import re
from pyspark import SparkContext

sc = SparkContext.getOrCreate()

LOG_PATTERN = re.compile(r'^(\S+) (\S+) (\S+) \[([\w:/]+\s[+-]\d{4})\] "(\S+) (\S+)\s*(\S*)\s?" (\d{3}) (\S+)')


def parse_log_line(line):
    match = LOG_PATTERN.match(line)
    if not match:
        return None

    return {
        'ip': match.group(1)
    }


logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
raw_logs = sc.textFile(logFile)

parsed_logs = raw_logs.map(parse_log_line).filter(lambda x: x is not None)

# 提取 IP 地址并统计唯一主机数量
unique_hosts = parsed_logs.map(lambda log: log['ip']).distinct()
unique_host_count = unique_hosts.count()

print("Total number of unique hosts: {0}".format(unique_host_count))

sc.stop()