NIFI-11029 Added Standard XML parsing to ExtractCCDAAttributes

- Added DeprecationNotice to ExtractCCDAAttributes

Signed-off-by: Matthew Burgess <mattyb149@apache.org>

This closes #6828

Author: exceptionfactory

nifi-nar-bundles/nifi-ccda-bundle/nifi-ccda-processors/pom.xml

@@ -35,6 +35,11 @@
             <artifactId>nifi-utils</artifactId>
             <version>1.20.0-SNAPSHOT</version>
         </dependency>
+        <dependency>
+            <groupId>org.apache.nifi</groupId>
+            <artifactId>nifi-xml-processing</artifactId>
+            <version>1.20.0-SNAPSHOT</version>
+        </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-lang3</artifactId>

nifi-nar-bundles/nifi-ccda-bundle/nifi-ccda-processors/src/main/java/org/apache/nifi/processors/ccda/ExtractCCDAAttributes.java

@@ -41,6 +41,7 @@
 import org.apache.nifi.annotation.behavior.SideEffectFree;
 import org.apache.nifi.annotation.behavior.SupportsBatching;
 import org.apache.nifi.annotation.documentation.CapabilityDescription;
+import org.apache.nifi.annotation.documentation.DeprecationNotice;
 import org.apache.nifi.annotation.documentation.Tags;
 import org.apache.nifi.annotation.lifecycle.OnScheduled;
 import org.apache.nifi.components.PropertyDescriptor;
@@ -53,6 +54,7 @@
 import org.apache.nifi.processor.exception.ProcessException;
 import org.apache.nifi.processor.util.StandardValidators;
 import org.apache.nifi.util.StopWatch;
+import org.apache.nifi.xml.processing.parsers.StandardDocumentProvider;
 import org.eclipse.emf.common.util.Diagnostic;
 import org.openhealthtools.mdht.uml.cda.CDAPackage;
 import org.openhealthtools.mdht.uml.cda.ClinicalDocument;
@@ -62,7 +64,9 @@
 import org.openhealthtools.mdht.uml.cda.ihe.IHEPackage;
 import org.openhealthtools.mdht.uml.cda.util.CDAUtil;
 import org.openhealthtools.mdht.uml.cda.util.CDAUtil.ValidationHandler;
+import org.w3c.dom.Document;
 
+@DeprecationNotice(reason = "Parsing XML elements to FlowFile attributes is not recommend and should be replaced with record-oriented handling")
 @SideEffectFree
 @SupportsBatching
 @InputRequirement(Requirement.INPUT_REQUIRED)
@@ -284,7 +288,11 @@ protected ClinicalDocument loadDocument(InputStream inputStream, Boolean skipVal
         ClinicalDocument cd = null;
 
         try {
-            cd = CDAUtil.load(inputStream); // load CDA document
+            final StandardDocumentProvider documentProvider = new StandardDocumentProvider();
+            documentProvider.setNamespaceAware(true);
+            final Document document = documentProvider.parse(inputStream);
+
+            cd = CDAUtil.load(document); // load CDA document
             if (!skipValidation && !CDAUtil.validate(cd, new CDAValidationHandler())) { //optional validation
                 getLogger().error("Failed to validate CDA document");
                 throw new ProcessException("Failed to validate CDA document");

nifi-nar-bundles/nifi-ccda-bundle/nifi-ccda-processors/src/test/java/org/apache/nifi/processors/ccda/TestExtractCCDAAttributes.java

@@ -19,7 +19,6 @@
 import org.apache.nifi.util.MockFlowFile;
 import org.apache.nifi.util.TestRunner;
 import org.apache.nifi.util.TestRunners;
-import org.junit.jupiter.api.BeforeAll;
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
 import org.openhealthtools.mdht.uml.cda.consol.ConsolFactory;
@@ -33,20 +32,17 @@
 import org.openhealthtools.mdht.uml.cda.consol.VitalSignsSection;
 import org.openhealthtools.mdht.uml.cda.util.CDAUtil;
 
-import java.io.IOException;
 import java.io.StringWriter;
-import java.util.HashMap;
+import java.util.LinkedHashMap;
 import java.util.Map;
 
-
 public class TestExtractCCDAAttributes {
 
-    private TestRunner runner;
+    private static final String INVALID_DOCTYPE = "<!DOCTYPE invalid [<!ENTITY entity SYSTEM 'file:///file-not-found'> %entity;]>";
 
-    @BeforeAll
-    public static void setup() {
-        System.setProperty("org.slf4j.simpleLogger.log.org.apache.nifi", "INFO");
-    }
+    private static final String INVALID_DOCUMENT = String.format("<?xml version=\"1.0\" encoding=\"UTF-8\" ?>%s<ClinicalDocument xmlns=\"urn:hl7-org:v3\" />", INVALID_DOCTYPE);
+
+    private TestRunner runner;
 
     @BeforeEach
     public void init() {
@@ -55,7 +51,7 @@ public void init() {
 
     @Test
     public void testProcessor() throws Exception {
-        Map<String, String> expectedAttributes = new HashMap<String, String>();
+        Map<String, String> expectedAttributes = new LinkedHashMap<>();
         expectedAttributes.put("code.code", "34133-9");
         expectedAttributes.put("code.codeSystem", "2.16.840.1.113883.6.1");
         expectedAttributes.put("code.codeSystemName", "LOINC");
@@ -110,11 +106,21 @@ public void testProcessor() throws Exception {
         StringWriter writer = new StringWriter();
         CDAUtil.save(doc, writer);
 
-        runTests(writer.toString(), expectedAttributes, true, true);
+        runTests(writer.toString(), expectedAttributes);
+    }
+
+    @Test
+    public void testRunInvalidDocument() {
+        runner.enqueue(INVALID_DOCUMENT);
+
+        runner.run();
+
+        runner.assertAllFlowFilesTransferred(ExtractCCDAAttributes.REL_FAILURE);
     }
 
-    private void runTests(final String content, Map<String, String> expectedAttributes, final boolean skipValidation, final boolean prettyPrinting) throws IOException{
-        runner.setProperty(ExtractCCDAAttributes.SKIP_VALIDATION, String.valueOf(skipValidation));
+
+    private void runTests(final String content, final Map<String, String> expectedAttributes) {
+        runner.setProperty(ExtractCCDAAttributes.SKIP_VALIDATION, Boolean.TRUE.toString());
 
         runner.enqueue(content);