Content - Code Search

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

        String extention;
        String content;
        if (File.separator.equals("/")) {
            // Unix
            extention = ".sh";
            content = "#!/bin/bash\nsleep " + sleep + ";cp $1 $2";
        } else {
            // Windows
            extention = ".bat";
            content = "ping localhost -n " + sleep + "\r\ncopy %1 %2";
        }
        File file;

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

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

- 9.8K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/test/java/org/codelibs/fess/suggest/analysis/SuggestAnalyzerTest.java

        String field = "content";
        String lang = "en";

        List<AnalyzeToken> tokens = analyzer.analyze(text, field, lang);

        assertNotNull(tokens);
        assertTrue(tokens.isEmpty());
    }

    @Test
    public void testAnalyzeWithNullText() {
        // Test analyze with null text
        String text = null;
        String field = "content";
        String lang = "en";

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Mon Sep 01 13:33:03 UTC 2025

- 15.7K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/test/java/org/codelibs/fess/suggest/converter/ReadingConverterTest.java

    }

    @Test
    public void testConvertWithNormalText() throws IOException {
        // Test convert with normal text
        converter.init();
        String text = "hello world";
        String field = "content";

        List<String> readings = converter.convert(text, field, "en");

        assertNotNull(readings);
        assertEquals(1, readings.size());
        assertEquals("HELLO WORLD", readings.get(0));
    }

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Mon Sep 01 13:33:03 UTC 2025

- 13.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(LhaExtractor.class);

    /** Maximum content size for extraction. -1 means no limit. */

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

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

- 5.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

    }

    /**
     * Gets the extracted content.
     *
     * @return the extracted content
     */
    public String getContent() {
        return content;
    }

    /**
     * Sets the extracted content.
     *
     * @param content the content to set
     */
    public void setContent(final String content) {
        this.content = content;
    }

    /**

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

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

- 3.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        Map<String, String> params = new HashMap<>();
        params.put("Content-Type", "text/plain");
        final ExtractData extractData = tikaExtractor.getText(in, params);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    // TODO tika needs to support pdfbox 2.0
    //    public void test_getTika_pdf() {

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

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 30.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        assertTrue(content.contains("画像1"));
        assertTrue(content.contains("画像2"));
        assertTrue(content.contains("タイトル1"));
        assertTrue(content.contains("タイトル2"));
        assertTrue(content.contains("リンク1"));
    }

    public void test_getHtml_empty() {
        final InputStream in = new ByteArrayInputStream("".getBytes());
        final String content = htmlXpathExtractor.getText(in, null).getContent();

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/resources/html/test1.shtml

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>タイトル</title>
</head>
<body>
<h1>第一章</h1>
<h2>第一節</h2>
<p>ほげほげ<br>ふがふが</p>
<p>
<a href="test2.html">LINK</a>
</p>
<h1>第2章</h1>
<h2>第2節</h2>
</body>

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

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

- 289 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        params.put("resourceName", "test.odt");
        ExtractData extractData = jodExtractor.getText(in, params);
        String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_ooow_as() {
        InputStream in = ResourceUtil.getResourceAsStream("extractor/ooo/test_as.odt");

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

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

- 9.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/ajax/index.html

<!DOCTYPE html>
<html>
<head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
    <title>Ajax Test</title>
    <script language="javascript" src="js/jquery-2.1.1.min.js" type="text/javascript"></script>
    <script language="javascript" src="js/test.js" type="text/javascript"></script>
</head>
<body>
    <div id="header">
        <h1>Ajax Test Site</h1>
    </div>
    <div id="menubar">
        <ul>

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

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

- 1.5K bytes

- Viewed (0)

Search Options