Skip to content

ARROW-241: Checking list-types in schema support raises an error #223

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Jun 28, 2024
Merged

ARROW-241: Checking list-types in schema support raises an error #223

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b537bf6
list support in schema
lazargugleta Jun 26, 2024
3d90ed0
add test for python list
lazargugleta Jun 26, 2024
3bd24f0
raise if multiple elements in list without a struct + add test for th…
lazargugleta Jun 27, 2024
b320fb0
add empty list case and merge them
lazargugleta Jun 27, 2024
5489ff1
reformat message
lazargugleta Jun 27, 2024
892053a
remove empty list raises
lazargugleta Jun 27, 2024
d8fd09e
add empty list test + reformat code
lazargugleta Jun 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion bindings/python/pymongoarrow/types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,10 @@ def _normalize_typeid(typeid, field_name):
fields.append((sub_field_name, _normalize_typeid(sub_typeid, sub_field_name)))
return struct(fields)
if isinstance(typeid, list):
return list_(_normalize_typeid(type(typeid[0]), "0"))
if len(typeid) != 1:
msg = f"list field in schema must contain exactly one element, not {len(typeid)}"
raise ValueError(msg)
return list_(_normalize_typeid(typeid[0], "0"))
if _is_typeid_supported(typeid):
normalizer = _TYPE_NORMALIZER_FACTORY[typeid]
return normalizer(typeid)
Expand Down
20 changes: 20 additions & 0 deletions bindings/python/test/test_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
from datetime import datetime
from unittest import TestCase

import pytest
from bson import Binary, Code, Decimal128, Int64, ObjectId
from pyarrow import Table, field, float64, int64, list_, struct, timestamp
from pyarrow import schema as ArrowSchema
Expand Down Expand Up @@ -94,3 +95,22 @@ def test_list_of_list_projection(self):
}
)
self.assertEqual(schema._get_projection(), {"_id": True, "list": {"a": True, "b": True}})

def test_py_list_projection(self):
schema = Schema(
{"_id": ObjectId, "list": [(struct([field("a", int64()), field("b", float64())]))]}
)

self.assertEqual(schema._get_projection(), {"_id": True, "list": {"a": True, "b": True}})

def test_py_list_with_multiple_fields_raises(self):
with pytest.raises(
ValueError, match="list field in schema must contain exactly one element, not 2"
):
_ = Schema({"_id": ObjectId, "list": [([field("a", int64()), field("b", float64())])]})

def test_py_empty_list_raises(self):
with pytest.raises(
ValueError, match="list field in schema must contain exactly one element, not 0"
):
_ = Schema({"_id": ObjectId, "list": []})
Loading