vtd_xml 0.0.3-java

data/bundle/jruby/1.9/gems/nokogiri-1.6.1-java/ext/java/nokogiri/internals/HtmlDomParserContext.java

@@ -0,0 +1,243 @@
+/**
+ * (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.isNamespace;
+import static nokogiri.internals.NokogiriHelpers.stringOrNil;
+import nokogiri.HtmlDocument;
+import nokogiri.NokogiriService;
+import nokogiri.XmlDocument;
+
+import org.apache.xerces.parsers.DOMParser;
+import org.apache.xerces.xni.Augmentations;
+import org.apache.xerces.xni.QName;
+import org.apache.xerces.xni.XMLAttributes;
+import org.apache.xerces.xni.XNIException;
+import org.apache.xerces.xni.parser.XMLDocumentFilter;
+import org.apache.xerces.xni.parser.XMLParserConfiguration;
+import org.cyberneko.html.HTMLConfiguration;
+import org.cyberneko.html.filters.DefaultFilter;
+import org.jruby.Ruby;
+import org.jruby.RubyClass;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.builtin.IRubyObject;
+import org.w3c.dom.Document;
+import org.w3c.dom.NamedNodeMap;
+import org.w3c.dom.NodeList;
+
+/**
+ * Parser for HtmlDocument. This class actually parses HtmlDocument using NekoHtml.
+ * 
+ * @author sergio
+ * @author Patrick Mahoney <pat@polycrystal.org>
+ * @author Yoko Harada <yokolet@gmail.com>
+ */
+public class HtmlDomParserContext extends XmlDomParserContext {
+
+    public HtmlDomParserContext(Ruby runtime, IRubyObject options) {
+        super(runtime, options);
+    }
+    
+    public HtmlDomParserContext(Ruby runtime, IRubyObject encoding, IRubyObject options) {
+        super(runtime, encoding, options);
+    }
+
+    @Override
+    protected void initErrorHandler() {
+        if (options.strict) {
+            errorHandler = new NokogiriStrictErrorHandler(options.noError, options.noWarning);
+        } else {
+            errorHandler = new NokogiriNonStrictErrorHandler4NekoHtml(options.noError, options.noWarning);
+        }
+    }
+
+    @Override
+    protected void initParser(Ruby runtime) {
+        XMLParserConfiguration config = new HTMLConfiguration();
+        XMLDocumentFilter removeNSAttrsFilter = new RemoveNSAttrsFilter();
+        XMLDocumentFilter elementValidityCheckFilter = new ElementValidityCheckFilter(errorHandler);
+        //XMLDocumentFilter[] filters = { removeNSAttrsFilter,  elementValidityCheckFilter};
+        XMLDocumentFilter[] filters = { elementValidityCheckFilter};
+
+        config.setErrorHandler(this.errorHandler);
+
+        parser = new NokogiriDomParser(config);
+
+        // see http://nekohtml.sourceforge.net/settings.html for details
+        setProperty("http://cyberneko.org/html/properties/default-encoding", java_encoding);
+        setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
+        setProperty("http://cyberneko.org/html/properties/names/attrs", "lower");
+        setProperty("http://cyberneko.org/html/properties/filters", filters);
+        setFeature("http://cyberneko.org/html/features/report-errors", true);
+        setFeature("http://xml.org/sax/features/namespaces", false);
+    }
+
+    /**
+     * Enable NekoHTML feature for balancing tags in a document fragment.
+     * 
+     * This method is used in XmlNode#in_context method.
+     */
+    public void enableDocumentFragment() {
+        setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment", true);
+    }
+
+    @Override
+    protected XmlDocument getNewEmptyDocument(ThreadContext context) {
+        IRubyObject[] args = new IRubyObject[0];
+        return (XmlDocument) XmlDocument.rbNew(context, getNokogiriClass(context.getRuntime(), "Nokogiri::HTML::Document"), args);
+    }
+
+    @Override
+    protected XmlDocument wrapDocument(ThreadContext context,
+                                       RubyClass klazz,
+                                       Document document) {
+        HtmlDocument htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(context.getRuntime(), klazz);
+        htmlDocument.setDocumentNode(context, document);
+        if (ruby_encoding.isNil()) {
+            // ruby_encoding might have detected by HtmlDocument::EncodingReader
+            if (detected_encoding != null && !detected_encoding.isNil()) {
+                ruby_encoding = detected_encoding;
+            } else {
+                // no encoding given & no encoding detected, then try to get it
+                String charset = tryGetCharsetFromHtml5MetaTag(document);
+                ruby_encoding = stringOrNil(context.getRuntime(), charset);
+            }
+        }
+        htmlDocument.setEncoding(ruby_encoding);
+        htmlDocument.setParsedEncoding(java_encoding);
+        return htmlDocument;
+    }
+    
+    // NekoHtml doesn't understand HTML5 meta tag format. This fails to detect charset
+    // from an HTML5 style meta tag. Luckily, the meta tag and charset exists in DOM tree
+    // so, this method attempts to find the charset.
+    private String tryGetCharsetFromHtml5MetaTag(Document document) {
+        if (!"html".equalsIgnoreCase(document.getDocumentElement().getNodeName())) return null;
+        NodeList list = document.getDocumentElement().getChildNodes();
+        for (int i = 0; i < list.getLength(); i++) {
+            if ("head".equalsIgnoreCase(list.item(i).getNodeName())) {
+                NodeList headers = list.item(i).getChildNodes();
+                for (int j = 0; j < headers.getLength(); j++) {
+                    if ("meta".equalsIgnoreCase(headers.item(j).getNodeName())) {
+                        NamedNodeMap nodeMap = headers.item(j).getAttributes();
+                        for (int k = 0; k < nodeMap.getLength(); k++) {
+                            if ("charset".equalsIgnoreCase(nodeMap.item(k).getNodeName())) {
+                                return nodeMap.item(k).getNodeValue();
+                            }
+                        }
+                    }
+                }
+            }
+        }
+        return null;
+    }
+
+    /**
+     * Filter to strip out attributes that pertain to XML namespaces.
+     */
+    public static class RemoveNSAttrsFilter extends DefaultFilter {
+        @Override
+        public void startElement(QName element, XMLAttributes attrs,
+                                 Augmentations augs) throws XNIException {
+            int i;
+            for (i = 0; i < attrs.getLength(); ++i) {
+                if (isNamespace(attrs.getQName(i))) {
+                    attrs.removeAttributeAt(i);
+                    --i;
+                }
+            }
+
+            element.uri = null;
+            super.startElement(element, attrs, augs);
+        }
+    }
+    
+    public static class ElementValidityCheckFilter extends DefaultFilter {
+        private NokogiriErrorHandler errorHandler;
+        
+        private ElementValidityCheckFilter(NokogiriErrorHandler errorHandler) {
+            this.errorHandler = errorHandler;
+        }
+        
+        // element names from xhtml1-strict.dtd
+        private static String[][] element_names = {
+                {"a", "abbr", "acronym", "address", "area"},
+                {"b", "base", "basefont", "bdo", "big", "blockquote", "body", "br", "button"},
+                {"caption", "cite", "code", "col", "colgroup"},
+                {"dd", "del", "dfn", "div", "dl", "dt"},
+                {"em"},
+                {"fieldset", "font", "form", "frame", "frameset"},
+                {}, // g
+                {"h1", "h2", "h3", "h4", "h5", "h6", "head", "hr", "html"},
+                {"i", "iframe", "img", "input", "ins"},
+                {}, // j
+                {"kbd"},
+                {"label", "legend", "li", "link"},
+                {"map", "meta"},
+                {"noframes", "noscript"},
+                {"object", "ol", "optgroup", "option"},
+                {"p", "param", "pre"},
+                {"q"},
+                {}, // r
+                {"s", "samp", "script", "select", "small", "span", "strike", "strong", "style", "sub", "sup"},
+                {"table", "tbody", "td", "textarea", "tfoot", "th", "thead", "title", "tr", "tt"},
+                {"u", "ul"},
+                {"var"},
+                {}, // w
+                {}, // x
+                {}, // y
+                {}  // z
+        };
+        
+        private boolean isValid(String testee) {
+            char[] c = testee.toCharArray();
+            int index = new Integer(c[0]) - 97;
+            if (index > 25) return false;
+            for (int i=0; i<element_names[index].length; i++) {
+                if (testee.equals(element_names[index][i])) {
+                    return true;
+                }
+            }
+            return false;
+        }
+        
+        @Override
+        public void startElement(QName name, XMLAttributes attrs, Augmentations augs) throws XNIException {
+            if (!isValid(name.rawname)) {
+                errorHandler.getErrors().add(new Exception("Tag " + name.rawname + " invalid"));
+            }
+            super.startElement(name, attrs, augs);
+        }
+    }
+}

data/bundle/jruby/1.9/gems/nokogiri-1.6.1-java/ext/java/nokogiri/internals/NokogiriBlockingQueueInputStream.java

@@ -0,0 +1,151 @@
+/**
+ *
+ */
+package nokogiri.internals;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.LinkedList;
+import java.util.List;
+import java.util.concurrent.Callable;
+import java.util.concurrent.Future;
+import java.util.concurrent.FutureTask;
+import java.util.concurrent.LinkedBlockingQueue;
+
+import nokogiri.XmlSaxPushParser;
+
+/**
+ * A smart input stream that signals the caller when a chunk of data is consumed
+ * from the stream. The main use of this stream is to synchronize the
+ * {@link XmlSaxPushParser} and the {@link XmlSaxParser} which runs in a
+ * different thread.
+ *
+ * @author John Shahid <jvshahid@gmail.com>
+ */
+public class NokogiriBlockingQueueInputStream extends InputStream {
+  private final LinkedBlockingQueue<Task>  queue;
+  protected Task                           currentTask;
+  protected ByteArrayInputStream           currentStream;
+  protected int                            position;
+  protected boolean                        closed = false;
+
+  public static final ByteArrayInputStream END    = new ByteArrayInputStream(new byte[0]);
+
+  private static class Task extends FutureTask<Void> {
+    private final ByteArrayInputStream stream;
+
+    public Task(ByteArrayInputStream stream) {
+      super(new Callable<Void>() {
+        @Override
+        public Void call() throws Exception {
+          // TODO Auto-generated method stub
+          return null;
+        }
+      });
+      this.stream = stream;
+    }
+
+    public ByteArrayInputStream getStream() {
+      return stream;
+    }
+
+    @Override
+    public void run() {
+      // don't do anything
+    }
+
+    @Override
+    public boolean runAndReset() {
+      // don't do anything
+      return true;
+    }
+
+    @Override
+    public void set(Void v) {
+      super.set(v);
+    }
+  }
+
+  public NokogiriBlockingQueueInputStream() {
+    queue = new LinkedBlockingQueue<Task>();
+  }
+
+  /**
+   * This method shouldn't be called unless the parser has finished parsing or
+   * threw an exception while doing so, otherwise, there'll be the protential
+   * that the read method will block indefinitely.
+   */
+  @Override
+  public synchronized void close() {
+    closed = true;
+    List<Task> tasks = new LinkedList<Task>();
+    queue.drainTo(tasks);
+    tasks.add(currentTask);
+    for (Task task : tasks) {
+      task.set(null);
+    }
+  }
+
+  /**
+   * Add @param stream to the end of the queue of data that will be returned by
+   * {@link #read()} and its variants. The method will @return a future whose
+   * {@link Future#get()} will block until the data in @param stream is read.
+   *
+   * Passing the special stream {@link #END} to this method, will cause
+   * {@link #read()} to return an eof indicator (i.e. -1) to the caller, after
+   * all the data inserted before {@link #END} is processed.
+   *
+   * @return
+   */
+  public synchronized Future<Void> addChunk(ByteArrayInputStream stream) throws ClosedStreamException {
+    if (closed)
+      throw new ClosedStreamException("Cannot add a chunk to a closed stream");
+    Task task = new Task(stream);
+    queue.add(task);
+    return task;
+  }
+
+  /*
+   * (non-Javadoc)
+   *
+   * @see java.io.InputStream#read()
+   */
+  @Override
+  public int read() throws IOException {
+    if (currentTask == null || currentStream.available() == 0)
+      if (getNextTask() == -1)
+        return -1;
+    return currentStream.read();
+  }
+
+  /*
+   * (non-Javadoc)
+   *
+   * @see java.io.InputStream#read(byte[], int, int)
+   */
+  @Override
+  public int read(byte[] bytes, int off, int len) {
+    if (currentTask == null || currentStream.available() == 0) {
+      if (getNextTask() == -1) {
+        currentTask.set(null);
+        return -1;
+      }
+    }
+    return currentStream.read(bytes, off, len);
+  }
+
+  protected int getNextTask() {
+    while (true) {
+      try {
+        if (currentTask != null)
+          currentTask.set(null);
+        currentTask = queue.take();
+        currentStream = currentTask.getStream();
+        return currentStream.available() == 0 ? -1 : currentStream.available();
+      } catch (InterruptedException ex) {
+        // keep retrying to read
+      }
+    }
+  }
+}

data/bundle/jruby/1.9/gems/nokogiri-1.6.1-java/ext/java/nokogiri/internals/NokogiriDocumentCache.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 java.util.Hashtable;
+import nokogiri.XmlDocument;
+import org.w3c.dom.Document;
+
+/**
+ * Currently, this class is not used anywhere.
+ * I'm not sure what for this class was written.(Yoko)
+ * 
+ * @author sergio
+ */
+public class NokogiriDocumentCache {
+
+    private static NokogiriDocumentCache instance;
+    protected Hashtable<Document, XmlDocument> cache;
+
+    private NokogiriDocumentCache() {
+        this.cache = new Hashtable<Document, XmlDocument>();
+    }
+
+    public static NokogiriDocumentCache getInstance() {
+        if(instance == null) {
+            instance = new NokogiriDocumentCache();
+        }
+        return instance;
+    }
+
+    public XmlDocument getXmlDocument(Document doc) {
+        return this.cache.get(doc);
+    }
+
+    public void putDocument(Document doc, XmlDocument xmlDoc) {
+        this.cache.put(doc, xmlDoc);
+    }
+
+    public XmlDocument removeDocument(Document doc) {
+        return this.cache.remove(doc);
+    }
+
+}

data/bundle/jruby/1.9/gems/nokogiri-1.6.1-java/ext/java/nokogiri/internals/NokogiriDomParser.java

@@ -0,0 +1,116 @@
+/**
+ * (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 java.io.IOException;
+
+import nokogiri.XmlDocument;
+
+import org.apache.xerces.parsers.DOMParser;
+import org.apache.xerces.parsers.XIncludeParserConfiguration;
+import org.apache.xerces.xni.parser.XMLParserConfiguration;
+import org.cyberneko.dtd.DTDConfiguration;
+import org.w3c.dom.Document;
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.InputSource;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * Sets up a Xerces/XNI DOM Parser for use with Nokogiri.  Uses
+ * NekoDTD to parse the DTD into a tree of Nodes.
+ *
+ * @author Patrick Mahoney <pat@polycrystal.org>
+ */
+public class NokogiriDomParser extends DOMParser {
+    protected DOMParser dtd;
+    protected boolean xInclude;
+    protected XMLParserConfiguration config;
+
+    public NokogiriDomParser(XMLParserConfiguration config) {
+        super(config);
+        this.config = config;
+        initialize();
+    }
+
+    public NokogiriDomParser(ParserContext.Options options) {
+        xInclude = options.xInclude;
+        initialize();
+    }
+
+    protected void initialize() {
+        if (config == null) {
+            if (xInclude) {
+                config = new XIncludeParserConfiguration();
+            } else {
+                config = getXMLParserConfiguration();
+            }
+        }
+
+        DTDConfiguration dtdConfig = new DTDConfiguration();
+        dtd = new DOMParser(dtdConfig);
+
+        config.setDTDHandler(dtdConfig);
+        config.setDTDContentModelHandler(dtdConfig);
+    }
+
+    @Override
+    public void parse(InputSource source) throws SAXException, IOException {
+        dtd.reset();
+        if (xInclude) {
+            setEntityResolver(new NokogiriXInlcudeEntityResolver(source));
+        }
+        super.parse(source);
+        Document doc = getDocument();
+        if (doc == null)
+            throw new RuntimeException("null document");
+
+        doc.setUserData(XmlDocument.DTD_RAW_DOCUMENT, dtd.getDocument(), null);
+    }
+
+    private class NokogiriXInlcudeEntityResolver implements org.xml.sax.EntityResolver {
+        InputSource source;
+        private NokogiriXInlcudeEntityResolver(InputSource source) {
+            this.source = source;
+        }
+
+        @Override
+        public InputSource resolveEntity(String publicId, String systemId)
+                throws SAXException, IOException {
+            if (systemId != null) source.setSystemId(systemId);
+            if (publicId != null) source.setPublicId(publicId);
+            return source;
+        }
+    }
+}

data/bundle/jruby/1.9/gems/nokogiri-1.6.1-java/ext/java/nokogiri/internals/NokogiriEncodingReaderWrapper.java

@@ -0,0 +1,109 @@
+package nokogiri.internals;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.jruby.Ruby;
+import org.jruby.RubyObject;
+import org.jruby.RubyProcess.Sys;
+import org.jruby.exceptions.RaiseException;
+import org.jruby.javasupport.util.RuntimeHelpers;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.builtin.IRubyObject;
+import org.jruby.util.ByteList;
+
+/**
+ * This class wraps the EncodingReader which act like a rewinding input stream,
+ * it tries to read the first 1K of data to detect the encoding, but save
+ * this data in a buffer for the subsequent read. Unfortunately, the EncodingReader
+ * will behave as expected only if encoding was detected, otherwise, the read data
+ * won't be stored and EncodingReader will fallback to read directory from the io stream.
+ * this is kind of lame, since we need to have similar logic in both layers. The alternative
+ * is to implement the encoding detection similar to the way C-Nokogiri does it; it starts
+ * parsing assuming encoding is unknown and if encoding is detected it will throw an exception
+ * causing parsing to stop, in which case we have to intercept the exception and set the encoding.
+ * Also in this case we don't have to restart the parsing since html/document.rb does that for us.
+ *
+ * @author John Shahid <jvshahid@gmail.com>
+ *
+ */
+public class NokogiriEncodingReaderWrapper extends InputStream {
+  private final ThreadContext context;
+  private final IRubyObject   encodingReader;
+  private final Ruby          ruby;
+  private IRubyObject         detectedEncoding;
+  private final byte[]        firstChunk       = new byte[1024];
+  private int                 firstChunkOff    = 0;
+  private int                 firstChunkLength = 0;
+
+  public NokogiriEncodingReaderWrapper(ThreadContext context, RubyObject encodingReader) {
+    this.context = context;
+    this.encodingReader = encodingReader;
+    this.ruby = context.getRuntime();
+
+    if (!RuntimeHelpers.invoke(context, encodingReader, "respond_to?", ruby.newSymbol("read").to_sym()).isTrue()
+        || encodingReader.getInstanceVariable("@io") == null) {
+      throw ruby.newArgumentError("Argument doesn't respond to read or doesn't have instance variable @io");
+    }
+  }
+
+  public boolean detectEncoding() {
+    try {
+      firstChunkLength = read(firstChunk);
+    } catch (RaiseException e) {
+      detectedEncoding = e.getException().getInstanceVariable("@found_encoding");
+      return true;
+    }
+    detectedEncoding = context.nil;
+    return false;
+  }
+
+  public IRubyObject getEncoding() {
+    return detectedEncoding;
+  }
+
+  @Override
+  public int read(byte b[]) {
+    return read(b, 0, b.length);
+  }
+
+  @Override
+  public int read(byte b[], int off, int len) {
+    if (b == null) {
+      throw new NullPointerException();
+    } else if (off < 0 || len < 0 || len > b.length - off) {
+      throw new IndexOutOfBoundsException();
+    } else if (len == 0) {
+      return 0;
+    }
+
+    int copyLength = Math.min(firstChunkLength - firstChunkOff, len);
+    if (copyLength > 0) {
+      System.arraycopy(firstChunk, firstChunkOff, b, off, copyLength);
+      len -= copyLength;
+      firstChunkOff += copyLength;
+    }
+
+    if (len <= 0)
+      return copyLength;
+
+    IRubyObject returnValue = encodingReader.callMethod(context, "read", ruby.newFixnum(len));
+    if (returnValue.isNil())
+      return -1;
+
+    ByteList bytes = returnValue.asString().getByteList();
+    int length = bytes.length();
+    System.arraycopy(bytes.unsafeBytes(), bytes.getBegin(), b, off + copyLength, length);
+    return length + copyLength;
+  }
+
+  @Override
+  public int read() {
+    byte[] bytes = new byte[1];
+    int count = read(bytes, 0, 1);
+    if (count < 1)
+      return count;
+    return bytes[0];
+  }
+
+}