expo/troggle
2
0
Fork 1
mirror of https://expo.survex.com/repositories/troggle/.git synced 2024-11-25 16:51:54 +00:00
Code Issues 19 Projects 3 Activity

Allow comments against names in logbooks in brackets

Browse Source 
Convert accent chars in names into simple chars as this is what people enter in the logbook
This commit is contained in:
Sam Wenham 2019-07-11 12:29:38 +01:00
parent 6b5b9a5315
commit a26109cb30
2 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
parsers/logbooks.py
View File

@ -25,9 +25,10 @@ from utils import save_carefully
# #
# the logbook loading section # the logbook loading section
# #
def GetTripPersons(trippeople, expedition, logtime_underground): def GetTripPersons(trippeople, expedition, logtime_underground):
res = [ ] res = [ ]
author = None author = None
round_bracket_regex = re.compile(r"[\(\[].*?[\)\]]")
for tripperson in re.split(r",|\+|&|&(?!\w+;)| and ", trippeople): for tripperson in re.split(r",|\+|&|&(?!\w+;)| and ", trippeople):
tripperson = tripperson.strip() tripperson = tripperson.strip()
mul = re.match(r"<u>(.*?)</u>$(?i)", tripperson) mul = re.match(r"<u>(.*?)</u>$(?i)", tripperson)
@ -35,6 +36,7 @@ def GetTripPersons(trippeople, expedition, logtime_underground):
tripperson = mul.group(1).strip() tripperson = mul.group(1).strip()
if tripperson and tripperson[0] != '*': if tripperson and tripperson[0] != '*':
#assert tripperson in personyearmap, "'%s' << %s\n\n %s" % (tripperson, trippeople, personyearmap) #assert tripperson in personyearmap, "'%s' << %s\n\n %s" % (tripperson, trippeople, personyearmap)
tripperson = re.sub(round_bracket_regex, "", tripperson).strip()
personyear = GetPersonExpeditionNameLookup(expedition).get(tripperson.lower()) personyear = GetPersonExpeditionNameLookup(expedition).get(tripperson.lower())
if not personyear: if not personyear:
print(" - No name match for: '%s'" % tripperson) print(" - No name match for: '%s'" % tripperson)
@ -172,8 +174,8 @@ def Parseloghtmltxt(year, expedition, txt):
tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups() tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups()
ldate = ParseDate(tripdate.strip(), year) ldate = ParseDate(tripdate.strip(), year)
#assert tripid[:-1] == "t" + tripdate, (tripid, tripdate) #assert tripid[:-1] == "t" + tripdate, (tripid, tripdate)
#trippeople = re.sub(r"Ol(?!l)", "Olly", trippeople) #trippeople = re.sub(r"Ol(?!l)", "Olly", trippeople)
#trippeople = re.sub(r"Wook(?!e)", "Wookey", trippeople) #trippeople = re.sub(r"Wook(?!e)", "Wookey", trippeople)
triptitles = triptitle.split(" - ") triptitles = triptitle.split(" - ")
if len(triptitles) >= 2: if len(triptitles) >= 2:
tripcave = triptitles[0] tripcave = triptitles[0]

11
parsers/people.py
View File

@ -4,6 +4,8 @@ from django.conf import settings
import troggle.core.models as models import troggle.core.models as models
import csv, re, datetime, os, shutil import csv, re, datetime, os, shutil
from utils import save_carefully from utils import save_carefully
from HTMLParser import HTMLParser
from unidecode import unidecode
def saveMugShot(mugShotPath, mugShotFilename, person): 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 if mugShotFilename.startswith(r'i/'): #if filename in cell has the directory attached (I think they all do), remove it
@ -132,11 +134,12 @@ def GetPersonExpeditionNameLookup(expedition):
print("Calculating GetPersonExpeditionNameLookup for " + expedition.year) print("Calculating GetPersonExpeditionNameLookup for " + expedition.year)
personexpeditions = models.PersonExpedition.objects.filter(expedition=expedition) personexpeditions = models.PersonExpedition.objects.filter(expedition=expedition)
htmlparser = HTMLParser()
for personexpedition in personexpeditions: for personexpedition in personexpeditions:
possnames = [ ] possnames = [ ]
f = personexpedition.person.first_name.lower() f = unidecode(htmlparser.unescape(personexpedition.person.first_name.lower()))
l = personexpedition.person.last_name.lower() l = unidecode(htmlparser.unescape(personexpedition.person.last_name.lower()))
full = personexpedition.person.fullname.lower() full = unidecode(htmlparser.unescape(personexpedition.person.fullname.lower()))
if l: if l:
possnames.append(f + " " + l) possnames.append(f + " " + l)
possnames.append(f + " " + l[0]) possnames.append(f + " " + l[0])
@ -154,6 +157,8 @@ def GetPersonExpeditionNameLookup(expedition):
possnames.append(personexpedition.nickname.lower() + " " + l) possnames.append(personexpedition.nickname.lower() + " " + l)
if str(personexpedition.nickname.lower() + " " + l[0]) not in possnames: if str(personexpedition.nickname.lower() + " " + l[0]) not in possnames:
possnames.append(personexpedition.nickname.lower() + " " + l[0]) 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: for possname in possnames:
if possname in res: if possname in res: