22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
for (let i=0; i <= sWord.length - n; i++) {
lNgrams.push(sWord.slice(i, i+n));
}
return lNgrams;
},
_xTransCharsForSpelling: new Map([
['ſ', 's'], ['ffi', 'ffi'], ['ffl', 'ffl'], ['ff', 'ff'], ['ſt', 'ft'], ['fi', 'fi'], ['fl', 'fl'], ['st', 'st']
]),
spellingNormalization: function (sWord) {
let sNewWord = "";
for (let c of sWord) {
sNewWord += this._xTransCharsForSpelling.gl_get(c, c);
}
|
|
>
|
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
|
for (let i=0; i <= sWord.length - n; i++) {
lNgrams.push(sWord.slice(i, i+n));
}
return lNgrams;
},
_xTransCharsForSpelling: new Map([
['ſ', 's'], ['ffi', 'ffi'], ['ffl', 'ffl'], ['ff', 'ff'], ['ſt', 'ft'], ['fi', 'fi'], ['fl', 'fl'], ['st', 'st'],
["'", '’']
]),
spellingNormalization: function (sWord) {
let sNewWord = "";
for (let c of sWord) {
sNewWord += this._xTransCharsForSpelling.gl_get(c, c);
}
|