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 8f634f482828f64896ee7795e60f0267ee21ee02..2ac74e2a98bc1c1c666d674fcb4591976801845a 100644 (file)
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2016 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.
@@ -13,37 +13,73 @@ 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((?:ftp|https?|nntp)://
-                [\@:\w\.-]+/
-                ?[\@\w\+\&\?\.\%\;/#=-]*)!x;
+my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|imaps?|s?news|gopher)://
+                [\@:\w\.-]+(?:/
+                (?:[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]*)
+                (?:\?[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
+                (?:\#[a-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@/%\?]+)?
+                )?
+               )}xi;
 
-sub new { bless {}, shift }
+sub new { bless {}, $_[0] }
+
+# try to distinguish paired punctuation chars from the URL itself
+# Maybe other languages/formats can be supported here, too...
+my %pairs = (
+       "(" => qr/(\)[\.,;\+]?)\z/, # Markdown (,), Ruby (+) (, for arrays)
+       "'" => qr/('[\.,;\+]?)\z/, # Perl / Ruby
+       "!" => qr/(![\.,;\+]?)\z/, # Perl / Ruby
+);
 
 sub linkify_1 {
-       my ($self, $s) = @_;
-       $s =~ s!$LINK_RE!
-               my $url = $1;
+       $_[1] =~ s^$LINK_RE^
+               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 (defined(my $re = $pairs{$beg})) {
+                       if ($url =~ s/$re//) {
+                               $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;
-               $self->{$key} = $url;
-               'PI-LINK-'. $key;
-       !ge;
-       $s;
+               $_[0]->{$key} = $url;
+               $beg . 'PI-LINK-'. $key . $end;
+       ^geo;
+       $_[1];
 }
 
 sub linkify_2 {
-       my ($self, $s) = @_;
-
        # Added "PI-LINK-" prefix to avoid false-positives on git commits
-       $s =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+       $_[1] =~ s!\bPI-LINK-([a-f0-9]{40})\b!
                my $key = $1;
-               my $url = $self->{$key};
+               my $url = $_[0]->{$key};
                if (defined $url) {
                        "<a\nhref=\"$url\">$url</a>";
                } else {
@@ -51,7 +87,39 @@ sub linkify_2 {
                        $key;
                }
        !ge;
-       $s;
+       $_[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;