From 13757b1198a4f565409c2735544c733bcb86a2ac Mon Sep 17 00:00:00 2001 From: Nick Pentreath Date: Fri, 15 Mar 2013 10:52:01 +0200 Subject: Adding Java versions of Pi and LogQuery --- .../src/main/java/spark/examples/JavaLogQuery.java | 113 +++++++++++++++++++++ .../src/main/java/spark/examples/JavaSparkPi.java | 47 +++++++++ .../src/main/scala/spark/examples/SparkPi.scala | 1 + 3 files changed, 161 insertions(+) create mode 100644 examples/src/main/java/spark/examples/JavaLogQuery.java create mode 100644 examples/src/main/java/spark/examples/JavaSparkPi.java (limited to 'examples') diff --git a/examples/src/main/java/spark/examples/JavaLogQuery.java b/examples/src/main/java/spark/examples/JavaLogQuery.java new file mode 100644 index 0000000000..56fceefcae --- /dev/null +++ b/examples/src/main/java/spark/examples/JavaLogQuery.java @@ -0,0 +1,113 @@ +package spark.examples; + +import com.google.common.collect.Lists; +import scala.Tuple2; +import scala.Tuple3; +import spark.api.java.JavaPairRDD; +import spark.api.java.JavaRDD; +import spark.api.java.JavaSparkContext; +import spark.api.java.function.Function2; +import spark.api.java.function.PairFunction; + +import java.io.Serializable; +import java.util.Collections; +import java.util.List; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * Executes a roll up-style query against Apache logs. + */ +public class JavaLogQuery { + + public static List exampleApacheLogs = Lists.newArrayList( + "10.10.10.10 - \"FRED\" [18/Jan/2013:17:56:07 +1100] \"GET http://images.com/2013/Generic.jpg " + + "HTTP/1.1\" 304 315 \"http://referall.com/\" \"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; GTB7.4; .NET CLR 2.0.50727; " + + ".NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 1.0.3705; .NET CLR 1.1.4322; .NET CLR " + + "3.5.30729; Release=ARP)\" \"UD-1\" - \"image/jpeg\" \"whatever\" 0.350 \"-\" - \"\" 265 923 934 \"\" " + + "62.24.11.25 images.com 1358492167 - Whatup", + "10.10.10.10 - \"FRED\" [18/Jan/2013:18:02:37 +1100] \"GET http://images.com/2013/Generic.jpg " + + "HTTP/1.1\" 304 306 \"http:/referall.com\" \"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; " + + "GTB7.4; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648; .NET CLR " + + "3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 1.0.3705; .NET CLR 1.1.4322; .NET CLR " + + "3.5.30729; Release=ARP)\" \"UD-1\" - \"image/jpeg\" \"whatever\" 0.352 \"-\" - \"\" 256 977 988 \"\" " + + "0 73.23.2.15 images.com 1358492557 - Whatup"); + + + public static Pattern apacheLogRegex = Pattern.compile("^([\\d.]+) (\\S+) (\\S+) \\[([\\w\\d:/]+\\s[+\\-]\\d{4})\\] \"(.+?)\" (\\d{3}) ([\\d\\-]+) \"([^\"]+)\" \"([^\"]+)\".*"); + + /** Tracks the total query count and number of aggregate bytes for a particular group. */ + public static class Stats implements Serializable { + + private int count; + private int numBytes; + + public Stats(int count, int numBytes) { + this.count = count; + this.numBytes = numBytes; + } + public Stats merge(Stats other) { + return new Stats(count + other.count, numBytes + other.numBytes); + } + + public String toString() { + return String.format("bytes=%s\tn=%s", numBytes, count); + } + } + + public static Tuple3 extractKey(String line) { + Matcher m = apacheLogRegex.matcher(line); + List key = Collections.emptyList(); + if (m.find()) { + String ip = m.group(1); + String user = m.group(3); + String query = m.group(5); + if (!user.equalsIgnoreCase("-")) { + return new Tuple3(ip, user, query); + } + } + return new Tuple3(null, null, null); + } + + public static Stats extractStats(String line) { + Matcher m = apacheLogRegex.matcher(line); + if (m.find()) { + int bytes = Integer.parseInt(m.group(7)); + return new Stats(1, bytes); + } + else + return new Stats(1, 0); + } + + public static void main(String[] args) throws Exception { + if (args.length == 0) { + System.err.println("Usage: JavaLogQuery [logFile]"); + System.exit(1); + } + + JavaSparkContext jsc = new JavaSparkContext(args[0], "JavaLogQuery", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + + JavaRDD dataSet = (args.length == 2) ? jsc.textFile(args[1]) : jsc.parallelize(exampleApacheLogs); + + JavaPairRDD, Stats> extracted = dataSet.map(new PairFunction, Stats>() { + @Override + public Tuple2, Stats> call(String s) throws Exception { + return new Tuple2, Stats>(extractKey(s), extractStats(s)); + } + }); + + JavaPairRDD, Stats> counts = extracted.reduceByKey(new Function2() { + @Override + public Stats call(Stats stats, Stats stats2) throws Exception { + return stats.merge(stats2); + } + }); + + List, Stats>> output = counts.collect(); + for (Tuple2 t : output) { + System.out.println(t._1 + "\t" + t._2); + } + System.exit(0); + } +} diff --git a/examples/src/main/java/spark/examples/JavaSparkPi.java b/examples/src/main/java/spark/examples/JavaSparkPi.java new file mode 100644 index 0000000000..e4cee97a42 --- /dev/null +++ b/examples/src/main/java/spark/examples/JavaSparkPi.java @@ -0,0 +1,47 @@ +package spark.examples; + +import spark.api.java.JavaRDD; +import spark.api.java.JavaSparkContext; +import spark.api.java.function.Function; +import spark.api.java.function.Function2; + +import java.util.ArrayList; +import java.util.List; + +/** Computes an approximation to pi */ +public class JavaSparkPi { + + public static void main(String[] args) throws Exception { + if (args.length == 0) { + System.err.println("Usage: JavaLogQuery [slices]"); + System.exit(1); + } + + JavaSparkContext jsc = new JavaSparkContext(args[0], "JavaLogQuery", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + + int slices = (args.length == 2) ? Integer.parseInt(args[1]) : 2; + int n = 100000 * slices; + List l = new ArrayList(n); + for (int i = 0; i < n; i++) + l.add(i); + + JavaRDD dataSet = jsc.parallelize(l, slices); + + int count = dataSet.map(new Function() { + @Override + public Integer call(Integer integer) throws Exception { + double x = Math.random() * 2 - 1; + double y = Math.random() * 2 - 1; + return (x * x + y * y < 1) ? 1 : 0; + } + }).reduce(new Function2() { + @Override + public Integer call(Integer integer, Integer integer2) throws Exception { + return integer + integer2; + } + }); + + System.out.println("Pi is roughly " + 4.0 * count / n); + } +} diff --git a/examples/src/main/scala/spark/examples/SparkPi.scala b/examples/src/main/scala/spark/examples/SparkPi.scala index 5a31d74444..f598d2ff9c 100644 --- a/examples/src/main/scala/spark/examples/SparkPi.scala +++ b/examples/src/main/scala/spark/examples/SparkPi.scala @@ -4,6 +4,7 @@ import scala.math.random import spark._ import SparkContext._ +/** Computes an approximation to pi */ object SparkPi { def main(args: Array[String]) { if (args.length == 0) { -- cgit v1.2.3