summaryrefslogtreecommitdiffstats
path: root/ctok.c
blob: 3d0b55f778d8ddd1e9dd16c3ead43aac620b9973 (plain)
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
/* cfgtok.c - helper class to tokenize an input stream - which surprisingly
 * currently does not work with streams but with string. But that will
 * probably change over time ;) This class was originally written to support
 * the expression module but may evolve when (if) the expression module is
 * expanded (or aggregated) by a full-fledged ctoken based config parser.
 * Obviously, this class is used together with config files and not any other
 * parse function.
 *
 * Module begun 2008-02-19 by Rainer Gerhards
 *
 * Copyright 2008 Rainer Gerhards and Adiscon GmbH.
 *
 * This file is part of rsyslog.
 *
 * Rsyslog 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 3 of the License, or
 * (at your option) any later version.
 *
 * Rsyslog 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.
 *
 * You should have received a copy of the GNU General Public License
 * along with Rsyslog.  If not, see <http://www.gnu.org/licenses/>.
 *
 * A copy of the GPL can be found in the file "COPYING" in this distribution.
 */

#include "config.h"
#include <stdlib.h>
#include <ctype.h>
#include <strings.h>
#include <assert.h>

#include "rsyslog.h"
#include "template.h"
#include "ctok.h"

/* static data */
DEFobjStaticHelpers


/* Standard-Constructor
 */
BEGINobjConstruct(ctok) /* be sure to specify the object type also in END macro! */
ENDobjConstruct(ctok)


/* ConstructionFinalizer
 * rgerhards, 2008-01-09
 */
rsRetVal ctokConstructFinalize(ctok_t __attribute__((unused)) *pThis)
{
	DEFiRet;
	RETiRet;
}


/* destructor for the ctok object */
BEGINobjDestruct(ctok) /* be sure to specify the object type also in END and CODESTART macros! */
CODESTARTobjDestruct(ctok)
	/* ... then free resources */
ENDobjDestruct(ctok)


/* unget character from input stream. At most one character can be ungotten.
 * This funtion is only permitted to be called after at least one character
 * has been read from the stream. Right now, we handle the situation simply by
 * moving the string "stream" pointer one position backwards. If we work with
 * real streams (some time), the strm object will handle the functionality
 * itself. -- rgerhards, 2008-02-19
 */
static rsRetVal
ctokUngetCharFromStream(ctok_t *pThis, uchar __attribute__((unused)) c)
{
	DEFiRet;

	ISOBJ_TYPE_assert(pThis, ctok);
	--pThis->pp;

	RETiRet;
}


/* get the next character from the input "stream" (currently just a in-memory
 * string...) -- rgerhards, 2008-02-19
 */
static rsRetVal 
ctokGetCharFromStream(ctok_t *pThis, uchar *pc)
{
	DEFiRet;

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(pc != NULL);

	/* end of string or begin of comment terminates the "stream" */
	if(*pThis->pp == '\0' || *pThis->pp == '#') {
		ABORT_FINALIZE(RS_RET_EOS);
	} else {
		*pc = *pThis->pp;
		++pThis->pp;
	}

finalize_it:
	RETiRet;
}


/* skip whitespace in the input "stream".
 * rgerhards, 2008-02-19
 */
static rsRetVal 
ctokSkipWhitespaceFromStream(ctok_t *pThis)
{
	DEFiRet;
	uchar c;

	ISOBJ_TYPE_assert(pThis, ctok);

	CHKiRet(ctokGetCharFromStream(pThis, &c));
	while(isspace(c)) {
		CHKiRet(ctokGetCharFromStream(pThis, &c));
	}

	/* we must unget the one non-whitespace we found */
	CHKiRet(ctokUngetCharFromStream(pThis, c));

dbgprintf("skipped whitepsace, stream now '%s'\n", pThis->pp);
finalize_it:
	RETiRet;
}


/* get the next word from the input "stream" (currently just a in-memory
 * string...). A word is anything from the current location until the
 * first non-alphanumeric character. If the word is longer
 * than the provided memory buffer, parsing terminates when buffer length
 * has been reached. A buffer of 128 bytes or more should always be by
 * far sufficient. -- rgerhards, 2008-02-19
 */
static rsRetVal 
ctokGetWordFromStream(ctok_t *pThis, uchar *pWordBuf, size_t lenWordBuf)
{
	DEFiRet;
	uchar c;

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(pWordBuf != NULL);
	ASSERT(lenWordBuf > 0);

	CHKiRet(ctokSkipWhitespaceFromStream(pThis));

	CHKiRet(ctokGetCharFromStream(pThis, &c));
	while(isalnum(c) && lenWordBuf > 1) {
		*pWordBuf++ = c;
		--lenWordBuf;
		CHKiRet(ctokGetCharFromStream(pThis, &c));
	}
	*pWordBuf = '\0'; /* there is always space for this - see while() */

	/* push back the char that we have read too much */
	CHKiRet(ctokUngetCharFromStream(pThis, c));

dbgprintf("end ctokGetWordFromStream, stream now '%s'\n", pThis->pp);
finalize_it:
	RETiRet;
}


/* read in a constant number
 * This is the "number" ABNF element
 * rgerhards, 2008-02-19
 */
static rsRetVal
ctokGetNumber(ctok_t *pThis, ctok_token_t *pToken)
{
	DEFiRet;
	int64 n; /* the parsed number */
	uchar c;
	int valC;
	int iBase;

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(pToken != NULL);

	pToken->tok = ctok_NUMBER;

	CHKiRet(ctokGetCharFromStream(pThis, &c));
	if(c == '0') { /* octal? */
		CHKiRet(ctokGetCharFromStream(pThis, &c));
		if(c == 'x') { /* nope, hex! */
			CHKiRet(ctokGetCharFromStream(pThis, &c));
			c = tolower(c);
			iBase = 16;
		} else {
			iBase = 8;
		}
	} else {
		iBase = 10;
	}
		
	n = 0;
	/* this loop is quite simple, a variable name is terminated by whitespace. */
	while(isdigit(c) || (c >= 'a' && c <= 'f')) {
		if(isdigit(c)) {
			valC = c - '0';
		} else {
			valC = c - 'a' + 10;
		}
		
		if(valC >= iBase) {
			if(iBase == 8) {
				ABORT_FINALIZE(RS_RET_INVALID_OCTAL_DIGIT);
			} else {
				ABORT_FINALIZE(RS_RET_INVALID_HEX_DIGIT);
			}
		}
		/* we now have the next value and know it is right */
		n = n * iBase + valC;
		CHKiRet(ctokGetCharFromStream(pThis, &c));
		c = tolower(c);
	}
	pToken->intVal = n;

dbgprintf("number, number is: '%lld'\n", pToken->intVal);

finalize_it:
	RETiRet;
}


/* read in a variable
 * This covers both msgvar and sysvar from the ABNF.
 * rgerhards, 2008-02-19
 */
static rsRetVal
ctokGetVar(ctok_t *pThis, ctok_token_t *pToken)
{
	DEFiRet;
	uchar c;

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(pToken != NULL);

	CHKiRet(ctokGetCharFromStream(pThis, &c));

	if(c == '$') { /* second dollar, we have a system variable */
		pToken->tok = ctok_SYSVAR;
		CHKiRet(ctokGetCharFromStream(pThis, &c)); /* "eat" it... */
	} else {
		pToken->tok = ctok_MSGVAR;
	}

	CHKiRet(rsCStrConstruct(&pToken->pstrVal));
	/* this loop is quite simple, a variable name is terminated by whitespace. */
	while(!isspace(c)) {
		CHKiRet(rsCStrAppendChar(pToken->pstrVal, tolower(c)));
		CHKiRet(ctokGetCharFromStream(pThis, &c));
	}
	CHKiRet(rsCStrFinish(pStrB));

dbgprintf("var, var is: '%s'\n", rsCStrGetSzStr(pToken->pstrVal));

finalize_it:
	if(iRet != RS_RET_OK) {
		if(pToken->pstrVal != NULL) {
			rsCStrDestruct(&pToken->pstrVal);
		}
	}

	RETiRet;
}


/* read in a simple string (simpstr in ABNF)
 * rgerhards, 2008-02-19
 */
static rsRetVal
ctokGetSimpStr(ctok_t *pThis, ctok_token_t *pToken)
{
	DEFiRet;
	uchar c;
	int bInEsc = 0;

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(pToken != NULL);

	pToken->tok = ctok_SIMPSTR;

	CHKiRet(rsCStrConstruct(&pToken->pstrVal));
	CHKiRet(ctokGetCharFromStream(pThis, &c));
	/* while we are in escape mode (had a backslash), no sequence
	 * terminates the loop. If outside, it is terminated by a single quote.
	 */
	while(bInEsc || c != '\'') {
		if(bInEsc) {
			CHKiRet(rsCStrAppendChar(pToken->pstrVal, c));
			bInEsc = 0;
		} else {
			if(c == '\\') {
				bInEsc = 1;
			} else {
				CHKiRet(rsCStrAppendChar(pToken->pstrVal, c));
			}
		}
		CHKiRet(ctokGetCharFromStream(pThis, &c));
	}
	CHKiRet(rsCStrFinish(pStrB));

dbgprintf("simpstr, str is: '%s'\n", rsCStrGetSzStr(pToken->pstrVal));

finalize_it:
	if(iRet != RS_RET_OK) {
		if(pToken->pstrVal != NULL) {
			rsCStrDestruct(&pToken->pstrVal);
		}
	}

	RETiRet;
}


/* Unget a token. The token ungotten will be returned the next time
 * ctokGetToken() is called. Only one token can be ungotten at a time.
 * If a second token is ungotten, the first is lost. This is considered
 * a programming error.
 * rgerhards, 2008-02-20
 */
rsRetVal
ctokUngetToken(ctok_t *pThis, ctok_token_t *pToken)
{
	DEFiRet;

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(pToken != NULL);
	ASSERT(pThis->pUngotToken == NULL);

	pThis->pUngotToken = pToken;

	RETiRet;
}


/* skip an inine comment (just like a C-comment) 
 * rgerhards, 2008-02-20
 */
static rsRetVal
ctokSkipInlineComment(ctok_t *pThis)
{
	DEFiRet;
	uchar c;
	int bHadAsterisk = 0;

	ISOBJ_TYPE_assert(pThis, ctok);

	CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
	while(!(bHadAsterisk && c == '/')) {
		bHadAsterisk = (c == '*') ? 1 : 0;
		CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read next */
	}

finalize_it:
	RETiRet;
}



/* Get the *next* token from the input stream. This parses the next token and
 * ignores any whitespace in between. End of stream is communicated via iRet.
 * The returned token must either be destructed by the caller OR being passed
 * back to ctokUngetToken().
 * rgerhards, 2008-02-19
 */
rsRetVal
ctokGetToken(ctok_t *pThis, ctok_token_t **ppToken)
{
	DEFiRet;
	ctok_token_t *pToken;
	uchar c;
	uchar szWord[128];
	int bRetry = 0; /* retry parse? Only needed for inline comments... */

	ISOBJ_TYPE_assert(pThis, ctok);
	ASSERT(ppToken != NULL);

	/* first check if we have an ungotten token and, if so, provide that
	 * one back (without any parsing). -- rgerhards, 2008-02-20
	 */
	if(pThis->pUngotToken != NULL) {
		*ppToken = pThis->pUngotToken;
		pThis->pUngotToken = NULL;
		FINALIZE;
	}

	/* setup the stage - create our token */
	CHKiRet(ctok_tokenConstruct(&pToken));
	CHKiRet(ctok_tokenConstructFinalize(pToken));

	/* find the next token. We may loop when we have inline comments */
	do {
		bRetry = 0;
		CHKiRet(ctokSkipWhitespaceFromStream(pThis));
		CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
		switch(c) {
			case '=': /* == */
				CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
				pToken->tok = (c == '=')? ctok_CMP_EQ : ctok_INVALID;
				break;
			case '!': /* != */
				CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
				pToken->tok = (c == '=')? ctok_CMP_NEQ : ctok_INVALID;
				break;
			case '<': /* <, <=, <> */
				CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
				if(c == '=') {
					pToken->tok = ctok_CMP_LTEQ;
				} else if(c == '>') {
					pToken->tok = ctok_CMP_NEQ;
				} else {
					pToken->tok = ctok_CMP_LT;
				}
				break;
			case '>': /* >, >= */
				CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
				if(c == '=') {
					pToken->tok = ctok_CMP_GTEQ;
				} else {
					pToken->tok = ctok_CMP_GT;
				}
				break;
			case '+':
				pToken->tok = ctok_PLUS;
				break;
			case '-':
				pToken->tok = ctok_MINUS;
				break;
			case '*':
				pToken->tok = ctok_TIMES;
				break;
			case '/': /* /, /.* ... *./ (comments, mungled here for obvious reasons...) */
				CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
				if(c == '*') {
					/* we have a comment and need to skip it */
					ctokSkipInlineComment(pThis);
					bRetry = 1;
				} else {
					CHKiRet(ctokUngetCharFromStream(pThis, c)); /* put back, not processed */
				}
				pToken->tok = ctok_DIV;
				break;
			case '%':
				pToken->tok = ctok_MOD;
				break;
			case '(':
				pToken->tok = ctok_LPAREN;
				break;
			case ')':
				pToken->tok = ctok_RPAREN;
				break;
			case ',':
				pToken->tok = ctok_COMMA;
				break;
			case '$':
				CHKiRet(ctokGetVar(pThis, pToken));
				break;
			case '\'': /* simple string, this is somewhat more elaborate */
				CHKiRet(ctokGetSimpStr(pThis, pToken));
				break;
			case '"':
				/* TODO: template string parser */
				ABORT_FINALIZE(RS_RET_NOT_IMPLEMENTED);
				break;
			default:
				CHKiRet(ctokUngetCharFromStream(pThis, c)); /* push back, we need it in any case */
				if(isdigit(c)) {
					CHKiRet(ctokGetNumber(pThis, pToken));
				} else { /* now we check if we have a multi-char sequence */
					CHKiRet(ctokGetWordFromStream(pThis, szWord, sizeof(szWord)/sizeof(uchar)));
					if(!strcasecmp((char*)szWord, "and")) {
						pToken->tok = ctok_AND;
					} else if(!strcasecmp((char*)szWord, "or")) {
						pToken->tok = ctok_OR;
					} else if(!strcasecmp((char*)szWord, "not")) {
						pToken->tok = ctok_NOT;
					} else if(!strcasecmp((char*)szWord, "then")) {
						pToken->tok = ctok_THEN;
					} else {
						/* finally, we check if it is a function */
						CHKiRet(ctokGetCharFromStream(pThis, &c)); /* read a charater */
						if(c == '(') {
							/* push c back, higher level parser needs it */
							CHKiRet(ctokUngetCharFromStream(pThis, c));
							pToken->tok = ctok_FUNCTION;
							// TODO: fill function name
						} else { /* give up... */
							pToken->tok = ctok_INVALID;
						}
					}
				}
				break;
		}
	} while(bRetry); /* warning: do ... while()! */

	*ppToken = pToken;
RUNLOG_VAR("%d", pToken->tok);

finalize_it:
	if(iRet != RS_RET_OK) {
		if(pToken != NULL)
			ctok_tokenDestruct(&pToken);
	}

	RETiRet;
}


/* property set methods */
/* simple ones first */
DEFpropSetMeth(ctok, pp, uchar*)

/* return the current position of pp - most important as currently we do only
 * partial parsing, so the rest must know where to start from...
 * rgerhards, 2008-02-19
 */
rsRetVal
ctokGetpp(ctok_t *pThis, uchar **pp)
{
	DEFiRet;
	ASSERT(pp != NULL);
	*pp = pThis->pp;
	RETiRet;
}

BEGINObjClassInit(ctok, 1) /* class, version */
	OBJSetMethodHandler(objMethod_CONSTRUCTION_FINALIZER, ctokConstructFinalize);
ENDObjClassInit(ctok)

/* vi:set ai:
 */