Class: Rika::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/rika.rb

Instance Method Summary collapse

Constructor Details

#initialize(file_location, max_content_length = -1,, detector = DefaultDetector.new) ⇒ Parser

Returns a new instance of Parser.



42
43
44
45
46
47
48
49
50
51
52
53
54
 
# File 'lib/rika.rb', line 42

def initialize(file_location, max_content_length = -1, detector = DefaultDetector.new)
  @uri = file_location
  $rika_tika = @tika = if $rika_tika.nil?
                          puts "creating a new Tika"
                          Tika.new(detector)
                       else
                          $rika_tika
                       end
  @tika.set_max_string_length(max_content_length)
  @metadata_java = Metadata.new
  @metadata_ruby = nil
  @input_type = get_input_type
end

Instance Method Details

#available_metadata ⇒ Object 



81
82
83
 
# File 'lib/rika.rb', line 81

def available_metadata
  metadata.keys
end

#content ⇒ Object 



56
57
58
59
 
# File 'lib/rika.rb', line 56

def content
  self.parse
  @content
end

#file? ⇒ Boolean

Returns:

  • (Boolean) 


89
90
91
 
# File 'lib/rika.rb', line 89

def file?
  @input_type == :file
end

#language ⇒ Object 



93
94
95
96
97
 
# File 'lib/rika.rb', line 93

def language
  @lang ||= LanguageIdentifier.new(content)

  @lang.language
end

#language_is_reasonably_certain? ⇒ Boolean

Returns:

  • (Boolean) 


99
100
101
102
103
 
# File 'lib/rika.rb', line 99

def language_is_reasonably_certain?
  @lang ||= LanguageIdentifier.new(content)

  @lang.is_reasonably_certain
end

#media_type ⇒ Object 



73
74
75
76
77
78
79
 
# File 'lib/rika.rb', line 73

def media_type
  if file?
    @media_type ||= @tika.detect(java.io.File.new(@uri))
  else
    @media_type ||= @tika.detect(input_stream)
  end
end

#metadata ⇒ Object 



61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/rika.rb', line 61

def metadata
  unless @metadata_ruby
    self.parse
    @metadata_ruby = {}

    @metadata_java.names.each do |name|
      @metadata_ruby[name] = @metadata_java.get(name)
    end
  end
  @metadata_ruby
end

#metadata_exists?(name) ⇒ Boolean

Returns:

  • (Boolean) 


85
86
87
 
# File 'lib/rika.rb', line 85

def metadata_exists?(name)
  metadata[name] != nil
end