X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;ds=sidebyside;f=lib%2FPublicInbox%2FSearchIdx.pm;h=7d089e7aee4271645ae562ccf1b13ab24f6d68f7;hb=8e1ec8836dabc58dfc0115b36ed440b4371b70d7;hp=62e836e0d2d936ed849eec108cca7852b554cb14;hpb=da1ae9ccd829966195bfe59f17e416f218746def;p=public-inbox.git diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 62e836e0..7d089e7a 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2019 all contributors +# Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ # based on notmuch, but with no concept of folders, files or flags # @@ -12,13 +12,14 @@ 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_for_index/; +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); 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 { @@ -34,7 +35,7 @@ sub new { 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} || 1; + my $version = $ibx->version; my $indexlevel = 'full'; my $altid = $ibx->{altid}; if ($altid) { @@ -54,9 +55,10 @@ sub new { -inbox => $ibx, git => $ibx->git, -altid => $altid, - version => $version, + ibx_ver => $version, indexlevel => $indexlevel, }, $class; + $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium'; $ibx->umask_prepare; if ($version == 1) { $self->{lock_path} = "$inboxdir/ssoma.lock"; @@ -144,14 +146,14 @@ sub term_generator ($) { # write-only } sub index_text ($$$$) { - my ($self, $field, $n, $text) = @_; - my $tg = term_generator($self); + my ($self, $text, $wdf_inc, $prefix) = @_; + my $tg = term_generator($self); # man Search::Xapian::TermGenerator if ($self->{indexlevel} eq 'full') { - $tg->index_text($field, $n, $text); + $tg->index_text($text, $wdf_inc, $prefix); $tg->increase_termpos; } else { - $tg->index_text_without_positions($field, $n, $text); + $tg->index_text_without_positions($text, $wdf_inc, $prefix); } } @@ -199,22 +201,18 @@ sub index_old_diff_fn { } sub index_diff ($$$) { - 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 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 index_diff_inc($self, $fn, 'XDFN', $xnq); - $fn = (split('/', git_unquote($fb), 2))[1]; - $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); + } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) { + # wait until "---" and "+++" to capture filenames $in_diff = 1; # traditional diff: } elsif (m/^diff -(.+) (\S+) (\S+)$/) { @@ -224,12 +222,12 @@ sub index_diff ($$$) { next unless $opt =~ /[uU]/; $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb, $xnq); - } elsif (m!^--- ("?a/.+)!) { + } elsif (m!^--- ("?[^/]+/.+)!) { my $fn = $1; $fn = (split('/', git_unquote($fn), 2))[1]; $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; - } elsif (m!^\+\+\+ ("?b/.+)!) { + } elsif (m!^\+\+\+ ("?[^/]+/.+)!) { my $fn = $1; $fn = (split('/', git_unquote($fn), 2))[1]; $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); @@ -278,20 +276,17 @@ sub index_diff ($$$) { } sub index_body ($$$) { - my ($self, $lines, $doc) = @_; - my $txt = join("\n", @$lines); + my ($self, $txt, $doc) = @_; if ($doc) { # does it look like a diff? if ($txt =~ /^(?:diff|---|\+\+\+) /ms) { - $txt = undef; - index_diff($self, $lines, $doc); + index_diff($self, $txt, $doc); } else { index_text($self, $txt, 1, 'XNQ'); } } else { index_text($self, $txt, 0, 'XQUOT'); } - @$lines = (); } sub index_xapian { # msg_iter callback @@ -306,28 +301,20 @@ sub index_xapian { # msg_iter callback my ($s, undef) = msg_part_text($part, $ct); defined $s or return; - my (@orig, @quot); - my @lines = split(/\n/, $s); - while (defined(my $l = shift @lines)) { - if ($l =~ /^>/) { - index_body($self, \@orig, $doc) if @orig; - push @quot, $l; - } else { - index_body($self, \@quot, 0) if @quot; - push @orig, $l; - } - } - index_body($self, \@quot, 0) if @quot; - index_body($self, \@orig, $doc) if @orig; + # split off quoted and unquoted blocks: + my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s); + $part = $s = undef; + index_body($self, $_, /\A>/ ? 0 : $doc) for @sections; } -sub add_xapian ($$$$$$) { - my ($self, $mime, $num, $oid, $mids, $mid0) = @_; - my $smsg = PublicInbox::SearchMsg->new($mime); +sub add_xapian ($$$$) { + my ($self, $mime, $smsg, $mids) = @_; + $smsg->{mime} = $mime; # XXX dangerous + my $hdr = $mime->header_obj; my $doc = $X->{Document}->new; my $subj = $smsg->subject; - add_val($doc, PublicInbox::Search::TS(), $smsg->ts); - my @ds = gmtime($smsg->ds); + add_val($doc, PublicInbox::Search::TS(), $smsg->{ts}); + my @ds = gmtime($smsg->{ds}); my $yyyymmdd = strftime('%Y%m%d', @ds); add_val($doc, PublicInbox::Search::YYYYMMDD(), $yyyymmdd); my $dt = strftime('%Y%m%d%H%M%S', @ds); @@ -350,9 +337,9 @@ sub add_xapian ($$$$$$) { index_text($self, join(' ', @long), 1, 'XM'); } } - $smsg->{to} = $smsg->{cc} = ''; - PublicInbox::OverIdx::parse_references($smsg, $mid0, $mids); - my $data = $smsg->to_doc_data($oid, $mid0); + $smsg->{to} = $smsg->{cc} = ''; # WWW doesn't need these, only NNTP + PublicInbox::OverIdx::parse_references($smsg, $hdr, $mids); + my $data = $smsg->to_doc_data; $doc->set_data($data); if (my $altid = $self->{-altid}) { foreach my $alt (@$altid) { @@ -365,12 +352,12 @@ sub add_xapian ($$$$$$) { } } $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->{version} != 1; + 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); @@ -379,19 +366,31 @@ sub _msgmap_init ($) { 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 + 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 (need_xapian($self)) { - add_xapian($self, $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); } }; @@ -399,7 +398,7 @@ sub add_message { warn "failed to index message <".join('> <',@$mids).">: $@\n"; return undef; } - $num; + $smsg->{num}; } # returns begin and end PostingIterator @@ -445,7 +444,7 @@ sub remove_message { batch_do($self, 'Q' . $mid, sub { my ($ids) = @_; $db->delete_document($_) for @$ids; - $nr = scalar @$ids; + $nr += scalar @$ids; }); }; if ($@) { @@ -476,7 +475,7 @@ sub remove_by_oid { 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); @@ -539,9 +538,10 @@ 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 { @@ -604,14 +604,21 @@ sub read_log { next; } my $mime = do_cat_mail($git, $blob, \$bytes) or next; + my $smsg = bless {}, 'PublicInbox::Smsg'; batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr); - $add_cb->($self, $mime, $bytes, $blob); + $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: \$?=$?"; @@ -667,7 +674,7 @@ 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); } @@ -678,7 +685,6 @@ 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'; $? == 0; } @@ -837,20 +843,27 @@ sub begin_txn_lazy { }); } +# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard) +# This metadata is read by Admin::detect_indexlevel: +sub set_indexlevel { + my ($self) = @_; + + if (!$self->{shard} && # undef or 0, not >0 + delete($self->{-set_indexlevel_once})) { + my $xdb = $self->{xdb}; + my $level = $xdb->get_metadata('indexlevel'); + if (!$level || $level ne 'medium') { + $xdb->set_metadata('indexlevel', 'medium'); + } + } +} + sub commit_txn_lazy { my ($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') { - $xdb->set_metadata('indexlevel', 'medium'); - } - + set_indexlevel($self); $xdb->commit_transaction; } $self->{over}->commit_lazy if $self->{over};