nokogiri 1.5.0.beta.4 → 1.5.0

data/CHANGELOG.ja.rdoc

@@ -1,3 +1,24 @@
+== 1.5.0 / 2011年7月1日
+
+* Notes
+
+  * See changelog from 1.4.7
+
+* Features
+
+  * extracted sets of Node::SaveOptions into Node::SaveOptions::DEFAULT_{X,H,XH}TML (refactor)
+
+* Bugfixes
+
+  * default output of XML on JRuby is no longer formatted due to
+    inconsistent whitespace handling. #415
+  * (JRuby) making empty NodeSets with null `nodes` member safe to operate on. #443
+  * Fix a bug in advanced encoding detection that leads to partially
+    duplicated document when parsing an HTML file with unknown
+    encoding.
+  * Add support for <meta charset="...">.
+
+
 == 1.5.0 beta3 ２０１０年１２月２日
 
 * 註
@@ -27,6 +48,19 @@
   * LibXML 2.6.16および古いバージョンは非推奨. インストールできない.
   * FFIサポートは削除された.
 
+=== 1.4.7 / 2011年7月1日
+
+* バグの修正
+
+  * エンコーディング宣言のないHTMLファイルで部分的に重複したドキュメントが生成される問題を修正した. #478
+
+=== 1.4.6 / 2011年6月19日
+
+* ノート
+
+  * このバージョンは、1.4.5と機能的に同じです
+  * Rubyの1.8.6のサポートが復元されている
+
 === 1.4.5 / 未リリース
 
 * 新機能

data/CHANGELOG.rdoc

@@ -1,3 +1,23 @@
+== 1.5.0 / 2011-07-01
+
+* Notes
+
+  * See changelog from 1.4.7
+
+* Features
+
+  * extracted sets of Node::SaveOptions into Node::SaveOptions::DEFAULT_{X,H,XH}TML (refactor)
+
+* Bugfixes
+
+  * default output of XML on JRuby is no longer formatted due to
+    inconsistent whitespace handling. #415
+  * (JRuby) making empty NodeSets with null `nodes` member safe to operate on. #443
+  * Fix a bug in advanced encoding detection that leads to partially
+    duplicated document when parsing an HTML file with unknown
+    encoding.
+  * Add support for <meta charset="...">.
+
 == 1.5.0 beta3 / 2010/12/02
 
 * Notes
@@ -27,11 +47,28 @@
   * LibXML 2.6.16 and earlier are deprecated. Nokogiri will refuse to install.
   * FFI support is removed.
 
-=== 1.4.5 / unrelease
+=== 1.4.7 / 2011-07-01
+
+* Bugfixes
+
+  * Fix a bug in advanced encoding detection that leads to partially
+    duplicated document when parsing an HTML file with unknown
+    encoding. Thanks, Timothy Elliott (@ender672)! #478
+
+=== 1.4.6 / 2011-06-19
+
+* Notes
+
+  * This version is functionally identical to 1.4.5.
+  * Ruby 1.8.6 support has been restored.
+
+=== 1.4.5 / 2011-05-19
 
 * New Features
 
   * Nokogiri::HTML::Document#title accessor gets and sets the document title.
+  * extracted sets of Node::SaveOptions into Node::SaveOptions::DEFAULT_{X,H,XH}TML (refactor)
+  * Raise an exception if a string is passed to Nokogiri::XML::Schema#validate. #406
 
 * Bugfixes
 
@@ -44,6 +81,8 @@
   * HTML::SAX::Parser should call back a block given to parse*() if any, just as XML::SAX::Parser does.
   * Add further encoding detection to HTML parser that libxml2 does not do.
   * Document#remove_namespaces! now handles attributes with namespaces. #396
+  * XSLT::Stylesheet#transform no longer segfaults when handed a non-XML::Document. #452
+  * XML::Reader no longer segfaults when under GC pressure. #439
 
 === 1.4.4 / 2010-11-15
 

data/Manifest.txt

@@ -1,4 +1,5 @@
 .autotest
+.gemtest
 CHANGELOG.ja.rdoc
 CHANGELOG.rdoc
 Manifest.txt
@@ -6,7 +7,6 @@ README.ja.rdoc
 README.rdoc
 Rakefile
 bin/nokogiri
-deps.rip
 ext/java/nokogiri/EncodingHandler.java
 ext/java/nokogiri/HtmlDocument.java
 ext/java/nokogiri/HtmlElementDescription.java
@@ -50,10 +50,12 @@ ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java
 ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java
 ext/java/nokogiri/internals/NokogiriXPathFunction.java
 ext/java/nokogiri/internals/NokogiriXPathFunctionResolver.java
+ext/java/nokogiri/internals/NokogiriXPathVariableResolver.java
+ext/java/nokogiri/internals/NokogiriXsltErrorListener.java
 ext/java/nokogiri/internals/ParserContext.java
 ext/java/nokogiri/internals/PushInputStream.java
 ext/java/nokogiri/internals/ReaderNode.java
-ext/java/nokogiri/internals/SaveContext.java
+ext/java/nokogiri/internals/SaveContextVisitor.java
 ext/java/nokogiri/internals/SchemaErrorHandler.java
 ext/java/nokogiri/internals/XmlDeclHandler.java
 ext/java/nokogiri/internals/XmlDomParser.java
@@ -193,7 +195,9 @@ lib/nokogiri/xslt.rb
 lib/nokogiri/xslt/stylesheet.rb
 lib/xercesImpl.jar
 lib/xsd/xmlparser/nokogiri.rb
+nokogiri_help_responses.md
 tasks/cross_compile.rb
+tasks/nokogiri.org.rb
 tasks/test.rb
 test/css/test_nthiness.rb
 test/css/test_parser.rb
@@ -205,9 +209,13 @@ test/files/address_book.rlx
 test/files/address_book.xml
 test/files/bar/bar.xsd
 test/files/dont_hurt_em_why.xml
+test/files/encoding.html
+test/files/encoding.xhtml
 test/files/exslt.xml
 test/files/exslt.xslt
 test/files/foo/foo.xsd
+test/files/metacharset.html
+test/files/noencoding.html
 test/files/po.xml
 test/files/po.xsd
 test/files/shift_jis.html
@@ -272,3 +280,4 @@ test/xml/test_text.rb
 test/xml/test_unparented_node.rb
 test/xml/test_xpath.rb
 test/xslt/test_custom_functions.rb
+test/xslt/test_exception_handling.rb

data/README.rdoc

@@ -120,7 +120,7 @@ installed.
 
 Then install hoe and rake-compiler:
 
-    $ gem install hoe rake-compiler
+    $ gem install hoe rake-compiler racc rexical minitest
 
 Then run rake:
 

data/Rakefile

@@ -1,129 +1,117 @@
 # -*- ruby -*-
-
 require 'rubygems'
-gem 'hoe', '>= 2.1.0'
-require 'hoe'
 
-windows = RUBY_PLATFORM =~ /(mswin|mingw)/i
-java    = RUBY_PLATFORM =~ /java/
+gem 'hoe'
+require 'hoe'
+Hoe.plugin :debugging
+Hoe.plugin :git
+Hoe.plugin :gemspec
+Hoe.plugin :bundler
+Hoe.add_include_dirs '.' # for ruby 1.9.2
 
 GENERATED_PARSER    = "lib/nokogiri/css/parser.rb"
 GENERATED_TOKENIZER = "lib/nokogiri/css/tokenizer.rb"
-CROSS_DIR           = File.join(File.dirname(__FILE__), 'tmp', 'cross')
+CROSS_DIR           =  File.join(File.dirname(__FILE__), 'ports')
 
-EXTERNAL_JAVA_LIBRARIES = %w{isorelax jing nekohtml nekodtd xercesImpl}.map{|x| "lib/#{x}.jar"}
-JRUBY_HOME = Config::CONFIG['prefix']
-LIB_DIR = File.expand_path('lib')
-CLASSPATH = "#{JRUBY_HOME}/lib/jruby.jar:#{LIB_DIR}/nekohtml.jar:#{LIB_DIR}/nekodtd.jar:#{LIB_DIR}/xercesImpl.jar:#{LIB_DIR}/isorelax.jar:#{LIB_DIR}/jing.jar"
-
-# Make sure hoe-debugging is installed
-Hoe.plugin :debugging
-Hoe.plugin :git
+def java?
+  !! (RUBY_PLATFORM =~ /java/)
+end
 
+require 'tasks/nokogiri.org'
 
 HOE = Hoe.spec 'nokogiri' do
-  developer('Aaron Patterson', 'aaronp@rubyforge.org')
-  developer('Mike Dalessio', 'mike.dalessio@gmail.com')
-  self.readme_file   = ['README', ENV['HLANG'], 'rdoc'].compact.join('.')
-  self.history_file  = ['CHANGELOG', ENV['HLANG'], 'rdoc'].compact.join('.')
-  self.extra_rdoc_files  = FileList['*.rdoc','ext/nokogiri/*.c']
-  self.clean_globs = [
+  developer 'Aaron Patterson', 'aaronp@rubyforge.org'
+  developer 'Mike Dalessio',   'mike.dalessio@gmail.com'
+  developer 'Yoko Harada',     'yokolet@gmail.com'
+
+  self.readme_file  = ['README',    ENV['HLANG'], 'rdoc'].compact.join('.')
+  self.history_file = ['CHANGELOG', ENV['HLANG'], 'rdoc'].compact.join('.')
+
+  self.extra_rdoc_files = FileList['*.rdoc','ext/nokogiri/*.c']
+
+  self.clean_globs += [
+    'nokogiri.gemspec',
     'lib/nokogiri/*.{o,so,bundle,a,log,dll}',
+    'lib/nokogiri/nokogiri.{so,dylib,rb,bundle}',
     'lib/nokogiri/nokogiri.rb',
     'lib/nokogiri/1.{8,9}',
     GENERATED_PARSER,
-    GENERATED_TOKENIZER,
-    'cross',
+    GENERATED_TOKENIZER
   ]
 
-  %w{ racc rexical rake-compiler }.each do |dep|
-    extra_dev_deps << [dep, '>= 0']
-  end
-  extra_dev_deps << ["minitest", ">= 1.6.0"]
+  self.extra_dev_deps += [
+    ["racc",            ">= 1.4.6"],
+    ["rexical",         ">= 1.0.5"],
+    ["rake-compiler",   ">= 0.7.9"],
+    ["minitest",        "~> 2.2.2"],
+    ["mini_portile",    ">= 0.2.2"],
+    ["hoe-debugging",   ">= 0"],
+    ["hoe-git",         ">= 0"],
+    ["hoe-gemspec",     ">= 0"],
+    ["hoe-bundler",     ">= 0"]
+  ]
 
-  if java
+  if java?
     self.spec_extras = { :platform => 'java' }
   else
-    self.spec_extras = { :extensions => ["ext/nokogiri/extconf.rb"] }
+    self.spec_extras = {
+      :extensions => ["ext/nokogiri/extconf.rb"],
+      :required_ruby_version => '>= 1.8.7'
+    }
   end
 
   self.testlib = :minitest
 end
 
-Hoe.add_include_dirs '.'
-
-task :ws_docs do
-  title = "#{HOE.name}-#{HOE.version} Documentation"
-
-  options = []
-  options << "--main=#{HOE.readme_file}"
-  options << '--format=activerecord'
-  options << '--threads=1'
-  options << "--title=#{title.inspect}"
-
-  options += HOE.spec.require_paths
-  options += HOE.spec.extra_rdoc_files
-  require 'rdoc/rdoc'
-  ENV['RAILS_ROOT'] ||= File.expand_path(File.join('..', 'nokogiri_ws'))
-  RDoc::RDoc.new.document options
-end
-
+# ----------------------------------------
 
-gem 'rake-compiler', '>= 0.4.1'
-if java
+if java?
+  # TODO: clean this section up.
   require "rake/javaextensiontask"
   Rake::JavaExtensionTask.new("nokogiri", HOE.spec) do |ext|
+    jruby_home = RbConfig::CONFIG['prefix']
     ext.ext_dir = 'ext/java'
-    ext.classpath = CLASSPATH
+    ext.lib_dir = 'lib/nokogiri'
+    jars = ["#{jruby_home}/lib/jruby.jar"] + FileList['lib/*.jar']
+    ext.classpath = jars.map { |x| File.expand_path x }.join ':'
   end
-  path = "pkg/#{HOE.spec.name}-#{HOE.spec.version}"
-  task path => :compile do
-    cp 'lib/nokogiri/nokogiri.jar', File.join(path, 'lib')
+
+  gem_build_path = File.join 'pkg', HOE.spec.full_name
+
+  task gem_build_path => [:compile] do
+    cp 'lib/nokogiri/nokogiri.jar', File.join(gem_build_path, 'lib', 'nokogiri')
     HOE.spec.files += ['lib/nokogiri/nokogiri.jar']
   end
 else
+  require 'tasks/cross_compile'
   require "rake/extensiontask"
+
+  HOE.spec.files.reject! { |f| f =~ %r{^ext/java|\.jar$} }
+
   Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
     ext.lib_dir = File.join(*['lib', 'nokogiri', ENV['FAT_DIR']].compact)
-
     ext.config_options << ENV['EXTOPTS']
-    ext.cross_compile   = true
-    ext.cross_platform  = 'i386-mingw32'
-    # ext.cross_platform  = 'i386-mswin32'
-    ext.cross_config_options <<
-    "--with-xml2-include=#{File.join(CROSS_DIR, 'include', 'libxml2')}"
-    ext.cross_config_options <<
-    "--with-xml2-lib=#{File.join(CROSS_DIR, 'lib')}"
-    ext.cross_config_options << "--with-iconv-dir=#{CROSS_DIR}"
-    ext.cross_config_options << "--with-xslt-dir=#{CROSS_DIR}"
+    ext.cross_compile  = true
+    ext.cross_platform = ["x86-mswin32-60", "x86-mingw32"]
+    ext.cross_config_options << "--with-xml2-include=#{File.join($recipes[:libxml2].path, 'include', 'libxml2')}"
+    ext.cross_config_options << "--with-xml2-lib=#{File.join($recipes[:libxml2].path, 'lib')}"
+    ext.cross_config_options << "--with-iconv-dir=#{$recipes[:libiconv].path}"
+    ext.cross_config_options << "--with-xslt-dir=#{$recipes[:libxslt].path}"
     ext.cross_config_options << "--with-zlib-dir=#{CROSS_DIR}"
   end
 end
 
-namespace :java do
-  task :spec do
-    File.open("#{HOE.name}.gemspec", 'w') do |f|
-      f.write(HOE.spec.to_ruby)
-    end
-  end
-end
+puts HOE.spec.files
 
-namespace :gem do
-  namespace :dev do
-    task :spec => [ GENERATED_PARSER, GENERATED_TOKENIZER ] do
-      File.open("#{HOE.name}.gemspec", 'w') do |f|
-        HOE.spec.version = "#{HOE.version}.#{Time.now.strftime("%Y%m%d%H%M%S")}"
-        f.write(HOE.spec.to_ruby)
-      end
-    end
-  end
+# ----------------------------------------
 
-  task :spec => ['gem:dev:spec']
-end
+desc "Generate css/parser.rb and css/tokenizer.rex"
+task 'generate' => [GENERATED_PARSER, GENERATED_TOKENIZER]
+task 'gem:spec' => 'generate' if Rake::Task.task_defined?("gem:spec")
 
 file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
-  racc = Config::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
-  racc = "#{::Config::CONFIG['bindir']}/racc" if racc.empty?
+  racc = RbConfig::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
+  racc = "#{::RbConfig::CONFIG['bindir']}/racc" if racc.empty?
   sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
 end
 
@@ -131,13 +119,13 @@ file GENERATED_TOKENIZER => "lib/nokogiri/css/tokenizer.rex" do |t|
   sh "rex --independent -o #{t.name} #{t.prerequisites.first}"
 end
 
-require 'tasks/test'
-begin
-  require 'tasks/cross_compile' unless java
-rescue RuntimeError => e
-  warn "WARNING: Could not perform some cross-compiling: #{e}"
+[:compile, :check_manifest].each do |task_name|
+  Rake::Task[task_name].prerequisites << GENERATED_PARSER
+  Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
 end
 
+# ----------------------------------------
+
 desc "set environment variables to build and/or test with debug options"
 task :debug do
   ENV['NOKOGIRI_DEBUG'] = "true"
@@ -145,29 +133,37 @@ task :debug do
   ENV['CFLAGS'] += " -DDEBUG"
 end
 
-# required_ruby_version
+require 'tasks/test'
 
-# Only do this on unix, since we can't build on windows
-unless windows
-  [:compile, :check_manifest].each do |task_name|
-    Rake::Task[task_name].prerequisites << GENERATED_PARSER
-    Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
-    if java
-      Rake::Task[task_name].prerequisites.concat EXTERNAL_JAVA_LIBRARIES
-    end
+Rake::Task[:test].prerequisites << :compile
+Rake::Task[:test].prerequisites << :check_extra_deps unless java?
+if Hoe.plugins.include?(:debugging)
+  ['valgrind', 'valgrind:mem', 'valgrind:mem0'].each do |task_name|
+    Rake::Task["test:#{task_name}"].prerequisites << :compile
   end
+end
 
-  Rake::Task[:test].prerequisites << :compile
-  Rake::Task[:test].prerequisites << :check_extra_deps unless java
-  if Hoe.plugins.include?(:debugging)
-    ['valgrind', 'valgrind:mem', 'valgrind:mem0'].each do |task_name|
-      Rake::Task["test:#{task_name}"].prerequisites << :compile
+# ----------------------------------------
+
+desc "build a windows gem without all the ceremony."
+task "gem:windows" do
+  rake_compiler_config = YAML.load_file("#{ENV['HOME']}/.rake-compiler/config.yml")
+
+  # check that rake-compiler config contains the right patchlevels of 1.8.6 and 1.9.1. see #279.
+  ["1.8.6-p383", "1.9.1-p243"].each do |version|
+    majmin, patchlevel = version.split("-")
+    rbconfig = "rbconfig-#{majmin}"
+    unless rake_compiler_config.key?(rbconfig) && rake_compiler_config[rbconfig] =~ /-#{patchlevel}/
+      raise "rake-compiler '#{rbconfig}' not #{patchlevel}. try running 'env --unset=HOST rake-compiler cross-ruby VERSION=#{version}'"
     end
   end
-end
 
-namespace :rip do
-  task :install => [GENERATED_TOKENIZER, GENERATED_PARSER]
+  # verify that --export-all is in the 1.9.1 rbconfig. see #279,#374,#375.
+  rbconfig_191 = rake_compiler_config["rbconfig-1.9.1"]
+  raise "rbconfig #{rbconfig_191} needs --export-all in its DLDFLAGS value" if File.read(rbconfig_191).grep(/CONFIG\["DLDFLAGS"\].*--export-all/).empty?
+
+  pkg_config_path = [:libxslt, :libxml2].collect { |pkg| File.join($recipes[pkg].path, "lib/pkgconfig") }.join(":")
+  sh("env PKG_CONFIG_PATH=#{pkg_config_path} RUBY_CC_VERSION=1.8.6:1.9.1 rake cross native gem") || raise("build failed!")
 end
 
 # vim: syntax=Ruby

data/bin/nokogiri

@@ -33,8 +33,7 @@ opts = OptionParser.new do |opts|
   end
 
   opts.on_tail("-v", "--version", "Show version") do
-    require 'yaml'
-    puts Nokogiri::VERSION_INFO.to_yaml
+    puts Nokogiri::VersionInfo.instance.to_markdown
     exit
   end
 end