# Buildsheet autogenerated by ravenadm tool -- Do not edit.

NAMEBASE=		python-url-normalize
VERSION=		2.2.1
KEYWORDS=		python
VARIANTS=		v12 v13
SDESC[v12]=		URL normalization for Python (3.12)
SDESC[v13]=		URL normalization for Python (3.13)
HOMEPAGE=		https://github.com/niksite/url-normalize
CONTACT=		Python_Automaton[python@ironwolf.systems]

DOWNLOAD_GROUPS=	main
SITES[main]=		PYPIWHL/bc/d9/5ec15501b675f7bc07c5d16aa70d8d778b12375686b6efd47656efdc67cd
DISTFILE[1]=		url_normalize-2.2.1-py3-none-any.whl:main
DIST_SUBDIR=		python-src
DF_INDEX=		1
SPKGS[v12]=		single
SPKGS[v13]=		single

OPTIONS_AVAILABLE=	PY312 PY313
OPTIONS_STANDARD=	none
VOPTS[v12]=		PY312=ON PY313=OFF
VOPTS[v13]=		PY312=OFF PY313=ON

DISTNAME=		url_normalize-2.2.1.dist-info

GENERATED=		yes

[PY312].RUN_DEPENDS_ON=			python-idna:single:v12
[PY312].USES_ON=			python:v12,wheel

[PY313].RUN_DEPENDS_ON=			python-idna:single:v13
[PY313].USES_ON=			python:v13,wheel

[FILE:2650:descriptions/desc.single]
# url-normalize

[tests]
[Coveralls]
[PyPI]

A Python library for standardizing and normalizing URLs with support for
internationalized domain names (IDN).

## Table of Contents

- [Introduction]
- [Features]
- [Installation]
- [Usage]
  - [Python API]
  - [Command Line]
- [Documentation]
- [Contributing]
- [License]

## Introduction

url-normalize provides a robust URI normalization function that:

- Takes care of IDN domains.
- Always provides the URI scheme in lowercase characters.
- Always provides the host, if any, in lowercase characters.
- Only performs percent-encoding where it is essential.
- Always uses uppercase A-through-F characters when percent-encoding.
- Prevents dot-segments appearing in non-relative URI paths.
- For schemes that define a default authority, uses an empty authority if
the
  default is desired.
- For schemes that define an empty path to be equivalent to a path of "/",
  uses "/".
- For schemes that define a port, uses an empty port if the default is
desired
- Ensures all portions of the URI are utf-8 encoded NFC from Unicode
strings

Inspired by Sam Ruby's [urlnorm.py]

## Features

- **IDN Support**: Full internationalized domain name handling
- **Configurable Defaults**:
  - Customizable default scheme (https by default)
  - Configurable default domain for absolute paths
- **Query Parameter Control**:
  - Parameter filtering with allowlists
  - Support for domain-specific parameter rules
- **Versatile URL Handling**:
  - Empty string URLs
  - Double slash URLs (//domain.tld)
  - Shebang (#!) URLs
- **Developer Friendly**:
  - Cross-version Python compatibility (3.8+)
  - 100% test coverage
  - Modern type hints and string handling

## Installation

```sh
pip install url-normalize
```

## Usage

### Python API

```python
from url_normalize import url_normalize

# Basic normalization (uses https by default)
print(url_normalize("www.foo.com:80/foo"))
# Output: https://www.foo.com/foo

# With custom default scheme
print(url_normalize("www.foo.com/foo", default_scheme="http"))
# Output: http://www.foo.com/foo

# With query parameter filtering enabled
print(url_normalize("www.google.com/search?q=test&utm_source=test",
filter_params=True))
# Output: https://www.google.com/search?q=test

# With custom parameter allowlist as a dict
print(url_normalize(
    "example.com?page=1&id=123&ref=test",
    filter_params=True,
    param_allowlist={"example.com": ["page", "id"]}
))
# Output: https://example.com?page=1&id=123

# With custom parameter allowlist as a list
print(url_normalize(
    "example.com?page=1&id=123&ref=test",
    filter_params=True,
    param_allowlist=["page", "id"]


[FILE:126:distinfo]
3deb687587dc91f7b25c9ae5162ffc0f057ae85d22b1e15cf5698311247f567b        14728 python-src/url_normalize-2.2.1-py3-none-any.whl