use PublicInbox::Inbox;
use PublicInbox::OverIdx;
use PublicInbox::Msgmap;
-use PublicInbox::Spawn;
+use PublicInbox::Spawn qw(spawn);
+use PublicInbox::SearchIdx;
use IO::Handle;
# an estimate of the post-packed size to the raw uncompressed size
my $hdr = $mime->header_obj;
my $dig = content_digest($mime);
- $$mid0 = PublicInbox::Import::digest2mid($dig);
+ $$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
my $num = $self->{mm}->mid_insert($$mid0);
unless (defined $num) {
# it's hard to spoof the last Received: header
my @recvd = $hdr->header_raw('Received');
$dig->add("Received: $_") foreach (@recvd);
- $$mid0 = PublicInbox::Import::digest2mid($dig);
+ $$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
$num = $self->{mm}->mid_insert($$mid0);
# fall back to a random Message-ID and give up determinism:
until (defined($num)) {
$dig->add(rand);
- $$mid0 = PublicInbox::Import::digest2mid($dig);
+ $$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
warn "using random Message-ID <$$mid0> as fallback\n";
$num = $self->{mm}->mid_insert($$mid0);
}
$purges;
}
+sub content_ids ($) {
+ my ($mime) = @_;
+ my @cids = ( content_id($mime) );
+
+ # Email::MIME->as_string doesn't always round-trip, so we may
+ # use a second content_id
+ my $rt = content_id(PublicInbox::MIME->new(\($mime->as_string)));
+ push @cids, $rt if $cids[0] ne $rt;
+ \@cids;
+}
+
+sub content_matches ($$) {
+ my ($cids, $existing) = @_;
+ my $cid = content_id($existing);
+ foreach (@$cids) {
+ return 1 if $_ eq $cid
+ }
+ 0
+}
+
sub remove_internal {
my ($self, $mime, $cmt_msg, $purge) = @_;
$self->idx_init;
my $im = $self->importer unless $purge;
my $over = $self->{over};
- my $cid = content_id($mime);
+ my $cids = content_ids($mime);
my $parts = $self->{idx_parts};
my $mm = $self->{mm};
my $removed;
}
my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
- if (content_id($cur) eq $cid) {
+ if (content_matches($cids, $cur)) {
$smsg->{mime} = $cur;
$gone{$smsg->{num}} = [ $smsg, \$orig ];
}
sub diff ($$$) {
my ($mid, $cur, $new) = @_;
use File::Temp qw(tempfile);
- use PublicInbox::Spawn qw(spawn);
my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
print $ah $cur->as_string or die "print: $!";
sub lookup_content {
my ($self, $mime, $mid) = @_;
my $over = $self->{over};
- my $cid = content_id($mime);
- my $found;
+ my $cids = content_ids($mime);
my ($id, $prev);
while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
next;
}
my $cur = PublicInbox::MIME->new($msg);
- if (content_id($cur) eq $cid) {
+ if (content_matches($cids, $cur)) {
$smsg->{mime} = $cur;
- $found = $smsg;
- last;
+ return $smsg;
}
+
# XXX DEBUG_DIFF is experimental and may be removed
diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
}
- $found;
+ undef;
}
sub atfork_child {
$heads;
}
-sub is_ancestor ($$$) {
- my ($git, $cur, $tip) = @_;
- return 0 unless $git->check($cur);
- my $cmd = [ 'git', "--git-dir=$git->{git_dir}",
- qw(merge-base --is-ancestor), $cur, $tip ];
- my $pid = spawn($cmd);
- defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
- waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
- $? == 0;
-}
+*is_ancestor = *PublicInbox::SearchIdx::is_ancestor;
sub index_prepare {
my ($self, $opts, $epoch_max, $ranges) = @_;