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(
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() {
assertEquals("kyanpasu", transliterator.transliterate("キャンパス"));
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("xie xie", transliterator.transliterate("謝謝"));
- assertEquals("xie xie", transliterator.transliterate("谢谢"));
+ assertEquals("xiexie", transliterator.transliterate("謝謝"));
+ assertEquals("xiexie", transliterator.transliterate("谢谢"));
- assertEquals("dian nao", transliterator.transliterate("電腦"));
- assertEquals("dian nao", transliterator.transliterate("电脑"));
- assertEquals("ji suan ji", transliterator.transliterate("計算機"));
- assertEquals("ji suan ji", transliterator.transliterate("计算机"));
+ 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("cheng jiu", transliterator.transliterate("成就"));
+ assertEquals("chengjiu", transliterator.transliterate("成就"));
}
// 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());
+ }
}