This is an automated email from the ASF dual-hosted git repository.
fokko pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new 510915b Remove sort-order constraint (#349)
510915b is described below
commit 510915b36325bb4788941d0a974bb8bc6177e627
Author: Fokko Driesprong <[email protected]>
AuthorDate: Thu Feb 1 20:39:04 2024 +0100
Remove sort-order constraint (#349)
---
pyiceberg/io/pyarrow.py | 5 ++++-
pyiceberg/table/__init__.py | 9 ---------
2 files changed, 4 insertions(+), 10 deletions(-)
diff --git a/pyiceberg/io/pyarrow.py b/pyiceberg/io/pyarrow.py
index 7a94ce4..9e05e2d 100644
--- a/pyiceberg/io/pyarrow.py
+++ b/pyiceberg/io/pyarrow.py
@@ -1735,7 +1735,10 @@ def write_file(table: Table, tasks: Iterator[WriteTask])
-> Iterator[DataFile]:
file_format=FileFormat.PARQUET,
partition=Record(),
file_size_in_bytes=len(fo),
- sort_order_id=task.sort_order_id,
+ # After this has been fixed:
+ # https://github.com/apache/iceberg-python/issues/271
+ # sort_order_id=task.sort_order_id,
+ sort_order_id=None,
# Just copy these from the table for now
spec_id=table.spec().spec_id,
equality_ids=None,
diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py
index 16ed9ed..e3975dc 100644
--- a/pyiceberg/table/__init__.py
+++ b/pyiceberg/table/__init__.py
@@ -943,9 +943,6 @@ class Table:
if len(self.spec().fields) > 0:
raise ValueError("Cannot write to partitioned tables")
- if len(self.sort_order().fields) > 0:
- raise ValueError("Cannot write to tables with a sort-order")
-
data_files = _dataframe_to_data_files(self, df=df)
merge = _MergingSnapshotProducer(operation=Operation.APPEND,
table=self)
for data_file in data_files:
@@ -976,9 +973,6 @@ class Table:
if len(self.spec().fields) > 0:
raise ValueError("Cannot write to partitioned tables")
- if len(self.sort_order().fields) > 0:
- raise ValueError("Cannot write to tables with a sort-order")
-
data_files = _dataframe_to_data_files(self, df=df)
merge = _MergingSnapshotProducer(
operation=Operation.OVERWRITE if self.current_snapshot() is not
None else Operation.APPEND,
@@ -2279,9 +2273,6 @@ def _dataframe_to_data_files(table: Table, df: pa.Table)
-> Iterable[DataFile]:
if len(table.spec().fields) > 0:
raise ValueError("Cannot write to partitioned tables")
- if len(table.sort_order().fields) > 0:
- raise ValueError("Cannot write to tables with a sort-order")
-
write_uuid = uuid.uuid4()
counter = itertools.count(0)
