string_utility_belt 0.1.0

data/Rakefile

@@ -0,0 +1,51 @@
+# 
+# To change this template, choose Tools | Templates
+# and open the template in the editor.
+ 
+
+require 'rubygems'
+require 'rake'
+require 'rake/clean'
+require 'rake/gempackagetask'
+require 'rake/rdoctask'
+require 'rake/testtask'
+require 'spec/rake/spectask'
+
+spec = Gem::Specification.new do |s|
+  s.name = 'serradura-string_utility_belt'
+  s.version = '0.0.1'
+  s.has_rdoc = true
+  s.extra_rdoc_files = ['README', 'LICENSE']
+  s.summary = 'Your summary here'
+  s.description = s.summary
+  s.author = ''
+  s.email = ''
+  # s.executables = ['your_executable_here']
+  s.files = %w(LICENSE README Rakefile) + Dir.glob("{bin,lib,spec}/**/*")
+  s.require_path = "lib"
+  s.bindir = "bin"
+end
+
+Rake::GemPackageTask.new(spec) do |p|
+  p.gem_spec = spec
+  p.need_tar = true
+  p.need_zip = true
+end
+
+Rake::RDocTask.new do |rdoc|
+  files =['README', 'LICENSE', 'lib/**/*.rb']
+  rdoc.rdoc_files.add(files)
+  rdoc.main = "README" # page to start on
+  rdoc.title = "serradura-string_utility_belt Docs"
+  rdoc.rdoc_dir = 'doc/rdoc' # rdoc output folder
+  rdoc.options << '--line-numbers'
+end
+
+Rake::TestTask.new do |t|
+  t.test_files = FileList['test/**/*.rb']
+end
+
+Spec::Rake::SpecTask.new do |t|
+  t.spec_files = FileList['spec/**/*.rb']
+  t.libs << Dir["lib"]
+end

data/lib/general/general.rb

@@ -0,0 +1,28 @@
+
+module General
+
+  def words
+    self.scan(/\w[\w\'\-]*/)
+  end
+
+  def have_this_words? words_to_match, exact_word=false
+    helper_have_this_words? words_to_match, exact_word do |string, word, exact_world|
+      return false if (string !~ word.regex_me_to_search_ruby(:exact_word => exact_word, :case_insensitive => true))
+    end
+  end
+
+  def not_have_this_words? words_to_match, exact_word=false
+    helper_have_this_words? words_to_match, exact_word do |string, word, exact_world|
+      return false if (string =~ word.regex_me_to_search_ruby(:exact_word => exact_word, :case_insensitive => true))
+    end
+  end
+
+  private
+    def helper_have_this_words? words_to_match, exact_word
+      for word in words_to_match
+        yield self, word, exact_word
+      end
+      return true
+    end
+
+end

data/lib/html_and_aml/helpers/entities.rb

@@ -0,0 +1,16 @@
+
+require "rubygems" if RUBY_VERSION < "1.9"
+require "htmlentities"
+
+module Entities
+
+  def decode_entities
+    coder = HTMLEntities.new
+    coder.decode(self)
+  end
+
+  def decode_entities_and_cleaner
+    decode_entities.tag_cleaner
+  end
+
+end

data/lib/html_and_aml/helpers/tags.rb

@@ -0,0 +1,13 @@
+
+module Tags
+
+  def tag_cleaner
+    self.gsub(/<\/?[^>]*>/, "")
+  end
+
+  def html_tag_cleaner
+    sef.gsub(/<\/?(a|abbr|acronym|address|applet|area|b|base|basefont|bdo|big|blockquote|body|br|button|caption|center|cite|code|col|colgroup|dd|del|dfn|dir|div|dl|dt|em|fieldset|font|form|frame|frameset|h6|head|hr|html|i|iframe|img|input|ins|isindex|kbd|label|legend|li|link|map|menu|meta|noframes|noscript|object)[^>]+??>/im, "")
+    # TAGs disponíveis até 09/2010 - FONTE: http://www.w3schools.com/tags/default.asp
+  end
+
+end

data/lib/html_and_aml/html_and_aml.rb

@@ -0,0 +1,10 @@
+
+require File.join(File.dirname(__FILE__), "helpers/entities")
+require File.join(File.dirname(__FILE__), "helpers/tags")
+
+module HtmlAndAML # == HTML And Another Markup Language
+
+  include Entities
+  include Tags
+
+end

data/lib/match_rank/match_rank.rb

@@ -0,0 +1,43 @@
+
+module MatchRank
+
+  def match_and_score_by words_to_match
+    freq = self.total_frequency_by words_to_match
+    statistic = {:exact => freq[:exact].to_f, :matched => freq[:matched].to_f, :precision => 0.0}
+    
+    statistic[:precision] = (statistic[:exact] / statistic[:matched]) * 100
+
+    return statistic
+  end
+
+  private
+    def frequency_by words_to_match, frequency_object_a, frequency_object_b
+      self_words = self.words
+      freq = {:exact => frequency_object_a, :matched => frequency_object_b}
+
+      for word_to_match in words_to_match
+        for word in self_words
+          yield freq, word_to_match, word
+        end
+      end
+
+      return freq
+    end
+
+  public
+    def words_frequency_by words_to_match
+      frequency_by(words_to_match, Hash.new(0), Hash.new(0)) do |freq, word_to_match, word|
+          freq[:exact][word_to_match]   += 1 if word =~ word_to_match.regex_me_to_search_ruby(:exact_word => true  , :case_insensitive => true)
+          freq[:matched][word_to_match] += 1 if word =~ word_to_match.regex_me_to_search_ruby(:exact_word => false , :case_insensitive => true)
+      end
+    end
+
+    def total_frequency_by words_to_match
+      frequency_by(words_to_match, 0, 0) do |freq, word_to_match, word|
+        freq[:exact]   += 1 if word =~ word_to_match.regex_me_to_search_ruby(:exact_word => true  , :case_insensitive => true)
+        freq[:matched] += 1 if word =~ word_to_match.regex_me_to_search_ruby(:exact_word => false , :case_insensitive => true)
+      end
+    end
+
+end
+

data/lib/regex_me/helpers/string/regex_me.rb

@@ -0,0 +1,41 @@
+
+class String
+
+  def regex_builder options={}
+    self.gsub!(/\*/,'.*')                   if options[:any]
+    border_me(options[:border][:to],
+              options[:border][:direction]) if options[:border]
+    insert_OR_in_right                  unless options[:delete_or]
+    self
+  end
+
+  private
+    def insert_OR_in_right
+      self.insert(-1, "|")
+    end
+
+    def border_me border_to, direction
+      border = define_border_metachar(border_to)
+
+      case direction
+        when :left
+         self.insert(0, border[:left])
+        when :right
+         self.insert(-1, border[:right])
+        when :both
+         self.insert(0, border[:left]).insert(-1, border[:right])
+        when nil
+         self
+      end
+    end
+
+    def define_border_metachar border_to
+      case border_to
+        when :ruby
+          {:left => '\b'     , :right => '\b'}
+        when :mysql
+          {:left => '[[:<:]]', :right => '[[:>:]]'}
+      end
+    end
+
+end

data/lib/regex_me/regex_me.rb

@@ -0,0 +1,81 @@
+
+require File.join(File.dirname(__FILE__), "helpers", "string", "regex_me")
+
+module RegexMe
+
+  module To
+
+    module Search
+
+      private
+        def options_handler options
+           {
+            :exact_word       =>  options[:exact_word],
+            :case_insensitive => (options[:case_insensitive] ? :i : nil ),
+            :m                => (options[:m] ? :m : nil ),
+            :exact_phrase     =>  options[:exact_phrase]
+           }
+        end
+
+      private
+        def regex_me_to_search regex_empty, border_to, options
+            opt_handled = options_handler(options)
+
+            return regex_empty if self.strip.empty?
+            execute_builder(self, opt_handled, border_to)
+        end
+
+
+      public
+        def regex_me_to_search_ruby options={}
+            regex_me_to_search(//, :ruby, options)
+        end
+
+        def regex_me_to_search_mysql options={}
+            regex_me_to_search("", :mysql, options)
+        end
+
+      private
+        def execute_builder string, opt_handled, border_to
+          result_builder = builder(string, opt_handled[:exact_word], border_to, opt_handled[:exact_phrase])
+
+          case border_to
+            when :ruby
+              eval "/#{result_builder}/#{opt_handled[:case_insensitive]}#{opt_handled[:m]}"
+            when :mysql
+              result_builder.gsub(/\\b/,"[[:<:]]").gsub(/\\b$/, "[[:>:]])")
+          end
+
+        end
+
+        def builder string, exact_word, border_to, exact_phrase
+
+          if exact_phrase
+            regexp = string.gsub(/\s+/, " ").gsub(/\s/, '[^0-9a-zA-Z\_]+').regex_builder(:delete_or => true, :border => {:to => border_to, :direction => :both})
+          else
+            regexp = '('
+
+            for word in string.strip.split
+              case word
+                when/^\*/
+                  regexp << word.regex_builder(:any => true, :border => {:to => border_to, :direction => :right})
+                when /\*$/
+                  regexp << word.regex_builder(:any => true, :border => {:to => border_to, :direction => :left})
+                when /^.*\*.*$/
+                  regexp << word.regex_builder(:any => true, :border => {:to => border_to, :direction => :both})
+                else
+                  regexp << (exact_word ? word.regex_builder(:border => {:to => border_to, :direction => :both}) : word.regex_builder)
+              end
+            end
+
+            regexp = (regexp << ')').sub!(/\|\)/,')')
+          end
+
+          return regexp
+        end
+
+    end
+
+  end
+
+end

data/lib/string_utility_belt/version.rb

@@ -0,0 +1,8 @@
+module StringUtilityBelt
+	module Version
+		MAJOR  = 0
+		MINOR  = 1
+		PATCH  = 0
+		STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
+	end
+end

data/lib/string_utility_belt.rb

@@ -0,0 +1,18 @@
+
+require "general/general"
+require "html_and_aml/html_and_aml"
+require "match_rank/match_rank"
+require "regex_me/regex_me"
+
+module StringUtilityBelt
+
+  include RegexMe::To::Search
+  include MatchRank
+  include General
+  include HtmlAndAML
+
+end
+
+class String
+	include StringUtilityBelt
+end

data/string_utility_belt.gemspec

@@ -0,0 +1,10 @@
+$LOAD_PATH << File.join(File.dirname(__FILE__), 'lib')
+
+Gem::Specification.new do |s|
+	s.name        = "string_utility_belt"
+	s.version     = "0.1.0"
+	s.description = "Useful methods for strings!"
+	s.summary     = "Useful methods for strings!"
+	s.author      = "Rodrigo Serradura"
+	s.files       = Dir["{lib/**/*.rb,lib/**/**/*.rb,lib/**/**/**/*.rb,README.rdoc,Rakefile,*.gemspec}"]
+end

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification 
+name: string_utility_belt
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Rodrigo Serradura
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-09-02 00:00:00 -03:00
+default_executable: 
+dependencies: []
+
+description: Useful methods for strings!
+email: 
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/html_and_aml/helpers/tags.rb
+- lib/html_and_aml/helpers/entities.rb
+- lib/html_and_aml/html_and_aml.rb
+- lib/string_utility_belt.rb
+- lib/regex_me/regex_me.rb
+- lib/regex_me/helpers/string/regex_me.rb
+- lib/general/general.rb
+- lib/match_rank/match_rank.rb
+- lib/string_utility_belt/version.rb
+- Rakefile
+- string_utility_belt.gemspec
+has_rdoc: true
+homepage: 
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Useful methods for strings!
+test_files: []
+