# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\d+[-|/]\d+[-|/]\d+\s\S+)\s+(\w+)\s+([^:]+):\s+(.+)*"
test_str = ("2023-02-23 19:27:02 WARN SparkDriver(183): 是否使用testGo模式?false testGo模式下忽略命令行-b参数.\n"
"2023-02-23 19:27:02 WARN SparkDriver(359): 命令行参数(cmdOption):{a=de_boardHistory, b=boardHistory, g=[loadToAdb=false, upsert=true, etlDate=20230222], w=null}\n"
"2023-02-23 19:27:02 INFO ConfigOption(111): 加载本地配置文件(local.config),覆盖项目配置\n"
"2023-02-23 19:27:02 INFO ConfigOption(78): 提取命令行(cmdOption)相同key,覆盖项目配置\n"
"2023-02-23 19:27:02 WARN SparkDriver(183): 项目配置(configOption)重要参数:{cluster=true, test=false, projectName=ATLAS-ETL...\n"
"23/02/23 20:03:25 WARN [Driver] SparkUtil: /---------------------------------------*\n"
"23/02/23 20:03:25 WARN [Driver] SparkUtil: * SparkDiver *\n"
"23/02/23 20:03:25 WARN [Driver] SparkUtil: * <spark-2.4.7, scala-2.11> *\n"
"23/02/23 20:03:25 WARN [Driver] SparkUtil: *---------------------------------------*/\n"
"23/02/23 20:03:25 INFO [Driver] SparkUtil: init spark...\n"
"23/02/23 20:03:25 INFO [Driver] SparkUtil: localTest: false")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html