use bytes;
my $progname = $0; $progname =~ s@.*/@@g;
-my $version = q{ $Revision: 1.15 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
+my $version = q{ $Revision: 1.17 $ }; $version =~ s/^[^0-9]+([0-9.]+).*$/$1/;
my $verbose = 0;
my $http_proxy = undef;
"ocirc" => 'ô', "otilde" => 'õ', "ouml" => 'ö', "divide" => '÷',
"oslash" => 'ø', "ugrave" => 'ù', "uacute" => 'ú', "ucirc" => 'û',
"uuml" => 'ü', "yacute" => 'ý', "thorn" => 'þ', "yuml" => 'ÿ',
- "apos" => '\''
+ "apos" => '\'',
+
+ # HTML 4 entities that do not have 1:1 Latin1 mappings.
+ "bull" => "*", "hellip"=> "...", "prime" => "'", "Prime" => "\"",
+ "frasl" => "/", "trade" => "[tm]", "larr" => "<-", "rarr" => "->",
+ "harr" => "<->", "lArr" => "<=", "rArr" => "=>", "hArr" => "<=>",
+ "empty" => "Ø", "minus" => "-", "lowast"=> "*", "sim" => "~",
+ "cong" => "=~", "asymp" => "~", "ne" => "!=", "equiv" => "==",
+ "le" => "<=", "ge" => ">=", "lang" => "<", "rang" => ">",
+ "loz" => "<>", "OElig" => "OE", "oelig" => "oe", "Yuml" => "Y",
+ "circ" => "^", "tilde" => "~", "ensp" => " ", "emsp" => " ",
+ "thinsp"=> " ", "ndash" => "-", "mdash" => "-", "lsquo" => "`",
+ "rsquo" => "'", "sbquo" => "'", "ldquo" => "\"", "rdquo" => "\"",
+ "bdquo" => "\"", "lsaquo"=> "<", "rsaquo"=> ">",
);
# Maps certain UTF8 characters (2 or 3 bytes) to the corresponding
s/[ \t]+$//gm; # lose whitespace at end of line again
}
+ s/^\n+//gs;
+
y/A-Za-z/N-ZA-Mn-za-m/ if ($nyarlathotep_p);
print STDOUT $_;
}
$title = rss_field_to_html ($title || '');
$body1 = rss_field_to_html ($body1 || '');
+ $title = '' if ($body1 eq $title); # Identical in Twitter's atom feed.
+
reformat_html ("$title<P>$body1", 1);
print "\n";
}