Gowthami03B commented on code in PR #614:
URL: https://github.com/apache/iceberg-python/pull/614#discussion_r1657080281
##########
tests/integration/test_inspect_table.py:
##########
@@ -445,3 +445,109 @@ def check_pyiceberg_df_equals_spark_df(df: pa.Table,
spark_df: DataFrame) -> Non
df = tbl.inspect.partitions(snapshot_id=snapshot.snapshot_id)
spark_df = spark.sql(f"SELECT * FROM {identifier}.partitions VERSION
AS OF {snapshot.snapshot_id}")
check_pyiceberg_df_equals_spark_df(df, spark_df)
+
+
[email protected]
[email protected]("format_version", [1, 2])
+def test_inspect_files(
+ spark: SparkSession, session_catalog: Catalog, arrow_table_with_null:
pa.Table, format_version: int
+) -> None:
+ identifier = "default.table_metadata_files"
+
+ tbl = _create_table(session_catalog, identifier,
properties={"format-version": format_version})
+
+ tbl.overwrite(arrow_table_with_null)
+
+ # append more data
+ tbl.append(arrow_table_with_null)
+
+ df = tbl.refresh().inspect.files()
+
Review Comment:
Did this to only a subset of fields as the map type fields and readable
metrics need special processing.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
