snowpark-connect 0.27.0__py3-none-any.whl → 1.6.0__py3-none-any.whl

snowflake/snowpark_connect/relation/write/map_write_jdbc.py

@@ -4,6 +4,8 @@
 
 from snowflake import snowpark
 from snowflake.snowpark_connect.dataframe_container import DataFrameContainer
+from snowflake.snowpark_connect.error.error_codes import ErrorCodes
+from snowflake.snowpark_connect.error.error_utils import attach_custom_error_code
 from snowflake.snowpark_connect.relation.read.map_read_jdbc import (
     close_connection,
     create_connection,
@@ -35,7 +37,9 @@ def map_write_jdbc(
         dbtable = None
 
     if dbtable is None:
-        raise ValueError("Include dbtable is required option")
+        exception = ValueError("Include dbtable is required option")
+        attach_custom_error_code(exception, ErrorCodes.INVALID_INPUT)
+        raise exception
 
     try:
         JdbcDataFrameWriter(session, jdbc_options).jdbc_write_dbapi(
@@ -46,4 +50,6 @@ def map_write_jdbc(
             write_mode=write_mode,
         )
     except Exception as e:
-        raise Exception(f"Error accessing JDBC datasource for write: {e}")
+        exception = Exception(f"Error accessing JDBC datasource for write: {e}")
+        attach_custom_error_code(exception, ErrorCodes.INTERNAL_ERROR)
+        raise exception

snowflake/snowpark_connect/resources_initializer.py

@@ -1,18 +1,107 @@
 #
 # Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
 #
-import pathlib
 import threading
 import time
 
 from snowflake.snowpark_connect.utils.session import get_or_create_snowpark_session
 from snowflake.snowpark_connect.utils.snowpark_connect_logging import logger
 
-_resources_initialized = threading.Event()
-_initializer_lock = threading.Lock()
 SPARK_VERSION = "3.5.6"
 RESOURCE_PATH = "/snowflake/snowpark_connect/resources"
 
+# On demand Scala UDF jar upload state - separate from general resource initialization
+_scala_jars_uploaded = threading.Event()
+_scala_jars_lock = threading.Lock()
+
+# Define Scala resource names
+SPARK_SQL_JAR = f"spark-sql_2.12-{SPARK_VERSION}.jar"
+SPARK_CONNECT_CLIENT_JAR = f"spark-connect-client-jvm_2.12-{SPARK_VERSION}.jar"
+SPARK_COMMON_UTILS_JAR = f"spark-common-utils_2.12-{SPARK_VERSION}.jar"
+SAS_SCALA_UDF_JAR = "sas-scala-udf_2.12-0.2.0.jar"
+JSON_4S_JAR = "json4s-ast_2.12-3.7.0-M11.jar"
+SCALA_REFLECT_JAR = "scala-reflect-2.12.18.jar"
+
+
+def _upload_scala_udf_jars_impl() -> None:
+    """Upload Spark jar files required for creating Scala UDFs.
+    This is the internal implementation - use ensure_scala_udf_jars_uploaded() for thread-safe lazy loading."""
+    from pathlib import Path
+
+    session = get_or_create_snowpark_session()
+    stage = session.get_session_stage()
+    resource_path = stage + RESOURCE_PATH
+    import snowpark_connect_deps_1
+    import snowpark_connect_deps_2
+
+    jar_files = [
+        SPARK_SQL_JAR,
+        SPARK_CONNECT_CLIENT_JAR,
+        SPARK_COMMON_UTILS_JAR,
+        SAS_SCALA_UDF_JAR,
+        JSON_4S_JAR,
+        SCALA_REFLECT_JAR,  # Required for deserializing Scala lambdas
+    ]
+
+    # Path to includes/jars directory
+    includes_jars_dir = Path(__file__).parent / "includes" / "jars"
+
+    for jar_name in jar_files:
+        jar_path = None
+
+        # First check includes/jars directory
+        includes_jar_path = includes_jars_dir / jar_name
+        if includes_jar_path.exists():
+            jar_path = includes_jar_path
+            logger.info(f"Found {jar_name} in includes/jars")
+        else:
+            # Try to find the JAR in package 1 first, then package 2
+            try:
+                jar_path = snowpark_connect_deps_1.get_jar_path(jar_name)
+            except FileNotFoundError:
+                try:
+                    jar_path = snowpark_connect_deps_2.get_jar_path(jar_name)
+                except FileNotFoundError:
+                    raise FileNotFoundError(
+                        f"JAR {jar_name} not found in includes/jars or either package"
+                    )
+
+        try:
+            session.file.put(
+                str(jar_path),
+                resource_path,
+                auto_compress=False,
+                overwrite=False,
+                source_compression="NONE",
+            )
+        except Exception as e:
+            raise RuntimeError(f"Failed to upload JAR {jar_name}: {e}")
+
+
+def ensure_scala_udf_jars_uploaded() -> None:
+    """Ensure Scala UDF jars are uploaded to Snowflake, uploading them lazily if not already done.
+    This function is thread-safe and will only upload once even if called from multiple threads."""
+
+    # Fast path: if already uploaded, return immediately without acquiring lock
+    if _scala_jars_uploaded.is_set():
+        return
+
+    # Slow path: need to upload, acquire lock to ensure only one thread does it
+    with _scala_jars_lock:
+        # Double-check pattern: another thread might have uploaded while we waited for the lock
+        if _scala_jars_uploaded.is_set():
+            return
+
+        try:
+            start_time = time.time()
+            logger.info("Uploading Scala UDF jars on-demand...")
+            _upload_scala_udf_jars_impl()
+            _scala_jars_uploaded.set()
+            logger.info(f"Scala UDF jars uploaded in {time.time() - start_time:.2f}s")
+        except Exception as e:
+            logger.error(f"Failed to upload Scala UDF jars: {e}")
+            raise
+
 
 def initialize_resources() -> None:
     """Initialize all expensive resources. We should initialize what we can here, so that actual rpc calls like
@@ -44,34 +133,6 @@ def initialize_resources() -> None:
 
         session.sql("select 1 as sf_connection_warm_up").collect()
 
-    def upload_scala_udf_jars() -> None:
-        """Upload Spark jar files required for creating Scala UDFs."""
-        stage = session.get_session_stage()
-        resource_path = stage + RESOURCE_PATH
-        import snowflake
-
-        pyspark_jars = (
-            pathlib.Path(snowflake.snowpark_connect.__file__).parent / "includes/jars"
-        )
-        jar_files = [
-            f"spark-sql_2.12-{SPARK_VERSION}.jar",
-            f"spark-connect-client-jvm_2.12-{SPARK_VERSION}.jar",
-            f"spark-common-utils_2.12-{SPARK_VERSION}.jar",
-            "json4s-ast_2.12-3.7.0-M11.jar",
-            "json4s-native_2.12-3.7.0-M11.jar",
-            "json4s-core_2.12-3.7.0-M11.jar",
-            "paranamer-2.8.3.jar",
-        ]
-
-        for jar in jar_files:
-            session.file.put(
-                str(pyspark_jars) + "/" + jar,
-                resource_path,
-                auto_compress=False,
-                overwrite=False,
-                source_compression="NONE",
-            )
-
     start_time = time.time()
 
     resources = [
@@ -80,7 +141,6 @@ def initialize_resources() -> None:
         ("Initialize Session Stage", initialize_session_stage),  # Takes about 0.3s
         ("Initialize Session Catalog", initialize_catalog),  # Takes about 1.2s
         ("Snowflake Connection Warm Up", warm_up_sf_connection),  # Takes about 1s
-        ("Upload Scala UDF Jars", upload_scala_udf_jars),
     ]
 
     for name, resource_func in resources:
@@ -94,23 +154,25 @@ def initialize_resources() -> None:
             if str(e).find("because the session has been closed") == -1:
                 logger.error(f"Failed to initialize {name}: {e}")
 
-    _resources_initialized.set()
     logger.info(f"All resources initialized in {time.time() - start_time:.2f}s")
 
 
-_resource_initializer = threading.Thread(
-    target=initialize_resources, name="ResourceInitializer"
-)
-
-
-def initialize_resources_async() -> threading.Thread:
-    """Start resource initialization in background."""
-    with _initializer_lock:
-        if not _resource_initializer.is_alive() and _resource_initializer.ident is None:
-            _resource_initializer.start()
-        return _resource_initializer
-
-
 def wait_for_resource_initialization() -> None:
-    with _initializer_lock:
-        _resource_initializer.join()
+    """No-op function retained for backward compatibility.
+
+    This function is kept to maintain backward compatibility with external client code that may call it.
+    Previously, this function waited for asynchronous resource initialization to complete.
+    Now that resource initialization is synchronous, this function does nothing.
+    External callers can safely call this function without any effect.
+    """
+    pass
+
+
+def set_upload_jars(upload: bool) -> None:
+    """No-op function retained for backward compatibility.
+    This function is kept to maintain backward compatibility with external client code that may call it.
+    Previously, this function was used to set whether to upload jars required for Scala UDFs.
+    Now that Scala UDF jar upload has been moved to lazy on-demand loading via ensure_scala_udf_jars_uploaded(),
+    this function does nothing. External callers can safely call this function without any effect.
+    """
+    pass