support setting No_COW on Perl <5.22

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 080aca7cb7b79cb05509ef2a1916d0f65430ff5b..1cf3e66cf3ddbcbfb88b5b499e249e663ce0c621 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -12,21 +12,20 @@ use v5.10.1;
 use parent qw(PublicInbox::Search PublicInbox::Lock Exporter);
 use PublicInbox::Eml;
 use PublicInbox::InboxWritable;
-use PublicInbox::MID qw(mid_mime mids_for_index mids);
+use PublicInbox::MID qw(mids_for_index mids);
 use PublicInbox::MsgIter;
 use PublicInbox::IdxStack;
 use Carp qw(croak);
 use POSIX qw(strftime);
 use PublicInbox::OverIdx;
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Spawn qw(spawn nodatacow_dir);
 use PublicInbox::Git qw(git_unquote);
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
-our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size nodatacow_dir);
+our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size);
 my $X = \%PublicInbox::Search::X;
 my ($DB_CREATE_OR_OPEN, $DB_OPEN);
 our $DB_NO_SYNC = 0;
-our $BATCH_BYTES = defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
-                       0x7fffffff : 1_000_000;
+our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff : 1_000_000;
 use constant DEBUG => !!$ENV{DEBUG};
 
 my $xapianlevels = qr/\A(?:full|medium)\z/;
@@ -67,7 +66,7 @@ sub new {
                $self->{lock_path} = "$inboxdir/ssoma.lock";
                my $dir = $self->xdir;
                $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
-               $self->{over}->{-no_sync} = 1 if $ibx->{-no_sync};
+               $self->{over}->{-no_fsync} = 1 if $ibx->{-no_fsync};
                $self->{index_max_size} = $ibx->{index_max_size};
        } elsif ($version == 2) {
                defined $shard or die "shard is required for v2\n";
@@ -110,12 +109,6 @@ sub load_xapian_writable () {
        1;
 }
 
-sub nodatacow_dir ($) {
-       my ($dir) = @_;
-       opendir my $dh, $dir or die "opendir($dir): $!\n";
-       PublicInbox::Spawn::set_nodatacow(fileno($dh));
-}
-
 sub idx_acquire {
        my ($self) = @_;
        my $flag;
@@ -138,7 +131,7 @@ sub idx_acquire {
                }
        }
        return unless defined $flag;
-       $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_sync};
+       $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_fsync};
        my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
        if ($@) {
                die "Failed opening $dir: ", $@;
@@ -350,8 +343,7 @@ sub index_ids ($$$$) {
 }
 
 sub add_xapian ($$$$) {
-       my ($self, $mime, $smsg, $mids) = @_;
-       my $hdr = $mime->header_obj;
+       my ($self, $eml, $smsg, $mids) = @_;
        my $doc = $X->{Document}->new;
        add_val($doc, PublicInbox::Search::TS(), $smsg->{ts});
        my @ds = gmtime($smsg->{ds});
@@ -366,10 +358,10 @@ sub add_xapian ($$$$) {
        $tg->set_document($doc);
        index_headers($self, $smsg);
 
-       msg_iter($mime, \&index_xapian, [ $self, $doc ]);
-       index_ids($self, $doc, $hdr, $mids);
+       msg_iter($eml, \&index_xapian, [ $self, $doc ]);
+       index_ids($self, $doc, $eml, $mids);
        $smsg->{to} = $smsg->{cc} = ''; # WWW doesn't need these, only NNTP
-       PublicInbox::OverIdx::parse_references($smsg, $hdr, $mids);
+       PublicInbox::OverIdx::parse_references($smsg, $eml, $mids);
        my $data = $smsg->to_doc_data;
        $doc->set_data($data);
        if (my $altid = $self->{-altid}) {
@@ -390,7 +382,7 @@ sub _msgmap_init ($) {
        die "BUG: _msgmap_init is only for v1\n" if $self->{ibx_ver} != 1;
        $self->{mm} //= eval {
                require PublicInbox::Msgmap;
-               my $rw = $self->{ibx}->{-no_sync} ? 2 : 1;
+               my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
                PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw);
        };
 }
@@ -398,8 +390,7 @@ sub _msgmap_init ($) {
 sub add_message {
        # mime = PublicInbox::Eml or Email::MIME object
        my ($self, $mime, $smsg, $sync) = @_;
-       my $hdr = $mime->header_obj;
-       my $mids = mids_for_index($hdr);
+       my $mids = mids_for_index($mime);
        $smsg //= bless { blob => '' }, 'PublicInbox::Smsg'; # test-only compat
        $smsg->{mid} //= $mids->[0]; # v1 compatibility
        $smsg->{num} //= do { # v1
@@ -408,7 +399,7 @@ sub add_message {
        };
 
        # v1 and tests only:
-       $smsg->populate($hdr, $sync);
+       $smsg->populate($mime, $sync);
        $smsg->{bytes} //= length($mime->as_string);
 
        eval {
@@ -492,6 +483,11 @@ sub unindex_eml {
        while (my ($num, $nr) = each %tmp) {
                warn "BUG: $num appears >1 times ($nr) for $oid\n" if $nr != 1;
        }
+       if ($nr) {
+               $self->{mm}->num_delete($_) for (keys %tmp);
+       } else { # just in case msgmap and over.sqlite3 become desynched:
+               $self->{mm}->mid_delete($mids->[0]);
+       }
        xdb_remove($self, $oid, keys %tmp) if need_xapian($self);
 }
 
@@ -512,11 +508,6 @@ sub index_mm {
        }
 }
 
-sub unindex_mm {
-       my ($self, $mime) = @_;
-       $self->{mm}->mid_delete(mid_mime($mime));
-}
-
 # returns the number of bytes to add if given a non-CRLF arg
 sub crlf_adjust ($) {
        if (index($_[0], "\r\n") < 0) {
@@ -544,9 +535,7 @@ sub index_both { # git->cat_async callback
 
 sub unindex_both { # git->cat_async callback
        my ($bref, $oid, $type, $size, $self) = @_;
-       my $eml = PublicInbox::Eml->new($bref);
-       unindex_eml($self, $oid, $eml);
-       unindex_mm($self, $eml);
+       unindex_eml($self, $oid, PublicInbox::Eml->new($bref));
 }
 
 # called by public-inbox-index