@orama/orama
Version:
A complete search engine and RAG pipeline in your browser, server, or edge network with support for full-text, vector, and hybrid search in less than 2kb.
180 lines • 4.63 kB
JavaScript
// eslint-disable-next-line @typescript-eslint/ban-ts-comment
// @ts-nocheck
const step2List = {
ational: 'ate',
tional: 'tion',
enci: 'ence',
anci: 'ance',
izer: 'ize',
bli: 'ble',
alli: 'al',
entli: 'ent',
eli: 'e',
ousli: 'ous',
ization: 'ize',
ation: 'ate',
ator: 'ate',
alism: 'al',
iveness: 'ive',
fulness: 'ful',
ousness: 'ous',
aliti: 'al',
iviti: 'ive',
biliti: 'ble',
logi: 'log'
};
const step3List = {
icate: 'ic',
ative: '',
alize: 'al',
iciti: 'ic',
ical: 'ic',
ful: '',
ness: ''
};
// Consonant
const c = '[^aeiou]';
// Vowel
const v = '[aeiouy]';
// Consonant sequence
const C = c + '[^aeiouy]*';
// Vowel sequence
const V = v + '[aeiou]*';
// [C]VC... is m>0
const mgr0 = '^(' + C + ')?' + V + C;
// [C]VC[V] is m=1
const meq1 = '^(' + C + ')?' + V + C + '(' + V + ')?$';
// [C]VCVC... is m>1
const mgr1 = '^(' + C + ')?' + V + C + V + C;
// vowel in stem
const s_v = '^(' + C + ')?' + v;
export function stemmer(w) {
let stem;
let suffix;
let re;
let re2;
let re3;
let re4;
if (w.length < 3) {
return w;
}
const firstch = w.substring(0, 1);
if (firstch == 'y') {
w = firstch.toUpperCase() + w.substring(1);
}
re = /^(.+?)(ss|i)es$/;
re2 = /^(.+?)([^s])s$/;
if (re.test(w)) {
w = w.replace(re, '$1$2');
}
else if (re2.test(w)) {
w = w.replace(re2, '$1$2');
}
re = /^(.+?)eed$/;
re2 = /^(.+?)(ed|ing)$/;
if (re.test(w)) {
const fp = re.exec(w);
re = new RegExp(mgr0);
if (re.test(fp[1])) {
re = /.$/;
w = w.replace(re, '');
}
}
else if (re2.test(w)) {
const fp = re2.exec(w);
stem = fp[1];
re2 = new RegExp(s_v);
if (re2.test(stem)) {
w = stem;
re2 = /(at|bl|iz)$/;
re3 = new RegExp('([^aeiouylsz])\\1$');
re4 = new RegExp('^' + C + v + '[^aeiouwxy]$');
if (re2.test(w)) {
w = w + 'e';
}
else if (re3.test(w)) {
re = /.$/;
w = w.replace(re, '');
}
else if (re4.test(w)) {
w = w + 'e';
}
}
}
re = /^(.+?)y$/;
if (re.test(w)) {
const fp = re.exec(w);
stem = fp?.[1];
re = new RegExp(s_v);
if (stem && re.test(stem)) {
w = stem + 'i';
}
}
re =
/^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
if (re.test(w)) {
const fp = re.exec(w);
stem = fp?.[1];
suffix = fp?.[2];
re = new RegExp(mgr0);
if (stem && re.test(stem)) {
// eslint-disable-next-line @typescript-eslint/ban-ts-comment
// @ts-ignore
w = stem + step2List[suffix];
}
}
re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
if (re.test(w)) {
const fp = re.exec(w);
stem = fp?.[1];
suffix = fp?.[2];
re = new RegExp(mgr0);
// eslint-disable-next-line @typescript-eslint/ban-ts-comment
// @ts-ignore
if (stem && re.test(stem)) {
// eslint-disable-next-line @typescript-eslint/ban-ts-comment
// @ts-ignore
w = stem + step3List[suffix];
}
}
re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
re2 = /^(.+?)(s|t)(ion)$/;
if (re.test(w)) {
const fp = re.exec(w);
stem = fp?.[1];
re = new RegExp(mgr1);
if (stem && re.test(stem)) {
w = stem;
}
}
else if (re2.test(w)) {
const fp = re2.exec(w);
stem = fp?.[1] ?? '' + fp?.[2] ?? '';
re2 = new RegExp(mgr1);
if (re2.test(stem)) {
w = stem;
}
}
re = /^(.+?)e$/;
if (re.test(w)) {
const fp = re.exec(w);
stem = fp?.[1];
re = new RegExp(mgr1);
re2 = new RegExp(meq1);
re3 = new RegExp('^' + C + v + '[^aeiouwxy]$');
if (stem && (re.test(stem) || (re2.test(stem) && !re3.test(stem)))) {
w = stem;
}
}
re = /ll$/;
re2 = new RegExp(mgr1);
if (re.test(w) && re2.test(w)) {
re = /.$/;
w = w.replace(re, '');
}
if (firstch == 'y') {
w = firstch.toLowerCase() + w.substring(1);
}
return w;
}
//# sourceMappingURL=english-stemmer.js.map