| 19 | * Porter Stemmer |
| 20 | */ |
| 21 | var Stemmer = function() { |
| 22 | |
| 23 | var step2list = { |
| 24 | ational: 'ate', |
| 25 | tional: 'tion', |
| 26 | enci: 'ence', |
| 27 | anci: 'ance', |
| 28 | izer: 'ize', |
| 29 | bli: 'ble', |
| 30 | alli: 'al', |
| 31 | entli: 'ent', |
| 32 | eli: 'e', |
| 33 | ousli: 'ous', |
| 34 | ization: 'ize', |
| 35 | ation: 'ate', |
| 36 | ator: 'ate', |
| 37 | alism: 'al', |
| 38 | iveness: 'ive', |
| 39 | fulness: 'ful', |
| 40 | ousness: 'ous', |
| 41 | aliti: 'al', |
| 42 | iviti: 'ive', |
| 43 | biliti: 'ble', |
| 44 | logi: 'log' |
| 45 | }; |
| 46 | |
| 47 | var step3list = { |
| 48 | icate: 'ic', |
| 49 | ative: '', |
| 50 | alize: 'al', |
| 51 | iciti: 'ic', |
| 52 | ical: 'ic', |
| 53 | ful: '', |
| 54 | ness: '' |
| 55 | }; |
| 56 | |
| 57 | var c = "[^aeiou]"; // consonant |
| 58 | var v = "[aeiouy]"; // vowel |
| 59 | var C = c + "[^aeiouy]*"; // consonant sequence |
| 60 | var V = v + "[aeiou]*"; // vowel sequence |
| 61 | |
| 62 | var mgr0 = "^(" + C + ")?" + V + C; // [C]VC... is m>0 |
| 63 | var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$"; // [C]VC[V] is m=1 |
| 64 | var mgr1 = "^(" + C + ")?" + V + C + V + C; // [C]VCVC... is m>1 |
| 65 | var s_v = "^(" + C + ")?" + v; // vowel in stem |
| 66 | |
| 67 | this.stemWord = function (w) { |
| 68 | var stem; |
| 69 | var suffix; |
| 70 | var firstch; |
| 71 | var origword = w; |
| 72 | |
| 73 | if (w.length < 3) |
| 74 | return w; |
| 75 | |
| 76 | var re; |
| 77 | var re2; |
| 78 | var re3; |