dwc-archive 0.5.18 → 0.6.0
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.
- data/VERSION +1 -1
- data/lib/dwc-archive/classification_normalizer.rb +18 -2
- data/spec/files/sci_name_authorship_dup.tar.gz +0 -0
- data/spec/lib/dwc-archive_spec.rb +22 -10
- metadata +22 -21
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.
|
1
|
+
0.6.0
|
@@ -89,13 +89,29 @@ class DarwinCore
|
|
89
89
|
|
90
90
|
def set_scientific_name(row, fields)
|
91
91
|
row[fields[:scientificname]] = 'N/A' unless row[fields[:scientificname]]
|
92
|
-
canonical_name =
|
92
|
+
canonical_name = ''
|
93
|
+
scientific_name = row[fields[:scientificname]].strip
|
94
|
+
if separate_canonical_and_authorship?(row, fields)
|
95
|
+
canonical_name = row[fields[:scientificname]].strip
|
96
|
+
scientific_name += " #{row[fields[:scientificnameauthorship]].strip}"
|
97
|
+
else
|
98
|
+
canonical_name = get_canonical_name(row[fields[:scientificname]])
|
99
|
+
end
|
93
100
|
fields[:canonicalname] = row.size
|
94
101
|
row << canonical_name
|
95
|
-
scientific_name = row[fields[:scientificname]].strip
|
96
102
|
row[fields[:scientificname]] = scientific_name
|
97
103
|
end
|
98
104
|
|
105
|
+
def separate_canonical_and_authorship?(row, fields)
|
106
|
+
authorship = ''
|
107
|
+
if fields[:scientificnameauthorship]
|
108
|
+
authorship = row[fields[:scientificnameauthorship]].to_s.strip
|
109
|
+
end
|
110
|
+
!(authorship.empty? || row[fields[:scientificname]].index(authorship))
|
111
|
+
end
|
112
|
+
|
113
|
+
|
114
|
+
|
99
115
|
def ingest_core
|
100
116
|
raise RuntimeError, "Darwin Core core fields must contain taxon id and scientific name" unless (@core_fields[:id] && @core_fields[:scientificname])
|
101
117
|
@dwc.core.read do |rows|
|
Binary file
|
@@ -101,16 +101,28 @@ describe DarwinCore do
|
|
101
101
|
nodes_with_syn.first[1].synonyms.first.status.should == 'synonym'
|
102
102
|
end
|
103
103
|
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
104
|
+
it "should be able work with files which have scientificNameAuthorship" do
|
105
|
+
file = File.join(@file_dir, 'sci_name_authorship.tar.gz')
|
106
|
+
dwc = DarwinCore.new(file)
|
107
|
+
$lala = 1
|
108
|
+
norm = dwc.normalize_classification
|
109
|
+
require 'ruby-debug'; debugger
|
110
|
+
taxa = norm.select{|k,v| v.current_name_canonical.match " "}.select{|k,v| [v.current_name.split(" ").size > v.current_name_canonical.split(" ").size]}
|
111
|
+
taxa.size.should == 507
|
112
|
+
syn = norm.select{|k,v| v.synonyms.size > 0}.map {|k,v| v.synonyms}.flatten.select {|s| s.name.split(" ").size > s.canonical_name.split(" ").size}
|
113
|
+
syn.size.should == 50
|
114
|
+
end
|
115
|
+
|
116
|
+
it "should be able work with files which repeat scientificNameAuthorship value in scientificName field" do
|
117
|
+
file = File.join(@file_dir, 'sci_name_authorship_dup.tar.gz')
|
118
|
+
dwc = DarwinCore.new(file)
|
119
|
+
$lala = 1
|
120
|
+
norm = dwc.normalize_classification
|
121
|
+
taxa = norm.select{|k,v| v.current_name_canonical.match " "}.select{|k,v| [v.current_name.split(" ").size > v.current_name_canonical.split(" ").size]}
|
122
|
+
taxa.size.should == 507
|
123
|
+
syn = norm.select{|k,v| v.synonyms.size > 0}.map {|k,v| v.synonyms}.flatten.select {|s| s.name.split(" ").size > s.canonical_name.split(" ").size}
|
124
|
+
syn.size.should == 50
|
125
|
+
end
|
114
126
|
|
115
127
|
it "should be able to get language and locality fields for vernacular names" do
|
116
128
|
file = File.join(@file_dir, 'language_locality.tar.gz')
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dwc-archive
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.6.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -13,7 +13,7 @@ date: 2011-11-04 00:00:00.000000000Z
|
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: parsley-store
|
16
|
-
requirement: &
|
16
|
+
requirement: &70322001068080 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *70322001068080
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: rspec
|
27
|
-
requirement: &
|
27
|
+
requirement: &70322001067600 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ~>
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: 2.3.0
|
33
33
|
type: :development
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *70322001067600
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70322001067120 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>='
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0'
|
44
44
|
type: :development
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *70322001067120
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: cucumber
|
49
|
-
requirement: &
|
49
|
+
requirement: &70322001066640 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :development
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *70322001066640
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: bundler
|
60
|
-
requirement: &
|
60
|
+
requirement: &70322001066140 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: 1.0.0
|
66
66
|
type: :development
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *70322001066140
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: jeweler
|
71
|
-
requirement: &
|
71
|
+
requirement: &70322001065660 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ~>
|
@@ -76,10 +76,10 @@ dependencies:
|
|
76
76
|
version: 1.6.4
|
77
77
|
type: :development
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *70322001065660
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: ruby-debug19
|
82
|
-
requirement: &
|
82
|
+
requirement: &70322001065180 !ruby/object:Gem::Requirement
|
83
83
|
none: false
|
84
84
|
requirements:
|
85
85
|
- - ! '>='
|
@@ -87,10 +87,10 @@ dependencies:
|
|
87
87
|
version: '0'
|
88
88
|
type: :development
|
89
89
|
prerelease: false
|
90
|
-
version_requirements: *
|
90
|
+
version_requirements: *70322001065180
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: parsley-store
|
93
|
-
requirement: &
|
93
|
+
requirement: &70322001064700 !ruby/object:Gem::Requirement
|
94
94
|
none: false
|
95
95
|
requirements:
|
96
96
|
- - ! '>='
|
@@ -98,10 +98,10 @@ dependencies:
|
|
98
98
|
version: 0.2.0
|
99
99
|
type: :runtime
|
100
100
|
prerelease: false
|
101
|
-
version_requirements: *
|
101
|
+
version_requirements: *70322001064700
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: rspec
|
104
|
-
requirement: &
|
104
|
+
requirement: &70322001064220 !ruby/object:Gem::Requirement
|
105
105
|
none: false
|
106
106
|
requirements:
|
107
107
|
- - ! '>='
|
@@ -109,10 +109,10 @@ dependencies:
|
|
109
109
|
version: 1.2.9
|
110
110
|
type: :development
|
111
111
|
prerelease: false
|
112
|
-
version_requirements: *
|
112
|
+
version_requirements: *70322001064220
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: cucumber
|
115
|
-
requirement: &
|
115
|
+
requirement: &70322001063720 !ruby/object:Gem::Requirement
|
116
116
|
none: false
|
117
117
|
requirements:
|
118
118
|
- - ! '>='
|
@@ -120,7 +120,7 @@ dependencies:
|
|
120
120
|
version: '0'
|
121
121
|
type: :development
|
122
122
|
prerelease: false
|
123
|
-
version_requirements: *
|
123
|
+
version_requirements: *70322001063720
|
124
124
|
description: Darwin Core Archive is the current standard exchange format for GLobal
|
125
125
|
Names Architecture modules. This gem makes it easy to incorporate files in Darwin
|
126
126
|
Core Archive format into a ruby project.
|
@@ -172,6 +172,7 @@ files:
|
|
172
172
|
- spec/files/meta.xml
|
173
173
|
- spec/files/minimal.tar.gz
|
174
174
|
- spec/files/sci_name_authorship.tar.gz
|
175
|
+
- spec/files/sci_name_authorship_dup.tar.gz
|
175
176
|
- spec/files/synonyms_in_core_accepted_name_field.tar.gz
|
176
177
|
- spec/files/synonyms_in_extension.tar.gz
|
177
178
|
- spec/files/uncompressed
|