index: allow specifying --jobs=0 to disable multiprocess

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

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 594a3d9ca8dff6daf743e880b2cf72f7fb86a350..db7ebbab6421ec2cc1b849e4259b2ac82d6d745b 100755 (executable)
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -4,13 +4,13 @@
 # Basic tool to create a Xapian search index for a git repository
 # configured for public-inbox.
 # Usage with libeatmydata <https://www.flamingspork.com/projects/libeatmydata/>
-# highly recommended: eatmydata public-inbox-index GIT_DIR
+# highly recommended: eatmydata public-inbox-index REPO_DIR
 
 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 GIT_DIR";
+my $usage = "public-inbox-index REPO_DIR";
 use PublicInbox::Config;
 my $config = eval { PublicInbox::Config->new } || eval {
        warn "public-inbox unconfigured for serving, indexing anyways...\n";
@@ -23,13 +23,25 @@ if ($@) {
 }
 
 my $reindex;
-my %opts = ( '--reindex' => \$reindex );
+my $prune;
+my $jobs = undef;
+my %opts = (
+       '--reindex' => \$reindex,
+       '--jobs|j=i' => \$jobs,
+       '--prune' => \$prune,
+);
 GetOptions(%opts) or die "bad command-line args\n$usage";
+die "--jobs must be positive\n" if defined $jobs && $jobs < 0;
 
 my @dirs;
 
-sub resolve_git_dir {
+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, '-|';
@@ -53,9 +65,9 @@ sub resolve_git_dir {
 }
 
 if (@ARGV) {
-       @dirs = map { resolve_git_dir($_) } @ARGV;
+       @dirs = map { resolve_repo_dir($_) } @ARGV;
 } else {
-       @dirs = (resolve_git_dir());
+       @dirs = (resolve_repo_dir());
 }
 
 sub usage { print STDERR "Usage: $usage\n"; exit 1 }
@@ -73,14 +85,39 @@ foreach my $k (keys %$config) {
 }
 
 foreach my $dir (@dirs) {
+       if (!ref($dir) && -f "$dir/inbox.lock") { # v2
+               my $ibx = { mainrepo => $dir, name => 'unnamed' };
+               $dir = PublicInbox::Inbox->new($ibx);
+       }
        index_dir($dir);
 }
 
 sub index_dir {
-       my ($git_dir) = @_;
-       if (!ref $git_dir && ! -d $git_dir) {
-               die "$git_dir does not appear to be a git repository\n";
+       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 if $jobs;
+                       PublicInbox::V2Writable->new($repo);
+               };
+               if (defined $jobs) {
+                       if ($jobs == 0) {
+                               $v2w->{parallel} = 0;
+                       } else {
+                               my $n = $v2w->{partitions};
+                               if ($jobs != $n) {
+                                       warn
+"Unable to respect --jobs=$jobs, inbox was created with $n partitions\n";
+                               }
+                       }
+               }
+               $v2w->index_sync({ reindex => $reindex, prune => $prune });
+       } else {
+               my $s = PublicInbox::SearchIdx->new($repo, 1);
+               $s->index_sync({ reindex => $reindex });
        }
-       my $s = PublicInbox::SearchIdx->new($git_dir, 1);
-       $s->index_sync({ reindex => $reindex });
 }