def test_file_empty():
f = File()
assert isinstance(f, File)
assert f.title is None
assert f.href is None
assert f.category is None
assert f.description is None
def test_get_mapped_value(key, multilingual, result):
file_ = File('Test', '/api/attachments/1', 'main')
document = Document(id='test', title='Test', category='main', doctype='decree', files=[file_],
enactment_date=datetime.date.today(), subtype='Liestal', authority='Office')
source = OEREBlexSource(host='http://oereblex.example.com', language='de', canton='BL',
mapping={'municipality': 'subtype'})
assert source._get_mapped_value(document, key, multilingual) == result
def test_file():
f = File(description='File title',
href='http://my.link.to/file',
category='test',
title='test.pdf')
assert isinstance(f, File)
assert f.description == 'File title'
assert f.href == 'http://my.link.to/file'
assert f.category == 'test'
assert f.title == 'test.pdf'
def documents():
return [
Document(
id='1',
title='Document with file',
category='main',
doctype='decree',
files=[File(description='Test file', title='test.pdf',
href='http://www.example.com/test.pdf', category='main')],
enactment_date=datetime.date(2017, 1, 15)
)
]
def document_archived():
return [
Document(
id='1',
title='Archived document',
category='main',
doctype='decree',
files=[File(description='Test file', title='test.pdf',
href='http://www.example.com/test.pdf', category='main')],
enactment_date=datetime.date(2017, 1, 15),
abrogation_date=datetime.date(2019, 1, 1)
)
]
def test_get_document_records(i, document):
language = 'de'
source = OEREBlexSource(host='http://oereblex.example.com',
language='de',
canton='BL')
references = [
Document(id='ref',
title='Reference',
category='related',
doctype='edict',
authority='Office',
files=[File('Reference file', '/api/attachments/4', 'main')],
enactment_date=datetime.date.today())
]
if i == 3:
with pytest.raises(TypeError):
source._get_document_records(document, language, references)
elif i == 4:
assert source._get_document_records(document, language,
references) == []
else:
records = source._get_document_records(document, language, references)
assert len(records) == i
for idx, record in enumerate(records):
if i == 1:
assert isinstance(record, DocumentRecord)
elif i == 2:
assert isinstance(record, LegalProvisionRecord)
assert record.title == {'de': 'Document {0}'.format(i)}
assert record.published_from == datetime.date.today()
assert record.canton == 'BL'
assert record.text_at_web == {
'de': '/api/attachments/{fid}'.format(fid=i + idx)
}
assert len(record.references) == 1
reference = record.references[0]
assert isinstance(reference, DocumentRecord)
assert reference.title == {'de': 'Reference'}
assert reference.canton == 'BL'
assert reference.text_at_web == {'de': '/api/attachments/4'}
def test_document():
date = datetime.date.today()
d = Document(id='1',
title='Test',
category='test',
doctype='testdoc',
files=[
File('TestCategory', 'http://my.link.to/file',
'Test Title', 'test.pdf')
],
enactment_date=date,
federal_level='testlevel',
authority='Authority',
authority_url='http://my.link.to/authority',
type='testtype',
subtype='testsubtype',
decree_date=date,
instance='INST',
number='123',
abbreviation='abbr',
abrogation_date=date,
cycle='cycle')
assert isinstance(d, Document)
assert d.id == '1'
assert d.title == 'Test'
assert d.category == 'test'
assert d.doctype == 'testdoc'
assert len(d.files) == 1 and isinstance(d.files[0], File)
assert d.enactment_date == date
assert d.federal_level == 'testlevel'
assert d.authority == 'Authority'
assert d.authority_url == 'http://my.link.to/authority'
assert d.type == 'testtype'
assert d.subtype == 'testsubtype'
assert d.decree_date == date
assert d.instance == 'INST'
assert d.number == '123'
assert d.abbreviation == 'abbr'
assert d.abrogation_date == date
assert d.cycle == 'cycle'
source = OEREBlexSource(host='http://oereblex.example.com',
language='de',
canton='BL',
mapping={'municipality': 'subtype'})
assert source._get_mapped_value(document, key, language=language) == result
@pytest.mark.parametrize(
'i,document',
[(1,
Document(id='doc1',
title='Document 1',
category='main',
doctype='edict',
authority='Office',
files=[File(href='/api/attachments/1', category='main')],
enactment_date=datetime.date.today(),
index=1)),
(2,
Document(id='doc2',
title='Document 2',
category='main',
doctype='decree',
authority='Office',
files=[
File(href='/api/attachments/2', category='main'),
File(href='/api/attachments/3', category='additional')
],
enactment_date=datetime.date.today(),
index=2)),
(3,
def from_string(self, xml):
"""Parses XML into internal structure.
The specified XML string is gets validated against the geoLink XSD on parsing.
Args:
xml (str or bytes): The XML to be parsed.
Returns:
list[geolink_formatter.entity.Document]: A list containing the parsed document elements.
Raises:
lxml.etree.XMLSyntaxError: Raised on failed validation.
"""
root = self._parse_xml(xml)
documents = list()
for document_el in root.iter('document'):
doc_id = document_el.attrib.get('id')
doctype = document_el.attrib.get('doctype')
# Mangle doc_id for notices. While IDs are unique between decrees
# and edicts, this is not the case when adding notices to the mix.
if doctype == 'notice':
doc_id += doctype
if doc_id and doc_id not in [doc.id for doc in documents]:
files = list()
for file_el in document_el.iter('file'):
href = file_el.attrib.get('href')
if self.host_url and not href.startswith(u'http://') and not href.startswith(u'https://'):
href = u'{host}{href}'.format(host=self.host_url, href=href)
files.append(File(
title=file_el.attrib.get('title'),
description=file_el.attrib.get('description'),
href=href,
category=file_el.attrib.get('category')
))
enactment_date = document_el.attrib.get('enactment_date')
if enactment_date:
enactment_date = datetime.datetime.strptime(enactment_date, self._date_format).date()
decree_date = document_el.attrib.get('decree_date')
if decree_date:
decree_date = datetime.datetime.strptime(decree_date, self._date_format).date()
abrogation_date = document_el.attrib.get('abrogation_date')
if abrogation_date:
abrogation_date = datetime.datetime.strptime(abrogation_date, self._date_format).date()
documents.append(Document(
files=files,
id=doc_id,
category=document_el.attrib.get('category'),
doctype=document_el.attrib.get('doctype'),
federal_level=document_el.attrib.get('federal_level'),
authority=document_el.attrib.get('authority'),
authority_url=document_el.attrib.get('authority_url'),
title=document_el.attrib.get('title'),
number=document_el.attrib.get('number'),
abbreviation=document_el.attrib.get('abbreviation'),
instance=document_el.attrib.get('instance'),
type=document_el.attrib.get('type'),
subtype=document_el.attrib.get('subtype'),
decree_date=decree_date,
enactment_date=enactment_date,
abrogation_date=abrogation_date,
cycle=document_el.attrib.get('cycle')
))
return documents
file_ = File('Test', '/api/attachments/1', 'main')
document = Document(id='test', title='Test', category='main', doctype='decree', files=[file_],
enactment_date=datetime.date.today(), subtype='Liestal', authority='Office')
source = OEREBlexSource(host='http://oereblex.example.com', language='de', canton='BL',
mapping={'municipality': 'subtype'})
assert source._get_mapped_value(document, key, multilingual) == result
@pytest.mark.parametrize('i,document', [
(1, Document(
id='doc1',
title='Document 1',
category='main',
doctype='edict',
authority='Office',
files=[File('File 1', '/api/attachments/1', 'main')],
enactment_date=datetime.date.today()
)),
(2, Document(
id='doc2',
title='Document 2',
category='main',
doctype='decree',
authority='Office',
files=[
File('File 2', '/api/attachments/2', 'main'),
File('File 3', '/api/attachments/3', 'additional')
],
enactment_date=datetime.date.today()
)),
(3, Document(
def test_get_document_title():
document = Document([], id='1', title='Test')
result = {'de': 'Test'}
assert OEREBlexSource._get_document_title(document, File(), 'de') == result