Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 152 for Characters (0.06 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/TextUtil.java

             *
             * This method reads characters from the reader and processes them according to the following rules:
             * - ISO control characters and space characters are treated as spaces.
             * - Alphanumeric characters (0-9, A-Z, a-z) are appended to the buffer.
             * - Symbol characters (!-/, :-@, [-`, {-~) are appended to the buffer.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Nov 22 13:28:22 UTC 2025
    - 12K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/XmlUtil.java

        }
    
        /**
         * Strips invalid XML characters from the input string.
         *
         * This method removes characters that are not allowed in XML documents
         * according to the XML 1.0 specification. Valid characters include:
         * - Tab (0x9)
         * - Line feed (0xA)
         * - Carriage return (0xD)
         * - Any character between 0x20 and 0xD7FF
         * - Any character between 0xE000 and 0xFFFD
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Nov 22 13:28:22 UTC 2025
    - 9.5K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/util/CharUtilTest.java

            for (char c : validChars.toCharArray()) {
                assertTrue("Character '" + c + "' should be a valid URL character", CharUtil.isUrlChar(c));
            }
        }
    
        public void test_isUrlChar_boundaryChars() {
            // Test boundary characters for ranges
            assertTrue(CharUtil.isUrlChar('a')); // first lowercase
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 5.6K bytes
    - Viewed (0)
  4. src/main/java/org/codelibs/fess/dict/mapping/CharMappingItem.java

    /**
     * Represents a single character mapping rule that defines how input characters are mapped to output characters
     * for text analysis and search processing. This class is used in character mapping dictionaries to transform
     * text during indexing and search operations.
     *
     * <p>Each mapping item consists of one or more input character sequences that are mapped to a single output
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Nov 20 07:09:00 UTC 2025
    - 7.9K bytes
    - Viewed (0)
  5. src/main/java/org/codelibs/fess/suggest/normalizer/HankakuKanaToZenkakuKana.java

            }
            return c;
        }
    
        /**
         * Merges two characters, handling voiced and semi-voiced sound marks.
         * @param c1 The first character.
         * @param c2 The second character.
         * @return The merged character.
         */
        public static char mergeChar(final char c1, final char c2) {
            if (c2 == '゙') {
    Registered: Sat Dec 20 13:04:59 UTC 2025
    - Last Modified: Mon Nov 17 14:23:01 UTC 2025
    - 6.8K bytes
    - Viewed (0)
  6. fess-crawler/src/test/java/org/codelibs/fess/crawler/util/XmlUtilTest.java

            // Test all special characters
            String input = "Test & < > \"quote\" 'apos'";
            String expected = "Test &amp; &lt; &gt; &quot;quote&quot; &apos;apos&apos;";
            assertEquals(expected, XmlUtil.escapeXml(input));
        }
    
        public void test_escapeXml_noSpecialChars() {
            // Test string without special characters
            String input = "Simple text without special characters";
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 8.3K bytes
    - Viewed (0)
  7. guava/src/com/google/common/io/BaseEncoding.java

       *     separator
       */
      public abstract BaseEncoding withPadChar(char padChar);
    
      /**
       * Returns an encoding that behaves equivalently to this encoding, but adds a separator string
       * after every {@code n} characters. Any occurrences of any characters that occur in the separator
       * are skipped over in decoding.
       *
    Registered: Fri Dec 26 12:43:10 UTC 2025
    - Last Modified: Mon Oct 06 14:51:47 UTC 2025
    - 41.7K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

            /**
             * Compiles a robots.txt path pattern into a regular expression pattern.
             * According to RFC 9309:
             * - '*' matches any sequence of characters (including the empty sequence)
             * - '$' matches the end of the URL path
             * - All other characters are matched literally
             *
             * @param pattern the robots.txt path pattern
             * @return the compiled Pattern object
             */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 18.5K bytes
    - Viewed (0)
  9. src/main/java/org/codelibs/core/lang/StringUtil.java

            if (chars.length >= 2 && Character.isUpperCase(chars[0]) && Character.isUpperCase(chars[1])) {
                return name;
            }
            chars[0] = Character.toLowerCase(chars[0]);
            return new String(chars);
        }
    
        /**
         * Capitalizes a string according to JavaBeans conventions.
         * Note: If the first two characters are uppercase, the string will not be capitalized.
         * <p>
    Registered: Sat Dec 20 08:55:33 UTC 2025
    - Last Modified: Sat Nov 22 11:21:59 UTC 2025
    - 21.5K bytes
    - Viewed (0)
  10. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/TextExtractorEnhancedTest.java

                assertTrue("Error message should contain 'text content'", message.contains("text content"));
            }
        }
    
        /**
         * Test extraction with special characters and control characters.
         */
        public void test_getText_withSpecialCharacters_handlesCorrectly() {
            final String specialContent = "Tab\there\nNewline\rCarriage return\0Null byte";
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 8.9K bytes
    - Viewed (0)
Back to top