当前位置: 首页>>代码示例>>Java>>正文

Java UnicodeBlock.GENERAL_PUNCTUATION属性代码示例

本文整理汇总了Java中java.lang.Character.UnicodeBlock.GENERAL_PUNCTUATION属性的典型用法代码示例。如果您正苦于以下问题：Java UnicodeBlock.GENERAL_PUNCTUATION属性的具体用法？Java UnicodeBlock.GENERAL_PUNCTUATION怎么用？Java UnicodeBlock.GENERAL_PUNCTUATION使用的例子？那么, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类java.lang.Character.UnicodeBlock的用法示例。


在下文中一共展示了UnicodeBlock.GENERAL_PUNCTUATION属性的6个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。

示例1: normalize

/**
 * Character Normalization
 *
 * @param ch character to normalize
 * @return Normalized character
 */
static public char normalize(char ch) {
    Character.UnicodeBlock block = Character.UnicodeBlock.of(ch);
    if (block == UnicodeBlock.BASIC_LATIN) {
        if (ch < 'A' || (ch < 'a' && ch > 'Z') || ch > 'z') ch = ' ';
    } else if (block == UnicodeBlock.LATIN_1_SUPPLEMENT) {
        if (LATIN1_EXCLUDED.indexOf(ch) >= 0) ch = ' ';
    } else if (block == UnicodeBlock.LATIN_EXTENDED_B) {
        // normalization for Romanian
        if (ch == '\u0219') ch = '\u015f';  // Small S with comma below => with cedilla
        if (ch == '\u021b') ch = '\u0163';  // Small T with comma below => with cedilla
    } else if (block == UnicodeBlock.GENERAL_PUNCTUATION) {
        ch = ' ';
    } else if (block == UnicodeBlock.ARABIC) {
        if (ch == '\u06cc') ch = '\u064a';  // Farsi yeh => Arabic yeh
    } else if (block == UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) {
        if (ch >= '\u1ea0') ch = '\u1ec3';
    } else if (block == UnicodeBlock.HIRAGANA) {
        ch = '\u3042';
    } else if (block == UnicodeBlock.KATAKANA) {
        ch = '\u30a2';
    } else if (block == UnicodeBlock.BOPOMOFO || block == UnicodeBlock.BOPOMOFO_EXTENDED) {
        ch = '\u3105';
    } else if (block == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {
        if (cjk_map.containsKey(ch)) ch = cjk_map.get(ch);
    } else if (block == UnicodeBlock.HANGUL_SYLLABLES) {
        ch = '\uac00';
    }
    return ch;
}
开发者ID:malcolmgreaves，项目名称:language-detection，代码行数:35，代码来源:NGram.java

示例2: isChinese

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||
		ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS)
		return true;
	return false;
}
开发者ID:FudanNLP，项目名称:fnlp，代码行数:11，代码来源:LangDetection.java

示例3: normalize

/**
 * Character Normalization
 * @param ch
 * @return Normalized character
 */
static public char normalize(char ch) {
    Character.UnicodeBlock block = Character.UnicodeBlock.of(ch);
    if (block == UnicodeBlock.BASIC_LATIN) {
        if (ch<'A' || (ch<'a' && ch >'Z') || ch>'z') ch = ' ';
    } else if (block == UnicodeBlock.LATIN_1_SUPPLEMENT) {
        if (LATIN1_EXCLUDED.indexOf(ch)>=0) ch = ' ';
    } else if (block == UnicodeBlock.LATIN_EXTENDED_B) {
        // normalization for Romanian
        if (ch == '\u0219') ch = '\u015f';  // Small S with comma below => with cedilla
        if (ch == '\u021b') ch = '\u0163';  // Small T with comma below => with cedilla
    } else if (block == UnicodeBlock.GENERAL_PUNCTUATION) {
        ch = ' ';
    } else if (block == UnicodeBlock.ARABIC) {
        if (ch == '\u06cc') ch = '\u064a';  // Farsi yeh => Arabic yeh
    } else if (block == UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) {
        if (ch >= '\u1ea0') ch = '\u1ec3';
    } else if (block == UnicodeBlock.HIRAGANA) {
        ch = '\u3042';
    } else if (block == UnicodeBlock.KATAKANA) {
        ch = '\u30a2';
    } else if (block == UnicodeBlock.BOPOMOFO || block == UnicodeBlock.BOPOMOFO_EXTENDED) {
        ch = '\u3105';
    } else if (block == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {
        if (cjk_map.containsKey(ch)) ch = cjk_map.get(ch);
    } else if (block == UnicodeBlock.HANGUL_SYLLABLES) {
        ch = '\uac00';
    }
    return ch;
}
开发者ID:deezer，项目名称:weslang，代码行数:34，代码来源:NGram.java

示例4: normalize

public static char normalize(char c) {
    char ch = c;
    Character.UnicodeBlock block = Character.UnicodeBlock.of(ch);
    if (block == UnicodeBlock.BASIC_LATIN) {
        if (ch < 'A' || (ch < 'a' && ch > 'Z') || ch > 'z') {
            ch = ' ';
        }
    } else if (block == UnicodeBlock.LATIN_1_SUPPLEMENT) {
        if (LATIN1_EXCLUDED.indexOf(ch) >= 0) {
            ch = ' ';
        }
    } else if (block == UnicodeBlock.GENERAL_PUNCTUATION) {
        ch = ' ';
    } else if (block == UnicodeBlock.ARABIC) {
        if (ch == '\u06cc') {
            ch = '\u064a';
        }
    } else if (block == UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) {
        if (ch >= '\u1ea0') {
            ch = '\u1ec3';
        }
    } else if (block == UnicodeBlock.HIRAGANA) {
        ch = '\u3042';
    } else if (block == UnicodeBlock.KATAKANA) {
        ch = '\u30a2';
    } else if (block == UnicodeBlock.BOPOMOFO || block == UnicodeBlock.BOPOMOFO_EXTENDED) {
        ch = '\u3105';
    } else if (block == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {
        if (cjk_map.containsKey(ch)) {
            ch = cjk_map.get(ch);
        }
    } else if (block == UnicodeBlock.HANGUL_SYLLABLES) {
        ch = '\uac00';
    }
    return ch;
}
开发者ID:jprante，项目名称:elasticsearch-plugin-bundle，代码行数:36，代码来源:NGram.java

示例5: normalize

public static char normalize(char ch) {
    Character.UnicodeBlock block = Character.UnicodeBlock.of(ch);
    if (block == UnicodeBlock.BASIC_LATIN) {
        if (ch < 'A' || (ch < 'a' && ch > 'Z') || ch > 'z') {
            ch = ' ';
        }
    } else if (block == UnicodeBlock.LATIN_1_SUPPLEMENT) {
        if (LATIN1_EXCLUDED.indexOf(ch) >= 0) {
            ch = ' ';
        }
    } else if (block == UnicodeBlock.GENERAL_PUNCTUATION) {
        ch = ' ';
    } else if (block == UnicodeBlock.ARABIC) {
        if (ch == '\u06cc') {
            ch = '\u064a';
        }
    } else if (block == UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) {
        if (ch >= '\u1ea0') {
            ch = '\u1ec3';
        }
    } else if (block == UnicodeBlock.HIRAGANA) {
        ch = '\u3042';
    } else if (block == UnicodeBlock.KATAKANA) {
        ch = '\u30a2';
    } else if (block == UnicodeBlock.BOPOMOFO || block == UnicodeBlock.BOPOMOFO_EXTENDED) {
        ch = '\u3105';
    } else if (block == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {
        if (cjk_map.containsKey(ch)) {
            ch = cjk_map.get(ch);
        }
    } else if (block == UnicodeBlock.HANGUL_SYLLABLES) {
        ch = '\uac00';
    }
    return ch;
}
开发者ID:jprante，项目名称:elasticsearch-analysis-german，代码行数:35，代码来源:NGram.java

示例6: normalize

/**
 * Character Normalization
 * @param ch character
 * @return Normalized character
 */
public static char normalize(char ch) {
    final Character.UnicodeBlock block = Character.UnicodeBlock.of(ch);
    if (block == UnicodeBlock.BASIC_LATIN) {
        if (ch < 'A' || (ch < 'a' && ch > 'Z') || ch > 'z') {
            ch = ' ';
        }
    } else if (block == UnicodeBlock.LATIN_1_SUPPLEMENT) {
        if (LATIN1_EXCLUDED.indexOf(ch) >= 0) {
            ch = ' ';
        }
    } else if (block == UnicodeBlock.LATIN_EXTENDED_B) {
        // normalization for Romanian
        if (ch == '\u0219') {
            ch = '\u015f'; // Small S with comma below => with cedilla
        }
        if (ch == '\u021b') {
            ch = '\u0163'; // Small T with comma below => with cedilla
        }
    } else if (block == UnicodeBlock.GENERAL_PUNCTUATION) {
        ch = ' ';
    } else if (block == UnicodeBlock.ARABIC) {
        if (ch == '\u06cc') {
            ch = '\u064a'; // Farsi yeh => Arabic yeh
        }
    } else if (block == UnicodeBlock.LATIN_EXTENDED_ADDITIONAL) {
        if (ch >= '\u1ea0') {
            ch = '\u1ec3';
        }
    } else if (block == UnicodeBlock.HIRAGANA) {
        ch = '\u3042';
    } else if (block == UnicodeBlock.KATAKANA) {
        ch = '\u30a2';
    } else if (block == UnicodeBlock.BOPOMOFO
            || block == UnicodeBlock.BOPOMOFO_EXTENDED) {
        ch = '\u3105';
    } else if (block == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {
        if (cjkMap.containsKey(ch)) {
            ch = cjkMap.get(ch);
        }
    } else if (block == UnicodeBlock.HANGUL_SYLLABLES) {
        ch = '\uac00';
    }
    return ch;
}
开发者ID:codelibs，项目名称:elasticsearch-langfield，代码行数:49，代码来源:NGram.java


注：本文中的java.lang.Character.UnicodeBlock.GENERAL_PUNCTUATION属性示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。