/usr/share/perl5/Plucene/Index/TermInfosReader.pm is in libplucene-perl 1.25-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | package Plucene::Index::TermInfosReader;
=head1 NAME
Plucene::Index::TermInfosReader - read the term infos file
=head1 SYNOPSIS
my $reader = Plucene::Index::TermInfosReader->new(
$dir_name, $segment, $fis);
my Plucene::Index::TermInfo $term_info =
$reader->get(Plucene::Index::Term $term);
my Plucene::Index::SegmentTermEnum $enum =
$reader->terms(Plucene::Index::Term $term);
=head1 DESCRIPTION
This reads a term infos file.
=head1 METHODS
=cut
use strict;
use warnings;
use Memoize;
use Carp qw/confess/;
use Plucene::Index::SegmentTermEnum;
use Plucene::Index::TermInfosWriter;
use Plucene::Store::InputStream;
=head2 new
my $reader = Plucene::Index::TermInfosReader->new(
$dir_name, $segment, $fis);
This will create a new Plucene::Index::TermInfosReader object with
the passed directory name, segment name and field infos.
=cut
sub new {
my ($class, $dir, $seg, $fis) = @_;
my $file = "$dir/$seg.tis";
confess("$file is already open!") unless -s $file;
my $self = bless {
directory => $dir,
segment => $seg,
field_infos => $fis,
enum => Plucene::Index::SegmentTermEnum->new(
Plucene::Store::InputStream->new($file),
$fis, 0
),
}, $class;
$self->{size} = $self->{enum}->size;
$self->_read_index;
return $self;
}
sub _read_index {
my $self = shift;
my $index_enum = Plucene::Index::SegmentTermEnum->new(
Plucene::Store::InputStream->new(
"$self->{directory}/$self->{segment}.tii"),
$self->{field_infos},
1
);
my $size = $index_enum->size;
$self->{index_terms} = [];
$self->{index_infos} = [];
$self->{index_pointers} = [];
for (my $i = 0 ; $index_enum->next ; $i++) {
$self->{index_terms}->[$i] = $index_enum->term;
# Need to clone here.
$self->{index_infos}->[$i] =
Plucene::Index::TermInfo->new({ %{ $index_enum->term_info } });
$self->{index_pointers}->[$i] = $index_enum->index_pointer;
}
}
memoize('_get_index_offset');
sub _get_index_offset {
my ($self, $term) = @_;
my $lo = 0;
my $hi = $#{ $self->{index_terms} };
while ($hi >= $lo) {
my $mid = ($lo + $hi) >> 1;
# Terms are comparable, hooray
my $delta = $term->_cmp($self->{index_terms}->[$mid]);
if ($delta < 0) { $hi = $mid - 1; }
elsif ($delta > 0) { $lo = $mid + 1; }
else { return $mid }
}
return $hi;
}
=head2 get
my Plucene::Index::TermInfo $term_info =
$reader->get(Plucene::Index::Term $term);
=cut
sub get {
my ($self, $term) = @_;
return unless $self->{size};
$self->_seek_enum($self->_get_index_offset($term));
return $self->_scan_enum($term);
}
sub _seek_enum {
my ($self, $offset) = @_;
$self->{enum}->seek(
$self->{index_pointers}->[$offset],
$offset * Plucene::Index::TermInfosWriter::INDEX_INTERVAL() - 1,
$self->{index_terms}->[$offset],
$self->{index_infos}->[$offset]);
}
sub _scan_enum {
my ($self, $term) = @_;
1 while $term->gt($self->{enum}->term) && $self->{enum}->next;
return $self->{enum}->term_info
if $self->{enum}->term
and $self->{enum}->term->eq($term);
return;
}
=head2 get_int / get_position
These are never called.
=cut
sub get_int { }
sub get_position { }
=head2 terms
my Plucene::Index::SegmentTermEnum $enum =
$reader->terms(Plucene::Index::Term $term);
This will return the Plucene::Index::SegmentTermEnum for the passed-in
Plucene::Index::Term.
=cut
sub terms {
my ($self, $term) = @_;
$term ? $self->get($term) : $self->_seek_enum(0);
$self->{enum}->clone;
}
1;
|