1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
|
package Plucene::Index::FieldsWriter;
=head1 NAME
Plucene::Index::FieldsWriter - writes Fields to a Document
=head1 SYNOPSIS
my $writer = Plucene::Index::FieldsWriter->new(
$dir_name, $segment, $field_infos);
$writer->add_document(Plucene::Document $doc);
=head1 DESCRIPTION
This class add documents to the appropriate files.
=head1 METHODS
=cut
use strict;
use warnings;
use Plucene::Store::OutputStream;
use Plucene::Index::FieldInfos;
=head2 new
my $writer = Plucene::Index::FieldsWriter->new(
$dir_name, $segment, $field_infos);
This will create a new Plucene::Index::FieldsWriter object with the passed
directory name, segment and field infos.
=cut
# private FieldInfos fieldInfos;
# private OutputStream fieldsStream;
# private OutputStream indexStream;
# FieldsWriter(Directory d, String segment, FieldInfos fn)
# throws IOException {
# fieldInfos = fn;
# fieldsStream = d.createFile(segment + ".fdt");
# indexStream = d.createFile(segment + ".fdx");
# }
sub new {
my ($self, $d, $segment, $fn) = @_;
bless {
field_infos => $fn,
segment => $segment,
fields_stream => Plucene::Store::OutputStream->new("$d/$segment.fdt"),
index_stream => Plucene::Store::OutputStream->new("$d/$segment.fdx"),
}, $self;
}
=head2 close
$writer->close;
=cut
# final void close() throws IOException {
# fieldsStream.close();
# indexStream.close();
# }
sub close {
my $self = shift;
$self->{fields_stream}->close;
$self->{index_stream}->close;
}
=head2 add_document
$writer->add_document(Plucene::Document $doc);
This will add the passed Plucene::Document.
=cut
# final void addDocument(Document doc) throws IOException {
# indexStream.writeLong(fieldsStream.getFilePointer());
#
# int storedCount = 0;
# Enumeration fields = doc.fields();
# while (fields.hasMoreElements()) {
# Field field = (Field)fields.nextElement();
# if (field.isStored())
# storedCount++;
# }
# fieldsStream.writeVInt(storedCount);
#
# fields = doc.fields();
# while (fields.hasMoreElements()) {
# Field field = (Field)fields.nextElement();
# if (field.isStored()) {
# fieldsStream.writeVInt(fieldInfos.fieldNumber(field.name()));
#
# byte bits = 0;
# if (field.isTokenized())
# bits |= 1;
# fieldsStream.writeByte(bits);
#
# fieldsStream.writeString(field.stringValue());
# }
# }
# }
sub add_document {
my ($self, $doc) = @_;
$self->{index_stream}->write_long($self->{fields_stream}->tell);
my @stored = grep $_->is_stored, $doc->fields;
$self->{fields_stream}->write_vint(scalar @stored);
for my $field (@stored) {
$self->{fields_stream}
->write_vint($self->{field_infos}->field_number($field->name));
$self->{fields_stream}->print(chr($field->is_tokenized));
$self->{fields_stream}->write_string($field->string);
}
}
1;
|
