You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by GitBox <gi...@apache.org> on 2021/04/01 15:30:07 UTC
[GitHub] [iceberg] szehon-ho commented on a change in pull request #2266: Implement python drop_table
szehon-ho commented on a change in pull request #2266:
URL: https://github.com/apache/iceberg/pull/2266#discussion_r605749944
##########
File path: python/tests/hive/test_hive_tables.py
##########
@@ -157,3 +154,84 @@ def test_create_tables(client, current_call, base_scan_schema, base_scan_partiti
current_call.return_value = tbl[0].args[0].parameters['metadata_location']
tables.load("test.test_123")
+
+
+@mock.patch("iceberg.hive.HiveTableOperations.refresh_from_metadata_location")
+@mock.patch("iceberg.hive.HiveTableOperations.current")
+@mock.patch("iceberg.hive.HiveTables.get_client")
+def test_drop_tables(client, metadata, refresh_call, tmpdir):
+
+ parameters = {"table_type": "ICEBERG",
+ "partition_spec": [],
+ "metadata_location": "s3://path/to/iceberg.metadata.json"}
+
+ client.return_value.__enter__.return_value.get_table.return_value = MockHMSTable(parameters)
+ conf = {"hive.metastore.uris": 'thrift://hms:port',
+ "hive.metastore.warehouse.dir": tmpdir}
+ tables = HiveTables(conf)
+ tables.drop("test", "test_123", purge=False)
+ client.return_value.__enter__.return_value.drop_table.assert_called_with("test", "test_123", deleteData=False)
+
+
+@mock.patch("iceberg.hive.HiveTableOperations.refresh_from_metadata_location")
+@mock.patch("iceberg.hive.HiveTables.new_table_ops")
+@mock.patch("iceberg.hive.HiveTables.get_client")
+def test_drop_tables_purge(client, current_ops, refresh_call, tmpdir):
+ mock_snapshots = [MockSnapshot(location="snap-a.avro",
+ manifests=[
+ MockManifest("a-manifest.avro"),
+ MockManifest("b-manifest.avro")],
+ manifest_to_entries={
+ "a-manifest.avro": MockReader(
+ [MockManifestEntry("a.parquet"),
+ MockManifestEntry("b.parquet")]),
+ "b-manifest.avro": MockReader(
+ [MockManifestEntry("c.parquet"),
+ MockManifestEntry("d.parquet")])
+ }),
+ MockSnapshot(location="snap-b.avro",
+ manifests=[
+ MockManifest("b-manifest.avro"),
+ MockManifest("c-manifest.avro"),
+ MockManifest("d-manifest.avro")],
+ manifest_to_entries={
+ "b-manifest.avro": MockReader(
+ [MockManifestEntry("c.parquet"),
+ MockManifestEntry("d.parquet")]),
+ "c-manifest.avro": MockReader(
+ [MockManifestEntry("e.parquet"),
+ MockManifestEntry("f.parquet")]),
+ "d-manifest.avro": MockReader(
+ [MockManifestEntry("g.parquet"),
+ MockManifestEntry("h.parquet")])
+ })
+ ]
+ ops = MockTableOperations(MockMetadata(mock_snapshots), "a.json")
+ current_ops.return_value = ops
+
+ parameters = {"table_type": "ICEBERG",
+ "partition_spec": [],
+ "metadata_location": "s3://path/to/iceberg.metadata.json"}
+ client.return_value.__enter__.return_value.get_table.return_value = MockHMSTable(parameters)
+
+ conf = {"hive.metastore.uris": 'thrift://hms:port',
+ "hive.metastore.warehouse.dir": tmpdir}
+ tables = HiveTables(conf)
+ tables.drop("test", "test_123", purge=True)
+
+ assert len(ops.deleted) == len(set(ops.deleted)), "Paths should only be deleted once"
Review comment:
Validation for files referred to multiple times by various snapshots
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org