Created
July 29, 2020 08:40
-
-
Save rrei/9439ed7fa416dcf80bd3bb1693f2d13c to your computer and use it in GitHub Desktop.
Break a large Django queryset into an equivalent set of smaller querysets (caveats apply)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def chunked_queryset(queryset, chunk_size=10000): | |
"""Slice a queryset into chunks. This is useful to avoid memory issues when | |
iterating through large querysets. | |
Code adapted from https://djangosnippets.org/snippets/10599/ | |
""" | |
if not queryset.exists(): | |
return | |
queryset = queryset.order_by("pk") | |
pks = queryset.values_list("pk", flat=True) | |
start_pk = pks[0] | |
while True: | |
try: | |
end_pk = pks.filter(pk__gte=start_pk)[chunk_size] | |
except IndexError: | |
break | |
yield queryset.filter(pk__gte=start_pk, pk__lt=end_pk) | |
start_pk = end_pk | |
yield queryset.filter(pk__gte=start_pk) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment