-
Notifications
You must be signed in to change notification settings - Fork 1
/
filter-parser.c
457 lines (376 loc) · 9.58 KB
/
filter-parser.c
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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stddef.h>
#include <ctype.h>
#include "filter.h"
#include "netflow.h"
#include "flow-info.h"
#define READ_TOKEN_CHECK(I) \
do { \
read_token(I); \
if (I->error) { \
return 0; \
} \
} while (0)
static int expression(struct filter_input *q, struct filter_expr *e);
int
accept_(struct filter_input *i, enum TOKEN_ID token)
{
if (i->current_token.id != token) {
return 0;
}
READ_TOKEN_CHECK(i);
return 1;
}
static int
expect(struct filter_input *i, enum TOKEN_ID token)
{
if (!accept_(i, token)) {
/* unexpected token */
return 0;
}
return 1;
}
int
id(struct filter_input *f, struct filter_expr *e, enum FILTER_BASIC_TYPE type)
{
if ((f->current_token.id != ID)
&& (f->current_token.id != INT_RANGE)
&& (f->current_token.id != STRING)) {
mkerror(f, "Expected ID, INT, INT_RANGE or STRING");
return 0;
}
filter_add_to_basic_filter(f, e, &f->current_token, type);
READ_TOKEN_CHECK(f);
for (;;) {
if (!accept_(f, OR)) {
/* optional OR's */
break;
}
if ((f->current_token.id == ID)
|| (f->current_token.id == INT_RANGE)
|| (f->current_token.id == STRING)) {
filter_add_to_basic_filter(f, e, &f->current_token,
type);
READ_TOKEN_CHECK(f);
continue;
}
READ_TOKEN_CHECK(f);
expression(f, e);
filter_add_op(e, FILTER_OP_OR);
}
return 1;
}
static int
rule_without_direction(struct filter_input *q, struct filter_expr *e, int dir)
{
if (0) {
#define FIELD(NAME, STR, TYPE, SRC, DST) \
} else if (accept_(q, NAME)) { \
filter_add_basic_filter(e, FILTER_BASIC_##TYPE, \
FILTER_BASIC_NAME_##NAME, dir); \
return id(q, e, FILTER_BASIC_##TYPE);
#include "filter.def"
}
return 0;
}
static int
rule(struct filter_input *q, struct filter_expr *e)
{
/* functions */
enum TOKEN_ID div_tok;
if (function_div(q, e, &div_tok)) {
return 1;
}
if (function_min(q, e)) {
return 1;
}
if (function_mfreq(q, e)) {
return 1;
}
if (function_geoip(q, e)) {
return 1;
}
if (function_as(q, e)) {
return 1;
}
/* simple rules */
if (rule_without_direction(q, e, FILTER_BASIC_DIR_BOTH)) {
return 1;
}
if (accept_(q, SRC)) {
return rule_without_direction(q, e, FILTER_BASIC_DIR_SRC);
} else if (accept_(q, DST)) {
return rule_without_direction(q, e, FILTER_BASIC_DIR_DST);
} else {
return 0;
}
}
static int
factor(struct filter_input *f, struct filter_expr *e)
{
int inverse = 0;
if (accept_(f, NOT)) {
inverse = 1;
}
if (rule(f, e)) {
/* ok */
} else if (accept_(f, LPAREN)) {
if (!expression(f, e)) {
return 0;
}
if (!expect(f, RPAREN)) {
mkerror(f, "Expected ')' after expression");
return 0;
}
} else {
mkerror(f, "Syntax error");
return 0;
}
if (inverse) {
if (!filter_add_op(e, FILTER_OP_NOT)) {
return 0;
}
}
return 1;
}
static int
term(struct filter_input *f, struct filter_expr *e)
{
if (!factor(f, e)) {
return 0;
}
while (accept_(f, AND)) {
if (!factor(f, e)) {
return 0;
}
filter_add_op(e, FILTER_OP_AND);
}
return 1;
}
static int
expression(struct filter_input *f, struct filter_expr *e)
{
if (!term(f, e)) {
return 0;
}
while (accept_(f, OR)) {
if (!term(f, e)) {
return 0;
}
filter_add_op(e, FILTER_OP_OR);
}
return 1;
}
struct filter_expr *
parse_filter(struct filter_input *f)
{
struct filter_expr *e;
e = calloc(1, sizeof(struct filter_expr));
if (!e) {
return NULL;
}
READ_TOKEN_CHECK(f);
if (f->end) {
/* allow empty filter */
return e;
}
if (!expression(f, e)) {
return e;
}
if (!f->end) {
char err[ERR_MSG_LEN];
sprintf(err, "Unexpected token '%s' after expression",
f->current_token.data.str);
mkerror(f, err);
}
return e;
}
static int
field_map_flow_info(struct field *fld, const char *name)
{
if (0) {
#define FIELD(NAME, DESC, FLDTYPE, FLDID, SIZEMIN, SIZEMAX) \
} else if (strcmp(#NAME, name) == 0) { \
fld->nf_offset = offsetof(struct flow_info, NAME); \
fld->size = SIZEMAX; \
return 1;
#include "netflow.def"
}
return 0;
}
static int
field_without_direction(struct filter_input *in, struct field *fld, char *err,
int dir)
{
if (0) {
#define FIELD(NAME, STR, TYPE, SRC, DST) \
} else if (accept_(in, NAME)) { \
fld->type = FILTER_BASIC_##TYPE; \
fld->id = NAME; \
if (dir == FILTER_BASIC_DIR_BOTH) { \
if (strcmp(#SRC, #DST) != 0) { \
sprintf(err, "This field requires direction");\
return 0; \
} \
return field_map_flow_info(fld, #SRC); \
} else if (dir == FILTER_BASIC_DIR_SRC) { \
return field_map_flow_info(fld, #SRC); \
} else { \
return field_map_flow_info(fld, #DST); \
} \
return 1;
#include "filter.def"
}
sprintf(err, "Unknown field '%s'", in->current_token.data.str);
return 0;
}
static void
field_mk_names(struct filter_input *in, char *s,
struct field *fld, const char *sfx)
{
size_t len;
size_t i;
len = in->s - s;
/* copy name */
memcpy(fld->name, s, len);
fld->name[len] = '\0';
if (sfx) {
/* remove suffix */
size_t slen = strlen(sfx);
if (strcasecmp(fld->name + len - slen, sfx) == 0) {
*(fld->name + len - slen) = '\0';
}
/* remove white space at string tail */
for (;;) {
size_t nlen = strlen(fld->name);
if (nlen <= 1) {
break;
}
if (fld->name[nlen - 1] != ' ') {
break;
}
fld->name[nlen - 1] = '\0';
}
}
len = strlen(fld->name);
for (i=0; i<len; i++) {
if (isalnum(fld->name[i])) {
fld->sql_name[i] = fld->name[i];
} else {
fld->sql_name[i] = '_';
}
}
fld->sql_name[len] = '\0';
}
static int
field_without_order(struct filter_input *in, struct field *fld, char *err)
{
/* check if field is aggregable */
#define AGGR_FIELD(IN, FLD, NAME, NF_FIELD, SCALE) \
do { \
if (accept_(IN, NAME)) { \
FLD->id = NAME; \
FLD->type = FILTER_BASIC_RANGE; \
FLD->size = sizeof(uint64_t); \
FLD->nf_offset = offsetof(struct flow_info, NF_FIELD); \
FLD->aggr = 1; \
FLD->scale = SCALE; \
return 1; \
} \
} while (0)
/* fields from 'filter-ag.def' */
#define FIELD(NAME, STR, FLD, SCALE) \
AGGR_FIELD(in, fld, NAME, FLD, SCALE);
#include "filter-ag.def"
#undef AGGR_FIELD
/* field from list 'filter.def' */
if (field_without_direction(in, fld, err, FILTER_BASIC_DIR_BOTH)) {
return 1;
}
/* optional SRC/DST */
if (accept_(in, SRC)) {
return field_without_direction(in, fld, err,
FILTER_BASIC_DIR_SRC);
} else if (accept_(in, DST)) {
return field_without_direction(in, fld, err,
FILTER_BASIC_DIR_DST);
}
return 0;
}
/*
* Try to parse field. Field is given in form '[src/dst] field [asc/desc]'
* for example 'src host asc' or 'bits desc'
*/
int
parse_field(char *s, struct field *fld, char *err)
{
struct filter_input in;
enum TOKEN_ID div_tok;
enum TOKEN_ID geoip_tok;
enum TOKEN_ID as_tok;
memset(&in, 0, sizeof(struct filter_input));
in.s = s;
in.line = 1;
memset(fld, 0, sizeof(struct field));
READ_TOKEN_CHECK((&in));
if (in.end) {
sprintf(err, "Empty field not allowed");
return 0;
}
if (function_div_parse(&in, &fld->func_data.div, &div_tok)) {
fld->is_func = 1;
fld->id = div_tok;
fld->type = FILTER_BASIC_RANGE;
fld->size = sizeof(uint64_t);
} else if (function_min_parse(&in, &fld->func_data.min)) {
fld->is_func = 1;
fld->id = MIN;
fld->type = FILTER_BASIC_RANGE;
fld->size = sizeof(uint64_t);
} else if (function_mfreq_parse(&in, &fld->func_data.mfreq)) {
fld->is_func = 1;
fld->id = MFREQ;
fld->type = FILTER_BASIC_RANGE;
fld->size = sizeof(uint64_t);
} else if (function_geoip_parse(&in, &fld->func_data.geoip,
&geoip_tok)) {
fld->is_func = 1;
fld->id = geoip_tok;
fld->type = FILTER_BASIC_STRING;
fld->size = geoip_get_field_size(fld->func_data.geoip.field);
} else if (function_as_parse(&in, &fld->func_data.as, &as_tok)) {
fld->is_func = 1;
fld->id = as_tok;
if (as_tok == ASN) {
fld->type = FILTER_BASIC_RANGE;
fld->size = sizeof(((struct as_info *)0)->asn);
} else {
fld->type = FILTER_BASIC_STRING;
fld->size = sizeof(((struct as_info *)0)->asd);
}
} else {
/* parse field without ASC/DESC suffix */
if (!field_without_order(&in, fld, err)) {
return 0;
}
}
/* optional order */
fld->descending = 0;
if (accept_(&in, DESC)) {
fld->descending = 1;
field_mk_names(&in, s, fld, "desc");
} else if (accept_(&in, ASC)) {
/* default order */
field_mk_names(&in, s, fld, "asc");
} else {
/* no order */
field_mk_names(&in, s, fld, NULL);
}
if (!in.end) {
sprintf(err, "Extra symbols after field name");
return 0;
}
return 1;
}