def test_parse_pubmed_caption():
"""
Test parsing captions and figure ID from a PubMed XML file
"""
captions = pp.parse_pubmed_caption(
os.path.join("data", "pone.0046493.nxml"))
assert isinstance(captions, list)
assert isinstance(captions[0], dict)
assert (len(captions) == 4
), "Expected number of figures/captions to have a length of 4"
def merge(self):
print('PubMed path:', self.pubmed_path)
with open(self.output_filename, mode='w', newline='\n') as ofile:
# PubMed
for filename in glob.glob(os.path.join(self.pubmed_path,
'**/*.xml'),
recursive=self.recursive):
print('file:', filename)
dicts_out = pmp.parse_medline_xml(filename)
self.write_dicts(dicts_out, 'abstract', ofile, 'title',
'pubmed_abstract')
# PMC
for filename in glob.glob(os.path.join(self.pubmed_path,
'**/*.nxml'),
recursive=self.recursive):
print('file:', filename)
# OA abstract
try:
dicts_out = [pmp.parse_pubmed_xml(filename)]
self.write_dicts(dicts_out, 'abstract', ofile,
'full_title', 'pmc_oa_abstract')
except:
pass
# OA image caption
try:
dicts_out = pmp.parse_pubmed_caption(filename)
self.write_dicts(dicts_out, 'fig_caption', ofile,
'fig_label', 'pmc_oa_image-caption')
except:
pass
# OA Paragraph
try:
dicts_out = pmp.parse_pubmed_paragraph(filename,
all_paragraph=True)
self.write_dicts(dicts_out, 'text', ofile, 'reference_ids',
'pmc_oa_paragraph')
except:
pass
def parse_oa_xml(xml_file, output_file, mode):
"""Import pubmed open access XML file into prophet database."""
# For open access
import pubmed_parser as pp
if mode == 'paper':
dicts_out = pp.parse_pubmed_xml(xml_file)
elif mode == 'paragraphs':
dicts_out = pp.parse_pubmed_paragraph(xml_file, all_paragraph=True)
elif mode == 'references':
dicts_out = pp.parse_pubmed_references(xml_file)
elif mode == 'tables':
dicts_out = pp.parse_pubmed_table(xml_file, return_xml=False)
elif mode == 'figures':
dicts_out = pp.parse_pubmed_caption(xml_file)
with open(output_file, 'w') as fp:
json.dump(dicts_out, fp, cls=DateEncoder)
def extract(self, tar_buffer):
tar_buffer.seek(0)
tar = tarfile.open(fileobj=tar_buffer)
members = tar.getmembers()
imgs_files = re.compile(r'.*(\.gif|jpe?g|tiff?|png|webp|bmp)$')
text_file = re.compile(r'.*(\.nxml)$')
imgs = {}
for mem in members:
if imgs_files.match(mem.name):
img_ref = os.path.basename(mem.name)
img_ref = os.path.splitext(img_ref)[0]
imbuffer = tar.extractfile(mem).read()
imgs[img_ref] = imbuffer
if text_file.match(mem.name):
text = tar.extractfile(mem.name).read().decode('utf-8')
caption = pp.parse_pubmed_caption(text)
return imgs, caption