tzachz

sealed trait Result
class Success extends Result
class Failed extends Result

// For some types A, B, C, D, we have these async computations which may fail:
def f1(a: A): Future[Either[Failed, B]] = ???
def f2(b: B): Future[Either[Failed, C]] = ???
def f3(c: C): Future[Either[Failed, D]] = ???
def f4(d: D): Future[Either[Failed, Result]] = ???

tzachz

public class TestsExecutionRecorder {

    private String namespace;
    private Stopwatch stopwatch;
    private long duration;

    TestsExecutionRecorder(TestType testType) {
        this.namespace = "test." + testType;
    }

tzachz

public class CampaignServiceImpl {

    private static final double budgetMarginPercent = 0.03;
    private final CampaignCostService campaignCostService;

    /**** 
     * Read this and try to answer: when does a campaign have available funds? 
     *
     * Hard to answer because method deals with different abstraction levels - 
     * mixing the important business logic with the insignificant low-level details

tzachz

AnodotReporterConfiguration anodotConf = 
  new DefaultAnodotReporterConfiguration("your-token", 60, "https://api.anodot.com/api/v1/metrics");

Anodot3ReporterBuilder.builderFor(anodotConf)
  .build(metricRegistry)
  .start()

tzachz

// Inspired by https://gist.github.com/abesto/cdcdd38263eacf1cbb51
// Task creates a .dot file with all inter-module dependencies
// Supports any depth of nested modules

task moduleDependencyReport {
    doLast {
        def file = new File("project-dependencies.dot")
        file.delete()
        file << "digraph {\n"
        file << "splines=ortho\n"

tzachz

import org.apache.spark.SparkContext
import org.apache.spark.sql.expressions.{MutableAggregationBuffer, UserDefinedAggregateFunction}
import org.apache.spark.sql.types._
import org.apache.spark.sql.{Column, Row, SQLContext}

/***
  * UDAF combining maps, overriding any duplicate key with "latest" value
  * @param keyType DataType of Map key
  * @param valueType DataType of Value key
  * @param merge function to merge values of identical keys

tzachz

import java.io.{File, IOException}
import java.net.InetAddress

import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.slf4j.{Logger, LoggerFactory}

import scala.util.{Failure, Try}

object LocalDiskHealthCheck {

tzachz

import java.text.SimpleDateFormat
import java.util.Date
import org.json4s._
import org.json4s.jackson.JsonMethods.parse
import scala.io.Source.fromURL

object SparkAppStats {

  val url = "http://<host>:4040/api/v1/applications/<app-name>/jobs"

tzachz

import com.yammer.metrics.Metrics
import com.yammer.metrics.core.Gauge
import org.apache.spark.SparkContext

/**
 * Created by tzachz on 10/21/15
 */
object SparkContextInstrumentor {

  def instrument(context: SparkContext): SparkContext = {

tzachz

package com.kenshoo.kripke.core

import com.yammer.metrics.Metrics
import com.yammer.metrics.core.{MetricName, Counter}
import org.apache.spark.Accumulator
import org.apache.spark.rdd.RDD

import scala.reflect.ClassTag

object CounterBackedAccumulatorUtil {