summary refs log tree commit diff
path: root/bin/catsh/libedit/tokenizer.c
blob: 18532240dbb933b74815d8a77cb654b54f987ce9 (plain) (blame)
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
/*	$NetBSD: tokenizer.c,v 1.28 2016/04/11 18:56:31 christos Exp $	*/

/*-
 * Copyright (c) 1992, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Christos Zoulas of Cornell University.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

#include "config.h"
#if !defined(lint) && !defined(SCCSID)
#if 0
static char sccsid[] = "@(#)tokenizer.c	8.1 (Berkeley) 6/4/93";
#else
__RCSID("$NetBSD: tokenizer.c,v 1.28 2016/04/11 18:56:31 christos Exp $");
#endif
#endif /* not lint && not SCCSID */

/* We build this file twice, once as NARROW, once as WIDE. */
/*
 * tokenize.c: Bourne shell like tokenizer
 */
#include <stdlib.h>
#include <string.h>

#include "histedit.h"

typedef enum {
	Q_none, Q_single, Q_double, Q_one, Q_doubleone
} quote_t;

#define	TOK_KEEP	1
#define	TOK_EAT		2

#define	WINCR		20
#define	AINCR		10

#define	IFS		STR("\t \n")

#define	tok_malloc(a)		malloc(a)
#define	tok_free(a)		free(a)
#define	tok_realloc(a, b)	realloc(a, b)

#ifdef NARROWCHAR
#define	Char			char
#define	FUN(prefix, rest)	prefix ## _ ## rest
#define	TYPE(type)		type
#define	STR(x)			x
#define	Strchr(s, c)		strchr(s, c)
#define	tok_strdup(s)		strdup(s)
#else
#define	Char			wchar_t
#define	FUN(prefix, rest)	prefix ## _w ## rest
#define	TYPE(type)		type ## W
#define	STR(x)			L ## x
#define	Strchr(s, c)		wcschr(s, c)
#define	tok_strdup(s)		wcsdup(s)
#endif

struct TYPE(tokenizer) {
	Char	*ifs;		/* In field separator			 */
	size_t	 argc, amax;	/* Current and maximum number of args	 */
	Char   **argv;		/* Argument list			 */
	Char	*wptr, *wmax;	/* Space and limit on the word buffer	 */
	Char	*wstart;	/* Beginning of next word		 */
	Char	*wspace;	/* Space of word buffer			 */
	quote_t	 quote;		/* Quoting state			 */
	int	 flags;		/* flags;				 */
};


static void FUN(tok,finish)(TYPE(Tokenizer) *);


/* FUN(tok,finish)():
 *	Finish a word in the tokenizer.
 */
static void
FUN(tok,finish)(TYPE(Tokenizer) *tok)
{

	*tok->wptr = '\0';
	if ((tok->flags & TOK_KEEP) || tok->wptr != tok->wstart) {
		tok->argv[tok->argc++] = tok->wstart;
		tok->argv[tok->argc] = NULL;
		tok->wstart = ++tok->wptr;
	}
	tok->flags &= ~TOK_KEEP;
}


/* FUN(tok,init)():
 *	Initialize the tokenizer
 */
TYPE(Tokenizer) *
FUN(tok,init)(const Char *ifs)
{
	TYPE(Tokenizer) *tok = tok_malloc(sizeof(*tok));

	if (tok == NULL)
		return NULL;
	tok->ifs = tok_strdup(ifs ? ifs : IFS);
	if (tok->ifs == NULL) {
		tok_free(tok);
		return NULL;
	}
	tok->argc = 0;
	tok->amax = AINCR;
	tok->argv = tok_malloc(sizeof(*tok->argv) * tok->amax);
	if (tok->argv == NULL) {
		tok_free(tok->ifs);
		tok_free(tok);
		return NULL;
	}
	tok->argv[0] = NULL;
	tok->wspace = tok_malloc(WINCR * sizeof(*tok->wspace));
	if (tok->wspace == NULL) {
		tok_free(tok->argv);
		tok_free(tok->ifs);
		tok_free(tok);
		return NULL;
	}
	tok->wmax = tok->wspace + WINCR;
	tok->wstart = tok->wspace;
	tok->wptr = tok->wspace;
	tok->flags = 0;
	tok->quote = Q_none;

	return tok;
}


/* FUN(tok,reset)():
 *	Reset the tokenizer
 */
void
FUN(tok,reset)(TYPE(Tokenizer) *tok)
{

	tok->argc = 0;
	tok->wstart = tok->wspace;
	tok->wptr = tok->wspace;
	tok->flags = 0;
	tok->quote = Q_none;
}


/* FUN(tok,end)():
 *	Clean up
 */
void
FUN(tok,end)(TYPE(Tokenizer) *tok)
{

	tok_free(tok->ifs);
	tok_free(tok->wspace);
	tok_free(tok->argv);
	tok_free(tok);
}



/* FUN(tok,line)():
 *	Bourne shell (sh(1)) like tokenizing
 *	Arguments:
 *		tok	current tokenizer state (setup with FUN(tok,init)())
 *		line	line to parse
 *	Returns:
 *		-1	Internal error
 *		 3	Quoted return
 *		 2	Unmatched double quote
 *		 1	Unmatched single quote
 *		 0	Ok
 *	Modifies (if return value is 0):
 *		argc	number of arguments
 *		argv	argument array
 *		cursorc	if !NULL, argv element containing cursor
 *		cursorv	if !NULL, offset in argv[cursorc] of cursor
 */
int
FUN(tok,line)(TYPE(Tokenizer) *tok, const TYPE(LineInfo) *line,
    int *argc, const Char ***argv, int *cursorc, int *cursoro)
{
	const Char *ptr;
	int cc, co;

	cc = co = -1;
	ptr = line->buffer;
	for (ptr = line->buffer; ;ptr++) {
		if (ptr >= line->lastchar)
			ptr = STR("");
		if (ptr == line->cursor) {
			cc = (int)tok->argc;
			co = (int)(tok->wptr - tok->wstart);
		}
		switch (*ptr) {
		case '\'':
			tok->flags |= TOK_KEEP;
			tok->flags &= ~TOK_EAT;
			switch (tok->quote) {
			case Q_none:
				tok->quote = Q_single;	/* Enter single quote
							 * mode */
				break;

			case Q_single:	/* Exit single quote mode */
				tok->quote = Q_none;
				break;

			case Q_one:	/* Quote this ' */
				tok->quote = Q_none;
				*tok->wptr++ = *ptr;
				break;

			case Q_double:	/* Stay in double quote mode */
				*tok->wptr++ = *ptr;
				break;

			case Q_doubleone:	/* Quote this ' */
				tok->quote = Q_double;
				*tok->wptr++ = *ptr;
				break;

			default:
				return -1;
			}
			break;

		case '"':
			tok->flags &= ~TOK_EAT;
			tok->flags |= TOK_KEEP;
			switch (tok->quote) {
			case Q_none:	/* Enter double quote mode */
				tok->quote = Q_double;
				break;

			case Q_double:	/* Exit double quote mode */
				tok->quote = Q_none;
				break;

			case Q_one:	/* Quote this " */
				tok->quote = Q_none;
				*tok->wptr++ = *ptr;
				break;

			case Q_single:	/* Stay in single quote mode */
				*tok->wptr++ = *ptr;
				break;

			case Q_doubleone:	/* Quote this " */
				tok->quote = Q_double;
				*tok->wptr++ = *ptr;
				break;

			default:
				return -1;
			}
			break;

		case '\\':
			tok->flags |= TOK_KEEP;
			tok->flags &= ~TOK_EAT;
			switch (tok->quote) {
			case Q_none:	/* Quote next character */
				tok->quote = Q_one;
				break;

			case Q_double:	/* Quote next character */
				tok->quote = Q_doubleone;
				break;

			case Q_one:	/* Quote this, restore state */
				*tok->wptr++ = *ptr;
				tok->quote = Q_none;
				break;

			case Q_single:	/* Stay in single quote mode */
				*tok->wptr++ = *ptr;
				break;

			case Q_doubleone:	/* Quote this \ */
				tok->quote = Q_double;
				*tok->wptr++ = *ptr;
				break;

			default:
				return -1;
			}
			break;

		case '\n':
			tok->flags &= ~TOK_EAT;
			switch (tok->quote) {
			case Q_none:
				goto tok_line_outok;

			case Q_single:
			case Q_double:
				*tok->wptr++ = *ptr;	/* Add the return */
				break;

			case Q_doubleone:   /* Back to double, eat the '\n' */
				tok->flags |= TOK_EAT;
				tok->quote = Q_double;
				break;

			case Q_one:	/* No quote, more eat the '\n' */
				tok->flags |= TOK_EAT;
				tok->quote = Q_none;
				break;

			default:
				return 0;
			}
			break;

		case '\0':
			switch (tok->quote) {
			case Q_none:
				/* Finish word and return */
				if (tok->flags & TOK_EAT) {
					tok->flags &= ~TOK_EAT;
					return 3;
				}
				goto tok_line_outok;

			case Q_single:
				return 1;

			case Q_double:
				return 2;

			case Q_doubleone:
				tok->quote = Q_double;
				*tok->wptr++ = *ptr;
				break;

			case Q_one:
				tok->quote = Q_none;
				*tok->wptr++ = *ptr;
				break;

			default:
				return -1;
			}
			break;

		default:
			tok->flags &= ~TOK_EAT;
			switch (tok->quote) {
			case Q_none:
				if (Strchr(tok->ifs, *ptr) != NULL)
					FUN(tok,finish)(tok);
				else
					*tok->wptr++ = *ptr;
				break;

			case Q_single:
			case Q_double:
				*tok->wptr++ = *ptr;
				break;


			case Q_doubleone:
				*tok->wptr++ = '\\';
				tok->quote = Q_double;
				*tok->wptr++ = *ptr;
				break;

			case Q_one:
				tok->quote = Q_none;
				*tok->wptr++ = *ptr;
				break;

			default:
				return -1;

			}
			break;
		}

		if (tok->wptr >= tok->wmax - 4) {
			size_t size = (size_t)(tok->wmax - tok->wspace + WINCR);
			Char *s = tok_realloc(tok->wspace,
			    size * sizeof(*s));
			if (s == NULL)
				return -1;

			if (s != tok->wspace) {
				size_t i;
				for (i = 0; i < tok->argc; i++) {
				    tok->argv[i] =
					(tok->argv[i] - tok->wspace) + s;
				}
				tok->wptr = (tok->wptr - tok->wspace) + s;
				tok->wstart = (tok->wstart - tok->wspace) + s;
				tok->wspace = s;
			}
			tok->wmax = s + size;
		}
		if (tok->argc >= tok->amax - 4) {
			Char **p;
			tok->amax += AINCR;
			p = tok_realloc(tok->argv, tok->amax * sizeof(*p));
			if (p == NULL) {
				tok->amax -= AINCR;
				return -1;
			}
			tok->argv = p;
		}
	}
 tok_line_outok:
	if (cc == -1 && co == -1) {
		cc = (int)tok->argc;
		co = (int)(tok->wptr - tok->wstart);
	}
	if (cursorc != NULL)
		*cursorc = cc;
	if (cursoro != NULL)
		*cursoro = co;
	FUN(tok,finish)(tok);
	*argv = (const Char **)tok->argv;
	*argc = (int)tok->argc;
	return 0;
}

/* FUN(tok,str)():
 *	Simpler version of tok_line, taking a NUL terminated line
 *	and splitting into words, ignoring cursor state.
 */
int
FUN(tok,str)(TYPE(Tokenizer) *tok, const Char *line, int *argc,
    const Char ***argv)
{
	TYPE(LineInfo) li;

	memset(&li, 0, sizeof(li));
	li.buffer = line;
	li.cursor = li.lastchar = Strchr(line, '\0');
	return FUN(tok,line)(tok, &li, argc, argv, NULL, NULL);
}