From 58a5bb3e18901237b1ca34ef8f03f696be27d305 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Thu, 11 Aug 2016 00:23:48 +0000
Subject: search: support alt-ID for mapping legacy serial numbers

For some existing mailing list archives, messages are identified
by serial number (such as NNTP article numbers in gmane).  Those
links may become inaccessible (as is the current case for
gmane), so ensure users can still search based on old serial
numbers.

Now, I run the following periodically to get article numbers
from gmane (while news.gmane.org remains):

	NNTPSERVER=news.gmane.org
	export NNTPSERVER
	GROUP=gmane.comp.version-control.git
	perl -I lib scripts/xhdr-num2mid $GROUP --msgmap=/path/to/gmane.sqlite3

(I might integrate this further with public-inbox-* scripts one day).

My ~/.public-inbox/config as an added "altid" snippet which now
looks like this:

[publicinbox "git"]
	address = git@vger.kernel.org
	mainrepo = /path/to/git.vger.git
	newsgroup = inbox.comp.version-control.git

	; relative pathnames expand to $mainrepo/public-inbox/$file
	altid = serial:gmane:file=gmane.sqlite3

And run "public-inbox-index --reindex /path/to/git.vger.git"
periodically.

This ought to allow searching for "gmane:12345" to work for
Xapian-enabled instances.

Disclaimer: while public-inbox supports NNTP and stable article
serial numbers, use of those for public links is discouraged
since it encourages centralization.
---
 scripts/xhdr-num2mid | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

(limited to 'scripts')

diff --git a/scripts/xhdr-num2mid b/scripts/xhdr-num2mid
index f1e7ea34..bc3ede60 100755
--- a/scripts/xhdr-num2mid
+++ b/scripts/xhdr-num2mid
@@ -5,8 +5,18 @@
 use strict;
 use warnings;
 use Net::NNTP;
-use Data::Dumper;
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
 my $usage = "usage: NNTPSERVER=news.example.org $0 GROUP [FIRST_NUM]\n";
+my ($msgmap, $mm);
+my %opts = ( '--msgmap=s' => \$msgmap );
+GetOptions(%opts) or die "bad command-line args\n$usage";
+
+if ($msgmap) {
+	require PublicInbox::Msgmap;
+	require PublicInbox::MID; # mid_clean
+	$mm = PublicInbox::Msgmap->new_file($msgmap, 1);
+}
+
 my $group = shift or die $usage;
 my $nntp = Net::NNTP->new($ENV{NNTPSERVER} || '127.0.0.1');
 my ($num, $first, $last) = $nntp->group($group);
@@ -15,16 +25,29 @@ my $arg_first = shift;
 if (defined $arg_first) {
 	$arg_first =~ /\A\d+\z/ or die $usage;
 	$first = $arg_first;
+} elsif ($mm) {
+	my $last_article = $mm->meta_accessor('last_article');
+	$first = $last_article + 1 if defined $last_article;
 }
 
 my $batch = 1000;
 my $i;
 for ($i = $first; $i < $last; $i += $batch) {
-	my $j = $i + $batch;
+	my $j = $i + $batch - 1;
 	$j = $last if $j > $last;
 	my $num2mid = $nntp->xhdr('Message-ID', "$i-$j");
+
+	$mm->{dbh}->begin_work if $mm;
 	for my $n ($i..$j) {
 		defined(my $mid = $num2mid->{$n}) or next;
 		print "$n $mid\n";
+		if ($mm) {
+			$mid = PublicInbox::MID::mid_clean($mid);
+			$mm->mid_set($n, $mid);
+		}
+	}
+	if ($mm) {
+		$mm->meta_accessor('last_article', $j);
+		$mm->{dbh}->commit;
 	}
 }
-- 
cgit v1.2.3-24-ge0c7