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,

        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));
        }

 * 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;

 */
package org.codelibs.fess.suggest.index.contents.querylog;

import java.io.Closeable;

/**
 * The {@code QueryLogReader} interface provides methods to read query logs and close the reader.
 * It extends the {@code Closeable} interface, ensuring that resources can be released when no longer needed.
 */
public interface QueryLogReader extends Closeable {
    /**
     * Reads a query log.

            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) {

            throw new SuggestIndexException("Failed to index from query_string.", e);
        }
    }

    /**
     * Indexes documents from a query log reader asynchronously.
     * @param queryLogReader The query log reader.
     * @param docPerReq The number of documents to process per request.
     * @param requestInterval The interval between requests.

        CountDownLatch latch = new CountDownLatch(1);
        AtomicInteger numObInputDoc = new AtomicInteger(0);
        ESSourceReader reader = new ESSourceReader(client, suggester.settings(), indexName);
        reader.setScrollSize(1000);

        suggester.indexer().indexFromDocument(() -> reader, 1000, () -> ThreadUtil.sleep(100)).then(response -> {
            numObInputDoc.set(response.getNumberOfInputDocs());

                } catch (InterruptedException e) {
                    Thread.currentThread().interrupt();
                }
            }
        });

        Thread reader = new Thread(new Runnable() {
            @Override
            public void run() {
                try {
                    statusSetLatch.countDown();

    <!-- TIKA-85: http://www.apache.org/dev/svn-eol-style.txt -->
    <glob pattern="INSTALL"/>
    <glob pattern="KEYS"/>
    <glob pattern="LICENSE"/>
    <glob pattern="NOTICE"/>
    <glob pattern="README"/>
    <glob pattern="abs-linkmap"/>
    <glob pattern="abs-menulinks"/>
    <glob pattern="*.aart"/>
    <glob pattern="*.ac"/>
    <glob pattern="*.am"/>
    <glob pattern="*.apt"/>