"application/x-texinfo",
				"application/x-tika-msoffice",
				"application/x-tika-msoffice-embedded",
				"application/x-tika-msoffice-embedded;format=ole10_native",
				"application/x-tika-msoffice-embedded;format=comp_obj",
				"application/x-tika-msworks-spreadsheet",
				"application/x-tika-ooxml",
				"application/x-tika-ooxml-protected",
				"application/x-tika-staroffice",
				"application/x-uc2-compressed",

    public Logger getLogger() {
        return logger;
    }

    /**
     * Gets the appropriate extractor for the given response data.
     * Selects an extractor based on the MIME type or falls back to the Tika extractor.
     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document

## 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

### Prerequisites

- Java 21 or higher
- Maven 3.6 or higher

        } else {
            cmdList.add("-Dfess.log.level=" + logLevel);
            if ("debug".equalsIgnoreCase(logLevel)) {
                cmdList.add("-Dorg.apache.tika.service.error.warn=true");
            }
        }
        stream(fessConfig.getJvmCrawlerOptionsAsArray())
                .of(stream -> stream.filter(StringUtil::isNotBlank).forEach(value -> cmdList.add(value)));

        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    // TODO tika needs to support pdfbox 2.0
    //    public void test_getTika_pdf() {
    //        final InputStream in = ResourceUtil
    //                .getResourceAsStream("extractor/test.pdf");

"taču", "nu", "pat", "tiklab", "iekšpus", "nedz", "tik", "nevis", "turpretim", "jeb", "iekam", "iekām", "iekāms", "kolīdz", "līdzko", "tiklīdz", "jebšu", "tālab", "tāpēc", "nekā", "itin", "jā", "jau", "jel", "nē", "nezin", "tad", "tikai", "vis", "tak", "iekams", "vien", "# modal verbs", "būt  ", "biju ", "biji", "bija", "bijām", "bijāt", "esmu", "esi", "esam", "esat ", "būšu     ", "būsi", "būs", "būsim", "būsiet", "tikt", "tiku", "tiki", "tika", "tikām", "tikāt", "tieku", "tiec", "tiek", "tiekam",...

"taču", "nu", "pat", "tiklab", "iekšpus", "nedz", "tik", "nevis", "turpretim", "jeb", "iekam", "iekām", "iekāms", "kolīdz", "līdzko", "tiklīdz", "jebšu", "tālab", "tāpēc", "nekā", "itin", "jā", "jau", "jel", "nē", "nezin", "tad", "tikai", "vis", "tak", "iekams", "vien", "# modal verbs", "būt  ", "biju ", "biji", "bija", "bijām", "bijāt", "esmu", "esi", "esam", "esat ", "būšu     ", "būsi", "būs", "būsim", "būsiet", "tikt", "tiku", "tiki", "tika", "tikām", "tikāt", "tieku", "tiec", "tiek", "tiekam",...

# Type of hot thread monitoring (e.g., cpu).
crawler.hotthread.type=cpu
# Metadata fields to exclude from document content.
crawler.metadata.content.excludes=resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*,X-FESS.*
# Mapping for document metadata names.
crawler.metadata.name.mapping=\
title=title:string\n\
Title=title:string\n\
dc:title=title:string\n\

# html

    /** The key of the configuration. e.g. cpu */
    String CRAWLER_HOTTHREAD_TYPE = "crawler.hotthread.type";

    /** The key of the configuration. e.g. resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*,X-FESS.* */
    String CRAWLER_METADATA_CONTENT_EXCLUDES = "crawler.metadata.content.excludes";

    /** The key of the configuration. e.g. title=title:string<br>
     * Title=title:string<br>

* <a href="https://jinja.palletsprojects.com" target="_blank"><code>jinja2</code></a> - Dibutuhkan jika anda menggunakan konfigurasi template bawaan.