记录一次利用 python 进行日志模块开发过程

只记录大体思路和我认为其中需要记录的地方。

正则匹配

正则匹配的模式很难记忆，即使记住了，也很难写出无错误的匹配模式。但是，借助网上一些提供实时对比的网站，如 regexr.com。

代码示意：

import os

import re

'''

define regex mode

'''

get_imgpath_regex = re.compile(r'''(

    (\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2},\d+)      # time

    \s      # separate

    (.*)?get_imgpath\sused\stime\sis\s      # info

    (\d+.\d+)       # time

    \sargs\sis\s\(u'     # separate

    (.*?)',\)\sresult\sis\s     # img dir

    (.*?.jpg)      # img path

)''', re.VERBOSE)

get_imgpath_flag = 'get_imgpath'

def main():

    for infile in infile_list:

        # prase line using regex mode

        with open(infile, "r") as file:

            for line in file:    # 先判断关键词

                currentDict = {}

                if get_imgpath_flag in line:

                    for groups in regex['get_imgpath_regex'].findall(line):    #　再提取模式对应的内容

                        currentDict = {'date': groups[1], 'cost_time':groups[3],

                        'img_dir':groups[4], 'img_path':groups[5]}

                        # print(currentDict)

                        get_imgpath_match.append(currentDict)

    else:

                    pass

参数配置

采取的方式为参数存储在一个单独的文件，如 config.json。

{

    "FLAG" : {

        "SAVE_SPILT_LOG_FILE_FLAG" : false ,

        "SAVE_MERGE_LOG_FILE_FLAG" : false ,

        "USE_CURRENT_PATH" : false

    },

    "PATH" : {

        "INPUT_LOG_FILE_PATH" : "E:\\zwk\\Code\\logger_read\\data\\pro_data" ,

        "SAVE_SPILT_MERGE_LOG_PATH" : "E:\\zwk\\Code\\logger_read\\output\\spilt_merge_log" ,

        "OUTPUT_RESULT_PATH" : "E:\\zwk\\Code\\logger_read\\output"

    },

    "PARAMETERS" : {

        "windows_size" : 2 ,

        "duplicate_times" : 1

    }

}

再对参数进行解析，

import json

def main():

    # outfile_path = os.path.normpath("output/filtered")

    global parameters

    if(config['FLAG']['USE_CURRENT_PATH']):

        pwd = os.getcwd()

        config['PATH']['INPUT_LOG_FILE_PATH'] = os.path.join(pwd, 'data')

        config['PATH']['SAVE_SPILT_MERGE_LOG_PATH'] = os.path.join(pwd, 'output')

        config['PATH']['OUTPUT_RESULT_PATH'] = os.getcwd()

    output_file_path = config['PATH']

    flag = config['FLAG']

if __name__ == '__main__':

    this_folder = os.path.dirname(os.path.abspath(__file__))

    config_file = os.path.join(this_folder, 'config.json')

    exists_check = os.path.isfile(config_file)

    if not exists_check:

        print('Error: loss of config file, Exit !!!')

    with open(config_file, 'r') as f:

        config = json.load(f)

    # improve it, use as global variable

    parameters = config['PARAMETERS']

    main()

目录、文件名

在这里，示例我认为的还不错做法，主要是不受系统影响

    this_folder = os.path.dirname(os.path.abspath(__file__))

    config_file = os.path.join(this_folder, 'config.json')

    exists_check = os.path.isfile(config_file)

    if not exists_check:

        print('Error: loss of config file, Exit !!!')

    with open(config_file, 'r') as f:

        config = json.load(f)

    # 省略中间

    # write output to files

    os.makedirs(outfile['SAVE_SPILT_MERGE_LOG_PATH'], exist_ok=True)

巴特西

记录一次利用 python 进行日志模块开发过程

正则匹配

参数配置

目录、文件名

最新文章

热门文章