Python正则处理多行日志一例(可配置化)

　正则表达式基础知识请参阅《正则表达式基础知识》，本文使用正则表达式来匹配多行日志并从中解析出相应的信息。

    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
# User@Host: 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;
# User@Host: 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， 有如下知识点：

　  (1)  默认正则是单行模式， 要匹配多行，需要开启 "多行模式"：　MULTILINE； 对于点号，默认不匹配换行符，为了匹配换行符，也需要开启 "DOTALL模式"；

　  (2)  为了匹配每个多行日志，必须使用非贪婪模式，即在 .* 后面加 ? ,　否则第一个匹配会匹配到末尾；

　  (3)  分而治之。编写正确的正则表达式匹配指定长字符串是不容易的，采用的策略是分而治之，将整个字符串分解成多个子串，分别匹配字串。这里每个字串都是一行，匹配好一行后，可以进一步在行内更细化的匹配； 

　  (4)  无处不在的空格符要使用 s* 或 s+ 来增强健壮性； 固定的普通字符串可以在正则表达式中更好地标识各个字串，更容易地匹配到。

　  (5)  Python 正则有两个常用用法： re.findall , re.match ; 前者的匹配结果是一个列表，　每个列表元素是一个元组， 匹配一个多行日志；元组的每个元素用来提取对应捕获分组的字符串；　re.match 的匹配结果是一个 Match 对象， 可以通过 group(n) 来获取每个捕获分组的匹配字符串。下面的程序特意两种都用到了。对于多行匹配，使用了 re.findall ; 对于行内匹配，使用了 re.match ;  初学者常问这两者那两者有什么区别， 其实动手试试就知道了。

　  (6)  展示结构使用 Map. 解析出结果后，必然要展示或做成报告，使用 Map & List 结合的复合结构通常是非常适宜的选择。 比如这一例，如果要展示所有 SQL 日志详情，可以做成

           {"tablename1": [{sqlobj11}, {sqlobj12}], ...,  "tablenameN": [{sqlobjN1}, {sqlobjN2}] } ，每个 sqlobj 结构为：

　　　　{"sql": "select xxx", "QueryTime": 0.5600, ...}

           要展示简要的报告，比如每个表的 SQL 统计，　可以做成

　　　　{"tablename1": {"sql11": 98, "sql12": 16}, ..., "tablenameN": {"sqlN1": 75, "sqlN2": 23} } 

　

　　Python 程序实现：     

import re

globalRegex = r'^s*(.*?)# (User@Host:.*?)# (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('-------------------------------------: 
')
    f_res.write('Bref results: 
')
    for (tablename, sqlstat) in resultMap.iteritems():
        f_res.write('tablename: ' + tablename + '
')
        sortedsqlstat = sorted(sqlstat.iteritems(), key=lambda d:d[1], reverse = True)
        for sortedsql in sortedsqlstat:
            f_res.write('sql = %s
counts: %d

' % (sortedsql[0], sortedsql[1]))
    f_res.write('-------------------------------------: 

')

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

')
    f_res.write('-------------------------------------: 
')
    f_res.close()

   可配置

   事实上，可以做成可配置的。只要给定行间及行内关键字集合，可以分割多行及行内字段，就可以分别提取相应的内容。

   这里有个基本函数 matchOneLine： 根据一个依序分割一行内容的关键字列表，匹配一行内容，得到每个关键字对应的内容。这个函数用于匹配行内内容。

   配置方式： 采用列表的列表。列表中的每个元素列表是可以分割和匹配单行内容的关键字列表。 每个关键字都用于分割单行的某个区域的内容。 为了提升解析性能，这里对关键字列表进行了预编译正则表达式，以便在解析字符串的时候不做重复工作。

   见如下代码：

#!/usr/bin/python
#_*_encoding:utf-8_*_

import re

# config line keywords to seperate lines.
ksconf = [['S'], ['# User@Host:','Id:'] , ['# Schema:', 'Last_errno:', 'Killed:'], ['# Query_time:','Lock_time:', 'Rows_sent:', 'Rows_examined:', 'Rows_affected:'], ['# Bytes_sent:'], ['SET timestamp=']]
files = ['slow_sqls.txt']

#ksconf = [['id:'], ['name:'], ['able:']]
#files = ['stu.txt']

globalConf = {'ksconf': ksconf, 'files': files}

def produceRegex(keywordlistInOneLine):
    ''' build the regex to match keywords in the list of keywordlistInOneLine '''
    oneLineRegex = "^s*"
    oneLineRegex += "(.*?)".join(keywordlistInOneLine)
    oneLineRegex += "(.*?)s*$"
    return oneLineRegex

def readFile(filename):
    f = open(filename)
    ftext = ''
    for line in f:
        ftext += line
    f.close()
    return ftext

def readAllFiles(files):
    return ''.join(map(readFile, files))

def findInText(regex, text, linesConf):
    '''
       return a list of maps, each map is a match to multilines,
              in a map, key is the line keyword
                         and value is the content corresponding to the key
    '''
    matched = regex.findall(text)
    if empty(matched):
        return []

    allMatched = []
    linePatternMap = buildLinePatternMap(linesConf)
    for onematch in matched:
        oneMatchedMap = buildOneMatchMap(linesConf, onematch, linePatternMap)
        allMatched.append(oneMatchedMap)
    return allMatched

def buildOneMatchMap(linesConf, onematch, linePatternMap):
    sepLines = map(lambda ks:ks[0], linesConf)
    lenOflinesInOneMatch = len(sepLines)
    lineMatchedMap = {}
    for i in range(lenOflinesInOneMatch):
        lineContent = sepLines[i] + onematch[i].strip()
        linekey = getLineKey(linesConf[i])
        lineMatchedMap.update(matchOneLine(linesConf[i], lineContent, linePatternMap))
    
    return lineMatchedMap    

def matchOneLine(keywordlistOneLine, lineContent, patternMap):
    '''
       match lineContent with a list of keywords , and return a map 
       in which key is the keyword and value is the content matched the key.
       eg. 
       keywordlistOneLine = ["host:", "ip:"] , lineContent = "host: qinhost ip: 1.1.1.1"
       return {"host:": "qinhost", "ip": "1.1.1.1"}
    '''
    
    ksmatchedResult = {}
    if len(keywordlistOneLine) == 0 or lineContent.strip() == "":
        return {}
    linekey = getLineKey(keywordlistOneLine)
    
    if empty(patternMap):
        linePattern = getLinePattern(keywordlistOneLine)
    else:
        linePattern = patternMap.get(linekey)
    
    lineMatched = linePattern.findall(lineContent)
    if empty(lineMatched):
        return {}
    kslen = len(keywordlistOneLine)
    if kslen == 1:
        ksmatchedResult[cleankey(keywordlistOneLine[0])] = lineMatched[0].strip()
    else:
        for i in range(kslen):                            
            ksmatchedResult[cleankey(keywordlistOneLine[i])] = lineMatched[0][i].strip()
    
    return ksmatchedResult

def empty(obj):
    return obj is None or len(obj) == 0

def cleankey(dirtykey):
    ''' clean unused characters in key '''
    return re.sub(r"[# :]", "", dirtykey)

def printMatched(allMatched, linesConf):
    allks = []
    for kslist in linesConf:
        allks.extend(kslist)
    for matched in allMatched:
        for k in allks:
            print cleankey(k) , "=>", matched.get(cleankey(k))
        print '
'    

def buildLinePatternMap(linesConf):
    linePatternMap = {}
    for keywordlistOneLine in linesConf:
        linekey = getLineKey(keywordlistOneLine)
        linePatternMap[linekey] = getLinePattern(keywordlistOneLine)
    return linePatternMap    

def getLineKey(keywordlistForOneLine):
    return "_".join(keywordlistForOneLine)

def getLinePattern(keywordlistForOneLine):
    return re.compile(produceRegex(keywordlistForOneLine))

def testMatchOneLine():
    assert len(matchOneLine([], "haha", {})) == 0
    assert len(matchOneLine(["host"], "", {})) == 0
    assert len(matchOneLine("", "haha", {})) == 0 
    assert len(matchOneLine(["host", "ip"], "host:qqq addr: 1.1.1.1", {})) == 0

    lineMatchMap1 = matchOneLine(["id:"], "id: 123456", {"id:": re.compile(produceRegex(["id:"]))})
    assert lineMatchMap1.get("id") == "123456"

    lineMatchMap2 = matchOneLine(["host:", "ip:"], "host: qinhost  ip: 1.1.1.1  ", {"host:_ip:": re.compile(produceRegex(["host:", "ip:"]))})
    assert lineMatchMap2.get("host") == "qinhost"
    assert lineMatchMap2.get("ip") == "1.1.1.1"
    print 'testMatchOneLine passed.'


if __name__ == '__main__':

    testMatchOneLine()

    files = globalConf['files']
    linesConf = globalConf['ksconf']
    sepLines = map(lambda ks:ks[0], linesConf)

    text = readAllFiles(files)
    wholeRegex = produceRegex(sepLines)
    print 'wholeRegex: ', wholeRegex

    compiledPattern = re.compile(wholeRegex, flags=re.DOTALL+re.MULTILINE)
    allMatched = findInText(compiledPattern, text, linesConf)
    printMatched(allMatched, linesConf)

     如果想以下多行解析文本文件，只需要修改下 ksconf =  [['id:'], ['name:'], ['able:']]。

id:1
name:shu
able:swim,study

id:2
name:qin
able:sleep,run