xref: /freebsd/share/i18n/csmapper/APPLE/DEVANAGA%UCS.src (revision d0b2dbfa0ecf2bbc9709efc5e20baf8e4b44bbbf)
1
2TYPE		ROWCOL
3NAME		DEVANAGA/UCS
4SRC_ZONE	0x00-0xFA
5OOB_MODE	ILSEQ
6DST_ILSEQ	0xFFFE
7DST_UNIT_BITS	16
8#=======================================================================
9#   File name:  DEVANAGA.TXT
10#
11#   Contents:   Map (external version) from Mac OS Devanagari
12#               encoding to Unicode 2.1 and later.
13#
14#   Copyright:  (c) 1995-2002, 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; add section on
22#                           roundtrip considerations. Matches internal
23#                           xml <c1.1> and Text Encoding Converter 2.0.
24#      b3,c1 2002-Dec-19    Update URLs. Matches internal utom<b1>.
25#       b02  1999-Sep-22    Update contact e-mail address. Matches
26#                           internal utom<b1>, ufrm<b1>, and Text
27#                           Encoding Converter version 1.5.
28#       n04  1998-Feb-05    First version; matches internal utom<n9>,
29#                           ufrm<n15>.
30#
31# Standard header:
32# ----------------
33#
34#   Apple, the Apple logo, and Macintosh are trademarks of Apple
35#   Computer, Inc., registered in the United States and other countries.
36#   Unicode is a trademark of Unicode Inc. For the sake of brevity,
37#   throughout this document, "Macintosh" can be used to refer to
38#   Macintosh computers and "Unicode" can be used to refer to the
39#   Unicode standard.
40#
41#   Apple Computer, Inc. ("Apple") makes no warranty or representation,
42#   either express or implied, with respect to this document and the
43#   included data, its quality, accuracy, or fitness for a particular
44#   purpose. In no event will Apple be liable for direct, indirect,
45#   special, incidental, or consequential damages resulting from any
46#   defect or inaccuracy in this document or the included data.
47#
48#   These mapping tables and character lists are subject to change.
49#   The latest tables should be available from the following:
50#
51#   <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
52#
53#   For general information about Mac OS encodings and these mapping
54#   tables, see the file "README.TXT".
55#
56# Format:
57# -------
58#
59#   Three tab-separated columns;
60#   '#' begins a comment which continues to the end of the line.
61#     Column #1 is the Mac OS Devanagari code or code sequence
62#       (in hex as 0xNN or 0xNN+0xNN)
63#     Column #2 is the corresponding Unicode or Unicode sequence
64#       (in hex as 0xNNNN or 0xNNNN+0xNNNN).
65#     Column #3 is a comment containing the Unicode name or sequence
66#       of names. In some cases an additional comment follows the
67#       Unicode name(s).
68#
69#   The entries are in two sections. The first section is for pairs of
70#   Mac OS Devanagari code points that must be mapped in a special way.
71#   The second section maps individual code points.
72#
73#   Within each section, the entries are in Mac OS Devanagari code order.
74#
75#   Control character mappings are not shown in this table, following
76#   the conventions of the standard UTC mapping tables. However, the
77#   Mac OS Devanagari character set uses the standard control characters
78#   at 0x00-0x1F and 0x7F.
79#
80# Notes on Mac OS Devanagari:
81# ---------------------------
82#
83#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
84#   environments, it is only supported via transcoding to and from
85#   Unicode.
86#
87#   Mac OS Devanagari is based on IS 13194:1991 (ISCII-91), with the
88#   addition of several punctuation and symbol characters. However,
89#   Mac OS Devanagari does not support the ATR (attribute) mechanism of
90#   ISCII-91.
91#
92# 1. ISCII-91 features in Mac OS Devanagari include:
93#
94#  a) Overloading of nukta
95#
96#     In addition to using the nukta (0xE9) like a combining dot below,
97#     nukta is overloaded to function as a general character modifier.
98#     In this role, certain code points followed by 0xE9 are treated as
99#     a two-byte code point representing a character which may be
100#     rather different than the characters represented by either of
101#     the code points alone. For example, the character DEVANAGARI OM
102#     (U+0950) is represented in ISCII-91 as candrabindu + nukta.
103#
104#  b) Explicit halant and soft halant
105#
106#     A double halant (0xE8 + 0xE8) constitutes an "explicit halant",
107#     which will always appear as a halant instead of causing formation
108#     of a ligature or half-form consonant.
109#
110#     Halant followed by nukta (0xE8 + 0xE9) constitutes a "soft
111#     halant", which prevents formation of a ligature and instead
112#     retains the half-form of the first consonant.
113#
114#  c) Invisible consonant
115#
116#     The byte 0xD9 (called INV in ISCII-91) is an invisible consonant:
117#     It behaves like a consonant but has no visible appearance. It is
118#     intended to be used (often in combination with halant) to display
119#     dependent forms in isolation, such as the RA forms or consonant
120#     half-forms.
121#
122#  d) Extensions for Vedic, etc.
123#
124#     The byte 0xF0 (called EXT in ISCII-91) followed by any byte in
125#     the range 0xA1-0xEE constitutes a two-byte code point which can
126#     be used to represent additional characters for Vedic (or other
127#     extensions); 0xF0 followed by any other byte value constitutes
128#     malformed text. Mac OS Devanagari supports this mechanism, but
129#     does not currently map any of these two-byte code points to
130#     anything.
131#
132# 2. Mac OS Devanagari additions
133#
134#   Mac OS Devanagari adds characters using the code points
135#   0x80-0x8A and 0x90-0x91 (the latter are some Devanagari additions
136#   from Unicode).
137#
138# 3. Unused code points
139#
140#   The following code points are currently unused, and are not shown
141#   here: 0x8B-0x8F, 0x92-0xA0, 0xEB-0xEF, 0xFB-0xFF. In addition,
142#   0xF0 is not shown here, but it has a special function as described
143#   above.
144#
145# Unicode mapping issues and notes:
146# ---------------------------------
147#
148# 1. Mapping the byte pairs
149#
150#   If one of the following byte values is encountered when mapping
151#   Mac OS Devanagari text - 0xA1, 0xA6, 0xA7, 0xAA, 0xDB, 0xDC, 0xDF,
152#   0xE8, or 0xEA - then the next byte (if there is one) should be
153#   examined. If the next byte is 0xE9 - or also 0xE8, if the first
154#   byte was 0xE8 - then the byte pair should be mapped using the
155#   first section of the mapping table below. Otherwise, each byte
156#   should be mapped using the second section of the mapping table
157#   below.
158#
159#   - The Unicode Standard, Version 2.0, specifies how explicit
160#     halant and soft halant should be represented in Unicode;
161#     these mappings are used below.
162#
163#   If the byte value 0xF0 is encountered when mapping Mac OS
164#   Devanagari text, then the next byte should be examined. If there
165#   is no next byte (e.g. 0xF0 at end of buffer), the mapping
166#   process should indicate incomplete character. If there is a next
167#   byte but it is not in the range 0xA1-0xEE, the mapping process
168#   should indicate malformed text. Otherwise, the mapping process
169#   should treat the byte pair as a valid two-byte code point with no
170#   mapping (e.g. map it to QUESTION MARK, REPLACEMENT CHARACTER,
171#   etc.).
172#
173# 2. Mapping the invisible consonant
174#
175#   It has been suggested that INV in ISCII-91 should map to ZERO
176#   WIDTH NON-JOINER in Unicode. However, this causes problems with
177#   roundtrip fidelity: The ISCII-91 sequences 0xE8+0xE8 and 0xE8+0xD9
178#   would map to the same sequence of Unicode characters. We have
179#   instead mapped INV to LEFT-TO-RIGHT MARK, which avoids these
180#   problems.
181#
182# 3. Additional loose mappings from Unicode
183#
184#   These are not preserved in roundtrip mappings.
185#
186#   U+0958  0xB3+0xE9  # DEVANAGARI LETTER QA
187#   U+0959  0xB4+0xE9  # DEVANAGARI LETTER KHHA
188#   U+095A  0xB5+0xE9  # DEVANAGARI LETTER GHHA
189#   U+095B  0xBA+0xE9  # DEVANAGARI LETTER ZA
190#   U+095C  0xBF+0xE9  # DEVANAGARI LETTER DDDHA
191#   U+095D  0xC0+0xE9  # DEVANAGARI LETTER RHA
192#   U+095E  0xC9+0xE9  # DEVANAGARI LETTER FA
193#
194# 4. Roundtrip considerations when mapping to decomposed Unicode
195#
196#   Both ISCII-91 (hence Mac OS Devanagari) and Unicode provide multiple
197#   ways of representing certain Devanagari consonants. For example,
198#   DEVANAGARI LETTER NNNA can be represented in Unicode as the single
199#   character 0x0929 or as the sequence 0x0928 0x093C; similarly, this
200#   consonant can be represented in Mac OS Devanagari as 0xC7 or as the
201#   sequence 0xC6 0xE9. This leads to some roundtrip problems. First
202#   note that we have the following mappings without such problems:
203#
204#   ISCII/  standard                  decomposition of  reverse mapping
205#   Mac OS  Unicode mapping           standard mapping  of decomposition
206#   ------  -----------------------   ----------------  ----------------
207#   0xC6    0x0928  ... LETTER NA     0x0928 (same)     0xC6
208#   0xCD    0x092F  ... LETTER YA     0x092F (same)     0xCD
209#   0xCF    0x0930  ... LETTER RA     0x0930 (same)     0xCF
210#   0xD2    0x0933  ... LETTER LLA    0x0933 (same)     0xD2
211#   0xE9    0x093C  ... SIGN NUKTA    0x093C (same)     0xE9
212#
213#   However, those mappings above cause roundtrip problems for the
214#   the following mappings if they are decomposed:
215#
216#   ISCII/  standard                  decomposition of  reverse mapping
217#   Mac OS  Unicode mapping           standard mapping  of decomposition
218#   ------  -----------------------   ----------------  ----------------
219#   0xC7    0x0929  ... LETTER NNNA   0x0928 0x093C     0xC6 0xE9
220#   0xCE    0x095F  ... LETTER YYA    0x092F 0x093C     0xCD 0xE9
221#   0xD0    0x0931  ... LETTER RRA    0x0930 0x093C     0xCF 0xE9
222#   0xD3    0x0934  ... LETTER LLLA   0x0933 0x093C     0xD2 0xE9
223#
224#   One solution is to use a grouping transcoding hint with the four
225#   decompositions above to mark the decomposed sequence for special
226#   treatment in transcoding. This yields the following mappings to
227#   decomposed Unicode:
228#
229#   ISCII/                     decomposed
230#   Mac OS                     Unicode mapping
231#   ------                     ----------------
232#   0xC7                       0xF860 0x0928 0x093C
233#   0xCE                       0xF860 0x092F 0x093C
234#   0xD0                       0xF860 0x0930 0x093C
235#   0xD3                       0xF860 0x0933 0x093C
236#
237# Details of mapping changes in each version:
238# -------------------------------------------
239#
240##################
241# Section 1: Map the following byte pairs as indicated:
242# (ZWNJ means ZERO WIDTH NON-JOINER, ZWJ means ZERO WIDTH JOINER)
243# (Also see note about 0xF0 in comments above)
244# Section 2: Map the remaining bytes as follows:
245#
246#
247#
248#
249BEGIN_MAP
2500x00 - 0x7F = 0x0000 -
2510x80 = 0x00D7
2520x81 = 0x2212
2530x82 = 0x2013
2540x83 = 0x2014
2550x84 = 0x2018
2560x85 = 0x2019
2570x86 = 0x2026
2580x87 = 0x2022
2590x88 = 0x00A9
2600x89 = 0x00AE
2610x8A = 0x2122
2620x90 = 0x0965
2630x91 = 0x0970
2640xA1 = 0x0901
265#0xA1+0xE9 = 0x0950
2660xA2 = 0x0902
2670xA3 = 0x0903
2680xA4 = 0x0905
2690xA5 = 0x0906
2700xA6 = 0x0907
271#0xA6+0xE9 = 0x090C
2720xA7 = 0x0908
273#0xA7+0xE9 = 0x0961
2740xA8 = 0x0909
2750xA9 = 0x090A
2760xAA = 0x090B
277#0xAA+0xE9 = 0x0960
2780xAB = 0x090E
2790xAC = 0x090F
2800xAD = 0x0910
2810xAE = 0x090D
2820xAF = 0x0912
2830xB0 = 0x0913
2840xB1 = 0x0914
2850xB2 = 0x0911
2860xB3 = 0x0915
2870xB4 = 0x0916
2880xB5 = 0x0917
2890xB6 = 0x0918
2900xB7 = 0x0919
2910xB8 = 0x091A
2920xB9 = 0x091B
2930xBA = 0x091C
2940xBB = 0x091D
2950xBC = 0x091E
2960xBD = 0x091F
2970xBE = 0x0920
2980xBF = 0x0921
2990xC0 = 0x0922
3000xC1 = 0x0923
3010xC2 = 0x0924
3020xC3 = 0x0925
3030xC4 = 0x0926
3040xC5 = 0x0927
3050xC6 = 0x0928
3060xC7 = 0x0929
3070xC8 = 0x092A
3080xC9 = 0x092B
3090xCA = 0x092C
3100xCB = 0x092D
3110xCC = 0x092E
3120xCD = 0x092F
3130xCE = 0x095F
3140xCF = 0x0930
3150xD0 = 0x0931
3160xD1 = 0x0932
3170xD2 = 0x0933
3180xD3 = 0x0934
3190xD4 = 0x0935
3200xD5 = 0x0936
3210xD6 = 0x0937
3220xD7 = 0x0938
3230xD8 = 0x0939
3240xD9 = 0x200E
3250xDA = 0x093E
3260xDB = 0x093F
327#0xDB+0xE9 = 0x0962
3280xDC = 0x0940
329#0xDC+0xE9 = 0x0963
3300xDD = 0x0941
3310xDE = 0x0942
3320xDF = 0x0943
333#0xDF+0xE9 = 0x0944
3340xE0 = 0x0946
3350xE1 = 0x0947
3360xE2 = 0x0948
3370xE3 = 0x0945
3380xE4 = 0x094A
3390xE5 = 0x094B
3400xE6 = 0x094C
3410xE7 = 0x0949
3420xE8 = 0x094D
343#0xE8+0xE8 = 0x094D+0x200C
344#0xE8+0xE9 = 0x094D+0x200D
3450xE9 = 0x093C
3460xEA = 0x0964
347#0xEA+0xE9 = 0x093D
3480xF1 = 0x0966
3490xF2 = 0x0967
3500xF3 = 0x0968
3510xF4 = 0x0969
3520xF5 = 0x096A
3530xF6 = 0x096B
3540xF7 = 0x096C
3550xF8 = 0x096D
3560xF9 = 0x096E
3570xFA = 0x096F
358END_MAP
359