summaryrefslogtreecommitdiff
path: root/sfeed.c
blob: a77afb3d2d279bcac1878bbb5f6133f06987ada8 (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
#include <errno.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <strings.h>

#include "util.h"
#include "xml.h"

#define ISINCONTENT(ctx)  ((ctx).iscontent && !((ctx).iscontenttag))
#define ISCONTENTTAG(ctx) (!((ctx).iscontent) && (ctx).iscontenttag)

/* these feed fields support multiple separated values */
#define ISFEEDFIELDMULTI(t) ((t) == FeedFieldCategory)

/* string and byte-length */
#define STRP(s)           s,sizeof(s)-1

enum FeedType {
	FeedTypeNone = 0,
	FeedTypeRSS  = 1,
	FeedTypeAtom = 2
};

enum ContentType {
	ContentTypeNone  = 0,
	ContentTypePlain = 1,
	ContentTypeHTML  = 2
};
static const char *contenttypes[] = { "", "plain", "html" };

/* String data / memory pool */
typedef struct string {
	char   *data;   /* data */
	size_t  len;    /* string length */
	size_t  bufsiz; /* allocated size */
} String;

/* NOTE: the order of these fields (content, date, author) indicate the
 *       priority to use them, from least important to high. */
enum TagId {
	TagUnknown = 0,
	/* RSS */
	RSSTagDcdate, RSSTagPubdate, /* creation date has higher priority */
	RSSTagTitle,
	RSSTagMediaDescription, RSSTagDescription, RSSTagContentEncoded,
	RSSTagGuid,
	RSSTagGuidPermalinkFalse,
	RSSTagGuidPermalinkTrue,
	/* must be defined after GUID, because it can be a link (isPermaLink) */
	RSSTagLink,
	RSSTagEnclosure,
	RSSTagAuthor, RSSTagDccreator,
	RSSTagCategory,
	/* Atom */
	/* creation date has higher priority */
	AtomTagModified, AtomTagUpdated, AtomTagIssued, AtomTagPublished,
	AtomTagTitle,
	AtomTagMediaDescription, AtomTagSummary, AtomTagContent,
	AtomTagId,
	AtomTagLink,
	AtomTagLinkAlternate,
	AtomTagLinkEnclosure,
	AtomTagAuthor, AtomTagAuthorName,
	AtomTagCategory,
	TagLast
};

typedef struct feedtag {
	char       *name; /* name of tag to match */
	size_t      len;  /* len of `name` */
	enum TagId  id;   /* unique ID */
} FeedTag;

typedef struct field {
	String     str;
	enum TagId tagid; /* tagid set previously, used for tag priority */
} FeedField;

enum {
	FeedFieldTime = 0, FeedFieldTitle, FeedFieldLink, FeedFieldContent,
	FeedFieldId, FeedFieldAuthor, FeedFieldEnclosure, FeedFieldCategory,
	FeedFieldLast
};

typedef struct feedcontext {
	String          *field;        /* current FeedItem field String */
	FeedField        fields[FeedFieldLast]; /* data for current item */
	FeedTag          tag;          /* unique current parsed tag */
	int              iscontent;    /* in content data */
	int              iscontenttag; /* in content tag */
	enum ContentType contenttype;  /* content-type for item */
	enum FeedType    feedtype;
	int              attrcount;    /* count item HTML element attributes */
} FeedContext;

static long long datetounix(long long, int, int, int, int, int);
static FeedTag * gettag(enum FeedType, const char *, size_t);
static long gettzoffset(const char *);
static int  isattr(const char *, size_t, const char *, size_t);
static int  istag(const char *, size_t, const char *, size_t);
static int  parsetime(const char *, long long *);
static void printfields(void);
static void string_append(String *, const char *, size_t);
static void string_buffer_realloc(String *, size_t);
static void string_clear(String *);
static void string_print_encoded(String *);
static void string_print_timestamp(String *);
static void string_print_trimmed(String *);
static void string_print_trimmed_multi(String *);
static void string_print_uri(String *);
static void xmlattr(XMLParser *, const char *, size_t, const char *, size_t,
                    const char *, size_t);
static void xmlattrentity(XMLParser *, const char *, size_t, const char *,
                          size_t, const char *, size_t);
static void xmlattrend(XMLParser *, const char *, size_t, const char *,
                       size_t);
static void xmlattrstart(XMLParser *, const char *, size_t, const char *,
                         size_t);
static void xmldata(XMLParser *, const char *, size_t);
static void xmldataentity(XMLParser *, const char *, size_t);
static void xmltagend(XMLParser *, const char *, size_t, int);
static void xmltagstart(XMLParser *, const char *, size_t);
static void xmltagstartparsed(XMLParser *, const char *, size_t, int);

/* map tag name to TagId type */
/* RSS, must be alphabetical order */
static const FeedTag rsstags[] = {
	{ STRP("author"),            RSSTagAuthor            },
	{ STRP("category"),          RSSTagCategory          },
	{ STRP("content:encoded"),   RSSTagContentEncoded    },
	{ STRP("dc:creator"),        RSSTagDccreator         },
	{ STRP("dc:date"),           RSSTagDcdate            },
	{ STRP("description"),       RSSTagDescription       },
	/* RSS: <enclosure url="" />, Atom has <link rel="enclosure" /> */
	{ STRP("enclosure"),         RSSTagEnclosure         },
	{ STRP("guid"),              RSSTagGuid              },
	{ STRP("link"),              RSSTagLink              },
	{ STRP("media:description"), RSSTagMediaDescription  },
	{ STRP("pubdate"),           RSSTagPubdate           },
	{ STRP("title"),             RSSTagTitle             }
};

/* Atom, must be alphabetical order */
static const FeedTag atomtags[] = {
	{ STRP("author"),            AtomTagAuthor           },
	{ STRP("category"),          AtomTagCategory         },
	{ STRP("content"),           AtomTagContent          },
	{ STRP("id"),                AtomTagId               },
	{ STRP("issued"),            AtomTagIssued           }, /* Atom 0.3 */
	/* Atom: <link href="" />, RSS has <link></link> */
	{ STRP("link"),              AtomTagLink             },
	{ STRP("media:description"), AtomTagMediaDescription },
	{ STRP("modified"),          AtomTagModified         }, /* Atom 0.3 */
	{ STRP("published"),         AtomTagPublished        },
	{ STRP("summary"),           AtomTagSummary          },
	{ STRP("title"),             AtomTagTitle            },
	{ STRP("updated"),           AtomTagUpdated          }
};

/* special case: nested <author><name> */
static const FeedTag atomtagauthor = { STRP("author"), AtomTagAuthor };
static const FeedTag atomtagauthorname = { STRP("name"), AtomTagAuthorName };

/* reference to no / unknown tag */
static const FeedTag notag = { STRP(""), TagUnknown };

/* map TagId type to RSS/Atom field, all tags must be defined */
static const int fieldmap[TagLast] = {
	[TagUnknown]               = -1,
	/* RSS */
	[RSSTagDcdate]             = FeedFieldTime,
	[RSSTagPubdate]            = FeedFieldTime,
	[RSSTagTitle]              = FeedFieldTitle,
	[RSSTagMediaDescription]   = FeedFieldContent,
	[RSSTagDescription]        = FeedFieldContent,
	[RSSTagContentEncoded]     = FeedFieldContent,
	[RSSTagGuid]               = -1,
	[RSSTagGuidPermalinkFalse] = FeedFieldId,
	[RSSTagGuidPermalinkTrue]  = FeedFieldId, /* special-case: both a link and an id */
	[RSSTagLink]               = FeedFieldLink,
	[RSSTagEnclosure]          = FeedFieldEnclosure,
	[RSSTagAuthor]             = FeedFieldAuthor,
	[RSSTagDccreator]          = FeedFieldAuthor,
	[RSSTagCategory]           = FeedFieldCategory,
	/* Atom */
	[AtomTagModified]          = FeedFieldTime,
	[AtomTagUpdated]           = FeedFieldTime,
	[AtomTagIssued]            = FeedFieldTime,
	[AtomTagPublished]         = FeedFieldTime,
	[AtomTagTitle]             = FeedFieldTitle,
	[AtomTagMediaDescription]  = FeedFieldContent,
	[AtomTagSummary]           = FeedFieldContent,
	[AtomTagContent]           = FeedFieldContent,
	[AtomTagId]                = FeedFieldId,
	[AtomTagLink]              = -1,
	[AtomTagLinkAlternate]     = FeedFieldLink,
	[AtomTagLinkEnclosure]     = FeedFieldEnclosure,
	[AtomTagAuthor]            = -1,
	[AtomTagAuthorName]        = FeedFieldAuthor,
	[AtomTagCategory]          = FeedFieldCategory
};

static const int FieldSeparator = '\t';
/* separator for multiple values in a field, separator should be 1 byte */
static const char FieldMultiSeparator[] = "|";
static struct uri baseuri;
static const char *baseurl;

static FeedContext ctx;
static XMLParser parser; /* XML parser state */
static String attrispermalink, attrrel, attrtype, tmpstr;

static int
tagcmp(const void *v1, const void *v2)
{
	return strcasecmp(((FeedTag *)v1)->name, ((FeedTag *)v2)->name);
}

/* Unique tagid for parsed tag name. */
static FeedTag *
gettag(enum FeedType feedtype, const char *name, size_t namelen)
{
	FeedTag f, *r = NULL;

	f.name = (char *)name;

	switch (feedtype) {
	case FeedTypeRSS:
		r = bsearch(&f, rsstags, sizeof(rsstags) / sizeof(rsstags[0]),
		        sizeof(rsstags[0]), tagcmp);
		break;
	case FeedTypeAtom:
		r = bsearch(&f, atomtags, sizeof(atomtags) / sizeof(atomtags[0]),
		        sizeof(atomtags[0]), tagcmp);
		break;
	default:
		break;
	}

	return r;
}

static char *
ltrim(const char *s)
{
	for (; ISSPACE((unsigned char)*s); s++)
		;
	return (char *)s;
}

static char *
rtrim(const char *s)
{
	const char *e;

	for (e = s + strlen(s); e > s && ISSPACE((unsigned char)*(e - 1)); e--)
		;
	return (char *)e;
}

/* Clear string only; don't free, prevents unnecessary reallocation. */
static void
string_clear(String *s)
{
	if (s->data)
		s->data[0] = '\0';
	s->len = 0;
}

static void
string_buffer_realloc(String *s, size_t newlen)
{
	size_t alloclen;

	if (newlen > SIZE_MAX / 2) {
		alloclen = SIZE_MAX;
	} else {
		for (alloclen = 64; alloclen <= newlen; alloclen *= 2)
			;
	}
	if (!(s->data = realloc(s->data, alloclen)))
		err(1, "realloc");
	s->bufsiz = alloclen;
}

/* Append data to String, s->data and data may not overlap. */
static void
string_append(String *s, const char *data, size_t len)
{
	if (!len)
		return;

	if (s->len >= SIZE_MAX - len) {
		errno = EOVERFLOW;
		err(1, "realloc");
	}

	/* check if allocation is necessary, never shrink the buffer. */
	if (s->len + len >= s->bufsiz)
		string_buffer_realloc(s, s->len + len + 1);
	memcpy(s->data + s->len, data, len);
	s->len += len;
	s->data[s->len] = '\0';
}

/* Print text, encode TABs, newlines and '\', remove other whitespace.
 * Remove leading and trailing whitespace. */
static void
string_print_encoded(String *s)
{
	const char *p, *e;

	if (!s->data || !s->len)
		return;

	p = ltrim(s->data);
	e = rtrim(p);

	for (; *p && p != e; p++) {
		switch (*p) {
		case '\n': putchar('\\'); putchar('n'); break;
		case '\\': putchar('\\'); putchar('\\'); break;
		case '\t': putchar('\\'); putchar('t'); break;
		default:
			/* ignore control chars */
			if (!ISCNTRL((unsigned char)*p))
				putchar(*p);
			break;
		}
	}
}

static void
printtrimmed(const char *s)
{
	char *p, *e;

	p = ltrim(s);
	e = rtrim(p);
	for (; *p && p != e; p++) {
		if (ISSPACE((unsigned char)*p))
			putchar(' '); /* any whitespace to space */
		else if (!ISCNTRL((unsigned char)*p))
			/* ignore other control chars */
			putchar(*p);
	}
}

/* Print text, replace TABs, carriage return and other whitespace with ' '.
 * Other control chars are removed. Remove leading and trailing whitespace. */
static void
string_print_trimmed(String *s)
{
	if (!s->data || !s->len)
		return;

	printtrimmed(s->data);
}

/* Print each field with trimmed whitespace, separated by '|'. */
static void
string_print_trimmed_multi(String *s)
{
	char *p, *e;
	int c;

	if (!s->data || !s->len)
		return;

	for (p = s->data; ; p = e + 1) {
		if ((e = strstr(p, FieldMultiSeparator))) {
			c = *e;
			*e = '\0';
			printtrimmed(p);
			*e = c; /* restore NUL byte to original character */
			fputs(FieldMultiSeparator, stdout);
		} else {
			printtrimmed(p);
			break;
		}
	}
}

/* Print URL, if it's a relative URL then it uses the global `baseurl`. */
static void
printuri(char *s)
{
	char link[4096], *p, *e;
	struct uri newuri, olduri;
	int c, r = -1;

	p = ltrim(s);
	e = rtrim(p);
	c = *e;
	*e = '\0';

	if (baseurl && !uri_hasscheme(p) &&
	    uri_parse(p, &olduri) != -1 && !olduri.proto[0] &&
	    uri_makeabs(&newuri, &olduri, &baseuri) != -1 && newuri.proto[0])
		r = uri_format(link, sizeof(link), &newuri);

	if (r >= 0 && (size_t)r < sizeof(link))
		printtrimmed(link);
	else
		printtrimmed(p);

	*e = c; /* restore NUL byte to original character */
}

/* Print URL, if it's a relative URL then it uses the global `baseurl`. */
static void
string_print_uri(String *s)
{
	if (!s->data || !s->len)
		return;

	printuri(s->data);
}

/* Print as UNIX timestamp, print nothing if the time is empty or invalid. */
static void
string_print_timestamp(String *s)
{
	long long t;

	if (!s->data || !s->len)
		return;

	if (parsetime(s->data, &t) != -1)
		printf("%lld", t);
}

/* Convert time fields. Returns a UNIX timestamp. */
static long long
datetounix(long long year, int mon, int day, int hour, int min, int sec)
{
	static const int secs_through_month[] = {
		0, 31 * 86400, 59 * 86400, 90 * 86400,
		120 * 86400, 151 * 86400, 181 * 86400, 212 * 86400,
		243 * 86400, 273 * 86400, 304 * 86400, 334 * 86400 };
	int is_leap = 0, cycles, centuries = 0, leaps = 0, rem;
	long long t;

	if (year - 2ULL <= 136) {
		leaps = (year - 68) >> 2;
		if (!((year - 68) & 3)) {
			leaps--;
			is_leap = 1;
		} else {
			is_leap = 0;
		}
		t = 31536000 * (year - 70) + 86400 * leaps;
	} else {
		cycles = (year - 100) / 400;
		rem = (year - 100) % 400;
		if (rem < 0) {
			cycles--;
			rem += 400;
		}
		if (!rem) {
			is_leap = 1;
		} else {
			if (rem >= 300)
				centuries = 3, rem -= 300;
			else if (rem >= 200)
				centuries = 2, rem -= 200;
			else if (rem >= 100)
				centuries = 1, rem -= 100;
			if (rem) {
				leaps = rem / 4U;
				rem %= 4U;
				is_leap = !rem;
			}
		}
		leaps += 97 * cycles + 24 * centuries - is_leap;
		t = (year - 100) * 31536000LL + leaps * 86400LL + 946684800 + 86400;
	}
	t += secs_through_month[mon];
	if (is_leap && mon >= 2)
		t += 86400;
	t += 86400LL * (day - 1);
	t += 3600LL * hour;
	t += 60LL * min;
	t += sec;

	return t;
}

/* Get timezone from string, return time offset in seconds from UTC.
 * NOTE: only parses timezones in RFC-822, many other timezone names are
 * ambiguous anyway.
 * ANSI and military zones are defined wrong in RFC822 and are unsupported,
 * see note on RFC2822 4.3 page 32. */
static long
gettzoffset(const char *s)
{
	static const struct {
		char *name;
		int offhour;
	} tzones[] = {
		{ "CDT", -5 * 3600 },
		{ "CST", -6 * 3600 },
		{ "EDT", -4 * 3600 },
		{ "EST", -5 * 3600 },
		{ "MDT", -6 * 3600 },
		{ "MST", -7 * 3600 },
		{ "PDT", -7 * 3600 },
		{ "PST", -8 * 3600 },
	};
	const char *p;
	long tzhour = 0, tzmin = 0;
	size_t i;

	for (; ISSPACE((unsigned char)*s); s++)
		;
	switch (*s) {
	case '-': /* offset */
	case '+':
		for (i = 0, p = s + 1; i < 2 && ISDIGIT((unsigned char)*p); i++, p++)
			tzhour = (tzhour * 10) + (*p - '0');
		if (*p == ':')
			p++;
		for (i = 0; i < 2 && ISDIGIT((unsigned char)*p); i++, p++)
			tzmin = (tzmin * 10) + (*p - '0');
		return ((tzhour * 3600) + (tzmin * 60)) * (s[0] == '-' ? -1 : 1);
	default: /* timezone name */
		for (i = 0; ISALPHA((unsigned char)s[i]); i++)
			;
		if (i != 3)
			return 0;
		/* compare tz and adjust offset relative to UTC */
		for (i = 0; i < sizeof(tzones) / sizeof(*tzones); i++) {
			if (!memcmp(s, tzones[i].name, 3))
				return tzones[i].offhour;
		}
	}
	return 0;
}

/* Parse time string `s` into the UNIX timestamp `tp`.
   Returns 0 on success or -1 on failure. */
static int
parsetime(const char *s, long long *tp)
{
	static const struct {
		char *name;
		int len;
	} mons[] = {
		{ STRP("January"),   },
		{ STRP("February"),  },
		{ STRP("March"),     },
		{ STRP("April"),     },
		{ STRP("May"),       },
		{ STRP("June"),      },
		{ STRP("July"),      },
		{ STRP("August"),    },
		{ STRP("September"), },
		{ STRP("October"),   },
		{ STRP("November"),  },
		{ STRP("December"),  },
	};
	int va[6] = { 0 }, i, j, v, vi;
	size_t m;

	for (; ISSPACE((unsigned char)*s); s++)
		;
	if (!ISDIGIT((unsigned char)*s) && !ISALPHA((unsigned char)*s))
		return -1;

	if (ISDIGIT((unsigned char)s[0]) &&
	    ISDIGIT((unsigned char)s[1]) &&
	    ISDIGIT((unsigned char)s[2]) &&
	    ISDIGIT((unsigned char)s[3])) {
		/* formats "%Y-%m-%d %H:%M:%S", "%Y-%m-%dT%H:%M:%S" or "%Y%m%d%H%M%S" */
		vi = 0;
	} else {
		/* format: "[%a, ]%d %b %Y %H:%M:%S" */
		/* parse "[%a, ]%d %b %Y " part, then use time parsing as above */
		for (; ISALPHA((unsigned char)*s); s++)
			;
		for (; ISSPACE((unsigned char)*s); s++)
			;
		if (*s == ',')
			s++;
		for (; ISSPACE((unsigned char)*s); s++)
			;
		for (v = 0, i = 0; i < 2 && ISDIGIT((unsigned char)*s); s++, i++)
			v = (v * 10) + (*s - '0');
		va[2] = v; /* day */
		for (; ISSPACE((unsigned char)*s); s++)
			;
		/* end of word month */
		for (j = 0; ISALPHA((unsigned char)s[j]); j++)
			;
		/* check month name */
		if (j < 3 || j > 9)
			return -1; /* month cannot match */
		for (m = 0; m < sizeof(mons) / sizeof(*mons); m++) {
			/* abbreviation (3 length) or long name */
			if ((j == 3 || j == mons[m].len) &&
			    !strncasecmp(mons[m].name, s, j)) {
				va[1] = m + 1;
				s += j;
				break;
			}
		}
		if (m >= 12)
			return -1; /* no month found */
		for (; ISSPACE((unsigned char)*s); s++)
			;
		for (v = 0, i = 0; i < 4 && ISDIGIT((unsigned char)*s); s++, i++)
			v = (v * 10) + (*s - '0');
		/* obsolete short year: RFC2822 4.3 */
		if (i <= 3)
			v += (v >= 0 && v <= 49) ? 2000 : 1900;
		va[0] = v; /* year */
		for (; ISSPACE((unsigned char)*s); s++)
			;
		/* parse only regular time part, see below */
		vi = 3;
	}

	/* parse time parts (and possibly remaining date parts) */
	for (; *s && vi < 6; vi++) {
		for (i = 0, v = 0; i < ((vi == 0) ? 4 : 2) &&
		                   ISDIGIT((unsigned char)*s); s++, i++) {
			v = (v * 10) + (*s - '0');
		}
		va[vi] = v;

		if ((vi < 2 && *s == '-') ||
		    (vi == 2 && (*s == 'T' || ISSPACE((unsigned char)*s))) ||
		    (vi > 2 && *s == ':'))
			s++;
	}

	/* skip milliseconds in for example: "%Y-%m-%dT%H:%M:%S.000Z" */
	if (*s == '.') {
		for (s++; ISDIGIT((unsigned char)*s); s++)
			;
	}

	/* invalid range */
	if (va[0] < 0 || va[0] > 9999 ||
	    va[1] < 1 || va[1] > 12 ||
	    va[2] < 1 || va[2] > 31 ||
	    va[3] < 0 || va[3] > 23 ||
	    va[4] < 0 || va[4] > 59 ||
	    va[5] < 0 || va[5] > 60) /* allow leap second */
		return -1;

	*tp = datetounix(va[0] - 1900, va[1] - 1, va[2], va[3], va[4], va[5]) -
	      gettzoffset(s);

	return 0;
}

static void
printfields(void)
{
	string_print_timestamp(&ctx.fields[FeedFieldTime].str);
	putchar(FieldSeparator);
	string_print_trimmed(&ctx.fields[FeedFieldTitle].str);
	putchar(FieldSeparator);
	string_print_uri(&ctx.fields[FeedFieldLink].str);
	putchar(FieldSeparator);
	string_print_encoded(&ctx.fields[FeedFieldContent].str);
	putchar(FieldSeparator);
	fputs(contenttypes[ctx.contenttype], stdout);
	putchar(FieldSeparator);
	string_print_trimmed(&ctx.fields[FeedFieldId].str);
	putchar(FieldSeparator);
	string_print_trimmed(&ctx.fields[FeedFieldAuthor].str);
	putchar(FieldSeparator);
	string_print_uri(&ctx.fields[FeedFieldEnclosure].str);
	putchar(FieldSeparator);
	string_print_trimmed_multi(&ctx.fields[FeedFieldCategory].str);
	putchar('\n');

	if (ferror(stdout)) /* check for errors but do not flush */
		checkfileerror(stdout, "<stdout>", 'w');
}

static int
istag(const char *name, size_t len, const char *name2, size_t len2)
{
	return (len == len2 && !strcasecmp(name, name2));
}

static int
isattr(const char *name, size_t len, const char *name2, size_t len2)
{
	return (len == len2 && !strcasecmp(name, name2));
}

static void
xmlattr(XMLParser *p, const char *t, size_t tl, const char *n, size_t nl,
	const char *v, size_t vl)
{
	/* handles transforming inline XML to data */
	if (ISINCONTENT(ctx)) {
		if (ctx.contenttype == ContentTypeHTML)
			xmldata(p, v, vl);
		return;
	}

	if (!ctx.tag.id)
		return;

	/* content-type may be: Atom: text, xhtml, html or mime-type.
	   MRSS (media:description): plain, html. */
	if (ISCONTENTTAG(ctx)) {
		if (isattr(n, nl, STRP("type")))
			string_append(&attrtype, v, vl);
		return;
	}

	if (ctx.feedtype == FeedTypeRSS) {
		if (ctx.tag.id == RSSTagEnclosure &&
		    isattr(n, nl, STRP("url"))) {
			string_append(&tmpstr, v, vl);
		} else if (ctx.tag.id == RSSTagGuid &&
		           isattr(n, nl, STRP("ispermalink"))) {
			string_append(&attrispermalink, v, vl);
		}
	} else if (ctx.feedtype == FeedTypeAtom) {
		if (ctx.tag.id == AtomTagLink) {
			if (isattr(n, nl, STRP("rel"))) {
				string_append(&attrrel, v, vl);
			} else if (isattr(n, nl, STRP("href"))) {
				string_append(&tmpstr, v, vl);
			}
		} else if (ctx.tag.id == AtomTagCategory &&
			   isattr(n, nl, STRP("term"))) {
			string_append(&tmpstr, v, vl);
		}
	}
}

static void
xmlattrentity(XMLParser *p, const char *t, size_t tl, const char *n, size_t nl,
              const char *data, size_t datalen)
{
	char buf[16];
	int len;

	/* handles transforming inline XML to data */
	if (ISINCONTENT(ctx)) {
		if (ctx.contenttype == ContentTypeHTML)
			xmldata(p, data, datalen);
		return;
	}

	if (!ctx.tag.id)
		return;

	/* try to translate entity, else just pass as data to
	 * xmldata handler. */
	if ((len = xml_entitytostr(data, buf, sizeof(buf))) > 0)
		xmlattr(p, t, tl, n, nl, buf, (size_t)len);
	else
		xmlattr(p, t, tl, n, nl, data, datalen);
}

static void
xmlattrend(XMLParser *p, const char *t, size_t tl, const char *n, size_t nl)
{
	if (ISINCONTENT(ctx)) {
		if (ctx.contenttype == ContentTypeHTML) {
			/* handles transforming inline XML to data */
			xmldata(p, "\"", 1);
			ctx.attrcount = 0;
		}
		return;
	}
}

static void
xmlattrstart(XMLParser *p, const char *t, size_t tl, const char *n, size_t nl)
{
	if (ISINCONTENT(ctx)) {
		if (ctx.contenttype == ContentTypeHTML) {
			/* handles transforming inline XML to data */
			if (!ctx.attrcount)
				xmldata(p, " ", 1);
			ctx.attrcount++;
			xmldata(p, n, nl);
			xmldata(p, "=\"", 2);
		}
		return;
	}

	if (attrispermalink.len && isattr(n, nl, STRP("ispermalink")))
		string_clear(&attrispermalink);
	else if (attrrel.len && isattr(n, nl, STRP("rel")))
		string_clear(&attrrel);
	else if (attrtype.len && isattr(n, nl, STRP("type")))
		string_clear(&attrtype);
	else if (tmpstr.len &&
	    (isattr(n, nl, STRP("href")) ||
	     isattr(n, nl, STRP("term")) ||
	     isattr(n, nl, STRP("url"))))
		string_clear(&tmpstr); /* use the last value for multiple attribute values */
}

static void
xmldata(XMLParser *p, const char *s, size_t len)
{
	if (!ctx.field)
		return;

	if (ISFEEDFIELDMULTI(fieldmap[ctx.tag.id]))
		string_append(&tmpstr, s, len);
	else
		string_append(ctx.field, s, len);
}

static void
xmldataentity(XMLParser *p, const char *data, size_t datalen)
{
	char buf[16];
	int len;

	if (!ctx.field)
		return;

	/* try to translate entity, else just pass as data to
	 * xmldata handler. */
	if ((len = xml_entitytostr(data, buf, sizeof(buf))) > 0)
		xmldata(p, buf, (size_t)len);
	else
		xmldata(p, data, datalen);
}

static void
xmltagstart(XMLParser *p, const char *t, size_t tl)
{
	const FeedTag *f;

	if (ISINCONTENT(ctx)) {
		if (ctx.contenttype == ContentTypeHTML) {
			ctx.attrcount = 0;
			xmldata(p, "<", 1);
			xmldata(p, t, tl);
		}
		return;
	}

	/* start of RSS or Atom item / entry */
	if (ctx.feedtype == FeedTypeNone) {
		if (istag(t, tl, STRP("entry")))
			ctx.feedtype = FeedTypeAtom;
		else if (istag(t, tl, STRP("item")))
			ctx.feedtype = FeedTypeRSS;
		return;
	}

	/* field tagid already set or nested tags. */
	if (ctx.tag.id) {
		/* nested <author><name> for Atom */
		if (ctx.tag.id == AtomTagAuthor &&
		    istag(t, tl, STRP("name"))) {
			memcpy(&(ctx.tag), &atomtagauthorname, sizeof(ctx.tag));
		} else {
			return; /* other nested tags are not allowed: return */
		}
	}

	/* in item */
	if (ctx.tag.id == TagUnknown) {
		if (!(f = gettag(ctx.feedtype, t, tl)))
			f = &notag;
		memcpy(&(ctx.tag), f, sizeof(ctx.tag));
	}

	ctx.iscontenttag = (fieldmap[ctx.tag.id] == FeedFieldContent);
	string_clear(&attrispermalink);
	string_clear(&attrrel);
	string_clear(&attrtype);
}

static void
xmltagstartparsed(XMLParser *p, const char *t, size_t tl, int isshort)
{
	enum TagId tagid;

	if (ISINCONTENT(ctx)) {
		if (ctx.contenttype == ContentTypeHTML) {
			if (isshort)
				xmldata(p, "/>", 2);
			else
				xmldata(p, ">", 1);
		}
		return;
	}

	/* set tag type based on it's attribute value */
	if (ctx.tag.id == RSSTagGuid) {
		/* if empty the default is "true" */
		if (!attrispermalink.len ||
		    isattr(attrispermalink.data, attrispermalink.len, STRP("true")))
			ctx.tag.id = RSSTagGuidPermalinkTrue;
		else
			ctx.tag.id = RSSTagGuidPermalinkFalse;
	} else if (ctx.tag.id == AtomTagLink) {
		/* empty or "alternate": other types could be
		   "enclosure", "related", "self" or "via" */
		if (!attrrel.len || isattr(attrrel.data, attrrel.len, STRP("alternate")))
			ctx.tag.id = AtomTagLinkAlternate;
		else if (isattr(attrrel.data, attrrel.len, STRP("enclosure")))
			ctx.tag.id = AtomTagLinkEnclosure;
		else
			ctx.tag.id = AtomTagLink; /* unknown */
	}

	tagid = ctx.tag.id;

	/* map tag type to field: unknown or lesser priority is ignored,
	   when tags of the same type are repeated only the first is used. */
	if (fieldmap[tagid] == -1 ||
	    (!ISFEEDFIELDMULTI(fieldmap[tagid]) &&
	     tagid <= ctx.fields[fieldmap[tagid]].tagid)) {
		return;
	}

	if (ctx.iscontenttag) {
		ctx.iscontent = 1;
		ctx.iscontenttag = 0;

		/* detect content-type based on type attribute */
		if (attrtype.len) {
			if (isattr(attrtype.data, attrtype.len, STRP("html")) ||
			    isattr(attrtype.data, attrtype.len, STRP("xhtml")) ||
			    isattr(attrtype.data, attrtype.len, STRP("text/html")) ||
			    isattr(attrtype.data, attrtype.len, STRP("text/xhtml")) ||
			    isattr(attrtype.data, attrtype.len, STRP("application/xhtml+xml")))
				ctx.contenttype = ContentTypeHTML;
			else /* unknown: handle as base64 text data */
				ctx.contenttype = ContentTypePlain;
		} else {
			/* default content-type */
			if (tagid == RSSTagContentEncoded || tagid == RSSTagDescription)
				ctx.contenttype = ContentTypeHTML;
			else
				ctx.contenttype = ContentTypePlain;
		}
	}

	ctx.field = &(ctx.fields[fieldmap[tagid]].str);
	ctx.fields[fieldmap[tagid]].tagid = tagid;

	/* clear field if it is overwritten (with a priority order) for the new
	   value, if the field can have multiple values then do not clear it. */
	if (!ISFEEDFIELDMULTI(fieldmap[ctx.tag.id]))
		string_clear(ctx.field);
}

static void
xmltagend(XMLParser *p, const char *t, size_t tl, int isshort)
{
	size_t i;

	if (ctx.feedtype == FeedTypeNone)
		return;

	if (ISINCONTENT(ctx)) {
		/* not close content field */
		if (!istag(ctx.tag.name, ctx.tag.len, t, tl)) {
			if (!isshort && ctx.contenttype == ContentTypeHTML) {
				xmldata(p, "</", 2);
				xmldata(p, t, tl);
				xmldata(p, ">", 1);
			}
			return;
		}
	} else if (ctx.tag.id && istag(ctx.tag.name, ctx.tag.len, t, tl)) {
		/* matched tag end: close it */
		/* copy also to the link field if the attribute isPermaLink="true"
		   and it is not set by a tag with higher prio. */
		if (ctx.tag.id == RSSTagGuidPermalinkTrue && ctx.field &&
		    ctx.tag.id > ctx.fields[FeedFieldLink].tagid) {
			string_clear(&ctx.fields[FeedFieldLink].str);
			string_append(&ctx.fields[FeedFieldLink].str,
			              ctx.field->data, ctx.field->len);
			ctx.fields[FeedFieldLink].tagid = ctx.tag.id;
		}
	} else if (!ctx.tag.id && ((ctx.feedtype == FeedTypeAtom &&
	   istag(t, tl, STRP("entry"))) || /* Atom */
	   (ctx.feedtype == FeedTypeRSS &&
	   istag(t, tl, STRP("item"))))) /* RSS */
	{
		/* end of RSS or Atom entry / item */
		printfields();

		/* clear strings */
		for (i = 0; i < FeedFieldLast; i++) {
			string_clear(&ctx.fields[i].str);
			ctx.fields[i].tagid = TagUnknown;
		}
		ctx.contenttype = ContentTypeNone;
		/* allow parsing of Atom and RSS concatenated in one XML stream. */
		ctx.feedtype = FeedTypeNone;
	} else {
		return; /* not end of field */
	}

	/* temporary string: for fields that cannot be processed
	   directly and need more context, for example by it's tag
	   attributes, like the Atom link rel="alternate|enclosure". */
	if (tmpstr.len && ctx.field) {
		if (ISFEEDFIELDMULTI(fieldmap[ctx.tag.id])) {
			if (ctx.field->len)
				string_append(ctx.field, FieldMultiSeparator, 1);
			string_append(ctx.field, tmpstr.data, tmpstr.len);
		} else {
			string_clear(ctx.field);
			string_append(ctx.field, tmpstr.data, tmpstr.len);
		}
	}

	/* close field */
	string_clear(&tmpstr); /* reuse and clear temporary string */

	if (ctx.tag.id == AtomTagAuthorName)
		memcpy(&(ctx.tag), &atomtagauthor, sizeof(ctx.tag)); /* outer tag */
	else
		memcpy(&(ctx.tag), &notag, sizeof(ctx.tag));

	ctx.iscontent = 0;
	ctx.field = NULL;
}

int
main(int argc, char *argv[])
{
	if (pledge("stdio", NULL) == -1)
		err(1, "pledge");

	if (argc > 1) {
		if (uri_parse(argv[1], &baseuri) != -1 && baseuri.proto[0])
			baseurl = argv[1];
		else
			errx(1, "baseurl incorrect or too long");
	}

	memcpy(&(ctx.tag), &notag, sizeof(ctx.tag));

	parser.xmlattr = xmlattr;
	parser.xmlattrentity = xmlattrentity;
	parser.xmlattrend = xmlattrend;
	parser.xmlattrstart = xmlattrstart;
	parser.xmlcdata = xmldata;
	parser.xmldata = xmldata;
	parser.xmldataentity = xmldataentity;
	parser.xmltagend = xmltagend;
	parser.xmltagstart = xmltagstart;
	parser.xmltagstartparsed = xmltagstartparsed;

	/* NOTE: getnext is defined in xml.h for inline optimization */
	xml_parse(&parser);

	checkfileerror(stdin, "<stdin>", 'r');
	checkfileerror(stdout, "<stdout>", 'w');

	return 0;
}