在两个文件夹中打印不同文件时出现问题

Question

import os

def compare_files(file1, file2):
    # Function to compare files
    pass

def compare_folders(folder1, folder2):
    differences_found = False
    
    # Compare files in folder1
    for root, dirs, files in os.walk(folder1):
        for file in files:
            file1 = os.path.join(root, file)
            file2 = os.path.join(root.replace(folder1, folder2, 1), file)
            if not os.path.exists(file2):
                print(f"File {file} exists in {folder1} but not in {folder2}")
                differences_found = True
            elif os.path.isfile(file2):
                # If the file exists in both folders, compare them
                compare_files(file1, file2)
    
    # Compare files in folder2
    for root, dirs, files in os.walk(folder2):
        for file in files:
            file1 = os.path.join(root.replace(folder2, folder1, 1), file)
            file2 = os.path.join(root, file)
            if not os.path.exists(file1):
                print(f"File {file} exists in {folder2} but not in {folder1}")
                differences_found = True

    if not differences_found:
        print("No differences found between the files in the two folders.")

if __name__ == "__main__":
    folder1 = input("Enter path to the first folder: ")
    folder2 = input("Enter path to the second folder: ")
    
    compare_folders(folder1, folder2)

我想比较两个文件夹里的文件，找出它们之间不同的内容。同时也想列出在两个文件夹中不同的文件名。

Answer 1

这段代码有几个问题：

1. compare_files 现在并没有进行任何比较。它应该先比较两个输入文件的大小，然后再检查内容是否相同。根据文件是否相等，它应该返回 True 或 False，这个返回值应该用来设置 differences_found。
2. 如果你发现两个文件之间有差异，或者某个文件在一个目录中存在但在另一个目录中不存在，你输出的消息并没有显示文件的完整路径；你只是在输出根文件夹的名字。
3. 你写的是：

def compare_folders(folder1, folder2):
    differences_found = False
    
    # Compare files in folder1
    for root, dirs, files in os.walk(folder1):
        for file in files:
            file1 = os.path.join(root, file)
            file2 = os.path.join(root.replace(folder1, folder2, 1), file)
            if not os.path.exists(file2):
                print(f"File {file} exists in {folder1} but not in {folder2}")
                differences_found = True
            elif os.path.isfile(file2):
                # If the file exists in both folders, compare them
                compare_files(file1, file2)
...

我认为应该是：

def compare_folders(folder1, folder2):
    differences_found = False

    # Compare files in folder1
    for root1, dirs, files in os.walk(folder1):
        for file in files:
            file1 = os.path.join(root1, file)
            root2 = root1.replace(folder1, folder2, 1)
            file2 = os.path.join(root2, file)
            if not os.path.isfile(file2):
                print(f"File {file} exists in {root1} but not in {root2}")
                differences_found = True
            else:
                # If the file exists in both folders, compare them
                if not compare_files(file1, file2):
                    print(f"Files {file} differ in {root1} and {root2}")
                    differences_found = True
...

这样不仅可以从最初的文件夹开始打印出文件的完整路径，还修正了一个小错误：假设我们有文件夹 folder1/a/b/test，但 folder2/a/b/test 存在，但它是一个目录而不是文件。你现在的代码不会显示文件 test 在一个目录中存在而在另一个目录中不存在，也不会设置 differences_found 标志。

我在下面的完整代码中提供了 compare_files 的实现：

import os
import mmap

def compare_files(file1: str, file2: str) -> bool:
    """Function to compare files."""

    with open(file1, 'rb') as f1, open(file2, 'rb') as f2:
        size1 = f1.seek(0, 2)
        size2 = f2.seek(0, 2)
        if size1 != size2:
            return False
        if size1 == 0:
            return True

        with mmap.mmap(f1.fileno(), 0, access=mmap.ACCESS_READ) as mm1, \
        mmap.mmap(f2.fileno(), 0, access=mmap.ACCESS_READ) as mm2:
            return mm1[0:] == mm2[0:]

def compare_folders(folder1: str, folder2: str) -> None:
    differences_found = False

    # Compare files in folder1
    for root1, dirs, files in os.walk(folder1):
        for file in files:
            file1 = os.path.join(root1, file)
            root2 = root1.replace(folder1, folder2, 1)
            file2 = os.path.join(root2, file)
            if not os.path.isfile(file2):
                print(f"File {file} exists in {root1} but not in {root2}")
                differences_found = True
            else:
                # If the file exists in both folders, compare them
                if not compare_files(file1, file2):
                    print(f"Files {file} differ in {root1} and {root2}")
                    differences_found = True

    # Compare files in folder2
    for root2, dirs, files in os.walk(folder2):
        for file in files:
            root1 = root2.replace(folder2, folder1, 1)
            file1 = os.path.join(root1, file)
            file2 = os.path.join(root2, file)
            if not os.path.isfile(file1):
                print(f"File {file} exists in {root2} but not in {root1}")
                differences_found = True

    if not differences_found:
        print("No differences found between the files in the two folders.")

if __name__ == "__main__":
    folder1 = input("Enter path to the first folder: ")
    folder2 = input("Enter path to the second folder: ")

    compare_folders(folder1, folder2)

上面的代码对我来说是有效的，所以如果你仍然遇到困难，你需要明确展示出最小的目录结构，这些结构没有产生你期望的结果，同时说明你期望的结果是什么，以及你实际显示的内容。