natural 0.1.27 → 0.2.1

package/spec/classifier_spec.js

@@ -21,8 +21,20 @@ THE SOFTWARE.
 */
 
 var natural = require('lib/natural');
+var baseClassifier = require('lib/natural/classifiers/classifier.js');
+var fs = require('fs');
 
 describe('classifier', function () {
+
+    describe('addDocument', function () {
+
+        it('should ignore an empty document', function () {
+            var classifier = new natural.BayesClassifier();
+            classifier.addDocument('', 'philosophy');
+            expect(classifier.docs.length).toBe(0);
+        });
+    });
+
     describe('events emitters', function () {
 
         it('should be emitted when a document is classified', function () {
@@ -88,4 +100,76 @@ describe('classifier', function () {
         });
 
     });
+
+    describe('removeDocument', function () {
+
+        var classifier;
+        beforeEach(function () {
+            classifier = new natural.BayesClassifier();
+            classifier.addDocument('i fixed the box', 'computing');
+            classifier.addDocument('i write code', 'computing');
+            classifier.addDocument('write a book', 'literature');
+            classifier.addDocument('study the books', 'literature');
+        });
+
+        it('should do nothing if text is not a string', function () {
+            expect(classifier.docs.length).toBe(4);
+            classifier.removeDocument(['write a book'], 'literature');
+            classifier.removeDocument(['study the books'], 'literature');
+            expect(classifier.docs.length).toBe(4);
+        });
+
+        it('should do nothing if text is not a match', function () {
+            expect(classifier.docs.length).toBe(4);
+            classifier.removeDocument('something else', 'literature');
+            classifier.removeDocument('another thing', 'literature');
+            expect(classifier.docs.length).toBe(4);
+        });
+    });
+
+    describe('save', function () {
+
+        var tmpFilename = '/spec/test_data/deleteMe';
+        var nonExistentFilename = '/nonExistentDir/deleteMe';
+        var classifier;
+
+        beforeEach(function () {
+            classifier = new natural.BayesClassifier();
+            classifier.addDocument('I went to see the doctor of', 'philosophy');
+        });
+
+        afterEach(function () {
+            if (fs.existsSync(tmpFilename)) {
+                fs.unlinkSync(tmpFilename);
+                fs.unlinkSync(nonExistentFilename);
+            }
+        });
+
+        it('does nothing if called without a callback', function () {
+            classifier.save(tmpFilename);
+            expect(fs.existsSync(tmpFilename)).toBe(false);
+        });
+
+        it('fails if writing to a file fails', function () {
+            classifier.save(nonExistentFilename, function (err) {
+                expect(err).toBe.ok;
+                expect(fs.existsSync(tmpFilename)).toBe(false);
+            });
+        });
+    });
+
+    describe('load', function () {
+
+        it('does nothing if called without a callback', function () {
+            result = baseClassifier.load('/spec/test_data/tfidf_document1.txt');
+            expect(result).not.toBe.ok;
+        });
+
+        it('does nothing if called without a callback', function () {
+            result = baseClassifier.load('/nonexistentFilename', function (err, newClassifier){
+                expect(err).toBe.ok;
+                expect(newClassifier).not.toBe.ok;
+            });
+        });
+    });
 });

package/spec/double_metaphone_spec.js

@@ -737,7 +737,16 @@ describe('double metaphone', function() {
 
   describe('issue #34', function() {
 		it('terminate words ending in H', function() {
-	    expect(doubleMetaphone.process('ptah')).toEqual(['PT', 'PT']);
+	    	expect(doubleMetaphone.process('ptah')).toEqual(['PT', 'PT']);
 		});
   });
+
+  describe('issue #173', function() {
+  	it('handle initial cons correctly', function() {
+  		expect(doubleMetaphone.process('ceasar')).toEqual(['SSR', 'SSR']);
+  		expect(doubleMetaphone.process('ach')).toEqual(['AK', 'AK']);  	
+  		expect(doubleMetaphone.process('chemical')).toEqual(['KMKL', 'KMKL']);
+  		expect(doubleMetaphone.process('choral')).toEqual(['KRL', 'KRL']);  		
+  	});
+  });
 });

package/spec/lancaster_stemmer_spec.js

@@ -54,11 +54,20 @@ describe('lancaster_stemmer', function() {
     });
     
     it('should apply intact rules only to intact string', function() {
-	stemmer.attach();
+    stemmer.attach();
 
         expect('maximum'.stem()).toBe('maxim');
         expect('presumably'.stem()).toBe('presum');
         expect('MAXIMUM'.stem()).toBe('maxim');
         expect('PRESUMABLY'.stem()).toBe('presum');        
     });
+
+    it('#171 and #174, exceed, anguish, affluxion, discept', function() {
+    stemmer.attach();
+
+        expect('exceed'.stem()).toBe('excess');
+        expect('anguish'.stem()).toBe('anct');
+        expect('affluxion'.stem()).toBe('affluct');
+        expect('discept'.stem()).toBe('disceiv');
+    });
 });

package/spec/longest_path_tree_spec.js

@@ -0,0 +1,102 @@
+/*
+ Copyright (c) 2014, Lee Wenzhu
+
+ 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 LPT = require('../lib/natural/util/longest_path_tree'),
+    Topological = require('../lib/natural/util/topological'),
+    EdgeWeightedDigraph = require('../lib/natural/util/edge_weighted_digraph');
+
+describe("shortest path tree", function() {
+    var digraph = new EdgeWeightedDigraph();
+    digraph.add(5,4,0.35);
+    digraph.add(4,7,0.37);
+    digraph.add(5,7,0.28);
+    digraph.add(5,1,0.32);
+    digraph.add(4,0,0.38);
+    digraph.add(0,2,0.26);
+    digraph.add(3,7,0.39);
+    digraph.add(1,3,0.29);
+    digraph.add(7,2,0.34);
+    digraph.add(6,2,0.40);
+    digraph.add(3,6,0.52);
+    digraph.add(6,0,0.58);
+    digraph.add(6,4,0.93);
+    describe("edge weighted digraph normal operations", function() {
+        it("should get the numbers of vertexs", function() {
+            expect(digraph.v()).toBe(8);
+        });
+        it("should get the numbers of edges", function() {
+            expect(digraph.e()).toBe(13);
+        });
+        it("should print all item in digraph", function() {
+            expect(digraph.toString()).toBe('0 -> 2, 0.26\n' +
+                                            '1 -> 3, 0.29\n' +
+                                            '3 -> 7, 0.39\n' +
+                                            '3 -> 6, 0.52\n' +
+                                            '4 -> 7, 0.37\n' +
+                                            '4 -> 0, 0.38\n' +
+                                            '5 -> 4, 0.35\n' +
+                                            '5 -> 7, 0.28\n' +
+                                            '5 -> 1, 0.32\n' +
+                                            '6 -> 2, 0.4\n' +
+                                            '6 -> 0, 0.58\n' +
+                                            '6 -> 4, 0.93\n' +
+                                            '7 -> 2, 0.34');
+        });
+    });
+
+    describe("topo sort for digraph", function() {
+        it("should sort all the vertexs", function() {
+            var topoSort = new Topological(digraph);
+            expect(topoSort.isDAG()).toBe(true);
+            expect(topoSort.order()).toEqual([ 5, 1, 3, 6, 4, 7, 0, 2 ]);
+        });
+    });
+
+    describe("shortest path tree normal operations", function() {
+        var lpt = new LPT(digraph, 5);
+        expect(lpt.hasPathTo(0)).toBe(true);
+        expect(lpt.hasPathTo(1)).toBe(true);
+        expect(lpt.hasPathTo(2)).toBe(true);
+        expect(lpt.hasPathTo(3)).toBe(true);
+        expect(lpt.hasPathTo(4)).toBe(true);
+        expect(lpt.hasPathTo(5)).toBe(false);
+        expect(lpt.hasPathTo(6)).toBe(true);
+        expect(lpt.hasPathTo(7)).toBe(true);
+        expect(lpt.pathTo(0)).toEqual([ 5, 1, 3, 6, 4, 0 ]);
+        expect(lpt.pathTo(1)).toEqual([ 5, 1 ]);
+        expect(lpt.pathTo(2)).toEqual([ 5, 1, 3, 6, 4, 7, 2 ]);
+        expect(lpt.pathTo(3)).toEqual([ 5, 1, 3 ]);
+        expect(lpt.pathTo(4)).toEqual([ 5, 1, 3, 6, 4 ]);
+        expect(lpt.pathTo(5)).toEqual([ ]);
+        expect(lpt.pathTo(6)).toEqual([ 5, 1, 3, 6 ]);
+        expect(lpt.pathTo(7)).toEqual([ 5, 1, 3, 6, 4, 7 ]);
+        expect(lpt.getDistTo(0)).toBe(2.44);
+        expect(lpt.getDistTo(1)).toBe(0.32);
+        expect(lpt.getDistTo(2)).toBe(2.77);
+        expect(lpt.getDistTo(3)).toBe(0.61);
+        expect(lpt.getDistTo(4)).toBe(2.06);
+        expect(lpt.getDistTo(5)).toBe(0);
+        expect(lpt.getDistTo(6)).toBe(1.13);
+        expect(lpt.getDistTo(7)).toBe(2.43);
+    });
+});

package/spec/metaphone_spec.js

@@ -211,6 +211,11 @@ describe('metaphone', function() {
         expect(metaphone.compare('PHONETICS', 'garbonzo')).toBeFalsy();
     });
     
+    it('#173', function() {
+        //expect(metaphone.process('caesar')).toBe('KSR');   
+        //expect(metaphone.process('chemical')).toBe('KMKL');   
+    });
+
     it('should compare strings with string patch', function() {
         metaphone.attach();
         expect('phonetics'.soundsLike('fonetix')).toBeTruthy();
@@ -224,6 +229,11 @@ describe('metaphone', function() {
         expect('phonetics'.phonetics()).toBe('FNTKS');
         expect('PHONETICS'.phonetics()).toBe('FNTKS');        
     });
+
+    it('should transform PH to F #169', function() {
+	    expect('pharaoh'.phonetics()).toBe('FR');        
+	    expect('tough'.phonetics()).toBe('TF');        
+    });
     
     it('should tokenize and return string phonetics with string patch', function() {
         metaphone.attach();

package/spec/ngram_spec.js

@@ -66,4 +66,65 @@ describe('ngrams', function() {
                 ['are', 'some', 'words']]);
         });        
     });
+
+    // New Start/End Symbols Feature
+    it('should bigram a string with start and end symbols', function() {
+        expect(NGrams.ngrams('these are some words', 2, "[start]", "[end]")).toEqual([
+            ['[start]', 'these'], 
+            ['these', 'are'],
+            ['are', 'some' ], 
+            ['some', 'words'], 
+            ['words', '[end]']
+        ]);
+    });
+
+    it('should bigram a string with start symbols only', function() {
+        expect(NGrams.ngrams('these are some words', 2, "[start]")).toEqual([
+            ['[start]', 'these'], 
+            ['these', 'are'],
+            ['are', 'some' ], 
+            ['some', 'words']
+        ]);
+    });
+
+
+    it('should bigram a string with end symbols only', function() {
+        expect(NGrams.ngrams('these are some words', 2, null, "[end]")).toEqual([
+            ['these', 'are'],
+            ['are', 'some' ], 
+            ['some', 'words'],
+            ['words', '[end]']
+        ]);
+    });
+
+    it('should trigram a string with start and end symbols', function() {
+        expect(NGrams.ngrams('these are some words', 3, '[start]', '[end]')).toEqual([
+            ['[start]', '[start]', 'these'],
+            ['[start]', 'these', 'are'], 
+            ['these', 'are', 'some'],
+            ['are', 'some', 'words'], 
+            ['some', 'words', '[end]'],
+            ['words', '[end]', '[end]']
+        ]);
+    });
+
+    it('should 4-gram a string with start and end symbols', function() {
+        expect(NGrams.ngrams('these are some words', 4, '[start]', '[end]')).toEqual([
+            ['[start]', '[start]', '[start]', 'these'],
+            ['[start]', '[start]', 'these', 'are'],
+            ['[start]', 'these', 'are', 'some'],
+            ['these', 'are', 'some', 'words'], 
+            ['are', 'some', 'words', '[end]'],
+            ['some', 'words', '[end]', '[end]'],
+            ['words', '[end]', '[end]', '[end]']
+        ]);
+    });
+    
+    it('should use french tokenizer', function(){
+        var T = require('../lib/natural/tokenizers/aggressive_tokenizer_fr');
+        var t = new T();
+        NGrams.setTokenizer(t);
+        expect(NGrams.ngrams('Un Éléphant rouge', 2)).toEqual([['Un', 'Éléphant'],
+            ['Éléphant', 'rouge' ]]);
+    });
 });

package/spec/ngram_zh_spec.js

@@ -0,0 +1,122 @@
+/*
+Copyright (c) 2014, Lee Wenzhu
+
+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 NGramsZH = require('../lib/natural/ngrams/ngrams_zh');
+
+describe('ngrams', function() {
+    it('should bigram a string via ngrams', function() {
+        expect(NGramsZH.ngrams('中文文本测试', 2)).toEqual([['中', '文'],
+            ['文', '文' ], ['文', '本'], ['本','测'], ['测', '试']]);
+    });
+    
+    it('should bigram an array via ngrams', function() {
+        expect(NGramsZH.ngrams(['中','文','文','本','测','试'], 2)).toEqual([['中', '文'],
+            ['文', '文' ], ['文', '本'], ['本','测'], ['测', '试']]);
+    });
+    
+    it('should trigram a string via ngrams', function() {
+        expect(NGramsZH.ngrams('中文文本测试', 3)).toEqual([['中', '文', '文'],
+                ['文', '文', '本'],['文','本','测'],['本','测','试']]);
+    });    
+    
+    it('should trigram an array via ngrams', function() {
+        expect(NGramsZH.ngrams(['中','文','文','本','测','试'], 3)).toEqual([['中', '文', '文'],
+                ['文', '文', '本'],['文','本','测'],['本','测','试']]);
+    });    
+
+    describe('bigrams', function() {
+        it('should bigram a string', function() {
+            expect(NGramsZH.bigrams('中文文本测试')).toEqual([['中', '文'],
+                   ['文', '文' ], ['文', '本'], ['本','测'], ['测', '试']]);
+        });
+        
+        it('should bigram an array', function() {
+            expect(NGramsZH.bigrams(['中','文','文','本','测','试'])).toEqual([['中', '文'],
+                    ['文', '文' ], ['文', '本'], ['本','测'], ['测', '试']]);
+        });        
+    });
+
+    describe('trigrams', function() {
+        it('should trigram a string', function() {
+            expect(NGramsZH.ngrams('中文文本测试', 3)).toEqual([['中', '文', '文'],
+                    ['文', '文', '本'],['文','本','测'],['本','测','试']]);
+        });
+        
+        it('should bigram an array', function() {
+            expect(NGramsZH.ngrams(['中','文','文','本','测','试'], 3)).toEqual([['中', '文', '文'],
+                    ['文', '文', '本'],['文','本','测'],['本','测','试']]);
+        });        
+    });
+
+    it('should bigram a string with start and end symbols', function() {
+        expect(NGramsZH.ngrams('中文测试', 2, "[start]", "[end]")).toEqual([
+            ['[start]', '中'], 
+            ['中', '文'],
+            ['文', '测' ], 
+            ['测', '试'], 
+            ['试', '[end]']
+        ]);
+    });
+
+    it('should bigram a string with start symbols only', function() {
+        expect(NGramsZH.ngrams('中文测试', 2, "[start]")).toEqual([
+            ['[start]', '中'], 
+            ['中', '文'],
+            ['文', '测' ], 
+            ['测', '试'] 
+        ]);
+    });
+
+
+    it('should bigram a string with end symbols only', function() {
+        expect(NGramsZH.ngrams('中文测试', 2, null, "[end]")).toEqual([
+            ['中', '文'],
+            ['文', '测' ], 
+            ['测', '试'], 
+            ['试', '[end]']
+        ]);
+    });
+
+    it('should trigram a string with start and end symbols', function() {
+        expect(NGramsZH.ngrams('中文测试', 3, '[start]', '[end]')).toEqual([
+            ['[start]', '[start]', '中'],
+            ['[start]', '中', '文'], 
+            ['中', '文', '测'],
+            ['文', '测', '试'], 
+            ['测', '试', '[end]'],
+            ['试', '[end]', '[end]']
+        ]);
+    });
+
+    it('should 4-gram a string with start and end symbols', function() {
+        expect(NGramsZH.ngrams('中文测试', 4, '[start]', '[end]')).toEqual([
+            ['[start]', '[start]', '[start]', '中'],
+            ['[start]', '[start]', '中', '文'],
+            ['[start]', '中', '文', '测'],
+            ['中', '文', '测', '试'], 
+            ['文', '测', '试', '[end]'],
+            ['测', '试', '[end]', '[end]'],
+            ['试', '[end]', '[end]', '[end]']
+        ]);
+    });
+    
+});

package/spec/normalizer_ja_spec.js

@@ -54,8 +54,14 @@ describe('normalize_ja', function() {
 
   it('should transform halfwidth punctuation signs to fullwidth', function() {
     // Taken from http://unicode.org/cldr/trac/browser/trunk/common/main/ja.xml
-    expect(normalize_ja('‾ _＿ -－ ‐ — ― 〜 ・ ･ ,， 、､ ;； :： !！ ?？ .． ‥ … 。｡ ＇＼ ‘ ’ "＂ “ ” (（ )） [［ ]］ {｛ }｝ 〈 〉 《 》 「｢ 」｣ 『 』 【 】 〔 〕 ‖ § ¶ @＠ +＋ ^＾ $＄ *＊ /／ ＼\\ &＆ #＃ %％ ‰ † ‡ ′ ″ 〃 ※'))
-      .toEqual('‾ ＿＿ ─－ ‐ — ― 〜 ・ ・ ，， 、、 ；； ：： ！！ ？？ ．． ‥ … 。。 ＇＼ ‘ ’ ＂＂ “ ” （（ ）） ［［ ］］ ｛｛ ｝｝ 〈 〉 《 》 「「 」」 『 』 【 】 〔 〕 ‖ § ¶ ＠＠ ＋＋ ＾＾ ＄＄ ＊＊ ／／ ＼＼ ＆＆ ＃＃ ％％ ‰ † ‡ ′ ″ 〃 ※');
+    expect(normalize_ja('〜 ・ ･ 、､ 。｡ 「｢ 」｣'))
+      .toEqual('〜 ・ ・ 、、 。。 「「 」」');
+  });
+
+  it('should transform fullwidth symbols to halfwidth', function() {
+    // Taken from http://unicode.org/cldr/trac/browser/trunk/common/main/ja.xml
+    expect(normalize_ja('‾ _＿ -－ ‐ — ― ,， ;； :： !！ ?？ .． ‥ … ＇＼ ‘ ’ "＂ “ ” (（ )） [［ ]］ {｛ }｝ 〈 〉 《 》 『 』 【 】 〔 〕 ‖ § ¶ @＠ +＋ ^＾ $＄ *＊ /／ ＼\\ &＆ #＃ %％ ‰ † ‡ ′ ″ 〃 ※'))
+      .toEqual('‾ __ -- ‐ — ― ,, ;; :: !! ?? .. ‥ … ＇\\ ‘ ’ "" “ ” (( )) [[ ]] {{ }} 〈 〉 《 》 『 』 【 】 〔 〕 ‖ § ¶ @@ ++ ^^ $$ ** // \\\\ && ## %% ‰ † ‡ ′ ″ 〃 ※');
   });
 
   it('should replace repeat characters', function() {
@@ -65,7 +71,7 @@ describe('normalize_ja', function() {
 
   it('should replace composite symbols', function() {
     expect(normalize_ja('㍼54年㋃㏪')).toEqual('昭和54年4月11日');
-    expect(normalize_ja('㍧~㍬')).toEqual('15点～20点');
+    expect(normalize_ja('㍧〜㍬')).toEqual('15点〜20点');
     expect(normalize_ja('カンパニー㍿')).toEqual('カンパニー株式会社');
     expect(normalize_ja('100㌫')).toEqual('100パーセント');
     expect(normalize_ja('70㌔')).toEqual('70キロ');

package/spec/normalizer_no_spec.js

@@ -0,0 +1,111 @@
+/*
+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 normalizer = require("../lib/natural/normalizers/normalizer_no.js");
+
+describe('normalizer_no', function() {
+
+    /**
+     * Test character normalization
+     **/
+    describe("Normalization of diacritical marks", function(){
+        it("should leave uppercase and lowercase ä's untouched", function() {
+            expect(normalizer.remove_diacritics('ä')).toBe('ä');
+            expect(normalizer.remove_diacritics('Ä')).toBe('Ä');
+        });
+
+        it("should leave uppercase and lowercase ö's untouched", function() {
+            expect(normalizer.remove_diacritics('ö')).toBe('ö');
+            expect(normalizer.remove_diacritics('Ö')).toBe('Ö');
+        });
+
+        it("should leave uppercase and lowercase ü's untouched", function() {
+            expect(normalizer.remove_diacritics('ü')).toBe('ü');
+            expect(normalizer.remove_diacritics('Ü')).toBe('Ü');
+        });
+
+        it("should correctly normalize uppercase and lowercase a's with grave accents", function(){
+            expect(normalizer.remove_diacritics('à')).toBe('a');
+            expect(normalizer.remove_diacritics('À')).toBe('A');
+        });
+
+        it("should correctly normalize uppercase and lowercase a's with acute accents", function(){
+            expect(normalizer.remove_diacritics('á')).toBe('a');
+            expect(normalizer.remove_diacritics('Á')).toBe('A');
+        });
+
+        it("should correctly normalize uppercase and lowercase a's with circumflex accents", function(){
+            expect(normalizer.remove_diacritics('â')).toBe('a');
+            expect(normalizer.remove_diacritics('Â')).toBe('A');
+        });
+
+        it("should correctly normalize uppercase and lowercase c's with cedillas", function(){
+            expect(normalizer.remove_diacritics('ç')).toBe('c');
+            expect(normalizer.remove_diacritics('Ç')).toBe('C');
+        });
+
+        it("should correctly normalize uppercase and lowercase e's with grave accents", function(){
+            expect(normalizer.remove_diacritics('è')).toBe('e');
+            expect(normalizer.remove_diacritics('È')).toBe('E');
+        });
+
+        it("should correctly normalize uppercase and lowercase e's with acute accents", function(){
+            expect(normalizer.remove_diacritics('é')).toBe('e');
+            expect(normalizer.remove_diacritics('É')).toBe('E');
+        });
+
+        it("should correctly normalize uppercase and lowercase e's with circumflex accents", function(){
+            expect(normalizer.remove_diacritics('ê')).toBe('e');
+            expect(normalizer.remove_diacritics('Ê')).toBe('E');
+        });
+
+        it("should correctly normalize uppercase and lowercase i's with circumflex accents", function(){
+            expect(normalizer.remove_diacritics('î')).toBe('i');
+            expect(normalizer.remove_diacritics('Î')).toBe('I');
+        });
+
+        it("should correctly normalize uppercase and lowercase n's with tildes", function(){
+            expect(normalizer.remove_diacritics('ñ')).toBe('n');
+            expect(normalizer.remove_diacritics('Ñ')).toBe('N');
+        });
+
+        it("should correctly normalize uppercase and lowercase o's with acute accents", function(){
+            expect(normalizer.remove_diacritics('ó')).toBe('o');
+            expect(normalizer.remove_diacritics('Ó')).toBe('O');
+        });
+
+        it("should correctly normalize uppercase and lowercase o's with circumflex accents", function(){
+            expect(normalizer.remove_diacritics('ô')).toBe('o');
+            expect(normalizer.remove_diacritics('Ô')).toBe('O');
+        });
+
+        it("should correctly normalize uppercase and lowercase u's with circumflex accents", function(){
+            expect(normalizer.remove_diacritics('û')).toBe('u');
+            expect(normalizer.remove_diacritics('Û')).toBe('U');
+        });
+
+        it("should correctly normalize uppercase and lowercase s's with caron/wedge accents", function(){
+            expect(normalizer.remove_diacritics('š')).toBe('s');
+            expect(normalizer.remove_diacritics('Š')).toBe('S');
+        });
+    });
+});