1 /*
2 * Copyright (c) 2002, 2018, Oracle and/or its affiliates. All rights reserved.
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
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
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 *
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.
24 */
25
26 package java.lang;
27
28 import jdk.internal.HotSpotIntrinsicCandidate;
29
30 /** The CharacterData class encapsulates the large tables found in
31 Java.lang.Character. */
32
33 class CharacterDataLatin1 extends CharacterData {
34
35 /* The character properties are currently encoded into 32 bits in the following manner:
36 1 bit mirrored property
37 4 bits directionality property
38 9 bits signed offset used for converting case
39 1 bit if 1, adding the signed offset converts the character to lowercase
40 1 bit if 1, subtracting the signed offset converts the character to uppercase
41 1 bit if 1, this character has a titlecase equivalent (possibly itself)
42 3 bits 0 may not be part of an identifier
43 1 ignorable control; may continue a Unicode identifier or Java identifier
44 2 may continue a Java identifier but not a Unicode identifier (unused)
45 3 may continue a Unicode identifier or Java identifier
46 4 is a Java whitespace character
47 5 may start or continue a Java identifier;
48 may continue but not start a Unicode identifier (underscores)
49 6 may start or continue a Java identifier but not a Unicode identifier ($)
50 7 may start or continue a Unicode identifier or Java identifier
51 Thus:
52 5, 6, 7 may start a Java identifier
53 1, 2, 3, 5, 6, 7 may continue a Java identifier
54 7 may start a Unicode identifier
55 1, 3, 5, 7 may continue a Unicode identifier
56 1 is ignorable within an identifier
57 4 is Java whitespace
58 2 bits 0 this character has no numeric property
59 1 adding the digit offset to the character code and then
60 masking with 0x1F will produce the desired numeric value
61 2 this character has a "strange" numeric value
62 3 a Java supradecimal digit: adding the digit offset to the
63 character code, then masking with 0x1F, then adding 10
64 will produce the desired numeric value
65 5 bits digit offset
66 5 bits character type
67
68 The encoding of character properties is subject to change at any time.
69 */
70
71 int getProperties(int ch) {
72 char offset = (char)ch;
73 int props = $$Lookup(offset);
74 return props;
75 }
76
77 int getPropertiesEx(int ch) {
78 char offset = (char)ch;
79 int props = $$LookupEx(offset);
80 return props;
81 }
82
83 @HotSpotIntrinsicCandidate
84 boolean isDigit(int ch) {
85 return '0' <= ch && ch <= '9';
86 }
87
88 @HotSpotIntrinsicCandidate
89 boolean isLowerCase(int ch) {
90 int props = getProperties(ch);
91 return (props & $$maskType) == Character.LOWERCASE_LETTER;
92 }
93
94 @HotSpotIntrinsicCandidate
95 boolean isUpperCase(int ch) {
96 int props = getProperties(ch);
97 return (props & $$maskType) == Character.UPPERCASE_LETTER;
98 }
99
100 boolean isOtherLowercase(int ch) {
101 int props = getPropertiesEx(ch);
102 return (props & $$maskOtherLowercase) != 0;
103 }
104
105 boolean isOtherUppercase(int ch) {
106 int props = getPropertiesEx(ch);
107 return (props & $$maskOtherUppercase) != 0;
108 }
109
110 boolean isOtherAlphabetic(int ch) {
111 int props = getPropertiesEx(ch);
112 return (props & $$maskOtherAlphabetic) != 0;
113 }
114
115 boolean isIdeographic(int ch) {
116 int props = getPropertiesEx(ch);
117 return (props & $$maskIdeographic) != 0;
118 }
119
120 int getType(int ch) {
121 int props = getProperties(ch);
122 return (props & $$maskType);
123 }
124
125 boolean isJavaIdentifierStart(int ch) {
126 int props = getProperties(ch);
127 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
128 }
129
130 boolean isJavaIdentifierPart(int ch) {
131 int props = getProperties(ch);
132 return ((props & $$nonzeroJavaPart) != 0);
133 }
134
135 boolean isUnicodeIdentifierStart(int ch) {
136 int props = getProperties(ch);
137 return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
138 }
139
140 boolean isUnicodeIdentifierPart(int ch) {
141 int props = getProperties(ch);
142 return ((props & $$maskUnicodePart) != 0);
143 }
144
145 boolean isIdentifierIgnorable(int ch) {
146 int props = getProperties(ch);
147 return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
148 }
149
150 int toLowerCase(int ch) {
151 int mapChar = ch;
152 int val = getProperties(ch);
153
154 if (((val & $$maskLowerCase) != 0) &&
155 ((val & $$maskCaseOffset) != $$maskCaseOffset)) {
156 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
157 mapChar = ch + offset;
158 }
159 return mapChar;
160 }
161
162 int toUpperCase(int ch) {
163 int mapChar = ch;
164 int val = getProperties(ch);
165
166 if ((val & $$maskUpperCase) != 0) {
167 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
168 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
169 mapChar = ch - offset;
170 } else if (ch == 0x00B5) {
171 mapChar = 0x039C;
172 }
173 }
174 return mapChar;
175 }
176
177 int toTitleCase(int ch) {
178 return toUpperCase(ch);
179 }
180
181 // Digit values for codePoints in the 0-255 range. Contents generated using:
182 // for (char i = 0; i < 256; i++) {
183 // int v = -1;
184 // if (i >= '0' && i <= '9') { v = i - '0'; }
185 // else if (i >= 'A' && i <= 'Z') { v = i - 'A' + 10; }
186 // else if (i >= 'a' && i <= 'z') { v = i - 'a' + 10; }
187 // if (i % 20 == 0) System.out.println();
188 // System.out.printf("%2d, ", v);
189 // }
190 //
191 // Analysis has shown that generating the whole array allows the JIT to generate
192 // better code compared to a slimmed down array, such as one cutting off after 'z'
193 private static final byte[] DIGITS = new byte[] {
194 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
195 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
196 -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1,
197 -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
198 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1, 10, 11, 12,
199 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
200 33, 34, 35, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
201 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
202 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
203 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
204 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
205 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
206 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 };
207
208 int digit(int ch, int radix) {
209 int value = DIGITS[ch];
210 return (value >= 0 && value < radix && radix >= Character.MIN_RADIX
211 && radix <= Character.MAX_RADIX) ? value : -1;
212 }
213
214 int getNumericValue(int ch) {
215 int val = getProperties(ch);
216 int retval = -1;
217
218 switch (val & $$maskNumericType) {
219 default: // cannot occur
220 case ($$valueNotNumeric): // not numeric
221 retval = -1;
222 break;
223 case ($$valueDigit): // simple numeric
224 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
225 break;
226 case ($$valueStrangeNumeric) : // "strange" numeric
227 retval = -2;
228 break;
229 case ($$valueJavaSupradecimal): // Java supradecimal
230 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
231 break;
232 }
233 return retval;
234 }
235
236 @HotSpotIntrinsicCandidate
237 boolean isWhitespace(int ch) {
238 int props = getProperties(ch);
239 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
240 }
241
242 byte getDirectionality(int ch) {
243 int val = getProperties(ch);
244 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
245
246 if (directionality == 0xF ) {
247 directionality = -1;
248 }
249 return directionality;
250 }
251
252 boolean isMirrored(int ch) {
253 int props = getProperties(ch);
254 return ((props & $$maskMirrored) != 0);
255 }
256
257 int toUpperCaseEx(int ch) {
258 int mapChar = ch;
259 int val = getProperties(ch);
260
261 if ((val & $$maskUpperCase) != 0) {
262 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
263 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
264 mapChar = ch - offset;
265 }
266 else {
267 switch(ch) {
268 // map overflow characters
269 case 0x00B5 : mapChar = 0x039C; break;
270 default : mapChar = Character.ERROR; break;
271 }
272 }
273 }
274 return mapChar;
275 }
276
277 static char[] sharpsMap = new char[] {'S', 'S'};
278
279 char[] toUpperCaseCharArray(int ch) {
280 char[] upperMap = {(char)ch};
281 if (ch == 0x00DF) {
282 upperMap = sharpsMap;
283 }
284 return upperMap;
285 }
286
287 static final CharacterDataLatin1 instance = new CharacterDataLatin1();
288 private CharacterDataLatin1() {};
289
290 $$Tables
291
292 static {
293 $$Initializers
294 }
295 }
296