ocr-stringdist 0.0.6__cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl → 0.0.7__cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl

ocr_stringdist/__init__.py

@@ -1,7 +1,5 @@
-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__ = [
@@ -10,89 +8,3 @@ __all__ = [
     "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,
-    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
-    :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 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,
-        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/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-0.0.6.dist-info → ocr_stringdist-0.0.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stringdist
-Version: 0.0.6
+Version: 0.0.7
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python
 Classifier: Operating System :: OS Independent
@@ -60,7 +60,6 @@ distance = osd.weighted_levenshtein_distance(
     "hi", "Ini",
     cost_map=custom_map,
     symmetric=True,
-    max_token_characters=2,
 )
 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=Rx1RtodaH76hveE0246t_Lo-lID1h6rI_j47joUb6Ak,3494
+ocr_stringdist-0.0.7.dist-info/WHEEL,sha256=SW30N8kywnSNNSd8rZHXljiViD5k9KuBxLtnK5N91_Q,129
+ocr_stringdist-0.0.7.dist-info/licenses/LICENSE,sha256=5BPRcjlnbl2t4TidSgpfGrtC_birSf8JlZfA-qmVoQE,1072
+ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_stringdist/__init__.py,sha256=haj_CNOovN9O6j1ixmku6BNTV4U3NQ5JEN2dC_4TmXc,332
+ocr_stringdist/default_ocr_distances.py,sha256=oSu-TpHjPA4jxKpLAfmap8z0ZsC99jsOjnRVHW7Hj_Y,1033
+ocr_stringdist/matching.py,sha256=rr8R63Ttu2hTf5Mni7_P8aGBbjWs6t2QPV3wxKXspAs,3293
+ocr_stringdist/levenshtein.py,sha256=kJBJM5sG_g4MBXizbYVsGMQPWHk2vXWOvMspCYnthCA,3053
+ocr_stringdist/_rust_stringdist.cpython-312-arm-linux-gnueabihf.so,sha256=1c17EgzaztMl_v2bG3mK5c5-exqb3f1Xbbq1o2kpN6s,727928
+ocr_stringdist-0.0.7.dist-info/RECORD,,

ocr_stringdist-0.0.6.dist-info/RECORD

@@ -1,9 +0,0 @@
-ocr_stringdist-0.0.6.dist-info/METADATA,sha256=w_dnhka08_rjLZ3LxFzTqeaUuvUrzer7FkjrqQI2xIg,3522
-ocr_stringdist-0.0.6.dist-info/WHEEL,sha256=SW30N8kywnSNNSd8rZHXljiViD5k9KuBxLtnK5N91_Q,129
-ocr_stringdist-0.0.6.dist-info/licenses/LICENSE,sha256=5BPRcjlnbl2t4TidSgpfGrtC_birSf8JlZfA-qmVoQE,1072
-ocr_stringdist/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ocr_stringdist/__init__.py,sha256=45mZy8Gx3ygO60XAcWR8ZVS4LAoPcvKd946MwbM9-vc,4172
-ocr_stringdist/default_ocr_distances.py,sha256=oSu-TpHjPA4jxKpLAfmap8z0ZsC99jsOjnRVHW7Hj_Y,1033
-ocr_stringdist/matching.py,sha256=rr8R63Ttu2hTf5Mni7_P8aGBbjWs6t2QPV3wxKXspAs,3293
-ocr_stringdist/_rust_stringdist.cpython-312-arm-linux-gnueabihf.so,sha256=D7IVyBttsogLhQq8jzmWjW0OVo_jx8b7nJffA1EgM0c,736272
-ocr_stringdist-0.0.6.dist-info/RECORD,,