def authorlist(text):
"""Call the relevant formatter depending on the existence of affiliations.
Input can be in two different formats:
F. Lastname, F.M. Otherlastname
or
F. Lastname1, F.M. Otherlastname1,2
1 CERN
2 Otheraffiliation
There should always be only one affiliation per line and the affiliation
ids in author names should be separated with commas.
"""
if not text:
return ''
if not isinstance(text, six.text_type):
text = text.decode('utf-8')
# Do some pre-cleaning of the input string
text = text.replace('\r', '') # Input from the form contains unwanted \r's
text = text.replace(u'†', '')
text = text.replace(u'∗', '')
text = re.sub(r'(\n+)', r'\n', text)
text = replace_undesirable_characters(text)
text = wash_line(text)
# Assume that if there are numbers in author name, they are affilation ids.
# Also assume that if one author has an affiliation, everyone else has too.
if re.search(r'([a-zA-Z_-]+[\n]*\d+)', text):
return authorlist_with_affiliations(text)
return authorlist_without_affiliations(text)
def authorlist(text):
"""Call the relevant formatter depending on the existence of affiliations.
Input can be in two different formats:
F. Lastname, F.M. Otherlastname
or
F. Lastname1, F.M. Otherlastname1,2
1 CERN
2 Otheraffiliation
There should always be only one affiliation per line and the affiliation
ids in author names should be separated with commas.
"""
if not text:
return ''
if not isinstance(text, six.text_type):
text = text.decode('utf-8')
# Do some pre-cleaning of the input string
text = text.replace('\r', '') # Input from the form contains unwanted \r's
text = text.replace(u'†', '')
text = text.replace(u'∗', '')
text = re.sub(r'(\n+)', r'\n', text)
text = replace_undesirable_characters(text)
text = wash_line(text)
# Assume that if there are numbers in author name, they are affilation ids.
# Also assume that if one author has an affiliation, everyone else has too.
if re.search(r'([a-zA-Z_-]+[\n]*\d+)', text):
return authorlist_with_affiliations(text)
return authorlist_without_affiliations(text)
def authorlist(text):
"""
Return an author-structure parsed from text
and optional additional information.
"""
builder = LiteratureBuilder()
text = replace_undesirable_characters(text)
result = create_authors(text)
if "authors" in result:
for fullname, author_affs in result["authors"]:
builder.add_author(
builder.make_author(fullname, raw_affiliations=author_affs)
)
result["authors"] = builder.record["authors"]
return result
def authorlist(text):
"""
Return an author-structure parsed from text
and optional additional information.
"""
from inspire_schemas.api import LiteratureBuilder
from refextract.documents.pdf import replace_undesirable_characters
from inspirehep.modules.tools.authorlist import create_authors
builder = LiteratureBuilder()
text = replace_undesirable_characters(text)
result = create_authors(text)
if 'authors' in result:
for fullname, author_affs in result['authors']:
builder.add_author(
builder.make_author(fullname, raw_affiliations=author_affs))
result['authors'] = builder.record['authors']
return result
def authorlist(text):
"""
Return an author-structure parsed from text
and optional additional information.
"""
from inspire_schemas.api import LiteratureBuilder
from refextract.documents.pdf import replace_undesirable_characters
from inspirehep.modules.tools.authorlist import create_authors
builder = LiteratureBuilder()
text = replace_undesirable_characters(text)
result = create_authors(text)
if 'authors' in result:
for fullname, author_affs in result['authors']:
builder.add_author(
builder.make_author(fullname, raw_affiliations=author_affs)
)
result['authors'] = builder.record['authors']
return result