release large (non ref) scalars using `undef $sv'

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 5ca819c383525de90c72eae9bc5c3f31efea76ce..9a5484e30b81b8ac29bb9bbfa43816ac6ee04210 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -58,6 +58,7 @@ sub new {
                ibx_ver => $version,
                indexlevel => $indexlevel,
        }, $class;
+       $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium';
        $ibx->umask_prepare;
        if ($version == 1) {
                $self->{lock_path} = "$inboxdir/ssoma.lock";
@@ -274,22 +275,8 @@ sub index_diff ($$$) {
        index_text($self, join("\n", @xnq), 1, 'XNQ');
 }
 
-sub index_body ($$$) {
-       my ($self, $txt, $doc) = @_;
-       if ($doc) {
-               # does it look like a diff?
-               if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
-                       index_diff($self, $txt, $doc);
-               } else {
-                       index_text($self, $txt, 1, 'XNQ');
-               }
-       } else {
-               index_text($self, $txt, 0, 'XQUOT');
-       }
-}
-
 sub index_xapian { # msg_iter callback
-       my ($part, $depth, @idx) = @{$_[0]};
+       my $part = $_[0]->[0]; # ignore $depth and @idx
        my ($self, $doc) = @{$_[1]};
        my $ct = $part->content_type || 'text/plain';
        my $fn = $part->filename;
@@ -299,19 +286,30 @@ sub index_xapian { # msg_iter callback
 
        my ($s, undef) = msg_part_text($part, $ct);
        defined $s or return;
+       $_[0]->[0] = $part = undef; # free memory
 
        # split off quoted and unquoted blocks:
-       my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
-       $part = $s = undef;
-       index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
+       my @sections = PublicInbox::MsgIter::split_quotes($s);
+       undef $s; # free memory
+       for my $txt (@sections) {
+               if ($txt =~ /\A>/) {
+                       index_text($self, $txt, 0, 'XQUOT');
+               } else {
+                       # does it look like a diff?
+                       if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
+                               index_diff($self, $txt, $doc);
+                       } else {
+                               index_text($self, $txt, 1, 'XNQ');
+                       }
+               }
+               undef $txt; # free memory
+       }
 }
 
 sub add_xapian ($$$$) {
        my ($self, $mime, $smsg, $mids) = @_;
        $smsg->{mime} = $mime; # XXX dangerous
        my $hdr = $mime->header_obj;
-       $smsg->{ds} = msg_datestamp($hdr, $self->{autime});
-       $smsg->{ts} = msg_timestamp($hdr, $self->{cotime});
        my $doc = $X->{Document}->new;
        my $subj = $smsg->subject;
        add_val($doc, PublicInbox::Search::TS(), $smsg->{ts});
@@ -368,13 +366,19 @@ sub _msgmap_init ($) {
 sub add_message {
        # mime = Email::MIME object
        my ($self, $mime, $smsg) = @_;
-       my $mids = mids_for_index($mime->header_obj);
+       my $hdr = $mime->header_obj;
+       my $mids = mids_for_index($hdr);
        $smsg //= bless { blob => '' }, 'PublicInbox::Smsg'; # test-only compat
        $smsg->{mid} //= $mids->[0]; # v1 compatibility
        $smsg->{num} //= do { # v1
                _msgmap_init($self);
                index_mm($self, $mime);
        };
+
+       # v1 and tests only:
+       $smsg->{ds} //= msg_datestamp($hdr, $self->{autime});
+       $smsg->{ts} //= msg_timestamp($hdr, $self->{cotime});
+
        eval {
                # order matters, overview stores every possible piece of
                # data in doc_data (deflated).  Xapian only stores a subset
@@ -382,7 +386,7 @@ sub add_message {
                # storing doc_data in Xapian sometime after we get multi-inbox
                # search working.
                if (my $over = $self->{over}) { # v1 only
-                       $over->add_overview($mime, $smsg, $self);
+                       $over->add_overview($mime, $smsg);
                }
                if (need_xapian($self)) {
                        add_xapian($self, $mime, $smsg, $mids);
@@ -492,13 +496,13 @@ sub index_git_blob_id {
 
 sub unindex_blob {
        my ($self, $mime) = @_;
-       my $mid = eval { mid_clean(mid_mime($mime)) };
+       my $mid = eval { mid_mime($mime) };
        $self->remove_message($mid) if defined $mid;
 }
 
 sub index_mm {
        my ($self, $mime) = @_;
-       my $mid = mid_clean(mid_mime($mime));
+       my $mid = mid_mime($mime);
        my $mm = $self->{mm};
        my $num;
 
@@ -529,7 +533,7 @@ sub index_mm {
 
 sub unindex_mm {
        my ($self, $mime) = @_;
-       $self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
+       $self->{mm}->mid_delete(mid_mime($mime));
 }
 
 sub index_both {
@@ -611,9 +615,9 @@ sub read_log {
                        $latest = $1;
                        $newest ||= $latest;
                } elsif ($line =~ /^author .*? ([0-9]+) [\-\+][0-9]+$/) {
-                       $self->{over}->{autime} = $self->{autime} = $1;
+                       $self->{autime} = $1;
                } elsif ($line =~ /^committer .*? ([0-9]+) [\-\+][0-9]+$/) {
-                       $self->{over}->{cotime} = $self->{cotime} = $1;
+                       $self->{cotime} = $1;
                }
        }
        close($log) or die "git log failed: \$?=$?";
@@ -838,20 +842,27 @@ sub begin_txn_lazy {
        });
 }
 
+# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
+# This metadata is read by Admin::detect_indexlevel:
+sub set_indexlevel {
+       my ($self) = @_;
+
+       if (!$self->{shard} && # undef or 0, not >0
+                       delete($self->{-set_indexlevel_once})) {
+               my $xdb = $self->{xdb};
+               my $level = $xdb->get_metadata('indexlevel');
+               if (!$level || $level ne 'medium') {
+                       $xdb->set_metadata('indexlevel', 'medium');
+               }
+       }
+}
+
 sub commit_txn_lazy {
        my ($self) = @_;
        delete $self->{txn} or return;
        $self->{-inbox}->with_umask(sub {
                if (my $xdb = $self->{xdb}) {
-
-                       # store 'indexlevel=medium' in v2 shard=0 and
-                       # v1 (only one shard)
-                       # This metadata is read by Admin::detect_indexlevel:
-                       if (!$self->{shard} # undef or 0, not >0
-                           && $self->{indexlevel} eq 'medium') {
-                               $xdb->set_metadata('indexlevel', 'medium');
-                       }
-
+                       set_indexlevel($self);
                        $xdb->commit_transaction;
                }
                $self->{over}->commit_lazy if $self->{over};