biodiversity 1.0.10 → 3.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.rvmrc +1 -1
- data/.travis.yml +7 -0
- data/CHANGELOG +42 -0
- data/Gemfile +8 -6
- data/Gemfile.lock +33 -33
- data/README.md +167 -0
- data/Rakefile +16 -11
- data/VERSION +1 -1
- data/bin/parserver +33 -44
- data/lib/biodiversity/parser.rb +160 -33
- data/lib/biodiversity/parser/scientific_name_canonical.treetop +4 -2
- data/lib/biodiversity/parser/scientific_name_clean.treetop +479 -277
- data/lib/biodiversity/parser/scientific_name_dirty.treetop +11 -16
- data/spec/parser/scientific_name.spec.rb +63 -7
- data/spec/parser/scientific_name_clean.spec.rb +76 -24
- data/spec/parser/scientific_name_dirty.spec.rb +4 -6
- data/spec/parser/test_data.txt +132 -41
- data/spec/parser/todo.txt +27 -0
- metadata +153 -119
- data/README.rdoc +0 -99
data/spec/parser/todo.txt
CHANGED
@@ -26,3 +26,30 @@ Polypodium lineare C.Chr. f. caudatoattenuatum Takeda Polypodium
|
|
26
26
|
|
27
27
|
Rosa gallica × tomentosa var. eglandulosa R.Keller Rosa gallica
|
28
28
|
Rosa gallica × afzeliana subsp. vosagiaca forma subcomplicata R.Keller Rosa gallica
|
29
|
+
|
30
|
+
Salmonella sp. (ser.) brancaster Macdonald, Sivell, Emms and Taylor 1948
|
31
|
+
|
32
|
+
Stanhopea tigrina Bateman ex Lindl. x S. ecornuta Lem.
|
33
|
+
|
34
|
+
|
35
|
+
Junellia o'donelli Moldenke, 1946
|
36
|
+
|
37
|
+
119052670 | Human rhinovirus A11 |
|
38
|
+
|
39
|
+
Rubus idaeus monst. obtusifolius (Willd.) Focke | Rubus idaeus
|
40
|
+
|
41
|
+
Kerana var. cameroni |Kerana var
|
42
|
+
|
43
|
+
A. alba
|
44
|
+
A.alba
|
45
|
+
|
46
|
+
Bangalaia viridis sbsp. distinctemaculata Lepesme & Breuning, 1956
|
47
|
+
|
48
|
+
Clostridium sp. enrichment culture clone M4C16
|
49
|
+
|
50
|
+
|
51
|
+
000913765 Rubus x gracilidens Sudre
|
52
|
+
Rubus gracilidens | 1
|
53
|
+
|
54
|
+
|
55
|
+
Salix myrtilloides x starkeana ssp. starkeana
|
metadata
CHANGED
@@ -1,137 +1,178 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: biodiversity
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 3.0.0
|
5
5
|
prerelease:
|
6
|
-
segments:
|
7
|
-
- 1
|
8
|
-
- 0
|
9
|
-
- 10
|
10
|
-
version: 1.0.10
|
11
6
|
platform: ruby
|
12
|
-
authors:
|
7
|
+
authors:
|
13
8
|
- Dmitry Mozzherin
|
14
9
|
autorequire:
|
15
10
|
bindir: bin
|
16
11
|
cert_chain: []
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
none: false
|
23
|
-
requirements:
|
24
|
-
- -
|
25
|
-
- !ruby/object:Gem::Version
|
26
|
-
|
27
|
-
|
28
|
-
- 0
|
29
|
-
version: "0"
|
30
|
-
requirement: *id001
|
12
|
+
date: 2013-05-08 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rake
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '10.0'
|
22
|
+
type: :runtime
|
31
23
|
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '10.0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
32
31
|
name: treetop
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ~>
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '1.4'
|
33
38
|
type: :runtime
|
34
|
-
- !ruby/object:Gem::Dependency
|
35
|
-
version_requirements: &id002 !ruby/object:Gem::Requirement
|
36
|
-
none: false
|
37
|
-
requirements:
|
38
|
-
- - ">="
|
39
|
-
- !ruby/object:Gem::Version
|
40
|
-
hash: 3
|
41
|
-
segments:
|
42
|
-
- 0
|
43
|
-
version: "0"
|
44
|
-
requirement: *id002
|
45
39
|
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '1.4'
|
46
|
+
- !ruby/object:Gem::Dependency
|
46
47
|
name: parallel
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0.6'
|
54
|
+
type: :runtime
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.6'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: unicode_utils
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ~>
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '1.4'
|
47
70
|
type: :runtime
|
48
|
-
- !ruby/object:Gem::Dependency
|
49
|
-
version_requirements: &id003 !ruby/object:Gem::Requirement
|
50
|
-
none: false
|
51
|
-
requirements:
|
52
|
-
- - ">="
|
53
|
-
- !ruby/object:Gem::Version
|
54
|
-
hash: 3
|
55
|
-
segments:
|
56
|
-
- 0
|
57
|
-
version: "0"
|
58
|
-
requirement: *id003
|
59
71
|
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ~>
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '1.4'
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: debugger
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ~>
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '1.5'
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - ~>
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '1.5'
|
94
|
+
- !ruby/object:Gem::Dependency
|
60
95
|
name: jeweler
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ~>
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '1.8'
|
61
102
|
type: :development
|
62
|
-
- !ruby/object:Gem::Dependency
|
63
|
-
version_requirements: &id004 !ruby/object:Gem::Requirement
|
64
|
-
none: false
|
65
|
-
requirements:
|
66
|
-
- - ">="
|
67
|
-
- !ruby/object:Gem::Version
|
68
|
-
hash: 3
|
69
|
-
segments:
|
70
|
-
- 0
|
71
|
-
version: "0"
|
72
|
-
requirement: *id004
|
73
103
|
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ~>
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '1.8'
|
110
|
+
- !ruby/object:Gem::Dependency
|
74
111
|
name: treetop
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
115
|
+
- - ! '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
75
118
|
type: :runtime
|
76
|
-
- !ruby/object:Gem::Dependency
|
77
|
-
version_requirements: &id005 !ruby/object:Gem::Requirement
|
78
|
-
none: false
|
79
|
-
requirements:
|
80
|
-
- - ">="
|
81
|
-
- !ruby/object:Gem::Version
|
82
|
-
hash: 3
|
83
|
-
segments:
|
84
|
-
- 0
|
85
|
-
version: "0"
|
86
|
-
requirement: *id005
|
87
119
|
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
none: false
|
122
|
+
requirements:
|
123
|
+
- - ! '>='
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
126
|
+
- !ruby/object:Gem::Dependency
|
88
127
|
name: parallel
|
128
|
+
requirement: !ruby/object:Gem::Requirement
|
129
|
+
none: false
|
130
|
+
requirements:
|
131
|
+
- - ! '>='
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0'
|
89
134
|
type: :runtime
|
90
|
-
- !ruby/object:Gem::Dependency
|
91
|
-
version_requirements: &id006 !ruby/object:Gem::Requirement
|
92
|
-
none: false
|
93
|
-
requirements:
|
94
|
-
- - ">="
|
95
|
-
- !ruby/object:Gem::Version
|
96
|
-
hash: 3
|
97
|
-
segments:
|
98
|
-
- 0
|
99
|
-
version: "0"
|
100
|
-
requirement: *id006
|
101
|
-
prerelease: false
|
102
|
-
name: json
|
103
|
-
type: :runtime
|
104
|
-
- !ruby/object:Gem::Dependency
|
105
|
-
version_requirements: &id007 !ruby/object:Gem::Requirement
|
106
|
-
none: false
|
107
|
-
requirements:
|
108
|
-
- - ">="
|
109
|
-
- !ruby/object:Gem::Version
|
110
|
-
hash: 3
|
111
|
-
segments:
|
112
|
-
- 0
|
113
|
-
version: "0"
|
114
|
-
requirement: *id007
|
115
135
|
prerelease: false
|
136
|
+
version_requirements: !ruby/object:Gem::Requirement
|
137
|
+
none: false
|
138
|
+
requirements:
|
139
|
+
- - ! '>='
|
140
|
+
- !ruby/object:Gem::Version
|
141
|
+
version: '0'
|
142
|
+
- !ruby/object:Gem::Dependency
|
116
143
|
name: rspec
|
144
|
+
requirement: !ruby/object:Gem::Requirement
|
145
|
+
none: false
|
146
|
+
requirements:
|
147
|
+
- - ! '>='
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '0'
|
117
150
|
type: :development
|
151
|
+
prerelease: false
|
152
|
+
version_requirements: !ruby/object:Gem::Requirement
|
153
|
+
none: false
|
154
|
+
requirements:
|
155
|
+
- - ! '>='
|
156
|
+
- !ruby/object:Gem::Version
|
157
|
+
version: '0'
|
118
158
|
description: Tools for biodiversity informatics
|
119
159
|
email: dmozzherin@gmail.com
|
120
|
-
executables:
|
160
|
+
executables:
|
121
161
|
- nnparse
|
122
162
|
- parserver
|
123
163
|
extensions: []
|
124
|
-
|
125
|
-
extra_rdoc_files:
|
164
|
+
extra_rdoc_files:
|
126
165
|
- LICENSE
|
127
|
-
- README.
|
128
|
-
files:
|
166
|
+
- README.md
|
167
|
+
files:
|
129
168
|
- .document
|
130
169
|
- .rvmrc
|
170
|
+
- .travis.yml
|
171
|
+
- CHANGELOG
|
131
172
|
- Gemfile
|
132
173
|
- Gemfile.lock
|
133
174
|
- LICENSE
|
134
|
-
- README.
|
175
|
+
- README.md
|
135
176
|
- Rakefile
|
136
177
|
- VERSION
|
137
178
|
- bin/nnparse
|
@@ -158,36 +199,29 @@ files:
|
|
158
199
|
- spec/spec_helper.rb
|
159
200
|
homepage: http://github.com/GlobalNamesArchitecture/biodiversity
|
160
201
|
licenses: []
|
161
|
-
|
162
202
|
post_install_message:
|
163
203
|
rdoc_options: []
|
164
|
-
|
165
|
-
require_paths:
|
204
|
+
require_paths:
|
166
205
|
- lib
|
167
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
206
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
168
207
|
none: false
|
169
|
-
requirements:
|
170
|
-
- -
|
171
|
-
- !ruby/object:Gem::Version
|
172
|
-
|
173
|
-
segments:
|
208
|
+
requirements:
|
209
|
+
- - ! '>='
|
210
|
+
- !ruby/object:Gem::Version
|
211
|
+
version: '0'
|
212
|
+
segments:
|
174
213
|
- 0
|
175
|
-
|
176
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
214
|
+
hash: -3993295929745438801
|
215
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
177
216
|
none: false
|
178
|
-
requirements:
|
179
|
-
- -
|
180
|
-
- !ruby/object:Gem::Version
|
181
|
-
|
182
|
-
segments:
|
183
|
-
- 0
|
184
|
-
version: "0"
|
217
|
+
requirements:
|
218
|
+
- - ! '>='
|
219
|
+
- !ruby/object:Gem::Version
|
220
|
+
version: '0'
|
185
221
|
requirements: []
|
186
|
-
|
187
222
|
rubyforge_project:
|
188
|
-
rubygems_version: 1.8.
|
223
|
+
rubygems_version: 1.8.25
|
189
224
|
signing_key:
|
190
225
|
specification_version: 3
|
191
226
|
summary: Parser of scientific names
|
192
227
|
test_files: []
|
193
|
-
|
data/README.rdoc
DELETED
@@ -1,99 +0,0 @@
|
|
1
|
-
= Biodiversity
|
2
|
-
|
3
|
-
Parses taxonomic scientific name and breaks it into semantic elements.
|
4
|
-
|
5
|
-
== Installation
|
6
|
-
|
7
|
-
To install gem you need RubyGems >= 1.3.6
|
8
|
-
|
9
|
-
$ sudo gem install biodiversity #for ruby 1.8.x
|
10
|
-
$ sudo gem install biodiversity19 #for ruby 1.9.x
|
11
|
-
|
12
|
-
== Example usage
|
13
|
-
|
14
|
-
=== As a command line script
|
15
|
-
|
16
|
-
You can parse file with taxonomic names from command line. File should contain one scientific name per line
|
17
|
-
|
18
|
-
nnparser file_with_names
|
19
|
-
|
20
|
-
=== As a socket server
|
21
|
-
|
22
|
-
If you do not use ruby and need a fast access to the parser functionality you can use a socket server
|
23
|
-
|
24
|
-
parserver
|
25
|
-
|
26
|
-
options:
|
27
|
-
|
28
|
-
parserver --output=canonical
|
29
|
-
|
30
|
-
to return a canonical form of the name string
|
31
|
-
|
32
|
-
parserver --output=canonical_with_rank
|
33
|
-
|
34
|
-
the same as above, but infraspecies' rank is shown if available
|
35
|
-
|
36
|
-
parserver --port 5555
|
37
|
-
|
38
|
-
run socket server on a different port
|
39
|
-
|
40
|
-
Then you can access it via 4334 port using a socket client library of your programming language. You can find socket client script example in the examples directory of the gem.
|
41
|
-
|
42
|
-
If you want to check if socket server works for you:
|
43
|
-
|
44
|
-
#run server in one terminal
|
45
|
-
parserver
|
46
|
-
|
47
|
-
#in another terminal window type
|
48
|
-
telnet localhost 4334
|
49
|
-
|
50
|
-
If you enter a line with a scientific name server will send you back parsed information in json format.
|
51
|
-
|
52
|
-
To stop telnet client type any of 'end','exit','q', '.' (without quotes) instead of scientific name
|
53
|
-
|
54
|
-
$ telnet localhost 4334
|
55
|
-
Trying ::1...
|
56
|
-
Connected to localhost.
|
57
|
-
Escape character is '^]'.
|
58
|
-
Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan
|
59
|
-
{"scientificName":{"canonical":"Acacia abyssinica calophylla","parsed":true,"parser_run":1,"verbatim":"Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan\r\n","positions":{"0":["genus",6],"18":["author_word",25],"29":["author_word",35],"7":["species",17],"41":["infraspecies",51],"52":["author_word",58]},"hybrid":false,"normalized":"Acacia abyssinica Hochst. ex Benth. ssp. calophylla Brenan","details":[{"species":{"basionymAuthorTeam":{"exAuthorTeam":{"author":["Benth."],"authorTeam":"Benth."},"author":["Hochst."],"authorTeam":"Hochst."},"string":"abyssinica","authorship":"Hochst. ex Benth."},"infraspecies":[{"basionymAuthorTeam":{"author":["Brenan"],"authorTeam":"Brenan"},"string":"calophylla","rank":"ssp.","authorship":"Brenan"}],"genus":{"string":"Acacia"}}]}}
|
60
|
-
|
61
|
-
|
62
|
-
=== As a library
|
63
|
-
|
64
|
-
You can use it as a library
|
65
|
-
|
66
|
-
require 'biodiversity'
|
67
|
-
|
68
|
-
parser = ScientificNameParser.new
|
69
|
-
|
70
|
-
# to parse a scientific name into a ruby hash
|
71
|
-
parser.parse("Plantago major")
|
72
|
-
|
73
|
-
#to get json representation
|
74
|
-
parser.parse("Plantago").to_json
|
75
|
-
#or
|
76
|
-
parser.parse("Plantago")
|
77
|
-
parser.all_json
|
78
|
-
|
79
|
-
# to clean name up
|
80
|
-
parser.parse(" Plantago major ")[:scientificName][:normalized]
|
81
|
-
|
82
|
-
# to get only cleaned up latin part of the name
|
83
|
-
parser.parse("Pseudocercospora dendrobii (H.C. Burnett) U. Braun & Crous 2003")[:scientificName][:canonical]
|
84
|
-
|
85
|
-
# to get detailed information about elements of the name
|
86
|
-
parser.parse("Pseudocercospora dendrobii (H.C. Burnett 1883) U. Braun & Crous 2003")[:scientificName][:details]
|
87
|
-
|
88
|
-
# to parse using several CPUs (4 seem to be optimal)
|
89
|
-
parser = ParallelParser.new # ParallelParser.new(4) will try to run 4 processes if hardware allows
|
90
|
-
array_of_names = ["Betula alba", "Homo sapiens"....]
|
91
|
-
parser.parse(array_of_names) # -> {"Betula alba" => {:scientificName...}, "Homo sapiens" => {:scientificName...}, ...}
|
92
|
-
|
93
|
-
parallel parser takes list of names and returns back a hash with names as keys and parsed data as values
|
94
|
-
|
95
|
-
# to resolve lsid and get back RDF file
|
96
|
-
LsidResolver.resolve("urn:lsid:ubio.org:classificationbank:2232671")
|
97
|
-
|
98
|
-
Copyright (c) 2009-2011 Marine Biological Laboratory. See LICENSE.txt for
|
99
|
-
further details.
|