X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLinkify.pm;h=199457af351910c0a16b6250c74a48ee90e23c86;hb=02cdbe1c1638ba8e80351b39029c08343fab018b;hp=aa472cdb7167473d2706e069073eb9ef7683aa51;hpb=58700fb1830d1f854e688dfa47390d7f2eef9035;p=public-inbox.git
diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index aa472cdb..199457af 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 all contributors
+# Copyright (C) 2014-2019 all contributors
# License: AGPL-3.0+
# two-step linkification.
@@ -13,9 +13,10 @@ package PublicInbox::Linkify;
use strict;
use warnings;
use Digest::SHA qw/sha1_hex/;
+use PublicInbox::Hval qw(ascii_html);
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\-\._~!\$\&\';\(\)\*\+,;=:@/%]+)?
@@ -25,6 +26,14 @@ my $LINK_RE = qr{(\()?\b((?:ftps?|https?|nntps?|gopher)://
sub new { bless {}, $_[0] }
+# try to distinguish paired punctuation chars from the URL itself
+# Maybe other languages/formats can be supported here, too...
+my %pairs = (
+ "(" => qr/(\)[\.,;\+]?)\z/, # Markdown (,), Ruby (+) (, for arrays)
+ "'" => qr/('[\.,;\+]?)\z/, # Perl / Ruby
+ "!" => qr/(![\.,;\+]?)\z/, # Perl / Ruby
+);
+
sub linkify_1 {
$_[1] =~ s^$LINK_RE^
my $beg = $1 || '';
@@ -35,26 +44,33 @@ sub linkify_1 {
# '.', ',' or ';' to denote the end of a statement;
# assume the intent was to end the statement/sentence
# in English
- # Markdown compatibility:
- if ($beg eq '(') {
- if ($url =~ s/(\)[\.,;]?)\z//) {
+ if (defined(my $re = $pairs{$beg})) {
+ 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/&/&/g;
$_[0]->{$key} = $url;
$beg . 'PI-LINK-'. $key . $end;
- ^ge;
+ ^geo;
$_[1];
}
@@ -73,4 +89,37 @@ sub linkify_2 {
$_[1];
}
+# single pass linkification of within $str
+# with $pfx being the URL prefix
+sub linkify_mids {
+ my ($self, $pfx, $str, $raw) = @_;
+ $$str =~ s!<([^>]+)>!
+ my $msgid = PublicInbox::Hval->new_msgid($1);
+ my $html = $msgid->as_html;
+ my $href = $msgid->{href};
+ $href = ascii_html($href); # for IDN
+
+ # salt this, as this could be exploited to show
+ # links in the HTML which don't show up in the raw mail.
+ my $key = sha1_hex($html . $SALT);
+ my $repl = qq(<$html>);
+ $repl .= qq{ (raw)} if $raw;
+ $self->{$key} = $repl;
+ 'PI-LINK-'. $key;
+ !ge;
+ $$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;