X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=d39a6f894539b4dce8de87c7360f7724a38b86d7;hb=e5dbf0680cfbfa81bad38457c0430fd260dda682;hp=573a92aacdf14b2ae349353b25a4d33399236d10;hpb=04ad02d739b352514ddfb5cc659bb4a69c4d07e1;p=public-inbox.git diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm index 573a92aa..d39a6f89 100644 --- a/lib/PublicInbox/V2Writable.pm +++ b/lib/PublicInbox/V2Writable.pm @@ -150,9 +150,9 @@ sub add { # indexes a message, returns true if checkpointing is needed sub do_idx ($$$$$$$) { my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_; - $self->{over}->add_overview($mime, $len, $num, $oid, $mid0); + $self->{over}->add_overview($mime, $len, $num, $oid, $mid0, $self); my $idx = idx_shard($self, $num % $self->{shards}); - $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime); + $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime, $self); my $n = $self->{transact_bytes} += $len; $n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards}); } @@ -176,7 +176,7 @@ sub _add { defined $num or return; # duplicate defined $mid0 or die "BUG: $mid0 undefined\n"; my $im = $self->importer; - my $cmt = $im->add($mime); + my $cmt = $im->add($mime, undef, $self); # sets $self->{(au|co)time} $cmt = $im->get_mark($cmt); $self->{last_commit}->[$self->{epoch_max}] = $cmt; @@ -201,11 +201,10 @@ sub v2_num_for { # crap, Message-ID is already known, hope somebody just resent: foreach my $m (@$mids) { # read-only lookup now safe to do after above barrier - my $existing = lookup_content($self, $mime, $m); # easy, don't store duplicates # note: do not add more diagnostic info here since # it gets noisy on public-inbox-watch restarts - return () if $existing; + return () if content_exists($self, $mime, $m); } # AltId may pre-populate article numbers (e.g. X-Mail-Count @@ -824,7 +823,7 @@ sub get_blob ($$) { $ibx->msg_by_smsg($smsg); } -sub lookup_content ($$$) { +sub content_exists ($$$) { my ($self, $mime, $mid) = @_; my $over = $self->{over}; my $cids = content_ids($mime); @@ -836,11 +835,7 @@ sub lookup_content ($$$) { next; } my $cur = PublicInbox::MIME->new($msg); - if (content_matches($cids, $cur)) { - $smsg->{mime} = $cur; - return $smsg; - } - + return 1 if content_matches($cids, $cur); # XXX DEBUG_DIFF is experimental and may be removed diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF}; @@ -1271,15 +1266,17 @@ sub index_epoch ($$$) { $pr->("$i.git indexing $range\n"); } - my @cmd = qw(log --raw -r --pretty=tformat:%H + my @cmd = qw(log --raw -r --pretty=tformat:%H.%at.%ct --no-notes --no-color --no-abbrev --no-renames); my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range); my $cmt; while (<$fh>) { chomp; $self->{current_info} = "$i.git $_"; - if (/\A$x40$/o && !defined($cmt)) { - $cmt = $_; + if (/\A($x40)\.([0-9]+)\.([0-9]+)$/o) { + $cmt //= $1; + $self->{autime} = $2; + $self->{cotime} = $3; } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) { reindex_oid($self, $sync, $git, $1); } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/o) {