def test_schema_dstream(self):
def rddList(start, end):
return self.sc.parallelize(range(
start, end)).map(lambda i: (i, "Text" + str(i)))
def saveFunction(df):
df.write.format("column").mode("append").saveAsTable(
"streamingExample")
schema = StructType([
StructField("loc", IntegerType()),
StructField("text", StringType())
])
snsc = SnappyStreamingContext(self.sc, 1)
dstream = snsc.queueStream(
[rddList(1, 10), rddList(10, 20),
rddList(20, 30)])
snsc._snappycontext.dropTable("streamingExample", True)
snsc._snappycontext.createTable("streamingExample", "column", schema)
schemadstream = snsc.createSchemaDStream(dstream, schema)
schemadstream.foreachDataFrame(lambda df: saveFunction(df))
snsc.start()
time.sleep(1)
snsc.sql("select count(*) from streamingExample").show()
def setup():
conf = SparkConf().set("spark.default.parallelism", 1)
sc = SparkContext(conf=conf)
ssc = SnappyStreamingContext(sc, 0.5)
dstream = ssc.textFileStream(inputd).map(lambda x: (x, 1))
wc = dstream.updateStateByKey(updater)
wc.map(lambda x: "%s,%d" % x).saveAsTextFiles(outputd + "test")
wc.checkpoint(.5)
self.setupCalled = True
return ssc
def setup():
conf = SparkConf().set("spark.default.parallelism", 1)
sc = SparkContext(conf=conf)
ssc = SnappyStreamingContext(sc, 0.5)
# A function that cannot be serialized
def process(time, rdd):
sc.parallelize(range(1, 10))
ssc.textFileStream(inputd).foreachRDD(process)
return ssc
def test_text_file_stream(self):
d = tempfile.mkdtemp()
self.ssc = SnappyStreamingContext(self.sc, self.duration)
dstream2 = self.ssc.textFileStream(d).map(int)
result = self._collect(dstream2, 2, block=False)
self.ssc.start()
for name in ('a', 'b'):
time.sleep(1)
with open(os.path.join(d, name), "w") as f:
f.writelines(["%d\n" % i for i in range(10)])
self.wait_for(result, 2)
self.assertEqual([list(range(10)), list(range(10))], result)
def test_binary_records_stream(self):
d = tempfile.mkdtemp()
self.ssc = SnappyStreamingContext(self.sc, self.duration)
dstream = self.ssc.binaryRecordsStream(d, 10).map(
lambda v: struct.unpack("10b", bytes(v)))
result = self._collect(dstream, 2, block=False)
self.ssc.start()
for name in ('a', 'b'):
time.sleep(1)
with open(os.path.join(d, name), "wb") as f:
f.write(bytearray(range(10)))
self.wait_for(result, 2)
self.assertEqual([list(range(10)), list(range(10))], [list(v[0]) for v in result])
def test_get_active(self):
self.assertEqual(SnappyStreamingContext.getActive(), None)
# Verify that getActive() returns the active context
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(SnappyStreamingContext.getActive(), self.ssc)
# Verify that getActive() returns None
self.ssc.stop(False)
self.assertEqual(SnappyStreamingContext.getActive(), None)
# Verify that if the Java context is stopped, then getActive() returns None
self.ssc = SnappyStreamingContext(self.sc, self.duration)
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(SnappyStreamingContext.getActive(), self.ssc)
self.ssc._jssc.stop(False)
self.assertEqual(SnappyStreamingContext.getActive(), None)
def test_get_active_or_create(self):
# Test StreamingContext.getActiveOrCreate() without checkpoint data
# See CheckpointTests for tests with checkpoint data
self.ssc = None
self.assertEqual(SnappyStreamingContext.getActive(), None)
def setupFunc():
ssc = SnappyStreamingContext(self.sc, self.duration)
ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.setupCalled = True
return ssc
# Verify that getActiveOrCreate() (w/o checkpoint) calls setupFunc when no context is active
self.setupCalled = False
self.ssc = SnappyStreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
# Verify that getActiveOrCreate() retuns active context and does not call the setupFunc
self.ssc.start()
self.setupCalled = False
self.assertEqual(
SnappyStreamingContext.getActiveOrCreate(None, setupFunc),
self.ssc)
self.assertFalse(self.setupCalled)
# Verify that getActiveOrCreate() calls setupFunc after active context is stopped
self.ssc.stop(False)
self.setupCalled = False
self.ssc = SnappyStreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
# Verify that if the Java context is stopped, then getActive() returns None
self.ssc = SnappyStreamingContext(self.sc, self.duration)
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(SnappyStreamingContext.getActive(), self.ssc)
self.ssc._jssc.stop(False)
self.setupCalled = False
self.ssc = SnappyStreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
def setUp(self):
self.ssc = SnappyStreamingContext(self.sc, self.duration)
def setupFunc():
ssc = SnappyStreamingContext(self.sc, self.duration)
ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.setupCalled = True
return ssc
