diff options
Diffstat (limited to 'lib/PublicInbox/Search.pm')
| -rw-r--r-- | lib/PublicInbox/Search.pm | 232 |
1 files changed, 103 insertions, 129 deletions
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index df02e0b5..7175ddc5 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -8,16 +8,15 @@ use strict; use warnings; # values for searching -use constant TS => 0; # timestamp -use constant NUM => 1; # NNTP article number -use constant BYTES => 2; # :bytes as defined in RFC 3977 -use constant LINES => 3; # :lines as defined in RFC 3977 -use constant YYYYMMDD => 4; # for searching in the WWW UI +use constant TS => 0; # Received: header in Unix time +use constant YYYYMMDD => 1; # Date: header for searching in the WWW UI +use constant DT => 2; # Date: YYYYMMDDHHMMSS use Search::Xapian qw/:standard/; use PublicInbox::SearchMsg; use PublicInbox::MIME; -use PublicInbox::MID qw/mid_clean id_compress/; +use PublicInbox::MID qw/id_compress/; +use PublicInbox::Over; # This is English-only, everything else is non-standard and may be confused as # a prefix common in patch emails @@ -42,39 +41,34 @@ use constant { # 13 - fix threading for empty References/In-Reply-To # (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0) # 14 - fix ghost root vivification - SCHEMA_VERSION => 14, + SCHEMA_VERSION => 15, # n.b. FLAG_PURE_NOT is expensive not suitable for a public website # as it could become a denial-of-service vector QP_FLAGS => FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE|FLAG_WILDCARD, }; -# setup prefixes -my %bool_pfx_internal = ( - type => 'T', # "mail" or "ghost" - thread => 'G', # newsGroup (or similar entity - e.g. a web forum name) -); - my %bool_pfx_external = ( - mid => 'Q', # uniQue id (Message-ID) + mid => 'Q', # Message-ID (full/exact), this is mostly uniQue ); +my $non_quoted_body = 'XNQ XDFN XDFA XDFB XDFHH XDFCTX XDFPRE XDFPOST'; my %prob_prefix = ( # for mairix compatibility s => 'S', - m => 'XMID', # 'mid:' (bool) is exact, 'm:' (prob) can do partial + m => 'XM', # 'mid:' (bool) is exact, 'm:' (prob) can do partial f => 'A', t => 'XTO', tc => 'XTO XCC', c => 'XCC', tcf => 'XTO XCC A', a => 'XTO XCC A', - b => 'XNQ XQUOT', - bs => 'XNQ XQUOT S', + b => $non_quoted_body . ' XQUOT', + bs => $non_quoted_body . ' XQUOT S', n => 'XFN', q => 'XQUOT', - nq => 'XNQ', + nq => $non_quoted_body, dfn => 'XDFN', dfa => 'XDFA', dfb => 'XDFB', @@ -85,7 +79,7 @@ my %prob_prefix = ( dfblob => 'XDFPRE XDFPOST', # default: - '' => 'XMID S A XNQ XQUOT XFN', + '' => 'XM S A XQUOT XFN ' . $non_quoted_body, ); # not documenting m: and mid: for now, the using the URLs works w/o Xapian @@ -96,6 +90,9 @@ date range as YYYYMMDD e.g. d:19931002..20101002 Open-ended ranges such as d:19931002.. and d:..20101002 are also supported EOF + 'dt:' => <<EOF, +date-time range as YYYYMMDDhhmmss (e.g. dt:19931002011000..19931002011200) +EOF 'b:' => 'match within message body, including text attachments', 'nq:' => 'match non-quoted text within message body', 'q:' => 'match quoted text within message body', @@ -117,72 +114,102 @@ EOF ); chomp @HELP; -my $mail_query = Search::Xapian::Query->new('T' . 'mail'); - sub xdir { - my (undef, $git_dir) = @_; - "$git_dir/public-inbox/xapian" . SCHEMA_VERSION; + my ($self) = @_; + if ($self->{version} == 1) { + "$self->{mainrepo}/public-inbox/xapian" . SCHEMA_VERSION; + } else { + my $dir = "$self->{mainrepo}/xap" . SCHEMA_VERSION; + my $part = $self->{partition}; + defined $part or die "partition not given"; + $dir .= "/$part"; + } } sub new { - my ($class, $git_dir, $altid) = @_; - my $dir = $class->xdir($git_dir); - my $db = Search::Xapian::Database->new($dir); - bless { xdb => $db, git_dir => $git_dir, altid => $altid }, $class; + my ($class, $mainrepo, $altid) = @_; + my $version = 1; + my $ibx = $mainrepo; + if (ref $ibx) { + $version = $ibx->{version} || 1; + $mainrepo = $ibx->{mainrepo}; + } + my $self = bless { + mainrepo => $mainrepo, + altid => $altid, + version => $version, + }, $class; + my $dir; + if ($version >= 2) { + $dir = "$self->{mainrepo}/xap" . SCHEMA_VERSION; + my $xdb; + my $parts = 0; + foreach my $part (<$dir/*>) { + -d $part && $part =~ m!/\d+\z! or next; + $parts++; + my $sub = Search::Xapian::Database->new($part); + if ($xdb) { + $xdb->add_database($sub); + } else { + $xdb = $sub; + } + } + $self->{xdb} = $xdb; + } else { + $dir = $self->xdir; + $self->{xdb} = Search::Xapian::Database->new($dir); + } + $self->{over_ro} = PublicInbox::Over->new("$dir/over.sqlite3"); + $self; } -sub reopen { $_[0]->{xdb}->reopen } +sub reopen { + my ($self) = @_; + $self->{xdb}->reopen; + $self; # make chaining easier +} # read-only sub query { my ($self, $query_string, $opts) = @_; - my $query; - $opts ||= {}; - unless ($query_string eq '') { - $query = $self->qp->parse_query($query_string, QP_FLAGS); + if ($query_string eq '' && !$opts->{mset}) { + $self->{over_ro}->recent($opts); + } else { + my $query = $self->qp->parse_query($query_string, QP_FLAGS); $opts->{relevance} = 1 unless exists $opts->{relevance}; + _do_enquire($self, $query, $opts); } - - _do_enquire($self, $query, $opts); } sub get_thread { - my ($self, $mid, $opts) = @_; - my $smsg = eval { $self->lookup_message($mid) }; - - return { total => 0, msgs => [] } unless $smsg; - my $qtid = Search::Xapian::Query->new('G' . $smsg->thread_id); - my $path = $smsg->path; - if (defined $path && $path ne '') { - my $path = id_compress($smsg->path); - my $qsub = Search::Xapian::Query->new('XPATH' . $path); - $qtid = Search::Xapian::Query->new(OP_OR, $qtid, $qsub); - } - $opts ||= {}; - $opts->{limit} ||= 1000; - - # always sort threads by timestamp, this makes life easier - # for the threading algorithm (in SearchThread.pm) - $opts->{asc} = 1; - - _do_enquire($self, $qtid, $opts); + my ($self, $mid, $prev) = @_; + $self->{over_ro}->get_thread($mid, $prev); } sub retry_reopen { my ($self, $cb) = @_; - my $ret; - for (1..10) { - eval { $ret = $cb->() }; - return $ret unless $@; + for my $i (1..10) { + if (wantarray) { + my @ret; + eval { @ret = $cb->() }; + return @ret unless $@; + } else { + my $ret; + eval { $ret = $cb->() }; + return $ret unless $@; + } # Exception: The revision being read has been discarded - # you should call Xapian::Database::reopen() if (ref($@) eq 'Search::Xapian::DatabaseModifiedError') { + warn "reopen try #$i on $@\n"; reopen($self); } else { + warn "ref: ", ref($@), "\n"; die; } } + die "Too many Xapian database modifications in progress\n"; } sub _do_enquire { @@ -192,19 +219,16 @@ sub _do_enquire { sub _enquire_once { my ($self, $query, $opts) = @_; - my $enquire = $self->enquire; - if (defined $query) { - $query = Search::Xapian::Query->new(OP_AND,$query,$mail_query); - } else { - $query = $mail_query; - } + my $enquire = enquire($self); $enquire->set_query($query); $opts ||= {}; my $desc = !$opts->{asc}; - if ($opts->{relevance}) { + if (($opts->{mset} || 0) == 2) { + $enquire->set_docid_order(Search::Xapian::ENQ_ASCENDING()); + $enquire->set_weighting_scheme(Search::Xapian::BoolWeight->new); + delete $self->{enquire}; + } elsif ($opts->{relevance}) { $enquire->set_sort_by_relevance_then_value(TS, $desc); - } elsif ($opts->{num}) { - $enquire->set_sort_by_value(NUM, 0); } else { $enquire->set_sort_by_value_then_relevance(TS, $desc); } @@ -215,8 +239,9 @@ sub _enquire_once { my @msgs = map { PublicInbox::SearchMsg->load_doc($_->get_document); } $mset->items; + return \@msgs unless wantarray; - { total => $mset->get_matches_estimated, msgs => \@msgs } + ($mset->get_matches_estimated, \@msgs) } # read-write @@ -237,6 +262,8 @@ sub qp { $qp->set_stemming_strategy(STEM_SOME); $qp->add_valuerangeprocessor( Search::Xapian::NumberValueRangeProcessor->new(YYYYMMDD, 'd:')); + $qp->add_valuerangeprocessor( + Search::Xapian::NumberValueRangeProcessor->new(DT, 'dt:')); while (my ($name, $prefix) = each %bool_pfx_external) { $qp->add_boolean_prefix($name, $prefix); @@ -266,78 +293,25 @@ EOF $self->{query_parser} = $qp; } -sub num_range_processor { - $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM); -} - # only used for NNTP server sub query_xover { my ($self, $beg, $end, $offset) = @_; - my $qp = Search::Xapian::QueryParser->new; - $qp->set_database($self->{xdb}); - $qp->add_valuerangeprocessor($self->num_range_processor); - my $query = $qp->parse_query("$beg..$end", QP_FLAGS); - - _do_enquire($self, $query, {num => 1, limit => 200, offset => $offset}); + $self->{over_ro}->query_xover($beg, $end, $offset); } sub query_ts { - my ($self, $ts, $opts) = @_; - my $qp = $self->{qp_ts} ||= eval { - my $q = Search::Xapian::QueryParser->new; - $q->set_database($self->{xdb}); - $q->add_valuerangeprocessor( - Search::Xapian::NumberValueRangeProcessor->new(TS)); - $q - }; - my $query = $qp->parse_query($ts, QP_FLAGS); - _do_enquire($self, $query, $opts); + my ($self, $ts, $prev) = @_; + $self->{over_ro}->query_ts($ts, $prev); } -sub lookup_message { - my ($self, $mid) = @_; - $mid = mid_clean($mid); - - my $doc_id = $self->find_unique_doc_id('Q' . $mid); - my $smsg; - if (defined $doc_id) { - # raises on error: - my $doc = $self->{xdb}->get_document($doc_id); - $smsg = PublicInbox::SearchMsg->wrap($doc, $mid); - $smsg->{doc_id} = $doc_id; - } - $smsg; +sub lookup_article { + my ($self, $num) = @_; + $self->{over_ro}->get_art($num); } -sub lookup_mail { # no ghosts! - my ($self, $mid) = @_; - retry_reopen($self, sub { - my $smsg = lookup_message($self, $mid) or return; - $smsg->load_expand; - }); -} - -sub find_unique_doc_id { - my ($self, $termval) = @_; - - my ($begin, $end) = $self->find_doc_ids($termval); - - return undef if $begin->equal($end); # not found - - my $rv = $begin->get_docid; - - # sanity check - $begin->inc; - $begin->equal($end) or die "Term '$termval' is not unique\n"; - $rv; -} - -# returns begin and end PostingIterator -sub find_doc_ids { - my ($self, $termval) = @_; - my $db = $self->{xdb}; - - ($db->postlist_begin($termval), $db->postlist_end($termval)); +sub next_by_mid { + my ($self, $mid, $id, $prev) = @_; + $self->{over_ro}->next_by_mid($mid, $id, $prev); } # normalize subjects so they are suitable as pathnames for URLs |