X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=53def9a7253d918f9a68db705baea8fd9fdfcffd;hb=0b1de991a099b5e8b9a9e3e85b5eaaacc9362dbb;hp=61f21d7060c345378ab1e96893e4b589968a89b5;hpb=3f4c9ce3d2c0796c6c3f352b5b586ddd7a85ffb0;p=public-inbox.git

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 61f21d70..53def9a7 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,16 +1,22 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # 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);
-my $usage = "public-inbox-index GIT_DIR";
+my $usage = "public-inbox-index REPO_DIR";
 use PublicInbox::Config;
+use PublicInbox::Admin qw(resolve_repo_dir);
+
+my $config = eval { PublicInbox::Config->new } || eval {
+	warn "public-inbox unconfigured for serving, indexing anyways...\n";
+	undef;
+};
 eval { require PublicInbox::SearchIdx };
 if ($@) {
 	print STDERR "Search::Xapian required for $0\n";
@@ -18,51 +24,83 @@ if ($@) {
 }
 
 my $reindex;
-my %opts = ( '--reindex' => \$reindex );
+my $prune;
+my $jobs = undef;
+my $indexlevel;
+my %opts = (
+	'--reindex' => \$reindex,
+	'--jobs|j=i' => \$jobs,
+	'--prune' => \$prune,
+        'L|indexlevel=s' => \$indexlevel,
+);
 GetOptions(%opts) or die "bad command-line args\n$usage";
+die "--jobs must be positive\n" if defined $jobs && $jobs < 0;
 
 my @dirs;
 
-sub resolve_git_dir {
-	my ($cd) = @_;
-	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 $cd if ($dir eq '.' && defined $cd);
-		$dir;
-	}
-}
-
 if (@ARGV) {
-	@dirs = map { resolve_git_dir($_) } @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 }
 usage() unless @dirs;
 
+defined($config) and $config->each_inbox(sub {
+	my ($ibx) = @_;
+
+	for my $i (0..$#dirs) {
+		next if $dirs[$i] ne $ibx->{mainrepo};
+		$dirs[$i] = $ibx;
+	}
+});
+
 foreach my $dir (@dirs) {
-	index_dir($dir);
+	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} = $indexlevel;
+	}
+
+	index_inbox($dir);
 }
 
-sub index_dir {
-	my ($git_dir) = @_;
-	-d $git_dir or die "$git_dir does not appear to be a git repository\n";
-	my $s = PublicInbox::SearchIdx->new($git_dir, 1);
-	$s->index_sync({ reindex => $reindex });
+sub index_inbox {
+	my ($repo) = @_;
+	if (ref($repo) && ($repo->{version} || 1) == 2) {
+		eval { require PublicInbox::V2Writable };
+		die "v2 requirements not met: $@\n" if $@;
+		my $v2w = eval {
+			PublicInbox::V2Writable->new($repo, {nproc=>$jobs});
+		};
+		if (defined $jobs) {
+			if ($jobs == 0) {
+				$v2w->{parallel} = 0;
+			} else {
+				my $n = $v2w->{partitions};
+				if ($jobs != ($n + 1)) {
+					warn
+"Unable to respect --jobs=$jobs, inbox was created with $n partitions\n";
+				}
+			}
+		}
+		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 });
+	}
 }