Release 0.8.0.

Author: kbuilder user

CHANGES.md

@@ -1,6 +1,6 @@
 # Release Notes
 
-## Next
+## 0.8.0 - 2025-11-26
 
 * PR #99: feat: provide option to pass in a row filter in df and RDD
 * PR #101: feat: pushdown column filters from catalog

README.md

@@ -20,7 +20,7 @@ In Java and Scala applications, you can use different dependency management
 tools (e.g., Maven, sbt, or Gradle) to access the
 connector `com.google.cloud.spark.bigtable:spark-bigtable_2.13:<version>` or
 `com.google.cloud.spark.bigtable:spark-bigtable_2.12:<version>` (current
-`<version>` is `0.7.2`) and package it inside your application JAR
+`<version>` is `0.8.0`) and package it inside your application JAR
 using libraries such as Maven Shade Plugin. For PySpark applications, you can
 use the `--jars` flag to pass the GCS address of the connector when submitting
 it.
@@ -32,7 +32,7 @@ For Maven, you can add the following snippet to your `pom.xml` file:
 <dependency>
     <groupId>com.google.cloud.spark.bigtable</groupId>
     <artifactId>spark-bigtable_2.13</artifactId>
-    <version>0.7.2</version>
+    <version>0.8.0</version>
 </dependency>
 ```
 
@@ -41,20 +41,20 @@ For Maven, you can add the following snippet to your `pom.xml` file:
 <dependency>
     <groupId>com.google.cloud.spark.bigtable</groupId>
     <artifactId>spark-bigtable_2.12</artifactId>
-    <version>0.7.2</version>
+    <version>0.8.0</version>
 </dependency>
 ```
 
 For sbt, you can add the following to your `build.sbt` file:
 
 ```
 // for scala 2.13
-libraryDependencies += "com.google.cloud.spark.bigtable" % "spark-bigtable_2.13" % "0.7.2"
+libraryDependencies += "com.google.cloud.spark.bigtable" % "spark-bigtable_2.13" % "0.8.0"
 ```
 
 ```
 // for scala 2.12
-libraryDependencies += "com.google.cloud.spark.bigtable" % "spark-bigtable_2.12" % "0.7.2"
+libraryDependencies += "com.google.cloud.spark.bigtable" % "spark-bigtable_2.12" % "0.8.0"
 ```
 
 Finally, you can add the following to your `build.gradle` file when using
@@ -63,14 +63,14 @@ Gradle:
 ```
 // for scala 2.13
 dependencies {
-implementation group: 'com.google.cloud.bigtable', name: 'spark-bigtable_2.13', version: '0.7.2'
+implementation group: 'com.google.cloud.bigtable', name: 'spark-bigtable_2.13', version: '0.8.0'
 }
 ```
 
 ```
 // for scala 2.12
 dependencies {
-implementation group: 'com.google.cloud.bigtable', name: 'spark-bigtable_2.12', version: '0.7.2'
+implementation group: 'com.google.cloud.bigtable', name: 'spark-bigtable_2.12', version: '0.8.0'
 }
 ```
 
@@ -240,6 +240,32 @@ Dataset<Row> dataFrame = spark
   .load();
 ```
 
+### Reading from Bigtable with complex Filters
+
+You can read from Bigtable with any supported [filters](https://docs.cloud.google.com/bigtable/docs/using-filters) with
+the `spark.bigtable.read.row.filters` option. This option expects a string which is the Base64 encoding of a
+[Bigtable RowFilter](https://github.com/googleapis/java-bigtable/blob/v2.70.0/proto-google-cloud-bigtable-v2/src/main/java/com/google/bigtable/v2/RowFilter.java)
+object.
+
+```scala
+import com.google.cloud.spark.bigtable.repackaged.com.google.cloud.bigtable.data.v2.models.Filters.FILTERS
+import com.google.cloud.spark.bigtable.repackaged.com.google.common.io.BaseEncoding
+
+val filters = FILTERS.chain()
+        .filter(FILTERS.family().exactMatch("info"))
+        .filter(FILTERS.qualifier().regex("\\C*"))
+val filterString = BaseEncoding.base64().encode(filters.toProto.toByteArray)
+
+val dataFrame = spark
+  .read()
+  .format("bigtable")
+  .option("catalog", catalog)
+  .option("spark.bigtable.project.id", projectId)
+  .option("spark.bigtable.instance.id", instanceId)
+  .option("spark.bigtable.read.row.filters", filterString)
+  .load();
+```
+
 ### Efficient joins with other data sources
 
 If you have a large DataFrame that you want to join with some Bigtable data and

pom.xml

@@ -21,7 +21,7 @@
   <groupId>com.google.cloud.spark.bigtable</groupId>
   <artifactId>spark-bigtable-connector</artifactId>
   <packaging>pom</packaging>
-  <version>0.7.2</version>  <!-- ${NEXT_VERSION_FLAG} -->
+  <version>0.8.0</version>  <!-- ${NEXT_VERSION_FLAG} -->
   <name>Spark Bigtable Connector Build Parent</name>
   <description>Parent project for all the Spark Bigtable Connector artifacts</description>
   <url>https://github.com/GoogleCloudDataproc/spark-bigtable-connector</url>

spark-bigtable-core-it/pom.xml

@@ -21,14 +21,14 @@
   <parent>
     <groupId>com.google.cloud.spark.bigtable</groupId>
     <artifactId>spark-bigtable-connector</artifactId>
-    <version>0.7.2</version>  <!-- ${NEXT_VERSION_FLAG} -->
+    <version>0.8.0</version>  <!-- ${NEXT_VERSION_FLAG} -->
     <relativePath>../</relativePath>
   </parent>
 
   <groupId>com.google.cloud.spark.bigtable</groupId>
   <artifactId>spark-bigtable-core-it</artifactId>
   <name>Google Bigtable - Spark Connector Integration Tests</name>
-  <version>0.7.2</version>  <!-- ${NEXT_VERSION_FLAG} -->
+  <version>0.8.0</version>  <!-- ${NEXT_VERSION_FLAG} -->
 
   <dependencies>
     <dependency>
@@ -52,7 +52,7 @@
     <dependency>
       <groupId>com.google.cloud.spark.bigtable</groupId>
       <artifactId>${connector.artifact.id}</artifactId>
-      <version>0.7.2</version>  <!-- ${NEXT_VERSION_FLAG} -->
+      <version>0.8.0</version>  <!-- ${NEXT_VERSION_FLAG} -->
     </dependency>
 
     <dependency>

spark-bigtable-core/src/main/scala/com/google/cloud/spark/bigtable/BigtableDefaultSource.scala

@@ -33,7 +33,7 @@ import org.apache.spark.sql.{DataFrame, SQLContext, SaveMode, Row => SparkRow}
 import org.apache.yetus.audience.InterfaceAudience
 
 object UserAgentInformation {
-  val CONNECTOR_VERSION = "0.7.2" // ${NEXT_VERSION_FLAG}
+  val CONNECTOR_VERSION = "0.8.0" // ${NEXT_VERSION_FLAG}
   val DATA_SOURCE_VERSION = "V1"
   val DATAFRAME_TEXT = "DF/" + DATA_SOURCE_VERSION
   val RDD_TEXT = "RDD/"

spark-bigtable-core/src/main/scala/com/google/cloud/spark/bigtable/datasources/config/client/UserAgentConfig.scala

@@ -7,7 +7,7 @@ import com.google.common.collect.ImmutableMap
 import io.grpc.internal.GrpcUtil.USER_AGENT_KEY
 
 object UserAgentConfig {
-  private val CONNECTOR_VERSION = "0.7.2" // ${NEXT_VERSION_FLAG}
+  private val CONNECTOR_VERSION = "0.8.0" // ${NEXT_VERSION_FLAG}
   private val CONNECTOR_ID = "spark-bigtable"
 
   def apply(): UserAgentConfig = new UserAgentConfig(

spark-bigtable_2.12/pom.xml

@@ -21,14 +21,14 @@
   <parent>
     <groupId>com.google.cloud.spark.bigtable</groupId>
     <artifactId>spark-bigtable-connector</artifactId>
-    <version>0.7.2</version> <!-- ${NEXT_VERSION_FLAG} -->
+    <version>0.8.0</version> <!-- ${NEXT_VERSION_FLAG} -->
     <relativePath>../pom.xml</relativePath>
   </parent>
 
   <groupId>com.google.cloud.spark.bigtable</groupId>
   <artifactId>spark-bigtable_2.12</artifactId>
   <name>Google Bigtable - Apache Spark Connector</name>
-  <version>0.7.2</version> <!-- ${NEXT_VERSION_FLAG} -->
+  <version>0.8.0</version> <!-- ${NEXT_VERSION_FLAG} -->
 
   <properties>
     <scala.version>2.12.18</scala.version>

spark-bigtable_2.13/pom.xml

@@ -21,14 +21,14 @@
   <parent>
     <groupId>com.google.cloud.spark.bigtable</groupId>
     <artifactId>spark-bigtable-connector</artifactId>
-    <version>0.7.2</version> <!-- ${NEXT_VERSION_FLAG} -->
+    <version>0.8.0</version> <!-- ${NEXT_VERSION_FLAG} -->
     <relativePath>../pom.xml</relativePath>
   </parent>
 
   <groupId>com.google.cloud.spark.bigtable</groupId>
   <artifactId>spark-bigtable_2.13</artifactId>
   <name>Google Bigtable - Apache Spark Connector for Scala 2.13</name>
-  <version>0.7.2</version> <!-- ${NEXT_VERSION_FLAG} -->
+  <version>0.8.0</version> <!-- ${NEXT_VERSION_FLAG} -->
 
   <properties>
     <scala.version>2.13.14</scala.version>