fsp_harvester 0.1.11 → 0.1.14

Sign up to get free protection for your applications and to get access to all the features.
@@ -1,17 +1,17 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- module FspHarvester
3
+ module HarvesterTools
4
4
  class Error < StandardError
5
5
  end
6
6
 
7
7
  class MetadataHarvester
8
- def self.extract_metadata(links: [], metadata: FspHarvester::MetadataObject.new)
8
+ def self.extract_metadata_from_links(links: [], metadata: HarvesterTools::MetadataObject.new)
9
9
  @meta = metadata
10
10
  @meta.comments << 'INFO: now collecting both linked data and hash-style data using the harvested links'
11
11
 
12
12
  describedby = links.select { |l| l if l.relation == 'describedby' }
13
13
 
14
- hvst = FspHarvester::MetadataParser.new(metadata_object: @meta) # put here because the class variable for detecting duplicates should apply to all URIs
14
+ hvst = HarvesterTools::MetadataParser.new(metadata_object: @meta) # put here because the class variable for detecting duplicates should apply to all URIs
15
15
  describedby.each do |link|
16
16
  accepttype = ACCEPT_STAR_HEADER
17
17
  accept = link.respond_to?('type') ? link.type : nil
@@ -26,23 +26,42 @@ module FspHarvester
26
26
  next
27
27
  end
28
28
 
29
- # process according to detected type
30
- case abbreviation
31
- when 'html'
32
- @meta.comments << 'INFO: Processing html'
33
- hvst.process_html(body: response.body, uri: link)
34
- when 'xml'
35
- @meta.comments << 'INFO: Processing xml'
36
- hvst.process_xml(body: response.body)
37
- when 'json'
38
- @meta.comments << 'INFO: Processing json'
39
- hvst.process_json(body: response.body)
40
- when 'jsonld', 'rdfxml', 'turtle', 'ntriples', 'nquads'
41
- @meta.comments << 'INFO: Processing linked data'
42
- hvst.process_ld(body: response.body, content_type: content_type)
43
- when 'specialist'
44
- warn 'no specialized parsers so far'
45
- end
29
+ process_according_to_type(body: response.body, uri: link, metadata: @meta, abbreviation: abbreviation,
30
+ content_type: content_type, harvester: hvst)
31
+ end
32
+ end
33
+
34
+ def self.extract_metadata_from_body(response:, metadata: HarvesterTools::MetadataObject.new)
35
+ @meta = metadata
36
+ @meta.comments << 'INFO: now collecting both linked data and hash-style data using the harvested links'
37
+
38
+ abbreviation, content_type = attempt_to_detect_type(body: response.body, headers: response.headers)
39
+ unless abbreviation
40
+ @meta.add_warning(['017', response.request.url, ''])
41
+ @meta.comments << "WARN: metadata format returned from #{response.request.url} is not recognized. Moving on.\n"
42
+ return
43
+ end
44
+ process_according_to_type(body: response.body, uri: response.request.url, metadata: @meta,
45
+ abbreviation: abbreviation, content_type: content_type)
46
+ end
47
+
48
+ def self.process_according_to_type(body:, uri:, abbreviation:, content_type:, metadata:,
49
+ harvester: HarvesterTools::MetadataParser.new(metadata_object: @meta))
50
+ case abbreviation
51
+ when 'html'
52
+ @meta.comments << 'INFO: Processing html'
53
+ harvester.process_html(body: body, uri: uri, metadata: @meta)
54
+ when 'xml'
55
+ @meta.comments << 'INFO: Processing xml'
56
+ harvester.process_xml(body: body, metadata: @meta)
57
+ when 'json'
58
+ @meta.comments << 'INFO: Processing json'
59
+ harvester.process_json(body: body, metadata: @meta)
60
+ when 'jsonld', 'rdfxml', 'turtle', 'ntriples', 'nquads'
61
+ @meta.comments << 'INFO: Processing linked data'
62
+ harvester.process_ld(body: body, content_type: content_type, metadata: @meta)
63
+ when 'specialist'
64
+ warn 'no specialized parsers so far'
46
65
  end
47
66
  end
48
67
 
@@ -54,7 +73,7 @@ module FspHarvester
54
73
  @meta.comments << "INFO: link #{link.href} has no MIME type, defaulting to */*"
55
74
  end
56
75
  url = link.href
57
- response = FspHarvester::WebUtils.fspfetch(url: url, method: :get, headers: header)
76
+ response = HarvesterTools::WebUtils.fspfetch(url: url, method: :get, headers: header)
58
77
  unless response
59
78
  @meta.add_warning(['016', url, header])
60
79
  @meta.comments << "WARN: Unable to resolve describedby link #{url} using HTTP Accept header #{header}.\n"
@@ -111,24 +130,23 @@ module FspHarvester
111
130
  [abbreviation, contenttype]
112
131
  end
113
132
 
114
- def self.ntriples_hack(body:) # distriller cannot recognize single-line ntriples unless they end with a period, which is not required by the spec... so hack it!
133
+ def self.ntriples_hack(body:) # distriller cannot recognize single-line ntriples unless they end with a period, which is not required by the spec... so hack it!
115
134
  detected_type = nil
116
135
  body.split.each do |line|
117
136
  line.strip!
118
137
  next if line.empty?
119
- if line =~ %r{\s*<[^>]+>\s*<[^>]+>\s\S+}
120
- @meta.comments << "INFO: running ntriples hack on #{line + " ."}\n"
121
- detected_type = RDF::Format.for({ sample: "#{line} ." }) # adding a period allows detection of ntriples by distiller
122
- break
123
- end
124
- end
125
- @meta.comments << "INFO: ntriples hack found: #{detected_type.to_s}\n"
126
- if detected_type != RDF::NTriples::Format # only return the hacky case
127
- return nil
138
+
139
+ next unless line =~ /\s*<[^>]+>\s*<[^>]+>\s\S+/
140
+
141
+ @meta.comments << "INFO: running ntriples hack on #{line + ' .'}\n"
142
+ detected_type = RDF::Format.for({ sample: "#{line} ." }) # adding a period allows detection of ntriples by distiller
143
+ break
128
144
  end
129
- return detected_type
130
- end
145
+ @meta.comments << "INFO: ntriples hack found: #{detected_type}\n"
146
+ return nil if detected_type != RDF::NTriples::Format # only return the hacky case
131
147
 
148
+ detected_type
149
+ end
132
150
 
133
151
  def self.check_json(body:)
134
152
  abbreviation = nil
@@ -1,4 +1,4 @@
1
- module FspHarvester
1
+ module HarvesterTools
2
2
  class MetadataObject
3
3
  attr_accessor :hash, :graph, :comments, :links, :warnings, :guidtype, :full_response, :all_uris # a hash of metadata # a RDF.rb graph of metadata # an array of comments # the type of GUID that was detected # will be an array of Net::HTTP::Response
4
4
 
@@ -1,6 +1,6 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- module FspHarvester
3
+ module HarvesterTools
4
4
  class Error < StandardError
5
5
  end
6
6
 
@@ -9,17 +9,25 @@ module FspHarvester
9
9
 
10
10
  @@distillerknown = {}
11
11
 
12
- def initialize(metadata_object: FspHarvester::MetadataObject.new)
12
+ def initialize(metadata_object: HarvesterTools::MetadataObject.new)
13
13
  @meta = metadata_object
14
14
  end
15
15
 
16
- def process_html(body:, uri:)
17
- tools = FspHarvester::ExternalTools.new(metadata: @meta)
18
- tools.process_with_distiller(body: body)
19
- tools.process_with_extruct(uri: uri)
16
+ def process_html(body:, uri:, metadata:)
17
+ @meta = metadata
18
+ tools = HarvesterTools::ExternalTools.new(metadata: @meta)
19
+ result = tools.process_with_distiller(body: body)
20
+
21
+ jsonld, microdata, microformat, opengraph, rdfa = tools.process_with_extruct(uri: uri)
22
+ parse_rdf(body: jsonld, content_type: 'application/ld+json')
23
+ @meta.merge_hash(microdata)
24
+ @meta.merge_hash(microformat)
25
+ @meta.merge_hash(opengraph)
26
+ parse_rdf(body: rdfa, content_type: 'application/ld+json')
20
27
  end
21
28
 
22
- def process_xml(body:)
29
+ def process_xml(body:, metadata:)
30
+ @meta = metadata
23
31
  begin
24
32
  hash = XmlSimple.xml_in(body)
25
33
  rescue
@@ -30,7 +38,8 @@ module FspHarvester
30
38
  @meta.hash.merge hash
31
39
  end
32
40
 
33
- def process_json(body:)
41
+ def process_json(body:, metadata:)
42
+ @meta = metadata
34
43
  begin
35
44
  hash = JSON.parse(body)
36
45
  rescue
@@ -41,11 +50,17 @@ module FspHarvester
41
50
  @meta.hash.merge hash
42
51
  end
43
52
 
44
- def process_ld(body:, content_type:)
45
- parse_rdf(body: body, content_type: content_type)
53
+ def process_ld(body:, content_type:, metadata:)
54
+ @meta = metadata
55
+ parse_rdf(body: body, content_type: content_type, metadata: @meta)
56
+ end
57
+
58
+ def parse_rdf(body:, content_type:, metadata:)
59
+ self.class.parse_rdf(body: body, content_type: content_type, metadata: metadata)
46
60
  end
47
61
 
48
- def parse_rdf(body:, content_type:)
62
+ def self.parse_rdf(body:, content_type:, metadata:)
63
+ @meta = metadata
49
64
  unless body
50
65
  @meta.comments << "CRITICAL: The response message body component appears to have no content.\n"
51
66
  @meta.add_warning(['018', '', ''])
@@ -65,7 +80,7 @@ module FspHarvester
65
80
  return
66
81
  end
67
82
 
68
- graph = FspHarvester::Cache.checkRDFCache(body: body)
83
+ graph = HarvesterTools::Cache.checkRDFCache(body: body)
69
84
  if graph.size > 0
70
85
  warn "\n\n\n unmarshalling graph from cache\n\ngraph size #{graph.size}\n\n"
71
86
  @meta.merge_rdf(graph.to_a)
@@ -88,7 +103,7 @@ module FspHarvester
88
103
  end
89
104
  reader = rdfformat.reader.new(body) # have to re-read it here, but now its safe because we have already caught errors
90
105
  warn 'WRITING TO CACHE'
91
- FspHarvester::Cache.writeRDFCache(reader: reader, body: body) # write to the special RDF graph cache
106
+ HarvesterTools::Cache.writeRDFCache(reader: reader, body: body) # write to the special RDF graph cache
92
107
  warn 'WRITING DONE'
93
108
  reader = rdfformat.reader.new(body) # frustrating that we cannot rewind!
94
109
  warn 'RE-READING DONE'
@@ -1,4 +1,5 @@
1
- def check_for_citeas_conflicts(citeas: )
1
+ def check_for_citeas_conflicts(citeas:, metadata: )
2
+ @meta = metadata
2
3
  @meta.comments << 'INFO: checking for conflicting cite-as links'
3
4
  citeas_hrefs = Hash.new
4
5
  citeas.each do |link|
@@ -6,7 +7,7 @@ def check_for_citeas_conflicts(citeas: )
6
7
  @meta.comments << "INFO: Adding citeas #{link.href} to the testing queue."
7
8
  citeas_hrefs[link.href] = link
8
9
  end
9
-
10
+ #warn "finalhash #{citeas_hrefs}"
10
11
  if citeas_hrefs.length > 1
11
12
  @meta.comments << 'INFO: Found multiple non-identical cite-as links.'
12
13
  @meta.add_warning(['007', '', ''])
@@ -16,7 +17,8 @@ def check_for_citeas_conflicts(citeas: )
16
17
  end
17
18
 
18
19
 
19
- def check_describedby_rules(describedby:)
20
+ def check_describedby_rules(describedby:, metadata:)
21
+ @meta = metadata
20
22
  describedby.each do |l|
21
23
  unless l.respond_to? 'type'
22
24
  @meta.add_warning(['005', l.href, ''])
@@ -25,7 +27,7 @@ def check_describedby_rules(describedby:)
25
27
  type = l.type if l.respond_to? 'type'
26
28
  type ||= '*/*'
27
29
  header = { accept: type }
28
- response = FspHarvester::WebUtils.fspfetch(url: l.href, headers: header, method: :head)
30
+ response = HarvesterTools::WebUtils.fspfetch(url: l.href, headers: header, method: :head)
29
31
  if response
30
32
  responsetype = response.headers[:content_type]
31
33
  @meta.comments << "INFO: describedby link responds with content type #{responsetype}\n"
@@ -51,7 +53,8 @@ def check_describedby_rules(describedby:)
51
53
  end
52
54
  end
53
55
 
54
- def check_item_rules(item:)
56
+ def check_item_rules(item:, metadata:)
57
+ @meta = metadata
55
58
  item.each do |l| # l = LinkHeaders::Link
56
59
  unless l.respond_to? 'type'
57
60
  @meta.add_warning(['011', l.href, ''])
@@ -60,7 +63,7 @@ def check_item_rules(item:)
60
63
  type = l.type if l.respond_to? 'type'
61
64
  type ||= '*/*' # this becomes a frozen string
62
65
  header = { accept: type }
63
- response = FspHarvester::WebUtils.fspfetch(url: l.href, headers: header, method: :head)
66
+ response = HarvesterTools::WebUtils.fspfetch(url: l.href, headers: header, method: :head)
64
67
 
65
68
  if response
66
69
  if response.headers[:content_type] and type != '*/*'
data/lib/warnings.json CHANGED
@@ -1,107 +1,119 @@
1
1
  {
2
2
  "001": {
3
3
  "message": "Unable to resolve guid using default (*/*) Accept headers",
4
- "linkout": "",
4
+ "linkout": [{"FAIR Principle": "https://www.go-fair.org/fair-principles/metadata-retrievable-identifier-standardised-communication-protocol/"},
5
+ {"FAIRsharing": "https://doi.org/10.25504/FAIRsharing.cd2f9e"}
6
+ ],
5
7
  "severity": "WARN"
6
8
  },
7
9
  "002": {
8
10
  "message": "HTTP Response (203) is non-authoritative",
9
- "linkout": "",
11
+ "linkout": [{"Documentation": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/203"}],
10
12
  "severity": "WARN"
11
13
  },
12
14
  "003": {
13
15
  "message": "HTTP Response indicates failure (500-range)",
14
- "linkout": "",
16
+ "linkout": [{"Documentation": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500"}],
15
17
  "severity": "WARN"
16
18
  },
17
19
  "004": {
18
20
  "message": "The resource does not follow the FAIR Signposting standard, which requires exactly one cite-as header, and at least one describedby header",
19
- "linkout": "",
21
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
20
22
  "severity": "WARN"
21
23
  },
22
24
  "005": {
23
25
  "message": "The resource does not follow the FAIR Signposting standard, which requires any describedby links to also have a 'type' attribute indicating the Accept headers that should be sent with the request",
24
- "linkout": "",
26
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
25
27
  "severity": "WARN"
26
28
  },
27
29
  "006": {
28
30
  "message": "GUID type not recognized",
29
- "linkout": "",
31
+ "linkout": [{"FAIRsharing": "https://fairsharing.org/search?fairsharingRegistry=Standard&recordType=identifier_schema&page=1"}],
30
32
  "severity": "WARN"
31
33
  },
32
34
  "007": {
33
35
  "message": "Conflicting cite-as links",
34
- "linkout": "",
36
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
35
37
  "severity": "WARN"
36
38
  },
37
39
  "008": {
38
40
  "message": "describedby link does not resolve",
39
- "linkout": "",
41
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
40
42
  "severity": "WARN"
41
43
  },
42
44
  "009": {
43
45
  "message": "Content-type of described-by link does not match the type attribute in the link header itself",
44
- "linkout": "",
46
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"},
47
+ {"Documentation": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Type"}],
45
48
  "severity": "WARN"
46
49
  },
47
50
  "010": {
48
51
  "message": "Content-type of response from described-by link is undefined or cannot be compared to the link type",
49
- "linkout": "",
52
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
50
53
  "severity": "WARN"
51
54
  },
52
55
  "011": {
53
56
  "message": "The resource does not follow the FAIR Signposting standard, which encourages any item links to have a type attribute",
54
- "linkout": "",
57
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
55
58
  "severity": "WARN"
56
59
  },
57
60
  "012": {
58
61
  "message": "Content-type of response from resolving an item doesn't match the item type attribute in the link header",
59
- "linkout": "",
62
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"},
63
+ {"Documentation": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Type"}],
60
64
  "severity": "WARN"
61
65
  },
62
66
  "013": {
63
67
  "message": "Content-type of response from resolving an item is undefined or cannot be compared to the link type",
64
- "linkout": "",
68
+ "linkout": [{"Documentation": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Type"}],
65
69
  "severity": "WARN"
66
70
  },
67
71
  "014": {
68
72
  "message": "Item link does not resolve",
69
- "linkout": "",
73
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
70
74
  "severity": "WARN"
71
75
  },
72
76
  "015": {
73
77
  "message": "Link headers do not include a link of type 'type', as required by the FAIR Signposting specification",
74
- "linkout": "",
78
+ "linkout": [{"Documentation": "http://www.signposting.org/FAIR/#level1"}],
75
79
  "severity": "WARN"
76
80
  },
77
81
  "016": {
78
82
  "message": "Unable to resolve describedby link using Accept headers with the MIME type indicated in the link",
79
- "linkout": "",
83
+ "linkout": [{"Documentation": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Content_negotiation"}],
80
84
  "severity": "WARN"
81
85
  },
82
86
  "017": {
83
87
  "message": "Metadata format not recognized.",
84
- "linkout": "",
88
+ "linkout": [{"FAIRsharing": "https://fairsharing.org/search?subjects=Computer%2520Science,subject%2520agnostic&page=1&recordType=model_and_format"}],
85
89
  "severity": "WARN"
86
90
  },
87
91
  "018": {
88
92
  "message": "RDF parsing error - likely malformed RDF document.",
89
- "linkout": "",
93
+ "linkout": [{"FAIRsharing": "https://fairsharing.org/FAIRsharing.p77ph9"},
94
+ {"Documentation": "http://www.w3.org/TR/2014/REC-rdf11-concepts-20140225/"},
95
+ {"Validator": "http://rdf.greggkellogg.net/distiller"}],
90
96
  "severity": "WARN"
91
97
  },
92
98
  "019": {
93
99
  "message": "HTML parsing error - unable to extract linked data from HTML.",
94
- "linkout": "",
100
+ "linkout": [{"FAIRsharing": "https://fairsharing.org/FAIRsharing.YugnuL"},
101
+ {"Documentation": "https://www.w3.org/TR/html53/"},
102
+ {"validator": "https://validator.w3.org/"}],
95
103
  "severity": "WARN"
96
104
  },
97
105
  "020": {
98
106
  "message": "XML parsing error - unable to process XML document.",
99
- "linkout": "",
107
+ "linkout": [{"FAIRsharing": "https://fairsharing.org/FAIRsharing.b5cc91"},
108
+ {"Documentation": "https://www.w3.org/TR/xml/"},
109
+ {"Validator": "https://www.xmlvalidation.com/"}],
100
110
  "severity": "WARN"
101
111
  },
102
112
  "021": {
103
113
  "message": "JSON parsing error - unable to process JSON document.",
104
- "linkout": "",
114
+ "linkout": [{"FAIRsharing": "https://fairsharing.org/FAIRsharing.5bbab9"},
115
+ {"Documentation": "http://dx.doi.org/10.17487/RFC8259"},
116
+ {"Validator": "https://jsononline.net/json-validator"}],
105
117
  "severity": "WARN"
106
118
  }
107
119
  }
data/lib/web_utils.rb CHANGED
@@ -1,7 +1,7 @@
1
- module FspHarvester
1
+ module HarvesterTools
2
2
 
3
3
  class WebUtils
4
- def self.fspfetch(url:, headers: ACCEPT_ALL_HEADER, method: :get, meta: FspHarvester::MetadataObject.new)
4
+ def self.fspfetch(url:, headers: ACCEPT_ALL_HEADER, method: :get, meta: HarvesterTools::MetadataObject.new)
5
5
  warn 'In fetch routine now. '
6
6
 
7
7
  begin
@@ -18,13 +18,13 @@ module FspHarvester
18
18
  warn "final URL #{response.request.url}"
19
19
  warn "Response code #{response.code}"
20
20
  if response.code == 203
21
- meta.warnings << ["002", url, headers]
21
+ meta.add_warning(["002", url, headers])
22
22
  meta.comments << "WARN: Response is non-authoritative (HTTP response code: #{response.code}). Headers may have been manipulated encountered when trying to resolve #{url}\n"
23
23
  end
24
24
  response
25
25
  rescue RestClient::ExceptionWithResponse => e
26
- warn "EXCEPTION WITH RESPONSE! #{e.response}\n#{e.response.headers}"
27
- meta.warnings << ["003", url, headers]
26
+ warn "EXCEPTION WITH RESPONSE! #{e.response.code} with response #{e.response}\nfailed response headers: #{e.response.headers}"
27
+ meta.add_warning(["003", url, headers])
28
28
  meta.comments << "WARN: HTTP error #{e} encountered when trying to resolve #{url}\n"
29
29
  if (e.response.code == 500 or e.response.code == 404)
30
30
  return false
@@ -34,13 +34,13 @@ module FspHarvester
34
34
  # now we are returning the headers and body that were returned
35
35
  rescue RestClient::Exception => e
36
36
  warn "EXCEPTION WITH NO RESPONSE! #{e}"
37
- meta.warnings << ["003", url, headers]
37
+ meta.add_warning(["003", url, headers])
38
38
  meta.comments << "WARN: HTTP error #{e} encountered when trying to resolve #{url}\n"
39
39
  false
40
40
  # now we are returning 'False', and we will check that with an \"if\" statement in our main code
41
41
  rescue Exception => e
42
42
  warn "EXCEPTION UNKNOWN! #{e}"
43
- meta.warnings << ["003", url, headers]
43
+ meta.add_warning(["003", url, headers])
44
44
  meta.comments << "WARN: HTTP error #{e} encountered when trying to resolve #{url}\n"
45
45
  false
46
46
  # now we are returning 'False', and we will check that with an \"if\" statement in our main code
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: fsp_harvester
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.11
4
+ version: 0.1.14
5
5
  platform: ruby
6
6
  authors:
7
7
  - Mark Wilkinson
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2022-08-08 00:00:00.000000000 Z
11
+ date: 2022-08-12 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: json
@@ -44,14 +44,14 @@ dependencies:
44
44
  requirements:
45
45
  - - "~>"
46
46
  - !ruby/object:Gem::Version
47
- version: 0.1.16
47
+ version: 0.1.17
48
48
  type: :runtime
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
52
  - - "~>"
53
53
  - !ruby/object:Gem::Version
54
- version: 0.1.16
54
+ version: 0.1.17
55
55
  - !ruby/object:Gem::Dependency
56
56
  name: metainspector
57
57
  requirement: !ruby/object:Gem::Requirement
@@ -182,17 +182,19 @@ files:
182
182
  - bin/setup
183
183
  - example_test.rb
184
184
  - launch.json
185
+ - lib/config.conf
185
186
  - lib/config.conf_docker
186
187
  - lib/config.conf_local
187
188
  - lib/constants.rb
189
+ - lib/external_tools.rb
188
190
  - lib/fsp_harvester.rb
189
191
  - lib/fsp_harvester/version.rb
190
- - lib/fsp_metadata_external_tools.rb
191
- - lib/fsp_metadata_harvester.rb
192
- - lib/fsp_metadata_parser.rb
192
+ - lib/harvester.rb
193
+ - lib/harvester_utils.rb
194
+ - lib/metadata_harvester.rb
193
195
  - lib/metadata_object.rb
196
+ - lib/metadata_parser.rb
194
197
  - lib/signposting_tests.rb
195
- - lib/swagger.rb
196
198
  - lib/warnings.json
197
199
  - lib/web_utils.rb
198
200
  homepage: https://github.com/markwilkinson/FAIR-Signposting-Harvester