- ✅ Whitespace and empty string handling

---

### 3. ArchiveExtractorErrorHandlingTest.java
**Purpose**: Test improved error handling in archive extractors.

**Key Test Areas**:
- Enhanced error messages
- Partial extraction (continues on failure)
- Invalid archive handling
- Empty archive handling
- Mixed valid/invalid entries

**Covered Extractors**:
- ZipExtractor
- TarExtractor

**Test Count**: 12 tests

            buf.append(escapeJson(endRecordNumber));
            buf.append(",\"page_numbers\":");
            buf.append(escapeJson(pageNumbers));
            buf.append(",\"partial\":");
            buf.append(escapeJson(partial));
            buf.append(",\"search_query\":");
            buf.append(escapeJson(searchQuery));
            buf.append(",\"requested_time\":");
            buf.append(requestedTime);

        assertEquals(300L, controller.getDelayMillisBeforeProcessing());
        assertEquals(400L, controller.getDelayMillisForWaitingNewUrl());
    }

    /**
     * Test constructor with partial parameters uses defaults for missing values
     */
    public void test_constructorWithPartialParams() {
        final Map<String, Long> params = new HashMap<>();
        params.put("delayMillisAfterProcessing", 150L);

                            searchResponse.ifPresent(r -> {
                                if (r.getTotalShards() != r.getSuccessfulShards() && fessConfig.isQueryTimeoutLogging()) {
                                    // partial results
                                    final StringBuilder buf = new StringBuilder(1000);
                                    buf.append("[SEARCH TIMEOUT] {\"exec_time\":")

                throw new ExtractException("Failed to extract content from ZIP archive. No entries could be processed.", e);
            }
            if (logger.isWarnEnabled()) {
                logger.warn("Partial extraction from ZIP archive. Processed: {}, Failed: {}", processedEntries, failedEntries, e);
            }
        }

        return new ExtractData(buf.toString().trim());
    }

    /**

                throw new ExtractException("Failed to extract content from TAR archive. No entries could be processed.", e);
            }
            if (logger.isWarnEnabled()) {
                logger.warn("Partial extraction from TAR archive. Processed: {}, Failed: {}", processedEntries, failedEntries, e);
            }
        }

        return buf.toString().trim();
    }

    /**

     *
     * <p>This method is designed to be resilient to malformed robots.txt files.
     * It will parse valid directives and ignore invalid ones, ensuring that partial
     * content can be extracted even from poorly formatted files.</p>
     *
     * <p>The following errors are handled gracefully (line is skipped, parsing continues):</p>
     * <ul>

        assertNotNull(matched);
        assertEquals("GoogleBot", matched.getUserAgent());
    }

    public void test_getMatchedDirectiveWithPartialMatch() {
        // Test getMatchedDirective with partial pattern match
        RobotsTxt robotsTxt = new RobotsTxt();

        Directive directive = new Directive("Google*");
        directive.addDisallow("/private/");
        robotsTxt.addDirective(directive);

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.
 */
public class ArchiveExtractorErrorHandlingTest extends PlainTestCase {

     * @param allRecordCountRelation the relationship of the record count (exact, approximate, etc.)
     * @param queryTime the time taken to execute the search query
     * @param partialResults whether the results are partial due to timeout or other constraints
     * @param facetResponse the facet information for the search results
     * @param start the starting position for pagination
     * @param pageSize the size of the current page