Example usage for org.apache.commons.lang3 CharEncoding isSupported

Introduction

In this page you can find the example usage for org.apache.commons.lang3 CharEncoding isSupported.

Prototype

public static boolean isSupported(final String name) 

Source Link

Document

<p>Returns whether the named charset is supported.</p> <p>This is similar to <a href="http://download.oracle.com/javase/1.4.2/docs/api/java/nio/charset/Charset.html#isSupported%28java.lang.String%29"> java.nio.charset.Charset.isSupported(String)</a> but handles more formats</p>

Usage

From source file:com.norconex.importer.handler.tagger.AbstractCharStreamTagger.java

@Override
protected final void tagApplicableDocument(String reference, InputStream document, ImporterMetadata metadata,
        boolean parsed) throws ImporterHandlerException {

    String contentType = metadata.getString("Content-Type", "");
    contentType = StringUtils.substringBefore(contentType, ";");

    String charset = metadata.getString("Content-Encoding", null);
    if (charset == null) {
        charset = metadata.getString("charset", null);
    }/*from w  w w .j  av  a2s . co  m*/
    if (charset == null) {
        for (String type : metadata.getStrings("Content-Type")) {
            if (type.contains("charset")) {
                charset = StringUtils.trimToNull(StringUtils.substringAfter(type, "charset="));
                break;
            }
        }
    }
    if (StringUtils.isBlank(charset) || !CharEncoding.isSupported(charset)) {
        charset = CharEncoding.UTF_8;
    }
    try {
        InputStreamReader is = new InputStreamReader(document, charset);
        tagTextDocument(reference, is, metadata, parsed);
    } catch (UnsupportedEncodingException e) {
        throw new ImporterHandlerException(e);
    }
}

---

From source file:com.norconex.importer.parser.impl.xfdl.XFDLParser.java

@Override
public List<ImporterDocument> parseDocument(ImporterDocument doc, Writer output)
        throws DocumentParserException {
    try {//from ww  w.j a v  a 2s. c  om
        //TODO have a generic utility method for this?
        BufferedInputStream is = new BufferedInputStream(doc.getContent());
        CharsetDetector detector = new CharsetDetector();
        detector.enableInputFilter(true);
        detector.setText(is);
        CharsetMatch match = detector.detect();
        String charset = CharEncoding.UTF_8;
        if (match != null && CharEncoding.isSupported(match.getName())) {
            charset = match.getName();
        }
        BufferedReader reader = new BufferedReader(new InputStreamReader(is, charset));
        parse(reader, output, doc.getMetadata());
    } catch (IOException | ParserConfigurationException | SAXException e) {
        throw new DocumentParserException("Could not parse " + doc.getReference(), e);
    }
    return null;
}

---

From source file:com.norconex.commons.lang.url.URLNormalizer.java

/**
 * Create a new <code>URLNormalizer</code> instance.
 * @param url the url to normalize// w w  w  .  java  2 s.  co m
 */
public URLNormalizer(String url) {
    super();
    // make sure URL is valid
    String fixedURL = url;
    try {
        if (StringUtils.contains(fixedURL, " ")) {
            LOG.warn("URL syntax is invalid as it contains space "
                    + "character(s). Replacing them with %20. URL: " + url);
            fixedURL = StringUtils.replace(fixedURL, " ", "%20");
        }
        new URI(fixedURL);
    } catch (URISyntaxException e) {
        throw new URLException("Invalid URL syntax: " + url, e);
    }
    if (!CharEncoding.isSupported(CharEncoding.UTF_8)) {
        throw new URLException("UTF-8 is not supported by your system.");
    }
    this.url = fixedURL.trim();
}

---