X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=30d3fe926a14cef02834bfe3511ac37022e14bee;hb=970eb1fd83b93c790d2faed6bf64a97d6d5fe126;hp=d63dd7c742b4c21ef9420d810954df3e8332f45e;hpb=3fc59df0d633a17e0c5e43d633d12e8772c06ec3;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index d63dd7c7..30d3fe92 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -19,15 +19,15 @@ use PublicInbox::MsgIter;
 use Carp qw(croak);
 use POSIX qw(strftime);
 require PublicInbox::Git;
-*xpfx = *PublicInbox::Search::xpfx;
 
-use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
 use constant {
+	MAX_MID_SIZE => 244, # max term size - 1 in Xapian
 	PERM_UMASK => 0,
 	OLD_PERM_GROUP => 1,
 	OLD_PERM_EVERYBODY => 2,
 	PERM_GROUP => 0660,
 	PERM_EVERYBODY => 0664,
+	BATCH_BYTES => 1_000_000,
 };
 
 sub new {
@@ -72,7 +72,6 @@ sub _xdb_acquire {
 		require File::Path;
 		_lock_acquire($self);
 		File::Path::mkpath($dir);
-		$self->{batch_size} = 100;
 		$flag = Search::Xapian::DB_CREATE_OR_OPEN;
 	}
 	$self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag);
@@ -160,12 +159,12 @@ sub add_message {
 		}
 		$smsg = PublicInbox::SearchMsg->new($mime);
 		my $doc = $smsg->{doc};
-		$doc->add_term(xpfx('mid') . $mid);
+		$doc->add_term('Q' . $mid);
 
 		my $subj = $smsg->subject;
 		if ($subj ne '') {
 			my $path = $self->subject_path($subj);
-			$doc->add_term(xpfx('path') . id_compress($path));
+			$doc->add_term('XPATH' . id_compress($path));
 		}
 
 		add_values($smsg, $bytes, $num);
@@ -291,13 +290,12 @@ sub link_message {
 	my $mid = $smsg->mid;
 	my $mime = $smsg->{mime};
 	my $hdr = $mime->header_obj;
-	my $refs = $hdr->header_raw('References');
-	my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
-	my $irt = $hdr->header_raw('In-Reply-To');
-	if (defined $irt) {
-		$irt = mid_clean($irt);
-		$irt = undef if $mid eq $irt;
-	}
+
+	# last References should be IRT, but some mail clients do things
+	# out of order, so trust IRT over References iff IRT exists
+	my @refs = ($hdr->header_raw('References'),
+			$hdr->header_raw('In-Reply-To'));
+	@refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
 
 	my $tid;
 	if (@refs) {
@@ -305,15 +303,6 @@ sub link_message {
 		my @orig_refs = @refs;
 		@refs = ();
 
-		if (defined $irt) {
-			# to check MAX_MID_SIZE
-			push @orig_refs, $irt;
-
-			# below, we will ensure IRT (if specified)
-			# is the last References
-			$uniq{$irt} = 1;
-		}
-
 		# prevent circular references via References: here:
 		foreach my $ref (@orig_refs) {
 			if (length($ref) > MAX_MID_SIZE) {
@@ -325,10 +314,6 @@ sub link_message {
 		}
 	}
 
-	# last References should be IRT, but some mail clients do things
-	# out of order, so trust IRT over References iff IRT exists
-	push @refs, $irt if defined $irt;
-
 	if (@refs) {
 		$smsg->{references} = '<'.join('> <', @refs).'>';
 
@@ -344,9 +329,9 @@ sub link_message {
 			merge_threads($self, $tid, $ptid);
 		}
 	} else {
-		$tid = $self->next_thread_id;
+		$tid = defined $old_tid ? $old_tid : $self->next_thread_id;
 	}
-	$doc->add_term(xpfx('thread') . $tid);
+	$doc->add_term('G' . $tid);
 }
 
 sub index_blob {
@@ -410,6 +395,15 @@ sub index_sync {
 	with_umask($self, sub { $self->_index_sync($opts) });
 }
 
+sub batch_adjust ($$$$) {
+	my ($max, $bytes, $batch_cb, $latest) = @_;
+	$$max -= $bytes;
+	if ($$max <= 0) {
+		$$max = BATCH_BYTES;
+		$batch_cb->($latest, 1);
+	}
+}
+
 sub rlog {
 	my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_;
 	my $hex = '[a-f0-9]';
@@ -419,23 +413,21 @@ sub rlog {
 	my $git = $self->{git};
 	my $latest;
 	my $bytes;
-	my $max = $self->{batch_size}; # may be undef
+	my $max = BATCH_BYTES;
 	local $/ = "\n";
 	my $line;
 	while (defined($line = <$log>)) {
 		if ($line =~ /$addmsg/o) {
 			my $blob = $1;
 			my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+			batch_adjust(\$max, $bytes, $batch_cb, $latest);
 			$add_cb->($self, $mime, $bytes, $blob);
 		} elsif ($line =~ /$delmsg/o) {
 			my $blob = $1;
-			my $mime = do_cat_mail($git, $blob) or next;
+			my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+			batch_adjust(\$max, $bytes, $batch_cb, $latest);
 			$del_cb->($self, $mime);
 		} elsif ($line =~ /^commit ($h40)/o) {
-			if (defined $max && --$max <= 0) {
-				$max = $self->{batch_size};
-				$batch_cb->($latest, 1);
-			}
 			$latest = $1;
 		}
 	}
@@ -556,9 +548,9 @@ sub create_ghost {
 
 	my $tid = $self->next_thread_id;
 	my $doc = Search::Xapian::Document->new;
-	$doc->add_term(xpfx('mid') . $mid);
-	$doc->add_term(xpfx('thread') . $tid);
-	$doc->add_term(xpfx('type') . 'ghost');
+	$doc->add_term('Q' . $mid);
+	$doc->add_term('G' . $tid);
+	$doc->add_term('T' . 'ghost');
 
 	my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
 	$self->{xdb}->add_document($doc);
@@ -569,15 +561,14 @@ sub create_ghost {
 sub merge_threads {
 	my ($self, $winner_tid, $loser_tid) = @_;
 	return if $winner_tid == $loser_tid;
-	my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid);
-	my $thread_pfx = xpfx('thread');
+	my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid);
 	my $db = $self->{xdb};
 
 	for (; $head != $tail; $head->inc) {
 		my $docid = $head->get_docid;
 		my $doc = $db->get_document($docid);
-		$doc->remove_term($thread_pfx . $loser_tid);
-		$doc->add_term($thread_pfx . $winner_tid);
+		$doc->remove_term('G' . $loser_tid);
+		$doc->add_term('G' . $winner_tid);
 		$db->replace_document($docid, $doc);
 	}
 }
@@ -634,7 +625,7 @@ sub with_umask {
 	my $rv = eval { $cb->() };
 	my $err = $@;
 	umask $old;
-	die $err if $@;
+	die $err if $err;
 	$rv;
 }