mysql統計類似SQL語句查詢次數

mysql統計類似SQL語句查詢次數

vc-mysql-sniffer 工具抓取的sql分析。

1、先用shell腳本把所有enter符號替換為null，再根據語句前后的字符分隔語句

grep -Ev '# Time:|# User@Host' /tmp/tmp_vc_mysql.txt |sed 's/# Query_time.*/myxxxxx/g' |awk BEGIN{RS=EOF}'{gsub(/\\n/," ");print}'|awk BEGIN{RS=EOF}'{gsub(/myxxxxx/,"\\n");print}'

 

2、python實現替換無關字符串 vim analyze_sql.py

#!/usr/bin/python

#coding:utf8

# python analysis-vc-log.py 3315 | sort | uniq -c | sort -nr |head -n 10

 

import re

import sys

import os

import commands

 

if len(sys.argv) == 2:

    logPath = sys.argv[1]

    if not os.path.exists(logPath):

        print ("file " + logPath + " does not exists.")

        sys.exit(1)

else:

    print ("Usage: " + sys.argv[0] + " logPath")

    sys.exit(1)

logFo = open(logPath)

 

for line in logFo:

    line = re.sub(r"\n","",line)

    lineMatch = re.match(r".*",line,re.IGNORECASE)

    if lineMatch:

        lineTmp = lineMatch.group(0)

        # remove extra space 把多個空格的替換成一個空格 \s+ 表示空格至少出現一次

        lineTmp = re.sub(r"\s+", " ",lineTmp)

        # replace values (value) to values (x) \s*表示有0或多個空格, .*表示匹配除了換行外任意多次, ?為非貪婪模式

        lineTmp = re.sub(r"values\s*\(.*?\)", "values (x)",lineTmp)

        # replace filed = 'value' to filed = 'x'  s*('|\")表示匹配單引或雙引0或多次 \2表示應用第二個(...)分區,即 ('|\")  \\1可以寫成r"\1" 其實只是\<number> 。表示應用第一個分組 (=|>|<|>=|<=)

        lineTmp = re.sub(r"(=|>|<|>=|<=)\s*('|\").*?","\\1 'x'",lineTmp)

        # replace filed = value to filed = x  s*  匹配0或多個空格  [0-9]+ 匹配一個或多個數字

        lineTmp = re.sub(r"(=|>|<|>=|<=)\s*[0-9]+","\\1 x",lineTmp)

        # replace like 'value' to like 'x'

        lineTmp = re.sub(r"like\s+('|\").*?","like 'x'",lineTmp)

        # replace in (value) to in (x)   (.*?\) 匹配括號內的任意內容

        lineTmp = re.sub(r"in\s+\(.*?\)","in (x)",lineTmp)

    # replace between '...' and '...' to between 'x' and 'x'

    lineTmp = re.sub(r"between\s+('|\").*?\1\s+and\s+\1.*?\1","between 'x' and 'x' ",lineTmp)

    # replace between ... and ... to between x and x

    lineTmp = re.sub(r"between\s+[0-9]+\s+and\s+[0-9]+","between x and x ",lineTmp)    

        # replace limit x,y to limit

        lineTmp = re.sub(r"limit.*","limit",lineTmp)

        print lineTmp

logFo.close()

3 執行 python  analyze_sql.py tmp_vc_mysql.txt