</mime-type>
  <mime-type type="application/vnd.uplanet.alert"/>
  <mime-type type="application/vnd.uplanet.alert-wbxml"/>
  <mime-type type="application/vnd.uplanet.bearer-choice"/>
  <mime-type type="application/vnd.uplanet.bearer-choice-wbxml"/>
  <mime-type type="application/vnd.uplanet.cacheop"/>
  <mime-type type="application/vnd.uplanet.cacheop-wbxml"/>
  <mime-type type="application/vnd.uplanet.channel"/>

        /**
         * 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:

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");

            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 {

        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));
        }

            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());

            if (!dfos.isInMemory()) {
                tempFile = dfos.getFile();
            }

            try (Reader reader = new InputStreamReader(getContentStream(dfos), enc)) {
                if (normalizeText) {
                    return TextUtil.normalizeText(reader)
                            .initialCapacity(initialBufferSize)
                            .maxAlphanumTermSize(maxAlphanumTermSize)

            final BufferedReader reader = new BufferedReader(new InputStreamReader(new BOMInputStream(stream), charsetName));

            String line;
            final RobotsTxt robotsTxt = new RobotsTxt();
            final List<Directive> currentDirectiveList = new ArrayList<>();
            boolean isGroupRecordStarted = false;
            while ((line = reader.readLine()) != null) {