Class: RubyTikaApp

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

Defined Under Namespace

Classes: CommandFailedError, Error

Instance Method Summary collapse

Constructor Details

#initialize(document) ⇒ RubyTikaApp

Returns a new instance of RubyTikaApp.



18
19
20
21
22
23
24
25
26
27
28
29
30
# File 'lib/ruby_tika_app.rb', line 18

def initialize(document)
  if (document =~ /https?:\/\/[\S]+/) == 0
    @document = document
  else
    @document = "file://#{document}"
  end

  java_cmd = 'java'
  java_args = '-server -Djava.awt.headless=true'
  tika_path = "#{File.join(File.dirname(__FILE__))}/../ext/tika-app-1.9.jar"

  @tika_cmd = "#{java_cmd} #{java_args} -jar '#{tika_path}'"
end

Instance Method Details

#to_htmlObject



36
37
38
# File 'lib/ruby_tika_app.rb', line 36

def to_html
  run_tika('--html')
end

#to_jsonObject



40
41
42
# File 'lib/ruby_tika_app.rb', line 40

def to_json
  run_tika('--json')
end

#to_metadataObject



52
53
54
# File 'lib/ruby_tika_app.rb', line 52

def 
  run_tika('--metadata')
end

#to_textObject



44
45
46
# File 'lib/ruby_tika_app.rb', line 44

def to_text
  run_tika('--text')
end

#to_text_mainObject



48
49
50
# File 'lib/ruby_tika_app.rb', line 48

def to_text_main
  run_tika('--text-main')
end

#to_xmlObject



32
33
34
# File 'lib/ruby_tika_app.rb', line 32

def to_xml
  run_tika('--xml')
end