Merge pull request #487 from marklogic/feature/and-more-polaris

rjrudin · web-flow · commit 1bb1203b5a9e · 2025-04-30T13:55:57.000-04:00
More Polaris null fixes, trying out NotNull
diff --git a/marklogic-spark-api/src/main/java/com/marklogic/spark/Context.java b/marklogic-spark-api/src/main/java/com/marklogic/spark/Context.java
@@ -5,6 +5,7 @@
 
 import java.io.Serializable;
 import java.util.Map;
+import java.util.Objects;
 import java.util.stream.Stream;
 
 public class Context implements Serializable {
@@ -49,7 +50,7 @@ public final long getNumericOption(String optionName, long defaultValue, long mi
     public final boolean getBooleanOption(String option, boolean defaultValue) {
         if (hasOption(option)) {
             String value = getStringOption(option);
-            assert value != null;
+            Objects.requireNonNull(value);
             return Boolean.parseBoolean(value);
         }
         return defaultValue;
diff --git a/marklogic-spark-api/src/main/java/com/marklogic/spark/core/classifier/TextClassifierFactory.java b/marklogic-spark-api/src/main/java/com/marklogic/spark/core/classifier/TextClassifierFactory.java
@@ -18,6 +18,7 @@
 import java.net.URL;
 import java.util.HashMap;
 import java.util.Map;
+import java.util.Objects;
 
 public abstract class TextClassifierFactory {
 
@@ -29,7 +30,6 @@ public static TextClassifier newTextClassifier(Context context) {
 
         if (context.hasOption(MOCK_CLASSIFIER_OPTION)) {
             String mockResponse = context.getStringOption(MOCK_CLASSIFIER_OPTION);
-            assert mockResponse != null;
             semaphoreProxy = new MockSemaphoreProxy(mockResponse);
         } else if (host != null && !host.trim().isEmpty()) {
             try {
@@ -39,7 +39,7 @@ public static TextClassifier newTextClassifier(Context context) {
                 throw ex;
             } catch (Exception e) {
                 throw new ConnectorException(String.format("Unable to configure a connection for classifying text; cause: %s",
-                        e.getMessage()), e);
+                    e.getMessage()), e);
             }
         }
 
@@ -116,7 +116,7 @@ public URL getTokenUrl() {
                 return new URL(protocol, host, port, tokenEndpoint);
             } catch (MalformedURLException e) {
                 throw new ConnectorException(String.format("Unable to construct token URL with endpoint: %s; cause: %s",
-                        tokenEndpoint, e.getMessage()), e);
+                    tokenEndpoint, e.getMessage()), e);
             }
         }
 
@@ -142,6 +142,7 @@ 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);
             this.mockResponse = new DOMHelper(null).parseXmlString(mockResponse, null);
             timesInvoked = 0;
         }
@@ -157,14 +158,14 @@ public static int getTimesInvoked() {
         @Override
         public byte[] classifyDocument(byte[] content, String uri) {
             String mockSingleArticleResponse = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
-                    "            <response>\n" +
-                    "              <STRUCTUREDDOCUMENT>\n" +
-                    "              <URL>../tmp/ca002056-e3f6-4c81-8c9f-00ca218330c4/1739460469_43eb</URL>\n" +
-                    "              <SYSTEM name=\"HASH\" value=\"2c3bcaf41fbabf8ff2e236c7580893ec\"/>\n" +
-                    "              <META name=\"Type\" value=\"TEXT (4003)\"/>\n" +
-                    "              <META name=\"title/document_title\" value=\"/some-uri.xml\"/>\n" +
-                    "              <SYSTEM name=\"DeterminedLanguage\" value=\"default\"/>" +
-                    "</STRUCTUREDDOCUMENT></response>\n";
+                "            <response>\n" +
+                "              <STRUCTUREDDOCUMENT>\n" +
+                "              <URL>../tmp/ca002056-e3f6-4c81-8c9f-00ca218330c4/1739460469_43eb</URL>\n" +
+                "              <SYSTEM name=\"HASH\" value=\"2c3bcaf41fbabf8ff2e236c7580893ec\"/>\n" +
+                "              <META name=\"Type\" value=\"TEXT (4003)\"/>\n" +
+                "              <META name=\"title/document_title\" value=\"/some-uri.xml\"/>\n" +
+                "              <SYSTEM name=\"DeterminedLanguage\" value=\"default\"/>" +
+                "</STRUCTUREDDOCUMENT></response>\n";
 
             return mockSingleArticleResponse.getBytes();
         }
diff --git a/marklogic-spark-api/src/main/java/com/marklogic/spark/core/extraction/TikaTextExtractor.java b/marklogic-spark-api/src/main/java/com/marklogic/spark/core/extraction/TikaTextExtractor.java
@@ -15,7 +15,6 @@
 import java.io.IOException;
 import java.util.LinkedHashMap;
 import java.util.Map;
-import java.util.Objects;
 import java.util.Optional;
 
 public class TikaTextExtractor implements TextExtractor {
@@ -26,13 +25,12 @@ public class TikaTextExtractor implements TextExtractor {
 
     @Override
     public Optional<ExtractionResult> extractText(DocumentInputs inputs) {
-        Objects.requireNonNull(inputs);
-        if (inputs.getContent() == null) {
+        byte[] contentAsBytes = inputs.getContentAsBytes();
+        if (contentAsBytes == null) {
             return Optional.empty();
         }
 
-        Objects.requireNonNull(inputs.getContentAsBytes());
-        try (ByteArrayInputStream stream = new ByteArrayInputStream(inputs.getContentAsBytes())) {
+        try (ByteArrayInputStream stream = new ByteArrayInputStream(contentAsBytes)) {
             Metadata metadata = new Metadata();
             String extractedText = tika.parseToString(stream, metadata);
             // Retain the order of these while dropping known keys that we know are just noise.
diff --git a/marklogic-spark-connector/src/main/java/com/marklogic/spark/reader/document/DocumentRowSchema.java b/marklogic-spark-connector/src/main/java/com/marklogic/spark/reader/document/DocumentRowSchema.java
@@ -89,15 +89,16 @@ private static void addPermissionsToMetadata(InternalRow row, DocumentMetadataHa
             ArrayData roles = permissions.keyArray();
             ArrayData capabilities = permissions.valueArray();
             for (int i = 0; i < roles.numElements(); i++) {
-                String role = roles.get(i, DataTypes.StringType).toString();
+                Object role = roles.get(i, DataTypes.StringType);
+                Objects.requireNonNull(role);
                 ArrayData caps = capabilities.getArray(i);
                 DocumentMetadataHandle.Capability[] capArray = new DocumentMetadataHandle.Capability[caps.numElements()];
                 for (int j = 0; j < caps.numElements(); j++) {
                     Object value = caps.get(j, DataTypes.StringType);
                     Objects.requireNonNull(value);
                     capArray[j] = DocumentMetadataHandle.Capability.valueOf(value.toString().toUpperCase());
                 }
-                metadata.getPermissions().add(role, capArray);
+                metadata.getPermissions().add(role.toString(), capArray);
             }
         }
     }
diff --git a/marklogic-spark-connector/src/main/java/com/marklogic/spark/writer/file/ContentWriter.java b/marklogic-spark-connector/src/main/java/com/marklogic/spark/writer/file/ContentWriter.java
@@ -16,6 +16,7 @@
 import org.apache.commons.io.IOUtils;
 import org.apache.spark.sql.catalyst.InternalRow;
 
+import javax.validation.constraints.NotNull;
 import javax.xml.transform.*;
 import javax.xml.transform.stream.StreamResult;
 import javax.xml.transform.stream.StreamSource;
@@ -66,18 +67,17 @@ class ContentWriter {
         }
     }
 
-    void writeContent(InternalRow row, OutputStream outputStream) throws IOException {
-        Objects.requireNonNull(outputStream);
+    void writeContent(InternalRow row, @NotNull OutputStream outputStream) throws IOException {
         if (this.isStreamingFiles) {
             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)).
-            String content = new String(row.getBinary(1));
-            Objects.requireNonNull(content);
-            outputStream.write(content.getBytes(this.encoding));
+            byte[] binary = row.getBinary(1);
+            Objects.requireNonNull(binary);
+            outputStream.write(new String(binary).getBytes(this.encoding));
         } else {
             outputStream.write(row.getBinary(1));
         }
@@ -139,15 +139,15 @@ private Transformer newTransformer() {
         }
     }
 
-    private void prettyPrintContent(InternalRow row, OutputStream outputStream) throws IOException {
+    private void prettyPrintContent(InternalRow row, @NotNull OutputStream outputStream) throws IOException {
         final byte[] content = row.getBinary(1);
+        Objects.requireNonNull(content);
         final String format = row.isNullAt(2) ? null : row.getString(2);
         if ("JSON".equalsIgnoreCase(format)) {
             prettyPrintJson(content, outputStream);
         } else if ("XML".equalsIgnoreCase(format)) {
             prettyPrintXml(content, outputStream);
         } else {
-            Objects.requireNonNull(content);
             if (this.encoding != null) {
                 outputStream.write(new String(content).getBytes(this.encoding));
             } else {
diff --git a/marklogic-spark-connector/src/main/java/com/marklogic/spark/writer/file/ZipFileWriter.java b/marklogic-spark-connector/src/main/java/com/marklogic/spark/writer/file/ZipFileWriter.java
@@ -21,6 +21,7 @@
 import java.text.SimpleDateFormat;
 import java.util.Date;
 import java.util.Map;
+import java.util.Objects;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipOutputStream;
 
@@ -60,8 +61,8 @@ public void write(InternalRow row) throws IOException {
         if (contentWriter == null) {
             createZipFileAndContentWriter();
         }
-        assert zipOutputStream != null;
-        assert contentWriter != null;
+        Objects.requireNonNull(zipOutputStream);
+        Objects.requireNonNull(contentWriter);
 
         final String uri = row.getString(0);
         final String entryName = FileUtil.makePathFromDocumentURI(uri);

Original file line number	Diff line number	Diff line change
`@@ -89,15 +89,16 @@ private static void addPermissionsToMetadata(InternalRow row, DocumentMetadataHa`
`89`	`89`	`ArrayData roles = permissions.keyArray();`
`90`	`90`	`ArrayData capabilities = permissions.valueArray();`
`91`	`91`	`for (int i = 0; i < roles.numElements(); i++) {`
`92`		`- String role = roles.get(i, DataTypes.StringType).toString();`
	`92`	`+ Object role = roles.get(i, DataTypes.StringType);`
	`93`	`+ Objects.requireNonNull(role);`
`93`	`94`	`ArrayData caps = capabilities.getArray(i);`
`94`	`95`	`DocumentMetadataHandle.Capability[] capArray = new DocumentMetadataHandle.Capability[caps.numElements()];`
`95`	`96`	`for (int j = 0; j < caps.numElements(); j++) {`
`96`	`97`	`Object value = caps.get(j, DataTypes.StringType);`
`97`	`98`	`Objects.requireNonNull(value);`
`98`	`99`	`capArray[j] = DocumentMetadataHandle.Capability.valueOf(value.toString().toUpperCase());`
`99`	`100`	`}`
`100`		`- metadata.getPermissions().add(role, capArray);`
	`101`	`+ metadata.getPermissions().add(role.toString(), capArray);`
`101`	`102`	`}`
`102`	`103`	`}`
`103`	`104`	`}`