-# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# two-step linkification.
# Maybe this could be done more efficiently...
package PublicInbox::Linkify;
use strict;
-use warnings;
-use Digest::SHA qw/sha1_hex/;
+use v5.10.1;
+use PublicInbox::SHA qw(sha1_hex);
+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\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
$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/&/&/g;
+ $key =~ tr/0-9/A-J/; # no digits for YAML highlight
$_[0]->{$key} = $url;
- $beg . 'PI-LINK-'. $key . $end;
- ^ge;
+ $beg . 'LINKIFY' . $key . $end;
+ ^geo;
$_[1];
}
sub linkify_2 {
- # Added "PI-LINK-" prefix to avoid false-positives on git commits
- $_[1] =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+ # Added "LINKIFY" prefix to avoid false-positives on git commits
+ $_[1] =~ s!\bLINKIFY([a-fA-J]{40})\b!
my $key = $1;
my $url = $_[0]->{$key};
if (defined $url) {
"<a\nhref=\"$url\">$url</a>";
- } else {
- # false positive or somebody tried to mess with us
- $key;
+ } else { # false positive or somebody tried to mess with us
+ 'LINKIFY'.$key;
}
!ge;
$_[1];
}
+# single pass linkification of <Message-ID@example.com> within $str
+# with $pfx being the URL prefix
+sub linkify_mids {
+ my ($self, $pfx, $str, $raw) = @_;
+ $$str =~ s!$MID_EXTRACT!
+ my $mid = $1;
+ my $html = ascii_html($mid);
+ my $href = mid_href($mid);
+
+ # salt this, as this could be exploited to show
+ # links in the HTML which don't show up in the raw mail.
+ my $key = sha1_hex($html . $SALT);
+ $key =~ tr/0-9/A-J/;
+ my $repl = qq(<<a\nhref="$pfx/$href/">$html</a>>);
+ $repl .= qq{ (<a\nhref="$pfx/$href/raw">raw</a>)} if $raw;
+ $self->{$key} = $repl;
+ 'LINKIFY'.$key;
+ !ge;
+ $$str = ascii_html($$str);
+ $$str =~ s!\bLINKIFY([a-fA-J]{40})\b!
+ my $key = $1;
+ my $repl = $_[0]->{$key};
+ if (defined $repl) {
+ $repl;
+ } else { # false positive or somebody tried to mess with us
+ 'LINKIFY'.$key;
+ }
+ !ge;
+}
+
+sub to_html { linkify_2($_[0], ascii_html(linkify_1(@_))) }
+
1;