ocr-stringdist 0.0.5__cp310-cp310-win_amd64.whl → 0.0.7__cp310-cp310-win_amd64.whl

ocr_stringdist/__init__.py

@@ -1,42 +1,10 @@
-from typing import Optional
-
-from ._rust_stringdist import *  # noqa: F403
 from .default_ocr_distances import ocr_distance_map
+from .levenshtein import batch_weighted_levenshtein_distance, weighted_levenshtein_distance
 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",
 ]
-
-
-def weighted_levenshtein_distance(
-    s1: str,
-    s2: str,
-    /,
-    cost_map: Optional[dict[tuple[str, str], float]] = None,
-    *,
-    symmetric: bool = True,
-    default_cost: float = 1.0,
-) -> 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`.
-
-    :param s1: First string
-    :param s2: Second string
-    :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`.
-    """
-    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/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/levenshtein.py

@@ -0,0 +1,71 @@
+from typing import Optional
+
+from ._rust_stringdist import *  # noqa: F403
+from .default_ocr_distances import ocr_distance_map
+
+
+def weighted_levenshtein_distance(
+    s1: str,
+    s2: str,
+    /,
+    cost_map: Optional[dict[tuple[str, str], float]] = None,
+    *,
+    symmetric: bool = True,
+    default_cost: float = 1.0,
+) -> float:
+    """
+    Levenshtein distance with custom substitution costs.
+    Insertion/deletion costs are 1.
+
+    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 strings ("substitution tokens") to their
+                     substitution costs.
+                     Only one direction needs to be configured unless `symmetric` is False.
+                     Note that the runtime scales in the length of the longest substitution token.
+                     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`.
+    """
+    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
+    )
+
+
+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,
+) -> 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 strings ("substitution tokens") to their
+                     substitution costs.
+                     Only one direction needs to be configured unless `symmetric` is False.
+                     Note that the runtime scales in the length of the longest substitution token.
+                     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`.
+    :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
+    )

{ocr_stringdist-0.0.5.dist-info → ocr_stringdist-0.0.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stringdist
-Version: 0.0.5
+Version: 0.0.7
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python
 Classifier: Operating System :: OS Independent
@@ -36,7 +36,7 @@ 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").
@@ -60,7 +60,6 @@ distance = osd.weighted_levenshtein_distance(
     "hi", "Ini",
     cost_map=custom_map,
     symmetric=True,
-    default_cost=1.0,
 )
 print(f"Distance with custom map: {distance}")
 ```

ocr_stringdist-0.0.7.dist-info/RECORD

@@ -0,0 +1,10 @@
+ocr_stringdist-0.0.7.dist-info/METADATA,sha256=VQRJCE3NI3ZpbuesyXKgVqvp4yqmSQnJXDqtdVk9IQE,3564
+ocr_stringdist-0.0.7.dist-info/WHEEL,sha256=77DqkvxB4HqZitBRK_M49NRS207JKb0MotMEjnxEWQ8,96
+ocr_stringdist-0.0.7.dist-info/licenses/LICENSE,sha256=3cNRiJag5vI0KMMDNf0oiaY4vg43rLxRszbMJs1GBoU,1092
+ocr_stringdist/default_ocr_distances.py,sha256=vlhzQCCcE-D1xor5RvMW0oaMuL_HP_5Y7SO4ESkdb4w,1075
+ocr_stringdist/levenshtein.py,sha256=RF2B9dtlqDb6D3IjLlrJMYI5037N7U7-1mJwztijbBQ,3124
+ocr_stringdist/matching.py,sha256=KEzYBBEHZhfLA9eD3MxDaehKiD9lUb0RQq74u5qWpVw,3376
+ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_stringdist/__init__.py,sha256=MkIgLBJKXQRGfRoEdbrKBxwlRJKV85w-_jBdYDeH__0,342
+ocr_stringdist/_rust_stringdist.cp310-win_amd64.pyd,sha256=P9Mfe_5iu50XKb8kswsoLxR3k6oTsceJmGQRxfuiRoQ,355840
+ocr_stringdist-0.0.7.dist-info/RECORD,,

ocr_stringdist-0.0.5.dist-info/RECORD

@@ -1,9 +0,0 @@
-ocr_stringdist-0.0.5.dist-info/METADATA,sha256=R1JX6n_V46exR7NjMVdc4tachj3ceA-JsD-OMkQ1AfE,3549
-ocr_stringdist-0.0.5.dist-info/WHEEL,sha256=77DqkvxB4HqZitBRK_M49NRS207JKb0MotMEjnxEWQ8,96
-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.cp310-win_amd64.pyd,sha256=vkKitiAiQEq2IeCOtQWTxI9TDom2qNW8nE6ryjTRCh0,242176
-ocr_stringdist-0.0.5.dist-info/RECORD,,