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

TYPE		ROWCOL
NAME		UCS/ARABIC
SRC_ZONE	0x0000-0xFB02
OOB_MODE	INVALID
DST_INVALID	0x100
DST_UNIT_BITS	16

BEGIN_MAP
#=======================================================================
#   File name:  ARABIC.TXT
#
#   Contents:   Map (external version) from Mac OS Arabic
#               character set to Unicode 2.1 and later.
#
#   Copyright:  (c) 1994-2002, 2005 by Apple Computer, Inc., all rights
#               reserved.
#
#   Contact:    charsets@apple.com
#
#   Changes:
#
#       c02  2005-Apr-04    Update header comments. Matches internal xml
#                           <c1.2> and Text Encoding Converter 2.0.
#      b3,c1 2002-Dec-19    Add comments about character display and
#                           direction overrides. Update URLs, notes.
#                           Matches internal utom<b4>.
#       b02  1999-Sep-22    Update contact e-mail address. Matches
#                           internal utom<b1>, ufrm<b1>, and Text
#                           Encoding Converter version 1.5.
#       n10  1998-Feb-05    Show required Unicode character
#                           directionality in a different way. Matches
#                           internal utom<n4>, ufrm<n21>, and Text
#                           Encoding Converter version 1.3. Update
#                           header comments; include information on
#                           loose mapping of digits.
#       n07  1997-Jul-17    Update to match internal utom<n2>, ufrm<n17>:
#                           Change standard mapping for 0xC0 from U+066D
#                           to U+274A. Add direction overrides to
#                           mappings for 0x25, 0x2C, 0x3B, 0x3F. Add
#                           information on variants.
#       n03  1995-Apr-18    First version (after fixing some typos).
#                           Matches internal ufrm<n11>.
#
# 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 Arabic code (in hex as 0xNN).
#     Column #2 is the corresponding Unicode (in hex as 0xNNNN),
#       possibly preceded by a tag indicating required directionality
#       (i.e. <LR>+0xNNNN or <RL>+0xNNNN).
#     Column #3 is a comment containing the Unicode name.
#
#   The entries are in Mac OS Arabic code order.
#
#   Control character mappings are not shown in this table, following
#   the conventions of the standard UTC mapping tables. However, the
#   Mac OS Arabic character set uses the standard control characters at
#   0x00-0x1F and 0x7F.
#
# Notes on Mac OS Arabic:
# -----------------------
#
#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
#   environments, it is only supported via transcoding to and from
#   Unicode.
#
#   1. General
#
#   The Mac OS Arabic character set is intended to cover Arabic as
#   used in North Africa, the Arabian peninsula, and the Levant. It
#   also contains several characters needed for Urdu and/or Farsi.
#
#   The Mac OS Arabic character set is essentially a superset of ISO
#   8859-6. The 8859-6 code points that are interpreted differently
#   in the Mac OS Arabic set are as follows:
#    0xA0 is NO-BREAK SPACE in 8859-6 and right-left SPACE in Mac OS
#         Arabic; NO-BREAK is 0x81 in Mac OS Arabic.
#    0xA4 is CURRENCY SIGN in 8859-6 and right-left DOLLAR SIGN in
#         Mac OS Arabic.
#    0xAD is SOFT HYPHEN in 8859-6 and right-left HYPHEN-MINUS in
#         Mac OS Arabic.
#   ISO 8859-6 specifies that codes 0x30-0x39 can be rendered either
#   with European digit shapes or Arabic digit shapes. This is also
#   true in Mac OS Arabic, which determines from context which digit
#   shapes to use (see below).
#
#   The Mac OS Arabic character set uses the C1 controls area and other
#   code points which are undefined in ISO 8859-6 for additional
#   graphic characters: additional Arabic letters for Farsi and Urdu,
#   some accented Roman letters for European languages (such as French),
#   and duplicates of some of the punctuation, symbols, and digits in
#   the ASCII block. The duplicate punctuation, symbol, and digit
#   characters have right-left directionality, while the ASCII versions
#   have left-right directionality. See the next section for more
#   information on this.
#
#   Mac OS Arabic characters 0xEB-0xF2 are non-spacing/combining marks.
#
#   2. Directional characters and roundtrip fidelity
#
#   The Mac OS Arabic character set was developed in 1986-1987. At that
#   time the bidirectional line layout algorithm used in the Mac OS
#   Arabic system was fairly simple; it used only a few direction
#   classes (instead of the 19 now used in the Unicode bidirectional
#   algorithm). In order to permit users to handle some tricky layout
#   problems, certain punctuation and symbol characters were encoded
#   twice, one with a left-right direction attribute and the other with
#   a right-left direction attribute.
#
#   For example, plus sign is encoded at 0x2B with a left-right
#   attribute, and at 0xAB with a right-left attribute. However, there
#   is only one PLUS SIGN character in Unicode. This leads to some
#   interesting problems when mapping between Mac OS Arabic and Unicode;
#   see below.
#
#   A related problem is that even when a particular character is
#   encoded only once in Mac OS Arabic, it may have a different
#   direction attribute than the corresponding Unicode character.
#
#   For example, the Mac OS Arabic character at 0x93 is HORIZONTAL
#   ELLIPSIS with strong right-left direction. However, the Unicode
#   character HORIZONTAL ELLIPSIS has direction class neutral.
#
#   3. Behavior of ASCII-range numbers in WorldScript
#
#   Mac OS Arabic also has two sets of digit codes.
#
#   The digits at 0x30-0x39 may be displayed using either European
#   digit forms or Arabic digit forms, depending on context. If there
#   is a "strong European" character such as a Latin letter on either
#   side of a sequence consisting of digits 0x30-0x39 and possibly comma
#   0x2C or period 0x2E, then the characters will be displayed using
#   European forms (This will happen even if there are neutral characters
#   between the digits and the strong European character). Otherwise, the
#   digits will be displayed using Arabic forms, the comma will be
#   displayed as Arabic thousands separator, and the period as Arabic
#   decimal separator. In any case, 0x2C, 0x2E, and 0x30-0x39 are always
#   left-right.
#
#   The digits at 0xB0-0xB9 are always displayed using Arabic digit
#   shapes, and moreover, these digits always have strong right-left
#   directionality. These are mainly intended for special layout
#   purposes such as part numbers, etc.
#
#   4. Font variants
#
#   The table in this file gives the Unicode mappings for the standard
#   Mac OS Arabic encoding. This encoding is supported by the Cairo font
#   (the system font for Arabic), and is the encoding supported by the
#   text processing utilities. However, the other Arabic fonts actually
#   implement slightly different encodings; this mainly affects the code
#   points 0xAA and 0xC0. For these code points the standard Mac OS
#   Arabic encoding has the following mappings:
#     0xAA -> <RL>+0x002A ASTERISK, right-left
#     0xC0 -> <RL>+0x274A EIGHT TEARDROP-SPOKED PROPELLER ASTERISK,
#                         right-left
#   This mapping of 0xAA is consistent with the normal convention for
#   Mac OS Arabic and Hebrew that the right-left duplicates have codes
#   that are equal to the ASCII code of the left-right character plus
#   0x80. However, in all of the other fonts, 0xAA is MULTIPLY SIGN, and
#   right-left ASTERISK may be at a different code point. The other
#   variants are described below.
#
#   The TrueType variant is used for most of the Arabic TrueType fonts:
#   Baghdad, Geeza, Kufi, Nadeem.  It differs from the standard variant
#   in the following way:
#     0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left
#     0xC0 -> <RL>+0x002A ASTERISK, right-left
#
#   The Thuluth variant is used for the Arabic Postscript-only fonts:
#   Thuluth and Thuluth bold. It differs from the standard variant in
#   the following way:
#     0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left
#     0xC0 -> 0x066D ARABIC FIVE POINTED STAR
#
#   The AlBayan variant is used for the Arabic TrueType font Al Bayan.
#   It differs from the standard variant in the following way:
#     0x81 -> no mapping (glyph just has authorship information, etc.)
#     0xA3 -> 0xFDFA ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM
#     0xA4 -> 0xFDF2 ARABIC LIGATURE ALLAH ISOLATED FORM
#     0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left
#     0xDC -> <RL>+0x25CF BLACK CIRCLE, right-left
#     0xFC -> <RL>+0x25A0 BLACK SQUARE, right-left
#
# Unicode mapping issues and notes:
# ---------------------------------
#
#   1. Matching the direction of Mac OS Arabic characters
#
#   When Mac OS Arabic encodes a character twice but with different
#   direction attributes for the two code points - as in the case of
#   plus sign mentioned above - we need a way to map both Mac OS Arabic
#   code points to Unicode and back again without loss of information.
#   With the plus sign, for example, mapping one of the Mac OS Arabic
#   characters to a code in the Unicode corporate use zone is
#   undesirable, since both of the plus sign characters are likely to
#   be used in text that is interchanged.
#
#   The problem is solved with the use of direction override characters
#   and direction-dependent mappings. When mapping from Mac OS Arabic
#   to Unicode, we use direction overrides as necessary to force the
#   direction of the resulting Unicode characters.
#
#   The required direction is indicated by a direction tag in the
#   mappings. A tag of <LR> means the corresponding Unicode character
#   must have a strong left-right context, and a tag of <RL> indicates
#   a right-left context.
#
#   For example, the mapping of 0x2B is given as <LR>+0x002B; the
#   mapping of 0xAB is given as <RL>+0x002B. If we map an isolated
#   instance of 0x2B to Unicode, it should be mapped as follows (LRO
#   indicates LEFT-RIGHT OVERRIDE, PDF indicates POP DIRECTION
#   FORMATTING):
#
#     0x2B ->  0x202D (LRO) + 0x002B (PLUS SIGN) + 0x202C (PDF)
#
#   When mapping several characters in a row that require direction
#   forcing, the overrides need only be used at the beginning and end.
#   For example:
#
#     0x24 0x20 0x28 0x29 -> 0x202D 0x0024 0x0020 0x0028 0x0029 0x202C
#
#   If neutral characters that require direction forcing are already
#   between strong-direction characters with matching directionality,
#   then direction overrides need not be used. Direction overrides are
#   always needed to map the right-left digits at 0xB0-0xB9.
#
#   When mapping from Unicode to Mac OS Arabic, the Unicode
#   bidirectional algorithm should be used to determine resolved
#   direction of the Unicode characters. The mapping from Unicode to
#   Mac OS Arabic can then be disambiguated by the use of the resolved
#   direction:
#
#     Unicode 0x002B -> Mac OS Arabic 0x2B (if L) or 0xAB (if R)
#
#   However, this also means the direction override characters should
#   be discarded when mapping from Unicode to Mac OS Arabic (after
#   they have been used to determine resolved direction), since the
#   direction override information is carried by the code point itself.
#
#   Even when direction overrides are not needed for roundtrip
#   fidelity, they are sometimes used when mapping Mac OS Arabic
#   characters to Unicode in order to achieve similar text layout with
#   the resulting Unicode text. For example, the single Mac OS Arabic
#   ellipsis character has direction class right-left,and there is no
#   left-right version. However, the Unicode HORIZONTAL ELLIPSIS
#   character has direction class neutral (which means it may end up
#   with a resolved direction of left-right if surrounded by left-right
#   characters). When mapping the Mac OS Arabic ellipsis to Unicode, it
#   is surrounded with a direction override to help preserve proper
#   text layout. The resolved direction is not needed or used when
#   mapping the Unicode HORIZONTAL ELLIPSIS back to Mac OS Arabic.
#
#   2. Mapping the Mac OS Arabic digits
#
#   The main table below contains mappings that should be used when
#   strict round-trip fidelity is required. However, for numeric
#   values, the mappings in that table will produce Unicode characters
#   that may appear different than the Mac OS Arabic text displayed on
#   a Mac OS system using WorldScript. This is because WorldScript
#   uses context-dependent display for the 0x30-0x39 digits.
#
#   If roundtrip fidelity is not required, then the following
#   alternate mappings should be used when a sequence of 0x30-0x39
#   digits - possibly including 0x2C and 0x2E - occurs in an Arabic
#   context (that is, when the first "strong" character on either side
#   of the digit sequence is Arabic, or there is no strong character):
#
#     0x2C	0x066C	# ARABIC THOUSANDS SEPARATOR
#     0x2E	0x066B	# ARABIC DECIMAL SEPARATOR
#     0x30	0x0660	# ARABIC-INDIC DIGIT ZERO
#     0x31	0x0661	# ARABIC-INDIC DIGIT ONE
#     0x32	0x0662	# ARABIC-INDIC DIGIT TWO
#     0x33	0x0663	# ARABIC-INDIC DIGIT THREE
#     0x34	0x0664	# ARABIC-INDIC DIGIT FOUR
#     0x35	0x0665	# ARABIC-INDIC DIGIT FIVE
#     0x36	0x0666	# ARABIC-INDIC DIGIT SIX
#     0x37	0x0667	# ARABIC-INDIC DIGIT SEVEN
#     0x38	0x0668	# ARABIC-INDIC DIGIT EIGHT
#     0x39	0x0669	# ARABIC-INDIC DIGIT NINE
#
# Details of mapping changes in each version:
# -------------------------------------------
#
#   Changes from version n03 to version n07:
#
#   - Change mapping for 0xC0 from U+066D to U+274A.
#
#   - Add direction overrides (required directionality) to mappings
#     for 0x25, 0x2C, 0x3B, 0x3F.
#
##################
0x0000 - 0x007F = 0x00 -
0x00A0 = 0x81
0x00AB = 0x8C
0x00BB = 0x98
0x00C4 = 0x80
0x00C7 = 0x82
0x00C9 = 0x83
0x00D1 = 0x84
0x00D6 = 0x85
0x00DC = 0x86
0x00E0 = 0x88
0x00E1 = 0x87
0x00E2 = 0x89
0x00E4 = 0x8A
0x00E7 = 0x8D
0x00E8 = 0x8F
0x00E9 = 0x8E
0x00EA = 0x90
0x00EB = 0x91
0x00ED = 0x92
0x00EE = 0x94
0x00EF = 0x95
0x00F1 = 0x96
0x00F3 = 0x97
0x00F4 = 0x99
0x00F6 = 0x9A
0x00F7 = 0x9B
0x00F9 = 0x9D
0x00FA = 0x9C
0x00FB = 0x9E
0x00FC = 0x9F
0x060C = 0xAC
0x061B = 0xBB
0x061F = 0xBF
0x0621 = 0xC1
0x0622 = 0xC2
0x0623 = 0xC3
0x0624 = 0xC4
0x0625 = 0xC5
0x0626 = 0xC6
0x0627 = 0xC7
0x0628 = 0xC8
0x0629 = 0xC9
0x062A = 0xCA
0x062B = 0xCB
0x062C = 0xCC
0x062D = 0xCD
0x062E = 0xCE
0x062F = 0xCF
0x0630 = 0xD0
0x0631 = 0xD1
0x0632 = 0xD2
0x0633 = 0xD3
0x0634 = 0xD4
0x0635 = 0xD5
0x0636 = 0xD6
0x0637 = 0xD7
0x0638 = 0xD8
0x0639 = 0xD9
0x063A = 0xDA
0x0640 = 0xE0
0x0641 = 0xE1
0x0642 = 0xE2
0x0643 = 0xE3
0x0644 = 0xE4
0x0645 = 0xE5
0x0646 = 0xE6
0x0647 = 0xE7
0x0648 = 0xE8
0x0649 = 0xE9
0x064A = 0xEA
0x064B = 0xEB
0x064C = 0xEC
0x064D = 0xED
0x064E = 0xEE
0x064F = 0xEF
0x0650 = 0xF0
0x0651 = 0xF1
0x0652 = 0xF2
0x0660 = 0xB0
0x0661 = 0xB1
0x0662 = 0xB2
0x0663 = 0xB3
0x0664 = 0xB4
0x0665 = 0xB5
0x0666 = 0xB6
0x0667 = 0xB7
0x0668 = 0xB8
0x0669 = 0xB9
0x066A = 0xA5
0x066D = 0xC0
0x0679 = 0xF4
0x067E = 0xF3
0x0686 = 0xF5
0x0688 = 0xF9
0x0691 = 0xFA
0x0698 = 0xFE
0x06A4 = 0xF7
0x06AF = 0xF8
0x06BA = 0x8B
0x06D2 = 0xFF
0x06D5 = 0xF6
0x2026 = 0x93
0x274A = 0xC0
END_MAP