Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 14 for Body (0.04 sec)

  2. github.com/codelibs/fess-crawler

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

        /**
     * Checks if this response has a response body.
     *
     * @return true if the response has a body (either as bytes or file), false otherwise
     */
    public boolean hasResponseBody() {
        return responseBodyBytes != null || responseBodyFile != null;
    }

    /**
     * Gets the response body as an InputStream.
     * If the response body is stored as bytes, returns a ByteArrayInputStream.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 11.6K bytes
    - Viewed (0)
  3. github.com/codelibs/fess-crawler

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

        }

    /**
     * Creates a temporary file containing the response body from the given ResponseData.
     *
     * @param responseData the response data containing the response body
     * @return a temporary file containing the response body
     * @throws CrawlingAccessException if an error occurs while reading the response body
     */
    public static File createResponseBodyFile(final ResponseData responseData) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.4K bytes
    - Viewed (0)
  4. github.com/codelibs/fess-crawler

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

     *
 * <p>
 * This transformer extracts the binary content from the response body of a web resource,
 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>
 * The transform method takes a ResponseData object, checks if it has a response body,
 * and then reads the body into a byte array. This byte array is then set as the data
 * in the ResultData object.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.8K bytes
    - Viewed (0)
  5. github.com/codelibs/fess-crawler

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

     * transformer.addFieldRule("title", "//title/text()");
 * transformer.addFieldRule("body", "//body/p/text()");
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setBody(new ByteArrayInputStream("&lt;html&gt;&lt;head&gt;&lt;title&gt;Example&lt;/title&gt;&lt;/head&gt;&lt;body&gt;&lt;p&gt;Hello World&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;".getBytes()));
 * responseData.setUrl("http://example.com");
 *
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.1K bytes
    - Viewed (0)
  6. github.com/codelibs/fess-crawler

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

    import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 6.5K bytes
    - Viewed (0)
  7. github.com/codelibs/fess-crawler

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

        public void setMailProperties(final Properties mailProperties) {
        this.mailProperties = mailProperties;
    }

    /**
     * Extracts the body text from a MIME message.
     *
     * @param message the MIME message to extract text from
     * @return the extracted body text
     * @throws ExtractException if extraction fails
     */
    protected String getBodyText(final MimeMessage message) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 12.6K bytes
    - Viewed (0)
  8. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/TextTransformerTest.java 

            assertEquals("xyz", new String(resultData.getData(), resultData.getEncoding()));
    }

    public void test_transform_html() throws Exception {
        final byte[] data = new String("<html><body>xyz</body></html>").getBytes();
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("file:/test.html");
        responseData.setCharSet(Constants.UTF_8);
        responseData.setResponseBody(data);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (0)
  9. github.com/codelibs/fess-crawler

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

    import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  10. github.com/codelibs/fess-crawler

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

    /**
 * SitemapsRule is a rule implementation that extends RegexRule to determine if a given response data
 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.6K bytes
    - Viewed (0)
  11. github.com/codelibs/fess-crawler

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

     * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.
 * The default value for {@code targetNodePath} is "//HTML/BODY | //@alt | //@title", which selects the body of the HTML document,
 * as well as the alt and title attributes.
 * </p>
 * <p>
 * The class uses {@link DOMParser} to parse HTML documents and {@link XPathAPI} to execute XPath queries.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.3K bytes
    - Viewed (0)
Back to top