add SameHostsProblem and SameHostsSolution

Author: James Lee

in/nasa_19950701.tsv

@@ -1,4 +1,4 @@
-host	logname	time	method	url	response	bytes	referer	useragent
+host	logname	time	method	url	response	bytes
 199.72.81.55	-	804571201	GET	/history/apollo/	200	6245		
 unicomp6.unicomp.net	-	804571206	GET	/shuttle/countdown/	200	3985		
 199.120.110.21	-	804571209	GET	/shuttle/missions/sts-73/mission-sts-73.html	200	4085		

in/nasa_19950801.tsv

@@ -1,4 +1,4 @@
-host	logname	time	method	url	response	bytes	referer	useragent
+host	logname	time	method	url	response	bytes
 in24.inetnebr.com	-	807249601	GET	/shuttle/missions/sts-68/news/sts-68-mcc-05.txt	200	1839		
 uplherc.upl.com	-	807249607	GET	/	304	0		
 uplherc.upl.com	-	807249608	GET	/images/ksclogo-medium.gif	304	0		

src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/SameHostsProblem.java

@@ -0,0 +1,23 @@
+package com.sparkTutorial.rdd.nasaApacheWebLogs;
+
+public class SameHostsProblem {
+
+    public static void main(String[] args) throws Exception {
+
+        /* "in/nasa_19950701.tsv" file contains 10000 log lines from one of NASA's apache server for July 1st, 1995.
+           "in/nasa_19950801.tsv" file contains 10000 log lines for August 1st, 1995
+           Create a Spark program to generate a new RDD which contains the hosts which are accessed on BOTH days.
+           Save the resulting RDD to "out/nasa_logs_same_hosts.csv" file.
+
+           Example output:
+           vagrant.vf.mmc.com
+           www-a1.proxy.aol.com
+           .....
+
+           Keep in mind, that the original log files contains the following header lines.
+           host	logname	time	method	url	response	bytes
+
+           Make sure the head lines are removed in the resulting RDD.
+         */
+    }
+}

src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/SameHostsSolution.java

@@ -0,0 +1,26 @@
+package com.sparkTutorial.rdd.nasaApacheWebLogs;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+
+public class SameHostsSolution {
+
+    public static void main(String[] args) throws Exception {
+
+        SparkConf conf = new SparkConf().setAppName("sameHosts").setMaster("local[1]");
+
+        JavaSparkContext sc = new JavaSparkContext(conf);
+
+        JavaRDD<String> julyFirstLogs = sc.textFile("in/nasa_19950701.tsv");
+        JavaRDD<String> augustFirstLogs = sc.textFile("in/nasa_19950801.tsv");
+
+        JavaRDD<String> julyFirstHosts = julyFirstLogs.map(line -> line.split("\t")[0]);
+
+        JavaRDD<String> augustFirstHosts = augustFirstLogs.map(line -> line.split("\t")[0]);
+
+        JavaRDD<String> intersection = julyFirstHosts.intersection(augustFirstHosts);
+
+        intersection.saveAsTextFile("out/nasa_logs_same_hosts.csv");
+    }
+}

src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/NasaApacheWebLogsProblem.java renamed to src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/UnionLogProblem.java

@@ -1,16 +1,16 @@
 package com.sparkTutorial.rdd.nasaApacheWebLogs;
 
-public class NasaApacheWebLogsProblem {
+public class UnionLogProblem {
 
     public static void main(String[] args) throws Exception {
 
         /* "in/nasa_19950701.tsv" file contains 10000 log lines from one of NASA's apache server for July 1st, 1995.
            "in/nasa_19950801.tsv" file contains 10000 log lines for August 1st, 1995
-           Create a Spark program to create a new RDD which contains the log lines from both July 1st and August 1st,
+           Create a Spark program to generate a new RDD which contains the log lines from both July 1st and August 1st,
            take a 0.1 sample of those log lines and save it to "out/sample_nasa_logs.tsv" file.
 
            Keep in mind, that the original log files contains the following header lines.
-           host	logname	time	method	url	response	bytes	referer	useragent
+           host	logname	time	method	url	response	bytes
 
            Make sure the head lines are removed in the resulting RDD.
          */

src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/NasaApacheWebLogsSolution.java renamed to src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/UnionLogsSolution.java

@@ -4,11 +4,11 @@
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
 
-public class NasaApacheWebLogsSolution {
+public class UnionLogsSolution {
 
     public static void main(String[] args) throws Exception {
 
-        SparkConf conf = new SparkConf().setAppName("nasaApacheWebLogs").setMaster("local[*]");
+        SparkConf conf = new SparkConf().setAppName("unionLogs").setMaster("local[*]");
 
         JavaSparkContext sc = new JavaSparkContext(conf);