2
0
mirror of https://expo.survex.com/repositories/troggle/.git synced 2024-11-22 07:11:52 +00:00
troggle/parsers/people.py
2020-06-19 16:39:05 +01:00

187 lines
8.1 KiB
Python

#.-*- coding: utf-8 -*-
from django.conf import settings
import troggle.core.models as models
import csv, re, datetime, os, shutil
from utils import save_carefully
from html.parser import HTMLParser
from unidecode import unidecode
# def saveMugShot(mugShotPath, mugShotFilename, person):
# if mugShotFilename.startswith(r'i/'): #if filename in cell has the directory attached (I think they all do), remove it
# mugShotFilename=mugShotFilename[2:]
# else:
# mugShotFilename=mugShotFilename # just in case one doesn't
# dummyObj=models.DPhoto(file=mugShotFilename)
# #Put a copy of the file in the right place. mugShotObj.file.path is determined by the django filesystemstorage specified in models.py
# if not os.path.exists(dummyObj.file.path):
# shutil.copy(mugShotPath, dummyObj.file.path)
# mugShotObj, created = save_carefully(
# models.DPhoto,
# lookupAttribs={'is_mugshot':True, 'file':mugShotFilename},
# nonLookupAttribs={'caption':"Mugshot for "+person.first_name+" "+person.last_name}
# )
# if created:
# mugShotObj.contains_person.add(person)
# mugShotObj.save()
def parseMugShotAndBlurb(personline, header, person):
"""create mugshot Photo instance"""
mugShotFilename=personline[header["Mugshot"]]
mugShotPath = os.path.join(settings.EXPOWEB, "folk", mugShotFilename)
if mugShotPath[-3:]=='jpg': #if person just has an image, add it
#saveMugShot(mugShotPath=mugShotPath, mugShotFilename=mugShotFilename, person=person)
pass
elif mugShotPath[-3:]=='htm': #if person has an html page, find the image(s) and add it. Also, add the text from the html page to the "blurb" field in his model instance.
personPageOld=open(mugShotPath,'r').read()
if not person.blurb:
pblurb=re.search('<body>.*<hr',personPageOld,re.DOTALL)
if pblurb:
#this needs to be refined, take care of the HTML and make sure it doesn't match beyond the blurb.
#Only finds the first image, not all of them
person.blurb=re.search('<body>.*<hr',personPageOld,re.DOTALL).group()
else:
print("ERROR: --------------- Broken link or Blurb parse error in ", mugShotFilename)
#for mugShotFilename in re.findall('i/.*?jpg',personPageOld,re.DOTALL):
# mugShotPath = os.path.join(settings.EXPOWEB, "folk", mugShotFilename)
# saveMugShot(mugShotPath=mugShotPath, mugShotFilename=mugShotFilename, person=person)
person.save()
def LoadPersonsExpos():
persontab = open(os.path.join(settings.EXPOWEB, "folk", "folk.csv"))
personreader = csv.reader(persontab)
headers = next(personreader)
header = dict(list(zip(headers, list(range(len(headers))))))
# make expeditions
print(" - Loading expeditions")
years = headers[5:]
for year in years:
lookupAttribs = {'year':year}
nonLookupAttribs = {'name':"CUCC expo %s" % year}
save_carefully(models.Expedition, lookupAttribs, nonLookupAttribs)
# make persons
print(" - Loading personexpeditions")
for personline in personreader:
name = personline[header["Name"]]
name = re.sub(r"<.*?>", "", name)
firstname = ""
nickname = ""
rawlastname = personline[header["Lastname"]].strip()
matchlastname = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", rawlastname)
lastname = matchlastname.group(1).strip()
splitnick = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", name)
fullname = splitnick.group(1)
nickname = splitnick.group(2) or ""
fullname = fullname.strip()
names = fullname.split(' ')
firstname = names[0]
if len(names) == 1:
lastname = ""
if personline[header["VfHO member"]] =='':
vfho = False
else:
vfho = True
lookupAttribs={'first_name':firstname, 'last_name':(lastname or "")}
nonLookupAttribs={'is_vfho':vfho, 'fullname':fullname}
person, created = save_carefully(models.Person, lookupAttribs, nonLookupAttribs)
parseMugShotAndBlurb(personline=personline, header=header, person=person)
# make person expedition from table
for year, attended in list(zip(headers, personline))[5:]:
expedition = models.Expedition.objects.get(year=year)
if attended == "1" or attended == "-1":
lookupAttribs = {'person':person, 'expedition':expedition}
nonLookupAttribs = {'nickname':nickname, 'is_guest':(personline[header["Guest"]] == "1")}
save_carefully(models.PersonExpedition, lookupAttribs, nonLookupAttribs)
# this fills in those people for whom 2008 was their first expo
#print "Loading personexpeditions 2008"
#expoers2008 = """Edvin Deadman,Kathryn Hopkins,Djuke Veldhuis,Becka Lawson,Julian Todd,Natalie Uomini,Aaron Curtis,Tony Rooke,Ollie Stevens,Frank Tully,Martin Jahnke,Mark Shinwell,Jess Stirrups,Nial Peters,Serena Povia,Olly Madge,Steve Jones,Pete Harley,Eeva Makiranta,Keith Curtis""".split(",")
#expomissing = set(expoers2008)
#for name in expomissing:
# firstname, lastname = name.split()
# is_guest = name in ["Eeva Makiranta", "Keith Curtis"]
# print "2008:", name
# persons = list(models.Person.objects.filter(first_name=firstname, last_name=lastname))
# if not persons:
# person = models.Person(first_name=firstname, last_name = lastname, is_vfho = False, mug_shot = "")
# #person.Sethref()
# person.save()
# else:
# person = persons[0]
# expedition = models.Expedition.objects.get(year="2008")
# personexpedition = models.PersonExpedition(person=person, expedition=expedition, nickname="", is_guest=is_guest)
# personexpedition.save()
# used in other referencing parser functions
# expedition name lookup cached for speed (it's a very big list)
Gpersonexpeditionnamelookup = { }
def GetPersonExpeditionNameLookup(expedition):
global Gpersonexpeditionnamelookup
res = Gpersonexpeditionnamelookup.get(expedition.name)
if res:
return res
res = { }
duplicates = set()
#print("Calculating GetPersonExpeditionNameLookup for " + expedition.year)
personexpeditions = models.PersonExpedition.objects.filter(expedition=expedition)
htmlparser = HTMLParser()
for personexpedition in personexpeditions:
possnames = [ ]
f = unidecode(htmlparser.unescape(personexpedition.person.first_name.lower()))
l = unidecode(htmlparser.unescape(personexpedition.person.last_name.lower()))
full = unidecode(htmlparser.unescape(personexpedition.person.fullname.lower()))
if l:
possnames.append(f + " " + l)
possnames.append(f + " " + l[0])
possnames.append(f + l[0])
possnames.append(f[0] + " " + l)
possnames.append(f)
if full not in possnames:
possnames.append(full)
if personexpedition.nickname not in possnames:
possnames.append(personexpedition.nickname.lower())
if l:
# This allows for nickname to be used for short name eg Phil
# adding Phil Sargent to the list
if str(personexpedition.nickname.lower() + " " + l) not in possnames:
possnames.append(personexpedition.nickname.lower() + " " + l)
if str(personexpedition.nickname.lower() + " " + l[0]) not in possnames:
possnames.append(personexpedition.nickname.lower() + " " + l[0])
if str(personexpedition.nickname.lower() + l[0]) not in possnames:
possnames.append(personexpedition.nickname.lower() + l[0])
for possname in possnames:
if possname in res:
duplicates.add(possname)
else:
res[possname] = personexpedition
for possname in duplicates:
del res[possname]
Gpersonexpeditionnamelookup[expedition.name] = res
return res