From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: AS58073 46.182.106.0/24 X-Spam-Status: No, score=-1.2 required=3.0 tests=BAYES_00,RCVD_IN_BRBL_LASTEXT, RCVD_IN_MSPIKE_BL,RCVD_IN_MSPIKE_ZBI,RCVD_IN_XBL,SPF_FAIL,SPF_HELO_FAIL shortcircuit=no autolearn=no autolearn_force=no version=3.4.0 Received: from 80x24.org (tor-exit.critical.cat [46.182.106.190]) by dcvr.yhbt.net (Postfix) with ESMTP id 8466E1FC96 for ; Tue, 6 Dec 2016 23:01:44 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH] linkify: implement Markdown link compatibility Date: Tue, 6 Dec 2016 23:01:39 +0000 Message-Id: <20161206230139.25292-1-e@80x24.org> List-Id: Although unescaped parentheses in URLs are technically allowed, they are uncommon. However, Markdown-like syntaxes are unfortunately common for URLs, so we might as well support them. --- lib/PublicInbox/Linkify.pm | 15 +++++++++++---- t/linkify.t | 9 +++++++++ 2 files changed, 20 insertions(+), 4 deletions(-) diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm index ea7fd71..cc0f7e3 100644 --- a/lib/PublicInbox/Linkify.pm +++ b/lib/PublicInbox/Linkify.pm @@ -15,7 +15,7 @@ use warnings; use Digest::SHA qw/sha1_hex/; my $SALT = rand; -my $LINK_RE = qr{\b((?:ftps?|https?|nntps?|gopher):// +my $LINK_RE = qr{(\()?\b((?:ftps?|https?|nntps?|gopher):// [\@:\w\.-]+/ (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*) (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)? @@ -27,15 +27,22 @@ sub new { bless {}, shift } sub linkify_1 { my ($self, $s) = @_; $s =~ s!$LINK_RE! - my $url = $1; + 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 = $1 . $end; } # salt this, as this could be exploited to show @@ -45,7 +52,7 @@ sub linkify_1 { # only escape ampersands, others do not match LINK_RE $url =~ s/&/&/g; $self->{$key} = $url; - 'PI-LINK-'. $key . $end; + $beg . 'PI-LINK-'. $key . $end; !ge; $s; } diff --git a/t/linkify.t b/t/linkify.t index 49cbbd6..a794c78 100644 --- a/t/linkify.t +++ b/t/linkify.t @@ -57,4 +57,13 @@ use PublicInbox::Linkify; is($s, qq(hello $u world), "root + fragment"); } +{ + my $l = PublicInbox::Linkify->new; + my $u = 'http://example.com/'; + my $s = "[markdown]($u)"; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq![markdown]($u)!, 'markdown compatible'); +} + done_testing(); -- EW