Java UScript.HIRAGANA属性代码示例

/**
 * fast version of UScript.getScript(). Basic Latin is an array lookup
 */
private int getScript(int codepoint) {
    if (0 <= codepoint && codepoint < basicLatin.length) {
        return basicLatin[codepoint];
    } else {
        int script = UScript.getScript(codepoint);
        if (combineCJ) {
            if (script == UScript.HAN || script == UScript.HIRAGANA || script == UScript.KATAKANA) {
                return UScript.JAPANESE;
            } else if (codepoint >= 0xFF10 && codepoint <= 0xFF19) {
                // when using CJK dictionary breaking, don't let full width numbers go to it, otherwise
                // they are treated as punctuation. we currently have no cleaner way to fix this!
                return UScript.LATIN;
            } else {
                return script;
            }
        } else {
            return script;
        }
    }
}
 

/** fast version of UScript.getScript(). Basic Latin is an array lookup */
private int getScript(int codepoint) {
  if (0 <= codepoint && codepoint < basicLatin.length) {
    return basicLatin[codepoint];
  } else {
    int script = UScript.getScript(codepoint);
    if (combineCJ) {
      if (script == UScript.HAN || script == UScript.HIRAGANA || script == UScript.KATAKANA) {
        return UScript.JAPANESE;
      } else if (codepoint >= 0xFF10 && codepoint <= 0xFF19) {
        // when using CJK dictionary breaking, don't let full width numbers go to it, otherwise
        // they are treated as punctuation. we currently have no cleaner way to fix this!
        return UScript.LATIN; 
      } else {
        return script;
      }
    } else {
      return script;
    }
  }
}
 

@Override
public String getType(int script, int ruleStatus) {
    switch (ruleStatus) {
        case RuleBasedBreakIterator.WORD_IDEO:
            return WORD_IDEO;
        case RuleBasedBreakIterator.WORD_KANA:
            return script == UScript.HIRAGANA ? WORD_HIRAGANA : WORD_KATAKANA;
        case RuleBasedBreakIterator.WORD_LETTER:
            return script == UScript.HANGUL ? WORD_HANGUL : WORD_LETTER;
        case RuleBasedBreakIterator.WORD_NUMBER:
            return WORD_NUMBER;
        default: /* some other custom code */
            return "<OTHER>";
    }
}
 

@Override
public String getType(int script, int ruleStatus) {
  switch (ruleStatus) {
    case RuleBasedBreakIterator.WORD_IDEO:
      return WORD_IDEO;
    case RuleBasedBreakIterator.WORD_KANA:
      return script == UScript.HIRAGANA ? WORD_HIRAGANA : WORD_KATAKANA;
    case RuleBasedBreakIterator.WORD_LETTER:
      return script == UScript.HANGUL ? WORD_HANGUL : WORD_LETTER;
    case RuleBasedBreakIterator.WORD_NUMBER:
      return WORD_NUMBER;
    default: /* some other custom code */
      return "<OTHER>";
  }
}
 

private LanguageBreakEngine getLanguageBreakEngine(int c) {

        // We have a dictionary character.
        // Does an already instantiated break engine handle it?
        for (LanguageBreakEngine candidate : fBreakEngines.values()) {
            if (candidate.handles(c, fBreakType)) {
                return candidate;
            }
        }

        // if we don't have an existing engine, build one.
        int script = UCharacter.getIntPropertyValue(c, UProperty.SCRIPT);
        if (script == UScript.KATAKANA || script == UScript.HIRAGANA) {
            // Katakana, Hiragana and Han are handled by the same dictionary engine.
            // Fold them together for mapping from script -> engine.
            script = UScript.HAN;
        }

        LanguageBreakEngine eng = fBreakEngines.get(script);
        /*
        if (eng != null && !eng.handles(c, fBreakType)) {
            fUnhandledBreakEngine.handleChar(c, getBreakType());
            eng = fUnhandledBreakEngine;
        } else  */  {
            try {
                switch (script) {
                case UScript.THAI:
                    eng = new ThaiBreakEngine();
                    break;
                case UScript.LAO:
                    eng = new LaoBreakEngine();
                    break;
                case UScript.MYANMAR:
                    eng = new BurmeseBreakEngine();
                    break;
                case UScript.KHMER:
                    eng = new KhmerBreakEngine();
                    break;
                case UScript.HAN:
                    if (getBreakType() == KIND_WORD) {
                        eng = new CjkBreakEngine(false);
                    }
                    else {
                        fUnhandledBreakEngine.handleChar(c, getBreakType());
                        eng = fUnhandledBreakEngine;
                    }
                    break;
                case UScript.HANGUL:
                    if (getBreakType() == KIND_WORD) {
                        eng = new CjkBreakEngine(true);
                    } else {
                        fUnhandledBreakEngine.handleChar(c, getBreakType());
                        eng = fUnhandledBreakEngine;
                    }
                    break;
                default:
                    fUnhandledBreakEngine.handleChar(c, getBreakType());
                    eng = fUnhandledBreakEngine;
                    break;
                }
            } catch (IOException e) {
                eng = null;
            }
        }

        if (eng != null && eng != fUnhandledBreakEngine) {
            LanguageBreakEngine existingEngine = fBreakEngines.putIfAbsent(script, eng);
            if (existingEngine != null) {
                // There was a race & another thread was first to register an engine for this script.
                // Use theirs and discard the one we just created.
                eng = existingEngine;
            }
            // assert eng.handles(c, fBreakType);
        }
        return eng;
    }
 

/**
 * @param targetScript2
 * @return
 */
private boolean isWide(int script) {
    return script == UScript.BOPOMOFO || script == UScript.HAN || script == UScript.HANGUL || script == UScript.HIRAGANA || script == UScript.KATAKANA;
}