| Methods Summary |
|---|
| static int | digit(int ch, int radix)
int value = -1;
if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
int val = getProperties(ch);
int kind = val & 0x1F;
if (kind == Character.DECIMAL_DIGIT_NUMBER) {
value = ch + ((val & 0x3E0) >> 5) & 0x1F;
}
else if ((val & 0xC00) == 0x00000C00) {
// Java supradecimal digit
value = (ch + ((val & 0x3E0) >> 5) & 0x1F) + 10;
}
}
return (value < radix) ? value : -1;
|
| static int | findInCharMap(int ch)Finds the character in the uppercase mapping table.
if (charMap == null || charMap.length == 0) {
return -1;
}
int top, bottom, current;
bottom = 0;
top = charMap.length;
current = top/2;
// invariant: top > current >= bottom && ch >= CharacterData.charMap[bottom][0]
while (top - bottom > 1) {
if (ch >= charMap[current][0][0]) {
bottom = current;
} else {
top = current;
}
current = (top + bottom) / 2;
}
if (ch == charMap[current][0][0]) return current;
else return -1;
|
| static byte | getDirectionality(int ch)
int val = getProperties(ch);
byte directionality = (byte)((val & 0x78000000) >> 27);
if (directionality == 0xF ) {
switch(ch) {
case 0x202A :
// This is the only char with LRE
directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING;
break;
case 0x202B :
// This is the only char with RLE
directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING;
break;
case 0x202C :
// This is the only char with PDF
directionality = Character.DIRECTIONALITY_POP_DIRECTIONAL_FORMAT;
break;
case 0x202D :
// This is the only char with LRO
directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE;
break;
case 0x202E :
// This is the only char with RLO
directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE;
break;
default :
directionality = Character.DIRECTIONALITY_UNDEFINED;
break;
}
}
return directionality;
|
| static int | getNumericValue(int ch)
int val = getProperties(ch);
int retval = -1;
switch (val & 0xC00) {
default: // cannot occur
case (0x00000000): // not numeric
retval = -1;
break;
case (0x00000400): // simple numeric
retval = ch + ((val & 0x3E0) >> 5) & 0x1F;
break;
case (0x00000800) : // "strange" numeric
switch (ch) {
case 0x0BF1: retval = 100; break; // TAMIL NUMBER ONE HUNDRED
case 0x0BF2: retval = 1000; break; // TAMIL NUMBER ONE THOUSAND
case 0x1375: retval = 40; break; // ETHIOPIC NUMBER FORTY
case 0x1376: retval = 50; break; // ETHIOPIC NUMBER FIFTY
case 0x1377: retval = 60; break; // ETHIOPIC NUMBER SIXTY
case 0x1378: retval = 70; break; // ETHIOPIC NUMBER SEVENTY
case 0x1379: retval = 80; break; // ETHIOPIC NUMBER EIGHTY
case 0x137A: retval = 90; break; // ETHIOPIC NUMBER NINETY
case 0x137B: retval = 100; break; // ETHIOPIC NUMBER HUNDRED
case 0x137C: retval = 10000; break; // ETHIOPIC NUMBER TEN THOUSAND
case 0x215F: retval = 1; break; // FRACTION NUMERATOR ONE
case 0x216C: retval = 50; break; // ROMAN NUMERAL FIFTY
case 0x216D: retval = 100; break; // ROMAN NUMERAL ONE HUNDRED
case 0x216E: retval = 500; break; // ROMAN NUMERAL FIVE HUNDRED
case 0x216F: retval = 1000; break; // ROMAN NUMERAL ONE THOUSAND
case 0x217C: retval = 50; break; // SMALL ROMAN NUMERAL FIFTY
case 0x217D: retval = 100; break; // SMALL ROMAN NUMERAL ONE HUNDRED
case 0x217E: retval = 500; break; // SMALL ROMAN NUMERAL FIVE HUNDRED
case 0x217F: retval = 1000; break; // SMALL ROMAN NUMERAL ONE THOUSAND
case 0x2180: retval = 1000; break; // ROMAN NUMERAL ONE THOUSAND C D
case 0x2181: retval = 5000; break; // ROMAN NUMERAL FIVE THOUSAND
case 0x2182: retval = 10000; break; // ROMAN NUMERAL TEN THOUSAND
case 0x325C: retval = 32; break;
case 0x325D: retval = 33; break; // CIRCLED NUMBER THIRTY THREE
case 0x325E: retval = 34; break; // CIRCLED NUMBER THIRTY FOUR
case 0x325F: retval = 35; break; // CIRCLED NUMBER THIRTY FIVE
case 0x32B1: retval = 36; break; // CIRCLED NUMBER THIRTY SIX
case 0x32B2: retval = 37; break; // CIRCLED NUMBER THIRTY SEVEN
case 0x32B3: retval = 38; break; // CIRCLED NUMBER THIRTY EIGHT
case 0x32B4: retval = 39; break; // CIRCLED NUMBER THIRTY NINE
case 0x32B5: retval = 40; break; // CIRCLED NUMBER FORTY
case 0x32B6: retval = 41; break; // CIRCLED NUMBER FORTY ONE
case 0x32B7: retval = 42; break; // CIRCLED NUMBER FORTY TWO
case 0x32B8: retval = 43; break; // CIRCLED NUMBER FORTY THREE
case 0x32B9: retval = 44; break; // CIRCLED NUMBER FORTY FOUR
case 0x32BA: retval = 45; break; // CIRCLED NUMBER FORTY FIVE
case 0x32BB: retval = 46; break; // CIRCLED NUMBER FORTY SIX
case 0x32BC: retval = 47; break; // CIRCLED NUMBER FORTY SEVEN
case 0x32BD: retval = 48; break; // CIRCLED NUMBER FORTY EIGHT
case 0x32BE: retval = 49; break; // CIRCLED NUMBER FORTY NINE
case 0x32BF: retval = 50; break; // CIRCLED NUMBER FIFTY
default: retval = -2; break;
}
break;
case (0x00000C00): // Java supradecimal
retval = (ch + ((val & 0x3E0) >> 5) & 0x1F) + 10;
break;
}
return retval;
|
| static int | getProperties(int ch)
char offset = (char)ch;
int props = A[Y[X[offset>>5]|((offset>>1)&0xF)]|(offset&0x1)];
return props;
|
| static int | getType(int ch)
int props = getProperties(ch);
return (props & 0x1F);
|
| static boolean | isDefined(int ch)
int type = getType(ch);
return (type != Character.UNASSIGNED);
|
| static boolean | isDigit(int ch)
int type = getType(ch);
return (type == Character.DECIMAL_DIGIT_NUMBER);
|
| static boolean | isIdentifierIgnorable(int ch)
int props = getProperties(ch);
return ((props & 0x00007000) == 0x00001000);
|
| static boolean | isJavaIdentifierPart(int ch)
int props = getProperties(ch);
return ((props & 0x00003000) != 0);
|
| static boolean | isJavaIdentifierStart(int ch)
int props = getProperties(ch);
return ((props & 0x00007000) >= 0x00005000);
|
| static boolean | isLetter(int ch)
int type = getType(ch);
return (((((1 << Character.UPPERCASE_LETTER) |
(1 << Character.LOWERCASE_LETTER) |
(1 << Character.TITLECASE_LETTER) |
(1 << Character.MODIFIER_LETTER) |
(1 << Character.OTHER_LETTER)) >> type) & 1) != 0);
|
| static boolean | isLetterOrDigit(int ch)
int type = getType(ch);
return (((((1 << Character.UPPERCASE_LETTER) |
(1 << Character.LOWERCASE_LETTER) |
(1 << Character.TITLECASE_LETTER) |
(1 << Character.MODIFIER_LETTER) |
(1 << Character.OTHER_LETTER) |
(1 << Character.DECIMAL_DIGIT_NUMBER)) >> type) & 1) != 0);
|
| static boolean | isLowerCase(int ch)
int type = getType(ch);
return (type == Character.LOWERCASE_LETTER);
|
| static boolean | isMirrored(int ch)
int props = getProperties(ch);
return ((props & 0x80000000) != 0);
|
| static boolean | isSpaceChar(int ch)
int type = getType(ch);
return (((((1 << Character.SPACE_SEPARATOR) |
(1 << Character.LINE_SEPARATOR) |
(1 << Character.PARAGRAPH_SEPARATOR)) >> type) & 1) != 0);
|
| static boolean | isTitleCase(int ch)
int type = getType(ch);
return (type == Character.TITLECASE_LETTER);
|
| static boolean | isUnicodeIdentifierPart(int ch)
int props = getProperties(ch);
return ((props & 0x00001000) != 0);
|
| static boolean | isUnicodeIdentifierStart(int ch)
int props = getProperties(ch);
return ((props & 0x00007000) == 0x00007000);
|
| static boolean | isUpperCase(int ch)
int type = getType(ch);
return (type == Character.UPPERCASE_LETTER);
|
| static boolean | isWhitespace(int ch)
int props = getProperties(ch);
return ((props & 0x00007000) == 0x00004000);
|
| static int | toLowerCase(int ch)
int mapChar = ch;
int val = getProperties(ch);
if ((val & 0x00020000) != 0) {
if ((val & 0x07FC0000) == 0x07FC0000) {
switch(ch) {
// map the offset overflow chars
case 0x0130 : mapChar = 0x0069; break;
case 0x2126 : mapChar = 0x03C9; break;
case 0x212A : mapChar = 0x006B; break;
case 0x212B : mapChar = 0x00E5; break;
// map the titlecase chars with both a 1:M uppercase map
// and a lowercase map
case 0x1F88 : mapChar = 0x1F80; break;
case 0x1F89 : mapChar = 0x1F81; break;
case 0x1F8A : mapChar = 0x1F82; break;
case 0x1F8B : mapChar = 0x1F83; break;
case 0x1F8C : mapChar = 0x1F84; break;
case 0x1F8D : mapChar = 0x1F85; break;
case 0x1F8E : mapChar = 0x1F86; break;
case 0x1F8F : mapChar = 0x1F87; break;
case 0x1F98 : mapChar = 0x1F90; break;
case 0x1F99 : mapChar = 0x1F91; break;
case 0x1F9A : mapChar = 0x1F92; break;
case 0x1F9B : mapChar = 0x1F93; break;
case 0x1F9C : mapChar = 0x1F94; break;
case 0x1F9D : mapChar = 0x1F95; break;
case 0x1F9E : mapChar = 0x1F96; break;
case 0x1F9F : mapChar = 0x1F97; break;
case 0x1FA8 : mapChar = 0x1FA0; break;
case 0x1FA9 : mapChar = 0x1FA1; break;
case 0x1FAA : mapChar = 0x1FA2; break;
case 0x1FAB : mapChar = 0x1FA3; break;
case 0x1FAC : mapChar = 0x1FA4; break;
case 0x1FAD : mapChar = 0x1FA5; break;
case 0x1FAE : mapChar = 0x1FA6; break;
case 0x1FAF : mapChar = 0x1FA7; break;
case 0x1FBC : mapChar = 0x1FB3; break;
case 0x1FCC : mapChar = 0x1FC3; break;
case 0x1FFC : mapChar = 0x1FF3; break;
// default mapChar is already set, so no
// need to redo it here.
// default : mapChar = ch;
}
}
else {
int offset = val << 5 >> (5+18);
mapChar = ch + offset;
}
}
return mapChar;
|
| static int | toTitleCase(int ch)
int mapChar = ch;
int val = getProperties(ch);
if ((val & 0x00008000) != 0) {
// There is a titlecase equivalent. Perform further checks:
if ((val & 0x00010000) == 0) {
// The character does not have an uppercase equivalent, so it must
// already be uppercase; so add 1 to get the titlecase form.
mapChar = ch + 1;
}
else if ((val & 0x00020000) == 0) {
// The character does not have a lowercase equivalent, so it must
// already be lowercase; so subtract 1 to get the titlecase form.
mapChar = ch - 1;
}
// else {
// The character has both an uppercase equivalent and a lowercase
// equivalent, so it must itself be a titlecase form; return it.
// return ch;
//}
}
else if ((val & 0x00010000) != 0) {
// This character has no titlecase equivalent but it does have an
// uppercase equivalent, so use that (subtract the signed case offset).
mapChar = toUpperCase(ch);
}
return mapChar;
|
| static int | toUpperCase(int ch)
int mapChar = ch;
int val = getProperties(ch);
if ((val & 0x00010000) != 0) {
if ((val & 0x07FC0000) == 0x07FC0000) {
switch(ch) {
// map chars with overflow offsets
case 0x00B5 : mapChar = 0x039C; break;
case 0x017F : mapChar = 0x0053; break;
case 0x1FBE : mapChar = 0x0399; break;
// map char that have both a 1:1 and 1:M map
case 0x1F80 : mapChar = 0x1F88; break;
case 0x1F81 : mapChar = 0x1F89; break;
case 0x1F82 : mapChar = 0x1F8A; break;
case 0x1F83 : mapChar = 0x1F8B; break;
case 0x1F84 : mapChar = 0x1F8C; break;
case 0x1F85 : mapChar = 0x1F8D; break;
case 0x1F86 : mapChar = 0x1F8E; break;
case 0x1F87 : mapChar = 0x1F8F; break;
case 0x1F90 : mapChar = 0x1F98; break;
case 0x1F91 : mapChar = 0x1F99; break;
case 0x1F92 : mapChar = 0x1F9A; break;
case 0x1F93 : mapChar = 0x1F9B; break;
case 0x1F94 : mapChar = 0x1F9C; break;
case 0x1F95 : mapChar = 0x1F9D; break;
case 0x1F96 : mapChar = 0x1F9E; break;
case 0x1F97 : mapChar = 0x1F9F; break;
case 0x1FA0 : mapChar = 0x1FA8; break;
case 0x1FA1 : mapChar = 0x1FA9; break;
case 0x1FA2 : mapChar = 0x1FAA; break;
case 0x1FA3 : mapChar = 0x1FAB; break;
case 0x1FA4 : mapChar = 0x1FAC; break;
case 0x1FA5 : mapChar = 0x1FAD; break;
case 0x1FA6 : mapChar = 0x1FAE; break;
case 0x1FA7 : mapChar = 0x1FAF; break;
case 0x1FB3 : mapChar = 0x1FBC; break;
case 0x1FC3 : mapChar = 0x1FCC; break;
case 0x1FF3 : mapChar = 0x1FFC; break;
// ch must have a 1:M case mapping, but we
// can't handle it here. Return ch.
// since mapChar is already set, no need
// to redo it here.
//default : mapChar = ch;
}
}
else {
int offset = val << 5 >> (5+18);
mapChar = ch - offset;
}
}
return mapChar;
|
| static char[] | toUpperCaseCharArray(int ch)
char[] upperMap = {(char)ch};
int location = findInCharMap(ch);
if (location != -1) {
upperMap = charMap[location][1];
}
return upperMap;
|
| static int | toUpperCaseEx(int ch)
int mapChar = ch;
int val = getProperties(ch);
if ((val & 0x00010000) != 0) {
if ((val & 0x07FC0000) != 0x07FC0000) {
int offset = val << 5 >> (5+18);
mapChar = ch - offset;
}
else {
switch(ch) {
// map overflow characters
case 0x00B5 : mapChar = 0x039C; break;
case 0x017F : mapChar = 0x0053; break;
case 0x1FBE : mapChar = 0x0399; break;
default : mapChar = Character.ERROR; break;
}
}
}
return mapChar;
|
