nokogiri 1.5.0.beta.3 → 1.5.0.beta.4

data/CHANGELOG.ja.rdoc

@@ -1,31 +1,47 @@
-== 1.5.0 beta3 / 2010/12/02
+== 1.5.0 beta3 ２０１０年１２月２日
 
-* Notes
+* 註
 
-  * JRuby performance tuning
-  * See changelog from 1.4.4
+  * JRubyでの性能改善
+  * 1.4.4からの変更点を参照
 
-* Bugfixes
+* バグの修正
+
+  * Node#inner_textはnilを返さなくなった. (JRuby) #264
+
+== 1.5.0 beta2 ２０１０年７月３０日
+
+* 註
 
-  * Node#inner_text no longer returns nil. (JRuby) #264
+  * 1.4.3からの変更点を参照
 
-== 1.5.0 beta2 / 2010/07/30
+== 1.5.0 beta1 ２０１０年５月２２日
 
-* Notes
+* 註
 
-  * See changelog from 1.4.3
+  * 新しいピュアJavaバックエンドによりJRubyサポートを追加
 
-== 1.5.0 beta1 / 2010/05/22
+* 廃止
 
-* Notes
+  * Ruby 1.8.6は非推奨となった. インストールできるかもしれないが、正式なサポートは終了.
+  * 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.
 
-  * JRuby support is provided by a new pure-java backend.
+=== 1.4.5 / 未リリース
 
-* Deprecations
+* 新機能
+
+  * Nokogiri::HTML::Document#title アクセサメソッドでHTML文書のタイトルを読み書きできる
+
+* バグの修正
 
-  * Ruby 1.8.6 is deprecated. Nokogiri will install, but official support is ended.
-  * LibXML 2.6.16 and earlier are deprecated. Nokogiri will refuse to install.
-  * FFI support is removed.
+  * Node#serialize とその仲間達はSaveOptionオブジェクトを受け入れる
+  * Nokogiri::CSS::Parser has-a Nokogiri::CSS::Tokenizer
+  * [JRUBY+FFIのみ] 「弱い参照」はスレッドセーフになった. #355
+  * HTML::SAX::Parserから呼ばれるstart_element()コールバックのattributes引数はHTML::XML::Parserによるエミュレートコールバックと同じく連想配列になった.  rel. #356
+  * HTML::SAX::Parserのparse*()メソッドはXML::SAX::Parser同様に渡されたブロックをコールバックするようになった.
+  * HTMLパーサーのエンコーディング判定をlibxml2の仕様を超えて拡張・改善した. (XML宣言のencodingを認識、非ASCII文字出現後のmetaタグも文字化けを生じずに反映)
+  * Document#remove_namespaces! は名前空間付きの属性に対応した. #396
 
 === 1.4.4 ２０１０年１１月１５日
 

data/CHANGELOG.rdoc

@@ -27,6 +27,24 @@
   * LibXML 2.6.16 and earlier are deprecated. Nokogiri will refuse to install.
   * FFI support is removed.
 
+=== 1.4.5 / unrelease
+
+* New Features
+
+  * Nokogiri::HTML::Document#title accessor gets and sets the document title.
+
+* Bugfixes
+
+  * Node#serialize-and-friends now accepts a SaveOption object as the, erm, save object.
+  * Nokogiri::CSS::Parser has-a Nokogiri::CSS::Tokenizer
+  * [JRUBY+FFI only] Weak references are now threadsafe. #355
+  * Make direct start_element() callback (currently used for
+    HTML::SAX::Parser) pass attributes in assoc array, just as
+    emulated start_element() callback does.  rel. #356
+  * 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
+
 === 1.4.4 / 2010-11-15
 
 * New Features

data/Manifest.txt

@@ -134,11 +134,10 @@ lib/nekodtd.jar
 lib/nekohtml.jar
 lib/nokogiri.rb
 lib/nokogiri/css.rb
-lib/nokogiri/css/generated_parser.rb
-lib/nokogiri/css/generated_tokenizer.rb
 lib/nokogiri/css/node.rb
 lib/nokogiri/css/parser.rb
 lib/nokogiri/css/parser.y
+lib/nokogiri/css/parser_extras.rb
 lib/nokogiri/css/syntax_error.rb
 lib/nokogiri/css/tokenizer.rb
 lib/nokogiri/css/tokenizer.rex

data/README.rdoc

@@ -112,10 +112,34 @@ Binary packages are available for:
 
 == DEVELOPMENT:
 
-Developing Nokogiri requires racc and rexical.
+=== Developing on C Ruby (MRI)
 
-* rake install:deps
-* rake test
+Developing Nokogiri requires racc and rexical to generate the parser and
+tokenizer.  To start development, make sure you have `libxml2` and `libxslt`
+installed.
+
+Then install hoe and rake-compiler:
+
+    $ gem install hoe rake-compiler
+
+Then run rake:
+
+    $ rake
+
+=== Developing on JRuby
+
+Currently, development with JRuby depends on C Ruby being installed.  With
+normal C Ruby, install racc and rexical:
+
+    $ gem install racc rexical
+
+Make sure hoe and rake compiler are installed with JRuby:
+
+    $ jgem install hoe rake-compiler
+
+Then run rake:
+
+    $ jruby -S rake
 
 == LICENSE:
 

data/Rakefile

@@ -7,18 +7,20 @@ require 'hoe'
 windows = RUBY_PLATFORM =~ /(mswin|mingw)/i
 java    = RUBY_PLATFORM =~ /java/
 
-GENERATED_PARSER    = "lib/nokogiri/css/generated_parser.rb"
-GENERATED_TOKENIZER = "lib/nokogiri/css/generated_tokenizer.rb"
+GENERATED_PARSER    = "lib/nokogiri/css/parser.rb"
+GENERATED_TOKENIZER = "lib/nokogiri/css/tokenizer.rb"
 CROSS_DIR           = File.join(File.dirname(__FILE__), 'tmp', 'cross')
 
 EXTERNAL_JAVA_LIBRARIES = %w{isorelax jing nekohtml nekodtd xercesImpl}.map{|x| "lib/#{x}.jar"}
-JAVA_EXT = "lib/nokogiri/nokogiri.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
 
+
 HOE = Hoe.spec 'nokogiri' do
   developer('Aaron Patterson', 'aaronp@rubyforge.org')
   developer('Mike Dalessio', 'mike.dalessio@gmail.com')
@@ -35,14 +37,19 @@ HOE = Hoe.spec 'nokogiri' do
   ]
 
   %w{ racc rexical rake-compiler }.each do |dep|
-    self.extra_dev_deps << [dep, '>= 0']
+    extra_dev_deps << [dep, '>= 0']
   end
-  self.extra_dev_deps << ["minitest", ">= 1.6.0"]
+  extra_dev_deps << ["minitest", ">= 1.6.0"]
 
-  self.spec_extras = { :extensions => ["ext/nokogiri/extconf.rb"] }
+  if java
+    self.spec_extras = { :platform => 'java' }
+  else
+    self.spec_extras = { :extensions => ["ext/nokogiri/extconf.rb"] }
+  end
 
   self.testlib = :minitest
 end
+
 Hoe.add_include_dirs '.'
 
 task :ws_docs do
@@ -61,11 +68,22 @@ task :ws_docs do
   RDoc::RDoc.new.document options
 end
 
-unless java
-  gem 'rake-compiler', '>= 0.4.1'
-  require "rake/extensiontask"
 
-  RET = Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
+gem 'rake-compiler', '>= 0.4.1'
+if java
+  require "rake/javaextensiontask"
+  Rake::JavaExtensionTask.new("nokogiri", HOE.spec) do |ext|
+    ext.ext_dir = 'ext/java'
+    ext.classpath = CLASSPATH
+  end
+  path = "pkg/#{HOE.spec.name}-#{HOE.spec.version}"
+  task path => :compile do
+    cp 'lib/nokogiri/nokogiri.jar', File.join(path, 'lib')
+    HOE.spec.files += ['lib/nokogiri/nokogiri.jar']
+  end
+else
+  require "rake/extensiontask"
+  Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
     ext.lib_dir = File.join(*['lib', 'nokogiri', ENV['FAT_DIR']].compact)
 
     ext.config_options << ENV['EXTOPTS']
@@ -73,9 +91,9 @@ unless java
     ext.cross_platform  = 'i386-mingw32'
     # ext.cross_platform  = 'i386-mswin32'
     ext.cross_config_options <<
-      "--with-xml2-include=#{File.join(CROSS_DIR, 'include', 'libxml2')}"
+    "--with-xml2-include=#{File.join(CROSS_DIR, 'include', 'libxml2')}"
     ext.cross_config_options <<
-      "--with-xml2-lib=#{File.join(CROSS_DIR, 'lib')}"
+    "--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_config_options << "--with-zlib-dir=#{CROSS_DIR}"
@@ -83,49 +101,11 @@ unless java
 end
 
 namespace :java do
-  desc "Removes all generated during compilation .class files."
-  task :clean_classes do
-    (FileList['ext/java/nokogiri/internals/*.class'] + FileList['ext/java/nokogiri/*.class'] + FileList['ext/java/*.class']).to_a.each do |file|
-      File.delete file
-    end
-  end
-
-  desc "Removes the generated .jar"
-  task :clean_jar do
-    FileList['lib/nokogiri/*.jar'].each{|f| File.delete f }
-  end
-
-  desc  "Same as java:clean_classes and java:clean_jar"
-  task :clean_all => ["java:clean_classes", "java:clean_jar"]
-  
-  desc "Build a gem targetted for JRuby"
-  task :gem => ['java:spec', GENERATED_PARSER, GENERATED_TOKENIZER, :build] do
-    raise "ERROR: please run this task under jruby" unless java
-    system "gem build nokogiri.gemspec"
-    FileUtils.mkdir_p "pkg"
-    FileUtils.mv Dir.glob("nokogiri*-java.gem"), "pkg"
-  end
-
   task :spec do
     File.open("#{HOE.name}.gemspec", 'w') do |f|
-      HOE.spec.platform = 'java'
-      HOE.spec.files += [GENERATED_PARSER, GENERATED_TOKENIZER, JAVA_EXT] + EXTERNAL_JAVA_LIBRARIES
-      HOE.spec.extensions = []
       f.write(HOE.spec.to_ruby)
     end
   end
-
-  desc "Build external library"
-  task :build_external do
-    Dir.chdir('ext/java') do
-      LIB_DIR = '../../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"
-      sh "javac -g -cp #{CLASSPATH} nokogiri/*.java nokogiri/internals/*.java"
-      sh "jar cf ../../#{JAVA_EXT} nokogiri/*.class nokogiri/internals/*.class"
-    end
-  end
-
-  task :build => ["java:clean_jar", "java:build_external", "java:clean_classes"]
 end
 
 namespace :gem do
@@ -142,21 +122,13 @@ namespace :gem do
 end
 
 file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
-  begin
-    racc = Config::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
-    racc = "#{::Config::CONFIG['bindir']}/racc" if racc.empty?
-    sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
-  rescue
-    abort "need racc, sudo gem install racc"
-  end
+  racc = Config::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
+  racc = "#{::Config::CONFIG['bindir']}/racc" if racc.empty?
+  sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
 end
 
 file GENERATED_TOKENIZER => "lib/nokogiri/css/tokenizer.rex" do |t|
-  begin
-    sh "rex --independent -o #{t.name} #{t.prerequisites.first}"
-  rescue
-    abort "need rexical, sudo gem install rexical"
-  end
+  sh "rex --independent -o #{t.name} #{t.prerequisites.first}"
 end
 
 require 'tasks/test'
@@ -176,38 +148,22 @@ end
 # required_ruby_version
 
 # Only do this on unix, since we can't build on windows
-unless windows || java
+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
   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
-else
-  [:test, :check_manifest].each do |task_name|
-    if Rake::Task[task_name]
-      Rake::Task[task_name].prerequisites << GENERATED_PARSER
-      Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
-    end
-  end
-end
-
-namespace :install do
-  desc "Install rex and racc for development"
-  task :deps => %w(rexical racc)
-
-  task :racc do |t|
-    sh "sudo gem install racc"
-  end
-
-  task :rexical do
-    sh "sudo gem install rexical"
-  end
 end
 
 namespace :rip do

data/ext/java/nokogiri/EncodingHandler.java

@@ -1,7 +1,7 @@
 /**
  * (The MIT License)
  *
- * Copyright (c) 2008 - 2010:
+ * Copyright (c) 2008 - 2011:
  *
  * * {Aaron Patterson}[http://tenderlovemaking.com]
  * * {Mike Dalessio}[http://mike.daless.io]

data/ext/java/nokogiri/HtmlDocument.java

@@ -1,7 +1,7 @@
 /**
  * (The MIT License)
  *
- * Copyright (c) 2008 - 2010:
+ * Copyright (c) 2008 - 2011:
  *
  * * {Aaron Patterson}[http://tenderlovemaking.com]
  * * {Mike Dalessio}[http://mike.daless.io]
@@ -32,6 +32,7 @@
 
 package nokogiri;
 
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
 import nokogiri.internals.HtmlDomParserContext;
 import nokogiri.internals.SaveContext;
 
@@ -49,6 +50,8 @@ import org.w3c.dom.DocumentType;
 /**
  * Class for Nokogiri::HTML::Document.
  *
+ * @author sergio
+ * @author Yoko Harada <yokolet@gmail.com>
  */
 @JRubyClass(name="Nokogiri::HTML::Document", parent="Nokogiri::XML::Document")
 public class HtmlDocument extends XmlDocument {
@@ -62,20 +65,20 @@ public class HtmlDocument extends XmlDocument {
     }
 
     @JRubyMethod(name="new", meta = true, rest = true, required=0)
-    public static IRubyObject rbNew(ThreadContext context, IRubyObject cls,
+    public static IRubyObject rbNew(ThreadContext context, IRubyObject klazz,
                                     IRubyObject[] args) {
-        HtmlDocument doc = null;
+        HtmlDocument htmlDocument = null;
         try {
             Document docNode = createNewDocument();
-            doc = new HtmlDocument(context.getRuntime(), (RubyClass) cls, docNode);
+            htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass) klazz);
+            htmlDocument.setNode(context, docNode);
         } catch (Exception ex) {
-            throw context.getRuntime()
-                .newRuntimeError("couldn't create document: "+ex.toString());
+            throw context.getRuntime().newRuntimeError("couldn't create document: "+ex.toString());
         }
 
-        RuntimeHelpers.invoke(context, doc, "initialize", args);
+        RuntimeHelpers.invoke(context, htmlDocument, "initialize", args);
 
-        return doc;
+        return htmlDocument;
     }
 
     public static IRubyObject do_parse(ThreadContext context,
@@ -117,12 +120,6 @@ public class HtmlDocument extends XmlDocument {
         return do_parse(context, cls, args);
     }
 
-
-    @JRubyMethod
-    public static IRubyObject serialize(ThreadContext context, IRubyObject htmlDoc) {
-        throw context.getRuntime().newNotImplementedError("not implemented");
-    }
-
     @Override
     public void saveContent(ThreadContext context, SaveContext ctx) {
         Document doc = getDocument();

data/ext/java/nokogiri/HtmlElementDescription.java

@@ -1,7 +1,7 @@
 /**
  * (The MIT License)
  *
- * Copyright (c) 2008 - 2010:
+ * Copyright (c) 2008 - 2011:
  *
  * * {Aaron Patterson}[http://tenderlovemaking.com]
  * * {Mike Dalessio}[http://mike.daless.io]

data/ext/java/nokogiri/HtmlEntityLookup.java

@@ -1,7 +1,7 @@
 /**
  * (The MIT License)
  *
- * Copyright (c) 2008 - 2010:
+ * Copyright (c) 2008 - 2011:
  *
  * * {Aaron Patterson}[http://tenderlovemaking.com]
  * * {Mike Dalessio}[http://mike.daless.io]

data/ext/java/nokogiri/HtmlSaxParserContext.java

@@ -1,7 +1,7 @@
 /**
  * (The MIT License)
  *
- * Copyright (c) 2008 - 2010:
+ * Copyright (c) 2008 - 2011:
  *
  * * {Aaron Patterson}[http://tenderlovemaking.com]
  * * {Mike Dalessio}[http://mike.daless.io]
@@ -59,6 +59,9 @@ import org.xml.sax.SAXException;
 /**
  * Class for Nokogiri::HTML::SAX::ParserContext.
  *
+ * @author serabe
+ * @author Patrick Mahoney <pat@polycrystal.org>
+ * @author Yoko Harada <yokolet@gmail.com>
  */
 
 @JRubyClass(name="Nokogiri::HTML::SAX::ParserContext", parent="Nokogiri::XML::SAX::ParserContext")
@@ -67,7 +70,7 @@ public class HtmlSaxParserContext extends XmlSaxParserContext {
     public HtmlSaxParserContext(Ruby ruby, RubyClass rubyClass) {
         super(ruby, rubyClass);
     }
-
+    
     @Override
     protected AbstractSAXParser createParser() throws SAXException {
         SAXParser parser = new SAXParser();
@@ -89,8 +92,8 @@ public class HtmlSaxParserContext extends XmlSaxParserContext {
                                            IRubyObject klazz,
                                            IRubyObject data,
                                            IRubyObject encoding) {
-        HtmlSaxParserContext ctx =
-            new HtmlSaxParserContext(context.getRuntime(), (RubyClass) klazz);
+        HtmlSaxParserContext ctx = (HtmlSaxParserContext) NokogiriService.HTML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass)klazz);
+        ctx.initialize(context.getRuntime());
         String javaEncoding = findEncoding(context, encoding);
         if (javaEncoding != null) {
             String input = applyEncoding(rubyStringToString(data), javaEncoding);
@@ -195,8 +198,8 @@ public class HtmlSaxParserContext extends XmlSaxParserContext {
                                          IRubyObject klazz,
                                          IRubyObject data,
                                          IRubyObject encoding) {
-        HtmlSaxParserContext ctx =
-            new HtmlSaxParserContext(context.getRuntime(), (RubyClass) klazz);
+        HtmlSaxParserContext ctx = (HtmlSaxParserContext) NokogiriService.HTML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass)klazz);
+        ctx.initialize(context.getRuntime());
         ctx.setInputSourceFile(context, data);
         String javaEncoding = findEncoding(context, encoding);
         if (javaEncoding != null) {
@@ -210,8 +213,8 @@ public class HtmlSaxParserContext extends XmlSaxParserContext {
                                        IRubyObject klazz,
                                        IRubyObject data,
                                        IRubyObject encoding) {
-        HtmlSaxParserContext ctx =
-            new HtmlSaxParserContext(context.getRuntime(), (RubyClass) klazz);
+        HtmlSaxParserContext ctx = (HtmlSaxParserContext) NokogiriService.HTML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass)klazz);
+        ctx.initialize(context.getRuntime());
         ctx.setInputSource(context, data);
         String javaEncoding = findEncoding(context, encoding);
         if (javaEncoding != null) {
@@ -228,8 +231,8 @@ public class HtmlSaxParserContext extends XmlSaxParserContext {
     public static IRubyObject parse_stream(ThreadContext context,
                                            IRubyObject klazz,
                                            InputStream stream) {
-        HtmlSaxParserContext ctx =
-            new HtmlSaxParserContext(context.getRuntime(), (RubyClass)klazz);
+        HtmlSaxParserContext ctx = (HtmlSaxParserContext) NokogiriService.HTML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass)klazz);
+        ctx.initialize(context.getRuntime());
         ctx.setInputSource(stream);
         return ctx;
     }