#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
import time
from datetime import datetime
from joblib import Parallel, delayed, parallel_backend
from collections import deque
from multiprocessing import cpu_count
import threading


class LogParser(object):
    def __init__(self, chunk_size=1024*1024*10, process_num_for_log_parsing=cpu_count()):
        self.log_unparsed_queue = deque() # 用于存儲(chǔ)未解析日志
        self.log_line_parsed_queue = deque()  # 用于存儲(chǔ)已解析日志行
        self.is_all_files_read = False  # 標(biāo)識(shí)是否已讀取所有日志文件
        self.process_num_for_log_parsing = process_num_for_log_parsing # 并發(fā)解析日志文件進(jìn)程數(shù)
        self.chunk_size = chunk_size # 每次讀取日志的日志塊大小
        self.files_read_list = [] # 存放已讀取日志文件
        self.log_parsing_finished = False # 標(biāo)識(shí)是否完成日志解析


    def read_in_chunks(self, filePath, chunk_size=1024*1024):
        """
        惰性函數(shù)（生成器），用于逐塊讀取文件。
        默認(rèn)區(qū)塊大小：1M
        """

        with open(filePath, 'r', encoding='utf-8') as f:            
            while True:
                chunk_data = f.read(chunk_size)
                if not chunk_data:
                    break
                yield chunk_data


    def read_log_file(self, logfile_path):
        '''
        讀取日志文件
        這里假設(shè)日志文件都是文本文件，按塊讀取后，可按換行符進(jìn)行二次切分，以便獲取行日志
        '''

        temp_list = []  # 二次切分后，頭，尾行日志可能是不完整的，所以需要將日志塊頭尾行日志相連接，進(jìn)行拼接
        for chunk in self.read_in_chunks(logfile_path, self.chunk_size):
            log_chunk = chunk.split('\n')
            temp_list.extend([log_chunk[0], '\n'])
            temp_list.append(log_chunk[-1])
            self.log_unparsed_queue.append(log_chunk[1:-1])
        self.log_unparsed_queue.append(''.join(temp_list).split('\n'))
        self.files_read_list.remove(logfile_path)


    def start_processes_for_log_parsing(self):
        '''啟動(dòng)日志解析進(jìn)程'''

        with parallel_backend("multiprocessing", n_jobs=self.process_num_for_log_parsing):
            Parallel(require='sharedmem')(delayed(self.parse_logs)() for i in range(self.process_num_for_log_parsing))

        self.log_parsing_finished = True

    def parse_logs(self):
        '''解析日志'''

        method_url_re_pattern = re.compile('(HEAD|POST|GET)\s+([^\s]+?)\s+',re.DOTALL)
        url_time_taken_extractor = re.compile('HTTP/1\.1.+\|(.+)\|\d+\|', re.DOTALL)

        while self.log_unparsed_queue or self.files_read_list:
            if not self.log_unparsed_queue:
                continue
            log_line_list = self.log_unparsed_queue.popleft()
            for log_line in log_line_list:
                #### do something with log_line
                if not log_line.strip():
                    continue

                res = method_url_re_pattern.findall(log_line)
                if not res:
                    print('日志未匹配到請(qǐng)求URL，已忽略：\n%s' % log_line)
                    continue
                method = res[0][0]
                url = res[0][1].split('?')[0]  # 去掉了 ?及后面的url參數(shù)

                # 提取耗時(shí)
                res = url_time_taken_extractor.findall(log_line)
                if res:
                    time_taken = float(res[0])
                else:
                    print('未從日志提取到請(qǐng)求耗時(shí)，已忽略日志：\n%s' % log_line)
                    continue

                # 存儲(chǔ)解析后的日志信息
                self.log_line_parsed_queue.append({'method': method,
                                                   'url': url,
                                                   'time_taken': time_taken,
                                                   })


    def collect_statistics(self):
        '''收集統(tǒng)計(jì)數(shù)據(jù)'''

        def _collect_statistics():
            while self.log_line_parsed_queue or not self.log_parsing_finished:
                if not self.log_line_parsed_queue:
                    continue
                log_info = self.log_line_parsed_queue.popleft()
                # do something with log_info
       
        with parallel_backend("multiprocessing", n_jobs=1):
            Parallel()(delayed(_collect_statistics)() for i in range(1))

    def run(self, file_path_list):
        # 多線程讀取日志文件
        for file_path in file_path_list:
            thread = threading.Thread(target=self.read_log_file,
                                      name="read_log_file",
                                      args=(file_path,))
            thread.start()
            self.files_read_list.append(file_path)

        # 啟動(dòng)日志解析進(jìn)程
        thread = threading.Thread(target=self.start_processes_for_log_parsing, name="start_processes_for_log_parsing")
        thread.start()

        # 啟動(dòng)日志統(tǒng)計(jì)數(shù)據(jù)收集進(jìn)程
        thread = threading.Thread(target=self.collect_statistics, name="collect_statistics")
        thread.start()

        start = datetime.now()
        while threading.active_count() > 1:
            print('程序正在努力解析日志...')
            time.sleep(0.5)

        end = datetime.now()
        print('解析完成', 'start', start, 'end', end, '耗時(shí)', end - start)

if __name__ == "__main__":
    log_parser = LogParser()
    log_parser.run(['access.log', 'access2.log'])