X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=5adb6e741eff8f2578a780bd40738cd7c42ee7a6;hb=65323f060a3db731bb9fafa004336eeb4bbb8f00;hp=46584c1fff3502c71a087240fa0e1ab6215a24b1;hpb=e983376326eab20daac9c2bfbb65b88c4fd248a2;p=public-inbox.git diff --git a/script/public-inbox-index b/script/public-inbox-index index 46584c1f..5adb6e74 100755 --- a/script/public-inbox-index +++ b/script/public-inbox-index @@ -1,63 +1,93 @@ #!/usr/bin/perl -w -# Copyright (C) 2015 all contributors -# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) +# Copyright (C) 2015-2018 all contributors +# License: AGPL-3.0+ # Basic tool to create a Xapian search index for a git repository # configured for public-inbox. # Usage with 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); +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 $0\n"; exit 1; } -my @dirs; -sub resolve_git_dir { - my ($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; - } -} +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 && $jobs < 0; + +my @dirs; if (@ARGV) { - @dirs = map { resolve_git_dir($_) } @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 $dir (@dirs) { + if (!ref($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"; - - 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 { + $jobs and local $ENV{NPROC} = $jobs; + PublicInbox::V2Writable->new($repo); + }; + 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"; + } + } + } + $v2w->index_sync({ reindex => $reindex, prune => $prune }); + } else { + my $s = PublicInbox::SearchIdx->new($repo, 1); + $s->index_sync({ reindex => $reindex }); + } }