author | sherman |
Thu, 28 Apr 2011 20:18:57 -0700 | |
changeset 9535 | d930011fd275 |
parent 5506 | 202f599c92aa |
child 14342 | 8435a30053c1 |
permissions | -rw-r--r-- |
2 | 1 |
/* |
5506 | 2 |
* Copyright (c) 2002, 2006, Oracle and/or its affiliates. All rights reserved. |
2 | 3 |
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. |
4 |
* |
|
5 |
* This code is free software; you can redistribute it and/or modify it |
|
6 |
* under the terms of the GNU General Public License version 2 only, as |
|
5506 | 7 |
* published by the Free Software Foundation. Oracle designates this |
2 | 8 |
* particular file as subject to the "Classpath" exception as provided |
5506 | 9 |
* by Oracle in the LICENSE file that accompanied this code. |
2 | 10 |
* |
11 |
* This code is distributed in the hope that it will be useful, but WITHOUT |
|
12 |
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or |
|
13 |
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
|
14 |
* version 2 for more details (a copy is included in the LICENSE file that |
|
15 |
* accompanied this code). |
|
16 |
* |
|
17 |
* You should have received a copy of the GNU General Public License version |
|
18 |
* 2 along with this work; if not, write to the Free Software Foundation, |
|
19 |
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. |
|
20 |
* |
|
5506 | 21 |
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA |
22 |
* or visit www.oracle.com if you need additional information or have any |
|
23 |
* questions. |
|
2 | 24 |
*/ |
25 |
||
26 |
package java.lang; |
|
27 |
||
28 |
/** The CharacterData class encapsulates the large tables found in |
|
29 |
Java.lang.Character. */ |
|
30 |
||
31 |
class CharacterDataLatin1 extends CharacterData { |
|
32 |
||
33 |
/* The character properties are currently encoded into 32 bits in the following manner: |
|
34 |
1 bit mirrored property |
|
35 |
4 bits directionality property |
|
36 |
9 bits signed offset used for converting case |
|
37 |
1 bit if 1, adding the signed offset converts the character to lowercase |
|
38 |
1 bit if 1, subtracting the signed offset converts the character to uppercase |
|
39 |
1 bit if 1, this character has a titlecase equivalent (possibly itself) |
|
40 |
3 bits 0 may not be part of an identifier |
|
41 |
1 ignorable control; may continue a Unicode identifier or Java identifier |
|
42 |
2 may continue a Java identifier but not a Unicode identifier (unused) |
|
43 |
3 may continue a Unicode identifier or Java identifier |
|
44 |
4 is a Java whitespace character |
|
45 |
5 may start or continue a Java identifier; |
|
46 |
may continue but not start a Unicode identifier (underscores) |
|
47 |
6 may start or continue a Java identifier but not a Unicode identifier ($) |
|
48 |
7 may start or continue a Unicode identifier or Java identifier |
|
49 |
Thus: |
|
50 |
5, 6, 7 may start a Java identifier |
|
51 |
1, 2, 3, 5, 6, 7 may continue a Java identifier |
|
52 |
7 may start a Unicode identifier |
|
53 |
1, 3, 5, 7 may continue a Unicode identifier |
|
54 |
1 is ignorable within an identifier |
|
55 |
4 is Java whitespace |
|
56 |
2 bits 0 this character has no numeric property |
|
57 |
1 adding the digit offset to the character code and then |
|
58 |
masking with 0x1F will produce the desired numeric value |
|
59 |
2 this character has a "strange" numeric value |
|
60 |
3 a Java supradecimal digit: adding the digit offset to the |
|
61 |
character code, then masking with 0x1F, then adding 10 |
|
62 |
will produce the desired numeric value |
|
63 |
5 bits digit offset |
|
64 |
5 bits character type |
|
65 |
||
66 |
The encoding of character properties is subject to change at any time. |
|
67 |
*/ |
|
68 |
||
69 |
int getProperties(int ch) { |
|
9535
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
70 |
char offset = (char)ch; |
2 | 71 |
int props = $$Lookup(offset); |
72 |
return props; |
|
73 |
} |
|
74 |
||
9535
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
75 |
int getPropertiesEx(int ch) { |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
76 |
char offset = (char)ch; |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
77 |
int props = $$LookupEx(offset); |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
78 |
return props; |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
79 |
} |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
80 |
|
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
81 |
boolean isOtherLowercase(int ch) { |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
82 |
int props = getPropertiesEx(ch); |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
83 |
return (props & $$maskOtherLowercase) != 0; |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
84 |
} |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
85 |
|
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
86 |
boolean isOtherUppercase(int ch) { |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
87 |
int props = getPropertiesEx(ch); |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
88 |
return (props & $$maskOtherUppercase) != 0; |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
89 |
} |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
90 |
|
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
91 |
boolean isOtherAlphabetic(int ch) { |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
92 |
int props = getPropertiesEx(ch); |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
93 |
return (props & $$maskOtherAlphabetic) != 0; |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
94 |
} |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
95 |
|
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
96 |
boolean isIdeographic(int ch) { |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
97 |
int props = getPropertiesEx(ch); |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
98 |
return (props & $$maskIdeographic) != 0; |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
99 |
} |
d930011fd275
7037261: j.l.Character.isLowerCase/isUpperCase need to match the Unicode Standard
sherman
parents:
5506
diff
changeset
|
100 |
|
2 | 101 |
int getType(int ch) { |
102 |
int props = getProperties(ch); |
|
103 |
return (props & $$maskType); |
|
104 |
} |
|
105 |
||
106 |
boolean isJavaIdentifierStart(int ch) { |
|
107 |
int props = getProperties(ch); |
|
108 |
return ((props & $$maskIdentifierInfo) >= $$lowJavaStart); |
|
109 |
} |
|
110 |
||
111 |
boolean isJavaIdentifierPart(int ch) { |
|
112 |
int props = getProperties(ch); |
|
113 |
return ((props & $$nonzeroJavaPart) != 0); |
|
114 |
} |
|
115 |
||
116 |
boolean isUnicodeIdentifierStart(int ch) { |
|
117 |
int props = getProperties(ch); |
|
118 |
return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart); |
|
119 |
} |
|
120 |
||
121 |
boolean isUnicodeIdentifierPart(int ch) { |
|
122 |
int props = getProperties(ch); |
|
123 |
return ((props & $$maskUnicodePart) != 0); |
|
124 |
} |
|
125 |
||
126 |
boolean isIdentifierIgnorable(int ch) { |
|
127 |
int props = getProperties(ch); |
|
128 |
return ((props & $$maskIdentifierInfo) == $$valueIgnorable); |
|
129 |
} |
|
130 |
||
131 |
int toLowerCase(int ch) { |
|
132 |
int mapChar = ch; |
|
133 |
int val = getProperties(ch); |
|
134 |
||
135 |
if (((val & $$maskLowerCase) != 0) && |
|
136 |
((val & $$maskCaseOffset) != $$maskCaseOffset)) { |
|
137 |
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
|
138 |
mapChar = ch + offset; |
|
139 |
} |
|
140 |
return mapChar; |
|
141 |
} |
|
142 |
||
143 |
int toUpperCase(int ch) { |
|
144 |
int mapChar = ch; |
|
145 |
int val = getProperties(ch); |
|
146 |
||
147 |
if ((val & $$maskUpperCase) != 0) { |
|
148 |
if ((val & $$maskCaseOffset) != $$maskCaseOffset) { |
|
149 |
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
|
150 |
mapChar = ch - offset; |
|
151 |
} else if (ch == 0x00B5) { |
|
152 |
mapChar = 0x039C; |
|
153 |
} |
|
154 |
} |
|
155 |
return mapChar; |
|
156 |
} |
|
157 |
||
158 |
int toTitleCase(int ch) { |
|
159 |
return toUpperCase(ch); |
|
160 |
} |
|
161 |
||
162 |
int digit(int ch, int radix) { |
|
163 |
int value = -1; |
|
164 |
if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) { |
|
165 |
int val = getProperties(ch); |
|
166 |
int kind = val & $$maskType; |
|
167 |
if (kind == Character.DECIMAL_DIGIT_NUMBER) { |
|
168 |
value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; |
|
169 |
} |
|
170 |
else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) { |
|
171 |
// Java supradecimal digit |
|
172 |
value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; |
|
173 |
} |
|
174 |
} |
|
175 |
return (value < radix) ? value : -1; |
|
176 |
} |
|
177 |
||
178 |
int getNumericValue(int ch) { |
|
179 |
int val = getProperties(ch); |
|
180 |
int retval = -1; |
|
181 |
||
182 |
switch (val & $$maskNumericType) { |
|
183 |
default: // cannot occur |
|
184 |
case ($$valueNotNumeric): // not numeric |
|
185 |
retval = -1; |
|
186 |
break; |
|
187 |
case ($$valueDigit): // simple numeric |
|
188 |
retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; |
|
189 |
break; |
|
190 |
case ($$valueStrangeNumeric) : // "strange" numeric |
|
191 |
retval = -2; |
|
192 |
break; |
|
193 |
case ($$valueJavaSupradecimal): // Java supradecimal |
|
194 |
retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; |
|
195 |
break; |
|
196 |
} |
|
197 |
return retval; |
|
198 |
} |
|
199 |
||
200 |
boolean isWhitespace(int ch) { |
|
201 |
int props = getProperties(ch); |
|
202 |
return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace); |
|
203 |
} |
|
204 |
||
205 |
byte getDirectionality(int ch) { |
|
206 |
int val = getProperties(ch); |
|
207 |
byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi); |
|
208 |
||
209 |
if (directionality == 0xF ) { |
|
210 |
directionality = -1; |
|
211 |
} |
|
212 |
return directionality; |
|
213 |
} |
|
214 |
||
215 |
boolean isMirrored(int ch) { |
|
216 |
int props = getProperties(ch); |
|
217 |
return ((props & $$maskMirrored) != 0); |
|
218 |
} |
|
219 |
||
220 |
int toUpperCaseEx(int ch) { |
|
221 |
int mapChar = ch; |
|
222 |
int val = getProperties(ch); |
|
223 |
||
224 |
if ((val & $$maskUpperCase) != 0) { |
|
225 |
if ((val & $$maskCaseOffset) != $$maskCaseOffset) { |
|
226 |
int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
|
227 |
mapChar = ch - offset; |
|
228 |
} |
|
229 |
else { |
|
230 |
switch(ch) { |
|
231 |
// map overflow characters |
|
232 |
case 0x00B5 : mapChar = 0x039C; break; |
|
233 |
default : mapChar = Character.ERROR; break; |
|
234 |
} |
|
235 |
} |
|
236 |
} |
|
237 |
return mapChar; |
|
238 |
} |
|
239 |
||
240 |
static char[] sharpsMap = new char[] {'S', 'S'}; |
|
241 |
||
242 |
char[] toUpperCaseCharArray(int ch) { |
|
243 |
char[] upperMap = {(char)ch}; |
|
244 |
if (ch == 0x00DF) { |
|
245 |
upperMap = sharpsMap; |
|
246 |
} |
|
247 |
return upperMap; |
|
248 |
} |
|
249 |
||
250 |
static final CharacterDataLatin1 instance = new CharacterDataLatin1(); |
|
251 |
private CharacterDataLatin1() {}; |
|
252 |
||
253 |
$$Tables |
|
254 |
||
255 |
static { |
|
256 |
$$Initializers |
|
257 |
} |
|
258 |
} |
|
259 |