script/public-inbox-convert

#!/usr/bin/perl -w
# Copyright (C) all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <http://www.gnu.org/licenses/agpl-3.0.txt>
use strict;
use v5.10.1;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
usage: public-inbox-convert [options] OLD NEW

  convert v1 format inboxes to v2

options:

  --no-index          do not index after conversion
  --jobs=NUM          set shards (NUM=0)
  --verbose | -v      increase verbosity (may be repeated)

index options (see public-inbox-index(1) man page for full description):

  --no-fsync          speed up indexing, risk corruption on power outage
  -L LEVEL            `basic', `medium', or `full' (default: full)
  --compact | -c      run public-inbox-compact(1) after indexing
  --sequential-shard  index Xapian shards sequentially for slow storage
  --batch-size=BYTES  flush changes to OS after a given number of bytes
  --max-size=BYTES    do not index messages larger than the given size

See public-inbox-convert(1) man page for full documentation.
EOF

my $opt = {
	index => 1,
	# index defaults:
	quiet => -1, compact => 0, maxsize => undef, fsync => 1,
	reindex => 1, # we always reindex
};
GetOptions($opt, qw(jobs|j=i index! help|h C=s@),
		# index options
		qw(verbose|v+ rethread compact|c+ fsync|sync!
		indexlevel|index-level|L=s max_size|max-size=s
		batch_size|batch-size=s
		sequential-shard|seq-shard
		)) or die $help;
if ($opt->{help}) { print $help; exit 0 };
require PublicInbox::Admin;
PublicInbox::Admin::do_chdir(delete $opt->{C});
my $old_dir = shift(@ARGV) // '';
my $new_dir = shift(@ARGV) // '';
die $help if (scalar(@ARGV) || $new_dir eq '' || $old_dir eq '');
die "$new_dir exists\n" if -d $new_dir;
die "$old_dir not a directory\n" unless -d $old_dir;

require PublicInbox::Config;
require PublicInbox::InboxWritable;

my $cfg = PublicInbox::Config->new;
my @old = PublicInbox::Admin::resolve_inboxes([$old_dir], undef, $cfg);
@old > 1 and die "BUG: resolved several inboxes from $old_dir:\n",
		map { "\t$_->{inboxdir}\n" } @old;
my $old = PublicInbox::InboxWritable->new($old[0]);
if (delete $old->{-unconfigured}) {
	warn "W: $old_dir not configured in " .
		PublicInbox::Config::default_file() . "\n";
}
die "Only conversion from v1 inboxes is supported\n" if $old->version >= 2;

my $detected = $old->detect_indexlevel;
$old->{indexlevel} //= $detected;
my $env;
if ($opt->{'index'}) {
	my $mods = {};
	PublicInbox::Admin::scan_ibx_modules($mods, $old);
	PublicInbox::Admin::require_or_die(keys %$mods);
	PublicInbox::Admin::progress_prepare($opt);
	$env = PublicInbox::Admin::index_prepare($opt, $cfg);
}
local %ENV = (%$env, %ENV) if $env;
my $new = { %$old };
$new->{inboxdir} = PublicInbox::Config::rel2abs_collapsed($new_dir);
$new->{version} = 2;
$new = PublicInbox::InboxWritable->new($new, { nproc => $opt->{jobs} });
$new->{-no_fsync} = 1 if !$opt->{fsync};
my $v2w;

sub link_or_copy ($$) {
	my ($src, $dst) = @_;
	link($src, $dst) and return;
	$!{EXDEV} or warn "link $src, $dst failed: $!, trying cp\n";
	require File::Copy; # preserves permissions:
	File::Copy::cp($src, $dst) or die "cp $src, $dst failed: $!\n";
}

{
	my $restore = $old->with_umask;
	my $old_cfg = "$old->{inboxdir}/config";
	local $ENV{GIT_CONFIG} = $old_cfg;
	my $new_cfg = "$new->{inboxdir}/all.git/config";
	$v2w = $new->importer(1);
	$v2w->init_inbox(delete $opt->{jobs});
	unlink $new_cfg;
	link_or_copy($old_cfg, $new_cfg);
	if (my $alt = $new->{altid}) {
		require PublicInbox::AltId;
		foreach my $i (0..$#$alt) {
			my $src = PublicInbox::AltId->new($old, $alt->[$i], 0);
			$src = $src->mm_alt or next;
			$src = $src->{dbh}->sqlite_db_filename;
			my $dst = PublicInbox::AltId->new($new, $alt->[$i], 1);
			$dst->mm_alt->{dbh}->sqlite_backup_from_file($src);
		}
	}
	my $desc = "$old->{inboxdir}/description";
	link_or_copy($desc, "$new->{inboxdir}/description") if -e $desc;
	my $clone = "$old->{inboxdir}/cloneurl";
	warn <<"" if -e $clone;
$clone may not be valid after migrating to v2, not copying

}
my $state = '';
my $head = $old->{ref_head} || 'HEAD';
my $rd = $old->git->popen(qw(fast-export --use-done-feature), $head);
$v2w->idx_init($opt);
my $im = $v2w->importer;
my $io = $im->gfi_start;
my $h = '[0-9a-f]';
my %D;
my $last;
while (<$rd>) {
	if ($_ eq "blob\n") {
		$state = 'blob';
	} elsif (/^commit /) {
		$state = 'commit';
	} elsif (/^data ([0-9]+)/) {
		print $io $_ or $im->wfail;
		print $io PublicInbox::IO::read_all($rd, $1) or $im->wfail;
		next;
	} elsif ($state eq 'commit') {
		if (m{^M 100644 :([0-9]+) (${h}{2}/${h}{38})}o) {
			my ($mark, $path) = ($1, $2);
			$D{$path} = $mark;
			if ($last && $last ne 'm') {
				print $io "D $last\n" or $im->wfail;
			}
			print $io "M 100644 :$mark m\n" or $im->wfail;
			$last = 'm';
			next;
		}
		if (m{^D (${h}{2}/${h}{38})}o) {
			my $mark = delete $D{$1};
			defined $mark or die "undeleted path: $1\n";
			if ($last && $last ne 'd') {
				print $io "D $last\n" or $im->wfail;
			}
			print $io "M 100644 :$mark d\n" or $im->wfail;
			$last = 'd';
			next;
		}
	}
	last if $_ eq "done\n";
	print $io $_ or $im->wfail;
}
$rd->close or die "fast-export: \$?=$? \$!=$!\n";
$io = undef;
$v2w->done;
if (my $old_mm = $old->mm) {
	$old->cleanup;
	$old_mm = $old_mm->{dbh}->sqlite_db_filename;

	# we want to trigger a reindex, not a from scratch index if
	# we're reusing the msgmap from an existing v1 installation.
	$v2w->idx_init($opt);
	$v2w->{mm}->{dbh}->sqlite_backup_from_file($old_mm);

	my $epoch0 = PublicInbox::Git->new($v2w->{mg}->add_epoch(0));
	chop(my $cmt = $epoch0->qx(qw(rev-parse --verify), $head));
	$v2w->last_epoch_commit(0, $cmt);
}
$v2w->index_sync($opt) if delete $opt->{'index'};
$v2w->done;