xref: /freebsd-src/share/i18n/csmapper/APPLE/UCS%GUJARATI.src (revision d0b2dbfa0ecf2bbc9709efc5e20baf8e4b44bbbf)
1
2TYPE		ROWCOL
3NAME		UCS/GUJARATI
4SRC_ZONE	0x0000-0xFFFF
5OOB_MODE	INVALID
6DST_INVALID	0x100
7DST_UNIT_BITS	16
8#=======================================================================
9#   File name:  GUJARATI.TXT
10#
11#   Contents:   Map (external version) from Mac OS Gujarati
12#               encoding to Unicode 2.1 and later.
13#
14#   Copyright:  (c) 1997-2002, 2005 by Apple Computer, Inc., all rights
15#               reserved.
16#
17#   Contact:    charsets@apple.com
18#
19#   Changes:
20#
21#       c02  2005-Apr-05    Update header comments. Matches internal xml
22#                           <c1.1> and Text Encoding Converter 2.0.
23#      b3,c1 2002-Dec-19    Update URLs. Matches internal utom<b1>.
24#       b02  1999-Sep-22    Update contact e-mail address. Matches
25#                           internal utom<b1>, ufrm<b1>, and Text
26#                           Encoding Converter version 1.5.
27#       n02  1998-Feb-05    First version; matches internal utom<n4>,
28#                           ufrm<n5>.
29#
30# Standard header:
31# ----------------
32#
33#   Apple, the Apple logo, and Macintosh are trademarks of Apple
34#   Computer, Inc., registered in the United States and other countries.
35#   Unicode is a trademark of Unicode Inc. For the sake of brevity,
36#   throughout this document, "Macintosh" can be used to refer to
37#   Macintosh computers and "Unicode" can be used to refer to the
38#   Unicode standard.
39#
40#   Apple Computer, Inc. ("Apple") makes no warranty or representation,
41#   either express or implied, with respect to this document and the
42#   included data, its quality, accuracy, or fitness for a particular
43#   purpose. In no event will Apple be liable for direct, indirect,
44#   special, incidental, or consequential damages resulting from any
45#   defect or inaccuracy in this document or the included data.
46#
47#   These mapping tables and character lists are subject to change.
48#   The latest tables should be available from the following:
49#
50#   <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
51#
52#   For general information about Mac OS encodings and these mapping
53#   tables, see the file "README.TXT".
54#
55# Format:
56# -------
57#
58#   Three tab-separated columns;
59#   '#' begins a comment which continues to the end of the line.
60#     Column #1 is the Mac OS Gujarati code or code sequence
61#       (in hex as 0xNN or 0xNN+0xNN)
62#     Column #2 is the corresponding Unicode or Unicode sequence
63#       (in hex as 0xNNNN or 0xNNNN+0xNNNN).
64#     Column #3 is a comment containing the Unicode name or sequence
65#       of names. In some cases an additional comment follows the
66#       Unicode name(s).
67#
68#   The entries are in two sections. The first section is for pairs of
69#   Mac OS Gujarati code points that must be mapped in a special way.
70#   The second section maps individual code points.
71#
72#   Within each section, the entries are in Mac OS Gujarati code order.
73#
74#   Control character mappings are not shown in this table, following
75#   the conventions of the standard UTC mapping tables. However, the
76#   Mac OS Gujarati character set uses the standard control characters
77#   at 0x00-0x1F and 0x7F.
78#
79# Notes on Mac OS Gujarati:
80# -------------------------
81#
82#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
83#   environments, it is only supported via transcoding to and from
84#   Unicode.
85#
86#   Mac OS Gujarati is based on IS 13194:1991 (ISCII-91), with the
87#   addition of several punctuation and symbol characters. However,
88#   Mac OS Gujarati does not support the ATR (attribute) mechanism of
89#   ISCII-91.
90#
91# 1. ISCII-91 features in Mac OS Gujarati include:
92#
93#  a) Overloading of nukta
94#
95#     In addition to using the nukta (0xE9) like a combining dot below,
96#     nukta is overloaded to function as a general character modifier.
97#     In this role, certain code points followed by 0xE9 are treated as
98#     a two-byte code point representing a character which may be
99#     rather different than the characters represented by either of
100#     the code points alone. For example, the character GUJARATI OM
101#     (U+0AD0) is represented in ISCII-91 as candrabindu + nukta.
102#
103#  b) Explicit halant and soft halant
104#
105#     A double halant (0xE8 + 0xE8) constitutes an "explicit halant",
106#     which will always appear as a halant instead of causing formation
107#     of a ligature or half-form consonant.
108#
109#     Halant followed by nukta (0xE8 + 0xE9) constitutes a "soft
110#     halant", which prevents formation of a ligature and instead
111#     retains the half-form of the first consonant.
112#
113#  c) Invisible consonant
114#
115#     The byte 0xD9 (called INV in ISCII-91) is an invisible consonant:
116#     It behaves like a consonant but has no visible appearance. It is
117#     intended to be used (often in combination with halant) to display
118#     dependent forms in isolation, such as the RA forms or consonant
119#     half-forms.
120#
121#  d) Extensions for Vedic, etc.
122#
123#     The byte 0xF0 (called EXT in ISCII-91) followed by any byte in
124#     the range 0xA1-0xEE constitutes a two-byte code point which can
125#     be used to represent additional characters for Vedic (or other
126#     extensions); 0xF0 followed by any other byte value constitutes
127#     malformed text. Mac OS Gujarati supports this mechanism, but
128#     does not currently map any of these two-byte code points to
129#     anything.
130#
131# 2. Mac OS Gujarati additions
132#
133#   Mac OS Gujarati adds characters using the code points
134#   0x80-0x8A and 0x90.
135#
136# 3. Unused code points
137#
138#   The following code points are currently unused, and are not shown
139#   here: 0x8B-0x8F, 0x91-0xA0, 0xAB, 0xAF, 0xC7, 0xCE, 0xD0, 0xD3,
140#   0xE0, 0xE4, 0xEB-0xEF, 0xFB-0xFF. In addition, 0xF0 is not shown
141#   here, but it has a special function as described above.
142#
143# Unicode mapping issues and notes:
144# ---------------------------------
145#
146# 1. Mapping the byte pairs
147#
148#   If one of the following byte values is encountered when mapping
149#   Mac OS Gujarati text - xA1, xAA, xDF, or 0xE8 - then the next
150#   byte (if there is one) should be examined. If the next byte is
151#   0xE9 - or also 0xE8, if the first byte was 0xE8 - then the byte
152#   pair should be mapped using the first section of the mapping
153#   table below. Otherwise, each byte should be mapped using the
154#   second section of the mapping table below.
155#
156#   - The Unicode Standard, Version 2.0, specifies how explicit
157#     halant and soft halant should be represented in Unicode;
158#     these mappings are used below.
159#
160#   If the byte value 0xF0 is encountered when mapping Mac OS
161#   Gujarati text, then the next byte should be examined. If there
162#   is no next byte (e.g. 0xF0 at end of buffer), the mapping
163#   process should indicate incomplete character. If there is a next
164#   byte but it is not in the range 0xA1-0xEE, the mapping process
165#   should indicate malformed text. Otherwise, the mapping process
166#   should treat the byte pair as a valid two-byte code point with no
167#   mapping (e.g. map it to QUESTION MARK, REPLACEMENT CHARACTER,
168#   etc.).
169#
170# 2. Mapping the invisible consonant
171#
172#   It has been suggested that INV in ISCII-91 should map to ZERO
173#   WIDTH NON-JOINER in Unicode. However, this causes problems with
174#   roundtrip fidelity: The ISCII-91 sequences 0xE8+0xE8 and 0xE8+0xD9
175#   would map to the same sequence of Unicode characters. We have
176#   instead mapped INV to LEFT-TO-RIGHT MARK, which avoids these
177#   problems.
178#
179# Details of mapping changes in each version:
180# -------------------------------------------
181#
182##################
183BEGIN_MAP
1840x0000 - 0x007F = 0x00 -
1850x00A9 = 0x88
1860x00AE = 0x89
1870x00D7 = 0x80
1880x0964 = 0xEA
1890x0965 = 0x90
1900x0A81 = 0xA1
1910x0A82 = 0xA2
1920x0A83 = 0xA3
1930x0A85 = 0xA4
1940x0A86 = 0xA5
1950x0A87 = 0xA6
1960x0A88 = 0xA7
1970x0A89 = 0xA8
1980x0A8A = 0xA9
1990x0A8B = 0xAA
2000x0A8D = 0xAE
2010x0A8F = 0xAC
2020x0A90 = 0xAD
2030x0A91 = 0xB2
2040x0A93 = 0xB0
2050x0A94 = 0xB1
2060x0A95 = 0xB3
2070x0A96 = 0xB4
2080x0A97 = 0xB5
2090x0A98 = 0xB6
2100x0A99 = 0xB7
2110x0A9A = 0xB8
2120x0A9B = 0xB9
2130x0A9C = 0xBA
2140x0A9D = 0xBB
2150x0A9E = 0xBC
2160x0A9F = 0xBD
2170x0AA0 = 0xBE
2180x0AA1 = 0xBF
2190x0AA2 = 0xC0
2200x0AA3 = 0xC1
2210x0AA4 = 0xC2
2220x0AA5 = 0xC3
2230x0AA6 = 0xC4
2240x0AA7 = 0xC5
2250x0AA8 = 0xC6
2260x0AAA = 0xC8
2270x0AAB = 0xC9
2280x0AAC = 0xCA
2290x0AAD = 0xCB
2300x0AAE = 0xCC
2310x0AAF = 0xCD
2320x0AB0 = 0xCF
2330x0AB2 = 0xD1
2340x0AB3 = 0xD2
2350x0AB5 = 0xD4
2360x0AB6 = 0xD5
2370x0AB7 = 0xD6
2380x0AB8 = 0xD7
2390x0AB9 = 0xD8
2400x0ABC = 0xE9
2410x0ABE = 0xDA
2420x0ABF = 0xDB
2430x0AC0 = 0xDC
2440x0AC1 = 0xDD
2450x0AC2 = 0xDE
2460x0AC3 = 0xDF
247#0x0AC4 = 0xDF+0xE9
2480x0AC5 = 0xE3
2490x0AC7 = 0xE1
2500x0AC8 = 0xE2
2510x0AC9 = 0xE7
2520x0ACB = 0xE5
2530x0ACC = 0xE6
2540x0ACD = 0xE8
255#0x0ACD+0x200C = 0xE8+0xE8
256#0x0ACD+0x200D = 0xE8+0xE9
257#0x0AD0 = 0xA1+0xE9
258#0x0AE0 = 0xAA+0xE9
2590x0AE6 = 0xF1
2600x0AE7 = 0xF2
2610x0AE8 = 0xF3
2620x0AE9 = 0xF4
2630x0AEA = 0xF5
2640x0AEB = 0xF6
2650x0AEC = 0xF7
2660x0AED = 0xF8
2670x0AEE = 0xF9
2680x0AEF = 0xFA
2690x200E = 0xD9
2700x2013 = 0x82
2710x2014 = 0x83
2720x2018 = 0x84
2730x2019 = 0x85
2740x2022 = 0x87
2750x2026 = 0x86
2760x2122 = 0x8A
2770x2212 = 0x81
278END_MAP
279