* - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD
     * - Any character between 0x10000 and 0x10FFFF
     *
     * @param in the input string to be processed
     * @return a new string with invalid XML characters removed, or the original
     *         string if it is empty

        int num = 10000;

        addDocument(indexName, client, num);

        ESSourceReader reader = new ESSourceReader(client, settings, indexName);
        reader.setScrollSize(1000);
        int count = 0;
        Set<String> valueSet = Collections.synchronizedSet(new HashSet<>());
        Map<String, Object> source;
        while ((source = reader.read()) != null) {

        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());
            latch.countDown();
        }).error(t -> {

    }

    /**
     * Test concurrent access count operations
     */
    public void test_accessCount_concurrent() throws Exception {
        final int threadCount = 100;
        final int operationsPerThread = 1000;
        final CountDownLatch startLatch = new CountDownLatch(1);
        final CountDownLatch endLatch = new CountDownLatch(threadCount);

        ExecutorService executor = Executors.newFixedThreadPool(threadCount);

        }

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        final StringBuilder buf = new StringBuilder(1000);

        File tempFile = null;
        LhaFile lhaFile = null;
        try {
            tempFile = createTempFile("crawler-", ".lzh", null);
            try (FileOutputStream fos = new FileOutputStream(tempFile)) {

     * @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();

            throw new CrawlingAccessException("Could not parse " + responseData.getUrl(), e);
        }
        final Document document = parser.getDocument();

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

            boolean isSpace = false;
            int alphanumSize = 0;
            int symbolSize = 0;
            int c;
            final Set<String> termCache = new HashSet<>(1000);
            try {
                while ((c = reader.read()) != -1) {
                    if (Character.isISOControl(c) || isSpaceChar(c)) {
                        if (duplicateTermRemoved) {

    @Test
    public void testConvertWithLongText() throws IOException {
        // Test convert with long text
        converter.init();
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 1000; i++) {
            sb.append("word").append(i).append(" ");
        }
        String text = sb.toString();
        String field = "content";

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

    /**
     * Test edge cases for rule ID
     */
    public void test_ruleId_edgeCases() {
        // Very long rule ID
        StringBuilder longId = new StringBuilder();
        for (int i = 0; i < 1000; i++) {
            longId.append("verylongruleid");
        }
        testRule.setRuleId(longId.toString());
        assertEquals(longId.toString(), testRule.getRuleId());

        // Special characters in rule ID