daniel/tamigo-cli
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases 3 Wiki Activity

Initial commit: Tamigo CLI with Gitea Actions and global installation support

Browse Source
This commit is contained in:
Daniel Dybing
2026-03-11 12:07:08 +01:00
commit 146b79660d
2675 changed files with 462625 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.env Normal file
View File

@@ -0,0 +1,2 @@
TAMIGO_EMAIL=daniel.dybing@me.com
TAMIGO_PASSWORD=Rarlinkiso966!

59
.gitea/workflows/build.yml Normal file
View File

@@ -0,0 +1,59 @@
name: Build Tamigo CLI
on:
push:
branches: [ "main", "master" ]
pull_request:
branches: [ "main", "master" ]
workflow_dispatch:
jobs:
build-linux:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.12'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
- name: Build with PyInstaller
run: |
pyinstaller --onefile --name tamigo-cli tamigo.py
- name: Upload artifact
uses: actions/upload-artifact@v4
with:
name: tamigo-cli-linux
path: dist/tamigo-cli
build-windows:
runs-on: windows-latest
steps:
- uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.12'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
- name: Build with PyInstaller
run: |
pyinstaller --onefile --name tamigo-cli tamigo.py
- name: Upload artifact
uses: actions/upload-artifact@v4
with:
name: tamigo-cli-windows
path: dist/tamigo-cli.exe

BIN
Application Services - Web Services (API) tamigo Help Center.pdf Normal file
View File

Binary file not shown.

BIN
Application Services - Web Services (API) tamigo Help Center.pdf:Zone.Identifier Normal file
View File

Binary file not shown.

31
README.md Normal file
View File

@@ -0,0 +1,31 @@
# Tamigo CLI
A small CLI application to interface with Tamigo.
## Features
- Login with your Tamigo credentials.
- Calculate work days (check-ins) for the current month, year, and last 365 days.
- View recent work shifts.
- View your Tamigo profile info.
## Installation
1. Create a virtual environment:
```bash
python3 -m venv venv
source venv/bin/activate
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
## Usage
Run the application:
```bash
python tamigo.py
```
Follow the prompts to log in and select actions from the menu.

BIN
User Services - Web Services (API) – tamigo Help Center nov 2024.pdf Normal file
View File

Binary file not shown.

BIN
User Services - Web Services (API) – tamigo Help Center nov 2024.pdf:Zone.Identifier Normal file
View File

Binary file not shown.

19
pyproject.toml Normal file
View File

@@ -0,0 +1,19 @@
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "tamigo-cli"
version = "0.1.0"
description = "A CLI tool for Tamigo"
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
"requests",
"questionary",
"rich",
"python-dotenv",
]
[project.scripts]
tamigo-cli = "tamigo:main"

5
requirements.txt Normal file
View File

@@ -0,0 +1,5 @@
requests
questionary
rich
python-dotenv
pyinstaller

346
tamigo.py Normal file
View File

@@ -0,0 +1,346 @@
import requests
import questionary
from rich.console import Console
from rich.table import Table
import json
import os
import re
from datetime import datetime, timedelta
from dotenv import load_dotenv
# Load environment variables from .env if it exists
load_dotenv()
console = Console()
BASE_URL = "https://api.tamigo.com"
def parse_tamigo_date(date_str):
"""
Parses Tamigo date formats:
- /Date(1600898400000+0200)/
- 2023-10-27T08:00:00
"""
if not date_str:
return None
# Handle /Date(1600898400000+0200)/
match = re.search(r"/Date\((\d+)([+-]\d+)?\)/", date_str)
if match:
ms = int(match.group(1))
# Convert ms to seconds
return datetime.fromtimestamp(ms / 1000.0)
# Handle ISO format
try:
# datetime.fromisoformat handles T and optional Z/+offset in Python 3.7+
return datetime.fromisoformat(date_str.replace("Z", "+00:00"))
except:
return None
class TamigoClient:
def __init__(self):
self.session_token = None
self.user_info = None
self.employee_id = None
def login(self, email, password):
# Try different URL patterns based on docs and common patterns
urls = [
f"{BASE_URL}/login/application",
f"{BASE_URL}/Login",
f"{BASE_URL}/Login/",
f"{BASE_URL}/login",
f"{BASE_URL}/login/"
]
last_error = ""
for url in urls:
payload = {
"Email": email,
"Password": password,
"Name": "TamigoCLI", # For /login/application
"Key": password # For /login/application
}
try:
headers = {
"Content-Type": "application/json",
"Accept": "application/json"
}
response = requests.post(url, json=payload, headers=headers, timeout=15)
if response.status_code == 200:
try:
data = response.json()
# Token can be in different fields
self.session_token = data.get("SessionToken") or data.get("securitytoken") or data.get("Token")
if self.session_token:
self.user_info = data
self.employee_id = data.get("EmployeeId")
return True
except json.JSONDecodeError:
text = response.text.strip().strip('"')
if text and len(text) > 20:
self.session_token = text
self.user_info = {"Email": email}
return True
last_error = f"URL: {url}, Status: {response.status_code}"
except Exception as e:
last_error = f"URL: {url}, Error: {str(e)}"
console.print(f"[red]Login failed.[/red]")
console.print(f"[dim]Debug: {last_error}[/dim]")
return False
def get_employee_id(self):
if self.employee_id:
return self.employee_id
headers = {
"x-tamigo-token": self.session_token,
"securitytoken": self.session_token,
"Accept": "application/json"
}
# Method A: User Info from Login
if self.user_info and self.user_info.get("EmployeeId"):
self.employee_id = self.user_info.get("EmployeeId")
return self.employee_id
# Method B: My Overview
url = f"{BASE_URL}/shifts/myoverview"
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
shifts = response.json()
if shifts and len(shifts) > 0:
self.employee_id = shifts[0].get("EmployeeId")
return self.employee_id
except:
pass
return None
def get_employee_actual_shifts(self, start_date_dt, end_date_dt):
"""
Fetches actual worked shifts using employee-accessible endpoints.
Tamigo's 'past' endpoint often limits to 60 days, so we fetch in chunks.
"""
if not self.session_token:
return None
headers = {
"x-tamigo-token": self.session_token,
"securitytoken": self.session_token,
"Accept": "application/json"
}
all_shifts = []
days_diff = (end_date_dt - start_date_dt).days
# Fetch in 60-day chunks moving backwards from end_date
for i in range(0, days_diff + 1, 60):
target_date = (end_date_dt - timedelta(days=i)).strftime("%Y-%m-%d")
# Stop if we've moved past the start date
current_dt = end_date_dt - timedelta(days=i)
if current_dt < start_date_dt - timedelta(days=60):
break
url = f"{BASE_URL}/actualshifts/past/{target_date}"
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
data = response.json()
if isinstance(data, list):
all_shifts.extend(data)
elif response.status_code == 401:
response = requests.get(url, params={"securitytoken": self.session_token})
if response.status_code == 200:
all_shifts.extend(response.json())
except Exception as e:
console.print(f"[dim]Failed to fetch chunk at {target_date}: {e}[/dim]")
# Supplement with /shifts/period/
start_str = start_date_dt.strftime("%Y-%m-%d")
end_str = end_date_dt.strftime("%Y-%m-%d")
url_period = f"{BASE_URL}/shifts/period/{start_str}/{end_str}"
try:
response = requests.get(url_period, headers=headers)
if response.status_code == 200:
data = response.json()
if isinstance(data, list):
all_shifts.extend(data)
except:
pass
return all_shifts
def calculate_checkins(client):
range_choice = questionary.select(
"Select period:",
choices=[
"Last 365 days",
"Last 30 days",
"This Month",
"This Year",
"Custom range..."
]
).ask()
end_date_dt = datetime.now()
if range_choice == "Last 365 days":
start_date_dt = end_date_dt - timedelta(days=365)
elif range_choice == "Last 30 days":
start_date_dt = end_date_dt - timedelta(days=30)
elif range_choice == "This Month":
start_date_dt = end_date_dt.replace(day=1)
elif range_choice == "This Year":
start_date_dt = end_date_dt.replace(month=1, day=1)
else:
# Custom range
while True:
start_str = questionary.text("Start date (YYYY-MM-DD):", default=(datetime.now() - timedelta(days=30)).strftime("%Y-%m-%d")).ask()
end_str = questionary.text("End date (YYYY-MM-DD):", default=datetime.now().strftime("%Y-%m-%d")).ask()
try:
start_date_dt = datetime.strptime(start_str, "%Y-%m-%d")
end_date_dt = datetime.strptime(end_str, "%Y-%m-%d")
if start_date_dt > end_date_dt:
console.print("[red]Start date must be before end date![/red]")
continue
break
except ValueError:
console.print("[red]Invalid format. Please use YYYY-MM-DD.[/red]")
with console.status(f"[bold green]Fetching work history from {start_date_dt.strftime('%Y-%m-%d')} to {end_date_dt.strftime('%Y-%m-%d')}..."):
data = client.get_employee_actual_shifts(start_date_dt, end_date_dt)
if data:
work_days = {} # date_str -> {hours, text}
# Filter data to ensure it's strictly within our requested range
# (Since the API chunks might return slightly more)
requested_start = start_date_dt.date()
requested_end = end_date_dt.date()
for item in data:
raw_date = item.get("Date") or item.get("StartTime") or item.get("CheckInTime")
dt = parse_tamigo_date(raw_date)
if dt:
item_date = dt.date()
if not (requested_start <= item_date <= requested_end):
continue
date_str = dt.strftime("%Y-%m-%d")
is_absent = item.get("IsAbsent", False)
hours = (item.get("ActualShiftHours") or
item.get("CheckInOutShiftHours") or
item.get("Hours") or 0)
if hours == 0 and item.get("StartTime") and item.get("EndTime"):
st = parse_tamigo_date(item.get("StartTime"))
et = parse_tamigo_date(item.get("EndTime"))
if st and et:
hours = (et - st).total_seconds() / 3600.0
has_actual = False
if hours > 0 or item.get("CheckInTime") or item.get("ActualStartTime"):
has_actual = True
if item.get("ActualShift") and item["ActualShift"].get("Shift", 0) > 0:
has_actual = True
hours = item["ActualShift"]["Shift"]
if item.get("StartTime") and not is_absent:
has_actual = True
if has_actual and not is_absent:
if date_str not in work_days:
work_days[date_str] = {
"hours": float(hours),
"text": item.get("ActualShiftText") or item.get("ActivityName") or item.get("DepartmentName") or "Worked"
}
else:
work_days[date_str]["hours"] += float(hours)
if not work_days:
console.print("[yellow]No work records found for this period.[/yellow]")
return
all_dates = sorted(work_days.keys(), reverse=True)
table = Table(title="Worked Days in Period", show_header=True, header_style="bold magenta")
table.add_column("Date", style="cyan")
table.add_column("Hours", justify="right")
table.add_column("Details", style="dim")
for day in all_dates:
info = work_days[day]
table.add_row(day, f"{info['hours']:.2f}", str(info['text']))
console.print(table)
console.print(f"\n[bold]Work Statistics:[/bold]")
console.print(f" - Period: [cyan]{start_date_dt.strftime('%Y-%m-%d')} to {end_date_dt.strftime('%Y-%m-%d')}[/cyan]")
console.print(f" - Days Worked: [bold green]{len(all_dates)}[/bold green]")
total_hours = sum(d['hours'] for d in work_days.values())
console.print(f" - Total Hours: [bold green]{total_hours:.2f}[/bold green]")
else:
console.print("[yellow]Could not retrieve any shift data for this period.[/yellow]")
def show_profile(client):
if client.user_info:
console.print_json(data=client.user_info)
else:
console.print("[yellow]No profile info available. Are you logged in?[/yellow]")
def main():
client = TamigoClient()
console.print("[bold blue]Welcome to Tamigo CLI[/bold blue]")
email = os.getenv("TAMIGO_EMAIL")
if not email:
email = questionary.text("Email:").ask()
password = os.getenv("TAMIGO_PASSWORD")
if not password:
password = questionary.password("Password:").ask()
if not email or not password:
return
with console.status("[bold green]Logging in..."):
success = client.login(email, password)
if success:
console.print("[bold green]Login successful![/bold green]")
menu(client)
else:
console.print("[bold red]Login failed. Please check your credentials.[/bold red]")
def menu(client):
while True:
choice = questionary.select(
"What would you like to do?",
choices=[
"Calculate actual work days",
"Show profile info",
"Logout and Exit"
]
).ask()
if choice == "Calculate actual work days":
calculate_checkins(client)
elif choice == "Show profile info":
show_profile(client)
else:
break
if __name__ == "__main__":
main()

247
venv/bin/Activate.ps1 Normal file
View File

@@ -0,0 +1,247 @@
<#
.Synopsis
Activate a Python virtual environment for the current PowerShell session.
.Description
Pushes the python executable for a virtual environment to the front of the
$Env:PATH environment variable and sets the prompt to signify that you are
in a Python virtual environment. Makes use of the command line switches as
well as the `pyvenv.cfg` file values present in the virtual environment.
.Parameter VenvDir
Path to the directory that contains the virtual environment to activate. The
default value for this is the parent of the directory that the Activate.ps1
script is located within.
.Parameter Prompt
The prompt prefix to display when this virtual environment is activated. By
default, this prompt is the name of the virtual environment folder (VenvDir)
surrounded by parentheses and followed by a single space (ie. '(.venv) ').
.Example
Activate.ps1
Activates the Python virtual environment that contains the Activate.ps1 script.
.Example
Activate.ps1 -Verbose
Activates the Python virtual environment that contains the Activate.ps1 script,
and shows extra information about the activation as it executes.
.Example
Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
Activates the Python virtual environment located in the specified location.
.Example
Activate.ps1 -Prompt "MyPython"
Activates the Python virtual environment that contains the Activate.ps1 script,
and prefixes the current prompt with the specified string (surrounded in
parentheses) while the virtual environment is active.
.Notes
On Windows, it may be required to enable this Activate.ps1 script by setting the
execution policy for the user. You can do this by issuing the following PowerShell
command:
PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
For more information on Execution Policies:
https://go.microsoft.com/fwlink/?LinkID=135170
#>
Param(
[Parameter(Mandatory = $false)]
[String]
$VenvDir,
[Parameter(Mandatory = $false)]
[String]
$Prompt
)
<# Function declarations --------------------------------------------------- #>
<#
.Synopsis
Remove all shell session elements added by the Activate script, including the
addition of the virtual environment's Python executable from the beginning of
the PATH variable.
.Parameter NonDestructive
If present, do not remove this function from the global namespace for the
session.
#>
function global:deactivate ([switch]$NonDestructive) {
# Revert to original values
# The prior prompt:
if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
}
# The prior PYTHONHOME:
if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
}
# The prior PATH:
if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
Remove-Item -Path Env:_OLD_VIRTUAL_PATH
}
# Just remove the VIRTUAL_ENV altogether:
if (Test-Path -Path Env:VIRTUAL_ENV) {
Remove-Item -Path env:VIRTUAL_ENV
}
# Just remove VIRTUAL_ENV_PROMPT altogether.
if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
Remove-Item -Path env:VIRTUAL_ENV_PROMPT
}
# Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
}
# Leave deactivate function in the global namespace if requested:
if (-not $NonDestructive) {
Remove-Item -Path function:deactivate
}
}
<#
.Description
Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
given folder, and returns them in a map.
For each line in the pyvenv.cfg file, if that line can be parsed into exactly
two strings separated by `=` (with any amount of whitespace surrounding the =)
then it is considered a `key = value` line. The left hand string is the key,
the right hand is the value.
If the value starts with a `'` or a `"` then the first and last character is
stripped from the value before being captured.
.Parameter ConfigDir
Path to the directory that contains the `pyvenv.cfg` file.
#>
function Get-PyVenvConfig(
[String]
$ConfigDir
) {
Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
# Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
$pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
# An empty map will be returned if no config file is found.
$pyvenvConfig = @{ }
if ($pyvenvConfigPath) {
Write-Verbose "File exists, parse `key = value` lines"
$pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
$pyvenvConfigContent | ForEach-Object {
$keyval = $PSItem -split "\s*=\s*", 2
if ($keyval[0] -and $keyval[1]) {
$val = $keyval[1]
# Remove extraneous quotations around a string value.
if ("'""".Contains($val.Substring(0, 1))) {
$val = $val.Substring(1, $val.Length - 2)
}
$pyvenvConfig[$keyval[0]] = $val
Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
}
}
}
return $pyvenvConfig
}
<# Begin Activate script --------------------------------------------------- #>
# Determine the containing directory of this script
$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
$VenvExecDir = Get-Item -Path $VenvExecPath
Write-Verbose "Activation script is located in path: '$VenvExecPath'"
Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
# Set values required in priority: CmdLine, ConfigFile, Default
# First, get the location of the virtual environment, it might not be
# VenvExecDir if specified on the command line.
if ($VenvDir) {
Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
}
else {
Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
$VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
Write-Verbose "VenvDir=$VenvDir"
}
# Next, read the `pyvenv.cfg` file to determine any required value such
# as `prompt`.
$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
# Next, set the prompt from the command line, or the config file, or
# just use the name of the virtual environment folder.
if ($Prompt) {
Write-Verbose "Prompt specified as argument, using '$Prompt'"
}
else {
Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
Write-Verbose " Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
$Prompt = $pyvenvCfg['prompt'];
}
else {
Write-Verbose " Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
Write-Verbose " Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
$Prompt = Split-Path -Path $venvDir -Leaf
}
}
Write-Verbose "Prompt = '$Prompt'"
Write-Verbose "VenvDir='$VenvDir'"
# Deactivate any currently active virtual environment, but leave the
# deactivate function in place.
deactivate -nondestructive
# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
# that there is an activated venv.
$env:VIRTUAL_ENV = $VenvDir
if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
Write-Verbose "Setting prompt to '$Prompt'"
# Set the prompt to include the env name
# Make sure _OLD_VIRTUAL_PROMPT is global
function global:_OLD_VIRTUAL_PROMPT { "" }
Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
function global:prompt {
Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
_OLD_VIRTUAL_PROMPT
}
$env:VIRTUAL_ENV_PROMPT = $Prompt
}
# Clear PYTHONHOME
if (Test-Path -Path Env:PYTHONHOME) {
Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
Remove-Item -Path Env:PYTHONHOME
}
# Add the venv to the PATH
Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

70
venv/bin/activate Normal file
View File

@@ -0,0 +1,70 @@
# This file must be used with "source bin/activate" *from bash*
# You cannot run it directly
deactivate () {
# reset old environment variables
if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
PATH="${_OLD_VIRTUAL_PATH:-}"
export PATH
unset _OLD_VIRTUAL_PATH
fi
if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
export PYTHONHOME
unset _OLD_VIRTUAL_PYTHONHOME
fi
# Call hash to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
hash -r 2> /dev/null
if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
PS1="${_OLD_VIRTUAL_PS1:-}"
export PS1
unset _OLD_VIRTUAL_PS1
fi
unset VIRTUAL_ENV
unset VIRTUAL_ENV_PROMPT
if [ ! "${1:-}" = "nondestructive" ] ; then
# Self destruct!
unset -f deactivate
fi
}
# unset irrelevant variables
deactivate nondestructive
# on Windows, a path can contain colons and backslashes and has to be converted:
if [ "${OSTYPE:-}" = "cygwin" ] || [ "${OSTYPE:-}" = "msys" ] ; then
# transform D:\path\to\venv to /d/path/to/venv on MSYS
# and to /cygdrive/d/path/to/venv on Cygwin
export VIRTUAL_ENV=$(cygpath /home/daniel/Projects/tamigo-cli/venv)
else
# use the path as-is
export VIRTUAL_ENV=/home/daniel/Projects/tamigo-cli/venv
fi
_OLD_VIRTUAL_PATH="$PATH"
PATH="$VIRTUAL_ENV/"bin":$PATH"
export PATH
# unset PYTHONHOME if set
# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
# could use `if (set -u; : $PYTHONHOME) ;` in bash
if [ -n "${PYTHONHOME:-}" ] ; then
_OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
unset PYTHONHOME
fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1:-}"
PS1='(venv) '"${PS1:-}"
export PS1
VIRTUAL_ENV_PROMPT='(venv) '
export VIRTUAL_ENV_PROMPT
fi
# Call hash to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
hash -r 2> /dev/null

27
venv/bin/activate.csh Normal file
View File

@@ -0,0 +1,27 @@
# This file must be used with "source bin/activate.csh" *from csh*.
# You cannot run it directly.
# Created by Davide Di Blasi <davidedb@gmail.com>.
# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
# Unset irrelevant variables.
deactivate nondestructive
setenv VIRTUAL_ENV /home/daniel/Projects/tamigo-cli/venv
set _OLD_VIRTUAL_PATH="$PATH"
setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
set prompt = '(venv) '"$prompt"
setenv VIRTUAL_ENV_PROMPT '(venv) '
endif
alias pydoc python -m pydoc
rehash

69
venv/bin/activate.fish Normal file
View File

@@ -0,0 +1,69 @@
# This file must be used with "source <venv>/bin/activate.fish" *from fish*
# (https://fishshell.com/). You cannot run it directly.
function deactivate -d "Exit virtual environment and return to normal shell environment"
# reset old environment variables
if test -n "$_OLD_VIRTUAL_PATH"
set -gx PATH $_OLD_VIRTUAL_PATH
set -e _OLD_VIRTUAL_PATH
end
if test -n "$_OLD_VIRTUAL_PYTHONHOME"
set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
set -e _OLD_VIRTUAL_PYTHONHOME
end
if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
set -e _OLD_FISH_PROMPT_OVERRIDE
# prevents error when using nested fish instances (Issue #93858)
if functions -q _old_fish_prompt
functions -e fish_prompt
functions -c _old_fish_prompt fish_prompt
functions -e _old_fish_prompt
end
end
set -e VIRTUAL_ENV
set -e VIRTUAL_ENV_PROMPT
if test "$argv[1]" != "nondestructive"
# Self-destruct!
functions -e deactivate
end
end
# Unset irrelevant variables.
deactivate nondestructive
set -gx VIRTUAL_ENV /home/daniel/Projects/tamigo-cli/venv
set -gx _OLD_VIRTUAL_PATH $PATH
set -gx PATH "$VIRTUAL_ENV/"bin $PATH
# Unset PYTHONHOME if set.
if set -q PYTHONHOME
set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
set -e PYTHONHOME
end
if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
# fish uses a function instead of an env var to generate the prompt.
# Save the current fish_prompt function as the function _old_fish_prompt.
functions -c fish_prompt _old_fish_prompt
# With the original prompt function renamed, we can override with our own.
function fish_prompt
# Save the return status of the last command.
set -l old_status $status
# Output the venv prompt; color taken from the blue of the Python logo.
printf "%s%s%s" (set_color 4B8BBE) '(venv) ' (set_color normal)
# Restore the return status of the previous command.
echo "exit $old_status" | .
# Output the original/"old" prompt.
_old_fish_prompt
end
set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
set -gx VIRTUAL_ENV_PROMPT '(venv) '
end

8
venv/bin/dotenv Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from dotenv.__main__ import cli
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli())

8
venv/bin/markdown-it Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from markdown_it.cli.parse import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
venv/bin/normalizer Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from charset_normalizer.cli import cli_detect
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli_detect())

8
venv/bin/pip Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
venv/bin/pip3 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
venv/bin/pip3.12 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
venv/bin/pygmentize Executable file
View File

@@ -0,0 +1,8 @@
#!/home/daniel/Projects/tamigo-cli/venv/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pygments.cmdline import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

1
venv/bin/python Symbolic link
View File

@@ -0,0 +1 @@
python3

1
venv/bin/python3 Symbolic link
View File

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

1
venv/bin/python3.12 Symbolic link
View File

@@ -0,0 +1 @@
python3

BIN
venv/lib/python3.12/site-packages/81d243bd2c585b0f4821__mypyc.cpython-312-x86_64-linux-gnu.so Executable file
View File

Binary file not shown.

1
venv/lib/python3.12/site-packages/certifi-2026.2.25.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

78
venv/lib/python3.12/site-packages/certifi-2026.2.25.dist-info/METADATA Normal file
View File

@@ -0,0 +1,78 @@
Metadata-Version: 2.4
Name: certifi
Version: 2026.2.25
Summary: Python package for providing Mozilla's CA Bundle.
Home-page: https://github.com/certifi/python-certifi
Author: Kenneth Reitz
Author-email: me@kennethreitz.com
License: MPL-2.0
Project-URL: Source, https://github.com/certifi/python-certifi
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
Classifier: Natural Language :: English
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Python: >=3.7
License-File: LICENSE
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-python
Dynamic: summary
Certifi: Python SSL Certificates
================================
Certifi provides Mozilla's carefully curated collection of Root Certificates for
validating the trustworthiness of SSL certificates while verifying the identity
of TLS hosts. It has been extracted from the `Requests`_ project.
Installation
------------
``certifi`` is available on PyPI. Simply install it with ``pip``::
$ pip install certifi
Usage
-----
To reference the installed certificate authority (CA) bundle, you can use the
built-in function::
>>> import certifi
>>> certifi.where()
'/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
Or from the command line::
$ python -m certifi
/usr/local/lib/python3.7/site-packages/certifi/cacert.pem
Enjoy!
.. _`Requests`: https://requests.readthedocs.io/en/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.

14
venv/lib/python3.12/site-packages/certifi-2026.2.25.dist-info/RECORD Normal file
View File

@@ -0,0 +1,14 @@
certifi-2026.2.25.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
certifi-2026.2.25.dist-info/METADATA,sha256=4NMuGXdg_hBiRA3paKVXYcDmE3VXEBWxTvCL2xlDyPU,2474
certifi-2026.2.25.dist-info/RECORD,,
certifi-2026.2.25.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
certifi-2026.2.25.dist-info/licenses/LICENSE,sha256=6TcW2mucDVpKHfYP5pWzcPBpVgPSH2-D8FPkLPwQyvc,989
certifi-2026.2.25.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
certifi/__init__.py,sha256=c9eaYufv1pSLl0Q8QNcMiMLLH4WquDcxdPyKjmI4opY,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=_JFloSQDJj5-v72te-ej6sD6XTJdPHBGXyjTaQByyig,272441
certifi/core.py,sha256=XFXycndG5pf37ayeF8N32HUuDafsyhkVMbO4BAPWHa0,3394
certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

5
venv/lib/python3.12/site-packages/certifi-2026.2.25.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: setuptools (82.0.0)
Root-Is-Purelib: true
Tag: py3-none-any

20
venv/lib/python3.12/site-packages/certifi-2026.2.25.dist-info/licenses/LICENSE Normal file
View File

@@ -0,0 +1,20 @@
This package contains a modified version of ca-bundle.crt:
ca-bundle.crt -- Bundle of CA Root Certificates
This is a bundle of X.509 certificates of public Certificate Authorities
(CA). These were automatically extracted from Mozilla's root certificates
file (certdata.txt). This file can be found in the mozilla source tree:
https://hg.mozilla.org/mozilla-central/file/tip/security/nss/lib/ckfw/builtins/certdata.txt
It contains the certificates in PEM format and therefore
can be directly used with curl / libcurl / php_curl, or with
an Apache+mod_ssl webserver for SSL client authentication.
Just configure this file as the SSLCACertificateFile.#
***** BEGIN LICENSE BLOCK *****
This Source Code Form is subject to the terms of the Mozilla Public License,
v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
one at http://mozilla.org/MPL/2.0/.
***** END LICENSE BLOCK *****
@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

1
venv/lib/python3.12/site-packages/certifi-2026.2.25.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
certifi

4
venv/lib/python3.12/site-packages/certifi/__init__.py Normal file
View File

@@ -0,0 +1,4 @@
from .core import contents, where
__all__ = ["contents", "where"]
__version__ = "2026.02.25"

12
venv/lib/python3.12/site-packages/certifi/__main__.py Normal file
View File

@@ -0,0 +1,12 @@
import argparse
from certifi import contents, where
parser = argparse.ArgumentParser()
parser.add_argument("-c", "--contents", action="store_true")
args = parser.parse_args()
if args.contents:
print(contents())
else:
print(where())

BIN
venv/lib/python3.12/site-packages/certifi/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/certifi/__pycache__/__main__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/certifi/__pycache__/core.cpython-312.pyc Normal file
View File

Binary file not shown.

4494
venv/lib/python3.12/site-packages/certifi/cacert.pem Normal file
View File

File diff suppressed because it is too large Load Diff

83
venv/lib/python3.12/site-packages/certifi/core.py Normal file
View File

@@ -0,0 +1,83 @@
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem or its contents.
"""
import sys
import atexit
def exit_cacert_ctx() -> None:
_CACERT_CTX.__exit__(None, None, None) # type: ignore[union-attr]
if sys.version_info >= (3, 11):
from importlib.resources import as_file, files
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the file
# in cases where we're inside of a zipimport situation until someone
# actually calls where(), but we don't want to re-extract the file
# on every call of where(), so we'll do it once then store it in a
# global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you to
# manage the cleanup of this file, so it doesn't actually return a
# path, it returns a context manager that will give you the path
# when you enter it and will do any cleanup when you leave it. In
# the common case of not needing a temporary file, it will just
# return the file system location and the __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = as_file(files("certifi").joinpath("cacert.pem"))
_CACERT_PATH = str(_CACERT_CTX.__enter__())
atexit.register(exit_cacert_ctx)
return _CACERT_PATH
def contents() -> str:
return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
else:
from importlib.resources import path as get_path, read_text
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the
# file in cases where we're inside of a zipimport situation until
# someone actually calls where(), but we don't want to re-extract
# the file on every call of where(), so we'll do it once then store
# it in a global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you
# to manage the cleanup of this file, so it doesn't actually
# return a path, it returns a context manager that will give
# you the path when you enter it and will do any cleanup when
# you leave it. In the common case of not needing a temporary
# file, it will just return the file system location and the
# __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = get_path("certifi", "cacert.pem")
_CACERT_PATH = str(_CACERT_CTX.__enter__())
atexit.register(exit_cacert_ctx)
return _CACERT_PATH
def contents() -> str:
return read_text("certifi", "cacert.pem", encoding="ascii")

0
venv/lib/python3.12/site-packages/certifi/py.typed Normal file
View File

1
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

782
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/METADATA Normal file
View File

@@ -0,0 +1,782 @@
Metadata-Version: 2.4
Name: charset-normalizer
Version: 3.4.5
Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
Author-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
Maintainer-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
License: MIT
Project-URL: Changelog, https://github.com/jawah/charset_normalizer/blob/master/CHANGELOG.md
Project-URL: Documentation, https://charset-normalizer.readthedocs.io/
Project-URL: Code, https://github.com/jawah/charset_normalizer
Project-URL: Issue tracker, https://github.com/jawah/charset_normalizer/issues
Keywords: encoding,charset,charset-detector,detector,normalization,unicode,chardet,detect
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Typing :: Typed
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode-backport
Dynamic: license-file
<h1 align="center">Charset Detection, for Everyone 👋</h1>
<p align="center">
<sup>The Real First Universal Charset Detector</sup><br>
<a href="https://pypi.org/project/charset-normalizer">
<img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
</a>
<a href="https://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://static.pepy.tech/badge/charset-normalizer/month" />
</a>
<a href="https://bestpractices.coreinfrastructure.org/projects/7297">
<img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
</a>
</p>
<p align="center">
<sup><i>Featured Packages</i></sup><br>
<a href="https://github.com/jawah/niquests">
<img alt="Static Badge" src="https://img.shields.io/badge/Niquests-Most_Advanced_HTTP_Client-cyan">
</a>
<a href="https://github.com/jawah/wassima">
<img alt="Static Badge" src="https://img.shields.io/badge/Wassima-Certifi_Replacement-cyan">
</a>
</p>
<p align="center">
<sup><i>In other language (unofficial port - by the community)</i></sup><br>
<a href="https://github.com/nickspring/charset-normalizer-rs">
<img alt="Static Badge" src="https://img.shields.io/badge/Rust-red">
</a>
</p>
> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
> I'm trying to resolve the issue by taking a new approach.
> All IANA character set names for which the Python core library provides codecs are supported.
<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` | ✅ | ✅ | ✅ |
| `Universal**` | ❌ | ✅ | ❌ |
| `Reliable` **without** distinguishable standards | ✅ | ✅ | ✅ |
| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
| `License` | _Public Domain_<br>and/or<br>_LGPL-2.1_***<br>_restrictive_ | MIT | MPL-1.1<br>_restrictive_ |
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ✅ | ✅ | N/A |
| `UnicodeDecodeError Safety` | ❌ | ✅ | ❌ |
| `Whl Size (min)` | 500 kB | 150 kB | ~200 kB |
| `Supported Encoding` | 99 | [99](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) | 40 |
| `Can register custom encoding` | ❌ | ✅ | ❌ |
<p align="center">
<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
</p>
*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one.*<br>
*\*\*\* : The vast majority of the code is issued from an LLM agent (Claude), even if the author label this project now as MIT in his own name, it's clearly debatable. Most jurisdictions on copyright laws would nullify the license. With my personal education, **Public Domain or/and LGPL-2.1** is the most likely one based on Anthropic declarations about how they train their LLMs and the LGPL-2.1 itself (the original license as it's still the same statistical principle behind the scene, hugely refactored).*<br>
## ⚡ Performance
This package offer acceptable performances against Chardet. Here are some numbers.
| Package | Accuracy | Mean per file (ms) | File per sec (est) |
|-------------------------------------------------|:--------:|:------------------:|:------------------:|
| [chardet 7](https://github.com/chardet/chardet) | 89 % | **5 ms** | 200 file/sec |
| charset-normalizer | **97 %** | 8 ms | 125 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
|-------------------------------------------------|:---------------:|:---------------:|:---------------:|
| [chardet 7](https://github.com/chardet/chardet) | 32 ms | 17 ms | 1 ms |
| charset-normalizer | 63 ms | 29 ms | 3 ms |
_updated as of Mars 2026 using CPython 3.12, and Chardet 7_
~Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.~ No longer the case since Chardet 7.0+
> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
> And yes, these results might change at any time. The dataset can be updated to include more files.
> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
> Chardet claims on his documentation to have a greater accuracy than us based on the dataset they trained Chardet on(...)
> Well, it's normal, the opposite would have been worrying. Whereas charset-normalizer don't train on anything, our solution
> is based on a completely different algorithm, still heuristic through, it does not need weights across every encoding tables.
## ✨ Installation
Using pip:
```sh
pip install charset-normalizer -U
```
## 🚀 Basic Usage
### CLI
This package comes with a CLI.
```
usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
file [file ...]
The Real First Universal Charset Detector. Discover originating encoding used
on text file. Normalize text to unicode.
positional arguments:
files File(s) to be analysed
optional arguments:
-h, --help show this help message and exit
-v, --verbose Display complementary information about file if any.
Stdout will contain logs about the detection process.
-a, --with-alternative
Output complementary possibilities if any. Top-level
JSON WILL be a list.
-n, --normalize Permit to normalize input file. If not set, program
does not write anything.
-m, --minimal Only output the charset detected to STDOUT. Disabling
JSON output.
-r, --replace Replace file when trying to normalize it instead of
creating a new one.
-f, --force Replace file without asking if you are sure, use this
flag with caution.
-t THRESHOLD, --threshold THRESHOLD
Define a custom maximum amount of chaos allowed in
decoded content. 0. <= chaos <= 1.
--version Show version information and exit.
```
```bash
normalizer ./data/sample.1.fr.srt
```
or
```bash
python -m charset_normalizer ./data/sample.1.fr.srt
```
🎉 Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
```json
{
"path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
"encoding": "cp1252",
"encoding_aliases": [
"1252",
"windows_1252"
],
"alternative_encodings": [
"cp1254",
"cp1256",
"cp1258",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
"mbcs"
],
"language": "French",
"alphabets": [
"Basic Latin",
"Latin-1 Supplement"
],
"has_sig_or_bom": false,
"chaos": 0.149,
"coherence": 97.152,
"unicode_path": null,
"is_preferred": true
}
```
### Python
*Just print out normalized text*
```python
from charset_normalizer import from_path
results = from_path('./my_subtitle.srt')
print(str(results.best()))
```
*Upgrade your code without effort*
```python
from charset_normalizer import detect
```
The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
## 😇 Why
When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
reliable alternative using a completely different method. Also! I never back down on a good challenge!
I **don't care** about the **originating charset** encoding, because **two different tables** can
produce **two identical rendered string.**
What I want is to get readable text, the best I can.
In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair Unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
## 🍰 How
- Discard all charset encoding table that could not fit the binary content.
- Measure noise, or the mess once opened (by chunks) with a corresponding charset encoding.
- Extract matches with the lowest mess detected.
- Additionally, we measure coherence / probe for a language.
**Wait a minute**, what is noise/mess and coherence according to **YOU ?**
*Noise :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
**I established** some ground rules about **what is obvious** when **it seems like** a mess (aka. defining noise in rendered text).
I know that my interpretation of what is noise is probably incomplete, feel free to contribute in order to
improve or rewrite it.
*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
## ⚡ Known limitations
- Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
- Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
## ⚠️ About Python EOLs
**If you are running:**
- Python >=2.7,<3.5: Unsupported
- Python 3.5: charset-normalizer < 2.1
- Python 3.6: charset-normalizer < 3.1
Upgrade your Python interpreter as soon as possible.
## 👤 Contributing
Contributions, issues and feature requests are very much welcome.<br />
Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
## 📝 License
Copyright © [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)
## 💼 For Enterprise
Professional support for charset-normalizer is available as part of the [Tidelift
Subscription][1]. Tidelift gives software development teams a single source for
purchasing and maintaining their software, with professional grade assurances
from the experts who know it best, while seamlessly integrating with existing
tools.
[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/7297/badge)](https://www.bestpractices.dev/projects/7297)
# Changelog
All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [3.4.5](https://github.com/Ousret/charset_normalizer/compare/3.4.4...3.4.5) (2026-03-06)
### Changed
- Update `setuptools` constraint to `setuptools>=68,<=82`.
- Raised upper bound of mypyc for the optional pre-built extension to v1.19.1
### Fixed
- Add explicit link to lib math in our optimized build. (#692)
- Logger level not restored correctly for empty byte sequences. (#701)
- TypeError when passing bytearray to from_bytes. (#703)
### Misc
- Applied safe micro-optimizations in both our noise detector and language detector.
- Rewrote the `query_yes_no` function (inside CLI) to avoid using ambiguous licensed code.
- Added `cd.py` submodule into mypyc optional compilation to reduce further the performance impact.
## [3.4.4](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.4) (2025-10-13)
### Changed
- Bound `setuptools` to a specific constraint `setuptools>=68,<=81`.
- Raised upper bound of mypyc for the optional pre-built extension to v1.18.2
### Removed
- `setuptools-scm` as a build dependency.
### Misc
- Enforced hashes in `dev-requirements.txt` and created `ci-requirements.txt` for security purposes.
- Additional pre-built wheels for riscv64, s390x, and armv7l architectures.
- Restore ` multiple.intoto.jsonl` in GitHub releases in addition to individual attestation file per wheel.
## [3.4.3](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.3) (2025-08-09)
### Changed
- mypy(c) is no longer a required dependency at build time if `CHARSET_NORMALIZER_USE_MYPYC` isn't set to `1`. (#595) (#583)
- automatically lower confidence on small bytes samples that are not Unicode in `detect` output legacy function. (#391)
### Added
- Custom build backend to overcome inability to mark mypy as an optional dependency in the build phase.
- Support for Python 3.14
### Fixed
- sdist archive contained useless directories.
- automatically fallback on valid UTF-16 or UTF-32 even if the md says it's noisy. (#633)
### Misc
- SBOM are automatically published to the relevant GitHub release to comply with regulatory changes.
Each published wheel comes with its SBOM. We choose CycloneDX as the format.
- Prebuilt optimized wheel are no longer distributed by default for CPython 3.7 due to a change in cibuildwheel.
## [3.4.2](https://github.com/Ousret/charset_normalizer/compare/3.4.1...3.4.2) (2025-05-02)
### Fixed
- Addressed the DeprecationWarning in our CLI regarding `argparse.FileType` by backporting the target class into the package. (#591)
- Improved the overall reliability of the detector with CJK Ideographs. (#605) (#587)
### Changed
- Optional mypyc compilation upgraded to version 1.15 for Python >= 3.8
## [3.4.1](https://github.com/Ousret/charset_normalizer/compare/3.4.0...3.4.1) (2024-12-24)
### Changed
- Project metadata are now stored using `pyproject.toml` instead of `setup.cfg` using setuptools as the build backend.
- Enforce annotation delayed loading for a simpler and consistent types in the project.
- Optional mypyc compilation upgraded to version 1.14 for Python >= 3.8
### Added
- pre-commit configuration.
- noxfile.
### Removed
- `build-requirements.txt` as per using `pyproject.toml` native build configuration.
- `bin/integration.py` and `bin/serve.py` in favor of downstream integration test (see noxfile).
- `setup.cfg` in favor of `pyproject.toml` metadata configuration.
- Unused `utils.range_scan` function.
### Fixed
- Converting content to Unicode bytes may insert `utf_8` instead of preferred `utf-8`. (#572)
- Deprecation warning "'count' is passed as positional argument" when converting to Unicode bytes on Python 3.13+
## [3.4.0](https://github.com/Ousret/charset_normalizer/compare/3.3.2...3.4.0) (2024-10-08)
### Added
- Argument `--no-preemptive` in the CLI to prevent the detector to search for hints.
- Support for Python 3.13 (#512)
### Fixed
- Relax the TypeError exception thrown when trying to compare a CharsetMatch with anything else than a CharsetMatch.
- Improved the general reliability of the detector based on user feedbacks. (#520) (#509) (#498) (#407) (#537)
- Declared charset in content (preemptive detection) not changed when converting to utf-8 bytes. (#381)
## [3.3.2](https://github.com/Ousret/charset_normalizer/compare/3.3.1...3.3.2) (2023-10-31)
### Fixed
- Unintentional memory usage regression when using large payload that match several encoding (#376)
- Regression on some detection case showcased in the documentation (#371)
### Added
- Noise (md) probe that identify malformed arabic representation due to the presence of letters in isolated form (credit to my wife)
## [3.3.1](https://github.com/Ousret/charset_normalizer/compare/3.3.0...3.3.1) (2023-10-22)
### Changed
- Optional mypyc compilation upgraded to version 1.6.1 for Python >= 3.8
- Improved the general detection reliability based on reports from the community
## [3.3.0](https://github.com/Ousret/charset_normalizer/compare/3.2.0...3.3.0) (2023-09-30)
### Added
- Allow to execute the CLI (e.g. normalizer) through `python -m charset_normalizer.cli` or `python -m charset_normalizer`
- Support for 9 forgotten encoding that are supported by Python but unlisted in `encoding.aliases` as they have no alias (#323)
### Removed
- (internal) Redundant utils.is_ascii function and unused function is_private_use_only
- (internal) charset_normalizer.assets is moved inside charset_normalizer.constant
### Changed
- (internal) Unicode code blocks in constants are updated using the latest v15.0.0 definition to improve detection
- Optional mypyc compilation upgraded to version 1.5.1 for Python >= 3.8
### Fixed
- Unable to properly sort CharsetMatch when both chaos/noise and coherence were close due to an unreachable condition in \_\_lt\_\_ (#350)
## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
### Changed
- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
- Minor improvement over the global detection reliability
### Added
- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
- Explicit support for Python 3.12
### Fixed
- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
### Added
- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
### Removed
- Support for Python 3.6 (PR #260)
### Changed
- Optional speedup provided by mypy/c 1.0.1
## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
### Fixed
- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
### Changed
- Speedup provided by mypy/c 0.990 on Python >= 3.7
## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
- Sphinx warnings when generating the documentation
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
### Added
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Removed
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
### Fixed
- Sphinx warnings when generating the documentation
## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
### Changed
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Removed
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
### Deprecated
- Function `normalize` scheduled for removal in 3.0
### Changed
- Removed useless call to decode in fn is_unprintable (#206)
### Fixed
- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
### Added
- Output the Unicode table version when running the CLI with `--version` (PR #194)
### Changed
- Re-use decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
### Fixed
- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
### Removed
- Support for Python 3.5 (PR #192)
### Deprecated
- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
### Fixed
- ASCII miss-detection on rare cases (PR #170)
## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
### Added
- Explicit support for Python 3.11 (PR #164)
### Changed
- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
### Fixed
- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
### Changed
- Skipping the language-detection (CD) on ASCII (PR #155)
## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
### Changed
- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
### Fixed
- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
### Changed
- Improvement over Vietnamese detection (PR #126)
- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
- Code style as refactored by Sourcery-AI (PR #131)
- Minor adjustment on the MD around european words (PR #133)
- Remove and replace SRTs from assets / tests (PR #139)
- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
### Fixed
- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
- Avoid using too insignificant chunk (PR #137)
### Added
- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
### Added
- Add support for Kazakh (Cyrillic) language detection (PR #109)
### Changed
- Further, improve inferring the language from a given single-byte code page (PR #112)
- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
- Various detection improvement (MD+CD) (PR #117)
### Removed
- Remove redundant logging entry about detected language(s) (PR #115)
### Fixed
- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
### Fixed
- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
- Fix CLI crash when using --minimal output in certain cases (PR #103)
### Changed
- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
### Changed
- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
- The Unicode detection is slightly improved (PR #93)
- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
### Removed
- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
### Fixed
- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
- The MANIFEST.in was not exhaustive (PR #78)
## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
### Fixed
- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
- Submatch factoring could be wrong in rare edge cases (PR #72)
- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
- Fix line endings from CRLF to LF for certain project files (PR #67)
### Changed
- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
- Allow fallback on specified encoding if any (PR #71)
## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
### Changed
- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
### Fixed
- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59)
### Changed
- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
### Fixed
- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
### Changed
- Public function normalize default args values were not aligned with from_bytes (PR #53)
### Added
- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
### Changed
- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
- Accent has been made on UTF-8 detection, should perform rather instantaneous.
- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
- utf_7 detection has been reinstated.
### Removed
- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
- The exception hook on UnicodeDecodeError has been removed.
### Deprecated
- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
### Fixed
- The CLI output used the relative path of the file(s). Should be absolute.
## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
### Fixed
- Logger configuration/usage no longer conflict with others (PR #44)
## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
### Removed
- Using standard logging instead of using the package loguru.
- Dropping nose test framework in favor of the maintained pytest.
- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
- Stop support for UTF-7 that does not contain a SIG.
- Dropping PrettyTable, replaced with pure JSON output in CLI.
### Fixed
- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
- Not searching properly for the BOM when trying utf32/16 parent codec.
### Changed
- Improving the package final size by compressing frequencies.json.
- Huge improvement over the larges payload.
### Added
- CLI now produces JSON consumable output.
- Return ASCII if given sequences fit. Given reasonable confidence.
## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
### Fixed
- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
### Fixed
- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
### Fixed
- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
### Changed
- Amend the previous release to allow prettytable 2.0 (PR #35)
## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
### Fixed
- Fix error while using the package with a python pre-release interpreter (PR #33)
### Changed
- Dependencies refactoring, constraints revised.
### Added
- Add python 3.9 and 3.10 to the supported interpreters
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

36
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/RECORD Normal file
View File

@@ -0,0 +1,36 @@
../../../bin/normalizer,sha256=4nbFeY8b_phVKfTPTKpxz9aCKXid4J4_hjLlDDqTp7k,266
81d243bd2c585b0f4821__mypyc.cpython-312-x86_64-linux-gnu.so,sha256=ol-F_r6abrxGpRlWxSI7_945wGWttVZG8eyeELYEYIg,400712
charset_normalizer-3.4.5.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-3.4.5.dist-info/METADATA,sha256=EzjXveXyFIsZbPId0RGpMGQjUc-R5UKvA2WAtej3jDs,39168
charset_normalizer-3.4.5.dist-info/RECORD,,
charset_normalizer-3.4.5.dist-info/WHEEL,sha256=ND-iKo1q8cWcsXAKXBKvQvxAFH_GQvThPpjreAAS6vI,190
charset_normalizer-3.4.5.dist-info/entry_points.txt,sha256=ADSTKrkXZ3hhdOVFi6DcUEHQRS0xfxDIE_pEz4wLIXA,65
charset_normalizer-3.4.5.dist-info/licenses/LICENSE,sha256=bQ1Bv-FwrGx9wkjJpj4lTQ-0WmDVCoJX0K-SxuJJuIc,1071
charset_normalizer-3.4.5.dist-info/top_level.txt,sha256=c_vZbitqecT2GfK3zdxSTLCn8C-6pGnHQY5o_5Y32M0,47
charset_normalizer/__init__.py,sha256=OKRxRv2Zhnqk00tqkN0c1BtJjm165fWXLydE52IKuHc,1590
charset_normalizer/__main__.py,sha256=yzYxMR-IhKRHYwcSlavEv8oGdwxsR89mr2X09qXGdps,109
charset_normalizer/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/__pycache__/__main__.cpython-312.pyc,,
charset_normalizer/__pycache__/api.cpython-312.pyc,,
charset_normalizer/__pycache__/cd.cpython-312.pyc,,
charset_normalizer/__pycache__/constant.cpython-312.pyc,,
charset_normalizer/__pycache__/legacy.cpython-312.pyc,,
charset_normalizer/__pycache__/md.cpython-312.pyc,,
charset_normalizer/__pycache__/models.cpython-312.pyc,,
charset_normalizer/__pycache__/utils.cpython-312.pyc,,
charset_normalizer/__pycache__/version.cpython-312.pyc,,
charset_normalizer/api.py,sha256=TRSCafKaFBsVb58qldkSVKjMaVLRoO2K50HlnoVJS8k,22719
charset_normalizer/cd.cpython-312-x86_64-linux-gnu.so,sha256=KRs9UiPDxL5LmvMpsgOxjVpbPowT3L9yjkDmyP34GPI,15912
charset_normalizer/cd.py,sha256=4uPHsbkK1JMivEyl7IQX_sc1hmvos1GWClziah0eUmE,13639
charset_normalizer/cli/__init__.py,sha256=D8I86lFk2-py45JvqxniTirSj_sFyE6sjaY_0-G1shc,136
charset_normalizer/cli/__main__.py,sha256=YKJSlTzvQc5-bV2GiZa0YuENaQqBqu2o9-GfKeXpcv8,11946
charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc,,
charset_normalizer/constant.py,sha256=zxhEL0g0eGpeYSRzjDV712fChwyvzu2buf3_iFm5erU,43552
charset_normalizer/legacy.py,sha256=sYBzSpzsRrg_wF4LP536pG64BItw7Tqtc3SMQAHvFLM,2731
charset_normalizer/md.cpython-312-x86_64-linux-gnu.so,sha256=VaxqqP3RbmelZISMwRb2ahdtqNdbXBgN56dIZuZ-tfw,15912
charset_normalizer/md.py,sha256=8GHs8v9PRvpQptX1WMu9i-m8O1Iz8CMVpBCz3bVhfxk,23023
charset_normalizer/models.py,sha256=QSS3cmSdh4J4URyNOhyBdgDEbrHIY33eCuP-CNAjtGI,12320
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=Gnwvl3uLekr-I4ynGDT0BtCiDfh9QANfF6UWLWKjeYw,12240
charset_normalizer/version.py,sha256=cz8kM4B70kP_YEpiel3hbt_h-D9zYjlRRcwxzSBc378,115

7
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,7 @@
Wheel-Version: 1.0
Generator: setuptools (82.0.0)
Root-Is-Purelib: false
Tag: cp312-cp312-manylinux_2_17_x86_64
Tag: cp312-cp312-manylinux2014_x86_64
Tag: cp312-cp312-manylinux_2_28_x86_64

2
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/entry_points.txt Normal file
View File

@@ -0,0 +1,2 @@
[console_scripts]
normalizer = charset_normalizer.cli:cli_detect

21
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/licenses/LICENSE Normal file
View File

@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

2
venv/lib/python3.12/site-packages/charset_normalizer-3.4.5.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1,2 @@
81d243bd2c585b0f4821__mypyc
charset_normalizer

48
venv/lib/python3.12/site-packages/charset_normalizer/__init__.py Normal file
View File

@@ -0,0 +1,48 @@
"""
Charset-Normalizer
~~~~~~~~~~~~~~
The Real First Universal Charset Detector.
A library that helps you read text from an unknown charset encoding.
Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
All IANA character set names for which the Python core library provides codecs are supported.
Basic usage:
>>> from charset_normalizer import from_bytes
>>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
>>> best_guess = results.best()
>>> str(best_guess)
'Bсеки човек има право на образование. Oбразованието!'
Others methods and usages are available - see the full documentation
at <https://github.com/Ousret/charset_normalizer>.
:copyright: (c) 2021 by Ahmed TAHRI
:license: MIT, see LICENSE for more details.
"""
from __future__ import annotations
import logging
from .api import from_bytes, from_fp, from_path, is_binary
from .legacy import detect
from .models import CharsetMatch, CharsetMatches
from .utils import set_logging_handler
from .version import VERSION, __version__
__all__ = (
"from_fp",
"from_path",
"from_bytes",
"is_binary",
"detect",
"CharsetMatch",
"CharsetMatches",
"__version__",
"VERSION",
"set_logging_handler",
)
# Attach a NullHandler to the top level logger by default
# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())

6
venv/lib/python3.12/site-packages/charset_normalizer/__main__.py Normal file
View File

@@ -0,0 +1,6 @@
from __future__ import annotations
from .cli import cli_detect
if __name__ == "__main__":
cli_detect()

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/__main__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/api.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/cd.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/constant.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/legacy.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/md.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/models.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/utils.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/__pycache__/version.cpython-312.pyc Normal file
View File

Binary file not shown.

671
venv/lib/python3.12/site-packages/charset_normalizer/api.py Normal file
View File

@@ -0,0 +1,671 @@
from __future__ import annotations
import logging
from os import PathLike
from typing import BinaryIO
from .cd import (
coherence_ratio,
encoding_languages,
mb_encoding_languages,
merge_coherence_ratios,
)
from .constant import (
IANA_SUPPORTED,
IANA_SUPPORTED_SIMILAR,
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_multi_byte_encoding,
should_strip_sig_or_bom,
)
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 | bytearray,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.2,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> 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 blocks 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: {}".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: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
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: str | None = (
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] = []
soft_failure_skip: set[str] = set()
fallback_ascii: CharsetMatch | None = None
fallback_u8: CharsetMatch | None = None
fallback_specified: CharsetMatch | None = None
results: CharsetMatches = CharsetMatches()
early_stop_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: str | None = 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 won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
encoding_iana,
)
continue
if encoding_iana in {"utf_7"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.",
encoding_iana,
)
continue
# Skip encodings similar to ones that already soft-failed (high mess ratio).
# Checked BEFORE the expensive decode attempt.
if encoding_iana in soft_failure_skip:
logger.log(
TRACE,
"%s is deemed too similar to a code page that was already considered unsuited. Continuing!",
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
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,
explain is True and 1 <= len(cp_isolation) <= 2,
)
)
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)
if encoding_iana in IANA_SUPPORTED_SIMILAR:
soft_failure_skip.update(IANA_SUPPORTED_SIMILAR[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 (
enable_fallback
and encoding_iana
in ["ascii", "utf_8", specified_encoding, "utf_16", "utf_32"]
and not lazy_str_hard_failure
):
fallback_entry = CharsetMatch(
sequences,
encoding_iana,
threshold,
bom_or_sig_available,
[],
decoded_payload,
preemptive_declaration=specified_encoding,
)
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,
language_threshold,
",".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
),
)
current_match = CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
(
decoded_payload
if (
is_too_large_sequence is False
or encoding_iana in [specified_encoding, "ascii", "utf_8"]
)
else None
),
preemptive_declaration=specified_encoding,
)
results.append(current_match)
if (
encoding_iana in [specified_encoding, "ascii", "utf_8"]
and mean_mess_ratio < 0.1
):
# If md says nothing to worry about, then... stop immediately!
if mean_mess_ratio == 0.0:
logger.debug(
"Encoding detection: %s is most likely the one.",
current_match.encoding,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([current_match])
early_stop_results.append(current_match)
if (
len(early_stop_results)
and (specified_encoding is None or specified_encoding in tested)
and "ascii" in tested
and "utf_8" in tested
):
probable_result: CharsetMatch = early_stop_results.best() # type: ignore[assignment]
logger.debug(
"Encoding detection: %s is most likely the one.",
probable_result.encoding,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([probable_result])
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: # Defensive: ensure exit path clean handler
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 = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> 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,
language_threshold,
enable_fallback,
)
def from_path(
path: str | bytes | PathLike, # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> 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,
language_threshold,
enable_fallback,
)
def is_binary(
fp_or_path_or_payload: PathLike | str | BinaryIO | bytes, # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = False,
) -> bool:
"""
Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string.
Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match
are disabled to be stricter around ASCII-compatible but unlikely to be a string.
"""
if isinstance(fp_or_path_or_payload, (str, PathLike)):
guesses = from_path(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
elif isinstance(
fp_or_path_or_payload,
(
bytes,
bytearray,
),
):
guesses = from_bytes(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
else:
guesses = from_fp(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
return not guesses

BIN
venv/lib/python3.12/site-packages/charset_normalizer/cd.cpython-312-x86_64-linux-gnu.so Executable file
View File

Binary file not shown.

421
venv/lib/python3.12/site-packages/charset_normalizer/cd.py Normal file
View File

@@ -0,0 +1,421 @@
from __future__ import annotations
import importlib
from codecs import IncrementalDecoder
from collections import Counter
from functools import lru_cache
from typing import Counter as TypeCounter
from .constant import (
FREQUENCIES,
KO_NAMES,
LANGUAGE_SUPPORTED_COUNT,
TOO_SMALL_SEQUENCE,
ZH_NAMES,
_FREQUENCIES_SET,
_FREQUENCIES_RANK,
)
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 OSError("Function not supported on multi-byte code page")
decoder = importlib.import_module(f"encodings.{iana_name}").IncrementalDecoder
p: IncrementalDecoder = decoder(errors="ignore")
seen_ranges: dict[str, int] = {}
character_count: int = 0
for i in range(0x40, 0xFF):
chunk: str = p.decode(bytes([i]))
if chunk:
character_range: str | None = 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: str | None = None
for specified_range in unicode_ranges:
if "Latin" not in specified_range:
primary_range = specified_range
break
if primary_range is None:
return ["Latin Based"]
return unicode_range_languages(primary_range)
@lru_cache()
def mb_encoding_languages(iana_name: str) -> list[str]:
"""
Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
if (
iana_name.startswith("shift_")
or iana_name.startswith("iso2022_jp")
or iana_name.startswith("euc_j")
or iana_name == "cp932"
):
return ["Japanese"]
if iana_name.startswith("gb") or iana_name in ZH_NAMES:
return ["Chinese"]
if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES:
return ["Korean"]
return []
@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT)
def get_target_features(language: str) -> tuple[bool, bool]:
"""
Determine main aspects from a supported language if it contains accents and if is pure Latin.
"""
target_have_accents: bool = False
target_pure_latin: bool = True
for character in FREQUENCIES[language]:
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]] = []
characters_set: frozenset[str] = frozenset(characters)
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(_FREQUENCIES_SET[language] & characters_set)
ratio: float = character_match_count / character_count
if ratio >= 0.2:
languages.append((language, ratio))
languages = sorted(languages, key=lambda x: x[1], reverse=True)
return [compatible_language[0] for compatible_language in languages]
def characters_popularity_compare(
language: str, ordered_characters: list[str]
) -> float:
"""
Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
"""
if language not in FREQUENCIES:
raise ValueError(f"{language} not available")
character_approved_count: int = 0
frequencies_language_set: frozenset[str] = _FREQUENCIES_SET[language]
lang_rank: dict[str, int] = _FREQUENCIES_RANK[language]
ordered_characters_count: int = len(ordered_characters)
target_language_characters_count: int = len(FREQUENCIES[language])
large_alphabet: bool = target_language_characters_count > 26
expected_projection_ratio: float = (
target_language_characters_count / ordered_characters_count
)
# Pre-built rank dict for ordered_characters (avoids repeated list slicing).
ordered_rank: dict[str, int] = {
char: rank for rank, char in enumerate(ordered_characters)
}
# Pre-compute characters common to both orderings.
# Avoids repeated `c in ordered_rank` dict lookups in the inner counts.
common_chars: list[tuple[int, int]] = [
(lr, ordered_rank[c]) for c, lr in lang_rank.items() if c in ordered_rank
]
for character, character_rank in zip(
ordered_characters, range(0, ordered_characters_count)
):
if character not in frequencies_language_set:
continue
character_rank_in_language: int = lang_rank[character]
character_rank_projection: int = int(character_rank * expected_projection_ratio)
if (
large_alphabet is False
and abs(character_rank_projection - character_rank_in_language) > 4
):
continue
if (
large_alphabet is True
and abs(character_rank_projection - character_rank_in_language)
< target_language_characters_count / 3
):
character_approved_count += 1
continue
# Count how many characters appear "before" in both orderings,
# and how many appear "at or after" in both orderings.
before_match_count: int = sum(
1
for lr, orr in common_chars
if lr < character_rank_in_language and orr < character_rank
)
after_len: int = target_language_characters_count - character_rank_in_language
after_match_count: int = sum(
1
for lr, orr in common_chars
if lr >= character_rank_in_language and orr >= character_rank
)
if character_rank_in_language == 0 and before_match_count <= 4:
character_approved_count += 1
continue
if after_len == 0 and after_match_count <= 4:
character_approved_count += 1
continue
if (
character_rank_in_language > 0
and before_match_count / character_rank_in_language >= 0.4
) or (after_len > 0 and after_match_count / after_len >= 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, list[str]] = {}
# Fast path: track single-layer key to skip dict iteration for single-script text.
single_layer_key: str | None = None
multi_layer: bool = False
for character in decoded_sequence:
if character.isalpha() is False:
continue
character_range: str | None = unicode_range(character)
if character_range is None:
continue
layer_target_range: str | None = None
if multi_layer:
for discovered_range in layers:
if (
is_suspiciously_successive_range(discovered_range, character_range)
is False
):
layer_target_range = discovered_range
break
elif single_layer_key is not None:
if (
is_suspiciously_successive_range(single_layer_key, character_range)
is False
):
layer_target_range = single_layer_key
if layer_target_range is None:
layer_target_range = character_range
if layer_target_range not in layers:
layers[layer_target_range] = []
if single_layer_key is None:
single_layer_key = layer_target_range
else:
multi_layer = True
layers[layer_target_range].append(character)
return ["".join(chars).lower() for chars in layers.values()]
def merge_coherence_ratios(results: list[CoherenceMatches]) -> CoherenceMatches:
"""
This function merge results previously given by the function coherence_ratio.
The return type is the same as coherence_ratio.
"""
per_language_ratios: dict[str, list[float]] = {}
for result in results:
for sub_result in result:
language, ratio = sub_result
if language not in per_language_ratios:
per_language_ratios[language] = [ratio]
continue
per_language_ratios[language].append(ratio)
merge = [
(
language,
round(
sum(per_language_ratios[language]) / len(per_language_ratios[language]),
4,
),
)
for language in per_language_ratios
]
return sorted(merge, key=lambda x: x[1], reverse=True)
def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches:
"""
We shall NOT return "English—" in CoherenceMatches because it is an alternative
of "English". This function only keeps the best match and remove the em-dash in it.
"""
index_results: dict[str, list[float]] = dict()
for result in results:
language, ratio = result
no_em_name: str = language.replace("—", "")
if no_em_name not in index_results:
index_results[no_em_name] = []
index_results[no_em_name].append(ratio)
if any(len(index_results[e]) > 1 for e in index_results):
filtered_results: CoherenceMatches = []
for language in index_results:
filtered_results.append((language, max(index_results[language])))
return filtered_results
return results
@lru_cache(maxsize=2048)
def coherence_ratio(
decoded_sequence: str, threshold: float = 0.1, lg_inclusion: str | None = None
) -> CoherenceMatches:
"""
Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
A layer = Character extraction by alphabets/ranges.
"""
results: list[tuple[str, float]] = []
ignore_non_latin: bool = False
sufficient_match_count: int = 0
lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else []
if "Latin Based" in lg_inclusion_list:
ignore_non_latin = True
lg_inclusion_list.remove("Latin Based")
for layer in alpha_unicode_split(decoded_sequence):
sequence_frequencies: TypeCounter[str] = Counter(layer)
most_common = sequence_frequencies.most_common()
character_count: int = len(layer)
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(
filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True
)

8
venv/lib/python3.12/site-packages/charset_normalizer/cli/__init__.py Normal file
View File

@@ -0,0 +1,8 @@
from __future__ import annotations
from .__main__ import cli_detect, query_yes_no
__all__ = (
"cli_detect",
"query_yes_no",
)

363
venv/lib/python3.12/site-packages/charset_normalizer/cli/__main__.py Normal file
View File

@@ -0,0 +1,363 @@
from __future__ import annotations
import argparse
import sys
import typing
from json import dumps
from os.path import abspath, basename, dirname, join, realpath
from platform import python_version
from unicodedata import unidata_version
import charset_normalizer.md as md_module
from charset_normalizer import from_fp
from charset_normalizer.models import CliDetectionResult
from charset_normalizer.version import __version__
def query_yes_no(question: str, default: str = "yes") -> bool:
"""Ask a yes/no question via input() and return the answer as a bool."""
prompt = " [Y/n] " if default == "yes" else " [y/N] "
while True:
choice = input(question + prompt).strip().lower()
if not choice:
return default == "yes"
if choice in ("y", "yes"):
return True
if choice in ("n", "no"):
return False
print("Please respond with 'y' or 'n'.")
class FileType:
"""Factory for creating file object types
Instances of FileType are typically passed as type= arguments to the
ArgumentParser add_argument() method.
Keyword Arguments:
- mode -- A string indicating how the file is to be opened. Accepts the
same values as the builtin open() function.
- bufsize -- The file's desired buffer size. Accepts the same values as
the builtin open() function.
- encoding -- The file's encoding. Accepts the same values as the
builtin open() function.
- errors -- A string indicating how encoding and decoding errors are to
be handled. Accepts the same value as the builtin open() function.
Backported from CPython 3.12
"""
def __init__(
self,
mode: str = "r",
bufsize: int = -1,
encoding: str | None = None,
errors: str | None = None,
):
self._mode = mode
self._bufsize = bufsize
self._encoding = encoding
self._errors = errors
def __call__(self, string: str) -> typing.IO: # type: ignore[type-arg]
# the special argument "-" means sys.std{in,out}
if string == "-":
if "r" in self._mode:
return sys.stdin.buffer if "b" in self._mode else sys.stdin
elif any(c in self._mode for c in "wax"):
return sys.stdout.buffer if "b" in self._mode else sys.stdout
else:
msg = f'argument "-" with mode {self._mode}'
raise ValueError(msg)
# all other arguments are used as file names
try:
return open(string, self._mode, self._bufsize, self._encoding, self._errors)
except OSError as e:
message = f"can't open '{string}': {e}"
raise argparse.ArgumentTypeError(message)
def __repr__(self) -> str:
args = self._mode, self._bufsize
kwargs = [("encoding", self._encoding), ("errors", self._errors)]
args_str = ", ".join(
[repr(arg) for arg in args if arg != -1]
+ [f"{kw}={arg!r}" for kw, arg in kwargs if arg is not None]
)
return f"{type(self).__name__}({args_str})"
def cli_detect(argv: list[str] | None = None) -> int:
"""
CLI assistant using ARGV and ArgumentParser
:param argv:
:return: 0 if everything is fine, anything else equal trouble
"""
parser = argparse.ArgumentParser(
description="The Real First Universal Charset Detector. "
"Discover originating encoding used on text file. "
"Normalize text to unicode."
)
parser.add_argument(
"files", type=FileType("rb"), nargs="+", help="File(s) to be analysed"
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
default=False,
dest="verbose",
help="Display complementary information about file if any. "
"Stdout will contain logs about the detection process.",
)
parser.add_argument(
"-a",
"--with-alternative",
action="store_true",
default=False,
dest="alternatives",
help="Output complementary possibilities if any. Top-level JSON WILL be a list.",
)
parser.add_argument(
"-n",
"--normalize",
action="store_true",
default=False,
dest="normalize",
help="Permit to normalize input file. If not set, program does not write anything.",
)
parser.add_argument(
"-m",
"--minimal",
action="store_true",
default=False,
dest="minimal",
help="Only output the charset detected to STDOUT. Disabling JSON output.",
)
parser.add_argument(
"-r",
"--replace",
action="store_true",
default=False,
dest="replace",
help="Replace file when trying to normalize it instead of creating a new one.",
)
parser.add_argument(
"-f",
"--force",
action="store_true",
default=False,
dest="force",
help="Replace file without asking if you are sure, use this flag with caution.",
)
parser.add_argument(
"-i",
"--no-preemptive",
action="store_true",
default=False,
dest="no_preemptive",
help="Disable looking at a charset declaration to hint the detector.",
)
parser.add_argument(
"-t",
"--threshold",
action="store",
default=0.2,
type=float,
dest="threshold",
help="Define a custom maximum amount of noise allowed in decoded content. 0. <= noise <= 1.",
)
parser.add_argument(
"--version",
action="version",
version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format(
__version__,
python_version(),
unidata_version,
"OFF" if md_module.__file__.lower().endswith(".py") else "ON",
),
help="Show version information and exit.",
)
args = parser.parse_args(argv)
if args.replace is True and args.normalize is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --replace in addition of --normalize only.", file=sys.stderr)
return 1
if args.force is True and args.replace is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --force in addition of --replace only.", file=sys.stderr)
return 1
if args.threshold < 0.0 or args.threshold > 1.0:
if args.files:
for my_file in args.files:
my_file.close()
print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
return 1
x_ = []
for my_file in args.files:
matches = from_fp(
my_file,
threshold=args.threshold,
explain=args.verbose,
preemptive_behaviour=args.no_preemptive is False,
)
best_guess = matches.best()
if best_guess is None:
print(
'Unable to identify originating encoding for "{}". {}'.format(
my_file.name,
(
"Maybe try increasing maximum amount of chaos."
if args.threshold < 1.0
else ""
),
),
file=sys.stderr,
)
x_.append(
CliDetectionResult(
abspath(my_file.name),
None,
[],
[],
"Unknown",
[],
False,
1.0,
0.0,
None,
True,
)
)
else:
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
dir_path = dirname(realpath(my_file.name))
file_name = basename(realpath(my_file.name))
o_: list[str] = file_name.split(".")
if args.replace is False:
o_.insert(-1, best_guess.encoding)
if my_file.closed is False:
my_file.close()
elif (
args.force is False
and query_yes_no(
'Are you sure to normalize "{}" by replacing it ?'.format(
my_file.name
),
"no",
)
is False
):
if my_file.closed is False:
my_file.close()
continue
try:
x_[0].unicode_path = join(dir_path, ".".join(o_))
with open(x_[0].unicode_path, "wb") as fp:
fp.write(best_guess.output())
except OSError 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()

BIN
venv/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc Normal file
View File

Binary file not shown.

2031
venv/lib/python3.12/site-packages/charset_normalizer/constant.py Normal file
View File

File diff suppressed because it is too large Load Diff

80
venv/lib/python3.12/site-packages/charset_normalizer/legacy.py Normal file
View File

@@ -0,0 +1,80 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from warnings import warn
from .api import from_bytes
from .constant import CHARDET_CORRESPONDENCE, TOO_SMALL_SEQUENCE
# TODO: remove this check when dropping Python 3.7 support
if TYPE_CHECKING:
from typing_extensions import TypedDict
class ResultDict(TypedDict):
encoding: str | None
language: str
confidence: float | None
def detect(
byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
) -> ResultDict:
"""
chardet legacy method
Detect the encoding of the given byte string. It should be mostly backward-compatible.
Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
This function is deprecated and should be used to migrate your project easily, consult the documentation for
further information. Not planned for removal.
:param byte_str: The byte sequence to examine.
:param should_rename_legacy: Should we rename legacy encodings
to their more modern equivalents?
"""
if len(kwargs):
warn(
f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
)
if not isinstance(byte_str, (bytearray, bytes)):
raise TypeError( # pragma: nocover
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
if isinstance(byte_str, bytearray):
byte_str = bytes(byte_str)
r = from_bytes(byte_str).best()
encoding = r.encoding if r is not None else None
language = r.language if r is not None and r.language != "Unknown" else ""
confidence = 1.0 - r.chaos if r is not None else None
# automatically lower confidence
# on small bytes samples.
# https://github.com/jawah/charset_normalizer/issues/391
if (
confidence is not None
and confidence >= 0.9
and encoding
not in {
"utf_8",
"ascii",
}
and r.bom is False # type: ignore[union-attr]
and len(byte_str) < TOO_SMALL_SEQUENCE
):
confidence -= 0.2
# Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
# but chardet does return 'utf-8-sig' and it is a valid codec name.
if r is not None and encoding == "utf_8" and r.bom:
encoding += "_sig"
if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE:
encoding = CHARDET_CORRESPONDENCE[encoding]
return {
"encoding": encoding,
"language": language,
"confidence": confidence,
}

BIN
venv/lib/python3.12/site-packages/charset_normalizer/md.cpython-312-x86_64-linux-gnu.so Executable file
View File

Binary file not shown.

744
venv/lib/python3.12/site-packages/charset_normalizer/md.py Normal file
View File

@@ -0,0 +1,744 @@
from __future__ import annotations
import sys
from functools import lru_cache
from logging import getLogger
if sys.version_info >= (3, 8):
from typing import final
else:
try:
from typing_extensions import final
except ImportError:
def final(cls): # type: ignore[misc,no-untyped-def]
return cls
from .constant import (
COMMON_SAFE_ASCII_CHARACTERS,
TRACE,
UNICODE_SECONDARY_RANGE_KEYWORD,
_ACCENTUATED,
_CJK,
_HANGUL,
_HIRAGANA,
_KATAKANA,
_LATIN,
_THAI,
)
from .utils import (
_character_flags,
is_accentuated,
is_arabic,
is_arabic_isolated_form,
is_case_variable,
is_cjk,
is_emoticon,
is_latin,
is_punctuation,
is_separator,
is_symbol,
is_unprintable,
remove_accent,
unicode_range,
is_cjk_uncommon,
)
# Combined bitmask for CJK/Hangul/Katakana/Hiragana/Thai glyph detection.
_GLYPH_MASK: int = _CJK | _HANGUL | _KATAKANA | _HIRAGANA | _THAI
class MessDetectorPlugin:
"""
Base abstract class used for mess detection plugins.
All detectors MUST extend and implement given methods.
"""
__slots__ = ()
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
@final
class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
__slots__ = (
"_punctuation_count",
"_symbol_count",
"_character_count",
"_last_printable_char",
"_frenzy_symbol_in_word",
)
def __init__(self) -> None:
self._punctuation_count: int = 0
self._symbol_count: int = 0
self._character_count: int = 0
self._last_printable_char: str | None = 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 (
not character.isdigit()
and is_symbol(character)
and not is_emoticon(character)
):
self._symbol_count += 2
self._last_printable_char = character
def reset(self) -> None: # Abstract
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
@final
class TooManyAccentuatedPlugin(MessDetectorPlugin):
__slots__ = ("_character_count", "_accentuated_count")
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: # Abstract
self._character_count = 0
self._accentuated_count = 0
@property
def ratio(self) -> float:
if self._character_count < 8:
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
@final
class UnprintablePlugin(MessDetectorPlugin):
__slots__ = ("_unprintable_count", "_character_count")
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: # Abstract
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
@final
class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
__slots__ = (
"_successive_count",
"_character_count",
"_last_latin_character",
"_last_was_accentuated",
)
def __init__(self) -> None:
self._successive_count: int = 0
self._character_count: int = 0
self._last_latin_character: str | None = None
self._last_was_accentuated: bool = False
def eligible(self, character: str) -> bool:
return character.isalpha() and is_latin(character)
def feed(self, character: str) -> None:
self._character_count += 1
current_accentuated: bool = is_accentuated(character)
if (
self._last_latin_character is not None
and current_accentuated
and self._last_was_accentuated
):
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
self._last_was_accentuated = current_accentuated
def reset(self) -> None: # Abstract
self._successive_count = 0
self._character_count = 0
self._last_latin_character = None
self._last_was_accentuated = False
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._successive_count * 2) / self._character_count
@final
class SuspiciousRange(MessDetectorPlugin):
__slots__ = (
"_suspicious_successive_range_count",
"_character_count",
"_last_printable_seen",
"_last_printable_range",
)
def __init__(self) -> None:
self._suspicious_successive_range_count: int = 0
self._character_count: int = 0
self._last_printable_seen: str | None = None
self._last_printable_range: str | None = 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
self._last_printable_range = None
return
if self._last_printable_seen is None:
self._last_printable_seen = character
self._last_printable_range = unicode_range(character)
return
unicode_range_a: str | None = self._last_printable_range
unicode_range_b: str | None = 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
self._last_printable_range = unicode_range_b
def reset(self) -> None: # Abstract
self._character_count = 0
self._suspicious_successive_range_count = 0
self._last_printable_seen = None
self._last_printable_range = None
@property
def ratio(self) -> float:
if self._character_count <= 13:
return 0.0
ratio_of_suspicious_range_usage: float = (
self._suspicious_successive_range_count * 2
) / self._character_count
return ratio_of_suspicious_range_usage
@final
class SuperWeirdWordPlugin(MessDetectorPlugin):
__slots__ = (
"_word_count",
"_bad_word_count",
"_foreign_long_count",
"_is_current_word_bad",
"_foreign_long_watch",
"_character_count",
"_bad_character_count",
"_buffer_length",
"_buffer_last_char",
"_buffer_last_char_accentuated",
"_buffer_accent_count",
"_buffer_glyph_count",
"_buffer_upper_count",
)
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_length: int = 0
self._buffer_last_char: str | None = None
self._buffer_last_char_accentuated: bool = False
self._buffer_accent_count: int = 0
self._buffer_glyph_count: int = 0
self._buffer_upper_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if character.isalpha():
self._buffer_length += 1
self._buffer_last_char = character
if character.isupper():
self._buffer_upper_count += 1
flags: int = _character_flags(character)
char_accentuated: bool = bool(flags & _ACCENTUATED)
self._buffer_last_char_accentuated = char_accentuated
if char_accentuated:
self._buffer_accent_count += 1
if (
not self._foreign_long_watch
and (not (flags & _LATIN) or char_accentuated)
and not (flags & _GLYPH_MASK)
):
self._foreign_long_watch = True
if flags & _GLYPH_MASK:
self._buffer_glyph_count += 1
return
if not self._buffer_length:
return
if (
character.isspace() or is_punctuation(character) or is_separator(character)
) and self._buffer_length:
self._word_count += 1
buffer_length: int = self._buffer_length
self._character_count += buffer_length
if buffer_length >= 4:
if self._buffer_accent_count / buffer_length >= 0.5:
self._is_current_word_bad = True
# Word/Buffer ending with an upper case accentuated letter are so rare,
# that we will consider them all as suspicious. Same weight as foreign_long suspicious.
elif (
self._buffer_last_char_accentuated
and self._buffer_last_char.isupper() # type: ignore[union-attr]
and self._buffer_upper_count != buffer_length
):
self._foreign_long_count += 1
self._is_current_word_bad = True
elif self._buffer_glyph_count == 1:
self._is_current_word_bad = True
self._foreign_long_count += 1
if buffer_length >= 24 and self._foreign_long_watch:
probable_camel_cased: bool = (
self._buffer_upper_count > 0
and self._buffer_upper_count / buffer_length <= 0.3
)
if not probable_camel_cased:
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 += buffer_length
self._is_current_word_bad = False
self._foreign_long_watch = False
self._buffer_length = 0
self._buffer_last_char = None
self._buffer_last_char_accentuated = False
self._buffer_accent_count = 0
self._buffer_glyph_count = 0
self._buffer_upper_count = 0
elif (
character not in {"<", ">", "-", "=", "~", "|", "_"}
and not character.isdigit()
and is_symbol(character)
):
self._is_current_word_bad = True
self._buffer_length += 1
self._buffer_last_char = character
self._buffer_last_char_accentuated = False
def reset(self) -> None: # Abstract
self._buffer_length = 0
self._buffer_last_char = None
self._buffer_last_char_accentuated = False
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
self._buffer_accent_count = 0
self._buffer_glyph_count = 0
self._buffer_upper_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
@final
class CjkUncommonPlugin(MessDetectorPlugin):
"""
Detect messy CJK text that probably means nothing.
"""
__slots__ = ("_character_count", "_uncommon_count")
def __init__(self) -> None:
self._character_count: int = 0
self._uncommon_count: int = 0
def eligible(self, character: str) -> bool:
return is_cjk(character)
def feed(self, character: str) -> None:
self._character_count += 1
if is_cjk_uncommon(character):
self._uncommon_count += 1
return
def reset(self) -> None: # Abstract
self._character_count = 0
self._uncommon_count = 0
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
uncommon_form_usage: float = self._uncommon_count / self._character_count
# we can be pretty sure it's garbage when uncommon characters are widely
# used. otherwise it could just be traditional chinese for example.
return uncommon_form_usage / 10 if uncommon_form_usage > 0.5 else 0.0
@final
class ArchaicUpperLowerPlugin(MessDetectorPlugin):
__slots__ = (
"_buf",
"_character_count_since_last_sep",
"_successive_upper_lower_count",
"_successive_upper_lower_count_final",
"_character_count",
"_last_alpha_seen",
"_current_ascii_only",
)
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: str | None = None
self._current_ascii_only: bool = True
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
is_concerned: bool = character.isalpha() and is_case_variable(character)
chunk_sep: bool = not is_concerned
if chunk_sep and self._character_count_since_last_sep > 0:
if (
self._character_count_since_last_sep <= 64
and not character.isdigit()
and not self._current_ascii_only
):
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 and not character.isascii():
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:
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: # Abstract
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
@final
class ArabicIsolatedFormPlugin(MessDetectorPlugin):
__slots__ = ("_character_count", "_isolated_form_count")
def __init__(self) -> None:
self._character_count: int = 0
self._isolated_form_count: int = 0
def reset(self) -> None: # Abstract
self._character_count = 0
self._isolated_form_count = 0
def eligible(self, character: str) -> bool:
return is_arabic(character)
def feed(self, character: str) -> None:
self._character_count += 1
if is_arabic_isolated_form(character):
self._isolated_form_count += 1
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
isolated_form_usage: float = self._isolated_form_count / self._character_count
return isolated_form_usage
@lru_cache(maxsize=1024)
def is_suspiciously_successive_range(
unicode_range_a: str | None, unicode_range_b: str | None
) -> 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
if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
return False
return True
# import time messdetector plugins detection(...)
_DETECTOR_CLASSES: tuple[type[MessDetectorPlugin], ...] = tuple(
md_class for md_class in MessDetectorPlugin.__subclasses__()
)
@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 _DETECTOR_CLASSES]
mean_mess_ratio: float
seq_len: int = len(decoded_sequence)
if seq_len < 511:
step: int = 32
elif seq_len < 1024:
step = 64
else:
step = 128
for block_start in range(0, seq_len, step):
for character in decoded_sequence[block_start : block_start + step]:
for detector in detectors:
if detector.eligible(character):
detector.feed(character)
mean_mess_ratio = sum(dt.ratio for dt in detectors)
if mean_mess_ratio >= maximum_threshold:
break
else:
# Flush last word buffer in SuperWeirdWordPlugin via trailing newline.
for detector in detectors:
if detector.eligible("\n"):
detector.feed("\n")
mean_mess_ratio = sum(dt.ratio for dt in detectors)
if debug:
logger = getLogger("charset_normalizer")
logger.log(
TRACE,
"Mess-detector extended-analysis start. "
f"intermediary_mean_mess_ratio_calc={step} mean_mess_ratio={mean_mess_ratio} "
f"maximum_threshold={maximum_threshold}",
)
if seq_len > 16:
logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}")
logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}")
for dt in detectors:
logger.log(TRACE, f"{dt.__class__}: {dt.ratio}")
return round(mean_mess_ratio, 3)

359
venv/lib/python3.12/site-packages/charset_normalizer/models.py Normal file
View File

@@ -0,0 +1,359 @@
from __future__ import annotations
from encodings.aliases import aliases
from json import dumps
from re import sub
from typing import Any, Iterator, List, Tuple
from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE
from .utils import iana_name, is_multi_byte_encoding, unicode_range
class CharsetMatch:
def __init__(
self,
payload: bytes,
guessed_encoding: str,
mean_mess_ratio: float,
has_sig_or_bom: bool,
languages: CoherenceMatches,
decoded_payload: str | None = None,
preemptive_declaration: str | None = None,
):
self._payload: bytes = payload
self._encoding: str = guessed_encoding
self._mean_mess_ratio: float = mean_mess_ratio
self._languages: CoherenceMatches = languages
self._has_sig_or_bom: bool = has_sig_or_bom
self._unicode_ranges: list[str] | None = None
self._leaves: list[CharsetMatch] = []
self._mean_coherence_ratio: float = 0.0
self._output_payload: bytes | None = None
self._output_encoding: str | None = None
self._string: str | None = decoded_payload
self._preemptive_declaration: str | None = preemptive_declaration
def __eq__(self, other: object) -> bool:
if not isinstance(other, CharsetMatch):
if isinstance(other, str):
return iana_name(other) == self.encoding
return False
return self.encoding == other.encoding and self.fingerprint == other.fingerprint
def __lt__(self, other: object) -> bool:
"""
Implemented to make sorted available upon CharsetMatches items.
"""
if not isinstance(other, CharsetMatch):
raise ValueError
chaos_difference: float = abs(self.chaos - other.chaos)
coherence_difference: float = abs(self.coherence - other.coherence)
# Below 1% difference --> Use Coherence
if chaos_difference < 0.01 and coherence_difference > 0.02:
return self.coherence > other.coherence
elif chaos_difference < 0.01 and coherence_difference <= 0.02:
# When having a difficult decision, use the result that decoded as many multi-byte as possible.
# preserve RAM usage!
if len(self._payload) >= TOO_BIG_SEQUENCE:
return self.chaos < other.chaos
return self.multi_byte_usage > other.multi_byte_usage
return self.chaos < other.chaos
@property
def multi_byte_usage(self) -> float:
return 1.0 - (len(str(self)) / len(self.raw))
def __str__(self) -> str:
# Lazy Str Loading
if self._string is None:
self._string = str(self._payload, self._encoding, "strict")
return self._string
def __repr__(self) -> str:
return f"<CharsetMatch '{self.encoding}' fp({self.fingerprint})>"
def add_submatch(self, other: CharsetMatch) -> None:
if not isinstance(other, CharsetMatch) or other == self:
raise ValueError(
"Unable to add instance <{}> as a submatch of a CharsetMatch".format(
other.__class__
)
)
other._string = None # Unload RAM usage; dirty trick.
self._leaves.append(other)
@property
def encoding(self) -> str:
return self._encoding
@property
def encoding_aliases(self) -> list[str]:
"""
Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
"""
also_known_as: list[str] = []
for u, p in aliases.items():
if self.encoding == u:
also_known_as.append(p)
elif self.encoding == p:
also_known_as.append(u)
return also_known_as
@property
def bom(self) -> bool:
return self._has_sig_or_bom
@property
def byte_order_mark(self) -> bool:
return self._has_sig_or_bom
@property
def languages(self) -> list[str]:
"""
Return the complete list of possible languages found in decoded sequence.
Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
"""
return [e[0] for e in self._languages]
@property
def language(self) -> str:
"""
Most probable language found in decoded sequence. If none were detected or inferred, the property will return
"Unknown".
"""
if not self._languages:
# Trying to infer the language based on the given encoding
# Its either English or we should not pronounce ourselves in certain cases.
if "ascii" in self.could_be_from_charset:
return "English"
# doing it there to avoid circular import
from charset_normalizer.cd import encoding_languages, mb_encoding_languages
languages = (
mb_encoding_languages(self.encoding)
if is_multi_byte_encoding(self.encoding)
else encoding_languages(self.encoding)
)
if len(languages) == 0 or "Latin Based" in languages:
return "Unknown"
return languages[0]
return self._languages[0][0]
@property
def chaos(self) -> float:
return self._mean_mess_ratio
@property
def coherence(self) -> float:
if not self._languages:
return 0.0
return self._languages[0][1]
@property
def percent_chaos(self) -> float:
return round(self.chaos * 100, ndigits=3)
@property
def percent_coherence(self) -> float:
return round(self.coherence * 100, ndigits=3)
@property
def raw(self) -> bytes:
"""
Original untouched bytes.
"""
return self._payload
@property
def submatch(self) -> list[CharsetMatch]:
return self._leaves
@property
def has_submatch(self) -> bool:
return len(self._leaves) > 0
@property
def alphabets(self) -> list[str]:
if self._unicode_ranges is not None:
return self._unicode_ranges
# list detected ranges
detected_ranges: list[str | None] = [unicode_range(char) for char in str(self)]
# filter and sort
self._unicode_ranges = sorted(list({r for r in detected_ranges if r}))
return self._unicode_ranges
@property
def could_be_from_charset(self) -> list[str]:
"""
The complete list of encoding that output the exact SAME str result and therefore could be the originating
encoding.
This list does include the encoding available in property 'encoding'.
"""
return [self._encoding] + [m.encoding for m in self._leaves]
def output(self, encoding: str = "utf_8") -> bytes:
"""
Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
Any errors will be simply ignored by the encoder NOT replaced.
"""
if self._output_encoding is None or self._output_encoding != encoding:
self._output_encoding = encoding
decoded_string = str(self)
if (
self._preemptive_declaration is not None
and self._preemptive_declaration.lower()
not in ["utf-8", "utf8", "utf_8"]
):
patched_header = sub(
RE_POSSIBLE_ENCODING_INDICATION,
lambda m: m.string[m.span()[0] : m.span()[1]].replace(
m.groups()[0],
iana_name(self._output_encoding).replace("_", "-"), # type: ignore[arg-type]
),
decoded_string[:8192],
count=1,
)
decoded_string = patched_header + decoded_string[8192:]
self._output_payload = decoded_string.encode(encoding, "replace")
return self._output_payload # type: ignore
@property
def fingerprint(self) -> int:
"""
Retrieve a hash fingerprint of the decoded payload, used for deduplication.
"""
return hash(str(self))
class CharsetMatches:
"""
Container with every CharsetMatch items ordered by default from most probable to the less one.
Act like a list(iterable) but does not implements all related methods.
"""
def __init__(self, results: list[CharsetMatch] | None = None):
self._results: list[CharsetMatch] = sorted(results) if results else []
def __iter__(self) -> Iterator[CharsetMatch]:
yield from self._results
def __getitem__(self, item: int | str) -> CharsetMatch:
"""
Retrieve a single item either by its position or encoding name (alias may be used here).
Raise KeyError upon invalid index or encoding not present in results.
"""
if isinstance(item, int):
return self._results[item]
if isinstance(item, str):
item = iana_name(item, False)
for result in self._results:
if item in result.could_be_from_charset:
return result
raise KeyError
def __len__(self) -> int:
return len(self._results)
def __bool__(self) -> bool:
return len(self._results) > 0
def append(self, item: CharsetMatch) -> None:
"""
Insert a single match. Will be inserted accordingly to preserve sort.
Can be inserted as a submatch.
"""
if not isinstance(item, CharsetMatch):
raise ValueError(
"Cannot append instance '{}' to CharsetMatches".format(
str(item.__class__)
)
)
# We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
if len(item.raw) < TOO_BIG_SEQUENCE:
for match in self._results:
if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
match.add_submatch(item)
return
self._results.append(item)
self._results = sorted(self._results)
def best(self) -> CharsetMatch | None:
"""
Simply return the first match. Strict equivalent to matches[0].
"""
if not self._results:
return None
return self._results[0]
def first(self) -> CharsetMatch | None:
"""
Redundant method, call the method best(). Kept for BC reasons.
"""
return self.best()
CoherenceMatch = Tuple[str, float]
CoherenceMatches = List[CoherenceMatch]
class CliDetectionResult:
def __init__(
self,
path: str,
encoding: str | None,
encoding_aliases: list[str],
alternative_encodings: list[str],
language: str,
alphabets: list[str],
has_sig_or_bom: bool,
chaos: float,
coherence: float,
unicode_path: str | None,
is_preferred: bool,
):
self.path: str = path
self.unicode_path: str | None = unicode_path
self.encoding: str | None = encoding
self.encoding_aliases: list[str] = encoding_aliases
self.alternative_encodings: list[str] = alternative_encodings
self.language: str = language
self.alphabets: list[str] = alphabets
self.has_sig_or_bom: bool = has_sig_or_bom
self.chaos: float = chaos
self.coherence: float = coherence
self.is_preferred: bool = is_preferred
@property
def __dict__(self) -> dict[str, Any]: # type: ignore
return {
"path": self.path,
"encoding": self.encoding,
"encoding_aliases": self.encoding_aliases,
"alternative_encodings": self.alternative_encodings,
"language": self.language,
"alphabets": self.alphabets,
"has_sig_or_bom": self.has_sig_or_bom,
"chaos": self.chaos,
"coherence": self.coherence,
"unicode_path": self.unicode_path,
"is_preferred": self.is_preferred,
}
def to_json(self) -> str:
return dumps(self.__dict__, ensure_ascii=True, indent=4)

0
venv/lib/python3.12/site-packages/charset_normalizer/py.typed Normal file
View File

420
venv/lib/python3.12/site-packages/charset_normalizer/utils.py Normal file
View File

@@ -0,0 +1,420 @@
from __future__ import annotations
import importlib
import logging
import unicodedata
from bisect import bisect_right
from codecs import IncrementalDecoder
from encodings.aliases import aliases
from functools import lru_cache
from re import findall
from typing import Generator
from _multibytecodec import ( # type: ignore[import-not-found,import]
MultibyteIncrementalDecoder,
)
from .constant import (
ENCODING_MARKS,
IANA_SUPPORTED_SIMILAR,
RE_POSSIBLE_ENCODING_INDICATION,
UNICODE_RANGES_COMBINED,
UNICODE_SECONDARY_RANGE_KEYWORD,
UTF8_MAXIMAL_ALLOCATION,
COMMON_CJK_CHARACTERS,
_LATIN,
_CJK,
_HANGUL,
_KATAKANA,
_HIRAGANA,
_THAI,
_ARABIC,
_ARABIC_ISOLATED_FORM,
_ACCENT_KEYWORDS,
_ACCENTUATED,
)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def _character_flags(character: str) -> int:
"""Compute all name-based classification flags with a single unicodedata.name() call."""
try:
desc: str = unicodedata.name(character)
except ValueError:
return 0
flags: int = 0
if "LATIN" in desc:
flags |= _LATIN
if "CJK" in desc:
flags |= _CJK
if "HANGUL" in desc:
flags |= _HANGUL
if "KATAKANA" in desc:
flags |= _KATAKANA
if "HIRAGANA" in desc:
flags |= _HIRAGANA
if "THAI" in desc:
flags |= _THAI
if "ARABIC" in desc:
flags |= _ARABIC
if "ISOLATED FORM" in desc:
flags |= _ARABIC_ISOLATED_FORM
for kw in _ACCENT_KEYWORDS:
if kw in desc:
flags |= _ACCENTUATED
break
return flags
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_accentuated(character: str) -> bool:
return bool(_character_flags(character) & _ACCENTUATED)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def remove_accent(character: str) -> str:
decomposed: str = unicodedata.decomposition(character)
if not decomposed:
return character
codes: list[str] = decomposed.split(" ")
return chr(int(codes[0], 16))
# Pre-built sorted lookup table for O(log n) binary search in unicode_range().
# Each entry is (range_start, range_end_exclusive, range_name).
_UNICODE_RANGES_SORTED: list[tuple[int, int, str]] = sorted(
(ord_range.start, ord_range.stop, name)
for name, ord_range in UNICODE_RANGES_COMBINED.items()
)
_UNICODE_RANGE_STARTS: list[int] = [e[0] for e in _UNICODE_RANGES_SORTED]
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def unicode_range(character: str) -> str | None:
"""
Retrieve the Unicode range official name from a single character.
"""
character_ord: int = ord(character)
# Binary search: find the rightmost range whose start <= character_ord
idx = bisect_right(_UNICODE_RANGE_STARTS, character_ord) - 1
if idx >= 0:
start, stop, name = _UNICODE_RANGES_SORTED[idx]
if character_ord < stop:
return name
return None
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_latin(character: str) -> bool:
return bool(_character_flags(character) & _LATIN)
@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: str | None = 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: str | None = unicode_range(character)
if character_range is None:
return False
return "Forms" in character_range and character_category != "Lo"
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_emoticon(character: str) -> bool:
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Emoticons" in character_range or "Pictographs" in character_range
@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 or character_category in {"Po", "Pd", "Pc"}
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_case_variable(character: str) -> bool:
return character.islower() != character.isupper()
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk(character: str) -> bool:
return bool(_character_flags(character) & _CJK)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hiragana(character: str) -> bool:
return bool(_character_flags(character) & _HIRAGANA)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_katakana(character: str) -> bool:
return bool(_character_flags(character) & _KATAKANA)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hangul(character: str) -> bool:
return bool(_character_flags(character) & _HANGUL)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_thai(character: str) -> bool:
return bool(_character_flags(character) & _THAI)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic(character: str) -> bool:
return bool(_character_flags(character) & _ARABIC)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic_isolated_form(character: str) -> bool:
return bool(_character_flags(character) & _ARABIC_ISOLATED_FORM)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk_uncommon(character: str) -> bool:
return character not in COMMON_CJK_CHARACTERS
@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 != "\ufeff" # bug discovered in Python,
# Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space.
)
def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> str | None:
"""
Extract using ASCII-only decoder any specified encoding in the first n-bytes.
"""
if not isinstance(sequence, (bytes, bytearray)):
raise TypeError
seq_len: int = len(sequence)
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("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if encoding_alias == specified_encoding:
return encoding_iana
if encoding_iana == specified_encoding:
return encoding_iana
return None
@lru_cache(maxsize=128)
def is_multi_byte_encoding(name: str) -> bool:
"""
Verify is a specific encoding is a multi byte one based on it IANA name
"""
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(f"encodings.{name}").IncrementalDecoder,
MultibyteIncrementalDecoder,
)
def identify_sig_or_bom(sequence: bytes) -> tuple[str | None, bytes]:
"""
Identify and extract SIG/BOM in given sequence.
"""
for iana_encoding in ENCODING_MARKS:
marks: bytes | list[bytes] = ENCODING_MARKS[iana_encoding]
if isinstance(marks, bytes):
marks = [marks]
for mark in marks:
if sequence.startswith(mark):
return iana_encoding, mark
return None, b""
def should_strip_sig_or_bom(iana_encoding: str) -> bool:
return iana_encoding not in {"utf_16", "utf_32"}
def iana_name(cp_name: str, strict: bool = True) -> str:
"""Returns the Python normalized encoding name (Not the IANA official name)."""
cp_name = cp_name.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if cp_name in [encoding_alias, encoding_iana]:
return encoding_iana
if strict:
raise ValueError(f"Unable to retrieve IANA for '{cp_name}'")
return cp_name
def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
return 0.0
decoder_a = importlib.import_module(f"encodings.{iana_name_a}").IncrementalDecoder
decoder_b = importlib.import_module(f"encodings.{iana_name_b}").IncrementalDecoder
id_a: IncrementalDecoder = decoder_a(errors="ignore")
id_b: IncrementalDecoder = decoder_b(errors="ignore")
character_match_count: int = 0
for i in range(256):
to_be_decoded: bytes = bytes([i])
if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
character_match_count += 1
return character_match_count / 256
def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
"""
Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
the function cp_similarity.
"""
return (
iana_name_a in IANA_SUPPORTED_SIMILAR
and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]
)
def set_logging_handler(
name: str = "charset_normalizer",
level: int = logging.INFO,
format_string: str = "%(asctime)s | %(levelname)s | %(message)s",
) -> None:
logger = logging.getLogger(name)
logger.setLevel(level)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter(format_string))
logger.addHandler(handler)
def cut_sequence_chunks(
sequences: bytes,
encoding_iana: str,
offsets: range,
chunk_size: int,
bom_or_sig_available: bool,
strip_sig_or_bom: bool,
sig_payload: bytes,
is_multi_byte_decoder: bool,
decoded_payload: str | None = None,
) -> 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:
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

8
venv/lib/python3.12/site-packages/charset_normalizer/version.py Normal file
View File

@@ -0,0 +1,8 @@
"""
Expose version
"""
from __future__ import annotations
__version__ = "3.4.5"
VERSION = __version__.split(".")

51
venv/lib/python3.12/site-packages/dotenv/__init__.py Normal file
View File

@@ -0,0 +1,51 @@
from typing import Any, Optional
from .main import dotenv_values, find_dotenv, get_key, load_dotenv, set_key, unset_key
def load_ipython_extension(ipython: Any) -> None:
from .ipython import load_ipython_extension
load_ipython_extension(ipython)
def get_cli_string(
path: Optional[str] = None,
action: Optional[str] = None,
key: Optional[str] = None,
value: Optional[str] = None,
quote: Optional[str] = None,
):
"""Returns a string suitable for running as a shell script.
Useful for converting a arguments passed to a fabric task
to be passed to a `local` or `run` command.
"""
command = ["dotenv"]
if quote:
command.append(f"-q {quote}")
if path:
command.append(f"-f {path}")
if action:
command.append(action)
if key:
command.append(key)
if value:
if " " in value:
command.append(f'"{value}"')
else:
command.append(value)
return " ".join(command).strip()
__all__ = [
"get_cli_string",
"load_dotenv",
"dotenv_values",
"get_key",
"set_key",
"unset_key",
"find_dotenv",
"load_ipython_extension",
]

6
venv/lib/python3.12/site-packages/dotenv/__main__.py Normal file
View File

@@ -0,0 +1,6 @@
"""Entry point for cli, enables execution with `python -m dotenv`"""
from .cli import cli
if __name__ == "__main__":
cli()

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/__main__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/cli.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/ipython.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/main.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/parser.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/variables.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/dotenv/__pycache__/version.cpython-312.pyc Normal file
View File

Binary file not shown.

236
venv/lib/python3.12/site-packages/dotenv/cli.py Normal file
View File

@@ -0,0 +1,236 @@
import json
import os
import shlex
import sys
from contextlib import contextmanager
from typing import IO, Any, Dict, Iterator, List, Optional
if sys.platform == "win32":
from subprocess import Popen
try:
import click
except ImportError:
sys.stderr.write(
"It seems python-dotenv is not installed with cli option. \n"
'Run pip install "python-dotenv[cli]" to fix this.'
)
sys.exit(1)
from .main import dotenv_values, set_key, unset_key
from .version import __version__
def enumerate_env() -> Optional[str]:
"""
Return a path for the ${pwd}/.env file.
If pwd does not exist, return None.
"""
try:
cwd = os.getcwd()
except FileNotFoundError:
return None
path = os.path.join(cwd, ".env")
return path
@click.group()
@click.option(
"-f",
"--file",
default=enumerate_env(),
type=click.Path(file_okay=True),
help="Location of the .env file, defaults to .env file in current working directory.",
)
@click.option(
"-q",
"--quote",
default="always",
type=click.Choice(["always", "never", "auto"]),
help="Whether to quote or not the variable values. Default mode is always. This does not affect parsing.",
)
@click.option(
"-e",
"--export",
default=False,
type=click.BOOL,
help="Whether to write the dot file as an executable bash script.",
)
@click.version_option(version=__version__)
@click.pass_context
def cli(ctx: click.Context, file: Any, quote: Any, export: Any) -> None:
"""This script is used to set, get or unset values from a .env file."""
ctx.obj = {"QUOTE": quote, "EXPORT": export, "FILE": file}
@contextmanager
def stream_file(path: os.PathLike) -> Iterator[IO[str]]:
"""
Open a file and yield the corresponding (decoded) stream.
Exits with error code 2 if the file cannot be opened.
"""
try:
with open(path) as stream:
yield stream
except OSError as exc:
print(f"Error opening env file: {exc}", file=sys.stderr)
sys.exit(2)
@cli.command(name="list")
@click.pass_context
@click.option(
"--format",
"output_format",
default="simple",
type=click.Choice(["simple", "json", "shell", "export"]),
help="The format in which to display the list. Default format is simple, "
"which displays name=value without quotes.",
)
def list_values(ctx: click.Context, output_format: str) -> None:
"""Display all the stored key/value."""
file = ctx.obj["FILE"]
with stream_file(file) as stream:
values = dotenv_values(stream=stream)
if output_format == "json":
click.echo(json.dumps(values, indent=2, sort_keys=True))
else:
prefix = "export " if output_format == "export" else ""
for k in sorted(values):
v = values[k]
if v is not None:
if output_format in ("export", "shell"):
v = shlex.quote(v)
click.echo(f"{prefix}{k}={v}")
@cli.command(name="set")
@click.pass_context
@click.argument("key", required=True)
@click.argument("value", required=True)
def set_value(ctx: click.Context, key: Any, value: Any) -> None:
"""
Store the given key/value.
This doesn't follow symlinks, to avoid accidentally modifying a file at a
potentially untrusted path.
"""
file = ctx.obj["FILE"]
quote = ctx.obj["QUOTE"]
export = ctx.obj["EXPORT"]
success, key, value = set_key(file, key, value, quote, export)
if success:
click.echo(f"{key}={value}")
else:
sys.exit(1)
@cli.command()
@click.pass_context
@click.argument("key", required=True)
def get(ctx: click.Context, key: Any) -> None:
"""Retrieve the value for the given key."""
file = ctx.obj["FILE"]
with stream_file(file) as stream:
values = dotenv_values(stream=stream)
stored_value = values.get(key)
if stored_value:
click.echo(stored_value)
else:
sys.exit(1)
@cli.command()
@click.pass_context
@click.argument("key", required=True)
def unset(ctx: click.Context, key: Any) -> None:
"""
Removes the given key.
This doesn't follow symlinks, to avoid accidentally modifying a file at a
potentially untrusted path.
"""
file = ctx.obj["FILE"]
quote = ctx.obj["QUOTE"]
success, key = unset_key(file, key, quote)
if success:
click.echo(f"Successfully removed {key}")
else:
sys.exit(1)
@cli.command(
context_settings={
"allow_extra_args": True,
"allow_interspersed_args": False,
"ignore_unknown_options": True,
}
)
@click.pass_context
@click.option(
"--override/--no-override",
default=True,
help="Override variables from the environment file with those from the .env file.",
)
@click.argument("commandline", nargs=-1, type=click.UNPROCESSED)
def run(ctx: click.Context, override: bool, commandline: tuple[str, ...]) -> None:
"""Run command with environment variables present."""
file = ctx.obj["FILE"]
if not os.path.isfile(file):
raise click.BadParameter(
f"Invalid value for '-f' \"{file}\" does not exist.", ctx=ctx
)
dotenv_as_dict = {
k: v
for (k, v) in dotenv_values(file).items()
if v is not None and (override or k not in os.environ)
}
if not commandline:
click.echo("No command given.")
sys.exit(1)
run_command([*commandline, *ctx.args], dotenv_as_dict)
def run_command(command: List[str], env: Dict[str, str]) -> None:
"""Replace the current process with the specified command.
Replaces the current process with the specified command and the variables from `env`
added in the current environment variables.
Parameters
----------
command: List[str]
The command and it's parameters
env: Dict
The additional environment variables
Returns
-------
None
This function does not return any value. It replaces the current process with the new one.
"""
# copy the current environment variables and add the vales from
# `env`
cmd_env = os.environ.copy()
cmd_env.update(env)
if sys.platform == "win32":
# execvpe on Windows returns control immediately
# rather than once the command has finished.
p = Popen(command, universal_newlines=True, bufsize=0, shell=False, env=cmd_env)
_, _ = p.communicate()
sys.exit(p.returncode)
else:
os.execvpe(command[0], args=command, env=cmd_env)

50
venv/lib/python3.12/site-packages/dotenv/ipython.py Normal file
View File

@@ -0,0 +1,50 @@
from IPython.core.magic import Magics, line_magic, magics_class # type: ignore
from IPython.core.magic_arguments import (
argument,
magic_arguments,
parse_argstring,
) # type: ignore
from .main import find_dotenv, load_dotenv
@magics_class
class IPythonDotEnv(Magics):
@magic_arguments()
@argument(
"-o",
"--override",
action="store_true",
help="Indicate to override existing variables",
)
@argument(
"-v",
"--verbose",
action="store_true",
help="Indicate function calls to be verbose",
)
@argument(
"dotenv_path",
nargs="?",
type=str,
default=".env",
help="Search in increasingly higher folders for the `dotenv_path`",
)
@line_magic
def dotenv(self, line):
args = parse_argstring(self.dotenv, line)
# Locate the .env file
dotenv_path = args.dotenv_path
try:
dotenv_path = find_dotenv(dotenv_path, True, True)
except IOError:
print("cannot find .env file")
return
# Load the .env file
load_dotenv(dotenv_path, verbose=args.verbose, override=args.override)
def load_ipython_extension(ipython):
"""Register the %dotenv magic."""
ipython.register_magics(IPythonDotEnv)

480
venv/lib/python3.12/site-packages/dotenv/main.py Normal file
View File

@@ -0,0 +1,480 @@
import io
import logging
import os
import pathlib
import stat
import sys
import tempfile
from collections import OrderedDict
from contextlib import contextmanager
from typing import IO, Dict, Iterable, Iterator, Mapping, Optional, Tuple, Union
from .parser import Binding, parse_stream
from .variables import parse_variables
# A type alias for a string path to be used for the paths in this file.
# These paths may flow to `open()` and `os.replace()`.
StrPath = Union[str, "os.PathLike[str]"]
logger = logging.getLogger(__name__)
def _load_dotenv_disabled() -> bool:
"""
Determine if dotenv loading has been disabled.
"""
if "PYTHON_DOTENV_DISABLED" not in os.environ:
return False
value = os.environ["PYTHON_DOTENV_DISABLED"].casefold()
return value in {"1", "true", "t", "yes", "y"}
def with_warn_for_invalid_lines(mappings: Iterator[Binding]) -> Iterator[Binding]:
for mapping in mappings:
if mapping.error:
logger.warning(
"python-dotenv could not parse statement starting at line %s",
mapping.original.line,
)
yield mapping
class DotEnv:
def __init__(
self,
dotenv_path: Optional[StrPath],
stream: Optional[IO[str]] = None,
verbose: bool = False,
encoding: Optional[str] = None,
interpolate: bool = True,
override: bool = True,
) -> None:
self.dotenv_path: Optional[StrPath] = dotenv_path
self.stream: Optional[IO[str]] = stream
self._dict: Optional[Dict[str, Optional[str]]] = None
self.verbose: bool = verbose
self.encoding: Optional[str] = encoding
self.interpolate: bool = interpolate
self.override: bool = override
@contextmanager
def _get_stream(self) -> Iterator[IO[str]]:
if self.dotenv_path and _is_file_or_fifo(self.dotenv_path):
with open(self.dotenv_path, encoding=self.encoding) as stream:
yield stream
elif self.stream is not None:
yield self.stream
else:
if self.verbose:
logger.info(
"python-dotenv could not find configuration file %s.",
self.dotenv_path or ".env",
)
yield io.StringIO("")
def dict(self) -> Dict[str, Optional[str]]:
"""Return dotenv as dict"""
if self._dict:
return self._dict
raw_values = self.parse()
if self.interpolate:
self._dict = OrderedDict(
resolve_variables(raw_values, override=self.override)
)
else:
self._dict = OrderedDict(raw_values)
return self._dict
def parse(self) -> Iterator[Tuple[str, Optional[str]]]:
with self._get_stream() as stream:
for mapping in with_warn_for_invalid_lines(parse_stream(stream)):
if mapping.key is not None:
yield mapping.key, mapping.value
def set_as_environment_variables(self) -> bool:
"""
Load the current dotenv as system environment variable.
"""
if not self.dict():
return False
for k, v in self.dict().items():
if k in os.environ and not self.override:
continue
if v is not None:
os.environ[k] = v
return True
def get(self, key: str) -> Optional[str]:
""" """
data = self.dict()
if key in data:
return data[key]
if self.verbose:
logger.warning("Key %s not found in %s.", key, self.dotenv_path)
return None
def get_key(
dotenv_path: StrPath,
key_to_get: str,
encoding: Optional[str] = "utf-8",
) -> Optional[str]:
"""
Get the value of a given key from the given .env.
Returns `None` if the key isn't found or doesn't have a value.
"""
return DotEnv(dotenv_path, verbose=True, encoding=encoding).get(key_to_get)
@contextmanager
def rewrite(
path: StrPath,
encoding: Optional[str],
follow_symlinks: bool = False,
) -> Iterator[Tuple[IO[str], IO[str]]]:
if follow_symlinks:
path = os.path.realpath(path)
try:
source: IO[str] = open(path, encoding=encoding)
try:
path_stat = os.lstat(path)
original_mode: Optional[int] = (
stat.S_IMODE(path_stat.st_mode)
if stat.S_ISREG(path_stat.st_mode)
else None
)
except BaseException:
source.close()
raise
except FileNotFoundError:
source = io.StringIO("")
original_mode = None
with tempfile.NamedTemporaryFile(
mode="w",
encoding=encoding,
delete=False,
prefix=".tmp_",
dir=os.path.dirname(os.path.abspath(path)),
) as dest:
dest_path = pathlib.Path(dest.name)
error = None
try:
with source:
yield (source, dest)
except BaseException as err:
error = err
if error is None:
try:
if original_mode is not None:
os.chmod(dest_path, original_mode)
os.replace(dest_path, path)
except BaseException:
dest_path.unlink(missing_ok=True)
raise
else:
dest_path.unlink(missing_ok=True)
raise error from None
def set_key(
dotenv_path: StrPath,
key_to_set: str,
value_to_set: str,
quote_mode: str = "always",
export: bool = False,
encoding: Optional[str] = "utf-8",
follow_symlinks: bool = False,
) -> Tuple[Optional[bool], str, str]:
"""
Adds or Updates a key/value to the given .env
The target .env file is created if it doesn't exist.
This function doesn't follow symlinks by default, to avoid accidentally
modifying a file at a potentially untrusted path. If you don't need this
protection and need symlinks to be followed, use `follow_symlinks`.
"""
if quote_mode not in ("always", "auto", "never"):
raise ValueError(f"Unknown quote_mode: {quote_mode}")
quote = quote_mode == "always" or (
quote_mode == "auto" and not value_to_set.isalnum()
)
if quote:
value_out = "'{}'".format(value_to_set.replace("'", "\\'"))
else:
value_out = value_to_set
if export:
line_out = f"export {key_to_set}={value_out}\n"
else:
line_out = f"{key_to_set}={value_out}\n"
with rewrite(dotenv_path, encoding=encoding, follow_symlinks=follow_symlinks) as (
source,
dest,
):
replaced = False
missing_newline = False
for mapping in with_warn_for_invalid_lines(parse_stream(source)):
if mapping.key == key_to_set:
dest.write(line_out)
replaced = True
else:
dest.write(mapping.original.string)
missing_newline = not mapping.original.string.endswith("\n")
if not replaced:
if missing_newline:
dest.write("\n")
dest.write(line_out)
return True, key_to_set, value_to_set
def unset_key(
dotenv_path: StrPath,
key_to_unset: str,
quote_mode: str = "always",
encoding: Optional[str] = "utf-8",
follow_symlinks: bool = False,
) -> Tuple[Optional[bool], str]:
"""
Removes a given key from the given `.env` file.
If the .env path given doesn't exist, fails.
If the given key doesn't exist in the .env, fails.
This function doesn't follow symlinks by default, to avoid accidentally
modifying a file at a potentially untrusted path. If you don't need this
protection and need symlinks to be followed, use `follow_symlinks`.
"""
if not os.path.exists(dotenv_path):
logger.warning("Can't delete from %s - it doesn't exist.", dotenv_path)
return None, key_to_unset
removed = False
with rewrite(dotenv_path, encoding=encoding, follow_symlinks=follow_symlinks) as (
source,
dest,
):
for mapping in with_warn_for_invalid_lines(parse_stream(source)):
if mapping.key == key_to_unset:
removed = True
else:
dest.write(mapping.original.string)
if not removed:
logger.warning(
"Key %s not removed from %s - key doesn't exist.", key_to_unset, dotenv_path
)
return None, key_to_unset
return removed, key_to_unset
def resolve_variables(
values: Iterable[Tuple[str, Optional[str]]],
override: bool,
) -> Mapping[str, Optional[str]]:
new_values: Dict[str, Optional[str]] = {}
for name, value in values:
if value is None:
result = None
else:
atoms = parse_variables(value)
env: Dict[str, Optional[str]] = {}
if override:
env.update(os.environ) # type: ignore
env.update(new_values)
else:
env.update(new_values)
env.update(os.environ) # type: ignore
result = "".join(atom.resolve(env) for atom in atoms)
new_values[name] = result
return new_values
def _walk_to_root(path: str) -> Iterator[str]:
"""
Yield directories starting from the given directory up to the root
"""
if not os.path.exists(path):
raise IOError("Starting path not found")
if os.path.isfile(path):
path = os.path.dirname(path)
last_dir = None
current_dir = os.path.abspath(path)
while last_dir != current_dir:
yield current_dir
parent_dir = os.path.abspath(os.path.join(current_dir, os.path.pardir))
last_dir, current_dir = current_dir, parent_dir
def find_dotenv(
filename: str = ".env",
raise_error_if_not_found: bool = False,
usecwd: bool = False,
) -> str:
"""
Search in increasingly higher folders for the given file
Returns path to the file if found, or an empty string otherwise
"""
def _is_interactive():
"""Decide whether this is running in a REPL or IPython notebook"""
if hasattr(sys, "ps1") or hasattr(sys, "ps2"):
return True
try:
main = __import__("__main__", None, None, fromlist=["__file__"])
except ModuleNotFoundError:
return False
return not hasattr(main, "__file__")
def _is_debugger():
return sys.gettrace() is not None
if usecwd or _is_interactive() or _is_debugger() or getattr(sys, "frozen", False):
# Should work without __file__, e.g. in REPL or IPython notebook.
path = os.getcwd()
else:
# will work for .py files
frame = sys._getframe()
current_file = __file__
while frame.f_code.co_filename == current_file or not os.path.exists(
frame.f_code.co_filename
):
assert frame.f_back is not None
frame = frame.f_back
frame_filename = frame.f_code.co_filename
path = os.path.dirname(os.path.abspath(frame_filename))
for dirname in _walk_to_root(path):
check_path = os.path.join(dirname, filename)
if _is_file_or_fifo(check_path):
return check_path
if raise_error_if_not_found:
raise IOError("File not found")
return ""
def load_dotenv(
dotenv_path: Optional[StrPath] = None,
stream: Optional[IO[str]] = None,
verbose: bool = False,
override: bool = False,
interpolate: bool = True,
encoding: Optional[str] = "utf-8",
) -> bool:
"""Parse a .env file and then load all the variables found as environment variables.
Parameters:
dotenv_path: Absolute or relative path to .env file.
stream: Text stream (such as `io.StringIO`) with .env content, used if
`dotenv_path` is `None`.
verbose: Whether to output a warning the .env file is missing.
override: Whether to override the system environment variables with the variables
from the `.env` file.
encoding: Encoding to be used to read the file.
Returns:
Bool: True if at least one environment variable is set else False
If both `dotenv_path` and `stream` are `None`, `find_dotenv()` is used to find the
.env file with it's default parameters. If you need to change the default parameters
of `find_dotenv()`, you can explicitly call `find_dotenv()` and pass the result
to this function as `dotenv_path`.
If the environment variable `PYTHON_DOTENV_DISABLED` is set to a truthy value,
.env loading is disabled.
"""
if _load_dotenv_disabled():
logger.debug(
"python-dotenv: .env loading disabled by PYTHON_DOTENV_DISABLED environment variable"
)
return False
if dotenv_path is None and stream is None:
dotenv_path = find_dotenv()
dotenv = DotEnv(
dotenv_path=dotenv_path,
stream=stream,
verbose=verbose,
interpolate=interpolate,
override=override,
encoding=encoding,
)
return dotenv.set_as_environment_variables()
def dotenv_values(
dotenv_path: Optional[StrPath] = None,
stream: Optional[IO[str]] = None,
verbose: bool = False,
interpolate: bool = True,
encoding: Optional[str] = "utf-8",
) -> Dict[str, Optional[str]]:
"""
Parse a .env file and return its content as a dict.
The returned dict will have `None` values for keys without values in the .env file.
For example, `foo=bar` results in `{"foo": "bar"}` whereas `foo` alone results in
`{"foo": None}`
Parameters:
dotenv_path: Absolute or relative path to the .env file.
stream: `StringIO` object with .env content, used if `dotenv_path` is `None`.
verbose: Whether to output a warning if the .env file is missing.
encoding: Encoding to be used to read the file.
If both `dotenv_path` and `stream` are `None`, `find_dotenv()` is used to find the
.env file.
"""
if dotenv_path is None and stream is None:
dotenv_path = find_dotenv()
return DotEnv(
dotenv_path=dotenv_path,
stream=stream,
verbose=verbose,
interpolate=interpolate,
override=True,
encoding=encoding,
).dict()
def _is_file_or_fifo(path: StrPath) -> bool:
"""
Return True if `path` exists and is either a regular file or a FIFO.
"""
if os.path.isfile(path):
return True
try:
st = os.stat(path)
except (FileNotFoundError, OSError):
return False
return stat.S_ISFIFO(st.st_mode)

182
venv/lib/python3.12/site-packages/dotenv/parser.py Normal file
View File

@@ -0,0 +1,182 @@
import codecs
import re
from typing import (
IO,
Iterator,
Match,
NamedTuple,
Optional,
Pattern,
Sequence,
)
def make_regex(string: str, extra_flags: int = 0) -> Pattern[str]:
return re.compile(string, re.UNICODE | extra_flags)
_newline = make_regex(r"(\r\n|\n|\r)")
_multiline_whitespace = make_regex(r"\s*", extra_flags=re.MULTILINE)
_whitespace = make_regex(r"[^\S\r\n]*")
_export = make_regex(r"(?:export[^\S\r\n]+)?")
_single_quoted_key = make_regex(r"'([^']+)'")
_unquoted_key = make_regex(r"([^=\#\s]+)")
_equal_sign = make_regex(r"(=[^\S\r\n]*)")
_single_quoted_value = make_regex(r"'((?:\\'|[^'])*)'")
_double_quoted_value = make_regex(r'"((?:\\"|[^"])*)"')
_unquoted_value = make_regex(r"([^\r\n]*)")
_comment = make_regex(r"(?:[^\S\r\n]*#[^\r\n]*)?")
_end_of_line = make_regex(r"[^\S\r\n]*(?:\r\n|\n|\r|$)")
_rest_of_line = make_regex(r"[^\r\n]*(?:\r|\n|\r\n)?")
_double_quote_escapes = make_regex(r"\\[\\'\"abfnrtv]")
_single_quote_escapes = make_regex(r"\\[\\']")
class Original(NamedTuple):
string: str
line: int
class Binding(NamedTuple):
key: Optional[str]
value: Optional[str]
original: Original
error: bool
class Position:
def __init__(self, chars: int, line: int) -> None:
self.chars = chars
self.line = line
@classmethod
def start(cls) -> "Position":
return cls(chars=0, line=1)
def set(self, other: "Position") -> None:
self.chars = other.chars
self.line = other.line
def advance(self, string: str) -> None:
self.chars += len(string)
self.line += len(re.findall(_newline, string))
class Error(Exception):
pass
class Reader:
def __init__(self, stream: IO[str]) -> None:
self.string = stream.read()
self.position = Position.start()
self.mark = Position.start()
def has_next(self) -> bool:
return self.position.chars < len(self.string)
def set_mark(self) -> None:
self.mark.set(self.position)
def get_marked(self) -> Original:
return Original(
string=self.string[self.mark.chars : self.position.chars],
line=self.mark.line,
)
def peek(self, count: int) -> str:
return self.string[self.position.chars : self.position.chars + count]
def read(self, count: int) -> str:
result = self.string[self.position.chars : self.position.chars + count]
if len(result) < count:
raise Error("read: End of string")
self.position.advance(result)
return result
def read_regex(self, regex: Pattern[str]) -> Sequence[str]:
match = regex.match(self.string, self.position.chars)
if match is None:
raise Error("read_regex: Pattern not found")
self.position.advance(self.string[match.start() : match.end()])
return match.groups()
def decode_escapes(regex: Pattern[str], string: str) -> str:
def decode_match(match: Match[str]) -> str:
return codecs.decode(match.group(0), "unicode-escape") # type: ignore
return regex.sub(decode_match, string)
def parse_key(reader: Reader) -> Optional[str]:
char = reader.peek(1)
if char == "#":
return None
elif char == "'":
(key,) = reader.read_regex(_single_quoted_key)
else:
(key,) = reader.read_regex(_unquoted_key)
return key
def parse_unquoted_value(reader: Reader) -> str:
(part,) = reader.read_regex(_unquoted_value)
return re.sub(r"\s+#.*", "", part).rstrip()
def parse_value(reader: Reader) -> str:
char = reader.peek(1)
if char == "'":
(value,) = reader.read_regex(_single_quoted_value)
return decode_escapes(_single_quote_escapes, value)
elif char == '"':
(value,) = reader.read_regex(_double_quoted_value)
return decode_escapes(_double_quote_escapes, value)
elif char in ("", "\n", "\r"):
return ""
else:
return parse_unquoted_value(reader)
def parse_binding(reader: Reader) -> Binding:
reader.set_mark()
try:
reader.read_regex(_multiline_whitespace)
if not reader.has_next():
return Binding(
key=None,
value=None,
original=reader.get_marked(),
error=False,
)
reader.read_regex(_export)
key = parse_key(reader)
reader.read_regex(_whitespace)
if reader.peek(1) == "=":
reader.read_regex(_equal_sign)
value: Optional[str] = parse_value(reader)
else:
value = None
reader.read_regex(_comment)
reader.read_regex(_end_of_line)
return Binding(
key=key,
value=value,
original=reader.get_marked(),
error=False,
)
except Error:
reader.read_regex(_rest_of_line)
return Binding(
key=None,
value=None,
original=reader.get_marked(),
error=True,
)
def parse_stream(stream: IO[str]) -> Iterator[Binding]:
reader = Reader(stream)
while reader.has_next():
yield parse_binding(reader)

1
venv/lib/python3.12/site-packages/dotenv/py.typed Normal file
View File

@@ -0,0 +1 @@
# Marker file for PEP 561

86
venv/lib/python3.12/site-packages/dotenv/variables.py Normal file
View File

@@ -0,0 +1,86 @@
import re
from abc import ABCMeta, abstractmethod
from typing import Iterator, Mapping, Optional, Pattern
_posix_variable: Pattern[str] = re.compile(
r"""
\$\{
(?P<name>[^\}:]*)
(?::-
(?P<default>[^\}]*)
)?
\}
""",
re.VERBOSE,
)
class Atom(metaclass=ABCMeta):
def __ne__(self, other: object) -> bool:
result = self.__eq__(other)
if result is NotImplemented:
return NotImplemented
return not result
@abstractmethod
def resolve(self, env: Mapping[str, Optional[str]]) -> str: ...
class Literal(Atom):
def __init__(self, value: str) -> None:
self.value = value
def __repr__(self) -> str:
return f"Literal(value={self.value})"
def __eq__(self, other: object) -> bool:
if not isinstance(other, self.__class__):
return NotImplemented
return self.value == other.value
def __hash__(self) -> int:
return hash((self.__class__, self.value))
def resolve(self, env: Mapping[str, Optional[str]]) -> str:
return self.value
class Variable(Atom):
def __init__(self, name: str, default: Optional[str]) -> None:
self.name = name
self.default = default
def __repr__(self) -> str:
return f"Variable(name={self.name}, default={self.default})"
def __eq__(self, other: object) -> bool:
if not isinstance(other, self.__class__):
return NotImplemented
return (self.name, self.default) == (other.name, other.default)
def __hash__(self) -> int:
return hash((self.__class__, self.name, self.default))
def resolve(self, env: Mapping[str, Optional[str]]) -> str:
default = self.default if self.default is not None else ""
result = env.get(self.name, default)
return result if result is not None else ""
def parse_variables(value: str) -> Iterator[Atom]:
cursor = 0
for match in _posix_variable.finditer(value):
(start, end) = match.span()
name = match["name"]
default = match["default"]
if start > cursor:
yield Literal(value=value[cursor:start])
yield Variable(name=name, default=default)
cursor = end
length = len(value)
if cursor < length:
yield Literal(value=value[cursor:length])

1
venv/lib/python3.12/site-packages/dotenv/version.py Normal file
View File

@@ -0,0 +1 @@
__version__ = "1.2.2"

1
venv/lib/python3.12/site-packages/idna-3.11.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

209
venv/lib/python3.12/site-packages/idna-3.11.dist-info/METADATA Normal file
View File

@@ -0,0 +1,209 @@
Metadata-Version: 2.4
Name: idna
Version: 3.11
Summary: Internationalized Domain Names in Applications (IDNA)
Author-email: Kim Davies <kim+pypi@gumleaf.org>
Requires-Python: >=3.8
Description-Content-Type: text/x-rst
License-Expression: BSD-3-Clause
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: System Administrators
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Internet :: Name Service (DNS)
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Utilities
License-File: LICENSE.md
Requires-Dist: ruff >= 0.6.2 ; extra == "all"
Requires-Dist: mypy >= 1.11.2 ; extra == "all"
Requires-Dist: pytest >= 8.3.2 ; extra == "all"
Requires-Dist: flake8 >= 7.1.1 ; extra == "all"
Project-URL: Changelog, https://github.com/kjd/idna/blob/master/HISTORY.rst
Project-URL: Issue tracker, https://github.com/kjd/idna/issues
Project-URL: Source, https://github.com/kjd/idna
Provides-Extra: all
Internationalized Domain Names in Applications (IDNA)
=====================================================
Support for `Internationalized Domain Names in
Applications (IDNA) <https://tools.ietf.org/html/rfc5891>`_
and `Unicode IDNA Compatibility Processing
<https://unicode.org/reports/tr46/>`_.
The latest versions of these standards supplied here provide
more comprehensive language coverage and reduce the potential of
allowing domains with known security vulnerabilities. This library
is a suitable replacement for the “encodings.idna”
module that comes with the Python standard library, but which
only supports an older superseded IDNA specification from 2003.
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
------------
This package is available for installation from PyPI via the
typical mechanisms, such as:
.. code-block:: bash
$ python3 -m pip install idna
Usage
-----
For typical usage, the ``encode`` and ``decode`` functions will take a
domain name argument and perform a conversion to ASCII compatible encoding
(known as A-labels), or to Unicode strings (known as 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
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)
+++++++++++++++++++++++++++++++
This library provides support for `Unicode IDNA Compatibility
Processing <https://unicode.org/reports/tr46/>`_ which normalizes input from
different potential ways a user may input a domain prior to performing the IDNA
conversion operations. This functionality, known as a
`mapping <https://tools.ietf.org/html/rfc5895>`_, is considered by the
specification to be a local user-interface issue distinct from IDNA
conversion functionality.
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
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 position in the string (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 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 used for IDNA and
UTS 46 conversions. Implementers 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 be used 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 3.8 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 interpreter support.
Support for older versions are likely to be removed from new releases
as automated tests can no longer easily be run, i.e. once the Python
version is officially end-of-life.
* **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 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.
* **Transitional processing**. Unicode 16.0.0 removed transitional
processing so the `transitional` argument for the encode() method
no longer has any effect and will be removed at a later date.

22
venv/lib/python3.12/site-packages/idna-3.11.dist-info/RECORD Normal file
View File

@@ -0,0 +1,22 @@
idna-3.11.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
idna-3.11.dist-info/METADATA,sha256=fCwSww9SuiN8TIHllFSASUQCW55hAs8dzKnr9RaEEbA,8378
idna-3.11.dist-info/RECORD,,
idna-3.11.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
idna-3.11.dist-info/licenses/LICENSE.md,sha256=t6M2q_OwThgOwGXN0W5wXQeeHMehT5EKpukYfza5zYc,1541
idna/__init__.py,sha256=MPqNDLZbXqGaNdXxAFhiqFPKEQXju2jNQhCey6-5eJM,868
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=M2SGWN7cs_6B32QmKTyTN6xQGZeYQgQ2wiX3_DR6loE,3438
idna/compat.py,sha256=RzLy6QQCdl9784aFhb2EX9EKGCJjg0P3PilGdeXXcx8,316
idna/core.py,sha256=P26_XVycuMTZ1R2mNK1ZREVzM5mvTzdabBXfyZVU1Lc,13246
idna/idnadata.py,sha256=SG8jhaGE53iiD6B49pt2pwTv_UvClciWE-N54oR2p4U,79623
idna/intranges.py,sha256=amUtkdhYcQG8Zr-CoMM_kVRacxkivC1WgxN1b63KKdU,1898
idna/package_data.py,sha256=_CUavOxobnbyNG2FLyHoN8QHP3QM9W1tKuw7eq9QwBk,21
idna/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
idna/uts46data.py,sha256=H9J35VkD0F9L9mKOqjeNGd2A-Va6FlPoz6Jz4K7h-ps,243725

4
venv/lib/python3.12/site-packages/idna-3.11.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,4 @@
Wheel-Version: 1.0
Generator: flit 3.12.0
Root-Is-Purelib: true
Tag: py3-none-any

31
venv/lib/python3.12/site-packages/idna-3.11.dist-info/licenses/LICENSE.md Normal file
View File

@@ -0,0 +1,31 @@
BSD 3-Clause License
Copyright (c) 2013-2025, Kim Davies and contributors.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
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.

45
venv/lib/python3.12/site-packages/idna/__init__.py Normal file
View File

@@ -0,0 +1,45 @@
from .core import (
IDNABidiError,
IDNAError,
InvalidCodepoint,
InvalidCodepointContext,
alabel,
check_bidi,
check_hyphen_ok,
check_initial_combiner,
check_label,
check_nfc,
decode,
encode,
ulabel,
uts46_remap,
valid_contextj,
valid_contexto,
valid_label_length,
valid_string_length,
)
from .intranges import intranges_contain
from .package_data import __version__
__all__ = [
"__version__",
"IDNABidiError",
"IDNAError",
"InvalidCodepoint",
"InvalidCodepointContext",
"alabel",
"check_bidi",
"check_hyphen_ok",
"check_initial_combiner",
"check_label",
"check_nfc",
"decode",
"encode",
"intranges_contain",
"ulabel",
"uts46_remap",
"valid_contextj",
"valid_contexto",
"valid_label_length",
"valid_string_length",
]

BIN
venv/lib/python3.12/site-packages/idna/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/idna/__pycache__/codec.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/idna/__pycache__/compat.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.12/site-packages/idna/__pycache__/core.cpython-312.pyc Normal file
View File

Binary file not shown.

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