databricks-sql-connector 2.9.4b1__tar.gz → 2.9.6__tar.gz

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/CHANGELOG.md

@@ -1,8 +1,14 @@
 # Release History
 
-## 2.9.4 (Unreleased)
+## 2.9.6 (2024-04-18)
 
-## 2.9.4b1 (2024-02-16)
+- Fix: Remove cookie handling code (#379)
+
+## 2.9.5 (2024-03-19)
+
+- Fix: retry-after has a default value of 1 (#371)
+
+## 2.9.4 (2024-02-20)
 
 - Fix: Cloud fetch file download errors (#356)
 - Fix: Redact the URL query parameters from the urllib3.connectionpool logs (#341)
@@ -70,6 +76,7 @@
 - Other: Relax sqlalchemy required version as it was unecessarily strict.
 
 ## 2.5.0 (2023-04-14)
+
 - Add support for External Auth providers
 - Fix: Python HTTP proxies were broken
 - Other: All Thrift requests that timeout during connection will be automatically retried
@@ -91,8 +98,8 @@
 
 ## 2.2.2 (2023-01-03)
 
-- Support custom oauth client id and redirect port 
-- Fix: Add none check on _oauth_persistence in DatabricksOAuthProvider
+- Support custom oauth client id and redirect port
+- Fix: Add none check on \_oauth_persistence in DatabricksOAuthProvider
 
 ## 2.2.1 (2022-11-29)
 
@@ -124,57 +131,71 @@ Huge thanks to @dbaxa for contributing this change!
 
 - Add retry logic for `GetOperationStatus` requests that fail with an `OSError`
 - Reorganised code to use Poetry for dependency management.
+
 ## 2.0.2 (2022-05-04)
+
 - Better exception handling in automatic connection close
 
 ## 2.0.1 (2022-04-21)
+
 - Fixed Pandas dependency in setup.cfg to be >= 1.2.0
 
 ## 2.0.0 (2022-04-19)
+
 - Initial stable release of V2
-- Added better support for complex types, so that in Databricks runtime 10.3+, Arrays, Maps and Structs will get 
+- Added better support for complex types, so that in Databricks runtime 10.3+, Arrays, Maps and Structs will get
   deserialized as lists, lists of tuples and dicts, respectively.
 - Changed the name of the metadata arg to http_headers
 
 ## 2.0.b2 (2022-04-04)
+
 - Change import of collections.Iterable to collections.abc.Iterable to make the library compatible with Python 3.10
 - Fixed bug with .tables method so that .tables works as expected with Unity-Catalog enabled endpoints
 
 ## 2.0.0b1 (2022-03-04)
+
 - Fix packaging issue (dependencies were not being installed properly)
 - Fetching timestamp results will now return aware instead of naive timestamps
 - The client will now default to using simplified error messages
 
 ## 2.0.0b (2022-02-08)
+
 - Initial beta release of V2. V2 is an internal re-write of large parts of the connector to use Databricks edge features. All public APIs from V1 remain.
-- Added Unity Catalog support (pass catalog and / or  schema key word args to the .connect method to select initial schema and catalog)
+- Added Unity Catalog support (pass catalog and / or schema key word args to the .connect method to select initial schema and catalog)
 
 ---
 
 **Note**: The code for versions prior to `v2.0.0b` is not contained in this repository. The below entries are included for reference only.
 
 ---
+
 ## 1.0.0 (2022-01-20)
+
 - Add operations for retrieving metadata
 - Add the ability to access columns by name on result rows
 - Add the ability to provide configuration settings on connect
 
 ## 0.9.4 (2022-01-10)
+
 - Improved logging and error messages.
 
 ## 0.9.3 (2021-12-08)
+
 - Add retries for 429 and 503 HTTP responses.
 
 ## 0.9.2 (2021-12-02)
+
 - (Bug fix) Increased Thrift requirement from 0.10.0 to 0.13.0 as 0.10.0 was in fact incompatible
 - (Bug fix) Fixed error message after query execution failed -SQLSTATE and Error message were misplaced
 
 ## 0.9.1 (2021-09-01)
+
 - Public Preview release, Experimental tag removed
 - minor updates in internal build/packaging
 - no functional changes
 
 ## 0.9.0 (2021-08-04)
+
 - initial (Experimental) release of pyhive-forked connector
 - Python DBAPI 2.0 (PEP-0249), thrift based
 - see docs for more info: https://docs.databricks.com/dev-tools/python-sql-connector.html

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: databricks-sql-connector
-Version: 2.9.4b1
+Version: 2.9.6
 Summary: Databricks SQL Connector for Python
 License: Apache-2.0
 Author: Databricks

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "databricks-sql-connector"
-version = "2.9.4b1"
+version = "2.9.6"
 description = "Databricks SQL Connector for Python"
 authors = ["Databricks <databricks-sql-connector-maintainers@databricks.com>"]
 license = "Apache-2.0"

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/src/databricks/sql/__init__.py

@@ -31,8 +31,7 @@ class RedactUrlQueryParamsFilter(logging.Filter):
                 )
         else:
             record.args = tuple(
-                (self.redact(arg) if isinstance(arg, str) else arg)
-                for arg in record.args
+                (self.redact(arg) if isinstance(arg, str) else arg) for arg in record.args
             )
 
         return True
@@ -40,6 +39,7 @@ class RedactUrlQueryParamsFilter(logging.Filter):
 
 logging.getLogger("urllib3.connectionpool").addFilter(RedactUrlQueryParamsFilter())
 
+
 class DBAPITypeObject(object):
     def __init__(self, *values):
         self.values = values
@@ -60,7 +60,7 @@ DATETIME = DBAPITypeObject("timestamp")
 DATE = DBAPITypeObject("date")
 ROWID = DBAPITypeObject()
 
-__version__ = "2.9.4b1"
+__version__ = "2.9.6"
 USER_AGENT_NAME = "PyDatabricksSqlConnector"
 
 # These two functions are pyhive legacy

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/src/databricks/sql/auth/thrift_http_client.py

@@ -189,10 +189,6 @@ class THttpClient(thrift.transport.THttpClient.THttpClient):
         self.message = self.__resp.reason
         self.headers = self.__resp.headers
 
-        # Saves the cookie sent by the server response
-        if "Set-Cookie" in self.headers:
-            self.setCustomHeaders(dict("Cookie", self.headers["Set-Cookie"]))
-
     @staticmethod
     def basic_proxy_auth_header(proxy):
         if proxy is None or not proxy.username:

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/src/databricks/sql/cloudfetch/downloader.py

@@ -10,7 +10,7 @@ from databricks.sql.thrift_api.TCLIService.ttypes import TSparkArrowResultLink
 
 logger = logging.getLogger(__name__)
 
-DEFAULT_CLOUD_FILE_TIMEOUT = int(os.getenv("DATABRICKS_CLOUD_FILE_TIMEOUT", 60))
+DEFAULT_CLOUD_FILE_TIMEOUT = int(os.getenv("DATABRICKS_CLOUD_FILE_TIMEOUT", 180))
 
 
 @dataclass
@@ -221,9 +221,11 @@ def http_get_with_retry(url, max_retries=5, backoff_factor=2, download_timeout=6
                 return response
             else:
                 logger.error(response)
-        except requests.RequestException as e:
+        except Exception as e:
             # if this is not redacted, it will print the pre-signed URL
-            logger.error(f"request failed with exception: {re.sub(pattern, mask, str(e))}")
+            logger.error(
+                f"request failed with exception: {re.sub(pattern, mask, str(e))}"
+            )
         finally:
             session.close()
         # Exponential backoff before the next attempt

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/src/databricks/sql/thrift_backend.py

@@ -353,8 +353,8 @@ class ThriftBackend:
             # encapsulate retry checks, returns None || delay-in-secs
             # Retry IFF 429/503 code + Retry-After header set
             http_code = getattr(self._transport, "code", None)
-            retry_after = getattr(self._transport, "headers", {}).get("Retry-After")
-            if http_code in [429, 503] and retry_after:
+            retry_after = getattr(self._transport, "headers", {}).get("Retry-After", 1)
+            if http_code in [429, 503]:
                 # bound delay (seconds) by [min_delay*1.5^(attempt-1), max_delay]
                 return bound_retry_delay(attempt, int(retry_after))
             return None

{databricks_sql_connector-2.9.4b1 → databricks_sql_connector-2.9.6}/src/databricks/sql/utils.py

@@ -226,6 +226,9 @@ class CloudFetchQueue(ResultSetQueue):
         # The server rarely prepares the exact number of rows requested by the client in cloud fetch.
         # Subsequently, we drop the extraneous rows in the last file if more rows are retrieved than requested
         if arrow_table.num_rows > downloaded_file.row_count:
+            logger.debug(
+                f"received {arrow_table.num_rows} rows, expected {downloaded_file.row_count} rows. Dropping extraneous rows."
+            )
             self.start_row_index += downloaded_file.row_count
             return arrow_table.slice(0, downloaded_file.row_count)