List of usage examples for java.lang Character SURROGATE
byte SURROGATE
To view the source code for java.lang Character SURROGATE.
Click Source Link
From source file:Main.java
public static void main(String[] args) { for (char ch = Character.MIN_VALUE; ch < Character.MAX_VALUE; ch++) { if (Character.SURROGATE == Character.getType(ch)) { String s = String.format("\\u%04x", (int) ch); System.out.println(s); }// www . ja va 2 s . c o m } }
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 ww w.jav 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; }/* w w w. j a v a 2s . 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 {/*w w w .ja v a 2s . c om*/ 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: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/*w w w . j av a2 s . c o m*/ * @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:com.jecelyin.editor.v2.core.text.TextUtils.java
/** * Returns whether the given CharSequence contains any printable characters. *///from w ww .j a va 2 s . c o 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. */// w w w . j a va 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; }