taxamatch_rb 0.9.2 → 0.9.4

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/CHANGELOG CHANGED
@@ -1,3 +1,8 @@
1
+ 0.9.4 - updated parser (to 1.0.16), updated code to ruby 1.9.3
2
+
3
+ 0.9.3 - Taxamatch::Normalizer substitutes multiplication sign to 'x'
4
+ (lowcase) instead of '?'
5
+
1
6
  0.9.2 - Taxamatch::Normalizer.normalize always returns only ASCII
2
7
  characters, all utf-8 characters unknown to normalizer are becoming '?'
3
8
 
data/Gemfile CHANGED
@@ -2,17 +2,18 @@ source "http://rubygems.org"
2
2
  require 'yaml'
3
3
  # YAML::ENGINE.yamler= 'syck'
4
4
 
5
- gem "biodiversity19",">= 1.0.14"
5
+ gem "biodiversity19",">= 1.0.16"
6
6
  gem "damerau-levenshtein", ">= 0.5.4"
7
7
 
8
8
 
9
9
  group :development do
10
+ gem "rake"
10
11
  gem "rake-compiler"
11
- gem "rspec", "~> 2.3.0"
12
+ gem "rspec"
12
13
  gem "cucumber", ">= 0"
13
14
  gem "bundler", "~> 1.1.3"
14
15
  gem "jeweler", "~> 1.6.0"
15
- gem "ruby-debug19"
16
+ gem "debugger"
16
17
  gem "ruby-prof"
17
18
  gem "shoulda"
18
19
  gem "mocha"
data/Gemfile.lock CHANGED
@@ -4,8 +4,7 @@ GEM
4
4
  activesupport (3.2.6)
5
5
  i18n (~> 0.6)
6
6
  multi_json (~> 1.0)
7
- archive-tar-minitar (0.5.2)
8
- biodiversity19 (1.0.14)
7
+ biodiversity19 (1.0.16)
9
8
  parallel
10
9
  parallel
11
10
  treetop
@@ -18,6 +17,13 @@ GEM
18
17
  gherkin (~> 2.11.0)
19
18
  json (>= 1.4.6)
20
19
  damerau-levenshtein (0.5.4)
20
+ debugger (1.2.0)
21
+ columnize (>= 0.3.1)
22
+ debugger-linecache (~> 1.1.1)
23
+ debugger-ruby_core_source (~> 1.1.3)
24
+ debugger-linecache (1.1.2)
25
+ debugger-ruby_core_source (>= 1.1.1)
26
+ debugger-ruby_core_source (1.1.3)
21
27
  diff-lcs (1.1.3)
22
28
  gherkin (2.11.1)
23
29
  json (>= 1.4.6)
@@ -28,36 +34,24 @@ GEM
28
34
  git (>= 1.2.5)
29
35
  rake
30
36
  json (1.7.3)
31
- linecache19 (0.5.12)
32
- ruby_core_source (>= 0.1.4)
33
37
  metaclass (0.0.1)
34
38
  mocha (0.12.0)
35
39
  metaclass (~> 0.0.1)
36
40
  multi_json (1.3.6)
37
- parallel (0.5.17)
41
+ parallel (0.5.18)
38
42
  polyglot (0.3.3)
39
43
  rake (0.9.2.2)
40
44
  rake-compiler (0.8.1)
41
45
  rake
42
- rspec (2.3.0)
43
- rspec-core (~> 2.3.0)
44
- rspec-expectations (~> 2.3.0)
45
- rspec-mocks (~> 2.3.0)
46
- rspec-core (2.3.1)
47
- rspec-expectations (2.3.0)
48
- diff-lcs (~> 1.1.2)
49
- rspec-mocks (2.3.0)
50
- ruby-debug-base19 (0.11.25)
51
- columnize (>= 0.3.1)
52
- linecache19 (>= 0.5.11)
53
- ruby_core_source (>= 0.1.4)
54
- ruby-debug19 (0.11.6)
55
- columnize (>= 0.3.1)
56
- linecache19 (>= 0.5.11)
57
- ruby-debug-base19 (>= 0.11.19)
46
+ rspec (2.11.0)
47
+ rspec-core (~> 2.11.0)
48
+ rspec-expectations (~> 2.11.0)
49
+ rspec-mocks (~> 2.11.0)
50
+ rspec-core (2.11.1)
51
+ rspec-expectations (2.11.2)
52
+ diff-lcs (~> 1.1.3)
53
+ rspec-mocks (2.11.2)
58
54
  ruby-prof (0.11.2)
59
- ruby_core_source (0.1.5)
60
- archive-tar-minitar (>= 0.5.2)
61
55
  shoulda (3.1.1)
62
56
  shoulda-context (~> 1.0)
63
57
  shoulda-matchers (~> 1.2)
@@ -72,14 +66,15 @@ PLATFORMS
72
66
  ruby
73
67
 
74
68
  DEPENDENCIES
75
- biodiversity19 (>= 1.0.14)
69
+ biodiversity19 (>= 1.0.16)
76
70
  bundler (~> 1.1.3)
77
71
  cucumber
78
72
  damerau-levenshtein (>= 0.5.4)
73
+ debugger
79
74
  jeweler (~> 1.6.0)
80
75
  mocha
76
+ rake
81
77
  rake-compiler
82
- rspec (~> 2.3.0)
83
- ruby-debug19
78
+ rspec
84
79
  ruby-prof
85
80
  shoulda
data/VERSION CHANGED
@@ -1 +1 @@
1
- 0.9.2
1
+ 0.9.4
@@ -4,7 +4,7 @@ module Taxamatch
4
4
 
5
5
  module Normalizer
6
6
  def self.normalize(string)
7
- utf8_to_ascii(string.strip).upcase.gsub(/[^\x00-\x7F]/,'?')
7
+ utf8_to_ascii(string.strip.upcase).gsub(/[^\x00-\x7F]/,'?')
8
8
  end
9
9
 
10
10
  def self.normalize_word(word)
@@ -25,37 +25,24 @@ module Taxamatch
25
25
  private
26
26
  def self.utf8_to_ascii(string)
27
27
  string = string.gsub(/\s{2,}/, ' ')
28
- string = string.gsub(/[ÀÂÅÃÄÁẤẠÁ]/, "A")
29
- string = string.gsub(/[ÉÈÊË]/, "E")
30
- string = string.gsub(/[ÍÌÎÏ]/, "I")
31
- string = string.gsub(/[ÓÒÔØÕÖỚỔ]/, "O")
32
- string = string.gsub(/[ÚÙÛÜ]/, "U")
33
- string = string.gsub(/[Ý]/, "Y")
34
- string = string.gsub(/Æ/, "AE")
35
- string = string.gsub(/[ČÇ]/, "C")
36
- string = string.gsub(/[ŠŞ]/, "S")
37
- string = string.gsub(/[Đ]/, "D")
38
- string = string.gsub(/Ž/, "Z")
39
- string = string.gsub(/Ñ/, "N")
40
- string = string.gsub(/Œ/, "OE")
28
+ string = string.gsub("×", "x")
29
+ string = string.gsub(/[ÀÂÅÃÄÁẤẠÁáàâåãäăãắảạậầằá]/, "A")
30
+ string = string.gsub(/[ÉÈÊËéèêëĕěếệểễềẻ]/, "E")
31
+ string = string.gsub(/[ÍÌÎÏíìîïǐĭīĩỉï]/, "I")
32
+ string = string.gsub(/[ÓÒÔØÕÖỚỔóòôøõöŏỏỗộơọỡốơồờớổő]/, "O")
33
+ string = string.gsub(/[ÚÙÛÜúùûüůưừựủứụű]/, "U")
34
+ string = string.gsub(/[Ýýÿỹ]/, "Y")
35
+ string = string.gsub(/[Ææ]/, "AE")
36
+ string = string.gsub(/[ČÇčćç]/, "C")
37
+ string = string.gsub(/[ŠŞśšşſ]/, "S")
38
+ string = string.gsub(/[Đđð]/, "D")
39
+ string = string.gsub(/Žžź/, "Z")
40
+ string = string.gsub(/[Ññńň]/, "N")
41
+ string = string.gsub(/[Œœ]/, "OE")
41
42
  string = string.gsub(/ß/, "B")
42
43
  string = string.gsub(/Ķ/, "K")
43
- string = string.gsub(/[áàâåãäăãắảạậầằá]/, "a")
44
- string = string.gsub(/[éèêëĕěếệểễềẻ]/, "e")
45
- string = string.gsub(/[íìîïǐĭīĩỉï]/, "i")
46
- string = string.gsub(/[óòôøõöŏỏỗộơọỡốơồờớổő]/, "o")
47
- string = string.gsub(/[úùûüůưừựủứụű]/, "u")
48
- string = string.gsub(/[žź]/, "z")
49
- string = string.gsub(/[ýÿỹ]/, "y")
50
- string = string.gsub(/[đð]/, "d")
51
- string = string.gsub(/æ/, "ae")
52
- string = string.gsub(/[čćç]/, "c")
53
- string = string.gsub(/[ñńň]/, "n")
54
- string = string.gsub(/œ/, "oe")
55
- string = string.gsub(/[śšş]/, "s")
56
- string = string.gsub(/ř/, "r")
57
- string = string.gsub(/ğ/, "g")
58
- string = string.gsub(/Ř/, "R")
44
+ string = string.gsub(/ğ/, "G")
45
+ string = string.gsub(/[Řř]/, "R")
59
46
  end
60
47
 
61
48
  end
@@ -35,6 +35,7 @@ describe 'Taxamatch::Normalizer' do
35
35
  Taxamatch::Normalizer.normalize('Fallé€n').should == 'FALLE?N'
36
36
  Taxamatch::Normalizer.normalize('Fallén привет').should == 'FALLEN ??????'
37
37
  Taxamatch::Normalizer.normalize('Choriozopella trägårdhi').should == 'CHORIOZOPELLA TRAGARDHI'
38
+ Taxamatch::Normalizer.normalize('×Zygomena').should == 'xZYGOMENA'
38
39
  end
39
40
 
40
41
  it 'should normalize words' do
data/taxamatch_rb.gemspec CHANGED
@@ -5,11 +5,11 @@
5
5
 
6
6
  Gem::Specification.new do |s|
7
7
  s.name = "taxamatch_rb"
8
- s.version = "0.9.2"
8
+ s.version = "0.9.4"
9
9
 
10
10
  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
11
11
  s.authors = ["Dmitry Mozzherin"]
12
- s.date = "2012-07-18"
12
+ s.date = "2012-08-27"
13
13
  s.description = "This gem implements algorithm for fuzzy matching scientific names developed by Tony Rees"
14
14
  s.email = "dmozzherin@eol.org"
15
15
  s.extra_rdoc_files = [
@@ -45,39 +45,42 @@ Gem::Specification.new do |s|
45
45
  s.specification_version = 3
46
46
 
47
47
  if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
48
- s.add_runtime_dependency(%q<biodiversity19>, [">= 1.0.14"])
48
+ s.add_runtime_dependency(%q<biodiversity19>, [">= 1.0.16"])
49
49
  s.add_runtime_dependency(%q<damerau-levenshtein>, [">= 0.5.4"])
50
+ s.add_development_dependency(%q<rake>, [">= 0"])
50
51
  s.add_development_dependency(%q<rake-compiler>, [">= 0"])
51
- s.add_development_dependency(%q<rspec>, ["~> 2.3.0"])
52
+ s.add_development_dependency(%q<rspec>, [">= 0"])
52
53
  s.add_development_dependency(%q<cucumber>, [">= 0"])
53
54
  s.add_development_dependency(%q<bundler>, ["~> 1.1.3"])
54
55
  s.add_development_dependency(%q<jeweler>, ["~> 1.6.0"])
55
- s.add_development_dependency(%q<ruby-debug19>, [">= 0"])
56
+ s.add_development_dependency(%q<debugger>, [">= 0"])
56
57
  s.add_development_dependency(%q<ruby-prof>, [">= 0"])
57
58
  s.add_development_dependency(%q<shoulda>, [">= 0"])
58
59
  s.add_development_dependency(%q<mocha>, [">= 0"])
59
60
  else
60
- s.add_dependency(%q<biodiversity19>, [">= 1.0.14"])
61
+ s.add_dependency(%q<biodiversity19>, [">= 1.0.16"])
61
62
  s.add_dependency(%q<damerau-levenshtein>, [">= 0.5.4"])
63
+ s.add_dependency(%q<rake>, [">= 0"])
62
64
  s.add_dependency(%q<rake-compiler>, [">= 0"])
63
- s.add_dependency(%q<rspec>, ["~> 2.3.0"])
65
+ s.add_dependency(%q<rspec>, [">= 0"])
64
66
  s.add_dependency(%q<cucumber>, [">= 0"])
65
67
  s.add_dependency(%q<bundler>, ["~> 1.1.3"])
66
68
  s.add_dependency(%q<jeweler>, ["~> 1.6.0"])
67
- s.add_dependency(%q<ruby-debug19>, [">= 0"])
69
+ s.add_dependency(%q<debugger>, [">= 0"])
68
70
  s.add_dependency(%q<ruby-prof>, [">= 0"])
69
71
  s.add_dependency(%q<shoulda>, [">= 0"])
70
72
  s.add_dependency(%q<mocha>, [">= 0"])
71
73
  end
72
74
  else
73
- s.add_dependency(%q<biodiversity19>, [">= 1.0.14"])
75
+ s.add_dependency(%q<biodiversity19>, [">= 1.0.16"])
74
76
  s.add_dependency(%q<damerau-levenshtein>, [">= 0.5.4"])
77
+ s.add_dependency(%q<rake>, [">= 0"])
75
78
  s.add_dependency(%q<rake-compiler>, [">= 0"])
76
- s.add_dependency(%q<rspec>, ["~> 2.3.0"])
79
+ s.add_dependency(%q<rspec>, [">= 0"])
77
80
  s.add_dependency(%q<cucumber>, [">= 0"])
78
81
  s.add_dependency(%q<bundler>, ["~> 1.1.3"])
79
82
  s.add_dependency(%q<jeweler>, ["~> 1.6.0"])
80
- s.add_dependency(%q<ruby-debug19>, [">= 0"])
83
+ s.add_dependency(%q<debugger>, [">= 0"])
81
84
  s.add_dependency(%q<ruby-prof>, [">= 0"])
82
85
  s.add_dependency(%q<shoulda>, [">= 0"])
83
86
  s.add_dependency(%q<mocha>, [">= 0"])
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: taxamatch_rb
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.9.2
4
+ version: 0.9.4
5
5
  prerelease:
6
6
  platform: ruby
7
7
  authors:
@@ -9,7 +9,7 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2012-07-18 00:00:00.000000000 Z
12
+ date: 2012-08-27 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: biodiversity19
@@ -18,7 +18,7 @@ dependencies:
18
18
  requirements:
19
19
  - - ! '>='
20
20
  - !ruby/object:Gem::Version
21
- version: 1.0.14
21
+ version: 1.0.16
22
22
  type: :runtime
23
23
  prerelease: false
24
24
  version_requirements: !ruby/object:Gem::Requirement
@@ -26,7 +26,7 @@ dependencies:
26
26
  requirements:
27
27
  - - ! '>='
28
28
  - !ruby/object:Gem::Version
29
- version: 1.0.14
29
+ version: 1.0.16
30
30
  - !ruby/object:Gem::Dependency
31
31
  name: damerau-levenshtein
32
32
  requirement: !ruby/object:Gem::Requirement
@@ -43,6 +43,22 @@ dependencies:
43
43
  - - ! '>='
44
44
  - !ruby/object:Gem::Version
45
45
  version: 0.5.4
46
+ - !ruby/object:Gem::Dependency
47
+ name: rake
48
+ requirement: !ruby/object:Gem::Requirement
49
+ none: false
50
+ requirements:
51
+ - - ! '>='
52
+ - !ruby/object:Gem::Version
53
+ version: '0'
54
+ type: :development
55
+ prerelease: false
56
+ version_requirements: !ruby/object:Gem::Requirement
57
+ none: false
58
+ requirements:
59
+ - - ! '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
46
62
  - !ruby/object:Gem::Dependency
47
63
  name: rake-compiler
48
64
  requirement: !ruby/object:Gem::Requirement
@@ -64,17 +80,17 @@ dependencies:
64
80
  requirement: !ruby/object:Gem::Requirement
65
81
  none: false
66
82
  requirements:
67
- - - ~>
83
+ - - ! '>='
68
84
  - !ruby/object:Gem::Version
69
- version: 2.3.0
85
+ version: '0'
70
86
  type: :development
71
87
  prerelease: false
72
88
  version_requirements: !ruby/object:Gem::Requirement
73
89
  none: false
74
90
  requirements:
75
- - - ~>
91
+ - - ! '>='
76
92
  - !ruby/object:Gem::Version
77
- version: 2.3.0
93
+ version: '0'
78
94
  - !ruby/object:Gem::Dependency
79
95
  name: cucumber
80
96
  requirement: !ruby/object:Gem::Requirement
@@ -124,7 +140,7 @@ dependencies:
124
140
  - !ruby/object:Gem::Version
125
141
  version: 1.6.0
126
142
  - !ruby/object:Gem::Dependency
127
- name: ruby-debug19
143
+ name: debugger
128
144
  requirement: !ruby/object:Gem::Requirement
129
145
  none: false
130
146
  requirements:
@@ -228,7 +244,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
228
244
  version: '0'
229
245
  segments:
230
246
  - 0
231
- hash: 649911613402645259
247
+ hash: 2280518613036556094
232
248
  required_rubygems_version: !ruby/object:Gem::Requirement
233
249
  none: false
234
250
  requirements: