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 getType(ch) == Character.DECIMAL_DIGIT_NUMBER;
86 }
87
88 @HotSpotIntrinsicCandidate
89 boolean isLowerCase(int ch) {
90 return getType(ch) == Character.LOWERCASE_LETTER;
91 }
92
93 @HotSpotIntrinsicCandidate
94 boolean isUpperCase(int ch) {
95 return getType(ch) == Character.UPPERCASE_LETTER;
96 }
97
98 boolean isOtherLowercase(int ch) {
99 int props = getPropertiesEx(ch);
100 return (props & $$maskOtherLowercase) != 0;
101 }
102
103 boolean isOtherUppercase(int ch) {
104 int props = getPropertiesEx(ch);
105 return (props & $$maskOtherUppercase) != 0;
106 }
107
108 boolean isOtherAlphabetic(int ch) {
109 int props = getPropertiesEx(ch);
110 return (props & $$maskOtherAlphabetic) != 0;
111 }
112
113 boolean isIdeographic(int ch) {
114 int props = getPropertiesEx(ch);
115 return (props & $$maskIdeographic) != 0;
116 }
117
118 int getType(int ch) {
119 int props = getProperties(ch);
120 return (props & $$maskType);
121 }
122
123 boolean isJavaIdentifierStart(int ch) {
124 int props = getProperties(ch);
125 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
126 }
127
128 boolean isJavaIdentifierPart(int ch) {
129 int props = getProperties(ch);
130 return ((props & $$nonzeroJavaPart) != 0);
131 }
132
133 boolean isUnicodeIdentifierStart(int ch) {
134 int props = getProperties(ch);
135 return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
136 }
137
138 boolean isUnicodeIdentifierPart(int ch) {
139 int props = getProperties(ch);
140 return ((props & $$maskUnicodePart) != 0);
141 }
142
143 boolean isIdentifierIgnorable(int ch) {
144 int props = getProperties(ch);
145 return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
146 }
147
148 int toLowerCase(int ch) {
149 int mapChar = ch;
150 int val = getProperties(ch);
151
152 if (((val & $$maskLowerCase) != 0) &&
153 ((val & $$maskCaseOffset) != $$maskCaseOffset)) {
154 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
155 mapChar = ch + offset;
156 }
157 return mapChar;
158 }
159
160 int toUpperCase(int ch) {
161 int mapChar = ch;
162 int val = getProperties(ch);
163
164 if ((val & $$maskUpperCase) != 0) {
165 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
166 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
167 mapChar = ch - offset;
168 } else if (ch == 0x00B5) {
169 mapChar = 0x039C;
170 }
171 }
172 return mapChar;
173 }
174
175 int toTitleCase(int ch) {
176 return toUpperCase(ch);
177 }
178
179 // Digit values for codePoints in the 0-255 range. Contents generated using:
180 // for (char i = 0; i < 256; i++) {
181 // int v = -1;
182 // if (i >= '0' && i <= '9') { v = i - '0'; }
183 // else if (i >= 'A' && i <= 'Z') { v = i - 'A' + 10; }
184 // else if (i >= 'a' && i <= 'z') { v = i - 'a' + 10; }
185 // if (i % 20 == 0) System.out.println();
186 // System.out.printf("%2d, ", v);
187 // }
188 //
189 // Analysis has shown that generating the whole array allows the JIT to generate
190 // better code compared to a slimmed down array, such as one cutting off after 'z'
191 private static final byte[] DIGITS = new byte[] {
192 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
193 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
194 -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1,
195 -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
196 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1, 10, 11, 12,
197 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
198 33, 34, 35, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
199 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
200 -1, -1, -1, -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 };
205
206 int digit(int ch, int radix) {
207 int value = DIGITS[ch];
208 return (value >= 0 && value < radix && radix >= Character.MIN_RADIX
209 && radix <= Character.MAX_RADIX) ? value : -1;
210 }
211
212 int getNumericValue(int ch) {
213 int val = getProperties(ch);
214 int retval = -1;
215
216 switch (val & $$maskNumericType) {
217 default: // cannot occur
218 case ($$valueNotNumeric): // not numeric
219 retval = -1;
220 break;
221 case ($$valueDigit): // simple numeric
222 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
223 break;
224 case ($$valueStrangeNumeric) : // "strange" numeric
225 retval = -2;
226 break;
227 case ($$valueJavaSupradecimal): // Java supradecimal
228 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
229 break;
230 }
231 return retval;
232 }
233
234 @HotSpotIntrinsicCandidate
235 boolean isWhitespace(int ch) {
236 int props = getProperties(ch);
237 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
238 }
239
240 byte getDirectionality(int ch) {
241 int val = getProperties(ch);
242 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
243
244 if (directionality == 0xF ) {
245 directionality = -1;
246 }
247 return directionality;
248 }
249
250 boolean isMirrored(int ch) {
251 int props = getProperties(ch);
252 return ((props & $$maskMirrored) != 0);
253 }
254
255 int toUpperCaseEx(int ch) {
256 int mapChar = ch;
257 int val = getProperties(ch);
258
259 if ((val & $$maskUpperCase) != 0) {
260 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
261 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
262 mapChar = ch - offset;
263 }
264 else {
265 switch(ch) {
266 // map overflow characters
267 case 0x00B5 : mapChar = 0x039C; break;
268 default : mapChar = Character.ERROR; break;
269 }
270 }
271 }
272 return mapChar;
273 }
274
275 static char[] sharpsMap = new char[] {'S', 'S'};
276
277 char[] toUpperCaseCharArray(int ch) {
278 char[] upperMap = {(char)ch};
279 if (ch == 0x00DF) {
280 upperMap = sharpsMap;
281 }
282 return upperMap;
283 }
284
285 static final CharacterDataLatin1 instance = new CharacterDataLatin1();
286 private CharacterDataLatin1() {};
287
288 $$Tables
289
290 static {
291 $$Initializers
292 }
293 }
294