]> git.saurik.com Git - apple/icu.git/blob - icuSources/data/mappings/gsm-03.38-2000.ucm
ICU-531.48.tar.gz
[apple/icu.git] / icuSources / data / mappings / gsm-03.38-2000.ucm
1 # Copyright (c) 2000 Unicode, Inc. All Rights reserved.
2 #
3 # Name: GSM 03.38 to Unicode
4 # Unicode version: 3.0
5 # Table version: 1.1
6 # Date: 2000 May 30
7 # Authors: Ken Whistler
8 # Kent Karlsson
9 # Markus Kuhn
10 #
11 # Source: http://www.unicode.org/Public/MAPPINGS/ETSI/GSM0338.TXT
12 # See there for the license and for a description of the charset.
13 # Formatted into ICU .ucm format by Markus Scherer on 2006-nov-02.
14 # Commented-out mappings are turned into fallbacks (|1), all others are turned
15 # into round-trips (|0).
16 # Multi-byte mappings are preserved as multi-single-byte character mappings,
17 # using ICU's m:n conversion capability.
18 #
19 # The substitution character is not documented in the Unicode file.
20 # \x3F is chosen here because \x1A is a graphic character.
21 #
22 # Other deviations from the Unicode file:
23 # a)
24 # The GSM standard specifies that one or two ESC bytes (\x1B), if not followed
25 # by a recognized final byte, be mapped to spaces (that is, reverse fallbacks
26 # to U+0020).
27 # The Unicode file round-trips a single \x1B to U+00A0 (NBSP) and has no mapping
28 # for \x1B\x1B.
29 # (Reverse fallbacks to U+00A0 would result in Unicode text that cannot be
30 # converted back to GSM 03.38. A roundtrip for U+00A0 adds a character that is
31 # not mappable in the standard.)
32 #
33 # See the ietf-charsets list email "Re: GSM 03.38 substitution character?"
34 # at http://mail.apps.ietf.org/ietf/charsets/msg01696.html
35 #
36 # b)
37 # The GSM standard maps U+00C7 capital C-cedilla to \x09 but the Unicode file
38 # contains and documents a "fix" to map U+00E7 small c-cedilla instead, based on
39 # an interpretation of the intent of the standard. Prevailing implementations
40 # in mobile phones follow the standard.
41 #
42 # This file follows the GSM standard.
43 #
44 # See the GSM standard at
45 # http://www.3gpp.org/ftp/Specs/archive/03_series/03.38/0338-720.zip
46 #
47 # For problems with the table format please submit a bug
48 # at http://www.icu-project.org/ .
49 # For issues with the mappings please contact Unicode
50 # at http://www.unicode.org/reporting.html
51
52 <code_set_name> "gsm-03.38-2000"
53 <char_name_mask> "AXXXX"
54 <mb_cur_max> 1
55 <mb_cur_min> 1
56 <uconv_class> "SBCS"
57 <icu:state> 0-7f
58 <subchar> \x3F
59 <icu:charsetFamily> "ASCII"
60
61 CHARMAP
62 <U0000> \x00 |1
63 <U000A> \x0A |0
64 <U000C> \x1B\x0A |0
65 <U000D> \x0D |0
66 <U0020> \x20 |0
67 <U0020> \x1B |3
68 <U0020> \x1B\x1B |3
69 <U0021> \x21 |0
70 <U0022> \x22 |0
71 <U0023> \x23 |0
72 <U0024> \x02 |0
73 <U0025> \x25 |0
74 <U0026> \x26 |0
75 <U0027> \x27 |0
76 <U0028> \x28 |0
77 <U0029> \x29 |0
78 <U002A> \x2A |0
79 <U002B> \x2B |0
80 <U002C> \x2C |0
81 <U002D> \x2D |0
82 <U002E> \x2E |0
83 <U002F> \x2F |0
84 <U0030> \x30 |0
85 <U0031> \x31 |0
86 <U0032> \x32 |0
87 <U0033> \x33 |0
88 <U0034> \x34 |0
89 <U0035> \x35 |0
90 <U0036> \x36 |0
91 <U0037> \x37 |0
92 <U0038> \x38 |0
93 <U0039> \x39 |0
94 <U003A> \x3A |0
95 <U003B> \x3B |0
96 <U003C> \x3C |0
97 <U003D> \x3D |0
98 <U003E> \x3E |0
99 <U003F> \x3F |0
100 <U0040> \x00 |0
101 <U0041> \x41 |0
102 <U0042> \x42 |0
103 <U0043> \x43 |0
104 <U0044> \x44 |0
105 <U0045> \x45 |0
106 <U0046> \x46 |0
107 <U0047> \x47 |0
108 <U0048> \x48 |0
109 <U0049> \x49 |0
110 <U004A> \x4A |0
111 <U004B> \x4B |0
112 <U004C> \x4C |0
113 <U004D> \x4D |0
114 <U004E> \x4E |0
115 <U004F> \x4F |0
116 <U0050> \x50 |0
117 <U0051> \x51 |0
118 <U0052> \x52 |0
119 <U0053> \x53 |0
120 <U0054> \x54 |0
121 <U0055> \x55 |0
122 <U0056> \x56 |0
123 <U0057> \x57 |0
124 <U0058> \x58 |0
125 <U0059> \x59 |0
126 <U005A> \x5A |0
127 <U005B> \x1B\x3C |0
128 <U005C> \x1B\x2F |0
129 <U005D> \x1B\x3E |0
130 <U005E> \x1B\x14 |0
131 <U005F> \x11 |0
132 <U0061> \x61 |0
133 <U0062> \x62 |0
134 <U0063> \x63 |0
135 <U0064> \x64 |0
136 <U0065> \x65 |0
137 <U0066> \x66 |0
138 <U0067> \x67 |0
139 <U0068> \x68 |0
140 <U0069> \x69 |0
141 <U006A> \x6A |0
142 <U006B> \x6B |0
143 <U006C> \x6C |0
144 <U006D> \x6D |0
145 <U006E> \x6E |0
146 <U006F> \x6F |0
147 <U0070> \x70 |0
148 <U0071> \x71 |0
149 <U0072> \x72 |0
150 <U0073> \x73 |0
151 <U0074> \x74 |0
152 <U0075> \x75 |0
153 <U0076> \x76 |0
154 <U0077> \x77 |0
155 <U0078> \x78 |0
156 <U0079> \x79 |0
157 <U007A> \x7A |0
158 <U007B> \x1B\x28 |0
159 <U007C> \x1B\x40 |0
160 <U007D> \x1B\x29 |0
161 <U007E> \x1B\x3D |0
162 <U00A1> \x40 |0
163 <U00A3> \x01 |0
164 <U00A4> \x24 |0
165 <U00A5> \x03 |0
166 <U00A7> \x5F |0
167 <U00BF> \x60 |0
168 <U00C4> \x5B |0
169 <U00C5> \x0E |0
170 <U00C6> \x1C |0
171 <U00C7> \x09 |0
172 <U00C9> \x1F |0
173 <U00D1> \x5D |0
174 <U00D6> \x5C |0
175 <U00D8> \x0B |0
176 <U00DC> \x5E |0
177 <U00DF> \x1E |0
178 <U00E0> \x7F |0
179 <U00E4> \x7B |0
180 <U00E5> \x0F |0
181 <U00E6> \x1D |0
182 <U00E8> \x04 |0
183 <U00E9> \x05 |0
184 <U00EC> \x07 |0
185 <U00F1> \x7D |0
186 <U00F2> \x08 |0
187 <U00F6> \x7C |0
188 <U00F8> \x0C |0
189 <U00F9> \x06 |0
190 <U00FC> \x7E |0
191 <U0391> \x41 |1
192 <U0392> \x42 |1
193 <U0393> \x13 |0
194 <U0394> \x10 |0
195 <U0395> \x45 |1
196 <U0396> \x5A |1
197 <U0397> \x48 |1
198 <U0398> \x19 |0
199 <U0399> \x49 |1
200 <U039A> \x4B |1
201 <U039B> \x14 |0
202 <U039C> \x4D |1
203 <U039D> \x4E |1
204 <U039E> \x1A |0
205 <U039F> \x4F |1
206 <U03A0> \x16 |0
207 <U03A1> \x50 |1
208 <U03A3> \x18 |0
209 <U03A4> \x54 |1
210 <U03A5> \x55 |1
211 <U03A6> \x12 |0
212 <U03A7> \x58 |1
213 <U03A8> \x17 |0
214 <U03A9> \x15 |0
215 <U20AC> \x1B\x65 |0
216 END CHARMAP