forked from rsyslog/rsyslog
-
Notifications
You must be signed in to change notification settings - Fork 0
/
template.c
2432 lines (2274 loc) · 75.5 KB
/
template.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
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/* This is the template processing code of rsyslog.
* begun 2004-11-17 rgerhards
*
* Copyright 2004-2019 Rainer Gerhards and Adiscon
*
* This file is part of rsyslog.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
* -or-
* see COPYING.ASL20 in the source distribution
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
* Note: there is a tiny bit of code left where I could not get any response
* from the author if this code can be placed under ASL2.0. I have guarded this
* with #ifdef STRICT_GPLV3. Only if that macro is defined, the code will be
* compiled. Otherwise this feature is not present. The plan is to do a
* different implementation in the future to get rid of this problem.
* rgerhards, 2012-08-25
*/
#include "config.h"
#include "rsyslog.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <assert.h>
#include <json.h>
#include "stringbuf.h"
#include "syslogd-types.h"
#include "template.h"
#include "msg.h"
#include "dirty.h"
#include "obj.h"
#include "errmsg.h"
#include "strgen.h"
#include "rsconf.h"
#include "msg.h"
#include "parserif.h"
#include "unicode-helper.h"
PRAGMA_INGORE_Wswitch_enum
/* static data */
DEFobjCurrIf(obj)
DEFobjCurrIf(strgen)
/* tables for interfacing with the v6 config system */
static struct cnfparamdescr cnfparamdescr[] = {
{ "name", eCmdHdlrString, 1 },
{ "type", eCmdHdlrString, 1 },
{ "string", eCmdHdlrString, 0 },
{ "plugin", eCmdHdlrString, 0 },
{ "subtree", eCmdHdlrString, 0 },
{ "option.stdsql", eCmdHdlrBinary, 0 },
{ "option.sql", eCmdHdlrBinary, 0 },
{ "option.json", eCmdHdlrBinary, 0 },
{ "option.jsonf", eCmdHdlrBinary, 0 },
{ "option.casesensitive", eCmdHdlrBinary, 0 }
};
static struct cnfparamblk pblk =
{ CNFPARAMBLK_VERSION,
sizeof(cnfparamdescr)/sizeof(struct cnfparamdescr),
cnfparamdescr
};
static struct cnfparamdescr cnfparamdescrProperty[] = {
{ "name", eCmdHdlrString, 1 },
{ "outname", eCmdHdlrString, 0 },
{ "dateformat", eCmdHdlrString, 0 },
{ "date.inutc", eCmdHdlrBinary, 0 },
{ "compressspace", eCmdHdlrBinary, 0 },
{ "caseconversion", eCmdHdlrString, 0 },
{ "controlcharacters", eCmdHdlrString, 0 },
{ "securepath", eCmdHdlrString, 0 },
{ "format", eCmdHdlrString, 0 },
{ "position.from", eCmdHdlrInt, 0 },
{ "position.to", eCmdHdlrInt, 0 },
{ "position.relativetoend", eCmdHdlrBinary, 0 },
{ "field.number", eCmdHdlrInt, 0 },
{ "field.delimiter", eCmdHdlrInt, 0 },
{ "regex.expression", eCmdHdlrString, 0 },
{ "regex.type", eCmdHdlrString, 0 },
{ "regex.nomatchmode", eCmdHdlrString, 0 },
{ "regex.match", eCmdHdlrInt, 0 },
{ "regex.submatch", eCmdHdlrInt, 0 },
{ "droplastlf", eCmdHdlrBinary, 0 },
{ "fixedwidth", eCmdHdlrBinary, 0 },
{ "datatype", eCmdHdlrString, 0 },
{ "onempty", eCmdHdlrString, 0 },
{ "mandatory", eCmdHdlrBinary, 0 },
{ "spifno1stsp", eCmdHdlrBinary, 0 }
};
static struct cnfparamblk pblkProperty =
{ CNFPARAMBLK_VERSION,
sizeof(cnfparamdescrProperty)/sizeof(struct cnfparamdescr),
cnfparamdescrProperty
};
static struct cnfparamdescr cnfparamdescrConstant[] = {
{ "value", eCmdHdlrString, 1 },
{ "format", eCmdHdlrString, 0 },
{ "outname", eCmdHdlrString, 0 }
};
static struct cnfparamblk pblkConstant =
{ CNFPARAMBLK_VERSION,
sizeof(cnfparamdescrConstant)/sizeof(struct cnfparamdescr),
cnfparamdescrConstant
};
#ifdef FEATURE_REGEXP
DEFobjCurrIf(regexp)
static int bFirstRegexpErrmsg = 1; /**< did we already do a "can't load regexp" error message? */
#endif
/* helper to tplToString and strgen's, extends buffer */
#define ALLOC_INC 128
rsRetVal
ExtendBuf(actWrkrIParams_t *__restrict__ const iparam, const size_t iMinSize)
{
uchar *pNewBuf;
size_t iNewSize;
DEFiRet;
iNewSize = (iMinSize / ALLOC_INC + 1) * ALLOC_INC;
CHKmalloc(pNewBuf = (uchar*) realloc(iparam->param, iNewSize));
iparam->param = pNewBuf;
iparam->lenBuf = iNewSize;
finalize_it:
RETiRet;
}
/* This functions converts a template into a string.
*
* The function takes a pointer to a template and a pointer to a msg object
* as well as a pointer to an output buffer and its size. Note that the output
* buffer pointer may be NULL, size 0, in which case a new one is allocated.
* The output buffer is grown as required. It is the caller's duty to free the
* buffer when it is done. Note that it is advisable to reuse memory, as this
* offers big performance improvements.
* rewritten 2009-06-19 rgerhards
*/
rsRetVal
tplToString(struct template *__restrict__ const pTpl,
smsg_t *__restrict__ const pMsg,
actWrkrIParams_t *__restrict__ const iparam,
struct syslogTime *const ttNow)
{
DEFiRet;
struct templateEntry *__restrict__ pTpe;
size_t iBuf;
unsigned short bMustBeFreed = 0;
uchar *pVal;
rs_size_t iLenVal = 0;
if(pTpl->pStrgen != NULL) {
CHKiRet(pTpl->pStrgen(pMsg, iparam));
FINALIZE;
}
if(pTpl->bHaveSubtree) {
/* only a single CEE subtree must be provided */
/* note: we could optimize the code below, however, this is
* not worth the effort, as this passing mode is not expected
* in subtree mode and so most probably only used for debug & test.
*/
getJSONPropVal(pMsg, &pTpl->subtree, &pVal, &iLenVal, &bMustBeFreed);
if(iLenVal >= (rs_size_t)iparam->lenBuf) /* we reserve one char for the final \0! */
CHKiRet(ExtendBuf(iparam, iLenVal + 1));
memcpy(iparam->param, pVal, iLenVal+1);
FINALIZE;
}
/* we have a "regular" template with template entries */
/* loop through the template. We obtain one value
* and copy it over to our dynamic string buffer. Then, we
* free the obtained value (if requested). We continue this
* loop until we got hold of all values.
*/
pTpe = pTpl->pEntryRoot;
iBuf = 0;
const int extra_space = (pTpl->optFormatEscape == JSONF) ? 1 : 3;
if(pTpl->optFormatEscape == JSONF) {
if(iparam->lenBuf < 2) /* we reserve one char for the final \0! */
CHKiRet(ExtendBuf(iparam, 2));
iBuf = 1;
*iparam->param = '{';
}
while(pTpe != NULL) {
if(pTpe->eEntryType == CONSTANT) {
pVal = (uchar*) pTpe->data.constant.pConstant;
iLenVal = pTpe->data.constant.iLenConstant;
bMustBeFreed = 0;
} else if(pTpe->eEntryType == FIELD) {
pVal = (uchar*) MsgGetProp(pMsg, pTpe, &pTpe->data.field.msgProp,
&iLenVal, &bMustBeFreed, ttNow);
/* we now need to check if we should use SQL option. In this case,
* we must go over the generated string and escape '\'' characters.
* rgerhards, 2005-09-22: the option values below look somewhat misplaced,
* but they are handled in this way because of legacy (don't break any
* existing thing).
*/
if(pTpl->optFormatEscape == SQL_ESCAPE)
doEscape(&pVal, &iLenVal, &bMustBeFreed, SQL_ESCAPE);
else if(pTpl->optFormatEscape == JSON_ESCAPE)
doEscape(&pVal, &iLenVal, &bMustBeFreed, JSON_ESCAPE);
else if(pTpl->optFormatEscape == STDSQL_ESCAPE)
doEscape(&pVal, &iLenVal, &bMustBeFreed, STDSQL_ESCAPE);
} else {
DBGPRINTF("TplToString: invalid entry type %d\n", pTpe->eEntryType);
pVal = (uchar*) "*LOGIC ERROR*";
iLenVal = sizeof("*LOGIC ERROR*") - 1;
bMustBeFreed = 0;
}
/* got source, now copy over */
if(iLenVal > 0) { /* may be zero depending on property */
/* first, make sure buffer fits */
if(iBuf + iLenVal + extra_space >= iparam->lenBuf) /* we reserve one char for the final \0! */
CHKiRet(ExtendBuf(iparam, iBuf + iLenVal + 1));
memcpy(iparam->param + iBuf, pVal, iLenVal);
iBuf += iLenVal;
if(pTpl->optFormatEscape == JSONF) {
memcpy(iparam->param + iBuf,
(pTpe->pNext == NULL) ? "}\n" : ", ", 2);
iBuf += 2;
}
}
if(bMustBeFreed) {
free(pVal);
bMustBeFreed = 0;
}
pTpe = pTpe->pNext;
}
if(iBuf == iparam->lenBuf) {
/* in the weired case of an *empty* template, this can happen.
* it is debatable if we should really fix it here or simply
* forbid that case. However, performance toll is minimal, so
* I tend to permit it. -- 2010-11-05 rgerhards
*/
CHKiRet(ExtendBuf(iparam, iBuf + 1));
}
iparam->param[iBuf] = '\0';
iparam->lenStr = iBuf;
finalize_it:
if(bMustBeFreed) {
free(pVal);
bMustBeFreed = 0;
}
RETiRet;
}
/* This functions converts a template into a json object.
* For further general details, see the very similar funtion
* tpltoString().
* rgerhards, 2012-08-29
*/
rsRetVal
tplToJSON(struct template *pTpl, smsg_t *pMsg, struct json_object **pjson, struct syslogTime *ttNow)
{
struct templateEntry *pTpe;
rs_size_t propLen;
unsigned short bMustBeFreed;
uchar *pVal;
struct json_object *json, *jsonf;
rsRetVal localRet;
DEFiRet;
if(pTpl->bHaveSubtree){
if(jsonFind(pMsg->json, &pTpl->subtree, pjson) != RS_RET_OK)
*pjson = NULL;
if(*pjson == NULL) {
/* we need to have a root object! */
*pjson = json_object_new_object();
} else {
json_object_get(*pjson); /* inc refcount */
}
FINALIZE;
}
json = json_object_new_object();
for(pTpe = pTpl->pEntryRoot ; pTpe != NULL ; pTpe = pTpe->pNext) {
if(pTpe->eEntryType == CONSTANT) {
if(pTpe->fieldName == NULL)
continue;
jsonf = json_object_new_string((char*) pTpe->data.constant.pConstant);
json_object_object_add(json, (char*)pTpe->fieldName, jsonf);
} else if(pTpe->eEntryType == FIELD) {
if(pTpe->data.field.msgProp.id == PROP_CEE ||
pTpe->data.field.msgProp.id == PROP_LOCAL_VAR ||
pTpe->data.field.msgProp.id == PROP_GLOBAL_VAR ) {
localRet = msgGetJSONPropJSON(pMsg, &pTpe->data.field.msgProp, &jsonf);
if(localRet == RS_RET_OK) {
json_object_object_add(json, (char*)pTpe->fieldName, json_object_get(jsonf));
} else {
DBGPRINTF("tplToJSON: error %d looking up property %s\n",
localRet, pTpe->fieldName);
if(pTpe->data.field.options.bMandatory) {
json_object_object_add(json, (char*)pTpe->fieldName, NULL);
}
}
} else {
pVal = (uchar*) MsgGetProp(pMsg, pTpe, &pTpe->data.field.msgProp,
&propLen, &bMustBeFreed, ttNow);
if(pTpe->data.field.options.bMandatory || propLen > 0) {
jsonf = json_object_new_string_len((char*)pVal, propLen+1);
json_object_object_add(json, (char*)pTpe->fieldName, jsonf);
}
if(bMustBeFreed) { /* json-c makes its own private copy! */
free(pVal);
}
}
}
}
assert(iRet == RS_RET_OK);
*pjson = json;
finalize_it:
RETiRet;
}
/* Helper to doEscape. This is called if doEscape
* runs out of memory allocating the escaped string.
* Then we are in trouble. We can
* NOT simply return the unmodified string because this
* may cause SQL injection. But we also can not simply
* abort the run, this would be a DoS. I think an appropriate
* measure is to remove the dangerous \' characters (SQL). We
* replace them by \", which will break the message and
* signatures eventually present - but this is the
* best thing we can do now (or does anybody
* have a better idea?). rgerhards 2004-11-23
* added support for escape mode (see doEscape for details).
* if mode = SQL_ESCAPE, then backslashes are changed to slashes.
* rgerhards 2005-09-22
*/
static void doEmergencyEscape(register uchar *p, int mode)
{
while(*p) {
if((mode == SQL_ESCAPE||mode == STDSQL_ESCAPE) && *p == '\'') {
*p = '"';
} else if(mode == JSON_ESCAPE) {
if(*p == '"') {
*p = '\'';
} else if(*p == '\\' ) {
*p = '/';
}
} else if((mode == SQL_ESCAPE) && *p == '\\') {
*p = '/';
}
++p;
}
}
/* SQL-Escape a string. Single quotes are found and
* replaced by two of them. A new buffer is allocated
* for the provided string and the provided buffer is
* freed. The length is updated. Parameter pbMustBeFreed
* is set to 1 if a new buffer is allocated. Otherwise,
* it is left untouched.
* --
* We just discovered a security issue. MySQL is so
* "smart" to not only support the standard SQL mechanism
* for escaping quotes, but to also provide its own (using
* c-type syntax with backslashes). As such, it is actually
* possible to do sql injection via rsyslogd. The cure is now
* to escape backslashes, too. As we have found on the web, some
* other databases seem to be similar "smart" (why do we have standards
* at all if they are violated without any need???). Even better, MySQL's
* smartness depends on config settings. So we add a new option to this
* function that allows the caller to select if they want to standard or
* "smart" encoding ;)
* --
* Parameter "mode" is STDSQL_ESCAPE, SQL_ESCAPE "smart" SQL engines, or
* JSON_ESCAPE for everyone requiring escaped JSON (e.g. ElasticSearch).
* 2005-09-22 rgerhards
*/
rsRetVal
doEscape(uchar **pp, rs_size_t *pLen, unsigned short *pbMustBeFreed, int mode)
{
DEFiRet;
uchar *p = NULL;
int iLen;
cstr_t *pStrB = NULL;
uchar *pszGenerated;
assert(pp != NULL);
assert(*pp != NULL);
assert(pLen != NULL);
assert(pbMustBeFreed != NULL);
/* first check if we need to do anything at all... */
if(mode == STDSQL_ESCAPE)
for(p = *pp ; *p && *p != '\'' ; ++p)
;
else if(mode == SQL_ESCAPE)
for(p = *pp ; *p && *p != '\'' && *p != '\\' ; ++p)
;
else if(mode == JSON_ESCAPE)
for(p = *pp ; *p && (*p == '"' || *p == '\\' ) ; ++p)
;
/* when we get out of the loop, we are either at the
* string terminator or the first character to escape */
if(p && *p == '\0')
FINALIZE; /* nothing to do in this case! */
p = *pp;
iLen = *pLen;
CHKiRet(cstrConstruct(&pStrB));
while(*p) {
if((mode == SQL_ESCAPE || mode == STDSQL_ESCAPE) && *p == '\'') {
CHKiRet(cstrAppendChar(pStrB, (mode == STDSQL_ESCAPE) ? '\'' : '\\'));
iLen++; /* reflect the extra character */
} else if((mode == SQL_ESCAPE) && *p == '\\') {
CHKiRet(cstrAppendChar(pStrB, '\\'));
iLen++; /* reflect the extra character */
} else if((mode == JSON_ESCAPE) && (*p == '"' || *p == '\\' )) {
CHKiRet(cstrAppendChar(pStrB, '\\'));
iLen++; /* reflect the extra character */
}
CHKiRet(cstrAppendChar(pStrB, *p));
++p;
}
cstrFinalize(pStrB);
CHKiRet(cstrConvSzStrAndDestruct(&pStrB, &pszGenerated, 0));
if(*pbMustBeFreed)
free(*pp); /* discard previous value */
*pp = pszGenerated;
*pLen = iLen;
*pbMustBeFreed = 1;
finalize_it:
if(iRet != RS_RET_OK) {
doEmergencyEscape(*pp, mode);
if(pStrB != NULL)
cstrDestruct(&pStrB);
}
RETiRet;
}
/* Constructs a template entry object. Returns pointer to it
* or NULL (if it fails). Pointer to associated template list entry
* must be provided.
*/
static struct templateEntry* tpeConstruct(struct template *pTpl)
{
struct templateEntry *pTpe;
assert(pTpl != NULL);
if((pTpe = calloc(1, sizeof(struct templateEntry))) == NULL)
return NULL;
/* basic initialization is done via calloc() - need to
* initialize only values != 0. */
if(pTpl->pEntryLast == NULL){
/* we are the first element! */
pTpl->pEntryRoot = pTpl->pEntryLast = pTpe;
} else {
pTpl->pEntryLast->pNext = pTpe;
pTpl->pEntryLast = pTpe;
}
pTpl->tpenElements++;
return(pTpe);
}
/* Helper function to apply case-sensitivity to templates.
*/
static void
apply_case_sensitivity(struct template *pTpl)
{
if(pTpl->optCaseSensitive) return;
struct templateEntry *pTpe;
for(pTpe = pTpl->pEntryRoot ; pTpe != NULL ; pTpe = pTpe->pNext) {
if(pTpe->eEntryType == FIELD) {
if(pTpe->data.field.msgProp.id == PROP_CEE ||
pTpe->data.field.msgProp.id == PROP_LOCAL_VAR ||
pTpe->data.field.msgProp.id == PROP_GLOBAL_VAR ) {
uchar* p;
p = pTpe->fieldName;
for ( ; *p; ++p) *p = tolower(*p);
p = pTpe->data.field.msgProp.name;
for ( ; *p; ++p) *p = tolower(*p);
}
}
}
}
/* Constructs a template list object. Returns pointer to it
* or NULL (if it fails).
*/
static struct template*
tplConstruct(rsconf_t *conf)
{
struct template *pTpl;
if((pTpl = calloc(1, sizeof(struct template))) == NULL)
return NULL;
/* basic initialisation is done via calloc() - need to
* initialize only values != 0. */
if(conf->templates.last == NULL) {
/* we are the first element! */
conf->templates.root = conf->templates.last = pTpl;
} else {
conf->templates.last->pNext = pTpl;
conf->templates.last = pTpl;
}
return(pTpl);
}
/* helper to tplAddLine. Parses a constant and generates
* the necessary structure.
* Paramter "bDoEscapes" is to support legacy vs. v6+ config system. In
* legacy, we must do escapes ourselves, whereas v6+ passes in already
* escaped strings (which we are NOT permitted to further escape, this would
* cause invalid result strings!). Note: if escapes are not permitted,
* quotes (") are just a regular character and do NOT terminate the constant!
*/
static rsRetVal
do_Constant(unsigned char **pp, struct template *pTpl, int bDoEscapes)
{
register unsigned char *p;
cstr_t *pStrB;
struct templateEntry *pTpe;
int i;
DEFiRet;
assert(pp != NULL);
assert(*pp != NULL);
assert(pTpl != NULL);
p = *pp;
CHKiRet(cstrConstruct(&pStrB));
/* process the message and expand escapes
* (additional escapes can be added here if needed)
*/
while(*p && *p != '%' && !(bDoEscapes && *p == '\"')) {
if(bDoEscapes && *p == '\\') {
switch(*++p) {
case '\0':
/* the best we can do - it's invalid anyhow... */
cstrAppendChar(pStrB, *p);
break;
case 'n':
cstrAppendChar(pStrB, '\n');
++p;
break;
case 'r':
cstrAppendChar(pStrB, '\r');
++p;
break;
case '\\':
cstrAppendChar(pStrB, '\\');
++p;
break;
case '%':
cstrAppendChar(pStrB, '%');
++p;
break;
case '0': /* numerical escape sequence */
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
i = 0;
while(*p && isdigit((int)*p)) {
i = i * 10 + *p++ - '0';
}
cstrAppendChar(pStrB, i);
break;
default:
cstrAppendChar(pStrB, *p++);
break;
}
}
else
cstrAppendChar(pStrB, *p++);
}
if((pTpe = tpeConstruct(pTpl)) == NULL) {
rsCStrDestruct(&pStrB);
ABORT_FINALIZE(RS_RET_OUT_OF_MEMORY);
}
pTpe->eEntryType = CONSTANT;
cstrFinalize(pStrB);
/* We obtain the length from the counted string object
* (before we delete it). Later we might take additional
* benefit from the counted string object.
* 2005-09-09 rgerhards
*/
pTpe->data.constant.iLenConstant = rsCStrLen(pStrB);
CHKiRet(cstrConvSzStrAndDestruct(&pStrB, &pTpe->data.constant.pConstant, 0));
*pp = p;
finalize_it:
RETiRet;
}
/* Helper that checks to see if a property already has a format
* type defined
*/
static int hasFormat(struct templateEntry *pTpe) {
return (
pTpe->data.field.options.bCSV ||
pTpe->data.field.options.bJSON ||
pTpe->data.field.options.bJSONf ||
pTpe->data.field.options.bJSONr
);
}
/* Helper to do_Parameter(). This parses the formatting options
* specified in a template variable. It returns the passed-in pointer
* updated to the next processed character.
*/
static void doOptions(unsigned char **pp, struct templateEntry *pTpe)
{
register unsigned char *p;
unsigned char Buf[64];
size_t i;
assert(pp != NULL);
assert(*pp != NULL);
assert(pTpe != NULL);
p = *pp;
while(*p && *p != '%' && *p != ':') {
/* outer loop - until end of options */
i = 0;
while((i < sizeof(Buf)-1) &&
*p && *p != '%' && *p != ':' && *p != ',') {
/* inner loop - until end of ONE option */
Buf[i++] = tolower((int)*p);
++p;
}
Buf[i] = '\0'; /* terminate */
/* check if we need to skip oversize option */
while(*p && *p != '%' && *p != ':' && *p != ',')
++p; /* just skip */
if(*p == ',')
++p; /* eat ',' */
/* OK, we got the option, so now lets look what
* it tells us...
*/
if(!strcmp((char*)Buf, "date-mysql")) {
pTpe->data.field.eDateFormat = tplFmtMySQLDate;
} else if(!strcmp((char*)Buf, "date-pgsql")) {
pTpe->data.field.eDateFormat = tplFmtPgSQLDate;
} else if(!strcmp((char*)Buf, "date-rfc3164")) {
pTpe->data.field.eDateFormat = tplFmtRFC3164Date;
} else if(!strcmp((char*)Buf, "date-rfc3164-buggyday")) {
pTpe->data.field.eDateFormat = tplFmtRFC3164BuggyDate;
} else if(!strcmp((char*)Buf, "date-rfc3339")) {
pTpe->data.field.eDateFormat = tplFmtRFC3339Date;
} else if(!strcmp((char*)Buf, "date-unixtimestamp")) {
pTpe->data.field.eDateFormat = tplFmtUnixDate;
} else if(!strcmp((char*)Buf, "date-subseconds")) {
pTpe->data.field.eDateFormat = tplFmtSecFrac;
} else if(!strcmp((char*)Buf, "date-wdayname")) {
pTpe->data.field.eDateFormat = tplFmtWDayName;
} else if(!strcmp((char*)Buf, "date-wday")) {
pTpe->data.field.eDateFormat = tplFmtWDay;
} else if(!strcmp((char*)Buf, "date-year")) {
pTpe->data.field.eDateFormat = tplFmtYear;
} else if(!strcmp((char*)Buf, "date-month")) {
pTpe->data.field.eDateFormat = tplFmtMonth;
} else if(!strcmp((char*)Buf, "date-day")) {
pTpe->data.field.eDateFormat = tplFmtDay;
} else if(!strcmp((char*)Buf, "date-hour")) {
pTpe->data.field.eDateFormat = tplFmtHour;
} else if(!strcmp((char*)Buf, "date-minute")) {
pTpe->data.field.eDateFormat = tplFmtMinute;
} else if(!strcmp((char*)Buf, "date-second")) {
pTpe->data.field.eDateFormat = tplFmtSecond;
} else if(!strcmp((char*)Buf, "date-tzoffshour")) {
pTpe->data.field.eDateFormat = tplFmtTZOffsHour;
} else if(!strcmp((char*)Buf, "date-tzoffsmin")) {
pTpe->data.field.eDateFormat = tplFmtTZOffsMin;
} else if(!strcmp((char*)Buf, "date-tzoffsdirection")) {
pTpe->data.field.eDateFormat = tplFmtTZOffsDirection;
} else if (!strcmp((char*)Buf, "date-ordinal")) {
pTpe->data.field.eDateFormat = tplFmtOrdinal;
} else if (!strcmp((char*)Buf, "date-week")) {
pTpe->data.field.eDateFormat = tplFmtWeek;
} else if(!strcmp((char*)Buf, "date-utc")) {
pTpe->data.field.options.bDateInUTC = 1;
} else if(!strcmp((char*)Buf, "lowercase")) {
pTpe->data.field.eCaseConv = tplCaseConvLower;
} else if(!strcmp((char*)Buf, "uppercase")) {
pTpe->data.field.eCaseConv = tplCaseConvUpper;
} else if(!strcmp((char*)Buf, "sp-if-no-1st-sp")) {
pTpe->data.field.options.bSPIffNo1stSP = 1;
} else if(!strcmp((char*)Buf, "compressspace")) {
pTpe->data.field.options.bCompressSP = 1;
} else if(!strcmp((char*)Buf, "escape-cc")) {
pTpe->data.field.options.bEscapeCC = 1;
} else if(!strcmp((char*)Buf, "drop-cc")) {
pTpe->data.field.options.bDropCC = 1;
} else if(!strcmp((char*)Buf, "space-cc")) {
pTpe->data.field.options.bSpaceCC = 1;
} else if(!strcmp((char*)Buf, "drop-last-lf")) {
pTpe->data.field.options.bDropLastLF = 1;
} else if(!strcmp((char*)Buf, "secpath-drop")) {
pTpe->data.field.options.bSecPathDrop = 1;
} else if(!strcmp((char*)Buf, "secpath-replace")) {
pTpe->data.field.options.bSecPathReplace = 1;
} else if(!strcmp((char*)Buf, "pos-end-relative")) {
pTpe->data.field.options.bFromPosEndRelative = 1;
} else if(!strcmp((char*)Buf, "fixed-width")) {
pTpe->data.field.options.bFixedWidth = 1;
} else if(!strcmp((char*)Buf, "csv")) {
if(hasFormat(pTpe)) {
LogError(0, NO_ERRCODE, "error: can only specify "
"one option out of (json, jsonf, jsonr, jsonfr, csv) - csv ignored");
} else {
pTpe->data.field.options.bCSV = 1;
}
} else if(!strcmp((char*)Buf, "json")) {
if(hasFormat(pTpe)) {
LogError(0, NO_ERRCODE, "error: can only specify "
"one option out of (json, jsonf, jsonr, jsonfr, csv) - json ignored");
} else {
pTpe->data.field.options.bJSON = 1;
}
} else if(!strcmp((char*)Buf, "jsonf")) {
if(hasFormat(pTpe)) {
LogError(0, NO_ERRCODE, "error: can only specify "
"one option out of (json, jsonf, jsonr, jsonfr, csv) - jsonf ignored");
} else {
pTpe->data.field.options.bJSONf = 1;
}
} else if(!strcmp((char*)Buf, "jsonr")) {
if(hasFormat(pTpe)) {
LogError(0, NO_ERRCODE, "error: can only specify "
"one option out of (json, jsonf, jsonr, jsonfr, csv) - jsonr ignored");
} else {
pTpe->data.field.options.bJSONr = 1;
}
} else if(!strcmp((char*)Buf, "jsonfr")) {
if(hasFormat(pTpe)) {
LogError(0, NO_ERRCODE, "error: can only specify "
"one option out of (json, jsonf, jsonr, jsonfr, csv) - jsonfr ignored");
} else {
pTpe->data.field.options.bJSONfr = 1;
}
} else if(!strcmp((char*)Buf, "mandatory-field")) {
pTpe->data.field.options.bMandatory = 1;
} else {
LogError(0, NO_ERRCODE, "template error: invalid field option '%s' "
"specified - ignored", Buf);
}
}
*pp = p;
}
/* helper to tplAddLine. Parses a parameter and generates
* the necessary structure.
*/
static rsRetVal
do_Parameter(uchar **pp, struct template *pTpl)
{
uchar *p;
cstr_t *pStrProp = NULL;
cstr_t *pStrField = NULL;
struct templateEntry *pTpe;
int iNum; /* to compute numbers */
#ifdef FEATURE_REGEXP
/* APR: variables for regex */
rsRetVal iRetLocal;
int longitud;
unsigned char *regex_char;
unsigned char *regex_end;
#endif
DEFiRet;
assert(pp != NULL);
assert(*pp != NULL);
assert(pTpl != NULL);
p = (uchar*) *pp;
CHKiRet(cstrConstruct(&pStrProp));
CHKmalloc(pTpe = tpeConstruct(pTpl));
pTpe->eEntryType = FIELD;
while(*p && *p != '%' && *p != ':') {
cstrAppendChar(pStrProp, *p);
++p;
}
/* got the name */
cstrFinalize(pStrProp);
CHKiRet(msgPropDescrFill(&pTpe->data.field.msgProp, cstrGetSzStrNoNULL(pStrProp),
cstrLen(pStrProp)));
/* Check frompos, if it has an R, then topos should be a regex */
if(*p == ':') {
pTpe->bComplexProcessing = 1;
++p; /* eat ':' */
#ifdef FEATURE_REGEXP
if(*p == 'R') {
/* APR: R found! regex alarm ! :) */
++p; /* eat ':' */
/* first come the regex type */
if(*p == ',') {
++p; /* eat ',' */
if(p[0] == 'B' && p[1] == 'R' && p[2] == 'E' && (p[3] == ',' || p[3] == ':')) {
pTpe->data.field.typeRegex = TPL_REGEX_BRE;
p += 3; /* eat indicator sequence */
} else if(p[0] == 'E' && p[1] == 'R' && p[2] == 'E' && (p[3] == ',' || p[3] == ':')) {
pTpe->data.field.typeRegex = TPL_REGEX_ERE;
p += 3; /* eat indicator sequence */
} else {
LogError(0, NO_ERRCODE, "error: invalid regular expression "
"type, rest of line %s", (char*) p);
}
}
/* now check for submatch ID */
pTpe->data.field.iSubMatchToUse = 0;
if(*p == ',') {
/* in this case a number follows, which indicates which match
* shall be used. This must be a single digit.
*/
++p; /* eat ',' */
if(isdigit((int) *p)) {
pTpe->data.field.iSubMatchToUse = *p - '0';
++p; /* eat digit */
}
}
/* now pull what to do if we do not find a match */
if(*p == ',') {
++p; /* eat ',' */
if(p[0] == 'D' && p[1] == 'F' && p[2] == 'L' && p[3] == 'T'
&& (p[4] == ',' || p[4] == ':')) {
pTpe->data.field.nomatchAction = TPL_REGEX_NOMATCH_USE_DFLTSTR;
p += 4; /* eat indicator sequence */
} else if(p[0] == 'B' && p[1] == 'L' && p[2] == 'A' && p[3] == 'N' && p[4] == 'K'
&& (p[5] == ',' || p[5] == ':')) {
pTpe->data.field.nomatchAction = TPL_REGEX_NOMATCH_USE_BLANK;
p += 5; /* eat indicator sequence */
} else if(p[0] == 'F' && p[1] == 'I' && p[2] == 'E' && p[3] == 'L' && p[4] == 'D'
&& (p[5] == ',' || p[5] == ':')) {
pTpe->data.field.nomatchAction = TPL_REGEX_NOMATCH_USE_WHOLE_FIELD;
p += 5; /* eat indicator sequence */
} else if(p[0] == 'Z' && p[1] == 'E' && p[2] == 'R' && p[3] == 'O'
&& (p[4] == ',' || p[4] == ':')) {
pTpe->data.field.nomatchAction = TPL_REGEX_NOMATCH_USE_ZERO;
p += 4; /* eat indicator sequence */
} else if(p[0] == ',') { /* empty, use default */
pTpe->data.field.nomatchAction = TPL_REGEX_NOMATCH_USE_DFLTSTR;
/* do NOT eat indicator sequence, as this was already eaten - the
* comma itself is already part of the next field.
*/
} else {
LogError(0, NO_ERRCODE, "template %s error: invalid regular "
"expression type, rest of line %s",
pTpl->pszName, (char*) p);
}
}
/* now check for match ID */
pTpe->data.field.iMatchToUse = 0;
if(*p == ',') {
/* in this case a number follows, which indicates which match
* shall be used. This must be a single digit.
*/
++p; /* eat ',' */
if(isdigit((int) *p)) {
pTpe->data.field.iMatchToUse = *p - '0';
++p; /* eat digit */
}
}
if(*p != ':') {
/* There is something more than an R , this is invalid ! */
/* Complain on extra characters */
LogError(0, NO_ERRCODE, "error: invalid character in frompos "
"after \"R\", property: '%%%s'", (char*) *pp);
} else {
pTpe->data.field.has_regex = 1;
dbgprintf("we have a regexp and use match #%d, submatch #%d\n",
pTpe->data.field.iMatchToUse, pTpe->data.field.iSubMatchToUse);
}
} else {
/* now we fall through the "regular" FromPos code */
#endif /* #ifdef FEATURE_REGEXP */
if(*p == 'F') {
#ifdef STRICT_GPLV3
pTpe->data.field.field_expand = 0;
#endif
/* we have a field counter, so indicate it in the template */
++p; /* eat 'F' */
if (*p == ':') {
/* no delimiter specified, so use the default (HT) */
pTpe->data.field.has_fields = 1;
pTpe->data.field.field_delim = 9;
} else if (*p == ',') {
++p; /* eat ',' */
/* configured delimiter follows, so we need to obtain
* it. Important: the following number must be the
* **DECIMAL** ASCII value of the delimiter character.
*/
pTpe->data.field.has_fields = 1;
if(!isdigit((int)*p)) {
/* complain and use default */
LogError(0, NO_ERRCODE, "error: invalid character in "
"frompos after \"F,\", property: '%%%s' - using 9 (HT) as field delimiter",
(char*) *pp);
pTpe->data.field.field_delim = 9;
} else {
iNum = 0;
while(isdigit((int)*p))
iNum = iNum * 10 + *p++ - '0';
if(iNum < 0 || iNum > 255) {
LogError(0, NO_ERRCODE, "error: non-USASCII delimiter "
"character value %d in template - using 9 (HT) as substitute", iNum);
pTpe->data.field.field_delim = 9;
} else {
pTpe->data.field.field_delim = iNum;
# ifdef STRICT_GPLV3
if (*p == '+') {
pTpe->data.field.field_expand = 1;
p ++;
}
# endif
if(*p == ',') { /* real fromPos? */
++p;
iNum = 0;
while(isdigit((int)*p))
iNum = iNum * 10 + *p++ - '0';
pTpe->data.field.iFromPos = iNum;
} else if(*p != ':') {
parser_errmsg("error: invalid character "
"'%c' in frompos after \"F,\", property: '%s' "
"be sure to use DECIMAL character "
"codes!", *p, (char*) *pp);
ABORT_FINALIZE(RS_RET_SYNTAX_ERROR);
}
}
}
} else {
/* invalid character after F, so we need to reject
* this.
*/
LogError(0, NO_ERRCODE, "error: invalid character in frompos "
"after \"F\", property: '%%%s'", (char*) *pp);
}
} else {
/* we now have a simple offset in frompos (the previously "normal" case) */
iNum = 0;
while(isdigit((int)*p))
iNum = iNum * 10 + *p++ - '0';
pTpe->data.field.iFromPos = iNum;
/* skip to next known good */
while(*p && *p != '%' && *p != ':') {