implement Levenshtein.editops

src/rapidfuzz/distance/LCSseq_py.py

@@ -254,7 +254,7 @@ def normalized_similarity(
     return norm_sim if (score_cutoff is None or norm_sim >= score_cutoff) else 0
 
 
-def _matrix(s1: Sequence[Hashable], s2: Sequence[Hashable]):
+def _matrix(s1: Sequence[Hashable], s2: Sequence[Hashable]) -> ([int], int):
     if not s1:
         return (0, [])
 

src/rapidfuzz/distance/Levenshtein_py.py

@@ -5,10 +5,10 @@
 
 from typing import Callable, Hashable, Sequence
 
-from rapidfuzz._common_py import conv_sequences
+from rapidfuzz._common_py import common_affix, conv_sequences
 from rapidfuzz._utils import is_none
 from rapidfuzz.distance import Indel_py as Indel
-from rapidfuzz.distance._initialize_py import Editops, Opcodes
+from rapidfuzz.distance._initialize_py import Editop, Editops, Opcodes
 
 
 def _levenshtein_maximum(s1: Sequence[Hashable], s2: Sequence[Hashable], weights: tuple[int, int, int]) -> int:
@@ -372,6 +372,47 @@ def normalized_similarity(
     return norm_sim if (score_cutoff is None or norm_sim >= score_cutoff) else 0
 
 
+def _matrix(s1: Sequence[Hashable], s2: Sequence[Hashable]) -> int:
+    if not s1:
+        return (len(s2), [], [])
+
+    VP = (1 << len(s1)) - 1
+    VN = 0
+    currDist = len(s1)
+    mask = 1 << (len(s1) - 1)
+
+    block: dict[Hashable, int] = {}
+    block_get = block.get
+    x = 1
+    for ch1 in s1:
+        block[ch1] = block_get(ch1, 0) | x
+        x <<= 1
+
+    matrix_VP = []
+    matrix_VN = []
+    for ch2 in s2:
+        # Step 1: Computing D0
+        PM_j = block_get(ch2, 0)
+        X = PM_j
+        D0 = (((X & VP) + VP) ^ VP) | X | VN
+        # Step 2: Computing HP and HN
+        HP = VN | ~(D0 | VP)
+        HN = D0 & VP
+        # Step 3: Computing the value D[m,j]
+        currDist += (HP & mask) != 0
+        currDist -= (HN & mask) != 0
+        # Step 4: Computing Vp and VN
+        HP = (HP << 1) | 1
+        HN = HN << 1
+        VP = HN | ~(D0 | HP)
+        VN = HP & D0
+
+        matrix_VP.append(VP)
+        matrix_VN.append(VN)
+
+    return (currDist, matrix_VP, matrix_VN)
+
+
 def editops(
     s1: Sequence[Hashable],
     s2: Sequence[Hashable],
@@ -425,7 +466,54 @@ def editops(
         s2 = processor(s2)
 
     s1, s2 = conv_sequences(s1, s2)
-    raise NotImplementedError
+    prefix_len, suffix_len = common_affix(s1, s2)
+    s1 = s1[prefix_len : len(s1) - suffix_len]
+    s2 = s2[prefix_len : len(s2) - suffix_len]
+    dist, VP, VN = _matrix(s1, s2)
+
+    editops = Editops([], 0, 0)
+    editops._src_len = len(s1) + prefix_len + suffix_len
+    editops._dest_len = len(s2) + prefix_len + suffix_len
+
+    if dist == 0:
+        return editops
+
+    editop_list = [None] * dist
+    col = len(s1)
+    row = len(s2)
+    while row != 0 and col != 0:
+        # deletion
+        if VP[row - 1] & (1 << (col - 1)):
+            dist -= 1
+            col -= 1
+            editop_list[dist] = Editop("delete", col + prefix_len, row + prefix_len)
+        else:
+            row -= 1
+
+            # insertion
+            if row and (VN[row - 1] & (1 << (col - 1))):
+                dist -= 1
+                editop_list[dist] = Editop("insert", col + prefix_len, row + prefix_len)
+            else:
+                col -= 1
+
+                # replace (Matches are not recorded)
+                if s1[col] != s2[row]:
+                    dist -= 1
+                    editop_list[dist] = Editop("replace", col + prefix_len, row + prefix_len)
+
+    while col != 0:
+        dist -= 1
+        col -= 1
+        editop_list[dist] = Editop("delete", col + prefix_len, row + prefix_len)
+
+    while row != 0:
+        dist -= 1
+        row -= 1
+        editop_list[dist] = Editop("insert", col + prefix_len, row + prefix_len)
+
+    editops._editops = editop_list
+    return editops
 
 
 def opcodes(

tests/distance/test_Levenshtein.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-from rapidfuzz.distance import Opcode, Opcodes, metrics_cpp
 from tests.distance.common import Levenshtein
 
 
@@ -82,18 +81,18 @@ def test_Editops():
     """
     basic test for Levenshtein.editops
     """
-    assert metrics_cpp.levenshtein_editops("0", "").as_list() == [("delete", 0, 0)]
-    assert metrics_cpp.levenshtein_editops("", "0").as_list() == [("insert", 0, 0)]
+    assert Levenshtein.editops("0", "").as_list() == [("delete", 0, 0)]
+    assert Levenshtein.editops("", "0").as_list() == [("insert", 0, 0)]
 
-    assert metrics_cpp.levenshtein_editops("00", "0").as_list() == [("delete", 1, 1)]
-    assert metrics_cpp.levenshtein_editops("0", "00").as_list() == [("insert", 1, 1)]
+    assert Levenshtein.editops("00", "0").as_list() == [("delete", 1, 1)]
+    assert Levenshtein.editops("0", "00").as_list() == [("insert", 1, 1)]
 
-    assert metrics_cpp.levenshtein_editops("qabxcd", "abycdf").as_list() == [
+    assert Levenshtein.editops("qabxcd", "abycdf").as_list() == [
         ("delete", 0, 0),
         ("replace", 3, 2),
         ("insert", 6, 5),
     ]
-    assert metrics_cpp.levenshtein_editops("Lorem ipsum.", "XYZLorem ABC iPsum").as_list() == [
+    assert Levenshtein.editops("Lorem ipsum.", "XYZLorem ABC iPsum").as_list() == [
         ("insert", 0, 0),
         ("insert", 0, 1),
         ("insert", 0, 2),
@@ -105,7 +104,7 @@ def test_Editops():
         ("delete", 11, 18),
     ]
 
-    ops = metrics_cpp.levenshtein_editops("aaabaaa", "abbaaabba")
+    ops = Levenshtein.editops("aaabaaa", "abbaaabba")
     assert ops.src_len == 7
     assert ops.dest_len == 9
 
@@ -114,9 +113,7 @@ def test_Opcodes():
     """
     basic test for Levenshtein.opcodes
     """
-    assert metrics_cpp.levenshtein_opcodes("", "abc") == Opcodes(
-        [Opcode(tag="insert", src_start=0, src_end=0, dest_start=0, dest_end=3)], 0, 3
-    )
+    assert Levenshtein.opcodes("", "abc").as_list() == [("insert", 0, 0, 0, 3)]
 
 
 def test_mbleven():

tests/test_hypothesis.py

@@ -209,7 +209,7 @@ def test_matching_blocks(s1, s2):
     """
     test correct matching block conversion
     """
-    ops = metrics_cpp.levenshtein_editops(s1, s2)
+    ops = Levenshtein.editops(s1, s2)
     assert ops.as_matching_blocks() == ops.as_opcodes().as_matching_blocks()
 
 
@@ -219,7 +219,7 @@ def test_levenshtein_editops(s1, s2):
     """
     test Levenshtein.editops with any sizes
     """
-    ops = metrics_cpp.levenshtein_editops(s1, s2)
+    ops = Levenshtein.editops(s1, s2)
     assert ops.apply(s1, s2) == s2
 
 
@@ -229,7 +229,7 @@ def test_levenshtein_editops_block(s1, s2):
     """
     test Levenshtein.editops for long strings
     """
-    ops = metrics_cpp.levenshtein_editops(s1, s2)
+    ops = Levenshtein.editops(s1, s2)
     assert ops.apply(s1, s2) == s2
 
 
@@ -259,7 +259,7 @@ def test_levenshtein_opcodes(s1, s2):
     """
     test Levenshtein.opcodes with any sizes
     """
-    ops = metrics_cpp.levenshtein_opcodes(s1, s2)
+    ops = Levenshtein.opcodes(s1, s2)
     assert ops.apply(s1, s2) == s2
 
 
@@ -269,7 +269,7 @@ def test_levenshtein_opcodes_block(s1, s2):
     """
     test Levenshtein.opcodes for long strings
     """
-    ops = metrics_cpp.levenshtein_opcodes(s1, s2)
+    ops = Levenshtein.opcodes(s1, s2)
     assert ops.apply(s1, s2) == s2