loose_tight_dictionary 0.0.10 → 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +1 -0
- data/Gemfile +4 -0
- data/README.rdoc +76 -23
- data/Rakefile +2 -38
- data/benchmark/before-with-free.txt +283 -0
- data/benchmark/before-without-last-result.txt +257 -0
- data/benchmark/before.txt +304 -0
- data/benchmark/memory.rb +54 -0
- data/examples/bts_aircraft/5-2-A.htm +10305 -0
- data/examples/bts_aircraft/5-2-B.htm +9576 -0
- data/examples/bts_aircraft/5-2-D.htm +7094 -0
- data/examples/bts_aircraft/5-2-E.htm +2349 -0
- data/examples/bts_aircraft/5-2-G.htm +2922 -0
- data/examples/bts_aircraft/blockings.csv +1 -0
- data/examples/bts_aircraft/identities.csv +1 -0
- data/examples/bts_aircraft/negatives.csv +1 -0
- data/examples/bts_aircraft/number_260.csv +334 -0
- data/examples/bts_aircraft/positives.csv +1 -0
- data/examples/bts_aircraft/test_bts_aircraft.rb +123 -0
- data/examples/bts_aircraft/tighteners.csv +1 -0
- data/examples/first_name_matching.rb +14 -22
- data/lib/loose_tight_dictionary/blocking.rb +36 -0
- data/lib/loose_tight_dictionary/extract_regexp.rb +30 -0
- data/lib/loose_tight_dictionary/identity.rb +25 -0
- data/lib/loose_tight_dictionary/result.rb +23 -0
- data/lib/loose_tight_dictionary/score.rb +28 -0
- data/lib/loose_tight_dictionary/similarity.rb +62 -0
- data/lib/loose_tight_dictionary/tightener.rb +30 -0
- data/lib/loose_tight_dictionary/version.rb +3 -0
- data/lib/loose_tight_dictionary/wrapper.rb +37 -0
- data/lib/loose_tight_dictionary.rb +178 -305
- data/loose_tight_dictionary.gemspec +19 -64
- data/test/helper.rb +6 -6
- data/test/test_blocking.rb +23 -0
- data/test/test_extract_regexp.rb +18 -0
- data/test/test_identity.rb +18 -0
- data/test/test_loose_tight_dictionary.rb +52 -245
- data/test/test_loose_tight_dictionary_convoluted.rb.disabled +268 -0
- data/test/test_tightening.rb +10 -0
- metadata +52 -65
- data/VERSION +0 -1
- data/examples/icao-bts.rb +0 -58
@@ -0,0 +1,268 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
require 'shoulda'
|
4
|
+
|
5
|
+
$log = false
|
6
|
+
|
7
|
+
class TestLooseTightDictionaryConvoluted < Test::Unit::TestCase
|
8
|
+
def setup
|
9
|
+
clear_ltd
|
10
|
+
|
11
|
+
# dh 8 400
|
12
|
+
@a_needle = ['DE HAVILLAND CANADA DHC8400 Dash 8']
|
13
|
+
@a_haystack = ['DEHAVILLAND DEHAVILLAND DHC8-400 DASH-8']
|
14
|
+
# dh 88
|
15
|
+
@b_needle = ['ABCDEFG DH88 HIJKLMNOP']
|
16
|
+
# dh 89
|
17
|
+
@c_haystack = ['ABCDEFG DH89 HIJKLMNOP']
|
18
|
+
# dh 8 200
|
19
|
+
@d_needle = ['DE HAVILLAND CANADA DHC8200 Dash 8']
|
20
|
+
@d_haystack = ['BOMBARDIER DEHAVILLAND DHC8-200Q DASH-8']
|
21
|
+
@d_lookalike = ['ABCD DHC8200 Dash 8']
|
22
|
+
|
23
|
+
@t_1 = [ '/(dh)c?-?(\d{0,2})-?(\d{0,4})(?:.*?)(dash|\z)/i', 'good tightening for de havilland' ]
|
24
|
+
|
25
|
+
@r_1 = [ '/(dh)c?-?(\d{0,2})-?(\d{0,4})(?:.*?)(dash|\z)/i', 'good identity for de havilland' ]
|
26
|
+
|
27
|
+
@needle = [
|
28
|
+
@a_needle,
|
29
|
+
@b_needle,
|
30
|
+
['DE HAVILLAND DH89 Dragon Rapide'],
|
31
|
+
['DE HAVILLAND CANADA DHC8100 Dash 8 (E9, CT142, CC142)'],
|
32
|
+
@d_needle,
|
33
|
+
['DE HAVILLAND CANADA DHC8300 Dash 8'],
|
34
|
+
['DE HAVILLAND DH90 Dragonfly']
|
35
|
+
]
|
36
|
+
@haystack = [
|
37
|
+
@a_haystack,
|
38
|
+
@c_haystack,
|
39
|
+
@d_haystack,
|
40
|
+
['DEHAVILLAND DEHAVILLAND DHC8-100 DASH-8'],
|
41
|
+
['DEHAVILLAND DEHAVILLAND TWIN OTTER DHC-6']
|
42
|
+
]
|
43
|
+
@tightenings = []
|
44
|
+
@identities = []
|
45
|
+
@blockings = []
|
46
|
+
@positives = []
|
47
|
+
@negatives = []
|
48
|
+
end
|
49
|
+
|
50
|
+
def clear_ltd
|
51
|
+
@_ltd = nil
|
52
|
+
end
|
53
|
+
|
54
|
+
def ltd
|
55
|
+
@_ltd ||= LooseTightDictionary.new @haystack,
|
56
|
+
:tightenings => @tightenings,
|
57
|
+
:identities => @identities,
|
58
|
+
:blockings => @blockings,
|
59
|
+
:positives => @positives,
|
60
|
+
:negatives => @negatives,
|
61
|
+
:blocking_only => @blocking_only,
|
62
|
+
:log => $log
|
63
|
+
end
|
64
|
+
|
65
|
+
should "optionally only pay attention to things that match blockings" do
|
66
|
+
assert_equal @a_haystack, ltd.improver.match(@a_needle)
|
67
|
+
|
68
|
+
clear_ltd
|
69
|
+
@blocking_only = true
|
70
|
+
assert_equal nil, ltd.improver.match(@a_needle)
|
71
|
+
|
72
|
+
clear_ltd
|
73
|
+
@blocking_only = true
|
74
|
+
@blockings.push ['/dash/i']
|
75
|
+
assert_equal @a_haystack, ltd.improver.match(@a_needle)
|
76
|
+
end
|
77
|
+
|
78
|
+
# the example from the readme, considerably uglier here
|
79
|
+
should "check a simple table" do
|
80
|
+
@haystack = [ 'seamus', 'andy', 'ben' ]
|
81
|
+
@positives = [ [ 'seamus', 'Mr. Seamus Abshere' ] ]
|
82
|
+
needle = [ 'Mr. Seamus Abshere', 'Sr. Andy Rossmeissl', 'Master BenT' ]
|
83
|
+
|
84
|
+
assert_nothing_raised do
|
85
|
+
ltd.improver.check needle
|
86
|
+
end
|
87
|
+
end
|
88
|
+
|
89
|
+
should "treat a String as a full record if passed through" do
|
90
|
+
dash = 'DHC8-400'
|
91
|
+
b747 = 'B747200/300'
|
92
|
+
dc9 = 'DC-9-10'
|
93
|
+
haystack_records = [ dash, b747, dc9 ]
|
94
|
+
simple_ltd = LooseTightDictionary.new haystack_records, :log => $log
|
95
|
+
assert_equal dash, simple_ltd.improver.match('DeHavilland Dash-8 DHC-400')
|
96
|
+
assert_equal b747, simple_ltd.improver.match('Boeing 747-300')
|
97
|
+
assert_equal dc9, simple_ltd.improver.match('McDonnell Douglas MD81/DC-9')
|
98
|
+
end
|
99
|
+
|
100
|
+
should "call it a mismatch if you hit a blank positive" do
|
101
|
+
@positives.push [@a_needle[0], '']
|
102
|
+
assert_raises(LooseTightDictionary::Improver::Mismatch) do
|
103
|
+
ltd.improver.match @a_needle
|
104
|
+
end
|
105
|
+
end
|
106
|
+
|
107
|
+
should "call it a false positive if you hit a blank negative" do
|
108
|
+
@negatives.push [@a_needle[0], '']
|
109
|
+
assert_raises(LooseTightDictionary::Improver::FalsePositive) do
|
110
|
+
ltd.improver.match @a_needle
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
should "have a false match without blocking" do
|
115
|
+
# @d_needle will be our victim
|
116
|
+
@haystack.push @d_lookalike
|
117
|
+
@tightenings.push @t_1
|
118
|
+
|
119
|
+
assert_equal @d_lookalike, ltd.improver.match(@d_needle)
|
120
|
+
end
|
121
|
+
|
122
|
+
should "do blocking if the needle matches a block" do
|
123
|
+
# @d_needle will be our victim
|
124
|
+
@haystack.push @d_lookalike
|
125
|
+
@tightenings.push @t_1
|
126
|
+
@blockings.push ['/(bombardier|de ?havilland)/i']
|
127
|
+
|
128
|
+
assert_equal @d_haystack, ltd.improver.match(@d_needle)
|
129
|
+
end
|
130
|
+
|
131
|
+
should "treat blocks as exclusive" do
|
132
|
+
@haystack = [ @d_needle ]
|
133
|
+
@tightenings.push @t_1
|
134
|
+
@blockings.push ['/(bombardier|de ?havilland)/i']
|
135
|
+
|
136
|
+
assert_equal nil, ltd.improver.match(@d_lookalike)
|
137
|
+
end
|
138
|
+
|
139
|
+
should "only use identities if they stem from the same regexp" do
|
140
|
+
@identities.push @r_1
|
141
|
+
@identities.push [ '/(cessna)(?:.*?)(citation)/i' ]
|
142
|
+
@identities.push [ '/(cessna)(?:.*?)(\d\d\d)/i' ]
|
143
|
+
x_needle = [ 'CESSNA D-333 CITATION V']
|
144
|
+
x_haystack = [ 'CESSNA D-333' ]
|
145
|
+
@haystack.push x_haystack
|
146
|
+
|
147
|
+
assert_equal x_haystack, ltd.improver.match(x_needle)
|
148
|
+
end
|
149
|
+
|
150
|
+
should "use the best score from all of the tightenings" do
|
151
|
+
x_needle = ["BOEING 737100"]
|
152
|
+
x_haystack = ["BOEING BOEING 737-100/200"]
|
153
|
+
x_haystack_wrong = ["BOEING BOEING 737-900"]
|
154
|
+
@haystack.push x_haystack
|
155
|
+
@haystack.push x_haystack_wrong
|
156
|
+
@tightenings.push ['/(7\d)(7|0)-?\d{1,3}\/(\d\d\d)/i']
|
157
|
+
@tightenings.push ['/(7\d)(7|0)-?(\d{1,3}|[A-Z]{0,3})/i']
|
158
|
+
|
159
|
+
assert_equal x_haystack, ltd.improver.match(x_needle)
|
160
|
+
end
|
161
|
+
|
162
|
+
should "compare using prefixes if tightened key is shorter than correct match" do
|
163
|
+
x_needle = ["BOEING 720"]
|
164
|
+
x_haystack = ["BOEING BOEING 720-000"]
|
165
|
+
x_haystack_wrong = ["BOEING BOEING 717-200"]
|
166
|
+
@haystack.push x_haystack
|
167
|
+
@haystack.push x_haystack_wrong
|
168
|
+
@tightenings.push @t_1
|
169
|
+
@tightenings.push ['/(7\d)(7|0)-?\d{1,3}\/(\d\d\d)/i']
|
170
|
+
@tightenings.push ['/(7\d)(7|0)-?(\d{1,3}|[A-Z]{0,3})/i']
|
171
|
+
|
172
|
+
assert_equal x_haystack, ltd.improver.match(x_needle)
|
173
|
+
end
|
174
|
+
|
175
|
+
should "use the shortest original input" do
|
176
|
+
x_needle = ['De Havilland DHC8-777 Dash-8 Superstar']
|
177
|
+
x_haystack = ['DEHAVILLAND DEHAVILLAND DHC8-777 DASH-8 Superstar']
|
178
|
+
x_haystack_long = ['DEHAVILLAND DEHAVILLAND DHC8-777 DASH-8 Superstar/Supernova']
|
179
|
+
|
180
|
+
@haystack.push x_haystack_long
|
181
|
+
@haystack.push x_haystack
|
182
|
+
@tightenings.push @t_1
|
183
|
+
|
184
|
+
assert_equal x_haystack, ltd.improver.match(x_needle)
|
185
|
+
end
|
186
|
+
|
187
|
+
should "perform lookups needle to haystack" do
|
188
|
+
assert_equal @a_haystack, ltd.improver.match(@a_needle)
|
189
|
+
end
|
190
|
+
|
191
|
+
should "succeed if there are no checks" do
|
192
|
+
assert_nothing_raised do
|
193
|
+
ltd.improver.check @needle
|
194
|
+
end
|
195
|
+
end
|
196
|
+
|
197
|
+
should "succeed if the positive checks just work" do
|
198
|
+
@positives.push [ @a_needle[0], @a_haystack[0] ]
|
199
|
+
|
200
|
+
assert_nothing_raised do
|
201
|
+
ltd.improver.check @needle
|
202
|
+
end
|
203
|
+
end
|
204
|
+
|
205
|
+
should "fail if positive checks don't work" do
|
206
|
+
@positives.push [ @d_needle[0], @d_haystack[0] ]
|
207
|
+
|
208
|
+
assert_raises(LooseTightDictionary::Improver::Mismatch) do
|
209
|
+
ltd.improver.check @needle
|
210
|
+
end
|
211
|
+
end
|
212
|
+
|
213
|
+
should "succeed if proper tightening is applied" do
|
214
|
+
@positives.push [ @d_needle[0], @d_haystack[0] ]
|
215
|
+
@tightenings.push @t_1
|
216
|
+
|
217
|
+
assert_nothing_raised do
|
218
|
+
ltd.improver.check @needle
|
219
|
+
end
|
220
|
+
end
|
221
|
+
|
222
|
+
should "use a Google Docs spreadsheet as a source of tightenings" do
|
223
|
+
@positives.push [ @d_needle[0], @d_haystack[0] ]
|
224
|
+
@tightenings = RemoteTable.new :url => 'http://spreadsheets.google.com/pub?key=tiS_6CCDDM_drNphpYwE_iw&single=true&gid=0&output=csv', :headers => false
|
225
|
+
|
226
|
+
# sabshere 9/30/10 this shouldn't raise anything
|
227
|
+
# but the tightenings have been changed... we should be using test-only tightenings, not production ones
|
228
|
+
# assert_nothing_raised do
|
229
|
+
assert_raises(LooseTightDictionary::Improver::Mismatch) do
|
230
|
+
ltd.improver.check @needle
|
231
|
+
end
|
232
|
+
end
|
233
|
+
|
234
|
+
should "fail if negative checks don't work" do
|
235
|
+
@negatives.push [ @b_needle[0], @c_haystack[0] ]
|
236
|
+
|
237
|
+
assert_raises(LooseTightDictionary::Improver::FalsePositive) do
|
238
|
+
ltd.improver.check @needle
|
239
|
+
end
|
240
|
+
end
|
241
|
+
|
242
|
+
should "do inline checking" do
|
243
|
+
@negatives.push [ @b_needle[0], @c_haystack[0] ]
|
244
|
+
|
245
|
+
assert_raises(LooseTightDictionary::Improver::FalsePositive) do
|
246
|
+
ltd.improver.match @b_needle
|
247
|
+
end
|
248
|
+
end
|
249
|
+
|
250
|
+
should "fail if negative checks don't work, even with tightening" do
|
251
|
+
@negatives.push [ @b_needle[0], @c_haystack[0] ]
|
252
|
+
@tightenings.push @t_1
|
253
|
+
|
254
|
+
assert_raises(LooseTightDictionary::Improver::FalsePositive) do
|
255
|
+
ltd.improver.check @needle
|
256
|
+
end
|
257
|
+
end
|
258
|
+
|
259
|
+
should "succeed if proper identity is applied" do
|
260
|
+
@negatives.push [ @b_needle[0], @c_haystack[0] ]
|
261
|
+
@positives.push [ @d_needle[0], @d_haystack[0] ]
|
262
|
+
@identities.push @r_1
|
263
|
+
|
264
|
+
assert_nothing_raised do
|
265
|
+
ltd.improver.check @needle
|
266
|
+
end
|
267
|
+
end
|
268
|
+
end
|
@@ -0,0 +1,10 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestTightener < Test::Unit::TestCase
|
4
|
+
def test_001_apply
|
5
|
+
t = LooseTightDictionary::Tightener.new %r{(Ford )[ ]*(F)[\- ]*(\d\d\d)}i
|
6
|
+
assert_equal 'Ford F350', t.apply('Ford F-350')
|
7
|
+
assert_equal 'Ford F150', t.apply('Ford F150')
|
8
|
+
assert_equal 'Ford F350', t.apply('Ford F 350')
|
9
|
+
end
|
10
|
+
end
|
metadata
CHANGED
@@ -1,13 +1,8 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: loose_tight_dictionary
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
|
5
|
-
|
6
|
-
segments:
|
7
|
-
- 0
|
8
|
-
- 0
|
9
|
-
- 10
|
10
|
-
version: 0.0.10
|
4
|
+
prerelease:
|
5
|
+
version: 0.1.0
|
11
6
|
platform: ruby
|
12
7
|
authors:
|
13
8
|
- Seamus Abshere
|
@@ -15,7 +10,7 @@ autorequire:
|
|
15
10
|
bindir: bin
|
16
11
|
cert_chain: []
|
17
12
|
|
18
|
-
date: 2011-
|
13
|
+
date: 2011-04-18 00:00:00 -05:00
|
19
14
|
default_executable:
|
20
15
|
dependencies:
|
21
16
|
- !ruby/object:Gem::Dependency
|
@@ -26,9 +21,6 @@ dependencies:
|
|
26
21
|
requirements:
|
27
22
|
- - ">="
|
28
23
|
- !ruby/object:Gem::Version
|
29
|
-
hash: 3
|
30
|
-
segments:
|
31
|
-
- 0
|
32
24
|
version: "0"
|
33
25
|
type: :development
|
34
26
|
version_requirements: *id001
|
@@ -40,12 +32,7 @@ dependencies:
|
|
40
32
|
requirements:
|
41
33
|
- - ">="
|
42
34
|
- !ruby/object:Gem::Version
|
43
|
-
|
44
|
-
segments:
|
45
|
-
- 0
|
46
|
-
- 2
|
47
|
-
- 19
|
48
|
-
version: 0.2.19
|
35
|
+
version: "0"
|
49
36
|
type: :development
|
50
37
|
version_requirements: *id002
|
51
38
|
- !ruby/object:Gem::Dependency
|
@@ -56,76 +43,79 @@ dependencies:
|
|
56
43
|
requirements:
|
57
44
|
- - ">="
|
58
45
|
- !ruby/object:Gem::Version
|
59
|
-
hash: 11
|
60
|
-
segments:
|
61
|
-
- 2
|
62
|
-
- 3
|
63
|
-
- 4
|
64
46
|
version: 2.3.4
|
65
47
|
type: :runtime
|
66
48
|
version_requirements: *id003
|
67
49
|
- !ruby/object:Gem::Dependency
|
68
|
-
name:
|
50
|
+
name: amatch
|
69
51
|
prerelease: false
|
70
52
|
requirement: &id004 !ruby/object:Gem::Requirement
|
71
53
|
none: false
|
72
54
|
requirements:
|
73
55
|
- - ">="
|
74
56
|
- !ruby/object:Gem::Version
|
75
|
-
|
76
|
-
segments:
|
77
|
-
- 1
|
78
|
-
- 3
|
79
|
-
- 1
|
80
|
-
version: 1.3.1
|
57
|
+
version: "0"
|
81
58
|
type: :runtime
|
82
59
|
version_requirements: *id004
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
requirement: &id005 !ruby/object:Gem::Requirement
|
87
|
-
none: false
|
88
|
-
requirements:
|
89
|
-
- - ">="
|
90
|
-
- !ruby/object:Gem::Version
|
91
|
-
hash: 29
|
92
|
-
segments:
|
93
|
-
- 0
|
94
|
-
- 2
|
95
|
-
- 5
|
96
|
-
version: 0.2.5
|
97
|
-
type: :runtime
|
98
|
-
version_requirements: *id005
|
99
|
-
description: Create dictionaries that link rows between two tables (left and right) using loose matching (string similarity) by default and tight matching (regexp) by request.
|
100
|
-
email: seamus@abshere.net
|
60
|
+
description: Create dictionaries that link rows between two tables using loose matching (string similarity) by default and tight matching (regexp) by request.
|
61
|
+
email:
|
62
|
+
- seamus@abshere.net
|
101
63
|
executables: []
|
102
64
|
|
103
65
|
extensions: []
|
104
66
|
|
105
|
-
extra_rdoc_files:
|
106
|
-
|
107
|
-
- README.rdoc
|
67
|
+
extra_rdoc_files: []
|
68
|
+
|
108
69
|
files:
|
109
70
|
- .document
|
110
71
|
- .gitignore
|
72
|
+
- Gemfile
|
111
73
|
- LICENSE
|
112
74
|
- README.rdoc
|
113
75
|
- Rakefile
|
114
|
-
-
|
76
|
+
- benchmark/before-with-free.txt
|
77
|
+
- benchmark/before-without-last-result.txt
|
78
|
+
- benchmark/before.txt
|
79
|
+
- benchmark/memory.rb
|
80
|
+
- examples/bts_aircraft/5-2-A.htm
|
81
|
+
- examples/bts_aircraft/5-2-B.htm
|
82
|
+
- examples/bts_aircraft/5-2-D.htm
|
83
|
+
- examples/bts_aircraft/5-2-E.htm
|
84
|
+
- examples/bts_aircraft/5-2-G.htm
|
85
|
+
- examples/bts_aircraft/blockings.csv
|
86
|
+
- examples/bts_aircraft/identities.csv
|
87
|
+
- examples/bts_aircraft/negatives.csv
|
88
|
+
- examples/bts_aircraft/number_260.csv
|
89
|
+
- examples/bts_aircraft/positives.csv
|
90
|
+
- examples/bts_aircraft/test_bts_aircraft.rb
|
91
|
+
- examples/bts_aircraft/tighteners.csv
|
115
92
|
- examples/first_name_matching.rb
|
116
|
-
- examples/icao-bts.rb
|
117
93
|
- examples/icao-bts.xls
|
118
94
|
- lib/loose_tight_dictionary.rb
|
95
|
+
- lib/loose_tight_dictionary/blocking.rb
|
96
|
+
- lib/loose_tight_dictionary/extract_regexp.rb
|
97
|
+
- lib/loose_tight_dictionary/identity.rb
|
98
|
+
- lib/loose_tight_dictionary/result.rb
|
99
|
+
- lib/loose_tight_dictionary/score.rb
|
100
|
+
- lib/loose_tight_dictionary/similarity.rb
|
101
|
+
- lib/loose_tight_dictionary/tightener.rb
|
102
|
+
- lib/loose_tight_dictionary/version.rb
|
103
|
+
- lib/loose_tight_dictionary/wrapper.rb
|
119
104
|
- loose_tight_dictionary.gemspec
|
120
105
|
- test/helper.rb
|
106
|
+
- test/test_blocking.rb
|
107
|
+
- test/test_extract_regexp.rb
|
108
|
+
- test/test_identity.rb
|
121
109
|
- test/test_loose_tight_dictionary.rb
|
110
|
+
- test/test_loose_tight_dictionary_convoluted.rb.disabled
|
111
|
+
- test/test_tightening.rb
|
122
112
|
has_rdoc: true
|
123
|
-
homepage:
|
113
|
+
homepage: https://github.com/seamusabshere/loose_tight_dictionary
|
124
114
|
licenses: []
|
125
115
|
|
126
116
|
post_install_message:
|
127
|
-
rdoc_options:
|
128
|
-
|
117
|
+
rdoc_options: []
|
118
|
+
|
129
119
|
require_paths:
|
130
120
|
- lib
|
131
121
|
required_ruby_version: !ruby/object:Gem::Requirement
|
@@ -133,28 +123,25 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
133
123
|
requirements:
|
134
124
|
- - ">="
|
135
125
|
- !ruby/object:Gem::Version
|
136
|
-
hash: 3
|
137
|
-
segments:
|
138
|
-
- 0
|
139
126
|
version: "0"
|
140
127
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
141
128
|
none: false
|
142
129
|
requirements:
|
143
130
|
- - ">="
|
144
131
|
- !ruby/object:Gem::Version
|
145
|
-
hash: 3
|
146
|
-
segments:
|
147
|
-
- 0
|
148
132
|
version: "0"
|
149
133
|
requirements: []
|
150
134
|
|
151
|
-
rubyforge_project:
|
152
|
-
rubygems_version: 1.
|
135
|
+
rubyforge_project: loose_tight_dictionary
|
136
|
+
rubygems_version: 1.6.2
|
153
137
|
signing_key:
|
154
138
|
specification_version: 3
|
155
139
|
summary: Allows iterative development of dictionaries for big data sets.
|
156
140
|
test_files:
|
157
141
|
- test/helper.rb
|
142
|
+
- test/test_blocking.rb
|
143
|
+
- test/test_extract_regexp.rb
|
144
|
+
- test/test_identity.rb
|
158
145
|
- test/test_loose_tight_dictionary.rb
|
159
|
-
-
|
160
|
-
-
|
146
|
+
- test/test_loose_tight_dictionary_convoluted.rb.disabled
|
147
|
+
- test/test_tightening.rb
|