Add mkdocs configuration

Quantco · Jul 13, 2024 · 5c60bee · 5c60bee
1 parent 4282163
commit 5c60bee
Show file tree

Hide file tree

Showing 14 changed files with 1,487 additions and 214 deletions.
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -0,0 +1,23 @@
+name: Docs
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+permissions:
+  contents: write
+jobs:
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout branch
+        uses: actions/checkout@v4
+      - name: Set up pixi
+        uses: prefix-dev/setup-pixi@ba3bb36eb2066252b2363392b7739741bb777659
+        with:
+          environments: docs
+      - name: Build docs
+        run: pixi run -e docs docs-build
+      - name: Deploy docs
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        run: pixi run -e docs mkdocs gh-deploy --force
diff --git a/README.md b/README.md
@@ -1,6 +1,7 @@
 # multiregex
 
 [![CI](https://img.shields.io/github/actions/workflow/status/quantco/multiregex/ci.yml?style=flat-square&branch=main)](https://github.com/quantco/multiregex/actions/workflows/ci.yml)
+[![Documentation](https://img.shields.io/badge/docs-7E56C2?style=flat-square)](https://quantco.github.io/multiregex)
 [![conda-forge](https://img.shields.io/conda/vn/conda-forge/multiregex?logoColor=white&logo=conda-forge&style=flat-square)](https://prefix.dev/channels/conda-forge/packages/multiregex)
 [![pypi-version](https://img.shields.io/pypi/v/multiregex.svg?logo=pypi&logoColor=white&style=flat-square)](https://pypi.org/project/multiregex)
 [![python-version](https://img.shields.io/pypi/pyversions/multiregex?logoColor=white&logo=python&style=flat-square)](https://pypi.org/project/multiregex)

diff --git a/docs/Makefile b/docs/Makefile
diff --git a/docs/api-documentation.md b/docs/api-documentation.md
@@ -0,0 +1,3 @@
+# API Documentation
+
+::: multiregex
diff --git a/docs/changelog.rst b/docs/changelog.rst
diff --git a/docs/conf.py b/docs/conf.py
diff --git a/docs/index.md b/docs/index.md
@@ -0,0 +1,5 @@
+# multiregex
+
+Quickly match many regexes against a string. Provides 2-10x speedups over naïve regex matching.
+
+[API Documentation](api-documentation.md)
diff --git a/docs/index.rst b/docs/index.rst
diff --git a/docs/make.bat b/docs/make.bat
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -0,0 +1,58 @@
+site_name: multiregex
+site_description: Quickly match many regexes against a string. Provides 2-10x speedups over naïve regex matching.
+site_url: https://quantco.github.io/multiregex
+theme:
+  name: material
+  palette:
+    # Palette toggle for automatic mode
+    - media: "(prefers-color-scheme)"
+      toggle:
+        icon: material/brightness-auto
+        name: Switch to light mode
+    # Palette toggle for light mode
+    - media: "(prefers-color-scheme: light)"
+      scheme: default
+      toggle:
+        icon: material/brightness-7
+        name: Switch to dark mode
+      primary: deep purple
+    # Palette toggle for dark mode
+    - media: "(prefers-color-scheme: dark)"
+      scheme: slate
+      toggle:
+        icon: material/brightness-4
+        name: Switch to system preference
+      primary: deep purple
+  features:
+    - content.action.edit
+    - search.suggest
+    - search.highlight
+    - content.code.annotate
+    - content.code.copy
+  icon:
+    repo: fontawesome/brands/github-alt
+    edit: material/pencil
+repo_name: quantco/multiregex
+repo_url: https://github.com/quantco/multiregex
+edit_uri: edit/main/docs/
+plugins:
+  - search
+  - mkdocstrings:
+      handlers:
+        python:
+          options:
+            unwrap_annotated: true
+            show_symbol_type_heading: true
+            docstring_style: numpy
+            docstring_section_style: spacy
+            separate_signature: true
+            merge_init_into_class: true
+
+nav:
+- index.md
+- api-documentation.md
+markdown_extensions:
+  - admonition
+  - pymdownx.highlight
+  - pymdownx.superfences
+  - pymdownx.inlinehilite
diff --git a/multiregex/__init__.py b/multiregex/__init__.py
@@ -1,16 +1,18 @@
-r"""Speed up regex matching with non-regex substring "prematchers", similar to
-Bloom filters.
+r"""Speed up regex matching with non-regex substring "prematchers", similar to Bloom filters.
 
 For each regex pattern we use a list of simple (non-regex) substring prematchers.
 When evaluating regex patterns on a string, we use the prematchers to restrict
 the set of regex patterns to be run. Hence, the prematchers _must_ match each string
 unless it's impossible for the corresponding regex to match, similar to Bloom filters.
 
-Examples:
-    r"\bfoo\b"          -> ["foo"]
-    r"(foo|bar) \s*"    -> ["foo ", "bar "]
-    r"Gemäß Richtlinie" -> ["gemäß richtlinie"]
-    # Prematchers are all-lowercase (to support re.IGNORECASE).
+Examples
+--------
+```python
+r"\bfoo\b"          -> ["foo"]
+r"(foo|bar) \s*"    -> ["foo ", "bar "]
+r"Gemäß Richtlinie" -> ["gemäß richtlinie"]
+# Prematchers are all-lowercase (to support re.IGNORECASE).
+```
 
 Prematchers are attempted to be automatically generated from the regexes, see
 `RegexMatcher.generate_prematchers`.  You must provide a handcrafted list of
@@ -31,6 +33,7 @@
     import sre_constants
     import sre_parse
 from typing import (
+    Callable,
     Dict,
     Iterable,
     List,
@@ -68,21 +71,21 @@ def __init__(
         patterns: Iterable[
             Union[PatternOrStr, Tuple[PatternOrStr, Optional[Iterable[str]]]]
         ],
-        count_prematcher_false_positives=False,
+        count_prematcher_false_positives: bool = False,
     ):
-        """
+        """Create a new `RegexMatcher` instance.
+
         Parameters
         ----------
-        patterns : list of patterns or (pattern, prematchers) tuples
+        patterns: list of patterns or (pattern, prematchers) tuples
             The patterns to match against. Patterns may either be instances of
             `re.Pattern` (results from `re.compile`) or strings.
             If given as list of `(pattern, prematchers)` tuples, `prematchers`
             are custom prematchers (iterables of strings) or `None` for automatic
             prematchers using `generate_prematchers`. To disable prematchers for
             a specific pattern (ie., always run the "slow" matcher without any
             prematching), use a `(pattern, []`) tuple.
-        count_prematcher_false_positives : bool, default: False
-            If true, enable "profiling" to check the effectiveness of prematchers on
+        count_prematcher_false_positives: If true, enable "profiling" to check the effectiveness of prematchers on
             the input strings given to ``search``, ``match``, and ``fullmatch``.
             Use ``format_prematcher_false_positives`` to retrieve the profile.
         """
@@ -163,16 +166,16 @@ def _make_automaton(enumerated_patterns):
                 )
         return _ahocorasick_make_automaton(pattern_candidates_by_prematchers)
 
-    def run(self, match_func, s, enable_prematchers=True):
+    def run(self, match_func: Callable[[Pattern, str], re.Match], s: str, enable_prematchers: bool = True):
         """Quickly run `match_func` against `s` for all patterns.
 
         Parameters
         ----------
-        match_func : Callable[str] -> Match
+        match_func
             The base matching function, eg. `re.search`.
-        s : str
+        s
             The string to match against.
-        enable_prematchers : bool (default True)
+        enable_prematchers
             If false, do not use prematchers; use `match_func` only.
         """
         if enable_prematchers:
@@ -322,8 +325,7 @@ def _sre_find_terminals(sre_ast):
 
 
 def _ahocorasick_make_automaton(words: Dict[str, V]) -> "ahocorasick.Automaton[V]":
-    """Make an ahocorasick automaton from a dictionary of `needle -> value`
-    items."""
+    """Make an ahocorasick automaton from a dictionary of `needle -> value` items."""
     automaton = ahocorasick.Automaton()  # type: ahocorasick.Automaton[V]
     for word, value in words.items():
         _ahocorasick_ensure_successful(automaton.add_word(word, value))