WIP: Metadata walker for JAPI

daffodil-japi/src/main/scala/org/apache/daffodil/japi/Daffodil.scala

@@ -22,49 +22,36 @@
 import java.nio.channels.ReadableByteChannel
 import java.nio.channels.WritableByteChannel
 import scala.collection.JavaConverters._
-
-import org.apache.daffodil.core.compiler.{ Compiler => SCompiler }
-import org.apache.daffodil.core.compiler.{ InvalidParserException => SInvalidParserException }
-import org.apache.daffodil.core.compiler.{ ProcessorFactory => SProcessorFactory }
+import org.apache.daffodil.core.compiler.{Compiler => SCompiler}
+import org.apache.daffodil.core.compiler.{InvalidParserException => SInvalidParserException}
+import org.apache.daffodil.core.compiler.{ProcessorFactory => SProcessorFactory}
 import org.apache.daffodil.core.dsom.ExpressionCompilers
 import org.apache.daffodil.core.dsom.walker.RootView
 import org.apache.daffodil.japi.debugger._
 import org.apache.daffodil.japi.infoset._
 import org.apache.daffodil.japi.io.InputSourceDataInputStream
 import org.apache.daffodil.japi.packageprivate._
+import org.apache.daffodil.japi.schema.{RuntimeSchemaHandler, RuntimeSchemaWalker}
 import org.apache.daffodil.lib.api.URISchemaSource
 import org.apache.daffodil.lib.api.Validator
-import org.apache.daffodil.lib.api.{ DataLocation => SDataLocation }
-import org.apache.daffodil.lib.api.{ Diagnostic => SDiagnostic }
-import org.apache.daffodil.lib.api.{ LocationInSchemaFile => SLocationInSchemaFile }
-import org.apache.daffodil.lib.api.{ WithDiagnostics => SWithDiagnostics }
+import org.apache.daffodil.lib.api.{DataLocation => SDataLocation}
+import org.apache.daffodil.lib.api.{Diagnostic => SDiagnostic}
+import org.apache.daffodil.lib.api.{LocationInSchemaFile => SLocationInSchemaFile}
+import org.apache.daffodil.lib.api.{WithDiagnostics => SWithDiagnostics}
 import org.apache.daffodil.lib.xml.DFDLCatalogResolver
 import org.apache.daffodil.lib.xml.XMLUtils
-import org.apache.daffodil.runtime1.api.DFDL.{
-  DaffodilUnhandledSAXException => SDaffodilUnhandledSAXException,
-}
-import org.apache.daffodil.runtime1.api.DFDL.{
-  DaffodilUnparseContentHandler => SDaffodilUnparseContentHandler,
-}
-import org.apache.daffodil.runtime1.api.DFDL.{
-  DaffodilUnparseErrorSAXException => SDaffodilUnparseErrorSAXException,
-}
+import org.apache.daffodil.runtime1.api.DFDL.{DaffodilUnhandledSAXException => SDaffodilUnhandledSAXException}
+import org.apache.daffodil.runtime1.api.DFDL.{DaffodilUnparseContentHandler => SDaffodilUnparseContentHandler}
+import org.apache.daffodil.runtime1.api.DFDL.{DaffodilUnparseErrorSAXException => SDaffodilUnparseErrorSAXException}
 import org.apache.daffodil.runtime1.debugger.Debugger
-import org.apache.daffodil.runtime1.debugger.{ InteractiveDebugger => SInteractiveDebugger }
-import org.apache.daffodil.runtime1.debugger.{ TraceDebuggerRunner => STraceDebuggerRunner }
-import org.apache.daffodil.runtime1.processors.{
-  DaffodilParseXMLReader => SDaffodilParseXMLReader,
-}
-import org.apache.daffodil.runtime1.processors.{ DataProcessor => SDataProcessor }
-import org.apache.daffodil.runtime1.processors.{
-  ExternalVariableException => SExternalVariableException,
-}
-import org.apache.daffodil.runtime1.processors.{
-  InvalidUsageException => SInvalidUsageException,
-}
-import org.apache.daffodil.runtime1.processors.{ ParseResult => SParseResult }
-import org.apache.daffodil.runtime1.processors.{ UnparseResult => SUnparseResult }
-
+import org.apache.daffodil.runtime1.debugger.{InteractiveDebugger => SInteractiveDebugger}
+import org.apache.daffodil.runtime1.debugger.{TraceDebuggerRunner => STraceDebuggerRunner}
+import org.apache.daffodil.runtime1.processors.{DaffodilParseXMLReader => SDaffodilParseXMLReader}
+import org.apache.daffodil.runtime1.processors.{DataProcessor => SDataProcessor}
+import org.apache.daffodil.runtime1.processors.{ExternalVariableException => SExternalVariableException}
+import org.apache.daffodil.runtime1.processors.{InvalidUsageException => SInvalidUsageException}
+import org.apache.daffodil.runtime1.processors.{ParseResult => SParseResult}
+import org.apache.daffodil.runtime1.processors.{UnparseResult => SUnparseResult}
 import org.xml.sax.Attributes
 import org.xml.sax.ContentHandler
 import org.xml.sax.DTDHandler
@@ -401,6 +388,12 @@
   extends WithDiagnostics(dp)
   with Serializable {
 
+  /**
+   * For use by the JAPI implementation only.
+   * @return the underlying data processor
+   */
+  private [japi] def getUnderlyingDataProcessor = dp
+
   private def copy(dp: SDataProcessor = dp) = new DataProcessor(dp)
 
   /**
@@ -514,6 +507,11 @@
    */
   def save(output: WritableByteChannel): Unit = dp.save(output)
 
+  def walkRuntimeSchema(handler: RuntimeSchemaHandler): Unit = {
+    val walker = new RuntimeSchemaWalker(dp)
+    walker.walk(handler)
+  }
+
   /**
    *  Obtain a new [[DaffodilParseXMLReader]] from the current [[DataProcessor]].
    */

daffodil-japi/src/main/scala/org/apache/daffodil/japi/schema/RuntimeSchemaWalker.scala

@@ -0,0 +1,135 @@
+package org.apache.daffodil.japi.schema
+
+import org.apache.daffodil.japi.{ DataProcessor => JDataProcessor }
+import org.apache.daffodil.lib.exceptions.Assert
+import org.apache.daffodil.runtime1.dpath.NodeInfo.PrimType
+import org.apache.daffodil.runtime1.processors.{
+  ChoiceRuntimeData,
+  DataProcessor => SDataProcessor,
+  ElementRuntimeData,
+  ErrorERD,
+  SequenceRuntimeData,
+  TermRuntimeData,
+}
+
+/**
+ * Base class used by japi clients who want to walk the runtime schema information.
+ */
+abstract class RuntimeSchemaHandler() {
+
+  /**
+   * Called for simple type element declarations.
+   *
+   * @param qnameString
+   * @param primTypeName
+   * @param isArray only true if more than one occurrence is possible. Disjoint with isOptional
+   * @param isOptional true if 0 or 1 occurrence only. Allows for a different representation of optional from a 0..1 array
+   */
+  def elementSimple(
+    qnameString: String,
+    primTypeName: String,
+    isArray: Boolean,
+    isOptional: Boolean,
+  ): Unit
+
+  /**
+   * Called for complex type element declarations
+   *
+   * Subsequent calls will be for the model group making up the content
+   * of the element.
+   *
+   * @param qnameString
+   */
+  def startElementComplex(qnameString: String, isArray: Boolean, isOptional: Boolean): Unit
+  def endElementComplex(qnameString: String, isArray: Boolean, isOptional: Boolean): Unit
+
+  def startSequence(): Unit
+
+  def endSequence(): Unit
+
+  def startChoice(): Unit
+
+  def endChoice(): Unit
+
+}
+
+/**
+ * Walks the schema, but not the DSOM schema, it walks the RuntimeData objects that
+ * represent the DFDL schema at runtime.
+ *
+ * @param dp
+ */
+class RuntimeSchemaWalker(private val dp: SDataProcessor) {
+
+  // provided so that people can write various tests from JAPI only.
+  // we wouldn't need this otherwise.
+  def this(jdp: JDataProcessor) = this(jdp.getUnderlyingDataProcessor)
+
+  private lazy val rootERD = dp.ssrd.elementRuntimeData
+
+  def walk(handler: RuntimeSchemaHandler): Unit = {
+    walkTerm(handler, rootERD)
+  }
+
+  private def walkTerm(handler: RuntimeSchemaHandler, trd: TermRuntimeData): Unit = {
+    trd match {
+      case err: ErrorERD => Assert.invariantFailed("should not get ErrorERDs")
+      case erd: ElementRuntimeData => walkElement(handler, erd)
+      case srd: SequenceRuntimeData => walkSequence(handler, srd)
+      case crd: ChoiceRuntimeData => walkChoice(handler, crd)
+      case _ => Assert.invariantFailed(s"unrecognized TermRuntimeData subtype: $trd")
+    }
+  }
+
+  private def walkElement(handler: RuntimeSchemaHandler, erd: ElementRuntimeData): Unit = {
+    if (erd.optComplexTypeModelGroupRuntimeData.isDefined)
+      walkComplexElement(handler, erd)
+    else
+      walkSimpleElement(handler, erd)
+  }
+
+  private def walkComplexElement(
+    handler: RuntimeSchemaHandler,
+    erd: ElementRuntimeData,
+  ): Unit = {
+    val qname = erd.namedQName.toQNameString
+    val isArray = erd.isArray
+    val isOptional = erd.isOptional
+    val mgrd = erd.optComplexTypeModelGroupRuntimeData.getOrElse {
+      Assert.invariantFailed("not a complex type element")
+    }
+    handler.startElementComplex(qname, isArray, isOptional)
+    walkTerm(handler, mgrd)
+    handler.endElementComplex(qname, isArray, isOptional)
+  }
+
+  private def walkSimpleElement(
+    handler: RuntimeSchemaHandler,
+    erd: ElementRuntimeData,
+  ): Unit = {
+    val qname = erd.namedQName.toQNameString
+    val isArray = erd.isArray
+    val isOptional = erd.isOptional
+    val primType: PrimType = erd.optPrimType.getOrElse {
+      erd.optSimpleTypeRuntimeData.map { _.primType }.get
+    }
+    handler.elementSimple(qname, primType.toString, isArray, isOptional)
+  }
+
+  private def walkSequence(handler: RuntimeSchemaHandler, srd: SequenceRuntimeData): Unit = {
+    handler.startSequence()
+    srd.groupMembers.map { trd =>
+      walkTerm(handler, trd)
+    }
+    handler.endSequence()
+  }
+
+  private def walkChoice(handler: RuntimeSchemaHandler, crd: ChoiceRuntimeData): Unit = {
+    handler.startChoice()
+    crd.groupMembers.map { trd =>
+      walkTerm(handler, trd)
+    }
+    handler.endChoice()
+  }
+
+}