### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt
- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>
 * This client supports authentication, content retrieval, and metadata extraction from SMB files.

import org.codelibs.jcifs.smb1.util.LogStream;

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

        // Test multiple User-agents in sequence (Bot1, Bot2, Bot3 should share the same rules)
        assertFalse(robotsTxt.allows("/shared/", "Bot1"));
        assertFalse(robotsTxt.allows("/shared/", "Bot2"));
        assertFalse(robotsTxt.allows("/shared/", "Bot3"));

        // Test sitemaps - should parse valid sitemaps and ignore invalid ones

        if (isEmpty(name)) {
            return name;
        }
        final char[] chars = name.toCharArray();
        if (chars.length >= 2 && Character.isUpperCase(chars[0]) && Character.isUpperCase(chars[1])) {
            return name;
        }
        chars[0] = Character.toLowerCase(chars[0]);
        return new String(chars);
    }

    /**
     * Capitalizes a string according to JavaBeans conventions.

        assertNull(StringUtil.newStringUnsafe(null));
        char[] chars = new char[0];
        assertThat(StringUtil.newStringUnsafe(chars), is(""));
        chars = new char[] { 'a', 'b', 'c' };
        assertThat(StringUtil.newStringUnsafe(chars), is("abc"));
        chars = new char[] { 'a', 'b', 'c', ' ' };
        assertThat(StringUtil.newStringUnsafe(chars), is("abc "));
    }

        // Test extended ASCII characters (not valid URL chars without encoding)
        assertFalse(CharUtil.isUrlChar('\u00A0')); // non-breaking space
        assertFalse(CharUtil.isUrlChar('\u00FF')); // ÿ
    }

    public void test_isUrlChar_unicode() {
        // Test Unicode characters (not valid URL chars without encoding)
        assertFalse(CharUtil.isUrlChar('\u3042')); // あ (Hiragana)

index.document.suggest.index=fess
# Index name for crawler documents.
index.document.crawler.index=fess_crawler
# Number of primary shards for crawler queue index.
index.document.crawler.queue.number_of_shards=10
# Number of primary shards for crawler data index.
index.document.crawler.data.number_of_shards=10
# Number of primary shards for crawler filter index.
index.document.crawler.filter.number_of_shards=10
# Number of replicas for crawler queue index.

    public void test_analyzeTextWithLargeContent() throws Exception {
        SuggestAnalyzer analyzer = suggester.settings().analyzer().new DefaultContentsAnalyzer();
        // Create text larger than maxAnalyzedContentLength (1000 chars by default)
        StringBuilder largeText = new StringBuilder();
        for (int i = 0; i < 2000; i++) {
            largeText.append("テスト ");
        }

            { "aliases", "allocation", "count", "fielddata", "health", "indices", "master", "nodeattrs", "nodes", "pending_tasks",
                    "plugins", "recovery", "repositories", "thread_pool", "shards", "segments", "snapshots", "templates" };

    // ===================================================================================
    //                                                                           Attribute