Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 20 of 53 for ditamap (0.06 sec)

  1. src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java

                putResultDataBody(dataMap, fessConfig.getIndexFieldDigest(), digest);
            } else {
                putResultDataBody(dataMap, fessConfig.getIndexFieldDigest(),
                        documentHelper.getDigest(responseData, body, dataMap, fessConfig.getCrawlerDocumentHtmlMaxDigestLengthAsInteger()));
            }
            // segment
            putResultDataBody(dataMap, fessConfig.getIndexFieldSegment(), sessionId);
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Oct 24 13:01:38 UTC 2024
    - 42.9K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/SitemapsRuleTest.java

            sitemapsRule.addRule("url", Pattern.compile(".*sitemap.*"));
            assertTrue(sitemapsRule.match(responseData));
            InputStream is = responseData.getResponseBody();
            assertTrue(is instanceof InputStream);
            CloseableUtil.closeQuietly(responseData);
        }
    
        private void assertMatchFalse(ResponseData responseData) {
            sitemapsRule.addRule("url", Pattern.compile(".*sitemap.*"));
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 4.7K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/XmlUtil.java

        }
    
        private static class DocHandler extends DefaultHandler {
            private final Map<String, Object> dataMap = new HashMap<>();
    
            private String fieldName;
    
            private final StringBuilder buffer = new StringBuilder(1000);
    
            @Override
            public void startDocument() {
                dataMap.clear();
            }
    
            @Override
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.1K bytes
    - Viewed (0)
  4. src/main/resources/crawler/rule.xml

    			<component class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
    			</component>
    		</property>
    		<postConstruct name="addRule">
    			<arg>"url"</arg>
    			<arg>"http[s]?:.*sitemap[^/]*\.xml.*|http[s]?:.*sitemap[^/]*\.gz.*|http[s]?:.*sitemap[^/]*\.txt.*"</arg>
    		</postConstruct>
    	</component>
    
    	<component name="webHtmlRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >
    		<property name="ruleId">"webHtmlRule"</property>
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Jun 04 08:42:49 UTC 2020
    - 4.6K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapSet.java

        public static final String INDEX = "Index";
    
        private final List<Sitemap> sitemapList = new ArrayList<>();
    
        private String type = URLSET;
    
        public void addSitemap(final Sitemap sitemap) {
            sitemapList.add(sitemap);
        }
    
        public void removeSitemap(final Sitemap sitemap) {
            sitemapList.remove(sitemap);
        }
    
        public Sitemap[] getSitemaps() {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 1.7K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

                final Set<RequestData> requestDataSet = new LinkedHashSet<>();
                for (final Sitemap sitemap : sitemapSet.getSitemaps()) {
                    if (sitemap != null) {
                        requestDataSet.add(RequestDataBuilder.newRequestData().get().url(sitemap.getLoc()).build());
                    }
                }
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 2.4K bytes
    - Viewed (0)
  7. fess-crawler/src/test/resources/sitemaps/sitemap2.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
       <sitemap>
          <loc>http://www.example.com/sitemap1.xml.gz</loc>
          <lastmod>2004-10-01T18:23:17+00:00</lastmod>
       </sitemap>
       <sitemap>
          <loc>http://www.example.com/sitemap2.xml.gz</loc>
          <lastmod>2005-01-01</lastmod>
       </sitemap>
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 376 bytes
    - Viewed (0)
  8. src/main/java/org/codelibs/fess/crawler/FessCrawlerThread.java

                try {
                    final CrawlingConfig crawlingConfig = crawlingConfigHelper.get(crawlerContext.getSessionId());
                    final Map<String, Object> dataMap = new HashMap<>();
                    dataMap.put(fessConfig.getIndexFieldUrl(), url);
                    final List<String> roleTypeList = new ArrayList<>();
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Feb 22 01:37:57 UTC 2024
    - 14.6K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

            }
    
            final Map<String, Object> dataMap = XmlUtil.getDataMap(accessResultData);
            if (Map.class.equals(dataClass)) {
                return dataMap;
            }
    
            try {
                final Object obj = dataClass.getDeclaredConstructor().newInstance();
                BeanUtil.copyMapToBean(dataMap, obj);
                return obj;
            } catch (final Exception e) {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 8.8K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapFile.java

     * @author shinsuke
     *
     */
    public class SitemapFile implements Sitemap {
    
        private static final long serialVersionUID = 1L;
    
        /**
         * Identifies the location of the Sitemap. This location can be a Sitemap,
         * an Atom file, RSS file or a simple text file.
         */
        private String loc;
    
        /**
         * Identifies the time that the corresponding Sitemap file was modified. It
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 2.7K bytes
    - Viewed (0)
Back to top