X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=d1290dc208e37eb7689deff009da165fa5234ed1;hb=b15ca9a77bff088a3f5f0b8955de8b6a60565b04;hp=7d089e7aee4271645ae562ccf1b13ab24f6d68f7;hpb=8e1ec8836dabc58dfc0115b36ed440b4371b70d7;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 7d089e7a..d1290dc2 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -275,22 +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;
@@ -300,11 +286,24 @@ 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 ($$$$) {
@@ -497,13 +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;
 
@@ -534,7 +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 {
@@ -552,13 +551,11 @@ sub unindex_both {
 
 sub do_cat_mail {
 	my ($git, $blob, $sizeref) = @_;
-	my $mime = eval {
-		my $str = $git->cat_file($blob, $sizeref);
-		# fixup bugs from import:
-		$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
-		PublicInbox::MIME->new($str);
-	};
-	$@ ? undef : $mime;
+	my $str = $git->cat_file($blob, $sizeref) or
+		die "BUG: $blob not found in $git->{git_dir}";
+	# fixup bugs from import:
+	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+	PublicInbox::MIME->new($str);
 }
 
 # called by public-inbox-index
@@ -603,7 +600,7 @@ sub read_log {
 				}
 				next;
 			}
-			my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+			my $mime = do_cat_mail($git, $blob, \$bytes);
 			my $smsg = bless {}, 'PublicInbox::Smsg';
 			batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr);
 			$smsg->{blob} = $blob;
@@ -624,7 +621,7 @@ sub read_log {
 	close($log) or die "git log failed: \$?=$?";
 	# get the leftovers
 	foreach my $blob (keys %D) {
-		my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+		my $mime = do_cat_mail($git, $blob, \$bytes);
 		$del_cb->($self, $mime);
 	}
 	$batch_cb->($nr, $latest, $newest);
@@ -635,7 +632,7 @@ sub _git_log {
 	my $git = $self->{git};
 
 	if (index($range, '..') < 0) {
-		# don't show annoying git errrors to users who run -index
+		# don't show annoying git errors to users who run -index
 		# on empty inboxes
 		$git->qx(qw(rev-parse -q --verify), "$range^0");
 		if ($?) {