# 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 $ibx = $v2writable->{-inbox};
+ my ($class, $v2w, $shard) = @_;
+ my $ibx = $v2w->{ibx};
my $self = $class->SUPER::new($ibx, 1, $shard);
# create the DB before forking:
- $self->_xdb_acquire;
+ $self->idx_acquire;
$self->set_indexlevel;
- $self->_xdb_release;
- $self->spawn_worker($v2writable, $shard) if $v2writable->{parallel};
+ $self->idx_release;
+ $self->spawn_worker($v2w, $shard) if $v2w->{parallel};
$self;
}
my ($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: $!\n";
my ($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;
# n.b. $mid may contain spaces(!)
- my ($bytes, $num, $blob, $ds, $ts, $mid) =
- split(/ /, $line, 6);
+ my ($to_read, $bytes, $num, $blob, $ds, $ts, $mid) =
+ split(/ /, $line, 7);
$self->begin_txn_lazy;
- my $n = read($r, my $msg, $bytes) or die "read: $!\n";
- $n == $bytes or die "short read: $n != $bytes\n";
- my $mime = PublicInbox::MIME->new(\$msg);
+ 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 => $num + 0,
my ($self, $msgref, $mime, $smsg) = @_;
if (my $w = $self->{w}) {
# mid must be last, it can contain spaces (but not LF)
- print $w join(' ', @$smsg{qw(bytes num blob ds ts mid)}),
+ 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;