xref: /freebsd/share/i18n/csmapper/APPLE/UCS%SYMBOL.src (revision d0b2dbfa0ecf2bbc9709efc5e20baf8e4b44bbbf)
1
2TYPE		ROWCOL
3NAME		UCS/SYMBOL
4SRC_ZONE	0x0000-0xF8FF
5OOB_MODE	INVALID
6DST_INVALID	0x100
7DST_UNIT_BITS	16
8
9BEGIN_MAP
10#=======================================================================
11#   File name:  SYMBOL.TXT
12#
13#   Contents:   Map (external version) from Mac OS Symbol
14#               character set to Unicode 4.0 and later.
15#
16#   Copyright:  (c) 1994-2002, 2005 by Apple Computer, Inc., all rights
17#               reserved.
18#
19#   Contact:    charsets@apple.com
20#
21#   Changes:
22#
23#       c02  2005-Apr-05    Change mappings for 0xBD, 0xE0. Update
24#                           header comments. Matches internal xml <c1.2>
25#                           and Text Encoding Converter 2.0.
26#      b4,c1 2002-Dec-19    Update mappings for encoded glyph fragments
27#                           0xBE, 0xE6-EF, 0xF4, 0xF6-FE to use new
28#                           Unicode 3.2 characters instead of sequences
29#                           involving corporate-use characters. Update
30#                           URLs, notes. Matches internal utom<b4>.
31#       b03  1999-Sep-22    Update contact e-mail address. Matches
32#                           internal utom<b3>, ufrm<b3>, and Text
33#                           Encoding Converter version 1.5.
34#       b02  1998-Aug-18    Encoding changed for Mac OS 8.5; add new
35#                           mapping from 0xA0 to EURO SIGN. Matches
36#                           internal utom<b3>, ufrm<b3>.
37#       n05  1998-Feb-05    Update to match internal utom<n5>, ufrm<n15>
38#                           and Text Encoding Converter version 1.3:
39#                           Use standard Unicodes plus transcoding hints
40#                           instead of single corporate characters, also
41#                           change mappings for 0xE1 & 0xF1 from U+2329
42#                           & U+232A to their canonical decompositions;
43#                           see details below. Also update header
44#                           comments to new format.
45#       n03  1995-Apr-15    First version (after fixing some typos).
46#                           Matches internal ufrm<n4>.
47#
48# Standard header:
49# ----------------
50#
51#   Apple, the Apple logo, and Macintosh are trademarks of Apple
52#   Computer, Inc., registered in the United States and other countries.
53#   Unicode is a trademark of Unicode Inc. For the sake of brevity,
54#   throughout this document, "Macintosh" can be used to refer to
55#   Macintosh computers and "Unicode" can be used to refer to the
56#   Unicode standard.
57#
58#   Apple Computer, Inc. ("Apple") makes no warranty or representation,
59#   either express or implied, with respect to this document and the
60#   included data, its quality, accuracy, or fitness for a particular
61#   purpose. In no event will Apple be liable for direct, indirect,
62#   special, incidental, or consequential damages resulting from any
63#   defect or inaccuracy in this document or the included data.
64#
65#   These mapping tables and character lists are subject to change.
66#   The latest tables should be available from the following:
67#
68#   <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
69#
70#   For general information about Mac OS encodings and these mapping
71#   tables, see the file "README.TXT".
72#
73# Format:
74# -------
75#
76#   Three tab-separated columns;
77#   '#' begins a comment which continues to the end of the line.
78#     Column #1 is the Mac OS Symbol code (in hex as 0xNN)
79#     Column #2 is the corresponding Unicode or Unicode sequence
80#       (in hex as 0xNNNN or 0xNNNN+0xNNNN).
81#     Column #3 is a comment containing the Unicode name.
82#       In some cases an additional comment follows the Unicode name.
83#
84#   The entries are in Mac OS Symbol code order.
85#
86#   Some of these mappings require the use of corporate characters.
87#   See the file "CORPCHAR.TXT" and notes below.
88#
89#   Control character mappings are not shown in this table, following
90#   the conventions of the standard UTC mapping tables. However, the
91#   Mac OS Symbol character set uses the standard control characters
92#   at 0x00-0x1F and 0x7F.
93#
94# Notes on Mac OS Symbol:
95# -----------------------
96#
97#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
98#   environments, it is only supported directly in programming
99#   interfaces for QuickDraw Text, the Script Manager, and related
100#   Text Utilities. For other purposes it is supported via transcoding
101#   to and from Unicode.
102#
103#   The Mac OS Symbol encoding shares the script code smRoman
104#   (0) with the Mac OS Roman encoding. To determine if the Symbol
105#   encoding is being used, you must check if the font name is
106#   "Symbol".
107#
108#   Before Mac OS 8.5, code point 0xA0 was unused. In Mac OS 8.5
109#   and later versions, code point 0xA0 is EURO SIGN and maps to
110#   U+20AC (the Symbol font is updated for Mac OS 8.5 to reflect
111#   this).
112#
113#   The layout of the Mac OS Symbol character set is identical to
114#   the layout of the Adobe Symbol encoding vector, with the
115#   addition of the Apple logo character at 0xF0.
116#
117#   This character set encodes a number of glyph fragments. Some are
118#   used as extenders: 0x60 is used to extend radical signs, 0xBD and
119#   0xBE are used to extend vertical and horizontal arrows, etc. In
120#   addition, there are top, bottom, and center sections for
121#   parentheses, brackets, integral signs, and other signs that may
122#   extend vertically for 2 or more lines of normal text. As of
123#   Unicode 3.2, most of these are now encoded in Unicode; a few are
124#   not, so these are mapped using corporate-zone Unicode characters
125#   (see below).
126#
127#   In addition, Symbol separately encodes both serif and sans-serif
128#   forms for copyright, trademark, and registered signs. Unicode
129#   encodes only the abstract characters, so one set of these (the
130#   sans-serif forms) are also mapped using corporate-zone Unicode
131#   characters (see below).
132#
133#   The following code points are unused, and are not shown here:
134#   0x80-0x9F, 0xFF.
135#
136# Unicode mapping issues and notes:
137# ---------------------------------
138#
139#   The goals in the mappings provided here are:
140#   - Ensure roundtrip mapping from every character in the Mac OS
141#     Symbol character set to Unicode and back
142#   - Use standard Unicode characters as much as possible, to
143#     maximize interchangeability of the resulting Unicode text.
144#     Whenever possible, avoid having content carried by private-use
145#     characters.
146#
147#   Some of the characters in the Mac OS Symbol character set do not
148#   correspond to distinct, single Unicode characters. To map these
149#   and satisfy both goals above, we employ various strategies.
150#
151#   a) If possible, use private use characters in combination with
152#   standard Unicode characters to mark variants of the standard
153#   Unicode character.
154#
155#   Apple has defined a block of 32 corporate characters as "transcoding
156#   hints." These are used in combination with standard Unicode
157#   characters to force them to be treated in a special way for mapping
158#   to other encodings; they have no other effect. Sixteen of these
159#   transcoding hints are "grouping hints" - they indicate that the next
160#   2-4 Unicode characters should be treated as a single entity for
161#   transcoding. The other sixteen transcoding hints are "variant tags"
162#   - they are like combining characters, and can follow a standard
163#   Unicode (or a sequence consisting of a base character and other
164#   combining characters) to cause it to be treated in a special way for
165#   transcoding. These always terminate a combining-character sequence.
166#
167#   The transcoding coding hint used in this mapping table is the
168#   variant tag 0xF87F. Since this is combined with standard Unicode
169#   characters, some characters in the Mac OS Symbol character set map
170#   to a sequence of two Unicodes instead of a single Unicode character.
171#
172#   For example, the Mac OS Symbol character at 0xE2 is an alternate,
173#   sans-serif form of the REGISTERED SIGN (the standard mapping is for
174#   the abstract character at 0xD2, which here has a serif form). So 0xE2
175#   is mapped to 0x00AE (REGISTERED SIGN) + 0xF87F (a variant tag).
176#
177#   b) Otherwise, use private use characters by themselves to map
178#   Mac OS Symbol characters which have no relationship to any standard
179#   Unicode character.
180#
181#   The following additional corporate zone Unicode characters are
182#   used for this purpose here:
183#
184#     0xF8E5  radical extender
185#     0xF8FF  Apple logo
186#
187#   NOTE: The graphic image associated with the Apple logo character
188#   is not authorized for use without permission of Apple, and
189#   unauthorized use might constitute trademark infringement.
190#
191# Details of mapping changes in each version:
192# -------------------------------------------
193#
194#   Changes from version c01 to version c02:
195#
196#   - Update mappings for 0xBD from 0xF8E6 to 0x23D0 (use new Unicode
197#     4.0 char)
198#   - Correct mapping for 0xE0 from 0x22C4 to 0x25CA
199#
200#   Changes from version b02 to version b03/c01:
201#
202#   - Update mappings for encoded glyph fragments 0xBE, 0xE6-EF, 0xF4,
203#     0xF6-FE to use new Unicode 3.2 characters instead of using either
204#     single corporate-use characters (e.g. 0xBE was mapped to 0xF8E7) or
205#     sequences combining a standard Unicode character with a transcoding
206#     hint (e.g. 0xE6 was mapped to 0x0028+0xF870).
207#
208#   Changes from version n05 to version b02:
209#
210#   - Encoding changed for Mac OS 8.5; 0xA0 now maps to 0x20AC, EURO
211#   SIGN. 0xA0 was unmapped in earlier versions.
212#
213#   Changes from version n03 to version n05:
214#
215#   - Change strict mapping for 0xE1 & 0xF1 from U+2329 & U+232A
216#     to their canonical decompositions, U+3008 & U+3009.
217#
218#   - Change mapping for the following to use standard Unicode +
219#     transcoding hint, instead of single corporate-zone
220#     character: 0xE2-0xE4, 0xE6-0xEE, 0xF4, 0xF6-0xFE.
221#
222##################
223
2240x0000 - 0x007F = 0x00 -
2250x00A9 = 0xD3
226#0x00A9+0xF87F = 0xE3
2270x00AC = 0xD8
2280x00AE = 0xD2
229#0x00AE+0xF87F = 0xE2
2300x00B0 = 0xB0
2310x00B1 = 0xB1
2320x00D7 = 0xB4
2330x00F7 = 0xB8
2340x0192 = 0xA6
2350x0391 = 0x41
2360x0392 = 0x42
2370x0393 = 0x47
2380x0394 = 0x44
2390x0395 = 0x45
2400x0396 = 0x5A
2410x0397 = 0x48
2420x0398 = 0x51
2430x0399 = 0x49
2440x039A = 0x4B
2450x039B = 0x4C
2460x039C = 0x4D
2470x039D = 0x4E
2480x039E = 0x58
2490x039F = 0x4F
2500x03A0 = 0x50
2510x03A1 = 0x52
2520x03A3 = 0x53
2530x03A4 = 0x54
2540x03A5 = 0x55
2550x03A6 = 0x46
2560x03A7 = 0x43
2570x03A8 = 0x59
2580x03A9 = 0x57
2590x03B1 = 0x61
2600x03B2 = 0x62
2610x03B3 = 0x67
2620x03B4 = 0x64
2630x03B5 = 0x65
2640x03B6 = 0x7A
2650x03B7 = 0x68
2660x03B8 = 0x71
2670x03B9 = 0x69
2680x03BA = 0x6B
2690x03BB = 0x6C
2700x03BC = 0x6D
2710x03BD = 0x6E
2720x03BE = 0x78
2730x03BF = 0x6F
2740x03C0 = 0x70
2750x03C1 = 0x72
2760x03C2 = 0x56
2770x03C3 = 0x73
2780x03C4 = 0x74
2790x03C5 = 0x75
2800x03C6 = 0x66
2810x03C7 = 0x63
2820x03C8 = 0x79
2830x03C9 = 0x77
2840x03D1 = 0x4A
2850x03D2 = 0xA1
2860x03D5 = 0x6A
2870x03D6 = 0x76
2880x2022 = 0xB7
2890x2026 = 0xBC
2900x2032 = 0xA2
2910x2033 = 0xB2
2920x2044 = 0xA4
2930x20AC = 0xA0
2940x2111 = 0xC1
2950x2118 = 0xC3
2960x211C = 0xC2
2970x2122 = 0xD4
298#0x2122+0xF87F = 0xE4
2990x2135 = 0xC0
3000x2190 = 0xAC
3010x2191 = 0xAD
3020x2192 = 0xAE
3030x2193 = 0xAF
3040x2194 = 0xAB
3050x21B5 = 0xBF
3060x21D0 = 0xDC
3070x21D1 = 0xDD
3080x21D2 = 0xDE
3090x21D3 = 0xDF
3100x21D4 = 0xDB
3110x2200 = 0x22
3120x2202 = 0xB6
3130x2203 = 0x24
3140x2205 = 0xC6
3150x2207 = 0xD1
3160x2208 = 0xCE
3170x2209 = 0xCF
3180x220D = 0x27
3190x220F = 0xD5
3200x2211 = 0xE5
3210x2212 = 0x2D
3220x2217 = 0x2A
3230x221A = 0xD6
3240x221D = 0xB5
3250x221E = 0xA5
3260x2220 = 0xD0
3270x2227 = 0xD9
3280x2228 = 0xDA
3290x2229 = 0xC7
3300x222A = 0xC8
3310x222B = 0xF2
3320x2234 = 0x5C
3330x223C = 0x7E
3340x2245 = 0x40
3350x2248 = 0xBB
3360x2260 = 0xB9
3370x2261 = 0xBA
3380x2264 = 0xA3
3390x2265 = 0xB3
3400x2282 = 0xCC
3410x2283 = 0xC9
3420x2284 = 0xCB
3430x2286 = 0xCD
3440x2287 = 0xCA
3450x2295 = 0xC5
3460x2297 = 0xC4
3470x22A5 = 0x5E
3480x22C5 = 0xD7
3490x2320 = 0xF3
3500x2321 = 0xF5
3510x239B = 0xE6
3520x239C = 0xE7
3530x239D = 0xE8
3540x239E = 0xF6
3550x239F = 0xF7
3560x23A0 = 0xF8
3570x23A1 = 0xE9
3580x23A2 = 0xEA
3590x23A3 = 0xEB
3600x23A4 = 0xF9
3610x23A5 = 0xFA
3620x23A6 = 0xFB
3630x23A7 = 0xEC
3640x23A8 = 0xED
3650x23A9 = 0xEE
3660x23AA = 0xEF
3670x23AB = 0xFC
3680x23AC = 0xFD
3690x23AD = 0xFE
3700x23AE = 0xF4
3710x23AF = 0xBE
3720x23D0 = 0xBD
3730x25CA = 0xE0
3740x2660 = 0xAA
3750x2663 = 0xA7
3760x2665 = 0xA9
3770x2666 = 0xA8
3780x3008 = 0xE1
3790x3009 = 0xF1
3800xF8E5 = 0x60
3810xF8FF = 0xF0
382END_MAP
383