Bugfix for #15 for compressing large files

[lesthaeghet]

This is a potential quick fix for Issue #15 which occurs when attempting to compress files larger than ZIP64_LIMIT. zinfo.file_size is never initialized to the correct file size and thus the determination of whether zip64 is required is made based on the file size of 0. This later results in an exception being raised as though the file size increased during compression, since the file size is actually counted during compression and later saved over zinfo.file_size.

It is important to note that this fix may not be cross platform. Different versions of Python do different things on Windows with the st_size parameter in the os.stat call. So, that may be worth investigating further. However, in the short term, this will fix the problem on Linux, Mac, and some Windows platforms without making it worse where it still doesn't work.

I would leave it to the maintainers to make a broader decision on whether this fix is appropriate or if a better solution would be desired. I'm happy to help.

[lesthaeghet]

Alternatively, replacing st[6] with os.path.getsize(filename) is a cross-platform solution. I'm happy to make that change to the commit if you would prefer. I'm just not sure if there aren't any corner cases where non-existent files or anything like that are handled or expected to be handled. So, I'll defer to the judgment of the maintainers. Let me know if you'd like me to make any changes to my commit.

[rmeyers4]

This fix works if st[6] is replaced with os.path.getsize(filename), as shown above, and allowZip64=True is passed as an argument. I was able to download and decompress a 2.5GB file that was previously failing to unzip.