nokogiri 1.16.8-java → 1.17.0-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d738514ea45f87c34b937caf79fe740ee4e854c3977168bf92a9b9b0b5aa43ba
-  data.tar.gz: d0a5904665e3376d5da0ef4edd765aecad5f4023834e4b5d4dd5ea4d344ae40c
+  metadata.gz: e72cb3083fa1cff82029cbbf2fec76f1a8dd39937c017633b0d944925d72ccaa
+  data.tar.gz: 45760600fd16493478685f69e2d122bd807f869052e1a3d2f640e2ba2d0a1451
 SHA512:
-  metadata.gz: c26332a0911cbddad1bba94100c87267287339346ead9e9676d275de52363a50a73c73bfd5a123e21762ad828bbe69f0a3d933b14c54b78e443cac57245717d3
-  data.tar.gz: bb99ef98745b0c546a1556afa2c2309dad123240a675db7d6615e810df6dbb786d9b5edbbafad2d4b33f5b21b51a3b7c1f44eb0541d7efb57a5f0a4e3ed9dbf4
+  metadata.gz: db57663703ce10b22d3aa59ab5aa2a308ac5fda082cea1a4bb01245277b1b2df7b20eb103966b1fc814465276d921e52ff971adca42ea7e71b67fd20219fbeba
+  data.tar.gz: 979db2b053dc00919e9ea60a548af51eb30d2b447a8ae46bdcf5d66acba204ab5019b277614a321f03a0d8b7f6a62171d113b8d392f172c56af305ce343c5bdd

data/Gemfile

@@ -5,44 +5,34 @@ source "https://rubygems.org"
 gemspec
 
 group :development do
-  # ruby 3.4.0-dev removed some gems from the default set
-  #
-  # TODO: we should be able to remove these as our gem dependencies sort it out and we pull them in
-  # transitively.
-  gem "mutex_m"
-
   # bootstrapping
   gem "bundler", "~> 2.3"
-  gem "rake", "13.1.0"
+  gem "rake", "13.2.1"
 
   # building extensions
-  gem "rake-compiler", "1.2.6"
-  gem "rake-compiler-dock", "1.4.0"
+  gem "rake-compiler", "1.2.8"
+  gem "rake-compiler-dock", "1.5.2"
 
   # parser generator
-  gem "rexical", "= 1.0.7"
+  gem "rexical", "1.0.8"
 
   # tests
-  gem "minitest", "5.21.2"
+  gem "minitest", "5.25.2"
   gem "minitest-parallel_fork", "2.0.0"
-  gem "ruby_memcheck", "2.3.0"
+  gem "ruby_memcheck", "3.0.0"
   gem "rubyzip", "~> 2.3.2"
   gem "simplecov", "= 0.21.2"
 
   # rubocop
-  if Gem::Requirement.new("~> 3.0").satisfied_by?(Gem::Version.new(RUBY_VERSION))
-    gem "rubocop", "1.60.2"
-    gem "rubocop-minitest", "0.34.5"
-    gem "rubocop-packaging", "0.5.2"
-    gem "rubocop-performance", "1.20.2"
-    gem "rubocop-rake", "= 0.6.0"
-    gem "rubocop-shopify", "2.14.0"
-  end
+  gem "standard", "1.42.1"
+  gem "rubocop-minitest", "0.36.0"
+  gem "rubocop-packaging", "0.5.2"
+  gem "rubocop-rake", "0.6.0"
 end
 
 # If Psych doesn't build, you can disable this group locally by running
 # `bundle config set --local without rdoc`
 # Then re-run `bundle install`.
 group :rdoc do
-  gem "rdoc", "6.6.2"
+  gem "rdoc", "6.8.1"
 end

data/README.md

@@ -117,6 +117,10 @@ Requirements:
 - Ruby >= 3.0
 - JRuby >= 9.4.0.0
 
+If you are compiling the native extension against a system version of libxml2:
+
+- libxml2 >= 2.9.2 (recommended >= 2.12.0)
+
 
 ### Native Gems: Faster, more reliable installation
 

data/dependencies.yml

@@ -1,13 +1,13 @@
 ---
 libxml2:
-  version: "2.12.9"
-  sha256: "59912db536ab56a3996489ea0299768c7bcffe57169f0235e7f962a91f483590"
-  # sha-256 hash provided in https://download.gnome.org/sources/libxml2/2.12/libxml2-2.12.9.sha256sum
+  version: "2.13.5"
+  sha256: "74fc163217a3964257d3be39af943e08861263c4231f9ef5b496b6f6d4c7b2b6"
+  # sha-256 hash provided in https://download.gnome.org/sources/libxml2/2.13/libxml2-2.13.5.sha256sum
 
 libxslt:
-  version: "1.1.39"
-  sha256: "2a20ad621148339b0759c4d4e96719362dee64c9a096dbba625ba053846349f0"
-  # sha-256 hash provided in https://download.gnome.org/sources/libxslt/1.1/libxslt-1.1.39.sha256sum
+  version: "1.1.42"
+  sha256: "85ca62cac0d41fc77d3f6033da9df6fd73d20ea2fc18b0a3609ffb4110e1baeb"
+  # sha-256 hash provided in https://download.gnome.org/sources/libxslt/1.1/libxslt-1.1.42.sha256sum
 
 zlib:
   version: "1.3.1"

data/ext/java/nokogiri/Html4Document.java

@@ -30,7 +30,7 @@ public class Html4Document extends XmlDocument
 
   private static final String DEFAULT_CONTENT_TYPE = "html";
   private static final String DEFAULT_PUBLIC_ID = "-//W3C//DTD HTML 4.01//EN";
-  private static final String DEFAULT_SYTEM_ID = "http://www.w3.org/TR/html4/strict.dtd";
+  private static final String DEFAULT_SYSTEM_ID = "http://www.w3.org/TR/html4/strict.dtd";
 
   private String parsed_encoding = null;
 
@@ -88,7 +88,7 @@ public class Html4Document extends XmlDocument
                                        getDocument(),
                                        context.getRuntime().newString(DEFAULT_CONTENT_TYPE),
                                        context.getRuntime().newString(DEFAULT_PUBLIC_ID),
-                                       context.getRuntime().newString(DEFAULT_SYTEM_ID));
+                                       context.getRuntime().newString(DEFAULT_SYSTEM_ID));
       setInternalSubset(internalSubset);
     }
 
@@ -132,7 +132,7 @@ public class Html4Document extends XmlDocument
   }
 
   public String
-  getPraedEncoding()
+  getParsedEncoding()
   {
     return parsed_encoding;
   }

data/ext/java/nokogiri/Html4SaxParserContext.java

@@ -2,16 +2,12 @@ package nokogiri;
 
 import java.io.ByteArrayInputStream;
 import java.io.InputStream;
-import java.nio.charset.Charset;
-import java.nio.charset.IllegalCharsetNameException;
-import java.nio.charset.UnsupportedCharsetException;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
 
 import org.apache.xerces.parsers.AbstractSAXParser;
 import net.sourceforge.htmlunit.cyberneko.parsers.SAXParser;
 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;
@@ -23,6 +19,8 @@ import org.xml.sax.SAXException;
 import nokogiri.internals.NokogiriHandler;
 import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
 
+import static org.jruby.runtime.Helpers.invoke;
+
 /**
  * Class for Nokogiri::HTML4::SAX::ParserContext.
  *
@@ -56,10 +54,9 @@ public class Html4SaxParserContext extends XmlSaxParserContext
     SAXParser parser = new SAXParser();
 
     try {
-      parser.setProperty(
-        "http://cyberneko.org/html/properties/names/elems", "lower");
-      parser.setProperty(
-        "http://cyberneko.org/html/properties/names/attrs", "lower");
+      parser.setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
+      parser.setProperty("http://cyberneko.org/html/properties/names/attrs", "lower");
+      parser.setFeature("http://cyberneko.org/html/features/report-errors", true);
 
       // NekoHTML should not try to guess the encoding based on the meta
       // tags or other information in the document.  This is already
@@ -72,198 +69,73 @@ public class Html4SaxParserContext extends XmlSaxParserContext
     }
   }
 
-  @JRubyMethod(name = "memory", meta = true)
+  @JRubyMethod(name = "native_memory", meta = true)
   public static IRubyObject
-  parse_memory(ThreadContext context,
-               IRubyObject klazz,
-               IRubyObject data,
-               IRubyObject encoding)
+  parse_memory(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
   {
-    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
-    String javaEncoding = findEncodingName(context, encoding);
-    if (javaEncoding != null) {
-      CharSequence input = applyEncoding(rubyStringToString(data.convertToString()), javaEncoding);
-      ByteArrayInputStream istream = new ByteArrayInputStream(input.toString().getBytes());
-      ctx.setInputSource(istream);
-      ctx.getInputSource().setEncoding(javaEncoding);
-    }
-    return ctx;
-  }
-
-  public enum EncodingType {
-    NONE(0, "NONE"),
-    UTF_8(1, "UTF-8"),
-    UTF16LE(2, "UTF16LE"),
-    UTF16BE(3, "UTF16BE"),
-    UCS4LE(4, "UCS4LE"),
-    UCS4BE(5, "UCS4BE"),
-    EBCDIC(6, "EBCDIC"),
-    UCS4_2143(7, "ICS4-2143"),
-    UCS4_3412(8, "UCS4-3412"),
-    UCS2(9, "UCS2"),
-    ISO_8859_1(10, "ISO-8859-1"),
-    ISO_8859_2(11, "ISO-8859-2"),
-    ISO_8859_3(12, "ISO-8859-3"),
-    ISO_8859_4(13, "ISO-8859-4"),
-    ISO_8859_5(14, "ISO-8859-5"),
-    ISO_8859_6(15, "ISO-8859-6"),
-    ISO_8859_7(16, "ISO-8859-7"),
-    ISO_8859_8(17, "ISO-8859-8"),
-    ISO_8859_9(18, "ISO-8859-9"),
-    ISO_2022_JP(19, "ISO-2022-JP"),
-    SHIFT_JIS(20, "SHIFT-JIS"),
-    EUC_JP(21, "EUC-JP"),
-    ASCII(22, "ASCII");
-
-    private final int value;
-    private final String name;
-
-    EncodingType(int value, String name)
-    {
-      this.value = value;
-      this.name = name;
-    }
-
-    public int getValue()
-    {
-      return value;
-    }
-
-    public String toString()
-    {
-      return name;
-    }
-
-    private static transient EncodingType[] values;
-
-    // NOTE: assuming ordinal == value
-    static EncodingType get(final int ordinal)
-    {
-      EncodingType[] values = EncodingType.values;
-      if (values == null) {
-        values = EncodingType.values();
-        EncodingType.values = values;
+    String java_encoding = null;
+    if (encoding != context.runtime.getNil()) {
+      if (!(encoding instanceof RubyEncoding)) {
+        throw context.runtime.newTypeError("encoding must be kind_of Encoding");
       }
-      if (ordinal >= 0 && ordinal < values.length) {
-        return values[ordinal];
-      }
-      return null;
+      java_encoding = ((RubyEncoding)encoding).toString();
     }
 
-  }
-
-  private static String
-  findEncodingName(final int value)
-  {
-    EncodingType type = EncodingType.get(value);
-    if (type == null) { return null; }
-    assert type.value == value;
-    return type.name;
-  }
-
-  private static String
-  findEncodingName(ThreadContext context, IRubyObject encoding)
-  {
-    String rubyEncoding = null;
-    if (encoding instanceof RubyString) {
-      rubyEncoding = rubyStringToString((RubyString) encoding);
-    } else if (encoding instanceof RubyFixnum) {
-      rubyEncoding = findEncodingName(RubyFixnum.fix2int((RubyFixnum) encoding));
-    }
-    if (rubyEncoding == null) { return null; }
-    try {
-      return Charset.forName(rubyEncoding).displayName();
-    } catch (UnsupportedCharsetException e) {
-      throw context.getRuntime().newEncodingCompatibilityError(rubyEncoding + "is not supported");
-    } catch (IllegalCharsetNameException e) {
-      throw context.getRuntime().newEncodingError(e.getMessage());
-    }
-  }
-
-  private static final Pattern CHARSET_PATTERN = Pattern.compile("charset(()|\\s)=(()|\\s)([a-z]|-|_|\\d)+",
-      Pattern.CASE_INSENSITIVE);
+    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
+    ctx.setStringInputSourceNoEnc(context, data, context.runtime.getNil());
 
-  private static CharSequence
-  applyEncoding(final String input, final String enc)
-  {
-    int start_pos = 0;
-    int end_pos = 0;
-    if (containsIgnoreCase(input, "charset")) {
-      Matcher m = CHARSET_PATTERN.matcher(input);
-      while (m.find()) {
-        start_pos = m.start();
-        end_pos = m.end();
-      }
+    if (java_encoding != null) {
+      ctx.getInputSource().setEncoding(java_encoding);
     }
-    if (start_pos != end_pos) {
-      return new StringBuilder(input).replace(start_pos, end_pos, "charset=" + enc);
-    }
-    return input;
-  }
 
-  private static boolean
-  containsIgnoreCase(final String str, final String sub)
-  {
-    final int len = sub.length();
-    final int max = str.length() - len;
-
-    if (len == 0) { return true; }
-    final char c0Lower = Character.toLowerCase(sub.charAt(0));
-    final char c0Upper = Character.toUpperCase(sub.charAt(0));
-
-    for (int i = 0; i <= max; i++) {
-      final char ch = str.charAt(i);
-      if (ch != c0Lower && Character.toLowerCase(ch) != c0Lower && Character.toUpperCase(ch) != c0Upper) {
-        continue; // first char doesn't match
-      }
-
-      if (str.regionMatches(true, i + 1, sub, 0 + 1, len - 1)) {
-        return true;
-      }
-    }
-    return false;
+    return ctx;
   }
 
-  @JRubyMethod(name = "file", meta = true)
+  @JRubyMethod(name = "native_file", meta = true)
   public static IRubyObject
-  parse_file(ThreadContext context,
-             IRubyObject klass,
-             IRubyObject data,
-             IRubyObject encoding)
+  parse_file(ThreadContext context, IRubyObject klass, IRubyObject data, IRubyObject encoding)
   {
-    if (!(data instanceof RubyString)) {
-      throw context.getRuntime().newTypeError("data must be kind_of String");
-    }
-    if (!(encoding instanceof RubyString)) {
-      throw context.getRuntime().newTypeError("data must be kind_of String");
+    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();
     }
 
     Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klass);
     ctx.setInputSourceFile(context, data);
-    String javaEncoding = findEncodingName(context, encoding);
-    if (javaEncoding != null) {
-      ctx.getInputSource().setEncoding(javaEncoding);
+
+    if (java_encoding != null) {
+      ctx.getInputSource().setEncoding(java_encoding);
     }
+
     return ctx;
   }
 
-  @JRubyMethod(name = "io", meta = true)
+  @JRubyMethod(name = "native_io", meta = true)
   public static IRubyObject
-  parse_io(ThreadContext context,
-           IRubyObject klass,
-           IRubyObject data,
-           IRubyObject encoding)
+  parse_io(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
   {
-    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");
     }
 
-    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klass);
+    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();
+    }
+
+    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
     ctx.setIOInputSource(context, data, context.nil);
-    String javaEncoding = findEncodingName(context, encoding);
-    if (javaEncoding != null) {
-      ctx.getInputSource().setEncoding(javaEncoding);
+
+    if (java_encoding != null) {
+      ctx.getInputSource().setEncoding(java_encoding);
     }
+
     return ctx;
   }
 

data/ext/java/nokogiri/NokogiriService.java

@@ -37,7 +37,7 @@ public class NokogiriService implements BasicLibraryService
   }
 
   private static Map<String, RubyClass>
-  populateNokogiriClassCahce(Ruby ruby)
+  populateNokogiriClassCache(Ruby ruby)
   {
     Map<String, RubyClass> nokogiriClassCache = new HashMap<String, RubyClass>();
     nokogiriClassCache.put("Nokogiri::HTML4::Document", (RubyClass)ruby.getClassFromPath("Nokogiri::HTML4::Document"));
@@ -91,7 +91,7 @@ public class NokogiriService implements BasicLibraryService
     createDocuments(ruby, xmlModule, htmlModule, xmlNode);
     createSaxModule(ruby, xmlSaxModule, htmlSaxModule);
     createXsltModule(ruby, xsltModule);
-    nokogiri.setInternalVariable("cache", populateNokogiriClassCahce(ruby));
+    nokogiri.setInternalVariable("cache", populateNokogiriClassCache(ruby));
   }
 
   private void

data/ext/java/nokogiri/XmlCdata.java

@@ -46,6 +46,9 @@ public class XmlCdata extends XmlText
     IRubyObject rbDocument = args[0];
     content = args[1];
 
+    if (content.isNil()) {
+      throw context.runtime.newTypeError("expected second parameter to be a String, received NilClass");
+    }
     if (!(rbDocument instanceof XmlNode)) {
       String msg = "expected first parameter to be a Nokogiri::XML::Document, received " + rbDocument.getMetaClass();
       throw context.runtime.newTypeError(msg);

data/ext/java/nokogiri/XmlDocument.java

@@ -414,20 +414,13 @@ public class XmlDocument extends XmlNode
     return getCachedNodeOrCreate(context.runtime, rootNode);
   }
 
-  protected IRubyObject
-  dup_implementation(Ruby runtime, boolean deep)
-  {
-    XmlDocument doc = (XmlDocument) super.dup_implementation(runtime, deep);
-    // Avoid creating a new XmlDocument since we cloned one
-    // already. Otherwise the following test will fail:
-    //
-    //   dup = doc.dup
-    //   dup.equal?(dup.children[0].document)
-    //
-    // Since `dup.children[0].document' will end up creating a new
-    // XmlDocument.  See #1060.
-    doc.resetCache();
-    return doc;
+  @JRubyMethod(visibility = Visibility.PROTECTED)
+  public IRubyObject
+  initialize_copy_with_args(ThreadContext context, IRubyObject other, IRubyObject level)
+  {
+    super.initialize_copy_with_args(context, other, level, null);
+    resetCache();
+    return this;
   }
 
   @JRubyMethod(name = "root=")

data/ext/java/nokogiri/XmlDocumentFragment.java

@@ -48,112 +48,24 @@ public class XmlDocumentFragment extends XmlNode
     super(ruby, klazz);
   }
 
-  @JRubyMethod(name = "new", meta = true, required = 1, optional = 3)
+  @JRubyMethod(name = "native_new", meta = true)
   public static IRubyObject
-  rbNew(ThreadContext context, IRubyObject cls, IRubyObject[] args, Block block)
+  rbNew(ThreadContext context, IRubyObject cls, IRubyObject value)
   {
-    if (args.length < 1) {
-      throw context.runtime.newArgumentError(args.length, 1);
-    }
-
-    if (!(args[0] instanceof XmlDocument)) {
+    if (!(value instanceof XmlDocument)) {
       throw context.runtime.newArgumentError("first parameter must be a Nokogiri::XML::Document instance");
     }
 
-    XmlDocument doc = (XmlDocument) args[0];
-
-    // make wellformed fragment, ignore invalid namespace, or add appropriate namespace to parse
-    if (args.length > 1 && args[1] instanceof RubyString) {
-      final RubyString arg1 = (RubyString) args[1];
-      if (XmlDocumentFragment.isTag(arg1)) {
-        args[1] = RubyString.newString(context.runtime, addNamespaceDeclIfNeeded(doc, rubyStringToString(arg1)));
-      }
-    }
+    XmlDocument doc = (XmlDocument) value;
 
     XmlDocumentFragment fragment = (XmlDocumentFragment) NokogiriService.XML_DOCUMENT_FRAGMENT_ALLOCATOR.allocate(
                                      context.runtime, (RubyClass)cls);
     fragment.setDocument(context, doc);
     fragment.setNode(context.runtime, doc.getDocument().createDocumentFragment());
 
-    Helpers.invoke(context, fragment, "initialize", args, block);
     return fragment;
   }
 
-  private static final ByteList TAG_BEG = ByteList.create("<");
-  private static final ByteList TAG_END = ByteList.create(">");
-
-  private static boolean
-  isTag(final RubyString str)
-  {
-    return str.getByteList().startsWith(TAG_BEG) && str.getByteList().endsWith(TAG_END);
-  }
-
-  private static boolean
-  isNamespaceDefined(String qName, NamedNodeMap nodeMap)
-  {
-    if (isNamespace(qName.intern())) { return true; }
-    for (int i = 0; i < nodeMap.getLength(); i++) {
-      Attr attr = (Attr)nodeMap.item(i);
-      if (isNamespace(attr.getNodeName())) {
-        String localPart = getLocalNameForNamespace(attr.getNodeName(), null);
-        if (getPrefix(qName).equals(localPart)) {
-          return true;
-        }
-      }
-    }
-    return false;
-  }
-
-  private static final Pattern QNAME_RE = Pattern.compile("[^</:>\\s]+:[^</:>=\\s]+");
-  private static final Pattern START_TAG_RE = Pattern.compile("<[^</>]+>");
-
-  private static String
-  addNamespaceDeclIfNeeded(XmlDocument doc, String tags)
-  {
-    if (doc.getDocument() == null) { return tags; }
-    if (doc.getDocument().getDocumentElement() == null) { return tags; }
-    Matcher matcher = START_TAG_RE.matcher(tags);
-    Map<CharSequence, CharSequence> rewriteTable = null;
-    while (matcher.find()) {
-      String start_tag = matcher.group();
-      Matcher matcher2 = QNAME_RE.matcher(start_tag);
-      while (matcher2.find()) {
-        String qName = matcher2.group();
-        NamedNodeMap nodeMap = doc.getDocument().getDocumentElement().getAttributes();
-        if (isNamespaceDefined(qName, nodeMap)) {
-          CharSequence namespaceDecl = getNamespaceDecl(getPrefix(qName), nodeMap);
-          if (namespaceDecl != null) {
-            if (rewriteTable == null) { rewriteTable = new HashMap<CharSequence, CharSequence>(8, 1); }
-            StringBuilder str = new StringBuilder(qName.length() + namespaceDecl.length() + 3);
-            String key = str.append('<').append(qName).append('>').toString();
-            str.setCharAt(key.length() - 1, ' '); // (last) '>' -> ' '
-            rewriteTable.put(key, str.append(namespaceDecl).append('>'));
-          }
-        }
-      }
-    }
-    if (rewriteTable != null) {
-      for (Map.Entry<CharSequence, CharSequence> e : rewriteTable.entrySet()) {
-        tags = tags.replace(e.getKey(), e.getValue());
-      }
-    }
-
-    return tags;
-  }
-
-  private static CharSequence
-  getNamespaceDecl(final String prefix, NamedNodeMap nodeMap)
-  {
-    for (int i = 0; i < nodeMap.getLength(); i++) {
-      Attr attr = (Attr) nodeMap.item(i);
-      if (prefix.equals(attr.getLocalName())) {
-        return new StringBuilder().
-               append(attr.getName()).append('=').append('"').append(attr.getValue()).append('"');
-      }
-    }
-    return null;
-  }
-
   @Override
   public void
   relink_namespace(ThreadContext context)

data/ext/java/nokogiri/XmlDtd.java

@@ -141,7 +141,7 @@ public class XmlDtd extends XmlNode
    *
    * NekoDTD parser returns a new document node containing elements
    * representing the dtd declarations. The plan is to get the root
-   * element and adopt it into the correct document, stipping the
+   * element and adopt it into the correct document, stripping the
    * Document provided by NekoDTD.
    *
    */
@@ -454,7 +454,7 @@ public class XmlDtd extends XmlNode
    * This recursive function will not descend into an
    * 'externalSubset' node, thus for an internal subset it only
    * extracts nodes in the internal subset, and for an external
-   * subset it extracts everything and assumess <code>node</code>
+   * subset it extracts everything and assumes <code>node</code>
    * and all children are part of the external subset.
    */
   protected IRubyObject[]

data/ext/java/nokogiri/XmlEntityReference.java

@@ -61,19 +61,23 @@ public class XmlEntityReference extends XmlNode
   public void
   accept(ThreadContext context, SaveContextVisitor visitor)
   {
+    //
+    // Note that when noEnt is set, we call setFeature(FEATURE_NOT_EXPAND_ENTITY, false) in
+    // XmlDomParserContext.
+    //
+    // See https://xerces.apache.org/xerces-j/features.html section on `create-entity-ref-nodes`
+    //
+    // When set to true (the default), then EntityReference nodes are present in the DOM tree, and
+    // its children represent the replacement text. When set to false, then the EntityReference is
+    // not present in the tree, and instead the replacement text nodes are present.
+    //
+    // So: if we are here, then noEnt must be true, and we should just serialize the EntityReference
+    // and not worry about the replacement text. When noEnt is false, we would never this and
+    // instead would be serializing the replacement text.
+    //
+    // https://github.com/sparklemotion/nokogiri/issues/3270
+    //
     visitor.enter(node);
-    Node child = node.getFirstChild();
-    while (child != null) {
-      IRubyObject nokoNode = getCachedNodeOrCreate(context.getRuntime(), child);
-      if (nokoNode instanceof XmlNode) {
-        XmlNode cur = (XmlNode) nokoNode;
-        cur.accept(context, visitor);
-      } else if (nokoNode instanceof XmlNamespace) {
-        XmlNamespace cur = (XmlNamespace) nokoNode;
-        cur.accept(context, visitor);
-      }
-      child = child.getNextSibling();
-    }
     visitor.leave(node);
   }
 }