Example usage for java.lang Character CONNECTOR_PUNCTUATION

List of usage examples for java.lang Character CONNECTOR_PUNCTUATION

Introduction

In this page you can find the example usage for java.lang Character CONNECTOR_PUNCTUATION.

Prototype

byte CONNECTOR_PUNCTUATION

To view the source code for java.lang Character CONNECTOR_PUNCTUATION.

Click Source Link

Document

General category "Pc" in the Unicode specification.

Usage

From source file:Main.java

public static void main(String[] args) {
    for (char ch = Character.MIN_VALUE; ch < Character.MAX_VALUE; ch++) {
        if (Character.CONNECTOR_PUNCTUATION == Character.getType(ch)) {
            String s = String.format("\\u%04x", (int) ch);
            System.out.println(s);
        }/*from w ww  . j a va2s. c  om*/
    }
}

From source file:Main.java

public static void main(String[] args) throws java.io.IOException {
    char c = 'a';

    System.out.println("Character = " + (int) c);
    System.out.println("Defined = " + Character.isDefined(c));
    System.out.println("Digit = " + Character.isDigit(c));
    System.out.println("Ignorable = " + Character.isIdentifierIgnorable(c));
    System.out.println("ISO control = " + Character.isISOControl(c));
    System.out.println("Java identifier part = " + Character.isJavaIdentifierPart(c));
    System.out.println("Java identifier start = " + Character.isJavaIdentifierStart(c));
    System.out.println("Letter = " + Character.isLetter(c));
    System.out.println("Letter or digit = " + Character.isLetterOrDigit(c));
    System.out.println("Lowercase = " + Character.isLowerCase(c));
    System.out.println("Space = " + Character.isSpaceChar(c));
    System.out.println("Titlecase = " + Character.isTitleCase(c));
    System.out.println("Unicode identifier part = " + Character.isUnicodeIdentifierPart(c));
    System.out.println("Unicode identifier start = " + Character.isUnicodeIdentifierStart(c));
    System.out.println("Uppercase = " + Character.isUpperCase(c));
    System.out.println("White space = " + Character.isWhitespace(c));

    byte[] types = { Character.COMBINING_SPACING_MARK, Character.CONNECTOR_PUNCTUATION, Character.CONTROL,
            Character.CURRENCY_SYMBOL, Character.DASH_PUNCTUATION, Character.DECIMAL_DIGIT_NUMBER,
            Character.ENCLOSING_MARK, Character.END_PUNCTUATION, Character.FORMAT, Character.LETTER_NUMBER,
            Character.LINE_SEPARATOR, Character.LOWERCASE_LETTER, Character.MATH_SYMBOL,
            Character.MODIFIER_SYMBOL, Character.NON_SPACING_MARK, Character.OTHER_LETTER,
            Character.OTHER_NUMBER, Character.OTHER_PUNCTUATION, Character.OTHER_SYMBOL,
            Character.PARAGRAPH_SEPARATOR, Character.PRIVATE_USE, Character.SPACE_SEPARATOR,
            Character.START_PUNCTUATION, Character.SURROGATE, Character.TITLECASE_LETTER, Character.UNASSIGNED,
            Character.UPPERCASE_LETTER };

    String[] typeNames = { "Combining spacing mark", "Connector punctuation", "Control", "Currency symbol",
            "Dash punctuation", "Decimal digit number", "Enclosing mark", "End punctuation", "Format",
            "Letter number", "Line separator", "Lowercase letter", "Math symbol", "Modifier symbol",
            "Non spacing mark", "Other letter", "Other number", "Other punctuation", "Other symbol",
            "Paragraph separator", "Private use", "Space separator", "Start punctuation", "Surrogate",
            "Titlecase letter", "Unassigned", "Uppercase letter" };

    int type = Character.getType(c);

    for (int i = 0; i < types.length; i++)
        if (type == types[i]) {
            System.out.println("Type name = " + typeNames[i]);
            break;
        }//from   w ww .j ava 2 s.  co m

    System.out.println("Unicode block = " + Character.UnicodeBlock.of(c));
}

From source file:Classify.java

public static void main(String[] args) throws java.io.IOException {
    char c = '\u0beb'; // Tamil digit.

    System.out.println("Character = " + (int) c);
    System.out.println("Defined = " + Character.isDefined(c));
    System.out.println("Digit = " + Character.isDigit(c));
    System.out.println("Ignorable = " + Character.isIdentifierIgnorable(c));
    System.out.println("ISO control = " + Character.isISOControl(c));
    System.out.println("Java identifier part = " + Character.isJavaIdentifierPart(c));
    System.out.println("Java identifier start = " + Character.isJavaIdentifierStart(c));
    System.out.println("Letter = " + Character.isLetter(c));
    System.out.println("Letter or digit = " + Character.isLetterOrDigit(c));
    System.out.println("Lowercase = " + Character.isLowerCase(c));
    System.out.println("Space = " + Character.isSpaceChar(c));
    System.out.println("Titlecase = " + Character.isTitleCase(c));
    System.out.println("Unicode identifier part = " + Character.isUnicodeIdentifierPart(c));
    System.out.println("Unicode identifier start = " + Character.isUnicodeIdentifierStart(c));
    System.out.println("Uppercase = " + Character.isUpperCase(c));
    System.out.println("White space = " + Character.isWhitespace(c));

    byte[] types = { Character.COMBINING_SPACING_MARK, Character.CONNECTOR_PUNCTUATION, Character.CONTROL,
            Character.CURRENCY_SYMBOL, Character.DASH_PUNCTUATION, Character.DECIMAL_DIGIT_NUMBER,
            Character.ENCLOSING_MARK, Character.END_PUNCTUATION, Character.FORMAT, Character.LETTER_NUMBER,
            Character.LINE_SEPARATOR, Character.LOWERCASE_LETTER, Character.MATH_SYMBOL,
            Character.MODIFIER_SYMBOL, Character.NON_SPACING_MARK, Character.OTHER_LETTER,
            Character.OTHER_NUMBER, Character.OTHER_PUNCTUATION, Character.OTHER_SYMBOL,
            Character.PARAGRAPH_SEPARATOR, Character.PRIVATE_USE, Character.SPACE_SEPARATOR,
            Character.START_PUNCTUATION, Character.SURROGATE, Character.TITLECASE_LETTER, Character.UNASSIGNED,
            Character.UPPERCASE_LETTER };

    String[] typeNames = { "Combining spacing mark", "Connector punctuation", "Control", "Currency symbol",
            "Dash punctuation", "Decimal digit number", "Enclosing mark", "End punctuation", "Format",
            "Letter number", "Line separator", "Lowercase letter", "Math symbol", "Modifier symbol",
            "Non spacing mark", "Other letter", "Other number", "Other punctuation", "Other symbol",
            "Paragraph separator", "Private use", "Space separator", "Start punctuation", "Surrogate",
            "Titlecase letter", "Unassigned", "Uppercase letter" };

    int type = Character.getType(c);

    for (int i = 0; i < types.length; i++)
        if (type == types[i]) {
            System.out.println("Type name = " + typeNames[i]);
            break;
        }/*from ww w  . ja v a 2s .com*/

    System.out.println("Unicode block = " + Character.UnicodeBlock.of(c));
}

From source file:info.magnolia.cms.taglibs.util.BaseImageTag.java

/**
 * Replace any special characters that are not letters or numbers with a replacement string. The two exceptions are
 * '-' and '_', which are allowed.//from   w  ww  .j  a v a  2  s. c om
 */
public String convertToSimpleString(String string) {

    final StringBuffer result = new StringBuffer();

    final StringCharacterIterator iterator = new StringCharacterIterator(string);
    char character = iterator.current();
    while (character != CharacterIterator.DONE) {
        int charType = Character.getType(character);
        if (charType == Character.SPACE_SEPARATOR) {
            result.append("-");
        } else if ((charType != Character.UPPERCASE_LETTER) && (charType != Character.LOWERCASE_LETTER)
                && (charType != Character.DECIMAL_DIGIT_NUMBER) && (charType != Character.CONNECTOR_PUNCTUATION)
                && (charType != Character.DASH_PUNCTUATION)) {
            result.append("u" + (int) character);

        } else {
            // the char is not a special one
            // add it to the result as is
            result.append(character);
        }
        character = iterator.next();
    }
    return result.toString();
}

From source file:org.grails.datastore.bson.json.JsonWriter.java

private void writeStringHelper(final String str) throws IOException {
    writer.write('"');
    for (final char c : str.toCharArray()) {
        switch (c) {
        case '"':
            writer.write("\\\"");
            break;
        case '\\':
            writer.write("\\\\");
            break;
        case '\b':
            writer.write("\\b");
            break;
        case '\f':
            writer.write("\\f");
            break;
        case '\n':
            writer.write("\\n");
            break;
        case '\r':
            writer.write("\\r");
            break;
        case '\t':
            writer.write("\\t");
            break;
        default:/*from   ww  w  .j a  va 2  s  .  co m*/
            switch (Character.getType(c)) {
            case Character.UPPERCASE_LETTER:
            case Character.LOWERCASE_LETTER:
            case Character.TITLECASE_LETTER:
            case Character.OTHER_LETTER:
            case Character.DECIMAL_DIGIT_NUMBER:
            case Character.LETTER_NUMBER:
            case Character.OTHER_NUMBER:
            case Character.SPACE_SEPARATOR:
            case Character.CONNECTOR_PUNCTUATION:
            case Character.DASH_PUNCTUATION:
            case Character.START_PUNCTUATION:
            case Character.END_PUNCTUATION:
            case Character.INITIAL_QUOTE_PUNCTUATION:
            case Character.FINAL_QUOTE_PUNCTUATION:
            case Character.OTHER_PUNCTUATION:
            case Character.MATH_SYMBOL:
            case Character.CURRENCY_SYMBOL:
            case Character.MODIFIER_SYMBOL:
            case Character.OTHER_SYMBOL:
                writer.write(c);
                break;
            default:
                writer.write("\\u");
                writer.write(Integer.toHexString((c & 0xf000) >> 12));
                writer.write(Integer.toHexString((c & 0x0f00) >> 8));
                writer.write(Integer.toHexString((c & 0x00f0) >> 4));
                writer.write(Integer.toHexString(c & 0x000f));
                break;
            }
            break;
        }
    }
    writer.write('"');
}

From source file:org.apache.orc.impl.mask.RedactMaskFactory.java

/**
 * Given a UTF code point, find the replacement codepoint
 * @param codepoint a UTF character//  w w w.  jav a2  s .  co m
 * @return the replacement codepoint
 */
int getReplacement(int codepoint) {
    switch (Character.getType(codepoint)) {
    case Character.UPPERCASE_LETTER:
        return UPPPER_REPLACEMENT;
    case Character.LOWERCASE_LETTER:
        return LOWER_REPLACEMENT;
    case Character.TITLECASE_LETTER:
    case Character.MODIFIER_LETTER:
    case Character.OTHER_LETTER:
        return OTHER_LETTER_REPLACEMENT;
    case Character.NON_SPACING_MARK:
    case Character.ENCLOSING_MARK:
    case Character.COMBINING_SPACING_MARK:
        return MARK_REPLACEMENT;
    case Character.DECIMAL_DIGIT_NUMBER:
        return DIGIT_CP_REPLACEMENT;
    case Character.LETTER_NUMBER:
    case Character.OTHER_NUMBER:
        return OTHER_NUMBER_REPLACEMENT;
    case Character.SPACE_SEPARATOR:
    case Character.LINE_SEPARATOR:
    case Character.PARAGRAPH_SEPARATOR:
        return SEPARATOR_REPLACEMENT;
    case Character.MATH_SYMBOL:
    case Character.CURRENCY_SYMBOL:
    case Character.MODIFIER_SYMBOL:
    case Character.OTHER_SYMBOL:
        return SYMBOL_REPLACEMENT;
    case Character.DASH_PUNCTUATION:
    case Character.START_PUNCTUATION:
    case Character.END_PUNCTUATION:
    case Character.CONNECTOR_PUNCTUATION:
    case Character.OTHER_PUNCTUATION:
        return PUNCTUATION_REPLACEMENT;
    default:
        return OTHER_REPLACEMENT;
    }
}