Update jdbc string

Update default option

Update log stmt

Reorder parameters

Minimise diff

Author: andy-k-improving

connectors/athena-databricks-connector/README.md

@@ -40,8 +40,7 @@ From the repository root, initialize the submodule and build:
 
 ```bash
 git submodule update --init
-cd connectors
-mvn clean package -DskipTests
+mvn clean package -DskipTests -f connectors/pom.xml
 ```
 
 The parent POM builds the `athena-jdbc` dependency from the submodule first, then the Databricks connector.
@@ -58,10 +57,11 @@ sam deploy --guided -t connectors/athena-databricks-connector/athena-databricks-
 | Parameter | Description | Default |
 |-----------|-------------|---------|
 | AthenaCatalogName | Lambda function name (must match pattern: `^[a-z0-9-_]{1,64}$`) | databricks |
-| SpillBucket | S3 bucket for spilling data | Required |
+| SpillBucket | S3 bucket name for spilling data (bucket name only, not URI or ARN) | Required |
 | SpillPrefix | Prefix within SpillBucket | athena-spill |
 | LambdaTimeout | Maximum Lambda invocation runtime (1-900 seconds) | 900 |
 | LambdaMemory | Lambda memory in MB (128-3008) | 1024 |
+| DatabricksHost | Databricks workspace hostname (e.g. `dbc-59ed3753-5cf0.cloud.databricks.com`) | Required |
 | SecretName | Name of the Secrets Manager secret containing the Databricks personal access token | Required |
 | DatabricksDefaultDatabase | Default Databricks Unity Catalog database (catalog.schema) | default |
 | DisableSpillEncryption | Disable encryption for spilled data | false |

connectors/athena-databricks-connector/athena-databricks-connector.yaml

@@ -19,13 +19,38 @@ Parameters:
     Type: String
     AllowedPattern: ^[a-z0-9-_]{1,64}$
     Default: databricks
+  DatabricksHost:
+    Description: "The Databricks workspace hostname (e.g. dbc-59ed3753-5cf0.cloud.databricks.com). Do not include https:// or port."
+    Type: String
+    AllowedPattern: ^[a-zA-Z0-9][a-zA-Z0-9.\-]+[a-zA-Z0-9]$
+    ConstraintDescription: "Enter only the hostname (e.g. dbc-59ed3753-5cf0.cloud.databricks.com), not a full URL."
+  DatabricksHttpPath:
+    Description: "The HTTP path for the Databricks SQL warehouse API (e.g., /sql/1.0/warehouses/abc123)."
+    Type: String
+  DatabricksConnCatalog:
+    Description: "The Databricks Unity Catalog name to connect to."
+    Type: String
+    Default: workspace
+  SecretName:
+    Description: "The name of the secret in AWS Secrets Manager that contains the Databricks personal access token."
+    Type: String
   SpillBucket:
-    Description: 'The name of the bucket where this function can spill data.'
+    Description: 'The name of the bucket where this function can spill data. Use only the bucket name (e.g. my-athena-spill), not the full S3 URI or ARN.'
     Type: String
+    AllowedPattern: ^[a-z0-9][a-z0-9.\-]{1,61}[a-z0-9]$
+    ConstraintDescription: 'Enter only the bucket name (e.g. my-athena-spill), not an S3 URI (s3://...) or ARN.'
   SpillPrefix:
     Description: 'The prefix within SpillBucket where this function can spill data.'
     Type: String
     Default: athena-spill
+  DatabricksDefaultDatabase:
+    Description: "The default Databricks Unity Catalog database (catalog.schema) to use when not specified in the query."
+    Default: default
+    Type: String
+  DatabricksFetchSize:
+    Description: "Number of rows fetched per JDBC round trip. Higher values improve throughput but use more memory."
+    Default: 10000
+    Type: Number
   LambdaTimeout:
     Description: "Maximum Lambda invocation runtime in seconds. (min 1 - 900 max)"
     Default: 900
@@ -34,23 +59,6 @@ Parameters:
     Description: "Lambda memory in MB (min 128 - 3008 max)."
     Default: 1024
     Type: Number
-  SecretName:
-    Description: "The name of the secret in AWS Secrets Manager that contains the Databricks personal access token."
-    Type: String
-  DatabricksHttpPath:
-    Description: "The HTTP path for the Databricks SQL warehouse API (e.g., /sql/1.0/warehouses/abc123)."
-    Type: String
-  DatabricksConnCatalog:
-    Description: "The Databricks Unity Catalog name to connect to."
-    Type: String
-  DatabricksFetchSize:
-    Description: "Number of rows fetched per JDBC round trip. Higher values improve throughput but use more memory."
-    Default: 10000
-    Type: Number
-  DatabricksDefaultDatabase:
-    Description: "The default Databricks Unity Catalog database (catalog.schema) to use when not specified in the query."
-    Default: default
-    Type: String
   DisableSpillEncryption:
     Description: "WARNING: If set to 'true' encryption for spilled data is disabled."
     Default: "false"
@@ -65,6 +73,7 @@ Resources:
       ImageUri: connectorconfig:v1
       Environment:
         Variables:
+          databricks_host: !Ref DatabricksHost
           disable_spill_encryption: !Ref DisableSpillEncryption
           spill_bucket: !Ref SpillBucket
           spill_prefix: !Ref SpillPrefix

connectors/athena-databricks-connector/src/main/java/com/amazonaws/athena/connectors/databricks/DatabricksConstants.java

@@ -38,6 +38,12 @@ private DatabricksConstants() {}
     /** Databricks SQL quote character for identifiers. */
     public static final String QUOTE_CHARACTER = "`";
 
+    /** Environment variable key for the Databricks workspace hostname. */
+    public static final String HOST_CONFIG_KEY = "databricks_host";
+    /** Environment variable key for the Secrets Manager secret name containing the Databricks PAT. */
+    public static final String SECRET_NAME_CONFIG_KEY = "secret_manager_databricks_token_name";
+    /** Environment variable key for the default Databricks database. */
+    public static final String DEFAULT_DATABASE_CONFIG_KEY = "databricks_default_database";
     /** Environment variable key for the Databricks SQL warehouse HTTP path. */
     public static final String HTTP_PATH_CONFIG_KEY = "databricks_http_path";
     /** Environment variable key for the Databricks Unity Catalog name. */

connectors/athena-databricks-connector/src/main/java/com/amazonaws/athena/connectors/databricks/DatabricksEnvironmentProperties.java

@@ -20,15 +20,54 @@
 package com.amazonaws.athena.connectors.databricks;
 
 import com.amazonaws.athena.connectors.jdbc.JdbcEnvironmentProperties;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.util.Map;
 
+import static com.amazonaws.athena.connectors.databricks.DatabricksConstants.DATABRICKS_DEFAULT_PORT;
+import static com.amazonaws.athena.connectors.databricks.DatabricksConstants.DEFAULT_DATABASE_CONFIG_KEY;
+import static com.amazonaws.athena.connectors.databricks.DatabricksConstants.HOST_CONFIG_KEY;
+import static com.amazonaws.athena.connectors.databricks.DatabricksConstants.SECRET_NAME_CONFIG_KEY;
+
 /**
  * Provides Databricks-specific JDBC environment properties.
- * Configures the JDBC connection string prefix for Databricks.
+ * Builds the connection string from individual environment variables (host, database, secret)
+ * so users don't need to provide the full JDBC URL.
  */
 public class DatabricksEnvironmentProperties extends JdbcEnvironmentProperties
 {
+    private static final Logger LOGGER = LoggerFactory.getLogger(DatabricksEnvironmentProperties.class);
+    /**
+     * Builds the {@code default} connection string required by the Athena Federation SDK
+     * from individual Lambda environment variables.
+     *
+     * <p>If a {@code default} env var is already present (e.g. via a Glue connection),
+     * it is left unchanged. Otherwise, the connection string is assembled from:
+     * <ul>
+     *   <li>{@code databricks_host} — workspace hostname</li>
+     *   <li>{@code databricks_default_database} — target database (defaults to {@code "default"})</li>
+     *   <li>{@code secret_manager_databricks_token_name} — Secrets Manager secret for PAT injection</li>
+     * </ul>
+     *
+     * @return environment map containing the {@code default} connection string and all Lambda env vars
+     */
+    @Override
+    public Map<String, String> createEnvironment()
+    {
+        Map<String, String> env = super.createEnvironment();
+        if (!env.containsKey("default") && env.containsKey(HOST_CONFIG_KEY)) {
+            String host = env.get(HOST_CONFIG_KEY);
+            String database = env.getOrDefault(DEFAULT_DATABASE_CONFIG_KEY, "default");
+            String secret = env.getOrDefault(SECRET_NAME_CONFIG_KEY, "");
+            String connectionString = String.format("databricks://jdbc:databricks://%s:%d/%s${%s}",
+                    host, DATABRICKS_DEFAULT_PORT, database, secret);
+            env.put("default", connectionString);
+            LOGGER.trace("Built JDBC connection string: {}", connectionString);
+        }
+        return env;
+    }
+
     /**
      * {@inheritDoc}
      */