def filter_bibentry(self, entry):
#
# entry is a pybtex.database.Entry object
#
for role in self.roles:
if role not in entry.persons:
continue
for k in range(len(entry.persons[role])):
p = entry.persons[role][k];
# de-latex the person first
pstr = unicode(p);
# BUG: FIXME: remove space after any macros
pstr = re.sub(r'(\\[a-zA-Z]+)\s+', r'\1{}', pstr); # replace "blah\macro blah" by "blah\macro{}blah"
if (self._names_to_utf8):
pstr = latex2text.latex2text(pstr)
p = Person(pstr)
if self._only_single_letter_firsts:
from pybtex.textutils import abbreviate
def getparts(p, x):
for part in p.get_part(x, False):
if len(part) == 1:
yield abbreviate(part)
else:
yield part
pnew = Person('', " ".join(getparts(p, 'first')), " ".join(getparts(p, 'middle')),
" ".join(p.prelast()),
" ".join(p.last()), " ".join(p.lineage()));
else:
pnew = Person('', " ".join(p.first(True)), " ".join(p.middle(True)), " ".join(p.prelast()),
" ".join(p.last()), " ".join(p.lineage()));
entry.persons[role][k] = pnew
#logger.debug("nameinitials: %r became %r" % (p, pnew));
return
def thefilter(x):
if (self.fix_swedish_a):
x = re.sub(r'\\AA\s+', r'\AA{}', x);
if (self.encode_utf8_to_latex):
x = latexencode.utf8tolatex(x, non_ascii_only=True);
if (self.encode_latex_to_utf8):
x = latex2text.latex2text(x);
return x
def delatex_for_xml(s):
s = unicode(s)
logger.longdebug('delatexing `%s\' [:100] ...', s[:100])
text = latex2text.latex2text(s, tolerant_parsing=True, keep_comments=True)
#logger.longdebug(' --> text is %r [:100]', text[:100])
xml = unicode_to_xml(text)
logger.longdebug(' --> xml is `%s\' [:100]', xml[:100])
return xml
def thefilter(x):
if (self.fix_space_after_escape):
x = do_fix_space_after_escape(x)
if (self.fix_swedish_a):
# OBSOLETE, but still accepted for backwards compatibility
x = re.sub(r'\\AA\s+', r'\AA{}', x);
x = re.sub(r'\\o\s+', r'\o{}', x);
if (self.encode_utf8_to_latex):
# Need non_ascii_only=True because we might have e.g. braces or other
# LaTeX code we want to preserve.
x = latexencode.utf8tolatex(x, non_ascii_only=True);
if (self.encode_latex_to_utf8):
x = latex2text.latex2text(x);
return x
def delatex(s):
# Fixed: bug in pybtex.
# ### FIXME: Where the hell are all the "\~"'s being replaced by "\ " ??
# s = s.replace(r'\ ', r'\~');
return latex2text.latex2text(unicode(s));
def delatex(s):
if (not isinstance(s, unicode)):
s = unicode(s.decode('utf-8'))
return latex2text.latex2text(s);
