+#!/usr/bin/perl -w
+# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <http://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use warnings;
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+use PublicInbox::MIME;
+use PublicInbox::Inbox;
+use PublicInbox::Config;
+use PublicInbox::V2Writable;
+use PublicInbox::Spawn qw(spawn);
+use Cwd 'abs_path';
+my $usage = "Usage: public-inbox-convert OLD NEW\n";
+my $jobs;
+my $index = 1;
+my %opts = (
+ '--jobs|j=i' => \$jobs,
+ '--index!' => \$index,
+);
+GetOptions(%opts) or die "bad command-line args\n$usage";
+GetOptions(%opts) or die "bad command-line args\n$usage";
+my $old_dir = shift or die $usage;
+my $new_dir = shift or die $usage;
+die "$new_dir exists\n" if -d $new_dir;
+die "$old_dir not a directory\n" unless -d $old_dir;
+my $config = PublicInbox::Config->new;
+$old_dir = abs_path($old_dir);
+my $old;
+$config->each_inbox(sub {
+ $old = $_[0] if abs_path($_[0]->{mainrepo}) eq $old_dir;
+});
+unless ($old) {
+ warn "W: $old_dir not configured in " .
+ PublicInbox::Config::default_file() . "\n";
+ $old = {
+ mainrepo => $old_dir,
+ name => 'ignored',
+ address => [ 'old@example.com' ],
+ };
+ $old = PublicInbox::Inbox->new($old);
+}
+if (($old->{version} || 1) >= 2) {
+ die "Only conversion from v1 inboxes is supported\n";
+}
+my $new = { %$old };
+delete $new->{altid}; # TODO: support altid for v2
+$new->{mainrepo} = $new_dir;
+$new->{version} = 2;
+$new = PublicInbox::Inbox->new($new);
+my $v2w = PublicInbox::V2Writable->new($new, 1);
+$v2w->init_inbox($jobs);
+my $state = '';
+my ($prev, $from);
+my $head = $old->{ref_head} || 'HEAD';
+my ($rd, $pid) = $old->git->popen(qw(fast-export --use-done-feature), $head);
+$v2w->idx_init;
+my $im = $v2w->importer;
+my ($r, $w) = $im->gfi_start;
+my $h = '[0-9a-f]';
+my %D;
+while (<$rd>) {
+ if ($_ eq "blob\n") {
+ $state = 'blob';
+ } elsif (/^commit /) {
+ $state = 'commit';
+ } elsif (/^data (\d+)/) {
+ my $len = $1;
+ $w->print($_) or $im->wfail;
+ while ($len) {
+ my $n = read($rd, my $tmp, $len) or die "read: $!";
+ warn "$n != $len\n" if $n != $len;
+ $len -= $n;
+ $w->print($tmp) or $im->wfail;
+ }
+ next;
+ } elsif ($state eq 'commit') {
+ if (m{^M 100644 :(\d+) (${h}{2}/${h}{38})}o) {
+ my ($mark, $path) = ($1, $2);
+ $D{$path} = $mark;
+ $w->print("M 100644 :$mark m\n") or $im->wfail;
+ next;
+ }
+ if (m{^D (${h}{2}/${h}{38})}o) {
+ my $mark = delete $D{$1};
+ defined $mark or die "undeleted path: $1\n";
+ $w->print("M 100644 :$mark _/D\n") or $im->wfail;
+ next;
+ }
+ if (m{^from (:\d+)}) {
+ $prev = $from;
+ $from = $1;
+ # no next
+ }
+ } elsif ($_ eq "done\n") {
+ last;
+ }
+ $w->print($_) or $im->wfail;
+}
+$w = $r = undef;
+close $rd or die "close fast-export: $!\n";
+waitpid($pid, 0) or die "waitpid failed: $!\n";
+$? == 0 or die "fast-export failed: $?\n";
+my $mm = $old->mm;
+$mm->{dbh}->sqlite_backup_to_file("$new_dir/msgmap.sqlite3") if $mm;
+$v2w->done;
+if ($index) {
+ $v2w->reindex;
+ $v2w->done;
+}