nokogiri 1.5.0.beta.1 → 1.5.0.beta.2

data/CHANGELOG.ja.rdoc

@@ -1,8 +1,28 @@
-=== 1.4.2 ２０１０年５月２２日
+=== 1.4.3 ２０１０年７月２８日
 
 * 新しい機能
 
-  * XML::Node#parse　定義されたコンテキストノードで、XML 又はHTMLのフレグメント
+  * XML::Reader#empty_element?  - 子の無いエレメントにtrueを返す　 #262
+  * Node#remove_namespaces! - 1.4.2では 名前空間のみを取り除いていたが、
+    1.4.3 では名前空間及び、名前空間宣言も取り除く　#294
+
+* バグの修正
+
+  * XML::NodeSet#{include?,delete,push} はXML::Namespaceを受入れる
+  * XML::Document#parse - 1.4.3より文書内の文脈を解析する機能を追加
+  * XML::DocumentFragment#inner_html= 文脈解析を共に実行する　#298, #281
+  * lib/nokogiri/css/parser.y  はCSSと疑似選別の両方を機能
+  * 演算によって近隣に存在する併合型ノードへの遊離問題の有無に関わらず、一切の
+    弊害なしにテキストノードの繰り返しが実行可能　 #283
+  * xmlFirstElementChild et al.による libxml2バージョンでの不適合性を修正 #303
+  * XML::Attr#add_namespace　（！）文字通りの機能実現!　 #252
+  * HTML::DocumentFragment が文字列に存在するエンコードを使用　#305
+
+=== 1.4.2 ２０１０年５月２２日
+
+* 新機能
+
+  * XML::Node#parse　定義されたコンテキストノードでXML 又はHTMLのフレグメント
     を解析する
   * XML::Node#namespacesが子ノードとその祖先ノード内で定義された全ての名前空間
     を返すようになった（以前は祖先ノードの名前空間は返されなかった）
@@ -30,18 +50,18 @@
   * XML::Node#xpath はNodeSetのオブジェクト以外のオブジェクトを返す　GH #208
   * XSLT::StyleSheet#transformはパラメーターのハッシュを受け入れる　GH #223
   * CSSのnot()の疑似セレクタの修正　 GH #205
-  * XML::Builder  はノード達が切り離されても破壊しない（vihaiの協力に感謝）
+  * XML::Builder  はノードらが切り離されても破壊しない（vihaiの協力に感謝）
     GH #228
   * SAX parser経由でエンコードを強制することが出来る　 Eugene Pimenovに感謝!
     GH #204
-  * XML::DocumentFragment はML::Node#parse を使用して子供を限定する
-  * XML Reader内のメモリリークを修正　 sdorさん、ありがとう! GH#244
+  * XML::DocumentFragment はML::Node#parse を使用して子を限定する
+  * XML Reader内のメモリリーク修正　 sdorさん、ありがとう! GH#244
 
 * ノート
 
-  * 今日４月１８日現在、Windows gems は libxml 2.7.6 とlibxslt
-    1.1.26にDLLsを正規装備しています。このリリース以前にも既にDLLsはlibxml
-    2.7.3 と libxslt 1.1.24に正規装備されています。
+  * 今日４月１８日現在、Windows gems は libxml 2.7.7 とlibxslt
+    1.1.26にDLLsを標準装備しています。このリリース以前にも既にDLLsはlibxml
+    2.7.3 と libxslt 1.1.24に標準装備済み。
 
 === 1.4.1 ２００９年１２月１０日
 

data/CHANGELOG.rdoc

@@ -10,6 +10,29 @@
   * LibXML 2.6.16 and earlier are deprecated. Nokogiri will refuse to install.
   * FFI support is removed.
 
+=== 1.4.3 / 2010/07/28
+
+* New Features
+
+  * XML::Reader#empty_element? returns true for empty elements. #262
+  * Node#remove_namespaces! now removes namespace *declarations* as well. #294
+  * NodeSet#at_xpath, NodeSet#at_css and NodeSet#> do what the corresponding
+    methods of Node do.
+
+* Bugfixes
+
+  * XML::NodeSet#{include?,delete,push} accept an XML::Namespace
+  * XML::Document#parse added for parsing in the context of a document
+  * XML::DocumentFragment#inner_html= works with contextual parsing! #298, #281
+  * lib/nokogiri/css/parser.y Combined CSS functions + pseudo selectors fixed
+  * Reparenting text nodes is safe, even when the operation frees adjacent merged nodes. #283
+  * Fixed libxml2 versionitis issue with xmlFirstElementChild et al. #303
+  * XML::Attr#add_namespace now works as expected. #252
+  * HTML::DocumentFragment uses the string's encoding. #305
+  * Fix the CSS3 selector translation rule for the general sibling combinator
+    (a.k.a. preceding selector) that incorrectly converted "E + F G" to
+    "//F//G[preceding-sibling::E]".
+
 === 1.4.2 / 2010/05/22
 
 * New Features

data/Manifest.txt

@@ -7,6 +7,59 @@ README.rdoc
 Rakefile
 bin/nokogiri
 deps.rip
+ext/java/nokogiri/EncodingHandler.java
+ext/java/nokogiri/HtmlDocument.java
+ext/java/nokogiri/HtmlElementDescription.java
+ext/java/nokogiri/HtmlEntityLookup.java
+ext/java/nokogiri/HtmlSaxParserContext.java
+ext/java/nokogiri/NokogiriService.java
+ext/java/nokogiri/XmlAttr.java
+ext/java/nokogiri/XmlAttributeDecl.java
+ext/java/nokogiri/XmlCdata.java
+ext/java/nokogiri/XmlComment.java
+ext/java/nokogiri/XmlDocument.java
+ext/java/nokogiri/XmlDocumentFragment.java
+ext/java/nokogiri/XmlDtd.java
+ext/java/nokogiri/XmlElement.java
+ext/java/nokogiri/XmlElementContent.java
+ext/java/nokogiri/XmlElementDecl.java
+ext/java/nokogiri/XmlEntityDecl.java
+ext/java/nokogiri/XmlEntityReference.java
+ext/java/nokogiri/XmlNamespace.java
+ext/java/nokogiri/XmlNode.java
+ext/java/nokogiri/XmlNodeSet.java
+ext/java/nokogiri/XmlProcessingInstruction.java
+ext/java/nokogiri/XmlReader.java
+ext/java/nokogiri/XmlRelaxng.java
+ext/java/nokogiri/XmlSaxParserContext.java
+ext/java/nokogiri/XmlSaxPushParser.java
+ext/java/nokogiri/XmlSchema.java
+ext/java/nokogiri/XmlSyntaxError.java
+ext/java/nokogiri/XmlText.java
+ext/java/nokogiri/XmlXpathContext.java
+ext/java/nokogiri/XsltStylesheet.java
+ext/java/nokogiri/internals/HtmlDomParserContext.java
+ext/java/nokogiri/internals/NokogiriDocumentCache.java
+ext/java/nokogiri/internals/NokogiriErrorHandler.java
+ext/java/nokogiri/internals/NokogiriHandler.java
+ext/java/nokogiri/internals/NokogiriHelpers.java
+ext/java/nokogiri/internals/NokogiriNamespaceCache.java
+ext/java/nokogiri/internals/NokogiriNamespaceContext.java
+ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java
+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/ParserContext.java
+ext/java/nokogiri/internals/PushInputStream.java
+ext/java/nokogiri/internals/ReaderNode.java
+ext/java/nokogiri/internals/SaveContext.java
+ext/java/nokogiri/internals/SchemaErrorHandler.java
+ext/java/nokogiri/internals/XmlDeclHandler.java
+ext/java/nokogiri/internals/XmlDomParser.java
+ext/java/nokogiri/internals/XmlDomParserContext.java
+ext/java/nokogiri/internals/XmlSaxParser.java
+ext/nokogiri/depend
 ext/nokogiri/extconf.rb
 ext/nokogiri/html_document.c
 ext/nokogiri/html_document.h
@@ -44,6 +97,8 @@ 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
@@ -72,6 +127,10 @@ ext/nokogiri/xml_xpath_context.c
 ext/nokogiri/xml_xpath_context.h
 ext/nokogiri/xslt_stylesheet.c
 ext/nokogiri/xslt_stylesheet.h
+lib/isorelax.jar
+lib/jing.jar
+lib/nekodtd.jar
+lib/nekohtml.jar
 lib/nokogiri.rb
 lib/nokogiri/css.rb
 lib/nokogiri/css/generated_parser.rb
@@ -93,9 +152,9 @@ 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/nokogiri.jar
 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
@@ -133,7 +192,10 @@ lib/nokogiri/xml/xpath/syntax_error.rb
 lib/nokogiri/xml/xpath_context.rb
 lib/nokogiri/xslt.rb
 lib/nokogiri/xslt/stylesheet.rb
+lib/xercesImpl.jar
 lib/xsd/xmlparser/nokogiri.rb
+spec/helper.rb
+spec/xml/reader_spec.rb
 tasks/cross_compile.rb
 tasks/test.rb
 test/css/test_nthiness.rb

data/README.ja.rdoc

@@ -3,7 +3,7 @@
 * http://nokogiri.org/
 * http://github.com/tenderlove/nokogiri/wikis
 * http://github.com/tenderlove/nokogiri/tree/master
-* http://groups.google.com/group/nokogiri-talk
+* http://groups.google.com/group/nokogiri-list
 * http://github.com/tenderlove/nokogiri/issues
 
 == DESCRIPTION:

data/README.rdoc

@@ -81,9 +81,27 @@ The IRC channel is #nokogiri on freenode.
 
 == 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.
+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:
 
@@ -94,7 +112,7 @@ to_html and inner_html) will return a string encoded like the source document.
 Binary packages are available for:
 
 * SuSE[http://download.opensuse.org/repositories/devel:/languages:/ruby:/extensions/]
-* Fedora[https://admin.fedoraproject.org/pkgdb/packages/name/rubygem-nokogiri]
+* Fedora[http://s390.koji.fedoraproject.org/koji/packageinfo?packageID=6756]
 
 == DEVELOPMENT:
 

data/Rakefile

@@ -140,7 +140,7 @@ end
 
 file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
   begin
-    racc = `which racc`.strip
+    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
@@ -157,7 +157,11 @@ file GENERATED_TOKENIZER => "lib/nokogiri/css/tokenizer.rex" do |t|
 end
 
 require 'tasks/test'
-require 'tasks/cross_compile' unless RUBY_PLATFORM =~ /java/
+begin
+  require 'tasks/cross_compile' unless java
+rescue RuntimeError => e
+  warn "WARNING: Could not perform some cross-compiling: #{e}"
+end
 
 desc "set environment variables to build and/or test with debug options"
 task :debug do

data/ext/java/nokogiri/EncodingHandler.java

@@ -0,0 +1,92 @@
+package nokogiri;
+
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
+
+import java.util.HashMap;
+
+import org.jruby.Ruby;
+import org.jruby.RubyClass;
+import org.jruby.RubyObject;
+import org.jruby.anno.JRubyClass;
+import org.jruby.anno.JRubyMethod;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.builtin.IRubyObject;
+
+/**
+ * Stub class to satisfy unit tests.  I'm not sure where this class is
+ * meant to be used. As coded it won't really interact with any other
+ * classes and will have no effect on character encodings reported by
+ * documents being parsed.
+ *
+ * @author Patrick Mahoney <pat@polycrstal.org>
+ */
+@JRubyClass(name="Nokogiri::EncodingHandler")
+public class EncodingHandler extends RubyObject {
+    protected static HashMap<String,String> map = new HashMap<String,String>();
+    static {
+        addInitial();
+    }
+
+    protected String name;
+
+    protected static void addInitial() {
+        map.put("UTF-8", "UTF-8");
+    }
+
+    public EncodingHandler(Ruby ruby, RubyClass klass, String value) {
+        super(ruby, klass);
+        name = value;
+    }
+
+    @JRubyMethod(name="[]", meta=true)
+    public static IRubyObject get(ThreadContext context,
+                                  IRubyObject _klass,
+                                  IRubyObject keyObj) {
+        Ruby ruby = context.getRuntime();
+        String key = keyObj.toString();
+        String value = map.get(key);
+        if (value == null)
+            return ruby.getNil();
+
+        return new EncodingHandler(
+            ruby,
+            getNokogiriClass(ruby, "Nokogiri::EncodingHandler"),
+            value);
+    }
+
+    @JRubyMethod(meta=true)
+    public static IRubyObject delete(ThreadContext context,
+                                     IRubyObject _klass,
+                                     IRubyObject keyObj) {
+        String key = keyObj.toString();
+        String value = map.remove(key);
+        if (value == null)
+            return context.getRuntime().getNil();
+        return context.getRuntime().newString(value);
+    }
+
+    @JRubyMethod(name="clear_aliases!", meta=true)
+    public static IRubyObject clear_aliases(ThreadContext context,
+                                            IRubyObject _klass) {
+        map.clear();
+        addInitial();
+        return context.getRuntime().getNil();
+    }
+
+    @JRubyMethod(meta=true)
+    public static IRubyObject alias(ThreadContext context,
+                                    IRubyObject _klass,
+                                    IRubyObject orig,
+                                    IRubyObject alias) {
+        String value = map.get(orig.toString());
+        if (value != null)
+            map.put(alias.toString(), value);
+
+        return context.getRuntime().getNil();
+    }
+
+    @JRubyMethod
+    public IRubyObject name(ThreadContext context) {
+        return context.getRuntime().newString(name);
+    }
+}

data/ext/java/nokogiri/HtmlDocument.java

@@ -0,0 +1,116 @@
+package nokogiri;
+
+import nokogiri.internals.HtmlDomParserContext;
+import nokogiri.internals.SaveContext;
+
+import org.jruby.Ruby;
+import org.jruby.RubyClass;
+import org.jruby.anno.JRubyClass;
+import org.jruby.anno.JRubyMethod;
+import org.jruby.javasupport.util.RuntimeHelpers;
+import org.jruby.runtime.Arity;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.builtin.IRubyObject;
+import org.w3c.dom.Document;
+import org.w3c.dom.DocumentType;
+
+@JRubyClass(name="Nokogiri::HTML::Document", parent="Nokogiri::XML::Document")
+public class HtmlDocument extends XmlDocument {
+
+    public HtmlDocument(Ruby ruby, RubyClass klazz) {
+        super(ruby, klazz);
+    }
+    
+    public HtmlDocument(Ruby ruby, RubyClass klazz, Document doc) {
+        super(ruby, klazz, doc);
+    }
+
+    @JRubyMethod(name="new", meta = true, rest = true, required=0)
+    public static IRubyObject rbNew(ThreadContext context, IRubyObject cls,
+                                    IRubyObject[] args) {
+        HtmlDocument doc = null;
+        try {
+            Document docNode = createNewDocument();
+            doc = new HtmlDocument(context.getRuntime(), (RubyClass) cls, docNode);
+        } catch (Exception ex) {
+            throw context.getRuntime()
+                .newRuntimeError("couldn't create document: "+ex.toString());
+        }
+
+        RuntimeHelpers.invoke(context, doc, "initialize", args);
+
+        return doc;
+    }
+
+    public static IRubyObject do_parse(ThreadContext context,
+                                       IRubyObject klass,
+                                       IRubyObject[] args) {
+        Ruby ruby = context.getRuntime();
+        Arity.checkArgumentCount(ruby, args, 4, 4);
+        HtmlDomParserContext ctx =
+            new HtmlDomParserContext(ruby, args[2], args[3]);
+        ctx.setInputSource(context, args[0]);
+        return ctx.parse(context, klass, args[1]);
+    }
+
+    /*
+     * call-seq:
+     *  read_io(io, url, encoding, options)
+     *
+     * Read the HTML document from +io+ with given +url+, +encoding+,
+     * and +options+.  See Nokogiri::HTML.parse
+     */
+    @JRubyMethod(meta = true, rest = true)
+    public static IRubyObject read_io(ThreadContext context,
+                                      IRubyObject cls,
+                                      IRubyObject[] args) {
+        return do_parse(context, cls, args);
+    }
+
+    /*
+     * call-seq:
+     *  read_memory(string, url, encoding, options)
+     *
+     * Read the HTML document contained in +string+ with given +url+, +encoding+,
+     * and +options+.  See Nokogiri::HTML.parse
+     */
+    @JRubyMethod(meta = true, rest = true)
+    public static IRubyObject read_memory(ThreadContext context,
+                                          IRubyObject cls,
+                                          IRubyObject[] args) {
+        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();
+        DocumentType dtd = doc.getDoctype();
+
+        if(dtd != null) {
+            ctx.append("<!DOCTYPE ");
+            ctx.append(dtd.getName());
+            if(dtd.getPublicId() != null) {
+                ctx.append(" PUBLIC ");
+                ctx.appendQuoted(dtd.getPublicId());
+                if(dtd.getSystemId() != null) {
+                    ctx.append(" ");
+                    ctx.appendQuoted(dtd.getSystemId());
+                }
+            } else if(dtd.getSystemId() != null) {
+                ctx.append(" SYSTEM ");
+                ctx.appendQuoted(dtd.getSystemId());
+            }
+            ctx.append(">\n");
+        }
+
+        this.saveNodeListContent(context,
+                (XmlNodeSet) this.children(context), ctx);
+        ctx.append("\n");
+    }
+}