NIFI-1632: Fixed NPE that occurs if a capturing group is optional and not matched; updated docs to illustrate how this is handled

Signed-off-by: joewitt <joewitt@apache.org>

nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/ExtractText.java

@@ -67,7 +67,11 @@ import org.apache.nifi.stream.io.StreamUtils;
         + "the name of the property maps to the Attribute Name into which the result will be placed.  "
         + "The first capture group, if any found, will be placed into that attribute name."
         + "But all capture groups, including the matching string sequence itself will also be "
-        + "provided at that attribute name with an index value provided."
+        + "provided at that attribute name with an index value provided, with the exception of a capturing group "
+        + "that is optional and does not match - for example, given the attribute name \"regex\" and expression "
+        + "\"abc(def)?(g)\" we would add an attribute \"regex.1\" with a value of \"def\" if the \"def\" matched. If "
+        + "the \"def\" did not match, no attribute named \"regex.1\" would be added but an attribute named \"regex.2\" "
+        + "with a value of \"g\" will be added regardless."
         + "The value of the property must be a valid Regular Expressions with one or more capturing groups.  "
         + "If the Regular Expression matches more than once, only the first match will be used.  "
         + "If any provided Regular Expression matches, the FlowFile(s) will be routed to 'matched'. "
@@ -322,6 +326,7 @@ public class ExtractText extends AbstractProcessor {
                 for (int i = startGroupIdx; i <= matcher.groupCount(); i++) {
                     final String key = new StringBuilder(baseKey).append(".").append(i).toString();
                     String value = matcher.group(i);
+                    if (value != null) {
                         if (value.length() > maxCaptureGroupLength) {
                             value = value.substring(0, maxCaptureGroupLength);
                         }
@@ -332,6 +337,7 @@ public class ExtractText extends AbstractProcessor {
                     }
                 }
             }
+        }
 
         if (!regexResults.isEmpty()) {
             flowFile = session.putAllAttributes(flowFile, regexResults);

nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/test/java/org/apache/nifi/processors/standard/TestExtractText.java

@@ -65,6 +65,27 @@ public class TestExtractText {
         out.assertAttributeEquals("regex.result7", null);
     }
 
+    @Test
+    public void testWithUnmatchedOptionalCapturingGroup() {
+        final TestRunner testRunner = TestRunners.newTestRunner(new ExtractText());
+        testRunner.setProperty("regex", "abc(def)?(g)");
+        testRunner.enqueue("abcg");
+        testRunner.run();
+
+        testRunner.assertAllFlowFilesTransferred(ExtractText.REL_MATCH, 1);
+        final MockFlowFile out = testRunner.getFlowFilesForRelationship(ExtractText.REL_MATCH).get(0);
+        out.assertAttributeNotExists("regex.1");
+        out.assertAttributeEquals("regex.2", "g");
+
+        testRunner.clearTransferState();
+
+        testRunner.enqueue("abcdefg");
+        testRunner.run();
+        final MockFlowFile out2 = testRunner.getFlowFilesForRelationship(ExtractText.REL_MATCH).get(0);
+        out2.assertAttributeEquals("regex.1", "def");
+        out2.assertAttributeEquals("regex.2", "g");
+    }
+
     @Test
     public void testProcessorWithDotall() throws Exception {