Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 20 of 58 for rules (0.01 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/RuleManager.java

         */
        /**
         * Adds a rule to the specified index.
         *
         * @param index the position at which the rule should be added
         * @param rule the rule to be added
         */
        void addRule(int index, Rule rule);
    
        /**
         * Removes the specified rule from the rule manager.
         *
         * @param rule the rule to be removed
         * @return true if the rule was successfully removed, false otherwise
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.1K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

        }
    
        /**
         * Gets the map of child URL extraction rules.
         *
         * @return the child URL rule map
         */
        public Map<String, String> getChildUrlRuleMap() {
            return childUrlRuleMap;
        }
    
        /**
         * Sets the map of child URL extraction rules.
         *
         * @param childUrlRuleMap the child URL rule map to set
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 28.5K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/TextUtil.java

    /**
     * Utility class for text normalization and processing.
     *
     * This class provides methods to normalize text by reading characters from a provided Reader
     * and processing them according to specific rules. The main functionality is encapsulated
     * within the nested {@link TextNormalizeContext} class.
     *
     * <p>The text normalization process includes:
     * <ul>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 12K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/filter/impl/UrlFilterImpl.java

    /**
     * Implementation of the {@link UrlFilter} interface.
     * This class provides functionality to filter URLs based on include and exclude patterns.
     * It uses a {@link UrlFilterService} to manage the URL filtering rules.
     * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.
     * It also provides methods to initialize the filter with a session ID, clear the filter,
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 9.2K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/TransformerTest.java

                // Apply transformation rules
                try (InputStream is = responseData.getResponseBody()) {
                    byte[] bytes = is.readAllBytes();
                    String content = new String(bytes);
                    for (Map.Entry<String, String> rule : transformationRules.entrySet()) {
                        content = content.replaceAll(rule.getKey(), rule.getValue());
                    }
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 28K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/service/impl/UrlFilterServiceImpl.java

    import org.codelibs.fess.crawler.service.UrlFilterService;
    
    import jakarta.annotation.Resource;
    
    /**
     * Implementation of the {@link UrlFilterService} interface.
     * This class provides methods for managing URL filtering rules,
     * including adding include and exclude URL patterns, deleting patterns,
     * and retrieving lists of compiled URL patterns. It utilizes a
     * {@link MemoryDataHelper} to store and manage the URL patterns in memory.
     *
     */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.2K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java

        /**
         * Sets whether to use robots.txt disallow rules.
         *
         * @param useRobotsTxtDisallows True to use disallow rules, false otherwise
         */
        public void setUseRobotsTxtDisallows(final boolean useRobotsTxtDisallows) {
            this.useRobotsTxtDisallows = useRobotsTxtDisallows;
        }
    
        /**
         * Sets whether to use robots.txt allow rules.
         *
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 52.2K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

            }
        }
    
        /**
         * Returns the field rule map.
         * @return The field rule map.
         */
        public Map<String, String> getFieldRuleMap() {
            return fieldRuleMap;
        }
    
        /**
         * Sets the field rule map.
         * @param fieldRuleMap The field rule map to set.
         */
        public void setFieldRuleMap(final Map<String, String> fieldRuleMap) {
    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/CrawlerContext.java

            this.urlFilter = urlFilter;
        }
    
        /**
         * Returns the rule manager.
         * @return The RuleManager.
         */
        public RuleManager getRuleManager() {
            return ruleManager;
        }
    
        /**
         * Sets the rule manager.
         * @param ruleManager The RuleManager.
         */
        public void setRuleManager(final RuleManager ruleManager) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 8.9K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XmlTransformer.java

     *   <li>Coalescing</li>
     *   <li>Entity expansion</li>
     *   <li>Ignoring comments and whitespace</li>
     *   <li>Validation</li>
     *   <li>XInclude awareness</li>
     * </ul>
     *
     * <p>
     * It also allows defining field rules using XPath expressions to extract specific data from the XML document and map it to fields in the ResultData.
     * The extracted data is then formatted into an XML structure suitable for indexing.
     * </p>
     *
     * <p>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 23.9K bytes
    - Viewed (0)
Back to top