Stefan Wolf <******@****.***> 1633938695 +0200

 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */
    ExtractData getText(InputStream in, Map<String, String> params);

    /**

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.

            ReadingConverter readingConverter, Normalizer normalizer);

    /**
     * Parses a document and extracts suggest items based on the provided fields and converters.
     *
     * @param document The document to parse, represented as a map of field names to values.
     * @param fields The fields to extract from the document.
     * @param tagFieldNames The names of the fields that contain tags.

	line, col int
	Key       string `yaml:"key" json:"key"`
	Value     string `yaml:"value" json:"value"`
}

var _ yaml.Unmarshaler = &BatchJobKV{}

// UnmarshalYAML - BatchJobKV extends default unmarshal to extract line, col information.
func (kv *BatchJobKV) UnmarshalYAML(val *yaml.Node) error {
	type jobKV BatchJobKV
	var tmp jobKV
	err := val.Decode(&tmp)
	if err != nil {
		return err
	}
	*kv = BatchJobKV(tmp)

		Creds: credentials.NewStaticV4("access-key", "secret-key", ""),
	})
	if err != nil {
		log.Fatalln(err)
	}

	var opts minio.GetObjectOptions

	// Add extract header to request:
	opts.Set("x-minio-extract", "true")

	// Download API.md from the archive
	rd, err := s3Client.GetObject(context.Background(), "your-bucket", "path/to/file.zip/data.csv", opts)
	if err != nil {
		log.Fatalln(err)
	}

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.

        ByteBuffer bb = ByteBuffer.wrap(result).order(java.nio.ByteOrder.LITTLE_ENDIAN);

        long mostSig = guid.getMostSignificantBits();
        long leastSig = guid.getLeastSignificantBits();

        // Extract GUID components from UUID
        int data1 = (int) (mostSig >>> 32); // first 4 bytes
        short data2 = (short) (mostSig >>> 16); // next 2 bytes
        short data3 = (short) mostSig; // next 2 bytes

    signatureVersion: 'v4'
});

// List all contents stored in the zip archive
s3.listObjectsV2({Bucket : 'your-bucket', Prefix: 'path/to/file.zip/'}).
    on('build', function(req) { req.httpRequest.headers['X-Minio-Extract'] = 'true'; }).
    send(function(err, data) {
        if (err) {
            console.log("Error", err);
        } else {
            console.log("Success", data);
        }
    });

    public void test_field_name_extraction() {
        // Test that field names can be extracted from encoded strings
        String originalFieldName = "author";
        String encodedFieldName = BaseEncoding.base64().encode(originalFieldName.getBytes(StandardCharsets.UTF_8));
        String fullFieldName = Constants.FACET_FIELD_PREFIX + encodedFieldName;

        // Extract the encoded part