assertTrue("Should preserve Unicode characters", result.getContent().contains("世界"));
    }

    /**
     * Test that encoding can be changed and applied correctly.
     */
    public void test_encoding_canBeChangedAndApplied() {
        final String originalEncoding = textExtractor.getEncoding();
        assertEquals("UTF-8", originalEncoding);

        textExtractor.setEncoding("ISO-8859-1");