extsearch: support publicinbox.*.boost parameter

This behaves identically the lei external "boost" parameter in
prioritizing raw messages for extindex.

Relying exclusively on the config file order doesn't work well
for mirrors since it's impossible to guarantee config file
ordering via grokmirror hooks.

Config file ordering remains the default if boost is
unconfigured, or in case of ties.

Note: I chose the name "boost" rather than "priority" or "rank"
since I always get confused by whether higher or lower numbers
take precedence when it comes to kernel scheduling.  "weight" is
also a part of Xapian API terminology, which we currently do not
expose to configuration (but may in the future).

diff --git a/Documentation/public-inbox-config.pod b/Documentation/public-inbox-config.pod
index 05d9ca6266cd4ca3fd1b1fe4509c59455d43ab4a..5b86ef6cbfcd0152cb8ff41a285c28e31835fea3 100644 (file)
--- a/Documentation/public-inbox-config.pod
+++ b/Documentation/public-inbox-config.pod
@@ -124,6 +124,14 @@ allow for searching for phrases using quoted text.
 
 Default: C<full>
 
+=item publicinbox.<name>.boost
+
+Control indexing order for L<public-inbox-extindex(1)>, with ties
+broken by config file order.  This only affects indexing and does
+not affect messages which are already indexed.
+
+Default: C<0>
+
 =item publicinbox.<name>.indexSequentialShard
 
 See L<public-inbox-index(1)/publicInbox.indexSequentialShard>

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index 8e46328dbd70288291b423236c8a4c049eceb26a..7aa1f6c898ab7f75c3d2da3955a1f182fda7c501 100644 (file)
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -429,7 +429,7 @@ sub _fill_ibx {
                $ibx->{$k} = $v if defined $v;
        }
        for my $k (qw(filter inboxdir newsgroup replyto httpbackendmax feedmax
-                       indexlevel indexsequentialshard)) {
+                       indexlevel indexsequentialshard boost)) {
                my $v = get_1($self, $pfx, $k) // next;
                $ibx->{$k} = $v;
        }

diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 0e27bba6573f91d125d95d1933b04c0fd5eaeb3a..357312b8d602591b4e89642964cf9e646b2c7b7c 100644 (file)
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -44,7 +44,7 @@ sub new {
                topdir => $dir,
                creat => $opt->{creat},
                ibx_map => {}, # (newsgroup//inboxdir) => $ibx
-               ibx_list => [],
+               ibx_cfg => [], # by config section order
                indexlevel => $l,
                transact_bytes => 0,
                total_bytes => 0,
@@ -62,7 +62,8 @@ sub new {
 sub attach_inbox {
        my ($self, $ibx) = @_;
        $self->{ibx_map}->{$ibx->eidx_key} //= do {
-               push @{$self->{ibx_list}}, $ibx;
+               delete $self->{-ibx_ary}; # invalidate cache
+               push @{$self->{ibx_cfg}}, $ibx;
                $ibx;
        }
 }
@@ -388,7 +389,7 @@ sub _ibx_for ($$$) {
        my ($self, $sync, $smsg) = @_;
        my $ibx_id = delete($smsg->{ibx_id}) // die '{ibx_id} unset';
        my $pos = $sync->{id2pos}->{$ibx_id} // die "$ibx_id no pos";
-       $self->{ibx_list}->[$pos] // die "BUG: ibx for $smsg->{blob} not mapped"
+       $self->{-ibx_ary}->[$pos] // die "BUG: ibx for $smsg->{blob} not mapped"
 }
 
 sub _fd_constrained ($) {
@@ -402,7 +403,7 @@ sub _fd_constrained ($) {
                        chomp($soft = `sh -c 'ulimit -n'`);
                }
                if (defined($soft)) {
-                       my $want = scalar(@{$self->{ibx_list}}) + 64; # estimate
+                       my $want = scalar(@{$self->{-ibx_ary}}) + 64; # estimate
                        my $ret = $want > $soft;
                        if ($ret) {
                                warn <<EOF;
@@ -524,10 +525,10 @@ BUG? #$docid $smsg->{blob} is not referenced by inboxes during reindex
                return;
        }
 
-       # we sort {xr3r} in the reverse order of {ibx_list} so we can
+       # we sort {xr3r} in the reverse order of ibx_sorted so we can
        # hit the common case in _reindex_finalize without rereading
        # from git (or holding multiple messages in memory).
-       my $id2pos = $sync->{id2pos}; # index in {ibx_list}
+       my $id2pos = $sync->{id2pos}; # index in ibx_sorted
        @$xr3 = sort {
                $id2pos->{$b->[0]} <=> $id2pos->{$a->[0]}
                                ||
@@ -621,6 +622,17 @@ EOF
        undef;
 }
 
+sub ibx_sorted ($) {
+       my ($self) = @_;
+       $self->{-ibx_ary} //= do {
+               # highest boost first, stable for config-ordering tiebreaker
+               use sort 'stable';
+               [ sort {
+                       ($b->{boost} // 0) <=> ($a->{boost} // 0)
+                 } @{$self->{ibx_cfg}} ];
+       }
+}
+
 sub eidxq_process ($$) { # for reindexing
        my ($self, $sync) = @_;
 
@@ -638,7 +650,7 @@ sub eidxq_process ($$) { # for reindexing
        $sync->{id2pos} //= do {
                my %id2pos;
                my $pos = 0;
-               $id2pos{$_->{-ibx_id}} = $pos++ for @{$self->{ibx_list}};
+               $id2pos{$_->{-ibx_id}} = $pos++ for (@{ibx_sorted($self)});
                \%id2pos;
        };
        my ($del, $iter);
@@ -829,7 +841,7 @@ sub eidx_reindex {
                warn "E: aborting --reindex\n";
                return;
        }
-       for my $ibx (@{$self->{ibx_list}}) {
+       for my $ibx (@{ibx_sorted($self)}) {
                _reindex_inbox($self, $sync, $ibx);
                last if $sync->{quit};
        }
@@ -959,7 +971,7 @@ sub eidx_sync { # main entry point
        local $SIG{QUIT} = $quit;
        local $SIG{INT} = $quit;
        local $SIG{TERM} = $quit;
-       for my $ibx (@{$self->{ibx_list}}) {
+       for my $ibx (@{ibx_sorted($self)}) {
                $ibx->{-ibx_id} //= $self->{oidx}->ibx_id($ibx->eidx_key);
        }
        if (delete($opt->{dedupe})) {
@@ -973,7 +985,7 @@ sub eidx_sync { # main entry point
 
        # don't use $_ here, it'll get clobbered by reindex_checkpoint
        if ($opt->{scan} // 1) {
-               for my $ibx (@{$self->{ibx_list}}) {
+               for my $ibx (@{ibx_sorted($self)}) {
                        last if $sync->{quit};
                        sync_inbox($self, $sync, $ibx);
                }
@@ -1115,7 +1127,7 @@ sub idx_init { # similar to V2Writable
                }
                undef $dh;
        }
-       for my $ibx (@{$self->{ibx_list}}) {
+       for my $ibx (@{ibx_sorted($self)}) {
                # create symlinks for multi-pack-index
                $git_midx += symlink_packs($ibx, $pd);
                # add new lines to our alternates file
@@ -1180,7 +1192,8 @@ sub eidx_reload { # -extindex --watch SIGHUP handler
                my $pr = $self->{-watch_sync}->{-opt}->{-progress};
                $pr->('reloading ...') if $pr;
                delete $self->{-resync_queue};
-               @{$self->{ibx_list}} = ();
+               delete $self->{-ibx_ary};
+               $self->{ibx_cfg} = [];
                %{$self->{ibx_map}} = ();
                delete $self->{-watch_sync}->{id2pos};
                my $cfg = PublicInbox::Config->new;
@@ -1194,7 +1207,7 @@ sub eidx_reload { # -extindex --watch SIGHUP handler
 
 sub eidx_resync_start ($) { # -extindex --watch SIGUSR1 handler
        my ($self) = @_;
-       $self->{-resync_queue} //= [ @{$self->{ibx_list}} ];
+       $self->{-resync_queue} //= [ @{ibx_sorted($self)} ];
        PublicInbox::DS::requeue($self); # trigger our ->event_step
 }
 
@@ -1225,9 +1238,9 @@ sub eidx_watch { # public-inbox-extindex --watch main loop
        require PublicInbox::Sigfd;
        my $idler = PublicInbox::InboxIdle->new($self->{cfg});
        if (!$self->{cfg}) {
-               $idler->watch_inbox($_) for @{$self->{ibx_list}};
+               $idler->watch_inbox($_) for (@{ibx_sorted($self)});
        }
-       $_->subscribe_unlock(__PACKAGE__, $self) for @{$self->{ibx_list}};
+       $_->subscribe_unlock(__PACKAGE__, $self) for (@{ibx_sorted($self)});
        my $pr = $opt->{-progress};
        $pr->("performing initial scan ...\n") if $pr;
        my $sync = eidx_sync($self, $opt); # initial sync

diff --git a/t/extsearch.t b/t/extsearch.t
index 5f0cd8662bfc0a102bbc32223e4c42a0fa199a30..46a6f2ec5eb80b1f81a911486839c42cc5b0a654 100644 (file)
--- a/t/extsearch.t
+++ b/t/extsearch.t
@@ -60,6 +60,38 @@ ok(run_script([qw(-extindex --all), "$home/extindex"]), 'extindex init');
        ok($es->has_threadid, '->has_threadid');
 }
 
+if ('with boost') {
+       xsys([qw(git config publicinbox.v1test.boost), 10],
+               { GIT_CONFIG => $cfg_path });
+       ok(run_script([qw(-extindex --all), "$home/extindex-b"]),
+               'extindex init with boost');
+       my $es = PublicInbox::ExtSearch->new("$home/extindex-b");
+       my $smsg = $es->over->get_art(1);
+       ok($smsg, 'got first article');
+       my $xref3 = $es->over->get_xref3($smsg->{num});
+       my @v1 = grep(/\Av1/, @$xref3);
+       my @v2 = grep(/\Av2/, @$xref3);
+       like($v1[0], qr/\Av1\.example.*?\b\Q$smsg->{blob}\E\b/,
+               'smsg->{blob} respected boost');
+       is(scalar(@$xref3), 2, 'only to entries');
+       undef $es;
+
+       xsys([qw(git config publicinbox.v2test.boost), 20],
+               { GIT_CONFIG => $cfg_path });
+       ok(run_script([qw(-extindex --all --reindex), "$home/extindex-b"]),
+               'extindex --reindex with altered boost');
+
+       $es = PublicInbox::ExtSearch->new("$home/extindex-b");
+       $smsg = $es->over->get_art(1);
+       like($v2[0], qr/\Av2\.example.*?\b\Q$smsg->{blob}\E\b/,
+                       'smsg->{blob} respects boost after reindex');
+
+       xsys([qw(git config --unset publicinbox.v1test.boost)],
+               { GIT_CONFIG => $cfg_path });
+       xsys([qw(git config --unset publicinbox.v2test.boost)],
+               { GIT_CONFIG => $cfg_path });
+}
+
 { # TODO: -extindex should write this to config
        open $fh, '>>', $cfg_path or BAIL_OUT $!;
        print $fh <<EOF or BAIL_OUT $!;