> ## Documentation Index
> Fetch the complete documentation index at: https://docs.open-metadata.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Run the Salesforce Data360 Connector Externally

> Use YAML to configure the Salesforce Data360 database connector for metadata ingestion of data spaces, objects, and fields.

export const CodePanel = ({children, fileName = 'config.yaml', showLineNumbers = false}) => {
  const codePanelRef = useRef(null);
  const codeContentRef = useRef(null);
  const isProgrammaticScroll = useRef(false);
  const hoverTimeout = useRef(null);
  useEffect(() => {
    let tries = 0;
    const wrapLines = () => {
      const root = codeContentRef.current;
      if (!root) return;
      const pres = Array.from(root.querySelectorAll('pre'));
      if (!pres.length) {
        if (tries++ < 20) requestAnimationFrame(wrapLines);
        return;
      }
      let globalLine = 1;
      pres.forEach(pre => {
        const code = pre.querySelector('code') || pre;
        if (!code || code.dataset.wrapped === 'true') return;
        const raw = code.textContent || '';
        let lines = raw.split('\n');
        while (lines[0] === '') lines.shift();
        while (lines[lines.length - 1] === '') lines.pop();
        code.innerHTML = lines.map(line => {
          const ln = globalLine++;
          const num = showLineNumbers ? `<span class="line-number">${ln}</span>` : '';
          const safe = line.replace(/</g, '&lt;').replace(/>/g, '&gt;') || ' ';
          return `<span class="code-line" data-line="${ln}">${num}${safe}</span>`;
        }).join('');
        code.dataset.wrapped = 'true';
      });
    };
    wrapLines();
  }, [children, showLineNumbers]);
  useEffect(() => {
    const panel = codePanelRef.current;
    const content = codeContentRef.current;
    if (!panel || !content) return;
    const waitForLines = () => {
      const codeLines = content.querySelectorAll('.code-line');
      if (!codeLines.length) {
        requestAnimationFrame(waitForLines);
        return;
      }
      setupHighlighting(codeLines);
    };
    const setupHighlighting = codeLines => {
      const layout = panel.closest('.split-layout');
      const sections = layout.querySelectorAll('.content-section');
      const parseLines = str => {
        if (!str) return [];
        const out = [];
        str.split(',').forEach(p => {
          if (p.includes('-')) {
            const [s, e] = p.split('-').map(Number);
            for (let i = s; i <= e; i++) out.push(i);
          } else {
            const n = Number(p);
            if (!isNaN(n)) out.push(n);
          }
        });
        return out;
      };
      const clearHighlight = () => {
        codeLines.forEach(l => l.classList.remove('highlighted'));
      };
      const highlight = lines => {
        clearHighlight();
        lines.forEach(n => {
          const el = content.querySelector(`.code-line[data-line="${n}"]`);
          if (el) el.classList.add('highlighted');
        });
      };
      const scrollToLines = lines => {
        if (!lines.length) return;
        const first = lines[0];
        const targetLine = lines.length > 1 ? first : lines[0];
        const el = content.querySelector(`.code-line[data-line="${targetLine}"]`);
        if (!el) return;
        isProgrammaticScroll.current = true;
        const containerRect = content.getBoundingClientRect();
        const elRect = el.getBoundingClientRect();
        const offset = elRect.top - containerRect.top + content.scrollTop;
        const TOP_PADDING = 16;
        content.scrollTo({
          top: Math.max(offset - TOP_PADDING, 0),
          behavior: 'smooth'
        });
        setTimeout(() => {
          isProgrammaticScroll.current = false;
        }, 200);
      };
      const activate = (section, scroll) => {
        if (section.classList.contains('active')) return;
        sections.forEach(s => s.classList.remove('active'));
        section.classList.add('active');
        const lines = parseLines(section.dataset.lines);
        highlight(lines);
        if (scroll) scrollToLines(lines);
      };
      const observer = new IntersectionObserver(entries => {
        if (isProgrammaticScroll.current) return;
        entries.forEach(e => {
          if (e.isIntersecting) activate(e.target, false);
        });
      }, {
        threshold: 0.3,
        rootMargin: '-80px 0px -40% 0px'
      });
      sections.forEach(section => {
        observer.observe(section);
        section.addEventListener('click', () => activate(section, true));
        section.addEventListener('mouseenter', () => {
          clearTimeout(hoverTimeout.current);
          hoverTimeout.current = setTimeout(() => activate(section, true), 80);
        });
      });
      if (sections[0]) activate(sections[0], false);
    };
    waitForLines();
  }, []);
  const handleCopy = e => {
    const btn = e.currentTarget;
    const codeLines = codeContentRef.current?.querySelectorAll('.code-line');
    if (!codeLines || codeLines.length === 0) return;
    const text = Array.from(codeLines).map(line => {
      const clone = line.cloneNode(true);
      const lineNumber = clone.querySelector('.line-number');
      if (lineNumber) lineNumber.remove();
      return clone.textContent;
    }).join('\n');
    if (!text) return;
    navigator.clipboard.writeText(text).then(() => {
      btn.dataset.copied = 'true';
      setTimeout(() => btn.dataset.copied = 'false', 1500);
    });
  };
  return <div className="code-panel" ref={codePanelRef}>
      <div className="code-header">
        {fileName}
        <button className="copy-btn" aria-label="Copy full code" data-copied="false" onClick={handleCopy}>
          <svg className="icon-copy" viewBox="0 0 15 16" fill="currentColor">
            <path d="M10.113 3.124H2.205C1.463 3.124.86 3.655.86 4.31v10.005c0 .654.603 1.186 1.345 1.186h7.908c.742 0 1.345-.532 1.345-1.186V4.31c0-.655-.606-1.186-1.345-1.186Z" />
            <path d="M13.138.5H5.229c-.742 0-1.344.531-1.344 1.186 0 .23.209.414.47.414s.47-.184.47-.414c0-.197.182-.357.404-.357h7.909c.223 0 .404.16.404.357V11.69c0 .196-.181.356-.404.356-.262 0-.47.184-.47.415 0 .23.208.415.47.415.742 0 1.344-.532 1.344-1.186V1.686C14.482 1.03 13.88.5 13.138.5Z" />
          </svg>

          <svg className="icon-check" viewBox="0 0 20 20" fill="currentColor">
            <path fillRule="evenodd" d="M16.707 5.293a1 1 0 010 1.414l-7.25 7.25a1 1 0 01-1.414 0l-3.25-3.25a1 1 0 011.414-1.414l2.543 2.543 6.543-6.543a1 1 0 011.414 0z" clipRule="evenodd" />
          </svg>
        </button>
      </div>

      <div className="code-content" ref={codeContentRef}>
        {children}
      </div>
    </div>;
};

export const ContentSection = ({id, title, lines, children}) => <div className="content-section" data-content-id={id} data-lines={lines}>
    {title && <h4>{title}</h4>}
    {children}
  </div>;

export const ContentPanel = ({children}) => <div className="content-panel">{children}</div>;

export const CodePreview = ({children}) => {
  const [instanceId] = useState(() => `preview-${Math.random().toString(36).slice(2)}`);
  useEffect(() => {
    const nav = document.querySelector('nav') || document.querySelector('header') || document.querySelector('[class*="nav"]');
    if (nav) {
      document.documentElement.style.setProperty('--navbar-height', `${nav.offsetHeight}px`);
    }
  }, []);
  return <div className="split-layout" data-preview-id={instanceId}>
      {children}
    </div>;
};

export const ConnectorDetailsHeader = ({name, icon, stage, availableFeatures, unavailableFeatures = [], availableFeaturesCollate = []}) => {
  const showSubHeading = availableFeatures?.length > 0 || unavailableFeatures?.length > 0 || availableFeaturesCollate?.length > 0;
  const totalAvailableFeatures = [...availableFeatures || [], ...availableFeaturesCollate || []];
  return <div className="container">
      <div className="Heading">
        <div className="flex items-center gap-3">
          {icon && <div className="IconContainer">
              <img src={icon} alt={name} noZoom className="ConnectorIcon" />
            </div>}
          <h1 className="ConnectorName">{name}</h1>
          <span className={`StageBadge ${stage === 'PROD' ? 'prod' : 'beta'}`}>
            {stage}
          </span>
        </div>
      </div>
      {showSubHeading && <div className="SubHeading">
          <div className="FeaturesHeading">Feature List</div>
          <div className="FeaturesList">
            {totalAvailableFeatures.map(feature => <div className="FeatureTag AvailableFeature" key={feature}>
                ✓ {feature}
              </div>)}
            {unavailableFeatures.map(feature => <div className="FeatureTag UnavailableFeature" key={feature}>
                ✕ {feature}
              </div>)}
          </div>
        </div>}
    </div>;
};

<ConnectorDetailsHeader icon="/public/images/connectors/data360.png" name="Salesforce Data360" stage="BETA" availableFeatures={["Metadata", "Tags"]} unavailableFeatures={["Query Usage", "Data Profiler", "Data Quality", "dbt", "Lineage", "Column-level Lineage", "Sample Data", "Auto-Classification", "Stored Procedures", "Owners"]} />

Use this guide to configure the Salesforce Data360 connector.

Configure and run Salesforce Data360 metadata workflows externally with YAML:

* [Requirements](#requirements)
* [Metadata Ingestion](#metadata-ingestion)

## How to Run the Connector Externally

To run the Ingestion via the UI you'll need to use the OpenMetadata Ingestion Container, which comes shipped with
custom Airflow plugins to handle the workflow deployment.

If, instead, you want to manage your workflows externally on your preferred orchestrator, you can check
the following docs to run the Ingestion Framework **anywhere**.

<Columns cols={2}>
  <Card title="External Schedulers" href="/v2.1.x-SNAPSHOT/deployment/ingestion">
    Get more information about running the Ingestion Framework Externally
  </Card>
</Columns>

## Requirements

OpenMetadata connects to Salesforce Data360 through the Salesforce REST API using a **connected app** that authenticates with the OAuth 2.0 client credentials flow. You'll need:

* A Salesforce connected app configured for the OAuth 2.0 client credentials flow. The app provides the **Consumer Key** and **Consumer Secret**.
* The Data360 (Data Cloud) API scopes — `cdp_query_api` and `cdp_profile_api` — granted to that connected app.
* An integration user with permission to view the data spaces and objects you want to ingest: Data Lake Objects, Data Model Objects, and Calculated Insights.

### Python Requirements

Use a Python version supported by the `openmetadata-ingestion` package that matches your OpenMetadata server. To find the supported range for your release, check the `Requires-Python` metadata of that release’s ingestion package.

To run the Salesforce Data360 ingestion, install:

```bash theme={null}
pip3 install "openmetadata-ingestion[data360]"
```

## Metadata Ingestion

All connectors are defined as JSON Schemas. See the
[Salesforce Data360 connection JSON Schema](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/entity/services/connections/database/data360Connection.json)
for the structure used to create a connection to Salesforce Data360.
To create and run a metadata ingestion workflow, create a YAML configuration.
The configuration connects to the source, processes entities if needed, and reaches the OpenMetadata server.
The workflow is modeled around the following
[JSON Schema](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/metadataIngestion/workflow.json).

### 1. Define the YAML Config

This is a sample config for Salesforce Data360:

<CodePreview>
  <ContentPanel>
    <ContentSection id={1} title="Source Configuration" lines="1-6">
      Configure the source type and service name for your Salesforce Data360 connector.
    </ContentSection>

    <ContentSection id={2} title="Consumer Key" lines="7">
      **consumerKey**: The consumer key from your Salesforce connected app. This is the client identifier used for OAuth authentication.
    </ContentSection>

    <ContentSection id={3} title="Consumer Secret" lines="8">
      **consumerSecret**: The consumer secret from your Salesforce connected app. This is the client secret used for OAuth authentication.
    </ContentSection>

    <ContentSection id={4} title="Salesforce API Version" lines="9">
      **salesforceApiVersion**: The Salesforce REST API version to call. Defaults to `63.0`. Change this only if your Salesforce org requires a different version.
    </ContentSection>

    <ContentSection id={5} title="Salesforce Domain" lines="10">
      **salesforceDomain**: The domain of your Salesforce instance, used to build the login URL. Defaults to `login`. Use `test` for a sandbox, or your My Domain subdomain for a custom domain.
    </ContentSection>

    <ContentSection id={6} title="Pagination Limit" lines="11">
      **paginationLimit**: How many Data360 objects to request per page when listing data spaces and objects. Defaults to `10`. Valid values are `1`–`100`.
    </ContentSection>

    <ContentSection id={7} title="Source Config" lines="12-64">
      The `sourceConfig` is defined [here](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/metadataIngestion/databaseServiceMetadataPipeline.json):

      * **markDeletedTables**: To flag tables as soft-deleted if they are not present anymore in the source system.
      * **markDeletedStoredProcedures**: Optional configuration to soft delete stored procedures in OpenMetadata if the source stored procedures are deleted. Also, if the stored procedure is deleted, all the associated entities like lineage, etc., with that stored procedure will be deleted.
      * **markDeletedSchemas**: Optional configuration to soft delete schemas stored in OpenMetadata if the source schema is deleted. Setting this flag to true will only keep filtered schemas and delete any other schemas that do not match schemaFilterPattern or do not exist at source.
      * **markDeletedDatabases**: Additional optional configuration for soft deletion, providing a granular option to select which particular entities should be deleted.
      * **includeTables**: Set to `true` or `false` to ingest table data. Default is `true`.
      * **includeViews**: Set to `true` or `false` to ingest view definitions.
      * **includeTags**: Optional configuration to toggle the tags ingestion.
      * **includeOwners**: Set the **Include Owners** toggle to control whether to include owners to the ingested entity if the owner email matches with a user stored in the OM server as part of metadata ingestion. If the ingested entity already exists and has an owner, the owner will not be overwritten.
      * **ownerConfig**: Advanced, hierarchical configuration for assigning owners to databases, schemas, and tables during ingestion, with per-entity mappings and inheritance. For more information, see [Hierarchical Owner Configuration](/connectors/ingestion/workflows/metadata/hierarchical-owner-configuration).
      * **includeStoredProcedures**: Optional configuration to toggle the Stored Procedures ingestion.
      * **includeDDL**: Optional configuration to toggle the DDL Statements ingestion.
      * **overrideMetadata** *(boolean)*: Set the **Override Metadata** toggle to control whether to override the existing metadata in the OpenMetadata server with the metadata fetched from the source. If the toggle is set to true, the metadata fetched from the source will override the existing metadata in the OpenMetadata server. If the toggle is set to false, the metadata fetched from the source will not override the existing metadata in the OpenMetadata server. This is applicable for fields like description, tags, owner, and displayName.
      * **queryLogDuration**: Configuration to tune how far we want to look back in query logs to process Stored Procedures results.
      * **queryParsingTimeoutLimit**: Configuration to set the timeout for parsing the query in seconds.
      * **useFqnForFiltering**: Regex will be applied on the fully qualified name (for example, `service_name.db_name.schema_name.table_name`) instead of the raw name (for example, `table_name`).
      * **databaseFilterPattern**, **schemaFilterPattern**: Note that the filter supports regex as include or exclude. You can find examples [here](/connectors/ingestion/workflows/metadata/filter-patterns/database).
      * **tableFilterPattern**: Note that the filter supports regex as include or exclude. You can find examples [here](/connectors/ingestion/workflows/metadata/filter-patterns/table).
      * **threads (beta)**: The number of threads to use when extracting the metadata using multithreading.
      * **databaseMetadataConfigType** *(string)*: Database Source Config Metadata Pipeline type.
      * **incremental (beta)**: Incremental Extraction configuration. Currently implemented for [BigQuery](/connectors/ingestion/workflows/metadata/incremental-extraction/bigquery), [Redshift](/connectors/ingestion/workflows/metadata/incremental-extraction/redshift), and [Snowflake](/connectors/ingestion/workflows/metadata/incremental-extraction/snowflake).
    </ContentSection>

    <ContentSection id={8} title="Sink Configuration" lines="65-67">
      To send the metadata to OpenMetadata, it needs to be specified as `type: metadata-rest`.
    </ContentSection>

    <ContentSection id={9} title="Workflow Configuration" lines="68-84">
      The main property here is `openMetadataServerConfig`, where you can define the host and security provider of your OpenMetadata installation.

      * **loggerLevel**: Specify the logger level depending on your needs. If you are troubleshooting an ingestion, use `DEBUG` for more detailed traces.
      * **JWT token**: JWT tokens allow clients to authenticate against the OpenMetadata server. See [Enable JWT Tokens](/deployment/security/enable-jwt-tokens) and [JWT Troubleshooting](/deployment/security/jwt-troubleshooting) for more information.
      * **storeServiceConnection**: If set to `true` (default), sensitive information is stored encrypted with the Fernet Key or externally if you have configured a [Secrets Manager](/deployment/secrets-manager). If set to `false`, the service is created, but the service connection information is only used by the Ingestion Framework at runtime and is not sent to the OpenMetadata server.
      * **SSL configuration**: If you have added SSL to the [OpenMetadata server](/deployment/security/enable-ssl), configure the certificates for ingestion. Set `verifySSL` to `ignore`, or set it to `validate` and provide `sslConfig.caCertificate` with a local path to the server certificate. See [SSL Troubleshooting](/deployment/security/enable-ssl/ssl-troubleshooting) for more information.
      * **ingestionPipelineFQN**: Fully qualified name of the ingestion pipeline, used to identify the current ingestion pipeline.
    </ContentSection>
  </ContentPanel>

  <CodePanel fileName="data360_config.yaml">
    ```yaml theme={null}
    source:
      type: data360
      serviceName: local_data360
      serviceConnection:
        config:
          type: Data360
          consumerKey: <consumer key>  # REQUIRED
          consumerSecret: <consumer secret>  # REQUIRED
          # salesforceApiVersion: "63.0"
          # salesforceDomain: login
          # paginationLimit: 10
    ```

    ```yaml theme={null}
      sourceConfig:
        config:
          type: DatabaseMetadata
          markDeletedTables: true
          markDeletedStoredProcedures: true
          markDeletedSchemas: true
          markDeletedDatabases: true
          includeTables: true
          includeViews: true
          # includeTags: true
          # includeOwners: false
          # ownerConfig:
          #   default: data-platform-team
          #   database:
          #     database1: owner1
          #   databaseSchema:
          #     database1.schema1: owner1
          #   table:
          #     database1.schema1.table1: owner1
          #   enableInheritance: true
          # includeStoredProcedures: true
          # includeDDL: true
          # overrideMetadata: false
          # queryLogDuration: 1
          # queryParsingTimeoutLimit: 300
          # useFqnForFiltering: false
          # threads: 1
          # databaseMetadataConfigType: ()
          # incremental:
          #   enabled: true
          #   lookbackDays: 7
          #   safetyMarginDays: 1
          # databaseFilterPattern:
          #   includes:
          #     - database1
          #     - database2
          #   excludes:
          #     - database3
          #     - database4
          # schemaFilterPattern:
          #   includes:
          #     - schema1
          #     - schema2
          #   excludes:
          #     - schema3
          #     - schema4
          # tableFilterPattern:
          #   includes:
          #     - users
          #     - type_test
          #   excludes:
          #     - table3
          #     - table4
    ```

    ```yaml theme={null}
    sink:
      type: metadata-rest
      config: {}
    ```

    ```yaml theme={null}
    workflowConfig:
      loggerLevel: INFO  # DEBUG, INFO, WARNING or ERROR
      openMetadataServerConfig:
        hostPort: "http://localhost:8585/api"
        authProvider: openmetadata
        securityConfig:
          jwtToken: "{bot_jwt_token}"
        ## Store the service Connection information
        storeServiceConnection: true  # false
        ## Secrets Manager Configuration
        # secretsManagerProvider: aws, azure or noop
        # secretsManagerLoader: airflow or env
        ## If SSL, fill the following
        # verifySSL: validate  # or ignore
        # sslConfig:
        #   caCertificate: /local/path/to/certificate
    # ingestionPipelineFQN: <service name>.<ingestion name> ## e.g., "my_redshift.metadata"
    ```
  </CodePanel>
</CodePreview>

### 2. Run with the CLI

First, we will need to save the YAML file. Afterward, and with all requirements installed, we can run:

```bash theme={null}
metadata ingest -c <path-to-yaml>
```

Note that from connector to connector, this recipe will always be the same. By updating the YAML configuration,
you will be able to extract metadata from different sources.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.