- **Data Persistence**: Multiple backend options including OpenSearch integration

## Technology Stack

- **Java**: 21+ (requires Java 21 or higher)
- **Build System**: Maven 3.x
- **DI Container**: LastaFlute DI
- **HTTP Client**: Apache HttpComponents
- **Content Extraction**: Apache Tika, Apache POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Testcontainers
- **Storage Backends**: OpenSearch, Memory-based

## Quick Start

        isDaemon = true
        uncaughtExceptionHandler = loggingUncaughtExceptionHandler
      }
    }

  private val backend = TaskRunner.RealBackend(threadFactory)
  private val taskRunner = TaskRunner(backend)
  private val queue = taskRunner.newQueue()

  @AfterEach fun tearDown() {
    backend.shutdown()
  }

  @Test fun test() {
    val t1 = System.nanoTime() / 1e6

 */
class TaskRunner(
  val backend: Backend,
  internal val logger: Logger = TaskRunner.logger,
) : Lockable {
  private var nextQueueName = 10000
  private var coordinatorWaiting = false
  private var coordinatorWakeUpAt = 0L

  /**
   * When we need a new thread to run tasks, we call [Backend.execute]. A few microseconds later we

  if (loggingEnabled) {
    startNs = queue.taskRunner.backend.nanoTime()
    log(task, queue, "starting")
  }

  var completedNormally = false
  try {
    val result = block()
    completedNormally = true
    return result
  } finally {
    if (loggingEnabled) {
      val elapsedNs = queue.taskRunner.backend.nanoTime() - startNs
      if (completedNormally) {

    if (isLoom()) {
      val backend = TaskRunner.RealBackend(loomThreadFactory())
      val taskRunner = TaskRunner(backend)

      OkHttpClient
        .Builder()
        .connectionPool(
          buildConnectionPool(
            connectionListener = connectionListener,
            taskRunner = taskRunner,
          ),
        ).dispatcher(Dispatcher(backend.executor))
        .taskRunnerInternal(taskRunner)

  /**
   * Results are posted here as they occur. The find job is done when either one plan completes
   * successfully or all plans fail.
   */
  private val connectResults = taskRunner.backend.decorate(LinkedBlockingDeque<ConnectResult>())

  override fun find(): RealConnection {
    var firstException: IOException? = null
    try {
      while (tcpConnectsInFlight.isNotEmpty() || routePlanner.hasNext()) {

import org.lastaflute.web.validation.Required;

/**
 * Form for uploading files to the storage system via the admin API.
 * This form is used in the admin API interface to upload files to the storage backend
 * with optional path specification for file organization.
 */
public class UploadForm {

    /**
     * The storage path where the file should be uploaded.

 * [advanceUntil]. These functions don't return until the task threads are all idle.
 *
 * Task threads release their execution privilege in these ways:
 *
 *  * By yielding in [TaskRunner.Backend.coordinatorWait].
 *  * By yielding in [BlockingQueue.poll].
 *  * By completing.
 */
class TaskFaker : Closeable {
  val logger = Logger.getLogger("TaskFaker." + instance++)

## Architecture

### Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core framework
├── fess-crawler-lasta/        # LastaFlute DI integration
└── fess-crawler-opensearch/   # OpenSearch backend
```

### Key Design Patterns

**Factory**: `CrawlerClientFactory`, `ExtractorFactory` - protocol/format-specific component selection
**Strategy**: `CrawlerClient`, `Extractor`, `Transformer` - pluggable implementations

  internal fun scheduleAndDecide(
    task: Task,
    delayNanos: Long,
    recurrence: Boolean,
  ): Boolean {
    task.initQueue(this)

    val now = taskRunner.backend.nanoTime()
    val executeNanoTime = now + delayNanos

    // If the task is already scheduled, take the earlier of the two times.
    val existingIndex = futureTasks.indexOf(task)
    if (existingIndex != -1) {