1# $NetBSD: UCS%THAI.src,v 1.2 2006/04/08 15:47:40 tnozaki Exp $ 2 3TYPE ROWCOL 4NAME UCS/THAI 5SRC_ZONE 0x0000-0x2122 6OOB_MODE INVALID 7DST_INVALID 0x100 8DST_UNIT_BITS 16 9 10BEGIN_MAP 11# 12# This mapping data is made from the mapping data provided by Unicode, Inc. 13# Original notice: 14# 15#======================================================================= 16# File name: THAI.TXT 17# 18# Contents: Map (external version) from Mac OS Thai 19# character set to Unicode 3.2 and later. 20# 21# Copyright: (c) 1995-2002, 2005 by Apple Computer, Inc., all rights 22# reserved. 23# 24# Contact: charsets@apple.com 25# 26# Changes: 27# 28# c02 2005-Apr-05 Update header comments. Matches internal xml 29# <c1.1> and Text Encoding Converter 2.0. 30# b3,c1 2002-Dec-19 Update mapping for 0xDB to use new Unicode 31# 3.2 WORD JOINER instead of ZWNBSP (BOM). 32# Update URLs. Matches internal utom<b3>. 33# b02 1999-Sep-22 Update contact e-mail address. Matches 34# internal utom<b1>, ufrm<b2>, and Text 35# Encoding Converter version 1.5. 36# n07 1998-Feb-05 Update to match internal utom<n5>, ufrm<n13> 37# and Text Encoding Converter version 1.3: 38# Use standard Unicodes plus transcoding hints 39# instead of single corporate characters; see 40# details below. Also update header comments 41# to new format. 42# n04 1995-Nov-17 First version (after fixing some typos). 43# Matches internal ufrm<n6>. 44# 45# Standard header: 46# ---------------- 47# 48# Apple, the Apple logo, and Macintosh are trademarks of Apple 49# Computer, Inc., registered in the United States and other countries. 50# Unicode is a trademark of Unicode Inc. For the sake of brevity, 51# throughout this document, "Macintosh" can be used to refer to 52# Macintosh computers and "Unicode" can be used to refer to the 53# Unicode standard. 54# 55# Apple Computer, Inc. ("Apple") makes no warranty or representation, 56# either express or implied, with respect to this document and the 57# included data, its quality, accuracy, or fitness for a particular 58# purpose. In no event will Apple be liable for direct, indirect, 59# special, incidental, or consequential damages resulting from any 60# defect or inaccuracy in this document or the included data. 61# 62# These mapping tables and character lists are subject to change. 63# The latest tables should be available from the following: 64# 65# <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/> 66# 67# For general information about Mac OS encodings and these mapping 68# tables, see the file "README.TXT". 69# 70# Format: 71# ------- 72# 73# Three tab-separated columns; 74# '#' begins a comment which continues to the end of the line. 75# Column #1 is the Mac OS Thai code (in hex as 0xNN) 76# Column #2 is the corresponding Unicode or Unicode sequence 77# (in hex as 0xNNNN or 0xNNNN+0xNNNN). 78# Column #3 is a comment containing the Unicode name 79# 80# The entries are in Mac OS Thai code order. 81# 82# Some of these mappings require the use of corporate characters. 83# See the file "CORPCHAR.TXT" and notes below. 84# 85# Control character mappings are not shown in this table, following 86# the conventions of the standard UTC mapping tables. However, the 87# Mac OS Thai character set uses the standard control characters at 88# 0x00-0x1F and 0x7F. 89# 90# Notes on Mac OS Thai: 91# --------------------- 92# 93# This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa 94# environments, it is only supported via transcoding to and from 95# Unicode. 96# 97# Codes 0xA1-0xDA and 0xDF-0xFB are the character set from Thai 98# standard TIS 620-2533, except that the following changes are 99# made: 100# 0xEE is TRADE MARK SIGN (instead of THAI CHARACTER YAMAKKAN) 101# 0xFA is REGISTERED SIGN (instead of THAI CHARACTER ANGKHANKHU) 102# 0xFB is COPYRIGHT SIGN (instead of THAI CHARACTER KHOMUT) 103# 104# Codes 0x80-0x82, 0x8D-0x8E, 0x91, 0x9D-0x9E, and 0xDB-0xDE are 105# various additional punctuation marks (e.g. curly quotes, 106# ellipsis), no-break space, and two special characters "word join" 107# and "word break". 108# 109# Codes 0x83-0x8C, 0x8F, and 0x92-0x9C are for positional variants 110# of the upper vowels, tone marks, and other signs at 0xD1, 111# 0xD4-0xD7, and 0xE7-0xED. The positional variants would normally 112# be considered presentation forms only and not characters. In most 113# cases they are not typed directly; they are selected automatically 114# at display time by the WorldScript software. However, using the 115# Thai-DTP keyboard, the presentation forms can in fact be typed 116# directly using dead keys. Thus they must be treated as real 117# characters in the Mac OS Thai encoding. They are mapped using 118# variant tags; see below. 119# 120# Several code points are undefined and unused (they cannot be 121# typed using any of the Mac OS Thai keyboard layouts): 0x90, 0x9F, 122# 0xFC-0xFE. These are not shown in the table below. 123# 124# Unicode mapping issues and notes: 125# --------------------------------- 126# 127# The goals in the Apple mappings provided here are: 128# - Ensure roundtrip mapping from every character in the Mac OS Thai 129# character set to Unicode and back 130# - Use standard Unicode characters as much as possible, to maximize 131# interchangeability of the resulting Unicode text. Whenever possible, 132# avoid having content carried by private-use characters. 133# 134# To satisfy both goals, we use private use characters to mark variants 135# that are similar to a sequence of one or more standard Unicode 136# characters. 137# 138# Apple has defined a block of 32 corporate characters as "transcoding 139# hints." These are used in combination with standard Unicode characters 140# to force them to be treated in a special way for mapping to other 141# encodings; they have no other effect. Sixteen of these transcoding 142# hints are "grouping hints" - they indicate that the next 2-4 Unicode 143# characters should be treated as a single entity for transcoding. The 144# other sixteen transcoding hints are "variant tags" - they are like 145# combining characters, and can follow a standard Unicode (or a sequence 146# consisting of a base character and other combining characters) to 147# cause it to be treated in a special way for transcoding. These always 148# terminate a combining-character sequence. 149# 150# The transcoding coding hints used in this mapping table are four 151# variant tags in the range 0xF873-75. Since these are combined with 152# standard Unicode characters, some characters in the Mac OS Thai 153# character set map to a sequence of two Unicodes instead of a single 154# Unicode character. For example, the Mac OS Thai character at 0x83 is a 155# low-left positional variant of THAI CHARACTER MAI EK (the standard 156# mapping is for the abstract character at 0xE8). So 0x83 is mapped to 157# 0x0E48 (THAI CHARACTER MAI EK) + 0xF875 (a variant tag). 158# 159# Details of mapping changes in each version: 160# ------------------------------------------- 161# 162# Changes from version b02 to version b03/c01: 163# 164# - Update mapping for 0xDB to use new Unicode 3.2 character U+2060 165# WORD JOINER instead of U+FEFF ZERO WIDTH NO-BREAK SPACE (BOM) 166# 167# Changes from version n04 to version n07: 168# 169# - Changed mappings of the positional variants to use standard 170# Unicodes + transcoding hint, instead of using single corporate 171# zone characters. This affected the mappings for the following: 172# 0x83-08C, 0x8F, 0x92-0x9C 173# 174# - Just comment out unused code points in the table, instead 175# of mapping them to U+FFFD. 176# 177################## 1780x0000 - 0x007E = 0x00 - 1790x00A0 = 0xA0 1800x00A9 = 0xFB 1810x00AB = 0x80 1820x00AE = 0xFA 1830x00BB = 0x81 1840x0E01 = 0xA1 1850x0E02 = 0xA2 1860x0E03 = 0xA3 1870x0E04 = 0xA4 1880x0E05 = 0xA5 1890x0E06 = 0xA6 1900x0E07 = 0xA7 1910x0E08 = 0xA8 1920x0E09 = 0xA9 1930x0E0A = 0xAA 1940x0E0B = 0xAB 1950x0E0C = 0xAC 1960x0E0D = 0xAD 1970x0E0E = 0xAE 1980x0E0F = 0xAF 1990x0E10 = 0xB0 2000x0E11 = 0xB1 2010x0E12 = 0xB2 2020x0E13 = 0xB3 2030x0E14 = 0xB4 2040x0E15 = 0xB5 2050x0E16 = 0xB6 2060x0E17 = 0xB7 2070x0E18 = 0xB8 2080x0E19 = 0xB9 2090x0E1A = 0xBA 2100x0E1B = 0xBB 2110x0E1C = 0xBC 2120x0E1D = 0xBD 2130x0E1E = 0xBE 2140x0E1F = 0xBF 2150x0E20 = 0xC0 2160x0E21 = 0xC1 2170x0E22 = 0xC2 2180x0E23 = 0xC3 2190x0E24 = 0xC4 2200x0E25 = 0xC5 2210x0E26 = 0xC6 2220x0E27 = 0xC7 2230x0E28 = 0xC8 2240x0E29 = 0xC9 2250x0E2A = 0xCA 2260x0E2B = 0xCB 2270x0E2C = 0xCC 2280x0E2D = 0xCD 2290x0E2E = 0xCE 2300x0E2F = 0xCF 2310x0E30 = 0xD0 2320x0E31 = 0x92 2330x0E31 = 0xD1 2340x0E32 = 0xD2 2350x0E33 = 0xD3 2360x0E34 = 0x94 2370x0E34 = 0xD4 2380x0E35 = 0x95 2390x0E35 = 0xD5 2400x0E36 = 0x96 2410x0E36 = 0xD6 2420x0E37 = 0x97 2430x0E37 = 0xD7 2440x0E38 = 0xD8 2450x0E39 = 0xD9 2460x0E3A = 0xDA 2470x0E3F = 0xDF 2480x0E40 = 0xE0 2490x0E41 = 0xE1 2500x0E42 = 0xE2 2510x0E43 = 0xE3 2520x0E44 = 0xE4 2530x0E45 = 0xE5 2540x0E46 = 0xE6 2550x0E47 = 0x93 2560x0E47 = 0xE7 2570x0E48 = 0x83 2580x0E48 = 0x88 2590x0E48 = 0x98 2600x0E48 = 0xE8 2610x0E49 = 0x84 2620x0E49 = 0x89 2630x0E49 = 0x99 2640x0E49 = 0xE9 2650x0E4A = 0x85 2660x0E4A = 0x8A 2670x0E4A = 0x9A 2680x0E4A = 0xEA 2690x0E4B = 0x86 2700x0E4B = 0x8B 2710x0E4B = 0x9B 2720x0E4B = 0xEB 2730x0E4C = 0x87 2740x0E4C = 0x8C 2750x0E4C = 0x9C 2760x0E4C = 0xEC 2770x0E4D = 0x8F 2780x0E4D = 0xED 2790x0E4F = 0xEF 2800x0E50 = 0xF0 2810x0E51 = 0xF1 2820x0E52 = 0xF2 2830x0E53 = 0xF3 2840x0E54 = 0xF4 2850x0E55 = 0xF5 2860x0E56 = 0xF6 2870x0E57 = 0xF7 2880x0E58 = 0xF8 2890x0E59 = 0xF9 2900x200B = 0xDC 2910x2013 = 0xDD 2920x2014 = 0xDE 2930x2018 = 0x9D 2940x2019 = 0x9E 2950x201C = 0x8D 2960x201D = 0x8E 2970x2022 = 0x91 2980x2026 = 0x82 2990x2060 = 0xDB 3000x2122 = 0xEE 301END_MAP 302