summaryrefslogtreecommitdiff
path: root/dviware/umddvi/libcompat/regex.c
blob: 73c1e0cf7378071f6e8ff96dea0535367e4dec55 (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
/*
 * Copyright (c) 1980 Regents of the University of California.
 * All rights reserved.  The Berkeley software License Agreement
 * specifies the terms and conditions for redistribution.
 */

#if defined(LIBC_SCCS) && !defined(lint)
static char sccsid[] = "@(#)regex.c	5.2 (Berkeley) 3/9/86";
#endif LIBC_SCCS and not lint

#

/*
 * routines to do regular expression matching
 *
 * Entry points:
 *
 *	re_comp(s)
 *		char *s;
 *	 ... returns 0 if the string s was compiled successfully,
 *		     a pointer to an error message otherwise.
 *	     If passed 0 or a null string returns without changing
 *           the currently compiled re (see note 11 below).
 *
 *	re_exec(s)
 *		char *s;
 *	 ... returns 1 if the string s matches the last compiled regular
 *		       expression, 
 *		     0 if the string s failed to match the last compiled
 *		       regular expression, and
 *		    -1 if the compiled regular expression was invalid 
 *		       (indicating an internal error).
 *
 * The strings passed to both re_comp and re_exec may have trailing or
 * embedded newline characters; they are terminated by nulls.
 *
 * The identity of the author of these routines is lost in antiquity;
 * this is essentially the same as the re code in the original V6 ed.
 *
 * The regular expressions recognized are described below. This description
 * is essentially the same as that for ed.
 *
 *	A regular expression specifies a set of strings of characters.
 *	A member of this set of strings is said to be matched by
 *	the regular expression.  In the following specification for
 *	regular expressions the word `character' means any character but NUL.
 *
 *	1.  Any character except a special character matches itself.
 *	    Special characters are the regular expression delimiter plus
 *	    \ [ . and sometimes ^ * $.
 *	2.  A . matches any character.
 *	3.  A \ followed by any character except a digit or ( )
 *	    matches that character.
 *	4.  A nonempty string s bracketed [s] (or [^s]) matches any
 *	    character in (or not in) s. In s, \ has no special meaning,
 *	    and ] may only appear as the first letter. A substring 
 *	    a-b, with a and b in ascending ASCII order, stands for
 *	    the inclusive range of ASCII characters.
 *	5.  A regular expression of form 1-4 followed by * matches a
 *	    sequence of 0 or more matches of the regular expression.
 *	6.  A regular expression, x, of form 1-8, bracketed \(x\)
 *	    matches what x matches.
 *	7.  A \ followed by a digit n matches a copy of the string that the
 *	    bracketed regular expression beginning with the nth \( matched.
 *	8.  A regular expression of form 1-8, x, followed by a regular
 *	    expression of form 1-7, y matches a match for x followed by
 *	    a match for y, with the x match being as long as possible
 *	    while still permitting a y match.
 *	9.  A regular expression of form 1-8 preceded by ^ (or followed
 *	    by $), is constrained to matches that begin at the left
 *	    (or end at the right) end of a line.
 *	10. A regular expression of form 1-9 picks out the longest among
 *	    the leftmost matches in a line.
 *	11. An empty regular expression stands for a copy of the last
 *	    regular expression encountered.
 */

/*
 * constants for re's
 */
#define	CBRA	1
#define	CCHR	2
#define	CDOT	4
#define	CCL	6
#define	NCCL	8
#define	CDOL	10
#define	CEOF	11
#define	CKET	12
#define	CBACK	18

#define	CSTAR	01

#define	ESIZE	512
#define	NBRA	9

static	char	expbuf[ESIZE], *braslist[NBRA], *braelist[NBRA];
static	char	circf;

/*
 * compile the regular expression argument into a dfa
 */
char *
re_comp(sp)
	register char	*sp;
{
	register int	c;
	register char	*ep = expbuf;
	int	cclcnt, numbra = 0;
	char	*lastep = 0;
	char	bracket[NBRA];
	char	*bracketp = &bracket[0];
	static	char	*retoolong = "Regular expression too long";

#define	comerr(msg) {expbuf[0] = 0; numbra = 0; return(msg); }

	if (sp == 0 || *sp == '\0') {
		if (*ep == 0)
			return("No previous regular expression");
		return(0);
	}
	if (*sp == '^') {
		circf = 1;
		sp++;
	}
	else
		circf = 0;
	for (;;) {
		if (ep >= &expbuf[ESIZE])
			comerr(retoolong);
		if ((c = *sp++) == '\0') {
			if (bracketp != bracket)
				comerr("unmatched \\(");
			*ep++ = CEOF;
			*ep++ = 0;
			return(0);
		}
		if (c != '*')
			lastep = ep;
		switch (c) {

		case '.':
			*ep++ = CDOT;
			continue;

		case '*':
			if (lastep == 0 || *lastep == CBRA || *lastep == CKET)
				goto defchar;
			*lastep |= CSTAR;
			continue;

		case '$':
			if (*sp != '\0')
				goto defchar;
			*ep++ = CDOL;
			continue;

		case '[':
			*ep++ = CCL;
			*ep++ = 0;
			cclcnt = 1;
			if ((c = *sp++) == '^') {
				c = *sp++;
				ep[-2] = NCCL;
			}
			do {
				if (c == '\0')
					comerr("missing ]");
				if (c == '-' && ep [-1] != 0) {
					if ((c = *sp++) == ']') {
						*ep++ = '-';
						cclcnt++;
						break;
					}
					while (ep[-1] < c) {
						*ep = ep[-1] + 1;
						ep++;
						cclcnt++;
						if (ep >= &expbuf[ESIZE])
							comerr(retoolong);
					}
				}
				*ep++ = c;
				cclcnt++;
				if (ep >= &expbuf[ESIZE])
					comerr(retoolong);
			} while ((c = *sp++) != ']');
			lastep[1] = cclcnt;
			continue;

		case '\\':
			if ((c = *sp++) == '(') {
				if (numbra >= NBRA)
					comerr("too many \\(\\) pairs");
				*bracketp++ = numbra;
				*ep++ = CBRA;
				*ep++ = numbra++;
				continue;
			}
			if (c == ')') {
				if (bracketp <= bracket)
					comerr("unmatched \\)");
				*ep++ = CKET;
				*ep++ = *--bracketp;
				continue;
			}
			if (c >= '1' && c < ('1' + NBRA)) {
				*ep++ = CBACK;
				*ep++ = c - '1';
				continue;
			}
			*ep++ = CCHR;
			*ep++ = c;
			continue;

		defchar:
		default:
			*ep++ = CCHR;
			*ep++ = c;
		}
	}
}

/* 
 * match the argument string against the compiled re
 */
int
re_exec(p1)
	register char	*p1;
{
	register char	*p2 = expbuf;
	register int	c;
	int	rv;

	for (c = 0; c < NBRA; c++) {
		braslist[c] = 0;
		braelist[c] = 0;
	}
	if (circf)
		return((advance(p1, p2)));
	/*
	 * fast check for first character
	 */
	if (*p2 == CCHR) {
		c = p2[1];
		do {
			if (*p1 != c)
				continue;
			if (rv = advance(p1, p2))
				return(rv);
		} while (*p1++);
		return(0);
	}
	/*
	 * regular algorithm
	 */
	do
		if (rv = advance(p1, p2))
			return(rv);
	while (*p1++);
	return(0);
}

/* 
 * try to match the next thing in the dfa
 */
static	int
advance(lp, ep)
	register char	*lp, *ep;
{
	register char	*curlp;
	int	ct, i;
	int	rv;

	for (;;)
		switch (*ep++) {

		case CCHR:
			if (*ep++ == *lp++)
				continue;
			return(0);

		case CDOT:
			if (*lp++)
				continue;
			return(0);

		case CDOL:
			if (*lp == '\0')
				continue;
			return(0);

		case CEOF:
			return(1);

		case CCL:
			if (cclass(ep, *lp++, 1)) {
				ep += *ep;
				continue;
			}
			return(0);

		case NCCL:
			if (cclass(ep, *lp++, 0)) {
				ep += *ep;
				continue;
			}
			return(0);

		case CBRA:
			braslist[*ep++] = lp;
			continue;

		case CKET:
			braelist[*ep++] = lp;
			continue;

		case CBACK:
			if (braelist[i = *ep++] == 0)
				return(-1);
			if (backref(i, lp)) {
				lp += braelist[i] - braslist[i];
				continue;
			}
			return(0);

		case CBACK|CSTAR:
			if (braelist[i = *ep++] == 0)
				return(-1);
			curlp = lp;
			ct = braelist[i] - braslist[i];
			while (backref(i, lp))
				lp += ct;
			while (lp >= curlp) {
				if (rv = advance(lp, ep))
					return(rv);
				lp -= ct;
			}
			continue;

		case CDOT|CSTAR:
			curlp = lp;
			while (*lp++)
				;
			goto star;

		case CCHR|CSTAR:
			curlp = lp;
			while (*lp++ == *ep)
				;
			ep++;
			goto star;

		case CCL|CSTAR:
		case NCCL|CSTAR:
			curlp = lp;
			while (cclass(ep, *lp++, ep[-1] == (CCL|CSTAR)))
				;
			ep += *ep;
			goto star;

		star:
			do {
				lp--;
				if (rv = advance(lp, ep))
					return(rv);
			} while (lp > curlp);
			return(0);

		default:
			return(-1);
		}
}

backref(i, lp)
	register int	i;
	register char	*lp;
{
	register char	*bp;

	bp = braslist[i];
	while (*bp++ == *lp++)
		if (bp >= braelist[i])
			return(1);
	return(0);
}

int
cclass(set, c, af)
	register char	*set, c;
	int	af;
{
	register int	n;

	if (c == 0)
		return(0);
	n = *set++;
	while (--n)
		if (*set++ == c)
			return(af);
	return(! af);
}