// Unicode characters
        testRule.setRuleId("ルール日本語");
        assertEquals("ルール日本語", testRule.getRuleId());

        // Whitespace
        testRule.setRuleId("  rule with spaces  ");
        assertEquals("  rule with spaces  ", testRule.getRuleId());
    }

    /**
     * Test multiple registrations of same rule
     */
    public void test_multipleRegistrations() {

    /**
     * The priority of this URL relative to other URLs on your site. Valid
     * values range from 0.0 to 1.0. This value does not affect how your pages
     * are compared to pages on other sites—it only lets the search engines know
     * which pages you deem most important for the crawlers.
     *
     * The default priority of a page is 0.5.
     *

        // Test index name with special characters
        builder.setSettingsIndexName("Test-Index_Name.2024");
        assertEquals("test-index_name.2024", builder.settingsIndexName);

        // Test index name with spaces (should be lowercased)
        builder.setSettingsIndexName("Test Index Name");
        assertEquals("test index name", builder.settingsIndexName);
    }

    @Test
    public void testVariousTimeoutFormats() {

 * <ul>
 *   <li>Output encoding</li>
 *   <li>Maximum compression ratio and uncompression size</li>
 *   <li>Initial buffer size</li>
 *   <li>Memory size for temporary file storage</li>
 *   <li>Maximum term sizes for alphanumeric and symbolic terms</li>
 *   <li>Custom Tika configuration</li>
 *   <li>Tesseract OCR configuration for image-based documents</li>
 *   <li>PDF Parser configuration for PDF documents</li>
 * </ul>
 *

          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,

          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,

        assertEquals("3", extractData.getValues("meta:character-count")[0]);
        assertEquals("じょうたい", extractData.getValues("cp:contentStatus")[0]);
        assertEquals("3", extractData.getValues("meta:character-count-with-spaces")[0]);
        assertEquals("たいとる", extractData.getValues("dc:title")[0]);
        assertEquals("2", extractData.getValues("extended-properties:TotalTime")[0]);

  </mime-type>
  <mime-type type="image/vnd.dxf;format=ascii">
    <sub-class-of type="image/vnd.dxf"/>
    <_comment>AutoCAD DXF in ASCII Text form</_comment>
    <magic priority="50">
      <!-- Variable number of spaces or possibly creator tool before the code groups -->
      <!-- allow 999 (comments) before section -->
      <match type="regex" value="(999\r?\n[^\r\n]{0,64}\\s+)?0\r?\nSECTION\r?\n" offset="0:32">