X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=c4368cccc8502616ab8c4c536720d7c17106f596;hb=c4aa293b2320feb805c5afeaa373f608e5bc8618;hp=5c104d8ec27df12fa93528834f3d396e401e0691;hpb=0514c910b0a33fe758cd92fd89fa79a3291bf5fc;p=public-inbox.git

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 5c104d8e..c4368ccc 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -50,12 +50,12 @@ sub new {
 	}
 	$nparts = nproc() if ($nparts == 0);
 
+	$v2ibx = PublicInbox::InboxWritable->new($v2ibx);
 	my $self = {
 		-inbox => $v2ibx,
 		im => undef, #  PublicInbox::Import
-		xap_rw => undef, # PublicInbox::V2SearchIdx
-		xap_ro => undef,
 		partitions => $nparts,
+		parallel => 1,
 		transact_bytes => 0,
 		lock_path => "$dir/inbox.lock",
 		# limit each repo to 1GB or so
@@ -64,6 +64,16 @@ sub new {
 	bless $self, $class;
 }
 
+sub init_inbox {
+	my ($self, $parallel) = @_;
+	$self->{parallel} = $parallel;
+	$self->idx_init;
+	my $max_git = -1;
+	git_dir_latest($self, \$max_git);
+	$self->git_init($max_git >= 0 ? $max_git : 0);
+	$self->done;
+}
+
 # returns undef on duplicate or spam
 # mimics Import::add and wraps it for v2
 sub add {
@@ -93,7 +103,7 @@ sub add {
 	my $nparts = $self->{partitions};
 	my $part = $num % $nparts;
 	my $idx = $self->idx_part($part);
-	$idx->index_raw($len, $msgref, $num, $oid, $mid0);
+	$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
 	my $n = $self->{transact_bytes} += $len;
 	if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
 		$self->checkpoint;
@@ -118,17 +128,17 @@ sub num_for {
 		foreach my $m (@$mids) {
 			# read-only lookup now safe to do after above barrier
 			my $existing = $self->lookup_content($mime, $m);
-			if ($existing) {
-				warn "<$m> resent\n";
-				return; # easy, don't store duplicates
-			}
+			# 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;
 		}
 
 		# very unlikely:
 		warn "<$mid> reused for mismatched content\n";
 
 		# try the rest of the mids
-		foreach my $i (1..$#$mids) {
+		for(my $i = $#$mids; $i >= 1; $i--) {
 			my $m = $mids->[$i];
 			$num = $self->{skel}->{mm}->mid_insert($m);
 			if (defined $num) {
@@ -164,8 +174,7 @@ sub num_for_harder {
 			$num = $self->{skel}->{mm}->mid_insert($$mid0);
 		}
 	}
-	my @cur = $hdr->header_raw('Message-Id');
-	$hdr->header_set('Message-Id', "<$$mid0>", @cur);
+	PublicInbox::Import::append_mid($hdr, $$mid0);
 	$num;
 }
 
@@ -185,27 +194,41 @@ sub idx_init {
 	# frequently activated.
 	delete $ibx->{$_} foreach (qw(git mm search));
 
-	$self->lock_acquire;
+	$ibx->umask_prepare;
+	$ibx->with_umask(sub {
+		$self->lock_acquire;
 
-	# first time initialization, first we create the skeleton pipe:
-	my $skel = $self->{skel} = PublicInbox::SearchIdxSkeleton->new($self);
+		# first time initialization, first we create the skeleton pipe:
+		my $skel = PublicInbox::SearchIdxSkeleton->new($self);
+		$self->{skel} = $skel;
 
-	# need to create all parts before initializing msgmap FD
-	my $max = $self->{partitions} - 1;
-	my $idx = $self->{idx_parts} = [];
-	for my $i (0..$max) {
-		push @$idx, PublicInbox::SearchIdxPart->new($self, $i, $skel);
-	}
+		# need to create all parts before initializing msgmap FD
+		my $max = $self->{partitions} - 1;
+		@{$self->{idx_parts}} = map {
+			PublicInbox::SearchIdxPart->new($self, $_, $skel);
+		} (0..$max);
 
-	# Now that all subprocesses are up, we can open the FD for SQLite:
-	$skel->_msgmap_init->{dbh}->begin_work;
+		# Now that all subprocesses are up, we can open the FD for SQLite:
+		$skel->_msgmap_init->{dbh}->begin_work;
+	});
 }
 
-sub remove {
-	my ($self, $mime, $cmt_msg) = @_;
+sub purge_oids {
+	my ($self, $purge) = @_; # $purge = { $object_id => 1, ... }
+	$self->done;
+	my $pfx = "$self->{-inbox}->{mainrepo}/git";
+	foreach my $i (0..$self->{max_git}) {
+		my $git = PublicInbox::Git->new("$pfx/$i.git");
+		my $im = $self->import_init($git, 0);
+		$im->purge_oids($purge);
+	}
+}
+
+sub remove_internal {
+	my ($self, $mime, $cmt_msg, $purge) = @_;
 	$self->barrier;
 	$self->idx_init;
-	my $im = $self->importer;
+	my $im = $self->importer unless $purge;
 	my $ibx = $self->{-inbox};
 	my $srch = $ibx->search;
 	my $cid = content_id($mime);
@@ -214,6 +237,12 @@ 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) = @_;
@@ -231,11 +260,15 @@ sub remove {
 				# no bugs in our deduplication code:
 				$removed = $smsg;
 				$removed->{mime} = $cur;
-				$im->remove(\$orig, $cmt_msg);
+				my $oid = $smsg->{blob};
+				if ($purge) {
+					$purge->{$oid} = 1;
+				} else {
+					$im->remove(\$orig, $cmt_msg);
+				}
 				$orig = undef;
 				$removed->num; # memoize this for callers
 
-				my $oid = $smsg->{blob};
 				foreach my $idx (@$parts, $skel) {
 					$idx->remote_remove($oid, $mid);
 				}
@@ -244,9 +277,23 @@ sub remove {
 		});
 		$self->barrier;
 	}
+	if ($purge && scalar keys %$purge) {
+		purge_oids($self, $purge);
+	}
 	$removed;
 }
 
+sub remove {
+	my ($self, $mime, $cmt_msg) = @_;
+	remove_internal($self, $mime, $cmt_msg);
+}
+
+sub purge {
+	my ($self, $mime) = @_;
+	remove_internal($self, $mime, undef, {});
+}
+
+
 sub done {
 	my ($self) = @_;
 	my $locked = defined $self->{idx_parts};
@@ -280,7 +327,7 @@ sub barrier {
 		# Now deal with Xapian
 		$skel->barrier_init(scalar(@$parts));
 		# each partition needs to issue a barrier command to skel:
-		$_->barrier foreach @$parts;
+		$_->remote_barrier foreach @$parts;
 
 		$skel->barrier_wait; # wait for each Xapian partition
 
@@ -319,7 +366,6 @@ sub git_init {
 	my ($self, $new) = @_;
 	my $pfx = "$self->{-inbox}->{mainrepo}/git";
 	my $git_dir = "$pfx/$new.git";
-	die "$git_dir exists\n" if -e $git_dir;
 	my @cmd = (qw(git init --bare -q), $git_dir);
 	PublicInbox::Import::run_die(\@cmd);
 
@@ -350,6 +396,23 @@ sub git_init {
 	$git_dir
 }
 
+sub git_dir_latest {
+	my ($self, $max) = @_;
+	$$max = -1;
+	my $pfx = "$self->{-inbox}->{mainrepo}/git";
+	return unless -d $pfx;
+	my $latest;
+	opendir my $dh, $pfx or die "opendir $pfx: $!\n";
+	while (defined(my $git_dir = readdir($dh))) {
+		$git_dir =~ m!\A(\d+)\.git\z! or next;
+		if ($1 > $$max) {
+			$$max = $1;
+			$latest = "$pfx/$git_dir";
+		}
+	}
+	$latest;
+}
+
 sub importer {
 	my ($self) = @_;
 	my $im = $self->{im};
@@ -366,20 +429,9 @@ sub importer {
 			return $self->import_init($git, 0);
 		}
 	}
-	my $latest;
-	my $max = -1;
 	my $new = 0;
-	my $pfx = "$self->{-inbox}->{mainrepo}/git";
-	if (-d $pfx) {
-		foreach my $git_dir (glob("$pfx/*.git")) {
-			$git_dir =~ m!/(\d+)\.git\z! or next;
-			my $n = $1;
-			if ($n > $max) {
-				$max = $n;
-				$latest = $git_dir;
-			}
-		}
-	}
+	my $max;
+	my $latest = git_dir_latest($self, \$max);
 	if (defined $latest) {
 		my $git = PublicInbox::Git->new($latest);
 		my $packed_bytes = $git->packed_bytes;
@@ -405,6 +457,27 @@ sub import_init {
 	$self->{im} = $im;
 }
 
+# XXX experimental
+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: $!";
+	close $ah or die "close: $!";
+	my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1);
+	PublicInbox::Import::drop_unwanted_headers($new);
+	print $bh $new->as_string or die "print: $!";
+	close $bh or die "close: $!";
+	my $cmd = [ qw(diff -u), $an, $bn ];
+	print STDERR "# MID conflict <$mid>\n";
+	my $pid = spawn($cmd, undef, { 1 => 2 });
+	defined $pid or die "diff failed to spawn $!";
+	waitpid($pid, 0) == $pid or die "diff did not finish";
+	unlink($an, $bn);
+}
+
 sub lookup_content {
 	my ($self, $mime, $mid) = @_;
 	my $ibx = $self->{-inbox};
@@ -426,6 +499,10 @@ sub lookup_content {
 			$found = $smsg;
 			return 0; # break out of loop
 		}
+
+		# XXX DEBUG_DIFF is experimental and may be removed
+		diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
+
 		1; # continue
 	});
 	$found;
@@ -433,6 +510,8 @@ sub lookup_content {
 
 sub atfork_child {
 	my ($self) = @_;
+	my $fh = delete $self->{reindex_pipe};
+	close $fh if $fh;
 	if (my $parts = $self->{idx_parts}) {
 		$_->atfork_child foreach @$parts;
 	}
@@ -441,4 +520,174 @@ sub atfork_child {
 	}
 }
 
+sub mark_deleted {
+	my ($self, $D, $git, $oid) = @_;
+	my $msgref = $git->cat_file($oid);
+	my $mime = PublicInbox::MIME->new($$msgref);
+	my $mids = mids($mime->header_obj);
+	my $cid = content_id($mime);
+	foreach my $mid (@$mids) {
+		$D->{"$mid\0$cid"} = 1;
+	}
+}
+
+sub reindex_oid {
+	my ($self, $mm_tmp, $D, $git, $oid, $regen) = @_;
+	my $len;
+	my $msgref = $git->cat_file($oid, \$len);
+	my $mime = PublicInbox::MIME->new($$msgref);
+	my $mids = mids($mime->header_obj);
+	my $cid = content_id($mime);
+
+	# get the NNTP article number we used before, highest number wins
+	# and gets deleted from mm_tmp;
+	my $mid0;
+	my $num = -1;
+	my $del = 0;
+	foreach my $mid (@$mids) {
+		$del += (delete $D->{"$mid\0$cid"} || 0);
+		my $n = $mm_tmp->num_for($mid);
+		if (defined $n && $n > $num) {
+			$mid0 = $mid;
+			$num = $n;
+		}
+	}
+	if (!defined($mid0) && $regen && !$del) {
+		$num = $$regen--;
+		die "BUG: ran out of article numbers\n" if $num <= 0;
+		my $mm = $self->{skel}->{mm};
+		foreach my $mid (reverse @$mids) {
+			if ($mm->mid_set($num, $mid) == 1) {
+				$mid0 = $mid;
+				last;
+			}
+		}
+		if (!defined($mid0)) {
+			my $id = '<' . join('> <', @$mids) . '>';
+			warn "Message-ID $id unusable for $num\n";
+			foreach my $mid (@$mids) {
+				defined(my $n = $mm->num_for($mid)) or next;
+				warn "#$n previously mapped for <$mid>\n";
+			}
+		}
+	}
+
+	if (!defined($mid0) || $del) {
+		if (!defined($mid0) && $del) { # expected for deletes
+			$$regen--;
+			return
+		}
+
+		my $id = '<' . join('> <', @$mids) . '>';
+		defined($mid0) or
+			warn "Skipping $id, no article number found\n";
+		if ($del && defined($mid0)) {
+			warn "$id was deleted $del " .
+				"time(s) but mapped to article #$num\n";
+		}
+		return;
+
+	}
+	$mm_tmp->mid_delete($mid0) or
+		die "failed to delete <$mid0> for article #$num\n";
+
+	my $nparts = $self->{partitions};
+	my $part = $num % $nparts;
+	my $idx = $self->idx_part($part);
+	$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
+	my $n = $self->{transact_bytes} += $len;
+	if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
+		$git->cleanup;
+		$mm_tmp->atfork_prepare;
+		$self->done; # release lock
+		# allow -watch or -mda to write...
+		$self->idx_init; # reacquire lock
+		$mm_tmp->atfork_parent;
+	}
+}
+
+sub reindex {
+	my ($self, $regen) = @_;
+	my $ibx = $self->{-inbox};
+	my $pfx = "$ibx->{mainrepo}/git";
+	my $max_git;
+	my $latest = git_dir_latest($self, \$max_git);
+	return unless defined $latest;
+	my $head = $ibx->{ref_head} || 'refs/heads/master';
+	$self->idx_init; # acquire lock
+	my $x40 = qr/[a-f0-9]{40}/;
+	my $mm_tmp = $self->{skel}->{mm}->tmp_clone;
+	if (!$regen) {
+		my (undef, $max) = $mm_tmp->minmax;
+		unless (defined $max) {
+			$regen = 1;
+			warn
+"empty msgmap.sqlite3, regenerating article numbers\n";
+		}
+	}
+	my $tip; # latest commit out of all git repos
+	if ($regen) {
+		my $regen_max = 0;
+		for (my $cur = $max_git; $cur >= 0; $cur--) {
+			die "already reindexing!\n" if $self->{reindex_pipe};
+			my $git = PublicInbox::Git->new("$pfx/$cur.git");
+			-d $git->{git_dir} or next; # missing parts are fine
+			chomp($tip = $git->qx('rev-parse', $head)) unless $tip;
+			my $h = $cur == $max_git ? $tip : $head;
+			my @count = ('rev-list', '--count', $h, '--', 'm');
+			$regen_max += $git->qx(@count);
+		}
+		die "No messages found in $pfx/*.git, bug?\n" unless $regen_max;
+		$regen = \$regen_max;
+	}
+	my $D = {};
+	my @cmd = qw(log --raw -r --pretty=tformat:%h
+			--no-notes --no-color --no-abbrev);
+
+	# if we are regenerating, we must not use a newer tip commit than what
+	# the regeneration counter used:
+	$tip ||= $head;
+
+	# work backwards through history
+	for (my $cur = $max_git; $cur >= 0; $cur--) {
+		die "already reindexing!\n" if delete $self->{reindex_pipe};
+		my $cmt;
+		my $git_dir = "$pfx/$cur.git";
+		-d $git_dir or next; # missing parts are fine
+		my $git = PublicInbox::Git->new($git_dir);
+		my $h = $cur == $max_git ? $tip : $head;
+		my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $h);
+		while (<$fh>) {
+			if (/\A$x40$/o) {
+				chomp($cmt = $_);
+			} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
+				$self->reindex_oid($mm_tmp, $D, $git, $1,
+						$regen);
+			} elsif (m!\A:\d{6} 100644 $x40 ($x40) [AM]\t_/D$!o) {
+				$self->mark_deleted($D, $git, $1);
+			}
+		}
+		delete $self->{reindex_pipe};
+	}
+	my $gaps;
+	if ($regen && $$regen != 0) {
+		warn "W: leftover article number ($$regen)\n";
+		$gaps = 1;
+	}
+	my ($min, $max) = $mm_tmp->minmax;
+	if (defined $max) {
+		warn "W: leftover article numbers at $min..$max\n";
+		$gaps = 1;
+	}
+	warn "W: were old git partitions deleted?\n" if $gaps;
+	my @d = sort keys %$D;
+	if (@d) {
+		warn "BUG: ", scalar(@d)," unseen deleted messages marked\n";
+		foreach (@d) {
+			my ($mid, undef) = split(/\0/, $_, 2);
+			warn "<$mid>\n";
+		}
+	}
+}
+
 1;