ocr-stringdist 0.0.4__tar.gz → 0.0.6__tar.gz

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/.github/workflows/CI.yml

@@ -1,4 +1,3 @@
-# This file was edited manually to add
 # The original was autogenerated by maturin v0.14.15
 on:
   push:

ocr_stringdist-0.0.6/.github/workflows/docs.yml

@@ -0,0 +1,70 @@
+name: Deploy Documentation to Pages
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch: # Allows manual triggering from the Actions tab
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install uv
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
+
+      - name: Create virtual environment
+        run: uv venv
+
+      - name: Install dependencies
+        run: uv sync --group docs
+
+      - name: Build Sphinx documentation
+        run: |
+          uv run make -C docs html
+          # Add a .nojekyll file to the build output directory to prevent
+          # GitHub Pages from ignoring files that start with an underscore
+          # (like Sphinx's _static and _images directories).
+          touch docs/build/html/.nojekyll
+
+      - name: Setup Pages
+        uses: actions/configure-pages@v4
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          # Upload entire directory. GitHub Pages expects index.html at the root.
+          path: './docs/build/html'
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4
+        # This action automatically downloads the artifact uploaded by
+        # upload-pages-artifact and deploys it to GitHub Pages.

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/Cargo.lock

@@ -2,19 +2,6 @@
 # It is not intended for manual editing.
 version = 3
 
-[[package]]
-name = "ahash"
-version = "0.8.11"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
-dependencies = [
- "cfg-if",
- "getrandom",
- "once_cell",
- "version_check",
- "zerocopy",
-]
-
 [[package]]
 name = "autocfg"
 version = "1.4.0"
@@ -28,16 +15,36 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
-name = "getrandom"
-version = "0.2.15"
+name = "crossbeam-deque"
+version = "0.8.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
+checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
 dependencies = [
- "cfg-if",
- "libc",
- "wasi",
+ "crossbeam-epoch",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-epoch"
+version = "0.9.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+dependencies = [
+ "crossbeam-utils",
 ]
 
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
 [[package]]
 name = "heck"
 version = "0.5.0"
@@ -67,11 +74,10 @@ dependencies = [
 
 [[package]]
 name = "ocr_stringdist"
-version = "0.0.4"
+version = "0.0.6"
 dependencies = [
- "ahash",
  "pyo3",
- "smallvec",
+ "rayon",
 ]
 
 [[package]]
@@ -168,10 +174,24 @@ dependencies = [
 ]
 
 [[package]]
-name = "smallvec"
-version = "1.15.0"
+name = "rayon"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa"
+dependencies = [
+ "either",
+ "rayon-core",
+]
+
+[[package]]
+name = "rayon-core"
+version = "1.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8917285742e9f3e1683f0a9c4e6b57960b7314d0b08d30d1ecd426713ee2eee9"
+checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2"
+dependencies = [
+ "crossbeam-deque",
+ "crossbeam-utils",
+]
 
 [[package]]
 name = "syn"
@@ -201,35 +221,3 @@ name = "unindent"
 version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
-
-[[package]]
-name = "version_check"
-version = "0.9.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
-
-[[package]]
-name = "wasi"
-version = "0.11.0+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
-
-[[package]]
-name = "zerocopy"
-version = "0.7.35"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0"
-dependencies = [
- "zerocopy-derive",
-]
-
-[[package]]
-name = "zerocopy-derive"
-version = "0.7.35"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "ocr_stringdist"
-version = "0.0.4"
+version = "0.0.6"
 edition = "2021"
 description = "String distances considering OCR errors."
 authors = ["Niklas von Moers <niklasvmoers@protonmail.com>"]
@@ -15,8 +15,7 @@ crate-type = ["cdylib"]
 
 [dependencies]
 pyo3 = { version = "0.24.0", features = [] }
-ahash = "^0.8"
-smallvec = "1.15.0"
+rayon = "1.10.0"
 
 [features]
 python = []

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/Justfile

@@ -4,7 +4,7 @@ venv:
     uv sync
 
 pytest:
-    maturin develop
+    uv run maturin develop
     uv run pytest
 
 test:
@@ -12,3 +12,9 @@ test:
 
 mypy:
     uv run mypy .
+
+lint:
+    uv run ruff check . --fix
+
+doc:
+    uv run make -C docs html

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stringdist
-Version: 0.0.4
+Version: 0.0.6
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python
 Classifier: Operating System :: OS Independent
@@ -17,6 +17,8 @@ Project-URL: repository, https://github.com/NiklasvonM/ocr-stringdist
 
 A Python library for string distance calculations that account for common OCR (optical character recognition) errors.
 
+Documentation: https://niklasvonm.github.io/ocr-stringdist/
+
 [![PyPI](https://img.shields.io/badge/PyPI-Package-blue)](https://pypi.org/project/ocr-stringdist/)
 [![License](https://img.shields.io/badge/License-MIT-green)](LICENSE)
 
@@ -34,10 +36,12 @@ pip install ocr-stringdist
 
 ## Features
 
-- **Weighted Levenshtein Distance**: An adaptation of the classic Levenshtein algorithm with custom substitution costs for character pairs that are commonly confused in OCR models.
+- **Weighted Levenshtein Distance**: An adaptation of the classic Levenshtein algorithm with custom substitution costs for character pairs that are commonly confused in OCR models, including efficient batch processing.
+- **Unicode Support**: Arbitrary unicode strings can be compared.
+- **Substitution of Multiple Characters**: Not just character pairs, but string pairs may be substituted, for example the Korean syllable "이" for the two letters "OI".
 - **Pre-defined OCR Distance Map**: A built-in distance map for common OCR confusions (e.g., "0" vs "O", "1" vs "l", "5" vs "S").
 - **Customizable Cost Maps**: Create your own substitution cost maps for specific OCR systems or domains.
-- **Best Match Finder**: Utility function find_best_candidate to efficiently find the best matching string from a collection of candidates using any specified distance function (including the library's OCR-aware ones). Supports early stopping for performance optimization.
+- **Best Match Finder**: Utility function `find_best_candidate` to efficiently find the best matching string from a collection of candidates using any specified distance function (including the library's OCR-aware ones).
 
 ## Usage
 
@@ -51,12 +55,12 @@ distance = osd.weighted_levenshtein_distance("OCR5", "OCRS")
 print(f"Distance between 'OCR5' and 'OCRS': {distance}")  # Will be less than 1.0
 
 # Custom cost map
-custom_map = {("f", "t"): 0.2, ("m", "n"): 0.1}
+custom_map = {("In", "h"): 0.5}
 distance = osd.weighted_levenshtein_distance(
-    "first", "tirst",
+    "hi", "Ini",
     cost_map=custom_map,
     symmetric=True,
-    default_cost=1.0
+    max_token_characters=2,
 )
 print(f"Distance with custom map: {distance}")
 ```

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/README.md

@@ -2,6 +2,8 @@
 
 A Python library for string distance calculations that account for common OCR (optical character recognition) errors.
 
+Documentation: https://niklasvonm.github.io/ocr-stringdist/
+
 [![PyPI](https://img.shields.io/badge/PyPI-Package-blue)](https://pypi.org/project/ocr-stringdist/)
 [![License](https://img.shields.io/badge/License-MIT-green)](LICENSE)
 
@@ -19,10 +21,12 @@ pip install ocr-stringdist
 
 ## Features
 
-- **Weighted Levenshtein Distance**: An adaptation of the classic Levenshtein algorithm with custom substitution costs for character pairs that are commonly confused in OCR models.
+- **Weighted Levenshtein Distance**: An adaptation of the classic Levenshtein algorithm with custom substitution costs for character pairs that are commonly confused in OCR models, including efficient batch processing.
+- **Unicode Support**: Arbitrary unicode strings can be compared.
+- **Substitution of Multiple Characters**: Not just character pairs, but string pairs may be substituted, for example the Korean syllable "이" for the two letters "OI".
 - **Pre-defined OCR Distance Map**: A built-in distance map for common OCR confusions (e.g., "0" vs "O", "1" vs "l", "5" vs "S").
 - **Customizable Cost Maps**: Create your own substitution cost maps for specific OCR systems or domains.
-- **Best Match Finder**: Utility function find_best_candidate to efficiently find the best matching string from a collection of candidates using any specified distance function (including the library's OCR-aware ones). Supports early stopping for performance optimization.
+- **Best Match Finder**: Utility function `find_best_candidate` to efficiently find the best matching string from a collection of candidates using any specified distance function (including the library's OCR-aware ones).
 
 ## Usage
 
@@ -36,12 +40,12 @@ distance = osd.weighted_levenshtein_distance("OCR5", "OCRS")
 print(f"Distance between 'OCR5' and 'OCRS': {distance}")  # Will be less than 1.0
 
 # Custom cost map
-custom_map = {("f", "t"): 0.2, ("m", "n"): 0.1}
+custom_map = {("In", "h"): 0.5}
 distance = osd.weighted_levenshtein_distance(
-    "first", "tirst",
+    "hi", "Ini",
     cost_map=custom_map,
     symmetric=True,
-    default_cost=1.0
+    max_token_characters=2,
 )
 print(f"Distance with custom map: {distance}")
 ```

ocr_stringdist-0.0.6/docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

ocr_stringdist-0.0.6/docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

ocr_stringdist-0.0.6/docs/source/api/index.rst

@@ -0,0 +1,22 @@
+.. _api_reference:
+
+API Reference
+=============
+
+This page contains the auto-generated API reference documentation.
+
+.. autofunction:: ocr_stringdist.weighted_levenshtein_distance
+
+.. autofunction:: ocr_stringdist.batch_weighted_levenshtein_distance
+
+.. automodule:: ocr_stringdist.matching
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. autodata:: ocr_stringdist.default_ocr_distances.ocr_distance_map
+   :annotation:
+.. literalinclude:: ../../../python/ocr_stringdist/default_ocr_distances.py
+   :language: python
+   :start-after: OCR_DISTANCE_MAP_START
+   :end-before: OCR_DISTANCE_MAP_END

ocr_stringdist-0.0.6/docs/source/conf.py

@@ -0,0 +1,40 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+
+import os
+import sys
+
+# source code is in project_root/python/ocr_stringdist
+sys.path.insert(0, os.path.abspath("../../python"))
+
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = "OCR-StringDist"
+copyright = "2025, Niklas von Moers"
+author = "Niklas von Moers"
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions: list[str] = [
+    "sphinx.ext.autodoc",  # Core library to pull documentation from docstrings
+    "sphinx.ext.napoleon",  # Support for Google and NumPy style docstrings
+    "sphinx.ext.intersphinx",  # Link to other projects' documentation
+    "sphinx.ext.viewcode",  # Add links to source code
+    "sphinx_mdinclude",  # Include Markdown
+]
+
+templates_path = ["_templates"]
+exclude_patterns: list[str] = []
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = "sphinx_rtd_theme"
+html_static_path: list[str] = ["_static"]

ocr_stringdist-0.0.6/docs/source/index.rst

@@ -0,0 +1,10 @@
+.. OCR-StringDist documentation master file, created by
+   sphinx-quickstart on Sun Apr 20 10:40:20 2025.
+
+.. mdinclude:: ../../README.md
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   api/index

ocr_stringdist-0.0.6/examples/batch_processing.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+"""
+Example demonstrating the usage of the batch processing functions from ocr_stringdist.
+"""
+
+import time
+from typing import Any, Callable
+
+import ocr_stringdist as osd
+
+MAX_TOKEN_CHARACTERS = 1
+
+
+def benchmark(func: Callable, *args: Any, **kwargs: Any) -> tuple[Any, float]:  # type: ignore
+    """Run a function and return the execution time in seconds."""
+    start = time.time()
+    result = func(*args, **kwargs)
+    end = time.time()
+    return result, end - start
+
+
+def compare_methods() -> None:
+    """
+    Compare the performance of different methods for calculating Levenshtein distances.
+    """
+    # Example data
+    source = "recognition"
+    candidates = ["recognition", "recogmtion", "recognltlon", "recogrtition", "recognitton"] * 1000
+
+    print("\nSingle string against multiple candidates:")
+    print("-" * 50)
+
+    # Standard loop approach
+    _, time_loop = benchmark(
+        lambda: [
+            osd.weighted_levenshtein_distance(
+                source, cand, max_token_characters=MAX_TOKEN_CHARACTERS
+            )
+            for cand in candidates
+        ]
+    )
+    print(
+        f"Loop of single calls: {time_loop:.6f} seconds "
+        f"({1000 * time_loop / len(candidates):.6f}ms each)"
+    )
+
+    # Batch approach
+    _, time_batch = benchmark(
+        osd.batch_weighted_levenshtein_distance,
+        source,
+        candidates,
+        max_token_characters=MAX_TOKEN_CHARACTERS,
+    )
+    print(
+        f"Batch function: {time_batch:.6f} seconds "
+        f"({1000 * time_batch / len(candidates):.6f}ms each)"
+    )
+    print(f"Speedup: {time_loop / time_batch:.2f}x")
+
+
+def main() -> None:
+    """Main function."""
+    print("Demonstrating batch processing functions from ocr_stringdist\n")
+
+    # Run the benchmarks
+    compare_methods()
+
+
+if __name__ == "__main__":
+    main()

ocr_stringdist-0.0.4/example.py → ocr_stringdist-0.0.6/examples/weighted_levenshtein.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 from icecream import ic
 from ocr_stringdist import find_best_candidate, weighted_levenshtein_distance
 
@@ -17,29 +18,27 @@ ic(
     )
 )
 
+# Substitution of multiple characters at once is supported.
 ic(
     weighted_levenshtein_distance(
-        "ABCDE",
-        "XBCDE",
-        cost_map={},
-        default_cost=0.8,  # Lower default substitution cost (default is 1.0)
-    )
+        "이탈리",
+        "OI탈리",  # Korean syllables may be confused with multiple Latin letters at once
+        {("이", "OI"): 0.5},
+        max_token_characters=2,
+    ),
 )
 
 ic(
     weighted_levenshtein_distance(
-        "RO8ERT",
-        "R0BERT",
-        {("O", "0"): 0.1, ("B", "8"): 0.2},
+        "ABCDE",
+        "XBCDE",
+        cost_map={},
+        default_cost=0.8,  # Lower default substitution cost (default is 1.0)
     )
 )
 
-
 ic(weighted_levenshtein_distance("A", "B", {("A", "B"): 0.0}, symmetric=False))
 ic(weighted_levenshtein_distance("A", "B", {("B", "A"): 0.0}, symmetric=False))
-ic(weighted_levenshtein_distance("B", "A", {("B", "A"): 0.0}, symmetric=False))
-ic(weighted_levenshtein_distance("B", "A", {("A", "B"): 0.0}, symmetric=False))
-
 
 ic(
     find_best_candidate(

{ocr_stringdist-0.0.4 → ocr_stringdist-0.0.6}/pyproject.toml

@@ -30,3 +30,8 @@ dev = [
     "ruff>=0.11.6",
     "wheel>=0.45.1",
 ]
+docs = [
+    "sphinx>=7.4.7",
+    "sphinx-mdinclude>=0.6.2",
+    "sphinx-rtd-theme>=3.0.2",
+]