From: Eric Wong <e@80x24.org>
Date: Tue, 25 Apr 2023 10:50:50 +0000 (+0000)
Subject: mail_diff: match ContentHash EOL and EOM behavior more closely
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=b00cfa89a6e0a9fc89aedf1a66172c4ad0566ece;p=thirdparty%2Fpublic-inbox.git

mail_diff: match ContentHash EOL and EOM behavior more closely

ContentHash currently doesn't convert CRCRLF to LF.  Perhaps it
should, but for now, have diff behavior match the actual
comparison behavior used for dedupe and omit all trailing
whitespace for diff.
---

diff --git a/lib/PublicInbox/ContentHash.pm b/lib/PublicInbox/ContentHash.pm
index a4f6196f8..fc94257c7 100644
--- a/lib/PublicInbox/ContentHash.pm
+++ b/lib/PublicInbox/ContentHash.pm
@@ -45,7 +45,7 @@ sub content_dig_i {
 	my $ct = $part->content_type || 'text/plain';
 	my ($s, undef) = msg_part_text($part, $ct);
 	if (defined $s) {
-		$s =~ s/\r\n/\n/gs;
+		$s =~ s/\r\n/\n/gs; # TODO: consider \r+\n to match View
 		$s =~ s/\s*\z//s;
 		utf8::encode($s);
 	} else {
diff --git a/lib/PublicInbox/MailDiff.pm b/lib/PublicInbox/MailDiff.pm
index 7511144c6..d9733ed40 100644
--- a/lib/PublicInbox/MailDiff.pm
+++ b/lib/PublicInbox/MailDiff.pm
@@ -11,7 +11,7 @@ use PublicInbox::GitAsyncCat;
 sub write_part { # Eml->each_part callback
 	my ($ary, $self) = @_;
 	my ($part, $depth, $idx) = @$ary;
-	if ($idx ne '1' || $self->{-raw_hdr}) {
+	if ($idx ne '1' || $self->{-raw_hdr}) { # lei mail-diff --raw-header
 		open my $fh, '>', "$self->{curdir}/$idx.hdr" or die "open: $!";
 		print $fh ${$part->{hdr}} or die "print $!";
 		close $fh or die "close $!";
@@ -20,7 +20,8 @@ sub write_part { # Eml->each_part callback
 	my ($s, $err) = msg_part_text($part, $ct);
 	my $sfx = defined($s) ? 'txt' : 'bin';
 	$s //= $part->body;
-	$s =~ s/\r+\n/\n/sg;
+	$s =~ s/\r\n/\n/gs; # TODO: consider \r+\n to match View
+	$s =~ s/\s*\z//s;
 	open my $fh, '>:utf8', "$self->{curdir}/$idx.$sfx" or die "open: $!";
 	print $fh $s or die "print $!";
 	close $fh or die "close $!";