Package java.lang.Character

Examples of java.lang.Character.UnicodeBlock

619
620
621
622
623
624
625
626
627
628
629
              } catch (IllegalArgumentException e) {
                // ok
              }
           
              try {
                UnicodeBlock found = UnicodeBlock.forName(predefined);
                javaPredefName = "In" + predefined;
              } catch (IllegalArgumentException e) {
                // ok
              }
             
View Full Code Here
18
19
20
21
22
23
24
25
26
27
28
      char ch = myBuffer[i];
      if ((int) ch < 10) {
        sb.append("\\u000" + (int) ch);
        continue;
      }
      UnicodeBlock ub = UnicodeBlock.of(ch);
      if (ub == UnicodeBlock.BASIC_LATIN) {
        // 英文及数字等
        sb.append(myBuffer[i]);
      } else if (ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
        // 全角半角字符
View Full Code Here
289
290
291
292
293
294
295
296
297
298
299
300
301
  static boolean isLatinLetter(char letter) {
    // Combining marks are a subset of non-spacing-mark.
    if (!Character.isLetter(letter) && Character.getType(letter) != Character.NON_SPACING_MARK) {
      return false;
    }
    UnicodeBlock block = UnicodeBlock.of(letter);
    return block.equals(UnicodeBlock.BASIC_LATIN) ||
        block.equals(UnicodeBlock.LATIN_1_SUPPLEMENT) ||
        block.equals(UnicodeBlock.LATIN_EXTENDED_A) ||
        block.equals(UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) ||
        block.equals(UnicodeBlock.LATIN_EXTENDED_B) ||
        block.equals(UnicodeBlock.COMBINING_DIACRITICAL_MARKS);
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
    }
    return false;
  }
 
  private static boolean isChinese(char c) {
    UnicodeBlock ub = UnicodeBlock.of(c);
    if(ub==UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS ||
      ub == UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS||
      ub == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A||
      ub == UnicodeBlock.GENERAL_PUNCTUATION||
      ub == UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION||
View Full Code Here
270
271
272
273
274
275
276
277
278
279
280
281
282
  static boolean isLatinLetter(char letter) {
    // Combining marks are a subset of non-spacing-mark.
    if (!Character.isLetter(letter) && Character.getType(letter) != Character.NON_SPACING_MARK) {
      return false;
    }
    UnicodeBlock block = UnicodeBlock.of(letter);
    return block.equals(UnicodeBlock.BASIC_LATIN) ||
        block.equals(UnicodeBlock.LATIN_1_SUPPLEMENT) ||
        block.equals(UnicodeBlock.LATIN_EXTENDED_A) ||
        block.equals(UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) ||
        block.equals(UnicodeBlock.LATIN_EXTENDED_B) ||
        block.equals(UnicodeBlock.COMBINING_DIACRITICAL_MARKS);
  }
View Full Code Here
156
157
158
159
160
161
162
163
164
165
166
    private String checkASCIIString(String string) {
        StringBuffer buf = new StringBuffer();

        for (int i = 0; i < string.length(); i++) {
            UnicodeBlock characterBlock = UnicodeBlock.of(string.charAt(i));
            if (characterBlock == UnicodeBlock.BASIC_LATIN) {
                buf.append(string.charAt(i));
            } else {
                buf.append('_');
            }
View Full Code Here
213
214
215
216
217
218
219
220
221
222
223
    public String getUnicodeBlockDistribution(String text)
    {
        HashMap<Character.UnicodeBlock, Integer> map = new HashMap<Character.UnicodeBlock, Integer>();
        for (int i=0; i<text.length(); i++)
        {
            UnicodeBlock ub = Character.UnicodeBlock.of(text.charAt(i));
            if (ub!=null)
            {
                if (map.containsKey(ub))
                    map.put(ub, map.get(ub)+1);
                else
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
      + "\\p{InCombiningDiacriticalMarks}]");

  private static UnicodeBlock getBlock(final String word)
  {
    final int c = word.codePointAt(0);
    final UnicodeBlock block = UnicodeBlock.of(c);
    if (block == UnicodeBlock.BASIC_LATIN && HYPEREXTENDED_LATIN.matcher(word).find())
    {
      return UnicodeBlock.LATIN_EXTENDED_A;
    }
    if (block == UnicodeBlock.BASIC_LATIN && EXTENDED_LATIN.matcher(word).find())
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
    boolean hasExtendedLatin = false;
    boolean hasHyperextendedLatin = false;
    final Counter<UnicodeBlock> counter = new Counter<UnicodeBlock>();
    for (final String word : words)
    {
      final UnicodeBlock block = getBlock(word);
      if (block == UnicodeBlock.LATIN_1_SUPPLEMENT)
      {
        hasExtendedLatin = true;
      }
      if (block == UnicodeBlock.LATIN_EXTENDED_A)
      {
        hasHyperextendedLatin = true;
      }
      counter.note(block);
    }
    final List<UnicodeBlock> mostFrequent = counter.getMostFrequent(1);
    if (mostFrequent.size() == 0)
    {
      return null;
    }
    UnicodeBlock b = mostFrequent.get(0);
    /*
     * If we've seen *any* extended latin, and we're mostly latin, then
     * treat the whole thing as extended.
     */
    if (b == UnicodeBlock.BASIC_LATIN || b == UnicodeBlock.LATIN_1_SUPPLEMENT)
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
            final String u = decode(bytes, "KOI8_U");
            if (! r.equals(u)) {
                differences++;
                final char rc = r.charAt(0);
                final char uc = u.charAt(0);
                final UnicodeBlock rcb = UnicodeBlock.of(rc);
                final UnicodeBlock ucb = UnicodeBlock.of(uc);
                System.out.printf("%02x => %04x %s, %04x %s%n",
                                  i, (int) rc, rcb, (int) uc, ucb);
                check(rcb == UnicodeBlock.BOX_DRAWING &&
                      ucb == UnicodeBlock.CYRILLIC);
            }
View Full Code Here
TOP

Related Classes of java.lang.Character.UnicodeBlock

  • com.github.stephenc.javaisotools.iso9660.impl.ISO9660Config
  • com.google.i18n.phonenumbers.PhoneNumberMatcher
  • cue.lang.unicode.BlockUtil
  • erjang.m.re.Native$Options
  • fr.eolya.extraction.CharsetLanguages
  • net.loyin.util.UnicodeTool
  • org.apache.jena.iri.impl.AbsLexer
  • org.fnlp.nlp.cn.LangDetection
  • UkrainianIsNotRussian
    • 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.