* Constructs an AccessTimeoutTarget with the specified thread.
     * @param thread The thread to monitor.
     */
    public AccessTimeoutTarget(final Thread thread) {
        runningThread = thread;
        running.set(true);
    }

    /**
     * {@inheritDoc}
     *
     * @see org.codelibs.core.timer.TimeoutTarget#expired()
     */
    @Override
    public void expired() {
        int count = 0;

     */
    public HtmlXpathExtractor() {
        super();
    }

    /**
     * Initializes the XPathAPI cache with a specified cache duration.
     * This method is called to set up the cache for XPathAPI instances.
     */
    @Resource
    public void init() {
        xpathAPICache =

     */
    public static UrlQueue<?> getUrlQueue() {
        return URL_QUEUE_THREAD_LOCAL.get();
    }

    /**
     * Sets the URL queue for the current thread. If the provided URL queue is null,
     * the URL queue for the current thread is removed.
     *
     * @param urlQueue the URL queue to be set for the current thread, or null to remove the URL queue
     */

     * @param objs the log objects (should contain UrlQueue and Set of RequestData)
     */
    protected void processProcessChildUrlsByException(final Object... objs) {
        // CrawlerContext crawlerContext = (CrawlerContext) objs[0];
        final UrlQueue<?> urlQueue = (UrlQueue<?>) objs[1];
        @SuppressWarnings("unchecked")
        final Set<RequestData> requestDataSet = (Set<RequestData>) objs[2];
        if (logger.isDebugEnabled()) {

     *
     * @param maxDuplicatedPath the maximum duplicated path count to set
     */
    public void setMaxDuplicatedPath(final int maxDuplicatedPath) {
        this.maxDuplicatedPath = maxDuplicatedPath;
    }

    /**
     * Gets the character set name used for encoding file paths.
     *
     * @return the character set name
     */
    public String getCharsetName() {
        return charsetName;

    }

    /**
     * Returns the set of robots.txt URLs.
     * @return The set of robots.txt URLs.
     */
    public Set<String> getRobotsTxtUrlSet() {
        return robotsTxtUrlSet;
    }

    /**
     * Sets the set of robots.txt URLs.
     * @param robotsTxtUrlSet The set of robots.txt URLs.
     */
    public void setRobotsTxtUrlSet(final Set<String> robotsTxtUrlSet) {

     *
     * @param officeManager the office manager to set
     */
    public void setOfficeManager(final OfficeManager officeManager) {
        this.officeManager = officeManager;
    }

    /**
     * Sets the temporary directory for file operations.
     *
     * @param tempDir the temporary directory to set
     */
    public void setTempDir(final File tempDir) {

</components>
```

### Crawler Context Configuration

```java
// Set maximum number of URLs to crawl
crawler.crawlerContext.setMaxAccessCount(1000);

// Set number of crawler threads
crawler.crawlerContext.setNumOfThread(10);

// Set maximum crawl depth
crawler.crawlerContext.setMaxDepth(3);

// Set request interval (politeness)
crawler.crawlerContext.setDefaultIntervalTime(1000); // 1 second
```

 */
package org.codelibs.opensearch.extension.kuromoji.index.analysis;

import static java.util.Collections.singletonMap;

import java.util.Map;
import java.util.Set;

import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ja.JapaneseAnalyzer;

  pull_request:
    branches:
    - master
    - "*.x"

jobs:
  build:

    runs-on: ubuntu-latest
    env:
      PARENT_BRANCH: main

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 21
      uses: actions/setup-java@v4
      with:
        java-version: '21'
        distribution: 'temurin'
    - uses: actions/cache@v4
      with:
        path: ~/.m2/repository