diff options
Diffstat (limited to 'parsers/logbooks.py')
| -rw-r--r-- | parsers/logbooks.py | 43 |
1 files changed, 32 insertions, 11 deletions
diff --git a/parsers/logbooks.py b/parsers/logbooks.py index e2f0ba0..f0ae2fa 100644 --- a/parsers/logbooks.py +++ b/parsers/logbooks.py @@ -12,6 +12,7 @@ from django.template.defaultfilters import slugify from django.utils.timezone import get_current_timezone, make_aware import troggle.core.models as models +import troggle.core.models_caves as models_caves from parsers.people import GetPersonExpeditionNameLookup from utils import save_carefully @@ -49,23 +50,24 @@ def GetTripPersons(trippeople, expedition, logtime_underground): 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 +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))) + katastNumRes=list(models_caves.Cave.objects.filter(kataster_number=int(place))) except ValueError: pass - officialNameRes=list(models.Cave.objects.filter(official_name=place)) + officialNameRes=list(models_caves.Cave.objects.filter(official_name=place)) tripCaveRes=officialNameRes+katastNumRes if len(tripCaveRes)==1: -# print "Place " , place , "entered as" , tripCaveRes[0] + # 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 + elif models_caves.OtherCaveName.objects.filter(name=place): + tripCaveRes=models_caves.OtherCaveName.objects.filter(name__icontains=place)[0].cave + # print "Place " , place , "entered as" , tripCaveRes return tripCaveRes elif len(tripCaveRes)>1: @@ -76,6 +78,25 @@ def GetTripCave(place): #need to be fuzzier about matching here. Already a very print(("No cave found for place " , place)) return +# lookup function modelled on GetPersonExpeditionNameLookup +Gcavelookup = None +def GetCaveLookup(): + global Gcavelookup + if Gcavelookup: + return Gcavelookup + Gcavelookup = {"NONEPLACEHOLDER":None} + for cave in models_caves.Cave.objects.all(): + Gcavelookup[cave.official_name.lower()] = cave + if cave.kataster_number: + Gcavelookup[cave.kataster_number] = cave + if cave.unofficial_number: + Gcavelookup[cave.unofficial_number] = cave + + Gcavelookup["tunnocks"] = Gcavelookup["258"] + Gcavelookup["hauchhole"] = Gcavelookup["234"] + return Gcavelookup + + logentries = [] # the entire logbook is a single object: a list of entries noncaveplaces = [ "Journey", "Loser Plateau" ] @@ -195,7 +216,6 @@ def Parseloghtmltxt(year, expedition, txt): if logbook_entry_count == 0: print(" - No trip entries found in logbook, check the syntax matches htmltxt format") - # main parser for 1991 - 2001. simpler because the data has been hacked so much to fit it def Parseloghtml01(year, expedition, txt): tripparas = re.findall(r"<hr[\s/]*>([\s\S]*?)(?=<hr)", txt) @@ -381,6 +401,7 @@ def LoadLogbookForExpedition(expedition): #return "TOLOAD: " + year + " " + str(expedition.personexpedition_set.all()[1].logbookentry_set.count()) + " " + str(models.PersonTrip.objects.filter(personexpedition__expedition=expedition).count()) + def LoadLogbooks(): """ This is the master function for parsing all logbooks into the Troggle database. """ @@ -440,7 +461,7 @@ def parseAutoLogBookEntry(filename): if caveMatch: caveRef, = caveMatch.groups() try: - cave = models.getCaveByReference(caveRef) + cave = models_caves.getCaveByReference(caveRef) except AssertionError: cave = None errors.append("Cave not found in database") @@ -496,4 +517,4 @@ def parseAutoLogBookEntry(filename): time_underground = TU, logbook_entry = logbookEntry, is_logbook_entry_author = author).save() - print(logbookEntry) + print(logbookEntry)
\ No newline at end of file |