import org.codelibs.core.lang.StringUtil;

/**
 * Represents an HTTP request header with a name and value.
 * This class is used to encapsulate the header information for HTTP requests.
 * It provides methods to get and set the name and value of the header,
 * as well as a method to validate the header.
 *
 * <p>Example usage:</p>
 * <pre>
 *     RequestHeader header = new RequestHeader("Content-Type", "application/json");

        /**
         * Constructor.
         * @param reader The reader.
         */
        public TextNormalizeContext(final Reader reader) {
            this.reader = reader;
        }

        /**
         * Executes the text processing operation on the provided reader.
         *
         * This method reads characters from the reader and processes them according to the following rules:

        addDocument(indexName, client, num);

        ESSourceReader reader = new ESSourceReader(client, settings, indexName);
        reader.setScrollSize(1);
        reader.setLimitDocNumPercentage("1%");
        int count = 0;
        Set<String> valueSet = Collections.synchronizedSet(new HashSet<>());
        Map<String, Object> source;
        while ((source = reader.read()) != null) {

 * String indexName = "your_index_name";
 *
 * ESSourceReader reader = new ESSourceReader(client, settings, indexName);
 * reader.setScrollSize(1000); // Set the scroll size
 * reader.setLimitOfDocumentSize(1024 * 1024); // Limit document size to 1MB
 * reader.setQuery(QueryBuilders.termQuery("field", "value")); // Set a query
 *
 * Map<String, Object> document;
 * while ((document = reader.read()) != null) {
 *     // Process the document

            return StringUtil.EMPTY;
        }
        try (final Reader reader = new StringReader(str)) {
            return normalizeText(reader, initialCapacity, maxAlphanumTermSize, maxSymbolTermSize, removeDuplication);
        } catch (final IOException e) {
            return StringUtil.EMPTY;
        }
    }

    public static String normalizeText(final Reader reader, final int initialCapacity, final int maxAlphanumTermSize,

            }
            responseData.setHttpStatusCode(httpStatusCode);
            for (final Header header : response.getAllHeaders()) {
                responseData.addMetaData(header.getName(), header.getValue());
            }
            responseData.setMimeType(contentType);
            final Header contentLengthHeader = response.getFirstHeader("Content-Length");
            if (contentLengthHeader == null) {

            }

            data.setContent(EntityUtils.toString(response.getEntity(), Charsets.UTF_8));
            final Header[] headers = response.getAllHeaders();
            for (final Header header : headers) {
                data.putValue(header.getName(), header.getValue());
            }
        } catch (final IOException e) {
            throw new ExtractException(e);
        } finally {

            final ExtractData data = new ExtractData(content != null ? content : StringUtil.EMPTY);
            final Enumeration<Header> headers = message.getAllHeaders();
            while (headers.hasMoreElements()) {
                final Header header = headers.nextElement();
                data.putValue(header.getName(), header.getValue());
            }
            putValue(data, "Content-ID", message.getContentID());

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.converter;

import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.TokenizerFactory;

        super();
    }

    @Override
    protected ExtractData createExtractData(final String content) {
        final DOMParser parser = getDomParser();
        try (final Reader reader = new StringReader(content)) {
            parser.parse(new InputSource(reader));
        } catch (final Exception e) {
            logger.warn("Failed to parse the content.", e);
            return new ExtractData(extractString(content));
        }