*idx: pass $smsg in more places instead of many args

[public-inbox.git] / lib / PublicInbox / V2Writable.pm

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 82843241f50a507ad4001723f632b976b30c33c1..34dd139b8ab82495296ddb9abd76847dee54b5fc 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # This interface wraps and mimics PublicInbox::Import
@@ -150,9 +150,15 @@ 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);
+       my $smsg = bless {
+               bytes => $len,
+               num => $num,
+               blob => $oid,
+               mid => $mid0,
+       }, 'PublicInbox::Smsg';
+       $self->{over}->add_overview($mime, $smsg, $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 +182,7 @@ 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 +207,10 @@ 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
@@ -381,7 +386,7 @@ sub rewrite_internal ($$;$$$) {
        }
        my $over = $self->{over};
        my $cids = content_ids($old_mime);
-       my $removed;
+       my @removed;
        my $mids = mids($old_mime->header_obj);
 
        # We avoid introducing new blobs into git since the raw content
@@ -391,7 +396,7 @@ sub rewrite_internal ($$;$$$) {
        my $mark;
 
        foreach my $mid (@$mids) {
-               my %gone; # num => [ smsg, raw ]
+               my %gone; # num => [ smsg, $mime, raw ]
                my ($id, $prev);
                while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
                        my $msg = get_blob($self, $smsg);
@@ -402,8 +407,7 @@ sub rewrite_internal ($$;$$$) {
                        my $orig = $$msg;
                        my $cur = PublicInbox::MIME->new($msg);
                        if (content_matches($cids, $cur)) {
-                               $smsg->{mime} = $cur;
-                               $gone{$smsg->{num}} = [ $smsg, \$orig ];
+                               $gone{$smsg->{num}} = [ $smsg, $cur, \$orig ];
                        }
                }
                my $n = scalar keys %gone;
@@ -413,15 +417,16 @@ sub rewrite_internal ($$;$$$) {
                                join(',', sort keys %gone), "\n";
                }
                foreach my $num (keys %gone) {
-                       my ($smsg, $orig) = @{$gone{$num}};
-                       # $removed should only be set once assuming
+                       my ($smsg, $mime, $orig) = @{$gone{$num}};
+                       # @removed should only be set once assuming
                        # no bugs in our deduplication code:
-                       $removed = $smsg;
+                       @removed = (undef, $mime, $smsg);
                        my $oid = $smsg->{blob};
                        if ($replace_map) {
                                $replace_map->{$oid} = $sref;
                        } else {
                                ($mark, undef) = $im->remove($orig, $cmt_msg);
+                               $removed[0] = $mark;
                        }
                        $orig = undef;
                        if ($need_reindex) { # ->replace
@@ -441,15 +446,18 @@ sub rewrite_internal ($$;$$$) {
                my $rewrites = _replace_oids($self, $new_mime, $replace_map);
                return { rewrites => $rewrites, need_reindex => $need_reindex };
        }
-       $removed;
+       defined($mark) ? @removed : undef;
 }
 
-# public
+# public (see PublicInbox::Import->remove), but note the 3rd element
+# (retval[2]) is not part of the stable API shared with Import->remove
 sub remove {
        my ($self, $mime, $cmt_msg) = @_;
+       my @ret;
        $self->{-inbox}->with_umask(sub {
-               rewrite_internal($self, $mime, $cmt_msg);
+               @ret = rewrite_internal($self, $mime, $cmt_msg);
        });
+       defined($ret[0]) ? @ret : undef;
 }
 
 sub _replace ($$;$$) {
@@ -821,7 +829,7 @@ 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);
@@ -833,11 +841,7 @@ 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};
@@ -1268,15 +1272,17 @@ 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) {