/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.

 * 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.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**

			<component class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>"http[s]?:.*sitemap[^/]*\.xml.*|http[s]?:.*sitemap[^/]*\.gz.*|http[s]?:.*sitemap[^/]*\.txt.*"</arg>
		</postConstruct>
	</component>

	<component name="webHtmlRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >
		<property name="ruleId">"webHtmlRule"</property>

    }

    public void test_getRule_sitemaps5() {
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("http://www.example.com/sitemap/");
        File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.xml");
        responseData.setResponseBody(file, false);
        final Rule rule = ruleManager.getRule(responseData);
        assertNotNull(rule);

    }

    /**
     * Adds sitemaps to the thread-local storage.
     * @param sitemaps An array of sitemap URLs.
     */
    public void addSitemaps(final String[] sitemaps) {
        sitemapsLocal.set(sitemaps);
    }

    /**
     * Removes sitemaps from the thread-local storage and returns them.
     * @return An array of sitemap URLs, or null if none were present.
     */

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

User-agent: Crawler/2.0
Disallow: /ccc

User-agent: Hoge Crawler
Disallow: /ddd

sitemap: http://www.example.com/sitmap.xml

<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
      <loc>http://www.example.com/</loc>
      <lastmod>2005-01-01</lastmod>
      <changefreq>monthly</changefreq>
      <priority>0.8</priority>
   </url>
   <url>
      <loc>http://www.example.com/catalog?item=12&amp;desc=vacation_hawaii</loc>
      <changefreq>weekly</changefreq>
   </url>
   <url>

    controller.setDefaultIntervalTime(1000);
});
```

### Sitemap Support

```java
// Enable sitemap processing
container.singleton("sitemapsRule", SitemapsRule.class, rule -> {
    rule.addRule("url", ".*sitemap.*");
});

// Add sitemap URL
crawler.addUrl("https://example.com/sitemap.xml");
```

## Data Access and Storage

### Accessing Crawled Data

```java

    protected static final Pattern CRAWL_DELAY_RECORD = Pattern.compile("^crawl-delay:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for Sitemap record.
     */
    protected static final Pattern SITEMAP_RECORD = Pattern.compile("^sitemap:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Whether robots.txt processing is enabled. */
    protected boolean enabled = true;

    /**

			<component
				class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>".*sitemap.*"</arg>
		</postConstruct>
	</component>

	<component name="fileRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule">
		<property name="ruleId">"fileRule"</property>
		<property name="defaultRule">true</property>