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: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.0 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 38C091FC96; Tue, 6 Dec 2016 23:42:12 +0000 (UTC) Date: Tue, 6 Dec 2016 23:42:12 +0000 From: Eric Wong To: meta@public-inbox.org Subject: [PATCH] linkify: implement Markdown link compatibility (again) Message-ID: <20161206234212.GA22817@dcvr> References: <20161206230139.25292-1-e@80x24.org> <20161206231710.GA13120@dcvr> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20161206231710.GA13120@dcvr> 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. This fixes parentheses detection at sentence endings, as seen in practice on emails. --- lib/PublicInbox/Linkify.pm | 14 ++++++++++---- t/linkify.t | 22 ++++++++++++++++++++++ 2 files changed, 32 insertions(+), 4 deletions(-) diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm index ea7fd71..acd2a47 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\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)? @@ -27,14 +27,20 @@ sub new { bless {}, shift } sub linkify_1 { my ($self, $s) = @_; $s =~ s!$LINK_RE! - my $url = $1; + my $beg = $1 || ''; + my $url = $2; my $end = ''; # it's fairly common to end URLs in messages with # '.', ',' or ';' to denote the end of a statement; # assume the intent was to end the statement/sentence # in English - if ($url =~ s/([\.,;])\z//) { + # Markdown compatibility: + if ($beg eq '(') { + if ($url =~ s/(\)[\.,;]?)\z//) { + $end = $1; + } + } elsif ($url =~ s/([\.,;])\z//) { $end = $1; } @@ -45,7 +51,7 @@ 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; $s; } diff --git a/t/linkify.t b/t/linkify.t index 49cbbd6..99acf17 100644 --- a/t/linkify.t +++ b/t/linkify.t @@ -57,4 +57,26 @@ use PublicInbox::Linkify; is($s, qq(hello $u world), "root + fragment"); } +# Markdown compatibility +{ + 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'); + + $s = qq![markdown]($u "title")!; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq![markdown]($u "title")!, + 'Markdown title compatible'); + + $s = qq![markdown]($u).!; + $s = $l->linkify_1($s); + $s = $l->linkify_2($s); + is($s, qq![markdown]($u).!, + 'Markdown-compatible end of sentence'); +} + done_testing(); -- EW