Class: Henkei

Inherits:
Object
  • Object
show all
Defined in:
lib/henkei.rb,
lib/henkei/version.rb,
lib/henkei/configuration.rb

Overview

Henkei monkey patch for configuration support

Defined Under Namespace

Classes: Configuration

Constant Summary collapse

GEM_PATH =

rubocop:disable Metrics/ClassLength

File.dirname(File.dirname(__FILE__))
JAR_PATH = 
File.join(Henkei::GEM_PATH, 'jar', 'tika-app-2.9.1.jar')
CONFIG_PATH = 
File.join(Henkei::GEM_PATH, 'jar', 'tika-config.xml')
CONFIG_WITHOUT_OCR_PATH = 
File.join(Henkei::GEM_PATH, 'jar', 'tika-config-without-ocr.xml')
VERSION = 
'2.9.1.1'

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(input) ⇒ Henkei

Create a new instance of Henkei with a given document.

Using a file path:

Henkei.new 'sample.pages'

Using a URL:

Henkei.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'

From a stream or an object which responds to read

Henkei.new File.open('sample.pages')



74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
 
# File 'lib/henkei.rb', line 74

def initialize(input)
  if input.is_a? String
    if File.exist? input
      @path = input
    elsif input =~ URI::DEFAULT_PARSER.make_regexp
      @uri = URI.parse input
    else
      raise Errno::ENOENT, "missing file or invalid URI - #{input}"
    end
  elsif input.respond_to? :read
    @stream = input
  else
    raise TypeError, "can't read from #{input.class.name}"
  end
end

Class Method Details

.configuration ⇒ Object 



5
6
7
 
# File 'lib/henkei/configuration.rb', line 5

def self.configuration
  @configuration ||= Configuration.new
end

.configure {|configuration| ... } ⇒ Object

Yields:



9
10
11
 
# File 'lib/henkei/configuration.rb', line 9

def self.configure
  yield(configuration)
end

.mimetype(content_type) ⇒ Object 



32
33
34
35
36
37
38
39
40
41
42
 
# File 'lib/henkei.rb', line 32

def self.mimetype(content_type)
  if Henkei.configuration.mime_library == 'mime/types' && defined?(MIME::Types)
    warn '[DEPRECATION] `mime/types` is deprecated. Please use `mini_mime` instead. ' \
         'Use Henkei.configure and assign "mini_mime" to `mime_library`.'
    MIME::Types[content_type].first
  else
    MiniMime.lookup_by_content_type(content_type).tap do |object|
      object.define_singleton_method(:extensions) { [extension] }
    end
  end
end

.read(type, data, include_ocr: false) ⇒ Object

Read text or metadata from a data buffer.

data = File.read 'sample.pages'
text = Henkei.read :text, data
metadata = Henkei.read :metadata, data



50
51
52
53
54
55
56
57
58
 
# File 'lib/henkei.rb', line 50

def self.read(type, data, include_ocr: false)
  result = client_read(type, data, include_ocr: include_ocr)

  case type
  when :text, :html then result
  when :metadata then JSON.parse(result)
  when :mimetype then Henkei.mimetype(JSON.parse(result)['Content-Type'])
  end
end

Instance Method Details

#creation_date ⇒ Object

Returns true if the Henkei document was specified using a file path.

henkei = Henkei.new 'sample.pages'
henkei.path? #=> true



149
150
151
152
153
154
 
# File 'lib/henkei.rb', line 149

def creation_date
  return @creation_date if defined? @creation_date
  return unless metadata['dcterms:created']

  @creation_date = Time.parse(metadata['dcterms:created'])
end

#data ⇒ Object

Returns the raw/unparsed content of the Henkei document.

henkei = Henkei.new 'sample.pages'
henkei.data



189
190
191
192
193
194
195
196
197
198
199
200
201
 
# File 'lib/henkei.rb', line 189

def data
  return @data if defined? @data

  if path?
    @data = File.read @path
  elsif uri?
    @data = Net::HTTP.get @uri
  elsif stream?
    @data = @stream.read
  end

  @data
end

#html(include_ocr: false) ⇒ Object

Returns the text content of the Henkei document in HTML.

henkei = Henkei.new 'sample.pages'
henkei.html

Include OCR results from images (includes embedded images in pages/docx/pdf etc)

henkei.html(include_ocr: true)



114
115
116
117
118
 
# File 'lib/henkei.rb', line 114

def html(include_ocr: false)
  return @html if defined? @html

  @html = Henkei.read :html, data, include_ocr: include_ocr
end

#metadata ⇒ Object

Returns the metadata hash of the Henkei document.

henkei = Henkei.new 'sample.pages'
henkei.metadata['Content-Type']



125
126
127
128
129
 
# File 'lib/henkei.rb', line 125

def metadata
  return @metadata if defined? @metadata

  @metadata = Henkei.read :metadata, data
end

#mimetype ⇒ Object

Returns the mimetype object of the Henkei document.

henkei = Henkei.new 'sample.docx'
henkei.mimetype.content_type #=> 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
henkei.mimetype.extensions #=> ['docx']



137
138
139
140
141
142
 
# File 'lib/henkei.rb', line 137

def mimetype
  return @mimetype if defined? @mimetype

  content_type = metadata['Content-Type'].is_a?(Array) ? metadata['Content-Type'].first : metadata['Content-Type']
  @mimetype = Henkei.mimetype(content_type)
end

#path? ⇒ Boolean

Returns true if the Henkei document was specified using a file path.

henkei = Henkei.new '/my/document/path/sample.docx'
henkei.path? #=> true

Returns:

  • (Boolean) 


161
162
163
 
# File 'lib/henkei.rb', line 161

def path?
  !!@path
end

#stream? ⇒ Boolean

Returns true if the Henkei document was specified from a stream or an object which responds to read.

file = File.open('sample.pages')
henkei = Henkei.new file
henkei.stream? #=> true

Returns:

  • (Boolean) 


180
181
182
 
# File 'lib/henkei.rb', line 180

def stream?
  !!@stream
end

#text(include_ocr: false) ⇒ Object

Returns the text content of the Henkei document.

henkei = Henkei.new 'sample.pages'
henkei.text

Include OCR results from images (includes embedded images in pages/docx/pdf etc)

henkei.text(include_ocr: true)



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

def text(include_ocr: false)
  return @text if defined? @text

  @text = Henkei.read :text, data, include_ocr: include_ocr
end

#uri? ⇒ Boolean

Returns true if the Henkei document was specified using a URI.

henkei = Henkei.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
henkei.uri? #=> true

Returns:

  • (Boolean) 


170
171
172
 
# File 'lib/henkei.rb', line 170

def uri?
  !!@uri
end