From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@yhbt.net>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id B3C271F61C
	for <meta@public-inbox.org>; Fri, 20 Mar 2020 08:18:21 +0000 (UTC)
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 2/9] v2writable: preserve timestamps from import
Date: Fri, 20 Mar 2020 08:18:14 +0000
Message-Id: <20200320081821.21715-3-e@yhbt.net>
In-Reply-To: <20200320081821.21715-1-e@yhbt.net>
References: <20200320081821.21715-1-e@yhbt.net>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

While v2 indexing is triggered immediately after writing the
commit to the git repository, there may be a gap between when
PublicInbox::Import generates a timestamp and when
PublicInbox::SearchIdx sees the message.  So follow the mirror
indexing behavior and take the to-be-indexed (time|date)stamps
directly from the git commit.
---
 lib/PublicInbox/Import.pm     | 12 ++++++++----
 lib/PublicInbox/V2Writable.pm |  2 +-
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 68dc0c7e..3853ff2b 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -274,8 +274,8 @@ sub git_timestamp {
 	"$ts $zone";
 }
 
-sub extract_cmt_info ($) {
-	my ($mime) = @_;
+sub extract_cmt_info ($;$) {
+	my ($mime, $v2w) = @_;
 
 	my $sender = '';
 	my $from = $mime->header('From');
@@ -325,6 +325,10 @@ sub extract_cmt_info ($) {
 	utf8::encode($subject);
 	my $at = git_timestamp(my @at = msg_datestamp($hdr));
 	my $ct = git_timestamp(my @ct = msg_timestamp($hdr));
+	if ($v2w) { # set fallbacks in case message had no date
+		$v2w->{autime} = $at[0];
+		$v2w->{cotime} = $ct[0];
+	}
 	($name, $email, $at, $ct, $subject);
 }
 
@@ -370,9 +374,9 @@ sub clean_tree_v2 ($$$) {
 # returns undef on duplicate
 # returns the :MARK of the most recent commit
 sub add {
-	my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
+	my ($self, $mime, $check_cb, $v2w) = @_; # mime = Email::MIME
 
-	my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+	my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $v2w);
 	my $path_type = $self->{path_type};
 	my $path;
 	if ($path_type eq '2/38') {
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index f1842843..d39a6f89 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -176,7 +176,7 @@ sub _add {
 	defined $num or return; # duplicate
 	defined $mid0 or die "BUG: $mid0 undefined\n";
 	my $im = $self->importer;
-	my $cmt = $im->add($mime);
+	my $cmt = $im->add($mime, undef, $self); # sets $self->{(au|co)time}
 	$cmt = $im->get_mark($cmt);
 	$self->{last_commit}->[$self->{epoch_max}] = $cmt;