fsp_harvester 0.1.25 → 0.1.27

Sign up to get free protection for your applications and to get access to all the features.
Files changed (12) hide show
  1. checksums.yaml +4 -4
  2. data/.rspec_status +60 -60
  3. data/.vscode/launch.json +21 -0
  4. data/Gemfile.lock +168 -162
  5. data/lib/fsp_harvester/version.rb +1 -1
  6. data/lib/fsp_harvester.rb +1 -0
  7. data/lib/harvester.rb +2 -0
  8. data/lib/metadata_harvester.rb +5 -0
  9. data/lib/metadata_parser.rb +5 -1
  10. data/tryme.rb +9 -0
  11. metadata +35 -6
  12. data/launch.json +0 -11
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 99d8004e7780475df62b9fdc440d2563434aa927fa7630a6b8ae286df1e27de0
4
- data.tar.gz: c4ae1b36eceb9170bc41ff649c7d0427af537c48b6430544c03534b27ab73c1a
3
+ metadata.gz: 6a12db5f7c5c6ade0a6009a073db5c499453ca68d19fc7ea436f8bde29fafded
4
+ data.tar.gz: ca57a628a60a64bab692a2fcbd020f18fdc18604f272530435d66d4ecd5be9ba
5
5
  SHA512:
6
- metadata.gz: 26e46c3b840d204a9089351b4f03782c02cc14a4615b248e8a8da43ff3e9b13944586358a056fdf2d4054c7531489fd68acadce9578809da61f80df679d34049
7
- data.tar.gz: 7d0b7975d4d2a4ddf734b4fb6253ce389258a51918b1bd5b133f7714080f27aaa0d449a4fa1286eb7d096f7c4e7deec728c6704a68c26101c8c5fc1d31e8b69e
6
+ metadata.gz: 2f07c82fd470041116a98723ac5b8bf151552951f3caa07f00c720b58ff768d1daae57641664ec0b93cdf2205d66e99cfeb5d05371342c626ed5d7d7796944f4
7
+ data.tar.gz: 0253eac41a6b38f427accfb68239c3e6274ac9dd661a220e466164f49a40ac6de2b3afd37d263d2478faba20406cc6f296a30efca72c69c26c0f4a5a507d7444
data/.rspec_status CHANGED
@@ -1,60 +1,60 @@
1
- example_id | status | run_time |
2
- ---------------------------------- | ------ | --------------------- |
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
- ./spec/cite-as_spec.rb[1:1:12] | passed | 2.23 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
- ./spec/cite-as_spec.rb[1:1:17] | passed | 1.19 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
- ./spec/describedby_spec.rb[1:1:5] | passed | 1.24 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 | 0.00178 seconds |
44
- ./spec/fsp_harvester_spec.rb[1:2] | passed | 5.49 seconds |
45
- ./spec/fsp_harvester_spec.rb[1:3] | passed | 39.87 seconds |
46
- ./spec/fsp_harvester_spec.rb[1:4] | passed | 2.62 seconds |
47
- ./spec/fsp_harvester_spec.rb[1:5] | passed | 2.61 seconds |
48
- ./spec/fsp_harvester_spec.rb[1:6] | failed | 54.05 seconds |
49
- ./spec/fsp_harvester_spec.rb[1:7] | passed | 1 minute 26.9 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
- ./spec/item_spec.rb[1:1:3] | passed | 1.33 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 |
1
+ example_id | status | run_time |
2
+ ---------------------------------- | ------ | --------------- |
3
+ ./spec/cite-as_spec.rb[1:1:1] | passed | 0.92505 seconds |
4
+ ./spec/cite-as_spec.rb[1:1:2] | passed | 0.91715 seconds |
5
+ ./spec/cite-as_spec.rb[1:1:3] | passed | 0.59784 seconds |
6
+ ./spec/cite-as_spec.rb[1:1:4] | passed | 1.09 seconds |
7
+ ./spec/cite-as_spec.rb[1:1:5] | passed | 2.43 seconds |
8
+ ./spec/cite-as_spec.rb[1:1:6] | passed | 1.49 seconds |
9
+ ./spec/cite-as_spec.rb[1:1:7] | passed | 2.5 seconds |
10
+ ./spec/cite-as_spec.rb[1:1:8] | passed | 1.43 seconds |
11
+ ./spec/cite-as_spec.rb[1:1:9] | passed | 3.36 seconds |
12
+ ./spec/cite-as_spec.rb[1:1:10] | passed | 1.19 seconds |
13
+ ./spec/cite-as_spec.rb[1:1:11] | passed | 3.03 seconds |
14
+ ./spec/cite-as_spec.rb[1:1:12] | passed | 1.21 seconds |
15
+ ./spec/cite-as_spec.rb[1:1:13] | passed | 2.4 seconds |
16
+ ./spec/cite-as_spec.rb[1:1:14] | passed | 1.27 seconds |
17
+ ./spec/cite-as_spec.rb[1:1:15] | passed | 0.91669 seconds |
18
+ ./spec/cite-as_spec.rb[1:1:16] | passed | 0.8317 seconds |
19
+ ./spec/cite-as_spec.rb[1:1:17] | passed | 0.95717 seconds |
20
+ ./spec/cite-as_spec.rb[1:1:18] | passed | 0.86864 seconds |
21
+ ./spec/cite-as_spec.rb[1:1:19] | passed | 2.17 seconds |
22
+ ./spec/cite-as_spec.rb[1:1:20] | passed | 1.24 seconds |
23
+ ./spec/cite-as_spec.rb[1:1:21] | passed | 1.79 seconds |
24
+ ./spec/cite-as_spec.rb[1:1:22] | passed | 0.89065 seconds |
25
+ ./spec/cite-as_spec.rb[1:1:23] | passed | 0.81873 seconds |
26
+ ./spec/cite-as_spec.rb[1:1:24] | passed | 0.97719 seconds |
27
+ ./spec/cite-as_spec.rb[1:1:25] | passed | 0.25903 seconds |
28
+ ./spec/describedby_spec.rb[1:1:1] | passed | 1.66 seconds |
29
+ ./spec/describedby_spec.rb[1:1:2] | passed | 0.92657 seconds |
30
+ ./spec/describedby_spec.rb[1:1:3] | passed | 0.92638 seconds |
31
+ ./spec/describedby_spec.rb[1:1:4] | passed | 0.83822 seconds |
32
+ ./spec/describedby_spec.rb[1:1:5] | passed | 0.83941 seconds |
33
+ ./spec/describedby_spec.rb[1:1:6] | passed | 0.55956 seconds |
34
+ ./spec/describedby_spec.rb[1:1:7] | passed | 0.60106 seconds |
35
+ ./spec/describedby_spec.rb[1:1:8] | passed | 1.76 seconds |
36
+ ./spec/describedby_spec.rb[1:1:9] | passed | 1.14 seconds |
37
+ ./spec/describedby_spec.rb[1:1:10] | passed | 1.35 seconds |
38
+ ./spec/describedby_spec.rb[1:1:11] | passed | 2.01 seconds |
39
+ ./spec/describedby_spec.rb[1:1:12] | passed | 1.9 seconds |
40
+ ./spec/describedby_spec.rb[1:1:13] | passed | 1.16 seconds |
41
+ ./spec/describedby_spec.rb[1:1:14] | passed | 1.62 seconds |
42
+ ./spec/describedby_spec.rb[1:1:15] | passed | 1.39 seconds |
43
+ ./spec/fsp_harvester_spec.rb[1:1] | passed | 0.0001 seconds |
44
+ ./spec/fsp_harvester_spec.rb[1:2] | passed | 1.46 seconds |
45
+ ./spec/fsp_harvester_spec.rb[1:3] | passed | 20.9 seconds |
46
+ ./spec/fsp_harvester_spec.rb[1:4] | passed | 2.11 seconds |
47
+ ./spec/fsp_harvester_spec.rb[1:5] | passed | 2.16 seconds |
48
+ ./spec/fsp_harvester_spec.rb[1:6] | passed | 23.24 seconds |
49
+ ./spec/fsp_harvester_spec.rb[1:7] | passed | 20.85 seconds |
50
+ ./spec/item_spec.rb[1:1:1] | passed | 1.72 seconds |
51
+ ./spec/item_spec.rb[1:1:2] | passed | 1.61 seconds |
52
+ ./spec/item_spec.rb[1:1:3] | passed | 0.89622 seconds |
53
+ ./spec/item_spec.rb[1:1:4] | passed | 1.18 seconds |
54
+ ./spec/item_spec.rb[1:1:5] | passed | 1.32 seconds |
55
+ ./spec/item_spec.rb[1:1:6] | passed | 1.24 seconds |
56
+ ./spec/item_spec.rb[1:1:7] | passed | 1.82 seconds |
57
+ ./spec/item_spec.rb[1:1:8] | passed | 0.27709 seconds |
58
+ ./spec/type_spec.rb[1:1:1] | passed | 0.80665 seconds |
59
+ ./spec/type_spec.rb[1:1:2] | passed | 0.84617 seconds |
60
+ ./spec/type_spec.rb[1:1:3] | passed | 0.82173 seconds |
data/.vscode/launch.json ADDED
@@ -0,0 +1,21 @@
1
+ {
2
+ // Use IntelliSense to learn about possible attributes.
3
+ // Hover to view descriptions of existing attributes.
4
+ // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
5
+ "version": "0.2.0",
6
+ "configurations": [
7
+ {
8
+ "type": "rdbg",
9
+ "name": "Debug current file with rdbg",
10
+ "request": "launch",
11
+ "script": "${file}",
12
+ "args": [],
13
+ "askParameters": true
14
+ },
15
+ {
16
+ "type": "rdbg",
17
+ "name": "Attach with rdbg",
18
+ "request": "attach"
19
+ }
20
+ ]
21
+ }
data/Gemfile.lock CHANGED
@@ -1,13 +1,15 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- fsp_harvester (0.1.23)
4
+ fsp_harvester (0.1.27)
5
5
  json (~> 2.0)
6
6
  linkeddata (~> 3.2)
7
- linkheaders-processor (~> 0.1.18)
7
+ linkheaders-processor (~> 0.1.19)
8
8
  metainspector (~> 5.11.2)
9
9
  parseconfig (~> 1.1)
10
10
  rake (~> 13.0)
11
+ rdf-raptor (~> 3.2.0)
12
+ require_all (~> 3.0.0)
11
13
  rest-client (~> 2.1)
12
14
  rspec (~> 3.11)
13
15
  rubocop (~> 1.7)
@@ -17,26 +19,23 @@ PATH
17
19
  GEM
18
20
  remote: https://rubygems.org/
19
21
  specs:
20
- addressable (2.8.0)
21
- public_suffix (>= 2.0.2, < 5.0)
22
- amazing_print (1.4.0)
22
+ addressable (2.8.5)
23
+ public_suffix (>= 2.0.2, < 6.0)
23
24
  ast (2.4.2)
24
- bcp47 (0.3.3)
25
- i18n
25
+ bcp47_spec (0.2.1)
26
26
  builder (3.2.4)
27
- concurrent-ruby (1.1.10)
28
- connection_pool (2.2.5)
27
+ concurrent-ruby (1.2.2)
28
+ connection_pool (2.4.1)
29
29
  diff-lcs (1.5.0)
30
30
  domain_name (0.5.20190701)
31
31
  unf (>= 0.0.5, < 1.0.0)
32
- ebnf (2.3.1)
33
- amazing_print (~> 1.4)
32
+ ebnf (2.4.0)
34
33
  htmlentities (~> 4.3)
35
- rdf (~> 3.2)
34
+ rdf (~> 3.3)
36
35
  scanf (~> 1.0)
37
- sxp (~> 1.2)
38
- unicode-types (~> 1.7)
39
- faraday (1.10.1)
36
+ sxp (~> 1.3)
37
+ unicode-types (~> 1.8)
38
+ faraday (1.10.3)
40
39
  faraday-em_http (~> 1.0)
41
40
  faraday-em_synchrony (~> 1.0)
42
41
  faraday-excon (~> 1.1)
@@ -56,7 +55,7 @@ GEM
56
55
  faraday-encoding (0.0.5)
57
56
  faraday
58
57
  faraday-excon (1.1.0)
59
- faraday-http-cache (2.4.1)
58
+ faraday-http-cache (2.5.0)
60
59
  faraday (>= 0.8)
61
60
  faraday-httpclient (1.0.1)
62
61
  faraday-multipart (1.0.4)
@@ -68,9 +67,11 @@ GEM
68
67
  faraday-retry (1.0.3)
69
68
  faraday_middleware (1.2.0)
70
69
  faraday (~> 1.0)
71
- fastimage (2.2.6)
72
- haml (5.2.2)
73
- temple (>= 0.8.0)
70
+ fastimage (2.2.7)
71
+ ffi (1.15.5)
72
+ haml (6.1.2)
73
+ temple (>= 0.8.2)
74
+ thor
74
75
  tilt
75
76
  hamster (3.0.0)
76
77
  concurrent-ruby (~> 1.0)
@@ -78,56 +79,54 @@ GEM
78
79
  http-accept (1.7.0)
79
80
  http-cookie (1.0.5)
80
81
  domain_name (~> 0.5)
81
- i18n (1.12.0)
82
- concurrent-ruby (~> 1.0)
83
82
  json (2.6.2)
84
- json-canonicalization (0.3.0)
85
- json-ld (3.2.3)
83
+ json-canonicalization (0.3.2)
84
+ json-ld (3.3.0)
86
85
  htmlentities (~> 4.3)
87
- json-canonicalization (~> 0.3)
86
+ json-canonicalization (~> 0.3, >= 0.3.2)
88
87
  link_header (~> 0.0, >= 0.0.8)
89
88
  multi_json (~> 1.15)
90
- rack (~> 2.2)
91
- rdf (~> 3.2, >= 3.2.9)
92
- json-ld-preloaded (3.2.0)
93
- json-ld (~> 3.2)
94
- rdf (~> 3.2)
95
- ld-patch (3.2.0)
96
- ebnf (~> 2.2)
97
- rdf (~> 3.2)
98
- rdf-xsd (~> 3.2)
99
- sparql (~> 3.2)
100
- sxp (~> 1.2)
89
+ rack (>= 2.2, < 4)
90
+ rdf (~> 3.3)
91
+ json-ld-preloaded (3.3.0)
92
+ json-ld (~> 3.3)
93
+ rdf (~> 3.3)
94
+ ld-patch (3.3.0)
95
+ ebnf (~> 2.4)
96
+ rdf (~> 3.3)
97
+ rdf-xsd (~> 3.3)
98
+ sparql (~> 3.3)
99
+ sxp (~> 1.3)
101
100
  link_header (0.0.8)
102
- linkeddata (3.2.1)
103
- json-ld (~> 3.2, >= 3.2.3)
104
- json-ld-preloaded (~> 3.2)
105
- ld-patch (~> 3.2)
106
- nokogiri (~> 1.13, >= 1.13.8)
107
- rdf (~> 3.2, >= 3.2.9)
108
- rdf-aggregate-repo (~> 3.2, >= 3.2.1)
109
- rdf-hamster-repo (~> 3.2)
110
- rdf-isomorphic (~> 3.2, >= 3.2.1)
111
- rdf-json (~> 3.2)
112
- rdf-microdata (~> 3.2, >= 3.2.1)
113
- rdf-n3 (~> 3.2, >= 3.2.1)
114
- rdf-normalize (~> 0.5)
115
- rdf-ordered-repo (~> 3.2, >= 3.2.1)
116
- rdf-rdfa (~> 3.2)
117
- rdf-rdfxml (~> 3.2)
118
- rdf-reasoner (~> 0.8)
119
- rdf-tabular (~> 3.2, >= 3.2.1)
120
- rdf-trig (~> 3.2)
121
- rdf-trix (~> 3.2)
122
- rdf-turtle (~> 3.2, >= 3.2.1)
123
- rdf-vocab (~> 3.2, >= 3.2.1)
124
- rdf-xsd (~> 3.2, >= 3.2.1)
125
- shacl (~> 0.2, >= 0.2.1)
126
- shex (~> 0.7, >= 0.7.1)
127
- sparql (~> 3.2, >= 3.2.4)
128
- sparql-client (~> 3.2, >= 3.2.1)
101
+ linkeddata (3.3.1)
102
+ json-ld (~> 3.3)
103
+ json-ld-preloaded (~> 3.3)
104
+ ld-patch (~> 3.3)
105
+ nokogiri (~> 1.15, >= 1.15.4)
106
+ rdf (~> 3.2, >= 3.2.1)
107
+ rdf-aggregate-repo (~> 3.2)
108
+ rdf-hamster-repo (~> 3.3)
109
+ rdf-isomorphic (~> 3.3)
110
+ rdf-json (~> 3.3)
111
+ rdf-microdata (~> 3.3)
112
+ rdf-n3 (~> 3.3)
113
+ rdf-normalize (~> 0.7)
114
+ rdf-ordered-repo (~> 3.3)
115
+ rdf-rdfa (~> 3.3)
116
+ rdf-rdfxml (~> 3.3)
117
+ rdf-reasoner (~> 0.9)
118
+ rdf-tabular (~> 3.3)
119
+ rdf-trig (~> 3.3)
120
+ rdf-trix (~> 3.3)
121
+ rdf-turtle (~> 3.3)
122
+ rdf-vocab (~> 3.3)
123
+ rdf-xsd (~> 3.3)
124
+ shacl (~> 0.4)
125
+ shex (~> 0.8)
126
+ sparql (~> 3.3)
127
+ sparql-client (~> 3.3)
129
128
  yaml-ld (~> 0.0)
130
- linkheaders-processor (0.1.18)
129
+ linkheaders-processor (0.1.19)
131
130
  json (~> 2.0)
132
131
  json-ld (~> 3.2)
133
132
  json-ld-preloaded (~> 3.2)
@@ -135,7 +134,7 @@ GEM
135
134
  metainspector (~> 5.11.2)
136
135
  rest-client (~> 2.1)
137
136
  securerandom (~> 0.1.0)
138
- logger (1.5.1)
137
+ logger (1.5.3)
139
138
  matrix (0.4.2)
140
139
  metainspector (5.11.2)
141
140
  addressable (~> 2.7)
@@ -147,92 +146,97 @@ GEM
147
146
  fastimage (~> 2.2)
148
147
  nesty (~> 1.0)
149
148
  nokogiri (~> 1.11)
150
- mime-types (3.4.1)
149
+ mime-types (3.5.1)
151
150
  mime-types-data (~> 3.2015)
152
- mime-types-data (3.2022.0105)
151
+ mime-types-data (3.2023.0808)
153
152
  multi_json (1.15.0)
154
- multipart-post (2.2.3)
153
+ multipart-post (2.3.0)
155
154
  nesty (1.0.2)
156
- net-http-persistent (4.0.1)
155
+ net-http-persistent (4.0.2)
157
156
  connection_pool (~> 2.2)
158
157
  netrc (0.11.0)
159
- nokogiri (1.13.8-x86_64-linux)
158
+ nokogiri (1.15.4-x86_64-linux)
160
159
  racc (~> 1.4)
161
160
  parallel (1.22.1)
162
161
  parseconfig (1.1.2)
163
162
  parser (3.1.2.1)
164
163
  ast (~> 2.4.1)
165
- psych (4.0.4)
164
+ psych (5.1.0)
166
165
  stringio
167
- public_suffix (4.0.7)
168
- racc (1.6.0)
169
- rack (2.2.4)
166
+ public_suffix (5.0.3)
167
+ racc (1.7.1)
168
+ rack (3.0.8)
170
169
  rainbow (3.1.1)
171
170
  rake (13.0.6)
172
- rdf (3.2.9)
171
+ rdf (3.3.1)
172
+ bcp47_spec (~> 0.2)
173
173
  link_header (~> 0.0, >= 0.0.8)
174
- rdf-aggregate-repo (3.2.1)
175
- rdf (~> 3.2)
176
- rdf-hamster-repo (3.2.1)
174
+ rdf-aggregate-repo (3.3.0)
175
+ rdf (~> 3.3)
176
+ rdf-hamster-repo (3.3.0)
177
177
  hamster (~> 3.0)
178
- rdf (~> 3.2, >= 3.2.1)
179
- rdf-isomorphic (3.2.1)
180
- rdf (~> 3.2)
181
- rdf-json (3.2.0)
182
- rdf (~> 3.2)
183
- rdf-microdata (3.2.1)
178
+ rdf (~> 3.3)
179
+ rdf-isomorphic (3.3.0)
180
+ rdf (~> 3.3)
181
+ rdf-json (3.3.0)
182
+ rdf (~> 3.3)
183
+ rdf-microdata (3.3.0)
184
184
  htmlentities (~> 4.3)
185
- nokogiri (~> 1.13)
186
- rdf (~> 3.2)
187
- rdf-rdfa (~> 3.2)
188
- rdf-xsd (~> 3.2)
189
- rdf-n3 (3.2.1)
190
- ebnf (~> 2.2)
191
- rdf (~> 3.2)
192
- sparql (~> 3.2)
193
- sxp (~> 1.2)
194
- rdf-normalize (0.5.0)
185
+ nokogiri (~> 1.15, >= 1.15.4)
186
+ rdf (~> 3.3)
187
+ rdf-rdfa (~> 3.3)
188
+ rdf-xsd (~> 3.3)
189
+ rdf-n3 (3.3.0)
190
+ ebnf (~> 2.4)
191
+ rdf (~> 3.3)
192
+ sparql (~> 3.3)
193
+ sxp (~> 1.3)
194
+ rdf-normalize (0.7.0)
195
+ rdf (~> 3.3)
196
+ rdf-ordered-repo (3.3.0)
197
+ rdf (~> 3.3)
198
+ rdf-raptor (3.2.0)
199
+ ffi (~> 1.15)
195
200
  rdf (~> 3.2)
196
- rdf-ordered-repo (3.2.1)
197
- rdf (~> 3.2, >= 3.2.1)
198
- rdf-rdfa (3.2.0)
199
- haml (~> 5.2)
201
+ rdf-rdfa (3.3.0)
202
+ haml (~> 6.1)
200
203
  htmlentities (~> 4.3)
201
- rdf (~> 3.2)
202
- rdf-aggregate-repo (~> 3.2)
203
- rdf-vocab (~> 3.2)
204
- rdf-xsd (~> 3.2)
205
- rdf-rdfxml (3.2.0)
204
+ rdf (~> 3.3)
205
+ rdf-aggregate-repo (~> 3.3)
206
+ rdf-vocab (~> 3.3)
207
+ rdf-xsd (~> 3.3)
208
+ rdf-rdfxml (3.3.0)
209
+ builder (~> 3.2, >= 3.2.4)
206
210
  htmlentities (~> 4.3)
207
- rdf (~> 3.2)
208
- rdf-rdfa (~> 3.2)
209
- rdf-xsd (~> 3.2)
210
- rdf-reasoner (0.8.0)
211
- rdf (~> 3.2)
212
- rdf-xsd (~> 3.2)
213
- rdf-tabular (3.2.1)
211
+ rdf (~> 3.3)
212
+ rdf-xsd (~> 3.3)
213
+ rdf-reasoner (0.9.0)
214
+ rdf (~> 3.3)
215
+ rdf-xsd (~> 3.3)
216
+ rdf-tabular (3.3.0)
214
217
  addressable (~> 2.8)
215
- bcp47 (~> 0.3, >= 0.3.3)
216
- json-ld (~> 3.2)
217
- rdf (~> 3.2, >= 3.2.7)
218
- rdf-vocab (~> 3.2)
219
- rdf-xsd (~> 3.2)
220
- rdf-trig (3.2.0)
221
- ebnf (~> 2.2)
222
- rdf (~> 3.2)
223
- rdf-turtle (~> 3.2)
224
- rdf-trix (3.2.0)
225
- rdf (~> 3.2)
226
- rdf-xsd (~> 3.2)
227
- rdf-turtle (3.2.1)
228
- ebnf (~> 2.3)
229
- rdf (~> 3.2)
230
- rdf-vocab (3.2.1)
231
- rdf (~> 3.2, >= 3.2.4)
232
- rdf-xsd (3.2.1)
233
- rdf (~> 3.2)
218
+ bcp47_spec (~> 0.2)
219
+ json-ld (~> 3.3)
220
+ rdf (~> 3.3)
221
+ rdf-vocab (~> 3.3)
222
+ rdf-xsd (~> 3.3)
223
+ rdf-trig (3.3.0)
224
+ ebnf (~> 2.4)
225
+ rdf (~> 3.3)
226
+ rdf-turtle (~> 3.3)
227
+ rdf-trix (3.3.0)
228
+ rdf (~> 3.3)
229
+ rdf-xsd (~> 3.3)
230
+ rdf-turtle (3.3.0)
231
+ ebnf (~> 2.4)
232
+ rdf (~> 3.3)
233
+ rdf-vocab (3.3.0)
234
+ rdf (~> 3.3)
235
+ rdf-xsd (3.3.0)
236
+ rdf (~> 3.3)
234
237
  rexml (~> 3.2)
235
238
  regexp_parser (2.5.0)
239
+ require_all (3.0.0)
236
240
  rest-client (2.1.0)
237
241
  http-accept (>= 1.7.0, < 2.0)
238
242
  http-cookie (>= 1.0.2, < 2.0)
@@ -268,49 +272,51 @@ GEM
268
272
  ruby2_keywords (0.0.5)
269
273
  scanf (1.0.0)
270
274
  securerandom (0.1.1)
271
- shacl (0.3.0)
272
- json-ld (~> 3.2)
273
- rdf (~> 3.2, >= 3.2.8)
274
- sparql (~> 3.2, >= 3.2.4)
275
+ shacl (0.4.0)
276
+ json-ld (~> 3.3)
277
+ rdf (~> 3.3)
278
+ sparql (~> 3.3)
275
279
  sxp (~> 1.2)
276
- shex (0.7.1)
277
- ebnf (~> 2.2)
280
+ shex (0.8.0)
281
+ ebnf (~> 2.4)
278
282
  htmlentities (~> 4.3)
279
- json-ld (~> 3.2)
280
- json-ld-preloaded (~> 3.2)
281
- rdf (~> 3.2)
282
- rdf-xsd (~> 3.2)
283
- sparql (~> 3.2)
284
- sxp (~> 1.2)
285
- sparql (3.2.4)
286
- builder (~> 3.2)
287
- ebnf (~> 2.2, >= 2.3.1)
283
+ json-ld (~> 3.3)
284
+ json-ld-preloaded (~> 3.3)
285
+ rdf (~> 3.3)
286
+ rdf-xsd (~> 3.3)
287
+ sparql (~> 3.3)
288
+ sxp (~> 1.3)
289
+ sparql (3.3.0)
290
+ builder (~> 3.2, >= 3.2.4)
291
+ ebnf (~> 2.4)
288
292
  logger (~> 1.5)
289
- rdf (~> 3.2, >= 3.2.8)
290
- rdf-aggregate-repo (~> 3.2)
291
- rdf-xsd (~> 3.2)
292
- sparql-client (~> 3.2, >= 3.2.1)
293
- sxp (~> 1.2, >= 1.2.2)
294
- sparql-client (3.2.1)
295
- net-http-persistent (~> 4.0, >= 4.0.1)
296
- rdf (~> 3.2, >= 3.2.6)
297
- stringio (3.0.2)
298
- sxp (1.2.2)
299
- matrix
300
- rdf (~> 3.2)
301
- temple (0.8.2)
302
- tilt (2.0.11)
293
+ rdf (~> 3.3)
294
+ rdf-aggregate-repo (~> 3.3)
295
+ rdf-xsd (~> 3.3)
296
+ sparql-client (~> 3.3)
297
+ sxp (~> 1.3)
298
+ sparql-client (3.3.0)
299
+ net-http-persistent (~> 4.0, >= 4.0.2)
300
+ rdf (~> 3.3)
301
+ stringio (3.0.8)
302
+ sxp (1.3.0)
303
+ matrix (~> 0.4)
304
+ rdf (~> 3.3)
305
+ temple (0.10.2)
306
+ thor (1.2.2)
307
+ tilt (2.3.0)
303
308
  unf (0.1.4)
304
309
  unf_ext
305
310
  unf_ext (0.0.8.2)
306
311
  unicode-display_width (2.2.0)
307
- unicode-types (1.7.0)
312
+ unicode-types (1.8.0)
308
313
  xml-simple (1.1.9)
309
314
  rexml
310
- yaml-ld (0.0.1)
311
- json-ld (~> 3.2, >= 3.2.2)
312
- psych (~> 4.0)
313
- rdf (~> 3.2)
315
+ yaml-ld (0.0.2)
316
+ json-ld (~> 3.2, >= 3.2.3)
317
+ psych (>= 3.3)
318
+ rdf (~> 3.2, >= 3.2.9)
319
+ rdf-xsd (~> 3.2)
314
320
 
315
321
  PLATFORMS
316
322
  x86_64-linux
data/lib/fsp_harvester/version.rb CHANGED
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module FspHarvester
4
- VERSION = "0.1.25"
4
+ VERSION = "0.1.27"
5
5
  end
data/lib/fsp_harvester.rb CHANGED
@@ -12,6 +12,7 @@ module FspHarvester
12
12
  links.each do |l|
13
13
  db << l if l.relation == 'describedby'
14
14
  end
15
+ warn db.length
15
16
  HarvesterTools::MetadataHarvester.extract_metadata_from_links(links: db, metadata: @meta) # everything is gathered into the @meta metadata object
16
17
  @meta
17
18
  end
data/lib/harvester.rb CHANGED
@@ -16,6 +16,8 @@ require 'digest'
16
16
  require 'open3'
17
17
  require 'metainspector'
18
18
  require 'rdf/xsd'
19
+ require 'linkeddata'
20
+ require 'rdf/raptor'
19
21
  require_relative './metadata_object'
20
22
  require_relative './constants'
21
23
  require_relative './web_utils'
data/lib/metadata_harvester.rb CHANGED
@@ -10,6 +10,7 @@ module HarvesterTools
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
+ warn "metadata harvester links length #{describedby.length}"
13
14
 
14
15
  hvst = HarvesterTools::MetadataParser.new(metadata_object: @meta) # put here because the class variable for detecting duplicates should apply to all URIs
15
16
  describedby.each do |link|
@@ -18,8 +19,10 @@ module HarvesterTools
18
19
  accepttype = { 'Accept' => accept } if accept
19
20
 
20
21
  response = attempt_to_resolve(link: link, headers: accepttype)
22
+ warn "\n\nRESPONSE #{response}\n\n"
21
23
 
22
24
  abbreviation, content_type = attempt_to_detect_type(body: response.body, headers: response.headers)
25
+ warn "ABBR #{abbreviation} CONT #{content_type}\n\n"
23
26
  unless abbreviation
24
27
  @meta.add_warning(['017', url, header])
25
28
  @meta.comments << "WARN: metadata format returned from #{url} using Accept header #{header} is not recognized. Processing will end now.\n"
@@ -52,6 +55,7 @@ module HarvesterTools
52
55
 
53
56
  def self.process_according_to_type(body:, uri:, abbreviation:, content_type:, metadata:,
54
57
  harvester: HarvesterTools::MetadataParser.new(metadata_object: @meta))
58
+ warn "PROCESSING #{abbreviation}"
55
59
  case abbreviation
56
60
  when 'html'
57
61
  @meta.comments << 'INFO: Processing html'
@@ -63,6 +67,7 @@ module HarvesterTools
63
67
  @meta.comments << 'INFO: Processing json'
64
68
  harvester.process_json(body: body, metadata: @meta)
65
69
  when 'jsonld', 'rdfxml', 'turtle', 'ntriples', 'nquads'
70
+ warn "PROCESSING USING TURTLE"
66
71
  @meta.comments << 'INFO: Processing linked data'
67
72
  harvester.process_ld(body: body, content_type: content_type, metadata: @meta)
68
73
  when 'specialist'
data/lib/metadata_parser.rb CHANGED
@@ -1,5 +1,4 @@
1
1
  # frozen_string_literal: true
2
-
3
2
  module HarvesterTools
4
3
  class Error < StandardError
5
4
  end
@@ -58,19 +57,24 @@ module HarvesterTools
58
57
 
59
58
  def self.parse_rdf(body:, content_type:, metadata:)
60
59
  @meta = metadata
60
+ warn "1 PARSING RDF #{body}"
61
61
  unless body
62
62
  metadata.comments << "CRITICAL: The response message body component appears to have no content.\n"
63
63
  metadata.add_warning(['018', '', ''])
64
64
  return
65
65
  end
66
+ warn "2 PARSING RDF #{body}"
66
67
 
67
68
  unless body.match(/\w/)
68
69
  metadata.comments << "CRITICAL: The response message body component appears to have no content.\n"
69
70
  metadata.add_warning(['018', '', ''])
70
71
  return
71
72
  end
73
+ warn "3 PARSING RDF #{body} content type #{content_type.class}"
72
74
 
73
75
  rdfformat = RDF::Format.for(content_type: content_type)
76
+ warn "FORMAT #{rdfformat}"
77
+ warn "FORMAT #{RDF::Format.for(content_type: 'text/turtle')}"
74
78
  unless rdfformat
75
79
  metadata.comments << "CRITICAL: Found what appears 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"
76
80
  metadata.add_warning(['018', '', ''])
data/tryme.rb ADDED
@@ -0,0 +1,9 @@
1
+ require 'require_all'
2
+ warn `pwd`
3
+ require_all './lib/'
4
+
5
+ guid = 'https://w3id.org/a2a-fair-metrics/22-http-html-citeas-describedby-mixed/'
6
+ guid = 'https://doi.org/10.7910/DVN/Z2JD58'
7
+ links, metadata = HarvesterTools::Utils.resolve_guid(guid: guid)
8
+ meta = FspHarvester::Utils.gather_metadata_from_describedby_links(links: links, metadata: metadata)
9
+ puts meta.graph.triples
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: 0.1.25
4
+ version: 0.1.27
5
5
  platform: ruby
6
6
  authors:
7
7
  - Mark Wilkinson
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2022-08-20 00:00:00.000000000 Z
11
+ date: 2023-09-26 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: json
@@ -38,20 +38,34 @@ dependencies:
38
38
  - - "~>"
39
39
  - !ruby/object:Gem::Version
40
40
  version: '3.2'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rdf-raptor
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: 3.2.0
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: 3.2.0
41
55
  - !ruby/object:Gem::Dependency
42
56
  name: linkheaders-processor
43
57
  requirement: !ruby/object:Gem::Requirement
44
58
  requirements:
45
59
  - - "~>"
46
60
  - !ruby/object:Gem::Version
47
- version: 0.1.18
61
+ version: 0.1.19
48
62
  type: :runtime
49
63
  prerelease: false
50
64
  version_requirements: !ruby/object:Gem::Requirement
51
65
  requirements:
52
66
  - - "~>"
53
67
  - !ruby/object:Gem::Version
54
- version: 0.1.18
68
+ version: 0.1.19
55
69
  - !ruby/object:Gem::Dependency
56
70
  name: metainspector
57
71
  requirement: !ruby/object:Gem::Requirement
@@ -164,6 +178,20 @@ dependencies:
164
178
  - - "~>"
165
179
  - !ruby/object:Gem::Version
166
180
  version: '1.1'
181
+ - !ruby/object:Gem::Dependency
182
+ name: require_all
183
+ requirement: !ruby/object:Gem::Requirement
184
+ requirements:
185
+ - - "~>"
186
+ - !ruby/object:Gem::Version
187
+ version: 3.0.0
188
+ type: :runtime
189
+ prerelease: false
190
+ version_requirements: !ruby/object:Gem::Requirement
191
+ requirements:
192
+ - - "~>"
193
+ - !ruby/object:Gem::Version
194
+ version: 3.0.0
167
195
  description: Metadata harvester that follows the FAIR Signposting specification.
168
196
  email:
169
197
  - markw@illuminae.com
@@ -172,6 +200,7 @@ extensions: []
172
200
  extra_rdoc_files: []
173
201
  files:
174
202
  - ".rspec_status"
203
+ - ".vscode/launch.json"
175
204
  - CHANGELOG.md
176
205
  - Gemfile
177
206
  - Gemfile.lock
@@ -180,7 +209,6 @@ files:
180
209
  - Rakefile
181
210
  - bin/console
182
211
  - bin/setup
183
- - launch.json
184
212
  - lib/constants.rb
185
213
  - lib/external_tools.rb
186
214
  - lib/fsp_harvester.rb
@@ -197,6 +225,7 @@ files:
197
225
  - lib/signposting_tests.rb
198
226
  - lib/warnings.json
199
227
  - lib/web_utils.rb
228
+ - tryme.rb
200
229
  homepage: https://github.com/markwilkinson/FAIR-Signposting-Harvester
201
230
  licenses:
202
231
  - MIT
@@ -220,7 +249,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
220
249
  - !ruby/object:Gem::Version
221
250
  version: '0'
222
251
  requirements: []
223
- rubygems_version: 3.2.28
252
+ rubygems_version: 3.3.23
224
253
  signing_key:
225
254
  specification_version: 4
226
255
  summary: Metadata harvester that follows the FAIR Signposting specification.
data/launch.json DELETED
@@ -1,11 +0,0 @@
1
- {
2
- "name": "RSpec - all",
3
- "type": "Ruby",
4
- "request": "launch",
5
- "cwd": "${workspaceRoot}",
6
- "program": "/home/osboxes/.rvm/gems/ruby-3.0.0/bin/rspec",
7
- "args": [
8
- "-I",
9
- "${workspaceRoot}"
10
- ]
11
- }