X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLinkify.pm;h=af9be3ff1632be1d8f7ede077f982c55501a782e;hb=a8ae7e31ac36bcda04bf13a1b834207a89b0014c;hp=71193bc28732f28ca715323b04d31e53467ab189;hpb=348f6b2b271d3562509420070bd94d6ac00619dc;p=public-inbox.git

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 71193bc2..af9be3ff 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.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>
 
 # two-step linkification.
@@ -13,6 +13,7 @@ package PublicInbox::Linkify;
 use strict;
 use warnings;
 use Digest::SHA qw/sha1_hex/;
+use PublicInbox::Hval qw(ascii_html);
 
 my $SALT = rand;
 my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
@@ -47,18 +48,26 @@ sub linkify_1 {
 			if ($url =~ s/$re//) {
 				$end = $1;
 			}
-		} elsif ($url =~ s/([\.,;])\z//) {
-			$end = $1;
+		} elsif ($url =~ s/(\))?([\.,;])\z//) {
+			$end = $2;
+			# require ')' to be paired with '('
+			if (defined $1) { # ')'
+				if (index($url, '(') < 0) {
+					$end = ")$end";
+				} else {
+					$url .= ')';
+				}
+			}
 		} elsif ($url !~ /\(/ && $url =~ s/\)\z//) {
 			$end = ')';
 		}
 
+		$url = ascii_html($url); # for IDN
+
 		# salt this, as this could be exploited to show
 		# links in the HTML which don't show up in the raw mail.
 		my $key = sha1_hex($url . $SALT);
 
-		# only escape ampersands, others do not match LINK_RE
-		$url =~ s/&/&#38;/g;
 		$_[0]->{$key} = $url;
 		$beg . 'PI-LINK-'. $key . $end;
 	^ge;
@@ -80,4 +89,35 @@ sub linkify_2 {
 	$_[1];
 }
 
+# single pass linkification of <Message-ID@example.com> within $str
+# with $pfx being the URL prefix
+sub linkify_mids {
+	my ($self, $pfx, $str, $raw) = @_;
+	$$str =~ s!<([^>]+)>!
+		my $msgid = PublicInbox::Hval->new_msgid($1);
+		my $html = $msgid->as_html;
+		my $href = $msgid->{href};
+		$href = ascii_html($href); # for IDN
+
+		# salt this, as this could be exploited to show
+		# links in the HTML which don't show up in the raw mail.
+		my $key = sha1_hex($html . $SALT);
+		my $repl = qq(&lt;<a\nhref="$pfx/$href/">$html</a>&gt;);
+		$repl .= qq{ (<a\nhref="$pfx/$href/raw">raw</a>)} if $raw;
+		$self->{$key} = $repl;
+		'PI-LINK-'. $key;
+		!ge;
+	$$str = ascii_html($$str);
+	$$str =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+		my $key = $1;
+		my $repl = $_[0]->{$key};
+		if (defined $repl) {
+			$repl;
+		} else {
+			# false positive or somebody tried to mess with us
+			$key;
+		}
+	!ge;
+}
+
 1;