Class: FAIRChampionHarvester::Core

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

Constant Summary collapse

@@distillerknown =

global, hash of sha256 keys of message bodies - have they been seen before t/f

{}

Class Method Summary collapse

Class Method Details

.convertToURL(guid) ⇒ Object 



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
 
# File 'lib/harvester.rb', line 50

def self.convertToURL(guid)
  FAIRChampionHarvester::Utils::GUID_TYPES.each do |pair|
    k, regex = pair
    if k == "inchi" and regex.match(guid)
      return "inchi", "https://pubchem.ncbi.nlm.nih.gov/rest/rdf/inchikey/#{guid}"
    elsif k == "handle1" and regex.match(guid)
      return "handle", "http://hdl.handle.net/#{guid}"
    elsif k == "handle2" and regex.match(guid)
      return "handle", "http://hdl.handle.net/#{guid}"
    elsif k == "uri" and regex.match(guid)
      return "uri", guid
    elsif k == "doi" and regex.match(guid)
      return "doi", "https://doi.org/#{guid}"
    elsif k == "ark_url" and regex.match(guid)
      return "ark_url", guid
    elsif k == "ark" and regex.match(guid)
      return "ark", "https://n2t.net/#{guid}"
    end
  end
  [nil, nil]
end

.deep_dive_properties(myHash, property = nil, props = []) ⇒ Object 



327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
 
# File 'lib/harvester.rb', line 327

def self.deep_dive_properties(myHash, property = nil, props = [])
  return props unless myHash.is_a?(Hash)

  myHash.each_pair do |key, value|
    # The conditional is redundant — both branches are identical
    # This is very likely a bug or unfinished implementation.
    props << if property && property == key
               [key, value]
             else
               [key, value]
             end

    if value.is_a?(Hash)
      # $stderr.puts "key: #{key} recursing..."   # uncomment for debugging
      deep_dive_properties(value, property, props)
    end
  end

  props
end

.deep_dive_values(myHash, value = nil, vals = []) ⇒ Object 



314
315
316
317
318
319
320
321
322
323
324
325
 
# File 'lib/harvester.rb', line 314

def self.deep_dive_values(myHash, value = nil, vals = [])
  myHash.each_pair do |_key, value|
    if value.is_a?(Hash)
      # $stderr.puts "key: #{_key} recursing..."   # uncomment for debugging
      deep_dive_values(value, value, vals)
    else
      vals << value
    end
  end

  vals
end

.fetch(guid:, headers: FAIRChampionHarvester::Utils::AcceptHeader, meta: nil) ⇒ Object

we will try to retrieve turtle whenever possible



376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
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
 
# File 'lib/harvester.rb', line 376

def self.fetch(guid:, headers: FAIRChampionHarvester::Utils::AcceptHeader, meta: nil) # we will try to retrieve turtle whenever possible
  head, body, finalURI = FAIRChampionHarvester::Cache.checkCache(guid, headers)
  return false if head and head == "ERROR"

  meta.finalURI |= [finalURI] if meta && finalURI

  warn meta.finalURI.inspect if meta
  if head and body
    warn "Retrieved from cache, returning data to code"
    return [head, body]
  end

  warn "In fetch routine now.  "
  begin
    warn "executing call over the Web to #{guid}"
    # response = RestClient::Request.execute(
    #   method: :get,
    #   url: guid.to_s,
    #   # user: user,
    #   # password: pass,
    #   headers: headers
    # )
    response = HTTP
               .headers(headers).follow
               .get(guid.to_s) # or full URL

    if response.status.success?
      final_url = response.uri.to_s
      meta.finalURI |= [final_url] if meta
      warn "There was a response to the call #{guid}"
      FAIRChampionHarvester::Cache.writeToCache(guid, headers, response.headers, response.body.to_s,
                                                response.uri.to_s)
      [response.headers, response.body.to_s] # return headers, body, and final URL
    else
      # Handle HTTP error status codes (4xx, 5xx, etc.)
      warn "HTTP Error #{response.status} for #{guid}"
      warn "Final URL: #{response.uri}" if response.uri
      FAIRChampionHarvester::Cache.writeErrorToCache(guid, headers)
      meta.comments << "WARN: HTTP error #{response.status} encountered when trying to resolve #{guid}\n" if meta
      false
    end
  rescue HTTP::Error => e
    # This catches network errors, timeouts, connection failures, DNS errors, etc.
    warn "HTTP Request Failed for #{guid}: #{e.message}"
    FAIRChampionHarvester::Cache.writeErrorToCache(guid, headers)
    meta.comments << "WARN: HTTP error #{e.message} encountered when trying to resolve #{guid}\n" if meta
    false
  rescue StandardError => e
    # Catch any other unexpected errors
    warn "Unexpected error while fetching #{guid}: #{e.class} - #{e.message}"
    warn e.backtrace.first(10).join("\n")
    FAIRChampionHarvester::Cache.writeErrorToCache(guid, headers)
    meta.comments << "WARN: HTTP error #{e.message} encountered when trying to resolve #{guid}\n" if meta
    false
  end
  # rescue RestClient::ExceptionWithResponse => e
  #   warn "ERROR! #{e.response}"
  #   FAIRChampionHarvester::Cache.writeErrorToCache(guid, headers)
  #   meta.comments << "WARN: HTTP error #{e} encountered when trying to resolve #{guid}\n" if meta
  #   false
  #   # now we are returning 'False', and we will check that with an \"if\" statement in our main code
  # rescue RestClient::Exception => e
  #   warn "ERROR! #{e}"
  #   meta.comments << "WARN: HTTP error #{e} encountered when trying to resolve #{guid}\n" if meta
  #   FAIRChampionHarvester::Cache.writeErrorToCache(guid, headers)
  #   false
  #   # now we are returning 'False', and we will check that with an \"if\" statement in our main code
  # rescue Exception => e
  #   warn "ERROR! #{e}"
  #   meta.comments << "WARN: HTTP error #{e} encountered when trying to resolve #{guid}\n" if meta
  #   FAIRChampionHarvester::Cache.writeErrorToCache(guid, headers)
  #   false
  #   # now we are returning 'False', and we will check that with an \"if\" statement in our main code
  # end # you can capture the Exception and do something useful with it!\n",
end

.figure_out_type(head) ⇒ Object 



348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
 
# File 'lib/harvester.rb', line 348

def self.figure_out_type(head)
  type = head[:content_type]
  if type.nil?
    warn "\n\nSTRANGE - headers had no content-type\n\n"
    return nil, nil
  end
  type.match(%r{([\w+.]+/[\w+.]+):?;?}im)
  type = ::Regexp.last_match(1)
  # $stderr.puts "\n\nsearching for #{type}\n\n"

  FAIRChampionHarvester::Utils::RDF_FORMATS.each do |parser, types|
    return parser, type if types.include? type
  end
  FAIRChampionHarvester::Utils::JSON_FORMATS.each do |parser, types|
    return parser, type if types.include? type
  end
  FAIRChampionHarvester::Utils::TEXT_FORMATS.each do |parser, types|
    return parser, type if types.include? type
  end
  FAIRChampionHarvester::Utils::XML_FORMATS.each do |parser, types|
    return parser, type if types.include? type
  end
  FAIRChampionHarvester::Utils::HTML_FORMATS.each do |parser, types|
    return parser, type if types.include? type
  end
  [nil, nil]
end

.head(url, headers = FAIRChampionHarvester::Utils::AcceptHeader) ⇒ Object

this returns the URI that results from all redirects, etc.



483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
 
# File 'lib/harvester.rb', line 483

def self.head(url, headers = FAIRChampionHarvester::Utils::AcceptHeader)
  response = RestClient::Request.execute({
                                           method: :head,
                                           url: url.to_s,
                                           # user: user,
                                           # password: pass,
                                           headers: headers
                                         })
  response.headers
rescue RestClient::ExceptionWithResponse => e
  warn e.response
  false
# now we are returning 'False', and we will check that with an \"if\" statement in our main code
rescue RestClient::Exception => e
  warn e.response
  false
# now we are returning 'False', and we will check that with an \"if\" statement in our main code
rescue StandardError => e
  warn e
  false
  # now we are returning 'False', and we will check that with an \"if\" statement in our main code
  # you can capture the Exception and do something useful with it!\n",
end

.parse_html(meta, body) ⇒ Object 



104
105
106
 
# File 'lib/harvester.rb', line 104

def self.parse_html(meta, body)
  # just use extruct and distiller instead
end

.parse_json(meta, body) ⇒ Object 



93
94
95
96
97
98
99
100
101
102
 
# File 'lib/harvester.rb', line 93

def self.parse_json(meta, body)
  hash = JSON.parse(body)
  # warn body
  # warn hash.inspect
  # warn hash.class

  meta.hash.merge!(hash)
  #      warn meta.hash
  meta.hash
end

.parse_link_body_headers(url, body) ⇒ Object 



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
 
# File 'lib/harvester.rb', line 268

def self.parse_link_body_headers(url, body)
  # Parse the HTML body (Nokogiri is tolerant of malformed HTML)
  doc = Nokogiri::HTML(body)

  # Focus on <link> tags inside <head> (MetaInspector's head_links equivalent)
  # We use css selector for simplicity and readability
  link_nodes = doc.css('head link[rel="alternate"][type]') +
               doc.css('head link[rel="describedby"][type]')

  # Your format lists – assuming these are constants/hashes like:
  # FAIRChampionHarvester::Utils::RDF_FORMATS  => { jsonld: "application/ld+json", ... }
  # We flatten them once for efficiency
  allowed_types = [
    FAIRChampionHarvester::Utils::RDF_FORMATS.values,
    FAIRChampionHarvester::Utils::XML_FORMATS.values,
    FAIRChampionHarvester::Utils::JSON_FORMATS.values
  ].flatten.uniq # uniq to avoid duplicates if any overlap

  # Filter and extract hrefs
  urls = link_nodes.filter_map do |link|
    type = link["type"]&.strip
    next unless type && allowed_types.include?(type)

    href = link["href"]&.strip
    href if href && !href.empty?
  end

  # Optional: make relative URLs absolute (MetaInspector usually does this)
  base_uri = begin
    URI.parse(url)
  rescue StandardError
    nil
  end
  if base_uri
    urls.map! do |href|
      URI.join(base_uri, href).to_s
    rescue StandardError
      href
    end
  end

  warn "\n\nGOT BODY LINKS #{urls}\n\n"

  urls
end

.parse_link_http_headers(headers) ⇒ Object 



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
 
# File 'lib/harvester.rb', line 235

def self.parse_link_http_headers(headers)
  # we can be sure that a Link header is a URL
  # code stolen from https://gist.github.com/thesowah/0ca5e1b4b3c61bfe8e13 with a few tweaks

  links = headers[:link]
  return [] unless links

  parts = Array(links).flat_map { |l| l.split(",") }

  urls = []
  # Parse each part into a named link
  parts.each do |part, _index|
    section = part.split(";")
    next unless section[0]

    url = section[0][/<([^>]*)>/, 1]
    next unless url
    next unless section[1]

    type = nil
    section[1..].each do |s|
      type = s[/rel="?([\w-]+)"?/, 1]
      break if type
    end
    next unless type
    # "meta" headers are for old versions of Virtuoso LDP - not in link relations standared
    next unless %w[meta alternate describedby].include?(type.downcase)

    urls << url
  end
  urls
end

.parse_rdf(meta, body, format = nil) ⇒ Object 



108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
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
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
 
# File 'lib/harvester.rb', line 108

def self.parse_rdf(meta, body, format = nil)
  unless body
    meta.comments << "CRITICAL: The response message body component appears to have no content.\n"
    return meta
  end
  unless body.match(/\w/)
    meta.comments << "CRITICAL: The response message body component appears to have no content.\n"
    return meta
  end

  warn "\n\n\nSANITY CHECK \n\n#{body[0..300]}\n\n"
  # sanitycheck = RDF::Format.for({ sample: body[0..5000] })
  # unless sanitycheck
  #   meta.comments << "CRITICAL: The Evaluator found what it believed to be RDF (sample:  #{body[0..300].delete!("\n")}), but it could not find a parser.  Please report this error, along with the GUID of the resource, to the maintainer of the system.\n"
  #   return meta
  # end

  graph = FAIRChampionHarvester::Cache.checkRDFCache(body)
  if graph.size > 0
    warn "\n\n\n unmarshalling graph from cache\n\n"
    warn "\n\ngraph size #{graph.size} #{graph.inspect}\n\n"
    meta.merge_rdf(graph.to_a)
    return meta
  end

  formattype = nil
  warn "\n\n\ndeclared format #{format}\n\n"
  if format.nil?
    formattype = RDF::Format.for({ sample: body[0..3000] })
    warn "\n\n\ndetected format #{formattype}\n\n"
  else
    warn "\n\n\ntesting declared format #{format}\n\n"
    formattype = RDF::Format.for(content_type: format)
    warn "\n\n\nfound format #{formattype}\n\n"
  end
  warn "\n\n\nfinal format #{formattype}\n\n"
  # $stderr.puts "\n\n\nBODY #{body}\n\n"

  unless formattype
    meta.comments << "CRITICAL: Unable to find an RDF reader type that matches the content that was returned from resolution.  Here is a sample #{body[0..100]}  Please send your GUID to the dev team so we can investigate!\n"
    return meta
  end
  meta.comments << "INFO: The response message body component appears to contain #{formattype}.\n"
  if formattype.to_s.include?('JSON::LD')
    # JSON-LD: expand with remote context resolution to correctly apply @type: @id coercions
    # (e.g. schema.org "license" coerced to IRI resource instead of string literal)
    # json/ld/preloaded provides schema.org and other common contexts without network calls
    begin
      json_body = JSON.parse(body)
      context_hint = json_body.is_a?(Array) ? json_body.first&.[]('@context') : json_body['@context']
      warn "JSON-LD Expansion: Context is #{context_hint}"

      expanded = JSON::LD::API.expand(json_body, processingMode: 'json-ld-1.1')
      warn "JSON-LD Expansion: Output has #{expanded.length} objects"

      graph = RDF::Graph.new
      JSON::LD::API.toRdf(expanded) { |statement| graph << statement }

      if graph.size == 0
        meta.comments << "WARN: Though linked data was found, it failed to parse.  This likely indicates some syntax error in the data.  As a result, no metadata will be extracted from this message.\n"
        return meta
      end

      meta.comments << "INFO: JSON-LD context resolved and expanded successfully.\n"
      FAIRChampionHarvester::Cache.writeRDFCache(graph, body)
      meta.merge_rdf(graph.to_a)

    rescue JSON::LD::JsonLdError => e
      meta.comments << "WARN: JSON-LD context resolution failed: #{e.message}. Attempting parse without expansion.\n"
      warn "JSON-LD JsonLdError: #{e.message}"
      begin
        reader = formattype.reader.new(body)
        meta.merge_rdf(reader.to_a)
        meta.comments << "WARN: Parsed JSON-LD without context expansion. Results may be incomplete.\n"
      rescue => fallback_error
        meta.comments << "CRITICAL: JSON-LD parsing failed even without context expansion: #{fallback_error.message}\n"
        return meta
      end
    rescue StandardError => e
      meta.comments << "WARN: Though linked data was found, it failed to parse.  This likely indicates some syntax error in the data.  As a result, no metadata will be extracted from this message.\n"
      warn "JSON-LD StandardError: #{e.message}"
      return meta
    end
  else
    reader = ""
    begin
      reader = formattype.reader.new(body)
    rescue StandardError
      meta.comments << "WARN: Though linked data was found, it failed to parse.  This likely indicates some syntax error in the data.  As a result, no metadata will be extracted from this message.\n"
      return meta
    end

    begin
      # $stderr.puts "Reader Class #{reader.class}\n\n #{reader.inspect}"
      if reader.size == 0
        meta.comments << "WARN: Though linked data was found, it failed to parse.  This likely indicates some syntax error in the data.  As a result, no metadata will be extracted from this message.\n"
        return meta
      end
      #       reader.rewind!
      # for some reason, the rewind method isn't working here...??
      reader = formattype.reader.new(body) # have to re-read it here, but now its safe because we have already caught errors
      warn "WRITING TO CACHE"
      FAIRChampionHarvester::Cache.writeRDFCache(reader, body) # write to the special RDF graph cache
      warn "WRITING DONE"
      reader = formattype.reader.new(body)
      warn "RE-READING DONE"
      meta.merge_rdf(reader.to_a)
      warn "MERGE DONE"
    rescue RDF::ReaderError => e
      meta.comments << "CRITICAL: The Linked Data was malformed and caused the parser to crash with error message: #{e.message} ||  (sample of what was parsed:  #{body[0..300].delete("\n")})\n"
      warn "CRITICAL: The Linked Data was malformed and caused the parser to crash with error message: #{e.message} ||  (sample of what was parsed:  #{body[0..300].delete("\n")})\n"
      nil
    rescue Exception => e
      meta.comments << "CRITICAL: An unknown error occurred while parsing the (apparent) Linked Data (sample of what was parsed:  #{body[0..300].delete("\n")}).  Moving on...\n"
      warn "\n\nCRITICAL: #{e.inspect} An unknown error occurred while parsing the (apparent) Linked Data (full body:  #{body}).  Moving on...\n\n"
      nil
    end
  end
end

.parse_text(meta, body) ⇒ Object

================================================================== ================================================================== ================================================================== ================================================================== ==================================================================



86
87
88
89
90
91
 
# File 'lib/harvester.rb', line 86

def self.parse_text(meta, body)
  meta.comments << "WARTN: Plain Text cannot be mapped to any parser.  No structured metadata found.\n"
  meta.comments << "INFO: Using Apache Tika to attempt to extract metadata from plaintext.\n"

  FAIRChampionHarvester::Tika.do_tika(meta, body)
end

.parse_xml(meta, body) ⇒ Object 



228
229
230
231
232
233
 
# File 'lib/harvester.rb', line 228

def self.parse_xml(meta, body)
  hash = XmlSimple.xml_in(body)
  meta.comments << "INFO: The XML is being converted into a simple hash structure.\n"
  meta.hash.merge hash
  meta.hash
end

.resolve(url, headers = FAIRChampionHarvester::Utils::AcceptHeader) ⇒ Object

this returns the URI that results from all redirects, etc.



508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
 
# File 'lib/harvester.rb', line 508

def self.resolve(url, headers = FAIRChampionHarvester::Utils::AcceptHeader)
  response = RestClient::Request.execute({
                                           method: :head,
                                           url: url.to_s,
                                           # user: user,
                                           # password: pass,
                                           headers: headers
                                         })
  response.request.url
rescue RestClient::ExceptionWithResponse => e
  warn e.response
  false
# now we are returning 'False', and we will check that with an \"if\" statement in our main code
rescue RestClient::Exception => e
  warn e.response
  false
# now we are returning 'False', and we will check that with an \"if\" statement in our main code
rescue StandardError => e
  warn e
  false
  # now we are returning 'False', and we will check that with an \"if\" statement in our main code
  # you can capture the Exception and do something useful with it!\n",
end

.resolveit(guid) ⇒ Object 



19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
 
# File 'lib/harvester.rb', line 19

def self.resolveit(guid)
  # if meta = FAIRChampionHarvester::Utils::retrieveMetaObject(guid)
  #    return meta
  # end

  meta = FAIRChampionHarvester::MetadataObject.new

  FAIRChampionHarvester::Utils::GUID_TYPES.each do |pair| # meta object gets updated in each case
    k, regex = pair
    if k == "inchi" and regex.match(guid)
      FAIRChampionHarvester::INCHI.resolve_inchi(guid, meta)
    elsif k == "handle1" and regex.match(guid)
      FAIRChampionHarvester::Handle.resolve_handle(guid, meta)
    elsif k == "handle2" and regex.match(guid)
      FAIRChampionHarvester::Handle.resolve_handle(guid, meta)
    elsif k == "uri" and regex.match(guid)
      FAIRChampionHarvester::Uri.resolve_uri(guid, meta)
    elsif k == "doi" and regex.match(guid)
      FAIRChampionHarvester::DOI.resolve_doi(guid, meta)
    end
  end

  if meta.comments.empty? # didn't match any of the types, so no comments were added
    meta.guidtype = "unknown"
    meta.comments << "CRITICAL: The guid '#{guid}' did not correspond to any known GUID format. Tested #{FAIRChampionHarvester::Utils::GUID_TYPES.keys}. Halting.\n"
  end
  meta.comments << "INFO: END OF HARVESTING\n"
  # FAIRChampionHarvester::Utils::cacheMetaObject(meta, guid)
  meta
end

.simplefetch(url, headers = FAIRChampionHarvester::Utils::AcceptHeader, _meta = nil) ⇒ Object

we will try to retrieve turtle whenever possible



452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
 
# File 'lib/harvester.rb', line 452

def self.simplefetch(url, headers = FAIRChampionHarvester::Utils::AcceptHeader, _meta = nil) # we will try to retrieve turtle whenever possible
  # head = FAIRChampionHarvester::Utils::head(url, headers)
  # $stderr.puts "content length " + head[:content_length].to_s
  # if head[:content_length] and head[:content_length].to_f > 300000 and meta
  #    meta.comments << "WARN: The size of the content at #{url} reports itself to be >300kb.  This service will not download something so large.  This does not mean that the content is not FAIR, only that this service will not test it.  Sorry!\n"
  #    return false
  # end

  response = HTTP
             .headers(headers).follow
             .get(url.to_s) # or full URL

  if response.status.success?
    [response.headers, response.body.to_s] # return headers, body, and final URL
  else
    # Handle HTTP error status codes (4xx, 5xx, etc.)
    warn "HTTP Error #{response.status} for #{url}"
    warn "Final URL: #{response.uri}" if response.uri
    false
  end
rescue HTTP::Error => e
  # This catches network errors, timeouts, connection failures, DNS errors, etc.
  warn "HTTP Request Failed for #{url}: #{e.message}"
  false
rescue StandardError => e
  # Catch any other unexpected errors
  warn "Unexpected error while fetching #{url}: #{e.class} - #{e.message}"
  false
end

.typeit(guid) ⇒ Object 



72
73
74
75
76
77
78
 
# File 'lib/harvester.rb', line 72

def self.typeit(guid)
  FAIRChampionHarvester::Utils::GUID_TYPES.each do |pair|
    type, regex = pair
    return type if regex.match(guid)
  end
  false
end