Fixed combining marks on Unicode regexes.

[DictionaryPC.git] / src / com / hughes / android / dictionary / engine / LanguageTest.java

diff --git a/src/com/hughes/android/dictionary/engine/LanguageTest.java b/src/com/hughes/android/dictionary/engine/LanguageTest.java
index e4ad6de8228323d2ba2562a0350bbc36bfdfd325..7b84dd644845682305cab6e6f7482f70ceb55b21 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/LanguageTest.java
+++ b/src/com/hughes/android/dictionary/engine/LanguageTest.java
@@ -1,12 +1,30 @@
+// Copyright 2011 Google Inc. All Rights Reserved.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
 package com.hughes.android.dictionary.engine;
 
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
+import java.util.LinkedHashSet;
 import java.util.List;
+import java.util.Set;
 
 import junit.framework.TestCase;
 
+import com.hughes.android.dictionary.parser.DictFileParser;
+import com.hughes.android.dictionary.parser.wiktionary.WiktionaryLangs;
 import com.ibm.icu.text.Transliterator;
 
 public class LanguageTest extends TestCase {
@@ -92,7 +110,7 @@ public class LanguageTest extends TestCase {
   public void testLanguage() {
     assertEquals(Language.de, Language.lookup("de"));
     assertEquals(Language.en, Language.lookup("en"));
-    assertEquals("es", Language.lookup("es").getSymbol());
+    assertEquals("es", Language.lookup("es").getIsoCode());
   }
 
   public void testTextNorm() {
@@ -106,7 +124,71 @@ public class LanguageTest extends TestCase {
     assertEquals("alphabetikos katalogos", transliterator.transliterate("Αλφαβητικός Κατάλογος"));
     assertEquals("biologiceskom", transliterator.transliterate("биологическом"));
   }
+  public void testHalfTextNorm() {
+    final Transliterator transliterator = Transliterator.createFromRules("", ":: Any-Latin; ' ' > ; :: Lower; ", Transliterator.FORWARD);
+    assertEquals("kyanpasu", transliterator.transliterate("キャンパス"));
+    assertEquals("alphabētikóskatálogos", transliterator.transliterate("Αλφαβητικός Κατάλογος"));
+    assertEquals("biologičeskom", transliterator.transliterate("биологическом"));
+
+    assertEquals("xièxiè", transliterator.transliterate("謝謝"));
+    assertEquals("xièxiè", transliterator.transliterate("谢谢"));
+
+    assertEquals("diànnǎo", transliterator.transliterate("電腦"));
+    assertEquals("diànnǎo", transliterator.transliterate("电脑"));
+    assertEquals("jìsuànjī", transliterator.transliterate("計算機"));
+    assertEquals("jìsuànjī", transliterator.transliterate("计算机"));
+  }
+
+  
+  public void testChinese() {
+    final Language zh = Language.lookup("zh");
+    final Transliterator transliterator = Transliterator.createFromRules("", zh.getDefaultNormalizerRules(), Transliterator.FORWARD);
+    
+    assertEquals("xiexie", transliterator.transliterate("謝謝"));
+    assertEquals("xiexie", transliterator.transliterate("谢谢"));
+
+    assertEquals("diannao", transliterator.transliterate("電腦"));
+    assertEquals("diannao", transliterator.transliterate("电脑"));
+    assertEquals("jisuanji", transliterator.transliterate("計算機"));
+    assertEquals("jisuanji", transliterator.transliterate("计算机"));
+    
+    assertEquals("chengjiu", transliterator.transliterate("成就"));
+    
+  }
+  
+  public void testArabic() {
+    final Language ar = Language.lookup("ar");
+    final Transliterator transliterator = Transliterator.createFromRules("", ar.getDefaultNormalizerRules(), Transliterator.FORWARD);
+    // These don't seem quite right....
+    assertEquals("haswb", transliterator.transliterate("حاسوب"));
+    assertEquals("kmbywtr", transliterator.transliterate("كمبيوتر"));
+
+    assertEquals("{\u200e كمبيوتر \u200e}", Language.fixBidiText("{كمبيوتر}"));
+    assertEquals("{a=\u200e كمبيوتر \u200e}", Language.fixBidiText("{a=كمبيوتر}"));
+    assertEquals("(\u200e كمبيوتر \u200e)", Language.fixBidiText("(كمبيوتر)"));
+    assertEquals("أنثى أنْثَى (’únθā) {f}, إناث (’ināθ) {p}, اناثى (’anāθā) {p}", Language.fixBidiText("أنثى أنْثَى (’únθā) {f}, إناث (’ināθ) {p}, اناثى (’anāθā) {p}"));
+       
+  }
 
+  public void testThai() {
+    final Language th = Language.lookup("TH");
+    final Transliterator transliterator = Transliterator.createFromRules("", th.getDefaultNormalizerRules(), Transliterator.FORWARD);
+    // Not sure these are right, just to know...
+    assertEquals("d", transliterator.transliterate("ด"));
+    assertEquals("di", transliterator.transliterate("ด ี"));
+    assertEquals("dii", transliterator.transliterate("ดีี"));
+    
+    assertEquals(Collections.singleton("ดีี"), DictFileParser.tokenize("ดีี", DictFileParser.NON_CHAR));
+  }
 
+  
+  public void testEnWiktionaryNames() {
+    final Set<String> enLangs = new LinkedHashSet<String>(WiktionaryLangs.isoCodeToWikiName.keySet());
+    for (final String code : WiktionaryLangs.isoCodeToWikiName.keySet()) {
+      enLangs.add(code.toLowerCase());
+    }
+    assertEquals(enLangs.toString(), Language.isoCodeToResources.keySet().toString());
+    assertEquals(enLangs, Language.isoCodeToResources.keySet());
+  }
 
 }