dwca_hunter 0.5.3 → 0.7.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.byebug_history +37 -0
- data/.gitignore +5 -0
- data/.rubocop.yml +11 -2
- data/.ruby-version +1 -1
- data/Gemfile.lock +90 -84
- data/LICENSE.txt +1 -1
- data/README.md +1 -1
- data/dwca_hunter.gemspec +13 -12
- data/exe/dwcahunter +1 -5
- data/lib/dwca_hunter.rb +33 -0
- data/lib/dwca_hunter/resource.rb +8 -3
- data/lib/dwca_hunter/resources/aos-birds.rb +143 -0
- data/lib/dwca_hunter/resources/arctos.rb +115 -149
- data/lib/dwca_hunter/resources/clements.rb +151 -0
- data/lib/dwca_hunter/resources/freebase.rb +51 -49
- data/lib/dwca_hunter/resources/how-moore-birds.rb +168 -0
- data/lib/dwca_hunter/resources/index-fungorum.rb +131 -0
- data/lib/dwca_hunter/resources/ioc_word_bird.rb +200 -0
- data/lib/dwca_hunter/resources/ion.rb +98 -0
- data/lib/dwca_hunter/resources/ipni.rb +3 -2
- data/lib/dwca_hunter/resources/itis.rb +99 -99
- data/lib/dwca_hunter/resources/mammal_divdb.rb +186 -0
- data/lib/dwca_hunter/resources/mammal_species.rb +3 -3
- data/lib/dwca_hunter/resources/mcz.rb +123 -0
- data/lib/dwca_hunter/resources/ncbi.rb +22 -23
- data/lib/dwca_hunter/resources/opentree.rb +5 -5
- data/lib/dwca_hunter/resources/paleobiodb.rb +193 -0
- data/lib/dwca_hunter/resources/paleodb_harvester.rb +140 -0
- data/lib/dwca_hunter/resources/sherborn.rb +91 -0
- data/lib/dwca_hunter/resources/wikispecies.rb +166 -184
- data/lib/dwca_hunter/version.rb +1 -1
- metadata +54 -32
- data/ipni.csv.gz +0 -0
- data/ipniWebName.csv.xz?dl=1 +0 -0
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 26106d03a805f473871c3092a84b8d0498f991ff809a7e3f259f1e20d29bca80
|
4
|
+
data.tar.gz: 28ac068cf264870f67ffdc6697801c683ffec0e101c582ddbd50aa77b7831b8f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3a1e49e6db3aa0bb79616a512feb8c05438f3534d6c7bdd43a0ae32981e32f83ccd74bdcd682130bdf044dd893e0017eeddf533b170109338bb8d95f0379e2b7
|
7
|
+
data.tar.gz: 35bb769a822639d26380ad70db0b7aeed22483ce7184e62b7fad38c8d5c3b7ab5ea3b82e3dce00bb012bcc18e719077c2c3bb4a2b53830f7babd693c26aa2caf
|
data/.byebug_history
CHANGED
@@ -1,3 +1,40 @@
|
|
1
|
+
q
|
2
|
+
row
|
3
|
+
data
|
4
|
+
cc
|
5
|
+
c
|
6
|
+
data
|
7
|
+
c
|
8
|
+
data
|
9
|
+
c
|
10
|
+
data
|
11
|
+
c
|
12
|
+
data
|
13
|
+
c
|
14
|
+
data
|
15
|
+
q
|
16
|
+
p n
|
17
|
+
n
|
18
|
+
q
|
19
|
+
@name_id_json[n]
|
20
|
+
n = row[:acc_name].to_sym
|
21
|
+
row[:acc_name].to_sym
|
22
|
+
row[:acc_name]
|
23
|
+
acc_id
|
24
|
+
vi acc_id
|
25
|
+
q
|
26
|
+
@name_id
|
27
|
+
acc_id
|
28
|
+
id
|
29
|
+
q
|
30
|
+
DwcaHunter.resources
|
31
|
+
q
|
32
|
+
DwcaHunter.resources
|
33
|
+
q
|
34
|
+
res.size
|
35
|
+
res.len
|
36
|
+
res
|
37
|
+
trd
|
1
38
|
exit
|
2
39
|
pp row
|
3
40
|
require "pp"
|
data/.gitignore
CHANGED
data/.rubocop.yml
CHANGED
@@ -1,5 +1,6 @@
|
|
1
1
|
AllCops:
|
2
|
-
|
2
|
+
NewCops: disable
|
3
|
+
TargetRubyVersion: 3.0.0
|
3
4
|
Exclude:
|
4
5
|
- bin/**/*
|
5
6
|
- db/**/*
|
@@ -27,7 +28,15 @@ Metrics/ClassLength:
|
|
27
28
|
Metrics/MethodLength:
|
28
29
|
Enabled: false
|
29
30
|
|
31
|
+
Metrics/AbcSize:
|
32
|
+
Enabled: false
|
33
|
+
|
34
|
+
Metrics/PerceivedComplexity:
|
35
|
+
Enabled: false
|
36
|
+
|
37
|
+
|
38
|
+
|
30
39
|
Naming/FileName:
|
31
40
|
Exclude:
|
32
41
|
- Gemfile
|
33
|
-
- Rakefile
|
42
|
+
- Rakefile
|
data/.ruby-version
CHANGED
@@ -1 +1 @@
|
|
1
|
-
|
1
|
+
3.0.0
|
data/Gemfile.lock
CHANGED
@@ -1,140 +1,146 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
dwca_hunter (0.
|
5
|
-
biodiversity (~>
|
6
|
-
dwc-archive (~> 1.
|
4
|
+
dwca_hunter (0.7.2)
|
5
|
+
biodiversity (~> 5.1.2)
|
6
|
+
dwc-archive (~> 1.1.3)
|
7
7
|
gn_uuid (~> 0.5)
|
8
8
|
htmlentities (~> 4.3)
|
9
|
-
nokogiri (~> 1.
|
10
|
-
rest-client (~> 2.
|
9
|
+
nokogiri (~> 1.11)
|
10
|
+
rest-client (~> 2.1)
|
11
11
|
ruby-xz (~> 1.0)
|
12
|
-
|
12
|
+
rubyzip (~> 2.3)
|
13
|
+
thor (~> 1.1)
|
13
14
|
|
14
15
|
GEM
|
15
16
|
remote: http://rubygems.org/
|
16
17
|
specs:
|
17
|
-
ast (2.4.
|
18
|
-
backport (
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
byebug (10.0.2)
|
25
|
-
coveralls (0.8.22)
|
18
|
+
ast (2.4.2)
|
19
|
+
backport (1.1.2)
|
20
|
+
benchmark (0.1.1)
|
21
|
+
biodiversity (5.1.2)
|
22
|
+
ffi (~> 1.14)
|
23
|
+
byebug (11.1.3)
|
24
|
+
coveralls (0.8.23)
|
26
25
|
json (>= 1.8, < 3)
|
27
26
|
simplecov (~> 0.16.1)
|
28
27
|
term-ansicolor (~> 1.3)
|
29
|
-
thor (
|
28
|
+
thor (>= 0.19.4, < 2.0)
|
30
29
|
tins (~> 1.6)
|
31
|
-
diff-lcs (1.
|
32
|
-
docile (1.3.
|
30
|
+
diff-lcs (1.4.4)
|
31
|
+
docile (1.3.5)
|
33
32
|
domain_name (0.5.20190701)
|
34
33
|
unf (>= 0.0.5, < 1.0.0)
|
35
|
-
dwc-archive (1.
|
36
|
-
|
37
|
-
|
34
|
+
dwc-archive (1.1.3)
|
35
|
+
biodiversity (~> 5.1.2)
|
36
|
+
nokogiri (~> 1.11)
|
37
|
+
e2mmap (0.1.0)
|
38
|
+
ffi (1.14.2)
|
38
39
|
gn_uuid (0.5.1)
|
39
40
|
htmlentities (4.3.4)
|
40
41
|
http-accept (1.7.0)
|
41
42
|
http-cookie (1.0.3)
|
42
43
|
domain_name (~> 0.5)
|
43
|
-
jaro_winkler (1.5.
|
44
|
-
json (2.
|
45
|
-
kramdown (
|
46
|
-
|
44
|
+
jaro_winkler (1.5.4)
|
45
|
+
json (2.5.1)
|
46
|
+
kramdown (2.3.0)
|
47
|
+
rexml
|
48
|
+
kramdown-parser-gfm (1.1.0)
|
49
|
+
kramdown (~> 2.0)
|
50
|
+
mime-types (3.3.1)
|
47
51
|
mime-types-data (~> 3.2015)
|
48
|
-
mime-types-data (3.
|
49
|
-
mini_portile2 (2.
|
52
|
+
mime-types-data (3.2020.1104)
|
53
|
+
mini_portile2 (2.5.0)
|
50
54
|
netrc (0.11.0)
|
51
|
-
nokogiri (1.
|
52
|
-
mini_portile2 (~> 2.
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
redis (~> 3.0)
|
59
|
-
polyglot (0.3.5)
|
60
|
-
powerpack (0.1.2)
|
61
|
-
psych (3.1.0)
|
55
|
+
nokogiri (1.11.1)
|
56
|
+
mini_portile2 (~> 2.5.0)
|
57
|
+
racc (~> 1.4)
|
58
|
+
parallel (1.20.1)
|
59
|
+
parser (3.0.0.0)
|
60
|
+
ast (~> 2.4.1)
|
61
|
+
racc (1.5.2)
|
62
62
|
rainbow (3.0.0)
|
63
|
-
rake (
|
64
|
-
|
63
|
+
rake (13.0.3)
|
64
|
+
regexp_parser (2.0.3)
|
65
65
|
rest-client (2.1.0)
|
66
66
|
http-accept (>= 1.7.0, < 2.0)
|
67
67
|
http-cookie (>= 1.0.2, < 2.0)
|
68
68
|
mime-types (>= 1.16, < 4.0)
|
69
69
|
netrc (~> 0.8)
|
70
|
-
reverse_markdown (
|
70
|
+
reverse_markdown (2.0.0)
|
71
71
|
nokogiri
|
72
|
-
|
73
|
-
|
74
|
-
rspec-
|
75
|
-
rspec-
|
76
|
-
|
77
|
-
|
78
|
-
|
72
|
+
rexml (3.2.4)
|
73
|
+
rspec (3.10.0)
|
74
|
+
rspec-core (~> 3.10.0)
|
75
|
+
rspec-expectations (~> 3.10.0)
|
76
|
+
rspec-mocks (~> 3.10.0)
|
77
|
+
rspec-core (3.10.1)
|
78
|
+
rspec-support (~> 3.10.0)
|
79
|
+
rspec-expectations (3.10.1)
|
79
80
|
diff-lcs (>= 1.2.0, < 2.0)
|
80
|
-
rspec-support (~> 3.
|
81
|
-
rspec-mocks (3.
|
81
|
+
rspec-support (~> 3.10.0)
|
82
|
+
rspec-mocks (3.10.1)
|
82
83
|
diff-lcs (>= 1.2.0, < 2.0)
|
83
|
-
rspec-support (~> 3.
|
84
|
-
rspec-support (3.
|
85
|
-
rubocop (
|
86
|
-
jaro_winkler (~> 1.5.1)
|
84
|
+
rspec-support (~> 3.10.0)
|
85
|
+
rspec-support (3.10.1)
|
86
|
+
rubocop (1.9.0)
|
87
87
|
parallel (~> 1.10)
|
88
|
-
parser (>=
|
89
|
-
powerpack (~> 0.1)
|
90
|
-
psych (>= 3.1.0)
|
88
|
+
parser (>= 3.0.0.0)
|
91
89
|
rainbow (>= 2.2.2, < 4.0)
|
90
|
+
regexp_parser (>= 1.8, < 3.0)
|
91
|
+
rexml
|
92
|
+
rubocop-ast (>= 1.2.0, < 2.0)
|
92
93
|
ruby-progressbar (~> 1.7)
|
93
|
-
unicode-display_width (
|
94
|
-
|
94
|
+
unicode-display_width (>= 1.4.0, < 3.0)
|
95
|
+
rubocop-ast (1.4.1)
|
96
|
+
parser (>= 2.7.1.5)
|
97
|
+
ruby-progressbar (1.11.0)
|
95
98
|
ruby-xz (1.0.0)
|
99
|
+
rubyzip (2.3.0)
|
96
100
|
simplecov (0.16.1)
|
97
101
|
docile (~> 1.1)
|
98
102
|
json (>= 1.8, < 3)
|
99
103
|
simplecov-html (~> 0.10.0)
|
100
104
|
simplecov-html (0.10.2)
|
101
|
-
solargraph (0.
|
102
|
-
backport (~>
|
103
|
-
|
105
|
+
solargraph (0.40.2)
|
106
|
+
backport (~> 1.1)
|
107
|
+
benchmark
|
108
|
+
bundler (>= 1.17.2)
|
109
|
+
e2mmap
|
104
110
|
jaro_winkler (~> 1.5)
|
105
|
-
kramdown (~>
|
106
|
-
parser (~>
|
107
|
-
|
108
|
-
|
109
|
-
|
111
|
+
kramdown (~> 2.3)
|
112
|
+
kramdown-parser-gfm (~> 1.1)
|
113
|
+
parser (~> 3.0)
|
114
|
+
reverse_markdown (>= 1.0.5, < 3)
|
115
|
+
rubocop (>= 0.52)
|
116
|
+
thor (~> 1.0)
|
110
117
|
tilt (~> 2.0)
|
111
|
-
yard (~> 0.9)
|
118
|
+
yard (~> 0.9, >= 0.9.24)
|
119
|
+
sync (0.5.0)
|
112
120
|
term-ansicolor (1.7.1)
|
113
121
|
tins (~> 1.0)
|
114
|
-
thor (
|
115
|
-
tilt (2.0.
|
116
|
-
tins (1.
|
117
|
-
|
118
|
-
polyglot (~> 0.3)
|
122
|
+
thor (1.1.0)
|
123
|
+
tilt (2.0.10)
|
124
|
+
tins (1.28.0)
|
125
|
+
sync
|
119
126
|
unf (0.1.4)
|
120
127
|
unf_ext
|
121
|
-
unf_ext (0.0.7.
|
122
|
-
unicode-display_width (
|
123
|
-
|
124
|
-
yard (0.9.20)
|
128
|
+
unf_ext (0.0.7.7)
|
129
|
+
unicode-display_width (2.0.0)
|
130
|
+
yard (0.9.26)
|
125
131
|
|
126
132
|
PLATFORMS
|
127
133
|
ruby
|
128
134
|
|
129
135
|
DEPENDENCIES
|
130
|
-
bundler (~> 2.
|
131
|
-
byebug (~>
|
136
|
+
bundler (~> 2.2)
|
137
|
+
byebug (~> 11.1)
|
132
138
|
coveralls (~> 0.8)
|
133
139
|
dwca_hunter!
|
134
|
-
rake (~>
|
135
|
-
rspec (~> 3.
|
136
|
-
rubocop (~>
|
137
|
-
solargraph (~> 0.
|
140
|
+
rake (~> 13.0)
|
141
|
+
rspec (~> 3.10)
|
142
|
+
rubocop (~> 1.9)
|
143
|
+
solargraph (~> 0.40)
|
138
144
|
|
139
145
|
BUNDLED WITH
|
140
|
-
2.
|
146
|
+
2.2.7
|
data/LICENSE.txt
CHANGED
data/README.md
CHANGED
@@ -32,7 +32,7 @@ See dwca_hunter/bin/dwca-hunt.rb as a example how to use the code.
|
|
32
32
|
|
33
33
|
## Copyright
|
34
34
|
|
35
|
-
Copyright (c) 2011-
|
35
|
+
Copyright (c) 2011-2020 Dmitry Mozzherin. See LICENSE.txt for further details.
|
36
36
|
|
37
37
|
[code-climate-img]: https://codeclimate.com/badge.png
|
38
38
|
[code-climate]: https://codeclimate.com/github/GlobalNamesArchitecture/dwca_hunter
|
data/dwca_hunter.gemspec
CHANGED
@@ -6,7 +6,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
|
6
6
|
require "dwca_hunter/version"
|
7
7
|
|
8
8
|
Gem::Specification.new do |gem|
|
9
|
-
gem.required_ruby_version = ">=
|
9
|
+
gem.required_ruby_version = ">= 3.0.0"
|
10
10
|
gem.name = "dwca_hunter"
|
11
11
|
gem.version = DwcaHunter.version
|
12
12
|
gem.license = "MIT"
|
@@ -26,20 +26,21 @@ Gem::Specification.new do |gem|
|
|
26
26
|
gem.executables = gem.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
27
27
|
gem.require_paths = ["lib"]
|
28
28
|
|
29
|
-
gem.add_dependency "biodiversity", "~>
|
30
|
-
gem.add_dependency "dwc-archive", "~> 1.
|
29
|
+
gem.add_dependency "biodiversity", "~> 5.1.2"
|
30
|
+
gem.add_dependency "dwc-archive", "~> 1.1.3"
|
31
31
|
gem.add_dependency "gn_uuid", "~> 0.5"
|
32
32
|
gem.add_dependency "htmlentities", "~> 4.3"
|
33
|
-
gem.add_dependency "nokogiri", "~> 1.
|
34
|
-
gem.add_dependency "rest-client", "~> 2.
|
33
|
+
gem.add_dependency "nokogiri", "~> 1.11"
|
34
|
+
gem.add_dependency "rest-client", "~> 2.1"
|
35
35
|
gem.add_dependency "ruby-xz", "~> 1.0"
|
36
|
-
gem.add_dependency "
|
36
|
+
gem.add_dependency "rubyzip", "~> 2.3"
|
37
|
+
gem.add_dependency "thor", "~> 1.1"
|
37
38
|
|
38
|
-
gem.add_development_dependency "bundler", "~> 2.
|
39
|
-
gem.add_development_dependency "byebug", "~>
|
39
|
+
gem.add_development_dependency "bundler", "~> 2.2"
|
40
|
+
gem.add_development_dependency "byebug", "~> 11.1"
|
40
41
|
gem.add_development_dependency "coveralls", "~> 0.8"
|
41
|
-
gem.add_development_dependency "rake", "~>
|
42
|
-
gem.add_development_dependency "rspec", "~> 3.
|
43
|
-
gem.add_development_dependency "rubocop", "~>
|
44
|
-
gem.add_development_dependency "solargraph", "~> 0.
|
42
|
+
gem.add_development_dependency "rake", "~> 13.0"
|
43
|
+
gem.add_development_dependency "rspec", "~> 3.10"
|
44
|
+
gem.add_development_dependency "rubocop", "~> 1.9"
|
45
|
+
gem.add_development_dependency "solargraph", "~> 0.40"
|
45
46
|
end
|
data/exe/dwcahunter
CHANGED
@@ -37,9 +37,7 @@ class DwcaHunterCLI < Thor
|
|
37
37
|
res = []
|
38
38
|
DwcaHunter.resources.each do |resource|
|
39
39
|
r = resource.new
|
40
|
-
if add_resource?(search, r)
|
41
|
-
res << { n: nil, command: r.command, resource: r.title }
|
42
|
-
end
|
40
|
+
res << { n: nil, command: r.command, resource: r.title } if add_resource?(search, r)
|
43
41
|
end
|
44
42
|
res.sort_by { |r| r[:command] }.each_with_object([]) do |r, a|
|
45
43
|
r[:n] = a.size + 1
|
@@ -53,7 +51,6 @@ class DwcaHunterCLI < Thor
|
|
53
51
|
resource.abbr =~ /#{search}/i)
|
54
52
|
end
|
55
53
|
|
56
|
-
# rubocop:disable Metrics/AbcSize
|
57
54
|
def print_table(data)
|
58
55
|
table = [data.first.keys.map { |k| k.to_s.capitalize }] + data.map(&:values)
|
59
56
|
widths = table_widths(table)
|
@@ -61,7 +58,6 @@ class DwcaHunterCLI < Thor
|
|
61
58
|
format = widths.collect { |n| "%-#{n}s" }.join(" ")
|
62
59
|
table.each { |line| printf " #{format} \n", *line }
|
63
60
|
end
|
64
|
-
# rubocop:enable Metrics/AbcSize
|
65
61
|
|
66
62
|
def table_widths(table)
|
67
63
|
table.each_with_object([]) do |line, widths|
|
data/lib/dwca_hunter.rb
CHANGED
@@ -7,11 +7,13 @@ require "dwca_hunter/resource"
|
|
7
7
|
require "fileutils"
|
8
8
|
require "htmlentities"
|
9
9
|
require "json"
|
10
|
+
require "zip"
|
10
11
|
require "logger"
|
11
12
|
require "net/http"
|
12
13
|
require "rest_client"
|
13
14
|
require "tmpdir"
|
14
15
|
require "uri"
|
16
|
+
require "cgi"
|
15
17
|
|
16
18
|
Dir[File.join(__dir__, "dwca_hunter", "*.rb")].
|
17
19
|
each { |f| require f }
|
@@ -51,5 +53,36 @@ module DwcaHunter
|
|
51
53
|
c < Resource
|
52
54
|
end
|
53
55
|
end
|
56
|
+
|
57
|
+
def normalize_authors(auth)
|
58
|
+
reg = Regexp.new(/^(\(?)(.*?)(([\s,)][^[:upper:]]*)?$)/)
|
59
|
+
auth = auth.gsub(/duPont/, "du Pont")
|
60
|
+
match = reg.match(auth)
|
61
|
+
return auth if match.nil?
|
62
|
+
|
63
|
+
a1, a2, a3 = match[1..3]
|
64
|
+
a2mod = a2.gsub("&", ",")
|
65
|
+
ary2 = a2mod.split(",").map(&:strip)
|
66
|
+
a2 = move_initials(ary2) if ary2.size > 1
|
67
|
+
"#{a1}#{a2}#{a3}"
|
68
|
+
end
|
69
|
+
|
70
|
+
def move_initials(ary)
|
71
|
+
res = []
|
72
|
+
ary.each do |a|
|
73
|
+
if res.empty?
|
74
|
+
res << a
|
75
|
+
next
|
76
|
+
end
|
77
|
+
match = /^([[:upper:]]{1,4})(\sJr)?$/.match(a)
|
78
|
+
if !match.nil?
|
79
|
+
initialls = match[1].split("").join(". ")
|
80
|
+
res[-1] = "#{initialls}. #{res[-1]}#{match[2]}"
|
81
|
+
else
|
82
|
+
res << a
|
83
|
+
end
|
84
|
+
end
|
85
|
+
res.size == 1 ? res[0] : "#{res[0..-2].join(', ')} & #{res[-1]}"
|
86
|
+
end
|
54
87
|
end
|
55
88
|
end
|