* rule.addRule("url", "https://example.com/.*");
 * rule.addRule("contentType", "text/html");
 * rule.setAllRequired(true); // Both URL and content type must match
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setUrl("https://example.com/page1");
 * responseData.setContentType("text/html");
 *
 * boolean matches = rule.match(responseData); // Returns true
 * }
 * </pre>
 *
 */

        assertTrue(urlFilter.match("https://example.com/page.html"));
        assertTrue(urlFilter.match("https://example.com/document.pdf"));
        assertFalse(urlFilter.match("https://example.com/image.jpg"));
        assertFalse(urlFilter.match("https://example.com/admin/dashboard"));
        assertFalse(urlFilter.match("https://other.com/page.html"));
    }

    /**
     * Test match with no patterns configured

                    LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/x-lha", lhaExtractor);

                })//
        ;

        lhaExtractor = container.getComponent("lhaExtractor");

    }

        assertNotNull(accessResult2);

        accessResult2.setMimeType("text/html");
        dataService.update(accessResult2);

        final AccessResult accessResult3 = dataService.getAccessResult("id1", "http://www.id1.com/");
        assertNotNull(accessResult3);
        assertEquals("text/html", accessResult3.getMimeType());

        dataService.delete("id1");

data/folder/file.html テスト data/file.txt テキスト...

test.tar data/folder/file.html テスト data/file.txt テキスト...

import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>

                    ZipExtractor zipExtractor = container.getComponent("zipExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);

                })//
        ;

        zipExtractor = container.getComponent("zipExtractor");
    }

                    TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/tar", tarExtractor);
                })//
        ;

        tarExtractor = container.getComponent("tarExtractor");
    }

- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files