Question

我试图在两个文件夹中比较所有文件对（具有相同文件名的文件）＆＃39; test1＆＃39;和＆＃39; test2＆＃39;并打印他们可能存在的任何差异。我在下面有这个代码部分工作正常。它获取具有相同文件名的文件，但仅比较第一个文件对而不是文件夹中的所有文件。我如何解决它？示例csv文件可能如下所示

import os
from collections import defaultdict
import csv

def relative_files(path):
    for root, dirnames, files in os.walk(path):
        relroot = os.path.relpath(root, path)
        for filename in files:
            yield os.path.join(relroot, filename)

def difference_in_files (root_one, root_two):
    files_one = set(relative_files(root_one))
    for same in files_one.intersection(relative_files(root_two)):
        try:
            with open(os.path.join(root_one, same)) as csvfile, open(os.path.join(root_two, same)) as csvfile2:
                d = defaultdict(list)
                d2 = defaultdict(list)
                header = next(csvfile).rstrip().split("\t")
                h1 = next((i for i, x in enumerate(header) if x == "h1"),None)
                h2 = next((i for i, x in enumerate(header) if x == "h2"),None)
                header2 = next(csvfile2).rstrip().split("\t")
                h12 = next((i for i, x in enumerate(header2) if x == "h1"),None)
                h22 = next((i for i, x in enumerate(header2) if x == "h2"),None)
                if h1 is not None and h2 is not None:
                    r = csv.reader(csvfile,delimiter="\t")
                    for row in r:
                        d[row[h1]].append(row[h2])
                if h12 is not None and h22 is not None:
                    r = csv.reader(csvfile2,delimiter="\t")
                    for row in r:
                        d2[row[h12]].append(row[h22])
            d2 = {k: list(set(v)) for k,v in dict(d2).items()}
            d = {k: list(set(v)) for k,v in dict(d).items()}

            diff = dict([ (key, d2.get(key, d.get(key))) for key in set(d.keys()+d2.keys()) if (key in d and (not key in d2 or d2[key] != d[key])) or (key in d2 and (not key in d or d[key] != d2[key])) ])
            diff2 = dict([ (key, d.get(key, d2.get(key))) for key in set(d2.keys()+d.keys()) if (key in d2 and (not key in d or d[key] != d2[key])) or (key in d and (not key in d2 or d2[key] != d[key])) ])
            return diff, diff2
        except TypeError:
            pass


if __name__ == '__main__':
    root_one = 'test1'
    root_two = 'test2'
    difference_in_files (root_one, root_two)

TEST1 / csv1.csv

h1,h2,h3
aa,90,io
bb,86,0n

test1.csv2.csv

h1,h8,h2
jj,kj,64
df,hj,12

TEST2 / csv1.csv

h1,h2,h3
aa,90,io
bb,66,0n

test2.csv2.csv

h1,h8,h2
jj,kj,64
df,hj,12
mm,h9,09

它只比较两个文件中的csv1而不是csv2。

Answer 1

所以只是为了正式回答。问题在于：

返回diff，diff2在for循环中。它将在结束时执行循环的第一次迭代。因此，没有其他迭代执行。

使用Python比较两个文件夹中的文件

1 个答案: