encoding - Code Search

fess-crawler-lasta/src/main/resources/crawler/encoding.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="encodingHelper" class="org.codelibs.fess.crawler.helper.EncodingHelper">
		<postConstruct name="addEncodingMapping">
			<arg>"unicode"</arg>
			<arg>"UTF-16LE"</arg>
		</postConstruct>
	</component>

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

- Last Modified: Fri Jun 16 13:35:06 UTC 2017

- 454 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        final String encoding = xmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("Shift_JIS", encoding);
    }

    public void test_getEncoding_utf8bom() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/xml/test_utf8bom.xml");
        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = xmlExtractor.getEncoding(bis);

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/transformer/impl/TextTransformer.java

 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>

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

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

- 6.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/extractor/test_utf8.xml

<?xml version="1.0" encoding="UTF-8"?>
<html>
<head>
<title>タイトル</title>
</head>
<body>
<div>テスト $test</div>
<!-- コメント -->
</body>

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

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

- 161 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

    }

    /**
     * Returns the current encoding setting.
     * @return The current encoding.
     */
    public String getEncoding() {
        return encoding;
    }

    /**
     * Sets the encoding for content extraction.
     * @param encoding The encoding to set.
     */
    public void setEncoding(final String encoding) {
        this.encoding = encoding;
    }

    /**

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

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

- 8.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/container.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">

	<component class="org.lastaflute.di.naming.StyledNamingConvention">
	</component>

	<!-- Container -->
	<component name="crawlerContainer"
		class="org.codelibs.fess.crawler.container.LastaCrawlerContainer">
	</component>

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

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

- 418 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/filter.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="urlFilter"
		class="org.codelibs.fess.crawler.filter.impl.UrlFilterImpl" instance="prototype">
	</component>

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

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

- 364 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

     */
    void setData(byte[] data);

    /**
     * Retrieves the encoding used for the access result data.
     *
     * @return the encoding as a String.
     */
    String getEncoding();

    /**
     * Sets the encoding for the access result data.
     *
     * @param encoding the encoding to set
     */
    void setEncoding(String encoding);

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

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

- 2.2K bytes

- Viewed (10)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/extractor/test.xml

<?xml version="1.0" encoding="UTF-8"?>
<address xmlns:hoge="http://www.example.com/hoge">
	<item sex="male" custid="A12345">
		<name>鈴木太郎</name>
		<access kind="email"></access>
		<access kind="url">http://www.taro.com/</access>
		<image file="taro.png" />
	</item>
	<item sex="male" custid="B23456">
		<name>佐藤二朗</name>
		<access kind="email">******@****.***</access>
		<image file="jiro.png" />
	</item>
	<item sex="female" custid="C34567">

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

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

- 582 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlXpathExtractor.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

- 4.2K bytes

- Viewed (0)

Search Options