import org.codelibs.fess.util.SystemUtil;

import jakarta.servlet.ServletContext;

/**
 * CrawlJob is responsible for executing the crawling process in Fess.
 * This job launches a separate crawler process that can crawl web sites, file systems,
 * and data sources based on the configured crawling settings.
 *
 * <p>The job supports selective crawling by specifying configuration IDs for different

 * monitoring, and cleanup operations.
 *
 * <p>The crawler can operate in different modes based on command-line options:
 * <ul>
 * <li>Web crawling - crawls web sites and web content</li>
 * <li>File system crawling - crawls file systems and documents</li>
 * <li>Data store crawling - crawls databases and other data sources</li>

     * Gets the maximum allowed length for site strings from configuration.
     *
     * @return the maximum site length as configured
     */
    default int getMaxSiteLength() {
        return getFessConfig().getCrawlerDocumentMaxSiteLengthAsInteger();
    }

    /**
     * Abbreviates a site string to the maximum allowed length if configured.
     *
     * @param value the site string to abbreviate

	<property name="suggest.dir" value="${basedir}/src/main/webapp/WEB-INF/env/suggest" />
	<property name="thumbnail.dir" value="${basedir}/src/main/webapp/WEB-INF/env/thumbnail" />
	<property name="site.dir" value="${basedir}/src/main/webapp/WEB-INF/site" />
	<property name="kopf.branch" value="main" />

	<!-- Maven Repository -->
	<property name="maven.snapshot.repo.url" value="https://central.sonatype.com/repository/maven-snapshots" />

*[Fess Site Search](https://github.com/codelibs/fess-site-search)* is a free alternative to [Google Site Search](https://enterprise.google.com/search/products/gss.html). For more details, see the [FSS JS Generator documentation](https://fss-generator.codelibs.org/docs/manual).

## Website

    /** Field name for OpenSearch document score */
    public static final String DOC_SCORE_FIELD = "_score";

    /** Field name for site information in search results */
    public static final String SITE_FIELD = "site";

    /** Field name for URL-based search queries */
    public static final String INURL_FIELD = "inurl";

    /** Sort value for score-based sorting */

crawler.data.serializer=kryo
# Maximum length of site name in documents.
crawler.document.max.site.length=100
# Encoding for site names in documents.
crawler.document.site.encoding=UTF-8
# Hostname to use when unknown in documents.
crawler.document.unknown.hostname=unknown
# Whether to use site encoding for English documents.
crawler.document.use.site.encoding.on.english=false
# Whether to append data to documents.

                    .maxExpansions(fessConfig.getQueryBoostFuzzyContentExpansionsAsInteger()));
        }
        return defaultQuery;
    }

    /**
     * Converts a site field query to a prefix query for site filtering.
     *
     * @param fessConfig the Fess configuration
     * @param context the query context
     * @param termQuery the term query to convert
     * @param boost the boost value to apply

set FESS_MIN_MEM=256m
)

if "%FESS_MAX_MEM%" == "" (
set FESS_MAX_MEM=1g
)

if NOT "%FESS_HEAP_SIZE%" == "" (
set FESS_MIN_MEM=%FESS_HEAP_SIZE%
set FESS_MAX_MEM=%FESS_HEAP_SIZE%
)

REM min and max heap sizes should be set to the same value to avoid
REM stop-the-world GC pauses during resize, and so that we can lock the
REM heap in memory on startup to prevent any of it from being swapped
REM out.

        }
        buf.append(segment);
        return buf.toString();
    }

    /**
     * Gets the site path for display purposes.
     * Extracts and formats the site path from document URL.
     *
     * @param docMap the document data map
     * @return the formatted site path
     */
    public Object getSitePath(final Map<String, Object> docMap) {