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
|
/*
* Copyright (C) 2001-2006 Andreas Steffen
*
* 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. See <http://www.fsf.org/copyleft/gpl.txt>.
*
* 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.
*
* $Id: lexparser.c 3872 2008-04-25 07:04:59Z andreas $
*/
/* memrchr is a GNU extension */
#define _GNU_SOURCE
#include <string.h>
#include "lexparser.h"
/**
* eat whitespace
*/
bool eat_whitespace(chunk_t *src)
{
while (src->len > 0 && (*src->ptr == ' ' || *src->ptr == '\t'))
{
src->ptr++; src->len--;
}
return src->len > 0 && *src->ptr != '#';
}
/**
* compare string with chunk
*/
bool match(const char *pattern, const chunk_t *ch)
{
return ch->len == strlen(pattern) && strncmp(pattern, ch->ptr, ch->len) == 0;
}
/**
* extracts a token ending with the first occurrence of a given termination symbol
*/
bool extract_token(chunk_t *token, const char termination, chunk_t *src)
{
u_char *eot = memchr(src->ptr, termination, src->len);
if (termination == ' ')
{
u_char *eot_tab = memchr(src->ptr, '\t', src->len);
/* check if a tab instead of a space terminates the token */
eot = ( eot_tab == NULL || (eot && eot < eot_tab) ) ? eot : eot_tab;
}
/* initialize empty token */
*token = chunk_empty;
if (eot == NULL) /* termination symbol not found */
{
return FALSE;
}
/* extract token */
token->ptr = src->ptr;
token->len = (u_int)(eot - src->ptr);
/* advance src pointer after termination symbol */
src->ptr = eot + 1;
src->len -= (token->len + 1);
return TRUE;
}
/**
* extracts a token ending with the last occurrence of a given termination symbol
*/
bool extract_last_token(chunk_t *token, const char termination, chunk_t *src)
{
u_char *eot = memrchr(src->ptr, termination, src->len);
/* initialize empty token */
*token = chunk_empty;
if (eot == NULL) /* termination symbol not found */
{
return FALSE;
}
/* extract token */
token->ptr = src->ptr;
token->len = (u_int)(eot - src->ptr);
/* advance src pointer after termination symbol */
src->ptr = eot + 1;
src->len -= (token->len + 1);
return TRUE;
}
/**
* fetches a new line terminated by \n or \r\n
*/
bool fetchline(chunk_t *src, chunk_t *line)
{
if (src->len == 0) /* end of src reached */
return FALSE;
if (extract_token(line, '\n', src))
{
if (line->len > 0 && *(line->ptr + line->len -1) == '\r')
line->len--; /* remove optional \r */
}
else /*last line ends without newline */
{
*line = *src;
src->ptr += src->len;
src->len = 0;
}
return TRUE;
}
err_t extract_value(chunk_t *value, chunk_t *line)
{
char delimiter = ' ';
if (!eat_whitespace(line))
{
*value = chunk_empty;
return NULL;
}
if (*line->ptr == '\'' || *line->ptr == '"')
{
delimiter = *line->ptr;
line->ptr++; line->len--;
}
if (!extract_token(value, delimiter, line))
{
if (delimiter == ' ')
{
*value = *line;
line->len = 0;
}
else
{
return "missing second delimiter";
}
}
return NULL;
}
/**
* extracts a parameter: value pair
*/
err_t extract_parameter_value(chunk_t *name, chunk_t *value, chunk_t *line)
{
/* extract name */
if (!extract_token(name,':', line))
{
return "missing ':'";
}
/* extract value */
return extract_value(value, line);
}
|
