nokogiri-backport 1.11.0

data/ext/java/nokogiri/internals/SchemaErrorHandler.java

@@ -0,0 +1,73 @@
+/**
+ * (The MIT License)
+ *
+ * Copyright (c) 2008 - 2011:
+ *
+ * * {Aaron Patterson}[http://tenderlovemaking.com]
+ * * {Mike Dalessio}[http://mike.daless.io]
+ * * {Charles Nutter}[http://blog.headius.com]
+ * * {Sergio Arbeo}[http://www.serabe.com]
+ * * {Patrick Mahoney}[http://polycrystal.org]
+ * * {Yoko Harada}[http://yokolet.blogspot.com]
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining
+ * a copy of this software and associated documentation files (the
+ * 'Software'), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * 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.
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+package nokogiri.internals;
+
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
+import nokogiri.NokogiriService;
+import nokogiri.XmlSyntaxError;
+
+import org.jruby.Ruby;
+import org.jruby.RubyArray;
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+/**
+ * Error handler for Relax and W3C XML Schema.
+ * 
+ * @author sergio
+ * @author Yoko Harada <yokolet@gmail.com>
+ */
+public class SchemaErrorHandler implements ErrorHandler {
+
+    private final Ruby runtime;
+    final RubyArray errors;
+
+    public SchemaErrorHandler(Ruby ruby, RubyArray array) {
+        this.runtime = ruby;
+        this.errors = array;
+    }
+
+    public void warning(SAXParseException ex) throws SAXException {
+        errors.append( XmlSyntaxError.createWarning(runtime, ex) );
+    }
+
+    public void error(SAXParseException ex) throws SAXException {
+        errors.append( XmlSyntaxError.createError(runtime, ex) );
+    }
+
+    public void fatalError(SAXParseException ex) throws SAXException {
+        throw ex;
+    }
+
+}

data/ext/java/nokogiri/internals/XalanDTMManagerPatch.java

@@ -0,0 +1,168 @@
+/*
+ * Copyright (c) 2017 [Karol Bucek](http://kares.org/)
+ *
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the  "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package nokogiri.internals;
+
+import javax.xml.transform.dom.DOMSource;
+
+import org.apache.xml.dtm.DTM;
+import nokogiri.internals.dom2dtm.DOM2DTM;
+import nokogiri.internals.dom2dtm.DOM2DTMdefaultNamespaceDeclarationNode;
+import org.apache.xml.dtm.DTMWSFilter;
+import org.apache.xml.res.XMLErrorResources;
+import org.apache.xml.res.XMLMessages;
+import org.w3c.dom.Node;
+
+/**
+ * @author kares
+ */
+public final class XalanDTMManagerPatch extends org.apache.xml.dtm.ref.DTMManagerDefault {
+
+    /**
+     * Given a W3C DOM node, try and return a DTM handle.
+     * Note: calling this may be non-optimal, and there is no guarantee that
+     * the node will be found in any particular DTM.
+     *
+     * @param node Non-null reference to a DOM node.
+     *
+     * @return a valid DTM handle.
+     */
+    @Override
+    public /* synchronized */ int getDTMHandleFromNode(org.w3c.dom.Node node) {
+        //if (node == null) // "node must be non-null for getDTMHandleFromNode!");
+        //    throw new IllegalArgumentException(XMLMessages.createXMLMessage(XMLErrorResources.ER_NODE_NON_NULL, null));
+        assert node != null;
+
+        if (node instanceof org.apache.xml.dtm.ref.DTMNodeProxy) {
+            return ((org.apache.xml.dtm.ref.DTMNodeProxy) node).getDTMNodeNumber();
+        }
+
+        // Find the DOM2DTMs wrapped around this Document (if any)
+        // and check whether they contain the Node in question.
+        //
+        // NOTE that since a DOM2DTM may represent a subtree rather
+        // than a full document, we have to be prepared to check more
+        // than one -- and there is no guarantee that we will find
+        // one that contains ancestors or siblings of the node we're
+        // seeking.
+        //
+        // %REVIEW% We could search for the one which contains this
+        // node at the deepest level, and thus covers the widest
+        // subtree, but that's going to entail additional work
+        // checking more DTMs... and getHandleOfNode is not a
+        // cheap operation in most implementations.
+        //
+        // TODO: %REVIEW% If overflow addressing, we may recheck a DTM
+        // already examined. Ouch. But with the increased number of DTMs,
+        // scanning back to check this is painful.
+        // POSSIBLE SOLUTIONS:
+        //   Generate a list of _unique_ DTM objects?
+        //   Have each DTM cache last DOM node search?
+        for(int i = 0; i < m_dtms.length; i++) {
+            DTM thisDTM = m_dtms[i];
+            if (thisDTM instanceof DOM2DTM) {
+                int handle = ((DOM2DTM) thisDTM).getHandleOfNode(node);
+                if (handle != DTM.NULL) {
+                    return handle;
+                }
+            }
+        }
+
+        // Not found; generate a new DTM.
+        //
+        // %REVIEW% Is this really desirable, or should we return null
+        // and make folks explicitly instantiate from a DOMSource? The
+        // latter is more work but gives the caller the opportunity to
+        // explicitly add the DTM to a DTMManager... and thus to know when
+        // it can be discarded again, which is something we need to pay much
+        // more attention to. (Especially since only DTMs which are assigned
+        // to a manager can use the overflow addressing scheme.)
+        //
+        // %BUG% If the source node was a DOM2DTM$defaultNamespaceDeclarationNode
+        // and the DTM wasn't registered with this DTMManager, we will create
+        // a new DTM and _still_ not be able to find the node (since it will
+        // be resynthesized). Another reason to push hard on making all DTMs
+        // be managed DTMs.
+
+        // Since the real root of our tree may be a DocumentFragment, we need to
+        // use getParent to find the root, instead of getOwnerDocument.  Otherwise
+        // DOM2DTM#getHandleOfNode will be very unhappy.
+        Node root = node; int rootType = root.getNodeType();
+        Node p = (rootType == Node.ATTRIBUTE_NODE) ? ((org.w3c.dom.Attr) root).getOwnerElement() : root.getParentNode();
+        for (; p != null; p = p.getParentNode()) root = p;
+
+        // DOM2DTM dtm = (DOM2DTM) getDTM(new DOMSource(root), false, null);
+        DOM2DTM dtm = getDTM(new DOMSource(root), false, null/*, true, true*/);
+
+        int handle;
+
+        if (node instanceof org.apache.xml.dtm.ref.dom2dtm.DOM2DTMdefaultNamespaceDeclarationNode
+                || node instanceof DOM2DTMdefaultNamespaceDeclarationNode) {
+            // Can't return the same node since it's unique to a specific DTM,
+            // but can return the equivalent node -- find the corresponding
+            // Document Element, then ask it for the xml: namespace decl.
+            handle = dtm.getHandleOfNode(((org.w3c.dom.Attr) node).getOwnerElement());
+            handle = dtm.getAttributeNode(handle, node.getNamespaceURI(), node.getLocalName());
+        }
+        else {
+            handle = dtm.getHandleOfNode(node);
+
+            rootType = root.getNodeType();
+            // Is Node actually within the same document? If not, don't search!
+            // This would be easier if m_root was always the Document node, but
+            // we decided to allow wrapping a DTM around a subtree.
+            if((root==node) ||
+                (rootType==Node.DOCUMENT_NODE && root==node.getOwnerDocument()) ||
+                (rootType!=Node.DOCUMENT_NODE && root.getOwnerDocument()==node.getOwnerDocument())
+                )
+            {
+                // If node _is_ in m_root's tree, find its handle
+                //
+                // %OPT% This check may be improved significantly when DOM
+                // Level 3 nodeKey and relative-order tests become
+                // available!
+                for (Node cursor = node; cursor != null;
+                    cursor = (cursor.getNodeType()!=Node.ATTRIBUTE_NODE)
+                            ? cursor.getParentNode()
+                            : ((org.w3c.dom.Attr)cursor).getOwnerElement()) {
+                    if (cursor==root) {
+                        // We know this node; find its handle.
+                        return (dtm).getHandleFromNode(node);
+                    }
+                } // for ancestors of node
+            } // if node and m_root in same Document
+        }
+
+        if (DTM.NULL == handle)
+            throw new RuntimeException(XMLMessages.createXMLMessage(XMLErrorResources.ER_COULD_NOT_RESOLVE_NODE, null)); //"Could not resolve the node to a handle!");
+
+        return handle;
+    }
+
+    private DOM2DTM getDTM(DOMSource source, boolean unique, DTMWSFilter whiteSpaceFilter/*, boolean incremental, boolean doIndexing*/) {
+        int dtmPos = getFirstFreeDTMID();
+        int documentID = dtmPos << IDENT_DTM_NODE_BITS;
+
+        DOM2DTM dtm = new DOM2DTM(this, source, documentID, whiteSpaceFilter, m_xsf, true);
+
+        addDTM(dtm, dtmPos, 0);
+        return dtm;
+    }
+
+}

data/ext/java/nokogiri/internals/XmlDeclHandler.java

@@ -0,0 +1,42 @@
+/**
+ * (The MIT License)
+ *
+ * Copyright (c) 2008 - 2012:
+ *
+ * * {Aaron Patterson}[http://tenderlovemaking.com]
+ * * {Mike Dalessio}[http://mike.daless.io]
+ * * {Charles Nutter}[http://blog.headius.com]
+ * * {Sergio Arbeo}[http://www.serabe.com]
+ * * {Patrick Mahoney}[http://polycrystal.org]
+ * * {Yoko Harada}[http://yokolet.blogspot.com]
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining
+ * a copy of this software and associated documentation files (the
+ * 'Software'), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * 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.
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+package nokogiri.internals;
+
+/**
+ * Interface for receiving xmlDecl information.
+ *
+ * @author Patrick Mahoney <pat@polycrystal.org>
+ */
+public interface XmlDeclHandler {
+    public void xmlDecl(String version, String encoding, String standalone);
+}

data/ext/java/nokogiri/internals/XmlDomParserContext.java

@@ -0,0 +1,274 @@
+/**
+ * (The MIT License)
+ *
+ * Copyright (c) 2008 - 2012:
+ *
+ * * {Aaron Patterson}[http://tenderlovemaking.com]
+ * * {Mike Dalessio}[http://mike.daless.io]
+ * * {Charles Nutter}[http://blog.headius.com]
+ * * {Sergio Arbeo}[http://www.serabe.com]
+ * * {Patrick Mahoney}[http://polycrystal.org]
+ * * {Yoko Harada}[http://yokolet.blogspot.com]
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining
+ * a copy of this software and associated documentation files (the
+ * 'Software'), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * 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.
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+package nokogiri.internals;
+
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
+import static nokogiri.internals.NokogiriHelpers.isBlank;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.xerces.parsers.DOMParser;
+import org.jruby.Ruby;
+import org.jruby.RubyArray;
+import org.jruby.RubyClass;
+import org.jruby.RubyFixnum;
+import org.jruby.exceptions.RaiseException;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.builtin.IRubyObject;
+import org.w3c.dom.Document;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
+import org.xml.sax.SAXException;
+
+import nokogiri.NokogiriService;
+import nokogiri.XmlDocument;
+import nokogiri.XmlDtd;
+import nokogiri.XmlSyntaxError;
+
+/**
+ * Parser class for XML DOM processing. This class actually parses XML document
+ * and creates DOM tree in Java side. However, DOM tree in Ruby side is not since
+ * we delay creating objects for performance.
+ *  
+ * @author sergio
+ * @author Yoko Harada <yokolet@gmail.com>
+ */
+public class XmlDomParserContext extends ParserContext {
+
+    protected static final String FEATURE_LOAD_EXTERNAL_DTD =
+        "http://apache.org/xml/features/nonvalidating/load-external-dtd";
+    protected static final String FEATURE_LOAD_DTD_GRAMMAR =
+        "http://apache.org/xml/features/nonvalidating/load-dtd-grammar";
+    protected static final String FEATURE_INCLUDE_IGNORABLE_WHITESPACE =
+        "http://apache.org/xml/features/dom/include-ignorable-whitespace";
+    protected static final String CONTINUE_AFTER_FATAL_ERROR =
+        "http://apache.org/xml/features/continue-after-fatal-error";
+    protected static final String FEATURE_NOT_EXPAND_ENTITY =
+        "http://apache.org/xml/features/dom/create-entity-ref-nodes";
+    protected static final String FEATURE_VALIDATION = "http://xml.org/sax/features/validation";
+    private static final String XINCLUDE_FEATURE_ID = "http://apache.org/xml/features/xinclude";
+    private static final String SECURITY_MANAGER = "http://apache.org/xml/properties/security-manager";
+
+    protected ParserContext.Options options;
+    protected DOMParser parser;
+    protected NokogiriErrorHandler errorHandler;
+    protected IRubyObject ruby_encoding;
+
+    public XmlDomParserContext(Ruby runtime, IRubyObject options) {
+        this(runtime, runtime.getNil(), options);
+    }
+    
+    public XmlDomParserContext(Ruby runtime, IRubyObject encoding, IRubyObject options) {
+        super(runtime);
+        this.options = new ParserContext.Options(RubyFixnum.fix2long(options));
+        java_encoding = NokogiriHelpers.getValidEncodingOrNull(encoding);
+        ruby_encoding = encoding;
+        initErrorHandler();
+        initParser(runtime);
+    }
+
+    protected void initErrorHandler() {
+        if (options.recover) {
+            errorHandler = new NokogiriNonStrictErrorHandler(options.noError, options.noWarning);
+        } else {
+            errorHandler = new NokogiriStrictErrorHandler(options.noError, options.noWarning);
+        }
+    }
+
+    protected void initParser(Ruby runtime) {
+        if (options.xInclude) {
+            System.setProperty("org.apache.xerces.xni.parser.XMLParserConfiguration",
+                    "org.apache.xerces.parsers.XIncludeParserConfiguration");
+        }
+
+        parser = new NokogiriDomParser(options);
+        parser.setErrorHandler(errorHandler);
+
+        // Fix for Issue#586.  This limits entity expansion up to 100000 and nodes up to 3000.
+        setProperty(SECURITY_MANAGER, new org.apache.xerces.util.SecurityManager());
+
+        if (options.noBlanks) {
+            setFeature(FEATURE_INCLUDE_IGNORABLE_WHITESPACE, false);
+        }
+
+        if (options.recover) {
+            setFeature(CONTINUE_AFTER_FATAL_ERROR, true);
+        }
+
+        if (options.dtdValid) {
+            setFeature(FEATURE_VALIDATION, true);
+        }
+
+        if (!options.noEnt) {
+          setFeature(FEATURE_NOT_EXPAND_ENTITY, true);
+      }
+        // If we turn off loading of external DTDs complete, we don't
+        // getthe publicID.  Instead of turning off completely, we use
+        // an entity resolver that returns empty documents.
+        if (options.dtdLoad) {
+            setFeature(FEATURE_LOAD_EXTERNAL_DTD, true);
+            setFeature(FEATURE_LOAD_DTD_GRAMMAR, true);
+        }
+        parser.setEntityResolver(new NokogiriEntityResolver(runtime, errorHandler, options));
+    }
+
+    /**
+     * Convenience method that catches and ignores SAXException
+     * (unrecognized and unsupported exceptions).
+     */
+    protected void setFeature(String feature, boolean value) {
+        try {
+            parser.setFeature(feature, value);
+        } catch (SAXException e) {
+            // ignore
+        }
+    }
+
+    /**
+     * Convenience method that catches and ignores SAXException
+     * (unrecognized and unsupported exceptions).
+     */
+    protected void setProperty(String property, Object value) {
+        try {
+            parser.setProperty(property, value);
+        } catch (SAXException e) {
+            // ignore
+        }
+    }
+
+    public void addErrorsIfNecessary(ThreadContext context, XmlDocument doc) {
+        doc.setInstanceVariable("@errors", mapErrors(context, errorHandler));
+    }
+
+
+    public static RubyArray mapErrors(ThreadContext context, NokogiriErrorHandler errorHandler) {
+        final Ruby runtime = context.runtime;
+        final List<Exception> errors = errorHandler.getErrors();
+        final IRubyObject[] errorsAry = new IRubyObject[errors.size()];
+        for (int i = 0; i < errors.size(); i++) {
+            XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(runtime);
+            xmlSyntaxError.setException(errors.get(i));
+            errorsAry[i] = xmlSyntaxError;
+        }
+        return runtime.newArrayNoCopy(errorsAry);
+    }
+
+    public XmlDocument getDocumentWithErrorsOrRaiseException(ThreadContext context, RubyClass klazz, Exception ex) {
+        if (options.recover) {
+            XmlDocument xmlDocument = getInterruptedOrNewXmlDocument(context, klazz);
+            this.addErrorsIfNecessary(context, xmlDocument);
+            XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
+            xmlSyntaxError.setException(ex);
+            ((RubyArray) xmlDocument.getInstanceVariable("@errors")).append(xmlSyntaxError);
+            return xmlDocument;
+        } else {
+            XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
+            xmlSyntaxError.setException(ex);
+            throw xmlSyntaxError.toThrowable();
+        }
+    }
+    
+    private XmlDocument getInterruptedOrNewXmlDocument(ThreadContext context, RubyClass klass) {
+        Document document = parser.getDocument();
+        XmlDocument xmlDocument = new XmlDocument(context.runtime, klass, document);
+        xmlDocument.setEncoding(ruby_encoding);
+        return xmlDocument;
+    }
+
+    /**
+     * This method is broken out so that HtmlDomParserContext can
+     * override it.
+     */
+    protected XmlDocument wrapDocument(ThreadContext context, RubyClass klass, Document doc) {
+        XmlDocument xmlDocument = new XmlDocument(context.runtime, klass, doc);
+        xmlDocument.setEncoding(ruby_encoding);
+
+        if (options.dtdLoad) {
+            IRubyObject dtd = XmlDtd.newFromExternalSubset(context.runtime, doc);
+            if (!dtd.isNil()) {
+                doc.setUserData(XmlDocument.DTD_EXTERNAL_SUBSET, (XmlDtd) dtd, null);
+            }
+        }
+        return xmlDocument;
+    }
+
+    /**
+     * Must call setInputSource() before this method.
+     */
+    public XmlDocument parse(ThreadContext context, RubyClass klass, IRubyObject url) {
+        XmlDocument xmlDoc;
+        try {
+            Document doc = do_parse();
+            xmlDoc = wrapDocument(context, klass, doc);
+            xmlDoc.setUrl(url);
+            addErrorsIfNecessary(context, xmlDoc);
+            return xmlDoc;
+        } catch (SAXException e) {
+            return getDocumentWithErrorsOrRaiseException(context, klass, e);
+        } catch (IOException e) {
+            return getDocumentWithErrorsOrRaiseException(context, klass, e);
+        }
+    }
+
+    protected Document do_parse() throws SAXException, IOException {
+        try {
+          parser.parse(getInputSource());
+        } catch (NullPointerException ex) {
+          // FIXME: this is really a hack to fix #838. Xerces will throw a NullPointerException
+          // if we tried to parse '<? ?>'. We should submit a patch to Xerces.
+        }
+        if (options.noBlanks) {
+            List<Node> emptyNodes = new ArrayList<Node>();
+            findEmptyTexts(parser.getDocument(), emptyNodes);
+            if (emptyNodes.size() > 0) {
+                for (Node node : emptyNodes) {
+                    node.getParentNode().removeChild(node);
+                }
+            }
+        }
+        return parser.getDocument();
+    }
+    
+    private static void findEmptyTexts(Node node, List<Node> emptyNodes) {
+        if (node.getNodeType() == Node.TEXT_NODE && isBlank(node.getTextContent())) {
+            emptyNodes.add(node);
+        } else {
+            NodeList children = node.getChildNodes();
+            for (int i=0; i < children.getLength(); i++) {
+                findEmptyTexts(children.item(i), emptyNodes);
+            }
+        }
+    }
+}

data/ext/java/nokogiri/internals/XmlSaxParser.java

@@ -0,0 +1,65 @@
+/**
+ * (The MIT License)
+ *
+ * Copyright (c) 2008 - 2011:
+ *
+ * * {Aaron Patterson}[http://tenderlovemaking.com]
+ * * {Mike Dalessio}[http://mike.daless.io]
+ * * {Charles Nutter}[http://blog.headius.com]
+ * * {Sergio Arbeo}[http://www.serabe.com]
+ * * {Patrick Mahoney}[http://polycrystal.org]
+ * * {Yoko Harada}[http://yokolet.blogspot.com]
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining
+ * a copy of this software and associated documentation files (the
+ * 'Software'), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * 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.
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+package nokogiri.internals;
+
+import org.apache.xerces.parsers.SAXParser;
+import org.apache.xerces.xni.Augmentations;
+import org.apache.xerces.xni.XNIException;
+
+/**
+ * Extends SAXParser in order to receive xmlDecl events and pass them
+ * on to a handler.
+ *
+ * @author Patrick Mahoney <pat@polycrystal.org>
+ */
+public class XmlSaxParser extends SAXParser {
+
+    protected XmlDeclHandler xmlDeclHandler = null;
+
+    public XmlSaxParser() {
+        super();
+    }
+
+    public void setXmlDeclHandler(XmlDeclHandler xmlDeclHandler) {
+        this.xmlDeclHandler = xmlDeclHandler;
+    }
+
+    @Override
+    public void xmlDecl(String version, String encoding, String standalone,
+                        Augmentations augs) throws XNIException {
+        super.xmlDecl(version, encoding, standalone, augs);
+        if (xmlDeclHandler != null) {
+            xmlDeclHandler.xmlDecl(version, encoding, standalone);
+        }
+    }
+}