diogodanielsoaresferreira

@Component
class MessageListenerImpl(
    @Autowired private val saveMessageUseCase: SaveMessageUseCase
): MessageListener {

    private val logger: Logger = LoggerFactory.getLogger(this.javaClass)

    @RabbitListener(queues = ["\${messages.processor.queue.name}"])
    override fun process(event: MessageEvent) {
        logger.debug("operation=process, message='received MessageEvent {}'", event)

diogodanielsoaresferreira

@Repository
class MessageRepositoryImpl(
    @Autowired private val jdbcTemplate: JdbcTemplate
): MessageRepository {

    private val logger: Logger = LoggerFactory.getLogger(this.javaClass)

    override fun save(entity: Message) {
        val insertQuery = """
            INSERT INTO public.message(message_timestamp, message_value)

diogodanielsoaresferreira

interface MessageListener {
    fun process(event: MessageEvent)
}

diogodanielsoaresferreira

interface MessageRepository {
    fun save(entity: Message)
}

diogodanielsoaresferreira

@Component
class SaveMessageUseCase(
    @Autowired private val repository: MessageRepository
): {

    private val logger: Logger = LoggerFactory.getLogger(this.javaClass)

    override fun execute(message: Message) {
        logger.debug("operation=save, message='saving message {}'", message)
        repository.save(message)

diogodanielsoaresferreira

data class Message(
    val timestamp: OffsetDateTime,
    val value: String
)

diogodanielsoaresferreira

$ time python most_common_combinations.py
[2]    10731 killed     python3 most_common_combinations.py
python3 most_common_combinations.py  103,54s user 19,39s system 93% cpu 2:12,04 total
$ time ./most_common_combinations.py
./most_common_combinations.sh  162,86s user 24,32s system 113% cpu 2:44,33 total

diogodanielsoaresferreira

$ time python most_common_combinations.py
python3 most_common_combinations.py  13,45s user 1,62s system 99% cpu 15,072 total
$ time ./most_common_combinations.py
./most_common_combinations.sh  22,89s user 2,48s system 112% cpu 22,638 total

diogodanielsoaresferreira

tail -n +1 Dataset-Unicauca-Version2-87Atts.csv 
	| awk -F',' '{print $2, $3, $4, $5}' 
	| sort 
	| uniq -c 
	| sort -nr 
	| head -n 20 
	> "processed_data_bash.tsv"

diogodanielsoaresferreira

import pandas as pd
pd.read_csv('Dataset-Unicauca-Version2-87Atts.csv', header = 0)
	.groupby(['Source.IP', 'Source.Port', 'Destination.IP', 'Destination.Port'])
	.size()
	.sort_values(ascending=False)[:20]
	.to_csv('processed_data_python.csv')