From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id A8E0F1F9FE for ; Wed, 24 Feb 2021 23:37:18 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 1/2] lei_external: don't treat IPv6 URLs as globs Date: Thu, 25 Feb 2021 05:37:17 +0600 Message-Id: <20210224233718.19007-2-e@80x24.org> In-Reply-To: <20210224233718.19007-1-e@80x24.org> References: <20210224233718.19007-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: IPv6 addresses are hexadecimals and colons inside brackets, so add some DWIM-ery to ensure we don't attempt to treat addresses like "http://[dead:beef]/foo/" as a glob. --- lib/PublicInbox/LeiExternal.pm | 8 +++++++- t/lei_external.t | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/lib/PublicInbox/LeiExternal.pm b/lib/PublicInbox/LeiExternal.pm index 0cc84cca..47791d4e 100644 --- a/lib/PublicInbox/LeiExternal.pm +++ b/lib/PublicInbox/LeiExternal.pm @@ -54,6 +54,12 @@ sub glob2re { my $p = ''; my $in_bracket = 0; my $qm = 0; + my $schema_host_port = ''; + + # don't glob URL-looking things that look like IPv6 + if ($re =~ s!\A([a-z0-9\+]+://\[[a-f0-9\:]+\](?::[0-9]+)?/)!!i) { + $schema_host_port = quotemeta $1; # "http://[::1]:1234" + } my $changes = ($re =~ s!(.)! $re_map{$p eq '\\' ? '' : do { if ($1 eq '[') { ++$in_bracket } @@ -69,7 +75,7 @@ sub glob2re { (my $in_braces = $2) =~ tr!,!|!; $1."($in_braces)"; /sge); - ($changes - $qm) ? $re : undef; + ($changes - $qm) ? $schema_host_port.$re : undef; } # get canonicalized externals list matching $loc diff --git a/t/lei_external.t b/t/lei_external.t index 78f71658..51d0af5c 100644 --- a/t/lei_external.t +++ b/t/lei_external.t @@ -17,6 +17,7 @@ is($canon->('/this//path/'), '/this/path', 'extra slashes gone'); is($canon->('/ALL/CAPS'), '/ALL/CAPS', 'caps preserved'); my $glob2re = $cls->can('glob2re'); +is($glob2re->('http://[::1]:1234/foo/'), undef, 'IPv6 URL not globbed'); is($glob2re->('foo'), undef, 'plain string unchanged'); is_deeply($glob2re->('[f-o]'), '[f-o]' , 'range accepted'); is_deeply($glob2re->('*'), '[^/]*?' , 'wildcard accepted');