summaryrefslogtreecommitdiffstats
path: root/parsers/logbooks.py
blob: 9d568940dac92fe3c94dd0fe223e4c43fc82b2fc (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
import csv
import datetime
import os
import re
import time
import pickle
import shelve

from django.conf import settings
from django.template.defaultfilters import slugify
from django.utils.timezone import get_current_timezone, make_aware

from troggle.core.models.troggle import DataIssue, Expedition
from troggle.core.utils import TROG, save_carefully
from troggle.core.models.caves import Cave, LogbookEntry, PersonTrip, GetCaveLookup
from parsers.people import GetPersonExpeditionNameLookup

'''
Parses and imports logbooks in all their wonderful confusion

# When we edit logbook entries, allow a "?" after any piece of data to say we've frigged it and
# it can be checked up later from the hard-copy if necessary; or it's not possible to determin (name, trip place, etc)
'''

#
# the logbook loading section
#
def GetTripPersons(trippeople, expedition, logtime_underground):
    res = [ ]
    author = None
    round_bracket_regex = re.compile(r"[\(\[].*?[\)\]]")
    for tripperson in re.split(r",|\+|&|&(?!\w+;)| and ", trippeople):
        tripperson = tripperson.strip()
        mul = re.match(r"<u>(.*?)</u>$(?i)", tripperson)
        if mul:
            tripperson = mul.group(1).strip()
        if tripperson and tripperson[0] != '*':
            tripperson = re.sub(round_bracket_regex, "", tripperson).strip()
            personyear = GetPersonExpeditionNameLookup(expedition).get(tripperson.lower())
            if not personyear:
                message = "No name match for: ||'%s'|| in year '%s'" % (tripperson, expedition.year)
                print(message)
                DataIssue.objects.create(parser='logbooks', message=message)
                logdataissues[expedition.year + "~" + tripperson]=message
            res.append((personyear, logtime_underground))
            if mul:
                author = personyear
    if not author:
        if not res:
            return None, None
        author = res[-1][0]
    return res, author

def GetTripCave(place):  
    try:
        katastNumRes=[]
        katastNumRes=list(Cave.objects.filter(kataster_number=int(place)))
    except ValueError:
        message = " ! - ValueError on finding place " + str(place) + " entered. " + tripdate + " - " + year 
        DataIssue.objects.create(parser='logbooks', message=message)
        logdataissues["author"]=message
    officialNameRes=list(Cave.objects.filter(official_name=place))
    tripCaveRes=officialNameRes+katastNumRes

    if len(tripCaveRes)==1:
        return tripCaveRes[0]
    elif len(tripCaveRes)>1:
        message = " ! - Ambiguous place " + str(place) + " entered. " + tripdate + " - " + year + " " + str(tripCaveRes)
        DataIssue.objects.create(parser='logbooks', message=message)
        logdataissues["author"]=message
        return tripCaveRes[0]
    else:
        print((" " , place))
        message = " ! - No cave found for place:" + str(place) + tripdate + " - " + year 
        DataIssue.objects.create(parser='logbooks', message=message)
        logdataissues["author"]=message
        return None


logentries = [] # the entire logbook for one year is a single object: a list of entries
noncaveplaces = [ "QMplaceholder", "Journey", "Loser Plateau", "UNKNOWN", 'plateau', 
        'base camp', 'basecamp', 'top camp', 'topcamp' ]
logdataissues = {}
trips ={}

def EnterLogIntoDbase(date, place, title, text, trippeople, expedition, logtime_underground, entry_type="wiki"):
    """ saves a logbook entry and related persontrips 
    Does NOT save the expeditionday_id  - all NULLs. why?
    """
    trippersons, author = GetTripPersons(trippeople, expedition, logtime_underground)
    if not author:
        print(" ! - Skipping logentry: " + title + " - no author for entry")
        message = " ! - Skipping logentry: %s - no author for entry in year '%s'" % (title, expedition.year)
        DataIssue.objects.create(parser='logbooks', message=message)
        logdataissues["title"]=message
        return

    # This needs attention. The slug field is derived from 'title'
    # both GetCaveLookup() and GetTripCave() need to work together better. None of this data is *used* though?
    #tripCave = GetTripCave(place):

    lplace = place.lower()
    cave=None
    if lplace not in noncaveplaces:
        cave = GetCaveLookup().get(lplace)
        # message = " ! - '" + lplace + "' place not in noncaveplaces."
        # print(message)
        # DataIssue.objects.create(parser='logbooks', message=message)

    #Check for an existing copy of the current entry, and save
    expeditionday = expedition.get_expedition_day(date)
    lookupAttribs={'date':date, 'title':title}
    # 'cave' is converted to a string doing this, which renders as the cave slug.
    # but it is a db query which we should try to avoid - rewrite this
    nonLookupAttribs={'place':place, 'text':text, 'expedition':expedition, 'cave_slug':str(cave), 'slug':slugify(title)[:50], 'entry_type':entry_type}
    lbo, created=save_carefully(LogbookEntry, lookupAttribs, nonLookupAttribs)

    
    for tripperson, time_underground in trippersons:
        lookupAttribs={'personexpedition':tripperson, 'logbook_entry':lbo}
        nonLookupAttribs={'time_underground':time_underground, 'is_logbook_entry_author':(tripperson == author)}
        save_carefully(PersonTrip, lookupAttribs, nonLookupAttribs) # PersonTrip also saved in SetDatesFromLogbookEntries

def ParseDate(tripdate, year):
    """ Interprets dates in the expo logbooks and returns a correct datetime.date object  """
    mdatestandard = re.match(r"(\d\d\d\d)-(\d\d)-(\d\d)", tripdate)
    mdategoof = re.match(r"(\d\d?)/0?(\d)/(20|19)?(\d\d)", tripdate)
    if mdatestandard:
        if not (mdatestandard.group(1) == year):
            message = " ! - Bad date (year) in logbook: " + tripdate + " - " + year
            DataIssue.objects.create(parser='logbooks', message=message)
            logdataissues["tripdate"]=message
            return datetime.date('1970', '01', '01')
        else:
            year, month, day = int(mdatestandard.group(1)), int(mdatestandard.group(2)), int(mdatestandard.group(3))
    elif mdategoof:
        if not (not mdategoof.group(3) or mdategoof.group(3) == year[:2]):
            message = " ! - Bad date mdategoof.group(3) in logbook: " + tripdate + " - " + mdategoof.group(3)
            DataIssue.objects.create(parser='logbooks', message=message)
            logdataissues["tripdate"]=message
            return datetime.date('1970', '01', '01')
        else:
            yadd = int(year[:2]) * 100
            day, month, year = int(mdategoof.group(1)), int(mdategoof.group(2)), int(mdategoof.group(4)) + yadd
    else:
        message = " ! - Bad date in logbook: " + tripdate + " - " + year
        DataIssue.objects.create(parser='logbooks', message=message)
        logdataissues["tripdate"]=message

    return datetime.date(year, month, day)

# (2006 - not any more), 2008 - 2009
def Parselogwikitxt(year, expedition, txt):
    global logentries
    global logdataissues

    logbook_entry_count = 0
    trippara = re.findall(r"===(.*?)===([\s\S]*?)(?====)", txt)
    for triphead, triptext in trippara:
        logbook_entry_count += 1
        tripheadp = triphead.split("|")
        if not (len(tripheadp) == 3):
            message = " ! - Bad no of items in tripdate in logbook: " + tripdate + " - " + tripheadp
            DataIssue.objects.create(parser='logbooks', message=message)
            logdataissues["tripdate"]=message
         
        tripdate, tripplace, trippeople = tripheadp
        tripsplace = tripplace.split(" - ")
        tripcave = tripsplace[0].strip()
        if len(tripsplace) == 1:
            tripsplace = tripsplace[0] 
        else:
            tripsplace = tripsplace[1]
            
        print(f"! LOGBOOK {year} {logbook_entry_count:2}  {len(triptext):4}  '{tripsplace}'")

        tul = re.findall(r"T/?U:?\s*(\d+(?:\.\d*)?|unknown)\s*(hrs|hours)?", triptext)
        if tul:
            tu = tul[0][0]
        else:
            tu = ""

        ldate = ParseDate(tripdate.strip(), year)
        tripid =""
        
        entrytuple = (ldate, tripcave, tripsplace, triptext, 
                trippeople, expedition, tu, "wiki", tripid)
        logentries.append(entrytuple)

        EnterLogIntoDbase(date = ldate, place = tripcave, title = tripplace, text = triptext, trippeople=trippeople, 
                expedition=expedition, logtime_underground=0)
        
        EnterLogIntoObjStore(year, ldate, tripcave, tripplace, triptext, trippeople, 
                tu, "wiki", tripid, logbook_entry_count)


def EnterLogIntoObjStore(year, date, tripcave, triptitle, text, trippeople, tu, formattype, tripid1, seq):
    # This will need additional functions to replicate the persontrip calculation and storage. For the
    # moment we leave all that to be done in the django db
    global trips # should be a singleton TROG eventually
    global logdataissues

    if tripid1 is None or tripid1 =="":
       tid= "n{}-s{:02d}".format(str(date),seq)
       #print(" - New id ",tid)
    else:
        tid= tripid1
    if tid in trips:
        msg = "   ! DUPLICATE id .{}. {} ~{}~".format(tid, trips[tid][0], trips[tid][1])
        print(msg)
        DataIssue.objects.create(parser='logbooks', message=msg)
        tid= "d{}-s{:02d}".format(str(date),seq)
        #print("   - De-dup ",seq, tid)
        logdataissues[tid]=msg
    trips[tid] = (year, date, tripcave, triptitle, text, trippeople, tu, formattype)

    ## copy a lot of checking functionality here from EnterLogIntoDbase()
    # GetTripPersons is a db query, so this will need to be put in ObjStore  before this will work..
    # or design a different way to do it.
    #trippersons, author = GetTripPersons(trippeople, expedition, logtime_underground)
    # if not author:
        # print(" ! - Skipping logentry: " + title + " - no RECOGNISED author for entry")
        # message = " ! - Skipping logentry: %s - no author for entry in year '%s'" % (title, expedition.year)
        # DataIssue.objects.create(parser='logbooks', message=message)
        # logdataissues[tid+"author"]=message
    pass
 
# 2002, 2004, 2005, 2007, 2010 - now
# 2006 wiki text is incomplete, but the html all there. So using this parser now.
def Parseloghtmltxt(year, expedition, txt):
    global logentries
    global logdataissues

    tripparas = re.findall(r"<hr\s*/>([\s\S]*?)(?=<hr)", txt)
    logbook_entry_count = 0
    for trippara in tripparas:
        logbook_entry_count += 1
        
        s = re.match(r'''(?x)(?:\s*<div\sclass="tripdate"\sid=".*?">.*?</div>\s*<p>)?  # second date
                            \s*(?:<a\s+id="(.*?)"\s*/>\s*</a>)?
                            \s*<div\s+class="tripdate"\s*(?:id="(.*?)")?>(.*?)</div>(?:<p>)?
                            \s*<div\s+class="trippeople">\s*(.*?)</div>
                            \s*<div\s+class="triptitle">\s*(.*?)</div>
                            ([\s\S]*?)
                            \s*(?:<div\s+class="timeug">\s*(.*?)</div>)?
                            \s*$
                     ''', trippara)
        if not s:
            if not re.search(r"Rigging Guide", trippara):
                msg = " !- Logbook. Can't parse: {} entry:{}".format(trippara, logbook_entry_count) 
                print(msg)
                DataIssue.objects.create(parser='logbooks', message=msg)
                logdataissues[tid]=msg
            continue
        tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups()
        ldate = ParseDate(tripdate.strip(), year)
        triptitles = triptitle.split(" - ")
        if len(triptitles) >= 2:
            tripcave = triptitles[0]
        else:
            tripcave = "UNKNOWN"
        ltriptext = re.sub(r"</p>", "", triptext)
        ltriptext = re.sub(r"\s*?\n\s*", " ", ltriptext)
        ltriptext = re.sub(r"<p>", "</br></br>", ltriptext).strip()

        entrytuple = (ldate, tripcave, triptitle, ltriptext, 
                trippeople, expedition, tu, "html", tripid1)
        logentries.append(entrytuple)

        EnterLogIntoDbase(date = ldate, place = tripcave, title = triptitle, text = ltriptext,
                          trippeople=trippeople, expedition=expedition, logtime_underground=0,
                          entry_type="html")

        EnterLogIntoObjStore(year, ldate, tripcave, triptitle, ltriptext, trippeople, tu, 
                            "html", tripid1, logbook_entry_count)

# main parser for 1991 - 2001.  simpler because the data has been hacked so much to fit it
# trying it out for years 1982 - 1990 too. Some logbook editing required by hand..
def Parseloghtml01(year, expedition, txt):
    global logentries
    global logdataissues
    errorcount = 0

    tripparas = re.findall(r"<hr[\s/]*>([\s\S]*?)(?=<hr)", txt)
    logbook_entry_count = 0
    for trippara in tripparas:
        logbook_entry_count += 1
        try:
            tripentry = year + "." + str(logbook_entry_count)
            s = re.match(r"(?s)\s*(?:<p>)?(.*?)</?p>(.*)$(?i)", trippara)
            if not s:
                message = " ! - Skipping logentry on failure to parse header: " + tripentry + trippara[:300] + "..."
                DataIssue.objects.create(parser='logbooks', message=message)
                logdataissues[tripentry]=message
                print(message)
                break
            tripheader, triptext = s.group(1), s.group(2)
            mtripid = re.search(r'<a id="(.*?)"', tripheader)
            tripid = mtripid and mtripid.group(1) or ""
            tripheader = re.sub(r"</?(?:[ab]|span)[^>]*>", "", tripheader)

            tripdate, triptitle, trippeople = tripheader.split("|")
            ldate = ParseDate(tripdate.strip(), year)
        
            mtu = re.search(r'<p[^>]*>(T/?U.*)', triptext)
            if mtu:
                tu = mtu.group(1)
                triptext = triptext[:mtu.start(0)] + triptext[mtu.end():]
            else:
                tu = ""

            triptitles = triptitle.split(" - ")
            tripcave = triptitles[0].strip()

            ltriptext = triptext
            
            mtail = re.search(r'(?:<a href="[^"]*">[^<]*</a>|\s|/|-|&amp;|</?p>|\((?:same day|\d+)\))*$', ltriptext)
            if mtail:
                ltriptext = ltriptext[:mtail.start(0)]
            ltriptext = re.sub(r"</p>", "", ltriptext)
            ltriptext = re.sub(r"\s*?\n\s*", " ", ltriptext)
            ltriptext = re.sub(r"<p>|<br>", "\n\n", ltriptext).strip()
            ltriptext = re.sub(r"</?u>", "_", ltriptext)
            ltriptext = re.sub(r"</?i>", "''", ltriptext)
            ltriptext = re.sub(r"</?b>", "'''", ltriptext)

            entrytuple = (ldate, tripcave, triptitle, ltriptext, 
                    trippeople, expedition, tu, "html01", tripid)
            logentries.append(entrytuple)

            EnterLogIntoDbase(date=ldate, place=tripcave, title=triptitle, text=ltriptext,
                              trippeople=trippeople, expedition=expedition, logtime_underground=0,
                              entry_type="html")

            EnterLogIntoObjStore(year, ldate, tripcave, triptitle, ltriptext, trippeople, tu, 
                                "html01", tripid, logbook_entry_count)
        except:
            message = " ! - Skipping logentry due to exception in: " + tripentry 
            DataIssue.objects.create(parser='logbooks', message=message)
            logdataissues[tripentry]=message
            print(message)
            errorcount += 1
            if errorcount >5 :
                message = " !!- TOO MANY ERRORS - aborting logbook: " + year
                DataIssue.objects.create(parser='logbooks', message=message)
                logdataissues[tripentry]=message
                print(message)
                return

# parser for 2003
def Parseloghtml03(year, expedition, txt):
    global logentries
    global logdataissues

    tripparas = re.findall(r"<hr\s*/>([\s\S]*?)(?=<hr)", txt)
    logbook_entry_count = 0
    for trippara in tripparas:
        logbook_entry_count += 1
        
        s = re.match(r"(?s)\s*<p>(.*?)</p>(.*)$", trippara)
        if not ( s ) :
            message = " ! - Skipping logentry on failure to parse Parseloghtml03: {} {} {}...".format(tripentry,s,trippara[:300])
            DataIssue.objects.create(parser='logbooks', message=message)
            logdataissues[tripentry]=message
            print(message)
            break
        
        tripheader, triptext = s.group(1), s.group(2)
        tripheader = re.sub(r"&nbsp;", " ", tripheader)
        tripheader = re.sub(r"\s+", " ", tripheader).strip()
        sheader = tripheader.split(" -- ")
        tu = ""
        if re.match("T/U|Time underwater", sheader[-1]):
            tu = sheader.pop()
        if len(sheader) != 3:
            print((" ! Header not three pieces", sheader))
        tripdate, triptitle, trippeople = sheader
        ldate = ParseDate(tripdate.strip(), year)
        triptitles = triptitle.split(" , ")
        if len(triptitles) >= 2:
            tripcave = triptitles[0]
        else:
            tripcave = "UNKNOWN"
        ltriptext = re.sub(r"</p>", "", triptext)
        ltriptext = re.sub(r"\s*?\n\s*", " ", ltriptext)
        ltriptext = re.sub(r"<p>", "\n\n", ltriptext).strip()
        ltriptext = re.sub(r"[^\s0-9a-zA-Z\-.,:;'!&()\[\]<>?=+*%]", "_NONASCII_", ltriptext)

        tid= "n{}-s{:02d}".format(str(ldate),logbook_entry_count)

        entrytuple = (ldate, tripcave, triptitle, ltriptext, 
                trippeople, expedition, tu, "html03", tid)
        logentries.append(entrytuple)

        EnterLogIntoDbase(date = ldate, place = tripcave, title = triptitle,
                          text = ltriptext, trippeople=trippeople, expedition=expedition,
                          logtime_underground=0, entry_type="html")

        EnterLogIntoObjStore(year, ldate, tripcave, triptitle, ltriptext, trippeople, tu, 
                            "html03", tid, logbook_entry_count)


def SetDatesFromLogbookEntries(expedition):
    """
    Sets the date_from and date_to field for an expedition based on persontrips.
    Then sets the expedition date_from and date_to based on the personexpeditions.
    """
    # Probably a faster way to do this. This uses a lot of db queries, but we have all this
    # in memory..
    for personexpedition in expedition.personexpedition_set.all():
        persontrips = personexpedition.persontrip_set.order_by('logbook_entry__date')
        # sequencing is difficult to do
        lprevpersontrip = None
        for persontrip in persontrips:
            persontrip.persontrip_prev = lprevpersontrip
            if lprevpersontrip:
                lprevpersontrip.persontrip_next = persontrip
                lprevpersontrip.save()
            persontrip.persontrip_next = None
            lprevpersontrip = persontrip
            persontrip.save() # also saved in EnterLogIntoDbase. MERGE these to speed up import.


def LoadLogbookForExpedition(expedition, expect):
    """ Parses all logbook entries for one expedition 
    If a cache is found it uses it. If not found, or fails sanity checks, parses source file.
    """
    # absolutely horrid. REFACTOR THIS (all my fault..)
    global logentries
    logbook_parseable = False
    logbook_cached = False
    yearlinks   = settings.LOGBOOK_PARSER_SETTINGS
    expologbase = os.path.join(settings.EXPOWEB, "years")
    logentries=[]
    
    def validcache(year,n):
        if year != expedition:
            print("   ! year != expedition ",year, expedition )
            return False
        if len(logentries) != n:
            print("   ! len(logentries) != n ",len(logentries), n )
            return False
        if n != expect:
            print("   ! n != expect ",n, expect )
            return False
        return True
    
    if expedition.year in yearlinks:
        logbookfile = os.path.join(expologbase, yearlinks[expedition.year][0])
        parsefunc   = yearlinks[expedition.year][1]
    else:
        logbookfile = os.path.join(expologbase, expedition.year, settings.DEFAULT_LOGBOOK_FILE)
        parsefunc   = settings.DEFAULT_LOGBOOK_PARSER
    cache_filename = logbookfile + ".cache"

    try:
        bad_cache = False
        now = time.time()
        cache_t = os.path.getmtime(cache_filename)
        if os.path.getmtime(logbookfile) - cache_t > 2: # at least 2 secs later
            bad_cache= True
        if now - cache_t > 30*24*60*60:
            bad_cache= True
        if bad_cache:
            print(" - ! Cache is either stale or more than 30 days old. Deleting it.")
            os.remove(cache_filename)
            logentries=[]
            print("   ! Removed stale or corrupt cache file")
            raise
        print("   - Reading cache: " + cache_filename, end='')
        try:
            with open(cache_filename, "rb") as f:
                year,n,logentries = pickle.load(f) 
            if validcache(year,n):
                print("  -- Loaded ", len(logentries), " log entries")
                logbook_cached = True
            else:
                print("  !- Should be ", expect, " but ", len(logentries), " found in cache")
                raise
        except:
            print("   ! Failed to load corrupt cache. Deleting it.")
            os.remove(cache_filename)
            logentries=[]
            raise
    except : # no cache found
        #print("   - No cache \"" + cache_filename +"\"")
        try:
            file_in = open(logbookfile,'rb')
            txt = file_in.read().decode("latin1")
            file_in.close()
            logbook_parseable = True
            print(("   - Using: " + parsefunc + " to parse " + logbookfile))
        except (IOError):
            logbook_parseable = False
            print(("   ! Couldn't open logbook " + logbookfile))

    if logbook_parseable:
        parser = globals()[parsefunc]
        parser(expedition.year, expedition, txt)
        SetDatesFromLogbookEntries(expedition)
        if len(logentries) >0:
            print("   - Cacheing " , len(logentries), " log entries")
            with open(cache_filename, "wb") as fc:
                logbk=(expedition,len(logentries),logentries)
                pickle.dump(logbk, fc, protocol=4)
        else:
            print("   ! NO TRIP entries found in logbook, check the syntax.")

    if logbook_cached: # working on this bit...
        i=0
        for entrytuple in range(len(logentries)):
            date, tripcave, triptitle, text, trippeople, expedition, logtime_underground, entry_type, tripid1 = logentries[i]
            EnterLogIntoDbase(date, tripcave, triptitle, text, trippeople, expedition, 0,
                    entry_type)
            EnterLogIntoObjStore(expedition.year, date, tripcave, triptitle, text, trippeople, logtime_underground, 
                    entry_type, tripid1, i)
            i +=1
        SetDatesFromLogbookEntries(expedition)
    return len(logentries)

def LoadLogbooks():
    """ This is the master function for parsing all logbooks into the Troggle database. 
    Parser settings appropriate for each year are set in settings.py LOGBOOK_PARSER_SETTINGS.
    This should be rewritten to use coroutines to load all logbooks from disc in parallel.
    """
    global logdataissues

    logdataissues = {}
    DataIssue.objects.filter(parser='logbooks').delete()
    expos = Expedition.objects.all()
    if len(expos) <= 1:
        print(" ! No expeditions found. Load 'people' first.\n")
    nologbook = ["1976", "1977", "1978", "1979", "1980", "1981", 
        "1982", "1983", "1984", "1985", "1987", "1988", "1989",
        "1986", "2020",]
    entries = {"2021": 0, "2019": 20, "2018": 74, "2017": 60, "2016": 81, "2015": 79, 
        "2014": 65, "2013": 51, "2012": 75, "2011": 68, "2010": 22, "2009": 52, 
        "2008": 49, "2007": 111, "2006": 60, "2005": 55, "2004": 76, "2003": 40, "2002": 31, 
        "2001": 48, "2000": 54, "1999": 79, "1998": 43, "1997": 53, "1996": 94, "1995": 41, 
        "1994": 32, "1993": 41, "1992": 61, "1991": 38, "1990": 87, "1989": 1,"1988": 1,"1987": 1,
        "1985": 1,"1984": 1,"1983": 1,"1982": 42,}
    # Logbooks log.htm exist for 1983, 84, 85, 87, 88, 89 but have no full-working parser, or need hand-editing.
    try:
        os.remove("loadlogbk.log")
    except OSError:
        pass
    nlbe={}
    expd ={}
    with open("loadlogbk.log", "a") as log:
        for expo in expos:
            TROG['pagecache']['expedition'][expo.year] = None # clear cache
            if expo.year not in nologbook:
                print((" - Logbook for: " + expo.year))
                numentries = LoadLogbookForExpedition(expo, entries[expo.year])
                log.write("{} {:5d} should be {}\n".format(expo.year, numentries, entries[expo.year]))
                nlbe[expo.year]=numentries
                expd[expo.year]= 0
    print("** total trips in ObjStore:", len(trips))
    #for i in logdataissues:
    #    print("{:15s}:   {}".format(i, logdataissues[i]))
        
    for lbe in trips:
        year, date, tripcave, triptitle, text, trippeople, tu, formattype = trips[lbe]
        expd[year] += 1
    yt=0
    for y in expd:
        print("{} {}".format(y, expd[y]), nlbe[y])
        yt += expd[y]
    print("total {} log entries in all expeditions".format(yt))
    
    with shelve.open('logbktrips.shelve',writeback=True) as odb:
        for lbe in trips:
            odb[lbe]=trips[lbe]
    odb.sync()
    odb.close()

dateRegex = re.compile(r'<span\s+class="date">(\d\d\d\d)-(\d\d)-(\d\d)</span>', re.S)
expeditionYearRegex = re.compile(r'<span\s+class="expeditionyear">(.*?)</span>', re.S)
titleRegex = re.compile(r'<H1>(.*?)</H1>', re.S)
reportRegex = re.compile(r'<div\s+class="report">(.*)</div>\s*</body>', re.S)
personRegex = re.compile(r'<div\s+class="person">(.*?)</div>', re.S)
nameAuthorRegex = re.compile(r'<span\s+class="name(,author|)">(.*?)</span>', re.S)
TURegex = re.compile(r'<span\s+class="TU">([0-9]*\.?[0-9]+)</span>', re.S)
locationRegex = re.compile(r'<span\s+class="location">(.*?)</span>', re.S)
caveRegex = re.compile(r'<span\s+class="cave">(.*?)</span>', re.S)

def parseAutoLogBookEntry(filename):
    errors = []
    f = open(filename, "r")
    contents = f.read()
    f.close()

    dateMatch = dateRegex.search(contents)
    if dateMatch:
        year, month, day = [int(x) for x in dateMatch.groups()]
        date = datetime.date(year, month, day)
    else:
        errors.append(" - Date could not be found")

    expeditionYearMatch = expeditionYearRegex.search(contents)
    if expeditionYearMatch:
        try:
            expedition = Expedition.objects.get(year = expeditionYearMatch.groups()[0])
            personExpeditionNameLookup = GetPersonExpeditionNameLookup(expedition)
        except Expedition.DoesNotExist:
            errors.append(" - Expedition not in database")   
    else:
        errors.append(" - Expedition Year could not be parsed")   

    titleMatch = titleRegex.search(contents)
    if titleMatch:
        title, = titleMatch.groups()
        if len(title) > settings.MAX_LOGBOOK_ENTRY_TITLE_LENGTH:
            errors.append(" - Title too long")   
    else:
        errors.append(" - Title could not be found") 

    caveMatch = caveRegex.search(contents)
    if caveMatch:
        caveRef, = caveMatch.groups()
        try:
            # this is a slow and uncertain function:
            cave = getCaveByReference(caveRef)
        except:
            cave = None
            errors.append(" - Cave not found in database")   
    else:
        cave = None

    locationMatch = locationRegex.search(contents)
    if locationMatch:
        location, = locationMatch.groups() 
    else:
        location = None
       
    if cave is None and location is None:
        errors.append(" - Location nor cave could not be found") 

    reportMatch = reportRegex.search(contents)
    if reportMatch:
        report, = reportMatch.groups()
    else:
        errors.append(" - Contents could not be found") 
    if errors:
        return errors # Easiest to bail out at this point as we need to make sure that we know which expedition to look for people from.
    people = []
    for personMatch in personRegex.findall(contents):
       nameAuthorMatch = nameAuthorRegex.search(contents)
       if nameAuthorMatch:
           author, name = nameAuthorMatch.groups()
           if name.lower() in personExpeditionNameLookup:
               personExpo = personExpeditionNameLookup[name.lower()]
           else:
               errors.append(" - Person could not be found in database")
           author = bool(author)
       else:
           errors.append(" - Persons name could not be found")
       
       TUMatch = TURegex.search(contents)
       if TUMatch:
           TU, = TUMatch.groups()
       else:
           errors.append(" - TU could not be found")
       if not errors:
           people.append((name, author, TU))
    if errors:
        return errors # Bail out before committing to the database
    logbookEntry = LogbookEntry(date = date, 
                                       expedition  = expedition,
                                       title = title, cave = cave, place = location, 
                                       text = report, slug = slugify(title)[:50],
                                       filename = filename)
    logbookEntry.save()
    for name, author, TU in people:
        PersonTrip(personexpedition = personExpo,  
                          time_underground = TU, 
                          logbook_entry = logbookEntry, 
                          is_logbook_entry_author = author).save()
    print(logbookEntry)