From f99f9048cdac42509fbbc1f97e2af32fa3bffca6 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Tue, 6 Dec 2016 23:40:33 +0000 Subject: linkify: implement Markdown link compatibility (again) 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 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'lib/PublicInbox') diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm index ea7fd71f..acd2a47e 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; } -- cgit v1.2.3-24-ge0c7