def write_avro(schema, records, runs=1):
times = []
for _ in range(runs):
iostream = BytesIO()
start = time.time()
writer = DataFileWriter(iostream, DatumWriter(),
avro.schema.SchemaFromJSONData(schema))
for record in records:
writer.append(record)
writer.flush()
end = time.time()
times.append(end - start)
print(f'... {runs} runs averaged {sum(times) / runs} seconds')
return iostream
def _write_data(self,
directory=None,
prefix=tempfile.template,
codec='null',
count=len(RECORDS)):
with tempfile.NamedTemporaryFile(delete=False,
dir=directory,
prefix=prefix) as f:
writer = DataFileWriter(f, DatumWriter(), self.SCHEMA, codec=codec)
len_records = len(self.RECORDS)
for i in range(count):
writer.append(self.RECORDS[i % len_records])
writer.close()
self._temp_files.append(f.name)
return f.name
def _write_data(self,
directory=None,
prefix=tempfile.template,
codec='null',
count=len(RECORDS),
sync_interval=avro.datafile.SYNC_INTERVAL):
old_sync_interval = avro.datafile.SYNC_INTERVAL
try:
avro.datafile.SYNC_INTERVAL = sync_interval
with tempfile.NamedTemporaryFile(delete=False,
dir=directory,
prefix=prefix) as f:
writer = DataFileWriter(f, DatumWriter(), self.SCHEMA, codec=codec)
len_records = len(self.RECORDS)
for i in range(count):
writer.append(self.RECORDS[i % len_records])
writer.close()
self._temp_files.append(f.name)
return f.name
finally:
avro.datafile.SYNC_INTERVAL = old_sync_interval
