fsp_harvester 0.1.21 → 0.1.22

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 8498c33db9c350fec8ea4e734b31087f798a4f433f211115c69ded468dbcdb12
4
- data.tar.gz: f3f408b24575f4f310c6f00ac0d42c3106f68fcd43199d3dbb73d8e4deb403fe
3
+ metadata.gz: dfe28e2fc429fd0c550539b356e325a1735d323e72fa9c4ee502fbedb1c818df
4
+ data.tar.gz: b1ec033372645ca2129f44c4faad380b690527ab2f0823583985b12328bdce54
5
5
  SHA512:
6
- metadata.gz: 263549dc8b8bf2fe8a4bc50289092ad2e55d9bbc05cabc509637786b4923948345220f0ee7a04fa5db497f670d9ab79d4e35e05648f09f189103ae869040baad
7
- data.tar.gz: 6b35a320400ff37561ddf2cff506a3a4f385cd31933e4df8ceb4d436a4f97974e7122ab96962b8ce3cfc183144fcf41592fa417abcdb609fd44080061fc5e1a3
6
+ metadata.gz: 11b5ce8b8368d70171e3e376ee75275e1c2892ec58be07976fa225a2df1841ae11b06c335105ab1915a001fb1f0e6247fadf00e3d06f33b21918593c3ada5fc0
7
+ data.tar.gz: b0c82ea9e81183789227a22eb3c160bfad5d4aa346f0aebb349b383f3d920877c28addb6f936a8a4f5b59d352bcecd313984f7ef7bb90aa4b5e93653e22fd176
data/.rspec_status CHANGED
@@ -1,60 +1,60 @@
1
1
  example_id | status | run_time |
2
2
  ---------------------------------- | ------ | ---------------------- |
3
- ./spec/cite-as_spec.rb[1:1:1] | passed | 1.77 seconds |
4
- ./spec/cite-as_spec.rb[1:1:2] | passed | 1.22 seconds |
5
- ./spec/cite-as_spec.rb[1:1:3] | passed | 1.09 seconds |
6
- ./spec/cite-as_spec.rb[1:1:4] | passed | 1.89 seconds |
7
- ./spec/cite-as_spec.rb[1:1:5] | passed | 2.95 seconds |
8
- ./spec/cite-as_spec.rb[1:1:6] | passed | 2.14 seconds |
9
- ./spec/cite-as_spec.rb[1:1:7] | passed | 2.96 seconds |
10
- ./spec/cite-as_spec.rb[1:1:8] | passed | 2.28 seconds |
11
- ./spec/cite-as_spec.rb[1:1:9] | passed | 3.4 seconds |
12
- ./spec/cite-as_spec.rb[1:1:10] | passed | 2.21 seconds |
13
- ./spec/cite-as_spec.rb[1:1:11] | passed | 2.82 seconds |
3
+ ./spec/cite-as_spec.rb[1:1:1] | passed | 1.87 seconds |
4
+ ./spec/cite-as_spec.rb[1:1:2] | passed | 1.3 seconds |
5
+ ./spec/cite-as_spec.rb[1:1:3] | passed | 1.53 seconds |
6
+ ./spec/cite-as_spec.rb[1:1:4] | passed | 2.09 seconds |
7
+ ./spec/cite-as_spec.rb[1:1:5] | passed | 8.09 seconds |
8
+ ./spec/cite-as_spec.rb[1:1:6] | passed | 2.63 seconds |
9
+ ./spec/cite-as_spec.rb[1:1:7] | passed | 2.9 seconds |
10
+ ./spec/cite-as_spec.rb[1:1:8] | passed | 2.21 seconds |
11
+ ./spec/cite-as_spec.rb[1:1:9] | passed | 2.85 seconds |
12
+ ./spec/cite-as_spec.rb[1:1:10] | passed | 2.89 seconds |
13
+ ./spec/cite-as_spec.rb[1:1:11] | passed | 3.16 seconds |
14
14
  ./spec/cite-as_spec.rb[1:1:12] | passed | 2.23 seconds |
15
- ./spec/cite-as_spec.rb[1:1:13] | passed | 3.36 seconds |
16
- ./spec/cite-as_spec.rb[1:1:14] | passed | 2.19 seconds |
17
- ./spec/cite-as_spec.rb[1:1:15] | passed | 1.19 seconds |
18
- ./spec/cite-as_spec.rb[1:1:16] | passed | 1.23 seconds |
15
+ ./spec/cite-as_spec.rb[1:1:13] | passed | 2.92 seconds |
16
+ ./spec/cite-as_spec.rb[1:1:14] | passed | 2.8 seconds |
17
+ ./spec/cite-as_spec.rb[1:1:15] | passed | 1.21 seconds |
18
+ ./spec/cite-as_spec.rb[1:1:16] | passed | 1.28 seconds |
19
19
  ./spec/cite-as_spec.rb[1:1:17] | passed | 1.19 seconds |
20
- ./spec/cite-as_spec.rb[1:1:18] | passed | 1.28 seconds |
21
- ./spec/cite-as_spec.rb[1:1:19] | passed | 1.94 seconds |
22
- ./spec/cite-as_spec.rb[1:1:20] | passed | 2.1 seconds |
23
- ./spec/cite-as_spec.rb[1:1:21] | passed | 2.23 seconds |
24
- ./spec/cite-as_spec.rb[1:1:22] | passed | 1.17 seconds |
25
- ./spec/cite-as_spec.rb[1:1:23] | passed | 1.13 seconds |
26
- ./spec/cite-as_spec.rb[1:1:24] | failed | 1.24 seconds |
27
- ./spec/cite-as_spec.rb[1:1:25] | passed | 0.49678 seconds |
28
- ./spec/describedby_spec.rb[1:1:1] | passed | 3.18 seconds |
29
- ./spec/describedby_spec.rb[1:1:2] | passed | 1.34 seconds |
30
- ./spec/describedby_spec.rb[1:1:3] | passed | 1.2 seconds |
31
- ./spec/describedby_spec.rb[1:1:4] | passed | 1.14 seconds |
20
+ ./spec/cite-as_spec.rb[1:1:18] | passed | 1.24 seconds |
21
+ ./spec/cite-as_spec.rb[1:1:19] | passed | 1.7 seconds |
22
+ ./spec/cite-as_spec.rb[1:1:20] | passed | 1.74 seconds |
23
+ ./spec/cite-as_spec.rb[1:1:21] | passed | 2.75 seconds |
24
+ ./spec/cite-as_spec.rb[1:1:22] | passed | 1.35 seconds |
25
+ ./spec/cite-as_spec.rb[1:1:23] | passed | 1.19 seconds |
26
+ ./spec/cite-as_spec.rb[1:1:24] | failed | 1.2 seconds |
27
+ ./spec/cite-as_spec.rb[1:1:25] | passed | 0.60282 seconds |
28
+ ./spec/describedby_spec.rb[1:1:1] | passed | 3.23 seconds |
29
+ ./spec/describedby_spec.rb[1:1:2] | passed | 1.43 seconds |
30
+ ./spec/describedby_spec.rb[1:1:3] | passed | 1.31 seconds |
31
+ ./spec/describedby_spec.rb[1:1:4] | passed | 1.37 seconds |
32
32
  ./spec/describedby_spec.rb[1:1:5] | passed | 1.24 seconds |
33
- ./spec/describedby_spec.rb[1:1:6] | passed | 1.04 seconds |
34
- ./spec/describedby_spec.rb[1:1:7] | passed | 0.9844 seconds |
35
- ./spec/describedby_spec.rb[1:1:8] | passed | 2.07 seconds |
36
- ./spec/describedby_spec.rb[1:1:9] | passed | 2.16 seconds |
37
- ./spec/describedby_spec.rb[1:1:10] | passed | 2.36 seconds |
38
- ./spec/describedby_spec.rb[1:1:11] | passed | 2.91 seconds |
39
- ./spec/describedby_spec.rb[1:1:12] | passed | 2.93 seconds |
40
- ./spec/describedby_spec.rb[1:1:13] | passed | 1.79 seconds |
41
- ./spec/describedby_spec.rb[1:1:14] | passed | 2.5 seconds |
42
- ./spec/describedby_spec.rb[1:1:15] | passed | 2.24 seconds |
43
- ./spec/fsp_harvester_spec.rb[1:1] | passed | 0.00102 seconds |
44
- ./spec/fsp_harvester_spec.rb[1:2] | passed | 2.5 seconds |
45
- ./spec/fsp_harvester_spec.rb[1:3] | passed | 29.49 seconds |
46
- ./spec/fsp_harvester_spec.rb[1:4] | passed | 2.53 seconds |
47
- ./spec/fsp_harvester_spec.rb[1:5] | passed | 2.65 seconds |
48
- ./spec/fsp_harvester_spec.rb[1:6] | failed | 1 minute 24.1 seconds |
49
- ./spec/fsp_harvester_spec.rb[1:7] | passed | 2 minutes 24.3 seconds |
50
- ./spec/item_spec.rb[1:1:1] | passed | 2.71 seconds |
51
- ./spec/item_spec.rb[1:1:2] | passed | 2.98 seconds |
33
+ ./spec/describedby_spec.rb[1:1:6] | passed | 1.09 seconds |
34
+ ./spec/describedby_spec.rb[1:1:7] | passed | 1.03 seconds |
35
+ ./spec/describedby_spec.rb[1:1:8] | passed | 2.28 seconds |
36
+ ./spec/describedby_spec.rb[1:1:9] | passed | 1.84 seconds |
37
+ ./spec/describedby_spec.rb[1:1:10] | passed | 2.23 seconds |
38
+ ./spec/describedby_spec.rb[1:1:11] | passed | 2.97 seconds |
39
+ ./spec/describedby_spec.rb[1:1:12] | passed | 2.97 seconds |
40
+ ./spec/describedby_spec.rb[1:1:13] | passed | 1.65 seconds |
41
+ ./spec/describedby_spec.rb[1:1:14] | passed | 2.27 seconds |
42
+ ./spec/describedby_spec.rb[1:1:15] | passed | 2.53 seconds |
43
+ ./spec/fsp_harvester_spec.rb[1:1] | passed | 0.00025 seconds |
44
+ ./spec/fsp_harvester_spec.rb[1:2] | passed | 2.69 seconds |
45
+ ./spec/fsp_harvester_spec.rb[1:3] | passed | 45.63 seconds |
46
+ ./spec/fsp_harvester_spec.rb[1:4] | passed | 2.86 seconds |
47
+ ./spec/fsp_harvester_spec.rb[1:5] | passed | 2.67 seconds |
48
+ ./spec/fsp_harvester_spec.rb[1:6] | passed | 2 minutes 1.6 seconds |
49
+ ./spec/fsp_harvester_spec.rb[1:7] | passed | 1 minute 28.63 seconds |
50
+ ./spec/item_spec.rb[1:1:1] | passed | 3.8 seconds |
51
+ ./spec/item_spec.rb[1:1:2] | passed | 3.3 seconds |
52
52
  ./spec/item_spec.rb[1:1:3] | passed | 1.33 seconds |
53
- ./spec/item_spec.rb[1:1:4] | passed | 1.81 seconds |
54
- ./spec/item_spec.rb[1:1:5] | passed | 2.2 seconds |
55
- ./spec/item_spec.rb[1:1:6] | passed | 2.25 seconds |
56
- ./spec/item_spec.rb[1:1:7] | passed | 2.94 seconds |
57
- ./spec/item_spec.rb[1:1:8] | passed | 0.62818 seconds |
58
- ./spec/type_spec.rb[1:1:1] | passed | 1.33 seconds |
59
- ./spec/type_spec.rb[1:1:2] | passed | 1.22 seconds |
60
- ./spec/type_spec.rb[1:1:3] | passed | 1.61 seconds |
53
+ ./spec/item_spec.rb[1:1:4] | passed | 1.68 seconds |
54
+ ./spec/item_spec.rb[1:1:5] | passed | 2.44 seconds |
55
+ ./spec/item_spec.rb[1:1:6] | passed | 2.64 seconds |
56
+ ./spec/item_spec.rb[1:1:7] | passed | 3.02 seconds |
57
+ ./spec/item_spec.rb[1:1:8] | passed | 0.49403 seconds |
58
+ ./spec/type_spec.rb[1:1:1] | passed | 1.23 seconds |
59
+ ./spec/type_spec.rb[1:1:2] | passed | 1.25 seconds |
60
+ ./spec/type_spec.rb[1:1:3] | passed | 1.57 seconds |
data/Gemfile.lock CHANGED
@@ -1,7 +1,7 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- fsp_harvester (0.1.21)
4
+ fsp_harvester (0.1.22)
5
5
  json (~> 2.0)
6
6
  linkeddata (~> 3.2)
7
7
  linkheaders-processor (~> 0.1.18)
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module FspHarvester
4
- VERSION = "0.1.21"
4
+ VERSION = "0.1.22"
5
5
  end
@@ -153,7 +153,7 @@ module HarvesterTools
153
153
  def self.check_ld(body:, claimed_type:)
154
154
  detected_type = ntriples_hack(body: body) # ntriples hack for one-line metadata records
155
155
  unless detected_type # see if distiller can detect a type
156
- detected_type = RDF::Format.for({ sample: body[0..5000] })
156
+ detected_type = RDF::Format.for({ sample: body[0..5000].force_encoding('UTF-8')})
157
157
  @meta.comments << "INFO: Auto-detected type #{detected_type}\n"
158
158
  end
159
159
  # at this point, detected_type is something like RDF::Turtle::Format (or nil). This will return a content-type
@@ -199,7 +199,7 @@ module HarvesterTools
199
199
  abbreviation = nil
200
200
  parsed = nil
201
201
  begin
202
- parsed = JSON.parse(body)
202
+ parsed = JSON.parse(body.force_encoding('UTF-8'))
203
203
  rescue StandardError
204
204
  abbreviation = nil
205
205
  end
@@ -88,7 +88,7 @@ module HarvesterTools
88
88
  @meta.comments << "INFO: The response message body component appears to contain #{rdfformat}.\n"
89
89
  reader = ''
90
90
  begin
91
- reader = rdfformat.reader.new(body)
91
+ reader = rdfformat.reader.new(body.force_encoding('UTF-8'))
92
92
  rescue Exception => e
93
93
  @meta.comments << "WARN: Though linked data was found, it failed to parse (Exception #{e}). This likely indicates some syntax error in the data. As a result, no metadata will be extracted from this message.\n"
94
94
  @meta.add_warning(['018', '', ''])
@@ -102,9 +102,9 @@ module HarvesterTools
102
102
  end
103
103
  reader = rdfformat.reader.new(body) # have to re-read it here, but now its safe because we have already caught errors
104
104
  warn 'WRITING TO CACHE'
105
- HarvesterTools::Cache.writeRDFCache(reader: reader, body: body) # write to the special RDF graph cache
105
+ HarvesterTools::Cache.writeRDFCache(reader: reader, body: body.force_encoding('UTF-8')) # write to the special RDF graph cache
106
106
  warn 'WRITING DONE'
107
- reader = rdfformat.reader.new(body) # frustrating that we cannot rewind!
107
+ reader = rdfformat.reader.new(body.force_encoding('UTF-8')) # frustrating that we cannot rewind!
108
108
  warn 'RE-READING DONE'
109
109
  @meta.merge_rdf(reader.to_a)
110
110
  warn 'MERGE DONE'
@@ -114,7 +114,7 @@ module HarvesterTools
114
114
  @meta.add_warning(['018', '', ''])
115
115
  rescue Exception => e
116
116
  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"
117
- warn "\n\nCRITICAL: #{e.inspect} An unknown error occurred while parsing the (apparent) Linked Data (full body: #{body}). Moving on...\n"
117
+ warn "\n\nCRITICAL: #{e.inspect} An unknown error occurred while parsing the (apparent) Linked Data (full body: #{body.force_encoding('UTF-8')}). Moving on...\n"
118
118
  @meta.add_warning(['018', '', ''])
119
119
  end
120
120
  end
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: 0.1.21
4
+ version: 0.1.22
5
5
  platform: ruby
6
6
  authors:
7
7
  - Mark Wilkinson
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2022-08-18 00:00:00.000000000 Z
11
+ date: 2022-08-19 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: json