X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=56df5bfec6faed0a9338c88cecf5230607dcf3a9;hb=8a66a8d396c6cff82e6041d107d7fb842db6d602;hp=b353093e49250e2296f6c12edaee656dd40fb064;hpb=20759636853f59b1d59cd979e72375422de29059;p=public-inbox.git

diff --git a/script/public-inbox-index b/script/public-inbox-index
index b353093e..56df5bfe 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,95 +1,90 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2020 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.
+# Basic tool to create a Xapian search index for a public-inbox.
 # Usage with libeatmydata <https://www.flamingspork.com/projects/libeatmydata/>
-# highly recommended: eatmydata public-inbox-index REPO_DIR
+# highly recommended: eatmydata public-inbox-index INBOX_DIR
 
 use strict;
 use warnings;
 use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-my $usage = "public-inbox-index REPO_DIR";
-use PublicInbox::Config;
-use PublicInbox::Admin qw(resolve_repo_dir);
+my $usage = "public-inbox-index INBOX_DIR";
+use PublicInbox::Admin;
+PublicInbox::Admin::require_or_die('-index');
+use PublicInbox::Xapcmd;
 
-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";
-	exit 1;
-}
+my $compact_opt;
+my $opt = { quiet => -1, compact => 0, maxsize => undef, fsync => 1 };
+GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
+		fsync|sync! xapianonly|xapian-only
+		indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s
+		sequentialshard|seq-shard|sequential-shard))
+	or die "bad command-line args\n$usage";
+die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
 
-my $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 && $jobs < 0;
+if ($opt->{compact}) {
+	require PublicInbox::Xapcmd;
+	PublicInbox::Xapcmd::check_compact();
+	$compact_opt = { -coarse_lock => 1, compact => 1 };
+	if (defined(my $jobs = $opt->{jobs})) {
+		$compact_opt->{jobs} = $jobs;
+	}
+}
 
-my @dirs;
+my $cfg = PublicInbox::Config->new;
+my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg);
+PublicInbox::Admin::require_or_die('-index');
+unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
 
-if (@ARGV) {
-	@dirs = map { resolve_repo_dir($_) } @ARGV;
-} else {
-	@dirs = (resolve_repo_dir());
+my $max_size = $opt->{maxsize} // $cfg->{lc('publicInbox.indexMaxSize')};
+if (defined $max_size) {
+	PublicInbox::Admin::parse_unsigned(\$max_size) or
+		die "`publicInbox.indexMaxSize=$max_size' not parsed\n";
 }
 
-sub usage { print STDERR "Usage: $usage\n"; exit 1 }
-usage() unless @dirs;
+if (my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')}) {
+	PublicInbox::Admin::parse_unsigned(\$bs) or
+		die "`publicInbox.indexBatchSize=$bs' not parsed\n";
+	$PublicInbox::SearchIdx::BATCH_BYTES = $bs;
+}
 
-defined($config) and $config->each_inbox(sub {
-	my ($ibx) = @_;
+my $s = $opt->{sequentialshard} //
+			$cfg->{lc('publicInbox.indexSequentialShard')};
+if (defined $s) {
+	my $v = $cfg->git_bool($s);
+	defined($v) or
+		die "`publicInbox.indexSequentialShard=$s' not boolean\n";
+	$opt->{sequentialshard} = $v;
+}
 
-	for my $i (0..$#dirs) {
-		next if $dirs[$i] ne $ibx->{mainrepo};
-		$dirs[$i] = $ibx;
-	}
-});
+my $mods = {};
+foreach my $ibx (@ibxs) {
+	# XXX: users can shoot themselves in the foot, with opt->{indexlevel}
+	$ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapianonly} ?
+			'full' : PublicInbox::Admin::detect_indexlevel($ibx));
+	$ibx->{index_max_size} = $max_size;
+	PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
+}
 
-foreach my $dir (@dirs) {
-	if (!ref($dir) && -f "$dir/inbox.lock") { # v2
-		my $ibx = { mainrepo => $dir, name => 'unnamed' };
-		$dir = PublicInbox::Inbox->new($ibx);
+PublicInbox::Admin::require_or_die(keys %$mods);
+PublicInbox::Admin::progress_prepare($opt);
+for my $ibx (@ibxs) {
+	$ibx = PublicInbox::InboxWritable->new($ibx);
+	if ($opt->{compact} >= 2) {
+		PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
 	}
-	index_dir($dir);
-}
+	$ibx->{-no_fsync} = 1 if !$opt->{fsync};
 
-sub index_dir {
-	my ($repo) = @_;
-	if (!ref $repo && ! -d $repo) {
-		die "$repo does not appear to be an inbox repository\n";
+	my $ibx_opt = $opt;
+	if (defined(my $s = $ibx->{indexsequentialshard})) {
+		defined(my $v = $cfg->git_bool($s)) or die <<EOL;
+publicInbox.$ibx->{name}.indexSequentialShard not boolean
+EOL
+		$ibx_opt = { %$opt, sequentialshard => $v };
 	}
-	if (ref($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 => $reindex });
+	PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
+	if ($compact_opt) {
+		local $compact_opt->{jobs} = 0 if $ibx_opt->{sequentialshard};
+		PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
 	}
 }