/* * Copyright (c) 2002, 2023, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 only, as * published by the Free Software Foundation. Oracle designates this * particular file as subject to the "Classpath" exception as provided * by Oracle in the LICENSE file that accompanied this code. * * This code is distributed in the hope that it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License * version 2 for more details (a copy is included in the LICENSE file that * accompanied this code). * * You should have received a copy of the GNU General Public License version * 2 along with this work; if not, write to the Free Software Foundation, * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA * or visit www.oracle.com if you need additional information or have any * questions. */ package java.lang; import jdk.internal.vm.annotation.IntrinsicCandidate; /** The CharacterData class encapsulates the large tables found in Java.lang.Character. */ class CharacterDataLatin1 extends CharacterData { /* The character properties are currently encoded into 32 bits in the following manner: 1 bit mirrored property 4 bits directionality property 9 bits signed offset used for converting case 1 bit if 1, adding the signed offset converts the character to lowercase 1 bit if 1, subtracting the signed offset converts the character to uppercase 1 bit if 1, this character has a titlecase equivalent (possibly itself) 3 bits 0 may not be part of an identifier 1 ignorable control; may continue a Unicode identifier or Java identifier 2 may continue a Java identifier but not a Unicode identifier (unused) 3 may continue a Unicode identifier or Java identifier 4 is a Java whitespace character 5 may start or continue a Java identifier; may continue but not start a Unicode identifier (underscores) 6 may start or continue a Java identifier but not a Unicode identifier ($) 7 may start or continue a Unicode identifier or Java identifier Thus: 5, 6, 7 may start a Java identifier 1, 2, 3, 5, 6, 7 may continue a Java identifier 7 may start a Unicode identifier 1, 3, 5, 7 may continue a Unicode identifier 1 is ignorable within an identifier 4 is Java whitespace 2 bits 0 this character has no numeric property 1 adding the digit offset to the character code and then masking with 0x1F will produce the desired numeric value 2 this character has a "strange" numeric value 3 a Java supradecimal digit: adding the digit offset to the character code, then masking with 0x1F, then adding 10 will produce the desired numeric value 5 bits digit offset 5 bits character type The encoding of character properties is subject to change at any time. */ int getProperties(int ch) { char offset = (char)ch; int props = $$Lookup(offset); return props; } int getPropertiesEx(int ch) { char offset = (char)ch; int props = $$LookupEx(offset); return props; } @IntrinsicCandidate boolean isDigit(int ch) { return '0' <= ch && ch <= '9'; } @IntrinsicCandidate boolean isLowerCase(int ch) { return (getPropertiesEx(ch) & $$maskOtherLowercase) != 0; } @IntrinsicCandidate boolean isUpperCase(int ch) { return (getPropertiesEx(ch) & $$maskOtherUppercase) != 0; } boolean isOtherAlphabetic(int ch) { int props = getPropertiesEx(ch); return (props & $$maskOtherAlphabetic) != 0; } boolean isIdeographic(int ch) { int props = getPropertiesEx(ch); return (props & $$maskIdeographic) != 0; } int getType(int ch) { int props = getProperties(ch); return (props & $$maskType); } boolean isJavaIdentifierStart(int ch) { int props = getProperties(ch); return ((props & $$maskIdentifierInfo) >= $$lowJavaStart); } boolean isJavaIdentifierPart(int ch) { int props = getProperties(ch); return ((props & $$nonzeroJavaPart) != 0); } boolean isUnicodeIdentifierStart(int ch) { return (getPropertiesEx(ch) & $$maskIDStart) != 0; } boolean isUnicodeIdentifierPart(int ch) { return (getPropertiesEx(ch) & $$maskIDContinue) != 0 || isIdentifierIgnorable(ch); } boolean isIdentifierIgnorable(int ch) { int props = getProperties(ch); return ((props & $$maskIdentifierInfo) == $$valueIgnorable); } boolean isEmoji(int ch) { return (getPropertiesEx(ch) & $$maskEmoji) != 0; } boolean isEmojiPresentation(int ch) { return (getPropertiesEx(ch) & $$maskEmojiPresentation) != 0; } boolean isEmojiModifier(int ch) { return (getPropertiesEx(ch) & $$maskEmojiModifier) != 0; } boolean isEmojiModifierBase(int ch) { return (getPropertiesEx(ch) & $$maskEmojiModifierBase) != 0; } boolean isEmojiComponent(int ch) { return (getPropertiesEx(ch) & $$maskEmojiComponent) != 0; } boolean isExtendedPictographic(int ch) { return (getPropertiesEx(ch) & $$maskExtendedPictographic) != 0; } int toLowerCase(int ch) { if (ch < 'A') { // Fast path for low code points return ch; } // ASCII and Latin-1 were designed to optimize case-twiddling operations int lower = ch | 0x20; if (lower <= 'z' // In range a-z || (lower >= 0xE0 && lower <= 0xFE && lower != 0xF7)) { // ..or agrave-thorn, excluding division return lower; } return ch; } int toUpperCase(int ch) { if (ch < 'a') { // Fast path for low code points return ch; } // ASCII and Latin-1 were designed to optimize case-twiddling operations int upper = ch & 0xDF; if (upper <= 'Z' // In range A-Z || (upper >= 0xC0 && upper <= 0xDE && upper != 0xD7)) { // ..or Agrave-Thorn, not multiplication return upper; } // Special-case for 'y with Diaeresis' which uppercases out of latin1 if (ch == 0xFF) { return 0x178; // Capital Letter Y with Diaeresis } // Special-case for 'Micro Sign' which uppercases out of latin1 if (ch == 0xB5) { return 0x39C; // Greek Capital Letter Mu } return ch; } /** * Compares two latin1 code points, ignoring case considerations * * @param b1 byte representing a latin1 code point * @param b2 another byte representing a latin1 code point * @return true if the two bytes are considered equals ignoring case in latin1 */ static boolean equalsIgnoreCase(byte b1, byte b2) { if (b1 == b2) { return true; } // ASCII and Latin-1 were designed to optimize case-twiddling operations int upper = b1 & 0xDF; if (upper < 'A') { return false; // Low ASCII } return (upper <= 'Z' // In range A-Z || (upper >= 0xC0 && upper <= 0XDE && upper != 0xD7)) // ..or A-grave-Thorn, not multiplication && upper == (b2 & 0xDF); // b2 has same uppercase } int toTitleCase(int ch) { return toUpperCase(ch); } // Digit values for codePoints in the 0-255 range. Contents generated using: // for (char i = 0; i < 256; i++) { // int v = -1; // if (i >= '0' && i <= '9') { v = i - '0'; } // else if (i >= 'A' && i <= 'Z') { v = i - 'A' + 10; } // else if (i >= 'a' && i <= 'z') { v = i - 'a' + 10; } // if (i % 20 == 0) System.out.println(); // System.out.printf("%2d, ", v); // } // // Analysis has shown that generating the whole array allows the JIT to generate // better code compared to a slimmed down array, such as one cutting off after 'z' private static final byte[] DIGITS = new byte[] { -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 }; int digit(int ch, int radix) { int value = DIGITS[ch]; return (value >= 0 && value < radix && radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) ? value : -1; } int getNumericValue(int ch) { int val = getProperties(ch); int retval = -1; switch (val & $$maskNumericType) { default: // cannot occur case ($$valueNotNumeric): // not numeric retval = -1; break; case ($$valueDigit): // simple numeric retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; break; case ($$valueStrangeNumeric) : // "strange" numeric retval = -2; break; case ($$valueJavaSupradecimal): // Java supradecimal retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; break; } return retval; } @IntrinsicCandidate boolean isWhitespace(int ch) { int props = getProperties(ch); return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace); } byte getDirectionality(int ch) { int val = getProperties(ch); byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi); if (directionality == 0xF ) { directionality = -1; } return directionality; } boolean isMirrored(int ch) { int props = getProperties(ch); return ((props & $$maskMirrored) != 0); } int toUpperCaseEx(int ch) { int mapChar = ch; int val = getProperties(ch); if ((val & $$maskUpperCase) != 0) { if ((val & $$maskCaseOffset) != $$maskCaseOffset) { int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); mapChar = ch - offset; } else { switch(ch) { // map overflow characters case 0x00B5 : mapChar = 0x039C; break; default : mapChar = Character.ERROR; break; } } } return mapChar; } static char[] sharpsMap = new char[] {'S', 'S'}; char[] toUpperCaseCharArray(int ch) { char[] upperMap = {(char)ch}; if (ch == 0x00DF) { upperMap = sharpsMap; } return upperMap; } static final CharacterDataLatin1 instance = new CharacterDataLatin1(); private CharacterDataLatin1() {}; $$Tables static { $$Initializers } }