Enhanced to handle PI that starts with <?xml-model ...?>

This occurs in test infoset data for the iCalendar DFDL schema.
Xerces was tolerating this before, so our constructing loader
should also.

DAFFODIL-2527

daffodil-lib/src/main/scala/org/apache/daffodil/xml/DaffodilConstructingLoader.scala

@@ -304,6 +304,48 @@ class DaffodilConstructingLoader private[xml] (uri: URI,
   override def procInstr(pos: Int, target: String, txt: String) =
     ProcInstr(target, text(pos, txt).text)
 
+  private def parseXMLPrologAttributes(m: MetaData): (Option[String], Option[String], Option[Boolean]) = {
+
+    var info_ver: Option[String] = None
+    var info_enc: Option[String] = None
+    var info_stdl: Option[Boolean] = None
+
+    var n = 0
+    m("version") match {
+      case null =>
+      case Text("1.0") =>
+        info_ver = Some("1.0"); n += 1
+      case _ => reportSyntaxError("cannot deal with versions != 1.0")
+    }
+
+    m("encoding") match {
+      case null =>
+      case Text(enc) =>
+        if (!isValidIANAEncoding(enc))
+          reportSyntaxError("\"" + enc + "\" is not a valid encoding")
+        else {
+          info_enc = Some(enc)
+          n += 1
+        }
+    }
+
+    m("standalone") match {
+      case null =>
+      case Text("yes") =>
+        info_stdl = Some(true); n += 1
+      case Text("no") =>
+        info_stdl = Some(false); n += 1
+      case _ => reportSyntaxError("either 'yes' or 'no' expected")
+    }
+
+    if (m.length - n != 0) {
+      reportSyntaxError(
+        "only 'version', 'encoding', and 'standalone' attributes are expected in xml prolog. Found: " + m)
+    }
+
+    (info_ver, info_enc, info_stdl)
+  }
+
   /**
    * Override of document to make it tolerant of the start of the file
    * being whitespace instead of a "<" character
@@ -320,12 +362,28 @@ class DaffodilConstructingLoader private[xml] (uri: URI,
     if ('<' == ch) {
       nextch()
       if ('?' == ch) {
-        // It's an XML Prolog
         nextch()
-        val info_prolog = prolog()
-        doc.version = info_prolog._1
-        doc.encoding = info_prolog._2
-        doc.standAlone = info_prolog._3
+        // It's probably an XML prolog, but
+        // there are cases where there is no XML Prolog, but a starting
+        // PI of <?xml-model href="...."?>
+        // So we have to recognize as a general PI, then look and see if
+        // it is a prolog.
+        val name = xName
+        xSpace()
+        val (md, scp) = xAttributes(TopScope)
+        if (scp != TopScope)
+          reportSyntaxError("no xmlns definitions allowed.")
+        xToken('?')
+        xToken('>')
+        if (name == "xml") {
+          val info_prolog = parseXMLPrologAttributes(md)
+          doc.version = info_prolog._1
+          doc.encoding = info_prolog._2
+          doc.standAlone = info_prolog._3
+        } else {
+          // not an xml prolog. It's some other PI
+          // do nothing. We're just skipping those PIs
+        }
         children = content(TopScope)
       } else {
         val ts = new NodeBuffer()

daffodil-lib/src/test/scala/org/apache/daffodil/xml/test/unit/TestXMLLoader.scala

@@ -31,7 +31,41 @@ class TestXMLLoader {
   @Test
   def test_schemaLoad(): Unit = {
     val data =
-      """<xs:schema targetNamespace="http://example.com"
+      """<?xml version="1.0"?>
+        |<xs:schema
+        |targetNamespace="http://example.com"
+        |xmlns:ex="http://example.com"
+        |xmlns:xs="http://www.w3.org/2001/XMLSchema"
+        |xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+        |xmlns:dfdl="http://www.ogf.org/dfdl/dfdl-1.0/">
+        |  <xs:include schemaLocation="org/apache/daffodil/xsd/DFDLGeneralFormat.dfdl.xsd"/>
+        |  <xs:annotation>
+        |    <xs:appinfo source="http://www.ogf.org/dfdl/">
+        |      <dfdl:format lengthKind="delimited" ref="ex:GeneralFormat"/>
+        |    </xs:appinfo>
+        |  </xs:annotation>
+        |  <xs:element name="e1">
+        |    <xs:complexType>
+        |      <xs:sequence>
+        |        <xs:element name="s1" type="xs:int"/>
+        |      </xs:sequence>
+        |    </xs:complexType>
+        |  </xs:element>
+        |</xs:schema>
+        |""".stripMargin
+    val loader = new DaffodilXMLLoader()
+    val ss = StringSchemaSource(data)
+    val root =
+      loader.load(ss, None, false)
+    assertEquals("http://example.com", (root \ "@targetNamespace").text)
+  }
+
+  @Test
+  def test_startsWithPINotProlog(): Unit = {
+    val data =
+      """<?xml-model href="../Schematron/iCalendar.sch" type="application/xml" schematypens="http://purl.oclc.org/dsdl/schematron"?>
+        |<xs:schema
+        |targetNamespace="http://example.com"
         |xmlns:ex="http://example.com"
         |xmlns:xs="http://www.w3.org/2001/XMLSchema"
         |xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"