File: sortm.c

package info (click to toggle)
nmh 1.8-4
  • links: PTS
  • area: main
  • in suites: forky, sid
  • size: 7,860 kB
  • sloc: ansic: 50,445; sh: 22,697; makefile: 1,138; lex: 740; perl: 509; yacc: 265
file content (626 lines) | stat: -rw-r--r-- 14,981 bytes parent folder | download | duplicates (3)
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
/* sortm.c -- sort messages in a folder by date/time
 *
 * This code is Copyright (c) 2002, by the authors of nmh.  See the
 * COPYRIGHT file in the root directory of the nmh distribution for
 * complete copyright information.
 */

#include "h/mh.h"
#include "sbr/dtime.h"
#include "sbr/m_name.h"
#include "sbr/m_getfld.h"
#include "sbr/getarguments.h"
#include "sbr/seq_setprev.h"
#include "sbr/seq_setcur.h"
#include "sbr/seq_save.h"
#include "sbr/smatch.h"
#include "sbr/uprf.h"
#include "sbr/m_convert.h"
#include "sbr/getfolder.h"
#include "sbr/ext_hook.h"
#include "sbr/folder_read.h"
#include "sbr/folder_free.h"
#include "sbr/context_save.h"
#include "sbr/context_replace.h"
#include "sbr/context_find.h"
#include "sbr/ambigsw.h"
#include "sbr/path.h"
#include "sbr/print_version.h"
#include "sbr/print_help.h"
#include "sbr/error.h"
#include "h/tws.h"
#include "sbr/done.h"
#include "sbr/utils.h"
#include "sbr/m_maildir.h"
#include "sbr/globals.h"

#define SORTM_SWITCHES \
    X("datefield field", 0, DATESW) \
    X("textfield field", 0, TEXTSW) \
    X("notextfield", 0, NSUBJSW) \
    X("subject", -3, SUBJSW) /* backward-compatibility */ \
    X("limit days", 0, LIMSW) \
    X("nolimit", 0, NLIMSW) \
    X("verbose", 0, VERBSW) \
    X("noverbose", 0, NVERBSW) \
    X("all", 0, ALLMSGS) \
    X("noall", 0, NALLMSGS) \
    X("check", 0, CHECKSW) \
    X("nocheck", 0, NCHECKSW) \
    X("version", 0, VERSIONSW) \
    X("help", 0, HELPSW) \

#define X(sw, minchars, id) id,
DEFINE_SWITCH_ENUM(SORTM);
#undef X

#define X(sw, minchars, id) { sw, minchars, id },
DEFINE_SWITCH_ARRAY(SORTM, switches);
#undef X

struct smsg {
    int s_msg;
    time_t s_clock;
    char *s_subj;
};

static struct smsg *smsgs;
int nmsgs;

char *subjsort;                 /* sort on subject if != 0 */
time_t datelimit = 0;
bool submajor;			/* if true, sort on subject-major */
bool verbose;
int allmsgs = 1;
int check_failed = 0;

/* This keeps compiler happy on calls to qsort */
typedef int (*qsort_comp) (const void *, const void *);

/*
 * static prototypes
 */
static int read_hdrs (struct msgs *, char *);
static int get_fields (char *, int, struct smsg *);
static int dsort (struct smsg **, struct smsg **);
static int subsort (struct smsg **, struct smsg **);
static int txtsort (struct smsg **, struct smsg **);
static void rename_chain (struct msgs *, struct smsg **, int, int);
static void rename_msgs (struct msgs *, struct smsg **);


int
main (int argc, char **argv)
{
    int	i, msgnum;
    char *cp, *maildir, *datesw = NULL;
    char *folder = NULL, buf[BUFSIZ], **argp;
    char **arguments;
    struct msgs_array msgs = { 0, 0, NULL };
    struct msgs *mp;
    struct smsg **dlist;
    bool checksw = false;

    if (nmh_init(argv[0], true, true)) { return 1; }

    arguments = getarguments (invo_name, argc, argv, 1);
    argp = arguments;

    /*
     * Parse arguments
     */
    while ((cp = *argp++)) {
	if (*cp == '-') {
	    switch (smatch (++cp, switches)) {
	    case AMBIGSW:
		ambigsw (cp, switches);
		done (1);
	    case UNKWNSW:
		die("-%s unknown", cp);

	    case HELPSW:
		snprintf(buf, sizeof(buf), "%s [+folder] [msgs] [switches]",
			invo_name);
		print_help (buf, switches, 1);
		done (0);
	    case VERSIONSW:
		print_version(invo_name);
		done (0);

	    case DATESW:
		if (datesw)
		    die("only one date field at a time");
		if (!(datesw = *argp++) || *datesw == '-')
		    die("missing argument to %s", argp[-2]);
		continue;

	    case TEXTSW:
		if (subjsort)
		    die("only one text field at a time");
		if (!(subjsort = *argp++) || *subjsort == '-')
		    die("missing argument to %s", argp[-2]);
		continue;

	    case SUBJSW:
		subjsort = "subject";
		continue;
	    case NSUBJSW:
		subjsort = NULL;
		continue;

	    case LIMSW:
		if (!(cp = *argp++) || *cp == '-')
			die("missing argument to %s", argp[-2]);
		while (*cp == '0')
		    cp++;		/* skip any leading zeros */
		if (!*cp) {		/* hit end of string */
		    submajor = true;	/* sort subject-major */
		    continue;
		}
		if (!isdigit((unsigned char) *cp) || !(datelimit = atoi(cp)))
		    die("impossible limit %s", cp);
		datelimit *= 60*60*24;
		continue;
	    case NLIMSW:
		submajor = false;	/* use date-major, but */
		datelimit = 0;	        /* use no limit */
		continue;

	    case VERBSW:
		verbose = true;
		continue;
	    case NVERBSW:
		verbose = false;
		continue;

	    case ALLMSGS:
		allmsgs = 1;
		continue;
	    case NALLMSGS:
		allmsgs = 0;
		continue;

	    case CHECKSW:
		checksw = true;
		continue;
	    case NCHECKSW:
		checksw = false;
		continue;
	    }
	}
	if (*cp == '+' || *cp == '@') {
	    if (folder)
		die("only one folder at a time!");
            folder = pluspath (cp);
	} else
            app_msgarg(&msgs, cp);
    }

    if (!context_find ("path"))
	free (path ("./", TFOLDER));
    if (!msgs.size) {
	if (allmsgs) {
	    app_msgarg(&msgs, "all");
        } else {
	    die("must specify messages to sort with -noall");
        }
    }
    if (!datesw)
	datesw = "date";
    if (!folder)
	folder = getfolder (1);
    maildir = m_maildir (folder);

    if (chdir (maildir) == -1)
	adios (maildir, "unable to change directory to");

    /* read folder and create message structure */
    if (!(mp = folder_read (folder, 1)))
	die("unable to read folder %s", folder);

    /* check for empty folder */
    if (mp->nummsg == 0)
	die("no messages in %s", folder);

    /* parse all the message ranges/sequences and set SELECTED */
    for (msgnum = 0; msgnum < msgs.size; msgnum++)
	if (!m_convert (mp, msgs.msgs[msgnum]))
	    done (1);
    seq_setprev (mp);	/* set the previous sequence */

    if ((nmsgs = read_hdrs (mp, datesw)) <= 0)
	die("no messages to sort");

    if (checksw  &&  check_failed) {
	die("errors found, no messages sorted");
    }

    /*
     * sort a list of pointers to our "messages to be sorted".
     */
    dlist = mh_xmalloc ((nmsgs+1) * sizeof(*dlist));
    for (i = 0; i < nmsgs; i++)
	dlist[i] = &smsgs[i];
    dlist[nmsgs] = 0;

    if (verbose) {	/* announce what we're doing */
	if (subjsort)
	    if (submajor)
		printf ("sorting by %s\n", subjsort);
	    else
		printf ("sorting by %s-major %s-minor\n", subjsort, datesw);
	else
	    printf ("sorting by datefield %s\n", datesw);
    }

    /* first sort by date, or by subject-major, date-minor */
    qsort (dlist, nmsgs, sizeof(*dlist),
	    (qsort_comp) (submajor && subjsort ? txtsort : dsort));

    /*
     * if we're sorting on subject, we need another list
     * in subject order, then a merge pass to collate the
     * two sorts.
     */
    if (!submajor && subjsort) {	/* already date sorted */
	struct smsg **slist, **flist;
	struct smsg ***il, **fp, **dp;

	slist = mh_xmalloc ((nmsgs+1) * sizeof(*slist));
	memcpy(slist, dlist, (nmsgs+1)*sizeof(*slist));
	qsort(slist, nmsgs, sizeof(*slist), (qsort_comp) subsort);

	/*
	 * make an inversion list so we can quickly find
	 * the collection of messages with the same subj
	 * given a message number.
	 */
	il = mh_xcalloc(mp->hghsel + 1, sizeof *il);
	for (i = 0; i < nmsgs; i++)
	    il[slist[i]->s_msg] = &slist[i];
	/*
	 * make up the final list, chronological but with
	 * all the same subjects grouped together.
	 */
	flist = mh_xmalloc ((nmsgs+1) * sizeof(*flist));
	fp = flist;
	for (dp = dlist; *dp;) {
	    struct smsg **s = il[(*dp++)->s_msg];

	    /* see if we already did this guy */
	    if (! s)
		continue;

	    *fp++ = *s++;
	    /*
	     * take the next message(s) if there is one,
	     * its subject isn't null and its subject
	     * is the same as this one and it's not too
	     * far away in time.
	     */
	    while (*s && (*s)->s_subj[0] &&
		   strcmp((*s)->s_subj, s[-1]->s_subj) == 0 &&
		   (datelimit == 0 ||
		   (*s)->s_clock - s[-1]->s_clock <= datelimit)) {
		il[(*s)->s_msg] = 0;
		*fp++ = *s++;
	    }
	}
	*fp = 0;
	free (il);
	free (slist);
	free (dlist);
	dlist = flist;
    }

    /*
     * At this point, dlist is a sorted array of pointers to smsg structures,
     * each of which contains a message number.
     */

    rename_msgs (mp, dlist);

    context_replace (pfolder, folder);	/* update current folder         */
    seq_save (mp);			/* synchronize message sequences */
    context_save ();			/* save the context file         */
    folder_free (mp);			/* free folder/message structure */
    done (0);
    return 1;
}

static int
read_hdrs (struct msgs *mp, char *datesw)
{
    int msgnum;
    struct smsg *s;

    smsgs = mh_xcalloc(mp->hghsel - mp->lowsel + 2, sizeof *smsgs);
    s = smsgs;
    for (msgnum = mp->lowsel; msgnum <= mp->hghsel; msgnum++) {
	if (is_selected(mp, msgnum)) {
	    if (get_fields (datesw, msgnum, s)) {
		s->s_msg = msgnum;
		s++;
	    }
	}
    }
    s->s_msg = 0;
    return s - smsgs;
}


/*
 * Parse the message and get the data or subject field,
 * if needed.
 */

static int
get_fields (char *datesw, int msg, struct smsg *smsg)
{
    int state;
    int compnum;
    char *msgnam, buf[NMH_BUFSIZ], nam[NAMESZ];
    struct tws *tw;
    char *datecomp = NULL, *subjcomp = NULL;
    FILE *in;
    m_getfld_state_t gstate;

    if ((in = fopen (msgnam = m_name (msg), "r")) == NULL) {
	admonish (msgnam, "unable to read message");
	return 0;
    }
    gstate = m_getfld_state_init(in);
    for (compnum = 1;;) {
	int bufsz = sizeof buf;
	switch (state = m_getfld2(&gstate, nam, buf, &bufsz)) {
	case FLD:
	case FLDPLUS:
	    compnum++;
	    if (!strcasecmp (nam, datesw)) {
		datecomp = add (buf, datecomp);
		while (state == FLDPLUS) {
		    bufsz = sizeof buf;
		    state = m_getfld2(&gstate, nam, buf, &bufsz);
		    datecomp = add (buf, datecomp);
		}
		if (!subjsort || subjcomp)
		    break;
	    } else if (subjsort && !strcasecmp (nam, subjsort)) {
		subjcomp = add (buf, subjcomp);
		while (state == FLDPLUS) {
		    bufsz = sizeof buf;
		    state = m_getfld2(&gstate, nam, buf, &bufsz);
		    subjcomp = add (buf, subjcomp);
		}
		if (datecomp)
		    break;
	    } else {
		/* just flush this guy */
		while (state == FLDPLUS) {
		    bufsz = sizeof buf;
		    state = m_getfld2(&gstate, nam, buf, &bufsz);
		}
	    }
	    continue;

	case BODY:
	case FILEEOF:
	    break;

	case LENERR:
	case FMTERR:
	    if (state == LENERR || state == FMTERR) {
		inform("format error in message %d (header #%d), continuing...",
		      msg, compnum);
		check_failed = 1;
	    }
            free(datecomp);
            free(subjcomp);
	    fclose (in);
	    return 0;

	default:
	    die("internal error -- you lose");
	}
	break;
    }
    m_getfld_state_destroy (&gstate);

    /*
     * If no date component, then use the modification
     * time of the file as its date
     */
    if (!datecomp || (tw = dparsetime (datecomp)) == NULL) {
	struct stat st;

	inform("can't parse %s field in message %d, "
            "will use file modification time", datesw, msg);
	fstat (fileno (in), &st);
	smsg->s_clock = st.st_mtime;
	check_failed = 1;
    } else {
	smsg->s_clock = dmktime (tw);
    }

    if (subjsort) {
	if (subjcomp) {
	    /*
	     * try to make the subject "canonical": delete
	     * leading "re:", everything but letters & smash
	     * letters to lower case.
	     */
	    char  *cp, *cp2, c;

	    cp = subjcomp;
	    cp2 = subjcomp;
	    if (strcmp (subjsort, "subject") == 0) {
		while ((c = *cp)) {
		    if (! isspace((unsigned char) c)) {
			if(!uprf(cp, "re:"))
			    break;
                        cp += 2;
		    }
		    cp++;
		}
	    }

	    while ((c = *cp++)) {
		if (isascii((unsigned char) c) && isalnum((unsigned char) c))
		    *cp2++ = tolower((unsigned char)c);
	    }

	    *cp2 = '\0';
	} else
	    subjcomp = "";

	smsg->s_subj = subjcomp;
    }
    fclose (in);
    free(datecomp);

    return 1;
}

/*
 * sort on dates.
 */
static int
dsort (struct smsg **a, struct smsg **b)
{
    if ((*a)->s_clock < (*b)->s_clock)
	return -1;
    if ((*a)->s_clock > (*b)->s_clock)
	return 1;
    if ((*a)->s_msg < (*b)->s_msg)
	return -1;
    return 1;
}

/*
 * sort on subjects.
 */
static int
subsort (struct smsg **a, struct smsg **b)
{
    int i;

    if ((i = strcmp ((*a)->s_subj, (*b)->s_subj)))
	return i;

    return dsort(a, b);
}

static int
txtsort (struct smsg **a, struct smsg **b)
{
    int i;

    if ((i = strcmp ((*a)->s_subj, (*b)->s_subj)))
	return i;
    if ((*a)->s_msg < (*b)->s_msg)
	return -1;
    return 1;
}

static void
rename_chain (struct msgs *mp, struct smsg **mlist, int msg, int endmsg)
{
    int nxt, old, new;
    char *newname, oldname[BUFSIZ];
    char newbuf[PATH_MAX + 1];

    for (;;) {
	nxt = mlist[msg] - smsgs;	/* mlist[msg] is a ptr into smsgs */
	mlist[msg] = NULL;
	old = smsgs[nxt].s_msg;
	new = smsgs[msg].s_msg;
	strncpy (oldname, m_name (old), sizeof(oldname) - 1);
	newname = m_name (new);
	if (verbose)
	    printf ("message %d becomes message %d\n", old, new);

	(void)snprintf(oldname, sizeof (oldname), "%s/%d", mp->foldpath, old);
	(void)snprintf(newbuf, sizeof (newbuf), "%s/%d", mp->foldpath, new);
	ext_hook("ref-hook", oldname, newbuf);

	if (rename (oldname, newname) == -1)
	    adios (newname, "unable to rename %s to", oldname);

	copy_msg_flags (mp, new, old);
	if (mp->curmsg == old)
	    seq_setcur (mp, new);

	if (nxt == endmsg)
	    break;

	msg = nxt;
    }
/*	if (nxt != endmsg); */
/*	rename_chain (mp, mlist, nxt, endmsg); */
}

static void
rename_msgs (struct msgs *mp, struct smsg **mlist)
{
    int i, j, old, new;
    bvector_t tmpset = bvector_create ();
    char f1[BUFSIZ], tmpfil[BUFSIZ];
    char newbuf[PATH_MAX + 1];
    struct smsg *sp;

    strncpy (tmpfil, m_name (mp->hghmsg + 1), sizeof(tmpfil) - 1);

    for (i = 0; i < nmsgs; i++) {
	if (! (sp = mlist[i]))
	    continue;   /* did this one */

	j = sp - smsgs;
	if (j == i)
	    continue;   /* this one doesn't move */

	/*
	 * the guy that was msg j is about to become msg i.
	 * rename 'j' to make a hole, then recursively rename
	 * guys to fill up the hole.
	 */
	old = smsgs[j].s_msg;
	new = smsgs[i].s_msg;
	strncpy (f1, m_name (old), sizeof(f1) - 1);

	if (verbose)
	    printf ("renaming message chain from %d to %d\n", old, new);

	/*
	 *	Run the external hook to refile the old message as the
	 *	temporary message number that is off of the end of the
	 *	messages in the folder.
	 */

	(void)snprintf(f1, sizeof (f1), "%s/%d", mp->foldpath, old);
	(void)snprintf(newbuf, sizeof (newbuf), "%s/%d", mp->foldpath, mp->hghmsg + 1);
	ext_hook("ref-hook", f1, newbuf);

	if (rename (f1, tmpfil) == -1)
	    adios (tmpfil, "unable to rename %s to ", f1);

	get_msg_flags (mp, tmpset, old);

	rename_chain (mp, mlist, j, i);

	/*
	 *	Run the external hook to refile the temporary message number
	 *	to the real place.
	 */

	(void)snprintf(f1, sizeof (f1), "%s/%d", mp->foldpath, new);
	ext_hook("ref-hook", newbuf, f1);

	if (rename (tmpfil, m_name(new)) == -1)
	    adios (m_name(new), "unable to rename %s to", tmpfil);

	set_msg_flags (mp, tmpset, new);
	mp->msgflags |= SEQMOD;
    }

    bvector_free (tmpset);
}