ulink - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.
 * These RequestData objects are added to a set of child URLs, which are then
 * passed to a {@link ChildUrlsException} to be processed by the crawler.
 * </p>
 *
 * <p>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 3.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/util/XPathAPI.java

    }

    /**
     * Creates an instance of {@link XPath} using the provided {@link Consumer} to configure the {@link XPathFactory}.
     *
     * @param builder a {@link Consumer} that accepts an {@link XPathFactory} and configures it.
     * @return a configured instance of {@link XPath}.
     * @throws CrawlerSystemException if an error occurs while creating the {@link XPath} instance.
     */

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 4.6K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/index/contents/document/DocumentReader.java

 * Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *
 * <p>This interface extends {@link java.io.Closeable}, so implementations
 * should also handle resource cleanup when the {@link #close()} method is called.</p>
 */
public interface DocumentReader extends Closeable {
    /**
     * Reads a document and returns its contents as a map.
     *

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Fri Jul 04 14:00:23 UTC 2025

- 1.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/AbstractRule.java

import org.codelibs.fess.crawler.rule.RuleManager;

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Wed Sep 03 14:42:53 UTC 2025

- 2.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/exception/CrawlerSystemException.java

     *
     * @param message the detail message (which is saved for later retrieval by the {@link #getMessage()} method).
     * @param cause the cause (which is saved for later retrieval by the {@link #getCause()} method).
     *              (A {@code null} value is permitted, and indicates that the cause is nonexistent or unknown.)
     */

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 3K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/normalizer/NormalizerChain.java

 * chain.add(new AnotherNormalizer());
 * String normalizedText = chain.normalize("input text", "field", "en");
 * </pre>
 *
 * <p>Methods:</p>
 * <ul>
 *   <li>{@link #normalize(String, String, String...)} - Applies all added normalizers to the input text.</li>
 *   <li>{@link #add(Normalizer)} - Adds a new normalizer to the chain.</li>
 * </ul>
 *
 * <p>Fields:</p>
 * <ul>

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Fri Jul 04 14:00:23 UTC 2025

- 2.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/html/test1.html

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>タイトル</title>
</head>
<body>
<h1>第一章</h1>
<h2>第一節</h2>
<p>ほげほげ<br>ふがふが</p>
<p>
<a href="test2.html">LINK</a>
</p>
<h1>第2章</h1>
<h2>第2節</h2>
</body>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 289 bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/SuggesterBuilder.java

import org.opensearch.transport.client.Client;

/**
 * Builder class for creating instances of {@link Suggester}.
 * This class allows for the configuration of various components used by the {@link Suggester}.
 */
public class SuggesterBuilder {
    /**
     * Constructs a new {@link SuggesterBuilder}.
     */
    public SuggesterBuilder() {
        // nothing
    }

    /** The suggest settings. */

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Fri Jul 04 14:00:23 UTC 2025

- 6K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/converter/ReadingConverterChain.java

 */
package org.codelibs.fess.suggest.converter;

import java.io.IOException;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;
import java.util.Queue;

/**
 * A chain of {@link ReadingConverter} implementations that applies each converter in sequence to generate possible reading variations of a given text.

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Fri Jul 04 14:00:23 UTC 2025

- 2.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/util/CrawlingParameterUtil.java

 *
 * <p>The following parameters are managed:</p>
 * <ul>
 *   <li>{@link UrlQueue} - The queue of URLs to be crawled.</li>
 *   <li>{@link CrawlerContext} - The context of the current crawling process.</li>
 *   <li>{@link UrlQueueService} - The service for managing the URL queue.</li>
 *   <li>{@link DataService} - The service for managing access results.</li>
 * </ul>
 *

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 6.4K bytes

- Viewed (0)

Search Options