/**
 * <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents

import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>

            throw new CrawlingAccessException("Could not access " + uri, e);
        }

        return responseData;
    }

    /**
     * Processes access control entries (ACEs) for the given SMB1 file and adds them to the response data.
     *
     * @param responseData the response data to update
     * @param file the SMB1 file to process
     */

 * </p>
 *
 * <p>
 * The conversion process involves iterating through the input string, identifying Katakana characters,
 * and replacing them with their corresponding Alphabet representations based on the internal mapping.
 * When a Katakana character has multiple Alphabet representations, the converter generates multiple
 * possible readings.
 * </p>
 *
 * <p>

    System.out.println("Processed: " + processed + " URLs");
    Thread.sleep(5000);
}
```

## Contributing

We welcome contributions to Fess Crawler! Please follow these guidelines:

1. **Fork** the repository
2. **Create** a feature branch (`git checkout -b feature/amazing-feature`)
3. **Commit** your changes (`git commit -m 'Add amazing feature'`)

 * The {@link ContentWriter} functional interface is used to abstract the process of writing content to a writer.
 * </p>
 *
 * <p>
 * The class uses temporary files for processing large input streams and ensures that these files are deleted after
 * processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

    private static final Logger logger = LogManager.getLogger(TikaExtractor.class);

            throw new CrawlingAccessException("Could not access " + uri, e);
        }

        return responseData;
    }

    /**
     * Processes access control entries (ACEs) for the given SMB file and adds them to the response data.
     *
     * @param responseData the response data to update
     * @param file the SMB file to process
     */

            }
        } catch (final IOException e) {
            logger.warn("Failed to parse embedded documents.", e);
        }
    }

    /**
     * Processes embedded document names and extracts text from them.
     * @param embeddedFileNames the map of embedded file names to specifications
     * @param writer the writer to append extracted text to
     */

    }

    /**
     * Escapes wildcard characters in the given query string.
     *
     * This method replaces all occurrences of '*' with '\*' and
     * all occurrences of '?' with '\?' to ensure that these characters
     * are treated as literals rather than wildcard characters in queries.
     *
     * @param query the query string to escape
     * @return the escaped query string
     */

            throw new CrawlingAccessException("Could not access " + uri, e);
        }

        return responseData;
    }

    /**
     * Parses file ownership attributes and adds them to the response data.
     *
     * @param responseData the response data to add attributes to
     * @param file the file to parse attributes from
     * @return the file owner attribute view