Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 20 of 44 for Extract (0.03 sec)

  1. src/main/java/org/codelibs/fess/suggest/converter/KatakanaConverter.java

     * use a tokenizer to process the input.
     *
     * <p>
     * The class provides methods to initialize the converter, convert strings, and
     * check if a tokenizer is enabled. It also includes methods to create a token
     * stream and extract reading information from the stream's attributes, although
     * the tokenizer-related functionality is currently commented out.
     * </p>
     */
    public class KatakanaConverter implements ReadingConverter {
    
    Registered: Fri Sep 19 09:08:11 UTC 2025
    - Last Modified: Fri Jul 04 14:00:23 UTC 2025
    - 6.1K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractor.java

            } catch (final MessagingException e) {
                throw new ExtractException(e);
            }
        }
    
        /**
         * Puts a value into the extract data with appropriate type conversion.
         *
         * @param data the extract data to store the value in
         * @param key the key for the value
         * @param value the value to store
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 12.6K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlExtractor.java

                });
                return extractData;
            } finally {
                xpathAPI.remove();
            }
        }
    
        /**
         * Extracts strings from a document using the specified XPath expression.
         *
         * @param document the DOM document to extract strings from
         * @param path the XPath expression to evaluate
         * @return an array of strings extracted from the document
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 9.3K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/TextTransformer.java

    import jakarta.annotation.Resource;
    
    /**
     * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
     * It uses an Extractor to extract the text from the response body based on the MIME type.
     * The extracted text is then converted into a byte array using the specified charset encoding.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 6.5K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/JodExtractor.java

                }
    
                return extractData;
            } catch (final OfficeException e) {
                throw new ExtractException("Could not extract a content.", e);
            } finally {
                FileUtil.deleteInBackground(inputFile);
                FileUtil.deleteInBackground(outputFile);
            }
        }
    
        /**
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.3K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

                throw new RobotsTxtException("Failed to parse robots.txt.", e);
            }
        }
    
        /**
         * Extracts the value from a line using the given pattern.
         * @param pattern the pattern to match against
         * @param line the line to extract the value from
         * @return the extracted value, or null if no match
         */
        protected String getValue(final Pattern pattern, final String line) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7.7K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractor.java

                } catch (final IOException e) {
                    logger.error("Failed to close httpClient.", e);
                }
            }
        }
    
        /**
         * Extracts text from the input stream using the API endpoint.
         *
         * @param in the input stream to extract text from
         * @param params additional parameters
         * @return the extracted data
         * @throws ExtractException if extraction fails
         */
        @Override
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 12.2K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java

     * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
     * </p>
     *
     * <p>
     * This class provides methods to extract text from an input stream, handling different scenarios such as:
     * </p>
     * <ul>
     *   <li>Normalizing text content</li>
     *   <li>Handling resource names and content types</li>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 30.7K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/net/protocol/storage/Handler.java

            private StatObjectResponse statObject;
    
            /**
             * Constructs a new StorageURLConnection for the specified URL.
             * This constructor parses the URL to extract bucket and object names.
             *
             * @param url The storage URL to connect to
             */
            protected StorageURLConnection(final URL url) {
                super(url);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.5K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/form/FormScheme.java

                    logger.debug("Logged in {}", originalLoginUrl);
                }
            });
    
        }
    
        /**
         * Parses the token page and extracts token information.
         * @param tokenPattern The regex pattern to extract the token.
         * @param responseParams The list to store response parameters.
         * @param entity The HTTP entity containing the token page content.
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14.3K bytes
    - Viewed (1)
Back to top