Nokogiri_precompiled_aarch64_dedshit 1.14.5

data/ext/java/nokogiri/XsltStylesheet.java

@@ -0,0 +1,368 @@
+package nokogiri;
+
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
+import static nokogiri.internals.NokogiriHelpers.stringOrBlank;
+
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+import java.io.PipedReader;
+import java.io.PipedWriter;
+import java.io.StringReader;
+import java.util.Set;
+import java.util.Map;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import javax.xml.transform.OutputKeys;
+import javax.xml.transform.Templates;
+import javax.xml.transform.Transformer;
+import javax.xml.transform.TransformerConfigurationException;
+import javax.xml.transform.TransformerException;
+import javax.xml.transform.TransformerFactory;
+import javax.xml.transform.dom.DOMResult;
+import javax.xml.transform.dom.DOMSource;
+import javax.xml.transform.stream.StreamResult;
+import javax.xml.transform.stream.StreamSource;
+
+import org.apache.xml.serializer.SerializationHandler;
+import org.apache.xml.serializer.Serializer;
+import org.apache.xml.serializer.SerializerFactory;
+
+import org.jruby.Ruby;
+import org.jruby.RubyArray;
+import org.jruby.RubyClass;
+import org.jruby.RubyHash;
+import org.jruby.RubyObject;
+import org.jruby.RubyString;
+import org.jruby.anno.JRubyClass;
+import org.jruby.anno.JRubyMethod;
+import org.jruby.runtime.Helpers;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.builtin.IRubyObject;
+import org.w3c.dom.Document;
+
+import nokogiri.internals.NokogiriXsltErrorListener;
+
+/**
+ * Class for Nokogiri::XSLT::Stylesheet
+ *
+ * @author sergio
+ * @author Yoko Harada <yokolet@gmail.com>
+ */
+@JRubyClass(name = "Nokogiri::XSLT::Stylesheet")
+public class XsltStylesheet extends RubyObject
+{
+  private static final long serialVersionUID = 1L;
+
+  private TransformerFactory factory = null;
+  private Templates sheet = null;
+  private IRubyObject stylesheet = null;
+  private boolean htmlish = false;
+
+  public
+  XsltStylesheet(Ruby ruby, RubyClass rubyClass)
+  {
+    super(ruby, rubyClass);
+  }
+
+  /**
+   * Create and return a copy of this object.
+   *
+   * @return a clone of this object
+   */
+  @Override
+  public Object
+  clone() throws CloneNotSupportedException
+  {
+    return super.clone();
+  }
+
+  private void
+  addParametersToTransformer(ThreadContext context, Transformer transf, IRubyObject parameters)
+  {
+    Ruby runtime = context.getRuntime();
+
+    if (parameters instanceof RubyHash) {
+      setHashParameters(transf, (RubyHash)parameters);
+    } else if (parameters instanceof RubyArray) {
+      setArrayParameters(transf, runtime, (RubyArray)parameters);
+    } else {
+      throw runtime.newTypeError("parameters should be given either Array or Hash");
+    }
+  }
+
+  @SuppressWarnings("unchecked")
+  private void
+  setHashParameters(Transformer transformer, RubyHash hash)
+  {
+    for (Map.Entry<Object, Object> entry : (Set<Map.Entry<Object, Object>>)hash.entrySet()) {
+      transformer.setParameter((String)entry.getKey(), unparseValue((String)entry.getValue()));
+    }
+  }
+
+  private void
+  setArrayParameters(Transformer transformer, Ruby runtime, RubyArray<?> params)
+  {
+    int limit = params.getLength();
+    if (limit % 2 == 1) { limit--; }
+
+    for (int i = 0; i < limit; i += 2) {
+      String name = params.aref(runtime.newFixnum(i)).asJavaString();
+      String value = params.aref(runtime.newFixnum(i + 1)).asJavaString();
+      transformer.setParameter(name, unparseValue(value));
+    }
+  }
+
+  private static final Pattern QUOTED = Pattern.compile("'.{1,}'");
+
+  private String
+  unparseValue(String orig)
+  {
+    if ((orig.startsWith("\"") && orig.endsWith("\"")) || QUOTED.matcher(orig).matches()) {
+      orig = orig.substring(1, orig.length() - 1);
+    }
+
+    return orig;
+  }
+
+  @JRubyMethod(meta = true, rest = true)
+  public static IRubyObject
+  parse_stylesheet_doc(ThreadContext context, IRubyObject klazz, IRubyObject[] args)
+  {
+
+    Ruby runtime = context.getRuntime();
+
+    ensureFirstArgIsDocument(runtime, args[0]);
+
+    XmlDocument xmlDoc = (XmlDocument) args[0];
+    ensureDocumentHasNoError(context, xmlDoc);
+
+    Document doc = ((XmlDocument) xmlDoc.dup_implementation(context, true)).getDocument();
+
+    XsltStylesheet xslt =
+      (XsltStylesheet) NokogiriService.XSLT_STYLESHEET_ALLOCATOR.allocate(runtime, (RubyClass)klazz);
+
+    try {
+      xslt.init(args[1], doc);
+    } catch (TransformerConfigurationException ex) {
+      throw runtime.newRuntimeError("could not parse xslt stylesheet");
+    }
+
+    return xslt;
+  }
+
+  private void
+  init(IRubyObject stylesheet, Document document) throws TransformerConfigurationException
+  {
+    this.stylesheet = stylesheet;  // either RubyString or RubyFile
+    if (factory == null) { factory = TransformerFactory.newInstance(); }
+    NokogiriXsltErrorListener elistener = new NokogiriXsltErrorListener();
+    factory.setErrorListener(elistener);
+    sheet = factory.newTemplates(new DOMSource(document));
+  }
+
+  private static void
+  ensureFirstArgIsDocument(Ruby runtime, IRubyObject arg)
+  {
+    if (arg instanceof XmlDocument) { return; }
+    throw runtime.newArgumentError("doc must be a Nokogiri::XML::Document instance");
+  }
+
+  private static void
+  ensureDocumentHasNoError(ThreadContext context, XmlDocument xmlDoc)
+  {
+    Ruby runtime = context.getRuntime();
+    RubyArray<?> errors_of_xmlDoc = (RubyArray) xmlDoc.getInstanceVariable("@errors");
+    if (!errors_of_xmlDoc.isEmpty()) {
+      throw runtime.newRuntimeError(errors_of_xmlDoc.first().asString().asJavaString());
+    }
+  }
+
+  @JRubyMethod
+  public IRubyObject
+  serialize(ThreadContext context, IRubyObject doc) throws IOException
+  {
+    XmlDocument xmlDoc = (XmlDocument) doc;
+    ByteArrayOutputStream writer = new ByteArrayOutputStream();
+
+    java.util.Properties props = this.sheet.getOutputProperties();
+    if (props.getProperty(OutputKeys.METHOD) == null) {
+      props.setProperty(OutputKeys.METHOD, org.apache.xml.serializer.Method.UNKNOWN);
+    }
+
+    Serializer serializer = SerializerFactory.getSerializer(props);
+    serializer.setOutputStream(writer);
+    ((SerializationHandler) serializer).serialize(xmlDoc.getNode());
+
+    return context.getRuntime().newString(writer.toString());
+  }
+
+  @JRubyMethod(rest = true, required = 1, optional = 2)
+  public IRubyObject
+  transform(ThreadContext context, IRubyObject[] args)
+  {
+    Ruby runtime = context.getRuntime();
+
+    argumentTypeCheck(runtime, args[0]);
+
+    NokogiriXsltErrorListener elistener = new NokogiriXsltErrorListener();
+    DOMSource domSource = new DOMSource(((XmlDocument) args[0]).getDocument());
+    final DOMResult result;
+    String stringResult = null;
+    try {
+      result = tryXsltTransformation(context, args, domSource, elistener); // DOMResult
+      if (result.getNode().getFirstChild() == null) {
+        stringResult = retryXsltTransformation(context, args, domSource, elistener); // StreamResult
+      }
+    } catch (TransformerConfigurationException ex) {
+      throw runtime.newRuntimeError(ex.getMessage());
+    } catch (TransformerException ex) {
+      throw runtime.newRuntimeError(ex.getMessage());
+    } catch (IOException ex) {
+      throw runtime.newRuntimeError(ex.getMessage());
+    }
+
+    switch (elistener.getErrorType()) {
+      case ERROR:
+      case FATAL:
+        throw runtime.newRuntimeError(elistener.getErrorMessage());
+      case WARNING:
+      default:
+        // no-op
+    }
+
+    if (stringResult == null) {
+      return createDocumentFromDomResult(context, runtime, result);
+    } else {
+      return createDocumentFromString(context, runtime, stringResult);
+    }
+  }
+
+  private DOMResult
+  tryXsltTransformation(ThreadContext context, IRubyObject[] args, DOMSource domSource,
+                        NokogiriXsltErrorListener elistener) throws TransformerException
+  {
+    Transformer transf = sheet.newTransformer();
+    transf.reset();
+    transf.setErrorListener(elistener);
+    if (args.length > 1) {
+      addParametersToTransformer(context, transf, args[1]);
+    }
+
+    DOMResult result = new DOMResult();
+    transf.transform(domSource, result);
+    return result;
+  }
+
+  private String
+  retryXsltTransformation(ThreadContext context,
+                          IRubyObject[] args,
+                          DOMSource domSource,
+                          NokogiriXsltErrorListener elistener)
+  throws TransformerException, IOException
+  {
+    Templates templates = getTemplatesFromStreamSource();
+    Transformer transf = templates.newTransformer();
+    transf.setErrorListener(elistener);
+    if (args.length > 1) {
+      addParametersToTransformer(context, transf, args[1]);
+    }
+    PipedWriter pwriter = new PipedWriter();
+    PipedReader preader = new PipedReader();
+    pwriter.connect(preader);
+    StreamResult result = new StreamResult(pwriter);
+    transf.transform(domSource, result);
+
+    char[] cbuf = new char[1024];
+    int len = preader.read(cbuf, 0, 1024);
+    StringBuilder builder = new StringBuilder(len);
+    builder.append(cbuf, 0, len);
+    htmlish = isHtml(builder); // judge from the first chunk
+
+    while (len == 1024) {
+      len = preader.read(cbuf, 0, 1024);
+      if (len > 0) {
+        builder.append(cbuf, 0, len);
+      }
+    }
+
+    preader.close();
+    pwriter.close();
+
+    return builder.toString();
+  }
+
+  private IRubyObject
+  createDocumentFromDomResult(ThreadContext context, Ruby runtime, DOMResult domResult)
+  {
+    if ("html".equals(domResult.getNode().getFirstChild().getNodeName())) {
+      return new Html4Document(context.runtime, (Document) domResult.getNode());
+    } else {
+      return new XmlDocument(context.runtime, (Document) domResult.getNode());
+    }
+  }
+
+  private Templates
+  getTemplatesFromStreamSource() throws TransformerConfigurationException
+  {
+    if (stylesheet instanceof RubyString) {
+      StringReader reader = new StringReader(stylesheet.asJavaString());
+      StreamSource xsltStreamSource = new StreamSource(reader);
+      return factory.newTemplates(xsltStreamSource);
+    }
+    return null;
+  }
+
+  private static final Pattern HTML_TAG = Pattern.compile("<(%s)*html", Pattern.CASE_INSENSITIVE);
+
+  private static boolean
+  isHtml(CharSequence chunk)
+  {
+    Matcher match = HTML_TAG.matcher(chunk);
+    return match.find();
+  }
+
+  private IRubyObject
+  createDocumentFromString(ThreadContext context, Ruby runtime, String stringResult)
+  {
+    IRubyObject[] args = new IRubyObject[4];
+    args[0] = stringOrBlank(runtime, stringResult);
+    args[1] = runtime.getNil();  // url
+    args[2] = runtime.getNil();  // encoding
+    RubyClass parse_options = (RubyClass)runtime.getClassFromPath("Nokogiri::XML::ParseOptions");
+    if (htmlish) {
+      args[3] = parse_options.getConstant("DEFAULT_HTML");
+      RubyClass htmlDocumentClass = getNokogiriClass(runtime, "Nokogiri::HTML4::Document");
+      return Helpers.invoke(context, htmlDocumentClass, "parse", args);
+    } else {
+      args[3] = parse_options.getConstant("DEFAULT_XML");
+      RubyClass xmlDocumentClass = getNokogiriClass(runtime, "Nokogiri::XML::Document");
+      XmlDocument xmlDocument = (XmlDocument) Helpers.invoke(context, xmlDocumentClass, "parse", args);
+      if (((Document)xmlDocument.getNode()).getDocumentElement() == null) {
+        RubyArray<?> errors = (RubyArray) xmlDocument.getInstanceVariable("@errors");
+        Helpers.invoke(context, errors, "<<", args[0]);
+      }
+      return xmlDocument;
+    }
+  }
+
+  private static void
+  argumentTypeCheck(Ruby runtime, IRubyObject arg)
+  {
+    if (arg instanceof XmlDocument) { return; }
+    throw runtime.newArgumentError("argument must be a Nokogiri::XML::Document");
+  }
+
+  @JRubyMethod(name = {"registr", "register"}, meta = true)
+  public static IRubyObject
+  register(ThreadContext context, IRubyObject cls, IRubyObject uri, IRubyObject receiver)
+  {
+    throw context.getRuntime().newNotImplementedError("Nokogiri::XSLT.register method is not implemented");
+    /* When API conflict is solved, this method should be below:
+    // ThreadContext is used while executing xslt extension function
+    registry.put("context", context);
+    registry.put("receiver", receiver);
+    return context.getRuntime().getNil();
+    */
+  }
+}

data/ext/java/nokogiri/internals/ClosedStreamException.java

@@ -0,0 +1,13 @@
+package nokogiri.internals;
+
+@SuppressWarnings("serial")
+public class ClosedStreamException extends Exception
+{
+
+  public
+  ClosedStreamException(String message)
+  {
+    super(message);
+  }
+
+}

data/ext/java/nokogiri/internals/HtmlDomParserContext.java

@@ -0,0 +1,252 @@
+package nokogiri.internals;
+
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
+import static nokogiri.internals.NokogiriHelpers.isNamespace;
+import static nokogiri.internals.NokogiriHelpers.stringOrNil;
+
+import nokogiri.Html4Document;
+import nokogiri.NokogiriService;
+import nokogiri.XmlDocument;
+import nokogiri.XmlSyntaxError;
+
+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 net.sourceforge.htmlunit.cyberneko.HTMLConfiguration;
+import net.sourceforge.htmlunit.cyberneko.filters.DefaultFilter;
+import org.jruby.Ruby;
+import org.jruby.RubyClass;
+import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.Helpers;
+import org.jruby.runtime.builtin.IRubyObject;
+import org.w3c.dom.Document;
+import org.w3c.dom.NamedNodeMap;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
+
+/**
+ * Parser for Html4Document. This class actually parses Html4Document using NekoHtml.
+ *
+ * @author sergio
+ * @author Patrick Mahoney <pat@polycrystal.org>
+ * @author Yoko Harada <yokolet@gmail.com>
+ */
+public class HtmlDomParserContext extends XmlDomParserContext
+{
+  private static final long serialVersionUID = 1L;
+
+  public
+  HtmlDomParserContext(Ruby runtime, IRubyObject options)
+  {
+    this(runtime, runtime.getNil(), options);
+  }
+
+  public
+  HtmlDomParserContext(Ruby runtime, IRubyObject encoding, IRubyObject options)
+  {
+    super(runtime, encoding, options);
+    java_encoding = NokogiriHelpers.getValidEncoding(encoding);
+  }
+
+  @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);
+  }
+
+  @Override
+  public void
+  setEncoding(String encoding)
+  {
+    super.setEncoding(encoding);
+  }
+
+  /**
+   * 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
+  public XmlDocument
+  parse(ThreadContext context, RubyClass klass, IRubyObject url)
+  {
+    XmlDocument xmlDoc = super.parse(context, klass, url);
+
+    // let's be consistent in how we handle RECOVER and NORECOVER (a.k.a. STRICT)
+    // https://github.com/sparklemotion/nokogiri/issues/2130
+    if (!options.recover && errorHandler.getErrors().size() > 0) {
+      XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
+      String exceptionMsg = String.format("%s: '%s'",
+                                          "Parser without recover option encountered error or warning",
+                                          errorHandler.getErrors().get(0));
+      xmlSyntaxError.setException(new Exception(exceptionMsg));
+      throw xmlSyntaxError.toThrowable();
+    }
+
+    return xmlDoc;
+  }
+
+  @Override
+  protected XmlDocument
+  wrapDocument(ThreadContext context, RubyClass klass, Document document)
+  {
+    Html4Document htmlDocument = new Html4Document(context.runtime, klass, document);
+    htmlDocument.setDocumentNode(context.runtime, document);
+    Helpers.invoke(context, htmlDocument, "initialize");
+
+    if (ruby_encoding.isNil()) {
+      // ruby_encoding might have detected by Html4Document::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.runtime, 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 static String
+  tryGetCharsetFromHtml5MetaTag(Document document)
+  {
+    if (!"html".equalsIgnoreCase(document.getDocumentElement().getNodeName())) { return null; }
+    NodeList list = document.getDocumentElement().getChildNodes();
+    Node item;
+    for (int i = 0; i < list.getLength(); i++) {
+      if ("head".equalsIgnoreCase((item = list.item(i)).getNodeName())) {
+        NodeList headers = item.getChildNodes();
+        for (int j = 0; j < headers.getLength(); j++) {
+          if ("meta".equalsIgnoreCase((item = headers.item(j)).getNodeName())) {
+            NamedNodeMap nodeMap = item.getAttributes();
+            for (int k = 0; k < nodeMap.getLength(); k++) {
+              if ("charset".equalsIgnoreCase((item = nodeMap.item(k)).getNodeName())) {
+                return item.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 static boolean
+    isValid(final String name)
+    {
+      int index = name.charAt(0) - 97;
+      if (index >= element_names.length) { return false; }
+      String[] elementNames = element_names[index];
+      for (int i = 0; i < elementNames.length; i++) {
+        if (name.equals(elementNames[i])) {
+          return true;
+        }
+      }
+      return false;
+    }
+
+    @Override
+    public void
+    startElement(QName name, XMLAttributes attrs, Augmentations augs) throws XNIException
+    {
+      if (!isValid(name.rawname)) {
+        errorHandler.addError(new Exception("Tag " + name.rawname + " invalid"));
+      }
+      super.startElement(name, attrs, augs);
+    }
+  }
+}

data/ext/java/nokogiri/internals/IgnoreSchemaErrorsErrorHandler.java

@@ -0,0 +1,27 @@
+package nokogiri.internals;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+public class IgnoreSchemaErrorsErrorHandler implements ErrorHandler
+{
+
+  @Override
+  public void
+  warning(SAXParseException exception) throws SAXException
+  {
+  }
+
+  @Override
+  public void
+  error(SAXParseException exception) throws SAXException
+  {
+  }
+
+  @Override
+  public void
+  fatalError(SAXParseException exception) throws SAXException
+  {
+  }
+}