Hadoopのログから日付、ログレベル、メッセージを分割して返す

gistfile1.py

example = """2014-01-05 22:20:50,307 INFO org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceScanner: Verification succeeded for BP-1337840909-192.168.0.1-1374311151785:blk_8462243608396789329_201176
"""

def parse_datetime_and_level(line):
    """ input: hadoop log
        output: [datetime, loglevel, message]
    """
    import re
    r = re.compile("(^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2},\d{3}) ([A-Z]{4,5}) (.*)")
    m = r.match(line)
    return m.groups()