on:
  push:
    branches:
    - master
    - "*.x"
  pull_request:
    branches:
    - master
    - "*.x"

jobs:
  build:

    runs-on: ubuntu-latest
    env:
      PARENT_BRANCH: main

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 21
      uses: actions/setup-java@v4
      with:
        java-version: '21'
        distribution: 'temurin'
    - uses: actions/cache@v4

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.transformer.impl.FileTransformer;

public class BasicCrawlerExample {
    public static void main(String[] args) throws Exception {
        // Create crawler container
        StandardCrawlerContainer container = new StandardCrawlerContainer();
        
        // Configure basic components

on:
  push:
    branches:
    - master
    - "*.x"
  pull_request:
    branches:
    - master
    - "*.x"

jobs:
  build:

    runs-on: ubuntu-latest
    env:
      PARENT_BRANCH: main

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 21
      uses: actions/setup-java@v4
      with:
        java-version: '21'
        distribution: 'temurin'
    - uses: actions/cache@v4

    .setFields(new String[]{"title"})       // search specific fields
    .execute()
    .getResponse();
```

## Project Structure

```
src/
├── main/java/org/codelibs/fess/suggest/
│   ├── Suggester.java              # Main suggester API
│   ├── SuggesterBuilder.java       # Builder pattern implementation
│   ├── entity/
│   │   ├── SuggestItem.java        # Core suggestion data structure

 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface
 * for configuring the extraction parameters and handling the underlying complexities of content processing,

 *   <li>Handling resource names and content types</li>
 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>
 *   <li>Reading content as plain text if all other methods fail</li>
 *   <li>Applying post-extraction filters</li>
 *   <li>Handling Tika exceptions, including zip bomb exceptions</li>
 * </ul>

     */
    public void test_stackTraceWithCause() {
        Exception cause = new IllegalArgumentException("Cause exception");
        CrawlerSystemException exception = new CrawlerSystemException("Main exception", cause);

        StackTraceElement[] mainStackTrace = exception.getStackTrace();
        StackTraceElement[] causeStackTrace = cause.getStackTrace();

        assertNotNull(mainStackTrace);

import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * The Crawler class is the main class for web crawling. It manages the crawling process,
 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>

 * {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} in case of errors.
 * </p>
 *
 * <p>
 * The {@link #storeData(ResponseData, ResultData)} method is the main entry point for storing
 * the content of a crawled resource. The {@link #getData(AccessResultData)} method retrieves
 * the stored file path as a File object.
 * </p>
 */
public class FileTransformer extends HtmlTransformer {