I'm reading some data from avro file using the avro library. It takes about a minute to load 33K objects from the file. This seem very slow to me, specially with the Java version reading the same file in about 1sec.
Here is the code, am I doing something wrong?
import avro.datafile
import avro.io
from time import time
def load(filename):
fo = open(filename, "rb")
reader = avro.datafile.DataFileReader(fo, avro.io.DatumReader())
for i, record in enumerate(reader):
pass
return i + 1
def main(argv=None):
import sys
from argparse import ArgumentParser
argv = argv or sys.argv
parser = ArgumentParser(description="Read avro file")
start = time()
num_records = load("events.avro")
end = time()
print("{0} records in {1} seconds".format(num_records, end - start))
if __name__ == "__main__":
main()
