nokogiri 1.2.3-x86-mswin32-60 → 1.4.5-x86-mswin32-60

data/Manifest.txt

@@ -1,21 +1,28 @@
 .autotest
+.gemtest
 CHANGELOG.ja.rdoc
 CHANGELOG.rdoc
 Manifest.txt
 README.ja.rdoc
 README.rdoc
 Rakefile
+bin/nokogiri
+ext/nokogiri/depend
 ext/nokogiri/extconf.rb
 ext/nokogiri/html_document.c
 ext/nokogiri/html_document.h
+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/native.c
-ext/nokogiri/native.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
@@ -26,10 +33,22 @@ 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_encoding_handler.c
+ext/nokogiri/xml_encoding_handler.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
 ext/nokogiri/xml_io.h
+ext/nokogiri/xml_libxml2_hacks.c
+ext/nokogiri/xml_libxml2_hacks.h
+ext/nokogiri/xml_namespace.c
+ext/nokogiri/xml_namespace.h
 ext/nokogiri/xml_node.c
 ext/nokogiri/xml_node.h
 ext/nokogiri/xml_node_set.c
@@ -38,67 +57,140 @@ ext/nokogiri/xml_processing_instruction.c
 ext/nokogiri/xml_processing_instruction.h
 ext/nokogiri/xml_reader.c
 ext/nokogiri/xml_reader.h
+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
+ext/nokogiri/xml_schema.h
 ext/nokogiri/xml_syntax_error.c
 ext/nokogiri/xml_syntax_error.h
 ext/nokogiri/xml_text.c
 ext/nokogiri/xml_text.h
-ext/nokogiri/xml_xpath.c
-ext/nokogiri/xml_xpath.h
 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
-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
 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/hpricot.rb
+lib/nokogiri/ffi/encoding_handler.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_context.rb
+lib/nokogiri/ffi/io_callbacks.rb
+lib/nokogiri/ffi/libxml.rb
+lib/nokogiri/ffi/structs/common_node.rb
+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_char_encoding_handler.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_parser_input.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
+lib/nokogiri/ffi/structs/xml_schema.rb
+lib/nokogiri/ffi/structs/xml_syntax_error.rb
+lib/nokogiri/ffi/structs/xml_text_reader.rb
+lib/nokogiri/ffi/structs/xml_xpath_context.rb
+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/weak_bucket.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
+lib/nokogiri/ffi/xml/node_set.rb
+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
+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/html.rb
 lib/nokogiri/html/builder.rb
 lib/nokogiri/html/document.rb
+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/comment.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/element.rb
-lib/nokogiri/xml/entity_declaration.rb
-lib/nokogiri/xml/fragment_handler.rb
+lib/nokogiri/xml/element_content.rb
+lib/nokogiri/xml/element_decl.rb
+lib/nokogiri/xml/entity_decl.rb
+lib/nokogiri/xml/namespace.rb
 lib/nokogiri/xml/node.rb
 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/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
 lib/nokogiri/xml/text.rb
 lib/nokogiri/xml/xpath.rb
@@ -107,52 +199,60 @@ lib/nokogiri/xml/xpath_context.rb
 lib/nokogiri/xslt.rb
 lib/nokogiri/xslt/stylesheet.rb
 lib/xsd/xmlparser/nokogiri.rb
+tasks/cross_compile.rb
 tasks/test.rb
 test/css/test_nthiness.rb
 test/css/test_parser.rb
 test/css/test_tokenizer.rb
 test/css/test_xpath_visitor.rb
+test/decorators/test_slop.rb
+test/ffi/test_document.rb
+test/files/2ch.html
+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/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
+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
+test/test_encoding_handler.rb
 test/test_memory_leak.rb
 test/test_nokogiri.rb
 test/test_reader.rb
+test/test_soap4r_sax.rb
 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
@@ -161,12 +261,23 @@ 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
+test/xml/test_node_attributes.rb
 test/xml/test_node_encoding.rb
+test/xml/test_node_reparenting.rb
 test/xml/test_node_set.rb
+test/xml/test_parse_options.rb
 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
+test/xslt/test_custom_functions.rb

data/README.ja.rdoc

@@ -1,39 +1,39 @@
 = Nokogiri (鋸)
 
-* http://nokogiri.rubyforge.org/
+* http://nokogiri.org/
 * http://github.com/tenderlove/nokogiri/wikis
 * http://github.com/tenderlove/nokogiri/tree/master
-* http://rubyforge.org/mailman/listinfo/nokogiri-talk
-* http://nokogiri.lighthouseapp.com/projects/19607-nokogiri/overview
+* http://groups.google.com/group/nokogiri-list
+* http://github.com/tenderlove/nokogiri/issues
 
 == DESCRIPTION:
 
-Nokogiri はHTMLやXMLやSAXやXSLTやReaderのパーサーです。
+Nokogiri はHTMLとXMLとSAXとXSLTとReaderのパーサーです。とりわけ重要な特徴は、
+ドキュメントをXPathやCSS3セレクター経由で探索する機能を持つことです。
 
-== FEATURES:
-
-* XPath で探せる
-* CSS3 のセレクターで探せる
-* XML/HTMLのビルダーはある
-
-検索出来たり、正確にCSS3とXPathをサポート出来たりする。
+XMLは暴力に似ている - XMLが君の問題を解決しないとしたら、君はXMLを十分に
+使いこなしていない事になる。
 
-これはスピードテストです：
+== FEATURES:
 
-  * http://gist.github.com/24605
+* XPath による探索
+* CSS3 のセレクターによる探索
+* XML/HTMLのビルダー
 
-NokogiriはHpricotの代わりに使用出来る。
-その互換性は簡単に正しいCSSとXPathを使用する事が出来る。
+XML/HTMLの高速な解析と探索検索、ならびにCSS3セレクタとXPathをサポートしています。
 
 == SUPPORT:
 
-ノコギリのメーリングリストは:
+日本語でNokogiriの
+{メーリングリスト}[http://groups.google.com/group/nokogiri-list]
+
+  * http://groups.google.com/group/nokogiri-list
 
-  * http://rubyforge.org/mailman/listinfo/nokogiri-talk
+{バグ報告}[http://github.com/tenderlove/nokogiri/issues]
 
-バグファイルは:
+  * http://github.com/tenderlove/nokogiri/issues
 
-  * http://nokogiri.lighthouseapp.com/projects/19607-nokogiri/overview
+IRCのチャンネルはfreenodeの #nokogiri です。
 
 == SYNOPSIS:
 
@@ -77,7 +77,7 @@ NokogiriはHpricotの代わりに使用出来る。
 
 (The MIT License)
 
-Copyright (c) 2008 - 2009:
+Copyright (c) 2008 - 2010:
 
 * {Aaron Patterson}[http://tenderlovemaking.com]
 * {Mike Dalessio}[http://mike.daless.io]

data/README.rdoc

@@ -1,51 +1,51 @@
 = Nokogiri
 
-* http://nokogiri.rubyforge.org/
+* http://nokogiri.org
 * http://github.com/tenderlove/nokogiri/wikis
 * http://github.com/tenderlove/nokogiri/tree/master
-* http://rubyforge.org/mailman/listinfo/nokogiri-talk
-* http://nokogiri.lighthouseapp.com/projects/19607-nokogiri/overview
+* http://groups.google.com/group/nokogiri-talk
+* http://github.com/tenderlove/nokogiri/issues
 
 == DESCRIPTION:
 
-Nokogiri (鋸) is an HTML, XML, SAX, and Reader parser.
+Nokogiri (鋸) is an HTML, XML, SAX, and Reader parser.  Among Nokogiri's
+many features is the ability to search documents via XPath or CSS3 selectors.
+
+XML is like violence - if it doesn’t solve your problems, you are not using
+enough of it.
 
 == FEATURES:
 
 * 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.
 
-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
 
-  * http://rubyforge.org/mailman/listinfo/nokogiri-talk
+The {bug tracker}[http://github.com/tenderlove/nokogiri/issues]
+is available here:
 
-The bug tracker is available here:
+  * http://github.com/tenderlove/nokogiri/issues
 
-  * http://nokogiri.lighthouseapp.com/projects/19607-nokogiri/overview
+The IRC channel is #nokogiri on freenode.
 
 == SYNOPSIS:
 
   require 'nokogiri'
   require 'open-uri'
-  
+
   # Get a Nokogiri::HTML:Document for the page we’re interested in...
 
   doc = Nokogiri::HTML(open('http://www.google.com/search?q=tenderlove'))
-  
+
   # Do funky things with it using Nokogiri::XML::Node methods...
 
   ####
@@ -53,13 +53,13 @@ The bug tracker is available here:
   doc.css('h3.r a.l').each do |link|
     puts link.content
   end
-  
+
   ####
   # Search for nodes by xpath
   doc.xpath('//h3/a[@class="l"]').each do |link|
     puts link.content
   end
-  
+
   ####
   # Or mix and match.
   doc.search('h3.r a.l', '//h3/a[@class="l"]').each do |link|
@@ -75,13 +75,44 @@ The bug tracker is available here:
 * libxslt
 * libxslt-dev
 
+== ENCODING:
+
+Strings are always stored as UTF-8 internally.  Methods that return
+text values will always return UTF-8 encoded strings.  Methods that
+return XML (like to_xml, to_html and inner_html) will return a string
+encoded like the source document.
+
+*WARNING*
+
+Some documents declare one particular encoding, but use a different
+one. So, which encoding should the parser choose?
+
+Remember that data is just a stream of bytes. Only us humans add
+meaning to that stream. Any particular set of bytes could be valid
+characters in multiple encodings, so detecting encoding with 100%
+accuracy is not possible. libxml2 does its best, but it can't be right
+100% of the time.
+
+If you want Nokogiri to handle the document encoding properly, your
+best bet is to explicitly set the encoding.  Here is an example of
+explicitly setting the encoding to EUC-JP on the parser:
+
+    doc = Nokogiri.XML('<foo><bar /><foo>', nil, 'EUC-JP')
+
 == INSTALL:
 
 * sudo gem install nokogiri
 
+=== Binary packages
+
+Binary packages are available for:
+
+* SuSE[http://download.opensuse.org/repositories/devel:/languages:/ruby:/extensions/]
+* Fedora[http://s390.koji.fedoraproject.org/koji/packageinfo?packageID=6756]
+
 == DEVELOPMENT:
 
-Developing Nokogiri requires racc and frex.
+Developing Nokogiri requires racc and rexical.
 
 * rake install:deps
 * rake test
@@ -90,7 +121,7 @@ Developing Nokogiri requires racc and frex.
 
 (The MIT License)
 
-Copyright (c) 2008 - 2009:
+Copyright (c) 2008 - 2010:
 
 * {Aaron Patterson}[http://tenderlovemaking.com]
 * {Mike Dalessio}[http://mike.daless.io]