xref: /freebsd-src/share/i18n/csmapper/APPLE/SYMBOL%UCS.src (revision d0b2dbfa0ecf2bbc9709efc5e20baf8e4b44bbbf)
1
2TYPE		ROWCOL
3NAME		SYMBOL/UCS
4SRC_ZONE	0x00-0xFF
5OOB_MODE	ILSEQ
6DST_ILSEQ	0xFFFE
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
2240x00 - 0x7F = 0x0000 -
2250xA0 = 0x20AC
2260xA1 = 0x03D2
2270xA2 = 0x2032
2280xA3 = 0x2264
2290xA4 = 0x2044
2300xA5 = 0x221E
2310xA6 = 0x0192
2320xA7 = 0x2663
2330xA8 = 0x2666
2340xA9 = 0x2665
2350xAA = 0x2660
2360xAB = 0x2194
2370xAC = 0x2190
2380xAD = 0x2191
2390xAE = 0x2192
2400xAF = 0x2193
2410xB0 = 0x00B0
2420xB1 = 0x00B1
2430xB2 = 0x2033
2440xB3 = 0x2265
2450xB4 = 0x00D7
2460xB5 = 0x221D
2470xB6 = 0x2202
2480xB7 = 0x2022
2490xB8 = 0x00F7
2500xB9 = 0x2260
2510xBA = 0x2261
2520xBB = 0x2248
2530xBC = 0x2026
2540xBD = 0x23D0
2550xBE = 0x23AF
2560xBF = 0x21B5
2570xC0 = 0x2135
2580xC1 = 0x2111
2590xC2 = 0x211C
2600xC3 = 0x2118
2610xC4 = 0x2297
2620xC5 = 0x2295
2630xC6 = 0x2205
2640xC7 = 0x2229
2650xC8 = 0x222A
2660xC9 = 0x2283
2670xCA = 0x2287
2680xCB = 0x2284
2690xCC = 0x2282
2700xCD = 0x2286
2710xCE = 0x2208
2720xCF = 0x2209
2730xD0 = 0x2220
2740xD1 = 0x2207
2750xD2 = 0x00AE
2760xD3 = 0x00A9
2770xD4 = 0x2122
2780xD5 = 0x220F
2790xD6 = 0x221A
2800xD7 = 0x22C5
2810xD8 = 0x00AC
2820xD9 = 0x2227
2830xDA = 0x2228
2840xDB = 0x21D4
2850xDC = 0x21D0
2860xDD = 0x21D1
2870xDE = 0x21D2
2880xDF = 0x21D3
2890xE0 = 0x25CA
2900xE1 = 0x3008
291#0xE2 = 0x00AE+0xF87F
292#0xE3 = 0x00A9+0xF87F
293#0xE4 = 0x2122+0xF87F
2940xE5 = 0x2211
2950xE6 = 0x239B
2960xE7 = 0x239C
2970xE8 = 0x239D
2980xE9 = 0x23A1
2990xEA = 0x23A2
3000xEB = 0x23A3
3010xEC = 0x23A7
3020xED = 0x23A8
3030xEE = 0x23A9
3040xEF = 0x23AA
3050xF0 = 0xF8FF
3060xF1 = 0x3009
3070xF2 = 0x222B
3080xF3 = 0x2320
3090xF4 = 0x23AE
3100xF5 = 0x2321
3110xF6 = 0x239E
3120xF7 = 0x239F
3130xF8 = 0x23A0
3140xF9 = 0x23A4
3150xFA = 0x23A5
3160xFB = 0x23A6
3170xFC = 0x23AB
3180xFD = 0x23AC
3190xFE = 0x23AD
320END_MAP
321