ocr-stringdist 0.0.3__tar.gz → 0.0.5__tar.gz

{ocr_stringdist-0.0.3 → ocr_stringdist-0.0.5}/.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-0.0.5/.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-0.0.3 → ocr_stringdist-0.0.5}/.gitignore

@@ -15,7 +15,6 @@ _build/
 wheelhouse/
 site/
 target/
-Cargo.lock
 .venv
 .vscode
 

{ocr_stringdist-0.0.3 → ocr_stringdist-0.0.5}/Cargo.lock

@@ -1,19 +1,6 @@
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
-version = 4
-
-[[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",
-]
+version = 3
 
 [[package]]
 name = "autocfg"
@@ -27,17 +14,6 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
-[[package]]
-name = "getrandom"
-version = "0.2.15"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
-dependencies = [
- "cfg-if",
- "libc",
- "wasi",
-]
-
 [[package]]
 name = "heck"
 version = "0.5.0"
@@ -67,11 +43,9 @@ dependencies = [
 
 [[package]]
 name = "ocr_stringdist"
-version = "0.0.3"
+version = "0.0.5"
 dependencies = [
- "ahash",
  "pyo3",
- "smallvec",
 ]
 
 [[package]]
@@ -167,12 +141,6 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "smallvec"
-version = "1.15.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8917285742e9f3e1683f0a9c4e6b57960b7314d0b08d30d1ecd426713ee2eee9"
-
 [[package]]
 name = "syn"
 version = "2.0.100"
@@ -201,35 +169,3 @@ 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-0.0.3 → ocr_stringdist-0.0.5}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "ocr_stringdist"
-version = "0.0.3"
+version = "0.0.5"
 edition = "2021"
 description = "String distances considering OCR errors."
 authors = ["Niklas von Moers <niklasvmoers@protonmail.com>"]
@@ -15,8 +15,6 @@ crate-type = ["cdylib"]
 
 [dependencies]
 pyo3 = { version = "0.24.0", features = [] }
-ahash = "^0.8"
-smallvec = "1.15.0"
 
 [features]
 python = []

ocr_stringdist-0.0.5/Justfile

@@ -0,0 +1,14 @@
+venv:
+    rm -rf .venv
+    uv venv
+    uv sync
+
+pytest:
+    uv run maturin develop
+    uv run pytest
+
+test:
+    cargo test
+
+mypy:
+    uv run mypy .

{ocr_stringdist-0.0.3 → ocr_stringdist-0.0.5}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: ocr_stringdist
-Version: 0.0.3
+Version: 0.0.5
 Classifier: Programming Language :: Rust
-Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Programming Language :: Python
 Classifier: Operating System :: OS Independent
 License-File: LICENSE
 Summary: String distances considering OCR errors.
@@ -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)
 
@@ -35,11 +37,16 @@ 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.
+- **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).
 
 ## Usage
 
+### Weighted Levenshtein Distance
+
 ```python
 import ocr_stringdist as osd
 
@@ -48,16 +55,32 @@ 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
+    default_cost=1.0,
 )
 print(f"Distance with custom map: {distance}")
 ```
 
+### Finding the Best Candidate
+
+```python
+import ocr_stringdist as osd
+
+s = "apple"
+candidates = ["apply", "apples", "orange", "appIe"]  # 'appIe' has an OCR-like error
+
+def ocr_aware_distance(s1: str, s2: str) -> float:
+    return osd.weighted_levenshtein_distance(s1, s2, cost_map={("l", "I"): 0.1})
+
+best_candidate, best_dist = osd.find_best_candidate(s, candidates, ocr_aware_distance)
+print(f"Best candidate for '{s}' is '{best_candidate}' with distance {best_dist}")
+# Output: Best candidate for 'apple' is 'appIe' with distance 0.1
+```
+
 ## Acknowledgements
 
 This project is inspired by [jellyfish](https://github.com/jamesturk/jellyfish), providing the base implementations of the algorithms used here.

{ocr_stringdist-0.0.3 → ocr_stringdist-0.0.5}/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)
 
@@ -20,11 +22,16 @@ 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.
+- **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).
 
 ## Usage
 
+### Weighted Levenshtein Distance
+
 ```python
 import ocr_stringdist as osd
 
@@ -33,16 +40,32 @@ 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
+    default_cost=1.0,
 )
 print(f"Distance with custom map: {distance}")
 ```
 
+### Finding the Best Candidate
+
+```python
+import ocr_stringdist as osd
+
+s = "apple"
+candidates = ["apply", "apples", "orange", "appIe"]  # 'appIe' has an OCR-like error
+
+def ocr_aware_distance(s1: str, s2: str) -> float:
+    return osd.weighted_levenshtein_distance(s1, s2, cost_map={("l", "I"): 0.1})
+
+best_candidate, best_dist = osd.find_best_candidate(s, candidates, ocr_aware_distance)
+print(f"Best candidate for '{s}' is '{best_candidate}' with distance {best_dist}")
+# Output: Best candidate for 'apple' is 'appIe' with distance 0.1
+```
+
 ## Acknowledgements
 
 This project is inspired by [jellyfish](https://github.com/jamesturk/jellyfish), providing the base implementations of the algorithms used here.

ocr_stringdist-0.0.5/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-0.0.5/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-0.0.5/docs/source/api/index.rst

@@ -0,0 +1,18 @@
+.. _api_reference:
+
+API Reference
+=============
+
+This page contains the auto-generated API reference documentation.
+
+.. autofunction:: ocr_stringdist.__init__.weighted_levenshtein_distance
+
+.. automodule:: ocr_stringdist.matching
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: ocr_stringdist.default_ocr_distances
+   :members:
+   :undoc-members:
+   :show-inheritance:

ocr_stringdist-0.0.5/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-0.0.5/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-0.0.3 → ocr_stringdist-0.0.5}/example.py

@@ -1,5 +1,5 @@
-from ocr_stringdist import weighted_levenshtein_distance
 from icecream import ic
+from ocr_stringdist import find_best_candidate, weighted_levenshtein_distance
 
 ic(
     weighted_levenshtein_distance(
@@ -17,6 +17,15 @@ ic(
     )
 )
 
+# Substitution of multiple characters at once is supported.
+ic(
+    weighted_levenshtein_distance(
+        "이탈리",
+        "OI탈리",  # Korean syllables may be confused with multiple Latin letters at once
+        {("이", "OI"): 0.5},
+    ),
+)
+
 ic(
     weighted_levenshtein_distance(
         "ABCDE",
@@ -26,16 +35,13 @@ ic(
     )
 )
 
+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(
-        "RO8ERT",
-        "R0BERT",
-        {("O", "0"): 0.1, ("B", "8"): 0.2},
+    find_best_candidate(
+        "apple",
+        ["apply", "apples", "orange", "appIe"],
+        lambda s1, s2: weighted_levenshtein_distance(s1, s2, {("l", "I"): 0.1}),
     )
 )
-
-
-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))

ocr_stringdist-0.0.5/mypy.ini

@@ -0,0 +1,137 @@
+; Based on https://gist.github.com/CodeByAidan/adb2b9e188256def1fe35b932cba7eb8
+[mypy]
+check_untyped_defs = True
+disallow_any_generics = True
+disallow_any_unimported = True
+disallow_subclassing_any = True
+disallow_untyped_calls = True
+disallow_untyped_decorators = True
+disallow_untyped_defs = True
+ignore_missing_imports = True
+no_implicit_optional = True
+pretty = True
+show_column_numbers = True
+show_error_codes = True
+show_error_context = True
+strict_equality = True
+warn_return_any = True
+warn_unused_ignores = True
+
+; All of this below is just defaults:
+; -----------------------------------
+; (if any flags are commented out with a = and nothing after it,
+;  it means there is no default value/custom)
+;  ex. ; mypy_path =
+; -----------------------------------
+; (if any flags are commented out with a = and a value after it,
+;  it means that is the default value but it was changed out for
+;  my personal preference in my config above)
+;  ex. ; ignore_missing_imports = False
+
+; == Import discovery ==
+; mypy_path =
+; files =
+; modules =
+; packages =
+; exclude =
+namespace_packages = True
+explicit_package_bases = False
+; ignore_missing_imports = False
+follow_imports = normal
+follow_imports_for_stubs = False
+; python_executable =
+no_site_packages = False
+no_silence_site_packages = False
+
+; == Platform configuration ==
+; python_version =
+; platform =
+; always_true =
+; always_false =
+
+; == Disallow dynamic typing ==
+; disallow_any_unimported = False
+disallow_any_expr = False
+disallow_any_decorated = False
+disallow_any_explicit = False
+; disallow_any_generics = False
+; disallow_subclassing_any = False
+
+; == Untyped definitions and calls ==
+; disallow_untyped_calls = False
+; untyped_calls_exclude =
+; disallow_untyped_defs = False
+disallow_incomplete_defs = False
+; check_untyped_defs = False
+; disallow_untyped_decorators = False
+
+; == None and Optional handling ==
+implicit_optional = False
+strict_optional = True
+
+; == Configuring warnings ==
+warn_redundant_casts = False
+; warn_unused_ignores = False
+warn_no_return = True
+; warn_return_any = False
+warn_unreachable = False
+
+; == Suppressing errors ==
+ignore_errors = False
+
+; == Miscellaneous strictness flags ==
+allow_untyped_globals = False
+allow_redefinition = False
+local_partial_types = False
+; disable_error_code =
+; enable_error_code =
+implicit_reexport = True
+strict_concatenate = False
+; strict_equality = False
+strict = False
+
+; == Configuring error messages ==
+; show_error_context = False
+; show_column_numbers = False
+hide_error_codes = False
+; pretty = False
+color_output = True
+error_summary = True
+show_absolute_path = False
+force_uppercase_builtins = False
+force_union_syntax = False
+
+; == Incremental mode ==
+incremental = True
+cache_dir = .mypy_cache
+sqlite_cache = False
+cache_fine_grained = False
+skip_version_check = False
+skip_cache_mtime_checks = False
+
+; == Advanced options ==
+; plugins =
+pdb = False
+show_traceback = False
+raise_exceptions = False
+; custom_typing_module =
+; custom_typeshed_dir =
+warn_incomplete_stub = False
+
+; == Report generation ==
+; any_exprs_report =
+; cobertura_xml_report = ; pip install mypy[reports]
+; html_report = ; pip install mypy[reports]
+; xslt_html_report = ; pip install mypy[reports]
+; linecount_report =
+; linecoverage_report =
+; lineprecision_report =
+; txt_report = ; pip install mypy[reports]
+; xslt_txt_report = ; pip install mypy[reports]
+; xml_report = ; pip install mypy[reports]
+
+; == Miscellaneous ==
+; junit_xml =
+scripts_are_modules = False
+warn_unused_configs = False
+verbosity = 0