def to_cldf(self, dest, mdname='cldf-metadata.json'):
"""
Write the data from the db to a CLDF dataset according to the metadata in `self.dataset`.
:param dest:
:param mdname:
:return: path of the metadata file
"""
dest = Path(dest)
if not dest.exists():
dest.mkdir()
data = self.read()
if data[self.source_table_name]:
sources = Sources()
for src in data[self.source_table_name]:
sources.add(Source(
src['genre'],
src['id'],
**{k: v for k, v in src.items() if k not in ['id', 'genre']}))
sources.write(dest / self.dataset.properties.get('dc:source', 'sources.bib'))
for table_type, items in data.items():
try:
table = self.dataset[table_type]
table.common_props['dc:extent'] = table.write(
[self.retranslate(table, item) for item in items],
base=dest)
except KeyError:
assert table_type == self.source_table_name, table_type
return self.dataset.write_metadata(dest / 'cldf-metadata.json')
def test_Sources_with_None_values(self):
from pycldf.sources import Sources, Source
src = Sources()
src.add(Source('book', 'huber2005', title=None))
bib = self.tmp_path('test.bib')
src.write(bib.name, bib.parent)
def to_cldf(self, dest, mdname='cldf-metadata.json', coordinate_precision=4):
"""
Write the data from the db to a CLDF dataset according to the metadata in `self.dataset`.
:param dest:
:param mdname:
:return: path of the metadata file
"""
dest = pathlib.Path(dest)
if not dest.exists():
dest.mkdir()
data = self.read()
if data[self.source_table_name]:
sources = Sources()
for src in data[self.source_table_name]:
sources.add(Source(
src['genre'],
src['id'],
**{k: v for k, v in src.items() if k not in ['id', 'genre']}))
sources.write(dest / self.dataset.properties.get('dc:source', 'sources.bib'))
for table_type, items in data.items():
try:
table = self.dataset[table_type]
items = [
self.round_geocoordinates(item, precision=coordinate_precision)
for item in items]
table.common_props['dc:extent'] = table.write(
[self.retranslate(table, item) for item in items],
base=dest)
except KeyError:
assert table_type == self.source_table_name, table_type
return self.dataset.write_metadata(dest / mdname)
def test_field_order(tmpdir):
srcs = Sources()
src = Source('misc', 'x') # src is an OrderedDict and we add title *after* year.
src['year'] = '2018'
src['title'] = 'The Title'
srcs.add(src)
bib = tmpdir / 'test.bib'
srcs.write(str(bib))
res = bib.read_text(encoding='utf8')
# Still, title should be printed in the BibTeX before year:
assert res.index('title =') < res.index('year =')
def test_Source_expand_refs():
sources = Sources()
src = Source(
'book', 'Meier2005', author='Hans Meier', year='2005', title='The Book')
assert 'Meier2005' in repr(src)
sources.add(src)
bib = sources._bibdata.to_string(bib_format='bibtex')
assert len(bib.split('author')) == 2
assert len(list(sources.expand_refs('Meier2005'))) == 1
bib = sources._bibdata.to_string(bib_format='bibtex')
assert len(bib.split('author')) == 2
assert len(list(sources.expand_refs('12345'))) == 1
def test_Source_expand_refs():
sources = Sources()
src = Source(
'book', 'Meier2005', author='Hans Meier', year='2005', title='The Book')
assert 'Meier2005' in repr(src)
sources.add(src)
bib = sources._bibdata.to_string(bib_format='bibtex')
assert len(bib.split('author')) == 2
assert len(list(sources.expand_refs('Meier2005'))) == 1
bib = sources._bibdata.to_string(bib_format='bibtex')
assert len(bib.split('author')) == 2
assert len(list(sources.expand_refs('12345'))) == 1
def test_Source_expand_refs(self):
from pycldf.sources import Sources, Source
sources = Sources()
src = Source(
'book', 'Meier2005', author='Hans Meier', year='2005', title='The Book')
self.assertIn('Meier2005', repr(src))
sources.add(src)
bib = sources._bibdata.to_string(bib_format='bibtex')
self.assertEqual(len(bib.split('author')), 2)
self.assertEqual(len(list(sources.expand_refs('Meier2005'))), 1)
bib = sources._bibdata.to_string(bib_format='bibtex')
self.assertEqual(len(bib.split('author')), 2)
def test_Sources(tmpdir):
src = Sources()
src.add(BIB, Source(
'book', 'huber2005', author='Herrmann Huber', year='2005', title='y'))
for entry in src:
assert entry.genre == 'book'
break
assert len(list(src.items())) == 3
assert len(list(src.keys())) == 3
refs = ['huber2005[1-6]', 'Obrazy', 'Elegie[34]']
assert src.format_refs(*list(src.expand_refs(refs))) == refs
assert '%s' % src['huber2005'] == 'Huber, Herrmann. 2005. y.'
with pytest.raises(ValueError):
src.add(5)
with pytest.raises(ValueError):
src.add('@misc{a.b,\n author="a.b"\n}')
with pytest.raises(ValueError):
_ = src['unknown']
assert _ # pragma: no cover
with pytest.raises(ValueError):
src.parse('a[x')
with pytest.raises(ValueError):
src.parse('[x]')
with pytest.raises(ValueError):
src.validate(['x'])
bib = str(tmpdir / 'test.bib')
src.write(bib)
src2 = Sources()
src2.read(bib)
src2.write(bib, ids=['huber2005'])
src = Sources.from_file(bib)
assert len(src) == 1
def test_Sources(tmpdir):
src = Sources()
src.add(BIB, Source(
'book', 'huber2005', author='Herrmann Huber', year='2005', title='y'))
for entry in src:
assert entry.genre == 'book'
break
assert len(list(src.items())) == 3
assert len(list(src.keys())) == 3
refs = ['huber2005[1-6]', 'Obrazy', 'Elegie[34]']
assert src.format_refs(*list(src.expand_refs(refs))) == refs
assert '%s' % src['huber2005'] == 'Huber, Herrmann. 2005. y.'
with pytest.raises(ValueError):
src.add(5)
with pytest.raises(ValueError):
src.add('@misc{a.b,\n author="a.b"\n}')
with pytest.raises(ValueError):
_ = src['unknown']
assert _ # pragma: no cover
with pytest.raises(ValueError):
src.parse('a[x')
with pytest.raises(ValueError):
src.parse('[x]')
with pytest.raises(ValueError):
src.validate(['x'])
bib = str(tmpdir / 'test.bib')
src.write(bib)
src2 = Sources()
src2.read(bib)
src2.write(bib, ids=['huber2005'])
src = Sources.from_file(bib)
assert len(src) == 1
def test_Sources(self):
from pycldf.sources import Sources, Source
src = Sources()
src.add(BIB, Source(
'book', 'huber2005', author='Herrmann Huber', year='2005', title='y'))
self.assertEqual(len(list(src.items())), 3)
self.assertEqual(len(list(src.keys())), 3)
refs = 'huber2005[1-6];Obrazy;Elegie[34]'
self.assertEqual(src.format_refs(*list(src.expand_refs(refs))), refs)
self.assertEqual('%s' % src['huber2005'], 'Huber, Herrmann. 2005. y.')
with self.assertRaises(ValueError):
src.add(5)
with self.assertRaises(ValueError):
src.add('@misc{a.b,\n author="a.b"\n}')
bib = self.tmp_path('test.bib')
src.write(bib.name, bib.parent)
src2 = Sources()
src2.read(bib.name, bib.parent)
bib = self.tmp_path('test.bib')
src2.write(bib.name, bib.parent, ids=['huber2005'])
src = Sources()
src.read(bib.name, bib.parent)
self.assertEqual(len(src), 1)
def test_Sources_roundtrip_latex(tmpdir, bibtex, expected):
src = Sources()
src.add(bibtex)
bib = tmpdir / 'test.bib'
src.write(str(bib))
assert expected in bib.read_text('utf8')
def test_Sources_with_None_values(tmpdir):
src = Sources()
src.add(Source('book', 'huber2005', title=None))
bib = tmpdir / 'test.bib'
src.write(str(bib))
def test_Sources_roundtrip_latex(tmpdir, bibtex, expected):
src = Sources()
src.add(bibtex)
bib = tmpdir / 'test.bib'
src.write(str(bib))
assert expected in bib.read_text('utf8')
def test_Sources_with_None_values(tmpdir):
src = Sources()
src.add(Source('book', 'huber2005', title=None))
bib = tmpdir / 'test.bib'
src.write(str(bib))