ocr-stringdist 0.0.7__pp311-pypy311_pp73-macosx_11_0_arm64.whl → 0.1.0__pp311-pypy311_pp73-macosx_11_0_arm64.whl

ocr_stringdist/levenshtein.py

@@ -8,33 +8,56 @@ def weighted_levenshtein_distance(
     s1: str,
     s2: str,
     /,
-    cost_map: Optional[dict[tuple[str, str], float]] = None,
+    substitution_costs: Optional[dict[tuple[str, str], float]] = None,
+    insertion_costs: Optional[dict[str, float]] = None,
+    deletion_costs: Optional[dict[str, float]] = None,
     *,
-    symmetric: bool = True,
-    default_cost: float = 1.0,
+    symmetric_substitution: bool = True,
+    default_substitution_cost: float = 1.0,
+    default_insertion_cost: float = 1.0,
+    default_deletion_cost: float = 1.0,
 ) -> float:
     """
-    Levenshtein distance with custom substitution costs.
-    Insertion/deletion costs are 1.
+    Levenshtein distance with custom substitution, insertion and deletion costs.
 
-    The default `cost_map` considers common OCR errors, see
+    The default `substitution_costs` considers common OCR errors, see
     :py:data:`ocr_stringdist.default_ocr_distances.ocr_distance_map`.
 
-    :param s1: First string
+    :param s1: First string (interpreted as the string read via OCR)
     :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.
+    :param substitution_costs: Dictionary mapping tuples of strings ("substitution tokens") to their
+                     substitution costs. Only one direction needs to be configured unless
+                     `symmetric_substitution` 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`.
+    :param insertion_costs: Dictionary mapping strings to their insertion costs.
+    :param deletion_costs: Dictionary mapping strings to their deletion costs.
+    :param symmetric_substitution: Should the keys of `substitution_costs` be considered to be
+                                   symmetric? Defaults to True.
+    :param default_substitution_cost: The default substitution cost for character pairs not found
+                                      in `substitution_costs`.
+    :param default_insertion_cost: The default insertion cost for characters not found in
+                                   `insertion_costs`.
+    :param default_deletion_cost: The default deletion cost for characters not found in
+                                  `deletion_costs`.
     """
-    if cost_map is None:
-        cost_map = ocr_distance_map
+    if substitution_costs is None:
+        substitution_costs = ocr_distance_map
+    if insertion_costs is None:
+        insertion_costs = {}
+    if deletion_costs is None:
+        deletion_costs = {}
     # _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,
+        substitution_costs=substitution_costs,
+        insertion_costs=insertion_costs,
+        deletion_costs=deletion_costs,
+        symmetric_substitution=symmetric_substitution,
+        default_substitution_cost=default_substitution_cost,
+        default_insertion_cost=default_insertion_cost,
+        default_deletion_cost=default_deletion_cost,
     )
 
 
@@ -42,30 +65,54 @@ def batch_weighted_levenshtein_distance(
     s: str,
     candidates: list[str],
     /,
-    cost_map: Optional[dict[tuple[str, str], float]] = None,
+    substitution_costs: Optional[dict[tuple[str, str], float]] = None,
+    insertion_costs: Optional[dict[str, float]] = None,
+    deletion_costs: Optional[dict[str, float]] = None,
     *,
-    symmetric: bool = True,
-    default_cost: float = 1.0,
+    symmetric_substitution: bool = True,
+    default_substitution_cost: float = 1.0,
+    default_insertion_cost: float = 1.0,
+    default_deletion_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 s: The string to compare (interpreted as the string read via OCR)
     :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.
+    :param substitution_costs: Dictionary mapping tuples of strings ("substitution tokens") to their
+                     substitution costs. Only one direction needs to be configured unless
+                     `symmetric_substitution` 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`.
+    :param insertion_costs: Dictionary mapping strings to their insertion costs.
+    :param deletion_costs: Dictionary mapping strings to their deletion costs.
+    :param symmetric_substitution: Should the keys of `substitution_costs` be considered to be
+                                   symmetric? Defaults to True.
+    :param default_substitution_cost: The default substitution cost for character pairs not found
+                                      in `substitution_costs`.
+    :param default_insertion_cost: The default insertion cost for characters not found in
+                                   `insertion_costs`.
+    :param default_deletion_cost: The default deletion cost for characters not found in
+                                  `deletion_costs`.
     :return: A list of distances corresponding to each candidate
     """
-    if cost_map is None:
-        cost_map = ocr_distance_map
+    if substitution_costs is None:
+        substitution_costs = ocr_distance_map
+    if insertion_costs is None:
+        insertion_costs = {}
+    if deletion_costs is None:
+        deletion_costs = {}
     # _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
+        s,
+        candidates,
+        substitution_costs=substitution_costs,
+        insertion_costs=insertion_costs,
+        deletion_costs=deletion_costs,
+        symmetric_substitution=symmetric_substitution,
+        default_substitution_cost=default_substitution_cost,
+        default_insertion_cost=default_insertion_cost,
+        default_deletion_cost=default_deletion_cost,
     )

{ocr_stringdist-0.0.7.dist-info → ocr_stringdist-0.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stringdist
-Version: 0.0.7
+Version: 0.1.0
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python
 Classifier: Operating System :: OS Independent
@@ -40,7 +40,6 @@ pip install ocr-stringdist
 - **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

ocr_stringdist-0.1.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+ocr_stringdist-0.1.0.dist-info/METADATA,sha256=vQJRhn0AEoIm159PyKQGMmH7JW35ZWUrQ-PWEBRteg8,3388
+ocr_stringdist-0.1.0.dist-info/WHEEL,sha256=d4nkB8nDBtE7QiNpIO4hl5gGjw3iQWNAqvU5LfTpJ00,111
+ocr_stringdist-0.1.0.dist-info/licenses/LICENSE,sha256=5BPRcjlnbl2t4TidSgpfGrtC_birSf8JlZfA-qmVoQE,1072
+ocr_stringdist/default_ocr_distances.py,sha256=oSu-TpHjPA4jxKpLAfmap8z0ZsC99jsOjnRVHW7Hj_Y,1033
+ocr_stringdist/__init__.py,sha256=haj_CNOovN9O6j1ixmku6BNTV4U3NQ5JEN2dC_4TmXc,332
+ocr_stringdist/matching.py,sha256=rr8R63Ttu2hTf5Mni7_P8aGBbjWs6t2QPV3wxKXspAs,3293
+ocr_stringdist/levenshtein.py,sha256=hHcarxjOzxhuopNNW3ZkPIcrSx2NjXYUWh9rR59W0Tc,5627
+ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_stringdist/_rust_stringdist.pypy311-pp73-darwin.so,sha256=r4Ltn067saa8O-9ezDvzcbNMHBUeAGMb0M6gqvbTRco,716912
+ocr_stringdist-0.1.0.dist-info/RECORD,,

ocr_stringdist-0.0.7.dist-info/RECORD

@@ -1,10 +0,0 @@
-ocr_stringdist-0.0.7.dist-info/METADATA,sha256=Rx1RtodaH76hveE0246t_Lo-lID1h6rI_j47joUb6Ak,3494
-ocr_stringdist-0.0.7.dist-info/WHEEL,sha256=d4nkB8nDBtE7QiNpIO4hl5gGjw3iQWNAqvU5LfTpJ00,111
-ocr_stringdist-0.0.7.dist-info/licenses/LICENSE,sha256=5BPRcjlnbl2t4TidSgpfGrtC_birSf8JlZfA-qmVoQE,1072
-ocr_stringdist/default_ocr_distances.py,sha256=oSu-TpHjPA4jxKpLAfmap8z0ZsC99jsOjnRVHW7Hj_Y,1033
-ocr_stringdist/__init__.py,sha256=haj_CNOovN9O6j1ixmku6BNTV4U3NQ5JEN2dC_4TmXc,332
-ocr_stringdist/matching.py,sha256=rr8R63Ttu2hTf5Mni7_P8aGBbjWs6t2QPV3wxKXspAs,3293
-ocr_stringdist/levenshtein.py,sha256=kJBJM5sG_g4MBXizbYVsGMQPWHk2vXWOvMspCYnthCA,3053
-ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ocr_stringdist/_rust_stringdist.pypy311-pp73-darwin.so,sha256=TYzBkI-7RS126tUb6CLlF6G-O6w7stbMk-aXZ9qbynY,676368
-ocr_stringdist-0.0.7.dist-info/RECORD,,