xref: /freebsd/share/i18n/csmapper/APPLE/UCS%SYMBOL.src (revision d0b2dbfa0ecf2bbc9709efc5e20baf8e4b44bbbf)

TYPE		ROWCOL
NAME		UCS/SYMBOL
SRC_ZONE	0x0000-0xF8FF
OOB_MODE	INVALID
DST_INVALID	0x100
DST_UNIT_BITS	16

BEGIN_MAP
#=======================================================================
#   File name:  SYMBOL.TXT
#
#   Contents:   Map (external version) from Mac OS Symbol
#               character set to Unicode 4.0 and later.
#
#   Copyright:  (c) 1994-2002, 2005 by Apple Computer, Inc., all rights
#               reserved.
#
#   Contact:    charsets@apple.com
#
#   Changes:
#
#       c02  2005-Apr-05    Change mappings for 0xBD, 0xE0. Update
#                           header comments. Matches internal xml <c1.2>
#                           and Text Encoding Converter 2.0.
#      b4,c1 2002-Dec-19    Update mappings for encoded glyph fragments
#                           0xBE, 0xE6-EF, 0xF4, 0xF6-FE to use new
#                           Unicode 3.2 characters instead of sequences
#                           involving corporate-use characters. Update
#                           URLs, notes. Matches internal utom<b4>.
#       b03  1999-Sep-22    Update contact e-mail address. Matches
#                           internal utom<b3>, ufrm<b3>, and Text
#                           Encoding Converter version 1.5.
#       b02  1998-Aug-18    Encoding changed for Mac OS 8.5; add new
#                           mapping from 0xA0 to EURO SIGN. Matches
#                           internal utom<b3>, ufrm<b3>.
#       n05  1998-Feb-05    Update to match internal utom<n5>, ufrm<n15>
#                           and Text Encoding Converter version 1.3:
#                           Use standard Unicodes plus transcoding hints
#                           instead of single corporate characters, also
#                           change mappings for 0xE1 & 0xF1 from U+2329
#                           & U+232A to their canonical decompositions;
#                           see details below. Also update header
#                           comments to new format.
#       n03  1995-Apr-15    First version (after fixing some typos).
#                           Matches internal ufrm<n4>.
#
# 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 Symbol 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.
#       In some cases an additional comment follows the Unicode name.
#
#   The entries are in Mac OS Symbol 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 Symbol character set uses the standard control characters
#   at 0x00-0x1F and 0x7F.
#
# Notes on Mac OS Symbol:
# -----------------------
#
#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
#   environments, it is only supported directly in programming
#   interfaces for QuickDraw Text, the Script Manager, and related
#   Text Utilities. For other purposes it is supported via transcoding
#   to and from Unicode.
#
#   The Mac OS Symbol encoding shares the script code smRoman
#   (0) with the Mac OS Roman encoding. To determine if the Symbol
#   encoding is being used, you must check if the font name is
#   "Symbol".
#
#   Before Mac OS 8.5, code point 0xA0 was unused. In Mac OS 8.5
#   and later versions, code point 0xA0 is EURO SIGN and maps to
#   U+20AC (the Symbol font is updated for Mac OS 8.5 to reflect
#   this).
#
#   The layout of the Mac OS Symbol character set is identical to
#   the layout of the Adobe Symbol encoding vector, with the
#   addition of the Apple logo character at 0xF0.
#
#   This character set encodes a number of glyph fragments. Some are
#   used as extenders: 0x60 is used to extend radical signs, 0xBD and
#   0xBE are used to extend vertical and horizontal arrows, etc. In
#   addition, there are top, bottom, and center sections for
#   parentheses, brackets, integral signs, and other signs that may
#   extend vertically for 2 or more lines of normal text. As of
#   Unicode 3.2, most of these are now encoded in Unicode; a few are
#   not, so these are mapped using corporate-zone Unicode characters
#   (see below).
#
#   In addition, Symbol separately encodes both serif and sans-serif
#   forms for copyright, trademark, and registered signs. Unicode
#   encodes only the abstract characters, so one set of these (the
#   sans-serif forms) are also mapped using corporate-zone Unicode
#   characters (see below).
#
#   The following code points are unused, and are not shown here:
#   0x80-0x9F, 0xFF.
#
# Unicode mapping issues and notes:
# ---------------------------------
#
#   The goals in the mappings provided here are:
#   - Ensure roundtrip mapping from every character in the Mac OS
#     Symbol 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.
#
#   Some of the characters in the Mac OS Symbol character set do not
#   correspond to distinct, single Unicode characters. To map these
#   and satisfy both goals above, we employ various strategies.
#
#   a) If possible, use private use characters in combination with
#   standard Unicode characters to mark variants of the standard
#   Unicode character.
#
#   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 hint used in this mapping table is the
#   variant tag 0xF87F. Since this is combined with standard Unicode
#   characters, some characters in the Mac OS Symbol character set map
#   to a sequence of two Unicodes instead of a single Unicode character.
#
#   For example, the Mac OS Symbol character at 0xE2 is an alternate,
#   sans-serif form of the REGISTERED SIGN (the standard mapping is for
#   the abstract character at 0xD2, which here has a serif form). So 0xE2
#   is mapped to 0x00AE (REGISTERED SIGN) + 0xF87F (a variant tag).
#
#   b) Otherwise, use private use characters by themselves to map
#   Mac OS Symbol characters which have no relationship to any standard
#   Unicode character.
#
#   The following additional corporate zone Unicode characters are
#   used for this purpose here:
#
#     0xF8E5  radical extender
#     0xF8FF  Apple logo
#
#   NOTE: The graphic image associated with the Apple logo character
#   is not authorized for use without permission of Apple, and
#   unauthorized use might constitute trademark infringement.
#
# Details of mapping changes in each version:
# -------------------------------------------
#
#   Changes from version c01 to version c02:
#
#   - Update mappings for 0xBD from 0xF8E6 to 0x23D0 (use new Unicode
#     4.0 char)
#   - Correct mapping for 0xE0 from 0x22C4 to 0x25CA
#
#   Changes from version b02 to version b03/c01:
#
#   - Update mappings for encoded glyph fragments 0xBE, 0xE6-EF, 0xF4,
#     0xF6-FE to use new Unicode 3.2 characters instead of using either
#     single corporate-use characters (e.g. 0xBE was mapped to 0xF8E7) or
#     sequences combining a standard Unicode character with a transcoding
#     hint (e.g. 0xE6 was mapped to 0x0028+0xF870).
#
#   Changes from version n05 to version b02:
#
#   - Encoding changed for Mac OS 8.5; 0xA0 now maps to 0x20AC, EURO
#   SIGN. 0xA0 was unmapped in earlier versions.
#
#   Changes from version n03 to version n05:
#
#   - Change strict mapping for 0xE1 & 0xF1 from U+2329 & U+232A
#     to their canonical decompositions, U+3008 & U+3009.
#
#   - Change mapping for the following to use standard Unicode +
#     transcoding hint, instead of single corporate-zone
#     character: 0xE2-0xE4, 0xE6-0xEE, 0xF4, 0xF6-0xFE.
#
##################

0x0000 - 0x007F = 0x00 -
0x00A9 = 0xD3
#0x00A9+0xF87F = 0xE3
0x00AC = 0xD8
0x00AE = 0xD2
#0x00AE+0xF87F = 0xE2
0x00B0 = 0xB0
0x00B1 = 0xB1
0x00D7 = 0xB4
0x00F7 = 0xB8
0x0192 = 0xA6
0x0391 = 0x41
0x0392 = 0x42
0x0393 = 0x47
0x0394 = 0x44
0x0395 = 0x45
0x0396 = 0x5A
0x0397 = 0x48
0x0398 = 0x51
0x0399 = 0x49
0x039A = 0x4B
0x039B = 0x4C
0x039C = 0x4D
0x039D = 0x4E
0x039E = 0x58
0x039F = 0x4F
0x03A0 = 0x50
0x03A1 = 0x52
0x03A3 = 0x53
0x03A4 = 0x54
0x03A5 = 0x55
0x03A6 = 0x46
0x03A7 = 0x43
0x03A8 = 0x59
0x03A9 = 0x57
0x03B1 = 0x61
0x03B2 = 0x62
0x03B3 = 0x67
0x03B4 = 0x64
0x03B5 = 0x65
0x03B6 = 0x7A
0x03B7 = 0x68
0x03B8 = 0x71
0x03B9 = 0x69
0x03BA = 0x6B
0x03BB = 0x6C
0x03BC = 0x6D
0x03BD = 0x6E
0x03BE = 0x78
0x03BF = 0x6F
0x03C0 = 0x70
0x03C1 = 0x72
0x03C2 = 0x56
0x03C3 = 0x73
0x03C4 = 0x74
0x03C5 = 0x75
0x03C6 = 0x66
0x03C7 = 0x63
0x03C8 = 0x79
0x03C9 = 0x77
0x03D1 = 0x4A
0x03D2 = 0xA1
0x03D5 = 0x6A
0x03D6 = 0x76
0x2022 = 0xB7
0x2026 = 0xBC
0x2032 = 0xA2
0x2033 = 0xB2
0x2044 = 0xA4
0x20AC = 0xA0
0x2111 = 0xC1
0x2118 = 0xC3
0x211C = 0xC2
0x2122 = 0xD4
#0x2122+0xF87F = 0xE4
0x2135 = 0xC0
0x2190 = 0xAC
0x2191 = 0xAD
0x2192 = 0xAE
0x2193 = 0xAF
0x2194 = 0xAB
0x21B5 = 0xBF
0x21D0 = 0xDC
0x21D1 = 0xDD
0x21D2 = 0xDE
0x21D3 = 0xDF
0x21D4 = 0xDB
0x2200 = 0x22
0x2202 = 0xB6
0x2203 = 0x24
0x2205 = 0xC6
0x2207 = 0xD1
0x2208 = 0xCE
0x2209 = 0xCF
0x220D = 0x27
0x220F = 0xD5
0x2211 = 0xE5
0x2212 = 0x2D
0x2217 = 0x2A
0x221A = 0xD6
0x221D = 0xB5
0x221E = 0xA5
0x2220 = 0xD0
0x2227 = 0xD9
0x2228 = 0xDA
0x2229 = 0xC7
0x222A = 0xC8
0x222B = 0xF2
0x2234 = 0x5C
0x223C = 0x7E
0x2245 = 0x40
0x2248 = 0xBB
0x2260 = 0xB9
0x2261 = 0xBA
0x2264 = 0xA3
0x2265 = 0xB3
0x2282 = 0xCC
0x2283 = 0xC9
0x2284 = 0xCB
0x2286 = 0xCD
0x2287 = 0xCA
0x2295 = 0xC5
0x2297 = 0xC4
0x22A5 = 0x5E
0x22C5 = 0xD7
0x2320 = 0xF3
0x2321 = 0xF5
0x239B = 0xE6
0x239C = 0xE7
0x239D = 0xE8
0x239E = 0xF6
0x239F = 0xF7
0x23A0 = 0xF8
0x23A1 = 0xE9
0x23A2 = 0xEA
0x23A3 = 0xEB
0x23A4 = 0xF9
0x23A5 = 0xFA
0x23A6 = 0xFB
0x23A7 = 0xEC
0x23A8 = 0xED
0x23A9 = 0xEE
0x23AA = 0xEF
0x23AB = 0xFC
0x23AC = 0xFD
0x23AD = 0xFE
0x23AE = 0xF4
0x23AF = 0xBE
0x23D0 = 0xBD
0x25CA = 0xE0
0x2660 = 0xAA
0x2663 = 0xA7
0x2665 = 0xA9
0x2666 = 0xA8
0x3008 = 0xE1
0x3009 = 0xF1
0xF8E5 = 0x60
0xF8FF = 0xF0
END_MAP