def generateUniqueID(paper):
"""
Returns a simple string id that is the mashup of the title and authors
:param paper:
:return:
"""
author_bit = ''
if paper.extra_data.get('xref_author'):
authors = paper.extra_data['xref_author']
else:
try:
authors = parseBibAuthors(paper.authors)
except:
print("Failed to parse authors string", paper.authors)
authors = [{'given': '', 'family': ''}]
for author in authors:
if isinstance(author, str):
author_bit += author
else:
if author.get('family'):
author_bit += author.get('family', '_')[0] + author.get(
'given', '_')[0]
title_bit = normalizeTitle(paper.title)
title_bit = re.sub("\s+", "", title_bit)
full_id = title_bit + "_" + author_bit
full_id = full_id.lower()
return full_id
def exportBibToRIS(entries):
lines = []
for entry in entries:
authors = parseBibAuthors(entry['author'])
if entry['ENTRYTYPE'].lower() in type_mapping:
ris_type = type_mapping[entry['ENTRYTYPE'].lower()]
else:
ris_type = 'JOUR'
lines.append('TY - ' + ris_type)
for author in authors:
au_line = 'AU - %s, %s' % (author['family'], author['given'])
if author.get('middle'):
au_line += ' ' + author['middle']
lines.append(au_line)
# lines.append('PY - %s/%s/%s/' % (entry['year'], entry['month'], entry['day']))
lines.append('PY - %s' % (entry.get('year', ''), ))
pages = entry.get('pages')
if pages:
bits = pages.split('-')
lines.append('SP - ' + bits[0])
lines.append('EP - ' + bits[-1])
for eq in mapping:
if entry.get(eq[0]):
lines.append(str(eq[1]) + ' - ' + str(entry[eq[0]]))
lines.append('ER - ')
return '\n'.join(lines)
def computeAuthorDistance(paper1, paper2):
"""
Returns a measure of how much the authors of papers overlap
:param paper1:
:param paper2:
:return:
"""
if not paper1.bib.get('author') or not paper2.bib.get('author'):
return 1
authors1 = paper1.extra_data.get('x_authors',
parseBibAuthors(paper1.bib.get('author')))
authors2 = paper2.extra_data.get('x_authors',
parseBibAuthors(paper2.bib.get('author')))
score = 0
if len(authors1) >= len(authors2):
a_short = authors2
a_long = authors1
else:
a_short = authors1
a_long = authors2
max_score = 0
for index, author in enumerate(a_short):
factor = (len(a_long) - index)**2
if author['family'].lower() == a_long[index]['family'].lower():
score += factor
max_score += factor
if max_score == 0:
return 1
distance = 1 - (score / max_score)
return distance
def generateFilename(paper):
res = ''
authors = parseBibAuthors(paper.authors)
if not authors:
print(paper.authors)
print()
if authors and authors[0].get('family'):
res += authors[0]['family'] + ' '
if paper.year:
res += '(%s)' % paper.year
if len(res) > 0:
res += ' - '
res += paper.norm_title.title()
return res
def fixBibData(bib, index):
"""
Add mandatory missing fields to bibtex data
:param bib:
:param index:
:return:
"""
if "ENTRYTYPE" not in bib:
bib["ENTRYTYPE"] = "ARTICLE"
if "ID" not in bib:
authors = parseBibAuthors(bib["author"])
if not authors:
bib['ID'] = 'id' + str(random.randint(1000, 9000))
else:
bib["ID"] = authors[0]["family"]
bib['ID'] += str(bib.get("year",
"YEAR")) + bib["title"].split()[0].lower()
return bib