X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLinkify.pm;h=175f8d724dbb25e2d8e04f89a2a1792373d83b3c;hb=9bd675d33ad1e49bd2ebe12a1d216216e61380de;hp=cc0f7e3a5a3a775d3744100a0e67e3f71a11a3db;hpb=130d0c4e33c5c73dc69e270fc698735d49e0f159;p=public-inbox.git

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index cc0f7e3a..175f8d72 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2016 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.
@@ -13,57 +13,72 @@ 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)://
-		 [\@:\w\.-]+/
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
+		 [\@:\w\.-]+(?:/
 		 (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
 		 (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
 		 (?:\#[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%\?]+)?
-		 )}xi;
+		 )?
+		)}xi;
 
-sub new { bless {}, shift }
+sub new { bless {}, $_[0] }
+
+# try to distinguish paired punctuation chars from the URL itself
+# Maybe other languages/formats can be supported here, too...
+my %pairs = (
+	"(" => qr/(\)[\.,;\+]?)\z/, # Markdown (,), Ruby (+) (, for arrays)
+	"'" => qr/('[\.,;\+]?)\z/, # Perl / Ruby
+	"!" => qr/(![\.,;\+]?)\z/, # Perl / Ruby
+);
 
 sub linkify_1 {
-	my ($self, $s) = @_;
-	$s =~ s!$LINK_RE!
+	$_[1] =~ s^$LINK_RE^
 		my $beg = $1 || '';
 		my $url = $2;
 		my $end = '';
 
-		# Markdown compatibility:
-		if ($beg eq '(') {
-			$url =~ s/\)\z//;
-			$end = ')';
-		}
-
 		# it's fairly common to end URLs in messages with
 		# '.', ',' or ';' to denote the end of a statement;
 		# assume the intent was to end the statement/sentence
 		# in English
-		if ($url =~ s/([\.,;])\z//) {
-			$end = $1 . $end;
+		if (defined(my $re = $pairs{$beg})) {
+			if ($url =~ s/$re//) {
+				$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;
-		$self->{$key} = $url;
+		$_[0]->{$key} = $url;
 		$beg . 'PI-LINK-'. $key . $end;
-	!ge;
-	$s;
+	^ge;
+	$_[1];
 }
 
 sub linkify_2 {
-	my ($self, $s) = @_;
-
 	# Added "PI-LINK-" prefix to avoid false-positives on git commits
-	$s =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+	$_[1] =~ s!\bPI-LINK-([a-f0-9]{40})\b!
 		my $key = $1;
-		my $url = $self->{$key};
+		my $url = $_[0]->{$key};
 		if (defined $url) {
 			"<a\nhref=\"$url\">$url</a>";
 		} else {
@@ -71,7 +86,7 @@ sub linkify_2 {
 			$key;
 		}
 	!ge;
-	$s;
+	$_[1];
 }
 
 1;