-
- assertTrue(comparator.compare("pre-print", "preppy") < 0);
-
- }
-
- public void testLanguage() {
- assertEquals(Language.de, Language.lookup("de"));
- assertEquals(Language.en, Language.lookup("en"));
- assertEquals("es", Language.lookup("es").getIsoCode());
- }
-
- public void testTextNorm() {
- //final Transliterator transliterator = Transliterator.getInstance("Any-Latin; Upper; Lower; 'oe' > 'o'; NFD; [:Nonspacing Mark:] Remove; NFC", Transliterator.FORWARD);
- final Transliterator transliterator = Transliterator.createFromRules("", ":: Any-Latin; :: Upper; :: Lower; 'oe' > 'o'; :: NFD; :: [:Nonspacing Mark:] Remove; :: NFC ;", Transliterator.FORWARD);
- assertEquals("hoschen", transliterator.transliterate("Höschen"));
- assertEquals("hoschen", transliterator.transliterate("Hoeschen"));
- assertEquals("grosspoo", transliterator.transliterate("Großpoo"));
-
- 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("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());
+
+
+ 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<>(WiktionaryLangs.isoCodeToEnWikiName.keySet());
+ final List<String> names = new ArrayList<>();
+ 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());