Biblio-Document-Parser
view release on metacpan or search on metacpan
======================================================================
Known Bugs & Issues in current ParaTools release
======================================================================
See the docs for how to submit a bug/issue.
----------------------------------------------------------------------
Internationalisation
----------------------------------------------------------------------
- Need to add proper unicode support
----------------------------------------------------------------------
Parsing
----------------------------------------------------------------------
- Need to find a PDF-to-text tool that works properly on all PDF files.
lib/Biblio/Document/Parser/Brody.pm view on Meta::CPAN
# } elsif( $BIBL =~ /$RE_BOR/mi ) {
# warn "Skipping section ...\n" if $DEBUG;
# $BIBL = $';
# } else {
# last;
# }
}
for( my $i = 0; $i < @REFS; $i++ ) {
my $ref = $REFS[$i] or next;
# $REFS[$i] = "[" . ($i+1) . "] " . unicode_string($ref);
$REFS[$i] = "[" . ($i+1) . "] " . $ref;
}
return grep { defined($_) && length($_) } @REFS;
}
#my ($BIBL, $buffer);
#$BIBL = '';
#my $lc = 0;
lib/Biblio/Document/Parser/Brody.pm view on Meta::CPAN
sub header_to_regexp {
my $header = shift;
$header =~ s/([\\\|\(\)\[\]\.\*\+\?\{\}])/\\$1/g;
$header =~ s/\s+/\\s+/g;
$header =~ s/\d+/\\d+/g;
return $header;
return q/(?:\n\s*){3}(/.$header.q/)(?:\n\s*){2}/;
}
#sub unicode_string {
# $_ = shift();
# s/[\x00-\x08\x0b-\x0c\x0e-\x1f]//sg;
# s/([\x80-\xff])/sprintf("&#x%04x;",ord($1))/seg;
# return $_;
#}
1;
__END__
( run in 0.330 second using v1.01-cache-2.11-cpan-88abd93f124 )