X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=8810fe76450dde64728d715e4e63f14b3c6bb741;hb=b0e5062d43a96372801713ef78a78d6a1bc852bc;hp=107cd3457133cbe9d9442045dd0e5b7a2cc06d04;hpb=c339a14b11c57e7b330f4efef6903bcbea2b3463;p=public-inbox.git diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 107cd345..8810fe76 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -22,10 +22,13 @@ require PublicInbox::Git; use Compress::Zlib qw(compress); use constant { - BATCH_BYTES => 1_000_000, + BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ? + 0x7fffffff : 1_000_000, DEBUG => !!$ENV{DEBUG}, }; +my $xapianlevels = qr/\A(?:full|medium)\z/; + my %GIT_ESC = ( a => "\a", b => "\b", @@ -47,10 +50,12 @@ sub git_unquote ($) { sub new { my ($class, $ibx, $creat, $part) = @_; + 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 $indexlevel = 'full'; if (ref $ibx) { $mainrepo = $ibx->{mainrepo}; $altid = $ibx->{altid}; @@ -61,6 +66,13 @@ sub new { PublicInbox::AltId->new($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 }; } @@ -72,6 +84,7 @@ sub new { git => $ibx->git, -altid => $altid, version => $version, + indexlevel => $indexlevel, }, $class; $ibx->umask_prepare; if ($version == 1) { @@ -118,34 +131,42 @@ sub add_val ($$$) { $doc->add_value($col, $num); } +sub index_text ($$$$) +{ + my ($self, $field, $n, $text) = @_; + my $tg = $self->term_generator; + + if ($self->{indexlevel} eq 'full') { + $tg->index_text($field, $n, $text); + $tg->increase_termpos; + } else { + $tg->index_text_without_positions($field, $n, $text); + } +} + sub index_users ($$) { - 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; + $self->index_text($from, 1, 'A'); # A - author + $self->index_text($to, 1, 'XTO') if $to ne ''; + $self->index_text($cc, 1, 'XCC') if $cc ne ''; } sub index_diff_inc ($$$$) { - my ($tg, $text, $pfx, $xnq) = @_; + my ($self, $text, $pfx, $xnq) = @_; if (@$xnq) { - $tg->index_text(join("\n", @$xnq), 1, 'XNQ'); - $tg->increase_termpos; + $self->index_text(join("\n", @$xnq), 1, 'XNQ'); @$xnq = (); } - $tg->index_text($text, 1, $pfx); - $tg->increase_termpos; + $self->index_text($text, 1, $pfx); } sub index_old_diff_fn { - my ($tg, $seen, $fa, $fb, $xnq) = @_; + my ($self, $seen, $fa, $fb, $xnq) = @_; # no renames or space support for traditional diffs, # find the number of leading common paths to strip: @@ -156,7 +177,7 @@ sub index_old_diff_fn { $fb = join('/', @fb); if ($fa eq $fb) { unless ($seen->{$fa}++) { - index_diff_inc($tg, $fa, 'XDFN', $xnq); + $self->index_diff_inc($fa, 'XDFN', $xnq); } return 1; } @@ -167,22 +188,22 @@ sub index_old_diff_fn { } sub index_diff ($$$) { - my ($tg, $lines, $doc) = @_; + my ($self, $lines, $doc) = @_; my %seen; my $in_diff; my @xnq; my $xnq = \@xnq; foreach (@$lines) { if ($in_diff && s/^ //) { # diff context - index_diff_inc($tg, $_, 'XDFCTX', $xnq); + $self->index_diff_inc($_, '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($tg, $fn, 'XDFN', $xnq); + $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); $fn = (split('/', git_unquote($fb), 2))[1]; - $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq); + $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); $in_diff = 1; # traditional diff: } elsif (m/^diff -(.+) (\S+) (\S+)$/) { @@ -190,26 +211,26 @@ sub index_diff ($$$) { push @xnq, $_; # only support unified: next unless $opt =~ /[uU]/; - $in_diff = index_old_diff_fn($tg, \%seen, $fa, $fb, + $in_diff = $self->index_old_diff_fn(\%seen, $fa, $fb, $xnq); } elsif (m!^--- ("?a/.+)!) { my $fn = (split('/', git_unquote($1), 2))[1]; - $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq); + $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); $in_diff = 1; } elsif (m!^\+\+\+ ("?b/.+)!) { my $fn = (split('/', git_unquote($1), 2))[1]; - $seen{$fn}++ or index_diff_inc($tg, $fn, 'XDFN', $xnq); + $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq); $in_diff = 1; } elsif (/^--- (\S+)/) { $in_diff = $1; push @xnq, $_; } elsif (defined $in_diff && /^\+\+\+ (\S+)/) { - $in_diff = index_old_diff_fn($tg, \%seen, $in_diff, $1, + $in_diff = $self->index_old_diff_fn(\%seen, $in_diff, $1, $xnq); } elsif ($in_diff && s/^\+//) { # diff added - index_diff_inc($tg, $_, 'XDFB', $xnq); + $self->index_diff_inc($_, 'XDFB', $xnq); } elsif ($in_diff && s/^-//) { # diff removed - index_diff_inc($tg, $_, 'XDFA', $xnq); + $self->index_diff_inc($_, 'XDFA', $xnq); } elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) { my ($ba, $bb) = ($1, $2); index_git_blob_id($doc, 'XDFPRE', $ba); @@ -219,7 +240,7 @@ sub index_diff ($$$) { # traditional diff w/o -p } elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) { # hunk header context - index_diff_inc($tg, $1, 'XDFHH', $xnq); + $self->index_diff_inc($1, 'XDFHH', $xnq); # ignore the following lines: } elsif (/^(?:dis)similarity index/ || /^(?:old|new) mode/ || @@ -238,32 +259,101 @@ sub index_diff ($$$) { } } - $tg->index_text(join("\n", @xnq), 1, 'XNQ'); - $tg->increase_termpos; + $self->index_text(join("\n", @xnq), 1, 'XNQ'); } sub index_body ($$$) { - my ($tg, $lines, $doc) = @_; + my ($self, $lines, $doc) = @_; my $txt = join("\n", @$lines); if ($doc) { # does it look like a diff? if ($txt =~ /^(?:diff|---|\+\+\+) /ms) { $txt = undef; - index_diff($tg, $lines, $doc); + $self->index_diff($lines, $doc); } else { - $tg->index_text($txt, 1, 'XNQ'); + $self->index_text($txt, 1, 'XNQ'); } } else { - $tg->index_text($txt, 0, 'XQUOT'); + $self->index_text($txt, 0, 'XQUOT'); } - $tg->increase_termpos; @$lines = (); } +sub add_xapian ($$$$$) { + my ($self, $mime, $num, $oid, $mids, $mid0) = @_; + my $smsg = PublicInbox::SearchMsg->new($mime); + my $doc = Search::Xapian::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 = $self->term_generator; + + $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; + }); + + foreach my $mid (@$mids) { + $self->index_text($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'); + } + } + $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_boolean_term($pfx . $id); + } + } + } + $doc->add_boolean_term('Q' . $_) foreach @$mids; + $self->{xdb}->replace_document($num, $doc); +} + sub add_message { # mime = Email::MIME object my ($self, $mime, $bytes, $num, $oid, $mid0) = @_; - my $doc_id; my $mids = mids($mime->header_obj); $mid0 = $mids->[0] unless defined $mid0; # v1 compatibility unless (defined $num) { # v1 @@ -271,102 +361,19 @@ sub add_message { $num = index_mm($self, $mime); } eval { - my $smsg = PublicInbox::SearchMsg->new($mime); - my $doc = $smsg->{doc}; - 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 = $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'); - $tg->increase_termpos; - } - - 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; - }); - - foreach my $mid (@$mids) { - $tg->index_text($mid, 1, 'XM'); - - # because too many Message-IDs are prefixed with - # "Pine.LNX."... - if ($mid =~ /\w{12,}/) { - my @long = ($mid =~ /(\w{3,}+)/g); - $tg->index_text(join(' ', @long), 1, 'XM'); - } - $tg->increase_termpos; + if ($self->{indexlevel} =~ $xapianlevels) { + $self->add_xapian($mime, $num, $oid, $mids, $mid0) } - $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_boolean_term($pfx . $id); - } - } - } - if (my $over = $self->{over}) { $over->add_overview($mime, $bytes, $num, $oid, $mid0); } - $doc->add_boolean_term('Q' . $_) foreach @$mids; - $self->{xdb}->replace_document($doc_id = $num, $doc); }; if ($@) { warn "failed to index message <".join('> <',@$mids).">: $@\n"; return undef; } - $doc_id; + $num; } # returns begin and end PostingIterator @@ -432,8 +439,8 @@ sub remove_by_oid { for (; $head != $tail; $head->inc) { my $docid = $head->get_docid; my $doc = $db->get_document($docid); - my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid); - $smsg->load_expand; + my $smsg = PublicInbox::SearchMsg->wrap($mid); + $smsg->load_expand($doc); if ($smsg->{blob} eq $oid) { push(@delete, $docid); } @@ -561,7 +568,13 @@ sub read_log { while (defined($line = <$log>)) { if ($line =~ /$addmsg/o) { my $blob = $1; - delete $D{$blob} and next; + 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); $add_cb->($self, $mime, $bytes, $blob); @@ -595,28 +608,45 @@ sub _git_log { my $git = $self->{git}; if (index($range, '..') < 0) { - my $regen_max = 0; - # 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); - ++$regen_max while <$fh>; - my (undef, $max) = $self->{mm}->minmax; - - if ($max && $max == $regen_max) { + # 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; + # 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>; + my $high = $self->{mm}->num_highwater; + + 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} = $max; + $self->{regen_up} = $high; } else { # normal regen is for for fresh data - $self->{regen_down} = $regen_max; + $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); } +# --is-ancestor requires git 1.8.0+ sub is_ancestor ($$$) { my ($git, $cur, $tip) = @_; return 0 unless $git->check($cur); @@ -690,7 +720,7 @@ sub _index_sync { } $dbh->commit; } - if ($mkey && $newest) { + if ($mkey && $newest && $self->{indexlevel} =~ $xapianlevels) { my $cur = $xdb->get_metadata($mkey); if (need_update($self, $cur, $newest)) { $xdb->set_metadata($mkey, $newest);