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
|
#include "logparse.h"
#include "apr_file_info.h"
#include "apr_file_io.h"
#include "apr_strings.h"
void find_log_files(config_t *cfg)
{
apr_pool_t *tp;
apr_dir_t *dir;
apr_finfo_t finfo;
char **newp;
if (!cfg->input_dir)
return;
apr_pool_create(&tp, cfg->pool);
if (apr_dir_open(&dir, cfg->input_dir, tp)==APR_SUCCESS) {
while (apr_dir_read(&finfo, APR_FINFO_NAME | APR_FINFO_TYPE, dir)
== APR_SUCCESS) {
if (finfo.filetype == APR_DIR)
continue;
newp = (char **)apr_array_push(cfg->input_files);
apr_filepath_merge(newp, cfg->input_dir, finfo.name,
APR_FILEPATH_TRUENAME, cfg->pool);
}
apr_dir_close(dir);
}
apr_pool_destroy(tp);
}
/*
* Modified version of apr_tokenize_to_argv to add [] as quoting characters
*
* token_context: Context from which pool allocations will occur.
* arg_str: Input string for conversion to argv[].
* argv_out: Output location. This is a pointer to an array
* of pointers to strings (ie. &(char *argv[]).
* This value will be allocated from the contexts
* pool and filled in with copies of the tokens
* found during parsing of the arg_str.
* keepquotes: Keep the quotes instead of stripping them
*/
apr_status_t tokenize_logline(const char *arg_str, char ***argv_out,
apr_pool_t *token_context, int keepquotes)
{
const char *cp;
const char *ct;
char *cleaned, *dirty;
int escaped;
int isquoted, numargs = 0, argnum;
#define SKIP_WHITESPACE(cp) \
for ( ; *cp == ' ' || *cp == '\t'; ) { \
cp++; \
};
#define CHECK_QUOTATION(cp,isquoted) \
isquoted = 0; \
if (*cp == '"') { \
isquoted = 1; \
cp++; \
} \
else if (*cp == '\'') { \
isquoted = 2; \
cp++; \
} \
else if (*cp == '[') { \
isquoted = 3; \
cp++; \
}
/* DETERMINE_NEXTSTRING:
* At exit, cp will point to one of the following: NULL, SPACE, TAB or QUOTE.
* NULL implies the argument string has been fully traversed.
*/
#define DETERMINE_NEXTSTRING(cp,isquoted) \
for ( ; *cp != '\0'; cp++) { \
if ( (isquoted && (*cp == ' ' || *cp == '\t')) \
|| (*cp == '\\' && (*(cp+1) == ' ' || *(cp+1) == '\t' || \
*(cp+1) == '"' || *(cp+1) == '\'' || \
*(cp+1) == '[' || *(cp+1) == ']'))) { \
cp++; \
continue; \
} \
if ( (!isquoted && (*cp == ' ' || *cp == '\t')) \
|| (isquoted == 1 && *cp == '"') \
|| (isquoted == 2 && *cp == '\'') \
|| (isquoted == 3 && *cp == ']') \
) { \
break; \
} \
}
/* REMOVE_ESCAPE_CHARS:
* Compresses the arg string to remove all of the '\' escape chars.
* The final argv strings should not have any extra escape chars in it.
*/
#define REMOVE_ESCAPE_CHARS(cleaned, dirty, escaped) \
escaped = 0; \
while(*dirty) { \
if (!escaped && *dirty == '\\') { \
escaped = 1; \
} \
else { \
escaped = 0; \
*cleaned++ = *dirty; \
} \
++dirty; \
} \
*cleaned = 0; /* last line of macro... */
cp = arg_str;
SKIP_WHITESPACE(cp);
ct = cp;
/* This is ugly and expensive, but if anyone wants to figure a
* way to support any number of args without counting and
* allocating, please go ahead and change the code.
*
* Must account for the trailing NULL arg.
*/
numargs = 1;
while (*ct != '\0') {
CHECK_QUOTATION(ct, isquoted)
;
DETERMINE_NEXTSTRING(ct, isquoted);
if (*ct != '\0') {
ct++;
}
numargs++;
SKIP_WHITESPACE(ct);
}
*argv_out = apr_palloc(token_context, numargs * sizeof(char*));
/* determine first argument */
for (argnum = 0; argnum < (numargs-1); argnum++) {
SKIP_WHITESPACE(cp);
CHECK_QUOTATION(cp, isquoted)
;
ct = cp;
DETERMINE_NEXTSTRING(cp, isquoted);
cp++;
if (isquoted && keepquotes) {
(*argv_out)[argnum] = apr_palloc(token_context, cp - ct + 2);
apr_cpystrn((*argv_out)[argnum], ct -1, cp - ct + 2);
} else {
(*argv_out)[argnum] = apr_palloc(token_context, cp - ct);
apr_cpystrn((*argv_out)[argnum], ct, cp - ct);
}
cleaned = dirty = (*argv_out)[argnum];
REMOVE_ESCAPE_CHARS(cleaned, dirty, escaped)
;
}
(*argv_out)[argnum] = NULL;
return APR_SUCCESS;
}
apr_status_t parse_logfile(config_t *cfg, const char *filename)
{
apr_pool_t *tp, *argp;
apr_file_t *file;
apr_status_t rv;
char buff[2048];
char **targv;
int targc;
int line;
apr_pool_create(&tp, cfg->pool);
apr_pool_create(&argp, tp);
rv = apr_file_open(&file, filename, APR_FOPEN_READ | APR_BUFFERED,
APR_OS_DEFAULT, tp);
if (rv != APR_SUCCESS) {
printf("Could not open %s\n", filename);
return rv;
}
line = 0;
do {
rv = apr_file_gets(buff, 1024, file);
if (rv == APR_SUCCESS) {
line++;
char *ptr;
// chomp off newline
for (ptr = buff + strlen(buff); *ptr != '\r' && *ptr != '\n'; ptr--)
;
*ptr = '\0';
apr_pool_clear(argp);
tokenize_logline(buff, &targv, argp, 1);
targc = 0;
while (targv[targc]) targc++;
if (targc != 9) {
int i;
printf("Line %d(%d): %s\n",line, targc, buff);
for (i = 0; targv[i]; i++) {
printf("Arg (%d): '%s'\n", i, targv[i]);
}
}
}
} while (rv == APR_SUCCESS);
printf("Total Lines: %d\n", line);
apr_file_close(file);
apr_pool_destroy(tp);
return APR_SUCCESS;
}
|
