Fokko commented on code in PR #1285:
URL: https://github.com/apache/iceberg-python/pull/1285#discussion_r1916863476
##########
dev/provision.py:
##########
@@ -401,3 +401,27 @@
)
spark.sql(f"ALTER TABLE {catalog_name}.default.test_empty_scan_ordered_str
WRITE ORDERED BY id")
spark.sql(f"INSERT INTO {catalog_name}.default.test_empty_scan_ordered_str
VALUES 'a', 'c'")
+
+ spark.sql(
+ f"""
+ CREATE OR REPLACE TABLE
{catalog_name}.default.test_table_statistics_operations (
+ number integer
+ )
+ USING iceberg
+ TBLPROPERTIES (
+ 'format-version'='2'
+ );
+ """
+ )
+ spark.sql(
+ f"""
+ INSERT INTO {catalog_name}.default.test_table_statistics_operations
+ VALUES (1)
+ """
+ )
+ spark.sql(
+ f"""
+ INSERT INTO {catalog_name}.default.test_table_statistics_operations
+ VALUES (2)
+ """
+ )
Review Comment:
Why do this in Spark? It looks like there is nothing special going on here,
and we can also create the table in PyIceberg as part of the test (this makes
the tests self-contained).
##########
mkdocs/docs/api.md:
##########
@@ -1250,6 +1250,29 @@ with table.manage_snapshots() as ms:
ms.create_branch(snapshot_id1, "Branch_A").create_tag(snapshot_id2,
"tag789")
```
+## Table Statistics Management
+
+Manage table statistics with operations through the `Table` API:
+
+```python
+# To run a specific operation
+table.update_statistics().set_statistics(snapshot_id, statistics_file).commit()
Review Comment:
I like it how you did it in the pythondoc as well:
```suggestion
table.update_statistics().set_statistics(snapshot_id=1,
statistics_file=statistics_file).commit()
```
##########
pyiceberg/table/update/__init__.py:
##########
@@ -475,6 +489,28 @@ def _(
return base_metadata.model_copy(update={"default_sort_order_id":
new_sort_order_id})
+@_apply_table_update.register(SetStatisticsUpdate)
+def _(update: SetStatisticsUpdate, base_metadata: TableMetadata, context:
_TableMetadataUpdateContext) -> TableMetadata:
+ if update.snapshot_id != update.statistics.snapshot_id:
+ raise ValueError("Snapshot id in statistics does not match the
snapshot id in the update")
Review Comment:
It's a bit of an [awkward
check](https://lists.apache.org/thread/6fnrp73wokfqlt5vormpjyjmtvl29ll1), but
something that we have to live with I guess.
##########
mkdocs/docs/api.md:
##########
@@ -1250,6 +1250,29 @@ with table.manage_snapshots() as ms:
ms.create_branch(snapshot_id1, "Branch_A").create_tag(snapshot_id2,
"tag789")
```
+## Table Statistics Management
+
+Manage table statistics with operations through the `Table` API:
+
+```python
+# To run a specific operation
+table.update_statistics().set_statistics(snapshot_id, statistics_file).commit()
+# To run multiple operations
+table.update_statistics()
+ .set_statistics(snapshot_id1, statistics_file1)
+ .remove_statistics(snapshot_id2)
+ .commit()
+# Operations are applied on commit.
+```
+
+You can also use context managers to make more changes:
+
+```python
+with table.update_statistics() as update:
+ update.set_statistics(snaphsot_id1, statistics_file)
+ update.remove_statistics(snapshot_id2)
Review Comment:
The other examples are in the four-spaces camp :)
```suggestion
update.set_statistics(snaphsot_id1, statistics_file)
update.remove_statistics(snapshot_id2)
```
##########
pyiceberg/table/statistics.py:
##########
@@ -0,0 +1,49 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from typing import (
+ Dict,
+ List,
+ Optional,
+)
+
+from pydantic import Field
+
+from pyiceberg.typedef import IcebergBaseModel
+
+
+class BlobMetadata(IcebergBaseModel):
+ type: str
Review Comment:
How about being explicit about the options:
```suggestion
type: Literal['apache-datasketches-theta-v1', 'deletion-vector-v1']
```
https://iceberg.apache.org/puffin-spec/#blobmetadata
--
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
