这样的文本怎么处理

noshell

aksdopk 11 111110,111111,111113,111115,11111,111113,111115,111117,112310 1,2,3,4,5,6,7,9

文本是这样的的格式，要处理成后面2个拆分开。


aksdopk 11 111110 1
aksdopk 11 111111 2
aksdopk 11 111113 3
aksdopk 11 111115 4
aksdopk 11 11111  5
aksdopk 11 111113 6
aksdopk 11 111115 7
aksdopk 11 111117 8
aksdopk 11 112310 9

jason680

回复 1# noshell

$ awk '{t=split($3,a,",");split($4,b,",");for(n=1;n<=t;n++)print $1,$2,a[n],b[n]}' FILE
aksdopk 11 111110 1
aksdopk 11 111111 2
aksdopk 11 111113 3
aksdopk 11 111115 4
aksdopk 11 11111 5
aksdopk 11 111113 6
aksdopk 11 111115 7
aksdopk 11 111117 9
aksdopk 11 112310

   

关阴月飞

回复 1# noshell

1. awk '{split($3,a,",");for(i=0;i++<split($4,b,",");)print $1,$2,a[i],b[i]}'  urfile

复制代码

noshell

你是大师，每次看你回帖都是艺术。值得欣赏回复 2# jason680


   

noshell

大神。NB回复 3# 关阴月飞


   

ly5066113

回复 1# noshell


try:

1. sed -r 's/(.+ )([^,]+),(.+ )([^,]*),?/\1\2 \4\n\1\3/;P;D' file

复制代码

jcdiy0601

1. #!/usr/bin/env python
   
2. 
   
3. file = open('test','r')
   
4. line = file.read()
   
5. file.close()
   
6. line = line.strip('\n')
   
7. list_all = line.split(' ')
   
8. list_1 = list_all[2].split(',')
   
9. list_2 = list_all[3].split(',')
   
10. sum1 = len(list_1)
    
11. sum2 = len(list_2)
    
12. if sum1 > sum2:
    
13.         sum = sum1
    
14. else:
    
15.         sum = sum2
    
16. for i in range(sum):
    
17.         print "%s %s %s %s" % (list_all[0],list_all[1],list_1[i],list_2[i])

复制代码

reyleon

来一发python

1. #!/usr/bin/python
   
2. # -*- coding: utf-8 -*-
   
3. 
   
4. import sys, fileinput
   
5. for line in fileinput.input(sys.argv[1]):
   
6.     fd = line.split()
   
7.     fv = fd[-2].split(",")
   
8.     fn = fd[-1].split(",")
   
9.     try:
   
10.         for i in range(len(fv)):
    
11.             print fd[0],fd[1],fv[i],fn[i]
    
12.     except IndexError:
    
13.         pass

复制代码

1. [root@localhost ~]# python r.py <(echo aksdopk 11 111110,111111,111113,111115,11111,111113,111115,111117,112310 1,2,3,4,5,6,7,9)
   
2. aksdopk 11 111110 1
   
3. aksdopk 11 111111 2
   
4. aksdopk 11 111113 3
   
5. aksdopk 11 111115 4
   
6. aksdopk 11 11111 5
   
7. aksdopk 11 111113 6
   
8. aksdopk 11 111115 7
   
9. aksdopk 11 111117 9
   
10. aksdopk 11 112310
    
11. [root@localhost ~]#

复制代码

yestreenstars

1. $ echo 'aksdopk 11 111110,111111,111113,111115,11111,111113,111115,111117,112310 1,2,3,4,5,6,7,8,9' | awk '{n=split($3,a,",");split($4,b,",");for(i=0;i++<n;)print $1,$2,a[i],b[i]}'
   
2. aksdopk 11 111110 1
   
3. aksdopk 11 111111 2
   
4. aksdopk 11 111113 3
   
5. aksdopk 11 111115 4
   
6. aksdopk 11 11111 5
   
7. aksdopk 11 111113 6
   
8. aksdopk 11 111115 7
   
9. aksdopk 11 111117 8
   
10. aksdopk 11 112310 9

复制代码

noshell

NB，学习了！
for i in range(len(fn)):也可以的
回复 8# reyleon