ngram 1.0.0

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.
Files changed (3) hide show
  1. checksums.yaml +7 -0
  2. data/lib/ngram.rb +29 -0
  3. metadata +59 -0
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ data.tar.gz: 24d70550296074ff0c420c90f3c6dea8bf9c97d1
4
+ metadata.gz: 5a098b7eba2e5a37f01e09d52e5fda018bb630ba
5
+ SHA512:
6
+ data.tar.gz: 235df4e836d8f556c9835c825b263c11863e4a7d339db14f07620099cd47c551c4f149044cba43a7c4ffc32729d75690a969d9ff783735df7869e3e9df820e74
7
+ metadata.gz: 6bbb302861599e7f8d1ec2bd5ea70783aaa46286cc249bd1c759d725c8849caf89a736e1510cbf2a78a0e3c86f684bf5a237d3273657dbe3d7c47cf2a5294180
@@ -0,0 +1,29 @@
1
+ class NGram
2
+ VERSION = "1.0.0"
3
+
4
+ attr_accessor :size, :word_separator, :padchar
5
+
6
+ def initialize(opts={})
7
+ @size = opts[:size]||2
8
+ @word_separator = opts[:word_separator]||" "
9
+ @padchar = opts[:padchar]||"_"
10
+ end
11
+
12
+ def parse(phrase)
13
+ words = phrase.split(@separator)
14
+ if words.length == 1
15
+ process(phrase)
16
+ else
17
+ words.map { |w| process(w) }
18
+ end
19
+ end
20
+
21
+ def process(word)
22
+ pad = @padchar*(@size-1)
23
+ word = "#{pad}#{word}#{pad}"
24
+ (0..word.length - @size).map do |idx|
25
+ "#{word[idx, @size]}"
26
+ end
27
+ end
28
+ private :process
29
+ end
metadata ADDED
@@ -0,0 +1,59 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: ngram
3
+ version: !ruby/object:Gem::Version
4
+ version: 1.0.0
5
+ platform: ruby
6
+ authors:
7
+ - Tyler Kellen
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+
12
+ date: 2013-12-12 00:00:00 Z
13
+ dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: rspec
16
+ prerelease: false
17
+ requirement: &id001 !ruby/object:Gem::Requirement
18
+ requirements:
19
+ - &id002
20
+ - ">="
21
+ - !ruby/object:Gem::Version
22
+ version: "0"
23
+ type: :development
24
+ version_requirements: *id001
25
+ description: Break words and phrases into ngrams.
26
+ email: tyler@sleekcode.net
27
+ executables: []
28
+
29
+ extensions: []
30
+
31
+ extra_rdoc_files: []
32
+
33
+ files:
34
+ - lib/ngram.rb
35
+ homepage: https://github.com/tkellen/ruby-ngram
36
+ licenses:
37
+ - MIT
38
+ metadata: {}
39
+
40
+ post_install_message:
41
+ rdoc_options: []
42
+
43
+ require_paths:
44
+ - lib
45
+ required_ruby_version: !ruby/object:Gem::Requirement
46
+ requirements:
47
+ - *id002
48
+ required_rubygems_version: !ruby/object:Gem::Requirement
49
+ requirements:
50
+ - *id002
51
+ requirements: []
52
+
53
+ rubyforge_project:
54
+ rubygems_version: 2.1.11
55
+ signing_key:
56
+ specification_version: 4
57
+ summary: Break words and phrases into ngrams.
58
+ test_files: []
59
+