Skip to content

Inject columns of proper length for missing fields #1767

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
kevinjqliu merged 1 commit into from
Mar 5, 2025
Merged

Inject columns of proper length for missing fields #1767

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion pyiceberg/io/pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1438,7 +1438,8 @@ def _task_to_record_batches(
for name, value in projected_missing_fields.items():
index = result_batch.schema.get_field_index(name)
if index != -1:
result_batch = result_batch.set_column(index, name, [value])
arr = pa.repeat(value, result_batch.num_rows)
result_batch = result_batch.set_column(index, name, arr)

yield result_batch

Expand Down
17 changes: 8 additions & 9 deletions tests/io/test_pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1153,7 +1153,7 @@ def test_identity_transform_column_projection(tmp_path: str, catalog: InMemoryCa
properties={TableProperties.DEFAULT_NAME_MAPPING: create_mapping_from_schema(schema).model_dump_json()},
)

file_data = pa.array(["foo"], type=pa.string())
file_data = pa.array(["foo", "bar", "baz"], type=pa.string())
file_loc = f"{tmp_path}/test.parquet"
pq.write_table(pa.table([file_data], names=["other_field"]), file_loc)

Expand Down Expand Up @@ -1181,14 +1181,13 @@ def test_identity_transform_column_projection(tmp_path: str, catalog: InMemoryCa
with transaction.update_snapshot().overwrite() as update:
update.append_data_file(unpartitioned_file)

assert (
str(table.scan().to_arrow())
== """pyarrow.Table
other_field: large_string
partition_id: int64
----
other_field: [["foo"]]
partition_id: [[1]]"""
schema = pa.schema([("other_field", pa.large_string()), ("partition_id", pa.int64())])
assert table.scan().to_arrow() == pa.table(
{
"other_field": ["foo", "bar", "baz"],
"partition_id": [1, 1, 1],
},
schema=schema,
)


Expand Down