yasc 0.0.1

data/lib/yasc/spelling_corrector.rb

@@ -0,0 +1,48 @@
+# require 'open-uri'
+module Yasc
+  class SpellingCorrector
+    class << self
+      def words text
+        text.downcase.scan(/[a-z]+/)
+      end
+
+      def train features
+        model = Hash.new(1)
+        features.each {|f| model[f] += 1 }
+        return model
+      end
+
+      def edits1 word
+        n = word.length
+        deletion = (0...n).collect {|i| word[0...i]+word[i+1..-1] }
+        transposition = (0...n-1).collect {|i| word[0...i]+word[i+1,1]+word[i,1]+word[i+2..-1] }
+        alteration = []
+        n.times {|i| LETTERS.each_byte {|l| alteration << word[0...i]+l.chr+word[i+1..-1] } }
+        insertion = []
+        (n+1).times {|i| LETTERS.each_byte {|l| insertion << word[0...i]+l.chr+word[i..-1] } }
+        result = deletion + transposition + alteration + insertion
+        result.empty? ? nil : result
+      end
+
+      def known_edits2 word
+        result = []
+        edits1(word).each {|e1| edits1(e1).each {|e2| result << e2 if NWORDS.has_key?(e2) }}
+        result.empty? ? nil : result
+      end
+
+      def known words
+        result = words.find_all {|w| NWORDS.has_key?(w) }
+        result.empty? ? nil : result
+      end
+
+      def correct word
+        (known([word]) or known(edits1(word)) or known_edits2(word) or
+          [word]).max {|a,b| NWORDS[a] <=> NWORDS[b] }
+      end
+    end
+  
+    # NWORDS = train(words(open('http://norvig.com/big.txt') {|f| f.read }))
+    NWORDS = train(words(File.new('big.txt').read))
+    LETTERS = ("a".."z").to_a.join
+  end
+end

data/lib/yasc/version.rb

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

data/yasc.gemspec

@@ -0,0 +1,17 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/yasc/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Yu Zhang"]
+  gem.email         = ["ian7zy@gmail.com"]
+  gem.description   = %q{Yet another spelling checker}
+  gem.summary       = %q{This gem implements the spelling checker following this tutorial http://norvig.com/spell-correct.html}
+  gem.homepage      = "https://github.com/ianzhang/yasc"
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "yasc"
+  gem.require_paths = ["lib"]
+  gem.version       = Yasc::VERSION
+end

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: yasc
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Yu Zhang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-08-13 00:00:00.000000000Z
+dependencies: []
+description: Yet another spelling checker
+email:
+- ian7zy@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .DS_Store
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- lib/.DS_Store
+- lib/yasc.rb
+- lib/yasc/.DS_Store
+- lib/yasc/big.txt
+- lib/yasc/spelling_corrector.rb
+- lib/yasc/version.rb
+- yasc.gemspec
+homepage: https://github.com/ianzhang/yasc
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: This gem implements the spelling checker following this tutorial http://norvig.com/spell-correct.html
+test_files: []