multiregex 2.0.0__tar.gz → 2.0.2__tar.gz

{multiregex-2.0.0 → multiregex-2.0.2}/.gitattributes

@@ -4,3 +4,5 @@
 
 *.{py,yaml,yml,sh} text eol=lf
 *.bat text eol=crlf
+# GitHub syntax highlighting
+pixi.lock linguist-language=YAML linguist-generated=true

multiregex-2.0.2/.github/CODEOWNERS

@@ -0,0 +1,2 @@
+* @0xbe7a
+* @pavelzw

multiregex-2.0.2/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

multiregex-2.0.2/.github/ISSUE_TEMPLATE/issue-template.md

@@ -0,0 +1,6 @@
+---
+name: New issue
+about: Create a new issue
+---
+
+<!-- ⚠️ This is an open-source repository. Do not share sensitive information. -->

multiregex-2.0.0/.github/PULL_REQUEST_TEMPLATE.md → multiregex-2.0.2/.github/pull_request_template.md

@@ -1,3 +1,5 @@
+<!-- ⚠️ This is an open-source repository. Do not share sensitive information. -->
+
 <!--
 Thank you for pull request.
 Below are a few things we ask you kindly to self-check before getting a review. Remove checks that are not relevant.
@@ -5,4 +7,4 @@ Below are a few things we ask you kindly to self-check before getting a review.
 
 # Checklist
 
-* [ ] Added a `CHANGELOG.rst` entry
+- [ ] Added a `CHANGELOG.rst` entry

multiregex-2.0.2/.github/workflows/build.yml

@@ -0,0 +1,44 @@
+name: Build
+on:
+  pull_request:
+  push:
+    branches:
+      - "main"
+    tags:
+      - "*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.ref }}
+          fetch-depth: 0
+      - name: Set up pixi
+        uses: prefix-dev/setup-pixi@v0.8.0
+        with:
+          environments: build
+      - name: Build project
+        run: pixi run -e build build-wheel
+      - name: Upload package
+        uses: actions/upload-artifact@v4
+        with:
+          name: artifact
+          path: dist/*
+
+  release:
+    name: Publish package
+    if: startsWith(github.ref, 'refs/tags/')
+    needs: [build]
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    environment: pypi
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: artifact
+          path: dist
+      - name: Publish package on PyPi
+        uses: pypa/gh-action-pypi-publish@81e9d935c883d0b210363ab89cf05f3894778450

multiregex-2.0.2/.github/workflows/ci.yml

@@ -0,0 +1,60 @@
+name: CI
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+defaults:
+  run:
+    shell: bash -el {0}
+
+jobs:
+  unit-tests:
+    name: pytest
+    timeout-minutes: 10
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - { os: ubuntu-latest, environment: py38 }
+          - { os: ubuntu-latest, environment: py312 }
+          - { os: windows-latest, environment: py38 }
+          - { os: windows-latest, environment: py312 }
+          - { os: macos-latest, environment: py38 }
+          - { os: macos-latest, environment: py312 }
+    steps:
+      - name: Checkout branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.ref }}
+          fetch-depth: 0
+      - name: Set up pixi
+        uses: prefix-dev/setup-pixi@v0.8.0
+        with:
+          environments: ${{ matrix.environment }}
+      - name: Install repository
+        run: pixi run -e ${{ matrix.environment }} postinstall
+      - name: Run unittests
+        uses: quantco/pytest-action@v2
+        with:
+          report-title: Unit tests ${{ matrix.environment }}
+          custom-pytest: pixi run -e ${{ matrix.environment }} pytest
+
+  pre-commit-checks:
+    name: Pre-commit Checks
+    timeout-minutes: 30
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.ref }}
+          fetch-depth: 0
+      - name: Set up pixi
+        uses: prefix-dev/setup-pixi@v0.8.0
+        with:
+          environments: lint default
+      - name: pre-commit
+        run: pixi run pre-commit-run --color=always --show-diff-on-failure

multiregex-2.0.2/.gitignore

@@ -0,0 +1,127 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+.envrc
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+.asv
+pip-wheel-metadata
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+/.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs/api/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# pycharm
+/.idea/
+
+
+# experiments
+private_*
+
+# mlflow
+mlruns
+
+# vscode
+.vscode
+
+# direnv
+.envrc
+# pixi environments
+.pixi
+*.egg-info
+
+.ruff_cache

multiregex-2.0.2/.pre-commit-config.yaml

@@ -0,0 +1,65 @@
+repos:
+  - repo: local
+    hooks:
+      # docformatter
+      - id: docformatter
+        name: docformatter
+        entry: pixi run -e lint docformatter -i
+        language: system
+        types: [python]
+      # ruff
+      - id: ruff
+        name: ruff
+        entry: pixi run -e lint ruff check --fix --exit-non-zero-on-fix --force-exclude
+        language: system
+        types_or: [python, pyi]
+        require_serial: true
+      - id: ruff-format
+        name: ruff-format
+        entry: pixi run -e lint ruff format --force-exclude
+        language: system
+        types_or: [python, pyi]
+        require_serial: true
+      # prettier
+      - id: prettier
+        name: prettier
+        entry: pixi run -e lint prettier --write --list-different --ignore-unknown
+        language: system
+        types: [text]
+        files: \.(md|yml|yaml)$
+      # pre-commit-hooks
+      - id: trailing-whitespace-fixer
+        name: trailing-whitespace-fixer
+        entry: pixi run -e lint trailing-whitespace-fixer
+        language: system
+        types: [text]
+      - id: end-of-file-fixer
+        name: end-of-file-fixer
+        entry: pixi run -e lint end-of-file-fixer
+        language: system
+        types: [text]
+      - id: check-merge-conflict
+        name: check-merge-conflict
+        entry: pixi run -e lint check-merge-conflict --assume-in-merge
+        language: system
+        types: [text]
+      # typos
+      - id: typos
+        name: typos
+        entry: pixi run -e lint typos --force-exclude
+        language: system
+        types: [text]
+        require_serial: true
+      # mypy
+      - id: mypy
+        name: mypy
+        entry: pixi run -e default mypy
+        language: system
+        types: [python]
+        require_serial: true
+      # taplo
+      - id: taplo
+        name: taplo
+        entry: pixi run -e lint taplo format
+        language: system
+        types: [toml]

{multiregex-2.0.0 → multiregex-2.0.2}/CHANGELOG.rst

@@ -7,6 +7,15 @@
 Changelog
 =========
 
+2.0.2 (2024-05-23)
+------------------
+- Included a py.typed file to indicate that the package is fully typed.
+
+2.0.1 (2023-06-11)
+------------------
+
+- Fix exception when mixing patterns with prematchers and without prematchers.
+
 2.0.0 (2023-03-08)
 ------------------
 

{multiregex-2.0.0 → multiregex-2.0.2}/PKG-INFO

@@ -1,45 +1,48 @@
 Metadata-Version: 2.1
 Name: multiregex
-Version: 2.0.0
-Summary: Speed up regex matching with non-regex substring "prematchers", similar to Bloom filters.
-Author-email: "QuantCo, Inc." <noreply@quantco.com>
-Maintainer-email: Jonas Haag <jonas.haag@quantco.com>
-Description-Content-Type: text/markdown
+Version: 2.0.2
+Summary: Quickly match many regexes against a string. Provides 2-10x speedups over naïve regex matching.
+Author-email: "QuantCo, Inc." <noreply@quantco.com>, Jonas Haag <jonas@lophus.org>
+Maintainer-email: Bela Stoyan <bela.stoyan@quantco.com>
+Project-URL: Home, https://github.com/quantco/multiregex
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.4
-Classifier: Programming Language :: Python :: 3.5
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
-Project-URL: Home, https://github.com/quantco/multiregex
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pyahocorasick
 
 # multiregex
 
 [![CI](https://github.com/Quantco/multiregex/actions/workflows/ci.yml/badge.svg)](https://github.com/Quantco/multiregex/actions/workflows/ci.yml)
 [![Documentation](https://img.shields.io/badge/docs-latest-success?style=plastic)](https://docs.dev.quantco.cloud/qc-github-artifacts/Quantco/multiregex/latest/index.html)
+[![conda-forge](https://img.shields.io/conda/vn/conda-forge/multiregex?logoColor=white&logo=conda-forge)](https://anaconda.org/conda-forge/multiregex)
+[![pypi-version](https://img.shields.io/pypi/v/multiregex.svg?logo=pypi&logoColor=white)](https://pypi.org/project/multiregex)
+[![python-version](https://img.shields.io/pypi/pyversions/multiregex?logoColor=white&logo=python)](https://pypi.org/project/multiregex)
 
 Quickly match many regexes against a string. Provides 2-10x speedups over naïve regex matching.
 
+## Introduction
+
+See [this introductory blog post](https://tech.quantco.com/2022/07/31/multiregex.html).
+
 ## Installation
 
 You can install the package in development mode using:
 
 ```bash
-git clone git@github.com:quantco/multiregex.git
+git clone https://github.com/quantco/multiregex
 cd multiregex
 
-# create and activate a fresh environment named multiregex
-# see environment.yml for details
-mamba env create
-conda activate multiregex
-
-pre-commit install
-pip install --no-build-isolation -e .
+pixi run pre-commit-install
+pixi run postinstall
+pixi run test
 ```
 
-
 ## Usage
 
 ```py
@@ -68,7 +71,7 @@ To be able to quickly match many regexes against a string, `multiregex` uses
 at least one can be assumed to be present in the haystack if the corresponding regex matches.
 As an example, a valid prematcher of `r"\w+\.com"` could be `[".com"]` and a valid
 prematcher of `r"(B|b)aNäNa"` could be `["b"]` or `["anäna"]`.
-Note that prematchers must be all-lowercase (in order for ``multiregex`` to be able to support ``re.IGNORECASE``).
+Note that prematchers must be all-lowercase (in order for `multiregex` to be able to support `re.IGNORECASE`).
 
 You will likely have to provide your own prematchers for all but the simplest
 regex patterns:
@@ -120,4 +123,3 @@ print(matcher.format_prematcher_false_positives())
 
 In this example, there were 137 input strings that were matched positive by the prematcher but negative by the regex.
 In other words, the prematcher failed to prevent slow regex evaluation in 72% of the cases.
-

{multiregex-2.0.0 → multiregex-2.0.2}/README.md

@@ -2,27 +2,29 @@
 
 [![CI](https://github.com/Quantco/multiregex/actions/workflows/ci.yml/badge.svg)](https://github.com/Quantco/multiregex/actions/workflows/ci.yml)
 [![Documentation](https://img.shields.io/badge/docs-latest-success?style=plastic)](https://docs.dev.quantco.cloud/qc-github-artifacts/Quantco/multiregex/latest/index.html)
+[![conda-forge](https://img.shields.io/conda/vn/conda-forge/multiregex?logoColor=white&logo=conda-forge)](https://anaconda.org/conda-forge/multiregex)
+[![pypi-version](https://img.shields.io/pypi/v/multiregex.svg?logo=pypi&logoColor=white)](https://pypi.org/project/multiregex)
+[![python-version](https://img.shields.io/pypi/pyversions/multiregex?logoColor=white&logo=python)](https://pypi.org/project/multiregex)
 
 Quickly match many regexes against a string. Provides 2-10x speedups over naïve regex matching.
 
+## Introduction
+
+See [this introductory blog post](https://tech.quantco.com/2022/07/31/multiregex.html).
+
 ## Installation
 
 You can install the package in development mode using:
 
 ```bash
-git clone git@github.com:quantco/multiregex.git
+git clone https://github.com/quantco/multiregex
 cd multiregex
 
-# create and activate a fresh environment named multiregex
-# see environment.yml for details
-mamba env create
-conda activate multiregex
-
-pre-commit install
-pip install --no-build-isolation -e .
+pixi run pre-commit-install
+pixi run postinstall
+pixi run test
 ```
 
-
 ## Usage
 
 ```py
@@ -51,7 +53,7 @@ To be able to quickly match many regexes against a string, `multiregex` uses
 at least one can be assumed to be present in the haystack if the corresponding regex matches.
 As an example, a valid prematcher of `r"\w+\.com"` could be `[".com"]` and a valid
 prematcher of `r"(B|b)aNäNa"` could be `["b"]` or `["anäna"]`.
-Note that prematchers must be all-lowercase (in order for ``multiregex`` to be able to support ``re.IGNORECASE``).
+Note that prematchers must be all-lowercase (in order for `multiregex` to be able to support `re.IGNORECASE`).
 
 You will likely have to provide your own prematchers for all but the simplest
 regex patterns:

{multiregex-2.0.0 → multiregex-2.0.2}/docs/make.bat

@@ -32,4 +32,4 @@ goto end
 %SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
 
 :end
-popd
+popd

{multiregex-2.0.0/src → multiregex-2.0.2}/multiregex/__init__.py

@@ -1,4 +1,5 @@
-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
@@ -19,7 +20,9 @@ automatically generated prematchers.
 
 import collections
 import functools
+import importlib
 import re
+import warnings
 
 try:
     sre_constants = re._constants  # type: ignore
@@ -42,7 +45,12 @@ from typing import (
 
 import ahocorasick
 
-__version__ = "2.0.0"
+try:
+    __version__ = importlib.metadata.version(__name__)
+except importlib.metadata.PackageNotFoundError as e:
+    warnings.warn(f"Could not determine version of {__name__}", stacklevel=1)
+    warnings.warn(str(e), stacklevel=1)
+    __version__ = "unknown"
 
 
 V = TypeVar("V")
@@ -83,10 +91,13 @@ class RegexMatcher:
         patterns = self._generate_missing_prematchers(patterns)
         self.patterns = [pattern for pattern, _ in patterns]
         self.prematchers = dict(patterns)
+        enumerated_patterns = list(enumerate(patterns))
         self.patterns_without_prematchers = {
-            pattern for pattern, prematchers in patterns if not prematchers
+            (idx, pattern)
+            for idx, (pattern, prematchers) in enumerated_patterns
+            if not prematchers
         }
-        self.automaton = self._make_automaton(patterns)
+        self.automaton = self._make_automaton(enumerated_patterns)
 
         self.count_prematcher_false_positives = count_prematcher_false_positives
         if count_prematcher_false_positives:
@@ -107,9 +118,7 @@ class RegexMatcher:
         def safe_set(iterable):
             if isinstance(iterable, str):
                 raise TypeError(
-                    "Refusing to interpret {!r} as a list of patterns, pass a list of strings instead".format(
-                        iterable
-                    )
+                    f"Refusing to interpret {iterable!r} as a list of patterns, pass a list of strings instead"
                 )
             else:
                 return set(iterable)
@@ -130,9 +139,11 @@ class RegexMatcher:
         patterns = [
             (
                 pattern,
-                self.generate_prematchers(pattern)
-                if prematchers is None
-                else prematchers,
+                (
+                    self.generate_prematchers(pattern)
+                    if prematchers is None
+                    else prematchers
+                ),
             )
             for pattern, prematchers in patterns
         ]
@@ -142,10 +153,10 @@ class RegexMatcher:
         return patterns
 
     @staticmethod
-    def _make_automaton(patterns):
+    def _make_automaton(enumerated_patterns):
         """Create the pyahocorasick automaton."""
         pattern_candidates_by_prematchers = collections.defaultdict(set)
-        for pattern_idx, (pattern, prematchers) in enumerate(patterns):
+        for pattern_idx, (pattern, prematchers) in enumerated_patterns:
             for prematcher in prematchers:
                 # `pattern_idx` is used for keeping patterns in order, see `get_pattern_candidates`.
                 pattern_candidates_by_prematchers[prematcher].add(
@@ -190,10 +201,8 @@ class RegexMatcher:
 
     """Alias for ``run(re.search, ...)``."""
     search = functools.partialmethod(run, re.search)
-
     """Alias for ``run(re.match, ...)``."""
     match = functools.partialmethod(run, re.match)
-
     """Alias for ``run(re.fullmatch, ...)``."""
     fullmatch = functools.partialmethod(run, re.fullmatch)
 
@@ -248,18 +257,17 @@ class RegexMatcher:
 def validate_prematcher(prematcher: str) -> None:
     if not prematcher or any(map(str.isupper, prematcher)):
         raise ValueError(
-            "Prematcher {!r} must be non-empty, all-lowercase, all-ASCII".format(
-                prematcher
-            )
+            f"Prematcher {prematcher!r} must be non-empty, all-lowercase, all-ASCII"
         )
 
 
 def generate_prematchers(pattern: Pattern) -> Prematchers:
     """Generate fallback/default prematchers for the given regex `pattern`.
 
-    Currently the fallback prematcher is just the set of longest terminal texts
-    in the pattern, eg. "Fast(er)? regex(es| matching)" -> {" regex"}. One level of
-    branches with the "|" character is supported, ie. "(a|bb|ccc)" -> {"ccc", "a", "bb"}.
+    Currently the fallback prematcher is just the set of longest
+    terminal texts in the pattern, eg. "Fast(er)? regex(es| matching)"
+    -> {" regex"}. One level of branches with the "|" character is
+    supported, ie. "(a|bb|ccc)" -> {"ccc", "a", "bb"}.
     """
 
     def _get_top_level_prematcher(sre_ast):
@@ -283,7 +291,7 @@ def generate_prematchers(pattern: Pattern) -> Prematchers:
         if all(child_prematchers):
             return child_prematchers
 
-    raise ValueError("Could not generate prematchers for {!r}".format(pattern.pattern))
+    raise ValueError(f"Could not generate prematchers for {pattern.pattern!r}")
 
 
 def _simplify_sre_ast(sre_ast):
@@ -315,7 +323,8 @@ 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))
@@ -324,6 +333,6 @@ def _ahocorasick_make_automaton(words: Dict[str, V]) -> "ahocorasick.Automaton[V
 
 
 def _ahocorasick_ensure_successful(res):
-    """pyahocorasick returns errors as bools."""
+    """Pyahocorasick returns errors as bools."""
     if res is False:
         raise AhocorasickError("Error performing ahocorasick call")