Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 27 for parse (0.05 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

            // Default constructor
        }
    
        /**
         * Parses a robots.txt file from the given input stream using UTF-8 encoding.
         * @param stream the input stream to parse
         * @return the parsed RobotsTxt object, or null if disabled
         */
        public RobotsTxt parse(final InputStream stream) {
            return parse(stream, Constants.UTF_8);
        }
    
        /**
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7.7K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/SitemapsHelper.java

         */
        public SitemapSet parse(final InputStream in) {
            return parse(in, true);
        }
    
        /**
         * Parses a sitemap from the given input stream.
         * @param in the input stream to parse
         * @param recursive whether to recursively parse compressed files
         * @return the parsed sitemap set
         */
        protected SitemapSet parse(final InputStream in, final boolean recursive) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14.7K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/SitemapsHelperTest.java

            try {
                sitemapsHelper.parse(in);
                fail();
            } catch (final CrawlingAccessException e) {
                // NOP
            }
        }
    
        public void test_parseXmlSitemaps_invalid2() {
            final byte[] bytes = "test".getBytes();
            final InputStream in = new ByteArrayInputStream(bytes);
    
            try {
                sitemapsHelper.parse(in);
                fail();
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 9.6K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/XmlUtil.java

                spfactory.setFeature(Constants.FEATURE_EXTERNAL_PARAMETER_ENTITIES, false);
                // create a sax parser
                final SAXParser parser = spfactory.newSAXParser();
                try {
                    parser.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, StringUtil.EMPTY);
                    parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);
                } catch (final Exception e) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 9.4K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java

        }
    
        /**
         * Creates a parse context.
         *
         * @param parser A parser.
         * @param params A map of parameters.
         * @return a parse context.
         */
        protected ParseContext createParseContext(final Parser parser, final Map<String, String> params) {
            final ParseContext parseContext = new ParseContext();
            parseContext.set(Parser.class, parser);
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 30.7K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

    import jakarta.annotation.Resource;
    
    /**
     * A response processor implementation that handles sitemaps.
     * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
     * and adds them as child URLs to be crawled.
     *
     * <p>
     * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
     * It then iterates through the sitemaps in the SitemapSet, extracts the URL
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/fs/FileSystemClient.java

            }
    
            return responseData;
        }
    
        /**
         * Parses file ownership attributes and adds them to the response data.
         *
         * @param responseData the response data to add attributes to
         * @param file the file to parse attributes from
         * @return the file owner attribute view
         * @throws CrawlingAccessException if parsing fails
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.8K bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

        }
    
        public void testParse() {
            RobotsTxt robotsTxt;
            final InputStream in = RobotsTxtHelperTest.class.getResourceAsStream("robots.txt");
            try {
                robotsTxt = robotsTxtHelper.parse(in);
            } finally {
                CloseableUtil.closeQuietly(in);
            }
    
            for (String userAgent : new String[] { "FessCrawler", "FessCrawler/1.0", "Mozilla FessCrawler" }) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 5.9K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlExtractor.java

            final DOMParser parser = getDomParser();
            try (final Reader reader = new StringReader(content)) {
                parser.parse(new InputSource(reader));
            } catch (final Exception e) {
                logger.warn("Failed to parse the content.", e);
                return new ExtractData(extractString(content));
            }
    
            final Document document = parser.getDocument();
            try {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 9.3K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

            final DOMParser parser = getDomParser();
            try (final InputStream in = responseData.getResponseBody()) {
                final InputSource is = new InputSource(in);
                if (responseData.getCharSet() != null) {
                    is.setEncoding(responseData.getCharSet());
                }
                parser.parse(is);
            } catch (final Exception e) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.1K bytes
    - Viewed (0)
Back to top