<artifactId>parent</artifactId>
  <version>11-SNAPSHOT</version>

  <name>Model inheritance test parent: module path != artifactId</name>

  <modules>
    <module>child</module>
  </modules>

  <!-- 5 URLs in the pom will be inherited with path added -->
  <url>http://www.apache.org/</url>
  <scm>
    <connection>scm:my-scm:http://domain.org/base</connection>

</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);

{
    "properties": {
      "name": {
        "type": "keyword"
      },
      "urls": {
        "type": "keyword"
      },
      "includedUrls": {
        "type": "keyword"
      },
      "excludedUrls": {
        "type": "keyword"
      },
      "includedDocUrls": {
        "type": "keyword"
      },
      "excludedDocUrls": {
        "type": "keyword"
      },
      "configParameter": {
        "type": "keyword"

    <artifactId>parent</artifactId>
    <version>11-SNAPSHOT</version>
  </parent>

  <groupId>inheritance</groupId>
  <artifactId>inheritance</artifactId>
  <version>11-SNAPSHOT</version>
  <name>Model urls inheritance test child</name>

  <scm child.scm.connection.inherit.append.path="false"
       child.scm.developerConnection.inherit.append.path="false"
       child.scm.url.inherit.append.path="false">

        } catch (final Exception e) {
            return url;
        }
    }

    /**
     * Extracts anchor URLs from the HTML document.
     *
     * @param document the parsed HTML document
     * @param responseData the response data from crawling
     * @return list of anchor URLs found in the document
     */
    protected List<String> getAnchorList(final Document document, final ResponseData responseData) {

			<ErrorToWarnRewritePolicy loggers="org.apache.fontbox,org.apache.pdfbox,org.apache.poi" />
		</Rewrite>
		<RollingFile name="StatsFile" fileName="${log.file.basedir}/fess-urls.log"
			filePattern="${log.file.basedir}/fess-urls${backup.date.suffix}-%i.log.gz">
			<PatternLayout>
				<Pattern>${stats.log.pattern}</Pattern>
			</PatternLayout>
			<Policies>
				<TimeBasedTriggeringPolicy />

* [FastAPI CSS](https://fastapi.tiangolo.com/css/fastapi.css)
* [FastAPI JS](https://fastapi.tiangolo.com/js/fastapi.js)

Tool should NOT add language code to their URLs.

## HTML-style links { #html-style-links }

This is an <a href="https://example.com" target="_blank" class="external-link">HTML link</a> to an external site.

     *     exception by calling [HttpUrl.parse]; it returns null for invalid URLs.
     */
    open fun url(url: String): Builder = url(canonicalUrl(url).toHttpUrl())

    // Silently replace web socket URLs with HTTP URLs.
    private fun canonicalUrl(url: String) =
      when {
        url.startsWith("ws:", ignoreCase = true) -> "http:${url.substring(3)}"

    }

    /**
     * Calculates the relative path from the base directory of the parent to the parent directory of the base directory
     * of the child. The general idea is to adjust inherited URLs to match the project layout (in SCM).
     *
     * <p>This calculation is only a heuristic based on our conventions.
     * In detail, the algo relies on the following assumptions: <ul>

    private static void createWebConfig() {
        final Map<String, Object> requestBody = new HashMap<>();
        final String urls = "http://failure.test.url";
        final String includedUrls = "http://failure.test.url.*";
        requestBody.put("name", NAME_PREFIX + "WebConfig");
        requestBody.put("urls", urls);
        requestBody.put("included_urls", includedUrls);
        requestBody.put("user_agent", "Mozilla/5.0");