RubyGems - nekohtml - Versions diffs - 0.0.3 - Mend

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (12) hide show

data/.document +5 -0
data/.gitignore +21 -0
data/LICENSE +20 -0
data/README.rdoc +39 -0
data/Rakefile +54 -0
data/VERSION +1 -0
data/lib/nekohtml.rb +35 -0
data/lib/nekohtml/html_document.rb +78 -0
data/test/helper.rb +5 -0
data/test/test_html_node.rb +31 -0
data/test/test_html_parser.rb +71 -0
metadata +97 -0

data/.document ADDED Viewed

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

data/.gitignore ADDED Viewed

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+## TEXTMATE
+*.tmproj
+tmtags
+## EMACS
+*~
+\#*
+.\#*
+## VIM
+*.swp
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+## PROJECT::SPECIFIC

data/LICENSE ADDED Viewed

@@ -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 ADDED Viewed

@@ -0,0 +1,39 @@
+= nekohtml
+A thin wrapper around NekoHTML as provided by Celerity.
+At the moment this gem depends on Celerity to provide the nekohtml jar.
+Once I can figure out how to make this optional, I'll provide it here if
+the celerity gem isn't here at install time.
+== Usage
+    jruby-1.4.0 > require 'nekohtml'
+     => true
+    jruby-1.4.0 > html= "<html><head><title>Title of Majesty</title></head></html>"
+     => "<html><head><title>Title of Majesty</title></head></html>"
+    jruby-1.4.0 > doc= Nekohtml.parse(html)
+     => #<Nekohtml::HtmlDocument:0x3f70119f ... >
+    jruby-1.4.0 > doc.search("//TITLE")
+     => #<Nekohtml::HtmlNodeList:0x1a7b5617 ... >
+    jruby-1.4.0 > _.first.text
+     => "Title of Majesty"
+Note that the xpath must use all-caps for tag names. This is a limitation
+of NekoHTML; I may plunder Celerity's source to see how they/HtmlUnit handle
+it but for now, that's what you've got.
+== Note on Patches/Pull Requests
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a
+  commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+== Copyright
+Copyright (c) 2010 Alex Young. See LICENSE for details.

data/Rakefile ADDED Viewed

@@ -0,0 +1,54 @@
+require 'rubygems'
+require 'rake'
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "nekohtml"
+    gem.summary = %Q{Thin wrapper around the NekoHTML parser}
+    gem.description = %Q{Almost the briefest possible wrapper around the NekoHTML parser to provide xpath functionality.}
+    gem.email = "alex@blackkettle.org"
+    gem.homepage = "http://github.com/regularfry/nekohtml"
+    gem.authors = ["Alex Young"]
+    gem.add_dependency "celerity", ">=0"
+    gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    gem.add_development_dependency "yard", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: 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 :test => :check_dependencies
+task :default => :test
+begin
+  require 'yard'
+  YARD::Rake::YardocTask.new
+rescue LoadError
+  task :yardoc do
+    abort "YARD is not available. In order to run yardoc, you must: sudo gem install yard"
+  end
+end

data/VERSION ADDED Viewed

	@@ -0,0 +1 @@
1	+ 0.0.3

data/lib/nekohtml.rb ADDED Viewed

@@ -0,0 +1,35 @@
+require 'celerity'
+require 'nekohtml/html_document'
+module Nekohtml
+  class << self
+    def parser()
+      configuration = org.cyberneko.html.HTMLConfiguration.new
+      jparser = org.apache.xerces.parsers.DOMParser.new(configuration)
+      jparser.setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
+      jparser.setFeature("http://xml.org/sax/features/namespaces", false)
+      return jparser
+    end
+    # Parse the string. case_sensitive controls whether you can use lower-case xpath
+    # elements for tag names or not. case_sensitive=true uses the default NekoHTML
+    # parser, which forces everything to be upper case per HTML 4.01. This is a pain.
+    def parse(string)
+      if string
+        jparser = parser()
+        jinput_reader = java.io.StringReader.new(string.to_java_string)
+        jinput_source = org.xml.sax.InputSource.new(jinput_reader)
+        jparser.parse(jinput_source)
+        jdocument = jparser.get_document()
+        # We know that the document has successfully been parsed
+        # at this point.
+        return HtmlDocument.new(jdocument)
+      else
+        raise ArgumentError.new
+      end
+    end
+  end
+end

data/lib/nekohtml/html_document.rb ADDED Viewed

@@ -0,0 +1,78 @@
+module Nekohtml
+  class HtmlThing
+    attr_accessor :java_object
+    def initialize(java_object)
+      @java_object = java_object
+      @jxpath_factory =
+        javax.xml.xpath.XPathFactory.newInstance()
+    end
+    def do_search(xpath, settings)
+      jxpath_object = @jxpath_factory.newXPath()
+      jmaybe_node_list = begin
+                           jxpath_object.evaluate(
+                             xpath,
+                             @java_object,
+                             settings
+                           )
+                         rescue
+                           nil
+                         end
+      return jmaybe_node_list
+    end
+    def search(xpath)
+      @jxpath_settings = javax.xml.xpath.XPathConstants::NODESET
+      jnode_list = self.do_search(xpath, @jxpath_settings)
+      result = jnode_list ? HtmlNodeList.new(jnode_list) : nil
+    end
+    def at(xpath)
+      @jxpath_settings = javax.xml.xpath.XPathConstants::NODE
+      jnode = self.do_search(xpath, @jxpath_settings)
+      result = jnode ? HtmlNode.new(jnode) : nil
+    end
+  end
+  class HtmlDocument < HtmlThing; end
+  class HtmlNodeList < HtmlThing
+    # @java_object is a NodeList in this case
+    include Enumerable
+    def initialize(*args)
+      super
+      # Just an alias
+      @jnode_list = @java_object
+    end
+    def length
+      @jnode_list.getLength()
+    end
+    def each
+      @jnode_list.getLength().times do |i|
+        yield HtmlNode.new(@jnode_list.item(i))
+      end
+    end
+  end
+  class HtmlNode < HtmlThing
+    def initialize(java_object)
+      super
+      @jelement = @java_object
+    end
+    def text
+      @jelement.text_content
+    end
+    def value
+      return self.text
+    end
+  end
+end

data/test/helper.rb ADDED Viewed

@@ -0,0 +1,5 @@
+require 'rubygems'
+require 'test/unit'
+require 'mocha'
+gem 'celerity'
+$:.push 'lib'

data/test/test_html_node.rb ADDED Viewed

@@ -0,0 +1,31 @@
+require File.expand_path(File.join(File.dirname(__FILE__), 'helper'))
+require 'nekohtml/html_document'
+class TestHtmlNode < Test::Unit::TestCase
+  include Nekohtml
+  def setup
+    @java_node = stub("(java_node)")
+    @node = HtmlNode.new(@java_node)
+  end
+  def test_search
+    xpath = "//example/xpath"
+    @node.expects(:do_search).with(xpath,
+                                  javax.xml.xpath.XPathConstants::NODESET)
+    @node.search(xpath)
+  end
+  def test_text
+    @java_node.expects(:text_content).returns("")
+    @node.text
+  end
+  def test_value
+    @java_node.expects(:text_content).returns(nil)
+    @node.value
+  end
+end

data/test/test_html_parser.rb ADDED Viewed

@@ -0,0 +1,71 @@
+require 'test/helper'
+require 'nekohtml'
+class TestNekohtml < Test::Unit::TestCase
+  def test_nil_content_raises
+    assert_raises(ArgumentError) do
+      Nekohtml.parse(nil)
+    end
+  end
+  def test_parse_simple_content
+    content = "<html><head></head><body></body></html>"
+    assert_not_nil Nekohtml.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 = Nekohtml.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
+  def test_html_with_namespaces
+    content = <<-HTML
+      <?xml version="1.0" encoding="UTF-8"?>
+      <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+      <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+        <head></head>
+      </html>
+    HTML
+    root_node = Nekohtml.parse(content)
+    assert_not_nil root_node
+    xpath = "//head"
+    search_results = root_node.search(xpath)
+    assert_equal 1, search_results.length
+  end
+  def test_not_case_sensitive
+    content = "<html> <head><title>Foo</title></head> <body><h1>Heading</h1></body> </html>"
+    root_node = Nekohtml.parse(content)
+    xpath = "//h1"
+    search_result = root_node.at(xpath)
+    assert_not_nil search_result, "Nothing found with the xpath #{xpath}."
+    assert_equal "Heading", search_result.text
+  end
+end

metadata ADDED Viewed

@@ -0,0 +1,97 @@
+--- !ruby/object:Gem::Specification
+name: nekohtml
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+platform: ruby
+authors:
+  - Alex Young
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2010-02-15 00:00:00 +00:00
+default_executable:
+dependencies:
+  - !ruby/object:Gem::Dependency
+    name: celerity
+    type: :runtime
+    version_requirement:
+    version_requirements: !ruby/object:Gem::Requirement
+      requirements:
+        - - ">="
+          - !ruby/object:Gem::Version
+            version: "0"
+      version:
+  - !ruby/object:Gem::Dependency
+    name: thoughtbot-shoulda
+    type: :development
+    version_requirement:
+    version_requirements: !ruby/object:Gem::Requirement
+      requirements:
+        - - ">="
+          - !ruby/object:Gem::Version
+            version: "0"
+      version:
+  - !ruby/object:Gem::Dependency
+    name: yard
+    type: :development
+    version_requirement:
+    version_requirements: !ruby/object:Gem::Requirement
+      requirements:
+        - - ">="
+          - !ruby/object:Gem::Version
+            version: "0"
+      version:
+description: Almost the briefest possible wrapper around the NekoHTML parser to provide xpath functionality.
+email: alex@blackkettle.org
+executables: []
+extensions: []
+extra_rdoc_files:
+  - LICENSE
+  - README.rdoc
+files:
+  - .document
+  - .gitignore
+  - LICENSE
+  - README.rdoc
+  - Rakefile
+  - VERSION
+  - lib/nekohtml.rb
+  - lib/nekohtml/html_document.rb
+  - test/helper.rb
+  - test/test_html_node.rb
+  - test/test_html_parser.rb
+has_rdoc: true
+homepage: http://github.com/regularfry/nekohtml
+licenses: []
+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:
+rubygems_version: 1.3.5
+signing_key:
+specification_version: 3
+summary: Thin wrapper around the NekoHTML parser
+test_files:
+  - test/test_html_parser.rb
+  - test/test_html_node.rb
+  - test/helper.rb

nekohtml 0.0.3