v2writable: clarify header cleanups

We want to make it clear to the code and DEBUG_DIFF users
that we do not introduce messages with unsuitable headers
into public archives.

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index d69934b0678aa2e7927b02f218524f4e7f4782c0..5d116a1c7207b9ea4c0b1f74b0a10ecba46f7e3c 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -288,6 +288,14 @@ sub extract_author_info ($) {
        ($name, $email);
 }
 
+# kill potentially confusing/misleading headers
+sub drop_unwanted_headers ($) {
+       my ($mime) = @_;
+
+       $mime->header_set($_) for qw(bytes lines content-length status);
+       $mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS;
+}
+
 # returns undef on duplicate
 # returns the :MARK of the most recent commit
 sub add {
@@ -321,9 +329,7 @@ sub add {
                _check_path($r, $w, $tip, $path) and return;
        }
 
-       # kill potentially confusing/misleading headers
-       $mime->header_set($_) for qw(bytes lines content-length status);
-       $mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS;
+       drop_unwanted_headers($mime);
 
        # spam check:
        if ($check_cb) {

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 605f68879ed2e2d5b0dd2e0f7920db2983ffb034..44b5528f5145bc3b751e604954de843280b3b23e 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -223,6 +223,12 @@ sub remove {
        my $mm = $skel->{mm};
        my $removed;
        my $mids = mids($mime->header_obj);
+
+       # We avoid introducing new blobs into git since the raw content
+       # can be slightly different, so we do not need the user-supplied
+       # message now that we have the mids and content_id
+       $mime = undef;
+
        foreach my $mid (@$mids) {
                $srch->reopen->each_smsg_by_mid($mid, sub {
                        my ($smsg) = @_;
@@ -430,6 +436,7 @@ sub diff ($$$) {
        print $ah $cur->as_string or die "print: $!";
        close $ah or die "close: $!";
        my ($bh, $bn) = tempfile('email-new-XXXXXXXX');
+       PublicInbox::Import::drop_unwanted_headers($new);
        print $bh $new->as_string or die "print: $!";
        close $bh or die "close: $!";
        my $cmd = [ qw(diff -u), $an, $bn ];