summaryrefslogtreecommitdiffstats
path: root/Parser/tokenizer.c
blob: 22c20b0b7635d178b62475d26e10f580efbd825a (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
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
/***********************************************************
Copyright 1991, 1992, 1993 by Stichting Mathematisch Centrum,
Amsterdam, The Netherlands.

                        All Rights Reserved

Permission to use, copy, modify, and distribute this software and its 
documentation for any purpose and without fee is hereby granted, 
provided that the above copyright notice appear in all copies and that
both that copyright notice and this permission notice appear in 
supporting documentation, and that the names of Stichting Mathematisch
Centrum or CWI not be used in advertising or publicity pertaining to
distribution of the software without specific, written prior permission.

STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO
THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE
FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

******************************************************************/

/* Tokenizer implementation */

/* XXX This is rather old, should be restructured perhaps */
/* XXX Need a better interface to report errors than writing to stderr */
/* XXX Should use editor resource to fetch true tab size on Macintosh */

#include "pgenheaders.h"

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

#include "fgetsintr.h"
#include "tokenizer.h"
#include "errcode.h"

/* Don't ever change this -- it would break the portability of Python code */
#define TABSIZE 8

/* Forward */
static struct tok_state *tok_new PROTO((void));
static int tok_nextc PROTO((struct tok_state *tok));
static void tok_backup PROTO((struct tok_state *tok, int c));

/* Token names */

char *tok_name[] = {
	"ENDMARKER",
	"NAME",
	"NUMBER",
	"STRING",
	"NEWLINE",
	"INDENT",
	"DEDENT",
	"LPAR",
	"RPAR",
	"LSQB",
	"RSQB",
	"COLON",
	"COMMA",
	"SEMI",
	"PLUS",
	"MINUS",
	"STAR",
	"SLASH",
	"VBAR",
	"AMPER",
	"LESS",
	"GREATER",
	"EQUAL",
	"DOT",
	"PERCENT",
	"BACKQUOTE",
	"LBRACE",
	"RBRACE",
	"EQEQUAL",
	"NOTEQUAL",
	"LESSEQUAL",
	"GREATEREQUAL",
	"TILDE",
	"CIRCUMFLEX",
	"LEFTSHIFT",
	"RIGHTSHIFT",
	/* This table must match the #defines in token.h! */
	"OP",
	"<ERRORTOKEN>",
	"<N_TOKENS>"
};


/* Create and initialize a new tok_state structure */

static struct tok_state *
tok_new()
{
	struct tok_state *tok = NEW(struct tok_state, 1);
	if (tok == NULL)
		return NULL;
	tok->buf = tok->cur = tok->end = tok->inp = NULL;
	tok->done = E_OK;
	tok->fp = NULL;
	tok->tabsize = TABSIZE;
	tok->indent = 0;
	tok->indstack[0] = 0;
	tok->atbol = 1;
	tok->pendin = 0;
	tok->prompt = tok->nextprompt = NULL;
	tok->lineno = 0;
	return tok;
}


/* Set up tokenizer for string */

struct tok_state *
tok_setups(str)
	char *str;
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	tok->buf = tok->cur = str;
	tok->end = tok->inp = strchr(str, '\0');
	return tok;
}


/* Set up tokenizer for file */

struct tok_state *
tok_setupf(fp, ps1, ps2)
	FILE *fp;
	char *ps1, *ps2;
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	if ((tok->buf = NEW(char, BUFSIZ)) == NULL) {
		DEL(tok);
		return NULL;
	}
	tok->cur = tok->inp = tok->buf;
	tok->end = tok->buf + BUFSIZ;
	tok->fp = fp;
	tok->prompt = ps1;
	tok->nextprompt = ps2;
	return tok;
}


/* Free a tok_state structure */

void
tok_free(tok)
	struct tok_state *tok;
{
	/* XXX really need a separate flag to say 'my buffer' */
	if (tok->fp != NULL && tok->buf != NULL)
		DEL(tok->buf);
	DEL(tok);
}


/* Get next char, updating state; error code goes into tok->done */

static int
tok_nextc(tok)
	register struct tok_state *tok;
{
	if (tok->done != E_OK)
		return EOF;
	
	for (;;) {
		if (tok->cur < tok->inp)
			return *tok->cur++;
		if (tok->fp == NULL) {
			tok->done = E_EOF;
			return EOF;
		}
		if (tok->inp > tok->buf && tok->inp[-1] == '\n')
			tok->inp = tok->buf;
		if (tok->inp == tok->end) {
			int n = tok->end - tok->buf;
			char *new = tok->buf;
			RESIZE(new, char, n+n);
			if (new == NULL) {
				fprintf(stderr, "tokenizer out of mem\n");
				tok->done = E_NOMEM;
				return EOF;
			}
			tok->buf = new;
			tok->inp = tok->buf + n;
			tok->end = tok->inp + n;
		}
#ifdef USE_READLINE
		if (tok->prompt != NULL) {
			extern char *readline PROTO((char *prompt));
			static int been_here;
			if (!been_here) {
				/* Force rebind of TAB to insert-tab */
				extern int rl_insert();
				rl_bind_key('\t', rl_insert);
				been_here++;
			}
			if (tok->buf != NULL)
				free(tok->buf);
			tok->buf = readline(tok->prompt);
			(void) intrcheck(); /* Clear pending interrupt */
			if (tok->nextprompt != NULL)
				tok->prompt = tok->nextprompt;
				/* XXX different semantics w/o readline()! */
			if (tok->buf == NULL) {
				tok->done = E_EOF;
			}
			else {
				unsigned int n = strlen(tok->buf);
				if (n > 0)
					add_history(tok->buf);
				/* Append the '\n' that readline()
				   doesn't give us, for the tokenizer... */
				tok->buf = realloc(tok->buf, n+2);
				if (tok->buf == NULL)
					tok->done = E_NOMEM;
				else {
					tok->end = tok->buf + n;
					*tok->end++ = '\n';
					*tok->end = '\0';
					tok->inp = tok->end;
					tok->cur = tok->buf;
				}
			}
		}
		else
#endif
		{
			tok->cur = tok->inp;
			if (tok->prompt != NULL && tok->inp == tok->buf) {
				fprintf(stderr, "%s", tok->prompt);
				tok->prompt = tok->nextprompt;
			}
			tok->done = fgets_intr(tok->inp,
				(int)(tok->end - tok->inp), tok->fp);
		}
		if (tok->done != E_OK) {
			if (tok->prompt != NULL)
				fprintf(stderr, "\n");
			return EOF;
		}
		tok->inp = strchr(tok->inp, '\0');
	}
}


/* Back-up one character */

static void
tok_backup(tok, c)
	register struct tok_state *tok;
	register int c;
{
	if (c != EOF) {
		if (--tok->cur < tok->buf) {
			fprintf(stderr, "tok_backup: begin of buffer\n");
			abort();
		}
		if (*tok->cur != c)
			*tok->cur = c;
	}
}


/* Return the token corresponding to a single character */

int
tok_1char(c)
	int c;
{
	switch (c) {
	case '(':	return LPAR;
	case ')':	return RPAR;
	case '[':	return LSQB;
	case ']':	return RSQB;
	case ':':	return COLON;
	case ',':	return COMMA;
	case ';':	return SEMI;
	case '+':	return PLUS;
	case '-':	return MINUS;
	case '*':	return STAR;
	case '/':	return SLASH;
	case '|':	return VBAR;
	case '&':	return AMPER;
	case '<':	return LESS;
	case '>':	return GREATER;
	case '=':	return EQUAL;
	case '.':	return DOT;
	case '%':	return PERCENT;
	case '`':	return BACKQUOTE;
	case '{':	return LBRACE;
	case '}':	return RBRACE;
	case '^':	return CIRCUMFLEX;
	case '~':	return TILDE;
	default:	return OP;
	}
}


int
tok_2char(c1, c2)
	int c1, c2;
{
	switch (c1) {
	case '=':
		switch (c2) {
		case '=':	return EQEQUAL;
		}
		break;
	case '!':
		switch (c2) {
		case '=':	return NOTEQUAL;
		}
		break;
	case '<':
		switch (c2) {
		case '>':	return NOTEQUAL;
		case '=':	return LESSEQUAL;
		case '<':	return LEFTSHIFT;
		}
		break;
	case '>':
		switch (c2) {
		case '=':	return GREATEREQUAL;
		case '>':	return RIGHTSHIFT;
		}
		break;
	}
	return OP;
}


/* Get next token, after space stripping etc. */

int
tok_get(tok, p_start, p_end)
	register struct tok_state *tok; /* In/out: tokenizer state */
	char **p_start, **p_end; /* Out: point to start/end of token */
{
	register int c;
	int blankline;

  nextline:
	blankline = 0;

	/* Get indentation level */
	if (tok->atbol) {
		register int col = 0;
		tok->atbol = 0;
		tok->lineno++;
		for (;;) {
			c = tok_nextc(tok);
			if (c == ' ')
				col++;
			else if (c == '\t')
				col = (col/tok->tabsize + 1) * tok->tabsize;
			else
				break;
		}
		tok_backup(tok, c);
		if (c == '#' || c == '\n') {
			/* Lines with only whitespace and/or comments
			   shouldn't affect the indentation and are
			   not passed to the parser as NEWLINE tokens,
			   except *totally* empty lines in interactive
			   mode, which signal the end of a command group. */
			if (col == 0 && c == '\n' && tok->prompt != NULL)
				blankline = 0; /* Let it through */
			else
				blankline = 1; /* Ignore completely */
			/* We can't jump back right here since we still
			   may need to skip to the end of a comment */
		}
		if (!blankline) {
			if (col == tok->indstack[tok->indent]) {
				/* No change */
			}
			else if (col > tok->indstack[tok->indent]) {
				/* Indent -- always one */
				if (tok->indent+1 >= MAXINDENT) {
					fprintf(stderr, "excessive indent\n");
					tok->done = E_TOKEN;
					return ERRORTOKEN;
				}
				tok->pendin++;
				tok->indstack[++tok->indent] = col;
			}
			else /* col < tok->indstack[tok->indent] */ {
				/* Dedent -- any number, must be consistent */
				while (tok->indent > 0 &&
					col < tok->indstack[tok->indent]) {
					tok->indent--;
					tok->pendin--;
				}
				if (col != tok->indstack[tok->indent]) {
					fprintf(stderr, "inconsistent dedent\n");
					tok->done = E_TOKEN;
					return ERRORTOKEN;
				}
			}
		}
	}
	
	*p_start = *p_end = tok->cur;
	
	/* Return pending indents/dedents */
	if (tok->pendin != 0) {
		if (tok->pendin < 0) {
			tok->pendin++;
			return DEDENT;
		}
		else {
			tok->pendin--;
			return INDENT;
		}
	}
	
 again:
	/* Skip spaces */
	do {
		c = tok_nextc(tok);
	} while (c == ' ' || c == '\t');
	
	/* Set start of current token */
	*p_start = tok->cur - 1;
	
	/* Skip comment */
	if (c == '#') {
		/* Hack to allow overriding the tabsize in the file.
		   This is also recognized by vi, when it occurs near the
		   beginning or end of the file.  (Will vi never die...?)
		   For Python it must be at the beginning of the file! */
		int x;
		/* XXX The cast to (unsigned char *) is needed by THINK C 3.0 */
		if (sscanf(/*(unsigned char *)*/tok->cur,
				" vi:set tabsize=%d:", &x) == 1 &&
						x >= 1 && x <= 40) {
			/* fprintf(stderr, "# vi:set tabsize=%d:\n", x); */
			tok->tabsize = x;
		}
		do {
			c = tok_nextc(tok);
		} while (c != EOF && c != '\n');
	}
	
	/* Check for EOF and errors now */
	if (c == EOF) {
		*p_start = *p_end = tok->cur;
		return tok->done == E_EOF ? ENDMARKER : ERRORTOKEN;
	}
	
	/* Identifier (most frequent token!) */
	if (isalpha(c) || c == '_') {
		do {
			c = tok_nextc(tok);
		} while (isalnum(c) || c == '_');
		tok_backup(tok, c);
		*p_end = tok->cur;
		return NAME;
	}
	
	/* Newline */
	if (c == '\n') {
		tok->atbol = 1;
		if (blankline)
			goto nextline;
		*p_end = tok->cur - 1; /* Leave '\n' out of the string */
		return NEWLINE;
	}
	
	/* Period or number starting with period? */
	if (c == '.') {
		c = tok_nextc(tok);
		if (isdigit(c)) {
			goto fraction;
		}
		else {
			tok_backup(tok, c);
			*p_end = tok->cur;
			return DOT;
		}
	}
	
	/* Number */
	if (isdigit(c)) {
		if (c == '0') {
			/* Hex or octal */
			c = tok_nextc(tok);
			if (c == '.')
				goto fraction;
			if (c == 'x' || c == 'X') {
				/* Hex */
				do {
					c = tok_nextc(tok);
				} while (isxdigit(c));
			}
			else {
				/* XXX This is broken!  E.g.,
				   09.9 should be accepted as float! */
				/* Octal; c is first char of it */
				/* There's no 'isoctdigit' macro, sigh */
				while ('0' <= c && c < '8') {
					c = tok_nextc(tok);
				}
			}
			if (c == 'l' || c == 'L')
				c = tok_nextc(tok);
		}
		else {
			/* Decimal */
			do {
				c = tok_nextc(tok);
			} while (isdigit(c));
			if (c == 'l' || c == 'L')
				c = tok_nextc(tok);
			else {
				/* Accept floating point numbers.
				   XXX This accepts incomplete things like
				   XXX 12e or 1e+; worry run-time.
				   XXX Doesn't accept numbers
				   XXX starting with a dot */
				if (c == '.') {
		fraction:
					/* Fraction */
					do {
						c = tok_nextc(tok);
					} while (isdigit(c));
				}
				if (c == 'e' || c == 'E') {
					/* Exponent part */
					c = tok_nextc(tok);
					if (c == '+' || c == '-')
						c = tok_nextc(tok);
					while (isdigit(c)) {
						c = tok_nextc(tok);
					}
				}
			}
		}
		tok_backup(tok, c);
		*p_end = tok->cur;
		return NUMBER;
	}
	
	/* String */
	if (c == '\'') {
		for (;;) {
			c = tok_nextc(tok);
			if (c == '\n' || c == EOF) {
				tok->done = E_TOKEN;
				return ERRORTOKEN;
			}
			if (c == '\\') {
				c = tok_nextc(tok);
				*p_end = tok->cur;
				if (c == '\n' || c == EOF) {
					tok->done = E_TOKEN;
					return ERRORTOKEN;
				}
				continue;
			}
			if (c == '\'')
				break;
		}
		*p_end = tok->cur;
		return STRING;
	}
	
	/* Line continuation */
	if (c == '\\') {
		c = tok_nextc(tok);
		if (c != '\n') {
			tok->done = E_TOKEN;
			return ERRORTOKEN;
		}
		tok->lineno++;
		goto again; /* Read next line */
	}
	
	/* Check for two-character token */
	{
		int c2 = tok_nextc(tok);
		int token = tok_2char(c, c2);
		if (token != OP) {
			*p_end = tok->cur;
			return token;
		}
		tok_backup(tok, c2);
	}
	
	/* Punctuation character */
	*p_end = tok->cur;
	return tok_1char(c);
}


#ifdef DEBUG

void
tok_dump(type, start, end)
	int type;
	char *start, *end;
{
	printf("%s", tok_name[type]);
	if (type == NAME || type == NUMBER || type == STRING || type == OP)
		printf("(%.*s)", (int)(end - start), start);
}

#endif