Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 10 for Body (0.01 sec)

  2. 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)
  3. 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)
  4. github.com/codelibs/fess-crawler

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

                xpathTransformer.setChildUrlRuleMap(childUrlRuleMap);
            Map<String, String> fieldRuleMap = newLinkedHashMap();
            fieldRuleMap.put("title", "//TITLE");
            fieldRuleMap.put("body", "//BODY");
            fieldRuleMap.put("pcount", "count(//P)");
            fieldRuleMap.put("true", "true()");
            fieldRuleMap.put("false", "false()");
            xpathTransformer.setFieldRuleMap(fieldRuleMap);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 12.5K 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/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)
  7. github.com/codelibs/fess-crawler

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

            url = "/../../../index.html";
        assertEquals("/../index.html", htmlTransformer.normalizeUrl(url));
    }

    public void test_getData() throws Exception {
        final String value = "<html><body>hoge</body></html>";
        final AccessResultDataImpl accessResultDataImpl = new AccessResultDataImpl();
        accessResultDataImpl.setData(value.getBytes());
        accessResultDataImpl.setEncoding(Constants.UTF_8);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 13.8K bytes
    - Viewed (0)
  8. 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)
  9. github.com/codelibs/fess-crawler

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

            // TODO support other type
        return "<?xml version=\"1.0\"?>\n<doc>\n";
    }

    /**
     * Returns the body of the result data for a single value.
     * @param name The name of the field.
     * @param value The value of the field.
     * @return The result data body.
     */
    protected String getResultDataBody(final String name, final String value) {
        // TODO support other type
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 23.9K bytes
    - Viewed (0)
  10. 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)
  11. 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)
Back to top