v2: support incremental indexing + purge

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

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 578d91d5bf50b767171b490594215b295a52e64f..73f88ac6bee72fd0eabc3497881cf42e3392cc97 100755 (executable)
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,24 +1,47 @@
 #!/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;
-my $usage = "public-inbox-index GIT_DIR";
+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;
+my $config = eval { PublicInbox::Config->new } || eval {
+       warn "public-inbox unconfigured for serving, indexing anyways...\n";
+       {}
+};
 eval { require PublicInbox::SearchIdx };
 if ($@) {
        print STDERR "Search::Xapian required for $0\n";
        exit 1;
 }
+
+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;
+
 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, '-|';
@@ -36,30 +59,65 @@ sub resolve_git_dir {
                };
                close $fh or die "error in $cmd: $!\n";
                chomp $dir;
-               return $cd if ($dir eq '.' && defined $cd);
-               $dir;
+               return abs_path($cd) if ($dir eq '.' && defined $cd);
+               abs_path($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;
 
+foreach my $k (keys %$config) {
+       $k =~ /\Apublicinbox\.([^\.]+)\.mainrepo\z/ or next;
+       my $name = $1;
+       my $v = $config->{$k};
+       for my $i (0..$#dirs) {
+               next if $dirs[$i] ne $v;
+               my $ibx = $config->lookup_name($name);
+               $dirs[$i] = $ibx if $ibx;
+       }
+}
+
 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) = @_;
-       -d $git_dir or die "$git_dir does not appear to be a git repository\n";
-
-       system('git', "--git-dir=$git_dir", 'update-server-info') and
-               die "git update-server-info failed for $git_dir";
-       my $s = PublicInbox::SearchIdx->new($git_dir, 1);
-       $s->index_sync;
+       my ($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);
+               };
+               if (defined $jobs) {
+                       if ($jobs == 1) {
+                               $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 });
+       }
 }