s/\xC3\x83\xC2\x83\xC3\x85\xC2\xB8/ß/gs && $stat->{'ss'}++;
s/$junk\xC3\x82\xC2\x8D/č/gs && $stat->{'cv'}++;
+s/\xC3\x84\xC2\x8D/č/gs && $stat->{'cv 84'}++;
+
s/$junk\xC2\x80\xC2\xA1/ć/gs && $stat->{"c"}++;
+# #Buri\xC3\x84\xC2\x87.pdf
+s/\xC3\x84\xC2\x87/ć/gs && $stat->{'c C384C287'}++;
+
s/$junk\xC3\x82\xC2\xA1/š/gs && $stat->{'s'}++;
+#Ma\xC3\x85\xC2\xA1a
+s/\xC3\x85\xC2\xA1/š/gs && $stat->{'s C385C2'}++;
s/$junk\xC2\x80\xC4\xA1/š/gs && $stat->{'s C4'}++;
+
s/$junk\xC3\x82\xC2\xBE/ž/gs && $stat->{'z'}++;
s/$junk\xC2\x80\xC2\x98/đ/gs && $stat->{'d'}++;
s/$junk\xC2\x80\xC2\x9C/-/gs && $stat->{'--'}++;
s/$junk\xC2\x9D/-/gs && $stat->{'-- ?'}++;
+s/$junk\xC3\x82\xC2\xA2/- /gs && $stat->{'dot'}++;
+
+
my $e = $_;
- if ( $e =~ m/([\xC0-\xC4][\x80-\xff]{4,8})/s ) {
+ if ( $e =~ m/([\xC0-\xC4][\x80-\xff]{3,99})/s ) {
warn "XXX ", dump($e), "\n$e\n";
}
print $e;