From 0c586dc64b3b6642a894e125d09df446667a4079 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@yhbt.net>
Date: Sat, 18 Apr 2020 03:38:53 +0000
Subject: reduce scope of mbox From_ line removal

It's unnecessary overhead for anything which does Email::MIME
parsing.  It was never done for v2 indexing, even though v1->v2
conversions did NOT remove those From_ lines.  There was never a
need to remote From_ lines the v1 SearchIdx paths, either.

Hitting a /$INBOX_URL/$MSGID/T/ endpoint with an 18 message
thread reveals a ~0.5% speed improvement.  This will become
more apparent when we have a faster MIME parser.
---
 lib/PublicInbox/Inbox.pm     | 8 ++------
 lib/PublicInbox/Mbox.pm      | 7 +++++--
 lib/PublicInbox/NNTP.pm      | 2 ++
 lib/PublicInbox/SearchIdx.pm | 2 --
 4 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'lib')

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 4bd82989..186eb420 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -311,9 +311,7 @@ sub nntp_usable {
 # for v1 users w/o SQLite only
 sub msg_by_path ($$;$) {
 	my ($self, $path, $ref) = @_;
-	my $str = git($self)->cat_file('HEAD:'.$path, $ref);
-	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str;
-	$str;
+	git($self)->cat_file('HEAD:'.$path, $ref);
 }
 
 sub msg_by_smsg ($$;$) {
@@ -324,9 +322,7 @@ sub msg_by_smsg ($$;$) {
 	return unless defined $smsg;
 	defined(my $blob = $smsg->{blob}) or return;
 
-	my $str = git($self)->cat_file($blob, $ref);
-	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str;
-	$str;
+	git($self)->cat_file($blob, $ref);
 }
 
 sub smsg_mime {
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 16de1a72..9995140c 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -106,8 +106,11 @@ sub msg_hdr ($$;$) {
 		'List-Post', "<mailto:$ibx->{-primary_address}>",
 	);
 	my $crlf = $header_obj->crlf;
-	my $buf = 'From mboxrd@z Thu Jan  1 00:00:00 1970' . $crlf .
-			$header_obj->as_string;
+	my $buf = $header_obj->as_string;
+	# fixup old bug from import (pre-a0c07cba0e5d8b6a)
+	$buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+	$buf = "From mboxrd\@z Thu Jan  1 00:00:00 1970" . $crlf . $buf;
+
 	for (my $i = 0; $i < @append; $i += 2) {
 		my $k = $append[$i];
 		my $v = $append[$i + 1];
diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm
index d1f75f6f..c79f198b 100644
--- a/lib/PublicInbox/NNTP.pm
+++ b/lib/PublicInbox/NNTP.pm
@@ -506,6 +506,8 @@ sub set_art {
 sub msg_hdr_write ($$$) {
 	my ($self, $hdr, $body_follows) = @_;
 	$hdr = $hdr->as_string;
+	# fixup old bug from import (pre-a0c07cba0e5d8b6a)
+	$hdr =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 	utf8::encode($hdr);
 	$hdr =~ s/(?<!\r)\n/\r\n/sg; # Alpine barfs without this
 
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index d1290dc2..579b85e3 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -553,8 +553,6 @@ sub do_cat_mail {
 	my ($git, $blob, $sizeref) = @_;
 	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);
 }
 
-- 
cgit v1.2.3-24-ge0c7