|
1 /* |
|
2 * Copyright (c) 2003, 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 /** The CharacterData class encapsulates the large tables found in |
|
29 Java.lang.Character. */ |
|
30 |
|
31 class CharacterData02 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 int props = getProperties(ch); |
|
117 return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart); |
|
118 } |
|
119 |
|
120 boolean isUnicodeIdentifierPart(int ch) { |
|
121 int props = getProperties(ch); |
|
122 return ((props & $$maskUnicodePart) != 0); |
|
123 } |
|
124 |
|
125 boolean isIdentifierIgnorable(int ch) { |
|
126 int props = getProperties(ch); |
|
127 return ((props & $$maskIdentifierInfo) == $$valueIgnorable); |
|
128 } |
|
129 |
|
130 int toLowerCase(int ch) { |
|
131 int mapChar = ch; |
|
132 int val = getProperties(ch); |
|
133 |
|
134 if ((val & $$maskLowerCase) != 0) { |
|
135 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
|
136 mapChar = ch + offset; |
|
137 } |
|
138 return mapChar; |
|
139 } |
|
140 |
|
141 int toUpperCase(int ch) { |
|
142 int mapChar = ch; |
|
143 int val = getProperties(ch); |
|
144 |
|
145 if ((val & $$maskUpperCase) != 0) { |
|
146 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
|
147 mapChar = ch - offset; |
|
148 } |
|
149 return mapChar; |
|
150 } |
|
151 |
|
152 int toTitleCase(int ch) { |
|
153 int mapChar = ch; |
|
154 int val = getProperties(ch); |
|
155 |
|
156 if ((val & $$maskTitleCase) != 0) { |
|
157 // There is a titlecase equivalent. Perform further checks: |
|
158 if ((val & $$maskUpperCase) == 0) { |
|
159 // The character does not have an uppercase equivalent, so it must |
|
160 // already be uppercase; so add 1 to get the titlecase form. |
|
161 mapChar = ch + 1; |
|
162 } |
|
163 else if ((val & $$maskLowerCase) == 0) { |
|
164 // The character does not have a lowercase equivalent, so it must |
|
165 // already be lowercase; so subtract 1 to get the titlecase form. |
|
166 mapChar = ch - 1; |
|
167 } |
|
168 // else { |
|
169 // The character has both an uppercase equivalent and a lowercase |
|
170 // equivalent, so it must itself be a titlecase form; return it. |
|
171 // return ch; |
|
172 //} |
|
173 } |
|
174 else if ((val & $$maskUpperCase) != 0) { |
|
175 // This character has no titlecase equivalent but it does have an |
|
176 // uppercase equivalent, so use that (subtract the signed case offset). |
|
177 mapChar = toUpperCase(ch); |
|
178 } |
|
179 return mapChar; |
|
180 } |
|
181 |
|
182 int digit(int ch, int radix) { |
|
183 int value = -1; |
|
184 if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) { |
|
185 int val = getProperties(ch); |
|
186 int kind = val & $$maskType; |
|
187 if (kind == Character.DECIMAL_DIGIT_NUMBER) { |
|
188 value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; |
|
189 } |
|
190 else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) { |
|
191 // Java supradecimal digit |
|
192 value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; |
|
193 } |
|
194 } |
|
195 return (value < radix) ? value : -1; |
|
196 } |
|
197 |
|
198 int getNumericValue(int ch) { |
|
199 int val = getProperties(ch); |
|
200 int retval = -1; |
|
201 |
|
202 switch (val & $$maskNumericType) { |
|
203 default: // cannot occur |
|
204 case ($$valueNotNumeric): // not numeric |
|
205 retval = -1; |
|
206 break; |
|
207 case ($$valueDigit): // simple numeric |
|
208 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; |
|
209 break; |
|
210 case ($$valueStrangeNumeric) : // "strange" numeric |
|
211 retval = -2; |
|
212 break; |
|
213 case ($$valueJavaSupradecimal): // Java supradecimal |
|
214 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; |
|
215 break; |
|
216 } |
|
217 return retval; |
|
218 } |
|
219 |
|
220 boolean isWhitespace(int ch) { |
|
221 return (getProperties(ch) & $$maskIdentifierInfo) == $$valueJavaWhitespace; |
|
222 } |
|
223 |
|
224 byte getDirectionality(int ch) { |
|
225 int val = getProperties(ch); |
|
226 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi); |
|
227 if (directionality == 0xF ) { |
|
228 directionality = Character.DIRECTIONALITY_UNDEFINED; |
|
229 } |
|
230 return directionality; |
|
231 } |
|
232 |
|
233 boolean isMirrored(int ch) { |
|
234 return (getProperties(ch) & $$maskMirrored) != 0; |
|
235 } |
|
236 |
|
237 static final CharacterData instance = new CharacterData02(); |
|
238 private CharacterData02() {}; |
|
239 |
|
240 $$Tables |
|
241 |
|
242 static { |
|
243 $$Initializers |
|
244 } |
|
245 } |