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
232
233
234
235
236
237
238
239
240
|
/** @file
* Routines for handling character sets
*
* Wireshark - Network traffic analyzer
* By Gerald Combs <gerald@wireshark.org>
* Copyright 1998 Gerald Combs
*
* SPDX-License-Identifier: GPL-2.0-or-later
*/
#ifndef __CHARSETS_H__
#define __CHARSETS_H__
#include "ws_symbol_export.h"
#ifdef __cplusplus
extern "C" {
#endif /* __cplusplus */
/*
* Translation tables that map the upper 128 code points in single-byte
* "extended ASCII" character encodings to Unicode code points in the
* Basic Multilingual Plane.
*/
/* Table for windows-1250 */
extern const gunichar2 charset_table_cp1250[0x80];
/* Table for windows-1251 */
extern const gunichar2 charset_table_cp1251[0x80];
/* Table for windows-1252 */
extern const gunichar2 charset_table_cp1252[0x80];
/* Tables for ISO-8859-X */
extern const gunichar2 charset_table_iso_8859_2[0x80];
extern const gunichar2 charset_table_iso_8859_3[0x80];
extern const gunichar2 charset_table_iso_8859_4[0x80];
extern const gunichar2 charset_table_iso_8859_5[0x80];
extern const gunichar2 charset_table_iso_8859_6[0x80];
extern const gunichar2 charset_table_iso_8859_7[0x80];
extern const gunichar2 charset_table_iso_8859_8[0x80];
extern const gunichar2 charset_table_iso_8859_9[0x80];
extern const gunichar2 charset_table_iso_8859_10[0x80];
extern const gunichar2 charset_table_iso_8859_11[0x80];
extern const gunichar2 charset_table_iso_8859_13[0x80];
extern const gunichar2 charset_table_iso_8859_14[0x80];
extern const gunichar2 charset_table_iso_8859_15[0x80];
extern const gunichar2 charset_table_iso_8859_16[0x80];
/* Tables for Mac character sets */
extern const gunichar2 charset_table_mac_roman[0x80];
/* Tables for DOS code pages */
extern const gunichar2 charset_table_cp437[0x80];
extern const gunichar2 charset_table_cp855[0x80];
extern const gunichar2 charset_table_cp866[0x80];
/*
* Translation tables that map the lower 128 code points in single-byte
* ISO 646-based character encodings to Unicode code points in the
* Basic Multilingual Plane.
*/
extern const gunichar2 charset_table_iso_646_basic[0x80];
/* Tables for EBCDIC code pages */
extern const gunichar2 charset_table_ebcdic[256];
extern const gunichar2 charset_table_ebcdic_cp037[256];
extern const gunichar2 charset_table_ebcdic_cp500[256];
/*
* Given a wmem scope, a pointer, and a length, treat the string of bytes
* referred to by the pointer and length as an ASCII string, with all bytes
* with the high-order bit set being invalid, and return a pointer to a
* UTF-8 string, allocated using the wmem scope.
*
* Octets with the highest bit set will be converted to the Unicode
* REPLACEMENT CHARACTER.
*/
WS_DLL_PUBLIC guint8 *
get_ascii_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
/*
* Given a wmem scope, a pointer, and a length, treat the string of bytes
* referred to by the pointer and length as a UTF-8 string, and return a
* pointer to a UTF-8 string, allocated using the wmem scope, with all
* ill-formed sequences replaced with the Unicode REPLACEMENT CHARACTER
* according to the recommended "best practices" given in the Unicode
* Standard and specified by W3C/WHATWG.
*/
WS_DLL_PUBLIC guint8 *
get_utf_8_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
/*
* Given a wmem scope, a pointer, a length, and a translation table,
* treat the string of bytes referred to by the pointer and length as a
* string encoded using one octet per character, with octets with the
* high-order bit clear being mapped by the translation table to 2-byte
* Unicode Basic Multilingual Plane characters (including REPLACEMENT
* CHARACTER) and octets with the high-order bit set being mapped to
* REPLACEMENT CHARACTER, and return a pointer to a UTF-8 string,
* allocated using the wmem scope.
*/
WS_DLL_PUBLIC guint8 *
get_iso_646_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, const gunichar2 table[0x80]);
/*
* Given a wmem scope, a pointer, and a length, treat the string of bytes
* referred to by the pointer and length as an ISO 8859/1 string, and
* return a pointer to a UTF-8 string, allocated using the wmem scope.
*/
WS_DLL_PUBLIC guint8 *
get_8859_1_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
/*
* Given a wmem scope, a pointer, a length, and a translation table with
* 128 entries, treat the string of bytes referred to by the pointer and
* length as a string encoded using one octet per character, with octets
* with the high-order bit clear being ASCII and octets with the high-order
* bit set being mapped by the translation table to 2-byte Unicode Basic
* Multilingual Plane characters (including REPLACEMENT CHARACTER), and
* return a pointer to a UTF-8 string, allocated using the wmem scope.
*/
WS_DLL_PUBLIC guint8 *
get_unichar2_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, const gunichar2 table[0x80]);
/*
* Given a wmem scope, a pointer, and a length, treat the string of bytes
* referred to by the pointer and length as a UCS-2 encoded string
* containing characters from the Basic Multilingual Plane (plane 0) of
* Unicode, and return a pointer to a UTF-8 string, allocated with the
* wmem scope.
*
* Encoding parameter should be ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN,
* possibly ORed with ENC_BOM.
*
* Specify length in bytes.
*/
WS_DLL_PUBLIC guint8 *
get_ucs_2_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, guint encoding);
/*
* Given a wmem scope, a pointer, and a length, treat the string of bytes
* referred to by the pointer and length as a UTF-16 encoded string, and
* return a pointer to a UTF-8 string, allocated with the wmem scope.
*
* See RFC 2781 section 2.2.
*
* Encoding parameter should be ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN,
* possibly ORed with ENC_BOM.
*
* Specify length in bytes.
*/
WS_DLL_PUBLIC guint8 *
get_utf_16_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, guint encoding);
/*
* Given a wmem scope, a pointer, and a length, treat the string of bytes
* referred to by the pointer and length as a UCS-4 encoded string, and
* return a pointer to a UTF-8 string, allocated with the wmem scope.
*
* Encoding parameter should be ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN,
* possibly ORed with ENC_BOM.
*
* Specify length in bytes.
*/
WS_DLL_PUBLIC guint8 *
get_ucs_4_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, guint encoding);
WS_DLL_PUBLIC guint8 *
get_ts_23_038_7bits_string_packed(wmem_allocator_t *scope, const guint8 *ptr,
const gint bit_offset, gint no_of_chars);
WS_DLL_PUBLIC guint8 *
get_ts_23_038_7bits_string_unpacked(wmem_allocator_t *scope, const guint8 *ptr,
gint length);
WS_DLL_PUBLIC guint8 *
get_etsi_ts_102_221_annex_a_string(wmem_allocator_t *scope, const guint8 *ptr,
gint length);
WS_DLL_PUBLIC guint8 *
get_ascii_7bits_string(wmem_allocator_t *scope, const guint8 *ptr,
const gint bit_offset, gint no_of_chars);
/*
* Given a wmem scope, a pointer, a length, and a translation table with
* 256 entries, treat the string of bytes referred to by the pointer and
* length as a string encoded using one octet per character, with octets
* being mapped by the translation table to 2-byte Unicode Basic Multilingual
* Plane characters (including REPLACEMENT CHARACTER), and return a
* pointer to a UTF-8 string, allocated using the wmem scope.
*/
WS_DLL_PUBLIC guint8 *
get_nonascii_unichar2_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, const gunichar2 table[256]);
/*
* Given a wmem scope, a pointer, and a length, treat the bytes referred to
* by the pointer and length as a GB18030 encoded string, and return a pointer
* to a UTF-8 string, allocated using the wmem scope, converted having
* substituted REPLACEMENT CHARACTER according to the Unicode Standard
* 5.22 U+FFFD Substitution for Conversion.
* ( https://www.unicode.org/versions/Unicode13.0.0/ch05.pdf )
*
* As expected, this will also decode GBK and GB2312 strings.
*/
WS_DLL_PUBLIC guint8 *
get_gb18030_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
/*
* Given a wmem scope, a pointer, and a length, treat the bytes referred to
* by the pointer and length as a EUC-KR encoded string, and return a pointer
* to a UTF-8 string, allocated using the wmem scope, converted having
* substituted REPLACEMENT CHARACTER according to the Unicode Standard
* 5.22 U+FFFD Substitution for Conversion.
* ( https://www.unicode.org/versions/Unicode13.0.0/ch05.pdf )
*/
WS_DLL_PUBLIC guint8 *
get_euc_kr_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
WS_DLL_PUBLIC guint8 *
get_t61_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
WS_DLL_PUBLIC guint8 *
get_dect_standard_8bits_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
#ifdef __cplusplus
}
#endif /* __cplusplus */
#endif /* __CHARSETS_H__ */
/*
* Editor modelines - https://www.wireshark.org/tools/modelines.html
*
* Local variables:
* c-basic-offset: 4
* tab-width: 8
* indent-tabs-mode: nil
* End:
*
* vi: set shiftwidth=4 tabstop=8 expandtab:
* :indentSize=4:tabSize=8:noTabs=true:
*/
|
