Next - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/SitemapsHelper.java

import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.

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

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

- 14.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/client/fs/FileSystemClientTest.java

        assertNotNull(responseData.getLastModified());
        assertEquals(Constants.GET_METHOD, responseData.getMethod());
        assertEquals("text/plain", responseData.getMimeType());
        assertTrue(responseData.getUrl().endsWith("test/text%203.txt"));
        final String content = new String(InputStreamUtil.getBytes(responseData.getResponseBody()), "UTF-8");
        assertEquals("test3\n", content);
    }

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

- Last Modified: Sat Sep 06 04:15:37 UTC 2025

- 8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {
        super();
    }

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.

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

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

- 2.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.
 *
 * @author shinsuke
 *
 */
public class MsVisioExtractor extends AbstractExtractor {

    /**
     * Creates a new MsVisioExtractor instance.
     */
    public MsVisioExtractor() {
        super();
    }

    /**
     * Extracts text from the Visio input stream.
     * @param in The input stream.

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

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

- 1.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

     */
    public LhaExtractor() {
        super();
    }

    /**
     * Extracts text content from an LHA archive input stream.
     *
     * @param in the input stream containing the LHA archive
     * @param params extraction parameters
     * @return the extracted text data
     * @throws CrawlerSystemException if the input stream is null

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

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

- 5.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

<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-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractorTest.java

        final Map<String, String> params = new HashMap<String, String>();
        //final ExtractData text = extractor.getText(new ByteArrayInputStream(FileUtils.readFileToByteArray(new File(filePath))), params);
        final ExtractData text = extractor.getText(new ByteArrayInputStream(testStr.getBytes()), params);
        assertEquals(content, text.getContent());
    }

    // TODO other tests

    static class TestApiExtractorServer {

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

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

- 5.4K 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-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/ExtractData.java

    public static final String FILE_PASSWORDS = "file.passwords";

    /** Map containing metadata key-value pairs */
    protected Map<String, String[]> metadata = new HashMap<>();

    /** The extracted content text */
    protected String content;

    /**
     * Constructs a new ExtractData.
     */
    public ExtractData() {
        // Default constructor
    }

    /**

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

- Last Modified: Sat Sep 06 04:15:37 UTC 2025

- 3.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

                logger.error("Failed to close httpClient.", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

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

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 12.2K bytes

- Viewed (0)

Search Options