_content - Code Search

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/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/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/test/resources/ajax/js/jquery-2.1.1.min.js

this}return d=l.getElementById(c[2]),d&&d.parentNode&&(this.length=1,this[0]=d),this.context=l,this.selector=a,this}return a.nodeType?(this.context=this[0]=a,this.length=1,this):n.isFunction(a)?"undefined"!=typeof y.ready?y.ready(a):a(n):(void 0!==a.selector&&(this.selector=a.selector,this.context=a.context),n.makeArray(a,this))};A.prototype=n.fn,y=n(l);var B=/^(?:parents|prev(?:Until|All))/,C={children:!0,contents:!0,next:!0,prev:!0};n.extend({dir:function(a,b,c){var d=[],e=void 0!==c;while((a=a[...

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

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

- 82.3K 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/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

    /**
     * Parses the charset from the content string.
     *
     * @param content the content to parse
     * @return the parsed charset name, or null if not found
     */
    protected String parseCharset(final String content) {
        final Pattern pattern = Pattern.compile("; *charset *= *([a-zA-Z0-9\\-_]+)", Pattern.CASE_INSENSITIVE);
        final Matcher matcher = pattern.matcher(content);
        if (matcher.find()) {

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

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

- 28.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

     */
    public void setCookieStore(final CookieStore cookieStore) {
        this.cookieStore = cookieStore;
    }

    /**
     * Sets the HTTP client context for requests.
     *
     * @param httpClientContext The HTTP client context
     */
    public void setHttpClientContext(final HttpClientContext httpClientContext) {
        this.httpClientContext = httpClientContext;
    }

    /**

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

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

- 52.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        }

        return encoding;
    }

    /**
     * Extracts text content from the given content by removing tags and processing attributes.
     * @param content The content to extract from.
     * @return The extracted text.
     */
    protected String extractString(final String content) {
        String input = content.replaceAll("[\\r\\n]", " ");
        if (ignoreCommentTag) {

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

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

- 8.5K bytes

- Viewed (0)

Search Options