File: pmatch.c

package info (click to toggle)
sgrep 1.94a-4
  • links: PTS
  • area: main
  • in suites: bullseye, buster, jessie, jessie-kfreebsd, sid, squeeze, stretch, wheezy
  • size: 880 kB
  • ctags: 1,074
  • sloc: ansic: 10,566; sh: 3,433; makefile: 134
file content (723 lines) | stat: -rw-r--r-- 18,560 bytes parent folder | download | duplicates (6)
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
/*
	System: Structured text retrieval tool sgrep.
	Module: pmatch.c
	Author: Pekka Kilpel�inen & Jani Jaakkola
	Description: Pattern matching using Aho-Corasick automate (ACsearch() )
	Version history: Original version February 1995 by JJ & PK
	Copyright: University of Helsinki, Dept. of Computer Science
		   Distributed under GNU General Public Lisence
		   See file COPYING for details
*/

/* NOTE: Aho-Corasick automate can only take constant patterns. There is
         no wild card expansions and it's always case sensitive. Maybe
         something should be done about this.
*/

/*
 * NOTE: This module is used both by normal query engine and indexing
 * engine. query engine accesses this module through search().
 * Interface to indexer is a bit awkward: index.c calls index() function
 * to start scanning files and this module calls add_region_index() 
 * to add the newly found regions to index. This is a bit awkward and
 * possibly also somewhat (little?) inefficient.
 */


#include <stdio.h>
#include <string.h>
#include <ctype.h>

#define SGREP_LIBRARY
#include "sgrep.h"

/*
 * Private data structures
 */

/* Scanbuffer is for reading files */
struct ScanBuffer {
    SgrepData *sgrep;
    FileList *file_list;
    int len;
    int file_num;
    int old_file_num;
    int last_file;
    int region_start;
    const unsigned char *map;
    int map_size;
};


/* OutputList, ACState and ACScanner are for Aho-Corasick automate */
struct OutputList {
	struct PHRASE_NODE *phrase;
	struct OutputList *next;
};

struct ACState {
    struct ACState *gotos[256];
    struct ACState *fail;
    struct ACState *next; /* queue needed when creating fail function */
    struct OutputList *output_list;
#ifdef DEBUG
    int state_num;
#endif
};

struct ACScanner {
    SgrepData *sgrep;
    struct PHRASE_NODE *phrase_list; /* Points to this scanners phrase list */
    struct ACState *root_state; /* Points to root state */
    struct ACState *s;          /* Points to current state */
    int ignore_case;
} AC_scanner; /* THE AC_scanner, since only one is needed */


/*
 * Private prototypes
 */
void new_output( SgrepData *sgrep, struct ACState *s, 
			struct PHRASE_NODE *pn);
void ACsearch(struct ACScanner *scanner, const unsigned char *buf, 
	      int len, int start);
void enter(SgrepData *sgrep, struct PHRASE_NODE *pn, 
		  struct ACState *root_state, int ignore_case);
void create_fail(SgrepData *sgrep, struct ACState *root_state);
void create_goto(SgrepData *sgrep,struct PHRASE_NODE *phrase_list, 
			struct ACState *root_state,
			int ignore_case);

#ifdef DEBUG
void show_states(int depth,struct State_Data *s);
void show_ACtree();
void show_outputs(struct State_Data *s);
#endif



void print_scanner_help() {
    printf("      %-12s%s\n","sgml","use SGML scanner");
    printf("      %-12s%s\n","html","use HTML scanner (currently same as sgml scanner)");
    printf("      %-12s%s\n","xml","use XML scanner");
    printf("      %-12s%s\n","sgml-debug","show recognized SGML tokens");
    printf("      %-12s%s\n","include-entities","  automatically include system entities");
}

int set_scanner_option(SgrepData *sgrep,const char *a) {
    int i;
    char *arg=sgrep_strdup(a);
    for(i=0;arg[i];i++) arg[i]=tolower(arg[i]);

    if ( strcmp(arg,"sgml")==0 || 
	 strcmp(arg,"html")==0) {
	sgrep->scanner_type=SGML_SCANNER;
    } else if (strcmp(arg,"xml")==0) {
	sgrep->scanner_type=XML_SCANNER;
    } else if (strcmp(arg,"text")==0) {
	sgrep->scanner_type=TEXT_SCANNER;	
    } else if (strcmp(arg,"sgml-debug")==0) {
	sgrep->sgml_debug=1;
    } else if (strcmp(arg,"include-entities")==0) {
	sgrep->include_system_entities=1;
    } else if (strcmp(arg,"encoding=iso-8859-1")==0) {
	sgrep->default_encoding=ENCODING_8BIT;
    } else if (strcmp(arg,"encoding=utf8")==0) {
	sgrep->default_encoding=ENCODING_UTF8;
    } else if (strcmp(arg,"encoding=utf16")==0) {
	sgrep->default_encoding=ENCODING_UTF16;
    } else {
	sgrep_error(sgrep,"Unknown scanner argument '%s'\n",arg);
	sgrep_free(arg);
	return SGREP_ERROR;
    }
    sgrep_free(arg);
    return SGREP_OK;
}

/*
 * Creates and initializes a new scanner buffer struct with given
 * input files
 */
struct ScanBuffer *new_scan_buffer(SgrepData *sgrep,FileList *files) {
    struct ScanBuffer *sc;
    sc=sgrep_new(struct ScanBuffer);
    sc->sgrep=sgrep;
    sc->file_list=files;
    sc->len=0;
    sc->file_num=0;
    sc->old_file_num=-1;
    sc->last_file=-1; /* As many files there is in list */
    sc->region_start=0;
    sc->map=NULL;
    sc->map_size=0;
    return sc;
}

struct ScanBuffer *reset_scan_buffer(struct ScanBuffer *sc, 
				     int f_file, int l_file) {
    sc->file_num=f_file;
    sc->last_file=l_file;
    sc->region_start=flist_start(sc->file_list,f_file);
    return sc;
}


void delete_scan_buffer(struct ScanBuffer *b) {
    SgrepData *sgrep=b->sgrep;
    sgrep_free(b);
}

/*
 * Fills the scanner input buffer and sets len and file_num respectively
 * if all files have been processed returns 0
 * otherwise returns number of bytes available in buffer
 * NEW: uses map_file() instead of read()
 */
int next_scan_buffer(struct ScanBuffer *sb)
{
    SGREPDATA(sb);
    if (sb->map && sb->len==sb->map_size) {
	sb->file_num++;
    }
    /* Skip zero length files */
    while(sb->file_num<flist_files(sb->file_list) &&
	  flist_length(sb->file_list,sb->file_num)==0) {
	sb->file_num++;
    }
    if (sb->old_file_num!=sb->file_num && sb->map) {
	unmap_file(sgrep,(void *)sb->map,sb->map_size);
	sb->map=NULL;
	sb->map_size=0;
    }
    if ( (sb->last_file==-1 && sb->file_num>=flist_files(sb->file_list)) ||
	 (sb->last_file>=0 && sb->file_num>sb->last_file) ) {
	/* All files scanned */
	return 0;
    }
    if (!sb->map) {
	void *map;
	sb->map_size=map_file(sgrep,flist_name(sb->file_list,sb->file_num),
			      &map);
	sb->map=(const unsigned char*)map;
    }
    if (sb->map==NULL) {
	sgrep_error(sgrep,"Failed to scan file '%s'\n",
		    flist_name(sb->file_list,sb->file_num));
	return SGREP_ERROR;
    }
    sb->old_file_num=sb->file_num;
    if (sb->map_size!=flist_length(sb->file_list,sb->file_num)) {
	sgrep_error(sgrep,"Size of file '%s' has changed\n",
		    flist_name(sb->file_list,sb->file_num));
    }
    sb->region_start+=sb->len;
    sb->len=sb->map_size;
    return sb->len;
}
		
/*
 * Gives and inits a new state to the automate.
 */
/* If root_state is NULL
 * it inits the root_state 
 */
struct ACState *new_state(SgrepData *sgrep)
{
	int i;
	struct ACState *s;
#ifdef DEBUG
	static int snum;
#endif
	s=(struct ACState *)sgrep_malloc( sizeof(struct ACState));
	for (i=0;i<256;i++) s->gotos[i]=NULL;
	s->output_list=NULL;
	s->next=NULL;
	s->fail=NULL;
#ifdef DEBUG
	snum++;
	s->state_num=snum;
#endif
	return s;
}

/*
 * Enters a new output link to a state 
 */
void new_output(SgrepData *sgrep, struct ACState *s, struct PHRASE_NODE *pn)
{
	struct OutputList **op;

	op=&s->output_list;
	while (*op!=NULL) op=& (*op)->next;
	*op=sgrep_new(struct OutputList);
	(*op)->next=NULL;
	(*op)->phrase=pn;
}

/*
 * Enters a new phrase to automate given with root_state
 */
void enter(SgrepData *sgrep, struct PHRASE_NODE *pn, 
	   struct ACState *root_state,
	   int ignore_case)
{
	struct ACState *state=root_state;
	size_t j;
	unsigned char pch;

#ifdef DEBUG
	printf("enter %s",str);
#endif
	assert(pn->phrase->s[0]=='n');
	j=1;
	pch=pn->phrase->s[j];
	if (ignore_case) pch=toupper(pch);
	while ( state->gotos[pch]!=NULL && j<pn->phrase->length )
	{
		state=state->gotos[pch];
		j++;
		pch=pn->phrase->s[j];
		if (ignore_case) pch=toupper(pch);
	}
	
	while( j<pn->phrase->length )
	{
		state->gotos[pch]=new_state(sgrep);
		state=state->gotos[pch];
		j++;
		pch=pn->phrase->s[j];
		if (ignore_case) pch=toupper(pch);
	}
	new_output(sgrep,state,pn);
#ifdef DEBUG
	printf(" done\n");
#endif
}
	
/*
 * The creation of the AC goto function using the enter function 
 * and the phrase list. 
 * The automate is spesified with root_state
 */
void create_goto(SgrepData *sgrep, struct PHRASE_NODE *phrase_list,
		 struct ACState *root_state,
		 int ignore_case)
{
	struct PHRASE_NODE *pn;

	for(pn=phrase_list;pn!=NULL;pn=pn->next) {
	    if (pn->phrase->s[0]=='n') {
		/* Add only AC phrases to automate */
#if DEBUG
		fprintf(stderr,"AC phrase:%s\n",lpn->phrase->s);
#endif		
		enter(sgrep,pn,root_state,ignore_case);
	    }
	}
}

/*
 * The creation of the AC fail function and the final output function 
 * The automate to use is given with root_state
 */
void create_fail(SgrepData *sgrep,struct ACState *root_state) 
{
	int i;
	struct ACState *s,*r,*state;
	struct ACState *first=NULL;
	struct ACState *last=NULL;	
	struct OutputList *op;
	
#ifdef DEBUG
	printf("Create fail :");
#endif	
	for (i=0;i<256;i++)
	{
		if ( (s=root_state->gotos[i]) !=root_state )
		{		
			if (first==NULL) first=s;
			if (last!=NULL) last->next=s;
			last=s;
			last->next=NULL;
			s->fail=root_state;
		}
	}
#ifdef DEBUG
	printf(" root done");
#endif
	while (first!=NULL)
	{
		r=first;
		first=first->next;
		for (i=0;i<256;i++) if ( r->gotos[i]!=NULL )
		{
			s=r->gotos[i];
			last->next=s;
			last=s;
			last->next=NULL;
			if (first==NULL) first=last;
			state=r->fail;
			while (state->gotos[i]==NULL) state=state->fail;
			s->fail=state->gotos[i];
			for (op=s->fail->output_list;
			     op!=NULL;
			     op=op->next) {
			    assert(op->phrase!=NULL);
			    new_output(sgrep,s,op->phrase);
			}
		}
	}
#ifdef DEBUG
	printf(", all done\n");
#endif
}

/* Phrases list points to list of phrases to be
 * matched. ifs points to names of input files, and lf is the number of
 * input files.
 */
struct ACScanner *init_AC_search(SgrepData *sgrep,
				 struct PHRASE_NODE *phrase_list) {
    int i;
    struct ACScanner *sc;

    sc=sgrep_new(struct ACScanner);
    sc->sgrep=sgrep;
    sc->root_state=new_state(sgrep);
    sc->phrase_list=phrase_list;
    sc->s=sc->root_state;
    sc->ignore_case=sgrep->ignore_case;
    create_goto(sgrep,phrase_list,sc->root_state,sc->ignore_case);
    /* there isn't any fail links from root state */
    for (i=0;i<256;i++) {
	if (sc->root_state->gotos[i]==NULL) 
	    sc->root_state->gotos[i]=sc->root_state;
    }
    create_fail(sgrep,sc->root_state);
    return sc;
}

void delete_AC_state(SgrepData *sgrep,struct ACState *as) {
    int i;
    for(i=0;i<256;i++) {
	if (as->gotos[i] && as->gotos[i]!=as) {
	    delete_AC_state(sgrep,as->gotos[i]);
	}
	while(as->output_list) {
	    struct OutputList *ol=as->output_list;
	    as->output_list=as->output_list->next;
	    sgrep_free(ol);
	}
    }
    sgrep_free(as);
}
	
void delete_AC_scanner(struct ACScanner *ac) {
    /* FIXME: this leaks memory! */
    SGREPDATA(ac);
    delete_AC_state(sgrep,ac->root_state);
    sgrep_free(ac);
}


/* 
 * The AC automate search. 
 * (A dramatically simpler version, than which it used to be four years
 *  ago when it first saw the light of the day.
 *  It seems that i've actually gained some "programming experience"
 *  in these years :) 
 */
void ACsearch(struct ACScanner *scanner, const unsigned char *buf, 
	      int len, int start)
{
    struct OutputList *op;
    int ch;
    int i;
    struct ACState *s;

    s=scanner->s;
    for(i=0;i<len;i++) {
	ch=(scanner->ignore_case) ? toupper(buf[i]) : buf[i];
	while (s->gotos[ch]==NULL) {
	    assert(s->fail);
	    s=s->fail;
	}	
	s=s->gotos[ch];
	op=s->output_list;
	while(op!=NULL) {
	    scanner->sgrep->statistics.phrases++;
	    assert(op->phrase->regions!=NULL);
	    add_region( op->phrase->regions,
			i-(op->phrase->phrase->length-1)+start+1,
			i+start);
#ifdef DEBUG
	    printf("Found \"%s\" in file %s at %d  gc<-(%d,%d)\n",
		   op->phrase->phrase->s,
		   file_list->files[file_num].name,
		   file_pos-buf_end+buf_pos-(op->phrase->phrase->length),
		   i- ( op->phrase->phrase->length ) , i-1);
#endif
	    op=op->next;
	} while ( op!=NULL );
    }
    scanner->s=s;
}


int search(SgrepData *sgrep,struct PHRASE_NODE *phrase_list, FileList *files, 
	   int f_file, int l_file) {
    int sgml_phrases;
    int regex_phrases;
    int ac_phrases;
    int file_phrases;
    int e=SGREP_OK;
    int previous_file=-1;

    /* If there is no phrases, there is no point to do searching */
    if (phrase_list==NULL) {
	sgrep_progress(sgrep,"No phrases. Skipping search\n");
	return SGREP_OK;
    }
    if (sgrep->index_file==NULL) {
	struct ScanBuffer *sb=NULL;
	struct ACScanner *acs=NULL;
	SGMLScanner *sgmls=NULL;
	struct PHRASE_NODE *j=NULL;

	file_phrases=ac_phrases=sgml_phrases=regex_phrases=0;

	/* We have to create empty gc lists for phrases */
	for (j=phrase_list;j!=NULL;j=j->next)
	{
	    assert(j->regions==NULL);
	    j->regions=new_region_list(sgrep);
	    if (j->phrase->s[0]=='@' ||
		j->phrase->s[0]=='*') {
		list_set_sorted(j->regions,NOT_SORTED);
		j->regions->nested=1;
	    }
	    
	    switch (j->phrase->s[0]) {
	    case 'n':
		ac_phrases++;
		break;
	    case 'r':
		regex_phrases++;
		break;
	    case 'f':
		file_phrases++;
		break;
	    case '#':
		/* Input independent phrases */
		break;
	    default:
		sgml_phrases++;
	    }	
	}

	/* Initialization */
	sb=new_scan_buffer(sgrep,files);
	reset_scan_buffer(sb,f_file,l_file);
	if (ac_phrases) {
	    acs=init_AC_search(sgrep,phrase_list);
	}
	if (sgml_phrases) {
	    sgmls=new_sgml_phrase_scanner(sgrep,files,phrase_list);
	}
	
	/* Main scanning loop, only if there is something to scan */
	if (acs || sgmls) while((e=next_scan_buffer(sb))>0) {
	    if (flist_files(files)>1) {
		sgrep_progress(sgrep,"Scanning %d/%d files %d/%dK (%d%%)\n",
			       sb->file_num,flist_files(files),
			       sb->region_start/1024,flist_total(files)/1024,
			       sb->region_start/(flist_total(files)/100+1));
	    } else {
		sgrep_progress(sgrep,"Scanning file '%s' %d/%dK (%d%%)\n",
			       flist_name(sb->file_list,sb->file_num),
			       sb->region_start/1024,flist_total(files)/1024,
			       sb->region_start/(flist_total(files)/100+1));
	    }		    
	    if (sgrep->progress_callback) {
		sgrep->progress_callback(sgrep->progress_data,
					 sb->file_num,flist_files(files),
					 sb->region_start,flist_total(files)); 
	    }			     	    
	    if (ac_phrases) {
		ACsearch(acs,sb->map,sb->len,sb->region_start);
	    }
	    if (sgml_phrases) {
		if (previous_file!=-1 && sb->file_num!=previous_file) {
		    sgml_flush(sgmls);
		}
		previous_file=sb->file_num;
		sgml_scan(sgmls,sb->map,sb->len,sb->region_start,sb->file_num);
	    }
	}
#if 0
	/* FIXME: think this over */
	if (sgmls && sgmls->parse_errors>0) {
	    fprintf(stderr,"There was %d SGML parse errors\n",
		    sgmls->parse_errors);
	}
#endif
	/* Clean up scanners */
	delete_scan_buffer(sb);
	if (sgmls) {
	    sgml_flush(sgmls);
	    delete_sgml_scanner(sgmls);
	}	
	if (acs) delete_AC_scanner(acs);

	/* Now handle the phrases, whose contents we know only after
	 * scanning or which are independent of scanning */
	/* FIXME and include-entities will break this */
	for(j=phrase_list;j!=NULL; j=j->next) {

	    switch(j->phrase->s[0]) {

	    case '#':
		if (strcmp(j->phrase->s,"#start")==0) {
		    int start=flist_start(files,f_file);
		    add_region(j->regions,start,start);
		} else if (strcmp(j->phrase->s,"#end")==0) {
		    int last=flist_start(files,l_file)+
			flist_length(files,l_file)-1;
		    add_region(j->regions,last,last);
		} else {
		    sgrep_error(sgrep,"Don't know how to handle phrase %s\n",
				j->phrase->s);
		}
		break;
		
	    case 'f': {
		int f;	       
		for(f=f_file;f<=l_file;f++) {
		    /* Check for filename */
		    if (j->phrase->s[j->phrase->length-1]=='*') {
			/* Wildcard */
			if (strncmp((char *)j->phrase->s+1,flist_name(files,f),
				    j->phrase->length-2)==0 &&
			    flist_length(files,f)>0) {
			    add_region(j->regions,
				       flist_start(files,f),
				       flist_start(files,f)+
				       flist_length(files,f)-1);
			}
		    } else if (strcmp((char *)j->phrase->s+1,
				      flist_name(files,f))==0 &&
			       flist_length(files,f)>0) {
			add_region(j->regions,
				   flist_start(files,f),
				   flist_start(files,f)+
				   flist_length(files,f)-1);
		    }
		}
	    }
	    break;
	    }
	}
    } else {
	sgrep_progress(sgrep,"Using lazy index file mode\n"); 
	e=SGREP_OK;
    }
    return (e==SGREP_ERROR) ? SGREP_ERROR:SGREP_OK;
}

/* FIXME: merge this better with search() */
int index_search(SgrepData *sgrep,struct IndexWriterStruct *writer,
		  FileList *files) {
    struct ScanBuffer *sb;
    int previous_file=-1;
    SGMLScanner *sgmls;

    sb=new_scan_buffer(sgrep,files);
    sgmls=new_sgml_index_scanner(sgrep,files,writer);
    while(next_scan_buffer(sb)>0) {
	if (previous_file!=-1 && sb->file_num!=previous_file) {
	    sgml_flush(sgmls);
	}
	previous_file=sb->file_num;
	sgrep_progress(sgrep,"Indexing file %d/%d '%s' %d/%dK (%d%%)\n",
		      sb->file_num+1,flist_files(files),
		       flist_name(files,sb->file_num),
		      sb->region_start/1024,flist_total(files)/1024,
		      sb->region_start/(flist_total(files)/100+1));	
	if (sgrep->progress_callback) {
	    sgrep->progress_callback(sgrep->progress_data,
				     sb->file_num,flist_files(files),
				     sb->region_start,flist_total(files)); 
	}
	if (sgml_scan(sgmls,sb->map,sb->len,sb->region_start,sb->file_num)
	    ==SGREP_ERROR) {
	    delete_scan_buffer(sb);
	    delete_sgml_scanner(sgmls);
	    return SGREP_ERROR;
	}
    }
    sgml_flush(sgmls);
    delete_scan_buffer(sb);
    delete_sgml_scanner(sgmls);
    return SGREP_OK;
}


#ifdef DEBUG
/*
 * These are (were) used for debugging the creation of ac-automate
 */
void show_ACtree()
{
	printf("-------------------\n AC-tree\n------------------\n");
	show_states(0,root_state);
	show_outputs(root_state); 
}

void show_states(int depth,struct State_Data *s)
{
	int end=0;
	int i,j;
	
	for(i=0;i<256;i++)
	{
		if (s->gotos[i]!=NULL && 
		   !( s==root_state && s->gotos[i]==root_state ) )
		{
			if (end>0)
			for (j=0;j<depth;j++) printf("                ");
			printf("%2d:f=%2d:",s->state_num,s->fail->state_num);
			end++;
			printf("%c->%2d , ",i,s->gotos[i]->state_num);
			show_states(depth+1,s->gotos[i]);
		}
	}
	if (!end)
	{
		printf("%2d:f=%2d <---\n",s->state_num,s->fail->state_num);
	}
}

void show_outputs(struct State_Data *s)
{
	int i;
	struct OutPut *op;
	
	op=&s->out_list;
	if (op->phrase!=NULL)
	{
		printf("state %d:",s->state_num);
		do {
			printf(" %s",op->phrase->phrase->s);
			op=op->next;
		} while ( op!=NULL );
		printf("\n");
	}
	
	for (i=0;i<256;i++)
	{
		if (s->gotos[i]!=NULL && s->gotos[i]!=root_state )
			show_outputs(s->gotos[i]);
	}
}		
#endif