> ## Documentation Index
> Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Custom Spark Jobs

export const schema = {
  "type": "object",
  "title": "Custom Spark Job",
  "description": "Runs a custom Java or Scala class on the Fusion Spark cluster using a JAR uploaded to the blob store. Specify the fully-qualified class name and optionally provide an inline Scala script or additional arguments. Use this job for custom data processing workflows such as index maintenance, analytics, and batch transformations.",
  "required": ["id", "klassName", "type"],
  "properties": {
    "id": {
      "type": "string",
      "title": "Spark Job ID",
      "description": "Sets the unique identifier for this Spark job, used to reference it in the API. Allowed characters: a-z, A-Z, dash (`-`), and underscore (`_`). Must start with a letter.",
      "maxLength": 63,
      "pattern": "[a-zA-Z][_\\-a-zA-Z0-9]*[a-zA-Z0-9]?"
    },
    "sparkConfig": {
      "type": "array",
      "title": "Spark Settings",
      "description": "Sets Spark configuration key-value pairs applied to this job's execution context. Use entries like `spark.executor.memory=4g` to tune resource allocation beyond cluster defaults.",
      "hints": ["advanced"],
      "items": {
        "type": "object",
        "required": ["key"],
        "properties": {
          "key": {
            "type": "string",
            "title": "Parameter Name"
          },
          "value": {
            "type": "string",
            "title": "Parameter Value"
          }
        }
      }
    },
    "klassName": {
      "type": "string",
      "title": "Class name",
      "description": "Specifies the fully-qualified Java or Scala class name to invoke when running this Spark job. The class must be present in a JAR uploaded to the blob store and implement the expected entry point interface."
    },
    "submitArgs": {
      "type": "array",
      "title": "Script args",
      "description": "Sets additional command-line arguments passed to the application when the Spark job runs. These arguments are available to the main class at runtime via the standard `args` parameter.",
      "items": {
        "type": "string"
      }
    },
    "script": {
      "type": "string",
      "title": "Scala Script",
      "description": "Sets an optional inline Scala script executed by this Spark job. Provide this field for lightweight scripting use cases. Use `klassName` with a compiled JAR for production workloads.",
      "hints": ["code/scala", "lengthy", "advanced"]
    },
    "type": {
      "type": "string",
      "title": "Spark Job Type",
      "enum": ["custom_spark_scala_job"],
      "default": "custom_spark_scala_job",
      "hints": ["readonly"]
    }
  },
  "additionalProperties": true,
  "category": "Other",
  "categoryPriority": 1
};

export const SchemaParamFields = ({schema}) => {
  const sanitize = str => {
    if (typeof str !== "string") return str;
    return str.replace(/^"(.*)"$/s, "$1").replace(/\\/g, "").replace(/"/g, "'");
  };
  const renderMd = str => {
    const s = sanitize(str);
    const text = (/[.!?]\)*$/).test(s) ? s : `${s}.`;
    return text.split(/(\*\*[^*]+\*\*|_[^_]+_|`[^`]+`)/g).map((part, i) => {
      if (part.startsWith("**")) return <strong key={i}>{part.slice(2, -2)}</strong>;
      if (part.startsWith("_")) return <em key={i}>{part.slice(1, -1)}</em>;
      if (part.startsWith("`")) return <code key={i}>{part.slice(1, -1)}</code>;
      return part;
    });
  };
  const {description, properties = {}, required: requiredProps = []} = schema;
  const visibleProps = useMemo(() => Object.entries(properties).filter(([, prop]) => !prop.hints?.includes("hidden")), [properties]);
  const renderProp = ([name, prop]) => {
    const isRequired = requiredProps.includes(name);
    const hasDefault = prop.default !== undefined;
    const rawDefault = prop.default;
    const hints = prop.hints || [];
    const isComplexDefault = hasDefault && (typeof rawDefault === "object" || typeof rawDefault === "string" && (rawDefault.length > 20 || rawDefault.includes('"')));
    const postBadges = [];
    if (prop.title) {
      postBadges.push(<><span className="text-stone-400 dark:text-stone-500">API property: </span>{name}</>);
    }
    const constraints = [];
    if (prop.minimum !== undefined && prop.maximum !== undefined) {
      constraints.push(`Range: ${prop.minimum} – ${prop.maximum}`);
    } else if (prop.minimum !== undefined) {
      constraints.push(`Min: ${prop.minimum}`);
    } else if (prop.maximum !== undefined) {
      constraints.push(`Max: ${prop.maximum}`);
    }
    if (prop.minLength !== undefined && prop.maxLength !== undefined) {
      constraints.push(`Length: ${prop.minLength} – ${prop.maxLength}`);
    } else if (prop.minLength !== undefined) {
      constraints.push(`Min length: ${prop.minLength}`);
    } else if (prop.maxLength !== undefined) {
      constraints.push(`Max length: ${prop.maxLength}`);
    }
    const fieldProps = {
      key: name,
      body: prop.title || name,
      type: prop.type,
      ...postBadges.length > 0 && ({
        post: postBadges
      }),
      ...isRequired && ({
        required: true
      }),
      ...!isComplexDefault && hasDefault ? {
        default: sanitize(String(rawDefault))
      } : {}
    };
    const isObject = prop.type === "object" && prop.properties;
    const isArrayOfObjects = prop.type === "array" && prop.items?.type === "object" && prop.items.properties;
    return <ParamField {...fieldProps}>
        {prop.description && <p>{renderMd(prop.description)}</p>}

        {prop.enum && <p>
            Allowed values: 
            {prop.enum.map((v, i) => <>{i > 0 && ", "}<code key={i}>{String(v)}</code></>)}
          </p>}

        {constraints.length > 0 && <p className="text-stone-500 dark:text-stone-400 text-sm">
            {constraints.join(" · ")}
          </p>}

        {isComplexDefault && <div className="flex">
            <p>
              <strong>Default:</strong>
            </p>
            <pre className="!my-0">
              <code>
                {JSON.stringify(rawDefault, null, 2)}
              </code>
            </pre>
          </div>}

        {isArrayOfObjects && <Expandable title="item properties">
            <SchemaParamFields schema={{
      properties: prop.items.properties,
      required: prop.items.required
    }} />
          </Expandable>}

        {isObject && <Expandable title="properties">
            <SchemaParamFields schema={{
      properties: prop.properties,
      required: prop.required
    }} />
          </Expandable>}
      </ParamField>;
  };
  return <div>
      {description && <p>{renderMd(description)}</p>}

      {visibleProps.map(renderProp)}
    </div>;
};

export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => {
  const [isLoaded, setIsLoaded] = useState(false);
  useEffect(() => {
    const timer = setTimeout(() => {
      setIsLoaded(true);
    }, 500);
    return () => clearTimeout(timer);
  }, []);
  return <div className="lw-template-container">
      <Card title={title} icon={icon}>
        {isLoaded && <span dangerouslySetInnerHTML={{
    __html: `<lw-template id="a029c1a9-28be-427e-b0e1-5d918920246a"></lw-template
            >`
  }} />}
        <Link href={linkHref} className="agent-studio-link text-left text-gray-600 gap-2 dark:text-gray-400 text-sm font-medium flex flex-row items-center hover:text-primary dark:hover:text-primary-light group-hover:text-primary group-hover:dark:text-primary-light">Powered by Lucidworks Agent Studio</Link>
      </Card>
    </div>;
};

[localhost link]: http://localhost:3000/docs/5/fusion/reference/config-ref/jobs/custom-spark-job

[mintlify link]: https://doc.lucidworks.com/docs/5/fusion/reference/config-ref/jobs/custom-spark-job

[old doc.lw link]: https://doc.lucidworks.com/fusion/5.9/383

Custom Spark jobs run Java ARchive (JAR) files uploaded to the [blob store](/docs/5/fusion/getting-data-in/blob-storage).

To configure a custom Spark job, sign in to Fusion and click **Collections > Jobs**. Then click **Add+** and in the Custom and Other Jobs section, select **Custom Spark Job**. You can enter basic and advanced parameters to configure the job. If the field has a default value, it is populated when you click to add the job.

<LwTemplate />

## Basic parameters

<Note>
  To enter advanced parameters in the UI, click **Advanced**. Those parameters are described in [the advanced parameters section](#advanced-parameters).
</Note>

* **Spark job ID.** The unique ID for the Spark job that references this job in the API. This is the `id` field in the configuration file. Required field.
* **Class name.** The fully-qualified name of the Java/Scala class to invoke for this job. This is the `klassName` field in the configuration file. Required field.
* **Script ARGs.** The arguments (ARGs), which are additional options to pass to the application when running this job. This is the `submitArgs` field in the configuration file. Optional field.

## Advanced parameters

If you click the **Advanced** toggle, the following optional fields are displayed in the UI.

* **Spark Settings.** This section lets you enter `parameter name:parameter value` options to configure Spark settings. This is the `sparkConfig` field in the configuration file.
* **Scala Script.** The value in this text field overrides running `className.main(args)` default behavior. This is the `script` field in the configuration file.

<Note>
  Alternatives to custom Spark jobs are [Custom Python Jobs](/docs/5/fusion/reference/config-ref/jobs/custom-python) and Scala [Script Jobs](/docs/5/fusion/reference/config-ref/jobs/script).
</Note>

## Configuration properties

<SchemaParamFields schema={schema} />