- ✅ Encoding information in TextExtractor errors
- ✅ File type context in MS Office errors
- ✅ Archive type in archive extractor errors

## Testing Best Practices

1. **Isolation**: Each test is independent and doesn't affect others
2. **Clarity**: Test names clearly describe what is being tested
3. **Coverage**: Both success and failure paths are tested
4. **Edge Cases**: Null, empty, and boundary conditions are covered

        assertSame(pooled1.getObject(), pooled2.getObject()); // Same wrapped object
    }

    /**
     * Test factory configuration independence
     */
    public void test_factoryConfigurationIndependence() {
        // Each factory instance has independent configuration
        assertEquals("testComponent", factory.getComponentName());
        assertSame(container, factory.getCrawlerContainer());

    </magic>
    <!-- The priority is 60, as .webarchive files often contain
         (X)HTML content. The bplist magic must trump the XHTML
         magics further within the file. This must also be
         independent of the internal ordering of patterns within
         MimeTypes -->
    <magic priority="60">
      <match value="bplist" type="string" offset="0"/>
    </magic>
  </mime-type>

            int bytesRead1 = stream1.read(buffer1);
            assertEquals(testContent, new String(buffer1, 0, bytesRead1, "UTF-8"));
        }

        // Second read - should work independently
        try (InputStream stream2 = cache.getInputStream()) {
            byte[] buffer2 = new byte[1024];
            int bytesRead2 = stream2.read(buffer2);