* It implements the stemming algorithm defined by a snowball script.
*/
-public class frenchStemmer extends com.nexwave.stemmer.snowball.SnowballStemmer {
+public class FrenchStemmer extends com.nexwave.stemmer.snowball.SnowballStemmer {
private static final long serialVersionUID = 1L;
- private final static frenchStemmer methodObject = new frenchStemmer ();
+ private final static FrenchStemmer METHOD_OBJECT = new FrenchStemmer();
private final static Among a_0[] = {
- new Among ( "col", -1, -1, "", methodObject ),
- new Among ( "par", -1, -1, "", methodObject ),
- new Among ( "tap", -1, -1, "", methodObject )
+ new Among ( "col", -1, -1, "", METHOD_OBJECT),
+ new Among ( "par", -1, -1, "", METHOD_OBJECT),
+ new Among ( "tap", -1, -1, "", METHOD_OBJECT)
};
private final static Among a_1[] = {
- new Among ( "", -1, 4, "", methodObject ),
- new Among ( "I", 0, 1, "", methodObject ),
- new Among ( "U", 0, 2, "", methodObject ),
- new Among ( "Y", 0, 3, "", methodObject )
+ new Among ( "", -1, 4, "", METHOD_OBJECT),
+ new Among ( "I", 0, 1, "", METHOD_OBJECT),
+ new Among ( "U", 0, 2, "", METHOD_OBJECT),
+ new Among ( "Y", 0, 3, "", METHOD_OBJECT)
};
private final static Among a_2[] = {
- new Among ( "iqU", -1, 3, "", methodObject ),
- new Among ( "abl", -1, 3, "", methodObject ),
- new Among ( "I\u00E8r", -1, 4, "", methodObject ),
- new Among ( "i\u00E8r", -1, 4, "", methodObject ),
- new Among ( "eus", -1, 2, "", methodObject ),
- new Among ( "iv", -1, 1, "", methodObject )
+ new Among ( "iqU", -1, 3, "", METHOD_OBJECT),
+ new Among ( "abl", -1, 3, "", METHOD_OBJECT),
+ new Among ( "I\u00E8r", -1, 4, "", METHOD_OBJECT),
+ new Among ( "i\u00E8r", -1, 4, "", METHOD_OBJECT),
+ new Among ( "eus", -1, 2, "", METHOD_OBJECT),
+ new Among ( "iv", -1, 1, "", METHOD_OBJECT)
};
private final static Among a_3[] = {
- new Among ( "ic", -1, 2, "", methodObject ),
- new Among ( "abil", -1, 1, "", methodObject ),
- new Among ( "iv", -1, 3, "", methodObject )
+ new Among ( "ic", -1, 2, "", METHOD_OBJECT),
+ new Among ( "abil", -1, 1, "", METHOD_OBJECT),
+ new Among ( "iv", -1, 3, "", METHOD_OBJECT)
};
private final static Among a_4[] = {
- new Among ( "iqUe", -1, 1, "", methodObject ),
- new Among ( "atrice", -1, 2, "", methodObject ),
- new Among ( "ance", -1, 1, "", methodObject ),
- new Among ( "ence", -1, 5, "", methodObject ),
- new Among ( "logie", -1, 3, "", methodObject ),
- new Among ( "able", -1, 1, "", methodObject ),
- new Among ( "isme", -1, 1, "", methodObject ),
- new Among ( "euse", -1, 11, "", methodObject ),
- new Among ( "iste", -1, 1, "", methodObject ),
- new Among ( "ive", -1, 8, "", methodObject ),
- new Among ( "if", -1, 8, "", methodObject ),
- new Among ( "usion", -1, 4, "", methodObject ),
- new Among ( "ation", -1, 2, "", methodObject ),
- new Among ( "ution", -1, 4, "", methodObject ),
- new Among ( "ateur", -1, 2, "", methodObject ),
- new Among ( "iqUes", -1, 1, "", methodObject ),
- new Among ( "atrices", -1, 2, "", methodObject ),
- new Among ( "ances", -1, 1, "", methodObject ),
- new Among ( "ences", -1, 5, "", methodObject ),
- new Among ( "logies", -1, 3, "", methodObject ),
- new Among ( "ables", -1, 1, "", methodObject ),
- new Among ( "ismes", -1, 1, "", methodObject ),
- new Among ( "euses", -1, 11, "", methodObject ),
- new Among ( "istes", -1, 1, "", methodObject ),
- new Among ( "ives", -1, 8, "", methodObject ),
- new Among ( "ifs", -1, 8, "", methodObject ),
- new Among ( "usions", -1, 4, "", methodObject ),
- new Among ( "ations", -1, 2, "", methodObject ),
- new Among ( "utions", -1, 4, "", methodObject ),
- new Among ( "ateurs", -1, 2, "", methodObject ),
- new Among ( "ments", -1, 15, "", methodObject ),
- new Among ( "ements", 30, 6, "", methodObject ),
- new Among ( "issements", 31, 12, "", methodObject ),
- new Among ( "it\u00E9s", -1, 7, "", methodObject ),
- new Among ( "ment", -1, 15, "", methodObject ),
- new Among ( "ement", 34, 6, "", methodObject ),
- new Among ( "issement", 35, 12, "", methodObject ),
- new Among ( "amment", 34, 13, "", methodObject ),
- new Among ( "emment", 34, 14, "", methodObject ),
- new Among ( "aux", -1, 10, "", methodObject ),
- new Among ( "eaux", 39, 9, "", methodObject ),
- new Among ( "eux", -1, 1, "", methodObject ),
- new Among ( "it\u00E9", -1, 7, "", methodObject )
+ new Among ( "iqUe", -1, 1, "", METHOD_OBJECT),
+ new Among ( "atrice", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ance", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ence", -1, 5, "", METHOD_OBJECT),
+ new Among ( "logie", -1, 3, "", METHOD_OBJECT),
+ new Among ( "able", -1, 1, "", METHOD_OBJECT),
+ new Among ( "isme", -1, 1, "", METHOD_OBJECT),
+ new Among ( "euse", -1, 11, "", METHOD_OBJECT),
+ new Among ( "iste", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ive", -1, 8, "", METHOD_OBJECT),
+ new Among ( "if", -1, 8, "", METHOD_OBJECT),
+ new Among ( "usion", -1, 4, "", METHOD_OBJECT),
+ new Among ( "ation", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ution", -1, 4, "", METHOD_OBJECT),
+ new Among ( "ateur", -1, 2, "", METHOD_OBJECT),
+ new Among ( "iqUes", -1, 1, "", METHOD_OBJECT),
+ new Among ( "atrices", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ances", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ences", -1, 5, "", METHOD_OBJECT),
+ new Among ( "logies", -1, 3, "", METHOD_OBJECT),
+ new Among ( "ables", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ismes", -1, 1, "", METHOD_OBJECT),
+ new Among ( "euses", -1, 11, "", METHOD_OBJECT),
+ new Among ( "istes", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ives", -1, 8, "", METHOD_OBJECT),
+ new Among ( "ifs", -1, 8, "", METHOD_OBJECT),
+ new Among ( "usions", -1, 4, "", METHOD_OBJECT),
+ new Among ( "ations", -1, 2, "", METHOD_OBJECT),
+ new Among ( "utions", -1, 4, "", METHOD_OBJECT),
+ new Among ( "ateurs", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ments", -1, 15, "", METHOD_OBJECT),
+ new Among ( "ements", 30, 6, "", METHOD_OBJECT),
+ new Among ( "issements", 31, 12, "", METHOD_OBJECT),
+ new Among ( "it\u00E9s", -1, 7, "", METHOD_OBJECT),
+ new Among ( "ment", -1, 15, "", METHOD_OBJECT),
+ new Among ( "ement", 34, 6, "", METHOD_OBJECT),
+ new Among ( "issement", 35, 12, "", METHOD_OBJECT),
+ new Among ( "amment", 34, 13, "", METHOD_OBJECT),
+ new Among ( "emment", 34, 14, "", METHOD_OBJECT),
+ new Among ( "aux", -1, 10, "", METHOD_OBJECT),
+ new Among ( "eaux", 39, 9, "", METHOD_OBJECT),
+ new Among ( "eux", -1, 1, "", METHOD_OBJECT),
+ new Among ( "it\u00E9", -1, 7, "", METHOD_OBJECT)
};
private final static Among a_5[] = {
- new Among ( "ira", -1, 1, "", methodObject ),
- new Among ( "ie", -1, 1, "", methodObject ),
- new Among ( "isse", -1, 1, "", methodObject ),
- new Among ( "issante", -1, 1, "", methodObject ),
- new Among ( "i", -1, 1, "", methodObject ),
- new Among ( "irai", 4, 1, "", methodObject ),
- new Among ( "ir", -1, 1, "", methodObject ),
- new Among ( "iras", -1, 1, "", methodObject ),
- new Among ( "ies", -1, 1, "", methodObject ),
- new Among ( "\u00EEmes", -1, 1, "", methodObject ),
- new Among ( "isses", -1, 1, "", methodObject ),
- new Among ( "issantes", -1, 1, "", methodObject ),
- new Among ( "\u00EEtes", -1, 1, "", methodObject ),
- new Among ( "is", -1, 1, "", methodObject ),
- new Among ( "irais", 13, 1, "", methodObject ),
- new Among ( "issais", 13, 1, "", methodObject ),
- new Among ( "irions", -1, 1, "", methodObject ),
- new Among ( "issions", -1, 1, "", methodObject ),
- new Among ( "irons", -1, 1, "", methodObject ),
- new Among ( "issons", -1, 1, "", methodObject ),
- new Among ( "issants", -1, 1, "", methodObject ),
- new Among ( "it", -1, 1, "", methodObject ),
- new Among ( "irait", 21, 1, "", methodObject ),
- new Among ( "issait", 21, 1, "", methodObject ),
- new Among ( "issant", -1, 1, "", methodObject ),
- new Among ( "iraIent", -1, 1, "", methodObject ),
- new Among ( "issaIent", -1, 1, "", methodObject ),
- new Among ( "irent", -1, 1, "", methodObject ),
- new Among ( "issent", -1, 1, "", methodObject ),
- new Among ( "iront", -1, 1, "", methodObject ),
- new Among ( "\u00EEt", -1, 1, "", methodObject ),
- new Among ( "iriez", -1, 1, "", methodObject ),
- new Among ( "issiez", -1, 1, "", methodObject ),
- new Among ( "irez", -1, 1, "", methodObject ),
- new Among ( "issez", -1, 1, "", methodObject )
+ new Among ( "ira", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ie", -1, 1, "", METHOD_OBJECT),
+ new Among ( "isse", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issante", -1, 1, "", METHOD_OBJECT),
+ new Among ( "i", -1, 1, "", METHOD_OBJECT),
+ new Among ( "irai", 4, 1, "", METHOD_OBJECT),
+ new Among ( "ir", -1, 1, "", METHOD_OBJECT),
+ new Among ( "iras", -1, 1, "", METHOD_OBJECT),
+ new Among ( "ies", -1, 1, "", METHOD_OBJECT),
+ new Among ( "\u00EEmes", -1, 1, "", METHOD_OBJECT),
+ new Among ( "isses", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issantes", -1, 1, "", METHOD_OBJECT),
+ new Among ( "\u00EEtes", -1, 1, "", METHOD_OBJECT),
+ new Among ( "is", -1, 1, "", METHOD_OBJECT),
+ new Among ( "irais", 13, 1, "", METHOD_OBJECT),
+ new Among ( "issais", 13, 1, "", METHOD_OBJECT),
+ new Among ( "irions", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issions", -1, 1, "", METHOD_OBJECT),
+ new Among ( "irons", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issons", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issants", -1, 1, "", METHOD_OBJECT),
+ new Among ( "it", -1, 1, "", METHOD_OBJECT),
+ new Among ( "irait", 21, 1, "", METHOD_OBJECT),
+ new Among ( "issait", 21, 1, "", METHOD_OBJECT),
+ new Among ( "issant", -1, 1, "", METHOD_OBJECT),
+ new Among ( "iraIent", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issaIent", -1, 1, "", METHOD_OBJECT),
+ new Among ( "irent", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issent", -1, 1, "", METHOD_OBJECT),
+ new Among ( "iront", -1, 1, "", METHOD_OBJECT),
+ new Among ( "\u00EEt", -1, 1, "", METHOD_OBJECT),
+ new Among ( "iriez", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issiez", -1, 1, "", METHOD_OBJECT),
+ new Among ( "irez", -1, 1, "", METHOD_OBJECT),
+ new Among ( "issez", -1, 1, "", METHOD_OBJECT)
};
private final static Among a_6[] = {
- new Among ( "a", -1, 3, "", methodObject ),
- new Among ( "era", 0, 2, "", methodObject ),
- new Among ( "asse", -1, 3, "", methodObject ),
- new Among ( "ante", -1, 3, "", methodObject ),
- new Among ( "\u00E9e", -1, 2, "", methodObject ),
- new Among ( "ai", -1, 3, "", methodObject ),
- new Among ( "erai", 5, 2, "", methodObject ),
- new Among ( "er", -1, 2, "", methodObject ),
- new Among ( "as", -1, 3, "", methodObject ),
- new Among ( "eras", 8, 2, "", methodObject ),
- new Among ( "\u00E2mes", -1, 3, "", methodObject ),
- new Among ( "asses", -1, 3, "", methodObject ),
- new Among ( "antes", -1, 3, "", methodObject ),
- new Among ( "\u00E2tes", -1, 3, "", methodObject ),
- new Among ( "\u00E9es", -1, 2, "", methodObject ),
- new Among ( "ais", -1, 3, "", methodObject ),
- new Among ( "erais", 15, 2, "", methodObject ),
- new Among ( "ions", -1, 1, "", methodObject ),
- new Among ( "erions", 17, 2, "", methodObject ),
- new Among ( "assions", 17, 3, "", methodObject ),
- new Among ( "erons", -1, 2, "", methodObject ),
- new Among ( "ants", -1, 3, "", methodObject ),
- new Among ( "\u00E9s", -1, 2, "", methodObject ),
- new Among ( "ait", -1, 3, "", methodObject ),
- new Among ( "erait", 23, 2, "", methodObject ),
- new Among ( "ant", -1, 3, "", methodObject ),
- new Among ( "aIent", -1, 3, "", methodObject ),
- new Among ( "eraIent", 26, 2, "", methodObject ),
- new Among ( "\u00E8rent", -1, 2, "", methodObject ),
- new Among ( "assent", -1, 3, "", methodObject ),
- new Among ( "eront", -1, 2, "", methodObject ),
- new Among ( "\u00E2t", -1, 3, "", methodObject ),
- new Among ( "ez", -1, 2, "", methodObject ),
- new Among ( "iez", 32, 2, "", methodObject ),
- new Among ( "eriez", 33, 2, "", methodObject ),
- new Among ( "assiez", 33, 3, "", methodObject ),
- new Among ( "erez", 32, 2, "", methodObject ),
- new Among ( "\u00E9", -1, 2, "", methodObject )
+ new Among ( "a", -1, 3, "", METHOD_OBJECT),
+ new Among ( "era", 0, 2, "", METHOD_OBJECT),
+ new Among ( "asse", -1, 3, "", METHOD_OBJECT),
+ new Among ( "ante", -1, 3, "", METHOD_OBJECT),
+ new Among ( "\u00E9e", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ai", -1, 3, "", METHOD_OBJECT),
+ new Among ( "erai", 5, 2, "", METHOD_OBJECT),
+ new Among ( "er", -1, 2, "", METHOD_OBJECT),
+ new Among ( "as", -1, 3, "", METHOD_OBJECT),
+ new Among ( "eras", 8, 2, "", METHOD_OBJECT),
+ new Among ( "\u00E2mes", -1, 3, "", METHOD_OBJECT),
+ new Among ( "asses", -1, 3, "", METHOD_OBJECT),
+ new Among ( "antes", -1, 3, "", METHOD_OBJECT),
+ new Among ( "\u00E2tes", -1, 3, "", METHOD_OBJECT),
+ new Among ( "\u00E9es", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ais", -1, 3, "", METHOD_OBJECT),
+ new Among ( "erais", 15, 2, "", METHOD_OBJECT),
+ new Among ( "ions", -1, 1, "", METHOD_OBJECT),
+ new Among ( "erions", 17, 2, "", METHOD_OBJECT),
+ new Among ( "assions", 17, 3, "", METHOD_OBJECT),
+ new Among ( "erons", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ants", -1, 3, "", METHOD_OBJECT),
+ new Among ( "\u00E9s", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ait", -1, 3, "", METHOD_OBJECT),
+ new Among ( "erait", 23, 2, "", METHOD_OBJECT),
+ new Among ( "ant", -1, 3, "", METHOD_OBJECT),
+ new Among ( "aIent", -1, 3, "", METHOD_OBJECT),
+ new Among ( "eraIent", 26, 2, "", METHOD_OBJECT),
+ new Among ( "\u00E8rent", -1, 2, "", METHOD_OBJECT),
+ new Among ( "assent", -1, 3, "", METHOD_OBJECT),
+ new Among ( "eront", -1, 2, "", METHOD_OBJECT),
+ new Among ( "\u00E2t", -1, 3, "", METHOD_OBJECT),
+ new Among ( "ez", -1, 2, "", METHOD_OBJECT),
+ new Among ( "iez", 32, 2, "", METHOD_OBJECT),
+ new Among ( "eriez", 33, 2, "", METHOD_OBJECT),
+ new Among ( "assiez", 33, 3, "", METHOD_OBJECT),
+ new Among ( "erez", 32, 2, "", METHOD_OBJECT),
+ new Among ( "\u00E9", -1, 2, "", METHOD_OBJECT)
};
private final static Among a_7[] = {
- new Among ( "e", -1, 3, "", methodObject ),
- new Among ( "I\u00E8re", 0, 2, "", methodObject ),
- new Among ( "i\u00E8re", 0, 2, "", methodObject ),
- new Among ( "ion", -1, 1, "", methodObject ),
- new Among ( "Ier", -1, 2, "", methodObject ),
- new Among ( "ier", -1, 2, "", methodObject ),
- new Among ( "\u00EB", -1, 4, "", methodObject )
+ new Among ( "e", -1, 3, "", METHOD_OBJECT),
+ new Among ( "I\u00E8re", 0, 2, "", METHOD_OBJECT),
+ new Among ( "i\u00E8re", 0, 2, "", METHOD_OBJECT),
+ new Among ( "ion", -1, 1, "", METHOD_OBJECT),
+ new Among ( "Ier", -1, 2, "", METHOD_OBJECT),
+ new Among ( "ier", -1, 2, "", METHOD_OBJECT),
+ new Among ( "\u00EB", -1, 4, "", METHOD_OBJECT)
};
private final static Among a_8[] = {
- new Among ( "ell", -1, -1, "", methodObject ),
- new Among ( "eill", -1, -1, "", methodObject ),
- new Among ( "enn", -1, -1, "", methodObject ),
- new Among ( "onn", -1, -1, "", methodObject ),
- new Among ( "ett", -1, -1, "", methodObject )
+ new Among ( "ell", -1, -1, "", METHOD_OBJECT),
+ new Among ( "eill", -1, -1, "", METHOD_OBJECT),
+ new Among ( "enn", -1, -1, "", METHOD_OBJECT),
+ new Among ( "onn", -1, -1, "", METHOD_OBJECT),
+ new Among ( "ett", -1, -1, "", METHOD_OBJECT)
};
private static final char g_v[] = {17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 130, 103, 8, 5 };
private int I_p1;
private int I_pV;
- private void copy_from(frenchStemmer other) {
+ private void copy_from(FrenchStemmer other) {
I_p2 = other.I_p2;
I_p1 = other.I_p1;
I_pV = other.I_pV;
}
public boolean equals( Object o ) {
- return o instanceof frenchStemmer;
+ return o instanceof FrenchStemmer;
}
public int hashCode() {
- return frenchStemmer.class.getName().hashCode();
+ return FrenchStemmer.class.getName().hashCode();
}
--- /dev/null
+/*
+ * Author: Kasun Gajasinghe
+ * E-Mail: kasunbg@gmail.com
+ * Date: 09.08.2010
+ *
+ * usage: stemmer(word);
+ * ex: var stem = stemmer(foobar);
+ * Implementation of the stemming algorithm from http://snowball.tartarus.org/algorithms/french/stemmer.html
+ *
+ * LICENSE:
+ *
+ * Copyright (c) 2010, Kasun Gajasinghe. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without modification,
+ * are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ *
+ * THIS SOFTWARE IS PROVIDED BY KASUN GAJASINGHE ''AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL KASUN GAJASINGHE BE LIABLE FOR ANY DIRECT,
+ * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+var stemmer = function(word){
+// Letters in French include the following accented forms,
+// â à ç ë é ê è ï î ô û ù
+// The following letters are vowels:
+// a e i o u y â à ë é ê è ï î ô û ù
+
+ word = word.toLowerCase();
+ var oriWord = word;
+ word = word.replace(/qu/g, 'qU'); //have to perform first, as after the operation, capital U is not treated as a vowel
+ word = word.replace(/([aeiouyâàëéêèïîôûù])u([aeiouyâàëéêèïîôûù])/g, '$1U$2');
+ word = word.replace(/([aeiouyâàëéêèïîôûù])i([aeiouyâàëéêèïîôûù])/g, '$1I$2');
+ word = word.replace(/([aeiouyâàëéêèïîôûù])y/g, '$1Y');
+ word = word.replace(/y([aeiouyâàëéêèïîôûù])/g, 'Y$1');
+
+ var rv='';
+ var rvIndex = -1;
+ if(word.search(/^(par|col|tap)/) != -1 || word.search(/^[aeiouyâàëéêèïîôûù]{2}/) != -1){
+ rv = word.substring(3);
+ rvIndex = 3;
+ } else {
+ rvIndex = word.substring(1).search(/[aeiouyâàëéêèïîôûù]/);
+ if(rvIndex != -1){
+ rvIndex +=2; //+2 is to supplement the substring(1) used to find rvIndex
+ rv = word.substring(rvIndex);
+ } else {
+ rvIndex = word.length;
+ }
+ }
+
+// R1 is the region after the first non-vowel following a vowel, or the end of the word if there is no such non-vowel.
+// R2 is the region after the first non-vowel following a vowel in R1, or the end of the word if there is no such non-vowel
+ var r1Index = word.search(/[aeiouyâàëéêèïîôûù][^aeiouyâàëéêèïîôûù]/);
+ var r1 = '';
+ if (r1Index != -1) {
+ r1Index += 2;
+ r1 = word.substring(r1Index);
+ } else {
+ r1Index = word.length;
+ }
+
+ var r2Index = -1;
+ var r2 = '';
+ if (r1Index != -1) {
+ r2Index = r1.search(/[aeiouyâàëéêèïîôûù][^aeiouyâàëéêèïîôûù]/);
+ if (r2Index != -1) {
+ r2Index += 2;
+ r2 = r1.substring(r2Index);
+ r2Index += r1Index;
+ } else {
+ r2 = '';
+ r2Index = word.length;
+ }
+ }
+ if (r1Index != -1 && r1Index < 3) {
+ r1Index = 3;
+ r1 = word.substring(r1Index);
+ }
+
+ /*
+ Step 1: Standard suffix removal
+ */
+ var a1Index = word.search(/(ance|iqUe|isme|able|iste|eux|ances|iqUes|ismes|ables|istes)$/);
+ var a2Index = word.search(/(atrice|ateur|ation|atrices|ateurs|ations)$/);
+ var a3Index = word.search(/(logie|logies)$/);
+ var a4Index = word.search(/(usion|ution|usions|utions)$/);
+ var a5Index = word.search(/(ence|ences)$/);
+ var a6Index = word.search(/(ement|ements)$/);
+ var a7Index = word.search(/(ité|ités)$/);
+ var a8Index = word.search(/(if|ive|ifs|ives)$/);
+ var a9Index = word.search(/(eaux)$/);
+ var a10Index = word.search(/(aux)$/);
+ var a11Index = word.search(/(euse|euses)$/);
+ var a12Index = word.search(/[^aeiouyâàëéêèïîôûù](issement|issements)$/);
+ var a13Index = word.search(/(amment)$/);
+ var a14Index = word.search(/(emment)$/);
+ var a15Index = word.search(/[aeiouyâàëéêèïîôûù](ment|ments)$/);
+
+ if(a1Index != -1 && a1Index >= r2Index){
+ word = word.substring(0,a1Index);
+ } else if(a2Index != -1 && a2Index >= r2Index){
+ word = word.substring(0,a2Index);
+ var a2Index2 = word.search(/(ic)$/);
+ if(a2Index2 != -1 && a2Index2 >= r2Index){
+ word = word.substring(0, a2Index2); //if preceded by ic, delete if in R2,
+ } else { //else replace by iqU
+ word = word.replace(/(ic)$/,'iqU');
+ }
+ } else if(a3Index != -1 && a3Index >= r2Index){
+ word = word.replace(/(logie|logies)$/,'log'); //replace with log if in R2
+ } else if(a4Index != -1 && a4Index >= r2Index){
+ word = word.replace(/(usion|ution|usions|utions)$/,'u'); //replace with u if in R2
+ } else if(a5Index != -1 && a5Index >= r2Index){
+ word = word.replace(/(ence|ences)$/,'ent'); //replace with ent if in R2
+ } else if(a6Index != -1 && a6Index >= rvIndex){
+ word = word.substring(0,a6Index);
+ if(word.search(/(iv)$/) >= r2Index){
+ word = word.replace(/(iv)$/, '');
+ if(word.search(/(at)$/) >= r2Index){
+ word = word.replace(/(at)$/, '');
+ }
+ } else if(word.search(/(eus)$/) != -1){
+ var a6Index2 = word.search(/(eus)$/);
+ if(a6Index2 >=r2Index){
+ word = word.substring(0, a6Index2);
+ } else if(a6Index2 >= r1Index){
+ word = word.substring(0,a6Index2)+"eux";
+ }
+ } else if(word.search(/(abl|iqU)$/) >= r2Index){
+ word = word.replace(/(abl|iqU)$/,''); //if preceded by abl or iqU, delete if in R2,
+ } else if(word.search(/(ièr|Ièr)$/) >= rvIndex){
+ word = word.replace(/(ièr|Ièr)$/,'i'); //if preceded by abl or iqU, delete if in R2,
+ }
+ } else if(a7Index != -1 && a7Index >= r2Index){
+ word = word.substring(0,a7Index); //delete if in R2
+ if(word.search(/(abil)$/) != -1){ //if preceded by abil, delete if in R2, else replace by abl, otherwise,
+ var a7Index2 = word.search(/(abil)$/);
+ if(a7Index2 >=r2Index){
+ word = word.substring(0, a7Index2);
+ } else {
+ word = word.substring(0,a7Index2)+"abl";
+ }
+ } else if(word.search(/(ic)$/) != -1){
+ var a7Index3 = word.search(/(ic)$/);
+ if(a7Index3 != -1 && a7Index3 >= r2Index){
+ word = word.substring(0, a7Index3); //if preceded by ic, delete if in R2,
+ } else { //else replace by iqU
+ word = word.replace(/(ic)$/,'iqU');
+ }
+ } else if(word.search(/(iv)$/) != r2Index){
+ word = word.replace(/(iv)$/,'');
+ }
+ } else if(a8Index != -1 && a8Index >= r2Index){
+ word = word.substring(0,a8Index);
+ if(word.search(/(at)$/) >= r2Index){
+ word = word.replace(/(at)$/, '');
+ if(word.search(/(ic)$/) >= r2Index){
+ word = word.replace(/(ic)$/, '');
+ } else { word = word.replace(/(ic)$/, 'iqU'); }
+ }
+ } else if(a9Index != -1){ word = word.replace(/(eaux)/,'eau')
+ } else if(a10Index >= r1Index){ word = word.replace(/(aux)/,'al')
+ } else if(a11Index != -1 ){
+ var a11Index2 = word.search(/(euse|euses)$/);
+ if(a11Index2 >=r2Index){
+ word = word.substring(0, a11Index2);
+ } else if(a11Index2 >= r1Index){
+ word = word.substring(0, a11Index2)+"eux";
+ }
+ } else if(a12Index!=-1 && a12Index>=r1Index){
+ word = word.substring(0,a12Index+1); //+1- amendment to non-vowel
+ } else if(a13Index!=-1 && a13Index>=rvIndex){
+ word = word.replace(/(amment)$/,'ant');
+ } else if(a14Index!=-1 && a14Index>=rvIndex){
+ word = word.replace(/(emment)$/,'ent');
+ } else if(a15Index!=-1 && a15Index>=rvIndex){
+ word = word.substring(0,a15Index+1);
+ }
+
+ /* Step 2a: Verb suffixes beginning i*/
+ var wordStep1 = word;
+ var step2aDone = false;
+ if(oriWord == word.toLowerCase() || oriWord.search(/(amment|emment|ment|ments)$/) != -1){
+ step2aDone = true;
+ var b1Regex = /([^aeiouyâàëéêèïîôûù])(îmes|ît|îtes|i|ie|ies|ir|ira|irai|iraIent|irais|irait|iras|irent|irez|iriez|irions|irons|iront|is|issaIent|issais|issait|issant|issante|issantes|issants|isse|issent|isses|issez|issiez|issions|issons|it)$/i;
+ if(word.search(b1Regex) >= rvIndex){
+ word = word.replace(b1Regex,'$1');
+ }
+ }
+
+ /* Step 2b: Other verb suffixes*/
+ if (step2aDone && wordStep1 == word) {
+ if (word.search(/(ions)$/) >= r2Index) {
+ word = word.replace(/(ions)$/, '');
+ } else {
+ var b2Regex = /(é|ée|ées|és|èrent|er|era|erai|eraIent|erais|erait|eras|erez|eriez|erions|erons|eront|ez|iez)$/i;
+ if (word.search(b2Regex) >= rvIndex) {
+ word = word.replace(b2Regex, '');
+ } else {
+ var b3Regex = /e(âmes|ât|âtes|a|ai|aIent|ais|ait|ant|ante|antes|ants|as|asse|assent|asses|assiez|assions)$/i;
+ if (word.search(b3Regex) >= rvIndex) {
+ word = word.replace(b3Regex, '');
+ } else {
+ var b3Regex2 = /(âmes|ât|âtes|a|ai|aIent|ais|ait|ant|ante|antes|ants|as|asse|assent|asses|assiez|assions)$/i;
+ if (word.search(b3Regex2) >= rvIndex) {
+ word = word.replace(b3Regex2, '');
+ }
+ }
+ }
+ }
+ }
+
+ if(oriWord != word.toLowerCase()){
+ /* Step 3 */
+ var rep = '';
+ if(word.search(/Y$/) != -1) {
+ word = word.replace(/Y$/, 'i');
+ } else if(word.search(/ç$/) != -1){
+ word = word.replace(/ç$/, 'c');
+ }
+ } else {
+ /* Step 4 */
+ //If the word ends s, not preceded by a, i, o, u, è or s, delete it.
+ if (word.search(/([^aiouès])s$/) >= rvIndex) {
+ word = word.replace(/([^aiouès])s$/, '$1');
+ }
+ var e1Index = word.search(/ion$/);
+ if (e1Index >= r2Index && word.search(/[st]ion$/) >= rvIndex) {
+ word = word.substring(0, e1Index);
+ } else {
+ var e2Index = word.search(/(ier|ière|Ier|Ière)$/);
+ if (e2Index != -1 && e2Index >= rvIndex) {
+ word = word.substring(0, e2Index) + "i";
+ } else {
+ if (word.search(/e$/) >= rvIndex) {
+ word = word.replace(/e$/, ''); //delete last e
+ } else if (word.search(/guë$/) >= rvIndex) {
+ word = word.replace(/guë$/, 'gu');
+ }
+ }
+ }
+ }
+
+ /* Step 5: Undouble */
+ //word = word.replace(/(en|on|et|el|eil)(n|t|l)$/,'$1');
+ word = word.replace(/(en|on)(n)$/,'$1');
+ word = word.replace(/(ett)$/,'et');
+ word = word.replace(/(el|eil)(l)$/,'$1');
+
+ /* Step 6: Un-accent */
+ word = word.replace(/[éè]([^aeiouyâàëéêèïîôûù]+)$/,'e$1');
+ word = word.toLowerCase();
+ return word;
+};
+
+var eqOut = new Array();
+var noteqOut = new Array();
+var eqCount = 0;
+/*
+To test the stemming, create two arrays named "voc" and "COut" which are for vocabualary and the stemmed output.
+Then add the vocabulary strings and output strings. This method will generate the stemmed output for "voc" and will
+compare the output with COut.
+ (I used porter's voc and out files and did a regex to convert them to js objects. regex: /");\nvoc.push("/g . This
+ will add strings to voc array such that output would look like: voc.push("foobar"); ) drop me an email for any help.
+ */
+function testFr(){
+ var start = new Date().getTime(); //execution time
+ eqCount = 0;
+ eqOut = new Array();
+ noteqOut = new Array();
+ for(var k=0;k<voc.length;k++){
+ if(COut[k]==stemmer(voc[k])){
+ eqCount++;
+ eqOut.push("v: "+voc[k]+" c: "+COut[k]);
+ } else {
+ noteqOut.push(voc[k]+", c: "+COut[k]+" s:"+stemmer(voc[k]));
+ }
+ }
+ var end = new Date().getTime(); //execution time
+ var time = end-start;
+ alert("equal count= "+eqCount+" out of "+voc.length+" words. time= "+time+" ms");
+ //console.log("equal count= "+eqCount+" out of "+voc.length+" words. time= "+time+" ms");
+}
+
+
projects / docbook-dsssl / commitdiff
