# For more information see: https://help.github.com/actions/language-and-framework-guides/building-and-testing-java-with-maven

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

# For more information see: https://help.github.com/actions/language-and-framework-guides/building-and-testing-java-with-maven

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

  <mime-type type="application/vnd.oasis.opendocument.text-master">
    <alias type="application/x-vnd.oasis.opendocument.text-master"/>
    <_comment>OpenDocument v1.0: Global Text document</_comment>
    <magic>
      <match type="string" offset="0" value="PK">
        <match type="string" offset="30"
               value="mimetypeapplication/vnd.oasis.opendocument.text-master"/>
      </match>
    </magic>

    /**
     * Constructs a new {@code CrawlerSystemException} with the specified detail message and cause.
     *
     * @param message the detail message (which is saved for later retrieval by the {@link #getMessage()} method).
     * @param cause the cause (which is saved for later retrieval by the {@link #getCause()} method).
     *              (A {@code null} value is permitted, and indicates that the cause is nonexistent or unknown.)
     */

 * It allows setting delays before processing, after processing, when no URLs are in the queue,
 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *
 */
public class DefaultIntervalController extends AbstractIntervalController {

    /** Delay in milliseconds after processing a URL */
    protected long delayMillisAfterProcessing = 0L;

    /**
     * Constructs a new ExtractException with the specified message and cause.
     *
     * @param message the detail message. The detail message is saved for later retrieval by the {@link #getMessage()} method.
     * @param cause the cause (which is saved for later retrieval by the {@link #getCause()} method).
     *              (A {@code null} value is permitted, and indicates that the cause is nonexistent or unknown.)
     */

    /**
     * Constructs a new exception with the specified detail message and cause.
     *
     * @param message the detail message
     * @param cause the cause (which is saved for later retrieval by the {@link Throwable#getCause()} method)
     */
    public ExecutionTimeoutException(final String message, final Throwable cause) {
        super(message, cause);
    }

    /**

 *
 * <p>
 * This class defines the contract for delaying the crawling process at various points, such as:
 * </p>
 * <ul>
 *   <li>Before processing a URL ({@link #delayBeforeProcessing()})</li>
 *   <li>After processing a URL ({@link #delayAfterProcessing()})</li>
 *   <li>When there are no URLs in the queue ({@link #delayAtNoUrlInQueue()})</li>

        assertTrue(urlFilter.match("https://example.com/page"));
        assertFalse(urlFilter.match("https://other.com/page"));

        // Clear the filter
        urlFilter.clear();

        // After clear, all URLs should match (no filters applied)
        assertTrue(urlFilter.match("https://example.com/page"));
        assertTrue(urlFilter.match("https://other.com/page"));

        if (m.matches() && m.groupCount() > 0) {
            return m.group(1);
        }
        return null;
    }

    /**
     * Strips comments from a line (everything after '#' character).
     * @param line the line to strip comments from
     * @return the line without comments
     */
    protected String stripComment(final String line) {