vastdb 1.3.11__tar.gz → 1.4.0__tar.gz

{vastdb-1.3.11 → vastdb-1.4.0}/CHANGELOG.md

@@ -4,7 +4,13 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
-## [1.3.11] (2025-007-10)
+## [1.4.0] (2025-07-28)
+[1.4.0]: https://github.com/vast-data/vastdb_sdk/compare/v1.3.11...v1.4.0
+
+### Added
+- Support for inserting rows by columns
+
+## [1.3.11] (2025-07-10)
 [1.3.11]: https://github.com/vast-data/vastdb_sdk/compare/v1.3.10...v1.3.11
 
 ### Added

{vastdb-1.3.11 → vastdb-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vastdb
-Version: 1.3.11
+Version: 1.4.0
 Summary: VAST Data SDK
 Home-page: https://github.com/vast-data/vastdb_sdk
 Author: VAST DATA

{vastdb-1.3.11 → vastdb-1.4.0}/setup.py

@@ -29,7 +29,7 @@ setup(
     name='vastdb',
     python_requires='>=3.9.0',
     description='VAST Data SDK',
-    version='1.3.11' + suffix,
+    version='1.4.0' + suffix,
     url='https://github.com/vast-data/vastdb_sdk',
     author='VAST DATA',
     author_email='hello@vastdata.com',

{vastdb-1.3.11 → vastdb-1.4.0}/vastdb/table.py

@@ -532,19 +532,24 @@ class Table:
             columns_name_chunk = columns_names[start:end]
             columns_chunks = columns[start:end]
             arrays_chunks = arrays[start:end]
-            columns_chunks.append(INTERNAL_ROW_ID_FIELD)
+            columns_chunks.append(INTERNAL_ROW_ID_SORTED_FIELD if self.sorted_table else INTERNAL_ROW_ID_FIELD)
             arrays_chunks.append(row_ids.to_pylist())
             column_record_batch = pa.RecordBatch.from_arrays(arrays_chunks, schema=pa.schema(columns_chunks))
             self.update(rows=column_record_batch, columns=columns_name_chunk)
         return row_ids
 
-    def insert(self, rows: Union[pa.RecordBatch, pa.Table]):
+    def insert(self, rows: Union[pa.RecordBatch, pa.Table], by_columns: bool = False):
         """Insert a RecordBatch into this table."""
         if self._imports_table:
             raise errors.NotSupportedCommand(self.bucket.name, self.schema.name, self.name)
         if 0 == rows.num_rows:
             log.debug("Ignoring empty insert into %s", self.name)
-            return pa.chunked_array([], type=INTERNAL_ROW_ID_FIELD.type)
+            return pa.chunked_array([], type=(INTERNAL_ROW_ID_SORTED_FIELD if self.sorted_table else INTERNAL_ROW_ID_FIELD).type)
+
+        if by_columns:
+            self.tx._rpc.features.check_return_row_ids()
+            return self.insert_in_column_batches(rows)
+
         try:
             row_ids = []
             serialized_slices = util.iter_serialized_slices(rows, MAX_INSERT_ROWS_PER_PATCH)
@@ -557,7 +562,7 @@ class Table:
                 self.tx._rpc.features.check_return_row_ids()
             except errors.NotSupportedVersion:
                 return  # type: ignore
-            return pa.chunked_array(row_ids, type=INTERNAL_ROW_ID_FIELD.type)
+            return pa.chunked_array(row_ids, type=(INTERNAL_ROW_ID_SORTED_FIELD if self.sorted_table else INTERNAL_ROW_ID_FIELD).type)
         except errors.TooWideRow:
             self.tx._rpc.features.check_return_row_ids()
             return self.insert_in_column_batches(rows)

{vastdb-1.3.11 → vastdb-1.4.0}/vastdb/tests/test_tables.py

@@ -15,10 +15,11 @@ import pytest
 from requests.exceptions import HTTPError
 
 from vastdb.errors import BadRequest
+from vastdb.session import Session
 
 from .. import errors
 from ..table import INTERNAL_ROW_ID, QueryConfig
-from .util import prepare_data
+from .util import assert_row_ids_ascending_on_first_insertion_to_table, prepare_data
 
 log = logging.getLogger(__name__)
 
@@ -1150,7 +1151,7 @@ def test_elysium_tx(elysium_session, clean_bucket_name):
         t = s.create_table(table_name, arrow_table.schema)
         row_ids_array = t.insert(arrow_table)
         row_ids = row_ids_array.to_pylist()
-        assert row_ids == list(range(arrow_table.num_rows))
+        assert_row_ids_ascending_on_first_insertion_to_table(row_ids, arrow_table.num_rows, t.sorted_table)
         sorted_columns = t.sorted_columns()
         assert len(sorted_columns) == 0
         t.add_sorting_key(sorting)
@@ -1186,7 +1187,7 @@ def test_elysium_double_enable(elysium_session, clean_bucket_name):
             t.add_sorting_key(sorting)
 
 
-def test_elysium_update_table_tx(elysium_session, clean_bucket_name):
+def test_elysium_update_table_tx(elysium_session: Session, clean_bucket_name):
     columns = pa.schema([
         ('a', pa.int64()),
         ('b', pa.float32()),
@@ -1205,7 +1206,7 @@ def test_elysium_update_table_tx(elysium_session, clean_bucket_name):
         t = s.create_table(table_name, arrow_table.schema, sorting_key=sorting)
         row_ids_array = t.insert(arrow_table)
         row_ids = row_ids_array.to_pylist()
-        assert row_ids == list(range(arrow_table.num_rows))
+        assert_row_ids_ascending_on_first_insertion_to_table(row_ids, arrow_table.num_rows, t.sorted_table)
         sorted_columns = t.sorted_columns()
         assert sorted_columns[0].name == 's'
         assert sorted_columns[1].name == 'b'
@@ -1278,7 +1279,7 @@ def test_elysium_splits(elysium_session, clean_bucket_name):
         t = s.create_table(table_name, arrow_table.schema, sorting_key=sorting)
         row_ids_array = t.insert(arrow_table)
         row_ids = row_ids_array.to_pylist()
-        assert row_ids == list(range(arrow_table.num_rows))
+        assert_row_ids_ascending_on_first_insertion_to_table(row_ids, arrow_table.num_rows, t.sorted_table)
         sorted_columns = t.sorted_columns()
         assert sorted_columns[0].name == 'a'
 

{vastdb-1.3.11 → vastdb-1.4.0}/vastdb/tests/util.py

@@ -3,17 +3,27 @@ from contextlib import contextmanager
 
 import pyarrow as pa
 
+from vastdb.session import Session
+
 log = logging.getLogger(__name__)
 
 
+def assert_row_ids_ascending_on_first_insertion_to_table(row_ids, expected_num_rows, sorted_table):
+    adjusted_row_ids = [
+        int(row_id) & 0xFFFFFFFFFFFFFF for row_id in row_ids
+        ] if sorted_table else row_ids
+
+    assert adjusted_row_ids == list(range(expected_num_rows))
+
+
 @contextmanager
-def prepare_data(session, clean_bucket_name, schema_name, table_name, arrow_table, sorting_key=[]):
+def prepare_data(session: Session, clean_bucket_name, schema_name, table_name, arrow_table, sorting_key=[]):
     with session.transaction() as tx:
         s = tx.bucket(clean_bucket_name).create_schema(schema_name)
         t = s.create_table(table_name, arrow_table.schema, sorting_key=sorting_key)
         row_ids_array = t.insert(arrow_table)
         row_ids = row_ids_array.to_pylist()
-        assert row_ids == list(range(arrow_table.num_rows))
+        assert_row_ids_ascending_on_first_insertion_to_table(row_ids, arrow_table.num_rows, t.sorted_table)
         yield t
         t.drop()
         s.drop()

{vastdb-1.3.11 → vastdb-1.4.0}/vastdb.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vastdb
-Version: 1.3.11
+Version: 1.4.0
 Summary: VAST Data SDK
 Home-page: https://github.com/vast-data/vastdb_sdk
 Author: VAST DATA