test.tar data/folder/file.html テスト data/file.txt テキスト...

Shinsuke Sugaya <******@****.***> 1444529815 +0900

            final char originalChar1 = sb.charAt(i);
            final char originalChar2 = sb.charAt(i + 1);
            final char margedChar = mergeChar(originalChar1, originalChar2);
            if (margedChar != originalChar1) {
                sb.setCharAt(i, margedChar);
                sb.deleteCharAt(i + 1);
            } else {

                        .replace("\'", "'")//
        );
    }

    /**
     * Strips invalid XML characters from the input string.
     *
     * This method removes characters that are not allowed in XML documents
     * according to the XML 1.0 specification. Valid characters include:
     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)

     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**
     * The priority of this URL relative to other URLs on your site. Valid

 * HostIntervalController is an implementation of {@link org.codelibs.fess.crawler.interval.IntervalController}
 * that controls the interval between requests to the same host.
 * It uses a ConcurrentMap to store the last access time for each host.
 * The delayBeforeProcessing method is overridden to introduce a delay before processing a URL,
 * ensuring that requests to the same host are not made too frequently.

 *   <li>{@code POST_PROCESSING} - Represents the post-processing state.</li>
 *   <li>{@code NO_URL_IN_QUEUE} - Indicates that there are no URLs in the queue.</li>
 *   <li>{@code WAIT_NEW_URL} - Indicates that the crawler is waiting for new URLs.</li>
 * </ul>
 */
public interface IntervalController {
    /** Constant representing the pre-processing state. */
    int PRE_PROCESSING = 1;

    private final BytesRef scratchBytes = new BytesRef();

    private final CharsRef scratchChars = new CharsRef();

    private int longestMatchEndOffset;

    private int ch;

    private final char[] readBuffer;

    private int readBufferIndex;

    private int readBufferLen;

    StringBuilder block;

    int blkStart;

    int nextBlkStart;

    private int finalOffset;

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.FileUtil;

/**
 * A custom InputStream that wraps a temporary file. This class ensures that the temporary file
 * is deleted when the stream is closed.
 */
public class TemporaryFileInputStream extends InputStream {

        // Test that readings respect max reading limit
        TestReadingConverterWithLimit limitConverter = new TestReadingConverterWithLimit();
        limitConverter.init();

        assertEquals(5, limitConverter.getMaxReadingNum());

        String text = "test";
        String field = "content";

        // Request more languages than max reading num