Using NotNull only for method params

Author: rjrudin

marklogic-spark-api/build.gradle

@@ -11,9 +11,13 @@ dependencies {
     exclude group: "com.fasterxml.jackson.dataformat"
   }
 
-  // This is compileOnly as Spark will provide its own copy.
+  // This is compileOnly as Spark will provide its own copy at runtime.
   compileOnly "com.fasterxml.jackson.core:jackson-databind:2.15.2"
 
+  // Used for null-checks; Spark should provide its own copy at runtime as well, but this is included just in case
+  // a particular Spark runtime doesn't include this.
+  implementation "jakarta.validation:jakarta.validation-api:2.0.2"
+
   // For logging.
   implementation "org.slf4j:jcl-over-slf4j:2.0.13"
 

marklogic-spark-api/src/main/java/com/marklogic/spark/core/classifier/TextClassifierFactory.java

@@ -14,11 +14,11 @@
 import com.smartlogic.cloud.TokenFetcher;
 import org.w3c.dom.Document;
 
+import javax.validation.constraints.NotNull;
 import java.net.MalformedURLException;
 import java.net.URL;
 import java.util.HashMap;
 import java.util.Map;
-import java.util.Objects;
 
 public abstract class TextClassifierFactory {
 
@@ -141,8 +141,7 @@ public static class MockSemaphoreProxy implements SemaphoreProxy {
 
         // Sonar doesn't like this static assignment, but it's fine in a class that's only used as a mock.
         @SuppressWarnings("java:S3010")
-        private MockSemaphoreProxy(String mockResponse) {
-            Objects.requireNonNull(mockResponse);
+        private MockSemaphoreProxy(@NotNull String mockResponse) {
             this.mockResponse = new DOMHelper(null).parseXmlString(mockResponse, null);
             timesInvoked = 0;
         }

marklogic-spark-connector/src/main/java/com/marklogic/spark/reader/document/OpticTriplesReader.java

@@ -20,6 +20,7 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import javax.validation.constraints.NotNull;
 import java.io.IOException;
 import java.net.URI;
 import java.net.URISyntaxException;
@@ -105,8 +106,7 @@ public void close() {
         IOUtils.closeQuietly(this.currentRowSet);
     }
 
-    private void readNextBatchOfTriples(List<String> uris) {
-        Objects.requireNonNull(uris);
+    private void readNextBatchOfTriples(@NotNull List<String> uris) {
         PlanBuilder.ModifyPlan plan = op
             .fromTriples(op.pattern(op.col("subject"), op.col("predicate"), op.col(OBJECT_COLUMN), op.graphCol(GRAPH_COLUMN)))
             .where(op.cts.documentQuery(op.xs.stringSeq(uris.toArray(new String[0]))));

marklogic-spark-connector/src/main/java/com/marklogic/spark/reader/file/RdfZipFileReader.java

@@ -8,10 +8,10 @@
 import org.apache.commons.io.IOUtils;
 import org.apache.spark.sql.catalyst.InternalRow;
 import org.apache.spark.sql.connector.read.PartitionReader;
-import org.jetbrains.annotations.NotNull;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import javax.validation.constraints.NotNull;
 import java.io.IOException;
 import java.io.InputStream;
 import java.util.zip.ZipEntry;

marklogic-spark-connector/src/main/java/com/marklogic/spark/writer/file/ContentWriter.java

@@ -72,14 +72,16 @@ void writeContent(InternalRow row, @NotNull OutputStream outputStream) throws IO
             streamDocumentToFile(row, outputStream);
         } else if (this.prettyPrint) {
             prettyPrintContent(row, outputStream);
-        } else if (this.encoding != null) {
-            // We know the string from MarkLogic is UTF-8, so we use getBytes to convert it to the user's
-            // specified encoding (as opposed to new String(bytes, encoding)).
+        } else {
             byte[] binary = row.getBinary(1);
             Objects.requireNonNull(binary);
-            outputStream.write(new String(binary).getBytes(this.encoding));
-        } else {
-            outputStream.write(row.getBinary(1));
+            if (this.encoding != null) {
+                // We know the string from MarkLogic is UTF-8, so we use getBytes to convert it to the user's
+                // specified encoding (as opposed to new String(bytes, encoding)).
+                outputStream.write(new String(binary).getBytes(this.encoding));
+            } else {
+                outputStream.write(binary);
+            }
         }
     }
 

tests/src/test/java/com/marklogic/spark/writer/file/WriteDocumentZipFilesTest.java

@@ -12,7 +12,6 @@
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
 import org.apache.spark.sql.SaveMode;
-import org.jetbrains.annotations.NotNull;
 import org.junit.jupiter.api.Test;
 import org.junit.jupiter.api.io.TempDir;
 
@@ -46,7 +45,7 @@ void defaultPartitionCount(@TempDir Path tempDir) throws Exception {
     }
 
     @Test
-    void customPartitionCount(@TempDir @NotNull Path tempDir) throws IOException {
+    void customPartitionCount(@TempDir Path tempDir) throws IOException {
         readAuthorCollection()
             .repartition(5)
             .write()
@@ -64,7 +63,7 @@ void customPartitionCount(@TempDir @NotNull Path tempDir) throws IOException {
     }
 
     @Test
-    void opaqueURI(@TempDir @NotNull Path tempDir) throws IOException {
+    void opaqueURI(@TempDir Path tempDir) throws IOException {
         final String uri = "org:example/123.xml";
 
         getDatabaseClient().newXMLDocumentManager().write(uri,