houdinirx 0.0.1

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 houdini.gemspec
+gemspec

data/README

@@ -0,0 +1,39 @@
+A ruby DSL for building long complex regular expressions used frequently across large data extraction projects.
+
+This is the simplest possible example, but given the following text:
+t = "$10.99 (555) 444-3322 Boston, MA"
+
+Instead of writing a regular expression like the following:
+data = t.match(/\$(\d+[,\d]*\.\d+)\s*(\(\d{3}\)\s\d{3}-\d{4})\s*(\w+),\s(\w+)/)
+
+and then retrieving the data with match result indices:
+data[1] => "10.99"
+data[2] => "(555) 444-3322"
+data[3] => "Boston"
+data[4] => "MA"
+
+We can use Houdini to build the regular expression in easy to read and reusable pieces
+
+Define a regular expression for use across your project:
+Houdini.define(:word, /\w+/)
+
+Call hmatch or hscan on a string and build your expression pieces with the r() method by defining the expression inline or using a pre-defined expression.  Then build your match results with the m( ) method.
+
+data = t.hmatch do
+  r("amount", /\d+[,\d]*\.\d+/)
+  r("phone_number", /\(\d{3}\)\s+\d{3}-\d{4}/)
+  r("city", :word)
+  r("state", :word)
+  m("\\$(amount) (phone_number) (city), (state)")
+end
+
+Now you can access the data as methods on the resulting object:
+
+data.amount        => "10.99"
+data.phone_number  => "(555) 444-3322"
+data.city          => "Boston"
+data.state         => "MA"
+
+or access the original MatchData object
+
+data.match =>  #<MatchData "$10.99 (555) 444-3322 Boston, MA" 1:"10.99" 2:"(555) 444-3322" 3:"Boston" 4:"MA">

data/Rakefile

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

data/houdinirx.gemspec

@@ -0,0 +1,20 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "houdinirx/version"
+
+Gem::Specification.new do |s|
+  s.name        = "houdinirx"
+  s.version     = Houdini::VERSION
+  s.authors     = ["Eric Campbell", "Duncan Mak"]
+  s.email       = ["ericcampbell59@gmail.com", "duncanmak@gmail.com"]
+  s.homepage    = ""
+  s.summary     = %q{A Ruby DSL for building regular expressions}
+  s.description = %q{A ruby DSL for building long complex regular expressions used frequently across large data extraction projects}
+
+  s.rubyforge_project = "houdinirx"
+
+  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"]
+end

data/lib/houdinirx/match_result.rb

@@ -0,0 +1,27 @@
+module Houdini
+  class MatchResult
+    
+    attr_accessor :match, :captures
+    
+    def initialize(match, captures)
+      @match = match
+
+      raise RuntimeError, "Regex failed" if @match.nil?
+      @captures = captures.collect {|c| c.to_sym }
+    end
+    
+    def method_missing(method, *args, &block)
+      if @captures.include?(method)
+        index = @captures.index(method)
+        if @match.class == MatchData
+          @match.captures[index]
+        else
+          @match[index]
+        end
+      else
+        raise RuntimeError, "#{method} not captured"
+      end
+    end
+    
+  end
+end

data/lib/houdinirx/regex_helper.rb

@@ -0,0 +1,54 @@
+module Houdini
+  class RegexHelper
+    attr_accessor :expressions, :match_string, :captures, :regexp
+  
+    def initialize
+      @expressions = []
+      @captures = []
+      @regexp = nil
+    end
+  
+    def r(*args)
+      if args.size == 2
+        @expressions << [args[0], args[1]]
+      else
+        expression = args.pop
+        args.each do |name|
+          @expressions << [name, expression]
+        end
+      end
+    end
+  
+    def m(match_str)
+      @match_string = match_str
+    end
+  
+    def match(text, options=Regexp::IGNORECASE)
+      @regexp = match_string.gsub(/\s/, "\\s*")
+      replace_expressions!(@regexp)
+      r = Regexp.new(@regexp, options)
+      puts r.inspect
+      Houdini::MatchResult.new(text.match(r), @captures)
+    end
+    
+    def scan(text, options=Regexp::IGNORECASE)
+      @regexp = match_string.gsub(/\s/, "\\s*")
+      replace_expressions!(@regexp)
+      r = Regexp.new(@regexp, options)
+      scans = text.scan(r)
+      scans.collect {|scan| Houdini::MatchResult.new(scan, @captures) }
+    end
+    
+    protected
+    def replace_expressions!(regex)
+      @expressions.each do |name, r|
+        if regex =~ /\(#{name}\)/
+          @captures << name
+        end
+        r = Houdini[r].source if r.class == Symbol
+        r = r.source if r.class == Regexp
+        regex.gsub!(name, r)
+      end
+    end
+  end
+end

data/lib/houdinirx/string.rb

@@ -0,0 +1,13 @@
+class String
+  def hmatch(options=nil, &block)
+    regex_helper = Houdini::RegexHelper.new()
+    regex_helper.instance_eval(&block)
+    regex_helper.match(self)
+  end
+  
+  def hscan(options=nil, &block)
+    regex_helper = Houdini::RegexHelper.new()
+    regex_helper.instance_eval(&block)
+    regex_helper.scan(self)
+  end
+end

data/lib/houdinirx/version.rb

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

data/lib/houdinirx.rb

@@ -0,0 +1,25 @@
+$:.unshift(File.dirname(__FILE__)) unless
+$:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+
+require "houdinirx/version"
+require "houdinirx/string"
+require "houdinirx/regex_helper"
+require "houdinirx/match_result"
+
+module Houdini
+  
+  class << self
+    def [](name)
+      definitions[name]
+    end
+    
+    def define(name, regex)
+      definitions[name] = regex
+    end
+    
+    def definitions
+      @@def ||= {}
+    end
+  end
+  
+end

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification 
+name: houdinirx
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Eric Campbell
+- Duncan Mak
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-08-01 00:00:00 Z
+dependencies: []
+
+description: A ruby DSL for building long complex regular expressions used frequently across large data extraction projects
+email: 
+- ericcampbell59@gmail.com
+- duncanmak@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- Gemfile
+- README
+- Rakefile
+- houdinirx.gemspec
+- lib/houdinirx.rb
+- lib/houdinirx/match_result.rb
+- lib/houdinirx/regex_helper.rb
+- lib/houdinirx/string.rb
+- lib/houdinirx/version.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 
+      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: houdinirx
+rubygems_version: 1.8.5
+signing_key: 
+specification_version: 3
+summary: A Ruby DSL for building regular expressions
+test_files: []
+