_content - Code Search

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

     * @return An ExtractData object containing the filename as content.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        final String content = params.getOrDefault(ExtractData.RESOURCE_NAME_KEY, StringUtil.EMPTY);
        try {

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/test/java/org/codelibs/fess/crawler/extractor/impl/LhaExtractorTest.java

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/lha/test.lzh");
        final String content = lhaExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertTrue(content.contains("テキスト"));
    }

    public void test_getText_maxSize() throws IOException {

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

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

- 3.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

    }

    /**
     * Returns the default maximum content length.
     * @return The default maximum content length in bytes.
     */
    public long getDefaultMaxLength() {
        return defaultMaxLength;
    }

    /**
     * Sets the default maximum content length.
     * @param defaultMaxLength The default maximum content length to set.
     */

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

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

- 3.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test.txt");
        final String content = textExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_null() {
        try {
            textExtractor.getText(null, null);

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

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

- 2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/extractor/eml/sample2.eml

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="viewport" content="width=device-width, minimum-scale=1.0, maximum-scale=1.0, user-scalable=0" />
<meta name="apple-mobile-web-app-capable" content="yes" />
<style type="text/css">

@media only screen and (max-width: 420px) {
a[class="article-headline"] {

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

- Last Modified: Sat Jan 16 07:50:35 UTC 2016

- 91.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

            ExtractData data = emlExtractor.getText(in, null);
            final String content = data.getContent();
            logger.info(content);
            assertTrue(content.contains("Exkursion und Museumsbesuch"));
            assertTrue(content.contains("Fahrt nach Baruth"));
            assertTrue(content.contains("Technische Universität"));
        }
    }

    public void test_getText_null() {

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

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

- 4.6K bytes

- Viewed (1)

github.com/codelibs/fess-crawler

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

        final String content = data.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertEquals("タイトル", data.getValues("title")[0]);
    }

    public void test_getHtml_empty() {
        final InputStream in = new ByteArrayInputStream("".getBytes());
        final String content = htmlExtractor.getText(in, null).getContent();

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

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

- 3.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/TextTransformer.java

        params.put(ExtractData.RESOURCE_NAME_KEY, getResourceName(responseData));
        params.put(ExtractData.CONTENT_TYPE, responseData.getMimeType());
        String content = null;
        try (final InputStream in = responseData.getResponseBody()) {
            content = extractor.getText(in, params).getContent();
        } catch (final Exception e) {
            throw new CrawlingAccessException("Could not extract data.", e);
        }

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

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

- 6.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/main/java/org/codelibs/fess/crawler/entity/OpenSearchUrlFilter.java

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

import java.io.IOException;

import org.opensearch.core.xcontent.ToXContent;
import org.opensearch.core.xcontent.XContentBuilder;

/**
 * OpenSearchUrlFilter is an entity for URL filters in OpenSearch.
 */
public class OpenSearchUrlFilter implements ToXContent {

    /**

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

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

- 3.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        final ExtractData extractData = pdfExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertEquals("Writer", extractData.getValues("Creator")[0]);
        assertEquals("OpenOffice.org 3.0", extractData.getValues("Producer")[0]);

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

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

- 7.6K bytes

- Viewed (0)

Search Options