Issue #326 - Part 1c: Generated files for Unicode 9.0.

In order to generate these files, refer to
 https://wiki.mozilla.org/I18n:Updating_Unicode_version
For those too lazy to go to the link (or if the link no longer works), we need the
 following files from http://www.unicode.org/Public/9.0.0/ucd/:
 - UnicodeData.txt
 - Scripts.txt
 - EastAsianWidth.txt
 - BidiMirroring.txt
 - HangulSyllableType.txt
 - SpecialCasing.txt
 - ReadMe.txt (to record version/date of the UCD)
 - Unihan_Variants.txt (from Unihan.zip)
 As well as Identifier*.txt from http://www.unicode.org/Public/security/9.0.0/,
 which should be put in a "security" subdirectory under the UCD folder, and
 http://www.unicode.org/Public/vertical/revision-15/VerticalOrientation-15.txt put
 in a "vertical" subdirectory.
I suggest downloading all files with GetEmAll, just in case.
Change the perl command a bit, as the guide seems to be outdated:
 perl ../tools/genUnicodePropertyData.pl /path/to/platform/gfx/harfbuzz/src/ /path/to/platform/intl/icu/source/common/unicode/ /path/to/UCD-directory/
This commit is contained in:
Job Bautista 2022-06-22 18:07:24 +08:00 committed by roytam1
commit 66d4f38c85
2 changed files with 181 additions and 279 deletions

View file

@ -11,13 +11,13 @@
*/
/*
* Created on Wed Oct 26 09:12:45 2016 from UCD data files with version info:
* Created on Wed Jun 22 10:06:55 2022 from UCD data files with version info:
*
# Date: 2015-06-16, 20:24:00 GMT [KW]
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# Date: 2016-06-20, 14:59:00 GMT [KW]
# © 2016 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# For documentation, see the following:
@ -25,41 +25,44 @@
# UAX #38, "Unicode Han Database (Unihan)"
# UAX #44, "Unicode Character Database."
#
# The UAXes can be accessed at http://www.unicode.org/versions/Unicode8.0.0/
# The UAXes can be accessed at http://www.unicode.org/versions/Unicode9.0.0/
This directory contains the final data files
for the Unicode Character Database, for Version 8.0.0 of the Unicode
Standard.
for the Unicode Character Database, for Version 9.0.0 of the Unicode Standard.
# Scripts-9.0.0.txt
# Date: 2016-06-01, 10:34:37 GMT
# Scripts-8.0.0.txt
# Date: 2015-03-11, 22:29:42 GMT [MD]
# BidiMirroring-9.0.0.txt
# Date: 2016-01-21, 22:00:00 GMT [KW, LI]
# BidiMirroring-8.0.0.txt
# Date: 2015-01-20, 18:30:00 GMT [KW, LI]
# BidiBrackets-9.0.0.txt
# Date: 2016-06-07, 22:30:00 GMT [AG, LI, KW]
# BidiBrackets-8.0.0.txt
# Date: 2015-01-20, 19:00:00 GMT [AG, LI, KW]
# HangulSyllableType-9.0.0.txt
# Date: 2016-03-02, 18:55:01 GMT
# HangulSyllableType-8.0.0.txt
# Date: 2014-12-16, 23:07:45 GMT [MD]
# LineBreak-9.0.0.txt
# Date: 2016-05-26, 01:00:00 GMT [KW, LI]
# LineBreak-8.0.0.txt
# Date: 2015-02-13, 09:15:00 GMT [KW, LI]
# EastAsianWidth-9.0.0.txt
# Date: 2016-05-27, 17:00:00 GMT [KW, LI]
# EastAsianWidth-8.0.0.txt
# Date: 2015-02-10, 21:00:00 GMT [KW, LI]
# DerivedCoreProperties-9.0.0.txt
# Date: 2016-06-01, 10:34:24 GMT
# File: xidmodifications.txt
# Version: 8.0.0
# Generated: 2015-05-17, 03:09:04 GMT
# IdentifierStatus.txt
# Date: 2016-06-16, 13:41:30 GMT
# IdentifierType.txt
# Date: 2016-06-16, 13:41:30 GMT
#
# Unihan_Variants.txt
# Date: 2015-04-30 18:38:20 GMT [JHJ]
# Date: 2016-06-01 07:01:48 GMT [JHJ]
# VerticalOrientation-13.txt
# Date: 2014-09-03, 17:30:00 GMT [EM, KI, LI]
# VerticalOrientation-15.txt
# Date: 2015-11-16, 20:00:00 GMT [EM, KI, LI]
*
* * * * * This file contains MACHINE-GENERATED DATA, do not edit! * * * * *
@ -71,13 +74,17 @@ Standard.
#pragma pack(1)
struct nsCharProps2 {
// Currently only 6 bits are defined here, so 2 more could be added without
// affecting the storage requirements for this struct.
// Currently only 4 bits are defined here, so 4 more could be added without
// affecting the storage requirements for this struct. Or we could pack two
// records per byte, at the cost of a slightly more complex accessor.
unsigned char mVertOrient:2;
unsigned char mXidmod:4;
unsigned char mIdType:2;
};
#pragma pack()
namespace mozilla {
@ -250,8 +257,16 @@ enum class Script {
MULTANI = 164,
PAU_CIN_HAU = 165,
SIDDHAM = 166,
ADLAM = 167,
BHAIKSUKI = 168,
MARCHEN = 169,
NEWA = 170,
OSAGE = 171,
HAN_WITH_BOPOMOFO = 172,
JAMO = 173,
SYMBOLS_EMOJI = 174,
NUM_SCRIPT_CODES = 167,
NUM_SCRIPT_CODES = 175,
INVALID = -1
};