introduce html4 namespace

.yardopts

@@ -1,5 +1,8 @@
 --embed-mixins
 --main=README.md
+--exclude=lib/nokogiri/css/tokenizer.rb
+--exclude=lib/nokogiri/css/parser.rb
+--exclude=ext/nokogiri/test_global_handlers.c
 lib/**/*.rb
 ext/nokogiri/*.c
 -

CHANGELOG.md

@@ -6,17 +6,25 @@ Nokogiri follows [Semantic Versioning](https://semver.org/), please see the [REA
 
 ## next / unreleased
 
-### Added
+### Notable Addition: HTML5 Support (CRuby only)
 
 __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).
 
-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. 🙌
 
-#### Other
+
+### Notable Change: `Nokogiri::HTML4` module and namespace
+
+`Nokogiri::HTML` has been renamed to `Nokogiri::HTML4`, and `Nokogiri::HTML` is aliased to preserve backwards-compatibility. `Nokogiri::HTML` and `Nokogiri::HTML4` parse methods still use libxml2's (or NekoHTML's) HTML4 parser in the v1.12 release series. 
+
+Take special note that if you rely on the class name of an object in your code, objects will now report a class of `Nokogiri::HTML4::Foo` where they previously reported `Nokogiri::HTML::Foo`. Instead of relying on the string returned by `Object#class`, prefer `Class#===` or `Object#is_a?` or `Object#instance_of?`.
+
+Future releases of Nokogiri may deprecate `HTML` methods or otherwise change this behavior, so please start using `HTML4` in place of `HTML`.
+
+
+### Added
 
 * [CRuby] `Nokogiri::VERSION_INFO["libxslt"]["datetime_enabled"]` is a new boolean value which describes whether libxslt (or, more properly, libexslt) has compiled-in datetime support. This generally going to be `true`, but some distros ship without this support (e.g., some mingw UCRT-based packages, see https://github.com/msys2/MINGW-packages/pull/8957). See [#2272](https://github.com/sparklemotion/nokogiri/issues/2272) for more details.
 
@@ -38,6 +46,11 @@ Many thanks to Sam Ruby, Steve Checkoway, and Craig Barnes for creating and main
 * [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.)
 
 
+### Deprecated
+
+* Deprecating Nokogumbo's `Nokogiri::HTML5.get`. This method will be removed in a future version of Nokogiri.
+
+
 ### Dependencies
 
 * [CRuby] Upgrade mini_portile2 dependency from `~> 2.5.0` to `~> 2.6.1`. ("ruby" platform gem only.)

README.md

@@ -14,7 +14,7 @@ Some guiding principles Nokogiri tries to follow:
 
 ## Features Overview
 
-- DOM Parser for XML and HTML4
+- DOM Parser for XML, HTML4, and HTML5
 - SAX Parser for XML and HTML4
 - Push Parser for XML and HTML4
 - Document search via XPath 1.0

ext/java/nokogiri/HtmlDocument.java → ext/java/nokogiri/Html4Document.java

@@ -18,13 +18,13 @@
 import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
 
 /**
- * Class for Nokogiri::HTML::Document.
+ * Class for Nokogiri::HTML4::Document.
  *
  * @author sergio
  * @author Yoko Harada <yokolet@gmail.com>
  */
-@JRubyClass(name = "Nokogiri::HTML::Document", parent = "Nokogiri::XML::Document")
-public class HtmlDocument extends XmlDocument
+@JRubyClass(name = "Nokogiri::HTML4::Document", parent = "Nokogiri::XML::Document")
+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";
@@ -33,19 +33,19 @@ public class HtmlDocument extends XmlDocument
   private String parsed_encoding = null;
 
   public
-  HtmlDocument(Ruby ruby, RubyClass klazz)
+  Html4Document(Ruby ruby, RubyClass klazz)
   {
     super(ruby, klazz);
   }
 
   public
-  HtmlDocument(Ruby runtime, Document document)
+  Html4Document(Ruby runtime, Document document)
   {
     this(runtime, getNokogiriClass(runtime, "Nokogiri::XML::Document"), document);
   }
 
   public
-  HtmlDocument(Ruby ruby, RubyClass klazz, Document doc)
+  Html4Document(Ruby ruby, RubyClass klazz, Document doc)
   {
     super(ruby, klazz, doc);
   }
@@ -55,10 +55,10 @@ public class HtmlDocument extends XmlDocument
   rbNew(ThreadContext context, IRubyObject klazz, IRubyObject[] args)
   {
     final Ruby runtime = context.runtime;
-    HtmlDocument htmlDocument;
+    Html4Document htmlDocument;
     try {
       Document docNode = createNewDocument(runtime);
-      htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(runtime, (RubyClass) klazz);
+      htmlDocument = (Html4Document) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(runtime, (RubyClass) klazz);
       htmlDocument.setDocumentNode(context.runtime, docNode);
     } catch (Exception ex) {
       throw asRuntimeError(runtime, "couldn't create document: ", ex);
@@ -135,13 +135,6 @@ public class HtmlDocument extends XmlDocument
     return parsed_encoding;
   }
 
-  /*
-   * call-seq:
-   *  read_io(io, url, encoding, options)
-   *
-   * Read the HTML document from +io+ with given +url+, +encoding+,
-   * and +options+.  See Nokogiri::HTML.parse
-   */
   @JRubyMethod(meta = true, required = 4)
   public static IRubyObject
   read_io(ThreadContext context, IRubyObject klass, IRubyObject[] args)
@@ -151,13 +144,6 @@ public class HtmlDocument extends XmlDocument
     return ctx.parse(context, (RubyClass) klass, args[1]);
   }
 
-  /*
-   * call-seq:
-   *  read_memory(string, url, encoding, options)
-   *
-   * Read the HTML document contained in +string+ with given +url+, +encoding+,
-   * and +options+.  See Nokogiri::HTML.parse
-   */
   @JRubyMethod(meta = true, required = 4)
   public static IRubyObject
   read_memory(ThreadContext context, IRubyObject klass, IRubyObject[] args)

ext/java/nokogiri/HtmlElementDescription.java → ext/java/nokogiri/Html4ElementDescription.java

@@ -16,12 +16,12 @@
 import org.jruby.runtime.builtin.IRubyObject;
 
 /**
- * Class for Nokogiri::HTML::ElementDescription.
+ * Class for Nokogiri::HTML4::ElementDescription.
  *
  * @author Patrick Mahoney <pat@polycrystal.org>
  */
-@JRubyClass(name = "Nokogiri::HTML::ElementDescription")
-public class HtmlElementDescription extends RubyObject
+@JRubyClass(name = "Nokogiri::HTML4::ElementDescription")
+public class Html4ElementDescription extends RubyObject
 {
 
   /**
@@ -38,7 +38,7 @@ public class HtmlElementDescription extends RubyObject
   protected HTMLElements.Element element;
 
   public
-  HtmlElementDescription(Ruby runtime, RubyClass rubyClass)
+  Html4ElementDescription(Ruby runtime, RubyClass rubyClass)
   {
     super(runtime, rubyClass);
   }
@@ -89,8 +89,8 @@ public class HtmlElementDescription extends RubyObject
       return context.nil;
     }
 
-    HtmlElementDescription desc =
-      new HtmlElementDescription(context.getRuntime(), (RubyClass)klazz);
+    Html4ElementDescription desc =
+      new Html4ElementDescription(context.getRuntime(), (RubyClass)klazz);
     desc.element = elem;
     return desc;
   }

ext/java/nokogiri/HtmlEntityLookup.java → ext/java/nokogiri/Html4EntityLookup.java

@@ -12,16 +12,16 @@
 import org.jruby.runtime.builtin.IRubyObject;
 
 /**
- * Class for Nokogiri::HTML::EntityLookup.
+ * Class for Nokogiri::HTML4::EntityLookup.
  *
  * @author Patrick Mahoney <pat@polycrystal.org>
  */
-@JRubyClass(name = "Nokogiri::HTML::EntityLookup")
-public class HtmlEntityLookup extends RubyObject
+@JRubyClass(name = "Nokogiri::HTML4::EntityLookup")
+public class Html4EntityLookup extends RubyObject
 {
 
   public
-  HtmlEntityLookup(Ruby runtime, RubyClass rubyClass)
+  Html4EntityLookup(Ruby runtime, RubyClass rubyClass)
   {
     super(runtime, rubyClass);
   }
@@ -41,7 +41,7 @@ public class HtmlEntityLookup extends RubyObject
     if (val == -1) { return ruby.getNil(); }
 
     IRubyObject edClass =
-      ruby.getClassFromPath("Nokogiri::HTML::EntityDescription");
+      ruby.getClassFromPath("Nokogiri::HTML4::EntityDescription");
     IRubyObject edObj = invoke(context, edClass, "new",
                                ruby.newFixnum(val), ruby.newString(name),
                                ruby.newString(name + " entity"));

ext/java/nokogiri/HtmlSaxParserContext.java → ext/java/nokogiri/Html4SaxParserContext.java

@@ -24,27 +24,27 @@
 import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
 
 /**
- * Class for Nokogiri::HTML::SAX::ParserContext.
+ * Class for Nokogiri::HTML4::SAX::ParserContext.
  *
  * @author serabe
  * @author Patrick Mahoney <pat@polycrystal.org>
  * @author Yoko Harada <yokolet@gmail.com>
  */
 
-@JRubyClass(name = "Nokogiri::HTML::SAX::ParserContext", parent = "Nokogiri::XML::SAX::ParserContext")
-public class HtmlSaxParserContext extends XmlSaxParserContext
+@JRubyClass(name = "Nokogiri::HTML4::SAX::ParserContext", parent = "Nokogiri::XML::SAX::ParserContext")
+public class Html4SaxParserContext extends XmlSaxParserContext
 {
 
-  static HtmlSaxParserContext
+  static Html4SaxParserContext
   newInstance(final Ruby runtime, final RubyClass klazz)
   {
-    HtmlSaxParserContext instance = new HtmlSaxParserContext(runtime, klazz);
+    Html4SaxParserContext instance = new Html4SaxParserContext(runtime, klazz);
     instance.initialize(runtime);
     return instance;
   }
 
   public
-  HtmlSaxParserContext(Ruby ruby, RubyClass rubyClass)
+  Html4SaxParserContext(Ruby ruby, RubyClass rubyClass)
   {
     super(ruby, rubyClass);
   }
@@ -68,7 +68,7 @@ public class HtmlSaxParserContext extends XmlSaxParserContext
       return parser;
     } catch (SAXException ex) {
       throw new SAXException(
-        "Problem while creating HTML SAX Parser: " + ex.toString());
+        "Problem while creating HTML4 SAX Parser: " + ex.toString());
     }
   }
 
@@ -79,7 +79,7 @@ public class HtmlSaxParserContext extends XmlSaxParserContext
                IRubyObject data,
                IRubyObject encoding)
   {
-    HtmlSaxParserContext ctx = HtmlSaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
+    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
     String javaEncoding = findEncodingName(context, encoding);
     if (javaEncoding != null) {
       CharSequence input = applyEncoding(rubyStringToString(data.convertToString()), javaEncoding);
@@ -231,7 +231,7 @@ static EncodingType get(final int ordinal)
              IRubyObject data,
              IRubyObject encoding)
   {
-    HtmlSaxParserContext ctx = HtmlSaxParserContext.newInstance(context.runtime, (RubyClass) klass);
+    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klass);
     ctx.setInputSourceFile(context, data);
     String javaEncoding = findEncodingName(context, encoding);
     if (javaEncoding != null) {
@@ -247,7 +247,7 @@ static EncodingType get(final int ordinal)
            IRubyObject data,
            IRubyObject encoding)
   {
-    HtmlSaxParserContext ctx = HtmlSaxParserContext.newInstance(context.runtime, (RubyClass) klass);
+    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klass);
     ctx.setIOInputSource(context, data, context.nil);
     String javaEncoding = findEncodingName(context, encoding);
     if (javaEncoding != null) {
@@ -258,12 +258,12 @@ static EncodingType get(final int ordinal)
 
   /**
    * Create a new parser context that will read from a raw input stream.
-   * Meant to be run in a separate thread by HtmlSaxPushParser.
+   * Meant to be run in a separate thread by Html4SaxPushParser.
    */
-  static HtmlSaxParserContext
+  static Html4SaxParserContext
   parse_stream(final Ruby runtime, RubyClass klass, InputStream stream)
   {
-    HtmlSaxParserContext ctx = HtmlSaxParserContext.newInstance(runtime, klass);
+    Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(runtime, klass);
     ctx.setInputSource(stream);
     return ctx;
   }

ext/java/nokogiri/HtmlSaxPushParser.java → ext/java/nokogiri/Html4SaxPushParser.java

@@ -27,25 +27,25 @@
 import org.jruby.runtime.builtin.IRubyObject;
 
 /**
- * Class for Nokogiri::HTML::SAX::PushParser
+ * Class for Nokogiri::HTML4::SAX::PushParser
  *
  * @author
  * @author Piotr Szmielew <p.szmielew@ava.waw.pl> - based on Nokogiri::XML::SAX::PushParser
  */
-@JRubyClass(name = "Nokogiri::HTML::SAX::PushParser")
-public class HtmlSaxPushParser extends RubyObject
+@JRubyClass(name = "Nokogiri::HTML4::SAX::PushParser")
+public class Html4SaxPushParser extends RubyObject
 {
   ParserContext.Options options;
   IRubyObject saxParser;
 
   NokogiriBlockingQueueInputStream stream;
 
   private ParserTask parserTask = null;
-  private FutureTask<HtmlSaxParserContext> futureTask = null;
+  private FutureTask<Html4SaxParserContext> futureTask = null;
   private ExecutorService executor = null;
 
   public
-  HtmlSaxPushParser(Ruby ruby, RubyClass rubyClass)
+  Html4SaxPushParser(Ruby ruby, RubyClass rubyClass)
   {
     super(ruby, rubyClass);
   }
@@ -111,7 +111,7 @@ public class HtmlSaxPushParser extends RubyObject
     final ByteArrayInputStream data = NokogiriHelpers.stringBytesToStream(chunk);
     if (data == null) {
       terminateTask(context.runtime);
-      throw XmlSyntaxError.createHTMLSyntaxError(context.runtime).toThrowable(); // Nokogiri::HTML::SyntaxError
+      throw XmlSyntaxError.createHTMLSyntaxError(context.runtime).toThrowable(); // Nokogiri::HTML4::SyntaxError
     }
 
     int errorCount0 = parserTask.getErrorCount();
@@ -149,12 +149,12 @@ public class HtmlSaxPushParser extends RubyObject
 
       assert saxParser != null : "saxParser null";
       parserTask = new ParserTask(context, saxParser, stream);
-      futureTask = new FutureTask<HtmlSaxParserContext>((Callable) parserTask);
+      futureTask = new FutureTask<Html4SaxParserContext>((Callable) parserTask);
       executor = Executors.newSingleThreadExecutor(new ThreadFactory() {
         @Override
         public Thread newThread(Runnable r) {
           Thread t = new Thread(r);
-          t.setName("HtmlSaxPushParser");
+          t.setName("Html4SaxPushParser");
           t.setDaemon(true);
           return t;
         }
@@ -187,14 +187,14 @@ public Thread newThread(Runnable r) {
     futureTask = null;
   }
 
-  private static HtmlSaxParserContext
+  private static Html4SaxParserContext
   parse(final Ruby runtime, final InputStream stream)
   {
-    RubyClass klazz = getNokogiriClass(runtime, "Nokogiri::HTML::SAX::ParserContext");
-    return HtmlSaxParserContext.parse_stream(runtime, klazz, stream);
+    RubyClass klazz = getNokogiriClass(runtime, "Nokogiri::HTML4::SAX::ParserContext");
+    return Html4SaxParserContext.parse_stream(runtime, klazz, stream);
   }
 
-  static class ParserTask extends XmlSaxPushParser.ParserTask /* <HtmlSaxPushParser> */
+  static class ParserTask extends XmlSaxPushParser.ParserTask /* <Html4SaxPushParser> */
   {
 
     private
@@ -204,10 +204,10 @@ static class ParserTask extends XmlSaxPushParser.ParserTask /* <HtmlSaxPushParse
     }
 
     @Override
-    public HtmlSaxParserContext
+    public Html4SaxParserContext
     call() throws Exception
     {
-      return (HtmlSaxParserContext) super.call();
+      return (Html4SaxParserContext) super.call();
     }
 
   }