Merge pull request 'fix_refresh_data' (#5) from fix_refresh_data into master

Reviewed-on: #5
This commit is contained in:
pcoder116 2022-03-11 11:25:35 +00:00
commit 907ae0c256
3 changed files with 96 additions and 34 deletions

View File

@ -39,7 +39,7 @@ def add_linked(person, obj, data):
tgt.name = n
tgt.save()
field.append(tgt)
return field
return field
# Fetch an object by source_id (numeric identifier used in source DB)
@ -71,7 +71,8 @@ def reindex_data():
# Data update routine
def refresh_data(filename, fmt=None):
def refresh_data(filename, fmt=None, update_existing=False):
print("refresh_data")
count = 0
rowcount = 0
if not isfile(filename):
@ -101,42 +102,72 @@ def refresh_data(filename, fmt=None):
return None
if fmt['dataformat'] is DataFormat.PERSON_DETAIL:
print(row)
person, source_id = get_by_id(row['ID'], Person)
if not person:
person = Person.objects.filter(first_name=row['First name'], last_name=row['Last name']).first()
if person:
print("Fetched from DB")
else:
print("Does not exist in DB")
if not person:
person = Person(first_name=row['First name'], last_name=row['Last name'], source_id=row['ID'])
person.source_id = source_id
person.title = row['Title']
print(row)
person.organisation = row['Organisation English']
print("Country = %s" % row['country'] if 'country' in row else '')
if 'country' not in row or row['country'] is None or row['country'].strip() == '':
row['country'] = 0
c = Country.objects.get(id=row['country'])
person.country = c
person.position = row['Position']
person.biography = row['Biography']
person.contact_email = row['e-mail 1']
person.personal_url = fix_url(row['URL'])
person.save()
print("Created")
# Update data fields
person.source_id = source_id
person.title = row['Title']
person.organisation = row['Organisation English']
print("Country = %s" % row['country'])
if row['country'] is None or row['country'].strip() == '':
row['country'] = 0
c = Country.objects.get(id=row['country'])
person.country = c
person.position = row['Position']
person.biography = row['Biography']
person.contact_email = row['e-mail 1']
person.personal_url = fix_url(row['URL'])
if update_existing:
person.source_id = source_id
person.title = row['Title']
print(row)
person.organisation = row['Organisation English']
print("Country = %s" % row['country'] if 'country' in row else '')
if 'country' not in row or row['country'] is None or row['country'].strip() == '':
row['country'] = 0
c = Country.objects.get(id=row['country'])
person.country = c
person.position = row['Position']
person.biography = row['Biography']
person.contact_email = row['e-mail 1']
person.personal_url = fix_url(row['URL'])
person.save()
with transaction.atomic():
research_methods = add_linked(person, Method, row['Methods'])
methods_people = [MethodsPeople.objects.get_or_create(method_id=m.id, person_id=person.id) for m in research_methods]
methods_people = [MethodsPeople.objects.get_or_create(method_id=m.id, person_id=person.id)[0] for m in research_methods]
person.methodspeople_set.set(methods_people)
research_scales = add_linked(person, Scale, row['Scale'])
scales_people = [ScalesPeople.objects.get_or_create(scale_id=s.id, person_id=person.id) for s in research_scales]
scales_people = [ScalesPeople.objects.get_or_create(scale_id=s.id, person_id=person.id)[0] for s in research_scales]
person.scalespeople_set.set(scales_people)
research_taxa = add_linked(person, Taxon, row['Taxa'])
taxa_people = [TaxaPeople.objects.get_or_create(taxon_id=t.id, person_id=person.id) for t in research_taxa]
taxa_people = [TaxaPeople.objects.get_or_create(taxon_id=t.id, person_id=person.id)[0] for t in research_taxa]
person.taxapeople_set.set(taxa_people)
research_fields = add_linked(person, Field, row['Field of expertise'])
fields_people = [FieldsPeople.objects.get_or_create(field_id=f.id, person_id=person.id) for f in research_fields]
fields_people = [FieldsPeople.objects.get_or_create(field_id=f.id, person_id=person.id)[0] for f in research_fields]
person.fieldspeople_set.set(fields_people)
# research_ranges = add_linked(person, MountainRange, row['MountainRange'])
# ranges_people = [RangesPeople.objects.get_or_create(range_id=r.id, person_id=person.id)[0] for r in research_ranges]
# person.rangespeople_set.set(ranges_people)
person.index()
person.save()
count = count + 1
elif fmt['dataformat'] is DataFormat.RESOURCE_DETAIL:
res, source_id = get_by_id(row['ID'], Resource)
if not res: res = Resource(source_id=source_id)
if not res:
res = Resource(source_id=source_id)
res.title = row['Title']
res.citation = row['Citation']
res.url = fix_url(row['URL'].strip('#')) # remove weird #formatting#
@ -155,9 +186,11 @@ def refresh_data(filename, fmt=None):
elif fmt['dataformat'] is DataFormat.PERSON_RESOURCE:
rzs, source_id = get_by_id(row['Resource'], Resource, first=False)
if not rzs or not rzs.first(): continue
if not rzs or not rzs.first():
continue
ppl, source_id = get_by_id(row['Person'], Person, first=False)
if not ppl or not ppl.first(): continue
if not ppl or not ppl.first():
continue
for person in ppl:
person.resources = []
for r in rzs:
@ -167,15 +200,30 @@ def refresh_data(filename, fmt=None):
elif fmt['dataformat'] is DataFormat.PERSON_RANGE:
rzs, source_id = get_by_id(row['MountainRange'], MountainRange, first=False)
print(" range=%s, source_id=%s" % (rzs, source_id))
if not rzs or not rzs.first():
print(" --- No rzs, continue")
continue
ppl, source_id = get_by_id(row['Person'], Person, first=False)
if not ppl or not ppl.first(): continue
for person in ppl:
person.ranges = []
for r in rzs:
person.ranges.append(r)
print(" +++ ppl=%s, source_id=%s" % (ppl, source_id))
if not ppl or not ppl.first():
print(" --- No ppl, continue")
continue
with transaction.atomic():
person = ppl.first()
research_ranges = add_linked(person, MountainRange, row['MountainRange'])
ranges_people = [PeopleRange.objects.get_or_create(range_id=r.id, person_id=person.id)[0] for r in research_ranges]
person.peoplerange_set.set(ranges_people)
# for person in ppl:
# research_ranges = add_linked(person, MountainRange, row['MountainRange'])
# ranges_people = [RangesPeople.objects.get_or_create(range_id=r.id, person_id=person.id)[0] for r in research_ranges]
# person.rangespeople_set.set(ranges_people)
# ranges_people = RangesPeople
# for r in rzs:
# ranges_people.append(r)
# person.rangespeople_set.set(ranges_people)
person.save()
#print(" *** Saved %s => %s (%s)" % (person, ranges_people, len(ranges_people)))
count = count + 1
elif fmt['extension'] == 'geojson':

View File

@ -666,10 +666,18 @@ Involved scientist''')
return False
def index(self):
self.field_indexer = " ".join([
self.first_name, self.last_name, self.organisation, self.position, self.biography
])
return True
if self:
self.field_indexer = " ".join([
self.first_name if self and self.first_name else "",
self.last_name if self and self.last_name else "",
self.organisation if self and self.organisation else "",
self.position if self and self.position else "",
self.biography if self and self.biography else ""
] if self else "")
self.save()
return True
else:
return False
def fullname(self):
return " ".join([self.title if self.title else '',

View File

@ -176,11 +176,17 @@ def get_paginated(query_set, page, per_page):
for p in paginator.object_list:
filters['country'].append(p.country.short_name)
for r in p.peoplerange_set.all():
filters['range'].append(r.range.range_name)
if r.range and r.range.range_name:
filters['range'].append(r.range.range_name)
else:
print("r.range.range_name is None %s %s" % (r.range_id, r.person_id))
for r in p.fieldspeople_set.all():
filters['field'].append(r.field.name)
for r in p.taxapeople_set.all():
filters['taxon'].append(r.taxon.name)
if r and r.taxon and r.taxon.name:
filters['taxon'].append(r.taxon.name)
else:
print("r.taxon.name is None %s %s" % (r.range_id, r.taxon))
filters = {
'country': sorted(set(filters['country'])),
'range': sorted(set(filters['range'])),
@ -219,7 +225,7 @@ class SearchView(View):
if len(q_country) > 2:
query_set = query_set.filter(country__short_name__icontains=q_country.strip().lower())
if len(q_range) > 2:
ranges_people = PeopleRange.objects.filter(range__name__icontains=q_range.strip().lower())
ranges_people = PeopleRange.objects.filter(range__range_name__icontains=q_range.strip().lower())
r_people_ids = [rp.person_id for rp in ranges_people]
query_set = query_set.filter(id__in=r_people_ids)
if len(q_field) > 2: