lib/PublicInbox/Xapcmd.pm | 34 ++++++++++++++++++++++++++++++++--
script/public-inbox-xcpdb | 8 ++++++--
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index ca74ea0c4c09f9ed2df7013679e3ab0d185dac31..d2de874357ab24b1f3e90e48baa221a7c3ac6578 100644
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -8,6 +8,10 @@ use PublicInbox::Over;
use File::Temp qw(tempdir);
use File::Path qw(remove_tree);
+# support testing with dev versions of Xapian which installs
+# commands with a version number suffix (e.g. "xapian-compact-1.5")
+our $XAPIAN_COMPACT = $ENV{XAPIAN_COMPACT} || 'xapian-compact';
+
sub commit_changes ($$$) {
my ($im, $old, $new) = @_;
my @st = stat($old) or die "failed to stat($old): $!\n";
@@ -36,6 +40,11 @@ exit 0;
} else {
spawn($cmd, $env, $opt);
}
+}
+
+sub runnable_or_die ($) {
+ my ($exe) = @_;
+ which($exe) or die "$exe not found in PATH\n";
}
sub run {
@@ -44,11 +53,12 @@ $opt ||= {};
my $dir = $ibx->{mainrepo} or die "no mainrepo in inbox\n";
my $exe = $cmd->[0];
my $pfx = $exe;
+ runnable_or_die($XAPIAN_COMPACT) if $opt->{compact};
if (ref($exe) eq 'CODE') {
$pfx = 'CODE';
require Search::Xapian::WritableDatabase;
} else {
- which($exe) or die "$exe not found in PATH\n";
+ runnable_or_die($exe);
}
$ibx->umask_prepare;
my $old = $ibx->search->xdir(1);
@@ -107,11 +117,12 @@ sub cpdb {
my ($args, $env, $opt) = @_;
my ($old, $new) = @$args;
my $src = Search::Xapian::Database->new($old);
+ my $tmp = $opt->{compact} ? "$new.compact" : $new;
# like copydatabase(1), be sure we don't overwrite anything in case
# of other bugs:
my $creat = Search::Xapian::DB_CREATE();
- my $dst = Search::Xapian::WritableDatabase->new($new, $creat);
+ my $dst = Search::Xapian::WritableDatabase->new($tmp, $creat);
my ($it, $end);
do {
@@ -140,6 +151,25 @@ # the Perl APIs don't expose iterators for them
# (and public-inbox does not use those features)
};
} while (cpdb_retryable($src, $@));
+
+ return unless $opt->{compact};
+
+ $src = $dst = undef; # flushes and closes
+
+ # this is probably the best place to do xapian-compact
+ # since $dst isn't readable by HTTP or NNTP clients, yet:
+ my $cmd = [ $XAPIAN_COMPACT, '--no-renumber', $tmp, $new ];
+ my $rdr = {};
+ foreach my $fd (0..2) {
+ defined(my $dst = $opt->{$fd}) or next;
+ $rdr->{$fd} = $dst;
+ }
+ my $pid = spawn($cmd, $env, $rdr);
+ my $r = waitpid($pid, 0);
+ if ($? || $r != $pid) {
+ die join(' ', @$cmd)." failed: $? (pid=$pid, reaped=$r)\n";
+ }
+ remove_tree($tmp) or die "failed to remove $tmp: $!\n";
}
1;
diff --git a/script/public-inbox-xcpdb b/script/public-inbox-xcpdb
index d494991dd50e34724e5edf1f193feaf5f38c24d7..78d37da266153465878902475de3a40f0fd26521 100755
--- a/script/public-inbox-xcpdb
+++ b/script/public-inbox-xcpdb
@@ -2,17 +2,21 @@ #!/usr/bin/perl -w
# Copyright (C) 2019 all contributors
# License: AGPL-3.0+
# xcpdb: Xapian copy database, a wrapper around Xapian's copydatabase(1)
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
use PublicInbox::InboxWritable;
use PublicInbox::Xapcmd;
use PublicInbox::Admin;
PublicInbox::Admin::require_or_die('-search');
my $usage = "Usage: public-inbox-xcpdb INBOX_DIR\n";
+my $opt = {};
+GetOptions($opt, qw(compact)) or die "bad command-line args\n$usage";
my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV) or die $usage;
+
my $cmd = [ \&PublicInbox::Xapcmd::cpdb ];
open my $null, '>', '/dev/null' or die "failed to open /dev/null: $!\n";
-my $rdr = { 1 => fileno($null) };
+$opt->{1} = fileno($null);
foreach (@ibxs) {
my $ibx = PublicInbox::InboxWritable->new($_);
# we rely on --no-renumber to keep docids synched to NNTP
- PublicInbox::Xapcmd::run($ibx, $cmd, undef, $rdr);
+ PublicInbox::Xapcmd::run($ibx, $cmd, undef, $opt);
}