Ninluc/Smartwave
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Init

Browse Source
This commit is contained in:
Matthias Guillitte
2026-07-13 15:46:44 +02:00
commit 1df9d878ca
1729 changed files with 326867 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
venv/bin/Activate.ps1
+247
View File
@@ -0,0 +1,247 @@
<#
.Synopsis
Activate a Python virtual environment for the current PowerShell session.
.Description
Pushes the python executable for a virtual environment to the front of the
$Env:PATH environment variable and sets the prompt to signify that you are
in a Python virtual environment. Makes use of the command line switches as
well as the `pyvenv.cfg` file values present in the virtual environment.
.Parameter VenvDir
Path to the directory that contains the virtual environment to activate. The
default value for this is the parent of the directory that the Activate.ps1
script is located within.
.Parameter Prompt
The prompt prefix to display when this virtual environment is activated. By
default, this prompt is the name of the virtual environment folder (VenvDir)
surrounded by parentheses and followed by a single space (ie. '(.venv) ').
.Example
Activate.ps1
Activates the Python virtual environment that contains the Activate.ps1 script.
.Example
Activate.ps1 -Verbose
Activates the Python virtual environment that contains the Activate.ps1 script,
and shows extra information about the activation as it executes.
.Example
Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
Activates the Python virtual environment located in the specified location.
.Example
Activate.ps1 -Prompt "MyPython"
Activates the Python virtual environment that contains the Activate.ps1 script,
and prefixes the current prompt with the specified string (surrounded in
parentheses) while the virtual environment is active.
.Notes
On Windows, it may be required to enable this Activate.ps1 script by setting the
execution policy for the user. You can do this by issuing the following PowerShell
command:
PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
For more information on Execution Policies:
https://go.microsoft.com/fwlink/?LinkID=135170
#>
Param(
[Parameter(Mandatory = $false)]
[String]
$VenvDir,
[Parameter(Mandatory = $false)]
[String]
$Prompt
)
<# Function declarations --------------------------------------------------- #>
<#
.Synopsis
Remove all shell session elements added by the Activate script, including the
addition of the virtual environment's Python executable from the beginning of
the PATH variable.
.Parameter NonDestructive
If present, do not remove this function from the global namespace for the
session.
#>
function global:deactivate ([switch]$NonDestructive) {
# Revert to original values
# The prior prompt:
if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
}
# The prior PYTHONHOME:
if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
}
# The prior PATH:
if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
Remove-Item -Path Env:_OLD_VIRTUAL_PATH
}
# Just remove the VIRTUAL_ENV altogether:
if (Test-Path -Path Env:VIRTUAL_ENV) {
Remove-Item -Path env:VIRTUAL_ENV
}
# Just remove VIRTUAL_ENV_PROMPT altogether.
if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
Remove-Item -Path env:VIRTUAL_ENV_PROMPT
}
# Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
}
# Leave deactivate function in the global namespace if requested:
if (-not $NonDestructive) {
Remove-Item -Path function:deactivate
}
}
<#
.Description
Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
given folder, and returns them in a map.
For each line in the pyvenv.cfg file, if that line can be parsed into exactly
two strings separated by `=` (with any amount of whitespace surrounding the =)
then it is considered a `key = value` line. The left hand string is the key,
the right hand is the value.
If the value starts with a `'` or a `"` then the first and last character is
stripped from the value before being captured.
.Parameter ConfigDir
Path to the directory that contains the `pyvenv.cfg` file.
#>
function Get-PyVenvConfig(
[String]
$ConfigDir
) {
Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
# Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
$pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
# An empty map will be returned if no config file is found.
$pyvenvConfig = @{ }
if ($pyvenvConfigPath) {
Write-Verbose "File exists, parse `key = value` lines"
$pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
$pyvenvConfigContent | ForEach-Object {
$keyval = $PSItem -split "\s*=\s*", 2
if ($keyval[0] -and $keyval[1]) {
$val = $keyval[1]
# Remove extraneous quotations around a string value.
if ("'""".Contains($val.Substring(0, 1))) {
$val = $val.Substring(1, $val.Length - 2)
}
$pyvenvConfig[$keyval[0]] = $val
Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
}
}
}
return $pyvenvConfig
}
<# Begin Activate script --------------------------------------------------- #>
# Determine the containing directory of this script
$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
$VenvExecDir = Get-Item -Path $VenvExecPath
Write-Verbose "Activation script is located in path: '$VenvExecPath'"
Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
# Set values required in priority: CmdLine, ConfigFile, Default
# First, get the location of the virtual environment, it might not be
# VenvExecDir if specified on the command line.
if ($VenvDir) {
Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
}
else {
Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
$VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
Write-Verbose "VenvDir=$VenvDir"
}
# Next, read the `pyvenv.cfg` file to determine any required value such
# as `prompt`.
$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
# Next, set the prompt from the command line, or the config file, or
# just use the name of the virtual environment folder.
if ($Prompt) {
Write-Verbose "Prompt specified as argument, using '$Prompt'"
}
else {
Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
Write-Verbose " Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
$Prompt = $pyvenvCfg['prompt'];
}
else {
Write-Verbose " Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
Write-Verbose " Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
$Prompt = Split-Path -Path $venvDir -Leaf
}
}
Write-Verbose "Prompt = '$Prompt'"
Write-Verbose "VenvDir='$VenvDir'"
# Deactivate any currently active virtual environment, but leave the
# deactivate function in place.
deactivate -nondestructive
# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
# that there is an activated venv.
$env:VIRTUAL_ENV = $VenvDir
if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
Write-Verbose "Setting prompt to '$Prompt'"
# Set the prompt to include the env name
# Make sure _OLD_VIRTUAL_PROMPT is global
function global:_OLD_VIRTUAL_PROMPT { "" }
Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
function global:prompt {
Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
_OLD_VIRTUAL_PROMPT
}
$env:VIRTUAL_ENV_PROMPT = $Prompt
}
# Clear PYTHONHOME
if (Test-Path -Path Env:PYTHONHOME) {
Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
Remove-Item -Path Env:PYTHONHOME
}
# Add the venv to the PATH
Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"
venv/bin/activate
+70
View File
@@ -0,0 +1,70 @@
# This file must be used with "source bin/activate" *from bash*
# You cannot run it directly
deactivate () {
# reset old environment variables
if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
PATH="${_OLD_VIRTUAL_PATH:-}"
export PATH
unset _OLD_VIRTUAL_PATH
fi
if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
export PYTHONHOME
unset _OLD_VIRTUAL_PYTHONHOME
fi
# Call hash to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
hash -r 2> /dev/null
if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
PS1="${_OLD_VIRTUAL_PS1:-}"
export PS1
unset _OLD_VIRTUAL_PS1
fi
unset VIRTUAL_ENV
unset VIRTUAL_ENV_PROMPT
if [ ! "${1:-}" = "nondestructive" ] ; then
# Self destruct!
unset -f deactivate
fi
}
# unset irrelevant variables
deactivate nondestructive
# on Windows, a path can contain colons and backslashes and has to be converted:
if [ "${OSTYPE:-}" = "cygwin" ] || [ "${OSTYPE:-}" = "msys" ] ; then
# transform D:\path\to\venv to /d/path/to/venv on MSYS
# and to /cygdrive/d/path/to/venv on Cygwin
export VIRTUAL_ENV=$(cygpath /home/ninluc/Documents/school/IoT/smartWave/venv)
else
# use the path as-is
export VIRTUAL_ENV=/home/ninluc/Documents/school/IoT/smartWave/venv
fi
_OLD_VIRTUAL_PATH="$PATH"
PATH="$VIRTUAL_ENV/"bin":$PATH"
export PATH
# unset PYTHONHOME if set
# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
# could use `if (set -u; : $PYTHONHOME) ;` in bash
if [ -n "${PYTHONHOME:-}" ] ; then
_OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
unset PYTHONHOME
fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1:-}"
PS1='(venv) '"${PS1:-}"
export PS1
VIRTUAL_ENV_PROMPT='(venv) '
export VIRTUAL_ENV_PROMPT
fi
# Call hash to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
hash -r 2> /dev/null
venv/bin/activate.csh
+27
View File
@@ -0,0 +1,27 @@
# This file must be used with "source bin/activate.csh" *from csh*.
# You cannot run it directly.
# Created by Davide Di Blasi <davidedb@gmail.com>.
# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
# Unset irrelevant variables.
deactivate nondestructive
setenv VIRTUAL_ENV /home/ninluc/Documents/school/IoT/smartWave/venv
set _OLD_VIRTUAL_PATH="$PATH"
setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
set prompt = '(venv) '"$prompt"
setenv VIRTUAL_ENV_PROMPT '(venv) '
endif
alias pydoc python -m pydoc
rehash
venv/bin/activate.fish
+69
View File
@@ -0,0 +1,69 @@
# This file must be used with "source <venv>/bin/activate.fish" *from fish*
# (https://fishshell.com/). You cannot run it directly.
function deactivate -d "Exit virtual environment and return to normal shell environment"
# reset old environment variables
if test -n "$_OLD_VIRTUAL_PATH"
set -gx PATH $_OLD_VIRTUAL_PATH
set -e _OLD_VIRTUAL_PATH
end
if test -n "$_OLD_VIRTUAL_PYTHONHOME"
set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
set -e _OLD_VIRTUAL_PYTHONHOME
end
if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
set -e _OLD_FISH_PROMPT_OVERRIDE
# prevents error when using nested fish instances (Issue #93858)
if functions -q _old_fish_prompt
functions -e fish_prompt
functions -c _old_fish_prompt fish_prompt
functions -e _old_fish_prompt
end
end
set -e VIRTUAL_ENV
set -e VIRTUAL_ENV_PROMPT
if test "$argv[1]" != "nondestructive"
# Self-destruct!
functions -e deactivate
end
end
# Unset irrelevant variables.
deactivate nondestructive
set -gx VIRTUAL_ENV /home/ninluc/Documents/school/IoT/smartWave/venv
set -gx _OLD_VIRTUAL_PATH $PATH
set -gx PATH "$VIRTUAL_ENV/"bin $PATH
# Unset PYTHONHOME if set.
if set -q PYTHONHOME
set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
set -e PYTHONHOME
end
if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
# fish uses a function instead of an env var to generate the prompt.
# Save the current fish_prompt function as the function _old_fish_prompt.
functions -c fish_prompt _old_fish_prompt
# With the original prompt function renamed, we can override with our own.
function fish_prompt
# Save the return status of the last command.
set -l old_status $status
# Output the venv prompt; color taken from the blue of the Python logo.
printf "%s%s%s" (set_color 4B8BBE) '(venv) ' (set_color normal)
# Restore the return status of the previous command.
echo "exit $old_status" | .
# Output the original/"old" prompt.
_old_fish_prompt
end
set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
set -gx VIRTUAL_ENV_PROMPT '(venv) '
end
venv/bin/flask
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from flask.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/idna
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from idna.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/mpremote
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from mpremote.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/normalizer
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from charset_normalizer.cli import cli_detect
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli_detect())
venv/bin/pip
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/pip3
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/pip3.12
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/pyserial-miniterm
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from serial.tools.miniterm import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/pyserial-ports
Executable
+8
View File
@@ -0,0 +1,8 @@
#!/home/ninluc/Documents/school/IoT/smartWave/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from serial.tools.list_ports import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())
venv/bin/python
Symlink
+1
View File
@@ -0,0 +1 @@
python3
venv/bin/python3
Symlink
+1
View File
@@ -0,0 +1 @@
/usr/bin/python3
venv/bin/python3.12
Symlink
+1
View File
@@ -0,0 +1 @@
python3
venv/lib/python3.12/site-packages/ada92cb5d92a588d1b93__mypyc.cpython-312-x86_64-linux-gnu.so
Executable
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/blinker-1.9.0.dist-info/INSTALLER
+1
View File
@@ -0,0 +1 @@
pip
venv/lib/python3.12/site-packages/blinker-1.9.0.dist-info/LICENSE.txt
+20
View File
@@ -0,0 +1,20 @@
Copyright 2010 Jason Kirtland
Permission is hereby granted, free of charge, to any person obtaining a
copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be included
in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
venv/lib/python3.12/site-packages/blinker-1.9.0.dist-info/METADATA
+60
View File
@@ -0,0 +1,60 @@
Metadata-Version: 2.3
Name: blinker
Version: 1.9.0
Summary: Fast, simple object-to-object and broadcast signaling
Author: Jason Kirtland
Maintainer-email: Pallets Ecosystem <contact@palletsprojects.com>
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Classifier: Development Status :: 5 - Production/Stable
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Typing :: Typed
Project-URL: Chat, https://discord.gg/pallets
Project-URL: Documentation, https://blinker.readthedocs.io
Project-URL: Source, https://github.com/pallets-eco/blinker/
# Blinker
Blinker provides a fast dispatching system that allows any number of
interested parties to subscribe to events, or "signals".
## Pallets Community Ecosystem
> [!IMPORTANT]\
> This project is part of the Pallets Community Ecosystem. Pallets is the open
> source organization that maintains Flask; Pallets-Eco enables community
> maintenance of related projects. If you are interested in helping maintain
> this project, please reach out on [the Pallets Discord server][discord].
>
> [discord]: https://discord.gg/pallets
## Example
Signal receivers can subscribe to specific senders or receive signals
sent by any sender.
```pycon
>>> from blinker import signal
>>> started = signal('round-started')
>>> def each(round):
... print(f"Round {round}")
...
>>> started.connect(each)
>>> def round_two(round):
... print("This is round two.")
...
>>> started.connect(round_two, sender=2)
>>> for round in range(1, 4):
... started.send(round)
...
Round 1!
Round 2!
This is round two.
Round 3!
```
venv/lib/python3.12/site-packages/blinker-1.9.0.dist-info/RECORD
+12
View File
@@ -0,0 +1,12 @@
blinker-1.9.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
blinker-1.9.0.dist-info/LICENSE.txt,sha256=nrc6HzhZekqhcCXSrhvjg5Ykx5XphdTw6Xac4p-spGc,1054
blinker-1.9.0.dist-info/METADATA,sha256=uIRiM8wjjbHkCtbCyTvctU37IAZk0kEe5kxAld1dvzA,1633
blinker-1.9.0.dist-info/RECORD,,
blinker-1.9.0.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
blinker/__init__.py,sha256=I2EdZqpy4LyjX17Hn1yzJGWCjeLaVaPzsMgHkLfj_cQ,317
blinker/__pycache__/__init__.cpython-312.pyc,,
blinker/__pycache__/_utilities.cpython-312.pyc,,
blinker/__pycache__/base.cpython-312.pyc,,
blinker/_utilities.py,sha256=0J7eeXXTUx0Ivf8asfpx0ycVkp0Eqfqnj117x2mYX9E,1675
blinker/base.py,sha256=QpDuvXXcwJF49lUBcH5BiST46Rz9wSG7VW_p7N_027M,19132
blinker/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
venv/lib/python3.12/site-packages/blinker-1.9.0.dist-info/WHEEL
+4
View File
@@ -0,0 +1,4 @@
Wheel-Version: 1.0
Generator: flit 3.10.1
Root-Is-Purelib: true
Tag: py3-none-any
venv/lib/python3.12/site-packages/blinker/__init__.py
+17
View File
@@ -0,0 +1,17 @@
from __future__ import annotations
from .base import ANY
from .base import default_namespace
from .base import NamedSignal
from .base import Namespace
from .base import Signal
from .base import signal
__all__ = [
"ANY",
"default_namespace",
"NamedSignal",
"Namespace",
"Signal",
"signal",
]
venv/lib/python3.12/site-packages/blinker/__pycache__/__init__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/blinker/__pycache__/_utilities.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/blinker/__pycache__/base.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/blinker/_utilities.py
+64
View File
@@ -0,0 +1,64 @@
from __future__ import annotations
import collections.abc as c
import inspect
import typing as t
from weakref import ref
from weakref import WeakMethod
T = t.TypeVar("T")
class Symbol:
"""A constant symbol, nicer than ``object()``. Repeated calls return the
same instance.
>>> Symbol('foo') is Symbol('foo')
True
>>> Symbol('foo')
foo
"""
symbols: t.ClassVar[dict[str, Symbol]] = {}
def __new__(cls, name: str) -> Symbol:
if name in cls.symbols:
return cls.symbols[name]
obj = super().__new__(cls)
cls.symbols[name] = obj
return obj
def __init__(self, name: str) -> None:
self.name = name
def __repr__(self) -> str:
return self.name
def __getnewargs__(self) -> tuple[t.Any, ...]:
return (self.name,)
def make_id(obj: object) -> c.Hashable:
"""Get a stable identifier for a receiver or sender, to be used as a dict
key or in a set.
"""
if inspect.ismethod(obj):
# The id of a bound method is not stable, but the id of the unbound
# function and instance are.
return id(obj.__func__), id(obj.__self__)
if isinstance(obj, (str, int)):
# Instances with the same value always compare equal and have the same
# hash, even if the id may change.
return obj
# Assume other types are not hashable but will always be the same instance.
return id(obj)
def make_ref(obj: T, callback: c.Callable[[ref[T]], None] | None = None) -> ref[T]:
if inspect.ismethod(obj):
return WeakMethod(obj, callback) # type: ignore[arg-type, return-value]
return ref(obj, callback)
venv/lib/python3.12/site-packages/blinker/base.py
+512
View File
@@ -0,0 +1,512 @@
from __future__ import annotations
import collections.abc as c
import sys
import typing as t
import weakref
from collections import defaultdict
from contextlib import contextmanager
from functools import cached_property
from inspect import iscoroutinefunction
from ._utilities import make_id
from ._utilities import make_ref
from ._utilities import Symbol
F = t.TypeVar("F", bound=c.Callable[..., t.Any])
ANY = Symbol("ANY")
"""Symbol for "any sender"."""
ANY_ID = 0
class Signal:
"""A notification emitter.
:param doc: The docstring for the signal.
"""
ANY = ANY
"""An alias for the :data:`~blinker.ANY` sender symbol."""
set_class: type[set[t.Any]] = set
"""The set class to use for tracking connected receivers and senders.
Python's ``set`` is unordered. If receivers must be dispatched in the order
they were connected, an ordered set implementation can be used.
.. versionadded:: 1.7
"""
@cached_property
def receiver_connected(self) -> Signal:
"""Emitted at the end of each :meth:`connect` call.
The signal sender is the signal instance, and the :meth:`connect`
arguments are passed through: ``receiver``, ``sender``, and ``weak``.
.. versionadded:: 1.2
"""
return Signal(doc="Emitted after a receiver connects.")
@cached_property
def receiver_disconnected(self) -> Signal:
"""Emitted at the end of each :meth:`disconnect` call.
The sender is the signal instance, and the :meth:`disconnect` arguments
are passed through: ``receiver`` and ``sender``.
This signal is emitted **only** when :meth:`disconnect` is called
explicitly. This signal cannot be emitted by an automatic disconnect
when a weakly referenced receiver or sender goes out of scope, as the
instance is no longer be available to be used as the sender for this
signal.
An alternative approach is available by subscribing to
:attr:`receiver_connected` and setting up a custom weakref cleanup
callback on weak receivers and senders.
.. versionadded:: 1.2
"""
return Signal(doc="Emitted after a receiver disconnects.")
def __init__(self, doc: str | None = None) -> None:
if doc:
self.__doc__ = doc
self.receivers: dict[
t.Any, weakref.ref[c.Callable[..., t.Any]] | c.Callable[..., t.Any]
] = {}
"""The map of connected receivers. Useful to quickly check if any
receivers are connected to the signal: ``if s.receivers:``. The
structure and data is not part of the public API, but checking its
boolean value is.
"""
self.is_muted: bool = False
self._by_receiver: dict[t.Any, set[t.Any]] = defaultdict(self.set_class)
self._by_sender: dict[t.Any, set[t.Any]] = defaultdict(self.set_class)
self._weak_senders: dict[t.Any, weakref.ref[t.Any]] = {}
def connect(self, receiver: F, sender: t.Any = ANY, weak: bool = True) -> F:
"""Connect ``receiver`` to be called when the signal is sent by
``sender``.
:param receiver: The callable to call when :meth:`send` is called with
the given ``sender``, passing ``sender`` as a positional argument
along with any extra keyword arguments.
:param sender: Any object or :data:`ANY`. ``receiver`` will only be
called when :meth:`send` is called with this sender. If ``ANY``, the
receiver will be called for any sender. A receiver may be connected
to multiple senders by calling :meth:`connect` multiple times.
:param weak: Track the receiver with a :mod:`weakref`. The receiver will
be automatically disconnected when it is garbage collected. When
connecting a receiver defined within a function, set to ``False``,
otherwise it will be disconnected when the function scope ends.
"""
receiver_id = make_id(receiver)
sender_id = ANY_ID if sender is ANY else make_id(sender)
if weak:
self.receivers[receiver_id] = make_ref(
receiver, self._make_cleanup_receiver(receiver_id)
)
else:
self.receivers[receiver_id] = receiver
self._by_sender[sender_id].add(receiver_id)
self._by_receiver[receiver_id].add(sender_id)
if sender is not ANY and sender_id not in self._weak_senders:
# store a cleanup for weakref-able senders
try:
self._weak_senders[sender_id] = make_ref(
sender, self._make_cleanup_sender(sender_id)
)
except TypeError:
pass
if "receiver_connected" in self.__dict__ and self.receiver_connected.receivers:
try:
self.receiver_connected.send(
self, receiver=receiver, sender=sender, weak=weak
)
except TypeError:
# TODO no explanation or test for this
self.disconnect(receiver, sender)
raise
return receiver
def connect_via(self, sender: t.Any, weak: bool = False) -> c.Callable[[F], F]:
"""Connect the decorated function to be called when the signal is sent
by ``sender``.
The decorated function will be called when :meth:`send` is called with
the given ``sender``, passing ``sender`` as a positional argument along
with any extra keyword arguments.
:param sender: Any object or :data:`ANY`. ``receiver`` will only be
called when :meth:`send` is called with this sender. If ``ANY``, the
receiver will be called for any sender. A receiver may be connected
to multiple senders by calling :meth:`connect` multiple times.
:param weak: Track the receiver with a :mod:`weakref`. The receiver will
be automatically disconnected when it is garbage collected. When
connecting a receiver defined within a function, set to ``False``,
otherwise it will be disconnected when the function scope ends.=
.. versionadded:: 1.1
"""
def decorator(fn: F) -> F:
self.connect(fn, sender, weak)
return fn
return decorator
@contextmanager
def connected_to(
self, receiver: c.Callable[..., t.Any], sender: t.Any = ANY
) -> c.Generator[None, None, None]:
"""A context manager that temporarily connects ``receiver`` to the
signal while a ``with`` block executes. When the block exits, the
receiver is disconnected. Useful for tests.
:param receiver: The callable to call when :meth:`send` is called with
the given ``sender``, passing ``sender`` as a positional argument
along with any extra keyword arguments.
:param sender: Any object or :data:`ANY`. ``receiver`` will only be
called when :meth:`send` is called with this sender. If ``ANY``, the
receiver will be called for any sender.
.. versionadded:: 1.1
"""
self.connect(receiver, sender=sender, weak=False)
try:
yield None
finally:
self.disconnect(receiver)
@contextmanager
def muted(self) -> c.Generator[None, None, None]:
"""A context manager that temporarily disables the signal. No receivers
will be called if the signal is sent, until the ``with`` block exits.
Useful for tests.
"""
self.is_muted = True
try:
yield None
finally:
self.is_muted = False
def send(
self,
sender: t.Any | None = None,
/,
*,
_async_wrapper: c.Callable[
[c.Callable[..., c.Coroutine[t.Any, t.Any, t.Any]]], c.Callable[..., t.Any]
]
| None = None,
**kwargs: t.Any,
) -> list[tuple[c.Callable[..., t.Any], t.Any]]:
"""Call all receivers that are connected to the given ``sender``
or :data:`ANY`. Each receiver is called with ``sender`` as a positional
argument along with any extra keyword arguments. Return a list of
``(receiver, return value)`` tuples.
The order receivers are called is undefined, but can be influenced by
setting :attr:`set_class`.
If a receiver raises an exception, that exception will propagate up.
This makes debugging straightforward, with an assumption that correctly
implemented receivers will not raise.
:param sender: Call receivers connected to this sender, in addition to
those connected to :data:`ANY`.
:param _async_wrapper: Will be called on any receivers that are async
coroutines to turn them into sync callables. For example, could run
the receiver with an event loop.
:param kwargs: Extra keyword arguments to pass to each receiver.
.. versionchanged:: 1.7
Added the ``_async_wrapper`` argument.
"""
if self.is_muted:
return []
results = []
for receiver in self.receivers_for(sender):
if iscoroutinefunction(receiver):
if _async_wrapper is None:
raise RuntimeError("Cannot send to a coroutine function.")
result = _async_wrapper(receiver)(sender, **kwargs)
else:
result = receiver(sender, **kwargs)
results.append((receiver, result))
return results
async def send_async(
self,
sender: t.Any | None = None,
/,
*,
_sync_wrapper: c.Callable[
[c.Callable[..., t.Any]], c.Callable[..., c.Coroutine[t.Any, t.Any, t.Any]]
]
| None = None,
**kwargs: t.Any,
) -> list[tuple[c.Callable[..., t.Any], t.Any]]:
"""Await all receivers that are connected to the given ``sender``
or :data:`ANY`. Each receiver is called with ``sender`` as a positional
argument along with any extra keyword arguments. Return a list of
``(receiver, return value)`` tuples.
The order receivers are called is undefined, but can be influenced by
setting :attr:`set_class`.
If a receiver raises an exception, that exception will propagate up.
This makes debugging straightforward, with an assumption that correctly
implemented receivers will not raise.
:param sender: Call receivers connected to this sender, in addition to
those connected to :data:`ANY`.
:param _sync_wrapper: Will be called on any receivers that are sync
callables to turn them into async coroutines. For example,
could call the receiver in a thread.
:param kwargs: Extra keyword arguments to pass to each receiver.
.. versionadded:: 1.7
"""
if self.is_muted:
return []
results = []
for receiver in self.receivers_for(sender):
if not iscoroutinefunction(receiver):
if _sync_wrapper is None:
raise RuntimeError("Cannot send to a non-coroutine function.")
result = await _sync_wrapper(receiver)(sender, **kwargs)
else:
result = await receiver(sender, **kwargs)
results.append((receiver, result))
return results
def has_receivers_for(self, sender: t.Any) -> bool:
"""Check if there is at least one receiver that will be called with the
given ``sender``. A receiver connected to :data:`ANY` will always be
called, regardless of sender. Does not check if weakly referenced
receivers are still live. See :meth:`receivers_for` for a stronger
search.
:param sender: Check for receivers connected to this sender, in addition
to those connected to :data:`ANY`.
"""
if not self.receivers:
return False
if self._by_sender[ANY_ID]:
return True
if sender is ANY:
return False
return make_id(sender) in self._by_sender
def receivers_for(
self, sender: t.Any
) -> c.Generator[c.Callable[..., t.Any], None, None]:
"""Yield each receiver to be called for ``sender``, in addition to those
to be called for :data:`ANY`. Weakly referenced receivers that are not
live will be disconnected and skipped.
:param sender: Yield receivers connected to this sender, in addition
to those connected to :data:`ANY`.
"""
# TODO: test receivers_for(ANY)
if not self.receivers:
return
sender_id = make_id(sender)
if sender_id in self._by_sender:
ids = self._by_sender[ANY_ID] | self._by_sender[sender_id]
else:
ids = self._by_sender[ANY_ID].copy()
for receiver_id in ids:
receiver = self.receivers.get(receiver_id)
if receiver is None:
continue
if isinstance(receiver, weakref.ref):
strong = receiver()
if strong is None:
self._disconnect(receiver_id, ANY_ID)
continue
yield strong
else:
yield receiver
def disconnect(self, receiver: c.Callable[..., t.Any], sender: t.Any = ANY) -> None:
"""Disconnect ``receiver`` from being called when the signal is sent by
``sender``.
:param receiver: A connected receiver callable.
:param sender: Disconnect from only this sender. By default, disconnect
from all senders.
"""
sender_id: c.Hashable
if sender is ANY:
sender_id = ANY_ID
else:
sender_id = make_id(sender)
receiver_id = make_id(receiver)
self._disconnect(receiver_id, sender_id)
if (
"receiver_disconnected" in self.__dict__
and self.receiver_disconnected.receivers
):
self.receiver_disconnected.send(self, receiver=receiver, sender=sender)
def _disconnect(self, receiver_id: c.Hashable, sender_id: c.Hashable) -> None:
if sender_id == ANY_ID:
if self._by_receiver.pop(receiver_id, None) is not None:
for bucket in self._by_sender.values():
bucket.discard(receiver_id)
self.receivers.pop(receiver_id, None)
else:
self._by_sender[sender_id].discard(receiver_id)
self._by_receiver[receiver_id].discard(sender_id)
def _make_cleanup_receiver(
self, receiver_id: c.Hashable
) -> c.Callable[[weakref.ref[c.Callable[..., t.Any]]], None]:
"""Create a callback function to disconnect a weakly referenced
receiver when it is garbage collected.
"""
def cleanup(ref: weakref.ref[c.Callable[..., t.Any]]) -> None:
# If the interpreter is shutting down, disconnecting can result in a
# weird ignored exception. Don't call it in that case.
if not sys.is_finalizing():
self._disconnect(receiver_id, ANY_ID)
return cleanup
def _make_cleanup_sender(
self, sender_id: c.Hashable
) -> c.Callable[[weakref.ref[t.Any]], None]:
"""Create a callback function to disconnect all receivers for a weakly
referenced sender when it is garbage collected.
"""
assert sender_id != ANY_ID
def cleanup(ref: weakref.ref[t.Any]) -> None:
self._weak_senders.pop(sender_id, None)
for receiver_id in self._by_sender.pop(sender_id, ()):
self._by_receiver[receiver_id].discard(sender_id)
return cleanup
def _cleanup_bookkeeping(self) -> None:
"""Prune unused sender/receiver bookkeeping. Not threadsafe.
Connecting & disconnecting leaves behind a small amount of bookkeeping
data. Typical workloads using Blinker, for example in most web apps,
Flask, CLI scripts, etc., are not adversely affected by this
bookkeeping.
With a long-running process performing dynamic signal routing with high
volume, e.g. connecting to function closures, senders are all unique
object instances. Doing all of this over and over may cause memory usage
to grow due to extraneous bookkeeping. (An empty ``set`` for each stale
sender/receiver pair.)
This method will prune that bookkeeping away, with the caveat that such
pruning is not threadsafe. The risk is that cleanup of a fully
disconnected receiver/sender pair occurs while another thread is
connecting that same pair. If you are in the highly dynamic, unique
receiver/sender situation that has lead you to this method, that failure
mode is perhaps not a big deal for you.
"""
for mapping in (self._by_sender, self._by_receiver):
for ident, bucket in list(mapping.items()):
if not bucket:
mapping.pop(ident, None)
def _clear_state(self) -> None:
"""Disconnect all receivers and senders. Useful for tests."""
self._weak_senders.clear()
self.receivers.clear()
self._by_sender.clear()
self._by_receiver.clear()
class NamedSignal(Signal):
"""A named generic notification emitter. The name is not used by the signal
itself, but matches the key in the :class:`Namespace` that it belongs to.
:param name: The name of the signal within the namespace.
:param doc: The docstring for the signal.
"""
def __init__(self, name: str, doc: str | None = None) -> None:
super().__init__(doc)
#: The name of this signal.
self.name: str = name
def __repr__(self) -> str:
base = super().__repr__()
return f"{base[:-1]}; {self.name!r}>" # noqa: E702
class Namespace(dict[str, NamedSignal]):
"""A dict mapping names to signals."""
def signal(self, name: str, doc: str | None = None) -> NamedSignal:
"""Return the :class:`NamedSignal` for the given ``name``, creating it
if required. Repeated calls with the same name return the same signal.
:param name: The name of the signal.
:param doc: The docstring of the signal.
"""
if name not in self:
self[name] = NamedSignal(name, doc)
return self[name]
class _PNamespaceSignal(t.Protocol):
def __call__(self, name: str, doc: str | None = None) -> NamedSignal: ...
default_namespace: Namespace = Namespace()
"""A default :class:`Namespace` for creating named signals. :func:`signal`
creates a :class:`NamedSignal` in this namespace.
"""
signal: _PNamespaceSignal = default_namespace.signal
"""Return a :class:`NamedSignal` in :data:`default_namespace` with the given
``name``, creating it if required. Repeated calls with the same name return the
same signal.
"""
venv/lib/python3.12/site-packages/blinker/py.typed
View File
venv/lib/python3.12/site-packages/certifi-2026.6.17.dist-info/INSTALLER
+1
View File
@@ -0,0 +1 @@
pip
venv/lib/python3.12/site-packages/certifi-2026.6.17.dist-info/METADATA
+78
View File
@@ -0,0 +1,78 @@
Metadata-Version: 2.4
Name: certifi
Version: 2026.6.17
Summary: Python package for providing Mozilla's CA Bundle.
Home-page: https://github.com/certifi/python-certifi
Author: Kenneth Reitz
Author-email: me@kennethreitz.com
License: MPL-2.0
Project-URL: Source, https://github.com/certifi/python-certifi
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
Classifier: Natural Language :: English
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Python: >=3.7
License-File: LICENSE
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-python
Dynamic: summary
Certifi: Python SSL Certificates
================================
Certifi provides Mozilla's carefully curated collection of Root Certificates for
validating the trustworthiness of SSL certificates while verifying the identity
of TLS hosts. It has been extracted from the `Requests`_ project.
Installation
------------
``certifi`` is available on PyPI. Simply install it with ``pip``::
$ pip install certifi
Usage
-----
To reference the installed certificate authority (CA) bundle, you can use the
built-in function::
>>> import certifi
>>> certifi.where()
'/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
Or from the command line::
$ python -m certifi
/usr/local/lib/python3.7/site-packages/certifi/cacert.pem
Enjoy!
.. _`Requests`: https://requests.readthedocs.io/en/latest/
Addition/Removal of Certificates
--------------------------------
Certifi does not support any addition/removal or other modification of the
CA trust store content. This project is intended to provide a reliable and
highly portable root of trust to python deployments. Look to upstream projects
for methods to use alternate trust.
venv/lib/python3.12/site-packages/certifi-2026.6.17.dist-info/RECORD
+14
View File
@@ -0,0 +1,14 @@
certifi-2026.6.17.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
certifi-2026.6.17.dist-info/METADATA,sha256=6hXAnt0a2el7xm2e9xvPuRCntZLjdKCkN81e47E0wN8,2474
certifi-2026.6.17.dist-info/RECORD,,
certifi-2026.6.17.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
certifi-2026.6.17.dist-info/licenses/LICENSE,sha256=6TcW2mucDVpKHfYP5pWzcPBpVgPSH2-D8FPkLPwQyvc,989
certifi-2026.6.17.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
certifi/__init__.py,sha256=-W1R_y8WCaSkT1tdjuxH_zTBZY1YH6xQgdN1nbBajOE,94
certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
certifi/__pycache__/__init__.cpython-312.pyc,,
certifi/__pycache__/__main__.cpython-312.pyc,,
certifi/__pycache__/core.cpython-312.pyc,,
certifi/cacert.pem,sha256=u8fpwB11UbuKFZtd7dmJuO484QWv9SK2jrGwG_hUyrA,234354
certifi/core.py,sha256=XFXycndG5pf37ayeF8N32HUuDafsyhkVMbO4BAPWHa0,3394
certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
venv/lib/python3.12/site-packages/certifi-2026.6.17.dist-info/WHEEL
+5
View File
@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: setuptools (82.0.1)
Root-Is-Purelib: true
Tag: py3-none-any
venv/lib/python3.12/site-packages/certifi-2026.6.17.dist-info/licenses/LICENSE
+20
View File
@@ -0,0 +1,20 @@
This package contains a modified version of ca-bundle.crt:
ca-bundle.crt -- Bundle of CA Root Certificates
This is a bundle of X.509 certificates of public Certificate Authorities
(CA). These were automatically extracted from Mozilla's root certificates
file (certdata.txt). This file can be found in the mozilla source tree:
https://hg.mozilla.org/mozilla-central/file/tip/security/nss/lib/ckfw/builtins/certdata.txt
It contains the certificates in PEM format and therefore
can be directly used with curl / libcurl / php_curl, or with
an Apache+mod_ssl webserver for SSL client authentication.
Just configure this file as the SSLCACertificateFile.#
***** BEGIN LICENSE BLOCK *****
This Source Code Form is subject to the terms of the Mozilla Public License,
v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
one at http://mozilla.org/MPL/2.0/.
***** END LICENSE BLOCK *****
@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $
venv/lib/python3.12/site-packages/certifi-2026.6.17.dist-info/top_level.txt
+1
View File
@@ -0,0 +1 @@
certifi
venv/lib/python3.12/site-packages/certifi/__init__.py
+4
View File
@@ -0,0 +1,4 @@
from .core import contents, where
__all__ = ["contents", "where"]
__version__ = "2026.06.17"
venv/lib/python3.12/site-packages/certifi/__main__.py
+12
View File
@@ -0,0 +1,12 @@
import argparse
from certifi import contents, where
parser = argparse.ArgumentParser()
parser.add_argument("-c", "--contents", action="store_true")
args = parser.parse_args()
if args.contents:
print(contents())
else:
print(where())
venv/lib/python3.12/site-packages/certifi/__pycache__/__init__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/certifi/__pycache__/__main__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/certifi/__pycache__/core.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/certifi/cacert.pem
+3863
View File
File diff suppressed because it is too large Load Diff
venv/lib/python3.12/site-packages/certifi/core.py
+83
View File
@@ -0,0 +1,83 @@
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem or its contents.
"""
import sys
import atexit
def exit_cacert_ctx() -> None:
_CACERT_CTX.__exit__(None, None, None) # type: ignore[union-attr]
if sys.version_info >= (3, 11):
from importlib.resources import as_file, files
_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 = as_file(files("certifi").joinpath("cacert.pem"))
_CACERT_PATH = str(_CACERT_CTX.__enter__())
atexit.register(exit_cacert_ctx)
return _CACERT_PATH
def contents() -> str:
return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
else:
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("certifi", "cacert.pem")
_CACERT_PATH = str(_CACERT_CTX.__enter__())
atexit.register(exit_cacert_ctx)
return _CACERT_PATH
def contents() -> str:
return read_text("certifi", "cacert.pem", encoding="ascii")
venv/lib/python3.12/site-packages/certifi/py.typed
View File
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/INSTALLER
+1
View File
@@ -0,0 +1 @@
pip
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/METADATA
+827
View File
@@ -0,0 +1,827 @@
Metadata-Version: 2.4
Name: charset-normalizer
Version: 3.4.9
Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
Author-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
Maintainer-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
License: MIT
Project-URL: Changelog, https://github.com/jawah/charset_normalizer/blob/master/CHANGELOG.md
Project-URL: Documentation, https://charset-normalizer.readthedocs.io/
Project-URL: Code, https://github.com/jawah/charset_normalizer
Project-URL: Issue tracker, https://github.com/jawah/charset_normalizer/issues
Keywords: encoding,charset,charset-detector,detector,normalization,unicode,chardet,detect
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Programming Language :: Python :: Free Threading :: 4 - Resilient
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Typing :: Typed
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode-backport
Dynamic: license-file
<h1 align="center">Charset Detection, for Everyone 👋</h1>
<p align="center">
<sup>The Real First Universal Charset Detector</sup><br>
<a href="https://pypi.org/project/charset-normalizer">
<img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
</a>
<a href="https://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://static.pepy.tech/badge/charset-normalizer/month" />
</a>
<a href="https://bestpractices.coreinfrastructure.org/projects/7297">
<img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
</a>
</p>
<p align="center">
<sup><i>Featured Packages</i></sup><br>
<a href="https://github.com/jawah/niquests">
<img alt="Static Badge" src="https://img.shields.io/badge/Niquests-Most_Advanced_HTTP_Client-cyan">
</a>
<a href="https://github.com/jawah/wassima">
<img alt="Static Badge" src="https://img.shields.io/badge/Wassima-Certifi_Replacement-cyan">
</a>
</p>
<p align="center">
<sup><i>In other language (unofficial port - by the community)</i></sup><br>
<a href="https://github.com/nickspring/charset-normalizer-rs">
<img alt="Static Badge" src="https://img.shields.io/badge/Rust-red">
</a>
</p>
> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
> I'm trying to resolve the issue by taking a new approach.
> All IANA character set names for which the Python core library provides codecs are supported.
> You can also register your own set of codecs, and yes, it would work as-is.
This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
| Feature | [Chardet](https://github.com/chardet/chardet) | Charset Normalizer | [cChardet](https://github.com/PyYoshi/cChardet) |
|--------------------------------------------------|:---------------------------------------------:|:-----------------------------------------------------------------------------------------------:|:-----------------------------------------------:|
| `Fast` | ✅ | ✅ | ✅ |
| `Universal`[^1] | ❌ | ✅ | ❌ |
| `Reliable` **without** distinguishable standards | ✅ | ✅ | ✅ |
| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
| `License` | _Disputed_[^2]<br>_restrictive_ | MIT | MPL-1.1<br>_restrictive_ |
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ✅ | ✅ | N/A |
| `UnicodeDecodeError Safety` | ✅ | ✅ | ❌ |
| `Whl Size (min)` | 500 kB | 150 kB | ~200 kB |
| `Supported Encoding` | 99 | [99](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) | 40 |
| `Can register custom encoding` | ❌ | ✅ | ❌ |
<p align="center">
<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
</p>
[^1]: They are clearly using specific code for a specific encoding even if covering most of used one.
[^2]: Chardet 7.0+ was relicensed from LGPL-2.1 to MIT following an AI-assisted rewrite. This relicensing is disputed on two independent grounds: **(a)** the original author [contests](https://github.com/chardet/chardet/issues/327) that the maintainer had the right to relicense, arguing the rewrite is a derivative work of the LGPL-licensed codebase since it was not a clean room implementation; **(b)** the copyright claim itself is [questionable](https://github.com/chardet/chardet/issues/334) given the code was primarily generated by an LLM, and AI-generated output may not be copyrightable under most jurisdictions. Either issue alone could undermine the MIT license. Beyond licensing, the rewrite raises questions about responsible use of AI in open source: key architectural ideas pioneered by charset-normalizer - notably decode-first validity filtering (our foundational approach since v1) and encoding pairwise similarity with the same algorithm and threshold — surfaced in chardet 7 without acknowledgment. The project also imported test files from charset-normalizer to train and benchmark against it, then claimed superior accuracy on those very files. Charset-normalizer has always been MIT-licensed, encoding-agnostic by design, and built on a verifiable human-authored history.
## ⚡ Performance
This package offer better performances against Chardet. Here are some numbers.
| Package | Accuracy | Mean per file (ms) | File per sec (est) |
|---------------------------------------------------|:--------:|:------------------:|:------------------:|
| [chardet 7.4](https://github.com/chardet/chardet) | 89 % | 3 ms | 333 file/sec |
| charset-normalizer | **97 %** | 1 ms | 1000 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
|---------------------------------------------------|:---------------:|:---------------:|:---------------:|
| [chardet 7.4](https://github.com/chardet/chardet) | 28 ms | 16 ms | < 1 ms |
| charset-normalizer | 8 ms | 5 ms | 1 ms |
_updated as of July 2026 using CPython 3.12, Charset-Normalizer 3.4.8, and Chardet 7.4.3_
~Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.~ No longer the case since Chardet 7.0+
> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
> And yes, these results might change at any time. The dataset can be updated to include more files.
> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
> Chardet claims on his documentation to have a greater accuracy than us based on the dataset they trained Chardet on(...)
> Well, it's normal, the opposite would have been worrying. Whereas charset-normalizer don't train on anything, our solution
> is based on a completely different algorithm, still heuristic through, it does not need weights across every encoding tables.
## ✨ Installation
Using pip:
```sh
pip install charset-normalizer -U
```
## 🚀 Basic Usage
### CLI
This package comes with a CLI.
```
usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
file [file ...]
The Real First Universal Charset Detector. Discover originating encoding used
on text file. Normalize text to unicode.
positional arguments:
files File(s) to be analysed
optional arguments:
-h, --help show this help message and exit
-v, --verbose Display complementary information about file if any.
Stdout will contain logs about the detection process.
-a, --with-alternative
Output complementary possibilities if any. Top-level
JSON WILL be a list.
-n, --normalize Permit to normalize input file. If not set, program
does not write anything.
-m, --minimal Only output the charset detected to STDOUT. Disabling
JSON output.
-r, --replace Replace file when trying to normalize it instead of
creating a new one.
-f, --force Replace file without asking if you are sure, use this
flag with caution.
-t THRESHOLD, --threshold THRESHOLD
Define a custom maximum amount of chaos allowed in
decoded content. 0. <= chaos <= 1.
--version Show version information and exit.
```
```bash
normalizer ./data/sample.1.fr.srt
```
or
```bash
python -m charset_normalizer ./data/sample.1.fr.srt
```
🎉 Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
```json
{
"path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
"encoding": "cp1252",
"encoding_aliases": [
"1252",
"windows_1252"
],
"alternative_encodings": [
"cp1254",
"cp1256",
"cp1258",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
"mbcs"
],
"language": "French",
"alphabets": [
"Basic Latin",
"Latin-1 Supplement"
],
"has_sig_or_bom": false,
"chaos": 0.149,
"coherence": 97.152,
"unicode_path": null,
"is_preferred": true
}
```
### Python
*Just print out normalized text*
```python
from charset_normalizer import from_path
results = from_path('./my_subtitle.srt')
print(str(results.best()))
```
*Upgrade your code without effort*
```python
from charset_normalizer import detect
```
The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
## 😇 Why
When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
reliable alternative using a completely different method. Also! I never back down on a good challenge!
I **don't care** about the **originating charset** encoding, because **two different tables** can
produce **two identical rendered string.**
What I want is to get readable text, the best I can.
In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair Unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
## 🍰 How
- Discard all charset encoding table that could not fit the binary content.
- Measure noise, or the mess once opened (by chunks) with a corresponding charset encoding.
- Extract matches with the lowest mess detected.
- Additionally, we measure coherence / probe for a language.
**Wait a minute**, what is noise/mess and coherence according to **YOU ?**
*Noise :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
**I established** some ground rules about **what is obvious** when **it seems like** a mess (aka. defining noise in rendered text).
I know that my interpretation of what is noise is probably incomplete, feel free to contribute in order to
improve or rewrite it.
*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
## ⚡ Known limitations
- Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
- Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
## ⚠️ About Python EOLs
**If you are running:**
- Python >=2.7,<3.5: Unsupported
- Python 3.5: charset-normalizer < 2.1
- Python 3.6: charset-normalizer < 3.1
Upgrade your Python interpreter as soon as possible.
## 👤 Contributing
Contributions, issues and feature requests are very much welcome.<br />
Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
## 📝 License
Copyright © [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)
## 💼 For Enterprise
Professional support for charset-normalizer is available as part of the [Tidelift
Subscription][1]. Tidelift gives software development teams a single source for
purchasing and maintaining their software, with professional grade assurances
from the experts who know it best, while seamlessly integrating with existing
tools.
[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/7297/badge)](https://www.bestpractices.dev/projects/7297)
# Changelog
All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [3.4.9](https://github.com/Ousret/charset_normalizer/compare/3.4.8...3.4.9) (2026-07-07)
### Fixed
- Regression in our fallback path leading to a decode error. (#771)
We've yanked 3.4.8 as a result of that bug.
## [3.4.8](https://github.com/Ousret/charset_normalizer/compare/3.4.7...3.4.8) (2026-07-06)
### Fixed
- Wall import time due to cascade codec imports for our multibyte first sort of iana supported codecs (#742)
- Unnecessary json import at runtime (#753)
- Inverse capitalization not seen by noise detector (#731)
### Changed
- No longer holding a global cache for our noise / coherence measurements. Relax RSS memory usage.
- Micro-optimizations in our noise / coherence measurements.
- No longer using regex search by default for our preemptive charset mark algorithm.
- Raised upperbound of setuptools to v83.
- Raised upperbound of mypy(c) to v2.1.
### Removed
- Redundant UTF7 BOM marker (#730)
## [3.4.7](https://github.com/Ousret/charset_normalizer/compare/3.4.6...3.4.7) (2026-04-02)
### Changed
- Pre-built optimized version using mypy[c] v1.20.
- Relax `setuptools` constraint to `setuptools>=68,<82.1`.
### Fixed
- Correctly remove SIG remnant in utf-7 decoded string. (#718) (#716)
## [3.4.6](https://github.com/Ousret/charset_normalizer/compare/3.4.5...3.4.6) (2026-03-15)
### Changed
- Flattened the logic in `charset_normalizer.md` for higher performance. Removed `eligible(..)` and `feed(...)`
in favor of `feed_info(...)`.
- Raised upper bound for mypy[c] to 1.20, for our optimized version.
- Updated `UNICODE_RANGES_COMBINED` using Unicode blocks v17.
### Fixed
- Edge case where noise difference between two candidates can be almost insignificant. (#672)
- CLI `--normalize` writing to wrong path when passing multiple files in. (#702)
### Misc
- Freethreaded pre-built wheels now shipped in PyPI starting with 3.14t. (#616)
## [3.4.5](https://github.com/Ousret/charset_normalizer/compare/3.4.4...3.4.5) (2026-03-06)
### Changed
- Update `setuptools` constraint to `setuptools>=68,<=82`.
- Raised upper bound of mypyc for the optional pre-built extension to v1.19.1
### Fixed
- Add explicit link to lib math in our optimized build. (#692)
- Logger level not restored correctly for empty byte sequences. (#701)
- TypeError when passing bytearray to from_bytes. (#703)
### Misc
- Applied safe micro-optimizations in both our noise detector and language detector.
- Rewrote the `query_yes_no` function (inside CLI) to avoid using ambiguous licensed code.
- Added `cd.py` submodule into mypyc optional compilation to reduce further the performance impact.
## [3.4.4](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.4) (2025-10-13)
### Changed
- Bound `setuptools` to a specific constraint `setuptools>=68,<=81`.
- Raised upper bound of mypyc for the optional pre-built extension to v1.18.2
### Removed
- `setuptools-scm` as a build dependency.
### Misc
- Enforced hashes in `dev-requirements.txt` and created `ci-requirements.txt` for security purposes.
- Additional pre-built wheels for riscv64, s390x, and armv7l architectures.
- Restore ` multiple.intoto.jsonl` in GitHub releases in addition to individual attestation file per wheel.
## [3.4.3](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.3) (2025-08-09)
### Changed
- mypy(c) is no longer a required dependency at build time if `CHARSET_NORMALIZER_USE_MYPYC` isn't set to `1`. (#595) (#583)
- automatically lower confidence on small bytes samples that are not Unicode in `detect` output legacy function. (#391)
### Added
- Custom build backend to overcome inability to mark mypy as an optional dependency in the build phase.
- Support for Python 3.14
### Fixed
- sdist archive contained useless directories.
- automatically fallback on valid UTF-16 or UTF-32 even if the md says it's noisy. (#633)
### Misc
- SBOM are automatically published to the relevant GitHub release to comply with regulatory changes.
Each published wheel comes with its SBOM. We choose CycloneDX as the format.
- Prebuilt optimized wheel are no longer distributed by default for CPython 3.7 due to a change in cibuildwheel.
## [3.4.2](https://github.com/Ousret/charset_normalizer/compare/3.4.1...3.4.2) (2025-05-02)
### Fixed
- Addressed the DeprecationWarning in our CLI regarding `argparse.FileType` by backporting the target class into the package. (#591)
- Improved the overall reliability of the detector with CJK Ideographs. (#605) (#587)
### Changed
- Optional mypyc compilation upgraded to version 1.15 for Python >= 3.8
## [3.4.1](https://github.com/Ousret/charset_normalizer/compare/3.4.0...3.4.1) (2024-12-24)
### Changed
- Project metadata are now stored using `pyproject.toml` instead of `setup.cfg` using setuptools as the build backend.
- Enforce annotation delayed loading for a simpler and consistent types in the project.
- Optional mypyc compilation upgraded to version 1.14 for Python >= 3.8
### Added
- pre-commit configuration.
- noxfile.
### Removed
- `build-requirements.txt` as per using `pyproject.toml` native build configuration.
- `bin/integration.py` and `bin/serve.py` in favor of downstream integration test (see noxfile).
- `setup.cfg` in favor of `pyproject.toml` metadata configuration.
- Unused `utils.range_scan` function.
### Fixed
- Converting content to Unicode bytes may insert `utf_8` instead of preferred `utf-8`. (#572)
- Deprecation warning "'count' is passed as positional argument" when converting to Unicode bytes on Python 3.13+
## [3.4.0](https://github.com/Ousret/charset_normalizer/compare/3.3.2...3.4.0) (2024-10-08)
### Added
- Argument `--no-preemptive` in the CLI to prevent the detector to search for hints.
- Support for Python 3.13 (#512)
### Fixed
- Relax the TypeError exception thrown when trying to compare a CharsetMatch with anything else than a CharsetMatch.
- Improved the general reliability of the detector based on user feedbacks. (#520) (#509) (#498) (#407) (#537)
- Declared charset in content (preemptive detection) not changed when converting to utf-8 bytes. (#381)
## [3.3.2](https://github.com/Ousret/charset_normalizer/compare/3.3.1...3.3.2) (2023-10-31)
### Fixed
- Unintentional memory usage regression when using large payload that match several encoding (#376)
- Regression on some detection case showcased in the documentation (#371)
### Added
- Noise (md) probe that identify malformed arabic representation due to the presence of letters in isolated form (credit to my wife)
## [3.3.1](https://github.com/Ousret/charset_normalizer/compare/3.3.0...3.3.1) (2023-10-22)
### Changed
- Optional mypyc compilation upgraded to version 1.6.1 for Python >= 3.8
- Improved the general detection reliability based on reports from the community
## [3.3.0](https://github.com/Ousret/charset_normalizer/compare/3.2.0...3.3.0) (2023-09-30)
### Added
- Allow to execute the CLI (e.g. normalizer) through `python -m charset_normalizer.cli` or `python -m charset_normalizer`
- Support for 9 forgotten encoding that are supported by Python but unlisted in `encoding.aliases` as they have no alias (#323)
### Removed
- (internal) Redundant utils.is_ascii function and unused function is_private_use_only
- (internal) charset_normalizer.assets is moved inside charset_normalizer.constant
### Changed
- (internal) Unicode code blocks in constants are updated using the latest v15.0.0 definition to improve detection
- Optional mypyc compilation upgraded to version 1.5.1 for Python >= 3.8
### Fixed
- Unable to properly sort CharsetMatch when both chaos/noise and coherence were close due to an unreachable condition in \_\_lt\_\_ (#350)
## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
### Changed
- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
- Minor improvement over the global detection reliability
### Added
- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
- Explicit support for Python 3.12
### Fixed
- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
### Added
- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
### Removed
- Support for Python 3.6 (PR #260)
### Changed
- Optional speedup provided by mypy/c 1.0.1
## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
### Fixed
- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
### Changed
- Speedup provided by mypy/c 0.990 on Python >= 3.7
## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
- Sphinx warnings when generating the documentation
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
### Added
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Removed
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
### Fixed
- Sphinx warnings when generating the documentation
## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
### Changed
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Removed
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
### Deprecated
- Function `normalize` scheduled for removal in 3.0
### Changed
- Removed useless call to decode in fn is_unprintable (#206)
### Fixed
- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
### Added
- Output the Unicode table version when running the CLI with `--version` (PR #194)
### Changed
- Reuse decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
### Fixed
- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
### Removed
- Support for Python 3.5 (PR #192)
### Deprecated
- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
### Fixed
- ASCII miss-detection on rare cases (PR #170)
## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
### Added
- Explicit support for Python 3.11 (PR #164)
### Changed
- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
### Fixed
- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
### Changed
- Skipping the language-detection (CD) on ASCII (PR #155)
## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
### Changed
- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
### Fixed
- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
### Changed
- Improvement over Vietnamese detection (PR #126)
- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
- Code style as refactored by Sourcery-AI (PR #131)
- Minor adjustment on the MD around european words (PR #133)
- Remove and replace SRTs from assets / tests (PR #139)
- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
### Fixed
- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
- Avoid using too insignificant chunk (PR #137)
### Added
- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
### Added
- Add support for Kazakh (Cyrillic) language detection (PR #109)
### Changed
- Further, improve inferring the language from a given single-byte code page (PR #112)
- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
- Various detection improvement (MD+CD) (PR #117)
### Removed
- Remove redundant logging entry about detected language(s) (PR #115)
### Fixed
- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
### Fixed
- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
- Fix CLI crash when using --minimal output in certain cases (PR #103)
### Changed
- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
### Changed
- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
- The Unicode detection is slightly improved (PR #93)
- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
### Removed
- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
### Fixed
- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
- The MANIFEST.in was not exhaustive (PR #78)
## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
### Fixed
- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
- Submatch factoring could be wrong in rare edge cases (PR #72)
- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
- Fix line endings from CRLF to LF for certain project files (PR #67)
### Changed
- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
- Allow fallback on specified encoding if any (PR #71)
## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
### Changed
- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
### Fixed
- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59)
### Changed
- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
### Fixed
- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
### Changed
- Public function normalize default args values were not aligned with from_bytes (PR #53)
### Added
- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
### Changed
- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
- Accent has been made on UTF-8 detection, should perform rather instantaneous.
- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
- utf_7 detection has been reinstated.
### Removed
- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
- The exception hook on UnicodeDecodeError has been removed.
### Deprecated
- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
### Fixed
- The CLI output used the relative path of the file(s). Should be absolute.
## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
### Fixed
- Logger configuration/usage no longer conflict with others (PR #44)
## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
### Removed
- Using standard logging instead of using the package loguru.
- Dropping nose test framework in favor of the maintained pytest.
- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
- Stop support for UTF-7 that does not contain a SIG.
- Dropping PrettyTable, replaced with pure JSON output in CLI.
### Fixed
- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
- Not searching properly for the BOM when trying utf32/16 parent codec.
### Changed
- Improving the package final size by compressing frequencies.json.
- Huge improvement over the larges payload.
### Added
- CLI now produces JSON consumable output.
- Return ASCII if given sequences fit. Given reasonable confidence.
## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
### Fixed
- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
### Fixed
- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
### Fixed
- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
### Changed
- Amend the previous release to allow prettytable 2.0 (PR #35)
## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
### Fixed
- Fix error while using the package with a python pre-release interpreter (PR #33)
### Changed
- Dependencies refactoring, constraints revised.
### Added
- Add python 3.9 and 3.10 to the supported interpreters
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/RECORD
+36
View File
@@ -0,0 +1,36 @@
../../../bin/normalizer,sha256=g0IlkIjn1xmaIFNjQj1k40XlzyG1Hj51rQ1SX3MF8BY,277
ada92cb5d92a588d1b93__mypyc.cpython-312-x86_64-linux-gnu.so,sha256=aIdLxZY-RSJ2C4KiLW5ye2ucy6X1_pw77SdPSlhVZyI,457584
charset_normalizer-3.4.9.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-3.4.9.dist-info/METADATA,sha256=DdPeF2CbDbZL0dRkPFvQ3TW16zxb53-LF7wZDy9KKsA,41678
charset_normalizer-3.4.9.dist-info/RECORD,,
charset_normalizer-3.4.9.dist-info/WHEEL,sha256=kPfBHUCXEMd9_xazqE-bWrrpnGTuP83yeVdC3i0eh6U,190
charset_normalizer-3.4.9.dist-info/entry_points.txt,sha256=ADSTKrkXZ3hhdOVFi6DcUEHQRS0xfxDIE_pEz4wLIXA,65
charset_normalizer-3.4.9.dist-info/licenses/LICENSE,sha256=bQ1Bv-FwrGx9wkjJpj4lTQ-0WmDVCoJX0K-SxuJJuIc,1071
charset_normalizer-3.4.9.dist-info/top_level.txt,sha256=y65Zf_GLs5FHscGHzcUTGAldXcp5mEVXbh8Mo0ZlmWs,47
charset_normalizer/__init__.py,sha256=OKRxRv2Zhnqk00tqkN0c1BtJjm165fWXLydE52IKuHc,1590
charset_normalizer/__main__.py,sha256=yzYxMR-IhKRHYwcSlavEv8oGdwxsR89mr2X09qXGdps,109
charset_normalizer/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/__pycache__/__main__.cpython-312.pyc,,
charset_normalizer/__pycache__/api.cpython-312.pyc,,
charset_normalizer/__pycache__/cd.cpython-312.pyc,,
charset_normalizer/__pycache__/constant.cpython-312.pyc,,
charset_normalizer/__pycache__/legacy.cpython-312.pyc,,
charset_normalizer/__pycache__/md.cpython-312.pyc,,
charset_normalizer/__pycache__/models.cpython-312.pyc,,
charset_normalizer/__pycache__/utils.cpython-312.pyc,,
charset_normalizer/__pycache__/version.cpython-312.pyc,,
charset_normalizer/api.py,sha256=kXhFlZNMi6_p0YhbTeGTswoK_DZ6oeAdprPxE8F4yfM,42325
charset_normalizer/cd.cpython-312-x86_64-linux-gnu.so,sha256=R9WQd3NirBV0quIUAT8Kr7kQ_h2EqUb94KGDOxFxxV4,16040
charset_normalizer/cd.py,sha256=6dJOZvd0rrEEWvkx54kAEy9qAP_uIuiWMAi5wX8OZsY,15980
charset_normalizer/cli/__init__.py,sha256=D8I86lFk2-py45JvqxniTirSj_sFyE6sjaY_0-G1shc,136
charset_normalizer/cli/__main__.py,sha256=NPK3yYAkXXE7Uvs6IqijkgZzS6G6fguRFuKXzgpf8Uc,11949
charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc,,
charset_normalizer/constant.py,sha256=vp9HvaompccS71BXPZk8lVahonkPbBpeVE3NzKZe2sk,44624
charset_normalizer/legacy.py,sha256=bgkdEvubTCOPlMKOzuENXHMiarh36VaGbRvWSlIr1KA,2651
charset_normalizer/md.cpython-312-x86_64-linux-gnu.so,sha256=1NCejiMAxx7khs9xwL4V2f-dahqGXknNz304xK9TJbY,16040
charset_normalizer/md.py,sha256=bwD18o2xLkGxBkuM1HPnYULsLBzNVe09j727Tng2tJw,32641
charset_normalizer/models.py,sha256=BAYguAENiSKBb7mf3DKzY3qgqjrjBeP0dySCmQSieXE,12830
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=fMCjgJXzMFegyO-gX-NElZi1rmdF1y1xax2Y-V2eudo,13537
charset_normalizer/version.py,sha256=FUQoaRCvGW_xwCoesgsGTwzekLTlCkAJr7diNpv-gPI,115
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/WHEEL
+7
View File
@@ -0,0 +1,7 @@
Wheel-Version: 1.0
Generator: setuptools (83.0.0)
Root-Is-Purelib: false
Tag: cp312-cp312-manylinux_2_17_x86_64
Tag: cp312-cp312-manylinux2014_x86_64
Tag: cp312-cp312-manylinux_2_28_x86_64
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/entry_points.txt
+2
View File
@@ -0,0 +1,2 @@
[console_scripts]
normalizer = charset_normalizer.cli:cli_detect
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/licenses/LICENSE
+21
View File
@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
venv/lib/python3.12/site-packages/charset_normalizer-3.4.9.dist-info/top_level.txt
+2
View File
@@ -0,0 +1,2 @@
ada92cb5d92a588d1b93__mypyc
charset_normalizer
venv/lib/python3.12/site-packages/charset_normalizer/__init__.py
+48
View File
@@ -0,0 +1,48 @@
"""
Charset-Normalizer
~~~~~~~~~~~~~~
The Real First Universal Charset Detector.
A library that helps you read text from an unknown charset encoding.
Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
All IANA character set names for which the Python core library provides codecs are supported.
Basic usage:
>>> from charset_normalizer import from_bytes
>>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
>>> best_guess = results.best()
>>> str(best_guess)
'Bсеки човек има право на образование. Oбразованието!'
Others methods and usages are available - see the full documentation
at <https://github.com/Ousret/charset_normalizer>.
:copyright: (c) 2021 by Ahmed TAHRI
:license: MIT, see LICENSE for more details.
"""
from __future__ import annotations
import logging
from .api import from_bytes, from_fp, from_path, is_binary
from .legacy import detect
from .models import CharsetMatch, CharsetMatches
from .utils import set_logging_handler
from .version import VERSION, __version__
__all__ = (
"from_fp",
"from_path",
"from_bytes",
"is_binary",
"detect",
"CharsetMatch",
"CharsetMatches",
"__version__",
"VERSION",
"set_logging_handler",
)
# Attach a NullHandler to the top level logger by default
# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())
venv/lib/python3.12/site-packages/charset_normalizer/__main__.py
+6
View File
@@ -0,0 +1,6 @@
from __future__ import annotations
from .cli import cli_detect
if __name__ == "__main__":
cli_detect()
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/__init__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/__main__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/api.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/cd.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/constant.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/legacy.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/md.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/models.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/utils.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/version.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/api.py
+1065
View File
File diff suppressed because it is too large Load Diff
venv/lib/python3.12/site-packages/charset_normalizer/cd.cpython-312-x86_64-linux-gnu.so
Executable
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/cd.py
+467
View File
@@ -0,0 +1,467 @@
from __future__ import annotations
import importlib
from codecs import IncrementalDecoder
from functools import lru_cache
from .constant import (
FREQUENCIES,
KO_NAMES,
LANGUAGE_SUPPORTED_COUNT,
TOO_SMALL_SEQUENCE,
ZH_NAMES,
_FREQUENCIES_SET,
_FREQUENCIES_RANK,
)
from .md import _ASCII_CHAR_INFO, _char_info, is_suspiciously_successive_range
from .models import CoherenceMatches
from .utils import (
is_multi_byte_encoding,
is_unicode_range_secondary,
)
def encoding_unicode_range(iana_name: str) -> list[str]:
"""
Return associated unicode ranges in a single byte code page.
"""
if is_multi_byte_encoding(iana_name):
raise OSError( # Defensive:
"Function not supported on multi-byte code page"
)
decoder = importlib.import_module(f"encodings.{iana_name}").IncrementalDecoder
p: IncrementalDecoder = decoder(errors="ignore")
seen_ranges: dict[str, int] = {}
character_count: int = 0
for i in range(0x40, 0xFF):
chunk: str = p.decode(bytes([i]))
if chunk:
chunk_codepoint = ord(chunk)
character_range: str | None = (
_ASCII_CHAR_INFO[chunk_codepoint].range
if chunk_codepoint < 128
else _char_info(chunk).range
)
if character_range is None:
continue
if not is_unicode_range_secondary(character_range):
if character_range not in seen_ranges:
seen_ranges[character_range] = 0
seen_ranges[character_range] += 1
character_count += 1
return sorted(
[
character_range
for character_range in seen_ranges
if seen_ranges[character_range] / character_count >= 0.15
]
)
def unicode_range_languages(primary_range: str) -> list[str]:
"""
Return inferred languages used with a unicode range.
"""
languages: list[str] = []
for language, characters in FREQUENCIES.items():
for character in characters:
codepoint = ord(character)
info = (
_ASCII_CHAR_INFO[codepoint]
if codepoint < 128
else _char_info(character)
)
if info.range == primary_range:
languages.append(language)
break
return languages
@lru_cache()
def encoding_languages(iana_name: str) -> list[str]:
"""
Single-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
try:
unicode_ranges: list[str] = encoding_unicode_range(iana_name)
except ImportError: # Defensive: encoding unavailable on this build.
return []
primary_range: str | None = None
for specified_range in unicode_ranges:
if "Latin" not in specified_range:
primary_range = specified_range
break
if primary_range is None:
return ["Latin Based"]
return unicode_range_languages(primary_range)
@lru_cache()
def mb_encoding_languages(iana_name: str) -> list[str]:
"""
Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
if (
iana_name.startswith("shift_")
or iana_name.startswith("iso2022_jp")
or iana_name.startswith("euc_j")
or iana_name == "cp932"
):
return ["Japanese"]
if iana_name.startswith("gb") or iana_name in ZH_NAMES:
return ["Chinese"]
if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES:
return ["Korean"]
return []
@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT)
def get_target_features(language: str) -> tuple[bool, bool]:
"""
Determine main aspects from a supported language if it contains accents and if is pure Latin.
"""
target_have_accents: bool = False
target_pure_latin: bool = True
for character in FREQUENCIES[language]:
codepoint = ord(character)
info = _ASCII_CHAR_INFO[codepoint] if codepoint < 128 else _char_info(character)
if not target_have_accents and info.accentuated:
target_have_accents = True
if target_pure_latin and not info.latin:
target_pure_latin = False
return target_have_accents, target_pure_latin
def alphabet_languages(
characters: list[str], ignore_non_latin: bool = False
) -> list[str]:
"""
Return associated languages associated to given characters.
"""
languages: list[tuple[str, float]] = []
characters_set: frozenset[str] = frozenset(characters)
source_have_accents = False
for character in characters:
codepoint = ord(character)
info = _ASCII_CHAR_INFO[codepoint] if codepoint < 128 else _char_info(character)
if info.accentuated:
source_have_accents = True
break
for language, language_characters in FREQUENCIES.items():
target_have_accents, target_pure_latin = get_target_features(language)
if ignore_non_latin and not target_pure_latin:
continue
if not target_have_accents and source_have_accents:
continue
character_count: int = len(language_characters)
character_match_count: int = len(_FREQUENCIES_SET[language] & characters_set)
ratio: float = character_match_count / character_count
if ratio >= 0.2:
languages.append((language, ratio))
languages = sorted(languages, key=lambda x: x[1], reverse=True)
return [compatible_language[0] for compatible_language in languages]
def characters_popularity_compare(
language: str, ordered_characters: list[str]
) -> float:
"""
Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
"""
if language not in FREQUENCIES:
raise ValueError(f"{language} not available") # Defensive:
character_approved_count: int = 0
lang_rank: dict[str, int] = _FREQUENCIES_RANK[language]
ordered_characters_count: int = len(ordered_characters)
target_language_characters_count: int = len(FREQUENCIES[language])
large_alphabet: bool = target_language_characters_count > 26
large_alphabet_threshold: float = target_language_characters_count / 3
expected_projection_ratio: float = (
target_language_characters_count / ordered_characters_count
)
# Single pass: characters present in the language vocabulary, as
# (language rank, popularity rank) pairs. The scoring below only ever
# needs ranks, never the characters themselves.
common_lr: list[int] = []
common_orr: list[int] = []
for popularity_rank, character in enumerate(ordered_characters):
language_rank = lang_rank.get(character)
if language_rank is not None:
common_lr.append(language_rank)
common_orr.append(popularity_rank)
for character_rank_in_language, character_rank in zip(common_lr, common_orr):
character_rank_projection: int = int(character_rank * expected_projection_ratio)
if (
not large_alphabet
and abs(character_rank_projection - character_rank_in_language) > 4
):
continue
if (
large_alphabet
and abs(character_rank_projection - character_rank_in_language)
< large_alphabet_threshold
):
character_approved_count += 1
continue
if character_rank_in_language == 0:
# before_match_count is structurally 0 here (no pair can have a
# smaller language rank): the historic "before <= 4" acceptance
# always holds. (The symmetric "after_len == 0" case is
# impossible: language ranks are strictly below the language
# character count, hence after_len >= 1.)
character_approved_count += 1
continue
after_len: int = target_language_characters_count - character_rank_in_language
# Count how many characters appear "before" in both orderings, and
# how many appear "at or after" in both orderings. Both counts grow
# monotonically and the approval thresholds
# (before / rank >= 0.4 or after / after_len >= 0.4) are known
# upfront, expressed below as exact integer comparisons: exit as
# soon as one is crossed.
before_match_count: int = 0
after_match_count: int = 0
for lr_i, orr_i in zip(common_lr, common_orr):
if lr_i < character_rank_in_language:
if orr_i < character_rank:
before_match_count += 1
if 5 * before_match_count >= 2 * character_rank_in_language:
character_approved_count += 1
break
else:
if orr_i >= character_rank:
after_match_count += 1
if 5 * after_match_count >= 2 * after_len:
character_approved_count += 1
break
return character_approved_count / len(ordered_characters)
def alpha_unicode_split(decoded_sequence: str) -> list[str]:
"""
Given a decoded text sequence, return a list of str. Unicode range / alphabet separation.
Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list;
One containing the latin letters and the other hebrew.
"""
layers: dict[str, list[str]] = {}
# Fast path: track single-layer key to skip dict iteration for single-script text.
single_layer_key: str | None = None
multi_layer: bool = False
# Cache the last character_range and its resolved layer to avoid repeated
# is_suspiciously_successive_range calls for consecutive same-range chars.
prev_character_range: str | None = None
prev_layer_target: str | None = None
for character in decoded_sequence:
# Reuse the per-codepoint CharInfo cache: info.alpha and info.range
# are computed with the very same str.isalpha() / unicode_range()
# calls this loop historically made per character occurrence.
codepoint: int = ord(character)
if codepoint < 128:
info = _ASCII_CHAR_INFO[codepoint]
else:
info = _char_info(character)
if not info.alpha:
continue
character_range: str | None = info.range
if character_range is None:
continue
# Fast path: same range as previous character → reuse cached layer target.
if character_range == prev_character_range:
if prev_layer_target is not None:
layers[prev_layer_target].append(character)
continue
layer_target_range: str | None = None
if multi_layer:
for discovered_range in layers:
if not is_suspiciously_successive_range(
discovered_range, character_range
):
layer_target_range = discovered_range
break
elif single_layer_key is not None:
if not is_suspiciously_successive_range(single_layer_key, character_range):
layer_target_range = single_layer_key
if layer_target_range is None:
layer_target_range = character_range
if layer_target_range not in layers:
layers[layer_target_range] = []
if single_layer_key is None:
single_layer_key = layer_target_range
else:
multi_layer = True
layers[layer_target_range].append(character)
# Cache for next iteration
prev_character_range = character_range
prev_layer_target = layer_target_range
return ["".join(chars).lower() for chars in layers.values()]
def merge_coherence_ratios(results: list[CoherenceMatches]) -> CoherenceMatches:
"""
This function merge results previously given by the function coherence_ratio.
The return type is the same as coherence_ratio.
"""
per_language_ratios: dict[str, list[float]] = {}
for result in results:
for sub_result in result:
language, ratio = sub_result
if language not in per_language_ratios:
per_language_ratios[language] = [ratio]
continue
per_language_ratios[language].append(ratio)
merge = [
(
language,
round(
sum(per_language_ratios[language]) / len(per_language_ratios[language]),
4,
),
)
for language in per_language_ratios
]
return sorted(merge, key=lambda x: x[1], reverse=True)
def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches:
"""
We shall NOT return "English—" in CoherenceMatches because it is an alternative
of "English". This function only keeps the best match and remove the em-dash in it.
"""
index_results: dict[str, list[float]] = dict()
for result in results:
language, ratio = result
no_em_name: str = language.replace("—", "")
if no_em_name not in index_results:
index_results[no_em_name] = []
index_results[no_em_name].append(ratio)
if any(len(index_results[e]) > 1 for e in index_results):
filtered_results: CoherenceMatches = []
for language in index_results:
filtered_results.append((language, max(index_results[language])))
return filtered_results
return results
def coherence_ratio(
decoded_sequence: str, threshold: float = 0.1, lg_inclusion: str | None = None
) -> CoherenceMatches:
"""
Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
A layer = Character extraction by alphabets/ranges.
"""
results: list[tuple[str, float]] = []
ignore_non_latin: bool = False
sufficient_match_count: int = 0
lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else []
if "Latin Based" in lg_inclusion_list:
ignore_non_latin = True
lg_inclusion_list.remove("Latin Based")
for layer in alpha_unicode_split(decoded_sequence):
# Native counting + stable sort reproduce Counter.most_common()
# ordering exactly (ties keep first-appearance order) without the
# interpreted Counter machinery in the compiled hot path.
char_counts: dict[str, int] = {}
for layer_character in layer:
char_counts[layer_character] = char_counts.get(layer_character, 0) + 1
character_count: int = len(layer)
if character_count <= TOO_SMALL_SEQUENCE:
continue
popular_character_ordered: list[str] = [
item[0]
for item in sorted(
char_counts.items(), key=lambda item: item[1], reverse=True
)
]
for language in lg_inclusion_list or alphabet_languages(
popular_character_ordered, ignore_non_latin
):
ratio: float = characters_popularity_compare(
language, popular_character_ordered
)
if ratio < threshold:
continue
elif ratio >= 0.8:
sufficient_match_count += 1
results.append((language, round(ratio, 4)))
if sufficient_match_count >= 3:
break
return sorted(
filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True
)
venv/lib/python3.12/site-packages/charset_normalizer/cli/__init__.py
+8
View File
@@ -0,0 +1,8 @@
from __future__ import annotations
from .__main__ import cli_detect, query_yes_no
__all__ = (
"cli_detect",
"query_yes_no",
)
venv/lib/python3.12/site-packages/charset_normalizer/cli/__main__.py
+363
View File
@@ -0,0 +1,363 @@
from __future__ import annotations
import argparse
import sys
import typing
from os.path import abspath, basename, dirname, join, realpath
from platform import python_version
from unicodedata import unidata_version
import charset_normalizer.md as md_module
from charset_normalizer import from_fp
from charset_normalizer.models import CliDetectionResult
from charset_normalizer.version import __version__
def query_yes_no(question: str, default: str = "yes") -> bool: # Defensive:
"""Ask a yes/no question via input() and return the answer as a bool."""
prompt = " [Y/n] " if default == "yes" else " [y/N] "
while True:
choice = input(question + prompt).strip().lower()
if not choice:
return default == "yes"
if choice in ("y", "yes"):
return True
if choice in ("n", "no"):
return False
print("Please respond with 'y' or 'n'.")
class FileType:
"""Factory for creating file object types
Instances of FileType are typically passed as type= arguments to the
ArgumentParser add_argument() method.
Keyword Arguments:
- mode -- A string indicating how the file is to be opened. Accepts the
same values as the builtin open() function.
- bufsize -- The file's desired buffer size. Accepts the same values as
the builtin open() function.
- encoding -- The file's encoding. Accepts the same values as the
builtin open() function.
- errors -- A string indicating how encoding and decoding errors are to
be handled. Accepts the same value as the builtin open() function.
Backported from CPython 3.12
"""
def __init__(
self,
mode: str = "r",
bufsize: int = -1,
encoding: str | None = None,
errors: str | None = None,
):
self._mode = mode
self._bufsize = bufsize
self._encoding = encoding
self._errors = errors
def __call__(self, string: str) -> typing.IO: # type: ignore[type-arg]
# the special argument "-" means sys.std{in,out}
if string == "-":
if "r" in self._mode:
return sys.stdin.buffer if "b" in self._mode else sys.stdin
elif any(c in self._mode for c in "wax"):
return sys.stdout.buffer if "b" in self._mode else sys.stdout
else:
msg = f'argument "-" with mode {self._mode}'
raise ValueError(msg)
# all other arguments are used as file names
try:
return open(string, self._mode, self._bufsize, self._encoding, self._errors)
except OSError as e:
message = f"can't open '{string}': {e}"
raise argparse.ArgumentTypeError(message)
def __repr__(self) -> str:
args = self._mode, self._bufsize
kwargs = [("encoding", self._encoding), ("errors", self._errors)]
args_str = ", ".join(
[repr(arg) for arg in args if arg != -1]
+ [f"{kw}={arg!r}" for kw, arg in kwargs if arg is not None]
)
return f"{type(self).__name__}({args_str})"
def cli_detect(argv: list[str] | None = None) -> int:
"""
CLI assistant using ARGV and ArgumentParser
:param argv:
:return: 0 if everything is fine, anything else equal trouble
"""
parser = argparse.ArgumentParser(
description="The Real First Universal Charset Detector. "
"Discover originating encoding used on text file. "
"Normalize text to unicode."
)
parser.add_argument(
"files", type=FileType("rb"), nargs="+", help="File(s) to be analysed"
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
default=False,
dest="verbose",
help="Display complementary information about file if any. "
"Stdout will contain logs about the detection process.",
)
parser.add_argument(
"-a",
"--with-alternative",
action="store_true",
default=False,
dest="alternatives",
help="Output complementary possibilities if any. Top-level JSON WILL be a list.",
)
parser.add_argument(
"-n",
"--normalize",
action="store_true",
default=False,
dest="normalize",
help="Permit to normalize input file. If not set, program does not write anything.",
)
parser.add_argument(
"-m",
"--minimal",
action="store_true",
default=False,
dest="minimal",
help="Only output the charset detected to STDOUT. Disabling JSON output.",
)
parser.add_argument(
"-r",
"--replace",
action="store_true",
default=False,
dest="replace",
help="Replace file when trying to normalize it instead of creating a new one.",
)
parser.add_argument(
"-f",
"--force",
action="store_true",
default=False,
dest="force",
help="Replace file without asking if you are sure, use this flag with caution.",
)
parser.add_argument(
"-i",
"--no-preemptive",
action="store_true",
default=False,
dest="no_preemptive",
help="Disable looking at a charset declaration to hint the detector.",
)
parser.add_argument(
"-t",
"--threshold",
action="store",
default=0.2,
type=float,
dest="threshold",
help="Define a custom maximum amount of noise allowed in decoded content. 0. <= noise <= 1.",
)
parser.add_argument(
"--version",
action="version",
version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format(
__version__,
python_version(),
unidata_version,
"OFF" if md_module.__file__.lower().endswith(".py") else "ON",
),
help="Show version information and exit.",
)
args = parser.parse_args(argv)
if args.replace is True and args.normalize is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --replace in addition of --normalize only.", file=sys.stderr)
return 1
if args.force is True and args.replace is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --force in addition of --replace only.", file=sys.stderr)
return 1
if args.threshold < 0.0 or args.threshold > 1.0:
if args.files:
for my_file in args.files:
my_file.close()
print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
return 1
x_ = []
for my_file in args.files:
matches = from_fp(
my_file,
threshold=args.threshold,
explain=args.verbose,
preemptive_behaviour=args.no_preemptive is False,
)
best_guess = matches.best()
if best_guess is None:
print(
'Unable to identify originating encoding for "{}". {}'.format(
my_file.name,
(
"Maybe try increasing maximum amount of chaos."
if args.threshold < 1.0
else ""
),
),
file=sys.stderr,
)
x_.append(
CliDetectionResult(
abspath(my_file.name),
None,
[],
[],
"Unknown",
[],
False,
1.0,
0.0,
None,
True,
)
)
else:
cli_result = CliDetectionResult(
abspath(my_file.name),
best_guess.encoding,
best_guess.encoding_aliases,
[
cp
for cp in best_guess.could_be_from_charset
if cp != best_guess.encoding
],
best_guess.language,
best_guess.alphabets,
best_guess.bom,
best_guess.percent_chaos,
best_guess.percent_coherence,
None,
True,
)
x_.append(cli_result)
if len(matches) > 1 and args.alternatives:
for el in matches:
if el != best_guess:
x_.append(
CliDetectionResult(
abspath(my_file.name),
el.encoding,
el.encoding_aliases,
[
cp
for cp in el.could_be_from_charset
if cp != el.encoding
],
el.language,
el.alphabets,
el.bom,
el.percent_chaos,
el.percent_coherence,
None,
False,
)
)
if args.normalize is True:
if best_guess.encoding.startswith("utf") is True:
print(
'"{}" file does not need to be normalized, as it already came from unicode.'.format(
my_file.name
),
file=sys.stderr,
)
if my_file.closed is False:
my_file.close()
continue
dir_path = dirname(realpath(my_file.name))
file_name = basename(realpath(my_file.name))
o_: list[str] = file_name.split(".")
if args.replace is False:
o_.insert(-1, best_guess.encoding)
if my_file.closed is False:
my_file.close()
elif (
args.force is False
and query_yes_no(
'Are you sure to normalize "{}" by replacing it ?'.format(
my_file.name
),
"no",
)
is False
):
if my_file.closed is False:
my_file.close()
continue
try:
cli_result.unicode_path = join(dir_path, ".".join(o_))
with open(cli_result.unicode_path, "wb") as fp:
fp.write(best_guess.output())
except OSError as e: # Defensive:
print(str(e), file=sys.stderr)
if my_file.closed is False:
my_file.close()
return 2
if my_file.closed is False:
my_file.close()
if args.minimal is False:
from json import dumps
print(
dumps(
[el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__,
ensure_ascii=True,
indent=4,
)
)
else:
for my_file in args.files:
print(
", ".join(
[
el.encoding or "undefined"
for el in x_
if el.path == abspath(my_file.name)
]
)
)
return 0
if __name__ == "__main__": # Defensive:
cli_detect()
venv/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/constant.py
+2055
View File
File diff suppressed because it is too large Load Diff
venv/lib/python3.12/site-packages/charset_normalizer/legacy.py
+79
View File
@@ -0,0 +1,79 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from warnings import warn
from .api import from_bytes
from .constant import CHARDET_CORRESPONDENCE, TOO_SMALL_SEQUENCE
if TYPE_CHECKING:
from typing import TypedDict
class ResultDict(TypedDict):
encoding: str | None
language: str
confidence: float | None
def detect(
byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
) -> ResultDict:
"""
chardet legacy method
Detect the encoding of the given byte string. It should be mostly backward-compatible.
Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
This function is deprecated and should be used to migrate your project easily, consult the documentation for
further information. Not planned for removal.
:param byte_str: The byte sequence to examine.
:param should_rename_legacy: Should we rename legacy encodings
to their more modern equivalents?
"""
if len(kwargs):
warn(
f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
)
if not isinstance(byte_str, (bytearray, bytes)):
raise TypeError( # pragma: nocover
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
if isinstance(byte_str, bytearray):
byte_str = bytes(byte_str)
r = from_bytes(byte_str).best()
encoding = r.encoding if r is not None else None
language = r.language if r is not None and r.language != "Unknown" else ""
confidence = 1.0 - r.chaos if r is not None else None
# automatically lower confidence
# on small bytes samples.
# https://github.com/jawah/charset_normalizer/issues/391
if (
confidence is not None
and confidence >= 0.9
and encoding
not in {
"utf_8",
"ascii",
}
and not r.bom # type: ignore[union-attr]
and len(byte_str) < TOO_SMALL_SEQUENCE
):
confidence -= 0.2
# Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
# but chardet does return 'utf-8-sig' and it is a valid codec name.
if r is not None and encoding == "utf_8" and r.bom:
encoding += "_sig"
if not should_rename_legacy and encoding in CHARDET_CORRESPONDENCE:
encoding = CHARDET_CORRESPONDENCE[encoding]
return {
"encoding": encoding,
"language": language,
"confidence": confidence,
}
venv/lib/python3.12/site-packages/charset_normalizer/md.cpython-312-x86_64-linux-gnu.so
Executable
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/charset_normalizer/md.py
+1002
View File
File diff suppressed because it is too large Load Diff
venv/lib/python3.12/site-packages/charset_normalizer/models.py
+370
View File
@@ -0,0 +1,370 @@
from __future__ import annotations
from encodings.aliases import aliases
from re import sub
from typing import Any, Iterator, List, Tuple
from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE
from .utils import iana_name, is_multi_byte_encoding, unicode_range
class CharsetMatch:
def __init__(
self,
payload: bytes | bytearray,
guessed_encoding: str,
mean_mess_ratio: float,
has_sig_or_bom: bool,
languages: CoherenceMatches,
decoded_payload: str | None = None,
preemptive_declaration: str | None = None,
):
self._payload: bytes | bytearray = payload
self._encoding: str = guessed_encoding
self._mean_mess_ratio: float = mean_mess_ratio
self._languages: CoherenceMatches = languages
self._has_sig_or_bom: bool = has_sig_or_bom
self._unicode_ranges: list[str] | None = None
self._leaves: list[CharsetMatch] = []
self._mean_coherence_ratio: float = 0.0
self._output_payload: bytes | None = None
self._output_encoding: str | None = None
self._string: str | None = decoded_payload
self._preemptive_declaration: str | None = preemptive_declaration
def __eq__(self, other: object) -> bool:
if not isinstance(other, CharsetMatch):
if isinstance(other, str):
return iana_name(other) == self.encoding
return False
return self.encoding == other.encoding and self.fingerprint == other.fingerprint
def __lt__(self, other: object) -> bool:
"""
Implemented to make sorted available upon CharsetMatches items.
"""
if not isinstance(other, CharsetMatch):
raise ValueError
chaos_difference: float = abs(self.chaos - other.chaos)
coherence_difference: float = abs(self.coherence - other.coherence)
# Below 0.5% difference --> Use Coherence
if chaos_difference < 0.005 and coherence_difference > 0.02:
return self.coherence > other.coherence
elif chaos_difference < 0.005 and coherence_difference <= 0.02:
# When having a difficult decision, use the result that decoded as many multi-byte as possible.
# preserve RAM usage!
if len(self._payload) >= TOO_BIG_SEQUENCE:
return self.chaos < other.chaos
return self.multi_byte_usage > other.multi_byte_usage
return self.chaos < other.chaos
@property
def multi_byte_usage(self) -> float:
return 1.0 - (len(str(self)) / len(self.raw))
def __str__(self) -> str:
# Lazy Str Loading
if self._string is None:
self._string = str(self._payload, self._encoding, "strict")
# UTF-7 BOM is encoded in modified Base64 whose byte boundary
# can overlap with the next character, so raw-byte stripping
# is unreliable. Strip the decoded BOM character instead.
if (
self._has_sig_or_bom
and self._encoding == "utf_7"
and self._string
and self._string[0] == "\ufeff"
):
self._string = self._string[1:]
return self._string
def __repr__(self) -> str:
return f"<CharsetMatch '{self.encoding}' fp({self.fingerprint})>"
def add_submatch(self, other: CharsetMatch) -> None:
if not isinstance(other, CharsetMatch) or other == self:
raise ValueError(
"Unable to add instance <{}> as a submatch of a CharsetMatch".format(
other.__class__
)
)
other._string = None # Unload RAM usage; dirty trick.
self._leaves.append(other)
@property
def encoding(self) -> str:
return self._encoding
@property
def encoding_aliases(self) -> list[str]:
"""
Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
"""
also_known_as: list[str] = []
for u, p in aliases.items():
if self.encoding == u:
also_known_as.append(p)
elif self.encoding == p:
also_known_as.append(u)
return also_known_as
@property
def bom(self) -> bool:
return self._has_sig_or_bom
@property
def byte_order_mark(self) -> bool:
return self._has_sig_or_bom
@property
def languages(self) -> list[str]:
"""
Return the complete list of possible languages found in decoded sequence.
Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
"""
return [e[0] for e in self._languages]
@property
def language(self) -> str:
"""
Most probable language found in decoded sequence. If none were detected or inferred, the property will return
"Unknown".
"""
if not self._languages:
# Trying to infer the language based on the given encoding
# Its either English or we should not pronounce ourselves in certain cases.
if "ascii" in self.could_be_from_charset:
return "English"
# doing it there to avoid circular import
from charset_normalizer.cd import encoding_languages, mb_encoding_languages
languages = (
mb_encoding_languages(self.encoding)
if is_multi_byte_encoding(self.encoding)
else encoding_languages(self.encoding)
)
if len(languages) == 0 or "Latin Based" in languages:
return "Unknown"
return languages[0]
return self._languages[0][0]
@property
def chaos(self) -> float:
return self._mean_mess_ratio
@property
def coherence(self) -> float:
if not self._languages:
return 0.0
return self._languages[0][1]
@property
def percent_chaos(self) -> float:
return round(self.chaos * 100, ndigits=3)
@property
def percent_coherence(self) -> float:
return round(self.coherence * 100, ndigits=3)
@property
def raw(self) -> bytes | bytearray:
"""
Original untouched bytes.
"""
return self._payload
@property
def submatch(self) -> list[CharsetMatch]:
return self._leaves
@property
def has_submatch(self) -> bool:
return len(self._leaves) > 0
@property
def alphabets(self) -> list[str]:
if self._unicode_ranges is not None:
return self._unicode_ranges
# list detected ranges
detected_ranges: list[str | None] = [unicode_range(char) for char in str(self)]
# filter and sort
self._unicode_ranges = sorted(list({r for r in detected_ranges if r}))
return self._unicode_ranges
@property
def could_be_from_charset(self) -> list[str]:
"""
The complete list of encoding that output the exact SAME str result and therefore could be the originating
encoding.
This list does include the encoding available in property 'encoding'.
"""
return [self._encoding] + [m.encoding for m in self._leaves]
def output(self, encoding: str = "utf_8") -> bytes:
"""
Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
Any errors will be simply ignored by the encoder NOT replaced.
"""
if self._output_encoding is None or self._output_encoding != encoding:
self._output_encoding = encoding
decoded_string = str(self)
if (
self._preemptive_declaration is not None
and self._preemptive_declaration.lower()
not in ["utf-8", "utf8", "utf_8"]
):
patched_header = sub(
RE_POSSIBLE_ENCODING_INDICATION,
lambda m: m.string[m.span()[0] : m.span()[1]].replace(
m.groups()[0],
iana_name(self._output_encoding).replace("_", "-"), # type: ignore[arg-type]
),
decoded_string[:8192],
count=1,
)
decoded_string = patched_header + decoded_string[8192:]
self._output_payload = decoded_string.encode(encoding, "replace")
return self._output_payload # type: ignore
@property
def fingerprint(self) -> int:
"""
Retrieve a hash fingerprint of the decoded payload, used for deduplication.
"""
return hash(str(self))
class CharsetMatches:
"""
Container with every CharsetMatch items ordered by default from most probable to the less one.
Act like a list(iterable) but does not implements all related methods.
"""
def __init__(self, results: list[CharsetMatch] | None = None):
self._results: list[CharsetMatch] = sorted(results) if results else []
def __iter__(self) -> Iterator[CharsetMatch]:
yield from self._results
def __getitem__(self, item: int | str) -> CharsetMatch:
"""
Retrieve a single item either by its position or encoding name (alias may be used here).
Raise KeyError upon invalid index or encoding not present in results.
"""
if isinstance(item, int):
return self._results[item]
if isinstance(item, str):
item = iana_name(item, False)
for result in self._results:
if item in result.could_be_from_charset:
return result
raise KeyError
def __len__(self) -> int:
return len(self._results)
def __bool__(self) -> bool:
return len(self._results) > 0
def append(self, item: CharsetMatch) -> None:
"""
Insert a single match. Will be inserted accordingly to preserve sort.
Can be inserted as a submatch.
"""
if not isinstance(item, CharsetMatch):
raise ValueError(
"Cannot append instance '{}' to CharsetMatches".format(
str(item.__class__)
)
)
# We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
if len(item.raw) < TOO_BIG_SEQUENCE:
for match in self._results:
if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
match.add_submatch(item)
return
self._results.append(item)
self._results = sorted(self._results)
def best(self) -> CharsetMatch | None:
"""
Simply return the first match. Strict equivalent to matches[0].
"""
if not self._results:
return None
return self._results[0]
def first(self) -> CharsetMatch | None:
"""
Redundant method, call the method best(). Kept for BC reasons.
"""
return self.best()
CoherenceMatch = Tuple[str, float]
CoherenceMatches = List[CoherenceMatch]
class CliDetectionResult:
def __init__(
self,
path: str,
encoding: str | None,
encoding_aliases: list[str],
alternative_encodings: list[str],
language: str,
alphabets: list[str],
has_sig_or_bom: bool,
chaos: float,
coherence: float,
unicode_path: str | None,
is_preferred: bool,
):
self.path: str = path
self.unicode_path: str | None = unicode_path
self.encoding: str | None = encoding
self.encoding_aliases: list[str] = encoding_aliases
self.alternative_encodings: list[str] = alternative_encodings
self.language: str = language
self.alphabets: list[str] = alphabets
self.has_sig_or_bom: bool = has_sig_or_bom
self.chaos: float = chaos
self.coherence: float = coherence
self.is_preferred: bool = is_preferred
@property
def __dict__(self) -> dict[str, Any]: # type: ignore
return {
"path": self.path,
"encoding": self.encoding,
"encoding_aliases": self.encoding_aliases,
"alternative_encodings": self.alternative_encodings,
"language": self.language,
"alphabets": self.alphabets,
"has_sig_or_bom": self.has_sig_or_bom,
"chaos": self.chaos,
"coherence": self.coherence,
"unicode_path": self.unicode_path,
"is_preferred": self.is_preferred,
}
def to_json(self) -> str:
from json import dumps
return dumps(self.__dict__, ensure_ascii=True, indent=4)
venv/lib/python3.12/site-packages/charset_normalizer/py.typed
View File
venv/lib/python3.12/site-packages/charset_normalizer/utils.py
+455
View File
@@ -0,0 +1,455 @@
from __future__ import annotations
import importlib
import logging
import unicodedata
from bisect import bisect_right
from codecs import IncrementalDecoder
from encodings.aliases import aliases
from functools import lru_cache
from re import findall
from typing import Generator
from .constant import (
ENCODING_MARKS,
IANA_SUPPORTED_SIMILAR,
RE_POSSIBLE_ENCODING_INDICATION,
UNICODE_RANGES_COMBINED,
_SECONDARY_RANGE_NAMES,
UTF8_MAXIMAL_ALLOCATION,
COMMON_CJK_CHARACTERS,
_LATIN,
_CJK,
_HANGUL,
_KATAKANA,
_HIRAGANA,
_THAI,
_ARABIC,
_ARABIC_ISOLATED_FORM,
_ACCENT_KEYWORDS,
_ACCENTUATED,
)
def _character_flags(character: str) -> int:
"""Compute all name-based classification flags with a single unicodedata.name() call."""
try:
desc: str = unicodedata.name(character)
except ValueError:
return 0
flags: int = 0
if "LATIN" in desc:
flags |= _LATIN
if "CJK" in desc:
flags |= _CJK
if "HANGUL" in desc:
flags |= _HANGUL
if "KATAKANA" in desc:
flags |= _KATAKANA
if "HIRAGANA" in desc:
flags |= _HIRAGANA
if "THAI" in desc:
flags |= _THAI
if "ARABIC" in desc:
flags |= _ARABIC
if "ISOLATED FORM" in desc:
flags |= _ARABIC_ISOLATED_FORM
for kw in _ACCENT_KEYWORDS:
if kw in desc:
flags |= _ACCENTUATED
break
return flags
def is_accentuated(character: str) -> bool:
return bool(_character_flags(character) & _ACCENTUATED)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def remove_accent(character: str) -> str:
decomposed: str = unicodedata.decomposition(character)
if not decomposed:
return character
codes: list[str] = decomposed.split(" ")
return chr(int(codes[0], 16))
# Pre-built sorted lookup table for O(log n) binary search in unicode_range().
# Each entry is (range_start, range_end_exclusive, range_name).
_UNICODE_RANGES_SORTED: list[tuple[int, int, str]] = sorted(
(ord_range.start, ord_range.stop, name)
for name, ord_range in UNICODE_RANGES_COMBINED.items()
)
_UNICODE_RANGE_STARTS: list[int] = [e[0] for e in _UNICODE_RANGES_SORTED]
def unicode_range(character: str) -> str | None:
"""
Retrieve the Unicode range official name from a single character.
"""
character_ord: int = ord(character)
# Binary search: find the rightmost range whose start <= character_ord
idx = bisect_right(_UNICODE_RANGE_STARTS, character_ord) - 1
if idx >= 0:
start, stop, name = _UNICODE_RANGES_SORTED[idx]
if character_ord < stop:
return name
return None
def is_latin(character: str) -> bool:
return bool(_character_flags(character) & _LATIN)
def is_punctuation(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "P" in character_category:
return True
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Punctuation" in character_range
def is_symbol(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "S" in character_category or "N" in character_category:
return True
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Forms" in character_range and character_category != "Lo"
def is_emoticon(character: str) -> bool:
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Emoticons" in character_range or "Pictographs" in character_range
def is_separator(character: str) -> bool:
if character.isspace() or character in {"｜", "+", "<", ">"}:
return True
character_category: str = unicodedata.category(character)
return "Z" in character_category or character_category in {"Po", "Pd", "Pc"}
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_case_variable(character: str) -> bool:
return character.islower() != character.isupper()
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk(character: str) -> bool:
return bool(_character_flags(character) & _CJK)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hiragana(character: str) -> bool:
return bool(_character_flags(character) & _HIRAGANA)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_katakana(character: str) -> bool:
return bool(_character_flags(character) & _KATAKANA)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hangul(character: str) -> bool:
return bool(_character_flags(character) & _HANGUL)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_thai(character: str) -> bool:
return bool(_character_flags(character) & _THAI)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic(character: str) -> bool:
return bool(_character_flags(character) & _ARABIC)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic_isolated_form(character: str) -> bool:
return bool(_character_flags(character) & _ARABIC_ISOLATED_FORM)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk_uncommon(character: str) -> bool:
return character not in COMMON_CJK_CHARACTERS
def is_unicode_range_secondary(range_name: str) -> bool:
return range_name in _SECONDARY_RANGE_NAMES
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_unprintable(character: str) -> bool:
return (
not character.isspace() # includes \n \t \r \v
and not character.isprintable()
and character != "\x1a" # Why? Its the ASCII substitute character.
and character != "\ufeff" # bug discovered in Python,
# Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space.
)
def any_specified_encoding(
sequence: bytes | bytearray, search_zone: int = 8192
) -> str | None:
"""
Extract using ASCII-only decoder any specified encoding in the first n-bytes.
"""
if not isinstance(sequence, (bytes, bytearray)):
raise TypeError
seq_len: int = len(sequence)
decoded_zone: str = sequence[: min(seq_len, search_zone)].decode(
"ascii", errors="ignore"
)
# Cheap literal pre-filter.
lowered_zone: str = decoded_zone.lower()
if "coding" not in lowered_zone and "charset" not in lowered_zone:
return None
results: list[str] = findall(
RE_POSSIBLE_ENCODING_INDICATION,
decoded_zone,
)
if len(results) == 0:
return None
for specified_encoding in results:
specified_encoding = specified_encoding.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if encoding_alias == specified_encoding:
return encoding_iana
if encoding_iana == specified_encoding:
return encoding_iana
return None
@lru_cache(maxsize=128)
def is_multi_byte_encoding(name: str) -> bool:
"""
Verify is a specific encoding is a multi byte one based on it IANA name
"""
if name in {
"utf_8",
"utf_8_sig",
"utf_16",
"utf_16_be",
"utf_16_le",
"utf_32",
"utf_32_le",
"utf_32_be",
"utf_7",
}:
return True
# Besides the Unicode family above, every multibyte codec shipped with
# Python is implemented by _multibytecodec through exactly one of the six
# cjkcodecs providers below. Probing those providers directly (getcodec)
# classifies a name without importing its "encodings.<name>" module:
# classifying the whole IANA_SUPPORTED list would otherwise import many
# modules and dominate "import charset_normalizer" wall time.
# see https://github.com/jawah/charset_normalizer/issues/742
for provider in (
"_codecs_cn",
"_codecs_hk",
"_codecs_iso2022",
"_codecs_jp",
"_codecs_kr",
"_codecs_tw",
):
try:
importlib.import_module(provider).getcodec(name) # type: ignore[attr-defined]
except (ImportError, AttributeError, LookupError): # Defensive: edge cases
continue
return True
return False
def identify_sig_or_bom(sequence: bytes | bytearray) -> tuple[str | None, bytes]:
"""
Identify and extract SIG/BOM in given sequence.
"""
for iana_encoding in ENCODING_MARKS:
marks: bytes | list[bytes] = ENCODING_MARKS[iana_encoding]
if isinstance(marks, bytes):
marks = [marks]
for mark in marks:
if sequence.startswith(mark):
return iana_encoding, mark
return None, b""
def should_strip_sig_or_bom(iana_encoding: str) -> bool:
return iana_encoding not in {"utf_16", "utf_32"}
def iana_name(cp_name: str, strict: bool = True) -> str:
"""Returns the Python normalized encoding name (Not the IANA official name)."""
cp_name = cp_name.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if cp_name in [encoding_alias, encoding_iana]:
return encoding_iana
if strict:
raise ValueError(f"Unable to retrieve IANA for '{cp_name}'")
return cp_name
def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
return 0.0
decoder_a = importlib.import_module(f"encodings.{iana_name_a}").IncrementalDecoder
decoder_b = importlib.import_module(f"encodings.{iana_name_b}").IncrementalDecoder
id_a: IncrementalDecoder = decoder_a(errors="ignore")
id_b: IncrementalDecoder = decoder_b(errors="ignore")
character_match_count: int = 0
for i in range(256):
to_be_decoded: bytes = bytes([i])
if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
character_match_count += 1
return character_match_count / 256
def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
"""
Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
the function cp_similarity.
"""
return (
iana_name_a in IANA_SUPPORTED_SIMILAR
and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]
)
def set_logging_handler(
name: str = "charset_normalizer",
level: int = logging.INFO,
format_string: str = "%(asctime)s | %(levelname)s | %(message)s",
) -> None:
logger = logging.getLogger(name)
logger.setLevel(level)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter(format_string))
logger.addHandler(handler)
def cut_sequence_chunks(
sequences: bytes | bytearray,
encoding_iana: str,
offsets: range,
chunk_size: int,
bom_or_sig_available: bool,
strip_sig_or_bom: bool,
sig_payload: bytes,
is_multi_byte_decoder: bool,
decoded_payload: str | None = None,
deferred_decoding: bool = False,
) -> Generator[str, None, None]:
if decoded_payload and not is_multi_byte_decoder:
for i in offsets:
chunk = decoded_payload[i : i + chunk_size]
if not chunk:
break
yield chunk
elif deferred_decoding:
# Deferred single-byte probing: the whole payload is not decoded
# yet. Single-byte codecs are stateless (1 byte == 1 char), hence
# decode(base)[i:j] == decode(base[i:j]): slicing the raw bytes
# yields exactly the chunks the branch above would have produced,
# short trailing chunks included, and raises UnicodeDecodeError on
# invalid bytes just like the whole-payload decode would.
base_bytes = (
sequences if not strip_sig_or_bom else sequences[len(sig_payload) :]
)
for i in offsets:
cut_sequence = base_bytes[i : i + chunk_size]
if not cut_sequence:
break
yield str(cut_sequence, encoding_iana)
else:
for i in offsets:
chunk_end = i + chunk_size
if chunk_end > len(sequences) + 8:
continue
cut_sequence = sequences[i : i + chunk_size]
if bom_or_sig_available and not strip_sig_or_bom:
cut_sequence = sig_payload + cut_sequence
chunk = cut_sequence.decode(
encoding_iana,
errors="ignore" if is_multi_byte_decoder else "strict",
)
# multi-byte bad cutting detector and adjustment
# not the cleanest way to perform that fix but clever enough for now.
if is_multi_byte_decoder and i > 0:
chunk_partial_size_chk: int = min(chunk_size, 16)
if (
decoded_payload
and chunk[:chunk_partial_size_chk] not in decoded_payload
):
for j in range(i, i - 4, -1):
cut_sequence = sequences[j:chunk_end]
if bom_or_sig_available and not strip_sig_or_bom:
cut_sequence = sig_payload + cut_sequence
chunk = cut_sequence.decode(encoding_iana, errors="ignore")
if chunk[:chunk_partial_size_chk] in decoded_payload:
break
yield chunk
venv/lib/python3.12/site-packages/charset_normalizer/version.py
+8
View File
@@ -0,0 +1,8 @@
"""
Expose version
"""
from __future__ import annotations
__version__ = "3.4.9"
VERSION = __version__.split(".")
venv/lib/python3.12/site-packages/click-8.4.2.dist-info/INSTALLER
+1
View File
@@ -0,0 +1 @@
pip
venv/lib/python3.12/site-packages/click-8.4.2.dist-info/METADATA
+84
View File
@@ -0,0 +1,84 @@
Metadata-Version: 2.4
Name: click
Version: 8.4.2
Summary: Composable command line interface toolkit
Maintainer-email: Pallets <contact@palletsprojects.com>
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-Expression: BSD-3-Clause
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Typing :: Typed
License-File: LICENSE.txt
Requires-Dist: colorama; platform_system == 'Windows'
Project-URL: Changes, https://click.palletsprojects.com/page/changes/
Project-URL: Chat, https://discord.gg/pallets
Project-URL: Documentation, https://click.palletsprojects.com/
Project-URL: Donate, https://palletsprojects.com/donate
Project-URL: Source, https://github.com/pallets/click/
<div align="center"><img src="https://raw.githubusercontent.com/pallets/click/refs/heads/stable/docs/_static/click-name.svg" alt="" height="150"></div>
# Click
Click is a Python package for creating beautiful command line interfaces
in a composable way with as little code as necessary. It's the "Command
Line Interface Creation Kit". It's highly configurable but comes with
sensible defaults out of the box.
It aims to make the process of writing command line tools quick and fun
while also preventing any frustration caused by the inability to
implement an intended CLI API.
Click in three points:
- Arbitrary nesting of commands
- Automatic help page generation
- Supports lazy loading of subcommands at runtime
## A Simple Example
```python
import click
@click.command()
@click.option("--count", default=1, help="Number of greetings.")
@click.option("--name", prompt="Your name", help="The person to greet.")
def hello(count, name):
"""Simple program that greets NAME for a total of COUNT times."""
for _ in range(count):
click.echo(f"Hello, {name}!")
if __name__ == '__main__':
hello()
```
```
$ python hello.py --count=3
Your name: Click
Hello, Click!
Hello, Click!
Hello, Click!
```
## Donate
The Pallets organization develops and supports Click and other popular
packages. In order to grow the community of contributors and users, and
allow the maintainers to devote more time to the projects, [please
donate today][].
[please donate today]: https://palletsprojects.com/donate
## Contributing
See our [detailed contributing documentation][contrib] for many ways to
contribute, including reporting issues, requesting features, asking or answering
questions, and making PRs.
[contrib]: https://palletsprojects.com/contributing/
venv/lib/python3.12/site-packages/click-8.4.2.dist-info/RECORD
+40
View File
@@ -0,0 +1,40 @@
click-8.4.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
click-8.4.2.dist-info/METADATA,sha256=GUyd2B1Wf5CB8CbH5AEGD7r6e8FHyOClizZotApkwDE,2621
click-8.4.2.dist-info/RECORD,,
click-8.4.2.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
click-8.4.2.dist-info/licenses/LICENSE.txt,sha256=morRBqOU6FO_4h9C9OctWSgZoigF2ZG18ydQKSkrZY0,1475
click/__init__.py,sha256=FId2fXCSJB3yeWD-e2uON-mBhFa2Yc9MvXGmHu8OXG0,4634
click/__pycache__/__init__.cpython-312.pyc,,
click/__pycache__/_compat.cpython-312.pyc,,
click/__pycache__/_termui_impl.cpython-312.pyc,,
click/__pycache__/_textwrap.cpython-312.pyc,,
click/__pycache__/_utils.cpython-312.pyc,,
click/__pycache__/_winconsole.cpython-312.pyc,,
click/__pycache__/core.cpython-312.pyc,,
click/__pycache__/decorators.cpython-312.pyc,,
click/__pycache__/exceptions.cpython-312.pyc,,
click/__pycache__/formatting.cpython-312.pyc,,
click/__pycache__/globals.cpython-312.pyc,,
click/__pycache__/parser.cpython-312.pyc,,
click/__pycache__/shell_completion.cpython-312.pyc,,
click/__pycache__/termui.cpython-312.pyc,,
click/__pycache__/testing.cpython-312.pyc,,
click/__pycache__/types.cpython-312.pyc,,
click/__pycache__/utils.cpython-312.pyc,,
click/_compat.py,sha256=gPNtXQ9q-G6Qil2b-MC5CsHsGGcQ4u6YSWy9_tlmuhc,18879
click/_termui_impl.py,sha256=CGdg24AeXijeGSzbu0Z7x3c4aaahVFjVBpEbbjhQ5K4,31730
click/_textwrap.py,sha256=7Z0N7Vmn-66TNSTUwp6OXJbcUXRmYET9h9c2ucD8oQQ,6270
click/_utils.py,sha256=eCZCtwJtsYD5QYkkNWJ8MY_8ABIjy8MczgMMyVY32rQ,996
click/_winconsole.py,sha256=KSxfNbMlYRa6GOJuCLgsg2Pb3dVkgJNPqLJPae-Pa10,8543
click/core.py,sha256=rZz76ihNTFV4Y2sxp3H-m93GxL2acD5Pqs0IobEvmuk,140616
click/decorators.py,sha256=9e1Ndu4jhGAcP6RGdNPAwAWtuP9hEs4ETp1u3lKmH1o,19709
click/exceptions.py,sha256=HvSY34G4auj_bYRR8-T8CU8Jwq_1-OcsRU4ezfozeEk,11862
click/formatting.py,sha256=8SW2KGkvjfz9Q1NbeojMHuZBN0cfnQJDs4mqDP6oXms,10444
click/globals.py,sha256=gM-Nh6A4M0HB_SgkaF5M4ncGGMDHc_flHXu9_oh4GEU,1923
click/parser.py,sha256=oJ-fU_3mvxugIuNtHaCATZ56lgEmHRggjJiSqEgYrjA,19052
click/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
click/shell_completion.py,sha256=5tGGY5pV3mAZ17xT23OnuKrWqzEyyLVtrJ30npUxjkU,22618
click/termui.py,sha256=Vn9ehmrQl92z2_6R4bVZOsHUI6j8LrT8u0RzNZUpCvY,33213
click/testing.py,sha256=S9I-pspAlJH3RvZJWDQoJXb-M0nrAEJzXcUzrVXsT34,26458
click/types.py,sha256=9G4DB-nBj-omA_XWsYwbQ3H9BkpH82wJj-kxIPScKmA,44788
click/utils.py,sha256=XwrDxOzU__rnHn-rvJmJcD7ecbypUKMeDJQRjN2F-OA,20942
venv/lib/python3.12/site-packages/click-8.4.2.dist-info/WHEEL
+4
View File
@@ -0,0 +1,4 @@
Wheel-Version: 1.0
Generator: flit 3.12.0
Root-Is-Purelib: true
Tag: py3-none-any
venv/lib/python3.12/site-packages/click-8.4.2.dist-info/licenses/LICENSE.txt
+28
View File
@@ -0,0 +1,28 @@
Copyright 2014 Pallets
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
3. Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
venv/lib/python3.12/site-packages/click/__init__.py
+126
View File
@@ -0,0 +1,126 @@
"""
Click is a simple Python module inspired by the stdlib optparse to make
writing command line scripts fun. Unlike other modules, it's based
around a simple API that does not come with too much magic and is
composable.
"""
from __future__ import annotations
from .core import Argument as Argument
from .core import Command as Command
from .core import CommandCollection as CommandCollection
from .core import Context as Context
from .core import Group as Group
from .core import Option as Option
from .core import Parameter as Parameter
from .core import ParameterSource as ParameterSource
from .decorators import argument as argument
from .decorators import command as command
from .decorators import confirmation_option as confirmation_option
from .decorators import group as group
from .decorators import help_option as help_option
from .decorators import make_pass_decorator as make_pass_decorator
from .decorators import option as option
from .decorators import pass_context as pass_context
from .decorators import pass_obj as pass_obj
from .decorators import password_option as password_option
from .decorators import version_option as version_option
from .exceptions import Abort as Abort
from .exceptions import BadArgumentUsage as BadArgumentUsage
from .exceptions import BadOptionUsage as BadOptionUsage
from .exceptions import BadParameter as BadParameter
from .exceptions import ClickException as ClickException
from .exceptions import FileError as FileError
from .exceptions import MissingParameter as MissingParameter
from .exceptions import NoSuchCommand as NoSuchCommand
from .exceptions import NoSuchOption as NoSuchOption
from .exceptions import UsageError as UsageError
from .formatting import HelpFormatter as HelpFormatter
from .formatting import wrap_text as wrap_text
from .globals import get_current_context as get_current_context
from .termui import clear as clear
from .termui import confirm as confirm
from .termui import echo_via_pager as echo_via_pager
from .termui import edit as edit
from .termui import get_pager_file as get_pager_file
from .termui import getchar as getchar
from .termui import launch as launch
from .termui import pause as pause
from .termui import progressbar as progressbar
from .termui import prompt as prompt
from .termui import secho as secho
from .termui import style as style
from .termui import unstyle as unstyle
from .types import BOOL as BOOL
from .types import Choice as Choice
from .types import DateTime as DateTime
from .types import File as File
from .types import FLOAT as FLOAT
from .types import FloatRange as FloatRange
from .types import INT as INT
from .types import IntRange as IntRange
from .types import ParamType as ParamType
from .types import Path as Path
from .types import STRING as STRING
from .types import Tuple as Tuple
from .types import UNPROCESSED as UNPROCESSED
from .types import UUID as UUID
from .utils import echo as echo
from .utils import format_filename as format_filename
from .utils import get_app_dir as get_app_dir
from .utils import get_binary_stream as get_binary_stream
from .utils import get_text_stream as get_text_stream
from .utils import open_file as open_file
def __getattr__(name: str) -> object:
import warnings
if name == "BaseCommand":
from .core import _BaseCommand
warnings.warn(
"'BaseCommand' is deprecated and will be removed in Click 9.0. Use"
" 'Command' instead.",
DeprecationWarning,
stacklevel=2,
)
return _BaseCommand
if name == "MultiCommand":
from .core import _MultiCommand
warnings.warn(
"'MultiCommand' is deprecated and will be removed in Click 9.0. Use"
" 'Group' instead.",
DeprecationWarning,
stacklevel=2,
)
return _MultiCommand
if name == "OptionParser":
from .parser import _OptionParser
warnings.warn(
"'OptionParser' is deprecated and will be removed in Click 9.0. The"
" old parser is available in 'optparse'.",
DeprecationWarning,
stacklevel=2,
)
return _OptionParser
if name == "__version__":
import importlib.metadata
import warnings
warnings.warn(
"The '__version__' attribute is deprecated and will be removed in"
" Click 9.1. Use feature detection or"
" 'importlib.metadata.version(\"click\")' instead.",
DeprecationWarning,
stacklevel=2,
)
return importlib.metadata.version("click")
raise AttributeError(name)
venv/lib/python3.12/site-packages/click/__pycache__/__init__.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/_compat.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/_termui_impl.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/_textwrap.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/_utils.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/_winconsole.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/core.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/decorators.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/exceptions.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/formatting.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/globals.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/parser.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/shell_completion.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/termui.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/testing.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/types.cpython-312.pyc
BIN
View File
Binary file not shown.
venv/lib/python3.12/site-packages/click/__pycache__/utils.cpython-312.pyc
BIN
View File
Binary file not shown.

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