1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
|
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
* qmicli -- Command line interface to control QMI devices
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* Copyright (C) 2010-2017 Red Hat, Inc.
*/
#include "config.h"
#include <unistd.h>
#include <string.h>
#include <ctype.h>
#include <glib.h>
#include "qmicli-charsets.h"
/* GSM 03.38 encoding conversion stuff */
#define GSM_DEF_ALPHABET_SIZE 128
#define GSM_EXT_ALPHABET_SIZE 10
typedef struct GsmUtf8Mapping {
gchar chars[3];
guint8 len;
guint8 gsm; /* only used for extended GSM charset */
} GsmUtf8Mapping;
#define ONE(a) { {a, 0x00, 0x00}, 1, 0 }
#define TWO(a, b) { {a, b, 0x00}, 2, 0 }
/**
* gsm_def_utf8_alphabet:
*
* Mapping from GSM default alphabet to UTF-8.
*
* ETSI GSM 03.38, version 6.0.1, section 6.2.1; Default alphabet. Mapping to UCS-2.
* Mapping according to http://unicode.org/Public/MAPPINGS/ETSI/GSM0338.TXT
*/
static const GsmUtf8Mapping gsm_def_utf8_alphabet[GSM_DEF_ALPHABET_SIZE] = {
/* @ £ $ ¥ */
ONE(0x40), TWO(0xc2, 0xa3), ONE(0x24), TWO(0xc2, 0xa5),
/* è é ù ì */
TWO(0xc3, 0xa8), TWO(0xc3, 0xa9), TWO(0xc3, 0xb9), TWO(0xc3, 0xac),
/* ò Ç \n Ø */
TWO(0xc3, 0xb2), TWO(0xc3, 0x87), ONE(0x0a), TWO(0xc3, 0x98),
/* ø \r Å å */
TWO(0xc3, 0xb8), ONE(0x0d), TWO(0xc3, 0x85), TWO(0xc3, 0xa5),
/* Δ _ Φ Γ */
TWO(0xce, 0x94), ONE(0x5f), TWO(0xce, 0xa6), TWO(0xce, 0x93),
/* Λ Ω Π Ψ */
TWO(0xce, 0x9b), TWO(0xce, 0xa9), TWO(0xce, 0xa0), TWO(0xce, 0xa8),
/* Σ Θ Ξ Escape Code */
TWO(0xce, 0xa3), TWO(0xce, 0x98), TWO(0xce, 0x9e), ONE(0xa0),
/* Æ æ ß É */
TWO(0xc3, 0x86), TWO(0xc3, 0xa6), TWO(0xc3, 0x9f), TWO(0xc3, 0x89),
/* ' ' ! " # */
ONE(0x20), ONE(0x21), ONE(0x22), ONE(0x23),
/* ¤ % & ' */
TWO(0xc2, 0xa4), ONE(0x25), ONE(0x26), ONE(0x27),
/* ( ) * + */
ONE(0x28), ONE(0x29), ONE(0x2a), ONE(0x2b),
/* , - . / */
ONE(0x2c), ONE(0x2d), ONE(0x2e), ONE(0x2f),
/* 0 1 2 3 */
ONE(0x30), ONE(0x31), ONE(0x32), ONE(0x33),
/* 4 5 6 7 */
ONE(0x34), ONE(0x35), ONE(0x36), ONE(0x37),
/* 8 9 : ; */
ONE(0x38), ONE(0x39), ONE(0x3a), ONE(0x3b),
/* < = > ? */
ONE(0x3c), ONE(0x3d), ONE(0x3e), ONE(0x3f),
/* ¡ A B C */
TWO(0xc2, 0xa1), ONE(0x41), ONE(0x42), ONE(0x43),
/* D E F G */
ONE(0x44), ONE(0x45), ONE(0x46), ONE(0x47),
/* H I J K */
ONE(0x48), ONE(0x49), ONE(0x4a), ONE(0x4b),
/* L M N O */
ONE(0x4c), ONE(0x4d), ONE(0x4e), ONE(0x4f),
/* P Q R S */
ONE(0x50), ONE(0x51), ONE(0x52), ONE(0x53),
/* T U V W */
ONE(0x54), ONE(0x55), ONE(0x56), ONE(0x57),
/* X Y Z Ä */
ONE(0x58), ONE(0x59), ONE(0x5a), TWO(0xc3, 0x84),
/* Ö Ñ Ü § */
TWO(0xc3, 0x96), TWO(0xc3, 0x91), TWO(0xc3, 0x9c), TWO(0xc2, 0xa7),
/* ¿ a b c */
TWO(0xc2, 0xbf), ONE(0x61), ONE(0x62), ONE(0x63),
/* d e f g */
ONE(0x64), ONE(0x65), ONE(0x66), ONE(0x67),
/* h i j k */
ONE(0x68), ONE(0x69), ONE(0x6a), ONE(0x6b),
/* l m n o */
ONE(0x6c), ONE(0x6d), ONE(0x6e), ONE(0x6f),
/* p q r s */
ONE(0x70), ONE(0x71), ONE(0x72), ONE(0x73),
/* t u v w */
ONE(0x74), ONE(0x75), ONE(0x76), ONE(0x77),
/* x y z ä */
ONE(0x78), ONE(0x79), ONE(0x7a), TWO(0xc3, 0xa4),
/* ö ñ ü à */
TWO(0xc3, 0xb6), TWO(0xc3, 0xb1), TWO(0xc3, 0xbc), TWO(0xc3, 0xa0)
};
static guint8
gsm_def_char_to_utf8 (const guint8 gsm, guint8 out_utf8[2])
{
g_return_val_if_fail (gsm < GSM_DEF_ALPHABET_SIZE, 0);
memcpy (&out_utf8[0], &gsm_def_utf8_alphabet[gsm].chars[0], gsm_def_utf8_alphabet[gsm].len);
return gsm_def_utf8_alphabet[gsm].len;
}
#define EONE(a, g) { {a, 0x00, 0x00}, 1, g }
#define ETHR(a, b, c, g) { {a, b, c}, 3, g }
/**
* gsm_ext_utf8_alphabet:
*
* Mapping from GSM extended alphabet to UTF-8.
*
*/
static const GsmUtf8Mapping gsm_ext_utf8_alphabet[GSM_EXT_ALPHABET_SIZE] = {
/* form feed ^ { } */
EONE(0x0c, 0x0a), EONE(0x5e, 0x14), EONE(0x7b, 0x28), EONE(0x7d, 0x29),
/* \ [ ~ ] */
EONE(0x5c, 0x2f), EONE(0x5b, 0x3c), EONE(0x7e, 0x3d), EONE(0x5d, 0x3e),
/* | € */
EONE(0x7c, 0x40), ETHR(0xe2, 0x82, 0xac, 0x65)
};
#define GSM_ESCAPE_CHAR 0x1b
static guint8
gsm_ext_char_to_utf8 (const guint8 gsm, guint8 out_utf8[3])
{
int i;
for (i = 0; i < GSM_EXT_ALPHABET_SIZE; i++) {
if (gsm == gsm_ext_utf8_alphabet[i].gsm) {
memcpy (&out_utf8[0], &gsm_ext_utf8_alphabet[i].chars[0], gsm_ext_utf8_alphabet[i].len);
return gsm_ext_utf8_alphabet[i].len;
}
}
return 0;
}
guint8 *
qmicli_charset_gsm_unpack (const guint8 *gsm,
guint32 num_septets,
guint32 *out_unpacked_len)
{
GByteArray *unpacked;
int i;
unpacked = g_byte_array_sized_new (num_septets + 1);
for (i = 0; i < num_septets; i++) {
guint8 bits_here, bits_in_next, octet, offset, c;
guint32 start_bit;
start_bit = i * 7; /* Overall bit offset of char in buffer */
offset = start_bit % 8; /* Offset to start of char in this byte */
bits_here = offset ? (8 - offset) : 7;
bits_in_next = 7 - bits_here;
/* Grab bits in the current byte */
octet = gsm[start_bit / 8];
c = (octet >> offset) & (0xFF >> (8 - bits_here));
/* Grab any bits that spilled over to next byte */
if (bits_in_next) {
octet = gsm[(start_bit / 8) + 1];
c |= (octet & (0xFF >> (8 - bits_in_next))) << bits_here;
}
g_byte_array_append (unpacked, &c, 1);
}
*out_unpacked_len = unpacked->len;
return g_byte_array_free (unpacked, FALSE);
}
guint8 *
qmicli_charset_gsm_unpacked_to_utf8 (const guint8 *gsm, guint32 len)
{
int i;
GByteArray *utf8;
g_return_val_if_fail (gsm != NULL, NULL);
g_return_val_if_fail (len < 4096, NULL);
/* worst case initial length */
utf8 = g_byte_array_sized_new (len * 2 + 1);
for (i = 0; i < len; i++) {
guint8 uchars[4];
guint8 ulen;
if (gsm[i] == GSM_ESCAPE_CHAR) {
/* Extended alphabet, decode next char */
ulen = gsm_ext_char_to_utf8 (gsm[i+1], uchars);
if (ulen)
i += 1;
} else {
/* Default alphabet */
ulen = gsm_def_char_to_utf8 (gsm[i], uchars);
}
if (ulen)
g_byte_array_append (utf8, &uchars[0], ulen);
else
g_byte_array_append (utf8, (guint8 *) "?", 1);
}
g_byte_array_append (utf8, (guint8 *) "\0", 1); /* NULL terminator */
return g_byte_array_free (utf8, FALSE);
}
|
