filter out header line in SameHostsSolution

James Lee · James Lee · commit bc19a77860d8 · 2017-03-11T11:09:05.000Z
diff --git a/src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/SameHostsSolution.java b/src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/SameHostsSolution.java
@@ -21,6 +21,8 @@ public static void main(String[] args) throws Exception {
 
         JavaRDD<String> intersection = julyFirstHosts.intersection(augustFirstHosts);
 
-        intersection.saveAsTextFile("out/nasa_logs_same_hosts.csv");
+        JavaRDD<String> cleanedHostIntersection = intersection.filter(host -> !host.equals("host"));
+
+        cleanedHostIntersection.saveAsTextFile("out/nasa_logs_same_hosts.csv");
     }
 }

Original file line number	Diff line number	Diff line change
`@@ -21,6 +21,8 @@ public static void main(String[] args) throws Exception {`
`21`	`21`
`22`	`22`	`JavaRDD<String> intersection = julyFirstHosts.intersection(augustFirstHosts);`
`23`	`23`
`24`		`- intersection.saveAsTextFile("out/nasa_logs_same_hosts.csv");`
	`24`	`+ JavaRDD<String> cleanedHostIntersection = intersection.filter(host -> !host.equals("host"));`
	`25`	`+`
	`26`	`+ cleanedHostIntersection.saveAsTextFile("out/nasa_logs_same_hosts.csv");`
`25`	`27`	`}`
`26`	`28`	`}`