lexical_units 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +4 -0
- data/README.md +1 -0
- data/lib/lexical_units.rb +1 -0
- data/lib/lexical_units/syllables.rb +5 -0
- data/lib/lexical_units/version.rb +1 -1
- data/lib/lexical_units/words.rb +3 -1
- data/spec/lexical_units/sentences_spec.rb +5 -7
- data/spec/lexical_units/syllables_spec.rb +8 -0
- data/spec/lexical_units/words_spec.rb +34 -21
- metadata +5 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: fb575468ab234bcb093fc2afef714783d6aaf1e6
|
|
4
|
+
data.tar.gz: 90dc07a58c80092a35eec789d753be608e9af013
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a40c9845569546f2014908aa585bd68ffd1207232aac5eb6870ce435acafb5fb64342721eccb5187ecfc34f9c8bc042f643cf4fc6fce08af17782fe892af5485
|
|
7
|
+
data.tar.gz: 7d2eaf43d6faa80ec1fe3da6bc6d0f40e22554e2e8e7416906a88636566f1cf4ba6faf09b48234cc23dee1ed1c6f61aa47d3b9f599460aa9862a4af858fbbb7d
|
data/CHANGELOG.md
CHANGED
data/README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
# LexicalUnits [](http://badge.fury.io/rb/lexical_units) [](https://travis-ci.org/fractalsoft/lexical_units) [](https://gemnasium.com/fractalsoft/lexical_units) [](https://coveralls.io/r/fractalsoft/lexical_units)
|
|
2
|
+
[](https://coderwall.com/torrocus)
|
|
2
3
|
|
|
3
4
|
Lexical unit is a single word, a part of a word, or a chain of words that forms the basic elements of a language's lexicon.
|
|
4
5
|
|
data/lib/lexical_units.rb
CHANGED
data/lib/lexical_units/words.rb
CHANGED
|
@@ -3,8 +3,6 @@ require 'spec_helper'
|
|
|
3
3
|
|
|
4
4
|
describe LexicalUnits do
|
|
5
5
|
context ".sentences" do
|
|
6
|
-
let(:klass) { LexicalUnits }
|
|
7
|
-
|
|
8
6
|
it "splits text into sentences" do
|
|
9
7
|
text = %q{Lorem ipsum dolor sit amet, consectetur adipiscing elit.
|
|
10
8
|
Fusce ut lacinia lorem. Nullam a sem quam. Duis faucibus tortor in.}
|
|
@@ -15,7 +13,7 @@ describe LexicalUnits do
|
|
|
15
13
|
"Duis faucibus tortor in."
|
|
16
14
|
]
|
|
17
15
|
|
|
18
|
-
|
|
16
|
+
subject.sentences(text).should eq(array)
|
|
19
17
|
end
|
|
20
18
|
|
|
21
19
|
it "splits text with question mark and exclamation mark into sentences" do
|
|
@@ -26,7 +24,7 @@ describe LexicalUnits do
|
|
|
26
24
|
"Consectetur adipiscing elit."
|
|
27
25
|
]
|
|
28
26
|
|
|
29
|
-
|
|
27
|
+
subject.sentences(text).should eq(array)
|
|
30
28
|
end
|
|
31
29
|
|
|
32
30
|
it "splits text with ellipsis into sentences" do
|
|
@@ -36,7 +34,7 @@ describe LexicalUnits do
|
|
|
36
34
|
"Consectetur adipiscing elit."
|
|
37
35
|
]
|
|
38
36
|
|
|
39
|
-
|
|
37
|
+
subject.sentences(text).should eq(array)
|
|
40
38
|
end
|
|
41
39
|
|
|
42
40
|
it "splits text with interrobangs into sentences" do
|
|
@@ -48,8 +46,8 @@ describe LexicalUnits do
|
|
|
48
46
|
"Really?"
|
|
49
47
|
]
|
|
50
48
|
|
|
51
|
-
|
|
49
|
+
subject.sentences(text).should eq(array)
|
|
52
50
|
end
|
|
53
51
|
|
|
54
52
|
end
|
|
55
|
-
end
|
|
53
|
+
end
|
|
@@ -3,76 +3,89 @@ require 'spec_helper'
|
|
|
3
3
|
|
|
4
4
|
describe LexicalUnits do
|
|
5
5
|
context ".words" do
|
|
6
|
-
|
|
6
|
+
before do
|
|
7
|
+
@array = %w(Lorem ipsum dolor sit amet)
|
|
8
|
+
end
|
|
7
9
|
|
|
8
10
|
it "splits text with whitespaces into words" do
|
|
9
11
|
text = "Lorem ipsum dolor sit amet"
|
|
10
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
11
12
|
|
|
12
|
-
|
|
13
|
+
subject.words(text).should eq(@array)
|
|
13
14
|
end
|
|
14
15
|
|
|
15
16
|
it "splits text with comma, colon and semicolon into words" do
|
|
16
17
|
text = "Lorem ipsum,dolor:sit;amet"
|
|
17
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
18
18
|
|
|
19
|
-
|
|
19
|
+
subject.words(text).should eq(@array)
|
|
20
20
|
end
|
|
21
21
|
|
|
22
22
|
it "splits text with dot, question mark and exclamation mark into words" do
|
|
23
23
|
text = "Lorem ipsum.dolor?sit!amet"
|
|
24
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
25
24
|
|
|
26
|
-
|
|
25
|
+
subject.words(text).should eq(@array)
|
|
27
26
|
end
|
|
28
27
|
|
|
29
28
|
it "splits other text with whitespaces, comma and dot into words" do
|
|
30
29
|
text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit."
|
|
31
30
|
array = %w(Lorem ipsum dolor sit amet consectetur adipiscing elit)
|
|
32
31
|
|
|
33
|
-
|
|
32
|
+
subject.words(text).should eq(array)
|
|
34
33
|
end
|
|
35
34
|
|
|
36
35
|
it "splits text with hyphen into words" do
|
|
37
36
|
text = "Lorem ipsum dolor-sit amet"
|
|
38
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
39
37
|
|
|
40
|
-
|
|
38
|
+
subject.words(text).should eq(@array)
|
|
41
39
|
end
|
|
42
40
|
|
|
43
41
|
it "splits text with slash into words" do
|
|
44
42
|
text = "Lorem ipsum dolor sit/amet"
|
|
45
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
46
43
|
|
|
47
|
-
|
|
44
|
+
subject.words(text).should eq(@array)
|
|
48
45
|
end
|
|
49
46
|
|
|
50
47
|
it "splits text with round brackets into words" do
|
|
51
48
|
text = "Lorem ipsum(dolor sit)amet"
|
|
52
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
53
49
|
|
|
54
|
-
|
|
50
|
+
subject.words(text).should eq(@array)
|
|
55
51
|
end
|
|
56
52
|
|
|
57
53
|
it "splits text with square brackets into words" do
|
|
58
54
|
text = "Lorem ipsum dolor[sit]amet"
|
|
59
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
60
55
|
|
|
61
|
-
|
|
56
|
+
subject.words(text).should eq(@array)
|
|
62
57
|
end
|
|
63
58
|
|
|
64
59
|
it "splits text with pointy brackets into words" do
|
|
65
60
|
text = "Lorem<ipsum dolor sit>amet"
|
|
66
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
67
61
|
|
|
68
|
-
|
|
62
|
+
subject.words(text).should eq(@array)
|
|
69
63
|
end
|
|
70
64
|
|
|
71
65
|
it "splits text with braces into words" do
|
|
72
66
|
text = "Lorem ipsum{dolor}sit amet"
|
|
73
|
-
array = %w(Lorem ipsum dolor sit amet)
|
|
74
67
|
|
|
75
|
-
|
|
68
|
+
subject.words(text).should eq(@array)
|
|
69
|
+
end
|
|
70
|
+
|
|
71
|
+
it "splits text with vertical bar into words" do
|
|
72
|
+
text = "Lorem ipsum|dolor sit amet"
|
|
73
|
+
|
|
74
|
+
subject.words(text).should eq(@array)
|
|
76
75
|
end
|
|
76
|
+
|
|
77
|
+
it "splits text with tilde into words" do
|
|
78
|
+
text = "Lorem ipsum dolor~sit amet"
|
|
79
|
+
|
|
80
|
+
subject.words(text).should eq(@array)
|
|
81
|
+
end
|
|
82
|
+
|
|
83
|
+
# Spanish
|
|
84
|
+
it "splits text with inverted question and exclamation marks into words" do
|
|
85
|
+
text = "Lorem¿ipsum?dolor¡sit!amet"
|
|
86
|
+
|
|
87
|
+
subject.words(text).should eq(@array)
|
|
88
|
+
end
|
|
89
|
+
|
|
77
90
|
end
|
|
78
|
-
end
|
|
91
|
+
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: lexical_units
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Aleksander Malaszkiewicz
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2013-07-
|
|
11
|
+
date: 2013-07-11 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -60,10 +60,12 @@ files:
|
|
|
60
60
|
- lib/lexical_units.rb
|
|
61
61
|
- lib/lexical_units/sentences.rb
|
|
62
62
|
- lib/lexical_units/string.rb
|
|
63
|
+
- lib/lexical_units/syllables.rb
|
|
63
64
|
- lib/lexical_units/version.rb
|
|
64
65
|
- lib/lexical_units/words.rb
|
|
65
66
|
- spec/lexical_units/sentences_spec.rb
|
|
66
67
|
- spec/lexical_units/string_spec.rb
|
|
68
|
+
- spec/lexical_units/syllables_spec.rb
|
|
67
69
|
- spec/lexical_units/words_spec.rb
|
|
68
70
|
- spec/spec_helper.rb
|
|
69
71
|
homepage: ''
|
|
@@ -93,5 +95,6 @@ summary: Split text into lexical units
|
|
|
93
95
|
test_files:
|
|
94
96
|
- spec/lexical_units/sentences_spec.rb
|
|
95
97
|
- spec/lexical_units/string_spec.rb
|
|
98
|
+
- spec/lexical_units/syllables_spec.rb
|
|
96
99
|
- spec/lexical_units/words_spec.rb
|
|
97
100
|
- spec/spec_helper.rb
|