1
2
3
4
5
6
7
8
9
10
11
12
13
|
//// STRING TRANSFORMATION
/*jslint esversion: 6*/
// Note: 48 is the ASCII code for "0"
var str_transform = {
distanceDamerauLevenshtein2: function (s1, s2) {
// distance of Damerau-Levenshtein between <s1> and <s2>
// https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
try {
let nLen1 = s1.length;
let nLen2 = s2.length;
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
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
42
43
44
45
46
47
48
49
50
51
52
53
54
|
//// STRING TRANSFORMATION
/*jslint esversion: 6*/
"use strict";
// Note: 48 is the ASCII code for "0"
var str_transform = {
longestCommonSubstring: function (string1, string2) {
// https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Longest_common_substring
// untested
// init max value
let longestCommonSubstring = 0;
// init 2D array with 0
let table = [],
len1 = string1.length,
len2 = string2.length,
row, col;
for (row = 0; row <= len1; row++) {
table[row] = [];
for (col = 0; col <= len2; col++) {
table[row][col] = 0;
}
}
// fill table
let i, j;
for (i = 0; i < len1; i++) {
for (j = 0; j < len2; j++) {
if (string1[i] === string2[j]) {
if (table[i][j] === 0){
table[i+1][j+1] = 1;
} else {
table[i+1][j+1] = table[i][j] + 1;
}
if (table[i+1][j+1] > longestCommonSubstring) {
longestCommonSubstring = table[i+1][j+1];
}
} else {
table[i+1][j+1] = 0;
}
}
}
return longestCommonSubstring;
},
distanceDamerauLevenshtein2: function (s1, s2) {
// distance of Damerau-Levenshtein between <s1> and <s2>
// https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
try {
let nLen1 = s1.length;
let nLen2 = s2.length;
|
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
|
break;
}
jSfx += 1;
}
return String.fromCharCode(sFlex.length-jSfx+48) + sStem.slice(jSfx);
},
getStemFromSuffixCode: function (sFlex, sSfxCode) {
// Suffix only
if (sSfxCode == "0") {
return sFlex;
}
return sSfxCode[0] == '0' ? sFlex + sSfxCode.slice(1) : sFlex.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
},
getStemFromAffixCode: function (sFlex, sAffCode) {
// Prefix and suffix
return sFlex;
}
if (!sAffCode.includes("/")) {
return "# error #";
}
let [sPfxCode, sSfxCode] = sAffCode.split('/');
sFlex = sPfxCode.slice(1) + sFlex.slice(sPfxCode.charCodeAt(0)-48);
return sSfxCode[0] == '0' ? sFlex + sSfxCode.slice(1) : sFlex.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
}
};
if (typeof(exports) !== 'undefined') {
exports.getStemFromSuffixCode = str_transform.getStemFromSuffixCode;
exports.getStemFromAffixCode = str_transform.getStemFromAffixCode;
}
|
|
<
|
|
<
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|
|
|
|
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
|
break;
}
jSfx += 1;
}
return String.fromCharCode(sFlex.length-jSfx+48) + sStem.slice(jSfx);
},
changeWordWithSuffixCode: function (sWord, sSfxCode) {
if (sSfxCode == "0") {
return sWord;
}
return sSfxCode[0] == '0' ? sWord + sSfxCode.slice(1) : sWord.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
},
// Prefix and suffix
defineAffixCode: function (sFlex, sStem) {
/*
UNTESTED!
Returns a string defining how to get stem from flexion. Examples:
"0" if stem = flexion
"stem" if no common substring
"n(pfx)/m(sfx)"
with n and m: chars with numeric meaning, "0" = 0, "1" = 1, ... ":" = 10, etc. (See ASCII table.) Says how many letters to strip from flexion.
pfx [optional]: string to add before the flexion
sfx [optional]: string to add after the flexion
*/
if (sFlex == sStem) {
return "0";
}
// is stem a substring of flexion?
let n = sFlex.indexOf(sStem);
if (n >= 0) {
return String.fromCharCode(n+48) + "/" + String.fromCharCode(sFlex.length-(sStem.length+n)+48);
}
// no, so we are looking for common substring
let sSubs = this.longestCommonSubstring(sFlex, sStem);
if (sSubs.length > 1) {
let iPos = sStem.indexOf(sSubs);
let sPfx = sStem.slice(0, iPos);
let sSfx = sStem.slice(iPos+sSubs.length);
let n = sFlex.indexOf(sSubs);
let m = sFlex.length - (sSubs.length+n);
return String.fromCharCode(n+48) + sPfx + "/" + String.fromCharCode(m+48) + sSfx;
}
return sStem;
},
changeWordWithAffixCode: function (sWord, sAffCode) {
if (sAffCode == "0") {
return sWord;
}
if (!sAffCode.includes("/")) {
return sAffCode;
}
let [sPfxCode, sSfxCode] = sAffCode.split('/');
sWord = sPfxCode.slice(1) + sWord.slice(sPfxCode.charCodeAt(0)-48);
return sSfxCode[0] == '0' ? sWord + sSfxCode.slice(1) : sWord.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
}
};
if (typeof(exports) !== 'undefined') {
exports.getStemFromSuffixCode = str_transform.getStemFromSuffixCode;
exports.getStemFromAffixCode = str_transform.getStemFromAffixCode;
}
|