[RFC] make external urls user configurable

[Ali Alnubani <alialnu@mellanox.com>]

The configuration variable publicinbox.exturls will
hold a comma-delimited list of external urls to point
to in case a thread wasn't found.
This configuration will replace the default hard-coded
list in the module 'PublicInbox::ExtMsg' (lib/PublicInbox/ExtMsg.pm:17).

An example configuration:

[publicinbox]
	exturls=//marc.info/?i=%s,\
	//www.mail-archive.com/search?l=mid&q=%s,\
	nntp://news.gmane.org/%s,\
	https://lists.debian.org/msgid-search/%s,\
	//docs.FreeBSD.org/cgi/mid.cgi?db=mid&id=%s,\
	https://www.w3.org/mid/%s,\
	http://www.postgresql.org/message-id/%s,\
	; The following entry has to be a single line
	https://lists.debconf.org/cgi-lurker/keyword.cgi?doc-url=/lurker&
	format=en.html&query=id:%s

---
We started using public-inbox for dpdk.org (http://inbox.dpdk.org/dev/),
and most of our mailing lists aren't archived by these external
websites.

This still needs further improvements.

 lib/PublicInbox/ExtMsg.pm | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm
index d07d5a7..b1f6528 100644
--- a/lib/PublicInbox/ExtMsg.pm
+++ b/lib/PublicInbox/ExtMsg.pm
@@ -13,20 +13,6 @@ use PublicInbox::MID qw/mid2path/;
 use PublicInbox::WwwStream;
 our $MIN_PARTIAL_LEN = 16;
 
-# TODO: user-configurable
-our @EXT_URL = map { ascii_html($_) } (
-	# leading "//" denotes protocol-relative (http:// or https://)
-	'//marc.info/?i=%s',
-	'//www.mail-archive.com/search?l=mid&q=%s',
-	'nntp://news.gmane.org/%s',
-	'https://lists.debian.org/msgid-search/%s',
-	'//docs.FreeBSD.org/cgi/mid.cgi?db=mid&id=%s',
-	'https://www.w3.org/mid/%s',
-	'http://www.postgresql.org/message-id/%s',
-	'https://lists.debconf.org/cgi-lurker/keyword.cgi?'.
-		'doc-url=/lurker&format=en.html&query=id:%s'
-);
-
 sub PARTIAL_MAX () { 100 }
 
 sub search_partial ($$) {
@@ -166,7 +152,9 @@ sub ext_urls {
 	if (@EXT_URL && index($mid, '@') >= 0) {
 		my $env = $ctx->{env};
 		my $e = "\nPerhaps try an external site:\n\n";
-		foreach my $url (@EXT_URL) {
+		my @exturls = grep { /\S/ } map { ascii_html($_) } (
+			split(/[\s,]+/, $ctx->{www}->{pi_config}->{'publicinbox.exturls'}));
+		foreach my $url (@exturls) {
 			my $u = PublicInbox::Hval::prurl($env, $url);
 			my $r = sprintf($u, $href);
 			my $t = sprintf($u, $html);
-- 
2.21.0