treewide: replace {-inbox} with {ibx} for consistency

[public-inbox.git] / lib / PublicInbox / Admin.pm

diff --git a/lib/PublicInbox/Admin.pm b/lib/PublicInbox/Admin.pm
index af2b3da95c3406bfe3dd53fdd062b08895dd6f3a..9d48e5ebee4131553e6442e135d7a0d642e55b58 100644 (file)
--- a/lib/PublicInbox/Admin.pm
+++ b/lib/PublicInbox/Admin.pm
@@ -48,13 +48,14 @@ sub resolve_repo_dir {
 sub detect_indexlevel ($) {
        my ($ibx) = @_;
 
-       # brand new or never before indexed inboxes default to full
-       return 'full' unless $ibx->over;
-       delete $ibx->{over}; # don't leave open FD lying around
+       my $over = $ibx->over;
+       my $srch = $ibx->search;
+       delete @$ibx{qw(over search)}; # don't leave open FDs lying around
 
+       # brand new or never before indexed inboxes default to full
+       return 'full' unless $over;
        my $l = 'basic';
-       my $srch = $ibx->search or return $l;
-       delete $ibx->{search}; # don't leave open FD lying around
+       return $l unless $srch;
        if (my $xdb = $srch->xdb) {
                $l = 'full';
                my $m = $xdb->get_metadata('indexlevel');
@@ -65,6 +66,7 @@ sub detect_indexlevel ($) {
 $ibx->{inboxdir} has unexpected indexlevel in Xapian: $m
 
                }
+               $ibx->{-skip_docdata} = 1 if $xdb->get_metadata('skip_docdata');
        }
        $l;
 }
@@ -95,12 +97,14 @@ sub resolve_inboxes ($;$$) {
        my $min_ver = $opt->{-min_inbox_version} || 0;
        my (@old, @ibxs);
        my %dir2ibx;
+       my $all = $opt->{all} ? [] : undef;
        if ($cfg) {
                $cfg->each_inbox(sub {
                        my ($ibx) = @_;
                        my $path = abs_path($ibx->{inboxdir});
                        if (defined($path)) {
                                $dir2ibx{$path} = $ibx;
+                               push @$all, $ibx if $all;
                        } else {
                                warn <<EOF;
 W: $ibx->{name} $ibx->{inboxdir}: $!
@@ -108,10 +112,9 @@ EOF
                        }
                });
        }
-       if ($opt->{all}) {
-               my @all = values %dir2ibx;
-               @all = grep { $_->version >= $min_ver } @all;
-               push @ibxs, @all;
+       if ($all) {
+               @$all = grep { $_->version >= $min_ver } @$all;
+               @ibxs = @$all;
        } else { # directories specified on the command-line
                my $i = 0;
                my @dirs = @$argv;
@@ -129,7 +132,7 @@ EOF
                }
        }
        if (@old) {
-               die "inboxes $min_ver inboxes not supported by $0\n\t",
+               die "-V$min_ver inboxes not supported by $0\n\t",
                    join("\n\t", @old), "\n";
        }
        @ibxs;
@@ -207,6 +210,9 @@ sub index_terminate {
 sub index_inbox {
        my ($ibx, $im, $opt) = @_;
        my $jobs = delete $opt->{jobs} if $opt;
+       if (my $pr = $opt->{-progress}) {
+               $pr->("indexing $ibx->{inboxdir} ...\n");
+       }
        local %SIG = %SIG;
        setup_signals(\&index_terminate, $ibx);
        if (ref($ibx) && $ibx->version == 2) {
@@ -219,9 +225,9 @@ sub index_inbox {
                                $v2w->{parallel} = 0;
                        } else {
                                my $n = $v2w->{shards};
-                               if ($jobs != ($n + 1) && !$opt->{reshard}) {
+                               if ($jobs < ($n + 1) && !$opt->{reshard}) {
                                        warn
-"Unable to respect --jobs=$jobs, inbox was created with $n shards\n";
+"Unable to respect --jobs=$jobs on index, inbox was created with $n shards\n";
                                }
                        }
                }
@@ -256,13 +262,49 @@ sub progress_prepare ($) {
 
 # same unit factors as git:
 sub parse_unsigned ($) {
-       my ($max_size) = @_;
+       my ($val) = @_;
 
-       $$max_size =~ /\A([0-9]+)([kmg])?\z/i or return;
+       $$val =~ /\A([0-9]+)([kmg])?\z/i or return;
        my ($n, $unit_factor) = ($1, $2 // '');
        my %u = ( k => 1024, m => 1024**2, g => 1024**3 );
-       $$max_size = $n * ($u{lc($unit_factor)} // 1);
+       $$val = $n * ($u{lc($unit_factor)} // 1);
        1;
 }
 
+sub index_prepare ($$) {
+       my ($opt, $cfg) = @_;
+       my $env;
+       if ($opt->{compact}) {
+               require PublicInbox::Xapcmd;
+               PublicInbox::Xapcmd::check_compact();
+               $opt->{compact_opt} = { -coarse_lock => 1, compact => 1 };
+               if (defined(my $jobs = $opt->{jobs})) {
+                       $opt->{compact_opt}->{jobs} = $jobs;
+               }
+       }
+       for my $k (qw(max_size batch_size)) {
+               my $git_key = "publicInbox.index".ucfirst($k);
+               $git_key =~ s/_([a-z])/\U$1/g;
+               defined(my $v = $opt->{$k} // $cfg->{lc($git_key)}) or next;
+               parse_unsigned(\$v) or die "`$git_key=$v' not parsed\n";
+               $v > 0 or die "`$git_key=$v' must be positive\n";
+               $opt->{$k} = $v;
+       }
+
+       # out-of-the-box builds of Xapian 1.4.x are still limited to 32-bit
+       # https://getting-started-with-xapian.readthedocs.io/en/latest/concepts/indexing/limitations.html
+       $opt->{batch_size} and
+               $env = { XAPIAN_FLUSH_THRESHOLD => '4294967295' };
+
+       for my $k (qw(sequential_shard)) {
+               my $git_key = "publicInbox.index".ucfirst($k);
+               $git_key =~ s/_([a-z])/\U$1/g;
+               defined(my $s = $opt->{$k} // $cfg->{lc($git_key)}) or next;
+               defined(my $v = $cfg->git_bool($s))
+                                       or die "`$git_key=$s' not boolean\n";
+               $opt->{$k} = $v;
+       }
+       $env;
+}
+
 1;