nokogiri 1.11.0.rc1-java → 1.11.2-java

data/ext/java/nokogiri/HtmlDocument.java

@@ -17,10 +17,10 @@
  * distribute, sublicense, and/or sell copies of the Software, and to
  * permit persons to whom the Software is furnished to do so, subject to
  * the following conditions:
- * 
+ *
  * The above copyright notice and this permission notice shall be
  * included in all copies or substantial portions of the Software.
- * 
+ *
  * THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
@@ -55,124 +55,147 @@ import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
  * @author sergio
  * @author Yoko Harada <yokolet@gmail.com>
  */
-@JRubyClass(name="Nokogiri::HTML::Document", parent="Nokogiri::XML::Document")
-public class HtmlDocument extends XmlDocument {
-    private static final String DEFAULT_CONTENT_TYPE = "html";
-    private static final String DEFAULT_PUBLIC_ID = "-//W3C//DTD HTML 4.01//EN";
-    private static final String DEFAULT_SYTEM_ID = "http://www.w3.org/TR/html4/strict.dtd";
-
-    private String parsed_encoding = null;
-
-    public HtmlDocument(Ruby ruby, RubyClass klazz) {
-        super(ruby, klazz);
-    }
-
-    public HtmlDocument(Ruby runtime, Document document) {
-        this(runtime, getNokogiriClass(runtime, "Nokogiri::XML::Document"), document);
+@JRubyClass(name = "Nokogiri::HTML::Document", parent = "Nokogiri::XML::Document")
+public class HtmlDocument extends XmlDocument
+{
+  private static final String DEFAULT_CONTENT_TYPE = "html";
+  private static final String DEFAULT_PUBLIC_ID = "-//W3C//DTD HTML 4.01//EN";
+  private static final String DEFAULT_SYTEM_ID = "http://www.w3.org/TR/html4/strict.dtd";
+
+  private String parsed_encoding = null;
+
+  public
+  HtmlDocument(Ruby ruby, RubyClass klazz)
+  {
+    super(ruby, klazz);
+  }
+
+  public
+  HtmlDocument(Ruby runtime, Document document)
+  {
+    this(runtime, getNokogiriClass(runtime, "Nokogiri::XML::Document"), document);
+  }
+
+  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 klazz, IRubyObject[] args)
+  {
+    final Ruby runtime = context.runtime;
+    HtmlDocument htmlDocument;
+    try {
+      Document docNode = createNewDocument(runtime);
+      htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(runtime, (RubyClass) klazz);
+      htmlDocument.setDocumentNode(context.runtime, docNode);
+    } catch (Exception ex) {
+      throw asRuntimeError(runtime, "couldn't create document: ", ex);
     }
 
-    public HtmlDocument(Ruby ruby, RubyClass klazz, Document doc) {
-        super(ruby, klazz, doc);
+    Helpers.invoke(context, htmlDocument, "initialize", args);
+
+    return htmlDocument;
+  }
+
+  public IRubyObject
+  getInternalSubset(ThreadContext context)
+  {
+    IRubyObject internalSubset = super.getInternalSubset(context);
+
+    // html documents are expected to have a default internal subset
+    // the default values are the same ones used when the following
+    // feature is turned on
+    // "http://cyberneko.org/html/features/insert-doctype"
+    // the reason we don't turn it on, is because it overrides the document's
+    // declared doctype declaration.
+
+    if (internalSubset.isNil()) {
+      internalSubset = XmlDtd.newEmpty(context.getRuntime(),
+                                       getDocument(),
+                                       context.getRuntime().newString(DEFAULT_CONTENT_TYPE),
+                                       context.getRuntime().newString(DEFAULT_PUBLIC_ID),
+                                       context.getRuntime().newString(DEFAULT_SYTEM_ID));
+      setInternalSubset(internalSubset);
     }
 
-    @JRubyMethod(name="new", meta = true, rest = true, required=0)
-    public static IRubyObject rbNew(ThreadContext context, IRubyObject klazz, IRubyObject[] args) {
-        final Ruby runtime = context.runtime;
-        HtmlDocument htmlDocument;
-        try {
-            Document docNode = createNewDocument(runtime);
-            htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(runtime, (RubyClass) klazz);
-            htmlDocument.setDocumentNode(context.runtime, docNode);
-        } catch (Exception ex) {
-            throw asRuntimeError(runtime, "couldn't create document: ", ex);
-        }
-
-        Helpers.invoke(context, htmlDocument, "initialize", args);
-
-        return htmlDocument;
+    return internalSubset;
+  }
+
+  @Override
+  void
+  init(Ruby runtime, Document document)
+  {
+    stabilizeTextContent(document);
+    document.normalize();
+    setInstanceVariable("@decorators", runtime.getNil());
+    if (document.getDocumentElement() != null) {
+      stabilizeAttrs(document.getDocumentElement());
     }
-
-    public IRubyObject getInternalSubset(ThreadContext context) {
-        IRubyObject internalSubset = super.getInternalSubset(context);
-
-        // html documents are expected to have a default internal subset
-        // the default values are the same ones used when the following
-        // feature is turned on
-        // "http://cyberneko.org/html/features/insert-doctype"
-        // the reason we don't turn it on, is because it overrides the document's
-        // declared doctype declaration.
-
-        if (internalSubset.isNil()) {
-            internalSubset = XmlDtd.newEmpty(context.getRuntime(),
-                                             getDocument(),
-                                             context.getRuntime().newString(DEFAULT_CONTENT_TYPE),
-                                             context.getRuntime().newString(DEFAULT_PUBLIC_ID),
-                                             context.getRuntime().newString(DEFAULT_SYTEM_ID));
-            setInternalSubset(internalSubset);
+  }
+
+  private static void
+  stabilizeAttrs(Node node)
+  {
+    if (node.hasAttributes()) {
+      NamedNodeMap nodeMap = node.getAttributes();
+      for (int i = 0; i < nodeMap.getLength(); i++) {
+        Node n = nodeMap.item(i);
+        if (n instanceof Attr) {
+          stabilizeAttr((Attr) n);
         }
-
-        return internalSubset;
+      }
     }
-
-    @Override
-    void init(Ruby runtime, Document document) {
-        stabilizeTextContent(document);
-        document.normalize();
-        setInstanceVariable("@decorators", runtime.getNil());
-        if (document.getDocumentElement() != null) {
-            stabilizeAttrs(document.getDocumentElement());
-        }
-    }
-
-    private static void stabilizeAttrs(Node node) {
-        if (node.hasAttributes()) {
-            NamedNodeMap nodeMap = node.getAttributes();
-            for (int i=0; i<nodeMap.getLength(); i++) {
-                Node n = nodeMap.item(i);
-                if (n instanceof Attr) {
-                    stabilizeAttr((Attr) n);
-                }
-            }
-        }
-        NodeList children = node.getChildNodes();
-        for (int i=0; i<children.getLength(); i++) {
-            stabilizeAttrs(children.item(i));
-        }
-    }
-    
-    public void setParsedEncoding(String encoding) {
-        parsed_encoding = encoding;
-    }
-    
-    public String getPraedEncoding() {
-        return parsed_encoding;
-    }
-
-    /*
-     * 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, required = 4)
-    public static IRubyObject read_io(ThreadContext context, IRubyObject klass, IRubyObject[] args) {
-        HtmlDomParserContext ctx = new HtmlDomParserContext(context.runtime, args[2], args[3]);
-        ctx.setIOInputSource(context, args[0], args[1]);
-        return ctx.parse(context, (RubyClass) klass, args[1]);
-    }
-
-    /*
-     * 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, required = 4)
-    public static IRubyObject read_memory(ThreadContext context, IRubyObject klass, IRubyObject[] args) {
-        HtmlDomParserContext ctx = new HtmlDomParserContext(context.runtime, args[2], args[3]);
-        ctx.setStringInputSource(context, args[0], args[1]);
-        return ctx.parse(context, (RubyClass) klass, args[1]);
+    NodeList children = node.getChildNodes();
+    for (int i = 0; i < children.getLength(); i++) {
+      stabilizeAttrs(children.item(i));
     }
+  }
+
+  public void
+  setParsedEncoding(String encoding)
+  {
+    parsed_encoding = encoding;
+  }
+
+  public String
+  getPraedEncoding()
+  {
+    return parsed_encoding;
+  }
+
+  /*
+   * 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, required = 4)
+  public static IRubyObject
+  read_io(ThreadContext context, IRubyObject klass, IRubyObject[] args)
+  {
+    HtmlDomParserContext ctx = new HtmlDomParserContext(context.runtime, args[2], args[3]);
+    ctx.setIOInputSource(context, args[0], args[1]);
+    return ctx.parse(context, (RubyClass) klass, args[1]);
+  }
+
+  /*
+   * 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, required = 4)
+  public static IRubyObject
+  read_memory(ThreadContext context, IRubyObject klass, IRubyObject[] args)
+  {
+    HtmlDomParserContext ctx = new HtmlDomParserContext(context.runtime, args[2], args[3]);
+    ctx.setStringInputSource(context, args[0], args[1]);
+    return ctx.parse(context, (RubyClass) klass, args[1]);
+  }
 }

data/ext/java/nokogiri/HtmlElementDescription.java

@@ -17,10 +17,10 @@
  * distribute, sublicense, and/or sell copies of the Software, and to
  * permit persons to whom the Software is furnished to do so, subject to
  * the following conditions:
- * 
+ *
  * The above copyright notice and this permission notice shall be
  * included in all copies or substantial portions of the Software.
- * 
+ *
  * THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
@@ -49,100 +49,117 @@ import org.jruby.runtime.builtin.IRubyObject;
 
 /**
  * Class for Nokogiri::HTML::ElementDescription.
- * 
+ *
  * @author Patrick Mahoney <pat@polycrystal.org>
  */
-@JRubyClass(name="Nokogiri::HTML::ElementDescription")
-public class HtmlElementDescription extends RubyObject {
-
-    /**
-     * Stores memoized hash of element -> list of valid subelements.
-     */
-    static protected Map<Short, List<String>> subElements;
-    static {
-        Map<Short, List<String>> _subElements =
-            new HashMap<Short, List<String>>();
-        subElements = Collections.synchronizedMap(_subElements);
-    }
-
-    protected HTMLElements.Element element;
-
-    public HtmlElementDescription(Ruby runtime, RubyClass rubyClass) {
-        super(runtime, rubyClass);
-    }
-
-    /**
-     * Lookup the list of sub elements of <code>code</code>.  If not
-     * already stored, iterate through all elements to find valid
-     * subelements; save this list and return it.
-     */
-    protected static List<String> findSubElements(HTMLElements.Element elem) {
-        List<String> subs = subElements.get(elem.code);
-
-        if (subs == null) {
-            subs = new ArrayList<String>();
-
-            /*
-             * A bit of a hack.  NekoHtml source code shows that
-             * UNKNOWN is the highest value element.  We cannot access
-             * the list of elements directly because it's protected.
-             */
-            for (short c = 0; c < HTMLElements.UNKNOWN; c++) {
-                HTMLElements.Element maybe_sub =
-                    HTMLElements.getElement(c);
-                if (maybe_sub.isParent(elem)) {
-                    subs.add(maybe_sub.name);
-                }
-            }
-
-            subElements.put(elem.code, subs);
+@JRubyClass(name = "Nokogiri::HTML::ElementDescription")
+public class HtmlElementDescription extends RubyObject
+{
+
+  /**
+   * Stores memoized hash of element -> list of valid subelements.
+   */
+  static protected Map<Short, List<String>> subElements;
+  static
+  {
+    Map<Short, List<String>> _subElements =
+      new HashMap<Short, List<String>>();
+    subElements = Collections.synchronizedMap(_subElements);
+  }
+
+  protected HTMLElements.Element element;
+
+  public
+  HtmlElementDescription(Ruby runtime, RubyClass rubyClass)
+  {
+    super(runtime, rubyClass);
+  }
+
+  /**
+   * Lookup the list of sub elements of <code>code</code>.  If not
+   * already stored, iterate through all elements to find valid
+   * subelements; save this list and return it.
+   */
+  protected static List<String>
+  findSubElements(HTMLElements.Element elem)
+  {
+    List<String> subs = subElements.get(elem.code);
+
+    if (subs == null) {
+      subs = new ArrayList<String>();
+
+      /*
+       * A bit of a hack.  NekoHtml source code shows that
+       * UNKNOWN is the highest value element.  We cannot access
+       * the list of elements directly because it's protected.
+       */
+      for (short c = 0; c < HTMLElements.UNKNOWN; c++) {
+        HTMLElements.Element maybe_sub =
+          HTMLElements.getElement(c);
+        if (maybe_sub.isParent(elem)) {
+          subs.add(maybe_sub.name);
         }
+      }
 
-        return subs;
+      subElements.put(elem.code, subs);
     }
 
-    @JRubyMethod(name="[]", meta=true)
-    public static IRubyObject get(ThreadContext context,
-                                  IRubyObject klazz, IRubyObject name) {
-
-        // nekohtml will return an element even for invalid names, see
-        // http://sourceforge.net/p/nekohtml/code/HEAD/tree/trunk/src/org/cyberneko/html/HTMLElements.java#l514
-        // which breaks `test_fetch_nonexistent'
-        HTMLElements.Element elem = HTMLElements.getElement(name.asJavaString(), HTMLElements.NO_SUCH_ELEMENT);
-        if (elem == HTMLElements.NO_SUCH_ELEMENT)
-            return context.nil;
-
-        HtmlElementDescription desc =
-            new HtmlElementDescription(context.getRuntime(), (RubyClass)klazz);
-        desc.element = elem;
-        return desc;
+    return subs;
+  }
+
+  @JRubyMethod(name = "[]", meta = true)
+  public static IRubyObject
+  get(ThreadContext context,
+      IRubyObject klazz, IRubyObject name)
+  {
+
+    // nekohtml will return an element even for invalid names, see
+    // http://sourceforge.net/p/nekohtml/code/HEAD/tree/trunk/src/org/cyberneko/html/HTMLElements.java#l514
+    // which breaks `test_fetch_nonexistent'
+    HTMLElements.Element elem = HTMLElements.getElement(name.asJavaString(), HTMLElements.NO_SUCH_ELEMENT);
+    if (elem == HTMLElements.NO_SUCH_ELEMENT) {
+      return context.nil;
     }
 
-    @JRubyMethod()
-    public IRubyObject name(ThreadContext context) {
-        return context.getRuntime().newString(element.name.toLowerCase());
+    HtmlElementDescription desc =
+      new HtmlElementDescription(context.getRuntime(), (RubyClass)klazz);
+    desc.element = elem;
+    return desc;
+  }
+
+  @JRubyMethod()
+  public IRubyObject
+  name(ThreadContext context)
+  {
+    return context.getRuntime().newString(element.name.toLowerCase());
+  }
+
+  @JRubyMethod(name = "inline?")
+  public IRubyObject
+  inline_eh(ThreadContext context)
+  {
+    return context.getRuntime().newBoolean(element.isInline());
+  }
+
+  @JRubyMethod(name = "empty?")
+  public IRubyObject
+  empty_eh(ThreadContext context)
+  {
+    return context.getRuntime().newBoolean(element.isEmpty());
+  }
+
+  @JRubyMethod()
+  public IRubyObject
+  sub_elements(ThreadContext context)
+  {
+    Ruby ruby = context.getRuntime();
+    List<String> subs = findSubElements(element);
+    IRubyObject[] ary = new IRubyObject[subs.size()];
+    for (int i = 0; i < subs.size(); ++i) {
+      ary[i] = ruby.newString(subs.get(i));
     }
 
-    @JRubyMethod(name="inline?")
-    public IRubyObject inline_eh(ThreadContext context) {
-        return context.getRuntime().newBoolean(element.isInline());
-    }
-
-    @JRubyMethod(name="empty?")
-    public IRubyObject empty_eh(ThreadContext context) {
-        return context.getRuntime().newBoolean(element.isEmpty());
-    }
-
-    @JRubyMethod()
-    public IRubyObject sub_elements(ThreadContext context) {
-        Ruby ruby = context.getRuntime();
-        List<String> subs = findSubElements(element);
-        IRubyObject[] ary = new IRubyObject[subs.size()];
-        for (int i = 0; i < subs.size(); ++i) {
-            ary[i] = ruby.newString(subs.get(i));
-        }
-
-        return ruby.newArray(ary);
-    }
+    return ruby.newArray(ary);
+  }
 
 }