jrexml 0.5

data/History.txt

@@ -0,0 +1,3 @@
+= 0.5
+
+* Birthday!

data/LICENSE.txt

@@ -0,0 +1,21 @@
+# (c) Copyright 2007 Nick Sieger <nicksieger@gmail.com>
+# 
+# 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/Manifest.txt

@@ -0,0 +1,11 @@
+History.txt
+Manifest.txt
+README.txt
+LICENSE.txt
+Rakefile
+lib/jrexml/java_pull_parser.rb
+lib/jrexml.rb
+lib/xpp3-1.1.4.jar
+lib/xpp3.LICENSE.txt
+spec/java_pull_parser_spec.rb
+spec/spec_helper.rb

data/README.txt

@@ -0,0 +1,20 @@
+JREXML is an add-on for JRuby that uses a Java pull parser library to speed up REXML.
+
+REXML is, unfortunately, painfully slow running under JRuby at the moment due to the slowness of regular expression parsing. JREXML shoves a small wrapper around XPP3/MXP1 (http://www.extreme.indiana.edu/xgws/xsoap/xpp/mxp1/) into the guts of REXML, disabling the regular expression parser and providing close to a 10x speedup.
+
+= Install
+
+Simply install the gem under JRuby:
+
+    jruby -S gem install jrexml
+
+And require 'jrexml' to speed up REXML.
+
+    gem 'jrexml'
+    require 'jrexml'
+
+= License
+
+This software is released under an MIT license.  For details, see the LICENSE.txt file included with the distribution.  The software is copyright (c) 2007 Nick Sieger <nicksieger@gmail.com>.
+
+This product includes software developed by the Indiana University Extreme! Lab (http://www.extreme.indiana.edu/).  See the license in the file lib/xpp3.LICENSE.txt for details.

data/Rakefile

@@ -0,0 +1,64 @@
+require 'spec/rake/spectask'
+
+MANIFEST = FileList["History.txt", "Manifest.txt", "README.txt", "LICENSE.txt", "Rakefile",
+  "lib/**/*.rb", "lib/xpp*", "spec/**/*.rb"]
+
+begin
+  require 'hoe'
+  hoe = Hoe.new("jrexml", "0.5") do |p|
+    p.rubyforge_name = "caldersphere"
+    p.url = "http://caldersphere.rubyforge.org/jrexml"
+    p.author = "Nick Sieger"
+    p.email = "nick@nicksieger.com"
+    p.summary = "JREXML speeds up REXML under JRuby by using a Java pull parser."
+    p.changes = p.paragraphs_of('History.txt', 0..1).join("\n\n")
+    p.description = p.paragraphs_of('README.txt', 0...1).join("\n\n")
+    p.extra_deps.reject!{|d| d.first == "hoe"}
+    p.test_globs = ["spec/**/*_spec.rb"]
+  end
+  hoe.spec.files = MANIFEST
+  hoe.spec.dependencies.delete_if { |dep| dep.name == "hoe" }
+rescue LoadError
+  puts "You really need Hoe installed to be able to package this gem"
+end
+
+# Hoe insists on setting task :default => :test
+# !@#$ no easy way to empty the default list of prerequisites
+Rake::Task['default'].send :instance_variable_set, "@prerequisites", FileList[]
+
+file "Manifest.txt" => :manifest
+task :manifest do
+  File.open("Manifest.txt", "w") {|f| MANIFEST.each {|n| f << "#{n}\n"} }
+end
+Rake::Task['manifest'].invoke # Always regen manifest, so Hoe has up-to-date list of files
+
+task :default => :spec
+
+Spec::Rake::SpecTask.new do |t|
+  t.libs << "lib"
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+task :benchmark do
+  $LOAD_PATH.unshift "lib"
+  require 'benchmark'
+  require 'rexml/document'
+
+  xml = File.open(File.dirname(__FILE__) + "/spec/atom_feed.xml") {|f| f.read }
+
+  Benchmark.bm(7) do |x|
+    x.report("REXML") do
+      10.times do
+        REXML::Document.new xml
+      end
+    end
+    if RUBY_PLATFORM =~ /java/
+      x.report("JREXML") do
+        require 'jrexml'
+        10.times do
+          REXML::Document.new xml
+        end
+      end
+    end
+  end
+end

data/lib/jrexml.rb

@@ -0,0 +1,13 @@
+require 'rexml/parsers/baseparser'
+require 'jrexml/java_pull_parser'
+
+class REXML::Parsers::BaseParser #:nodoc:
+  # Extend every REXML base parser with a version that uses a Java pull parser 
+  # library
+  def self.new(*args)
+    obj = allocate
+    obj.extend(JREXML::JavaPullParser)
+    obj.send :initialize, *args
+    obj
+  end
+end

data/lib/jrexml/java_pull_parser.rb

@@ -0,0 +1,171 @@
+module JREXML
+  begin
+    XmlPullParser = Java::org.xmlpull.v1.XmlPullParser
+  rescue
+    raise LoadError, "JREXML is only for JRuby" if RUBY_PLATFORM !~ /java/
+    XPP_VERSION = "1.1.4"
+    begin
+      require "xpp3-#{XPP_VERSION}.jar"
+      @triedxpp ||= 0
+      @triedxpp += 1
+      retry unless @triedxpp > 1
+    rescue LoadError
+      raise LoadError, "Unable to load XmlPullParser java class; " +
+        "you need to include xpp3-#{XPP_VERSION}.jar on the classpath"
+    end
+  end
+
+  START_DOCUMENT         = XmlPullParser::START_DOCUMENT
+  END_DOCUMENT           = XmlPullParser::END_DOCUMENT
+  START_TAG              = XmlPullParser::START_TAG
+  END_TAG                = XmlPullParser::END_TAG
+  TEXT                   = XmlPullParser::TEXT
+  CDSECT                 = XmlPullParser::CDSECT
+  COMMENT                = XmlPullParser::COMMENT
+  ENTITY_REF             = XmlPullParser::ENTITY_REF
+  IGNORABLE_WHITESPACE   = XmlPullParser::IGNORABLE_WHITESPACE
+  PROCESSING_INSTRUCTION = XmlPullParser::PROCESSING_INSTRUCTION
+  
+  ADJACENT_EVENTS = [TEXT, ENTITY_REF]
+
+  class XmlParsingError < StandardError; end
+
+  module JavaPullParser
+    def self.factory
+      @factory ||= proc do
+        fact = org.xmlpull.v1.XmlPullParserFactory.newInstance
+        fact.set_namespace_aware false
+        fact.set_validating false
+        fact
+      end.call     
+    end
+
+    def stream=(source)
+      @source = JavaPullParser.factory.newPullParser
+      @source.setInput java.io.ByteArrayInputStream.new(get_bytes(source)), nil
+    end
+
+    # Returns true if there are no more events
+    def empty?
+      event_stack.empty?
+    end
+
+    # Returns true if there are more events.  Synonymous with !empty?
+    def has_next?
+      !empty?
+    end
+
+    # Push an event back on the head of the stream.  This method
+    # has (theoretically) infinite depth.
+    def unshift(event)
+      @event_stack ||= []
+      @event_stack.unshift event
+    end
+
+    def peek(depth = 0)
+      raise "not implemented"
+    end
+
+    def pull
+      event = event_stack.shift
+      unless @first_event_seen
+        @first_event_seen = true
+        version = @source.getProperty("http://xmlpull.org/v1/doc/properties.html#xmldecl-version")
+        if version
+          standalone = @source.getProperty("http://xmlpull.org/v1/doc/properties.html#xmldecl-standalone")
+          encoding = @source.getInputEncoding
+          unshift event
+          return [:xmldecl, version, encoding, standalone] 
+        end
+      end
+      convert_event(event)
+    end
+
+    def all_events
+      events = []
+      while event = pull
+        events << event
+      end
+      events
+    end
+
+    private
+    def convert_event(event)
+      if ADJACENT_EVENTS.include?(event)
+        text = ""
+        loop do
+          case event
+          when TEXT
+            text << @source.text
+          when ENTITY_REF
+            text << "&#{@source.name};"
+          end
+          event = event_stack.shift
+          break unless event
+          if !ADJACENT_EVENTS.include?(event)
+            unshift event
+            return [:text, text]
+          end
+        end
+      end
+      convert_event_without_text_or_entityref(event)      
+    end
+
+    def convert_event_without_text_or_entityref(event)
+      case event
+      when START_DOCUMENT
+        [:start_document]
+      when END_DOCUMENT
+        @document_ended = true
+        [:end_document]
+      when START_TAG
+        attributes = {}
+        0.upto(@source.attribute_count - 1) do |i|
+          attributes[@source.getAttributeName(i)] = @source.getAttributeValue(i)
+        end
+        [:start_element, @source.name, attributes]
+      when END_TAG
+        [:end_element, @source.name]
+      when IGNORABLE_WHITESPACE
+        [:text, @source.text]
+      when CDSECT
+        [:cdata, @source.text]
+      when COMMENT
+        [:comment, @source.text]
+      when PROCESSING_INSTRUCTION
+        pi_info = @source.text.split(/ /, 2)
+        pi_info[1] = " #{pi_info[1]}" # REXML likes the space there
+        [:processing_instruction, *pi_info]
+      when nil
+        nil
+      else
+        [:unknown, debug_event(event)]
+      end
+    end
+
+    def event_stack
+      @event_stack ||= []
+      if @event_stack.empty? && !@document_ended
+        begin
+          @event_stack << @source.nextToken
+        rescue NativeException => e
+          raise XmlParsingError, e.message
+        end
+      end
+      @event_stack
+    end
+
+    def get_bytes(src)
+      string = if src.respond_to?(:read)
+        src.read
+      else
+        src.to_s
+      end
+      string.to_java_bytes
+    end
+
+    def debug_event(event)
+      "XmlPullParser::#{XmlPullParser::TYPES[event]}" if event
+    end
+  end
+end

data/lib/xpp3.LICENSE.txt

@@ -0,0 +1,47 @@
+# Indiana University Extreme! Lab Software License
+# 
+# Version 1.1.1
+# 
+# Copyright (c) 2002 Extreme! Lab, Indiana University. All rights reserved.
+# 
+# Redistribution and use in source and binary forms, with or without 
+# modification, are permitted provided that the following conditions 
+# are met:
+# 
+# 1. Redistributions of source code must retain the above copyright notice, 
+#    this list of conditions and the following disclaimer.
+# 
+# 2. Redistributions in binary form must reproduce the above copyright 
+#    notice, this list of conditions and the following disclaimer in 
+#    the documentation and/or other materials provided with the distribution.
+# 
+# 3. The end-user documentation included with the redistribution, if any, 
+#    must include the following acknowledgment:
+# 
+#   "This product includes software developed by the Indiana University 
+#   Extreme! Lab (http://www.extreme.indiana.edu/)."
+# 
+# Alternately, this acknowledgment may appear in the software itself, 
+# if and wherever such third-party acknowledgments normally appear.
+# 
+# 4. The names "Indiana Univeristy" and "Indiana Univeristy Extreme! Lab" 
+# must not be used to endorse or promote products derived from this 
+# software without prior written permission. For written permission, 
+# please contact http://www.extreme.indiana.edu/.
+# 
+# 5. Products derived from this software may not use "Indiana Univeristy" 
+# name nor may "Indiana Univeristy" appear in their name, without prior 
+# written permission of the Indiana University.
+# 
+# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESSED OR IMPLIED
+# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+# IN NO EVENT SHALL THE AUTHORS, COPYRIGHT HOLDERS OR ITS CONTRIBUTORS
+# BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+# BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+# ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#

data/spec/java_pull_parser_spec.rb

@@ -0,0 +1,99 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe JREXML::JavaPullParser do
+  def parse(source)
+    @parser = REXML::Parsers::BaseParser.new(source)
+    @parser.extend(JREXML::JavaPullParser)
+    @parser.stream = source
+    (class << @parser; self; end).send :define_method, "base_events" do
+      events = []
+      baseparser = REXML::Parsers::BaseParser.new(source)
+      loop do
+        event = baseparser.pull
+        events << event
+        break if event.first == :end_document
+      end
+      events
+    end
+    @parser
+  end
+
+  def verify_events
+    @parser.base_events.each do |evt|
+      @parser.pull.should == evt
+    end
+    @parser.should be_empty
+  end
+
+  def parse_and_verify(source)
+    parse source
+    verify_events
+  end
+
+  it "should parse a document consisting of a single empty element" do
+    parse_and_verify %q(<document/>)
+  end
+
+  it "should allow calling empty? or has_next? in between pulls" do
+    @parser = parse %q(<document/>)
+    @parser.pull.should == [:start_element, "document", {}]
+    @parser.should_not be_empty
+    @parser.pull.should == [:end_element, "document"]
+    @parser.has_next?.should == true
+    @parser.pull.should == [:end_document]
+    @parser.has_next?.should == false
+    @parser.should be_empty
+  end
+
+  it "should parse text between elements" do
+    parse_and_verify %q(<document>This is the body</document>)
+  end
+
+  it "should parse multiple texts" do
+    parse_and_verify <<-XML
+<document>
+  some text
+  <a-tag/>
+  some other text
+</document>
+XML
+  end
+
+  it "should parse attributes" do
+    parse_and_verify %q(<document attr1="value" attr2='value2'/>)
+  end
+
+  it "should handle namespaces in the same way as the base parser (which is to be ignorant of them)" do
+    parse_and_verify %q(<d:document xmlns:d="urn:example.com" d:attr="value"/>)
+  end
+
+  it "should handle the xml processing instruction" do
+    parse_and_verify <<-XML
+<?xml version="1.0" encoding="utf-8"?>
+<document/>
+XML
+  end
+
+  it "should handle CDATA" do
+    parse_and_verify %q(<document><![CDATA[some cdata]]></document>)
+  end
+
+  it "should handle comments" do
+    parse_and_verify %q(<document><!-- some comment --></document>)
+  end
+
+  it "should handle processing instructions" do
+    parse_and_verify %q(<?xml version="1.0"?>
+<?xml-stylesheet href="hello-page-html.xsl" type="text/xsl"?><document/>)
+  end
+
+  it "should handle simple entity refs" do
+    parse_and_verify %q(<document>text &lt; other &gt;&#x20;text</document>)
+  end
+
+  it "should handle a longer, more complex document (50+K atom feed)" do
+    File.open(File.dirname(__FILE__) + "/atom_feed.xml") do |f|
+      parse_and_verify f.read
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,8 @@
+$LOAD_PATH.unshift File.dirname(__FILE__) + '/../lib'
+require 'rexml/parsers/baseparser'
+require 'jrexml'
+
+Spec::Runner.configure do |config|
+  config.before :all do
+  end
+end

metadata

@@ -0,0 +1,61 @@
+--- !ruby/object:Gem::Specification 
+rubygems_version: 0.9.2
+specification_version: 1
+name: jrexml
+version: !ruby/object:Gem::Version 
+  version: "0.5"
+date: 2007-08-07 00:00:00 -07:00
+summary: JREXML speeds up REXML under JRuby by using a Java pull parser.
+require_paths: 
+- lib
+email: nick@nicksieger.com
+homepage: http://caldersphere.rubyforge.org/jrexml
+rubyforge_project: caldersphere
+description: JREXML is an add-on for JRuby that uses a Java pull parser library to speed up REXML.
+autorequire: 
+default_executable: 
+bindir: bin
+has_rdoc: true
+required_ruby_version: !ruby/object:Gem::Version::Requirement 
+  requirements: 
+  - - ">"
+    - !ruby/object:Gem::Version 
+      version: 0.0.0
+  version: 
+platform: ruby
+signing_key: 
+cert_chain: 
+post_install_message: 
+authors: 
+- Nick Sieger
+files: 
+- History.txt
+- Manifest.txt
+- README.txt
+- LICENSE.txt
+- Rakefile
+- lib/jrexml/java_pull_parser.rb
+- lib/jrexml.rb
+- lib/xpp3-1.1.4.jar
+- lib/xpp3.LICENSE.txt
+- spec/java_pull_parser_spec.rb
+- spec/spec_helper.rb
+test_files: 
+- spec/java_pull_parser_spec.rb
+rdoc_options: 
+- --main
+- README.txt
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- README.txt
+- LICENSE.txt
+- lib/xpp3.LICENSE.txt
+executables: []
+
+extensions: []
+
+requirements: []
+
+dependencies: []
+