[PATCH] convert: preserve highwater mark from v1 msgmap

[PATCH] convert: preserve highwater mark from v1 msgmap

[Eric Wong]

If we're reusing the msgmap from a v1 inbox, we also need to
ensure the highwater mark doesn't get doubled in the v1->v2
conversion by internally triggering the equivalent of
"--reindex" on a fresh v2 inbox.

This was needed to convert an indexed v1 inbox which featured
messages with multiple Message-IDs in it.  Fresh, unindexed
clones of v1 inboxes would not have been affected by this.
---
 script/public-inbox-convert | 16 +++++++++++++---
 t/convert-compact.t         |  8 ++++++++
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/script/public-inbox-convert b/script/public-inbox-convert
index 56a810eb..8ac111a2 100755
--- a/script/public-inbox-convert
+++ b/script/public-inbox-convert
@@ -7,6 +7,7 @@ use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
 use PublicInbox::InboxWritable;
 use PublicInbox::Config;
 use PublicInbox::V2Writable;
+use PublicInbox::Git;
 use PublicInbox::Spawn qw(spawn);
 use Cwd 'abs_path';
 use File::Copy 'cp'; # preserves permissions:
@@ -144,10 +145,19 @@ $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 (my $mm = $old->mm) {
+	$old->cleanup;
+	$mm->{dbh}->sqlite_backup_to_file("$new_dir/msgmap.sqlite3");
+
+	# 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;
+	my $epoch0 = PublicInbox::Git->new($v2w->git_init(0));
+	chop(my $cmt = $epoch0->qx(qw(rev-parse --verify), $head));
+	$v2w->last_epoch_commit(0, $cmt);
+}
 if ($index) {
-	$v2w->index_sync;
+	$v2w->index_sync({reindex => 1});
 	$v2w->done;
 }
diff --git a/t/convert-compact.t b/t/convert-compact.t
index 6e4a8268..fc46083b 100644
--- a/t/convert-compact.t
+++ b/t/convert-compact.t
@@ -69,6 +69,13 @@ is(scalar(@xdir), 1, 'got one xapian directory after compact');
 is(((stat($xdir[0]))[2]) & 07777, 0755,
 	'sharedRepository respected on v1 compact');
 
+my $hwm = do {
+	my $mm = $ibx->mm;
+	$ibx->cleanup;
+	$mm->num_highwater;
+};
+ok(defined($hwm) && $hwm > 0, "highwater mark set #$hwm");
+
 $cmd = [ '-convert', $ibx->{inboxdir}, "$tmpdir/v2" ];
 ok(run_script($cmd, undef, $rdr), 'convert works');
 @xdir = glob("$tmpdir/v2/xap*/*");
@@ -83,6 +90,7 @@ my $env = { NPROC => 2 };
 ok(run_script($cmd, $env, $rdr), 'v2 compact works');
 $ibx->{inboxdir} = "$tmpdir/v2";
 $ibx->{version} = 2;
+is($ibx->mm->num_highwater, $hwm, 'highwater mark unchanged in v2 inbox');
 
 @xdir = glob("$tmpdir/v2/xap*/*");
 foreach (@xdir) {