nokogiri 1.11.7-java → 1.12.0.rc1-java

data/ext/java/nokogiri/XmlSaxPushParser.java

@@ -211,7 +211,7 @@ public class XmlSaxPushParser extends RubyObject
     futureTask = null;
   }
 
-  // SHARED for HtmlSaxPushParser
+  // SHARED for Html4SaxPushParser
   static void
   terminateExecution(final ExecutorService executor, final NokogiriBlockingQueueInputStream stream,
                      final FutureTask<?> futureTask)
@@ -248,7 +248,7 @@ public class XmlSaxPushParser extends RubyObject
       this(context, handler, parse(context.runtime, stream), stream);
     }
 
-    // IMPL with HtmlSaxPushParser
+    // IMPL with Html4SaxPushParser
     protected
     ParserTask(ThreadContext context, IRubyObject handler, XmlSaxParserContext parser, InputStream stream)
     {

data/ext/java/nokogiri/XmlSyntaxError.java

@@ -63,7 +63,7 @@ public class XmlSyntaxError extends RubyException
   public static XmlSyntaxError
   createHTMLSyntaxError(final Ruby runtime)
   {
-    RubyClass klazz = (RubyClass) runtime.getClassFromPath("Nokogiri::HTML::SyntaxError");
+    RubyClass klazz = (RubyClass) runtime.getClassFromPath("Nokogiri::HTML4::SyntaxError");
     return new XmlSyntaxError(runtime, klazz);
   }
 

data/ext/java/nokogiri/XmlXpathContext.java

@@ -203,15 +203,15 @@ public class XmlXpathContext extends RubyObject
     }
 
     switch (xobj.getType()) {
-    case XObject.CLASS_BOOLEAN :
-      return context.runtime.newBoolean(xobj.bool());
-    case XObject.CLASS_NUMBER :
-      return context.runtime.newFloat(xobj.num());
-    case XObject.CLASS_NODESET :
-      IRubyObject[] nodes = nodeListToRubyArray(context.runtime, xobj.nodelist());
-      return XmlNodeSet.newNodeSet(context.runtime, nodes, this.context);
-    default :
-      return context.runtime.newString(xobj.str());
+      case XObject.CLASS_BOOLEAN :
+        return context.runtime.newBoolean(xobj.bool());
+      case XObject.CLASS_NUMBER :
+        return context.runtime.newFloat(xobj.num());
+      case XObject.CLASS_NODESET :
+        IRubyObject[] nodes = nodeListToRubyArray(context.runtime, xobj.nodelist());
+        return XmlNodeSet.newNodeSet(context.runtime, nodes, this.context);
+      default :
+        return context.runtime.newString(xobj.str());
     }
   }
 

data/ext/java/nokogiri/XsltStylesheet.java

@@ -213,12 +213,12 @@ public class XsltStylesheet extends RubyObject
     }
 
     switch (elistener.getErrorType()) {
-    case ERROR:
-    case FATAL:
-      throw runtime.newRuntimeError(elistener.getErrorMessage());
-    case WARNING:
-    default:
-      // no-op
+      case ERROR:
+      case FATAL:
+        throw runtime.newRuntimeError(elistener.getErrorMessage());
+      case WARNING:
+      default:
+        // no-op
     }
 
     if (stringResult == null) {
@@ -286,7 +286,7 @@ public class XsltStylesheet extends RubyObject
   createDocumentFromDomResult(ThreadContext context, Ruby runtime, DOMResult domResult)
   {
     if ("html".equals(domResult.getNode().getFirstChild().getNodeName())) {
-      return new HtmlDocument(context.runtime, (Document) domResult.getNode());
+      return new Html4Document(context.runtime, (Document) domResult.getNode());
     } else {
       return new XmlDocument(context.runtime, (Document) domResult.getNode());
     }
@@ -322,7 +322,7 @@ public class XsltStylesheet extends RubyObject
     RubyClass parse_options = (RubyClass)runtime.getClassFromPath("Nokogiri::XML::ParseOptions");
     if (htmlish) {
       args[3] = parse_options.getConstant("DEFAULT_HTML");
-      RubyClass htmlDocumentClass = getNokogiriClass(runtime, "Nokogiri::HTML::Document");
+      RubyClass htmlDocumentClass = getNokogiriClass(runtime, "Nokogiri::HTML4::Document");
       return Helpers.invoke(context, htmlDocumentClass, "parse", args);
     } else {
       args[3] = parse_options.getConstant("DEFAULT_XML");

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

@@ -4,7 +4,7 @@ import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
 import static nokogiri.internals.NokogiriHelpers.isNamespace;
 import static nokogiri.internals.NokogiriHelpers.stringOrNil;
 
-import nokogiri.HtmlDocument;
+import nokogiri.Html4Document;
 import nokogiri.NokogiriService;
 import nokogiri.XmlDocument;
 import nokogiri.XmlSyntaxError;
@@ -28,7 +28,7 @@ import org.w3c.dom.Node;
 import org.w3c.dom.NodeList;
 
 /**
- * Parser for HtmlDocument. This class actually parses HtmlDocument using NekoHtml.
+ * Parser for Html4Document. This class actually parses Html4Document using NekoHtml.
  *
  * @author sergio
  * @author Patrick Mahoney <pat@polycrystal.org>
@@ -115,12 +115,12 @@ public class HtmlDomParserContext extends XmlDomParserContext
   protected XmlDocument
   wrapDocument(ThreadContext context, RubyClass klass, Document document)
   {
-    HtmlDocument htmlDocument = new HtmlDocument(context.runtime, klass, 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 HtmlDocument::EncodingReader
+      // ruby_encoding might have detected by Html4Document::EncodingReader
       if (detected_encoding != null && !detected_encoding.isNil()) {
         ruby_encoding = detected_encoding;
       } else {

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

@@ -59,7 +59,7 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler
     this.object = object;
     charactersBuilder = new StringBuilder();
     String objectName = object.getMetaClass().getName();
-    if ("Nokogiri::HTML::SAX::Parser".equals(objectName)) { needEmptyAttrCheck = true; }
+    if ("Nokogiri::HTML4::SAX::Parser".equals(objectName)) { needEmptyAttrCheck = true; }
   }
 
   @Override

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

@@ -25,7 +25,7 @@ import org.w3c.dom.Document;
 import org.w3c.dom.Node;
 import org.w3c.dom.NodeList;
 
-import nokogiri.HtmlDocument;
+import nokogiri.Html4Document;
 import nokogiri.NokogiriService;
 import nokogiri.XmlAttr;
 import nokogiri.XmlCdata;
@@ -89,7 +89,7 @@ public class NokogiriHelpers
     if (node == null) { return runtime.getNil(); }
     if (node.getNodeType() == Node.ATTRIBUTE_NODE && isNamespace(node.getNodeName())) {
       XmlDocument xmlDocument = (XmlDocument) node.getOwnerDocument().getUserData(CACHED_NODE);
-      if (!(xmlDocument instanceof HtmlDocument)) {
+      if (!(xmlDocument instanceof Html4Document)) {
         String prefix = getLocalNameForNamespace(((Attr) node).getName(), null);
         String href = ((Attr) node).getValue();
         XmlNamespace xmlNamespace = xmlDocument.getNamespaceCache().get(prefix, href);
@@ -116,59 +116,59 @@ public class NokogiriHelpers
     if (node == null) { return runtime.getNil(); }
     // this is slow; need a way to cache nokogiri classes/modules somewhere
     switch (node.getNodeType()) {
-    case Node.ELEMENT_NODE:
-      XmlElement xmlElement = (XmlElement) NokogiriService.XML_ELEMENT_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                              "Nokogiri::XML::Element"));
-      xmlElement.setNode(runtime, node);
-      return xmlElement;
-    case Node.ATTRIBUTE_NODE:
-      XmlAttr xmlAttr = (XmlAttr) NokogiriService.XML_ATTR_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                        "Nokogiri::XML::Attr"));
-      xmlAttr.setNode(runtime, node);
-      return xmlAttr;
-    case Node.TEXT_NODE:
-      XmlText xmlText = (XmlText) NokogiriService.XML_TEXT_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                        "Nokogiri::XML::Text"));
-      xmlText.setNode(runtime, node);
-      return xmlText;
-    case Node.COMMENT_NODE:
-      XmlComment xmlComment = (XmlComment) NokogiriService.XML_COMMENT_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                              "Nokogiri::XML::Comment"));
-      xmlComment.setNode(runtime, node);
-      return xmlComment;
-    case Node.ENTITY_NODE:
-      return new XmlNode(runtime, getNokogiriClass(runtime, "Nokogiri::XML::EntityDecl"), node);
-    case Node.ENTITY_REFERENCE_NODE:
-      XmlEntityReference xmlEntityRef = (XmlEntityReference) NokogiriService.XML_ENTITY_REFERENCE_ALLOCATOR.allocate(runtime,
-                                        getNokogiriClass(runtime, "Nokogiri::XML::EntityReference"));
-      xmlEntityRef.setNode(runtime, node);
-      return xmlEntityRef;
-    case Node.PROCESSING_INSTRUCTION_NODE:
-      XmlProcessingInstruction xmlProcessingInstruction = (XmlProcessingInstruction)
-          NokogiriService.XML_PROCESSING_INSTRUCTION_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-              "Nokogiri::XML::ProcessingInstruction"));
-      xmlProcessingInstruction.setNode(runtime, node);
-      return xmlProcessingInstruction;
-    case Node.CDATA_SECTION_NODE:
-      XmlCdata xmlCdata = (XmlCdata) NokogiriService.XML_CDATA_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                          "Nokogiri::XML::CDATA"));
-      xmlCdata.setNode(runtime, node);
-      return xmlCdata;
-    case Node.DOCUMENT_NODE:
-      XmlDocument xmlDocument = (XmlDocument) NokogiriService.XML_DOCUMENT_ALLOCATOR.allocate(runtime,
-                                getNokogiriClass(runtime, "Nokogiri::XML::Document"));
-      xmlDocument.setDocumentNode(runtime, (Document) node);
-      return xmlDocument;
-    case Node.DOCUMENT_TYPE_NODE:
-      XmlDtd xmlDtd = (XmlDtd) NokogiriService.XML_DTD_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                      "Nokogiri::XML::DTD"));
-      xmlDtd.setNode(runtime, node);
-      return xmlDtd;
-    default:
-      XmlNode xmlNode = (XmlNode) NokogiriService.XML_NODE_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
-                        "Nokogiri::XML::Node"));
-      xmlNode.setNode(runtime, node);
-      return xmlNode;
+      case Node.ELEMENT_NODE:
+        XmlElement xmlElement = (XmlElement) NokogiriService.XML_ELEMENT_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                                "Nokogiri::XML::Element"));
+        xmlElement.setNode(runtime, node);
+        return xmlElement;
+      case Node.ATTRIBUTE_NODE:
+        XmlAttr xmlAttr = (XmlAttr) NokogiriService.XML_ATTR_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                          "Nokogiri::XML::Attr"));
+        xmlAttr.setNode(runtime, node);
+        return xmlAttr;
+      case Node.TEXT_NODE:
+        XmlText xmlText = (XmlText) NokogiriService.XML_TEXT_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                          "Nokogiri::XML::Text"));
+        xmlText.setNode(runtime, node);
+        return xmlText;
+      case Node.COMMENT_NODE:
+        XmlComment xmlComment = (XmlComment) NokogiriService.XML_COMMENT_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                                "Nokogiri::XML::Comment"));
+        xmlComment.setNode(runtime, node);
+        return xmlComment;
+      case Node.ENTITY_NODE:
+        return new XmlNode(runtime, getNokogiriClass(runtime, "Nokogiri::XML::EntityDecl"), node);
+      case Node.ENTITY_REFERENCE_NODE:
+        XmlEntityReference xmlEntityRef = (XmlEntityReference) NokogiriService.XML_ENTITY_REFERENCE_ALLOCATOR.allocate(runtime,
+                                          getNokogiriClass(runtime, "Nokogiri::XML::EntityReference"));
+        xmlEntityRef.setNode(runtime, node);
+        return xmlEntityRef;
+      case Node.PROCESSING_INSTRUCTION_NODE:
+        XmlProcessingInstruction xmlProcessingInstruction = (XmlProcessingInstruction)
+            NokogiriService.XML_PROCESSING_INSTRUCTION_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                "Nokogiri::XML::ProcessingInstruction"));
+        xmlProcessingInstruction.setNode(runtime, node);
+        return xmlProcessingInstruction;
+      case Node.CDATA_SECTION_NODE:
+        XmlCdata xmlCdata = (XmlCdata) NokogiriService.XML_CDATA_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                            "Nokogiri::XML::CDATA"));
+        xmlCdata.setNode(runtime, node);
+        return xmlCdata;
+      case Node.DOCUMENT_NODE:
+        XmlDocument xmlDocument = (XmlDocument) NokogiriService.XML_DOCUMENT_ALLOCATOR.allocate(runtime,
+                                  getNokogiriClass(runtime, "Nokogiri::XML::Document"));
+        xmlDocument.setDocumentNode(runtime, (Document) node);
+        return xmlDocument;
+      case Node.DOCUMENT_TYPE_NODE:
+        XmlDtd xmlDtd = (XmlDtd) NokogiriService.XML_DTD_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                        "Nokogiri::XML::DTD"));
+        xmlDtd.setNode(runtime, node);
+        return xmlDtd;
+      default:
+        XmlNode xmlNode = (XmlNode) NokogiriService.XML_NODE_ALLOCATOR.allocate(runtime, getNokogiriClass(runtime,
+                          "Nokogiri::XML::Node"));
+        xmlNode.setNode(runtime, node);
+        return xmlNode;
     }
   }
 
@@ -723,8 +723,8 @@ public class NokogiriHelpers
   public static CharSequence
   convertEncodingByNKFIfNecessary(ThreadContext context, XmlDocument doc, CharSequence str)
   {
-    if (!(doc instanceof HtmlDocument)) { return str; }
-    String parsed_encoding = ((HtmlDocument)doc).getPraedEncoding();
+    if (!(doc instanceof Html4Document)) { return str; }
+    String parsed_encoding = ((Html4Document)doc).getPraedEncoding();
     if (parsed_encoding == null) { return str; }
     String ruby_encoding = rubyStringToString(doc.getEncoding());
     if (ruby_encoding == null) { return str; }

data/ext/java/nokogiri/internals/SaveContextVisitor.java

@@ -296,30 +296,30 @@ public class SaveContextVisitor
     for (int i = 0; i < str.length(); i++) {
       char c;
       switch (c = str.charAt(i)) {
-      case '\n':
-        buffer.append("&#10;");
-        break;
-      case '\r':
-        buffer.append("&#13;");
-        break;
-      case '\t':
-        buffer.append("&#9;");
-        break;
-      case '"':
-        if (htmlDoc) { buffer.append("%22"); }
-        else { buffer.append("&quot;"); }
-        break;
-      case '<':
-        buffer.append("&lt;");
-        break;
-      case '>':
-        buffer.append("&gt;");
-        break;
-      case '&':
-        buffer.append("&amp;");
-        break;
-      default:
-        buffer.append(c);
+        case '\n':
+          buffer.append("&#10;");
+          break;
+        case '\r':
+          buffer.append("&#13;");
+          break;
+        case '\t':
+          buffer.append("&#9;");
+          break;
+        case '"':
+          if (htmlDoc) { buffer.append("%22"); }
+          else { buffer.append("&quot;"); }
+          break;
+        case '<':
+          buffer.append("&lt;");
+          break;
+        case '>':
+          buffer.append("&gt;");
+          break;
+        case '&':
+          buffer.append("&amp;");
+          break;
+        default:
+          buffer.append(c);
       }
     }
 

data/ext/java/nokogiri/internals/c14n/CanonicalizerBase.java

@@ -202,75 +202,75 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
     do {
       switch (currentNode.getNodeType()) {
 
-      case Node.ENTITY_NODE :
-      case Node.NOTATION_NODE :
-      case Node.ATTRIBUTE_NODE :
-        // illegal node type during traversal
-        throw new CanonicalizationException("empty");
-
-      case Node.DOCUMENT_FRAGMENT_NODE :
-      case Node.DOCUMENT_NODE :
-        ns.outputNodePush();
-        sibling = currentNode.getFirstChild();
-        break;
-
-      case Node.COMMENT_NODE :
-        if (includeComments) {
-          outputCommentToWriter((Comment) currentNode, writer, documentLevel);
-        }
-        break;
-
-      case Node.PROCESSING_INSTRUCTION_NODE :
-        outputPItoWriter((ProcessingInstruction) currentNode, writer, documentLevel);
-        break;
+        case Node.ENTITY_NODE :
+        case Node.NOTATION_NODE :
+        case Node.ATTRIBUTE_NODE :
+          // illegal node type during traversal
+          throw new CanonicalizationException("empty");
+
+        case Node.DOCUMENT_FRAGMENT_NODE :
+        case Node.DOCUMENT_NODE :
+          ns.outputNodePush();
+          sibling = currentNode.getFirstChild();
+          break;
 
-      case Node.TEXT_NODE :
-      case Node.CDATA_SECTION_NODE :
-        outputTextToWriter(currentNode.getNodeValue(), writer);
-        break;
+        case Node.COMMENT_NODE :
+          if (includeComments) {
+            outputCommentToWriter((Comment) currentNode, writer, documentLevel);
+          }
+          break;
 
-      case Node.ELEMENT_NODE :
-        documentLevel = NODE_NOT_BEFORE_OR_AFTER_DOCUMENT_ELEMENT;
-        if (currentNode == excludeNode) {
+        case Node.PROCESSING_INSTRUCTION_NODE :
+          outputPItoWriter((ProcessingInstruction) currentNode, writer, documentLevel);
           break;
-        }
-        if (filter != null && !filter.includeNodes(currentNode, parentNode)) {
+
+        case Node.TEXT_NODE :
+        case Node.CDATA_SECTION_NODE :
+          outputTextToWriter(currentNode.getNodeValue(), writer);
           break;
-        }
 
-        Element currentElement = (Element)currentNode;
-        //Add a level to the nssymbtable. So latter can be pop-back.
-        ns.outputNodePush();
-        writer.write('<');
-        String name = currentElement.getTagName();
-        UtfHelpper.writeByte(name, writer, cache);
-
-        Iterator<Attr> attrs = this.handleAttributesSubtree(currentElement, ns);
-        if (attrs != null) {
-          //we output all Attrs which are available
-          while (attrs.hasNext()) {
-            Attr attr = attrs.next();
-            outputAttrToWriter(attr.getNodeName(), attr.getNodeValue(), writer, cache);
+        case Node.ELEMENT_NODE :
+          documentLevel = NODE_NOT_BEFORE_OR_AFTER_DOCUMENT_ELEMENT;
+          if (currentNode == excludeNode) {
+            break;
+          }
+          if (filter != null && !filter.includeNodes(currentNode, parentNode)) {
+            break;
+          }
+
+          Element currentElement = (Element)currentNode;
+          //Add a level to the nssymbtable. So latter can be pop-back.
+          ns.outputNodePush();
+          writer.write('<');
+          String name = currentElement.getTagName();
+          UtfHelpper.writeByte(name, writer, cache);
+
+          Iterator<Attr> attrs = this.handleAttributesSubtree(currentElement, ns);
+          if (attrs != null) {
+            //we output all Attrs which are available
+            while (attrs.hasNext()) {
+              Attr attr = attrs.next();
+              outputAttrToWriter(attr.getNodeName(), attr.getNodeValue(), writer, cache);
+            }
           }
-        }
-        writer.write('>');
-        sibling = currentNode.getFirstChild();
-        if (sibling == null) {
-          writer.write(END_TAG);
-          UtfHelpper.writeStringToUtf8(name, writer);
           writer.write('>');
-          //We finished with this level, pop to the previous definitions.
-          ns.outputNodePop();
-          if (parentNode != null) {
-            sibling = currentNode.getNextSibling();
+          sibling = currentNode.getFirstChild();
+          if (sibling == null) {
+            writer.write(END_TAG);
+            UtfHelpper.writeStringToUtf8(name, writer);
+            writer.write('>');
+            //We finished with this level, pop to the previous definitions.
+            ns.outputNodePop();
+            if (parentNode != null) {
+              sibling = currentNode.getNextSibling();
+            }
+          } else {
+            parentNode = currentElement;
           }
-        } else {
-          parentNode = currentElement;
-        }
-        break;
-      case Node.DOCUMENT_TYPE_NODE :
-      default :
-        break;
+          break;
+        case Node.DOCUMENT_TYPE_NODE :
+        default :
+          break;
       }
       while (sibling == null && parentNode != null) {
         writer.write(END_TAG);
@@ -477,37 +477,37 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
 
       switch (c) {
 
-      case '&' :
-        toWrite = AMP;
-        break;
+        case '&' :
+          toWrite = AMP;
+          break;
 
-      case '<' :
-        toWrite = LT;
-        break;
+        case '<' :
+          toWrite = LT;
+          break;
 
-      case '"' :
-        toWrite = QUOT;
-        break;
+        case '"' :
+          toWrite = QUOT;
+          break;
 
-      case 0x09 :    // '\t'
-        toWrite = X9;
-        break;
+        case 0x09 :    // '\t'
+          toWrite = X9;
+          break;
 
-      case 0x0A :    // '\n'
-        toWrite = XA;
-        break;
+        case 0x0A :    // '\n'
+          toWrite = XA;
+          break;
 
-      case 0x0D :    // '\r'
-        toWrite = XD;
-        break;
+        case 0x0D :    // '\r'
+          toWrite = XD;
+          break;
 
-      default :
-        if (c < 0x80) {
-          writer.write(c);
-        } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
-        }
-        continue;
+        default :
+          if (c < 0x80) {
+            writer.write(c);
+          } else {
+            UtfHelpper.writeCharToUtf8(c, writer);
+          }
+          continue;
       }
       writer.write(toWrite);
     }
@@ -629,29 +629,29 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
 
       switch (c) {
 
-      case '&' :
-        toWrite = AMP;
-        break;
+        case '&' :
+          toWrite = AMP;
+          break;
 
-      case '<' :
-        toWrite = LT;
-        break;
+        case '<' :
+          toWrite = LT;
+          break;
 
-      case '>' :
-        toWrite = GT;
-        break;
+        case '>' :
+          toWrite = GT;
+          break;
 
-      case 0xD :
-        toWrite = XD;
-        break;
+        case 0xD :
+          toWrite = XD;
+          break;
 
-      default :
-        if (c < 0x80) {
-          writer.write(c);
-        } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
-        }
-        continue;
+        default :
+          if (c < 0x80) {
+            writer.write(c);
+          } else {
+            UtfHelpper.writeCharToUtf8(c, writer);
+          }
+          continue;
       }
       writer.write(toWrite);
     }