Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 6 of 6 for xmlExtractor (0.2 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/XmlExtractor.java

     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.extractor.impl;
    
    import java.util.regex.Pattern;
    
    /**
     * @author shinsuke
     *
     */
    public class XmlExtractor extends AbstractXmlExtractor {
        protected Pattern xmlEncodingPattern =
                Pattern.compile("<\\?xml.*encoding\\s*=\\s*['\"]([\\w\\d\\-_]*)['\"]\\s*\\?>", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 1.6K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/XmlExtractorTest.java

        public XmlExtractor xmlExtractor;
    
        @Override
        protected void setUp() throws Exception {
            super.setUp();
            StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("xmlExtractor", XmlExtractor.class);
            xmlExtractor = container.getComponent("xmlExtractor");
        }
    
        public void test_getXml_utf8() {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.4K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java

                    }
                    final Throwable cause = e.getCause();
                    if (cause instanceof SAXException) {
                        final Extractor xmlExtractor = crawlerContainer.getComponent("xmlExtractor");
                        if (xmlExtractor != null) {
                            InputStream in = null;
                            try {
                                if (isByteStream) {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:41:37 UTC 2024
    - 25K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/JodExtractor.java

            // Drawing Formats
            extensionMap.put("odg", "svg");
            extensionMap.put("otg", "svg");
    
            extractorMap.put("pdf", new PdfExtractor());
            extractorMap.put("svg", new XmlExtractor());
        }
    
        @PostConstruct
        public void init() {
            if (officeManager == null) {
                throw new CrawlerSystemException("officeManager is null.");
            }
            try {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 8.2K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractor.java

    /**
     * Gets a text from .eml file.
     *
     * @author shinsuke
     *
     */
    public class EmlExtractor extends AbstractExtractor {
        private static final String[] DAY_OF_WEEK = { "Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun" };
    
        private static final Logger logger = LoggerFactory.getLogger(EmlExtractor.class);
    
        protected Properties mailProperties = new Properties();
    
        /* (non-Javadoc)
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 10.8K bytes
    - Viewed (0)
  6. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractorTest.java

        private static final Logger logger = LoggerFactory.getLogger(EmlExtractorTest.class);
    
        public EmlExtractor emlExtractor;
    
        @Override
        protected void setUp() throws Exception {
            super.setUp();
            StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("emlExtractor", EmlExtractor.class);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 4.5K bytes
    - Viewed (0)
Back to top