name-spotter 0.2.4 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.byebug_history +44 -0
- data/.gitignore +51 -0
- data/.rspec +2 -0
- data/.ruby-version +1 -0
- data/.travis.yml +22 -0
- data/CHANGELOG +2 -0
- data/Gemfile +2 -22
- data/README.md +116 -0
- data/Rakefile +2 -19
- data/lib/name-spotter.rb +3 -1
- data/lib/name-spotter/monkey_patches.rb +4 -2
- data/lib/name-spotter/neti_neti_client.rb +13 -6
- data/lib/name-spotter/scientific_name.rb +3 -3
- data/lib/name-spotter/taxon_finder_client.rb +35 -24
- data/lib/name-spotter/version.rb +8 -0
- data/name-spotter.gemspec +26 -98
- data/spec/name-spotter_spec.rb +334 -131
- data/spec/scientific_name_spec.rb +14 -19
- data/spec/spec_helper.rb +2 -12
- data/tf_logic.txt +3 -3
- metadata +69 -142
- data/.rvmrc +0 -1
- data/Gemfile.lock +0 -84
- data/README.rdoc +0 -95
- data/VERSION +0 -1
- data/features/name-spotter.feature +0 -9
- data/features/step_definitions/name-spotter_steps.rb +0 -0
- data/features/support/env.rb +0 -13
data/name-spotter.gemspec
CHANGED
@@ -1,103 +1,31 @@
|
|
1
|
-
|
2
|
-
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
-
# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
|
4
|
-
# -*- encoding: utf-8 -*-
|
1
|
+
$:.push File.expand_path("../lib", __FILE__)
|
5
2
|
|
6
|
-
|
7
|
-
s.name = "name-spotter"
|
8
|
-
s.version = "0.2.4"
|
3
|
+
require "name-spotter/version"
|
9
4
|
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
".rvmrc",
|
23
|
-
"CHANGELOG",
|
24
|
-
"Gemfile",
|
25
|
-
"Gemfile.lock",
|
26
|
-
"LICENSE.txt",
|
27
|
-
"README.rdoc",
|
28
|
-
"Rakefile",
|
29
|
-
"VERSION",
|
30
|
-
"features/name-spotter.feature",
|
31
|
-
"features/step_definitions/name-spotter_steps.rb",
|
32
|
-
"features/support/env.rb",
|
33
|
-
"lib/name-spotter.rb",
|
34
|
-
"lib/name-spotter/client.rb",
|
35
|
-
"lib/name-spotter/monkey_patches.rb",
|
36
|
-
"lib/name-spotter/neti_neti_client.rb",
|
37
|
-
"lib/name-spotter/scientific_name.rb",
|
38
|
-
"lib/name-spotter/taxon_finder_client.rb",
|
39
|
-
"name-spotter.gemspec",
|
40
|
-
"spec/files/english.txt",
|
41
|
-
"spec/files/journalofentomol13pomo_0018.txt",
|
42
|
-
"spec/files/journalofentomol13pomo_0063.txt",
|
43
|
-
"spec/files/not_english.txt",
|
44
|
-
"spec/name-spotter_spec.rb",
|
45
|
-
"spec/scientific_name_spec.rb",
|
46
|
-
"spec/spec_helper.rb",
|
47
|
-
"tf_logic.txt"
|
48
|
-
]
|
49
|
-
s.homepage = "http://github.com/GlobalNamesArchitecture/name-spotter"
|
50
|
-
s.licenses = ["MIT"]
|
51
|
-
s.require_paths = ["lib"]
|
52
|
-
s.rubygems_version = "1.8.24"
|
53
|
-
s.summary = "Scientific names finder"
|
5
|
+
Gem::Specification.new do |gem|
|
6
|
+
gem.name = "name-spotter"
|
7
|
+
gem.homepage = "http://github.com/GlobalNamesArchitecture/name-spotter"
|
8
|
+
gem.version = NameSpotter::VERSION
|
9
|
+
gem.authors = ["Anthony Goddard", "Chuck Ha",
|
10
|
+
"Dmitry Mozzherin", "David Shorthouse"]
|
11
|
+
gem.license = "MIT"
|
12
|
+
gem.summary = "Scientific names finder"
|
13
|
+
gem.description = %q|The gem searches for scientific names in texts using
|
14
|
+
socket servers running TaxonFinder (by Patrick Leary)
|
15
|
+
and NetiNeti (by Lakshmi Manohar Akella)|
|
16
|
+
gem.email = "dmozzherin@gmail.com"
|
54
17
|
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
s.add_development_dependency(%q<cucumber>, [">= 0"])
|
68
|
-
s.add_development_dependency(%q<capybara>, [">= 0"])
|
69
|
-
s.add_development_dependency(%q<bundler>, [">= 0"])
|
70
|
-
s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
|
71
|
-
s.add_development_dependency(%q<debugger>, [">= 0"])
|
72
|
-
else
|
73
|
-
s.add_dependency(%q<rake>, [">= 0"])
|
74
|
-
s.add_dependency(%q<rest-client>, [">= 0"])
|
75
|
-
s.add_dependency(%q<builder>, [">= 0"])
|
76
|
-
s.add_dependency(%q<json>, [">= 0"])
|
77
|
-
s.add_dependency(%q<unicode_utils>, [">= 0"])
|
78
|
-
s.add_dependency(%q<unsupervised-language-detection>, [">= 0"])
|
79
|
-
s.add_dependency(%q<rspec>, [">= 0"])
|
80
|
-
s.add_dependency(%q<rspec-expectations>, [">= 0"])
|
81
|
-
s.add_dependency(%q<cucumber>, [">= 0"])
|
82
|
-
s.add_dependency(%q<capybara>, [">= 0"])
|
83
|
-
s.add_dependency(%q<bundler>, [">= 0"])
|
84
|
-
s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
|
85
|
-
s.add_dependency(%q<debugger>, [">= 0"])
|
86
|
-
end
|
87
|
-
else
|
88
|
-
s.add_dependency(%q<rake>, [">= 0"])
|
89
|
-
s.add_dependency(%q<rest-client>, [">= 0"])
|
90
|
-
s.add_dependency(%q<builder>, [">= 0"])
|
91
|
-
s.add_dependency(%q<json>, [">= 0"])
|
92
|
-
s.add_dependency(%q<unicode_utils>, [">= 0"])
|
93
|
-
s.add_dependency(%q<unsupervised-language-detection>, [">= 0"])
|
94
|
-
s.add_dependency(%q<rspec>, [">= 0"])
|
95
|
-
s.add_dependency(%q<rspec-expectations>, [">= 0"])
|
96
|
-
s.add_dependency(%q<cucumber>, [">= 0"])
|
97
|
-
s.add_dependency(%q<capybara>, [">= 0"])
|
98
|
-
s.add_dependency(%q<bundler>, [">= 0"])
|
99
|
-
s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
|
100
|
-
s.add_dependency(%q<debugger>, [">= 0"])
|
101
|
-
end
|
18
|
+
gem.files = `git ls-files`.split("\n")
|
19
|
+
gem.require_paths = ["lib"]
|
20
|
+
gem.add_runtime_dependency "rake", "~> 10.5"
|
21
|
+
gem.add_runtime_dependency "rest-client", "~> 1.8"
|
22
|
+
gem.add_runtime_dependency "nokogiri", "~> 1.6"
|
23
|
+
gem.add_runtime_dependency "builder", "~> 3.2"
|
24
|
+
gem.add_runtime_dependency "json", "~> 1.8"
|
25
|
+
gem.add_runtime_dependency "unicode_utils", "~> 1.4"
|
26
|
+
gem.add_runtime_dependency "unsupervised-language-detection", "~> 0.0.6"
|
27
|
+
gem.add_development_dependency "rspec", "~> 3.1"
|
28
|
+
gem.add_development_dependency "bundler", "~> 1.10"
|
29
|
+
gem.add_development_dependency "byebug", "~> 8.2"
|
102
30
|
end
|
103
31
|
|
data/spec/name-spotter_spec.rb
CHANGED
@@ -1,163 +1,366 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
3
|
-
|
4
1
|
describe "NameSpotter" do
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
@tf = NameSpotter.new(taxon_finder)
|
10
|
-
@clients = [@neti, @tf]
|
11
|
-
end
|
2
|
+
subject { NameSpotter }
|
3
|
+
let(:neti) { subject.new(subject::NetiNetiClient.new()) }
|
4
|
+
let(:tf) { subject.new(subject::TaxonFinderClient.new()) }
|
5
|
+
let(:clients) { [neti, tf] }
|
12
6
|
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
eng3 = open(File.join(File.dirname(__FILE__), 'files', 'journalofentomol13pomo_0018.txt'), 'r:utf-8').read
|
17
|
-
eng3 = open(File.join(File.dirname(__FILE__), 'files', 'journalofentomol13pomo_0063.txt'), 'r:utf-8').read
|
18
|
-
|
19
|
-
not_eng = open(File.join(File.dirname(__FILE__), 'files', 'not_english.txt'), 'r:utf-8').read
|
20
|
-
100.times do
|
21
|
-
NameSpotter.english?(eng).should be_true
|
22
|
-
NameSpotter.english?(eng2).should be_true
|
23
|
-
NameSpotter.english?(eng3).should be_false
|
24
|
-
NameSpotter.english?(not_eng).should be_false
|
7
|
+
describe ".version" do
|
8
|
+
it "returns version" do
|
9
|
+
expect(subject.version).to match /\d+\.\d+\.\d+/
|
25
10
|
end
|
26
11
|
end
|
27
12
|
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
13
|
+
describe ".english?" do
|
14
|
+
let(:eng) { read("english.txt") }
|
15
|
+
let(:eng2) { read("journalofentomol13pomo_0018.txt") }
|
16
|
+
let(:eng3) { read("journalofentomol13pomo_0063.txt") }
|
32
17
|
|
33
|
-
|
34
|
-
|
35
|
-
|
18
|
+
it "detects english" do
|
19
|
+
100.times do
|
20
|
+
expect(subject.english? eng).to be true
|
21
|
+
expect(subject.english? eng2).to be true
|
22
|
+
expect(subject.english? eng3).to be false
|
23
|
+
end
|
36
24
|
end
|
37
25
|
end
|
38
26
|
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
c.find('', 'json').should == "{\"names\":[]}"
|
44
|
-
c.find('', "xml").should == "<?xml version=\"1.0\"?>\n<names/>\n"
|
27
|
+
describe ".new" do
|
28
|
+
it "works" do
|
29
|
+
expect(neti).to be_kind_of NameSpotter
|
30
|
+
expect(tf).to be_kind_of NameSpotter
|
45
31
|
end
|
46
32
|
end
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
33
|
+
|
34
|
+
describe "#find" do
|
35
|
+
context "empty text" do
|
36
|
+
it "returns empty list" do
|
37
|
+
clients.each do |c|
|
38
|
+
expect(c.find(nil)).to eq({ names: [] })
|
39
|
+
expect(c.find(nil, 'json')).to eq "{\"names\":[]}"
|
40
|
+
expect(c.find(nil, "xml"))
|
41
|
+
.to eq "<?xml version=\"1.0\"?>\n<names/>\n"
|
42
|
+
expect(c.find('', 'json')).to eq "{\"names\":[]}"
|
43
|
+
expect(c.find('', "xml"))
|
44
|
+
.to eq "<?xml version=\"1.0\"?>\n<names/>\n"
|
45
|
+
end
|
46
|
+
end
|
53
47
|
end
|
54
|
-
end
|
55
48
|
|
56
|
-
|
57
|
-
|
58
|
-
res = @neti.find(text)[:names].map { |n| n[:scientificName] }
|
59
|
-
res.should == ["Betula alba", "Mus musculus", "B. alba", "Aranea röselii", "Varanus bitatawa"]
|
60
|
-
tf_res = @tf.find(text)
|
61
|
-
res = tf_res[:names].map { |n| n[:scientificName] }
|
62
|
-
res.should == ["Betula alba", "Mus musculus", "B[etula] alba", "Aranea röselii", "Varanus"]
|
63
|
-
end
|
49
|
+
context "text without sci names" do
|
50
|
+
let(:text) { "one two three, no scientific names" }
|
64
51
|
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
res.should == ['Xysticus canadensis', 'Pardosa moesta', 'X. canadensis']
|
75
|
-
res = @tf.find(text)[:names].map { |n| n[:scientificName] }
|
76
|
-
res.should == ['Xysticus canadensis', 'Pardosa moesta', 'X[ysticus] canadensis']
|
77
|
-
end
|
52
|
+
it "returns empty list" do
|
53
|
+
clients.each do |c|
|
54
|
+
expect(c.find(text)).to eq({ names: [] })
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
context "text with one sci name" do
|
60
|
+
let(:text) { "Pardosa moesta" }
|
78
61
|
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
res.map do |name|
|
85
|
-
verbatim = name[:verbatim]
|
86
|
-
found_name = text[name[:offsetStart]..name[:offsetEnd]]
|
87
|
-
found_name.should == verbatim
|
62
|
+
it "returns empty list" do
|
63
|
+
clients.each do |c|
|
64
|
+
expect(c.find(text)[:names].size).to eq 1
|
65
|
+
end
|
66
|
+
end
|
88
67
|
end
|
89
|
-
end
|
90
68
|
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
69
|
+
context "text with several names" do
|
70
|
+
let(:text) do
|
71
|
+
"Some text that has Betula\n alba and Mus musculus " \
|
72
|
+
"and \neven B. alba and even M. mus-\nculus and " \
|
73
|
+
"unicoded name Aranea röselii. Also it has name " \
|
74
|
+
"unknown before: Varanus bitatawa"
|
75
|
+
end
|
76
|
+
let(:text2) do
|
77
|
+
"Some another text that has Xysticus \ncanadensis and " \
|
78
|
+
"Pardosa moesta and \neven X. canadensis and even " \
|
79
|
+
"P. mo-\nesta."
|
80
|
+
end
|
81
|
+
|
82
|
+
it "returns names" do
|
83
|
+
res = neti.find(text)[:names].map { |n| n[:scientificName] }
|
84
|
+
expect(res).to eq ["Betula alba", "Mus musculus",
|
85
|
+
"B. alba", "Aranea röselii", "Varanus bitatawa"]
|
86
|
+
res = tf.find(text)[:names].map { |n| n[:scientificName] }
|
87
|
+
expect(res).to eq ["Betula alba", "Mus musculus",
|
88
|
+
"B[etula] alba", "Aranea röselii",
|
89
|
+
"Varanus"]
|
90
|
+
end
|
91
|
+
|
92
|
+
it "forgets previous searches" do
|
93
|
+
res = neti.find(text)[:names].map { |n| n[:scientificName] }
|
94
|
+
expect(res).to eq ["Betula alba", "Mus musculus",
|
95
|
+
"B. alba", "Aranea röselii", "Varanus bitatawa"]
|
96
|
+
res = tf.find(text)[:names].map { |n| n[:scientificName] }
|
97
|
+
expect(res).to eq ["Betula alba", "Mus musculus",
|
98
|
+
"B[etula] alba", "Aranea röselii",
|
99
|
+
"Varanus"]
|
100
|
+
res = neti.find(text2)[:names].map { |n| n[:scientificName] }
|
101
|
+
expect(res).to eq ['Xysticus canadensis', 'Pardosa moesta',
|
102
|
+
'X. canadensis']
|
103
|
+
res = tf.find(text2)[:names].map { |n| n[:scientificName] }
|
104
|
+
expect(res).to eq ['Xysticus canadensis', 'Pardosa moesta',
|
105
|
+
'X[ysticus] canadensis']
|
106
|
+
end
|
107
|
+
end
|
108
|
+
|
109
|
+
context "offsets" do
|
110
|
+
let(:text3) do
|
111
|
+
"\r\r\n>':¥/. \r\nA text with multibyte characters " \
|
112
|
+
"नेति नेति: Some text that has Betula\n alba and " \
|
113
|
+
"Mus musculus and \neven B. alba and even M. " \
|
114
|
+
"mus-\nculus. Also it has name " \
|
115
|
+
"unknown before: Varanus bitatawa species"
|
116
|
+
end
|
117
|
+
let(:text4) do
|
118
|
+
"We have to be sure that Betula\n alba and " \
|
119
|
+
"PSEUDOSCORPIONIDA and ×Inkea which is not " \
|
120
|
+
"Passeriformes. We also have another hybrid Passiflora " \
|
121
|
+
"×rosea and Aranea röselii and capitalized ARANEA " \
|
122
|
+
"RÖSELII and Pardosa\n moesta f. moesta Banks, 1892 " \
|
123
|
+
"all get their offsets"
|
124
|
+
end
|
125
|
+
let(:text5) { read "journalofentomol13pomo_0063.txt" }
|
126
|
+
|
127
|
+
it "return correct names with multibyte chars" do
|
128
|
+
# this test depends on netineti tornado server, not on
|
129
|
+
# namespotter itself. Go and fix that!
|
130
|
+
# the issue and the fix: https://github.com/mbl-cli/NetiNeti/pull/1
|
131
|
+
res = neti.find(text3)[:names]
|
132
|
+
res.map do |name|
|
133
|
+
verbatim = name[:verbatim]
|
134
|
+
found_name = text3[name[:offsetStart]..name[:offsetEnd]]
|
135
|
+
expect(found_name).to eq verbatim
|
136
|
+
end
|
137
|
+
end
|
138
|
+
|
139
|
+
it "returns offset for all names" do
|
140
|
+
res = neti.find(text4)
|
141
|
+
tf_res = tf.find(text4)
|
142
|
+
expect(res).to eq({names: [
|
143
|
+
{verbatim: "Betula\n alba", scientificName: "Betula alba",
|
144
|
+
offsetStart: 24, offsetEnd: 35},
|
145
|
+
{verbatim: "Passiflora ×rosea", scientificName: "Passiflora ×rosea",
|
146
|
+
offsetStart: 126, offsetEnd: 142},
|
147
|
+
{verbatim: "Aranea röselii", scientificName: "Aranea röselii",
|
148
|
+
offsetStart: 148, offsetEnd: 161},
|
149
|
+
{verbatim: "Pardosa\n moesta", scientificName: "Pardosa moesta",
|
150
|
+
offsetStart: 198, offsetEnd: 212}
|
151
|
+
]})
|
152
|
+
expect(tf_res).to eq({names: [
|
153
|
+
{verbatim: "Betula alba", scientificName: "Betula alba",
|
154
|
+
offsetStart: 24, offsetEnd: 35},
|
155
|
+
{verbatim: "PSEUDOSCORPIONIDA",
|
156
|
+
scientificName: "Pseudoscorpionida", offsetStart: 41,
|
157
|
+
offsetEnd: 57},
|
158
|
+
{verbatim: "Passeriformes.", scientificName: "Passeriformes",
|
159
|
+
offsetStart: 83, offsetEnd: 96},
|
160
|
+
{verbatim: "Passiflora ×rosea", scientificName: "Passiflora rosea",
|
161
|
+
offsetStart: 126, offsetEnd: 142},
|
162
|
+
{verbatim: "Aranea röselii", scientificName: "Aranea röselii",
|
163
|
+
offsetStart: 148, offsetEnd: 161},
|
164
|
+
{verbatim: "ARANEA", scientificName: "Aranea", offsetStart: 179,
|
165
|
+
offsetEnd: 184},
|
166
|
+
{verbatim: "Pardosa moesta f. moesta", scientificName:
|
167
|
+
"Pardosa moesta f. moesta", offsetStart: 198, offsetEnd: 222}
|
168
|
+
]})
|
169
|
+
end
|
170
|
+
|
171
|
+
it "makes offsets in order with netineti" do
|
172
|
+
res = neti.find(text5)
|
173
|
+
offsets = res[:names].map { |n| n[:offsetStart] }
|
174
|
+
expect(offsets).to eq offsets
|
175
|
+
expect(offsets[0]).to eq 67
|
176
|
+
end
|
177
|
+
end
|
103
178
|
end
|
104
179
|
|
105
|
-
|
106
|
-
text
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
180
|
+
context "abbreviations" do
|
181
|
+
let(:text) do
|
182
|
+
"Pardosa moesta Banks, 1892 is one spider, Schizocosa " \
|
183
|
+
"ocreata Keyserling, 1887 is a second and a third is " \
|
184
|
+
"Schizocosa saltatrix borealis. The abbreviations are P. " \
|
185
|
+
"moesta, S. ocreata, and S. saltatrix borealis is the third."
|
186
|
+
end
|
187
|
+
let(:text2) do
|
188
|
+
"Pardosa moesta! If we encounter Pardosa moesta and then P.modica " \
|
189
|
+
"another name I know is Xenopus laevis and also P.moesta. Again " \
|
190
|
+
"without space TaxonFinder should find both. And Plantago major foreva"
|
191
|
+
end
|
192
|
+
let(:text3) do
|
193
|
+
"What happens another called P. (LYCOSIDAE) is the species?"
|
194
|
+
end
|
195
|
+
|
196
|
+
it "ignores abbreviated genus before family for TaxonFinder" do
|
197
|
+
res = tf.find(text3)
|
198
|
+
expect(res[:names].size).to be 1
|
199
|
+
expect(res).to eq(
|
200
|
+
{names: [{verbatim: "(LYCOSIDAE)", scientificName: "Lycosidae",
|
201
|
+
offsetStart: 32, offsetEnd: 42}]}
|
202
|
+
)
|
203
|
+
end
|
204
|
+
|
205
|
+
it "preserves TaxonFinder expansions" do
|
206
|
+
tf_res = tf.find(text)
|
207
|
+
expect(tf_res).to eq(
|
208
|
+
{names: [
|
209
|
+
{verbatim: "Pardosa moesta", scientificName: "Pardosa moesta",
|
210
|
+
offsetStart: 0, offsetEnd: 13},
|
211
|
+
{verbatim: "Schizocosa ocreata",
|
212
|
+
scientificName: "Schizocosa ocreata", offsetStart: 42,
|
213
|
+
offsetEnd: 59},
|
214
|
+
{verbatim: "Schizocosa saltatrix borealis",
|
215
|
+
scientificName: "Schizocosa saltatrix borealis",
|
216
|
+
offsetStart: 105, offsetEnd: 133},
|
217
|
+
{verbatim: "P. moesta", scientificName: "P[ardosa] moesta",
|
218
|
+
offsetStart: 158, offsetEnd: 166},
|
219
|
+
{verbatim: "S. ocreata", scientificName: "S[chizocosa] ocreata",
|
220
|
+
offsetStart: 169, offsetEnd: 178},
|
221
|
+
{verbatim: "S. saltatrix borealis",
|
222
|
+
scientificName: "S[chizocosa] saltatrix borealis",
|
223
|
+
offsetStart: 185, offsetEnd: 205}]}
|
224
|
+
)
|
225
|
+
end
|
226
|
+
|
227
|
+
|
228
|
+
it "recognizes abbreviations no space (TF)" do
|
229
|
+
res = tf.find(text2)
|
230
|
+
expect(res).to eq(
|
231
|
+
{names: [
|
232
|
+
{verbatim: "Pardosa moesta", scientificName: "Pardosa moesta",
|
233
|
+
offsetStart: 0, offsetEnd: 13},
|
234
|
+
{verbatim: "Pardosa moesta", scientificName: "Pardosa moesta",
|
235
|
+
offsetStart: 32, offsetEnd: 45},
|
236
|
+
{verbatim: "P.modica", scientificName: "P[ardosa] modica",
|
237
|
+
offsetStart: 56, offsetEnd: 63},
|
238
|
+
{verbatim: "Xenopus laevis", scientificName: "Xenopus laevis",
|
239
|
+
offsetStart: 88, offsetEnd: 101},
|
240
|
+
{verbatim: "P.moesta", scientificName: "P[ardosa] moesta",
|
241
|
+
offsetStart: 112, offsetEnd: 119},
|
242
|
+
{verbatim: "Plantago major", scientificName: "Plantago major",
|
243
|
+
offsetStart: 176, offsetEnd: 189}]}
|
244
|
+
)
|
245
|
+
res[:names].map do |name|
|
246
|
+
verbatim = name[:verbatim]
|
247
|
+
found_name = text2[name[:offsetStart]..name[:offsetEnd]]
|
248
|
+
expect(found_name).to eq verbatim
|
249
|
+
end
|
250
|
+
end
|
111
251
|
end
|
112
252
|
|
113
|
-
|
253
|
+
context "capitalization" do
|
114
254
|
#this is a problem we are aware of
|
115
|
-
text
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
122
|
-
|
123
|
-
|
255
|
+
let(:text) do
|
256
|
+
"We need to make sure that Ophioihrix nidis and " \
|
257
|
+
"OPHTOMVXIDAE and also Ophiocynodus and especially " \
|
258
|
+
"ASTÉROCHEMIDAE and definitely STFROPHVTIDAE and may be " \
|
259
|
+
"Asleronyx excavata should all be capitalized correctly"
|
260
|
+
end
|
261
|
+
|
262
|
+
it "does not change capitalization" do
|
263
|
+
res = neti.find(text)
|
264
|
+
expect(res).to eq(
|
265
|
+
{names: [
|
266
|
+
{verbatim: "Ophioihrix nidis", scientificName: "Ophioihrix nidis",
|
267
|
+
offsetStart: 26, offsetEnd: 41},
|
268
|
+
{verbatim: "OPHTOMVXIDAE", scientificName: "OPHTOMVXIDAE",
|
269
|
+
offsetStart: 47, offsetEnd: 58},
|
270
|
+
{verbatim: "Ophiocynodus", scientificName: "Ophiocynodus",
|
271
|
+
offsetStart: 70, offsetEnd: 81},
|
272
|
+
{verbatim: "ASTÉROCHEMIDAE", scientificName: "ASTÉROCHEMIDAE",
|
273
|
+
offsetStart: 98, offsetEnd: 111},
|
274
|
+
{verbatim: "STFROPHVTIDAE", scientificName: "STFROPHVTIDAE",
|
275
|
+
offsetStart: 128, offsetEnd: 140},
|
276
|
+
{verbatim: "Asleronyx excavata", scientificName: "Asleronyx excavata",
|
277
|
+
offsetStart: 153, offsetEnd: 170}
|
278
|
+
]}
|
279
|
+
)
|
280
|
+
end
|
124
281
|
end
|
125
282
|
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
283
|
+
context "OCR errors" do
|
284
|
+
let(:pipe) do
|
285
|
+
"We need to make sure that Oph|oihrix nidis and " \
|
286
|
+
"OPHTOMVX|DAE will not break results"
|
287
|
+
end
|
288
|
+
|
289
|
+
it "substitutes | with l" do
|
290
|
+
res = neti.find(pipe)
|
291
|
+
expect(res).to eq(
|
292
|
+
{ names: [{ verbatim: "Ophloihrix nidis",
|
293
|
+
scientificName: "Ophloihrix nidis",
|
294
|
+
offsetStart: 26, offsetEnd: 41 }] }
|
295
|
+
)
|
296
|
+
end
|
130
297
|
end
|
131
298
|
|
132
|
-
|
133
|
-
text
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
|
299
|
+
context "extremely nexted infraspecies" do
|
300
|
+
let(:text) do
|
301
|
+
"If we encounter Plantago major it is ok, but if it is " \
|
302
|
+
"Plantago quercus quercus quercus quercus quercus quercus " \
|
303
|
+
"quercus quercus quercus quercus quercus quercus quercus " \
|
304
|
+
"quercus, something is probably not right. However we take " \
|
305
|
+
"Plantago quercus quercus quercus quercus quercus by some " \
|
306
|
+
"strange reason. Well, the reason is this kind of thing -- " \
|
307
|
+
"Pardosa moesta var. moesta f. moesta or something like that"
|
308
|
+
end
|
309
|
+
|
310
|
+
it "stops at five infraspecies levels" do
|
311
|
+
res = tf.find(text)
|
312
|
+
expect(res).to eq(
|
313
|
+
{names: [
|
314
|
+
{verbatim: "Plantago major", scientificName: "Plantago major",
|
315
|
+
offsetStart: 16, offsetEnd: 29},
|
316
|
+
{verbatim: "Plantago quercus quercus quercus quercus quercus",
|
317
|
+
scientificName: "Plantago quercus quercus quercus quercus quercus",
|
318
|
+
offsetStart: 225, offsetEnd: 272},
|
319
|
+
{verbatim: "Pardosa moesta var. moesta f. moesta",
|
320
|
+
scientificName: "Pardosa moesta var. moesta f. moesta",
|
321
|
+
offsetStart: 340, offsetEnd: 375}]}
|
322
|
+
)
|
323
|
+
end
|
147
324
|
end
|
148
325
|
|
149
|
-
|
150
|
-
text
|
151
|
-
|
152
|
-
|
153
|
-
|
326
|
+
context "nested names" do
|
327
|
+
let(:text) do
|
328
|
+
"What happens another called Pardosa moesta (Araneae: Lycosidae) is " \
|
329
|
+
"the species?"
|
330
|
+
end
|
331
|
+
|
332
|
+
it "(TF) handles nested names in one cycle" do
|
333
|
+
res = tf.find(text)
|
334
|
+
expect(res).to eq (
|
335
|
+
{names: [
|
336
|
+
{verbatim: "Pardosa moesta", scientificName: "Pardosa moesta",
|
337
|
+
offsetStart: 29, offsetEnd: 42},
|
338
|
+
{verbatim: "(Araneae:", scientificName: "Araneae",
|
339
|
+
offsetStart: 44, offsetEnd: 52},
|
340
|
+
{verbatim: "Lycosidae)", scientificName: "Lycosidae",
|
341
|
+
offsetStart: 54, offsetEnd: 63}]}
|
342
|
+
)
|
343
|
+
end
|
154
344
|
end
|
155
|
-
|
156
|
-
|
157
|
-
text
|
158
|
-
|
159
|
-
|
160
|
-
|
345
|
+
|
346
|
+
context "diacritics" do
|
347
|
+
let(:text) { "Mactra triangula Renieri. Fissurella nubécula Linnó." }
|
348
|
+
|
349
|
+
it "finds names with diacrictics" do
|
350
|
+
res = tf.find(text)
|
351
|
+
expect(res[:names].size).to be 2
|
352
|
+
expect(res).to eq(
|
353
|
+
{names: [
|
354
|
+
{verbatim: "Mactra triangula", scientificName: "Mactra triangula",
|
355
|
+
offsetStart: 0, offsetEnd: 15},
|
356
|
+
{verbatim: "Fissurella nubécula",
|
357
|
+
scientificName: "Fissurella nubécula",
|
358
|
+
offsetStart: 26, offsetEnd: 44}]}
|
359
|
+
)
|
360
|
+
end
|
161
361
|
end
|
162
362
|
|
363
|
+
def read(file)
|
364
|
+
File.read(File.join(__dir__, "files", file))
|
365
|
+
end
|
163
366
|
end
|