summaryrefslogtreecommitdiffstats
path: root/parsers/logbooks.py
blob: ec314b69eddb54347eefacbf697e17d8ad2ebf0f (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
#.-*- coding: utf-8 -*-

from django.conf import settings
import core.models as models

from parsers.people import GetPersonExpeditionNameLookup
from parsers.cavetab import GetCaveLookup

from django.template.defaultfilters import slugify

import csv
import re
import datetime
import os

from utils import save_carefully

# 
# 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
    for tripperson in re.split(",|\+|&|&(?!\w+;)| and ", trippeople):
        tripperson = tripperson.strip()
        mul = re.match("<u>(.*?)</u>$(?i)", tripperson)
        if mul:
            tripperson = mul.group(1).strip()
        if tripperson and tripperson[0] != '*':
            #assert tripperson in personyearmap, "'%s' << %s\n\n %s" % (tripperson, trippeople, personyearmap)
            personyear = GetPersonExpeditionNameLookup(expedition).get(tripperson.lower())
            if not personyear:
                print "NoMatchFor: '%s'" % tripperson    
            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):                     #need to be fuzzier about matching here. Already a very slow function...
#    print "Getting cave for " , place
    try:
        katastNumRes=[]
        katastNumRes=list(models.Cave.objects.filter(kataster_number=int(place)))
    except ValueError:
        pass
    officialNameRes=list(models.Cave.objects.filter(official_name=place))
    tripCaveRes=officialNameRes+katastNumRes

    if len(tripCaveRes)==1:
#        print "Place " , place , "entered as" , tripCaveRes[0]
        return tripCaveRes[0]

    elif models.OtherCaveName.objects.filter(name=place):
        tripCaveRes=models.OtherCaveName.objects.filter(name__icontains=place)[0].cave
#        print "Place " , place , "entered as" , tripCaveRes
        return tripCaveRes

    elif len(tripCaveRes)>1:
        print "Ambiguous place " + str(place) + " entered. Choose from " + str(tripCaveRes)
        correctIndex=input("type list index of correct cave")
        return tripCaveRes[correctIndex]
    else:
        print "No cave found for place " , place
        return


noncaveplaces = [ "Journey", "Loser Plateau" ]
def EnterLogIntoDbase(date, place, title, text, trippeople, expedition, logtime_underground):
    """ saves a logbook entry and related persontrips """
    trippersons, author = GetTripPersons(trippeople, expedition, logtime_underground)
    if not author:
        print "skipping logentry", title
        return
    
#    tripCave = GetTripCave(place)
    #
    lplace = place.lower()
    if lplace not in noncaveplaces:
        cave=GetCaveLookup().get(lplace)

    #Check for an existing copy of the current entry, and save
    lookupAttribs={'date':date, 'title':title} 
    nonLookupAttribs={'place':place, 'text':text, 'author':author, 'expedition':expedition, 'cave':cave, 'slug':slugify(title)[:50]}
    lbo, created=save_carefully(models.LogbookEntry, lookupAttribs, nonLookupAttribs)
    expeditiondate = expedition.get_expedition_date(date)
    
    for tripperson, time_underground in trippersons:
        lookupAttribs={'person_expedition':tripperson, 'logbook_entry':lbo}
        nonLookupAttribs={'time_underground':time_underground, 'date':date, 'expeditiondate':expeditiondate, 'is_logbook_entry_author':(tripperson == author)}
        #print nonLookupAttribs
        save_carefully(models.PersonTrip, lookupAttribs, nonLookupAttribs)


def ParseDate(tripdate, year):
    """ Interprets dates in the expo logbooks and returns a correct datetime.date object  """
    mdatestandard = re.match("(\d\d\d\d)-(\d\d)-(\d\d)", tripdate)
    mdategoof = re.match("(\d\d?)/0?(\d)/(20|19)?(\d\d)", tripdate)
    if mdatestandard:
        assert mdatestandard.group(1) == year, (tripdate, year)
        year, month, day = int(mdatestandard.group(1)), int(mdatestandard.group(2)), int(mdatestandard.group(3))
    elif mdategoof:
        assert not mdategoof.group(3) or mdategoof.group(3) == year[:2], mdategoof.groups()
        yadd = int(year[:2]) * 100
        day, month, year = int(mdategoof.group(1)), int(mdategoof.group(2)), int(mdategoof.group(4)) + yadd
    else:
        assert False, tripdate
    return datetime.date(year, month, day)

# 2007, 2008, 2006
def Parselogwikitxt(year, expedition, txt):
    trippara = re.findall("===(.*?)===([\s\S]*?)(?====)", txt)
    for triphead, triptext in trippara:
        tripheadp = triphead.split("|")
        #print tripheadp
        assert len(tripheadp) == 3, (tripheadp, triptext)
        tripdate, tripplace, trippeople = tripheadp
        tripsplace = tripplace.split(" - ")
        tripcave = tripsplace[0].strip()

        tul = re.findall("T/?U:?\s*(\d+(?:\.\d*)?|unknown)\s*(hrs|hours)?", triptext)
        if tul:
            #assert len(tul) <= 1, (triphead, triptext)
            #assert tul[0][1] in ["hrs", "hours"], (triphead, triptext)
            tu = tul[0][0]
        else:
            tu = ""
            #assert tripcave == "Journey", (triphead, triptext)

        print tripdate
        ldate = ParseDate(tripdate.strip(), year)
        #print "\n", tripcave, "---   ppp", trippeople, len(triptext)
        EnterLogIntoDbase(date = ldate, place = tripcave, title = tripplace, text = triptext, trippeople=trippeople, expedition=expedition, logtime_underground=0)

# 2002, 2004, 2005
def Parseloghtmltxt(year, expedition, txt):
    tripparas = re.findall("<hr\s*/>([\s\S]*?)(?=<hr)", txt)
    for trippara in tripparas:
        
        s = re.match('''(?x)(?:\s*<div\sclass="tripdate"\sid=".*?">.*?</div>\s*<p>)?  # second date
                            \s*(?:<a\s+id="(.*?)"\s*/>)?
                            \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:
            print "can't parse: ", trippara  # this is 2007 which needs editing
            #assert s, trippara
            continue

        tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups()
        ldate = ParseDate(tripdate.strip(), year)
        #assert tripid[:-1] == "t" + tripdate, (tripid, tripdate)
        trippeople = re.sub("Ol(?!l)", "Olly", trippeople)        
        trippeople = re.sub("Wook(?!e)", "Wookey", trippeople)        
        triptitles = triptitle.split(" - ")
        if len(triptitles) >= 2:
            tripcave = triptitles[0]
        else:
            tripcave = "UNKNOWN"
        #print "\n", tripcave, "---   ppp", trippeople, len(triptext)
        ltriptext = re.sub("</p>", "", triptext)
        ltriptext = re.sub("\s*?\n\s*", " ", ltriptext)
        ltriptext = re.sub("<p>", "\n\n", ltriptext).strip()
        EnterLogIntoDbase(date = ldate, place = tripcave, title = triptitle, text = ltriptext, trippeople=trippeople, expedition=expedition, logtime_underground=0)


# main parser for pre-2001.  simpler because the data has been hacked so much to fit it
def Parseloghtml01(year, expedition, txt):
    tripparas = re.findall("<hr[\s/]*>([\s\S]*?)(?=<hr)", txt)
    for trippara in tripparas:
        s = re.match(u"(?s)\s*(?:<p>)?(.*?)</?p>(.*)$(?i)", trippara)
        assert s, trippara[:300]
        tripheader, triptext = s.group(1), s.group(2)
        mtripid = re.search('<a id="(.*?)"', tripheader)
        tripid = mtripid and mtripid.group(1) or ""
        tripheader = re.sub("</?(?:[ab]|span)[^>]*>", "", tripheader)

        #print "   ", [tripheader]
        #continue

        tripdate, triptitle, trippeople = tripheader.split("|")
        ldate = ParseDate(tripdate.strip(), year)
    
        mtu = re.search('<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('(?:<a href="[^"]*">[^<]*</a>|\s|/|-|&amp;|</?p>|\((?:same day|\d+)\))*$', ltriptext)
        if mtail:
            #print mtail.group(0)
            ltriptext = ltriptext[:mtail.start(0)]
        ltriptext = re.sub("</p>", "", ltriptext)
        ltriptext = re.sub("\s*?\n\s*", " ", ltriptext)
        ltriptext = re.sub("<p>|<br>", "\n\n", ltriptext).strip()
        #ltriptext = re.sub("[^\s0-9a-zA-Z\-.,:;'!]", "NONASCII", ltriptext)
        ltriptext = re.sub("</?u>", "_", ltriptext)
        ltriptext = re.sub("</?i>", "''", ltriptext)
        ltriptext = re.sub("</?b>", "'''", ltriptext)
        

        print ldate, trippeople.strip()
            # could includ the tripid (url link for cross referencing)
        EnterLogIntoDbase(date=ldate, place=tripcave, title=triptitle, text=ltriptext, trippeople=trippeople, expedition=expedition, logtime_underground=0)


def Parseloghtml03(year, expedition, txt):
    tripparas = re.findall("<hr\s*/>([\s\S]*?)(?=<hr)", txt)
    for trippara in tripparas:
        s = re.match(u"(?s)\s*<p>(.*?)</p>(.*)$", trippara)
        assert s, trippara
        tripheader, triptext = s.group(1), s.group(2)
        tripheader = re.sub("&nbsp;", " ", tripheader)
        tripheader = re.sub("\s+", " ", tripheader).strip()
        sheader = tripheader.split(" -- ")
        tu = ""
        if re.match("T/U|Time underwater", sheader[-1]):
            tu = sheader.pop()
        if len(sheader) != 3:
            print sheader
        #    continue
        tripdate, triptitle, trippeople = sheader
        ldate = ParseDate(tripdate.strip(), year)
        triptitles = triptitle.split(" , ")
        if len(triptitles) >= 2:
            tripcave = triptitles[0]
        else:
            tripcave = "UNKNOWN"
        #print tripcave, "---   ppp", triptitle, trippeople, len(triptext)
        ltriptext = re.sub("</p>", "", triptext)
        ltriptext = re.sub("\s*?\n\s*", " ", ltriptext)
        ltriptext = re.sub("<p>", "\n\n", ltriptext).strip()
        ltriptext = re.sub("[^\s0-9a-zA-Z\-.,:;'!&()\[\]<>?=+*%]", "_NONASCII_", ltriptext)
        EnterLogIntoDbase(date = ldate, place = tripcave, title = triptitle, text = ltriptext, trippeople=trippeople, expedition=expedition, logtime_underground=0)

yearlinks = [ 
                ("2009", "2009/2009logbook.txt", Parselogwikitxt), 
                ("2008", "2008/2008logbook.txt", Parselogwikitxt), 
                ("2007", "2007/logbook.html", Parseloghtmltxt), 
                ("2006", "2006/logbook/logbook_06.txt", Parselogwikitxt), 
                ("2005", "2005/logbook.html", Parseloghtmltxt), 
                ("2004", "2004/logbook.html", Parseloghtmltxt), 
                ("2003", "2003/logbook.html", Parseloghtml03), 
                ("2002", "2002/logbook.html", Parseloghtmltxt), 
                ("2001", "2001/log.htm", Parseloghtml01), 
                ("2000", "2000/log.htm", Parseloghtml01), 
                ("1999", "1999/log.htm", Parseloghtml01), 
                ("1998", "1998/log.htm", Parseloghtml01), 
                ("1997", "1997/log.htm", Parseloghtml01), 
                ("1996", "1996/log.htm", Parseloghtml01),
                ("1995", "1995/log.htm", Parseloghtml01), 
                ("1994", "1994/log.htm", Parseloghtml01), 
                ("1993", "1993/log.htm", Parseloghtml01), 		
                ("1992", "1992/log.htm", Parseloghtml01), 		
                ("1991", "1991/log.htm", Parseloghtml01), 		
            ]

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.
    """
    for personexpedition in expedition.personexpedition_set.all():
        persontrips = personexpedition.persontrip_set.order_by('logbook_entry__date')
        personexpedition.date_from = min([persontrip.logbook_entry.date  for persontrip in persontrips] or [None])
        personexpedition.date_to = max([persontrip.logbook_entry.date  for persontrip in persontrips] or [None])
        personexpedition.save()

        # 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()
            
    # from trips rather than logbook entries, which may include events outside the expedition
    expedition.date_from = min([personexpedition.date_from  for personexpedition in expedition.personexpedition_set.all()  if personexpedition.date_from] or [None])
    expedition.date_to = max([personexpedition.date_to  for personexpedition in expedition.personexpedition_set.all()  if personexpedition.date_to] or [None])
    expedition.save()

# The below has been replaced with the methods get_next_by_id and get_previous_by_id
#    # order by appearance in the logbook (done by id)
#    lprevlogbookentry = None
#    for logbookentry in expedition.logbookentry_set.order_by('id'):
#        logbookentry.logbookentry_prev = lprevlogbookentry
#        if lprevlogbookentry:
#            lprevlogbookentry.logbookentry_next = logbookentry
#            lprevlogbookentry.save()
#        logbookentry.logbookentry_next = None
#        logbookentry.save()
#        lprevlogbookentry = logbookentry
        
# This combined date / number key is a weird way of doing things. Use the primary key instead. If we are going to use the date for looking up entries, we should set it up to allow multiple results.
    # order by date for setting the references
#    lprevlogbookentry = None
#    for logbookentry in expedition.logbookentry_set.order_by('date'):
#        if lprevlogbookentry and lprevlogbookentry.date == logbookentry.date:
#            mcount = re.search("_(\d+)$", lprevlogbookentry.href)
#            mc = mcount and (int(mcount.group(1)) + 1) or 1
#            logbookentry.href = "%s_%d" % (logbookentry.date, mc)
#        else:
#            logbookentry.href = "%s" % logbookentry.date
#        logbookentry.save()
#        lprevlogbookentry = logbookentry

        
        
def LoadLogbookForExpedition(expedition):
    """ Parses all logbook entries for one expedition """
    
    #We're checking for stuff that's changed in admin before deleting it now.
    #print "deleting logbooks for", expedition
    #expedition.logbookentry_set.all().delete()
    #models.PersonTrip.objects.filter(person_expedition__expedition=expedition).delete()
    
    expowebbase = os.path.join(settings.EXPOWEB, "years")  
    year = str(expedition.year)
    for lyear, lloc, parsefunc in yearlinks:
        if lyear == year:
            break
    fin = open(os.path.join(expowebbase, lloc))
    print "opennning", lloc
    txt = fin.read().decode("latin1")
    fin.close()
    parsefunc(year, expedition, txt)
    SetDatesFromLogbookEntries(expedition)
    return "TOLOAD: " + year + "  " + str(expedition.personexpedition_set.all()[1].logbookentry_set.count()) + "  " + str(models.PersonTrip.objects.filter(person_expedition__expedition=expedition).count())


def LoadLogbooks():
    """ This is the master function for parsing all logbooks into the Troggle database. Requires yearlinks, which is a list of tuples for each expedition with expedition year, logbook path, and parsing function. """
    
    #Deletion has been moved to a seperate function to enable the non-destructive importing
    #models.LogbookEntry.objects.all().delete()
    expowebbase = os.path.join(settings.EXPOWEB, "years")  
    #yearlinks = [ ("2001", "2001/log.htm", Parseloghtml01), ] #overwrite
    #yearlinks = [ ("1996", "1996/log.htm", Parseloghtml01),] # overwrite

    for year, lloc, parsefunc in yearlinks:
        expedition = models.Expedition.objects.filter(year = year)[0]
        fin = open(os.path.join(expowebbase, lloc))
        txt = fin.read().decode("latin1")
        fin.close()
        parsefunc(year, expedition, txt)
        SetDatesFromLogbookEntries(expedition)