Python正则处理多行日志一例

假设现在有这样的SQL日志：

SELECT * FROM open_app WHERE 1 and `client_id` = ‘a08f5e32909cc9418f‘ and `is_valid` = ‘1‘ order by id desc limit 32700,100;
# Time: 160616 10:05:10
# [email protected]: shuqin[qqqq] @  [1.1.1.1]  Id: 46765069
# Schema: db_xxx  Last_errno: 0  Killed: 0
# Query_time: 0.561383  Lock_time: 0.000048  Rows_sent: 100  Rows_examined: 191166  Rows_affected: 0
# Bytes_sent: 14653
SET timestamp=1466042710;
SELECT * FROM open_app WHERE 1 and `client_id` = ‘a08f5e32909cc9418f‘ and `is_valid` = ‘1‘ order by id desc limit 36700,100;
# [email protected]: shuqin[ssss] @  [2.2.2.2]  Id: 46765069
# Schema: db_yyy  Last_errno: 0  Killed: 0
# Query_time: 0.501094  Lock_time: 0.000042  Rows_sent: 100  Rows_examined: 192966  Rows_affected: 0
# Bytes_sent: 14966
SET timestamp=1466042727;

要求从中解析出相应的信息， Python 程序：

import re

globalRegex = r‘^\s*(.*?)# ([email protected]:.*?)# (Schema:.*?)# (Query_time:.*?)# Bytes_sent:(.*?)SET timestamp=(\d+);\s*$‘
costRegex = r‘Query_time:\s*(.*)\s*Lock_time:\s*(.*)\s*Rows_sent:\s*(\d+)\s*Rows_examined:\s*(\d+)\s*Rows_affected:\s*(\d+)\s*‘
schemaRegex = r‘Schema:\s*(.*)\s*Last_errno:(.*)\s*Killed:\s*(.*)\s*‘

def readSlowSqlFile(slowSqlFilename):
    f = open(slowSqlFilename)
    ftext = ‘‘
    for line in f:
         ftext += line
    f.close()
    return ftext

def findInText(regex, text):
    return re.findall(regex, text, flags=re.DOTALL+re.MULTILINE)

def parseSql(sqlobj, sqlText):
    try:
        if sqlText.find(‘#‘) != -1:
            sqlobj[‘sql‘] = sqlText.split(‘#‘)[0].strip()
            sqlobj[‘time‘] = sqlText.split(‘#‘)[1].strip()
        else:
            sqlobj[‘sql‘] = sqlText.strip()
            sqlobj[‘time‘] = ‘‘
    except:
        sqlobj[‘sql‘] = sqlText.strip()

def parseCost(sqlobj, costText):
    matched = re.match(costRegex, costText)
    sqlobj[‘Cost‘] = costText
    if matched:
        sqlobj[‘QueryTime‘] = matched.group(1).strip()
        sqlobj[‘LockTime‘] = matched.group(2).strip()
        sqlobj[‘RowsSent‘] = int(matched.group(3))
        sqlobj[‘RowsExamined‘] = int(matched.group(4))
        sqlobj[‘RowsAffected‘] = int(matched.group(5))

def parseSchema(sqlobj, schemaText):
    matched = re.match(schemaRegex, schemaText)
    sqlobj[‘Schema‘] = schemaText
    if matched:
        sqlobj[‘Schema‘] = matched.group(1).strip()
        sqlobj[‘LastErrno‘] = int(matched.group(2))
        sqlobj[‘Killed‘] = int(matched.group(3))

def parseSQLObj(matched):
    sqlobj = {}
    try:
        if matched and len(matched) > 0:
            parseSql(sqlobj, matched[0].strip())
            sqlobj[‘UserHost‘] = matched[1].strip()
            sqlobj[‘ByteSent‘] = int(matched[4])
            sqlobj[‘timestamp‘] = int(matched[5])
            parseCost(sqlobj, matched[3].strip())
            parseSchema(sqlobj, matched[2].strip())
            return sqlobj
    except:
        return sqlobj

if __name__ == ‘__main__‘:

    files = [‘slow_sqls.txt‘]

    alltext = ‘‘
    for f in files:
        text = readSlowSqlFile(f)
        alltext += text
    allmatched = findInText(globalRegex, alltext)

    tablenames = [‘open_app‘]

    if not allmatched or len(allmatched) == 0:
        print ‘No matched. exit.‘
        exit(1)

    sqlobjMap = {}
    for matched in allmatched:
        sqlobj = parseSQLObj(matched)
        if len(sqlobj) == 0:
            continue
        for tablename in tablenames:
            if sqlobj[‘sql‘].find(tablename) != -1:
                 if not sqlobjMap.get(tablename):
                     sqlobjMap[tablename] = []
                 sqlobjMap[tablename].append(sqlobj)
                 break

    resultMap = {}
    for (tablename, sqlobjlist) in sqlobjMap.iteritems():
        sqlstat = {}
        for sqlobj in sqlobjlist:
            if sqlobj[‘sql‘] not in sqlstat:
                sqlstat[sqlobj[‘sql‘]] = 0
            sqlstat[sqlobj[‘sql‘]] += 1
        resultMap[tablename] = sqlstat

    f_res = open(‘/tmp/res.txt‘, ‘w‘)
    f_res.write(‘-------------------------------------: \n‘)
    f_res.write(‘Bref results: \n‘)
    for (tablename, sqlstat) in resultMap.iteritems():
        f_res.write(‘tablename: ‘ + tablename + ‘\n‘)
        sortedsqlstat = sorted(sqlstat.iteritems(), key=lambda d:d[1], reverse = True)
        for sortedsql in sortedsqlstat:
            f_res.write(‘sql = %s\ncounts: %d\n\n‘ % (sortedsql[0], sortedsql[1]))
    f_res.write(‘-------------------------------------: \n\n‘)

    f_res.write(‘-------------------------------------: \n‘)
    f_res.write(‘Detail results: \n‘)
    for (tablename, sqlobjlist) in sqlobjMap.iteritems():
        f_res.write(‘tablename: ‘ + tablename + ‘\n‘)
        f_res.write(‘sqlinfo: \n‘)
        for sqlobj in sqlobjlist:
            f_res.write(‘sql: ‘ + sqlobj[‘sql‘] + ‘ QueryTime: ‘ + str(sqlobj.get(‘QueryTime‘)) + ‘ LockTime: ‘ + str(sqlobj.get(‘LockTime‘)) + ‘\n‘)
            f_res.write(str(sqlobj) + ‘\n\n‘)
    f_res.write(‘-------------------------------------: \n‘)
    f_res.close()