ngrams_parser 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/.ruby-gemset +1 -0
- data/.ruby-version +1 -0
- data/CHANGELOG.md +3 -0
- data/Gemfile +13 -0
- data/Guardfile +13 -0
- data/LICENSE.txt +22 -0
- data/README.md +43 -0
- data/Rakefile +10 -0
- data/lib/ngrams_parser.rb +7 -0
- data/lib/ngrams_parser/ngram.rb +15 -0
- data/lib/ngrams_parser/ngrams.rb +12 -0
- data/lib/ngrams_parser/string.rb +8 -0
- data/lib/ngrams_parser/version.rb +3 -0
- data/ngrams_parser.gemspec +24 -0
- data/spec/ngrams_parser/ngram_spec.rb +30 -0
- data/spec/ngrams_parser/ngrams_spec.rb +114 -0
- data/spec/ngrams_parser/string_spec.rb +29 -0
- data/spec/spec_helper.rb +9 -0
- metadata +110 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: fed54ec83869838172748c8260f8c48eeeed5be0
|
4
|
+
data.tar.gz: af4d624af9d708cfcd8624d32a6a605350ff554d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 633367af35abcb5298894de7464513fc271290ebe9fa21ccb198aadacdae3f1bb91aa8fd769088d2d4330f2d354dca3fd5057b1e70b0a133a0990feb4cea24b6
|
7
|
+
data.tar.gz: e359a7dc70271d7ee7c87715bdfc59de9c1c17c6ecc7f4018c86cb7311ca1883f41904aa60d32c694c5cded703ec90b13eed0864d031bfa5ec5f1b1fea9e49ab
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.ruby-gemset
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
ngrams_parser
|
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.0.0
|
data/CHANGELOG.md
ADDED
data/Gemfile
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
source 'https://rubygems.org'
|
2
|
+
|
3
|
+
# Specify your gem's dependencies in ngrams_parser.gemspec
|
4
|
+
gemspec
|
5
|
+
|
6
|
+
group :development, :test do
|
7
|
+
gem 'coveralls', require: false
|
8
|
+
gem 'rspec'
|
9
|
+
gem 'reek'
|
10
|
+
gem 'guard'
|
11
|
+
gem 'guard-bundler'
|
12
|
+
gem 'guard-rspec'
|
13
|
+
end
|
data/Guardfile
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
guard 'bundler' do
|
2
|
+
watch('Gemfile')
|
3
|
+
watch(/^.+\.gemspec/)
|
4
|
+
end
|
5
|
+
|
6
|
+
guard :rspec do
|
7
|
+
watch(%r{^spec/.+_spec\.rb$})
|
8
|
+
watch(%r{^lib/(.+)\.rb$}) do |array|
|
9
|
+
name = array.last
|
10
|
+
"spec/#{name}_spec.rb"
|
11
|
+
end
|
12
|
+
watch('spec/spec_helper.rb') { "spec" }
|
13
|
+
end
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Fractal Soft
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
# NgramsParser [![Gem Version](https://badge.fury.io/rb/ngrams_parser.png)](http://badge.fury.io/rb/ngrams_parser) [![Build Status](https://travis-ci.org/fractalsoft/ngrams_parser.png)](https://travis-ci.org/fractalsoft/ngrams_parser) [![Dependency Status](https://gemnasium.com/fractalsoft/ngrams_parser.png)](https://gemnasium.com/fractalsoft/ngrams_parser) [![Coverage Status](https://coveralls.io/repos/fractalsoft/ngrams_parser/badge.png)](https://coveralls.io/r/fractalsoft/ngrams_parser)
|
2
|
+
|
3
|
+
N-gram is a contiguous sequence of n items from a given sequence of text or speech. The items are letters, but can be phonemes, syllables, words or base pairs according to the application. The n-grams typically are collected from a text or speech corpus.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'ngrams_parser'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install ngrams_parser
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
```ruby
|
22
|
+
# splits single word into ngrams
|
23
|
+
NgramsParser::ngram(word, size)
|
24
|
+
|
25
|
+
# splits given text into ngrams
|
26
|
+
NgramsParser::ngrams(text, size)
|
27
|
+
```
|
28
|
+
|
29
|
+
You can use ngrams method into String class:
|
30
|
+
|
31
|
+
```ruby
|
32
|
+
class String
|
33
|
+
include NgramsParser::String
|
34
|
+
end
|
35
|
+
```
|
36
|
+
|
37
|
+
## Contributing
|
38
|
+
|
39
|
+
1. Fork it
|
40
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
41
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
42
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
43
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
module NgramsParser
|
3
|
+
# Split word into ngrams
|
4
|
+
#
|
5
|
+
# self.ngram("lorem", 2) #=> ["lo", "or", "re", "em", "m "]
|
6
|
+
# self.ngram("ipsum", 3) #=> ["ips", "psu", "sum", "um ", "m "]
|
7
|
+
def self.ngram(word, size)
|
8
|
+
array = []
|
9
|
+
word.split('').each_index do |index|
|
10
|
+
text = word[index..index+size-1]
|
11
|
+
array << text.ljust(size, ' ')
|
12
|
+
end
|
13
|
+
array
|
14
|
+
end
|
15
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'ngrams_parser/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ngrams_parser"
|
8
|
+
spec.version = NgramsParser::VERSION
|
9
|
+
spec.authors = ["Aleksander Malaszkiewicz"]
|
10
|
+
spec.email = ["info@fractalsoft.org"]
|
11
|
+
spec.summary = %q{Split text into ngrams}
|
12
|
+
spec.homepage = ""
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files`.split($/)
|
16
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
17
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
21
|
+
spec.add_development_dependency "rake"
|
22
|
+
|
23
|
+
spec.add_dependency "lexical_units"
|
24
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe NgramsParser do
|
4
|
+
context ".ngram" do
|
5
|
+
let(:klass) { NgramsParser }
|
6
|
+
|
7
|
+
[
|
8
|
+
{
|
9
|
+
text: "Will's",
|
10
|
+
digrams: ["Wi", "il", "ll", "l'", "'s", "s "],
|
11
|
+
trigrams: ["Wil", "ill", "ll'", "l's", "'s ", "s "],
|
12
|
+
},
|
13
|
+
{
|
14
|
+
text: "činčilový",
|
15
|
+
digrams: ["či", "in", "nč", "či", "il", "lo", "ov", "vý", "ý "],
|
16
|
+
trigrams: ["čin", "inč", "nči", "čil", "ilo", "lov", "ový", "vý ", "ý "]
|
17
|
+
}
|
18
|
+
].each do |hash|
|
19
|
+
text, bigrams, trigrams = hash.values
|
20
|
+
|
21
|
+
it "split word '#{text}' into bigrams: #{bigrams}" do
|
22
|
+
klass::ngram(text, 2).should eq(bigrams)
|
23
|
+
end
|
24
|
+
|
25
|
+
it "split word '#{text}' into trigrams: #{trigrams}" do
|
26
|
+
klass::ngram(text, 3).should eq(trigrams)
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,114 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe NgramsParser do
|
4
|
+
context ".ngrams" do
|
5
|
+
let(:klass) { NgramsParser }
|
6
|
+
|
7
|
+
[
|
8
|
+
{
|
9
|
+
text: "Will will Will will Will's will to Will?",
|
10
|
+
bigrams: [
|
11
|
+
["Wi", "il", "ll", "l ", "wi", "il", "ll", "l "],
|
12
|
+
["Wi", "il", "ll", "l ", "wi", "il", "ll", "l "],
|
13
|
+
["Wi", "il", "ll", "l'", "'s", "s ", "wi", "il", "ll", "l "],
|
14
|
+
["to", "o "],
|
15
|
+
["Wi", "il", "ll", "l "]
|
16
|
+
].flatten,
|
17
|
+
trigrams: [
|
18
|
+
["Wil", "ill", "ll ","l "],
|
19
|
+
["wil", "ill", "ll ", "l "],
|
20
|
+
["Wil", "ill", "ll ","l "],
|
21
|
+
["wil", "ill", "ll ", "l "],
|
22
|
+
["Wil", "ill", "ll'","l's", "'s ", "s "],
|
23
|
+
["wil", "ill", "ll ", "l "],
|
24
|
+
["to ", "o ", "Wil", "ill", "ll ", "l "]
|
25
|
+
].flatten
|
26
|
+
},
|
27
|
+
{
|
28
|
+
text: "Acht alte Ameisen aßen am Abend Ananas.",
|
29
|
+
bigrams: [
|
30
|
+
["Ac", "ch", "ht", "t "],
|
31
|
+
["al", "lt", "te", "e "],
|
32
|
+
["Am", "me", "ei", "is", "se", "en", "n "],
|
33
|
+
["aß", "ße", "en", "n "],
|
34
|
+
["am", "m "],
|
35
|
+
["Ab", "be", "en", "nd", "d "],
|
36
|
+
["An", "na", "an", "na", "as", "s "]
|
37
|
+
].flatten,
|
38
|
+
trigrams: [
|
39
|
+
["Ach", "cht", "ht ", "t "],
|
40
|
+
["alt", "lte", "te ", "e "],
|
41
|
+
["Ame", "mei", "eis", "ise", "sen", "en ", "n "],
|
42
|
+
["aße", "ßen", "en ", "n "],
|
43
|
+
["am ", "m "],
|
44
|
+
["Abe", "ben", "end", "nd ", "d "],
|
45
|
+
["Ana", "nan", "ana", "nas", "as ", "s "]
|
46
|
+
].flatten
|
47
|
+
},
|
48
|
+
{
|
49
|
+
text: "Ödögidöggi",
|
50
|
+
bigrams: ["Öd", "dö", "ög", "gi", "id", "dö", "ög", "gg", "gi", "i "],
|
51
|
+
trigrams: [
|
52
|
+
["Ödö", "dög", "ögi", "gid", "idö", "dög", "ögg", "ggi", "gi ", "i "]
|
53
|
+
].flatten
|
54
|
+
},
|
55
|
+
{
|
56
|
+
text: "Ćma ćmę ćmi.",
|
57
|
+
bigrams: [
|
58
|
+
["Ćm", "ma", "a ", "ćm", "mę", "ę ", "ćm", "mi", "i "]
|
59
|
+
].flatten,
|
60
|
+
trigrams: [
|
61
|
+
["Ćma", "ma ", "a ", "ćmę", "mę ", "ę ", "ćmi", "mi ", "i "]
|
62
|
+
].flatten
|
63
|
+
},
|
64
|
+
{
|
65
|
+
text: "Łzy złej zołzy",
|
66
|
+
bigrams: [
|
67
|
+
["Łz", "zy", "y ", "zł", "łe", "ej", "j "],
|
68
|
+
["zo", "oł", "łz", "zy", "y "]
|
69
|
+
].flatten,
|
70
|
+
trigrams: [
|
71
|
+
["Łzy", "zy ", "y ", "złe", "łej", "ej ", "j "],
|
72
|
+
["zoł", "ołz", "łzy", "zy ", "y "]
|
73
|
+
].flatten
|
74
|
+
},
|
75
|
+
{
|
76
|
+
text: "Żubr żuł żuchwą żurawinę.",
|
77
|
+
bigrams: [
|
78
|
+
["Żu", "ub", "br", "r ", "żu", "uł", "ł "],
|
79
|
+
["żu", "uc", "ch", "hw", "wą", "ą "],
|
80
|
+
["żu", "ur", "ra", "aw", "wi", "in", "nę", "ę "]
|
81
|
+
].flatten,
|
82
|
+
trigrams: [
|
83
|
+
["Żub", "ubr", "br ", "r ", "żuł", "uł ", "ł "],
|
84
|
+
["żuc", "uch", "chw", "hwą", "wą ", "ą "],
|
85
|
+
["żur", "ura", "raw", "awi", "win", "inę", "nę ", "ę "]
|
86
|
+
].flatten
|
87
|
+
},
|
88
|
+
{
|
89
|
+
text: "Čistý s Čistou čistili činčilový čepec.",
|
90
|
+
bigrams: [
|
91
|
+
["Či", "is", "st", "tý", "ý ", "s ", "Či", "is", "st", "to", "ou"],
|
92
|
+
["u ", "či", "is", "st", "ti", "il", "li", "i ", "či", "in", "nč"],
|
93
|
+
["či", "il", "lo", "ov", "vý", "ý ", "če", "ep", "pe", "ec", "c "]
|
94
|
+
].flatten,
|
95
|
+
trigrams: [
|
96
|
+
["Čis", "ist", "stý", "tý ", "ý ", "s ", "Čis", "ist", "sto"],
|
97
|
+
["tou", "ou ", "u ", "čis", "ist", "sti", "til", "ili", "li "],
|
98
|
+
["i ", "čin", "inč", "nči", "čil", "ilo", "lov", "ový", "vý "],
|
99
|
+
["ý ", "čep", "epe", "pec", "ec ", "c "]
|
100
|
+
].flatten
|
101
|
+
}
|
102
|
+
].each do |hash|
|
103
|
+
text, bigrams, trigrams = hash.values
|
104
|
+
|
105
|
+
it "split text '#{text}' into bigrams" do
|
106
|
+
klass::ngrams(text, 2).should eq(bigrams)
|
107
|
+
end
|
108
|
+
|
109
|
+
it "split text '#{text}' into trigrams" do
|
110
|
+
klass::ngrams(text, 3).should eq(trigrams)
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe NgramsParser::String do
|
4
|
+
class String
|
5
|
+
include NgramsParser::String
|
6
|
+
end
|
7
|
+
|
8
|
+
context "#ngrams" do
|
9
|
+
it "splits String into ngrams" do
|
10
|
+
string = "Lorem ipsum"
|
11
|
+
bigrams = [
|
12
|
+
"Lo", "or", "re", "em", "m ",
|
13
|
+
"ip", "ps", "su", "um", "m "
|
14
|
+
]
|
15
|
+
trigrams = [
|
16
|
+
"Lor", "ore", "rem", "em ", "m ",
|
17
|
+
"ips", "psu", "sum", "um ", "m "
|
18
|
+
]
|
19
|
+
quadgrams = [
|
20
|
+
"Lore", "orem", "rem ", "em ", "m ",
|
21
|
+
"ipsu", "psum", "sum ", "um ", "m "
|
22
|
+
]
|
23
|
+
|
24
|
+
string.ngrams(2).should eq(bigrams)
|
25
|
+
string.ngrams(3).should eq(trigrams)
|
26
|
+
string.ngrams(4).should eq(quadgrams)
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,110 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ngrams_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Aleksander Malaszkiewicz
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-07-07 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: lexical_units
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description:
|
56
|
+
email:
|
57
|
+
- info@fractalsoft.org
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- .gitignore
|
63
|
+
- .rspec
|
64
|
+
- .ruby-gemset
|
65
|
+
- .ruby-version
|
66
|
+
- CHANGELOG.md
|
67
|
+
- Gemfile
|
68
|
+
- Guardfile
|
69
|
+
- LICENSE.txt
|
70
|
+
- README.md
|
71
|
+
- Rakefile
|
72
|
+
- lib/ngrams_parser.rb
|
73
|
+
- lib/ngrams_parser/ngram.rb
|
74
|
+
- lib/ngrams_parser/ngrams.rb
|
75
|
+
- lib/ngrams_parser/string.rb
|
76
|
+
- lib/ngrams_parser/version.rb
|
77
|
+
- ngrams_parser.gemspec
|
78
|
+
- spec/ngrams_parser/ngram_spec.rb
|
79
|
+
- spec/ngrams_parser/ngrams_spec.rb
|
80
|
+
- spec/ngrams_parser/string_spec.rb
|
81
|
+
- spec/spec_helper.rb
|
82
|
+
homepage: ''
|
83
|
+
licenses:
|
84
|
+
- MIT
|
85
|
+
metadata: {}
|
86
|
+
post_install_message:
|
87
|
+
rdoc_options: []
|
88
|
+
require_paths:
|
89
|
+
- lib
|
90
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
91
|
+
requirements:
|
92
|
+
- - '>='
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: '0'
|
95
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
96
|
+
requirements:
|
97
|
+
- - '>='
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: '0'
|
100
|
+
requirements: []
|
101
|
+
rubyforge_project:
|
102
|
+
rubygems_version: 2.0.3
|
103
|
+
signing_key:
|
104
|
+
specification_version: 4
|
105
|
+
summary: Split text into ngrams
|
106
|
+
test_files:
|
107
|
+
- spec/ngrams_parser/ngram_spec.rb
|
108
|
+
- spec/ngrams_parser/ngrams_spec.rb
|
109
|
+
- spec/ngrams_parser/string_spec.rb
|
110
|
+
- spec/spec_helper.rb
|