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;
+import junit.framework.TestCase;
+
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(
- "er-ben",
- "erben",
- "Erben",
- "Erbse",
- "Erbsen",
- "essen",
- "Essen",
- "Grosformat",
- "Grosformats",
- "Grossformat",
- "Großformat",
- "Grossformats",
- "Großformats",
- "Großpoo",
- "Großpoos",
- "Hörvermögen",
- "Hörweite",
- "hos",
- "Höschen",
- "Hostel",
- "hulle",
- "Hulle",
- "huelle",
- "Huelle",
- "hülle",
- "Hülle",
- "Huellen",
- "Hüllen",
- "Hum"
- );
- final NormalizeComparator comparator = new NormalizeComparator(normalizer, Language.de.getCollator());
- assertEquals(1, comparator.compare("hülle", "huelle"));
- assertEquals(-1, comparator.compare("huelle", "hülle"));
-
- assertEquals(-1, comparator.compare("hülle", "Hülle"));
-
- assertEquals("hülle", normalizer.transform("Hülle"));
- assertEquals("hulle", normalizer.transform("Hulle"));
-
-
- final List<String> sorted = new ArrayList<String>(words);
+
+ public void testGermanSort() {
+ final Transliterator normalizer = Transliterator.createFromRules("", Language.de.getDefaultNormalizerRules(), Transliterator.FORWARD);
+ assertEquals("aüääss", normalizer.transform("aueAeAEß"));
+ final List<String> words = Arrays.asList(
+ "er-ben",
+ "erben",
+ "Erben",
+ "Erbse",
+ "Erbsen",
+ "essen",
+ "Essen",
+ "Grosformat",
+ "Grosformats",
+ "Grossformat",
+ "Großformat",
+ "Grossformats",
+ "Großformats",
+ "Großpoo",
+ "Großpoos",
+ "Hörvermögen",
+ "Hörweite",
+ "hos",
+ "Höschen",
+ "Hostel",
+ "hulle",
+ "Hulle",
+ "huelle",
+ "Huelle",
+ "hülle",
+ "Hülle",
+ "Huellen",
+ "Hüllen",
+ "Hum"
+ );
+ final NormalizeComparator comparator = new NormalizeComparator(normalizer, Language.de.getCollator(), 7);
+ assertEquals(1, comparator.compare("hülle", "huelle"));
+ assertEquals(-1, comparator.compare("huelle", "hülle"));
+
+ assertEquals(-1, comparator.compare("hülle", "Hülle"));
+
+ assertEquals("hülle", normalizer.transform("Hülle"));
+ assertEquals("hulle", normalizer.transform("Hulle"));
+
+
+ final List<String> sorted = new ArrayList<>(words);
// Collections.shuffle(shuffled, new Random(0));
- Collections.sort(sorted, comparator);
- System.out.println(sorted.toString());
- for (int i = 0; i < words.size(); ++i) {
- System.out.println(words.get(i) + "\t" + sorted.get(i));
- assertEquals(words.get(i), sorted.get(i));
+ sorted.sort(comparator);
+ System.out.println(sorted);
+ for (int i = 0; i < words.size(); ++i) {
+ System.out.println(words.get(i) + "\t" + sorted.get(i));
+ assertEquals(words.get(i), sorted.get(i));
+ }
}
- }
-
- public void testEnglishSort() {
- final Transliterator normalizer = Transliterator.createFromRules("", Language.en.getDefaultNormalizerRules(), Transliterator.FORWARD);
-
- final List<String> words = Arrays.asList(
- "pre-print",
- "preppie",
- "preppy",
- "preprocess");
-
- final List<String> sorted = new ArrayList<String>(words);
- final NormalizeComparator comparator = new NormalizeComparator(normalizer, Language.en.getCollator());
- Collections.sort(sorted, comparator);
- for (int i = 0; i < words.size(); ++i) {
- if (i > 0) {
- assertTrue(comparator.compare(words.get(i-1), words.get(i)) < 0);
- }
- System.out.println(words.get(i) + "\t" + sorted.get(i));
- assertEquals(words.get(i), sorted.get(i));
+
+ public void testEnglishSort() {
+ final Transliterator normalizer = Transliterator.createFromRules("", Language.en.getDefaultNormalizerRules(), Transliterator.FORWARD);
+
+ final List<String> words = Arrays.asList(
+ "pre-print",
+ "preppie",
+ "preppy",
+ "preprocess");
+
+ final List<String> sorted = new ArrayList<>(words);
+ final NormalizeComparator comparator = new NormalizeComparator(normalizer, Language.en.getCollator(), 7);
+ sorted.sort(comparator);
+ for (int i = 0; i < words.size(); ++i) {
+ if (i > 0) {
+ assertTrue(comparator.compare(words.get(i-1), words.get(i)) < 0);
+ }
+ System.out.println(words.get(i) + "\t" + sorted.get(i));
+ assertEquals(words.get(i), sorted.get(i));
+ }
+
+ 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"));
}
-
- 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").getSymbol());
- }
-
- 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 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());
+ }
}