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
|
import csv
import os
import re
from html import unescape
from pathlib import Path
from django.conf import settings
from django.contrib.auth.models import User
from django.db import models
from unidecode import unidecode
from troggle.core.models.troggle import DataIssue, Expedition, Person, PersonExpedition
from troggle.core.views.signup import read_signups
"""These functions do not match how the stand-alone folk script works. So the script produces an HTML file which has
href links to pages in troggle which troggle does not think are right.
The standalone script needs to be renedred defucnt, and all the parsing needs to be in troggle. Either that,
or they should use the same code by importing a module.
"""
todo = """
- [copy these from paper notes]
"""
def parse_blurb(personline, header, person):
"""create mugshot Photo instance
Would be better if all this was done before the Person object was created in the db, then it would not
need re-saving (which is slow)"""
ms_filename = personline[header["Mugshot"]]
ms_path = Path(settings.EXPOWEB, "folk", ms_filename)
if ms_filename:
if not ms_path.is_file():
message = f"! INVALID mug_shot field '{ms_filename}' for {person.fullname}"
print(message)
DataIssue.objects.create(parser="people", message=message, url=f"/person/{person.fullname}")
return
if ms_filename.startswith("i/"):
# if person just has an image, add it. It has format 'i/adama2018.jpg'
person.mug_shot = str(Path("/folk", ms_filename))
person.blurb = None
elif ms_filename.startswith("l/"):
# it has the format 'l/ollybetts.htm' the file may contain <img src="../i/mymug.jpg"> images
with open(ms_path, "r") as blurbfile:
blrb = blurbfile.read()
pblurb = re.search(r"<body>.*<hr", blrb, re.DOTALL)
if pblurb:
person.mug_shot = None
fragment = re.search("<body>(.*)<hr", blrb, re.DOTALL).group(1)
fragment = fragment.replace('src="../i/', 'src="/folk/i/')
fragment = fragment.replace("src='../i/", "src='/folk/i/")
fragment = re.sub(r"<h.*>[^<]*</h.>", "", fragment)
# replace src="../i/ with src="/folk/i
person.blurb = fragment
else:
message = f"! Blurb parse error in {ms_filename}"
print(message)
DataIssue.objects.create(parser="people", message=message, url="/folk/")
elif ms_filename == "":
pass
else:
message = f"! Unrecognised type of file at mug_shot field '{ms_filename}' for {person.fullname}"
print(message)
DataIssue.objects.create(parser="people", message=message, url="/folk/")
person.save()
slug_cache = {}
def troggle_slugify(longname):
"""Uniqueness enforcement too. Yes we have had two "Dave Johnson"s
This function copied intact to expoweb/scripts/make-folklist.py
"""
slug = longname.strip().lower().replace(" ","-")
slug = re.sub(r'\([^\)]*\)','',slug) # remove nickname in brackets
slug = slug.replace('é', 'e')
slug = slug.replace('á', 'a')
slug = slug.replace('ä', 'a')
slug = slug.replace('&', '') # otherwise just remove the &
slug = slug.replace(';', '') # otherwise just remove the ;
slug = slug.replace("'", "") # otherwise just remove the ', no O'Reilly problem # NEW
slug = re.sub(r'<[^>]*>','',slug) # remove <span-lang = "hu"> and any HTML tags
slug=slug.strip("-") # remove spare hyphens
if len(slug) > 40: # slugfield is 50 chars
slug = slug[:40]
if slug in slug_cache:
slug_cache[slug] += 1
slug = f"{slug}_{slug_cache[slug]}"
slug_cache[slug] = 1
return slug
def load_people_expos():
"""This is where the folk.csv file is parsed to read people's names.
This is ALSO where all the Expedition objects get created. So this is the point at which troggle
gets told what expeditions exist.
Given that we need to do stuff for the coming expo, well before we update the folk list,
the Expedition object for the coming expo is created elsewhere - in addition to
those created here, if it does not exist.
"""
DataIssue.objects.filter(parser="people").delete()
persontab = open(os.path.join(settings.EXPOWEB, "folk", "folk.csv")) # should really be EXPOFOLK I guess
personreader = csv.reader(persontab) # this is an iterator
headers = next(personreader)
header = dict(list(zip(headers, list(range(len(headers))))))
years = headers[5:]
nexpos = Expedition.objects.count()
if nexpos <= 0:
print(" - Creating expeditions")
for year in years:
year = year.strip()
coUniqueAttribs = {"year": year}
otherAttribs = {"name": f"CUCC expo {year}"}
e = Expedition.objects.create(**otherAttribs, **coUniqueAttribs)
print(" - Loading personexpeditions")
for personline in personreader:
# This is all horrible: refactor it.
# CSV: Name,Lastname,Guest,VfHO member,Mugshot,..
# e.g: Olly Betts (Ol),Betts,,,l/ollybetts.htm,
name = personline[header["Name"]]
plainname = re.sub(r"<.*?>", "", name) # now in slugify
match = re.match(r"^([^(]*)(\(([^)]*)\))?", name) # removes nickname in brackets
displayname = match.group(1)
slug = troggle_slugify(displayname)
firstname = ""
nick = ""
rawlastname = personline[header["Lastname"]].strip()
if rawlastname == "":
print(f"MISSING SURNAME FIELD for {name} - check against similar names in the list to see what you have done.")
if matchlastname := re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", rawlastname):
lastname = matchlastname.group(1).strip()
else:
print(f"MATCH FAIL {personline=}\n {slug=}\n {name=}\n {rawlastname=}")
exit(1)
splitnick = re.match(r"^([\w&;\s\-]+)(?:\(([^)]*)\))?", plainname)
fullname = splitnick.group(1) # removes Nickname in brackets, but also cuts hyphenated names
nick = splitnick.group(2) or ""
fullname = fullname.strip()
names = fullname.split(" ") # This may have more than one, e.g. "Adeleide de Diesback"
firstname = names[0]
if len(names) == 1:
lastname = "" # wookey special code
#restore fullname to be the whole string
fullname = displayname
if personline[header["VfHO member"]] == "":
vfho = False
else:
vfho = True
# would be better to just create the python object, and only cmmit to db once all done inc blurb
# and better to save all the Persons in a bulk update, then do all the PersonExpeditions
coUniqueAttribs = {"slug": slug}
otherAttribs = {"first_name": firstname, "last_name": (lastname or ""), "is_vfho": vfho, "fullname": fullname, "nickname": nick,"is_guest": (personline[header["Guest"]] == "1")}
person = Person.objects.create(**otherAttribs, **coUniqueAttribs)
parse_blurb(personline=personline, header=header, person=person) # saves to db too
# make person expedition from table
for year, attended in list(zip(headers, personline))[5:]:
expedition = Expedition.objects.get(year=year)
if attended == "1" or attended == "-1":
coUniqueAttribs = {"person": person, "expedition": expedition}
# otherAttribs = {"is_guest": (personline[header["Guest"]] == "1")}
pe = PersonExpedition.objects.create(**coUniqueAttribs)
print("", flush=True)
ensure_users_are_persons()
most_recent = Expedition.objects.all().first()
check_new_signups(most_recent)
def check_new_signups(expedition):
signups_clear = read_signups()
# print(signups_clear)
for slug in signups_clear:
print(slug)
p = Person.objects.get(slug=slug)
pe = PersonExpedition.objects.update_or_create(person=p, expedition=expedition)
# print("ADDING ",pe, expedition)
def ensure_users_are_persons():
# Just ensure this is up to date.
print(f"# ensure_users_are_persons() - except for expo and expoadmin of course")
users = User.objects.all()
for u in users:
ps = Person.objects.filter(slug=u.username)
if len(ps) >= 1:
p = ps[0]
p.user = u
p.save()
print(f" - {p.user} {u=}")
def who_is_this(year, possibleid):
expo = Expedition.objects.filter(year=year)
personexpedition = GetPersonExpeditionNameLookup(expo)[possibleid.lower()]
if personexpedition:
return personexpedition.person
else:
return None
def when_on_expo(name):
"""Returns a list of PersonExpedition objects for the string, if recognised as a name
"""
person_expos = []
expos = Expedition.objects.all()
for expo in expos:
expoers = GetPersonExpeditionNameLookup(expo)
if name in expoers:
person_expos.append(expoers[name])
print(f"{name} => {expoers[name]}")
return person_expos
global foreign_friends
foreign_friends = [
"Aiko",
"Arndt Karger",
"Dominik Jauch",
"Florian Gruner",
"Fritz Mammel",
"Gunter Graf",
"Helmut Stopka-Ebeler",
"K. Jäger",
"Kai Schwekend",
"Karl Gaisberger",
"Marcus Scheuermann",
"Marcus Scheuerman",
"Mark Morgan",
"P. Jeutter",
"R. Seebacher",
"Regina Kaiser",
"Robert Seebacher",
"S. Steinberger",
"Sepp Steinberger",
"Thilo Müller",
"Uli Schütz",
"Wieland Scheuerle",
]
def known_foreigner(id):
"""If this someone from ARGE or a known Austrian? Name has to be exact, no soft matching
"""
global foreign_friends
if id in foreign_friends:
return True
else:
return False
# Refactor. The dict GetPersonExpeditionNameLookup(expo) indexes by name and has values of personexpedition
# This is convoluted, the personexpedition concept is unnecessary, should it just retunr person??
# Or better, query with a string and return a list of personexpeditions
Gpersonexpeditionnamelookup = {}
def GetPersonExpeditionNameLookup(expedition):
"""Yes this should all be in an editable text file, not in the body of the code. Sorry.
This uses the existing database records of everone on an expedition to construct a dictionary
indexedby every possible pseudonym or alias that the person might be known by.
This dictionary is used when parsing logbooks and survex files to identify who is being
referred to, when the name written in the logbook is e.g. "Mike TA" == "Mike The Animal"
== "Mike Rickardson".
"""
global Gpersonexpeditionnamelookup
def apply_variations(f, l):
"""Be generous in guessing possible matches. Any duplicates will be ruled as invalid."""
f = f.lower()
l = l.lower()
variations = []
variations.append(f)
variations.append(l)
variations.append(f + l)
variations.append(f + " " + l)
variations.append(f + " " + l[0])
variations.append(f + l[0])
variations.append(f + " " + l[0] + ".")
variations.append(f[0] + " " + l)
variations.append(f[0] + ". " + l)
variations.append(f[0] + l)
variations.append(f[0] + l[0]) # initials e.g. gb or bl
return variations
res = Gpersonexpeditionnamelookup.get(expedition.name)
if res:
return res
res = {}
duplicates = set()
# print("Calculating GetPersonExpeditionNameLookup for " + expedition.year)
personexpeditions = PersonExpedition.objects.filter(expedition=expedition)
short = {}
dellist = []
for personexpedition in personexpeditions:
possnames = []
f = unidecode(unescape(personexpedition.person.first_name.lower().strip()))
l = unidecode(unescape(personexpedition.person.last_name.lower().strip()))
full = unidecode(unescape(personexpedition.person.fullname.lower().strip()))
n = unidecode(unescape(personexpedition.person.nickname.lower().strip()))
if full not in possnames:
possnames.append(full)
if n not in possnames:
possnames.append(n)
if l:
possnames += apply_variations(f, l)
if n:
possnames += apply_variations(n, l)
if f == "Adeleide".lower():
possnames += apply_variations("Adelaide", l)
if f == "Adelaide".lower():
possnames += apply_variations("Adeleide", l)
if f == "Robert".lower():
possnames += apply_variations("Bob", l)
if f == "Rob".lower():
possnames += apply_variations("Robert", l)
if f == "Thomas".lower():
possnames += apply_variations("Tom", l)
if f == "Tom".lower():
possnames += apply_variations("Thomas", l)
if f == "Lizzy".lower():
possnames += apply_variations("Lizzie", l)
if f == "Lizzie".lower():
possnames += apply_variations("Lizzy", l)
if f == "Phil".lower(): # needed when Phil is used with a surname initial, so default short-form does not work.
possnames += apply_variations("Philip", l)
if f == "Philip".lower():
possnames += apply_variations("Phil", l)
if f == "Andrew".lower():
possnames += apply_variations("Andy", l)
if f == "Andy".lower():
possnames += apply_variations("Andrew", l)
if f == "Michael".lower():
possnames += apply_variations("Mike", l)
if f == "Mike".lower():
possnames += apply_variations("Michael", l)
if f == "David".lower():
possnames += apply_variations("Dave", l)
if f == "Dave".lower():
possnames += apply_variations("David", l)
if f == "Peter".lower():
possnames += apply_variations("Pete", l)
if f == "Pete".lower():
possnames += apply_variations("Peter", l)
if f == "Tobias".lower():
possnames += apply_variations("Toby", l)
if f == "Toby".lower():
possnames += apply_variations("Tobias", l)
if f == "Olly".lower():
possnames += apply_variations("Oliver", l)
if f == "Oliver".lower():
possnames += apply_variations("Olly", l)
if f == "Ollie".lower():
possnames += apply_variations("Oliver", l)
if f == "Oliver".lower():
possnames += apply_variations("Ollie", l)
if f == "Becka".lower():
possnames += apply_variations("Rebecca", l)
if f"{f} {l}" == "Andy Waddington".lower():
possnames += apply_variations("aer", "waddington")
if f"{f} {l}" == "Phil Underwood".lower():
possnames += apply_variations("phil", "underpants")
if f"{f} {l}" == "Naomi Griffiths".lower():
possnames += apply_variations("naomi", "makins")
if f"{f} {l}" == "Tina White".lower():
possnames += apply_variations("tina", "richardson")
if f"{f} {l}" == "Cat Hulse".lower():
possnames += apply_variations("catherine", "hulse")
possnames += apply_variations("cat", "henry")
if f"{f} {l}" == "Jess Stirrups".lower():
possnames += apply_variations("jessica", "stirrups")
if f"{f} {l}" == "Nat Dalton".lower():
possnames += apply_variations("nathanael", "dalton") # correct. He has a weird spelling.
if f"{f} {l}" == "Mike Richardson".lower():
possnames.append("mta")
possnames.append("miketa")
possnames.append("mike the animal")
possnames.append("animal")
if f"{f} {l}" == "Eric Landgraf".lower():
possnames.append("eric c.landgraf")
possnames.append("eric c. landgraf")
possnames.append("eric c landgraf")
if f"{f} {l}" == "Nadia Raeburn".lower():
possnames.append("tinywoman")
possnames.append("nadia rc")
possnames.append("nadia raeburn-cherradi")
if f"{f} {l}" == "Phil Wigglesworth".lower():
possnames.append("wiggy")
if f"{f} {l}" == "Philip Banister".lower():
possnames.append("crofton")
if f"{f} {l}" == "Elaine Oliver".lower():
possnames.append("cavingpig")
if f"{f} {l}" == "Tom Crossley".lower():
possnames.append("tcacrossley")
if f"{f} {l}" == "Rob Watson".lower():
possnames.append("nobrotson")
if f"{f} {l}" == "Todd Rye".lower():
possnames.append("samouse1")
if f"{f} {l}" == "Jono Lester".lower():
possnames.append("ILoveCaves")
if f"{f} {l}" == "Joel Stobbart".lower():
possnames.append("El Stobbarto")
if f"{f} {l}" == "Rob Watson".lower():
possnames.append("nobrotson")
for i in [3, 4, 5, 6]:
lim = min(i, len(f) + 1) # short form, e.g. Dan for Daniel.
if f[:lim] not in short:
short[f[:lim]] = personexpedition
else:
dellist.append(f[:lim])
possnames = set(possnames) # remove duplicates
for possname in possnames:
if possname in res:
duplicates.add(possname)
else:
res[possname] = personexpedition
for possname in duplicates:
del res[possname]
for possname in dellist:
if possname in short: # always true ?
del short[possname]
for shortname in short:
res[shortname] = short[shortname]
Gpersonexpeditionnamelookup[expedition.name] = res
return res
|
