Example usage for java.lang Character UNASSIGNED

Introduction

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

Prototype

byte UNASSIGNED

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

Click Source Link

Document

General category "Cn" in the Unicode specification.

Usage

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 av  a 2  s .  com*/

    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  w  ww. j a  v  a 2 s .  c  o  m*/

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

---

From source file:Main.java

public static String removeUnprintableCharacters(String str) {

    int len = str.length();
    StringBuffer buf = new StringBuffer();
    try {//www  . j  a  v  a  2  s . co m
        for (int i = 0; i < len; i++) {
            String rep = "";
            char cp = str.charAt(i);// the code point
            // Replace invisible control characters and unused code points
            switch (Character.getType(cp)) {
            case Character.CONTROL: // \p{Cc}
            case Character.FORMAT: // \p{Cf}
            case Character.PRIVATE_USE: // \p{Co}
            case Character.SURROGATE: // \p{Cs}
            case Character.UNASSIGNED: // \p{Cn}
                buf = buf.append(rep);
                break;
            default:
                char[] chars = Character.toChars(cp);
                buf = buf.append(chars);
                break;
            }
        }
    } catch (NullPointerException e) {
        e.printStackTrace();
        System.err.println("Confused: " + e);
    } catch (IllegalArgumentException e) {
        e.printStackTrace();
        System.err.println("Confused: " + e);
    } catch (IndexOutOfBoundsException e) {
        e.printStackTrace();
        System.err.println("Confused: " + e);
    } catch (Exception e) {
        e.printStackTrace();
        System.err.println("Confused: " + e);
    }

    return buf.toString();
}

---

From source file:de.fau.cs.osr.utils.StringUtils.java

public static String escHtml(String text, boolean forAttribute) {
    // StringEscapeUtils.escapeHtml(in) does not escape '\'' but a lot of 
    // other stuff that doesn't need escaping.

    if (text == null)
        return "";

    int n = text.length();
    StringBuilder sb = new StringBuilder(n * 4 / 3);
    for (int i = 0; i < n; i++) {
        char ch = text.charAt(i);
        switch (ch) {
        case ' ':
        case '\n':
        case '\t':
            sb.append(ch);/*from  w w w  .  j a  va  2s  .  com*/
            break;
        case '<':
            sb.append("&lt;");
            break;
        case '>':
            sb.append(forAttribute ? "&gt;" : ">");
            break;
        case '&':
            sb.append("&amp;");
            break;
        case '\'':
            // &apos; cannot safely be used, see wikipedia
            sb.append("&#39;");
            break;
        case '"':
            sb.append(forAttribute ? "&quot;" : "\"");
            break;
        default:
            if ((ch >= 0 && ch < 0x20) || (ch == 0xFE)) {
                hexCharRef(sb, ch);
                break;
            } else if (Character.isHighSurrogate(ch)) {
                ++i;
                if (i < n) {
                    char ch2 = text.charAt(i);
                    if (Character.isLowSurrogate(ch2)) {
                        int codePoint = Character.toCodePoint(ch, ch2);
                        switch (Character.getType(codePoint)) {
                        case Character.CONTROL:
                        case Character.PRIVATE_USE:
                        case Character.UNASSIGNED:
                            hexCharRef(sb, codePoint);
                            break;

                        default:
                            sb.append(ch);
                            sb.append(ch2);
                            break;
                        }

                        continue;
                    }
                }
            } else if (!Character.isLowSurrogate(ch)) {
                sb.append(ch);
                continue;
            }

            // No low surrogate followed or only low surrogate
            throw new IllegalArgumentException("String contains isolated surrogates!");
        }
    }

    return sb.toString();
}

---

From source file:org.apache.accumulo.monitor.rest.logs.LogResource.java

private String sanitize(String s) {
    StringBuilder text = new StringBuilder();
    for (int i = 0; i < s.length(); i++) {
        char c = s.charAt(i);
        int type = Character.getType(c);
        boolean notPrintable = type == Character.UNASSIGNED || type == Character.LINE_SEPARATOR
                || type == Character.NON_SPACING_MARK || type == Character.PRIVATE_USE;
        text.append(notPrintable ? '?' : c);
    }//from   www. ja v a2s  . c  o  m
    return text.toString().replaceAll("&", "&amp;").replaceAll("<", "&lt;").replaceAll(">", "&gt;");
}

---

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

/**
 * Returns whether the given CharSequence contains any printable characters.
 *///from  w  ww. j  ava 2  s. co m
public static boolean isGraphic(CharSequence str) {
    final int len = str.length();
    for (int i = 0; i < len; i++) {
        int gc = Character.getType(str.charAt(i));
        if (gc != Character.CONTROL && gc != Character.FORMAT && gc != Character.SURROGATE
                && gc != Character.UNASSIGNED && gc != Character.LINE_SEPARATOR
                && gc != Character.PARAGRAPH_SEPARATOR && gc != Character.SPACE_SEPARATOR) {
            return true;
        }
    }
    return false;
}

---

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

/**
 * Returns whether this character is a printable character.
 *///from   w ww . ja v a  2  s. c  o  m
public static boolean isGraphic(char c) {
    int gc = Character.getType(c);
    return gc != Character.CONTROL && gc != Character.FORMAT && gc != Character.SURROGATE
            && gc != Character.UNASSIGNED && gc != Character.LINE_SEPARATOR
            && gc != Character.PARAGRAPH_SEPARATOR && gc != Character.SPACE_SEPARATOR;
}

---