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
|
/*
* Copyright (c) 2015 Balabit
* Copyright (c) 2015 Balázs Scheidler
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*
* As an additional exemption you are allowed to compile & link against the
* OpenSSL libraries as published by the OpenSSL project. See the file
* COPYING for details.
*
*/
#include "utf8utils.h"
#include "str-utils.h"
static inline gboolean
_is_character_unsafe(gunichar uchar, const gchar *unsafe_chars)
{
/* These G_LIKELY/UNLIKELY clauses assume that most characters are in the
* ASCII range and that unsafe characters are not specified. Since this function
* is called for each and every character generated by format-json/format-welf
* it does make a difference. */
if (G_UNLIKELY(uchar >= 256))
return FALSE;
if (G_LIKELY(!unsafe_chars))
return FALSE;
return _strchr_optimized_for_single_char_haystack(unsafe_chars, (gchar) uchar) != NULL;
}
/**
* This function escapes an unsanitized input (e.g. that can contain binary
* characters, and produces an escaped format that can be deescaped in need,
* which is guaranteed to be utf8 clean. The major difference between
* "binary" and "text" form is that the receiver is able to cope with \xXX
* sequences that can incorporate invalid utf8 sequences when decoded. With
* "text" format, we never embed anything that would become not valid utf8
* when decoded.
*
* Here are the rules that the routine follows:
* - well-known control characters are escaped (0x0a as \n and so on)
* - other control characters as per control_format
* - backslash is escaped as \\
* - any additional characters (only ASCII is supported) as \<char>
* - invalid utf8 sequences are converted as per invalid_format
* - utf8 characters are reproduced as is
*/
static gsize
_append_escaped_utf8_character(GString *escaped_output, const gchar **raw,
gssize raw_len, const gchar *unsafe_chars,
const gchar *control_format,
const gchar *invalid_format)
{
const gchar *char_ptr = *raw;
gunichar uchar = g_utf8_get_char_validated(char_ptr, raw_len);
if (G_UNLIKELY(uchar == (gunichar) -1 || uchar == (gunichar) -2))
{
g_string_append_printf(escaped_output, invalid_format, *(guint8 *) char_ptr);
(*raw)++;
return 1;
}
else if (G_UNLIKELY(uchar < 32 || uchar == '\\'))
{
switch (uchar)
{
case '\b':
g_string_append(escaped_output, "\\b");
break;
case '\f':
g_string_append(escaped_output, "\\f");
break;
case '\n':
g_string_append(escaped_output, "\\n");
break;
case '\r':
g_string_append(escaped_output, "\\r");
break;
case '\t':
g_string_append(escaped_output, "\\t");
break;
case '\\':
g_string_append(escaped_output, "\\\\");
break;
default:
g_string_append_printf(escaped_output, control_format, uchar);
break;
}
}
else if (G_UNLIKELY(_is_character_unsafe(uchar, unsafe_chars)))
g_string_append_printf(escaped_output, "\\%c", (gchar) uchar);
else
g_string_append_unichar_optimized(escaped_output, uchar);
*raw = g_utf8_next_char(char_ptr);
return *raw - char_ptr;
}
static void
_append_unsafe_utf8_as_escaped_with_specific_length(GString *escaped_output, const gchar *raw,
gsize raw_len,
const gchar *unsafe_chars,
const gchar *control_format,
const gchar *invalid_format)
{
const gchar *raw_end = raw + raw_len;
while (raw < raw_end)
_append_escaped_utf8_character(escaped_output, &raw, raw_end - raw, unsafe_chars,
control_format, invalid_format);
}
static void
_append_unsafe_utf8_as_escaped_nul_terminated(GString *escaped_output, const gchar *raw,
const gchar *unsafe_chars,
const gchar *control_format,
const gchar *invalid_format)
{
_append_unsafe_utf8_as_escaped_with_specific_length(escaped_output, raw, strlen(raw), unsafe_chars, control_format,
invalid_format);
}
/**
* @see _append_escaped_utf8_character()
*/
static void
_append_unsafe_utf8_as_escaped(GString *escaped_output, const gchar *raw,
gssize raw_len, const gchar *unsafe_chars,
const gchar *control_format,
const gchar *invalid_format)
{
if (raw_len < 0)
_append_unsafe_utf8_as_escaped_nul_terminated(escaped_output, raw, unsafe_chars, control_format, invalid_format);
else
_append_unsafe_utf8_as_escaped_with_specific_length(escaped_output, raw, raw_len, unsafe_chars, control_format,
invalid_format);
}
/**
* This function escapes an unsanitized input (e.g. that can contain binary
* characters, and produces an escaped format that can be deescaped in need,
* which is guaranteed to be utf8 clean. The major difference between
* "binary" and "text" form is that the receiver is able to cope with \xXX
* sequences that can incorporate invalid utf8 sequences when decoded. With
* "text" format, we never embed anything that would become not valid utf8
* when decoded.
*
* Here are the rules that the routine follows:
* - well-known control characters are escaped (0x0a as \n and so on)
* - other control characters as per control_format (\xXX)
* - backslash is escaped as \\
* - any additional characters (only ASCII is supported) as \<char>
* - invalid utf8 sequences are converted as per invalid_format (\xXX)
* - utf8 characters are reproduced as is
*
* This is basically meant to be used when sending data to
* 8 bit clean receivers, e.g. syslog-ng or WELF.
* @see _append_unsafe_utf8_as_escaped()
*/
void
append_unsafe_utf8_as_escaped_binary(GString *escaped_string, const gchar *str,
gssize str_len, const gchar *unsafe_chars)
{
_append_unsafe_utf8_as_escaped(escaped_string, str, str_len, unsafe_chars,
"\\x%02x", "\\x%02x");
}
gchar *
convert_unsafe_utf8_to_escaped_binary(const gchar *str, gssize str_len,
const gchar *unsafe_chars)
{
if (str_len < 0)
str_len = strlen(str);
GString *escaped_string = g_string_sized_new(str_len);
append_unsafe_utf8_as_escaped_binary(escaped_string, str, str_len, unsafe_chars);
return g_string_free(escaped_string, FALSE);
}
/**
* This function escapes an unsanitized input (e.g. that can contain binary
* characters, and produces an escaped format that can be deescaped in need,
* which is guaranteed to be utf8 clean. The major difference between
* "binary" and "text" form is that the receiver is able to cope with \xXX
* sequences that can incorporate invalid utf8 sequences when decoded. With
* "text" format, we never embed anything that would become not valid utf8
* when decoded.
*
* Here are the rules that the routine follows:
* - well-known control characters are escaped (0x0a as \n and so on)
* - other control characters as per control_format (\u00XX)
* - backslash is escaped as \\
* - any additional characters (only ASCII is supported) as \<char>
* - invalid utf8 sequences are converted as per invalid_format (\\xXX)
* - utf8 characters are reproduced as is
*
* This is basically meant to be used when sending data to
* utf8 only receivers, e.g. JSON.
* @see _append_unsafe_utf8_as_escaped()
*/
void
append_unsafe_utf8_as_escaped_text(GString *escaped_string, const gchar *str,
gssize str_len, const gchar *unsafe_chars)
{
_append_unsafe_utf8_as_escaped(escaped_string, str, str_len, unsafe_chars,
"\\u%04x", "\\\\x%02x");
}
gchar *
convert_unsafe_utf8_to_escaped_text(const gchar *str, gssize str_len,
const gchar *unsafe_chars)
{
if (str_len < 0)
str_len = strlen(str);
GString *escaped_string = g_string_sized_new(str_len);
append_unsafe_utf8_as_escaped_text(escaped_string, str, str_len, unsafe_chars);
return g_string_free(escaped_string, FALSE);
}
|
