ocr-stringdist 0.0.4__cp313-cp313-win32.whl → 0.0.5__cp313-cp313-win32.whl

ocr_stringdist/__init__.py

@@ -36,6 +36,7 @@ def weighted_levenshtein_distance(
     """
     if cost_map is None:
         cost_map = ocr_distance_map
+    # _weighted_levenshtein_distance is written in Rust, see src/rust_stringdist.rs.
     return _weighted_levenshtein_distance(  # type: ignore  # noqa: F405
         s1, s2, cost_map=cost_map, symmetric=symmetric, default_cost=default_cost
     )

{ocr_stringdist-0.0.4.dist-info → ocr_stringdist-0.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stringdist
-Version: 0.0.4
+Version: 0.0.5
 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)
 
@@ -35,9 +37,11 @@ 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). 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
+    default_cost=1.0,
 )
 print(f"Distance with custom map: {distance}")
 ```

ocr_stringdist-0.0.5.dist-info/RECORD

@@ -0,0 +1,9 @@
+ocr_stringdist-0.0.5.dist-info/METADATA,sha256=R1JX6n_V46exR7NjMVdc4tachj3ceA-JsD-OMkQ1AfE,3549
+ocr_stringdist-0.0.5.dist-info/WHEEL,sha256=eh90R9THiv1HYPhYUCnpm_RAErMfEQKvZWVMxF3uaCM,92
+ocr_stringdist-0.0.5.dist-info/licenses/LICENSE,sha256=3cNRiJag5vI0KMMDNf0oiaY4vg43rLxRszbMJs1GBoU,1092
+ocr_stringdist/default_ocr_distances.py,sha256=STNRMGWEYOCHo11uP51JUQfvNrSZleMCxt6wsPkctfg,925
+ocr_stringdist/matching.py,sha256=KEzYBBEHZhfLA9eD3MxDaehKiD9lUb0RQq74u5qWpVw,3376
+ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_stringdist/__init__.py,sha256=rEW1u0sWzXDSoziEJzfCgxbKQiYNmrLCdQzFfZ1mDtM,1557
+ocr_stringdist/_rust_stringdist.cp313-win32.pyd,sha256=tC7HRCuACl-L1_RsgaJw93uaBTAtFHciXps3Q3HwDbU,208384
+ocr_stringdist-0.0.5.dist-info/RECORD,,

ocr_stringdist-0.0.4.dist-info/RECORD

@@ -1,9 +0,0 @@
-ocr_stringdist-0.0.4.dist-info/METADATA,sha256=1lSh8HZ9TrBv0BWdBbMZk-_0qbE1tEEUd25xfAFnd7s,3320
-ocr_stringdist-0.0.4.dist-info/WHEEL,sha256=eh90R9THiv1HYPhYUCnpm_RAErMfEQKvZWVMxF3uaCM,92
-ocr_stringdist-0.0.4.dist-info/licenses/LICENSE,sha256=3cNRiJag5vI0KMMDNf0oiaY4vg43rLxRszbMJs1GBoU,1092
-ocr_stringdist/default_ocr_distances.py,sha256=STNRMGWEYOCHo11uP51JUQfvNrSZleMCxt6wsPkctfg,925
-ocr_stringdist/matching.py,sha256=KEzYBBEHZhfLA9eD3MxDaehKiD9lUb0RQq74u5qWpVw,3376
-ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ocr_stringdist/__init__.py,sha256=Z6ZeTSfpKRaUM15FPW00MfLBKVDUCP21Xh5VLtnC4Tk,1471
-ocr_stringdist/_rust_stringdist.cp313-win32.pyd,sha256=_gG1gEjjgQmcDh0QaxCEI1OLMw5NrUngnvxckxjhl94,199680
-ocr_stringdist-0.0.4.dist-info/RECORD,,