name: Java CI with Maven

on:
  push:
    branches:
    - master
    - "*.x"
  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'

    /**
     * Filter for URLs to control which URLs are crawled.
     */
    @Resource
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.
     */
    @Resource
    protected RuleManager ruleManager;

    /**
     * Container for managing crawler components.
     */
    @Resource

name: Java CI with Maven

on:
  push:
    branches:
    - master
    - "*.x"
  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'

import java.io.Serializable;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic
 * to determine if a given response data matches the rule, retrieve the rule's identifier,

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.
 * It uses a {@link UrlFilterService} to manage the URL filtering rules.
 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.
 * It also provides methods to initialize the filter with a session ID, clear the filter,

 *   <li>Extracting child URLs from the HTML content based on configured rules.</li>
 *   <li>Handling redirect URLs specified in the response headers.</li>
 * </ol>
 * <p>
 * The class also provides methods for configuring features and properties of the
 * underlying DOM parser, as well as defining rules for extracting child URLs
 * from specific HTML tags and attributes.
 * </p>
 *
 * <p>

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>

import org.codelibs.fess.crawler.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilterService} interface.
 * This class provides methods for managing URL filtering rules,
 * including adding include and exclude URL patterns, deleting patterns,
 * and retrieving lists of compiled URL patterns. It utilizes a
 * {@link MemoryDataHelper} to store and manage the URL patterns in memory.
 *
 */

    /**
     * Sets whether to use robots.txt disallow rules.
     *
     * @param useRobotsTxtDisallows True to use disallow rules, false otherwise
     */
    public void setUseRobotsTxtDisallows(final boolean useRobotsTxtDisallows) {
        this.useRobotsTxtDisallows = useRobotsTxtDisallows;
    }

    /**
     * Sets whether to use robots.txt allow rules.
     *

import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>