Merge remote branch 'origin/master'

README.txt → README.md

@@ -29,26 +29,27 @@ Getting Started
 To try it out run:
 
 1. compile and download all dependencies
-   
-    ant
+
+        ant
 
 2. start cassandra with built in job/task trackers
 
-    ./bin/brisk cassandra -t  
+        ./bin/brisk cassandra -t
 
 3. view jobtracker
-   
-    http://localhost:50030
+
+        http://localhost:50030
 
 4. examine CassandraFS
 
-    ./bin/brisk hadoop fs -lsr cfs:///
+        ./bin/brisk hadoop fs -lsr cfs:///
 
 5. start hive shell or webUI
-   
-   ./bin/brisk hive
+
+        ./bin/brisk hive
 
    or
-
-   ./bin/brisk hive --service hwi
-   open web browser to http://localhost:9999/hwi
+
+        ./bin/brisk hive --service hwi
+
+open web browser to http://localhost:9999/hwi

test/integration/com/datastax/TestUtils.java

@@ -226,7 +226,7 @@ public static Connection getHiveConnection()
             }
 
             String connectionString = "jdbc:hive://" + hiveServer + ":" + hiveServerPort + "/default";
-            System.out.println("Connection String: " + connectionString);
+            //System.out.println("Connection String: " + connectionString);
 
             Class.forName("org.apache.hadoop.hive.jdbc.HiveDriver");
 

test/integration/com/datastax/hive/runHiveExamplesTest.java

@@ -27,7 +27,6 @@ public static void tearDownAfterClass() throws Exception {
    /* movieline_u_data: load and query u_data from movie line demo */
     public void movieline_u_data() throws Exception {
 		HiveJDBCRunner.runQueries(connection, "movieline_u_data"); 
-		HiveJDBCRunner.runQueries(connection, "movieline_query_u_data"); 
     }   
 
    //@Ignore
@@ -36,7 +35,6 @@ public void movieline_u_data() throws Exception {
     public void movieline_u_user() throws Exception {
 		HiveJDBCRunner.runQueries(connection, "movieline_u_occupation"); 
 		HiveJDBCRunner.runQueries(connection, "movieline_u_user"); 
-		//HiveJDBCRunner.runQueries(connection, "movieline_query_u_user"); 
     }   
 
    //@Ignore
@@ -45,7 +43,6 @@ public void movieline_u_user() throws Exception {
     public void movieline_u_item() throws Exception {
 		HiveJDBCRunner.runQueries(connection, "movieline_u_genre"); 
 		HiveJDBCRunner.runQueries(connection, "movieline_u_item"); 
-		//HiveJDBCRunner.runQueries(connection, "movieline_query_u_item"); 
     }  
 
    @Ignore

test/integration/com/datastax/hive/testCases/movieline_u_data

@@ -15,7 +15,30 @@ ROW FORMAT DELIMITED
 FIELDS TERMINATED BY '\t';
 
 -- Query out data
-SELECT userid, count(*) 
-FROM u_data 
+SELECT COUNT(*), COUNT(distinct userid) FROM u_data;
+
+-- Add MapReduce Python MR Job
+ADD FILE [[DATA_DIR]]/weekday_mapper.py;
+
+-- Transform and Insert Data from Source to Target
+INSERT OVERWRITE TABLE u_data_new
+SELECT TRANSFORM (userid, movieid, rating, unixtime)
+  USING 'python weekday_mapper.py' AS (userid, movieid, rating, weekday)
+FROM u_data;
+
+-- Query Data out of Target
+SELECT weekday, COUNT(*) FROM u_data_new GROUP BY weekday;
+
+-- Query Data out of Source
+SELECT userid, count(*) FROM u_data 
+WHERE userid > 100 and userid < 150 
 GROUP BY userid 
-ORDER BY userid;
+ORDER BY userid;
+
+SELECT * FROM u_data 
+ORDER BY userid, movieid, rating 
+LIMIT 20;
+
+SELECT userid, movieid, rating FROM u_data 
+ORDER BY userid, movieid, rating 
+LIMIT 20;