Android XML InputStream Parse obtainEncodingStringFromInputStream(InputStream bis)

Description

Helper method to obtain the content encoding from an input stream.

Parameter

Parameter	Description
bis	file to parse

Exception

Parameter	Description

Return

the encoding if we are able to extract and parse it, else the default value expected by the expat parser, i.e. "UTF-8"

Declaration

public static String obtainEncodingStringFromInputStream(InputStream bis)
        throws IOException 

Method Source Code

//package com.java2s;
import java.io.DataInputStream;
import java.io.IOException;
import java.io.InputStream;

import java.util.regex.Pattern;

public class Main {
    private static final int ENOUGH = 200;
    protected static final String EXTRACT_ENCODING_REGEX = ".*encoding=\"";
    protected static final String XML_FIRST_LINE_REGEX = "<\\?xml version=\"1\\.0\" encoding=\"(.*)\"?>";

    /**/*from  ww  w . j a v  a 2 s.c  om*/
     * Helper method to obtain the content encoding from an input stream.
     * 
     * @param bis file to parse
     * @return the encoding if we are able to extract and parse it, else the
     *         default value expected by the expat parser, i.e. "UTF-8"
     * @throws {@link IOException} if there is a problem reading from the file.
     * @throws {@link IllegalArgumentException} if the InputStream does not
     *         support mark and reset.
     */
    public static String obtainEncodingStringFromInputStream(InputStream bis)
            throws IOException {
        String encoding = "UTF-8";
        if (!bis.markSupported()) {
            throw new IllegalArgumentException(
                    "Error in the program, InputStream needs to support markSupported()");
        }

        // read the first line after setting the mark, then reset
        // before calling the parser.
        bis.mark(ENOUGH);
        DataInputStream dis = new DataInputStream(bis);

        String line = dis.readLine();
        line = line.replace("'", "\"");
        if (line.matches(XML_FIRST_LINE_REGEX)) {
            encoding = extractEncoding(line);
        }
        bis.reset();
        return encoding;
    }

    /**
     * Helper method to extract the XML file encoding
     * 
     * @param line the first line of an XML file
     * @return The value of the encoding in lower-case.
     */
    protected static String extractEncoding(String line) {
        Pattern p = Pattern.compile(EXTRACT_ENCODING_REGEX);
        String matches[] = p.split(line);
        // We want the value after encoding="
        String value = matches[1];
        // We don't need anything after the first " after the value
        String cleanup[] = value.split("\"");
        String encoding = cleanup[0];
        return encoding.toLowerCase();
    }
}

Related

1. InputStreamToDocument(InputStream istr)
2. LoadXml(InputStream stream)
3. getDocument(InputStream is)
4. getPullParser(InputStream in, String encoding)
5. newPullParser(InputStream input)
6. parse(InputStream in, ContentHandler handler)
7. parse(InputStream is)
8. parse(InputStream is)
9. parse(InputStream is, Class cls, List fields, List elements, String itemelement)