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

Context: dotnet/android#9647dotnet/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

Author: pjcollins

src/Java.Interop.Tools.JavaSource/Java.Interop.Tools.JavaSource/SourceJavadocToXmldocGrammar.HtmlBnfTerms.cs

@@ -66,7 +66,7 @@ internal void CreateRules (SourceJavadocToXmldocGrammar grammar)
 varfontstyle_i=CreateHtmlToCrefElement(grammar,"i","i",InlineDeclarations,optionalEnd:true);
 
 varpreText=newPreBlockDeclarationBodyTerminal();
-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)=>{
 varremarks=FinishParse(context,parseNode).Remarks;
@@ -260,7 +260,7 @@ static string GetChildNodesAsString (ParseTreeNode parseNode)
 
 staticNonTerminalCreateHtmlToCrefElement(Grammargrammar,stringhtmlElement,stringcrefElement,BnfTermbody,booloptionalEnd=false)
 {
-varstart=CreateStartElement(htmlElement,grammar);
+varstart=CreateStartElement(htmlElement);
 varend=CreateEndElement(htmlElement,grammar,optionalEnd);
 varnonTerminal=newNonTerminal("<"+htmlElement+">",ConcatChildNodes){
 Rule=start+body+end,
@@ -275,28 +275,15 @@ static NonTerminal CreateHtmlToCrefElement (Grammar grammar, string htmlElement,
 returnnonTerminal;
 }
 
-staticNonTerminalCreateStartElement(stringstartElement,Grammargrammar)
+staticRegexBasedTerminalCreateStartElement(stringstartElement,stringattribute="")
 {
-varstart=newNonTerminal("<"+startElement+">",nodeCreator:(context,parseNode)=>parseNode.AstNode=""){
-Rule=grammar.ToTerm("<"+startElement+">")|"<"+startElement.ToUpperInvariant()+">",
-};
-returnstart;
-}
-
-staticRegexBasedTerminalCreateStartElementIgnoreAttribute(stringstartElement,stringattribute)
-{
-returnnewRegexBasedTerminal($"<{startElement}{attribute}",$@"(?i)<{startElement}\s*{attribute}[^>]*>"){
+returnnewRegexBasedTerminal($"<{startElement}{attribute}>",$@"(?i)<\b{startElement}\b\s*{attribute}[^>]*>"){
 AstConfig=newAstNodeConfig{
 NodeCreator=(context,parseNode)=>parseNode.AstNode="",
 },
 };
 }
 
-staticRegexBasedTerminalCreateStartElementIgnoreAttribute(stringstartElement)
-{
-returnCreateStartElementIgnoreAttribute(startElement,"");
-}
-
 staticNonTerminalCreateEndElement(stringendElement,Grammargrammar,booloptional=false)
 {
 varend=newNonTerminal(endElement,nodeCreator:(context,parseNode)=>parseNode.AstNode=""){

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]