X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=4e951bbedc7449d899a683b8ce6f965f3d291e5e;hb=227a1d886672767e37cc86a3432952c14eb8a143;hp=5559b39d80b78642b96ca2b746909710890de325;hpb=ebb59815035b42c276a89a585e16e69f51dbdb98;p=public-inbox.git diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 5559b39d..4e951bbe 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2018 all contributors +# Copyright (C) 2015-2019 all contributors # License: AGPL-3.0+ # based on notmuch, but with no concept of folders, files or flags # @@ -9,159 +9,175 @@ package PublicInbox::SearchIdx; use strict; use warnings; -use Fcntl qw(:flock :DEFAULT); +use base qw(PublicInbox::Search PublicInbox::Lock); use PublicInbox::MIME; -use Email::MIME::ContentType; -$Email::MIME::ContentType::STRICT_PARAMS = 0; -use base qw(PublicInbox::Search); -use PublicInbox::MID qw/mid_clean id_compress mid_mime/; +use PublicInbox::InboxWritable; +use PublicInbox::MID qw/mid_clean mid_mime mids_for_index/; use PublicInbox::MsgIter; use Carp qw(croak); use POSIX qw(strftime); -require PublicInbox::Git; - +use PublicInbox::OverIdx; +use PublicInbox::Spawn qw(spawn); +use PublicInbox::Git qw(git_unquote); +my $X = \%PublicInbox::Search::X; +my ($DB_CREATE_OR_OPEN, $DB_OPEN); use constant { - MAX_MID_SIZE => 244, # max term size - 1 in Xapian - PERM_UMASK => 0, - OLD_PERM_GROUP => 1, - OLD_PERM_EVERYBODY => 2, - PERM_GROUP => 0660, - PERM_EVERYBODY => 0664, - BATCH_BYTES => 1_000_000, + BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ? + 0x7fffffff : 1_000_000, DEBUG => !!$ENV{DEBUG}, }; -my %GIT_ESC = ( - a => "\a", - b => "\b", - f => "\f", - n => "\n", - r => "\r", - t => "\t", - v => "\013", -); - -sub git_unquote ($) { - my ($s) = @_; - return $s unless ($s =~ /\A"(.*)"\z/); - $s = $1; - $s =~ s/\\([abfnrtv])/$GIT_ESC{$1}/g; - $s =~ s/\\([0-7]{1,3})/chr(oct($1))/ge; - $s; -} +my $xapianlevels = qr/\A(?:full|medium)\z/; sub new { - my ($class, $inbox, $creat) = @_; - my $git_dir = $inbox; - my $altid; - if (ref $inbox) { - $git_dir = $inbox->{mainrepo}; - $altid = $inbox->{altid}; - if ($altid) { - require PublicInbox::AltId; - $altid = [ map { - PublicInbox::AltId->new($inbox, $_); - } @$altid ]; + my ($class, $ibx, $creat, $shard) = @_; + ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx"; + my $levels = qr/\A(?:full|medium|basic)\z/; + my $inboxdir = $ibx->{inboxdir}; + my $version = $ibx->version; + my $indexlevel = 'full'; + my $altid = $ibx->{altid}; + if ($altid) { + require PublicInbox::AltId; + $altid = [ map { PublicInbox::AltId->new($ibx, $_); } @$altid ]; + } + if ($ibx->{indexlevel}) { + if ($ibx->{indexlevel} =~ $levels) { + $indexlevel = $ibx->{indexlevel}; + } else { + die("Invalid indexlevel $ibx->{indexlevel}\n"); } } - 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; - $self->{lock_path} = "$git_dir/ssoma.lock"; - $self->{git} = PublicInbox::Git->new($git_dir); + $ibx = PublicInbox::InboxWritable->new($ibx); + my $self = bless { + inboxdir => $inboxdir, + -inbox => $ibx, + git => $ibx->git, + -altid => $altid, + version => $version, + indexlevel => $indexlevel, + }, $class; + $ibx->umask_prepare; + if ($version == 1) { + $self->{lock_path} = "$inboxdir/ssoma.lock"; + my $dir = $self->xdir; + $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3"); + } elsif ($version == 2) { + defined $shard or die "shard is required for v2\n"; + # shard is a number + $self->{shard} = $shard; + $self->{lock_path} = undef; + } else { + die "unsupported inbox version=$version\n"; + } $self->{creat} = ($creat || 0) == 1; $self; } +sub need_xapian ($) { $_[0]->{indexlevel} =~ $xapianlevels } + sub _xdb_release { my ($self) = @_; - my $xdb = delete $self->{xdb} or croak 'not acquired'; - $xdb->close; - _lock_release($self) if $self->{creat}; + if (need_xapian($self)) { + my $xdb = delete $self->{xdb} or croak 'not acquired'; + $xdb->close; + } + $self->lock_release if $self->{creat}; undef; } -sub _xdb_acquire { - my ($self) = @_; - croak 'already acquired' if $self->{xdb}; - my $dir = PublicInbox::Search->xdir($self->{git_dir}); - my $flag = Search::Xapian::DB_OPEN; - if ($self->{creat}) { - require File::Path; - _lock_acquire($self); - File::Path::mkpath($dir); - $flag = Search::Xapian::DB_CREATE_OR_OPEN; +sub load_xapian_writable () { + return 1 if $X->{WritableDatabase}; + PublicInbox::Search::load_xapian() or return; + my $xap = $PublicInbox::Search::Xap; + for (qw(Document TermGenerator WritableDatabase)) { + $X->{$_} = $xap.'::'.$_; } - $self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag); + eval 'require '.$X->{WritableDatabase} or die; + *sortable_serialise = $xap.'::sortable_serialise'; + $DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()'); + $DB_OPEN = eval($xap.'::DB_OPEN()'); + 1; } -# we only acquire the flock if creating or reindexing; -# PublicInbox::Import already has the lock on its own. -sub _lock_acquire { +sub _xdb_acquire { my ($self) = @_; - croak 'already locked' if $self->{lockfh}; - sysopen(my $lockfh, $self->{lock_path}, O_WRONLY|O_CREAT) or - die "failed to open lock $self->{lock_path}: $!\n"; - flock($lockfh, LOCK_EX) or die "lock failed: $!\n"; - $self->{lockfh} = $lockfh; -} + my $flag; + my $dir = $self->xdir; + if (need_xapian($self)) { + croak 'already acquired' if $self->{xdb}; + load_xapian_writable(); + $flag = $self->{creat} ? $DB_CREATE_OR_OPEN : $DB_OPEN; + } + if ($self->{creat}) { + require File::Path; + $self->lock_acquire; -sub _lock_release { - my ($self) = @_; - my $lockfh = delete $self->{lockfh} or croak 'not locked'; - flock($lockfh, LOCK_UN) or die "unlock failed: $!\n"; - close $lockfh or die "close failed: $!\n"; + # don't create empty Xapian directories if we don't need Xapian + my $is_shard = defined($self->{shard}); + if (!$is_shard || ($is_shard && need_xapian($self))) { + File::Path::mkpath($dir); + } + } + return unless defined $flag; + my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) }; + if ($@) { + die "Failed opening $dir: ", $@; + } + $self->{xdb} = $xdb; } sub add_val ($$$) { my ($doc, $col, $num) = @_; - $num = Search::Xapian::sortable_serialise($num); + $num = sortable_serialise($num); $doc->add_value($col, $num); } -sub add_values ($$$) { - my ($smsg, $bytes, $num) = @_; - - my $ts = $smsg->ts; - my $doc = $smsg->{doc}; - add_val($doc, &PublicInbox::Search::TS, $ts); - - defined($num) and add_val($doc, &PublicInbox::Search::NUM, $num); +sub term_generator ($) { # write-only + my ($self) = @_; - defined($bytes) and add_val($doc, &PublicInbox::Search::BYTES, $bytes); + $self->{term_generator} //= do { + my $tg = $X->{TermGenerator}->new; + $tg->set_stemmer($self->stemmer); + $tg; + } +} - add_val($doc, &PublicInbox::Search::LINES, - $smsg->{mime}->body_raw =~ tr!\n!\n!); +sub index_text ($$$$) { + my ($self, $text, $wdf_inc, $prefix) = @_; + my $tg = term_generator($self); # man Search::Xapian::TermGenerator - my $yyyymmdd = strftime('%Y%m%d', gmtime($ts)); - add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd); + if ($self->{indexlevel} eq 'full') { + $tg->index_text($text, $wdf_inc, $prefix); + $tg->increase_termpos; + } else { + $tg->index_text_without_positions($text, $wdf_inc, $prefix); + } } sub index_users ($$) { - my ($tg, $smsg) = @_; + my ($self, $smsg) = @_; my $from = $smsg->from; my $to = $smsg->to; my $cc = $smsg->cc; - $tg->index_text($from, 1, 'A'); # A - author - $tg->increase_termpos; - $tg->index_text($to, 1, 'XTO') if $to ne ''; - $tg->increase_termpos; - $tg->index_text($cc, 1, 'XCC') if $cc ne ''; - $tg->increase_termpos; + index_text($self, $from, 1, 'A'); # A - author + index_text($self, $to, 1, 'XTO') if $to ne ''; + index_text($self, $cc, 1, 'XCC') if $cc ne ''; } -sub index_text_inc ($$$) { - my ($tg, $text, $pfx) = @_; - $tg->index_text($text, 1, $pfx); - $tg->increase_termpos; +sub index_diff_inc ($$$$) { + my ($self, $text, $pfx, $xnq) = @_; + if (@$xnq) { + index_text($self, join("\n", @$xnq), 1, 'XNQ'); + @$xnq = (); + } + index_text($self, $text, 1, $pfx); } sub index_old_diff_fn { - my ($tg, $seen, $fa, $fb) = @_; + my ($self, $seen, $fa, $fb, $xnq) = @_; # no renames or space support for traditional diffs, # find the number of leading common paths to strip: @@ -171,7 +187,9 @@ sub index_old_diff_fn { $fa = join('/', @fa); $fb = join('/', @fb); if ($fa eq $fb) { - index_text_inc($tg, $fa,'XDFN') unless $seen->{$fa}++; + unless ($seen->{$fa}++) { + index_diff_inc($self, $fa, 'XDFN', $xnq); + } return 1; } shift @fa; @@ -181,43 +199,51 @@ sub index_old_diff_fn { } sub index_diff ($$$) { - my ($tg, $lines, $doc) = @_; + my ($self, $txt, $doc) = @_; my %seen; my $in_diff; - foreach (@$lines) { + my @xnq; + my $xnq = \@xnq; + foreach (split(/\n/, $txt)) { if ($in_diff && s/^ //) { # diff context - index_text_inc($tg, $_, 'XDFCTX'); + index_diff_inc($self, $_, 'XDFCTX', $xnq); } elsif (/^-- $/) { # email signature begins $in_diff = undef; } elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) { my ($fa, $fb) = ($1, $2); my $fn = (split('/', git_unquote($fa), 2))[1]; - index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $fn = (split('/', git_unquote($fb), 2))[1]; - index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; # traditional diff: } elsif (m/^diff -(.+) (\S+) (\S+)$/) { my ($opt, $fa, $fb) = ($1, $2, $3); + push @xnq, $_; # only support unified: next unless $opt =~ /[uU]/; - $in_diff = index_old_diff_fn($tg, \%seen, $fa, $fb); + $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb, + $xnq); } elsif (m!^--- ("?a/.+)!) { - my $fn = (split('/', git_unquote($1), 2))[1]; - index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + my $fn = $1; + $fn = (split('/', git_unquote($fn), 2))[1]; + $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; } elsif (m!^\+\+\+ ("?b/.+)!) { - my $fn = (split('/', git_unquote($1), 2))[1]; - index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + my $fn = $1; + $fn = (split('/', git_unquote($fn), 2))[1]; + $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; } elsif (/^--- (\S+)/) { $in_diff = $1; + push @xnq, $_; } elsif (defined $in_diff && /^\+\+\+ (\S+)/) { - $in_diff = index_old_diff_fn($tg, \%seen, $in_diff, $1); + $in_diff = index_old_diff_fn($self, \%seen, $in_diff, + $1, $xnq); } elsif ($in_diff && s/^\+//) { # diff added - index_text_inc($tg, $_, 'XDFB'); + index_diff_inc($self, $_, 'XDFB', $xnq); } elsif ($in_diff && s/^-//) { # diff removed - index_text_inc($tg, $_, 'XDFA'); + index_diff_inc($self, $_, 'XDFA', $xnq); } elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) { my ($ba, $bb) = ($1, $2); index_git_blob_id($doc, 'XDFPRE', $ba); @@ -227,236 +253,225 @@ sub index_diff ($$$) { # traditional diff w/o -p } elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) { # hunk header context - index_text_inc($tg, $1, 'XDFHH'); + index_diff_inc($self, $1, 'XDFHH', $xnq); # ignore the following lines: - } elsif (/^(?:dis)similarity index/) { - } elsif (/^(?:old|new) mode/) { - } elsif (/^(?:deleted|new) file mode/) { - } elsif (/^(?:copy|rename) (?:from|to) /) { - } elsif (/^(?:dis)?similarity index /) { - } elsif (/^\\ No newline at end of file/) { - } elsif (/^Binary files .* differ/) { + } elsif (/^(?:dis)similarity index/ || + /^(?:old|new) mode/ || + /^(?:deleted|new) file mode/ || + /^(?:copy|rename) (?:from|to) / || + /^(?:dis)?similarity index / || + /^\\ No newline at end of file/ || + /^Binary files .* differ/) { + push @xnq, $_; } elsif ($_ eq '') { - $in_diff = undef; + # possible to be in diff context, some mail may be + # stripped by MUA or even GNU diff(1). "git apply" + # treats a bare "\n" as diff context, too } else { + push @xnq, $_; warn "non-diff line: $_\n" if DEBUG && $_ ne ''; $in_diff = undef; } } + + index_text($self, join("\n", @xnq), 1, 'XNQ'); } sub index_body ($$$) { - my ($tg, $lines, $doc) = @_; - my $txt = join("\n", @$lines); - $tg->index_text($txt, !!$doc, $doc ? 'XNQ' : 'XQUOT'); - $tg->increase_termpos; - # does it look like a diff? - if ($doc && $txt =~ /^(?:diff|---|\+\+\+) /ms) { - $txt = undef; - index_diff($tg, $lines, $doc); + my ($self, $txt, $doc) = @_; + if ($doc) { + # does it look like a diff? + if ($txt =~ /^(?:diff|---|\+\+\+) /ms) { + index_diff($self, $txt, $doc); + } else { + index_text($self, $txt, 1, 'XNQ'); + } + } else { + index_text($self, $txt, 0, 'XQUOT'); } - @$lines = (); } -sub add_message { - my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object - my $db = $self->{xdb}; - - my ($doc_id, $old_tid); - my $mid = mid_clean(mid_mime($mime)); +sub index_xapian { # msg_iter callback + my ($part, $depth, @idx) = @{$_[0]}; + my ($self, $doc) = @{$_[1]}; + my $ct = $part->content_type || 'text/plain'; + my $fn = $part->filename; + if (defined $fn && $fn ne '') { + index_text($self, $fn, 1, 'XFN'); + } - eval { - die 'Message-ID too long' if length($mid) > MAX_MID_SIZE; - my $smsg = $self->lookup_message($mid); - if ($smsg) { - # convert a ghost to a regular message - # it will also clobber any existing regular message - $doc_id = $smsg->{doc_id}; - $old_tid = $smsg->thread_id; + my ($s, undef) = msg_part_text($part, $ct); + defined $s or return; + + # split off quoted and unquoted blocks: + my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s); + $part = $s = undef; + index_body($self, $_, /\A>/ ? 0 : $doc) for @sections; +} + +sub add_xapian ($$$$$$) { + my ($self, $mime, $num, $oid, $mids, $mid0) = @_; + my $smsg = PublicInbox::SearchMsg->new($mime); + my $doc = $X->{Document}->new; + my $subj = $smsg->subject; + add_val($doc, PublicInbox::Search::TS(), $smsg->ts); + my @ds = gmtime($smsg->ds); + my $yyyymmdd = strftime('%Y%m%d', @ds); + add_val($doc, PublicInbox::Search::YYYYMMDD(), $yyyymmdd); + my $dt = strftime('%Y%m%d%H%M%S', @ds); + add_val($doc, PublicInbox::Search::DT(), $dt); + + my $tg = term_generator($self); + + $tg->set_document($doc); + index_text($self, $subj, 1, 'S') if $subj; + index_users($self, $smsg); + + msg_iter($mime, \&index_xapian, [ $self, $doc ]); + foreach my $mid (@$mids) { + index_text($self, $mid, 1, 'XM'); + + # because too many Message-IDs are prefixed with + # "Pine.LNX."... + if ($mid =~ /\w{12,}/) { + my @long = ($mid =~ /(\w{3,}+)/g); + index_text($self, join(' ', @long), 1, 'XM'); } - $smsg = PublicInbox::SearchMsg->new($mime); - my $doc = $smsg->{doc}; - $doc->add_term('Q' . $mid); - - my $subj = $smsg->subject; - if ($subj ne '') { - my $path = $self->subject_path($subj); - $doc->add_term('XPATH' . id_compress($path)); - } - - add_values($smsg, $bytes, $num); - - my $tg = $self->term_generator; - - $tg->set_document($doc); - $tg->index_text($subj, 1, 'S') if $subj; - $tg->increase_termpos; - - index_users($tg, $smsg); - - msg_iter($mime, sub { - my ($part, $depth, @idx) = @{$_[0]}; - my $ct = $part->content_type || 'text/plain'; - my $fn = $part->filename; - if (defined $fn && $fn ne '') { - $tg->index_text($fn, 1, 'XFN'); - } - - return if $ct =~ m!\btext/x?html\b!i; - - my $s = eval { $part->body_str }; - if ($@) { - if ($ct =~ m!\btext/plain\b!i) { - # Try to assume UTF-8 because Alpine - # seems to do wacky things and set - # charset=X-UNKNOWN - $part->charset_set('UTF-8'); - $s = eval { $part->body_str }; - $s = $part->body if $@; - } - } - defined $s or return; - - my (@orig, @quot); - my $body = $part->body; - my @lines = split(/\n/, $body); - while (defined(my $l = shift @lines)) { - if ($l =~ /^>/) { - index_body($tg, \@orig, $doc) if @orig; - push @quot, $l; - } else { - index_body($tg, \@quot, 0) if @quot; - push @orig, $l; - } - } - index_body($tg, \@quot, 0) if @quot; - index_body($tg, \@orig, $doc) if @orig; - }); - - link_message($self, $smsg, $old_tid); - $tg->index_text($mid, 1, 'XMID'); - $doc->set_data($smsg->to_doc_data($blob)); - - if (my $altid = $self->{-altid}) { - foreach my $alt (@$altid) { + } + $smsg->{to} = $smsg->{cc} = ''; + PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids); + my $data = $smsg->to_doc_data($oid, $mid0); + $doc->set_data($data); + if (my $altid = $self->{-altid}) { + foreach my $alt (@$altid) { + my $pfx = $alt->{xprefix}; + foreach my $mid (@$mids) { my $id = $alt->mid2alt($mid); next unless defined $id; - $doc->add_term($alt->{xprefix} . $id); + $doc->add_boolean_term($pfx . $id); } } - if (defined $doc_id) { - $db->replace_document($doc_id, $doc); - } else { - $doc_id = $db->add_document($doc); - } - }; - - if ($@) { - warn "failed to index message <$mid>: $@\n"; - return undef; } - $doc_id; + $doc->add_boolean_term('Q' . $_) foreach @$mids; + $self->{xdb}->replace_document($num, $doc); } -# returns deleted doc_id on success, undef on missing -sub remove_message { - my ($self, $mid) = @_; - my $db = $self->{xdb}; - my $doc_id; - $mid = mid_clean($mid); +sub _msgmap_init ($) { + my ($self) = @_; + die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1; + $self->{mm} //= eval { + require PublicInbox::Msgmap; + PublicInbox::Msgmap->new($self->{inboxdir}, 1); + }; +} +sub add_message { + # mime = Email::MIME object + my ($self, $mime, $bytes, $num, $oid, $mid0) = @_; + my $mids = mids_for_index($mime->header_obj); + $mid0 //= $mids->[0]; # v1 compatibility + $num //= do { # v1 + _msgmap_init($self); + index_mm($self, $mime); + }; eval { - $doc_id = $self->find_unique_doc_id('Q' . $mid); - if (defined $doc_id) { - $db->delete_document($doc_id); - } else { - warn "cannot remove non-existent <$mid>\n"; + if (need_xapian($self)) { + add_xapian($self, $mime, $num, $oid, $mids, $mid0); + } + if (my $over = $self->{over}) { + $over->add_overview($mime, $bytes, $num, $oid, $mid0); } }; if ($@) { - warn "failed to remove message <$mid>: $@\n"; + warn "failed to index message <".join('> <',@$mids).">: $@\n"; return undef; } - $doc_id; + $num; } -sub term_generator { # write-only - my ($self) = @_; - - my $tg = $self->{term_generator}; - return $tg if $tg; - - $tg = Search::Xapian::TermGenerator->new; - $tg->set_stemmer($self->stemmer); - - $self->{term_generator} = $tg; -} - -# increments last_thread_id counter -# returns a 64-bit integer represented as a hex string -sub next_thread_id { - my ($self) = @_; +# returns begin and end PostingIterator +sub find_doc_ids { + my ($self, $termval) = @_; my $db = $self->{xdb}; - my $last_thread_id = int($db->get_metadata('last_thread_id') || 0); - $db->set_metadata('last_thread_id', ++$last_thread_id); - - $last_thread_id; + ($db->postlist_begin($termval), $db->postlist_end($termval)); } -sub link_message { - my ($self, $smsg, $old_tid) = @_; - my $doc = $smsg->{doc}; - my $mid = $smsg->mid; - my $mime = $smsg->{mime}; - my $hdr = $mime->header_obj; - - # last References should be IRT, but some mail clients do things - # out of order, so trust IRT over References iff IRT exists - my @refs = (($hdr->header_raw('References') || '') =~ /<([^>]+)>/g); - push(@refs, (($hdr->header_raw('In-Reply-To') || '') =~ /<([^>]+)>/g)); +# v1 only +sub batch_do { + my ($self, $termval, $cb) = @_; + my $batch_size = 1000; # don't let @ids grow too large to avoid OOM + while (1) { + my ($head, $tail) = $self->find_doc_ids($termval); + return if $head == $tail; + my @ids; + for (; $head != $tail && @ids < $batch_size; $head++) { + push @ids, $head->get_docid; + } + $cb->(\@ids); + } +} - my $tid; - if (@refs) { - my %uniq = ($mid => 1); - my @orig_refs = @refs; - @refs = (); +# v1 only, where $mid is unique +sub remove_message { + my ($self, $mid) = @_; + $mid = mid_clean($mid); - # prevent circular references via References: here: - foreach my $ref (@orig_refs) { - if (length($ref) > MAX_MID_SIZE) { - warn "References: <$ref> too long, ignoring\n"; - } - next if $uniq{$ref}; - $uniq{$ref} = 1; - push @refs, $ref; + if (my $over = $self->{over}) { + my $nr = eval { $over->remove_oid(undef, $mid) }; + if ($@) { + warn "failed to remove <$mid> from overview: $@\n"; + } elsif ($nr == 0) { + warn "<$mid> missing for removal from overview\n"; } } + return unless need_xapian($self); + my $db = $self->{xdb}; + my $nr = 0; + eval { + batch_do($self, 'Q' . $mid, sub { + my ($ids) = @_; + $db->delete_document($_) for @$ids; + $nr += scalar @$ids; + }); + }; + if ($@) { + warn "failed to remove <$mid> from Xapian: $@\n"; + } elsif ($nr == 0) { + warn "<$mid> missing for removal from Xapian\n"; + } +} - if (@refs) { - $smsg->{references} = '<'.join('> <', @refs).'>'; +# MID is a hint in V2 +sub remove_by_oid { + my ($self, $oid, $mid) = @_; - # first ref *should* be the thread root, - # but we can never trust clients to do the right thing - my $ref = shift @refs; - $tid = $self->_resolve_mid_to_tid($ref); - $self->merge_threads($tid, $old_tid) if defined $old_tid; + $self->{over}->remove_oid($oid, $mid) if $self->{over}; - # the rest of the refs should point to this tid: - foreach $ref (@refs) { - my $ptid = $self->_resolve_mid_to_tid($ref); - merge_threads($self, $tid, $ptid); + return unless need_xapian($self); + my $db = $self->{xdb}; + + # XXX careful, we cannot use batch_do here since we conditionally + # delete documents based on other factors, so we cannot call + # find_doc_ids twice. + my ($head, $tail) = $self->find_doc_ids('Q' . $mid); + return if $head == $tail; + + # there is only ONE element in @delete unless we + # have bugs in our v2writable deduplication check + my @delete; + for (; $head != $tail; $head++) { + my $docid = $head->get_docid; + my $doc = $db->get_document($docid); + my $smsg = PublicInbox::SearchMsg->wrap($mid); + $smsg->load_expand($doc); + if ($smsg->{blob} eq $oid) { + push(@delete, $docid); } - } else { - $tid = defined $old_tid ? $old_tid : $self->next_thread_id; } - $doc->add_term('G' . $tid); -} - -sub index_blob { - my ($self, $mime, $bytes, $num, $blob) = @_; - $self->add_message($mime, $bytes, $num, $blob); + $db->delete_document($_) foreach @delete; + scalar(@delete); } sub index_git_blob_id { @@ -479,33 +494,42 @@ sub index_mm { my ($self, $mime) = @_; my $mid = mid_clean(mid_mime($mime)); my $mm = $self->{mm}; - my $num = $mm->mid_insert($mid); + my $num; - # fallback to num_for since filters like RubyLang set the number - defined $num ? $num : $mm->num_for($mid); -} + if (defined $self->{regen_down}) { + $num = $mm->num_for($mid) and return $num; -sub unindex_mm { - my ($self, $mime) = @_; - $self->{mm}->mid_delete(mid_clean(mid_mime($mime))); -} + while (($num = $self->{regen_down}--) > 0) { + if ($mm->mid_set($num, $mid) != 0) { + return $num; + } + } + } elsif (defined $self->{regen_up}) { + $num = $mm->num_for($mid) and return $num; -sub index_mm2 { - my ($self, $mime, $bytes, $blob) = @_; - my $num = $self->{mm}->num_for(mid_clean(mid_mime($mime))); - index_blob($self, $mime, $bytes, $num, $blob); + # this is to fixup old bugs due to add-remove-add + while (($num = ++$self->{regen_up})) { + if ($mm->mid_set($num, $mid) != 0) { + return $num; + } + } + } + + $num = $mm->mid_insert($mid) and return $num; + + # fallback to num_for since filters like RubyLang set the number + $mm->num_for($mid); } -sub unindex_mm2 { +sub unindex_mm { my ($self, $mime) = @_; $self->{mm}->mid_delete(mid_clean(mid_mime($mime))); - unindex_blob($self, $mime); } sub index_both { my ($self, $mime, $bytes, $blob) = @_; my $num = index_mm($self, $mime); - index_blob($self, $mime, $bytes, $num, $blob); + add_message($self, $mime, $bytes, $num, $blob); } sub unindex_both { @@ -525,21 +549,24 @@ sub do_cat_mail { $@ ? undef : $mime; } +# called by public-inbox-index sub index_sync { my ($self, $opts) = @_; - with_umask($self, sub { $self->_index_sync($opts) }); + delete $self->{lock_path} if $opts->{-skip_lock}; + $self->{-inbox}->with_umask(sub { $self->_index_sync($opts) }) } -sub batch_adjust ($$$$) { - my ($max, $bytes, $batch_cb, $latest) = @_; +sub batch_adjust ($$$$$) { + my ($max, $bytes, $batch_cb, $latest, $nr) = @_; $$max -= $bytes; if ($$max <= 0) { $$max = BATCH_BYTES; - $batch_cb->($latest, 1); + $batch_cb->($nr, $latest); } } -sub rlog { +# only for v1 +sub read_log { my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_; my $hex = '[a-f0-9]'; my $h40 = $hex .'{40}'; @@ -550,231 +577,279 @@ sub rlog { my $bytes; my $max = BATCH_BYTES; local $/ = "\n"; + my %D; my $line; + my $newest; + my $nr = 0; while (defined($line = <$log>)) { if ($line =~ /$addmsg/o) { my $blob = $1; + if (delete $D{$blob}) { + if (defined $self->{regen_down}) { + my $num = $self->{regen_down}--; + $self->{mm}->num_highwater($num); + } + next; + } my $mime = do_cat_mail($git, $blob, \$bytes) or next; - batch_adjust(\$max, $bytes, $batch_cb, $latest); + batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr); $add_cb->($self, $mime, $bytes, $blob); } elsif ($line =~ /$delmsg/o) { my $blob = $1; - my $mime = do_cat_mail($git, $blob, \$bytes) or next; - batch_adjust(\$max, $bytes, $batch_cb, $latest); - $del_cb->($self, $mime); + $D{$blob} = 1; } elsif ($line =~ /^commit ($h40)/o) { $latest = $1; + $newest ||= $latest; } } - $batch_cb->($latest, 0); -} - -sub _msgmap_init { - my ($self) = @_; - $self->{mm} = eval { - require PublicInbox::Msgmap; - PublicInbox::Msgmap->new($self->{git_dir}, 1); - }; + close($log) or die "git log failed: \$?=$?"; + # get the leftovers + foreach my $blob (keys %D) { + my $mime = do_cat_mail($git, $blob, \$bytes) or next; + $del_cb->($self, $mime); + } + $batch_cb->($nr, $latest, $newest); } sub _git_log { - my ($self, $range) = @_; - $self->{git}->popen(qw/log --reverse --no-notes --no-color + my ($self, $opts, $range) = @_; + my $git = $self->{git}; + + if (index($range, '..') < 0) { + # don't show annoying git errrors to users who run -index + # on empty inboxes + $git->qx(qw(rev-parse -q --verify), "$range^0"); + if ($?) { + open my $fh, '<', '/dev/null' or + die "failed to open /dev/null: $!\n"; + return $fh; + } + } + + # Count the new files so they can be added newest to oldest + # and still have numbers increasing from oldest to newest + my $fcount = 0; + my $pr = $opts->{-progress}; + $pr->("counting changes\n\t$range ... ") if $pr; + # 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), $range); + ++$fcount while <$fh>; + close $fh or die "git log failed: \$?=$?"; + my $high = $self->{mm}->num_highwater; + $pr->("$fcount\n") if $pr; # continue previous line + $self->{ntodo} = $fcount; + + if (index($range, '..') < 0) { + if ($high && $high == $fcount) { + # fix up old bugs in full indexes which caused messages to + # not appear in Msgmap + $self->{regen_up} = $high; + } else { + # normal regen is for for fresh data + $self->{regen_down} = $fcount; + } + } else { + # Give oldest messages the smallest numbers + $self->{regen_down} = $high + $fcount; + } + + $git->popen(qw/log --no-notes --no-color --no-renames --raw -r --no-abbrev/, $range); } -# indexes all unindexed messages +# --is-ancestor requires git 1.8.0+ +sub is_ancestor ($$$) { + my ($git, $cur, $tip) = @_; + return 0 unless $git->check($cur); + my $cmd = [ 'git', "--git-dir=$git->{git_dir}", + qw(merge-base --is-ancestor), $cur, $tip ]; + my $pid = spawn($cmd); + waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish'; + $? == 0; +} + +sub need_update ($$$) { + my ($self, $cur, $new) = @_; + my $git = $self->{git}; + return 1 if $cur && !is_ancestor($git, $cur, $new); + my $range = $cur eq '' ? $new : "$cur..$new"; + chomp(my $n = $git->qx(qw(rev-list --count), $range)); + ($n eq '' || $n > 0); +} + +# The last git commit we indexed with Xapian or SQLite (msgmap) +# This needs to account for cases where Xapian or SQLite is +# out-of-date with respect to the other. +sub _last_x_commit { + my ($self, $mm) = @_; + my $lm = $mm->last_commit || ''; + my $lx = ''; + if (need_xapian($self)) { + $lx = $self->{xdb}->get_metadata('last_commit') || ''; + } else { + $lx = $lm; + } + # Use last_commit from msgmap if it is older or unset + if (!$lm || ($lx && $lm && is_ancestor($self->{git}, $lm, $lx))) { + $lx = $lm; + } + $lx; +} + +sub reindex_from ($$) { + my ($reindex, $last_commit) = @_; + return $last_commit unless $reindex; + ref($reindex) eq 'HASH' ? $reindex->{from} : ''; +} + +# indexes all unindexed messages (v1 only) sub _index_sync { my ($self, $opts) = @_; my $tip = $opts->{ref} || 'HEAD'; - my $reindex = $opts->{reindex}; - my ($mkey, $last_commit, $lx, $xlog); - $self->{git}->batch_prepare; - my $xdb = _xdb_acquire($self); - $xdb->begin_transaction; + my ($last_commit, $lx, $xlog); + my $git = $self->{git}; + $git->batch_prepare; + my $pr = $opts->{-progress}; + + my $xdb = $self->begin_txn_lazy; + my $mm = _msgmap_init($self); do { - $xlog = undef; - $mkey = 'last_commit'; - $last_commit = $xdb->get_metadata('last_commit'); - $lx = $last_commit; - if ($reindex) { - $lx = ''; - $mkey = undef if $last_commit ne ''; + if ($xlog) { + close($xlog) or die "git log failed: \$?=$?"; + $xlog = undef; } - $xdb->cancel_transaction; + $last_commit = _last_x_commit($self, $mm); + $lx = reindex_from($opts->{reindex}, $last_commit); + + $self->{over}->rollback_lazy; + $self->{over}->disconnect; + $git->cleanup; + delete $self->{txn}; + $xdb->cancel_transaction if $xdb; $xdb = _xdb_release($self); - # ensure we leak no FDs to "git log" + # ensure we leak no FDs to "git log" with Xapian <= 1.2 my $range = $lx eq '' ? $tip : "$lx..$tip"; - $xlog = _git_log($self, $range); + $xlog = _git_log($self, $opts, $range); - $xdb = _xdb_acquire($self); - $xdb->begin_transaction; - } while ($xdb->get_metadata('last_commit') ne $last_commit); + $xdb = $self->begin_txn_lazy; + } while (_last_x_commit($self, $mm) ne $last_commit); - my $mm = _msgmap_init($self); my $dbh = $mm->{dbh} if $mm; - my $mm_only; my $cb = sub { - my ($commit, $more) = @_; + my ($nr, $commit, $newest) = @_; if ($dbh) { - $mm->last_commit($commit) if $commit; + if ($newest) { + my $cur = $mm->last_commit || ''; + if (need_update($self, $cur, $newest)) { + $mm->last_commit($newest); + } + } $dbh->commit; } - if (!$mm_only) { - $xdb->set_metadata($mkey, $commit) if $mkey && $commit; - $xdb->commit_transaction; - $xdb = _xdb_release($self); + if ($newest && need_xapian($self)) { + my $cur = $xdb->get_metadata('last_commit'); + if (need_update($self, $cur, $newest)) { + $xdb->set_metadata('last_commit', $newest); + } } + $self->commit_txn_lazy; + $git->cleanup; + $xdb = _xdb_release($self); # let another process do some work... < - if ($more) { - if (!$mm_only) { - $xdb = _xdb_acquire($self); - $xdb->begin_transaction; - } + $pr->("indexed $nr/$self->{ntodo}\n") if $pr && $nr; + if (!$newest) { + $xdb = $self->begin_txn_lazy; $dbh->begin_work if $dbh; } }; - if ($mm) { - $dbh->begin_work; - my $lm = $mm->last_commit || ''; - if ($lm eq $lx) { - # Common case is the indexes are synced, - # we only need to run git-log once: - rlog($self, $xlog, *index_both, *unindex_both, $cb); - } else { - # Uncommon case, msgmap and xapian are out-of-sync - # do not care for performance (but git is fast :>) - # This happens if we have to reindex Xapian since - # msgmap is a frozen format and our Xapian format - # is evolving. - my $r = $lm eq '' ? $tip : "$lm..$tip"; - - # first, ensure msgmap is up-to-date: - my $mkey_prev = $mkey; - $mkey = undef; # ignore xapian, for now - my $mlog = _git_log($self, $r); - $mm_only = 1; - rlog($self, $mlog, *index_mm, *unindex_mm, $cb); - $mm_only = $mlog = undef; - - # now deal with Xapian - $mkey = $mkey_prev; - $dbh = undef; - rlog($self, $xlog, *index_mm2, *unindex_mm2, $cb); - } - } else { - # user didn't install DBD::SQLite and DBI - rlog($self, $xlog, *index_blob, *unindex_blob, $cb); - } + $dbh->begin_work; + read_log($self, $xlog, *index_both, *unindex_both, $cb); } -# this will create a ghost as necessary -sub _resolve_mid_to_tid { - my ($self, $mid) = @_; - - my $smsg = $self->lookup_message($mid) || $self->create_ghost($mid); - $smsg->thread_id; -} - -sub create_ghost { - my ($self, $mid) = @_; - - my $tid = $self->next_thread_id; - my $doc = Search::Xapian::Document->new; - $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); - - $smsg; +sub DESTROY { + # order matters for unlocking + $_[0]->{xdb} = undef; + $_[0]->{lockfh} = undef; } -sub merge_threads { - my ($self, $winner_tid, $loser_tid) = @_; - return if $winner_tid == $loser_tid; - my $db = $self->{xdb}; - - my $batch_size = 1000; # don't let @ids grow too large to avoid OOM - while (1) { - my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid); - return if $head == $tail; - my @ids; - for (; $head != $tail && @ids < $batch_size; $head->inc) { - push @ids, $head->get_docid; - } - foreach my $docid (@ids) { - my $doc = $db->get_document($docid); - $doc->remove_term('G' . $loser_tid); - $doc->add_term('G' . $winner_tid); - $db->replace_document($docid, $doc); - } +# remote_* subs are only used by SearchIdxPart +sub remote_commit { + my ($self) = @_; + if (my $w = $self->{w}) { + print $w "commit\n" or die "failed to write commit: $!"; + } else { + $self->commit_txn_lazy; } } -sub _read_git_config_perm { +sub remote_close { 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; + if (my $w = delete $self->{w}) { + my $pid = delete $self->{pid} or die "no process to wait on\n"; + print $w "close\n" or die "failed to write to pid:$pid: $!\n"; + close $w or die "failed to close pipe for pid:$pid: $!\n"; + waitpid($pid, 0) == $pid or die "remote process did not finish"; + $? == 0 or die ref($self)." pid:$pid exited with: $?"; + } else { + die "transaction in progress $self\n" if $self->{txn}; + $self->_xdb_release if $self->{xdb}; } - 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"; +sub remote_remove { + my ($self, $oid, $mid) = @_; + if (my $w = $self->{w}) { + # triggers remove_by_oid in a shard + print $w "D $oid $mid\n" or die "failed to write remove $!"; + } else { + $self->begin_txn_lazy; + $self->remove_by_oid($oid, $mid); } - ($i & 0666); } -sub _umask_for { - my ($perm) = @_; # _git_config_perm return value - my $rv = $perm; - return umask if $rv == 0; +sub begin_txn_lazy { + my ($self) = @_; + return if $self->{txn}; - # 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); + $self->{-inbox}->with_umask(sub { + my $xdb = $self->{xdb} || $self->_xdb_acquire; + $self->{over}->begin_lazy if $self->{over}; + $xdb->begin_transaction if $xdb; + $self->{txn} = 1; + $xdb; + }); } -sub with_umask { - my ($self, $cb) = @_; - my $old = umask $self->{umask}; - my $rv = eval { $cb->() }; - my $err = $@; - umask $old; - die $err if $err; - $rv; +sub commit_txn_lazy { + my ($self) = @_; + delete $self->{txn} or return; + $self->{-inbox}->with_umask(sub { + if (my $xdb = $self->{xdb}) { + + # store 'indexlevel=medium' in v2 shard=0 and + # v1 (only one shard) + # This metadata is read by Admin::detect_indexlevel: + if (!$self->{shard} # undef or 0, not >0 + && $self->{indexlevel} eq 'medium') { + $xdb->set_metadata('indexlevel', 'medium'); + } + + $xdb->commit_transaction; + } + $self->{over}->commit_lazy if $self->{over}; + }); } -sub DESTROY { - # order matters for unlocking - $_[0]->{xdb} = undef; - $_[0]->{lockfh} = undef; +sub worker_done { + my ($self) = @_; + if (need_xapian($self)) { + die "$$ $0 xdb not released\n" if $self->{xdb}; + } + die "$$ $0 still in transaction\n" if $self->{txn}; } 1;