請(qǐng)問：怎么把a(bǔ).txt中相同的set或者setenv合并起來（相同值忽略），若path1中含有mnt的換成${mntpath}且生成一行獨(dú)立的行，結(jié)果輸出到b.txta.txt：set value1 /usrset value1 /sysset value1 /sysset value2 /asdset value2 /xyzset value2 /xyzsetenv path1 /usr/lib:/usr/abcsetenv path1 /usr/asdsetenv path2 /usrsetenv path2 $path2:/abcsetenv path2 $path2:/aaasetenv path1 $path1:/mnt/abc:/mnt/xyzsetenv path1 $path1:/mnt/ccc:/mnt/dddb.txt：set value1 "/usr:/sys"set value2 "/asd:/xyz"setenv path1 "/usr/lib:/usr/abc:/usr/asd"setenv path2 "/usr:/abc:/aaa"setenv path1 "${path1}:/${mntpath}/abc:/${mntpath}/xyz:/${mntpath}/ccc:/${mntpath}/ddd"由于不知道怎么以code形式或以附件形式發(fā)布，所以只能這么貼了。
3 回答
函數(shù)式編程
TA貢獻(xiàn)1807條經(jīng)驗(yàn) 獲得超9個(gè)贊
#!/usr/bin/env python3# -*- coding: utf-8 -*- def zhidao_560604345(infile, outfile): reader = open(infile, 'r') set_dict = {} setenv_dict = {} while True: line = reader.readline() if len(line) == 0: break a, b, c = line.strip().split(maxsplit=2) if a == 'set': if not b in set_dict: set_dict[b] = set() set_dict[b].add(c.strip()) elif a == 'setenv': if not b in setenv_dict: setenv_dict[b] = set() setenv_dict[b].update(c.strip().split(':')) reader.close() buff = [] for k, v in set_dict.items(): buff.append('set %s "%s"' % (k, ':'.join(list(v)))) for k, v in setenv_dict.items(): tmp = [] for item in list(v): if item == '$' + k: pass elif item.startswith('/mnt/'): tmp.append('{mntpath}/' + item[5:]) else: tmp.append(item) tmp.sort() buff.append('setenv %s "%s"' % (k, ':'.join(tmp))) writer = open(outfile, 'w') writer.write('\n'.join(buff)) writer.close() if __name__ == '__main__': zhidao_560604345('zhidao_560604345.input', 'zhidao_560604345.output') |
運(yùn)行結(jié)果：
set value2 "/asd:/xyz"set value1 "/usr:/sys"setenv path2 "/aaa:/abc:/usr"setenv path1 "/usr/abc:/usr/asd:/usr/lib:{mntpath}/abc:{mntpath}/ccc:{mntpath}/ddd:{mntpath}/xyz" |
白衣染霜花
TA貢獻(xiàn)1796條經(jīng)驗(yàn) 獲得超10個(gè)贊
分隔日志文件存為小文件
#coding:utf-8
#file: FileSplit.py
import os,os.path,time
def FileSplit(sourceFile, targetFolder):
sFile = open(sourceFile, 'r')
number = 100000 #每個(gè)小文件中保存100000條數(shù)據(jù)
dataLine = sFile.readline()
tempData = [] #緩存列表
fileNum = 1
if not os.path.isdir(targetFolder): #如果目標(biāo)目錄不存在，則創(chuàng)建
os.mkdir(targetFolder)
while dataLine: #有數(shù)據(jù)
for row in range(number):
tempData.append(dataLine) #將一行數(shù)據(jù)添加到列表中
dataLine = sFile.readline()
if not dataLine :
break
tFilename = os.path.join(targetFolder,os.path.split(sourceFile)[1] + str(fileNum) + ".txt")
tFile = open(tFilename, 'a+') #創(chuàng)建小文件
tFile.writelines(tempData) #將列表保存到文件中
tFile.close()
tempData = [] #清空緩存列表
print(tFilename + " 創(chuàng)建于: " + str(time.ctime()))
fileNum += 1 #文件編號(hào)
sFile.close()
if __name__ == "__main__" :
FileSplit("access.log","access")
分類匯總小文件：
#coding:utf-8
#file: Map.py
import os,os.path,re
def Map(sourceFile, targetFolder):
sFile = open(sourceFile, 'r')
dataLine = sFile.readline()
tempData = {} #緩存列表
if not os.path.isdir(targetFolder): #如果目標(biāo)目錄不存在，則創(chuàng)建
os.mkdir(targetFolder)
while dataLine: #有數(shù)據(jù)
p_re = re.compile(r'(GET|POST)\s(.*?)\sHTTP/1.[01]',re.IGNORECASE) #用正則表達(dá)式解析數(shù)據(jù)
match = p_re.findall(dataLine)
if match:
visitUrl = match[0][1]
if visitUrl in tempData:
tempData[visitUrl] += 1
else:
tempData[visitUrl] = 1
dataLine = sFile.readline() #讀入下一行數(shù)據(jù)
sFile.close()
tList = []
for key,value in sorted(tempData.items(),key = lambda k:k[1],reverse = True):
tList.append(key + " " + str(value) + '\n')
tFilename = os.path.join(targetFolder,os.path.split(sourceFile)[1] + "_map.txt")
tFile = open(tFilename, 'a+') #創(chuàng)建小文件
tFile.writelines(tList) #將列表保存到文件中
tFile.close()
if __name__ == "__main__" :
Map("access\\access.log1.txt","access")
Map("access\\access.log2.txt","access")
Map("access\\access.log3.txt","access")
3. 再次將多個(gè)文件分類匯總為一個(gè)文件。
#coding:utf-8
#file: Reduce.py
import os,os.path,re
def Reduce(sourceFolder, targetFile):
tempData = {} #緩存列表
p_re = re.compile(r'(.*?)(\d{1,}$)',re.IGNORECASE) #用正則表達(dá)式解析數(shù)據(jù)
for root,dirs,files in os.walk(sourceFolder):
for fil in files:
if fil.endswith('_map.txt'): #是reduce文件
sFile = open(os.path.abspath(os.path.join(root,fil)), 'r')
dataLine = sFile.readline()
while dataLine: #有數(shù)據(jù)
subdata = p_re.findall(dataLine) #用空格分割數(shù)據(jù)
#print(subdata[0][0]," ",subdata[0][1])
if subdata[0][0] in tempData:
tempData[subdata[0][0]] += int(subdata[0][1])
else:
tempData[subdata[0][0]] = int(subdata[0][1])
dataLine = sFile.readline() #讀入下一行數(shù)據(jù)
sFile.close()
tList = []
for key,value in sorted(tempData.items(),key = lambda k:k[1],reverse = True):
tList.append(key + " " + str(value) + '\n')
tFilename = os.path.join(sourceFolder,targetFile + "_reduce.txt")
tFile = open(tFilename, 'a+') #創(chuàng)建小文件
tFile.writelines(tList) #將列表保存到文件中
tFile.close()
if __name__ == "__main__" :
Reduce("access","access")
添加回答
舉報(bào)
0/150
提交
取消