id_encoder 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

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

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012
+
+MIT License
+
+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 +1,58 @@
+# IdEncoder
+
+Ruby implementation for generating Tiny URL- and bit.ly-like URLs.
+
+A bit-shuffling approach is used to avoid generating consecutive, predictable 
+URLs. However, the algorithm is deterministic and will guarantee that no 
+collisions will occur.
+
+The URL alphabet is fully customizable and may contain any number of 
+characters.  By default, digits and lower-case letters are used, with 
+some removed to avoid confusion between characters like o, O and 0.  The 
+default alphabet is shuffled and has a prime number of characters to further 
+improve the results of the algorithm.
+
+The block size specifies how many bits will be shuffled.  The lower BLOCK_SIZE 
+bits are reversed.  Any bits higher than BLOCK_SIZE will remain as is.
+BLOCK_SIZE of 0 will leave all bits unaffected and the algorithm will simply 
+be converting your integer to a different base.
+
+The intended use is that incrementing, consecutive integers will be used as 
+keys to generate the short URLs.  For example, when creating a new URL, the 
+unique integer ID assigned by a database could be used to generate the URL 
+by using this module.  Or a simple counter may be used.  As long as the same 
+integer is not used twice, the same short URL will not be generated twice.
+
+The module supports both encoding and decoding of URLs. The min_length 
+parameter allows you to pad the URL if you want it to be a specific length.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'id_encoder'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install id_encoder
+
+## Usage
+
+	>> require 'id_encoder'
+	=> true
+	>> IdEncoder::UrlEncoder.encode_url(10)
+	=> "csqsc"
+	>> IdEncoder::UrlEncoder.decode_url('csqsc')
+	=> 10
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/id_encoder.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/id_encoder/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Ruslan Khakimov"]
+  gem.email         = ["ruslan@khakimov.com"]
+  gem.description   = %q{A bit-shuffling approach is used to avoid generating 
+    consecutive, predictable URLs. However, the algorithm is deterministic and 
+    will guarantee that no collisions will occur.
+    
+    The gem supports both encoding and decoding of URLs. The min_length parameter 
+    allows you to pad the URL if you want it to be a specific length.
+  }
+  gem.summary       = %q{Ruby implementation for generating Tiny URL- and bit.ly-like URLs.}
+  gem.homepage      = ""
+
+  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          = "id_encoder"
+  gem.require_paths = ["lib"]
+  gem.version       = IdEncoder::VERSION
+end

data/lib/id_encoder.rb

@@ -0,0 +1,125 @@
+# Short URL Generator
+# ===================
+
+# Ruby implementation for generating Tiny URL- and bit.ly-like URLs.
+
+# A bit-shuffling approach is used to avoid generating consecutive, predictable 
+# URLs. However, the algorithm is deterministic and will guarantee that no 
+# collisions will occur.
+
+# The URL alphabet is fully customizable and may contain any number of 
+# characters.  By default, digits and lower-case letters are used, with 
+# some removed to avoid confusion between characters like o, O and 0.  The 
+# default alphabet is shuffled and has a prime number of characters to further 
+# improve the results of the algorithm.
+
+# The block size specifies how many bits will be shuffled.  The lower BLOCK_SIZE 
+# bits are reversed.  Any bits higher than BLOCK_SIZE will remain as is.
+# BLOCK_SIZE of 0 will leave all bits unaffected and the algorithm will simply 
+# be converting your integer to a different base.
+
+# The intended use is that incrementing, consecutive integers will be used as 
+# keys to generate the short URLs.  For example, when creating a new URL, the 
+# unique integer ID assigned by a database could be used to generate the URL 
+# by using this module.  Or a simple counter may be used.  As long as the same 
+# integer is not used twice, the same short URL will not be generated twice.
+
+# The module supports both encoding and decoding of URLs. The min_length 
+# parameter allows you to pad the URL if you want it to be a specific length.
+
+# Sample Usage:
+#
+# gem install id_encoder
+#
+# >> require 'id_encoder'
+# => true
+# >> IdEncoder::UrlEncoder.encode_url(10)
+# => "csqsc"
+# >> IdEncoder::UrlEncoder.decode_url('csqsc')
+# => 10
+# 
+# Use the functions in the top-level of the module to use the default encoder. 
+# Otherwise, you may create your own UrlEncoder object and use its encode_url 
+# and decode_url methods.
+
+# Author of Python version: Michael Fogleman
+# Link: http://code.activestate.com/recipes/576918/
+# License: MIT
+
+# Author of Ruby version: Ruslan Khakimov
+# Link: http://github.com/khakimov/id_encoder
+# License: MIT
+
+require "id_encoder/version"
+
+DEFAULT_ALPHABET = 'mn6j2c4rv8bpygw95z7hsdaetxuk3fq'
+DEFAULT_BLOCK_SIZE = 24
+MIN_LENGTH = 4
+
+module IdEncoder
+	class UrlEncoder
+
+		@alphabet = DEFAULT_ALPHABET
+		@block_size = DEFAULT_BLOCK_SIZE
+		@mask = (1 << @block_size) - 1 # left-shift
+		@mapping = (0..(@block_size-1)).to_a.reverse!
+
+		def self.encode_url(n, min_length=MIN_LENGTH)
+			enbase(encode(n), min_length)
+		end
+
+		def self.decode_url(n)
+			decode(debase(n))
+		end
+
+		def self.encode(n)
+			(n & ~@mask) | _encode(n & @mask)
+		end
+
+		def self.decode(n)
+			(n & ~@mask) | _decode(n & @mask)
+		end
+
+		def self._encode(n)
+			result = 0
+			@mapping.each_with_index { |item, index|
+				if n & (1 << index) != 0
+					result = result | (1 << item)
+				end
+			}
+			result
+		end
+
+		def self._decode(n)
+			result = 0
+			@mapping.each_with_index { |item, index|
+				if n & (1 << item) != 0
+					result = result | (1 << index)
+				end
+			}
+		 	result
+		end
+
+		def self.enbase(x, min_length=MIN_LENGTH)
+			_enbase(x)
+		end
+
+		def self._enbase(x)
+			n = @alphabet.size
+			if x < n
+				return @alphabet[x]
+			end
+			_enbase(x/n) + @alphabet[x % n]
+		end
+
+		def self.debase(x)
+			n = @alphabet.size
+			result = 0
+			a = x.split('').reverse
+			a.each_with_index {|item, i|
+				result += @alphabet.index(item) * (n ** i)
+			}
+			result
+		end
+	end
+end

data/lib/id_encoder/version.rb

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

metadata

@@ -0,0 +1,57 @@
+--- !ruby/object:Gem::Specification
+name: id_encoder
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Ruslan Khakimov
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-05-24 00:00:00.000000000 Z
+dependencies: []
+description: ! "A bit-shuffling approach is used to avoid generating \n    consecutive,
+  predictable URLs. However, the algorithm is deterministic and \n    will guarantee
+  that no collisions will occur.\n    \n    The gem supports both encoding and decoding
+  of URLs. The min_length parameter \n    allows you to pad the URL if you want it
+  to be a specific length.\n  "
+email:
+- ruslan@khakimov.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- id_encoder.gemspec
+- lib/id_encoder.rb
+- lib/id_encoder/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
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Ruby implementation for generating Tiny URL- and bit.ly-like URLs.
+test_files: []