1 /*
2 * Copyright (c) 2002, 2013, 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 java.util.Arrays;
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 boolean isOtherLowercase(int ch) {
84 int props = getPropertiesEx(ch);
85 return (props & $$maskOtherLowercase) != 0;
86 }
87
88 boolean isOtherUppercase(int ch) {
89 int props = getPropertiesEx(ch);
90 return (props & $$maskOtherUppercase) != 0;
91 }
92
93 boolean isOtherAlphabetic(int ch) {
94 int props = getPropertiesEx(ch);
95 return (props & $$maskOtherAlphabetic) != 0;
96 }
97
98 boolean isIdeographic(int ch) {
99 int props = getPropertiesEx(ch);
100 return (props & $$maskIdeographic) != 0;
101 }
102
103 int getType(int ch) {
104 int props = getProperties(ch);
105 return (props & $$maskType);
106 }
107
108 boolean isJavaIdentifierStart(int ch) {
109 int props = getProperties(ch);
110 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
111 }
112
113 boolean isJavaIdentifierPart(int ch) {
114 int props = getProperties(ch);
115 return ((props & $$nonzeroJavaPart) != 0);
116 }
117
118 boolean isUnicodeIdentifierStart(int ch) {
119 int props = getProperties(ch);
120 return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
121 }
122
123 boolean isUnicodeIdentifierPart(int ch) {
124 int props = getProperties(ch);
125 return ((props & $$maskUnicodePart) != 0);
126 }
127
128 boolean isIdentifierIgnorable(int ch) {
129 int props = getProperties(ch);
130 return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
131 }
132
133 int toLowerCase(int ch) {
134 int mapChar = ch;
135 int val = getProperties(ch);
136
137 if (((val & $$maskLowerCase) != 0) &&
138 ((val & $$maskCaseOffset) != $$maskCaseOffset)) {
139 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
140 mapChar = ch + offset;
141 }
142 return mapChar;
143 }
144
145 int toUpperCase(int ch) {
146 int mapChar = ch;
147 int val = getProperties(ch);
148
149 if ((val & $$maskUpperCase) != 0) {
150 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
151 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
152 mapChar = ch - offset;
153 } else if (ch == 0x00B5) {
154 mapChar = 0x039C;
155 }
156 }
157 return mapChar;
158 }
159
160 int toTitleCase(int ch) {
161 return toUpperCase(ch);
162 }
163
164 // Digit values for codePoints in the 0-255 range. Contents generated using:
165 // for (char i = 0; i < 256; i++) {
166 // int v = -1;
167 // if (i >= '0' && i <= '9') { v = i - '0'; }
168 // else if (i >= 'A' && i <= 'Z') { v = i - 'A' + 10; }
169 // else if (i >= 'a' && i <= 'z') { v = i - 'a' + 10; }
170 // if (i % 20 == 0) System.out.println();
171 // System.out.printf("%2d, ", v);
172 // }
173 private static final byte[] DIGITS = new byte[] {
174 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
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, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1,
177 -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
178 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1, 10, 11, 12,
179 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
180 33, 34, 35, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
181 -1, -1, -1, -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 };
187
188 int digit(int ch, int radix) {
189 int value = DIGITS[ch];
190 if (value >= 0 && radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
191 value = (value < radix) ? value : -1;
192 }
193 return value;
194 }
195
196 int getNumericValue(int ch) {
197 int val = getProperties(ch);
198 int retval = -1;
199
200 switch (val & $$maskNumericType) {
201 default: // cannot occur
202 case ($$valueNotNumeric): // not numeric
203 retval = -1;
204 break;
205 case ($$valueDigit): // simple numeric
206 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
207 break;
208 case ($$valueStrangeNumeric) : // "strange" numeric
209 retval = -2;
210 break;
211 case ($$valueJavaSupradecimal): // Java supradecimal
212 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
213 break;
214 }
215 return retval;
216 }
217
218 boolean isWhitespace(int ch) {
219 int props = getProperties(ch);
220 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
221 }
222
223 byte getDirectionality(int ch) {
224 int val = getProperties(ch);
225 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
226
227 if (directionality == 0xF ) {
228 directionality = -1;
229 }
230 return directionality;
231 }
232
233 boolean isMirrored(int ch) {
234 int props = getProperties(ch);
235 return ((props & $$maskMirrored) != 0);
236 }
237
238 int toUpperCaseEx(int ch) {
239 int mapChar = ch;
240 int val = getProperties(ch);
241
242 if ((val & $$maskUpperCase) != 0) {
243 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
244 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
245 mapChar = ch - offset;
246 }
247 else {
248 switch(ch) {
249 // map overflow characters
250 case 0x00B5 : mapChar = 0x039C; break;
251 default : mapChar = Character.ERROR; break;
252 }
253 }
254 }
255 return mapChar;
256 }
257
258 static char[] sharpsMap = new char[] {'S', 'S'};
259
260 char[] toUpperCaseCharArray(int ch) {
261 char[] upperMap = {(char)ch};
262 if (ch == 0x00DF) {
263 upperMap = sharpsMap;
264 }
265 return upperMap;
266 }
267
268 static final CharacterDataLatin1 instance = new CharacterDataLatin1();
269 private CharacterDataLatin1() {};
270
271 $$Tables
272
273 static {
274 $$Initializers
275 }
276 }
277