regularfry-celerity_parser 0.1.1-java

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,5 @@
+*.sw?
+.DS_Store
+coverage
+rdoc
+pkg

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Alex Young
+
+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/README.rdoc

@@ -0,0 +1,57 @@
+celerity_parser
+    by Alex Young 
+    http://github.com/regularfry/celerity_parser
+
+== DESCRIPTION:
+
+A very thin wrapper around HtmlUnit's HTML parser to allow xpath searches of
+HTML documents for JRuby. At the moment there's not much here. I don't know yet
+whether it's worth expanding the API to a full nokogiri/hpricot-style
+implementation.  What's here works for what I need for now.
+
+== FEATURES/PROBLEMS:
+
+* Reuses HtmlUnit's parser as wrapped by celerity to provide a stable HTML
+* parsing capability.
+
+== SYNOPSIS:
+
+Basic use:
+
+    root_node = CelerityParser.parse(html_content)
+    found_elements = root_node.search("//html/head/title")
+    found_elements.first.text # => "Html page title"
+
+
+== REQUIREMENTS:
+
+    $ jruby -S gem install jarib-celerity --source=http://gems.github.com
+
+== INSTALL:
+
+    $ jruby -S gem install celerity_parser --source=http://gems.github.com
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2009 Alex Young
+
+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/Rakefile

@@ -0,0 +1,60 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "celerity_parser"
+    gem.summary = %Q{Thin wrapper around a native Java HTML parser}
+    gem.email = "alex@blackkettle.org"
+    gem.homepage = "http://github.com/regularfry/celerity_parser"
+    gem.authors = ["Alex Young"]
+    gem.rubyforge_project = "celerity_parser"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+    gem.add_dependency 'jarib-celerity', '>= 0.0.6.10'
+    gem.platform = "java"
+  end
+
+  Jeweler::RubyforgeTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/*_test.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "celerity_parser #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+

data/VERSION

@@ -0,0 +1 @@
+0.1.1

data/celerity_parser.gemspec

@@ -0,0 +1,57 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{celerity_parser}
+  s.version = "0.1.1"
+  s.platform = %q{java}
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Alex Young"]
+  s.date = %q{2009-06-22}
+  s.email = %q{alex@blackkettle.org}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "celerity_parser.gemspec",
+     "lib/celerity_parser.rb",
+     "lib/celerity_parser/html_node.rb",
+     "lib/celerity_parser/html_parser.rb",
+     "test/helper.rb",
+     "test/test_celerity_parser.rb",
+     "test/test_html_node.rb",
+     "test/test_html_parser.rb"
+  ]
+  s.homepage = %q{http://github.com/regularfry/celerity_parser}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = %q{celerity_parser}
+  s.rubygems_version = %q{1.3.3}
+  s.summary = %q{Thin wrapper around a native Java HTML parser}
+  s.test_files = [
+    "test/helper.rb",
+     "test/test_html_node.rb",
+     "test/test_html_parser.rb",
+     "test/test_celerity_parser.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<jarib-celerity>, [">= 0.0.6.10"])
+    else
+      s.add_dependency(%q<jarib-celerity>, [">= 0.0.6.10"])
+    end
+  else
+    s.add_dependency(%q<jarib-celerity>, [">= 0.0.6.10"])
+  end
+end

data/lib/celerity_parser/html_node.rb

@@ -0,0 +1,47 @@
+module CelerityParser
+
+  class HtmlNode# {{{
+    
+    # This extra entry point will allow me to insert different Node
+    # classes in the future if necessary.
+    def self.wrap(java_node)
+      new(java_node) 
+    end
+
+    # Not called by user code.
+    def initialize(java_node)
+      @java_node = java_node
+    end
+
+    # Perform an xpath search from this node and return an array
+    # of HtmlNodes representing the results.
+    def search(xpath)
+      wrap_java_nodes(@java_node.get_by_xpath(xpath))
+    end
+
+    # The innerText of the node.
+    def text
+      @java_node.as_text
+    end
+
+    # HtmlNodes represent both tags and attributes, but attributes
+    # have value rather than text.
+    def value
+      @java_node.value
+    end
+
+    # The XHTML representation of this node.
+    def html
+      @java_node.as_xml
+    end
+
+    def wrap_java_nodes(java_results)
+      java_results.map do |java_node|
+        HtmlNode.wrap(java_node)
+      end
+    end
+    private :wrap_java_nodes
+
+  end # }}}
+
+end

data/lib/celerity_parser/html_parser.rb

@@ -0,0 +1,24 @@
+require 'celerity_parser/html_node'
+
+require 'celerity'
+
+module CelerityParser
+  class HtmlParser# {{{
+    def self.get_window(title)
+      client = Java.com.gargoylesoftware.htmlunit.WebClient.new()
+      return Java.com.gargoylesoftware.htmlunit.TopLevelWindow.new(title, client)
+    end
+
+    def self.get_wrapped_content(content, href=nil)
+      url = java.net.URL.new(href || "http://example.com")
+      return Java.com.gargoylesoftware.htmlunit.StringWebResponse.new(content, url)
+    end
+
+    def self.parse(content, href=nil)
+      raise ArgumentError.new("Nil content!") if !content
+      window = self.get_window("window")
+      wrapped_content = self.get_wrapped_content(content, href)
+      return HtmlNode.wrap(Java.com.gargoylesoftware.htmlunit.html.HTMLParser.parse(wrapped_content, window))
+    end
+  end# }}}
+end

data/lib/celerity_parser.rb

@@ -0,0 +1,56 @@
+require 'celerity'
+
+module CelerityParser
+
+  # :stopdoc:
+  VERSION = '1.0.0'
+  LIBPATH = ::File.expand_path(::File.dirname(__FILE__)) + ::File::SEPARATOR
+  PATH = ::File.dirname(LIBPATH) + ::File::SEPARATOR
+  # :startdoc:
+
+  # Returns the version string for the library.
+  #
+  def self.version
+    VERSION
+  end
+
+  # Returns the library path for the module. If any arguments are given,
+  # they will be joined to the end of the libray path using
+  # <tt>File.join</tt>.
+  #
+  def self.libpath( *args )
+    args.empty? ? LIBPATH : ::File.join(LIBPATH, args.flatten)
+  end
+
+  # Returns the lpath for the module. If any arguments are given,
+  # they will be joined to the end of the path using
+  # <tt>File.join</tt>.
+  #
+  def self.path( *args )
+    args.empty? ? PATH : ::File.join(PATH, args.flatten)
+  end
+
+  # Utility method used to require all files ending in .rb that lie in the
+  # directory below this file that has the same name as the filename passed
+  # in. Optionally, a specific _directory_ name can be passed in such that
+  # the _filename_ does not have to be equivalent to the directory.
+  #
+  def self.require_all_libs_relative_to( fname, dir = nil )
+    dir ||= ::File.basename(fname, '.*')
+    search_me = ::File.expand_path(
+        ::File.join(::File.dirname(fname), dir, '**', '*.rb'))
+
+    Dir.glob(search_me).sort.each {|rb| require rb}
+  end
+
+  # The entry point. Pass the html string as content, with an optional
+  # href to use for resolving relative URLs.
+  def self.parse(content, href=nil)
+    return CelerityParser::HtmlParser.parse(content, href)
+  end
+
+end  # module CelerityParser
+
+CelerityParser.require_all_libs_relative_to(__FILE__)
+
+# EOF

data/test/helper.rb

@@ -0,0 +1,5 @@
+$LOAD_PATH.unshift(File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib')))
+require 'rubygems'
+require 'test/unit'
+require 'mocha'
+gem 'jarib-celerity'

data/test/test_html_node.rb

@@ -0,0 +1,39 @@
+require File.expand_path(File.join(File.dirname(__FILE__), 'helper'))
+require 'celerity_parser/html_node'
+
+class TestHtmlNode < Test::Unit::TestCase
+  include CelerityParser
+
+  def setup
+    @java_node = stub("(java_node)")
+    @node = HtmlNode.new(@java_node)
+  end
+    
+  def test_search
+    xpath = "//example/xpath"
+    @java_node.expects(:get_by_xpath).with(xpath).returns([])
+
+    @node.search(xpath)
+  end
+
+  def test_wrap
+    HtmlNode.any_instance.expects(:initialize).with(@java_node)
+    HtmlNode.wrap(@java_node)
+  end
+
+  def test_text
+    @java_node.expects(:as_text).returns("")
+    @node.text
+  end
+
+  def test_value
+    @java_node.expects(:value).returns(nil)
+    @node.value
+  end
+
+  def test_html
+    @java_node.expects(:as_xml).returns("")
+    @node.html
+  end
+
+end

data/test/test_html_parser.rb

@@ -0,0 +1,55 @@
+require File.expand_path(File.join(File.dirname(__FILE__), 'helper'))
+require 'celerity_parser/html_parser'
+
+class TestHtmlParser < Test::Unit::TestCase
+  include CelerityParser
+
+  def test_nil_content_raises
+    assert_raises(ArgumentError) do
+      HtmlParser.parse(nil)
+    end
+  end
+
+  def test_get_window
+    assert_not_nil HtmlParser.get_window("foo title")
+  end
+  
+  def test_get_wrapped_content
+    content = "<html></html>"
+    assert_not_nil HtmlParser.get_wrapped_content(content)
+  end
+
+  def test_parse_simple_content
+    content = "<html><head></head><body></body></html>"
+    assert_not_nil HtmlParser.parse(content)
+  end
+
+  ###
+  # This is something of an integration test
+  def test_parse_to_xpath
+    content = <<-HTML
+    <html>
+      <head>
+        <title>HTML Page Title</title>
+      </head>
+      <body>
+        <ul>
+          <li>Foo</li>
+          <li>Bar</li>
+        </ul>
+      </body>
+    </html>
+    HTML
+
+    root_node = HtmlParser.parse(content)
+    flunk "Bad root node" if root_node.nil?
+
+    xpath = "//li"
+
+    search_results = root_node.search(xpath)
+
+    assert_equal 2, search_results.length
+    assert_equal ["Foo", "Bar"], search_results.map{|r| r.text}
+  end
+
+end

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification 
+name: regularfry-celerity_parser
+version: !ruby/object:Gem::Version 
+  version: 0.1.1
+platform: java
+authors: 
+- Alex Young
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-06-22 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: jarib-celerity
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.6.10
+    version: 
+description: 
+email: alex@blackkettle.org
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- celerity_parser.gemspec
+- lib/celerity_parser.rb
+- lib/celerity_parser/html_node.rb
+- lib/celerity_parser/html_parser.rb
+- test/helper.rb
+- test/test_celerity_parser.rb
+- test/test_html_node.rb
+- test/test_html_parser.rb
+has_rdoc: false
+homepage: http://github.com/regularfry/celerity_parser
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: celerity_parser
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 3
+summary: Thin wrapper around a native Java HTML parser
+test_files: 
+- test/helper.rb
+- test/test_html_node.rb
+- test/test_html_parser.rb
+- test/test_celerity_parser.rb