From 7a3a4b9d310876f68f4ba788afaef77ad15fc62b Mon Sep 17 00:00:00 2001
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
Date: Mon, 19 Mar 2018 08:14:41 +0000
Subject: import: (v2) delete writes the blob into history in subdir

This makes it easier to audit deletes with "git log -p" and
prevents an unstable specification of "content_id" from being
stored in history.

This should be cost-free if done in the same partition (and even
cheaper than before as it introduces no new blobs).  It does
have a higher cost across partitions, but is probably irrelevant
given the typical ham:spam ratio.
---
 lib/PublicInbox/Import.pm     | 15 ++++++++++-----
 lib/PublicInbox/V2Writable.pm |  4 +++-
 2 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'lib')

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index e20c6e03..94a49fe6 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -11,7 +11,6 @@ use Fcntl qw(:flock :DEFAULT);
 use PublicInbox::Spawn qw(spawn);
 use PublicInbox::MID qw(mid_mime mid2path);
 use PublicInbox::Address;
-use PublicInbox::ContentId qw(content_id);
 use PublicInbox::MsgTime qw(msg_timestamp);
 
 sub new {
@@ -163,7 +162,6 @@ sub get_mark {
 # ('MISMATCH', Email::MIME) on mismatch
 # (:MARK, Email::MIME) on success
 #
-# For v2 inboxes, the content_id is returned instead of the msg
 # v2 callers should check with Xapian before calling this as
 # it is not idempotent.
 sub remove {
@@ -179,10 +177,17 @@ sub remove {
 		($err, $cur) = check_remove_v1($r, $w, $tip, $path, $mime);
 		return ($err, $cur) if $err;
 	} else {
-		$cur = content_id($mime);
-		my $len = length($cur);
+		my $sref;
+		if (ref($mime) eq 'SCALAR') { # optimization used by V2Writable
+			$sref = $mime;
+		} else { # XXX should not be necessary:
+			my $str = $mime->as_string;
+			$sref = \$str;
+		}
+		my $len = length($$sref);
 		$blob = $self->{mark}++;
-		print $w "blob\nmark :$blob\ndata $len\n$cur\n" or wfail;
+		print $w "blob\nmark :$blob\ndata $len\n",
+			$$sref, "\n" or wfail;
 	}
 
 	my $ref = $self->{ref};
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 656f0693..fd9bf615 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -220,6 +220,7 @@ sub remove {
 				warn "broken smsg for $mid\n";
 				return 1; # continue
 			}
+			my $orig = $$msg;
 			my $cur = PublicInbox::MIME->new($msg);
 			if (content_id($cur) eq $cid) {
 				$mm->num_delete($smsg->num);
@@ -227,7 +228,8 @@ sub remove {
 				# no bugs in our deduplication code:
 				$removed = $smsg;
 				$removed->{mime} = $cur;
-				$im->remove($cur, $cmt_msg);
+				$im->remove(\$orig, $cmt_msg);
+				$orig = undef;
 				$removed->num; # memoize this for callers
 
 				my $oid = $smsg->{blob};
-- 
cgit v1.2.3-24-ge0c7