summaryrefslogtreecommitdiffstats
path: root/Parser/tokenizer.c
blob: ef0d7118b8c10e210cd8d5474522c9b0ce45e03b (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
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
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
/***********************************************************
Copyright (c) 2000, BeOpen.com.
Copyright (c) 1995-2000, Corporation for National Research Initiatives.
Copyright (c) 1990-1995, Stichting Mathematisch Centrum.
All rights reserved.

See the file "Misc/COPYRIGHT" for information on usage and
redistribution of this file, and for a DISCLAIMER OF ALL WARRANTIES.
******************************************************************/

/* Tokenizer implementation */

#include "pgenheaders.h"

#include <ctype.h>

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

extern char *PyOS_Readline Py_PROTO((char *));
/* Return malloc'ed string including trailing \n;
   empty malloc'ed string for EOF;
   NULL if interrupted */

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

/* Convert a possibly signed character to a nonnegative int */
/* XXX This assumes characters are 8 bits wide */
#ifdef __CHAR_UNSIGNED__
#define Py_CHARMASK(c)		(c)
#else
#define Py_CHARMASK(c)		((c) & 0xff)
#endif

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

/* Token names */

char *_PyParser_TokenNames[] = {
	"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",
	"DOUBLESTAR",
	/* 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 = PyMem_NEW(struct tok_state, 1);
	if (tok == NULL)
		return NULL;
	tok->buf = tok->cur = tok->end = tok->inp = tok->start = 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;
	tok->level = 0;
	tok->filename = NULL;
	tok->altwarning = 0;
	tok->alterror = 0;
	tok->alttabsize = 1;
	tok->altindstack[0] = 0;
	return tok;
}


/* Set up tokenizer for string */

struct tok_state *
PyTokenizer_FromString(str)
	char *str;
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	tok->buf = tok->cur = tok->end = tok->inp = str;
	return tok;
}


/* Set up tokenizer for file */

struct tok_state *
PyTokenizer_FromFile(fp, ps1, ps2)
	FILE *fp;
	char *ps1, *ps2;
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	if ((tok->buf = PyMem_NEW(char, BUFSIZ)) == NULL) {
		PyMem_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
PyTokenizer_Free(tok)
	struct tok_state *tok;
{
	if (tok->fp != NULL && tok->buf != NULL)
		PyMem_DEL(tok->buf);
	PyMem_DEL(tok);
}


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

static int
tok_nextc(tok)
	register struct tok_state *tok;
{
	for (;;) {
		if (tok->cur != tok->inp) {
			return Py_CHARMASK(*tok->cur++); /* Fast path */
		}
		if (tok->done != E_OK)
			return EOF;
		if (tok->fp == NULL) {
			char *end = strchr(tok->inp, '\n');
			if (end != NULL)
				end++;
			else {
				end = strchr(tok->inp, '\0');
				if (end == tok->inp) {
					tok->done = E_EOF;
					return EOF;
				}
			}
			if (tok->start == NULL)
				tok->buf = tok->cur;
			tok->lineno++;
			tok->inp = end;
			return Py_CHARMASK(*tok->cur++);
		}
		if (tok->prompt != NULL) {
			char *new = PyOS_Readline(tok->prompt);
			if (tok->nextprompt != NULL)
				tok->prompt = tok->nextprompt;
			if (new == NULL)
				tok->done = E_INTR;
			else if (*new == '\0') {
				PyMem_FREE(new);
				tok->done = E_EOF;
			}
			else if (tok->start != NULL) {
				size_t start = tok->start - tok->buf;
				size_t oldlen = tok->cur - tok->buf;
				size_t newlen = oldlen + strlen(new);
				char *buf = tok->buf;
				PyMem_RESIZE(buf, char, newlen+1);
				tok->lineno++;
				if (buf == NULL) {
					PyMem_DEL(tok->buf);
					tok->buf = NULL;
					PyMem_FREE(new);
					tok->done = E_NOMEM;
					return EOF;
				}
				tok->buf = buf;
				tok->cur = tok->buf + oldlen;
				strcpy(tok->buf + oldlen, new);
				PyMem_FREE(new);
				tok->inp = tok->buf + newlen;
				tok->end = tok->inp + 1;
				tok->start = tok->buf + start;
			}
			else {
				tok->lineno++;
				if (tok->buf != NULL)
					PyMem_DEL(tok->buf);
				tok->buf = new;
				tok->cur = tok->buf;
				tok->inp = strchr(tok->buf, '\0');
				tok->end = tok->inp + 1;
			}
		}
		else {
			int done = 0;
			int cur = 0;
			char *pt;
			if (tok->start == NULL) {
				if (tok->buf == NULL) {
					tok->buf = PyMem_NEW(char, BUFSIZ);
					if (tok->buf == NULL) {
						tok->done = E_NOMEM;
						return EOF;
					}
					tok->end = tok->buf + BUFSIZ;
				}
				if (fgets(tok->buf, (int)(tok->end - tok->buf),
					  tok->fp) == NULL) {
					tok->done = E_EOF;
					done = 1;
				}
				else {
					tok->done = E_OK;
					tok->inp = strchr(tok->buf, '\0');
					done = tok->inp[-1] == '\n';
				}
			}
			else {
				cur = tok->cur - tok->buf;
				if (feof(tok->fp)) {
					tok->done = E_EOF;
					done = 1;
				}
				else
					tok->done = E_OK;
			}
			tok->lineno++;
			/* Read until '\n' or EOF */
			while (!done) {
				int curstart = tok->start == NULL ? -1 :
					       tok->start - tok->buf;
				int curvalid = tok->inp - tok->buf;
				int newsize = curvalid + BUFSIZ;
				char *newbuf = tok->buf;
				PyMem_RESIZE(newbuf, char, newsize);
				if (newbuf == NULL) {
					tok->done = E_NOMEM;
					tok->cur = tok->inp;
					return EOF;
				}
				tok->buf = newbuf;
				tok->inp = tok->buf + curvalid;
				tok->end = tok->buf + newsize;
				tok->start = curstart < 0 ? NULL :
					     tok->buf + curstart;
				if (fgets(tok->inp,
					       (int)(tok->end - tok->inp),
					       tok->fp) == NULL) {
					/* Last line does not end in \n,
					   fake one */
					strcpy(tok->inp, "\n");
				}
				tok->inp = strchr(tok->inp, '\0');
				done = tok->inp[-1] == '\n';
			}
			tok->cur = tok->buf + cur;
#ifndef macintosh
			/* replace "\r\n" with "\n" */
			/* For Mac we leave the \r, giving a syntax error */
			pt = tok->inp - 2;
			if (pt >= tok->buf && *pt == '\r') {
				*pt++ = '\n';
				*pt = '\0';
				tok->inp = pt;
			}
#endif
		}
		if (tok->done != E_OK) {
			if (tok->prompt != NULL)
				PySys_WriteStderr("\n");
			tok->cur = tok->inp;
			return EOF;
		}
	}
	/*NOTREACHED*/
}


/* 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)
			Py_FatalError("tok_backup: begin of buffer");
		if (*tok->cur != c)
			*tok->cur = c;
	}
}


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

int
PyToken_OneChar(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
PyToken_TwoChars(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;
	case '*':
		switch (c2) {
		case '*':	return DOUBLESTAR;
		}
		break;
	}
	return OP;
}


static int
indenterror(tok)
	struct tok_state *tok;
{
	if (tok->alterror) {
		tok->done = E_INDENT;
		tok->cur = tok->inp;
		return 1;
	}
	if (tok->altwarning) {
		PySys_WriteStderr("%s: inconsistent tab/space usage\n",
			tok->filename);
		tok->altwarning = 0;
	}
	return 0;
}


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

int
PyTokenizer_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;

	*p_start = *p_end = NULL;
  nextline:
	tok->start = NULL;
	blankline = 0;

	/* Get indentation level */
	if (tok->atbol) {
		register int col = 0;
		register int altcol = 0;
		tok->atbol = 0;
		for (;;) {
			c = tok_nextc(tok);
			if (c == ' ')
				col++, altcol++;
			else if (c == '\t') {
				col = (col/tok->tabsize + 1) * tok->tabsize;
				altcol = (altcol/tok->alttabsize + 1)
					* tok->alttabsize;
			}
			else if (c == '\014') /* Control-L (formfeed) */
				col = altcol = 0; /* For Emacs users */
			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 && tok->level == 0) {
			if (col == tok->indstack[tok->indent]) {
				/* No change */
				if (altcol != tok->altindstack[tok->indent]) {
					if (indenterror(tok))
						return ERRORTOKEN;
				}
			}
			else if (col > tok->indstack[tok->indent]) {
				/* Indent -- always one */
				if (tok->indent+1 >= MAXINDENT) {
					PySys_WriteStderr(
						"excessive indent\n");
					tok->done = E_TOKEN;
					tok->cur = tok->inp;
					return ERRORTOKEN;
				}
				if (altcol <= tok->altindstack[tok->indent]) {
					if (indenterror(tok))
						return ERRORTOKEN;
				}
				tok->pendin++;
				tok->indstack[++tok->indent] = col;
				tok->altindstack[tok->indent] = altcol;
			}
			else /* col < tok->indstack[tok->indent] */ {
				/* Dedent -- any number, must be consistent */
				while (tok->indent > 0 &&
					col < tok->indstack[tok->indent]) {
					tok->pendin--;
					tok->indent--;
				}
				if (col != tok->indstack[tok->indent]) {
					PySys_WriteStderr(
						"inconsistent dedent\n");
					tok->done = E_TOKEN;
					tok->cur = tok->inp;
					return ERRORTOKEN;
				}
				if (altcol != tok->altindstack[tok->indent]) {
					if (indenterror(tok))
						return ERRORTOKEN;
				}
			}
		}
	}
	
	tok->start = tok->cur;
	
	/* Return pending indents/dedents */
	if (tok->pendin != 0) {
		if (tok->pendin < 0) {
			tok->pendin++;
			return DEDENT;
		}
		else {
			tok->pendin--;
			return INDENT;
		}
	}
	
 again:
	tok->start = NULL;
	/* Skip spaces */
	do {
		c = tok_nextc(tok);
	} while (c == ' ' || c == '\t' || c == '\014');
	
	/* Set start of current token */
	tok->start = tok->cur - 1;
	
	/* Skip comment, while looking for tab-setting magic */
	if (c == '#') {
		static char *tabforms[] = {
			"tab-width:",		/* Emacs */
			":tabstop=",		/* vim, full form */
			":ts=",			/* vim, abbreviated form */
			"set tabsize=",		/* will vi never die? */
		/* more templates can be added here to support other editors */
		};
		char cbuf[80];
		char *tp, **cp;
		tp = cbuf;
		do {
			*tp++ = c = tok_nextc(tok);
		} while (c != EOF && c != '\n' &&
			 tp - cbuf + 1 < sizeof(cbuf));
		*tp = '\0';
		for (cp = tabforms; 
		     cp < tabforms + sizeof(tabforms)/sizeof(tabforms[0]);
		     cp++) {
			if ((tp = strstr(cbuf, *cp))) {
				int newsize = atoi(tp + strlen(*cp));

				if (newsize >= 1 && newsize <= 40) {
					tok->tabsize = newsize;
					if (Py_VerboseFlag)
					    PySys_WriteStderr(
						"Tab size set to %d\n",
						newsize);
				}
			}
		}
		while (c != EOF && c != '\n')
			c = tok_nextc(tok);
	}
	
	/* Check for EOF and errors now */
	if (c == EOF) {
		return tok->done == E_EOF ? ENDMARKER : ERRORTOKEN;
	}
	
	/* Identifier (most frequent token!) */
	if (isalpha(c) || c == '_') {
		/* Process r"", u"" and ur"" */
		switch (c) {
		case 'r':
		case 'R':
			c = tok_nextc(tok);
			if (c == '"' || c == '\'')
				goto letter_quote;
			break;
		case 'u':
		case 'U':
			c = tok_nextc(tok);
			if (c == 'r' || c == 'R')
				c = tok_nextc(tok);
			if (c == '"' || c == '\'')
				goto letter_quote;
			break;
		}
		while (isalnum(c) || c == '_') {
			c = tok_nextc(tok);
		}
		tok_backup(tok, c);
		*p_start = tok->start;
		*p_end = tok->cur;
		return NAME;
	}
	
	/* Newline */
	if (c == '\n') {
		tok->atbol = 1;
		if (blankline || tok->level > 0)
			goto nextline;
		*p_start = tok->start;
		*p_end = tok->cur - 1; /* Leave '\n' out of the string */
		return NEWLINE;
	}
	
#ifdef macintosh
	if (c == '\r') {
		PySys_WriteStderr(
		  "File contains \\r characters (incorrect line endings?)\n");
		tok->done = E_TOKEN;
		tok->cur = tok->inp;
		return ERRORTOKEN;
	}
#endif	
	/* Period or number starting with period? */
	if (c == '.') {
		c = tok_nextc(tok);
		if (isdigit(c)) {
			goto fraction;
		}
		else {
			tok_backup(tok, c);
			*p_start = tok->start;
			*p_end = tok->cur;
			return DOT;
		}
	}

	/* Number */
	if (isdigit(c)) {
		if (c == '0') {
			/* Hex or octal */
			c = tok_nextc(tok);
			if (c == '.')
				goto fraction;
#ifndef WITHOUT_COMPLEX
			if (c == 'j' || c == 'J')
				goto imaginary;
#endif
			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 */
				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);
					}
				}
#ifndef WITHOUT_COMPLEX
				if (c == 'j' || c == 'J')
					/* Imaginary part */
		imaginary:
					c = tok_nextc(tok);
#endif
			}
		}
		tok_backup(tok, c);
		*p_start = tok->start;
		*p_end = tok->cur;
		return NUMBER;
	}

  letter_quote:
	/* String */
	if (c == '\'' || c == '"') {
		int quote2 = tok->cur - tok->start + 1;
		int quote = c;
		int triple = 0;
		int tripcount = 0;
		for (;;) {
			c = tok_nextc(tok);
			if (c == '\n') {
				if (!triple) {
					tok->done = E_TOKEN;
					tok_backup(tok, c);
					return ERRORTOKEN;
				}
				tripcount = 0;
			}
			else if (c == EOF) {
				tok->done = E_TOKEN;
				tok->cur = tok->inp;
				return ERRORTOKEN;
			}
			else if (c == quote) {
				tripcount++;
				if (tok->cur - tok->start == quote2) {
					c = tok_nextc(tok);
					if (c == quote) {
						triple = 1;
						tripcount = 0;
						continue;
					}
					tok_backup(tok, c);
				}
				if (!triple || tripcount == 3)
					break;
			}
			else if (c == '\\') {
				tripcount = 0;
				c = tok_nextc(tok);
				if (c == EOF) {
					tok->done = E_TOKEN;
					tok->cur = tok->inp;
					return ERRORTOKEN;
				}
			}
			else
				tripcount = 0;
		}
		*p_start = tok->start;
		*p_end = tok->cur;
		return STRING;
	}
	
	/* Line continuation */
	if (c == '\\') {
		c = tok_nextc(tok);
		if (c != '\n') {
			tok->done = E_TOKEN;
			tok->cur = tok->inp;
			return ERRORTOKEN;
		}
		goto again; /* Read next line */
	}
	
	/* Check for two-character token */
	{
		int c2 = tok_nextc(tok);
		int token = PyToken_TwoChars(c, c2);
		if (token != OP) {
			*p_start = tok->start;
			*p_end = tok->cur;
			return token;
		}
		tok_backup(tok, c2);
	}
	
	/* Keep track of parentheses nesting level */
	switch (c) {
	case '(':
	case '[':
	case '{':
		tok->level++;
		break;
	case ')':
	case ']':
	case '}':
		tok->level--;
		break;
	}
	
	/* Punctuation character */
	*p_start = tok->start;
	*p_end = tok->cur;
	return PyToken_OneChar(c);
}


#ifdef Py_DEBUG

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

#endif