當前位置: 首頁>>代碼示例>>Java>>正文

Java UnicodeBlock.of方法代碼示例

本文整理匯總了Java中java.lang.Character.UnicodeBlock.of方法的典型用法代碼示例。如果您正苦於以下問題：Java UnicodeBlock.of方法的具體用法？Java UnicodeBlock.of怎麽用？Java UnicodeBlock.of使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類java.lang.Character.UnicodeBlock的用法示例。


在下文中一共展示了UnicodeBlock.of方法的15個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Java代碼示例。

示例1: removeDiacritics

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
/**
 * Remove diacritics from the specified string.
 * @param s
 * @return a copy of the specified string with diacritics removed.
 */
public static final String removeDiacritics(String s) {
	String n = Normalizer.normalize(s, Form.NFD);
	StringBuilder sb = null;
	for (int i = 0; i < n.length(); ++i) {
		char c = n.charAt(i);
		UnicodeBlock b = UnicodeBlock.of(c);
		if (UnicodeBlock.COMBINING_DIACRITICAL_MARKS.equals(b) || UnicodeBlock.COMBINING_DIACRITICAL_MARKS_SUPPLEMENT.equals(b)) {
			if (sb == null) {
				sb = new StringBuilder(n.length());
				sb.append(n.substring(0, i));
			}
			continue;
		}
		if (sb != null)
			sb.append(c);
	}
	if (sb == null)
		return n;
	return sb.toString();
}
開發者ID:Bibliome，項目名稱:bibliome-java-utils，代碼行數:26，代碼來源:Strings.java

示例2: utf8ToUnicode

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
/**
 * utf-8 轉unicode
 *
 * @param inStr
 * @return String
 */
public static String utf8ToUnicode(String inStr) {
    char[] myBuffer = inStr.toCharArray();
 
    StringBuffer sb = new StringBuffer();
    for (int i = 0; i < inStr.length(); i++) {
        UnicodeBlock ub = UnicodeBlock.of(myBuffer[i]);
        if (ub == UnicodeBlock.BASIC_LATIN) {
            sb.append(myBuffer[i]);
        } else if (ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
            int j = (int) myBuffer[i] - 65248;
            sb.append((char) j);
        } else {
            short s = (short) myBuffer[i];
            String hexS = Integer.toHexString(s);
            String unicode = "\\u" + hexS;
            sb.append(unicode.toLowerCase());
        }
    }
    return sb.toString().replaceAll("ffff", "");
}
開發者ID:AndroidStudioTranslate，項目名稱:Android-Studio-Translate-Tool，代碼行數:27，代碼來源:WordsTransfer.java

示例3: isChinese

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
public boolean isChinese(char c) {
		Set<UnicodeBlock> chineseUnicodeBlocks = new HashSet<UnicodeBlock>();
		chineseUnicodeBlocks.add(UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS);
//			add(UnicodeBlock.CJK_COMPATIBILITY);
//			add(UnicodeBlock.CJK_COMPATIBILITY_FORMS);
//			add(UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS);
//			add(UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT);
//			add(UnicodeBlock.CJK_RADICALS_SUPPLEMENT);
//			add(UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION);
//			add(UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS);
//			add(UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A);
//			add(UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B);
//			add(UnicodeBlock.KANGXI_RADICALS);
//			add(UnicodeBlock.IDEOGRAPHIC_DESCRIPTION_CHARACTERS);
		
		UnicodeBlock block = UnicodeBlock.of(c);
		return chineseUnicodeBlocks.contains(block);
	}
開發者ID:donkirkby，項目名稱:donkirkby，代碼行數:19，代碼來源:CharacterClassifier.java

示例4: tokenize

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
@Override
public List<String> tokenize(String text) {
	int beginIndex = -1;
	UnicodeBlock current = null;
	List<String> list = new LinkedList<>();
	for (int i = 0; i < text.length(); i++) {
		UnicodeBlock block = UnicodeBlock.of(text.charAt(i));
		if (current != block) {
			if (beginIndex >= 0) {
				list.add(text.substring(beginIndex, i));
			}
			beginIndex = i;
			current = block;
		}
	}
	if (beginIndex >= 0) {
		list.add(text.substring(beginIndex));
	}
	return list;
}
開發者ID:agwlvssainokuni，項目名稱:sqlapp，代碼行數:21，代碼來源:UnicodeBlockTokenizer.java

示例5: utf8ToUnicode

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
/**
 * utf-8 轉換成 unicode
 *
 * @param inStr
 * @return
 * @author fanhui
 * 2007-3-15
 */
public static String utf8ToUnicode(String inStr) {
    char[] myBuffer = inStr.toCharArray();

    StringBuffer sb = new StringBuffer();
    for (int i = 0; i < inStr.length(); i++) {
        UnicodeBlock ub = UnicodeBlock.of(myBuffer[i]);
        if (ub == UnicodeBlock.BASIC_LATIN) {
            //英文及數字等
            sb.append(myBuffer[i]);
        } else if (ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
            //全角半角字符
            int j = (int) myBuffer[i] - 65248;
            sb.append((char) j);
        } else {
            //漢字
            short s = (short) myBuffer[i];
            String hexS = Integer.toHexString(s);
            String unicode = "\\u" + hexS;
            sb.append(unicode.toLowerCase());
        }
    }
    return sb.toString();
}
開發者ID:blademainer，項目名稱:common_utils，代碼行數:32，代碼來源:UnicodeHelper.java

示例6: of

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
static public TTUnicodeRange of(long a_unicode) {
    initList();

    TTUnicodeRange retval = null;
    UnicodeBlock block = UnicodeBlock.of((int) a_unicode);
    if (block == null) {
        return retval;
    }

    int i;
    for (i = 0; i < s_list.size(); i++) {
        TTUnicodeRange range = s_list.get(i);
        if (range.m_block.equals(block)) {
            return range;
        }
    }

    return retval;
}
開發者ID:jindrapetrik，項目名稱:jpexs-decompiler，代碼行數:20，代碼來源:TTUnicodeRange.java

示例7: guessCJKNameStyle

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
private int guessCJKNameStyle(String name, int offset) {
    int length = name.length();
    while (offset < length) {
        int codePoint = Character.codePointAt(name, offset);
        if (Character.isLetter(codePoint)) {
            UnicodeBlock unicodeBlock = UnicodeBlock.of(codePoint);
            if (isJapanesePhoneticUnicodeBlock(unicodeBlock)) {
                return FullNameStyle.JAPANESE;
            }
            if (isKoreanUnicodeBlock(unicodeBlock)) {
                return FullNameStyle.KOREAN;
            }
        }
        offset += Character.charCount(codePoint);
    }

    return FullNameStyle.CJK;
}
開發者ID:SilentCircle，項目名稱:silent-contacts-android，代碼行數:19，代碼來源:NameSplitter.java

示例8: recognizeLanguage

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
public static int recognizeLanguage(String text) {
    int kanCount = 0;
    int tamCount = 0;
    int digitCount = 0;
    for (int i = 0; i < text.length(); i++) {
        char c = text.charAt(i);
        UnicodeBlock ub = UnicodeBlock.of(c);
        if (ub == UnicodeBlock.KANNADA) {
            kanCount++;
        } else if (ub == UnicodeBlock.TAMIL) {
            tamCount++;
        } else if (Character.isDigit(c)) {
            digitCount++;
        }
    }
    if (kanCount == 0 && tamCount == 0) {
        if (digitCount > 0) {
            return PREVIOUS_LANGUAGE;
        }
        return LANGUAGE_UNKNOWN;
    }
    if (tamCount > kanCount) {
        PREVIOUS_LANGUAGE = LANGUAGE_TAMIL;
        return LANGUAGE_TAMIL;
    } else {
        PREVIOUS_LANGUAGE = LANGUAGE_KANNADA;
        return LANGUAGE_KANNADA;
    }
}
開發者ID:bhashiniservices，項目名稱:g2p，代碼行數:30，代碼來源:LangUtil.java

示例9: testString

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
@Test
public void testString(){
	
	char[] chars = "ㄱㄴㄷㅏㅠㅠ한[email protected]#$%^&*()_".toCharArray();
	for (int i = 0; i < chars.length; i++) {
		char ch =  chars[i];
		UnicodeBlock block = UnicodeBlock.of(ch);
		String type = TypeTokenizer.getType(ch);
		System.out.println(i+ " : " + ch +" : " + type + " : "+block);
	}
}
開發者ID:gncloud，項目名稱:fastcatsearch3，代碼行數:12，代碼來源:TypeTokenizerTest.java

示例10: testAll

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
@Test
public void testAll(){
	
	for (int i = 0; i < 1000; i++) {
		char ch =  (char) i;
		UnicodeBlock block = UnicodeBlock.of(ch);
		String type = TypeTokenizer.getType(ch);
		if(type == TypeTokenizer.UNCATEGORIZED){
			System.out.println(i+ " : " + ch +" : " + type + " : "+block);
		}
	}
}
開發者ID:gncloud，項目名稱:fastcatsearch3，代碼行數:13，代碼來源:TypeTokenizerTest.java

示例11: toUseGlyphRenderer

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
protected boolean toUseGlyphRenderer(JRPrintText text)
{
	String value = styledTextUtil.getTruncatedText(text);
	if (value == null)
	{
		return false;
	}
	
	if (glyphRendererBlocks.isEmpty())
	{
		return false;
	}
	
	int charCount = value.length();
	char[] chars = new char[charCount];
	value.getChars(0, charCount, chars, 0);
	for (char c : chars)
	{
		UnicodeBlock block = UnicodeBlock.of(c);
		if (glyphRendererBlocks.contains(block))
		{
			if (log.isTraceEnabled())
			{
				log.trace("found character in block " + block + ", using the glyph renderer");
			}
			
			return true;
		}
	}
	
	return false;
}
開發者ID:TIBCOSoftware，項目名稱:jasperreports，代碼行數:33，代碼來源:JRPdfExporter.java

示例12: isLatinLetter

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
/**
 * Helper method to determine if a character is a Latin-script letter or not. For our purposes,
 * combining marks should also return true since we assume they have been added to a preceding
 * Latin character.
 */
// @VisibleForTesting
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);
}
開發者ID:MichaelRocks，項目名稱:libphonenumber-android，代碼行數:20，代碼來源:PhoneNumberMatcher.java

示例13: processInput

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
@Override
protected CharSequence processInput(final CharSequence input) {
    final StringBuilder buf = new StringBuilder(input.length());
    char prev = 0;
    for (int pos = 0; pos < input.length(); pos++) {
        final char c = input.charAt(pos);
        switch (c) {
        case U002D:
        case UFF0D:
        case U2010:
        case U2011:
        case U2012:
        case U2013:
        case U2014:
        case U2015:
        case U207B:
        case U208B:
        case U30FC:
            if (prev != 0) {
                final UnicodeBlock block = UnicodeBlock.of(prev);
                if (block == UnicodeBlock.HIRAGANA
                        || block == UnicodeBlock.KATAKANA
                        || block == UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS) {
                    buf.append(replacement);
                } else {
                    buf.append(c);
                }
            } else {
                buf.append(c);
            }
            break;
        default:
            buf.append(c);
            break;
        }
        prev = c;
    }
    return buf;
}
開發者ID:codelibs，項目名稱:analyzers-ja，代碼行數:40，代碼來源:ProlongedSoundMarkCharFilter.java

示例14: findWordStart

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
private static int findWordStart(CharSequence text, int start) {
    if ( text.length() <= start ){
        return start;
    }

    UnicodeBlock c0 = UnicodeBlock.of(text.charAt(start));

    for (; start > 0; start--) {
        char c = text.charAt(start - 1);
        UnicodeBlock cb = UnicodeBlock.of(c);
        if ( c0 == UnicodeBlock.BASIC_LATIN ){
            int type = Character.getType(c);

            if (c != '\'' &&
                type != Character.UPPERCASE_LETTER &&
                type != Character.LOWERCASE_LETTER &&
                type != Character.TITLECASE_LETTER &&
                type != Character.MODIFIER_LETTER &&
                type != Character.DECIMAL_DIGIT_NUMBER) {
                break;
            }
        }else if ( c0 != cb ){
            break;
        }
    }

    return start;
}
開發者ID:jiro-aqua，項目名稱:JotaTextEditor，代碼行數:29，代碼來源:ArrowKeyMovementMethod.java

示例15: findWordEnd

import java.lang.Character.UnicodeBlock; //導入方法依賴的package包/類
private static int findWordEnd(CharSequence text, int end) {
    int len = text.length();

    if ( len <= end ){
        return end;
    }

    UnicodeBlock c0 = UnicodeBlock.of(text.charAt(end));

    for (; end < len; end++) {
        char c = text.charAt(end);
        UnicodeBlock cb = UnicodeBlock.of(c);
        if ( c0 == UnicodeBlock.BASIC_LATIN ){
            int type = Character.getType(c);

            if (c != '\'' &&
                type != Character.UPPERCASE_LETTER &&
                type != Character.LOWERCASE_LETTER &&
                type != Character.TITLECASE_LETTER &&
                type != Character.MODIFIER_LETTER &&
                type != Character.DECIMAL_DIGIT_NUMBER) {
                break;
            }
        }else if ( c0 != cb ){
            break;
        }
    }

    return end;
}
開發者ID:jiro-aqua，項目名稱:JotaTextEditor，代碼行數:31，代碼來源:ArrowKeyMovementMethod.java


注：本文中的java.lang.Character.UnicodeBlock.of方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。