Class: DoverToCalais::Dover

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

Overview

This class is responsible for parsing, reading and sending to OpenCalais, text from a data source. The data source is passed to the class constructor and can be pretty much any form of document or URL. The class allows the user to specify one or more callbacks, to be called when the data source has been processed by OpenCalais (#to_calais).

Constant Summary collapse

CALAIS_SERVICE = 
'https://api.opencalais.com/tag/rs/enrich'

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(data_src) ⇒ Dover

creates a new Dover object, passing the name of the data source to be processed

Parameters:

  • data_src (String) —

    the name of the data source to be processed



173
174
175
176
 
# File 'lib/dover_to_calais.rb', line 173

def initialize(data_src)
  @data_src = data_src
  @callbacks = []
end

Instance Attribute Details

#data_src ⇒ String (readonly)

Returns the data source to be processed, either a file path or a URL.

Returns:

  • (String) —

    the data source to be processed, either a file path or a URL.



164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
 
# File 'lib/dover_to_calais.rb', line 164

class Dover

  CALAIS_SERVICE = 'https://api.opencalais.com/tag/rs/enrich'

  attr_reader :data_src, :error

  # creates a new Dover object, passing the name of the data source to be processed
  #
  # @param data_src [String] the name of the data source to be processed
  def initialize(data_src)
    @data_src = data_src
    @callbacks = []
  end


  # uses the {https://github.com/Erol/yomu yomu} gem to extract text from a number of document formats and URLs.
  # If an exception occurs, it is written to the {@error} instance variable
  #
  # @param [String] src the name of the data source (file-path or URI)
  # @return [String, nil] the extracted text, or nil if an exception occurred.
  def get_src_data(src)
    begin
      yomu = Yomu.new src

    rescue Exception=>e
      @error = "ERR: #{e}"
    else
      yomu.text
    end

  end

  # Defines the user callbacks. If the data source is successfully read, then this method will store a
  # user-defined block which will be called on completion of the OpenCalais HTTP request. If the data source
  # cannot be read -for whatever reason- then the block will immediately be called, passing the parameter that
  # caused the read failure.
  #
  # @param block a user-defined block
  # @return N/A
  def to_calais(&block)
    #fred rules ok
    if !@error
      @callbacks << block
    else
      result = ResponseData.new nil, @error
      block.call(result)
    end

  end #method

  # Gets the source text parsed. If the parsing is successful, the data source is POSTed to OpenCalais
  # via an EventMachine request and a callback is set to manage the OpenCalais response.
  # All Dover object callbacks are then called with the request result yielded to them. 
  #
  # @param N/A
  # @return a {Class ResponseData} object
  def analyse_this

    @document = get_src_data(@data_src)
    begin
      if @document[0..2].eql?('ERR')
        raise 'Invalid data source'
      else
        response = nil

        connection_options = {:inactivity_timeout => 0}


        if DoverToCalais::PROXY &&
            DoverToCalais::PROXY.class.eql?('Hash') &&
            DoverToCalais::PROXY.keys[0].eql?(:proxy)

          connection_options = connection_options.merge(DoverToCalais::PROXY)
        end

        request_options = {
            :body => @document.to_s,
            :head => {
                'x-calais-licenseID' => DoverToCalais::API_KEY,
                :content_type => 'TEXT/RAW',
                :enableMetadataType => 'GenericRelations,SocialTags',
                :outputFormat => 'Text/Simple'}
        }

        http = EventMachine::HttpRequest.new(CALAIS_SERVICE, connection_options ).post request_options


        http.callback do

          if http.response_header.status == 200
            http.response.match(/<OpenCalaisSimple>/) do |m|
              response = Nokogiri::XML('<OpenCalaisSimple>' + m.post_match)  do |config|
                #strict xml parsing, disallow network connections
                config.strict.nonet
              end #block
            end #block

            result =   response ?
                      ResponseData.new(response, nil) :
                      ResponseData.new(nil,'ERR: cannot find <OpenCalaisSimple> tag in response data - source invalid?')
          else #non-200 response header
            result = ResponseData.new nil, 
                          "ERR: OpenCalais service responded with #{http.response_header.status} - response body: '#{http.response}'"
          end 

          @callbacks.each { |c| c.call(result) }

        end  #callback


        http.errback do
          result = ResponseData.new nil, "ERR: #{http.error}"
          @callbacks.each { |c| c.call(result) }
        end  #errback


      end  #if
    rescue  Exception=>e
      #result = ResponseData.new nil,  "ERR: #{e}"
      #@callbacks.each { |c| c.call(result) }
      @error = "ERR: #{e}"
    end

  end  #method


  alias_method :analyze_this, :analyse_this
  public :to_calais, :analyse_this
  private :get_src_data


end

#error ⇒ String? (readonly)

Returns any error that occurred during data-source processing, nil if none occurred.

Returns:

  • (String, nil) —

    any error that occurred during data-source processing, nil if none occurred



164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
 
# File 'lib/dover_to_calais.rb', line 164

class Dover

  CALAIS_SERVICE = 'https://api.opencalais.com/tag/rs/enrich'

  attr_reader :data_src, :error

  # creates a new Dover object, passing the name of the data source to be processed
  #
  # @param data_src [String] the name of the data source to be processed
  def initialize(data_src)
    @data_src = data_src
    @callbacks = []
  end


  # uses the {https://github.com/Erol/yomu yomu} gem to extract text from a number of document formats and URLs.
  # If an exception occurs, it is written to the {@error} instance variable
  #
  # @param [String] src the name of the data source (file-path or URI)
  # @return [String, nil] the extracted text, or nil if an exception occurred.
  def get_src_data(src)
    begin
      yomu = Yomu.new src

    rescue Exception=>e
      @error = "ERR: #{e}"
    else
      yomu.text
    end

  end

  # Defines the user callbacks. If the data source is successfully read, then this method will store a
  # user-defined block which will be called on completion of the OpenCalais HTTP request. If the data source
  # cannot be read -for whatever reason- then the block will immediately be called, passing the parameter that
  # caused the read failure.
  #
  # @param block a user-defined block
  # @return N/A
  def to_calais(&block)
    #fred rules ok
    if !@error
      @callbacks << block
    else
      result = ResponseData.new nil, @error
      block.call(result)
    end

  end #method

  # Gets the source text parsed. If the parsing is successful, the data source is POSTed to OpenCalais
  # via an EventMachine request and a callback is set to manage the OpenCalais response.
  # All Dover object callbacks are then called with the request result yielded to them. 
  #
  # @param N/A
  # @return a {Class ResponseData} object
  def analyse_this

    @document = get_src_data(@data_src)
    begin
      if @document[0..2].eql?('ERR')
        raise 'Invalid data source'
      else
        response = nil

        connection_options = {:inactivity_timeout => 0}


        if DoverToCalais::PROXY &&
            DoverToCalais::PROXY.class.eql?('Hash') &&
            DoverToCalais::PROXY.keys[0].eql?(:proxy)

          connection_options = connection_options.merge(DoverToCalais::PROXY)
        end

        request_options = {
            :body => @document.to_s,
            :head => {
                'x-calais-licenseID' => DoverToCalais::API_KEY,
                :content_type => 'TEXT/RAW',
                :enableMetadataType => 'GenericRelations,SocialTags',
                :outputFormat => 'Text/Simple'}
        }

        http = EventMachine::HttpRequest.new(CALAIS_SERVICE, connection_options ).post request_options


        http.callback do

          if http.response_header.status == 200
            http.response.match(/<OpenCalaisSimple>/) do |m|
              response = Nokogiri::XML('<OpenCalaisSimple>' + m.post_match)  do |config|
                #strict xml parsing, disallow network connections
                config.strict.nonet
              end #block
            end #block

            result =   response ?
                      ResponseData.new(response, nil) :
                      ResponseData.new(nil,'ERR: cannot find <OpenCalaisSimple> tag in response data - source invalid?')
          else #non-200 response header
            result = ResponseData.new nil, 
                          "ERR: OpenCalais service responded with #{http.response_header.status} - response body: '#{http.response}'"
          end 

          @callbacks.each { |c| c.call(result) }

        end  #callback


        http.errback do
          result = ResponseData.new nil, "ERR: #{http.error}"
          @callbacks.each { |c| c.call(result) }
        end  #errback


      end  #if
    rescue  Exception=>e
      #result = ResponseData.new nil,  "ERR: #{e}"
      #@callbacks.each { |c| c.call(result) }
      @error = "ERR: #{e}"
    end

  end  #method


  alias_method :analyze_this, :analyse_this
  public :to_calais, :analyse_this
  private :get_src_data


end

Instance Method Details

#analyse_this ⇒ Object Also known as: analyze_this

Gets the source text parsed. If the parsing is successful, the data source is POSTed to OpenCalais via an EventMachine request and a callback is set to manage the OpenCalais response. All Dover object callbacks are then called with the request result yielded to them.

Parameters:

  • N/A 


220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
 
# File 'lib/dover_to_calais.rb', line 220

def analyse_this

  @document = get_src_data(@data_src)
  begin
    if @document[0..2].eql?('ERR')
      raise 'Invalid data source'
    else
      response = nil

      connection_options = {:inactivity_timeout => 0}


      if DoverToCalais::PROXY &&
          DoverToCalais::PROXY.class.eql?('Hash') &&
          DoverToCalais::PROXY.keys[0].eql?(:proxy)

        connection_options = connection_options.merge(DoverToCalais::PROXY)
      end

      request_options = {
          :body => @document.to_s,
          :head => {
              'x-calais-licenseID' => DoverToCalais::API_KEY,
              :content_type => 'TEXT/RAW',
              :enableMetadataType => 'GenericRelations,SocialTags',
              :outputFormat => 'Text/Simple'}
      }

      http = EventMachine::HttpRequest.new(CALAIS_SERVICE, connection_options ).post request_options


      http.callback do

        if http.response_header.status == 200
          http.response.match(/<OpenCalaisSimple>/) do |m|
            response = Nokogiri::XML('<OpenCalaisSimple>' + m.post_match)  do |config|
              #strict xml parsing, disallow network connections
              config.strict.nonet
            end #block
          end #block

          result =   response ?
                    ResponseData.new(response, nil) :
                    ResponseData.new(nil,'ERR: cannot find <OpenCalaisSimple> tag in response data - source invalid?')
        else #non-200 response header
          result = ResponseData.new nil, 
                        "ERR: OpenCalais service responded with #{http.response_header.status} - response body: '#{http.response}'"
        end 

        @callbacks.each { |c| c.call(result) }

      end  #callback


      http.errback do
        result = ResponseData.new nil, "ERR: #{http.error}"
        @callbacks.each { |c| c.call(result) }
      end  #errback


    end  #if
  rescue  Exception=>e
    #result = ResponseData.new nil,  "ERR: #{e}"
    #@callbacks.each { |c| c.call(result) }
    @error = "ERR: #{e}"
  end

end

#to_calais(&block) ⇒ Object

Defines the user callbacks. If the data source is successfully read, then this method will store a user-defined block which will be called on completion of the OpenCalais HTTP request. If the data source cannot be read -for whatever reason- then the block will immediately be called, passing the parameter that caused the read failure.

Parameters:

  • block —

    a user-defined block

Returns:

  • N/A



203
204
205
206
207
208
209
210
211
212
 
# File 'lib/dover_to_calais.rb', line 203

def to_calais(&block)
  #fred rules ok
  if !@error
    @callbacks << block
  else
    result = ResponseData.new nil, @error
    block.call(result)
  end

end