Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for normalize_text (0.27 sec)

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

        public static final String TIKA_TESSERACT_CONFIG = "tika.tesseract.config";
    
        public static final String TIKA_PDF_CONFIG = "tika.pdf.config";
    
        public static final String NORMALIZE_TEXT = "normalize_text";
    
        private static final String FILE_PASSWORD = "fess.file.password";
    
        protected String outputEncoding = Constants.UTF_8;
    
        protected boolean readAsTextIfFailed = false;
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:41:37 UTC 2024
    - 25K bytes
    - Viewed (0)
  2. src/main/java/org/codelibs/fess/crawler/transformer/AbstractFessFileTransformer.java

            if (configParam != null) {
                final String keepOriginalBody = configParam.get(Config.KEEP_ORIGINAL_BODY);
                if (StringUtil.isNotBlank(keepOriginalBody)) {
                    params.put(TikaExtractor.NORMALIZE_TEXT,
                            Constants.TRUE.equalsIgnoreCase(keepOriginalBody) ? Constants.FALSE : Constants.TRUE);
                }
            }
            return params;
        }
    
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Oct 11 21:11:58 UTC 2024
    - 23.6K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/TextUtil.java

            public TextNormalizeContext spaceChars(final int[] spaceChars) {
                this.spaceChars = spaceChars;
                return this;
            }
        }
    
        public static TextNormalizeContext normalizeText(final Reader reader) {
            return new TextNormalizeContext(reader);
        }
    
        private static boolean isLastSpaceChar(final StringBuilder buf) {
            if (buf.length() == 0) {
                return false;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 7.9K bytes
    - Viewed (0)
Back to top