use Encode qw(find_encoding);
use PublicInbox::MID qw/mid_clean mid_escape/;
use base qw/Exporter/;
-our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename/;
-
-# for user-generated content (UGC) which may have excessively long lines
-# and screw up rendering on some browsers. This is the only CSS style
-# feature we use.
-use constant STYLE => '<style>pre{white-space:pre-wrap}</style>';
-
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape
+ to_attr from_attr/;
my $enc_ascii = find_encoding('us-ascii');
+# safe-ish acceptable filename pattern for portability
+our $FN = '[a-zA-Z0-9][a-zA-Z0-9_\-\.]+[a-zA-Z0-9]'; # needs \z anchor
+
sub new {
my ($class, $raw, $href) = @_;
$class->new($raw);
}
+# some of these overrides are standard C escapes so they're
+# easy-to-understand when rendered.
+my %escape_sequence = (
+ "\x00" => '\\0', # NUL
+ "\x07" => '\\a', # bell
+ "\x08" => '\\b', # backspace
+ "\x09" => "\t", # obvious to show as-is
+ "\x0a" => "\n", # obvious to show as-is
+ "\x0b" => '\\v', # vertical tab
+ "\x0c" => '\\f', # form feed
+ "\x0d" => '\\r', # carriage ret (not preceding \n)
+ "\x1b" => '^[', # ASCII escape (mutt seems to escape this way)
+ "\x7f" => '\\x7f', # DEL
+);
+
my %xhtml_map = (
'"' => '"',
'&' => '&',
);
$xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
-# some of these overrides are standard C escapes so they're
-# easy-to-understand when rendered.
-$xhtml_map{"\x00"} = '\\0'; # NUL
-$xhtml_map{"\x07"} = '\\a'; # bell
-$xhtml_map{"\x08"} = '\\b'; # backspace
-$xhtml_map{"\x09"} = "\t"; # obvious to show as-is
-$xhtml_map{"\x0a"} = "\n"; # obvious to show as-is
-$xhtml_map{"\x0b"} = '\\v'; # vertical tab
-$xhtml_map{"\x0c"} = '\\f'; # form feed
-$xhtml_map{"\x0d"} = '\\r'; # carriage ret (not preceding \n)
-$xhtml_map{"\x1b"} = '^['; # ASCII escape (mutt seems to escape this way)
-$xhtml_map{"\x7f"} = '\\x7f'; # DEL
+%xhtml_map = (%xhtml_map, %escape_sequence);
+
+sub src_escape ($) {
+ $_[0] =~ s/\r\n/\n/sg;
+ $_[0] =~ s/([\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
+ $_[0] = $enc_ascii->encode($_[0], Encode::HTMLCREF);
+}
sub ascii_html {
my ($s) = @_;
$s
}
+# convert a filename (or any string) to HTML attribute
+
+my %ESCAPES = map { chr($_) => sprintf('::%02x', $_) } (0..255);
+$ESCAPES{'/'} = ':'; # common
+
+sub to_attr ($) {
+ my ($str) = @_;
+
+ # git would never do this to us:
+ return if index($str, '//') >= 0;
+
+ my $first = '';
+ if ($str =~ s/\A([^A-Ya-z])//ms) { # start with a letter
+ $first = sprintf('Z%02x', ord($1));
+ }
+ $str =~ s/([^A-Za-z0-9_\.\-])/$ESCAPES{$1}/egms;
+ $first . $str;
+}
+
+# reverse the result of to_attr
+sub from_attr ($) {
+ my ($str) = @_;
+ my $first = '';
+ if ($str =~ s/\AZ([a-f0-9]{2})//ms) {
+ $first = chr(hex($1));
+ }
+ $str =~ s!::([a-f0-9]{2})!chr(hex($1))!egms;
+ $str =~ tr!:!/!;
+ $first . $str;
+}
+
1;