soumya-ghosh commented on code in PR #1241:
URL: https://github.com/apache/iceberg-python/pull/1241#discussion_r1819502718
##########
tests/integration/test_inspect_table.py:
##########
@@ -846,3 +846,95 @@ def inspect_files_asserts(df: pa.Table) -> None:
inspect_files_asserts(files_df)
inspect_files_asserts(data_files_df)
inspect_files_asserts(delete_files_df)
+
+
[email protected]
[email protected]("format_version", [1, 2])
+def test_inspect_all_manifests(spark: SparkSession, session_catalog: Catalog,
format_version: int) -> None:
+ identifier = "default.table_metadata_all_manifests"
+ try:
+ session_catalog.drop_table(identifier=identifier)
+ except NoSuchTableError:
+ pass
+
+ spark.sql(
+ f"""
+ CREATE TABLE {identifier} (
+ id int,
+ data string
+ )
+ PARTITIONED BY (data)
+ TBLPROPERTIES ('write.update.mode'='merge-on-read',
+ 'write.delete.mode'='merge-on-read')
+ """
+ )
+ tbl = session_catalog.load_table(identifier)
+
+ # check all_manifests when there are no snapshots
+ lhs = tbl.inspect.all_manifests().to_pandas()
+ rhs = spark.table(f"{identifier}.all_manifests").toPandas()
+ assert lhs.empty
+ assert rhs.empty
+
+ spark.sql(f"INSERT INTO {identifier} VALUES (1, 'a')")
+
+ spark.sql(f"INSERT INTO {identifier} VALUES (2, 'b')")
+
+ spark.sql(f"UPDATE {identifier} SET data = 'c' WHERE id = 1")
+
+ spark.sql(f"DELETE FROM {identifier} WHERE id = 2")
+
+ spark.sql(f"INSERT OVERWRITE {identifier} VALUES (1, 'a')")
+
+ df = tbl.inspect.all_manifests()
+
+ assert df.column_names == [
+ "content",
+ "path",
+ "length",
+ "partition_spec_id",
+ "added_snapshot_id",
+ "added_data_files_count",
+ "existing_data_files_count",
+ "deleted_data_files_count",
+ "added_delete_files_count",
+ "existing_delete_files_count",
+ "deleted_delete_files_count",
+ "partition_summaries",
+ "reference_snapshot_id",
+ ]
+
+ int_cols = [
+ "content",
+ "length",
+ "partition_spec_id",
+ "added_snapshot_id",
+ "added_data_files_count",
+ "existing_data_files_count",
+ "deleted_data_files_count",
+ "added_delete_files_count",
+ "existing_delete_files_count",
+ "deleted_delete_files_count",
+ "reference_snapshot_id",
+ ]
+
+ for column in int_cols:
+ for value in df[column]:
+ assert isinstance(value.as_py(), int)
+
+ for value in df["path"]:
+ assert isinstance(value.as_py(), str)
+
+ for value in df["partition_summaries"]:
+ assert isinstance(value.as_py(), list)
+ for row in value:
+ assert isinstance(row["contains_null"].as_py(), bool)
+ assert isinstance(row["contains_nan"].as_py(), (bool, type(None)))
+ assert isinstance(row["lower_bound"].as_py(), (str, type(None)))
+ assert isinstance(row["upper_bound"].as_py(), (str, type(None)))
+
+ lhs = spark.table(f"{identifier}.all_manifests").toPandas()
+ rhs = df.to_pandas()
+ for column in df.column_names:
+ for left, right in zip(lhs[column].to_list(), rhs[column].to_list()):
+ assert left == right, f"Difference in column {column}: {left} !=
{right}"
Review Comment:
Yes, making the change.
--
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]
