imap+nntp: share COMPRESS implementation

[public-inbox.git] / lib / PublicInbox / Linkify.pm

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index 71193bc28732f28ca715323b04d31e53467ab189..2ac74e2a98bc1c1c666d674fcb4591976801845a 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # two-step linkification.
@@ -13,9 +13,11 @@ package PublicInbox::Linkify;
 use strict;
 use warnings;
 use Digest::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\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
@@ -47,21 +49,29 @@ sub linkify_1 {
                        if ($url =~ s/$re//) {
                                $end = $1;
                        }
-               } elsif ($url =~ s/([\.,;])\z//) {
-                       $end = $1;
+               } elsif ($url =~ s/(\))?([\.,;])\z//) {
+                       $end = $2;
+                       # require ')' to be paired with '('
+                       if (defined $1) { # ')'
+                               if (index($url, '(') < 0) {
+                                       $end = ")$end";
+                               } else {
+                                       $url .= ')';
+                               }
+                       }
                } elsif ($url !~ /\(/ && $url =~ s/\)\z//) {
                        $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/&/&#38;/g;
                $_[0]->{$key} = $url;
                $beg . 'PI-LINK-'. $key . $end;
-       ^ge;
+       ^geo;
        $_[1];
 }
 
@@ -80,4 +90,36 @@ sub linkify_2 {
        $_[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) = @_;
+       $$str =~ s!$MID_EXTRACT!
+               my $mid = $1;
+               my $html = ascii_html($mid);
+               my $href = mid_href($mid);
+
+               # salt this, as this could be exploited to show
+               # links in the HTML which don't show up in the raw mail.
+               my $key = sha1_hex($html . $SALT);
+               my $repl = qq(&lt;<a\nhref="$pfx/$href/">$html</a>&gt;);
+               $repl .= qq{ (<a\nhref="$pfx/$href/raw">raw</a>)} if $raw;
+               $self->{$key} = $repl;
+               'PI-LINK-'. $key;
+               !ge;
+       $$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;