Find broken symlinks with Python

Question

If I call os.stat() on a broken symlink, python throws an OSError exception. This makes it useful for finding them. However, there are

Answer 1

I had a similar problem: how to catch broken symlinks, even when they occur in some parent dir? I also wanted to log all of them (in an application dealing with a fairly large number of files), but without too many repeats.

Here is what I came up with, including unit tests.

fileutil.py:

import os
from functools import lru_cache
import logging

logger = logging.getLogger(__name__)

@lru_cache(maxsize=2000)
def check_broken_link(filename):
    """
    Check for broken symlinks, either at the file level, or in the
    hierarchy of parent dirs.
    If it finds a broken link, an ERROR message is logged.
    The function is cached, so that the same error messages are not repeated.

    Args:
        filename: file to check

    Returns:
        True if the file (or one of its parents) is a broken symlink.
        False otherwise (i.e. either it exists or not, but no element
        on its path is a broken link).

    """
    if os.path.isfile(filename) or os.path.isdir(filename):
        return False
    if os.path.islink(filename):
        # there is a symlink, but it is dead (pointing nowhere)
        link = os.readlink(filename)
        logger.error('broken symlink: {} -> {}'.format(filename, link))
        return True
    # ok, we have either:
    #   1. a filename that simply doesn't exist (but the containing dir
           does exist), or
    #   2. a broken link in some parent dir
    parent = os.path.dirname(filename)
    if parent == filename:
        # reached root
        return False
    return check_broken_link(parent)

Unit tests:

import logging
import shutil
import tempfile
import os

import unittest
from ..util import fileutil


class TestFile(unittest.TestCase):

    def _mkdir(self, path, create=True):
        d = os.path.join(self.test_dir, path)
        if create:
            os.makedirs(d, exist_ok=True)
        return d

    def _mkfile(self, path, create=True):
        f = os.path.join(self.test_dir, path)
        if create:
            d = os.path.dirname(f)
            os.makedirs(d, exist_ok=True)
            with open(f, mode='w') as fp:
                fp.write('hello')
        return f

    def _mklink(self, target, path):
        f = os.path.join(self.test_dir, path)
        d = os.path.dirname(f)
        os.makedirs(d, exist_ok=True)
        os.symlink(target, f)
        return f

    def setUp(self):
        # reset the lru_cache of check_broken_link
        fileutil.check_broken_link.cache_clear()

        # create a temporary directory for our tests
        self.test_dir = tempfile.mkdtemp()

        # create a small tree of dirs, files, and symlinks
        self._mkfile('a/b/c/foo.txt')
        self._mklink('b', 'a/x')
        self._mklink('b/c/foo.txt', 'a/f')
        self._mklink('../..', 'a/b/c/y')
        self._mklink('not_exist.txt', 'a/b/c/bad_link.txt')
        bad_path = self._mkfile('a/XXX/c/foo.txt', create=False)
        self._mklink(bad_path, 'a/b/c/bad_path.txt')
        self._mklink('not_a_dir', 'a/bad_dir')

    def tearDown(self):
        # Remove the directory after the test
        shutil.rmtree(self.test_dir)

    def catch_check_broken_link(self, expected_errors, expected_result, path):
        filename = self._mkfile(path, create=False)
        with self.assertLogs(level='ERROR') as cm:
            result = fileutil.check_broken_link(filename)
            logging.critical('nothing')  # trick: emit one extra message, so the with assertLogs block doesn't fail
        error_logs = [r for r in cm.records if r.levelname is 'ERROR']
        actual_errors = len(error_logs)
        self.assertEqual(expected_result, result, msg=path)
        self.assertEqual(expected_errors, actual_errors, msg=path)

    def test_check_broken_link_exists(self):
        self.catch_check_broken_link(0, False, 'a/b/c/foo.txt')
        self.catch_check_broken_link(0, False, 'a/x/c/foo.txt')
        self.catch_check_broken_link(0, False, 'a/f')
        self.catch_check_broken_link(0, False, 'a/b/c/y/b/c/y/b/c/foo.txt')

    def test_check_broken_link_notfound(self):
        self.catch_check_broken_link(0, False, 'a/b/c/not_found.txt')

    def test_check_broken_link_badlink(self):
        self.catch_check_broken_link(1, True, 'a/b/c/bad_link.txt')
        self.catch_check_broken_link(0, True, 'a/b/c/bad_link.txt')

    def test_check_broken_link_badpath(self):
        self.catch_check_broken_link(1, True, 'a/b/c/bad_path.txt')
        self.catch_check_broken_link(0, True, 'a/b/c/bad_path.txt')

    def test_check_broken_link_badparent(self):
        self.catch_check_broken_link(1, True, 'a/bad_dir/c/foo.txt')
        self.catch_check_broken_link(0, True, 'a/bad_dir/c/foo.txt')
        # bad link, but shouldn't log a new error:
        self.catch_check_broken_link(0, True, 'a/bad_dir/c')
        # bad link, but shouldn't log a new error:
        self.catch_check_broken_link(0, True, 'a/bad_dir')

if __name__ == '__main__':
    unittest.main()