hpricot 0.8.2-java

data/CHANGELOG

@@ -0,0 +1,88 @@
+= 0.8.2
+=== 5 November, 2009
+* Bring JRuby support up to speed, including Java-based hpricot_css support
+* Change JRuby fast_xs to have same escaping behavior as C fast_xs
+
+= 0.8.1
+=== 3 April, 2009
+* fix for issue #2, downcasing of html attributes inside the parser.
+* solve issue #3 with bogus etags being preserved in `to_s` rather than just `to_original_html`.
+* fix error when attempting to reparent cleared node. (issue #5)
+* Hpricot::Attributes proxy object for using `ele.attributes[k] = v` directly.
+  however, it is preferred to use the jquery-like `elements.attr(k, v)`.
+
+= 0.8
+=== 31st March, 2009
+* Saving memory and speed by using RStruct-based elements in the C extension.
+* Bug in tag parsing, causing runaway <script> and <style> tags in HTML.
+* Problem compiling under Ruby 1.9, due to our_rb_hash_lookup function meant for Ruby 1.8.
+* CData was missing inner_text method.
+
+= 0.7
+=== 17th March, 2009
+* Rewritten parser routine, much lighter on memory, quite a bit faster.
+* Friendlier with Ruby 1.9.
+* Fixes to nth-child and text() selectors.
+
+= 0.6
+=== 15th June, 2007
+* Hpricot for JRuby -- nice work Ola Bini!
+* Inline Markaby for Hpricot documents.
+* XML tags and attributes are no longer downcased like HTML is.
+* new syntax for grabbing everything between two elements using a Range in the search method: (doc/("font".."font/br")) or in nodes_at like so: (doc/"font").nodes_at("*".."br"). Only works with either a pair of siblings or a set of a parent and a sibling. 
+* Ignore self-closing endings on tags (such as form) which are containers. Treat them like open parent tags. Reported by Jonathan Nichols on the hpricot list.
+* Escaping of attributes, yanked from Jim Weirich and Sam Ruby's work in Builder.
+* Element#raw_attributes gives unescaped data.  Element#attributes gives escaped.
+* Added: Elements#attr, Elements#remove_attr, Elements#remove_class.
+* Added: Traverse#preceding, Traverse#following, Traverse#previous, Traverse#next. 
+
+= 0.5
+=== 31rd January, 2007
+
+* support for a[text()="Click Me!"] and h3[text()*="space"] and the like.
+* Hpricot.buffer_size accessor for increasing Hpricot's buffer if you're encountering huge ASP.NET viewstate attribs.
+* some support for colons in tag names (not full namespace support yet.)
+* Element.to_original_html will attempt to preserve the original HTML while merging your changes.
+* Element.to_plain_text converts an element's contents to a simple text format.
+* Element.inner_text removes all tags and returns text nodes concatenated into a single string.
+* no @raw_string variable kept for comments, text, and cdata -- as it's redundant.
+* xpath-style indices (//p/a[1]) but keep in mind that they aren't zero-based.
+* node_position is the index among all sibling nodes, while position is the position among children of identical type.
+* comment() and text() search criteria, like: //p/text(), which selects all text inside paragraph tags.
+* every element has css_path and xpath methods which return respective absolute paths.
+* more flexibility all around: in parsing attributes, tags, comments and cdata.
+
+= 0.4
+=== 11th August, 2006
+
+* The :fixup_tags option will try to sort out the hierarchy so elements end up with the right parents.
+* Elements such as *script* and *style* (identified as having CDATA contents) receive a single text node as their children now.  Previously, Hpricot was parsing out tags found in scripts.
+* Better scanning of partially quoted attributes (found by Brent Beardsly on http://uswebgen.com/)
+* Better scanning of unquoted attributes -- thanks to Aaron Patterson for the test cases!
+* Some tags were being output in the empty tag style, although browsers hated that.  FIXED!
+* Added Elements#at for finding single elements.
+* Added Elem::Trav#[] and Elem::Trav#[]= for reading and writing attributes.
+
+= 0.3
+=== 7th July, 2006
+
+* Fixed negative string size error on empty tokens. (news.bbc.co.uk)
+* Allow the parser to accept just text nodes. (such as: <tt>Hpricot.parse('TEXT')</tt>)
+* from JQuery to Hpricot::Elements: remove, empty, append, prepend, before, after, wrap, set, 
+  html(...), to_html, to_s. 
+* on containers: to_html, replace_child, insert_before, insert_after, innerHTML=.
+* Hpricot(...) is an alias for parse.
+* open up all properties to setters, let people do as they may. 
+* use to_html for the full html of a node or set of elements.
+* doctypes were messed.
+
+= 0.2
+=== 4th July, 2006
+
+* Rewrote the HTree parser to be simpler, more adequate for the common man.  Will add encoding back in later.
+
+= 0.1
+=== 3rd July, 2006
+
+* For whatever reason, wrote this HTML parser in C.
+  I guess Ragel is addictive and I want to improve HTree.

data/COPYING

@@ -0,0 +1,18 @@
+Copyright (c) 2006 why the lucky stiff
+
+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 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

@@ -0,0 +1,275 @@
+= Hpricot, Read Any HTML
+
+Hpricot is a fast, flexible HTML parser written in C.  It's designed to be very
+accommodating (like Tanaka Akira's HTree) and to have a very helpful library
+(like some JavaScript libs -- JQuery, Prototype -- give you.)  The XPath and CSS
+parser, in fact, is based on John Resig's JQuery.
+
+Also, Hpricot can be handy for reading broken XML files, since many of the same
+techniques can be used.  If a quote is missing, Hpricot tries to figure it out.
+If tags overlap, Hpricot works on sorting them out.  You know, that sort of
+thing.
+
+*Please read this entire document* before making assumptions about how this
+software works.
+
+== An Overview
+
+Let's clear up what Hpricot is.
+
+# Hpricot is *a standalone library*.  It requires no other libraries.  Just Ruby!
+# While priding itself on speed, Hpricot *works hard to sort out bad HTML* and
+  pays a small penalty in order to get that right.  So that's slightly more important
+  to me than speed.
+# *If you can see it in Firefox, then Hpricot should parse it.*  That's
+  how it should be!  Let me know the minute it's otherwise.
+# Primarily, Hpricot is used for reading HTML and tries to sort out troubled
+  HTML by having some idea of what good HTML is.  Some people still like to use
+  Hpricot for XML reading, but *remember to use the Hpricot::XML() method* for that!
+
+== The Hpricot Kingdom
+
+First, here are all the links you need to know:
+
+* http://wiki.github.com/hpricot/hpricot is the Hpricot wiki and
+  http://github.com/hpricot/hpricot/issues is the bug tracker.
+  Go there for news and recipes and patches.  It's the center of activity.
+* http://github.com/hpricot/hpricot is the main Git
+  repository for Hpricot.  You can get the latest code there.
+* See COPYING for the terms of this software. (Spoiler: it's absolutely free.)
+
+If you have any trouble, don't hesitate to contact the author.  As always, I'm
+not going to say "Use at your own risk" because I don't want this library to be
+risky.  If you trip on something, I'll share the liability by repairing things
+as quickly as I can.  Your responsibility is to report the inadequacies.
+
+== Installing Hpricot
+
+You may get the latest stable version from Rubyforge. Win32 binaries,
+Java binaries (for JRuby), and source gems are available.
+
+  $ gem install hpricot
+
+== An Hpricot Showcase
+
+We're going to run through a big pile of examples to get you jump-started.
+Many of these examples are also found at
+http://wiki.github.com/hpricot/hpricot/hpricot-basics, in case you
+want to add some of your own.
+
+=== Loading Hpricot Itself
+
+You have probably got the gem, right?  To load Hpricot:
+
+ require 'rubygems'
+ require 'hpricot'
+
+If you've installed the plain source distribution, go ahead and just:
+
+ require 'hpricot'
+
+=== Load an HTML Page
+
+The <tt>Hpricot()</tt> method takes a string or any IO object and loads the
+contents into a document object.
+
+ doc = Hpricot("<p>A simple <b>test</b> string.</p>")
+
+To load from a file, just get the stream open:
+
+ doc = open("index.html") { |f| Hpricot(f) }
+
+To load from a web URL, use <tt>open-uri</tt>, which comes with Ruby:
+
+ require 'open-uri'
+ doc = open("http://qwantz.com/") { |f| Hpricot(f) }
+
+Hpricot uses an internal buffer to parse the file, so the IO will stream
+properly and large documents won't be loaded into memory all at once.  However,
+the parsed document object will be present in memory, in its entirety.
+
+=== Search for Elements
+
+Use <tt>Doc.search</tt>:
+
+ doc.search("//p[@class='posted']")
+ #=> #<Hpricot:Elements[{p ...}, {p ...}]>
+
+<tt>Doc.search</tt> can take an XPath or CSS expression.  In the above example,
+all paragraph <tt><p></tt> elements are grabbed which have a <tt>class</tt>
+attribute of <tt>"posted"</tt>.
+
+A shortcut is to use the divisor:
+
+ (doc/"p.posted")
+ #=> #<Hpricot:Elements[{p ...}, {p ...}]>
+
+=== Finding Just One Element
+
+If you're looking for a single element, the <tt>at</tt> method will return the
+first element matched by the expression.  In this case, you'll get back the
+element itself rather than the <tt>Hpricot::Elements</tt> array.
+
+ doc.at("body")['onload']
+
+The above code will find the body tag and give you back the <tt>onload</tt>
+attribute.  This is the most common reason to use the element directly: when
+reading and writing HTML attributes.
+
+=== Fetching the Contents of an Element
+
+Just as with browser scripting, the <tt>inner_html</tt> property can be used to
+get the inner contents of an element.
+
+ (doc/"#elementID").inner_html
+ #=> "..<b>contents</b>.."
+
+If your expression matches more than one element, you'll get back the contents
+of ''all the matched elements''.  So you may want to use <tt>first</tt> to be
+sure you get back only one.
+
+ (doc/"#elementID").first.inner_html
+ #=> "..<b>contents</b>.."
+
+=== Fetching the HTML for an Element
+
+If you want the HTML for the whole element (not just the contents), use
+<tt>to_html</tt>:
+
+ (doc/"#elementID").to_html
+ #=> "<div id='elementID'>...</div>"
+
+=== Looping
+
+All searches return a set of <tt>Hpricot::Elements</tt>.  Go ahead and loop
+through them like you would an array.
+
+ (doc/"p/a/img").each do |img|
+   puts img.attributes['class']
+ end
+
+=== Continuing Searches
+
+Searches can be continued from a collection of elements, in order to search deeper.
+
+ # find all paragraphs.
+ elements = doc.search("/html/body//p")
+ # continue the search by finding any images within those paragraphs.
+ (elements/"img")
+ #=> #<Hpricot::Elements[{img ...}, {img ...}]>
+
+Searches can also be continued by searching within container elements.
+
+ # find all images within paragraphs.
+ doc.search("/html/body//p").each do |para|
+   puts "== Found a paragraph =="
+   pp para
+
+   imgs = para.search("img")
+   if imgs.any?
+     puts "== Found #{imgs.length} images inside =="
+   end
+ end
+
+Of course, the most succinct ways to do the above are using CSS or XPath.
+
+ # the xpath version
+ (doc/"/html/body//p//img")
+ # the css version
+ (doc/"html > body > p img")
+ # ..or symbols work, too!
+ (doc/:html/:body/:p/:img)
+
+=== Looping Edits
+
+You may certainly edit objects from within your search loops.  Then, when you
+spit out the HTML, the altered elements will show.
+
+ (doc/"span.entryPermalink").each do |span|
+   span.attributes['class'] = 'newLinks'
+ end
+ puts doc
+
+This changes all <tt>span.entryPermalink</tt> elements to
+<tt>span.newLinks</tt>.  Keep in mind that there are often more convenient ways
+of doing this.  Such as the <tt>set</tt> method:
+
+ (doc/"span.entryPermalink").set(:class => 'newLinks')
+
+=== Figuring Out Paths
+
+Every element can tell you its unique path (either XPath or CSS) to get to the
+element from the root tag.
+
+The <tt>css_path</tt> method:
+
+ doc.at("div > div:nth(1)").css_path
+   #=> "div > div:nth(1)" 
+ doc.at("#header").css_path
+   #=> "#header" 
+
+Or, the <tt>xpath</tt> method:
+
+ doc.at("div > div:nth(1)").xpath
+   #=> "/div/div:eq(1)" 
+ doc.at("#header").xpath
+   #=> "//div[@id='header']" 
+
+== Hpricot Fixups
+
+When loading HTML documents, you have a few settings that can make Hpricot more
+or less intense about how it gets involved.
+
+== :fixup_tags
+
+Really, there are so many ways to clean up HTML and your intentions may be to
+keep the HTML as-is.  So Hpricot's default behavior is to keep things flexible.
+Making sure to open and close all the tags, but ignore any validation problems.
+
+As of Hpricot 0.4, there's a new <tt>:fixup_tags</tt> option which will attempt
+to shift the document's tags to meet XHTML 1.0 Strict.
+
+ doc = open("index.html") { |f| Hpricot f, :fixup_tags => true }
+
+This doesn't quite meet the XHTML 1.0 Strict standard, it just tries to follow
+the rules a bit better.  Like: say Hpricot finds a paragraph in a link, it's
+going to move the paragraph below the link.  Or up and out of other elements
+where paragraphs don't belong.
+
+If an unknown element is found, it is ignored.  Again, <tt>:fixup_tags</tt>.
+
+== :xhtml_strict
+
+So, let's go beyond just trying to fix the hierarchy.  The
+<tt>:xhtml_strict</tt> option really tries to force the document to be an XHTML
+1.0 Strict document.  Even at the cost of removing elements that get in the way.
+
+ doc = open("index.html") { |f| Hpricot f, :xhtml_strict => true }
+
+What measures does <tt>:xhtml_strict</tt> take?
+
+ 1. Shift elements into their proper containers just like :fixup_tags.
+ 2. Remove unknown elements.
+ 3. Remove unknown attributes.
+ 4. Remove illegal content.
+ 5. Alter the doctype to XHTML 1.0 Strict.
+
+== Hpricot.XML()
+
+The last option is the <tt>:xml</tt> option, which makes some slight variations
+on the standard mode.  The main difference is that :xml mode won't try to output
+tags which are friendlier for browsers.  For example, if an opening and closing
+<tt>br</tt> tag is found, XML mode won't try to turn that into an empty element.
+
+XML mode also doesn't downcase the tags and attributes for you.  So pay attention
+to case, friends.
+
+The primary way to use Hpricot's XML mode is to call the Hpricot.XML method:
+
+ doc = open("http://redhanded.hobix.com/index.xml") do |f|
+   Hpricot.XML(f)
+ end
+
+*Also, :fixup_tags is canceled out by the :xml option.*  This is because
+:fixup_tags makes assumptions based how HTML is structured.  Specifically, how
+tags are defined in the XHTML 1.0 DTD.

data/Rakefile

@@ -0,0 +1,272 @@
+require 'rake'
+require 'rake/clean'
+require 'rake/gempackagetask'
+require 'rake/rdoctask'
+require 'rake/testtask'
+require 'fileutils'
+include FileUtils
+
+RbConfig = Config unless defined?(RbConfig)
+
+NAME = "hpricot"
+REV = (`#{ENV['GIT'] || "git"} rev-list HEAD`.split.length + 1).to_s
+VERS = ENV['VERSION'] || "0.8" + (REV ? ".#{REV}" : "")
+PKG = "#{NAME}-#{VERS}"
+BIN = "*.{bundle,jar,so,o,obj,pdb,lib,def,exp,class}"
+CLEAN.include ["ext/hpricot_scan/#{BIN}", "ext/fast_xs/#{BIN}", "lib/**/#{BIN}",
+               'ext/fast_xs/Makefile', 'ext/hpricot_scan/Makefile',
+               '**/.*.sw?', '*.gem', '.config', 'pkg']
+RDOC_OPTS = ['--quiet', '--title', 'The Hpricot Reference', '--main', 'README', '--inline-source']
+PKG_FILES = %w(CHANGELOG COPYING README Rakefile) +
+      Dir.glob("{bin,doc,test,lib,extras}/**/*") +
+      Dir.glob("ext/**/*.{h,java,c,rb,rl}") +
+      %w[ext/hpricot_scan/hpricot_scan.c ext/hpricot_scan/hpricot_css.c ext/hpricot_scan/HpricotScanService.java] # needed because they are generated later
+RAGEL_C_CODE_GENERATION_STYLES = {
+  "table_driven" => 'T0',
+  "faster_table_driven" => 'T1',
+  "flat_table_driven" => 'F0',
+  "faster_flat_table_driven" => 'F1',
+  "goto_driven" => 'G0',
+  "faster_goto_driven" => 'G1',
+  "really_fast goto_driven" => 'G2'
+  # "n_way_split_really_fast_goto_driven" => 'P<N>'
+}
+DEFAULT_RAGEL_C_CODE_GENERATION = "really_fast goto_driven"
+SPEC =
+  Gem::Specification.new do |s|
+    s.name = NAME
+    s.version = VERS
+    s.platform = Gem::Platform::RUBY
+    s.has_rdoc = true
+    s.rdoc_options += RDOC_OPTS
+    s.extra_rdoc_files = ["README", "CHANGELOG", "COPYING"]
+    s.summary = "a swift, liberal HTML parser with a fantastic library"
+    s.description = s.summary
+    s.author = "why the lucky stiff"
+    s.email = 'why@ruby-lang.org'
+    s.homepage = 'http://code.whytheluckystiff.net/hpricot/'
+    s.rubyforge_project = 'hobix'
+    s.files = PKG_FILES
+    s.require_paths = ["lib"]
+    s.extensions = FileList["ext/**/extconf.rb"].to_a
+    s.bindir = "bin"
+  end
+
+Win32Spec = SPEC.dup
+Win32Spec.platform = 'x86-mswin32'
+Win32Spec.files = PKG_FILES + ["lib/hpricot_scan.so", "lib/fast_xs.so"]
+Win32Spec.extensions = []
+
+WIN32_PKG_DIR = "#{PKG}-mswin32"
+
+desc "Does a full compile, test run"
+if defined?(JRUBY_VERSION)
+task :default => [:compile_java, :test]
+else
+task :default => [:compile, :test]
+end
+
+desc "Packages up Hpricot."
+task :package => [:clean, :ragel]
+
+desc "Releases packages for all Hpricot packages and platforms."
+task :release => [:package, :package_win32, :package_jruby]
+
+
+desc "Run all the tests"
+Rake::TestTask.new do |t|
+    t.libs << "test"
+    t.test_files = FileList['test/test_*.rb']
+    t.verbose = true
+end
+
+Rake::RDocTask.new do |rdoc|
+    rdoc.rdoc_dir = 'doc/rdoc'
+    rdoc.options += RDOC_OPTS
+    rdoc.main = "README"
+    rdoc.rdoc_files.add ['README', 'CHANGELOG', 'COPYING', 'lib/**/*.rb']
+end
+
+Rake::GemPackageTask.new(SPEC) do |p|
+    p.need_tar = true
+    p.gem_spec = SPEC
+end
+
+['hpricot_scan', 'fast_xs'].each do |extension|
+  ext = "ext/#{extension}"
+  ext_so = "#{ext}/#{extension}.#{Config::CONFIG['DLEXT']}"
+  ext_files = FileList[
+    "#{ext}/*.c",
+    "#{ext}/*.h",
+    "#{ext}/*.rl",
+    "#{ext}/extconf.rb",
+    "#{ext}/Makefile",
+    "lib"
+  ]
+
+  desc "Builds just the #{extension} extension"
+  task extension.to_sym => [:ragel, "#{ext}/Makefile", ext_so ]
+
+  file "#{ext}/Makefile" => ["#{ext}/extconf.rb"] do
+    Dir.chdir(ext) do ruby "extconf.rb" end
+  end
+
+  file ext_so => ext_files do
+    Dir.chdir(ext) do
+      sh(RUBY_PLATFORM =~ /mswin/ ? 'nmake' : 'make')
+    end
+    cp ext_so, "lib"
+  end
+
+  desc "Cross-compile the #{extension} extension for win32"
+  file "#{extension}_win32" => [WIN32_PKG_DIR] do
+    cp "extras/mingw-rbconfig.rb", "#{WIN32_PKG_DIR}/ext/#{extension}/rbconfig.rb"
+    sh "cd #{WIN32_PKG_DIR}/ext/#{extension}/ && ruby -I. extconf.rb && make"
+    mv "#{WIN32_PKG_DIR}/ext/#{extension}/#{extension}.so", "#{WIN32_PKG_DIR}/lib"
+  end
+end
+
+task "lib" do
+  directory "lib"
+end
+
+desc "Compiles the Ruby extension"
+task :compile => [:hpricot_scan, :fast_xs] do
+  if Dir.glob(File.join("lib","hpricot_scan.*")).length == 0
+    STDERR.puts "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
+    STDERR.puts "Gem actually failed to build.  Your system is"
+    STDERR.puts "NOT configured properly to build hpricot."
+    STDERR.puts "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
+    exit(1)
+  end
+end
+
+desc "Determines the Ragel version and displays it on the console along with the location of the Ragel binary."
+task :ragel_version do
+  @ragel_v = `ragel -v`[/(version )(\S*)/,2].to_f
+  puts "Using ragel version: #{@ragel_v}, location: #{`which ragel`}"
+  @ragel_v
+end
+
+desc "Generates the C scanner code with Ragel."
+task :ragel => [:ragel_version] do
+  if @ragel_v >= 6.1
+    @ragel_c_code_generation_style = RAGEL_C_CODE_GENERATION_STYLES[DEFAULT_RAGEL_C_CODE_GENERATION]
+    Dir.chdir("ext/hpricot_scan") do
+      sh %{ragel hpricot_scan.rl -#{@ragel_c_code_generation_style} -o hpricot_scan.c}
+      sh %{ragel hpricot_css.rl -#{@ragel_c_code_generation_style} -o hpricot_css.c}
+    end
+  else
+    STDERR.puts "Ragel 6.1 or greater is required."
+    exit(1)
+  end
+end
+
+# Java only supports the table-driven code
+# generation style at this point.
+desc "Generates the Java scanner code using the Ragel table-driven code generation style."
+task :ragel_java => [:ragel_version] do
+  if @ragel_v >= 6.1
+    puts "compiling with ragel version #{@ragel_v}"
+    Dir.chdir("ext/hpricot_scan") do
+      sh %{ragel -J -o HpricotCss.java hpricot_css.java.rl}
+      sh %{ragel -J -o HpricotScanService.java hpricot_scan.java.rl}
+    end
+  else
+    STDERR.puts "Ragel 6.1 or greater is required."
+    exit(1)
+  end
+end
+
+### Win32 Packages ###
+
+desc "Package up the Win32 distribution."
+file WIN32_PKG_DIR => [:package] do
+  sh "tar zxf pkg/#{PKG}.tgz"
+  mv PKG, WIN32_PKG_DIR
+end
+
+desc "Build the binary RubyGems package for win32"
+task :package_win32 => ["fast_xs_win32", "hpricot_scan_win32"] do
+  Dir.chdir("#{WIN32_PKG_DIR}") do
+    Gem::Builder.new(Win32Spec).build
+    verbose(true) {
+      mv Dir["*.gem"].first, "../pkg/"
+    }
+  end
+end
+
+CLEAN.include WIN32_PKG_DIR
+
+### JRuby Packages ###
+
+def java_classpath_arg # myriad of ways to discover JRuby classpath
+  begin
+    cpath  = Java::java.lang.System.getProperty('java.class.path').split(File::PATH_SEPARATOR)
+    cpath += Java::java.lang.System.getProperty('sun.boot.class.path').split(File::PATH_SEPARATOR)
+    jruby_cpath = cpath.compact.join(File::PATH_SEPARATOR)
+  rescue => e
+  end
+  unless jruby_cpath
+    jruby_cpath = ENV['JRUBY_PARENT_CLASSPATH'] || ENV['JRUBY_HOME'] &&
+      FileList["#{ENV['JRUBY_HOME']}/lib/*.jar"].join(File::PATH_SEPARATOR)
+  end
+  jruby_cpath ? "-cp \"#{jruby_cpath}\"" : ""
+end
+
+def compile_java(filenames, jarname)
+  sh %{javac -source 1.5 -target 1.5 #{java_classpath_arg} #{filenames.join(" ")}}
+  sh %{jar cf #{jarname} *.class}
+end
+
+task :hpricot_scan_java => [:ragel_java] do
+  Dir.chdir "ext/hpricot_scan" do
+    compile_java(["HpricotScanService.java", "HpricotCss.java"], "hpricot_scan.jar")
+  end
+end
+
+task :fast_xs_java do
+  Dir.chdir "ext/fast_xs" do
+    compile_java(["FastXsService.java"], "fast_xs.jar")
+  end
+end
+
+desc "Compiles the JRuby extensions"
+task :compile_java => [:hpricot_scan_java, :fast_xs_java] do
+  %w(hpricot_scan fast_xs).each {|ext| mv "ext/#{ext}/#{ext}.jar", "lib"}
+end
+
+JRubySpec = SPEC.dup
+JRubySpec.platform = 'java'
+JRubySpec.files = PKG_FILES + ["lib/hpricot_scan.jar", "lib/fast_xs.jar"]
+JRubySpec.extensions = []
+
+JRUBY_PKG_DIR = "#{PKG}-java"
+
+desc "Package up the JRuby distribution."
+file JRUBY_PKG_DIR => [:ragel_java, :package] do
+  sh "tar zxf pkg/#{PKG}.tgz"
+  mv PKG, JRUBY_PKG_DIR
+end
+
+desc "Build the RubyGems package for JRuby"
+task :package_jruby => JRUBY_PKG_DIR do
+  Dir.chdir("#{JRUBY_PKG_DIR}") do
+    Rake::Task[:compile_java].invoke
+    Gem::Builder.new(JRubySpec).build
+    verbose(true) {
+      mv Dir["*.gem"].first, "../pkg/#{JRUBY_PKG_DIR}.gem"
+    }
+  end
+end
+
+CLEAN.include JRUBY_PKG_DIR
+
+task :install do
+  sh %{rake package}
+  sh %{sudo gem install pkg/#{NAME}-#{VERS}}
+end
+
+task :uninstall => [:clean] do
+  sh %{sudo gem uninstall #{NAME}}
+end