Package com.ibm.icu.text

Examples of com.ibm.icu.text.Transliterator$Position

21
22
23
24
25
26
27
28
29
    public static void main(String[] args) throws Exception {
        new AnyScriptTest().run(args);
    }
   
    public void TestContext() {
        Transliterator t = Transliterator.createFromRules("foo", "::[bc]; a{b}d > B;", Transliterator.FORWARD);
        String sample = "abd abc b";
        assertEquals("context works", "aBd abc b", t.transform(sample));
    }
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
                    ) {
                continue;
            }
           
            String scriptName = UScript.getName(script);
            Transliterator t;
            try {
                t = Transliterator.getInstance("any-" + scriptName);
            } catch (Exception e) {
                testedUnavailableScript = true;
                logln("Skipping unavailable: " + scriptName);
                continue; // we don't handle all scripts
            }
            logln("Checking: " + scriptName);
            if (t != null) {
                t.transform(test); // just verify we don't crash
            }
            scriptName = UScript.getShortName(script);
            t = Transliterator.getInstance("any-" + scriptName);
            t.transform(test); // just verify we don't crash
        }
    }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
   
    /**
     * Check to make sure that wide characters are converted when going to narrow scripts.
     */
    public void TestForWidth(){
        Transliterator widen = Transliterator.getInstance("halfwidth-fullwidth");
        Transliterator narrow = Transliterator.getInstance("fullwidth-halfwidth");
        UnicodeSet ASCII = new UnicodeSet("[:ascii:]");
        String lettersAndSpace = "abc def";
        final String punctOnly = "( )";
       
        String wideLettersAndSpace = widen.transform(lettersAndSpace);
        String widePunctOnly = widen.transform(punctOnly);
        assertContainsNone("Should be wide", ASCII, wideLettersAndSpace);
        assertContainsNone("Should be wide", ASCII, widePunctOnly);
       
        String back;
        back = narrow.transform(wideLettersAndSpace);
        assertEquals("Should be narrow", lettersAndSpace, back);
        back = narrow.transform(widePunctOnly);
        assertEquals("Should be narrow", punctOnly, back);
       
        Transliterator latin = Transliterator.getInstance("any-Latn");
        back = latin.transform(wideLettersAndSpace);
        assertEquals("Should be ascii", lettersAndSpace, back);
       
        back = latin.transform(widePunctOnly);
        assertEquals("Should be ascii", punctOnly, back);
      
        Transliterator t2 = Transliterator.getInstance("any-Han");
        back = t2.transform(widePunctOnly);
        assertEquals("Should be same", widePunctOnly, back);


    }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
   
    public void TestCommonDigits() {
        UnicodeSet westernDigitSet = new UnicodeSet("[0-9]");
        UnicodeSet westernDigitSetAndMarks = new UnicodeSet("[[0-9][:Mn:]]");
        UnicodeSet arabicDigitSet = new UnicodeSet("[[:Nd:]&[:block=Arabic:]]");
        Transliterator latin = Transliterator.getInstance("Any-Latn");
        Transliterator arabic = Transliterator.getInstance("Any-Arabic");
        String westernDigits = getList(westernDigitSet);
        String arabicDigits = getList(arabicDigitSet);

        String fromArabic = latin.transform(arabicDigits);
        assertContainsAll("Any-Latin transforms Arabic digits", westernDigitSetAndMarks, fromArabic);
        if (false) { // we don't require conversion to Arabic digits
            String fromLatin = arabic.transform(westernDigits);
            assertContainsAll("Any-Arabic transforms Western digits", arabicDigitSet, fromLatin);
        }
    }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
    checkToken(Transliterator.createFromRules("test", rules, Transliterator.FORWARD), "caa", "cbd");
  }
 
  public void testOptimizer() throws Exception {
    String rules = "a > b; b > c;"; // convert a's to b's and b's to c's
    Transliterator custom = Transliterator.createFromRules("test", rules, Transliterator.FORWARD);
    assertTrue(custom.getFilter() == null);
    new ICUTransformFilter(new KeywordTokenizer(new StringReader("")), custom);
    assertTrue(custom.getFilter().equals(new UnicodeSet("[ab]")));
  }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
        "ABCDE", "abcde");
  }
 
  public void testOptimizerSurrogate() throws Exception {
    String rules = "\\U00020087 > x;"; // convert CJK UNIFIED IDEOGRAPH-20087 to an x
    Transliterator custom = Transliterator.createFromRules("test", rules, Transliterator.FORWARD);
    assertTrue(custom.getFilter() == null);
    new ICUTransformFilter(new KeywordTokenizer(new StringReader("")), custom);
    assertTrue(custom.getFilter().equals(new UnicodeSet("[\\U00020087]")));
  }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
    assertTokenStreamContents(ts, new String[] { expected });
  }
 
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    final Transliterator transform = Transliterator.getInstance("Any-Latin");
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new ICUTransformFilter(tokenizer, transform));
View Full Code Here
63
64
65
66
67
68
69
70
71
72
    checkToken(Transliterator.createFromRules("test", rules, Transliterator.FORWARD), "caa", "cbd");
  }
 
  public void testOptimizer() throws Exception {
    String rules = "a > b; b > c;"; // convert a's to b's and b's to c's
    Transliterator custom = Transliterator.createFromRules("test", rules, Transliterator.FORWARD);
    assertTrue(custom.getFilter() == null);
    new ICUTransformFilter(new KeywordTokenizer(new StringReader("")), custom);
    assertTrue(custom.getFilter().equals(new UnicodeSet("[ab]")));
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
        "ABCDE", "abcde");
  }
 
  public void testOptimizerSurrogate() throws Exception {
    String rules = "\\U00020087 > x;"; // convert CJK UNIFIED IDEOGRAPH-20087 to an x
    Transliterator custom = Transliterator.createFromRules("test", rules, Transliterator.FORWARD);
    assertTrue(custom.getFilter() == null);
    new ICUTransformFilter(new KeywordTokenizer(new StringReader("")), custom);
    assertTrue(custom.getFilter().equals(new UnicodeSet("[\\U00020087]")));
  }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
    assertTokenStreamContents(ts, new String[] { expected });
  }
 
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    final Transliterator transform = Transliterator.getInstance("Any-Latin");
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new ICUTransformFilter(tokenizer, transform));
View Full Code Here
TOP

Related Classes of com.ibm.icu.text.Transliterator$Position

  • ca.uhn.fhir.model.primitive.DecimalDt
  • com.google.gdt.eclipse.designer.uibinder.model.widgets.WidgetInfo
  • com.ibm.icu.dev.demo.translit.TransliterationChart
  • com.ibm.icu.dev.test.translit.AnyScriptTest
  • com.ibm.icu.dev.test.util.TransliteratorUtilities
  • com.ibm.icu.impl.ICUResourceBundle
  • com.ibm.icu.text.RuleBasedTransliterator.Data
  • com.ibm.icu.util.CaseInsensitiveString
  • com.sun.tools.classfile.TypeAnnotation.Position.TypePathEntry
  • org.apache.lucene.analysis.icu.TestICUTransformFilter
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.