Merge pull request #314 from marklogic/release/2.4.1

Merge release/2.4.1 into master

Author: rjrudin

.env

@@ -1,3 +1,3 @@
 # Defines environment variables for docker-compose.
 # Can be overridden via e.g. `MARKLOGIC_TAG=latest-10.0 docker-compose up -d --build`.
-MARKLOGIC_TAG=latest
+MARKLOGIC_TAG=11.3.0-ubi

build.gradle

@@ -9,7 +9,7 @@ plugins {
 }
 
 group 'com.marklogic'
-version '2.4.0'
+version '2.4.1'
 
 java {
   // To support reading RDF files, Apache Jena is used - but that requires Java 11.
@@ -37,6 +37,14 @@ configurations {
   testImplementation.extendsFrom(compileOnly)
 }
 
+configurations.all {
+  // Ensures that slf4j-api 1.x does not appear on the Flux classpath in particular, which can lead to this
+  // issue - https://www.slf4j.org/codes.html#StaticLoggerBinder .
+  resolutionStrategy {
+    force "org.slf4j:slf4j-api:2.0.13"
+  }
+}
+
 dependencies {
   // This is compileOnly as any environment this is used in will provide the Spark dependencies itself.
   compileOnly ('org.apache.spark:spark-sql_2.12:' + sparkVersion) {
@@ -53,7 +61,10 @@ dependencies {
   }
 
   // Required for converting JSON to XML. Using 2.15.2 to align with Spark 3.5.3.
-  shadowDependencies "com.fasterxml.jackson.dataformat:jackson-dataformat-xml:2.15.2"
+  shadowDependencies ("com.fasterxml.jackson.dataformat:jackson-dataformat-xml:2.15.2") {
+    // Not needed, as the modules in this group that this dependency depends on are all provided by Spark.
+    exclude group: "com.fasterxml.jackson.core"
+  }
 
   // Need this so that an OkHttpClientConfigurator can be created.
   shadowDependencies 'com.squareup.okhttp3:okhttp:4.12.0'

docs/getting-started/jupyter.md

@@ -32,15 +32,15 @@ connector and also to initialize Spark:
 
 ```
 import os
-os.environ['PYSPARK_SUBMIT_ARGS'] = '--jars "/path/to/marklogic-spark-connector-2.4.0.jar" pyspark-shell'
+os.environ['PYSPARK_SUBMIT_ARGS'] = '--jars "/path/to/marklogic-spark-connector-2.4.1.jar" pyspark-shell'
 
 from pyspark.sql import SparkSession
 spark = SparkSession.builder.master("local[*]").appName('My Notebook').getOrCreate()
 spark.sparkContext.setLogLevel("WARN")
 spark
 ```
 
-The path of `/path/to/marklogic-spark-connector-2.4.0.jar` should be changed to match the location of the connector 
+The path of `/path/to/marklogic-spark-connector-2.4.1.jar` should be changed to match the location of the connector 
 jar on your filesystem. You are free to customize the `spark` variable in any manner you see fit as well. 
 
 Now that you have an initialized Spark session, you can run any of the examples found in the 

docs/getting-started/pyspark.md

@@ -29,7 +29,7 @@ shell by pressing `ctrl-D`.
 
 Run PySpark from the directory that you downloaded the connector to per the [setup instructions](setup.md):
 
-    pyspark --jars marklogic-spark-connector-2.4.0.jar
+    pyspark --jars marklogic-spark-connector-2.4.1.jar
 
 The `--jars` command line option is PySpark's method for utilizing Spark connectors. Each Spark environment should have
 a similar mechanism for including third party connectors; please see the documentation for your particular Spark

docs/getting-started/setup.md

@@ -31,10 +31,10 @@ have an instance of MarkLogic running, you can skip step 4 below, but ensure tha
 extracted directory contains valid connection properties for your instance of MarkLogic.
 
 1. From [this repository's Releases page](https://github.com/marklogic/marklogic-spark-connector/releases), select 
-   the latest release and download the `marklogic-spark-getting-started-2.4.0.zip` file.
+   the latest release and download the `marklogic-spark-getting-started-2.4.1.zip` file.
 2. Extract the contents of the downloaded zip file. 
 3. Open a terminal window and go to the directory created by extracting the zip file; the directory should have a 
-   name of "marklogic-spark-getting-started-2.4.0".
+   name of "marklogic-spark-getting-started-2.4.1".
 4. Run `docker-compose up -d` to start an instance of MarkLogic
 5. Ensure that the `./gradlew` file is executable; depending on your operating system, you may need to run
    `chmod 755 gradlew` to make the file executable.

examples/entity-aggregation/build.gradle

@@ -8,7 +8,7 @@ repositories {
 
 dependencies {
   implementation 'org.apache.spark:spark-sql_2.12:3.5.3'
-  implementation "com.marklogic:marklogic-spark-connector:2.4.0"
+  implementation "com.marklogic:marklogic-spark-connector:2.4.1"
   implementation "org.postgresql:postgresql:42.6.2"
 }
 

examples/getting-started/marklogic-spark-getting-started.ipynb

@@ -9,7 +9,7 @@
    "source": [
     "# Make the MarkLogic connector available to the underlying PySpark application.\n",
     "import os\n",
-    "os.environ['PYSPARK_SUBMIT_ARGS'] = '--jars \"marklogic-spark-connector-2.4.0.jar\" pyspark-shell'\n",
+    "os.environ['PYSPARK_SUBMIT_ARGS'] = '--jars \"marklogic-spark-connector-2.4.1.jar\" pyspark-shell'\n",
     "\n",
     "# Define the connection details for the getting-started example application.\n",
     "client_uri = \"spark-example-user:password@localhost:8003\"\n",

examples/java-dependency/build.gradle

@@ -8,7 +8,7 @@ repositories {
 
 dependencies {
   implementation 'org.apache.spark:spark-sql_2.12:3.5.3'
-  implementation 'com.marklogic:marklogic-spark-connector:2.4.0'
+  implementation 'com.marklogic:marklogic-spark-connector:2.4.1'
 }
 
 task runApp(type: JavaExec) {