url-normalize 2.2.1__tar.gz → 3.0.0__tar.gz

url_normalize-3.0.0/PKG-INFO

@@ -0,0 +1,211 @@
+Metadata-Version: 2.4
+Name: url-normalize
+Version: 3.0.0
+Summary: URL normalization for Python
+Author-email: Nikolay Panov <github@npanov.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/niksite/url-normalize
+Project-URL: Repository, https://github.com/niksite/url-normalize
+Project-URL: Issues, https://github.com/niksite/url-normalize/issues
+Project-URL: Changelog, https://github.com/niksite/url-normalize/blob/master/CHANGELOG.md
+Keywords: url,normalization,normalize,normalizer
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+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: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: idna>=3.3
+Provides-Extra: dev
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-socket; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Dynamic: license-file
+
+# url-normalize
+
+[![tests](https://github.com/niksite/url-normalize/actions/workflows/ci.yml/badge.svg)](https://github.com/niksite/url-normalize/actions/workflows/ci.yml)
+[![Coveralls](https://img.shields.io/coveralls/github/niksite/url-normalize/master.svg)](https://coveralls.io/r/niksite/url-normalize)
+[![PyPI](https://img.shields.io/pypi/v/url-normalize.svg)](https://pypi.org/project/url-normalize/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/url-normalize.svg)](https://pypi.org/project/url-normalize/)
+[![License](https://img.shields.io/pypi/l/url-normalize.svg)](https://github.com/niksite/url-normalize/blob/master/LICENSE)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+
+A Python library for standardizing and normalizing URLs. Ideal for database deduplication, caching, web crawling, and anywhere you need to ensure that equivalent URLs resolve to the exact same string.
+
+```python
+from url_normalize import url_normalize
+
+# Fixes IDN, lowercases host/scheme, removes default ports, resolves path segments
+url_normalize("HTTP://User:Pass@www.FOO.com:80///foo/../bar/./baz?q=1#frag")
+# -> 'http://User:Pass@www.foo.com/bar/baz?q=1#frag'
+```
+
+## Features
+
+url-normalize provides a robust URI normalization function that handles IDN domains, scheme/host lowercasing, and RFC-compliant path normalization.
+
+- **IDN Support**: Full internationalized domain name handling (using IDNA2008 with UTS46).
+- **Humanization**: Convert normalized URLs to a readable display format while preserving round-trip normalization.
+- **RFC Compliance**:
+  - Proper percent-encoding (minimal, uppercase hex).
+  - Dot-segment removal in paths.
+  - Default port and authority handling.
+  - UTF-8 NFC normalization.
+- **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**: Handles empty strings, double-slash URLs (//domain.tld), and shebang (#!) URLs.
+- **Developer Friendly**:
+  - Python 3.10+ compatibility.
+  - 100% test coverage.
+  - Modern type hints and string handling.
+
+Inspired by Sam Ruby's [urlnorm.py](http://intertwingly.net/blog/2004/08/04/Urlnorm).
+
+## Installation
+
+Install as a library:
+
+```sh
+pip install url-normalize
+```
+
+Or install as a standalone CLI tool using [uv](https://docs.astral.sh/uv/):
+
+```sh
+uv tool install url-normalize
+```
+
+## Usage
+
+### Python API
+
+#### Basic Normalization
+
+```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
+```
+
+#### Query Parameter Filtering
+
+You can strip out tracking parameters and only keep the ones you care about using allowlists.
+
+```python
+# With query parameter filtering enabled (strips all params by default)
+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 list
+print(url_normalize(
+    "example.com?page=1&id=123&ref=test",
+    filter_params=True,
+    param_allowlist=["page", "id"]
+))
+# Output: https://example.com?page=1&id=123
+
+# With domain-specific parameter allowlists
+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
+```
+
+#### Default Domain & Scheme
+
+Useful for resolving relative URLs found on a specific page.
+
+```python
+# With default domain for absolute paths
+print(url_normalize("/images/logo.png", default_domain="example.com"))
+# Output: https://example.com/images/logo.png
+
+# With default domain and custom scheme
+print(url_normalize("/images/logo.png", default_scheme="http", default_domain="example.com"))
+# Output: http://example.com/images/logo.png
+```
+
+#### Humanizing URLs
+
+Convert normalized URLs back into a user-friendly format for display, particularly useful for IDN domains and percent-encoded paths.
+
+```python
+from url_normalize import url_humanize
+
+# Human-readable display form that still normalizes back to the same URL
+print(url_humanize("https://xn--e1afmkfd.xn--80akhbyknj4f/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"))
+# Output: https://пример.испытание/Служебная
+
+# Humanization accepts the same normalization options
+print(url_humanize("/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F", default_domain="xn--e1afmkfd.xn--80akhbyknj4f"))
+# Output: https://пример.испытание/Служебная
+```
+
+### Command-line Usage
+
+You can also use `url-normalize` directly from the terminal to process URLs.
+
+```bash
+$ url-normalize "www.foo.com:80/foo"
+# Output: https://www.foo.com/foo
+
+# With custom default scheme
+$ url-normalize -s http "www.foo.com/foo"
+# Output: http://www.foo.com/foo
+
+# With query parameter filtering
+$ url-normalize -f "www.google.com/search?q=test&utm_source=test"
+# Output: https://www.google.com/search?q=test
+
+# With custom allowlist
+$ url-normalize -f -p page,id "example.com?page=1&id=123&ref=test"
+# Output: https://example.com/?page=1&id=123
+
+# With default domain for absolute paths
+$ url-normalize -d example.com "/images/logo.png"
+# Output: https://example.com/images/logo.png
+
+# With default domain and custom scheme
+$ url-normalize -d example.com -s http "/images/logo.png"
+# Output: http://example.com/images/logo.png
+
+# Human-readable display form
+$ url-normalize -H "https://xn--e1afmkfd.xn--80akhbyknj4f/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"
+# Output: https://пример.испытание/Служебная
+
+# Via uv tool/uvx
+$ uvx url-normalize www.foo.com:80/foo
+# Output: https://www.foo.com:80/foo
+```
+
+## Documentation
+
+For a complete history of changes, see [CHANGELOG.md](CHANGELOG.md).
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+MIT License

url_normalize-3.0.0/README.md

@@ -0,0 +1,180 @@
+# url-normalize
+
+[![tests](https://github.com/niksite/url-normalize/actions/workflows/ci.yml/badge.svg)](https://github.com/niksite/url-normalize/actions/workflows/ci.yml)
+[![Coveralls](https://img.shields.io/coveralls/github/niksite/url-normalize/master.svg)](https://coveralls.io/r/niksite/url-normalize)
+[![PyPI](https://img.shields.io/pypi/v/url-normalize.svg)](https://pypi.org/project/url-normalize/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/url-normalize.svg)](https://pypi.org/project/url-normalize/)
+[![License](https://img.shields.io/pypi/l/url-normalize.svg)](https://github.com/niksite/url-normalize/blob/master/LICENSE)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+
+A Python library for standardizing and normalizing URLs. Ideal for database deduplication, caching, web crawling, and anywhere you need to ensure that equivalent URLs resolve to the exact same string.
+
+```python
+from url_normalize import url_normalize
+
+# Fixes IDN, lowercases host/scheme, removes default ports, resolves path segments
+url_normalize("HTTP://User:Pass@www.FOO.com:80///foo/../bar/./baz?q=1#frag")
+# -> 'http://User:Pass@www.foo.com/bar/baz?q=1#frag'
+```
+
+## Features
+
+url-normalize provides a robust URI normalization function that handles IDN domains, scheme/host lowercasing, and RFC-compliant path normalization.
+
+- **IDN Support**: Full internationalized domain name handling (using IDNA2008 with UTS46).
+- **Humanization**: Convert normalized URLs to a readable display format while preserving round-trip normalization.
+- **RFC Compliance**:
+  - Proper percent-encoding (minimal, uppercase hex).
+  - Dot-segment removal in paths.
+  - Default port and authority handling.
+  - UTF-8 NFC normalization.
+- **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**: Handles empty strings, double-slash URLs (//domain.tld), and shebang (#!) URLs.
+- **Developer Friendly**:
+  - Python 3.10+ compatibility.
+  - 100% test coverage.
+  - Modern type hints and string handling.
+
+Inspired by Sam Ruby's [urlnorm.py](http://intertwingly.net/blog/2004/08/04/Urlnorm).
+
+## Installation
+
+Install as a library:
+
+```sh
+pip install url-normalize
+```
+
+Or install as a standalone CLI tool using [uv](https://docs.astral.sh/uv/):
+
+```sh
+uv tool install url-normalize
+```
+
+## Usage
+
+### Python API
+
+#### Basic Normalization
+
+```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
+```
+
+#### Query Parameter Filtering
+
+You can strip out tracking parameters and only keep the ones you care about using allowlists.
+
+```python
+# With query parameter filtering enabled (strips all params by default)
+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 list
+print(url_normalize(
+    "example.com?page=1&id=123&ref=test",
+    filter_params=True,
+    param_allowlist=["page", "id"]
+))
+# Output: https://example.com?page=1&id=123
+
+# With domain-specific parameter allowlists
+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
+```
+
+#### Default Domain & Scheme
+
+Useful for resolving relative URLs found on a specific page.
+
+```python
+# With default domain for absolute paths
+print(url_normalize("/images/logo.png", default_domain="example.com"))
+# Output: https://example.com/images/logo.png
+
+# With default domain and custom scheme
+print(url_normalize("/images/logo.png", default_scheme="http", default_domain="example.com"))
+# Output: http://example.com/images/logo.png
+```
+
+#### Humanizing URLs
+
+Convert normalized URLs back into a user-friendly format for display, particularly useful for IDN domains and percent-encoded paths.
+
+```python
+from url_normalize import url_humanize
+
+# Human-readable display form that still normalizes back to the same URL
+print(url_humanize("https://xn--e1afmkfd.xn--80akhbyknj4f/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"))
+# Output: https://пример.испытание/Служебная
+
+# Humanization accepts the same normalization options
+print(url_humanize("/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F", default_domain="xn--e1afmkfd.xn--80akhbyknj4f"))
+# Output: https://пример.испытание/Служебная
+```
+
+### Command-line Usage
+
+You can also use `url-normalize` directly from the terminal to process URLs.
+
+```bash
+$ url-normalize "www.foo.com:80/foo"
+# Output: https://www.foo.com/foo
+
+# With custom default scheme
+$ url-normalize -s http "www.foo.com/foo"
+# Output: http://www.foo.com/foo
+
+# With query parameter filtering
+$ url-normalize -f "www.google.com/search?q=test&utm_source=test"
+# Output: https://www.google.com/search?q=test
+
+# With custom allowlist
+$ url-normalize -f -p page,id "example.com?page=1&id=123&ref=test"
+# Output: https://example.com/?page=1&id=123
+
+# With default domain for absolute paths
+$ url-normalize -d example.com "/images/logo.png"
+# Output: https://example.com/images/logo.png
+
+# With default domain and custom scheme
+$ url-normalize -d example.com -s http "/images/logo.png"
+# Output: http://example.com/images/logo.png
+
+# Human-readable display form
+$ url-normalize -H "https://xn--e1afmkfd.xn--80akhbyknj4f/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"
+# Output: https://пример.испытание/Служебная
+
+# Via uv tool/uvx
+$ uvx url-normalize www.foo.com:80/foo
+# Output: https://www.foo.com:80/foo
+```
+
+## Documentation
+
+For a complete history of changes, see [CHANGELOG.md](CHANGELOG.md).
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+MIT License

{url_normalize-2.2.1 → url_normalize-3.0.0}/pyproject.toml

@@ -1,12 +1,21 @@
 [project]
 name = "url-normalize"
-version = "2.2.1"
+version = "3.0.0"
 description = "URL normalization for Python"
 authors = [{ name = "Nikolay Panov", email = "github@npanov.com" }]
-license = { text = "MIT" }
+license = "MIT"
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.10"
 keywords = ["url", "normalization", "normalize", "normalizer"]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+]
 dependencies = ["idna>=3.3"]
 
 [project.urls]
@@ -22,7 +31,7 @@ url-normalize = "url_normalize.cli:main"
 dev = ["mypy", "pre-commit", "pytest-cov", "pytest-socket", "pytest", "ruff"]
 
 [tool.ruff]
-target-version = "py38"
+target-version = "py310"
 line-length = 88
 unsafe-fixes = true
 
@@ -53,11 +62,11 @@ indent-style = "space"
 [tool.mypy]
 ignore_missing_imports = true
 exclude = ["tests"]
-python_version = "3.8"
+python_version = "3.10"
 show_error_codes = true
 
 [build-system]
-requires = ["setuptools>=42", "wheel"]
+requires = ["setuptools>=77", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.pytest.ini_options]

{url_normalize-2.2.1 → url_normalize-3.0.0}/tests/test_cli.py

@@ -22,7 +22,7 @@ def run_cli(*args: str) -> subprocess.CompletedProcess:
     """
     command = [sys.executable, "-m", "url_normalize.cli", *list(args)]
     return subprocess.run(  # noqa: S603
-        command, capture_output=True, text=True, check=False
+        command, capture_output=True, text=True, encoding="utf-8", check=False
     )
 
 
@@ -66,6 +66,56 @@ def test_cli_basic_normalization_short_args() -> None:
     assert not result.stderr
 
 
+def test_cli_humanize() -> None:
+    """Test human-readable URL output via CLI."""
+    url = (
+        "https://xn--e1afmkfd.xn--80akhbyknj4f/"
+        "%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"
+    )
+    expected = "https://пример.испытание/Служебная"
+
+    result = run_cli("--humanize", url)
+
+    assert result.returncode == 0
+    assert result.stdout.strip() == expected
+    assert not result.stderr
+
+
+def test_cli_humanize_short_arg() -> None:
+    """Test human-readable URL output via CLI using short argument."""
+    url = (
+        "https://xn--e1afmkfd.xn--80akhbyknj4f/"
+        "%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"
+    )
+    expected = "https://пример.испытание/Служебная"
+
+    result = run_cli("-H", url)
+
+    assert result.returncode == 0
+    assert result.stdout.strip() == expected
+    assert not result.stderr
+
+
+def test_cli_humanize_respects_normalization_options() -> None:
+    """Test humanized output keeps the existing CLI normalization options."""
+    url = "/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"
+    expected = "https://пример.испытание/Служебная?keep=Ç"
+
+    result = run_cli(
+        "--humanize",
+        "--default-domain",
+        "xn--e1afmkfd.xn--80akhbyknj4f",
+        "--filter-params",
+        "--param-allowlist",
+        "keep",
+        f"{url}?utm_source=ignored&keep=%C3%87",
+    )
+
+    assert result.returncode == 0
+    assert result.stdout.strip() == expected
+    assert not result.stderr
+
+
 def test_cli_default_scheme() -> None:
     """Test default scheme addition via CLI."""
     url = "//example.com"

{url_normalize-2.2.1 → url_normalize-3.0.0}/tests/test_normalize_host.py

@@ -17,7 +17,7 @@ from url_normalize.url_normalize import normalize_host
         # Mixed case with Cyrillic
         ("ExAmPle.РФ", "example.xn--p1ai"),
         # IDNA2008 with UTS46
-        ("faß.de", "fass.de"),  # Normalize using transitional rules
+        ("faß.de", "xn--fa-hia.de"),
         # Edge cases
         ("ドメイン.テスト", "xn--eckwd4c7c.xn--zckzah"),  # Japanese
         ("domain.café", "domain.xn--caf-dma"),  # Latin with diacritic

url_normalize-3.0.0/tests/test_url_humanize.py

@@ -0,0 +1,122 @@
+"""Tests for URL humanization."""
+
+from __future__ import annotations
+
+import pytest
+
+import url_normalize as package
+
+
+@pytest.mark.parametrize(
+    ("normalized", "expected"),
+    [
+        (
+            "https://xn--e1afmkfd.xn--80akhbyknj4f/"
+            "%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F:Search/Test",
+            "https://пример.испытание/Служебная:Search/Test",
+        ),
+        (
+            "https://xn--fa-hia.de/%C3%BCber?q=%C3%87#%D0%BF%D1%80%D0%B8%D0%BC%D0%B5%D1%80",
+            "https://faß.de/über?q=Ç#пример",
+        ),
+        (
+            "https://example.com/?q=%23test&where=code%3D123",
+            "https://example.com/?q=%23test&where=code=123",
+        ),
+    ],
+)
+def test_url_humanize_returns_readable_url_that_normalizes_back(
+    normalized: str,
+    expected: str,
+) -> None:
+    """Assert humanized URLs are readable without changing normalized meaning."""
+    humanized = package.url_humanize(normalized)
+
+    assert humanized == expected
+    assert package.url_normalize(humanized) == normalized
+
+
+@pytest.mark.parametrize("value", ["", None])
+def test_url_humanize_preserves_empty_values(value: str | None) -> None:
+    """Assert empty inputs match url_normalize behavior."""
+    assert package.url_humanize(value) == value
+
+
+@pytest.mark.parametrize(
+    "value",
+    [
+        (
+            "https://xn--e1afmkfd.xn--80akhbyknj4f/"
+            "%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F:Search/Test"
+        ),
+        "https://faß.de/über?q=Ç#пример",
+        "https://example.com/a%2Fb?equals=a%3Db&letter=%C3%87#%D1%84",
+        "https://example.com/?hash=%23test&amp=a%26b&query=a%3Fb",
+    ],
+)
+def test_url_humanize_round_trips_to_normalized_url(value: str) -> None:
+    """Assert humanization never changes the canonical normalized URL."""
+    humanized = package.url_humanize(value)
+
+    assert package.url_normalize(humanized) == package.url_normalize(value)
+
+
+def test_url_humanize_accepts_url_normalize_options() -> None:
+    """Assert humanization can be combined with normalizer options."""
+    humanized = package.url_humanize(
+        "/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F"
+        "?utm_source=ignored&keep=%C3%87",
+        default_domain="xn--e1afmkfd.xn--80akhbyknj4f",
+        filter_params=True,
+        param_allowlist=["keep"],
+    )
+
+    assert humanized == "https://пример.испытание/Служебная?keep=Ç"
+
+
+def test_url_humanize_keeps_query_delimiters_encoded() -> None:
+    """Assert humanization does not expose encoded query separators."""
+    normalized = "https://example.com/?hash=%23test&amp=a%26b&key%3Dpart=value"
+
+    assert package.url_humanize(normalized) == normalized
+
+
+def test_url_humanize_decodes_safe_query_parts_independently() -> None:
+    """Assert safe query key and value decoding is applied per component."""
+    normalized = (
+        "https://example.com/?letter=%C3%87&equals=a%3Db&%D0%BA%D0%BB%D1%8E%D1%87=value"
+    )
+
+    assert (
+        package.url_humanize(normalized)
+        == "https://example.com/?letter=Ç&equals=a=b&ключ=value"
+    )
+
+
+def test_url_humanize_keeps_malformed_percent_encoding_normalized() -> None:
+    """Assert malformed UTF-8 escapes are not rendered with replacement text."""
+    value = "https://example.com/%E0%A4%A?bad=%E0%A4%A#%E0%A4%A"
+    normalized = package.url_normalize(value)
+
+    assert package.url_humanize(value) == normalized
+
+
+def test_url_humanize_documents_encoded_slash_normalization() -> None:
+    """Assert encoded slashes follow url_normalize path semantics."""
+    value = "https://example.com/a%2Fb"
+    humanized = package.url_humanize(value)
+
+    assert humanized == "https://example.com/a/b"
+    assert package.url_normalize(humanized) == package.url_normalize(value)
+
+
+def test_url_humanize_handles_idna_error() -> None:
+    """Assert IDNA decoding fallback gracefully handles bad IDNA labels."""
+    value = "https://xn--bad-label.com/"
+    assert package.url_humanize(value) == "https://xn--bad-label.com/"
+
+
+def test_url_humanize_skips_failed_round_trip() -> None:
+    """Assert parts that break round-trip normalizations are kept as is."""
+    value = "https://example.com/a%3Fb"
+    assert package.url_humanize(value) == value

{url_normalize-2.2.1 → url_normalize-3.0.0}/url_normalize/__init__.py

@@ -5,9 +5,10 @@ SPDX-License-Identifier: MIT
 
 """
 
+from .url_humanize import url_humanize
 from .url_normalize import url_normalize
 
 __license__ = "MIT"
-__version__ = "2.2.1"
+__version__ = "3.0.0"
 
-__all__ = ["url_normalize"]
+__all__ = ["url_humanize", "url_normalize"]