Fix: ml/engine/utils/FileUtils casts long file length to int incorrectly

ml-algorithms/src/main/java/org/opensearch/ml/engine/utils/FileUtils.java

@@ -45,16 +45,16 @@ public class FileUtils {
      * @throws IOException
      */
     public static List<String> splitFileIntoChunks(File file, Path outputPath, int chunkSize) throws IOException {
-        int fileSize = (int) file.length();
+        long fileSize = file.length();
         ArrayList<String> nameList = new ArrayList<>();
         try (InputStream inStream = new BufferedInputStream(new FileInputStream(file))) {
             int numberOfChunk = 0;
-            int totalBytesRead = 0;
+            long totalBytesRead = 0;
             while (totalBytesRead < fileSize) {
                 String partName = numberOfChunk + "";
-                int bytesRemaining = fileSize - totalBytesRead;
+                long bytesRemaining = fileSize - totalBytesRead;
                 if (bytesRemaining < chunkSize) {
-                    chunkSize = bytesRemaining;
+                    chunkSize = (int) bytesRemaining;
                 }
                 byte[] temporary = new byte[chunkSize];
                 int bytesRead = inStream.read(temporary, 0, chunkSize);

ml-algorithms/src/test/java/org/opensearch/ml/engine/utils/FileUtilsTest.java

@@ -0,0 +1,60 @@
+/*
+ * Copyright OpenSearch Contributors
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+package org.opensearch.ml.engine.utils;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
+import java.io.File;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.util.Arrays;
+import java.util.List;
+import java.util.Random;
+
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+
+public class FileUtilsTest {
+    private final TemporaryFolder tempDir = new TemporaryFolder();
+
+    @Before
+    public void setUp() throws Exception {
+        tempDir.create();
+    }
+
+    @After
+    public void tearUp() {
+        tempDir.delete();
+    }
+
+    @Test
+    public void testSplitFileIntoChunks() throws Exception {
+        // Write file.
+        Random random = new Random();
+        File file = tempDir.newFile("large_file");
+        byte[] data = new byte[1017];
+        random.nextBytes(data);
+        Files.write(file.toPath(), data);
+
+        // Split file into chunks.
+        int chunkSize = 325;
+        List<String> chunkPaths = FileUtils.splitFileIntoChunks(file, tempDir.newFolder().toPath(), chunkSize);
+
+        // Verify.
+        int currentPosition = 0;
+        for (String chunkPath : chunkPaths) {
+            byte[] chunk = Files.readAllBytes(Path.of(chunkPath));
+            assertTrue("Chunk size", currentPosition + chunk.length <= data.length);
+            Assert.assertArrayEquals(Arrays.copyOfRange(data, currentPosition, currentPosition + chunk.length), chunk);
+            currentPosition += chunk.length;
+        }
+        assertEquals(currentPosition, data.length);
+    }
+}