jurossiar commented on issue #992:
URL: https://github.com/apache/iceberg-python/issues/992#issuecomment-2269572366
> Here's what I ran based on the video, I cannot reproduce the issue using
0.7.0.
>
> In Jupyter,
>
> ```
> !pip install pyiceberg==0.7.0 --force -q
> ```
>
> With pyiceberg integration docker running, `docker compose -f
dev/docker-compose-integration.yml up -d`,
>
> ```
> from pyiceberg.catalog import load_catalog
> import pyarrow as pa
> from pyiceberg.schema import Schema
> from pyiceberg.types import NestedField, StringType
> from pyiceberg.expressions import EqualTo
>
>
> catalog = load_catalog(
> "demo",
> **{
> "type": "rest",
> "uri": "http://localhost:8181";,
> "s3.endpoint": "http://localhost:9000";,
> "s3.access-key-id": "admin",
> "s3.secret-access-key": "password",
> },
> )
>
> catalog.create_namespace_if_not_exists("default")
>
> schema = Schema(
> NestedField(field_id=1, name="table_id", field_type=StringType(),
required=True),
> NestedField(field_id=2, name="name", field_type=StringType(),
required=True),
> NestedField(field_id=3, name="dataset", field_type=StringType(),
required=True),
> NestedField(
> field_id=4, name="description", field_type=StringType(),
required=False
> ),
> identifier_field_ids=[1],
> )
>
> try:
> catalog.purge_table("default.some_table")
> except:
> pass
>
> table = catalog.create_table("default.some_table", schema=schema)
>
> schema = pa.schema([
> ("table_id", pa.string(), False),
> ("name", pa.string(), False),
> ("dataset", pa.string(), False),
> ("description", pa.string(), True)
> ])
>
> # Create data arrays
> data = [
> ['id_1', 'id_2', 'id_3', 'id_4'],
> ['name_1', 'name_2', 'name_3', 'name_4'],
> ['dataset_1', 'dataset_1', 'dataset_2', 'dataset_3'],
> ['desc_1', 'desc_2', 'desc_3', 'desc_4']
> ]
>
> # Create PyArrow Table
> table_data = pa.Table.from_arrays(data, schema=schema)
> table = catalog.load_table("default.some_table")
> table.append(table_data)
>
> from pyiceberg.expressions import BooleanExpression, And, EqualTo,
AlwaysTrue
>
> def build_row_filter(equality_key_value: dict) -> BooleanExpression:
> if not equality_key_value or len(equality_key_value) == 0:
> return AlwaysTrue
> else:
> expressions: list[BooleanExpression] = []
> for key in equality_key_value:
> expressions.append(EqualTo(key, equality_key_value[key]))
> if len(expressions) == 1:
> return expressions[0]
> else:
> return And(*expressions)
>
> requested_columns = ["*"]
> scan = table.scan(
> selected_fields=(requested_columns),
> row_filter=build_row_filter({
> "dataset": "dataset_1",
> })
> )
> scan.to_pandas()
> ```
This query doesn't fail. The issue happens when you have empty results and
not with any combination.
This is the query that fails:
```
requested_columns=['*']
scan = table.scan(
selected_fields = (requested_columns),
row_filter=build_row_filter({
"dataset": "dataset_2_xxxx",
})
)
scan.to_pandas()
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
