| 1 |
758 |
jeremybenn |
/* java.lang.Character -- Wrapper class for char, and Unicode subsets
|
| 2 |
|
|
Copyright (C) 1998, 1999, 2001, 2002, 2007 Free Software Foundation, Inc.
|
| 3 |
|
|
|
| 4 |
|
|
This file is part of GNU Classpath.
|
| 5 |
|
|
|
| 6 |
|
|
GNU Classpath is free software; you can redistribute it and/or modify
|
| 7 |
|
|
it under the terms of the GNU General Public License as published by
|
| 8 |
|
|
the Free Software Foundation; either version 2, or (at your option)
|
| 9 |
|
|
any later version.
|
| 10 |
|
|
|
| 11 |
|
|
GNU Classpath is distributed in the hope that it will be useful, but
|
| 12 |
|
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
| 13 |
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
| 14 |
|
|
General Public License for more details.
|
| 15 |
|
|
|
| 16 |
|
|
You should have received a copy of the GNU General Public License
|
| 17 |
|
|
along with GNU Classpath; see the file COPYING. If not, write to the
|
| 18 |
|
|
Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
|
| 19 |
|
|
02110-1301 USA.
|
| 20 |
|
|
|
| 21 |
|
|
Linking this library statically or dynamically with other modules is
|
| 22 |
|
|
making a combined work based on this library. Thus, the terms and
|
| 23 |
|
|
conditions of the GNU General Public License cover the whole
|
| 24 |
|
|
combination.
|
| 25 |
|
|
|
| 26 |
|
|
As a special exception, the copyright holders of this library give you
|
| 27 |
|
|
permission to link this library with independent modules to produce an
|
| 28 |
|
|
executable, regardless of the license terms of these independent
|
| 29 |
|
|
modules, and to copy and distribute the resulting executable under
|
| 30 |
|
|
terms of your choice, provided that you also meet, for each linked
|
| 31 |
|
|
independent module, the terms and conditions of the license of that
|
| 32 |
|
|
module. An independent module is a module which is not derived from
|
| 33 |
|
|
or based on this library. If you modify this library, you may extend
|
| 34 |
|
|
this exception to your version of the library, but you are not
|
| 35 |
|
|
obligated to do so. If you do not wish to do so, delete this
|
| 36 |
|
|
exception statement from your version. */
|
| 37 |
|
|
|
| 38 |
|
|
#include <config.h>
|
| 39 |
|
|
|
| 40 |
|
|
#include <gcj/cni.h>
|
| 41 |
|
|
#include <jvm.h>
|
| 42 |
|
|
#include <java/lang/Character.h>
|
| 43 |
|
|
|
| 44 |
|
|
#include <java-chartables.h>
|
| 45 |
|
|
|
| 46 |
|
|
|
| 47 |
|
|
|
| 48 |
|
|
// These constants define the return values for characters that are unassigned
|
| 49 |
|
|
// or reserved for private use.
|
| 50 |
|
|
#define UNASSIGNED_TYPE 0
|
| 51 |
|
|
#define UNASSIGNED_DIGIT -1
|
| 52 |
|
|
#define UNASSIGNED_DIRECTION -1
|
| 53 |
|
|
#define UNASSIGNED_NUMERIC_VALUE -1
|
| 54 |
|
|
|
| 55 |
|
|
#define PRIVATE_TYPE 18
|
| 56 |
|
|
#define PRIVATE_DIRECTION 0
|
| 57 |
|
|
|
| 58 |
|
|
// The methods that take a char as an argument all have counterparts that
|
| 59 |
|
|
// take ints. The ones that take chars only work for the BMP or plane 0 of the
|
| 60 |
|
|
// Unicode standard but the ones that take ints work for all Unicode code
|
| 61 |
|
|
// points. However, the ones that take chars don't simply redirect the calls
|
| 62 |
|
|
// because the BMP is by far the most used plane so saving a little time on
|
| 63 |
|
|
// each call makes sense.
|
| 64 |
|
|
|
| 65 |
|
|
jchar
|
| 66 |
|
|
java::lang::Character::readChar(jchar ch)
|
| 67 |
|
|
{
|
| 68 |
|
|
// Perform 16-bit addition to find the correct entry in data.
|
| 69 |
|
|
return data[0][(jchar) (blocks[0][ch >> shift[0]] + ch)];
|
| 70 |
|
|
}
|
| 71 |
|
|
|
| 72 |
|
|
jchar
|
| 73 |
|
|
java::lang::Character::readCodePoint(jint codePoint)
|
| 74 |
|
|
{
|
| 75 |
|
|
jint plane = codePoint >> 16;
|
| 76 |
|
|
jchar offset = (jchar)(codePoint & 0xffff);
|
| 77 |
|
|
// Be careful not to call this method with an unassigned character. The only
|
| 78 |
|
|
// characters assigned as of Unicode 4.0.0 belong to planes 0, 1, 2, and 14.
|
| 79 |
|
|
return data[plane][(jchar) (blocks[plane][offset >> shift[plane]] + offset)];
|
| 80 |
|
|
}
|
| 81 |
|
|
|
| 82 |
|
|
jint
|
| 83 |
|
|
java::lang::Character::getType(jchar ch)
|
| 84 |
|
|
{
|
| 85 |
|
|
// Perform 16-bit addition to find the correct entry in data.
|
| 86 |
|
|
return (jint) (data[0][(jchar) (blocks[0][ch >> shift[0]] + ch)] & TYPE_MASK);
|
| 87 |
|
|
}
|
| 88 |
|
|
|
| 89 |
|
|
jint
|
| 90 |
|
|
java::lang::Character::getType(jint codePoint)
|
| 91 |
|
|
{
|
| 92 |
|
|
jint plane = codePoint >> 16;
|
| 93 |
|
|
if (plane < 0 || (plane > 2 && plane != 14))
|
| 94 |
|
|
{
|
| 95 |
|
|
if (plane > 14 && ((codePoint & 0xffff) < 0xfffe))
|
| 96 |
|
|
return (jint) PRIVATE_TYPE;
|
| 97 |
|
|
return (jint) UNASSIGNED_TYPE;
|
| 98 |
|
|
}
|
| 99 |
|
|
jint offset = codePoint & 0xffff;
|
| 100 |
|
|
return (jint)
|
| 101 |
|
|
(data[plane]
|
| 102 |
|
|
[(jchar) (blocks[plane][offset >> shift[plane]] + offset)] & TYPE_MASK);
|
| 103 |
|
|
}
|
| 104 |
|
|
|
| 105 |
|
|
jchar
|
| 106 |
|
|
java::lang::Character::toLowerCase(jchar ch)
|
| 107 |
|
|
{
|
| 108 |
|
|
return (jchar) (ch + lower[0][readChar(ch) >> 7]);
|
| 109 |
|
|
}
|
| 110 |
|
|
|
| 111 |
|
|
jint
|
| 112 |
|
|
java::lang::Character::toLowerCase(jint codePoint)
|
| 113 |
|
|
{
|
| 114 |
|
|
jint plane = codePoint >> 16;
|
| 115 |
|
|
if (plane < 0 || (plane > 2 && plane != 14))
|
| 116 |
|
|
return codePoint;
|
| 117 |
|
|
return (lower[plane][readCodePoint(codePoint) >> 7]) + codePoint;
|
| 118 |
|
|
}
|
| 119 |
|
|
|
| 120 |
|
|
jchar
|
| 121 |
|
|
java::lang::Character::toUpperCase(jchar ch)
|
| 122 |
|
|
{
|
| 123 |
|
|
return (jchar) (ch + upper[0][readChar(ch) >> 7]);
|
| 124 |
|
|
}
|
| 125 |
|
|
|
| 126 |
|
|
jint
|
| 127 |
|
|
java::lang::Character::toUpperCase(jint codePoint)
|
| 128 |
|
|
{
|
| 129 |
|
|
jint plane = codePoint >> 16;
|
| 130 |
|
|
if (plane < 0 || (plane > 2 && plane != 14))
|
| 131 |
|
|
return codePoint;
|
| 132 |
|
|
return (upper[plane][readCodePoint(codePoint) >> 7]) + codePoint;
|
| 133 |
|
|
}
|
| 134 |
|
|
|
| 135 |
|
|
jchar
|
| 136 |
|
|
java::lang::Character::toTitleCase(jchar ch)
|
| 137 |
|
|
{
|
| 138 |
|
|
// As title is short, it doesn't hurt to exhaustively iterate over it.
|
| 139 |
|
|
for (int i = title_length - 2; i >= 0; i -= 2)
|
| 140 |
|
|
if (title[i] == ch)
|
| 141 |
|
|
return title[i + 1];
|
| 142 |
|
|
return toUpperCase(ch);
|
| 143 |
|
|
}
|
| 144 |
|
|
|
| 145 |
|
|
jint
|
| 146 |
|
|
java::lang::Character::toTitleCase(jint codePoint)
|
| 147 |
|
|
{
|
| 148 |
|
|
// As of Unicode 4.0.0 no characters outside of plane 0 have titlecase
|
| 149 |
|
|
// mappings that are different from their uppercase mapping.
|
| 150 |
|
|
if (codePoint >= 0 && codePoint < 0x10000)
|
| 151 |
|
|
return toTitleCase((jchar)codePoint);
|
| 152 |
|
|
return toUpperCase(codePoint);
|
| 153 |
|
|
}
|
| 154 |
|
|
|
| 155 |
|
|
jint
|
| 156 |
|
|
java::lang::Character::digit(jchar ch, jint radix)
|
| 157 |
|
|
{
|
| 158 |
|
|
if (radix < MIN_RADIX || radix > MAX_RADIX)
|
| 159 |
|
|
return (jint) -1;
|
| 160 |
|
|
jchar attr = readChar(ch);
|
| 161 |
|
|
if (((1 << (attr & TYPE_MASK))
|
| 162 |
|
|
& ((1 << UPPERCASE_LETTER)
|
| 163 |
|
|
| (1 << LOWERCASE_LETTER)
|
| 164 |
|
|
| (1 << DECIMAL_DIGIT_NUMBER))))
|
| 165 |
|
|
{
|
| 166 |
|
|
// Signedness doesn't matter; 0xffff vs. -1 are both rejected.
|
| 167 |
|
|
jint digit = (jint) numValue[0][attr >> 7];
|
| 168 |
|
|
return (digit >= 0 && digit < radix) ? digit : (jint) -1;
|
| 169 |
|
|
}
|
| 170 |
|
|
return (jint) -1;
|
| 171 |
|
|
}
|
| 172 |
|
|
|
| 173 |
|
|
jint
|
| 174 |
|
|
java::lang::Character::digit(jint codePoint, jint radix)
|
| 175 |
|
|
{
|
| 176 |
|
|
if (radix < MIN_RADIX || radix > MAX_RADIX)
|
| 177 |
|
|
return (jint) -1;
|
| 178 |
|
|
|
| 179 |
|
|
jint plane = codePoint >> 16;
|
| 180 |
|
|
if (plane < 0 || (plane > 2 && plane != 14))
|
| 181 |
|
|
return UNASSIGNED_DIGIT;
|
| 182 |
|
|
|
| 183 |
|
|
jchar attr = readCodePoint(codePoint);
|
| 184 |
|
|
if (((1 << (attr & TYPE_MASK))
|
| 185 |
|
|
& ((1 << UPPERCASE_LETTER)
|
| 186 |
|
|
| (1 << LOWERCASE_LETTER)
|
| 187 |
|
|
| (1 << DECIMAL_DIGIT_NUMBER))))
|
| 188 |
|
|
{
|
| 189 |
|
|
// Signedness doesn't matter; 0xffff vs. -1 are both rejected.
|
| 190 |
|
|
jint digit = (jint) numValue[plane][attr >> 7];
|
| 191 |
|
|
if (digit <= -3)
|
| 192 |
|
|
digit = largenums[-digit -3];
|
| 193 |
|
|
return (digit >= 0 && digit < radix) ? digit : (jint) -1;
|
| 194 |
|
|
}
|
| 195 |
|
|
return (jint) -1;
|
| 196 |
|
|
|
| 197 |
|
|
}
|
| 198 |
|
|
|
| 199 |
|
|
jint
|
| 200 |
|
|
java::lang::Character::getNumericValue(jchar ch)
|
| 201 |
|
|
{
|
| 202 |
|
|
// numValue is stored as an array of jshort, since 10000 is the maximum.
|
| 203 |
|
|
return (jint) numValue[0][readChar(ch) >> 7];
|
| 204 |
|
|
}
|
| 205 |
|
|
|
| 206 |
|
|
jint
|
| 207 |
|
|
java::lang::Character::getNumericValue(jint codePoint)
|
| 208 |
|
|
{
|
| 209 |
|
|
jint plane = codePoint >> 16;
|
| 210 |
|
|
if (plane < 0 || (plane > 2 && plane != 14))
|
| 211 |
|
|
return UNASSIGNED_NUMERIC_VALUE;
|
| 212 |
|
|
jshort num = numValue[plane][readCodePoint(codePoint) >> 7];
|
| 213 |
|
|
if (num <= -3)
|
| 214 |
|
|
return largenums[-num - 3];
|
| 215 |
|
|
return num;
|
| 216 |
|
|
}
|
| 217 |
|
|
|
| 218 |
|
|
jbyte
|
| 219 |
|
|
java::lang::Character::getDirectionality(jchar ch)
|
| 220 |
|
|
{
|
| 221 |
|
|
return direction[0][readChar(ch) >> 7];
|
| 222 |
|
|
}
|
| 223 |
|
|
|
| 224 |
|
|
jbyte
|
| 225 |
|
|
java::lang::Character::getDirectionality(jint codePoint)
|
| 226 |
|
|
{
|
| 227 |
|
|
jint plane = codePoint >> 16;
|
| 228 |
|
|
if (plane < 0 || (plane > 2 && plane != 14))
|
| 229 |
|
|
{
|
| 230 |
|
|
if (plane > 14 && ((codePoint & 0xffff) < 0xfffe))
|
| 231 |
|
|
return (jint) PRIVATE_DIRECTION;
|
| 232 |
|
|
return (jint) UNASSIGNED_DIRECTION;
|
| 233 |
|
|
}
|
| 234 |
|
|
return direction[plane][readCodePoint(codePoint) >> 7];
|
| 235 |
|
|
}
|