ocr-stringdist 0.0.4__cp310-cp310-win_amd64.whl → 0.0.6__cp310-cp310-win_amd64.whl

ocr_stringdist/__init__.py

@@ -6,7 +6,8 @@ from .matching import find_best_candidate
 
 __all__ = [
     "ocr_distance_map",
-    "weighted_levenshtein_distance",  # noqa: F405
+    "weighted_levenshtein_distance",
+    "batch_weighted_levenshtein_distance",
     "find_best_candidate",
 ]
 
@@ -19,23 +20,79 @@ def weighted_levenshtein_distance(
     *,
     symmetric: bool = True,
     default_cost: float = 1.0,
+    max_token_characters: int = 1,
 ) -> float:
     """
     Levenshtein distance with custom substitution costs.
     Insertion/deletion costs are 1.
 
-    The default `cost_map` considers common OCR errors, see `ocr_stringdist.ocr_distance_map`.
+    The default `cost_map` considers common OCR errors, see
+    :py:data:`ocr_stringdist.default_ocr_distances.ocr_distance_map`.
 
     :param s1: First string
     :param s2: Second string
-    :param cost_map: Dictionary mapping tuples of characters to their substitution cost.
+    :param cost_map: Dictionary mapping tuples of strings ("substitution tokens") to their
+                     substitution costs.
                      Only one direction needs to be configured unless `symmetric` is False.
+                     Note that you need to set `max_token_characters` if the substitution tokens
+                     have more than one character, for example when substituting "w" for "vv".
                      Defaults to `ocr_stringdist.ocr_distance_map`.
     :param symmetric: Should the keys of `cost_map` be considered to be symmetric? Defaults to True.
     :param default_cost: The default substitution cost for character pairs not found in `cost_map`.
+    :param max_token_characters: A positive integer, indicating the maximum number of characters a
+                                 substitution token in `cost_map` may have. The default 1 indicates
+                                 that only single characters can be substituted for each other.
+                                 Higher values lead to slower calculations.
     """
     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
+        s1,
+        s2,
+        cost_map=cost_map,
+        symmetric=symmetric,
+        default_cost=default_cost,
+        max_token_characters=max_token_characters,
+    )
+
+
+def batch_weighted_levenshtein_distance(
+    s: str,
+    candidates: list[str],
+    /,
+    cost_map: Optional[dict[tuple[str, str], float]] = None,
+    *,
+    symmetric: bool = True,
+    default_cost: float = 1.0,
+    max_token_characters: int = 1,
+) -> list[float]:
+    """
+    Calculate weighted Levenshtein distances between a string and multiple candidates.
+
+    This is more efficient than calling :func:`weighted_levenshtein_distance` multiple times.
+
+    :param s: The string to compare
+    :param candidates: List of candidate strings to compare against
+    :param cost_map: Dictionary mapping tuples of characters to their substitution cost.
+                     Only one direction needs to be configured unless `symmetric` is False.
+                     Defaults to `ocr_stringdist.ocr_distance_map`.
+    :param symmetric: Should the keys of `cost_map` be considered to be symmetric? Defaults to True.
+    :param default_cost: The default substitution cost for character pairs not found in `cost_map`.
+    :param max_token_characters: A positive integer, indicating the maximum number of characters a
+                                 substitution token in `cost_map` may have. The default 1 indicates
+                                 that only single characters can be substituted for each other.
+                                 Higher values lead to slower calculations.
+    :return: A list of distances corresponding to each candidate
+    """
+    if cost_map is None:
+        cost_map = ocr_distance_map
+    # _batch_weighted_levenshtein_distance is written in Rust, see src/rust_stringdist.rs.
+    return _batch_weighted_levenshtein_distance(  # type: ignore  # noqa: F405
+        s,
+        candidates,
+        cost_map=cost_map,
+        symmetric=symmetric,
+        default_cost=default_cost,
+        max_token_characters=max_token_characters,
     )

ocr_stringdist/default_ocr_distances.py

@@ -1,3 +1,5 @@
+# Start marker for literalinclude, see docs/source/api/index.rst.
+# OCR_DISTANCE_MAP_START
 ocr_distance_map: dict[tuple[str, str], float] = {
     ("O", "0"): 0.1,
     ("l", "1"): 0.1,
@@ -31,6 +33,8 @@ ocr_distance_map: dict[tuple[str, str], float] = {
     ("é", "á"): 0.7,
     ("E", "F"): 0.8,
 }
+# OCR_DISTANCE_MAP_END
+# End marker for literalinclude
 """
 Pre-defined distance map between characters, considering common OCR errors.
 The distances are between 0 and 1.

{ocr_stringdist-0.0.4.dist-info → ocr_stringdist-0.0.6.dist-info}/METADATA

@@ -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-0.0.6.dist-info/RECORD

@@ -0,0 +1,9 @@
+ocr_stringdist-0.0.6.dist-info/METADATA,sha256=c64RjWARPaiMAlVCUQrrCk2-pvgN1LjOMUOOHkg4FH4,3593
+ocr_stringdist-0.0.6.dist-info/WHEEL,sha256=77DqkvxB4HqZitBRK_M49NRS207JKb0MotMEjnxEWQ8,96
+ocr_stringdist-0.0.6.dist-info/licenses/LICENSE,sha256=3cNRiJag5vI0KMMDNf0oiaY4vg43rLxRszbMJs1GBoU,1092
+ocr_stringdist/default_ocr_distances.py,sha256=vlhzQCCcE-D1xor5RvMW0oaMuL_HP_5Y7SO4ESkdb4w,1075
+ocr_stringdist/matching.py,sha256=KEzYBBEHZhfLA9eD3MxDaehKiD9lUb0RQq74u5qWpVw,3376
+ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_stringdist/__init__.py,sha256=scHB0ZWB5vh5FShJIubGJlh3Pl8YaQ5HwWYXfof3MGA,4270
+ocr_stringdist/_rust_stringdist.cp310-win_amd64.pyd,sha256=bPEYoyrt0dWWA8_Rnw-vREuR348eSzreeHh4KauXjis,356864
+ocr_stringdist-0.0.6.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=77DqkvxB4HqZitBRK_M49NRS207JKb0MotMEjnxEWQ8,96
-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.cp310-win_amd64.pyd,sha256=mYFfcM02m0F4CEhC9aZcL993QVUaSZRkCZ2I52Theuw,236032
-ocr_stringdist-0.0.4.dist-info/RECORD,,