scripts/xhdr-num2mid

#!/usr/bin/perl -w
# Copyright (C) 2016-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Useful for mapping article IDs from existing NNTP servers to MIDs
use strict;
use warnings;
use Net::NNTP;
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);
die "Invalid group\n" if !(defined $num && defined $first && defined $last);
my $arg_first = shift;
if (defined $arg_first) {
	$arg_first =~ /\A[0-9]+\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 - 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;
	}
}