index: update [extindex "all"] by default, support -E

In most cases, this ensures users will only have to opt-in to
using -extindex once and won't have to issue extra commands
to keep external indices up-to-date when using
public-inbox-index.

Since we support arbitrary numbers of external indices for
ease-of-development, we'll support repeating "-E"
("--update-extindex=") in case users want to test changes in
parallel.

diff --git a/Documentation/public-inbox-index.pod b/Documentation/public-inbox-index.pod
index 0848e8604c8aa842a9fdcda6aec4026a45f9442b..2d5df93087796424455a4118835580f8ff3846be 100644 (file)
--- a/Documentation/public-inbox-index.pod
+++ b/Documentation/public-inbox-index.pod
@@ -162,6 +162,23 @@ See L<public-inbox-init(1)/--skip-docdata> for description and caveats.
 
 Available in public-inbox 1.6.0+.
 
+=item --update-extindex=EXTINDEX, -E
+
+Update the given external index (L<public-inbox-extindex-format(5)>.
+Either the configured section name (e.g. C<all>) or a directory name
+may be specified.
+
+Defaults to C<all> if C<[extindex "all"]> is configured,
+otherwise no external indices are updated.
+
+May be specified multiple times in rare cases where multiple
+external indices are configured.
+
+=item --no-update-extindex
+
+Do not update the C<all> external index by default.  This negates
+all uses of C<-E> / C<--update-extindex=> on the command-line.
+
 =back
 
 =head1 FILES
@@ -297,4 +314,4 @@ License: AGPL-3.0+ L<https://www.gnu.org/licenses/agpl-3.0.txt>
 
 =head1 SEE ALSO
 
-L<Search::Xapian>, L<DBD::SQLite>
+L<Search::Xapian>, L<DBD::SQLite>, L<public-inbox-extindex-format(5)>

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 8a61817ce7f012401b9c606f3c54ff7519263c8d..f10bb5adb4110ad69552cfa7a221b09a26d3ec48 100755 (executable)
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -17,7 +17,7 @@ options:
 
   --no-fsync          speed up indexing, risk corruption on power outage
   -L LEVEL            `basic', `medium', or `full' (default: full)
-  -E EIDX             update EIDX (e.g. `all')
+  -E EXTINDEX         update extindex (default: `all')
   --all               index all configured inboxes
   --compact | -c      run public-inbox-compact(1) after indexing
   --sequential-shard  index Xapian shards sequentially for slow storage
@@ -32,12 +32,16 @@ options:
 BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes)
 See public-inbox-index(1) man page for full documentation.
 EOF
-my $opt = { quiet => -1, compact => 0, max_size => undef, fsync => 1 };
+my $opt = {
+       quiet => -1, compact => 0, max_size => undef, fsync => 1,
+       'update-extindex' => [], # ":s@" optional arg sets '' if no arg given
+};
 GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
                fsync|sync! xapian_only|xapian-only
                indexlevel|index-level|L=s max_size|max-size=s
                batch_size|batch-size=s
                sequential_shard|seq-shard|sequential-shard
+               no-update-extindex update-extindex|E=s@
                skip-docdata all help|h))
        or die $help;
 if ($opt->{help}) { print $help; exit 0 };
@@ -56,7 +60,31 @@ my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
 PublicInbox::Admin::require_or_die('-index');
 unless (@ibxs) { print STDERR $help; exit 1 }
 
+my (@eidx_dir, %eidx_seen);
+my $update_extindex = $opt->{'update-extindex'};
+if (!scalar(@$update_extindex) && (my $ALL = $cfg->ALL)) {
+       # extindex and normal inboxes may have different owners
+       push(@$update_extindex, 'all') if -w $ALL->{topdir};
+}
+@$update_extindex = () if $opt->{'no-update-extindex'};
+if (scalar @$update_extindex) {
+       PublicInbox::Admin::require_or_die('-search');
+       require PublicInbox::ExtSearchIdx;
+}
+for my $ei_name (@$update_extindex) {
+       my $es = $cfg->lookup_ei($ei_name);
+       my $topdir;
+       if (!$es && -d $ei_name) { # allow dirname or config section name
+               $topdir = $ei_name;
+       } elsif ($es) {
+               $topdir = $es->{topdir};
+       } else {
+               die "extindex `$ei_name' not configured or found\n";
+       }
+       $eidx_seen{$topdir} //= push(@eidx_dir, $topdir);
+}
 my $mods = {};
+my @eidx_unconfigured;
 foreach my $ibx (@ibxs) {
        # detect_indexlevel may also set $ibx->{-skip_docdata}
        my $detected = PublicInbox::Admin::detect_indexlevel($ibx);
@@ -64,7 +92,14 @@ foreach my $ibx (@ibxs) {
        $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ?
                        'full' : $detected);
        PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
+       if (@eidx_dir && $ibx->{-unconfigured}) {
+               push @eidx_unconfigured, "  $ibx->{inboxdir}\n";
+       }
 }
+warn <<EOF if @eidx_unconfigured;
+The following inboxes are unconfigured and will not be updated in
+@$update_extindex:\n@eidx_unconfigured
+EOF
 
 # "Search::Xapian" includes SWIG "Xapian", too:
 $opt->{compact} = 0 if !$mods->{'Search::Xapian'};
@@ -96,4 +131,12 @@ EOL
                local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard};
                PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
        }
+       next if $ibx->{-unconfigured};
+       last if $ibx_opt->{quit};
+       for my $dir (@eidx_dir) {
+               my $eidx = PublicInbox::ExtSearchIdx->new($dir);
+               $eidx->attach_inbox($ibx);
+               $eidx->eidx_sync($ibx_opt);
+               last if $ibx_opt->{quit};
+       }
 }