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.



19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
# File 'lib/ruby_tika_app.rb', line 19

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

  java_cmd = 'java'
  java_args = '-server -Djava.awt.headless=true -Dfile.encoding=UTF-8'
  ext_dir = File.join(File.dirname(__FILE__))
  tika_path = "/opt/tika-app.jar"
  tika_config_path = "#{ext_dir}/../ext/tika-config.xml"

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

Instance Method Details

#to_htmlObject



39
40
41
# File 'lib/ruby_tika_app.rb', line 39

def to_html
  run_tika('--html')
end

#to_json(*_args) ⇒ Object



43
44
45
# File 'lib/ruby_tika_app.rb', line 43

def to_json(*_args)
  run_tika('--json')
end

#to_metadataObject



55
56
57
# File 'lib/ruby_tika_app.rb', line 55

def 
  run_tika('--metadata')
end

#to_textObject



47
48
49
# File 'lib/ruby_tika_app.rb', line 47

def to_text
  run_tika('--text')
end

#to_text_mainObject



51
52
53
# File 'lib/ruby_tika_app.rb', line 51

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

#to_xmlObject



35
36
37
# File 'lib/ruby_tika_app.rb', line 35

def to_xml
  run_tika('--xml')
end