302 lines
9.3 KiB
Plaintext
302 lines
9.3 KiB
Plaintext
# $NetBSD: THAI%UCS.src,v 1.1 2006/03/13 19:45:36 tnozaki Exp $
|
|
|
|
TYPE ROWCOL
|
|
NAME THAI/UCS
|
|
SRC_ZONE 0x00-0xFF
|
|
OOB_MODE ILSEQ
|
|
DST_ILSEQ 0xFFFE
|
|
DST_UNIT_BITS 16
|
|
|
|
BEGIN_MAP
|
|
#
|
|
# This mapping data is made from the mapping data provided by Unicode, Inc.
|
|
# Original notice:
|
|
#
|
|
#=======================================================================
|
|
# File name: THAI.TXT
|
|
#
|
|
# Contents: Map (external version) from Mac OS Thai
|
|
# character set to Unicode 3.2 and later.
|
|
#
|
|
# Copyright: (c) 1995-2002, 2005 by Apple Computer, Inc., all rights
|
|
# reserved.
|
|
#
|
|
# Contact: charsets@apple.com
|
|
#
|
|
# Changes:
|
|
#
|
|
# c02 2005-Apr-05 Update header comments. Matches internal xml
|
|
# <c1.1> and Text Encoding Converter 2.0.
|
|
# b3,c1 2002-Dec-19 Update mapping for 0xDB to use new Unicode
|
|
# 3.2 WORD JOINER instead of ZWNBSP (BOM).
|
|
# Update URLs. Matches internal utom<b3>.
|
|
# b02 1999-Sep-22 Update contact e-mail address. Matches
|
|
# internal utom<b1>, ufrm<b2>, and Text
|
|
# Encoding Converter version 1.5.
|
|
# n07 1998-Feb-05 Update to match internal utom<n5>, ufrm<n13>
|
|
# and Text Encoding Converter version 1.3:
|
|
# Use standard Unicodes plus transcoding hints
|
|
# instead of single corporate characters; see
|
|
# details below. Also update header comments
|
|
# to new format.
|
|
# n04 1995-Nov-17 First version (after fixing some typos).
|
|
# Matches internal ufrm<n6>.
|
|
#
|
|
# Standard header:
|
|
# ----------------
|
|
#
|
|
# Apple, the Apple logo, and Macintosh are trademarks of Apple
|
|
# Computer, Inc., registered in the United States and other countries.
|
|
# Unicode is a trademark of Unicode Inc. For the sake of brevity,
|
|
# throughout this document, "Macintosh" can be used to refer to
|
|
# Macintosh computers and "Unicode" can be used to refer to the
|
|
# Unicode standard.
|
|
#
|
|
# Apple Computer, Inc. ("Apple") makes no warranty or representation,
|
|
# either express or implied, with respect to this document and the
|
|
# included data, its quality, accuracy, or fitness for a particular
|
|
# purpose. In no event will Apple be liable for direct, indirect,
|
|
# special, incidental, or consequential damages resulting from any
|
|
# defect or inaccuracy in this document or the included data.
|
|
#
|
|
# These mapping tables and character lists are subject to change.
|
|
# The latest tables should be available from the following:
|
|
#
|
|
# <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
|
|
#
|
|
# For general information about Mac OS encodings and these mapping
|
|
# tables, see the file "README.TXT".
|
|
#
|
|
# Format:
|
|
# -------
|
|
#
|
|
# Three tab-separated columns;
|
|
# '#' begins a comment which continues to the end of the line.
|
|
# Column #1 is the Mac OS Thai code (in hex as 0xNN)
|
|
# Column #2 is the corresponding Unicode or Unicode sequence
|
|
# (in hex as 0xNNNN or 0xNNNN+0xNNNN).
|
|
# Column #3 is a comment containing the Unicode name
|
|
#
|
|
# The entries are in Mac OS Thai code order.
|
|
#
|
|
# Some of these mappings require the use of corporate characters.
|
|
# See the file "CORPCHAR.TXT" and notes below.
|
|
#
|
|
# Control character mappings are not shown in this table, following
|
|
# the conventions of the standard UTC mapping tables. However, the
|
|
# Mac OS Thai character set uses the standard control characters at
|
|
# 0x00-0x1F and 0x7F.
|
|
#
|
|
# Notes on Mac OS Thai:
|
|
# ---------------------
|
|
#
|
|
# This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
|
|
# environments, it is only supported via transcoding to and from
|
|
# Unicode.
|
|
#
|
|
# Codes 0xA1-0xDA and 0xDF-0xFB are the character set from Thai
|
|
# standard TIS 620-2533, except that the following changes are
|
|
# made:
|
|
# 0xEE is TRADE MARK SIGN (instead of THAI CHARACTER YAMAKKAN)
|
|
# 0xFA is REGISTERED SIGN (instead of THAI CHARACTER ANGKHANKHU)
|
|
# 0xFB is COPYRIGHT SIGN (instead of THAI CHARACTER KHOMUT)
|
|
#
|
|
# Codes 0x80-0x82, 0x8D-0x8E, 0x91, 0x9D-0x9E, and 0xDB-0xDE are
|
|
# various additional punctuation marks (e.g. curly quotes,
|
|
# ellipsis), no-break space, and two special characters "word join"
|
|
# and "word break".
|
|
#
|
|
# Codes 0x83-0x8C, 0x8F, and 0x92-0x9C are for positional variants
|
|
# of the upper vowels, tone marks, and other signs at 0xD1,
|
|
# 0xD4-0xD7, and 0xE7-0xED. The positional variants would normally
|
|
# be considered presentation forms only and not characters. In most
|
|
# cases they are not typed directly; they are selected automatically
|
|
# at display time by the WorldScript software. However, using the
|
|
# Thai-DTP keyboard, the presentation forms can in fact be typed
|
|
# directly using dead keys. Thus they must be treated as real
|
|
# characters in the Mac OS Thai encoding. They are mapped using
|
|
# variant tags; see below.
|
|
#
|
|
# Several code points are undefined and unused (they cannot be
|
|
# typed using any of the Mac OS Thai keyboard layouts): 0x90, 0x9F,
|
|
# 0xFC-0xFE. These are not shown in the table below.
|
|
#
|
|
# Unicode mapping issues and notes:
|
|
# ---------------------------------
|
|
#
|
|
# The goals in the Apple mappings provided here are:
|
|
# - Ensure roundtrip mapping from every character in the Mac OS Thai
|
|
# character set to Unicode and back
|
|
# - Use standard Unicode characters as much as possible, to maximize
|
|
# interchangeability of the resulting Unicode text. Whenever possible,
|
|
# avoid having content carried by private-use characters.
|
|
#
|
|
# To satisfy both goals, we use private use characters to mark variants
|
|
# that are similar to a sequence of one or more standard Unicode
|
|
# characters.
|
|
#
|
|
# Apple has defined a block of 32 corporate characters as "transcoding
|
|
# hints." These are used in combination with standard Unicode characters
|
|
# to force them to be treated in a special way for mapping to other
|
|
# encodings; they have no other effect. Sixteen of these transcoding
|
|
# hints are "grouping hints" - they indicate that the next 2-4 Unicode
|
|
# characters should be treated as a single entity for transcoding. The
|
|
# other sixteen transcoding hints are "variant tags" - they are like
|
|
# combining characters, and can follow a standard Unicode (or a sequence
|
|
# consisting of a base character and other combining characters) to
|
|
# cause it to be treated in a special way for transcoding. These always
|
|
# terminate a combining-character sequence.
|
|
#
|
|
# The transcoding coding hints used in this mapping table are four
|
|
# variant tags in the range 0xF873-75. Since these are combined with
|
|
# standard Unicode characters, some characters in the Mac OS Thai
|
|
# character set map to a sequence of two Unicodes instead of a single
|
|
# Unicode character. For example, the Mac OS Thai character at 0x83 is a
|
|
# low-left positional variant of THAI CHARACTER MAI EK (the standard
|
|
# mapping is for the abstract character at 0xE8). So 0x83 is mapped to
|
|
# 0x0E48 (THAI CHARACTER MAI EK) + 0xF875 (a variant tag).
|
|
#
|
|
# Details of mapping changes in each version:
|
|
# -------------------------------------------
|
|
#
|
|
# Changes from version b02 to version b03/c01:
|
|
#
|
|
# - Update mapping for 0xDB to use new Unicode 3.2 character U+2060
|
|
# WORD JOINER instead of U+FEFF ZERO WIDTH NO-BREAK SPACE (BOM)
|
|
#
|
|
# Changes from version n04 to version n07:
|
|
#
|
|
# - Changed mappings of the positional variants to use standard
|
|
# Unicodes + transcoding hint, instead of using single corporate
|
|
# zone characters. This affected the mappings for the following:
|
|
# 0x83-08C, 0x8F, 0x92-0x9C
|
|
#
|
|
# - Just comment out unused code points in the table, instead
|
|
# of mapping them to U+FFFD.
|
|
#
|
|
##################
|
|
0x00 - 0x7E = 0x0000 -
|
|
0x80 = 0x00AB
|
|
0x81 = 0x00BB
|
|
0x82 = 0x2026
|
|
0x83 = 0x0E48
|
|
0x84 = 0x0E49
|
|
0x85 = 0x0E4A
|
|
0x86 = 0x0E4B
|
|
0x87 = 0x0E4C
|
|
0x88 = 0x0E48
|
|
0x89 = 0x0E49
|
|
0x8A = 0x0E4A
|
|
0x8B = 0x0E4B
|
|
0x8C = 0x0E4C
|
|
0x8D = 0x201C
|
|
0x8E = 0x201D
|
|
0x8F = 0x0E4D
|
|
0x91 = 0x2022
|
|
0x92 = 0x0E31
|
|
0x93 = 0x0E47
|
|
0x94 = 0x0E34
|
|
0x95 = 0x0E35
|
|
0x96 = 0x0E36
|
|
0x97 = 0x0E37
|
|
0x98 = 0x0E48
|
|
0x99 = 0x0E49
|
|
0x9A = 0x0E4A
|
|
0x9B = 0x0E4B
|
|
0x9C = 0x0E4C
|
|
0x9D = 0x2018
|
|
0x9E = 0x2019
|
|
0xA0 = 0x00A0
|
|
0xA1 = 0x0E01
|
|
0xA2 = 0x0E02
|
|
0xA3 = 0x0E03
|
|
0xA4 = 0x0E04
|
|
0xA5 = 0x0E05
|
|
0xA6 = 0x0E06
|
|
0xA7 = 0x0E07
|
|
0xA8 = 0x0E08
|
|
0xA9 = 0x0E09
|
|
0xAA = 0x0E0A
|
|
0xAB = 0x0E0B
|
|
0xAC = 0x0E0C
|
|
0xAD = 0x0E0D
|
|
0xAE = 0x0E0E
|
|
0xAF = 0x0E0F
|
|
0xB0 = 0x0E10
|
|
0xB1 = 0x0E11
|
|
0xB2 = 0x0E12
|
|
0xB3 = 0x0E13
|
|
0xB4 = 0x0E14
|
|
0xB5 = 0x0E15
|
|
0xB6 = 0x0E16
|
|
0xB7 = 0x0E17
|
|
0xB8 = 0x0E18
|
|
0xB9 = 0x0E19
|
|
0xBA = 0x0E1A
|
|
0xBB = 0x0E1B
|
|
0xBC = 0x0E1C
|
|
0xBD = 0x0E1D
|
|
0xBE = 0x0E1E
|
|
0xBF = 0x0E1F
|
|
0xC0 = 0x0E20
|
|
0xC1 = 0x0E21
|
|
0xC2 = 0x0E22
|
|
0xC3 = 0x0E23
|
|
0xC4 = 0x0E24
|
|
0xC5 = 0x0E25
|
|
0xC6 = 0x0E26
|
|
0xC7 = 0x0E27
|
|
0xC8 = 0x0E28
|
|
0xC9 = 0x0E29
|
|
0xCA = 0x0E2A
|
|
0xCB = 0x0E2B
|
|
0xCC = 0x0E2C
|
|
0xCD = 0x0E2D
|
|
0xCE = 0x0E2E
|
|
0xCF = 0x0E2F
|
|
0xD0 = 0x0E30
|
|
0xD1 = 0x0E31
|
|
0xD2 = 0x0E32
|
|
0xD3 = 0x0E33
|
|
0xD4 = 0x0E34
|
|
0xD5 = 0x0E35
|
|
0xD6 = 0x0E36
|
|
0xD7 = 0x0E37
|
|
0xD8 = 0x0E38
|
|
0xD9 = 0x0E39
|
|
0xDA = 0x0E3A
|
|
0xDB = 0x2060
|
|
0xDC = 0x200B
|
|
0xDD = 0x2013
|
|
0xDE = 0x2014
|
|
0xDF = 0x0E3F
|
|
0xE0 = 0x0E40
|
|
0xE1 = 0x0E41
|
|
0xE2 = 0x0E42
|
|
0xE3 = 0x0E43
|
|
0xE4 = 0x0E44
|
|
0xE5 = 0x0E45
|
|
0xE6 = 0x0E46
|
|
0xE7 = 0x0E47
|
|
0xE8 = 0x0E48
|
|
0xE9 = 0x0E49
|
|
0xEA = 0x0E4A
|
|
0xEB = 0x0E4B
|
|
0xEC = 0x0E4C
|
|
0xED = 0x0E4D
|
|
0xEE = 0x2122
|
|
0xEF = 0x0E4F
|
|
0xF0 = 0x0E50
|
|
0xF1 = 0x0E51
|
|
0xF2 = 0x0E52
|
|
0xF3 = 0x0E53
|
|
0xF4 = 0x0E54
|
|
0xF5 = 0x0E55
|
|
0xF6 = 0x0E56
|
|
0xF7 = 0x0E57
|
|
0xF8 = 0x0E58
|
|
0xF9 = 0x0E59
|
|
0xFA = 0x00AE
|
|
0xFB = 0x00A9
|
|
END_MAP
|