body - Code Search

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)

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)

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)

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)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/TransformerTest.java

        ResponseData responseData = new ResponseData();
        responseData.setUrl("http://example.com/page.html");
        responseData.setParentUrl("http://example.com/");
        responseData.setResponseBody("<html><body>  Test   Content  </body></html>".getBytes());
        responseData.setHttpStatusCode(200);
        responseData.setMimeType("text/html");

        // Transform response

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-crawler

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

        final String value = "<?xml version=\"1.0\"?>\n"//
                + "<doc>\n"//
                + "<field name=\"title\">タイトル</field>\n"//
                + "<field name=\"body\">第一章 第一節 ほげほげふがふが LINK 第2章 第2節</field>\n"//
                + "<field name=\"list\"><list><item>リスト1</item><item>リスト2</item><item>リスト3</item></list></field>\n"//
                + "</doc>";

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

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

- 13.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

    private static String getHtmlContent(final int count) {
        final StringBuilder buf = new StringBuilder();
        buf.append("<html><head><title>Title ");
        buf.append(count);
        buf.append("</title></head><body><h1>Content ");
        buf.append(count);
        buf.append("</h1><br>");
        buf.append("<a href=\"index.html\">Index</a><br>");
        for (int i = 1; i <= 10; i++) {
            buf.append("<a href=\"file");

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

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

- 6.3K bytes

- Viewed (0)

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)

github.com/codelibs/fess-crawler

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

    @Override
    public ResultData transform(final ResponseData responseData) {
        if (responseData == null || !responseData.hasResponseBody()) {
            throw new CrawlingAccessException("No response body.");
        }

        // encoding
        updateCharset(responseData);

        final ResultData resultData = new ResultData();
        resultData.setTransformerName(getName());

        try {

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

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

- 28.5K bytes

- Viewed (0)

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)

Search Options