Example usage for java.lang Character START

Introduction

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

Prototype

byte START_PUNCTUATION

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

Click Source Link

Document

General category "Ps" 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.START_PUNCTUATION == Character.getType(ch)) {

            String s = String.format("\\u%04x", (int) ch);
            System.out.println(s);
        }//from  ww  w  .ja  v a2 s  .com
    }
}

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  w  w .  ja v a  2 s  . c  o  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  www.ja va2s.co m

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

From source file:Main.java

public static boolean isPrintable(char c) {
    if (Character.isJavaIdentifierStart(c)) {
        // Letters and $ _
        return true;
    }// w w  w  .  ja v  a  2 s  .  c o  m
    if (Character.isDigit(c)) {
        return true;
    }
    switch (Character.getType(c)) {
    case Character.MODIFIER_SYMBOL:
        return true; // ` ^
    case Character.DASH_PUNCTUATION:
        return true; // -
    case Character.MATH_SYMBOL:
        return true; // = ~ + | < >
    case Character.OTHER_PUNCTUATION:
        return true; // !@#%&*;':",./?
    case Character.START_PUNCTUATION:
        return true; // ( [ {
    case Character.END_PUNCTUATION:
        return true; // ) ] }
    }
    return false;
}

From source file:gov.va.vinci.leo.ae.ExampleWhitespaceTokenizer.java

/**
 * Given a character c return the type definition from the
 * list of public static type definitions in this class.
 *
 * @param c/*from   www  .j a v a 2  s .c om*/
 * @return type definition for the character c
 */
private static int characterType(char c) {
    switch (Character.getType(c)) {
    //letters
    case Character.UPPERCASE_LETTER:
    case Character.LOWERCASE_LETTER:
    case Character.TITLECASE_LETTER:
    case Character.MODIFIER_LETTER:
    case Character.OTHER_LETTER:
    case Character.NON_SPACING_MARK:
    case Character.ENCLOSING_MARK:
    case Character.COMBINING_SPACING_MARK:
    case Character.PRIVATE_USE:
    case Character.SURROGATE:
    case Character.MODIFIER_SYMBOL:
        return TK_LETTER;
    //numbers
    case Character.DECIMAL_DIGIT_NUMBER:
    case Character.LETTER_NUMBER:
    case Character.OTHER_NUMBER:
        return TK_NUMBER;
    //Regular Whitespace
    case Character.SPACE_SEPARATOR:
        return TK_WHITESPACE;
    //Punctuation
    case Character.DASH_PUNCTUATION:
    case Character.START_PUNCTUATION:
    case Character.END_PUNCTUATION:
    case Character.OTHER_PUNCTUATION:
        return TK_PUNCTUATION;
    //Simple NewLine
    case Character.LINE_SEPARATOR:
    case Character.PARAGRAPH_SEPARATOR:
        return TK_NEWLINE;
    //Other types of "control" characters
    case Character.CONTROL:
        if (c == '\n' || c == '\r')
            return TK_NEWLINE;
        if (Character.isWhitespace(c)) //Tab char is a "Control" character
            return TK_WHITESPACE;
        return TK_CONTROL;
    default:
        if (Character.isWhitespace(c)) {
            return TK_WHITESPACE;
        } //if
        return TK_UNKNOWN;
    }//switch
}

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  2s . c o 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:com.vuze.android.remote.adapter.TorrentListAdapter.java

private static boolean isStandardPuncuation(int c) {
    int type = Character.getType(c);
    return type == Character.START_PUNCTUATION || type == Character.END_PUNCTUATION
            || type == Character.OTHER_PUNCTUATION;
}

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

/**
 * Given a UTF code point, find the replacement codepoint
 * @param codepoint a UTF character//from   w w w  .j  a v  a 2 s.  com
 * @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;
    }
}

From source file:com.jecelyin.editor.v2.core.text.TextUtils.java

/**
 * Determine what caps mode should be in effect at the current offset in
 * the text.  Only the mode bits set in <var>reqModes</var> will be
 * checked.  Note that the caps mode flags here are explicitly defined
 * to match those in {@link android.text.InputType}.
 *
 * @param cs The text that should be checked for caps modes.
 * @param off Location in the text at which to check.
 * @param reqModes The modes to be checked: may be any combination of
 * {@link #CAP_MODE_CHARACTERS}, {@link #CAP_MODE_WORDS}, and
 * {@link #CAP_MODE_SENTENCES}./* w w w.  ja v a2  s.  c  o  m*/
 *
 * @return Returns the actual capitalization modes that can be in effect
 * at the current position, which is any combination of
 * {@link #CAP_MODE_CHARACTERS}, {@link #CAP_MODE_WORDS}, and
 * {@link #CAP_MODE_SENTENCES}.
 */
public static int getCapsMode(CharSequence cs, int off, int reqModes) {
    if (off < 0) {
        return 0;
    }

    int i;
    char c;
    int mode = 0;

    if ((reqModes & CAP_MODE_CHARACTERS) != 0) {
        mode |= CAP_MODE_CHARACTERS;
    }
    if ((reqModes & (CAP_MODE_WORDS | CAP_MODE_SENTENCES)) == 0) {
        return mode;
    }

    // Back over allowed opening punctuation.

    for (i = off; i > 0; i--) {
        c = cs.charAt(i - 1);

        if (c != '"' && c != '\'' && Character.getType(c) != Character.START_PUNCTUATION) {
            break;
        }
    }

    // Start of paragraph, with optional whitespace.

    int j = i;
    while (j > 0 && ((c = cs.charAt(j - 1)) == ' ' || c == '\t')) {
        j--;
    }
    if (j == 0 || cs.charAt(j - 1) == '\n') {
        return mode | CAP_MODE_WORDS;
    }

    // Or start of word if we are that style.

    if ((reqModes & CAP_MODE_SENTENCES) == 0) {
        if (i != j)
            mode |= CAP_MODE_WORDS;
        return mode;
    }

    // There must be a space if not the start of paragraph.

    if (i == j) {
        return mode;
    }

    // Back over allowed closing punctuation.

    for (; j > 0; j--) {
        c = cs.charAt(j - 1);

        if (c != '"' && c != '\'' && Character.getType(c) != Character.END_PUNCTUATION) {
            break;
        }
    }

    if (j > 0) {
        c = cs.charAt(j - 1);

        if (c == '.' || c == '?' || c == '!') {
            // Do not capitalize if the word ends with a period but
            // also contains a period, in which case it is an abbreviation.

            if (c == '.') {
                for (int k = j - 2; k >= 0; k--) {
                    c = cs.charAt(k);

                    if (c == '.') {
                        return mode;
                    }

                    if (!Character.isLetter(c)) {
                        break;
                    }
                }
            }

            return mode | CAP_MODE_SENTENCES;
        }
    }

    return mode;
}

Example usage for java.lang Character START_PUNCTUATION

Introduction

Prototype

Document

Usage