- "*.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
        key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}

    - "*.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
        key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}

/**
 * AccessTimeoutTarget is a class that implements the TimeoutTarget interface.
 * It is used to interrupt a running thread when a timeout occurs.
 * The class provides methods to interrupt the thread and stop the timeout target.
 *
 * <p>
 * The class uses a logger to log debug messages.
 * It also uses an AtomicBoolean to track whether the thread is running.
 * </p>
 *
 * <p>

 *
 * @see com.ibm.icu.text.Transliterator
 */
public class ICUNormalizer implements Normalizer {
    /** The transliterator used for normalization. */
    protected Transliterator transliterator;

    /**
     * Constructor for ICUNormalizer.
     * @param transliteratorId The ID of the transliterator to use.
     */
    public ICUNormalizer(final String transliteratorId) {

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.

import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.

import org.codelibs.fess.crawler.helper.SitemapsHelper;

/**
 * SitemapsRule is a rule implementation that extends RegexRule to determine if a given response data
 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.

/**
 * RegexRule is a rule implementation that uses regular expressions to match against the ResponseData.
 * It allows defining multiple regular expressions for different fields of the ResponseData.
 * The rule can be configured to require all regular expressions to match (allRequired = true) or
 * only one of them (allRequired = false). It also supports a default rule that always matches.
 *
 * <p>

 * This class provides methods to store, retrieve, update, and delete access results,
 * as well as to iterate over them. It uses a {@link MemoryDataHelper} to store the data in memory.
 *
 * <p>
 * The class uses a static {@code idCount} to generate unique IDs for each access result.
 * The {@code idCountLock} object is used to synchronize access to the {@code idCount} variable,
 * ensuring that IDs are generated in a thread-safe manner.
 * </p>
 *

 * </ul>
 *
 * <p>
 * The client uses a {@link SmbAuthenticationHolder} to manage SMB authentication credentials.
 * It also integrates with other Fess Crawler components, such as {@link ContentLengthHelper} and
 * {@link MimeTypeHelper}, to handle content length checks and MIME type detection.
 * </p>
 *
 * <p>
 * The class uses JCIFS properties to configure the SMB connection.
 * </p>
 *
 * <p>