python - 集合中的索引中断

Question

我正在编写一个 python 脚本，它将如下文本文件作为输入:

0   A   (*) Begin
1   A
2   A
3   A
4   A
5   A   (*) End
0   B   (*) Begin
1   B
2   B
3   B
4   B
5   B
6   B   (*) End
0   B   (*) Begin
1   B
2   B   (*) End
0   B   (*) Begin
1   B
2   B
3   B
4   B   (*) End

现在我想接收这样的输出:

0   A   (*) Begin [0]
1   A
2   A
3   A
4   A
5   A   (*) End [0]
0   B   (*) Begin [0]
1   B
2   B
3   B
4   B
5   B
6   B   (*) End [0]
0   B   (*) Begin [1]
1   B
2   B   (*) End [1]
0   B   (*) Begin [2]
1   B
2   B
3   B
4   B   (*) End [2]

这将是翻译:

>>>A = [0,1,2,3,4,5]
>>>A
[0, 1, 2, 3, 4, 5]
>>>len(A)
6
>>>B = [(0,1,2,3,4,5,6), (0,1,2), (0,1,2,3,4)]
>>>B
[(0,1,2,3,4,5,6), (0,1,2), (0,1,2,3,4)]
>>>len(B[0])
7
>>>len(B[1])
3
>>>len(B[2])
5

我现在这样试过:

import sys, os
import os.path

txtdir = os.path.dirname(os.path.abspath(__file__))
path = os.path.join(txtdir, 'txt/')

textfile = "%sfile.txt" % (path)
with open(textfile,"r") as f:
    # read a LIST of rows into "data"
    data = f.readlines()

previous_col = ''
current_col = ''
for row in data:
    match_1 = "(*) Begin"
    match_2 = "(*) End"
    if (match_1 in row or match_2 in row):
        col = row.split()
        print col
        print len(col)

        if (col[3] == "End"):
            previous_col = col[1]
        elif (col[3] == "Begin"):
            current_col = col[1]

        i = 0
        if current_col:
            if (col[3] == "Begin" and current_col == previous_col):
                i += 1 # increment
                col[3] = "Begin [%s]" % (i)
            else:
                col[3] = "Begin [0]"

# and write everything back
with open(textfile, 'w') as f:
    f.writelines( data )

# close f file
f.close()

但是“file.txt”没有变化

你能给我一些建议吗？

非常感谢，

里卡多

Answer 1

除了 Paul Lo 指出的您根本没有更新 data 列表的明显问题外，我认为您使这些东西过于复杂，您只需使用 collections.Counter 即可完成此操作:

from collections import Counter

c = Counter()

with open('file.txt') as f, open('outfile.txt', 'w') as out:
    for line in f:
        # In `if` and `elif`, use the current value of the counter
        # for the second column, default is 0.   
        if '(*) Begin' in line:
            text = line.split(None, 2)[1]
            out.write('{}[{}]\n'.format(line.strip(), c[text]))
        elif '(*) End' in line:
            text = line.split(None, 2)[1]
            out.write('{}[{}]\n'.format(line.strip(), c[text]))
            # End found, so now increment the counter  
            c[text] += 1
        else:
            out.write(line)

另外，要就地修改同一个文件，我建议使用 fileinput 模块:

from collections import Counter
import fileinput

c = Counter()

for line in  fileinput.input('file1.txt', inplace=True):
    if '(*) Begin' in line:
        text = line.split(None, 2)[1]
        print '{}[{}]'.format(line.strip(), c[text])
    elif '(*) End' in line:
        text = line.split(None, 2)[1]
        print '{}[{}]'.format(line.strip(), c[text])
        # End found, so now increment the counter  
        c[text] += 1
    else:
        print line,

输出:

0   A   (*) Begin[0]
1   A
2   A
3   A
4   A
5   A   (*) End[0]
0   B   (*) Begin[0]
1   B
2   B
3   B
4   B
5   B
6   B   (*) End[0]
0   B   (*) Begin[1]
1   B
2   B   (*) End[1]
0   B   (*) Begin[2]
1   B
2   B
3   B
4   B   (*) End[2]