web code

Inspect a website like a string in Ruby

Put the following function into your ~/.bash_login (or alternatives).

unset -f inspect_url

function inspect_url() { 
   /usr/bin/curl -L -s --max-time 10 "${@}" | ruby -n -e 'p $_.to_s'
   return 0
}

inspect_url http://www.ruby-forum.com

to html mac unix osx bash shell encoding web url character inspect by ntk on Jul 09, 2008

Compile & install Nginx web server

Requirement on Mac OS X: Xcode

# See:
# - http://en.wikipedia.org/wiki/Nginx
# - http://wiki.codemongers.com/NginxGettingStarted
# - http://wiki.codemongers.com/NginxInstallOptions
# - http://wiki.codemongers.com/NginxCommandLine
# - http://wiki.codemongers.com/NginxConfiguration

export PATH="/usr/local/bin:/usr/local/sbin:/usr/bin:/bin:/usr/sbin:/sbin"

mkdir -p ~/Desktop/Nginx
cd ~/Desktop/Nginx

curl -L -O http://sysoev.ru/nginx/nginx-0.7.2.tar.gz
tar -xzf nginx-0.7.2.tar.gz

curl -L -O http://downloads.sourceforge.net/pcre/pcre-7.7.tar.gz
tar -xzf pcre-7.7.tar.gz

cd ~/Desktop/Nginx/nginx-0.7.2
./configure --help
./configure --prefix=/usr/local/nginx --sbin-path=/usr/local/sbin --with-debug --with-http_ssl_module --with-pcre=../pcre-7.7
make
sudo make install


which nginx
otool -L /usr/local/sbin/nginx
open /usr/local/nginx
open -e /usr/local/nginx/conf/nginx.conf

nginx -v
nginx -V
sudo nginx   # start server
sudo nginx -t

open http://localhost:80
open http://localhost:80/50x.html

sudo nano /usr/local/nginx/conf/nginx.conf   # editing ... server {  listen  8080; ... 

# reload configuration
sudo kill -HUP `cat /usr/local/nginx/logs/nginx.pid`  

# stop server
sudo kill -15 $(ps -auxxx | egrep "[n]ginx.*master" | awk '{ print $2 }') 2>/dev/null

to mac unix osx shell web webserver install compile nginx by ntk on Jun 18, 2008

Basic WEBrick setup for local web server

Put the following functions and aliases into your ~/.bash_login (or alternatives).


unset -f webrick_local

function webrick_local() { 

   declare root_dir="${HOME}/Desktop/www"

   /bin/mkdir -p "${root_dir}/WEBrickLog"
   /bin/chmod 0754 "${root_dir}" "${root_dir}/WEBrickLog"

   /usr/bin/touch "${root_dir}/WEBrickLog/webrick.pid" "${root_dir}/WEBrickLog/webrick_ruby.pid"
   /bin/chmod 0644 "${root_dir}/WEBrickLog/webrick.pid" "${root_dir}/WEBrickLog/webrick_ruby.pid"

#   /usr/bin/touch "${root_dir}/index.html"
#   /bin/chmod 0754 "${root_dir}/index.html"


/usr/local/bin/ruby <<-HEREDOC

   require 'webrick'
   require 'webrick/accesslog'
   include WEBrick

   require 'thread'
   require 'pp'

   root_dir = "${root_dir}"
   http_dir = File.expand_path(root_dir)

   File.open(http_dir + "/WEBrickLog/webrick_ruby.pid", "w") do |f|
      f.puts(Process.pid)
   end

   # cf. http://microjet.ath.cx/webrickguide/html/Logging.html
   webrick_log_file = File.expand_path(http_dir + "/WEBrickLog/webrick.log")
   #webrick_log_file = '/dev/null'  # disable logging
   webrick_logger = WEBrick::Log.new(webrick_log_file, WEBrick::Log::DEBUG)

   access_log_stream = webrick_logger
   access_log = [[ access_log_stream, WEBrick::AccessLog::COMBINED_LOG_FORMAT ]]

   system_mime_table = WEBrick::HTTPUtils::load_mime_types('/private/etc/httpd/mime.types.default')
   system_mime_table.store('rhtml', 'text/html')   # add a mime type for .rhtml files
   system_mime_table.store('php', 'text/html')
   system_mime_table.store('rb', 'text/plain')
   system_mime_table.store('pid', 'text/plain')
   #pp system_mime_table.sort_by { |k,v| k }

   server = WEBrick::HTTPServer.new(
     :BindAddress     =>    "localhost",
     :Port            =>    9090,
     :DocumentRoot    =>    http_dir,
     :FancyIndexing   =>    true,
     :MimeTypes       =>    system_mime_table,
     :Logger          =>    webrick_logger,
     :AccessLog       =>    access_log
   )

   server.config.store(:DirectoryIndex, server.config[:DirectoryIndex] << "default.htm")
   #pp server.config

   # cf. http://snippets.dzone.com/posts/show/5208
   class TimeServlet < HTTPServlet::AbstractServlet

      def do_GET(req, res)
         res['Content-Type'] = 'text/html'
         res.status = 200
         res.body = "<html>Time: #{Time.now.to_s}</html>" + "\n"
      end

      # cf. http://www.hiveminds.co.uk/node/244, published under the
      # GNU Free Documentation License, http://www.gnu.org/copyleft/fdl.html

      @@instance = nil
      @@instance_creation_mutex = Mutex.new

      def self.get_instance(config, *options)
         #pp @@instance
         @@instance_creation_mutex.synchronize { 
            @@instance = @@instance || self.new(config, *options) }
      end

   end


   # cf. http://ttripp.blogspot.com/2007/01/fun-with-http.html
   class PostDumper < WEBrick::HTTPServlet::AbstractServlet
  
      # Reload file for each request, instantly
      # updating the server with code changes 
      # without needing a restart.

=begin
      def PostDumper.get_instance( config, *options )
         load __FILE__
         PostDumper.new config, *options
      end
=end

      # cf. http://www.hiveminds.co.uk/node/244, published under the
      # GNU Free Documentation License, http://www.gnu.org/copyleft/fdl.html

      @@instance = nil
      @@instance_creation_mutex = Mutex.new

      def self.get_instance(config, *options)
         #pp @@instance
         @@instance_creation_mutex.synchronize { 
            @@instance = @@instance || self.new(config, *options) }
      end

      def do_GET( request, response )
         response.status = 200
         response['Content-Type'] = "text/plain"
         response.body = dump_request( request )
      end
  
      def do_POST( request, response )
         response.status = 200
         response['Content-Type'] = "text/plain"
         response.body = dump_request( request )
         response.body << request.body
      end
  
      def dump_request( request )
         request.request_line << "\r\n" <<
         request.raw_header.join( "" ) << "\r\n"
      end
   end

   server.mount("/dump", PostDumper)
   server.mount("/time", TimeServlet, {:FancyIndexing=>true})

   # handle signals
   %w(INT).each do |signal|
      trap(signal) { server.shutdown }
   end

   server.start

HEREDOC

return 0

}

export -f webrick_local

# start WEBrick alias
alias webrick='swr'

# start WEBrick
unset -f swr
function swr() {   
  declare webrick_pid_file="${HOME}/Desktop/www/WEBrickLog/webrick.pid"
  if [[ -e "${webrick_pid_file}" ]]; then echo "WEBrick already started!"; return 1; fi
  /bin/bash -c "webrick_local" &
  declare WEBRICKPID=$!
  mkdir -p "${HOME}/Desktop/www/WEBrickLog"
  echo $WEBRICKPID > "${HOME}/Desktop/www/WEBrickLog/webrick.pid"
  return 0
}
export -f swr

# quit WEBrick
unset -f qwr
function qwr() { 
   declare webrick_pid_file="${HOME}/Desktop/www/WEBrickLog/webrick.pid"
   declare webrick_ruby_pid_file="${HOME}/Desktop/www/WEBrickLog/webrick_ruby.pid"
   if [[ ! -e "${webrick_pid_file}" ]]; then echo "no such file: ${webrick_pid_file}"; return 1; fi
   declare PIDW=$(cat "${webrick_pid_file}" 2>/dev/null)
   declare PIDR=$(cat "${webrick_ruby_pid_file}" 2>/dev/null)
   kill -INT $PIDW 2>/dev/null || echo "no such PIDW: ${PIDW}"
   kill -INT $PIDR 2>/dev/null || echo "no such PIDR: ${PIDR}"
   rm -f "${webrick_pid_file}" "${webrick_ruby_pid_file}"
   return 0
}
export -f qwr

# quit WEBrick; cf. Job Control Commands, http://tldp.org/LDP/abs/html/x8816.html
###alias qwr='echo "quit WEBrick with ctrl-c ..."; fg %webrick 2>/dev/null'

alias openwww='/usr/bin/open http://localhost:9090'
alias wrlog='/usr/bin/open http://localhost:9090/WEBrickLog/webrick.log'


#----------------------------------------


source ~/.bash_login

webrick

openwww
wrlog
open http://localhost:9090 
open http://localhost:9090/WEBrickLog
open http://localhost:9090/WEBrickLog/webrick.log

open http://localhost:9090/time
open http://localhost:9090/dump

wrlog
qwr

Further information:

- WEBrick
- WEBrick RDoc
- What is WEBrick?
- Guide to using WEBrick for Rails development
- Dynamic WEBrick Servers in Ruby
- Gnome's Guide to WEBrick
- Running Servlets with WEBrick
- rsphandler
- URL rewriting with WEBrick

to ruby mac osx bash shell web webrick webserver LOCAL servlet by ntk on Jun 17, 2008

One-line web server in Ruby


# 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}'

to ruby unix bash shell web server socket TCPServer by ntk on Apr 23, 2008

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

to ruby utf8 unicode web http internet ascii punycode idn by ntk on Sep 26, 2007

Search DZone Snippets

Popular @ dzone.com

Related Tags

ntk's Tags

Never been to DZone Snippets before?

About this user

Inspect a website like a string in Ruby

Compile & install Nginx web server

Basic WEBrick setup for local web server

One-line web server in Ruby

Punycoded URLs in Ruby