Package com.ibm.icu.text

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

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 WhitespaceTokenizer(TEST_VERSION_CURRENT, reader);
        return new TokenStreamComponents(tokenizer, new ICUTransformFilter(tokenizer, transform));
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
118
        return !Boolean.parseBoolean(obj.toString());
    }

    public static String cleanString(String str) {

        Transliterator accentsconverter = Transliterator.getInstance("Latin; NFD; [:Nonspacing Mark:] Remove; NFC;");

        str = accentsconverter.transliterate(str);

        // the character ? seems to not be changed to d by the transliterate function

        StringBuffer cleanedStr = new StringBuffer(str.trim());
        // delete special character
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
118
119
120
121
122
123
124
125
126
127
128
129
130
   }

   public static String cleanString(String str)
   {

      Transliterator accentsconverter = Transliterator.getInstance("Latin; NFD; [:Nonspacing Mark:] Remove; NFC;");

      str = accentsconverter.transliterate(str);

      //the character ? seems to not be changed to d by the transliterate function

      StringBuffer cleanedStr = new StringBuffer(str.trim());
      // delete special character
View Full Code Here
20
21
22
23
24
25
26
27
28
29
30
    public static void registerTransliteratorFromFile(String dir, String id) {
        try {
            String filename = id.replace('-', '_') +  ".txt";
            String rules = getFileContents(dir, filename);
            Transliterator t;
            int pos = id.indexOf('-');
            String rid;
            if (pos < 0) {
                rid = id + "-Any";
                id = "Any-" + id;
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
        pw.println("td { text-align: Center; font-size: 200% }");
        pw.println("tt { font-size: 50% }");
        pw.println("td.miss { background-color: #CCCCFF }");
        pw.println("</style></head><body bgcolor='#FFFFFF'>");

        Transliterator anyToLatin = Transliterator.getInstance("any-latin");
       
        String testString = "\u0946\u093E";
       
        UnicodeSet failNorm = new UnicodeSet();
        Set latinFail = new TreeSet();
       
        for (int i = 0; i < indicScripts.length; ++i) {
            if (indicScripts[i] == UScript.LATIN) continue;
            String source = names[i];
            System.out.println(source);
            UnicodeSet sourceChars = sets[i];

            for (int j = 0; j < indicScripts.length; ++j) {
                if (i == j) continue;
                String target = names[j];
                Transliterator forward = Transliterator.getInstance(source + '-' + target);
                Transliterator backward = forward.getInverse();
                UnicodeSetIterator it = new UnicodeSetIterator(sourceChars);
                while (it.next()) {
                    if (lengthMarks.contains(it.codepoint)) continue;
                    String s = Normalizer.normalize(it.codepoint,Normalizer.NFC,0);
                    //if (!Normalizer.isNormalized(s,Normalizer.NFC,0)) continue;
                    if (!s.equals(Normalizer.normalize(s,Normalizer.NFD,0))) {
                        failNorm.add(it.codepoint);
                    }
                    String t = fix(forward.transliterate(s));
                    if (t.equals(testString)) {
                        System.out.println("debug");
                    }

                    String r = fix(backward.transliterate(t));
                    if (Normalizer.compare(s,r,0) == 0) {
                        if (indicScripts[j] != UScript.LATIN) eq.add(s,t);
                    } else {
                        if (indicScripts[j] == UScript.LATIN) {
                            latinFail.add(s + " - " + t + " - " + r);
View Full Code Here
TOP

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

  • asia.redact.bracket.properties.alt.DotPropertiesParser
  • asia.redact.bracket.properties.line.LineScanner
  • asia.redact.bracket.properties.mgmt.Attributes
  • asia.redact.bracket.properties.mgmt.LoadList
  • avrora.sim.clock.ClockDomain
  • avrora.sim.mcu.ATMega128
  • backtype.storm.tuple.Values
  • com.eviware.soapui.impl.wadl.inference.schema.content.EmptyContent
  • com.eviware.soapui.impl.wadl.inference.schema.particles.AttributeParticle
  • com.eviware.soapui.impl.wadl.inference.schema.particles.ElementParticle
    • 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.