1 /*
2 * Copyright (c) 2003, 2019, 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 CharacterData0E extends CharacterData {
32 /* The character properties are currently encoded into 32 bits in the following manner:
33 1 bit mirrored property
34 4 bits directionality property
35 9 bits signed offset used for converting case
36 1 bit if 1, adding the signed offset converts the character to lowercase
37 1 bit if 1, subtracting the signed offset converts the character to uppercase
38 1 bit if 1, this character has a titlecase equivalent (possibly itself)
39 3 bits 0 may not be part of an identifier
40 1 ignorable control; may continue a Unicode identifier or Java identifier
41 2 may continue a Java identifier but not a Unicode identifier (unused)
42 3 may continue a Unicode identifier or Java identifier
43 4 is a Java whitespace character
44 5 may start or continue a Java identifier;
45 may continue but not start a Unicode identifier (underscores)
46 6 may start or continue a Java identifier but not a Unicode identifier ($)
47 7 may start or continue a Unicode identifier or Java identifier
48 Thus:
49 5, 6, 7 may start a Java identifier
50 1, 2, 3, 5, 6, 7 may continue a Java identifier
51 7 may start a Unicode identifier
52 1, 3, 5, 7 may continue a Unicode identifier
53 1 is ignorable within an identifier
54 4 is Java whitespace
55 2 bits 0 this character has no numeric property
56 1 adding the digit offset to the character code and then
57 masking with 0x1F will produce the desired numeric value
58 2 this character has a "strange" numeric value
59 3 a Java supradecimal digit: adding the digit offset to the
60 character code, then masking with 0x1F, then adding 10
61 will produce the desired numeric value
62 5 bits digit offset
63 5 bits character type
64
65 The encoding of character properties is subject to change at any time.
66 */
67
68 int getProperties(int ch) {
69 char offset = (char)ch;
70 int props = $$Lookup(offset);
71 return props;
72 }
73
74 int getPropertiesEx(int ch) {
75 char offset = (char)ch;
76 int props = $$LookupEx(offset);
77 return props;
78 }
79
80 boolean isOtherLowercase(int ch) {
81 int props = getPropertiesEx(ch);
82 return (props & $$maskOtherLowercase) != 0;
83 }
84
85 boolean isOtherUppercase(int ch) {
86 int props = getPropertiesEx(ch);
87 return (props & $$maskOtherUppercase) != 0;
88 }
89
90 boolean isOtherAlphabetic(int ch) {
91 int props = getPropertiesEx(ch);
92 return (props & $$maskOtherAlphabetic) != 0;
93 }
94
95 boolean isIdeographic(int ch) {
96 int props = getPropertiesEx(ch);
97 return (props & $$maskIdeographic) != 0;
98 }
99
100 int getType(int ch) {
101 int props = getProperties(ch);
102 return (props & $$maskType);
103 }
104
105 boolean isJavaIdentifierStart(int ch) {
106 int props = getProperties(ch);
107 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
108 }
109
110 boolean isJavaIdentifierPart(int ch) {
111 int props = getProperties(ch);
112 return ((props & $$nonzeroJavaPart) != 0);
113 }
114
115 boolean isUnicodeIdentifierStart(int ch) {
116 return (getPropertiesEx(ch) & $$maskIDStart) != 0 ||
117 ch == 0x2E2F;
118 }
119
120 boolean isUnicodeIdentifierPart(int ch) {
121 return (getPropertiesEx(ch) & $$maskIDContinue) != 0 ||
122 isIdentifierIgnorable(ch) ||
123 ch == 0x2E2F;
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 & $$maskLowerCase) != 0) {
136 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
137 mapChar = ch + offset;
138 }
139 return mapChar;
140 }
141
142 int toUpperCase(int ch) {
143 int mapChar = ch;
144 int val = getProperties(ch);
145
146 if ((val & $$maskUpperCase) != 0) {
147 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
148 mapChar = ch - offset;
149 }
150 return mapChar;
151 }
152
153 int toTitleCase(int ch) {
154 int mapChar = ch;
155 int val = getProperties(ch);
156
157 if ((val & $$maskTitleCase) != 0) {
158 // There is a titlecase equivalent. Perform further checks:
159 if ((val & $$maskUpperCase) == 0) {
160 // The character does not have an uppercase equivalent, so it must
161 // already be uppercase; so add 1 to get the titlecase form.
162 mapChar = ch + 1;
163 }
164 else if ((val & $$maskLowerCase) == 0) {
165 // The character does not have a lowercase equivalent, so it must
166 // already be lowercase; so subtract 1 to get the titlecase form.
167 mapChar = ch - 1;
168 }
169 // else {
170 // The character has both an uppercase equivalent and a lowercase
171 // equivalent, so it must itself be a titlecase form; return it.
172 // return ch;
173 //}
174 }
175 else if ((val & $$maskUpperCase) != 0) {
176 // This character has no titlecase equivalent but it does have an
177 // uppercase equivalent, so use that (subtract the signed case offset).
178 mapChar = toUpperCase(ch);
179 }
180 return mapChar;
181 }
182
183 int digit(int ch, int radix) {
184 int value = -1;
185 if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
186 int val = getProperties(ch);
187 int kind = val & $$maskType;
188 if (kind == Character.DECIMAL_DIGIT_NUMBER) {
189 value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
190 }
191 else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) {
192 // Java supradecimal digit
193 value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
194 }
195 }
196 return (value < radix) ? value : -1;
197 }
198
199 int getNumericValue(int ch) {
200 int val = getProperties(ch);
201 int retval = -1;
202
203 switch (val & $$maskNumericType) {
204 default: // cannot occur
205 case ($$valueNotNumeric): // not numeric
206 retval = -1;
207 break;
208 case ($$valueDigit): // simple numeric
209 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
210 break;
211 case ($$valueStrangeNumeric) : // "strange" numeric
212 retval = -2;
213 break;
214 case ($$valueJavaSupradecimal): // Java supradecimal
215 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
216 break;
217 }
218 return retval;
219 }
220
221 boolean isDigit(int ch) {
222 int props = getProperties(ch);
223 return (props & $$maskType) == Character.DECIMAL_DIGIT_NUMBER;
224 }
225
226 boolean isLowerCase(int ch) {
227 int props = getProperties(ch);
228 return (props & $$maskType) == Character.LOWERCASE_LETTER;
229 }
230
231 boolean isUpperCase(int ch) {
232 int props = getProperties(ch);
233 return (props & $$maskType) == Character.UPPERCASE_LETTER;
234 }
235
236 boolean isWhitespace(int ch) {
237 int props = getProperties(ch);
238 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
239 }
240
241 byte getDirectionality(int ch) {
242 int val = getProperties(ch);
243 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
244 if (directionality == 0xF ) {
245 directionality = Character.DIRECTIONALITY_UNDEFINED;
246 }
247 return directionality;
248 }
249
250 boolean isMirrored(int ch) {
251 int props = getProperties(ch);
252 return ((props & $$maskMirrored) != 0);
253 }
254
255 static final CharacterData instance = new CharacterData0E();
256 private CharacterData0E() {};
257
258 $$Tables
259
260 static {
261 $$Initializers
262 }
263 }