update copyrights for 2021

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

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index b6eef6bdd4b80bc6600af0d100ba5b0260a66d55..45240e0793a8867e272005d386712e81004af803 100644 (file)
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Internal interface for a single Xapian shard in V2 inboxes.
@@ -34,6 +34,7 @@ sub spawn_worker {
        my $pid = fork;
        defined $pid or die "fork failed: $!\n";
        if ($pid == 0) {
+               eval { PublicInbox::DS->Reset };
                # these signals are localized in parent
                $SIG{$_} = 'IGNORE' for (qw(TERM INT QUIT));
                PublicInbox::Sigfd::sig_setmask($oldset);
@@ -69,35 +70,37 @@ sub shard_worker_loop ($$$$$) {
        $0 = "shard[$shard]";
        $self->begin_txn_lazy;
        while (my $line = readline($r)) {
+               chomp $line;
                $v2w->{current_info} = "[$shard] $line";
-               if ($line eq "commit\n") {
+               if ($line eq 'commit') {
                        $self->commit_txn_lazy;
-               } elsif ($line eq "close\n") {
+               } elsif ($line eq 'close') {
                        $self->idx_release;
-               } elsif ($line eq "barrier\n") {
+               } elsif ($line eq 'barrier') {
                        $self->commit_txn_lazy;
                        # no need to lock < 512 bytes is atomic under POSIX
                        print $bnote "barrier $shard\n" or
                                        die "write failed for barrier $!\n";
-               } elsif ($line =~ /\AD ([0-9]+)\n\z/s) {
+               } elsif ($line =~ /\AD ([0-9]+)\z/s) {
                        $self->remove_by_docid($1 + 0);
                } elsif ($line =~ s/\A\+X //) {
                        my ($len, $docid, $eidx_key) = split(/ /, $line, 3);
-                       chomp $eidx_key;
                        $self->add_eidx_info($docid, $eidx_key, eml($r, $len));
                } elsif ($line =~ s/\A-X //) {
                        my ($len, $docid, $eidx_key) = split(/ /, $line, 3);
-                       chomp $eidx_key;
                        $self->remove_eidx_info($docid, $eidx_key,
                                                        eml($r, $len));
-               } elsif ($line =~ s/\AO ([^\n]+)\n//) {
+               } elsif ($line =~ s/\A=K (\d+) //) {
+                       $self->set_keywords($1 + 0, split(/ /, $line));
+               } elsif ($line =~ s/\A-K (\d+) //) {
+                       $self->remove_keywords($1 + 0, split(/ /, $line));
+               } elsif ($line =~ s/\A\+K (\d+) //) {
+                       $self->add_keywords($1 + 0, split(/ /, $line));
+               } elsif ($line =~ s/\AO ([^\n]+)//) {
                        my $over_fn = $1;
                        $over_fn =~ tr/\0/\n/;
                        $self->over_check(PublicInbox::Over->new($over_fn));
-               } elsif ($line =~ /\AE ([0-9]+)\n/) {
-                       $self->reindex_docid($1 + 0);
                } else {
-                       chomp $line;
                        my $eidx_key;
                        if ($line =~ s/\AX=(.+)\0//) {
                                $eidx_key = $1;
@@ -124,9 +127,9 @@ sub shard_worker_loop ($$$$$) {
 }
 
 sub index_raw {
-       my ($self, $msgref, $eml, $smsg, $ibx) = @_;
+       my ($self, $msgref, $eml, $smsg, $eidx_key) = @_;
        if (my $w = $self->{w}) {
-               my @ekey = $ibx ? ('X='.$ibx->eidx_key."\0") : ();
+               my @ekey = defined($eidx_key) ? ("X=$eidx_key\0") : ();
                $msgref //= \($eml->as_string);
                $smsg->{raw_bytes} //= length($$msgref);
                # mid must be last, it can contain spaces (but not LF)
@@ -140,7 +143,7 @@ sub index_raw {
                        $eml = PublicInbox::Eml->new($msgref);
                }
                $self->begin_txn_lazy;
-               $smsg->{eidx_key} = $ibx->eidx_key if $ibx;
+               $smsg->{eidx_key} = $eidx_key if defined $eidx_key;
                $self->add_message($eml, $smsg);
        }
 }
@@ -214,6 +217,33 @@ sub shard_remove {
        }
 }
 
+sub shard_set_keywords {
+       my ($self, $docid, @kw) = @_;
+       if (my $w = $self->{w}) { # triggers remove_by_docid in a shard child
+               print $w "=K $docid @kw\n" or die "failed to write: $!";
+       } else { # same process
+               $self->set_keywords($docid, @kw);
+       }
+}
+
+sub shard_remove_keywords {
+       my ($self, $docid, @kw) = @_;
+       if (my $w = $self->{w}) { # triggers remove_by_docid in a shard child
+               print $w "-K $docid @kw\n" or die "failed to write: $!";
+       } else { # same process
+               $self->remove_keywords($docid, @kw);
+       }
+}
+
+sub shard_add_keywords {
+       my ($self, $docid, @kw) = @_;
+       if (my $w = $self->{w}) { # triggers remove_by_docid in a shard child
+               print $w "+K $docid @kw\n" or die "failed to write: $!";
+       } else { # same process
+               $self->add_keywords($docid, @kw);
+       }
+}
+
 sub shard_over_check {
        my ($self, $over) = @_;
        if (my $w = $self->{w}) { # triggers remove_by_docid in a shard child
@@ -225,13 +255,4 @@ sub shard_over_check {
        }
 }
 
-sub shard_reindex_docid {
-       my ($self, $docid) = @_;
-       if (my $w = $self->{w}) {
-               print $w "E $docid\n" or die "failed to write to shard: $!";
-       } else {
-               $self->reindex_docid($docid);
-       }
-}
-
 1;