X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=0e290601f2a0d74284f4b24278e7eeab8c973137;hb=9bd675d33ad1e49bd2ebe12a1d216216e61380de;hp=4d70d5e5008c5185ad743687437039f0f49dcceb;hpb=e2708d16d8f801bdf3a61306d07a127c3c9176ee;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 4d70d5e5..0e290601 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # represents a header value in various forms.  Used for HTML generation
@@ -9,10 +9,13 @@ use warnings;
 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/;
-
+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) = @_;
 
@@ -63,6 +66,12 @@ my %xhtml_map = (
 $xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
 %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) = @_;
 	$s =~ s/\r\n/\n/sg; # fixup bad line endings
@@ -116,4 +125,35 @@ sub to_filename ($) {
 	$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;