MinIO's Object Lambda implementation allows for transforming your data to serve unique data format requirements for each application. For example, a dataset created by an ecommerce application might include personally identifiable information (PII). When the same data is processed for analytics, PII should be redacted. However, if the same dataset is used for a marketing campaign, you might need to enrich the data with additional details, such as information from the customer loyalty database.

### **4.2 WordCount**

WordCount is a simple program that counts how often a word occurs in a text file. The code builds a dataset of (String, Int) pairs called counts, and saves the dataset to a file.

The following example submits WordCount code to the Scala shell. Select an input file for the Spark WordCount example. We can use any text file as input.

- Login as user **‘spark’**.

        print(statsDetails['BytesScanned'])
        print("Stats details bytesProcessed: ")
        print(statsDetails['BytesProcessed'])
```

## 4. Run the Program

Upload a sample dataset to MinIO using the following commands.

```sh
curl "https://population.un.org/wpp/Download/Files/1_Indicators%20(Standard)/CSV_FILES/WPP2019_TotalPopulationBySex.csv" > TotalPopulation.csv
mc mb myminio/mycsvbucket

			if err.Error() != test.ExpectedErr.Error() {
				t.Errorf("Test %d: got error '%v' - want error '%v'", i, err, test.ExpectedErr)
			}
		}
		if !bytes.Equal(dataKey, test.DataKey) {
			t.Errorf("Test %d: got data key '%v' - want data key '%v'", i, dataKey, test.DataKey)
		}
		if keyID != test.KeyID {
			t.Errorf("Test %d: got key-ID '%v' - want key-ID '%v'", i, keyID, test.KeyID)
		}

		if err != nil {
			t.Fatalf("Test %d: failed to decrypt key: %v", i, err)
		}
		if !bytes.Equal(plaintext, dataKey) {
			t.Fatalf("Test %d: decrypted key does not generated one: got %x - want %x", i, plaintext, dataKey)
		}
	}
}

var decryptKeyTests = []struct {
	KeyID      string
	Plaintext  string
	Ciphertext string
	Context    Context
}{
	{

				int64(testCase.dataLen), testCase.chunkSize, bytes.NewReader(testCase.data),
				testCase.accessKey, testCase.secretKey)
		case testCase.contentEncoding == "":
			req, err = newTestStreamingSignedRequest(http.MethodPut,
				getPutObjectURL("", testCase.bucketName, testCase.objectName),
				int64(testCase.dataLen), testCase.chunkSize, bytes.NewReader(testCase.data),

	srcSet := s.getHashedSet(srcObject)
	dstSet := s.getHashedSet(dstObject)

	cpSrcDstSame := srcSet == dstSet
	// Check if this request is only metadata update.
	if cpSrcDstSame && srcInfo.metadataOnly {
		// Version ID is set for the destination and source == destination version ID.

}

// calculateSignedChunkLength - calculates the length of the overall stream (data + metadata)
func calculateStreamContentLength(dataLen, chunkSize int64) int64 {
	if dataLen <= 0 {
		return 0
	}
	chunksCount := dataLen / chunkSize
	remainingBytes := dataLen % chunkSize
	var streamLen int64
	streamLen += chunksCount * calculateSignedChunkLength(chunkSize)
	if remainingBytes > 0 {