dimus-taxamatch_rb 0.5.6 → 0.5.7
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/taxamatch_rb/atomizer.rb +19 -25
- data/spec/taxamatch_rb_spec.rb +2 -1
- metadata +3 -3
@@ -12,7 +12,7 @@ module Taxamatch
|
|
12
12
|
|
13
13
|
def parse(name)
|
14
14
|
@res = {:all_authors => [], :all_years => []}
|
15
|
-
@parsed_raw =
|
15
|
+
@parsed_raw = @parser.parse(name)[:scientificName]
|
16
16
|
organize_results
|
17
17
|
end
|
18
18
|
|
@@ -24,12 +24,12 @@ module Taxamatch
|
|
24
24
|
|
25
25
|
def organize_results
|
26
26
|
pr = @parsed_raw
|
27
|
-
return nil unless pr[
|
28
|
-
d = pr[
|
29
|
-
process_node(:uninomial, d[
|
30
|
-
process_node(:genus, d[
|
31
|
-
process_node(:species, d[
|
32
|
-
process_infraspecies(d[
|
27
|
+
return nil unless pr[:parsed]
|
28
|
+
d = pr[:details][0]
|
29
|
+
process_node(:uninomial, d[:uninomial])
|
30
|
+
process_node(:genus, d[:genus])
|
31
|
+
process_node(:species, d[:species], true)
|
32
|
+
process_infraspecies(d[:infraspecies])
|
33
33
|
@res[:all_authors] = @res[:all_authors].uniq.map {|a| Taxamatch::Normalizer.normalize(a)}
|
34
34
|
@res[:all_years].uniq!
|
35
35
|
@res.keys.size > 2 ? @res : nil
|
@@ -38,9 +38,9 @@ module Taxamatch
|
|
38
38
|
def process_node(name, node, is_species = false)
|
39
39
|
return unless node
|
40
40
|
@res[name] = {}
|
41
|
-
@res[name][:epitheton] = node[
|
42
|
-
@res[name][:normalized] = Taxamatch::Normalizer.normalize(node[
|
43
|
-
@res[name][:phonetized] = Taxamatch::Phonetizer.near_match(node[
|
41
|
+
@res[name][:epitheton] = node[:epitheton]
|
42
|
+
@res[name][:normalized] = Taxamatch::Normalizer.normalize(node[:epitheton])
|
43
|
+
@res[name][:phonetized] = Taxamatch::Phonetizer.near_match(node[:epitheton], is_species)
|
44
44
|
get_authors_years(node, @res[name])
|
45
45
|
end
|
46
46
|
|
@@ -49,9 +49,9 @@ module Taxamatch
|
|
49
49
|
@res[:infraspecies] = []
|
50
50
|
node.each do |infr|
|
51
51
|
hsh = {}
|
52
|
-
hsh[:epitheton] = infr[
|
53
|
-
hsh[:normalized] = Taxamatch::Normalizer.normalize(infr[
|
54
|
-
hsh[:phonetized] = Taxamatch::Phonetizer.near_match(infr[
|
52
|
+
hsh[:epitheton] = infr[:epitheton]
|
53
|
+
hsh[:normalized] = Taxamatch::Normalizer.normalize(infr[:epitheton])
|
54
|
+
hsh[:phonetized] = Taxamatch::Phonetizer.near_match(infr[:epitheton], true)
|
55
55
|
get_authors_years(infr,hsh)
|
56
56
|
@res[:infraspecies] << hsh
|
57
57
|
end
|
@@ -60,13 +60,13 @@ module Taxamatch
|
|
60
60
|
def get_authors_years(node, res)
|
61
61
|
res[:authors] = []
|
62
62
|
res[:years] = []
|
63
|
-
[
|
63
|
+
[:basionymAuthorTeam, :combinationAuthorTeam].each do |au|
|
64
64
|
if node[au]
|
65
|
-
res[:authors] += node[au][
|
66
|
-
res[:years] << node[au][
|
67
|
-
if node[au][
|
68
|
-
res[:authors] += node[au][
|
69
|
-
res[:years] << node[au][
|
65
|
+
res[:authors] += node[au][:author]
|
66
|
+
res[:years] << node[au][:year] if node[au][:year]
|
67
|
+
if node[au][:exAuthorTeam]
|
68
|
+
res[:authors] += node[au][:exAuthorTeam][:author]
|
69
|
+
res[:years] << node[au][:exAuthorTeam][:year] if node[au][:exAuthorTeam][:year]
|
70
70
|
end
|
71
71
|
end
|
72
72
|
end
|
@@ -80,9 +80,3 @@ module Taxamatch
|
|
80
80
|
end
|
81
81
|
end
|
82
82
|
|
83
|
-
if __FILE__ == $0
|
84
|
-
require 'pp'
|
85
|
-
p = Parser.new
|
86
|
-
puts p.parse('Salmonella werahensis (Castellani) Hauduroy and Ehringer in Hauduroy 1937')
|
87
|
-
end
|
88
|
-
|
data/spec/taxamatch_rb_spec.rb
CHANGED
@@ -14,12 +14,13 @@ describe 'DamerauLevenshteinMod' do
|
|
14
14
|
end
|
15
15
|
end
|
16
16
|
|
17
|
-
describe '
|
17
|
+
describe 'Atomizer' do
|
18
18
|
before(:all) do
|
19
19
|
@parser = Taxamatch::Atomizer.new
|
20
20
|
end
|
21
21
|
|
22
22
|
it 'should parse uninomials' do
|
23
|
+
@parser.parse
|
23
24
|
@parser.parse('Betula').should == {:all_authors=>[], :all_years=>[], :uninomial=>{:epitheton=>"Betula", :normalized=>"BETULA", :phonetized=>"BITILA", :authors=>[], :years=>[], :normalized_authors=>[]}}
|
24
25
|
@parser.parse('Ærenea Lacordaire, 1872').should == {:all_authors=>["LACORDAIRE"], :all_years=>["1872"], :uninomial=>{:epitheton=>"Aerenea", :normalized=>"AERENEA", :phonetized=>"ERINIA", :authors=>["Lacordaire"], :years=>["1872"], :normalized_authors=>["LACORDAIRE"]}}
|
25
26
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dimus-taxamatch_rb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.5.
|
4
|
+
version: 0.5.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dmitry Mozzherin
|
@@ -9,7 +9,7 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2009-08-
|
12
|
+
date: 2009-08-17 00:00:00 -07:00
|
13
13
|
default_executable:
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
@@ -30,7 +30,7 @@ dependencies:
|
|
30
30
|
requirements:
|
31
31
|
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version:
|
33
|
+
version: 0.5.13
|
34
34
|
version:
|
35
35
|
description: This gem implements algorithsm for fuzzy matching scientific names developed by Tony Rees
|
36
36
|
email: dmozzherin@eol.org
|