nokogiri 1.16.8-java → 1.17.0-java

data/ext/java/nokogiri/XmlNode.java

@@ -287,7 +287,7 @@ public class XmlNode extends RubyObject
    * args but not for an exact number.  Any extra args will then be
    * passed to 'initialize'.  The way 'new' and this 'init' function
    * interact means that subclasses cannot arbitrarily change the
-   * require aruments by defining an 'initialize' method.  This is
+   * require arguments by defining an 'initialize' method.  This is
    * how the C libxml wrapper works also.
    *
    * As written it performs initialization for a new Element with
@@ -407,7 +407,7 @@ public class XmlNode extends RubyObject
   /**
    * This method should be called after a node has been adopted in a new
    * document. This method will ensure that the node is renamed with the
-   * appriopriate NS uri. First the prefix of the node is extracted, then is
+   * appropriate NS uri. First the prefix of the node is extracted, then is
    * used to lookup the namespace uri in the new document starting at the
    * current node and traversing the ancestors. If the namespace uri wasn't
    * empty (or null) all children and the node has attributes and/or children
@@ -643,12 +643,22 @@ public class XmlNode extends RubyObject
 
   @JRubyMethod(name = {"attribute", "attr"})
   public IRubyObject
-  attribute(ThreadContext context, IRubyObject name)
+  attribute(ThreadContext context, IRubyObject rbName)
   {
-    NamedNodeMap attrs = this.node.getAttributes();
-    Node attr = attrs.getNamedItem(rubyStringToString(name));
-    if (attr == null) { return context.nil; }
-    return getCachedNodeOrCreate(context.runtime, attr);
+    NamedNodeMap attributes = this.node.getAttributes();
+    String name = rubyStringToString(rbName);
+
+    for (int j = 0 ; j < attributes.getLength() ; j++) {
+      Node attribute = attributes.item(j);
+      String localName = attribute.getLocalName();
+      if (localName == null) {
+        continue;
+      }
+      if (localName.equals(name)) {
+        return getCachedNodeOrCreate(context.runtime, attribute);
+      }
+    }
+    return context.nil;
   }
 
   @JRubyMethod
@@ -966,45 +976,13 @@ public class XmlNode extends RubyObject
     return doc;
   }
 
+  @JRubyMethod(visibility = Visibility.PROTECTED)
   public IRubyObject
-  dup()
-  {
-    return dup_implementation(getMetaClass().getClassRuntime(), true);
-  }
-
-  @JRubyMethod
-  public IRubyObject
-  dup(ThreadContext context)
-  {
-    return dup_implementation(context, true);
-  }
-
-  @JRubyMethod
-  public IRubyObject
-  dup(ThreadContext context, IRubyObject depth)
+  initialize_copy_with_args(ThreadContext context, IRubyObject other, IRubyObject level, IRubyObject _ignored)
   {
-    boolean deep = depth instanceof RubyInteger && RubyFixnum.fix2int(depth) != 0;
-    return dup_implementation(context, deep);
-  }
-
-  protected final IRubyObject
-  dup_implementation(ThreadContext context, boolean deep)
-  {
-    return dup_implementation(context.runtime, deep);
-  }
-
-  protected IRubyObject
-  dup_implementation(Ruby runtime, boolean deep)
-  {
-    XmlNode clone;
-    try {
-      clone = (XmlNode) clone();
-    } catch (CloneNotSupportedException e) {
-      throw runtime.newRuntimeError(e.toString());
-    }
-    Node newNode = node.cloneNode(deep);
-    clone.node = newNode;
-    return clone;
+    boolean deep = level instanceof RubyInteger && RubyFixnum.fix2int(level) != 0;
+    this.node = asXmlNode(context, other).node.cloneNode(deep);
+    return this;
   }
 
   public static RubyString
@@ -1447,11 +1425,12 @@ public class XmlNode extends RubyObject
       }
     }
 
-    if (uri != null) {
-      element.setAttributeNS(uri, key, val);
-    } else {
+    if (colonIndex > 0 && uri == null) {
       element.setAttribute(key, val);
+    } else {
+      element.setAttributeNS(uri, key, val);
     }
+
     clearXpathContext(node);
   }
 

data/ext/java/nokogiri/XmlNodeSet.java

@@ -15,6 +15,7 @@ import org.jruby.RubyRange;
 import org.jruby.anno.JRubyClass;
 import org.jruby.anno.JRubyMethod;
 import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.Visibility;
 import org.jruby.runtime.builtin.IRubyObject;
 import org.w3c.dom.Node;
 import org.w3c.dom.NodeList;
@@ -201,7 +202,6 @@ public class XmlNodeSet extends RubyObject implements NodeList
     return context.nil;
   }
 
-  @JRubyMethod
   public IRubyObject
   dup(ThreadContext context)
   {
@@ -210,6 +210,15 @@ public class XmlNodeSet extends RubyObject implements NodeList
     return dup;
   }
 
+  @JRubyMethod(visibility = Visibility.PROTECTED)
+  public IRubyObject
+  initialize_copy(ThreadContext context, IRubyObject other)
+  {
+    setNodes(getNodes(context, other));
+    initializeFrom(context, (XmlNodeSet)other);
+    return this;
+  }
+
   @JRubyMethod(name = "include?")
   public IRubyObject
   include_p(ThreadContext context, IRubyObject node_or_namespace)

data/ext/java/nokogiri/XmlSaxParserContext.java

@@ -1,10 +1,14 @@
 package nokogiri;
 
 import nokogiri.internals.*;
+import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
+
 import org.apache.xerces.parsers.AbstractSAXParser;
 import org.jruby.Ruby;
 import org.jruby.RubyClass;
+import org.jruby.RubyEncoding;
 import org.jruby.RubyFixnum;
+import org.jruby.RubyString;
 import org.jruby.anno.JRubyClass;
 import org.jruby.anno.JRubyMethod;
 import org.jruby.exceptions.RaiseException;
@@ -14,6 +18,7 @@ import org.jruby.runtime.builtin.IRubyObject;
 import org.xml.sax.SAXException;
 import org.xml.sax.SAXParseException;
 
+import java.io.ByteArrayInputStream;
 import java.io.IOException;
 import java.io.InputStream;
 
@@ -43,7 +48,7 @@ public class XmlSaxParserContext extends ParserContext
 
   protected NokogiriHandler handler;
   protected NokogiriErrorHandler errorHandler;
-  private boolean replaceEntities = true;
+  private boolean replaceEntities = false;
   private boolean recovery = false;
 
   public
@@ -90,16 +95,26 @@ public class XmlSaxParserContext extends ParserContext
    * Create a new parser context that will parse the string
    * <code>data</code>.
    */
-  @JRubyMethod(name = "memory", meta = true)
+  @JRubyMethod(name = "native_memory", meta = true)
   public static IRubyObject
-  parse_memory(ThreadContext context,
-               IRubyObject klazz,
-               IRubyObject data)
+  parse_memory(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
   {
-    final Ruby runtime = context.runtime;
-    XmlSaxParserContext ctx = newInstance(runtime, (RubyClass) klazz);
-    ctx.initialize(runtime);
-    ctx.setStringInputSource(context, data, runtime.getNil());
+    String java_encoding = null;
+    if (encoding != context.runtime.getNil()) {
+      if (!(encoding instanceof RubyEncoding)) {
+        throw context.runtime.newTypeError("encoding must be kind_of Encoding");
+      }
+      java_encoding = ((RubyEncoding)encoding).toString();
+    }
+
+    XmlSaxParserContext ctx = newInstance(context.runtime, (RubyClass) klazz);
+    ctx.initialize(context.runtime);
+    ctx.setStringInputSourceNoEnc(context, data, context.runtime.getNil());
+
+    if (java_encoding != null) {
+      ctx.getInputSource().setEncoding(java_encoding);
+    }
+
     return ctx;
   }
 
@@ -107,16 +122,26 @@ public class XmlSaxParserContext extends ParserContext
    * Create a new parser context that will read from the file
    * <code>data</code> and parse.
    */
-  @JRubyMethod(name = "file", meta = true)
+  @JRubyMethod(name = "native_file", meta = true)
   public static IRubyObject
-  parse_file(ThreadContext context,
-             IRubyObject klazz,
-             IRubyObject data)
+  parse_file(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
   {
-    final Ruby runtime = context.runtime;
-    XmlSaxParserContext ctx = newInstance(runtime, (RubyClass) klazz);
-    ctx.initialize(context.getRuntime());
+    String java_encoding = null;
+    if (encoding != context.runtime.getNil()) {
+      if (!(encoding instanceof RubyEncoding)) {
+        throw context.runtime.newTypeError("encoding must be kind_of Encoding");
+      }
+      java_encoding = ((RubyEncoding)encoding).toString();
+    }
+
+    XmlSaxParserContext ctx = newInstance(context.runtime, (RubyClass) klazz);
+    ctx.initialize(context.runtime);
     ctx.setInputSourceFile(context, data);
+
+    if (java_encoding != null) {
+      ctx.getInputSource().setEncoding(java_encoding);
+    }
+
     return ctx;
   }
 
@@ -126,21 +151,30 @@ public class XmlSaxParserContext extends ParserContext
    *
    * TODO: Currently ignores encoding <code>enc</code>.
    */
-  @JRubyMethod(name = "io", meta = true)
+  @JRubyMethod(name = "native_io", meta = true)
   public static IRubyObject
-  parse_io(ThreadContext context,
-           IRubyObject klazz,
-           IRubyObject data,
-           IRubyObject encoding)
+  parse_io(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
   {
-    // check the type of the unused encoding to match behavior of CRuby
-    if (!(encoding instanceof RubyFixnum)) {
-      throw context.getRuntime().newTypeError("encoding must be kind_of String");
+    if (!invoke(context, data, "respond_to?", context.runtime.newSymbol("read")).isTrue()) {
+      throw context.runtime.newTypeError("argument expected to respond to :read");
     }
-    final Ruby runtime = context.runtime;
-    XmlSaxParserContext ctx = newInstance(runtime, (RubyClass) klazz);
-    ctx.initialize(runtime);
-    ctx.setIOInputSource(context, data, runtime.getNil());
+
+    String java_encoding = null;
+    if (encoding != context.runtime.getNil()) {
+      if (!(encoding instanceof RubyEncoding)) {
+        throw context.runtime.newTypeError("encoding must be kind_of Encoding");
+      }
+      java_encoding = ((RubyEncoding)encoding).toString();
+    }
+
+    XmlSaxParserContext ctx = newInstance(context.runtime, (RubyClass) klazz);
+    ctx.initialize(context.runtime);
+    ctx.setIOInputSource(context, data, context.runtime.getNil());
+
+    if (java_encoding != null) {
+      ctx.getInputSource().setEncoding(java_encoding);
+    }
+
     return ctx;
   }
 
@@ -222,9 +256,12 @@ public class XmlSaxParserContext extends ParserContext
 
     /* TODO: how should we pass in parse options? */
     ParserContext.Options options = defaultParseOptions(context);
+    if (replaceEntities) {
+      options.noEnt = true;
+    }
 
     errorHandler = new NokogiriStrictErrorHandler(runtime, options.noError, options.noWarning);
-    handler = new NokogiriHandler(runtime, handlerRuby, errorHandler);
+    handler = new NokogiriHandler(runtime, handlerRuby, errorHandler, options.noEnt);
 
     preParse(runtime, handlerRuby, handler);
     parser.setContentHandler(handler);
@@ -233,6 +270,7 @@ public class XmlSaxParserContext extends ParserContext
 
     try {
       parser.setProperty("http://xml.org/sax/properties/lexical-handler", handler);
+      parser.setProperty("http://xml.org/sax/properties/declaration-handler", handler);
     } catch (Exception ex) {
       throw runtime.newRuntimeError("Problem while creating XML SAX Parser: " + ex.toString());
     }
@@ -241,16 +279,15 @@ public class XmlSaxParserContext extends ParserContext
       try {
         do_parse();
       } catch (SAXParseException ex) {
-        // A bad document (<foo><bar></foo>) should call the
-        // error handler instead of raising a SAX exception.
-
-        // However, an EMPTY document should raise a RuntimeError.
-        // This is a bit kludgy, but AFAIK SAX doesn't distinguish
-        // between empty and bad whereas Nokogiri does.
+        // An EMPTY document should raise a RuntimeError. This is a bit kludgy, but AFAIK SAX
+        // doesn't distinguish between empty and bad whereas Nokogiri does.
         String message = ex.getMessage();
         if (message != null && message.contains("Premature end of file.") && stringDataSize < 1) {
-          throw runtime.newRuntimeError("couldn't parse document: " + message);
+          throw runtime.newRuntimeError("input string cannot be empty");
         }
+
+        // A bad document (<foo><bar></foo>) should call the
+        // error handler instead of raising a SAX exception.
         handler.error(ex);
       }
     } catch (SAXException ex) {

data/ext/java/nokogiri/XmlSchema.java

@@ -175,19 +175,6 @@ public class XmlSchema extends RubyObject
     return getSchema(context, (RubyClass)klazz, source, parseOptions);
   }
 
-  @JRubyMethod(meta = true, required = 1, optional = 1)
-  public static IRubyObject
-  read_memory(ThreadContext context, IRubyObject klazz, IRubyObject[] args)
-  {
-    IRubyObject content = args[0];
-    IRubyObject parseOptions = null;
-    if (args.length > 1) {
-      parseOptions = args[1];
-    }
-    String data = content.convertToString().asJavaString();
-    return getSchema(context, (RubyClass) klazz, new StreamSource(new StringReader(data)), parseOptions);
-  }
-
   private static IRubyObject
   getSchema(ThreadContext context, RubyClass klazz, Source source, IRubyObject parseOptions)
   {
@@ -215,14 +202,22 @@ public class XmlSchema extends RubyObject
 
     XmlDomParserContext ctx = new XmlDomParserContext(runtime, RubyFixnum.newFixnum(runtime, 1L));
     ctx.setInputSourceFile(context, file);
-    XmlDocument xmlDocument = ctx.parse(context, getNokogiriClass(runtime, "Nokogiri::XML::Document"), context.nil);
-    return validate_document_or_file(context, xmlDocument);
+    try {
+      XmlDocument xmlDocument = ctx.parse(context, getNokogiriClass(runtime, "Nokogiri::XML::Document"), context.nil);
+      return validate_document_or_file(context, xmlDocument);
+    } catch (Exception ex) {
+      RubyArray errors = (RubyArray)context.runtime.newEmptyArray();
+      XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
+      xmlSyntaxError.setException(ex);
+      errors.append(xmlSyntaxError);
+      return errors;
+    }
   }
 
   IRubyObject
   validate_document_or_file(ThreadContext context, XmlDocument xmlDocument)
   {
-    RubyArray<?> errors = (RubyArray) this.getInstanceVariable("@errors");
+    RubyArray errors = context.runtime.newEmptyArray();
     ErrorHandler errorHandler = new SchemaErrorHandler(context.runtime, errors);
     setErrorHandler(errorHandler);
 
@@ -248,6 +243,10 @@ public class XmlSchema extends RubyObject
   protected void
   validate(Document document) throws SAXException, IOException
   {
+    if (document.getDocumentElement() == null) {
+      throw new SAXException("Document is empty");
+    }
+
     DOMSource docSource = new DOMSource(document);
     validator.validate(docSource);
   }

data/ext/java/nokogiri/XsltStylesheet.java

@@ -135,7 +135,7 @@ public class XsltStylesheet extends RubyObject
     XmlDocument xmlDoc = (XmlDocument) args[0];
     ensureDocumentHasNoError(context, xmlDoc);
 
-    Document doc = ((XmlDocument) xmlDoc.dup_implementation(context, true)).getDocument();
+    Document doc = ((XmlDocument)xmlDoc.callMethod(context, "dup", runtime.newFixnum(1))).getDocument();
 
     XsltStylesheet xslt =
       (XsltStylesheet) NokogiriService.XSLT_STYLESHEET_ALLOCATOR.allocate(runtime, (RubyClass)klazz);

data/ext/java/nokogiri/internals/NokogiriBlockingQueueInputStream.java

@@ -87,7 +87,7 @@ public class NokogiriBlockingQueueInputStream extends InputStream
 
   /**
    * 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
+   * threw an exception while doing so, otherwise, there'll be the potential
    * that the read method will block indefinitely.
    */
   @Override

data/ext/java/nokogiri/internals/NokogiriDomParser.java

@@ -66,7 +66,7 @@ public class NokogiriDomParser extends DOMParser
   {
     dtd.reset();
     if (xInclude) {
-      setEntityResolver(new NokogiriXInlcudeEntityResolver(source));
+      setEntityResolver(new NokogiriXIncludeEntityResolver(source));
     }
     super.parse(source);
     Document doc = getDocument();
@@ -77,11 +77,11 @@ public class NokogiriDomParser extends DOMParser
     doc.setUserData(XmlDocument.DTD_RAW_DOCUMENT, dtd.getDocument(), null);
   }
 
-  private static class NokogiriXInlcudeEntityResolver implements org.xml.sax.EntityResolver
+  private static class NokogiriXIncludeEntityResolver implements org.xml.sax.EntityResolver
   {
     InputSource source;
     private
-    NokogiriXInlcudeEntityResolver(InputSource source)
+    NokogiriXIncludeEntityResolver(InputSource source)
     {
       this.source = source;
     }

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

@@ -42,27 +42,26 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
 
   private Locator locator;
   private boolean needEmptyAttrCheck;
+  private boolean replaceEntities;
+  private Set<String> entities = new HashSet<String>();
 
   public
-  NokogiriHandler(Ruby runtime, IRubyObject object, NokogiriErrorHandler errorHandler)
+  NokogiriHandler(Ruby runtime,
+                  IRubyObject object,
+                  NokogiriErrorHandler errorHandler,
+                  boolean replaceEntities)
   {
     assert object != null;
     this.runtime = runtime;
     this.attrClass = (RubyClass) runtime.getClassFromPath("Nokogiri::XML::SAX::Parser::Attribute");
     this.object = object;
     this.errorHandler = errorHandler;
+    this.replaceEntities = replaceEntities;
     charactersBuilder = new StringBuilder();
     String objectName = object.getMetaClass().getName();
     if ("Nokogiri::HTML4::SAX::Parser".equals(objectName)) { needEmptyAttrCheck = true; }
   }
 
-  @Override
-  public void
-  skippedEntity(String skippedEntity)
-  {
-    call("error", runtime.newString("Entity '" + skippedEntity + "' not defined\n"));
-  }
-
   @Override
   public void
   setDocumentLocator(Locator locator)
@@ -88,7 +87,7 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
   public void
   endDocument()
   {
-    populateCharacters();
+    flushCharacters();
     call("end_document");
   }
 
@@ -161,12 +160,12 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
     }
 
     if (localName == null || localName.isEmpty()) { localName = getLocalPart(qName); }
-    populateCharacters();
+    flushCharacters();
     call("start_element_namespace",
          stringOrNil(runtime, localName),
          rubyAttr,
          stringOrNil(runtime, getPrefix(qName)),
-         stringOrNil(runtime, uri),
+         uri.length() > 0 ? stringOrNil(runtime, uri) : runtime.getNil(),
          rubyNSAttr);
   }
 
@@ -204,7 +203,7 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
   public void
   endElement(String uri, String localName, String qName)
   {
-    populateCharacters();
+    flushCharacters();
     call("end_element_namespace",
          stringOrNil(runtime, localName),
          stringOrNil(runtime, getPrefix(qName)),
@@ -218,11 +217,56 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
     charactersBuilder.append(ch, start, length);
   }
 
+  @Override
+  public void
+  externalEntityDecl(java.lang.String name, java.lang.String publicId, java.lang.String systemId)
+  throws SAXException
+  {
+    entities.add(name);
+  }
+
+  @Override
+  public void
+  internalEntityDecl(java.lang.String name, java.lang.String value)
+  throws SAXException
+  {
+    entities.add(name);
+  }
+
+  @Override
+  public void
+  skippedEntity(String name)
+  {
+    call("error", runtime.newString("Entity '" + name + "' not defined\n"));
+    if (!replaceEntities) {
+      call("reference", runtime.newString(name), runtime.getNil());
+    }
+  }
+
+  @Override
+  public void
+  startEntity(String name)
+  {
+    flushCharacters();
+  }
+
+  @Override
+  public void
+  endEntity(String name)
+  {
+    IRubyObject content = charactersBuilder.length() > 0 ? runtime.newString(charactersBuilder.toString()) :
+                          runtime.getNil();
+    if (!replaceEntities && entities.contains(name)) {
+      call("reference", runtime.newString(name), content);
+    }
+    flushCharacters();
+  }
+
   @Override
   public void
   comment(char[] ch, int start, int length)
   {
-    populateCharacters();
+    flushCharacters();
     call("comment", runtime.newString(new String(ch, start, length)));
   }
 
@@ -230,7 +274,7 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
   public void
   startCDATA()
   {
-    populateCharacters();
+    flushCharacters();
   }
 
   @Override
@@ -329,7 +373,7 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
   }
 
   protected void
-  populateCharacters()
+  flushCharacters()
   {
     if (charactersBuilder.length() > 0) {
       call("characters", runtime.newString(charactersBuilder.toString()));

data/ext/java/nokogiri/internals/NokogiriHelpers.java

@@ -724,7 +724,7 @@ public class NokogiriHelpers
   convertEncodingByNKFIfNecessary(ThreadContext context, XmlDocument doc, CharSequence str)
   {
     if (!(doc instanceof Html4Document)) { return str; }
-    String parsed_encoding = ((Html4Document)doc).getPraedEncoding();
+    String parsed_encoding = ((Html4Document)doc).getParsedEncoding();
     if (parsed_encoding == null) { return str; }
     String ruby_encoding = rubyStringToString(doc.getEncoding());
     if (ruby_encoding == null) { return str; }