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 /** 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) {
70 char offset = (char)ch;
71 int props = $$Lookup(offset);
72 return props;
73 }
74
75 int getPropertiesEx(int ch) {
76 char offset = (char)ch;
77 int props = $$LookupEx(offset);
78 return props;
79 }
80
81 boolean isOtherLowercase(int ch) {
82 int props = getPropertiesEx(ch);
83 return (props & $$maskOtherLowercase) != 0;
84 }
85
86 boolean isOtherUppercase(int ch) {
87 int props = getPropertiesEx(ch);
88 return (props & $$maskOtherUppercase) != 0;
89 }
90
91 boolean isOtherAlphabetic(int ch) {
92 int props = getPropertiesEx(ch);
93 return (props & $$maskOtherAlphabetic) != 0;
94 }
95
96 boolean isIdeographic(int ch) {
97 int props = getPropertiesEx(ch);
98 return (props & $$maskIdeographic) != 0;
99 }
100
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 // Digit values for codePoints in the 0-255 range. Contents generated using:
163 // for (char i = 0; i < 256; i++) {
164 // int v = -1;
165 // if (i >= '0' && i <= '9') { v = i - '0'; }
166 // else if (i >= 'A' && i <= 'Z') { v = i - 'A' + 10; }
167 // else if (i >= 'a' && i <= 'z') { v = i - 'a' + 10; }
168 // if (i % 20 == 0) System.out.println();
169 // System.out.printf("%2d, ", v);
170 // }
171 //
172 // Analysis has shown that generating the whole array allows the JIT to generate
173 // better code compared to a slimmed down array, such as one cutting off after 'z'
174 private static final byte[] DIGITS = new byte[] {
175 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
176 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
177 -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1,
178 -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
179 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1, 10, 11, 12,
180 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
181 33, 34, 35, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
182 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
183 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
184 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
185 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
186 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
187 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 };
188
189 int digit(int ch, int radix) {
190 int value = DIGITS[ch];
191 return (value >= 0 && value < radix && radix >= Character.MIN_RADIX
192 && radix <= Character.MAX_RADIX) ? value : -1;
193 }
194
195 int getNumericValue(int ch) {
196 int val = getProperties(ch);
197 int retval = -1;
198
199 switch (val & $$maskNumericType) {
200 default: // cannot occur
201 case ($$valueNotNumeric): // not numeric
202 retval = -1;
203 break;
204 case ($$valueDigit): // simple numeric
205 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
206 break;
207 case ($$valueStrangeNumeric) : // "strange" numeric
208 retval = -2;
209 break;
210 case ($$valueJavaSupradecimal): // Java supradecimal
211 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
212 break;
213 }
214 return retval;
215 }
216
217 boolean isWhitespace(int ch) {
218 int props = getProperties(ch);
219 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
220 }
221
222 byte getDirectionality(int ch) {
223 int val = getProperties(ch);
224 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
225
226 if (directionality == 0xF ) {
227 directionality = -1;
228 }
229 return directionality;
230 }
231
232 boolean isMirrored(int ch) {
233 int props = getProperties(ch);
234 return ((props & $$maskMirrored) != 0);
235 }
236
237 int toUpperCaseEx(int ch) {
238 int mapChar = ch;
239 int val = getProperties(ch);
240
241 if ((val & $$maskUpperCase) != 0) {
242 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
243 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
244 mapChar = ch - offset;
245 }
246 else {
247 switch(ch) {
248 // map overflow characters
249 case 0x00B5 : mapChar = 0x039C; break;
250 default : mapChar = Character.ERROR; break;
251 }
252 }
253 }
254 return mapChar;
255 }
256
257 static char[] sharpsMap = new char[] {'S', 'S'};
258
259 char[] toUpperCaseCharArray(int ch) {
260 char[] upperMap = {(char)ch};
261 if (ch == 0x00DF) {
262 upperMap = sharpsMap;
263 }
264 return upperMap;
265 }
266
267 static final CharacterDataLatin1 instance = new CharacterDataLatin1();
268 private CharacterDataLatin1() {};
269
270 $$Tables
271
272 static {
273 $$Initializers
274 }
275 }
276