natural 0.1.27 → 0.2.1

package/spec/normalizer_spec.js

@@ -31,7 +31,6 @@ describe('normalizer', function() {
         it("should correctly normalize n't as not", function(){
             expect(JSON.stringify(normalizer.normalize_tokens(["hasn't"]))).toBe(JSON.stringify(["has", "not"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["hadn't"]))).toBe(JSON.stringify(["had", "not"]));
-            expect(JSON.stringify(normalizer.normalize_tokens(["hasn't"]))).toBe(JSON.stringify(["has", "not"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["haven't"]))).toBe(JSON.stringify(["have", "not"]));
         });
 
@@ -63,7 +62,7 @@ describe('normalizer', function() {
      **/
     describe("special cases", function(){
         it("should convert can't to cannot", function(){
-            expect(JSON.stringify(normalizer.normalize_tokens(["can't"]))).toBe(JSON.stringify(["cannot"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["can't"]))).toBe(JSON.stringify(["can","not"]));
         });
 
         it("should convert couldn't've as could not have", function(){
@@ -86,9 +85,9 @@ describe('normalizer', function() {
         it("should handle different cases on special case conversion", function(){
             expect(JSON.stringify(normalizer.normalize_tokens(["I'm"]))).toBe(JSON.stringify(["I", "am"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["i'm"]))).toBe(JSON.stringify(["I", "am"]));
-            expect(JSON.stringify(normalizer.normalize_tokens(["can't"]))).toBe(JSON.stringify(["cannot"]));
-            expect(JSON.stringify(normalizer.normalize_tokens(["Can't"]))).toBe(JSON.stringify(["cannot"]));
-            expect(JSON.stringify(normalizer.normalize_tokens(["CaN'T"]))).toBe(JSON.stringify(["cannot"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["can't"]))).toBe(JSON.stringify(["can", "not"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["Can't"]))).toBe(JSON.stringify(["can", "not"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["CaN'T"]))).toBe(JSON.stringify(["can", "not"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["how'd"]))).toBe(JSON.stringify(["how", "did"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["how'D"]))).toBe(JSON.stringify(["how", "did"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["HOw'd"]))).toBe(JSON.stringify(["how", "did"]));
@@ -115,5 +114,27 @@ describe('normalizer', function() {
             expect(JSON.stringify(normalizer.normalize_tokens(["i'd"]))).toBe(JSON.stringify(["i", "would"]));
             expect(JSON.stringify(normalizer.normalize_tokens(["I'D"]))).toBe(JSON.stringify(["I", "would"]));
         });
+
+        it("should convert a string to an array for normalization", function() {
+            expect(JSON.stringify(normalizer.normalize_tokens("I'D"))).toBe(JSON.stringify(["I", "would"]));
+        });
+
+        it("should simply tokenize a string that does not match a rule", function() {
+            expect(JSON.stringify(normalizer.normalize_tokens(["Has", "not"]))).toBe(JSON.stringify(["Has", "not"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["HAs", "not"]))).toBe(JSON.stringify(["HAs", "not"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["has", "noT"]))).toBe(JSON.stringify(["has", "noT"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["It", "is"]))).toBe(JSON.stringify(["It", "is"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["IT", "is"]))).toBe(JSON.stringify(["IT", "is"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["it", "iS"]))).toBe(JSON.stringify(["it", "iS"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["We", "will"]))).toBe(JSON.stringify(["We", "will"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["WE", "will"]))).toBe(JSON.stringify(["WE", "will"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["we", "wiLl"]))).toBe(JSON.stringify(["we", "wiLl"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["How", "are"]))).toBe(JSON.stringify(["How", "are"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["hOW", "are"]))).toBe(JSON.stringify(["hOW", "are"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["how", "aRE"]))).toBe(JSON.stringify(["how", "aRE"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["I", "would"]))).toBe(JSON.stringify(["I", "would"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["i", "would"]))).toBe(JSON.stringify(["i", "would"]));
+            expect(JSON.stringify(normalizer.normalize_tokens(["I", "woulD"]))).toBe(JSON.stringify(["I", "woulD"]));
+        });
     });
 });

package/spec/porter_stemmer_fr_spec.js

@@ -0,0 +1,101 @@
+/*
+Copyright (c) 2014, Ismaël Héry
+
+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.
+*/
+
+var stemmer = require('../lib/natural/stemmers/porter_stemmer_fr');
+var fs = require('fs');
+
+describe('porter_stemmer', function() {
+
+  it('should prelude', function() {
+    expect(stemmer.prelude('JOUER')).toBe('joUer');
+    expect(stemmer.prelude('ennuie')).toBe('ennuIe');
+    expect(stemmer.prelude('yeux')).toBe('Yeux');
+    expect(stemmer.prelude('quand')).toBe('qUand');
+  });
+
+  it('should compute regions', function() {
+    expect(stemmer.regions('fameusement').r1).toBe(3);
+    expect(stemmer.regions('fameusement').r2).toBe(6);
+
+    expect(stemmer.regions('taii').r1).toBe(4);
+    expect(stemmer.regions('taii').r2).toBe(4);
+
+    expect(stemmer.regions('parade').rv).toBe(3);
+    expect(stemmer.regions('colet').rv).toBe(3);
+    expect(stemmer.regions('tapis').rv).toBe(3);
+    expect(stemmer.regions('aimer').rv).toBe(3);
+    expect(stemmer.regions('adorer').rv).toBe(3);
+    expect(stemmer.regions('voler').rv).toBe(2);
+    expect(stemmer.regions('tue').rv).toBe(2);
+  });
+
+  it('should compute longest suffix ends in Arr', function() {
+    expect(stemmer.endsinArr('voudriez', ['ez', 'iez', 'z'])).toBe('iez');
+  });
+
+  it('should stem some word', function() {
+    expect(stemmer.stem('volera')).toBe('vol');
+    expect(stemmer.stem('volerait')).toBe('vol');
+    expect(stemmer.stem('subitement')).toBe('subit');
+    expect(stemmer.stem('tempérament')).toBe('temper');
+    expect(stemmer.stem('voudriez')).toBe('voudr');
+    expect(stemmer.stem('vengeait')).toBe('veng');
+    expect(stemmer.stem('saisissement')).toBe('sais');
+    expect(stemmer.stem('transatlantique')).toBe('transatlant');
+    expect(stemmer.stem('premièrement')).toBe('premi');
+    expect(stemmer.stem('instruments')).toBe('instrument');
+    expect(stemmer.stem('trouverions')).toBe('trouv');
+    expect(stemmer.stem('voyiez')).toBe('voi');
+    expect(stemmer.stem('publicité')).toBe('publiqu');
+    expect(stemmer.stem('pitoyable')).toBe('pitoi');
+  });
+
+  it('should perform stemming on a lot of words', function() {
+    var ok = [];
+    var ko = [];
+    fs.readFileSync('spec/test_data/snowball_fr.txt').toString().split('\n').forEach(function(line) {
+      if (line) {
+        var fields = line.replace(/(\s)+/g, ' ').split(' ');
+        var stemmed = stemmer.stem(fields[0]);
+        var regs = stemmer.regions(fields[0]);
+        var txtRegions = {
+          r1: fields[0].substring(regs.r1),
+          r2: fields[0].substring(regs.r2),
+          rv: fields[0].substring(regs.rv)
+        }
+
+        if (stemmed === fields[1])
+          ok.push(fields[0]);
+        else
+          ko.push({
+            word: fields[0],
+            expected: fields[1],
+            actual: stemmed,
+            regions: txtRegions
+          });
+      }
+    });
+
+    expect(ko.length).toBe(0);
+  });
+
+});

package/spec/porter_stemmer_no_spec.js

@@ -0,0 +1,143 @@
+/*
+Copyright (c) 2014, Kristoffer Brabrand
+
+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.
+*/
+
+var stemmer = require('../lib/natural/stemmers/porter_stemmer_no'),
+    fs = require('fs');
+
+describe('porter_stemmer_no', function() {
+    it('should perform step 1a', function() {
+        expect(stemmer.step1a('forenkla')).toBe('forenkl');
+        expect(stemmer.step1a('aase')).toBe('aas');
+        expect(stemmer.step1a('allerede')).toBe('aller');
+        expect(stemmer.step1a('aukande')).toBe('auk');
+        expect(stemmer.step1a('avbøtende')).toBe('avbøt');
+        expect(stemmer.step1a('avdelingane')).toBe('avdeling');
+        expect(stemmer.step1a('avgiftene')).toBe('avgift');
+        expect(stemmer.step1a('havnevirksomhetene')).toBe('havnevirksom');
+        expect(stemmer.step1a('heimelen')).toBe('heimel');
+        expect(stemmer.step1a('hovedvirksomheten')).toBe('hovedvirksom');
+        expect(stemmer.step1a('hovudreglar')).toBe('hovudregl');
+        expect(stemmer.step1a('hugger')).toBe('hugg');
+        expect(stemmer.step1a('importvirksomheter')).toBe('importvirksom');
+        expect(stemmer.step1a('ivaretas')).toBe('ivaret');
+        expect(stemmer.step1a('iverksettes')).toBe('iverksett');
+        expect(stemmer.step1a('konsekvensutredes')).toBe('konsekvensutr');
+        expect(stemmer.step1a('oversendes')).toBe('overs');
+        expect(stemmer.step1a('pensjonenes')).toBe('pensjon');
+        expect(stemmer.step1a('myndighetenes')).toBe('myndig');
+        expect(stemmer.step1a('møteleiarens')).toBe('møteleiar');
+        expect(stemmer.step1a('virksomhetens')).toBe('virksom');
+        expect(stemmer.step1a('aktørers')).toBe('aktør');
+        expect(stemmer.step1a('arbeidslivets')).toBe('arbeidsliv');
+        expect(stemmer.step1a('arbeidskapasitet')).toBe('arbeidskapasit');
+        expect(stemmer.step1a('arealknapphet')).toBe('arealknapp');
+        expect(stemmer.step1a('attgjevast')).toBe('attgjev');
+    });
+
+    it('should perform step 1b', function() {
+        expect(stemmer.step1b('hinder')).toBe('hinder');
+        expect(stemmer.step1b('erwerbs')).toBe('erwerb');
+        expect(stemmer.step1b('alltids')).toBe('alltid');
+    });
+
+    it('should perform step 1c', function() {
+        expect(stemmer.step1c('akkumulerte')).toBe('akkumuler');
+        expect(stemmer.step1c('akseptert')).toBe('aksepter');
+    });
+
+    it('should perform step 1 (a-c)', function() {
+        expect(stemmer.step1('andelar')).toBe('andel');
+        expect(stemmer.step1('andeleigar')).toBe('andeleig');
+        expect(stemmer.step1('andeleigarane')).toBe('andeleigar');
+        expect(stemmer.step1('andeleigarbok')).toBe('andeleigarbok');
+        expect(stemmer.step1('andelen')).toBe('andel');
+        expect(stemmer.step1('andelene')).toBe('andel');
+        expect(stemmer.step1('andeler')).toBe('andel');
+        expect(stemmer.step1('andelsbevis')).toBe('andelsbevis');
+        expect(stemmer.step1('andelsbok')).toBe('andelsbok');
+        expect(stemmer.step1('andelsboka')).toBe('andelsbok');
+        expect(stemmer.step1('andelsboligforening')).toBe('andelsboligforening');
+        expect(stemmer.step1('andelsboligforeninger')).toBe('andelsboligforening');
+        expect(stemmer.step1('andelsboligorganisation')).toBe('andelsboligorganisation');
+        expect(stemmer.step1('andelsboligorganisationer')).toBe('andelsboligorganisation');
+        expect(stemmer.step1('andelsbrev')).toBe('andelsbrev');
+    });
+
+    it('should perform step 2', function() {
+        expect(stemmer.step2('hvorvidt')).toBe('hvorvid');
+        expect(stemmer.step2('innovativt')).toBe('innovativ');
+    });
+
+    it('should perform step 3', function() {
+        expect(stemmer.step3('lovleg')).toBe('lov');
+        expect(stemmer.step3('konkurranseskadeleg')).toBe('konkurranseskad');
+        expect(stemmer.step3('lystig')).toBe('lyst');
+        expect(stemmer.step3('utrolig')).toBe('utro');
+        expect(stemmer.step3('utrøstelig')).toBe('utrøst');
+        expect(stemmer.step3('boliglov')).toBe('bolig');
+        expect(stemmer.step3('samvirkelov')).toBe('samvirk');
+        expect(stemmer.step3('arveavgiftslov')).toBe('arveavgift');
+    });
+
+    it('should perform stemming on a lot of words', function() {
+        var ok = [];
+        var ko = [];
+
+        fs.readFileSync('spec/test_data/snowball_no.txt').toString().split('\n').forEach(function(line) {
+            if (line) {
+                var fields = line.replace(/(\s)+/g, ' ').split(' ');
+                var stemmed = stemmer.stem(fields[0]);
+
+                if (stemmed === fields[1]) {
+                    ok.push(fields[0]);
+                } else {
+                    ko.push({
+                        word: fields[0],
+                        expected: fields[1],
+                        actual: stemmed
+                    });
+                }
+            }
+        });
+
+        expect(ko.length).toBe(0);
+    });
+
+    it('should perform complete stemming', function() {
+        expect(stemmer.step1a('forenkla')).toBe('forenkl');
+        expect(stemmer.step1a('aase')).toBe('aas');
+        expect(stemmer.step1a('allerede')).toBe('aller');
+        expect(stemmer.step1a('aukande')).toBe('auk');
+        expect(stemmer.step1a('avbøtende')).toBe('avbøt');
+        expect(stemmer.step1b('hinder')).toBe('hinder');
+        expect(stemmer.step1b('erwerbs')).toBe('erwerb');
+        expect(stemmer.step3('boliglov')).toBe('bolig');
+        expect(stemmer.step3('samvirkelov')).toBe('samvirk');
+        expect(stemmer.step3('arveavgiftslov')).toBe('arveavgift');
+    });
+
+    it('should tokenize and stem attached', function() {
+        stemmer.attach();
+        expect('forebygger vedlikeholdsbehovene'.tokenizeAndStem()).toEqual(['forebygg', 'vedlikeholdsbehov']);
+        expect('FOREBYGGER VEDLIKEHOLDSBEHOVENE'.tokenizeAndStem()).toEqual(['forebygg', 'vedlikeholdsbehov']);
+    });
+});

package/spec/porter_stemmer_pt_spec.js

@@ -0,0 +1,50 @@
+/*
+Copyright (c) 2014, Luís Rodrigues
+
+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.
+*/
+
+var PorterStemmer = require('../lib/natural/stemmers/porter_stemmer_pt'),
+	fs = require('fs');
+
+describe('porter_stemmer_pt', function() {
+
+ 	it('should perform stemming on a lot of words', function() {
+ 		var errors = [];
+
+ 		fs.readFileSync('spec/test_data/snowball_pt.txt').toString().split('\n').forEach(function(line) {
+ 			if (line) {
+ 				var fields = line.replace(/\s+/g, ' ').split(' '),
+ 					stemmed = PorterStemmer.stem(fields[0]);
+
+ 				if (stemmed !== fields[1]) {
+					console.log('Error:', fields[0], 'Expected:', fields[1], 'Got:', stemmed);
+ 					errors.push({
+ 						word:     fields[0],
+ 						expected: fields[1],
+ 						actual:   stemmed
+ 					});
+ 				}
+ 			}
+ 		});
+
+ 		expect(errors.length).toBe(0);
+ 	});
+
+});

package/spec/porter_stemmer_spec.js

@@ -23,6 +23,15 @@ THE SOFTWARE.
 var stemmer = require('../lib/natural/stemmers/porter_stemmer');
 
 describe('porter_stemmer', function() {
+	it('should categorizeGroups', function() {
+		expect(stemmer.categorizeGroups('syllog')).toBe('CVCVC');
+		expect(stemmer.categorizeGroups('gypsy')).toBe('CVCV');		
+	});
+
+	it('should measure', function() {
+		expect(stemmer.measure('syllog')).toBe(2);
+	});
+
 	it('should perform step 1a', function() {
 		expect(stemmer.step1a('caresses')).toBe('caress');
 		expect(stemmer.step1a('ponies')).toBe('poni');
@@ -125,6 +134,46 @@ describe('porter_stemmer', function() {
 		expect(stemmer.stem('doing')).toBe('do');
 	});
 
+	it('should perform stem animated to anim', function() {
+		expect(stemmer.stem('animated')).toBe('anim');
+	});
+
+	it('issue 176 - attemptReplace ed|ing', function() {
+		expect(stemmer.stem('aedile')).toBe('aedil');
+		expect(stemmer.stem('adoptedly')).toBe('adoptedli');
+	});
+
+	it('issue 176 - minimum length for final e', function() {
+		expect(stemmer.stem('ace')).toBe('ac');
+	});
+
+	it('issue 176 - minimum length for final s', function() {
+		expect(stemmer.stem('yes')).toBe('ye');
+	});
+
+	it('issue 176 - s/tion measure', function() {
+		expect(stemmer.stem('invasion')).toBe('invas');
+	});
+
+	it('issue 176 - vehement - step 4', function() {
+		expect(stemmer.stem('vehement')).toBe('vehement');
+		expect(stemmer.stem('syllogism')).toBe('syllog');
+		expect(stemmer.stem('gypsy')).toBe('gypsi');
+	});
+
+	it('issue 176 step 2', function() {
+		expect(stemmer.stem('terribly')).toBe('terribl');				
+		expect(stemmer.stem('apology')).toBe('apolog');	
+	});
+
+	it('issue 176 - step 5a', function() {
+		expect(stemmer.stem('type')).toBe('type');
+	});	
+
+	it('issue 176 - corruptiblity', function() {
+		expect(stemmer.stem('corruptibility')).toBe('corrupt');
+	});	
+
 	it('should tokenize and stem attached', function() {
 		stemmer.attach();
 		expect('scoring stinks'.tokenizeAndStem()).toEqual(['score', 'stink']);

package/spec/present_verb_inflector_spec.js

@@ -57,6 +57,7 @@ describe('present verb inflector', function() {
         it('should singularize irregular forms', function() {
             expect(inflector.singularize('are')).toBe('is');
             expect(inflector.singularize('were')).toBe('was');
+            expect(inflector.singularize('have')).toBe('has');
         });
 
         it('should singularize ies forms', function() {
@@ -105,6 +106,8 @@ describe('present verb inflector', function() {
         it('should pluralize irregular forms', function() {
             expect(inflector.pluralize('was')).toBe('were');                        
             expect(inflector.pluralize('is')).toBe('are');
+            expect(inflector.pluralize('am')).toBe('are');
+            expect(inflector.pluralize('has')).toBe('have');
         });
 
         it('should pluralize ies forms', function() {

package/spec/remove_diacritics_spec.js

@@ -0,0 +1,31 @@
+/*
+Copyright (c) 2013, Ken Koch
+
+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.
+*/
+
+var removeDiacritics = require("../lib/natural/normalizers/remove_diacritics.js");
+
+describe('remove_diacritics', function() {
+
+    it('should correctly remove diacritics', function () {
+        var original_phrase = 'piñon ça va über résumé';
+        expect(removeDiacritics(original_phrase)).toEqual('pinon ca va uber resume');
+    });
+});