Filter example - binary document manipulation

package com.example.pluginexamples;

import com.funnelback.filter.api.filters.BytesDocumentFilter;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

import com.funnelback.filter.api.FilterContext;
import com.funnelback.filter.api.FilterResult;
import com.funnelback.filter.api.documents.NoContentDocument;
import com.funnelback.filter.api.documents.BytesDocument;
import com.funnelback.filter.api.filters.PreFilterCheck;

import java.util.Base64;

public class DocumentFilterBinaryManipulation implements BytesDocumentFilter {
/*
 * This example filter Base64 decodes documents
 */
    private static final Logger log = LogManager.getLogger(DocumentFilterBinaryManipulation.class);

    @Override
    public PreFilterCheck canFilter(NoContentDocument noContentDocument, FilterContext filterContext) {
        // Pre filter checks could be done here, we assume all documents are
        // Base64 encoded.
        return PreFilterCheck.ATTEMPT_FILTER;
    }

    @Override
    public FilterResult filterAsBytesDocument(BytesDocument document, FilterContext context) {
        // Gets the document contents as raw bytes and decode the bytes
        byte[] decodedBytes = Base64.getDecoder().decode(document.getCopyOfContents());

        log.debug("Decoding resulted in a " + decodedBytes.length + " byte content for: " + document.getURI());

        // Make a clone of the document updating the content to be the decoded bytes.
        // We keep the existing document type and charset.
        BytesDocument newDocument = document.cloneWithContent(
                document.getDocumentType(),
                document.getCharset(),
                decodedBytes);
        return FilterResult.of(newDocument);
    }
}

package com.example.pluginexamples;

import org.junit.Assert;
import org.junit.Test;

import com.funnelback.filter.api.DocumentType;
import com.funnelback.filter.api.FilterResult;
import com.funnelback.filter.api.documents.BytesDocument;
import com.funnelback.filter.api.mock.MockDocuments;
import com.funnelback.filter.api.mock.MockFilterContext;

import static java.nio.charset.StandardCharsets.UTF_8;
import java.util.Optional;

public class DocumentFilterBinaryManipulationTest {

    @Test
    public void simpleDecodeTest() throws Exception {
        MockFilterContext mockContext = MockFilterContext.getEmptyContext();

        // Create the input document with base 64 encoded bytes.
        BytesDocument doc = MockDocuments.mockEmptyByteDoc()
                .cloneWithContent(
                        DocumentType.MIME_UNKNOWN,
                        Optional.empty(),
                        "SGVsbG8gRnVubmVsYmFjaw==".getBytes(UTF_8));

        // Create and run the filter, getting the filtered result.
        DocumentFilterBinaryManipulation underTest = new DocumentFilterBinaryManipulation();

        FilterResult res = underTest.filter(doc, mockContext);

        // Get the resulting document from filtering,
        // there should be exactly one document.
        BytesDocument document = (BytesDocument) res
                .getFilteredDocuments().get(0);

        // Convert the document content to a string.
        String decodedString = new String(document.getCopyOfContents(), UTF_8);

        // Check that we correctly decoded the document.
        Assert.assertEquals(
                "The content was not correctly decoded",
                "Hello Funnelback",
                decodedString);
    }
}