texts - Code Search

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/java/org/codelibs/fess/crawler/extractor/impl/TarExtractorTest.java

                    TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/tar", tarExtractor);
                })//
        ;

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

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

- 3.7K 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/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/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/test/java/org/codelibs/fess/crawler/transformer/TransformerTest.java

        responseData.setUrl("http://example.com");
        responseData.setResponseBody("This is old text with 123 numbers".getBytes());

        ResultData resultData = transformer.transform(responseData);

        assertNotNull(resultData);
        assertEquals("contentTransformer", resultData.getTransformerName());
        assertEquals("This is new text with NUMBER numbers", new String(resultData.getData()));

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

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

- 28K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/request/popularwords/PopularWordsRequest.java

        }

        for (final SearchHit hit : hits) {
            final Map<String, Object> source = hit.getSourceAsMap();
            final String text = source.get(FieldNames.TEXT).toString();
            words.add(text);

            if (detail) {
                items.add(SuggestItem.parseSource(source));
            }
        }

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

- Last Modified: Thu Aug 07 02:41:28 UTC 2025

- 9.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/AbstractRuleTest.java

        conditionalRule.setUrlPattern("https?://.*\\.example\\.com/.*");
        conditionalRule.setMimeTypePattern("text/.*");

        // Test matching
        ResponseData responseData1 = new ResponseData();
        responseData1.setUrl("http://www.example.com/page");
        responseData1.setMimeType("text/html");
        assertTrue(conditionalRule.match(responseData1));

        // Test non-matching URL

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

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

- 21.9K 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