| /* |
| * Copyright (c) 2003, 2013, 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; |
| |
| /** The CharacterData class encapsulates the large tables once found in |
| * java.lang.Character. |
| */ |
| |
| class CharacterData01 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; |
| } |
| |
| int getType(int ch) { |
| int props = getProperties(ch); |
| return (props & $$maskType); |
| } |
| |
| boolean isOtherLowercase(int ch) { |
| int props = getPropertiesEx(ch); |
| return (props & $$maskOtherLowercase) != 0; |
| } |
| |
| boolean isOtherUppercase(int ch) { |
| int props = getPropertiesEx(ch); |
| return (props & $$maskOtherUppercase) != 0; |
| } |
| |
| boolean isOtherAlphabetic(int ch) { |
| int props = getPropertiesEx(ch); |
| return (props & $$maskOtherAlphabetic) != 0; |
| } |
| |
| boolean isIdeographic(int ch) { |
| int props = getPropertiesEx(ch); |
| return (props & $$maskIdeographic) != 0; |
| } |
| |
| boolean isJavaIdentifierStart(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$maskIdentifierInfo) >= $$lowJavaStart); |
| } |
| |
| boolean isJavaIdentifierPart(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$nonzeroJavaPart) != 0); |
| } |
| |
| boolean isUnicodeIdentifierStart(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart); |
| } |
| |
| boolean isUnicodeIdentifierPart(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$maskUnicodePart) != 0); |
| } |
| |
| boolean isIdentifierIgnorable(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$maskIdentifierInfo) == $$valueIgnorable); |
| } |
| |
| int toLowerCase(int ch) { |
| int mapChar = ch; |
| int val = getProperties(ch); |
| |
| if ((val & $$maskLowerCase) != 0) { |
| int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
| mapChar = ch + offset; |
| } |
| return mapChar; |
| } |
| |
| int toUpperCase(int ch) { |
| int mapChar = ch; |
| int val = getProperties(ch); |
| |
| if ((val & $$maskUpperCase) != 0) { |
| int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset); |
| mapChar = ch - offset; |
| } |
| return mapChar; |
| } |
| |
| int toTitleCase(int ch) { |
| int mapChar = ch; |
| int val = getProperties(ch); |
| |
| if ((val & $$maskTitleCase) != 0) { |
| // There is a titlecase equivalent. Perform further checks: |
| if ((val & $$maskUpperCase) == 0) { |
| // The character does not have an uppercase equivalent, so it must |
| // already be uppercase; so add 1 to get the titlecase form. |
| mapChar = ch + 1; |
| } |
| else if ((val & $$maskLowerCase) == 0) { |
| // The character does not have a lowercase equivalent, so it must |
| // already be lowercase; so subtract 1 to get the titlecase form. |
| mapChar = ch - 1; |
| } |
| // else { |
| // The character has both an uppercase equivalent and a lowercase |
| // equivalent, so it must itself be a titlecase form; return it. |
| // return ch; |
| //} |
| } |
| else if ((val & $$maskUpperCase) != 0) { |
| // This character has no titlecase equivalent but it does have an |
| // uppercase equivalent, so use that (subtract the signed case offset). |
| mapChar = toUpperCase(ch); |
| } |
| return mapChar; |
| } |
| |
| int digit(int ch, int radix) { |
| int value = -1; |
| if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) { |
| int val = getProperties(ch); |
| int kind = val & $$maskType; |
| if (kind == Character.DECIMAL_DIGIT_NUMBER) { |
| value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit; |
| } |
| else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) { |
| // Java supradecimal digit |
| value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; |
| } |
| } |
| return (value < 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 |
| switch(ch) { |
| case 0x10113: retval = 40; break; // AEGEAN NUMBER FORTY |
| case 0x10114: retval = 50; break; // AEGEAN NUMBER FIFTY |
| case 0x10115: retval = 60; break; // AEGEAN NUMBER SIXTY |
| case 0x10116: retval = 70; break; // AEGEAN NUMBER SEVENTY |
| case 0x10117: retval = 80; break; // AEGEAN NUMBER EIGHTY |
| case 0x10118: retval = 90; break; // AEGEAN NUMBER NINETY |
| case 0x10119: retval = 100; break; // AEGEAN NUMBER ONE HUNDRED |
| case 0x1011A: retval = 200; break; // AEGEAN NUMBER TWO HUNDRED |
| case 0x1011B: retval = 300; break; // AEGEAN NUMBER THREE HUNDRED |
| case 0x1011C: retval = 400; break; // AEGEAN NUMBER FOUR HUNDRED |
| case 0x1011D: retval = 500; break; // AEGEAN NUMBER FIVE HUNDRED |
| case 0x1011E: retval = 600; break; // AEGEAN NUMBER SIX HUNDRED |
| case 0x1011F: retval = 700; break; // AEGEAN NUMBER SEVEN HUNDRED |
| case 0x10120: retval = 800; break; // AEGEAN NUMBER EIGHT HUNDRED |
| case 0x10121: retval = 900; break; // AEGEAN NUMBER NINE HUNDRED |
| case 0x10122: retval = 1000; break; // AEGEAN NUMBER ONE THOUSAND |
| case 0x10123: retval = 2000; break; // AEGEAN NUMBER TWO THOUSAND |
| case 0x10124: retval = 3000; break; // AEGEAN NUMBER THREE THOUSAND |
| case 0x10125: retval = 4000; break; // AEGEAN NUMBER FOUR THOUSAND |
| case 0x10126: retval = 5000; break; // AEGEAN NUMBER FIVE THOUSAND |
| case 0x10127: retval = 6000; break; // AEGEAN NUMBER SIX THOUSAND |
| case 0x10128: retval = 7000; break; // AEGEAN NUMBER SEVEN THOUSAND |
| case 0x10129: retval = 8000; break; // AEGEAN NUMBER EIGHT THOUSAND |
| case 0x1012A: retval = 9000; break; // AEGEAN NUMBER NINE THOUSAND |
| case 0x1012B: retval = 10000; break; // AEGEAN NUMBER TEN THOUSAND |
| case 0x1012C: retval = 20000; break; // AEGEAN NUMBER TWENTY THOUSAND |
| case 0x1012D: retval = 30000; break; // AEGEAN NUMBER THIRTY THOUSAND |
| case 0x1012E: retval = 40000; break; // AEGEAN NUMBER FORTY THOUSAND |
| case 0x1012F: retval = 50000; break; // AEGEAN NUMBER FIFTY THOUSAND |
| case 0x10130: retval = 60000; break; // AEGEAN NUMBER SIXTY THOUSAND |
| case 0x10131: retval = 70000; break; // AEGEAN NUMBER SEVENTY THOUSAND |
| case 0x10132: retval = 80000; break; // AEGEAN NUMBER EIGHTY THOUSAND |
| case 0x10133: retval = 90000; break; // AEGEAN NUMBER NINETY THOUSAND |
| case 0x10323: retval = 50; break; // OLD ITALIC NUMERAL FIFTY |
| |
| case 0x010144: retval = 50; break; // ACROPHONIC ATTIC FIFTY |
| case 0x010145: retval = 500; break; // ACROPHONIC ATTIC FIVE HUNDRED |
| case 0x010146: retval = 5000; break; // ACROPHONIC ATTIC FIVE THOUSAND |
| case 0x010147: retval = 50000; break; // ACROPHONIC ATTIC FIFTY THOUSAND |
| case 0x01014A: retval = 50; break; // ACROPHONIC ATTIC FIFTY TALENTS |
| case 0x01014B: retval = 100; break; // ACROPHONIC ATTIC ONE HUNDRED TALENTS |
| case 0x01014C: retval = 500; break; // ACROPHONIC ATTIC FIVE HUNDRED TALENTS |
| case 0x01014D: retval = 1000; break; // ACROPHONIC ATTIC ONE THOUSAND TALENTS |
| case 0x01014E: retval = 5000; break; // ACROPHONIC ATTIC FIVE THOUSAND TALENTS |
| case 0x010151: retval = 50; break; // ACROPHONIC ATTIC FIFTY STATERS |
| case 0x010152: retval = 100; break; // ACROPHONIC ATTIC ONE HUNDRED STATERS |
| case 0x010153: retval = 500; break; // ACROPHONIC ATTIC FIVE HUNDRED STATERS |
| case 0x010154: retval = 1000; break; // ACROPHONIC ATTIC ONE THOUSAND STATERS |
| case 0x010155: retval = 10000; break; // ACROPHONIC ATTIC TEN THOUSAND STATERS |
| case 0x010156: retval = 50000; break; // ACROPHONIC ATTIC FIFTY THOUSAND STATERS |
| case 0x010166: retval = 50; break; // ACROPHONIC TROEZENIAN FIFTY |
| case 0x010167: retval = 50; break; // ACROPHONIC TROEZENIAN FIFTY ALTERNATE FORM |
| case 0x010168: retval = 50; break; // ACROPHONIC HERMIONIAN FIFTY |
| case 0x010169: retval = 50; break; // ACROPHONIC THESPIAN FIFTY |
| case 0x01016A: retval = 100; break; // ACROPHONIC THESPIAN ONE HUNDRED |
| case 0x01016B: retval = 300; break; // ACROPHONIC THESPIAN THREE HUNDRED |
| case 0x01016C: retval = 500; break; // ACROPHONIC EPIDAUREAN FIVE HUNDRED |
| case 0x01016D: retval = 500; break; // ACROPHONIC TROEZENIAN FIVE HUNDRED |
| case 0x01016E: retval = 500; break; // ACROPHONIC THESPIAN FIVE HUNDRED |
| case 0x01016F: retval = 500; break; // ACROPHONIC CARYSTIAN FIVE HUNDRED |
| case 0x010170: retval = 500; break; // ACROPHONIC NAXIAN FIVE HUNDRED |
| case 0x010171: retval = 1000; break; // ACROPHONIC THESPIAN ONE THOUSAND |
| case 0x010172: retval = 5000; break; // ACROPHONIC THESPIAN FIVE THOUSAND |
| case 0x010174: retval = 50; break; // ACROPHONIC STRATIAN FIFTY MNAS |
| case 0x010341: retval = 90; break; // GOTHIC LETTER NINETY |
| case 0x01034A: retval = 900; break; // GOTHIC LETTER NINE HUNDRED |
| case 0x0103D5: retval = 100; break; // OLD PERSIAN NUMBER HUNDRED |
| case 0x01085D: retval = 100; break; // IMPERIAL ARAMAIC NUMBER ONE HUNDRED |
| case 0x01085E: retval = 1000; break; // IMPERIAL ARAMAIC NUMBER ONE THOUSAND |
| case 0x01085F: retval = 10000; break; // IMPERIAL ARAMAIC NUMBER TEN THOUSAND |
| case 0x010919: retval = 100; break; // PHOENICIAN NUMBER ONE HUNDRED |
| case 0x010A46: retval = 100; break; // KHAROSHTHI NUMBER ONE HUNDRED |
| case 0x010A47: retval = 1000; break; // KHAROSHTHI NUMBER ONE THOUSAND |
| case 0x010A7E: retval = 50; break; // OLD SOUTH ARABIAN NUMBER FIFTY |
| case 0x010B5E: retval = 100; break; // INSCRIPTIONAL PARTHIAN NUMBER ONE HUNDRED |
| case 0x010B5F: retval = 1000; break; // INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND |
| case 0x010B7E: retval = 100; break; // INSCRIPTIONAL PAHLAVI NUMBER ONE HUNDRED |
| case 0x010B7F: retval = 1000; break; // INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND |
| case 0x010E6C: retval = 40; break; // RUMI NUMBER FORTY |
| case 0x010E6D: retval = 50; break; // RUMI NUMBER FIFTY |
| case 0x010E6E: retval = 60; break; // RUMI NUMBER SIXTY |
| case 0x010E6F: retval = 70; break; // RUMI NUMBER SEVENTY |
| case 0x010E70: retval = 80; break; // RUMI NUMBER EIGHTY |
| case 0x010E71: retval = 90; break; // RUMI NUMBER NINETY |
| case 0x010E72: retval = 100; break; // RUMI NUMBER ONE HUNDRED |
| case 0x010E73: retval = 200; break; // RUMI NUMBER TWO HUNDRED |
| case 0x010E74: retval = 300; break; // RUMI NUMBER THREE HUNDRED |
| case 0x010E75: retval = 400; break; // RUMI NUMBER FOUR HUNDRED |
| case 0x010E76: retval = 500; break; // RUMI NUMBER FIVE HUNDRED |
| case 0x010E77: retval = 600; break; // RUMI NUMBER SIX HUNDRED |
| case 0x010E78: retval = 700; break; // RUMI NUMBER SEVEN HUNDRED |
| case 0x010E79: retval = 800; break; // RUMI NUMBER EIGHT HUNDRED |
| case 0x010E7A: retval = 900; break; // RUMI NUMBER NINE HUNDRED |
| case 0x01105E: retval = 40; break; // BRAHMI NUMBER FORTY |
| case 0x01105F: retval = 50; break; // BRAHMI NUMBER FIFTY |
| case 0x011060: retval = 60; break; // BRAHMI NUMBER SIXTY |
| case 0x011061: retval = 70; break; // BRAHMI NUMBER SEVENTY |
| case 0x011062: retval = 80; break; // BRAHMI NUMBER EIGHTY |
| case 0x011063: retval = 90; break; // BRAHMI NUMBER NINETY |
| case 0x011064: retval = 100; break; // BRAHMI NUMBER ONE HUNDRED |
| case 0x011065: retval = 1000; break; // BRAHMI NUMBER ONE THOUSAND |
| case 0x012432: retval = 216000; break; // CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH |
| case 0x012433: retval = 432000; break; // CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN |
| case 0x01D36C: retval = 40; break; // COUNTING ROD TENS DIGIT FOUR |
| case 0x01D36D: retval = 50; break; // COUNTING ROD TENS DIGIT FIVE |
| case 0x01D36E: retval = 60; break; // COUNTING ROD TENS DIGIT SIX |
| case 0x01D36F: retval = 70; break; // COUNTING ROD TENS DIGIT SEVEN |
| case 0x01D370: retval = 80; break; // COUNTING ROD TENS DIGIT EIGHT |
| case 0x01D371: retval = 90; break; // COUNTING ROD TENS DIGIT NINE |
| default: retval = -2; break; |
| } |
| |
| break; |
| case ($$valueJavaSupradecimal): // Java supradecimal |
| retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; |
| break; |
| } |
| return retval; |
| } |
| |
| boolean isWhitespace(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace); |
| } |
| |
| byte getDirectionality(int ch) { |
| int val = getProperties(ch); |
| byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi); |
| if (directionality == 0xF ) { |
| directionality = Character.DIRECTIONALITY_UNDEFINED; |
| } |
| return directionality; |
| } |
| |
| boolean isMirrored(int ch) { |
| int props = getProperties(ch); |
| return ((props & $$maskMirrored) != 0); |
| } |
| |
| static final CharacterData instance = new CharacterData01(); |
| private CharacterData01() {}; |
| |
| $$Tables |
| |
| static { |
| $$Initializers |
| } |
| } |
