Securely connecting
siloed content to AI pipelines.

<!-- Add core connector API to your spring boot application -->
<dependency>
    <groupId>org.opencrawling</groupId>
    <artifactId>oc-core</artifactId>
    <version>1.0.0-SNAPSHOT</version>
</dependency>

<!-- Include FileSystem Repository Connector if required -->
<dependency>
    <groupId>org.opencrawling</groupId>
    <artifactId>oc-filesystem-repository-connector</artifactId>
    <version>1.0.0-SNAPSHOT</version>
</dependency>

// Implement RepositoryConnector interface to create custom sources
public class MyCustomRepositoryConnector implements RepositoryConnector {

    @Override
    public void connect(Map<String, String> configParams) throws RepositoryConnectionException {
        // Establish authentication with target repository
    }

    @Override
    public void scanDocuments(DocumentProcessor processor, JobContext context) {
        // Scan documents incrementally and dispatch to processor
        for (Document doc : fetchNewDocuments()) {
            processor.processDocument(
                doc.getId(),
                doc.getContentStream(),
                doc.getMetadata(),
                doc.getAcl() // Synchronize Access Control Lists!
            );
        }
    }
}