123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200 |
- /*
- * language_data.js
- * ~~~~~~~~~~~~~~~~
- *
- * This script contains the language-specific data used by searchtools.js,
- * namely the list of stopwords, stemmer, scorer and splitter.
- *
- * :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
- * :license: BSD, see LICENSE for details.
- *
- */
- var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
- /* Non-minified version is copied as a separate JS file, is available */
- /**
- * Porter Stemmer
- */
- var Stemmer = function() {
- var 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'
- };
- var step3list = {
- icate: 'ic',
- ative: '',
- alize: 'al',
- iciti: 'ic',
- ical: 'ic',
- ful: '',
- ness: ''
- };
- var c = "[^aeiou]"; // consonant
- var v = "[aeiouy]"; // vowel
- var C = c + "[^aeiouy]*"; // consonant sequence
- var V = v + "[aeiou]*"; // vowel sequence
- var mgr0 = "^(" + C + ")?" + V + C; // [C]VC... is m>0
- var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$"; // [C]VC[V] is m=1
- var mgr1 = "^(" + C + ")?" + V + C + V + C; // [C]VCVC... is m>1
- var s_v = "^(" + C + ")?" + v; // vowel in stem
- this.stemWord = function (w) {
- var stem;
- var suffix;
- var firstch;
- var origword = w;
- if (w.length < 3)
- return w;
- var re;
- var re2;
- var re3;
- var re4;
- firstch = w.substr(0,1);
- if (firstch == "y")
- w = firstch.toUpperCase() + w.substr(1);
- // Step 1a
- re = /^(.+?)(ss|i)es$/;
- re2 = /^(.+?)([^s])s$/;
- if (re.test(w))
- w = w.replace(re,"$1$2");
- else if (re2.test(w))
- w = w.replace(re2,"$1$2");
- // Step 1b
- re = /^(.+?)eed$/;
- re2 = /^(.+?)(ed|ing)$/;
- if (re.test(w)) {
- var fp = re.exec(w);
- re = new RegExp(mgr0);
- if (re.test(fp[1])) {
- re = /.$/;
- w = w.replace(re,"");
- }
- }
- else if (re2.test(w)) {
- var 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";
- }
- }
- // Step 1c
- re = /^(.+?)y$/;
- if (re.test(w)) {
- var fp = re.exec(w);
- stem = fp[1];
- re = new RegExp(s_v);
- if (re.test(stem))
- w = stem + "i";
- }
- // Step 2
- re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
- if (re.test(w)) {
- var fp = re.exec(w);
- stem = fp[1];
- suffix = fp[2];
- re = new RegExp(mgr0);
- if (re.test(stem))
- w = stem + step2list[suffix];
- }
- // Step 3
- re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
- if (re.test(w)) {
- var fp = re.exec(w);
- stem = fp[1];
- suffix = fp[2];
- re = new RegExp(mgr0);
- if (re.test(stem))
- w = stem + step3list[suffix];
- }
- // Step 4
- re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
- re2 = /^(.+?)(s|t)(ion)$/;
- if (re.test(w)) {
- var fp = re.exec(w);
- stem = fp[1];
- re = new RegExp(mgr1);
- if (re.test(stem))
- w = stem;
- }
- else if (re2.test(w)) {
- var fp = re2.exec(w);
- stem = fp[1] + fp[2];
- re2 = new RegExp(mgr1);
- if (re2.test(stem))
- w = stem;
- }
- // Step 5
- re = /^(.+?)e$/;
- if (re.test(w)) {
- var fp = re.exec(w);
- stem = fp[1];
- re = new RegExp(mgr1);
- re2 = new RegExp(meq1);
- re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
- if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
- w = stem;
- }
- re = /ll$/;
- re2 = new RegExp(mgr1);
- if (re.test(w) && re2.test(w)) {
- re = /.$/;
- w = w.replace(re,"");
- }
- // and turn initial Y back to y
- if (firstch == "y")
- w = firstch.toLowerCase() + w.substr(1);
- return w;
- }
- }
|