def process(self, element,
timer1=DoFn.TimerParam(EMIT_TIMER_1),
timer2=DoFn.TimerParam(EMIT_TIMER_2),
timer3=DoFn.TimerParam(EMIT_TIMER_3)):
timer1.set(10)
timer2.set(20)
timer3.set(30)
def process(
self,
element,
buffer=DoFn.StateParam(BUFFER_STATE),
timer1=DoFn.TimerParam(EXPIRY_TIMER),
dynamic_timer=DoFn.TimerParam(EXPIRY_TIMER_FAMILY)):
yield element
def process(self,
element,
t=DoFn.TimestampParam,
buffer_1=DoFn.StateParam(BUFFER_STATE_1),
buffer_2=DoFn.StateParam(BUFFER_STATE_2),
timer_1=DoFn.TimerParam(EXPIRY_TIMER_1),
timer_2=DoFn.TimerParam(EXPIRY_TIMER_2)):
yield element
def process(self,
element,
emit=DoFn.TimerParam(EMIT_TIMER_FAMILY),
gc=DoFn.TimerParam(GC_TIMER)):
emit.set(10, dynamic_timer_tag='emit1')
emit.set(20, dynamic_timer_tag='emit2')
emit.set(30, dynamic_timer_tag='emit3')
gc.set(40)
def on_expiry_1(self,
window=DoFn.WindowParam,
timestamp=DoFn.TimestampParam,
key=DoFn.KeyParam,
buffer=DoFn.StateParam(BUFFER_STATE_1),
timer_1=DoFn.TimerParam(EXPIRY_TIMER_1),
timer_2=DoFn.TimerParam(EXPIRY_TIMER_2),
timer_3=DoFn.TimerParam(EXPIRY_TIMER_3)):
yield 'expired1'
def process(self,
element,
emit1=DoFn.TimerParam(EMIT_TIMER_FAMILY1),
emit2=DoFn.TimerParam(EMIT_TIMER_FAMILY2)):
emit1.set(10, dynamic_timer_tag='emit11')
emit1.set(20, dynamic_timer_tag='emit12')
emit1.set(30, dynamic_timer_tag='emit13')
emit2.set(30, dynamic_timer_tag='emit21')
emit2.set(20, dynamic_timer_tag='emit22')
emit2.set(10, dynamic_timer_tag='emit23')
def test_spec_construction(self):
BagStateSpec('statename', VarIntCoder())
with self.assertRaises(TypeError):
BagStateSpec(123, VarIntCoder())
CombiningValueStateSpec('statename', VarIntCoder(), TopCombineFn(10))
with self.assertRaises(TypeError):
CombiningValueStateSpec(123, VarIntCoder(), TopCombineFn(10))
with self.assertRaises(TypeError):
CombiningValueStateSpec('statename', VarIntCoder(), object())
SetStateSpec('setstatename', VarIntCoder())
with self.assertRaises(TypeError):
SetStateSpec(123, VarIntCoder())
with self.assertRaises(TypeError):
SetStateSpec('setstatename', object())
ReadModifyWriteStateSpec('valuestatename', VarIntCoder())
with self.assertRaises(TypeError):
ReadModifyWriteStateSpec(123, VarIntCoder())
with self.assertRaises(TypeError):
ReadModifyWriteStateSpec('valuestatename', object())
# TODO: add more spec tests
with self.assertRaises(ValueError):
DoFn.TimerParam(BagStateSpec('elements', BytesCoder()))
TimerSpec('timer', TimeDomain.WATERMARK)
TimerSpec('timer', TimeDomain.REAL_TIME)
with self.assertRaises(ValueError):
TimerSpec('timer', 'bogus_time_domain')
with self.assertRaises(ValueError):
DoFn.StateParam(TimerSpec('timer', TimeDomain.WATERMARK))
def process(self, element, emit=DoFn.TimerParam(EMIT_TIMER_FAMILY)):
if element[1] == 'set':
emit.set(10, dynamic_timer_tag='emit1')
emit.set(20, dynamic_timer_tag='emit2')
emit.set(30, dynamic_timer_tag='emit3')
if element[1] == 'clear':
emit.clear(dynamic_timer_tag='emit3')
def on_buffering_timer(
self,
element_state=DoFn.StateParam(ELEMENT_STATE),
count_state=DoFn.StateParam(COUNT_STATE),
buffering_timer=DoFn.TimerParam(BUFFERING_TIMER)):
return self.flush_batch(element_state, count_state,
buffering_timer)
def process(self,
element,
buffer=DoFn.StateParam(BUFFER_STATE),
timer1=DoFn.TimerParam(EXPIRY_TIMER)):
unused_key, value = element
buffer.add(value)
timer1.set(20)
def process(self,
element,
window=DoFn.WindowParam,
element_state=DoFn.StateParam(ELEMENT_STATE),
count_state=DoFn.StateParam(COUNT_STATE),
window_timer=DoFn.TimerParam(WINDOW_TIMER),
buffering_timer=DoFn.TimerParam(BUFFERING_TIMER)):
# Allowed lateness not supported in Python SDK
# https://beam.apache.org/documentation/programming-guide/#watermarks-and-late-data
window_timer.set(window.end)
element_state.add(element)
count_state.add(1)
count = count_state.read()
if count == 1 and max_buffering_duration_secs > 0:
# This is the first element in batch. Start counting buffering time if a
# limit was set.
buffering_timer.set(clock() + max_buffering_duration_secs)
if count >= batch_size:
return self.flush_batch(element_state, count_state,
buffering_timer)
def process(self, element, state=DoFn.StateParam(BUFFER_STATE),
timer=DoFn.TimerParam(UNMATCHED_TIMER)):
key, value = element
existing_values = list(state.read())
if not existing_values:
state.add(value)
timer.set(100)
else:
yield b'Record<%s,%s,%s>' % (key, existing_values[0], value)
state.clear()
timer.clear()
def process(self, element,
window=DoFn.WindowParam,
element_state=DoFn.StateParam(ELEMENT_STATE),
count_state=DoFn.StateParam(COUNT_STATE),
expiry_timer=DoFn.TimerParam(EXPIRY_TIMER)):
# Allowed lateness not supported in Python SDK
# https://beam.apache.org/documentation/programming-guide/#watermarks-and-late-data
expiry_timer.set(window.end)
element_state.add(element)
count_state.add(1)
count = count_state.read()
if count >= batch_size:
batch = [element for element in element_state.read()]
yield batch
element_state.clear()
count_state.clear()
def process(self,
element,
timer1=DoFn.TimerParam(EXPIRY_TIMER_1),
timer2=DoFn.TimerParam(EXPIRY_TIMER_2)):
pass
def expiry_callback(self,
element,
t1=DoFn.TimerParam(EXPIRY_TIMER_2),
t2=DoFn.TimerParam(EXPIRY_TIMER_2)):
yield element
def process(self,
element,
t1=DoFn.TimerParam(TIMER),
t2=DoFn.TimerParam(TIMER)):
yield element
def expiry_callback(self,
element,
timer=DoFn.TimerParam(EXPIRY_TIMER)):
yield element
def test_param_construction(self):
with self.assertRaises(ValueError):
DoFn.StateParam(TimerSpec('timer', TimeDomain.WATERMARK))
with self.assertRaises(ValueError):
DoFn.TimerParam(BagStateSpec('elements', BytesCoder()))
def process(self, element, timer1=DoFn.TimerParam(EMIT_TIMER_1)):
timer1.set(10)
def process(self,
element,
emit=DoFn.TimerParam(EMIT_CLEAR_SET_TIMER)):
yield ('1', 'set')
emit.set(1)
def on_expiry_family(self,
dynamic_timer=DoFn.TimerParam(EXPIRY_TIMER_FAMILY),
dynamic_timer_tag=DoFn.DynamicTimerTagParam):
yield (dynamic_timer_tag, 'expired_dynamic_timer')
def expiry_family_callback(
self,
element,
dynamic_timer=DoFn.TimerParam(EXPIRY_TIMER_FAMILY)):
yield element
def process(self, element,
emit=DoFn.TimerParam(EMIT_TIMER_FAMILY)):
emit.set(10)
emit.set(20, dynamic_timer_tag='')
def process(self,
element,
dynamic_timer_1=DoFn.TimerParam(EXPIRY_TIMER_FAMILY),
dynamic_timer_2=DoFn.TimerParam(EXPIRY_TIMER_FAMILY)):
yield element
def on_expiry_3(self,
buffer_1=DoFn.StateParam(BUFFER_STATE_1),
buffer_2=DoFn.StateParam(BUFFER_STATE_2),
timer_3=DoFn.TimerParam(EXPIRY_TIMER_3)):
yield 'expired3'
def expiry_callback(self,
buffer=DoFn.StateParam(BUFFER_STATE),
timer=DoFn.TimerParam(EXPIRY_TIMER)):
yield ''.join(str(x) for x in sorted(buffer.read()))
