X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=445c2d8a403f4b3a314954852d7afd3819de565f;hb=adecbd43d2eed046fe6e88a459d03567461fd84b;hp=0f7815fb610124ece7bbbc8867e93199e085490e;hpb=f564327fd1e694056a4b13ed398cabd8d0d4c173;p=public-inbox.git diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index 0f7815fb..445c2d8a 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -12,6 +12,7 @@ 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 Search::Xapian qw/:standard/; use PublicInbox::SearchMsg; @@ -36,7 +37,8 @@ use constant { # 8 - remove redundant/unneeded document data # 9 - disable Message-ID compression (SHA-1) # 10 - optimize doc for NNTP overviews - SCHEMA_VERSION => 10, + # 11 - merge threads when vivifying ghosts + SCHEMA_VERSION => 11, # n.b. FLAG_PURE_NOT is expensive not suitable for a public website # as it could become a denial-of-service vector @@ -49,6 +51,7 @@ my %bool_pfx_internal = ( thread => 'G', # newsGroup (or similar entity - e.g. a web forum name) ); +# do we still need these? probably not.. my %bool_pfx_external = ( path => 'XPATH', mid => 'Q', # uniQue id (Message-ID) @@ -60,6 +63,29 @@ my %prob_prefix = ( m => 'Q', # 'mid' is exact, 'm' can do partial ); +# not documenting m: and mid: for now, the using the URLs works w/o Xapian +our @HELP = ( + 's:' => < <xdir($git_dir); my $db = Search::Xapian::Database->new($dir); - bless { xdb => $db, git_dir => $git_dir }, $class; + bless { xdb => $db, git_dir => $git_dir, altid => $altid }, $class; } sub reopen { $_[0]->{xdb}->reopen } @@ -97,7 +123,7 @@ sub query { $opts->{relevance} = 1 unless exists $opts->{relevance}; } - $self->do_enquire($query, $opts); + _do_enquire($self, $query, $opts); } sub get_thread { @@ -106,13 +132,34 @@ sub get_thread { return { total => 0, msgs => [] } unless $smsg; my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id); - my $path = id_compress($smsg->path); - my $qsub = Search::Xapian::Query->new(xpfx('path').$path); - my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub); - $self->do_enquire($query, $opts); + my $path = $smsg->path; + if (defined $path && $path ne '') { + my $path = id_compress($smsg->path); + my $qsub = Search::Xapian::Query->new(xpfx('path').$path); + $qtid = Search::Xapian::Query->new(OP_OR, $qtid, $qsub); + } + $opts ||= {}; + $opts->{limit} ||= 1000; + _do_enquire($self, $qtid, $opts); +} + +sub _do_enquire { + my ($self, $query, $opts) = @_; + my $ret; + for (1..10) { + eval { $ret = _enquire_once($self, $query, $opts) }; + return $ret unless $@; + # Exception: The revision being read has been discarded - + # you should call Xapian::Database::reopen() + if (index($@, 'Xapian::Database::reopen') >= 0) { + reopen($self); + } else { + die $@; + } + } } -sub do_enquire { +sub _enquire_once { my ($self, $query, $opts) = @_; my $enquire = $self->enquire; if (defined $query) { @@ -125,6 +172,8 @@ sub do_enquire { my $desc = !$opts->{asc}; if ($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); } @@ -155,13 +204,29 @@ sub qp { $qp->set_database($self->{xdb}); $qp->set_stemmer($self->stemmer); $qp->set_stemming_strategy(STEM_SOME); - $qp->add_valuerangeprocessor($self->ts_range_processor); - $qp->add_valuerangeprocessor($self->date_range_processor); + $qp->add_valuerangeprocessor( + Search::Xapian::StringValueRangeProcessor->new(YYYYMMDD, 'd:')); while (my ($name, $prefix) = each %bool_pfx_external) { $qp->add_boolean_prefix($name, $prefix); } + # we do not actually create AltId objects, + # just parse the spec to avoid the extra DB handles for now. + if (my $altid = $self->{altid}) { + my $user_pfx = $self->{-user_pfx} ||= []; + for (@$altid) { + # $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3' + /\Aserial:(\w+):/ or next; + my $pfx = $1; + push @$user_pfx, "$pfx:", < XGMANE + $qp->add_boolean_prefix($pfx, 'X'.uc($pfx)); + } + } + while (my ($name, $prefix) = each %prob_prefix) { $qp->add_prefix($name, $prefix); } @@ -169,14 +234,6 @@ sub qp { $self->{query_parser} = $qp; } -sub ts_range_processor { - $_[0]->{tsrp} ||= Search::Xapian::NumberValueRangeProcessor->new(TS); -} - -sub date_range_processor { - $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS); -} - sub num_range_processor { $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM); } @@ -184,21 +241,12 @@ sub num_range_processor { # only used for NNTP server sub query_xover { my ($self, $beg, $end, $offset) = @_; - my $enquire = $self->enquire; 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); - $query = Search::Xapian::Query->new(OP_AND, $mail_query, $query); - $enquire->set_query($query); - $enquire->set_sort_by_value(NUM, 0); - my $limit = 200; - my $mset = $enquire->get_mset($offset, $limit); - my @msgs = map { - PublicInbox::SearchMsg->load_doc($_->get_document); - } $mset->items; - { total => $mset->get_matches_estimated, msgs => \@msgs } + _do_enquire($self, $query, {num => 1, limit => 200, offset => $offset}); } sub lookup_message { @@ -216,6 +264,12 @@ sub lookup_message { $smsg; } +sub lookup_mail { # no ghosts! + my ($self, $mid) = @_; + my $smsg = lookup_message($self, $mid) or return; + PublicInbox::SearchMsg->load_doc($smsg->{doc}); +} + sub find_unique_doc_id { my ($self, $term, $value) = @_; @@ -295,4 +349,14 @@ sub enquire { $self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb}); } +sub help { + my ($self) = @_; + $self->qp; # parse altids + my @ret = @HELP; + if (my $user_pfx = $self->{-user_pfx}) { + push @ret, @$user_pfx; + } + \@ret; +} + 1;