/**
     * A string to replace &.
     */
    protected String ampersandStr = "_AMP_";

    /** Maximum number of duplicated paths to attempt */
    protected int maxDuplicatedPath = 100;

    /** Character set name for encoding file paths */
    protected String charsetName = Constants.UTF_8;

    /**
     * A directory to store downloaded files.
     */
    protected File baseDir;

            final DocumentBuilder builder = factory.newDocumentBuilder();

            final Document doc = builder.parse(is);

            final StringBuilder buf = new StringBuilder(1000);
            buf.append(getResultDataHeader());
            for (final Map.Entry<String, String> entry : fieldRuleMap.entrySet()) {
                final List<String> nodeStrList = new ArrayList<>();
                try {

     * @return the extracted body text
     * @throws ExtractException if extraction fails
     */
    protected String getBodyText(final MimeMessage message) {
        final StringBuilder buf = new StringBuilder(1000);
        try {
            final Object content = message.getContent();
            if (content instanceof final Multipart multipart) {
                final int count = multipart.getCount();

    }

    @Test
    public void testConvertWithLongText() throws IOException {
        // Test convert with long text
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 100; i++) {
            sb.append("word").append(i).append(" ");
        }
        String text = sb.toString();
        String field = "content";

        List<String> results = converter.convert(text, field, "en");

     * If true, read a content as a text when an extraction fails.
     */
    protected boolean readAsTextIfFailed = false;

    /**
     * Max compression ratio.
     */
    protected long maxCompressionRatio = 100;

    /**
     * Max uncompression size.
     */
    protected long maxUncompressionSize = 1000000;

    /**
     * Initial buffer size.
     */
    protected int initialBufferSize = 10000;

        String filePath = uri;
        if (!filePath.startsWith("file:")) {
            filePath = "file://" + filePath;
        }

        final StringBuilder buf = new StringBuilder(filePath.length() + 100);
        try {
            for (final char c : filePath.toCharArray()) {
                if (c == ' ') {
                    buf.append("%20");
                } else {

        readBuffer = new char[BUFFER_SIZE];
        readBufferIndex = BUFFER_SIZE;
        readBufferLen = 0;
        block = new StringBuilder();
        nextBlkStart = 0;
        queue = new PriorityQueue<>(100, new MyTokensComparator());
        this.synonyms = new ArrayList<>();
    }

    @Override
    public boolean incrementToken() throws IOException {
        while (true) {

                if (logger.isDebugEnabled()) {
                    logger.debug("Parsing SmbFile Directory: {}", filePath);
                }
                final Set<RequestData> requestDataSet = new HashSet<>(100);
                if (includeContent) {
                    final SmbFile[] files = file.listFiles();
                    if (files != null) {
                        for (final SmbFile f : files) {

    /**
     * Converts the suggest item to a JSON string.
     * @return The JSON string representation of the suggest item.
     */
    public String toJsonString() {
        final StringBuilder buf = new StringBuilder(100);
        buf.append('{').append('"').append(FieldNames.TEXT).append("\":").append(convertJsonString(text));

        for (int i = 0; i < readings.length; i++) {

        if (StringUtil.isBlank(url) || StringUtil.isBlank(enc)) {
            return url;
        }

        final StringBuilder buf = new StringBuilder(url.length() + 100);
        for (final char c : url.toCharArray()) {
            if (CharUtil.isUrlChar(c)) {
                buf.append(c);
            } else {
                try {