summaryrefslogtreecommitdiffstats
path: root/Parser/tokenizer.c
blob: 885b91622ac9d45a4a0ca410088a338e403c046a (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
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504

/* Tokenizer implementation */

#include "Python.h"
#include "pgenheaders.h"

#include <ctype.h>
#include <assert.h>

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

#ifndef PGEN
#include "unicodeobject.h"
#include "stringobject.h"
#include "fileobject.h"
#include "codecs.h"
#include "abstract.h"
#endif /* PGEN */

extern char *PyOS_Readline(FILE *, FILE *, 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(void);
static int tok_nextc(struct tok_state *tok);
static void tok_backup(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",
	"PLUSEQUAL",
	"MINEQUAL",
	"STAREQUAL",
	"SLASHEQUAL",
	"PERCENTEQUAL",
	"AMPEREQUAL",
	"VBAREQUAL",
	"CIRCUMFLEXEQUAL",
	"LEFTSHIFTEQUAL",
	"RIGHTSHIFTEQUAL",
	"DOUBLESTAREQUAL",
	"DOUBLESLASH",
	"DOUBLESLASHEQUAL",
	"AT",
	/* 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(void)
{
	struct tok_state *tok = (struct tok_state *)PyMem_MALLOC(
                                                sizeof(struct tok_state));
	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 = 1;
	tok->alterror = 1;
	tok->alttabsize = 1;
	tok->altindstack[0] = 0;
	tok->decoding_state = 0;
	tok->decoding_erred = 0;
	tok->read_coding_spec = 0;
	tok->encoding = NULL;
        tok->cont_line = 0;
#ifndef PGEN
	tok->decoding_readline = NULL;
	tok->decoding_buffer = NULL;
#endif
	return tok;
}

#ifdef PGEN

static char *
decoding_fgets(char *s, int size, struct tok_state *tok)
{
	return fgets(s, size, tok->fp);
}

static int
decoding_feof(struct tok_state *tok)
{
	return feof(tok->fp);
}

static const char *
decode_str(const char *str, struct tok_state *tok)
{
	return str;
}

#else /* PGEN */

static char *
error_ret(struct tok_state *tok) /* XXX */
{
	tok->decoding_erred = 1;
	if (tok->fp != NULL && tok->buf != NULL) /* see PyTokenizer_Free */
		PyMem_FREE(tok->buf);
	tok->buf = NULL;
	return NULL;		/* as if it were EOF */
}

static char *
new_string(const char *s, Py_ssize_t len)
{
	char* result = (char *)PyMem_MALLOC(len + 1);
	if (result != NULL) {
		memcpy(result, s, len);
		result[len] = '\0';
	}
	return result;
}

static char *
get_normal_name(char *s)	/* for utf-8 and latin-1 */
{
	char buf[13];
	int i;
	for (i = 0; i < 12; i++) {
		int c = s[i];
		if (c == '\0') break;
		else if (c == '_') buf[i] = '-';
		else buf[i] = tolower(c);
	}
	buf[i] = '\0';
	if (strcmp(buf, "utf-8") == 0 ||
	    strncmp(buf, "utf-8-", 6) == 0) return "utf-8";
	else if (strcmp(buf, "latin-1") == 0 ||
		 strcmp(buf, "iso-8859-1") == 0 ||
		 strcmp(buf, "iso-latin-1") == 0 ||
		 strncmp(buf, "latin-1-", 8) == 0 ||
		 strncmp(buf, "iso-8859-1-", 11) == 0 ||
		 strncmp(buf, "iso-latin-1-", 12) == 0) return "iso-8859-1";
	else return s;
}

/* Return the coding spec in S, or NULL if none is found.  */

static char *
get_coding_spec(const char *s, Py_ssize_t size)
{
	Py_ssize_t i;
	/* Coding spec must be in a comment, and that comment must be
         * the only statement on the source code line. */
        for (i = 0; i < size - 6; i++) {
		if (s[i] == '#')
			break;
		if (s[i] != ' ' && s[i] != '\t' && s[i] != '\014')
			return NULL;
	}
	for (; i < size - 6; i++) { /* XXX inefficient search */
		const char* t = s + i;
		if (strncmp(t, "coding", 6) == 0) {
			const char* begin = NULL;
			t += 6;
			if (t[0] != ':' && t[0] != '=')
				continue;
			do {
				t++;
			} while (t[0] == '\x20' || t[0] == '\t');

			begin = t;
			while (isalnum(Py_CHARMASK(t[0])) ||
			       t[0] == '-' || t[0] == '_' || t[0] == '.')
				t++;

			if (begin < t) {
				char* r = new_string(begin, t - begin);
				char* q = get_normal_name(r);
				if (r != q) {
					PyMem_FREE(r);
					r = new_string(q, strlen(q));
				}
				return r;
			}
		}
	}
	return NULL;
}

/* Check whether the line contains a coding spec. If it does,
   invoke the set_readline function for the new encoding.
   This function receives the tok_state and the new encoding.
   Return 1 on success, 0 on failure.  */

static int
check_coding_spec(const char* line, Py_ssize_t size, struct tok_state *tok,
		  int set_readline(struct tok_state *, const char *))
{
	char * cs;
	int r = 1;

        if (tok->cont_line)
		/* It's a continuation line, so it can't be a coding spec. */
		return 1;
	cs = get_coding_spec(line, size);
	if (cs != NULL) {
		tok->read_coding_spec = 1;
		if (tok->encoding == NULL) {
			assert(tok->decoding_state == 1); /* raw */
			if (strcmp(cs, "utf-8") == 0 ||
			    strcmp(cs, "iso-8859-1") == 0) {
				tok->encoding = cs;
			} else {
#ifdef Py_USING_UNICODE
				r = set_readline(tok, cs);
				if (r) {
					tok->encoding = cs;
					tok->decoding_state = -1;
				}
				else
					PyMem_FREE(cs);
#else
                                /* Without Unicode support, we cannot
                                   process the coding spec. Since there
                                   won't be any Unicode literals, that
                                   won't matter. */
				PyMem_FREE(cs);
#endif
			}
		} else {	/* then, compare cs with BOM */
			r = (strcmp(tok->encoding, cs) == 0);
			PyMem_FREE(cs);
		}
	}
	if (!r) {
		cs = tok->encoding;
		if (!cs)
			cs = "with BOM";
		PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);
	}
	return r;
}

/* See whether the file starts with a BOM. If it does,
   invoke the set_readline function with the new encoding.
   Return 1 on success, 0 on failure.  */

static int
check_bom(int get_char(struct tok_state *),
	  void unget_char(int, struct tok_state *),
	  int set_readline(struct tok_state *, const char *),
	  struct tok_state *tok)
{
	int ch = get_char(tok);
	tok->decoding_state = 1;
	if (ch == EOF) {
		return 1;
	} else if (ch == 0xEF) {
		ch = get_char(tok); if (ch != 0xBB) goto NON_BOM;
		ch = get_char(tok); if (ch != 0xBF) goto NON_BOM;
#if 0
	/* Disable support for UTF-16 BOMs until a decision
	   is made whether this needs to be supported.  */
	} else if (ch == 0xFE) {
		ch = get_char(tok); if (ch != 0xFF) goto NON_BOM;
		if (!set_readline(tok, "utf-16-be")) return 0;
		tok->decoding_state = -1;
	} else if (ch == 0xFF) {
		ch = get_char(tok); if (ch != 0xFE) goto NON_BOM;
		if (!set_readline(tok, "utf-16-le")) return 0;
		tok->decoding_state = -1;
#endif
	} else {
		unget_char(ch, tok);
		return 1;
	}
	if (tok->encoding != NULL)
		PyMem_FREE(tok->encoding);
	tok->encoding = new_string("utf-8", 5);	/* resulting is in utf-8 */
	return 1;
  NON_BOM:
	/* any token beginning with '\xEF', '\xFE', '\xFF' is a bad token */
	unget_char(0xFF, tok);	/* XXX this will cause a syntax error */
	return 1;
}

/* Read a line of text from TOK into S, using the stream in TOK.
   Return NULL on failure, else S.

   On entry, tok->decoding_buffer will be one of:
     1) NULL: need to call tok->decoding_readline to get a new line
     2) PyUnicodeObject *: decoding_feof has called tok->decoding_readline and
           stored the result in tok->decoding_buffer
     3) PyStringObject *: previous call to fp_readl did not have enough room
           (in the s buffer) to copy entire contents of the line read
           by tok->decoding_readline.  tok->decoding_buffer has the overflow.
           In this case, fp_readl is called in a loop (with an expanded buffer)
           until the buffer ends with a '\n' (or until the end of the file is
           reached): see tok_nextc and its calls to decoding_fgets.
*/

static char *
fp_readl(char *s, int size, struct tok_state *tok)
{
#ifndef Py_USING_UNICODE
	/* In a non-Unicode built, this should never be called. */
	Py_FatalError("fp_readl should not be called in this build.");
	return NULL; /* Keep compiler happy (not reachable) */
#else
	PyObject* utf8 = NULL;
	PyObject* buf = tok->decoding_buffer;
	char *str;
	Py_ssize_t utf8len;

	/* Ask for one less byte so we can terminate it */
	assert(size > 0);
	size--;

	if (buf == NULL) {
		buf = PyObject_CallObject(tok->decoding_readline, NULL);
		if (buf == NULL)
			return error_ret(tok);
	} else {
		tok->decoding_buffer = NULL;
		if (PyString_CheckExact(buf))
			utf8 = buf;
	}
	if (utf8 == NULL) {
		utf8 = PyUnicode_AsUTF8String(buf);
		Py_DECREF(buf);
		if (utf8 == NULL)
			return error_ret(tok);
	}
	str = PyString_AsString(utf8);
	utf8len = PyString_GET_SIZE(utf8);
	if (utf8len > size) {
		tok->decoding_buffer = PyString_FromStringAndSize(str+size, utf8len-size);
		if (tok->decoding_buffer == NULL) {
			Py_DECREF(utf8);
			return error_ret(tok);
		}
		utf8len = size;
	}
	memcpy(s, str, utf8len);
	s[utf8len] = '\0';
	Py_DECREF(utf8);
	if (utf8len == 0) return NULL; /* EOF */
	return s;
#endif
}

/* Set the readline function for TOK to a StreamReader's
   readline function. The StreamReader is named ENC.

   This function is called from check_bom and check_coding_spec.

   ENC is usually identical to the future value of tok->encoding,
   except for the (currently unsupported) case of UTF-16.

   Return 1 on success, 0 on failure. */

static int
fp_setreadl(struct tok_state *tok, const char* enc)
{
	PyObject *reader, *stream, *readline;

	/* XXX: constify filename argument. */
	stream = PyFile_FromFile(tok->fp, (char*)tok->filename, "rb", NULL);
	if (stream == NULL)
		return 0;

	reader = PyCodec_StreamReader(enc, stream, NULL);
	Py_DECREF(stream);
	if (reader == NULL)
		return 0;

	readline = PyObject_GetAttrString(reader, "readline");
	Py_DECREF(reader);
	if (readline == NULL)
		return 0;

	tok->decoding_readline = readline;
	return 1;
}

/* Fetch the next byte from TOK. */

static int fp_getc(struct tok_state *tok) {
	return getc(tok->fp);
}

/* Unfetch the last byte back into TOK.  */

static void fp_ungetc(int c, struct tok_state *tok) {
	ungetc(c, tok->fp);
}

/* Read a line of input from TOK. Determine encoding
   if necessary.  */

static char *
decoding_fgets(char *s, int size, struct tok_state *tok)
{
	char *line = NULL;
	int badchar = 0;
	for (;;) {
		if (tok->decoding_state < 0) {
			/* We already have a codec associated with
			   this input. */
			line = fp_readl(s, size, tok);
			break;
		} else if (tok->decoding_state > 0) {
			/* We want a 'raw' read. */
			line = Py_UniversalNewlineFgets(s, size,
							tok->fp, NULL);
			break;
		} else {
			/* We have not yet determined the encoding.
			   If an encoding is found, use the file-pointer
			   reader functions from now on. */
			if (!check_bom(fp_getc, fp_ungetc, fp_setreadl, tok))
				return error_ret(tok);
			assert(tok->decoding_state != 0);
		}
	}
	if (line != NULL && tok->lineno < 2 && !tok->read_coding_spec) {
		if (!check_coding_spec(line, strlen(line), tok, fp_setreadl)) {
			return error_ret(tok);
		}
	}
#ifndef PGEN
	/* The default encoding is ASCII, so make sure we don't have any
           non-ASCII bytes in it. */
	if (line && !tok->encoding) {
		unsigned char *c;
		for (c = (unsigned char *)line; *c; c++)
			if (*c > 127) {
				badchar = *c;
				break;
			}
	}
	if (badchar) {
		char buf[500];
		/* Need to add 1 to the line number, since this line
		   has not been counted, yet.  */
		sprintf(buf,
			"Non-ASCII character '\\x%.2x' "
			"in file %.200s on line %i, "
			"but no encoding declared; "
			"see http://www.python.org/peps/pep-0263.html for details",
			badchar, tok->filename, tok->lineno + 1);
		PyErr_SetString(PyExc_SyntaxError, buf);
		return error_ret(tok);
	}
#endif
	return line;
}

static int
decoding_feof(struct tok_state *tok)
{
	if (tok->decoding_state >= 0) {
		return feof(tok->fp);
	} else {
		PyObject* buf = tok->decoding_buffer;
		if (buf == NULL) {
			buf = PyObject_CallObject(tok->decoding_readline, NULL);
			if (buf == NULL) {
				error_ret(tok);
				return 1;
			} else {
				tok->decoding_buffer = buf;
			}
		}
		return PyObject_Length(buf) == 0;
	}
}

/* Fetch a byte from TOK, using the string buffer. */

static int
buf_getc(struct tok_state *tok) {
	return Py_CHARMASK(*tok->str++);
}

/* Unfetch a byte from TOK, using the string buffer. */

static void
buf_ungetc(int c, struct tok_state *tok) {
	tok->str--;
	assert(Py_CHARMASK(*tok->str) == c);	/* tok->cur may point to read-only segment */
}

/* Set the readline function for TOK to ENC. For the string-based
   tokenizer, this means to just record the encoding. */

static int
buf_setreadl(struct tok_state *tok, const char* enc) {
	tok->enc = enc;
	return 1;
}

/* Return a UTF-8 encoding Python string object from the
   C byte string STR, which is encoded with ENC. */

#ifdef Py_USING_UNICODE
static PyObject *
translate_into_utf8(const char* str, const char* enc) {
	PyObject *utf8;
	PyObject* buf = PyUnicode_Decode(str, strlen(str), enc, NULL);
	if (buf == NULL)
		return NULL;
	utf8 = PyUnicode_AsUTF8String(buf);
	Py_DECREF(buf);
	return utf8;
}
#endif

/* Decode a byte string STR for use as the buffer of TOK.
   Look for encoding declarations inside STR, and record them
   inside TOK.  */

static const char *
decode_str(const char *str, struct tok_state *tok)
{
	PyObject* utf8 = NULL;
	const char *s;
	int lineno = 0;
	tok->enc = NULL;
	tok->str = str;
	if (!check_bom(buf_getc, buf_ungetc, buf_setreadl, tok))
		return error_ret(tok);
	str = tok->str;		/* string after BOM if any */
	assert(str);
#ifdef Py_USING_UNICODE
	if (tok->enc != NULL) {
		utf8 = translate_into_utf8(str, tok->enc);
		if (utf8 == NULL)
			return error_ret(tok);
		str = PyString_AsString(utf8);
	}
#endif
	for (s = str;; s++) {
		if (*s == '\0') break;
		else if (*s == '\n') {
			lineno++;
			if (lineno == 2) break;
		}
	}
	tok->enc = NULL;
	if (!check_coding_spec(str, s - str, tok, buf_setreadl))
		return error_ret(tok);
#ifdef Py_USING_UNICODE
	if (tok->enc != NULL) {
		assert(utf8 == NULL);
		utf8 = translate_into_utf8(str, tok->enc);
		if (utf8 == NULL) {
			PyErr_Format(PyExc_SyntaxError,
				"unknown encoding: %s", tok->enc);
			return error_ret(tok);
		}
		str = PyString_AsString(utf8);
	}
#endif
	assert(tok->decoding_buffer == NULL);
	tok->decoding_buffer = utf8; /* CAUTION */
	return str;
}

#endif /* PGEN */

/* Set up tokenizer for string */

struct tok_state *
PyTokenizer_FromString(const char *str)
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	str = (char *)decode_str(str, tok);
	if (str == NULL) {
		PyTokenizer_Free(tok);
		return NULL;
	}

	/* XXX: constify members. */
	tok->buf = tok->cur = tok->end = tok->inp = (char*)str;
	return tok;
}


/* Set up tokenizer for file */

struct tok_state *
PyTokenizer_FromFile(FILE *fp, char *ps1, char *ps2)
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	if ((tok->buf = (char *)PyMem_MALLOC(BUFSIZ)) == NULL) {
		PyTokenizer_Free(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(struct tok_state *tok)
{
	if (tok->encoding != NULL)
		PyMem_FREE(tok->encoding);
#ifndef PGEN
	Py_XDECREF(tok->decoding_readline);
	Py_XDECREF(tok->decoding_buffer);
#endif
	if (tok->fp != NULL && tok->buf != NULL)
		PyMem_FREE(tok->buf);
	PyMem_FREE(tok);
}

#if !defined(PGEN) && defined(Py_USING_UNICODE)
static int
tok_stdin_decode(struct tok_state *tok, char **inp)
{
	PyObject *enc, *sysstdin, *decoded, *utf8;
	const char *encoding;
	char *converted;

	if (PySys_GetFile((char *)"stdin", NULL) != stdin)
		return 0;
	sysstdin = PySys_GetObject("stdin");
	if (sysstdin == NULL || !PyFile_Check(sysstdin))
		return 0;

	enc = ((PyFileObject *)sysstdin)->f_encoding;
	if (enc == NULL || !PyString_Check(enc))
		return 0;
	Py_INCREF(enc);

	encoding = PyString_AsString(enc);
	decoded = PyUnicode_Decode(*inp, strlen(*inp), encoding, NULL);
	if (decoded == NULL)
		goto error_clear;

	utf8 = PyUnicode_AsEncodedString(decoded, "utf-8", NULL);
	Py_DECREF(decoded);
	if (utf8 == NULL)
		goto error_clear;

	assert(PyString_Check(utf8));
	converted = new_string(PyString_AS_STRING(utf8),
			       PyString_GET_SIZE(utf8));
	Py_DECREF(utf8);
	if (converted == NULL)
		goto error_nomem;

	PyMem_FREE(*inp);
	*inp = converted;
	if (tok->encoding != NULL)
		PyMem_FREE(tok->encoding);
	tok->encoding = new_string(encoding, strlen(encoding));
	if (tok->encoding == NULL)
		goto error_nomem;

	Py_DECREF(enc);
	return 0;

error_nomem:
	Py_DECREF(enc);
	tok->done = E_NOMEM;
	return -1;

error_clear:
	/* Fallback to iso-8859-1: for backward compatibility */
	Py_DECREF(enc);
	PyErr_Clear();
	return 0;
}
#endif

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

static int
tok_nextc(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->line_start = tok->cur;
			tok->lineno++;
			tok->inp = end;
			return Py_CHARMASK(*tok->cur++);
		}
		if (tok->prompt != NULL) {
			char *newtok = PyOS_Readline(stdin, stdout, tok->prompt);
			if (tok->nextprompt != NULL)
				tok->prompt = tok->nextprompt;
			if (newtok == NULL)
				tok->done = E_INTR;
			else if (*newtok == '\0') {
				PyMem_FREE(newtok);
				tok->done = E_EOF;
			}
#if !defined(PGEN) && defined(Py_USING_UNICODE)
			else if (tok_stdin_decode(tok, &newtok) != 0)
				PyMem_FREE(newtok);
#endif
			else if (tok->start != NULL) {
				size_t start = tok->start - tok->buf;
				size_t oldlen = tok->cur - tok->buf;
				size_t newlen = oldlen + strlen(newtok);
				char *buf = tok->buf;
				buf = (char *)PyMem_REALLOC(buf, newlen+1);
				tok->lineno++;
				if (buf == NULL) {
					PyMem_FREE(tok->buf);
					tok->buf = NULL;
					PyMem_FREE(newtok);
					tok->done = E_NOMEM;
					return EOF;
				}
				tok->buf = buf;
				tok->cur = tok->buf + oldlen;
				tok->line_start = tok->cur;
				strcpy(tok->buf + oldlen, newtok);
				PyMem_FREE(newtok);
				tok->inp = tok->buf + newlen;
				tok->end = tok->inp + 1;
				tok->start = tok->buf + start;
			}
			else {
				tok->lineno++;
				if (tok->buf != NULL)
					PyMem_FREE(tok->buf);
				tok->buf = newtok;
				tok->line_start = tok->buf;
				tok->cur = tok->buf;
				tok->line_start = tok->buf;
				tok->inp = strchr(tok->buf, '\0');
				tok->end = tok->inp + 1;
			}
		}
		else {
			int done = 0;
			Py_ssize_t cur = 0;
			char *pt;
			if (tok->start == NULL) {
				if (tok->buf == NULL) {
					tok->buf = (char *)
						PyMem_MALLOC(BUFSIZ);
					if (tok->buf == NULL) {
						tok->done = E_NOMEM;
						return EOF;
					}
					tok->end = tok->buf + BUFSIZ;
				}
				if (decoding_fgets(tok->buf, (int)(tok->end - tok->buf),
					  tok) == 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 (decoding_feof(tok)) {
					tok->done = E_EOF;
					done = 1;
				}
				else
					tok->done = E_OK;
			}
			tok->lineno++;
			/* Read until '\n' or EOF */
			while (!done) {
				Py_ssize_t curstart = tok->start == NULL ? -1 :
					          tok->start - tok->buf;
				Py_ssize_t curvalid = tok->inp - tok->buf;
				Py_ssize_t newsize = curvalid + BUFSIZ;
				char *newbuf = tok->buf;
				newbuf = (char *)PyMem_REALLOC(newbuf,
							       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 (decoding_fgets(tok->inp,
					       (int)(tok->end - tok->inp),
					       tok) == NULL) {
					/* Break out early on decoding
					   errors, as tok->buf will be NULL
					 */
					if (tok->decoding_erred)
						return EOF;
					/* Last line does not end in \n,
					   fake one */
					strcpy(tok->inp, "\n");
				}
				tok->inp = strchr(tok->inp, '\0');
				done = tok->inp[-1] == '\n';
			}
			if (tok->buf != NULL) {
				tok->cur = tok->buf + cur;
				tok->line_start = tok->cur;
				/* replace "\r\n" with "\n" */
				/* For Mac leave the \r, giving syntax error */
				pt = tok->inp - 2;
				if (pt >= tok->buf && *pt == '\r') {
					*pt++ = '\n';
					*pt = '\0';
					tok->inp = pt;
				}
			}
		}
		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(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(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;
	case '@':       return AT;
	default:	return OP;
	}
}


int
PyToken_TwoChars(int c1, int 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 PLUSEQUAL;
		}
		break;
	case '-':
		switch (c2) {
		case '=':	return MINEQUAL;
		}
		break;
	case '*':
		switch (c2) {
		case '*':	return DOUBLESTAR;
		case '=':	return STAREQUAL;
		}
		break;
	case '/':
		switch (c2) {
		case '/':	return DOUBLESLASH;
		case '=':	return SLASHEQUAL;
		}
		break;
	case '|':
		switch (c2) {
		case '=':	return VBAREQUAL;
		}
		break;
	case '%':
		switch (c2) {
		case '=':	return PERCENTEQUAL;
		}
		break;
	case '&':
		switch (c2) {
		case '=':	return AMPEREQUAL;
		}
		break;
	case '^':
		switch (c2) {
		case '=':	return CIRCUMFLEXEQUAL;
		}
		break;
	}
	return OP;
}

int
PyToken_ThreeChars(int c1, int c2, int c3)
{
	switch (c1) {
	case '<':
		switch (c2) {
		case '<':
			switch (c3) {
			case '=':
				return LEFTSHIFTEQUAL;
			}
			break;
		}
		break;
	case '>':
		switch (c2) {
		case '>':
			switch (c3) {
			case '=':
				return RIGHTSHIFTEQUAL;
			}
			break;
		}
		break;
	case '*':
		switch (c2) {
		case '*':
			switch (c3) {
			case '=':
				return DOUBLESTAREQUAL;
			}
			break;
		}
		break;
	case '/':
		switch (c2) {
		case '/':
			switch (c3) {
			case '=':
				return DOUBLESLASHEQUAL;
			}
			break;
		}
		break;
	}
	return OP;
}

static int
indenterror(struct tok_state *tok)
{
	if (tok->alterror) {
		tok->done = E_TABSPACE;
		tok->cur = tok->inp;
		return 1;
	}
	if (tok->altwarning) {
		PySys_WriteStderr("%s: inconsistent use of tabs and spaces "
                                  "in indentation\n", tok->filename);
		tok->altwarning = 0;
	}
	return 0;
}


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

static int
tok_get(register struct tok_state *tok, char **p_start, char **p_end)
{
	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) {
					tok->done = E_TOODEEP;
					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]) {
					tok->done = E_DEDENT;
					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 */
	if (c == '#')
		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 */
                tok->cont_line = 0;
		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_start = tok->start;
			*p_end = tok->cur;
			return DOT;
		}
	}

	/* Number */
	if (isdigit(c)) {
		if (c == '0') {
			/* Hex or octal -- maybe. */
			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 {
				int found_decimal = 0;
				/* Octal; c is first char of it */
				/* There's no 'isoctdigit' macro, sigh */
				while ('0' <= c && c < '8') {
					c = tok_nextc(tok);
				}
				if (isdigit(c)) {
					found_decimal = 1;
					do {
						c = tok_nextc(tok);
					} while (isdigit(c));
				}
				if (c == '.')
					goto fraction;
				else if (c == 'e' || c == 'E')
					goto exponent;
#ifndef WITHOUT_COMPLEX
				else if (c == 'j' || c == 'J')
					goto imaginary;
#endif
				else if (found_decimal) {
					tok->done = E_TOKEN;
					tok_backup(tok, c);
					return ERRORTOKEN;
				}
			}
			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. */
				if (c == '.') {
		fraction:
					/* Fraction */
					do {
						c = tok_nextc(tok);
					} while (isdigit(c));
				}
				if (c == 'e' || c == 'E') {
		exponent:
					/* Exponent part */
					c = tok_nextc(tok);
					if (c == '+' || c == '-')
						c = tok_nextc(tok);
					if (!isdigit(c)) {
						tok->done = E_TOKEN;
						tok_backup(tok, c);
						return ERRORTOKEN;
					}
					do {
						c = tok_nextc(tok);
					} while (isdigit(c));
				}
#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 == '"') {
		Py_ssize_t 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_EOLS;
					tok_backup(tok, c);
					return ERRORTOKEN;
				}
				tripcount = 0;
                                tok->cont_line = 1; /* multiline string. */
			}
			else if (c == EOF) {
				if (triple)
					tok->done = E_EOFS;
				else
					tok->done = E_EOLS;
				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_EOLS;
					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_LINECONT;
			tok->cur = tok->inp;
			return ERRORTOKEN;
		}
                tok->cont_line = 1;
		goto again; /* Read next line */
	}

	/* Check for two-character token */
	{
		int c2 = tok_nextc(tok);
		int token = PyToken_TwoChars(c, c2);
		if (token != OP) {
			int c3 = tok_nextc(tok);
			int token3 = PyToken_ThreeChars(c, c2, c3);
			if (token3 != OP) {
				token = token3;
			} else {
				tok_backup(tok, c3);
			}
			*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);
}

int
PyTokenizer_Get(struct tok_state *tok, char **p_start, char **p_end)
{
	int result = tok_get(tok, p_start, p_end);
	if (tok->decoding_erred) {
		result = ERRORTOKEN;
		tok->done = E_DECODE;
	}
	return result;
}

#ifdef Py_DEBUG

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

#endif