def iterentries_from_text(text, encoding='utf-8'):
py2_decode = identity
if hasattr(text, 'read'):
text = text.read(-1)
if not isinstance(text, str):
text = text.decode(encoding)
for entrytype, (bibkey, fields) in LowLevelParser(text):
fields = {
py2_decode(name).lower():
whitespace_re.sub(' ', py2_decode(''.join(values)).strip())
for name, values in fields}
yield py2_decode(bibkey), (py2_decode(entrytype), fields)
def iterentries(filename, encoding=None):
encoding = encoding or 'utf8'
with memorymapped(filename) as source:
try:
for entrytype, (bibkey, fields) in BibTeXEntryIterator(source):
fields = {
name.decode(encoding).lower():
whitespace_re.sub(' ', ''.join(values).decode(encoding).strip())
for name, values in fields}
yield bibkey.decode(encoding), (entrytype.decode(encoding), fields)
except PybtexSyntaxError as e: # pragma: no cover
debug_pybtex(source, e)
def iterentries(filename, encoding=None):
encoding = encoding or 'utf8'
with memorymapped(filename) as source:
try:
for entrytype, (bibkey, fields) in BibTeXEntryIterator(source):
fields = {
name.decode(encoding).lower():
whitespace_re.sub(' ',
''.join(values).decode(encoding).strip())
for name, values in fields
}
yield bibkey.decode(encoding), (entrytype.decode(encoding),
fields)
except PybtexSyntaxError as e: # pragma: no cover
debug_pybtex(source, e)
def iterentries_from_text(text, encoding='utf-8'):
if PY2:
py2_decode = lambda text: text.decode(encoding)
else: # pragma: no cover
py2_decode = lambda text: text
if hasattr(text, 'read'):
text = text.read()
if not isinstance(text, text_type):
text = text.decode(encoding)
for entrytype, (bibkey, fields) in BibTeXEntryIterator(text):
fields = {
py2_decode(name).lower():
whitespace_re.sub(' ', py2_decode(''.join(values)).strip())
for name, values in fields}
yield py2_decode(bibkey), (py2_decode(entrytype), fields)
def iterentries(filename, encoding=None, use_pybtex=True):
if not use_pybtex: # legacy code path for conversion/comparison
if encoding not in (None, 'ascii'):
raise NotImplementedError
import _libmonster
with memorymapped(filename) as source:
for bibkey, entrytype, fields in _libmonster.pitems(source):
yield bibkey, (entrytype, fields)
elif encoding is None:
raise NotImplementedError
else:
with memorymapped(filename) as source:
try:
for entrytype, (bibkey, fields) in BibTeXEntryIterator(source):
fields = {name.decode(encoding).lower():
whitespace_re.sub(' ', ''.join(values).decode(encoding).strip())
for name, values in fields}
yield bibkey.decode(encoding), (entrytype.decode(encoding), fields)
except PybtexSyntaxError as e:
debug_pybtex(source, e)
