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

TYPE		ROWCOL
NAME		FARSI/UCS
SRC_ZONE	0x00-0xFF
OOB_MODE	ILSEQ
DST_ILSEQ	0xFFFE
DST_UNIT_BITS	16

BEGIN_MAP
#=======================================================================
#   File name:  FARSI.TXT
#
#   Contents:   Map (external version) from Mac OS Farsi
#               character set to Unicode 2.1 and later.
#
#   Copyright:  (c) 1997-2002, 2005 by Apple Computer, Inc., all rights
#               reserved.
#
#   Contact:    charsets@apple.com
#
#   Changes:
#
#       c02  2005-Apr-05    Update header comments. Matches internal xml
#                           <c1.1> 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<b3>.
#       b02  1999-Sep-22    Update contact e-mail address. Matches
#                           internal utom<b1>, ufrm<b1>, and Text
#                           Encoding Converter version 1.5.
#       n04  1998-Feb-05    Show required Unicode character
#                           directionality in a different way. Matches
#                           internal utom<n3>, ufrm<n9>, and Text
#                           Encoding Converter version 1.3. Update
#                           header comments; include information on
#                           loose mapping of digits, and changes to
#                           mapping for the TrueType variant.
#       n01  1997-Jul-17    First version. Matches internal utom<n1>,
#                           ufrm<n2>.
#
# 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 Farsi 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 Farsi code order.
#
#   Control character mappings are not shown in this table, following
#   the conventions of the standard UTC mapping tables. However, the
#   Mac OS Farsi character set uses the standard control characters at
#   0x00-0x1F and 0x7F.
#
# Notes on Mac OS Farsi:
# ----------------------
#
#   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 Farsi character set is based on the Mac OS Arabic
#   character set. The main difference is in the right-to-left digits
#   0xB0-0xB9: For Mac OS Arabic these correspond to right-left
#   versions of the Unicode ARABIC-INDIC DIGITs 0660-0669; for
#   Mac OS Farsi these correspond to right-left versions of the
#   Unicode EXTENDED ARABIC-INDIC DIGITs 06F0-06F9. The other
#   difference is in the nature of the font variants.
#
#   For more information, see the comments in the mapping table for
#   Mac OS Arabic.
#
#   Mac OS Farsi characters 0xEB-0xF2 are non-spacing/combining marks.
#
#   2. Directional characters and roundtrip fidelity
#
#   The Mac OS Arabic character set (on which Mac OS Farsi is based)
#   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. This
#   is the case in Mac OS Farsi too.
#
#   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 Farsi and Unicode;
#   see below.
#
#   A related problem is that even when a particular character is
#   encoded only once in Mac OS Farsi, it may have a different
#   direction attribute than the corresponding Unicode character.
#
#   For example, the Mac OS Farsi 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 Farsi also has two sets of digit codes.

#   The digits at 0x30-0x39 may be displayed using either European
#   digit forms or Persian 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 Persian 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 Persian 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 Farsi encoding. This encoding is supported by the Tehran font
#   (the system font for Farsi), and is the encoding supported by the
#   text processing utilities. However, the other Farsi fonts actually
#   implement a somewhat different encoding; this affects nine code
#   points including 0xAA and 0xC0 (which are also affected by font
#   variants in Mac OS Arabic). For these nine code points the standard
#   Mac OS Farsi encoding has the following mappings:
#       0x8B -> 0x06BA ARABIC LETTER NOON GHUNNA (Urdu)
#       0xA4 -> <RL>+0x0024 DOLLAR SIGN, right-left
#       0xAA -> <RL>+0x002A ASTERISK, right-left
#       0xC0 -> <RL>+0x274A EIGHT TEARDROP-SPOKED PROPELLER ASTERISK,
#               right-left
#       0xF4 -> 0x0679 ARABIC LETTER TTEH (Urdu)
#       0xF7 -> 0x06A4 ARABIC LETTER VEH (for transliteration)
#       0xF9 -> 0x0688 ARABIC LETTER DDAL (Urdu)
#       0xFA -> 0x0691 ARABIC LETTER RREH (Urdu)
#       0xFF -> 0x06D2 ARABIC LETTER YEH BARREE (Urdu)
#
#   The TrueType variant is used for the Farsi TrueType fonts: Ashfahan,
#   Amir, Kamran, Mashad, NadeemFarsi. It differs from the standard
#   variant in the following ways:
#       0x8B -> 0xF882 Arabic ligature "peace on him" (corporate char.)
#       0xA4 -> 0xFDFC RIAL SIGN (added in Unicode 3.2)
#       0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left
#       0xC0 -> <RL>+0x002A ASTERISK, right-left
#       0xF4 -> <RL>+0x00B0 DEGREE SIGN, right-left
#       0xF7 -> 0xFDFA ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM
#       0xF9 -> <RL>+0x25CF BLACK CIRCLE, right-left
#       0xFA -> <RL>+0x25A0 BLACK SQUARE, right-left
#       0xFF -> <RL>+0x25B2 BLACK UP-POINTING TRIANGLE, right-left
#
# Unicode mapping issues and notes:
# ---------------------------------
#
#   1. Matching the direction of Mac OS Farsi characters
#
#   When Mac OS Farsi 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 Farsi
#   code points to Unicode and back again without loss of information.
#   With the plus sign, for example, mapping one of the Mac OS Farsi
#   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 Farsi
#   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 Farsi, the Unicode
#   bidirectional algorithm should be used to determine resolved
#   direction of the Unicode characters. The mapping from Unicode to
#   Mac OS Farsi can then be disambiguated by the use of the resolved
#   direction:
#
#     Unicode 0x002B -> Mac OS Farsi 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 Farsi (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 Farsi
#   characters to Unicode in order to achieve similar text layout with
#   the resulting Unicode text. For example, the single Mac OS Farsi
#   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 Farsi 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 Farsi.
#
#   2. Mapping the Mac OS Farsi 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 Farsi 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	0x06F0	# EXTENDED ARABIC-INDIC DIGIT ZERO
#     0x31	0x06F1	# EXTENDED ARABIC-INDIC DIGIT ONE
#     0x32	0x06F2	# EXTENDED ARABIC-INDIC DIGIT TWO
#     0x33	0x06F3	# EXTENDED ARABIC-INDIC DIGIT THREE
#     0x34	0x06F4	# EXTENDED ARABIC-INDIC DIGIT FOUR
#     0x35	0x06F5	# EXTENDED ARABIC-INDIC DIGIT FIVE
#     0x36	0x06F6	# EXTENDED ARABIC-INDIC DIGIT SIX
#     0x37	0x06F7	# EXTENDED ARABIC-INDIC DIGIT SEVEN
#     0x38	0x06F8	# EXTENDED ARABIC-INDIC DIGIT EIGHT
#     0x39	0x06F9	# EXTENDED ARABIC-INDIC DIGIT NINE
#
#   3. Use of corporate-zone Unicodes (mapping the TrueType variant)
#
#   The following corporate zone Unicode character is used in this
#   mapping:
#
#     0xF882  Arabic ligature "peace on him"
#
# Details of mapping changes in each version:
# -------------------------------------------
#
#   Changes from version b02 to version b03/c01:
#
#   - Update mapping of 0xA4 in TrueType variant to use new Unicode
#     character U+FDFC RIAL SIGN addded for Unicode 3.2
#
#   Changes from version n01 to version n04:
#
#   - Change mapping of 0xA4 in TrueType variant (just described in
#     header comment) from single corporate character to use
#     grouping hint
#
##################

0x00 - 0x7F = 0x0000 -
0x80 = 0x00C4
0x81 = 0x00A0
0x82 = 0x00C7
0x83 = 0x00C9
0x84 = 0x00D1
0x85 = 0x00D6
0x86 = 0x00DC
0x87 = 0x00E1
0x88 = 0x00E0
0x89 = 0x00E2
0x8A = 0x00E4
0x8B = 0x06BA
0x8C = 0x00AB
0x8D = 0x00E7
0x8E = 0x00E9
0x8F = 0x00E8
0x90 = 0x00EA
0x91 = 0x00EB
0x92 = 0x00ED
0x93 = 0x2026
0x94 = 0x00EE
0x95 = 0x00EF
0x96 = 0x00F1
0x97 = 0x00F3
0x98 = 0x00BB
0x99 = 0x00F4
0x9A = 0x00F6
0x9B = 0x00F7
0x9C = 0x00FA
0x9D = 0x00F9
0x9E = 0x00FB
0x9F = 0x00FC
0xA0 = 0x0020
0xA1 = 0x0021
0xA2 = 0x0022
0xA3 = 0x0023
0xA4 = 0x0024
0xA5 = 0x066A
0xA6 = 0x0026
0xA7 = 0x0027
0xA8 = 0x0028
0xA9 = 0x0029
0xAA = 0x002A
0xAB = 0x002B
0xAC = 0x060C
0xAD = 0x002D
0xAE = 0x002E
0xAF = 0x002F
0xB0 = 0x06F0
0xB1 = 0x06F1
0xB2 = 0x06F2
0xB3 = 0x06F3
0xB4 = 0x06F4
0xB5 = 0x06F5
0xB6 = 0x06F6
0xB7 = 0x06F7
0xB8 = 0x06F8
0xB9 = 0x06F9
0xBA = 0x003A
0xBB = 0x061B
0xBC = 0x003C
0xBD = 0x003D
0xBE = 0x003E
0xBF = 0x061F
0xC0 = 0x274A
0xC1 = 0x0621
0xC2 = 0x0622
0xC3 = 0x0623
0xC4 = 0x0624
0xC5 = 0x0625
0xC6 = 0x0626
0xC7 = 0x0627
0xC8 = 0x0628
0xC9 = 0x0629
0xCA = 0x062A
0xCB = 0x062B
0xCC = 0x062C
0xCD = 0x062D
0xCE = 0x062E
0xCF = 0x062F
0xD0 = 0x0630
0xD1 = 0x0631
0xD2 = 0x0632
0xD3 = 0x0633
0xD4 = 0x0634
0xD5 = 0x0635
0xD6 = 0x0636
0xD7 = 0x0637
0xD8 = 0x0638
0xD9 = 0x0639
0xDA = 0x063A
0xDB = 0x005B
0xDC = 0x005C
0xDD = 0x005D
0xDE = 0x005E
0xDF = 0x005F
0xE0 = 0x0640
0xE1 = 0x0641
0xE2 = 0x0642
0xE3 = 0x0643
0xE4 = 0x0644
0xE5 = 0x0645
0xE6 = 0x0646
0xE7 = 0x0647
0xE8 = 0x0648
0xE9 = 0x0649
0xEA = 0x064A
0xEB = 0x064B
0xEC = 0x064C
0xED = 0x064D
0xEE = 0x064E
0xEF = 0x064F
0xF0 = 0x0650
0xF1 = 0x0651
0xF2 = 0x0652
0xF3 = 0x067E
0xF4 = 0x0679
0xF5 = 0x0686
0xF6 = 0x06D5
0xF7 = 0x06A4
0xF8 = 0x06AF
0xF9 = 0x0688
0xFA = 0x0691
0xFB = 0x007B
0xFC = 0x007C
0xFD = 0x007D
0xFE = 0x0698
0xFF = 0x06D2
END_MAP