X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=51723e55ffb44662087f349a41a69a30fb36c5c1;hb=537eb7ec8c0f8ebd6fa39807a08515ccd3c4be66;hp=605f68879ed2e2d5b0dd2e0f7920db2983ffb034;hpb=4c5fa84eec85cf406cbcd900f92dc478ed14ea30;p=public-inbox.git

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 605f6887..51723e55 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -50,11 +50,10 @@ 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 => $nparts,
 		parallel => 1,
 		transact_bytes => 0,
@@ -69,7 +68,9 @@ sub init_inbox {
 	my ($self, $parallel) = @_;
 	$self->{parallel} = $parallel;
 	$self->idx_init;
-	$self->git_init(0);
+	my $max_git = -1;
+	git_dir_latest($self, \$max_git);
+	$self->git_init($max_git >= 0 ? $max_git : 0);
 	$self->done;
 }
 
@@ -137,7 +138,7 @@ sub num_for {
 		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) {
@@ -173,8 +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;
 }
 
@@ -194,27 +194,45 @@ 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;
+
+		# idx_parts must be visible to all forked processes
+		my $idx = $self->{idx_parts} = [];
+		for my $i (0..$max) {
+			push @$idx,
+			     PublicInbox::SearchIdxPart->new($self, $i, $skel);
+		}
 
-	# 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);
@@ -223,6 +241,12 @@ 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) = @_;
@@ -240,11 +264,15 @@ 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);
 				}
@@ -253,9 +281,23 @@ 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 $self->{idx_parts};
@@ -328,7 +370,6 @@ sub git_init {
 	my ($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);
 
@@ -426,10 +467,11 @@ sub diff ($$$) {
 	use File::Temp qw(tempfile);
 	use PublicInbox::Spawn qw(spawn);
 
-	my ($ah, $an) = tempfile('email-cur-XXXXXXXX');
+	my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
 	print $ah $cur->as_string or die "print: $!";
 	close $ah or die "close: $!";
-	my ($bh, $bn) = tempfile('email-new-XXXXXXXX');
+	my ($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 ];
@@ -489,7 +531,7 @@ sub mark_deleted {
 	my $mids = mids($mime->header_obj);
 	my $cid = content_id($mime);
 	foreach my $mid (@$mids) {
-		$D->{$mid.$cid} = 1;
+		$D->{"$mid\0$cid"} = 1;
 	}
 }
 
@@ -507,7 +549,7 @@ sub reindex_oid {
 	my $num = -1;
 	my $del = 0;
 	foreach my $mid (@$mids) {
-		$del += (delete $D->{$mid.$cid} || 0);
+		$del += (delete $D->{"$mid\0$cid"} || 0);
 		my $n = $mm_tmp->num_for($mid);
 		if (defined $n && $n > $num) {
 			$mid0 = $mid;
@@ -518,7 +560,7 @@ sub reindex_oid {
 		$num = $$regen--;
 		die "BUG: ran out of article numbers\n" if $num <= 0;
 		my $mm = $self->{skel}->{mm};
-		foreach my $mid (@$mids) {
+		foreach my $mid (reverse @$mids) {
 			if ($mm->mid_set($num, $mid) == 1) {
 				$mid0 = $mid;
 				last;
@@ -526,7 +568,11 @@ sub reindex_oid {
 		}
 		if (!defined($mid0)) {
 			my $id = '<' . join('> <', @$mids) . '>';
-			warn "Message-Id $id unusable for $num\n";
+			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";
+			}
 		}
 	}
 
@@ -589,17 +635,22 @@ sub reindex {
 		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);
+
+			# can't use 'rev-list --count' if we use --diff-filter
+			my $fh = $git->popen(qw(log --pretty=tformat:%h
+					--no-notes --no-color --no-renames
+					--diff-filter=AM), $h, '--', 'm');
+			++$regen_max while <$fh>;
 		}
 		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);
+			--no-notes --no-color --no-abbrev --no-renames);
 
 	# if we are regenerating, we must not use a newer tip commit than what
 	# the regeneration counter used:
@@ -610,6 +661,7 @@ sub reindex {
 		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);
@@ -619,14 +671,31 @@ sub reindex {
 			} 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) {
+			} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/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;
-	defined $max and die "leftover article numbers at $min..$max\n";
+	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;