Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Reviewed-by: rriggs, joehw
- Loading branch information
Showing
40 changed files
with
3,814 additions
and
1,841 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Original file line | Diff line number | Diff line change |
|---|---|---|---|
| @@ -0,0 +1,259 @@ | |||
| /* | |||
| * Copyright (c) 2020, 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 found in | |||
| Java.lang.Character. */ | |||
|
|
|||
| class CharacterData03 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; | |||
| } | |||
|
|
|||
| 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; | |||
| } | |||
|
|
|||
| 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); | |||
| } | |||
|
|
|||
| 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 | |||
| retval = -2; | |||
| break; | |||
| case ($$valueJavaSupradecimal): // Java supradecimal | |||
| retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10; | |||
| break; | |||
| } | |||
| return retval; | |||
| } | |||
|
|
|||
| boolean isDigit(int ch) { | |||
| int props = getProperties(ch); | |||
| return (props & $$maskType) == Character.DECIMAL_DIGIT_NUMBER; | |||
| } | |||
|
|
|||
| boolean isLowerCase(int ch) { | |||
| int props = getProperties(ch); | |||
| return (props & $$maskType) == Character.LOWERCASE_LETTER; | |||
| } | |||
|
|
|||
| boolean isUpperCase(int ch) { | |||
| int props = getProperties(ch); | |||
| return (props & $$maskType) == Character.UPPERCASE_LETTER; | |||
| } | |||
|
|
|||
| boolean isWhitespace(int ch) { | |||
| return (getProperties(ch) & $$maskIdentifierInfo) == $$valueJavaWhitespace; | |||
| } | |||
|
|
|||
| byte getDirectionality(int ch) { | |||
| int val = getProperties(ch); | |||
| byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi); | |||
| if (directionality == 0xF ) { | |||
| directionality = Character.DIRECTIONALITY_UNDEFINED; | |||
| } | |||
| return directionality; | |||
| } | |||
|
|
|||
| boolean isMirrored(int ch) { | |||
| return (getProperties(ch) & $$maskMirrored) != 0; | |||
| } | |||
|
|
|||
| static final CharacterData instance = new CharacterData03(); | |||
| private CharacterData03() {}; | |||
|
|
|||
| $$Tables | |||
|
|
|||
| static { | |||
| $$Initializers | |||
| } | |||
| } | |||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.