X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLinkify.pm;h=9fc3128fdc2d6842d5f021da71cb7c6423277e31;hb=3f3c294e9466a4db7e0ed53e57b37226d0715f8a;hp=5b83742c14b36ace1e62790b20d417e0971dbc87;hpb=2394cb0bdc671605729b5a4c578ef4cd3b9813fd;p=public-inbox.git

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 5b83742c..9fc3128f 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # two-step linkification.
@@ -11,12 +11,13 @@
 # Maybe this could be done more efficiently...
 package PublicInbox::Linkify;
 use strict;
-use warnings;
+use v5.10.1;
 use Digest::SHA qw/sha1_hex/;
-use PublicInbox::Hval qw(ascii_html);
+use PublicInbox::Hval qw(ascii_html mid_href);
+use PublicInbox::MID qw($MID_EXTRACT);
 
 my $SALT = rand;
-my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|imaps?|s?news|gopher)://
 		 [\@:\w\.-]+(?:/
 		 (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
 		 (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
@@ -67,23 +68,22 @@ sub linkify_1 {
 		# 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);
-
+		$key =~ tr/0-9/A-J/; # no digits for YAML highlight
 		$_[0]->{$key} = $url;
-		$beg . 'PI-LINK-'. $key . $end;
-	^ge;
+		$beg . 'LINKIFY' . $key . $end;
+	^geo;
 	$_[1];
 }
 
 sub linkify_2 {
-	# Added "PI-LINK-" prefix to avoid false-positives on git commits
-	$_[1] =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+	# Added "LINKIFY" prefix to avoid false-positives on git commits
+	$_[1] =~ s!\bLINKIFY([a-fA-J]{40})\b!
 		my $key = $1;
 		my $url = $_[0]->{$key};
 		if (defined $url) {
 			"<a\nhref=\"$url\">$url</a>";
-		} else {
-			# false positive or somebody tried to mess with us
-			$key;
+		} else { # false positive or somebody tried to mess with us
+			'LINKIFY'.$key;
 		}
 	!ge;
 	$_[1];
@@ -92,30 +92,33 @@ sub linkify_2 {
 # single pass linkification of <Message-ID@example.com> within $str
 # with $pfx being the URL prefix
 sub linkify_mids {
-	my ($self, $pfx, $str) = @_;
-	$$str =~ s!<([^>]+)>!
-		my $msgid = PublicInbox::Hval->new_msgid($1);
-		my $html = $msgid->as_html;
-		my $href = $msgid->{href};
-		$href = ascii_html($href); # for IDN
+	my ($self, $pfx, $str, $raw) = @_;
+	$$str =~ s!$MID_EXTRACT!
+		my $mid = $1;
+		my $html = ascii_html($mid);
+		my $href = mid_href($mid);
 
 		# 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);
-		$self->{$key} = [ $href, $html ];
-		'<PI-LINK-'. $key . '>';
+		$key =~ tr/0-9/A-J/;
+		my $repl = qq(&lt;<a\nhref="$pfx/$href/">$html</a>&gt;);
+		$repl .= qq{ (<a\nhref="$pfx/$href/raw">raw</a>)} if $raw;
+		$self->{$key} = $repl;
+		'LINKIFY'.$key;
 		!ge;
 	$$str = ascii_html($$str);
-	$$str =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+	$$str =~ s!\bLINKIFY([a-fA-J]{40})\b!
 		my $key = $1;
 		my $repl = $_[0]->{$key};
 		if (defined $repl) {
-			"<a\nhref=\"$pfx/$repl->[0]/\">$repl->[1]</a>";
-		} else {
-			# false positive or somebody tried to mess with us
-			$key;
+			$repl;
+		} else { # false positive or somebody tried to mess with us
+			'LINKIFY'.$key;
 		}
 	!ge;
 }
 
+sub to_html { linkify_2($_[0], ascii_html(linkify_1(@_))) }
+
 1;