1/* 2 * Copyright (c) 2003, 2021, 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 26package java.lang; 27 28/** The CharacterData class encapsulates the large tables found in 29 Java.lang.Character. */ 30 31class 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 isOtherAlphabetic(int ch) { 81 int props = getPropertiesEx(ch); 82 return (props & $$maskOtherAlphabetic) != 0; 83 } 84 85 boolean isIdeographic(int ch) { 86 int props = getPropertiesEx(ch); 87 return (props & $$maskIdeographic) != 0; 88 } 89 90 int getType(int ch) { 91 int props = getProperties(ch); 92 return (props & $$maskType); 93 } 94 95 boolean isJavaIdentifierStart(int ch) { 96 int props = getProperties(ch); 97 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart); 98 } 99 100 boolean isJavaIdentifierPart(int ch) { 101 int props = getProperties(ch); 102 return ((props & $$nonzeroJavaPart) != 0); 103 } 104 105 boolean isUnicodeIdentifierStart(int ch) { 106 return (getPropertiesEx(ch) & $$maskIDStart) != 0; 107 } 108 109 boolean isUnicodeIdentifierPart(int ch) { 110 return (getPropertiesEx(ch) & $$maskIDContinue) != 0 || 111 isIdentifierIgnorable(ch); 112 } 113 114 boolean isIdentifierIgnorable(int ch) { 115 int props = getProperties(ch); 116 return ((props & $$maskIdentifierInfo) == $$valueIgnorable); 117 } 118 119 int toLowerCase(int ch) { 120 int mapChar = ch; 121 int val = getProperties(ch); 122 123 if ((val & $$maskLowerCase) != 0) { 124 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); 125 mapChar = ch + offset; 126 } 127 return mapChar; 128 } 129 130 int toUpperCase(int ch) { 131 int mapChar = ch; 132 int val = getProperties(ch); 133 134 if ((val & $$maskUpperCase) != 0) { 135 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); 136 mapChar = ch - offset; 137 } 138 return mapChar; 139 } 140 141 int toTitleCase(int ch) { 142 int mapChar = ch; 143 int val = getProperties(ch); 144 145 if ((val & $$maskTitleCase) != 0) { 146 // There is a titlecase equivalent. Perform further checks: 147 if ((val & $$maskUpperCase) == 0) { 148 // The character does not have an uppercase equivalent, so it must 149 // already be uppercase; so add 1 to get the titlecase form. 150 mapChar = ch + 1; 151 } 152 else if ((val & $$maskLowerCase) == 0) { 153 // The character does not have a lowercase equivalent, so it must 154 // already be lowercase; so subtract 1 to get the titlecase form. 155 mapChar = ch - 1; 156 } 157 // else { 158 // The character has both an uppercase equivalent and a lowercase 159 // equivalent, so it must itself be a titlecase form; return it. 160 // return ch; 161 //} 162 } 163 else if ((val & $$maskUpperCase) != 0) { 164 // This character has no titlecase equivalent but it does have an 165 // uppercase equivalent, so use that (subtract the signed case offset). 166 mapChar = toUpperCase(ch); 167 } 168 return mapChar; 169 } 170 171 int digit(int ch, int radix) { 172 int value = -1; 173 if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) { 174 int val = getProperties(ch); 175 int kind = val & $$maskType; 176 if (kind == Character.DECIMAL_DIGIT_NUMBER) { 177 value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; 178 } 179 else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) { 180 // Java supradecimal digit 181 value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; 182 } 183 } 184 return (value < radix) ? value : -1; 185 } 186 187 int getNumericValue(int ch) { 188 int val = getProperties(ch); 189 int retval = -1; 190 191 switch (val & $$maskNumericType) { 192 default: // cannot occur 193 case ($$valueNotNumeric): // not numeric 194 retval = -1; 195 break; 196 case ($$valueDigit): // simple numeric 197 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; 198 break; 199 case ($$valueStrangeNumeric) : // "strange" numeric 200 retval = -2; 201 break; 202 case ($$valueJavaSupradecimal): // Java supradecimal 203 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; 204 break; 205 } 206 return retval; 207 } 208 209 boolean isDigit(int ch) { 210 int props = getProperties(ch); 211 return (props & $$maskType) == Character.DECIMAL_DIGIT_NUMBER; 212 } 213 214 boolean isLowerCase(int ch) { 215 return (getPropertiesEx(ch) & $$maskOtherLowercase) != 0; 216 } 217 218 boolean isUpperCase(int ch) { 219 return (getPropertiesEx(ch) & $$maskOtherUppercase) != 0; 220 } 221 222 boolean isWhitespace(int ch) { 223 return (getProperties(ch) & $$maskIdentifierInfo) == $$valueJavaWhitespace; 224 } 225 226 byte getDirectionality(int ch) { 227 int val = getProperties(ch); 228 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi); 229 if (directionality == 0xF ) { 230 directionality = Character.DIRECTIONALITY_UNDEFINED; 231 } 232 return directionality; 233 } 234 235 boolean isMirrored(int ch) { 236 return (getProperties(ch) & $$maskMirrored) != 0; 237 } 238 239 static final CharacterData instance = new CharacterData02(); 240 private CharacterData02() {}; 241 242 $$Tables 243 244 static { 245 $$Initializers 246 } 247} 248