mvn test

# Run single unit test
mvn test -Dtest=SearchEngineClientTest

# Run integration tests (*Tests.java in src/test/java/org/codelibs/fess/it/)
# Requires Fess server and OpenSearch running
mvn test -P integrationTests -Dtest.fess.url="http://localhost:8080" -Dtest.search_engine.url="http://localhost:9201"

# Run single integration test

#### 4. Run Integration Tests

    $ mvn test -P integrationTests -Dtest.fess.url="http://localhost:8080" -Dtest.search_engine.url="http://localhost:9201"

To run a single test case:

    $ mvn test -P integrationTests -Dtest.fess.url="http://localhost:8080" -Dtest.search_engine.url="http://localhost:9201" -Dtest=SearchApiTests

### Translate In Your Language

Fess is internationalized software.

     *
     * @param outputFile the converted output file
     * @param outExt the output file extension
     * @return the extracted text content
     * @throws ExtractException if an error occurs while reading the file
     */
    protected String getOutputContent(final File outputFile, final String outExt) {
        final Extractor extractor = getExtractor(outExt);
        if (extractor != null) {

    }

    fun BuildResult.assertOutputContains(text: String) =
        assertTrue("Output should contain text:\n'$text',\nbut given text was not matched.\n", output.contains(text))

    protected
    fun File.withFile(path: String, text: String = ""): File =
        resolve(path).apply {
            parentFile.mkdirs()
            writeText(text.trimIndent())
        }

    protected

        if (text == null) {
            return null;
        }
        if (suffix == null) {
            return text;
        }
        if (text.endsWith(suffix)) {
            return text.substring(0, text.length() - suffix.length());
        }
        return text;
    }

    /**
     * Removes the prefix from the string if it is present.
     *
     * @param text

import com.fasterxml.jackson.databind.node.ArrayNode;
import com.fasterxml.jackson.databind.node.ObjectNode;

/**
 * Extracts text content and metadata from JSON files.
 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Structured text extraction with key-value pairs</li>
 *   <li>Top-level field extraction as metadata</li>

Core attributes: `text`, `timestamp`, `queryFreq`, `docFreq`, `userBoost`, `readings`, `tags`, `roles`, `languages`, `kinds`

Kind types: `DOCUMENT`, `QUERY`, `USER`

---

## Development Workflow

### Build Commands

```bash
mvn compile                              # Compile
mvn test                                 # Run all tests
mvn test -Dtest=SuggesterTest           # Run specific test

**Registration**:
```java
extractorFactory.addExtractor("text/html", htmlExtractor, 2);  // Weight 2
extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

**RobotsTxtHelper**: RFC 9309 parsing, user-agent matching, crawl-delay, sitemaps

			continue
		}
		delete(hexByLine, p.Line())
		if text == nil {
			t.Errorf("%s: instruction outside TEXT", p)
		}
		size := int64(len(text.P)) - p.Pc
		if p.Link != nil {
			size = p.Link.Pc - p.Pc
		} else if p.Isize != 0 {
			size = int64(p.Isize)
		}
		var code []byte
		if p.Pc < int64(len(text.P)) {
			code = text.P[p.Pc:]
			if size < int64(len(code)) {
				code = code[:size]
			}

				"text/x-cobol",
				"text/x-coldfusion",
				"text/x-common-lisp",
				"text/x-diff",
				"text/x-eiffel",
				"text/x-emacs-lisp",
				"text/x-erlang",
				"text/x-expect",
				"text/x-forth",
				"text/x-fortran",
				"text/x-go",
				"text/x-groovy",
				"text/x-haskell",
				"text/x-idl",
				"text/x-ini",
				"text/x-java-source",
				"text/x-jsp",