dwc-archive 0.9.11 → 1.1.3
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 +5 -5
- data/.gitignore +1 -0
- data/.rspec +2 -1
- data/.rubocop.yml +23 -0
- data/.ruby-version +1 -1
- data/.travis.yml +4 -7
- data/CHANGELOG +4 -0
- data/Gemfile +3 -1
- data/LICENSE +1 -1
- data/README.md +114 -109
- data/Rakefile +13 -36
- data/dwc-archive.gemspec +23 -19
- data/features/step_definitions/dwc-creator_steps.rb +5 -5
- data/features/step_definitions/dwc-reader_steps.rb +47 -28
- data/features/support/env.rb +1 -1
- data/lib/dwc_archive.rb +124 -0
- data/lib/dwc_archive/archive.rb +60 -0
- data/lib/dwc_archive/classification_normalizer.rb +382 -0
- data/lib/dwc_archive/core.rb +25 -0
- data/lib/{dwc-archive → dwc_archive}/errors.rb +10 -0
- data/lib/dwc_archive/expander.rb +88 -0
- data/lib/{dwc-archive → dwc_archive}/extension.rb +5 -3
- data/lib/dwc_archive/generator.rb +91 -0
- data/lib/{dwc-archive → dwc_archive}/generator_eml_xml.rb +40 -33
- data/lib/{dwc-archive → dwc_archive}/generator_meta_xml.rb +21 -20
- data/lib/dwc_archive/gnub_taxon.rb +14 -0
- data/lib/dwc_archive/ingester.rb +106 -0
- data/lib/dwc_archive/metadata.rb +57 -0
- data/lib/dwc_archive/taxon_normalized.rb +23 -0
- data/lib/dwc_archive/version.rb +6 -0
- data/lib/dwc_archive/xml_reader.rb +90 -0
- data/spec/files/file with characters(3).gz b/data/spec/files/file with → characters(3).tar.gz +0 -0
- data/spec/files/generator_eml.xml +1 -1
- data/spec/lib/classification_normalizer_spec.rb +96 -105
- data/spec/lib/core_spec.rb +43 -41
- data/spec/lib/darwin_core_spec.rb +108 -138
- data/spec/lib/generator_eml_xml_spec.rb +12 -11
- data/spec/lib/generator_meta_xml_spec.rb +12 -11
- data/spec/lib/generator_spec.rb +73 -74
- data/spec/lib/gnub_taxon_spec.rb +15 -17
- data/spec/lib/metadata_spec.rb +50 -41
- data/spec/lib/taxon_normalized_spec.rb +62 -65
- data/spec/lib/xml_reader_spec.rb +9 -12
- data/spec/spec_helper.rb +54 -51
- metadata +101 -87
- data/.rvmrc +0 -1
- data/lib/dwc-archive.rb +0 -107
- data/lib/dwc-archive/archive.rb +0 -40
- data/lib/dwc-archive/classification_normalizer.rb +0 -427
- data/lib/dwc-archive/core.rb +0 -19
- data/lib/dwc-archive/expander.rb +0 -85
- data/lib/dwc-archive/generator.rb +0 -86
- data/lib/dwc-archive/ingester.rb +0 -101
- data/lib/dwc-archive/metadata.rb +0 -48
- data/lib/dwc-archive/version.rb +0 -3
- data/lib/dwc-archive/xml_reader.rb +0 -80
data/spec/lib/xml_reader_spec.rb
CHANGED
@@ -1,18 +1,15 @@
|
|
1
|
-
|
1
|
+
# frozen_string_literal: true
|
2
2
|
|
3
|
-
describe DarwinCore::XmlReader do
|
4
|
-
|
5
|
-
|
3
|
+
describe DarwinCore::XmlReader do
|
4
|
+
describe ".from_xml" do
|
5
|
+
let(:file) { File.expand_path("../files/meta.xml", __dir__) }
|
6
|
+
subject { DarwinCore::XmlReader.from_xml(File.read(file)) }
|
6
7
|
|
7
8
|
it "reads xml to hash" do
|
8
|
-
|
9
|
-
|
10
|
-
expect(
|
11
|
-
|
12
|
-
expect(meta[:archive][:core].keys.sort).
|
13
|
-
to eq [:attributes, :field, :files, :id]
|
9
|
+
expect(subject).to be_kind_of Hash
|
10
|
+
expect(subject[:archive].keys.sort).to eq %i[core extension]
|
11
|
+
expect(subject[:archive][:core].keys.sort).
|
12
|
+
to eq %i[attributes field files id]
|
14
13
|
end
|
15
|
-
|
16
14
|
end
|
17
|
-
|
18
15
|
end
|
data/spec/spec_helper.rb
CHANGED
@@ -1,60 +1,63 @@
|
|
1
|
-
#
|
2
|
-
# HACK: to suppress warnings
|
3
|
-
$VERBOSE = nil
|
1
|
+
# frozen_string_literal: true
|
4
2
|
|
5
|
-
require
|
6
|
-
|
3
|
+
require "dwc_archive"
|
4
|
+
require "rspec"
|
5
|
+
require "rspec/mocks"
|
6
|
+
require "socket"
|
7
7
|
|
8
|
-
|
9
|
-
require 'rspec'
|
10
|
-
require 'rspec/mocks'
|
11
|
-
require 'socket'
|
12
|
-
|
13
|
-
RSpec.configure do |config|
|
8
|
+
RSpec.configure do
|
14
9
|
end
|
15
10
|
|
16
11
|
unless defined?(SPEC_CONSTANTS)
|
17
|
-
EML_DATA =
|
18
|
-
|
19
|
-
|
20
|
-
|
12
|
+
EML_DATA =
|
13
|
+
{
|
14
|
+
id: "1234",
|
15
|
+
license: "http://creativecommons.org/licenses/by-sa/3.0/",
|
16
|
+
title: "Test Classification",
|
21
17
|
authors: [
|
22
|
-
{ first_name:
|
23
|
-
last_name:
|
24
|
-
email:
|
25
|
-
organization:
|
26
|
-
position:
|
27
|
-
url:
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
18
|
+
{ first_name: "John",
|
19
|
+
last_name: "Doe",
|
20
|
+
email: "jdoe@example.com",
|
21
|
+
organization: "Example",
|
22
|
+
position: "Assistant Professor",
|
23
|
+
url: "http://example.org" },
|
24
|
+
{ first_name: "Jane",
|
25
|
+
last_name: "Doe",
|
26
|
+
email: "jane@example.com" }
|
27
|
+
],
|
32
28
|
metadata_providers: [
|
33
|
-
{ first_name:
|
34
|
-
last_name:
|
35
|
-
email:
|
36
|
-
url:
|
37
|
-
|
29
|
+
{ first_name: "Jim",
|
30
|
+
last_name: "Doe",
|
31
|
+
email: "jimdoe@example.com",
|
32
|
+
url: "http://aggregator.example.org" }
|
33
|
+
],
|
34
|
+
abstract: "test classification",
|
38
35
|
citation:
|
39
|
-
|
40
|
-
url:
|
41
|
-
}
|
36
|
+
"Test classification: Doe John, Doe Jane, Taxnonmy, 10, 1, 2010",
|
37
|
+
url: "http://example.com"
|
38
|
+
}.freeze
|
42
39
|
META_DATA = {
|
43
|
-
extensions:
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
40
|
+
extensions:
|
41
|
+
[
|
42
|
+
{ fields:
|
43
|
+
[
|
44
|
+
"http://rs.tdwg.org/dwc/terms/TaxonID",
|
45
|
+
"http://rs.tdwg.org/dwc/terms/vernacularName"
|
46
|
+
],
|
47
|
+
ignoreHeaderLines: 1,
|
48
|
+
location: "vern.csv",
|
49
|
+
rowType: "http://rs.gbif.org/terms/1.0/VernacularName" }
|
50
|
+
],
|
51
|
+
core: { fields:
|
52
|
+
[
|
53
|
+
"http://rs.tdwg.org/dwc/terms/taxonID",
|
54
|
+
"http://rs.tdwg.org/dwc/terms/parentNameUsageID",
|
55
|
+
"http://rs.tdwg.org/dwc/terms/scientificName",
|
56
|
+
"http://rs.tdwg.org/dwc/terms/taxonRank"
|
57
|
+
],
|
58
|
+
ignoreHeaderLines: 1,
|
59
|
+
location: "core.csv" }
|
60
|
+
}.freeze
|
58
61
|
CORE_DATA = [
|
59
62
|
["http://rs.tdwg.org/dwc/terms/taxonID",
|
60
63
|
"http://rs.tdwg.org/dwc/terms/parentNameUsageID",
|
@@ -63,16 +66,16 @@ unless defined?(SPEC_CONSTANTS)
|
|
63
66
|
[1, 0, "Plantae", "kingdom"],
|
64
67
|
[2, 1, "Betula", "genus"],
|
65
68
|
[3, 2, "Betula verucosa", "species"]
|
66
|
-
]
|
69
|
+
].freeze
|
67
70
|
EXTENSION_DATA = [
|
68
71
|
["http://rs.tdwg.org/dwc/terms/TaxonID",
|
69
|
-
|
72
|
+
"http://rs.tdwg.org/dwc/terms/vernacularName"],
|
70
73
|
[1, "Plants"],
|
71
74
|
[1, "Растения"],
|
72
75
|
[2, "Birch"],
|
73
76
|
[2, "Береза"],
|
74
77
|
[3, "Wheeping Birch"],
|
75
78
|
[3, "Береза плакучая"]
|
76
|
-
]
|
79
|
+
].freeze
|
77
80
|
SPEC_CONSTANTS = true
|
78
81
|
end
|
metadata
CHANGED
@@ -1,171 +1,184 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dwc-archive
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 1.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dmitry Mozzherin
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-01-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name:
|
14
|
+
name: biodiversity
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - ~>
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version:
|
19
|
+
version: 5.1.2
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - ~>
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version:
|
26
|
+
version: 5.1.2
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
28
|
+
name: nokogiri
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - ~>
|
31
|
+
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '1.11'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - ~>
|
38
|
+
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '1.11'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: bundler
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - ~>
|
45
|
+
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
48
|
-
type: :
|
47
|
+
version: '2.2'
|
48
|
+
type: :development
|
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: '
|
54
|
+
version: '2.2'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: byebug
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - ~>
|
59
|
+
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
61
|
+
version: '11.1'
|
62
62
|
type: :development
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- - ~>
|
66
|
+
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
68
|
+
version: '11.1'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
70
|
+
name: cucumber
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- - ~>
|
73
|
+
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version: '
|
75
|
+
version: '5'
|
76
76
|
type: :development
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- - ~>
|
80
|
+
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version: '
|
82
|
+
version: '5'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
|
-
name:
|
84
|
+
name: git
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
|
-
- - ~>
|
87
|
+
- - "~>"
|
88
88
|
- !ruby/object:Gem::Version
|
89
|
-
version: '
|
89
|
+
version: '1.8'
|
90
90
|
type: :development
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
|
-
- - ~>
|
94
|
+
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
|
-
version: '
|
96
|
+
version: '1.8'
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
|
-
name:
|
98
|
+
name: rake
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
|
-
- - ~>
|
101
|
+
- - "~>"
|
102
102
|
- !ruby/object:Gem::Version
|
103
|
-
version: '
|
103
|
+
version: '13'
|
104
104
|
type: :development
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
|
-
- - ~>
|
108
|
+
- - "~>"
|
109
109
|
- !ruby/object:Gem::Version
|
110
|
-
version: '
|
110
|
+
version: '13'
|
111
111
|
- !ruby/object:Gem::Dependency
|
112
|
-
name:
|
112
|
+
name: rspec
|
113
113
|
requirement: !ruby/object:Gem::Requirement
|
114
114
|
requirements:
|
115
|
-
- - ~>
|
115
|
+
- - "~>"
|
116
116
|
- !ruby/object:Gem::Version
|
117
|
-
version: '
|
117
|
+
version: '3.10'
|
118
118
|
type: :development
|
119
119
|
prerelease: false
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
121
121
|
requirements:
|
122
|
-
- - ~>
|
122
|
+
- - "~>"
|
123
123
|
- !ruby/object:Gem::Version
|
124
|
-
version: '
|
124
|
+
version: '3.10'
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
|
-
name:
|
126
|
+
name: rubocop
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
128
128
|
requirements:
|
129
|
-
- - ~>
|
129
|
+
- - "~>"
|
130
130
|
- !ruby/object:Gem::Version
|
131
|
-
version: '1.
|
131
|
+
version: '1.8'
|
132
132
|
type: :development
|
133
133
|
prerelease: false
|
134
134
|
version_requirements: !ruby/object:Gem::Requirement
|
135
135
|
requirements:
|
136
|
-
- - ~>
|
136
|
+
- - "~>"
|
137
137
|
- !ruby/object:Gem::Version
|
138
|
-
version: '1.
|
138
|
+
version: '1.8'
|
139
139
|
- !ruby/object:Gem::Dependency
|
140
|
-
name:
|
140
|
+
name: solargraph
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0.40'
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - "~>"
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0.40'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: travis
|
141
155
|
requirement: !ruby/object:Gem::Requirement
|
142
156
|
requirements:
|
143
|
-
- - ~>
|
157
|
+
- - "~>"
|
144
158
|
- !ruby/object:Gem::Version
|
145
|
-
version: '1.
|
159
|
+
version: '1.10'
|
146
160
|
type: :development
|
147
161
|
prerelease: false
|
148
162
|
version_requirements: !ruby/object:Gem::Requirement
|
149
163
|
requirements:
|
150
|
-
- - ~>
|
164
|
+
- - "~>"
|
151
165
|
- !ruby/object:Gem::Version
|
152
|
-
version: '1.
|
153
|
-
description:
|
154
|
-
|
155
|
-
|
156
|
-
format into a ruby project."
|
166
|
+
version: '1.10'
|
167
|
+
description: Darwin Core Archive is the current standard exchange format for GLobal
|
168
|
+
Names Architecture modules. This gem makes it easy to incorporate files in Darwin
|
169
|
+
Core Archive format into a ruby project.
|
157
170
|
email:
|
158
171
|
- dmozzherin at gmail dot com
|
159
172
|
executables: []
|
160
173
|
extensions: []
|
161
174
|
extra_rdoc_files: []
|
162
175
|
files:
|
163
|
-
- .document
|
164
|
-
- .gitignore
|
165
|
-
- .rspec
|
166
|
-
- .
|
167
|
-
- .
|
168
|
-
- .travis.yml
|
176
|
+
- ".document"
|
177
|
+
- ".gitignore"
|
178
|
+
- ".rspec"
|
179
|
+
- ".rubocop.yml"
|
180
|
+
- ".ruby-version"
|
181
|
+
- ".travis.yml"
|
169
182
|
- CHANGELOG
|
170
183
|
- Gemfile
|
171
184
|
- LICENSE
|
@@ -177,27 +190,29 @@ files:
|
|
177
190
|
- features/step_definitions/dwc-creator_steps.rb
|
178
191
|
- features/step_definitions/dwc-reader_steps.rb
|
179
192
|
- features/support/env.rb
|
180
|
-
- lib/
|
181
|
-
- lib/
|
182
|
-
- lib/
|
183
|
-
- lib/
|
184
|
-
- lib/
|
185
|
-
- lib/
|
186
|
-
- lib/
|
187
|
-
- lib/
|
188
|
-
- lib/
|
189
|
-
- lib/
|
190
|
-
- lib/
|
191
|
-
- lib/
|
192
|
-
- lib/
|
193
|
-
- lib/
|
193
|
+
- lib/dwc_archive.rb
|
194
|
+
- lib/dwc_archive/archive.rb
|
195
|
+
- lib/dwc_archive/classification_normalizer.rb
|
196
|
+
- lib/dwc_archive/core.rb
|
197
|
+
- lib/dwc_archive/errors.rb
|
198
|
+
- lib/dwc_archive/expander.rb
|
199
|
+
- lib/dwc_archive/extension.rb
|
200
|
+
- lib/dwc_archive/generator.rb
|
201
|
+
- lib/dwc_archive/generator_eml_xml.rb
|
202
|
+
- lib/dwc_archive/generator_meta_xml.rb
|
203
|
+
- lib/dwc_archive/gnub_taxon.rb
|
204
|
+
- lib/dwc_archive/ingester.rb
|
205
|
+
- lib/dwc_archive/metadata.rb
|
206
|
+
- lib/dwc_archive/taxon_normalized.rb
|
207
|
+
- lib/dwc_archive/version.rb
|
208
|
+
- lib/dwc_archive/xml_reader.rb
|
194
209
|
- spec/files/broken.tar.gz
|
195
210
|
- spec/files/data.tar.gz
|
196
211
|
- spec/files/data.zip
|
197
212
|
- spec/files/data_with_quotes.tar.gz
|
198
213
|
- spec/files/eml.xml
|
199
214
|
- spec/files/empty_coreid.tar.gz
|
200
|
-
- spec/files/file with characters(3).gz
|
215
|
+
- spec/files/file with characters(3).tar.gz
|
201
216
|
- spec/files/flat_list.tar.gz
|
202
217
|
- spec/files/generator_eml.xml
|
203
218
|
- spec/files/generator_meta.xml
|
@@ -230,24 +245,23 @@ homepage: http://github.com/GlobalNamesArchitecture/dwc-archive
|
|
230
245
|
licenses:
|
231
246
|
- MIT
|
232
247
|
metadata: {}
|
233
|
-
post_install_message:
|
248
|
+
post_install_message:
|
234
249
|
rdoc_options: []
|
235
250
|
require_paths:
|
236
251
|
- lib
|
237
252
|
required_ruby_version: !ruby/object:Gem::Requirement
|
238
253
|
requirements:
|
239
|
-
- -
|
254
|
+
- - ">="
|
240
255
|
- !ruby/object:Gem::Version
|
241
|
-
version:
|
256
|
+
version: 2.6.0
|
242
257
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
243
258
|
requirements:
|
244
|
-
- -
|
259
|
+
- - ">="
|
245
260
|
- !ruby/object:Gem::Version
|
246
261
|
version: '0'
|
247
262
|
requirements: []
|
248
|
-
|
249
|
-
|
250
|
-
signing_key:
|
263
|
+
rubygems_version: 3.2.6
|
264
|
+
signing_key:
|
251
265
|
specification_version: 4
|
252
266
|
summary: Handler of Darwin Core Archive files
|
253
267
|
test_files:
|
@@ -262,7 +276,7 @@ test_files:
|
|
262
276
|
- spec/files/data_with_quotes.tar.gz
|
263
277
|
- spec/files/eml.xml
|
264
278
|
- spec/files/empty_coreid.tar.gz
|
265
|
-
- spec/files/file with characters(3).gz
|
279
|
+
- spec/files/file with characters(3).tar.gz
|
266
280
|
- spec/files/flat_list.tar.gz
|
267
281
|
- spec/files/generator_eml.xml
|
268
282
|
- spec/files/generator_meta.xml
|