slugsmith 0.1.0__tar.gz

slugsmith-0.1.0/.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

slugsmith-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,41 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      - name: Install dependencies
+        run: uv sync
+      - name: Run tests
+        run: uv run pytest tests/ -v
+
+  typecheck:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      - name: Install dependencies
+        run: uv sync
+      - name: Run mypy
+        run: uv run mypy src/ --strict

slugsmith-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,20 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v6
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      - name: Build distribution
+        run: uv build
+      - name: Publish to PyPI
+        run: uv publish

slugsmith-0.1.0/.gitignore

@@ -0,0 +1,14 @@
+__pycache__/
+*.py[cod]
+*$py.class
+.venv/
+.env
+dist/
+build/
+*.egg-info/
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+coverage/
+htmlcov/
+.coverage

slugsmith-0.1.0/CHANGELOG.md

@@ -0,0 +1,13 @@
+# Changelog
+
+## [0.1.0] - 2026-03-14
+
+### Added
+
+- Initial release of slugsmith — modern, zero-dependency URL slug generator
+- Built-in Unicode transliteration (no external deps) covering Latin, Greek, Cyrillic, and CJK scripts
+- Language-specific character mappings (German ü→ue, ß→ss, etc.)
+- Full `python-slugify`-compatible API (`slugify()` with `separator`, `max_length`, `word_boundary`, `stopwords`, `replacements`, `lowercase`, `truncate_chars` parameters)
+- Strict type annotations throughout (PEP 561 `py.typed` marker)
+- Comprehensive test suite (87 tests) covering edge cases and Unicode handling
+- Python 3.9–3.13 support

slugsmith-0.1.0/Makefile

@@ -0,0 +1,22 @@
+.PHONY: install build test lint fmt clean ci
+
+install:
+	uv sync
+
+build:
+	uv build
+
+test:
+	uv run pytest tests/ -v
+
+lint:
+	uv run ruff check src/
+	uv run mypy src/
+
+fmt:
+	uv run ruff format src/ tests/
+
+clean:
+	rm -rf dist/ build/ *.egg-info/ .pytest_cache/ .mypy_cache/
+
+ci: lint test

slugsmith-0.1.0/PKG-INFO

@@ -0,0 +1,176 @@
+Metadata-Version: 2.4
+Name: slugsmith
+Version: 0.1.0
+Summary: Modern, zero-dependency URL slug generator with built-in Unicode transliteration
+Project-URL: Homepage, https://github.com/agentine/slugsmith
+Project-URL: Repository, https://github.com/agentine/slugsmith
+Author: Agentine
+License-Expression: MIT
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+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: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# slugsmith
+
+[![CI](https://github.com/agentine/slugsmith/actions/workflows/ci.yml/badge.svg)](https://github.com/agentine/slugsmith/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/slugsmith)](https://pypi.org/project/slugsmith/)
+[![Python](https://img.shields.io/pypi/pyversions/slugsmith)](https://pypi.org/project/slugsmith/)
+
+Modern, zero-dependency Python library for generating URL-friendly slugs from Unicode text.
+
+A drop-in replacement for [python-slugify](https://github.com/un33k/python-slugify) with built-in transliteration, no external dependencies, and full type annotations.
+
+## Installation
+
+```bash
+pip install slugsmith
+```
+
+## Quick Start
+
+```python
+from slugsmith import slugify
+
+slugify("Hello World")          # "hello-world"
+slugify("café latte")           # "cafe-latte"
+slugify("Ελληνικά")             # "ellinika"
+slugify("Привет мир")           # "privet-mir"
+slugify("北京")                  # "bei-jing"
+```
+
+## Features
+
+- **Zero dependencies** — built-in Unicode→ASCII transliteration; no `text-unidecode` or `Unidecode` required
+- **Drop-in replacement** for `python-slugify` — same `slugify()` signature
+- **Language-aware** — language-specific mappings for German, Turkish, Polish, Czech, Finnish, Swedish
+- **Type-safe** — full type annotations, PEP 561 compliant, passes mypy strict
+- **MIT licensed** — no GPL dependency concerns
+
+## API Reference
+
+### `slugify(text, **options) -> str`
+
+Generate a URL-friendly slug from `text`.
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `text` | `str` | *(required)* | Input string to slugify |
+| `separator` | `str` | `"-"` | Character(s) between words |
+| `lowercase` | `bool` | `True` | Convert to lowercase |
+| `max_length` | `int` | `0` | Max slug length (0 = unlimited) |
+| `word_boundary` | `bool` | `False` | Truncate at word boundary when `max_length` is set |
+| `save_order` | `bool` | `False` | Accepted for python-slugify compatibility (word order is always preserved) |
+| `stopwords` | `Iterable[str]` | `()` | Words to remove from the slug |
+| `regex_pattern` | `str \| None` | `None` | Custom regex pattern for allowed characters |
+| `replacements` | `Sequence[Sequence[str]] \| None` | `None` | Sequence of `(old, new)` pairs applied before transliteration; accepts lists of tuples or lists of lists |
+| `allow_unicode` | `bool` | `False` | Keep Unicode characters in the slug |
+| `lang` | `str \| None` | `None` | Language code for language-specific transliteration |
+
+Returns an empty string if `text` is empty.
+
+## Examples
+
+### Separator and case
+
+```python
+slugify("Hello World", separator="_")           # "hello_world"
+slugify("Hello World", lowercase=False)         # "Hello-World"
+slugify("Hello World", separator="")            # "helloworld"
+```
+
+### Length limiting
+
+```python
+slugify("the quick brown fox", max_length=15)               # "the-quick-brow"
+slugify("the quick brown fox", max_length=15, word_boundary=True)  # "the-quick"
+```
+
+### Stopwords
+
+```python
+slugify("the quick brown fox", stopwords=("the",))   # "quick-brown-fox"
+```
+
+### Replacements
+
+```python
+slugify("C++ is great", replacements=[("++", "pp")])  # "cpp-is-great"
+slugify("$100 deal", replacements=[("$", "dollar")])   # "dollar100-deal"
+```
+
+### Unicode passthrough
+
+```python
+slugify("café au lait", allow_unicode=True)   # "café-au-lait"
+slugify("北京 city", allow_unicode=True)       # "北京-city"
+```
+
+### Language-specific transliteration
+
+```python
+slugify("Ü-bung", lang="de")    # "ue-bung"   (German: ü→ue, ö→oe, ä→ae)
+slugify("çalış", lang="tr")     # "calis"     (Turkish: ç→c, ş→s)
+slugify("łódź", lang="pl")      # "lodz"      (Polish: ł→l, ó→o, ź→z)
+slugify("říjen", lang="cs")     # "rijen"     (Czech: ř→r, í→i)
+```
+
+Supported language codes: `de` (German), `tr` (Turkish), `pl` (Polish), `cs` (Czech), `fi` (Finnish), `sv` (Swedish).
+
+### Script coverage
+
+slugsmith's built-in transliteration covers a wide range of Unicode scripts without any external dependencies:
+
+| Script | Coverage | Example |
+|--------|----------|---------|
+| Latin Extended | Full diacritics (NFKD + explicit map) | `café` → `cafe` |
+| Cyrillic | Russian + Ukrainian | `Привет` → `Privet`, `їжак` → `yizhak` |
+| Greek | Modern Greek alphabet | `Ελληνικά` → `Ellinika` |
+| Arabic | Basic alphabet (28 letters) | `مرحبا` → `mrhba` |
+| Hebrew | Basic alphabet (22 letters + finals) | `שלום` → `shalom` |
+| Symbols | Common currency and typographic symbols | `€100` → `euro100`, `™` → `tm` |
+
+Characters not covered by the table are decomposed via NFKD normalisation; if decomposition yields ASCII, that is used. Remaining non-ASCII characters are silently dropped (same behaviour as `text-unidecode`).
+
+### Custom regex
+
+```python
+# Allow only alphanumeric and hyphens (strip underscores too)
+slugify("hello_world foo", regex_pattern=r"[^a-z0-9-]")  # "helloworld-foo"
+```
+
+## Migration from python-slugify
+
+slugsmith is a drop-in replacement:
+
+```python
+# Before
+from slugify import slugify
+
+# After
+from slugsmith import slugify
+```
+
+The `slugify()` signature is identical. No other code changes are needed.
+
+**Behavioural differences:**
+
+| Feature | python-slugify | slugsmith |
+|---------|---------------|-----------|
+| Transliteration | `text-unidecode` (external dep) | Built-in table (zero deps) |
+| License | MIT | MIT (no GPL risk) |
+| Python support | 3.7+ | 3.9+ |
+| Type annotations | Partial | Full (mypy strict) |
+| Language-specific | Not built-in | `lang=` parameter |
+
+## License
+
+MIT

slugsmith-0.1.0/PLAN.md

@@ -0,0 +1,65 @@
+# Slugsmith — Implementation Plan
+
+## Overview
+
+**Slugsmith** is a modern, self-contained Python library for generating URL-friendly slugs from Unicode text. It replaces **python-slugify** (62M/month downloads, single maintainer inactive since March 2024, stale dependency chain).
+
+**PyPI name:** `slugsmith` (verified available)
+
+## Target Library: python-slugify
+
+- **Downloads:** 62M/month (2.4M/day)
+- **Maintainer:** un33k (Val Neekman) — last code commit March 2024
+- **Issues:** 4 open, 3 unmerged PRs, no review activity
+- **Key risk:** Depends on `text-unidecode` (last release 2019, abandoned)
+- **License concern:** Alternative dependency `Unidecode` is GPL; many projects cannot use it
+
+## Architecture
+
+### Core Module: `slugsmith/`
+
+```
+slugsmith/
+├── __init__.py          # Public API: slugify()
+├── slugify.py           # Core slugification logic
+├── transliterate.py     # Built-in Unicode→ASCII transliteration (no external deps)
+├── special.py           # Language-specific character mappings (German ü→ue, etc.)
+├── py.typed             # PEP 561 marker
+└── _version.py          # Version string
+```
+
+### Key Design Decisions
+
+1. **Zero dependencies** — Built-in transliteration tables eliminate the need for text-unidecode or Unidecode. Ship comprehensive Unicode→ASCII mappings derived from CLDR/Unicode data (MIT-compatible sources only).
+
+2. **API compatibility** — Provide a `slugify()` function with the same core parameters as python-slugify (`text`, `separator`, `lowercase`, `max_length`, `word_boundary`, `save_order`, `stopwords`, `regex_pattern`, `replacements`, `allow_unicode`). Easy migration path.
+
+3. **Type-safe** — Full type annotations, PEP 561 compliant, passes mypy strict.
+
+4. **Performance** — Optimize hot paths. Avoid unnecessary regex compilation on each call (pre-compile patterns). Target ≥2x throughput vs python-slugify.
+
+5. **Modern Python** — Require Python 3.9+. Use modern string/regex features.
+
+6. **MIT licensed** — Clear, permissive license with no GPL dependencies.
+
+### Transliteration Strategy
+
+- Ship a comprehensive mapping table covering Latin Extended, Cyrillic, Greek, CJK (basic), Arabic, Hebrew, Thai, and other major scripts.
+- Source mappings from CLDR transliteration rules and Unicode NFKD decomposition.
+- Support language-specific transliteration (e.g., German: ü→ue, ö→oe; Turkish: ı→i).
+- Use `unicodedata.normalize('NFKD', ...)` as first pass, then apply custom mappings for characters that don't decompose cleanly.
+
+## Deliverables
+
+1. Core `slugify()` function with full parameter compatibility
+2. Built-in transliteration engine (no external dependencies)
+3. Language-specific character mappings
+4. Comprehensive test suite (unit + property-based)
+5. Migration guide from python-slugify
+6. PyPI package published as `slugsmith`
+
+## Non-Goals
+
+- Django integration (users can wrap `slugify()` themselves)
+- CLI tool (keep scope focused on the library)
+- Python 2 or Python <3.9 support

slugsmith-0.1.0/README.md

@@ -0,0 +1,155 @@
+# slugsmith
+
+[![CI](https://github.com/agentine/slugsmith/actions/workflows/ci.yml/badge.svg)](https://github.com/agentine/slugsmith/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/slugsmith)](https://pypi.org/project/slugsmith/)
+[![Python](https://img.shields.io/pypi/pyversions/slugsmith)](https://pypi.org/project/slugsmith/)
+
+Modern, zero-dependency Python library for generating URL-friendly slugs from Unicode text.
+
+A drop-in replacement for [python-slugify](https://github.com/un33k/python-slugify) with built-in transliteration, no external dependencies, and full type annotations.
+
+## Installation
+
+```bash
+pip install slugsmith
+```
+
+## Quick Start
+
+```python
+from slugsmith import slugify
+
+slugify("Hello World")          # "hello-world"
+slugify("café latte")           # "cafe-latte"
+slugify("Ελληνικά")             # "ellinika"
+slugify("Привет мир")           # "privet-mir"
+slugify("北京")                  # "bei-jing"
+```
+
+## Features
+
+- **Zero dependencies** — built-in Unicode→ASCII transliteration; no `text-unidecode` or `Unidecode` required
+- **Drop-in replacement** for `python-slugify` — same `slugify()` signature
+- **Language-aware** — language-specific mappings for German, Turkish, Polish, Czech, Finnish, Swedish
+- **Type-safe** — full type annotations, PEP 561 compliant, passes mypy strict
+- **MIT licensed** — no GPL dependency concerns
+
+## API Reference
+
+### `slugify(text, **options) -> str`
+
+Generate a URL-friendly slug from `text`.
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `text` | `str` | *(required)* | Input string to slugify |
+| `separator` | `str` | `"-"` | Character(s) between words |
+| `lowercase` | `bool` | `True` | Convert to lowercase |
+| `max_length` | `int` | `0` | Max slug length (0 = unlimited) |
+| `word_boundary` | `bool` | `False` | Truncate at word boundary when `max_length` is set |
+| `save_order` | `bool` | `False` | Accepted for python-slugify compatibility (word order is always preserved) |
+| `stopwords` | `Iterable[str]` | `()` | Words to remove from the slug |
+| `regex_pattern` | `str \| None` | `None` | Custom regex pattern for allowed characters |
+| `replacements` | `Sequence[Sequence[str]] \| None` | `None` | Sequence of `(old, new)` pairs applied before transliteration; accepts lists of tuples or lists of lists |
+| `allow_unicode` | `bool` | `False` | Keep Unicode characters in the slug |
+| `lang` | `str \| None` | `None` | Language code for language-specific transliteration |
+
+Returns an empty string if `text` is empty.
+
+## Examples
+
+### Separator and case
+
+```python
+slugify("Hello World", separator="_")           # "hello_world"
+slugify("Hello World", lowercase=False)         # "Hello-World"
+slugify("Hello World", separator="")            # "helloworld"
+```
+
+### Length limiting
+
+```python
+slugify("the quick brown fox", max_length=15)               # "the-quick-brow"
+slugify("the quick brown fox", max_length=15, word_boundary=True)  # "the-quick"
+```
+
+### Stopwords
+
+```python
+slugify("the quick brown fox", stopwords=("the",))   # "quick-brown-fox"
+```
+
+### Replacements
+
+```python
+slugify("C++ is great", replacements=[("++", "pp")])  # "cpp-is-great"
+slugify("$100 deal", replacements=[("$", "dollar")])   # "dollar100-deal"
+```
+
+### Unicode passthrough
+
+```python
+slugify("café au lait", allow_unicode=True)   # "café-au-lait"
+slugify("北京 city", allow_unicode=True)       # "北京-city"
+```
+
+### Language-specific transliteration
+
+```python
+slugify("Ü-bung", lang="de")    # "ue-bung"   (German: ü→ue, ö→oe, ä→ae)
+slugify("çalış", lang="tr")     # "calis"     (Turkish: ç→c, ş→s)
+slugify("łódź", lang="pl")      # "lodz"      (Polish: ł→l, ó→o, ź→z)
+slugify("říjen", lang="cs")     # "rijen"     (Czech: ř→r, í→i)
+```
+
+Supported language codes: `de` (German), `tr` (Turkish), `pl` (Polish), `cs` (Czech), `fi` (Finnish), `sv` (Swedish).
+
+### Script coverage
+
+slugsmith's built-in transliteration covers a wide range of Unicode scripts without any external dependencies:
+
+| Script | Coverage | Example |
+|--------|----------|---------|
+| Latin Extended | Full diacritics (NFKD + explicit map) | `café` → `cafe` |
+| Cyrillic | Russian + Ukrainian | `Привет` → `Privet`, `їжак` → `yizhak` |
+| Greek | Modern Greek alphabet | `Ελληνικά` → `Ellinika` |
+| Arabic | Basic alphabet (28 letters) | `مرحبا` → `mrhba` |
+| Hebrew | Basic alphabet (22 letters + finals) | `שלום` → `shalom` |
+| Symbols | Common currency and typographic symbols | `€100` → `euro100`, `™` → `tm` |
+
+Characters not covered by the table are decomposed via NFKD normalisation; if decomposition yields ASCII, that is used. Remaining non-ASCII characters are silently dropped (same behaviour as `text-unidecode`).
+
+### Custom regex
+
+```python
+# Allow only alphanumeric and hyphens (strip underscores too)
+slugify("hello_world foo", regex_pattern=r"[^a-z0-9-]")  # "helloworld-foo"
+```
+
+## Migration from python-slugify
+
+slugsmith is a drop-in replacement:
+
+```python
+# Before
+from slugify import slugify
+
+# After
+from slugsmith import slugify
+```
+
+The `slugify()` signature is identical. No other code changes are needed.
+
+**Behavioural differences:**
+
+| Feature | python-slugify | slugsmith |
+|---------|---------------|-----------|
+| Transliteration | `text-unidecode` (external dep) | Built-in table (zero deps) |
+| License | MIT | MIT (no GPL risk) |
+| Python support | 3.7+ | 3.9+ |
+| Type annotations | Partial | Full (mypy strict) |
+| Language-specific | Not built-in | `lang=` parameter |
+
+## License
+
+MIT

slugsmith-0.1.0/pyproject.toml

@@ -0,0 +1,49 @@
+[project]
+name = "slugsmith"
+version = "0.1.0"
+description = "Modern, zero-dependency URL slug generator with built-in Unicode transliteration"
+readme = "README.md"
+license = "MIT"
+authors = [
+    { name = "Agentine" }
+]
+requires-python = ">=3.9"
+dependencies = []
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Typing :: Typed",
+]
+
+[project.urls]
+Homepage = "https://github.com/agentine/slugsmith"
+Repository = "https://github.com/agentine/slugsmith"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/slugsmith"]
+
+[dependency-groups]
+dev = [
+    "mypy>=1.19",
+    "pytest>=8.0",
+    "ruff>=0.11",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.mypy]
+strict = true
+warn_return_any = true
+warn_unused_configs = true

slugsmith-0.1.0/src/slugsmith/__init__.py

@@ -0,0 +1,6 @@
+"""Slugsmith — modern, zero-dependency URL slug generator."""
+
+from slugsmith._version import __version__
+from slugsmith.slugify import slugify
+
+__all__ = ["slugify", "__version__"]

slugsmith-0.1.0/src/slugsmith/_version.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"