boogex 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: f9474689b9e61cffbef211549d9e942254c1d0e8
+  data.tar.gz: f56c73ade74210ca6aa2a82e69936e7bedeb678a
+SHA512:
+  metadata.gz: 19d9416eb7d615dee24a748f0405f81eb188264e168576ff66cba4e0086d790149605a3f3b09b1696e33cba81ec39c8ecf7c71587e4e838db68a3831d19b6c6f
+  data.tar.gz: 41d95f425232c4ee624570d6121606cb65ef134919302f18aa458d278fec408963afdd80744b13fce032aabf72e0ebca5e8d62fa137e5c888b2573208aab8e9a

data/Gemfile

@@ -0,0 +1,14 @@
+# encoding: utf-8
+
+source 'https://rubygems.org'
+
+group :development, :test do
+  gem 'rake'
+  gem 'minitest'
+  gem 'minitest-reporters'
+  gem 'webmock'
+  gem 'faker'
+  gem 'factory_girl'
+end
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,52 @@
+PATH
+  remote: .
+  specs:
+    boogex (0.0.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (4.2.3)
+      i18n (~> 0.7)
+      json (~> 1.7, >= 1.7.7)
+      minitest (~> 5.1)
+      thread_safe (~> 0.3, >= 0.3.4)
+      tzinfo (~> 1.1)
+    addressable (2.3.8)
+    ansi (1.5.0)
+    builder (3.2.2)
+    crack (0.4.2)
+      safe_yaml (~> 1.0.0)
+    factory_girl (4.5.0)
+      activesupport (>= 3.0.0)
+    faker (1.4.3)
+      i18n (~> 0.5)
+    i18n (0.7.0)
+    json (1.8.3)
+    minitest (5.7.0)
+    minitest-reporters (1.0.7)
+      ansi
+      builder
+      minitest (>= 5.0)
+      ruby-progressbar
+    rake (10.4.2)
+    ruby-progressbar (1.7.5)
+    safe_yaml (1.0.4)
+    thread_safe (0.3.5)
+    tzinfo (1.2.2)
+      thread_safe (~> 0.1)
+    webmock (1.21.0)
+      addressable (>= 2.3.6)
+      crack (>= 0.3.2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  boogex!
+  factory_girl
+  faker
+  minitest
+  minitest-reporters
+  rake
+  webmock

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2015 Lexer
+
+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 +1,13 @@
+# boogex.gem
+
+This is a Gem that allows conversion of Lucene.
+
+# Tests
+
+Run tests:
+    bundle exec rake test
+
+# IRB
+
+If you need to have a laugh and play around with gem:
+    irb -rubygems -I lib -r $PWD/lib/boogex.rb

data/Rakefile

@@ -0,0 +1,11 @@
+# encoding: utf-8
+require 'bundler'
+require 'rake'
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+  t.test_files = FileList['test/**/*_test.rb']
+  t.libs.push 'spec'
+end
+
+task default: [:test]

data/boogex.gemspec

@@ -0,0 +1,22 @@
+Gem::Specification.new do |s|
+  s.name        = 'boogex'
+  s.version     = '0.0.1'
+  s.date        = '2016-02-14'
+  s.homepage    = 'https://github.com/lexerdev/boogex.gem'
+  s.license     = 'MIT'
+  s.summary     = "Boolean Lucene to Regex convertor."
+  s.description = "Converts Lucene Boolean query language into ruby regex."
+  s.authors     = ["Sam Crouch"]
+  s.email       = 'samuel.crouch@lexer.com.au'
+  s.files = `git ls-files`.split($RS).reject do |file|
+    file =~ %r{^(?:
+    spec/.*
+    |Gemfile
+    |Rakefile
+    |\.gitignore
+    |\.rubocop.yml
+    )$}x
+  end
+  s.test_files    = `git ls-files`.split($RS)
+  s.require_paths = ['lib']
+end

data/lib/boogex.rb

@@ -0,0 +1,8 @@
+# encoding: utf-8
+require 'boogex/error'
+require 'boogex/version'
+require 'boogex/helper'
+require 'boogex/convertor'
+
+module Boogex
+end

data/lib/boogex/convertor.rb

@@ -0,0 +1,176 @@
+# encoding: utf-8
+
+module Boogex
+  def self.convert(text)
+    puts "Converting \"#{text}\" into regex"
+    array = array_struct(text)
+    array = ors_to_pipes(array)
+    array = regex_formatting(array)
+    regex_array_to_string(array)
+  end
+
+  private
+
+  # This function converts a string into an array where brackets in the string are converted to an array structure
+  # to allow further manipulation
+  # "a OR (b) OR c" => ["a OR ", ["b"], " OR c"]
+  # "a OR (b AND (c OR d)) OR e" => ["a OR ", ["b AND ", ["c OR d"]], " OR e"]
+  def self.array_struct(text)
+    inside_brackets = "[^\(\)]*"
+
+    #This regex looks for anything in brackets OR anything with brackets in brackets OR anything with brackets in brackets in brackets
+    regex = /(\(#{inside_brackets}\))|(\(#{inside_brackets}\(#{inside_brackets}\)#{inside_brackets}\))|(\(#{inside_brackets}\(#{inside_brackets}\(#{inside_brackets}\)#{inside_brackets}\)#{inside_brackets}\))/
+    
+    cuts = text.scan(regex).to_a.flatten.reject(&:nil?)
+
+    # If nothing found then return orignal text
+    return text if cuts.empty?
+    
+    # The text is now cut into an array where the bracketing of the string determines the elements
+    # ie. "a OR (b) OR c" => ["a OR ", ["b"], " OR c"]
+    text_array = cuts.inject([text]) do |a, cut|
+      a.each_with_object([]) do |str, result|
+        if !str.include?(cut)
+          result << str
+        else
+          splits = str.split(cut)
+    
+          result << splits.first
+          cut_without_brackets = cut[1..-2]
+          result << [cut_without_brackets]
+          result << splits.last
+        end
+      end
+    end.uniq
+
+    # This recursively converts any brackets in the text back into the array_struct function
+    # where the upper limit of recursion is 3 levels of bracketing. This is limitied by the regex
+    # on line 9 but can easily be extended.
+    # If the element of the array is a string then no recursion to apply.
+    # If the element of the array is an array then iterate THAT through the array_struct function
+    text_array.reject(&:empty?).each_with_object([]) do |str, result|
+    	if str.is_a?(String)
+    	  result << str
+    	  next
+    	end
+
+    	result << str.collect do |str|
+        array_struct(str)
+      end
+    end
+  end
+
+  # This function converts the Lucene Boolean `OR` into regex `|` and removes any quotation marks
+  def self.ors_to_pipes(obj)
+    return obj.gsub(' OR ', '|').gsub('"', '').gsub("'", '') if obj.is_a?(String)
+
+    # This recursively applies this function to ensure all levels of the array are converted
+    obj.collect do |text|
+      ors_to_pipes(text)
+    end
+  end
+
+  # This function begins to tranform the elements of the array structure to regex formatting
+  # including:
+  # - (a) Any elements that are not bookended by | are then wrapped in (?:) as this modularises 
+  # the regex of the elements of the structures
+  #
+  # - (b) Converting any Lucene Boolean `AND` into an AND array structure where the first element is "AND" and the 
+  # remaining elements of that array are the regexes that make up the `AND`
+  # ie. ["pete AND james"] => ["AND", "pete", "james"]
+  # ie. ["jenny AND", ["billy OR jimmy"]] => ["AND", "jenny", ["billy OR jimmy"]]
+  def self.regex_formatting(obj)
+    # (a)
+    # if string then wrap it in brackets if needed and then return
+    if obj.is_a?(String)
+      if contain_AND?(obj)
+        result = ['AND']
+        result = result + obj.split(' AND ').reject(&:empty?).collect do |str|
+          regex_formatting(str)
+        end
+        return result
+      end
+      needs_brackets = not_in_or?(obj)
+      obj = wrap_in_brackets(obj) if needs_brackets
+      return obj
+    end
+    
+    # if an all string array, then check if any of the elements of the array need bracket wrapped and return
+    if all_strings?(obj)
+      needs_brackets = obj.any? do |text|
+        not_in_or?(text)
+      end
+      obj = obj.join('')
+      obj = wrap_in_brackets(obj) if needs_brackets
+      return obj
+    end
+
+    # (b)
+    result = []
+
+    # If this level of bracket contains a string with `AND` in it, then consider this element an `AND` array
+    result << 'AND' if obj.any? do |elem|
+      contain_AND?(elem)
+    end
+
+    obj.each_with_object(result) do |text, result|
+      if contain_AND?(text)
+        text.split(' AND ').reject(&:empty?).each do |str|
+          result << regex_formatting(str)
+        end
+      else
+        result << regex_formatting(text)
+      end
+    end
+  end
+
+  # This function converts the entire array with regex formatting into a regex string
+  # The AND array is an adhoc format generated by Lexer as regex doesn't have a Lucene
+  # Boolean `AND` equivalent. This adhoc regex AND is generated in the Lexer stack in the task generator
+  def self.regex_array_to_string(obj)
+    return obj if obj.is_a?(String)
+
+    is_AND_array = is_AND_array?(obj)
+
+    # This removes the "AND" from the AND array
+    obj.shift if is_AND_array
+
+    result = obj.collect do |text|
+      regex_array_to_string(text)
+    end
+    return construct_AND_array(result) if is_AND_array
+    
+    result.join('')
+  end
+
+  def self.is_AND_array?(array)
+    array[0] == 'AND'
+  end
+
+  def self.construct_AND_array(array)
+    '#{andify["' + array.join('", "') + '"]}' 
+  end
+
+  def self.contain_AND?(obj)
+    obj.is_a?(String) && obj.include?(' AND ')
+  end
+
+  def self.all_strings?(array)
+    array.all? do |elem|
+      elem.is_a?(String)
+    end
+  end
+
+  # Is this text not in awe? lols. Rather, is it not wrapped in regex `or` .
+  # ie. |pieceofcontent| = false
+  # ie. |pieceofcontent = true
+  # ie. pieceofcontent| = true
+  # ie. pieceofcontent = true
+  def self.not_in_or?(text)
+    text[0] != '|' && text[-1] != '|'
+  end
+
+  def self.wrap_in_brackets(text)
+    '(?:' + text + ')'
+  end
+end

data/lib/boogex/error.rb

@@ -0,0 +1,4 @@
+# encoding: utf-8
+module Boogex
+  Error = Class.new(StandardError)
+end

data/lib/boogex/helper.rb

@@ -0,0 +1,5 @@
+# encoding: utf-8
+$LOAD_PATH.unshift("#{File.dirname(__FILE__)}")
+
+module Boogex::Helper
+end

data/lib/boogex/version.rb

@@ -0,0 +1,4 @@
+# encoding: utf-8
+module Boogex
+  VERSION = '0.0.1'
+end

data/test/convertor_test.rb

@@ -0,0 +1,36 @@
+require "#{File.dirname(__FILE__)}/test_helper"
+
+describe Boogex do
+  it 'turns OR into |' do
+    string = 'This OR That'
+    expecting = '(?:This|That)'
+    result = Boogex.convert(string)
+    assert_equal expecting, result
+  end
+
+  it 'turns AND into andify array string' do
+    string = 'This AND That'
+    expecting = '#{andify["(?:This)", "(?:That)"]}'
+    result = Boogex.convert(string)
+    assert_equal expecting, result
+  end
+
+  it 'understands bracketing' do
+    string = '(This OR That) AND My self'
+    expecting = '#{andify["(?:This|That)", "(?:My self)"]}'
+    result = Boogex.convert(string)
+    assert_equal expecting, result
+
+    string = 'This AND (That OR (My self)'
+    expecting = '#{andify["(?:This|That)", "(?:My self)"]}'
+    result = Boogex.convert(string)
+    assert_equal expecting, result
+  end
+
+  it 'correctly convert this Lucene boolean query string' do
+    string = '(((asd OR dd) AND that) AND this) OR What?'
+    expecting = '#{andify["#{andify["(?:asd|dd)", "(?:that)"]}", "(?:this)"]}|What?'
+    result = Boogex.convert(string)
+    assert_equal expecting, result
+  end
+end

data/test/reports/TEST-Boogex.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<testsuite name="Boogex" skipped="0" failures="0" errors="0" tests="4" assertions="4" time="0.0007573158945888281">
+  <testcase name="test_0001_correctly convert this Lucene boolean query string" classname="Boogex" assertions="1" time="0.0001257510157302022">
+  </testcase>
+  <testcase name="test_0002_correctly convert this Lucene boolean query string" classname="Boogex" assertions="1" time="0.00011062994599342346">
+  </testcase>
+  <testcase name="test_0003_correctly convert this Lucene boolean query string" classname="Boogex" assertions="1" time="0.00020186102483421564">
+  </testcase>
+  <testcase name="test_0004_correctly convert this Lucene boolean query string" classname="Boogex" assertions="1" time="0.0003190739080309868">
+  </testcase>
+</testsuite>

data/test/test_helper.rb

@@ -0,0 +1,8 @@
+# encoding: UTF-8
+
+require 'minitest/autorun'
+require 'minitest/reporters'
+require 'minitest/spec'
+
+MiniTest::Reporters.use! [Minitest::Reporters::SpecReporter.new, MiniTest::Reporters::JUnitReporter.new]
+require File.join(File.dirname(__FILE__), '..', 'lib', 'boogex')

metadata

@@ -0,0 +1,71 @@
+--- !ruby/object:Gem::Specification
+name: boogex
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Sam Crouch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-02-14 00:00:00.000000000 Z
+dependencies: []
+description: Converts Lucene Boolean query language into ruby regex.
+email: samuel.crouch@lexer.com.au
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- boogex.gemspec
+- lib/boogex.rb
+- lib/boogex/convertor.rb
+- lib/boogex/error.rb
+- lib/boogex/helper.rb
+- lib/boogex/version.rb
+- test/convertor_test.rb
+- test/reports/TEST-Boogex.xml
+- test/test_helper.rb
+homepage: https://github.com/lexerdev/boogex.gem
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Boolean Lucene to Regex convertor.
+test_files:
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- boogex.gemspec
+- lib/boogex.rb
+- lib/boogex/convertor.rb
+- lib/boogex/error.rb
+- lib/boogex/helper.rb
+- lib/boogex/version.rb
+- test/convertor_test.rb
+- test/reports/TEST-Boogex.xml
+- test/test_helper.rb