context - Code Search

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/test/resources/extractor/test_attr.html

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>タイトル</title>
</head>
<body>
本文1
<img src="hoge.gif" alt="画像1"/>
<img src="hoge.gif" alt="画像2" title="タイトル1"/>
<a href="hoge.html" title="タイトル2">リンク1</a>
本文2
</body>

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

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

- 308 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

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

    public void test_getText_null() {
        try {
            msExcelExtractor.getText(null, null);

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

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

- 2.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

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

    public void test_getText_null() {
        try {
            msPowerPointExtractor.getText(null, null);

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

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

- 2.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

     * @return An ExtractData object containing the filename as content.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        final String content = params.getOrDefault(ExtractData.RESOURCE_NAME_KEY, StringUtil.EMPTY);
        try {

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

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

- 1.9K 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/ZipExtractorTest.java

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/zip/test.zip");
        final String content = zipExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertTrue(content.contains("テキスト"));
    }

    public void test_getText_maxSize() throws IOException {

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

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

- 3.7K 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)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/form/FormScheme.java

    /**
     * Extracts the token value from the content using the given pattern.
     * @param tokenPattern The regex pattern.
     * @param content The content to search.
     * @return The extracted token value.
     */
    protected String getTokenValue(final String tokenPattern, final String content) {
        final Matcher matcher = Pattern.compile(tokenPattern).matcher(content);
        if (matcher.find()) {

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

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

- 14.3K bytes

- Viewed (1)

github.com/codelibs/fess-crawler

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

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>タイトル</title>
</head>
<body>
<div>テスト</div>
</body>

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

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

- 162 bytes

- Viewed (0)

Search Options