natural 0.5.4 → 0.6.1

package/lib/natural/stemmers/porter_stemmer_es.js

@@ -1,221 +1,287 @@
 /*
-Copyright (c) 2012, David Przybilla, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+  Copyright (c) 2018, Domingo Martín Mancera
+
+  Permission is hereby granted, free of charge, to any person obtaining a copy
+  of this software and associated documentation files (the "Software"), to deal
+  in the Software without restriction, including without limitation the rights
+  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+  copies of the Software, and to permit persons to whom the Software is
+  furnished to do so, subject to the following conditions:
+
+  The above copyright notice and this permission notice shall be included in
+  all copies or substantial portions of the Software.
+
+  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+  THE SOFTWARE.
 */
 
+'use strict';
+
 var Stemmer = require('./stemmer_es');
 
-var PorterStemmer = new Stemmer();
-module.exports = PorterStemmer;
-
-
-function isVowel(letter){
-	return (letter == 'a' || letter == 'e' || letter == 'i' || letter == 'o' || letter == 'u' || letter == 'á' || letter == 'é' ||
-			letter == 'í' || letter == 'ó' || letter == 'ú');
-};
-
-function getNextVowelPos(token,start){
-	length=token.length
-			for (var i = start; i < length; i++)
-				if (isVowel(token[i])) return i;
-			return length;
-};
-
-function getNextConsonantPos(token,start){
-	length=token.length
-			for (var i = start; i < length; i++)
-				if (!isVowel(token[i])) return i;
-			return length;
-};
-
-
-function endsin(token, suffix) {
-	if (token.length < suffix.length) return false;
-	return (token.slice(-suffix.length) == suffix);
-};
-
-function endsinArr(token, suffixes) {
-	for(var i=0;i<suffixes.length;i++){
-		if (endsin(token, suffixes[i])) return suffixes[i];
-	}
-	return '';
-};
-
-function removeAccent(token) {
-	var str=token.replace(/á/gi,'a');
-	str=str.replace(/é/gi,'e');
-	str=str.replace(/í/gi,'i');
-	str=str.replace(/ó/gi,'o');
-	str=str.replace(/ú/gi,'u');
-	return str;
-};
-
-// perform full stemming algorithm on a single word
-PorterStemmer.stem = function(token) {
-	token = token.toLowerCase();
-
-	if (token.length<3){
-		return token;
-	}
-
-	var r1,r2,rv,len= token.length;
-	//looking for regions after vowels
-
-	for(var i=0; i< token.length-1 && r1==len;i++){
- 		if(isVowel(token[i]) && !isVowel(token[i+1]) ){
- 			r1=i+2;
- 		}
-
-	}
-
-	for(var i=r1; i< token.length-1 && r2==len;i++){
-		if(isVowel(token[i]) && !isVowel(token[i+1])){
-			r2=i+2;
+// Inherit from the utility class in stemmer_es
+class PorterStemmer extends Stemmer
+{
+    constructor() {
+      super();
+    }
+
+    isVowel(c)
+    {
+        var regex = /[aeiouáéíóú]/gi;
+
+        return regex.test(c);
+    }
+
+    nextVowelPosition(word, start = 0)
+    {
+        var length = word.length;
+
+        for(var position = start; position < length; position++){
+            if(this.isVowel(word[position])){
+                return position;
+            }
+        }
+
+        return length;
+    }
+
+    nextConsonantPosition(word, start = 0)
+    {
+        var length = word.length;
+
+        for(var position = start; position < length; position++){
+            if(!this.isVowel(word[position])){
+                return position;
+            }
+        }
+
+        return length;
+    }
+
+    endsIn(word, suffix)
+    {
+        if(word.length < suffix.length){
+            return false;
+        }
+
+        return (word.slice(-suffix.length) === suffix);
+    }
+
+    endsInArr(word, suffixes)
+    {
+        var matches = [];
+        for(var i in suffixes) {
+            if(this.endsIn(word, suffixes[i])){
+                matches.push(suffixes[i]);
+            }
+        }
+        var longest = matches.sort(function (a, b) {
+            return b.length - a.length;
+        })[0];
+
+        if(longest){
+            return longest
+        } else {
+            return '';
+        }
+    }
+
+    removeAccent(word)
+    {
+        var accentedVowels = ['á', 'é', 'í', 'ó', 'ú'];
+        var vowels = ['a', 'e', 'i', 'o', 'u'];
+
+        for(var i in accentedVowels){
+            word = word.replace(accentedVowels[i], vowels[i]);
+        }
+
+        return word;
+    }
+
+    stem(word)
+    {
+        var length = word.length;
+
+        word.toLowerCase();
+
+        if(length < 2){
+            return this.removeAccent(word);
+        }
+
+        var r1, r2, rv;
+        r1 = length;
+        r2 = length;
+        rv = length;
+
+        // R1 is the region after the first non-vowel following a vowel, or is the null region
+        // at the end of the word if there is no such non-vowel.
+        for(var i = 0; i < (length - 1) && r1 == length; i++){
+            if(this.isVowel(word[i]) && !this.isVowel(word[i + 1])){
+                r1 = i + 2;
+            }
+        }
+
+        // R2 is the region after the first non-vowel following a vowel in R1,
+        // or is the null region at the end of the word if there is no such non-vowel.
+        for(var i = r1; i < (length - 1) && r2 == length; i++){
+            if(this.isVowel(word[i]) && !this.isVowel(word[i + 1])){
+                r2 = i + 2;
+            }
+        }
+
+        if(length > 3){
+            if(!this.isVowel(word[1])){
+                rv = this.nextVowelPosition(word, 2) + 1;
+            } else if(this.isVowel(word[0]) && this.isVowel(word[1])){
+                rv = this.nextConsonantPosition(word, 2) + 1;
+            } else {
+                rv = 3;
+            }
+        }
+
+        var r1Text = word.slice(r1);
+        var r2Text = word.slice(r2);
+        var rvText = word.slice(rv);
+        var originalWord = word;
+
+        // Step 0: Attached pronoun
+        var pronounSuffix = ['me', 'se', 'sela', 'selo', 'selas', 'selos', 'la', 'le', 'lo', 'las', 'les', 'los', 'nos'];
+        var pronounSuffixPre1 = ['iéndo', 'ándo', 'ár', 'ér', 'ír'];
+        var pronounSuffixPre2 = ['iendo', 'ando', 'ar', 'er', 'ir'];
+
+        var suffix = this.endsInArr(word, pronounSuffix);
+
+        if(suffix != ''){
+            var preSuffix = this.endsInArr(rvText.slice(0, -suffix.length), pronounSuffixPre1);
+
+            if(preSuffix != ''){
+                word = this.removeAccent(word.slice(0, -suffix.length));
+            } else {
+                preSuffix = this.endsInArr(rvText.slice(0, -suffix.length), pronounSuffixPre2);
+
+                if(preSuffix != '' || (this.endsIn(word.slice(0, -suffix.length), 'uyendo'))){
+
+                    word = word.slice(0, -suffix.length);
+                }
+            }
+        }
+
+        if(word != originalWord){
+            r1Text = word.slice(r1);
+            r2Text = word.slice(r2);
+            rvText = word.slice(rv);
+        }
+
+        var wordAfter0 = word;
+
+        if(( suf = this.endsInArr(r2Text, ['anza', 'anzas', 'ico', 'ica', 'icos', 'icas', 'ismo', 'ismos',
+                                            'able', 'ables', 'ible', 'ibles', 'ista', 'istas', 'oso', 'osa',
+                                            'osos', 'osas', 'amiento', 'amientos', 'imiento', 'imientos'])) != '')
+        {
+            word = word.slice(0, -suf.length);
 		}
-	}
-
-	if (len > 3) {
-			if(isVowel(token[1])) {
-				// If the second letter is a consonant, RV is the region after the next following vowel
-				rv = getNextVowelPos(token, 2) +1;
-			} else if (isVowel(token[0]) && isVowel(token[1])) {
-				// or if the first two letters are vowels, RV is the region after the next consonant
-				rv = getNextConsonantPos(token, 2) + 1;
-			} else {
-				//otherwise (consonant-vowel case) RV is the region after the third letter. But RV is the end of the word if these positions cannot be found.
-				rv = 3;
-			}
+        else if((suf = this.endsInArr(r2Text, ['icadora', 'icador', 'icación', 'icadoras', 'icadores', 'icaciones',
+                                            'icante', 'icantes', 'icancia', 'icancias', 'adora', 'ador', 'ación',
+                                            'adoras', 'adores', 'aciones', 'ante', 'antes', 'ancia', 'ancias'])) != '')
+        {
+            word = word.slice(0, -suf.length);
 		}
-
-	var r1_txt = token.substring(r1-1);
-	var r2_txt = token.substring(r2-1);
-	var rv_txt = token.substring(rv-1);
-
-
-	var token_orig = token;
-
-	// Step 0: Attached pronoun
-	var pronoun_suf = new Array('me', 'se', 'sela', 'selo', 'selas', 'selos', 'la', 'le', 'lo', 'las', 'les', 'los', 'nos');
-	var pronoun_suf_pre1 = new Array('éndo', 'ándo', 'ár', 'ér', 'ír');
-	var pronoun_suf_pre2 = new Array('ando', 'iendo', 'ar', 'er', 'ir');
-	var suf = endsinArr(token, pronoun_suf);
-
-
-	if (suf!='') {
-
-		var pre_suff = endsinArr(rv_txt.slice(0,-suf.length),pronoun_suf_pre1);
-
-		if (pre_suff != '') {
-
-				token = removeAccent(token.slice(0,-suf.length));
-		} else {
-			var pre_suff = endsinArr(rv_txt.slice(0,-suf.length),pronoun_suf_pre2);
-
-			if (pre_suff != '' ||
-				(endsin(token, 'yendo' ) &&
-				(token.slice(-suf.length-6,1) == 'u'))) {
-				token = token.slice(0,-suf.length);
-			}
+        else if((suf = this.endsInArr(r2Text, ['logía', 'logías'])) != ''){
+            word = word.slice(0, -suf.length) + 'log';
 		}
-	}
-
-		if (token != token_orig) {
-			r1_txt = token.substring(r1-1);
-			r2_txt = token.substring(r2-1);
-			rv_txt = token.substring(rv-1);
+        else if((suf = this.endsInArr(r2Text, ['ución', 'uciones'])) != ''){
+            word = word.slice(0, -suf.length) + 'u';
 		}
-		var token_after0 = token;
-
-		if ((suf = endsinArr(r2_txt, new Array('anza', 'anzas', 'ico', 'ica', 'icos', 'icas', 'ismo', 'ismos', 'able', 'ables', 'ible', 'ibles', 'ista', 'istas', 'oso', 'osa', 'osos', 'osas', 'amiento', 'amientos', 'imiento', 'imientos'))) != '') {
-			token = token.slice(0, -suf.length);
-		} else if ((suf = endsinArr(r2_txt, new  Array('icadora', 'icador', 'icación', 'icadoras', 'icadores', 'icaciones', 'icante', 'icantes', 'icancia', 'icancias', 'adora', 'ador', 'ación', 'adoras', 'adores', 'aciones', 'ante', 'antes', 'ancia', 'ancias'))) != '') {
-			token = token.slice(0,  -suf.length);
-		} else if ((suf = endsinArr(r2_txt, new  Array('logía', 'logías'))) != '') {
-			token = token.slice(0,  -suf.length)+ 'log';
-		} else if ((suf =endsinArr(r2_txt, new  Array('ución', 'uciones'))) != '') {
-			token = token.slice(0,  -suf.length) + 'u';
-		} else if ((suf = endsinArr(r2_txt, new  Array('encia', 'encias'))) != '') {
-			token = token.slice(0,  -suf.length)+ 'ente';
-		} else if ((suf = endsinArr(r2_txt, new  Array('ativamente', 'ivamente', 'osamente', 'icamente', 'adamente'))) != '') {
-			token = token.slice(0,  -suf.length);
-		} else if ((suf = endsinArr(r1_txt, new  Array('amente'))) != '') {
-			token = token.slice(0,  -suf.length);
-		} else if ((suf = endsinArr(r2_txt, new  Array('antemente', 'ablemente', 'iblemente', 'mente'))) != '') {
-			token = token.slice(0,  -suf.length);
-		} else if ((suf = endsinArr(r2_txt, new  Array('abilidad', 'abilidades', 'icidad', 'icidades', 'ividad', 'ividades', 'idad', 'idades'))) != '') {
-			token = token.slice(0,  -suf.length);
-		} else if ((suf = endsinArr(r2_txt, new  Array('ativa', 'ativo', 'ativas', 'ativos', 'iva', 'ivo', 'ivas', 'ivos'))) != '') {
-			token = token.slice(0,  -suf.length);
+        else if((suf = this.endsInArr(r2Text, ['encia', 'encias'])) != ''){
+            word = word.slice(0, -suf.length) + 'ente';
 		}
-
-		if (token != token_after0) {
-			r1_txt = token.substring(r1-1);
-			r2_txt = token.substring(r2-1);
-			rv_txt = token.substring(rv-1);
+        else if((suf = this.endsInArr(r2Text, ['ativamente', 'ivamente', 'osamente', 'icamente', 'adamente'])) != ''){
+            word = word.slice(0, -suf.length);
+		}
+        else if((suf = this.endsInArr(r1Text, ['amente'])) != ''){
+			word = word.slice(0, -suf.length);
+		}
+        else if((suf = this.endsInArr(r2Text, ['antemente', 'ablemente', 'iblemente', 'mente'])) != ''){
+			word = word.slice(0, -suf.length);
+		}
+        else if((suf = this.endsInArr(r2Text, ['abilidad', 'abilidades', 'icidad', 'icidades', 'ividad', 'ividades', 'idad', 'idades'])) != ''){
+			word = word.slice(0, -suf.length);
+		}
+        else if((suf = this.endsInArr(r2Text, ['ativa', 'ativo', 'ativas', 'ativos', 'iva', 'ivo', 'ivas', 'ivos'])) != ''){
+            word = word.slice(0, -suf.length);
 		}
-		var token_after1 = token;
 
-		if (token_after0 == token_after1) {
-			// Do step 2a if no ending was removed by step 1.
-			if ((suf = endsinArr(rv_txt, new Array('ya', 'ye', 'yan', 'yen', 'yeron', 'yendo', 'yo', 'yó', 'yas', 'yes', 'yais', 'yamos'))) != '' && (token.substring(suf.length-1,1) == 'u')) {
-				token = token.slice(0, -suf.length);
-			}
+        if(word != wordAfter0){
+            r1Text = word.slice(r1);
+            r2Text = word.slice(r2);
+            rvText = word.slice(rv);
+        }
+        var wordAfter1 = word;
 
-			if (token != token_after1) {
-				r1_txt = token.substring(r1-1);
-				r2_txt = token.substring(r2-1);
-				rv_txt = token.substring(rv-1);
-			}
-			var token_after2a = token;
+        if(wordAfter0 === wordAfter1){
 
-			// Do Step 2b if step 2a was done, but failed to remove a suffix.
-			if (token_after2a == token_after1) {
+            // Do step 2a if no ending was removed by step 1.
+            var suf = this.endsInArr(rvText, ['ya', 'ye', 'yan', 'yen', 'yeron', 'yendo', 'yo', 'yó', 'yas', 'yes', 'yais', 'yamos']);
 
-				if ((suf = endsinArr(rv_txt,new Array('en', 'es', 'éis', 'emos'))) != '') {
-					token = token.slice(0,-suf.length);
-					if (endsin(token, 'gu')) {
-						token = token.slice(0,-1);
-					}
-				} else if ((suf = endsinArr(rv_txt, new Array('arían', 'arías', 'arán', 'arás', 'aríais', 'aría', 'aréis', 'aríamos', 'aremos', 'ará', 'aré', 'erían', 'erías', 'erán', 'erás', 'eríais', 'ería', 'eréis', 'eríamos', 'eremos', 'erá', 'eré', 'irían', 'irías', 'irán', 'irás', 'iríais', 'iría', 'iréis', 'iríamos', 'iremos', 'irá', 'iré', 'aba', 'ada', 'ida', 'ía', 'ara', 'iera', 'ad', 'ed', 'id', 'ase', 'iese', 'aste', 'iste', 'an', 'aban', 'ían', 'aran', 'ieran', 'asen', 'iesen', 'aron', 'ieron', 'ado', 'ido', 'ando', 'iendo', 'ió', 'ar', 'er', 'ir', 'as', 'abas', 'adas', 'idas', 'ías', 'aras', 'ieras', 'ases', 'ieses', 'ís', 'áis', 'abais', 'íais', 'arais', 'ierais', '  aseis', 'ieseis', 'asteis', 'isteis', 'ados', 'idos', 'amos', 'ábamos', 'íamos', 'imos', 'áramos', 'iéramos', 'iésemos', 'ásemos'))) != '') {
-
-					token = token.slice(0, -suf.length);
+			if(suf != '' && (word.slice(-suf.length - 1, -suf.length) == 'u')){
+                word = word.slice(0, -suf.length);
+			}
 
+            if(word != wordAfter1){
+				r1Text = word.slice(r1);
+                r2Text = word.slice(r2);
+                rvText = word.slice(rv);
+            }
+
+			var wordAfter2a = word;
+            // Do Step 2b if step 2a was done, but failed to remove a suffix.
+            if (wordAfter2a == wordAfter1) {
+                if((suf = this.endsInArr(rvText, ['arían', 'arías', 'arán', 'arás', 'aríais', 'aría', 'aréis',
+                                                    'aríamos', 'aremos', 'ará', 'aré', 'erían', 'erías', 'erán',
+                                                    'erás', 'eríais', 'ería', 'eréis', 'eríamos', 'eremos', 'erá',
+                                                    'eré', 'irían', 'irías', 'irán', 'irás', 'iríais', 'iría', 'iréis',
+                                                    'iríamos', 'iremos', 'irá', 'iré', 'aba', 'ada', 'ida', 'ía', 'ara',
+                                                    'iera', 'ad', 'ed', 'id', 'ase', 'iese', 'aste', 'iste', 'an',
+                                                    'aban', 'ían', 'aran', 'ieran', 'asen', 'iesen', 'aron', 'ieron',
+                                                    'ado', 'ido', 'ando', 'iendo', 'ió', 'ar', 'er', 'ir', 'as', 'abas',
+                                                    'adas', 'idas', 'ías', 'aras', 'ieras', 'ases', 'ieses', 'ís', 'áis',
+                                                    'abais', 'íais', 'arais', 'ierais', '  aseis', 'ieseis', 'asteis',
+                                                    'isteis', 'ados', 'idos', 'amos', 'ábamos', 'íamos', 'imos', 'áramos',
+                                                    'iéramos', 'iésemos', 'ásemos'])) != '')
+                {
+                    word = word.slice(0, -suf.length);
+                }else if((suf = this.endsInArr(rvText, ['en', 'es', 'éis', 'emos'])) != '') {
+					word = word.slice(0, -suf.length);
+                    if(this.endsIn(word, 'gu')){
+                        word = word.slice(0, -1);
+					}
 				}
+            }
+        }
+
+        r1Text = word.slice(r1);
+        r2Text = word.slice(r2);
+        rvText = word.slice(rv);
+
+        if ((suf = this.endsInArr(rvText, ['os', 'a', 'o', 'á', 'í', 'ó'])) != '') {
+			word = word.slice(0, -suf.length);
+		} else if ((this.endsInArr(rvText , ['e','é'])) != '') {
+			word = word.slice(0, -1);
+			rvText = word.slice(rv);
+			if (this.endsIn(rvText, 'u') && this.endsIn(word, 'gu')) {
+				word = word.slice(0, -1);
 			}
 		}
 
-		// Always do step 3.
-		r1_txt = token.substring(r1-1);
-		r2_txt = token.substring(r2-1);
-		rv_txt = token.substring(rv-1);
-
-		if ((suf = endsinArr(rv_txt, new Array('os', 'a', 'o', 'á', 'í', 'ó'))) != '') {
-			token = token.slice(0, -suf.length);
-		} else if ((suf = endsinArr(rv_txt ,new Array('e','é'))) != '') {
-			token = token.slice(0,-1);
-			rv_txt = token.substring(rv-1);
-			if (endsin(rv_txt,'u') && endsin(token,'gu')) {
-				token = token.slice(0,-1);
-			}
-		}
+		return this.removeAccent(word);
+    }
 
-		return removeAccent(token);
+}
 
-};
+module.exports = new PorterStemmer();

package/lib/natural/stemmers/porter_stemmer_fr.js

@@ -374,4 +374,4 @@ function isVowel(letter) {
 function endsin(token, suffix) {
   if (token.length < suffix.length) return false;
   return (token.slice(-suffix.length) == suffix);
-};
+};