[Java.Interop.Tools.JavaSource] Support html tags with attributes (#1286)

pjcollins · web-flow · commit fe00cef5290a · 2025-01-07T15:56:25.000-05:00
Context: dotnet/android#9647 dotnet/android#9647 attempted to import API docs for API 35, and produced the following warning: The following issues were found, review the build log for more details: > ## Unable to translate remarks for android/app/admin/DevicePolicyManager: > JavadocImport-Error (31:39): Syntax error, expected: </p>, </P>, #PCDATA, <tt>, <TT>, <i>, <I>, <a attr=, <code>, {@code, {@docroot}, {@inheritdoc}, {@link, {@linkplain, {@literal, {@see, {@value}, {@value, IgnorableDeclaration, {@param, UnknownHtmlElementStart, <p>, <P>, <pre , @author, @apiSince, @deprecated, @deprecatedSince, @exception, @inheritdoc, @hide, @param, @return, @see, @Serialdata, @serialField, @SInCE, @throws, @[unknown], @Version <li>A <i id="deviceowner">Device Owner</i>, which only ever exists on the ^ Parsing logic fails here because the `<i>` tag has an `id` attribute _and_ is present in an open `<p>` tag. Turns Out™ that HTML allows attributes on nearly *everything*; e.g. from [§3.2.3 Global attributes][0]: > The following attributes are common to and may be specified on all > [HTML elements](https://dev.w3.org/html5/spec-LC/infrastructure.html#html-elements) > (even those not defined in this specification): > * … > * `id` Given this, it doesn't make sense for `CreateStartElement()` to not allow any attributes. Update `CreateStartElement()` so that *all* elements *ignore* any specified attributes (by default), which allows `<i id="deviceowner">Device Owner</i>` to work. The regex used has also been improved to include word boundaries around the tag name to make sure that it does not match unexpected elements. [0]: https://dev.w3.org/html5/spec-LC/elements.html#global-attributes
diff --git a/src/Java.Interop.Tools.JavaSource/Java.Interop.Tools.JavaSource/SourceJavadocToXmldocGrammar.HtmlBnfTerms.cs b/src/Java.Interop.Tools.JavaSource/Java.Interop.Tools.JavaSource/SourceJavadocToXmldocGrammar.HtmlBnfTerms.cs
@@ -66,7 +66,7 @@ internal void CreateRules (SourceJavadocToXmldocGrammar grammar)
 				var fontstyle_i     = CreateHtmlToCrefElement (grammar, "i",    "i", InlineDeclarations, optionalEnd: true);
 
 				var preText = new PreBlockDeclarationBodyTerminal ();
-				PreBlockDeclaration.Rule = CreateStartElementIgnoreAttribute ("pre") + preText + CreateEndElement ("pre", grammar, optional: true);
+				PreBlockDeclaration.Rule = CreateStartElement ("pre") + preText + CreateEndElement ("pre", grammar, optional: true);
 				PreBlockDeclaration.AstConfig.NodeCreator = (context, parseNode) => {
 					if (!grammar.ShouldImport (ImportJavadoc.Remarks)) {
 						parseNode.AstNode   = "";
@@ -82,7 +82,7 @@ internal void CreateRules (SourceJavadocToXmldocGrammar grammar)
 				FontStyleDeclaration.Rule = fontstyle_tt | fontstyle_i;
 
 				PBlockDeclaration.Rule =
-					CreateStartElement ("p", grammar) + InlineDeclarations + CreateEndElement ("p", grammar, optional:true)
+					CreateStartElement ("p") + InlineDeclarations + CreateEndElement ("p", grammar, optional:true)
 					;
 				PBlockDeclaration.AstConfig.NodeCreator = (context, parseNode) => {
 					var remarks     = FinishParse (context, parseNode).Remarks;
@@ -260,7 +260,7 @@ static string GetChildNodesAsString (ParseTreeNode parseNode)
 
 			static NonTerminal CreateHtmlToCrefElement (Grammar grammar, string htmlElement, string crefElement, BnfTerm body, bool optionalEnd = false)
 			{
-				var start       = CreateStartElement (htmlElement, grammar);
+				var start       = CreateStartElement (htmlElement);
 				var end         = CreateEndElement (htmlElement, grammar, optionalEnd);
 				var nonTerminal = new NonTerminal ("<" + htmlElement + ">", ConcatChildNodes) {
 					Rule = start + body + end,
@@ -275,28 +275,15 @@ static NonTerminal CreateHtmlToCrefElement (Grammar grammar, string htmlElement,
 				return nonTerminal;
 			}
 
-			static NonTerminal CreateStartElement (string startElement, Grammar grammar)
+			static RegexBasedTerminal CreateStartElement (string startElement, string attribute = "")
 			{
-				var start   = new NonTerminal ("<" + startElement + ">", nodeCreator: (context, parseNode) => parseNode.AstNode = "") {
-					Rule    = grammar.ToTerm ("<" + startElement + ">") | "<" + startElement.ToUpperInvariant () + ">",
-				};
-				return start;
-			}
-
-			static RegexBasedTerminal CreateStartElementIgnoreAttribute (string startElement, string attribute)
-			{
-				return new RegexBasedTerminal ($"<{startElement} {attribute}", $@"(?i)<{startElement}\s*{attribute}[^>]*>") {
+				return new RegexBasedTerminal ($"<{startElement} {attribute}>", $@"(?i)<\b{startElement}\b\s*{attribute}[^>]*>") {
 					AstConfig = new AstNodeConfig {
 						NodeCreator = (context, parseNode) => parseNode.AstNode = "",
 					},
 				};
 			}
 
-			static RegexBasedTerminal CreateStartElementIgnoreAttribute (string startElement)
-			{
-				return CreateStartElementIgnoreAttribute (startElement, "");
-			}
-
 			static NonTerminal CreateEndElement (string endElement, Grammar grammar, bool optional = false)
 			{
 				var end	    = new NonTerminal (endElement, nodeCreator: (context, parseNode) => parseNode.AstNode = "") {
diff --git a/tests/Java.Interop.Tools.JavaSource-Tests/SourceJavadocToXmldocGrammar.HtmlBnfTermsTests.cs b/tests/Java.Interop.Tools.JavaSource-Tests/SourceJavadocToXmldocGrammar.HtmlBnfTermsTests.cs
@@ -34,6 +34,10 @@ public void PBlockDeclaration ()
 			r = p.Parse("<p>r= <em>unknown</em> text");
 			Assert.IsFalse (r.HasErrors (), DumpMessages (r, p));
 			Assert.AreEqual ("<para>r= &lt;em&gt;unknown&lt;/em&gt; text</para>", r.Root.AstNode.ToString ());
+
+			r = p.Parse ("<p>For <li>A <i id=\"deviceowner\">Device Owner</i>");
+			Assert.IsFalse (r.HasErrors (), DumpMessages (r, p));
+			Assert.AreEqual ("<para>For &lt;li&gt;A <i>Device Owner</i></para>", r.Root.AstNode.ToString ());
 		}
 
 		[Test]
