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

        try (InputStream is = new ByteArrayInputStream(SQL_REM_CONTENT.getBytes(StandardCharsets.UTF_8))) {
            final String contentType = mimeTypeHelper.getContentType(is, "test.sql");
            // Without override, Tika detects based on content+filename
            assertNotNull(contentType);
        }
    }

    @Test
    public void test_init_nullConfig() throws IOException {

3. **Fallback**: English (from `fess_label.properties` and `fess_message.properties`)

### Document Language Detection

During crawling and indexing, Fess:

1. Detects language from document content using Apache Tika
2. Validates against `supported.languages` list
3. Creates language-specific fields (e.g., `content_ja`, `title_en`, `content_sv`)
4. Applies language-specific analyzers for better search results

## 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)));

toei.aichi.jp
toga.toyama.jp
togakushi.nagano.jp
togane.chiba.jp
togitsu.nagasaki.jp
togliatti.su
togo.aichi.jp
togura.nagano.jp
tohma.hokkaido.jp
tohnosho.chiba.jp
toho.fukuoka.jp
tokai.aichi.jp
tokai.ibaraki.jp
tokamachi.niigata.jp
tokashiki.okinawa.jp
toki.gifu.jp
tokigawa.saitama.jp
tokke.no
tokoname.aichi.jp
tokorozawa.saitama.jp
tokushima.jp
tokushima.tokushima.jp

# 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

toei.aichi.jp
toga.toyama.jp
togakushi.nagano.jp
togane.chiba.jp
togitsu.nagasaki.jp
togliatti.su
togo.aichi.jp
togura.nagano.jp
tohma.hokkaido.jp
tohnosho.chiba.jp
toho.fukuoka.jp
tokai.aichi.jp
tokai.ibaraki.jp
tokamachi.niigata.jp
tokashiki.okinawa.jp
toki.gifu.jp
tokigawa.saitama.jp
tokke.no
tokoname.aichi.jp
tokorozawa.saitama.jp
tokushima.jp
tokushima.tokushima.jp

    /** 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>

okazaki.aichi.jp
owariasahi.aichi.jp
seto.aichi.jp
shikatsu.aichi.jp
shinshiro.aichi.jp
shitara.aichi.jp
tahara.aichi.jp
takahama.aichi.jp
tobishima.aichi.jp
toei.aichi.jp
togo.aichi.jp
tokai.aichi.jp
tokoname.aichi.jp
toyoake.aichi.jp
toyohashi.aichi.jp
toyokawa.aichi.jp
toyone.aichi.jp
toyota.aichi.jp
tsushima.aichi.jp
yatomi.aichi.jp
akita.akita.jp
daisen.akita.jp