X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdxShard.pm;h=59b360872b3bb4db111b5354b7a5b4b1aecbd41d;hb=99def67b86c4d270e8cfda4d1fad418291b6f3a4;hp=74c624a4d3dddcb67ac5938aaa1f5186c34284e1;hpb=8e81d6f0d44198717ae540421a09824d75c9bb6d;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index 74c624a4..59b36087 100644
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -5,17 +5,20 @@
 # See L<public-inbox-v2-format(5)> for more info on how we shard Xapian
 package PublicInbox::SearchIdxShard;
 use strict;
-use warnings;
-use base qw(PublicInbox::SearchIdx);
+use v5.10.1;
+use parent qw(PublicInbox::SearchIdx);
 use IO::Handle (); # autoflush
+use PublicInbox::Eml;
 
 sub new {
-	my ($class, $v2writable, $shard) = @_;
-	my $self = $class->SUPER::new($v2writable->{-inbox}, 1, $shard);
+	my ($class, $v2w, $shard) = @_;
+	my $ibx = $v2w->{ibx};
+	my $self = $class->SUPER::new($ibx, 1, $shard);
 	# create the DB before forking:
-	$self->_xdb_acquire;
-	$self->_xdb_release;
-	$self->spawn_worker($v2writable, $shard) if $v2writable->{parallel};
+	$self->idx_acquire;
+	$self->set_indexlevel;
+	$self->idx_release;
+	$self->spawn_worker($v2w, $shard) if $v2w->{parallel};
 	$self;
 }
 
@@ -23,8 +26,6 @@ sub spawn_worker {
 	my ($self, $v2w, $shard) = @_;
 	my ($r, $w);
 	pipe($r, $w) or die "pipe failed: $!\n";
-	binmode $r, ':raw';
-	binmode $w, ':raw';
 	$w->autoflush(1);
 	my $pid = fork;
 	defined $pid or die "fork failed: $!\n";
@@ -50,33 +51,37 @@ sub shard_worker_loop ($$$$$) {
 	my ($self, $v2w, $r, $shard, $bnote) = @_;
 	$0 = "pi-v2-shard[$shard]";
 	$self->begin_txn_lazy;
-	while (my $line = $r->getline) {
+	while (my $line = readline($r)) {
 		$v2w->{current_info} = "[$shard] $line";
 		if ($line eq "commit\n") {
 			$self->commit_txn_lazy;
 		} elsif ($line eq "close\n") {
-			$self->_xdb_release;
+			$self->idx_release;
 		} elsif ($line eq "barrier\n") {
 			$self->commit_txn_lazy;
 			# no need to lock < 512 bytes is atomic under POSIX
 			print $bnote "barrier $shard\n" or
 					die "write failed for barrier $!\n";
-		} elsif ($line =~ /\AD ([a-f0-9]{40,}) (.+)\n\z/s) {
-			my ($oid, $mid) = ($1, $2);
-			$self->begin_txn_lazy;
-			$self->remove_by_oid($oid, $mid);
+		} elsif ($line =~ /\AD ([a-f0-9]{40,}) ([0-9]+)\n\z/s) {
+			$self->remove_by_oid($1, $2 + 0);
 		} else {
 			chomp $line;
-			my ($len, $artnum, $oid, $mid0, $autime, $cotime) =
-							split(/ /, $line);
+			# n.b. $mid may contain spaces(!)
+			my ($to_read, $bytes, $num, $blob, $ds, $ts, $mid) =
+							split(/ /, $line, 7);
 			$self->begin_txn_lazy;
-			my $n = read($r, my $msg, $len) or die "read: $!\n";
-			$n == $len or die "short read: $n != $len\n";
-			my $mime = PublicInbox::MIME->new(\$msg);
-			$artnum = int($artnum);
-			$self->{autime} = $autime;
-			$self->{cotime} = $cotime;
-			$self->add_message($mime, $n, $artnum, $oid, $mid0);
+			my $n = read($r, my $msg, $to_read) or die "read: $!\n";
+			$n == $to_read or die "short read: $n != $to_read\n";
+			my $mime = PublicInbox::Eml->new(\$msg);
+			my $smsg = bless {
+				bytes => $bytes,
+				num => $num + 0,
+				blob => $blob,
+				mid => $mid,
+				ds => $ds,
+				ts => $ts,
+			}, 'PublicInbox::Smsg';
+			$self->add_message($mime, $smsg);
 		}
 	}
 	$self->worker_done;
@@ -84,18 +89,20 @@ sub shard_worker_loop ($$$$$) {
 
 # called by V2Writable
 sub index_raw {
-	my ($self, $bytes, $msgref, $artnum, $oid, $mid0, $mime, $times) = @_;
-	my $at = $times->{autime} // time;
-	my $ct = $times->{cotime} // time;
+	my ($self, $msgref, $eml, $smsg) = @_;
 	if (my $w = $self->{w}) {
-		print $w "$bytes $artnum $oid $mid0 $at $ct\n", $$msgref or
-			die "failed to write shard $!\n";
+		# mid must be last, it can contain spaces (but not LF)
+		print $w join(' ', @$smsg{qw(raw_bytes bytes
+						num blob ds ts mid)}),
+			"\n", $$msgref or die "failed to write shard $!\n";
 	} else {
-		$$msgref = undef;
+		if ($eml) {
+			$$msgref = undef;
+		} else { # --xapian-only + --sequential-shard:
+			$eml = PublicInbox::Eml->new($msgref);
+		}
 		$self->begin_txn_lazy;
-		$self->{autime} = $at;
-		$self->{cotime} = $ct;
-		$self->add_message($mime, $bytes, $artnum, $oid, $mid0);
+		$self->add_message($eml, $smsg);
 	}
 }