Merge branch 'main' into geospatial-datatype

Author: sreekanth-db

.github/ISSUE_TEMPLATE/bug_report.md

@@ -26,7 +26,7 @@ If available, share redacted client side logs
  - OS: [e.g. Windows]
  - Java version [e.g. Java 21]
  - Java vendor [e.g. OpenJDK]
- - Driver Version [e.g. 1.0.9-oss]
+ - Driver Version [e.g. 1.0.10-oss]
  - BI Tool (if used) [e.g. DBeaver]
  - BI Tool version (if applicable) [e.g. 24.3.5]
 

.github/workflows/release-thin.yml

@@ -0,0 +1,66 @@
+name: Release Thin JAR
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+jobs:
+  publish-thin:
+    runs-on:
+      group: databricks-protected-runner-group
+      labels: linux-ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Java for publishing to Maven Central Repository
+        uses: actions/setup-java@v4
+        with:
+          java-version: 11
+          distribution: "adopt"
+          server-id: central
+          server-username: MAVEN_CENTRAL_USERNAME
+          server-password: MAVEN_CENTRAL_PASSWORD
+          gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }}
+          gpg-passphrase: GPG_PASSPHRASE
+
+      - name: Configure GPG
+        run: |
+          echo "allow-loopback-pinentry" >> ~/.gnupg/gpg-agent.conf
+          echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
+          gpg-connect-agent reloadagent /bye
+
+      - name: Build thin JAR
+        run: |
+          mvn -B -DskipTests package
+
+      - name: Verify thin jar exists
+        run: |
+          VERSION=$(grep -m1 '<version>' pom.xml | sed 's/.*<version>\(.*\)<\/version>.*/\1/')
+          test -f "target/databricks-jdbc-${VERSION}-oss-thin.jar"
+
+      - name: Publish Thin JAR as Separate Artifact to Maven Central
+        run: |
+          VERSION=$(grep -m1 '<version>' pom.xml | sed 's/.*<version>\(.*\)<\/version>.*/\1/')
+          mvn -Prelease gpg:sign-and-deploy-file \
+            -Dfile="target/databricks-jdbc-${VERSION}-oss-thin.jar" \
+            -DrepositoryId=central \
+            -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ \
+            -DgroupId=com.databricks \
+            -DartifactId=databricks-jdbc-thin \
+            -Dversion="${VERSION}" \
+            -Dpackaging=jar \
+            -DgeneratePom=true \
+            -Dgpg.passphrase="${GPG_PASSPHRASE}"
+        env:
+          GPG_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}
+          MAVEN_CENTRAL_USERNAME: ${{ secrets.MAVEN_CENTRAL_USERNAME }}
+          MAVEN_CENTRAL_PASSWORD: ${{ secrets.MAVEN_CENTRAL_PASSWORD }}
+
+      - name: Upload Thin JAR to GitHub Release
+        uses: softprops/action-gh-release@v1
+        with:
+          files: |
+            target/*-oss-thin.jar
+

.github/workflows/release.yml

@@ -32,7 +32,9 @@ jobs:
           gpg-connect-agent reloadagent /bye
 
       - name: Publish to the Maven Central Repository
-        run: mvn -Prelease --batch-mode deploy -Dnvd.api.key=${{ secrets.NVD_API_KEY }}
+        run: |
+          # Deploy main artifacts (uber JAR, sources, javadoc)
+          mvn -Prelease --batch-mode deploy -Dnvd.api.key=${{ secrets.NVD_API_KEY }}
         env:
           GPG_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}
           MAVEN_CENTRAL_USERNAME: ${{ secrets.MAVEN_CENTRAL_USERNAME }}
@@ -41,4 +43,8 @@ jobs:
       - name: Create GitHub release
         uses: softprops/action-gh-release@v1
         with:
-          files: target/*.jar
+          files: |
+            target/databricks-jdbc-*-oss.jar
+            target/databricks-jdbc-*-sources.jar
+            target/databricks-jdbc-*-javadoc.jar
+          fail_on_unmatched_files: false

.github/workflows/releaseFreeze.yml

@@ -6,7 +6,9 @@ on:
 
 jobs:
   freeze-check:
-    runs-on: ubuntu-latest
+    runs-on:
+      group: databricks-protected-runner-group
+      labels: linux-ubuntu-latest
 
     steps:
       - name: Check out repository
@@ -15,14 +17,37 @@ jobs:
       - name: Set up jq
         run: sudo apt-get update && sudo apt-get install -y jq
 
+      - name: Fetch PR message
+        id: pr-message
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Use the GitHub API to fetch the PR message
+          pr_message=$(gh pr view ${{ github.event.pull_request.number }} --json body -q '.body')
+          
+          # Sanitize the PR message to avoid code injection, keeping the equal sign
+          sanitized_pr_message=$(echo "$pr_message" | sed 's/[^a-zA-Z0-9._/-=]/_/g')
+          
+          # Store the sanitized PR message
+          echo "$sanitized_pr_message" > pr_message.txt
+          echo "$sanitized_pr_message"
+
       - name: Enforce branch freeze logic
         shell: bash
         env:
           # GITHUB_HEAD_REF: Source branch name for PRs
           PR_BRANCH: ${{ github.head_ref }}
         run: |
-          CONFIG_FILE="development/.release-config.json"
+          CONFIG_FILE="development/.release-freeze.json"
+
+          # 1. Check for explicit override flag in PR message
+          pr_message=$(cat pr_message.txt)
+          if echo "$pr_message" | grep -q "OVERRIDE_FREEZE=true"; then
+            echo "✅ OVERRIDE_FREEZE=true found in PR message. Freeze override permitted."
+            exit 0
+          fi
 
+          # 2. Proceed with freeze checks
           if [[ ! -f "$CONFIG_FILE" ]]; then
             echo "✅ No release config file - passing check."
             exit 0
@@ -35,26 +60,7 @@ jobs:
             exit 0
           fi
 
-          ALLOW_LIST=( $(jq -r '.allow_list[]' "$CONFIG_FILE") )
-
-          BRANCH="$PR_BRANCH"
-          ALLOWED=0
-
-          # Check for exact branch name in allow_list
-          for ENTRY in $(jq -r '.allow_list[]' "$CONFIG_FILE"); do
-            if [[ "$BRANCH" == "$ENTRY" ]]; then
-              ALLOWED=1
-              break
-            fi
-          done
-
-          if [[ "$ALLOWED" == "1" ]]; then
-            echo "✅ Branch '$BRANCH' is in allow_list. Passing check."
-            exit 0
-          else
-            echo "❌ Release freeze is ACTIVE!"
-            REASON=$(jq -r '.reason' "$CONFIG_FILE")
-            echo "Reason: $REASON"
-            echo "Branch '$BRANCH' is NOT permitted to merge under current freeze rules."
-            exit 1
-          fi
+          # 3. Freeze is ON and no override flag. Block PR.
+          echo "Release freeze is ACTIVE! Branch '${PR_BRANCH}' is NOT permitted to merge."
+          echo "To override, add OVERRIDE_FREEZE=true to your PR description."
+          exit 1

CHANGELOG.md

@@ -1,5 +1,31 @@
 # Version Changelog
 
+## [v1.0.10-oss] - 2025-09-18
+### Added
+- **Query Tags support**: Added ability to attach key-value tags to SQL queries for analytical purposes that would appear in `system.query.history` table. Example: `jdbc:databricks://host;QUERY_TAGS=team:marketing,dashboard:abc123`. (This feature is in [private preview](https://docs.databricks.com/aws/en/release-notes/release-types#:~:text=Private%20Preview-,Invite%20only,-No))
+- **SQL Scripting support**: Added support for [SQL Scripting](https://docs.databricks.com/aws/en/sql/language-manual/sql-ref-scripting)
+- Added a client property `enableVolumeOperations` to enable  GET/PUT/REMOVE volume operations on a stream. For backward compatibility, allowedVolumeIngestionPaths can also be used for REMOVE operation.
+- Support for fetching schemas across all catalogs (when catalog is specified as null or a wildcard) in `DatabaseMetaData#getSchemas` API in SQL Execution mode.
+- **Configurable SQL validation in isValid()**: Added `EnableSQLValidationForIsValid` connection property to control whether `isValid()` method executes an actual SQL query for server-side validation. Default value is 0.
+- Implement multi-row INSERT batching optimization for prepared statements to improve performance when executing large batches of INSERT operations.
+- Implement lazy/incremental fetching for columnar results when using Databricks JDBC in Thrift mode without Arrow support. The change modifies the behavior from buffering entire result sets in memory to maintaining only a limited number of rows at a time, reducing peak heap memory usage and preventing OutOfMemory errors.
+- Added new artifact `databricks-jdbc-thin` for thin jar with runtime dependency metadata.
+- Introduce a memory-efficient columnar data access mechanism for JDBC result processing.
+- Added support for using a custom Discovery URL in U2M flows on AWS and GCP.
+
+### Updated
+- Databricks SDK dependency upgraded to latest version 0.64.0
+
+### Fixed
+- Integrated Azure U2M flow into driver for improved stability.
+- Fixed `ResultSet.getString` for Boolean columns in Metadata result set.
+- Fixed volume operations not completing unless the ResultSet is fully iterated.
+- Fixed `connection.getMetadata().getColumns()` to return the correct SQL data type code for complex type columns.
+- Fixed a bug in the JDBC driver's metadata parsing for nested decimal fields within struct types.
+- Fixed case sensitive table search in `connection.getMetadata().getTables()`
+- Fixed `connection.getMetadata().getColumns()` to return the correct scale.
+---
+
 ## [v1.0.9-oss] - 2025-08-19
 ### Added
 - Added support for providing custom HTTP options: `HttpMaxConnectionsPerRoute` and `HttpConnectionRequestTimeout`.

NEXT_CHANGELOG.md

@@ -3,23 +3,16 @@
 ## [Unreleased]
 
 ### Added
-
-- **Query Tags support**: Added ability to attach key-value tags to SQL queries for analytical purposes that would appear in `system.query.history` table. Example: `jdbc:databricks://host;QUERY_TAGS=team:marketing,dashboard:abc123`. 
-- **SQL Scripting support**: Added support for [SQL Scripting](https://docs.databricks.com/aws/en/sql/language-manual/sql-ref-scripting)
-- Added a client property `enableVolumeOperations` to enable  GET/PUT/REMOVE volume operations on a stream. For backward compatibility, allowedVolumeIngestionPaths can also be used for REMOVE operation.
-- Support for fetching schemas across all catalogs (when catalog is specified as null or a wildcard) in `DatabaseMetaData#getSchemas` API in SQL Execution mode.
-- **Configurable SQL validation in isValid()**: Added `EnableSQLValidationForIsValid` connection property to control whether `isValid()` method executes an actual SQL query for server-side validation. Default value is 0.
-- Implement multi-row INSERT batching optimization for prepared statements to improve performance when executing large batches of INSERT operations.
-- Implement lazy/incremental fetching for columnar results when using Databricks JDBC in Thrift mode without Arrow support. The change modifies the behavior from buffering entire result sets in memory to maintaining only a limited number of rows at a time, reducing peak heap memory usage and preventing OutOfMemory errors.
-
+- Enabled direct results by default in SEA mode to improve latency for short and small queries.
 ### Updated
-- Databricks SDK dependency upgraded to latest version 0.60.0
+- Telemetry data is now captured more efficiently and consistently due to enhancements in the log and connection close flush logic.
+- Updated Databricks SDK version to v0.65.0 (This is to fix OAuthClient to properly encode complex query parameters.)
+- Added IgnoreTransactions connection parameter to silently ignore transaction method calls.
 
 ### Fixed
-- Integrated Azure U2M flow into driver for improved stability.
-- Fixed `ResultSet.getString` for Boolean columns in Metadata result set.
-- Fixed volume operations not completing unless the ResultSet is fully iterated.
-- Fixed `connection.getMetadata().getColumns()` to return the correct SQL data type code for complex type columns.
-- Fixed a bug in the JDBC driver's metadata parsing for nested decimal fields within struct types.
+- Fixed state leaking issue in thrift client.
+- Fixed timestamp values returning only milliseconds instead of the full nanosecond precision.
+- Fixed Statement.getUpdateCount() for DML queries.
+- Fixed Maven Central publishing to use minimal POM for both main and thin JARs, restoring behavior from v1.0.7 and earlier
 ---
 *Note: When making changes, please add your change under the appropriate section with a brief description.* 

README.md

@@ -20,20 +20,43 @@ Add the following dependency to your `pom.xml`:
 <dependency>
   <groupId>com.databricks</groupId>
   <artifactId>databricks-jdbc</artifactId>
-  <version>1.0.9-oss</version>
+  <version>1.0.10-oss</version>
 </dependency>
 ```
 
+#### Thin JAR
+
+For applications requiring explicit dependency management, use the thin JAR variant:
+
+```xml
+<!-- Note: Available from version 1.0.10-oss onwards -->
+<dependency>
+  <groupId>com.databricks</groupId>
+  <artifactId>databricks-jdbc-thin</artifactId>
+  <version>1.0.10-oss</version>
+</dependency>
+```
+
+The thin JAR contains only the driver code and declares all dependencies in its POM, enabling dependency introspection and version management.
+
 ### Build from Source
 
 1. Clone the repository
 2. Run the following command:
    ```bash
    mvn clean package
    ```
-3. The jar file is generated as `target/databricks-jdbc-<version>.jar`
+3. The following JAR files are generated:
+   - `target/databricks-jdbc-<version>.jar` (standard JAR with bundled dependencies)
+   - `target/databricks-jdbc-<version>-thin.jar` (thin JAR without dependencies)
 4. The test coverage report is generated in `target/site/jacoco/index.html`
 
+To install the thin JAR locally with dependency metadata:
+```bash
+VERSION=$(grep -m1 '<version>' pom.xml | sed 's/.*<version>\(.*\)<\/version>.*/\1/')
+mvn install:install-file -Dfile="target/databricks-jdbc-${VERSION}-thin.jar" -DpomFile=thin_public_pom.xml
+```
+
 ## Usage
 
 ### Connection String

development/.release-freeze.json

@@ -1,5 +1,4 @@
 {
   "freeze": false,
-  "reason": "Release description",
-  "allow_list": []
-}
+  "reason": ""
+}

pom.xml

@@ -5,7 +5,7 @@
   <groupId>com.databricks</groupId>
   <artifactId>databricks-jdbc</artifactId>
   <!-- This value may be modified by a release script to reflect the current version of the driver. -->
-  <version>1.0.9-oss</version>
+  <version>1.0.10-oss</version>
   <packaging>jar</packaging>
   <name>Databricks JDBC Driver</name>
   <description>Databricks JDBC Driver.</description>
@@ -51,11 +51,12 @@
     <google.guava.version>33.0.0-jre</google.guava.version>
     <junit.jupiter.version>5.9.2</junit.jupiter.version>
     <google.findbugs.annotations.version>3.0.1</google.findbugs.annotations.version>
+    <gson.version>2.13.2</gson.version>
     <immutables.value.version>2.9.2</immutables.value.version>
     <httpclient.version>4.5.14</httpclient.version>
     <commons-configuration.version>2.10.1</commons-configuration.version>
     <commons-io.version>2.14.0</commons-io.version>
-    <databricks-sdk.version>0.60.0</databricks-sdk.version>
+    <databricks-sdk.version>0.65.0</databricks-sdk.version>
     <maven-surefire-plugin.version>3.1.2</maven-surefire-plugin.version>
     <sql-logic-test.version>0.3</sql-logic-test.version>
     <lz4-compression.version>1.8.0</lz4-compression.version>
@@ -65,9 +66,9 @@
     <slt.token>dummy-token</slt.token>
     <wiremock.version>3.5.4</wiremock.version>
     <nimbusjose.version>10.0.2</nimbusjose.version>
-    <bouncycastle.version>1.78.1</bouncycastle.version>
+    <bouncycastle.version>1.79</bouncycastle.version>
     <async-httpclient.version>5.3.1</async-httpclient.version>
-    <netty.version>4.2.0.Final</netty.version>
+    <netty.version>4.2.6.Final</netty.version>
     <grpc.version>1.71.0</grpc.version>
     <resilience4j.version>1.7.0</resilience4j.version>
   </properties>
@@ -79,6 +80,12 @@
         <artifactId>commons-lang3</artifactId>
         <version>${commons-lang3.version}</version>
       </dependency>
+      <!-- Force safe version of Gson to fix CVE-2025-53864 -->
+      <dependency>
+        <groupId>com.google.code.gson</groupId>
+        <artifactId>gson</artifactId>
+        <version>${gson.version}</version>
+      </dependency>
     </dependencies>
   </dependencyManagement>
   <dependencies>
@@ -676,9 +683,6 @@
               <pomFile>${project.basedir}/uber-minimal-pom.xml</pomFile>
               <sources>${project.build.directory}/${project.build.finalName}-sources.jar</sources>
               <javadoc>${project.build.directory}/${project.build.finalName}-javadoc.jar</javadoc>
-              <files>${project.build.directory}/${project.build.finalName}-thin.jar</files>
-              <types>jar</types>
-              <classifiers>thin</classifiers>
             </configuration>
             <executions>
               <execution>
@@ -699,10 +703,14 @@
              <publishingServerId>central</publishingServerId>
               <autoPublish>true</autoPublish>
               <waitUntil>published</waitUntil>
+              <!-- Use minimal POM for fat jar publishing -->
+              <pomFile>${project.basedir}/uber-minimal-pom.xml</pomFile>
             </configuration>
           </plugin>
         </plugins>
       </build>
     </profile>
+    
   </profiles>
+  
 </project>

src/main/java/com/databricks/client/jdbc/Driver.java

@@ -22,10 +22,11 @@
 import java.util.List;
 import java.util.Properties;
 import java.util.TimeZone;
+import java.util.concurrent.CompletableFuture;
 import java.util.logging.Logger;
 
 /** Databricks JDBC driver. */
-public class Driver implements IDatabricksDriver, java.sql.Driver {
+public class Driver implements IDatabricksDriver {
   private static final JdbcLogger LOGGER = JdbcLoggerFactory.getLogger(Driver.class);
   private static final Driver INSTANCE;
 
@@ -57,8 +58,8 @@ public Connection connect(String url, Properties info) throws DatabricksSQLExcep
     IDatabricksConnectionContext connectionContext =
         DatabricksConnectionContextFactory.create(url, info);
     DriverUtil.setUpLogging(connectionContext);
+    CompletableFuture.runAsync(() -> LOGGER.info(getDriverSystemConfiguration().toString()));
     UserAgentManager.setUserAgent(connectionContext);
-    LOGGER.info(getDriverSystemConfiguration().toString());
     DatabricksConnection connection = new DatabricksConnection(connectionContext);
     boolean isConnectionOpen = false;
     try {