27 |
|
|
28 |
=cut |
=cut |
29 |
|
|
30 |
|
=head1 Inheritable common methods |
31 |
|
|
32 |
|
This methods should really move somewhere else. |
33 |
|
|
34 |
=head2 _s |
=head2 _s |
35 |
|
|
36 |
Remove multiple whitespaces from string, as well as whitespaces at beginning or end |
Remove multiple whitespaces from string, as well as whitespaces at beginning or end |
60 |
This class implements Document which is collection of attributes |
This class implements Document which is collection of attributes |
61 |
(key=value), vectors (also key value) display text and hidden text. |
(key=value), vectors (also key value) display text and hidden text. |
62 |
|
|
63 |
|
|
64 |
=head2 new |
=head2 new |
65 |
|
|
66 |
Create new document, empty or from draft. |
Create new document, empty or from draft. |
180 |
push @{ $self->{htexts} }, $self->_s($text); |
push @{ $self->{htexts} }, $self->_s($text); |
181 |
} |
} |
182 |
|
|
183 |
|
|
184 |
=head2 id |
=head2 id |
185 |
|
|
186 |
Get the ID number of document. If the object has never been registred, C<-1> is returned. |
Get the ID number of document. If the object has never been registred, C<-1> is returned. |
194 |
return $self->{id}; |
return $self->{id}; |
195 |
} |
} |
196 |
|
|
197 |
|
|
198 |
=head2 attr_names |
=head2 attr_names |
199 |
|
|
200 |
Returns array with attribute names from document object. |
Returns array with attribute names from document object. |
240 |
return @{ $self->{dtexts} }; |
return @{ $self->{dtexts} }; |
241 |
} |
} |
242 |
|
|
243 |
|
|
244 |
=head2 cat_texts |
=head2 cat_texts |
245 |
|
|
246 |
Return whole text as single scalar. |
Return whole text as single scalar. |
254 |
return join(' ',@{ $self->{dtexts} }); |
return join(' ',@{ $self->{dtexts} }); |
255 |
} |
} |
256 |
|
|
257 |
|
|
258 |
=head2 dump_draft |
=head2 dump_draft |
259 |
|
|
260 |
Dump draft data from document object. |
Dump draft data from document object. |
287 |
return $draft; |
return $draft; |
288 |
} |
} |
289 |
|
|
290 |
|
|
291 |
=head2 delete |
=head2 delete |
292 |
|
|
293 |
Empty document object |
Empty document object |
340 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
341 |
} |
} |
342 |
|
|
343 |
|
|
344 |
=head2 set_phrase |
=head2 set_phrase |
345 |
|
|
346 |
$cond->set_phrase('search phrase'); |
$cond->set_phrase('search phrase'); |
352 |
$self->{phrase} = $self->_s( shift ); |
$self->{phrase} = $self->_s( shift ); |
353 |
} |
} |
354 |
|
|
355 |
|
|
356 |
=head2 add_attr |
=head2 add_attr |
357 |
|
|
358 |
$cond->add_attr('@URI STRINC /~dpavlin/'); |
$cond->add_attr('@URI STRINC /~dpavlin/'); |
365 |
push @{ $self->{attrs} }, $self->_s( $attr ); |
push @{ $self->{attrs} }, $self->_s( $attr ); |
366 |
} |
} |
367 |
|
|
368 |
|
|
369 |
=head2 set_order |
=head2 set_order |
370 |
|
|
371 |
$cond->set_order('@mdate NUMD'); |
$cond->set_order('@mdate NUMD'); |
377 |
$self->{order} = shift; |
$self->{order} = shift; |
378 |
} |
} |
379 |
|
|
380 |
|
|
381 |
=head2 set_max |
=head2 set_max |
382 |
|
|
383 |
$cond->set_max(42); |
$cond->set_max(42); |
387 |
sub set_max { |
sub set_max { |
388 |
my $self = shift; |
my $self = shift; |
389 |
my $max = shift; |
my $max = shift; |
390 |
croak "set_max needs number" unless ($max =~ m/^\d+$/); |
croak "set_max needs number, not '$max'" unless ($max =~ m/^\d+$/); |
391 |
$self->{max} = $max; |
$self->{max} = $max; |
392 |
} |
} |
393 |
|
|
394 |
|
|
395 |
=head2 set_options |
=head2 set_options |
396 |
|
|
397 |
$cond->set_options( SURE => 1 ); |
$cond->set_options( SURE => 1 ); |
420 |
$self->{options} ||= $options->{$option}; |
$self->{options} ||= $options->{$option}; |
421 |
} |
} |
422 |
|
|
423 |
|
|
424 |
=head2 phrase |
=head2 phrase |
425 |
|
|
426 |
Return search phrase. |
Return search phrase. |
434 |
return $self->{phrase}; |
return $self->{phrase}; |
435 |
} |
} |
436 |
|
|
437 |
|
|
438 |
=head2 order |
=head2 order |
439 |
|
|
440 |
Return search result order. |
Return search result order. |
448 |
return $self->{order}; |
return $self->{order}; |
449 |
} |
} |
450 |
|
|
451 |
|
|
452 |
=head2 attrs |
=head2 attrs |
453 |
|
|
454 |
Return search result attrs. |
Return search result attrs. |
463 |
return @{ $self->{attrs} }; |
return @{ $self->{attrs} }; |
464 |
} |
} |
465 |
|
|
466 |
|
|
467 |
=head2 max |
=head2 max |
468 |
|
|
469 |
Return maximum number of results. |
Return maximum number of results. |
479 |
return $self->{max}; |
return $self->{max}; |
480 |
} |
} |
481 |
|
|
482 |
|
|
483 |
=head2 options |
=head2 options |
484 |
|
|
485 |
Return options for this condition. |
Return options for this condition. |
531 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
532 |
} |
} |
533 |
|
|
534 |
|
|
535 |
=head2 uri |
=head2 uri |
536 |
|
|
537 |
Return URI of result document |
Return URI of result document |
560 |
return sort keys %{ $self->{attrs} }; |
return sort keys %{ $self->{attrs} }; |
561 |
} |
} |
562 |
|
|
563 |
|
|
564 |
=head2 attr |
=head2 attr |
565 |
|
|
566 |
Returns value of an attribute. |
Returns value of an attribute. |
575 |
return $self->{attrs}->{ $name }; |
return $self->{attrs}->{ $name }; |
576 |
} |
} |
577 |
|
|
578 |
|
|
579 |
=head2 snippet |
=head2 snippet |
580 |
|
|
581 |
Return snippet from result document |
Return snippet from result document |
589 |
return $self->{snippet}; |
return $self->{snippet}; |
590 |
} |
} |
591 |
|
|
592 |
|
|
593 |
=head2 keywords |
=head2 keywords |
594 |
|
|
595 |
Return keywords from result document |
Return keywords from result document |
634 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
635 |
} |
} |
636 |
|
|
637 |
|
|
638 |
=head2 doc_num |
=head2 doc_num |
639 |
|
|
640 |
Return number of documents |
Return number of documents |
648 |
return $#{$self->{docs}}; |
return $#{$self->{docs}}; |
649 |
} |
} |
650 |
|
|
651 |
|
|
652 |
=head2 get_doc |
=head2 get_doc |
653 |
|
|
654 |
Return single document |
Return single document |
662 |
sub get_doc { |
sub get_doc { |
663 |
my $self = shift; |
my $self = shift; |
664 |
my $num = shift; |
my $num = shift; |
665 |
croak "expect number as argument" unless ($num =~ m/^\d+$/); |
croak "expect number as argument, not '$num'" unless ($num =~ m/^\d+$/); |
666 |
return undef if ($num < 0 || $num > $self->{docs}); |
return undef if ($num < 0 || $num > $self->{docs}); |
667 |
return $self->{docs}->[$num]; |
return $self->{docs}->[$num]; |
668 |
} |
} |
669 |
|
|
670 |
|
|
671 |
=head2 hint |
=head2 hint |
672 |
|
|
673 |
Return specific hint from results. |
Return specific hint from results. |
688 |
|
|
689 |
package Search::Estraier::Node; |
package Search::Estraier::Node; |
690 |
|
|
691 |
use Carp qw/carp croak/; |
use Carp qw/carp croak confess/; |
692 |
use URI; |
use URI; |
693 |
use MIME::Base64; |
use MIME::Base64; |
694 |
use IO::Socket::INET; |
use IO::Socket::INET; |
724 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
725 |
} |
} |
726 |
|
|
727 |
|
|
728 |
=head2 set_url |
=head2 set_url |
729 |
|
|
730 |
Specify URL to node server |
Specify URL to node server |
738 |
$self->{url} = shift; |
$self->{url} = shift; |
739 |
} |
} |
740 |
|
|
741 |
|
|
742 |
=head2 set_proxy |
=head2 set_proxy |
743 |
|
|
744 |
Specify proxy server to connect to node server |
Specify proxy server to connect to node server |
750 |
sub set_proxy { |
sub set_proxy { |
751 |
my $self = shift; |
my $self = shift; |
752 |
my ($host,$port) = @_; |
my ($host,$port) = @_; |
753 |
croak "proxy port must be number" unless ($port =~ m/^\d+$/); |
croak "proxy port must be number, not '$port'" unless ($port =~ m/^\d+$/); |
754 |
$self->{pxhost} = $host; |
$self->{pxhost} = $host; |
755 |
$self->{pxport} = $port; |
$self->{pxport} = $port; |
756 |
} |
} |
757 |
|
|
758 |
|
|
759 |
=head2 set_timeout |
=head2 set_timeout |
760 |
|
|
761 |
Specify timeout of connection in seconds |
Specify timeout of connection in seconds |
767 |
sub set_timeout { |
sub set_timeout { |
768 |
my $self = shift; |
my $self = shift; |
769 |
my $sec = shift; |
my $sec = shift; |
770 |
croak "timeout must be number" unless ($sec =~ m/^\d+$/); |
croak "timeout must be number, not '$sec'" unless ($sec =~ m/^\d+$/); |
771 |
$self->{timeout} = $sec; |
$self->{timeout} = $sec; |
772 |
} |
} |
773 |
|
|
774 |
|
|
775 |
=head2 set_auth |
=head2 set_auth |
776 |
|
|
777 |
Specify name and password for authentication to node server. |
Specify name and password for authentication to node server. |
788 |
$self->{auth} = $basic_auth; |
$self->{auth} = $basic_auth; |
789 |
} |
} |
790 |
|
|
791 |
|
|
792 |
=head2 status |
=head2 status |
793 |
|
|
794 |
Return status code of last request. |
Return status code of last request. |
804 |
return $self->{status}; |
return $self->{status}; |
805 |
} |
} |
806 |
|
|
807 |
|
|
808 |
=head2 put_doc |
=head2 put_doc |
809 |
|
|
810 |
Add a document |
Add a document |
818 |
sub put_doc { |
sub put_doc { |
819 |
my $self = shift; |
my $self = shift; |
820 |
my $doc = shift || return; |
my $doc = shift || return; |
821 |
return unless ($self->{url}); |
return unless ($self->{url} && $doc->isa('Search::Estraier::Document')); |
822 |
$self->shuttle_url( $self->{url} . '/put_doc', |
$self->shuttle_url( $self->{url} . '/put_doc', |
823 |
'text/x-estraier-draft', |
'text/x-estraier-draft', |
824 |
$doc->dump_draft, |
$doc->dump_draft, |
841 |
my $self = shift; |
my $self = shift; |
842 |
my $id = shift || return; |
my $id = shift || return; |
843 |
return unless ($self->{url}); |
return unless ($self->{url}); |
844 |
croak "id must be number" unless ($id =~ m/^\d+$/); |
croak "id must be number, not '$id'" unless ($id =~ m/^\d+$/); |
845 |
$self->shuttle_url( $self->{url} . '/out_doc', |
$self->shuttle_url( $self->{url} . '/out_doc', |
846 |
'application/x-www-form-urlencoded', |
'application/x-www-form-urlencoded', |
847 |
"id=$id", |
"id=$id", |
854 |
|
|
855 |
Remove a registrated document using it's uri |
Remove a registrated document using it's uri |
856 |
|
|
857 |
$node->out_doc_by_uri( 'file:///document_url' ) or "can't remove document"; |
$node->out_doc_by_uri( 'file:///document/uri/42' ) or "can't remove document"; |
858 |
|
|
859 |
Return true on success or false on failture. |
Return true on success or false on failture. |
860 |
|
|
871 |
) == 200; |
) == 200; |
872 |
} |
} |
873 |
|
|
874 |
|
|
875 |
|
=head2 edit_doc |
876 |
|
|
877 |
|
Edit attributes of a document |
878 |
|
|
879 |
|
$node->edit_doc( $document_draft ) or die "can't edit document"; |
880 |
|
|
881 |
|
Return true on success or false on failture. |
882 |
|
|
883 |
|
=cut |
884 |
|
|
885 |
|
sub edit_doc { |
886 |
|
my $self = shift; |
887 |
|
my $doc = shift || return; |
888 |
|
return unless ($self->{url} && $doc->isa('Search::Estraier::Document')); |
889 |
|
$self->shuttle_url( $self->{url} . '/edit_doc', |
890 |
|
'text/x-estraier-draft', |
891 |
|
$doc->dump_draft, |
892 |
|
undef |
893 |
|
) == 200; |
894 |
|
} |
895 |
|
|
896 |
|
|
897 |
|
=head2 get_doc |
898 |
|
|
899 |
|
Retreive document |
900 |
|
|
901 |
|
my $doc = $node->get_doc( document_id ) or die "can't get document"; |
902 |
|
|
903 |
|
Return true on success or false on failture. |
904 |
|
|
905 |
|
=cut |
906 |
|
|
907 |
|
sub get_doc { |
908 |
|
my $self = shift; |
909 |
|
my $id = shift || return; |
910 |
|
return $self->_fetch_doc( id => $id ); |
911 |
|
} |
912 |
|
|
913 |
|
|
914 |
|
=head2 get_doc_by_uri |
915 |
|
|
916 |
|
Retreive document |
917 |
|
|
918 |
|
my $doc = $node->get_doc_by_uri( 'file:///document/uri/42' ) or die "can't get document"; |
919 |
|
|
920 |
|
Return true on success or false on failture. |
921 |
|
|
922 |
|
=cut |
923 |
|
|
924 |
|
sub get_doc_by_uri { |
925 |
|
my $self = shift; |
926 |
|
my $uri = shift || return; |
927 |
|
return $self->_fetch_doc( uri => $uri ); |
928 |
|
} |
929 |
|
|
930 |
|
|
931 |
|
=head2 etch_doc |
932 |
|
|
933 |
|
Exctract document keywords |
934 |
|
|
935 |
|
my $keywords = $node->etch_doc( document_id ) or die "can't etch document"; |
936 |
|
|
937 |
|
=cut |
938 |
|
|
939 |
|
sub erch_doc { |
940 |
|
my $self = shift; |
941 |
|
my $id = shift || return; |
942 |
|
return $self->_fetch_doc( id => $id, etch => 1 ); |
943 |
|
} |
944 |
|
|
945 |
|
=head2 etch_doc_by_uri |
946 |
|
|
947 |
|
Retreive document |
948 |
|
|
949 |
|
my $keywords = $node->etch_doc_by_uri( 'file:///document/uri/42' ) or die "can't etch document"; |
950 |
|
|
951 |
|
Return true on success or false on failture. |
952 |
|
|
953 |
|
=cut |
954 |
|
|
955 |
|
sub etch_doc_by_uri { |
956 |
|
my $self = shift; |
957 |
|
my $uri = shift || return; |
958 |
|
return $self->_fetch_doc( uri => $uri, etch => 1 ); |
959 |
|
} |
960 |
|
|
961 |
|
|
962 |
|
=head2 uri_to_id |
963 |
|
|
964 |
|
Get ID of document specified by URI |
965 |
|
|
966 |
|
my $id = $node->uri_to_id( 'file:///document/uri/42' ); |
967 |
|
|
968 |
|
=cut |
969 |
|
|
970 |
|
sub uri_to_id { |
971 |
|
my $self = shift; |
972 |
|
my $uri = shift || return; |
973 |
|
return $self->_fetch_doc( uri => $uri, path => '/uri_to_id', chomp_resbody => 1 ); |
974 |
|
} |
975 |
|
|
976 |
|
|
977 |
|
=head2 _fetch_doc |
978 |
|
|
979 |
|
Private function used for implementing of C<get_doc>, C<get_doc_by_uri>, |
980 |
|
C<etch_doc>, C<etch_doc_by_uri>. |
981 |
|
|
982 |
|
# this will decode received draft into Search::Estraier::Document object |
983 |
|
my $doc = $node->_fetch_doc( id => 42 ); |
984 |
|
my $doc = $node->_fetch_doc( uri => 'file:///document/uri/42' ); |
985 |
|
|
986 |
|
# to extract keywords, add etch |
987 |
|
my $doc = $node->_fetch_doc( id => 42, etch => 1 ); |
988 |
|
my $doc = $node->_fetch_doc( uri => 'file:///document/uri/42', etch => 1 ); |
989 |
|
|
990 |
|
# more general form which allows implementation of |
991 |
|
# uri_to_id |
992 |
|
my $id = $node->_fetch_doc( |
993 |
|
uri => 'file:///document/uri/42', |
994 |
|
path => '/uri_to_id', |
995 |
|
chomp_resbody => 1 |
996 |
|
); |
997 |
|
|
998 |
|
=cut |
999 |
|
|
1000 |
|
sub _fetch_doc { |
1001 |
|
my $self = shift; |
1002 |
|
my $a = {@_}; |
1003 |
|
return unless ( ($a->{id} || $a->{uri}) && $self->{url} ); |
1004 |
|
|
1005 |
|
my ($arg, $resbody); |
1006 |
|
|
1007 |
|
my $path = $a->{path} || '/get_doc'; |
1008 |
|
$path = '/etch_doc' if ($a->{etch}); |
1009 |
|
|
1010 |
|
if ($a->{id}) { |
1011 |
|
croak "id must be numberm not '$a->{id}'" unless ($a->{id} =~ m/^\d+$/); |
1012 |
|
$arg = 'id=' . $a->{id}; |
1013 |
|
} elsif ($a->{uri}) { |
1014 |
|
$arg = 'uri=' . $a->{uri}; |
1015 |
|
} else { |
1016 |
|
confess "unhandled argument. Need id or uri."; |
1017 |
|
} |
1018 |
|
|
1019 |
|
my $rv = $self->shuttle_url( $self->{url} . $path, |
1020 |
|
'application/x-www-form-urlencoded', |
1021 |
|
$arg, |
1022 |
|
\$resbody, |
1023 |
|
); |
1024 |
|
|
1025 |
|
return if ($rv != 200); |
1026 |
|
|
1027 |
|
if ($a->{etch}) { |
1028 |
|
$self->{kwords} = {}; |
1029 |
|
return +{} unless ($resbody); |
1030 |
|
foreach my $l (split(/\n/, $resbody)) { |
1031 |
|
my ($k,$v) = split(/\t/, $l, 2); |
1032 |
|
$self->{kwords}->{$k} = $v if ($v); |
1033 |
|
} |
1034 |
|
return $self->{kwords}; |
1035 |
|
} elsif ($a->{chomp_resbody}) { |
1036 |
|
return unless (defined($resbody)); |
1037 |
|
chomp($resbody); |
1038 |
|
return $resbody; |
1039 |
|
} else { |
1040 |
|
return new Search::Estraier::Document($resbody); |
1041 |
|
} |
1042 |
|
} |
1043 |
|
|
1044 |
|
|
1045 |
|
=head2 name |
1046 |
|
|
1047 |
|
my $node_name = $node->name; |
1048 |
|
|
1049 |
|
=cut |
1050 |
|
|
1051 |
|
sub name { |
1052 |
|
my $self = shift; |
1053 |
|
$self->set_info unless ($self->{name}); |
1054 |
|
return $self->{name}; |
1055 |
|
} |
1056 |
|
|
1057 |
|
|
1058 |
|
=head2 label |
1059 |
|
|
1060 |
|
my $node_label = $node->label; |
1061 |
|
|
1062 |
|
=cut |
1063 |
|
|
1064 |
|
sub label { |
1065 |
|
my $self = shift; |
1066 |
|
$self->set_info unless ($self->{label}); |
1067 |
|
return $self->{label}; |
1068 |
|
} |
1069 |
|
|
1070 |
|
|
1071 |
|
=head2 doc_num |
1072 |
|
|
1073 |
|
my $documents_in_node = $node->doc_num; |
1074 |
|
|
1075 |
|
=cut |
1076 |
|
|
1077 |
|
sub doc_num { |
1078 |
|
my $self = shift; |
1079 |
|
$self->set_info if ($self->{dnum} < 0); |
1080 |
|
return $self->{dnum}; |
1081 |
|
} |
1082 |
|
|
1083 |
|
|
1084 |
|
=head2 word_num |
1085 |
|
|
1086 |
|
my $words_in_node = $node->word_num; |
1087 |
|
|
1088 |
|
=cut |
1089 |
|
|
1090 |
|
sub word_num { |
1091 |
|
my $self = shift; |
1092 |
|
$self->set_info if ($self->{wnum} < 0); |
1093 |
|
return $self->{wnum}; |
1094 |
|
} |
1095 |
|
|
1096 |
|
|
1097 |
|
=head2 size |
1098 |
|
|
1099 |
|
my $node_size = $node->size; |
1100 |
|
|
1101 |
|
=cut |
1102 |
|
|
1103 |
|
sub size { |
1104 |
|
my $self = shift; |
1105 |
|
$self->set_info if ($self->{size} < 0); |
1106 |
|
return $self->{size}; |
1107 |
|
} |
1108 |
|
|
1109 |
|
|
1110 |
|
|
1111 |
=head2 shuttle_url |
=head2 shuttle_url |
1112 |
|
|
1113 |
This is method which uses C<IO::Socket::INET> to communicate with Hyper Estraier node |
This is method which uses C<IO::Socket::INET> to communicate with Hyper Estraier node |
1219 |
return $self->{status}; |
return $self->{status}; |
1220 |
} |
} |
1221 |
|
|
1222 |
|
|
1223 |
|
=head2 set_info |
1224 |
|
|
1225 |
|
Set information for node |
1226 |
|
|
1227 |
|
$node->set_info; |
1228 |
|
|
1229 |
|
=cut |
1230 |
|
|
1231 |
|
sub set_info { |
1232 |
|
my $self = shift; |
1233 |
|
|
1234 |
|
$self->{status} = -1; |
1235 |
|
return unless ($self->{url}); |
1236 |
|
|
1237 |
|
my $resbody; |
1238 |
|
my $rv = $self->shuttle_url( $self->{url} . '/inform', |
1239 |
|
'text/plain', |
1240 |
|
undef, |
1241 |
|
\$resbody, |
1242 |
|
); |
1243 |
|
|
1244 |
|
return if ($rv != 200 || !$resbody); |
1245 |
|
|
1246 |
|
chomp($resbody); |
1247 |
|
|
1248 |
|
( $self->{name}, $self->{label}, $self->{dnum}, $self->{wnum}, $self->{size} ) = |
1249 |
|
split(/\t/, $resbody, 5); |
1250 |
|
|
1251 |
|
} |
1252 |
|
|
1253 |
### |
### |
1254 |
|
|
1255 |
=head1 EXPORT |
=head1 EXPORT |