def is_valid_bibtex(reference):
"""
Use pybtex to validate that a reference is in proper BibTeX format
Args:
reference: A String reference in BibTeX format.
Returns:
Boolean indicating if reference is valid bibtex.
"""
# str is necessary since pybtex seems to have an issue with unicode. The
# filter expression removes all non-ASCII characters.
sio = cStringIO.StringIO(remove_non_ascii(reference))
parser = bibtex.Parser()
bib_data = parser.parse_stream(sio)
return len(bib_data.entries) > 0
def is_valid_bibtex(reference):
"""
Use pybtex to validate that a reference is in proper BibTeX format
Args:
reference:
A String reference in BibTeX format
Returns:
Boolean indicating if reference is valid bibtex.
"""
# str is necessary since pybtex seems to have an issue with unicode. The
# filter expression removes all non-ASCII characters.
sio = cStringIO.StringIO(remove_non_ascii(reference))
parser = bibtex.Parser()
bib_data = parser.parse_stream(sio)
return len(bib_data.entries) > 0
def _clean_cif(s):
"""
Removes non-ASCII and some unsupported _cgraph fields from the cif
string
"""
clean = []
lines = s.split("\n")
skip = False
while len(lines) > 0:
l = lines.pop(0)
if skip:
if l.strip().startswith("_") or l.strip() == "loop_":
skip = False
else:
continue
if l.strip().startswith("_cgraph"):
skip = True
elif not l.strip().startswith("_eof"):
clean.append(remove_non_ascii(l))
return "\n".join(clean)
def _clean_cif(s):
"""
Removes non-ASCII and some unsupported _cgraph fields from the cif
string
"""
clean = []
lines = s.split("\n")
skip = False
while len(lines) > 0:
l = lines.pop(0)
if skip:
if l.strip().startswith("_") or l.strip() == "loop_":
skip = False
else:
continue
if l.strip().startswith("_cgraph"):
skip = True
elif not l.strip().startswith("_eof"):
clean.append(remove_non_ascii(l))
return "\n".join(clean)
def test_remove_non_ascii(self):
s = "".join(chr(random.randint(0, 127)) for i in xrange(10))
s += "".join(chr(random.randint(128, 150)) for i in xrange(10))
clean = remove_non_ascii(s)
self.assertEqual(len(clean), 10)
def test_remove_non_ascii(self):
s = "".join(chr(random.randint(0, 127)) for i in xrange(10))
s += "".join(chr(random.randint(128, 150)) for i in xrange(10))
clean = remove_non_ascii(s)
self.assertEqual(len(clean), 10)
