import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for archive extractor error handling improvements.
 * Tests partial extraction, error recovery, and improved error messages.
 */

                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {
                            final Map<String, String> map = new HashMap<>();
                            map.put(ExtractData.RESOURCE_NAME_KEY, filename);
                            buf.append(extractor.getText(new IgnoreCloseInputStream(ais), map).getContent());

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;

                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {
                            final Map<String, String> map = new HashMap<>();
                            map.put(ExtractData.RESOURCE_NAME_KEY, filename);
                            buf.append(extractor.getText(new IgnoreCloseInputStream(ais), map).getContent());

        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

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

        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

    /**
     * Get the extracted data.
     * @param extractor The extractor.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    protected ExtractData getExtractData(final Extractor extractor, final InputStream in, final Map<String, String> params) {
        try {
            return extractor.getText(in, params);
        } catch (final RuntimeException e) {

		if testCase.expectedCode != actualCode {
			t.Errorf("Test %d: Expected the APIErrCode to be %d, but instead found %d", i+1, testCase.expectedCode, actualCode)
		}
	}
}

// Tests validate metadata extraction from http headers.
func TestExtractMetadataHeaders(t *testing.T) {
	testCases := []struct {
		header     http.Header
		metadata   map[string]string
		shouldFail bool
	}{

                logger.warn("Failed to close HTTP client for API extractor", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override