vastdb 0.0.5.2__tar.gz → 0.0.5.4__tar.gz

{vastdb-0.0.5.2 → vastdb-0.0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vastdb
-Version: 0.0.5.2
+Version: 0.0.5.4
 Summary: VAST Data SDK
 Home-page: https://github.com/vast-data/vastdb_sdk
 Author: VAST DATA

{vastdb-0.0.5.2 → vastdb-0.0.5.4}/setup.py

@@ -46,7 +46,7 @@ if os.environ.get('VASTDB_APPEND_VERSION_SUFFIX'):
 setup(
     name='vastdb',
     description='VAST Data SDK',
-    version='0.0.5.2' + suffix,
+    version='0.0.5.4' + suffix,
     url='https://github.com/vast-data/vastdb_sdk',
     author='VAST DATA',
     author_email='hello@vastdata.com',

{vastdb-0.0.5.2 → vastdb-0.0.5.4}/vastdb/api.py

@@ -757,6 +757,7 @@ class VastdbApi:
         if not port:
             port = 443 if secure else 80
 
+        self.default_max_list_columns_page_size = 1000
         self.session = requests.Session()
         self.session.verify = False
         self.session.headers['user-agent'] = "VastData Tabular API 1.0 - 2022 (c)"
@@ -1207,7 +1208,7 @@ class VastdbApi:
                                 data=serialized_schema, headers=headers)
         return self._check_res(res, "drop_columns", expected_retvals)
 
-    def list_columns(self, bucket, schema, table, *, txid=0, client_tags=None, max_keys=1000, next_key=0,
+    def list_columns(self, bucket, schema, table, *, txid=0, client_tags=None, max_keys=None, next_key=0,
                      count_only=False, name_prefix="", exact_match=False,
                      expected_retvals=None, bc_list_internals=False):
         """
@@ -1218,6 +1219,7 @@ class VastdbApi:
         tabular-max-keys: 1000
         tabular-next-key: NextColumnId
         """
+        max_keys = max_keys or self.default_max_list_columns_page_size
         client_tags = client_tags or []
         expected_retvals = expected_retvals or []
 
@@ -1294,7 +1296,7 @@ class VastdbApi:
         return self._check_res(res, "get_transaction", expected_retvals)
 
     def select_row_ids(self, bucket, schema, table, params, txid=0, client_tags=[], expected_retvals=[],
-                       retry_count=0, enable_sorted_projections=False):
+                       retry_count=0, enable_sorted_projections=True):
         """
         POST /mybucket/myschema/mytable?query-data=SelectRowIds HTTP/1.1
         """
@@ -1311,7 +1313,7 @@ class VastdbApi:
         return self._check_res(res, "query_data", expected_retvals)
 
     def read_columns_data(self, bucket, schema, table, params, txid=0, client_tags=[], expected_retvals=[], tenant_guid=None,
-                          retry_count=0, enable_sorted_projections=False):
+                          retry_count=0, enable_sorted_projections=True):
         """
         POST /mybucket/myschema/mytable?query-data=ReadColumns HTTP/1.1
         """
@@ -1327,7 +1329,7 @@ class VastdbApi:
         return self._check_res(res, "query_data", expected_retvals)
 
     def count_rows(self, bucket, schema, table, params, txid=0, client_tags=[], expected_retvals=[], tenant_guid=None,
-                   retry_count=0, enable_sorted_projections=False):
+                   retry_count=0, enable_sorted_projections=True):
         """
         POST /mybucket/myschema/mytable?query-data=CountRows HTTP/1.1
         """
@@ -1483,10 +1485,11 @@ class VastdbApi:
         return False
 
     def _query_page(self, bucket, schema, table, query_data_request, split=(0, 1, 8), num_sub_splits=1, response_row_id=False,
-                   txid=0, limit_rows=0, sub_split_start_row_ids=[], filters=None, field_names=None):
+                   txid=0, limit_rows=0, sub_split_start_row_ids=[], filters=None, field_names=None, enable_sorted_projections=True):
         res = self.query_data(bucket=bucket, schema=schema, table=table, params=query_data_request.serialized, split=split,
                               num_sub_splits=num_sub_splits, response_row_id=response_row_id, txid=txid,
-                              limit_rows=limit_rows, sub_split_start_row_ids=sub_split_start_row_ids)
+                              limit_rows=limit_rows, sub_split_start_row_ids=sub_split_start_row_ids,
+                              enable_sorted_projections=enable_sorted_projections)
         start_row_ids = {}
         sub_split_tables = parse_query_data_response(res.raw, query_data_request.response_schema,
                                                     start_row_ids=start_row_ids)
@@ -1497,10 +1500,11 @@ class VastdbApi:
         return table_page, start_row_ids
 
     def _query_page_iterator(self, bucket, schema, table, query_data_request, split=(0, 1, 8), num_sub_splits=1, response_row_id=False,
-                             txid=0, limit_rows=0, start_row_ids={}, filters=None, field_names=None):
+                             txid=0, limit_rows=0, start_row_ids={}, filters=None, field_names=None, enable_sorted_projections=True):
         res = self.query_data(bucket=bucket, schema=schema, table=table, params=query_data_request.serialized, split=split,
                               num_sub_splits=num_sub_splits, response_row_id=response_row_id, txid=txid,
-                              limit_rows=limit_rows, sub_split_start_row_ids=start_row_ids.items())
+                              limit_rows=limit_rows, sub_split_start_row_ids=start_row_ids.items(),
+                              enable_sorted_projections=enable_sorted_projections)
         for sub_split_table in parse_query_data_response(res.raw, query_data_request.response_schema,
                                                         start_row_ids=start_row_ids):
             for record_batch in sub_split_table.to_batches():
@@ -1508,7 +1512,8 @@ class VastdbApi:
         _logger.info(f"query_page_iterator: start_row_ids={start_row_ids}")
 
     def query_iterator(self, bucket, schema, table, num_sub_splits=1, num_row_groups_per_sub_split=8,
-                       response_row_id=False, txid=0, limit_per_sub_split=128*1024, filters=None, field_names=None):
+                       response_row_id=False, txid=0, limit_per_sub_split=128*1024, filters=None, field_names=None,
+                       enable_sorted_projections=True):
         """
         query rows into a table.
 
@@ -1586,7 +1591,8 @@ class VastdbApi:
                                                                          split=(split_id, num_splits, num_row_groups_per_sub_split),
                                                                          num_sub_splits=num_sub_splits, response_row_id=response_row_id,
                                                                          txid=txid, limit_rows=limit_per_sub_split,
-                                                                         start_row_ids=start_row_ids):
+                                                                         start_row_ids=start_row_ids,
+                                                                         enable_sorted_projections=enable_sorted_projections):
                             output_queue.put((split_id, record_batch))
                             while not next_sems[split_id].acquire(timeout=1): # wait for the main thread to request the next record batch
                                 if killall:
@@ -1680,7 +1686,7 @@ class VastdbApi:
 
     def query(self, bucket, schema, table, num_sub_splits=1, num_row_groups_per_sub_split=8,
               response_row_id=False, txid=0, limit=0, limit_per_sub_split=131072, filters=None, field_names=None,
-              queried_columns=None):
+              queried_columns=None, enable_sorted_projections=True):
         """
         query rows into a table.
 
@@ -1767,7 +1773,8 @@ class VastdbApi:
                                                                         split=(split_id, num_splits, num_row_groups_per_sub_split),
                                                                         num_sub_splits=num_sub_splits, response_row_id=response_row_id,
                                                                         txid=txid, limit_rows=limit_rows,
-                                                                        sub_split_start_row_ids=start_row_ids.items())
+                                                                        sub_split_start_row_ids=start_row_ids.items(),
+                                                                        enable_sorted_projections=enable_sorted_projections)
                         with lock:
                             table_pages.append(table_page)
                             row_counts[split_id] += len(table_page)
@@ -2007,7 +2014,7 @@ class VastdbApi:
         txid, created_txid = self._begin_tx_if_necessary(txid)
 
         if rows:
-            columns = self._list_table_columns(bucket, schema, table, field_names=rows.keys())
+            columns = self._list_table_columns(bucket, schema, table, field_names=rows.keys(), txid=txid)
             columns_dict = dict([(column[0], column[1]) for column in columns])
             arrow_schema = pa.schema([])
             arrays = []

{vastdb-0.0.5.2 → vastdb-0.0.5.4}/vastdb.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vastdb
-Version: 0.0.5.2
+Version: 0.0.5.4
 Summary: VAST Data SDK
 Home-page: https://github.com/vast-data/vastdb_sdk
 Author: VAST DATA