* Helper class for managing data crawling operations in Fess.
 * This class coordinates the execution of data store crawling processes,
 * managing multiple concurrent crawling threads and handling the indexing
 * of crawled documents into the search engine.
 *
 * <p>The DataIndexHelper supports:</p>
 * <ul>
 *   <li>Concurrent crawling of multiple data configurations</li>
 *   <li>Thread pool management for crawler execution</li>

    protected final Set<String> inlineMimeTypeSet = new HashSet<>();

    /** Cache for facet responses */
    protected Cache<String, FacetResponse> facetCache;

    /** Duration for facet cache in seconds (10 minutes) */
    protected long facetCacheDuration = 60 * 10L;

    /** Length of text fragment prefix */
    protected int textFragmentPrefixLength;

    /** Length of text fragment suffix */

- ACCEPTED on 2026-03-05
- PROPOSED on 2026-02-26

## Context

[Gradle properties](https://docs.gradle.org/current/userguide/build_environment.html#sec:gradle_configuration_properties)
are flags that allow build engineers to opt into and out of features of Gradle Runtime or Core Plugins.
Practically every Gradle feature is behind a flag, and additional sub-flags or options provide further control.

        assertEquals("value1", paramMap.get("key1"));
        assertEquals("value2", paramMap.get("key2"));
        assertEquals("value3", paramMap.get("key3"));

        // Test loading into existing map
        paramMap = new HashMap<>();
        paramMap.put("existing", "existingValue");
        configParam = "key1=value1\nkey2=value2";
        ParameterUtil.loadConfigParams(paramMap, configParam);

     *
     * @return the logger instance
     */
    @Override
    public Logger getLogger() {
        return logger;
    }

    /**
     * Stores parsed data from response into result data.
     * Processes HTML content using XPath expressions and handles robots tags.
     *
     * @param responseData the response data from crawling

labels.urlExpr=Condição
labels.boostExpr=Expressão de impulso
labels.confirmPassword=Confirmar
labels.crawler=Rastreador
labels.crudMode=Modo
labels.errorCountMax=Número máximo de erros
labels.errorCountMin=Número mínimo de erros
labels.facet=Faceta
labels.geo=Geo
labels.groups=Grupos
labels.hash=Hash
labels.maxSize=Tamanho máximo
labels.order=Ordem
labels.purgeSuggestSearchLogDay=Excluir informações de sugestão anteriores

before{content:"\f3c9"}.fa-microphone-alt-slash:before{content:"\f539"}.fa-microphone-slash:before{content:"\f131"}.fa-microscope:before{content:"\f610"}.fa-microsoft:before{content:"\f3ca"}.fa-minus:before{content:"\f068"}.fa-minus-circle:before{content:"\f056"}.fa-minus-square:before{content:"\f146"}.fa-mitten:before{content:"\f7b5"}.fa-mix:before{content:"\f3cb"}.fa-mixcloud:before{content:"\f289"}.fa-mizuni:before{content:"\f3cc"}.fa-mobile:before{content:"\f10b"}.fa-mobile-alt:before{conten...

val Project.testDistributionServerUrl: Provider<String>
    get() = gradleProperty(TEST_DISTRIBUTION_SERVER_URL)


// Controls the test distribution partition size. The test classes smaller than this value will be merged into a "partition"
val Project.maxTestDistributionPartitionSecond: Long?
    get() = systemProperty(TEST_DISTRIBUTION_PARTITION_SIZE).orNull?.toLong()


val Project.maxParallelForks: Int

    /** Default cron expression for general scheduling (daily at midnight). */
    public static final String DEFAULT_CRON_EXPRESSION = "0 0 * * *";

    /** Default cron expression for search log processing (every minute). */
    public static final String DEFAULT_SEARCH_LOG_CRON_EXPRESSION = "* * * * *";

    /** Default cron expression for daily tasks (daily at midnight). */

  ```bash
  curl -u admin:admin ...
  # or
  curl -H "Authorization: Basic YWRtaW46YWRtaW4=" ...
  ```

#### Issue: Large bulk imports timing out

**Solution**:
- Split large files into smaller batches (e.g., 10,000 docs per file)
- Increase timeout in `system.properties`:
  ```properties
  crawler.document.request.timeout=600000
  ```
- Use asynchronous import via Admin UI instead of API