haml - Code Search

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

        final String content = htmlXpathExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getHtml_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");

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

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

- 4.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/client/http/HcHttpClientTest.java

        assertEquals("http://localhost/login.html", HcHttpClient.constructRedirectLocation("http://localhost/", "/login.html"));
        assertEquals("http://localhost/path/login.html", HcHttpClient.constructRedirectLocation("http://localhost/path/", "login.html"));
        assertEquals("http://localhost/login.html", HcHttpClient.constructRedirectLocation("http://localhost/path/", "/login.html"));
        assertEquals("https://example.com/newpage",

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

- Last Modified: Sat Sep 06 04:15:37 UTC 2025

- 11.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/RegexRuleTest.java

        responseData.setMimeType("text/html");
        return responseData;
    }

    private ResponseData getTestData2() {
        final ResponseData responseData = new ResponseData();
        responseData.setHttpStatusCode(200);
        responseData.setUrl("https://example.com/");
        responseData.setMimeType("text/html");
        return responseData;
    }

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

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

- 4.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/service/impl/OpenSearchDataServiceTest.java

        assertNotNull(accessResult2);

        accessResult2.setMimeType("text/html");
        dataService.update(accessResult2);

        final AccessResult accessResult3 = dataService.getAccessResult("id1", "http://www.id1.com/");
        assertNotNull(accessResult3);
        assertEquals("text/html", accessResult3.getMimeType());

        dataService.delete("id1");

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

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

- 6.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots.txt

Disallow: /
Allow: /foo/bar/
Crawl-delay: 1314000

# welcome!
User-agent: Googlebot
Crawl-delay: 1

User-agent: *
Disallow: /private/
Disallow: /help        # disallows /help.html, /help/index.html, etc.
Allow: /help/faq.html
Crawl-delay: 3

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

User-agent: Crawler/2.0
Disallow: /ccc

User-agent: Hoge Crawler

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

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 566 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

 * 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/transformer/TransformerTest.java

        transformer.addTransformationRule("\\s+", " "); // Normalize whitespace

        // Simulate crawling response
        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());

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

    }

    /**
     * Gets the pattern used for matching HTML tags.
     *
     * @return the HTML tag pattern
     */
    public Pattern getHtmlTagPattern() {
        return htmlTagPattern;
    }

    /**
     * Sets the pattern used for matching HTML tags.
     *
     * @param htmlTagPattern the HTML tag pattern to set
     */

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/extractor/impl/HtmlExtractorTest.java

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");

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/test/resources/extractor/zip/test.zip

data/folder/file.html テスト data/file.txt テキスト...

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

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 449 bytes

- Viewed (0)

Search Options