DZone Snippets: web code

One-line web server in Ruby

ntk () — Wed, 23 Apr 2008 13:22:36 GMT





# From: http://www.ntecs.de/blog/articles/2008/02/09/the-worlds-smallest-webserver

# Author: Michael Neumann

# ... point your browser to http://localhost:3125/etc/motd



ruby -rsocket -e 's=TCPServer.new(5**5);loop{_=s.accept;_<<"HTTP/1.0 200 OK\r\n\r\n#{File.read(_.gets.split[1])rescue nil}";_.close}'

Run TCPServer as a simple Web server

jrobertson (James Robertson) — Thu, 10 Apr 2008 14:05:56 GMT

A TCPServer accepts incoming TCP connections. Here is a Web server that listens on a given port and returns the time.



require 'socket'

port = (ARGV[0] || 80).to_i

server = TCPServer.new('localhost', port)

while (session = server.accept)

  puts "Request: #{session.gets}"

  session.print "HTTP/1.1 200/OK\r\nContent-type: text/html\r\n\r\n"

  session.print "#{Time.now}\r\n"

  session.close

end

This code was copied from Programming Ruby: The Pragmatic Programmer's Guide [rubycentral.com] while looking for information on Ruby CGI global variables.

Upload a file using Ruby

jrobertson (James Robertson) — Sat, 23 Feb 2008 13:26:00 GMT

The following code was used to upload an image file to the web server. Source code origin: Ruby Language Stuff | mod_ruby File upload scripts [zytrax.com]

file: file_upload.cgi



#!/usr/bin/ruby



# ruby script fragment

require 'cgi'

require 'stringio'



cgi = CGI.new()  # New CGI object

puts "Content-Type: text/plain"

puts

print ''



# get uri of tx'd file (in tmp normally)

tmpfile = cgi.params['myfile'].first.path



# OR (functionally the same)

tmpfile = cgi.params['myfile'][0].path



# create a Tempfile reference

fromfile = cgi.params['myfile'].first



#displays the original file name as supplied in the form

puts fromfile.original_filename



# displays the content (mime) type e.g. text/html

puts fromfile.content_type



# create output file reference as original filename in our chosen directory

tofile = '/var/www/yourdomain.com/htdocs/r/'+fromfile.original_filename



# copy the file

# note the untaint prevents a security error

# cgi sets up an StringIO object if file < 10240

# or a Tempfile object following works for both

File.open(tofile.untaint, 'w') { |file| file << fromfile.read}

# when the page finishes the Tempfile/StringIO!) thing is deleted automatically



print ''

file: file_upload.html



  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">



  

    File upload

    

  

  

        action='/p/file_upload.cgi' method='post'>

Getting Started With WWW::Mechanize

jrobertson (James Robertson) — Tue, 12 Feb 2008 17:53:54 GMT

This Ruby code uses WWW:mechanize to act like a web browser.



 require 'rubygems'

 require 'mechanize'



 agent = WWW::Mechanize.new

 page = agent.get('http://google.com/')

Refer to the documentation at http://mechanize.rubyforge.org/mechanize/. Then gem install mechanize, and try running the code in an irb session.

output (extract):



=> # {url #}

 {meta}

 {title "Google"}

 {iframes}

 {frames}

 {links

  #   "Images"

   "http://images.google.com/imghp?hl=en&tab=wi">

  #   "Maps"

   "http://maps.google.com/maps?hl=en&tab=wl">

  #   "News"

   "http://news.google.com/nwshp?hl=en&tab=wn">

  #   "Shopping"

   "http://www.google.com/prdhp?hl=en&tab=wf">

  #   "Gmail"

   "http://mail.google.com/mail/?hl=en&tab=wm">

bScan - Simple Web Aplications Scanner

Black_H (Black_H) — Sun, 03 Feb 2008 11:51:05 GMT

// Web application scanner (ex: phpBB, myCMS, myBlog, mySite etc..) - Only in PHP !
// Find XSS, sql injection, remote file inclusion



#####################################################################################

#	Black_H  / Nooz -- 30:01:07 

#	Bl4ck.H<>gmail<>com

#



class BScan



#####################################################################################

#	Regex

#



@@space    = '([[:space:]]*)'



@@userdat  = '('

@@userdat += '(\$_SERVER\[([\'\"]*)HTTP_)|'

@@userdat += '(\$_GET)|'

@@userdat += '(\$_POST)|'

@@userdat += '(\$_COOKIE)|'

@@userdat += '(\$_REQUEST)|'

@@userdat += '(\$_FILES)|'

@@userdat += '(\$_ENV)|'

@@userdat += '(\$_HTTP_COOKIE_VARS)|'

@@userdat += '(\$_HTTP_ENV_VARS)|'

@@userdat += '(\$_HTTP_GET_VARS)|'

@@userdat += '(\$_HTTP_POST_FILES)|'

@@userdat += '(\$_HTTP_POST_VARS)|'

@@userdat += '(\$_HTTP_SERVER_VARS\[([\'\"]*)HTTP_)'

@@userdat += ')'



@@regex = Hash.new

@@regex = 

	{'TYPE' => 'vars overwrite','LEVEL' => '2','REGEX' => /extract#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'vars overwrite','LEVEL' => '2','REGEX' => /import_request_variables#{@@space}\((.*)\)/i},

	{'TYPE' => 'fopen vuln','LEVEL' => '3','REGEX' => /fopen#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'copy vuln','LEVEL' => '3','REGEX' => /copy#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'fwrite vuln','LEVEL' => '3','REGEX' => /fwrite#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'sql injection','LEVEL' => '2','REGEX' => /(mysql_query|mssql_query|mysqli_query)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'crlf injection','LEVEL' => '1','REGEX' => /mail#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'cross site scripting','LEVEL' => '1','REGEX' => /\<\?\=#{@@space}(.*)#{@@userdat}/i},

	{'TYPE' => 'cross site scripting','LEVEL' => '1','REGEX' => /(print|echo|print_r|var_dump)#{@@space}(|\(|\")(.*)#{@@userdat}/i},

	{'TYPE' => 'php code execution','LEVEL' => '3','REGEX' => /eval#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'php code execution','LEVEL' => '3','REGEX' => /file_put_contents#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'variable attribution', 'LEVEL' => '2','REGEX' => /(.*)\$#{@@userdat}(.*)/i},

	{'TYPE' => 'chmod affectation','LEVEL' => '1','REGEX' => /chmod#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'file disclosure','LEVEL' => '2','REGEX' => /(readfile|file_get_contents|file)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'file disclosure','LEVEL' => '2','REGEX' => /(show_source|highlight_file)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'bzopen vuln','LEVEL' => '2','REGEX' => /bzopen#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'file deletion','LEVEL' => '2','REGEX' => /(rmdir|unlink|delete)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'command execution','LEVEL' => '3','REGEX' => /(exec|system|passthru|shell_exec|proc_open|pcntl_exec)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'buffer overflow','LEVEL' => '3','REGEX' => /(confirm_phpdoc_compiled|mssql_pconnect|mssql_connect|crack_opendict|snmpget|ibase_connect)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'ip falsification','LEVEL' => '1','REGEX' => /(.*)(HTTP_CLIENT_IP|HTTP_X_FORWARDED_FOR|HTTP_PC_REMOTE_ADDR)(.*)/i},

	{'TYPE' => 'putenv vuln','LEVEL' => '2','REGEX' => /putenv#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'full path disclosure','LEVEL' => '1','REGEX' => /(htmlentities|htmlspecialchars)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'magic_quotes_gpc bypass','LEVEL' => '1','REGEX' => /(stripslashes|urldecode)#{@@space}\((.*)#{@@userdat}(.*)\)/i},

	{'TYPE' => 'file inclusion','LEVEL' => '3','REGEX' => /(include|include_once|require|require_once)#{@@space}(|\(|\")(.*)#{@@userdat}/i}



#####################################################################################

#	Main

#



  def initialize()



	################

	#	Usage



if (ARGV.length < 4)

puts  '

 ---------------------------------------------------------------------

|             Credits: Black_H                     |

|                 URL: Lemon-Inside.sup.fr                            |

|                Note: Premier code Ruby                              |

 ---------------------------------------------------------------------



 ---------------------------------------------------------------------

|   Usage:  scan.rb -d  -i                        |

|   Ex:  scan.rb -d ./ -i output.html                                 |

 ---------------------------------------------------------------------		

 '

 end

 

	################

	#	Options & Vars

	

	@@scan_alldir =  self.options('d')

	@@out_file =  self.options('i')

	

	@@ban = [".", "..", "scan.rb", @@out_file.to_s]



	@@scan_buffer = Array.new

	

	################

	#	Options Error ?

	

	if (@@scan_alldir != false and @@scan_alldir.empty? == false)

	self.dscan(@@scan_alldir)

	self.output(@@scan_buffer)

	@@scan_buffer = ''

	end





	



  end



#####################################################################################

#	Dir Scan 

#

  

  def dscan(dir)

      

	d = Dir.open(dir.to_s)

	d = d.sort - @@ban

	

      d.each { |fichier|



      case File.ftype(dir+fichier)

        when "directory"

          self.dscan(dir + fichier + "/")

        when "file"

		  puts  'Scan => ' + dir + fichier 

          self.fscan(dir + fichier)

      end



	  }

  end



#####################################################################################

#	File Scan 

#

  

  def fscan(file)



	fichier = File.readlines(file)

	i = 1



	fichier.each { |line|

						

		@@regex.each  { |info|

			

			test = (line  =~ info['REGEX']) 

		

				if (test) 

			

				@@scan_buffer += ['FILE' => file, 'LINE' => i.to_s, 'MATCH' => line, 'LEVEL' => info['LEVEL'], 'TYPE' => info['TYPE']]

				#	5 , 1 , 3 , 4 , 2

				next @@scan_buffer

				end

		}



	i += 1

  	} 

	

  end



#####################################################################################

#	Output buffer

#

  

  def output(buffer)

  

	@html_hmodel = ''

	@html_hmodel += 'BScan v1.0
'



	code = @html_hmodel

	

	buffer.each { |infos|

	

	keys = infos.keys

	code += "" + keys[1].to_s + ' : ' + infos["TYPE"] + '
'

	code += "" + keys[3].to_s + ' : ' + infos["LEVEL"] + '
'

	code += "" + keys[4].to_s + ' : ' + infos["FILE"] + '
'

	code += "" + keys[0].to_s + ' : ' + infos["LINE"] + '
'

	code += "" + keys[2].to_s + ' : ' + infos["MATCH"] + '
'

	



	}

		code += ""

		fhtml = File.open(@@out_file.to_s, "w")

		fhtml.write code

		code = ''



	

  end

#####################################################################################

#	Parse & Get Options

#

 

  def options(param)

  

	i = 0

		ARGV.each  { |valeur|

		

    		if (valeur == '-' + param.to_s)

				return ARGV[i+1]

			elseif (valeur != '-' + param.to_s)

				return false

			end

		i += 1

		}

		

	end

  

end



scan = BScan.new

Runt.rb

mcandre (Andrew Pennebaker) — Sat, 19 Jan 2008 06:46:42 GMT

// A tiny Ruby web server.



#!/usr/bin/env ruby



require "webrick"



s=WEBrick::HTTPServer.new(

        :BindAddress => "localhost",

        :Port => 8080,

        :DocumentRoot => File.dirname($0)+"/"+"www/"

)



trap("INT") { s.shutdown }



s.start

How to detect a browser iPhone ?

ki4ngel (Benoit Asselin) — Thu, 29 Nov 2007 10:34:42 GMT

The browser is :





Mozilla/5.0 (iPhone; U; CPU like Mac OS X; fr) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/3B48b Safari/419.3

Source: ab-d.fr
Internet with iPhone

I can't be bothered going downstairs to watch the daily show

tunah (Sam McCall) — Sun, 18 Nov 2007 06:44:14 GMT

scraper.rb - scrapes metadata from thedailyshow.com.
Just run it - creates videos/index.yml



#!/usr/bin/ruby



require 'rubygems'

require 'leecher'

require 'open-uri'

require 'hpricot'



class Scraper

	SEARCH_PAGE="http://www.thedailyshow.com/tds_files/includes/search/search_results.jhtml"

	def scrape_day(site, date, force=false)

		return if site.skip.include?(date) and not force

		url = sprintf("#{SEARCH_PAGE}?searchterm=%02d-%02d-%04d",date.month,date.day,date.year)

		puts "Fetching #{url}" if $DEBUG



		data = open(url) {|f| f.read }

		h = Hpricot(data)



		# can't use a real xpath - they all use an _id_ istead of a class

		results = (h/"div").find_all {|x| x['id'] == "videoListItem_1" }

		results.each {|result|

			url = result.at("a[1]")['href']

			vid = if url =~ /videoId=(\d+)/

				$1.to_i

			else

				raise "Failed to parse link #{url}"

			end



			title = ((result/"a")[1]/"text()").to_s

			date = Date.parse((result/"a[@onclick][1]/text()").to_s)



			descr = result/"div.video_description"

			description = (descr/"div[1]/text()").to_s

			tags = (descr/".tags/a/text()").map {|x| unescape(x.to_s) }

			

			vid = Video.new(site, vid, date, unescape(title), unescape(description), tags)

			puts vid

		}

	

		results.length

	end



	def unescape(t)

		t.gsub(/&([^;]{1,5});/) {|ent|

			case $1

				when /^#(\d+)$/

					[$1.to_i].pack('C')

				when /^#x([0-9a-zA-Z]+)$/

					[$1].pack('H2')

				when 'amp'

					'&'

				when 'gt'

					'>'

				when 'quot'

					'"'

				when 'apos'

					"'"

				when 'lt'

					'<'

				else

					$stderr.puts "Unknown entity #{$1.inspect}"

					'?'

			end

		}

	end

end



if __FILE__ == $0

	Site.load

	tds = Site.sites.find {|s| s.short_name == "tds" }

	tds ||= Site.new("The Daily Show","tds")



	day = Date.today

	start = Date.new(1999)



	counter=0



	s = Scraper.new

	while day >= start

		results = s.scrape_day(tds, day)

		puts "#{results} results for #{day}" if results # else skipped



		# Mark days as done once we've scraped them a month after air

		if (Date.today - day) > 30 and not results.nil?

			tds.skip!(day)

		end



		day -= 1

		unless results.nil? or results.zero?

			Site.save if (counter += 1)%10 == 0

		end

	end

	Site.save

end

leecher.rb - downloads/searches/plays videos
./leecher.rb [download/list/play] [searchterm ... ]
Search terms can be
date: 2007 or 2007-10 or 2007-10-01
tag: interview
id: 31723
already downloaded?: downloaded or !downloaded



#!/usr/bin/ruby



MEDIA_PLAYER = %w{mplayer -fs}



require 'rubygems'

require 'open-uri'

require 'rexml/document'

require 'rexml/xpath'

require 'fileutils'

require 'yaml'

require 'rio'

require 'set'



class Site

	class << self

		attr_reader :base

		attr_reader :alternates

		attr_reader :sites

		

		def init

			unless self.base or self.sites

				@base = "./videos"

				@alternates = []

				@sites = []

			end

		end



		def load(stream=nil)

			if stream

				stuff = YAML::load(stream)

				@base = stuff['base'] || "./videos"

				@sites = stuff['sites'] || []

				@alternates = stuff['alternates'] || []

			else

				init

				begin

					File.open(File.join(base,'index.yml')) {|f|

						load(f)

					}

				rescue Errno::ENOENT

					$stderr.puts "Warning, no database found, starting a new one"

				end

			end

		end

		

		def save(stream=nil)

			if stream

				YAML::dump({'base' => base, 'sites' => sites, 'alternates' => 'alternates'},stream)

			else

				File.open(File.join(base,'index.yml_'),'w') {|f|

					save(f)

				}

				FileUtils.mv(File.join(base,'index.yml_'),File.join(base,'index.yml'))

			end

		end



		def each(&block)

			sites.each(&block)

		end

	end



	def initialize(name, short_name=name)

		Site.init

		@videos = {}

		@name, @short_name = name, short_name

		@skip = Set.new

		Site.sites << self

	end



	attr_reader :videos

	attr_reader :name

	attr_reader :short_name

	attr_reader :skip



	def directory

		File.join(Site.base, short_name)

	end

	def directory_alternates

		Site.alternates.map {|d| File.join(d, short_name) }

	end



	def ensure_dir_exists!

		FileUtils.mkpath(directory)

	end



	def <<(vid)

		self.videos[vid.id] = vid

	end



	def skip!(date)

		self.skip << date

	end



	def [](id)

		self.videos[id]

	end



	def to_s

		name

	end



	def each 

		self.videos.each {|k,v| yield v }	

	end

end



class Video

	attr_reader :tags

	attr_reader :site

	attr_reader :id

	attr_reader :date

	attr_reader :title

	attr_reader :description



	def initialize(site, id, date=nil, title = nil, description=nil, tags=[]) 

 		@site = site

		@id = id

		@title = title

		@tags = tags

		@date = date

		@description = description



		site << self

	end



	def filename

		site.directory_alternates.map{|x| 

			File.join(x,"#{id}.flv")

		}.find {|f| 

			File.exists?(f) 

		} || File.join(site.directory, "#{id}.flv")

	end



	def downloaded?

		File.exists?(filename)

	end



	def download

		download! unless downloaded?

	end



	SHARED_DATA = "http://www.comedycentral.com/sitewide/video_player/shared/data"

	def download!

		site.ensure_dir_exists!

		url = download_url()

		begin

			rio(url) > rio(filename)

			File.size(filename)

		rescue Exception => x

			begin

				File.delete(filename)

			rescue Exception

			end

			raise x

		end

	end



	def to_s 

		sprintf("[%1s %7d - %s - %s - %20s]",(downloaded?? 'D' : ' '), id, date, site, title) 

	end



	def download_url

		manifest = open("#{SHARED_DATA}/flv_xml_gen.jhtml?ml_video=#{id}&hiLoPref=hi") {|f| f.read }

		doc = REXML::Document.new(manifest)

		REXML::XPath.first(doc, "/package/video/item/src/text()").to_s

	end

end



class Filter

	class << self

		def method_missing(sym,*args,&block)

			if sym.to_s =~ /^by/

				new.send(sym,*args,&block)

			else

				super

			end

		end

	end



	def initialize(parent=nil,&block)

		@parent = parent

		@test = block

	end

	

	def [](video)

		case video

			when Video

				video if (@test.nil? or @test[video]) and (@parent.nil? or @parent[video])

			when Site

				if block_given?

					video.each {|v| yield v if self[v] }

				else

					video.find_all {|v| self[v] }

				end

			else

				raise ArgumentError

		end

	end



	def each(&block)

		Site.each {|show| self.send(:[], show, &block) }

	end



	def filter(&block)

		Filter.new(self,&block)

	end



	def by_downloaded(dl=true)

		filter {|v| v.downloaded? == !!dl }

	end



	def by_date(y, m=nil, d=nil)

		if m.nil? and d.nil?

			filter {|v| v.date and v.date.year == y }

		elsif d.nil?

			filter {|v| v.date and v.date.year == y and v.date.month == m }

		else

			filter {|v| v.date and v.date.year == y and v.date.month == m and v.date.day == d }

		end

	end



	def by_id(vid)

		filter {|v| v.id == vid }

	end



	def by_tag(tag)

		filter {|v| v.tags.include? tag }

	end



	def by_text(text) 

		filter {|v| 

			v.title && v.title.downcase.include?(text.downcase) or 

			v.description && v.description.downcase.include?(text.downcase) or

			v.tags.include? text

		}

	end



	def by(arg)

		arg = arg.to_s

		case arg

			when 'downloaded'

				by_downloaded(true)

			when '!downloaded'

				by_downloaded(false)

			when /^(\d{4})$/

				by_date($1.to_i)

			when /^(\d{4})-(\d{1,2})$/

				by_date($1.to_i, $2.to_i)

			when /^(\d{4})-(\d{1,2})-(\d{1,2})$/

				by_date($1.to_i, $2.to_i, $3.to_i)

			when /^\d{5,}$/

				by_id(arg.to_i)

			else

				by_text(arg)

		end

	end

end



if __FILE__ == $0

	command = ARGV.shift or raise "Usage: leecher  [filters...]"

	action = case command.downcase

		when 'download'

			proc {|v| 

				puts "Fetching #{v}" unless v.downloaded?

				begin

					v.download

				rescue OpenURI::HTTPError => x

					$stderr.puts "Download failed, skipping: #{x}"

				rescue Errno::ENOENT => xm

					$stderr.puts "Download failed, skipping: #{x}"

				end

			}

		when 'list'

			proc {|v|

				puts "#{v} #{v.tags.join(', ')}"

			}

		when 'play'

			proc {|v|

				puts v

				system(*MEDIA_PLAYER, v.filename)

			}

		else

			raise "Unknown command #{command}"

	end



	filter = ARGV.inject(Filter.new) {|f, arg| f.by(arg)}



	Site.load

	filter.each(&action)

end

Punycoded URLs in Ruby

ntk () — Wed, 26 Sep 2007 21:00:18 GMT

This is just a proof-of-concept snippet for how to internationalize domain names using punycode4r (sudo gem install punycode4r).

For more information please see:
- Punycode
- Internationalized domain name





#!/usr/local/bin/ruby -Ku



# NOTE: The following is not the complete source code by Kazuhiro NISHIYAMA.

#       For the full source code with more features, comments & test cases please see: 

#       open -e `gem environment gemdir`/gems/punycode4r-0.2.0/lib/punycode.rb

#

# This is pure Ruby implementing Punycode (RFC 3492).

# (original ANSI C code (C89) implementing Punycode is in RFC 3492)

#

# copyright (c) 2005 Kazuhiro NISHIYAMA

# You can redistribute it and/or modify it under the same terms as Ruby.





require "unicode"     # sudo gem install unicode



module Punycode



  module Status

    class Error < StandardError; end

    class PunycodeSuccess; end

    # Input is invalid.

    class PunycodeBadInput < Error; end

    # Output would exceed the space provided.

    class PunycodeBigOutput< Error; end

    # Input needs wider integers to process.

    class PunycodeOverflow < Error; end

  end

  include Status





  BASE = 36; TMIN = 1; TMAX = 26; SKEW = 38; DAMP = 700

  INITIAL_BIAS = 72; INITIAL_N = 0x80; DELIMITER = 0x2D



  module_function



  def basic(cp)

    cp < 0x80

  end



  def delim(cp)

    cp == DELIMITER

  end



  def decode_digit(cp)

    cp - 48 < 10 ? cp - 22 :  cp - 65 < 26 ? cp - 65 :

      cp - 97 < 26 ? cp - 97 : BASE

  end



  def encode_digit(d, flag)

    return d + 22 + 75 * ((d < 26) ? 1 : 0) - ((flag ? 1 : 0) << 5)

  end



  def flagged(bcp)

    (0...26) === (bcp - 65)

  end



  def encode_basic(bcp, flag)

    # bcp -= (bcp - 97 < 26) << 5;

    if (0...26) === (bcp - 97)

      bcp -= 1 << 5

    end

    # return bcp + ((!flag && (bcp - 65 < 26)) << 5);

    if !flag and (0...26) === (bcp - 65)

      bcp += 1 << 5

    end

    bcp

  end



  MAXINT = 1 << 64





  def adapt(delta, numpoints, firsttime)

    delta = firsttime ? delta / DAMP : delta >> 1

    delta += delta / numpoints



    k = 0

    while delta > ((BASE - TMIN) * TMAX) / 2

      delta /= BASE - TMIN

      k += BASE

    end



    k + (BASE - TMIN + 1) * delta / (delta + SKEW)

  end



  def punycode_encode(input_length, input, case_flags, output_length, output)



    n = INITIAL_N

    delta = out = 0

    max_out = output_length[0]

    bias = INITIAL_BIAS



    input_length.times do |j|

      if basic(input[j])

        raise PunycodeBigOutput if max_out - out < 2

        output[out] =

          if case_flags

            encode_basic(input[j], case_flags[j])

          else

            input[j]

          end

        out+=1

      # elsif (input[j] < n)

      #   raise PunycodeBadInput

      # (not needed for Punycode with unsigned code points)

      end

    end



    h = b = out



    if b > 0

      output[out] = DELIMITER

      out+=1

    end



   while h < input_length



      m = MAXINT

      input_length.times do |j|

        # next if basic(input[j])

        # (not needed for Punycode)

        m = input[j] if (n...m) === input[j]

      end



      raise PunycodeOverflow if m - n > (MAXINT - delta) / (h + 1)

      delta += (m - n) * (h + 1)

      n = m



      input_length.times do |j|

        # Punycode does not need to check whether input[j] is basic:

        if input[j] < n # || basic(input[j])

          delta+=1

          raise PunycodeOverflow if delta == 0

        end



        if input[j] == n



          q = delta; k = BASE

          while true

            raise PunycodeBigOutput if out >= max_out

            t = if k <= bias # + TMIN # +TMIN not needed

                  TMIN

                elsif k >= bias + TMAX

                  TMAX

                else

                  k - bias

                end

            break if q < t

            output[out] = encode_digit(t + (q - t) % (BASE - t), false)

            out+=1

            q = (q - t) / (BASE - t)

            k += BASE

          end



          output[out] = encode_digit(q, case_flags && case_flags[j])

          out+=1

          bias = adapt(delta, h + 1, h == b)

          delta = 0

          h+=1

        end

      end



      delta+=1; n+=1

    end



    output_length[0] = out

    return PunycodeSuccess

  end



  def punycode_decode(input_length, input, output_length, output, case_flags)



    n = INITIAL_N



    out = i = 0

    max_out = output_length[0]

    bias = INITIAL_BIAS



    b = 0

    input_length.times do |j|

      b = j if delim(input[j])

    end

    raise PunycodeBigOutput if b > max_out



    b.times do |j|

      case_flags[out] = flagged(input[j]) if case_flags

      raise PunycodeBadInput unless basic(input[j])

      output[out] = input[j]

      out+=1

    end



    in_ = b > 0 ? b + 1 : 0

    while in_ < input_length



      oldi = i; w = 1; k = BASE

      while true

        raise PunycodeBadInput if in_ >= input_length

        digit = decode_digit(input[in_])

        in_+=1

        raise PunycodeBadInput if digit >= BASE

        raise PunycodeOverflow if digit > (MAXINT - i) / w

        i += digit * w

        t = if k <= bias # + TMIN # +TMIN not needed

              TMIN

            elsif k >= bias + TMAX

              TMAX

            else

              k - bias

            end

        break if digit < t

        raise PunycodeOverflow if w > MAXINT / (BASE - t)

        w *= BASE - t

        k += BASE

      end



      bias = adapt(i - oldi, out + 1, oldi == 0)



      raise PunycodeOverflow if i / (out + 1) > MAXINT - n

      n += i / (out + 1)

      i %= out + 1



      # not needed for Punycode:

      # raise PUNYCODE_INVALID_INPUT if decode_digit(n) <= base

      raise PunycodeBigOutput if out >= max_out



      if case_flags

        #memmove(case_flags + i + 1, case_flags + i, out - i)

        case_flags[i + 1, out - i] = case_flags[i, out - i]



        # Case of last character determines uppercase flag:

        case_flags[i] = flagged(input[in_ - 1])

      end



      #memmove(output + i + 1, output + i, (out - i) * sizeof *output)

      output[i + 1, out - i] = output[i, out - i]

      output[i] = n

      i+=1



      out+=1

    end



    output_length[0] = out

    return PunycodeSuccess

  end



  def encode(unicode_string, case_flags=nil, print_ascii_only=false)

    input = unicode_string.unpack('U*')

    output = [0] * (ACE_MAX_LENGTH+1)

    output_length = [ACE_MAX_LENGTH]



    punycode_encode(input.size, input, case_flags, output_length, output)



    outlen = output_length[0]

    outlen.times do |j|

      c = output[j]

      unless c >= 0 && c <= 127

        raise Error, "assertion error: invalid output char"

      end

      unless PRINT_ASCII[c]

        raise PunycodeBadInput

      end

      output[j] = PRINT_ASCII[c] if print_ascii_only

    end



    output[0..outlen].map{|x|x.chr}.join('').sub(/\0+\z/, '')

  end



  def decode(punycode, case_flags=[])

    input = []

    output = []



    if ACE_MAX_LENGTH*2 < punycode.size

      raise PunycodeBigOutput

    end

    punycode.each_byte do |c|

      unless c >= 0 && c <= 127

        raise PunycodeBadInput

      end

      input.push(c)

    end



    output_length = [UNICODE_MAX_LENGTH]

    Punycode.punycode_decode(input.length, input, output_length,

                             output, case_flags)

    output.pack('U*')

  end



  UNICODE_MAX_LENGTH = 256

  ACE_MAX_LENGTH = 256



  # The following string is used to convert printable

  # characters between ASCII and the native charset:



  PRINT_ASCII =

    "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" \

    "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" \

    " !\"\#$%&'()*+,-./" \

    "0123456789:;<=>?" \

    "@ABCDEFGHIJKLMNO" \

    "PQRSTUVWXYZ[\\]^_" \

    "`abcdefghijklmno" \

    "pqrstuvwxyz{|}~\n"

end







# cf. http://snippets.dzone.com/posts/show/4527



UTF8REGEX = /\A(?:                                                            

              [\x09\x0A\x0D\x20-\x7E]            # ASCII

            | [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte

            |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs

            | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte

            |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates

            |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3

            | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15

            |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16

            )*\z/mnx





UTF8_REGEX_MBYTE = /(?:                                 

                 [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte

               |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs

               | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte

               |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates

               |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3

               | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15

               |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16

               )/mnx







# cf. http://demo.icu-project.org/icu-bin/idnbrowser (samples)

# on Mac OS X you can check the Ruby conversions with the GUI app PunyCode, http://software.dibomedia.de/products/show/2



str = "http://www.ﺱﺲﺷ.com/"

str = "www.сделат картинки.com"

str = "http://www.сделаткартинки.com/"

str = "http://tūdaliņ.lv/"

str = "http://www.zürich.com/"

str = "http://www.hören.at/"

str = "http://www.žlutý kůň.com/"

str = "www.färgbolaget.nu"

str = "www.brændendekærlighed.com"

str = "www.mäkitorppa.com"

str = "www.färjestadsbk.net"

str = "あーるいん.com"

str = "www.예비교사.com"

str = "www.ハンドボールサムズ.com"

str = "www.日本平.jp"

str = "www.räksmörgås.se"

str = "www.różyczka.pl/"

str = "理容ナカムラ.com"

str = "http://Bücher.ch/"

str = "tūdaliņ.lv"





if str =~ UTF8REGEX && str =~ UTF8_REGEX_MBYTE



   s1 = str.gsub(/^(http:\/\/www\.|http:\/\/|).*?\.[^\.\/]+\/?$/n, '\1')

   s2 = str.gsub(/^(?:http:\/\/www\.|http:\/\/|)(www\.|).*?\.[^\.\/]+\/?$/n, '\1')

   s3 = str.gsub(/^(?:http:\/\/www\.|http:\/\/|www\.|)(.*?)\.[^\.\/]+\/?$/n, '\1')

   s4 = str.gsub(/^(?:http:\/\/www\.|http:\/\/|www\.|).*?(\.[^\.\/]+\/?)$/n, '\1')



   if s1.empty? then s1 = 'http://' end



   s3 = Punycode.encode(Unicode::normalize_KC(Unicode::downcase(s3)))



   punycoded_url = s1 << s2 << "xn--" << s3 << s4



   puts punycoded_url



   %x{ /usr/bin/open "#{punycoded_url}" }



end

Storm ORM by Canonical in WSGI enabled applications

sevkin (Vsevolod Balashov) — Fri, 10 Aug 2007 11:39:51 GMT



#!/usr/bin/env python

# vim:ts=4:sw=4:et

# (c) 2007 Vsevolod Balashov  under terms of LGPL 2.1

# use Storm ORM  in WSGI enabled applications



"""WSGI middleware for Storm.



This is the database access inteface for WSGI enabled (PEP 333) web applications.



Pylons framework example:



in wsgiapp.py



from storm.database import create_database

from middlestorm import MiddleStorm

...



# CUSTOM MIDDLEWARE HERE

app = MiddleStorm(app, create_database(config['app_conf']['sqlalchemy.default.uri']))



in controller:



class DemoController(BaseController):

    def index(self):

        store = request.environ['storm.store']

        ...

"""



from storm.database import Database

from storm.store import Store

from threading import local



__all__ = ["MiddleStorm"]

__author__ = "Vsevolod Balashov "

__version__ = "0.1"



class SingleConn(Database):

    """Database proxy class.

    Share single database connection between all Store object instances in threads.

    If you have readonly database or not use transactions why not?

    """

    def __init__(self, database):

        self._database = database

        self._connection = database.connect()

    def connect(self):

        return self._connection



class MiddleStorm(object):

    """WSGI middleware.

    Add Store object instance in environ['storm.store']. Each thread contains own instance.

    """



    def __init__(self, app, database, single = False):

        """Create WSGI middleware.

        @param app: up level application or middleware.

        @param database: instance of Database returned create_database.

        @param: single: use single database connection in all threads. 

        """

        assert isinstance(database, Database), \

            'database must be subclass of storm.database.Database'

        if single:

            self._database = SingleConn(database)

        else:

            self._database = database

        self._app = app

        self._local = local()



    def __call__(self, environ, start_response):

        try:

            environ['storm.store']  = self._local.store

        except AttributeError:

            environ['storm.store']  = \

                self._local.__dict__.setdefault('store', Store(self._database))

        return self._app(environ, start_response)