def test_decode_latex():
name_with_latex = u'{\\AA}άλφα'
expected_value = u'Åάλφα'
assert decode_latex(name_with_latex) == expected_value
name_with_latex = '{\\AA}βήτα'
expected_value = u'Åβήτα'
assert decode_latex(name_with_latex) == expected_value
def test_decode_latex():
name_with_latex = u'{\\AA}άλφα'
expected_value = u'Åάλφα'
assert decode_latex(name_with_latex) == expected_value
name_with_latex = '{\\AA}βήτα'
expected_value = u'Åβήτα'
assert decode_latex(name_with_latex) == expected_value
def _author_list(obj, eng):
arxiv_id = get_arxiv_id(obj.data)
filename = secure_filename('{0}.tar.gz'.format(arxiv_id))
try:
tarball = obj.files[filename]
except KeyError:
obj.log.info(
'Skipping author list extraction, no tarball with name "%s" found'
% filename)
return
with TemporaryDirectory(prefix='author_list') as scratch_space, \
retrieve_uri(tarball.file.uri, outdir=scratch_space) as tarball_file:
try:
file_list = untar(tarball_file, scratch_space)
except InvalidTarball:
obj.log.info(
'Invalid tarball %s for arxiv_id %s',
tarball.file.uri,
arxiv_id,
)
return
obj.log.info('Extracted tarball to: {0}'.format(scratch_space))
xml_files_list = [
path for path in file_list if path.endswith('.xml')
]
obj.log.info('Found xmlfiles: {0}'.format(xml_files_list))
extracted_authors = []
for xml_file in xml_files_list:
with open(xml_file, 'r') as xml_file_fd:
xml_content = xml_file_fd.read()
match = REGEXP_AUTHLIST.findall(xml_content)
if match:
obj.log.info('Found a match for author extraction')
try:
authors_xml = convert(xml_content, stylesheet)
except XMLSyntaxError:
# Probably the %auto-ignore comment exists, so we skip the
# first line. See: inspirehep/inspire-next/issues/2195
authors_xml = convert(
xml_content.split('\n', 1)[1],
stylesheet,
)
extracted_authors.extend(
marcxml2record(authors_xml).get('authors', []))
if extracted_authors:
for author in extracted_authors:
author['full_name'] = decode_latex(author['full_name'])
obj.data['authors'] = extracted_authors
def _author_list(obj, eng):
arxiv_id = LiteratureReader(obj.data).arxiv_id
filename = secure_filename('{0}.tar.gz'.format(arxiv_id))
try:
tarball = obj.files[filename]
except KeyError:
obj.log.info(
'Skipping author list extraction, no tarball with name "%s" found' % filename
)
return
with TemporaryDirectory(prefix='author_list') as scratch_space, \
retrieve_uri(tarball.file.uri, outdir=scratch_space) as tarball_file:
try:
file_list = untar(tarball_file, scratch_space)
except InvalidTarball:
obj.log.info(
'Invalid tarball %s for arxiv_id %s',
tarball.file.uri,
arxiv_id,
)
return
obj.log.info('Extracted tarball to: {0}'.format(scratch_space))
xml_files_list = [path for path in file_list if path.endswith('.xml')]
obj.log.info('Found xmlfiles: {0}'.format(xml_files_list))
extracted_authors = []
for xml_file in xml_files_list:
with open(xml_file, 'r') as xml_file_fd:
xml_content = xml_file_fd.read()
match = REGEXP_AUTHLIST.findall(xml_content)
if match:
obj.log.info('Found a match for author extraction')
try:
authors_xml = convert(xml_content, stylesheet)
except XMLSyntaxError:
# Probably the %auto-ignore comment exists, so we skip the
# first line. See: inspirehep/inspire-next/issues/2195
authors_xml = convert(
xml_content.split('\n', 1)[1],
stylesheet,
)
extracted_authors.extend(marcxml2record(authors_xml).get('authors', []))
if extracted_authors:
for author in extracted_authors:
author['full_name'] = decode_latex(author['full_name'])
obj.data['authors'] = extracted_authors
def test_decode_latex_with_empty_string():
name_with_latex = ''
expected_value = ''
assert decode_latex(name_with_latex) == expected_value
def test_decode_latex_with_empty_string():
name_with_latex = ''
expected_value = ''
assert decode_latex(name_with_latex) == expected_value