diff options
Diffstat (limited to 'lib/PublicInbox/SearchIdx.pm')
-rw-r--r-- | lib/PublicInbox/SearchIdx.pm | 114 |
1 files changed, 29 insertions, 85 deletions
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 8a529c66..8200b54c 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -16,18 +16,14 @@ $Email::MIME::ContentType::STRICT_PARAMS = 0; use base qw(PublicInbox::Search); use PublicInbox::MID qw/mid_clean id_compress mid_mime/; use PublicInbox::MsgIter; +use PublicInbox::GitIdx; use Carp qw(croak); use POSIX qw(strftime); require PublicInbox::Git; -*xpfx = *PublicInbox::Search::xpfx; -use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian use constant { - PERM_UMASK => 0, - OLD_PERM_GROUP => 1, - OLD_PERM_EVERYBODY => 2, - PERM_GROUP => 0660, - PERM_EVERYBODY => 0664, + MAX_MID_SIZE => 244, # max term size - 1 in Xapian + BATCH_BYTES => 1_000_000, }; sub new { @@ -46,11 +42,10 @@ sub new { } require Search::Xapian::WritableDatabase; my $self = bless { git_dir => $git_dir, -altid => $altid }, $class; - my $perm = $self->_git_config_perm; - my $umask = _umask_for($perm); - $self->{umask} = $umask; + my $git = $self->{git} = PublicInbox::Git->new($git_dir); + my $umask = git_umask_for($git); + $self->{'umask'} = $umask; $self->{lock_path} = "$git_dir/ssoma.lock"; - $self->{git} = PublicInbox::Git->new($git_dir); $self->{creat} = ($creat || 0) == 1; $self; } @@ -72,7 +67,6 @@ sub _xdb_acquire { require File::Path; _lock_acquire($self); File::Path::mkpath($dir); - $self->{batch_size} = 100; $flag = Search::Xapian::DB_CREATE_OR_OPEN; } $self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag); @@ -160,12 +154,12 @@ sub add_message { } $smsg = PublicInbox::SearchMsg->new($mime); my $doc = $smsg->{doc}; - $doc->add_term(xpfx('mid') . $mid); + $doc->add_term('Q' . $mid); my $subj = $smsg->subject; if ($subj ne '') { my $path = $self->subject_path($subj); - $doc->add_term(xpfx('path') . id_compress($path)); + $doc->add_term('XPATH' . id_compress($path)); } add_values($smsg, $bytes, $num); @@ -332,7 +326,7 @@ sub link_message { } else { $tid = $self->next_thread_id; } - $doc->add_term(xpfx('thread') . $tid); + $doc->add_term('G' . $tid); } sub index_blob { @@ -393,7 +387,16 @@ sub do_cat_mail { sub index_sync { my ($self, $opts) = @_; - with_umask($self, sub { $self->_index_sync($opts) }); + with_umask($self->{'umask'}, sub { $self->_index_sync($opts) }); +} + +sub batch_adjust ($$$$) { + my ($max, $bytes, $batch_cb, $latest) = @_; + $$max -= $bytes; + if ($$max <= 0) { + $$max = BATCH_BYTES; + $batch_cb->($latest, 1); + } } sub rlog { @@ -405,23 +408,21 @@ sub rlog { my $git = $self->{git}; my $latest; my $bytes; - my $max = $self->{batch_size}; # may be undef + my $max = BATCH_BYTES; local $/ = "\n"; my $line; while (defined($line = <$log>)) { if ($line =~ /$addmsg/o) { my $blob = $1; my $mime = do_cat_mail($git, $blob, \$bytes) or next; + batch_adjust(\$max, $bytes, $batch_cb, $latest); $add_cb->($self, $mime, $bytes, $blob); } elsif ($line =~ /$delmsg/o) { my $blob = $1; - my $mime = do_cat_mail($git, $blob) or next; + my $mime = do_cat_mail($git, $blob, \$bytes) or next; + batch_adjust(\$max, $bytes, $batch_cb, $latest); $del_cb->($self, $mime); } elsif ($line =~ /^commit ($h40)/o) { - if (defined $max && --$max <= 0) { - $max = $self->{batch_size}; - $batch_cb->($latest, 1); - } $latest = $1; } } @@ -542,9 +543,9 @@ sub create_ghost { my $tid = $self->next_thread_id; my $doc = Search::Xapian::Document->new; - $doc->add_term(xpfx('mid') . $mid); - $doc->add_term(xpfx('thread') . $tid); - $doc->add_term(xpfx('type') . 'ghost'); + $doc->add_term('Q' . $mid); + $doc->add_term('G' . $tid); + $doc->add_term('T' . 'ghost'); my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid); $self->{xdb}->add_document($doc); @@ -555,75 +556,18 @@ sub create_ghost { sub merge_threads { my ($self, $winner_tid, $loser_tid) = @_; return if $winner_tid == $loser_tid; - my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid); - my $thread_pfx = xpfx('thread'); + my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid); my $db = $self->{xdb}; for (; $head != $tail; $head->inc) { my $docid = $head->get_docid; my $doc = $db->get_document($docid); - $doc->remove_term($thread_pfx . $loser_tid); - $doc->add_term($thread_pfx . $winner_tid); + $doc->remove_term('G' . $loser_tid); + $doc->add_term('G' . $winner_tid); $db->replace_document($docid, $doc); } } -sub _read_git_config_perm { - my ($self) = @_; - my @cmd = qw(config core.sharedRepository); - my $fh = PublicInbox::Git->new($self->{git_dir})->popen(@cmd); - local $/ = "\n"; - my $perm = <$fh>; - chomp $perm if defined $perm; - $perm; -} - -sub _git_config_perm { - my $self = shift; - my $perm = scalar @_ ? $_[0] : _read_git_config_perm($self); - return PERM_GROUP if (!defined($perm) || $perm eq ''); - return PERM_UMASK if ($perm eq 'umask'); - return PERM_GROUP if ($perm eq 'group'); - if ($perm =~ /\A(?:all|world|everybody)\z/) { - return PERM_EVERYBODY; - } - return PERM_GROUP if ($perm =~ /\A(?:true|yes|on|1)\z/); - return PERM_UMASK if ($perm =~ /\A(?:false|no|off|0)\z/); - - my $i = oct($perm); - return PERM_UMASK if ($i == PERM_UMASK); - return PERM_GROUP if ($i == OLD_PERM_GROUP); - return PERM_EVERYBODY if ($i == OLD_PERM_EVERYBODY); - - if (($i & 0600) != 0600) { - die "core.sharedRepository mode invalid: ". - sprintf('%.3o', $i) . "\nOwner must have permissions\n"; - } - ($i & 0666); -} - -sub _umask_for { - my ($perm) = @_; # _git_config_perm return value - my $rv = $perm; - return umask if $rv == 0; - - # set +x bit if +r or +w were set - $rv |= 0100 if ($rv & 0600); - $rv |= 0010 if ($rv & 0060); - $rv |= 0001 if ($rv & 0006); - (~$rv & 0777); -} - -sub with_umask { - my ($self, $cb) = @_; - my $old = umask $self->{umask}; - my $rv = eval { $cb->() }; - my $err = $@; - umask $old; - die $err if $@; - $rv; -} - sub DESTROY { # order matters for unlocking $_[0]->{xdb} = undef; |