drop binmode usage

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

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index 0522eceae13ada18cd57819ebdc0c1fb12325fe0..b51d148b161492bcb07d04f36e60a569d89b45d4 100644 (file)
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -1,19 +1,22 @@
-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # used to interface with a single Xapian shard in V2 repos.
 # 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 $ibx = $v2writable->{-inbox};
+       my $self = $class->SUPER::new($ibx, 1, $shard);
        # create the DB before forking:
        $self->_xdb_acquire;
+       $self->set_indexlevel;
        $self->_xdb_release;
        $self->spawn_worker($v2writable, $shard) if $v2writable->{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";
@@ -50,7 +51,7 @@ sub shard_worker_loop ($$$$$) {
        my ($self, $v2w, $r, $shard, $bnote) = @_;
        $0 = "pi-v2-shard[$shard]";
        $self->begin_txn_lazy;
-       while (my $line = $r->getline) {
+       while (my $line = readline($r)) {
                $v2w->{current_info} = "[$shard] $line";
                if ($line eq "commit\n") {
                        $self->commit_txn_lazy;
@@ -67,13 +68,22 @@ sub shard_worker_loop ($$$$$) {
                        $self->remove_by_oid($oid, $mid);
                } else {
                        chomp $line;
-                       my ($len, $artnum, $oid, $mid0) = split(/ /, $line);
+                       # n.b. $mid may contain spaces(!)
+                       my ($to_read, $bytes, $num, $blob, $ds, $ts, $mid) =
+                                                       split(/ /, $line, 7);
                        $self->begin_txn_lazy;
-                       my $n = read($r, my $msg, $len) or die "read: $!\n";
-                       $n == $len or die "short read: $n != $len\n";
-                       my $mime = PublicInbox::MIME->new(\$msg);
-                       $artnum = int($artnum);
-                       $self->add_message($mime, $n, $artnum, $oid, $mid0);
+                       my $n = read($r, my $msg, $to_read) or die "read: $!\n";
+                       $n == $to_read or die "short read: $n != $to_read\n";
+                       my $mime = PublicInbox::Eml->new(\$msg);
+                       my $smsg = bless {
+                               bytes => $bytes,
+                               num => $num + 0,
+                               blob => $blob,
+                               mid => $mid,
+                               ds => $ds,
+                               ts => $ts,
+                       }, 'PublicInbox::Smsg';
+                       $self->add_message($mime, $smsg);
                }
        }
        $self->worker_done;
@@ -81,14 +91,16 @@ sub shard_worker_loop ($$$$$) {
 
 # called by V2Writable
 sub index_raw {
-       my ($self, $bytes, $msgref, $artnum, $oid, $mid0, $mime) = @_;
+       my ($self, $msgref, $mime, $smsg) = @_;
        if (my $w = $self->{w}) {
-               print $w "$bytes $artnum $oid $mid0\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;
                $self->begin_txn_lazy;
-               $self->add_message($mime, $bytes, $artnum, $oid, $mid0);
+               $self->add_message($mime, $smsg);
        }
 }