shingling 0.0.3

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in shingling.gemspec
+gemspec

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/lib/shingling.rb

@@ -0,0 +1,50 @@
+require "shingling/version"
+
+module Resemblance
+  class Shingling
+    def initialize(content = '', options = {})
+      @content = content
+      @shingle_length = options[:shingle_length] || 5
+      @stop_words = options[:stop_words] || []
+      @downcase = options[:downcase] || false
+      @replace_chars = options[:replace_chars] || {}
+    end
+
+    def each_shingles
+      word = ""
+      char_flag = false
+      shingling = []
+      position_end_words = []
+      position_start, position_end = 0, 0
+
+      @content.each_char do |char|
+        char = @replace_chars[char] if @replace_chars.key? char
+        if char !~ /[[:word:]]+/
+          char_flag = true
+        else
+          if char_flag
+            if !stop_word?(word) || word !~ /\S/
+              shingling << (@downcase ? Unicode::downcase(word) : word)
+              word = ""
+              position_end_words << position_end
+              if shingling.size == @shingle_length
+                yield(shingling, position_start, position_end - 1)
+                position_start = position_end_words.shift
+                shingling.shift
+              end
+            end
+            char_flag = false
+          end
+          word << char
+        end
+        position_end += 1
+      end        
+    end
+
+    private
+
+    def stop_word? word
+      @stop_words.include? word
+    end  
+  end
+end

data/lib/shingling/version.rb

@@ -0,0 +1,3 @@
+module Shingling
+  VERSION = "0.0.3"
+end

data/shingling.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "shingling/version"
+
+Gem::Specification.new do |s|
+  s.name        = "shingling"
+  s.version     = Shingling::VERSION
+  s.authors     = ["vad"]
+  s.email       = ["vad4msiu@gmail.com"]
+  s.homepage    = ""
+  s.summary     = "Shingling"
+  s.description = "Shingling"
+
+  s.rubyforge_project = "shingling"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+  
+  s.add_dependency "unicode"
+  s.add_development_dependency "rspec"
+end

data/spec/shingling_spec.rb

@@ -0,0 +1,5 @@
+require "shingling"
+
+describe Shingling do
+  it "Create test"
+end

metadata

@@ -0,0 +1,76 @@
+--- !ruby/object:Gem::Specification
+name: shingling
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+  prerelease: 
+platform: ruby
+authors:
+- vad
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-11-05 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: unicode
+  requirement: &2152592500 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2152592500
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &2152591880 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2152591880
+description: Shingling
+email:
+- vad4msiu@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/shingling.rb
+- lib/shingling/version.rb
+- shingling.gemspec
+- spec/shingling_spec.rb
+homepage: ''
+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: shingling
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Shingling
+test_files:
+- spec/shingling_spec.rb
+has_rdoc: