dwc-archive 0.7.2 → 0.7.3
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.
- data/Rakefile +1 -1
- data/VERSION +1 -1
- data/lib/dwc-archive/classification_normalizer.rb +6 -8
- data/spec/lib/dwc-archive_spec.rb +3 -2
- metadata +21 -21
data/Rakefile
CHANGED
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.7.
|
1
|
+
0.7.3
|
@@ -60,7 +60,7 @@ class DarwinCore
|
|
60
60
|
def get_canonical_name(a_scientific_name)
|
61
61
|
a_scientific_name.force_encoding('utf-8')
|
62
62
|
canonical_name = @parser.parse(a_scientific_name, :canonical_only => true)
|
63
|
-
canonical_name.to_s.empty? ? a_scientific_name : canonical_name
|
63
|
+
canonical_name.to_s.empty? ? a_scientific_name : canonical_name
|
64
64
|
end
|
65
65
|
|
66
66
|
def get_fields(element)
|
@@ -89,10 +89,10 @@ class DarwinCore
|
|
89
89
|
def set_scientific_name(row, fields)
|
90
90
|
row[fields[:scientificname]] = 'N/A' unless row[fields[:scientificname]]
|
91
91
|
canonical_name = ''
|
92
|
-
scientific_name = row[fields[:scientificname]].strip
|
92
|
+
scientific_name = row[fields[:scientificname]].strip.force_encoding('utf-8')
|
93
93
|
if separate_canonical_and_authorship?(row, fields)
|
94
|
-
canonical_name = row[fields[:scientificname]].strip
|
95
|
-
scientific_name += " #{row[fields[:scientificnameauthorship]].strip}"
|
94
|
+
canonical_name = row[fields[:scientificname]].strip.force_encoding('utf-8')
|
95
|
+
scientific_name += " #{row[fields[:scientificnameauthorship]].strip.force_encoding('utf-8')}"
|
96
96
|
else
|
97
97
|
canonical_name = get_canonical_name(row[fields[:scientificname]])
|
98
98
|
end
|
@@ -124,8 +124,8 @@ class DarwinCore
|
|
124
124
|
else
|
125
125
|
taxon = @normalized_data[r[@core_fields[:id]]] ? @normalized_data[r[@core_fields[:id]]] : @normalized_data[r[@core_fields[:id]]] = DarwinCore::TaxonNormalized.new
|
126
126
|
taxon.id = r[@core_fields[:id]]
|
127
|
-
taxon.current_name = r[@core_fields[:scientificname]]
|
128
|
-
taxon.current_name_canonical = r[@core_fields[:canonicalname]]
|
127
|
+
taxon.current_name = r[@core_fields[:scientificname]]
|
128
|
+
taxon.current_name_canonical = r[@core_fields[:canonicalname]]
|
129
129
|
taxon.parent_id = r[parent_id]
|
130
130
|
taxon.rank = r[@core_fields[:taxonrank]] if @core_fields[:taxonrank]
|
131
131
|
taxon.status = r[@core_fields[:taxonomicstatus]] if @core_fields[:taxonomicstatus]
|
@@ -248,5 +248,3 @@ class DarwinCore
|
|
248
248
|
|
249
249
|
end
|
250
250
|
end
|
251
|
-
|
252
|
-
|
@@ -120,9 +120,11 @@ describe DarwinCore do
|
|
120
120
|
it "should be able work with files which have scientificNameAuthorship" do
|
121
121
|
file = File.join(@file_dir, 'sci_name_authorship.tar.gz')
|
122
122
|
dwc = DarwinCore.new(file)
|
123
|
-
$lala = 1
|
124
123
|
cn = DarwinCore::ClassificationNormalizer.new(dwc)
|
125
124
|
norm = cn.normalize
|
125
|
+
path_encodings = norm.map {|taxon_id, taxon| taxon.classification_path}.flatten.map { |name| name.encoding.to_s }.uniq
|
126
|
+
path_encodings.size.should == 1
|
127
|
+
path_encodings[0].should == "UTF-8"
|
126
128
|
taxa = norm.select{|k,v| v.current_name_canonical.match " "}.select{|k,v| [v.current_name.split(" ").size > v.current_name_canonical.split(" ").size]}
|
127
129
|
taxa.size.should == 507
|
128
130
|
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}
|
@@ -132,7 +134,6 @@ describe DarwinCore do
|
|
132
134
|
it "should be able work with files which repeat scientificNameAuthorship value in scientificName field" do
|
133
135
|
file = File.join(@file_dir, 'sci_name_authorship_dup.tar.gz')
|
134
136
|
dwc = DarwinCore.new(file)
|
135
|
-
$lala = 1
|
136
137
|
norm = dwc.normalize_classification
|
137
138
|
taxa = norm.select{|k,v| v.current_name_canonical.match " "}.select{|k,v| [v.current_name.split(" ").size > v.current_name_canonical.split(" ").size]}
|
138
139
|
taxa.size.should == 507
|
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: 0.7.
|
4
|
+
version: 0.7.3
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -13,7 +13,7 @@ date: 2011-11-16 00:00:00.000000000Z
|
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: parsley-store
|
16
|
-
requirement: &
|
16
|
+
requirement: &70195181105880 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ~>
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: 0.3.0
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *70195181105880
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: rspec
|
27
|
-
requirement: &
|
27
|
+
requirement: &70195181104820 !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: *70195181104820
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70195181104200 !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: *70195181104200
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: cucumber
|
49
|
-
requirement: &
|
49
|
+
requirement: &70195181103720 !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: *70195181103720
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: bundler
|
60
|
-
requirement: &
|
60
|
+
requirement: &70195181103100 !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: *70195181103100
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: jeweler
|
71
|
-
requirement: &
|
71
|
+
requirement: &70195181102480 !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: *70195181102480
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: ruby-debug19
|
82
|
-
requirement: &
|
82
|
+
requirement: &70195181102000 !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: *70195181102000
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: parsley-store
|
93
|
-
requirement: &
|
93
|
+
requirement: &70195181101520 !ruby/object:Gem::Requirement
|
94
94
|
none: false
|
95
95
|
requirements:
|
96
96
|
- - ! '>='
|
@@ -98,10 +98,10 @@ dependencies:
|
|
98
98
|
version: 0.3.0
|
99
99
|
type: :runtime
|
100
100
|
prerelease: false
|
101
|
-
version_requirements: *
|
101
|
+
version_requirements: *70195181101520
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: rspec
|
104
|
-
requirement: &
|
104
|
+
requirement: &70195181101020 !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: *70195181101020
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: cucumber
|
115
|
-
requirement: &
|
115
|
+
requirement: &70195181100540 !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: *70195181100540
|
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.
|