comment - Code Search

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

        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getXml_mm() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test.mm");
        final String content = xmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

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

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

- 6.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/MimeTypeHelper.java

 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.
 * It allows content type detection based on the stream's content and/or filename.
 */
public interface MimeTypeHelper {
    /**
     * Determines the content type of the given input stream and filename.
     * @param is the input stream to analyze
     * @param filename the filename to help determine the content type
     * @return the detected content type

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

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

- 1.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        String content = "<input name=\"authenticity_token\" value=\"abcdefg\">";
        assertEquals("abcdefg", formScheme.getTokenValue(tokenPattern, content));

        tokenPattern = "name=\"authenticity_token\" +value=\"[^\"]+\"";
        content = "<input name=\"authenticity_token\" value=\"abcdefg\">";
        assertNull(formScheme.getTokenValue(tokenPattern, content));

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

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

- 1.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        String content;

        content = "...;charset=UTF-8\"...";
        assertEquals("UTF-8", htmlTransformer.parseCharset(content));

        content = "...; charset=UTF-8\"...";
        assertEquals("UTF-8", htmlTransformer.parseCharset(content));

        content = "...;charset = UTF-8\"...";
        assertEquals("UTF-8", htmlTransformer.parseCharset(content));

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/pom.xml

		</dependency>
		<dependency>
			<groupId>commons-codec</groupId>
			<artifactId>commons-codec</artifactId>
			<version>${commons.codec.version}</version>
		</dependency>
		<dependency>
			<groupId>commons-io</groupId>
			<artifactId>commons-io</artifactId>
			<version>${commons.io.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-lang3</artifactId>

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

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

- 11.3K 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-crawler

fess-crawler/src/test/resources/extractor/test_sjis.html

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Shift_JIS"/>
<title>�^�C�g��</title>
</head>
<body>
�e�X�g
</body>

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

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

- 149 bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/test/java/org/codelibs/fess/suggest/index/contents/DefaultContentsParserTest.java

    String[] supportedFields = new String[] { "content", "title" };
    String[] tagFieldNames = new String[] { "label", "virtual_host" };
    String roleFieldName = "role";

    public void test_parseQueryLog() throws Exception {

        QueryLog queryLog = new QueryLog("content:検索エンジン", null);

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

- Last Modified: Sat Mar 15 06:51:20 UTC 2025

- 3.4K 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)

Search Options