def test_find_simple(self):
za = Country.objects.get(pk=1)
user1 = User.objects.get(pk=1)
settings.INDIGO['WORK_PROPERTIES'] = {
'za': {
'cap': 'Chapter (cap)',
}
}
work = Work(
frbr_uri='/akn/za/act/2002/5',
title='Act 5 of 2002',
country=za,
created_by_user=user1,
)
work.properties['cap'] = '12'
work.updated_by_user = user1
work.save()
document = Document(
document_xml=document_fixture(
xml="""
<section eId="sec_1">
<num>1.</num>
<heading>Tester</heading>
<paragraph eId="sec_1.paragraph-0">
<content>
<p>Something to do with Cap. 12.</p>
</content>
</paragraph>
</section>"""
),
language=self.eng,
work=work)
expected = Document(
document_xml=document_fixture(
xml="""
<section eId="sec_1">
<num>1.</num>
<heading>Tester</heading>
<paragraph eId="sec_1.paragraph-0">
<content>
<p>Something to do with <ref href="/akn/za/act/2002/5">Cap. 12</ref>.</p>
</content>
</paragraph>
</section>"""
),
language=self.eng,
work=work)
self.finder.find_references_in_document(document)
root = etree.fromstring(expected.content)
expected.content = etree.tostring(root, encoding='utf-8').decode('utf-8')
self.assertEqual(expected.content, document.content)
def get_works(self, table):
works = []
# clean up headers
headers = [h.split(' ')[0].lower() for h in table[0]]
# transform rows into list of dicts for easy access
rows = [{header: row[i]
for i, header in enumerate(headers) if header}
for row in table[1:]]
for idx, row in enumerate(rows):
# ignore if it's blank or explicitly marked 'ignore' in the 'ignore' column
if not row.get('ignore') and [
val for val in row.itervalues() if val
]:
info = {
'row': idx + 2,
}
works.append(info)
try:
frbr_uri = self.get_frbr_uri(self.country, self.locality,
row)
except ValueError as e:
info['status'] = 'error'
info['error_message'] = e.message
continue
try:
work = Work.objects.get(frbr_uri=frbr_uri)
info['work'] = work
info['status'] = 'duplicate'
# TODO one day: also mark first work as duplicate if user is trying to import two of the same (currently only the second one will be)
except Work.DoesNotExist:
work = Work()
work.frbr_uri = frbr_uri
work.title = row.get('title')
work.country = self.country
work.locality = self.locality
work.publication_name = row.get('publication_name')
work.publication_number = row.get('publication_number')
work.created_by_user = self.request.user
work.updated_by_user = self.request.user
try:
work.publication_date = self.make_date(
row.get('publication_date'), 'publication_date')
work.commencement_date = self.make_date(
row.get('commencement_date'), 'commencement_date')
work.assent_date = self.make_date(
row.get('assent_date'), 'assent_date')
work.full_clean()
work.save()
# signals
work_changed.send(sender=work.__class__,
work=work,
request=self.request)
info['status'] = 'success'
info['work'] = work
except ValidationError as e:
info['status'] = 'error'
if hasattr(e, 'message_dict'):
info['error_message'] = ' '.join([
'%s: %s' % (f, '; '.join(errs))
for f, errs in e.message_dict.items()
])
else:
info['error_message'] = e.message
return works
def get_works(self, table, form):
works = []
# clean up headers
headers = [h.split(' ')[0].lower() for h in table[0]]
# transform rows into list of dicts for easy access
rows = [
{header: row[i] for i, header in enumerate(headers) if header}
for row in table[1:]
]
for idx, row in enumerate(rows):
# ignore if it's blank or explicitly marked 'ignore' in the 'ignore' column
if not row.get('ignore') and [val for val in row.itervalues() if val]:
info = {
'row': idx + 2,
}
works.append(info)
try:
frbr_uri = self.get_frbr_uri(self.country, self.locality, row)
except ValueError as e:
info['status'] = 'error'
info['error_message'] = e.message
continue
try:
work = Work.objects.get(frbr_uri=frbr_uri)
info['work'] = work
info['status'] = 'duplicate'
if row.get('amends'):
info['amends'] = row.get('amends')
if row.get('commencement_date'):
info['commencement_date'] = row.get('commencement_date')
except Work.DoesNotExist:
work = Work()
work.frbr_uri = frbr_uri
work.title = self.strip_title_string(row.get('title'))
work.country = self.country
work.locality = self.locality
work.publication_name = row.get('publication_name')
work.publication_number = row.get('publication_number')
work.created_by_user = self.request.user
work.updated_by_user = self.request.user
work.stub = not row.get('primary')
try:
work.publication_date = self.make_date(row.get('publication_date'), 'publication_date')
work.commencement_date = self.make_date(row.get('commencement_date'), 'commencement_date')
work.assent_date = self.make_date(row.get('assent_date'), 'assent_date')
work.full_clean()
work.save()
# link publication document
params = {
'date': row.get('publication_date'),
'number': work.publication_number,
'publication': work.publication_name,
'country': self.country.place_code,
'locality': self.locality.code if self.locality else None,
}
self.get_publication_document(params, work, form)
# signals
work_changed.send(sender=work.__class__, work=work, request=self.request)
info['status'] = 'success'
info['work'] = work
# TODO: neaten this up
if row.get('commenced_by'):
info['commenced_by'] = row.get('commenced_by')
if row.get('amends'):
info['amends'] = row.get('amends')
if row.get('repealed_by'):
info['repealed_by'] = row.get('repealed_by')
if row.get('with_effect_from'):
info['with_effect_from'] = row.get('with_effect_from')
if row.get('parent_work'):
info['parent_work'] = row.get('parent_work')
except ValidationError as e:
info['status'] = 'error'
if hasattr(e, 'message_dict'):
info['error_message'] = ' '.join(
['%s: %s' % (f, '; '.join(errs)) for f, errs in e.message_dict.items()]
)
else:
info['error_message'] = e.message
return works