_CHAR_TO_ORDER,
language_model=TURKISH_LANG_MODEL,
typical_positive_ratio=0.97029,
keep_ascii_letters=True,
alphabet='ABCDEFGHIJKLMNOPRSTUVYZabcdefghijklmnoprstuvyzÂÇÎÖÛÜâçîöûüĞğİıŞş')
ISO_8859_9_TURKISH_MODEL = SingleByteCharSetModel(
charset_name="ISO-8859-9",
language="Turkish",
char_to_order_map=ISO_8859_9_TURKISH_CHAR_TO_ORDER,
language_model=TURKISH_LANG_MODEL,
typical_positive_ratio=0.97029,
keep_ascii_letters=True,
alphabet="ABCDEFGHIJKLMNOPRSTUVYZabcdefghijklmnoprstuvyzÂÇÎÖÛÜâçîöûüĞğİıŞş",
)

44
venv/Lib/site-packages/pip/_vendor/chardet/latin1prober.py
View File

@@ -26,6 +26,8 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from typing import List, Union
from .charsetprober import CharSetProber
from .enums import ProbingState
@@ -41,6 +43,7 @@ ASV = 6 # accent small vowel
ASO = 7 # accent small other
CLASS_NUM = 8 # total classes
# fmt: off
Latin1_CharToClass = (
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 00 - 07
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 08 - 0F
@@ -91,34 +94,34 @@ Latin1ClassModel = (
0, 3, 1, 3, 1, 1, 1, 3, # ASV
0, 3, 1, 3, 1, 1, 3, 3, # ASO
)
# fmt: on
class Latin1Prober(CharSetProber):
def __init__(self):
super(Latin1Prober, self).__init__()
self._last_char_class = None
self._freq_counter = None
def __init__(self) -> None:
super().__init__()
self._last_char_class = OTH
self._freq_counter: List[int] = []
self.reset()
def reset(self):
def reset(self) -> None:
self._last_char_class = OTH
self._freq_counter = [0] * FREQ_CAT_NUM
CharSetProber.reset(self)
super().reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return "ISO-8859-1"
@property
def language(self):
def language(self) -> str:
return ""
def feed(self, byte_str):
byte_str = self.filter_with_english_letters(byte_str)
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
byte_str = self.remove_xml_tags(byte_str)
for c in byte_str:
char_class = Latin1_CharToClass[c]
freq = Latin1ClassModel[(self._last_char_class * CLASS_NUM)
+ char_class]
freq = Latin1ClassModel[(self._last_char_class * CLASS_NUM) + char_class]
if freq == 0:
self._state = ProbingState.NOT_ME
break
@@ -127,19 +130,18 @@ class Latin1Prober(CharSetProber):
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
if self.state == ProbingState.NOT_ME:
return 0.01
total = sum(self._freq_counter)
if total < 0.01:
confidence = 0.0
else:
confidence = ((self._freq_counter[3] - self._freq_counter[1] * 20.0)
/ total)
if confidence < 0.0:
confidence = 0.0
confidence = (
0.0
if total < 0.01
else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total
)
confidence = max(confidence, 0.0)
# lower the confidence of latin1 so that other more accurate
# detector can take priority.
confidence = confidence * 0.73
confidence *= 0.73
return confidence

62
venv/Lib/site-packages/pip/_vendor/chardet/mbcharsetprober.py
View File

@@ -27,8 +27,12 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from typing import Optional, Union
from .chardistribution import CharDistributionAnalysis
from .charsetprober import CharSetProber
from .enums import ProbingState, MachineState
from .codingstatemachine import CodingStateMachine
from .enums import LanguageFilter, MachineState, ProbingState
class MultiByteCharSetProber(CharSetProber):
@@ -36,56 +40,56 @@ class MultiByteCharSetProber(CharSetProber):
MultiByteCharSetProber
"""
def __init__(self, lang_filter=None):
super(MultiByteCharSetProber, self).__init__(lang_filter=lang_filter)
self.distribution_analyzer = None
self.coding_sm = None
self._last_char = [0, 0]
def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
super().__init__(lang_filter=lang_filter)
self.distribution_analyzer: Optional[CharDistributionAnalysis] = None
self.coding_sm: Optional[CodingStateMachine] = None
self._last_char = bytearray(b"\0\0")
def reset(self):
super(MultiByteCharSetProber, self).reset()
def reset(self) -> None:
super().reset()
if self.coding_sm:
self.coding_sm.reset()
if self.distribution_analyzer:
self.distribution_analyzer.reset()
self._last_char = [0, 0]
self._last_char = bytearray(b"\0\0")
@property
def charset_name(self):
raise NotImplementedError
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
assert self.coding_sm is not None
assert self.distribution_analyzer is not None
@property
def language(self):
raise NotImplementedError
def feed(self, byte_str):
for i in range(len(byte_str)):
coding_state = self.coding_sm.next_state(byte_str[i])
for i, byte in enumerate(byte_str):
coding_state = self.coding_sm.next_state(byte)
if coding_state == MachineState.ERROR:
self.logger.debug('%s %s prober hit error at byte %s',
self.charset_name, self.language, i)
self.logger.debug(
"%s %s prober hit error at byte %s",
self.charset_name,
self.language,
i,
)
self._state = ProbingState.NOT_ME
break
elif coding_state == MachineState.ITS_ME:
if coding_state == MachineState.ITS_ME:
self._state = ProbingState.FOUND_IT
break
elif coding_state == MachineState.START:
if coding_state == MachineState.START:
char_len = self.coding_sm.get_current_charlen()
if i == 0:
self._last_char[1] = byte_str[0]
self._last_char[1] = byte
self.distribution_analyzer.feed(self._last_char, char_len)
else:
self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
char_len)
self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len)
self._last_char[0] = byte_str[-1]
if self.state == ProbingState.DETECTING:
if (self.distribution_analyzer.got_enough_data() and
(self.get_confidence() > self.SHORTCUT_THRESHOLD)):
if self.distribution_analyzer.got_enough_data() and (
self.get_confidence() > self.SHORTCUT_THRESHOLD
):
self._state = ProbingState.FOUND_IT
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
assert self.distribution_analyzer is not None
return self.distribution_analyzer.get_confidence()

23
venv/Lib/site-packages/pip/_vendor/chardet/mbcsgroupprober.py
View File

@@ -27,20 +27,22 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .charsetgroupprober import CharSetGroupProber
from .utf8prober import UTF8Prober
from .sjisprober import SJISProber
from .eucjpprober import EUCJPProber
from .gb2312prober import GB2312Prober
from .euckrprober import EUCKRProber
from .cp949prober import CP949Prober
from .big5prober import Big5Prober
from .charsetgroupprober import CharSetGroupProber
from .cp949prober import CP949Prober
from .enums import LanguageFilter
from .eucjpprober import EUCJPProber
from .euckrprober import EUCKRProber
from .euctwprober import EUCTWProber
from .gb2312prober import GB2312Prober
from .johabprober import JOHABProber
from .sjisprober import SJISProber
from .utf8prober import UTF8Prober
class MBCSGroupProber(CharSetGroupProber):
def __init__(self, lang_filter=None):
super(MBCSGroupProber, self).__init__(lang_filter=lang_filter)
def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
super().__init__(lang_filter=lang_filter)
self.probers = [
UTF8Prober(),
SJISProber(),
@@ -49,6 +51,7 @@ class MBCSGroupProber(CharSetGroupProber):
EUCKRProber(),
CP949Prober(),
Big5Prober(),
EUCTWProber()
EUCTWProber(),
JOHABProber(),
]
self.reset()

817
venv/Lib/site-packages/pip/_vendor/chardet/mbcssm.py
View File

@@ -25,43 +25,45 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .codingstatemachinedict import CodingStateMachineDict
from .enums import MachineState
# BIG5
# fmt: off
BIG5_CLS = (
1,1,1,1,1,1,1,1, # 00 - 07 #allow 0x00 as legal value
1,1,1,1,1,1,0,0, # 08 - 0f
1,1,1,1,1,1,1,1, # 10 - 17
1,1,1,0,1,1,1,1, # 18 - 1f
1,1,1,1,1,1,1,1, # 20 - 27
1,1,1,1,1,1,1,1, # 28 - 2f
1,1,1,1,1,1,1,1, # 30 - 37
1,1,1,1,1,1,1,1, # 38 - 3f
2,2,2,2,2,2,2,2, # 40 - 47
2,2,2,2,2,2,2,2, # 48 - 4f
2,2,2,2,2,2,2,2, # 50 - 57
2,2,2,2,2,2,2,2, # 58 - 5f
2,2,2,2,2,2,2,2, # 60 - 67
2,2,2,2,2,2,2,2, # 68 - 6f
2,2,2,2,2,2,2,2, # 70 - 77
2,2,2,2,2,2,2,1, # 78 - 7f
4,4,4,4,4,4,4,4, # 80 - 87
4,4,4,4,4,4,4,4, # 88 - 8f
4,4,4,4,4,4,4,4, # 90 - 97
4,4,4,4,4,4,4,4, # 98 - 9f
4,3,3,3,3,3,3,3, # a0 - a7
3,3,3,3,3,3,3,3, # a8 - af
3,3,3,3,3,3,3,3, # b0 - b7
3,3,3,3,3,3,3,3, # b8 - bf
3,3,3,3,3,3,3,3, # c0 - c7
3,3,3,3,3,3,3,3, # c8 - cf
3,3,3,3,3,3,3,3, # d0 - d7
3,3,3,3,3,3,3,3, # d8 - df
3,3,3,3,3,3,3,3, # e0 - e7
3,3,3,3,3,3,3,3, # e8 - ef
3,3,3,3,3,3,3,3, # f0 - f7
3,3,3,3,3,3,3,0 # f8 - ff
1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 #allow 0x00 as legal value
1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f
1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17
1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f
1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27
1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f
1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37
1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f
2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47
2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f
2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57
2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f
2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67
2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f
2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77
2, 2, 2, 2, 2, 2, 2, 1, # 78 - 7f
4, 4, 4, 4, 4, 4, 4, 4, # 80 - 87
4, 4, 4, 4, 4, 4, 4, 4, # 88 - 8f
4, 4, 4, 4, 4, 4, 4, 4, # 90 - 97
4, 4, 4, 4, 4, 4, 4, 4, # 98 - 9f
4, 3, 3, 3, 3, 3, 3, 3, # a0 - a7
3, 3, 3, 3, 3, 3, 3, 3, # a8 - af
3, 3, 3, 3, 3, 3, 3, 3, # b0 - b7
3, 3, 3, 3, 3, 3, 3, 3, # b8 - bf
3, 3, 3, 3, 3, 3, 3, 3, # c0 - c7
3, 3, 3, 3, 3, 3, 3, 3, # c8 - cf
3, 3, 3, 3, 3, 3, 3, 3, # d0 - d7
3, 3, 3, 3, 3, 3, 3, 3, # d8 - df
3, 3, 3, 3, 3, 3, 3, 3, # e0 - e7
3, 3, 3, 3, 3, 3, 3, 3, # e8 - ef
3, 3, 3, 3, 3, 3, 3, 3, # f0 - f7
3, 3, 3, 3, 3, 3, 3, 0 # f8 - ff
)
BIG5_ST = (
@@ -69,34 +71,37 @@ BIG5_ST = (
MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,#08-0f
MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START#10-17
)
# fmt: on
BIG5_CHAR_LEN_TABLE = (0, 1, 1, 2, 0)
BIG5_SM_MODEL = {'class_table': BIG5_CLS,
'class_factor': 5,
'state_table': BIG5_ST,
'char_len_table': BIG5_CHAR_LEN_TABLE,
'name': 'Big5'}
BIG5_SM_MODEL: CodingStateMachineDict = {
"class_table": BIG5_CLS,
"class_factor": 5,
"state_table": BIG5_ST,
"char_len_table": BIG5_CHAR_LEN_TABLE,
"name": "Big5",
}
# CP949
# fmt: off
CP949_CLS = (
1,1,1,1,1,1,1,1, 1,1,1,1,1,1,0,0, # 00 - 0f
1,1,1,1,1,1,1,1, 1,1,1,0,1,1,1,1, # 10 - 1f
1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1, # 20 - 2f
1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1, # 30 - 3f
1,4,4,4,4,4,4,4, 4,4,4,4,4,4,4,4, # 40 - 4f
4,4,5,5,5,5,5,5, 5,5,5,1,1,1,1,1, # 50 - 5f
1,5,5,5,5,5,5,5, 5,5,5,5,5,5,5,5, # 60 - 6f
5,5,5,5,5,5,5,5, 5,5,5,1,1,1,1,1, # 70 - 7f
0,6,6,6,6,6,6,6, 6,6,6,6,6,6,6,6, # 80 - 8f
6,6,6,6,6,6,6,6, 6,6,6,6,6,6,6,6, # 90 - 9f
6,7,7,7,7,7,7,7, 7,7,7,7,7,8,8,8, # a0 - af
7,7,7,7,7,7,7,7, 7,7,7,7,7,7,7,7, # b0 - bf
7,7,7,7,7,7,9,2, 2,3,2,2,2,2,2,2, # c0 - cf
2,2,2,2,2,2,2,2, 2,2,2,2,2,2,2,2, # d0 - df
2,2,2,2,2,2,2,2, 2,2,2,2,2,2,2,2, # e0 - ef
2,2,2,2,2,2,2,2, 2,2,2,2,2,2,2,0, # f0 - ff
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, # 00 - 0f
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, # 10 - 1f
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 2f
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # 30 - 3f
1, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, # 40 - 4f
4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 1, 1, 1, 1, 1, # 50 - 5f
1, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, # 60 - 6f
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 1, 1, 1, 1, 1, # 70 - 7f
0, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, # 80 - 8f
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, # 90 - 9f
6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, # a0 - af
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, # b0 - bf
7, 7, 7, 7, 7, 7, 9, 2, 2, 3, 2, 2, 2, 2, 2, 2, # c0 - cf
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # d0 - df
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # e0 - ef
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, # f0 - ff
)
CP949_ST = (
@@ -109,50 +114,53 @@ CP949_ST = (
MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START, # 5
MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START, # 6
)
# fmt: on
CP949_CHAR_LEN_TABLE = (0, 1, 2, 0, 1, 1, 2, 2, 0, 2)
CP949_SM_MODEL = {'class_table': CP949_CLS,
'class_factor': 10,
'state_table': CP949_ST,
'char_len_table': CP949_CHAR_LEN_TABLE,
'name': 'CP949'}
CP949_SM_MODEL: CodingStateMachineDict = {
"class_table": CP949_CLS,
"class_factor": 10,
"state_table": CP949_ST,
"char_len_table": CP949_CHAR_LEN_TABLE,
"name": "CP949",
}
# EUC-JP
# fmt: off
EUCJP_CLS = (
4,4,4,4,4,4,4,4, # 00 - 07
4,4,4,4,4,4,5,5, # 08 - 0f
4,4,4,4,4,4,4,4, # 10 - 17
4,4,4,5,4,4,4,4, # 18 - 1f
4,4,4,4,4,4,4,4, # 20 - 27
4,4,4,4,4,4,4,4, # 28 - 2f
4,4,4,4,4,4,4,4, # 30 - 37
4,4,4,4,4,4,4,4, # 38 - 3f
4,4,4,4,4,4,4,4, # 40 - 47
4,4,4,4,4,4,4,4, # 48 - 4f
4,4,4,4,4,4,4,4, # 50 - 57
4,4,4,4,4,4,4,4, # 58 - 5f
4,4,4,4,4,4,4,4, # 60 - 67
4,4,4,4,4,4,4,4, # 68 - 6f
4,4,4,4,4,4,4,4, # 70 - 77
4,4,4,4,4,4,4,4, # 78 - 7f
5,5,5,5,5,5,5,5, # 80 - 87
5,5,5,5,5,5,1,3, # 88 - 8f
5,5,5,5,5,5,5,5, # 90 - 97
5,5,5,5,5,5,5,5, # 98 - 9f
5,2,2,2,2,2,2,2, # a0 - a7
2,2,2,2,2,2,2,2, # a8 - af
2,2,2,2,2,2,2,2, # b0 - b7
2,2,2,2,2,2,2,2, # b8 - bf
2,2,2,2,2,2,2,2, # c0 - c7
2,2,2,2,2,2,2,2, # c8 - cf
2,2,2,2,2,2,2,2, # d0 - d7
2,2,2,2,2,2,2,2, # d8 - df
0,0,0,0,0,0,0,0, # e0 - e7
0,0,0,0,0,0,0,0, # e8 - ef
0,0,0,0,0,0,0,0, # f0 - f7
0,0,0,0,0,0,0,5 # f8 - ff
4, 4, 4, 4, 4, 4, 4, 4, # 00 - 07
4, 4, 4, 4, 4, 4, 5, 5, # 08 - 0f
4, 4, 4, 4, 4, 4, 4, 4, # 10 - 17
4, 4, 4, 5, 4, 4, 4, 4, # 18 - 1f
4, 4, 4, 4, 4, 4, 4, 4, # 20 - 27
4, 4, 4, 4, 4, 4, 4, 4, # 28 - 2f
4, 4, 4, 4, 4, 4, 4, 4, # 30 - 37
4, 4, 4, 4, 4, 4, 4, 4, # 38 - 3f
4, 4, 4, 4, 4, 4, 4, 4, # 40 - 47
4, 4, 4, 4, 4, 4, 4, 4, # 48 - 4f
4, 4, 4, 4, 4, 4, 4, 4, # 50 - 57
4, 4, 4, 4, 4, 4, 4, 4, # 58 - 5f
4, 4, 4, 4, 4, 4, 4, 4, # 60 - 67
4, 4, 4, 4, 4, 4, 4, 4, # 68 - 6f
4, 4, 4, 4, 4, 4, 4, 4, # 70 - 77
4, 4, 4, 4, 4, 4, 4, 4, # 78 - 7f
5, 5, 5, 5, 5, 5, 5, 5, # 80 - 87
5, 5, 5, 5, 5, 5, 1, 3, # 88 - 8f
5, 5, 5, 5, 5, 5, 5, 5, # 90 - 97
5, 5, 5, 5, 5, 5, 5, 5, # 98 - 9f
5, 2, 2, 2, 2, 2, 2, 2, # a0 - a7
2, 2, 2, 2, 2, 2, 2, 2, # a8 - af
2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7
2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf
2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7
2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf
2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7
2, 2, 2, 2, 2, 2, 2, 2, # d8 - df
0, 0, 0, 0, 0, 0, 0, 0, # e0 - e7
0, 0, 0, 0, 0, 0, 0, 0, # e8 - ef
0, 0, 0, 0, 0, 0, 0, 0, # f0 - f7
0, 0, 0, 0, 0, 0, 0, 5 # f8 - ff
)
EUCJP_ST = (
@@ -162,100 +170,163 @@ EUCJP_ST = (
MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 3,MachineState.ERROR,#18-1f
3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START#20-27
)
# fmt: on
EUCJP_CHAR_LEN_TABLE = (2, 2, 2, 3, 1, 0)
EUCJP_SM_MODEL = {'class_table': EUCJP_CLS,
'class_factor': 6,
'state_table': EUCJP_ST,
'char_len_table': EUCJP_CHAR_LEN_TABLE,
'name': 'EUC-JP'}
EUCJP_SM_MODEL: CodingStateMachineDict = {
"class_table": EUCJP_CLS,
"class_factor": 6,
"state_table": EUCJP_ST,
"char_len_table": EUCJP_CHAR_LEN_TABLE,
"name": "EUC-JP",
}
# EUC-KR
# fmt: off
EUCKR_CLS = (
1,1,1,1,1,1,1,1, # 00 - 07
1,1,1,1,1,1,0,0, # 08 - 0f
1,1,1,1,1,1,1,1, # 10 - 17
1,1,1,0,1,1,1,1, # 18 - 1f
1,1,1,1,1,1,1,1, # 20 - 27
1,1,1,1,1,1,1,1, # 28 - 2f
1,1,1,1,1,1,1,1, # 30 - 37
1,1,1,1,1,1,1,1, # 38 - 3f
1,1,1,1,1,1,1,1, # 40 - 47
1,1,1,1,1,1,1,1, # 48 - 4f
1,1,1,1,1,1,1,1, # 50 - 57
1,1,1,1,1,1,1,1, # 58 - 5f
1,1,1,1,1,1,1,1, # 60 - 67
1,1,1,1,1,1,1,1, # 68 - 6f
1,1,1,1,1,1,1,1, # 70 - 77
1,1,1,1,1,1,1,1, # 78 - 7f
0,0,0,0,0,0,0,0, # 80 - 87
0,0,0,0,0,0,0,0, # 88 - 8f
0,0,0,0,0,0,0,0, # 90 - 97
0,0,0,0,0,0,0,0, # 98 - 9f
0,2,2,2,2,2,2,2, # a0 - a7
2,2,2,2,2,3,3,3, # a8 - af
2,2,2,2,2,2,2,2, # b0 - b7
2,2,2,2,2,2,2,2, # b8 - bf
2,2,2,2,2,2,2,2, # c0 - c7
2,3,2,2,2,2,2,2, # c8 - cf
2,2,2,2,2,2,2,2, # d0 - d7
2,2,2,2,2,2,2,2, # d8 - df
2,2,2,2,2,2,2,2, # e0 - e7
2,2,2,2,2,2,2,2, # e8 - ef
2,2,2,2,2,2,2,2, # f0 - f7
2,2,2,2,2,2,2,0 # f8 - ff
1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07
1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f
1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17
1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f
1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27
1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f
1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37
1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f
1, 1, 1, 1, 1, 1, 1, 1, # 40 - 47
1, 1, 1, 1, 1, 1, 1, 1, # 48 - 4f
1, 1, 1, 1, 1, 1, 1, 1, # 50 - 57
1, 1, 1, 1, 1, 1, 1, 1, # 58 - 5f
1, 1, 1, 1, 1, 1, 1, 1, # 60 - 67
1, 1, 1, 1, 1, 1, 1, 1, # 68 - 6f
1, 1, 1, 1, 1, 1, 1, 1, # 70 - 77
1, 1, 1, 1, 1, 1, 1, 1, # 78 - 7f
0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87
0, 0, 0, 0, 0, 0, 0, 0, # 88 - 8f
0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97
0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f
0, 2, 2, 2, 2, 2, 2, 2, # a0 - a7
2, 2, 2, 2, 2, 3, 3, 3, # a8 - af
2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7
2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf
2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7
2, 3, 2, 2, 2, 2, 2, 2, # c8 - cf
2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7
2, 2, 2, 2, 2, 2, 2, 2, # d8 - df
2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7
2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef
2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7
2, 2, 2, 2, 2, 2, 2, 0 # f8 - ff
)
EUCKR_ST = (
MachineState.ERROR,MachineState.START, 3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#00-07
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START #08-0f
)
# fmt: on
EUCKR_CHAR_LEN_TABLE = (0, 1, 2, 0)
EUCKR_SM_MODEL = {'class_table': EUCKR_CLS,
'class_factor': 4,
'state_table': EUCKR_ST,
'char_len_table': EUCKR_CHAR_LEN_TABLE,
'name': 'EUC-KR'}
EUCKR_SM_MODEL: CodingStateMachineDict = {
"class_table": EUCKR_CLS,
"class_factor": 4,
"state_table": EUCKR_ST,
"char_len_table": EUCKR_CHAR_LEN_TABLE,
"name": "EUC-KR",
}
# JOHAB
# fmt: off
JOHAB_CLS = (
4,4,4,4,4,4,4,4, # 00 - 07
4,4,4,4,4,4,0,0, # 08 - 0f
4,4,4,4,4,4,4,4, # 10 - 17
4,4,4,0,4,4,4,4, # 18 - 1f
4,4,4,4,4,4,4,4, # 20 - 27
4,4,4,4,4,4,4,4, # 28 - 2f
4,3,3,3,3,3,3,3, # 30 - 37
3,3,3,3,3,3,3,3, # 38 - 3f
3,1,1,1,1,1,1,1, # 40 - 47
1,1,1,1,1,1,1,1, # 48 - 4f
1,1,1,1,1,1,1,1, # 50 - 57
1,1,1,1,1,1,1,1, # 58 - 5f
1,1,1,1,1,1,1,1, # 60 - 67
1,1,1,1,1,1,1,1, # 68 - 6f
1,1,1,1,1,1,1,1, # 70 - 77
1,1,1,1,1,1,1,2, # 78 - 7f
6,6,6,6,8,8,8,8, # 80 - 87
8,8,8,8,8,8,8,8, # 88 - 8f
8,7,7,7,7,7,7,7, # 90 - 97
7,7,7,7,7,7,7,7, # 98 - 9f
7,7,7,7,7,7,7,7, # a0 - a7
7,7,7,7,7,7,7,7, # a8 - af
7,7,7,7,7,7,7,7, # b0 - b7
7,7,7,7,7,7,7,7, # b8 - bf
7,7,7,7,7,7,7,7, # c0 - c7
7,7,7,7,7,7,7,7, # c8 - cf
7,7,7,7,5,5,5,5, # d0 - d7
5,9,9,9,9,9,9,5, # d8 - df
9,9,9,9,9,9,9,9, # e0 - e7
9,9,9,9,9,9,9,9, # e8 - ef
9,9,9,9,9,9,9,9, # f0 - f7
9,9,5,5,5,5,5,0 # f8 - ff
)
JOHAB_ST = (
# cls = 0 1 2 3 4 5 6 7 8 9
MachineState.ERROR ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.ERROR ,MachineState.ERROR ,3 ,3 ,4 , # MachineState.START
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME, # MachineState.ITS_ME
MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR , # MachineState.ERROR
MachineState.ERROR ,MachineState.START ,MachineState.START ,MachineState.ERROR ,MachineState.ERROR ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.START , # 3
MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START , # 4
)
# fmt: on
JOHAB_CHAR_LEN_TABLE = (0, 1, 1, 1, 1, 0, 0, 2, 2, 2)
JOHAB_SM_MODEL: CodingStateMachineDict = {
"class_table": JOHAB_CLS,
"class_factor": 10,
"state_table": JOHAB_ST,
"char_len_table": JOHAB_CHAR_LEN_TABLE,
"name": "Johab",
}
# EUC-TW
# fmt: off
EUCTW_CLS = (
2,2,2,2,2,2,2,2, # 00 - 07
2,2,2,2,2,2,0,0, # 08 - 0f
2,2,2,2,2,2,2,2, # 10 - 17
2,2,2,0,2,2,2,2, # 18 - 1f
2,2,2,2,2,2,2,2, # 20 - 27
2,2,2,2,2,2,2,2, # 28 - 2f
2,2,2,2,2,2,2,2, # 30 - 37
2,2,2,2,2,2,2,2, # 38 - 3f
2,2,2,2,2,2,2,2, # 40 - 47
2,2,2,2,2,2,2,2, # 48 - 4f
2,2,2,2,2,2,2,2, # 50 - 57
2,2,2,2,2,2,2,2, # 58 - 5f
2,2,2,2,2,2,2,2, # 60 - 67
2,2,2,2,2,2,2,2, # 68 - 6f
2,2,2,2,2,2,2,2, # 70 - 77
2,2,2,2,2,2,2,2, # 78 - 7f
0,0,0,0,0,0,0,0, # 80 - 87
0,0,0,0,0,0,6,0, # 88 - 8f
0,0,0,0,0,0,0,0, # 90 - 97
0,0,0,0,0,0,0,0, # 98 - 9f
0,3,4,4,4,4,4,4, # a0 - a7
5,5,1,1,1,1,1,1, # a8 - af
1,1,1,1,1,1,1,1, # b0 - b7
1,1,1,1,1,1,1,1, # b8 - bf
1,1,3,1,3,3,3,3, # c0 - c7
3,3,3,3,3,3,3,3, # c8 - cf
3,3,3,3,3,3,3,3, # d0 - d7
3,3,3,3,3,3,3,3, # d8 - df
3,3,3,3,3,3,3,3, # e0 - e7
3,3,3,3,3,3,3,3, # e8 - ef
3,3,3,3,3,3,3,3, # f0 - f7
3,3,3,3,3,3,3,0 # f8 - ff
2, 2, 2, 2, 2, 2, 2, 2, # 00 - 07
2, 2, 2, 2, 2, 2, 0, 0, # 08 - 0f
2, 2, 2, 2, 2, 2, 2, 2, # 10 - 17
2, 2, 2, 0, 2, 2, 2, 2, # 18 - 1f
2, 2, 2, 2, 2, 2, 2, 2, # 20 - 27
2, 2, 2, 2, 2, 2, 2, 2, # 28 - 2f
2, 2, 2, 2, 2, 2, 2, 2, # 30 - 37
2, 2, 2, 2, 2, 2, 2, 2, # 38 - 3f
2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47
2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f
2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57
2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f
2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67
2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f
2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77
2, 2, 2, 2, 2, 2, 2, 2, # 78 - 7f
0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87
0, 0, 0, 0, 0, 0, 6, 0, # 88 - 8f
0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97
0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f
0, 3, 4, 4, 4, 4, 4, 4, # a0 - a7
5, 5, 1, 1, 1, 1, 1, 1, # a8 - af
1, 1, 1, 1, 1, 1, 1, 1, # b0 - b7
1, 1, 1, 1, 1, 1, 1, 1, # b8 - bf
1, 1, 3, 1, 3, 3, 3, 3, # c0 - c7
3, 3, 3, 3, 3, 3, 3, 3, # c8 - cf
3, 3, 3, 3, 3, 3, 3, 3, # d0 - d7
3, 3, 3, 3, 3, 3, 3, 3, # d8 - df
3, 3, 3, 3, 3, 3, 3, 3, # e0 - e7
3, 3, 3, 3, 3, 3, 3, 3, # e8 - ef
3, 3, 3, 3, 3, 3, 3, 3, # f0 - f7
3, 3, 3, 3, 3, 3, 3, 0 # f8 - ff
)
EUCTW_ST = (
@@ -266,50 +337,53 @@ EUCTW_ST = (
5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.ERROR,MachineState.START,MachineState.START,#20-27
MachineState.START,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START #28-2f
)
# fmt: on
EUCTW_CHAR_LEN_TABLE = (0, 0, 1, 2, 2, 2, 3)
EUCTW_SM_MODEL = {'class_table': EUCTW_CLS,
'class_factor': 7,
'state_table': EUCTW_ST,
'char_len_table': EUCTW_CHAR_LEN_TABLE,
'name': 'x-euc-tw'}
EUCTW_SM_MODEL: CodingStateMachineDict = {
"class_table": EUCTW_CLS,
"class_factor": 7,
"state_table": EUCTW_ST,
"char_len_table": EUCTW_CHAR_LEN_TABLE,
"name": "x-euc-tw",
}
# GB2312
# fmt: off
GB2312_CLS = (
1,1,1,1,1,1,1,1, # 00 - 07
1,1,1,1,1,1,0,0, # 08 - 0f
1,1,1,1,1,1,1,1, # 10 - 17
1,1,1,0,1,1,1,1, # 18 - 1f
1,1,1,1,1,1,1,1, # 20 - 27
1,1,1,1,1,1,1,1, # 28 - 2f
3,3,3,3,3,3,3,3, # 30 - 37
3,3,1,1,1,1,1,1, # 38 - 3f
2,2,2,2,2,2,2,2, # 40 - 47
2,2,2,2,2,2,2,2, # 48 - 4f
2,2,2,2,2,2,2,2, # 50 - 57
2,2,2,2,2,2,2,2, # 58 - 5f
2,2,2,2,2,2,2,2, # 60 - 67
2,2,2,2,2,2,2,2, # 68 - 6f
2,2,2,2,2,2,2,2, # 70 - 77
2,2,2,2,2,2,2,4, # 78 - 7f
5,6,6,6,6,6,6,6, # 80 - 87
6,6,6,6,6,6,6,6, # 88 - 8f
6,6,6,6,6,6,6,6, # 90 - 97
6,6,6,6,6,6,6,6, # 98 - 9f
6,6,6,6,6,6,6,6, # a0 - a7
6,6,6,6,6,6,6,6, # a8 - af
6,6,6,6,6,6,6,6, # b0 - b7
6,6,6,6,6,6,6,6, # b8 - bf
6,6,6,6,6,6,6,6, # c0 - c7
6,6,6,6,6,6,6,6, # c8 - cf
6,6,6,6,6,6,6,6, # d0 - d7
6,6,6,6,6,6,6,6, # d8 - df
6,6,6,6,6,6,6,6, # e0 - e7
6,6,6,6,6,6,6,6, # e8 - ef
6,6,6,6,6,6,6,6, # f0 - f7
6,6,6,6,6,6,6,0 # f8 - ff
1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07
1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f
1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17
1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f
1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27
1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f
3, 3, 3, 3, 3, 3, 3, 3, # 30 - 37
3, 3, 1, 1, 1, 1, 1, 1, # 38 - 3f
2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47
2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f
2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57
2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f
2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67
2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f
2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77
2, 2, 2, 2, 2, 2, 2, 4, # 78 - 7f
5, 6, 6, 6, 6, 6, 6, 6, # 80 - 87
6, 6, 6, 6, 6, 6, 6, 6, # 88 - 8f
6, 6, 6, 6, 6, 6, 6, 6, # 90 - 97
6, 6, 6, 6, 6, 6, 6, 6, # 98 - 9f
6, 6, 6, 6, 6, 6, 6, 6, # a0 - a7
6, 6, 6, 6, 6, 6, 6, 6, # a8 - af
6, 6, 6, 6, 6, 6, 6, 6, # b0 - b7
6, 6, 6, 6, 6, 6, 6, 6, # b8 - bf
6, 6, 6, 6, 6, 6, 6, 6, # c0 - c7
6, 6, 6, 6, 6, 6, 6, 6, # c8 - cf
6, 6, 6, 6, 6, 6, 6, 6, # d0 - d7
6, 6, 6, 6, 6, 6, 6, 6, # d8 - df
6, 6, 6, 6, 6, 6, 6, 6, # e0 - e7
6, 6, 6, 6, 6, 6, 6, 6, # e8 - ef
6, 6, 6, 6, 6, 6, 6, 6, # f0 - f7
6, 6, 6, 6, 6, 6, 6, 0 # f8 - ff
)
GB2312_ST = (
@@ -320,6 +394,7 @@ GB2312_ST = (
MachineState.ERROR,MachineState.ERROR, 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,#20-27
MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START #28-2f
)
# fmt: on
# To be accurate, the length of class 6 can be either 2 or 4.
# But it is not necessary to discriminate between the two since
@@ -328,100 +403,105 @@ GB2312_ST = (
# 2 here.
GB2312_CHAR_LEN_TABLE = (0, 1, 1, 1, 1, 1, 2)
GB2312_SM_MODEL = {'class_table': GB2312_CLS,
'class_factor': 7,
'state_table': GB2312_ST,
'char_len_table': GB2312_CHAR_LEN_TABLE,
'name': 'GB2312'}
GB2312_SM_MODEL: CodingStateMachineDict = {
"class_table": GB2312_CLS,
"class_factor": 7,
"state_table": GB2312_ST,
"char_len_table": GB2312_CHAR_LEN_TABLE,
"name": "GB2312",
}
# Shift_JIS
# fmt: off
SJIS_CLS = (
1,1,1,1,1,1,1,1, # 00 - 07
1,1,1,1,1,1,0,0, # 08 - 0f
1,1,1,1,1,1,1,1, # 10 - 17
1,1,1,0,1,1,1,1, # 18 - 1f
1,1,1,1,1,1,1,1, # 20 - 27
1,1,1,1,1,1,1,1, # 28 - 2f
1,1,1,1,1,1,1,1, # 30 - 37
1,1,1,1,1,1,1,1, # 38 - 3f
2,2,2,2,2,2,2,2, # 40 - 47
2,2,2,2,2,2,2,2, # 48 - 4f
2,2,2,2,2,2,2,2, # 50 - 57
2,2,2,2,2,2,2,2, # 58 - 5f
2,2,2,2,2,2,2,2, # 60 - 67
2,2,2,2,2,2,2,2, # 68 - 6f
2,2,2,2,2,2,2,2, # 70 - 77
2,2,2,2,2,2,2,1, # 78 - 7f
3,3,3,3,3,2,2,3, # 80 - 87
3,3,3,3,3,3,3,3, # 88 - 8f
3,3,3,3,3,3,3,3, # 90 - 97
3,3,3,3,3,3,3,3, # 98 - 9f
1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07
1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f
1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17
1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f
1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27
1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f
1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37
1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f
2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47
2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f
2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57
2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f
2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67
2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f
2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77
2, 2, 2, 2, 2, 2, 2, 1, # 78 - 7f
3, 3, 3, 3, 3, 2, 2, 3, # 80 - 87
3, 3, 3, 3, 3, 3, 3, 3, # 88 - 8f
3, 3, 3, 3, 3, 3, 3, 3, # 90 - 97
3, 3, 3, 3, 3, 3, 3, 3, # 98 - 9f
#0xa0 is illegal in sjis encoding, but some pages does
#contain such byte. We need to be more error forgiven.
2,2,2,2,2,2,2,2, # a0 - a7
2,2,2,2,2,2,2,2, # a8 - af
2,2,2,2,2,2,2,2, # b0 - b7
2,2,2,2,2,2,2,2, # b8 - bf
2,2,2,2,2,2,2,2, # c0 - c7
2,2,2,2,2,2,2,2, # c8 - cf
2,2,2,2,2,2,2,2, # d0 - d7
2,2,2,2,2,2,2,2, # d8 - df
3,3,3,3,3,3,3,3, # e0 - e7
3,3,3,3,3,4,4,4, # e8 - ef
3,3,3,3,3,3,3,3, # f0 - f7
3,3,3,3,3,0,0,0) # f8 - ff
2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7
2, 2, 2, 2, 2, 2, 2, 2, # a8 - af
2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7
2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf
2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7
2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf
2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7
2, 2, 2, 2, 2, 2, 2, 2, # d8 - df
3, 3, 3, 3, 3, 3, 3, 3, # e0 - e7
3, 3, 3, 3, 3, 4, 4, 4, # e8 - ef
3, 3, 3, 3, 3, 3, 3, 3, # f0 - f7
3, 3, 3, 3, 3, 0, 0, 0, # f8 - ff
)
SJIS_ST = (
MachineState.ERROR,MachineState.START,MachineState.START, 3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#00-07
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f
MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START #10-17
)
# fmt: on
SJIS_CHAR_LEN_TABLE = (0, 1, 1, 2, 0, 0)
SJIS_SM_MODEL = {'class_table': SJIS_CLS,
'class_factor': 6,
'state_table': SJIS_ST,
'char_len_table': SJIS_CHAR_LEN_TABLE,
'name': 'Shift_JIS'}
SJIS_SM_MODEL: CodingStateMachineDict = {
"class_table": SJIS_CLS,
"class_factor": 6,
"state_table": SJIS_ST,
"char_len_table": SJIS_CHAR_LEN_TABLE,
"name": "Shift_JIS",
}
# UCS2-BE
# fmt: off
UCS2BE_CLS = (
0,0,0,0,0,0,0,0, # 00 - 07
0,0,1,0,0,2,0,0, # 08 - 0f
0,0,0,0,0,0,0,0, # 10 - 17
0,0,0,3,0,0,0,0, # 18 - 1f
0,0,0,0,0,0,0,0, # 20 - 27
0,3,3,3,3,3,0,0, # 28 - 2f
0,0,0,0,0,0,0,0, # 30 - 37
0,0,0,0,0,0,0,0, # 38 - 3f
0,0,0,0,0,0,0,0, # 40 - 47
0,0,0,0,0,0,0,0, # 48 - 4f
0,0,0,0,0,0,0,0, # 50 - 57
0,0,0,0,0,0,0,0, # 58 - 5f
0,0,0,0,0,0,0,0, # 60 - 67
0,0,0,0,0,0,0,0, # 68 - 6f
0,0,0,0,0,0,0,0, # 70 - 77
0,0,0,0,0,0,0,0, # 78 - 7f
0,0,0,0,0,0,0,0, # 80 - 87
0,0,0,0,0,0,0,0, # 88 - 8f
0,0,0,0,0,0,0,0, # 90 - 97
0,0,0,0,0,0,0,0, # 98 - 9f
0,0,0,0,0,0,0,0, # a0 - a7
0,0,0,0,0,0,0,0, # a8 - af
0,0,0,0,0,0,0,0, # b0 - b7
0,0,0,0,0,0,0,0, # b8 - bf
0,0,0,0,0,0,0,0, # c0 - c7
0,0,0,0,0,0,0,0, # c8 - cf
0,0,0,0,0,0,0,0, # d0 - d7
0,0,0,0,0,0,0,0, # d8 - df
0,0,0,0,0,0,0,0, # e0 - e7
0,0,0,0,0,0,0,0, # e8 - ef
0,0,0,0,0,0,0,0, # f0 - f7
0,0,0,0,0,0,4,5 # f8 - ff
0, 0, 0, 0, 0, 0, 0, 0, # 00 - 07
0, 0, 1, 0, 0, 2, 0, 0, # 08 - 0f
0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17
0, 0, 0, 3, 0, 0, 0, 0, # 18 - 1f
0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27
0, 3, 3, 3, 3, 3, 0, 0, # 28 - 2f
0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37
0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f
0, 0, 0, 0, 0, 0, 0, 0, # 40 - 47
0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f
0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57
0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f
0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67
0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f
0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77
0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f
0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87
0, 0, 0, 0, 0, 0, 0, 0, # 88 - 8f
0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97
0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f
0, 0, 0, 0, 0, 0, 0, 0, # a0 - a7
0, 0, 0, 0, 0, 0, 0, 0, # a8 - af
0, 0, 0, 0, 0, 0, 0, 0, # b0 - b7
0, 0, 0, 0, 0, 0, 0, 0, # b8 - bf
0, 0, 0, 0, 0, 0, 0, 0, # c0 - c7
0, 0, 0, 0, 0, 0, 0, 0, # c8 - cf
0, 0, 0, 0, 0, 0, 0, 0, # d0 - d7
0, 0, 0, 0, 0, 0, 0, 0, # d8 - df
0, 0, 0, 0, 0, 0, 0, 0, # e0 - e7
0, 0, 0, 0, 0, 0, 0, 0, # e8 - ef
0, 0, 0, 0, 0, 0, 0, 0, # f0 - f7
0, 0, 0, 0, 0, 0, 4, 5 # f8 - ff
)
UCS2BE_ST = (
@@ -433,50 +513,53 @@ UCS2BE_ST = (
5, 8, 6, 6,MachineState.ERROR, 6, 6, 6,#28-2f
6, 6, 6, 6,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START #30-37
)
# fmt: on
UCS2BE_CHAR_LEN_TABLE = (2, 2, 2, 0, 2, 2)
UCS2BE_SM_MODEL = {'class_table': UCS2BE_CLS,
'class_factor': 6,
'state_table': UCS2BE_ST,
'char_len_table': UCS2BE_CHAR_LEN_TABLE,
'name': 'UTF-16BE'}
UCS2BE_SM_MODEL: CodingStateMachineDict = {
"class_table": UCS2BE_CLS,
"class_factor": 6,
"state_table": UCS2BE_ST,
"char_len_table": UCS2BE_CHAR_LEN_TABLE,
"name": "UTF-16BE",
}
# UCS2-LE
# fmt: off
UCS2LE_CLS = (
0,0,0,0,0,0,0,0, # 00 - 07
0,0,1,0,0,2,0,0, # 08 - 0f
0,0,0,0,0,0,0,0, # 10 - 17
0,0,0,3,0,0,0,0, # 18 - 1f
0,0,0,0,0,0,0,0, # 20 - 27
0,3,3,3,3,3,0,0, # 28 - 2f
0,0,0,0,0,0,0,0, # 30 - 37
0,0,0,0,0,0,0,0, # 38 - 3f
0,0,0,0,0,0,0,0, # 40 - 47
0,0,0,0,0,0,0,0, # 48 - 4f
0,0,0,0,0,0,0,0, # 50 - 57
0,0,0,0,0,0,0,0, # 58 - 5f
0,0,0,0,0,0,0,0, # 60 - 67
0,0,0,0,0,0,0,0, # 68 - 6f
0,0,0,0,0,0,0,0, # 70 - 77
0,0,0,0,0,0,0,0, # 78 - 7f
0,0,0,0,0,0,0,0, # 80 - 87
0,0,0,0,0,0,0,0, # 88 - 8f
0,0,0,0,0,0,0,0, # 90 - 97
0,0,0,0,0,0,0,0, # 98 - 9f
0,0,0,0,0,0,0,0, # a0 - a7
0,0,0,0,0,0,0,0, # a8 - af
0,0,0,0,0,0,0,0, # b0 - b7
0,0,0,0,0,0,0,0, # b8 - bf
0,0,0,0,0,0,0,0, # c0 - c7
0,0,0,0,0,0,0,0, # c8 - cf
0,0,0,0,0,0,0,0, # d0 - d7
0,0,0,0,0,0,0,0, # d8 - df
0,0,0,0,0,0,0,0, # e0 - e7
0,0,0,0,0,0,0,0, # e8 - ef
0,0,0,0,0,0,0,0, # f0 - f7
0,0,0,0,0,0,4,5 # f8 - ff
0, 0, 0, 0, 0, 0, 0, 0, # 00 - 07
0, 0, 1, 0, 0, 2, 0, 0, # 08 - 0f
0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17
0, 0, 0, 3, 0, 0, 0, 0, # 18 - 1f
0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27
0, 3, 3, 3, 3, 3, 0, 0, # 28 - 2f
0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37
0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f
0, 0, 0, 0, 0, 0, 0, 0, # 40 - 47
0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f
0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57
0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f
0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67
0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f
0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77
0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f
0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87
0, 0, 0, 0, 0, 0, 0, 0, # 88 - 8f
0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97
0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f
0, 0, 0, 0, 0, 0, 0, 0, # a0 - a7
0, 0, 0, 0, 0, 0, 0, 0, # a8 - af
0, 0, 0, 0, 0, 0, 0, 0, # b0 - b7
0, 0, 0, 0, 0, 0, 0, 0, # b8 - bf
0, 0, 0, 0, 0, 0, 0, 0, # c0 - c7
0, 0, 0, 0, 0, 0, 0, 0, # c8 - cf
0, 0, 0, 0, 0, 0, 0, 0, # d0 - d7
0, 0, 0, 0, 0, 0, 0, 0, # d8 - df
0, 0, 0, 0, 0, 0, 0, 0, # e0 - e7
0, 0, 0, 0, 0, 0, 0, 0, # e8 - ef
0, 0, 0, 0, 0, 0, 0, 0, # f0 - f7
0, 0, 0, 0, 0, 0, 4, 5 # f8 - ff
)
UCS2LE_ST = (
@@ -488,50 +571,53 @@ UCS2LE_ST = (
5, 5, 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 5, 5,#28-2f
5, 5, 5,MachineState.ERROR, 5,MachineState.ERROR,MachineState.START,MachineState.START #30-37
)
# fmt: on
UCS2LE_CHAR_LEN_TABLE = (2, 2, 2, 2, 2, 2)
UCS2LE_SM_MODEL = {'class_table': UCS2LE_CLS,
'class_factor': 6,
'state_table': UCS2LE_ST,
'char_len_table': UCS2LE_CHAR_LEN_TABLE,
'name': 'UTF-16LE'}
UCS2LE_SM_MODEL: CodingStateMachineDict = {
"class_table": UCS2LE_CLS,
"class_factor": 6,
"state_table": UCS2LE_ST,
"char_len_table": UCS2LE_CHAR_LEN_TABLE,
"name": "UTF-16LE",
}
# UTF-8
# fmt: off
UTF8_CLS = (
1,1,1,1,1,1,1,1, # 00 - 07 #allow 0x00 as a legal value
1,1,1,1,1,1,0,0, # 08 - 0f
1,1,1,1,1,1,1,1, # 10 - 17
1,1,1,0,1,1,1,1, # 18 - 1f
1,1,1,1,1,1,1,1, # 20 - 27
1,1,1,1,1,1,1,1, # 28 - 2f
1,1,1,1,1,1,1,1, # 30 - 37
1,1,1,1,1,1,1,1, # 38 - 3f
1,1,1,1,1,1,1,1, # 40 - 47
1,1,1,1,1,1,1,1, # 48 - 4f
1,1,1,1,1,1,1,1, # 50 - 57
1,1,1,1,1,1,1,1, # 58 - 5f
1,1,1,1,1,1,1,1, # 60 - 67
1,1,1,1,1,1,1,1, # 68 - 6f
1,1,1,1,1,1,1,1, # 70 - 77
1,1,1,1,1,1,1,1, # 78 - 7f
2,2,2,2,3,3,3,3, # 80 - 87
4,4,4,4,4,4,4,4, # 88 - 8f
4,4,4,4,4,4,4,4, # 90 - 97
4,4,4,4,4,4,4,4, # 98 - 9f
5,5,5,5,5,5,5,5, # a0 - a7
5,5,5,5,5,5,5,5, # a8 - af
5,5,5,5,5,5,5,5, # b0 - b7
5,5,5,5,5,5,5,5, # b8 - bf
0,0,6,6,6,6,6,6, # c0 - c7
6,6,6,6,6,6,6,6, # c8 - cf
6,6,6,6,6,6,6,6, # d0 - d7
6,6,6,6,6,6,6,6, # d8 - df
7,8,8,8,8,8,8,8, # e0 - e7
8,8,8,8,8,9,8,8, # e8 - ef
10,11,11,11,11,11,11,11, # f0 - f7
12,13,13,13,14,15,0,0 # f8 - ff
1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 #allow 0x00 as a legal value
1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f
1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17
1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f
1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27
1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f
1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37
1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f
1, 1, 1, 1, 1, 1, 1, 1, # 40 - 47
1, 1, 1, 1, 1, 1, 1, 1, # 48 - 4f
1, 1, 1, 1, 1, 1, 1, 1, # 50 - 57
1, 1, 1, 1, 1, 1, 1, 1, # 58 - 5f
1, 1, 1, 1, 1, 1, 1, 1, # 60 - 67
1, 1, 1, 1, 1, 1, 1, 1, # 68 - 6f
1, 1, 1, 1, 1, 1, 1, 1, # 70 - 77
1, 1, 1, 1, 1, 1, 1, 1, # 78 - 7f
2, 2, 2, 2, 3, 3, 3, 3, # 80 - 87
4, 4, 4, 4, 4, 4, 4, 4, # 88 - 8f
4, 4, 4, 4, 4, 4, 4, 4, # 90 - 97
4, 4, 4, 4, 4, 4, 4, 4, # 98 - 9f
5, 5, 5, 5, 5, 5, 5, 5, # a0 - a7
5, 5, 5, 5, 5, 5, 5, 5, # a8 - af
5, 5, 5, 5, 5, 5, 5, 5, # b0 - b7
5, 5, 5, 5, 5, 5, 5, 5, # b8 - bf
0, 0, 6, 6, 6, 6, 6, 6, # c0 - c7
6, 6, 6, 6, 6, 6, 6, 6, # c8 - cf
6, 6, 6, 6, 6, 6, 6, 6, # d0 - d7
6, 6, 6, 6, 6, 6, 6, 6, # d8 - df
7, 8, 8, 8, 8, 8, 8, 8, # e0 - e7
8, 8, 8, 8, 8, 9, 8, 8, # e8 - ef
10, 11, 11, 11, 11, 11, 11, 11, # f0 - f7
12, 13, 13, 13, 14, 15, 0, 0 # f8 - ff
)
UTF8_ST = (
@@ -562,11 +648,14 @@ UTF8_ST = (
MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,#c0-c7
MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR #c8-cf
)
# fmt: on
UTF8_CHAR_LEN_TABLE = (0, 1, 0, 0, 0, 0, 2, 3, 3, 3, 4, 4, 5, 5, 6, 6)
UTF8_SM_MODEL = {'class_table': UTF8_CLS,
'class_factor': 16,
'state_table': UTF8_ST,
'char_len_table': UTF8_CHAR_LEN_TABLE,
'name': 'UTF-8'}
UTF8_SM_MODEL: CodingStateMachineDict = {
"class_table": UTF8_CLS,
"class_factor": 16,
"state_table": UTF8_ST,
"char_len_table": UTF8_CHAR_LEN_TABLE,
"name": "UTF-8",
}

576
venv/Lib/site-packages/pip/_vendor/chardet/metadata/languages.py
View File

@@ -1,19 +1,17 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Metadata about languages used by our model training code for our
SingleByteCharSetProbers. Could be used for other things in the future.
This code is based on the language metadata from the uchardet project.
"""
from __future__ import absolute_import, print_function
from string import ascii_letters
from typing import List, Optional
# TODO: Add Ukrainian (KOI8-U)
# TODO: Add Ukranian (KOI8-U)
class Language(object):
class Language:
"""Metadata about a language useful for training models
:ivar name: The human name for the language, in English.
@@ -33,9 +31,17 @@ class Language(object):
Wikipedia for training data.
:type wiki_start_pages: list of str
"""
def __init__(self, name=None, iso_code=None, use_ascii=True, charsets=None,
alphabet=None, wiki_start_pages=None):
super(Language, self).__init__()
def __init__(
self,
name: Optional[str] = None,
iso_code: Optional[str] = None,
use_ascii: bool = True,
charsets: Optional[List[str]] = None,
alphabet: Optional[str] = None,
wiki_start_pages: Optional[List[str]] = None,
) -> None:
super().__init__()
self.name = name
self.iso_code = iso_code
self.use_ascii = use_ascii
@@ -46,265 +52,301 @@ class Language(object):
else:
alphabet = ascii_letters
elif not alphabet:
raise ValueError('Must supply alphabet if use_ascii is False')
self.alphabet = ''.join(sorted(set(alphabet))) if alphabet else None
raise ValueError("Must supply alphabet if use_ascii is False")
self.alphabet = "".join(sorted(set(alphabet))) if alphabet else None
self.wiki_start_pages = wiki_start_pages
def __repr__(self):
return '{}({})'.format(self.__class__.__name__,
', '.join('{}={!r}'.format(k, v)
for k, v in self.__dict__.items()
if not k.startswith('_')))
def __repr__(self) -> str:
param_str = ", ".join(
f"{k}={v!r}" for k, v in self.__dict__.items() if not k.startswith("_")
)
return f"{self.__class__.__name__}({param_str})"
LANGUAGES = {'Arabic': Language(name='Arabic',
iso_code='ar',
use_ascii=False,
# We only support encodings that use isolated
# forms, because the current recommendation is
# that the rendering system handles presentation
# forms. This means we purposefully skip IBM864.
charsets=['ISO-8859-6', 'WINDOWS-1256',
'CP720', 'CP864'],
alphabet=u'ءآأؤإئابةتثجحخدذرزسشصضطظعغػؼؽؾؿـفقكلمنهوىيًٌٍَُِّ',
wiki_start_pages=[u'الصفحة_الرئيسية']),
'Belarusian': Language(name='Belarusian',
iso_code='be',
use_ascii=False,
charsets=['ISO-8859-5', 'WINDOWS-1251',
'IBM866', 'MacCyrillic'],
alphabet=(u'АБВГДЕЁЖЗІЙКЛМНОПРСТУЎФХЦЧШЫЬЭЮЯ'
u'абвгдеёжзійклмнопрстуўфхцчшыьэюяʼ'),
wiki_start_pages=[u'Галоўная_старонка']),
'Bulgarian': Language(name='Bulgarian',
iso_code='bg',
use_ascii=False,
charsets=['ISO-8859-5', 'WINDOWS-1251',
'IBM855'],
alphabet=(u'АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ'
u'абвгдежзийклмнопрстуфхцчшщъьюя'),
wiki_start_pages=[u'Начална_страница']),
'Czech': Language(name='Czech',
iso_code='cz',
use_ascii=True,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=u'áčďéěíňóřšťúůýžÁČĎÉĚÍŇÓŘŠŤÚŮÝŽ',
wiki_start_pages=[u'Hlavní_strana']),
'Danish': Language(name='Danish',
iso_code='da',
use_ascii=True,
charsets=['ISO-8859-1', 'ISO-8859-15',
'WINDOWS-1252'],
alphabet=u'æøåÆØÅ',
wiki_start_pages=[u'Forside']),
'German': Language(name='German',
iso_code='de',
use_ascii=True,
charsets=['ISO-8859-1', 'WINDOWS-1252'],
alphabet=u'äöüßÄÖÜ',
wiki_start_pages=[u'Wikipedia:Hauptseite']),
'Greek': Language(name='Greek',
iso_code='el',
use_ascii=False,
charsets=['ISO-8859-7', 'WINDOWS-1253'],
alphabet=(u'αβγδεζηθικλμνξοπρσςτυφχψωάέήίόύώ'
u'ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΣΤΥΦΧΨΩΆΈΉΊΌΎΏ'),
wiki_start_pages=[u'Πύλη:Κύρια']),
'English': Language(name='English',
iso_code='en',
use_ascii=True,
charsets=['ISO-8859-1', 'WINDOWS-1252'],
wiki_start_pages=[u'Main_Page']),
'Esperanto': Language(name='Esperanto',
iso_code='eo',
# Q, W, X, and Y not used at all
use_ascii=False,
charsets=['ISO-8859-3'],
alphabet=(u'abcĉdefgĝhĥijĵklmnoprsŝtuŭvz'
u'ABCĈDEFGĜHĤIJĴKLMNOPRSŜTUŬVZ'),
wiki_start_pages=[u'Vikipedio:Ĉefpaĝo']),
'Spanish': Language(name='Spanish',
iso_code='es',
use_ascii=True,
charsets=['ISO-8859-1', 'ISO-8859-15',
'WINDOWS-1252'],
alphabet=u'ñáéíóúüÑÁÉÍÓÚÜ',
wiki_start_pages=[u'Wikipedia:Portada']),
'Estonian': Language(name='Estonian',
iso_code='et',
use_ascii=False,
charsets=['ISO-8859-4', 'ISO-8859-13',
'WINDOWS-1257'],
# C, F, Š, Q, W, X, Y, Z, Ž are only for
# loanwords
alphabet=(u'ABDEGHIJKLMNOPRSTUVÕÄÖÜ'
u'abdeghijklmnoprstuvõäöü'),
wiki_start_pages=[u'Esileht']),
'Finnish': Language(name='Finnish',
iso_code='fi',
use_ascii=True,
charsets=['ISO-8859-1', 'ISO-8859-15',
'WINDOWS-1252'],
alphabet=u'ÅÄÖŠŽåäöšž',
wiki_start_pages=[u'Wikipedia:Etusivu']),
'French': Language(name='French',
iso_code='fr',
use_ascii=True,
charsets=['ISO-8859-1', 'ISO-8859-15',
'WINDOWS-1252'],
alphabet=u'œàâçèéîïùûêŒÀÂÇÈÉÎÏÙÛÊ',
wiki_start_pages=[u'Wikipédia:Accueil_principal',
u'Bœuf (animal)']),
'Hebrew': Language(name='Hebrew',
iso_code='he',
use_ascii=False,
charsets=['ISO-8859-8', 'WINDOWS-1255'],
alphabet=u'אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ',
wiki_start_pages=[u'עמוד_ראשי']),
'Croatian': Language(name='Croatian',
iso_code='hr',
# Q, W, X, Y are only used for foreign words.
use_ascii=False,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=(u'abcčćdđefghijklmnoprsštuvzž'
u'ABCČĆDĐEFGHIJKLMNOPRSŠTUVZŽ'),
wiki_start_pages=[u'Glavna_stranica']),
'Hungarian': Language(name='Hungarian',
iso_code='hu',
# Q, W, X, Y are only used for foreign words.
use_ascii=False,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=(u'abcdefghijklmnoprstuvzáéíóöőúüű'
u'ABCDEFGHIJKLMNOPRSTUVZÁÉÍÓÖŐÚÜŰ'),
wiki_start_pages=[u'Kezdőlap']),
'Italian': Language(name='Italian',
iso_code='it',
use_ascii=True,
charsets=['ISO-8859-1', 'ISO-8859-15',
'WINDOWS-1252'],
alphabet=u'ÀÈÉÌÒÓÙàèéìòóù',
wiki_start_pages=[u'Pagina_principale']),
'Lithuanian': Language(name='Lithuanian',
iso_code='lt',
use_ascii=False,
charsets=['ISO-8859-13', 'WINDOWS-1257',
'ISO-8859-4'],
# Q, W, and X not used at all
alphabet=(u'AĄBCČDEĘĖFGHIĮYJKLMNOPRSŠTUŲŪVZŽ'
u'aąbcčdeęėfghiįyjklmnoprsštuųūvzž'),
wiki_start_pages=[u'Pagrindinis_puslapis']),
'Latvian': Language(name='Latvian',
iso_code='lv',
use_ascii=False,
charsets=['ISO-8859-13', 'WINDOWS-1257',
'ISO-8859-4'],
# Q, W, X, Y are only for loanwords
alphabet=(u'AĀBCČDEĒFGĢHIĪJKĶLĻMNŅOPRSŠTUŪVZŽ'
u'aābcčdeēfgģhiījkķlļmnņoprsštuūvzž'),
wiki_start_pages=[u'Sākumlapa']),
'Macedonian': Language(name='Macedonian',
iso_code='mk',
use_ascii=False,
charsets=['ISO-8859-5', 'WINDOWS-1251',
'MacCyrillic', 'IBM855'],
alphabet=(u'АБВГДЃЕЖЗЅИЈКЛЉМНЊОПРСТЌУФХЦЧЏШ'
u'абвгдѓежзѕијклљмнњопрстќуфхцчџш'),
wiki_start_pages=[u'Главна_страница']),
'Dutch': Language(name='Dutch',
iso_code='nl',
use_ascii=True,
charsets=['ISO-8859-1', 'WINDOWS-1252'],
wiki_start_pages=[u'Hoofdpagina']),
'Polish': Language(name='Polish',
iso_code='pl',
# Q and X are only used for foreign words.
use_ascii=False,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=(u'AĄBCĆDEĘFGHIJKLŁMNŃOÓPRSŚTUWYZŹŻ'
u'aąbcćdeęfghijklłmnńoóprsśtuwyzźż'),
wiki_start_pages=[u'Wikipedia:Strona_główna']),
'Portuguese': Language(name='Portuguese',
iso_code='pt',
use_ascii=True,
charsets=['ISO-8859-1', 'ISO-8859-15',
'WINDOWS-1252'],
alphabet=u'ÁÂÃÀÇÉÊÍÓÔÕÚáâãàçéêíóôõú',
wiki_start_pages=[u'Wikipédia:Página_principal']),
'Romanian': Language(name='Romanian',
iso_code='ro',
use_ascii=True,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=u'ăâîșțĂÂÎȘȚ',
wiki_start_pages=[u'Pagina_principală']),
'Russian': Language(name='Russian',
iso_code='ru',
use_ascii=False,
charsets=['ISO-8859-5', 'WINDOWS-1251',
'KOI8-R', 'MacCyrillic', 'IBM866',
'IBM855'],
alphabet=(u'абвгдеёжзийклмнопрстуфхцчшщъыьэюя'
u'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ'),
wiki_start_pages=[u'Заглавная_страница']),
'Slovak': Language(name='Slovak',
iso_code='sk',
use_ascii=True,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=u'áäčďéíĺľňóôŕšťúýžÁÄČĎÉÍĹĽŇÓÔŔŠŤÚÝŽ',
wiki_start_pages=[u'Hlavná_stránka']),
'Slovene': Language(name='Slovene',
iso_code='sl',
# Q, W, X, Y are only used for foreign words.
use_ascii=False,
charsets=['ISO-8859-2', 'WINDOWS-1250'],
alphabet=(u'abcčdefghijklmnoprsštuvzž'
u'ABCČDEFGHIJKLMNOPRSŠTUVZŽ'),
wiki_start_pages=[u'Glavna_stran']),
# Serbian can be written in both Latin and Cyrillic, but there's no
# simple way to get the Latin alphabet pages from Wikipedia through
# the API, so for now we just support Cyrillic.
'Serbian': Language(name='Serbian',
iso_code='sr',
alphabet=(u'АБВГДЂЕЖЗИЈКЛЉМНЊОПРСТЋУФХЦЧЏШ'
u'абвгдђежзијклљмнњопрстћуфхцчџш'),
charsets=['ISO-8859-5', 'WINDOWS-1251',
'MacCyrillic', 'IBM855'],
wiki_start_pages=[u'Главна_страна']),
'Thai': Language(name='Thai',
iso_code='th',
use_ascii=False,
charsets=['ISO-8859-11', 'TIS-620', 'CP874'],
alphabet=u'กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛',
wiki_start_pages=[u'หน้าหลัก']),
'Turkish': Language(name='Turkish',
iso_code='tr',
# Q, W, and X are not used by Turkish
use_ascii=False,
charsets=['ISO-8859-3', 'ISO-8859-9',
'WINDOWS-1254'],
alphabet=(u'abcçdefgğhıijklmnoöprsştuüvyzâîû'
u'ABCÇDEFGĞHIİJKLMNOÖPRSŞTUÜVYZÂÎÛ'),
wiki_start_pages=[u'Ana_Sayfa']),
'Vietnamese': Language(name='Vietnamese',
iso_code='vi',
use_ascii=False,
# Windows-1258 is the only common 8-bit
# Vietnamese encoding supported by Python.
# From Wikipedia:
# For systems that lack support for Unicode,
# dozens of 8-bit Vietnamese code pages are
# available.[1] The most common are VISCII
# (TCVN 5712:1993), VPS, and Windows-1258.[3]
# Where ASCII is required, such as when
# ensuring readability in plain text e-mail,
# Vietnamese letters are often encoded
# according to Vietnamese Quoted-Readable
# (VIQR) or VSCII Mnemonic (VSCII-MNEM),[4]
# though usage of either variable-width
# scheme has declined dramatically following
# the adoption of Unicode on the World Wide
# Web.
charsets=['WINDOWS-1258'],
alphabet=(u'aăâbcdđeêghiklmnoôơpqrstuưvxy'
u'AĂÂBCDĐEÊGHIKLMNOÔƠPQRSTUƯVXY'),
wiki_start_pages=[u'Chữ_Quốc_ngữ']),
}
LANGUAGES = {
"Arabic": Language(
name="Arabic",
iso_code="ar",
use_ascii=False,
# We only support encodings that use isolated
# forms, because the current recommendation is
# that the rendering system handles presentation
# forms. This means we purposefully skip IBM864.
charsets=["ISO-8859-6", "WINDOWS-1256", "CP720", "CP864"],
alphabet="ءآأؤإئابةتثجحخدذرزسشصضطظعغػؼؽؾؿـفقكلمنهوىيًٌٍَُِّ",
wiki_start_pages=["الصفحة_الرئيسية"],
),
"Belarusian": Language(
name="Belarusian",
iso_code="be",
use_ascii=False,
charsets=["ISO-8859-5", "WINDOWS-1251", "IBM866", "MacCyrillic"],
alphabet="АБВГДЕЁЖЗІЙКЛМНОПРСТУЎФХЦЧШЫЬЭЮЯабвгдеёжзійклмнопрстуўфхцчшыьэюяʼ",
wiki_start_pages=["Галоўная_старонка"],
),
"Bulgarian": Language(
name="Bulgarian",
iso_code="bg",
use_ascii=False,
charsets=["ISO-8859-5", "WINDOWS-1251", "IBM855"],
alphabet="АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя",
wiki_start_pages=["Начална_страница"],
),
"Czech": Language(
name="Czech",
iso_code="cz",
use_ascii=True,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="áčďéěíňóřšťúůýžÁČĎÉĚÍŇÓŘŠŤÚŮÝŽ",
wiki_start_pages=["Hlavní_strana"],
),
"Danish": Language(
name="Danish",
iso_code="da",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="æøåÆØÅ",
wiki_start_pages=["Forside"],
),
"German": Language(
name="German",
iso_code="de",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="äöüßẞÄÖÜ",
wiki_start_pages=["Wikipedia:Hauptseite"],
),
"Greek": Language(
name="Greek",
iso_code="el",
use_ascii=False,
charsets=["ISO-8859-7", "WINDOWS-1253"],
alphabet="αβγδεζηθικλμνξοπρσςτυφχψωάέήίόύώΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΣΤΥΦΧΨΩΆΈΉΊΌΎΏ",
wiki_start_pages=["Πύλη:Κύρια"],
),
"English": Language(
name="English",
iso_code="en",
use_ascii=True,
charsets=["ISO-8859-1", "WINDOWS-1252", "MacRoman"],
wiki_start_pages=["Main_Page"],
),
"Esperanto": Language(
name="Esperanto",
iso_code="eo",
# Q, W, X, and Y not used at all
use_ascii=False,
charsets=["ISO-8859-3"],
alphabet="abcĉdefgĝhĥijĵklmnoprsŝtuŭvzABCĈDEFGĜHĤIJĴKLMNOPRSŜTUŬVZ",
wiki_start_pages=["Vikipedio:Ĉefpaĝo"],
),
"Spanish": Language(
name="Spanish",
iso_code="es",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="ñáéíóúüÑÁÉÍÓÚÜ",
wiki_start_pages=["Wikipedia:Portada"],
),
"Estonian": Language(
name="Estonian",
iso_code="et",
use_ascii=False,
charsets=["ISO-8859-4", "ISO-8859-13", "WINDOWS-1257"],
# C, F, Š, Q, W, X, Y, Z, Ž are only for
# loanwords
alphabet="ABDEGHIJKLMNOPRSTUVÕÄÖÜabdeghijklmnoprstuvõäöü",
wiki_start_pages=["Esileht"],
),
"Finnish": Language(
name="Finnish",
iso_code="fi",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="ÅÄÖŠŽåäöšž",
wiki_start_pages=["Wikipedia:Etusivu"],
),
"French": Language(
name="French",
iso_code="fr",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="œàâçèéîïùûêŒÀÂÇÈÉÎÏÙÛÊ",
wiki_start_pages=["Wikipédia:Accueil_principal", "Bœuf (animal)"],
),
"Hebrew": Language(
name="Hebrew",
iso_code="he",
use_ascii=False,
charsets=["ISO-8859-8", "WINDOWS-1255"],
alphabet="אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ",
wiki_start_pages=["עמוד_ראשי"],
),
"Croatian": Language(
name="Croatian",
iso_code="hr",
# Q, W, X, Y are only used for foreign words.
use_ascii=False,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="abcčćdđefghijklmnoprsštuvzžABCČĆDĐEFGHIJKLMNOPRSŠTUVZŽ",
wiki_start_pages=["Glavna_stranica"],
),
"Hungarian": Language(
name="Hungarian",
iso_code="hu",
# Q, W, X, Y are only used for foreign words.
use_ascii=False,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="abcdefghijklmnoprstuvzáéíóöőúüűABCDEFGHIJKLMNOPRSTUVZÁÉÍÓÖŐÚÜŰ",
wiki_start_pages=["Kezdőlap"],
),
"Italian": Language(
name="Italian",
iso_code="it",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="ÀÈÉÌÒÓÙàèéìòóù",
wiki_start_pages=["Pagina_principale"],
),
"Lithuanian": Language(
name="Lithuanian",
iso_code="lt",
use_ascii=False,
charsets=["ISO-8859-13", "WINDOWS-1257", "ISO-8859-4"],
# Q, W, and X not used at all
alphabet="AĄBCČDEĘĖFGHIĮYJKLMNOPRSŠTUŲŪVZŽaąbcčdeęėfghiįyjklmnoprsštuųūvzž",
wiki_start_pages=["Pagrindinis_puslapis"],
),
"Latvian": Language(
name="Latvian",
iso_code="lv",
use_ascii=False,
charsets=["ISO-8859-13", "WINDOWS-1257", "ISO-8859-4"],
# Q, W, X, Y are only for loanwords
alphabet="AĀBCČDEĒFGĢHIĪJKĶLĻMNŅOPRSŠTUŪVZŽaābcčdeēfgģhiījkķlļmnņoprsštuūvzž",
wiki_start_pages=["Sākumlapa"],
),
"Macedonian": Language(
name="Macedonian",
iso_code="mk",
use_ascii=False,
charsets=["ISO-8859-5", "WINDOWS-1251", "MacCyrillic", "IBM855"],
alphabet="АБВГДЃЕЖЗЅИЈКЛЉМНЊОПРСТЌУФХЦЧЏШабвгдѓежзѕијклљмнњопрстќуфхцчџш",
wiki_start_pages=["Главна_страница"],
),
"Dutch": Language(
name="Dutch",
iso_code="nl",
use_ascii=True,
charsets=["ISO-8859-1", "WINDOWS-1252", "MacRoman"],
wiki_start_pages=["Hoofdpagina"],
),
"Polish": Language(
name="Polish",
iso_code="pl",
# Q and X are only used for foreign words.
use_ascii=False,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="AĄBCĆDEĘFGHIJKLŁMNŃOÓPRSŚTUWYZŹŻaąbcćdeęfghijklłmnńoóprsśtuwyzźż",
wiki_start_pages=["Wikipedia:Strona_główna"],
),
"Portuguese": Language(
name="Portuguese",
iso_code="pt",
use_ascii=True,
charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
alphabet="ÁÂÃÀÇÉÊÍÓÔÕÚáâãàçéêíóôõú",
wiki_start_pages=["Wikipédia:Página_principal"],
),
"Romanian": Language(
name="Romanian",
iso_code="ro",
use_ascii=True,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="ăâîșțĂÂÎȘȚ",
wiki_start_pages=["Pagina_principală"],
),
"Russian": Language(
name="Russian",
iso_code="ru",
use_ascii=False,
charsets=[
"ISO-8859-5",
"WINDOWS-1251",
"KOI8-R",
"MacCyrillic",
"IBM866",
"IBM855",
],
alphabet="абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ",
wiki_start_pages=["Заглавная_страница"],
),
"Slovak": Language(
name="Slovak",
iso_code="sk",
use_ascii=True,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="áäčďéíĺľňóôŕšťúýžÁÄČĎÉÍĹĽŇÓÔŔŠŤÚÝŽ",
wiki_start_pages=["Hlavná_stránka"],
),
"Slovene": Language(
name="Slovene",
iso_code="sl",
# Q, W, X, Y are only used for foreign words.
use_ascii=False,
charsets=["ISO-8859-2", "WINDOWS-1250"],
alphabet="abcčdefghijklmnoprsštuvzžABCČDEFGHIJKLMNOPRSŠTUVZŽ",
wiki_start_pages=["Glavna_stran"],
),
# Serbian can be written in both Latin and Cyrillic, but there's no
# simple way to get the Latin alphabet pages from Wikipedia through
# the API, so for now we just support Cyrillic.
"Serbian": Language(
name="Serbian",
iso_code="sr",
alphabet="АБВГДЂЕЖЗИЈКЛЉМНЊОПРСТЋУФХЦЧЏШабвгдђежзијклљмнњопрстћуфхцчџш",
charsets=["ISO-8859-5", "WINDOWS-1251", "MacCyrillic", "IBM855"],
wiki_start_pages=["Главна_страна"],
),
"Thai": Language(
name="Thai",
iso_code="th",
use_ascii=False,
charsets=["ISO-8859-11", "TIS-620", "CP874"],
alphabet="กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛",
wiki_start_pages=["หน้าหลัก"],
),
"Turkish": Language(
name="Turkish",
iso_code="tr",
# Q, W, and X are not used by Turkish
use_ascii=False,
charsets=["ISO-8859-3", "ISO-8859-9", "WINDOWS-1254"],
alphabet="abcçdefgğhıijklmnoöprsştuüvyzâîûABCÇDEFGĞHIİJKLMNOÖPRSŞTUÜVYZÂÎÛ",
wiki_start_pages=["Ana_Sayfa"],
),
"Vietnamese": Language(
name="Vietnamese",
iso_code="vi",
use_ascii=False,
# Windows-1258 is the only common 8-bit
# Vietnamese encoding supported by Python.
# From Wikipedia:
# For systems that lack support for Unicode,
# dozens of 8-bit Vietnamese code pages are
# available.[1] The most common are VISCII
# (TCVN 5712:1993), VPS, and Windows-1258.[3]
# Where ASCII is required, such as when
# ensuring readability in plain text e-mail,
# Vietnamese letters are often encoded
# according to Vietnamese Quoted-Readable
# (VIQR) or VSCII Mnemonic (VSCII-MNEM),[4]
# though usage of either variable-width
# scheme has declined dramatically following
# the adoption of Unicode on the World Wide
# Web.
charsets=["WINDOWS-1258"],
alphabet="aăâbcdđeêghiklmnoôơpqrstuưvxyAĂÂBCDĐEÊGHIKLMNOÔƠPQRSTUƯVXY",
wiki_start_pages=["Chữ_Quốc_ngữ"],
),
}

95
venv/Lib/site-packages/pip/_vendor/chardet/sbcharsetprober.py
View File

@@ -26,70 +26,77 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from collections import namedtuple
from typing import Dict, List, NamedTuple, Optional, Union
from .charsetprober import CharSetProber
from .enums import CharacterCategory, ProbingState, SequenceLikelihood
SingleByteCharSetModel = namedtuple('SingleByteCharSetModel',
['charset_name',
'language',
'char_to_order_map',
'language_model',
'typical_positive_ratio',
'keep_ascii_letters',
'alphabet'])
class SingleByteCharSetModel(NamedTuple):
charset_name: str
language: str
char_to_order_map: Dict[int, int]
language_model: Dict[int, Dict[int, int]]
typical_positive_ratio: float
keep_ascii_letters: bool
alphabet: str
class SingleByteCharSetProber(CharSetProber):
SAMPLE_SIZE = 64
SB_ENOUGH_REL_THRESHOLD = 1024 # 0.25 * SAMPLE_SIZE^2
SB_ENOUGH_REL_THRESHOLD = 1024 # 0.25 * SAMPLE_SIZE^2
POSITIVE_SHORTCUT_THRESHOLD = 0.95
NEGATIVE_SHORTCUT_THRESHOLD = 0.05
def __init__(self, model, reversed=False, name_prober=None):
super(SingleByteCharSetProber, self).__init__()
def __init__(
self,
model: SingleByteCharSetModel,
is_reversed: bool = False,
name_prober: Optional[CharSetProber] = None,
) -> None:
super().__init__()
self._model = model
# TRUE if we need to reverse every pair in the model lookup
self._reversed = reversed
self._reversed = is_reversed
# Optional auxiliary prober for name decision
self._name_prober = name_prober
self._last_order = None
self._seq_counters = None
self._total_seqs = None
self._total_char = None
self._freq_char = None
self._last_order = 255
self._seq_counters: List[int] = []
self._total_seqs = 0
self._total_char = 0
self._control_char = 0
self._freq_char = 0
self.reset()
def reset(self):
super(SingleByteCharSetProber, self).reset()
def reset(self) -> None:
super().reset()
# char order of last character
self._last_order = 255
self._seq_counters = [0] * SequenceLikelihood.get_num_categories()
self._total_seqs = 0
self._total_char = 0
self._control_char = 0
# characters that fall in our sampling range
self._freq_char = 0
@property
def charset_name(self):
def charset_name(self) -> Optional[str]:
if self._name_prober:
return self._name_prober.charset_name
else:
return self._model.charset_name
return self._model.charset_name
@property
def language(self):
def language(self) -> Optional[str]:
if self._name_prober:
return self._name_prober.language
else:
return self._model.language
return self._model.language
def feed(self, byte_str):
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
# TODO: Make filter_international_words keep things in self.alphabet
if not self._model.keep_ascii_letters:
byte_str = self.filter_international_words(byte_str)
else:
byte_str = self.remove_xml_tags(byte_str)
if not byte_str:
return self.state
char_to_order_map = self._model.char_to_order_map
@@ -103,9 +110,6 @@ class SingleByteCharSetProber(CharSetProber):
# _total_char purposes.
if order < CharacterCategory.CONTROL:
self._total_char += 1
# TODO: Follow uchardet's lead and discount confidence for frequent
# control characters.
# See https://github.com/BYVoid/uchardet/commit/55b4f23971db61
if order < self.SAMPLE_SIZE:
self._freq_char += 1
if self._last_order < self.SAMPLE_SIZE:
@@ -122,23 +126,36 @@ class SingleByteCharSetProber(CharSetProber):
if self._total_seqs > self.SB_ENOUGH_REL_THRESHOLD:
confidence = self.get_confidence()
if confidence > self.POSITIVE_SHORTCUT_THRESHOLD:
self.logger.debug('%s confidence = %s, we have a winner',
charset_name, confidence)
self.logger.debug(
"%s confidence = %s, we have a winner", charset_name, confidence
)
self._state = ProbingState.FOUND_IT
elif confidence < self.NEGATIVE_SHORTCUT_THRESHOLD:
self.logger.debug('%s confidence = %s, below negative '
'shortcut threshhold %s', charset_name,
confidence,
self.NEGATIVE_SHORTCUT_THRESHOLD)
self.logger.debug(
"%s confidence = %s, below negative shortcut threshold %s",
charset_name,
confidence,
self.NEGATIVE_SHORTCUT_THRESHOLD,
)
self._state = ProbingState.NOT_ME
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
r = 0.01
if self._total_seqs > 0:
r = ((1.0 * self._seq_counters[SequenceLikelihood.POSITIVE]) /
self._total_seqs / self._model.typical_positive_ratio)
r = (
(
self._seq_counters[SequenceLikelihood.POSITIVE]
+ 0.25 * self._seq_counters[SequenceLikelihood.LIKELY]
)
/ self._total_seqs
/ self._model.typical_positive_ratio
)
# The more control characters (proportionnaly to the size
# of the text), the less confident we become in the current
# charset.
r = r * (self._total_char - self._control_char) / self._total_char
r = r * self._freq_char / self._total_char
if r >= 1.0:
r = 0.99

33
venv/Lib/site-packages/pip/_vendor/chardet/sbcsgroupprober.py
View File

@@ -28,33 +28,38 @@
from .charsetgroupprober import CharSetGroupProber
from .hebrewprober import HebrewProber
from .langbulgarianmodel import (ISO_8859_5_BULGARIAN_MODEL,
WINDOWS_1251_BULGARIAN_MODEL)
from .langbulgarianmodel import ISO_8859_5_BULGARIAN_MODEL, WINDOWS_1251_BULGARIAN_MODEL
from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL
from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL
# from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL,
# WINDOWS_1250_HUNGARIAN_MODEL)
from .langrussianmodel import (IBM855_RUSSIAN_MODEL, IBM866_RUSSIAN_MODEL,
ISO_8859_5_RUSSIAN_MODEL, KOI8_R_RUSSIAN_MODEL,
MACCYRILLIC_RUSSIAN_MODEL,
WINDOWS_1251_RUSSIAN_MODEL)
from .langrussianmodel import (
IBM855_RUSSIAN_MODEL,
IBM866_RUSSIAN_MODEL,
ISO_8859_5_RUSSIAN_MODEL,
KOI8_R_RUSSIAN_MODEL,
MACCYRILLIC_RUSSIAN_MODEL,
WINDOWS_1251_RUSSIAN_MODEL,
)
from .langthaimodel import TIS_620_THAI_MODEL
from .langturkishmodel import ISO_8859_9_TURKISH_MODEL
from .sbcharsetprober import SingleByteCharSetProber
class SBCSGroupProber(CharSetGroupProber):
def __init__(self):
super(SBCSGroupProber, self).__init__()
def __init__(self) -> None:
super().__init__()
hebrew_prober = HebrewProber()
logical_hebrew_prober = SingleByteCharSetProber(WINDOWS_1255_HEBREW_MODEL,
False, hebrew_prober)
logical_hebrew_prober = SingleByteCharSetProber(
WINDOWS_1255_HEBREW_MODEL, is_reversed=False, name_prober=hebrew_prober
)
# TODO: See if using ISO-8859-8 Hebrew model works better here, since
# it's actually the visual one
visual_hebrew_prober = SingleByteCharSetProber(WINDOWS_1255_HEBREW_MODEL,
True, hebrew_prober)
hebrew_prober.set_model_probers(logical_hebrew_prober,
visual_hebrew_prober)
visual_hebrew_prober = SingleByteCharSetProber(
WINDOWS_1255_HEBREW_MODEL, is_reversed=True, name_prober=hebrew_prober
)
hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober)
# TODO: ORDER MATTERS HERE. I changed the order vs what was in master
# and several tests failed that did not before. Some thought
# should be put into the ordering, and we should consider making

65
venv/Lib/site-packages/pip/_vendor/chardet/sjisprober.py
View File

@@ -25,68 +25,81 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from typing import Union
from .chardistribution import SJISDistributionAnalysis
from .codingstatemachine import CodingStateMachine
from .enums import MachineState, ProbingState
from .jpcntx import SJISContextAnalysis
from .mbcharsetprober import MultiByteCharSetProber
from .mbcssm import SJIS_SM_MODEL
from .enums import ProbingState, MachineState
class SJISProber(MultiByteCharSetProber):
def __init__(self):
super(SJISProber, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(SJIS_SM_MODEL)
self.distribution_analyzer = SJISDistributionAnalysis()
self.context_analyzer = SJISContextAnalysis()
self.reset()
def reset(self):
super(SJISProber, self).reset()
def reset(self) -> None:
super().reset()
self.context_analyzer.reset()
@property
def charset_name(self):
def charset_name(self) -> str:
return self.context_analyzer.charset_name
@property
def language(self):
def language(self) -> str:
return "Japanese"
def feed(self, byte_str):
for i in range(len(byte_str)):
coding_state = self.coding_sm.next_state(byte_str[i])
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
assert self.coding_sm is not None
assert self.distribution_analyzer is not None
for i, byte in enumerate(byte_str):
coding_state = self.coding_sm.next_state(byte)
if coding_state == MachineState.ERROR:
self.logger.debug('%s %s prober hit error at byte %s',
self.charset_name, self.language, i)
self.logger.debug(
"%s %s prober hit error at byte %s",
self.charset_name,
self.language,
i,
)
self._state = ProbingState.NOT_ME
break
elif coding_state == MachineState.ITS_ME:
if coding_state == MachineState.ITS_ME:
self._state = ProbingState.FOUND_IT
break
elif coding_state == MachineState.START:
if coding_state == MachineState.START:
char_len = self.coding_sm.get_current_charlen()
if i == 0:
self._last_char[1] = byte_str[0]
self.context_analyzer.feed(self._last_char[2 - char_len:],
char_len)
self._last_char[1] = byte
self.context_analyzer.feed(
self._last_char[2 - char_len :], char_len
)
self.distribution_analyzer.feed(self._last_char, char_len)
else:
self.context_analyzer.feed(byte_str[i + 1 - char_len:i + 3
- char_len], char_len)
self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
char_len)
self.context_analyzer.feed(
byte_str[i + 1 - char_len : i + 3 - char_len], char_len
)
self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len)
self._last_char[0] = byte_str[-1]
if self.state == ProbingState.DETECTING:
if (self.context_analyzer.got_enough_data() and
(self.get_confidence() > self.SHORTCUT_THRESHOLD)):
if self.context_analyzer.got_enough_data() and (
self.get_confidence() > self.SHORTCUT_THRESHOLD
):
self._state = ProbingState.FOUND_IT
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
assert self.distribution_analyzer is not None
context_conf = self.context_analyzer.get_confidence()
distrib_conf = self.distribution_analyzer.get_confidence()
return max(context_conf, distrib_conf)

234
venv/Lib/site-packages/pip/_vendor/chardet/universaldetector.py
View File

@@ -39,16 +39,21 @@ class a user of ``chardet`` should use.
import codecs
import logging
import re
from typing import List, Optional, Union
from .charsetgroupprober import CharSetGroupProber
from .charsetprober import CharSetProber
from .enums import InputState, LanguageFilter, ProbingState
from .escprober import EscCharSetProber
from .latin1prober import Latin1Prober
from .macromanprober import MacRomanProber
from .mbcsgroupprober import MBCSGroupProber
from .resultdict import ResultDict
from .sbcsgroupprober import SBCSGroupProber
from .utf1632prober import UTF1632Prober
class UniversalDetector(object):
class UniversalDetector:
"""
The ``UniversalDetector`` class underlies the ``chardet.detect`` function
and coordinates all of the different charset probers.
@@ -66,49 +71,87 @@ class UniversalDetector(object):
"""
MINIMUM_THRESHOLD = 0.20
HIGH_BYTE_DETECTOR = re.compile(b'[\x80-\xFF]')
ESC_DETECTOR = re.compile(b'(\033|~{)')
WIN_BYTE_DETECTOR = re.compile(b'[\x80-\x9F]')
ISO_WIN_MAP = {'iso-8859-1': 'Windows-1252',
'iso-8859-2': 'Windows-1250',
'iso-8859-5': 'Windows-1251',
'iso-8859-6': 'Windows-1256',
'iso-8859-7': 'Windows-1253',
'iso-8859-8': 'Windows-1255',
'iso-8859-9': 'Windows-1254',
'iso-8859-13': 'Windows-1257'}
HIGH_BYTE_DETECTOR = re.compile(b"[\x80-\xFF]")
ESC_DETECTOR = re.compile(b"(\033|~{)")
WIN_BYTE_DETECTOR = re.compile(b"[\x80-\x9F]")
ISO_WIN_MAP = {
"iso-8859-1": "Windows-1252",
"iso-8859-2": "Windows-1250",
"iso-8859-5": "Windows-1251",
"iso-8859-6": "Windows-1256",
"iso-8859-7": "Windows-1253",
"iso-8859-8": "Windows-1255",
"iso-8859-9": "Windows-1254",
"iso-8859-13": "Windows-1257",
}
# Based on https://encoding.spec.whatwg.org/#names-and-labels
# but altered to match Python names for encodings and remove mappings
# that break tests.
LEGACY_MAP = {
"ascii": "Windows-1252",
"iso-8859-1": "Windows-1252",
"tis-620": "ISO-8859-11",
"iso-8859-9": "Windows-1254",
"gb2312": "GB18030",
"euc-kr": "CP949",
"utf-16le": "UTF-16",
}
def __init__(self, lang_filter=LanguageFilter.ALL):
self._esc_charset_prober = None
self._charset_probers = []
self.result = None
self.done = None
self._got_data = None
self._input_state = None
self._last_char = None
def __init__(
self,
lang_filter: LanguageFilter = LanguageFilter.ALL,
should_rename_legacy: bool = False,
) -> None:
self._esc_charset_prober: Optional[EscCharSetProber] = None
self._utf1632_prober: Optional[UTF1632Prober] = None
self._charset_probers: List[CharSetProber] = []
self.result: ResultDict = {
"encoding": None,
"confidence": 0.0,
"language": None,
}
self.done = False
self._got_data = False
self._input_state = InputState.PURE_ASCII
self._last_char = b""
self.lang_filter = lang_filter
self.logger = logging.getLogger(__name__)
self._has_win_bytes = None
self._has_win_bytes = False
self.should_rename_legacy = should_rename_legacy
self.reset()
def reset(self):
@property
def input_state(self) -> int:
return self._input_state
@property
def has_win_bytes(self) -> bool:
return self._has_win_bytes
@property
def charset_probers(self) -> List[CharSetProber]:
return self._charset_probers
def reset(self) -> None:
"""
Reset the UniversalDetector and all of its probers back to their
initial states. This is called by ``__init__``, so you only need to
call this directly in between analyses of different documents.
"""
self.result = {'encoding': None, 'confidence': 0.0, 'language': None}
self.result = {"encoding": None, "confidence": 0.0, "language": None}
self.done = False
self._got_data = False
self._has_win_bytes = False
self._input_state = InputState.PURE_ASCII
self._last_char = b''
self._last_char = b""
if self._esc_charset_prober:
self._esc_charset_prober.reset()
if self._utf1632_prober:
self._utf1632_prober.reset()
for prober in self._charset_probers:
prober.reset()
def feed(self, byte_str):
def feed(self, byte_str: Union[bytes, bytearray]) -> None:
"""
Takes a chunk of a document and feeds it through all of the relevant
charset probers.
@@ -125,7 +168,7 @@ class UniversalDetector(object):
if self.done:
return
if not len(byte_str):
if not byte_str:
return
if not isinstance(byte_str, bytearray):
@@ -136,35 +179,38 @@ class UniversalDetector(object):
# If the data starts with BOM, we know it is UTF
if byte_str.startswith(codecs.BOM_UTF8):
# EF BB BF UTF-8 with BOM
self.result = {'encoding': "UTF-8-SIG",
'confidence': 1.0,
'language': ''}
elif byte_str.startswith((codecs.BOM_UTF32_LE,
codecs.BOM_UTF32_BE)):
self.result = {
"encoding": "UTF-8-SIG",
"confidence": 1.0,
"language": "",
}
elif byte_str.startswith((codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE)):
# FF FE 00 00 UTF-32, little-endian BOM
# 00 00 FE FF UTF-32, big-endian BOM
self.result = {'encoding': "UTF-32",
'confidence': 1.0,
'language': ''}
elif byte_str.startswith(b'\xFE\xFF\x00\x00'):
self.result = {"encoding": "UTF-32", "confidence": 1.0, "language": ""}
elif byte_str.startswith(b"\xFE\xFF\x00\x00"):
# FE FF 00 00 UCS-4, unusual octet order BOM (3412)
self.result = {'encoding': "X-ISO-10646-UCS-4-3412",
'confidence': 1.0,
'language': ''}
elif byte_str.startswith(b'\x00\x00\xFF\xFE'):
self.result = {
# TODO: This encoding is not supported by Python. Should remove?
"encoding": "X-ISO-10646-UCS-4-3412",
"confidence": 1.0,
"language": "",
}
elif byte_str.startswith(b"\x00\x00\xFF\xFE"):
# 00 00 FF FE UCS-4, unusual octet order BOM (2143)
self.result = {'encoding': "X-ISO-10646-UCS-4-2143",
'confidence': 1.0,
'language': ''}
self.result = {
# TODO: This encoding is not supported by Python. Should remove?
"encoding": "X-ISO-10646-UCS-4-2143",
"confidence": 1.0,
"language": "",
}
elif byte_str.startswith((codecs.BOM_LE, codecs.BOM_BE)):
# FF FE UTF-16, little endian BOM
# FE FF UTF-16, big endian BOM
self.result = {'encoding': "UTF-16",
'confidence': 1.0,
'language': ''}
self.result = {"encoding": "UTF-16", "confidence": 1.0, "language": ""}
self._got_data = True
if self.result['encoding'] is not None:
if self.result["encoding"] is not None:
self.done = True
return
@@ -173,12 +219,29 @@ class UniversalDetector(object):
if self._input_state == InputState.PURE_ASCII:
if self.HIGH_BYTE_DETECTOR.search(byte_str):
self._input_state = InputState.HIGH_BYTE
elif self._input_state == InputState.PURE_ASCII and \
self.ESC_DETECTOR.search(self._last_char + byte_str):
elif (
self._input_state == InputState.PURE_ASCII
and self.ESC_DETECTOR.search(self._last_char + byte_str)
):
self._input_state = InputState.ESC_ASCII
self._last_char = byte_str[-1:]
# next we will look to see if it is appears to be either a UTF-16 or
# UTF-32 encoding
if not self._utf1632_prober:
self._utf1632_prober = UTF1632Prober()
if self._utf1632_prober.state == ProbingState.DETECTING:
if self._utf1632_prober.feed(byte_str) == ProbingState.FOUND_IT:
self.result = {
"encoding": self._utf1632_prober.charset_name,
"confidence": self._utf1632_prober.get_confidence(),
"language": "",
}
self.done = True
return
# If we've seen escape sequences, use the EscCharSetProber, which
# uses a simple state machine to check for known escape sequences in
# HZ and ISO-2022 encodings, since those are the only encodings that
@@ -187,12 +250,11 @@ class UniversalDetector(object):
if not self._esc_charset_prober:
self._esc_charset_prober = EscCharSetProber(self.lang_filter)
if self._esc_charset_prober.feed(byte_str) == ProbingState.FOUND_IT:
self.result = {'encoding':
self._esc_charset_prober.charset_name,
'confidence':
self._esc_charset_prober.get_confidence(),
'language':
self._esc_charset_prober.language}
self.result = {
"encoding": self._esc_charset_prober.charset_name,
"confidence": self._esc_charset_prober.get_confidence(),
"language": self._esc_charset_prober.language,
}
self.done = True
# If we've seen high bytes (i.e., those with values greater than 127),
# we need to do more complicated checks using all our multi-byte and
@@ -207,17 +269,20 @@ class UniversalDetector(object):
if self.lang_filter & LanguageFilter.NON_CJK:
self._charset_probers.append(SBCSGroupProber())
self._charset_probers.append(Latin1Prober())
self._charset_probers.append(MacRomanProber())
for prober in self._charset_probers:
if prober.feed(byte_str) == ProbingState.FOUND_IT:
self.result = {'encoding': prober.charset_name,
'confidence': prober.get_confidence(),
'language': prober.language}
self.result = {
"encoding": prober.charset_name,
"confidence": prober.get_confidence(),
"language": prober.language,
}
self.done = True
break
if self.WIN_BYTE_DETECTOR.search(byte_str):
self._has_win_bytes = True
def close(self):
def close(self) -> ResultDict:
"""
Stop analyzing the current document and come up with a final
prediction.
@@ -231,13 +296,11 @@ class UniversalDetector(object):
self.done = True
if not self._got_data:
self.logger.debug('no data received!')
self.logger.debug("no data received!")
# Default to ASCII if it is all we've seen so far
elif self._input_state == InputState.PURE_ASCII:
self.result = {'encoding': 'ascii',
'confidence': 1.0,
'language': ''}
self.result = {"encoding": "ascii", "confidence": 1.0, "language": ""}
# If we have seen non-ASCII, return the best that met MINIMUM_THRESHOLD
elif self._input_state == InputState.HIGH_BYTE:
@@ -253,34 +316,47 @@ class UniversalDetector(object):
max_prober = prober
if max_prober and (max_prober_confidence > self.MINIMUM_THRESHOLD):
charset_name = max_prober.charset_name
lower_charset_name = max_prober.charset_name.lower()
assert charset_name is not None
lower_charset_name = charset_name.lower()
confidence = max_prober.get_confidence()
# Use Windows encoding name instead of ISO-8859 if we saw any
# extra Windows-specific bytes
if lower_charset_name.startswith('iso-8859'):
if lower_charset_name.startswith("iso-8859"):
if self._has_win_bytes:
charset_name = self.ISO_WIN_MAP.get(lower_charset_name,
charset_name)
self.result = {'encoding': charset_name,
'confidence': confidence,
'language': max_prober.language}
charset_name = self.ISO_WIN_MAP.get(
lower_charset_name, charset_name
)
# Rename legacy encodings with superset encodings if asked
if self.should_rename_legacy:
charset_name = self.LEGACY_MAP.get(
(charset_name or "").lower(), charset_name
)
self.result = {
"encoding": charset_name,
"confidence": confidence,
"language": max_prober.language,
}
# Log all prober confidences if none met MINIMUM_THRESHOLD
if self.logger.getEffectiveLevel() <= logging.DEBUG:
if self.result['encoding'] is None:
self.logger.debug('no probers hit minimum threshold')
if self.result["encoding"] is None:
self.logger.debug("no probers hit minimum threshold")
for group_prober in self._charset_probers:
if not group_prober:
continue
if isinstance(group_prober, CharSetGroupProber):
for prober in group_prober.probers:
self.logger.debug('%s %s confidence = %s',
prober.charset_name,
prober.language,
prober.get_confidence())
self.logger.debug(
"%s %s confidence = %s",
prober.charset_name,
prober.language,
prober.get_confidence(),
)
else:
self.logger.debug('%s %s confidence = %s',
group_prober.charset_name,
group_prober.language,
group_prober.get_confidence())
self.logger.debug(
"%s %s confidence = %s",
group_prober.charset_name,
group_prober.language,
group_prober.get_confidence(),
)
return self.result

36
venv/Lib/site-packages/pip/_vendor/chardet/utf8prober.py
View File

@@ -25,45 +25,46 @@
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .charsetprober import CharSetProber
from .enums import ProbingState, MachineState
from .codingstatemachine import CodingStateMachine
from .mbcssm import UTF8_SM_MODEL
from typing import Union
from .charsetprober import CharSetProber
from .codingstatemachine import CodingStateMachine
from .enums import MachineState, ProbingState
from .mbcssm import UTF8_SM_MODEL
class UTF8Prober(CharSetProber):
ONE_CHAR_PROB = 0.5
def __init__(self):
super(UTF8Prober, self).__init__()
def __init__(self) -> None:
super().__init__()
self.coding_sm = CodingStateMachine(UTF8_SM_MODEL)
self._num_mb_chars = None
self._num_mb_chars = 0
self.reset()
def reset(self):
super(UTF8Prober, self).reset()
def reset(self) -> None:
super().reset()
self.coding_sm.reset()
self._num_mb_chars = 0
@property
def charset_name(self):
def charset_name(self) -> str:
return "utf-8"
@property
def language(self):
def language(self) -> str:
return ""
def feed(self, byte_str):
def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
for c in byte_str:
coding_state = self.coding_sm.next_state(c)
if coding_state == MachineState.ERROR:
self._state = ProbingState.NOT_ME
break
elif coding_state == MachineState.ITS_ME:
if coding_state == MachineState.ITS_ME:
self._state = ProbingState.FOUND_IT
break
elif coding_state == MachineState.START:
if coding_state == MachineState.START:
if self.coding_sm.get_current_charlen() >= 2:
self._num_mb_chars += 1
@@ -73,10 +74,9 @@ class UTF8Prober(CharSetProber):
return self.state
def get_confidence(self):
def get_confidence(self) -> float:
unlike = 0.99
if self._num_mb_chars < 6:
unlike *= self.ONE_CHAR_PROB ** self._num_mb_chars
unlike *= self.ONE_CHAR_PROB**self._num_mb_chars
return 1.0 - unlike
else:
return unlike
return unlike

6
venv/Lib/site-packages/pip/_vendor/chardet/version.py
View File

@@ -1,9 +1,9 @@
"""
This module exists only to simplify retrieving the version number of chardet
from within setup.py and from chardet subpackages.
from within setuptools and from chardet subpackages.
:author: Dan Blanchard (dan.blanchard@gmail.com)
"""
__version__ = "4.0.0"
VERSION = __version__.split('.')
__version__ = "5.1.0"
VERSION = __version__.split(".")

5
venv/Lib/site-packages/pip/_vendor/colorama/__init__.py
View File

@@ -1,6 +1,7 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
from .initialise import init, deinit, reinit, colorama_text
from .initialise import init, deinit, reinit, colorama_text, just_fix_windows_console
from .ansi import Fore, Back, Style, Cursor
from .ansitowin32 import AnsiToWin32
__version__ = '0.4.4'
__version__ = '0.4.6'

27
venv/Lib/site-packages/pip/_vendor/colorama/ansitowin32.py
View File

@@ -4,7 +4,7 @@ import sys
import os
from .ansi import AnsiFore, AnsiBack, AnsiStyle, Style, BEL
from .winterm import WinTerm, WinColor, WinStyle
from .winterm import enable_vt_processing, WinTerm, WinColor, WinStyle
from .win32 import windll, winapi_test
@@ -37,6 +37,12 @@ class StreamWrapper(object):
def __exit__(self, *args, **kwargs):
return self.__wrapped.__exit__(*args, **kwargs)
def __setstate__(self, state):
self.__dict__ = state
def __getstate__(self):
return self.__dict__
def write(self, text):
self.__convertor.write(text)
@@ -57,7 +63,9 @@ class StreamWrapper(object):
stream = self.__wrapped
try:
return stream.closed
except AttributeError:
# AttributeError in the case that the stream doesn't support being closed
# ValueError for the case that the stream has already been detached when atexit runs
except (AttributeError, ValueError):
return True
@@ -86,15 +94,22 @@ class AnsiToWin32(object):
# (e.g. Cygwin Terminal). In this case it's up to the terminal
# to support the ANSI codes.
conversion_supported = on_windows and winapi_test()
try:
fd = wrapped.fileno()
except Exception:
fd = -1
system_has_native_ansi = not on_windows or enable_vt_processing(fd)
have_tty = not self.stream.closed and self.stream.isatty()
need_conversion = conversion_supported and not system_has_native_ansi
# should we strip ANSI sequences from our output?
if strip is None:
strip = conversion_supported or (not self.stream.closed and not self.stream.isatty())
strip = need_conversion or not have_tty
self.strip = strip
# should we should convert ANSI sequences into win32 calls?
if convert is None:
convert = conversion_supported and not self.stream.closed and self.stream.isatty()
convert = need_conversion and have_tty
self.convert = convert
# dict of ansi codes to win32 functions and parameters
@@ -256,3 +271,7 @@ class AnsiToWin32(object):
if params[0] in '02':
winterm.set_title(params[1])
return text
def flush(self):
self.wrapped.flush()

51
venv/Lib/site-packages/pip/_vendor/colorama/initialise.py
View File

@@ -6,13 +6,27 @@ import sys
from .ansitowin32 import AnsiToWin32
orig_stdout = None
orig_stderr = None
def _wipe_internal_state_for_tests():
global orig_stdout, orig_stderr
orig_stdout = None
orig_stderr = None
wrapped_stdout = None
wrapped_stderr = None
global wrapped_stdout, wrapped_stderr
wrapped_stdout = None
wrapped_stderr = None
atexit_done = False
global atexit_done
atexit_done = False
global fixed_windows_console
fixed_windows_console = False
try:
# no-op if it wasn't registered
atexit.unregister(reset_all)
except AttributeError:
# python 2: no atexit.unregister. Oh well, we did our best.
pass
def reset_all():
@@ -55,6 +69,29 @@ def deinit():
sys.stderr = orig_stderr
def just_fix_windows_console():
global fixed_windows_console
if sys.platform != "win32":
return
if fixed_windows_console:
return
if wrapped_stdout is not None or wrapped_stderr is not None:
# Someone already ran init() and it did stuff, so we won't second-guess them
return
# On newer versions of Windows, AnsiToWin32.__init__ will implicitly enable the
# native ANSI support in the console as a side-effect. We only need to actually
# replace sys.stdout/stderr if we're in the old-style conversion mode.
new_stdout = AnsiToWin32(sys.stdout, convert=None, strip=None, autoreset=False)
if new_stdout.convert:
sys.stdout = new_stdout
new_stderr = AnsiToWin32(sys.stderr, convert=None, strip=None, autoreset=False)
if new_stderr.convert:
sys.stderr = new_stderr
fixed_windows_console = True
@contextlib.contextmanager
def colorama_text(*args, **kwargs):
init(*args, **kwargs)
@@ -78,3 +115,7 @@ def wrap_stream(stream, convert, strip, autoreset, wrap):
if wrapper.should_wrap():
stream = wrapper.stream
return stream
# Use this for initial setup as well, to reduce code duplication
_wipe_internal_state_for_tests()

28
venv/Lib/site-packages/pip/_vendor/colorama/win32.py
View File

@@ -4,6 +4,8 @@
STDOUT = -11
STDERR = -12
ENABLE_VIRTUAL_TERMINAL_PROCESSING = 0x0004
try:
import ctypes
from ctypes import LibraryLoader
@@ -89,6 +91,20 @@ else:
]
_SetConsoleTitleW.restype = wintypes.BOOL
_GetConsoleMode = windll.kernel32.GetConsoleMode
_GetConsoleMode.argtypes = [
wintypes.HANDLE,
POINTER(wintypes.DWORD)
]
_GetConsoleMode.restype = wintypes.BOOL
_SetConsoleMode = windll.kernel32.SetConsoleMode
_SetConsoleMode.argtypes = [
wintypes.HANDLE,
wintypes.DWORD
]
_SetConsoleMode.restype = wintypes.BOOL
def _winapi_test(handle):
csbi = CONSOLE_SCREEN_BUFFER_INFO()
success = _GetConsoleScreenBufferInfo(
@@ -150,3 +166,15 @@ else:
def SetConsoleTitle(title):
return _SetConsoleTitleW(title)
def GetConsoleMode(handle):
mode = wintypes.DWORD()
success = _GetConsoleMode(handle, byref(mode))
if not success:
raise ctypes.WinError()
return mode.value
def SetConsoleMode(handle, mode):
success = _SetConsoleMode(handle, mode)
if not success:
raise ctypes.WinError()

28
venv/Lib/site-packages/pip/_vendor/colorama/winterm.py
View File

@@ -1,7 +1,13 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
from . import win32
try:
from msvcrt import get_osfhandle
except ImportError:
def get_osfhandle(_):
raise OSError("This isn't windows!")
from . import win32
# from wincon.h
class WinColor(object):
BLACK = 0
@@ -167,3 +173,23 @@ class WinTerm(object):
def set_title(self, title):
win32.SetConsoleTitle(title)
def enable_vt_processing(fd):
if win32.windll is None or not win32.winapi_test():
return False
try:
handle = get_osfhandle(fd)
mode = win32.GetConsoleMode(handle)
win32.SetConsoleMode(
handle,
mode | win32.ENABLE_VIRTUAL_TERMINAL_PROCESSING,
)
mode = win32.GetConsoleMode(handle)
if mode & win32.ENABLE_VIRTUAL_TERMINAL_PROCESSING:
return True
# Can get TypeError in testsuite where 'fd' is a Mock()
except (OSError, TypeError):
return False

4
venv/Lib/site-packages/pip/_vendor/distlib/__init__.py
View File

@@ -1,12 +1,12 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2012-2019 Vinay Sajip.
# Copyright (C) 2012-2022 Vinay Sajip.
# Licensed to the Python Software Foundation under a contributor agreement.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
import logging
__version__ = '0.3.2'
__version__ = '0.3.6'
class DistlibException(Exception):
pass

6
venv/Lib/site-packages/pip/_vendor/distlib/_backport/__init__.py
View File

@@ -1,6 +0,0 @@
"""Modules copied from Python 3 standard libraries, for internal use only.
Individual classes and functions are found in d2._backport.misc. Intended
usage is to always import things missing from 3.1 from that module: the
built-in/stdlib objects will be used if found.
"""

41
venv/Lib/site-packages/pip/_vendor/distlib/_backport/misc.py
View File

@@ -1,41 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2012 The Python Software Foundation.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
"""Backports for individual classes and functions."""
import os
import sys
__all__ = ['cache_from_source', 'callable', 'fsencode']
try:
from imp import cache_from_source
except ImportError:
def cache_from_source(py_file, debug=__debug__):
ext = debug and 'c' or 'o'
return py_file + ext
try:
callable = callable
except NameError:
from collections import Callable
def callable(obj):
return isinstance(obj, Callable)
try:
fsencode = os.fsencode
except AttributeError:
def fsencode(filename):
if isinstance(filename, bytes):
return filename
elif isinstance(filename, str):
return filename.encode(sys.getfilesystemencoding())
else:
raise TypeError("expect bytes or str, not %s" %
type(filename).__name__)

764
venv/Lib/site-packages/pip/_vendor/distlib/_backport/shutil.py
View File

@@ -1,764 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2012 The Python Software Foundation.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
"""Utility functions for copying and archiving files and directory trees.
XXX The functions here don't copy the resource fork or other metadata on Mac.
"""
import os
import sys
import stat
from os.path import abspath
import fnmatch
try:
from collections.abc import Callable
except ImportError:
from collections import Callable
import errno
from . import tarfile
try:
import bz2
_BZ2_SUPPORTED = True
except ImportError:
_BZ2_SUPPORTED = False
try:
from pwd import getpwnam
except ImportError:
getpwnam = None
try:
from grp import getgrnam
except ImportError:
getgrnam = None
__all__ = ["copyfileobj", "copyfile", "copymode", "copystat", "copy", "copy2",
"copytree", "move", "rmtree", "Error", "SpecialFileError",
"ExecError", "make_archive", "get_archive_formats",
"register_archive_format", "unregister_archive_format",
"get_unpack_formats", "register_unpack_format",
"unregister_unpack_format", "unpack_archive", "ignore_patterns"]
class Error(EnvironmentError):
pass
class SpecialFileError(EnvironmentError):
"""Raised when trying to do a kind of operation (e.g. copying) which is
not supported on a special file (e.g. a named pipe)"""
class ExecError(EnvironmentError):
"""Raised when a command could not be executed"""
class ReadError(EnvironmentError):
"""Raised when an archive cannot be read"""
class RegistryError(Exception):
"""Raised when a registry operation with the archiving
and unpacking registries fails"""
try:
WindowsError
except NameError:
WindowsError = None
def copyfileobj(fsrc, fdst, length=16*1024):
"""copy data from file-like object fsrc to file-like object fdst"""
while 1:
buf = fsrc.read(length)
if not buf:
break
fdst.write(buf)
def _samefile(src, dst):
# Macintosh, Unix.
if hasattr(os.path, 'samefile'):
try:
return os.path.samefile(src, dst)
except OSError:
return False
# All other platforms: check for same pathname.
return (os.path.normcase(os.path.abspath(src)) ==
os.path.normcase(os.path.abspath(dst)))
def copyfile(src, dst):
"""Copy data from src to dst"""
if _samefile(src, dst):
raise Error("`%s` and `%s` are the same file" % (src, dst))
for fn in [src, dst]:
try:
st = os.stat(fn)
except OSError:
# File most likely does not exist
pass
else:
# XXX What about other special files? (sockets, devices...)
if stat.S_ISFIFO(st.st_mode):
raise SpecialFileError("`%s` is a named pipe" % fn)
with open(src, 'rb') as fsrc:
with open(dst, 'wb') as fdst:
copyfileobj(fsrc, fdst)
def copymode(src, dst):
"""Copy mode bits from src to dst"""
if hasattr(os, 'chmod'):
st = os.stat(src)
mode = stat.S_IMODE(st.st_mode)
os.chmod(dst, mode)
def copystat(src, dst):
"""Copy all stat info (mode bits, atime, mtime, flags) from src to dst"""
st = os.stat(src)
mode = stat.S_IMODE(st.st_mode)
if hasattr(os, 'utime'):
os.utime(dst, (st.st_atime, st.st_mtime))
if hasattr(os, 'chmod'):
os.chmod(dst, mode)
if hasattr(os, 'chflags') and hasattr(st, 'st_flags'):
try:
os.chflags(dst, st.st_flags)
except OSError as why:
if (not hasattr(errno, 'EOPNOTSUPP') or
why.errno != errno.EOPNOTSUPP):
raise
def copy(src, dst):
"""Copy data and mode bits ("cp src dst").
The destination may be a directory.
"""
if os.path.isdir(dst):
dst = os.path.join(dst, os.path.basename(src))
copyfile(src, dst)
copymode(src, dst)
def copy2(src, dst):
"""Copy data and all stat info ("cp -p src dst").
The destination may be a directory.
"""
if os.path.isdir(dst):
dst = os.path.join(dst, os.path.basename(src))
copyfile(src, dst)
copystat(src, dst)
def ignore_patterns(*patterns):
"""Function that can be used as copytree() ignore parameter.
Patterns is a sequence of glob-style patterns
that are used to exclude files"""
def _ignore_patterns(path, names):
ignored_names = []
for pattern in patterns:
ignored_names.extend(fnmatch.filter(names, pattern))
return set(ignored_names)
return _ignore_patterns
def copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2,
ignore_dangling_symlinks=False):
"""Recursively copy a directory tree.
The destination directory must not already exist.
If exception(s) occur, an Error is raised with a list of reasons.
If the optional symlinks flag is true, symbolic links in the
source tree result in symbolic links in the destination tree; if
it is false, the contents of the files pointed to by symbolic
links are copied. If the file pointed by the symlink doesn't
exist, an exception will be added in the list of errors raised in
an Error exception at the end of the copy process.
You can set the optional ignore_dangling_symlinks flag to true if you
want to silence this exception. Notice that this has no effect on
platforms that don't support os.symlink.
The optional ignore argument is a callable. If given, it
is called with the `src` parameter, which is the directory
being visited by copytree(), and `names` which is the list of
`src` contents, as returned by os.listdir():
callable(src, names) -> ignored_names
Since copytree() is called recursively, the callable will be
called once for each directory that is copied. It returns a
list of names relative to the `src` directory that should
not be copied.
The optional copy_function argument is a callable that will be used
to copy each file. It will be called with the source path and the
destination path as arguments. By default, copy2() is used, but any
function that supports the same signature (like copy()) can be used.
"""
names = os.listdir(src)
if ignore is not None:
ignored_names = ignore(src, names)
else:
ignored_names = set()
os.makedirs(dst)
errors = []
for name in names:
if name in ignored_names:
continue
srcname = os.path.join(src, name)
dstname = os.path.join(dst, name)
try:
if os.path.islink(srcname):
linkto = os.readlink(srcname)
if symlinks:
os.symlink(linkto, dstname)
else:
# ignore dangling symlink if the flag is on
if not os.path.exists(linkto) and ignore_dangling_symlinks:
continue
# otherwise let the copy occurs. copy2 will raise an error
copy_function(srcname, dstname)
elif os.path.isdir(srcname):
copytree(srcname, dstname, symlinks, ignore, copy_function)
else:
# Will raise a SpecialFileError for unsupported file types
copy_function(srcname, dstname)
# catch the Error from the recursive copytree so that we can
# continue with other files
except Error as err:
errors.extend(err.args[0])
except EnvironmentError as why:
errors.append((srcname, dstname, str(why)))
try:
copystat(src, dst)
except OSError as why:
if WindowsError is not None and isinstance(why, WindowsError):
# Copying file access times may fail on Windows
pass
else:
errors.extend((src, dst, str(why)))
if errors:
raise Error(errors)
def rmtree(path, ignore_errors=False, onerror=None):
"""Recursively delete a directory tree.
If ignore_errors is set, errors are ignored; otherwise, if onerror
is set, it is called to handle the error with arguments (func,
path, exc_info) where func is os.listdir, os.remove, or os.rmdir;
path is the argument to that function that caused it to fail; and
exc_info is a tuple returned by sys.exc_info(). If ignore_errors
is false and onerror is None, an exception is raised.
"""
if ignore_errors:
def onerror(*args):
pass
elif onerror is None:
def onerror(*args):
raise
try:
if os.path.islink(path):
# symlinks to directories are forbidden, see bug #1669
raise OSError("Cannot call rmtree on a symbolic link")
except OSError:
onerror(os.path.islink, path, sys.exc_info())
# can't continue even if onerror hook returns
return
names = []
try:
names = os.listdir(path)
except os.error:
onerror(os.listdir, path, sys.exc_info())
for name in names:
fullname = os.path.join(path, name)
try:
mode = os.lstat(fullname).st_mode
except os.error:
mode = 0
if stat.S_ISDIR(mode):
rmtree(fullname, ignore_errors, onerror)
else:
try:
os.remove(fullname)
except os.error:
onerror(os.remove, fullname, sys.exc_info())
try:
os.rmdir(path)
except os.error:
onerror(os.rmdir, path, sys.exc_info())
def _basename(path):
# A basename() variant which first strips the trailing slash, if present.
# Thus we always get the last component of the path, even for directories.
return os.path.basename(path.rstrip(os.path.sep))
def move(src, dst):
"""Recursively move a file or directory to another location. This is
similar to the Unix "mv" command.
If the destination is a directory or a symlink to a directory, the source
is moved inside the directory. The destination path must not already
exist.
If the destination already exists but is not a directory, it may be
overwritten depending on os.rename() semantics.
If the destination is on our current filesystem, then rename() is used.
Otherwise, src is copied to the destination and then removed.
A lot more could be done here... A look at a mv.c shows a lot of
the issues this implementation glosses over.
"""
real_dst = dst
if os.path.isdir(dst):
if _samefile(src, dst):
# We might be on a case insensitive filesystem,
# perform the rename anyway.
os.rename(src, dst)
return
real_dst = os.path.join(dst, _basename(src))
if os.path.exists(real_dst):
raise Error("Destination path '%s' already exists" % real_dst)
try:
os.rename(src, real_dst)
except OSError:
if os.path.isdir(src):
if _destinsrc(src, dst):
raise Error("Cannot move a directory '%s' into itself '%s'." % (src, dst))
copytree(src, real_dst, symlinks=True)
rmtree(src)
else:
copy2(src, real_dst)
os.unlink(src)
def _destinsrc(src, dst):
src = abspath(src)
dst = abspath(dst)
if not src.endswith(os.path.sep):
src += os.path.sep
if not dst.endswith(os.path.sep):
dst += os.path.sep
return dst.startswith(src)
def _get_gid(name):
"""Returns a gid, given a group name."""
if getgrnam is None or name is None:
return None
try:
result = getgrnam(name)
except KeyError:
result = None
if result is not None:
return result[2]
return None
def _get_uid(name):
"""Returns an uid, given a user name."""
if getpwnam is None or name is None:
return None
try:
result = getpwnam(name)
except KeyError:
result = None
if result is not None:
return result[2]
return None
def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0,
owner=None, group=None, logger=None):
"""Create a (possibly compressed) tar file from all the files under
'base_dir'.
'compress' must be "gzip" (the default), "bzip2", or None.
'owner' and 'group' can be used to define an owner and a group for the
archive that is being built. If not provided, the current owner and group
will be used.
The output tar file will be named 'base_name' + ".tar", possibly plus
the appropriate compression extension (".gz", or ".bz2").
Returns the output filename.
"""
tar_compression = {'gzip': 'gz', None: ''}
compress_ext = {'gzip': '.gz'}
if _BZ2_SUPPORTED:
tar_compression['bzip2'] = 'bz2'
compress_ext['bzip2'] = '.bz2'
# flags for compression program, each element of list will be an argument
if compress is not None and compress not in compress_ext:
raise ValueError("bad value for 'compress', or compression format not "
"supported : {0}".format(compress))
archive_name = base_name + '.tar' + compress_ext.get(compress, '')
archive_dir = os.path.dirname(archive_name)
if not os.path.exists(archive_dir):
if logger is not None:
logger.info("creating %s", archive_dir)
if not dry_run:
os.makedirs(archive_dir)
# creating the tarball
if logger is not None:
logger.info('Creating tar archive')
uid = _get_uid(owner)
gid = _get_gid(group)
def _set_uid_gid(tarinfo):
if gid is not None:
tarinfo.gid = gid
tarinfo.gname = group
if uid is not None:
tarinfo.uid = uid
tarinfo.uname = owner
return tarinfo
if not dry_run:
tar = tarfile.open(archive_name, 'w|%s' % tar_compression[compress])
try:
tar.add(base_dir, filter=_set_uid_gid)
finally:
tar.close()
return archive_name
def _call_external_zip(base_dir, zip_filename, verbose=False, dry_run=False):
# XXX see if we want to keep an external call here
if verbose:
zipoptions = "-r"
else:
zipoptions = "-rq"
from distutils.errors import DistutilsExecError
from distutils.spawn import spawn
try:
spawn(["zip", zipoptions, zip_filename, base_dir], dry_run=dry_run)
except DistutilsExecError:
# XXX really should distinguish between "couldn't find
# external 'zip' command" and "zip failed".
raise ExecError("unable to create zip file '%s': "
"could neither import the 'zipfile' module nor "
"find a standalone zip utility") % zip_filename
def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None):
"""Create a zip file from all the files under 'base_dir'.
The output zip file will be named 'base_name' + ".zip". Uses either the
"zipfile" Python module (if available) or the InfoZIP "zip" utility
(if installed and found on the default search path). If neither tool is
available, raises ExecError. Returns the name of the output zip
file.
"""
zip_filename = base_name + ".zip"
archive_dir = os.path.dirname(base_name)
if not os.path.exists(archive_dir):
if logger is not None:
logger.info("creating %s", archive_dir)
if not dry_run:
os.makedirs(archive_dir)
# If zipfile module is not available, try spawning an external 'zip'
# command.
try:
import zipfile
except ImportError:
zipfile = None
if zipfile is None:
_call_external_zip(base_dir, zip_filename, verbose, dry_run)
else:
if logger is not None:
logger.info("creating '%s' and adding '%s' to it",
zip_filename, base_dir)
if not dry_run:
zip = zipfile.ZipFile(zip_filename, "w",
compression=zipfile.ZIP_DEFLATED)
for dirpath, dirnames, filenames in os.walk(base_dir):
for name in filenames:
path = os.path.normpath(os.path.join(dirpath, name))
if os.path.isfile(path):
zip.write(path, path)
if logger is not None:
logger.info("adding '%s'", path)
zip.close()
return zip_filename
_ARCHIVE_FORMATS = {
'gztar': (_make_tarball, [('compress', 'gzip')], "gzip'ed tar-file"),
'bztar': (_make_tarball, [('compress', 'bzip2')], "bzip2'ed tar-file"),
'tar': (_make_tarball, [('compress', None)], "uncompressed tar file"),
'zip': (_make_zipfile, [], "ZIP file"),
}
if _BZ2_SUPPORTED:
_ARCHIVE_FORMATS['bztar'] = (_make_tarball, [('compress', 'bzip2')],
"bzip2'ed tar-file")
def get_archive_formats():
"""Returns a list of supported formats for archiving and unarchiving.
Each element of the returned sequence is a tuple (name, description)
"""
formats = [(name, registry[2]) for name, registry in
_ARCHIVE_FORMATS.items()]
formats.sort()
return formats
def register_archive_format(name, function, extra_args=None, description=''):
"""Registers an archive format.
name is the name of the format. function is the callable that will be
used to create archives. If provided, extra_args is a sequence of
(name, value) tuples that will be passed as arguments to the callable.
description can be provided to describe the format, and will be returned
by the get_archive_formats() function.
"""
if extra_args is None:
extra_args = []
if not isinstance(function, Callable):
raise TypeError('The %s object is not callable' % function)
if not isinstance(extra_args, (tuple, list)):
raise TypeError('extra_args needs to be a sequence')
for element in extra_args:
if not isinstance(element, (tuple, list)) or len(element) !=2:
raise TypeError('extra_args elements are : (arg_name, value)')
_ARCHIVE_FORMATS[name] = (function, extra_args, description)
def unregister_archive_format(name):
del _ARCHIVE_FORMATS[name]
def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
dry_run=0, owner=None, group=None, logger=None):
"""Create an archive file (eg. zip or tar).
'base_name' is the name of the file to create, minus any format-specific
extension; 'format' is the archive format: one of "zip", "tar", "bztar"
or "gztar".
'root_dir' is a directory that will be the root directory of the
archive; ie. we typically chdir into 'root_dir' before creating the
archive. 'base_dir' is the directory where we start archiving from;
ie. 'base_dir' will be the common prefix of all files and
directories in the archive. 'root_dir' and 'base_dir' both default
to the current directory. Returns the name of the archive file.
'owner' and 'group' are used when creating a tar archive. By default,
uses the current owner and group.
"""
save_cwd = os.getcwd()
if root_dir is not None:
if logger is not None:
logger.debug("changing into '%s'", root_dir)
base_name = os.path.abspath(base_name)
if not dry_run:
os.chdir(root_dir)
if base_dir is None:
base_dir = os.curdir
kwargs = {'dry_run': dry_run, 'logger': logger}
try:
format_info = _ARCHIVE_FORMATS[format]
except KeyError:
raise ValueError("unknown archive format '%s'" % format)
func = format_info[0]
for arg, val in format_info[1]:
kwargs[arg] = val
if format != 'zip':
kwargs['owner'] = owner
kwargs['group'] = group
try:
filename = func(base_name, base_dir, **kwargs)
finally:
if root_dir is not None:
if logger is not None:
logger.debug("changing back to '%s'", save_cwd)
os.chdir(save_cwd)
return filename
def get_unpack_formats():
"""Returns a list of supported formats for unpacking.
Each element of the returned sequence is a tuple
(name, extensions, description)
"""
formats = [(name, info[0], info[3]) for name, info in
_UNPACK_FORMATS.items()]
formats.sort()
return formats
def _check_unpack_options(extensions, function, extra_args):
"""Checks what gets registered as an unpacker."""
# first make sure no other unpacker is registered for this extension
existing_extensions = {}
for name, info in _UNPACK_FORMATS.items():
for ext in info[0]:
existing_extensions[ext] = name
for extension in extensions:
if extension in existing_extensions:
msg = '%s is already registered for "%s"'
raise RegistryError(msg % (extension,
existing_extensions[extension]))
if not isinstance(function, Callable):
raise TypeError('The registered function must be a callable')
def register_unpack_format(name, extensions, function, extra_args=None,
description=''):
"""Registers an unpack format.
`name` is the name of the format. `extensions` is a list of extensions
corresponding to the format.
`function` is the callable that will be
used to unpack archives. The callable will receive archives to unpack.
If it's unable to handle an archive, it needs to raise a ReadError
exception.
If provided, `extra_args` is a sequence of
(name, value) tuples that will be passed as arguments to the callable.
description can be provided to describe the format, and will be returned
by the get_unpack_formats() function.
"""
if extra_args is None:
extra_args = []
_check_unpack_options(extensions, function, extra_args)
_UNPACK_FORMATS[name] = extensions, function, extra_args, description
def unregister_unpack_format(name):
"""Removes the pack format from the registry."""
del _UNPACK_FORMATS[name]
def _ensure_directory(path):
"""Ensure that the parent directory of `path` exists"""
dirname = os.path.dirname(path)
if not os.path.isdir(dirname):
os.makedirs(dirname)
def _unpack_zipfile(filename, extract_dir):
"""Unpack zip `filename` to `extract_dir`
"""
try:
import zipfile
except ImportError:
raise ReadError('zlib not supported, cannot unpack this archive.')
if not zipfile.is_zipfile(filename):
raise ReadError("%s is not a zip file" % filename)
zip = zipfile.ZipFile(filename)
try:
for info in zip.infolist():
name = info.filename
# don't extract absolute paths or ones with .. in them
if name.startswith('/') or '..' in name:
continue
target = os.path.join(extract_dir, *name.split('/'))
if not target:
continue
_ensure_directory(target)
if not name.endswith('/'):
# file
data = zip.read(info.filename)
f = open(target, 'wb')
try:
f.write(data)
finally:
f.close()
del data
finally:
zip.close()
def _unpack_tarfile(filename, extract_dir):
"""Unpack tar/tar.gz/tar.bz2 `filename` to `extract_dir`
"""
try:
tarobj = tarfile.open(filename)
except tarfile.TarError:
raise ReadError(
"%s is not a compressed or uncompressed tar file" % filename)
try:
tarobj.extractall(extract_dir)
finally:
tarobj.close()
_UNPACK_FORMATS = {
'gztar': (['.tar.gz', '.tgz'], _unpack_tarfile, [], "gzip'ed tar-file"),
'tar': (['.tar'], _unpack_tarfile, [], "uncompressed tar file"),
'zip': (['.zip'], _unpack_zipfile, [], "ZIP file")
}
if _BZ2_SUPPORTED:
_UNPACK_FORMATS['bztar'] = (['.bz2'], _unpack_tarfile, [],
"bzip2'ed tar-file")
def _find_unpack_format(filename):
for name, info in _UNPACK_FORMATS.items():
for extension in info[0]:
if filename.endswith(extension):
return name
return None
def unpack_archive(filename, extract_dir=None, format=None):
"""Unpack an archive.
`filename` is the name of the archive.
`extract_dir` is the name of the target directory, where the archive
is unpacked. If not provided, the current working directory is used.
`format` is the archive format: one of "zip", "tar", or "gztar". Or any
other registered format. If not provided, unpack_archive will use the
filename extension and see if an unpacker was registered for that
extension.
In case none is found, a ValueError is raised.
"""
if extract_dir is None:
extract_dir = os.getcwd()
if format is not None:
try:
format_info = _UNPACK_FORMATS[format]
except KeyError:
raise ValueError("Unknown unpack format '{0}'".format(format))
func = format_info[1]
func(filename, extract_dir, **dict(format_info[2]))
else:
# we need to look at the registered unpackers supported extensions
format = _find_unpack_format(filename)
if format is None:
raise ReadError("Unknown archive format '{0}'".format(filename))
func = _UNPACK_FORMATS[format][1]
kwargs = dict(_UNPACK_FORMATS[format][2])
func(filename, extract_dir, **kwargs)

84
venv/Lib/site-packages/pip/_vendor/distlib/_backport/sysconfig.cfg
View File

@@ -1,84 +0,0 @@
[posix_prefix]
# Configuration directories. Some of these come straight out of the
# configure script. They are for implementing the other variables, not to
# be used directly in [resource_locations].
confdir = /etc
datadir = /usr/share
libdir = /usr/lib
statedir = /var
# User resource directory
local = ~/.local/{distribution.name}
stdlib = {base}/lib/python{py_version_short}
platstdlib = {platbase}/lib/python{py_version_short}
purelib = {base}/lib/python{py_version_short}/site-packages
platlib = {platbase}/lib/python{py_version_short}/site-packages
include = {base}/include/python{py_version_short}{abiflags}
platinclude = {platbase}/include/python{py_version_short}{abiflags}
data = {base}
[posix_home]
stdlib = {base}/lib/python
platstdlib = {base}/lib/python
purelib = {base}/lib/python
platlib = {base}/lib/python
include = {base}/include/python
platinclude = {base}/include/python
scripts = {base}/bin
data = {base}
[nt]
stdlib = {base}/Lib
platstdlib = {base}/Lib
purelib = {base}/Lib/site-packages
platlib = {base}/Lib/site-packages
include = {base}/Include
platinclude = {base}/Include
scripts = {base}/Scripts
data = {base}
[os2]
stdlib = {base}/Lib
platstdlib = {base}/Lib
purelib = {base}/Lib/site-packages
platlib = {base}/Lib/site-packages
include = {base}/Include
platinclude = {base}/Include
scripts = {base}/Scripts
data = {base}
[os2_home]
stdlib = {userbase}/lib/python{py_version_short}
platstdlib = {userbase}/lib/python{py_version_short}
purelib = {userbase}/lib/python{py_version_short}/site-packages
platlib = {userbase}/lib/python{py_version_short}/site-packages
include = {userbase}/include/python{py_version_short}
scripts = {userbase}/bin
data = {userbase}
[nt_user]
stdlib = {userbase}/Python{py_version_nodot}
platstdlib = {userbase}/Python{py_version_nodot}
purelib = {userbase}/Python{py_version_nodot}/site-packages
platlib = {userbase}/Python{py_version_nodot}/site-packages
include = {userbase}/Python{py_version_nodot}/Include
scripts = {userbase}/Scripts
data = {userbase}
[posix_user]
stdlib = {userbase}/lib/python{py_version_short}
platstdlib = {userbase}/lib/python{py_version_short}
purelib = {userbase}/lib/python{py_version_short}/site-packages
platlib = {userbase}/lib/python{py_version_short}/site-packages
include = {userbase}/include/python{py_version_short}
scripts = {userbase}/bin
data = {userbase}
[osx_framework_user]
stdlib = {userbase}/lib/python
platstdlib = {userbase}/lib/python
purelib = {userbase}/lib/python/site-packages
platlib = {userbase}/lib/python/site-packages
include = {userbase}/include
scripts = {userbase}/bin
data = {userbase}

786
venv/Lib/site-packages/pip/_vendor/distlib/_backport/sysconfig.py
View File

@@ -1,786 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2012 The Python Software Foundation.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
"""Access to Python's configuration information."""
import codecs
import os
import re
import sys
from os.path import pardir, realpath
try:
import configparser
except ImportError:
import ConfigParser as configparser
__all__ = [
'get_config_h_filename',
'get_config_var',
'get_config_vars',
'get_makefile_filename',
'get_path',
'get_path_names',
'get_paths',
'get_platform',
'get_python_version',
'get_scheme_names',
'parse_config_h',
]
def _safe_realpath(path):
try:
return realpath(path)
except OSError:
return path
if sys.executable:
_PROJECT_BASE = os.path.dirname(_safe_realpath(sys.executable))
else:
# sys.executable can be empty if argv[0] has been changed and Python is
# unable to retrieve the real program name
_PROJECT_BASE = _safe_realpath(os.getcwd())
if os.name == "nt" and "pcbuild" in _PROJECT_BASE[-8:].lower():
_PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir))
# PC/VS7.1
if os.name == "nt" and "\\pc\\v" in _PROJECT_BASE[-10:].lower():
_PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir))
# PC/AMD64
if os.name == "nt" and "\\pcbuild\\amd64" in _PROJECT_BASE[-14:].lower():
_PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir))
def is_python_build():
for fn in ("Setup.dist", "Setup.local"):
if os.path.isfile(os.path.join(_PROJECT_BASE, "Modules", fn)):
return True
return False
_PYTHON_BUILD = is_python_build()
_cfg_read = False
def _ensure_cfg_read():
global _cfg_read
if not _cfg_read:
from ..resources import finder
backport_package = __name__.rsplit('.', 1)[0]
_finder = finder(backport_package)
_cfgfile = _finder.find('sysconfig.cfg')
assert _cfgfile, 'sysconfig.cfg exists'
with _cfgfile.as_stream() as s:
_SCHEMES.readfp(s)
if _PYTHON_BUILD:
for scheme in ('posix_prefix', 'posix_home'):
_SCHEMES.set(scheme, 'include', '{srcdir}/Include')
_SCHEMES.set(scheme, 'platinclude', '{projectbase}/.')
_cfg_read = True
_SCHEMES = configparser.RawConfigParser()
_VAR_REPL = re.compile(r'\{([^{]*?)\}')
def _expand_globals(config):
_ensure_cfg_read()
if config.has_section('globals'):
globals = config.items('globals')
else:
globals = tuple()
sections = config.sections()
for section in sections:
if section == 'globals':
continue
for option, value in globals:
if config.has_option(section, option):
continue
config.set(section, option, value)
config.remove_section('globals')
# now expanding local variables defined in the cfg file
#
for section in config.sections():
variables = dict(config.items(section))
def _replacer(matchobj):
name = matchobj.group(1)
if name in variables:
return variables[name]
return matchobj.group(0)
for option, value in config.items(section):
config.set(section, option, _VAR_REPL.sub(_replacer, value))
#_expand_globals(_SCHEMES)
_PY_VERSION = '%s.%s.%s' % sys.version_info[:3]
_PY_VERSION_SHORT = '%s.%s' % sys.version_info[:2]
_PY_VERSION_SHORT_NO_DOT = '%s%s' % sys.version_info[:2]
_PREFIX = os.path.normpath(sys.prefix)
_EXEC_PREFIX = os.path.normpath(sys.exec_prefix)
_CONFIG_VARS = None
_USER_BASE = None
def _subst_vars(path, local_vars):
"""In the string `path`, replace tokens like {some.thing} with the
corresponding value from the map `local_vars`.
If there is no corresponding value, leave the token unchanged.
"""
def _replacer(matchobj):
name = matchobj.group(1)
if name in local_vars:
return local_vars[name]
elif name in os.environ:
return os.environ[name]
return matchobj.group(0)
return _VAR_REPL.sub(_replacer, path)
def _extend_dict(target_dict, other_dict):
target_keys = target_dict.keys()
for key, value in other_dict.items():
if key in target_keys:
continue
target_dict[key] = value
def _expand_vars(scheme, vars):
res = {}
if vars is None:
vars = {}
_extend_dict(vars, get_config_vars())
for key, value in _SCHEMES.items(scheme):
if os.name in ('posix', 'nt'):
value = os.path.expanduser(value)
res[key] = os.path.normpath(_subst_vars(value, vars))
return res
def format_value(value, vars):
def _replacer(matchobj):
name = matchobj.group(1)
if name in vars:
return vars[name]
return matchobj.group(0)
return _VAR_REPL.sub(_replacer, value)
def _get_default_scheme():
if os.name == 'posix':
# the default scheme for posix is posix_prefix
return 'posix_prefix'
return os.name
def _getuserbase():
env_base = os.environ.get("PYTHONUSERBASE", None)
def joinuser(*args):
return os.path.expanduser(os.path.join(*args))
# what about 'os2emx', 'riscos' ?
if os.name == "nt":
base = os.environ.get("APPDATA") or "~"
if env_base:
return env_base
else:
return joinuser(base, "Python")
if sys.platform == "darwin":
framework = get_config_var("PYTHONFRAMEWORK")
if framework:
if env_base:
return env_base
else:
return joinuser("~", "Library", framework, "%d.%d" %
sys.version_info[:2])
if env_base:
return env_base
else:
return joinuser("~", ".local")
def _parse_makefile(filename, vars=None):
"""Parse a Makefile-style file.
A dictionary containing name/value pairs is returned. If an
optional dictionary is passed in as the second argument, it is
used instead of a new dictionary.
"""
# Regexes needed for parsing Makefile (and similar syntaxes,
# like old-style Setup files).
_variable_rx = re.compile(r"([a-zA-Z][a-zA-Z0-9_]+)\s*=\s*(.*)")
_findvar1_rx = re.compile(r"\$\(([A-Za-z][A-Za-z0-9_]*)\)")
_findvar2_rx = re.compile(r"\${([A-Za-z][A-Za-z0-9_]*)}")
if vars is None:
vars = {}
done = {}
notdone = {}
with codecs.open(filename, encoding='utf-8', errors="surrogateescape") as f:
lines = f.readlines()
for line in lines:
if line.startswith('#') or line.strip() == '':
continue
m = _variable_rx.match(line)
if m:
n, v = m.group(1, 2)
v = v.strip()
# `$$' is a literal `$' in make
tmpv = v.replace('$$', '')
if "$" in tmpv:
notdone[n] = v
else:
try:
v = int(v)
except ValueError:
# insert literal `$'
done[n] = v.replace('$$', '$')
else:
done[n] = v
# do variable interpolation here
variables = list(notdone.keys())
# Variables with a 'PY_' prefix in the makefile. These need to
# be made available without that prefix through sysconfig.
# Special care is needed to ensure that variable expansion works, even
# if the expansion uses the name without a prefix.
renamed_variables = ('CFLAGS', 'LDFLAGS', 'CPPFLAGS')
while len(variables) > 0:
for name in tuple(variables):
value = notdone[name]
m = _findvar1_rx.search(value) or _findvar2_rx.search(value)
if m is not None:
n = m.group(1)
found = True
if n in done:
item = str(done[n])
elif n in notdone:
# get it on a subsequent round
found = False
elif n in os.environ:
# do it like make: fall back to environment
item = os.environ[n]
elif n in renamed_variables:
if (name.startswith('PY_') and
name[3:] in renamed_variables):
item = ""
elif 'PY_' + n in notdone:
found = False
else:
item = str(done['PY_' + n])
else:
done[n] = item = ""
if found:
after = value[m.end():]
value = value[:m.start()] + item + after
if "$" in after:
notdone[name] = value
else:
try:
value = int(value)
except ValueError:
done[name] = value.strip()
else:
done[name] = value
variables.remove(name)
if (name.startswith('PY_') and
name[3:] in renamed_variables):
name = name[3:]
if name not in done:
done[name] = value
else:
# bogus variable reference (e.g. "prefix=$/opt/python");
# just drop it since we can't deal
done[name] = value
variables.remove(name)
# strip spurious spaces
for k, v in done.items():
if isinstance(v, str):
done[k] = v.strip()
# save the results in the global dictionary
vars.update(done)
return vars
def get_makefile_filename():
"""Return the path of the Makefile."""
if _PYTHON_BUILD:
return os.path.join(_PROJECT_BASE, "Makefile")
if hasattr(sys, 'abiflags'):
config_dir_name = 'config-%s%s' % (_PY_VERSION_SHORT, sys.abiflags)
else:
config_dir_name = 'config'
return os.path.join(get_path('stdlib'), config_dir_name, 'Makefile')
def _init_posix(vars):
"""Initialize the module as appropriate for POSIX systems."""
# load the installed Makefile:
makefile = get_makefile_filename()
try:
_parse_makefile(makefile, vars)
except IOError as e:
msg = "invalid Python installation: unable to open %s" % makefile
if hasattr(e, "strerror"):
msg = msg + " (%s)" % e.strerror
raise IOError(msg)
# load the installed pyconfig.h:
config_h = get_config_h_filename()
try:
with open(config_h) as f:
parse_config_h(f, vars)
except IOError as e:
msg = "invalid Python installation: unable to open %s" % config_h
if hasattr(e, "strerror"):
msg = msg + " (%s)" % e.strerror
raise IOError(msg)
# On AIX, there are wrong paths to the linker scripts in the Makefile
# -- these paths are relative to the Python source, but when installed
# the scripts are in another directory.
if _PYTHON_BUILD:
vars['LDSHARED'] = vars['BLDSHARED']
def _init_non_posix(vars):
"""Initialize the module as appropriate for NT"""
# set basic install directories
vars['LIBDEST'] = get_path('stdlib')
vars['BINLIBDEST'] = get_path('platstdlib')
vars['INCLUDEPY'] = get_path('include')
vars['SO'] = '.pyd'
vars['EXE'] = '.exe'
vars['VERSION'] = _PY_VERSION_SHORT_NO_DOT
vars['BINDIR'] = os.path.dirname(_safe_realpath(sys.executable))
#
# public APIs
#
def parse_config_h(fp, vars=None):
"""Parse a config.h-style file.
A dictionary containing name/value pairs is returned. If an
optional dictionary is passed in as the second argument, it is
used instead of a new dictionary.
"""
if vars is None:
vars = {}
define_rx = re.compile("#define ([A-Z][A-Za-z0-9_]+) (.*)\n")
undef_rx = re.compile("/[*] #undef ([A-Z][A-Za-z0-9_]+) [*]/\n")
while True:
line = fp.readline()
if not line:
break
m = define_rx.match(line)
if m:
n, v = m.group(1, 2)
try:
v = int(v)
except ValueError:
pass
vars[n] = v
else:
m = undef_rx.match(line)
if m:
vars[m.group(1)] = 0
return vars
def get_config_h_filename():
"""Return the path of pyconfig.h."""
if _PYTHON_BUILD:
if os.name == "nt":
inc_dir = os.path.join(_PROJECT_BASE, "PC")
else:
inc_dir = _PROJECT_BASE
else:
inc_dir = get_path('platinclude')
return os.path.join(inc_dir, 'pyconfig.h')
def get_scheme_names():
"""Return a tuple containing the schemes names."""
return tuple(sorted(_SCHEMES.sections()))
def get_path_names():
"""Return a tuple containing the paths names."""
# xxx see if we want a static list
return _SCHEMES.options('posix_prefix')
def get_paths(scheme=_get_default_scheme(), vars=None, expand=True):
"""Return a mapping containing an install scheme.
``scheme`` is the install scheme name. If not provided, it will
return the default scheme for the current platform.
"""
_ensure_cfg_read()
if expand:
return _expand_vars(scheme, vars)
else:
return dict(_SCHEMES.items(scheme))
def get_path(name, scheme=_get_default_scheme(), vars=None, expand=True):
"""Return a path corresponding to the scheme.
``scheme`` is the install scheme name.
"""
return get_paths(scheme, vars, expand)[name]
def get_config_vars(*args):
"""With no arguments, return a dictionary of all configuration
variables relevant for the current platform.
On Unix, this means every variable defined in Python's installed Makefile;
On Windows and Mac OS it's a much smaller set.
With arguments, return a list of values that result from looking up
each argument in the configuration variable dictionary.
"""
global _CONFIG_VARS
if _CONFIG_VARS is None:
_CONFIG_VARS = {}
# Normalized versions of prefix and exec_prefix are handy to have;
# in fact, these are the standard versions used most places in the
# distutils2 module.
_CONFIG_VARS['prefix'] = _PREFIX
_CONFIG_VARS['exec_prefix'] = _EXEC_PREFIX
_CONFIG_VARS['py_version'] = _PY_VERSION
_CONFIG_VARS['py_version_short'] = _PY_VERSION_SHORT
_CONFIG_VARS['py_version_nodot'] = _PY_VERSION[0] + _PY_VERSION[2]
_CONFIG_VARS['base'] = _PREFIX
_CONFIG_VARS['platbase'] = _EXEC_PREFIX
_CONFIG_VARS['projectbase'] = _PROJECT_BASE
try:
_CONFIG_VARS['abiflags'] = sys.abiflags
except AttributeError:
# sys.abiflags may not be defined on all platforms.
_CONFIG_VARS['abiflags'] = ''
if os.name in ('nt', 'os2'):
_init_non_posix(_CONFIG_VARS)
if os.name == 'posix':
_init_posix(_CONFIG_VARS)
# Setting 'userbase' is done below the call to the
# init function to enable using 'get_config_var' in
# the init-function.
if sys.version >= '2.6':
_CONFIG_VARS['userbase'] = _getuserbase()
if 'srcdir' not in _CONFIG_VARS:
_CONFIG_VARS['srcdir'] = _PROJECT_BASE
else:
_CONFIG_VARS['srcdir'] = _safe_realpath(_CONFIG_VARS['srcdir'])
# Convert srcdir into an absolute path if it appears necessary.
# Normally it is relative to the build directory. However, during
# testing, for example, we might be running a non-installed python
# from a different directory.
if _PYTHON_BUILD and os.name == "posix":
base = _PROJECT_BASE
try:
cwd = os.getcwd()
except OSError:
cwd = None
if (not os.path.isabs(_CONFIG_VARS['srcdir']) and
base != cwd):
# srcdir is relative and we are not in the same directory
# as the executable. Assume executable is in the build
# directory and make srcdir absolute.
srcdir = os.path.join(base, _CONFIG_VARS['srcdir'])
_CONFIG_VARS['srcdir'] = os.path.normpath(srcdir)
if sys.platform == 'darwin':
kernel_version = os.uname()[2] # Kernel version (8.4.3)
major_version = int(kernel_version.split('.')[0])
if major_version < 8:
# On Mac OS X before 10.4, check if -arch and -isysroot
# are in CFLAGS or LDFLAGS and remove them if they are.
# This is needed when building extensions on a 10.3 system
# using a universal build of python.
for key in ('LDFLAGS', 'BASECFLAGS',
# a number of derived variables. These need to be
# patched up as well.
'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'):
flags = _CONFIG_VARS[key]
flags = re.sub(r'-arch\s+\w+\s', ' ', flags)
flags = re.sub('-isysroot [^ \t]*', ' ', flags)
_CONFIG_VARS[key] = flags
else:
# Allow the user to override the architecture flags using
# an environment variable.
# NOTE: This name was introduced by Apple in OSX 10.5 and
# is used by several scripting languages distributed with
# that OS release.
if 'ARCHFLAGS' in os.environ:
arch = os.environ['ARCHFLAGS']
for key in ('LDFLAGS', 'BASECFLAGS',
# a number of derived variables. These need to be
# patched up as well.
'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'):
flags = _CONFIG_VARS[key]
flags = re.sub(r'-arch\s+\w+\s', ' ', flags)
flags = flags + ' ' + arch
_CONFIG_VARS[key] = flags
# If we're on OSX 10.5 or later and the user tries to
# compiles an extension using an SDK that is not present
# on the current machine it is better to not use an SDK
# than to fail.
#
# The major usecase for this is users using a Python.org
# binary installer on OSX 10.6: that installer uses
# the 10.4u SDK, but that SDK is not installed by default
# when you install Xcode.
#
CFLAGS = _CONFIG_VARS.get('CFLAGS', '')
m = re.search(r'-isysroot\s+(\S+)', CFLAGS)
if m is not None:
sdk = m.group(1)
if not os.path.exists(sdk):
for key in ('LDFLAGS', 'BASECFLAGS',
# a number of derived variables. These need to be
# patched up as well.
'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'):
flags = _CONFIG_VARS[key]
flags = re.sub(r'-isysroot\s+\S+(\s|$)', ' ', flags)
_CONFIG_VARS[key] = flags
if args:
vals = []
for name in args:
vals.append(_CONFIG_VARS.get(name))
return vals
else:
return _CONFIG_VARS
def get_config_var(name):
"""Return the value of a single variable using the dictionary returned by
'get_config_vars()'.
Equivalent to get_config_vars().get(name)
"""
return get_config_vars().get(name)
def get_platform():
"""Return a string that identifies the current platform.
This is used mainly to distinguish platform-specific build directories and
platform-specific built distributions. Typically includes the OS name
and version and the architecture (as supplied by 'os.uname()'),
although the exact information included depends on the OS; eg. for IRIX
the architecture isn't particularly important (IRIX only runs on SGI
hardware), but for Linux the kernel version isn't particularly
important.
Examples of returned values:
linux-i586
linux-alpha (?)
solaris-2.6-sun4u
irix-5.3
irix64-6.2
Windows will return one of:
win-amd64 (64bit Windows on AMD64 (aka x86_64, Intel64, EM64T, etc)
win-ia64 (64bit Windows on Itanium)
win32 (all others - specifically, sys.platform is returned)
For other non-POSIX platforms, currently just returns 'sys.platform'.
"""
if os.name == 'nt':
# sniff sys.version for architecture.
prefix = " bit ("
i = sys.version.find(prefix)
if i == -1:
return sys.platform
j = sys.version.find(")", i)
look = sys.version[i+len(prefix):j].lower()
if look == 'amd64':
return 'win-amd64'
if look == 'itanium':
return 'win-ia64'
return sys.platform
if os.name != "posix" or not hasattr(os, 'uname'):
# XXX what about the architecture? NT is Intel or Alpha,
# Mac OS is M68k or PPC, etc.
return sys.platform
# Try to distinguish various flavours of Unix
osname, host, release, version, machine = os.uname()
# Convert the OS name to lowercase, remove '/' characters
# (to accommodate BSD/OS), and translate spaces (for "Power Macintosh")
osname = osname.lower().replace('/', '')
machine = machine.replace(' ', '_')
machine = machine.replace('/', '-')
if osname[:5] == "linux":
# At least on Linux/Intel, 'machine' is the processor --
# i386, etc.
# XXX what about Alpha, SPARC, etc?
return "%s-%s" % (osname, machine)
elif osname[:5] == "sunos":
if release[0] >= "5": # SunOS 5 == Solaris 2
osname = "solaris"
release = "%d.%s" % (int(release[0]) - 3, release[2:])
# fall through to standard osname-release-machine representation
elif osname[:4] == "irix": # could be "irix64"!
return "%s-%s" % (osname, release)
elif osname[:3] == "aix":
return "%s-%s.%s" % (osname, version, release)
elif osname[:6] == "cygwin":
osname = "cygwin"
rel_re = re.compile(r'[\d.]+')
m = rel_re.match(release)
if m:
release = m.group()
elif osname[:6] == "darwin":
#
# For our purposes, we'll assume that the system version from
# distutils' perspective is what MACOSX_DEPLOYMENT_TARGET is set
# to. This makes the compatibility story a bit more sane because the
# machine is going to compile and link as if it were
# MACOSX_DEPLOYMENT_TARGET.
cfgvars = get_config_vars()
macver = cfgvars.get('MACOSX_DEPLOYMENT_TARGET')
if True:
# Always calculate the release of the running machine,
# needed to determine if we can build fat binaries or not.
macrelease = macver
# Get the system version. Reading this plist is a documented
# way to get the system version (see the documentation for
# the Gestalt Manager)
try:
f = open('/System/Library/CoreServices/SystemVersion.plist')
except IOError:
# We're on a plain darwin box, fall back to the default
# behaviour.
pass
else:
try:
m = re.search(r'<key>ProductUserVisibleVersion</key>\s*'
r'<string>(.*?)</string>', f.read())
finally:
f.close()
if m is not None:
macrelease = '.'.join(m.group(1).split('.')[:2])
# else: fall back to the default behaviour
if not macver:
macver = macrelease
if macver:
release = macver
osname = "macosx"
if ((macrelease + '.') >= '10.4.' and
'-arch' in get_config_vars().get('CFLAGS', '').strip()):
# The universal build will build fat binaries, but not on
# systems before 10.4
#
# Try to detect 4-way universal builds, those have machine-type
# 'universal' instead of 'fat'.
machine = 'fat'
cflags = get_config_vars().get('CFLAGS')
archs = re.findall(r'-arch\s+(\S+)', cflags)
archs = tuple(sorted(set(archs)))
if len(archs) == 1:
machine = archs[0]
elif archs == ('i386', 'ppc'):
machine = 'fat'
elif archs == ('i386', 'x86_64'):
machine = 'intel'
elif archs == ('i386', 'ppc', 'x86_64'):
machine = 'fat3'
elif archs == ('ppc64', 'x86_64'):
machine = 'fat64'
elif archs == ('i386', 'ppc', 'ppc64', 'x86_64'):
machine = 'universal'
else:
raise ValueError(
"Don't know machine value for archs=%r" % (archs,))
elif machine == 'i386':
# On OSX the machine type returned by uname is always the
# 32-bit variant, even if the executable architecture is
# the 64-bit variant
if sys.maxsize >= 2**32:
machine = 'x86_64'
elif machine in ('PowerPC', 'Power_Macintosh'):
# Pick a sane name for the PPC architecture.
# See 'i386' case
if sys.maxsize >= 2**32:
machine = 'ppc64'
else:
machine = 'ppc'
return "%s-%s-%s" % (osname, release, machine)
def get_python_version():
return _PY_VERSION_SHORT
def _print_dict(title, data):
for index, (key, value) in enumerate(sorted(data.items())):
if index == 0:
print('%s: ' % (title))
print('\t%s = "%s"' % (key, value))
def _main():
"""Display all information sysconfig detains."""
print('Platform: "%s"' % get_platform())
print('Python version: "%s"' % get_python_version())
print('Current installation scheme: "%s"' % _get_default_scheme())
print()
_print_dict('Paths', get_paths())
print()
_print_dict('Variables', get_config_vars())
if __name__ == '__main__':
_main()

2607
venv/Lib/site-packages/pip/_vendor/distlib/_backport/tarfile.py
View File

File diff suppressed because it is too large Load Diff

52
venv/Lib/site-packages/pip/_vendor/distlib/compat.py
View File

@@ -22,7 +22,6 @@ if sys.version_info[0] < 3: # pragma: no cover
from types import FileType as file_type
import __builtin__ as builtins
import ConfigParser as configparser
from ._backport import shutil
from urlparse import urlparse, urlunparse, urljoin, urlsplit, urlunsplit
from urllib import (urlretrieve, quote as _quote, unquote, url2pathname,
pathname2url, ContentTooShortError, splittype)
@@ -48,17 +47,18 @@ if sys.version_info[0] < 3: # pragma: no cover
from itertools import ifilter as filter
from itertools import ifilterfalse as filterfalse
_userprog = None
def splituser(host):
"""splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
global _userprog
if _userprog is None:
import re
_userprog = re.compile('^(.*)@(.*)$')
# Leaving this around for now, in case it needs resurrecting in some way
# _userprog = None
# def splituser(host):
# """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
# global _userprog
# if _userprog is None:
# import re
# _userprog = re.compile('^(.*)@(.*)$')
match = _userprog.match(host)
if match: return match.group(1, 2)
return None, host
# match = _userprog.match(host)
# if match: return match.group(1, 2)
# return None, host
else: # pragma: no cover
from io import StringIO
@@ -68,7 +68,7 @@ else: # pragma: no cover
import builtins
import configparser
import shutil
from urllib.parse import (urlparse, urlunparse, urljoin, splituser, quote,
from urllib.parse import (urlparse, urlunparse, urljoin, quote,
unquote, urlsplit, urlunsplit, splittype)
from urllib.request import (urlopen, urlretrieve, Request, url2pathname,
pathname2url,
@@ -88,6 +88,7 @@ else: # pragma: no cover
from itertools import filterfalse
filter = filter
try:
from ssl import match_hostname, CertificateError
except ImportError: # pragma: no cover
@@ -311,10 +312,8 @@ except ImportError: # pragma: no cover
return 'IronPython'
return 'CPython'
try:
import sysconfig
except ImportError: # pragma: no cover
from ._backport import sysconfig
import shutil
import sysconfig
try:
callable = callable
@@ -616,18 +615,15 @@ except ImportError: # pragma: no cover
try:
from importlib.util import cache_from_source # Python >= 3.4
except ImportError: # pragma: no cover
try:
from imp import cache_from_source
except ImportError: # pragma: no cover
def cache_from_source(path, debug_override=None):
assert path.endswith('.py')
if debug_override is None:
debug_override = __debug__
if debug_override:
suffix = 'c'
else:
suffix = 'o'
return path + suffix
def cache_from_source(path, debug_override=None):
assert path.endswith('.py')
if debug_override is None:
debug_override = __debug__
if debug_override:
suffix = 'c'
else:
suffix = 'o'
return path + suffix
try:
from collections import OrderedDict

67
venv/Lib/site-packages/pip/_vendor/distlib/database.py
View File

@@ -132,29 +132,35 @@ class DistributionPath(object):
r = finder.find(entry)
if not r or r.path in seen:
continue
if self._include_dist and entry.endswith(DISTINFO_EXT):
possible_filenames = [METADATA_FILENAME,
WHEEL_METADATA_FILENAME,
LEGACY_METADATA_FILENAME]
for metadata_filename in possible_filenames:
metadata_path = posixpath.join(entry, metadata_filename)
pydist = finder.find(metadata_path)
if pydist:
break
else:
continue
try:
if self._include_dist and entry.endswith(DISTINFO_EXT):
possible_filenames = [METADATA_FILENAME,
WHEEL_METADATA_FILENAME,
LEGACY_METADATA_FILENAME]
for metadata_filename in possible_filenames:
metadata_path = posixpath.join(entry, metadata_filename)
pydist = finder.find(metadata_path)
if pydist:
break
else:
continue
with contextlib.closing(pydist.as_stream()) as stream:
metadata = Metadata(fileobj=stream, scheme='legacy')
logger.debug('Found %s', r.path)
seen.add(r.path)
yield new_dist_class(r.path, metadata=metadata,
env=self)
elif self._include_egg and entry.endswith(('.egg-info',
'.egg')):
logger.debug('Found %s', r.path)
seen.add(r.path)
yield old_dist_class(r.path, self)
with contextlib.closing(pydist.as_stream()) as stream:
metadata = Metadata(fileobj=stream, scheme='legacy')
logger.debug('Found %s', r.path)
seen.add(r.path)
yield new_dist_class(r.path, metadata=metadata,
env=self)
elif self._include_egg and entry.endswith(('.egg-info',
'.egg')):
logger.debug('Found %s', r.path)
seen.add(r.path)
yield old_dist_class(r.path, self)
except Exception as e:
msg = 'Unable to read distribution at %s, perhaps due to bad metadata: %s'
logger.warning(msg, r.path, e)
import warnings
warnings.warn(msg % (r.path, e), stacklevel=2)
def _generate_cache(self):
"""
@@ -379,8 +385,9 @@ class Distribution(object):
def _get_requirements(self, req_attr):
md = self.metadata
logger.debug('Getting requirements from metadata %r', md.todict())
reqts = getattr(md, req_attr)
logger.debug('%s: got requirements %r from metadata: %r', self.name, req_attr,
reqts)
return set(md.get_requirements(reqts, extras=self.extras,
env=self.context))
@@ -1308,22 +1315,26 @@ def get_required_dists(dists, dist):
:param dists: a list of distributions
:param dist: a distribution, member of *dists* for which we are interested
in finding the dependencies.
"""
if dist not in dists:
raise DistlibException('given distribution %r is not a member '
'of the list' % dist.name)
graph = make_graph(dists)
req = [] # required distributions
req = set() # required distributions
todo = graph.adjacency_list[dist] # list of nodes we should inspect
seen = set(t[0] for t in todo) # already added to todo
while todo:
d = todo.pop()[0]
req.append(d)
for pred in graph.adjacency_list[d]:
if pred not in req:
req.add(d)
pred_list = graph.adjacency_list[d]
for pred in pred_list:
d = pred[0]
if d not in req and d not in seen:
seen.add(d)
todo.append(pred)
return req

13
venv/Lib/site-packages/pip/_vendor/distlib/index.py
View File

@@ -12,7 +12,7 @@ import subprocess
import tempfile
try:
from threading import Thread
except ImportError:
except ImportError: # pragma: no cover
from dummy_threading import Thread
from . import DistlibException
@@ -104,7 +104,7 @@ class PackageIndex(object):
pm.add_password(self.realm, netloc, self.username, self.password)
self.password_handler = HTTPBasicAuthHandler(pm)
def register(self, metadata):
def register(self, metadata): # pragma: no cover
"""
Register a distribution on PyPI, using the provided metadata.
@@ -142,8 +142,7 @@ class PackageIndex(object):
logger.debug('%s: %s' % (name, s))
stream.close()
def get_sign_command(self, filename, signer, sign_password,
keystore=None):
def get_sign_command(self, filename, signer, sign_password, keystore=None): # pragma: no cover
"""
Return a suitable command for signing a file.
@@ -206,7 +205,7 @@ class PackageIndex(object):
t2.join()
return p.returncode, stdout, stderr
def sign_file(self, filename, signer, sign_password, keystore=None):
def sign_file(self, filename, signer, sign_password, keystore=None): # pragma: no cover
"""
Sign a file.
@@ -286,7 +285,7 @@ class PackageIndex(object):
request = self.encode_request(d.items(), files)
return self.send_request(request)
def upload_documentation(self, metadata, doc_dir):
def upload_documentation(self, metadata, doc_dir): # pragma: no cover
"""
Upload documentation to the index.
@@ -499,7 +498,7 @@ class PackageIndex(object):
}
return Request(self.url, body, headers)
def search(self, terms, operator=None):
def search(self, terms, operator=None): # pragma: no cover
if isinstance(terms, string_types):
terms = {'name': terms}
rpc_proxy = ServerProxy(self.url, timeout=3.0)

6
venv/Lib/site-packages/pip/_vendor/distlib/locators.py
View File

@@ -633,7 +633,7 @@ class SimpleScrapingLocator(Locator):
self._threads = []
for i in range(self.num_workers):
t = threading.Thread(target=self._fetch)
t.setDaemon(True)
t.daemon = True
t.start()
self._threads.append(t)
@@ -1053,9 +1053,9 @@ class AggregatingLocator(Locator):
# We use a legacy scheme simply because most of the dists on PyPI use legacy
# versions which don't conform to PEP 426 / PEP 440.
# versions which don't conform to PEP 440.
default_locator = AggregatingLocator(
JSONLocator(),
# JSONLocator(), # don't use as PEP 426 is withdrawn
SimpleScrapingLocator('https://pypi.org/simple/',
timeout=3.0),
scheme='legacy')

26
venv/Lib/site-packages/pip/_vendor/distlib/markers.py
View File

@@ -13,19 +13,29 @@ Parser for the environment markers micro-language defined in PEP 508.
# as ~= and === which aren't in Python, necessitating a different approach.
import os
import re
import sys
import platform
from .compat import string_types
from .util import in_venv, parse_marker
from .version import NormalizedVersion as NV
__all__ = ['interpret']
_VERSION_PATTERN = re.compile(r'((\d+(\.\d+)*\w*)|\'(\d+(\.\d+)*\w*)\'|\"(\d+(\.\d+)*\w*)\")')
def _is_literal(o):
if not isinstance(o, string_types) or not o:
return False
return o[0] in '\'"'
def _get_versions(s):
result = []
for m in _VERSION_PATTERN.finditer(s):
result.append(NV(m.groups()[0]))
return set(result)
class Evaluator(object):
"""
This class is used to evaluate marker expessions.
@@ -70,9 +80,18 @@ class Evaluator(object):
lhs = self.evaluate(elhs, context)
rhs = self.evaluate(erhs, context)
if ((elhs == 'python_version' or erhs == 'python_version') and
op in ('<', '<=', '>', '>=', '===', '==', '!=', '~=')):
lhs = NV(lhs)
rhs = NV(rhs)
elif elhs == 'python_version' and op in ('in', 'not in'):
lhs = NV(lhs)
rhs = _get_versions(rhs)
result = self.operations[op](lhs, rhs)
return result
_DIGITS = re.compile(r'\d+\.\d+')
def default_context():
def format_full_version(info):
version = '%s.%s.%s' % (info.major, info.minor, info.micro)
@@ -88,6 +107,9 @@ def default_context():
implementation_version = '0'
implementation_name = ''
ppv = platform.python_version()
m = _DIGITS.match(ppv)
pv = m.group(0)
result = {
'implementation_name': implementation_name,
'implementation_version': implementation_version,
@@ -98,8 +120,8 @@ def default_context():
'platform_system': platform.system(),
'platform_version': platform.version(),
'platform_in_venv': str(in_venv()),
'python_full_version': platform.python_version(),
'python_version': platform.python_version()[:3],
'python_full_version': ppv,
'python_version': pv,
'sys_platform': sys.platform,
}
return result

48
venv/Lib/site-packages/pip/_vendor/distlib/metadata.py
View File

@@ -5,7 +5,7 @@
#
"""Implementation of the Metadata for Python packages PEPs.
Supports all metadata formats (1.0, 1.1, 1.2, 1.3/2.1 and withdrawn 2.0).
Supports all metadata formats (1.0, 1.1, 1.2, 1.3/2.1 and 2.2).
"""
from __future__ import unicode_literals
@@ -100,12 +100,17 @@ _566_FIELDS = _426_FIELDS + ('Description-Content-Type',
_566_MARKERS = ('Description-Content-Type',)
_643_MARKERS = ('Dynamic', 'License-File')
_643_FIELDS = _566_FIELDS + _643_MARKERS
_ALL_FIELDS = set()
_ALL_FIELDS.update(_241_FIELDS)
_ALL_FIELDS.update(_314_FIELDS)
_ALL_FIELDS.update(_345_FIELDS)
_ALL_FIELDS.update(_426_FIELDS)
_ALL_FIELDS.update(_566_FIELDS)
_ALL_FIELDS.update(_643_FIELDS)
EXTRA_RE = re.compile(r'''extra\s*==\s*("([^"]+)"|'([^']+)')''')
@@ -121,7 +126,10 @@ def _version2fieldlist(version):
# avoid adding field names if already there
return _345_FIELDS + tuple(f for f in _566_FIELDS if f not in _345_FIELDS)
elif version == '2.0':
return _426_FIELDS
raise ValueError('Metadata 2.0 is withdrawn and not supported')
# return _426_FIELDS
elif version == '2.2':
return _643_FIELDS
raise MetadataUnrecognizedVersionError(version)
@@ -139,7 +147,7 @@ def _best_version(fields):
continue
keys.append(key)
possible_versions = ['1.0', '1.1', '1.2', '1.3', '2.0', '2.1']
possible_versions = ['1.0', '1.1', '1.2', '1.3', '2.1', '2.2'] # 2.0 removed
# first let's try to see if a field is not part of one of the version
for key in keys:
@@ -159,9 +167,12 @@ def _best_version(fields):
if key != 'Description': # In 2.1, description allowed after headers
possible_versions.remove('2.1')
logger.debug('Removed 2.1 due to %s', key)
if key not in _426_FIELDS and '2.0' in possible_versions:
possible_versions.remove('2.0')
logger.debug('Removed 2.0 due to %s', key)
if key not in _643_FIELDS and '2.2' in possible_versions:
possible_versions.remove('2.2')
logger.debug('Removed 2.2 due to %s', key)
# if key not in _426_FIELDS and '2.0' in possible_versions:
# possible_versions.remove('2.0')
# logger.debug('Removed 2.0 due to %s', key)
# possible_version contains qualified versions
if len(possible_versions) == 1:
@@ -174,16 +185,18 @@ def _best_version(fields):
is_1_1 = '1.1' in possible_versions and _has_marker(keys, _314_MARKERS)
is_1_2 = '1.2' in possible_versions and _has_marker(keys, _345_MARKERS)
is_2_1 = '2.1' in possible_versions and _has_marker(keys, _566_MARKERS)
is_2_0 = '2.0' in possible_versions and _has_marker(keys, _426_MARKERS)
if int(is_1_1) + int(is_1_2) + int(is_2_1) + int(is_2_0) > 1:
raise MetadataConflictError('You used incompatible 1.1/1.2/2.0/2.1 fields')
# is_2_0 = '2.0' in possible_versions and _has_marker(keys, _426_MARKERS)
is_2_2 = '2.2' in possible_versions and _has_marker(keys, _643_MARKERS)
if int(is_1_1) + int(is_1_2) + int(is_2_1) + int(is_2_2) > 1:
raise MetadataConflictError('You used incompatible 1.1/1.2/2.1/2.2 fields')
# we have the choice, 1.0, or 1.2, or 2.0
# we have the choice, 1.0, or 1.2, 2.1 or 2.2
# - 1.0 has a broken Summary field but works with all tools
# - 1.1 is to avoid
# - 1.2 fixes Summary but has little adoption
# - 2.0 adds more features and is very new
if not is_1_1 and not is_1_2 and not is_2_1 and not is_2_0:
# - 2.1 adds more features
# - 2.2 is the latest
if not is_1_1 and not is_1_2 and not is_2_1 and not is_2_2:
# we couldn't find any specific marker
if PKG_INFO_PREFERRED_VERSION in possible_versions:
return PKG_INFO_PREFERRED_VERSION
@@ -193,8 +206,10 @@ def _best_version(fields):
return '1.2'
if is_2_1:
return '2.1'
# if is_2_2:
# return '2.2'
return '2.0'
return '2.2'
# This follows the rules about transforming keys as described in
# https://www.python.org/dev/peps/pep-0566/#id17
@@ -210,7 +225,7 @@ _LISTFIELDS = ('Platform', 'Classifier', 'Obsoletes',
'Requires', 'Provides', 'Obsoletes-Dist',
'Provides-Dist', 'Requires-Dist', 'Requires-External',
'Project-URL', 'Supported-Platform', 'Setup-Requires-Dist',
'Provides-Extra', 'Extension')
'Provides-Extra', 'Extension', 'License-File')
_LISTTUPLEFIELDS = ('Project-URL',)
_ELEMENTSFIELD = ('Keywords',)
@@ -602,7 +617,7 @@ LEGACY_METADATA_FILENAME = 'METADATA'
class Metadata(object):
"""
The metadata of a release. This implementation uses 2.0 (JSON)
The metadata of a release. This implementation uses 2.1
metadata where possible. If not possible, it wraps a LegacyMetadata
instance which handles the key-value metadata format.
"""
@@ -611,6 +626,8 @@ class Metadata(object):
NAME_MATCHER = re.compile('^[0-9A-Z]([0-9A-Z_.-]*[0-9A-Z])?$', re.I)
FIELDNAME_MATCHER = re.compile('^[A-Z]([0-9A-Z-]*[0-9A-Z])?$', re.I)
VERSION_MATCHER = PEP440_VERSION_RE
SUMMARY_MATCHER = re.compile('.{1,2047}')
@@ -638,6 +655,7 @@ class Metadata(object):
'name': (NAME_MATCHER, ('legacy',)),
'version': (VERSION_MATCHER, ('legacy',)),
'summary': (SUMMARY_MATCHER, ('legacy',)),
'dynamic': (FIELDNAME_MATCHER, ('legacy',)),
}
__slots__ = ('_legacy', '_data', 'scheme')

20
venv/Lib/site-packages/pip/_vendor/distlib/scripts.py
View File

@@ -10,11 +10,13 @@ import os
import re
import struct
import sys
import time
from zipfile import ZipInfo
from .compat import sysconfig, detect_encoding, ZipFile
from .resources import finder
from .util import (FileOperator, get_export_entry, convert_path,
get_executable, in_venv)
get_executable, get_platform, in_venv)
logger = logging.getLogger(__name__)
@@ -170,6 +172,11 @@ class ScriptMaker(object):
sysconfig.get_config_var('BINDIR'),
'python%s%s' % (sysconfig.get_config_var('VERSION'),
sysconfig.get_config_var('EXE')))
if not os.path.isfile(executable):
# for Python builds from source on Windows, no Python executables with
# a version suffix are created, so we use python.exe
executable = os.path.join(sysconfig.get_config_var('BINDIR'),
'python%s' % (sysconfig.get_config_var('EXE')))
if options:
executable = self._get_alternate_executable(executable, options)
@@ -244,7 +251,13 @@ class ScriptMaker(object):
launcher = self._get_launcher('w')
stream = BytesIO()
with ZipFile(stream, 'w') as zf:
zf.writestr('__main__.py', script_bytes)
source_date_epoch = os.environ.get('SOURCE_DATE_EPOCH')
if source_date_epoch:
date_time = time.gmtime(int(source_date_epoch))[:6]
zinfo = ZipInfo(filename='__main__.py', date_time=date_time)
zf.writestr(zinfo, script_bytes)
else:
zf.writestr('__main__.py', script_bytes)
zip_data = stream.getvalue()
script_bytes = launcher + shebang + zip_data
for name in names:
@@ -379,7 +392,8 @@ class ScriptMaker(object):
bits = '64'
else:
bits = '32'
name = '%s%s.exe' % (kind, bits)
platform_suffix = '-arm' if get_platform() == 'win-arm64' else ''
name = '%s%s%s.exe' % (kind, bits, platform_suffix)
# Issue 31: don't hardcode an absolute package name, but
# determine it relative to the current package
distlib_package = __name__.rsplit('.', 1)[0]

BIN
venv/Lib/site-packages/pip/_vendor/distlib/t32.exe
View File

Binary file not shown.

BIN
venv/Lib/site-packages/pip/_vendor/distlib/t64.exe
View File

Binary file not shown.

85
venv/Lib/site-packages/pip/_vendor/distlib/util.py
View File

@@ -215,6 +215,10 @@ def parse_requirement(req):
if not ver_remaining or ver_remaining[0] != ',':
break
ver_remaining = ver_remaining[1:].lstrip()
# Some packages have a trailing comma which would break things
# See issue #148
if not ver_remaining:
break
m = COMPARE_OP.match(ver_remaining)
if not m:
raise SyntaxError('invalid constraint: %s' % ver_remaining)
@@ -1428,29 +1432,19 @@ if ssl:
self.sock = sock
self._tunnel()
if not hasattr(ssl, 'SSLContext'):
# For 2.x
if self.ca_certs:
cert_reqs = ssl.CERT_REQUIRED
else:
cert_reqs = ssl.CERT_NONE
self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file,
cert_reqs=cert_reqs,
ssl_version=ssl.PROTOCOL_SSLv23,
ca_certs=self.ca_certs)
else: # pragma: no cover
context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
if hasattr(ssl, 'OP_NO_SSLv2'):
context.options |= ssl.OP_NO_SSLv2
if self.cert_file:
context.load_cert_chain(self.cert_file, self.key_file)
kwargs = {}
if self.ca_certs:
context.verify_mode = ssl.CERT_REQUIRED
context.load_verify_locations(cafile=self.ca_certs)
if getattr(ssl, 'HAS_SNI', False):
kwargs['server_hostname'] = self.host
self.sock = context.wrap_socket(sock, **kwargs)
context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
if hasattr(ssl, 'OP_NO_SSLv2'):
context.options |= ssl.OP_NO_SSLv2
if self.cert_file:
context.load_cert_chain(self.cert_file, self.key_file)
kwargs = {}
if self.ca_certs:
context.verify_mode = ssl.CERT_REQUIRED
context.load_verify_locations(cafile=self.ca_certs)
if getattr(ssl, 'HAS_SNI', False):
kwargs['server_hostname'] = self.host
self.sock = context.wrap_socket(sock, **kwargs)
if self.ca_certs and self.check_domain:
try:
match_hostname(self.sock.getpeercert(), self.host)
@@ -1509,25 +1503,6 @@ if ssl:
#
# XML-RPC with timeouts
#
_ver_info = sys.version_info[:2]
if _ver_info == (2, 6):
class HTTP(httplib.HTTP):
def __init__(self, host='', port=None, **kwargs):
if port == 0: # 0 means use port 0, not the default port
port = None
self._setup(self._connection_class(host, port, **kwargs))
if ssl:
class HTTPS(httplib.HTTPS):
def __init__(self, host='', port=None, **kwargs):
if port == 0: # 0 means use port 0, not the default port
port = None
self._setup(self._connection_class(host, port, **kwargs))
class Transport(xmlrpclib.Transport):
def __init__(self, timeout, use_datetime=0):
self.timeout = timeout
@@ -1535,14 +1510,10 @@ class Transport(xmlrpclib.Transport):
def make_connection(self, host):
h, eh, x509 = self.get_host_info(host)
if _ver_info == (2, 6):
result = HTTP(h, timeout=self.timeout)
else:
if not self._connection or host != self._connection[0]:
self._extra_headers = eh
self._connection = host, httplib.HTTPConnection(h)
result = self._connection[1]
return result
if not self._connection or host != self._connection[0]:
self._extra_headers = eh
self._connection = host, httplib.HTTPConnection(h)
return self._connection[1]
if ssl:
class SafeTransport(xmlrpclib.SafeTransport):
@@ -1555,15 +1526,11 @@ if ssl:
if not kwargs:
kwargs = {}
kwargs['timeout'] = self.timeout
if _ver_info == (2, 6):
result = HTTPS(host, None, **kwargs)
else:
if not self._connection or host != self._connection[0]:
self._extra_headers = eh
self._connection = host, httplib.HTTPSConnection(h, None,
**kwargs)
result = self._connection[1]
return result
if not self._connection or host != self._connection[0]:
self._extra_headers = eh
self._connection = host, httplib.HTTPSConnection(h, None,
**kwargs)
return self._connection[1]
class ServerProxy(xmlrpclib.ServerProxy):

2
venv/Lib/site-packages/pip/_vendor/distlib/version.py
View File

@@ -194,7 +194,7 @@ def _pep_440_key(s):
if not groups[0]:
epoch = 0
else:
epoch = int(groups[0])
epoch = int(groups[0][:-1])
pre = groups[4:6]
post = groups[7:9]
dev = groups[10:12]

BIN
venv/Lib/site-packages/pip/_vendor/distlib/w32.exe
View File

Binary file not shown.

BIN
venv/Lib/site-packages/pip/_vendor/distlib/w64.exe
View File

Binary file not shown.

56
venv/Lib/site-packages/pip/_vendor/distlib/wheel.py
View File

@@ -11,7 +11,6 @@ import codecs
import datetime
from email import message_from_file
import hashlib
import imp
import json
import logging
import os
@@ -47,10 +46,7 @@ else:
VER_SUFFIX = sysconfig.get_config_var('py_version_nodot')
if not VER_SUFFIX: # pragma: no cover
if sys.version_info[1] >= 10:
VER_SUFFIX = '%s_%s' % sys.version_info[:2] # PEP 641 (draft)
else:
VER_SUFFIX = '%s%s' % sys.version_info[:2]
VER_SUFFIX = '%s%s' % sys.version_info[:2]
PYVER = 'py' + VER_SUFFIX
IMPVER = IMP_PREFIX + VER_SUFFIX
@@ -64,10 +60,18 @@ else:
parts = ['cp', VER_SUFFIX]
if sysconfig.get_config_var('Py_DEBUG'):
parts.append('d')
if sysconfig.get_config_var('WITH_PYMALLOC'):
parts.append('m')
if sysconfig.get_config_var('Py_UNICODE_SIZE') == 4:
parts.append('u')
if IMP_PREFIX == 'cp':
vi = sys.version_info[:2]
if vi < (3, 8):
wpm = sysconfig.get_config_var('WITH_PYMALLOC')
if wpm is None:
wpm = True
if wpm:
parts.append('m')
if vi < (3, 3):
us = sysconfig.get_config_var('Py_UNICODE_SIZE')
if us == 4 or (us is None and sys.maxunicode == 0x10FFFF):
parts.append('u')
return ''.join(parts)
ABI = _derive_abi()
del _derive_abi
@@ -98,6 +102,29 @@ if os.sep == '/':
else:
to_posix = lambda o: o.replace(os.sep, '/')
if sys.version_info[0] < 3:
import imp
else:
imp = None
import importlib.machinery
import importlib.util
def _get_suffixes():
if imp:
return [s[0] for s in imp.get_suffixes()]
else:
return importlib.machinery.EXTENSION_SUFFIXES
def _load_dynamic(name, path):
# https://docs.python.org/3/library/importlib.html#importing-a-source-file-directly
if imp:
return imp.load_dynamic(name, path)
else:
spec = importlib.util.spec_from_file_location(name, path)
module = importlib.util.module_from_spec(spec)
sys.modules[name] = module
spec.loader.exec_module(module)
return module
class Mounter(object):
def __init__(self):
@@ -127,7 +154,7 @@ class Mounter(object):
else:
if fullname not in self.libs:
raise ImportError('unable to find extension for %s' % fullname)
result = imp.load_dynamic(fullname, self.libs[fullname])
result = _load_dynamic(fullname, self.libs[fullname])
result.__loader__ = self
parts = fullname.rsplit('.', 1)
if len(parts) > 1:
@@ -304,10 +331,9 @@ class Wheel(object):
result = base64.urlsafe_b64encode(result).rstrip(b'=').decode('ascii')
return hash_kind, result
def write_record(self, records, record_path, base):
def write_record(self, records, record_path, archive_record_path):
records = list(records) # make a copy, as mutated
p = to_posix(os.path.relpath(record_path, base))
records.append((p, '', ''))
records.append((archive_record_path, '', ''))
with CSVWriter(record_path) as writer:
for row in records:
writer.writerow(row)
@@ -324,8 +350,8 @@ class Wheel(object):
records.append((ap, digest, size))
p = os.path.join(distinfo, 'RECORD')
self.write_record(records, p, libdir)
ap = to_posix(os.path.join(info_dir, 'RECORD'))
self.write_record(records, p, ap)
archive_paths.append((ap, p))
def build_zip(self, pathname, archive_paths):
@@ -968,7 +994,7 @@ def compatible_tags():
versions.append(''.join([major, str(minor)]))
abis = []
for suffix, _, _ in imp.get_suffixes():
for suffix in _get_suffixes():
if suffix.startswith('.abi'):
abis.append(suffix.split('.', 2)[1])
abis.sort()

1230
venv/Lib/site-packages/pip/_vendor/distro.py
View File

File diff suppressed because it is too large Load Diff

35
venv/Lib/site-packages/pip/_vendor/html5lib/__init__.py
View File

@@ -1,35 +0,0 @@
"""
HTML parsing library based on the `WHATWG HTML specification
<https://whatwg.org/html>`_. The parser is designed to be compatible with
existing HTML found in the wild and implements well-defined error recovery that
is largely compatible with modern desktop web browsers.
Example usage::
from pip._vendor import html5lib
with open("my_document.html", "rb") as f:
tree = html5lib.parse(f)
For convenience, this module re-exports the following names:
* :func:`~.html5parser.parse`
* :func:`~.html5parser.parseFragment`
* :class:`~.html5parser.HTMLParser`
* :func:`~.treebuilders.getTreeBuilder`
* :func:`~.treewalkers.getTreeWalker`
* :func:`~.serializer.serialize`
"""
from __future__ import absolute_import, division, unicode_literals
from .html5parser import HTMLParser, parse, parseFragment
from .treebuilders import getTreeBuilder
from .treewalkers import getTreeWalker
from .serializer import serialize
__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
"getTreeWalker", "serialize"]
# this has to be at the top level, see how setup.py parses this
#: Distribution version number.
__version__ = "1.1"

289
venv/Lib/site-packages/pip/_vendor/html5lib/_ihatexml.py
View File

@@ -1,289 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
import re
import warnings
from .constants import DataLossWarning
baseChar = """
[#x0041-#x005A] | [#x0061-#x007A] | [#x00C0-#x00D6] | [#x00D8-#x00F6] |
[#x00F8-#x00FF] | [#x0100-#x0131] | [#x0134-#x013E] | [#x0141-#x0148] |
[#x014A-#x017E] | [#x0180-#x01C3] | [#x01CD-#x01F0] | [#x01F4-#x01F5] |
[#x01FA-#x0217] | [#x0250-#x02A8] | [#x02BB-#x02C1] | #x0386 |
[#x0388-#x038A] | #x038C | [#x038E-#x03A1] | [#x03A3-#x03CE] |
[#x03D0-#x03D6] | #x03DA | #x03DC | #x03DE | #x03E0 | [#x03E2-#x03F3] |
[#x0401-#x040C] | [#x040E-#x044F] | [#x0451-#x045C] | [#x045E-#x0481] |
[#x0490-#x04C4] | [#x04C7-#x04C8] | [#x04CB-#x04CC] | [#x04D0-#x04EB] |
[#x04EE-#x04F5] | [#x04F8-#x04F9] | [#x0531-#x0556] | #x0559 |
[#x0561-#x0586] | [#x05D0-#x05EA] | [#x05F0-#x05F2] | [#x0621-#x063A] |
[#x0641-#x064A] | [#x0671-#x06B7] | [#x06BA-#x06BE] | [#x06C0-#x06CE] |
[#x06D0-#x06D3] | #x06D5 | [#x06E5-#x06E6] | [#x0905-#x0939] | #x093D |
[#x0958-#x0961] | [#x0985-#x098C] | [#x098F-#x0990] | [#x0993-#x09A8] |
[#x09AA-#x09B0] | #x09B2 | [#x09B6-#x09B9] | [#x09DC-#x09DD] |
[#x09DF-#x09E1] | [#x09F0-#x09F1] | [#x0A05-#x0A0A] | [#x0A0F-#x0A10] |
[#x0A13-#x0A28] | [#x0A2A-#x0A30] | [#x0A32-#x0A33] | [#x0A35-#x0A36] |
[#x0A38-#x0A39] | [#x0A59-#x0A5C] | #x0A5E | [#x0A72-#x0A74] |
[#x0A85-#x0A8B] | #x0A8D | [#x0A8F-#x0A91] | [#x0A93-#x0AA8] |
[#x0AAA-#x0AB0] | [#x0AB2-#x0AB3] | [#x0AB5-#x0AB9] | #x0ABD | #x0AE0 |
[#x0B05-#x0B0C] | [#x0B0F-#x0B10] | [#x0B13-#x0B28] | [#x0B2A-#x0B30] |
[#x0B32-#x0B33] | [#x0B36-#x0B39] | #x0B3D | [#x0B5C-#x0B5D] |
[#x0B5F-#x0B61] | [#x0B85-#x0B8A] | [#x0B8E-#x0B90] | [#x0B92-#x0B95] |
[#x0B99-#x0B9A] | #x0B9C | [#x0B9E-#x0B9F] | [#x0BA3-#x0BA4] |
[#x0BA8-#x0BAA] | [#x0BAE-#x0BB5] | [#x0BB7-#x0BB9] | [#x0C05-#x0C0C] |
[#x0C0E-#x0C10] | [#x0C12-#x0C28] | [#x0C2A-#x0C33] | [#x0C35-#x0C39] |
[#x0C60-#x0C61] | [#x0C85-#x0C8C] | [#x0C8E-#x0C90] | [#x0C92-#x0CA8] |
[#x0CAA-#x0CB3] | [#x0CB5-#x0CB9] | #x0CDE | [#x0CE0-#x0CE1] |
[#x0D05-#x0D0C] | [#x0D0E-#x0D10] | [#x0D12-#x0D28] | [#x0D2A-#x0D39] |
[#x0D60-#x0D61] | [#x0E01-#x0E2E] | #x0E30 | [#x0E32-#x0E33] |
[#x0E40-#x0E45] | [#x0E81-#x0E82] | #x0E84 | [#x0E87-#x0E88] | #x0E8A |
#x0E8D | [#x0E94-#x0E97] | [#x0E99-#x0E9F] | [#x0EA1-#x0EA3] | #x0EA5 |
#x0EA7 | [#x0EAA-#x0EAB] | [#x0EAD-#x0EAE] | #x0EB0 | [#x0EB2-#x0EB3] |
#x0EBD | [#x0EC0-#x0EC4] | [#x0F40-#x0F47] | [#x0F49-#x0F69] |
[#x10A0-#x10C5] | [#x10D0-#x10F6] | #x1100 | [#x1102-#x1103] |
[#x1105-#x1107] | #x1109 | [#x110B-#x110C] | [#x110E-#x1112] | #x113C |
#x113E | #x1140 | #x114C | #x114E | #x1150 | [#x1154-#x1155] | #x1159 |
[#x115F-#x1161] | #x1163 | #x1165 | #x1167 | #x1169 | [#x116D-#x116E] |
[#x1172-#x1173] | #x1175 | #x119E | #x11A8 | #x11AB | [#x11AE-#x11AF] |
[#x11B7-#x11B8] | #x11BA | [#x11BC-#x11C2] | #x11EB | #x11F0 | #x11F9 |
[#x1E00-#x1E9B] | [#x1EA0-#x1EF9] | [#x1F00-#x1F15] | [#x1F18-#x1F1D] |
[#x1F20-#x1F45] | [#x1F48-#x1F4D] | [#x1F50-#x1F57] | #x1F59 | #x1F5B |
#x1F5D | [#x1F5F-#x1F7D] | [#x1F80-#x1FB4] | [#x1FB6-#x1FBC] | #x1FBE |
[#x1FC2-#x1FC4] | [#x1FC6-#x1FCC] | [#x1FD0-#x1FD3] | [#x1FD6-#x1FDB] |
[#x1FE0-#x1FEC] | [#x1FF2-#x1FF4] | [#x1FF6-#x1FFC] | #x2126 |
[#x212A-#x212B] | #x212E | [#x2180-#x2182] | [#x3041-#x3094] |
[#x30A1-#x30FA] | [#x3105-#x312C] | [#xAC00-#xD7A3]"""
ideographic = """[#x4E00-#x9FA5] | #x3007 | [#x3021-#x3029]"""
combiningCharacter = """
[#x0300-#x0345] | [#x0360-#x0361] | [#x0483-#x0486] | [#x0591-#x05A1] |
[#x05A3-#x05B9] | [#x05BB-#x05BD] | #x05BF | [#x05C1-#x05C2] | #x05C4 |
[#x064B-#x0652] | #x0670 | [#x06D6-#x06DC] | [#x06DD-#x06DF] |
[#x06E0-#x06E4] | [#x06E7-#x06E8] | [#x06EA-#x06ED] | [#x0901-#x0903] |
#x093C | [#x093E-#x094C] | #x094D | [#x0951-#x0954] | [#x0962-#x0963] |
[#x0981-#x0983] | #x09BC | #x09BE | #x09BF | [#x09C0-#x09C4] |
[#x09C7-#x09C8] | [#x09CB-#x09CD] | #x09D7 | [#x09E2-#x09E3] | #x0A02 |
#x0A3C | #x0A3E | #x0A3F | [#x0A40-#x0A42] | [#x0A47-#x0A48] |
[#x0A4B-#x0A4D] | [#x0A70-#x0A71] | [#x0A81-#x0A83] | #x0ABC |
[#x0ABE-#x0AC5] | [#x0AC7-#x0AC9] | [#x0ACB-#x0ACD] | [#x0B01-#x0B03] |
#x0B3C | [#x0B3E-#x0B43] | [#x0B47-#x0B48] | [#x0B4B-#x0B4D] |
[#x0B56-#x0B57] | [#x0B82-#x0B83] | [#x0BBE-#x0BC2] | [#x0BC6-#x0BC8] |
[#x0BCA-#x0BCD] | #x0BD7 | [#x0C01-#x0C03] | [#x0C3E-#x0C44] |
[#x0C46-#x0C48] | [#x0C4A-#x0C4D] | [#x0C55-#x0C56] | [#x0C82-#x0C83] |
[#x0CBE-#x0CC4] | [#x0CC6-#x0CC8] | [#x0CCA-#x0CCD] | [#x0CD5-#x0CD6] |
[#x0D02-#x0D03] | [#x0D3E-#x0D43] | [#x0D46-#x0D48] | [#x0D4A-#x0D4D] |
#x0D57 | #x0E31 | [#x0E34-#x0E3A] | [#x0E47-#x0E4E] | #x0EB1 |
[#x0EB4-#x0EB9] | [#x0EBB-#x0EBC] | [#x0EC8-#x0ECD] | [#x0F18-#x0F19] |
#x0F35 | #x0F37 | #x0F39 | #x0F3E | #x0F3F | [#x0F71-#x0F84] |
[#x0F86-#x0F8B] | [#x0F90-#x0F95] | #x0F97 | [#x0F99-#x0FAD] |
[#x0FB1-#x0FB7] | #x0FB9 | [#x20D0-#x20DC] | #x20E1 | [#x302A-#x302F] |
#x3099 | #x309A"""
digit = """
[#x0030-#x0039] | [#x0660-#x0669] | [#x06F0-#x06F9] | [#x0966-#x096F] |
[#x09E6-#x09EF] | [#x0A66-#x0A6F] | [#x0AE6-#x0AEF] | [#x0B66-#x0B6F] |
[#x0BE7-#x0BEF] | [#x0C66-#x0C6F] | [#x0CE6-#x0CEF] | [#x0D66-#x0D6F] |
[#x0E50-#x0E59] | [#x0ED0-#x0ED9] | [#x0F20-#x0F29]"""
extender = """
#x00B7 | #x02D0 | #x02D1 | #x0387 | #x0640 | #x0E46 | #x0EC6 | #x3005 |
#[#x3031-#x3035] | [#x309D-#x309E] | [#x30FC-#x30FE]"""
letter = " | ".join([baseChar, ideographic])
# Without the
name = " | ".join([letter, digit, ".", "-", "_", combiningCharacter,
extender])
nameFirst = " | ".join([letter, "_"])
reChar = re.compile(r"#x([\d|A-F]{4,4})")
reCharRange = re.compile(r"\[#x([\d|A-F]{4,4})-#x([\d|A-F]{4,4})\]")
def charStringToList(chars):
charRanges = [item.strip() for item in chars.split(" | ")]
rv = []
for item in charRanges:
foundMatch = False
for regexp in (reChar, reCharRange):
match = regexp.match(item)
if match is not None:
rv.append([hexToInt(item) for item in match.groups()])
if len(rv[-1]) == 1:
rv[-1] = rv[-1] * 2
foundMatch = True
break
if not foundMatch:
assert len(item) == 1
rv.append([ord(item)] * 2)
rv = normaliseCharList(rv)
return rv
def normaliseCharList(charList):
charList = sorted(charList)
for item in charList:
assert item[1] >= item[0]
rv = []
i = 0
while i < len(charList):
j = 1
rv.append(charList[i])
while i + j < len(charList) and charList[i + j][0] <= rv[-1][1] + 1:
rv[-1][1] = charList[i + j][1]
j += 1
i += j
return rv
# We don't really support characters above the BMP :(
max_unicode = int("FFFF", 16)
def missingRanges(charList):
rv = []
if charList[0] != 0:
rv.append([0, charList[0][0] - 1])
for i, item in enumerate(charList[:-1]):
rv.append([item[1] + 1, charList[i + 1][0] - 1])
if charList[-1][1] != max_unicode:
rv.append([charList[-1][1] + 1, max_unicode])
return rv
def listToRegexpStr(charList):
rv = []
for item in charList:
if item[0] == item[1]:
rv.append(escapeRegexp(chr(item[0])))
else:
rv.append(escapeRegexp(chr(item[0])) + "-" +
escapeRegexp(chr(item[1])))
return "[%s]" % "".join(rv)
def hexToInt(hex_str):
return int(hex_str, 16)
def escapeRegexp(string):
specialCharacters = (".", "^", "$", "*", "+", "?", "{", "}",
"[", "]", "|", "(", ")", "-")
for char in specialCharacters:
string = string.replace(char, "\\" + char)
return string
# output from the above
nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa
nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa
# Simpler things
nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\\-'()+,./:=?;!*#@$_%]")
class InfosetFilter(object):
replacementRegexp = re.compile(r"U[\dA-F]{5,5}")
def __init__(self,
dropXmlnsLocalName=False,
dropXmlnsAttrNs=False,
preventDoubleDashComments=False,
preventDashAtCommentEnd=False,
replaceFormFeedCharacters=True,
preventSingleQuotePubid=False):
self.dropXmlnsLocalName = dropXmlnsLocalName
self.dropXmlnsAttrNs = dropXmlnsAttrNs
self.preventDoubleDashComments = preventDoubleDashComments
self.preventDashAtCommentEnd = preventDashAtCommentEnd
self.replaceFormFeedCharacters = replaceFormFeedCharacters
self.preventSingleQuotePubid = preventSingleQuotePubid
self.replaceCache = {}
def coerceAttribute(self, name, namespace=None):
if self.dropXmlnsLocalName and name.startswith("xmlns:"):
warnings.warn("Attributes cannot begin with xmlns", DataLossWarning)
return None
elif (self.dropXmlnsAttrNs and
namespace == "http://www.w3.org/2000/xmlns/"):
warnings.warn("Attributes cannot be in the xml namespace", DataLossWarning)
return None
else:
return self.toXmlName(name)
def coerceElement(self, name):
return self.toXmlName(name)
def coerceComment(self, data):
if self.preventDoubleDashComments:
while "--" in data:
warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning)
data = data.replace("--", "- -")
if data.endswith("-"):
warnings.warn("Comments cannot end in a dash", DataLossWarning)
data += " "
return data
def coerceCharacters(self, data):
if self.replaceFormFeedCharacters:
for _ in range(data.count("\x0C")):
warnings.warn("Text cannot contain U+000C", DataLossWarning)
data = data.replace("\x0C", " ")
# Other non-xml characters
return data
def coercePubid(self, data):
dataOutput = data
for char in nonPubidCharRegexp.findall(data):
warnings.warn("Coercing non-XML pubid", DataLossWarning)
replacement = self.getReplacementCharacter(char)
dataOutput = dataOutput.replace(char, replacement)
if self.preventSingleQuotePubid and dataOutput.find("'") >= 0:
warnings.warn("Pubid cannot contain single quote", DataLossWarning)
dataOutput = dataOutput.replace("'", self.getReplacementCharacter("'"))
return dataOutput
def toXmlName(self, name):
nameFirst = name[0]
nameRest = name[1:]
m = nonXmlNameFirstBMPRegexp.match(nameFirst)
if m:
warnings.warn("Coercing non-XML name: %s" % name, DataLossWarning)
nameFirstOutput = self.getReplacementCharacter(nameFirst)
else:
nameFirstOutput = nameFirst
nameRestOutput = nameRest
replaceChars = set(nonXmlNameBMPRegexp.findall(nameRest))
for char in replaceChars:
warnings.warn("Coercing non-XML name: %s" % name, DataLossWarning)
replacement = self.getReplacementCharacter(char)
nameRestOutput = nameRestOutput.replace(char, replacement)
return nameFirstOutput + nameRestOutput
def getReplacementCharacter(self, char):
if char in self.replaceCache:
replacement = self.replaceCache[char]
else:
replacement = self.escapeChar(char)
return replacement
def fromXmlName(self, name):
for item in set(self.replacementRegexp.findall(name)):
name = name.replace(item, self.unescapeChar(item))
return name
def escapeChar(self, char):
replacement = "U%05X" % ord(char)
self.replaceCache[char] = replacement
return replacement
def unescapeChar(self, charcode):
return chr(int(charcode[1:], 16))

918
venv/Lib/site-packages/pip/_vendor/html5lib/_inputstream.py
View File

@@ -1,918 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
from pip._vendor.six import text_type
from pip._vendor.six.moves import http_client, urllib
import codecs
import re
from io import BytesIO, StringIO
from pip._vendor import webencodings
from .constants import EOF, spaceCharacters, asciiLetters, asciiUppercase
from .constants import _ReparseException
from . import _utils
# Non-unicode versions of constants for use in the pre-parser
spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters])
asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters])
asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase])
spacesAngleBrackets = spaceCharactersBytes | frozenset([b">", b"<"])
invalid_unicode_no_surrogate = "[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]" # noqa
if _utils.supports_lone_surrogates:
# Use one extra step of indirection and create surrogates with
# eval. Not using this indirection would introduce an illegal
# unicode literal on platforms not supporting such lone
# surrogates.
assert invalid_unicode_no_surrogate[-1] == "]" and invalid_unicode_no_surrogate.count("]") == 1
invalid_unicode_re = re.compile(invalid_unicode_no_surrogate[:-1] +
eval('"\\uD800-\\uDFFF"') + # pylint:disable=eval-used
"]")
else:
invalid_unicode_re = re.compile(invalid_unicode_no_surrogate)
non_bmp_invalid_codepoints = {0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE, 0x5FFFF,
0x6FFFE, 0x6FFFF, 0x7FFFE, 0x7FFFF, 0x8FFFE,
0x8FFFF, 0x9FFFE, 0x9FFFF, 0xAFFFE, 0xAFFFF,
0xBFFFE, 0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE,
0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF,
0x10FFFE, 0x10FFFF}
ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005C\u005B-\u0060\u007B-\u007E]")
# Cache for charsUntil()
charsUntilRegEx = {}
class BufferedStream(object):
"""Buffering for streams that do not have buffering of their own
The buffer is implemented as a list of chunks on the assumption that
joining many strings will be slow since it is O(n**2)
"""
def __init__(self, stream):
self.stream = stream
self.buffer = []
self.position = [-1, 0] # chunk number, offset
def tell(self):
pos = 0
for chunk in self.buffer[:self.position[0]]:
pos += len(chunk)
pos += self.position[1]
return pos
def seek(self, pos):
assert pos <= self._bufferedBytes()
offset = pos
i = 0
while len(self.buffer[i]) < offset:
offset -= len(self.buffer[i])
i += 1
self.position = [i, offset]
def read(self, bytes):
if not self.buffer:
return self._readStream(bytes)
elif (self.position[0] == len(self.buffer) and
self.position[1] == len(self.buffer[-1])):
return self._readStream(bytes)
else:
return self._readFromBuffer(bytes)
def _bufferedBytes(self):
return sum([len(item) for item in self.buffer])
def _readStream(self, bytes):
data = self.stream.read(bytes)
self.buffer.append(data)
self.position[0] += 1
self.position[1] = len(data)
return data
def _readFromBuffer(self, bytes):
remainingBytes = bytes
rv = []
bufferIndex = self.position[0]
bufferOffset = self.position[1]
while bufferIndex < len(self.buffer) and remainingBytes != 0:
assert remainingBytes > 0
bufferedData = self.buffer[bufferIndex]
if remainingBytes <= len(bufferedData) - bufferOffset:
bytesToRead = remainingBytes
self.position = [bufferIndex, bufferOffset + bytesToRead]
else:
bytesToRead = len(bufferedData) - bufferOffset
self.position = [bufferIndex, len(bufferedData)]
bufferIndex += 1
rv.append(bufferedData[bufferOffset:bufferOffset + bytesToRead])
remainingBytes -= bytesToRead
bufferOffset = 0
if remainingBytes:
rv.append(self._readStream(remainingBytes))
return b"".join(rv)
def HTMLInputStream(source, **kwargs):
# Work around Python bug #20007: read(0) closes the connection.
# http://bugs.python.org/issue20007
if (isinstance(source, http_client.HTTPResponse) or
# Also check for addinfourl wrapping HTTPResponse
(isinstance(source, urllib.response.addbase) and
isinstance(source.fp, http_client.HTTPResponse))):
isUnicode = False
elif hasattr(source, "read"):
isUnicode = isinstance(source.read(0), text_type)
else:
isUnicode = isinstance(source, text_type)
if isUnicode:
encodings = [x for x in kwargs if x.endswith("_encoding")]
if encodings:
raise TypeError("Cannot set an encoding with a unicode input, set %r" % encodings)
return HTMLUnicodeInputStream(source, **kwargs)
else:
return HTMLBinaryInputStream(source, **kwargs)
class HTMLUnicodeInputStream(object):
"""Provides a unicode stream of characters to the HTMLTokenizer.
This class takes care of character encoding and removing or replacing
incorrect byte-sequences and also provides column and line tracking.
"""
_defaultChunkSize = 10240
def __init__(self, source):
"""Initialises the HTMLInputStream.
HTMLInputStream(source, [encoding]) -> Normalized stream from source
for use by html5lib.
source can be either a file-object, local filename or a string.
The optional encoding parameter must be a string that indicates
the encoding. If specified, that encoding will be used,
regardless of any BOM or later declaration (such as in a meta
element)
"""
if not _utils.supports_lone_surrogates:
# Such platforms will have already checked for such
# surrogate errors, so no need to do this checking.
self.reportCharacterErrors = None
elif len("\U0010FFFF") == 1:
self.reportCharacterErrors = self.characterErrorsUCS4
else:
self.reportCharacterErrors = self.characterErrorsUCS2
# List of where new lines occur
self.newLines = [0]
self.charEncoding = (lookupEncoding("utf-8"), "certain")
self.dataStream = self.openStream(source)
self.reset()
def reset(self):
self.chunk = ""
self.chunkSize = 0
self.chunkOffset = 0
self.errors = []
# number of (complete) lines in previous chunks
self.prevNumLines = 0
# number of columns in the last line of the previous chunk
self.prevNumCols = 0
# Deal with CR LF and surrogates split over chunk boundaries
self._bufferedCharacter = None
def openStream(self, source):
"""Produces a file object from source.
source can be either a file object, local filename or a string.
"""
# Already a file object
if hasattr(source, 'read'):
stream = source
else:
stream = StringIO(source)
return stream
def _position(self, offset):
chunk = self.chunk
nLines = chunk.count('\n', 0, offset)
positionLine = self.prevNumLines + nLines
lastLinePos = chunk.rfind('\n', 0, offset)
if lastLinePos == -1:
positionColumn = self.prevNumCols + offset
else:
positionColumn = offset - (lastLinePos + 1)
return (positionLine, positionColumn)
def position(self):
"""Returns (line, col) of the current position in the stream."""
line, col = self._position(self.chunkOffset)
return (line + 1, col)
def char(self):
""" Read one character from the stream or queue if available. Return
EOF when EOF is reached.
"""
# Read a new chunk from the input stream if necessary
if self.chunkOffset >= self.chunkSize:
if not self.readChunk():
return EOF
chunkOffset = self.chunkOffset
char = self.chunk[chunkOffset]
self.chunkOffset = chunkOffset + 1
return char
def readChunk(self, chunkSize=None):
if chunkSize is None:
chunkSize = self._defaultChunkSize
self.prevNumLines, self.prevNumCols = self._position(self.chunkSize)
self.chunk = ""
self.chunkSize = 0
self.chunkOffset = 0
data = self.dataStream.read(chunkSize)
# Deal with CR LF and surrogates broken across chunks
if self._bufferedCharacter:
data = self._bufferedCharacter + data
self._bufferedCharacter = None
elif not data:
# We have no more data, bye-bye stream
return False
if len(data) > 1:
lastv = ord(data[-1])
if lastv == 0x0D or 0xD800 <= lastv <= 0xDBFF:
self._bufferedCharacter = data[-1]
data = data[:-1]
if self.reportCharacterErrors:
self.reportCharacterErrors(data)
# Replace invalid characters
data = data.replace("\r\n", "\n")
data = data.replace("\r", "\n")
self.chunk = data
self.chunkSize = len(data)
return True
def characterErrorsUCS4(self, data):
for _ in range(len(invalid_unicode_re.findall(data))):
self.errors.append("invalid-codepoint")
def characterErrorsUCS2(self, data):
# Someone picked the wrong compile option
# You lose
skip = False
for match in invalid_unicode_re.finditer(data):
if skip:
continue
codepoint = ord(match.group())
pos = match.start()
# Pretty sure there should be endianness issues here
if _utils.isSurrogatePair(data[pos:pos + 2]):
# We have a surrogate pair!
char_val = _utils.surrogatePairToCodepoint(data[pos:pos + 2])
if char_val in non_bmp_invalid_codepoints:
self.errors.append("invalid-codepoint")
skip = True
elif (codepoint >= 0xD800 and codepoint <= 0xDFFF and
pos == len(data) - 1):
self.errors.append("invalid-codepoint")
else:
skip = False
self.errors.append("invalid-codepoint")
def charsUntil(self, characters, opposite=False):
""" Returns a string of characters from the stream up to but not
including any character in 'characters' or EOF. 'characters' must be
a container that supports the 'in' method and iteration over its
characters.
"""
# Use a cache of regexps to find the required characters
try:
chars = charsUntilRegEx[(characters, opposite)]
except KeyError:
if __debug__:
for c in characters:
assert(ord(c) < 128)
regex = "".join(["\\x%02x" % ord(c) for c in characters])
if not opposite:
regex = "^%s" % regex
chars = charsUntilRegEx[(characters, opposite)] = re.compile("[%s]+" % regex)
rv = []
while True:
# Find the longest matching prefix
m = chars.match(self.chunk, self.chunkOffset)
if m is None:
# If nothing matched, and it wasn't because we ran out of chunk,
# then stop
if self.chunkOffset != self.chunkSize:
break
else:
end = m.end()
# If not the whole chunk matched, return everything
# up to the part that didn't match
if end != self.chunkSize:
rv.append(self.chunk[self.chunkOffset:end])
self.chunkOffset = end
break
# If the whole remainder of the chunk matched,
# use it all and read the next chunk
rv.append(self.chunk[self.chunkOffset:])
if not self.readChunk():
# Reached EOF
break
r = "".join(rv)
return r
def unget(self, char):
# Only one character is allowed to be ungotten at once - it must
# be consumed again before any further call to unget
if char is not EOF:
if self.chunkOffset == 0:
# unget is called quite rarely, so it's a good idea to do
# more work here if it saves a bit of work in the frequently
# called char and charsUntil.
# So, just prepend the ungotten character onto the current
# chunk:
self.chunk = char + self.chunk
self.chunkSize += 1
else:
self.chunkOffset -= 1
assert self.chunk[self.chunkOffset] == char
class HTMLBinaryInputStream(HTMLUnicodeInputStream):
"""Provides a unicode stream of characters to the HTMLTokenizer.
This class takes care of character encoding and removing or replacing
incorrect byte-sequences and also provides column and line tracking.
"""
def __init__(self, source, override_encoding=None, transport_encoding=None,
same_origin_parent_encoding=None, likely_encoding=None,
default_encoding="windows-1252", useChardet=True):
"""Initialises the HTMLInputStream.
HTMLInputStream(source, [encoding]) -> Normalized stream from source
for use by html5lib.
source can be either a file-object, local filename or a string.
The optional encoding parameter must be a string that indicates
the encoding. If specified, that encoding will be used,
regardless of any BOM or later declaration (such as in a meta
element)
"""
# Raw Stream - for unicode objects this will encode to utf-8 and set
# self.charEncoding as appropriate
self.rawStream = self.openStream(source)
HTMLUnicodeInputStream.__init__(self, self.rawStream)
# Encoding Information
# Number of bytes to use when looking for a meta element with
# encoding information
self.numBytesMeta = 1024
# Number of bytes to use when using detecting encoding using chardet
self.numBytesChardet = 100
# Things from args
self.override_encoding = override_encoding
self.transport_encoding = transport_encoding
self.same_origin_parent_encoding = same_origin_parent_encoding
self.likely_encoding = likely_encoding
self.default_encoding = default_encoding
# Determine encoding
self.charEncoding = self.determineEncoding(useChardet)
assert self.charEncoding[0] is not None
# Call superclass
self.reset()
def reset(self):
self.dataStream = self.charEncoding[0].codec_info.streamreader(self.rawStream, 'replace')
HTMLUnicodeInputStream.reset(self)
def openStream(self, source):
"""Produces a file object from source.
source can be either a file object, local filename or a string.
"""
# Already a file object
if hasattr(source, 'read'):
stream = source
else:
stream = BytesIO(source)
try:
stream.seek(stream.tell())
except Exception:
stream = BufferedStream(stream)
return stream
def determineEncoding(self, chardet=True):
# BOMs take precedence over everything
# This will also read past the BOM if present
charEncoding = self.detectBOM(), "certain"
if charEncoding[0] is not None:
return charEncoding
# If we've been overridden, we've been overridden
charEncoding = lookupEncoding(self.override_encoding), "certain"
if charEncoding[0] is not None:
return charEncoding
# Now check the transport layer
charEncoding = lookupEncoding(self.transport_encoding), "certain"
if charEncoding[0] is not None:
return charEncoding
# Look for meta elements with encoding information
charEncoding = self.detectEncodingMeta(), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Parent document encoding
charEncoding = lookupEncoding(self.same_origin_parent_encoding), "tentative"
if charEncoding[0] is not None and not charEncoding[0].name.startswith("utf-16"):
return charEncoding
# "likely" encoding
charEncoding = lookupEncoding(self.likely_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Guess with chardet, if available
if chardet:
try:
from pip._vendor.chardet.universaldetector import UniversalDetector
except ImportError:
pass
else:
buffers = []
detector = UniversalDetector()
while not detector.done:
buffer = self.rawStream.read(self.numBytesChardet)
assert isinstance(buffer, bytes)
if not buffer:
break
buffers.append(buffer)
detector.feed(buffer)
detector.close()
encoding = lookupEncoding(detector.result['encoding'])
self.rawStream.seek(0)
if encoding is not None:
return encoding, "tentative"
# Try the default encoding
charEncoding = lookupEncoding(self.default_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Fallback to html5lib's default if even that hasn't worked
return lookupEncoding("windows-1252"), "tentative"
def changeEncoding(self, newEncoding):
assert self.charEncoding[1] != "certain"
newEncoding = lookupEncoding(newEncoding)
if newEncoding is None:
return
if newEncoding.name in ("utf-16be", "utf-16le"):
newEncoding = lookupEncoding("utf-8")
assert newEncoding is not None
elif newEncoding == self.charEncoding[0]:
self.charEncoding = (self.charEncoding[0], "certain")
else:
self.rawStream.seek(0)
self.charEncoding = (newEncoding, "certain")
self.reset()
raise _ReparseException("Encoding changed from %s to %s" % (self.charEncoding[0], newEncoding))
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
def detectEncodingMeta(self):
"""Report the encoding declared by the meta element
"""
buffer = self.rawStream.read(self.numBytesMeta)
assert isinstance(buffer, bytes)
parser = EncodingParser(buffer)
self.rawStream.seek(0)
encoding = parser.getEncoding()
if encoding is not None and encoding.name in ("utf-16be", "utf-16le"):
encoding = lookupEncoding("utf-8")
return encoding
class EncodingBytes(bytes):
"""String-like object with an associated position and various extra methods
If the position is ever greater than the string length then an exception is
raised"""
def __new__(self, value):
assert isinstance(value, bytes)
return bytes.__new__(self, value.lower())
def __init__(self, value):
# pylint:disable=unused-argument
self._position = -1
def __iter__(self):
return self
def __next__(self):
p = self._position = self._position + 1
if p >= len(self):
raise StopIteration
elif p < 0:
raise TypeError
return self[p:p + 1]
def next(self):
# Py2 compat
return self.__next__()
def previous(self):
p = self._position
if p >= len(self):
raise StopIteration
elif p < 0:
raise TypeError
self._position = p = p - 1
return self[p:p + 1]
def setPosition(self, position):
if self._position >= len(self):
raise StopIteration
self._position = position
def getPosition(self):
if self._position >= len(self):
raise StopIteration
if self._position >= 0:
return self._position
else:
return None
position = property(getPosition, setPosition)
def getCurrentByte(self):
return self[self.position:self.position + 1]
currentByte = property(getCurrentByte)
def skip(self, chars=spaceCharactersBytes):
"""Skip past a list of characters"""
p = self.position # use property for the error-checking
while p < len(self):
c = self[p:p + 1]
if c not in chars:
self._position = p
return c
p += 1
self._position = p
return None
def skipUntil(self, chars):
p = self.position
while p < len(self):
c = self[p:p + 1]
if c in chars:
self._position = p
return c
p += 1
self._position = p
return None
def matchBytes(self, bytes):
"""Look for a sequence of bytes at the start of a string. If the bytes
are found return True and advance the position to the byte after the
match. Otherwise return False and leave the position alone"""
rv = self.startswith(bytes, self.position)
if rv:
self.position += len(bytes)
return rv
def jumpTo(self, bytes):
"""Look for the next sequence of bytes matching a given sequence. If
a match is found advance the position to the last byte of the match"""
try:
self._position = self.index(bytes, self.position) + len(bytes) - 1
except ValueError:
raise StopIteration
return True
class EncodingParser(object):
"""Mini parser for detecting character encoding from meta elements"""
def __init__(self, data):
"""string - the data to work on for encoding detection"""
self.data = EncodingBytes(data)
self.encoding = None
def getEncoding(self):
if b"<meta" not in self.data:
return None
methodDispatch = (
(b"<!--", self.handleComment),
(b"<meta", self.handleMeta),
(b"</", self.handlePossibleEndTag),
(b"<!", self.handleOther),
(b"<?", self.handleOther),
(b"<", self.handlePossibleStartTag))
for _ in self.data:
keepParsing = True
try:
self.data.jumpTo(b"<")
except StopIteration:
break
for key, method in methodDispatch:
if self.data.matchBytes(key):
try:
keepParsing = method()
break
except StopIteration:
keepParsing = False
break
if not keepParsing:
break
return self.encoding
def handleComment(self):
"""Skip over comments"""
return self.data.jumpTo(b"-->")
def handleMeta(self):
if self.data.currentByte not in spaceCharactersBytes:
# if we have <meta not followed by a space so just keep going
return True
# We have a valid meta element we want to search for attributes
hasPragma = False
pendingEncoding = None
while True:
# Try to find the next attribute after the current position
attr = self.getAttribute()
if attr is None:
return True
else:
if attr[0] == b"http-equiv":
hasPragma = attr[1] == b"content-type"
if hasPragma and pendingEncoding is not None:
self.encoding = pendingEncoding
return False
elif attr[0] == b"charset":
tentativeEncoding = attr[1]
codec = lookupEncoding(tentativeEncoding)
if codec is not None:
self.encoding = codec
return False
elif attr[0] == b"content":
contentParser = ContentAttrParser(EncodingBytes(attr[1]))
tentativeEncoding = contentParser.parse()
if tentativeEncoding is not None:
codec = lookupEncoding(tentativeEncoding)
if codec is not None:
if hasPragma:
self.encoding = codec
return False
else:
pendingEncoding = codec
def handlePossibleStartTag(self):
return self.handlePossibleTag(False)
def handlePossibleEndTag(self):
next(self.data)
return self.handlePossibleTag(True)
def handlePossibleTag(self, endTag):
data = self.data
if data.currentByte not in asciiLettersBytes:
# If the next byte is not an ascii letter either ignore this
# fragment (possible start tag case) or treat it according to
# handleOther
if endTag:
data.previous()
self.handleOther()
return True
c = data.skipUntil(spacesAngleBrackets)
if c == b"<":
# return to the first step in the overall "two step" algorithm
# reprocessing the < byte
data.previous()
else:
# Read all attributes
attr = self.getAttribute()
while attr is not None:
attr = self.getAttribute()
return True
def handleOther(self):
return self.data.jumpTo(b">")
def getAttribute(self):
"""Return a name,value pair for the next attribute in the stream,
if one is found, or None"""
data = self.data
# Step 1 (skip chars)
c = data.skip(spaceCharactersBytes | frozenset([b"/"]))
assert c is None or len(c) == 1
# Step 2
if c in (b">", None):
return None
# Step 3
attrName = []
attrValue = []
# Step 4 attribute name
while True:
if c == b"=" and attrName:
break
elif c in spaceCharactersBytes:
# Step 6!
c = data.skip()
break
elif c in (b"/", b">"):
return b"".join(attrName), b""
elif c in asciiUppercaseBytes:
attrName.append(c.lower())
elif c is None:
return None
else:
attrName.append(c)
# Step 5
c = next(data)
# Step 7
if c != b"=":
data.previous()
return b"".join(attrName), b""
# Step 8
next(data)
# Step 9
c = data.skip()
# Step 10
if c in (b"'", b'"'):
# 10.1
quoteChar = c
while True:
# 10.2
c = next(data)
# 10.3
if c == quoteChar:
next(data)
return b"".join(attrName), b"".join(attrValue)
# 10.4
elif c in asciiUppercaseBytes:
attrValue.append(c.lower())
# 10.5
else:
attrValue.append(c)
elif c == b">":
return b"".join(attrName), b""
elif c in asciiUppercaseBytes:
attrValue.append(c.lower())
elif c is None:
return None
else:
attrValue.append(c)
# Step 11
while True:
c = next(data)
if c in spacesAngleBrackets:
return b"".join(attrName), b"".join(attrValue)
elif c in asciiUppercaseBytes:
attrValue.append(c.lower())
elif c is None:
return None
else:
attrValue.append(c)
class ContentAttrParser(object):
def __init__(self, data):
assert isinstance(data, bytes)
self.data = data
def parse(self):
try:
# Check if the attr name is charset
# otherwise return
self.data.jumpTo(b"charset")
self.data.position += 1
self.data.skip()
if not self.data.currentByte == b"=":
# If there is no = sign keep looking for attrs
return None
self.data.position += 1
self.data.skip()
# Look for an encoding between matching quote marks
if self.data.currentByte in (b'"', b"'"):
quoteMark = self.data.currentByte
self.data.position += 1
oldPosition = self.data.position
if self.data.jumpTo(quoteMark):
return self.data[oldPosition:self.data.position]
else:
return None
else:
# Unquoted value
oldPosition = self.data.position
try:
self.data.skipUntil(spaceCharactersBytes)
return self.data[oldPosition:self.data.position]
except StopIteration:
# Return the whole remaining value
return self.data[oldPosition:]
except StopIteration:
return None
def lookupEncoding(encoding):
"""Return the python codec name corresponding to an encoding or None if the
string doesn't correspond to a valid encoding."""
if isinstance(encoding, bytes):
try:
encoding = encoding.decode("ascii")
except UnicodeDecodeError:
return None
if encoding is not None:
try:
return webencodings.lookup(encoding)
except AttributeError:
return None
else:
return None

1735
venv/Lib/site-packages/pip/_vendor/html5lib/_tokenizer.py
View File

File diff suppressed because it is too large Load Diff

5
venv/Lib/site-packages/pip/_vendor/html5lib/_trie/__init__.py
View File

@@ -1,5 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
from .py import Trie
__all__ = ["Trie"]

40
venv/Lib/site-packages/pip/_vendor/html5lib/_trie/_base.py
View File

@@ -1,40 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
try:
from collections.abc import Mapping
except ImportError: # Python 2.7
from collections import Mapping
class Trie(Mapping):
"""Abstract base class for tries"""
def keys(self, prefix=None):
# pylint:disable=arguments-differ
keys = super(Trie, self).keys()
if prefix is None:
return set(keys)
return {x for x in keys if x.startswith(prefix)}
def has_keys_with_prefix(self, prefix):
for key in self.keys():
if key.startswith(prefix):
return True
return False
def longest_prefix(self, prefix):
if prefix in self:
return prefix
for i in range(1, len(prefix) + 1):
if prefix[:-i] in self:
return prefix[:-i]
raise KeyError(prefix)
def longest_prefix_item(self, prefix):
lprefix = self.longest_prefix(prefix)
return (lprefix, self[lprefix])

67
venv/Lib/site-packages/pip/_vendor/html5lib/_trie/py.py
View File

@@ -1,67 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
from pip._vendor.six import text_type
from bisect import bisect_left
from ._base import Trie as ABCTrie
class Trie(ABCTrie):
def __init__(self, data):
if not all(isinstance(x, text_type) for x in data.keys()):
raise TypeError("All keys must be strings")
self._data = data
self._keys = sorted(data.keys())
self._cachestr = ""
self._cachepoints = (0, len(data))
def __contains__(self, key):
return key in self._data
def __len__(self):
return len(self._data)
def __iter__(self):
return iter(self._data)
def __getitem__(self, key):
return self._data[key]
def keys(self, prefix=None):
if prefix is None or prefix == "" or not self._keys:
return set(self._keys)
if prefix.startswith(self._cachestr):
lo, hi = self._cachepoints
start = i = bisect_left(self._keys, prefix, lo, hi)
else:
start = i = bisect_left(self._keys, prefix)
keys = set()
if start == len(self._keys):
return keys
while self._keys[i].startswith(prefix):
keys.add(self._keys[i])
i += 1
self._cachestr = prefix
self._cachepoints = (start, i)
return keys
def has_keys_with_prefix(self, prefix):
if prefix in self._data:
return True
if prefix.startswith(self._cachestr):
lo, hi = self._cachepoints
i = bisect_left(self._keys, prefix, lo, hi)
else:
i = bisect_left(self._keys, prefix)
if i == len(self._keys):
return False
return self._keys[i].startswith(prefix)

159
venv/Lib/site-packages/pip/_vendor/html5lib/_utils.py
View File

@@ -1,159 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
from types import ModuleType
try:
from collections.abc import Mapping
except ImportError:
from collections import Mapping
from pip._vendor.six import text_type, PY3
if PY3:
import xml.etree.ElementTree as default_etree
else:
try:
import xml.etree.cElementTree as default_etree
except ImportError:
import xml.etree.ElementTree as default_etree
__all__ = ["default_etree", "MethodDispatcher", "isSurrogatePair",
"surrogatePairToCodepoint", "moduleFactoryFactory",
"supports_lone_surrogates"]
# Platforms not supporting lone surrogates (\uD800-\uDFFF) should be
# caught by the below test. In general this would be any platform
# using UTF-16 as its encoding of unicode strings, such as
# Jython. This is because UTF-16 itself is based on the use of such
# surrogates, and there is no mechanism to further escape such
# escapes.
try:
_x = eval('"\\uD800"') # pylint:disable=eval-used
if not isinstance(_x, text_type):
# We need this with u"" because of http://bugs.jython.org/issue2039
_x = eval('u"\\uD800"') # pylint:disable=eval-used
assert isinstance(_x, text_type)
except Exception:
supports_lone_surrogates = False
else:
supports_lone_surrogates = True
class MethodDispatcher(dict):
"""Dict with 2 special properties:
On initiation, keys that are lists, sets or tuples are converted to
multiple keys so accessing any one of the items in the original
list-like object returns the matching value
md = MethodDispatcher({("foo", "bar"):"baz"})
md["foo"] == "baz"
A default value which can be set through the default attribute.
"""
def __init__(self, items=()):
_dictEntries = []
for name, value in items:
if isinstance(name, (list, tuple, frozenset, set)):
for item in name:
_dictEntries.append((item, value))
else:
_dictEntries.append((name, value))
dict.__init__(self, _dictEntries)
assert len(self) == len(_dictEntries)
self.default = None
def __getitem__(self, key):
return dict.get(self, key, self.default)
def __get__(self, instance, owner=None):
return BoundMethodDispatcher(instance, self)
class BoundMethodDispatcher(Mapping):
"""Wraps a MethodDispatcher, binding its return values to `instance`"""
def __init__(self, instance, dispatcher):
self.instance = instance
self.dispatcher = dispatcher
def __getitem__(self, key):
# see https://docs.python.org/3/reference/datamodel.html#object.__get__
# on a function, __get__ is used to bind a function to an instance as a bound method
return self.dispatcher[key].__get__(self.instance)
def get(self, key, default):
if key in self.dispatcher:
return self[key]
else:
return default
def __iter__(self):
return iter(self.dispatcher)
def __len__(self):
return len(self.dispatcher)
def __contains__(self, key):
return key in self.dispatcher
# Some utility functions to deal with weirdness around UCS2 vs UCS4
# python builds
def isSurrogatePair(data):
return (len(data) == 2 and
ord(data[0]) >= 0xD800 and ord(data[0]) <= 0xDBFF and
ord(data[1]) >= 0xDC00 and ord(data[1]) <= 0xDFFF)
def surrogatePairToCodepoint(data):
char_val = (0x10000 + (ord(data[0]) - 0xD800) * 0x400 +
(ord(data[1]) - 0xDC00))
return char_val
# Module Factory Factory (no, this isn't Java, I know)
# Here to stop this being duplicated all over the place.
def moduleFactoryFactory(factory):
moduleCache = {}
def moduleFactory(baseModule, *args, **kwargs):
if isinstance(ModuleType.__name__, type("")):
name = "_%s_factory" % baseModule.__name__
else:
name = b"_%s_factory" % baseModule.__name__
kwargs_tuple = tuple(kwargs.items())
try:
return moduleCache[name][args][kwargs_tuple]
except KeyError:
mod = ModuleType(name)
objs = factory(baseModule, *args, **kwargs)
mod.__dict__.update(objs)
if "name" not in moduleCache:
moduleCache[name] = {}
if "args" not in moduleCache[name]:
moduleCache[name][args] = {}
if "kwargs" not in moduleCache[name][args]:
moduleCache[name][args][kwargs_tuple] = {}
moduleCache[name][args][kwargs_tuple] = mod
return mod
return moduleFactory
def memoize(func):
cache = {}
def wrapped(*args, **kwargs):
key = (tuple(args), tuple(kwargs.items()))
if key not in cache:
cache[key] = func(*args, **kwargs)
return cache[key]
return wrapped

2946
venv/Lib/site-packages/pip/_vendor/html5lib/constants.py
View File

File diff suppressed because it is too large Load Diff

0
venv/Lib/site-packages/pip/_vendor/html5lib/filters/__init__.py
View File

29
venv/Lib/site-packages/pip/_vendor/html5lib/filters/alphabeticalattributes.py
View File

@@ -1,29 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
from . import base
from collections import OrderedDict
def _attr_key(attr):
"""Return an appropriate key for an attribute for sorting
Attributes have a namespace that can be either ``None`` or a string. We
can't compare the two because they're different types, so we convert
``None`` to an empty string first.
"""
return (attr[0][0] or ''), attr[0][1]
class Filter(base.Filter):
"""Alphabetizes attributes for elements"""
def __iter__(self):
for token in base.Filter.__iter__(self):
if token["type"] in ("StartTag", "EmptyTag"):
attrs = OrderedDict()
for name, value in sorted(token["data"].items(),
key=_attr_key):
attrs[name] = value
token["data"] = attrs
yield token

12
venv/Lib/site-packages/pip/_vendor/html5lib/filters/base.py
View File

@@ -1,12 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
class Filter(object):
def __init__(self, source):
self.source = source
def __iter__(self):
return iter(self.source)
def __getattr__(self, name):
return getattr(self.source, name)

73
venv/Lib/site-packages/pip/_vendor/html5lib/filters/inject_meta_charset.py
View File

@@ -1,73 +0,0 @@
from __future__ import absolute_import, division, unicode_literals
from . import base
class Filter(base.Filter):
"""Injects ``<meta charset=ENCODING>`` tag into head of document"""
def __init__(self, source, encoding):
"""Creates a Filter
:arg source: the source token stream
:arg encoding: the encoding to set
"""
base.Filter.__init__(self, source)
self.encoding = encoding
def __iter__(self):
state = "pre_head"
meta_found = (self.encoding is None)
pending = []
for token in base.Filter.__iter__(self):
type = token["type"]
if type == "StartTag":
if token["name"].lower() == "head":
state = "in_head"
elif type == "EmptyTag":
if token["name"].lower() == "meta":
# replace charset with actual encoding
has_http_equiv_content_type = False
for (namespace, name), value in token["data"].items():
if namespace is not None:
continue
elif name.lower() == 'charset':
token["data"][(namespace, name)] = self.encoding
meta_found = True
break
elif name == 'http-equiv' and value.lower() == 'content-type':
has_http_equiv_content_type = True
else:
if has_http_equiv_content_type and (None, "content") in token["data"]:
token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding
meta_found = True
elif token["name"].lower() == "head" and not meta_found:
# insert meta into empty head
yield {"type": "StartTag", "name": "head",
"data": token["data"]}
yield {"type": "EmptyTag", "name": "meta",
"data": {(None, "charset"): self.encoding}}
yield {"type": "EndTag", "name": "head"}
meta_found = True
continue
elif type == "EndTag":
if token["name"].lower() == "head" and pending:
# insert meta into head (if necessary) and flush pending queue
yield pending.pop(0)
if not meta_found:
yield {"type": "EmptyTag", "name": "meta",
"data": {(None, "charset"): self.encoding}}
while pending:
yield pending.pop(0)
meta_found = True
state = "post_head"
if state == "in_head":
pending.append(token)
else:
yield token

Some files were not shown because too many files have changed in this diff Show More