X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=44b05813f9a43e371068071ac9b2b666c275d555;hp=8810fe76450dde64728d715e4e63f14b3c6bb741;hb=b5bc3576af3d0ef0fa884ed32a674c7a703a19b2;hpb=b0e5062d43a96372801713ef78a78d6a1bc852bc diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 8810fe76..44b05813 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2018 all contributors +# Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ # based on notmuch, but with no concept of folders, files or flags # @@ -12,15 +12,16 @@ use warnings; use base qw(PublicInbox::Search PublicInbox::Lock); use PublicInbox::MIME; use PublicInbox::InboxWritable; -use PublicInbox::MID qw/mid_clean id_compress mid_mime mids/; +use PublicInbox::MID qw/mid_clean mid_mime mids_for_index/; use PublicInbox::MsgIter; use Carp qw(croak); use POSIX qw(strftime); use PublicInbox::OverIdx; use PublicInbox::Spawn qw(spawn); -require PublicInbox::Git; -use Compress::Zlib qw(compress); - +use PublicInbox::Git qw(git_unquote); +use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); +my $X = \%PublicInbox::Search::X; +my ($DB_CREATE_OR_OPEN, $DB_OPEN); use constant { BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ? 0x7fffffff : 1_000_000, @@ -29,72 +30,43 @@ use constant { my $xapianlevels = qr/\A(?:full|medium)\z/; -my %GIT_ESC = ( - a => "\a", - b => "\b", - f => "\f", - n => "\n", - r => "\r", - t => "\t", - v => "\013", -); - -sub git_unquote ($) { - 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; - $s; -} - sub new { - my ($class, $ibx, $creat, $part) = @_; + my ($class, $ibx, $creat, $shard) = @_; + ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx"; my $levels = qr/\A(?:full|medium|basic)\z/; - my $mainrepo = $ibx; # for "public-inbox-index" w/o entry in config - my $git_dir = $mainrepo; - my ($altid, $git); - my $version = 1; + my $inboxdir = $ibx->{inboxdir}; + my $version = $ibx->version; my $indexlevel = 'full'; - if (ref $ibx) { - $mainrepo = $ibx->{mainrepo}; - $altid = $ibx->{altid}; - $version = $ibx->{version} || 1; - if ($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"); - } + 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"); } - } else { # v1 - $ibx = { mainrepo => $git_dir, version => 1 }; } $ibx = PublicInbox::InboxWritable->new($ibx); - require Search::Xapian::WritableDatabase; my $self = bless { - mainrepo => $mainrepo, + inboxdir => $inboxdir, -inbox => $ibx, git => $ibx->git, -altid => $altid, - version => $version, + ibx_ver => $version, indexlevel => $indexlevel, }, $class; $ibx->umask_prepare; if ($version == 1) { - $self->{lock_path} = "$mainrepo/ssoma.lock"; + $self->{lock_path} = "$inboxdir/ssoma.lock"; my $dir = $self->xdir; $self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3"); } elsif ($version == 2) { - defined $part or die "partition is required for v2\n"; - # partition is a number - $self->{partition} = $part; + 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"; @@ -103,44 +75,84 @@ sub new { $self; } +sub need_xapian ($) { $_[0]->{indexlevel} =~ $xapianlevels } + sub _xdb_release { my ($self) = @_; - my $xdb = delete $self->{xdb} or croak 'not acquired'; - $xdb->close; + if (need_xapian($self)) { + my $xdb = delete $self->{xdb} or croak 'not acquired'; + $xdb->close; + } $self->lock_release if $self->{creat}; undef; } +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)) { + $X->{$_} = $xap.'::'.$_; + } + 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; +} + sub _xdb_acquire { my ($self) = @_; - croak 'already acquired' if $self->{xdb}; + my $flag; my $dir = $self->xdir; - my $flag = Search::Xapian::DB_OPEN; + if (need_xapian($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; $self->lock_acquire; - File::Path::mkpath($dir); - $flag = Search::Xapian::DB_CREATE_OR_OPEN; + + # 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); + } } - $self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag); + return unless defined $flag; + my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) }; + if ($@) { + die "Failed opening $dir: ", $@; + } + $self->{xdb} = $xdb; } sub add_val ($$$) { my ($doc, $col, $num) = @_; - $num = Search::Xapian::sortable_serialise($num); + $num = sortable_serialise($num); $doc->add_value($col, $num); } -sub index_text ($$$$) -{ - my ($self, $field, $n, $text) = @_; - my $tg = $self->term_generator; +sub term_generator ($) { # write-only + my ($self) = @_; + + $self->{term_generator} //= do { + my $tg = $X->{TermGenerator}->new; + $tg->set_stemmer($self->stemmer); + $tg; + } +} + +sub index_text ($$$$) { + my ($self, $text, $wdf_inc, $prefix) = @_; + my $tg = term_generator($self); # man Search::Xapian::TermGenerator if ($self->{indexlevel} eq 'full') { - $tg->index_text($field, $n, $text); + $tg->index_text($text, $wdf_inc, $prefix); $tg->increase_termpos; } else { - $tg->index_text_without_positions($field, $n, $text); + $tg->index_text_without_positions($text, $wdf_inc, $prefix); } } @@ -151,18 +163,18 @@ sub index_users ($$) { my $to = $smsg->to; my $cc = $smsg->cc; - $self->index_text($from, 1, 'A'); # A - author - $self->index_text($to, 1, 'XTO') if $to ne ''; - $self->index_text($cc, 1, 'XCC') if $cc ne ''; + index_text($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_diff_inc ($$$$) { my ($self, $text, $pfx, $xnq) = @_; if (@$xnq) { - $self->index_text(join("\n", @$xnq), 1, 'XNQ'); + index_text($self, join("\n", @$xnq), 1, 'XNQ'); @$xnq = (); } - $self->index_text($text, 1, $pfx); + index_text($self, $text, 1, $pfx); } sub index_old_diff_fn { @@ -177,7 +189,7 @@ sub index_old_diff_fn { $fb = join('/', @fb); if ($fa eq $fb) { unless ($seen->{$fa}++) { - $self->index_diff_inc($fa, 'XDFN', $xnq); + index_diff_inc($self, $fa, 'XDFN', $xnq); } return 1; } @@ -188,22 +200,18 @@ sub index_old_diff_fn { } sub index_diff ($$$) { - my ($self, $lines, $doc) = @_; + my ($self, $txt, $doc) = @_; my %seen; my $in_diff; my @xnq; my $xnq = \@xnq; - foreach (@$lines) { + foreach (split(/\n/, $txt)) { if ($in_diff && s/^ //) { # diff context - $self->index_diff_inc($_, 'XDFCTX', $xnq); + index_diff_inc($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]; - $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); - $fn = (split('/', git_unquote($fb), 2))[1]; - $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); + } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) { + # wait until "---" and "+++" to capture filenames $in_diff = 1; # traditional diff: } elsif (m/^diff -(.+) (\S+) (\S+)$/) { @@ -211,26 +219,28 @@ sub index_diff ($$$) { push @xnq, $_; # only support unified: next unless $opt =~ /[uU]/; - $in_diff = $self->index_old_diff_fn(\%seen, $fa, $fb, + $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb, $xnq); - } elsif (m!^--- ("?a/.+)!) { - my $fn = (split('/', git_unquote($1), 2))[1]; - $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); + } elsif (m!^--- ("?[^/]+/.+)!) { + my $fn = $1; + $fn = (split('/', git_unquote($fn), 2))[1]; + $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; - } elsif (m!^\+\+\+ ("?b/.+)!) { - my $fn = (split('/', git_unquote($1), 2))[1]; - $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); + } elsif (m!^\+\+\+ ("?[^/]+/.+)!) { + my $fn = $1; + $fn = (split('/', git_unquote($fn), 2))[1]; + $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; } elsif (/^--- (\S+)/) { $in_diff = $1; push @xnq, $_; } elsif (defined $in_diff && /^\+\+\+ (\S+)/) { - $in_diff = $self->index_old_diff_fn(\%seen, $in_diff, $1, - $xnq); + $in_diff = index_old_diff_fn($self, \%seen, $in_diff, + $1, $xnq); } elsif ($in_diff && s/^\+//) { # diff added - $self->index_diff_inc($_, 'XDFB', $xnq); + index_diff_inc($self, $_, 'XDFB', $xnq); } elsif ($in_diff && s/^-//) { # diff removed - $self->index_diff_inc($_, 'XDFA', $xnq); + index_diff_inc($self, $_, 'XDFA', $xnq); } elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) { my ($ba, $bb) = ($1, $2); index_git_blob_id($doc, 'XDFPRE', $ba); @@ -240,7 +250,7 @@ sub index_diff ($$$) { # traditional diff w/o -p } elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) { # hunk header context - $self->index_diff_inc($1, 'XDFHH', $xnq); + index_diff_inc($self, $1, 'XDFHH', $xnq); # ignore the following lines: } elsif (/^(?:dis)similarity index/ || /^(?:old|new) mode/ || @@ -251,7 +261,9 @@ sub index_diff ($$$) { /^Binary files .* differ/) { push @xnq, $_; } elsif ($_ eq '') { - $in_diff = undef; + # possible to be in diff context, some mail may be + # stripped by MUA or even GNU diff(1). "git apply" + # treats a bare "\n" as diff context, too } else { push @xnq, $_; warn "non-diff line: $_\n" if DEBUG && $_ ne ''; @@ -259,83 +271,74 @@ sub index_diff ($$$) { } } - $self->index_text(join("\n", @xnq), 1, 'XNQ'); + index_text($self, join("\n", @xnq), 1, 'XNQ'); } sub index_body ($$$) { - my ($self, $lines, $doc) = @_; - my $txt = join("\n", @$lines); + my ($self, $txt, $doc) = @_; if ($doc) { # does it look like a diff? if ($txt =~ /^(?:diff|---|\+\+\+) /ms) { - $txt = undef; - $self->index_diff($lines, $doc); + index_diff($self, $txt, $doc); } else { - $self->index_text($txt, 1, 'XNQ'); + index_text($self, $txt, 1, 'XNQ'); } } else { - $self->index_text($txt, 0, 'XQUOT'); + index_text($self, $txt, 0, 'XQUOT'); } - @$lines = (); } -sub add_xapian ($$$$$) { - my ($self, $mime, $num, $oid, $mids, $mid0) = @_; - my $smsg = PublicInbox::SearchMsg->new($mime); - my $doc = Search::Xapian::Document->new; +sub index_xapian { # msg_iter callback + my ($part, $depth, @idx) = @{$_[0]}; + my ($self, $doc) = @{$_[1]}; + my $ct = $part->content_type || 'text/plain'; + my $fn = $part->filename; + if (defined $fn && $fn ne '') { + index_text($self, $fn, 1, 'XFN'); + } + + my ($s, undef) = msg_part_text($part, $ct); + defined $s or return; + + # split off quoted and unquoted blocks: + my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s); + $part = $s = undef; + index_body($self, $_, /\A>/ ? 0 : $doc) for @sections; +} + +sub add_xapian ($$$$) { + my ($self, $mime, $smsg, $mids) = @_; + $smsg->{mime} = $mime; # XXX dangerous + my $hdr = $mime->header_obj; + my $doc = $X->{Document}->new; my $subj = $smsg->subject; - add_val($doc, PublicInbox::Search::TS(), $smsg->ts); - my @ds = gmtime($smsg->ds); + 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 = $self->term_generator; + my $tg = term_generator($self); $tg->set_document($doc); - $self->index_text($subj, 1, 'S') if $subj; - $self->index_users($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 '') { - $self->index_text($fn, 1, 'XFN'); - } - - my ($s, undef) = msg_part_text($part, $ct); - defined $s or return; - - my (@orig, @quot); - my @lines = split(/\n/, $s); - while (defined(my $l = shift @lines)) { - if ($l =~ /^>/) { - $self->index_body(\@orig, $doc) if @orig; - push @quot, $l; - } else { - $self->index_body(\@quot, 0) if @quot; - push @orig, $l; - } - } - $self->index_body(\@quot, 0) if @quot; - $self->index_body(\@orig, $doc) if @orig; - }); + index_text($self, $subj, 1, 'S') if $subj; + index_users($self, $smsg); + msg_iter($mime, \&index_xapian, [ $self, $doc ]); foreach my $mid (@$mids) { - $self->index_text($mid, 1, 'XM'); + 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); - $self->index_text(join(' ', @long), 1, 'XM'); + index_text($self, join(' ', @long), 1, 'XM'); } } - $smsg->{to} = $smsg->{cc} = ''; - PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids); - my $data = $smsg->to_doc_data($oid, $mid0); + $smsg->{to} = $smsg->{cc} = ''; # WWW doesn't need these, only NNTP + PublicInbox::OverIdx::parse_references($smsg, $hdr, $mids); + my $data = $smsg->to_doc_data; $doc->set_data($data); if (my $altid = $self->{-altid}) { foreach my $alt (@$altid) { @@ -348,24 +351,45 @@ sub add_xapian ($$$$$) { } } $doc->add_boolean_term('Q' . $_) foreach @$mids; - $self->{xdb}->replace_document($num, $doc); + $self->{xdb}->replace_document($smsg->{num}, $doc); +} + +sub _msgmap_init ($) { + my ($self) = @_; + die "BUG: _msgmap_init is only for v1\n" if $self->{ibx_ver} != 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($mime->header_obj); - $mid0 = $mids->[0] unless defined $mid0; # v1 compatibility - unless (defined $num) { # v1 - $self->_msgmap_init; - $num = index_mm($self, $mime); - } + my ($self, $mime, $smsg) = @_; + my $hdr = $mime->header_obj; + my $mids = mids_for_index($hdr); + $smsg //= bless { blob => '' }, 'PublicInbox::Smsg'; # test-only compat + $smsg->{mid} //= $mids->[0]; # v1 compatibility + $smsg->{num} //= do { # v1 + _msgmap_init($self); + index_mm($self, $mime); + }; + + # v1 and tests only: + $smsg->{ds} //= msg_datestamp($hdr, $self->{autime}); + $smsg->{ts} //= msg_timestamp($hdr, $self->{cotime}); + eval { - if ($self->{indexlevel} =~ $xapianlevels) { - $self->add_xapian($mime, $num, $oid, $mids, $mid0) + # order matters, overview stores every possible piece of + # data in doc_data (deflated). Xapian only stores a subset + # of the fields which exist in over.sqlite3. We may stop + # storing doc_data in Xapian sometime after we get multi-inbox + # search working. + if (my $over = $self->{over}) { # v1 only + $over->add_overview($mime, $smsg); } - if (my $over = $self->{over}) { - $over->add_overview($mime, $bytes, $num, $oid, $mid0); + if (need_xapian($self)) { + add_xapian($self, $mime, $smsg, $mids); } }; @@ -373,7 +397,7 @@ sub add_message { warn "failed to index message <".join('> <',@$mids).">: $@\n"; return undef; } - $num; + $smsg->{num}; } # returns begin and end PostingIterator @@ -384,6 +408,7 @@ sub find_doc_ids { ($db->postlist_begin($termval), $db->postlist_end($termval)); } +# v1 only sub batch_do { my ($self, $termval, $cb) = @_; my $batch_size = 1000; # don't let @ids grow too large to avoid OOM @@ -391,42 +416,52 @@ sub batch_do { my ($head, $tail) = $self->find_doc_ids($termval); return if $head == $tail; my @ids; - for (; $head != $tail && @ids < $batch_size; $head->inc) { + for (; $head != $tail && @ids < $batch_size; $head++) { push @ids, $head->get_docid; } $cb->(\@ids); } } +# v1 only, where $mid is unique sub remove_message { my ($self, $mid) = @_; - my $db = $self->{xdb}; - my $called; $mid = mid_clean($mid); - my $over = $self->{over}; + 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; - $over->delete_articles($ids) if $over; - $called = 1; + $nr += scalar @$ids; }); }; if ($@) { - warn "failed to remove message <$mid>: $@\n"; - } elsif (!$called) { - warn "cannot remove non-existent <$mid>\n"; + warn "failed to remove <$mid> from Xapian: $@\n"; + } elsif ($nr == 0) { + warn "<$mid> missing for removal from Xapian\n"; } } # MID is a hint in V2 sub remove_by_oid { my ($self, $oid, $mid) = @_; - my $db = $self->{xdb}; $self->{over}->remove_oid($oid, $mid) if $self->{over}; + 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. @@ -436,10 +471,10 @@ sub remove_by_oid { # there is only ONE element in @delete unless we # have bugs in our v2writable deduplication check my @delete; - for (; $head != $tail; $head->inc) { + for (; $head != $tail; $head++) { my $docid = $head->get_docid; my $doc = $db->get_document($docid); - my $smsg = PublicInbox::SearchMsg->wrap($mid); + my $smsg = PublicInbox::Smsg->wrap($mid); $smsg->load_expand($doc); if ($smsg->{blob} eq $oid) { push(@delete, $docid); @@ -449,18 +484,6 @@ sub remove_by_oid { scalar(@delete); } -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; -} - sub index_git_blob_id { my ($doc, $pfx, $objid) = @_; @@ -514,9 +537,10 @@ sub unindex_mm { } sub index_both { - my ($self, $mime, $bytes, $blob) = @_; + my ($self, $mime, $smsg) = @_; my $num = index_mm($self, $mime); - add_message($self, $mime, $bytes, $num, $blob); + $smsg->{num} = $num; + add_message($self, $mime, $smsg); } sub unindex_both { @@ -536,17 +560,19 @@ sub do_cat_mail { $@ ? undef : $mime; } +# called by public-inbox-index sub index_sync { my ($self, $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); + $batch_cb->($nr, $latest); } } @@ -565,6 +591,7 @@ sub read_log { my %D; my $line; my $newest; + my $nr = 0; while (defined($line = <$log>)) { if ($line =~ /$addmsg/o) { my $blob = $1; @@ -576,35 +603,34 @@ sub read_log { next; } my $mime = do_cat_mail($git, $blob, \$bytes) or next; - batch_adjust(\$max, $bytes, $batch_cb, $latest); - $add_cb->($self, $mime, $bytes, $blob); + my $smsg = bless {}, 'PublicInbox::Smsg'; + batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr); + $smsg->{blob} = $blob; + $smsg->{bytes} = $bytes; + $add_cb->($self, $mime, $smsg); } elsif ($line =~ /$delmsg/o) { my $blob = $1; $D{$blob} = 1; } elsif ($line =~ /^commit ($h40)/o) { $latest = $1; $newest ||= $latest; + } elsif ($line =~ /^author .*? ([0-9]+) [\-\+][0-9]+$/) { + $self->{autime} = $1; + } elsif ($line =~ /^committer .*? ([0-9]+) [\-\+][0-9]+$/) { + $self->{cotime} = $1; } } + close($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); } - $batch_cb->($latest, $newest); -} - -sub _msgmap_init { - my ($self) = @_; - die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1; - $self->{mm} ||= eval { - require PublicInbox::Msgmap; - PublicInbox::Msgmap->new($self->{mainrepo}, 1); - }; + $batch_cb->($nr, $latest, $newest); } sub _git_log { - my ($self, $range) = @_; + my ($self, $opts, $range) = @_; my $git = $self->{git}; if (index($range, '..') < 0) { @@ -621,12 +647,17 @@ sub _git_log { # 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) { @@ -642,7 +673,7 @@ sub _git_log { $self->{regen_down} = $high + $fcount; } - $git->popen(qw/log --no-notes --no-color --no-renames + $git->popen(qw/log --pretty=raw --no-notes --no-color --no-renames --raw -r --no-abbrev/, $range); } @@ -653,7 +684,6 @@ sub is_ancestor ($$$) { my $cmd = [ 'git', "--git-dir=$git->{git_dir}", qw(merge-base --is-ancestor), $cur, $tip ]; my $pid = spawn($cmd); - defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!"; waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish'; $? == 0; } @@ -667,50 +697,67 @@ sub need_update ($$$) { ($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); + 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 ''; - } - - # use last_commit from msgmap if it is older or unset - my $lm = $mm->last_commit || ''; - if (!$lm || ($lm && $lx && is_ancestor($git, $lm, $lx))) { - $lx = $lm; + if ($xlog) { + close($xlog) or die "git log failed: \$?=$?"; + $xlog = undef; } + $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; + $xdb->cancel_transaction if $xdb; $xdb = _xdb_release($self); # 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 = $self->begin_txn_lazy; - } while ($xdb->get_metadata('last_commit') ne $last_commit); + } while (_last_x_commit($self, $mm) ne $last_commit); my $dbh = $mm->{dbh} if $mm; my $cb = sub { - my ($commit, $newest) = @_; + my ($nr, $commit, $newest) = @_; if ($dbh) { if ($newest) { my $cur = $mm->last_commit || ''; @@ -720,16 +767,17 @@ sub _index_sync { } $dbh->commit; } - if ($mkey && $newest && $self->{indexlevel} =~ $xapianlevels) { - my $cur = $xdb->get_metadata($mkey); + if ($newest && need_xapian($self)) { + my $cur = $xdb->get_metadata('last_commit'); if (need_update($self, $cur, $newest)) { - $xdb->set_metadata($mkey, $newest); + $xdb->set_metadata('last_commit', $newest); } } $self->commit_txn_lazy; $git->cleanup; $xdb = _xdb_release($self); # let another process do some work... < + $pr->("indexed $nr/$self->{ntodo}\n") if $pr && $nr; if (!$newest) { $xdb = $self->begin_txn_lazy; $dbh->begin_work if $dbh; @@ -773,7 +821,7 @@ sub remote_close { sub remote_remove { my ($self, $oid, $mid) = @_; if (my $w = $self->{w}) { - # triggers remove_by_oid in a partition + # triggers remove_by_oid in a shard print $w "D $oid $mid\n" or die "failed to write remove $!"; } else { $self->begin_txn_lazy; @@ -788,7 +836,7 @@ sub begin_txn_lazy { $self->{-inbox}->with_umask(sub { my $xdb = $self->{xdb} || $self->_xdb_acquire; $self->{over}->begin_lazy if $self->{over}; - $xdb->begin_transaction; + $xdb->begin_transaction if $xdb; $self->{txn} = 1; $xdb; }); @@ -798,14 +846,27 @@ sub commit_txn_lazy { my ($self) = @_; delete $self->{txn} or return; $self->{-inbox}->with_umask(sub { - $self->{xdb}->commit_transaction; + 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 worker_done { my ($self) = @_; - die "$$ $0 xdb not released\n" if $self->{xdb}; + if (need_xapian($self)) { + die "$$ $0 xdb not released\n" if $self->{xdb}; + } die "$$ $0 still in transaction\n" if $self->{txn}; }