1# $FreeBSD$
2# $NetBSD: THAI%UCS.src,v 1.1 2006/03/13 19:45:36 tnozaki Exp $
3
4TYPE		ROWCOL
5NAME		THAI/UCS
6SRC_ZONE	0x00-0xFF
7OOB_MODE	ILSEQ
8DST_ILSEQ	0xFFFE
9DST_UNIT_BITS	16
10
11BEGIN_MAP
12#
13# This mapping data is made from the mapping data provided by Unicode, Inc.
14# Original notice:
15#
16#=======================================================================
17#   File name:  THAI.TXT
18#
19#   Contents:   Map (external version) from Mac OS Thai
20#               character set to Unicode 3.2 and later.
21#
22#   Copyright:  (c) 1995-2002, 2005 by Apple Computer, Inc., all rights
23#               reserved.
24#
25#   Contact:    charsets@apple.com
26#
27#   Changes:
28#
29#       c02  2005-Apr-05    Update header comments. Matches internal xml
30#                           <c1.1> and Text Encoding Converter 2.0.
31#      b3,c1 2002-Dec-19    Update mapping for 0xDB to use new Unicode
32#                           3.2 WORD JOINER instead of ZWNBSP (BOM).
33#                           Update URLs. Matches internal utom<b3>.
34#       b02  1999-Sep-22    Update contact e-mail address. Matches
35#                           internal utom<b1>, ufrm<b2>, and Text
36#                           Encoding Converter version 1.5.
37#       n07  1998-Feb-05    Update to match internal utom<n5>, ufrm<n13>
38#                           and Text Encoding Converter version 1.3:
39#                           Use standard Unicodes plus transcoding hints
40#                           instead of single corporate characters; see
41#                           details below. Also update header comments
42#                           to new format.
43#       n04  1995-Nov-17    First version (after fixing some typos).
44#                           Matches internal ufrm<n6>.
45#
46# Standard header:
47# ----------------
48#
49#   Apple, the Apple logo, and Macintosh are trademarks of Apple
50#   Computer, Inc., registered in the United States and other countries.
51#   Unicode is a trademark of Unicode Inc. For the sake of brevity,
52#   throughout this document, "Macintosh" can be used to refer to
53#   Macintosh computers and "Unicode" can be used to refer to the
54#   Unicode standard.
55#
56#   Apple Computer, Inc. ("Apple") makes no warranty or representation,
57#   either express or implied, with respect to this document and the
58#   included data, its quality, accuracy, or fitness for a particular
59#   purpose. In no event will Apple be liable for direct, indirect,
60#   special, incidental, or consequential damages resulting from any
61#   defect or inaccuracy in this document or the included data.
62#
63#   These mapping tables and character lists are subject to change.
64#   The latest tables should be available from the following:
65#
66#   <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
67#
68#   For general information about Mac OS encodings and these mapping
69#   tables, see the file "README.TXT".
70#
71# Format:
72# -------
73#
74#   Three tab-separated columns;
75#   '#' begins a comment which continues to the end of the line.
76#     Column #1 is the Mac OS Thai code (in hex as 0xNN)
77#     Column #2 is the corresponding Unicode or Unicode sequence
78#       (in hex as 0xNNNN or 0xNNNN+0xNNNN).
79#     Column #3 is a comment containing the Unicode name
80#
81#   The entries are in Mac OS Thai code order.
82#
83#   Some of these mappings require the use of corporate characters.
84#   See the file "CORPCHAR.TXT" and notes below.
85#
86#   Control character mappings are not shown in this table, following
87#   the conventions of the standard UTC mapping tables. However, the
88#   Mac OS Thai character set uses the standard control characters at
89#   0x00-0x1F and 0x7F.
90#
91# Notes on Mac OS Thai:
92# ---------------------
93#
94#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
95#   environments, it is only supported via transcoding to and from
96#   Unicode.
97#
98#   Codes 0xA1-0xDA and 0xDF-0xFB are the character set from Thai
99#   standard TIS 620-2533, except that the following changes are
100#   made:
101#     0xEE is TRADE MARK SIGN (instead of THAI CHARACTER YAMAKKAN)
102#     0xFA is REGISTERED SIGN (instead of THAI CHARACTER ANGKHANKHU)
103#     0xFB is COPYRIGHT SIGN (instead of THAI CHARACTER KHOMUT)
104#
105#   Codes 0x80-0x82, 0x8D-0x8E, 0x91, 0x9D-0x9E, and 0xDB-0xDE are
106#   various additional punctuation marks (e.g. curly quotes,
107#   ellipsis), no-break space, and two special characters "word join"
108#   and "word break".
109#
110#   Codes 0x83-0x8C, 0x8F, and 0x92-0x9C are for positional variants
111#   of the upper vowels, tone marks, and other signs at 0xD1,
112#   0xD4-0xD7, and 0xE7-0xED. The positional variants would normally
113#   be considered presentation forms only and not characters. In most
114#   cases they are not typed directly; they are selected automatically
115#   at display time by the WorldScript software. However, using the
116#   Thai-DTP keyboard, the presentation forms can in fact be typed
117#   directly using dead keys. Thus they must be treated as real
118#   characters in the Mac OS Thai encoding. They are mapped using
119#   variant tags; see below.
120#
121#   Several code points are undefined and unused (they cannot be
122#   typed using any of the Mac OS Thai keyboard layouts): 0x90, 0x9F,
123#   0xFC-0xFE. These are not shown in the table below.
124#
125# Unicode mapping issues and notes:
126# ---------------------------------
127#
128#   The goals in the Apple mappings provided here are:
129#   - Ensure roundtrip mapping from every character in the Mac OS Thai
130#   character set to Unicode and back
131#   - Use standard Unicode characters as much as possible, to maximize
132#   interchangeability of the resulting Unicode text. Whenever possible,
133#   avoid having content carried by private-use characters.
134#
135#   To satisfy both goals, we use private use characters to mark variants
136#   that are similar to a sequence of one or more standard Unicode
137#   characters.
138#
139#   Apple has defined a block of 32 corporate characters as "transcoding
140#   hints." These are used in combination with standard Unicode characters
141#   to force them to be treated in a special way for mapping to other
142#   encodings; they have no other effect. Sixteen of these transcoding
143#   hints are "grouping hints" - they indicate that the next 2-4 Unicode
144#   characters should be treated as a single entity for transcoding. The
145#   other sixteen transcoding hints are "variant tags" - they are like
146#   combining characters, and can follow a standard Unicode (or a sequence
147#   consisting of a base character and other combining characters) to
148#   cause it to be treated in a special way for transcoding. These always
149#   terminate a combining-character sequence.
150#
151#   The transcoding coding hints used in this mapping table are four
152#   variant tags in the range 0xF873-75. Since these are combined with
153#   standard Unicode characters, some characters in the Mac OS Thai
154#   character set map to a sequence of two Unicodes instead of a single
155#   Unicode character. For example, the Mac OS Thai character at 0x83 is a
156#   low-left positional variant of THAI CHARACTER MAI EK (the standard
157#   mapping is for the abstract character at 0xE8). So 0x83 is mapped to
158#   0x0E48 (THAI CHARACTER MAI EK) + 0xF875 (a variant tag).
159#
160# Details of mapping changes in each version:
161# -------------------------------------------
162#
163#   Changes from version b02 to version b03/c01:
164#
165#   - Update mapping for 0xDB to use new Unicode 3.2 character U+2060
166#     WORD JOINER instead of U+FEFF ZERO WIDTH NO-BREAK SPACE (BOM)
167#
168#   Changes from version n04 to version n07:
169#
170#   - Changed mappings of the positional variants to use standard
171#   Unicodes + transcoding hint, instead of using single corporate
172#   zone characters. This affected the mappings for the following:
173#   0x83-08C, 0x8F, 0x92-0x9C
174#
175#   - Just comment out unused code points in the table, instead
176#   of mapping them to U+FFFD.
177#
178##################
1790x00 - 0x7E = 0x0000 -
1800x80 = 0x00AB
1810x81 = 0x00BB
1820x82 = 0x2026
1830x83 = 0x0E48
1840x84 = 0x0E49
1850x85 = 0x0E4A
1860x86 = 0x0E4B
1870x87 = 0x0E4C
1880x88 = 0x0E48
1890x89 = 0x0E49
1900x8A = 0x0E4A
1910x8B = 0x0E4B
1920x8C = 0x0E4C
1930x8D = 0x201C
1940x8E = 0x201D
1950x8F = 0x0E4D
1960x91 = 0x2022
1970x92 = 0x0E31
1980x93 = 0x0E47
1990x94 = 0x0E34
2000x95 = 0x0E35
2010x96 = 0x0E36
2020x97 = 0x0E37
2030x98 = 0x0E48
2040x99 = 0x0E49
2050x9A = 0x0E4A
2060x9B = 0x0E4B
2070x9C = 0x0E4C
2080x9D = 0x2018
2090x9E = 0x2019
2100xA0 = 0x00A0
2110xA1 = 0x0E01
2120xA2 = 0x0E02
2130xA3 = 0x0E03
2140xA4 = 0x0E04
2150xA5 = 0x0E05
2160xA6 = 0x0E06
2170xA7 = 0x0E07
2180xA8 = 0x0E08
2190xA9 = 0x0E09
2200xAA = 0x0E0A
2210xAB = 0x0E0B
2220xAC = 0x0E0C
2230xAD = 0x0E0D
2240xAE = 0x0E0E
2250xAF = 0x0E0F
2260xB0 = 0x0E10
2270xB1 = 0x0E11
2280xB2 = 0x0E12
2290xB3 = 0x0E13
2300xB4 = 0x0E14
2310xB5 = 0x0E15
2320xB6 = 0x0E16
2330xB7 = 0x0E17
2340xB8 = 0x0E18
2350xB9 = 0x0E19
2360xBA = 0x0E1A
2370xBB = 0x0E1B
2380xBC = 0x0E1C
2390xBD = 0x0E1D
2400xBE = 0x0E1E
2410xBF = 0x0E1F
2420xC0 = 0x0E20
2430xC1 = 0x0E21
2440xC2 = 0x0E22
2450xC3 = 0x0E23
2460xC4 = 0x0E24
2470xC5 = 0x0E25
2480xC6 = 0x0E26
2490xC7 = 0x0E27
2500xC8 = 0x0E28
2510xC9 = 0x0E29
2520xCA = 0x0E2A
2530xCB = 0x0E2B
2540xCC = 0x0E2C
2550xCD = 0x0E2D
2560xCE = 0x0E2E
2570xCF = 0x0E2F
2580xD0 = 0x0E30
2590xD1 = 0x0E31
2600xD2 = 0x0E32
2610xD3 = 0x0E33
2620xD4 = 0x0E34
2630xD5 = 0x0E35
2640xD6 = 0x0E36
2650xD7 = 0x0E37
2660xD8 = 0x0E38
2670xD9 = 0x0E39
2680xDA = 0x0E3A
2690xDB = 0x2060
2700xDC = 0x200B
2710xDD = 0x2013
2720xDE = 0x2014
2730xDF = 0x0E3F
2740xE0 = 0x0E40
2750xE1 = 0x0E41
2760xE2 = 0x0E42
2770xE3 = 0x0E43
2780xE4 = 0x0E44
2790xE5 = 0x0E45
2800xE6 = 0x0E46
2810xE7 = 0x0E47
2820xE8 = 0x0E48
2830xE9 = 0x0E49
2840xEA = 0x0E4A
2850xEB = 0x0E4B
2860xEC = 0x0E4C
2870xED = 0x0E4D
2880xEE = 0x2122
2890xEF = 0x0E4F
2900xF0 = 0x0E50
2910xF1 = 0x0E51
2920xF2 = 0x0E52
2930xF3 = 0x0E53
2940xF4 = 0x0E54
2950xF5 = 0x0E55
2960xF6 = 0x0E56
2970xF7 = 0x0E57
2980xF8 = 0x0E58
2990xF9 = 0x0E59
3000xFA = 0x00AE
3010xFB = 0x00A9
302END_MAP
303