nokogiri 1.5.6.rc2-java → 1.5.6.rc3-java

data/CHANGELOG.ja.rdoc

@@ -2,13 +2,30 @@
 
 * Features
 
-* Bugfixes
+  * XML::Document#collect_namespaces　メソッドのパフォーマンスを改善した。 #761 (ありがとう、Juergen Mangler!)
+  * SAX::Document#processing_instructionに新しいcallbackが追加 (ありがとう、Kitaiti Makoto!)
+  * Node#native_content= メソッドでエスケープされていない文字列をセットできるようにした。 #768
+  * 名前空間を付けて xpath 式を書く場合に、シンボルキーを使えるようにした。#729 (ありがとう、Ben Langfeld.)
+  * XML::Node#[]= メソッド内で受け取った引数を文字列に変換するようにした。#729 (ありがとう、Ben Langfeld.)
+  * bin/nokogiri コマンドが $stdin からドキュメントを読んで処理できるようにした。
+  * bin/nokogiri -e を指定することでコマンドラインプログラムを実行できるようにした。
+
 
-  * JRuby で '#' で始まる文字列を名前とする EntityReference を作ろうとすると INVALID_CHARACTER_ERR という例外がはっせいする。 #719
-  * JRuby では Nodeのサブクラスのnamespaceを正しく文字列に変換しない。 #715
-  * Nokogiri now detects XSLT transform errors. #731 (Thanks, Justin Fitzsimmons!)
-  * Raise an ArgumentError if an invalid encoding is passed to the SAX parser. #756 (Thanks, Bradley Schaefer!)
-  * JRuby Node#content now renders newlines properly. #737 (Thanks, Piotr Szmielew!)
+* Bugfixes
+  * [JRuby] XML宣言の前にスペースがあると、ドキュメントのパーズに失敗する。(#748の修正でこれもなおっている) #790
+  * [JRuby] Nokogiri::XML::Node#content のJRubyの振る舞いがCRubyと同じではない。#794, #797
+  * [JRuby] で '#' で始まる文字列を名前とする EntityReference を作ろうとすると INVALID_CHARACTER_ERR という例外がはっせいする。 #719
+  * [JRuby] では Nodeのサブクラスのnamespaceを正しく文字列に変換しない。 #715
+  * Nokogiri はこのバージョンからXSLT変換のエラーを検出するようになった。#731 (ありがとう、Justin Fitzsimmons!)
+  * SAXパーザに不正なエンコーディングに渡された場合はArgumentErrorを投げるようにした。#756 (ありがとう、Bradley Schaefer!)
+  * [JRuby] Node#contentがこのバージョンから改行コードを正しく表示するようになった。#737 (ありがとう、Piotr Szmielew!)
+  * [JRuby] recover optionが指定されている場合は宣言の無いネームスペースを無視するようにした。#748
+  * [JRuby] ネームスペースを検出するXPathが続けて実行されても例外を投げてはいけない。#764
+  * [JRuby] XMLを表示(出力)する際のホワイトスペースの扱いをlibxml2バージョンとさらに同様になるようにした。#771
+  * [JRuby] ネームスペース付きの属性を含むXMLドキュメントを文字列でbuilderに追加しようとすると失敗する。#770
+  * [JRuby] Nokogiri::XML::Document#wrapを使って生成したドキュメントに << でノードを追加しようとすると
+     undefined method `length' for nil:NilClassのエラーが発生する #781
+  * [JRuby] 開いているファイルのデスクリプタを閉じようとすると、"bad file descriptor" が発生する。#495
 
 
 == 1.5.5 / ２０１２年６月２４日

data/CHANGELOG.rdoc

@@ -2,13 +2,29 @@
 
 * Features
 
-* Bugfixes
+  * Improved performance of XML::Document#collect_namespaces. #761 (Thanks, Juergen Mangler!)
+  * New callback SAX::Document#processing_instruction (Thanks, Kitaiti Makoto!)
+  * Node#native_content= allows setting unescaped node contant. #768
+  * XPath lookup with namespaces supports symbol keys. #729 (Thanks, Ben Langfeld.)
+  * XML::Node#[]= stringifies values. #729 (Thanks, Ben Langfeld.)
+  * bin/nokogiri will process a document from $stdin
+  * bin/nokogiri -e will execute a program from the command line
+
 
-  * JRuby raises INVALID_CHARACTER_ERR exception when EntityReference name starts with '#'. #719
-  * JRuby doesn't coerce namespaces out of strings on a direct subclass of Node. #715
+* Bugfixes
+  * [JRuby] space prior to xml preamble causes nokogiri to fail parsing. (fixed along with #748) #790
+  * [JRuby] Fixed the bug Nokogiri::XML::Node#content inconsistency between Java and C. #794, #797
+  * [JRuby] raises INVALID_CHARACTER_ERR exception when EntityReference name starts with '#'. #719
+  * [JRuby] doesn't coerce namespaces out of strings on a direct subclass of Node. #715
   * Nokogiri now detects XSLT transform errors. #731 (Thanks, Justin Fitzsimmons!)
   * Raise an ArgumentError if an invalid encoding is passed to the SAX parser. #756 (Thanks, Bradley Schaefer!)
-  * JRuby Node#content now renders newlines properly. #737 (Thanks, Piotr Szmielew!)
+  * [JRuby] Node#content now renders newlines properly. #737 (Thanks, Piotr Szmielew!)
+  * [JRuby] Unknown namespace are ignore when the recover option is used. #748
+  * [JRuby] XPath queries for namespaces should not throw exceptions when called twice in a row. #764
+  * [JRuby] More consistent (with libxml2) whitespace formatting when emitting XML. #771
+  * [JRuby] namespaced attributes broken when appending raw xml to builder. #770
+  * [JRuby] Nokogiri::XML::Document#wrap raises undefined method `length' for nil:NilClass when trying to << to a node. #781
+  * [JRuby] Fixed "bad file descriptor" bug when closing open file descriptors. #495
 
 
 == 1.5.5 / 2012-06-24

data/README.rdoc

@@ -122,13 +122,10 @@ 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:
+Then install core gems and bootstrap:
 
-    $ gem install hoe rake-compiler racc rexical minitest
-
-Then run rake:
-
-    $ rake
+    $ gem install hoe rake-compiler mini_portile
+    $ rake newb
 
 === Developing on JRuby
 

data/ROADMAP.md

@@ -19,8 +19,9 @@
 * https://github.com/sparklemotion/nokogiri/issues/679
   Mixing in Enumerable has some unintended consequences; plus we want to improve the attributes API
 
-* (closed) https://github.com/sparklemotion/nokogiri/issues/666
-  Some ideas for a better attributes API?
+* Some ideas for a better attributes API?
+  * (closed) https://github.com/sparklemotion/nokogiri/issues/666
+  * https://github.com/sparklemotion/nokogiri/issues/765
 
 
 ## improve CSS query parsing

data/Rakefile

@@ -17,6 +17,8 @@ def java?
   !! (RUBY_PLATFORM =~ /java/)
 end
 
+ENV['LANG'] = "en_US.UTF-8" # UBUNTU 10.04, Y U NO DEFAULT TO UTF-8?
+
 require 'tasks/nokogiri.org'
 
 HOE = Hoe.spec 'nokogiri' do
@@ -118,9 +120,9 @@ task 'gem:spec' => 'generate' if Rake::Task.task_defined?("gem:spec")
 # dependencies in the Gemfile are constrainted to ruby platforms
 # (i.e. MRI and Rubinius). There's no way to do that through hoe,
 # and any solution will require changing hoe and hoe-bundler.
-old_gemfile_task = Rake::Task['bundler:gemfile']
+old_gemfile_task = Rake::Task['bundler:gemfile'] rescue nil
 task 'bundler:gemfile' do
-  old_gemfile_task.invoke
+  old_gemfile_task.invoke if old_gemfile_task
 
   lines = File.open('Gemfile', 'r') { |f| f.readlines }.map do |line|
     line =~ /racc|rexical/ ? "#{line.strip}, :platform => :ruby" : line

data/bin/nokogiri

@@ -16,6 +16,7 @@ opts = OptionParser.new do |opts|
   opts.separator "Examples:"
   opts.separator "  nokogiri http://www.ruby-lang.org/"
   opts.separator "  nokogiri ./public/index.html"
+  opts.separator "  curl -s http://nokogiri.org | nokogiri -e'p $_.css(\"h1\").length'"
   opts.separator ""
   opts.separator "Options:"
 
@@ -27,6 +28,10 @@ opts = OptionParser.new do |opts|
     encoding = v
   end
 
+  opts.on("-e command", "Specifies script from command-line.") do |v|
+    @script = v
+  end
+
   opts.on("--rng <uri|path>", "Validate using this rng file.") do |v|
     @rng = open(v) {|f| Nokogiri::XML::RelaxNG(f)}
   end
@@ -45,19 +50,29 @@ opts.parse!
 
 uri = ARGV.shift
 
-if uri.to_s.strip.empty?
+if uri.to_s.strip.empty? && $stdin.tty?
   puts opts
   exit 1
 end
 
-@doc = parse_class.parse(open(uri).read, nil, encoding)
+if $stdin.tty?
+  @doc = parse_class.parse(open(uri).read, nil, encoding)
+else
+  @doc = parse_class.parse($stdin, nil, encoding)
+end
+
+$_ = @doc
 
 if @rng
   @rng.validate(@doc).each do |error|
     puts error.message
   end
 else
-  puts "Your document is stored in @doc..."
-  IRB.start
+  if @script
+    eval @script, binding, '<main>'
+  else
+    puts "Your document is stored in @doc..."
+    IRB.start
+  end
 end
 

data/build_all

@@ -13,6 +13,10 @@
 #
 #  as you build, you may run into these problems:
 #
+#  - if you're using Virtualbox shared directories, you'll get a mingw
+#    "Protocol error" at linktime. Boo! Either use NFS or a
+#    locally-checked-out repository.
+#
 #  - on ubuntus 11 and later, you may have issues with building
 #    rake-compiler's rubies against openssl v2. Just comment the lines
 #    out from ossl_ssl.c and you'll be fine.
@@ -43,7 +47,7 @@ fi
 
 function rvm_use {
     current_ruby=$1
-    rvm use "${1}@nokogiri" --create
+    rvm use "${1}@nokogiri" --create || rvm -v
 }
 
 set -o errexit

data/ext/java/nokogiri/XmlDocument.java

@@ -535,6 +535,7 @@ public class XmlDocument extends XmlNode {
     @JRubyMethod(meta=true)
     public static IRubyObject wrapJavaDocument(ThreadContext context, IRubyObject klazz, IRubyObject arg) {
         XmlDocument xmlDocument = (XmlDocument) NokogiriService.XML_DOCUMENT_ALLOCATOR.allocate(context.getRuntime(), getNokogiriClass(context.getRuntime(), "Nokogiri::XML::Document"));
+        RuntimeHelpers.invoke(context, xmlDocument, "initialize");
         Document document = (Document)arg.toJava(Document.class);
         xmlDocument.setDocumentNode(context, document);
         return xmlDocument;

data/ext/java/nokogiri/XmlNamespace.java

@@ -98,7 +98,6 @@ public class XmlNamespace extends RubyObject {
         this.href = href;
         this.prefixString = prefixString;
         this.hrefString = hrefString;
-        this.attr.setUserData(CACHED_NODE, this, null);
         setInstanceVariable("@document", xmlDocument);
     }
     

data/ext/java/nokogiri/XmlNode.java

@@ -45,6 +45,7 @@ import java.io.InputStream;
 import java.nio.charset.CharacterCodingException;
 import java.nio.charset.Charset;
 import java.util.ArrayList;
+import java.util.Iterator;
 import java.util.List;
 
 import nokogiri.internals.HtmlDomParserContext;
@@ -808,23 +809,46 @@ public class XmlNode extends RubyObject {
 
     @JRubyMethod(name = {"content", "text", "inner_text"})
     public IRubyObject content(ThreadContext context) {
-        if (content != null && content.isNil()) return content;
+        if (!node.hasChildNodes() && node.getNodeValue() == null &&
+            (node.getNodeType() == Node.TEXT_NODE || node.getNodeType() == Node.CDATA_SECTION_NODE))
+          return context.nil;
         String textContent;
-        if (content != null) textContent = rubyStringToString(content);
-        else if (this instanceof XmlDocument) {
+        if (this instanceof XmlDocument) {
             Node node = ((Document)this.node).getDocumentElement();
             if (node == null) {
                 textContent = "";
             } else {
-                textContent = ((Document)this.node).getDocumentElement().getTextContent();
+                Node documentElement = ((Document)this.node).getDocumentElement();
+                StringBuffer buffer = new StringBuffer();
+                getTextContentRecursively(context, buffer, documentElement);
+                textContent = buffer.toString();
             }
         } else {
-            textContent = this.node.getTextContent();
+            StringBuffer buffer = new StringBuffer();
+            getTextContentRecursively(context, buffer, node);
+            textContent = buffer.toString();
         }
-        textContent = NokogiriHelpers.convertEncodingByNKFIfNecessary(context.getRuntime(), (XmlDocument)document(context), textContent);
-        String decodedText = null;
-        if (textContent != null) decodedText = NokogiriHelpers.decodeJavaString(textContent);
-        return stringOrNil(context.getRuntime(), decodedText);
+        NokogiriHelpers.convertEncodingByNKFIfNecessary(context.getRuntime(), (XmlDocument)document(context), textContent);
+        return stringOrNil(context.getRuntime(), textContent);
+    }
+
+    private void getTextContentRecursively(ThreadContext context, StringBuffer buffer, Node currentNode) {
+      String textContent = currentNode.getNodeValue();
+      if (textContent != null && NokogiriHelpers.shouldDecode(currentNode))
+        textContent = NokogiriHelpers.decodeJavaString(textContent);
+      if (textContent != null)
+        buffer.append(textContent);
+      NodeList children = currentNode.getChildNodes();
+      for (int i = 0; i < children.getLength(); i++) {
+        Node child = children.item(i);
+        if (hasTextContent(child))
+          getTextContentRecursively(context, buffer, child);
+      }
+    }
+
+    private boolean hasTextContent(Node child) {
+      return child.getNodeType() != Node.COMMENT_NODE &&
+          child.getNodeType() != Node.PROCESSING_INSTRUCTION_NODE;
     }
 
     @JRubyMethod
@@ -892,9 +916,7 @@ public class XmlNode extends RubyObject {
             String key = rubyStringToString(rbkey);
             Element element = (Element) node;
             String value = element.getAttribute(key);
-            if (value != null) {
-                return context.getRuntime().newString(value);
-            }
+            return nonEmptyStringOrNil(context.getRuntime(), value);
         }
         return context.getRuntime().getNil();
     }
@@ -1004,7 +1026,7 @@ public class XmlNode extends RubyObject {
         NokogiriNamespaceCache nsCache = xmlDocument.getNamespaceCache();
         String prefix = node.getPrefix();
         XmlNamespace namespace = nsCache.get(prefix == null ? "" : prefix, node.getNamespaceURI());
-        if (namespace == null || ((XmlNamespace) namespace).isEmpty()) {
+        if (namespace == null || namespace.isEmpty()) {
             return context.getRuntime().getNil();
         }
 
@@ -1027,10 +1049,10 @@ public class XmlNode extends RubyObject {
         if (doc instanceof HtmlDocument) return namespace_definitions;
         List<XmlNamespace> namespaces = ((XmlDocument)doc).getNamespaceCache().get(node);
         for (XmlNamespace namespace : namespaces) {
-            ((RubyArray)namespace_definitions).append(namespace);
+            namespace_definitions.append(namespace);
         }
 
-        return (RubyArray) namespace_definitions;
+        return namespace_definitions;
     }
 
     /**
@@ -1060,12 +1082,13 @@ public class XmlNode extends RubyObject {
     }
 
     protected void setContent(IRubyObject content) {
-        this.content = content;
         String javaContent = rubyStringToString(content);
         node.setTextContent(javaContent);
         if (javaContent.length() == 0) return;
         if (node.getNodeType() == Node.TEXT_NODE || node.getNodeType() == Node.CDATA_SECTION_NODE) return;
-        node.getFirstChild().setUserData(NokogiriHelpers.ENCODED_STRING, true, null);
+        if (node.getFirstChild() != null) {
+            node.getFirstChild().setUserData(NokogiriHelpers.ENCODED_STRING, true, null);
+        }
     }
 
     private void setContent(String content) {
@@ -1073,7 +1096,7 @@ public class XmlNode extends RubyObject {
         this.content = null;    // clear cache
     }
 
-    @JRubyMethod(name = "native_content=", visibility = Visibility.PRIVATE)
+    @JRubyMethod(name = "native_content=")
     public IRubyObject native_content_set(ThreadContext context, IRubyObject content) {
         setContent(content);
         return content;
@@ -1162,13 +1185,42 @@ public class XmlNode extends RubyObject {
             String key = rubyStringToString(rbkey);
             String val = rubyStringToString(rbval);
             Element element = (Element) node;
-            element.setAttribute(key, val);
+
+            int colonIndex = key.indexOf(":");
+            if (colonIndex > 0) {
+              String prefix = key.substring(0, colonIndex);
+              String uri = null;
+              if (prefix.equals("xml")) {
+                uri = "http://www.w3.org/XML/1998/namespace";
+              } else {
+                uri = findNamespaceHref(context, prefix);
+              }
+              element.setAttributeNS(uri, key, val);
+            } else {
+              element.setAttribute(key, val);
+            }
             return this;
         } else {
             return rbval;
         }
     }
 
+    private String findNamespaceHref(ThreadContext context, String prefix) {
+      XmlNode currentNode = this;
+      while(currentNode != document(context)) {
+        RubyArray namespaces = (RubyArray) currentNode.namespace_scopes(context);
+        Iterator iterator = namespaces.iterator();
+        while(iterator.hasNext()) {
+          XmlNamespace namespace = (XmlNamespace) iterator.next();
+          if (namespace.getPrefix().equals(prefix)) {
+            return namespace.getHref();
+          }
+        }
+        currentNode = (XmlNode) currentNode.parent(context);
+      }
+      return null;
+    }
+
     @JRubyMethod
     public IRubyObject parent(ThreadContext context) {
         /*

data/ext/java/nokogiri/XmlText.java

@@ -34,13 +34,11 @@ package nokogiri;
 
 import static nokogiri.internals.NokogiriHelpers.getCachedNodeOrCreate;
 import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
-import static nokogiri.internals.NokogiriHelpers.stringOrNil;
 import nokogiri.internals.SaveContextVisitor;
 
 import org.jruby.Ruby;
 import org.jruby.RubyClass;
 import org.jruby.anno.JRubyClass;
-import org.jruby.anno.JRubyMethod;
 import org.jruby.runtime.ThreadContext;
 import org.jruby.runtime.builtin.IRubyObject;
 import org.w3c.dom.Document;
@@ -88,17 +86,7 @@ public class XmlText extends XmlNode {
         if (name == null) name = context.getRuntime().newString("text");
         return name;
     }
-    
-    @Override
-    @JRubyMethod(name = {"content", "text", "inner_text"})
-    public IRubyObject content(ThreadContext context) {
-        if (content == null || content.isNil()) {
-            return stringOrNil(context.getRuntime(), node.getTextContent());
-        } else {
-            return content;
-        }
-    }
-    
+
     @Override
     public void accept(ThreadContext context, SaveContextVisitor visitor) {
         visitor.enter((Text)node);
@@ -114,6 +102,6 @@ public class XmlText extends XmlNode {
             }
             child = child.getNextSibling();
         }
-        visitor.leave((Text)node);
+        visitor.leave(node);
     }
 }

data/ext/java/nokogiri/internals/NokogiriHandler.java

@@ -73,11 +73,11 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler {
      * TODO: should these be stored in the document 'errors' array?
      * Currently only string messages are stored there.
      */
-    private LinkedList<XmlSyntaxError> errors = new LinkedList<XmlSyntaxError>();
-    
+    private final LinkedList<XmlSyntaxError> errors = new LinkedList<XmlSyntaxError>();
+
     private Locator locator;
-    private ArrayDeque<Integer> lines;
-    private ArrayDeque<Integer> columns;
+    private final ArrayDeque<Integer> lines;
+    private final ArrayDeque<Integer> columns;
     private static String htmlParserName = "Nokogiri::HTML::SAX::Parser";
     private boolean needEmptyAttrCheck = false;
 
@@ -106,6 +106,7 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler {
         call("start_document");
     }
 
+    @Override
     public void xmlDecl(String version, String encoding, String standalone) {
         call("xmldecl", stringOrNil(ruby, version),
              stringOrNil(ruby, encoding),
@@ -117,6 +118,11 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler {
         call("end_document");
     }
 
+    @Override
+    public void processingInstruction(String target, String data) {
+      call("processing_instruction", ruby.newString(target), ruby.newString(data));
+    }
+
     /*
      * This has to call either "start_element" or
      * "start_element_namespace" depending on whether there are any