Split ZH into yue and cmn, fixed German heading.

[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 692bc41428d1de9e1fc6d4974bc5d1aba8be57b8..605e54650c89ac74fd1c0a9c3a834868b393d006 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/LanguageTest.java
+++ b/src/com/hughes/android/dictionary/engine/LanguageTest.java
@@ -17,17 +17,19 @@ 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 {
   
   public void testGermanSort() {
-    System.out.println(Language.isoCodeToWikiName.values());
-    
     final Transliterator normalizer = Transliterator.createFromRules("", Language.de.getDefaultNormalizerRules(), Transliterator.FORWARD);
     assertEquals("aüääss", normalizer.transform("aueAeAEß"));
     final List<String> words = Arrays.asList(
@@ -108,7 +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() {
@@ -122,7 +124,75 @@ 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 cmn = Language.lookup("cmn");
+    final Transliterator transliterator = Transliterator.createFromRules("", cmn.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.isoCodeToEnWikiName.keySet());
+    final List<String> names = new ArrayList<String>();
+    for (final String code : WiktionaryLangs.isoCodeToEnWikiName.keySet()) {
+      names.add(WiktionaryLangs.isoCodeToEnWikiName.get(code));
+      enLangs.add(code.toLowerCase());
+    }
+    Collections.sort(names);
+    System.out.println(names);
+    //assertEquals(enLangs, Language.isoCodeToResources.keySet());
+    assertEquals(enLangs, Language.isoCodeToResources.keySet());
+  }
 
 }