v2writable: clarify header cleanups

[public-inbox.git] / lib / PublicInbox / Import.pm

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index fc740fa451c9d7ad19da99c1dc0a5490358674ae..5d116a1c7207b9ea4c0b1f74b0a10ecba46f7e3c 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -11,8 +11,9 @@ use base qw(PublicInbox::Lock);
 use PublicInbox::Spawn qw(spawn);
 use PublicInbox::MID qw(mids mid_mime mid2path);
 use PublicInbox::Address;
-use PublicInbox::MsgTime qw(msg_timestamp);
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 use PublicInbox::ContentId qw(content_digest);
+use PublicInbox::MDA;
 
 sub new {
        my ($class, $git, $name, $email, $ibx) = @_;
@@ -243,9 +244,8 @@ sub remove {
        (($self->{tip} = ":$commit"), $cur);
 }
 
-sub parse_date ($) {
-       my ($mime) = @_;
-       my ($ts, $zone) = msg_timestamp($mime->header_obj);
+sub git_timestamp {
+       my ($ts, $zone) = @_;
        $ts = 0 if $ts < 0; # git uses unsigned times
        "$ts $zone";
 }
@@ -288,13 +288,25 @@ sub extract_author_info ($) {
        ($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 {
        my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
 
        my ($name, $email) = extract_author_info($mime);
-       my $date_raw = parse_date($mime);
+       my $hdr = $mime->header_obj;
+       my @at = msg_datestamp($hdr);
+       my @ct = msg_timestamp($hdr);
+       my $author_time_raw = git_timestamp(@at);
+       my $commit_time_raw = git_timestamp(@ct);
        my $subject = $mime->header('Subject');
        $subject = '(no subject)' unless defined $subject;
        my $path_type = $self->{path_type};
@@ -317,8 +329,7 @@ sub add {
                _check_path($r, $w, $tip, $path) and return;
        }
 
-       # kill potentially confusing/misleading headers
-       $mime->header_set($_) for qw(bytes lines content-length status);
+       drop_unwanted_headers($mime);
 
        # spam check:
        if ($check_cb) {
@@ -347,8 +358,8 @@ sub add {
 
        utf8::encode($subject);
        print $w "commit $ref\nmark :$commit\n",
-               "author $name <$email> $date_raw\n",
-               "committer $self->{ident} ", now_raw(), "\n" or wfail;
+               "author $name <$email> $author_time_raw\n",
+               "committer $self->{ident} $commit_time_raw\n" or wfail;
        print $w "data ", (length($subject) + 1), "\n",
                $subject, "\n\n" or wfail;
        if ($tip ne '') {