nokogiri 1.3.3 → 1.4.0

data/CHANGELOG.ja.rdoc

@@ -1,3 +1,48 @@
+=== 1.4.0 ２００９年１０月３０日
+
+* 今日はノコギリの満一歳のお誕生日です
+
+* 新しい機能
+  * Node#at_xpath はXPathの表現に適したNodeSetの一番最初の要素に返す
+  * Node#at_css はCSSのセレクターに合うNodeSetの一番最初の要素に返す
+  * NodeSet#| は合併させる機能を果たす　GH #119 (Serabe ありがとう！)
+  * NodeSet#inspect inspectは出力をきれいにさせる
+  * Node#inspect インスペクト後、普通のrubyで出力施行する
+  * XML::DTD#external_id を追加
+  * XML::DTD#system_id を追加
+  * XML::ElementContent はDTD要素のコンテンツを有効化させる
+  * Nokogiri::XML::Builder内での名前空間宣言用のサポートを改良
+  * XML::Node#external_subsetを追加
+  * XML::Node#create_external_subsetを追加
+  * XML::Node#create_internal_subsetを追加
+  * XML Builderは生成されていないstringsを付加出来る様になった
+    (GH #141, patch from dudleyf)
+  * XML::SAX::ParserContext を追加
+  * XML::Document#remove_namespaces! は名前空間を使いこなせない人たち用の措置
+
+* バグの修正
+
+  * HTMLドキュメントが メタエンコーディングのタグを宣言しない時、
+    nilを返すようになった　GH #115
+  * ENV['PATH'] を調節する為に、RbConfig::CONFIG['host_os']を使用できるように
+    なった GH #113
+  * NodeSet#searchが更に効率的になった　GH #119 (Serabe!に感謝します)
+  * NodeSet#xpathがcustom xpath機能を取り扱える様になった
+  * XML::Reader が現時点のノード用に属性を取得する際に、
+    SEGVを修正するようになった
+  * Node#inner_html がNode#to_html と同じ独立変数を受け入れるようになった
+    GH #117
+  * DocumentFragment#css は子ノードへ委任をするようになった GH #123
+  * NodeSet#[]がNodeSet#lengthより大きいスライスでも機能できるようになった
+    GH #131
+  * 新たな親ノードの名前空間の維持出来るようになった　GH #134
+  * XML::Document をNodeSetに追加の際にSEGVが修正されるようになった
+  * XML::SyntaxError が重複可
+
+* 廃棄予定
+
+  * Hpricot用の互換性レイヤーを削除
+
 === 1.3.3 / ２００９年７月２６日
 
 * 新しい機能
@@ -8,12 +53,12 @@
 
   * libxml-ruby のグローバ ルエラー ハンドラー に優先するようになった
   * ParseOption#strict を修正
-  * 空のstringを Node#inner_html= に与えた時に生じたSEGVを修正 GH #88
-  * Ruby 1.9 で返したStringのエンコードはUTF-8になった
+  * 空文字列を Node#inner_html= に与えた時に生じたSEGVを修正 GH #88
+  * Ruby 1.9 では文字列のエンコーディングをUTF-8になるようにした
   * ドキュメントの根ノードから違うドキュメントの根ノードに移動した時に生じた
     SEGVを修正 GH #91
   * ノードをインスタンス化する時のO(n)のペナルティーを修正 GH #101
-  * XMLのドキュメントをHTMLのドキュメントととして出力出来るようになった
+  * XMLのドキュメントをHTMLのドキュメントとして出力出来るようになった
 
 * 廃棄予定
 

data/CHANGELOG.rdoc

@@ -1,3 +1,45 @@
+=== 1.4.0 / 2009/10/30
+
+* Happy Birthday!
+
+* New Features
+
+  * Node#at_xpath returns the first element of the NodeSet matching the XPath
+    expression.
+  * Node#at_css returns the first element of the NodeSet matching the CSS
+    selector.
+  * NodeSet#| for unions GH #119 (Thanks Serabe!)
+  * NodeSet#inspect makes prettier output
+  * Node#inspect implemented for more rubyish document inspecting
+  * Added XML::DTD#external_id
+  * Added XML::DTD#system_id
+  * Added XML::ElementContent for DTD Element content validity
+  * Better namespace declaration support in Nokogiri::XML::Builder
+  * Added XML::Node#external_subset
+  * Added XML::Node#create_external_subset
+  * Added XML::Node#create_internal_subset
+  * XML Builder can append raw strings (GH #141, patch from dudleyf)
+  * XML::SAX::ParserContext added
+  * XML::Document#remove_namespaces! for the namespace-impaired
+
+* Bugfixes
+
+  * returns nil when HTML documents do not declare a meta encoding tag. GH #115
+  * Uses RbConfig::CONFIG['host_os'] to adjust ENV['PATH'] GH #113
+  * NodeSet#search is more efficient GH #119 (Thanks Serabe!)
+  * NodeSet#xpath handles custom xpath functions
+  * Fixing a SEGV when XML::Reader gets attributes for current node
+  * Node#inner_html takes the same arguments as Node#to_html GH #117
+  * DocumentFragment#css delegates to it's child nodes GH #123
+  * NodeSet#[] works with slices larger than NodeSet#length GH #131
+  * Reparented nodes maintain their namespace. GH #134
+  * Fixed SEGV when adding an XML::Document to NodeSet
+  * XML::SyntaxError can be duplicated. GH #148
+
+* Deprecations
+
+  * Hpricot compatibility layer removed
+
 === 1.3.3 / 2009/07/26
 
 * New Features

data/Manifest.txt

@@ -13,12 +13,14 @@ ext/nokogiri/html_element_description.c
 ext/nokogiri/html_element_description.h
 ext/nokogiri/html_entity_lookup.c
 ext/nokogiri/html_entity_lookup.h
-ext/nokogiri/html_sax_parser.c
-ext/nokogiri/html_sax_parser.h
+ext/nokogiri/html_sax_parser_context.c
+ext/nokogiri/html_sax_parser_context.h
 ext/nokogiri/nokogiri.c
 ext/nokogiri/nokogiri.h
 ext/nokogiri/xml_attr.c
 ext/nokogiri/xml_attr.h
+ext/nokogiri/xml_attribute_decl.c
+ext/nokogiri/xml_attribute_decl.h
 ext/nokogiri/xml_cdata.c
 ext/nokogiri/xml_cdata.h
 ext/nokogiri/xml_comment.c
@@ -29,6 +31,12 @@ ext/nokogiri/xml_document_fragment.c
 ext/nokogiri/xml_document_fragment.h
 ext/nokogiri/xml_dtd.c
 ext/nokogiri/xml_dtd.h
+ext/nokogiri/xml_element_content.c
+ext/nokogiri/xml_element_content.h
+ext/nokogiri/xml_element_decl.c
+ext/nokogiri/xml_element_decl.h
+ext/nokogiri/xml_entity_decl.c
+ext/nokogiri/xml_entity_decl.h
 ext/nokogiri/xml_entity_reference.c
 ext/nokogiri/xml_entity_reference.h
 ext/nokogiri/xml_io.c
@@ -47,6 +55,8 @@ ext/nokogiri/xml_relax_ng.c
 ext/nokogiri/xml_relax_ng.h
 ext/nokogiri/xml_sax_parser.c
 ext/nokogiri/xml_sax_parser.h
+ext/nokogiri/xml_sax_parser_context.c
+ext/nokogiri/xml_sax_parser_context.h
 ext/nokogiri/xml_sax_push_parser.c
 ext/nokogiri/xml_sax_push_parser.h
 ext/nokogiri/xml_schema.c
@@ -61,7 +71,6 @@ ext/nokogiri/xml_xpath_context.c
 ext/nokogiri/xml_xpath_context.h
 ext/nokogiri/xslt_stylesheet.c
 ext/nokogiri/xslt_stylesheet.h
-lib/action-nokogiri.rb
 lib/nokogiri.rb
 lib/nokogiri/css.rb
 lib/nokogiri/css/generated_parser.rb
@@ -73,16 +82,11 @@ lib/nokogiri/css/syntax_error.rb
 lib/nokogiri/css/tokenizer.rb
 lib/nokogiri/css/tokenizer.rex
 lib/nokogiri/css/xpath_visitor.rb
-lib/nokogiri/decorators.rb
-lib/nokogiri/decorators/hpricot.rb
-lib/nokogiri/decorators/hpricot/node.rb
-lib/nokogiri/decorators/hpricot/node_set.rb
-lib/nokogiri/decorators/hpricot/xpath_visitor.rb
 lib/nokogiri/decorators/slop.rb
 lib/nokogiri/ffi/html/document.rb
 lib/nokogiri/ffi/html/element_description.rb
 lib/nokogiri/ffi/html/entity_lookup.rb
-lib/nokogiri/ffi/html/sax/parser.rb
+lib/nokogiri/ffi/html/sax/parser_context.rb
 lib/nokogiri/ffi/io_callbacks.rb
 lib/nokogiri/ffi/libxml.rb
 lib/nokogiri/ffi/structs/common_node.rb
@@ -90,13 +94,19 @@ lib/nokogiri/ffi/structs/html_elem_desc.rb
 lib/nokogiri/ffi/structs/html_entity_desc.rb
 lib/nokogiri/ffi/structs/xml_alloc.rb
 lib/nokogiri/ffi/structs/xml_attr.rb
+lib/nokogiri/ffi/structs/xml_attribute.rb
 lib/nokogiri/ffi/structs/xml_buffer.rb
 lib/nokogiri/ffi/structs/xml_document.rb
 lib/nokogiri/ffi/structs/xml_dtd.rb
+lib/nokogiri/ffi/structs/xml_element.rb
+lib/nokogiri/ffi/structs/xml_element_content.rb
+lib/nokogiri/ffi/structs/xml_entity.rb
+lib/nokogiri/ffi/structs/xml_enumeration.rb
 lib/nokogiri/ffi/structs/xml_node.rb
 lib/nokogiri/ffi/structs/xml_node_set.rb
 lib/nokogiri/ffi/structs/xml_notation.rb
 lib/nokogiri/ffi/structs/xml_ns.rb
+lib/nokogiri/ffi/structs/xml_parser_context.rb
 lib/nokogiri/ffi/structs/xml_relax_ng.rb
 lib/nokogiri/ffi/structs/xml_sax_handler.rb
 lib/nokogiri/ffi/structs/xml_sax_push_parser_context.rb
@@ -108,11 +118,15 @@ lib/nokogiri/ffi/structs/xml_xpath_object.rb
 lib/nokogiri/ffi/structs/xml_xpath_parser_context.rb
 lib/nokogiri/ffi/structs/xslt_stylesheet.rb
 lib/nokogiri/ffi/xml/attr.rb
+lib/nokogiri/ffi/xml/attribute_decl.rb
 lib/nokogiri/ffi/xml/cdata.rb
 lib/nokogiri/ffi/xml/comment.rb
 lib/nokogiri/ffi/xml/document.rb
 lib/nokogiri/ffi/xml/document_fragment.rb
 lib/nokogiri/ffi/xml/dtd.rb
+lib/nokogiri/ffi/xml/element_content.rb
+lib/nokogiri/ffi/xml/element_decl.rb
+lib/nokogiri/ffi/xml/entity_decl.rb
 lib/nokogiri/ffi/xml/entity_reference.rb
 lib/nokogiri/ffi/xml/namespace.rb
 lib/nokogiri/ffi/xml/node.rb
@@ -121,6 +135,7 @@ lib/nokogiri/ffi/xml/processing_instruction.rb
 lib/nokogiri/ffi/xml/reader.rb
 lib/nokogiri/ffi/xml/relax_ng.rb
 lib/nokogiri/ffi/xml/sax/parser.rb
+lib/nokogiri/ffi/xml/sax/parser_context.rb
 lib/nokogiri/ffi/xml/sax/push_parser.rb
 lib/nokogiri/ffi/xml/schema.rb
 lib/nokogiri/ffi/xml/syntax_error.rb
@@ -128,7 +143,6 @@ lib/nokogiri/ffi/xml/text.rb
 lib/nokogiri/ffi/xml/xpath.rb
 lib/nokogiri/ffi/xml/xpath_context.rb
 lib/nokogiri/ffi/xslt/stylesheet.rb
-lib/nokogiri/hpricot.rb
 lib/nokogiri/html.rb
 lib/nokogiri/html/builder.rb
 lib/nokogiri/html/document.rb
@@ -136,17 +150,22 @@ lib/nokogiri/html/document_fragment.rb
 lib/nokogiri/html/element_description.rb
 lib/nokogiri/html/entity_lookup.rb
 lib/nokogiri/html/sax/parser.rb
+lib/nokogiri/html/sax/parser_context.rb
 lib/nokogiri/syntax_error.rb
 lib/nokogiri/version.rb
 lib/nokogiri/version_warning.rb
 lib/nokogiri/xml.rb
 lib/nokogiri/xml/attr.rb
+lib/nokogiri/xml/attribute_decl.rb
 lib/nokogiri/xml/builder.rb
 lib/nokogiri/xml/cdata.rb
+lib/nokogiri/xml/character_data.rb
 lib/nokogiri/xml/document.rb
 lib/nokogiri/xml/document_fragment.rb
 lib/nokogiri/xml/dtd.rb
-lib/nokogiri/xml/entity_declaration.rb
+lib/nokogiri/xml/element_content.rb
+lib/nokogiri/xml/element_decl.rb
+lib/nokogiri/xml/entity_decl.rb
 lib/nokogiri/xml/fragment_handler.rb
 lib/nokogiri/xml/namespace.rb
 lib/nokogiri/xml/node.rb
@@ -154,13 +173,16 @@ lib/nokogiri/xml/node/save_options.rb
 lib/nokogiri/xml/node_set.rb
 lib/nokogiri/xml/notation.rb
 lib/nokogiri/xml/parse_options.rb
+lib/nokogiri/xml/pp.rb
+lib/nokogiri/xml/pp/character_data.rb
+lib/nokogiri/xml/pp/node.rb
 lib/nokogiri/xml/processing_instruction.rb
 lib/nokogiri/xml/reader.rb
 lib/nokogiri/xml/relax_ng.rb
 lib/nokogiri/xml/sax.rb
 lib/nokogiri/xml/sax/document.rb
-lib/nokogiri/xml/sax/legacy_handlers.rb
 lib/nokogiri/xml/sax/parser.rb
+lib/nokogiri/xml/sax/parser_context.rb
 lib/nokogiri/xml/sax/push_parser.rb
 lib/nokogiri/xml/schema.rb
 lib/nokogiri/xml/syntax_error.rb
@@ -186,31 +208,17 @@ test/files/exslt.xslt
 test/files/foo/foo.xsd
 test/files/po.xml
 test/files/po.xsd
+test/files/shift_jis.html
 test/files/shift_jis.xml
 test/files/snuggles.xml
+test/files/staff.dtd
 test/files/staff.xml
 test/files/staff.xslt
 test/files/tlm.html
 test/files/valid_bar.xml
 test/helper.rb
-test/hpricot/files/basic.xhtml
-test/hpricot/files/boingboing.html
-test/hpricot/files/cy0.html
-test/hpricot/files/immob.html
-test/hpricot/files/pace_application.html
-test/hpricot/files/tenderlove.html
-test/hpricot/files/uswebgen.html
-test/hpricot/files/utf8.html
-test/hpricot/files/week9.html
-test/hpricot/files/why.xml
-test/hpricot/load_files.rb
-test/hpricot/test_alter.rb
-test/hpricot/test_builder.rb
-test/hpricot/test_parser.rb
-test/hpricot/test_paths.rb
-test/hpricot/test_preserved.rb
-test/hpricot/test_xml.rb
 test/html/sax/test_parser.rb
+test/html/sax/test_parser_context.rb
 test/html/test_builder.rb
 test/html/test_document.rb
 test/html/test_document_encoding.rb
@@ -218,6 +226,7 @@ test/html/test_document_fragment.rb
 test/html/test_element_description.rb
 test/html/test_named_characters.rb
 test/html/test_node.rb
+test/html/test_node_encoding.rb
 test/test_convert_xpath.rb
 test/test_css_cache.rb
 test/test_gc.rb
@@ -228,8 +237,10 @@ test/test_xslt_transforms.rb
 test/xml/node/test_save_options.rb
 test/xml/node/test_subclass.rb
 test/xml/sax/test_parser.rb
+test/xml/sax/test_parser_context.rb
 test/xml/sax/test_push_parser.rb
 test/xml/test_attr.rb
+test/xml/test_attribute_decl.rb
 test/xml/test_builder.rb
 test/xml/test_cdata.rb
 test/xml/test_comment.rb
@@ -238,6 +249,9 @@ test/xml/test_document_encoding.rb
 test/xml/test_document_fragment.rb
 test/xml/test_dtd.rb
 test/xml/test_dtd_encoding.rb
+test/xml/test_element_content.rb
+test/xml/test_element_decl.rb
+test/xml/test_entity_decl.rb
 test/xml/test_entity_reference.rb
 test/xml/test_namespace.rb
 test/xml/test_node.rb
@@ -249,6 +263,7 @@ test/xml/test_processing_instruction.rb
 test/xml/test_reader_encoding.rb
 test/xml/test_relax_ng.rb
 test/xml/test_schema.rb
+test/xml/test_syntax_error.rb
 test/xml/test_text.rb
 test/xml/test_unparented_node.rb
 test/xml/test_xpath.rb

data/README.ja.rdoc

@@ -26,8 +26,6 @@ XML/HTMLの高速な解析と探索検索、ならびにCSS3セレクタとXPath
 
   * http://gist.github.com/24605
 
-また、NokogiriはHpricot互換の特徴を持ち、CSSやXPathも簡単に取り扱うことが出来ます。
-
 == SUPPORT:
 
 Nokogiriのメーリングリスト:

data/README.rdoc

@@ -1,6 +1,6 @@
 = Nokogiri
 
-* http://nokogiri.org/
+* http://nokogiri.org
 * http://github.com/tenderlove/nokogiri/wikis
 * http://github.com/tenderlove/nokogiri/tree/master
 * http://groups.google.com/group/nokogiri-talk
@@ -19,7 +19,6 @@ enough of it.
 * XPath support for document searching
 * CSS3 selector support for document searching
 * XML/HTML builder
-* Drop in replacement for Hpricot (though not bug for bug)
 
 Nokogiri parses and searches XML/HTML very quickly, and also has
 correctly implemented CSS3 selector support as well as XPath support.
@@ -28,12 +27,10 @@ Here is a speed test:
 
   * http://gist.github.com/24605
 
-Nokogiri also features an Hpricot compatibility layer to help ease the change
-to using correct CSS and XPath.
-
 == SUPPORT:
 
-The Nokogiri mailing list is available here:
+The Nokogiri {mailing list}[http://groups.google.com/group/nokogiri-talk]
+is available here:
 
   * http://groups.google.com/group/nokogiri-talk
 
@@ -87,7 +84,7 @@ The IRC channel is #nokogiri on freenode.
 
 == DEVELOPMENT:
 
-Developing Nokogiri requires racc and frex.
+Developing Nokogiri requires racc and rexical.
 
 * rake install:deps
 * rake test

data/Rakefile

@@ -21,18 +21,36 @@ HOE = Hoe.spec 'nokogiri' do
   self.extra_rdoc_files  = FileList['*.rdoc']
   self.clean_globs = [
     'lib/nokogiri/*.{o,so,bundle,a,log,dll}',
+    'lib/nokogiri/nokogiri.rb',
+    'lib/nokogiri/1.{8,9}',
     GENERATED_PARSER,
     GENERATED_TOKENIZER,
     'cross',
   ]
 
   %w{ racc rexical rake-compiler }.each do |dep|
-    self.extra_dev_deps << dep
+    self.extra_dev_deps << [dep, '>= 0']
   end
 
   self.spec_extras = { :extensions => ["ext/nokogiri/extconf.rb"] }
 end
 
+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
+
 unless java
   gem 'rake-compiler', '>= 0.4.1'
   require "rake/extensiontask"
@@ -62,20 +80,22 @@ require "#{HOE.name}/\#{RUBY_VERSION.sub(/\\.\\d+$/, '')}/#{HOE.name}"
 
   namespace :cross do
     task :file_list do
-      HOE.spec.platform = 'x86-mswin32'
+      HOE.spec.platform = 'x86-mingw32'
       HOE.spec.extensions = []
       HOE.spec.files += Dir["lib/#{HOE.name}/#{HOE.name}.rb"]
+      HOE.spec.files += Dir["lib/#{HOE.name}/1.{8,9}/#{HOE.name}.so"]
       HOE.spec.files += Dir["ext/nokogiri/*.dll"]
     end
   end
 
   CLOBBER.include("lib/nokogiri/nokogiri.{so,dylib,rb,bundle}")
   CLOBBER.include("lib/nokogiri/1.{8,9}")
+  CLOBBER.include("ext/nokogiri/*.dll")
 end
 
 namespace :gem do
   namespace :dev do
-    task :spec 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)
@@ -96,6 +116,7 @@ namespace :gem do
         HOE.spec.platform = 'java'
         HOE.spec.files << GENERATED_PARSER
         HOE.spec.files << GENERATED_TOKENIZER
+        HOE.spec.files += Dir["ext/nokogiri/*.dll"]
         HOE.spec.extensions = []
         f.write(HOE.spec.to_ruby)
       end
@@ -130,7 +151,16 @@ libs = %w{
   libxslt-1.1.24.win32
 }
 
+lib_dlls = {
+  'iconv-1.9.2.win32'     => 'iconv.dll',
+  'zlib-1.2.3.win32'      => 'zlib1.dll',
+  'libxml2-2.7.3.win32'   => 'libxml2.dll',
+  'libxslt-1.1.24.win32'  => 'libxslt.dll',
+}
+
 libs.each do |lib|
+  libname = lib.split('-').first
+
   file "tmp/stash/#{lib}.zip" do |t|
     puts "downloading #{lib}"
     FileUtils.mkdir_p('tmp/stash')
@@ -140,23 +170,29 @@ libs.each do |lib|
     end
   end
 
-  file "tmp/cross/#{lib.split('-').first}" => ["tmp/stash/#{lib}.zip"] do |t|
+  file "tmp/cross/#{libname}" => ["tmp/stash/#{lib}.zip"] do |t|
     puts "unzipping #{lib}.zip"
     FileUtils.mkdir_p('tmp/cross')
     Dir.chdir('tmp/cross') do
       sh "unzip ../stash/#{lib}.zip"
       sh "cp #{lib}/bin/* #{lib}/lib" # put DLL in lib, so dirconfig works
-      sh "cp #{lib}/bin/*.dll ../../ext/nokogiri/"
       sh "mv #{lib} #{lib.split('-').first}"
       sh "touch #{lib.split('-').first}"
     end
   end
 
+  file "ext/nokogiri/#{lib_dlls[lib]}" => "tmp/cross/#{libname}" do |t|
+    Dir.chdir('tmp/cross') do
+      sh "cp #{libname}/bin/*.dll ../../ext/nokogiri/"
+    end
+  end
+
   if Rake::Task.task_defined?(:cross)
-    Rake::Task[:cross].prerequisites << "tmp/cross/#{lib.split('-').first}"
+    Rake::Task[:cross].prerequisites << "ext/nokogiri/#{lib_dlls[lib]}"
     Rake::Task[:cross].prerequisites << "lib/nokogiri/nokogiri.rb"
     Rake::Task[:cross].prerequisites << "cross:file_list"
   end
+  Rake::Task['gem:jruby:spec'].prerequisites << "ext/nokogiri/#{lib_dlls[lib]}"
 end
 
 require 'tasks/test'