Class: Ferret::Index::FieldsReader

Inherits:
Object
  • Object
show all
Includes:
Document
Defined in:
lib/ferret/index/fields_io.rb

Overview

Class responsible for access to stored document fields.

It uses <segment>.fdt and <segment>.fdx; files.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(d, segment, fi) ⇒ FieldsReader

Returns a new instance of FieldsReader.



15
16
17
18
19
20
21
22
 
# File 'lib/ferret/index/fields_io.rb', line 15

def initialize(d, segment, fi)
  @field_infos = fi

  @fields_stream = d.open_input(segment + ".fdt")
  @index_stream = d.open_input(segment + ".fdx")

  @size = (@index_stream.length() / 8).to_i
end

Instance Attribute Details

#size ⇒ Object (readonly) Also known as: length

Returns the value of attribute size.



12
13
14
 
# File 'lib/ferret/index/fields_io.rb', line 12

def size
  @size
end

Instance Method Details

#close ⇒ Object 



24
25
26
27
 
# File 'lib/ferret/index/fields_io.rb', line 24

def close()
  @fields_stream.close()
  @index_stream.close()
end

#doc(n) ⇒ Object 



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
 
# File 'lib/ferret/index/fields_io.rb', line 30

def doc(n)
  @index_stream.seek(n * 8)
  position = @index_stream.read_long()
  @fields_stream.seek(position)

  doc = Document.new
  @fields_stream.read_vint().times do
    field_number = @fields_stream.read_vint()
    fi = @field_infos[field_number]

    bits = @fields_stream.read_byte()
    
    compressed = (bits & FieldsWriter::FIELD_IS_COMPRESSED) != 0
    tokenize = (bits & FieldsWriter::FIELD_IS_TOKENIZED) != 0
    binary = (bits & FieldsWriter::FIELD_IS_BINARY) != 0
    
    if binary
      b = " " * @fields_stream.read_vint()
      @fields_stream.read_bytes(b, 0, b.length)
      if compressed
        doc << Field.new_binary_field(fi.name,
                                      uncompress(b),
                                      Field::Store::COMPRESS)
      else # No compression
        doc << Field.new_binary_field(fi.name, b, Field::Store::YES)
      end
    else 
      store = Field::Store::YES
      if fi.indexed? and tokenize
        index = Field::Index::TOKENIZED
      elsif fi.indexed? and not tokenize
        index = Field::Index::UNTOKENIZED
      else
        index = Field::Index::NO
      end
      data = nil
      if (compressed) 
        store = Field::Store::COMPRESS
        b = " " * @fields_stream.read_vint()
        @fields_stream.read_bytes(b, 0, b.length)
        data = uncompress(b)
      else
        data = @fields_stream.read_string()
      end
      stv =  Field::TermVector::NO
      if fi.store_term_vector? 
        if fi.store_positions? and fi.store_offsets?
          stv =  Field::TermVector::WITH_POSITIONS_OFFSETS 
        elsif fi.store_positions?
          stv =  Field::TermVector::WITH_POSITIONS
        elsif fi.store_offsets?
          stv =  Field::TermVector::WITH_OFFSETS 
        else
          stv =  Field::TermVector::YES 
        end
      end
      doc << Field.new(fi.name, data, store, index, stv)
    end
  end

  return doc
end

#uncompress(input) ⇒ Object 



93
94
95
96
97
98
99
 
# File 'lib/ferret/index/fields_io.rb', line 93

def uncompress(input)
  zstream = Zlib::Inflate.new
  buf = zstream.inflate(input)
  zstream.finish
  zstream.close
  buf
end