Home | History | Annotate | Download | only in translit 
      1 /* GENERATED SOURCE. DO NOT MODIFY. */
      2 /*
      3  *******************************************************************************
      4  * Copyright (C) 2009-2014, Google, International Business Machines Corporation and
      5  * others. All Rights Reserved.
      6  *******************************************************************************
      7  */
      8 package android.icu.dev.test.translit;
      9 
     10 import android.icu.dev.test.TestFmwk;
     11 import android.icu.lang.UScript;
     12 import android.icu.text.Transliterator;
     13 import android.icu.text.UTF16;
     14 import android.icu.text.UnicodeSet;
     15 import android.icu.text.UnicodeSetIterator;
     16 import android.icu.util.ULocale;
     17 import org.junit.runner.RunWith;
     18 import android.icu.junit.IcuTestFmwkRunner;
     19 
     20 /**
     21  * @author markdavis
     22  *
     23  */
     24 @RunWith(IcuTestFmwkRunner.class)
     25 public class AnyScriptTest extends TestFmwk {
     26     public static void main(String[] args) throws Exception {
     27         new AnyScriptTest().run(args);
     28     }
     29 
     30     public void TestContext() {
     31         Transliterator t = Transliterator.createFromRules("foo", "::[bc]; a{b}d > B;", Transliterator.FORWARD);
     32         String sample = "abd abc b";
     33         assertEquals("context works", "aBd abc b", t.transform(sample));
     34     }
     35 
     36     public void TestScripts(){
     37         // get a couple of characters of each script for testing
     38 
     39         StringBuffer testBuffer = new StringBuffer();
     40         for (int script = 0; script < UScript.CODE_LIMIT; ++script) {
     41             UnicodeSet test = new UnicodeSet().applyPropertyAlias("script", UScript.getName(script));
     42             int count = Math.min(20, test.size());
     43             for (int i = 0; i < count; ++i){
     44                 testBuffer.append(UTF16.valueOf(test.charAt(i)));
     45             }
     46         }
     47         String test = testBuffer.toString();
     48         logln("Test line: " + test);
     49 
     50         int inclusion = getInclusion();
     51         boolean testedUnavailableScript = false;
     52 
     53         for (int script = 0; script < UScript.CODE_LIMIT; ++script) {
     54             if (script == UScript.COMMON || script == UScript.INHERITED) {
     55                 continue;
     56             }
     57             // if the inclusion rate is not 10, skip all but a small number of items.
     58             // Make sure, however, that we test at least one unavailable script
     59             if (inclusion < 10 && script != UScript.LATIN
     60                     && script != UScript.HAN
     61                     && script != UScript.HIRAGANA
     62                     && testedUnavailableScript
     63                     ) {
     64                 continue;
     65             }
     66 
     67             String scriptName = UScript.getName(script);  // long name
     68             ULocale locale = new ULocale(scriptName);
     69             if (locale.getLanguage().equals("new") || locale.getLanguage().equals("pau")) {
     70                 if (logKnownIssue("11171",
     71                         "long script name loosely looks like a locale ID with a known likely script")) {
     72                     continue;
     73                 }
     74             }
     75             Transliterator t;
     76             try {
     77                 t = Transliterator.getInstance("any-" + scriptName);
     78             } catch (Exception e) {
     79                 testedUnavailableScript = true;
     80                 logln("Skipping unavailable: " + scriptName);
     81                 continue; // we don't handle all scripts
     82             }
     83             logln("Checking: " + scriptName);
     84             if (t != null) {
     85                 t.transform(test); // just verify we don't crash
     86             }
     87             String shortScriptName = UScript.getShortName(script);  // 4-letter script code
     88             try {
     89                 t = Transliterator.getInstance("any-" + shortScriptName);
     90             } catch (Exception e) {
     91                 errln("Transliterator.getInstance() worked for \"any-" + scriptName +
     92                         "\" but not for \"any-" + shortScriptName + '\"');
     93             }
     94             t.transform(test); // just verify we don't crash
     95         }
     96     }
     97 
     98     /**
     99      * Check to make sure that wide characters are converted when going to narrow scripts.
    100      */
    101     public void TestForWidth(){
    102         Transliterator widen = Transliterator.getInstance("halfwidth-fullwidth");
    103         Transliterator narrow = Transliterator.getInstance("fullwidth-halfwidth");
    104         UnicodeSet ASCII = new UnicodeSet("[:ascii:]");
    105         String lettersAndSpace = "abc def";
    106         final String punctOnly = "( )";
    107 
    108         String wideLettersAndSpace = widen.transform(lettersAndSpace);
    109         String widePunctOnly = widen.transform(punctOnly);
    110         assertContainsNone("Should be wide", ASCII, wideLettersAndSpace);
    111         assertContainsNone("Should be wide", ASCII, widePunctOnly);
    112 
    113         String back;
    114         back = narrow.transform(wideLettersAndSpace);
    115         assertEquals("Should be narrow", lettersAndSpace, back);
    116         back = narrow.transform(widePunctOnly);
    117         assertEquals("Should be narrow", punctOnly, back);
    118 
    119         Transliterator latin = Transliterator.getInstance("any-Latn");
    120         back = latin.transform(wideLettersAndSpace);
    121         assertEquals("Should be ascii", lettersAndSpace, back);
    122 
    123         back = latin.transform(widePunctOnly);
    124         assertEquals("Should be ascii", punctOnly, back);
    125 
    126         // Han-Latin is now forward-only per CLDR ticket #5630
    127         //Transliterator t2 = Transliterator.getInstance("any-Han");
    128         //back = t2.transform(widePunctOnly);
    129         //assertEquals("Should be same", widePunctOnly, back);
    130 
    131 
    132     }
    133 
    134     public void TestCommonDigits() {
    135         UnicodeSet westernDigitSet = new UnicodeSet("[0-9]");
    136         UnicodeSet westernDigitSetAndMarks = new UnicodeSet("[[0-9][:Mn:]]");
    137         UnicodeSet arabicDigitSet = new UnicodeSet("[[:Nd:]&[:block=Arabic:]]");
    138         Transliterator latin = Transliterator.getInstance("Any-Latn");
    139         Transliterator arabic = Transliterator.getInstance("Any-Arabic");
    140         String westernDigits = getList(westernDigitSet);
    141         String arabicDigits = getList(arabicDigitSet);
    142 
    143         String fromArabic = latin.transform(arabicDigits);
    144         assertContainsAll("Any-Latin transforms Arabic digits", westernDigitSetAndMarks, fromArabic);
    145         if (false) { // we don't require conversion to Arabic digits
    146             String fromLatin = arabic.transform(westernDigits);
    147             assertContainsAll("Any-Arabic transforms Western digits", arabicDigitSet, fromLatin);
    148         }
    149     }
    150 
    151     // might want to add to TestFmwk
    152     private void assertContainsAll(String message, UnicodeSet set, String string) {
    153         handleAssert(set.containsAll(string), message, set, string, "contains all of", false);
    154     }
    155 
    156     private void assertContainsNone(String message, UnicodeSet set, String string) {
    157         handleAssert(set.containsNone(string), message, set, string, "contains none of", false);
    158     }
    159 
    160     // might want to add to UnicodeSet
    161     private String getList(UnicodeSet set) {
    162         StringBuffer result = new StringBuffer();
    163         for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {
    164             result.append(it.getString());
    165         }
    166         return result.toString();
    167     }
    168 }
    169