1 | /*
|
---|
2 | * Copyright (c) 2003, 2006, 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 = $$Lookup(offset);
|
---|
71 | return props;
|
---|
72 | }
|
---|
73 |
|
---|
74 | int getType(int ch) {
|
---|
75 | int props = getProperties(ch);
|
---|
76 | return (props & $$maskType);
|
---|
77 | }
|
---|
78 |
|
---|
79 | boolean isJavaIdentifierStart(int ch) {
|
---|
80 | int props = getProperties(ch);
|
---|
81 | return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
|
---|
82 | }
|
---|
83 |
|
---|
84 | boolean isJavaIdentifierPart(int ch) {
|
---|
85 | int props = getProperties(ch);
|
---|
86 | return ((props & $$nonzeroJavaPart) != 0);
|
---|
87 | }
|
---|
88 |
|
---|
89 | boolean isUnicodeIdentifierStart(int ch) {
|
---|
90 | int props = getProperties(ch);
|
---|
91 | return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
|
---|
92 | }
|
---|
93 |
|
---|
94 | boolean isUnicodeIdentifierPart(int ch) {
|
---|
95 | int props = getProperties(ch);
|
---|
96 | return ((props & $$maskUnicodePart) != 0);
|
---|
97 | }
|
---|
98 |
|
---|
99 | boolean isIdentifierIgnorable(int ch) {
|
---|
100 | int props = getProperties(ch);
|
---|
101 | return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
|
---|
102 | }
|
---|
103 |
|
---|
104 | int toLowerCase(int ch) {
|
---|
105 | int mapChar = ch;
|
---|
106 | int val = getProperties(ch);
|
---|
107 |
|
---|
108 | if ((val & $$maskLowerCase) != 0) {
|
---|
109 | int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
|
---|
110 | mapChar = ch + offset;
|
---|
111 | }
|
---|
112 | return mapChar;
|
---|
113 | }
|
---|
114 |
|
---|
115 | int toUpperCase(int ch) {
|
---|
116 | int mapChar = ch;
|
---|
117 | int val = getProperties(ch);
|
---|
118 |
|
---|
119 | if ((val & $$maskUpperCase) != 0) {
|
---|
120 | int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
|
---|
121 | mapChar = ch - offset;
|
---|
122 | }
|
---|
123 | return mapChar;
|
---|
124 | }
|
---|
125 |
|
---|
126 | int toTitleCase(int ch) {
|
---|
127 | int mapChar = ch;
|
---|
128 | int val = getProperties(ch);
|
---|
129 |
|
---|
130 | if ((val & $$maskTitleCase) != 0) {
|
---|
131 | // There is a titlecase equivalent. Perform further checks:
|
---|
132 | if ((val & $$maskUpperCase) == 0) {
|
---|
133 | // The character does not have an uppercase equivalent, so it must
|
---|
134 | // already be uppercase; so add 1 to get the titlecase form.
|
---|
135 | mapChar = ch + 1;
|
---|
136 | }
|
---|
137 | else if ((val & $$maskLowerCase) == 0) {
|
---|
138 | // The character does not have a lowercase equivalent, so it must
|
---|
139 | // already be lowercase; so subtract 1 to get the titlecase form.
|
---|
140 | mapChar = ch - 1;
|
---|
141 | }
|
---|
142 | // else {
|
---|
143 | // The character has both an uppercase equivalent and a lowercase
|
---|
144 | // equivalent, so it must itself be a titlecase form; return it.
|
---|
145 | // return ch;
|
---|
146 | //}
|
---|
147 | }
|
---|
148 | else if ((val & $$maskUpperCase) != 0) {
|
---|
149 | // This character has no titlecase equivalent but it does have an
|
---|
150 | // uppercase equivalent, so use that (subtract the signed case offset).
|
---|
151 | mapChar = toUpperCase(ch);
|
---|
152 | }
|
---|
153 | return mapChar;
|
---|
154 | }
|
---|
155 |
|
---|
156 | int digit(int ch, int radix) {
|
---|
157 | int value = -1;
|
---|
158 | if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
|
---|
159 | int val = getProperties(ch);
|
---|
160 | int kind = val & $$maskType;
|
---|
161 | if (kind == Character.DECIMAL_DIGIT_NUMBER) {
|
---|
162 | value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
|
---|
163 | }
|
---|
164 | else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) {
|
---|
165 | // Java supradecimal digit
|
---|
166 | value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
|
---|
167 | }
|
---|
168 | }
|
---|
169 | return (value < radix) ? value : -1;
|
---|
170 | }
|
---|
171 |
|
---|
172 | int getNumericValue(int ch) {
|
---|
173 | int val = getProperties(ch);
|
---|
174 | int retval = -1;
|
---|
175 |
|
---|
176 | switch (val & $$maskNumericType) {
|
---|
177 | default: // cannot occur
|
---|
178 | case ($$valueNotNumeric): // not numeric
|
---|
179 | retval = -1;
|
---|
180 | break;
|
---|
181 | case ($$valueDigit): // simple numeric
|
---|
182 | retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
|
---|
183 | break;
|
---|
184 | case ($$valueStrangeNumeric) : // "strange" numeric
|
---|
185 | retval = -2;
|
---|
186 | break;
|
---|
187 | case ($$valueJavaSupradecimal): // Java supradecimal
|
---|
188 | retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
|
---|
189 | break;
|
---|
190 | }
|
---|
191 | return retval;
|
---|
192 | }
|
---|
193 |
|
---|
194 | boolean isWhitespace(int ch) {
|
---|
195 | int props = getProperties(ch);
|
---|
196 | return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
|
---|
197 | }
|
---|
198 |
|
---|
199 | byte getDirectionality(int ch) {
|
---|
200 | int val = getProperties(ch);
|
---|
201 | byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
|
---|
202 | if (directionality == 0xF ) {
|
---|
203 | directionality = Character.DIRECTIONALITY_UNDEFINED;
|
---|
204 | }
|
---|
205 | return directionality;
|
---|
206 | }
|
---|
207 |
|
---|
208 | boolean isMirrored(int ch) {
|
---|
209 | int props = getProperties(ch);
|
---|
210 | return ((props & $$maskMirrored) != 0);
|
---|
211 | }
|
---|
212 |
|
---|
213 | static final CharacterData instance = new CharacterData0E();
|
---|
214 | private CharacterData0E() {};
|
---|
215 |
|
---|
216 | $$Tables
|
---|
217 |
|
---|
218 | static {
|
---|
219 | $$Initializers
|
---|
220 | }
|
---|
221 | }
|
---|