Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 23 for unparse (0.06 sec)

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

         * @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);
        }
    
        /**
         * Parses a robots.txt file from the given input stream using the specified character encoding.
         * @param stream the input stream to parse
         * @param charsetName the character encoding to use
    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/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java

            } finally {
                FileUtil.deleteInBackground(tempFile);
            }
        }
    
        /**
         * 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) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 30.7K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/XmlUtil.java

                } catch (final Exception e) {
                    if (logger.isDebugEnabled()) {
                        logger.debug("Failed to set a property.", e);
                    }
                }
                // parse a content
                parser.parse(is, handler);
    
                return handler.getDataMap();
            } catch (final Exception e) {
                throw new CrawlerSystemException("Could not create a data map from XML content.", 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/processor/impl/SitemapsResponseProcessor.java

     * 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
     * from each sitemap, and creates a new {@link RequestData} object for each 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)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/fs/FileSystemClient.java

                File file = null;
                try {
                    file = new File(new URI(filePath));
                } catch (final URISyntaxException e) {
                    logger.warn("Could not parse url: " + filePath, e);
                }
    
                if (file == null) {
                    responseData.setHttpStatusCode(Constants.NOT_FOUND_STATUS_CODE);
                    responseData.setCharSet(charset);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.8K bytes
    - Viewed (0)
  7. 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)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

                if (responseData.getCharSet() != null) {
                    is.setEncoding(responseData.getCharSet());
                }
                parser.parse(is);
            } catch (final Exception e) {
                throw new CrawlingAccessException("Could not parse " + responseData.getUrl(), e);
            }
            final Document document = parser.getDocument();
    
            final StringBuilder buf = new StringBuilder(1000);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.1K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/PasswordBasedExtractor.java

                                    .collect(Collectors.toList());
                        } catch (final Exception e) {
                            logger.warn("Failed to parse passwords for " + url, e);
                            list = Collections.emptyList();
                        }
                        configPasswordMap.put(value, list);
                    }
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 5.1K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/PdfExtractor.java

                            }
                        }
                    }
                } catch (final IOException e) {
                    logger.warn("Failed to parse annotation.", e);
                }
            }
        }
    
        /**
         * Extracts text from an embedded file using the appropriate extractor.
         * @param filename the filename of the embedded file
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 12.7K bytes
    - Viewed (0)
Back to top