nokogiri 1.5.0-x86-mingw32 → 1.5.1.rc1-x86-mingw32

data/CHANGELOG.ja.rdoc

@@ -1,22 +1,49 @@
+== 1.5.1 / 未リリース
+
+* 新機能
+
+  * XML::Builder#comment はコメントノードを作れるようになった.
+  * CSS searches now support namespaced attributes. #593
+
+* バグの修正
+
+  * エンコーディング自動認識において発生しうるメモリリークを修正.
+    @ender672に感謝！
+
+  * homebrew はインストールしたら、extconf は homebrew のパスを読む。
+
+  * XML::Attr nodes are not allowed to be added as node children, so an
+    exception is raised. #558
+
+  * No longer defensively "pickle" adjacent text nodes on
+    Node#add_next_sibling and Node#add_previous_sibling calls. #595.
+
+  * Document#add_child now accepts a Node, NodeSet, DocumentFragment,
+    or String. #546.
+
+  * Document#create_element now recognizes namespaces containing
+    non-word characters (like "SOAP-ENV"). This is mostly relevant to
+    users of Builder, which calls Document#create_element for nearly
+    everything. #531.
+
 == 1.5.0 / 2011年7月1日
 
-* Notes
+* 註
 
-  * See changelog from 1.4.7
+  * 1.4.7からの変更点を参照
 
-* Features
+* 新機能
 
-  * extracted sets of Node::SaveOptions into Node::SaveOptions::DEFAULT_{X,H,XH}TML (refactor)
+  * 各文書形式用のデフォルトのNode::SaveOptionsの組合せを定数化.
+    (Node::SaveOptions::DEFAULT_{X,H,XH}TML)
 
-* Bugfixes
+* バグの修正
 
-  * 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="...">.
+  * JRuby版ではホワイトスペースの扱いに難があるため、XML出力（to_xml）において
+    自動整形をデフォルトでは行わないように変更. #415
+  * JRuby版でNodeのないNodeSetでNullPointerExceptionが発生するのを修正. #443
+  * 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
+  * <meta charset="..."> を認識するようになった.
 
 
 == 1.5.0 beta3 ２０１０年１２月２日

data/CHANGELOG.rdoc

@@ -1,3 +1,31 @@
+== 1.5.1 / unreleased
+
+* Features
+
+  * XML::Builder#comment allows creation of comment nodes.
+  * CSS searches now support namespaced attributes. #593
+
+* Bugfixes
+
+  * Fix a memory leak in encoding detection.  Thanks for pointing this
+    out, @ender672!
+
+  * extconf searches homebrew paths if homebrew is installed.
+
+  * XML::Attr nodes are not allowed to be added as node children, so an
+    exception is raised. #558
+
+  * No longer defensively "pickle" adjacent text nodes on
+    Node#add_next_sibling and Node#add_previous_sibling calls. #595.
+
+  * Document#add_child now accepts a Node, NodeSet, DocumentFragment,
+    or String. #546.
+
+  * Document#create_element now recognizes namespaces containing
+    non-word characters (like "SOAP-ENV"). This is mostly relevant to
+    users of Builder, which calls Document#create_element for nearly
+    everything. #531.
+
 == 1.5.0 / 2011-07-01
 
 * Notes

data/C_CODING_STYLE.rdoc

@@ -0,0 +1,27 @@
+= C/C++ mode style for Nokogiri
+
+Please don't propose commits that only change whitespace. However, if your
+commit touches a function or section that is not using MRI Ruby conventions,
+feel free to update whitespace in the surrounding code.
+
+= WHITESPACE:
+
+indent level: 2
+indent type: Always spaces
+Line Breaks: LF
+
+= FUNCTION DECLARATION:
+
+ANSI C style:
+
+    type name(args)
+    {
+      declarations
+    
+      code
+    }
+
+= SOURCES:
+
+* <3<3<3
+

data/Manifest.txt

@@ -72,6 +72,8 @@ ext/nokogiri/html_entity_lookup.c
 ext/nokogiri/html_entity_lookup.h
 ext/nokogiri/html_sax_parser_context.c
 ext/nokogiri/html_sax_parser_context.h
+ext/nokogiri/html_sax_push_parser.c
+ext/nokogiri/html_sax_push_parser.h
 ext/nokogiri/nokogiri.c
 ext/nokogiri/nokogiri.h
 ext/nokogiri/xml_attr.c
@@ -154,6 +156,7 @@ lib/nokogiri/html/element_description_defaults.rb
 lib/nokogiri/html/entity_lookup.rb
 lib/nokogiri/html/sax/parser.rb
 lib/nokogiri/html/sax/parser_context.rb
+lib/nokogiri/html/sax/push_parser.rb
 lib/nokogiri/syntax_error.rb
 lib/nokogiri/version.rb
 lib/nokogiri/xml.rb
@@ -270,6 +273,7 @@ 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_node_inheritance.rb
 test/xml/test_parse_options.rb
 test/xml/test_processing_instruction.rb
 test/xml/test_reader_encoding.rb

data/README.rdoc

@@ -1,4 +1,4 @@
-= Nokogiri
+= Nokogiri {<img src="https://secure.travis-ci.org/tenderlove/nokogiri.png?rvm=1.9.3" />}[http://travis-ci.org/tenderlove/nokogiri]
 
 * http://nokogiri.org
 * http://github.com/tenderlove/nokogiri/wikis
@@ -25,6 +25,10 @@ correctly implemented CSS3 selector support as well as XPath support.
 
 == SUPPORT:
 
+Before filing a bug report, please read our {submission guidelines}[http://nokogiri.org/tutorials/getting_help.html] at:
+
+  * http://nokogiri.org/tutorials/getting_help.html
+
 The Nokogiri {mailing list}[http://groups.google.com/group/nokogiri-talk]
 is available here:
 
@@ -50,19 +54,19 @@ The IRC channel is #nokogiri on freenode.
 
   ####
   # Search for nodes by css
-  doc.css('h3.r a.l').each do |link|
+  doc.css('h3.r a').each do |link|
     puts link.content
   end
 
   ####
   # Search for nodes by xpath
-  doc.xpath('//h3/a[@class="l"]').each do |link|
+  doc.xpath('//h3/a').each do |link|
     puts link.content
   end
 
   ####
   # Or mix and match.
-  doc.search('h3.r a.l', '//h3/a[@class="l"]').each do |link|
+  doc.search('h3.r a.l', '//h3/a').each do |link|
     puts link.content
   end
 
@@ -128,8 +132,8 @@ Then run rake:
 
 === Developing on JRuby
 
-Currently, development with JRuby depends on C Ruby being installed.  With
-normal C Ruby, install racc and rexical:
+Currently, development with JRuby depends on CRuby being installed.  With
+CRuby, install racc and rexical:
 
     $ gem install racc rexical
 
@@ -145,7 +149,7 @@ Then run rake:
 
 (The MIT License)
 
-Copyright (c) 2008 - 2010:
+Copyright (c) 2008 - 2012:
 
 * {Aaron Patterson}[http://tenderlovemaking.com]
 * {Mike Dalessio}[http://mike.daless.io]

data/Rakefile

@@ -31,24 +31,22 @@ HOE = Hoe.spec 'nokogiri' do
 
   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/nokogiri.{bundle,jar,rb,so}',
     'lib/nokogiri/1.{8,9}',
     GENERATED_PARSER,
     GENERATED_TOKENIZER
   ]
 
   self.extra_dev_deps += [
+    ["hoe-bundler",     ">= 1.1"],
+    ["hoe-debugging",   ">= 1.0.3"],
+    ["hoe-gemspec",     ">= 1.0"],
+    ["hoe-git",         ">= 1.4"],
+    ["mini_portile",    ">= 0.2.2"],
+    ["minitest",        "~> 2.2.2"],
     ["racc",            ">= 1.4.6"],
+    ["rake-compiler",   "=  0.8.0"],
     ["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?
@@ -83,7 +81,12 @@ if java?
     HOE.spec.files += ['lib/nokogiri/nokogiri.jar']
   end
 else
-  require 'tasks/cross_compile'
+  mingw_available = true
+  begin
+    require 'tasks/cross_compile'
+  rescue
+    mingw_available = false
+  end
   require "rake/extensiontask"
 
   HOE.spec.files.reject! { |f| f =~ %r{\.(java|jar)$} }
@@ -91,13 +94,15 @@ else
   Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
     ext.lib_dir = File.join(*['lib', 'nokogiri', ENV['FAT_DIR']].compact)
     ext.config_options << ENV['EXTOPTS']
-    ext.cross_compile  = true
-    ext.cross_platform = ["x86-mswin32-60", "x86-mingw32"]
-    ext.cross_config_options << "--with-xml2-include=#{File.join($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=#{$recipes[:libxslt].path}"
-    ext.cross_config_options << "--with-zlib-dir=#{CROSS_DIR}"
+    if mingw_available
+      ext.cross_compile  = true
+      ext.cross_platform = ["x86-mswin32-60", "x86-mingw32"]
+      ext.cross_config_options << "--with-xml2-include=#{File.join($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
 end
 
@@ -110,6 +115,7 @@ task 'gem:spec' => 'generate' if Rake::Task.task_defined?("gem:spec")
 file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
   racc = RbConfig::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
   racc = "#{::RbConfig::CONFIG['bindir']}/racc" if racc.empty?
+  racc = %x{command -v racc}.strip if racc.empty?
   sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
 end
 
@@ -145,10 +151,19 @@ end
 
 desc "build a windows gem without all the ceremony."
 task "gem:windows" => "gem" do
-  rake_compiler_config = YAML.load_file("#{ENV['HOME']}/.rake-compiler/config.yml")
+  cross_rubies = ["1.8.7-p330", "1.9.2-p136"]
+  ruby_cc_version = cross_rubies.collect { |_| _.split("-").first }.join(":") # e.g., "1.8.7:1.9.2"
+  rake_compiler_config_path = "#{ENV['HOME']}/.rake-compiler/config.yml"
+
+  unless File.exists? rake_compiler_config_path
+    raise "rake-compiler has not installed any cross rubies. try running 'env --unset=HOST rake-compiler cross-ruby VERSION=#{cross_rubies.first}'"
+  end
+  rake_compiler_config = YAML.load_file(rake_compiler_config_path)
 
-  # 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|
+  # check that rake-compiler config contains the right patchlevels. see #279 for background,
+  # and http://blog.mmediasys.com/2011/01/22/rake-compiler-updated-list-of-supported-ruby-versions-for-cross-compilation/
+  # for more up-to-date docs.
+  cross_rubies.each do |version|
     majmin, patchlevel = version.split("-")
     rbconfig = "rbconfig-#{majmin}"
     unless rake_compiler_config.key?(rbconfig) && rake_compiler_config[rbconfig] =~ /-#{patchlevel}/
@@ -156,12 +171,12 @@ task "gem:windows" => "gem" do
     end
   end
 
-  # 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?
+  # verify that --export-all is in the 1.9 rbconfig. see #279,#374,#375.
+  rbconfig_19 = rake_compiler_config["rbconfig-1.9.2"]
+  raise "rbconfig #{rbconfig_19} needs --export-all in its DLDFLAGS value" if File.read(rbconfig_19).split("\n").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!")
+  sh("env PKG_CONFIG_PATH=#{pkg_config_path} RUBY_CC_VERSION=#{ruby_cc_version} rake cross native gem") || raise("build failed!")
 end
 
 # vim: syntax=Ruby

data/bin/nokogiri

@@ -27,6 +27,10 @@ opts = OptionParser.new do |opts|
     encoding = v
   end
 
+  opts.on("--rng <uri|path>", "Validate using this rng file.") do |v|
+    @rng = open(v) {|f| Nokogiri::XML::RelaxNG(f)}
+  end
+
   opts.on_tail("-?", "--help", "Show this message") do
     puts opts
     exit
@@ -48,6 +52,10 @@ end
 
 @doc = parse_class.parse(open(uri).read, nil, encoding)
 
-puts "Your document is stored in @doc..."
-IRB.start
+if @rng
+  puts @rng.validate(@doc)
+else
+  puts "Your document is stored in @doc..."
+  IRB.start
+end
 

data/ext/nokogiri/extconf.rb

@@ -30,7 +30,8 @@ if RbConfig::MAKEFILE_CONFIG['CC'] =~ /mingw/
 end
 
 if RbConfig::MAKEFILE_CONFIG['CC'] =~ /gcc/
-  $CFLAGS << " -O3 -Wall -Wcast-qual -Wwrite-strings -Wconversion -Wmissing-noreturn -Winline"
+  $CFLAGS << " -O3" unless $CFLAGS[/-O\d/]
+  $CFLAGS << " -Wall -Wcast-qual -Wwrite-strings -Wconversion -Wmissing-noreturn -Winline"
 end
 
 if RbConfig::CONFIG['target_os'] =~ /mswin32/
@@ -80,6 +81,13 @@ else
     '/usr/local/include/libxml2',
     File.join(INCLUDEDIR, "libxml2")
   ] + HEADER_DIRS
+
+  # If the user has homebrew installed, use the libxml2 inside homebrew
+  brew_prefix = `brew --prefix libxml2 2> /dev/null`.chomp
+  unless brew_prefix.empty?
+    LIB_DIRS.unshift File.join(brew_prefix, 'lib')
+    XML2_HEADER_DIRS.unshift File.join(brew_prefix, 'include/libxml2')
+  end
 end
 
 dir_config('zlib', HEADER_DIRS, LIB_DIRS)

data/ext/nokogiri/html_document.c

@@ -1,5 +1,7 @@
 #include <html_document.h>
 
+static ID id_encoding_found;
+
 /*
  * call-seq:
  *  new
@@ -56,6 +58,18 @@ static VALUE read_io( VALUE klass,
   );
   xmlSetStructuredErrorFunc(NULL, NULL);
 
+  /*
+   * If EncodingFound has occurred in EncodingReader, make sure to do
+   * a cleanup and propagate the error.
+   */
+  if (rb_respond_to(io, id_encoding_found)) {
+    VALUE encoding_found = rb_funcall(io, id_encoding_found, 0);
+    if (!NIL_P(encoding_found)) {
+      xmlFreeDoc(doc);
+      rb_exc_raise(encoding_found);
+    }
+  }
+
   if(doc == NULL) {
     xmlErrorPtr error;
 
@@ -151,4 +165,6 @@ void init_html_document()
   rb_define_singleton_method(klass, "new", new, -1);
 
   rb_define_method(klass, "type", type, 0);
+
+  id_encoding_found = rb_intern("encoding_found");
 }

data/ext/nokogiri/html_sax_parser_context.c

@@ -13,31 +13,35 @@ static void deallocate(xmlParserCtxtPtr ctxt)
   NOKOGIRI_DEBUG_END(handler);
 }
 
-static VALUE parse_memory(VALUE klass, VALUE data, VALUE encoding)
+static VALUE
+parse_memory(VALUE klass, VALUE data, VALUE encoding)
 {
-  htmlParserCtxtPtr ctxt;
-
-  if(NIL_P(data)) rb_raise(rb_eArgError, "data cannot be nil");
-  if(!(int)RSTRING_LEN(data))
-    rb_raise(rb_eRuntimeError, "data cannot be empty");
-
-  ctxt = htmlCreateMemoryParserCtxt(
-      StringValuePtr(data),
-      (int)RSTRING_LEN(data)
-  );
+    htmlParserCtxtPtr ctxt;
+
+    if (NIL_P(data))
+	rb_raise(rb_eArgError, "data cannot be nil");
+    if (!(int)RSTRING_LEN(data))
+	rb_raise(rb_eRuntimeError, "data cannot be empty");
+
+    ctxt = htmlCreateMemoryParserCtxt(StringValuePtr(data),
+				      (int)RSTRING_LEN(data));
+    if (ctxt->sax) {
+	xmlFree(ctxt->sax);
+	ctxt->sax = NULL;
+    }
 
-  if(RTEST(encoding)) {
-    xmlCharEncodingHandlerPtr enc = xmlFindCharEncodingHandler(StringValuePtr(encoding));
-    if(enc != NULL) {
-      xmlSwitchToEncoding(ctxt, enc);
-      if(ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) {
-        rb_raise(rb_eRuntimeError, "Unsupported encoding %s",
-            StringValuePtr(encoding));
-      }
+    if (RTEST(encoding)) {
+	xmlCharEncodingHandlerPtr enc = xmlFindCharEncodingHandler(StringValuePtr(encoding));
+	if (enc != NULL) {
+	    xmlSwitchToEncoding(ctxt, enc);
+	    if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) {
+		rb_raise(rb_eRuntimeError, "Unsupported encoding %s",
+			 StringValuePtr(encoding));
+	    }
+	}
     }
-  }
 
-  return Data_Wrap_Struct(klass, NULL, deallocate, ctxt);
+    return Data_Wrap_Struct(klass, NULL, deallocate, ctxt);
 }
 
 static VALUE parse_file(VALUE klass, VALUE filename, VALUE encoding)
@@ -49,30 +53,48 @@ static VALUE parse_file(VALUE klass, VALUE filename, VALUE encoding)
   return Data_Wrap_Struct(klass, NULL, deallocate, ctxt);
 }
 
-static VALUE parse_with(VALUE self, VALUE sax_handler)
+static VALUE
+parse_doc(VALUE ctxt_val)
+{
+    htmlParserCtxtPtr ctxt = (htmlParserCtxtPtr)ctxt_val;
+    htmlParseDocument(ctxt);
+    return Qnil;
+}
+
+static VALUE
+parse_doc_finalize(VALUE ctxt_val)
 {
-  htmlParserCtxtPtr ctxt;
-  htmlSAXHandlerPtr sax;
+    htmlParserCtxtPtr ctxt = (htmlParserCtxtPtr)ctxt_val;
+
+    if (ctxt->myDoc)
+	xmlFreeDoc(ctxt->myDoc);
 
-  if(!rb_obj_is_kind_of(sax_handler, cNokogiriXmlSaxParser))
-    rb_raise(rb_eArgError, "argument must be a Nokogiri::XML::SAX::Parser");
+    NOKOGIRI_SAX_TUPLE_DESTROY(ctxt->userData);
+    return Qnil;
+}
+
+static VALUE
+parse_with(VALUE self, VALUE sax_handler)
+{
+    htmlParserCtxtPtr ctxt;
+    htmlSAXHandlerPtr sax;
 
-  Data_Get_Struct(self, htmlParserCtxt, ctxt);
-  Data_Get_Struct(sax_handler, htmlSAXHandler, sax);
+    if (!rb_obj_is_kind_of(sax_handler, cNokogiriXmlSaxParser))
+	rb_raise(rb_eArgError, "argument must be a Nokogiri::XML::SAX::Parser");
 
-  /* Free the sax handler since we'll assign our own */
-  if(ctxt->sax && ctxt->sax != (xmlSAXHandlerPtr)&xmlDefaultSAXHandler)
-    xmlFree(ctxt->sax);
+    Data_Get_Struct(self, htmlParserCtxt, ctxt);
+    Data_Get_Struct(sax_handler, htmlSAXHandler, sax);
 
-  ctxt->sax = sax;
-  ctxt->userData = (void *)NOKOGIRI_SAX_TUPLE_NEW(ctxt, sax_handler);
+    /* Free the sax handler since we'll assign our own */
+    if (ctxt->sax && ctxt->sax != (xmlSAXHandlerPtr)&xmlDefaultSAXHandler)
+	xmlFree(ctxt->sax);
 
-  htmlParseDocument(ctxt);
+    ctxt->sax = sax;
+    ctxt->userData = (void *)NOKOGIRI_SAX_TUPLE_NEW(ctxt, sax_handler);
 
-  if(NULL != ctxt->myDoc) xmlFreeDoc(ctxt->myDoc);
+    rb_ensure(parse_doc, (VALUE)ctxt, parse_doc_finalize, (VALUE)ctxt);
 
-  NOKOGIRI_SAX_TUPLE_DESTROY(ctxt->userData);
-  return self;
+    return self;
 }
 
 void init_html_sax_parser_context()