You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
332 lines
13 KiB
332 lines
13 KiB
// This file was generated AUTOMATICALLY from a template file Sat Dec 15 18:42:53 PST 2018
|
|
/*
|
|
* Copyright (c) 2002, 2013, Oracle and/or its affiliates. All rights reserved.
|
|
* ORACLE PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*
|
|
*/
|
|
|
|
package java.lang;
|
|
|
|
/** The CharacterData class encapsulates the large tables found in
|
|
Java.lang.Character. */
|
|
|
|
class CharacterDataLatin1 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 = A[offset];
|
|
return props;
|
|
}
|
|
|
|
int getPropertiesEx(int ch) {
|
|
char offset = (char)ch;
|
|
int props = B[offset];
|
|
return props;
|
|
}
|
|
|
|
boolean isOtherLowercase(int ch) {
|
|
int props = getPropertiesEx(ch);
|
|
return (props & 0x0001) != 0;
|
|
}
|
|
|
|
boolean isOtherUppercase(int ch) {
|
|
int props = getPropertiesEx(ch);
|
|
return (props & 0x0002) != 0;
|
|
}
|
|
|
|
boolean isOtherAlphabetic(int ch) {
|
|
int props = getPropertiesEx(ch);
|
|
return (props & 0x0004) != 0;
|
|
}
|
|
|
|
boolean isIdeographic(int ch) {
|
|
int props = getPropertiesEx(ch);
|
|
return (props & 0x0010) != 0;
|
|
}
|
|
|
|
int getType(int ch) {
|
|
int props = getProperties(ch);
|
|
return (props & 0x1F);
|
|
}
|
|
|
|
boolean isJavaIdentifierStart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x00007000) >= 0x00005000);
|
|
}
|
|
|
|
boolean isJavaIdentifierPart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x00003000) != 0);
|
|
}
|
|
|
|
boolean isUnicodeIdentifierStart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x00007000) == 0x00007000);
|
|
}
|
|
|
|
boolean isUnicodeIdentifierPart(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x00001000) != 0);
|
|
}
|
|
|
|
boolean isIdentifierIgnorable(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x00007000) == 0x00001000);
|
|
}
|
|
|
|
int toLowerCase(int ch) {
|
|
int mapChar = ch;
|
|
int val = getProperties(ch);
|
|
|
|
if (((val & 0x00020000) != 0) &&
|
|
((val & 0x07FC0000) != 0x07FC0000)) {
|
|
int offset = val << 5 >> (5+18);
|
|
mapChar = ch + offset;
|
|
}
|
|
return mapChar;
|
|
}
|
|
|
|
int toUpperCase(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 if (ch == 0x00B5) {
|
|
mapChar = 0x039C;
|
|
}
|
|
}
|
|
return mapChar;
|
|
}
|
|
|
|
int toTitleCase(int ch) {
|
|
return toUpperCase(ch);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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
|
|
retval = -2;
|
|
break;
|
|
case (0x00000C00): // Java supradecimal
|
|
retval = (ch + ((val & 0x3E0) >> 5) & 0x1F) + 10;
|
|
break;
|
|
}
|
|
return retval;
|
|
}
|
|
|
|
boolean isWhitespace(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x00007000) == 0x00004000);
|
|
}
|
|
|
|
byte getDirectionality(int ch) {
|
|
int val = getProperties(ch);
|
|
byte directionality = (byte)((val & 0x78000000) >> 27);
|
|
|
|
if (directionality == 0xF ) {
|
|
directionality = -1;
|
|
}
|
|
return directionality;
|
|
}
|
|
|
|
boolean isMirrored(int ch) {
|
|
int props = getProperties(ch);
|
|
return ((props & 0x80000000) != 0);
|
|
}
|
|
|
|
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;
|
|
default : mapChar = Character.ERROR; break;
|
|
}
|
|
}
|
|
}
|
|
return mapChar;
|
|
}
|
|
|
|
static char[] sharpsMap = new char[] {'S', 'S'};
|
|
|
|
char[] toUpperCaseCharArray(int ch) {
|
|
char[] upperMap = {(char)ch};
|
|
if (ch == 0x00DF) {
|
|
upperMap = sharpsMap;
|
|
}
|
|
return upperMap;
|
|
}
|
|
|
|
static final CharacterDataLatin1 instance = new CharacterDataLatin1();
|
|
private CharacterDataLatin1() {};
|
|
|
|
// The following tables and code generated using:
|
|
// java GenerateCharacter -template c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u201/12322/jdk/make/data/characterdata/CharacterDataLatin1.java.template -spec c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u201/12322/jdk/make/data/unicodedata/UnicodeData.txt -specialcasing c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u201/12322/jdk/make/data/unicodedata/SpecialCasing.txt -proplist c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u201/12322/jdk/make/data/unicodedata/PropList.txt -o c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u201/12322/build/windows-amd64/jdk/gensrc/java/lang/CharacterDataLatin1.java -string -usecharforbyte -latin1 8
|
|
// The A table has 256 entries for a total of 1024 bytes.
|
|
|
|
static final int A[] = new int[256];
|
|
static final String A_DATA =
|
|
"\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
|
|
"\u100F\u4800\u100F\u4800\u100F\u5800\u400F\u5000\u400F\u5800\u400F\u6000\u400F"+
|
|
"\u5000\u400F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
|
|
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F"+
|
|
"\u4800\u100F\u4800\u100F\u5000\u400F\u5000\u400F\u5000\u400F\u5800\u400F\u6000"+
|
|
"\u400C\u6800\030\u6800\030\u2800\030\u2800\u601A\u2800\030\u6800\030\u6800"+
|
|
"\030\uE800\025\uE800\026\u6800\030\u2000\031\u3800\030\u2000\024\u3800\030"+
|
|
"\u3800\030\u1800\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u1800"+
|
|
"\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u3800\030\u6800\030"+
|
|
"\uE800\031\u6800\031\uE800\031\u6800\030\u6800\030\202\u7FE1\202\u7FE1\202"+
|
|
"\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1"+
|
|
"\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202"+
|
|
"\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1"+
|
|
"\202\u7FE1\uE800\025\u6800\030\uE800\026\u6800\033\u6800\u5017\u6800\033\201"+
|
|
"\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2"+
|
|
"\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201"+
|
|
"\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2"+
|
|
"\201\u7FE2\201\u7FE2\201\u7FE2\uE800\025\u6800\031\uE800\026\u6800\031\u4800"+
|
|
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u5000\u100F"+
|
|
"\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
|
|
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F"+
|
|
"\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
|
|
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F"+
|
|
"\u3800\014\u6800\030\u2800\u601A\u2800\u601A\u2800\u601A\u2800\u601A\u6800"+
|
|
"\034\u6800\030\u6800\033\u6800\034\000\u7005\uE800\035\u6800\031\u4800\u1010"+
|
|
"\u6800\034\u6800\033\u2800\034\u2800\031\u1800\u060B\u1800\u060B\u6800\033"+
|
|
"\u07FD\u7002\u6800\030\u6800\030\u6800\033\u1800\u050B\000\u7005\uE800\036"+
|
|
"\u6800\u080B\u6800\u080B\u6800\u080B\u6800\030\202\u7001\202\u7001\202\u7001"+
|
|
"\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202"+
|
|
"\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001"+
|
|
"\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\u6800\031\202\u7001\202"+
|
|
"\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\u07FD\u7002\201\u7002"+
|
|
"\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201"+
|
|
"\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002"+
|
|
"\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\u6800"+
|
|
"\031\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002"+
|
|
"\u061D\u7002";
|
|
|
|
// The B table has 256 entries for a total of 512 bytes.
|
|
|
|
static final char B[] = (
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\001"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\001\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
|
|
"\000\000\000\000\000\000\000\000\000").toCharArray();
|
|
|
|
// In all, the character property tables require 1024 bytes.
|
|
|
|
static {
|
|
{ // THIS CODE WAS AUTOMATICALLY CREATED BY GenerateCharacter:
|
|
char[] data = A_DATA.toCharArray();
|
|
assert (data.length == (256 * 2));
|
|
int i = 0, j = 0;
|
|
while (i < (256 * 2)) {
|
|
int entry = data[i++] << 16;
|
|
A[j++] = entry | data[i++];
|
|
}
|
|
}
|
|
|
|
}
|
|
}
|
|
|