sentence_extractor 0.1.1 → 0.2.0
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/lib/sentence_extractor/extractor.rb +1 -1
- data/lib/sentence_extractor/version.rb +1 -1
- data/sentence_extractor.gemspec +1 -0
- data/spec/extractor_spec.rb +29 -0
- metadata +24 -9
@@ -45,7 +45,7 @@ module SentenceExtractor
|
|
45
45
|
while match != nil
|
46
46
|
sentence_end_point = remaining_text =~ /#{@reg_exp}/ # check for sentences
|
47
47
|
if sentence_end_point
|
48
|
-
sentences << remaining_text[0..sentence_end_point] # add new sentence to array
|
48
|
+
sentences << remaining_text[0..sentence_end_point].strip # add new sentence to array
|
49
49
|
remaining_text = remaining_text[sentence_end_point+1..remaining_text.size] # set the rest of the text to be processed.
|
50
50
|
else
|
51
51
|
match = nil
|
data/sentence_extractor.gemspec
CHANGED
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'lib/sentence_extractor.rb'
|
2
|
+
|
3
|
+
describe SentenceExtractor::Extractor do
|
4
|
+
it "Sould find a sentence with a full stop" do
|
5
|
+
sen_exc = SentenceExtractor::Extractor.new
|
6
|
+
sen_exc.extract_sentences("Hello.").should eql(["Hello."])
|
7
|
+
end
|
8
|
+
|
9
|
+
it "Sould find a sentence with a exclamation mark" do
|
10
|
+
sen_exc = SentenceExtractor::Extractor.new
|
11
|
+
sen_exc.extract_sentences("Hello!").should eql(["Hello!"])
|
12
|
+
end
|
13
|
+
|
14
|
+
it "Sould find a sentence with a question mark" do
|
15
|
+
sen_exc = SentenceExtractor::Extractor.new
|
16
|
+
sen_exc.extract_sentences("Hello?").should eql(["Hello?"])
|
17
|
+
end
|
18
|
+
|
19
|
+
it "Should not find anything" do
|
20
|
+
sen_exc = SentenceExtractor::Extractor.new
|
21
|
+
sen_exc.extract_sentences("Hello").should eql([])
|
22
|
+
end
|
23
|
+
|
24
|
+
it "Should find three sentences with no leading or trailing spaces" do
|
25
|
+
sen_exc = SentenceExtractor::Extractor.new
|
26
|
+
sen_exc.extract_sentences("Hello. How are you? Good thanks! ").should eql(["Hello.", "How are you?", "Good thanks!"])
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sentence_extractor
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 23
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
|
-
-
|
9
|
-
-
|
10
|
-
version: 0.
|
8
|
+
- 2
|
9
|
+
- 0
|
10
|
+
version: 0.2.0
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Seb Glazebrook
|
@@ -15,9 +15,23 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2012-03-
|
19
|
-
dependencies:
|
20
|
-
|
18
|
+
date: 2012-03-23 00:00:00 Z
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: rspec
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - ~>
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
hash: 15
|
29
|
+
segments:
|
30
|
+
- 2
|
31
|
+
- 6
|
32
|
+
version: "2.6"
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
21
35
|
description: This gem takes takes a bunch of text and returns the sentences found based on language specific rules. E.g. start and end delimiters etc.
|
22
36
|
email:
|
23
37
|
- me@sebglazebrook.com
|
@@ -38,6 +52,7 @@ files:
|
|
38
52
|
- lib/sentence_extractor/extractor.rb
|
39
53
|
- lib/sentence_extractor/version.rb
|
40
54
|
- sentence_extractor.gemspec
|
55
|
+
- spec/extractor_spec.rb
|
41
56
|
homepage: ""
|
42
57
|
licenses: []
|
43
58
|
|
@@ -71,5 +86,5 @@ rubygems_version: 1.8.9
|
|
71
86
|
signing_key:
|
72
87
|
specification_version: 3
|
73
88
|
summary: Give it some text and it will return an array of sentences.
|
74
|
-
test_files:
|
75
|
-
|
89
|
+
test_files:
|
90
|
+
- spec/extractor_spec.rb
|