tbody - Code Search

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/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)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/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

- 5K bytes

- Viewed (0)

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)

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/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)

github.com/codelibs/fess-crawler

fess-crawler/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/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)

github.com/codelibs/fess-crawler

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

    /** Map of parser properties. */
    protected Map<String, String> propertyMap = new HashMap<>();

    /** XPath expression for extracting content from the document body. */
    protected String contentXpath = "//BODY";

    /** Map of metadata field names to their corresponding XPath expressions. */
    protected Map<String, String> metadataXpathMap = new HashMap<>();

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

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

- 9.3K 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)

Search Options