Rename file without overwriting existing files

Mon Jan 30 05:55:45 EST 2017

Peter Otten writes:
> Steve D'Aprano wrote:
>>> On 2017年1月30日 03:33 pm, Cameron Simpson wrote:
>>>>> On 30Jan2017 13:49, Steve D'Aprano <steve+python at pearwood.info> wrote:
>>>>This code contains a Time Of Check to Time Of Use bug:
>>>>>>>> if os.path.exists(destination)
>>>> raise ValueError('destination already exists')
>>>> os.rename(oldname, destination)
>>>>>>>>>>>>In the microsecond between checking for the existence of the destination
>>>>and actually doing the rename, it is possible that another process may
>>>>create the destination, resulting in data loss.
>>>>>>>>Apart from keeping my fingers crossed, how should I fix this TOCTOU bug?
>>>>>> For files this is a problem at the Python level. At the UNIX level you
>>> can play neat games with open(2) and the various O_* modes.
>>>>>> however, with directories things are more cut and dry. Do you have much
>>> freedom here? What's the wider context of the question?
>>>> The wider context is that I'm taking from 1 to <arbitrarily huge number>
>> path names to existing files as arguments, and for each path name I
>> transfer the file name part (but not the directory part) and then rename
>> the file. For example:
>>>> foo/bar/baz/spam.txt
>>>> may be renamed to:
>>>> foo/bar/baz/ham.txt
>>>> but only provided ham.txt doesn't already exist.
>> Google finds
>> http://stackoverflow.com/questions/3222341/how-to-rename-without-race-conditions
>> and from a quick test it appears to work on Linux:

It doesn't seem to be documented. I looked at help(os.link) on Python
3.4 and the corresponding current library documentation on the web. I
saw no mention of what happens when dst exists already.
Also, creating a hard link doesn't seem to work between different file
systems, which may well be relevant to Steve's case. I get:
 OSError: [Errno 18] Invalid cross-device link: [snip]
And that also is not mentioned in the docs.