NIFI-9832: Fix disappearing XML element content when the element has attribute (#5896)

- NIFI-9832: Additional test cases for XMLReader

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/pom.xml

@@ -218,6 +218,7 @@
                         <exclude>src/test/resources/syslog/syslog5424/log_mix.txt</exclude>
                         <exclude>src/test/resources/syslog/syslog5424/log_mix_in_error.txt</exclude>
                         <exclude>src/test/resources/text/testschema</exclude>
+                        <exclude>src/test/resources/xml/field_with_sub-element.xml</exclude>
                         <exclude>src/test/resources/xml/people.xml</exclude>
                         <exclude>src/test/resources/xml/people2.xml</exclude>
                         <exclude>src/test/resources/xml/people3.xml</exclude>
@@ -236,6 +237,7 @@
                         <exclude>src/test/resources/xml/people_tag_in_characters.xml</exclude>
                         <exclude>src/test/resources/xml/people_with_header_and_comments.xml</exclude>
                         <exclude>src/test/resources/xml/person.xml</exclude>
+                        <exclude>src/test/resources/xml/person_record.xml</exclude>
                         <exclude>src/test/resources/xml/testschema</exclude>
                         <exclude>src/test/resources/xml/testschema2</exclude>
                         <exclude>src/test/resources/xml/testschema3</exclude>

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/main/java/org/apache/nifi/xml/XMLReader.java

@@ -97,7 +97,10 @@ public class XMLReader extends SchemaRegistryService implements RecordReaderFact
             .description("If tags with content (e. g. <field>content</field>) are defined as nested records in the schema, " +
                     "the name of the tag will be used as name for the record and the value of this property will be used as name for the field. " +
                     "If tags with content shall be parsed together with attributes (e. g. <field attribute=\"123\">content</field>), " +
-                    "they have to be defined as records. For additional information, see the section of processor usage.")
+                    "they have to be defined as records. In such a case, the name of the tag will be used as the name for the record and  " +
+                    "the value of this property will be used as the name for the field holding the original content. The name of the attribute " +
+                    "will be used to create a new record field, the content of which will be the value of the attribute. " +
+                    "For more information, see the 'Additional Details...' section of the XMLReader controller service's documentation.")
             .addValidator(StandardValidators.NON_EMPTY_VALIDATOR)
             .expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES)
             .required(false)
@@ -136,7 +139,12 @@ public class XMLReader extends SchemaRegistryService implements RecordReaderFact
 
     @Override
     protected SchemaAccessStrategy getSchemaAccessStrategy(final String strategy, final SchemaRegistry schemaRegistry, final PropertyContext context) {
-        final RecordSourceFactory<XmlNode> sourceFactory = (variables, contentStream) -> new XmlRecordSource(contentStream, isMultipleRecords(context, variables));
+
+        final RecordSourceFactory<XmlNode> sourceFactory = (variables, contentStream) -> {
+            String contentFieldName = trim(context.getProperty(CONTENT_FIELD_NAME).evaluateAttributeExpressions(variables).getValue());
+            contentFieldName = (contentFieldName == null) ? "value" : contentFieldName;
+            return new XmlRecordSource(contentStream, contentFieldName, isMultipleRecords(context, variables));
+        };
         final Supplier<SchemaInferenceEngine<XmlNode>> schemaInference = () -> new XmlSchemaInference(new TimeValueInference(dateFormat, timeFormat, timestampFormat));
 
         return SchemaInferenceUtil.getSchemaAccessStrategy(strategy, context, getLogger(), sourceFactory, schemaInference,

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/main/java/org/apache/nifi/xml/XMLRecordReader.java

@@ -339,8 +339,8 @@ public class XMLRecordReader implements RecordReader {
                 if (contentFieldName != null) {
                     recordValues.put(contentFieldName, content.toString());
                 } else {
-                    logger.debug("Found content for field that has to be parsed as record but property \"Field Name for Content\" is not set. " +
+                    logger.debug("Found content for a field that was supposed to be named with the value of the \"Field Name for Content\" property but " +
-                            "The content will not be added to the record.");
+                            "the property was not set. The content was not added to the record.");
                 }
 
                 return new MapRecord(new SimpleRecordSchema(Collections.emptyList()), recordValues);
@@ -486,10 +486,13 @@ public class XMLRecordReader implements RecordReader {
                 if (field.isPresent()) {
                     Object value = parseStringForType(content.toString(), contentFieldName, field.get().getDataType());
                     recordValues.put(contentFieldName, value);
+                } else {
+                    logger.debug("Found content for a field that was supposed to be named with the value of the \"Field Name for Content\" property " +
+                            "but no such field was present in the schema. The content was not added to the record.");
                 }
             } else {
-                logger.debug("Found content for field that is defined as record but property \"Field Name for Content\" is not set. " +
+                logger.debug("Found content for a field that was supposed to be named with the value of the \"Field Name for Content\" property but " +
-                        "The content will not be added to record.");
+                        "the property was not set. The content was not added to the record.");
             }
         }
 

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/main/java/org/apache/nifi/xml/inference/XmlRecordSource.java

@@ -35,8 +35,10 @@ import java.util.Map;
 public class XmlRecordSource implements RecordSource<XmlNode> {
 
     private final XMLEventReader xmlEventReader;
+    private final String contentFieldName;
 
-    public XmlRecordSource(final InputStream in, final boolean ignoreWrapper) throws IOException {
+    public XmlRecordSource(final InputStream in, final String contentFieldName, final boolean ignoreWrapper) throws IOException {
+        this.contentFieldName = contentFieldName;
         try {
             final XMLInputFactory xmlInputFactory = XMLInputFactory.newInstance();
 
@@ -125,7 +127,7 @@ public class XmlRecordSource implements RecordSource<XmlNode> {
         } else {
             final String textContent = content.toString().trim();
             if (!textContent.equals("")) {
-                childNodes.put("value", new XmlTextNode("value", textContent));
+                childNodes.put(contentFieldName, new XmlTextNode(contentFieldName, textContent));
             }
 
             return new XmlContainerNode(nodeName, childNodes);

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/main/resources/docs/org.apache.nifi.xml.XMLReader/additionalDetails.html

@@ -286,6 +286,357 @@
         for tags containing attributes and content.
     </p>
 
+    <h2>Example: Tags with Attributes and Schema Inference</h2>
+
+    <p>
+        When the record's schema is not provided but inferred based on the data itself, providing a value for the "Field Name for Content" property
+        is especially important. (For detailed information on schema inference, see the "Schema Inference" section below.)
+        Let's focus on cases where an XML element (called <code>&lt;field_with_attribute&gt;</code> in the examples) has an XML attribute and some content and no sub-elements.
+        For the examples below, let's assume that a ConvertRecord processor is used, and it uses an XMLReader controller service and an XMLRecordSetWriter
+        controller service. The settings for XMLReader are provided separately for each example. The settings for XMLRecordSetWriter are common
+        for all the examples below. This way an XML to XML conversion is executed and comparing the input data with the output highlights
+        the schema inference behavior. The same behavior can be observed if a different Writer controller service is used.
+        XMLRecordSetWriter was chosen for these examples so that the input and the output are easily comparable.
+        The settings of the common XMLRecordSetWriter are the following:
+    </p>
+
+    <table>
+        <tr>
+            <th>Property Name</th>
+            <th>Property Value</th>
+        </tr>
+        <tr>
+            <td>Schema Access Strategy</td>
+            <td><code>Inherit Record Schema</code></td>
+        </tr>
+        <tr>
+            <td>Suppress Null Values</td>
+            <td><code>Never Suppress</code></td>
+        </tr>
+    </table>
+
+    <h3>XML Attributes and Schema Inference Example 1</h3>
+
+    <p>
+        XMLReader settings:
+    </p>
+
+    <table>
+        <tr>
+            <th>Property Name</th>
+            <th>Property Value</th>
+        </tr>
+        <tr>
+            <td>Schema Access Strategy</td>
+            <td><code>Infer Schema</code></td>
+        </tr>
+        <tr>
+            <td>Expect Records as Array</td>
+            <td><code>false</code></td>
+        </tr>
+        <tr>
+            <td>Field Name for Content</td>
+            <td>not set</td>
+        </tr>
+    </table>
+
+    <p>
+        Input:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute attr="attr_content"&gt;
+                        content of field
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>As mentioned above, the element called "field_with_attribute" has an attribute and some content but no sub-element.</p>
+
+    <p>
+        Output:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute&gt;
+                        &lt;attr&gt;attr_content&lt;/attr&gt;
+                        &lt;value&gt;&lt;/value&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        In the XMLReader's settings, no value is set for the "Field Name for Content" property. In such cases the schema inference logic
+        adds a field named "value" to the schema. However, since "Field Name for Content" is not set, the data processing logic is instructed
+        not to consider the original content of the parent XML tags (<code>&lt;field_with_attribute&gt;</code> the content of which is "content of field"
+        in the example). So a new field named "value" appears in the schema but no value is assigned to it from the data, thus the field is empty.
+        The XML attribute (named "attr") is processed, a field named "attr" is added to the schema and the attribute's value ("attr_content") is assigned to it.
+        In a case like this, the parent field's original content is lost and a new field named "value" appears in the schema with no data assigned to it.
+        This is to make sure that no data is overwritten in the record if it already contains a field named "value". More on that case in Example 3 and Example 4.
+    </p>
+
+    <h3>XML Attributes and Schema Inference Example 2</h3>
+
+    <p>
+        In this example, the XMLReader's "Field Name for Content" property is filled with the value "original_content". The input data is the same as
+        in the previous example.
+    </p>
+
+    <p>
+        XMLReader settings:
+    </p>
+
+    <table>
+        <tr>
+            <th>Property Name</th>
+            <th>Property Value</th>
+        </tr>
+        <tr>
+            <td>Schema Access Strategy</td>
+            <td><code>Infer Schema</code></td>
+        </tr>
+        <tr>
+            <td>Expect Records as Array</td>
+            <td><code>false</code></td>
+        </tr>
+        <tr>
+            <td>Field Name for Content</td>
+            <td><code>original_content</code></td>
+        </tr>
+    </table>
+
+    <p>
+        Input:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute attr="attr_content"&gt;
+                        content of field
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        Output:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute&gt;
+                        &lt;attr&gt;attr_content&lt;/attr&gt;
+                        &lt;original_content&gt;content of field&lt;/original_content&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        The XMLReader's "Field Name for Content" property contains the value "original_content" (the concrete value is not important, what is important
+        is that a value is provided and it does not clash with the name of any sub-element in <code>&lt;field_with_attribute&gt;</code>).
+        This explicitly tells the XMLReader controller service to create a field named "original_content" and make the original content of
+        the parent XML tag the value of the field named "original_content". Adding the XML attributed named "attr" works just like in the first example.
+        Since the <code>&lt;field_with_attribute&gt;</code> element had no child-element with the name "original_content", no data is lost.
+    </p>
+
+    <h3>XML Attributes and Schema Inference Example 3</h3>
+
+    <p>
+        In this example, XMLReader's "Field Name for Content" property is left empty. In the input data, the <code>&lt;field_with_attribute&gt;</code> element
+        has some content and a sub-element named <code>&lt;value&gt;</code>.
+    </p>
+
+    <p>
+        XMLReader settings:
+    </p>
+
+    <table>
+        <tr>
+            <th>Property Name</th>
+            <th>Property Value</th>
+        </tr>
+        <tr>
+            <td>Schema Access Strategy</td>
+            <td><code>Infer Schema</code></td>
+        </tr>
+        <tr>
+            <td>Expect Records as Array</td>
+            <td><code>false</code></td>
+        </tr>
+        <tr>
+            <td>Field Name for Content</td>
+            <td>not set</td>
+        </tr>
+    </table>
+
+    <p>
+        Input:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute attr="attr_content"&gt;
+                          content of field&lt;value&gt;123&lt;/value&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        Output:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute&gt;
+                        &lt;attr&gt;attr_content&lt;/attr&gt;
+                        &lt;value&gt;123&lt;/value&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        The "Field Name for Content" property is not set, and the XML element has a sub-element named "value". The name of the sub-element clashes with the
+        default field name added to the schema by the Schema Inference logic (see Example 1). As seen in the output data, the input XML attribute's value
+        is added to the record just like in the previous examples. The value of the <code>&lt;value&gt;</code> element is retained, but the content of the
+        <code>&lt;field_with_attribute&gt;</code> that was outside of the sub-element, is lost.
+    </p>
+
+    <h3>XML Attributes and Schema Inference Example 4</h3>
+
+    <p>
+        In this example, XMLReader's "Field Name for Content" property is given the value "value". In the input data, the <code>&lt;field_with_attribute&gt;</code> element
+       has some content and a sub-element named <code>&lt;value&gt;</code>. The name of the sub-element clashes with the value of the "Field Name for Content" property.
+    </p>
+
+    <p>
+        XMLReader settings:
+    </p>
+
+    <table>
+        <tr>
+            <th>Property Name</th>
+            <th>Property Value</th>
+        </tr>
+        <tr>
+            <td>Schema Access Strategy</td>
+            <td><code>Infer Schema</code></td>
+        </tr>
+        <tr>
+            <td>Expect Records as Array</td>
+            <td><code>false</code></td>
+        </tr>
+        <tr>
+            <td>Field Name for Content</td>
+            <td><code>value</code></td>
+        </tr>
+    </table>
+
+    <p>
+        Input:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute attr="attr_content"&gt;
+                          content of field&lt;value&gt;123&lt;/value&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        Output:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute&gt;
+                        &lt;attr&gt;attr_content&lt;/attr&gt;
+                        &lt;value&gt;content of field&lt;/value&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        The "Field Name for Content" property's value is "value", and the XML element has a sub-element named "value". The name of the sub-element clashes with the
+        value of the "Field Name for Content" property. The value of the <code>&lt;value&gt;</code> element is replaced by the content of the
+        <code>&lt;field_with_attribute&gt;</code> element, and the original content of the <code>&lt;value&gt;</code> element is lost.
+    </p>
+
+    <h3>XML Attributes and Schema Inference Example 5</h3>
+
+    <p>
+        To avoid losing any data, the XMLReader's "Field Name for Content" property needs to be given a value that does not clash with any sub-element's name
+        in the input data. In this example the input data is the same as in the previous one, but the "Field Name for Content" property's value is "original_content",
+        a value that does not clash with any sub-element name. No data is lost in this case.
+    </p>
+
+    <p>
+        XMLReader settings:
+    </p>
+
+    <table>
+        <tr>
+            <th>Property Name</th>
+            <th>Property Value</th>
+        </tr>
+        <tr>
+            <td>Schema Access Strategy</td>
+            <td><code>Infer Schema</code></td>
+        </tr>
+        <tr>
+            <td>Expect Records as Array</td>
+            <td><code>false</code></td>
+        </tr>
+        <tr>
+            <td>Field Name for Content</td>
+            <td><code>original_content</code></td>
+        </tr>
+    </table>
+
+    <p>
+        Input:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute attr="attr_content"&gt;
+                          content of field&lt;value&gt;123&lt;/value&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        Output:
+    </p>
+
+    <code>
+            <pre>
+                &lt;record&gt;
+                    &lt;field_with_attribute&gt;
+                        &lt;attr&gt;attr_content&lt;/attr&gt;
+                        &lt;value&gt;123&lt;/value&gt;
+                        &lt;original_content&gt;content of field&lt;/original_content&gt;
+                    &lt;/field_with_attribute&gt;
+                &lt;/record&gt;</pre>
+    </code>
+
+    <p>
+        It can be seen in the output data, that the attribute has been added to the <code>&lt;field_with_attribute&gt;</code> element as a sub-element,
+        the <code>&lt;value&gt;</code> retained its value, and the original content of the <code>&lt;field_with_attribute&gt;</code> element has been added as a sub-element
+        named "original_content". This is because a value was chosen for the "Field Name for Content" property that does not clash with any of
+        the existing sub-elements of the input XML element (<code>&lt;field_with_attribute&gt;</code>). No data is lost.
+    </p>
+
     <h2>Example: Array of records</h2>
 
     <p>

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/test/java/org/apache/nifi/xml/TestInferXmlSchema.java

@@ -93,7 +93,8 @@ public class TestInferXmlSchema {
 
     @Test
     public void testStringFieldWithAttributes() throws IOException {
-        final RecordSchema schema = inferSchema("src/test/resources/xml/TextNodeWithAttribute.xml", true);
+        final String contentFieldName = "contentfield";
+        final RecordSchema schema = inferSchema("src/test/resources/xml/TextNodeWithAttribute.xml", contentFieldName, true);
 
         assertEquals(3, schema.getFieldCount());
 
@@ -106,12 +107,16 @@ public class TestInferXmlSchema {
 
         final RecordSchema childSchema = ((RecordDataType) softwareDataType).getChildSchema();
         assertSame(RecordFieldType.BOOLEAN, childSchema.getDataType("favorite").get().getFieldType());
-        assertSame(RecordFieldType.STRING, childSchema.getDataType("value").get().getFieldType());
+        assertSame(RecordFieldType.STRING, childSchema.getDataType(contentFieldName).get().getFieldType());
     }
 
     private RecordSchema inferSchema(final String filename, final boolean ignoreWrapper) throws IOException {
+        return inferSchema(filename, "contentfield", ignoreWrapper);
+    }
+
+    private RecordSchema inferSchema(final String filename, final String contentFieldName, final boolean ignoreWrapper) throws IOException {
         final File file = new File(filename);
-        final RecordSourceFactory<XmlNode> xmlSourceFactory = (var, in) ->  new XmlRecordSource(in, ignoreWrapper);
+        final RecordSourceFactory<XmlNode> xmlSourceFactory = (var, in) ->  new XmlRecordSource(in, contentFieldName, ignoreWrapper);
         final SchemaInferenceEngine<XmlNode> schemaInference = new XmlSchemaInference(timeValueInference);
         final InferSchemaAccessStrategy<XmlNode> inferStrategy = new InferSchemaAccessStrategy<>(xmlSourceFactory, schemaInference, Mockito.mock(ComponentLog.class));
 

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/test/java/org/apache/nifi/xml/TestXMLReader.java

@@ -17,8 +17,10 @@
 
 package org.apache.nifi.xml;
 
+import org.apache.nifi.components.PropertyDescriptor;
 import org.apache.nifi.reporting.InitializationException;
 import org.apache.nifi.schema.access.SchemaAccessUtils;
+import org.apache.nifi.schema.inference.SchemaInferenceUtil;
 import org.apache.nifi.util.MockFlowFile;
 import org.apache.nifi.util.TestRunner;
 import org.apache.nifi.util.TestRunners;
@@ -31,43 +33,48 @@ import java.nio.file.Files;
 import java.nio.file.Paths;
 import java.util.Arrays;
 import java.util.Collections;
+import java.util.HashMap;
 import java.util.List;
+import java.util.Map;
 
 import static junit.framework.TestCase.assertEquals;
 
 public class TestXMLReader {
 
-    private XMLReader reader;
-
     private final String ATTRIBUTE_PREFIX = "attribute_prefix";
     private final String CONTENT_NAME = "content_field";
     private final String EVALUATE_IS_ARRAY = "xml.stream.is.array";
 
-    public TestRunner setup(String filePath) throws InitializationException, IOException {
+    private TestRunner setup(Map<PropertyDescriptor, String> xmlReaderProperties) throws InitializationException {
-
         TestRunner runner = TestRunners.newTestRunner(TestXMLReaderProcessor.class);
-        reader = new XMLReader();
+        XMLReader reader = new XMLReader();
+
         runner.addControllerService("xml_reader", reader);
         runner.setProperty(TestXMLReaderProcessor.XML_READER, "xml_reader");
 
-        final String outputSchemaText = new String(Files.readAllBytes(Paths.get(filePath)));
+        for (Map.Entry<PropertyDescriptor, String> entry : xmlReaderProperties.entrySet()) {
-        runner.setProperty(reader, SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaAccessUtils.SCHEMA_TEXT_PROPERTY);
+            runner.setProperty(reader, entry.getKey(), entry.getValue());
-        runner.setProperty(reader, SchemaAccessUtils.SCHEMA_TEXT, outputSchemaText);
+        }
 
+        runner.enableControllerService(reader);
         return runner;
     }
 
     @Test
-    public void testRecordFormat() throws IOException, InitializationException {
+    public void testRecordFormatDeterminedBasedOnAttribute() throws IOException, InitializationException {
-        TestRunner runner = setup("src/test/resources/xml/testschema");
+        String outputSchemaPath = "src/test/resources/xml/testschema";
+        String outputSchemaText = new String(Files.readAllBytes(Paths.get(outputSchemaPath)));
 
-        runner.setProperty(reader, XMLReader.RECORD_FORMAT, XMLReader.RECORD_EVALUATE);
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaAccessUtils.SCHEMA_TEXT_PROPERTY.getValue());
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_TEXT, outputSchemaText);
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_EVALUATE.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
 
-        runner.enableControllerService(reader);
+        try (InputStream is = new FileInputStream("src/test/resources/xml/people.xml")) {
-
+            runner.enqueue(is, Collections.singletonMap(EVALUATE_IS_ARRAY, "true"));
-        InputStream is = new FileInputStream("src/test/resources/xml/people.xml");
+            runner.run();
-        runner.enqueue(is, Collections.singletonMap(EVALUATE_IS_ARRAY, "true"));
+        }
-        runner.run();
 
         List<MockFlowFile> flowFile = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS);
         List<String> records = Arrays.asList((new String(runner.getContentAsByteArray(flowFile.get(0)))).split("\n"));
@@ -76,16 +83,20 @@ public class TestXMLReader {
     }
 
     @Test
-    public void testRecordFormat2() throws IOException, InitializationException {
+    public void testRecordFormatArray() throws IOException, InitializationException {
-        TestRunner runner = setup("src/test/resources/xml/testschema");
+        String outputSchemaPath = "src/test/resources/xml/testschema";
+        String outputSchemaText = new String(Files.readAllBytes(Paths.get(outputSchemaPath)));
 
-        runner.setProperty(reader, XMLReader.RECORD_FORMAT, XMLReader.RECORD_ARRAY);
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaAccessUtils.SCHEMA_TEXT_PROPERTY.getValue());
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_TEXT, outputSchemaText);
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_ARRAY.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
 
-        runner.enableControllerService(reader);
+        try (InputStream is = new FileInputStream("src/test/resources/xml/people.xml")) {
-
+            runner.enqueue(is, Collections.singletonMap(EVALUATE_IS_ARRAY, "true"));
-        InputStream is = new FileInputStream("src/test/resources/xml/people.xml");
+            runner.run();
-        runner.enqueue(is, Collections.singletonMap(EVALUATE_IS_ARRAY, "true"));
+        }
-        runner.run();
 
         List<MockFlowFile> flowFile = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS);
         List<String> records = Arrays.asList((new String(runner.getContentAsByteArray(flowFile.get(0)))).split("\n"));
@@ -94,16 +105,20 @@ public class TestXMLReader {
     }
 
     @Test
-    public void testRecordFormat3() throws IOException, InitializationException {
+    public void testRecordFormatNotArray() throws IOException, InitializationException {
-        TestRunner runner = setup("src/test/resources/xml/testschema");
+        String outputSchemaPath = "src/test/resources/xml/testschema";
+        String outputSchemaText = new String(Files.readAllBytes(Paths.get(outputSchemaPath)));
 
-        runner.setProperty(reader, XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE);
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaAccessUtils.SCHEMA_TEXT_PROPERTY.getValue());
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_TEXT, outputSchemaText);
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
 
-        runner.enableControllerService(reader);
+        try (InputStream is = new FileInputStream("src/test/resources/xml/person.xml")) {
-
+            runner.enqueue(is, Collections.singletonMap(EVALUATE_IS_ARRAY, "true"));
-        InputStream is = new FileInputStream("src/test/resources/xml/person.xml");
+            runner.run();
-        runner.enqueue(is, Collections.singletonMap(EVALUATE_IS_ARRAY, "true"));
+        }
-        runner.run();
 
         List<MockFlowFile> flowFile = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS);
         List<String> records = Arrays.asList(new String(runner.getContentAsByteArray(flowFile.get(0))).split("\n"));
@@ -113,16 +128,20 @@ public class TestXMLReader {
 
     @Test
     public void testAttributePrefix() throws IOException, InitializationException {
-        TestRunner runner = setup("src/test/resources/xml/testschema");
+        String outputSchemaPath = "src/test/resources/xml/testschema";
+        String outputSchemaText = new String(Files.readAllBytes(Paths.get(outputSchemaPath)));
 
-        runner.setProperty(reader, XMLReader.ATTRIBUTE_PREFIX, "${" + ATTRIBUTE_PREFIX + "}");
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
-        runner.setProperty(reader, XMLReader.RECORD_FORMAT, XMLReader.RECORD_ARRAY);
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaAccessUtils.SCHEMA_TEXT_PROPERTY.getValue());
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_TEXT, outputSchemaText);
+        xmlReaderProperties.put(XMLReader.ATTRIBUTE_PREFIX, "${" + ATTRIBUTE_PREFIX + "}");
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_ARRAY.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
 
-        runner.enableControllerService(reader);
+        try (InputStream is = new FileInputStream("src/test/resources/xml/people.xml")) {
-
+            runner.enqueue(is, Collections.singletonMap(ATTRIBUTE_PREFIX, "ATTR_"));
-        InputStream is = new FileInputStream("src/test/resources/xml/people.xml");
+            runner.run();
-        runner.enqueue(is, Collections.singletonMap(ATTRIBUTE_PREFIX, "ATTR_"));
+        }
-        runner.run();
 
         List<MockFlowFile> flowFile = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS);
         List<String> records = Arrays.asList(new String(runner.getContentAsByteArray(flowFile.get(0))).split("\n"));
@@ -136,16 +155,20 @@ public class TestXMLReader {
 
     @Test
     public void testContentField() throws IOException, InitializationException {
-        TestRunner runner = setup("src/test/resources/xml/testschema2");
+        String outputSchemaPath = "src/test/resources/xml/testschema2";
+        String outputSchemaText = new String(Files.readAllBytes(Paths.get(outputSchemaPath)));
 
-        runner.setProperty(reader, XMLReader.CONTENT_FIELD_NAME, "${" + CONTENT_NAME + "}");
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
-        runner.setProperty(reader, XMLReader.RECORD_FORMAT, XMLReader.RECORD_ARRAY);
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaAccessUtils.SCHEMA_TEXT_PROPERTY.getValue());
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_TEXT, outputSchemaText);
+        xmlReaderProperties.put(XMLReader.CONTENT_FIELD_NAME, "${" + CONTENT_NAME + "}");
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_ARRAY.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
 
-        runner.enableControllerService(reader);
+        try (InputStream is = new FileInputStream("src/test/resources/xml/people_tag_in_characters.xml")) {
-
+            runner.enqueue(is, Collections.singletonMap(CONTENT_NAME, "CONTENT"));
-        InputStream is = new FileInputStream("src/test/resources/xml/people_tag_in_characters.xml");
+            runner.run();
-        runner.enqueue(is, Collections.singletonMap(CONTENT_NAME, "CONTENT"));
+        }
-        runner.run();
 
         List<MockFlowFile> flowFile = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS);
         List<String> records = Arrays.asList(new String(runner.getContentAsByteArray(flowFile.get(0))).split("\n"));
@@ -157,4 +180,103 @@ public class TestXMLReader {
         assertEquals("MapRecord[{ID=P4, NAME=MapRecord[{CONTENT=Elenora Scrivens, ATTR=attr content, INNER=inner content}], AGE=16}]", records.get(3));
         assertEquals("MapRecord[{ID=P5, NAME=MapRecord[{INNER=inner content}]}]", records.get(4));
     }
+
+    @Test
+    public void testInferSchema() throws InitializationException, IOException {
+        String expectedContent = "MapRecord[{software=MapRecord[{" + CONTENT_NAME + "=Apache NiFi, favorite=true}], num=123, name=John Doe}]";
+
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaInferenceUtil.INFER_SCHEMA.getValue());
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE.getValue());
+        xmlReaderProperties.put(XMLReader.CONTENT_FIELD_NAME, CONTENT_NAME);
+        TestRunner runner = setup(xmlReaderProperties);
+
+        try (InputStream is = new FileInputStream("src/test/resources/xml/person_record.xml")) {
+            runner.enqueue(is);
+            runner.run();
+        }
+
+        MockFlowFile out = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS).get(0);
+        String actualContent = out.getContent();
+        assertEquals(expectedContent, actualContent);
+    }
+
+    @Test
+    public void testInferSchemaContentFieldNameNotSet() throws InitializationException, IOException {
+        String expectedContent = "MapRecord[{software=MapRecord[{favorite=true}], num=123, name=John Doe}]";
+
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaInferenceUtil.INFER_SCHEMA.getValue());
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
+
+        try (InputStream is = new FileInputStream("src/test/resources/xml/person_record.xml")) {
+            runner.enqueue(is);
+            runner.run();
+        }
+
+        MockFlowFile out = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS).get(0);
+        String actualContent = out.getContent();
+        assertEquals(expectedContent, actualContent);
+    }
+
+    @Test
+    public void testInferSchemaContentFieldNameNotSetSubElementExists() throws InitializationException, IOException {
+        String expectedContent = "MapRecord[{field_with_attribute=MapRecord[{attr=attr_content, value=123}]}]";
+
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaInferenceUtil.INFER_SCHEMA.getValue());
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE.getValue());
+        TestRunner runner = setup(xmlReaderProperties);
+
+        try (InputStream is = new FileInputStream("src/test/resources/xml/field_with_sub-element.xml")) {
+            runner.enqueue(is);
+            runner.run();
+        }
+
+        MockFlowFile out = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS).get(0);
+        String actualContent = out.getContent();
+        assertEquals(expectedContent, actualContent);
+    }
+
+    @Test
+    public void testInferSchemaContentFieldNameSetSubElementExistsNameClash() throws InitializationException, IOException {
+        String expectedContent = "MapRecord[{field_with_attribute=MapRecord[{attr=attr_content, value=content of field}]}]";
+
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaInferenceUtil.INFER_SCHEMA.getValue());
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE.getValue());
+        xmlReaderProperties.put(XMLReader.CONTENT_FIELD_NAME, "value");
+        TestRunner runner = setup(xmlReaderProperties);
+
+        try (InputStream is = new FileInputStream("src/test/resources/xml/field_with_sub-element.xml")) {
+            runner.enqueue(is);
+            runner.run();
+        }
+
+        MockFlowFile out = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS).get(0);
+        String actualContent = out.getContent();
+        assertEquals(expectedContent, actualContent);
+    }
+
+    @Test
+    public void testInferSchemaContentFieldNameSetSubElementExistsNoNameClash() throws InitializationException, IOException {
+        String expectedContent = "MapRecord[{field_with_attribute=MapRecord[{" +CONTENT_NAME + "=content of field, " +
+                "attr=attr_content, value=123}]}]";
+
+        Map<PropertyDescriptor, String> xmlReaderProperties = new HashMap<>();
+        xmlReaderProperties.put(SchemaAccessUtils.SCHEMA_ACCESS_STRATEGY, SchemaInferenceUtil.INFER_SCHEMA.getValue());
+        xmlReaderProperties.put(XMLReader.RECORD_FORMAT, XMLReader.RECORD_SINGLE.getValue());
+        xmlReaderProperties.put(XMLReader.CONTENT_FIELD_NAME, CONTENT_NAME);
+        TestRunner runner = setup(xmlReaderProperties);
+
+        try (InputStream is = new FileInputStream("src/test/resources/xml/field_with_sub-element.xml")) {
+            runner.enqueue(is);
+            runner.run();
+        }
+
+        MockFlowFile out = runner.getFlowFilesForRelationship(TestXMLReaderProcessor.SUCCESS).get(0);
+        String actualContent = out.getContent();
+        assertEquals(expectedContent, actualContent);
+    }
 }

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/test/resources/xml/field_with_sub-element.xml

@@ -0,0 +1,4 @@
+<record>
+    <field_with_attribute attr="attr_content">content of field<value>123</value>
+    </field_with_attribute>
+</record>

nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/test/resources/xml/person_record.xml

@@ -0,0 +1,5 @@
+<record>
+    <num>123</num>
+    <name>John Doe</name>
+    <software favorite="true">Apache NiFi</software>
+</record>