X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=2e883f810023f2a0bb3314e418437cca469365e0;hb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;hp=2b4439703f59b692e9c6c80a628c809185c103fa;hpb=c5621af43e9c7cb1ff0565aa61a1d8fced55a23b;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 2b443970..2e883f81 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) 2014-2020 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
@@ -10,7 +10,7 @@ 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 src_escape
-		to_attr from_attr/;
+		to_attr prurl/;
 my $enc_ascii = find_encoding('us-ascii');
 
 # safe-ish acceptable filename pattern for portability
@@ -32,14 +32,6 @@ sub new_msgid {
 	$class->new($msgid, mid_escape($msgid));
 }
 
-sub new_oneline {
-	my ($class, $raw) = @_;
-	$raw = '' unless defined $raw;
-	$raw =~ tr/\t\n / /s; # squeeze spaces
-	$raw =~ tr/\r//d; # kill CR
-	$class->new($raw);
-}
-
 # some of these overrides are standard C escapes so they're
 # easy-to-understand when rendered.
 my %escape_sequence = (
@@ -66,8 +58,11 @@ my %xhtml_map = (
 $xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
 %xhtml_map = (%xhtml_map, %escape_sequence);
 
+# for post-processing the output of highlight.pm and perhaps other
+# highlighers in the future
 sub src_escape ($) {
 	$_[0] =~ s/\r\n/\n/sg;
+	$_[0] =~ s/&apos;/&#39;/sg; # workaround https://bugs.debian.org/927409
 	$_[0] =~ s/([\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
 	$_[0] = $enc_ascii->encode($_[0], Encode::HTMLCREF);
 }
@@ -89,8 +84,15 @@ sub raw {
 	}
 }
 
-sub prurl {
+# returns a protocol-relative URL string
+sub prurl ($$) {
 	my ($env, $u) = @_;
+	if (ref($u) eq 'ARRAY') {
+		my $h = $env->{HTTP_HOST} // $env->{SERVER_NAME};
+		my @host_match = grep(/\b\Q$h\E\b/, @$u);
+		$u = $host_match[0] // $u->[0];
+		# fall through to below:
+	}
 	index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
 }
 
@@ -137,22 +139,12 @@ sub to_attr ($) {
 	return if index($str, '//') >= 0;
 
 	my $first = '';
+	utf8::encode($str); # to octets
 	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;
-	$str =~ tr!:!/!;
+	utf8::decode($str); # allow wide chars
 	$first . $str;
 }