ngrams_parser 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: fed54ec83869838172748c8260f8c48eeeed5be0
+  data.tar.gz: af4d624af9d708cfcd8624d32a6a605350ff554d
+SHA512:
+  metadata.gz: 633367af35abcb5298894de7464513fc271290ebe9fa21ccb198aadacdae3f1bb91aa8fd769088d2d4330f2d354dca3fd5057b1e70b0a133a0990feb4cea24b6
+  data.tar.gz: e359a7dc70271d7ee7c87715bdfc59de9c1c17c6ecc7f4018c86cb7311ca1883f41904aa60d32c694c5cded703ec90b13eed0864d031bfa5ec5f1b1fea9e49ab

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format documentation

data/.ruby-gemset

@@ -0,0 +1 @@
+ngrams_parser

data/.ruby-version

@@ -0,0 +1 @@
+2.0.0

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+## v0.0.1
+
+* initial release

data/Gemfile

@@ -0,0 +1,13 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in ngrams_parser.gemspec
+gemspec
+
+group :development, :test do
+  gem 'coveralls', require: false
+  gem 'rspec'
+  gem 'reek'
+  gem 'guard'
+  gem 'guard-bundler'
+  gem 'guard-rspec'
+end

data/Guardfile

@@ -0,0 +1,13 @@
+guard 'bundler' do
+  watch('Gemfile')
+  watch(/^.+\.gemspec/)
+end
+
+guard :rspec do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$}) do |array|
+    name = array.last
+    "spec/#{name}_spec.rb"
+  end
+  watch('spec/spec_helper.rb')  { "spec" }
+end

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Fractal Soft
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,43 @@
+# 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)
+
+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.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'ngrams_parser'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ngrams_parser
+
+## Usage
+
+```ruby
+# splits single word into ngrams
+NgramsParser::ngram(word, size)
+
+# splits given text into ngrams
+NgramsParser::ngrams(text, size)
+```
+
+You can use ngrams method into String class:
+
+```ruby
+class String
+  include NgramsParser::String
+end
+```
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require 'rspec/core/rake_task'
+
+desc 'Default: run specs.'
+task default: :spec
+
+desc "Run specs"
+RSpec::Core::RakeTask.new do |t|
+  t.rspec_opts = "--tag fast"
+end

data/lib/ngrams_parser.rb

@@ -0,0 +1,7 @@
+require "ngrams_parser/ngram"
+require "ngrams_parser/ngrams"
+require "ngrams_parser/string"
+require "ngrams_parser/version"
+
+module NgramsParser
+end

data/lib/ngrams_parser/ngram.rb

@@ -0,0 +1,15 @@
+# coding: utf-8
+module NgramsParser
+  # Split word into ngrams
+  #
+  #   self.ngram("lorem", 2) #=> ["lo", "or", "re", "em", "m "]
+  #   self.ngram("ipsum", 3) #=> ["ips", "psu", "sum", "um ", "m  "]
+  def self.ngram(word, size)
+    array = []
+    word.split('').each_index do |index|
+      text = word[index..index+size-1]
+      array << text.ljust(size, ' ')
+    end
+    array
+  end
+end

data/lib/ngrams_parser/ngrams.rb

@@ -0,0 +1,12 @@
+# coding: utf-8
+require 'lexical_units'
+
+module NgramsParser
+  def self.ngrams(text, size)
+    array = []
+    LexicalUnits::words(text).each do |word|
+      array << ngram(word, size)
+    end
+    array.flatten
+  end
+end

data/lib/ngrams_parser/string.rb

@@ -0,0 +1,8 @@
+# coding: utf-8
+module NgramsParser
+  module String
+    def ngrams(size)
+      NgramsParser::ngrams(self, size)
+    end
+  end
+end

data/lib/ngrams_parser/version.rb

@@ -0,0 +1,3 @@
+module NgramsParser
+  VERSION = "0.0.1"
+end

data/ngrams_parser.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'ngrams_parser/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "ngrams_parser"
+  spec.version       = NgramsParser::VERSION
+  spec.authors       = ["Aleksander Malaszkiewicz"]
+  spec.email         = ["info@fractalsoft.org"]
+  spec.summary       = %q{Split text into ngrams}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+
+  spec.add_dependency "lexical_units"
+end

data/spec/ngrams_parser/ngram_spec.rb

@@ -0,0 +1,30 @@
+require 'spec_helper'
+
+describe NgramsParser do
+  context ".ngram" do
+    let(:klass) { NgramsParser }
+
+    [
+      {
+        text: "Will's",
+        digrams: ["Wi", "il", "ll", "l'", "'s", "s "],
+        trigrams: ["Wil", "ill", "ll'", "l's", "'s ", "s  "],
+      },
+      {
+        text: "činčilový",
+        digrams: ["či", "in", "nč", "či", "il", "lo", "ov", "vý", "ý "],
+        trigrams: ["čin", "inč", "nči", "čil", "ilo", "lov", "ový", "vý ", "ý  "]
+      }
+    ].each do |hash|
+      text, bigrams, trigrams = hash.values
+
+      it "split word '#{text}' into bigrams: #{bigrams}" do
+        klass::ngram(text, 2).should eq(bigrams)
+      end
+
+      it "split word '#{text}' into trigrams: #{trigrams}" do
+        klass::ngram(text, 3).should eq(trigrams)
+      end
+    end
+  end
+end

data/spec/ngrams_parser/ngrams_spec.rb

@@ -0,0 +1,114 @@
+require 'spec_helper'
+
+describe NgramsParser do
+  context ".ngrams" do
+    let(:klass) { NgramsParser }
+
+    [
+      {
+        text: "Will will Will will Will's will to Will?",
+        bigrams: [
+          ["Wi", "il", "ll", "l ", "wi", "il", "ll", "l "],
+          ["Wi", "il", "ll", "l ", "wi", "il", "ll", "l "],
+          ["Wi", "il", "ll", "l'", "'s", "s ", "wi", "il", "ll", "l "],
+          ["to", "o "],
+          ["Wi", "il", "ll", "l "]
+        ].flatten,
+        trigrams: [
+          ["Wil", "ill", "ll ","l  "],
+          ["wil", "ill", "ll ", "l  "],
+          ["Wil", "ill", "ll ","l  "],
+          ["wil", "ill", "ll ", "l  "],
+          ["Wil", "ill", "ll'","l's", "'s ", "s  "],
+          ["wil", "ill", "ll ", "l  "],
+          ["to ", "o  ", "Wil", "ill", "ll ", "l  "]
+        ].flatten
+      },
+      {
+        text: "Acht alte Ameisen aßen am Abend Ananas.",
+        bigrams: [
+          ["Ac", "ch", "ht", "t "],
+          ["al", "lt", "te", "e "],
+          ["Am", "me", "ei", "is", "se", "en", "n "],
+          ["aß", "ße", "en", "n "],
+          ["am", "m "],
+          ["Ab", "be", "en", "nd", "d "],
+          ["An", "na", "an", "na", "as", "s "]
+        ].flatten,
+        trigrams: [
+          ["Ach", "cht", "ht ", "t  "],
+          ["alt", "lte", "te ", "e  "],
+          ["Ame", "mei", "eis", "ise", "sen", "en ", "n  "],
+          ["aße", "ßen", "en ", "n  "],
+          ["am ", "m  "],
+          ["Abe", "ben", "end", "nd ", "d  "],
+          ["Ana", "nan", "ana", "nas", "as ", "s  "]
+        ].flatten
+      },
+      {
+        text: "Ödögidöggi",
+        bigrams: ["Öd", "dö", "ög", "gi", "id", "dö", "ög", "gg", "gi", "i "],
+        trigrams: [
+          ["Ödö", "dög", "ögi", "gid", "idö", "dög", "ögg", "ggi", "gi ", "i  "]
+        ].flatten
+      },
+      {
+        text: "Ćma ćmę ćmi.",
+        bigrams: [
+          ["Ćm", "ma", "a ", "ćm", "mę", "ę ", "ćm", "mi", "i "]
+        ].flatten,
+        trigrams: [
+          ["Ćma", "ma ", "a  ", "ćmę", "mę ", "ę  ", "ćmi", "mi ", "i  "]
+        ].flatten
+      },
+      {
+        text: "Łzy złej zołzy",
+        bigrams: [
+          ["Łz", "zy", "y ", "zł", "łe", "ej", "j "],
+          ["zo", "oł", "łz", "zy", "y "]
+        ].flatten,
+        trigrams: [
+          ["Łzy", "zy ", "y  ", "złe", "łej", "ej ", "j  "],
+          ["zoł", "ołz", "łzy", "zy ", "y  "]
+        ].flatten
+      },
+      {
+        text: "Żubr żuł żuchwą żurawinę.",
+        bigrams: [
+          ["Żu", "ub", "br", "r ", "żu", "uł", "ł "],
+          ["żu", "uc", "ch", "hw", "wą", "ą "],
+          ["żu", "ur", "ra", "aw", "wi", "in", "nę", "ę "]
+        ].flatten,
+        trigrams: [
+          ["Żub", "ubr", "br ", "r  ", "żuł", "uł ", "ł  "],
+          ["żuc", "uch", "chw", "hwą", "wą ", "ą  "],
+          ["żur", "ura", "raw", "awi", "win", "inę", "nę ", "ę  "]
+        ].flatten
+      },
+      {
+        text: "Čistý s Čistou čistili činčilový čepec.",
+        bigrams: [
+          ["Či", "is", "st", "tý", "ý ", "s ", "Či", "is", "st", "to", "ou"],
+          ["u ", "či", "is", "st", "ti", "il", "li", "i ", "či", "in", "nč"],
+          ["či", "il", "lo", "ov", "vý", "ý ", "če", "ep", "pe", "ec", "c "]
+        ].flatten,
+        trigrams: [
+          ["Čis", "ist", "stý", "tý ", "ý  ", "s  ", "Čis", "ist", "sto"],
+          ["tou", "ou ", "u  ", "čis", "ist", "sti", "til", "ili", "li "],
+          ["i  ", "čin", "inč", "nči", "čil", "ilo", "lov", "ový", "vý "],
+          ["ý  ", "čep", "epe", "pec", "ec ", "c  "]
+        ].flatten
+      }
+    ].each do |hash|
+      text, bigrams, trigrams = hash.values
+
+      it "split text '#{text}' into bigrams" do
+        klass::ngrams(text, 2).should eq(bigrams)
+      end
+
+      it "split text '#{text}' into trigrams" do
+        klass::ngrams(text, 3).should eq(trigrams)
+      end
+    end
+  end
+end

data/spec/ngrams_parser/string_spec.rb

@@ -0,0 +1,29 @@
+require 'spec_helper'
+
+describe NgramsParser::String do
+  class String
+    include NgramsParser::String
+  end
+
+  context "#ngrams" do
+    it "splits String into ngrams" do
+      string = "Lorem ipsum"
+      bigrams = [
+        "Lo", "or", "re", "em", "m ",
+        "ip", "ps", "su", "um", "m "
+      ]
+      trigrams = [
+        "Lor", "ore", "rem", "em ", "m  ",
+        "ips", "psu", "sum", "um ", "m  "
+      ]
+      quadgrams = [
+        "Lore", "orem", "rem ", "em  ", "m   ",
+        "ipsu", "psum", "sum ", "um  ", "m   "
+      ]
+
+      string.ngrams(2).should eq(bigrams)
+      string.ngrams(3).should eq(trigrams)
+      string.ngrams(4).should eq(quadgrams)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+require 'ngrams_parser'
+require 'coveralls'
+Coveralls.wear!
+
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+end

metadata

@@ -0,0 +1,110 @@
+--- !ruby/object:Gem::Specification
+name: ngrams_parser
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Aleksander Malaszkiewicz
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-07-07 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: lexical_units
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 
+email:
+- info@fractalsoft.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- .ruby-gemset
+- .ruby-version
+- CHANGELOG.md
+- Gemfile
+- Guardfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/ngrams_parser.rb
+- lib/ngrams_parser/ngram.rb
+- lib/ngrams_parser/ngrams.rb
+- lib/ngrams_parser/string.rb
+- lib/ngrams_parser/version.rb
+- ngrams_parser.gemspec
+- spec/ngrams_parser/ngram_spec.rb
+- spec/ngrams_parser/ngrams_spec.rb
+- spec/ngrams_parser/string_spec.rb
+- spec/spec_helper.rb
+homepage: ''
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Split text into ngrams
+test_files:
+- spec/ngrams_parser/ngram_spec.rb
+- spec/ngrams_parser/ngrams_spec.rb
+- spec/ngrams_parser/string_spec.rb
+- spec/spec_helper.rb