fix: ensure namespaced attributes are reparented properly

CHANGELOG.md

@@ -6,20 +6,36 @@ Nokogiri follows [Semantic Versioning](https://semver.org/), please see the [REA
 
 ## next / unreleased
 
-### Dependencies
+### Added
+
+__HTML5 support__ has been added (to CRuby only) by merging [Nokogumbo](https://github.com/rubys/nokogumbo) into Nokogiri. The Nokogumbo public API has been preserved, so this functionality is available under the `Nokogiri::HTML5` namespace. [[#2204](https://github.com/sparklemotion/nokogiri/issues/2204)]
+
+Please note that HTML5 support is not available for JRuby in this version. However, we feel it is important to think about JRuby and we hope to work on this in the future. If you're interested in helping with HTML5 support on JRuby, please reach out to the maintainers by commenting on issue [#2227](https://github.com/sparklemotion/nokogiri/issues/2227).
 
-* [MRI] Upgrade mini_portile2 dependency from `~> 2.5.0` to `~> 2.5.1`.
+Please also note that the `Nokogiri::HTML` parse methods still use libxml2's HTML4 parser in the v1.12 release series. Future releases of Nokogiri may change this behavior, but we'll proceed cautiously to avoid breaking existing applications.
+
+Many thanks to Sam Ruby, Steve Checkoway, and Craig Barnes for creating and maintaining Nokogumbo and supporting the Gumbo HTML5 parser. They're now Nokogiri core contributors with all the powers and privileges pertaining thereto. 🙌
 
 
 ### Changed
 
-* Introduce `Nokogiri::XML::ParseOptions::DEFAULT_XSLT` which adds the libxslt-preferred options of `NOENT | DTDLOAD | DTDATTR | NOCDATA` to `ParseOptions::DEFAULT_XML`.
-* `Nokogiri.XSLT` parses the stylesheet using `ParseOptions::DEFAULT_XSLT`, which should make some edge-case XSL transformations match libxslt's default behavior. [[#1940](https://github.com/sparklemotion/nokogiri/issues/1940)]
+* Introduce a new constant, `Nokogiri::XML::ParseOptions::DEFAULT_XSLT`, which adds the libxslt-preferred options of `NOENT | DTDLOAD | DTDATTR | NOCDATA` to `ParseOptions::DEFAULT_XML`.
+* `Nokogiri.XSLT` parses stylesheets using `ParseOptions::DEFAULT_XSLT`, which should make some edge-case XSL transformations match libxslt's default behavior. [[#1940](https://github.com/sparklemotion/nokogiri/issues/1940)]
+
+
+### Fixed
+
+* [CRuby] Namespaced attributes are handled properly when their parent node is reparented into another document. Previously, the namespace may have gotten dropped. [[#2228](https://github.com/sparklemotion/nokogiri/issues/2228)]
 
 
 ### Improved
 
-* [MRI] Speed up (slightly) the compile time of packaged libraries `libiconv`, `libxml2`, and `libxslt` by using autoconf's `--disable-dependency-tracking` option.
+* [CRuby] Speed up (slightly) the compile time of packaged libraries `libiconv`, `libxml2`, and `libxslt` by using autoconf's `--disable-dependency-tracking` option. ("ruby" platform gem only.)
+
+
+### Dependencies
+
+* [CRuby] Upgrade mini_portile2 dependency from `~> 2.5.0` to `~> 2.5.1`. ("ruby" platform gem only.)
 
 
 ## 1.11.3 / 2021-04-07

ext/java/nokogiri/XmlDocument.java

@@ -657,17 +657,17 @@ private static class DocumentBuilderFactoryHolder
     }
     String algorithmURI = null;
     switch (mode) {
-    case 0:  // XML_C14N_1_0
-      if (with_comments) { algorithmURI = Canonicalizer.ALGO_ID_C14N_WITH_COMMENTS; }
-      else { algorithmURI = Canonicalizer.ALGO_ID_C14N_OMIT_COMMENTS; }
-      break;
-    case 1:  // XML_C14N_EXCLUSIVE_1_0
-      if (with_comments) { algorithmURI = Canonicalizer.ALGO_ID_C14N_EXCL_WITH_COMMENTS; }
-      else { algorithmURI = Canonicalizer.ALGO_ID_C14N_EXCL_OMIT_COMMENTS; }
-      break;
-    case 2: // XML_C14N_1_1 = 2
-      if (with_comments) { algorithmURI = Canonicalizer.ALGO_ID_C14N11_WITH_COMMENTS; }
-      else { algorithmURI = Canonicalizer.ALGO_ID_C14N11_OMIT_COMMENTS; }
+      case 0:  // XML_C14N_1_0
+        if (with_comments) { algorithmURI = Canonicalizer.ALGO_ID_C14N_WITH_COMMENTS; }
+        else { algorithmURI = Canonicalizer.ALGO_ID_C14N_OMIT_COMMENTS; }
+        break;
+      case 1:  // XML_C14N_EXCLUSIVE_1_0
+        if (with_comments) { algorithmURI = Canonicalizer.ALGO_ID_C14N_EXCL_WITH_COMMENTS; }
+        else { algorithmURI = Canonicalizer.ALGO_ID_C14N_EXCL_OMIT_COMMENTS; }
+        break;
+      case 2: // XML_C14N_1_1 = 2
+        if (with_comments) { algorithmURI = Canonicalizer.ALGO_ID_C14N11_WITH_COMMENTS; }
+        else { algorithmURI = Canonicalizer.ALGO_ID_C14N11_OMIT_COMMENTS; }
     }
     try {
       Canonicalizer canonicalizer = Canonicalizer.getInstance(algorithmURI);

ext/java/nokogiri/XmlElementContent.java

@@ -142,11 +142,11 @@ public IRubyObject value(Ruby runtime)
     right = runtime.getNil();
 
     switch (type) {
-    case SEQ:
-    case OR:
-      applyGroup(runtime, klass, doc, iter);
-    default:
-      // noop
+      case SEQ:
+      case OR:
+        applyGroup(runtime, klass, doc, iter);
+      default:
+        // noop
     }
   }
 

ext/java/nokogiri/XmlNode.java

@@ -1516,56 +1516,56 @@ public class XmlNode extends RubyObject
   {
     String type;
     switch (node.getNodeType()) {
-    case Node.ELEMENT_NODE:
-      if (this instanceof XmlElementDecl) {
-        type = "ELEMENT_DECL";
-      } else if (this instanceof XmlAttributeDecl) {
-        type = "ATTRIBUTE_DECL";
-      } else if (this instanceof XmlEntityDecl) {
-        type = "ENTITY_DECL";
-      } else {
-        type = "ELEMENT_NODE";
-      }
-      break;
-    case Node.ATTRIBUTE_NODE:
-      type = "ATTRIBUTE_NODE";
-      break;
-    case Node.TEXT_NODE:
-      type = "TEXT_NODE";
-      break;
-    case Node.CDATA_SECTION_NODE:
-      type = "CDATA_SECTION_NODE";
-      break;
-    case Node.ENTITY_REFERENCE_NODE:
-      type = "ENTITY_REF_NODE";
-      break;
-    case Node.ENTITY_NODE:
-      type = "ENTITY_NODE";
-      break;
-    case Node.PROCESSING_INSTRUCTION_NODE:
-      type = "PI_NODE";
-      break;
-    case Node.COMMENT_NODE:
-      type = "COMMENT_NODE";
-      break;
-    case Node.DOCUMENT_NODE:
-      if (this instanceof HtmlDocument) {
-        type = "HTML_DOCUMENT_NODE";
-      } else {
-        type = "DOCUMENT_NODE";
-      }
-      break;
-    case Node.DOCUMENT_TYPE_NODE:
-      type = "DOCUMENT_TYPE_NODE";
-      break;
-    case Node.DOCUMENT_FRAGMENT_NODE:
-      type = "DOCUMENT_FRAG_NODE";
-      break;
-    case Node.NOTATION_NODE:
-      type = "NOTATION_NODE";
-      break;
-    default:
-      return context.runtime.newFixnum(0);
+      case Node.ELEMENT_NODE:
+        if (this instanceof XmlElementDecl) {
+          type = "ELEMENT_DECL";
+        } else if (this instanceof XmlAttributeDecl) {
+          type = "ATTRIBUTE_DECL";
+        } else if (this instanceof XmlEntityDecl) {
+          type = "ENTITY_DECL";
+        } else {
+          type = "ELEMENT_NODE";
+        }
+        break;
+      case Node.ATTRIBUTE_NODE:
+        type = "ATTRIBUTE_NODE";
+        break;
+      case Node.TEXT_NODE:
+        type = "TEXT_NODE";
+        break;
+      case Node.CDATA_SECTION_NODE:
+        type = "CDATA_SECTION_NODE";
+        break;
+      case Node.ENTITY_REFERENCE_NODE:
+        type = "ENTITY_REF_NODE";
+        break;
+      case Node.ENTITY_NODE:
+        type = "ENTITY_NODE";
+        break;
+      case Node.PROCESSING_INSTRUCTION_NODE:
+        type = "PI_NODE";
+        break;
+      case Node.COMMENT_NODE:
+        type = "COMMENT_NODE";
+        break;
+      case Node.DOCUMENT_NODE:
+        if (this instanceof HtmlDocument) {
+          type = "HTML_DOCUMENT_NODE";
+        } else {
+          type = "DOCUMENT_NODE";
+        }
+        break;
+      case Node.DOCUMENT_TYPE_NODE:
+        type = "DOCUMENT_TYPE_NODE";
+        break;
+      case Node.DOCUMENT_FRAGMENT_NODE:
+        type = "DOCUMENT_FRAG_NODE";
+        break;
+      case Node.NOTATION_NODE:
+        type = "NOTATION_NODE";
+        break;
+      default:
+        return context.runtime.newFixnum(0);
     }
 
     return getNokogiriClass(context.runtime, "Nokogiri::XML::Node").getConstant(type);
@@ -1676,23 +1676,23 @@ protected enum AdoptScheme {
       Node parent = thisNode.getParentNode();
 
       switch (scheme) {
-      case CHILD:
-        Node[] children = adoptAsChild(thisNode, otherNode);
-        if (children.length == 1 && otherNode == children[0]) {
+        case CHILD:
+          Node[] children = adoptAsChild(thisNode, otherNode);
+          if (children.length == 1 && otherNode == children[0]) {
+            break;
+          } else {
+            nodeOrTags = nodeArrayToRubyArray(context.runtime, children);
+          }
+          break;
+        case PREV_SIBLING:
+          adoptAsPrevSibling(context, parent, thisNode, otherNode);
+          break;
+        case NEXT_SIBLING:
+          adoptAsNextSibling(context, parent, thisNode, otherNode);
+          break;
+        case REPLACEMENT:
+          adoptAsReplacement(context, parent, thisNode, otherNode);
           break;
-        } else {
-          nodeOrTags = nodeArrayToRubyArray(context.runtime, children);
-        }
-        break;
-      case PREV_SIBLING:
-        adoptAsPrevSibling(context, parent, thisNode, otherNode);
-        break;
-      case NEXT_SIBLING:
-        adoptAsNextSibling(context, parent, thisNode, otherNode);
-        break;
-      case REPLACEMENT:
-        adoptAsReplacement(context, parent, thisNode, otherNode);
-        break;
       }
     } catch (Exception e) {
       throw context.runtime.newRuntimeError(e.toString());

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());
     }
   }
 

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) {

ext/java/nokogiri/internals/NokogiriHelpers.java

@@ -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;
     }
   }