PageSourceSearch

https://pyodide.org/en/stable/_static/language_data.js

js pyodide.org collected 2026-09-24 15:21:05 UTC 4,598 bytes, 192 lines download raw bytes

1/*
2 * This script contains the language-specific data used by searchtools.js,
3 * namely the list of stopwords, stemmer, scorer and splitter.
4 */
5
6var 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"];
7
8
9/* Non-minified version is copied as a separate JS file, if available */
10
11/**
12 * Porter Stemmer
13 */
14var Stemmer = function() {
15
16  var step2list = {
17    ational: 'ate',
18    tional: 'tion',
19    enci: 'ence',
20    anci: 'ance',
21    izer: 'ize',
22    bli: 'ble',
23    alli: 'al',
24    entli: 'ent',
25    eli: 'e',
26    ousli: 'ous',
27    ization: 'ize',
28    ation: 'ate',
29    ator: 'ate',
30    alism: 'al',
31    iveness: 'ive',
32    fulness: 'ful',
33    ousness: 'ous',
34    aliti: 'al',
35    iviti: 'ive',
36    biliti: 'ble',
37    logi: 'log'
38  };
39
40  var step3list = {
41    icate: 'ic',
42    ative: '',
43    alize: 'al',
44    iciti: 'ic',
45    ical: 'ic',
46    ful: '',
47    ness: ''
48  };
49
50  var c = "[^aeiou]";          // consonant
51  var v = "[aeiouy]";          // vowel
52  var C = c + "[^aeiouy]*";    // consonant sequence
53  var V = v + "[aeiou]*";      // vowel sequence
54
55  var mgr0 = "^(" + C + ")?" + V + C;                      // [C]VC... is m>0
56  var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$";    // [C]VC[V] is m=1
57  var mgr1 = "^(" + C + ")?" + V + C + V + C;              // [C]VCVC... is m>1
58  var s_v   = "^(" + C + ")?" + v;                         // vowel in stem
59
60  this.stemWord = function (w) {
61    var stem;
62    var suffix;
63    var firstch;
64    var origword = w;
65
66    if (w.length < 3)
67      return w;
68
69    var re;
70    var re2;
71    var re3;
72    var re4;
73
74    firstch = w.substr(0,1);
75    if (firstch == "y")
76      w = firstch.toUpperCase() + w.substr(1);
77
78    // Step 1a
79    re = /^(.+?)(ss|i)es$/;
80    re2 = /^(.+?)([^s])s$/;
81
82    if (re.test(w))
83      w = w.replace(re,"$1$2");
84    else if (re2.test(w))
85      w = w.replace(re2,"$1$2");
86
87    // Step 1b
88    re = /^(.+?)eed$/;
89    re2 = /^(.+?)(ed|ing)$/;
90    if (re.test(w)) {
91      var fp = re.exec(w);
92      re = new RegExp(mgr0);
93      if (re.test(fp[1])) {
94        re = /.$/;
95        w = w.replace(re,"");
96      }
97    }
98    else if (re2.test(w)) {
99      var fp = re2.exec(w);
100      stem = fp[1];
101      re2 = new RegExp(s_v);
102      if (re2.test(stem)) {
103        w = stem;
104        re2 = /(at|bl|iz)$/;
105        re3 = new RegExp("([^aeiouylsz])\\1$");
106        re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
107        if (re2.test(w))
108          w = w + "e";
109        else if (re3.test(w)) {
110          re = /.$/;
111          w = w.replace(re,"");
112        }
113        else if (re4.test(w))
114          w = w + "e";
115      }
116    }
117
118    // Step 1c
119    re = /^(.+?)y$/;
120    if (re.test(w)) {
121      var fp = re.exec(w);
122      stem = fp[1];
123      re = new RegExp(s_v);
124      if (re.test(stem))
125        w = stem + "i";
126    }
127
128    // Step 2
129    re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
130    if (re.test(w)) {
131      var fp = re.exec(w);
132      stem = fp[1];
133      suffix = fp[2];
134      re = new RegExp(mgr0);
135      if (re.test(stem))
136        w = stem + step2list[suffix];
137    }
138
139    // Step 3
140    re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
141    if (re.test(w)) {
142      var fp = re.exec(w);
143      stem = fp[1];
144      suffix = fp[2];
145      re = new RegExp(mgr0);
146      if (re.test(stem))
147        w = stem + step3list[suffix];
148    }
149
150    // Step 4
151    re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
152    re2 = /^(.+?)(s|t)(ion)$/;
153    if (re.test(w)) {
154      var fp = re.exec(w);
155      stem = fp[1];
156      re = new RegExp(mgr1);
157      if (re.test(stem))
158        w = stem;
159    }
160    else if (re2.test(w)) {
161      var fp = re2.exec(w);
162      stem = fp[1] + fp[2];
163      re2 = new RegExp(mgr1);
164      if (re2.test(stem))
165        w = stem;
166    }
167
168    // Step 5
169    re = /^(.+?)e$/;
170    if (re.test(w)) {
171      var fp = re.exec(w);
172      stem = fp[1];
173      re = new RegExp(mgr1);
174      re2 = new RegExp(meq1);
175      re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
176      if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
177        w = stem;
178    }
179    re = /ll$/;
180    re2 = new RegExp(mgr1);
181    if (re.test(w) && re2.test(w)) {
182      re = /.$/;
183      w = w.replace(re,"");
184    }
185
186    // and turn initial Y back to y
187    if (firstch == "y")
188      w = firstch.toLowerCase() + w.substr(1);
189    return w;
190  }
191}
192

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.