def word_count(input_path, output_path):
env = StreamExecutionEnvironment.get_execution_environment()
env.set_runtime_mode(RuntimeExecutionMode.BATCH)
# write all the data to one file
env.set_parallelism(1)
# define the source
if input_path is not None:
ds = env.from_source(
source=FileSource.for_record_stream_format(StreamFormat.text_line_format(),
input_path)
.process_static_file_set().build(),
watermark_strategy=WatermarkStrategy.for_monotonous_timestamps(),
source_name="file_source"
)
else:
print("Executing word_count example with default input data set.")
print("Use --input to specify file input.")
ds = env.from_collection(word_count_data)
def split(line):
yield from line.split()
# compute word count
ds = ds.flat_map(split) \
.map(lambda i: (i, 1), output_type=Types.TUPLE([Types.STRING(), Types.INT()])) \
.key_by(lambda i: i[0]) \
.reduce(lambda i, j: (i[0], i[1] + j[1]))
# define the sink
if output_path is not None:
ds.sink_to(
sink=FileSink.for_row_format(
base_path=output_path,
encoder=Encoder.simple_string_encoder())
.with_output_file_config(
OutputFileConfig.builder()
.with_part_prefix("prefix")
.with_part_suffix(".ext")
.build())
.with_rolling_policy(RollingPolicy.default_rolling_policy())
.build()
)
else:
print("Printing result to stdout. Use --output to specify output path.")
ds.print()
# submit for execution
env.execute()
def test_stream_file_sink(self):
self.env.set_parallelism(2)
ds = self.env.from_collection([('ab', 1), ('bdc', 2), ('cfgs', 3), ('deeefg', 4)],
type_info=Types.ROW([Types.STRING(), Types.INT()]))
ds.map(
lambda a: a[0],
Types.STRING()).add_sink(
StreamingFileSink.for_row_format(self.tempdir, Encoder.simple_string_encoder())
.with_rolling_policy(
RollingPolicy.default_rolling_policy(
part_size=1024 * 1024 * 1024,
rollover_interval=15 * 60 * 1000,
inactivity_interval=5 * 60 * 1000))
.with_output_file_config(
OutputFileConfig.OutputFileConfigBuilder()
.with_part_prefix("prefix")
.with_part_suffix("suffix").build()).build())
self.env.execute("test_streaming_file_sink")
results = []
import os
for root, dirs, files in os.walk(self.tempdir, topdown=True):
for file in files:
self.assertTrue(file.startswith('.prefix'))
self.assertTrue('suffix' in file)
path = root + "/" + file
with open(path) as infile:
for line in infile:
results.append(line)
expected = ['deeefg\n', 'bdc\n', 'ab\n', 'cfgs\n']
results.sort()
expected.sort()
self.assertEqual(expected, results)
def test_file_sink(self):
base_path = "/tmp/1.txt"
encoder = Encoder.simple_string_encoder()
file_sink_builder = FileSink.for_row_format(base_path, encoder)
file_sink = file_sink_builder\
.with_bucket_check_interval(1000) \
.with_bucket_assigner(BucketAssigner.base_path_bucket_assigner()) \
.with_rolling_policy(RollingPolicy.on_checkpoint_rolling_policy()) \
.with_output_file_config(
OutputFileConfig.builder().with_part_prefix("pre").with_part_suffix("suf").build())\
.build()
buckets_builder_field = \
load_java_class("org.apache.flink.connector.file.sink.FileSink"). \
getDeclaredField("bucketsBuilder")
buckets_builder_field.setAccessible(True)
buckets_builder = buckets_builder_field.get(
file_sink.get_java_function())
self.assertEqual("DefaultRowFormatBuilder",
buckets_builder.getClass().getSimpleName())
row_format_builder_clz = load_java_class(
"org.apache.flink.connector.file.sink.FileSink$RowFormatBuilder")
encoder_field = row_format_builder_clz.getDeclaredField("encoder")
encoder_field.setAccessible(True)
self.assertEqual(
"SimpleStringEncoder",
encoder_field.get(buckets_builder).getClass().getSimpleName())
interval_field = row_format_builder_clz.getDeclaredField(
"bucketCheckInterval")
interval_field.setAccessible(True)
self.assertEqual(1000, interval_field.get(buckets_builder))
bucket_assigner_field = row_format_builder_clz.getDeclaredField(
"bucketAssigner")
bucket_assigner_field.setAccessible(True)
self.assertEqual(
"BasePathBucketAssigner",
bucket_assigner_field.get(
buckets_builder).getClass().getSimpleName())
rolling_policy_field = row_format_builder_clz.getDeclaredField(
"rollingPolicy")
rolling_policy_field.setAccessible(True)
self.assertEqual(
"OnCheckpointRollingPolicy",
rolling_policy_field.get(
buckets_builder).getClass().getSimpleName())
output_file_config_field = row_format_builder_clz.getDeclaredField(
"outputFileConfig")
output_file_config_field.setAccessible(True)
output_file_config = output_file_config_field.get(buckets_builder)
self.assertEqual("pre", output_file_config.getPartPrefix())
self.assertEqual("suf", output_file_config.getPartSuffix())
('hi', 4), ('hi', 5), ('hi', 8),
('hi', 9), ('hi', 15)],
type_info=Types.TUPLE(
[Types.STRING(),
Types.INT()]))
# define the watermark strategy
watermark_strategy = WatermarkStrategy.for_monotonous_timestamps() \
.with_timestamp_assigner(MyTimestampAssigner())
ds = data_stream.assign_timestamps_and_watermarks(watermark_strategy) \
.key_by(lambda x: x[0], key_type=Types.STRING()) \
.window(TumblingEventTimeWindows.of(Time.milliseconds(5))) \
.process(CountWindowProcessFunction(),
Types.TUPLE([Types.STRING(), Types.INT(), Types.INT(), Types.INT()]))
# define the sink
if output_path is not None:
ds.sink_to(sink=FileSink.for_row_format(
base_path=output_path, encoder=Encoder.simple_string_encoder()
).with_output_file_config(OutputFileConfig.builder().with_part_prefix(
"prefix").with_part_suffix(".ext").build()).with_rolling_policy(
RollingPolicy.default_rolling_policy()).build())
else:
print(
"Printing result to stdout. Use --output to specify output path.")
ds.print()
# submit for execution
env.execute()