Class: RubyTikaApp

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

Defined Under Namespace

Classes: CommandFailedError, Error

Constant Summary collapse

TIKA_APP_VERSION = 
'1.23'

Instance Method Summary collapse

Constructor Details

#initialize(document) ⇒ RubyTikaApp

Returns a new instance of RubyTikaApp.



21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
 
# File 'lib/ruby_tika_app.rb', line 21

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 = "#{ext_dir}/../ext/tika-app-#{TIKA_APP_VERSION}.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_html ⇒ Object 



41
42
43
 
# File 'lib/ruby_tika_app.rb', line 41

def to_html
  run_tika('--html')
end

#to_json(*_args) ⇒ Object 



45
46
47
 
# File 'lib/ruby_tika_app.rb', line 45

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

#to_metadata ⇒ Object 



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

def to_metadata
  run_tika('--metadata')
end

#to_text ⇒ Object 



49
50
51
 
# File 'lib/ruby_tika_app.rb', line 49

def to_text
  run_tika('--text')
end

#to_text_main ⇒ Object 



53
54
55
 
# File 'lib/ruby_tika_app.rb', line 53

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

#to_xml ⇒ Object 



37
38
39
 
# File 'lib/ruby_tika_app.rb', line 37

def to_xml
  run_tika('--xml')
end