- Sort Score
- Num 10 results
- Language All
Results 41 - 50 of 639 for crawling (0.07 seconds)
-
fess-crawler-opensearch/src/main/java/org/codelibs/fess/crawler/service/impl/OpenSearchUrlQueueService.java
*/ public void setPollingFetchSize(final int pollingFetchSize) { this.pollingFetchSize = pollingFetchSize; } /** * Sets the maximum crawling queue size. * @param maxCrawlingQueueSize The maximum crawling queue size. */ public void setMaxCrawlingQueueSize(final int maxCrawlingQueueSize) { this.maxCrawlingQueueSize = maxCrawlingQueueSize; }Created: Sun Apr 12 03:50:13 GMT 2026 - Last Modified: Thu Nov 20 08:40:57 GMT 2025 - 16.9K bytes - Click Count (1) -
MIGRATION.md
#### Migration Steps **Step 1: Set Up Fess Crawling** 1. In Fess Admin, create a new Web crawling configuration 2. Add your website URL as the starting point 3. Configure crawl depth and URL patterns 4. Start crawling **Step 2: Replace JavaScript Code** Replace existing GSS/CSE code: ```javascript <!-- Old GSS/CSE Code -->
Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Thu Nov 06 12:40:11 GMT 2025 - 23.2K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/helper/DocumentHelper.java
} } /** * Processes a crawling request for a specific URL. * Executes the full crawling pipeline including client execution, rule processing, * transformation, and data extraction. * * @param crawlingConfig the crawling configuration to use * @param crawlingInfoId the crawling session ID * @param url the URL to processCreated: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Mon Mar 30 14:27:04 GMT 2026 - 17.4K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/crawler/FessCrawlerThread.java
* This class extends the base CrawlerThread and provides Fess-specific functionality for * crawling and indexing documents, including incremental crawling capabilities, content * modification checking, and integration with the Fess search engine backend. * * <p>Key features include:</p> * <ul> * <li>Incremental crawling support with last-modified timestamp checking</li> * <li>Document expiration handling</li>
Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Thu Dec 11 09:47:03 GMT 2025 - 19.5K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/app/service/FailureUrlService.java
import org.dbflute.optional.OptionalEntity; import jakarta.annotation.Resource; /** * Service class for managing failure URLs that occur during web crawling. * Provides functionality to store, retrieve, and manage failed crawling attempts * with their associated error information. */ public class FailureUrlService { /** Logger instance for this class */Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Thu Jul 17 08:28:31 GMT 2025 - 9.2K bytes - Click Count (0) -
src/test/java/org/codelibs/fess/exception/DataStoreCrawlingExceptionTest.java
// Test that constructor accepts Error as cause (verifies Throwable parameter change) String url = "http://example.com/large-dataset"; String message = "Crawling failed due to memory exhaustion"; OutOfMemoryError error = new OutOfMemoryError("Heap space exhausted"); DataStoreCrawlingException exception = new DataStoreCrawlingException(url, message, error);
Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Sun Jan 11 08:43:05 GMT 2026 - 16.6K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/app/web/api/admin/crawlinginfo/EditBody.java
import org.codelibs.fess.app.web.admin.crawlinginfo.EditForm; /** * Request body class for crawling info edit operations in the admin REST API. * This class extends EditForm to inherit the necessary form validation and binding capabilities * for crawling information management operations. */ public class EditBody extends EditForm { /** * Default constructor. */Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Thu Jul 17 08:28:31 GMT 2025 - 1.1K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/crawler/interval/FessIntervalController.java
import org.codelibs.fess.util.ComponentUtil; /** * FessIntervalController extends DefaultIntervalController to provide * Fess-specific interval control functionality for web crawling operations. * This controller manages delays and timing for various crawling states * including processing delays, queue waiting times, and new URL discovery. */ public class FessIntervalController extends DefaultIntervalController {Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Wed Nov 19 07:09:17 GMT 2025 - 5.1K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/app/web/api/admin/failureurl/SearchBody.java
*/ public class SearchBody extends BaseSearchBody { /** * Default constructor. */ public SearchBody() { super(); } /** The URL that failed during crawling */ public String url; /** Minimum error count filter */ public Integer errorCountMin; /** Maximum error count filter */ public Integer errorCountMax;Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Thu Jul 17 08:28:31 GMT 2025 - 1.2K bytes - Click Count (0) -
src/main/java/org/codelibs/fess/exception/ContentNotFoundException.java
*/ package org.codelibs.fess.exception; /** * Exception thrown when requested content cannot be found. * Typically used when a document or resource is not available during crawling or indexing. */ public class ContentNotFoundException extends FessSystemException { private static final long serialVersionUID = 1L; /**Created: Tue Mar 31 13:07:34 GMT 2026 - Last Modified: Thu Jul 17 08:28:31 GMT 2025 - 1.3K bytes - Click Count (0)