X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLinkify.pm;h=2ac74e2a98bc1c1c666d674fcb4591976801845a;hb=23af251dd607c4e75ab1e68063f2c885c48cc035;hp=175f8d724dbb25e2d8e04f89a2a1792373d83b3c;hpb=9bd675d33ad1e49bd2ebe12a1d216216e61380de;p=public-inbox.git diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm index 175f8d72..2ac74e2a 100644 --- a/lib/PublicInbox/Linkify.pm +++ b/lib/PublicInbox/Linkify.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2019 all contributors +# Copyright (C) 2014-2021 all contributors # License: AGPL-3.0+ # two-step linkification. @@ -13,10 +13,11 @@ package PublicInbox::Linkify; use strict; use warnings; 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\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)? @@ -70,7 +71,7 @@ sub linkify_1 { $_[0]->{$key} = $url; $beg . 'PI-LINK-'. $key . $end; - ^ge; + ^geo; $_[1]; } @@ -89,4 +90,36 @@ sub linkify_2 { $_[1]; } +# single pass linkification of within $str +# with $pfx being the URL prefix +sub linkify_mids { + my ($self, $pfx, $str, $raw) = @_; + $$str =~ s!$MID_EXTRACT! + my $mid = $1; + my $html = ascii_html($mid); + my $href = mid_href($mid); + + # salt this, as this could be exploited to show + # links in the HTML which don't show up in the raw mail. + my $key = sha1_hex($html . $SALT); + my $repl = qq(<$html>); + $repl .= qq{ (raw)} if $raw; + $self->{$key} = $repl; + 'PI-LINK-'. $key; + !ge; + $$str = ascii_html($$str); + $$str =~ s!\bPI-LINK-([a-f0-9]{40})\b! + my $key = $1; + my $repl = $_[0]->{$key}; + if (defined $repl) { + $repl; + } else { + # false positive or somebody tried to mess with us + $key; + } + !ge; +} + +sub to_html { linkify_2($_[0], ascii_html(linkify_1(@_))) } + 1;