url_escape 2009.06.24-java

data/ext/extconf.rb

@@ -0,0 +1,3 @@
+require 'mkmf'
+
+create_makefile "ext/url_escape"

data/lib/url_escape.rb

@@ -0,0 +1,17 @@
+# Copyright © 2009 Evan Phoenix and The Rubyists, LLC
+# Distributed under the terms of the MIT license.
+# See the LICENSE file which accompanies this software for the full text
+require 'java'
+
+module URLEscape
+  include_class 'java.net.URLEncoder'
+  include_class 'java.net.URLDecoder'
+
+  def self.escape(str)
+    URLEncoder.encode(str, "UTF-8")
+  end
+
+  def self.unescape(escaped_str)
+    URLDecoder.decode(escaped_str, "UTF-8")
+  end
+end

data/spec/bench.rb

@@ -0,0 +1,47 @@
+# Copyright © 2009 Evan Phoenix and The Rubyists, LLC
+# Distributed under the terms of the MIT license.
+# See the LICENSE file which accompanies this software for the full text
+require File.expand_path("../helper", __FILE__)
+require 'benchmark'
+require 'rack'
+require 'cgi'
+
+
+describe "URLEscape benchmark" do
+  def benchit(obj, meth, s = nil)
+    n = 100
+    s ||= "%03a" * 10000
+    bm = Benchmark.bmbm { |b|
+      b.report("#{obj.name}::#{meth}") { n.times{ obj.send(meth, s) } }
+    }
+  end
+
+  def multiplier
+   /java/i === RUBY_PLATFORM ? [4,2] : [25,15]
+  end
+
+  it "runs faster than standard CGI.unescape" do
+    one = benchit(URLEscape, :unescape).first
+    two = benchit(CGI, :unescape).first
+    two.real.should > multiplier.first * one.real
+  end
+
+  it "runs faster than Rack::Utils.unescape" do
+    one = benchit(URLEscape, :unescape).first
+    two = benchit(Rack::Utils, :unescape).first
+    two.real.should > multiplier.first * one.real
+  end
+
+  it "runs faster than standard CGI.escape" do
+    one = benchit(URLEscape, :escape).first
+    two = benchit(CGI, :escape).first
+    two.real.should > multiplier.last * one.real
+  end
+
+  it "runs faster than Rack::Utils.escape" do
+    one = benchit(URLEscape, :escape).first
+    two = benchit(Rack::Utils, :escape).first
+    two.real.should > multiplier.last * one.real
+  end
+
+end

data/spec/big_bench.rb

@@ -0,0 +1,76 @@
+# Copyright © 2009 Evan Phoenix and The Rubyists, LLC
+# Distributed under the terms of the MIT license.
+# See the LICENSE file which accompanies this software for the full text
+require File.expand_path("../helper", __FILE__)
+require 'benchmark'
+require 'rack'
+require 'cgi'
+
+describe "Long running benchmarks" do
+  def benchit(obj, meth, s)
+    n = 100
+    s = s * 10000
+    bm = Benchmark.bmbm { |b|
+      b.report("#{obj.name}::#{meth}") { n.times{ obj.send(meth, s) } }
+    }
+  end
+
+  def multiplier
+   /java/i === RUBY_PLATFORM ? [3,2] : [7,4]
+  end
+
+  it "is efficient on larger encoded sets" do
+    hex_table = [
+      "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07",
+      "%08", "%09", "%0a", "%0b", "%0c", "%0d", "%0e", "%0f",
+      "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17",
+      "%18", "%19", "%1a", "%1b", "%1c", "%1d", "%1e", "%1f",
+      "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
+      "%28", "%29", "%2a", "%2b", "%2c", "%2d", "%2e", "%2f",
+      "%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37",
+      "%38", "%39", "%3a", "%3b", "%3c", "%3d", "%3e", "%3f",
+      "%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47",
+      "%48", "%49", "%4a", "%4b", "%4c", "%4d", "%4e", "%4f",
+      "%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57",
+      "%58", "%59", "%5a", "%5b", "%5c", "%5d", "%5e", "%5f",
+      "%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67",
+      "%68", "%69", "%6a", "%6b", "%6c", "%6d", "%6e", "%6f",
+      "%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77",
+      "%78", "%79", "%7a", "%7b", "%7c", "%7d", "%7e", "%7f",
+      "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87",
+      "%88", "%89", "%8a", "%8b", "%8c", "%8d", "%8e", "%8f",
+      "%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97",
+      "%98", "%99", "%9a", "%9b", "%9c", "%9d", "%9e", "%9f",
+      "%a0", "%a1", "%a2", "%a3", "%a4", "%a5", "%a6", "%a7",
+      "%a8", "%a9", "%aa", "%ab", "%ac", "%ad", "%ae", "%af",
+      "%b0", "%b1", "%b2", "%b3", "%b4", "%b5", "%b6", "%b7",
+      "%b8", "%b9", "%ba", "%bb", "%bc", "%bd", "%be", "%bf",
+      "%c0", "%c1", "%c2", "%c3", "%c4", "%c5", "%c6", "%c7",
+      "%c8", "%c9", "%ca", "%cb", "%cc", "%cd", "%ce", "%cf",
+      "%d0", "%d1", "%d2", "%d3", "%d4", "%d5", "%d6", "%d7",
+      "%d8", "%d9", "%da", "%db", "%dc", "%dd", "%de", "%df",
+      "%e0", "%e1", "%e2", "%e3", "%e4", "%e5", "%e6", "%e7",
+      "%e8", "%e9", "%ea", "%eb", "%ec", "%ed", "%ee", "%ef",
+      "%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
+      "%f8", "%f9", "%fa", "%fb", "%fc", "%fd", "%fe", "%ff"
+    ]
+
+    s = URLEscape.unescape(hex_table.join)
+    one = benchit(URLEscape, :escape, s).first
+    two = benchit(Rack::Utils, :escape, s).first
+    two.real.should > multiplier.first * one.real
+
+    three = benchit(CGI, :escape, s).first
+    three.real.should > multiplier.first * one.real
+
+    s = hex_table.join
+    one = benchit(URLEscape, :unescape, s).first
+    two = benchit(Rack::Utils, :unescape, s).first
+    two.real.should >  multiplier.last * one.real
+
+    three = benchit(CGI, :unescape, s).first
+    three.real.should > multiplier.last * one.real
+  end
+end
+
+

data/spec/helper.rb

@@ -0,0 +1,21 @@
+# Copyright © 2009 Evan Phoenix and The Rubyists, LLC
+# Distributed under the terms of the MIT license.
+# See the LICENSE file which accompanies this software for the full text
+require 'rbconfig'
+
+unless RUBY_PLATFORM.match(/java/)
+  ext = File.expand_path("../../ext", __FILE__)
+  exec_format = RbConfig::CONFIG['ruby_install_name'].sub(/^ruby.*$/, '%s') rescue '%s'
+
+  system(exec_format % 'rake', 'build')
+
+  require File.join(ext, "url_escape")
+else
+  lib = File.expand_path("../../lib", __FILE__)
+  require File.join(lib, "url_escape")
+end
+
+  require "rubygems"
+  require "bacon"
+
+Bacon.summary_at_exit

data/spec/url_escape.rb

@@ -0,0 +1,108 @@
+# * Encoding: UTF-8
+# Copyright © 2009 Evan Phoenix and The Rubyists, LLC
+# Distributed under the terms of the MIT license.
+# See the LICENSE file which accompanies this software for the full text
+
+require File.expand_path("../helper", __FILE__)
+require "rack"
+require "cgi"
+
+describe "URLEscape" do
+  describe '#escape' do
+    def escape(input)
+      URLEscape.escape input
+    end
+
+    it "should escape a standard ascii string" do
+      s = "A standard ascii string."
+      escape(s).should == Rack::Utils.escape(s) # This should have spaces escaped
+      escape(s).should == CGI.escape(s) # This should have spaces escaped
+      escape(s).should == 'A+standard+ascii+string.' # This should have spaces escaped
+      s1 = 'a & b'
+      escape(s1).should == Rack::Utils.escape(s1) # This should have spaces escaped and the amp encoded
+      escape(s1).should == CGI.escape(s1) # This should have spaces escaped and the amp encoded
+      escape(s1).should == 'a+%26+b' # This should have spaces escaped and the amp encoded
+    end
+
+    it "should escape a very hairy ascii string" do
+      s = %q{oi&%$#@!;laksdf\"';:<>?\\}
+      escape(s).should == "oi%26%25%24%23%40%21%3Blaksdf%5C%22%27%3B%3A%3C%3E%3F%5C" # This should have lots of escapes
+      escape(s).should == CGI.escape(s)
+      escape(s).should == Rack::Utils.escape(s)
+    end
+
+    it 'escapes an escaped uri fragment' do
+      escape(s = "%C3%87").should == '%25C3%2587'
+      escape(s).should == CGI.escape(s)
+      escape(s).should == Rack::Utils.escape(s)
+    end
+
+    it 'escapes unicode' do
+      escape(s = 'ルビイスと').should == '%E3%83%AB%E3%83%93%E3%82%A4%E3%82%B9%E3%81%A8'
+      escape(s).should == CGI.escape(s)
+      escape(s).should == Rack::Utils.escape(s) unless /^1\.9/ === RUBY_VERSION
+    end
+
+    it 'escapes mixed ascii and unicode' do
+      escape(s = "oidfu㈤").should == "oidfu%E3%88%A4"
+      escape(s).should == CGI.escape(s)
+      escape(s).should == Rack::Utils.escape(s) unless /^1\.9/ === RUBY_VERSION
+    end
+
+    it 'handles high bit ascii strings' do
+      s = "\xA1oidfu\xB5"
+      if /java/i === RUBY_PLATFORM
+        escape(s).should == "%EF%BF%BDoidfu%EF%BF%BD"
+      else
+        escape(s).should == CGI.escape(s) unless /^1\.9/ === RUBY_VERSION
+        escape(s).should == Rack::Utils.escape(s) unless /^1\.9/ === RUBY_VERSION
+        escape(s).should == "%A1oidfu%B5"
+      end
+    end
+
+    it 'treats strings ending in a unicode starting byte as high bit ascii' do
+      s = "oidfu\xD5"
+      s1 = "\xE1\xB1"
+      if /java/i === RUBY_PLATFORM
+        escape(s).should == "oidfu%EF%BF%BD"
+        escape(s1).should == "%EF%BF%BD" 
+      else
+        escape(s).should == CGI.escape(s) unless /^1\.9/ === RUBY_VERSION
+        escape(s).should == Rack::Utils.escape(s) unless /^1\.9/ === RUBY_VERSION
+        escape(s).should == "oidfu%D5"
+
+        escape(s1).should == CGI.escape(s1) unless /^1\.9/ === RUBY_VERSION
+        escape(s1).should == Rack::Utils.escape(s1) unless /^1\.9/ === RUBY_VERSION
+        escape(s1).should == "%E1%B1" 
+      end
+    end
+  end
+
+  describe '#unescape' do
+    def unescape(input)
+      URLEscape.unescape input
+    end
+
+    it "should unescape a url" do
+      s = "http://a.simple.url/foo_bar.php?hey=you%20me"
+      unescape(s).should == "http://a.simple.url/foo_bar.php?hey=you me" # This should have spaces expanded
+      unescape(s).should == CGI.unescape(s)
+      unescape(s).should == Rack::Utils.unescape(s)
+    end
+
+    it 'should unescape unicode' do
+      s = 'ルビイスと'
+      if s.respond_to?(:force_encoding)
+        unescape('%E3%83%AB%E3%83%93%E3%82%A4%E3%82%B9%E3%81%A8').
+          should == s.force_encoding("ASCII-8BIT")
+        unescape(s).should == CGI.unescape(s)
+        unescape(s).should == Rack::Utils.unescape(s)
+      else
+        unescape('%E3%83%AB%E3%83%93%E3%82%A4%E3%82%B9%E3%81%A8').
+          should == s
+        unescape(s).should == CGI.unescape(s)
+        unescape(s).should == Rack::Utils.unescape(s)
+      end
+    end
+  end
+end

data/tasks/authors.rake

@@ -0,0 +1,34 @@
+# Once git has a fix for the glibc in handling .mailmap and another fix for
+# allowing empty mail address to be mapped in .mailmap we won't have to handle
+# them manually.
+
+desc 'Update AUTHORS'
+task :authors do
+  authors = Hash.new(0)
+  unless /java/i === RUBY_PLATFORM
+    `git shortlog -nse`.scan(/(\d+)\s(.+)\s<(.*)>$/) do |count, name, email|
+      # Examples of mappping, replace with your own or comment this out/delete it
+      case name
+      when /^(?:bougyman$|TJ Vanderpoel)/
+        name, email = "TJ Vanderpoel", "tj@rubyists.com"
+      when /^(?:manveru$|Michael Fellinger)/
+        name, email = "Michael Fellinger", "mf@rubyists.com"
+      when /^(?:deathsyn$|Kevin Berry)/
+        name, email = "Kevin Berry", "kb@rubyists.com"
+      when /^(?:Admin)/
+        name, email = "Trey Dempsey", "trey.dempsey@gmail.com"
+      end
+
+      authors[[name, email]] += count.to_i
+    end
+
+    File.open('AUTHORS', 'w+') do |io|
+      io.puts "Following persons have contributed to #{GEMSPEC.name}."
+      io.puts '(Sorted by number of submitted patches, then alphabetically)'
+      io.puts ''
+      authors.sort_by{|(n,e),c| [-c, n.downcase] }.each do |(name, email), count|
+        io.puts("%6d %s <%s>" % [count, name, email])
+      end
+    end
+  end
+end

data/tasks/bacon.rake

@@ -0,0 +1,77 @@
+desc 'Run all bacon specs with pretty output'
+task :bacon => :setup do
+  require 'open3'
+  require 'scanf'
+  require 'matrix'
+
+  specs = PROJECT_SPECS
+
+  some_failed = false
+  specs_size = specs.size
+  if specs.size == 0
+    $stderr.puts "You have no specs!  Put a spec in spec/ before running this task"
+    exit 1
+  end
+  len = specs.map{|s| s.size }.sort.last
+  total_tests = total_assertions = total_failures = total_errors = 0
+  totals = Vector[0, 0, 0, 0]
+
+  red, yellow, green = "\e[31m%s\e[0m", "\e[33m%s\e[0m", "\e[32m%s\e[0m"
+  left_format = "%4d/%d: %-#{len + 11}s"
+  spec_format = "%d specifications (%d requirements), %d failures, %d errors"
+
+  $stderr.puts "Executing on windows.  Colors won't work and errors won't be separated.\n" if(RUBY_PLATFORM.match(/mswin/))
+
+  specs.each_with_index do |spec, idx|
+    print(left_format % [idx + 1, specs_size, spec])
+
+    if(RUBY_PLATFORM.match(/mswin/))
+      running_spec = IO.popen("#{RUBY} #{spec}")
+      out = running_spec.read.strip
+      err = ""
+    else
+      sin, sout, serr = Open3.popen3(RUBY, spec)
+      out = sout.read.strip
+      err = serr.read.strip
+    end
+
+    # this is conventional, see spec/innate/state/fiber.rb for usage
+    if out =~ /^Bacon::Error: (needed .*)/
+      puts(yellow % ("%6s %s" % ['', $1]))
+    else
+      total = nil
+
+      out.each_line do |line|
+        scanned = line.scanf(spec_format)
+
+        next unless scanned.size == 4
+
+        total = Vector[*scanned]
+        break
+      end
+
+      if total
+        totals += total
+        tests, assertions, failures, errors = total_array = total.to_a
+
+        if tests > 0 && failures + errors == 0
+          puts((green % "%6d passed") % tests)
+        else
+          some_failed = true
+          puts(red % "       failed")
+          puts out unless out.empty?
+          puts err unless err.empty?
+        end
+      else
+        some_failed = true
+        puts(red % "       failed")
+        puts out unless out.empty?
+        puts err unless err.empty?
+      end
+    end
+  end
+
+  total_color = some_failed ? red : green
+  puts(total_color % (spec_format % totals.to_a))
+  exit 1 if some_failed
+end

data/tasks/build.rake

@@ -0,0 +1,56 @@
+require 'rbconfig'
+
+task :build do
+  if(RUBY_PLATFORM.match(/mswin/))
+    build_mswin
+  else
+    build_unix
+  end
+end
+
+def build_unix
+  Dir.chdir 'ext' do
+    sh 'make distclean' rescue nil
+    ruby 'extconf.rb'
+    sh 'make'
+  end
+end
+
+def build_mswin
+  mswin_gotchas
+  Dir.chdir 'ext' do
+    sh 'nmake distclean' rescue nil
+    File.unlink('url_escape.so.manifest') rescue nil
+    ruby 'extconf.rb'
+    sh 'nmake'
+    sh 'mt -manifest url_escape.so.manifest -outputresource:url_escape.so;#2'
+  end
+end
+
+def mswin_gotchas
+  if(ENV['VCINSTALLDIR'].nil?)
+    puts "\nWARNING: Your development environment may not be correctly configured.  Run vcvars32 first to setup the environment\n\n"
+    sleep 5
+  end
+
+  config_h = [
+    File.join(RbConfig::CONFIG["archdir"], "config.h"),
+    File.join(RbConfig::CONFIG["rubyhdrdir"], RbConfig::CONFIG["arch"], "ruby", "config.h")
+  ].detect { |file| File.exists?(file) }
+
+  if(config_h)
+    File.open(config_h, "r") do |f|
+      f.each do |l|
+        if(l.match(/_MSC_VER/))
+          puts "\nWARNING: Windows Ruby config.h checks for Microsoft VC 6.0.  Remove the following lines to allow compiling on later editions."
+          puts "Remove #if _MSC_VER != 1200"
+          puts "       #error MSC version unmatch"
+          puts "       #endif"
+          puts "From #{config_h}\n\n"
+          sleep 5
+          break
+        end
+      end
+    end
+  end
+end