return htmlTagPattern;
    }

    /**
     * Gets the pattern used for extracting charset from meta tags.
     *
     * @return the meta charset pattern
     */
    public Pattern getMetaCharsetPattern() {
        return metaCharsetPattern;
    }

    /**
     * Sets the pattern used for extracting charset from meta tags.
     *
     * @param metaCharsetPattern the meta charset pattern to set

 * may attempt to download and install SDK components (platforms, build-tools, platform-tools) simultaneously.
 * This can cause race conditions leading to:
 * - `FileAlreadyExistsException` when extracting files
 * - Corrupted installations (e.g., "Build-tool X has corrupt source.properties")
 * - Missing SDK components after installation
 *

        this.propertyMap = propertyMap;
    }

    /**
     * Gets the pattern for extracting charset from meta tags.
     *
     * @return the meta charset pattern
     */
    public Pattern getMetaCharsetPattern() {
        return metaCharsetPattern;
    }

    /**
     * Sets the pattern for extracting charset from meta tags.
     *
     * @param metaCharsetPattern the meta charset pattern to set

 *   <li>Extracting child URLs from the HTML content based on configured rules.</li>
 *   <li>Handling redirect URLs specified in the response headers.</li>
 * </ol>
 * <p>
 * The class also provides methods for configuring features and properties of the
 * underlying DOM parser, as well as defining rules for extracting child URLs
 * from specific HTML tags and attributes.
 * </p>
 *

    private static final String X_ROBOTS_TAG = "X-Robots-Tag";

    /** XPath expression for extracting thumbnail content from meta tags */
    private static final String META_NAME_THUMBNAIL_CONTENT = "//META[@name=\"thumbnail\" or @name=\"THUMBNAIL\"]/@content";

    /** XPath expression for extracting Open Graph image content from meta tags */

import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

import jakarta.annotation.PostConstruct;

/**
 * <p>
 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats
 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**

		}
		if actualErrCode == ErrNone {
			validateCredentialfields(t, i+1, testCase.expectedCredentials, actualCredential)
		}
	}
}

// TestParseSignature - validates the logic for extracting the signature string.
func TestParseSignature(t *testing.T) {
	testCases := []struct {
		inputSignElement string
		expectedSignStr  string
		expectedErrCode  APIErrorCode
	}{
		// Test case - 1.

                || url.startsWith("storage:") || url.startsWith("s3:") || url.startsWith("gcs:");
    }

    /**
     * Checks if the given URL should skip URL decoding when extracting file names.
     * Some protocols (like SMB, FTP, S3, GCS) should preserve the original URL encoding.
     *
     * @param url the URL to check
     * @return true if URL decoding should be skipped for this protocol

    /**
     * Extracts keywords from the given query string based on the specified fields.
     *
     * @param q the query string to parse and extract keywords from
     * @param fields the fields to consider when extracting keywords
     * @return a list of unique keywords extracted from the query string
     */
    public static List<String> getKeywords(final String q, final String[] fields) {