260 lines
11 KiB
Plaintext
260 lines
11 KiB
Plaintext
/*
|
|
* Copyright 2003-2006 Sun Microsystems, Inc. All Rights Reserved.
|
|
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
|
|
*
|
|
* This code is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License version 2 only, as
|
|
* published by the Free Software Foundation. Sun designates this
|
|
* particular file as subject to the "Classpath" exception as provided
|
|
* by Sun in the LICENSE file that accompanied this code.
|
|
*
|
|
* This code is distributed in the hope that it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
* version 2 for more details (a copy is included in the LICENSE file that
|
|
* accompanied this code).
|
|
*
|
|
* You should have received a copy of the GNU General Public License version
|
|
* 2 along with this work; if not, write to the Free Software Foundation,
|
|
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
*
|
|
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
|
|
* CA 95054 USA or visit www.sun.com if you need additional information or
|
|
* have any questions.
|
|
*/
|
|
|
|
package java.lang;
|
|
|
|
/** The CharacterData class encapsulates the large tables once found in
|
|
* java.lang.Character.
|
|
*/
|
|
|
|
class CharacterData01 extends CharacterData {
|
|
/* The character properties are currently encoded into 32 bits in the following manner:
|
|
1 bit mirrored property
|
|
4 bits directionality property
|
|
9 bits signed offset used for converting case
|
|
1 bit if 1, adding the signed offset converts the character to lowercase
|
|
1 bit if 1, subtracting the signed offset converts the character to uppercase
|
|
1 bit if 1, this character has a titlecase equivalent (possibly itself)
|
|
3 bits 0 may not be part of an identifier
|
|
1 ignorable control; may continue a Unicode identifier or Java identifier
|
|
2 may continue a Java identifier but not a Unicode identifier (unused)
|
|
3 may continue a Unicode identifier or Java identifier
|
|
4 is a Java whitespace character
|
|
5 may start or continue a Java identifier;
|
|
may continue but not start a Unicode identifier (underscores)
|
|
6 may start or continue a Java identifier but not a Unicode identifier ($)
|
|
7 may start or continue a Unicode identifier or Java identifier
|
|
Thus:
|
|
5, 6, 7 may start a Java identifier
|
|
1, 2, 3, 5, 6, 7 may continue a Java identifier
|
|
7 may start a Unicode identifier
|
|
1, 3, 5, 7 may continue a Unicode identifier
|
|
1 is ignorable within an identifier
|
|
4 is Java whitespace
|
|
2 bits 0 this character has no numeric property
|
|
1 adding the digit offset to the character code and then
|
|
masking with 0x1F will produce the desired numeric value
|
|
2 this character has a "strange" numeric value
|
|
3 a Java supradecimal digit: adding the digit offset to the
|
|
character code, then masking with 0x1F, then adding 10
|
|
will produce the desired numeric value
|
|
5 bits digit offset
|
|
5 bits character type
|
|
|
|
The encoding of character properties is subject to change at any time.
|
|
*/
|
|
|
|
int getProperties(int ch) {
|
|
char offset = (char)ch;
|
|
int props = $$Lookup(offset);
|
|
return props;
|
|
}
|
|
|
|
int getType(int ch) {
|
|
int props = getProperties(ch);
|
|
return (props & $$maskType);
|
|
}
|
|
|
|
boolean isJavaIdentifierStart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
|
|
}
|
|
|
|
boolean isJavaIdentifierPart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$nonzeroJavaPart) != 0);
|
|
}
|
|
|
|
boolean isUnicodeIdentifierStart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
|
|
}
|
|
|
|
boolean isUnicodeIdentifierPart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$maskUnicodePart) != 0);
|
|
}
|
|
|
|
boolean isIdentifierIgnorable(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
|
|
}
|
|
|
|
int toLowerCase(int ch) {
|
|
int mapChar = ch;
|
|
int val = getProperties(ch);
|
|
|
|
if ((val & $$maskLowerCase) != 0) {
|
|
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
|
|
mapChar = ch + offset;
|
|
}
|
|
return mapChar;
|
|
}
|
|
|
|
int toUpperCase(int ch) {
|
|
int mapChar = ch;
|
|
int val = getProperties(ch);
|
|
|
|
if ((val & $$maskUpperCase) != 0) {
|
|
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
|
|
mapChar = ch - offset;
|
|
}
|
|
return mapChar;
|
|
}
|
|
|
|
int toTitleCase(int ch) {
|
|
int mapChar = ch;
|
|
int val = getProperties(ch);
|
|
|
|
if ((val & $$maskTitleCase) != 0) {
|
|
// There is a titlecase equivalent. Perform further checks:
|
|
if ((val & $$maskUpperCase) == 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 & $$maskLowerCase) == 0) {
|
|
// The character does not have a lowercase equivalent, so it must
|
|
// already be lowercase; so subtract 1 to get the titlecase form.
|
|
mapChar = ch - 1;
|
|
}
|
|
// else {
|
|
// The character has both an uppercase equivalent and a lowercase
|
|
// equivalent, so it must itself be a titlecase form; return it.
|
|
// return ch;
|
|
//}
|
|
}
|
|
else if ((val & $$maskUpperCase) != 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;
|
|
}
|
|
|
|
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 & $$maskType;
|
|
if (kind == Character.DECIMAL_DIGIT_NUMBER) {
|
|
value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
|
|
}
|
|
else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) {
|
|
// Java supradecimal digit
|
|
value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
|
|
}
|
|
}
|
|
return (value < radix) ? value : -1;
|
|
}
|
|
|
|
int getNumericValue(int ch) {
|
|
int val = getProperties(ch);
|
|
int retval = -1;
|
|
|
|
switch (val & $$maskNumericType) {
|
|
default: // cannot occur
|
|
case ($$valueNotNumeric): // not numeric
|
|
retval = -1;
|
|
break;
|
|
case ($$valueDigit): // simple numeric
|
|
retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
|
|
break;
|
|
case ($$valueStrangeNumeric) : // "strange" numeric
|
|
switch(ch) {
|
|
case 0x10113: retval = 40; break; // AEGEAN NUMBER FORTY
|
|
case 0x10114: retval = 50; break; // AEGEAN NUMBER FIFTY
|
|
case 0x10115: retval = 60; break; // AEGEAN NUMBER SIXTY
|
|
case 0x10116: retval = 70; break; // AEGEAN NUMBER SEVENTY
|
|
case 0x10117: retval = 80; break; // AEGEAN NUMBER EIGHTY
|
|
case 0x10118: retval = 90; break; // AEGEAN NUMBER NINETY
|
|
case 0x10119: retval = 100; break; // AEGEAN NUMBER ONE HUNDRED
|
|
case 0x1011A: retval = 200; break; // AEGEAN NUMBER TWO HUNDRED
|
|
case 0x1011B: retval = 300; break; // AEGEAN NUMBER THREE HUNDRED
|
|
case 0x1011C: retval = 400; break; // AEGEAN NUMBER FOUR HUNDRED
|
|
case 0x1011D: retval = 500; break; // AEGEAN NUMBER FIVE HUNDRED
|
|
case 0x1011E: retval = 600; break; // AEGEAN NUMBER SIX HUNDRED
|
|
case 0x1011F: retval = 700; break; // AEGEAN NUMBER SEVEN HUNDRED
|
|
case 0x10120: retval = 800; break; // AEGEAN NUMBER EIGHT HUNDRED
|
|
case 0x10121: retval = 900; break; // AEGEAN NUMBER NINE HUNDRED
|
|
case 0x10122: retval = 1000; break; // AEGEAN NUMBER ONE THOUSAND
|
|
case 0x10123: retval = 2000; break; // AEGEAN NUMBER TWO THOUSAND
|
|
case 0x10124: retval = 3000; break; // AEGEAN NUMBER THREE THOUSAND
|
|
case 0x10125: retval = 4000; break; // AEGEAN NUMBER FOUR THOUSAND
|
|
case 0x10126: retval = 5000; break; // AEGEAN NUMBER FIVE THOUSAND
|
|
case 0x10127: retval = 6000; break; // AEGEAN NUMBER SIX THOUSAND
|
|
case 0x10128: retval = 7000; break; // AEGEAN NUMBER SEVEN THOUSAND
|
|
case 0x10129: retval = 8000; break; // AEGEAN NUMBER EIGHT THOUSAND
|
|
case 0x1012A: retval = 9000; break; // AEGEAN NUMBER NINE THOUSAND
|
|
case 0x1012B: retval = 10000; break; // AEGEAN NUMBER TEN THOUSAND
|
|
case 0x1012C: retval = 20000; break; // AEGEAN NUMBER TWENTY THOUSAND
|
|
case 0x1012D: retval = 30000; break; // AEGEAN NUMBER THIRTY THOUSAND
|
|
case 0x1012E: retval = 40000; break; // AEGEAN NUMBER FORTY THOUSAND
|
|
case 0x1012F: retval = 50000; break; // AEGEAN NUMBER FIFTY THOUSAND
|
|
case 0x10130: retval = 60000; break; // AEGEAN NUMBER SIXTY THOUSAND
|
|
case 0x10131: retval = 70000; break; // AEGEAN NUMBER SEVENTY THOUSAND
|
|
case 0x10132: retval = 80000; break; // AEGEAN NUMBER EIGHTY THOUSAND
|
|
case 0x10133: retval = 90000; break; // AEGEAN NUMBER NINETY THOUSAND
|
|
case 0x10323: retval = 50; break; // OLD ITALIC NUMERAL FIFTY
|
|
default: retval = -2; break;
|
|
}
|
|
|
|
break;
|
|
case ($$valueJavaSupradecimal): // Java supradecimal
|
|
retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
|
|
break;
|
|
}
|
|
return retval;
|
|
}
|
|
|
|
boolean isWhitespace(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
|
|
}
|
|
|
|
byte getDirectionality(int ch) {
|
|
int val = getProperties(ch);
|
|
byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
|
|
if (directionality == 0xF ) {
|
|
directionality = Character.DIRECTIONALITY_UNDEFINED;
|
|
}
|
|
return directionality;
|
|
}
|
|
|
|
boolean isMirrored(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & $$maskMirrored) != 0);
|
|
}
|
|
|
|
static final CharacterData instance = new CharacterData01();
|
|
private CharacterData01() {};
|
|
|
|
$$Tables
|
|
|
|
static {
|
|
$$Initializers
|
|
}
|
|
}
|