Class: BentoSearch::EdsEngine

Inherits:
Object
  • Object
show all
Extended by:
HTTPClientPatch::IncludeClient
Includes:
SearchEngine
Defined in:
app/search_engines/bento_search/eds_engine.rb

Overview

EDS docs:

Defined Under Namespace

Modules: CitationMessDecorator Classes: EdsCommException

Constant Summary collapse

HttpTimeout =

Can’t change http timeout in config, because we keep an http client at class-wide level, and config is not class-wide. Change this ‘constant’ if you want to change it, I guess.

4
AuthHeader = 
"x-authenticationToken"
SessionTokenHeader = 
"x-sessionToken"
@@remembered_auth = 
nil
@@remembered_auth_lock = 
Mutex.new

Constants included from SearchEngine

SearchEngine::DefaultPerPage

Class Method Summary collapse

Instance Method Summary collapse

Methods included from HTTPClientPatch::IncludeClient

include_http_client

Methods included from SearchEngine

#fill_in_search_metadata_for, #initialize, #normalized_search_arguments, #public_settable_search_args, #search

Methods included from SearchEngine::Capabilities

#max_per_page, #search_keys, #semantic_search_keys, #semantic_search_map, #sort_keys

Class Method Details

.default_configuration ⇒ Object 



506
507
508
509
510
511
512
513
514
515
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 506

def self.default_configuration
  {
    :auth_url => 'https://eds-api.ebscohost.com/authservice/rest/uidauth',
    :base_url => "http://eds-api.ebscohost.com/edsapi/rest/",
    :highlighting => true,
    :truncate_highlighted => 280,
    :assume_first_custom_link_openurl => true,
    :search_mode => 'all' # any | bool | all | smart ; http://support.epnet.com/knowledge_base/detail.php?topic=996&id=1288&page=1
  }
end

.remembered_auth ⇒ Object

Class variable to save current known good auth uses a mutex to be threadsafe. sigh.



118
119
120
121
122
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 118

def self.remembered_auth
  @@remembered_auth_lock.synchronize do      
    @@remembered_auth
  end
end

.remembered_auth=(token) ⇒ Object

Set class variable with current known good auth. uses a mutex to be threadsafe.



125
126
127
128
129
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 125

def self.remembered_auth=(token)
  @@remembered_auth_lock.synchronize do
    @@remembered_auth = token
  end
end

.required_configuration ⇒ Object 



143
144
145
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 143

def self.required_configuration
  %w{user_id password profile}
end

Instance Method Details

#at_xpath_text(noko, xpath) ⇒ Object

if the xpath responds, return #text of it, else nil.



373
374
375
376
377
378
379
380
381
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 373

def at_xpath_text(noko, xpath)
  node = noko.at_xpath(xpath)
  
  if node.nil?
    return node
  else
    return node.text
  end
end

#authenticated_end_user?(args) ⇒ Boolean

From config or args, args over-ride config

Returns:

  • (Boolean) 


148
149
150
151
152
153
154
155
156
157
158
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 148

def authenticated_end_user?(args)    
  config = configuration.auth ? true : false
  arg = args[:auth]
  if ! arg.nil?
    arg ? true : false
  elsif ! config.nil?
    config ? true : false
  else
    false
  end
end

#construct_search_url(args) ⇒ Object 



160
161
162
163
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
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 160

def construct_search_url(args)
  query = "AND,"
  if args[:search_field]
    query += "#{args[:search_field]}:"
  end
  # Can't have any commas in query, it turns out, although
  # this is not documented. 
  query += args[:query].gsub(",", " ")
  
  url = "#{configuration.base_url}search?view=detailed&query=#{CGI.escape query}"
  
  url += "&searchmode=#{CGI.escape configuration.search_mode}"
  
  url += "&highlight=#{configuration.highlighting ? 'y' : 'n' }"
  
  if args[:per_page]
    url += "&resultsperpage=#{args[:per_page]}"
  end
  if args[:page]
    url += "&pagenumber=#{args[:page]}"
  end
  
  if args[:sort]
    if (defn = self.sort_definitions[args[:sort]]) &&
         (value = defn[:implementation] )
      url += "&sort=#{CGI.escape value}"
    end
  end
  
  if configuration.only_source_types.present?
    # facetfilter=1,SourceType:Research Starters,SourceType:Books
    url += "&facetfilter=" + CGI.escape("1," + configuration.only_source_types.collect {|t| "SourceType:#{t}"}.join(","))
  end
  
  
  return url
end

#element_by_group(noko, group) ⇒ Object

Difficult to get individual elements out of an EDS XML <Record> response, requires weird xpath, so we do it for you. element_by_group(nokogiri_element, “Ti”)

Returns string or nil



332
333
334
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 332

def element_by_group(noko, group)
  at_xpath_text(noko, "./Items/Item[child::Group[text()='#{group}']]/Data")
end

#get_auth_token ⇒ Object

Has to make an HTTP request to get EBSCO’s auth token. returns the auth token. We aren’t bothering to keep track of the expiration ourselves, can’t neccesarily trust it anyway.

Raises an EdsCommException on error.



474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 474

def get_auth_token    
  # Can't send params as form-encoded, actually need to send a JSON or XML
  # body, argh. 
  
  body = <<-EOS
    {
      "UserId":"#{configuration.user_id}",
      "Password":"#{configuration.password}"
    }
  EOS
  
  s_time = Time.now
  response = http_client.post(configuration.auth_url, body, {'Accept' => "application/json", "Content-type" => "application/json"})
  Rails.logger.debug("EDS timing AUTH: #{Time.now - s_time}s")    
  
  unless HTTP::Status.successful? response.status
    raise EdsCommException.new("Could not get auth", response.status, response.body)
  end
      
  response_hash = nil
  begin
    response_hash = MultiJson.load response.body
  rescue MultiJson::DecodeError
  end

  unless response_hash.kind_of?(Hash) && response_hash.has_key?("AuthToken")
    raise EdsCommException.new("AuthToken not found in auth response", response.status, response.body)
  end
  
  return response_hash["AuthToken"]        
end

#get_with_auth(url, session_token = nil) ⇒ Object

Give it a url pointing at EDS API. Second arg must be a session_token if EDS request requires one. It will

  • Make a GET request

  • with memo-ized auth token added to headers

  • for XML, with all namespaces removed!

  • Parse JSON into a hash and return hash

  • Try ONCE more to get if EBSCO says bad auth token

  • Raise an EdsCommException if can’t auth after second try, or other error message, or JSON can’t be parsed.



421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 421

def get_with_auth(url, session_token = nil)
  auth_token = self.class.remembered_auth
  unless auth_token
    auth_token = self.class.remembered_auth = get_auth_token
  end
  
  response = nil
  response_xml = nil
  caught_exception = nil
              
  begin
    headers = {AuthHeader => auth_token, 'Accept' => 'application/xml'}
    headers[SessionTokenHeader] = session_token if session_token
    
    s_time = Time.now
    response = http_client.get(url, nil, headers)
    Rails.logger.debug("EDS timing GET: #{Time.now - s_time}:#{url}")
    
    response_xml = Nokogiri::XML(response.body)
    response_xml.remove_namespaces!
    
    if (at_xpath_text(response_xml, "//ErrorNumber") == "104") || (at_xpath_text(response_xml, "//ErrorDescription") == "Auth Token Invalid")
      # bad auth, try again just ONCE
      Rails.logger.debug("EDS auth failed, getting auth again")
      
      headers[AuthHeader] = self.class.remembered_auth = get_auth_token
      response = http_client.get(url, nil, headers)
      response_xml = Nokogiri::XML(response.body)
      response_xml.remove_namespaces!        
    end            
  rescue TimeoutError, HTTPClient::ConfigurationError, HTTPClient::BadResponseError, Nokogiri::SyntaxError => e
    caught_exception = e
  end
  
  if response.nil? || response_xml.nil? || caught_exception ||  (! HTTP::Status.successful? response.status)
    exception = EdsCommException.new("Error fetching URL: #{caught_exception.message if caught_exception} : #{url}")
    if response
      exception.http_body = response.body
      exception.http_status = response.status
    end
    raise exception
  end
      
  return response_xml
end

#helper ⇒ Object

an object that includes some Rails helper modules for text handling.



133
134
135
136
137
138
139
140
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 133

def helper
  unless @helper
    @helper = Object.new
    @helper.extend ActionView::Helpers::TextHelper # for truncate
    @helper.extend ActionView::Helpers::OutputSafetyHelper # for safe_join
  end
  return @helper
end

#prepare_eds_payload(str, html_safe = false) ⇒ Object

If EDS has put highlighting tags in a field, we need to HTML escape the literal values, while still using the highlighting tokens to put HTML tags around highlighted terms.

Second param, if to assume EDS literals are safe HTML, as they seem to be.



390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 390

def prepare_eds_payload(str, html_safe = false)
  return str if str.blank?
  
  unless configuration.highlighting
    str = str.html_safe if html_safe  
    return str
  end
      
  parts = 
  str.split(%r{(</?highlight>)}).collect do |substr|
    case substr
    when "<highlight>" then "<b class='bento_search_highlight'>".html_safe
    when "</highlight>" then "</b>".html_safe
    # Yes, EDS gives us HTML in the literals, we're choosing to trust it. 
    else substr.html_safe
    end
  end
      
  return helper.safe_join(parts, '')        
end

#search_field_definitions ⇒ Object 



525
526
527
528
529
530
531
532
533
534
535
536
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 525

def search_field_definitions
  {
    "TX" => {:semantic => :general},
    "AU" => {:semantic => :author},
    "TI" => {:semantic => :title},
    "SU" => {:semantic => :subject},
    "SO" => {}, # source, journal name
    "AB" => {}, # abstract
    "IS" => {:semantic => :issn},
    "IB" => {:semantic => :isbn},
  }
end

#search_implementation(args) ⇒ Object 



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
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 200

def search_implementation(args)
  results = BentoSearch::Results.new
  
  end_user_auth = authenticated_end_user? args
  
  begin
    with_session(end_user_auth) do |session_token|
                      
      url = construct_search_url(args)
           
      
      
      response = get_with_auth(url, session_token)
      
      results = BentoSearch::Results.new
      
      if (hits_node = at_xpath_text(response, "./SearchResponseMessageGet/SearchResult/Statistics/TotalHits"))          
        results.total_items = hits_node.to_i
      end
      
      response.xpath("./SearchResponseMessageGet/SearchResult/Data/Records/Record").each do |record_xml|
        item = BentoSearch::ResultItem.new
        
        item.title   = prepare_eds_payload( element_by_group(record_xml, "Ti"), true )
        
        # To get a unique id, we need to pull out db code and accession number
        # and combine em with colon, accession number is not unique by itself. 
        db           = record_xml.at_xpath("./Header/DbId").try(:text)
        accession    = record_xml.at_xpath("./Header/An").try(:text)
        if db && accession
          item.unique_id    = "#{db}:#{accession}"
        end
        
        
        if item.title.nil? && ! end_user_auth
          item.title = I18n.translate("bento_search.eds.record_not_available")
        end
        
        item.abstract = prepare_eds_payload( element_by_group(record_xml, "Ab"), true )

        # Believe it or not, the authors are encoded as an escaped
        # XML-ish payload, that we need to parse again and get the
        # actual authors out of. WTF. Thanks for handling fragments
        # nokogiri. 
        author_mess = element_by_group(record_xml, "Au")
        # only SOMETIMES does it have XML tags, other times it's straight text.
        # ARGH.           
        author_xml = Nokogiri::XML::fragment(author_mess)
        searchLinks = author_xml.xpath(".//searchLink")
        if searchLinks.size > 0
          author_xml.xpath(".//searchLink").each do |author_node|
            item.authors << BentoSearch::Author.new(:display => author_node.text)
          end
        else
          item.authors << BentoSearch::Author.new(:display => author_xml.text)
        end
        
        
        # PLink is main inward facing EBSCO link, put it as
        # main link. 
        if direct_link = record_xml.at_xpath("./PLink")
            item.link = direct_link.text
        end
        
        # Other links may be found in CustomLinks, it seems like usually
        # there will be at least one, hopefully the first one is the OpenURL?
        record_xml.xpath("./CustomLinks/CustomLink").each do |custom_link|
          item.other_links << BentoSearch::Link.new(
            :url => custom_link.at_xpath("./Url").text,
            :label => custom_link.at_xpath("./Name").text
            )
        end
        
        if (configuration.assume_first_custom_link_openurl &&
          (first = record_xml.xpath "./CustomLinks/CustomLink" ) &&
          (node = first.at_xpath "./Url" )
        )
        
          openurl = node.text
          
          index = openurl.index('?')
          item.openurl_kev_co = openurl.slice index..(openurl.length) if index            
        end

        # Format. 
        item.format_str = at_xpath_text record_xml, "./Header/PubType"
        # Can't find a list of possible PubTypes to see what's there to try
        # and map to our internal controlled vocab. oh wells. 
        
        
        
        # We have a single blob of human-readable citation, that's also
        # littered with XML-ish tags we need to deal with. We'll save
        # it in a custom location, and use a custom Decorator to display
        # it. Sorry it's way too hard for us to preserve <highlight>
        # tags in this mess, they will be lost. Probably don't
        # need highlighting in source anyhow. 
        citation_mess = element_by_group(record_xml, "Src")
        # Argh, but sometimes it's in SrcInfo _without_ tags instead
        if citation_mess          
          citation_txt = Nokogiri::XML::fragment(citation_mess).text
          # But strip off some "count of references" often on the end
          # which are confusing and useless. 
          item.custom_data["citation_blob"] = citation_txt.gsub(/ref +\d+ +ref\.$/, '')
        else
          # try another location
          item.custom_data["citation_blob"] = element_by_group(record_xml, "SrcInfo")
        end
        
                            
        item.extend CitationMessDecorator
        
        results << item
      end        
    end
    
    return results      
  rescue EdsCommException => e
    results.error ||= {}
    results.error[:exception] = e
    results.error[:http_status] = e.http_status
    results.error[:http_body] = e.http_body
    return results
  end
  
end

#sort_definitions ⇒ Object 



517
518
519
520
521
522
523
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 517

def sort_definitions       
  {        
    "date_desc"     => {:implementation => "date"},
    "relevance"     => {:implementation => "relevance" }
    #       "date_asc"      => {:implementaiton => "date2"}
  }
end

#with_session(auth = false, &block) ⇒ Object

Wraps calls to the EDS api with CreateSession and EndSession requests to EDS. Will pass sessionID in yield from block.

Second optional arg is whether this is an authenticated user, else guest access will be used. 

with_session(true) do |session_token|
  # can make more requests using session_token,
  # EndSession will be called for you at end of block. 
end



346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
 
# File 'app/search_engines/bento_search/eds_engine.rb', line 346

def with_session(auth = false, &block)
  auth_token = self.class.remembered_auth    
  if auth_token.nil?
    auth_token = self.class.remembered_auth = get_auth_token
  end
  
          
  create_url = "#{configuration.base_url}createsession?profile=#{configuration.profile}&guest=#{auth ? 'n' : 'y'}"    
  response_xml = get_with_auth(create_url)    
  
  session_token = nil
  unless response_xml && (session_token = at_xpath_text(response_xml, "//SessionToken"))  
    e = EdsCommException.new("Could not get SessionToken")      
  end
              
  begin    
    block.yield(session_token)
  ensure      
    if auth_token && session_token   
      end_url = "#{configuration.base_url}endsession?sessiontoken=#{CGI.escape session_token}"
      response_xml = get_with_auth(end_url)        
    end
  end
  
end