Python StreamingContext.getActiveOrCreate方法代码示例

# 需要导入模块: from pyspark.streaming.context import StreamingContext [as 别名]
# 或者: from pyspark.streaming.context.StreamingContext import getActiveOrCreate [as 别名]
    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(StreamingContext.getActive(), None)

        def setupFunc():
            ssc = StreamingContext(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 = StreamingContext.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(StreamingContext.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 = StreamingContext.getActiveOrCreate(None, setupFunc)
        self.assertTrue(self.setupCalled)

        # Verify that if the Java context is stopped, then getActive() returns None
        self.ssc = StreamingContext(self.sc, self.duration)
        self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
        self.ssc.start()
        self.assertEqual(StreamingContext.getActive(), self.ssc)
        self.ssc._jssc.stop(False)
        self.setupCalled = False
        self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
        self.assertTrue(self.setupCalled)

# 需要导入模块: from pyspark.streaming.context import StreamingContext [as 别名]
# 或者: from pyspark.streaming.context.StreamingContext import getActiveOrCreate [as 别名]
    def test_get_or_create_and_get_active_or_create(self):
        inputd = tempfile.mkdtemp()
        outputd = tempfile.mkdtemp() + "/"

        def updater(vs, s):
            return sum(vs, s or 0)

        def setup():
            conf = SparkConf().set("spark.default.parallelism", 1)
            sc = SparkContext(conf=conf)
            ssc = StreamingContext(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

        cpd = tempfile.mkdtemp("test_streaming_cps")
        self.ssc = StreamingContext.getOrCreate(cpd, setup)
        self.ssc.start()

        def check_output(n):
            while not os.listdir(outputd):
                time.sleep(0.01)
            time.sleep(1)  # make sure mtime is larger than the previous one
            with open(os.path.join(inputd, str(n)), 'w') as f:
                f.writelines(["%d\n" % i for i in range(10)])

            while True:
                p = os.path.join(outputd, max(os.listdir(outputd)))
                if '_SUCCESS' not in os.listdir(p):
                    # not finished
                    time.sleep(0.01)
                    continue
                ordd = self.ssc.sparkContext.textFile(p).map(lambda line: line.split(","))
                d = ordd.values().map(int).collect()
                if not d:
                    time.sleep(0.01)
                    continue
                self.assertEqual(10, len(d))
                s = set(d)
                self.assertEqual(1, len(s))
                m = s.pop()
                if n > m:
                    continue
                self.assertEqual(n, m)
                break

        check_output(1)
        check_output(2)

        # Verify the getOrCreate() recovers from checkpoint files
        self.ssc.stop(True, True)
        time.sleep(1)
        self.setupCalled = False
        self.ssc = StreamingContext.getOrCreate(cpd, setup)
        self.assertFalse(self.setupCalled)
        self.ssc.start()
        check_output(3)

        # Verify the getActiveOrCreate() recovers from checkpoint files
        self.ssc.stop(True, True)
        time.sleep(1)
        self.setupCalled = False
        self.ssc = StreamingContext.getActiveOrCreate(cpd, setup)
        self.assertFalse(self.setupCalled)
        self.ssc.start()
        check_output(4)

        # Verify that getActiveOrCreate() returns active context
        self.setupCalled = False
        self.assertEquals(StreamingContext.getActiveOrCreate(cpd, setup), self.ssc)
        self.assertFalse(self.setupCalled)

        # Verify that getActiveOrCreate() calls setup() in absence of checkpoint files
        self.ssc.stop(True, True)
        shutil.rmtree(cpd)  # delete checkpoint directory
        self.setupCalled = False
        self.ssc = StreamingContext.getActiveOrCreate(cpd, setup)
        self.assertTrue(self.setupCalled)
        self.ssc.stop(True, True)