lapatatedouce/custom-debian-iso
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

supprimé le dossier env

Browse Source
This commit is contained in:
lapatatedouce
2025-07-26 23:09:16 +02:00
parent 38bef25077
commit 97fdbafbe1
746 changed files with 0 additions and 254060 deletions
Download Patch File Download Diff File Expand all files Collapse all files

247
env/bin/Activate.ps1 vendored
View File

@@ -1,247 +0,0 @@
<#
.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"

70
env/bin/activate vendored
View File

@@ -1,70 +0,0 @@
# 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=$(cygpath /home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env)
else
# use the path as-is
export VIRTUAL_ENV=/home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env
fi
_OLD_VIRTUAL_PATH="$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="${PS1:-}"
PS1='(env) '"${PS1:-}"
export PS1
VIRTUAL_ENV_PROMPT='(env) '
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

27
env/bin/activate.csh vendored
View File

@@ -1,27 +0,0 @@
# 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/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env
set _OLD_VIRTUAL_PATH="$PATH"
setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
set prompt = '(env) '"$prompt"
setenv VIRTUAL_ENV_PROMPT '(env) '
endif
alias pydoc python -m pydoc
rehash

69
env/bin/activate.fish vendored
View File

@@ -1,69 +0,0 @@
# 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/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env
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) '(env) ' (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 '(env) '
end

8
env/bin/normalizer vendored
View File

@@ -1,8 +0,0 @@
#!/home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from charset_normalizer.cli.normalizer import cli_detect
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli_detect())

8
env/bin/pip vendored
View File

@@ -1,8 +0,0 @@
#!/home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env/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())

8
env/bin/pip3 vendored
View File

@@ -1,8 +0,0 @@
#!/home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env/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())

8
env/bin/pip3.12 vendored
View File

@@ -1,8 +0,0 @@
#!/home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env/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())

1
env/bin/python vendored
View File

@@ -1 +0,0 @@
python3

1
env/bin/python3 vendored
View File

@@ -1 +0,0 @@
/usr/bin/python3

1
env/bin/python3.12 vendored
View File

@@ -1 +0,0 @@
python3

8
env/bin/tqdm vendored
View File

@@ -1,8 +0,0 @@
#!/home/philippe/Documents/Documents_Philippe_Favre/gitea/custom-debian-iso/env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from tqdm.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

1
env/lib/python3.12/site-packages/beautifulsoup4-4.11.1.dist-info/INSTALLER vendored
View File

@@ -1 +0,0 @@
pip

119
env/lib/python3.12/site-packages/beautifulsoup4-4.11.1.dist-info/METADATA vendored
View File

@@ -1,119 +0,0 @@
Metadata-Version: 2.1
Name: beautifulsoup4
Version: 4.11.1
Summary: Screen-scraping library
Home-page: https://www.crummy.com/software/BeautifulSoup/bs4/
Author: Leonard Richardson
Author-email: leonardr@segfault.org
License: MIT
Download-URL: https://www.crummy.com/software/BeautifulSoup/bs4/download/
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Text Processing :: Markup :: HTML
Classifier: Topic :: Text Processing :: Markup :: XML
Classifier: Topic :: Text Processing :: Markup :: SGML
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.6.0
Description-Content-Type: text/markdown
Provides-Extra: lxml
Provides-Extra: html5lib
Requires-Dist: soupsieve (>1.2)
Provides-Extra: html5lib
Requires-Dist: html5lib; extra == 'html5lib'
Provides-Extra: lxml
Requires-Dist: lxml; extra == 'lxml'
Beautiful Soup is a library that makes it easy to scrape information
from web pages. It sits atop an HTML or XML parser, providing Pythonic
idioms for iterating, searching, and modifying the parse tree.
# Quick start
```
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print(soup.prettify())
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
'bad'
>>> soup.i
<i>HTML</i>
#
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
#
>>> print(soup.prettify())
<?xml version="1.0" encoding="utf-8"?>
<tag1>
Some
<tag2/>
bad
<tag3>
XML
</tag3>
</tag1>
```
To go beyond the basics, [comprehensive documentation is available](https://www.crummy.com/software/BeautifulSoup/bs4/doc/).
# Links
* [Homepage](https://www.crummy.com/software/BeautifulSoup/bs4/)
* [Documentation](https://www.crummy.com/software/BeautifulSoup/bs4/doc/)
* [Discussion group](https://groups.google.com/group/beautifulsoup/)
* [Development](https://code.launchpad.net/beautifulsoup/)
* [Bug tracker](https://bugs.launchpad.net/beautifulsoup/)
* [Complete changelog](https://bazaar.launchpad.net/~leonardr/beautifulsoup/bs4/view/head:/CHANGELOG)
# Note on Python 2 sunsetting
Beautiful Soup's support for Python 2 was discontinued on December 31,
2020: one year after the sunset date for Python 2 itself. From this
point onward, new Beautiful Soup development will exclusively target
Python 3. The final release of Beautiful Soup 4 to support Python 2
was 4.9.3.
# Supporting the project
If you use Beautiful Soup as part of your professional work, please consider a
[Tidelift subscription](https://tidelift.com/subscription/pkg/pypi-beautifulsoup4?utm_source=pypi-beautifulsoup4&utm_medium=referral&utm_campaign=readme).
This will support many of the free software projects your organization
depends on, not just Beautiful Soup.
If you use Beautiful Soup for personal projects, the best way to say
thank you is to read
[Tool Safety](https://www.crummy.com/software/BeautifulSoup/zine/), a zine I
wrote about what Beautiful Soup has taught me about software
development.
# Building the documentation
The bs4/doc/ directory contains full documentation in Sphinx
format. Run `make html` in that directory to create HTML
documentation.
# Running the unit tests
Beautiful Soup supports unit test discovery using Pytest:
```
$ pytest
```

54
env/lib/python3.12/site-packages/beautifulsoup4-4.11.1.dist-info/RECORD vendored
View File

@@ -1,54 +0,0 @@
beautifulsoup4-4.11.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
beautifulsoup4-4.11.1.dist-info/METADATA,sha256=zefuevXradYVap7gKfvpSwLzvs8FSBONKfY8j5HIj-k,3525
beautifulsoup4-4.11.1.dist-info/RECORD,,
beautifulsoup4-4.11.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
beautifulsoup4-4.11.1.dist-info/WHEEL,sha256=NzFAKnL7g-U64xnS1s5e3mJnxKpOTeOtlXdFwS9yNXI,92
beautifulsoup4-4.11.1.dist-info/top_level.txt,sha256=gpUVJcTwW3q7-QGp6tAEomZsskknmgSqVe6xn1C0jJI,26
bs4/__init__.py,sha256=v5VuQqegAzN3bo4kjs6fT0391zvKQGhvBlV841aJ86A,32832
bs4/__pycache__/__init__.cpython-312.pyc,,
bs4/__pycache__/dammit.cpython-312.pyc,,
bs4/__pycache__/diagnose.cpython-312.pyc,,
bs4/__pycache__/element.cpython-312.pyc,,
bs4/__pycache__/formatter.cpython-312.pyc,,
bs4/builder/__init__.py,sha256=Ny7NmZu3XDndp_elCrz2W8K9OUjrAjHQuYianJR6RDM,24378
bs4/builder/__pycache__/__init__.cpython-312.pyc,,
bs4/builder/__pycache__/_html5lib.cpython-312.pyc,,
bs4/builder/__pycache__/_htmlparser.cpython-312.pyc,,
bs4/builder/__pycache__/_lxml.cpython-312.pyc,,
bs4/builder/_html5lib.py,sha256=YFOKZf3E22AEp_V2k49U5LmF26bpSZixZrZGSwM_iCU,18946
bs4/builder/_htmlparser.py,sha256=6RYsAXWb_ppMZGB-7lpEmJQ73tpzSu_CJ5QPaFcJu-Y,19169
bs4/builder/_lxml.py,sha256=ik6BFGnxAzV2-21S_Wc-7ZeA174muSA_ZhmpnAe3g0E,14904
bs4/dammit.py,sha256=G0cQfsEqfwJ-FIQMkXgCJwSHMn7t9vPepCrud6fZEKk,41158
bs4/diagnose.py,sha256=MRbN2bJSpa8VFt8HemqP8BK9hL5ronCxZmrfGRZYwBg,7911
bs4/element.py,sha256=jjP-cIA3oWJrAhky61wayot92SQFKzJMEE8My6uTPDM,86753
bs4/formatter.py,sha256=f5UBtvW9twrrQeLjBeLaKp4ntZpUDmUBY8jF3BiLraM,7206
bs4/tests/__init__.py,sha256=yFvfhDv5vOeho6NEZcI0AIpmuEe9bvC7TsqNp3hDGxQ,49185
bs4/tests/__pycache__/__init__.cpython-312.pyc,,
bs4/tests/__pycache__/test_builder.cpython-312.pyc,,
bs4/tests/__pycache__/test_builder_registry.cpython-312.pyc,,
bs4/tests/__pycache__/test_dammit.cpython-312.pyc,,
bs4/tests/__pycache__/test_docs.cpython-312.pyc,,
bs4/tests/__pycache__/test_element.cpython-312.pyc,,
bs4/tests/__pycache__/test_formatter.cpython-312.pyc,,
bs4/tests/__pycache__/test_html5lib.cpython-312.pyc,,
bs4/tests/__pycache__/test_htmlparser.cpython-312.pyc,,
bs4/tests/__pycache__/test_lxml.cpython-312.pyc,,
bs4/tests/__pycache__/test_navigablestring.cpython-312.pyc,,
bs4/tests/__pycache__/test_pageelement.cpython-312.pyc,,
bs4/tests/__pycache__/test_soup.cpython-312.pyc,,
bs4/tests/__pycache__/test_tag.cpython-312.pyc,,
bs4/tests/__pycache__/test_tree.cpython-312.pyc,,
bs4/tests/test_builder.py,sha256=nc2JE5EMrEf-p24qhf2R8qAV5PpFiOuNpYCmtmCjlTI,1115
bs4/tests/test_builder_registry.py,sha256=_Vh2CyYzv4BKoJdCa7s4lsBLUQptskfgiSn3U3810CQ,5068
bs4/tests/test_dammit.py,sha256=lS3EWCYCtxVE4fC_J2eTcXiChhuaL4Vcbo94B5geIL4,15680
bs4/tests/test_docs.py,sha256=xoAxnUfoQ7aRqGImwW_9BJDU8WNMZHIuvWqVepvWXt8,1127
bs4/tests/test_element.py,sha256=92oRSRoGk8gIXAbAGHErKzocx2MK32TqcQdUJ-dGQMo,2377
bs4/tests/test_formatter.py,sha256=0qV9H7mMDBcnFFH-dwNCrSm2zNi_40WMB2GMcV35PoY,4128
bs4/tests/test_html5lib.py,sha256=X6r13jfJ-OmG6SL_hyfFNXWs7sEEq_1TmCzCJclxvbA,8246
bs4/tests/test_htmlparser.py,sha256=BFCspIdhkr8Bss-kHufeNcwa_lvJpVWKgJskPoZgZ7E,5532
bs4/tests/test_lxml.py,sha256=deaf1YOrR8I0T5yZAV4TDxcAXHzVhdlnsSajGpBoxs0,7376
bs4/tests/test_navigablestring.py,sha256=RGSgziNf7cZnYdEPsoqL1B2I68TUJp1JmEQVxbh_ryA,5081
bs4/tests/test_pageelement.py,sha256=fpOU3W5IAz92b0A2VxWKkI5pApObMB17cNzXNF85FfA,27792
bs4/tests/test_soup.py,sha256=CUnK-rDccIlKMLBP4AweCqRDbPt3Lqzln_BpnBgKm4M,17810
bs4/tests/test_tag.py,sha256=f19uie7QehvgvhIqNWfjDRR4TKa-ftm_RRoo6LXZyqk,9016
bs4/tests/test_tree.py,sha256=y9Qvs8nnYj6RnGRSxtoYQQwSja-DlbtukCVs0neVwyU,47557

0
env/lib/python3.12/site-packages/beautifulsoup4-4.11.1.dist-info/REQUESTED vendored
View File

5
env/lib/python3.12/site-packages/beautifulsoup4-4.11.1.dist-info/WHEEL vendored
View File

@@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.31.1)
Root-Is-Purelib: true
Tag: py3-none-any

3
env/lib/python3.12/site-packages/beautifulsoup4-4.11.1.dist-info/top_level.txt vendored
View File

@@ -1,3 +0,0 @@
bs4
bs4/builder
bs4/tests

1
env/lib/python3.12/site-packages/bs4-0.0.1.dist-info/INSTALLER vendored
View File

@@ -1 +0,0 @@
pip

31
env/lib/python3.12/site-packages/bs4-0.0.1.dist-info/METADATA vendored
View File

@@ -1,31 +0,0 @@
Metadata-Version: 2.4
Name: bs4
Version: 0.0.1
Summary: Screen-scraping library
Home-page: https://pypi.python.org/pypi/beautifulsoup4
Download-URL: http://www.crummy.com/software/BeautifulSoup/bs4/download/
Author: Leonard Richardson
Author-email: leonardr@segfault.org
License: MIT
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Text Processing :: Markup :: HTML
Classifier: Topic :: Text Processing :: Markup :: XML
Classifier: Topic :: Text Processing :: Markup :: SGML
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Dist: beautifulsoup4
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: download-url
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: summary
Use `beautifulsoup4 <https://pypi.python.org/pypi/beautifulsoup4>`_ instead.

6
env/lib/python3.12/site-packages/bs4-0.0.1.dist-info/RECORD vendored
View File

@@ -1,6 +0,0 @@
bs4-0.0.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
bs4-0.0.1.dist-info/METADATA,sha256=HqauQ32-W19om3ixlGPi2uzvyQy0zDTXVZKSGOQJa00,1096
bs4-0.0.1.dist-info/RECORD,,
bs4-0.0.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
bs4-0.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
bs4-0.0.1.dist-info/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1

0
env/lib/python3.12/site-packages/bs4-0.0.1.dist-info/REQUESTED vendored
View File

5
env/lib/python3.12/site-packages/bs4-0.0.1.dist-info/WHEEL vendored
View File

@@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: setuptools (80.9.0)
Root-Is-Purelib: true
Tag: py3-none-any

1
env/lib/python3.12/site-packages/bs4-0.0.1.dist-info/top_level.txt vendored
View File

@@ -1 +0,0 @@

812
env/lib/python3.12/site-packages/bs4/__init__.py vendored
View File

@@ -1,812 +0,0 @@
"""Beautiful Soup Elixir and Tonic - "The Screen-Scraper's Friend".
http://www.crummy.com/software/BeautifulSoup/
Beautiful Soup uses a pluggable XML or HTML parser to parse a
(possibly invalid) document into a tree representation. Beautiful Soup
provides methods and Pythonic idioms that make it easy to navigate,
search, and modify the parse tree.
Beautiful Soup works with Python 3.5 and up. It works better if lxml
and/or html5lib is installed.
For more than you ever wanted to know about Beautiful Soup, see the
documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
"""
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.11.1"
__copyright__ = "Copyright (c) 2004-2022 Leonard Richardson"
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = ['BeautifulSoup']
from collections import Counter
import os
import re
import sys
import traceback
import warnings
# The very first thing we do is give a useful error if someone is
# running this code under Python 2.
if sys.version_info.major < 3:
raise ImportError('You are trying to use a Python 3-specific version of Beautiful Soup under Python 2. This will not work. The final version of Beautiful Soup to support Python 2 was 4.9.3.')
from .builder import (
builder_registry,
ParserRejectedMarkup,
XMLParsedAsHTMLWarning,
)
from .dammit import UnicodeDammit
from .element import (
CData,
Comment,
DEFAULT_OUTPUT_ENCODING,
Declaration,
Doctype,
NavigableString,
PageElement,
ProcessingInstruction,
PYTHON_SPECIFIC_ENCODINGS,
ResultSet,
Script,
Stylesheet,
SoupStrainer,
Tag,
TemplateString,
)
# Define some custom warnings.
class GuessedAtParserWarning(UserWarning):
"""The warning issued when BeautifulSoup has to guess what parser to
use -- probably because no parser was specified in the constructor.
"""
class MarkupResemblesLocatorWarning(UserWarning):
"""The warning issued when BeautifulSoup is given 'markup' that
actually looks like a resource locator -- a URL or a path to a file
on disk.
"""
class BeautifulSoup(Tag):
"""A data structure representing a parsed HTML or XML document.
Most of the methods you'll call on a BeautifulSoup object are inherited from
PageElement or Tag.
Internally, this class defines the basic interface called by the
tree builders when converting an HTML/XML document into a data
structure. The interface abstracts away the differences between
parsers. To write a new tree builder, you'll need to understand
these methods as a whole.
These methods will be called by the BeautifulSoup constructor:
* reset()
* feed(markup)
The tree builder may call these methods from its feed() implementation:
* handle_starttag(name, attrs) # See note about return value
* handle_endtag(name)
* handle_data(data) # Appends to the current data node
* endData(containerClass) # Ends the current data node
No matter how complicated the underlying parser is, you should be
able to build a tree using 'start tag' events, 'end tag' events,
'data' events, and "done with data" events.
If you encounter an empty-element tag (aka a self-closing tag,
like HTML's <br> tag), call handle_starttag and then
handle_endtag.
"""
# Since BeautifulSoup subclasses Tag, it's possible to treat it as
# a Tag with a .name. This name makes it clear the BeautifulSoup
# object isn't a real markup tag.
ROOT_TAG_NAME = '[document]'
# If the end-user gives no indication which tree builder they
# want, look for one with these features.
DEFAULT_BUILDER_FEATURES = ['html', 'fast']
# A string containing all ASCII whitespace characters, used in
# endData() to detect data chunks that seem 'empty'.
ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, pass the additional argument 'features=\"%(parser)s\"' to the BeautifulSoup constructor.\n"
def __init__(self, markup="", features=None, builder=None,
parse_only=None, from_encoding=None, exclude_encodings=None,
element_classes=None, **kwargs):
"""Constructor.
:param markup: A string or a file-like object representing
markup to be parsed.
:param features: Desirable features of the parser to be
used. This may be the name of a specific parser ("lxml",
"lxml-xml", "html.parser", or "html5lib") or it may be the
type of markup to be used ("html", "html5", "xml"). It's
recommended that you name a specific parser, so that
Beautiful Soup gives you the same results across platforms
and virtual environments.
:param builder: A TreeBuilder subclass to instantiate (or
instance to use) instead of looking one up based on
`features`. You only need to use this if you've implemented a
custom TreeBuilder.
:param parse_only: A SoupStrainer. Only parts of the document
matching the SoupStrainer will be considered. This is useful
when parsing part of a document that would otherwise be too
large to fit into memory.
:param from_encoding: A string indicating the encoding of the
document to be parsed. Pass this in if Beautiful Soup is
guessing wrongly about the document's encoding.
:param exclude_encodings: A list of strings indicating
encodings known to be wrong. Pass this in if you don't know
the document's encoding but you know Beautiful Soup's guess is
wrong.
:param element_classes: A dictionary mapping BeautifulSoup
classes like Tag and NavigableString, to other classes you'd
like to be instantiated instead as the parse tree is
built. This is useful for subclassing Tag or NavigableString
to modify default behavior.
:param kwargs: For backwards compatibility purposes, the
constructor accepts certain keyword arguments used in
Beautiful Soup 3. None of these arguments do anything in
Beautiful Soup 4; they will result in a warning and then be
ignored.
Apart from this, any keyword arguments passed into the
BeautifulSoup constructor are propagated to the TreeBuilder
constructor. This makes it possible to configure a
TreeBuilder by passing in arguments, not just by saying which
one to use.
"""
if 'convertEntities' in kwargs:
del kwargs['convertEntities']
warnings.warn(
"BS4 does not respect the convertEntities argument to the "
"BeautifulSoup constructor. Entities are always converted "
"to Unicode characters.")
if 'markupMassage' in kwargs:
del kwargs['markupMassage']
warnings.warn(
"BS4 does not respect the markupMassage argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for any necessary markup massage.")
if 'smartQuotesTo' in kwargs:
del kwargs['smartQuotesTo']
warnings.warn(
"BS4 does not respect the smartQuotesTo argument to the "
"BeautifulSoup constructor. Smart quotes are always converted "
"to Unicode characters.")
if 'selfClosingTags' in kwargs:
del kwargs['selfClosingTags']
warnings.warn(
"BS4 does not respect the selfClosingTags argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for understanding self-closing tags.")
if 'isHTML' in kwargs:
del kwargs['isHTML']
warnings.warn(
"BS4 does not respect the isHTML argument to the "
"BeautifulSoup constructor. Suggest you use "
"features='lxml' for HTML and features='lxml-xml' for "
"XML.")
def deprecated_argument(old_name, new_name):
if old_name in kwargs:
warnings.warn(
'The "%s" argument to the BeautifulSoup constructor '
'has been renamed to "%s."' % (old_name, new_name),
DeprecationWarning
)
return kwargs.pop(old_name)
return None
parse_only = parse_only or deprecated_argument(
"parseOnlyThese", "parse_only")
from_encoding = from_encoding or deprecated_argument(
"fromEncoding", "from_encoding")
if from_encoding and isinstance(markup, str):
warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
from_encoding = None
self.element_classes = element_classes or dict()
# We need this information to track whether or not the builder
# was specified well enough that we can omit the 'you need to
# specify a parser' warning.
original_builder = builder
original_features = features
if isinstance(builder, type):
# A builder class was passed in; it needs to be instantiated.
builder_class = builder
builder = None
elif builder is None:
if isinstance(features, str):
features = [features]
if features is None or len(features) == 0:
features = self.DEFAULT_BUILDER_FEATURES
builder_class = builder_registry.lookup(*features)
if builder_class is None:
raise FeatureNotFound(
"Couldn't find a tree builder with the features you "
"requested: %s. Do you need to install a parser library?"
% ",".join(features))
# At this point either we have a TreeBuilder instance in
# builder, or we have a builder_class that we can instantiate
# with the remaining **kwargs.
if builder is None:
builder = builder_class(**kwargs)
if not original_builder and not (
original_features == builder.NAME or
original_features in builder.ALTERNATE_NAMES
) and markup:
# The user did not tell us which TreeBuilder to use,
# and we had to guess. Issue a warning.
if builder.is_xml:
markup_type = "XML"
else:
markup_type = "HTML"
# This code adapted from warnings.py so that we get the same line
# of code as our warnings.warn() call gets, even if the answer is wrong
# (as it may be in a multithreading situation).
caller = None
try:
caller = sys._getframe(1)
except ValueError:
pass
if caller:
globals = caller.f_globals
line_number = caller.f_lineno
else:
globals = sys.__dict__
line_number= 1
filename = globals.get('__file__')
if filename:
fnl = filename.lower()
if fnl.endswith((".pyc", ".pyo")):
filename = filename[:-1]
if filename:
# If there is no filename at all, the user is most likely in a REPL,
# and the warning is not necessary.
values = dict(
filename=filename,
line_number=line_number,
parser=builder.NAME,
markup_type=markup_type
)
warnings.warn(
self.NO_PARSER_SPECIFIED_WARNING % values,
GuessedAtParserWarning, stacklevel=2
)
else:
if kwargs:
warnings.warn("Keyword arguments to the BeautifulSoup constructor will be ignored. These would normally be passed into the TreeBuilder constructor, but a TreeBuilder instance was passed in as `builder`.")
self.builder = builder
self.is_xml = builder.is_xml
self.known_xml = self.is_xml
self._namespaces = dict()
self.parse_only = parse_only
if hasattr(markup, 'read'): # It's a file-type object.
markup = markup.read()
elif len(markup) <= 256 and (
(isinstance(markup, bytes) and not b'<' in markup)
or (isinstance(markup, str) and not '<' in markup)
):
# Issue warnings for a couple beginner problems
# involving passing non-markup to Beautiful Soup.
# Beautiful Soup will still parse the input as markup,
# since that is sometimes the intended behavior.
if not self._markup_is_url(markup):
self._markup_resembles_filename(markup)
rejections = []
success = False
for (self.markup, self.original_encoding, self.declared_html_encoding,
self.contains_replacement_characters) in (
self.builder.prepare_markup(
markup, from_encoding, exclude_encodings=exclude_encodings)):
self.reset()
self.builder.initialize_soup(self)
try:
self._feed()
success = True
break
except ParserRejectedMarkup as e:
rejections.append(e)
pass
if not success:
other_exceptions = [str(e) for e in rejections]
raise ParserRejectedMarkup(
"The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help.\n\nOriginal exception(s) from parser:\n " + "\n ".join(other_exceptions)
)
# Clear out the markup and remove the builder's circular
# reference to this object.
self.markup = None
self.builder.soup = None
def __copy__(self):
"""Copy a BeautifulSoup object by converting the document to a string and parsing it again."""
copy = type(self)(
self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
)
# Although we encoded the tree to UTF-8, that may not have
# been the encoding of the original markup. Set the copy's
# .original_encoding to reflect the original object's
# .original_encoding.
copy.original_encoding = self.original_encoding
return copy
def __getstate__(self):
# Frequently a tree builder can't be pickled.
d = dict(self.__dict__)
if 'builder' in d and d['builder'] is not None and not self.builder.picklable:
d['builder'] = None
return d
@classmethod
def _decode_markup(cls, markup):
"""Ensure `markup` is bytes so it's safe to send into warnings.warn.
TODO: warnings.warn had this problem back in 2010 but it might not
anymore.
"""
if isinstance(markup, bytes):
decoded = markup.decode('utf-8', 'replace')
else:
decoded = markup
return decoded
@classmethod
def _markup_is_url(cls, markup):
"""Error-handling method to raise a warning if incoming markup looks
like a URL.
:param markup: A string.
:return: Whether or not the markup resembles a URL
closely enough to justify a warning.
"""
if isinstance(markup, bytes):
space = b' '
cant_start_with = (b"http:", b"https:")
elif isinstance(markup, str):
space = ' '
cant_start_with = ("http:", "https:")
else:
return False
if any(markup.startswith(prefix) for prefix in cant_start_with):
if not space in markup:
warnings.warn(
'The input looks more like a URL than markup. You may want to use'
' an HTTP client like requests to get the document behind'
' the URL, and feed that document to Beautiful Soup.',
MarkupResemblesLocatorWarning
)
return True
return False
@classmethod
def _markup_resembles_filename(cls, markup):
"""Error-handling method to raise a warning if incoming markup
resembles a filename.
:param markup: A bytestring or string.
:return: Whether or not the markup resembles a filename
closely enough to justify a warning.
"""
path_characters = '/\\'
extensions = ['.html', '.htm', '.xml', '.xhtml', '.txt']
if isinstance(markup, bytes):
path_characters = path_characters.encode("utf8")
extensions = [x.encode('utf8') for x in extensions]
filelike = False
if any(x in markup for x in path_characters):
filelike = True
else:
lower = markup.lower()
if any(lower.endswith(ext) for ext in extensions):
filelike = True
if filelike:
warnings.warn(
'The input looks more like a filename than markup. You may'
' want to open this file and pass the filehandle into'
' Beautiful Soup.',
MarkupResemblesLocatorWarning
)
return True
return False
def _feed(self):
"""Internal method that parses previously set markup, creating a large
number of Tag and NavigableString objects.
"""
# Convert the document to Unicode.
self.builder.reset()
self.builder.feed(self.markup)
# Close out any unfinished strings and close all the open tags.
self.endData()
while self.currentTag.name != self.ROOT_TAG_NAME:
self.popTag()
def reset(self):
"""Reset this object to a state as though it had never parsed any
markup.
"""
Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
self.hidden = 1
self.builder.reset()
self.current_data = []
self.currentTag = None
self.tagStack = []
self.open_tag_counter = Counter()
self.preserve_whitespace_tag_stack = []
self.string_container_stack = []
self.pushTag(self)
def new_tag(self, name, namespace=None, nsprefix=None, attrs={},
sourceline=None, sourcepos=None, **kwattrs):
"""Create a new Tag associated with this BeautifulSoup object.
:param name: The name of the new Tag.
:param namespace: The URI of the new Tag's XML namespace, if any.
:param prefix: The prefix for the new Tag's XML namespace, if any.
:param attrs: A dictionary of this Tag's attribute values; can
be used instead of `kwattrs` for attributes like 'class'
that are reserved words in Python.
:param sourceline: The line number where this tag was
(purportedly) found in its source document.
:param sourcepos: The character position within `sourceline` where this
tag was (purportedly) found.
:param kwattrs: Keyword arguments for the new Tag's attribute values.
"""
kwattrs.update(attrs)
return self.element_classes.get(Tag, Tag)(
None, self.builder, name, namespace, nsprefix, kwattrs,
sourceline=sourceline, sourcepos=sourcepos
)
def string_container(self, base_class=None):
container = base_class or NavigableString
# There may be a general override of NavigableString.
container = self.element_classes.get(
container, container
)
# On top of that, we may be inside a tag that needs a special
# container class.
if self.string_container_stack and container is NavigableString:
container = self.builder.string_containers.get(
self.string_container_stack[-1].name, container
)
return container
def new_string(self, s, subclass=None):
"""Create a new NavigableString associated with this BeautifulSoup
object.
"""
container = self.string_container(subclass)
return container(s)
def insert_before(self, *args):
"""This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
it because there is nothing before or after it in the parse tree.
"""
raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
def insert_after(self, *args):
"""This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
it because there is nothing before or after it in the parse tree.
"""
raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
def popTag(self):
"""Internal method called by _popToTag when a tag is closed."""
tag = self.tagStack.pop()
if tag.name in self.open_tag_counter:
self.open_tag_counter[tag.name] -= 1
if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
self.preserve_whitespace_tag_stack.pop()
if self.string_container_stack and tag == self.string_container_stack[-1]:
self.string_container_stack.pop()
#print("Pop", tag.name)
if self.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
"""Internal method called by handle_starttag when a tag is opened."""
#print("Push", tag.name)
if self.currentTag is not None:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
if tag.name != self.ROOT_TAG_NAME:
self.open_tag_counter[tag.name] += 1
if tag.name in self.builder.preserve_whitespace_tags:
self.preserve_whitespace_tag_stack.append(tag)
if tag.name in self.builder.string_containers:
self.string_container_stack.append(tag)
def endData(self, containerClass=None):
"""Method called by the TreeBuilder when the end of a data segment
occurs.
"""
if self.current_data:
current_data = ''.join(self.current_data)
# If whitespace is not preserved, and this string contains
# nothing but ASCII spaces, replace it with a single space
# or newline.
if not self.preserve_whitespace_tag_stack:
strippable = True
for i in current_data:
if i not in self.ASCII_SPACES:
strippable = False
break
if strippable:
if '\n' in current_data:
current_data = '\n'
else:
current_data = ' '
# Reset the data collector.
self.current_data = []
# Should we add this string to the tree at all?
if self.parse_only and len(self.tagStack) <= 1 and \
(not self.parse_only.text or \
not self.parse_only.search(current_data)):
return
containerClass = self.string_container(containerClass)
o = containerClass(current_data)
self.object_was_parsed(o)
def object_was_parsed(self, o, parent=None, most_recent_element=None):
"""Method called by the TreeBuilder to integrate an object into the parse tree."""
if parent is None:
parent = self.currentTag
if most_recent_element is not None:
previous_element = most_recent_element
else:
previous_element = self._most_recent_element
next_element = previous_sibling = next_sibling = None
if isinstance(o, Tag):
next_element = o.next_element
next_sibling = o.next_sibling
previous_sibling = o.previous_sibling
if previous_element is None:
previous_element = o.previous_element
fix = parent.next_element is not None
o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
self._most_recent_element = o
parent.contents.append(o)
# Check if we are inserting into an already parsed node.
if fix:
self._linkage_fixer(parent)
def _linkage_fixer(self, el):
"""Make sure linkage of this fragment is sound."""
first = el.contents[0]
child = el.contents[-1]
descendant = child
if child is first and el.parent is not None:
# Parent should be linked to first child
el.next_element = child
# We are no longer linked to whatever this element is
prev_el = child.previous_element
if prev_el is not None and prev_el is not el:
prev_el.next_element = None
# First child should be linked to the parent, and no previous siblings.
child.previous_element = el
child.previous_sibling = None
# We have no sibling as we've been appended as the last.
child.next_sibling = None
# This index is a tag, dig deeper for a "last descendant"
if isinstance(child, Tag) and child.contents:
descendant = child._last_descendant(False)
# As the final step, link last descendant. It should be linked
# to the parent's next sibling (if found), else walk up the chain
# and find a parent with a sibling. It should have no next sibling.
descendant.next_element = None
descendant.next_sibling = None
target = el
while True:
if target is None:
break
elif target.next_sibling is not None:
descendant.next_element = target.next_sibling
target.next_sibling.previous_element = child
break
target = target.parent
def _popToTag(self, name, nsprefix=None, inclusivePop=True):
"""Pops the tag stack up to and including the most recent
instance of the given tag.
If there are no open tags with the given name, nothing will be
popped.
:param name: Pop up to the most recent tag with this name.
:param nsprefix: The namespace prefix that goes with `name`.
:param inclusivePop: It this is false, pops the tag stack up
to but *not* including the most recent instqance of the
given tag.
"""
#print("Popping to %s" % name)
if name == self.ROOT_TAG_NAME:
# The BeautifulSoup object itself can never be popped.
return
most_recently_popped = None
stack_size = len(self.tagStack)
for i in range(stack_size - 1, 0, -1):
if not self.open_tag_counter.get(name):
break
t = self.tagStack[i]
if (name == t.name and nsprefix == t.prefix):
if inclusivePop:
most_recently_popped = self.popTag()
break
most_recently_popped = self.popTag()
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
sourcepos=None, namespaces=None):
"""Called by the tree builder when a new tag is encountered.
:param name: Name of the tag.
:param nsprefix: Namespace prefix for the tag.
:param attrs: A dictionary of attribute values.
:param sourceline: The line number where this tag was found in its
source document.
:param sourcepos: The character position within `sourceline` where this
tag was found.
:param namespaces: A dictionary of all namespace prefix mappings
currently in scope in the document.
If this method returns None, the tag was rejected by an active
SoupStrainer. You should proceed as if the tag had not occurred
in the document. For instance, if this was a self-closing tag,
don't call handle_endtag.
"""
# print("Start tag %s: %s" % (name, attrs))
self.endData()
if (self.parse_only and len(self.tagStack) <= 1
and (self.parse_only.text
or not self.parse_only.search_tag(name, attrs))):
return None
tag = self.element_classes.get(Tag, Tag)(
self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element,
sourceline=sourceline, sourcepos=sourcepos,
namespaces=namespaces
)
if tag is None:
return tag
if self._most_recent_element is not None:
self._most_recent_element.next_element = tag
self._most_recent_element = tag
self.pushTag(tag)
return tag
def handle_endtag(self, name, nsprefix=None):
"""Called by the tree builder when an ending tag is encountered.
:param name: Name of the tag.
:param nsprefix: Namespace prefix for the tag.
"""
#print("End tag: " + name)
self.endData()
self._popToTag(name, nsprefix)
def handle_data(self, data):
"""Called by the tree builder when a chunk of textual data is encountered."""
self.current_data.append(data)
def decode(self, pretty_print=False,
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
formatter="minimal"):
"""Returns a string or Unicode representation of the parse tree
as an HTML or XML document.
:param pretty_print: If this is True, indentation will be used to
make the document more readable.
:param eventual_encoding: The encoding of the final document.
If this is None, the document will be a Unicode string.
"""
if self.is_xml:
# Print the XML declaration
encoding_part = ''
if eventual_encoding in PYTHON_SPECIFIC_ENCODINGS:
# This is a special Python encoding; it can't actually
# go into an XML document because it means nothing
# outside of Python.
eventual_encoding = None
if eventual_encoding != None:
encoding_part = ' encoding="%s"' % eventual_encoding
prefix = '<?xml version="1.0"%s?>\n' % encoding_part
else:
prefix = ''
if not pretty_print:
indent_level = None
else:
indent_level = 0
return prefix + super(BeautifulSoup, self).decode(
indent_level, eventual_encoding, formatter)
# Aliases to make it easier to get started quickly, e.g. 'from bs4 import _soup'
_s = BeautifulSoup
_soup = BeautifulSoup
class BeautifulStoneSoup(BeautifulSoup):
"""Deprecated interface to an XML parser."""
def __init__(self, *args, **kwargs):
kwargs['features'] = 'xml'
warnings.warn(
'The BeautifulStoneSoup class is deprecated. Instead of using '
'it, pass features="xml" into the BeautifulSoup constructor.',
DeprecationWarning
)
super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
class StopParsing(Exception):
"""Exception raised by a TreeBuilder if it's unable to continue parsing."""
pass
class FeatureNotFound(ValueError):
"""Exception raised by the BeautifulSoup constructor if no parser with the
requested features is found.
"""
pass
#If this file is run as a script, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print((soup.prettify()))

631
env/lib/python3.12/site-packages/bs4/builder/__init__.py vendored
View File

@@ -1,631 +0,0 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
from collections import defaultdict
import itertools
import re
import warnings
import sys
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
RubyParenthesisString,
RubyTextString,
Stylesheet,
Script,
TemplateString,
nonwhitespace_re
)
__all__ = [
'HTMLTreeBuilder',
'SAXTreeBuilder',
'TreeBuilder',
'TreeBuilderRegistry',
]
# Some useful features for a TreeBuilder to have.
FAST = 'fast'
PERMISSIVE = 'permissive'
STRICT = 'strict'
XML = 'xml'
HTML = 'html'
HTML_5 = 'html5'
class XMLParsedAsHTMLWarning(UserWarning):
"""The warning issued when an HTML parser is used to parse
XML that is not XHTML.
"""
MESSAGE = """It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor."""
class TreeBuilderRegistry(object):
"""A way of looking up TreeBuilder subclasses by their name or by desired
features.
"""
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised features.
:param treebuilder_class: A subclass of Treebuilder. its .features
attribute should list its features.
"""
for feature in treebuilder_class.features:
self.builders_for_feature[feature].insert(0, treebuilder_class)
self.builders.insert(0, treebuilder_class)
def lookup(self, *features):
"""Look up a TreeBuilder subclass with the desired features.
:param features: A list of features to look for. If none are
provided, the most recently registered TreeBuilder subclass
will be used.
:return: A TreeBuilder subclass, or None if there's no
registered subclass with all the requested features.
"""
if len(self.builders) == 0:
# There are no builders at all.
return None
if len(features) == 0:
# They didn't ask for any features. Give them the most
# recently registered builder.
return self.builders[0]
# Go down the list of features in order, and eliminate any builders
# that don't match every feature.
features = list(features)
features.reverse()
candidates = None
candidate_set = None
while len(features) > 0:
feature = features.pop()
we_have_the_feature = self.builders_for_feature.get(feature, [])
if len(we_have_the_feature) > 0:
if candidates is None:
candidates = we_have_the_feature
candidate_set = set(candidates)
else:
# Eliminate any candidates that don't have this feature.
candidate_set = candidate_set.intersection(
set(we_have_the_feature))
# The only valid candidates are the ones in candidate_set.
# Go through the original list of candidates and pick the first one
# that's in candidate_set.
if candidate_set is None:
return None
for candidate in candidates:
if candidate in candidate_set:
return candidate
return None
# The BeautifulSoup class will take feature lists from developers and use them
# to look up builders in this registry.
builder_registry = TreeBuilderRegistry()
class TreeBuilder(object):
"""Turn a textual document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
features = []
is_xml = False
picklable = False
empty_element_tags = None # A tag will be considered an empty-element
# tag when and only when it has no contents.
# A value for these tag/attribute combinations is a space- or
# comma-separated list of CDATA, rather than a single CDATA.
DEFAULT_CDATA_LIST_ATTRIBUTES = {}
# Whitespace should be preserved inside these tags.
DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
# The textual contents of tags with these names should be
# instantiated with some class other than NavigableString.
DEFAULT_STRING_CONTAINERS = {}
USE_DEFAULT = object()
# Most parsers don't keep track of line numbers.
TRACKS_LINE_NUMBERS = False
def __init__(self, multi_valued_attributes=USE_DEFAULT,
preserve_whitespace_tags=USE_DEFAULT,
store_line_numbers=USE_DEFAULT,
string_containers=USE_DEFAULT,
):
"""Constructor.
:param multi_valued_attributes: If this is set to None, the
TreeBuilder will not turn any values for attributes like
'class' into lists. Setting this to a dictionary will
customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
for an example.
Internally, these are called "CDATA list attributes", but that
probably doesn't make sense to an end-user, so the argument name
is `multi_valued_attributes`.
:param preserve_whitespace_tags: A list of tags to treat
the way <pre> tags are treated in HTML. Tags in this list
are immune from pretty-printing; their contents will always be
output as-is.
:param string_containers: A dictionary mapping tag names to
the classes that should be instantiated to contain the textual
contents of those tags. The default is to use NavigableString
for every tag, no matter what the name. You can override the
default by changing DEFAULT_STRING_CONTAINERS.
:param store_line_numbers: If the parser keeps track of the
line numbers and positions of the original markup, that
information will, by default, be stored in each corresponding
`Tag` object. You can turn this off by passing
store_line_numbers=False. If the parser you're using doesn't
keep track of this information, then setting store_line_numbers=True
will do nothing.
"""
self.soup = None
if multi_valued_attributes is self.USE_DEFAULT:
multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
self.cdata_list_attributes = multi_valued_attributes
if preserve_whitespace_tags is self.USE_DEFAULT:
preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
self.preserve_whitespace_tags = preserve_whitespace_tags
if store_line_numbers == self.USE_DEFAULT:
store_line_numbers = self.TRACKS_LINE_NUMBERS
self.store_line_numbers = store_line_numbers
if string_containers == self.USE_DEFAULT:
string_containers = self.DEFAULT_STRING_CONTAINERS
self.string_containers = string_containers
def initialize_soup(self, soup):
"""The BeautifulSoup object has been initialized and is now
being associated with the TreeBuilder.
:param soup: A BeautifulSoup object.
"""
self.soup = soup
def reset(self):
"""Do any work necessary to reset the underlying parser
for a new document.
By default, this does nothing.
"""
pass
def can_be_empty_element(self, tag_name):
"""Might a tag with this name be an empty-element tag?
The final markup may or may not actually present this tag as
self-closing.
For instance: an HTMLBuilder does not consider a <p> tag to be
an empty-element tag (it's not in
HTMLBuilder.empty_element_tags). This means an empty <p> tag
will be presented as "<p></p>", not "<p/>" or "<p>".
The default implementation has no opinion about which tags are
empty-element tags, so a tag will be presented as an
empty-element tag if and only if it has no children.
"<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will
be left alone.
:param tag_name: The name of a markup tag.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
This method is not implemented in TreeBuilder; it must be
implemented in subclasses.
:return: None.
"""
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding. NOTE: This argument is not used by the
calling code and can probably be removed.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
By default, the only strategy is to parse the markup
as-is. See `LXMLTreeBuilderForXML` and
`HTMLParserTreeBuilder` for implementations that take into
account the quirks of particular parsers.
"""
yield markup, None, None, False
def test_fragment_to_document(self, fragment):
"""Wrap an HTML fragment to make it look like a document.
Different parsers do this differently. For instance, lxml
introduces an empty <head> tag, and html5lib
doesn't. Abstracting this away lets us write simple tests
which run HTML fragments through the parser and compare the
results against other HTML fragments.
This method should not be used outside of tests.
:param fragment: A string -- fragment of HTML.
:return: A string -- a full HTML document.
"""
return fragment
def set_up_substitutions(self, tag):
"""Set up any substitutions that will need to be performed on
a `Tag` when it's output as a string.
By default, this does nothing. See `HTMLTreeBuilder` for a
case where this is used.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""When an attribute value is associated with a tag that can
have multiple values for that attribute, convert the string
value to a list of strings.
Basically, replaces class="foo bar" with class=["foo", "bar"]
NOTE: This method modifies its input in place.
:param tag_name: The name of a tag.
:param attrs: A dictionary containing the tag's attributes.
Any appropriate attribute values will be modified in place.
"""
if not attrs:
return attrs
if self.cdata_list_attributes:
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in list(attrs.keys()):
if attr in universal or (tag_specific and attr in tag_specific):
# We have a "class"-type attribute whose string
# value is a whitespace-separated list of
# values. Split it into a list.
value = attrs[attr]
if isinstance(value, str):
values = nonwhitespace_re.findall(value)
else:
# html5lib sometimes calls setAttributes twice
# for the same tag when rearranging the parse
# tree. On the second call the attribute value
# here is already a list. If this happens,
# leave the value alone rather than trying to
# split it again.
values = value
attrs[attr] = values
return attrs
class SAXTreeBuilder(TreeBuilder):
"""A Beautiful Soup treebuilder that listens for SAX events.
This is not currently used for anything, but it demonstrates
how a simple TreeBuilder would work.
"""
def feed(self, markup):
raise NotImplementedError()
def close(self):
pass
def startElement(self, name, attrs):
attrs = dict((key[1], value) for key, value in list(attrs.items()))
#print("Start %s, %r" % (name, attrs))
self.soup.handle_starttag(name, attrs)
def endElement(self, name):
#print("End %s" % name)
self.soup.handle_endtag(name)
def startElementNS(self, nsTuple, nodeName, attrs):
# Throw away (ns, nodeName) for now.
self.startElement(nodeName, attrs)
def endElementNS(self, nsTuple, nodeName):
# Throw away (ns, nodeName) for now.
self.endElement(nodeName)
#handler.endElementNS((ns, node.nodeName), node.nodeName)
def startPrefixMapping(self, prefix, nodeValue):
# Ignore the prefix for now.
pass
def endPrefixMapping(self, prefix):
# Ignore the prefix for now.
# handler.endPrefixMapping(prefix)
pass
def characters(self, content):
self.soup.handle_data(content)
def startDocument(self):
pass
def endDocument(self):
pass
class HTMLTreeBuilder(TreeBuilder):
"""This TreeBuilder knows facts about HTML.
Such as which tags are empty-element tags.
"""
empty_element_tags = set([
# These are from HTML5.
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
# These are from earlier versions of HTML and are removed in HTML5.
'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
])
# The HTML standard defines these as block-level elements. Beautiful
# Soup does not treat these elements differently from other elements,
# but it may do so eventually, and this information is available if
# you need to use it.
block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
# These HTML tags need special treatment so they can be
# represented by a string class other than NavigableString.
#
# For some of these tags, it's because the HTML standard defines
# an unusual content model for them. I made this list by going
# through the HTML spec
# (https://html.spec.whatwg.org/#metadata-content) and looking for
# "metadata content" elements that can contain strings.
#
# The Ruby tags (<rt> and <rp>) are here despite being normal
# "phrasing content" tags, because the content they contain is
# qualitatively different from other text in the document, and it
# can be useful to be able to distinguish it.
#
# TODO: Arguably <noscript> could go here but it seems
# qualitatively different from the other tags.
DEFAULT_STRING_CONTAINERS = {
'rt' : RubyTextString,
'rp' : RubyParenthesisString,
'style': Stylesheet,
'script': Script,
'template': TemplateString,
}
# The HTML standard defines these attributes as containing a
# space-separated list of values, not a single value. That is,
# class="foo bar" means that the 'class' attribute has two values,
# 'foo' and 'bar', not the single value 'foo bar'. When we
# encounter one of these attributes, we will parse its value into
# a list of values if possible. Upon output, the list will be
# converted back into a string.
DEFAULT_CDATA_LIST_ATTRIBUTES = {
"*" : ['class', 'accesskey', 'dropzone'],
"a" : ['rel', 'rev'],
"link" : ['rel', 'rev'],
"td" : ["headers"],
"th" : ["headers"],
"td" : ["headers"],
"form" : ["accept-charset"],
"object" : ["archive"],
# These are HTML5 specific, as are *.accesskey and *.dropzone above.
"area" : ["rel"],
"icon" : ["sizes"],
"iframe" : ["sandbox"],
"output" : ["for"],
}
DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
def set_up_substitutions(self, tag):
"""Replace the declared encoding in a <meta> tag with a placeholder,
to be substituted when the tag is output to a string.
An HTML document may come in to Beautiful Soup as one
encoding, but exit in a different encoding, and the <meta> tag
needs to be changed to reflect this.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
http_equiv = tag.get('http-equiv')
content = tag.get('content')
charset = tag.get('charset')
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag['charset'] = CharsetMetaAttributeValue(charset)
elif (content is not None and http_equiv is not None
and http_equiv.lower() == 'content-type'):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag['content'] = ContentMetaAttributeValue(content)
return (meta_encoding is not None)
class DetectsXMLParsedAsHTML(object):
"""A mixin class for any class (a TreeBuilder, or some class used by a
TreeBuilder) that's in a position to detect whether an XML
document is being incorrectly parsed as HTML, and issue an
appropriate warning.
This requires being able to observe an incoming processing
instruction that might be an XML declaration, and also able to
observe tags as they're opened. If you can't do that for a given
TreeBuilder, there's a less reliable implementation based on
examining the raw markup.
"""
# Regular expression for seeing if markup has an <html> tag.
LOOKS_LIKE_HTML = re.compile("<[^ +]html", re.I)
LOOKS_LIKE_HTML_B = re.compile(b"<[^ +]html", re.I)
XML_PREFIX = '<?xml'
XML_PREFIX_B = b'<?xml'
@classmethod
def warn_if_markup_looks_like_xml(cls, markup):
"""Perform a check on some markup to see if it looks like XML
that's not XHTML. If so, issue a warning.
This is much less reliable than doing the check while parsing,
but some of the tree builders can't do that.
:return: True if the markup looks like non-XHTML XML, False
otherwise.
"""
if isinstance(markup, bytes):
prefix = cls.XML_PREFIX_B
looks_like_html = cls.LOOKS_LIKE_HTML_B
else:
prefix = cls.XML_PREFIX
looks_like_html = cls.LOOKS_LIKE_HTML
if (markup is not None
and markup.startswith(prefix)
and not looks_like_html.search(markup[:500])
):
cls._warn()
return True
return False
@classmethod
def _warn(cls):
"""Issue a warning about XML being parsed as HTML."""
warnings.warn(
XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning
)
def _initialize_xml_detector(self):
"""Call this method before parsing a document."""
self._first_processing_instruction = None
self._root_tag = None
def _document_might_be_xml(self, processing_instruction):
"""Call this method when encountering an XML declaration, or a
"processing instruction" that might be an XML declaration.
"""
if (self._first_processing_instruction is not None
or self._root_tag is not None):
# The document has already started. Don't bother checking
# anymore.
return
self._first_processing_instruction = processing_instruction
# We won't know until we encounter the first tag whether or
# not this is actually a problem.
def _root_tag_encountered(self, name):
"""Call this when you encounter the document's root tag.
This is where we actually check whether an XML document is
being incorrectly parsed as HTML, and issue the warning.
"""
if self._root_tag is not None:
# This method was incorrectly called multiple times. Do
# nothing.
return
self._root_tag = name
if (name != 'html' and self._first_processing_instruction is not None
and self._first_processing_instruction.lower().startswith('xml ')):
# We encountered an XML declaration and then a tag other
# than 'html'. This is a reliable indicator that a
# non-XHTML document is being parsed as XML.
self._warn()
def register_treebuilders_from(module):
"""Copy TreeBuilders from the given module into this module."""
this_module = sys.modules[__name__]
for name in module.__all__:
obj = getattr(module, name)
if issubclass(obj, TreeBuilder):
setattr(this_module, name, obj)
this_module.__all__.append(name)
# Register the builder while we're at it.
this_module.builder_registry.register(obj)
class ParserRejectedMarkup(Exception):
"""An Exception to be raised when the underlying parser simply
refuses to parse the given markup.
"""
def __init__(self, message_or_exception):
"""Explain why the parser rejected the given markup, either
with a textual explanation or another exception.
"""
if isinstance(message_or_exception, Exception):
e = message_or_exception
message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
super(ParserRejectedMarkup, self).__init__(message_or_exception)
# Builders are registered in reverse order of priority, so that custom
# builder registrations will take precedence. In general, we want lxml
# to take precedence over html5lib, because it's faster. And we only
# want to use HTMLParser as a last resort.
from . import _htmlparser
register_treebuilders_from(_htmlparser)
try:
from . import _html5lib
register_treebuilders_from(_html5lib)
except ImportError:
# They don't have html5lib installed.
pass
try:
from . import _lxml
register_treebuilders_from(_lxml)
except ImportError:
# They don't have lxml installed.
pass

473
env/lib/python3.12/site-packages/bs4/builder/_html5lib.py vendored
View File

@@ -1,473 +0,0 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTML5TreeBuilder',
]
import warnings
import re
from bs4.builder import (
DetectsXMLParsedAsHTML,
PERMISSIVE,
HTML,
HTML_5,
HTMLTreeBuilder,
)
from bs4.element import (
NamespacedAttribute,
nonwhitespace_re,
)
import html5lib
from html5lib.constants import (
namespaces,
prefixes,
)
from bs4.element import (
Comment,
Doctype,
NavigableString,
Tag,
)
try:
# Pre-0.99999999
from html5lib.treebuilders import _base as treebuilder_base
new_html5lib = False
except ImportError as e:
# 0.99999999 and up
from html5lib.treebuilders import base as treebuilder_base
new_html5lib = True
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree.
Note that this TreeBuilder does not support some features common
to HTML TreeBuilders. Some of these features could theoretically
be implemented, but at the very least it's quite difficult,
because html5lib moves the parse tree around as it's being built.
* This TreeBuilder doesn't use different subclasses of NavigableString
based on the name of the tag in which the string was found.
* You can't use a SoupStrainer to parse only part of a document.
"""
NAME = "html5lib"
features = [NAME, PERMISSIVE, HTML_5, HTML]
# html5lib can tell us which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def prepare_markup(self, markup, user_specified_encoding,
document_declared_encoding=None, exclude_encodings=None):
# Store the user-specified encoding for use later on.
self.user_specified_encoding = user_specified_encoding
# document_declared_encoding and exclude_encodings aren't used
# ATM because the html5lib TreeBuilder doesn't use
# UnicodeDammit.
if exclude_encodings:
warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
# html5lib only parses HTML, so if it's given XML that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
yield (markup, None, None, False)
# These methods are defined by Beautiful Soup.
def feed(self, markup):
if self.soup.parse_only is not None:
warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
self.underlying_builder.parser = parser
extra_kwargs = dict()
if not isinstance(markup, str):
if new_html5lib:
extra_kwargs['override_encoding'] = self.user_specified_encoding
else:
extra_kwargs['encoding'] = self.user_specified_encoding
doc = parser.parse(markup, **extra_kwargs)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, str):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
original_encoding = parser.tokenizer.stream.charEncoding[0]
if not isinstance(original_encoding, str):
# In 0.99999999 and up, the encoding is an html5lib
# Encoding object. We want to use a string for compatibility
# with other tree builders.
original_encoding = original_encoding.name
doc.original_encoding = original_encoding
self.underlying_builder.parser = None
def create_treebuilder(self, namespaceHTMLElements):
self.underlying_builder = TreeBuilderForHtml5lib(
namespaceHTMLElements, self.soup,
store_line_numbers=self.store_line_numbers
)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, soup=None,
store_line_numbers=True, **kwargs):
if soup:
self.soup = soup
else:
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup(
"", "html.parser", store_line_numbers=store_line_numbers,
**kwargs
)
# TODO: What are **kwargs exactly? Should they be passed in
# here in addition to/instead of being passed to the BeautifulSoup
# constructor?
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
# This will be set later to an html5lib.html5parser.HTMLParser
# object, which we can use to track the current line number.
self.parser = None
self.store_line_numbers = store_line_numbers
def documentClass(self):
self.soup.reset()
return Element(self.soup, self.soup, None)
def insertDoctype(self, token):
name = token["name"]
publicId = token["publicId"]
systemId = token["systemId"]
doctype = Doctype.for_name_and_ids(name, publicId, systemId)
self.soup.object_was_parsed(doctype)
def elementClass(self, name, namespace):
kwargs = {}
if self.parser and self.store_line_numbers:
# This represents the point immediately after the end of the
# tag. We don't know when the tag started, but we do know
# where it ended -- the character just before this one.
sourceline, sourcepos = self.parser.tokenizer.stream.position()
kwargs['sourceline'] = sourceline
kwargs['sourcepos'] = sourcepos-1
tag = self.soup.new_tag(name, namespace, **kwargs)
return Element(tag, self.soup, namespace)
def commentClass(self, data):
return TextNode(Comment(data), self.soup)
def fragmentClass(self):
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup("", "html.parser")
self.soup.name = "[document_fragment]"
return Element(self.soup, self.soup, None)
def appendChild(self, node):
# XXX This code is not covered by the BS4 tests.
self.soup.append(node.element)
def getDocument(self):
return self.soup
def getFragment(self):
return treebuilder_base.TreeBuilder.getFragment(self).element
def testSerializer(self, element):
from bs4 import BeautifulSoup
rv = []
doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
def serializeElement(element, indent=0):
if isinstance(element, BeautifulSoup):
pass
if isinstance(element, Doctype):
m = doctype_re.match(element)
if m:
name = m.group(1)
if m.lastindex > 1:
publicId = m.group(2) or ""
systemId = m.group(3) or m.group(4) or ""
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
(' ' * indent, name, publicId, systemId))
else:
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
else:
rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
elif isinstance(element, Comment):
rv.append("|%s<!-- %s -->" % (' ' * indent, element))
elif isinstance(element, NavigableString):
rv.append("|%s\"%s\"" % (' ' * indent, element))
else:
if element.namespace:
name = "%s %s" % (prefixes[element.namespace],
element.name)
else:
name = element.name
rv.append("|%s<%s>" % (' ' * indent, name))
if element.attrs:
attributes = []
for name, value in list(element.attrs.items()):
if isinstance(name, NamespacedAttribute):
name = "%s %s" % (prefixes[name.namespace], name.name)
if isinstance(value, list):
value = " ".join(value)
attributes.append((name, value))
for name, value in sorted(attributes):
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
indent += 2
for child in element.children:
serializeElement(child, indent)
serializeElement(element, 0)
return "\n".join(rv)
class AttrList(object):
def __init__(self, element):
self.element = element
self.attrs = dict(self.element.attrs)
def __iter__(self):
return list(self.attrs.items()).__iter__()
def __setitem__(self, name, value):
# If this attribute is a multi-valued attribute for this element,
# turn its value into a list.
list_attr = self.element.cdata_list_attributes or {}
if (name in list_attr.get('*')
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = nonwhitespace_re.findall(value)
self.element[name] = value
def items(self):
return list(self.attrs.items())
def keys(self):
return list(self.attrs.keys())
def __len__(self):
return len(self.attrs)
def __getitem__(self, name):
return self.attrs[name]
def __contains__(self, name):
return name in list(self.attrs.keys())
class Element(treebuilder_base.Node):
def __init__(self, element, soup, namespace):
treebuilder_base.Node.__init__(self, element.name)
self.element = element
self.soup = soup
self.namespace = namespace
def appendChild(self, node):
string_child = child = None
if isinstance(node, str):
# Some other piece of code decided to pass in a string
# instead of creating a TextElement object to contain the
# string.
string_child = child = node
elif isinstance(node, Tag):
# Some other piece of code decided to pass in a Tag
# instead of creating an Element object to contain the
# Tag.
child = node
elif node.element.__class__ == NavigableString:
string_child = child = node.element
node.parent = self
else:
child = node.element
node.parent = self
if not isinstance(child, str) and child.parent is not None:
node.element.extract()
if (string_child is not None and self.element.contents
and self.element.contents[-1].__class__ == NavigableString):
# We are appending a string onto another string.
# TODO This has O(n^2) performance, for input like
# "a</a>a</a>a</a>..."
old_element = self.element.contents[-1]
new_element = self.soup.new_string(old_element + string_child)
old_element.replace_with(new_element)
self.soup._most_recent_element = new_element
else:
if isinstance(node, str):
# Create a brand new NavigableString from this string.
child = self.soup.new_string(node)
# Tell Beautiful Soup to act as if it parsed this element
# immediately after the parent's last descendant. (Or
# immediately after the parent, if it has no children.)
if self.element.contents:
most_recent_element = self.element._last_descendant(False)
elif self.element.next_element is not None:
# Something from further ahead in the parse tree is
# being inserted into this earlier element. This is
# very annoying because it means an expensive search
# for the last element in the tree.
most_recent_element = self.soup._last_descendant()
else:
most_recent_element = self.element
self.soup.object_was_parsed(
child, parent=self.element,
most_recent_element=most_recent_element)
def getAttributes(self):
if isinstance(self.element, Comment):
return {}
return AttrList(self.element)
def setAttributes(self, attributes):
if attributes is not None and len(attributes) > 0:
converted_attributes = []
for name, value in list(attributes.items()):
if isinstance(name, tuple):
new_name = NamespacedAttribute(*name)
del attributes[name]
attributes[new_name] = value
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
for name, value in list(attributes.items()):
self.element[name] = value
# The attributes may contain variables that need substitution.
# Call set_up_substitutions manually.
#
# The Tag constructor called this method when the Tag was created,
# but we just set/changed the attributes, so call it again.
self.soup.builder.set_up_substitutions(self.element)
attributes = property(getAttributes, setAttributes)
def insertText(self, data, insertBefore=None):
text = TextNode(self.soup.new_string(data), self.soup)
if insertBefore:
self.insertBefore(text, insertBefore)
else:
self.appendChild(text)
def insertBefore(self, node, refNode):
index = self.element.index(refNode.element)
if (node.element.__class__ == NavigableString and self.element.contents
and self.element.contents[index-1].__class__ == NavigableString):
# (See comments in appendChild)
old_node = self.element.contents[index-1]
new_str = self.soup.new_string(old_node + node.element)
old_node.replace_with(new_str)
else:
self.element.insert(index, node.element)
node.parent = self
def removeChild(self, node):
node.element.extract()
def reparentChildren(self, new_parent):
"""Move all of this tag's children into another tag."""
# print("MOVE", self.element.contents)
# print("FROM", self.element)
# print("TO", new_parent.element)
element = self.element
new_parent_element = new_parent.element
# Determine what this tag's next_element will be once all the children
# are removed.
final_next_element = element.next_sibling
new_parents_last_descendant = new_parent_element._last_descendant(False, False)
if len(new_parent_element.contents) > 0:
# The new parent already contains children. We will be
# appending this tag's children to the end.
new_parents_last_child = new_parent_element.contents[-1]
new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
else:
# The new parent contains no children.
new_parents_last_child = None
new_parents_last_descendant_next_element = new_parent_element.next_element
to_append = element.contents
if len(to_append) > 0:
# Set the first child's previous_element and previous_sibling
# to elements within the new parent
first_child = to_append[0]
if new_parents_last_descendant is not None:
first_child.previous_element = new_parents_last_descendant
else:
first_child.previous_element = new_parent_element
first_child.previous_sibling = new_parents_last_child
if new_parents_last_descendant is not None:
new_parents_last_descendant.next_element = first_child
else:
new_parent_element.next_element = first_child
if new_parents_last_child is not None:
new_parents_last_child.next_sibling = first_child
# Find the very last element being moved. It is now the
# parent's last descendant. It has no .next_sibling and
# its .next_element is whatever the previous last
# descendant had.
last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element is not None:
# TODO: This code has no test coverage and I'm not sure
# how to get html5lib to go through this path, but it's
# just the other side of the previous line.
new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
last_childs_last_descendant.next_sibling = None
for child in to_append:
child.parent = new_parent_element
new_parent_element.contents.append(child)
# Now that this element has no children, change its .next_element.
element.contents = []
element.next_element = final_next_element
# print("DONE WITH MOVE")
# print("FROM", self.element)
# print("TO", new_parent_element)
def cloneNode(self):
tag = self.soup.new_tag(self.element.name, self.namespace)
node = Element(tag, self.soup, self.namespace)
for key,value in self.attributes:
node.attributes[key] = value
return node
def hasContent(self):
return self.element.contents
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
nameTuple = property(getNameTuple)
class TextNode(Element):
def __init__(self, element, soup):
treebuilder_base.Node.__init__(self, None)
self.element = element
self.soup = soup
def cloneNode(self):
raise NotImplementedError

499
env/lib/python3.12/site-packages/bs4/builder/_htmlparser.py vendored
View File

@@ -1,499 +0,0 @@
# encoding: utf-8
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTMLParserTreeBuilder',
]
from html.parser import HTMLParser
try:
from html.parser import HTMLParseError
except ImportError as e:
# HTMLParseError is removed in Python 3.5. Since it can never be
# thrown in 3.5, we can just define our own class as a placeholder.
class HTMLParseError(Exception):
pass
import sys
import warnings
# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
# argument, which we'd like to set to False. Unfortunately,
# http://bugs.python.org/issue13273 makes strict=True a better bet
# before Python 3.2.3.
#
# At the end of this file, we monkeypatch HTMLParser so that
# strict=True works well on Python 3.2.2.
major, minor, release = sys.version_info[:3]
CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
from bs4.element import (
CData,
Comment,
Declaration,
Doctype,
ProcessingInstruction,
)
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.builder import (
DetectsXMLParsedAsHTML,
HTML,
HTMLTreeBuilder,
STRICT,
)
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
"""A subclass of the Python standard library's HTMLParser class, which
listens for HTMLParser events and translates them into calls
to Beautiful Soup's tree construction API.
"""
# Strategies for handling duplicate attributes
IGNORE = 'ignore'
REPLACE = 'replace'
def __init__(self, *args, **kwargs):
"""Constructor.
:param on_duplicate_attribute: A strategy for what to do if a
tag includes the same attribute more than once. Accepted
values are: REPLACE (replace earlier values with later
ones, the default), IGNORE (keep the earliest value
encountered), or a callable. A callable must take three
arguments: the dictionary of attributes already processed,
the name of the duplicate attribute, and the most recent value
encountered.
"""
self.on_duplicate_attribute = kwargs.pop(
'on_duplicate_attribute', self.REPLACE
)
HTMLParser.__init__(self, *args, **kwargs)
# Keep a list of empty-element tags that were encountered
# without an explicit closing tag. If we encounter a closing tag
# of this type, we'll associate it with one of those entries.
#
# This isn't a stack because we don't care about the
# order. It's a list of closing tags we've already handled and
# will ignore, assuming they ever show up.
self.already_closed_empty_element = []
self._initialize_xml_detector()
def error(self, msg):
"""In Python 3, HTMLParser subclasses must implement error(), although
this requirement doesn't appear to be documented.
In Python 2, HTMLParser implements error() by raising an exception,
which we don't want to do.
In any event, this method is called only on very strange
markup and our best strategy is to pretend it didn't happen
and keep going.
"""
warnings.warn(msg)
def handle_startendtag(self, name, attrs):
"""Handle an incoming empty-element tag.
This is only called when the markup looks like <tag/>.
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
"""
# is_startend() tells handle_starttag not to close the tag
# just because its name matches a known empty-element tag. We
# know that this is an empty-element tag and we want to call
# handle_endtag ourselves.
tag = self.handle_starttag(name, attrs, handle_empty_element=False)
self.handle_endtag(name)
def handle_starttag(self, name, attrs, handle_empty_element=True):
"""Handle an opening tag, e.g. '<tag>'
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
:param handle_empty_element: True if this tag is known to be
an empty-element tag (i.e. there is not expected to be any
closing tag).
"""
# XXX namespace
attr_dict = {}
for key, value in attrs:
# Change None attribute values to the empty string
# for consistency with the other tree builders.
if value is None:
value = ''
if key in attr_dict:
# A single attribute shows up multiple times in this
# tag. How to handle it depends on the
# on_duplicate_attribute setting.
on_dupe = self.on_duplicate_attribute
if on_dupe == self.IGNORE:
pass
elif on_dupe in (None, self.REPLACE):
attr_dict[key] = value
else:
on_dupe(attr_dict, key, value)
else:
attr_dict[key] = value
attrvalue = '""'
#print("START", name)
sourceline, sourcepos = self.getpos()
tag = self.soup.handle_starttag(
name, None, None, attr_dict, sourceline=sourceline,
sourcepos=sourcepos
)
if tag and tag.is_empty_element and handle_empty_element:
# Unlike other parsers, html.parser doesn't send separate end tag
# events for empty-element tags. (It's handled in
# handle_startendtag, but only if the original markup looked like
# <tag/>.)
#
# So we need to call handle_endtag() ourselves. Since we
# know the start event is identical to the end event, we
# don't want handle_endtag() to cross off any previous end
# events for tags of this name.
self.handle_endtag(name, check_already_closed=False)
# But we might encounter an explicit closing tag for this tag
# later on. If so, we want to ignore it.
self.already_closed_empty_element.append(name)
if self._root_tag is None:
self._root_tag_encountered(name)
def handle_endtag(self, name, check_already_closed=True):
"""Handle a closing tag, e.g. '</tag>'
:param name: A tag name.
:param check_already_closed: True if this tag is expected to
be the closing portion of an empty-element tag,
e.g. '<tag></tag>'.
"""
#print("END", name)
if check_already_closed and name in self.already_closed_empty_element:
# This is a redundant end tag for an empty-element tag.
# We've already called handle_endtag() for it, so just
# check it off the list.
#print("ALREADY CLOSED", name)
self.already_closed_empty_element.remove(name)
else:
self.soup.handle_endtag(name)
def handle_data(self, data):
"""Handle some textual data that shows up between tags."""
self.soup.handle_data(data)
def handle_charref(self, name):
"""Handle a numeric character reference by converting it to the
corresponding Unicode character and treating it as textual
data.
:param name: Character number, possibly in hexadecimal.
"""
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
if name.startswith('x'):
real_name = int(name.lstrip('x'), 16)
elif name.startswith('X'):
real_name = int(name.lstrip('X'), 16)
else:
real_name = int(name)
data = None
if real_name < 256:
# HTML numeric entities are supposed to reference Unicode
# code points, but sometimes they reference code points in
# some other encoding (ahem, Windows-1252). E.g. &#147;
# instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
# code tries to detect this situation and compensate.
for encoding in (self.soup.original_encoding, 'windows-1252'):
if not encoding:
continue
try:
data = bytearray([real_name]).decode(encoding)
except UnicodeDecodeError as e:
pass
if not data:
try:
data = chr(real_name)
except (ValueError, OverflowError) as e:
pass
data = data or "\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
def handle_entityref(self, name):
"""Handle a named entity reference by converting it to the
corresponding Unicode character(s) and treating it as textual
data.
:param name: Name of the entity reference.
"""
character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
if character is not None:
data = character
else:
# If this were XML, it would be ambiguous whether "&foo"
# was an character entity reference with a missing
# semicolon or the literal string "&foo". Since this is
# HTML, we have a complete list of all character entity references,
# and this one wasn't found, so assume it's the literal string "&foo".
data = "&%s" % name
self.handle_data(data)
def handle_comment(self, data):
"""Handle an HTML comment.
:param data: The text of the comment.
"""
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
"""Handle a DOCTYPE declaration.
:param data: The text of the declaration.
"""
self.soup.endData()
data = data[len("DOCTYPE "):]
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
"""Handle a declaration of unknown type -- probably a CDATA block.
:param data: The text of the declaration.
"""
if data.upper().startswith('CDATA['):
cls = CData
data = data[len('CDATA['):]
else:
cls = Declaration
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(cls)
def handle_pi(self, data):
"""Handle a processing instruction.
:param data: The text of the instruction.
"""
self.soup.endData()
self.soup.handle_data(data)
self._document_might_be_xml(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
"""A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
found in the Python standard library.
"""
is_xml = False
picklable = True
NAME = HTMLPARSER
features = [NAME, HTML, STRICT]
# The html.parser knows which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
"""Constructor.
:param parser_args: Positional arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param parser_kwargs: Keyword arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param kwargs: Keyword arguments for the superclass constructor.
"""
# Some keyword arguments will be pulled out of kwargs and placed
# into parser_kwargs.
extra_parser_kwargs = dict()
for arg in ('on_duplicate_attribute',):
if arg in kwargs:
value = kwargs.pop(arg)
extra_parser_kwargs[arg] = value
super(HTMLParserTreeBuilder, self).__init__(**kwargs)
parser_args = parser_args or []
parser_kwargs = parser_kwargs or {}
parser_kwargs.update(extra_parser_kwargs)
if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
parser_kwargs['strict'] = False
if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
parser_kwargs['convert_charrefs'] = False
self.parser_args = (parser_args, parser_kwargs)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
if isinstance(markup, str):
# Parse Unicode as-is.
yield (markup, None, None, False)
return
# Ask UnicodeDammit to sniff the most likely encoding.
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(
markup,
known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings,
is_html=True,
exclude_encodings=exclude_encodings
)
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
"""
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup
try:
parser.feed(markup)
parser.close()
except HTMLParseError as e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
parser.already_closed_empty_element = []
# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
# string.
#
# XXX This code can be removed once most Python 3 users are on 3.2.3.
if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
import re
attrfind_tolerant = re.compile(
r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
""", re.VERBOSE)
BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
from html.parser import tagfind, attrfind
def parse_starttag(self, i):
self.__starttag_text = None
endpos = self.check_for_whole_start_tag(i)
if endpos < 0:
return endpos
rawdata = self.rawdata
self.__starttag_text = rawdata[i:endpos]
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)
else:
m = attrfind_tolerant.match(rawdata, k)
if not m:
break
attrname, rest, attrvalue = m.group(1, 2, 3)
if not rest:
attrvalue = None
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
if attrvalue:
attrvalue = self.unescape(attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = m.end()
end = rawdata[k:endpos].strip()
if end not in (">", "/>"):
lineno, offset = self.getpos()
if "\n" in self.__starttag_text:
lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
if self.strict:
self.error("junk characters in start tag: %r"
% (rawdata[k:endpos][:20],))
self.handle_data(rawdata[i:endpos])
return endpos
if end.endswith('/>'):
# XHTML-style empty tag: <span attr="value" />
self.handle_startendtag(tag, attrs)
else:
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag)
return endpos
def set_cdata_mode(self, elem):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
BeautifulSoupHTMLParser.parse_starttag = parse_starttag
BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
CONSTRUCTOR_TAKES_STRICT = True

386
env/lib/python3.12/site-packages/bs4/builder/_lxml.py vendored
View File

@@ -1,386 +0,0 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
try:
from collections.abc import Callable # Python 3.6
except ImportError as e:
from collections import Callable
from io import BytesIO
from io import StringIO
from lxml import etree
from bs4.element import (
Comment,
Doctype,
NamespacedAttribute,
ProcessingInstruction,
XMLProcessingInstruction,
)
from bs4.builder import (
DetectsXMLParsedAsHTML,
FAST,
HTML,
HTMLTreeBuilder,
PERMISSIVE,
ParserRejectedMarkup,
TreeBuilder,
XML)
from bs4.dammit import EncodingDetector
LXML = 'lxml'
def _invert(d):
"Invert a dictionary."
return dict((v,k) for k, v in list(d.items()))
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
is_xml = True
processing_instruction_class = XMLProcessingInstruction
NAME = "lxml-xml"
ALTERNATE_NAMES = ["xml"]
# Well, it's permissive by XML parser standards.
features = [NAME, LXML, XML, FAST, PERMISSIVE]
CHUNK_SIZE = 512
# This namespace mapping is specified in the XML Namespace
# standard.
DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
# NOTE: If we parsed Element objects and looked at .sourceline,
# we'd be able to see the line numbers from the original document.
# But instead we build an XMLParser or HTMLParser object to serve
# as the target of parse messages, and those messages don't include
# line numbers.
# See: https://bugs.launchpad.net/lxml/+bug/1846906
def initialize_soup(self, soup):
"""Let the BeautifulSoup object know about the standard namespace
mapping.
:param soup: A `BeautifulSoup`.
"""
super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
self._register_namespaces(self.DEFAULT_NSMAPS)
def _register_namespaces(self, mapping):
"""Let the BeautifulSoup object know about namespaces encountered
while parsing the document.
This might be useful later on when creating CSS selectors.
This will track (almost) all namespaces, even ones that were
only in scope for part of the document. If two namespaces have
the same prefix, only the first one encountered will be
tracked. Un-prefixed namespaces are not tracked.
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
for key, value in list(mapping.items()):
# This is 'if key' and not 'if key is not None' because we
# don't track un-prefixed namespaces. Soupselect will
# treat an un-prefixed namespace as the default, which
# causes confusion in some cases.
if key and key not in self.soup._namespaces:
# Let the BeautifulSoup object know about a new namespace.
# If there are multiple namespaces defined with the same
# prefix, the first one in the document takes precedence.
self.soup._namespaces[key] = value
def default_parser(self, encoding):
"""Find the default parser for the given encoding.
:param encoding: A string.
:return: Either a parser object or a class, which
will be instantiated with default arguments.
"""
if self._default_parser is not None:
return self._default_parser
return etree.XMLParser(
target=self, strip_cdata=False, recover=True, encoding=encoding)
def parser_for(self, encoding):
"""Instantiate an appropriate parser for the given encoding.
:param encoding: A string.
:return: A parser object such as an `etree.XMLParser`.
"""
# Use the default parser.
parser = self.default_parser(encoding)
if isinstance(parser, Callable):
# Instantiate the parser with default arguments
parser = parser(
target=self, strip_cdata=False, recover=True, encoding=encoding
)
return parser
def __init__(self, parser=None, empty_element_tags=None, **kwargs):
# TODO: Issue a warning if parser is present but not a
# callable, since that means there's no way to create new
# parsers for different encodings.
self._default_parser = parser
if empty_element_tags is not None:
self.empty_element_tags = set(empty_element_tags)
self.soup = None
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
def _getNsTag(self, tag):
# Split the namespace URL out of a fully-qualified lxml tag
# name. Copied from lxml's src/lxml/sax.py.
if tag[0] == '{':
return tuple(tag[1:].split('}', 1))
else:
return (None, tag)
def prepare_markup(self, markup, user_specified_encoding=None,
exclude_encodings=None,
document_declared_encoding=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
lxml really wants to get a bytestring and convert it to
Unicode itself. So instead of using UnicodeDammit to convert
the bytestring to Unicode using different encodings, this
implementation uses EncodingDetector to iterate over the
encodings, and tell lxml to try to parse the document as each
one in turn.
:param markup: Some markup -- hopefully a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
# We're in HTML mode, so if we're given XML, that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
# TODO: This is a workaround for
# https://bugs.launchpad.net/lxml/+bug/1948551.
# We can remove it once the upstream issue is fixed.
if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
markup = markup[1:]
yield markup, None, document_declared_encoding, False
if isinstance(markup, str):
# No, apparently not. Convert the Unicode to UTF-8 and
# tell lxml to parse it as UTF-8.
yield (markup.encode("utf8"), "utf8",
document_declared_encoding, False)
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
detector = EncodingDetector(
markup, known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings, is_html=is_html,
exclude_encodings=exclude_encodings
)
for encoding in detector.encodings:
yield (detector.markup, encoding, document_declared_encoding, False)
def feed(self, markup):
if isinstance(markup, bytes):
markup = BytesIO(markup)
elif isinstance(markup, str):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
# or the parser won't be initialized.
data = markup.read(self.CHUNK_SIZE)
try:
self.parser = self.parser_for(self.soup.original_encoding)
self.parser.feed(data)
while len(data) != 0:
# Now call feed() on the rest of the data, chunk by chunk.
data = markup.read(self.CHUNK_SIZE)
if len(data) != 0:
self.parser.feed(data)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def close(self):
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
def start(self, name, attrs, nsmap={}):
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
attrs = dict(attrs)
nsprefix = None
# Invert each namespace map as it comes in.
if len(nsmap) == 0 and len(self.nsmaps) > 1:
# There are no new namespaces for this tag, but
# non-default namespaces are in play, so we need a
# separate tag stack to know when they end.
self.nsmaps.append(None)
elif len(nsmap) > 0:
# A new namespace mapping has come into play.
# First, Let the BeautifulSoup object know about it.
self._register_namespaces(nsmap)
# Then, add it to our running list of inverted namespace
# mappings.
self.nsmaps.append(_invert(nsmap))
# The currently active namespace prefixes have
# changed. Calculate the new mapping so it can be stored
# with all Tag objects created while these prefixes are in
# scope.
current_mapping = dict(self.active_namespace_prefixes[-1])
current_mapping.update(nsmap)
# We should not track un-prefixed namespaces as we can only hold one
# and it will be recognized as the default namespace by soupsieve,
# which may be confusing in some situations.
if '' in current_mapping:
del current_mapping['']
self.active_namespace_prefixes.append(current_mapping)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
for prefix, namespace in list(nsmap.items()):
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
# Namespaces are in play. Find any attributes that came in
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in list(attrs.items()):
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
else:
nsprefix = self._prefix_for_namespace(namespace)
attr = NamespacedAttribute(nsprefix, attr, namespace)
new_attrs[attr] = value
attrs = new_attrs
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_namespace(namespace)
self.soup.handle_starttag(
name, namespace, nsprefix, attrs,
namespaces=self.active_namespace_prefixes[-1]
)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
return None
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
return inverted_nsmap[namespace]
return None
def end(self, name):
self.soup.endData()
completed_tag = self.soup.tagStack[-1]
namespace, name = self._getNsTag(name)
nsprefix = None
if namespace is not None:
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
nsprefix = inverted_nsmap[namespace]
break
self.soup.handle_endtag(name, nsprefix)
if len(self.nsmaps) > 1:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
out_of_scope_nsmap = self.nsmaps.pop()
if out_of_scope_nsmap is not None:
# This tag introduced a namespace mapping which is no
# longer in scope. Recalculate the currently active
# namespace prefixes.
self.active_namespace_prefixes.pop()
def pi(self, target, data):
self.soup.endData()
data = target + ' ' + data
self.soup.handle_data(data)
self.soup.endData(self.processing_instruction_class)
def data(self, content):
self.soup.handle_data(content)
def doctype(self, name, pubid, system):
self.soup.endData()
doctype = Doctype.for_name_and_ids(name, pubid, system)
self.soup.object_was_parsed(doctype)
def comment(self, content):
"Handle comments as Comment objects."
self.soup.endData()
self.soup.handle_data(content)
self.soup.endData(Comment)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
NAME = LXML
ALTERNATE_NAMES = ["lxml-html"]
features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
is_xml = False
processing_instruction_class = ProcessingInstruction
def default_parser(self, encoding):
return etree.HTMLParser
def feed(self, markup):
encoding = self.soup.original_encoding
try:
self.parser = self.parser_for(encoding)
self.parser.feed(markup)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<html><body>%s</body></html>' % fragment

1095
env/lib/python3.12/site-packages/bs4/dammit.py vendored
View File

File diff suppressed because it is too large Load Diff

248
env/lib/python3.12/site-packages/bs4/diagnose.py vendored
View File

@@ -1,248 +0,0 @@
"""Diagnostic functions, mainly for use when doing tech support."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import cProfile
from io import BytesIO
from html.parser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
import os
import pstats
import random
import tempfile
import time
import traceback
import sys
import cProfile
def diagnose(data):
"""Diagnostic suite for isolating common problems.
:param data: A string containing markup that needs to be explained.
:return: None; diagnostics are printed to standard output.
"""
print(("Diagnostic running on Beautiful Soup %s" % __version__))
print(("Python version %s" % sys.version))
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append("lxml-xml")
try:
from lxml import etree
print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
except ImportError as e:
print(
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print(("Found html5lib version %s" % html5lib.__version__))
except ImportError as e:
print(
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif data.startswith("http:") or data.startswith("https:"):
print(('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data))
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
else:
try:
if os.path.exists(data):
print(('"%s" looks like a filename. Reading data from the file.' % data))
with open(data) as fp:
data = fp.read()
except ValueError:
# This can happen on some platforms when the 'filename' is
# too long. Assume it's data and not a filename.
pass
print("")
for parser in basic_parsers:
print(("Trying to parse your markup with %s" % parser))
success = False
try:
soup = BeautifulSoup(data, features=parser)
success = True
except Exception as e:
print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
print(("Here's what %s did with the markup:" % parser))
print((soup.prettify()))
print(("-" * 80))
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
This lets you see how lxml parses a document when no Beautiful
Soup code is running. You can use this to determine whether
an lxml-specific problem is in Beautiful Soup's lxml tree builders
or in lxml itself.
:param data: Some markup.
:param html: If True, markup will be parsed with lxml's HTML parser.
if False, lxml's XML parser will be used.
"""
from lxml import etree
recover = kwargs.pop('recover', True)
if isinstance(data, str):
data = data.encode("utf8")
reader = BytesIO(data)
for event, element in etree.iterparse(
reader, html=html, recover=recover, **kwargs
):
print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Subclass of HTMLParser that announces parse events, without doing
anything else.
You can use this to get a picture of how html.parser sees a given
document. The easiest way to do this is to call `htmlparser_trace`.
"""
def _p(self, s):
print(s)
def handle_starttag(self, name, attrs):
self._p("%s START" % name)
def handle_endtag(self, name):
self._p("%s END" % name)
def handle_data(self, data):
self._p("%s DATA" % data)
def handle_charref(self, name):
self._p("%s CHARREF" % name)
def handle_entityref(self, name):
self._p("%s ENTITYREF" % name)
def handle_comment(self, data):
self._p("%s COMMENT" % data)
def handle_decl(self, data):
self._p("%s DECL" % data)
def unknown_decl(self, data):
self._p("%s UNKNOWN-DECL" % data)
def handle_pi(self, data):
self._p("%s PI" % data)
def htmlparser_trace(data):
"""Print out the HTMLParser events that occur during parsing.
This lets you see how HTMLParser parses a document when no
Beautiful Soup code is running.
:param data: Some markup.
"""
parser = AnnouncingParser()
parser.feed(data)
_vowels = "aeiou"
_consonants = "bcdfghjklmnpqrstvwxyz"
def rword(length=5):
"Generate a random word-like string."
s = ''
for i in range(length):
if i % 2 == 0:
t = _consonants
else:
t = _vowels
s += random.choice(t)
return s
def rsentence(length=4):
"Generate a random sentence-like string."
return " ".join(rword(random.randint(4,9)) for i in range(length))
def rdoc(num_elements=1000):
"""Randomly generate an invalid HTML document."""
tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
elements = []
for i in range(num_elements):
choice = random.randint(0,3)
if choice == 0:
# New tag.
tag_name = random.choice(tag_names)
elements.append("<%s>" % tag_name)
elif choice == 1:
elements.append(rsentence(random.randint(1,4)))
elif choice == 2:
# Close a tag.
tag_name = random.choice(tag_names)
elements.append("</%s>" % tag_name)
return "<html>" + "\n".join(elements) + "</html>"
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print(("Comparative parser benchmark on Beautiful Soup %s" % __version__))
data = rdoc(num_elements)
print(("Generated a large invalid HTML document (%d bytes)." % len(data)))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
print(("BS4+%s parsed the markup in %.2fs." % (parser, b-a)))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print(("Raw lxml parsed the markup in %.2fs." % (b-a)))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print(("Raw html5lib parsed the markup in %.2fs." % (b-a)))
def profile(num_elements=100000, parser="lxml"):
"""Use Python's profiler on a randomly generated document."""
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
data = rdoc(num_elements)
vars = dict(bs4=bs4, data=data, parser=parser)
cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
stats = pstats.Stats(filename)
# stats.strip_dirs()
stats.sort_stats("cumulative")
stats.print_stats('_html5lib|bs4', 50)
# If this file is run as a script, standard input is diagnosed.
if __name__ == '__main__':
diagnose(sys.stdin.read())

2291
env/lib/python3.12/site-packages/bs4/element.py vendored
View File

File diff suppressed because it is too large Load Diff

185
env/lib/python3.12/site-packages/bs4/formatter.py vendored
View File

@@ -1,185 +0,0 @@
from bs4.dammit import EntitySubstitution
class Formatter(EntitySubstitution):
"""Describes a strategy to use when outputting a parse tree to a string.
Some parts of this strategy come from the distinction between
HTML4, HTML5, and XML. Others are configurable by the user.
Formatters are passed in as the `formatter` argument to methods
like `PageElement.encode`. Most people won't need to think about
formatters, and most people who need to think about them can pass
in one of these predefined strings as `formatter` rather than
making a new Formatter object:
For HTML documents:
* 'html' - HTML entity substitution for generic HTML documents. (default)
* 'html5' - HTML entity substitution for HTML5 documents, as
well as some optimizations in the way tags are rendered.
* 'minimal' - Only make the substitutions necessary to guarantee
valid HTML.
* None - Do not perform any substitution. This will be faster
but may result in invalid markup.
For XML documents:
* 'html' - Entity substitution for XHTML documents.
* 'minimal' - Only make the substitutions necessary to guarantee
valid XML. (default)
* None - Do not perform any substitution. This will be faster
but may result in invalid markup.
"""
# Registries of XML and HTML formatters.
XML_FORMATTERS = {}
HTML_FORMATTERS = {}
HTML = 'html'
XML = 'xml'
HTML_DEFAULTS = dict(
cdata_containing_tags=set(["script", "style"]),
)
def _default(self, language, value, kwarg):
if value is not None:
return value
if language == self.XML:
return set()
return self.HTML_DEFAULTS[kwarg]
def __init__(
self, language=None, entity_substitution=None,
void_element_close_prefix='/', cdata_containing_tags=None,
empty_attributes_are_booleans=False, indent=1,
):
"""Constructor.
:param language: This should be Formatter.XML if you are formatting
XML markup and Formatter.HTML if you are formatting HTML markup.
:param entity_substitution: A function to call to replace special
characters with XML/HTML entities. For examples, see
bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
:param void_element_close_prefix: By default, void elements
are represented as <tag/> (XML rules) rather than <tag>
(HTML rules). To get <tag>, pass in the empty string.
:param cdata_containing_tags: The list of tags that are defined
as containing CDATA in this dialect. For example, in HTML,
<script> and <style> tags are defined as containing CDATA,
and their contents should not be formatted.
:param blank_attributes_are_booleans: Render attributes whose value
is the empty string as HTML-style boolean attributes.
(Attributes whose value is None are always rendered this way.)
:param indent: If indent is a non-negative integer or string,
then the contents of elements will be indented
appropriately when pretty-printing. An indent level of 0,
negative, or "" will only insert newlines. Using a
positive integer indent indents that many spaces per
level. If indent is a string (such as "\t"), that string
is used to indent each level. The default behavior to
indent one space per level.
"""
self.language = language
self.entity_substitution = entity_substitution
self.void_element_close_prefix = void_element_close_prefix
self.cdata_containing_tags = self._default(
language, cdata_containing_tags, 'cdata_containing_tags'
)
self.empty_attributes_are_booleans=empty_attributes_are_booleans
if indent is None:
indent = 0
if isinstance(indent, int):
if indent < 0:
indent = 0
indent = ' ' * indent
elif isinstance(indent, str):
indent = indent
else:
indent = ' '
self.indent = indent
def substitute(self, ns):
"""Process a string that needs to undergo entity substitution.
This may be a string encountered in an attribute value or as
text.
:param ns: A string.
:return: A string with certain characters replaced by named
or numeric entities.
"""
if not self.entity_substitution:
return ns
from .element import NavigableString
if (isinstance(ns, NavigableString)
and ns.parent is not None
and ns.parent.name in self.cdata_containing_tags):
# Do nothing.
return ns
# Substitute.
return self.entity_substitution(ns)
def attribute_value(self, value):
"""Process the value of an attribute.
:param ns: A string.
:return: A string with certain characters replaced by named
or numeric entities.
"""
return self.substitute(value)
def attributes(self, tag):
"""Reorder a tag's attributes however you want.
By default, attributes are sorted alphabetically. This makes
behavior consistent between Python 2 and Python 3, and preserves
backwards compatibility with older versions of Beautiful Soup.
If `empty_boolean_attributes` is True, then attributes whose
values are set to the empty string will be treated as boolean
attributes.
"""
if tag.attrs is None:
return []
return sorted(
(k, (None if self.empty_attributes_are_booleans and v == '' else v))
for k, v in list(tag.attrs.items())
)
class HTMLFormatter(Formatter):
"""A generic Formatter for HTML."""
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(HTMLFormatter, self).__init__(self.HTML, *args, **kwargs)
class XMLFormatter(Formatter):
"""A generic Formatter for XML."""
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(XMLFormatter, self).__init__(self.XML, *args, **kwargs)
# Set up aliases for the default formatters.
HTMLFormatter.REGISTRY['html'] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_html
)
HTMLFormatter.REGISTRY["html5"] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_html,
void_element_close_prefix=None,
empty_attributes_are_booleans=True,
)
HTMLFormatter.REGISTRY["minimal"] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_xml
)
HTMLFormatter.REGISTRY[None] = HTMLFormatter(
entity_substitution=None
)
XMLFormatter.REGISTRY["html"] = XMLFormatter(
entity_substitution=EntitySubstitution.substitute_html
)
XMLFormatter.REGISTRY["minimal"] = XMLFormatter(
entity_substitution=EntitySubstitution.substitute_xml
)
XMLFormatter.REGISTRY[None] = Formatter(
Formatter(Formatter.XML, entity_substitution=None)
)

1191
env/lib/python3.12/site-packages/bs4/tests/__init__.py vendored
View File

File diff suppressed because it is too large Load Diff

29
env/lib/python3.12/site-packages/bs4/tests/test_builder.py vendored
View File

@@ -1,29 +0,0 @@
import pytest
from unittest.mock import patch
from bs4.builder import DetectsXMLParsedAsHTML
class TestDetectsXMLParsedAsHTML(object):
@pytest.mark.parametrize(
"markup,looks_like_xml",
[("No xml declaration", False),
("<html>obviously HTML</html", False),
("<?xml ><html>Actually XHTML</html>", False),
("<?xml> < html>Tricky XHTML</html>", False),
("<?xml ><no-html-tag>", True),
]
)
def test_warn_if_markup_looks_like_xml(self, markup, looks_like_xml):
# Test of our ability to guess at whether markup looks XML-ish
# _and_ not HTML-ish.
with patch('bs4.builder.DetectsXMLParsedAsHTML._warn') as mock:
for data in markup, markup.encode('utf8'):
result = DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
data
)
assert result == looks_like_xml
if looks_like_xml:
assert mock.called
else:
assert not mock.called
mock.reset_mock()

136
env/lib/python3.12/site-packages/bs4/tests/test_builder_registry.py vendored
View File

@@ -1,136 +0,0 @@
"""Tests of the builder registry."""
import pytest
import warnings
from bs4 import BeautifulSoup
from bs4.builder import (
builder_registry as registry,
HTMLParserTreeBuilder,
TreeBuilderRegistry,
)
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError:
HTML5LIB_PRESENT = False
try:
from bs4.builder import (
LXMLTreeBuilderForXML,
LXMLTreeBuilder,
)
LXML_PRESENT = True
except ImportError:
LXML_PRESENT = False
class TestBuiltInRegistry(object):
"""Test the built-in registry with the default builders registered."""
def test_combination(self):
assert registry.lookup('strict', 'html') == HTMLParserTreeBuilder
if LXML_PRESENT:
assert registry.lookup('fast', 'html') == LXMLTreeBuilder
assert registry.lookup('permissive', 'xml') == LXMLTreeBuilderForXML
if HTML5LIB_PRESENT:
assert registry.lookup('html5lib', 'html') == HTML5TreeBuilder
def test_lookup_by_markup_type(self):
if LXML_PRESENT:
assert registry.lookup('html') == LXMLTreeBuilder
assert registry.lookup('xml') == LXMLTreeBuilderForXML
else:
assert registry.lookup('xml') == None
if HTML5LIB_PRESENT:
assert registry.lookup('html') == HTML5TreeBuilder
else:
assert registry.lookup('html') == HTMLParserTreeBuilder
def test_named_library(self):
if LXML_PRESENT:
assert registry.lookup('lxml', 'xml') == LXMLTreeBuilderForXML
assert registry.lookup('lxml', 'html') == LXMLTreeBuilder
if HTML5LIB_PRESENT:
assert registry.lookup('html5lib') == HTML5TreeBuilder
assert registry.lookup('html.parser') == HTMLParserTreeBuilder
def test_beautifulsoup_constructor_does_lookup(self):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
# You can pass in a string.
BeautifulSoup("", features="html")
# Or a list of strings.
BeautifulSoup("", features=["html", "fast"])
pass
# You'll get an exception if BS can't find an appropriate
# builder.
with pytest.raises(ValueError):
BeautifulSoup("", features="no-such-feature")
class TestRegistry(object):
"""Test the TreeBuilderRegistry class in general."""
def setup_method(self):
self.registry = TreeBuilderRegistry()
def builder_for_features(self, *feature_list):
cls = type('Builder_' + '_'.join(feature_list),
(object,), {'features' : feature_list})
self.registry.register(cls)
return cls
def test_register_with_no_features(self):
builder = self.builder_for_features()
# Since the builder advertises no features, you can't find it
# by looking up features.
assert self.registry.lookup('foo') is None
# But you can find it by doing a lookup with no features, if
# this happens to be the only registered builder.
assert self.registry.lookup() == builder
def test_register_with_features_makes_lookup_succeed(self):
builder = self.builder_for_features('foo', 'bar')
assert self.registry.lookup('foo') is builder
assert self.registry.lookup('bar') is builder
def test_lookup_fails_when_no_builder_implements_feature(self):
builder = self.builder_for_features('foo', 'bar')
assert self.registry.lookup('baz') is None
def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
builder1 = self.builder_for_features('foo')
builder2 = self.builder_for_features('bar')
assert self.registry.lookup() == builder2
def test_lookup_fails_when_no_tree_builders_registered(self):
assert self.registry.lookup() is None
def test_lookup_gets_most_recent_builder_supporting_all_features(self):
has_one = self.builder_for_features('foo')
has_the_other = self.builder_for_features('bar')
has_both_early = self.builder_for_features('foo', 'bar', 'baz')
has_both_late = self.builder_for_features('foo', 'bar', 'quux')
lacks_one = self.builder_for_features('bar')
has_the_other = self.builder_for_features('foo')
# There are two builders featuring 'foo' and 'bar', but
# the one that also features 'quux' was registered later.
assert self.registry.lookup('foo', 'bar') == has_both_late
# There is only one builder featuring 'foo', 'bar', and 'baz'.
assert self.registry.lookup('foo', 'bar', 'baz') == has_both_early
def test_lookup_fails_when_cannot_reconcile_requested_features(self):
builder1 = self.builder_for_features('foo', 'bar')
builder2 = self.builder_for_features('foo', 'baz')
assert self.registry.lookup('bar', 'baz') is None

371
env/lib/python3.12/site-packages/bs4/tests/test_dammit.py vendored
View File

@@ -1,371 +0,0 @@
# encoding: utf-8
import pytest
import logging
import bs4
from bs4 import BeautifulSoup
from bs4.dammit import (
EntitySubstitution,
EncodingDetector,
UnicodeDammit,
)
class TestUnicodeDammit(object):
"""Standalone tests of UnicodeDammit."""
def test_unicode_input(self):
markup = "I'm already Unicode! \N{SNOWMAN}"
dammit = UnicodeDammit(markup)
assert dammit.unicode_markup == markup
def test_smart_quotes_to_unicode(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
assert dammit.unicode_markup == "<foo>\u2018\u2019\u201c\u201d</foo>"
def test_smart_quotes_to_xml_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="xml")
assert dammit.unicode_markup == "<foo>&#x2018;&#x2019;&#x201C;&#x201D;</foo>"
def test_smart_quotes_to_html_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="html")
assert dammit.unicode_markup == "<foo>&lsquo;&rsquo;&ldquo;&rdquo;</foo>"
def test_smart_quotes_to_ascii(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
assert dammit.unicode_markup == """<foo>''""</foo>"""
def test_detect_utf8(self):
utf8 = b"Sacr\xc3\xa9 bleu! \xe2\x98\x83"
dammit = UnicodeDammit(utf8)
assert dammit.original_encoding.lower() == 'utf-8'
assert dammit.unicode_markup == 'Sacr\xe9 bleu! \N{SNOWMAN}'
def test_convert_hebrew(self):
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
assert dammit.original_encoding.lower() == 'iso-8859-8'
assert dammit.unicode_markup == '\u05dd\u05d5\u05dc\u05e9'
def test_dont_see_smart_quotes_where_there_are_none(self):
utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
dammit = UnicodeDammit(utf_8)
assert dammit.original_encoding.lower() == 'utf-8'
assert dammit.unicode_markup.encode("utf-8") == utf_8
def test_ignore_inappropriate_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
assert dammit.original_encoding.lower() == 'utf-8'
def test_ignore_invalid_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
dammit = UnicodeDammit(utf8_data, [bad_encoding])
assert dammit.original_encoding.lower() == 'utf-8'
def test_exclude_encodings(self):
# This is UTF-8.
utf8_data = "Räksmörgås".encode("utf-8")
# But if we exclude UTF-8 from consideration, the guess is
# Windows-1252.
dammit = UnicodeDammit(utf8_data, exclude_encodings=["utf-8"])
assert dammit.original_encoding.lower() == 'windows-1252'
# And if we exclude that, there is no valid guess at all.
dammit = UnicodeDammit(
utf8_data, exclude_encodings=["utf-8", "windows-1252"])
assert dammit.original_encoding == None
class TestEncodingDetector(object):
def test_encoding_detector_replaces_junk_in_encoding_name_with_replacement_character(self):
detected = EncodingDetector(
b'<?xml version="1.0" encoding="UTF-\xdb" ?>')
encodings = list(detected.encodings)
assert 'utf-\N{REPLACEMENT CHARACTER}' in encodings
def test_detect_html5_style_meta_tag(self):
for data in (
b'<html><meta charset="euc-jp" /></html>',
b"<html><meta charset='euc-jp' /></html>",
b"<html><meta charset=euc-jp /></html>",
b"<html><meta charset=euc-jp/></html>"):
dammit = UnicodeDammit(data, is_html=True)
assert "euc-jp" == dammit.original_encoding
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
bs4.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
assert True == dammit.contains_replacement_characters
assert "\ufffd" in dammit.unicode_markup
soup = BeautifulSoup(doc, "html.parser")
assert soup.contains_replacement_characters
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet
def test_byte_order_mark_removed(self):
# A document written in UTF-16LE will have its byte order marker stripped.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
assert "<a>áé</a>" == dammit.unicode_markup
assert "utf-16le" == dammit.original_encoding
def test_known_definite_versus_user_encodings(self):
# The known_definite_encodings are used before sniffing the
# byte-order mark; the user_encodings are used afterwards.
# Here's a document in UTF-16LE.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
# We can process it as UTF-16 by passing it in as a known
# definite encoding.
before = UnicodeDammit(data, known_definite_encodings=["utf-16"])
assert "utf-16" == before.original_encoding
# If we pass UTF-18 as a user encoding, it's not even
# tried--the encoding sniffed from the byte-order mark takes
# precedence.
after = UnicodeDammit(data, user_encodings=["utf-8"])
assert "utf-16le" == after.original_encoding
assert ["utf-16le"] == [x[0] for x in dammit.tried_encodings]
# Here's a document in ISO-8859-8.
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, known_definite_encodings=["utf-8"],
user_encodings=["iso-8859-8"])
# The known_definite_encodings don't work, BOM sniffing does
# nothing (it only works for a few UTF encodings), but one of
# the user_encodings does work.
assert "iso-8859-8" == dammit.original_encoding
assert ["utf-8", "iso-8859-8"] == [x[0] for x in dammit.tried_encodings]
def test_deprecated_override_encodings(self):
# override_encodings is a deprecated alias for
# known_definite_encodings.
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(
hebrew,
known_definite_encodings=["shift-jis"],
override_encodings=["utf-8"],
user_encodings=["iso-8859-8"],
)
assert "iso-8859-8" == dammit.original_encoding
# known_definite_encodings and override_encodings were tried
# before user_encodings.
assert ["shift-jis", "utf-8", "iso-8859-8"] == (
[x[0] for x in dammit.tried_encodings]
)
def test_detwingle(self):
# Here's a UTF8 document.
utf8 = ("\N{SNOWMAN}" * 3).encode("utf8")
# Here's a Windows-1252 document.
windows_1252 = (
"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
"\N{RIGHT DOUBLE QUOTATION MARK}").encode("windows_1252")
# Through some unholy alchemy, they've been stuck together.
doc = utf8 + windows_1252 + utf8
# The document can't be turned into UTF-8:
with pytest.raises(UnicodeDecodeError):
doc.decode("utf8")
# Unicode, Dammit thinks the whole document is Windows-1252,
# and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
# But if we run it through fix_embedded_windows_1252, it's fixed:
fixed = UnicodeDammit.detwingle(doc)
assert "☃☃☃“Hi, I like Windows!”☃☃☃" == fixed.decode("utf8")
def test_detwingle_ignores_multibyte_characters(self):
# Each of these characters has a UTF-8 representation ending
# in \x93. \x93 is a smart quote if interpreted as
# Windows-1252. But our code knows to skip over multibyte
# UTF-8 characters, so they'll survive the process unscathed.
for tricky_unicode_char in (
"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
):
input = tricky_unicode_char.encode("utf8")
assert input.endswith(b'\x93')
output = UnicodeDammit.detwingle(input)
assert output == input
def test_find_declared_encoding(self):
# Test our ability to find a declared encoding inside an
# XML or HTML document.
#
# Even if the document comes in as Unicode, it may be
# interesting to know what encoding was claimed
# originally.
html_unicode = '<html><head><meta charset="utf-8"></head></html>'
html_bytes = html_unicode.encode("ascii")
xml_unicode= '<?xml version="1.0" encoding="ISO-8859-1" ?>'
xml_bytes = xml_unicode.encode("ascii")
m = EncodingDetector.find_declared_encoding
assert m(html_unicode, is_html=False) is None
assert "utf-8" == m(html_unicode, is_html=True)
assert "utf-8" == m(html_bytes, is_html=True)
assert "iso-8859-1" == m(xml_unicode)
assert "iso-8859-1" == m(xml_bytes)
# Normally, only the first few kilobytes of a document are checked for
# an encoding.
spacer = b' ' * 5000
assert m(spacer + html_bytes) is None
assert m(spacer + xml_bytes) is None
# But you can tell find_declared_encoding to search an entire
# HTML document.
assert (
m(spacer + html_bytes, is_html=True, search_entire_document=True)
== "utf-8"
)
# The XML encoding declaration has to be the very first thing
# in the document. We'll allow whitespace before the document
# starts, but nothing else.
assert m(xml_bytes, search_entire_document=True) == "iso-8859-1"
assert m(b' ' + xml_bytes, search_entire_document=True) == "iso-8859-1"
assert m(b'a' + xml_bytes, search_entire_document=True) is None
class TestEntitySubstitution(object):
"""Standalone tests of the EntitySubstitution class."""
def setup_method(self):
self.sub = EntitySubstitution
def test_simple_html_substitution(self):
# Unicode characters corresponding to named HTML entites
# are substituted, and no others.
s = "foo\u2200\N{SNOWMAN}\u00f5bar"
assert self.sub.substitute_html(s) == "foo&forall;\N{SNOWMAN}&otilde;bar"
def test_smart_quote_substitution(self):
# MS smart quotes are a common source of frustration, so we
# give them a special test.
quotes = b"\x91\x92foo\x93\x94"
dammit = UnicodeDammit(quotes)
assert self.sub.substitute_html(dammit.markup) == "&lsquo;&rsquo;foo&ldquo;&rdquo;"
def test_html5_entity(self):
# Some HTML5 entities correspond to single- or multi-character
# Unicode sequences.
for entity, u in (
# A few spot checks of our ability to recognize
# special character sequences and convert them
# to named entities.
('&models;', '\u22a7'),
('&Nfr;', '\U0001d511'),
('&ngeqq;', '\u2267\u0338'),
('&not;', '\xac'),
('&Not;', '\u2aec'),
# We _could_ convert | to &verbarr;, but we don't, because
# | is an ASCII character.
('|' '|'),
# Similarly for the fj ligature, which we could convert to
# &fjlig;, but we don't.
("fj", "fj"),
# We do convert _these_ ASCII characters to HTML entities,
# because that's required to generate valid HTML.
('&gt;', '>'),
('&lt;', '<'),
('&amp;', '&'),
):
template = '3 %s 4'
raw = template % u
with_entities = template % entity
assert self.sub.substitute_html(raw) == with_entities
def test_html5_entity_with_variation_selector(self):
# Some HTML5 entities correspond either to a single-character
# Unicode sequence _or_ to the same character plus U+FE00,
# VARIATION SELECTOR 1. We can handle this.
data = "fjords \u2294 penguins"
markup = "fjords &sqcup; penguins"
assert self.sub.substitute_html(data) == markup
data = "fjords \u2294\ufe00 penguins"
markup = "fjords &sqcups; penguins"
assert self.sub.substitute_html(data) == markup
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
s = 'Welcome to "my bar"'
assert self.sub.substitute_xml(s, False) == s
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
assert self.sub.substitute_xml("Welcome", True) == '"Welcome"'
assert self.sub.substitute_xml("Bob's Bar", True) == '"Bob\'s Bar"'
def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
s = 'Welcome to "my bar"'
assert self.sub.substitute_xml(s, True) == "'Welcome to \"my bar\"'"
def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
s = 'Welcome to "Bob\'s Bar"'
assert self.sub.substitute_xml(s, True) == '"Welcome to &quot;Bob\'s Bar&quot;"'
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
quoted = 'Welcome to "Bob\'s Bar"'
assert self.sub.substitute_xml(quoted) == quoted
def test_xml_quoting_handles_angle_brackets(self):
assert self.sub.substitute_xml("foo<bar>") == "foo&lt;bar&gt;"
def test_xml_quoting_handles_ampersands(self):
assert self.sub.substitute_xml("AT&T") == "AT&amp;T"
def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
assert self.sub.substitute_xml("&Aacute;T&T") == "&amp;Aacute;T&amp;T"
def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
assert self.sub.substitute_xml_containing_entities("&Aacute;T&T") == "&Aacute;T&amp;T"
def test_quotes_not_html_substituted(self):
"""There's no need to do this except inside attribute values."""
text = 'Bob\'s "bar"'
assert self.sub.substitute_html(text) == text

38
env/lib/python3.12/site-packages/bs4/tests/test_docs.py vendored
View File

@@ -1,38 +0,0 @@
"Test harness for doctests."
# TODO: Pretty sure this isn't used and should be deleted.
# pylint: disable-msg=E0611,W0142
__metaclass__ = type
__all__ = [
'additional_tests',
]
import atexit
import doctest
import os
#from pkg_resources import (
# resource_filename, resource_exists, resource_listdir, cleanup_resources)
import unittest
DOCTEST_FLAGS = (
doctest.ELLIPSIS |
doctest.NORMALIZE_WHITESPACE |
doctest.REPORT_NDIFF)
# def additional_tests():
# "Run the doc tests (README.txt and docs/*, if any exist)"
# doctest_files = [
# os.path.abspath(resource_filename('bs4', 'README.txt'))]
# if resource_exists('bs4', 'docs'):
# for name in resource_listdir('bs4', 'docs'):
# if name.endswith('.txt'):
# doctest_files.append(
# os.path.abspath(
# resource_filename('bs4', 'docs/%s' % name)))
# kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
# atexit.register(cleanup_resources)
# return unittest.TestSuite((
# doctest.DocFileSuite(*doctest_files, **kwargs)))

74
env/lib/python3.12/site-packages/bs4/tests/test_element.py vendored
View File

@@ -1,74 +0,0 @@
"""Tests of classes in element.py.
The really big classes -- Tag, PageElement, and NavigableString --
are tested in separate files.
"""
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
NamespacedAttribute,
)
from . import SoupTest
class TestNamedspacedAttribute(object):
def test_name_may_be_none_or_missing(self):
a = NamespacedAttribute("xmlns", None)
assert a == "xmlns"
a = NamespacedAttribute("xmlns", "")
assert a == "xmlns"
a = NamespacedAttribute("xmlns")
assert a == "xmlns"
def test_namespace_may_be_none_or_missing(self):
a = NamespacedAttribute(None, "tag")
assert a == "tag"
a = NamespacedAttribute("", "tag")
assert a == "tag"
def test_attribute_is_equivalent_to_colon_separated_string(self):
a = NamespacedAttribute("a", "b")
assert "a:b" == a
def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
a = NamespacedAttribute("a", "b", "c")
b = NamespacedAttribute("a", "b", "c")
assert a == b
# The actual namespace is not considered.
c = NamespacedAttribute("a", "b", None)
assert a == c
# But name and prefix are important.
d = NamespacedAttribute("a", "z", "c")
assert a != d
e = NamespacedAttribute("z", "b", "c")
assert a != e
class TestAttributeValueWithCharsetSubstitution(object):
"""Certain attributes are designed to have the charset of the
final document substituted into their value.
"""
def test_content_meta_attribute_value(self):
# The value of a CharsetMetaAttributeValue is whatever
# encoding the string is in.
value = CharsetMetaAttributeValue("euc-jp")
assert "euc-jp" == value
assert "euc-jp" == value.original_value
assert "utf8" == value.encode("utf8")
assert "ascii" == value.encode("ascii")
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
assert "text/html; charset=euc-jp" == value
assert "text/html; charset=euc-jp" == value.original_value
assert "text/html; charset=utf8" == value.encode("utf8")
assert "text/html; charset=ascii" == value.encode("ascii")

113
env/lib/python3.12/site-packages/bs4/tests/test_formatter.py vendored
View File

@@ -1,113 +0,0 @@
import pytest
from bs4.element import Tag
from bs4.formatter import (
Formatter,
HTMLFormatter,
XMLFormatter,
)
from . import SoupTest
class TestFormatter(SoupTest):
def test_default_attributes(self):
# Test the default behavior of Formatter.attributes().
formatter = Formatter()
tag = Tag(name="tag")
tag['b'] = 1
tag['a'] = 2
# Attributes come out sorted by name. In Python 3, attributes
# normally come out of a dictionary in the order they were
# added.
assert [('a', 2), ('b', 1)] == formatter.attributes(tag)
# This works even if Tag.attrs is None, though this shouldn't
# normally happen.
tag.attrs = None
assert [] == formatter.attributes(tag)
assert ' ' == formatter.indent
def test_sort_attributes(self):
# Test the ability to override Formatter.attributes() to,
# e.g., disable the normal sorting of attributes.
class UnsortedFormatter(Formatter):
def attributes(self, tag):
self.called_with = tag
for k, v in sorted(tag.attrs.items()):
if k == 'ignore':
continue
yield k,v
soup = self.soup('<p cval="1" aval="2" ignore="ignored"></p>')
formatter = UnsortedFormatter()
decoded = soup.decode(formatter=formatter)
# attributes() was called on the <p> tag. It filtered out one
# attribute and sorted the other two.
assert formatter.called_with == soup.p
assert '<p aval="2" cval="1"></p>' == decoded
def test_empty_attributes_are_booleans(self):
# Test the behavior of empty_attributes_are_booleans as well
# as which Formatters have it enabled.
for name in ('html', 'minimal', None):
formatter = HTMLFormatter.REGISTRY[name]
assert False == formatter.empty_attributes_are_booleans
formatter = XMLFormatter.REGISTRY[None]
assert False == formatter.empty_attributes_are_booleans
formatter = HTMLFormatter.REGISTRY['html5']
assert True == formatter.empty_attributes_are_booleans
# Verify that the constructor sets the value.
formatter = Formatter(empty_attributes_are_booleans=True)
assert True == formatter.empty_attributes_are_booleans
# Now demonstrate what it does to markup.
for markup in (
"<option selected></option>",
'<option selected=""></option>'
):
soup = self.soup(markup)
for formatter in ('html', 'minimal', 'xml', None):
assert b'<option selected=""></option>' == soup.option.encode(formatter='html')
assert b'<option selected></option>' == soup.option.encode(formatter='html5')
@pytest.mark.parametrize(
"indent,expect",
[
(None, '<a>\n<b>\ntext\n</b>\n</a>'),
(-1, '<a>\n<b>\ntext\n</b>\n</a>'),
(0, '<a>\n<b>\ntext\n</b>\n</a>'),
("", '<a>\n<b>\ntext\n</b>\n</a>'),
(1, '<a>\n <b>\n text\n </b>\n</a>'),
(2, '<a>\n <b>\n text\n </b>\n</a>'),
("\t", '<a>\n\t<b>\n\t\ttext\n\t</b>\n</a>'),
('abc', '<a>\nabc<b>\nabcabctext\nabc</b>\n</a>'),
# Some invalid inputs -- the default behavior is used.
(object(), '<a>\n <b>\n text\n </b>\n</a>'),
(b'bytes', '<a>\n <b>\n text\n </b>\n</a>'),
]
)
def test_indent(self, indent, expect):
# Pretty-print a tree with a Formatter set to
# indent in a certain way and verify the results.
soup = self.soup("<a><b>text</b></a>")
formatter = Formatter(indent=indent)
assert soup.prettify(formatter=formatter) == expect
# Pretty-printing only happens with prettify(), not
# encode().
assert soup.encode(formatter=formatter) != expect
def test_default_indent_value(self):
formatter = Formatter()
assert formatter.indent == ' '

223
env/lib/python3.12/site-packages/bs4/tests/test_html5lib.py vendored
View File

@@ -1,223 +0,0 @@
"""Tests to ensure that the html5lib tree builder generates good trees."""
import warnings
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError as e:
HTML5LIB_PRESENT = False
from bs4.element import SoupStrainer
from . import (
HTML5TreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not HTML5LIB_PRESENT,
"html5lib seems not to be present, not testing its tree builder.")
class TestHTML5LibBuilder(SoupTest, HTML5TreeBuilderSmokeTest):
"""See ``HTML5TreeBuilderSmokeTest``."""
@property
def default_builder(self):
return HTML5TreeBuilder
def test_soupstrainer(self):
# The html5lib tree builder does not support SoupStrainers.
strainer = SoupStrainer("b")
markup = "<p>A <b>bold</b> statement.</p>"
with warnings.catch_warnings(record=True) as w:
soup = self.soup(markup, parse_only=strainer)
assert soup.decode() == self.document_for(markup)
assert "the html5lib tree builder doesn't support parse_only" in str(w[0].message)
def test_correctly_nested_tables(self):
"""html5lib inserts <tbody> tags where other parsers don't."""
markup = ('<table id="1">'
'<tr>'
"<td>Here's another table:"
'<table id="2">'
'<tr><td>foo</td></tr>'
'</table></td>')
self.assert_soup(
markup,
'<table id="1"><tbody><tr><td>Here\'s another table:'
'<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
'</td></tr></tbody></table>')
self.assert_soup(
"<table><thead><tr><td>Foo</td></tr></thead>"
"<tbody><tr><td>Bar</td></tr></tbody>"
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
def test_xml_declaration_followed_by_doctype(self):
markup = '''<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html>
<html>
<head>
</head>
<body>
<p>foo</p>
</body>
</html>'''
soup = self.soup(markup)
# Verify that we can reach the <p> tag; this means the tree is connected.
assert b"<p>foo</p>" == soup.p.encode()
def test_reparented_markup(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
soup = self.soup(markup)
assert "<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>" == soup.body.decode()
assert 2 == len(soup.find_all('p'))
def test_reparented_markup_ends_with_whitespace(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
soup = self.soup(markup)
assert "<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>" == soup.body.decode()
assert 2 == len(soup.find_all('p'))
def test_reparented_markup_containing_identical_whitespace_nodes(self):
"""Verify that we keep the two whitespace nodes in this
document distinct when reparenting the adjacent <tbody> tags.
"""
markup = '<table> <tbody><tbody><ims></tbody> </table>'
soup = self.soup(markup)
space1, space2 = soup.find_all(string=' ')
tbody1, tbody2 = soup.find_all('tbody')
assert space1.next_element is tbody1
assert tbody2.next_element is space2
def test_reparented_markup_containing_children(self):
markup = '<div><a>aftermath<p><noscript>target</noscript>aftermath</a></p></div>'
soup = self.soup(markup)
noscript = soup.noscript
assert "target" == noscript.next_element
target = soup.find(string='target')
# The 'aftermath' string was duplicated; we want the second one.
final_aftermath = soup.find_all(string='aftermath')[-1]
# The <noscript> tag was moved beneath a copy of the <a> tag,
# but the 'target' string within is still connected to the
# (second) 'aftermath' string.
assert final_aftermath == target.next_element
assert target == final_aftermath.previous_element
def test_processing_instruction(self):
"""Processing instructions become comments."""
markup = b"""<?PITarget PIContent?>"""
soup = self.soup(markup)
assert str(soup).startswith("<!--?PITarget PIContent?-->")
def test_cloned_multivalue_node(self):
markup = b"""<a class="my_class"><p></a>"""
soup = self.soup(markup)
a1, a2 = soup.find_all('a')
assert a1 == a2
assert a1 is not a2
def test_foster_parenting(self):
markup = b"""<table><td></tbody>A"""
soup = self.soup(markup)
assert "<body>A<table><tbody><tr><td></td></tr></tbody></table></body>" == soup.body.decode()
def test_extraction(self):
"""
Test that extraction does not destroy the tree.
https://bugs.launchpad.net/beautifulsoup/+bug/1782928
"""
markup = """
<html><head></head>
<style>
</style><script></script><body><p>hello</p></body></html>
"""
soup = self.soup(markup)
[s.extract() for s in soup('script')]
[s.extract() for s in soup('style')]
assert len(soup.find_all("p")) == 1
def test_empty_comment(self):
"""
Test that empty comment does not break structure.
https://bugs.launchpad.net/beautifulsoup/+bug/1806598
"""
markup = """
<html>
<body>
<form>
<!----><input type="text">
</form>
</body>
</html>
"""
soup = self.soup(markup)
inputs = []
for form in soup.find_all('form'):
inputs.extend(form.find_all('input'))
assert len(inputs) == 1
def test_tracking_line_numbers(self):
# The html.parser TreeBuilder keeps track of line number and
# position of each element.
markup = "\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>"
soup = self.soup(markup)
assert 2 == soup.p.sourceline
assert 5 == soup.p.sourcepos
assert "sourceline" == soup.p.find('sourceline').name
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
assert "sourceline" == soup.p.sourceline.name
assert "sourcepos" == soup.p.sourcepos.name
def test_special_string_containers(self):
# The html5lib tree builder doesn't support this standard feature,
# because there's no way of knowing, when a string is created,
# where in the tree it will eventually end up.
pass
def test_html5_attributes(self):
# The html5lib TreeBuilder can convert any entity named in
# the HTML5 spec to a sequence of Unicode characters, and
# convert those Unicode characters to a (potentially
# different) named entity on the way out.
#
# This is a copy of the same test from
# HTMLParserTreeBuilderSmokeTest. It's not in the superclass
# because the lxml HTML TreeBuilder _doesn't_ work this way.
for input_element, output_unicode, output_element in (
("&RightArrowLeftArrow;", '\u21c4', b'&rlarr;'),
('&models;', '\u22a7', b'&models;'),
('&Nfr;', '\U0001d511', b'&Nfr;'),
('&ngeqq;', '\u2267\u0338', b'&ngeqq;'),
('&not;', '\xac', b'&not;'),
('&Not;', '\u2aec', b'&Not;'),
('&quot;', '"', b'"'),
('&there4;', '\u2234', b'&there4;'),
('&Therefore;', '\u2234', b'&there4;'),
('&therefore;', '\u2234', b'&there4;'),
("&fjlig;", 'fj', b'fj'),
("&sqcup;", '\u2294', b'&sqcup;'),
("&sqcups;", '\u2294\ufe00', b'&sqcups;'),
("&apos;", "'", b"'"),
("&verbar;", "|", b"|"),
):
markup = '<div>%s</div>' % input_element
div = self.soup(markup).div
without_element = div.encode()
expect = b"<div>%s</div>" % output_unicode.encode("utf8")
assert without_element == expect
with_element = div.encode(formatter="html")
expect = b"<div>%s</div>" % output_element
assert with_element == expect

136
env/lib/python3.12/site-packages/bs4/tests/test_htmlparser.py vendored
View File

@@ -1,136 +0,0 @@
"""Tests to ensure that the html.parser tree builder generates good
trees."""
from pdb import set_trace
import pickle
import warnings
from bs4.builder import (
HTMLParserTreeBuilder,
XMLParsedAsHTMLWarning,
)
from bs4.builder._htmlparser import BeautifulSoupHTMLParser
from . import SoupTest, HTMLTreeBuilderSmokeTest
class TestHTMLParserTreeBuilder(SoupTest, HTMLTreeBuilderSmokeTest):
default_builder = HTMLParserTreeBuilder
def test_namespaced_system_doctype(self):
# html.parser can't handle namespaced doctypes, so skip this one.
pass
def test_namespaced_public_doctype(self):
# html.parser can't handle namespaced doctypes, so skip this one.
pass
def test_builder_is_pickled(self):
"""Unlike most tree builders, HTMLParserTreeBuilder and will
be restored after pickling.
"""
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
assert isinstance(loaded.builder, type(tree.builder))
def test_redundant_empty_element_closing_tags(self):
self.assert_soup('<br></br><br></br><br></br>', "<br/><br/><br/>")
self.assert_soup('</br></br></br>', "")
def test_empty_element(self):
# This verifies that any buffered data present when the parser
# finishes working is handled.
self.assert_soup("foo &# bar", "foo &amp;# bar")
def test_tracking_line_numbers(self):
# The html.parser TreeBuilder keeps track of line number and
# position of each element.
markup = "\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>"
soup = self.soup(markup)
assert 2 == soup.p.sourceline
assert 3 == soup.p.sourcepos
assert "sourceline" == soup.p.find('sourceline').name
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
assert "sourceline" == soup.p.sourceline.name
assert "sourcepos" == soup.p.sourcepos.name
def test_on_duplicate_attribute(self):
# The html.parser tree builder has a variety of ways of
# handling a tag that contains the same attribute multiple times.
markup = '<a class="cls" href="url1" href="url2" href="url3" id="id">'
# If you don't provide any particular value for
# on_duplicate_attribute, later values replace earlier values.
soup = self.soup(markup)
assert "url3" == soup.a['href']
assert ["cls"] == soup.a['class']
assert "id" == soup.a['id']
# You can also get this behavior explicitly.
def assert_attribute(on_duplicate_attribute, expected):
soup = self.soup(
markup, on_duplicate_attribute=on_duplicate_attribute
)
assert expected == soup.a['href']
# Verify that non-duplicate attributes are treated normally.
assert ["cls"] == soup.a['class']
assert "id" == soup.a['id']
assert_attribute(None, "url3")
assert_attribute(BeautifulSoupHTMLParser.REPLACE, "url3")
# You can ignore subsequent values in favor of the first.
assert_attribute(BeautifulSoupHTMLParser.IGNORE, "url1")
# And you can pass in a callable that does whatever you want.
def accumulate(attrs, key, value):
if not isinstance(attrs[key], list):
attrs[key] = [attrs[key]]
attrs[key].append(value)
assert_attribute(accumulate, ["url1", "url2", "url3"])
def test_html5_attributes(self):
# The html.parser TreeBuilder can convert any entity named in
# the HTML5 spec to a sequence of Unicode characters, and
# convert those Unicode characters to a (potentially
# different) named entity on the way out.
for input_element, output_unicode, output_element in (
("&RightArrowLeftArrow;", '\u21c4', b'&rlarr;'),
('&models;', '\u22a7', b'&models;'),
('&Nfr;', '\U0001d511', b'&Nfr;'),
('&ngeqq;', '\u2267\u0338', b'&ngeqq;'),
('&not;', '\xac', b'&not;'),
('&Not;', '\u2aec', b'&Not;'),
('&quot;', '"', b'"'),
('&there4;', '\u2234', b'&there4;'),
('&Therefore;', '\u2234', b'&there4;'),
('&therefore;', '\u2234', b'&there4;'),
("&fjlig;", 'fj', b'fj'),
("&sqcup;", '\u2294', b'&sqcup;'),
("&sqcups;", '\u2294\ufe00', b'&sqcups;'),
("&apos;", "'", b"'"),
("&verbar;", "|", b"|"),
):
markup = '<div>%s</div>' % input_element
div = self.soup(markup).div
without_element = div.encode()
expect = b"<div>%s</div>" % output_unicode.encode("utf8")
assert without_element == expect
with_element = div.encode(formatter="html")
expect = b"<div>%s</div>" % output_element
assert with_element == expect
class TestHTMLParserSubclass(SoupTest):
def test_error(self):
"""Verify that our HTMLParser subclass implements error() in a way
that doesn't cause a crash.
"""
parser = BeautifulSoupHTMLParser()
with warnings.catch_warnings(record=True) as warns:
parser.error("don't crash")
[warning] = warns
assert "don't crash" == str(warning.message)

199
env/lib/python3.12/site-packages/bs4/tests/test_lxml.py vendored
View File

@@ -1,199 +0,0 @@
"""Tests to ensure that the lxml tree builder generates good trees."""
import pickle
import re
import warnings
try:
import lxml.etree
LXML_PRESENT = True
LXML_VERSION = lxml.etree.LXML_VERSION
except ImportError as e:
LXML_PRESENT = False
LXML_VERSION = (0,)
if LXML_PRESENT:
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
from bs4 import (
BeautifulSoup,
BeautifulStoneSoup,
)
from bs4.element import Comment, Doctype, SoupStrainer
from . import (
HTMLTreeBuilderSmokeTest,
XMLTreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its tree builder.")
class TestLXMLTreeBuilder(SoupTest, HTMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilder
def test_out_of_range_entity(self):
self.assert_soup(
"<p>foo&#10000000000000;bar</p>", "<p>foobar</p>")
self.assert_soup(
"<p>foo&#x10000000000000;bar</p>", "<p>foobar</p>")
self.assert_soup(
"<p>foo&#1000000000;bar</p>", "<p>foobar</p>")
def test_entities_in_foreign_document_encoding(self):
# We can't implement this case correctly because by the time we
# hear about markup like "&#147;", it's been (incorrectly) converted into
# a string like u'\x93'
pass
# In lxml < 2.3.5, an empty doctype causes a segfault. Skip this
# test if an old version of lxml is installed.
@skipIf(
not LXML_PRESENT or LXML_VERSION < (2,3,5,0),
"Skipping doctype test for old version of lxml to avoid segfault.")
def test_empty_doctype(self):
soup = self.soup("<!DOCTYPE>")
doctype = soup.contents[0]
assert "" == doctype.strip()
def test_beautifulstonesoup_is_xml_parser(self):
# Make sure that the deprecated BSS class uses an xml builder
# if one is installed.
with warnings.catch_warnings(record=True) as w:
soup = BeautifulStoneSoup("<b />")
assert "<b/>" == str(soup.b)
assert "BeautifulStoneSoup class is deprecated" in str(w[0].message)
def test_tracking_line_numbers(self):
# The lxml TreeBuilder cannot keep track of line numbers from
# the original markup. Even if you ask for line numbers, we
# don't have 'em.
#
# This means that if you have a tag like <sourceline> or
# <sourcepos>, attribute access will find it rather than
# giving you a numeric answer.
soup = self.soup(
"\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>",
store_line_numbers=True
)
assert "sourceline" == soup.p.sourceline.name
assert "sourcepos" == soup.p.sourcepos.name
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its XML tree builder.")
class TestLXMLXMLTreeBuilder(SoupTest, XMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilderForXML
def test_namespace_indexing(self):
soup = self.soup(
'<?xml version="1.1"?>\n'
'<root>'
'<tag xmlns="http://unprefixed-namespace.com">content</tag>'
'<prefix:tag2 xmlns:prefix="http://prefixed-namespace.com">content</prefix:tag2>'
'<prefix2:tag3 xmlns:prefix2="http://another-namespace.com">'
'<subtag xmlns="http://another-unprefixed-namespace.com">'
'<subsubtag xmlns="http://yet-another-unprefixed-namespace.com">'
'</prefix2:tag3>'
'</root>'
)
# The BeautifulSoup object includes every namespace prefix
# defined in the entire document. This is the default set of
# namespaces used by soupsieve.
#
# Un-prefixed namespaces are not included, and if a given
# prefix is defined twice, only the first prefix encountered
# in the document shows up here.
assert soup._namespaces == {
'xml': 'http://www.w3.org/XML/1998/namespace',
'prefix': 'http://prefixed-namespace.com',
'prefix2': 'http://another-namespace.com'
}
# A Tag object includes only the namespace prefixes
# that were in scope when it was parsed.
# We do not track un-prefixed namespaces as we can only hold
# one (the first one), and it will be recognized as the
# default namespace by soupsieve, even when operating from a
# tag with a different un-prefixed namespace.
assert soup.tag._namespaces == {
'xml': 'http://www.w3.org/XML/1998/namespace',
}
assert soup.tag2._namespaces == {
'prefix': 'http://prefixed-namespace.com',
'xml': 'http://www.w3.org/XML/1998/namespace',
}
assert soup.subtag._namespaces == {
'prefix2': 'http://another-namespace.com',
'xml': 'http://www.w3.org/XML/1998/namespace',
}
assert soup.subsubtag._namespaces == {
'prefix2': 'http://another-namespace.com',
'xml': 'http://www.w3.org/XML/1998/namespace',
}
def test_namespace_interaction_with_select_and_find(self):
# Demonstrate how namespaces interact with select* and
# find* methods.
soup = self.soup(
'<?xml version="1.1"?>\n'
'<root>'
'<tag xmlns="http://unprefixed-namespace.com">content</tag>'
'<prefix:tag2 xmlns:prefix="http://prefixed-namespace.com">content</tag>'
'<subtag xmlns:prefix="http://another-namespace-same-prefix.com">'
'<prefix:tag3>'
'</subtag>'
'</root>'
)
# soupselect uses namespace URIs.
assert soup.select_one('tag').name == 'tag'
assert soup.select_one('prefix|tag2').name == 'tag2'
# If a prefix is declared more than once, only the first usage
# is registered with the BeautifulSoup object.
assert soup.select_one('prefix|tag3') is None
# But you can always explicitly specify a namespace dictionary.
assert soup.select_one(
'prefix|tag3', namespaces=soup.subtag._namespaces
).name == 'tag3'
# And a Tag (as opposed to the BeautifulSoup object) will
# have a set of default namespaces scoped to that Tag.
assert soup.subtag.select_one('prefix|tag3').name=='tag3'
# the find() methods aren't fully namespace-aware; they just
# look at prefixes.
assert soup.find('tag').name == 'tag'
assert soup.find('prefix:tag2').name == 'tag2'
assert soup.find('prefix:tag3').name == 'tag3'
assert soup.subtag.find('prefix:tag3').name == 'tag3'
def test_pickle_removes_builder(self):
# The lxml TreeBuilder is not picklable, so it won't be
# preserved in a pickle/unpickle operation.
soup = self.soup("<a>some markup</a>")
assert isinstance(soup.builder, self.default_builder)
pickled = pickle.dumps(soup)
unpickled = pickle.loads(pickled)
assert "some markup" == unpickled.a.string
assert unpickled.builder is None

144
env/lib/python3.12/site-packages/bs4/tests/test_navigablestring.py vendored
View File

@@ -1,144 +0,0 @@
import pytest
from bs4.element import (
CData,
Comment,
Declaration,
Doctype,
NavigableString,
RubyParenthesisString,
RubyTextString,
Script,
Stylesheet,
TemplateString,
)
from . import SoupTest
class TestNavigableString(SoupTest):
def test_text_acquisition_methods(self):
# These methods are intended for use against Tag, but they
# work on NavigableString as well,
s = NavigableString("fee ")
cdata = CData("fie ")
comment = Comment("foe ")
assert "fee " == s.get_text()
assert "fee" == s.get_text(strip=True)
assert ["fee "] == list(s.strings)
assert ["fee"] == list(s.stripped_strings)
assert ["fee "] == list(s._all_strings())
assert "fie " == cdata.get_text()
assert "fie" == cdata.get_text(strip=True)
assert ["fie "] == list(cdata.strings)
assert ["fie"] == list(cdata.stripped_strings)
assert ["fie "] == list(cdata._all_strings())
# Since a Comment isn't normally considered 'text',
# these methods generally do nothing.
assert "" == comment.get_text()
assert [] == list(comment.strings)
assert [] == list(comment.stripped_strings)
assert [] == list(comment._all_strings())
# Unless you specifically say that comments are okay.
assert "foe" == comment.get_text(strip=True, types=Comment)
assert "foe " == comment.get_text(types=(Comment, NavigableString))
def test_string_has_immutable_name_property(self):
# string.name is defined as None and can't be modified
string = self.soup("s").string
assert None == string.name
with pytest.raises(AttributeError):
string.name = 'foo'
class TestNavigableStringSubclasses(SoupTest):
def test_cdata(self):
# None of the current builders turn CDATA sections into CData
# objects, but you can create them manually.
soup = self.soup("")
cdata = CData("foo")
soup.insert(1, cdata)
assert str(soup) == "<![CDATA[foo]]>"
assert soup.find(string="foo") == "foo"
assert soup.contents[0] == "foo"
def test_cdata_is_never_formatted(self):
"""Text inside a CData object is passed into the formatter.
But the return value is ignored.
"""
self.count = 0
def increment(*args):
self.count += 1
return "BITTER FAILURE"
soup = self.soup("")
cdata = CData("<><><>")
soup.insert(1, cdata)
assert b"<![CDATA[<><><>]]>" == soup.encode(formatter=increment)
assert 1 == self.count
def test_doctype_ends_in_newline(self):
# Unlike other NavigableString subclasses, a DOCTYPE always ends
# in a newline.
doctype = Doctype("foo")
soup = self.soup("")
soup.insert(1, doctype)
assert soup.encode() == b"<!DOCTYPE foo>\n"
def test_declaration(self):
d = Declaration("foo")
assert "<?foo?>" == d.output_ready()
def test_default_string_containers(self):
# In some cases, we use different NavigableString subclasses for
# the same text in different tags.
soup = self.soup(
"<div>text</div><script>text</script><style>text</style>"
)
assert [NavigableString, Script, Stylesheet] == [
x.__class__ for x in soup.find_all(string=True)
]
# The TemplateString is a little unusual because it's generally found
# _inside_ children of a <template> element, not a direct child of the
# <template> element.
soup = self.soup(
"<template>Some text<p>In a tag</p></template>Some text outside"
)
assert all(
isinstance(x, TemplateString)
for x in soup.template._all_strings(types=None)
)
# Once the <template> tag closed, we went back to using
# NavigableString.
outside = soup.template.next_sibling
assert isinstance(outside, NavigableString)
assert not isinstance(outside, TemplateString)
# The TemplateString is also unusual because it can contain
# NavigableString subclasses of _other_ types, such as
# Comment.
markup = b"<template>Some text<p>In a tag</p><!--with a comment--></template>"
soup = self.soup(markup)
assert markup == soup.template.encode("utf8")
def test_ruby_strings(self):
markup = "<ruby>漢 <rp>(</rp><rt>kan</rt><rp>)</rp> 字 <rp>(</rp><rt>ji</rt><rp>)</rp></ruby>"
soup = self.soup(markup)
assert isinstance(soup.rp.string, RubyParenthesisString)
assert isinstance(soup.rt.string, RubyTextString)
# Just as a demo, here's what this means for get_text usage.
assert "漢字" == soup.get_text(strip=True)
assert "漢(kan)字(ji)" == soup.get_text(
strip=True,
types=(NavigableString, RubyTextString, RubyParenthesisString)
)

751
env/lib/python3.12/site-packages/bs4/tests/test_pageelement.py vendored
View File

@@ -1,751 +0,0 @@
"""Tests of the bs4.element.PageElement class"""
import copy
import pickle
import pytest
from soupsieve import SelectorSyntaxError
from bs4 import BeautifulSoup
from bs4.element import (
Comment,
SoupStrainer,
)
from . import SoupTest
class TestEncoding(SoupTest):
"""Test the ability to encode objects into strings."""
def test_unicode_string_can_be_encoded(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert soup.b.string.encode("utf-8") == "\N{SNOWMAN}".encode("utf-8")
def test_tag_containing_unicode_string_can_be_encoded(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert soup.b.encode("utf-8") == html.encode("utf-8")
def test_encoding_substitutes_unrecognized_characters_by_default(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert soup.b.encode("ascii") == b"<b>&#9731;</b>"
def test_encoding_can_be_made_strict(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
with pytest.raises(UnicodeEncodeError):
soup.encode("ascii", errors="strict")
def test_decode_contents(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert "\N{SNOWMAN}" == soup.b.decode_contents()
def test_encode_contents(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert "\N{SNOWMAN}".encode("utf8") == soup.b.encode_contents(
encoding="utf8"
)
def test_deprecated_renderContents(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert "\N{SNOWMAN}".encode("utf8") == soup.b.renderContents()
def test_repr(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert html == repr(soup)
class TestFormatters(SoupTest):
"""Test the formatting feature, used by methods like decode() and
prettify(), and the formatters themselves.
"""
def test_default_formatter_is_minimal(self):
markup = "<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="minimal")
# The < is converted back into &lt; but the e-with-acute is left alone.
assert decoded == self.document_for(
"<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
)
def test_formatter_html(self):
markup = "<br><b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="html")
assert decoded == self.document_for(
"<br/><b>&lt;&lt;Sacr&eacute; bleu!&gt;&gt;</b>"
)
def test_formatter_html5(self):
markup = "<br><b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="html5")
assert decoded == self.document_for(
"<br><b>&lt;&lt;Sacr&eacute; bleu!&gt;&gt;</b>"
)
def test_formatter_minimal(self):
markup = "<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="minimal")
# The < is converted back into &lt; but the e-with-acute is left alone.
assert decoded == self.document_for(
"<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
)
def test_formatter_null(self):
markup = "<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter=None)
# Neither the angle brackets nor the e-with-acute are converted.
# This is not valid HTML, but it's what the user wanted.
assert decoded == self.document_for(
"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>"
)
def test_formatter_custom(self):
markup = "<b>&lt;foo&gt;</b><b>bar</b><br/>"
soup = self.soup(markup)
decoded = soup.decode(formatter = lambda x: x.upper())
# Instead of normal entity conversion code, the custom
# callable is called on every string.
assert decoded == self.document_for("<b><FOO></b><b>BAR</b><br/>")
def test_formatter_is_run_on_attribute_values(self):
markup = '<a href="http://a.com?a=b&c=é">e</a>'
soup = self.soup(markup)
a = soup.a
expect_minimal = '<a href="http://a.com?a=b&amp;c=é">e</a>'
assert expect_minimal == a.decode()
assert expect_minimal == a.decode(formatter="minimal")
expect_html = '<a href="http://a.com?a=b&amp;c=&eacute;">e</a>'
assert expect_html == a.decode(formatter="html")
assert markup == a.decode(formatter=None)
expect_upper = '<a href="HTTP://A.COM?A=B&C=É">E</a>'
assert expect_upper == a.decode(formatter=lambda x: x.upper())
def test_formatter_skips_script_tag_for_html_documents(self):
doc = """
<script type="text/javascript">
console.log("< < hey > > ");
</script>
"""
encoded = BeautifulSoup(doc, 'html.parser').encode()
assert b"< < hey > >" in encoded
def test_formatter_skips_style_tag_for_html_documents(self):
doc = """
<style type="text/css">
console.log("< < hey > > ");
</style>
"""
encoded = BeautifulSoup(doc, 'html.parser').encode()
assert b"< < hey > >" in encoded
def test_prettify_leaves_preformatted_text_alone(self):
soup = self.soup("<div> foo <pre> \tbar\n \n </pre> baz <textarea> eee\nfff\t</textarea></div>")
# Everything outside the <pre> tag is reformatted, but everything
# inside is left alone.
assert '<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n <textarea> eee\nfff\t</textarea>\n</div>' == soup.div.prettify()
def test_prettify_accepts_formatter_function(self):
soup = BeautifulSoup("<html><body>foo</body></html>", 'html.parser')
pretty = soup.prettify(formatter = lambda x: x.upper())
assert "FOO" in pretty
def test_prettify_outputs_unicode_by_default(self):
soup = self.soup("<a></a>")
assert str == type(soup.prettify())
def test_prettify_can_encode_data(self):
soup = self.soup("<a></a>")
assert bytes == type(soup.prettify("utf-8"))
def test_html_entity_substitution_off_by_default(self):
markup = "<b>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</b>"
soup = self.soup(markup)
encoded = soup.b.encode("utf-8")
assert encoded == markup.encode('utf-8')
def test_encoding_substitution(self):
# Here's the <meta> tag saying that a document is
# encoded in Shift-JIS.
meta_tag = ('<meta content="text/html; charset=x-sjis" '
'http-equiv="Content-type"/>')
soup = self.soup(meta_tag)
# Parse the document, and the charset apprears unchanged.
assert soup.meta['content'] == 'text/html; charset=x-sjis'
# Encode the document into some encoding, and the encoding is
# substituted into the meta tag.
utf_8 = soup.encode("utf-8")
assert b"charset=utf-8" in utf_8
euc_jp = soup.encode("euc_jp")
assert b"charset=euc_jp" in euc_jp
shift_jis = soup.encode("shift-jis")
assert b"charset=shift-jis" in shift_jis
utf_16_u = soup.encode("utf-16").decode("utf-16")
assert "charset=utf-16" in utf_16_u
def test_encoding_substitution_doesnt_happen_if_tag_is_strained(self):
markup = ('<head><meta content="text/html; charset=x-sjis" '
'http-equiv="Content-type"/></head><pre>foo</pre>')
# Beautiful Soup used to try to rewrite the meta tag even if the
# meta tag got filtered out by the strainer. This test makes
# sure that doesn't happen.
strainer = SoupStrainer('pre')
soup = self.soup(markup, parse_only=strainer)
assert soup.contents[0].name == 'pre'
class TestCSSSelectors(SoupTest):
"""Test basic CSS selector functionality.
This functionality is implemented in soupsieve, which has a much
more comprehensive test suite, so this is basically an extra check
that soupsieve works as expected.
"""
HTML = """
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>The title</title>
<link rel="stylesheet" href="blah.css" type="text/css" id="l1">
</head>
<body>
<custom-dashed-tag class="dashed" id="dash1">Hello there.</custom-dashed-tag>
<div id="main" class="fancy">
<div id="inner">
<h1 id="header1">An H1</h1>
<p>Some text</p>
<p class="onep" id="p1">Some more text</p>
<h2 id="header2">An H2</h2>
<p class="class1 class2 class3" id="pmulti">Another</p>
<a href="http://bob.example.org/" rel="friend met" id="bob">Bob</a>
<h2 id="header3">Another H2</h2>
<a id="me" href="http://simonwillison.net/" rel="me">me</a>
<span class="s1">
<a href="#" id="s1a1">span1a1</a>
<a href="#" id="s1a2">span1a2 <span id="s1a2s1">test</span></a>
<span class="span2">
<a href="#" id="s2a1">span2a1</a>
</span>
<span class="span3"></span>
<custom-dashed-tag class="dashed" id="dash2"/>
<div data-tag="dashedvalue" id="data1"/>
</span>
</div>
<x id="xid">
<z id="zida"/>
<z id="zidab"/>
<z id="zidac"/>
</x>
<y id="yid">
<z id="zidb"/>
</y>
<p lang="en" id="lang-en">English</p>
<p lang="en-gb" id="lang-en-gb">English UK</p>
<p lang="en-us" id="lang-en-us">English US</p>
<p lang="fr" id="lang-fr">French</p>
</div>
<div id="footer">
</div>
"""
def setup_method(self):
self.soup = BeautifulSoup(self.HTML, 'html.parser')
def assert_selects(self, selector, expected_ids, **kwargs):
el_ids = [el['id'] for el in self.soup.select(selector, **kwargs)]
el_ids.sort()
expected_ids.sort()
assert expected_ids == el_ids, "Selector %s, expected [%s], got [%s]" % (
selector, ', '.join(expected_ids), ', '.join(el_ids)
)
assertSelect = assert_selects
def assert_select_multiple(self, *tests):
for selector, expected_ids in tests:
self.assert_selects(selector, expected_ids)
def test_one_tag_one(self):
els = self.soup.select('title')
assert len(els) == 1
assert els[0].name == 'title'
assert els[0].contents == ['The title']
def test_one_tag_many(self):
els = self.soup.select('div')
assert len(els) == 4
for div in els:
assert div.name == 'div'
el = self.soup.select_one('div')
assert 'main' == el['id']
def test_select_one_returns_none_if_no_match(self):
match = self.soup.select_one('nonexistenttag')
assert None == match
def test_tag_in_tag_one(self):
els = self.soup.select('div div')
self.assert_selects('div div', ['inner', 'data1'])
def test_tag_in_tag_many(self):
for selector in ('html div', 'html body div', 'body div'):
self.assert_selects(selector, ['data1', 'main', 'inner', 'footer'])
def test_limit(self):
self.assert_selects('html div', ['main'], limit=1)
self.assert_selects('html body div', ['inner', 'main'], limit=2)
self.assert_selects('body div', ['data1', 'main', 'inner', 'footer'],
limit=10)
def test_tag_no_match(self):
assert len(self.soup.select('del')) == 0
def test_invalid_tag(self):
with pytest.raises(SelectorSyntaxError):
self.soup.select('tag%t')
def test_select_dashed_tag_ids(self):
self.assert_selects('custom-dashed-tag', ['dash1', 'dash2'])
def test_select_dashed_by_id(self):
dashed = self.soup.select('custom-dashed-tag[id=\"dash2\"]')
assert dashed[0].name == 'custom-dashed-tag'
assert dashed[0]['id'] == 'dash2'
def test_dashed_tag_text(self):
assert self.soup.select('body > custom-dashed-tag')[0].text == 'Hello there.'
def test_select_dashed_matches_find_all(self):
assert self.soup.select('custom-dashed-tag') == self.soup.find_all('custom-dashed-tag')
def test_header_tags(self):
self.assert_select_multiple(
('h1', ['header1']),
('h2', ['header2', 'header3']),
)
def test_class_one(self):
for selector in ('.onep', 'p.onep', 'html p.onep'):
els = self.soup.select(selector)
assert len(els) == 1
assert els[0].name == 'p'
assert els[0]['class'] == ['onep']
def test_class_mismatched_tag(self):
els = self.soup.select('div.onep')
assert len(els) == 0
def test_one_id(self):
for selector in ('div#inner', '#inner', 'div div#inner'):
self.assert_selects(selector, ['inner'])
def test_bad_id(self):
els = self.soup.select('#doesnotexist')
assert len(els) == 0
def test_items_in_id(self):
els = self.soup.select('div#inner p')
assert len(els) == 3
for el in els:
assert el.name == 'p'
assert els[1]['class'] == ['onep']
assert not els[0].has_attr('class')
def test_a_bunch_of_emptys(self):
for selector in ('div#main del', 'div#main div.oops', 'div div#main'):
assert len(self.soup.select(selector)) == 0
def test_multi_class_support(self):
for selector in ('.class1', 'p.class1', '.class2', 'p.class2',
'.class3', 'p.class3', 'html p.class2', 'div#inner .class2'):
self.assert_selects(selector, ['pmulti'])
def test_multi_class_selection(self):
for selector in ('.class1.class3', '.class3.class2',
'.class1.class2.class3'):
self.assert_selects(selector, ['pmulti'])
def test_child_selector(self):
self.assert_selects('.s1 > a', ['s1a1', 's1a2'])
self.assert_selects('.s1 > a span', ['s1a2s1'])
def test_child_selector_id(self):
self.assert_selects('.s1 > a#s1a2 span', ['s1a2s1'])
def test_attribute_equals(self):
self.assert_select_multiple(
('p[class="onep"]', ['p1']),
('p[id="p1"]', ['p1']),
('[class="onep"]', ['p1']),
('[id="p1"]', ['p1']),
('link[rel="stylesheet"]', ['l1']),
('link[type="text/css"]', ['l1']),
('link[href="blah.css"]', ['l1']),
('link[href="no-blah.css"]', []),
('[rel="stylesheet"]', ['l1']),
('[type="text/css"]', ['l1']),
('[href="blah.css"]', ['l1']),
('[href="no-blah.css"]', []),
('p[href="no-blah.css"]', []),
('[href="no-blah.css"]', []),
)
def test_attribute_tilde(self):
self.assert_select_multiple(
('p[class~="class1"]', ['pmulti']),
('p[class~="class2"]', ['pmulti']),
('p[class~="class3"]', ['pmulti']),
('[class~="class1"]', ['pmulti']),
('[class~="class2"]', ['pmulti']),
('[class~="class3"]', ['pmulti']),
('a[rel~="friend"]', ['bob']),
('a[rel~="met"]', ['bob']),
('[rel~="friend"]', ['bob']),
('[rel~="met"]', ['bob']),
)
def test_attribute_startswith(self):
self.assert_select_multiple(
('[rel^="style"]', ['l1']),
('link[rel^="style"]', ['l1']),
('notlink[rel^="notstyle"]', []),
('[rel^="notstyle"]', []),
('link[rel^="notstyle"]', []),
('link[href^="bla"]', ['l1']),
('a[href^="http://"]', ['bob', 'me']),
('[href^="http://"]', ['bob', 'me']),
('[id^="p"]', ['pmulti', 'p1']),
('[id^="m"]', ['me', 'main']),
('div[id^="m"]', ['main']),
('a[id^="m"]', ['me']),
('div[data-tag^="dashed"]', ['data1'])
)
def test_attribute_endswith(self):
self.assert_select_multiple(
('[href$=".css"]', ['l1']),
('link[href$=".css"]', ['l1']),
('link[id$="1"]', ['l1']),
('[id$="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's2a1', 's1a2s1', 'dash1']),
('div[id$="1"]', ['data1']),
('[id$="noending"]', []),
)
def test_attribute_contains(self):
self.assert_select_multiple(
# From test_attribute_startswith
('[rel*="style"]', ['l1']),
('link[rel*="style"]', ['l1']),
('notlink[rel*="notstyle"]', []),
('[rel*="notstyle"]', []),
('link[rel*="notstyle"]', []),
('link[href*="bla"]', ['l1']),
('[href*="http://"]', ['bob', 'me']),
('[id*="p"]', ['pmulti', 'p1']),
('div[id*="m"]', ['main']),
('a[id*="m"]', ['me']),
# From test_attribute_endswith
('[href*=".css"]', ['l1']),
('link[href*=".css"]', ['l1']),
('link[id*="1"]', ['l1']),
('[id*="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's1a2', 's2a1', 's1a2s1', 'dash1']),
('div[id*="1"]', ['data1']),
('[id*="noending"]', []),
# New for this test
('[href*="."]', ['bob', 'me', 'l1']),
('a[href*="."]', ['bob', 'me']),
('link[href*="."]', ['l1']),
('div[id*="n"]', ['main', 'inner']),
('div[id*="nn"]', ['inner']),
('div[data-tag*="edval"]', ['data1'])
)
def test_attribute_exact_or_hypen(self):
self.assert_select_multiple(
('p[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
('[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
('p[lang|="fr"]', ['lang-fr']),
('p[lang|="gb"]', []),
)
def test_attribute_exists(self):
self.assert_select_multiple(
('[rel]', ['l1', 'bob', 'me']),
('link[rel]', ['l1']),
('a[rel]', ['bob', 'me']),
('[lang]', ['lang-en', 'lang-en-gb', 'lang-en-us', 'lang-fr']),
('p[class]', ['p1', 'pmulti']),
('[blah]', []),
('p[blah]', []),
('div[data-tag]', ['data1'])
)
def test_quoted_space_in_selector_name(self):
html = """<div style="display: wrong">nope</div>
<div style="display: right">yes</div>
"""
soup = BeautifulSoup(html, 'html.parser')
[chosen] = soup.select('div[style="display: right"]')
assert "yes" == chosen.string
def test_unsupported_pseudoclass(self):
with pytest.raises(NotImplementedError):
self.soup.select("a:no-such-pseudoclass")
with pytest.raises(SelectorSyntaxError):
self.soup.select("a:nth-of-type(a)")
def test_nth_of_type(self):
# Try to select first paragraph
els = self.soup.select('div#inner p:nth-of-type(1)')
assert len(els) == 1
assert els[0].string == 'Some text'
# Try to select third paragraph
els = self.soup.select('div#inner p:nth-of-type(3)')
assert len(els) == 1
assert els[0].string == 'Another'
# Try to select (non-existent!) fourth paragraph
els = self.soup.select('div#inner p:nth-of-type(4)')
assert len(els) == 0
# Zero will select no tags.
els = self.soup.select('div p:nth-of-type(0)')
assert len(els) == 0
def test_nth_of_type_direct_descendant(self):
els = self.soup.select('div#inner > p:nth-of-type(1)')
assert len(els) == 1
assert els[0].string == 'Some text'
def test_id_child_selector_nth_of_type(self):
self.assert_selects('#inner > p:nth-of-type(2)', ['p1'])
def test_select_on_element(self):
# Other tests operate on the tree; this operates on an element
# within the tree.
inner = self.soup.find("div", id="main")
selected = inner.select("div")
# The <div id="inner"> tag was selected. The <div id="footer">
# tag was not.
self.assert_selects_ids(selected, ['inner', 'data1'])
def test_overspecified_child_id(self):
self.assert_selects(".fancy #inner", ['inner'])
self.assert_selects(".normal #inner", [])
def test_adjacent_sibling_selector(self):
self.assert_selects('#p1 + h2', ['header2'])
self.assert_selects('#p1 + h2 + p', ['pmulti'])
self.assert_selects('#p1 + #header2 + .class1', ['pmulti'])
assert [] == self.soup.select('#p1 + p')
def test_general_sibling_selector(self):
self.assert_selects('#p1 ~ h2', ['header2', 'header3'])
self.assert_selects('#p1 ~ #header2', ['header2'])
self.assert_selects('#p1 ~ h2 + a', ['me'])
self.assert_selects('#p1 ~ h2 + [rel="me"]', ['me'])
assert [] == self.soup.select('#inner ~ h2')
def test_dangling_combinator(self):
with pytest.raises(SelectorSyntaxError):
self.soup.select('h1 >')
def test_sibling_combinator_wont_select_same_tag_twice(self):
self.assert_selects('p[lang] ~ p', ['lang-en-gb', 'lang-en-us', 'lang-fr'])
# Test the selector grouping operator (the comma)
def test_multiple_select(self):
self.assert_selects('x, y', ['xid', 'yid'])
def test_multiple_select_with_no_space(self):
self.assert_selects('x,y', ['xid', 'yid'])
def test_multiple_select_with_more_space(self):
self.assert_selects('x, y', ['xid', 'yid'])
def test_multiple_select_duplicated(self):
self.assert_selects('x, x', ['xid'])
def test_multiple_select_sibling(self):
self.assert_selects('x, y ~ p[lang=fr]', ['xid', 'lang-fr'])
def test_multiple_select_tag_and_direct_descendant(self):
self.assert_selects('x, y > z', ['xid', 'zidb'])
def test_multiple_select_direct_descendant_and_tags(self):
self.assert_selects('div > x, y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
def test_multiple_select_indirect_descendant(self):
self.assert_selects('div x,y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
def test_invalid_multiple_select(self):
with pytest.raises(SelectorSyntaxError):
self.soup.select(',x, y')
with pytest.raises(SelectorSyntaxError):
self.soup.select('x,,y')
def test_multiple_select_attrs(self):
self.assert_selects('p[lang=en], p[lang=en-gb]', ['lang-en', 'lang-en-gb'])
def test_multiple_select_ids(self):
self.assert_selects('x, y > z[id=zida], z[id=zidab], z[id=zidb]', ['xid', 'zidb', 'zidab'])
def test_multiple_select_nested(self):
self.assert_selects('body > div > x, y > z', ['xid', 'zidb'])
def test_select_duplicate_elements(self):
# When markup contains duplicate elements, a multiple select
# will find all of them.
markup = '<div class="c1"/><div class="c2"/><div class="c1"/>'
soup = BeautifulSoup(markup, 'html.parser')
selected = soup.select(".c1, .c2")
assert 3 == len(selected)
# Verify that find_all finds the same elements, though because
# of an implementation detail it finds them in a different
# order.
for element in soup.find_all(class_=['c1', 'c2']):
assert element in selected
class TestPersistence(SoupTest):
"Testing features like pickle and deepcopy."
def setup_method(self):
self.page = """<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
"http://www.w3.org/TR/REC-html40/transitional.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>Beautiful Soup: We called him Tortoise because he taught us.</title>
<link rev="made" href="mailto:leonardr@segfault.org">
<meta name="Description" content="Beautiful Soup: an HTML parser optimized for screen-scraping.">
<meta name="generator" content="Markov Approximation 1.4 (module: leonardr)">
<meta name="author" content="Leonard Richardson">
</head>
<body>
<a href="foo">foo</a>
<a href="foo"><b>bar</b></a>
</body>
</html>"""
self.tree = self.soup(self.page)
def test_pickle_and_unpickle_identity(self):
# Pickling a tree, then unpickling it, yields a tree identical
# to the original.
dumped = pickle.dumps(self.tree, 2)
loaded = pickle.loads(dumped)
assert loaded.__class__ == BeautifulSoup
assert loaded.decode() == self.tree.decode()
def test_deepcopy_identity(self):
# Making a deepcopy of a tree yields an identical tree.
copied = copy.deepcopy(self.tree)
assert copied.decode() == self.tree.decode()
def test_copy_preserves_encoding(self):
soup = BeautifulSoup(b'<p>&nbsp;</p>', 'html.parser')
encoding = soup.original_encoding
copy = soup.__copy__()
assert "<p> </p>" == str(copy)
assert encoding == copy.original_encoding
def test_copy_preserves_builder_information(self):
tag = self.soup('<p></p>').p
# Simulate a tag obtained from a source file.
tag.sourceline = 10
tag.sourcepos = 33
copied = tag.__copy__()
# The TreeBuilder object is no longer availble, but information
# obtained from it gets copied over to the new Tag object.
assert tag.sourceline == copied.sourceline
assert tag.sourcepos == copied.sourcepos
assert tag.can_be_empty_element == copied.can_be_empty_element
assert tag.cdata_list_attributes == copied.cdata_list_attributes
assert tag.preserve_whitespace_tags == copied.preserve_whitespace_tags
def test_unicode_pickle(self):
# A tree containing Unicode characters can be pickled.
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
dumped = pickle.dumps(soup, pickle.HIGHEST_PROTOCOL)
loaded = pickle.loads(dumped)
assert loaded.decode() == soup.decode()
def test_copy_navigablestring_is_not_attached_to_tree(self):
html = "<b>Foo<a></a></b><b>Bar</b>"
soup = self.soup(html)
s1 = soup.find(string="Foo")
s2 = copy.copy(s1)
assert s1 == s2
assert None == s2.parent
assert None == s2.next_element
assert None != s1.next_sibling
assert None == s2.next_sibling
assert None == s2.previous_element
def test_copy_navigablestring_subclass_has_same_type(self):
html = "<b><!--Foo--></b>"
soup = self.soup(html)
s1 = soup.string
s2 = copy.copy(s1)
assert s1 == s2
assert isinstance(s2, Comment)
def test_copy_entire_soup(self):
html = "<div><b>Foo<a></a></b><b>Bar</b></div>end"
soup = self.soup(html)
soup_copy = copy.copy(soup)
assert soup == soup_copy
def test_copy_tag_copies_contents(self):
html = "<div><b>Foo<a></a></b><b>Bar</b></div>end"
soup = self.soup(html)
div = soup.div
div_copy = copy.copy(div)
# The two tags look the same, and evaluate to equal.
assert str(div) == str(div_copy)
assert div == div_copy
# But they're not the same object.
assert div is not div_copy
# And they don't have the same relation to the parse tree. The
# copy is not associated with a parse tree at all.
assert None == div_copy.parent
assert None == div_copy.previous_element
assert None == div_copy.find(string='Bar').next_element
assert None != div.find(string='Bar').next_element

462
env/lib/python3.12/site-packages/bs4/tests/test_soup.py vendored
View File

@@ -1,462 +0,0 @@
# -*- coding: utf-8 -*-
"""Tests of Beautiful Soup as a whole."""
from pdb import set_trace
import logging
import os
import pickle
import pytest
import sys
import tempfile
from bs4 import (
BeautifulSoup,
BeautifulStoneSoup,
GuessedAtParserWarning,
MarkupResemblesLocatorWarning,
dammit,
)
from bs4.builder import (
builder_registry,
TreeBuilder,
ParserRejectedMarkup,
)
from bs4.element import (
Comment,
SoupStrainer,
Tag,
NavigableString,
)
from . import (
default_builder,
SoupTest,
skipIf,
)
import warnings
try:
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
LXML_PRESENT = True
except ImportError as e:
LXML_PRESENT = False
PYTHON_3_PRE_3_2 = (sys.version_info[0] == 3 and sys.version_info < (3,2))
class TestConstructor(SoupTest):
def test_short_unicode_input(self):
data = "<h1>éé</h1>"
soup = self.soup(data)
assert "éé" == soup.h1.string
def test_embedded_null(self):
data = "<h1>foo\0bar</h1>"
soup = self.soup(data)
assert "foo\0bar" == soup.h1.string
def test_exclude_encodings(self):
utf8_data = "Räksmörgås".encode("utf-8")
soup = self.soup(utf8_data, exclude_encodings=["utf-8"])
assert "windows-1252" == soup.original_encoding
def test_custom_builder_class(self):
# Verify that you can pass in a custom Builder class and
# it'll be instantiated with the appropriate keyword arguments.
class Mock(object):
def __init__(self, **kwargs):
self.called_with = kwargs
self.is_xml = True
self.store_line_numbers = False
self.cdata_list_attributes = []
self.preserve_whitespace_tags = []
self.string_containers = {}
def initialize_soup(self, soup):
pass
def feed(self, markup):
self.fed = markup
def reset(self):
pass
def ignore(self, ignore):
pass
set_up_substitutions = can_be_empty_element = ignore
def prepare_markup(self, *args, **kwargs):
yield "prepared markup", "original encoding", "declared encoding", "contains replacement characters"
kwargs = dict(
var="value",
# This is a deprecated BS3-era keyword argument, which
# will be stripped out.
convertEntities=True,
)
with warnings.catch_warnings(record=True):
soup = BeautifulSoup('', builder=Mock, **kwargs)
assert isinstance(soup.builder, Mock)
assert dict(var="value") == soup.builder.called_with
assert "prepared markup" == soup.builder.fed
# You can also instantiate the TreeBuilder yourself. In this
# case, that specific object is used and any keyword arguments
# to the BeautifulSoup constructor are ignored.
builder = Mock(**kwargs)
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup(
'', builder=builder, ignored_value=True,
)
msg = str(w[0].message)
assert msg.startswith("Keyword arguments to the BeautifulSoup constructor will be ignored.")
assert builder == soup.builder
assert kwargs == builder.called_with
def test_parser_markup_rejection(self):
# If markup is completely rejected by the parser, an
# explanatory ParserRejectedMarkup exception is raised.
class Mock(TreeBuilder):
def feed(self, *args, **kwargs):
raise ParserRejectedMarkup("Nope.")
def prepare_markup(self, *args, **kwargs):
# We're going to try two different ways of preparing this markup,
# but feed() will reject both of them.
yield markup, None, None, False
yield markup, None, None, False
import re
with pytest.raises(ParserRejectedMarkup) as exc_info:
BeautifulSoup('', builder=Mock)
assert "The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help." in str(exc_info.value)
def test_cdata_list_attributes(self):
# Most attribute values are represented as scalars, but the
# HTML standard says that some attributes, like 'class' have
# space-separated lists as values.
markup = '<a id=" an id " class=" a class "></a>'
soup = self.soup(markup)
# Note that the spaces are stripped for 'class' but not for 'id'.
a = soup.a
assert " an id " == a['id']
assert ["a", "class"] == a['class']
# TreeBuilder takes an argument called 'mutli_valued_attributes' which lets
# you customize or disable this. As always, you can customize the TreeBuilder
# by passing in a keyword argument to the BeautifulSoup constructor.
soup = self.soup(markup, builder=default_builder, multi_valued_attributes=None)
assert " a class " == soup.a['class']
# Here are two ways of saying that `id` is a multi-valued
# attribute in this context, but 'class' is not.
for switcheroo in ({'*': 'id'}, {'a': 'id'}):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
soup = self.soup(markup, builder=None, multi_valued_attributes=switcheroo)
a = soup.a
assert ["an", "id"] == a['id']
assert " a class " == a['class']
def test_replacement_classes(self):
# Test the ability to pass in replacements for element classes
# which will be used when building the tree.
class TagPlus(Tag):
pass
class StringPlus(NavigableString):
pass
class CommentPlus(Comment):
pass
soup = self.soup(
"<a><b>foo</b>bar</a><!--whee-->",
element_classes = {
Tag: TagPlus,
NavigableString: StringPlus,
Comment: CommentPlus,
}
)
# The tree was built with TagPlus, StringPlus, and CommentPlus objects,
# rather than Tag, String, and Comment objects.
assert all(
isinstance(x, (TagPlus, StringPlus, CommentPlus))
for x in soup.recursiveChildGenerator()
)
def test_alternate_string_containers(self):
# Test the ability to customize the string containers for
# different types of tags.
class PString(NavigableString):
pass
class BString(NavigableString):
pass
soup = self.soup(
"<div>Hello.<p>Here is <b>some <i>bolded</i></b> text",
string_containers = {
'b': BString,
'p': PString,
}
)
# The string before the <p> tag is a regular NavigableString.
assert isinstance(soup.div.contents[0], NavigableString)
# The string inside the <p> tag, but not inside the <i> tag,
# is a PString.
assert isinstance(soup.p.contents[0], PString)
# Every string inside the <b> tag is a BString, even the one that
# was also inside an <i> tag.
for s in soup.b.strings:
assert isinstance(s, BString)
# Now that parsing was complete, the string_container_stack
# (where this information was kept) has been cleared out.
assert [] == soup.string_container_stack
class TestWarnings(SoupTest):
def _assert_warning(self, warnings, cls):
for w in warnings:
if isinstance(w.message, cls):
return w
raise Exception("%s warning not found in %r" % (cls, warnings))
def _assert_no_parser_specified(self, w):
warning = self._assert_warning(w, GuessedAtParserWarning)
message = str(warning.message)
assert message.startswith(BeautifulSoup.NO_PARSER_SPECIFIED_WARNING[:60])
def test_warning_if_no_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup("<a><b></b></a>")
self._assert_no_parser_specified(w)
def test_warning_if_parser_specified_too_vague(self):
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup("<a><b></b></a>", "html")
self._assert_no_parser_specified(w)
def test_no_warning_if_explicit_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup("<a><b></b></a>", "html.parser")
assert [] == w
def test_parseOnlyThese_renamed_to_parse_only(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", parseOnlyThese=SoupStrainer("b"))
msg = str(w[0].message)
assert "parseOnlyThese" in msg
assert "parse_only" in msg
assert b"<b></b>" == soup.encode()
def test_fromEncoding_renamed_to_from_encoding(self):
with warnings.catch_warnings(record=True) as w:
utf8 = b"\xc3\xa9"
soup = self.soup(utf8, fromEncoding="utf8")
msg = str(w[0].message)
assert "fromEncoding" in msg
assert "from_encoding" in msg
assert "utf8" == soup.original_encoding
def test_unrecognized_keyword_argument(self):
with pytest.raises(TypeError):
self.soup("<a>", no_such_argument=True)
@pytest.mark.parametrize(
"extension",
['markup.html', 'markup.htm', 'markup.HTML', 'markup.txt',
'markup.xhtml', 'markup.xml', "/home/user/file", "c:\\user\file"]
)
def test_resembles_filename_warning(self, extension):
# A warning is issued if the "markup" looks like the name of
# an HTML or text file, or a full path to a file on disk.
with warnings.catch_warnings(record=True) as w:
soup = self.soup("markup" + extension)
warning = self._assert_warning(w, MarkupResemblesLocatorWarning)
assert "looks more like a filename" in str(warning.message)
@pytest.mark.parametrize(
"extension",
['markuphtml', 'markup.com', '', 'markup.js']
)
def test_resembles_filename_no_warning(self, extension):
# The 'looks more like a filename' warning is not issued if
# the markup looks like a bare string, a domain name, or a
# file that's not an HTML file.
with warnings.catch_warnings(record=True) as w:
soup = self.soup("markup" + extension)
assert [] == w
def test_url_warning_with_bytes_url(self):
url = b"http://www.crummybytes.com/"
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(url)
warning = self._assert_warning(
warning_list, MarkupResemblesLocatorWarning
)
assert "looks more like a URL" in str(warning.message)
assert url not in str(warning.message).encode("utf8")
def test_url_warning_with_unicode_url(self):
url = "http://www.crummyunicode.com/"
with warnings.catch_warnings(record=True) as warning_list:
# note - this url must differ from the bytes one otherwise
# python's warnings system swallows the second warning
soup = self.soup(url)
warning = self._assert_warning(
warning_list, MarkupResemblesLocatorWarning
)
assert "looks more like a URL" in str(warning.message)
assert url not in str(warning.message)
def test_url_warning_with_bytes_and_space(self):
# Here the markup contains something besides a URL, so no warning
# is issued.
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(b"http://www.crummybytes.com/ is great")
assert not any("looks more like a URL" in str(w.message)
for w in warning_list)
def test_url_warning_with_unicode_and_space(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup("http://www.crummyunicode.com/ is great")
assert not any("looks more like a URL" in str(w.message)
for w in warning_list)
class TestSelectiveParsing(SoupTest):
def test_parse_with_soupstrainer(self):
markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
strainer = SoupStrainer("b")
soup = self.soup(markup, parse_only=strainer)
assert soup.encode() == b"<b>Yes</b><b>Yes <c>Yes</c></b>"
class TestNewTag(SoupTest):
"""Test the BeautifulSoup.new_tag() method."""
def test_new_tag(self):
soup = self.soup("")
new_tag = soup.new_tag("foo", bar="baz", attrs={"name": "a name"})
assert isinstance(new_tag, Tag)
assert "foo" == new_tag.name
assert dict(bar="baz", name="a name") == new_tag.attrs
assert None == new_tag.parent
def test_tag_inherits_self_closing_rules_from_builder(self):
if LXML_PRESENT:
xml_soup = BeautifulSoup("", "lxml-xml")
xml_br = xml_soup.new_tag("br")
xml_p = xml_soup.new_tag("p")
# Both the <br> and <p> tag are empty-element, just because
# they have no contents.
assert b"<br/>" == xml_br.encode()
assert b"<p/>" == xml_p.encode()
html_soup = BeautifulSoup("", "html.parser")
html_br = html_soup.new_tag("br")
html_p = html_soup.new_tag("p")
# The HTML builder users HTML's rules about which tags are
# empty-element tags, and the new tags reflect these rules.
assert b"<br/>" == html_br.encode()
assert b"<p></p>" == html_p.encode()
class TestNewString(SoupTest):
"""Test the BeautifulSoup.new_string() method."""
def test_new_string_creates_navigablestring(self):
soup = self.soup("")
s = soup.new_string("foo")
assert "foo" == s
assert isinstance(s, NavigableString)
def test_new_string_can_create_navigablestring_subclass(self):
soup = self.soup("")
s = soup.new_string("foo", Comment)
assert "foo" == s
assert isinstance(s, Comment)
class TestPickle(SoupTest):
# Test our ability to pickle the BeautifulSoup object itself.
def test_normal_pickle(self):
soup = self.soup("<a>some markup</a>")
pickled = pickle.dumps(soup)
unpickled = pickle.loads(pickled)
assert "some markup" == unpickled.a.string
def test_pickle_with_no_builder(self):
# We had a bug that prevented pickling from working if
# the builder wasn't set.
soup = self.soup("some markup")
soup.builder = None
pickled = pickle.dumps(soup)
unpickled = pickle.loads(pickled)
assert "some markup" == unpickled.string
class TestEncodingConversion(SoupTest):
# Test Beautiful Soup's ability to decode and encode from various
# encodings.
def setup_method(self):
self.unicode_data = '<html><head><meta charset="utf-8"/></head><body><foo>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</foo></body></html>'
self.utf8_data = self.unicode_data.encode("utf-8")
# Just so you know what it looks like.
assert self.utf8_data == b'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>'
def test_ascii_in_unicode_out(self):
# ASCII input is converted to Unicode. The original_encoding
# attribute is set to 'utf-8', a superset of ASCII.
chardet = dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
# Disable chardet, which will realize that the ASCII is ASCII.
dammit.chardet_dammit = noop
ascii = b"<foo>a</foo>"
soup_from_ascii = self.soup(ascii)
unicode_output = soup_from_ascii.decode()
assert isinstance(unicode_output, str)
assert unicode_output == self.document_for(ascii.decode())
assert soup_from_ascii.original_encoding.lower() == "utf-8"
finally:
logging.disable(logging.NOTSET)
dammit.chardet_dammit = chardet
def test_unicode_in_unicode_out(self):
# Unicode input is left alone. The original_encoding attribute
# is not set.
soup_from_unicode = self.soup(self.unicode_data)
assert soup_from_unicode.decode() == self.unicode_data
assert soup_from_unicode.foo.string == 'Sacr\xe9 bleu!'
assert soup_from_unicode.original_encoding == None
def test_utf8_in_unicode_out(self):
# UTF-8 input is converted to Unicode. The original_encoding
# attribute is set.
soup_from_utf8 = self.soup(self.utf8_data)
assert soup_from_utf8.decode() == self.unicode_data
assert soup_from_utf8.foo.string == 'Sacr\xe9 bleu!'
def test_utf8_out(self):
# The internal data structures can be encoded as UTF-8.
soup_from_unicode = self.soup(self.unicode_data)
assert soup_from_unicode.encode('utf-8') == self.utf8_data
@skipIf(
PYTHON_3_PRE_3_2,
"Bad HTMLParser detected; skipping test of non-ASCII characters in attribute name.")
def test_attribute_name_containing_unicode_characters(self):
markup = '<div><a \N{SNOWMAN}="snowman"></a></div>'
assert self.soup(markup).div.encode("utf8") == markup.encode("utf8")

221
env/lib/python3.12/site-packages/bs4/tests/test_tag.py vendored
View File

@@ -1,221 +0,0 @@
import warnings
from bs4.element import (
Comment,
NavigableString,
)
from . import SoupTest
class TestTag(SoupTest):
"""Test various methods of Tag which aren't so complicated they
need their own classes.
"""
def test__should_pretty_print(self):
# Test the rules about when a tag should be pretty-printed.
tag = self.soup("").new_tag("a_tag")
# No list of whitespace-preserving tags -> pretty-print
tag._preserve_whitespace_tags = None
assert True == tag._should_pretty_print(0)
# List exists but tag is not on the list -> pretty-print
tag.preserve_whitespace_tags = ["some_other_tag"]
assert True == tag._should_pretty_print(1)
# Indent level is None -> don't pretty-print
assert False == tag._should_pretty_print(None)
# Tag is on the whitespace-preserving list -> don't pretty-print
tag.preserve_whitespace_tags = ["some_other_tag", "a_tag"]
assert False == tag._should_pretty_print(1)
def test_len(self):
"""The length of a Tag is its number of children."""
soup = self.soup("<top>1<b>2</b>3</top>")
# The BeautifulSoup object itself contains one element: the
# <top> tag.
assert len(soup.contents) == 1
assert len(soup) == 1
# The <top> tag contains three elements: the text node "1", the
# <b> tag, and the text node "3".
assert len(soup.top) == 3
assert len(soup.top.contents) == 3
def test_member_access_invokes_find(self):
"""Accessing a Python member .foo invokes find('foo')"""
soup = self.soup('<b><i></i></b>')
assert soup.b == soup.find('b')
assert soup.b.i == soup.find('b').find('i')
assert soup.a == None
def test_deprecated_member_access(self):
soup = self.soup('<b><i></i></b>')
with warnings.catch_warnings(record=True) as w:
tag = soup.bTag
assert soup.b == tag
assert '.bTag is deprecated, use .find("b") instead. If you really were looking for a tag called bTag, use .find("bTag")' == str(w[0].message)
def test_has_attr(self):
"""has_attr() checks for the presence of an attribute.
Please note note: has_attr() is different from
__in__. has_attr() checks the tag's attributes and __in__
checks the tag's chidlren.
"""
soup = self.soup("<foo attr='bar'>")
assert soup.foo.has_attr('attr')
assert not soup.foo.has_attr('attr2')
def test_attributes_come_out_in_alphabetical_order(self):
markup = '<b a="1" z="5" m="3" f="2" y="4"></b>'
self.assertSoupEquals(markup, '<b a="1" f="2" m="3" y="4" z="5"></b>')
def test_string(self):
# A Tag that contains only a text node makes that node
# available as .string.
soup = self.soup("<b>foo</b>")
assert soup.b.string == 'foo'
def test_empty_tag_has_no_string(self):
# A Tag with no children has no .stirng.
soup = self.soup("<b></b>")
assert soup.b.string == None
def test_tag_with_multiple_children_has_no_string(self):
# A Tag with no children has no .string.
soup = self.soup("<a>foo<b></b><b></b></b>")
assert soup.b.string == None
soup = self.soup("<a>foo<b></b>bar</b>")
assert soup.b.string == None
# Even if all the children are strings, due to trickery,
# it won't work--but this would be a good optimization.
soup = self.soup("<a>foo</b>")
soup.a.insert(1, "bar")
assert soup.a.string == None
def test_tag_with_recursive_string_has_string(self):
# A Tag with a single child which has a .string inherits that
# .string.
soup = self.soup("<a><b>foo</b></a>")
assert soup.a.string == "foo"
assert soup.string == "foo"
def test_lack_of_string(self):
"""Only a Tag containing a single text node has a .string."""
soup = self.soup("<b>f<i>e</i>o</b>")
assert soup.b.string is None
soup = self.soup("<b></b>")
assert soup.b.string is None
def test_all_text(self):
"""Tag.text and Tag.get_text(sep=u"") -> all child text, concatenated"""
soup = self.soup("<a>a<b>r</b> <r> t </r></a>")
assert soup.a.text == "ar t "
assert soup.a.get_text(strip=True) == "art"
assert soup.a.get_text(",") == "a,r, , t "
assert soup.a.get_text(",", strip=True) == "a,r,t"
def test_get_text_ignores_special_string_containers(self):
soup = self.soup("foo<!--IGNORE-->bar")
assert soup.get_text() == "foobar"
assert soup.get_text(types=(NavigableString, Comment)) == "fooIGNOREbar"
assert soup.get_text(types=None) == "fooIGNOREbar"
soup = self.soup("foo<style>CSS</style><script>Javascript</script>bar")
assert soup.get_text() == "foobar"
def test_all_strings_ignores_special_string_containers(self):
soup = self.soup("foo<!--IGNORE-->bar")
assert ['foo', 'bar'] == list(soup.strings)
soup = self.soup("foo<style>CSS</style><script>Javascript</script>bar")
assert ['foo', 'bar'] == list(soup.strings)
def test_string_methods_inside_special_string_container_tags(self):
# Strings inside tags like <script> are generally ignored by
# methods like get_text, because they're not what humans
# consider 'text'. But if you call get_text on the <script>
# tag itself, those strings _are_ considered to be 'text',
# because there's nothing else you might be looking for.
style = self.soup("<div>a<style>Some CSS</style></div>")
template = self.soup("<div>a<template><p>Templated <b>text</b>.</p><!--With a comment.--></template></div>")
script = self.soup("<div>a<script><!--a comment-->Some text</script></div>")
assert style.div.get_text() == "a"
assert list(style.div.strings) == ["a"]
assert style.div.style.get_text() == "Some CSS"
assert list(style.div.style.strings) == ['Some CSS']
# The comment is not picked up here. That's because it was
# parsed into a Comment object, which is not considered
# interesting by template.strings.
assert template.div.get_text() == "a"
assert list(template.div.strings) == ["a"]
assert template.div.template.get_text() == "Templated text."
assert list(template.div.template.strings) == ["Templated ", "text", "."]
# The comment is included here, because it didn't get parsed
# into a Comment object--it's part of the Script string.
assert script.div.get_text() == "a"
assert list(script.div.strings) == ["a"]
assert script.div.script.get_text() == "<!--a comment-->Some text"
assert list(script.div.script.strings) == ['<!--a comment-->Some text']
class TestMultiValuedAttributes(SoupTest):
"""Test the behavior of multi-valued attributes like 'class'.
The values of such attributes are always presented as lists.
"""
def test_single_value_becomes_list(self):
soup = self.soup("<a class='foo'>")
assert ["foo"] ==soup.a['class']
def test_multiple_values_becomes_list(self):
soup = self.soup("<a class='foo bar'>")
assert ["foo", "bar"] == soup.a['class']
def test_multiple_values_separated_by_weird_whitespace(self):
soup = self.soup("<a class='foo\tbar\nbaz'>")
assert ["foo", "bar", "baz"] ==soup.a['class']
def test_attributes_joined_into_string_on_output(self):
soup = self.soup("<a class='foo\tbar'>")
assert b'<a class="foo bar"></a>' == soup.a.encode()
def test_get_attribute_list(self):
soup = self.soup("<a id='abc def'>")
assert ['abc def'] == soup.a.get_attribute_list('id')
def test_accept_charset(self):
soup = self.soup('<form accept-charset="ISO-8859-1 UTF-8">')
assert ['ISO-8859-1', 'UTF-8'] == soup.form['accept-charset']
def test_cdata_attribute_applying_only_to_one_tag(self):
data = '<a accept-charset="ISO-8859-1 UTF-8"></a>'
soup = self.soup(data)
# We saw in another test that accept-charset is a cdata-list
# attribute for the <form> tag. But it's not a cdata-list
# attribute for any other tag.
assert 'ISO-8859-1 UTF-8' == soup.a['accept-charset']
def test_customization(self):
# It's possible to change which attributes of which tags
# are treated as multi-valued attributes.
#
# Here, 'id' is a multi-valued attribute and 'class' is not.
#
# TODO: This code is in the builder and should be tested there.
soup = self.soup(
'<a class="foo" id="bar">', multi_valued_attributes={ '*' : 'id' }
)
assert soup.a['class'] == 'foo'
assert soup.a['id'] == ['bar']

1290
env/lib/python3.12/site-packages/bs4/tests/test_tree.py vendored
View File

File diff suppressed because it is too large Load Diff

1
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/INSTALLER vendored
View File

@@ -1 +0,0 @@
pip

21
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/LICENSE vendored
View File

@@ -1,21 +0,0 @@
This package contains a modified version of ca-bundle.crt:
ca-bundle.crt -- Bundle of CA Root Certificates
Certificate data from Mozilla as of: Thu Nov 3 19:04:19 2011#
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:
http://mxr.mozilla.org/mozilla/source/security/nss/lib/ckfw/builtins/certdata.txt?raw=1#
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 $

81
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/METADATA vendored
View File

@@ -1,81 +0,0 @@
Metadata-Version: 2.1
Name: certifi
Version: 2022.6.15
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
Platform: UNKNOWN
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 :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Requires-Python: >=3.6
License-File: LICENSE
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!
1024-bit Root Certificates
~~~~~~~~~~~~~~~~~~~~~~~~~~
Browsers and certificate authorities have concluded that 1024-bit keys are
unacceptably weak for certificates, particularly root certificates. For this
reason, Mozilla has removed any weak (i.e. 1024-bit key) certificate from its
bundle, replacing it with an equivalent strong (i.e. 2048-bit or greater key)
certificate from the same CA. Because Mozilla removed these certificates from
its bundle, ``certifi`` removed them as well.
In previous versions, ``certifi`` provided the ``certifi.old_where()`` function
to intentionally re-add the 1024-bit roots back into your bundle. This was not
recommended in production and therefore was removed at the end of 2018.
.. _`Requests`: https://requests.readthedocs.io/en/master/
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.

15
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/RECORD vendored
View File

@@ -1,15 +0,0 @@
certifi-2022.6.15.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
certifi-2022.6.15.dist-info/LICENSE,sha256=vp2C82ES-Hp_HXTs1Ih-FGe7roh4qEAEoAEXseR1o-I,1049
certifi-2022.6.15.dist-info/METADATA,sha256=1sLjV7SjXkcGhJr631JUqCLCDnqgTyFoFe-tRLxakTE,2804
certifi-2022.6.15.dist-info/RECORD,,
certifi-2022.6.15.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
certifi-2022.6.15.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
certifi-2022.6.15.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
certifi/__init__.py,sha256=SuZ3iYmzdRyUv-PiaZkquUgXtWZ16ICUKgymlEBspx0,94
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=pZ_eiDoO-ddKudrQCWieABc9KFlbV0FsmLLugygMbkw,285222
certifi/core.py,sha256=G5LqCBr4o8bozzzlYBE8nsd_ziB6XcxJiuMV4llFeYY,2515
certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

0
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/REQUESTED vendored
View File

5
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/WHEEL vendored
View File

@@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.0)
Root-Is-Purelib: true
Tag: py3-none-any

1
env/lib/python3.12/site-packages/certifi-2022.6.15.dist-info/top_level.txt vendored
View File

@@ -1 +0,0 @@
certifi

4
env/lib/python3.12/site-packages/certifi/__init__.py vendored
View File

@@ -1,4 +0,0 @@
from .core import contents, where
__all__ = ["contents", "where"]
__version__ = "2022.06.15"

12
env/lib/python3.12/site-packages/certifi/__main__.py vendored
View File

@@ -1,12 +0,0 @@
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())

4685
env/lib/python3.12/site-packages/certifi/cacert.pem vendored
View File

File diff suppressed because it is too large Load Diff

68
env/lib/python3.12/site-packages/certifi/core.py vendored
View File

@@ -1,68 +0,0 @@
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem or its contents.
"""
import os
import types
from typing import Union
try:
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__())
return _CACERT_PATH
except ImportError:
Package = Union[types.ModuleType, str]
Resource = Union[str, "os.PathLike"]
# This fallback will work for Python versions prior to 3.7 that lack the
# importlib.resources module but relies on the existing `where` function
# so won't address issues with environments like PyOxidizer that don't set
# __file__ on modules.
def read_text(
package: Package,
resource: Resource,
encoding: str = 'utf-8',
errors: str = 'strict'
) -> str:
with open(where(), encoding=encoding) as data:
return data.read()
# If we don't have importlib.resources, then we will just do the old logic
# of assuming we're on the filesystem and munge the path directly.
def where() -> str:
f = os.path.dirname(__file__)
return os.path.join(f, "cacert.pem")
def contents() -> str:
return read_text("certifi", "cacert.pem", encoding="ascii")

0
env/lib/python3.12/site-packages/certifi/py.typed vendored
View File

1
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/INSTALLER vendored
View File

@@ -1 +0,0 @@
pip

21
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/LICENSE vendored
View File

@@ -1,21 +0,0 @@
MIT License
Copyright (c) 2019 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.

269
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/METADATA vendored
View File

@@ -1,269 +0,0 @@
Metadata-Version: 2.1
Name: charset-normalizer
Version: 2.1.0
Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
Home-page: https://github.com/ousret/charset_normalizer
Author: Ahmed TAHRI @Ousret
Author-email: ahmed.tahri@cloudnursery.dev
License: MIT
Project-URL: Bug Reports, https://github.com/Ousret/charset_normalizer/issues
Project-URL: Documentation, https://charset-normalizer.readthedocs.io/en/latest
Keywords: encoding,i18n,txt,text,charset,charset-detector,normalization,unicode,chardet
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
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: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Typing :: Typed
Requires-Python: >=3.6.0
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode_backport
Requires-Dist: unicodedata2 ; extra == 'unicode_backport'
<h1 align="center">Charset Detection, for Everyone 👋 <a href="https://twitter.com/intent/tweet?text=The%20Real%20First%20Universal%20Charset%20%26%20Language%20Detector&url=https://www.github.com/Ousret/charset_normalizer&hashtags=python,encoding,chardet,developers"><img src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"/></a></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://codecov.io/gh/Ousret/charset_normalizer">
<img src="https://codecov.io/gh/Ousret/charset_normalizer/branch/master/graph/badge.svg" />
</a>
<a href="https://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://pepy.tech/badge/charset-normalizer/month" />
</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.
<p align="center">
>>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
</p>
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` | ❌<br> | ✅<br> | ✅ <br> |
| `Universal**` | ❌ | ✅ | ❌ |
| `Reliable` **without** distinguishable standards | ❌ | ✅ | ✅ |
| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
| `Free & Open` | ✅ | ✅ | ✅ |
| `License` | LGPL-2.1 | MIT | MPL-1.1
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ❌ | ✅ | N/A |
| `Supported Encoding` | 30 | :tada: [93](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) | 40
<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"/>
*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br>
Did you got there because of the logs? See [https://charset-normalizer.readthedocs.io/en/latest/user/miscellaneous.html](https://charset-normalizer.readthedocs.io/en/latest/user/miscellaneous.html)
## ⭐ Your support
*Fork, test-it, star-it, submit your ideas! We do listen.*
## ⚡ Performance
This package offer better performance than its counterpart Chardet. Here are some numbers.
| Package | Accuracy | Mean per file (ms) | File per sec (est) |
| ------------- | :-------------: | :------------------: | :------------------: |
| [chardet](https://github.com/chardet/chardet) | 92 % | 200 ms | 5 file/sec |
| charset-normalizer | **98 %** | **39 ms** | 26 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
| ------------- | :-------------: | :------------------: | :------------------: |
| [chardet](https://github.com/chardet/chardet) | 1200 ms | 287 ms | 23 ms |
| charset-normalizer | 400 ms | 200 ms | 15 ms |
Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
> 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.
[cchardet](https://github.com/PyYoshi/cChardet) is a non-native (cpp binding) and unmaintained faster alternative with
a better accuracy than chardet but lower than this package. If speed is the most important factor, you should try it.
## ✨ Installation
Using PyPi for latest stable
```sh
pip install charset-normalizer -U
```
If you want a more up-to-date `unicodedata` than the one available in your Python setup.
```sh
pip install charset-normalizer[unicode_backport] -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
```
:tada: 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()))
```
*Normalize any text file*
```python
from charset_normalizer import normalize
try:
normalize('./my_subtitle.srt') # should write to disk my_subtitle-***.srt
except IOError as e:
print('Sadly, we are unable to perform charset normalization.', str(e))
```
*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 chaos, 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 chaos/mess and coherence according to **YOU ?**
*Chaos :* 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.
I know that my interpretation of what is chaotic is very subjective, 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.
## 👤 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 © 2019 [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/)

34
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/RECORD vendored
View File

@@ -1,34 +0,0 @@
../../../bin/normalizer,sha256=QaLD0qrTVMJrk7hNvcpMCe-NZ_ryGSnk6Uz4Za0tZh4,317
charset_normalizer-2.1.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-2.1.0.dist-info/LICENSE,sha256=6zGgxaT7Cbik4yBV0lweX5w1iidS_vPNcgIT0cz-4kE,1070
charset_normalizer-2.1.0.dist-info/METADATA,sha256=PqR4yIS_Cr-NWPWOpEKrGzb8HltKDlD8-vXz-cMTaog,11718
charset_normalizer-2.1.0.dist-info/RECORD,,
charset_normalizer-2.1.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer-2.1.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
charset_normalizer-2.1.0.dist-info/entry_points.txt,sha256=5AJq_EPtGGUwJPgQLnBZfbVr-FYCIwT0xP7dIEZO3NI,77
charset_normalizer-2.1.0.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
charset_normalizer/__init__.py,sha256=x2A2OW29MBcqdxsvy6t1wzkUlH3ma0guxL6ZCfS8J94,1790
charset_normalizer/__pycache__/__init__.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=LwJ32ZBLv79ehfWN8nss7F--QkssNQIOQyjD1_t9a70,18960
charset_normalizer/assets/__init__.py,sha256=ZXzdy-3PHtCldBTF-3tDI9qERLKp9AN-yt-sB6fIMFs,15222
charset_normalizer/assets/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/cd.py,sha256=gUwdMn2Du-u31I4VlmGK2C5x1z_V6vhqFfEIp9w1uE0,10780
charset_normalizer/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/cli/__pycache__/normalizer.cpython-312.pyc,,
charset_normalizer/cli/normalizer.py,sha256=NmT5GSdXx0UJFxZaSp_DjPudcwc7JTB-MY3rfemgTpY,9501
charset_normalizer/constant.py,sha256=NgU-pY8JH2a9lkVT8oKwAFmIUYNKOuSBwZgF9MrlNCM,19157
charset_normalizer/legacy.py,sha256=XKeZOts_HdYQU_Jb3C9ZfOjY2CiUL132k9_nXer8gig,3384
charset_normalizer/md.py,sha256=pZP8IVpSC82D8INA9Tf_y0ijJSRI-UIncZvLdfTWEd4,17642
charset_normalizer/models.py,sha256=WkEr3Zr4m8VBxp3_2hMXhFFvRWDqoLDXKRDtAqBKMQg,13087
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=Z-VtLSynph2jMGpzZ5rgx21RM_4ALVpT63B5lQ7xreY,11726
charset_normalizer/version.py,sha256=aHhGbxCxD3_nEElAoNbMRqmGpyqLWCYkGvbAEHl34rM,79

0
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/REQUESTED vendored
View File

5
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/WHEEL vendored
View File

@@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.1)
Root-Is-Purelib: true
Tag: py3-none-any

3
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/entry_points.txt vendored
View File

@@ -1,3 +0,0 @@
[console_scripts]
normalizer = charset_normalizer.cli.normalizer:cli_detect

1
env/lib/python3.12/site-packages/charset_normalizer-2.1.0.dist-info/top_level.txt vendored
View File

@@ -1 +0,0 @@
charset_normalizer

56
env/lib/python3.12/site-packages/charset_normalizer/__init__.py vendored
View File

@@ -1,56 +0,0 @@
# -*- coding: utf_8 -*-
"""
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.
"""
import logging
from .api import from_bytes, from_fp, from_path, normalize
from .legacy import (
CharsetDetector,
CharsetDoctor,
CharsetNormalizerMatch,
CharsetNormalizerMatches,
detect,
)
from .models import CharsetMatch, CharsetMatches
from .utils import set_logging_handler
from .version import VERSION, __version__
__all__ = (
"from_fp",
"from_path",
"from_bytes",
"normalize",
"detect",
"CharsetMatch",
"CharsetMatches",
"CharsetNormalizerMatch",
"CharsetNormalizerMatches",
"CharsetDetector",
"CharsetDoctor",
"__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())

578
env/lib/python3.12/site-packages/charset_normalizer/api.py vendored
View File

@@ -1,578 +0,0 @@
import logging
from os import PathLike
from os.path import basename, splitext
from typing import BinaryIO, List, Optional, Set
from .cd import (
coherence_ratio,
encoding_languages,
mb_encoding_languages,
merge_coherence_ratios,
)
from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE
from .md import mess_ratio
from .models import CharsetMatch, CharsetMatches
from .utils import (
any_specified_encoding,
cut_sequence_chunks,
iana_name,
identify_sig_or_bom,
is_cp_similar,
is_multi_byte_encoding,
should_strip_sig_or_bom,
)
# Will most likely be controversial
# logging.addLevelName(TRACE, "TRACE")
logger = logging.getLogger("charset_normalizer")
explain_handler = logging.StreamHandler()
explain_handler.setFormatter(
logging.Formatter("%(asctime)s | %(levelname)s | %(message)s")
)
def from_bytes(
sequences: bytes,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.2,
cp_isolation: List[str] = None,
cp_exclusion: List[str] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
) -> CharsetMatches:
"""
Given a raw bytes sequence, return the best possibles charset usable to render str objects.
If there is no results, it is a strong indicator that the source is binary/not text.
By default, the process will extract 5 blocs of 512o each to assess the mess and coherence of a given sequence.
And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
but never take it for granted. Can improve the performance.
You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
purpose.
This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
Custom logging format and handler can be set manually.
"""
if not isinstance(sequences, (bytearray, bytes)):
raise TypeError(
"Expected object of type bytes or bytearray, got: {0}".format(
type(sequences)
)
)
if explain:
previous_logger_level: int = logger.level
logger.addHandler(explain_handler)
logger.setLevel(TRACE)
length: int = len(sequences)
if length == 0:
logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.")
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level or logging.WARNING)
return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
if cp_isolation is not None:
logger.log(
TRACE,
"cp_isolation is set. use this flag for debugging purpose. "
"limited list of encoding allowed : %s.",
", ".join(cp_isolation),
)
cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
else:
cp_isolation = []
if cp_exclusion is not None:
logger.log(
TRACE,
"cp_exclusion is set. use this flag for debugging purpose. "
"limited list of encoding excluded : %s.",
", ".join(cp_exclusion),
)
cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
else:
cp_exclusion = []
if length <= (chunk_size * steps):
logger.log(
TRACE,
"override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
steps,
chunk_size,
length,
)
steps = 1
chunk_size = length
if steps > 1 and length / steps < chunk_size:
chunk_size = int(length / steps)
is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE
is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE
if is_too_small_sequence:
logger.log(
TRACE,
"Trying to detect encoding from a tiny portion of ({}) byte(s).".format(
length
),
)
elif is_too_large_sequence:
logger.log(
TRACE,
"Using lazy str decoding because the payload is quite large, ({}) byte(s).".format(
length
),
)
prioritized_encodings: List[str] = []
specified_encoding: Optional[str] = (
any_specified_encoding(sequences) if preemptive_behaviour else None
)
if specified_encoding is not None:
prioritized_encodings.append(specified_encoding)
logger.log(
TRACE,
"Detected declarative mark in sequence. Priority +1 given for %s.",
specified_encoding,
)
tested: Set[str] = set()
tested_but_hard_failure: List[str] = []
tested_but_soft_failure: List[str] = []
fallback_ascii: Optional[CharsetMatch] = None
fallback_u8: Optional[CharsetMatch] = None
fallback_specified: Optional[CharsetMatch] = None
results: CharsetMatches = CharsetMatches()
sig_encoding, sig_payload = identify_sig_or_bom(sequences)
if sig_encoding is not None:
prioritized_encodings.append(sig_encoding)
logger.log(
TRACE,
"Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.",
len(sig_payload),
sig_encoding,
)
prioritized_encodings.append("ascii")
if "utf_8" not in prioritized_encodings:
prioritized_encodings.append("utf_8")
for encoding_iana in prioritized_encodings + IANA_SUPPORTED:
if cp_isolation and encoding_iana not in cp_isolation:
continue
if cp_exclusion and encoding_iana in cp_exclusion:
continue
if encoding_iana in tested:
continue
tested.add(encoding_iana)
decoded_payload: Optional[str] = None
bom_or_sig_available: bool = sig_encoding == encoding_iana
strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom(
encoding_iana
)
if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s wont be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
encoding_iana,
)
continue
try:
is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana)
except (ModuleNotFoundError, ImportError):
logger.log(
TRACE,
"Encoding %s does not provide an IncrementalDecoder",
encoding_iana,
)
continue
try:
if is_too_large_sequence and is_multi_byte_decoder is False:
str(
sequences[: int(50e4)]
if strip_sig_or_bom is False
else sequences[len(sig_payload) : int(50e4)],
encoding=encoding_iana,
)
else:
decoded_payload = str(
sequences
if strip_sig_or_bom is False
else sequences[len(sig_payload) :],
encoding=encoding_iana,
)
except (UnicodeDecodeError, LookupError) as e:
if not isinstance(e, LookupError):
logger.log(
TRACE,
"Code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
similar_soft_failure_test: bool = False
for encoding_soft_failed in tested_but_soft_failure:
if is_cp_similar(encoding_iana, encoding_soft_failed):
similar_soft_failure_test = True
break
if similar_soft_failure_test:
logger.log(
TRACE,
"%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
encoding_iana,
encoding_soft_failed,
)
continue
r_ = range(
0 if not bom_or_sig_available else len(sig_payload),
length,
int(length / steps),
)
multi_byte_bonus: bool = (
is_multi_byte_decoder
and decoded_payload is not None
and len(decoded_payload) < length
)
if multi_byte_bonus:
logger.log(
TRACE,
"Code page %s is a multi byte encoding table and it appear that at least one character "
"was encoded using n-bytes.",
encoding_iana,
)
max_chunk_gave_up: int = int(len(r_) / 4)
max_chunk_gave_up = max(max_chunk_gave_up, 2)
early_stop_count: int = 0
lazy_str_hard_failure = False
md_chunks: List[str] = []
md_ratios = []
try:
for chunk in cut_sequence_chunks(
sequences,
encoding_iana,
r_,
chunk_size,
bom_or_sig_available,
strip_sig_or_bom,
sig_payload,
is_multi_byte_decoder,
decoded_payload,
):
md_chunks.append(chunk)
md_ratios.append(mess_ratio(chunk, threshold))
if md_ratios[-1] >= threshold:
early_stop_count += 1
if (early_stop_count >= max_chunk_gave_up) or (
bom_or_sig_available and strip_sig_or_bom is False
):
break
except UnicodeDecodeError as e: # Lazy str loading may have missed something there
logger.log(
TRACE,
"LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
early_stop_count = max_chunk_gave_up
lazy_str_hard_failure = True
# We might want to check the sequence again with the whole content
# Only if initial MD tests passes
if (
not lazy_str_hard_failure
and is_too_large_sequence
and not is_multi_byte_decoder
):
try:
sequences[int(50e3) :].decode(encoding_iana, errors="strict")
except UnicodeDecodeError as e:
logger.log(
TRACE,
"LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
tested_but_soft_failure.append(encoding_iana)
logger.log(
TRACE,
"%s was excluded because of initial chaos probing. Gave up %i time(s). "
"Computed mean chaos is %f %%.",
encoding_iana,
early_stop_count,
round(mean_mess_ratio * 100, ndigits=3),
)
# Preparing those fallbacks in case we got nothing.
if (
encoding_iana in ["ascii", "utf_8", specified_encoding]
and not lazy_str_hard_failure
):
fallback_entry = CharsetMatch(
sequences, encoding_iana, threshold, False, [], decoded_payload
)
if encoding_iana == specified_encoding:
fallback_specified = fallback_entry
elif encoding_iana == "ascii":
fallback_ascii = fallback_entry
else:
fallback_u8 = fallback_entry
continue
logger.log(
TRACE,
"%s passed initial chaos probing. Mean measured chaos is %f %%",
encoding_iana,
round(mean_mess_ratio * 100, ndigits=3),
)
if not is_multi_byte_decoder:
target_languages: List[str] = encoding_languages(encoding_iana)
else:
target_languages = mb_encoding_languages(encoding_iana)
if target_languages:
logger.log(
TRACE,
"{} should target any language(s) of {}".format(
encoding_iana, str(target_languages)
),
)
cd_ratios = []
# We shall skip the CD when its about ASCII
# Most of the time its not relevant to run "language-detection" on it.
if encoding_iana != "ascii":
for chunk in md_chunks:
chunk_languages = coherence_ratio(
chunk, 0.1, ",".join(target_languages) if target_languages else None
)
cd_ratios.append(chunk_languages)
cd_ratios_merged = merge_coherence_ratios(cd_ratios)
if cd_ratios_merged:
logger.log(
TRACE,
"We detected language {} using {}".format(
cd_ratios_merged, encoding_iana
),
)
results.append(
CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
decoded_payload,
)
)
if (
encoding_iana in [specified_encoding, "ascii", "utf_8"]
and mean_mess_ratio < 0.1
):
logger.debug(
"Encoding detection: %s is most likely the one.", encoding_iana
)
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
if encoding_iana == sig_encoding:
logger.debug(
"Encoding detection: %s is most likely the one as we detected a BOM or SIG within "
"the beginning of the sequence.",
encoding_iana,
)
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
if len(results) == 0:
if fallback_u8 or fallback_ascii or fallback_specified:
logger.log(
TRACE,
"Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.",
)
if fallback_specified:
logger.debug(
"Encoding detection: %s will be used as a fallback match",
fallback_specified.encoding,
)
results.append(fallback_specified)
elif (
(fallback_u8 and fallback_ascii is None)
or (
fallback_u8
and fallback_ascii
and fallback_u8.fingerprint != fallback_ascii.fingerprint
)
or (fallback_u8 is not None)
):
logger.debug("Encoding detection: utf_8 will be used as a fallback match")
results.append(fallback_u8)
elif fallback_ascii:
logger.debug("Encoding detection: ascii will be used as a fallback match")
results.append(fallback_ascii)
if results:
logger.debug(
"Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.",
results.best().encoding, # type: ignore
len(results) - 1,
)
else:
logger.debug("Encoding detection: Unable to determine any suitable charset.")
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return results
def from_fp(
fp: BinaryIO,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: List[str] = None,
cp_exclusion: List[str] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but using a file pointer that is already ready.
Will not close the file pointer.
"""
return from_bytes(
fp.read(),
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
)
def from_path(
path: PathLike,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: List[str] = None,
cp_exclusion: List[str] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
Can raise IOError.
"""
with open(path, "rb") as fp:
return from_fp(
fp,
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
)
def normalize(
path: PathLike,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: List[str] = None,
cp_exclusion: List[str] = None,
preemptive_behaviour: bool = True,
) -> CharsetMatch:
"""
Take a (text-based) file path and try to create another file next to it, this time using UTF-8.
"""
results = from_path(
path,
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
)
filename = basename(path)
target_extensions = list(splitext(filename))
if len(results) == 0:
raise IOError(
'Unable to normalize "{}", no encoding charset seems to fit.'.format(
filename
)
)
result = results.best()
target_extensions[0] += "-" + result.encoding # type: ignore
with open(
"{}".format(str(path).replace(filename, "".join(target_extensions))), "wb"
) as fp:
fp.write(result.output()) # type: ignore
return result # type: ignore

1122
env/lib/python3.12/site-packages/charset_normalizer/assets/__init__.py vendored
View File

File diff suppressed because it is too large Load Diff

337
env/lib/python3.12/site-packages/charset_normalizer/cd.py vendored
View File

@@ -1,337 +0,0 @@
import importlib
from codecs import IncrementalDecoder
from collections import Counter
from functools import lru_cache
from typing import Dict, List, Optional, Tuple
from .assets import FREQUENCIES
from .constant import KO_NAMES, LANGUAGE_SUPPORTED_COUNT, TOO_SMALL_SEQUENCE, ZH_NAMES
from .md import is_suspiciously_successive_range
from .models import CoherenceMatches
from .utils import (
is_accentuated,
is_latin,
is_multi_byte_encoding,
is_unicode_range_secondary,
unicode_range,
)
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 IOError("Function not supported on multi-byte code page")
decoder = importlib.import_module("encodings.{}".format(iana_name)).IncrementalDecoder # type: ignore
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:
character_range: Optional[str] = unicode_range(chunk)
if character_range is None:
continue
if is_unicode_range_secondary(character_range) is False:
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:
if unicode_range(character) == 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.
"""
unicode_ranges: List[str] = encoding_unicode_range(iana_name)
primary_range: Optional[str] = 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", "Classical 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]:
if not target_have_accents and is_accentuated(character):
target_have_accents = True
if target_pure_latin and is_latin(character) is False:
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]] = []
source_have_accents = any(is_accentuated(character) for character in characters)
for language, language_characters in FREQUENCIES.items():
target_have_accents, target_pure_latin = get_target_features(language)
if ignore_non_latin and target_pure_latin is False:
continue
if target_have_accents is False and source_have_accents:
continue
character_count: int = len(language_characters)
character_match_count: int = len(
[c for c in language_characters if c in characters]
)
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("{} not available".format(language))
character_approved_count: int = 0
FREQUENCIES_language_set = set(FREQUENCIES[language])
for character in ordered_characters:
if character not in FREQUENCIES_language_set:
continue
characters_before_source: List[str] = FREQUENCIES[language][
0 : FREQUENCIES[language].index(character)
]
characters_after_source: List[str] = FREQUENCIES[language][
FREQUENCIES[language].index(character) :
]
characters_before: List[str] = ordered_characters[
0 : ordered_characters.index(character)
]
characters_after: List[str] = ordered_characters[
ordered_characters.index(character) :
]
before_match_count: int = len(
set(characters_before) & set(characters_before_source)
)
after_match_count: int = len(
set(characters_after) & set(characters_after_source)
)
if len(characters_before_source) == 0 and before_match_count <= 4:
character_approved_count += 1
continue
if len(characters_after_source) == 0 and after_match_count <= 4:
character_approved_count += 1
continue
if (
before_match_count / len(characters_before_source) >= 0.4
or after_match_count / len(characters_after_source) >= 0.4
):
character_approved_count += 1
continue
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, str] = {}
for character in decoded_sequence:
if character.isalpha() is False:
continue
character_range: Optional[str] = unicode_range(character)
if character_range is None:
continue
layer_target_range: Optional[str] = None
for discovered_range in layers:
if (
is_suspiciously_successive_range(discovered_range, character_range)
is False
):
layer_target_range = discovered_range
break
if layer_target_range is None:
layer_target_range = character_range
if layer_target_range not in layers:
layers[layer_target_range] = character.lower()
continue
layers[layer_target_range] += character.lower()
return list(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)
@lru_cache(maxsize=2048)
def coherence_ratio(
decoded_sequence: str, threshold: float = 0.1, lg_inclusion: Optional[str] = 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):
sequence_frequencies: Counter = Counter(layer)
most_common = sequence_frequencies.most_common()
character_count: int = sum(o for c, o in most_common)
if character_count <= TOO_SMALL_SEQUENCE:
continue
popular_character_ordered: List[str] = [c for c, o in most_common]
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(results, key=lambda x: x[1], reverse=True)

0
env/lib/python3.12/site-packages/charset_normalizer/cli/__init__.py vendored
View File

295
env/lib/python3.12/site-packages/charset_normalizer/cli/normalizer.py vendored
View File

@@ -1,295 +0,0 @@
import argparse
import sys
from json import dumps
from os.path import abspath
from platform import python_version
from typing import List
try:
from unicodedata2 import unidata_version
except ImportError:
from unicodedata import unidata_version
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:
"""Ask a yes/no question via input() and return their answer.
"question" is a string that is presented to the user.
"default" is the presumed answer if the user just hits <Enter>.
It must be "yes" (the default), "no" or None (meaning
an answer is required of the user).
The "answer" return value is True for "yes" or False for "no".
Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input
"""
valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False}
if default is None:
prompt = " [y/n] "
elif default == "yes":
prompt = " [Y/n] "
elif default == "no":
prompt = " [y/N] "
else:
raise ValueError("invalid default answer: '%s'" % default)
while True:
sys.stdout.write(question + prompt)
choice = input().lower()
if default is not None and choice == "":
return valid[default]
elif choice in valid:
return valid[choice]
else:
sys.stdout.write("Please respond with 'yes' or 'no' " "(or 'y' or 'n').\n")
def cli_detect(argv: List[str] = 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=argparse.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(
"-t",
"--threshold",
action="store",
default=0.2,
type=float,
dest="threshold",
help="Define a custom maximum amount of chaos allowed in decoded content. 0. <= chaos <= 1.",
)
parser.add_argument(
"--version",
action="version",
version="Charset-Normalizer {} - Python {} - Unicode {}".format(
__version__, python_version(), unidata_version
),
help="Show version information and exit.",
)
args = parser.parse_args(argv)
if args.replace is True and args.normalize is False:
print("Use --replace in addition of --normalize only.", file=sys.stderr)
return 1
if args.force is True and args.replace is False:
print("Use --force in addition of --replace only.", file=sys.stderr)
return 1
if args.threshold < 0.0 or args.threshold > 1.0:
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)
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:
x_.append(
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,
)
)
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
o_: List[str] = my_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:
x_[0].unicode_path = abspath("./{}".format(".".join(o_)))
with open(x_[0].unicode_path, "w", encoding="utf-8") as fp:
fp.write(str(best_guess))
except IOError as e:
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:
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__":
cli_detect()

497
env/lib/python3.12/site-packages/charset_normalizer/constant.py vendored
View File

@@ -1,497 +0,0 @@
from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE
from encodings.aliases import aliases
from re import IGNORECASE, compile as re_compile
from typing import Dict, List, Set, Union
from .assets import FREQUENCIES
# Contain for each eligible encoding a list of/item bytes SIG/BOM
ENCODING_MARKS: Dict[str, Union[bytes, List[bytes]]] = {
"utf_8": BOM_UTF8,
"utf_7": [
b"\x2b\x2f\x76\x38",
b"\x2b\x2f\x76\x39",
b"\x2b\x2f\x76\x2b",
b"\x2b\x2f\x76\x2f",
b"\x2b\x2f\x76\x38\x2d",
],
"gb18030": b"\x84\x31\x95\x33",
"utf_32": [BOM_UTF32_BE, BOM_UTF32_LE],
"utf_16": [BOM_UTF16_BE, BOM_UTF16_LE],
}
TOO_SMALL_SEQUENCE: int = 32
TOO_BIG_SEQUENCE: int = int(10e6)
UTF8_MAXIMAL_ALLOCATION: int = 1112064
UNICODE_RANGES_COMBINED: Dict[str, range] = {
"Control character": range(31 + 1),
"Basic Latin": range(32, 127 + 1),
"Latin-1 Supplement": range(128, 255 + 1),
"Latin Extended-A": range(256, 383 + 1),
"Latin Extended-B": range(384, 591 + 1),
"IPA Extensions": range(592, 687 + 1),
"Spacing Modifier Letters": range(688, 767 + 1),
"Combining Diacritical Marks": range(768, 879 + 1),
"Greek and Coptic": range(880, 1023 + 1),
"Cyrillic": range(1024, 1279 + 1),
"Cyrillic Supplement": range(1280, 1327 + 1),
"Armenian": range(1328, 1423 + 1),
"Hebrew": range(1424, 1535 + 1),
"Arabic": range(1536, 1791 + 1),
"Syriac": range(1792, 1871 + 1),
"Arabic Supplement": range(1872, 1919 + 1),
"Thaana": range(1920, 1983 + 1),
"NKo": range(1984, 2047 + 1),
"Samaritan": range(2048, 2111 + 1),
"Mandaic": range(2112, 2143 + 1),
"Syriac Supplement": range(2144, 2159 + 1),
"Arabic Extended-A": range(2208, 2303 + 1),
"Devanagari": range(2304, 2431 + 1),
"Bengali": range(2432, 2559 + 1),
"Gurmukhi": range(2560, 2687 + 1),
"Gujarati": range(2688, 2815 + 1),
"Oriya": range(2816, 2943 + 1),
"Tamil": range(2944, 3071 + 1),
"Telugu": range(3072, 3199 + 1),
"Kannada": range(3200, 3327 + 1),
"Malayalam": range(3328, 3455 + 1),
"Sinhala": range(3456, 3583 + 1),
"Thai": range(3584, 3711 + 1),
"Lao": range(3712, 3839 + 1),
"Tibetan": range(3840, 4095 + 1),
"Myanmar": range(4096, 4255 + 1),
"Georgian": range(4256, 4351 + 1),
"Hangul Jamo": range(4352, 4607 + 1),
"Ethiopic": range(4608, 4991 + 1),
"Ethiopic Supplement": range(4992, 5023 + 1),
"Cherokee": range(5024, 5119 + 1),
"Unified Canadian Aboriginal Syllabics": range(5120, 5759 + 1),
"Ogham": range(5760, 5791 + 1),
"Runic": range(5792, 5887 + 1),
"Tagalog": range(5888, 5919 + 1),
"Hanunoo": range(5920, 5951 + 1),
"Buhid": range(5952, 5983 + 1),
"Tagbanwa": range(5984, 6015 + 1),
"Khmer": range(6016, 6143 + 1),
"Mongolian": range(6144, 6319 + 1),
"Unified Canadian Aboriginal Syllabics Extended": range(6320, 6399 + 1),
"Limbu": range(6400, 6479 + 1),
"Tai Le": range(6480, 6527 + 1),
"New Tai Lue": range(6528, 6623 + 1),
"Khmer Symbols": range(6624, 6655 + 1),
"Buginese": range(6656, 6687 + 1),
"Tai Tham": range(6688, 6831 + 1),
"Combining Diacritical Marks Extended": range(6832, 6911 + 1),
"Balinese": range(6912, 7039 + 1),
"Sundanese": range(7040, 7103 + 1),
"Batak": range(7104, 7167 + 1),
"Lepcha": range(7168, 7247 + 1),
"Ol Chiki": range(7248, 7295 + 1),
"Cyrillic Extended C": range(7296, 7311 + 1),
"Sundanese Supplement": range(7360, 7375 + 1),
"Vedic Extensions": range(7376, 7423 + 1),
"Phonetic Extensions": range(7424, 7551 + 1),
"Phonetic Extensions Supplement": range(7552, 7615 + 1),
"Combining Diacritical Marks Supplement": range(7616, 7679 + 1),
"Latin Extended Additional": range(7680, 7935 + 1),
"Greek Extended": range(7936, 8191 + 1),
"General Punctuation": range(8192, 8303 + 1),
"Superscripts and Subscripts": range(8304, 8351 + 1),
"Currency Symbols": range(8352, 8399 + 1),
"Combining Diacritical Marks for Symbols": range(8400, 8447 + 1),
"Letterlike Symbols": range(8448, 8527 + 1),
"Number Forms": range(8528, 8591 + 1),
"Arrows": range(8592, 8703 + 1),
"Mathematical Operators": range(8704, 8959 + 1),
"Miscellaneous Technical": range(8960, 9215 + 1),
"Control Pictures": range(9216, 9279 + 1),
"Optical Character Recognition": range(9280, 9311 + 1),
"Enclosed Alphanumerics": range(9312, 9471 + 1),
"Box Drawing": range(9472, 9599 + 1),
"Block Elements": range(9600, 9631 + 1),
"Geometric Shapes": range(9632, 9727 + 1),
"Miscellaneous Symbols": range(9728, 9983 + 1),
"Dingbats": range(9984, 10175 + 1),
"Miscellaneous Mathematical Symbols-A": range(10176, 10223 + 1),
"Supplemental Arrows-A": range(10224, 10239 + 1),
"Braille Patterns": range(10240, 10495 + 1),
"Supplemental Arrows-B": range(10496, 10623 + 1),
"Miscellaneous Mathematical Symbols-B": range(10624, 10751 + 1),
"Supplemental Mathematical Operators": range(10752, 11007 + 1),
"Miscellaneous Symbols and Arrows": range(11008, 11263 + 1),
"Glagolitic": range(11264, 11359 + 1),
"Latin Extended-C": range(11360, 11391 + 1),
"Coptic": range(11392, 11519 + 1),
"Georgian Supplement": range(11520, 11567 + 1),
"Tifinagh": range(11568, 11647 + 1),
"Ethiopic Extended": range(11648, 11743 + 1),
"Cyrillic Extended-A": range(11744, 11775 + 1),
"Supplemental Punctuation": range(11776, 11903 + 1),
"CJK Radicals Supplement": range(11904, 12031 + 1),
"Kangxi Radicals": range(12032, 12255 + 1),
"Ideographic Description Characters": range(12272, 12287 + 1),
"CJK Symbols and Punctuation": range(12288, 12351 + 1),
"Hiragana": range(12352, 12447 + 1),
"Katakana": range(12448, 12543 + 1),
"Bopomofo": range(12544, 12591 + 1),
"Hangul Compatibility Jamo": range(12592, 12687 + 1),
"Kanbun": range(12688, 12703 + 1),
"Bopomofo Extended": range(12704, 12735 + 1),
"CJK Strokes": range(12736, 12783 + 1),
"Katakana Phonetic Extensions": range(12784, 12799 + 1),
"Enclosed CJK Letters and Months": range(12800, 13055 + 1),
"CJK Compatibility": range(13056, 13311 + 1),
"CJK Unified Ideographs Extension A": range(13312, 19903 + 1),
"Yijing Hexagram Symbols": range(19904, 19967 + 1),
"CJK Unified Ideographs": range(19968, 40959 + 1),
"Yi Syllables": range(40960, 42127 + 1),
"Yi Radicals": range(42128, 42191 + 1),
"Lisu": range(42192, 42239 + 1),
"Vai": range(42240, 42559 + 1),
"Cyrillic Extended-B": range(42560, 42655 + 1),
"Bamum": range(42656, 42751 + 1),
"Modifier Tone Letters": range(42752, 42783 + 1),
"Latin Extended-D": range(42784, 43007 + 1),
"Syloti Nagri": range(43008, 43055 + 1),
"Common Indic Number Forms": range(43056, 43071 + 1),
"Phags-pa": range(43072, 43135 + 1),
"Saurashtra": range(43136, 43231 + 1),
"Devanagari Extended": range(43232, 43263 + 1),
"Kayah Li": range(43264, 43311 + 1),
"Rejang": range(43312, 43359 + 1),
"Hangul Jamo Extended-A": range(43360, 43391 + 1),
"Javanese": range(43392, 43487 + 1),
"Myanmar Extended-B": range(43488, 43519 + 1),
"Cham": range(43520, 43615 + 1),
"Myanmar Extended-A": range(43616, 43647 + 1),
"Tai Viet": range(43648, 43743 + 1),
"Meetei Mayek Extensions": range(43744, 43775 + 1),
"Ethiopic Extended-A": range(43776, 43823 + 1),
"Latin Extended-E": range(43824, 43887 + 1),
"Cherokee Supplement": range(43888, 43967 + 1),
"Meetei Mayek": range(43968, 44031 + 1),
"Hangul Syllables": range(44032, 55215 + 1),
"Hangul Jamo Extended-B": range(55216, 55295 + 1),
"High Surrogates": range(55296, 56191 + 1),
"High Private Use Surrogates": range(56192, 56319 + 1),
"Low Surrogates": range(56320, 57343 + 1),
"Private Use Area": range(57344, 63743 + 1),
"CJK Compatibility Ideographs": range(63744, 64255 + 1),
"Alphabetic Presentation Forms": range(64256, 64335 + 1),
"Arabic Presentation Forms-A": range(64336, 65023 + 1),
"Variation Selectors": range(65024, 65039 + 1),
"Vertical Forms": range(65040, 65055 + 1),
"Combining Half Marks": range(65056, 65071 + 1),
"CJK Compatibility Forms": range(65072, 65103 + 1),
"Small Form Variants": range(65104, 65135 + 1),
"Arabic Presentation Forms-B": range(65136, 65279 + 1),
"Halfwidth and Fullwidth Forms": range(65280, 65519 + 1),
"Specials": range(65520, 65535 + 1),
"Linear B Syllabary": range(65536, 65663 + 1),
"Linear B Ideograms": range(65664, 65791 + 1),
"Aegean Numbers": range(65792, 65855 + 1),
"Ancient Greek Numbers": range(65856, 65935 + 1),
"Ancient Symbols": range(65936, 65999 + 1),
"Phaistos Disc": range(66000, 66047 + 1),
"Lycian": range(66176, 66207 + 1),
"Carian": range(66208, 66271 + 1),
"Coptic Epact Numbers": range(66272, 66303 + 1),
"Old Italic": range(66304, 66351 + 1),
"Gothic": range(66352, 66383 + 1),
"Old Permic": range(66384, 66431 + 1),
"Ugaritic": range(66432, 66463 + 1),
"Old Persian": range(66464, 66527 + 1),
"Deseret": range(66560, 66639 + 1),
"Shavian": range(66640, 66687 + 1),
"Osmanya": range(66688, 66735 + 1),
"Osage": range(66736, 66815 + 1),
"Elbasan": range(66816, 66863 + 1),
"Caucasian Albanian": range(66864, 66927 + 1),
"Linear A": range(67072, 67455 + 1),
"Cypriot Syllabary": range(67584, 67647 + 1),
"Imperial Aramaic": range(67648, 67679 + 1),
"Palmyrene": range(67680, 67711 + 1),
"Nabataean": range(67712, 67759 + 1),
"Hatran": range(67808, 67839 + 1),
"Phoenician": range(67840, 67871 + 1),
"Lydian": range(67872, 67903 + 1),
"Meroitic Hieroglyphs": range(67968, 67999 + 1),
"Meroitic Cursive": range(68000, 68095 + 1),
"Kharoshthi": range(68096, 68191 + 1),
"Old South Arabian": range(68192, 68223 + 1),
"Old North Arabian": range(68224, 68255 + 1),
"Manichaean": range(68288, 68351 + 1),
"Avestan": range(68352, 68415 + 1),
"Inscriptional Parthian": range(68416, 68447 + 1),
"Inscriptional Pahlavi": range(68448, 68479 + 1),
"Psalter Pahlavi": range(68480, 68527 + 1),
"Old Turkic": range(68608, 68687 + 1),
"Old Hungarian": range(68736, 68863 + 1),
"Rumi Numeral Symbols": range(69216, 69247 + 1),
"Brahmi": range(69632, 69759 + 1),
"Kaithi": range(69760, 69839 + 1),
"Sora Sompeng": range(69840, 69887 + 1),
"Chakma": range(69888, 69967 + 1),
"Mahajani": range(69968, 70015 + 1),
"Sharada": range(70016, 70111 + 1),
"Sinhala Archaic Numbers": range(70112, 70143 + 1),
"Khojki": range(70144, 70223 + 1),
"Multani": range(70272, 70319 + 1),
"Khudawadi": range(70320, 70399 + 1),
"Grantha": range(70400, 70527 + 1),
"Newa": range(70656, 70783 + 1),
"Tirhuta": range(70784, 70879 + 1),
"Siddham": range(71040, 71167 + 1),
"Modi": range(71168, 71263 + 1),
"Mongolian Supplement": range(71264, 71295 + 1),
"Takri": range(71296, 71375 + 1),
"Ahom": range(71424, 71487 + 1),
"Warang Citi": range(71840, 71935 + 1),
"Zanabazar Square": range(72192, 72271 + 1),
"Soyombo": range(72272, 72367 + 1),
"Pau Cin Hau": range(72384, 72447 + 1),
"Bhaiksuki": range(72704, 72815 + 1),
"Marchen": range(72816, 72895 + 1),
"Masaram Gondi": range(72960, 73055 + 1),
"Cuneiform": range(73728, 74751 + 1),
"Cuneiform Numbers and Punctuation": range(74752, 74879 + 1),
"Early Dynastic Cuneiform": range(74880, 75087 + 1),
"Egyptian Hieroglyphs": range(77824, 78895 + 1),
"Anatolian Hieroglyphs": range(82944, 83583 + 1),
"Bamum Supplement": range(92160, 92735 + 1),
"Mro": range(92736, 92783 + 1),
"Bassa Vah": range(92880, 92927 + 1),
"Pahawh Hmong": range(92928, 93071 + 1),
"Miao": range(93952, 94111 + 1),
"Ideographic Symbols and Punctuation": range(94176, 94207 + 1),
"Tangut": range(94208, 100351 + 1),
"Tangut Components": range(100352, 101119 + 1),
"Kana Supplement": range(110592, 110847 + 1),
"Kana Extended-A": range(110848, 110895 + 1),
"Nushu": range(110960, 111359 + 1),
"Duployan": range(113664, 113823 + 1),
"Shorthand Format Controls": range(113824, 113839 + 1),
"Byzantine Musical Symbols": range(118784, 119039 + 1),
"Musical Symbols": range(119040, 119295 + 1),
"Ancient Greek Musical Notation": range(119296, 119375 + 1),
"Tai Xuan Jing Symbols": range(119552, 119647 + 1),
"Counting Rod Numerals": range(119648, 119679 + 1),
"Mathematical Alphanumeric Symbols": range(119808, 120831 + 1),
"Sutton SignWriting": range(120832, 121519 + 1),
"Glagolitic Supplement": range(122880, 122927 + 1),
"Mende Kikakui": range(124928, 125151 + 1),
"Adlam": range(125184, 125279 + 1),
"Arabic Mathematical Alphabetic Symbols": range(126464, 126719 + 1),
"Mahjong Tiles": range(126976, 127023 + 1),
"Domino Tiles": range(127024, 127135 + 1),
"Playing Cards": range(127136, 127231 + 1),
"Enclosed Alphanumeric Supplement": range(127232, 127487 + 1),
"Enclosed Ideographic Supplement": range(127488, 127743 + 1),
"Miscellaneous Symbols and Pictographs": range(127744, 128511 + 1),
"Emoticons range(Emoji)": range(128512, 128591 + 1),
"Ornamental Dingbats": range(128592, 128639 + 1),
"Transport and Map Symbols": range(128640, 128767 + 1),
"Alchemical Symbols": range(128768, 128895 + 1),
"Geometric Shapes Extended": range(128896, 129023 + 1),
"Supplemental Arrows-C": range(129024, 129279 + 1),
"Supplemental Symbols and Pictographs": range(129280, 129535 + 1),
"CJK Unified Ideographs Extension B": range(131072, 173791 + 1),
"CJK Unified Ideographs Extension C": range(173824, 177983 + 1),
"CJK Unified Ideographs Extension D": range(177984, 178207 + 1),
"CJK Unified Ideographs Extension E": range(178208, 183983 + 1),
"CJK Unified Ideographs Extension F": range(183984, 191471 + 1),
"CJK Compatibility Ideographs Supplement": range(194560, 195103 + 1),
"Tags": range(917504, 917631 + 1),
"Variation Selectors Supplement": range(917760, 917999 + 1),
}
UNICODE_SECONDARY_RANGE_KEYWORD: List[str] = [
"Supplement",
"Extended",
"Extensions",
"Modifier",
"Marks",
"Punctuation",
"Symbols",
"Forms",
"Operators",
"Miscellaneous",
"Drawing",
"Block",
"Shapes",
"Supplemental",
"Tags",
]
RE_POSSIBLE_ENCODING_INDICATION = re_compile(
r"(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)",
IGNORECASE,
)
IANA_SUPPORTED: List[str] = sorted(
filter(
lambda x: x.endswith("_codec") is False
and x not in {"rot_13", "tactis", "mbcs"},
list(set(aliases.values())),
)
)
IANA_SUPPORTED_COUNT: int = len(IANA_SUPPORTED)
# pre-computed code page that are similar using the function cp_similarity.
IANA_SUPPORTED_SIMILAR: Dict[str, List[str]] = {
"cp037": ["cp1026", "cp1140", "cp273", "cp500"],
"cp1026": ["cp037", "cp1140", "cp273", "cp500"],
"cp1125": ["cp866"],
"cp1140": ["cp037", "cp1026", "cp273", "cp500"],
"cp1250": ["iso8859_2"],
"cp1251": ["kz1048", "ptcp154"],
"cp1252": ["iso8859_15", "iso8859_9", "latin_1"],
"cp1253": ["iso8859_7"],
"cp1254": ["iso8859_15", "iso8859_9", "latin_1"],
"cp1257": ["iso8859_13"],
"cp273": ["cp037", "cp1026", "cp1140", "cp500"],
"cp437": ["cp850", "cp858", "cp860", "cp861", "cp862", "cp863", "cp865"],
"cp500": ["cp037", "cp1026", "cp1140", "cp273"],
"cp850": ["cp437", "cp857", "cp858", "cp865"],
"cp857": ["cp850", "cp858", "cp865"],
"cp858": ["cp437", "cp850", "cp857", "cp865"],
"cp860": ["cp437", "cp861", "cp862", "cp863", "cp865"],
"cp861": ["cp437", "cp860", "cp862", "cp863", "cp865"],
"cp862": ["cp437", "cp860", "cp861", "cp863", "cp865"],
"cp863": ["cp437", "cp860", "cp861", "cp862", "cp865"],
"cp865": ["cp437", "cp850", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863"],
"cp866": ["cp1125"],
"iso8859_10": ["iso8859_14", "iso8859_15", "iso8859_4", "iso8859_9", "latin_1"],
"iso8859_11": ["tis_620"],
"iso8859_13": ["cp1257"],
"iso8859_14": [
"iso8859_10",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
],
"iso8859_15": [
"cp1252",
"cp1254",
"iso8859_10",
"iso8859_14",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
],
"iso8859_16": [
"iso8859_14",
"iso8859_15",
"iso8859_2",
"iso8859_3",
"iso8859_9",
"latin_1",
],
"iso8859_2": ["cp1250", "iso8859_16", "iso8859_4"],
"iso8859_3": ["iso8859_14", "iso8859_15", "iso8859_16", "iso8859_9", "latin_1"],
"iso8859_4": ["iso8859_10", "iso8859_2", "iso8859_9", "latin_1"],
"iso8859_7": ["cp1253"],
"iso8859_9": [
"cp1252",
"cp1254",
"cp1258",
"iso8859_10",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_4",
"latin_1",
],
"kz1048": ["cp1251", "ptcp154"],
"latin_1": [
"cp1252",
"cp1254",
"cp1258",
"iso8859_10",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_4",
"iso8859_9",
],
"mac_iceland": ["mac_roman", "mac_turkish"],
"mac_roman": ["mac_iceland", "mac_turkish"],
"mac_turkish": ["mac_iceland", "mac_roman"],
"ptcp154": ["cp1251", "kz1048"],
"tis_620": ["iso8859_11"],
}
CHARDET_CORRESPONDENCE: Dict[str, str] = {
"iso2022_kr": "ISO-2022-KR",
"iso2022_jp": "ISO-2022-JP",
"euc_kr": "EUC-KR",
"tis_620": "TIS-620",
"utf_32": "UTF-32",
"euc_jp": "EUC-JP",
"koi8_r": "KOI8-R",
"iso8859_1": "ISO-8859-1",
"iso8859_2": "ISO-8859-2",
"iso8859_5": "ISO-8859-5",
"iso8859_6": "ISO-8859-6",
"iso8859_7": "ISO-8859-7",
"iso8859_8": "ISO-8859-8",
"utf_16": "UTF-16",
"cp855": "IBM855",
"mac_cyrillic": "MacCyrillic",
"gb2312": "GB2312",
"gb18030": "GB18030",
"cp932": "CP932",
"cp866": "IBM866",
"utf_8": "utf-8",
"utf_8_sig": "UTF-8-SIG",
"shift_jis": "SHIFT_JIS",
"big5": "Big5",
"cp1250": "windows-1250",
"cp1251": "windows-1251",
"cp1252": "Windows-1252",
"cp1253": "windows-1253",
"cp1255": "windows-1255",
"cp1256": "windows-1256",
"cp1254": "Windows-1254",
"cp949": "CP949",
}
COMMON_SAFE_ASCII_CHARACTERS: Set[str] = {
"<",
">",
"=",
":",
"/",
"&",
";",
"{",
"}",
"[",
"]",
",",
"|",
'"',
"-",
}
KO_NAMES: Set[str] = {"johab", "cp949", "euc_kr"}
ZH_NAMES: Set[str] = {"big5", "cp950", "big5hkscs", "hz"}
NOT_PRINTABLE_PATTERN = re_compile(r"[0-9\W\n\r\t]+")
LANGUAGE_SUPPORTED_COUNT: int = len(FREQUENCIES)
# Logging LEVEL bellow DEBUG
TRACE: int = 5

95
env/lib/python3.12/site-packages/charset_normalizer/legacy.py vendored
View File

@@ -1,95 +0,0 @@
import warnings
from typing import Dict, Optional, Union
from .api import from_bytes, from_fp, from_path, normalize
from .constant import CHARDET_CORRESPONDENCE
from .models import CharsetMatch, CharsetMatches
def detect(byte_str: bytes) -> Dict[str, Optional[Union[str, float]]]:
"""
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.
"""
if not isinstance(byte_str, (bytearray, bytes)):
raise TypeError( # pragma: nocover
"Expected object of type bytes or bytearray, got: "
"{0}".format(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
# 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"
return {
"encoding": encoding
if encoding not in CHARDET_CORRESPONDENCE
else CHARDET_CORRESPONDENCE[encoding],
"language": language,
"confidence": confidence,
}
class CharsetNormalizerMatch(CharsetMatch):
pass
class CharsetNormalizerMatches(CharsetMatches):
@staticmethod
def from_fp(*args, **kwargs): # type: ignore
warnings.warn( # pragma: nocover
"staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
"and scheduled to be removed in 3.0",
DeprecationWarning,
)
return from_fp(*args, **kwargs) # pragma: nocover
@staticmethod
def from_bytes(*args, **kwargs): # type: ignore
warnings.warn( # pragma: nocover
"staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
"and scheduled to be removed in 3.0",
DeprecationWarning,
)
return from_bytes(*args, **kwargs) # pragma: nocover
@staticmethod
def from_path(*args, **kwargs): # type: ignore
warnings.warn( # pragma: nocover
"staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
"and scheduled to be removed in 3.0",
DeprecationWarning,
)
return from_path(*args, **kwargs) # pragma: nocover
@staticmethod
def normalize(*args, **kwargs): # type: ignore
warnings.warn( # pragma: nocover
"staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
"and scheduled to be removed in 3.0",
DeprecationWarning,
)
return normalize(*args, **kwargs) # pragma: nocover
class CharsetDetector(CharsetNormalizerMatches):
pass
class CharsetDoctor(CharsetNormalizerMatches):
pass

553
env/lib/python3.12/site-packages/charset_normalizer/md.py vendored
View File

@@ -1,553 +0,0 @@
from functools import lru_cache
from typing import List, Optional
from .constant import COMMON_SAFE_ASCII_CHARACTERS, UNICODE_SECONDARY_RANGE_KEYWORD
from .utils import (
is_accentuated,
is_ascii,
is_case_variable,
is_cjk,
is_emoticon,
is_hangul,
is_hiragana,
is_katakana,
is_latin,
is_punctuation,
is_separator,
is_symbol,
is_thai,
is_unprintable,
remove_accent,
unicode_range,
)
class MessDetectorPlugin:
"""
Base abstract class used for mess detection plugins.
All detectors MUST extend and implement given methods.
"""
def eligible(self, character: str) -> bool:
"""
Determine if given character should be fed in.
"""
raise NotImplementedError # pragma: nocover
def feed(self, character: str) -> None:
"""
The main routine to be executed upon character.
Insert the logic in witch the text would be considered chaotic.
"""
raise NotImplementedError # pragma: nocover
def reset(self) -> None: # pragma: no cover
"""
Permit to reset the plugin to the initial state.
"""
raise NotImplementedError
@property
def ratio(self) -> float:
"""
Compute the chaos ratio based on what your feed() has seen.
Must NOT be lower than 0.; No restriction gt 0.
"""
raise NotImplementedError # pragma: nocover
class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._punctuation_count: int = 0
self._symbol_count: int = 0
self._character_count: int = 0
self._last_printable_char: Optional[str] = None
self._frenzy_symbol_in_word: bool = False
def eligible(self, character: str) -> bool:
return character.isprintable()
def feed(self, character: str) -> None:
self._character_count += 1
if (
character != self._last_printable_char
and character not in COMMON_SAFE_ASCII_CHARACTERS
):
if is_punctuation(character):
self._punctuation_count += 1
elif (
character.isdigit() is False
and is_symbol(character)
and is_emoticon(character) is False
):
self._symbol_count += 2
self._last_printable_char = character
def reset(self) -> None: # pragma: no cover
self._punctuation_count = 0
self._character_count = 0
self._symbol_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
ratio_of_punctuation: float = (
self._punctuation_count + self._symbol_count
) / self._character_count
return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0
class TooManyAccentuatedPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._character_count: int = 0
self._accentuated_count: int = 0
def eligible(self, character: str) -> bool:
return character.isalpha()
def feed(self, character: str) -> None:
self._character_count += 1
if is_accentuated(character):
self._accentuated_count += 1
def reset(self) -> None: # pragma: no cover
self._character_count = 0
self._accentuated_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
ratio_of_accentuation: float = self._accentuated_count / self._character_count
return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0
class UnprintablePlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._unprintable_count: int = 0
self._character_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if is_unprintable(character):
self._unprintable_count += 1
self._character_count += 1
def reset(self) -> None: # pragma: no cover
self._unprintable_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._unprintable_count * 8) / self._character_count
class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._successive_count: int = 0
self._character_count: int = 0
self._last_latin_character: Optional[str] = None
def eligible(self, character: str) -> bool:
return character.isalpha() and is_latin(character)
def feed(self, character: str) -> None:
self._character_count += 1
if (
self._last_latin_character is not None
and is_accentuated(character)
and is_accentuated(self._last_latin_character)
):
if character.isupper() and self._last_latin_character.isupper():
self._successive_count += 1
# Worse if its the same char duplicated with different accent.
if remove_accent(character) == remove_accent(self._last_latin_character):
self._successive_count += 1
self._last_latin_character = character
def reset(self) -> None: # pragma: no cover
self._successive_count = 0
self._character_count = 0
self._last_latin_character = None
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._successive_count * 2) / self._character_count
class SuspiciousRange(MessDetectorPlugin):
def __init__(self) -> None:
self._suspicious_successive_range_count: int = 0
self._character_count: int = 0
self._last_printable_seen: Optional[str] = None
def eligible(self, character: str) -> bool:
return character.isprintable()
def feed(self, character: str) -> None:
self._character_count += 1
if (
character.isspace()
or is_punctuation(character)
or character in COMMON_SAFE_ASCII_CHARACTERS
):
self._last_printable_seen = None
return
if self._last_printable_seen is None:
self._last_printable_seen = character
return
unicode_range_a: Optional[str] = unicode_range(self._last_printable_seen)
unicode_range_b: Optional[str] = unicode_range(character)
if is_suspiciously_successive_range(unicode_range_a, unicode_range_b):
self._suspicious_successive_range_count += 1
self._last_printable_seen = character
def reset(self) -> None: # pragma: no cover
self._character_count = 0
self._suspicious_successive_range_count = 0
self._last_printable_seen = None
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
ratio_of_suspicious_range_usage: float = (
self._suspicious_successive_range_count * 2
) / self._character_count
if ratio_of_suspicious_range_usage < 0.1:
return 0.0
return ratio_of_suspicious_range_usage
class SuperWeirdWordPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._word_count: int = 0
self._bad_word_count: int = 0
self._foreign_long_count: int = 0
self._is_current_word_bad: bool = False
self._foreign_long_watch: bool = False
self._character_count: int = 0
self._bad_character_count: int = 0
self._buffer: str = ""
self._buffer_accent_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if character.isalpha():
self._buffer += character
if is_accentuated(character):
self._buffer_accent_count += 1
if (
self._foreign_long_watch is False
and (is_latin(character) is False or is_accentuated(character))
and is_cjk(character) is False
and is_hangul(character) is False
and is_katakana(character) is False
and is_hiragana(character) is False
and is_thai(character) is False
):
self._foreign_long_watch = True
return
if not self._buffer:
return
if (
character.isspace() or is_punctuation(character) or is_separator(character)
) and self._buffer:
self._word_count += 1
buffer_length: int = len(self._buffer)
self._character_count += buffer_length
if buffer_length >= 4:
if self._buffer_accent_count / buffer_length > 0.34:
self._is_current_word_bad = True
# Word/Buffer ending with a upper case accentuated letter are so rare,
# that we will consider them all as suspicious. Same weight as foreign_long suspicious.
if is_accentuated(self._buffer[-1]) and self._buffer[-1].isupper():
self._foreign_long_count += 1
self._is_current_word_bad = True
if buffer_length >= 24 and self._foreign_long_watch:
self._foreign_long_count += 1
self._is_current_word_bad = True
if self._is_current_word_bad:
self._bad_word_count += 1
self._bad_character_count += len(self._buffer)
self._is_current_word_bad = False
self._foreign_long_watch = False
self._buffer = ""
self._buffer_accent_count = 0
elif (
character not in {"<", ">", "-", "=", "~", "|", "_"}
and character.isdigit() is False
and is_symbol(character)
):
self._is_current_word_bad = True
self._buffer += character
def reset(self) -> None: # pragma: no cover
self._buffer = ""
self._is_current_word_bad = False
self._foreign_long_watch = False
self._bad_word_count = 0
self._word_count = 0
self._character_count = 0
self._bad_character_count = 0
self._foreign_long_count = 0
@property
def ratio(self) -> float:
if self._word_count <= 10 and self._foreign_long_count == 0:
return 0.0
return self._bad_character_count / self._character_count
class CjkInvalidStopPlugin(MessDetectorPlugin):
"""
GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and
can be easily detected. Searching for the overuse of '丅' and '丄'.
"""
def __init__(self) -> None:
self._wrong_stop_count: int = 0
self._cjk_character_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if character in {"丅", "丄"}:
self._wrong_stop_count += 1
return
if is_cjk(character):
self._cjk_character_count += 1
def reset(self) -> None: # pragma: no cover
self._wrong_stop_count = 0
self._cjk_character_count = 0
@property
def ratio(self) -> float:
if self._cjk_character_count < 16:
return 0.0
return self._wrong_stop_count / self._cjk_character_count
class ArchaicUpperLowerPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._buf: bool = False
self._character_count_since_last_sep: int = 0
self._successive_upper_lower_count: int = 0
self._successive_upper_lower_count_final: int = 0
self._character_count: int = 0
self._last_alpha_seen: Optional[str] = None
self._current_ascii_only: bool = True
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
is_concerned = character.isalpha() and is_case_variable(character)
chunk_sep = is_concerned is False
if chunk_sep and self._character_count_since_last_sep > 0:
if (
self._character_count_since_last_sep <= 64
and character.isdigit() is False
and self._current_ascii_only is False
):
self._successive_upper_lower_count_final += (
self._successive_upper_lower_count
)
self._successive_upper_lower_count = 0
self._character_count_since_last_sep = 0
self._last_alpha_seen = None
self._buf = False
self._character_count += 1
self._current_ascii_only = True
return
if self._current_ascii_only is True and is_ascii(character) is False:
self._current_ascii_only = False
if self._last_alpha_seen is not None:
if (character.isupper() and self._last_alpha_seen.islower()) or (
character.islower() and self._last_alpha_seen.isupper()
):
if self._buf is True:
self._successive_upper_lower_count += 2
self._buf = False
else:
self._buf = True
else:
self._buf = False
self._character_count += 1
self._character_count_since_last_sep += 1
self._last_alpha_seen = character
def reset(self) -> None: # pragma: no cover
self._character_count = 0
self._character_count_since_last_sep = 0
self._successive_upper_lower_count = 0
self._successive_upper_lower_count_final = 0
self._last_alpha_seen = None
self._buf = False
self._current_ascii_only = True
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return self._successive_upper_lower_count_final / self._character_count
@lru_cache(maxsize=1024)
def is_suspiciously_successive_range(
unicode_range_a: Optional[str], unicode_range_b: Optional[str]
) -> bool:
"""
Determine if two Unicode range seen next to each other can be considered as suspicious.
"""
if unicode_range_a is None or unicode_range_b is None:
return True
if unicode_range_a == unicode_range_b:
return False
if "Latin" in unicode_range_a and "Latin" in unicode_range_b:
return False
if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b:
return False
# Latin characters can be accompanied with a combining diacritical mark
# eg. Vietnamese.
if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and (
"Combining" in unicode_range_a or "Combining" in unicode_range_b
):
return False
keywords_range_a, keywords_range_b = unicode_range_a.split(
" "
), unicode_range_b.split(" ")
for el in keywords_range_a:
if el in UNICODE_SECONDARY_RANGE_KEYWORD:
continue
if el in keywords_range_b:
return False
# Japanese Exception
range_a_jp_chars, range_b_jp_chars = (
unicode_range_a
in (
"Hiragana",
"Katakana",
),
unicode_range_b in ("Hiragana", "Katakana"),
)
if (range_a_jp_chars or range_b_jp_chars) and (
"CJK" in unicode_range_a or "CJK" in unicode_range_b
):
return False
if range_a_jp_chars and range_b_jp_chars:
return False
if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b:
if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
return False
if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
return False
# Chinese/Japanese use dedicated range for punctuation and/or separators.
if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or (
unicode_range_a in ["Katakana", "Hiragana"]
and unicode_range_b in ["Katakana", "Hiragana"]
):
if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b:
return False
if "Forms" in unicode_range_a or "Forms" in unicode_range_b:
return False
return True
@lru_cache(maxsize=2048)
def mess_ratio(
decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False
) -> float:
"""
Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier.
"""
detectors: List[MessDetectorPlugin] = [
md_class() for md_class in MessDetectorPlugin.__subclasses__()
]
length: int = len(decoded_sequence) + 1
mean_mess_ratio: float = 0.0
if length < 512:
intermediary_mean_mess_ratio_calc: int = 32
elif length <= 1024:
intermediary_mean_mess_ratio_calc = 64
else:
intermediary_mean_mess_ratio_calc = 128
for character, index in zip(decoded_sequence + "\n", range(length)):
for detector in detectors:
if detector.eligible(character):
detector.feed(character)
if (
index > 0 and index % intermediary_mean_mess_ratio_calc == 0
) or index == length - 1:
mean_mess_ratio = sum(dt.ratio for dt in detectors)
if mean_mess_ratio >= maximum_threshold:
break
if debug:
for dt in detectors: # pragma: nocover
print(dt.__class__, dt.ratio)
return round(mean_mess_ratio, 3)

392
env/lib/python3.12/site-packages/charset_normalizer/models.py vendored
View File

@@ -1,392 +0,0 @@
import warnings
from collections import Counter
from encodings.aliases import aliases
from hashlib import sha256
from json import dumps
from re import sub
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
from .constant import NOT_PRINTABLE_PATTERN, TOO_BIG_SEQUENCE
from .md import mess_ratio
from .utils import iana_name, is_multi_byte_encoding, unicode_range
class CharsetMatch:
def __init__(
self,
payload: bytes,
guessed_encoding: str,
mean_mess_ratio: float,
has_sig_or_bom: bool,
languages: "CoherenceMatches",
decoded_payload: Optional[str] = None,
):
self._payload: bytes = 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: Optional[List[str]] = None
self._leaves: List[CharsetMatch] = []
self._mean_coherence_ratio: float = 0.0
self._output_payload: Optional[bytes] = None
self._output_encoding: Optional[str] = None
self._string: Optional[str] = decoded_payload
def __eq__(self, other: object) -> bool:
if not isinstance(other, CharsetMatch):
raise TypeError(
"__eq__ cannot be invoked on {} and {}.".format(
str(other.__class__), str(self.__class__)
)
)
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)
# Bellow 1% difference --> Use Coherence
if chaos_difference < 0.01 and coherence_difference > 0.02:
# When having a tough decision, use the result that decoded as many multi-byte as possible.
if chaos_difference == 0.0 and self.coherence == other.coherence:
return self.multi_byte_usage > other.multi_byte_usage
return self.coherence > other.coherence
return self.chaos < other.chaos
@property
def multi_byte_usage(self) -> float:
return 1.0 - len(str(self)) / len(self.raw)
@property
def chaos_secondary_pass(self) -> float:
"""
Check once again chaos in decoded text, except this time, with full content.
Use with caution, this can be very slow.
Notice: Will be removed in 3.0
"""
warnings.warn(
"chaos_secondary_pass is deprecated and will be removed in 3.0",
DeprecationWarning,
)
return mess_ratio(str(self), 1.0)
@property
def coherence_non_latin(self) -> float:
"""
Coherence ratio on the first non-latin language detected if ANY.
Notice: Will be removed in 3.0
"""
warnings.warn(
"coherence_non_latin is deprecated and will be removed in 3.0",
DeprecationWarning,
)
return 0.0
@property
def w_counter(self) -> Counter:
"""
Word counter instance on decoded text.
Notice: Will be removed in 3.0
"""
warnings.warn(
"w_counter is deprecated and will be removed in 3.0", DeprecationWarning
)
string_printable_only = sub(NOT_PRINTABLE_PATTERN, " ", str(self).lower())
return Counter(string_printable_only.split())
def __str__(self) -> str:
# Lazy Str Loading
if self._string is None:
self._string = str(self._payload, self._encoding, "strict")
return self._string
def __repr__(self) -> str:
return "<CharsetMatch '{}' bytes({})>".format(self.encoding, 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:
"""
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[Optional[str]] = [
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 first(self) -> "CharsetMatch":
"""
Kept for BC reasons. Will be removed in 3.0.
"""
return self
def best(self) -> "CharsetMatch":
"""
Kept for BC reasons. Will be removed in 3.0.
"""
return self
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
self._output_payload = str(self).encode(encoding, "replace")
return self._output_payload # type: ignore
@property
def fingerprint(self) -> str:
"""
Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
"""
return sha256(self.output()).hexdigest()
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):
self._results: List[CharsetMatch] = sorted(results) if results else []
def __iter__(self) -> Iterator[CharsetMatch]:
yield from self._results
def __getitem__(self, item: Union[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) -> Optional["CharsetMatch"]:
"""
Simply return the first match. Strict equivalent to matches[0].
"""
if not self._results:
return None
return self._results[0]
def first(self) -> Optional["CharsetMatch"]:
"""
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: Optional[str],
encoding_aliases: List[str],
alternative_encodings: List[str],
language: str,
alphabets: List[str],
has_sig_or_bom: bool,
chaos: float,
coherence: float,
unicode_path: Optional[str],
is_preferred: bool,
):
self.path: str = path
self.unicode_path: Optional[str] = unicode_path
self.encoding: Optional[str] = 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:
return dumps(self.__dict__, ensure_ascii=True, indent=4)

0
env/lib/python3.12/site-packages/charset_normalizer/py.typed vendored
View File

414
env/lib/python3.12/site-packages/charset_normalizer/utils.py vendored
View File

@@ -1,414 +0,0 @@
try:
# WARNING: unicodedata2 support is going to be removed in 3.0
# Python is quickly catching up.
import unicodedata2 as unicodedata
except ImportError:
import unicodedata # type: ignore[no-redef]
import importlib
import logging
from codecs import IncrementalDecoder
from encodings.aliases import aliases
from functools import lru_cache
from re import findall
from typing import Generator, List, Optional, Set, Tuple, Union
from _multibytecodec import MultibyteIncrementalDecoder # type: ignore
from .constant import (
ENCODING_MARKS,
IANA_SUPPORTED_SIMILAR,
RE_POSSIBLE_ENCODING_INDICATION,
UNICODE_RANGES_COMBINED,
UNICODE_SECONDARY_RANGE_KEYWORD,
UTF8_MAXIMAL_ALLOCATION,
)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_accentuated(character: str) -> bool:
try:
description: str = unicodedata.name(character)
except ValueError:
return False
return (
"WITH GRAVE" in description
or "WITH ACUTE" in description
or "WITH CEDILLA" in description
or "WITH DIAERESIS" in description
or "WITH CIRCUMFLEX" in description
or "WITH TILDE" in description
)
@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))
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def unicode_range(character: str) -> Optional[str]:
"""
Retrieve the Unicode range official name from a single character.
"""
character_ord: int = ord(character)
for range_name, ord_range in UNICODE_RANGES_COMBINED.items():
if character_ord in ord_range:
return range_name
return None
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_latin(character: str) -> bool:
try:
description: str = unicodedata.name(character)
except ValueError:
return False
return "LATIN" in description
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_ascii(character: str) -> bool:
try:
character.encode("ascii")
except UnicodeEncodeError:
return False
return True
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_punctuation(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "P" in character_category:
return True
character_range: Optional[str] = unicode_range(character)
if character_range is None:
return False
return "Punctuation" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
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: Optional[str] = unicode_range(character)
if character_range is None:
return False
return "Forms" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_emoticon(character: str) -> bool:
character_range: Optional[str] = unicode_range(character)
if character_range is None:
return False
return "Emoticons" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
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
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_case_variable(character: str) -> bool:
return character.islower() != character.isupper()
def is_private_use_only(character: str) -> bool:
character_category: str = unicodedata.category(character)
return character_category == "Co"
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError:
return False
return "CJK" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hiragana(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError:
return False
return "HIRAGANA" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_katakana(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError:
return False
return "KATAKANA" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hangul(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError:
return False
return "HANGUL" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_thai(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError:
return False
return "THAI" in character_name
@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
def is_unicode_range_secondary(range_name: str) -> bool:
return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_unprintable(character: str) -> bool:
return (
character.isspace() is False # includes \n \t \r \v
and character.isprintable() is False
and character != "\x1A" # Why? Its the ASCII substitute character.
and character != b"\xEF\xBB\xBF".decode("utf_8") # 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, search_zone: int = 4096) -> Optional[str]:
"""
Extract using ASCII-only decoder any specified encoding in the first n-bytes.
"""
if not isinstance(sequence, bytes):
raise TypeError
seq_len: int = len(sequence)
results: List[str] = findall(
RE_POSSIBLE_ENCODING_INDICATION,
sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"),
)
if len(results) == 0:
return None
for specified_encoding in results:
specified_encoding = specified_encoding.lower().replace("-", "_")
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
"""
return 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",
} or issubclass(
importlib.import_module("encodings.{}".format(name)).IncrementalDecoder, # type: ignore
MultibyteIncrementalDecoder,
)
def identify_sig_or_bom(sequence: bytes) -> Tuple[Optional[str], bytes]:
"""
Identify and extract SIG/BOM in given sequence.
"""
for iana_encoding in ENCODING_MARKS:
marks: Union[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:
cp_name = cp_name.lower().replace("-", "_")
for encoding_alias, encoding_iana in aliases.items():
if cp_name in [encoding_alias, encoding_iana]:
return encoding_iana
if strict:
raise ValueError("Unable to retrieve IANA for '{}'".format(cp_name))
return cp_name
def range_scan(decoded_sequence: str) -> List[str]:
ranges: Set[str] = set()
for character in decoded_sequence:
character_range: Optional[str] = unicode_range(character)
if character_range is None:
continue
ranges.add(character_range)
return list(ranges)
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("encodings.{}".format(iana_name_a)).IncrementalDecoder # type: ignore
decoder_b = importlib.import_module("encodings.{}".format(iana_name_b)).IncrementalDecoder # type: ignore
id_a: IncrementalDecoder = decoder_a(errors="ignore")
id_b: IncrementalDecoder = decoder_b(errors="ignore")
character_match_count: int = 0
for i in range(255):
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 / 254
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,
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: Optional[str] = None,
) -> Generator[str, None, None]:
if decoded_payload and is_multi_byte_decoder is False:
for i in offsets:
chunk = decoded_payload[i : i + chunk_size]
if not chunk:
break
yield chunk
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 strip_sig_or_bom is False:
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 and sequences[i] >= 0x80:
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 strip_sig_or_bom is False:
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

6
env/lib/python3.12/site-packages/charset_normalizer/version.py vendored
View File

@@ -1,6 +0,0 @@
"""
Expose version
"""
__version__ = "2.1.0"
VERSION = __version__.split(".")

1
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/INSTALLER vendored
View File

@@ -1 +0,0 @@
pip

27
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/LICENSE.txt vendored
View File

@@ -1,27 +0,0 @@
Copyright (c) 2010 Jonathan Hartley
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* 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.
* Neither the name of the copyright holders, nor those 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.

411
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/METADATA vendored
View File

@@ -1,411 +0,0 @@
Metadata-Version: 2.1
Name: colorama
Version: 0.4.5
Summary: Cross-platform colored terminal text.
Home-page: https://github.com/tartley/colorama
Author: Jonathan Hartley
Author-email: tartley@tartley.com
Maintainer: Arnon Yaari
License: BSD
Keywords: color colour terminal text ansi windows crossplatform xplatform
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
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 :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Terminals
Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*
License-File: LICENSE.txt
.. image:: https://img.shields.io/pypi/v/colorama.svg
:target: https://pypi.org/project/colorama/
:alt: Latest Version
.. image:: https://img.shields.io/pypi/pyversions/colorama.svg
:target: https://pypi.org/project/colorama/
:alt: Supported Python versions
.. image:: https://github.com/tartley/colorama/actions/workflows/test.yml/badge.svg
:target: https://github.com/tartley/colorama/actions/workflows/test.yml
:alt: Build Status
Colorama
========
Makes ANSI escape character sequences (for producing colored terminal text and
cursor positioning) work under MS Windows.
.. |donate| image:: https://www.paypalobjects.com/en_US/i/btn/btn_donate_SM.gif
:target: https://www.paypal.com/cgi-bin/webscr?cmd=_donations&business=2MZ9D2GMLYCUJ&item_name=Colorama&currency_code=USD
:alt: Donate with Paypal
`PyPI for releases <https://pypi.org/project/colorama/>`_ |
`Github for source <https://github.com/tartley/colorama>`_ |
`Colorama for enterprise on Tidelift <https://github.com/tartley/colorama/blob/master/ENTERPRISE.md>`_
If you find Colorama useful, please |donate| to the authors. Thank you!
Installation
------------
Tested on CPython 2.7, 3.5, 3.6, 3.7, 3.8, 3.9 and 3.10 and Pypy 2.7 and 3.6.
No requirements other than the standard library.
.. code-block:: bash
pip install colorama
# or
conda install -c anaconda colorama
Description
-----------
ANSI escape character sequences have long been used to produce colored terminal
text and cursor positioning on Unix and Macs. Colorama makes this work on
Windows, too, by wrapping ``stdout``, stripping ANSI sequences it finds (which
would appear as gobbledygook in the output), and converting them into the
appropriate win32 calls to modify the state of the terminal. On other platforms,
Colorama does nothing.
This has the upshot of providing a simple cross-platform API for printing
colored terminal text from Python, and has the happy side-effect that existing
applications or libraries which use ANSI sequences to produce colored output on
Linux or Macs can now also work on Windows, simply by calling
``colorama.init()``.
An alternative approach is to install ``ansi.sys`` on Windows machines, which
provides the same behaviour for all applications running in terminals. Colorama
is intended for situations where that isn't easy (e.g., maybe your app doesn't
have an installer.)
Demo scripts in the source code repository print some colored text using
ANSI sequences. Compare their output under Gnome-terminal's built in ANSI
handling, versus on Windows Command-Prompt using Colorama:
.. image:: https://github.com/tartley/colorama/raw/master/screenshots/ubuntu-demo.png
:width: 661
:height: 357
:alt: ANSI sequences on Ubuntu under gnome-terminal.
.. image:: https://github.com/tartley/colorama/raw/master/screenshots/windows-demo.png
:width: 668
:height: 325
:alt: Same ANSI sequences on Windows, using Colorama.
These screenshots show that, on Windows, Colorama does not support ANSI 'dim
text'; it looks the same as 'normal text'.
Usage
-----
Initialisation
..............
Applications should initialise Colorama using:
.. code-block:: python
from colorama import init
init()
On Windows, calling ``init()`` will filter ANSI escape sequences out of any
text sent to ``stdout`` or ``stderr``, and replace them with equivalent Win32
calls.
On other platforms, calling ``init()`` has no effect (unless you request other
optional functionality, see "Init Keyword Args" below; or if output
is redirected). By design, this permits applications to call ``init()``
unconditionally on all platforms, after which ANSI output should just work.
On all platforms, if output is redirected, ANSI escape sequences are completely
stripped out.
To stop using Colorama before your program exits, simply call ``deinit()``.
This will restore ``stdout`` and ``stderr`` to their original values, so that
Colorama is disabled. To resume using Colorama again, call ``reinit()``; it is
cheaper than calling ``init()`` again (but does the same thing).
Colored Output
..............
Cross-platform printing of colored text can then be done using Colorama's
constant shorthand for ANSI escape sequences. These are deliberately
rudimentary, see below.
.. code-block:: python
from colorama import Fore, Back, Style
print(Fore.RED + 'some red text')
print(Back.GREEN + 'and with a green background')
print(Style.DIM + 'and in dim text')
print(Style.RESET_ALL)
print('back to normal now')
...or simply by manually printing ANSI sequences from your own code:
.. code-block:: python
print('\033[31m' + 'some red text')
print('\033[39m') # and reset to default color
...or, Colorama can be used in conjunction with existing ANSI libraries
such as the venerable `Termcolor <https://pypi.org/project/termcolor/>`_
the fabulous `Blessings <https://pypi.org/project/blessings/>`_,
or the incredible `_Rich <https://pypi.org/project/rich/>`_.
If you wish Colorama's Fore, Back and Style constants were more capable,
then consider using one of the above highly capable libraries to generate
colors, etc, and use Colorama just for its primary purpose: to convert
those ANSI sequences to also work on Windows:
.. code-block:: python
from colorama import init
from termcolor import colored
# use Colorama to make Termcolor work on Windows too
init()
# then use Termcolor for all colored text output
print(colored('Hello, World!', 'green', 'on_red'))
Available formatting constants are::
Fore: BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE, RESET.
Back: BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE, RESET.
Style: DIM, NORMAL, BRIGHT, RESET_ALL
``Style.RESET_ALL`` resets foreground, background, and brightness. Colorama will
perform this reset automatically on program exit.
These are fairly well supported, but not part of the standard::
Fore: LIGHTBLACK_EX, LIGHTRED_EX, LIGHTGREEN_EX, LIGHTYELLOW_EX, LIGHTBLUE_EX, LIGHTMAGENTA_EX, LIGHTCYAN_EX, LIGHTWHITE_EX
Back: LIGHTBLACK_EX, LIGHTRED_EX, LIGHTGREEN_EX, LIGHTYELLOW_EX, LIGHTBLUE_EX, LIGHTMAGENTA_EX, LIGHTCYAN_EX, LIGHTWHITE_EX
Cursor Positioning
..................
ANSI codes to reposition the cursor are supported. See ``demos/demo06.py`` for
an example of how to generate them.
Init Keyword Args
.................
``init()`` accepts some ``**kwargs`` to override default behaviour.
init(autoreset=False):
If you find yourself repeatedly sending reset sequences to turn off color
changes at the end of every print, then ``init(autoreset=True)`` will
automate that:
.. code-block:: python
from colorama import init
init(autoreset=True)
print(Fore.RED + 'some red text')
print('automatically back to default color again')
init(strip=None):
Pass ``True`` or ``False`` to override whether ANSI codes should be
stripped from the output. The default behaviour is to strip if on Windows
or if output is redirected (not a tty).
init(convert=None):
Pass ``True`` or ``False`` to override whether to convert ANSI codes in the
output into win32 calls. The default behaviour is to convert if on Windows
and output is to a tty (terminal).
init(wrap=True):
On Windows, Colorama works by replacing ``sys.stdout`` and ``sys.stderr``
with proxy objects, which override the ``.write()`` method to do their work.
If this wrapping causes you problems, then this can be disabled by passing
``init(wrap=False)``. The default behaviour is to wrap if ``autoreset`` or
``strip`` or ``convert`` are True.
When wrapping is disabled, colored printing on non-Windows platforms will
continue to work as normal. To do cross-platform colored output, you can
use Colorama's ``AnsiToWin32`` proxy directly:
.. code-block:: python
import sys
from colorama import init, AnsiToWin32
init(wrap=False)
stream = AnsiToWin32(sys.stderr).stream
# Python 2
print >>stream, Fore.BLUE + 'blue text on stderr'
# Python 3
print(Fore.BLUE + 'blue text on stderr', file=stream)
Recognised ANSI Sequences
.........................
ANSI sequences generally take the form::
ESC [ <param> ; <param> ... <command>
Where ``<param>`` is an integer, and ``<command>`` is a single letter. Zero or
more params are passed to a ``<command>``. If no params are passed, it is
generally synonymous with passing a single zero. No spaces exist in the
sequence; they have been inserted here simply to read more easily.
The only ANSI sequences that Colorama converts into win32 calls are::
ESC [ 0 m # reset all (colors and brightness)
ESC [ 1 m # bright
ESC [ 2 m # dim (looks same as normal brightness)
ESC [ 22 m # normal brightness
# FOREGROUND:
ESC [ 30 m # black
ESC [ 31 m # red
ESC [ 32 m # green
ESC [ 33 m # yellow
ESC [ 34 m # blue
ESC [ 35 m # magenta
ESC [ 36 m # cyan
ESC [ 37 m # white
ESC [ 39 m # reset
# BACKGROUND
ESC [ 40 m # black
ESC [ 41 m # red
ESC [ 42 m # green
ESC [ 43 m # yellow
ESC [ 44 m # blue
ESC [ 45 m # magenta
ESC [ 46 m # cyan
ESC [ 47 m # white
ESC [ 49 m # reset
# cursor positioning
ESC [ y;x H # position cursor at x across, y down
ESC [ y;x f # position cursor at x across, y down
ESC [ n A # move cursor n lines up
ESC [ n B # move cursor n lines down
ESC [ n C # move cursor n characters forward
ESC [ n D # move cursor n characters backward
# clear the screen
ESC [ mode J # clear the screen
# clear the line
ESC [ mode K # clear the line
Multiple numeric params to the ``'m'`` command can be combined into a single
sequence::
ESC [ 36 ; 45 ; 1 m # bright cyan text on magenta background
All other ANSI sequences of the form ``ESC [ <param> ; <param> ... <command>``
are silently stripped from the output on Windows.
Any other form of ANSI sequence, such as single-character codes or alternative
initial characters, are not recognised or stripped. It would be cool to add
them though. Let me know if it would be useful for you, via the Issues on
GitHub.
Status & Known Problems
-----------------------
I've personally only tested it on Windows XP (CMD, Console2), Ubuntu
(gnome-terminal, xterm), and OS X.
Some presumably valid ANSI sequences aren't recognised (see details below),
but to my knowledge nobody has yet complained about this. Puzzling.
See outstanding issues and wish-list:
https://github.com/tartley/colorama/issues
If anything doesn't work for you, or doesn't do what you expected or hoped for,
I'd love to hear about it on that issues list, would be delighted by patches,
and would be happy to grant commit access to anyone who submits a working patch
or two.
If you're hacking on the code, see `README-hacking.md`_.
.. _README-hacking.md: README-hacking.md
License
-------
Copyright Jonathan Hartley & Arnon Yaari, 2013-2020. BSD 3-Clause license; see
LICENSE file.
Professional support
--------------------
.. |tideliftlogo| image:: https://cdn2.hubspot.net/hubfs/4008838/website/logos/logos_for_download/Tidelift_primary-shorthand-logo.png
:alt: Tidelift
:target: https://tidelift.com/subscription/pkg/pypi-colorama?utm_source=pypi-colorama&utm_medium=referral&utm_campaign=readme
.. list-table::
:widths: 10 100
* - |tideliftlogo|
- Professional support for colorama is available as part of the
`Tidelift Subscription`_.
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.
.. _Tidelift Subscription: https://tidelift.com/subscription/pkg/pypi-colorama?utm_source=pypi-colorama&utm_medium=referral&utm_campaign=readme
Thanks
------
* Marc Schlaich (schlamar) for a ``setup.py`` fix for Python2.5.
* Marc Abramowitz, reported & fixed a crash on exit with closed ``stdout``,
providing a solution to issue #7's setuptools/distutils debate,
and other fixes.
* User 'eryksun', for guidance on correctly instantiating ``ctypes.windll``.
* Matthew McCormick for politely pointing out a longstanding crash on non-Win.
* Ben Hoyt, for a magnificent fix under 64-bit Windows.
* Jesse at Empty Square for submitting a fix for examples in the README.
* User 'jamessp', an observant documentation fix for cursor positioning.
* User 'vaal1239', Dave Mckee & Lackner Kristof for a tiny but much-needed Win7
fix.
* Julien Stuyck, for wisely suggesting Python3 compatible updates to README.
* Daniel Griffith for multiple fabulous patches.
* Oscar Lesta for a valuable fix to stop ANSI chars being sent to non-tty
output.
* Roger Binns, for many suggestions, valuable feedback, & bug reports.
* Tim Golden for thought and much appreciated feedback on the initial idea.
* User 'Zearin' for updates to the README file.
* John Szakmeister for adding support for light colors
* Charles Merriam for adding documentation to demos
* Jurko for a fix on 64-bit Windows CPython2.5 w/o ctypes
* Florian Bruhin for a fix when stdout or stderr are None
* Thomas Weininger for fixing ValueError on Windows
* Remi Rampin for better Github integration and fixes to the README file
* Simeon Visser for closing a file handle using 'with' and updating classifiers
to include Python 3.3 and 3.4
* Andy Neff for fixing RESET of LIGHT_EX colors.
* Jonathan Hartley for the initial idea and implementation.

19
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/RECORD vendored
View File

@@ -1,19 +0,0 @@
colorama-0.4.5.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
colorama-0.4.5.dist-info/LICENSE.txt,sha256=ysNcAmhuXQSlpxQL-zs25zrtSWZW6JEQLkKIhteTAxg,1491
colorama-0.4.5.dist-info/METADATA,sha256=Kb6MoYzWBmkPhFCf0SW7a-5Eeyssj-szefJmxokQFSU,15128
colorama-0.4.5.dist-info/RECORD,,
colorama-0.4.5.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
colorama-0.4.5.dist-info/WHEEL,sha256=z9j0xAa_JmUKMpmz72K0ZGALSM_n-wQVmGbleXx2VHg,110
colorama-0.4.5.dist-info/top_level.txt,sha256=_Kx6-Cni2BT1PEATPhrSRxo0d7kSgfBbHf5o7IF1ABw,9
colorama/__init__.py,sha256=ihDoWQOkapwF7sqQ99AoDoEF3vGYm40OtmgW211cLZw,239
colorama/__pycache__/__init__.cpython-312.pyc,,
colorama/__pycache__/ansi.cpython-312.pyc,,
colorama/__pycache__/ansitowin32.cpython-312.pyc,,
colorama/__pycache__/initialise.cpython-312.pyc,,
colorama/__pycache__/win32.cpython-312.pyc,,
colorama/__pycache__/winterm.cpython-312.pyc,,
colorama/ansi.py,sha256=Top4EeEuaQdBWdteKMEcGOTeKeF19Q-Wo_6_Cj5kOzQ,2522
colorama/ansitowin32.py,sha256=gGrO7MVtwc-j1Sq3jKfZpERT1JWmYSOsTVDiTnFbZU4,10830
colorama/initialise.py,sha256=PprovDNxMTrvoNHFcL2NZjpH2XzDc8BLxLxiErfUl4k,1915
colorama/win32.py,sha256=bJ8Il9jwaBN5BJ8bmN6FoYZ1QYuMKv2j8fGrXh7TJjw,5404
colorama/winterm.py,sha256=2y_2b7Zsv34feAsP67mLOVc-Bgq51mdYGo571VprlrM,6438

0
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/REQUESTED vendored
View File

6
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/WHEEL vendored
View File

@@ -1,6 +0,0 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.1)
Root-Is-Purelib: true
Tag: py2-none-any
Tag: py3-none-any

1
env/lib/python3.12/site-packages/colorama-0.4.5.dist-info/top_level.txt vendored
View File

@@ -1 +0,0 @@
colorama

6
env/lib/python3.12/site-packages/colorama/__init__.py vendored
View File

@@ -1,6 +0,0 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
from .initialise import init, deinit, reinit, colorama_text
from .ansi import Fore, Back, Style, Cursor
from .ansitowin32 import AnsiToWin32
__version__ = '0.4.5'

102
env/lib/python3.12/site-packages/colorama/ansi.py vendored
View File

@@ -1,102 +0,0 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
'''
This module generates ANSI character codes to printing colors to terminals.
See: http://en.wikipedia.org/wiki/ANSI_escape_code
'''
CSI = '\033['
OSC = '\033]'
BEL = '\a'
def code_to_chars(code):
return CSI + str(code) + 'm'
def set_title(title):
return OSC + '2;' + title + BEL
def clear_screen(mode=2):
return CSI + str(mode) + 'J'
def clear_line(mode=2):
return CSI + str(mode) + 'K'
class AnsiCodes(object):
def __init__(self):
# the subclasses declare class attributes which are numbers.
# Upon instantiation we define instance attributes, which are the same
# as the class attributes but wrapped with the ANSI escape sequence
for name in dir(self):
if not name.startswith('_'):
value = getattr(self, name)
setattr(self, name, code_to_chars(value))
class AnsiCursor(object):
def UP(self, n=1):
return CSI + str(n) + 'A'
def DOWN(self, n=1):
return CSI + str(n) + 'B'
def FORWARD(self, n=1):
return CSI + str(n) + 'C'
def BACK(self, n=1):
return CSI + str(n) + 'D'
def POS(self, x=1, y=1):
return CSI + str(y) + ';' + str(x) + 'H'
class AnsiFore(AnsiCodes):
BLACK = 30
RED = 31
GREEN = 32
YELLOW = 33
BLUE = 34
MAGENTA = 35
CYAN = 36
WHITE = 37
RESET = 39
# These are fairly well supported, but not part of the standard.
LIGHTBLACK_EX = 90
LIGHTRED_EX = 91
LIGHTGREEN_EX = 92
LIGHTYELLOW_EX = 93
LIGHTBLUE_EX = 94
LIGHTMAGENTA_EX = 95
LIGHTCYAN_EX = 96
LIGHTWHITE_EX = 97
class AnsiBack(AnsiCodes):
BLACK = 40
RED = 41
GREEN = 42
YELLOW = 43
BLUE = 44
MAGENTA = 45
CYAN = 46
WHITE = 47
RESET = 49
# These are fairly well supported, but not part of the standard.
LIGHTBLACK_EX = 100
LIGHTRED_EX = 101
LIGHTGREEN_EX = 102
LIGHTYELLOW_EX = 103
LIGHTBLUE_EX = 104
LIGHTMAGENTA_EX = 105
LIGHTCYAN_EX = 106
LIGHTWHITE_EX = 107
class AnsiStyle(AnsiCodes):
BRIGHT = 1
DIM = 2
NORMAL = 22
RESET_ALL = 0
Fore = AnsiFore()
Back = AnsiBack()
Style = AnsiStyle()
Cursor = AnsiCursor()

266
env/lib/python3.12/site-packages/colorama/ansitowin32.py vendored
View File

@@ -1,266 +0,0 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
import re
import sys
import os
from .ansi import AnsiFore, AnsiBack, AnsiStyle, Style, BEL
from .winterm import WinTerm, WinColor, WinStyle
from .win32 import windll, winapi_test
winterm = None
if windll is not None:
winterm = WinTerm()
class StreamWrapper(object):
'''
Wraps a stream (such as stdout), acting as a transparent proxy for all
attribute access apart from method 'write()', which is delegated to our
Converter instance.
'''
def __init__(self, wrapped, converter):
# double-underscore everything to prevent clashes with names of
# attributes on the wrapped stream object.
self.__wrapped = wrapped
self.__convertor = converter
def __getattr__(self, name):
return getattr(self.__wrapped, name)
def __enter__(self, *args, **kwargs):
# special method lookup bypasses __getattr__/__getattribute__, see
# https://stackoverflow.com/questions/12632894/why-doesnt-getattr-work-with-exit
# thus, contextlib magic methods are not proxied via __getattr__
return self.__wrapped.__enter__(*args, **kwargs)
def __exit__(self, *args, **kwargs):
return self.__wrapped.__exit__(*args, **kwargs)
def __setstate__(self, state):
self.__dict__ = state
def __getstate__(self):
return self.__dict__
def write(self, text):
self.__convertor.write(text)
def isatty(self):
stream = self.__wrapped
if 'PYCHARM_HOSTED' in os.environ:
if stream is not None and (stream is sys.__stdout__ or stream is sys.__stderr__):
return True
try:
stream_isatty = stream.isatty
except AttributeError:
return False
else:
return stream_isatty()
@property
def closed(self):
stream = self.__wrapped
try:
return stream.closed
# AttributeError in the case that the stream doesn't support being closed
# ValueError for the case that the stream has already been detached when atexit runs
except (AttributeError, ValueError):
return True
class AnsiToWin32(object):
'''
Implements a 'write()' method which, on Windows, will strip ANSI character
sequences from the text, and if outputting to a tty, will convert them into
win32 function calls.
'''
ANSI_CSI_RE = re.compile('\001?\033\\[((?:\\d|;)*)([a-zA-Z])\002?') # Control Sequence Introducer
ANSI_OSC_RE = re.compile('\001?\033\\]([^\a]*)(\a)\002?') # Operating System Command
def __init__(self, wrapped, convert=None, strip=None, autoreset=False):
# The wrapped stream (normally sys.stdout or sys.stderr)
self.wrapped = wrapped
# should we reset colors to defaults after every .write()
self.autoreset = autoreset
# create the proxy wrapping our output stream
self.stream = StreamWrapper(wrapped, self)
on_windows = os.name == 'nt'
# We test if the WinAPI works, because even if we are on Windows
# we may be using a terminal that doesn't support the WinAPI
# (e.g. Cygwin Terminal). In this case it's up to the terminal
# to support the ANSI codes.
conversion_supported = on_windows and winapi_test()
# should we strip ANSI sequences from our output?
if strip is None:
strip = conversion_supported or (not self.stream.closed and not self.stream.isatty())
self.strip = strip
# should we should convert ANSI sequences into win32 calls?
if convert is None:
convert = conversion_supported and not self.stream.closed and self.stream.isatty()
self.convert = convert
# dict of ansi codes to win32 functions and parameters
self.win32_calls = self.get_win32_calls()
# are we wrapping stderr?
self.on_stderr = self.wrapped is sys.stderr
def should_wrap(self):
'''
True if this class is actually needed. If false, then the output
stream will not be affected, nor will win32 calls be issued, so
wrapping stdout is not actually required. This will generally be
False on non-Windows platforms, unless optional functionality like
autoreset has been requested using kwargs to init()
'''
return self.convert or self.strip or self.autoreset
def get_win32_calls(self):
if self.convert and winterm:
return {
AnsiStyle.RESET_ALL: (winterm.reset_all, ),
AnsiStyle.BRIGHT: (winterm.style, WinStyle.BRIGHT),
AnsiStyle.DIM: (winterm.style, WinStyle.NORMAL),
AnsiStyle.NORMAL: (winterm.style, WinStyle.NORMAL),
AnsiFore.BLACK: (winterm.fore, WinColor.BLACK),
AnsiFore.RED: (winterm.fore, WinColor.RED),
AnsiFore.GREEN: (winterm.fore, WinColor.GREEN),
AnsiFore.YELLOW: (winterm.fore, WinColor.YELLOW),
AnsiFore.BLUE: (winterm.fore, WinColor.BLUE),
AnsiFore.MAGENTA: (winterm.fore, WinColor.MAGENTA),
AnsiFore.CYAN: (winterm.fore, WinColor.CYAN),
AnsiFore.WHITE: (winterm.fore, WinColor.GREY),
AnsiFore.RESET: (winterm.fore, ),
AnsiFore.LIGHTBLACK_EX: (winterm.fore, WinColor.BLACK, True),
AnsiFore.LIGHTRED_EX: (winterm.fore, WinColor.RED, True),
AnsiFore.LIGHTGREEN_EX: (winterm.fore, WinColor.GREEN, True),
AnsiFore.LIGHTYELLOW_EX: (winterm.fore, WinColor.YELLOW, True),
AnsiFore.LIGHTBLUE_EX: (winterm.fore, WinColor.BLUE, True),
AnsiFore.LIGHTMAGENTA_EX: (winterm.fore, WinColor.MAGENTA, True),
AnsiFore.LIGHTCYAN_EX: (winterm.fore, WinColor.CYAN, True),
AnsiFore.LIGHTWHITE_EX: (winterm.fore, WinColor.GREY, True),
AnsiBack.BLACK: (winterm.back, WinColor.BLACK),
AnsiBack.RED: (winterm.back, WinColor.RED),
AnsiBack.GREEN: (winterm.back, WinColor.GREEN),
AnsiBack.YELLOW: (winterm.back, WinColor.YELLOW),
AnsiBack.BLUE: (winterm.back, WinColor.BLUE),
AnsiBack.MAGENTA: (winterm.back, WinColor.MAGENTA),
AnsiBack.CYAN: (winterm.back, WinColor.CYAN),
AnsiBack.WHITE: (winterm.back, WinColor.GREY),
AnsiBack.RESET: (winterm.back, ),
AnsiBack.LIGHTBLACK_EX: (winterm.back, WinColor.BLACK, True),
AnsiBack.LIGHTRED_EX: (winterm.back, WinColor.RED, True),
AnsiBack.LIGHTGREEN_EX: (winterm.back, WinColor.GREEN, True),
AnsiBack.LIGHTYELLOW_EX: (winterm.back, WinColor.YELLOW, True),
AnsiBack.LIGHTBLUE_EX: (winterm.back, WinColor.BLUE, True),
AnsiBack.LIGHTMAGENTA_EX: (winterm.back, WinColor.MAGENTA, True),
AnsiBack.LIGHTCYAN_EX: (winterm.back, WinColor.CYAN, True),
AnsiBack.LIGHTWHITE_EX: (winterm.back, WinColor.GREY, True),
}
return dict()
def write(self, text):
if self.strip or self.convert:
self.write_and_convert(text)
else:
self.wrapped.write(text)
self.wrapped.flush()
if self.autoreset:
self.reset_all()
def reset_all(self):
if self.convert:
self.call_win32('m', (0,))
elif not self.strip and not self.stream.closed:
self.wrapped.write(Style.RESET_ALL)
def write_and_convert(self, text):
'''
Write the given text to our wrapped stream, stripping any ANSI
sequences from the text, and optionally converting them into win32
calls.
'''
cursor = 0
text = self.convert_osc(text)
for match in self.ANSI_CSI_RE.finditer(text):
start, end = match.span()
self.write_plain_text(text, cursor, start)
self.convert_ansi(*match.groups())
cursor = end
self.write_plain_text(text, cursor, len(text))
def write_plain_text(self, text, start, end):
if start < end:
self.wrapped.write(text[start:end])
self.wrapped.flush()
def convert_ansi(self, paramstring, command):
if self.convert:
params = self.extract_params(command, paramstring)
self.call_win32(command, params)
def extract_params(self, command, paramstring):
if command in 'Hf':
params = tuple(int(p) if len(p) != 0 else 1 for p in paramstring.split(';'))
while len(params) < 2:
# defaults:
params = params + (1,)
else:
params = tuple(int(p) for p in paramstring.split(';') if len(p) != 0)
if len(params) == 0:
# defaults:
if command in 'JKm':
params = (0,)
elif command in 'ABCD':
params = (1,)
return params
def call_win32(self, command, params):
if command == 'm':
for param in params:
if param in self.win32_calls:
func_args = self.win32_calls[param]
func = func_args[0]
args = func_args[1:]
kwargs = dict(on_stderr=self.on_stderr)
func(*args, **kwargs)
elif command in 'J':
winterm.erase_screen(params[0], on_stderr=self.on_stderr)
elif command in 'K':
winterm.erase_line(params[0], on_stderr=self.on_stderr)
elif command in 'Hf': # cursor position - absolute
winterm.set_cursor_position(params, on_stderr=self.on_stderr)
elif command in 'ABCD': # cursor position - relative
n = params[0]
# A - up, B - down, C - forward, D - back
x, y = {'A': (0, -n), 'B': (0, n), 'C': (n, 0), 'D': (-n, 0)}[command]
winterm.cursor_adjust(x, y, on_stderr=self.on_stderr)
def convert_osc(self, text):
for match in self.ANSI_OSC_RE.finditer(text):
start, end = match.span()
text = text[:start] + text[end:]
paramstring, command = match.groups()
if command == BEL:
if paramstring.count(";") == 1:
params = paramstring.split(";")
# 0 - change title and icon (we will only change title)
# 1 - change icon (we don't support this)
# 2 - change title
if params[0] in '02':
winterm.set_title(params[1])
return text

80
env/lib/python3.12/site-packages/colorama/initialise.py vendored
View File

@@ -1,80 +0,0 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
import atexit
import contextlib
import sys
from .ansitowin32 import AnsiToWin32
orig_stdout = None
orig_stderr = None
wrapped_stdout = None
wrapped_stderr = None
atexit_done = False
def reset_all():
if AnsiToWin32 is not None: # Issue #74: objects might become None at exit
AnsiToWin32(orig_stdout).reset_all()
def init(autoreset=False, convert=None, strip=None, wrap=True):
if not wrap and any([autoreset, convert, strip]):
raise ValueError('wrap=False conflicts with any other arg=True')
global wrapped_stdout, wrapped_stderr
global orig_stdout, orig_stderr
orig_stdout = sys.stdout
orig_stderr = sys.stderr
if sys.stdout is None:
wrapped_stdout = None
else:
sys.stdout = wrapped_stdout = \
wrap_stream(orig_stdout, convert, strip, autoreset, wrap)
if sys.stderr is None:
wrapped_stderr = None
else:
sys.stderr = wrapped_stderr = \
wrap_stream(orig_stderr, convert, strip, autoreset, wrap)
global atexit_done
if not atexit_done:
atexit.register(reset_all)
atexit_done = True
def deinit():
if orig_stdout is not None:
sys.stdout = orig_stdout
if orig_stderr is not None:
sys.stderr = orig_stderr
@contextlib.contextmanager
def colorama_text(*args, **kwargs):
init(*args, **kwargs)
try:
yield
finally:
deinit()
def reinit():
if wrapped_stdout is not None:
sys.stdout = wrapped_stdout
if wrapped_stderr is not None:
sys.stderr = wrapped_stderr
def wrap_stream(stream, convert, strip, autoreset, wrap):
if wrap:
wrapper = AnsiToWin32(stream,
convert=convert, strip=strip, autoreset=autoreset)
if wrapper.should_wrap():
stream = wrapper.stream
return stream

152
env/lib/python3.12/site-packages/colorama/win32.py vendored
View File

@@ -1,152 +0,0 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
# from winbase.h
STDOUT = -11
STDERR = -12
try:
import ctypes
from ctypes import LibraryLoader
windll = LibraryLoader(ctypes.WinDLL)
from ctypes import wintypes
except (AttributeError, ImportError):
windll = None
SetConsoleTextAttribute = lambda *_: None
winapi_test = lambda *_: None
else:
from ctypes import byref, Structure, c_char, POINTER
COORD = wintypes._COORD
class CONSOLE_SCREEN_BUFFER_INFO(Structure):
"""struct in wincon.h."""
_fields_ = [
("dwSize", COORD),
("dwCursorPosition", COORD),
("wAttributes", wintypes.WORD),
("srWindow", wintypes.SMALL_RECT),
("dwMaximumWindowSize", COORD),
]
def __str__(self):
return '(%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d)' % (
self.dwSize.Y, self.dwSize.X
, self.dwCursorPosition.Y, self.dwCursorPosition.X
, self.wAttributes
, self.srWindow.Top, self.srWindow.Left, self.srWindow.Bottom, self.srWindow.Right
, self.dwMaximumWindowSize.Y, self.dwMaximumWindowSize.X
)
_GetStdHandle = windll.kernel32.GetStdHandle
_GetStdHandle.argtypes = [
wintypes.DWORD,
]
_GetStdHandle.restype = wintypes.HANDLE
_GetConsoleScreenBufferInfo = windll.kernel32.GetConsoleScreenBufferInfo
_GetConsoleScreenBufferInfo.argtypes = [
wintypes.HANDLE,
POINTER(CONSOLE_SCREEN_BUFFER_INFO),
]
_GetConsoleScreenBufferInfo.restype = wintypes.BOOL
_SetConsoleTextAttribute = windll.kernel32.SetConsoleTextAttribute
_SetConsoleTextAttribute.argtypes = [
wintypes.HANDLE,
wintypes.WORD,
]
_SetConsoleTextAttribute.restype = wintypes.BOOL
_SetConsoleCursorPosition = windll.kernel32.SetConsoleCursorPosition
_SetConsoleCursorPosition.argtypes = [
wintypes.HANDLE,
COORD,
]
_SetConsoleCursorPosition.restype = wintypes.BOOL
_FillConsoleOutputCharacterA = windll.kernel32.FillConsoleOutputCharacterA
_FillConsoleOutputCharacterA.argtypes = [
wintypes.HANDLE,
c_char,
wintypes.DWORD,
COORD,
POINTER(wintypes.DWORD),
]
_FillConsoleOutputCharacterA.restype = wintypes.BOOL
_FillConsoleOutputAttribute = windll.kernel32.FillConsoleOutputAttribute
_FillConsoleOutputAttribute.argtypes = [
wintypes.HANDLE,
wintypes.WORD,
wintypes.DWORD,
COORD,
POINTER(wintypes.DWORD),
]
_FillConsoleOutputAttribute.restype = wintypes.BOOL
_SetConsoleTitleW = windll.kernel32.SetConsoleTitleW
_SetConsoleTitleW.argtypes = [
wintypes.LPCWSTR
]
_SetConsoleTitleW.restype = wintypes.BOOL
def _winapi_test(handle):
csbi = CONSOLE_SCREEN_BUFFER_INFO()
success = _GetConsoleScreenBufferInfo(
handle, byref(csbi))
return bool(success)
def winapi_test():
return any(_winapi_test(h) for h in
(_GetStdHandle(STDOUT), _GetStdHandle(STDERR)))
def GetConsoleScreenBufferInfo(stream_id=STDOUT):
handle = _GetStdHandle(stream_id)
csbi = CONSOLE_SCREEN_BUFFER_INFO()
success = _GetConsoleScreenBufferInfo(
handle, byref(csbi))
return csbi
def SetConsoleTextAttribute(stream_id, attrs):
handle = _GetStdHandle(stream_id)
return _SetConsoleTextAttribute(handle, attrs)
def SetConsoleCursorPosition(stream_id, position, adjust=True):
position = COORD(*position)
# If the position is out of range, do nothing.
if position.Y <= 0 or position.X <= 0:
return
# Adjust for Windows' SetConsoleCursorPosition:
# 1. being 0-based, while ANSI is 1-based.
# 2. expecting (x,y), while ANSI uses (y,x).
adjusted_position = COORD(position.Y - 1, position.X - 1)
if adjust:
# Adjust for viewport's scroll position
sr = GetConsoleScreenBufferInfo(STDOUT).srWindow
adjusted_position.Y += sr.Top
adjusted_position.X += sr.Left
# Resume normal processing
handle = _GetStdHandle(stream_id)
return _SetConsoleCursorPosition(handle, adjusted_position)
def FillConsoleOutputCharacter(stream_id, char, length, start):
handle = _GetStdHandle(stream_id)
char = c_char(char.encode())
length = wintypes.DWORD(length)
num_written = wintypes.DWORD(0)
# Note that this is hard-coded for ANSI (vs wide) bytes.
success = _FillConsoleOutputCharacterA(
handle, char, length, start, byref(num_written))
return num_written.value
def FillConsoleOutputAttribute(stream_id, attr, length, start):
''' FillConsoleOutputAttribute( hConsole, csbi.wAttributes, dwConSize, coordScreen, &cCharsWritten )'''
handle = _GetStdHandle(stream_id)
attribute = wintypes.WORD(attr)
length = wintypes.DWORD(length)
num_written = wintypes.DWORD(0)
# Note that this is hard-coded for ANSI (vs wide) bytes.
return _FillConsoleOutputAttribute(
handle, attribute, length, start, byref(num_written))
def SetConsoleTitle(title):
return _SetConsoleTitleW(title)

169
env/lib/python3.12/site-packages/colorama/winterm.py vendored
View File

@@ -1,169 +0,0 @@
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
from . import win32
# from wincon.h
class WinColor(object):
BLACK = 0
BLUE = 1
GREEN = 2
CYAN = 3
RED = 4
MAGENTA = 5
YELLOW = 6
GREY = 7
# from wincon.h
class WinStyle(object):
NORMAL = 0x00 # dim text, dim background
BRIGHT = 0x08 # bright text, dim background
BRIGHT_BACKGROUND = 0x80 # dim text, bright background
class WinTerm(object):
def __init__(self):
self._default = win32.GetConsoleScreenBufferInfo(win32.STDOUT).wAttributes
self.set_attrs(self._default)
self._default_fore = self._fore
self._default_back = self._back
self._default_style = self._style
# In order to emulate LIGHT_EX in windows, we borrow the BRIGHT style.
# So that LIGHT_EX colors and BRIGHT style do not clobber each other,
# we track them separately, since LIGHT_EX is overwritten by Fore/Back
# and BRIGHT is overwritten by Style codes.
self._light = 0
def get_attrs(self):
return self._fore + self._back * 16 + (self._style | self._light)
def set_attrs(self, value):
self._fore = value & 7
self._back = (value >> 4) & 7
self._style = value & (WinStyle.BRIGHT | WinStyle.BRIGHT_BACKGROUND)
def reset_all(self, on_stderr=None):
self.set_attrs(self._default)
self.set_console(attrs=self._default)
self._light = 0
def fore(self, fore=None, light=False, on_stderr=False):
if fore is None:
fore = self._default_fore
self._fore = fore
# Emulate LIGHT_EX with BRIGHT Style
if light:
self._light |= WinStyle.BRIGHT
else:
self._light &= ~WinStyle.BRIGHT
self.set_console(on_stderr=on_stderr)
def back(self, back=None, light=False, on_stderr=False):
if back is None:
back = self._default_back
self._back = back
# Emulate LIGHT_EX with BRIGHT_BACKGROUND Style
if light:
self._light |= WinStyle.BRIGHT_BACKGROUND
else:
self._light &= ~WinStyle.BRIGHT_BACKGROUND
self.set_console(on_stderr=on_stderr)
def style(self, style=None, on_stderr=False):
if style is None:
style = self._default_style
self._style = style
self.set_console(on_stderr=on_stderr)
def set_console(self, attrs=None, on_stderr=False):
if attrs is None:
attrs = self.get_attrs()
handle = win32.STDOUT
if on_stderr:
handle = win32.STDERR
win32.SetConsoleTextAttribute(handle, attrs)
def get_position(self, handle):
position = win32.GetConsoleScreenBufferInfo(handle).dwCursorPosition
# Because Windows coordinates are 0-based,
# and win32.SetConsoleCursorPosition expects 1-based.
position.X += 1
position.Y += 1
return position
def set_cursor_position(self, position=None, on_stderr=False):
if position is None:
# I'm not currently tracking the position, so there is no default.
# position = self.get_position()
return
handle = win32.STDOUT
if on_stderr:
handle = win32.STDERR
win32.SetConsoleCursorPosition(handle, position)
def cursor_adjust(self, x, y, on_stderr=False):
handle = win32.STDOUT
if on_stderr:
handle = win32.STDERR
position = self.get_position(handle)
adjusted_position = (position.Y + y, position.X + x)
win32.SetConsoleCursorPosition(handle, adjusted_position, adjust=False)
def erase_screen(self, mode=0, on_stderr=False):
# 0 should clear from the cursor to the end of the screen.
# 1 should clear from the cursor to the beginning of the screen.
# 2 should clear the entire screen, and move cursor to (1,1)
handle = win32.STDOUT
if on_stderr:
handle = win32.STDERR
csbi = win32.GetConsoleScreenBufferInfo(handle)
# get the number of character cells in the current buffer
cells_in_screen = csbi.dwSize.X * csbi.dwSize.Y
# get number of character cells before current cursor position
cells_before_cursor = csbi.dwSize.X * csbi.dwCursorPosition.Y + csbi.dwCursorPosition.X
if mode == 0:
from_coord = csbi.dwCursorPosition
cells_to_erase = cells_in_screen - cells_before_cursor
elif mode == 1:
from_coord = win32.COORD(0, 0)
cells_to_erase = cells_before_cursor
elif mode == 2:
from_coord = win32.COORD(0, 0)
cells_to_erase = cells_in_screen
else:
# invalid mode
return
# fill the entire screen with blanks
win32.FillConsoleOutputCharacter(handle, ' ', cells_to_erase, from_coord)
# now set the buffer's attributes accordingly
win32.FillConsoleOutputAttribute(handle, self.get_attrs(), cells_to_erase, from_coord)
if mode == 2:
# put the cursor where needed
win32.SetConsoleCursorPosition(handle, (1, 1))
def erase_line(self, mode=0, on_stderr=False):
# 0 should clear from the cursor to the end of the line.
# 1 should clear from the cursor to the beginning of the line.
# 2 should clear the entire line.
handle = win32.STDOUT
if on_stderr:
handle = win32.STDERR
csbi = win32.GetConsoleScreenBufferInfo(handle)
if mode == 0:
from_coord = csbi.dwCursorPosition
cells_to_erase = csbi.dwSize.X - csbi.dwCursorPosition.X
elif mode == 1:
from_coord = win32.COORD(0, csbi.dwCursorPosition.Y)
cells_to_erase = csbi.dwCursorPosition.X
elif mode == 2:
from_coord = win32.COORD(0, csbi.dwCursorPosition.Y)
cells_to_erase = csbi.dwSize.X
else:
# invalid mode
return
# fill the entire screen with blanks
win32.FillConsoleOutputCharacter(handle, ' ', cells_to_erase, from_coord)
# now set the buffer's attributes accordingly
win32.FillConsoleOutputAttribute(handle, self.get_attrs(), cells_to_erase, from_coord)
def set_title(self, title):
win32.SetConsoleTitle(title)

1
env/lib/python3.12/site-packages/idna-3.3.dist-info/INSTALLER vendored
View File

@@ -1 +0,0 @@
pip

29
env/lib/python3.12/site-packages/idna-3.3.dist-info/LICENSE.md vendored
View File

@@ -1,29 +0,0 @@
BSD 3-Clause License
Copyright (c) 2013-2021, Kim Davies
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
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.

236
env/lib/python3.12/site-packages/idna-3.3.dist-info/METADATA vendored
View File

@@ -1,236 +0,0 @@
Metadata-Version: 2.1
Name: idna
Version: 3.3
Summary: Internationalized Domain Names in Applications (IDNA)
Home-page: https://github.com/kjd/idna
Author: Kim Davies
Author-email: kim@cynosure.com.au
License: BSD-3-Clause
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: System Administrators
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
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 :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Internet :: Name Service (DNS)
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Utilities
Requires-Python: >=3.5
License-File: LICENSE.md
Internationalized Domain Names in Applications (IDNA)
=====================================================
Support for the Internationalised Domain Names in Applications
(IDNA) protocol as specified in `RFC 5891 <https://tools.ietf.org/html/rfc5891>`_.
This is the latest version of the protocol and is sometimes referred to as
“IDNA 2008”.
This library also provides support for Unicode Technical Standard 46,
`Unicode IDNA Compatibility Processing <https://unicode.org/reports/tr46/>`_.
This acts as a suitable replacement for the “encodings.idna” module that
comes with the Python standard library, but which only supports the
older superseded IDNA specification (`RFC 3490 <https://tools.ietf.org/html/rfc3490>`_).
Basic functions are simply executed:
.. code-block:: pycon
>>> import idna
>>> idna.encode('ドメイン.テスト')
b'xn--eckwd4c7c.xn--zckzah'
>>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
ドメイン.テスト
Installation
------------
To install this library, you can use pip:
.. code-block:: bash
$ pip install idna
Alternatively, you can install the package using the bundled setup script:
.. code-block:: bash
$ python setup.py install
Usage
-----
For typical usage, the ``encode`` and ``decode`` functions will take a domain
name argument and perform a conversion to A-labels or U-labels respectively.
.. code-block:: pycon
>>> import idna
>>> idna.encode('ドメイン.テスト')
b'xn--eckwd4c7c.xn--zckzah'
>>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
ドメイン.テスト
You may use the codec encoding and decoding methods using the
``idna.codec`` module:
.. code-block:: pycon
>>> import idna.codec
>>> print('домен.испытание'.encode('idna'))
b'xn--d1acufc.xn--80akhbyknj4f'
>>> print(b'xn--d1acufc.xn--80akhbyknj4f'.decode('idna'))
домен.испытание
Conversions can be applied at a per-label basis using the ``ulabel`` or ``alabel``
functions if necessary:
.. code-block:: pycon
>>> idna.alabel('测试')
b'xn--0zwm56d'
Compatibility Mapping (UTS #46)
+++++++++++++++++++++++++++++++
As described in `RFC 5895 <https://tools.ietf.org/html/rfc5895>`_, the IDNA
specification does not normalize input from different potential ways a user
may input a domain name. This functionality, known as a “mapping”, is
considered by the specification to be a local user-interface issue distinct
from IDNA conversion functionality.
This library provides one such mapping, that was developed by the Unicode
Consortium. Known as `Unicode IDNA Compatibility Processing <https://unicode.org/reports/tr46/>`_,
it provides for both a regular mapping for typical applications, as well as
a transitional mapping to help migrate from older IDNA 2003 applications.
For example, “Königsgäßchen” is not a permissible label as *LATIN CAPITAL
LETTER K* is not allowed (nor are capital letters in general). UTS 46 will
convert this into lower case prior to applying the IDNA conversion.
.. code-block:: pycon
>>> import idna
>>> idna.encode('Königsgäßchen')
...
idna.core.InvalidCodepoint: Codepoint U+004B at position 1 of 'Königsgäßchen' not allowed
>>> idna.encode('Königsgäßchen', uts46=True)
b'xn--knigsgchen-b4a3dun'
>>> print(idna.decode('xn--knigsgchen-b4a3dun'))
königsgäßchen
Transitional processing provides conversions to help transition from the older
2003 standard to the current standard. For example, in the original IDNA
specification, the *LATIN SMALL LETTER SHARP S* (ß) was converted into two
*LATIN SMALL LETTER S* (ss), whereas in the current IDNA specification this
conversion is not performed.
.. code-block:: pycon
>>> idna.encode('Königsgäßchen', uts46=True, transitional=True)
'xn--knigsgsschen-lcb0w'
Implementors should use transitional processing with caution, only in rare
cases where conversion from legacy labels to current labels must be performed
(i.e. IDNA implementations that pre-date 2008). For typical applications
that just need to convert labels, transitional processing is unlikely to be
beneficial and could produce unexpected incompatible results.
``encodings.idna`` Compatibility
++++++++++++++++++++++++++++++++
Function calls from the Python built-in ``encodings.idna`` module are
mapped to their IDNA 2008 equivalents using the ``idna.compat`` module.
Simply substitute the ``import`` clause in your code to refer to the
new module name.
Exceptions
----------
All errors raised during the conversion following the specification should
raise an exception derived from the ``idna.IDNAError`` base class.
More specific exceptions that may be generated as ``idna.IDNABidiError``
when the error reflects an illegal combination of left-to-right and
right-to-left characters in a label; ``idna.InvalidCodepoint`` when
a specific codepoint is an illegal character in an IDN label (i.e.
INVALID); and ``idna.InvalidCodepointContext`` when the codepoint is
illegal based on its positional context (i.e. it is CONTEXTO or CONTEXTJ
but the contextual requirements are not satisfied.)
Building and Diagnostics
------------------------
The IDNA and UTS 46 functionality relies upon pre-calculated lookup
tables for performance. These tables are derived from computing against
eligibility criteria in the respective standards. These tables are
computed using the command-line script ``tools/idna-data``.
This tool will fetch relevant codepoint data from the Unicode repository
and perform the required calculations to identify eligibility. There are
three main modes:
* ``idna-data make-libdata``. Generates ``idnadata.py`` and ``uts46data.py``,
the pre-calculated lookup tables using for IDNA and UTS 46 conversions. Implementors
who wish to track this library against a different Unicode version may use this tool
to manually generate a different version of the ``idnadata.py`` and ``uts46data.py``
files.
* ``idna-data make-table``. Generate a table of the IDNA disposition
(e.g. PVALID, CONTEXTJ, CONTEXTO) in the format found in Appendix B.1 of RFC
5892 and the pre-computed tables published by `IANA <https://www.iana.org/>`_.
* ``idna-data U+0061``. Prints debugging output on the various properties
associated with an individual Unicode codepoint (in this case, U+0061), that are
used to assess the IDNA and UTS 46 status of a codepoint. This is helpful in debugging
or analysis.
The tool accepts a number of arguments, described using ``idna-data -h``. Most notably,
the ``--version`` argument allows the specification of the version of Unicode to use
in computing the table data. For example, ``idna-data --version 9.0.0 make-libdata``
will generate library data against Unicode 9.0.0.
Additional Notes
----------------
* **Packages**. The latest tagged release version is published in the
`Python Package Index <https://pypi.org/project/idna/>`_.
* **Version support**. This library supports Python 3.5 and higher. As this library
serves as a low-level toolkit for a variety of applications, many of which strive
for broad compatibility with older Python versions, there is no rush to remove
older intepreter support. Removing support for older versions should be well
justified in that the maintenance burden has become too high.
* **Python 2**. Python 2 is supported by version 2.x of this library. While active
development of the version 2.x series has ended, notable issues being corrected
may be backported to 2.x. Use "idna<3" in your requirements file if you need this
library for a Python 2 application.
* **Testing**. The library has a test suite based on each rule of the IDNA specification, as
well as tests that are provided as part of the Unicode Technical Standard 46,
`Unicode IDNA Compatibility Processing <https://unicode.org/reports/tr46/>`_.
* **Emoji**. It is an occasional request to support emoji domains in this library. Encoding
of symbols like emoji is expressly prohibited by the technical standard IDNA 2008 and
emoji domains are broadly phased out across the domain industry due to associated security
risks. For now, applications that wish need to support these non-compliant labels may
wish to consider trying the encode/decode operation in this library first, and then falling
back to using `encodings.idna`. See `the Github project <https://github.com/kjd/idna/issues/18>`_
for more discussion.

24
env/lib/python3.12/site-packages/idna-3.3.dist-info/RECORD vendored
View File

@@ -1,24 +0,0 @@
idna-3.3.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
idna-3.3.dist-info/LICENSE.md,sha256=otbk2UC9JNvnuWRc3hmpeSzFHbeuDVrNMBrIYMqj6DY,1523
idna-3.3.dist-info/METADATA,sha256=BdqiAf8ou4x1nzIHp2_sDfXWjl7BrSUGpOeVzbYHQuQ,9765
idna-3.3.dist-info/RECORD,,
idna-3.3.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
idna-3.3.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
idna-3.3.dist-info/top_level.txt,sha256=jSag9sEDqvSPftxOQy-ABfGV_RSy7oFh4zZJpODV8k0,5
idna/__init__.py,sha256=KJQN1eQBr8iIK5SKrJ47lXvxG0BJ7Lm38W4zT0v_8lk,849
idna/__pycache__/__init__.cpython-312.pyc,,
idna/__pycache__/codec.cpython-312.pyc,,
idna/__pycache__/compat.cpython-312.pyc,,
idna/__pycache__/core.cpython-312.pyc,,
idna/__pycache__/idnadata.cpython-312.pyc,,
idna/__pycache__/intranges.cpython-312.pyc,,
idna/__pycache__/package_data.cpython-312.pyc,,
idna/__pycache__/uts46data.cpython-312.pyc,,
idna/codec.py,sha256=6ly5odKfqrytKT9_7UrlGklHnf1DSK2r9C6cSM4sa28,3374
idna/compat.py,sha256=0_sOEUMT4CVw9doD3vyRhX80X19PwqFoUBs7gWsFME4,321
idna/core.py,sha256=RFIkY-HhFZaDoBEFjGwyGd_vWI04uOAQjnzueMWqwOU,12795
idna/idnadata.py,sha256=fzMzkCea2xieVxcrjngJ-2pLsKQNejPCZFlBajIuQdw,44025
idna/intranges.py,sha256=YBr4fRYuWH7kTKS2tXlFjM24ZF1Pdvcir-aywniInqg,1881
idna/package_data.py,sha256=szxQhV0ZD0nKJ84Kuobw3l8q4_KeCyXjFRdpwIpKZmw,21
idna/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
idna/uts46data.py,sha256=o-D7V-a0fOLZNd7tvxof6MYfUd0TBZzE2bLR5XO67xU,204400

0
env/lib/python3.12/site-packages/idna-3.3.dist-info/REQUESTED vendored
View File

5
env/lib/python3.12/site-packages/idna-3.3.dist-info/WHEEL vendored
View File

@@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.0)
Root-Is-Purelib: true
Tag: py3-none-any

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