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; |
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, |
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 |
|
|
885 |
sub edit_doc { |
sub edit_doc { |
886 |
my $self = shift; |
my $self = shift; |
887 |
my $doc = shift || return; |
my $doc = shift || return; |
888 |
return unless ($self->{url}); |
return unless ($self->{url} && $doc->isa('Search::Estraier::Document')); |
889 |
$self->shuttle_url( $self->{url} . '/edit_doc', |
$self->shuttle_url( $self->{url} . '/edit_doc', |
890 |
'text/x-estraier-draft', |
'text/x-estraier-draft', |
891 |
$doc->dump_draft, |
$doc->dump_draft, |
910 |
return $self->_fetch_doc( id => $id ); |
return $self->_fetch_doc( id => $id ); |
911 |
} |
} |
912 |
|
|
913 |
|
|
914 |
=head2 get_doc_by_uri |
=head2 get_doc_by_uri |
915 |
|
|
916 |
Retreive document |
Retreive document |
917 |
|
|
918 |
my $doc = $node->get_doc_by_uri( 'file:///document_uri' ) or die "can't get document"; |
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. |
Return true on success or false on failture. |
921 |
|
|
927 |
return $self->_fetch_doc( uri => $uri ); |
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 |
=head2 _fetch_doc |
978 |
|
|
979 |
Private function used for implementation of C<get_doc> and C<get_doc_by_uri>. |
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 |
my $doc = $node->fetch_doc( id => 42 ); |
# this will decode received draft into Search::Estraier::Document object |
983 |
my $doc = $node->fetch_doc( uri => 'file://uri/42' ); |
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 |
=cut |
999 |
|
|
1000 |
sub _fetch_doc { |
sub _fetch_doc { |
1001 |
my $self = shift; |
my $self = shift; |
1002 |
my ($name,$val) = @_; |
my $a = {@_}; |
1003 |
return unless ($name && defined($val) && $self->{url}); |
return unless ( ($a->{id} || $a->{uri}) && $self->{url} ); |
1004 |
if ($name eq 'id') { |
|
1005 |
croak "id must be numberm not '$val'" unless ($val =~ m/^\d+$/); |
my ($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 |
my $rv = $self->shuttle_url( $self->{url} . '/get_doc', |
|
1019 |
|
my $rv = $self->shuttle_url( $self->{url} . $path, |
1020 |
'application/x-www-form-urlencoded', |
'application/x-www-form-urlencoded', |
1021 |
"$name=$val", |
$arg, |
1022 |
my $draft, |
\$resbody, |
1023 |
); |
); |
1024 |
|
|
1025 |
return if ($rv != 200); |
return if ($rv != 200); |
1026 |
return new Search::Estraier::Document($draft); |
|
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 |
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 |