Grammalecte  Diff

Annotate Patch Side-by-side Diff

Differences From Artifact [5e51d32779]:

To Artifact [947dc593c6]:

1
2
3
4
5
6
7
8
9
10
11
12
















13
14
15
16
17
18
19

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35













+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+








"""
Operations on strings:
- calculate distance between two strings
- transform strings with transformation codes
"""

import unicodedata
import re

from .char_player import distanceBetweenChars, dDistanceBetweenChars
from .echo import echo


# import time
# from functools import wraps
#
# def timethis (func):
#     "decorator for the execution time"
#     @wraps(func)
#     def wrapper (*args, **kwargs):
#         "something to prevent pylint whining"
#         fStart = time.perf_counter_ns()
#         result = func(*args, **kwargs)
#         fEnd = time.perf_counter_ns()
#         print(func.__name__, fEnd - fStart)
#         return result
#     return wrapper


#### N-GRAMS

def getNgrams (sWord, n=2):
    "return a list of Ngrams strings"
    return [ sWord[i:i+n]  for i in range(len(sWord)-n+1) ]
︙
87
88
89
90
91
92
93






































































94
95
96
97
98
99
100
101
102
103
104
105
106
107



108
109
110
111

112
113
114

115
116













117
















118
119
120
121


122
123
124
125
126
127
128

103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191

192
193
194
195
196
197
198

199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238

239
240
241
242
243
244
245
246
247








+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+












-

+
+
+



-
+



+


+
+
+
+
+
+
+
+
+
+
+
+
+

+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+



-
+
+








                    nLongest = lMatrix[x][y]
                    nLongestX = x
            else:
                lMatrix[x][y] = 0
    return s1[nLongestX-nLongest : nLongestX]


llMatrix = [
    [  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41 ],
    [  1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  2,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  3,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  4,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  5,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  6,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  7,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  8,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [  9,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 10,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 11,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 12,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 13,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 14,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 15,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 16,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 17,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 18,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 19,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 20,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 21,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 22,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 23,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 24,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 25,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 26,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 27,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 28,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 29,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 30,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 31,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 32,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 33,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 34,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 35,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 36,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 37,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 38,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 39,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 40,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ],
    [ 41,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 ]
]

#@timethis
def distanceDamerauLevenshteinX (s1, s2):
    "distance of Damerau-Levenshtein between <s1> and <s2>"
    # https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
    if s1 == s2:
        return 0
    nLen1 = len(s1)
    nLen2 = len(s2)
    if nLen1 > 40 or nLen2 > 40:
        return distanceDamerauLevenshtein(s1, s2)
    for i in range(1, nLen1+1):
        for j in range(1, nLen2+1):
            #nCost = 0  if s1[i-1] == s2[j-1]  else 1
            nCost = distanceBetweenChars(s1[i-1], s2[j-1])
            llMatrix[i][j] = min(
                llMatrix[i-1][j]   + 1,        # Deletion
                llMatrix[i][j-1]   + 1,        # Insertion
                llMatrix[i-1][j-1] + nCost,    # Substitution
            )
            if i > 1 and j > 1 and s1[i-1] == s2[j-2] and s1[i-2] == s2[j-1]:
                llMatrix[i][j] = min(llMatrix[i][j], llMatrix[i-2][j-2] + nCost)     # Transposition
    #_showLLMatrix(s1, s2)
    return llMatrix[nLen1][nLen2]

#@timethis
def distanceDamerauLevenshtein (s1, s2):
    "distance of Damerau-Levenshtein between <s1> and <s2>"
    # https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
    d = {}
    nLen1 = len(s1)
    nLen2 = len(s2)
    for i in range(-1, nLen1+1):
        d[i, -1] = i + 1
    for j in range(-1, nLen2+1):
        d[-1, j] = j + 1
    for i in range(nLen1):
        for j in range(nLen2):
            nCost = 0  if s1[i] == s2[j]  else 1
            #nCost = distanceBetweenChars(s1[i], s2[j])
            # We don’t use distanceBetweenChars to speed up the calc,
            # as we use this function only for very long words.
            nCost = 0  if s1[i] == s2[j]  else 1
            d[i, j] = min(
                d[i-1, j]   + 1,        # Deletion
                d[i,   j-1] + 1,        # Insertion
                d[i-1, j-1] + nCost,    # Substitution
                d[i-1, j-1] + nCost     # Substitution
            )
            if i and j and s1[i] == s2[j-1] and s1[i-1] == s2[j]:
                d[i, j] = min(d[i, j], d[i-2, j-2] + nCost)     # Transposition
    #_showMatrix(s1, s2, d)
    return d[nLen1-1, nLen2-1]

def _showMatrix (s1, s2, dMatrix):
    "display the matrix for Damerau-Levenshtein distance calculation"
    nLen1 = len(s1)
    nLen2 = len(s2)
    print("\n  ", end="")
    for j in range(-1, nLen2+1):
        print(f"{s2[j:j+1]:>4}", end="")
    print("")
    for i in range(-1, nLen1+1):
        print(f"{s1[i:i+1]:2}", end="")
        for j in range(-1, nLen2+1):
            print(f"{dMatrix.get((i, j),'   ·'):4}", end="")
        print("")

def _showLLMatrix (s1, s2):
    "display the matrix for fast Damerau-Levenshtein distance calculation"
    nLen1 = len(s1)
    nLen2 = len(s2)
    print("\n  ", end="")
    for j in range(-1, nLen2+1):
        print(f"{s2[j:j+1]:>4}", end="")
    print("")
    for i in range(0, nLen1+2):
        print(f"{s1[i-1:i]:2}", end="")
        for v in llMatrix[i][:nLen2+2]:
            print(f"{v:4}", end="")
        print("")


#@timethis
def distanceJaroWinkler (sWord1, sWord2, fBoost = .666):
    "distance of Jaro-Winkler between <sWord1> and <sWord2>, returns a float"
    # https://github.com/thsig/jaro-winkler-JS
    #if (sWord1 == sWord2): return 1.0
    if (sWord1 == sWord2):
        return 1.0
    nLen1 = len(sWord1)
    nLen2 = len(sWord2)
    nMax = max(nLen1, nLen2)
    aFlags1 = [ None for _ in range(nMax) ]
    aFlags2 = [ None for _ in range(nMax) ]
    nSearchRange = (max(nLen1, nLen2) // 2) - 1
    nMinLen = min(nLen1, nLen2)
︙
189
190
191
192
193
194
195

196
197
198
199
200
201
202

308
309
310
311
312
313
314
315
316
317
318
319
320
321
322








+








        # and the agreeing characters must be more than half of the
        # remaining characters.
        if nMinLen > 4  and  nCommon > i + 1  and  2 * nCommon >= nMinLen + i:
            fWeight += (1 - fWeight) * ((nCommon - i - 1) / (nLen1 * nLen2 - i*2 + 2))
    return fWeight


#@timethis
def distanceSift4 (s1, s2, nMaxOffset=5):
    "implementation of general Sift4."
    # faster than Damerau-Levenshtein and Jaro-Winkler
    # https://siderite.dev/blog/super-fast-and-accurate-string-distance.html
    if not s1:
        return len(s2)
    if not s2:
︙
252
253
254
255
256
257
258
259

260

261
262
263

264
265
266
267
268
269
270

372
373
374
375
376
377
378

379
380
381
382
383

384
385
386
387
388
389
390
391








-
+

+


-
+








            nLocalCS = 0
            i1 = i2 = min(i1, i2)
    nLargestCS += nLocalCS
    return round(max(nLen1, nLen2) - nLargestCS + nTrans)


def showDistance (s1, s2):
    "display Damerau-Levenshtein distance and Sift4 distance between <s1> and <s2>"
    "display distances between <s1> and <s2>"
    nDL = distanceDamerauLevenshtein(s1, s2)
    fDLX = float(distanceDamerauLevenshteinX(s1, s2))
    nS4 = distanceSift4(s1, s2)
    fJW = distanceJaroWinkler(s1, s2)
    echo(f"{s1:22} ≠ {s2:22} \tDL: {nDL}\tS4: {nS4}\tJW: {fJW}")
    echo(f"{s1:22} ≠ {s2:22} \tDL: {nDL:2}\tDLX: {fDLX:2.2}\tS4: {nS4:2}\tJW: {fJW}")



#### STEMMING OPERATIONS

## No stemming
︙
Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.004s