lazy load Xapian and make it optional for v2

[public-inbox.git] / script / public-inbox-index

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 52d6ba70af7a8401db7311ca89a66406de4b34a1..53def9a7253d918f9a68db705baea8fd9fdfcffd 100755 (executable)
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -9,12 +9,13 @@
 use strict;
 use warnings;
 use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-use Cwd 'abs_path';
 my $usage = "public-inbox-index REPO_DIR";
 use PublicInbox::Config;
+use PublicInbox::Admin qw(resolve_repo_dir);
+
 my $config = eval { PublicInbox::Config->new } || eval {
        warn "public-inbox unconfigured for serving, indexing anyways...\n";
-       {}
+       undef;
 };
 eval { require PublicInbox::SearchIdx };
 if ($@) {
@@ -23,47 +24,20 @@ if ($@) {
 }
 
 my $reindex;
-my $regen;
+my $prune;
 my $jobs = undef;
+my $indexlevel;
 my %opts = (
        '--reindex' => \$reindex,
-       '--regenerate' => \$regen,
        '--jobs|j=i' => \$jobs,
+       '--prune' => \$prune,
+        'L|indexlevel=s' => \$indexlevel,
 );
 GetOptions(%opts) or die "bad command-line args\n$usage";
-die "--jobs must be positive\n" if defined $jobs && $jobs <= 0;
+die "--jobs must be positive\n" if defined $jobs && $jobs < 0;
 
 my @dirs;
 
-sub resolve_repo_dir {
-       my ($cd) = @_;
-       my $prefix = defined $cd ? $cd : './';
-       if (-d $prefix && -f "$prefix/inbox.lock") { # v2
-               return abs_path($prefix);
-       }
-
-       my @cmd = qw(git rev-parse --git-dir);
-       my $cmd = join(' ', @cmd);
-       my $pid = open my $fh, '-|';
-       defined $pid or die "forking $cmd failed: $!\n";
-       if ($pid == 0) {
-               if (defined $cd) {
-                       chdir $cd or die "chdir $cd failed: $!\n";
-               }
-               exec @cmd;
-               die "Failed to exec $cmd: $!\n";
-       } else {
-               my $dir = eval {
-                       local $/;
-                       <$fh>;
-               };
-               close $fh or die "error in $cmd: $!\n";
-               chomp $dir;
-               return abs_path($cd) if ($dir eq '.' && defined $cd);
-               abs_path($dir);
-       }
-}
-
 if (@ARGV) {
        @dirs = map { resolve_repo_dir($_) } @ARGV;
 } else {
@@ -73,58 +47,58 @@ if (@ARGV) {
 sub usage { print STDERR "Usage: $usage\n"; exit 1 }
 usage() unless @dirs;
 
-foreach my $k (keys %$config) {
-       $k =~ /\Apublicinbox\.([^\.]+)\.mainrepo\z/ or next;
-       my $name = $1;
-       my $v = $config->{$k};
+defined($config) and $config->each_inbox(sub {
+       my ($ibx) = @_;
+
        for my $i (0..$#dirs) {
-               next if $dirs[$i] ne $v;
-               my $ibx = $config->lookup_name($name);
-               $dirs[$i] = $ibx if $ibx;
+               next if $dirs[$i] ne $ibx->{mainrepo};
+               $dirs[$i] = $ibx;
        }
-}
+});
 
 foreach my $dir (@dirs) {
-       if (!ref($dir) && -f "$dir/inbox.lock") { # v2
-               my $ibx = { mainrepo => $dir, name => 'unnamed' };
+       if (!ref($dir)) {
+               unless (-d $dir) {
+                       die "$dir does not appear to be an inbox repository\n";
+               }
+               my $ibx = {
+                       mainrepo => $dir,
+                       name => 'unnamed',
+                       indexlevel => $indexlevel,
+                       version => -f "$dir/inbox.lock" ? 2 : 1,
+               };
                $dir = PublicInbox::Inbox->new($ibx);
+       } elsif (defined $indexlevel && !defined($dir->{indexlevel})) {
+               # XXX: users can shoot themselves in the foot, with this...
+               $dir->{indexlevel} = $indexlevel;
        }
-       index_dir($dir);
+
+       index_inbox($dir);
 }
 
-sub index_dir {
+sub index_inbox {
        my ($repo) = @_;
-       if (!ref $repo && ! -d $repo) {
-               die "$repo does not appear to be an inbox repository\n";
-       }
        if (ref($repo) && ($repo->{version} || 1) == 2) {
                eval { require PublicInbox::V2Writable };
                die "v2 requirements not met: $@\n" if $@;
                my $v2w = eval {
-                       local $ENV{NPROC} = $jobs;
-                       PublicInbox::V2Writable->new($repo);
+                       PublicInbox::V2Writable->new($repo, {nproc=>$jobs});
                };
                if (defined $jobs) {
-                       if ($jobs == 1) {
+                       if ($jobs == 0) {
                                $v2w->{parallel} = 0;
                        } else {
                                my $n = $v2w->{partitions};
-                               if ($jobs != $n) {
+                               if ($jobs != ($n + 1)) {
                                        warn
 "Unable to respect --jobs=$jobs, inbox was created with $n partitions\n";
                                }
                        }
                }
-               my $mm = $repo->mm;
-               my (undef, $max) = $mm->minmax if $mm;
-               if (defined($max) && !$reindex && !$regen) {
-                       die
-"v2 inboxes may only use --reindex and/or --regenerate once\n".
-"msgmap.sqlite3 is initialized\n";
-               }
-
-               $v2w->reindex($regen);
-               $v2w->done;
+               local $SIG{__WARN__} = sub {
+                       print STDERR $v2w->{current_info}, ': ', @_;
+               };
+               $v2w->index_sync({ reindex => $reindex, prune => $prune });
        } else {
                my $s = PublicInbox::SearchIdx->new($repo, 1);
                $s->index_sync({ reindex => $reindex });