Java CharsetUtil类代码示例

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
private static Charset determineCharset(String text) {
    // it is an important property of iso-8859-1 that it directly maps
    // unicode code points 0000 to 00ff to byte values 00 to ff.
    boolean ascii = true;
    final int len = text.length();
    for (int index = 0; index < len; index++) {
        char ch = text.charAt(index);
        if (ch > 0xff) {
            return CharsetUtil.UTF_8;
        }
        if (ch > 0x7f) {
            ascii = false;
        }
    }
    return ascii ? CharsetUtil.US_ASCII : CharsetUtil.ISO_8859_1;
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
protected Charset getCharset() {
    Entity e = getParent();
    ContentTypeField cField = (ContentTypeField) e.getHeader().getField(
            Field.CONTENT_TYPE);
    Charset charset = null;
    
    switch (this.mode) {
    case STRICT:
        charset = MIME.DEFAULT_CHARSET;
        break;
    case BROWSER_COMPATIBLE:
        if (cField.getCharset() != null) {
            charset = CharsetUtil.getCharset(cField.getCharset());
        } else {
            charset = CharsetUtil.getCharset(HTTP.DEFAULT_CONTENT_CHARSET);
        }
        break;
    }
    return charset;
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
@Override
protected Recipient defaultObject(String completionText) {
    Address[] parsedAddresses = Address.parse(completionText);
    if (!CharsetUtil.isASCII(completionText)) {
        setError(getContext().getString(R.string.recipient_error_non_ascii));
        return null;
    }
    if (parsedAddresses.length == 0 || parsedAddresses[0].getAddress() == null) {
        setError(getContext().getString(R.string.recipient_error_parse_failed));
        return null;
    }

    return new Recipient(parsedAddresses[0]);
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
/**
 * Decodes a string containing encoded words as defined by RFC 2047. Encoded
 * words have the form =?charset?enc?encoded-text?= where enc is either 'Q'
 * or 'q' for quoted-printable and 'B' or 'b' for base64.
 *
 * @param body the string to decode
 * @param monitor the DecodeMonitor to be used.
 * @return the decoded string.
 * @throws IllegalArgumentException only if the DecodeMonitor strategy throws it (Strict parsing)
 */
public static String decodeEncodedWords(String body, DecodeMonitor monitor) throws IllegalArgumentException {
	if(body != null && !body.isEmpty()){
		int tailIndex = 0;
		boolean lastMatchValid = false;

		StringBuilder sb = new StringBuilder();

		for (Matcher matcher = PATTERN_ENCODED_WORD.matcher(body); matcher.find();) {
			String separator = matcher.group(1);
			String mimeCharset = matcher.group(2);
			String encoding = matcher.group(3);
			String encodedText = matcher.group(4);

			mimeCharset = Common.getFallbackCharset(mimeCharset);

			String decoded = null;
			decoded = tryDecodeEncodedWord(mimeCharset, encoding, encodedText, monitor);
			if (decoded == null) {
				sb.append(matcher.group(0));
			} else {
				if (!lastMatchValid || !CharsetUtil.isWhitespace(separator)) {
					sb.append(separator);
				}
				sb.append(decoded);
			}

			tailIndex = matcher.end();
			lastMatchValid = decoded != null;
		}

		if (tailIndex == 0) {
			return body;
		} else {
			sb.append(body.substring(tailIndex));
			return sb.toString();
		}
	}
	return body;
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
/**
 * Write the Header to the given OutputStream. 
 * <p>
 * Compatibility mode:
 * <ul>
 *  <li>
 *   {@link MessageUtils#LENIENT}: use charset of the Content-Type header
 *  </li>
 *  <li>
 *   {@link MessageUtils#STRICT_ERROR}: use US-ASCII and throw {@link MimeException} 
 *    if a non ASCII character is encountered
 *   </li>
 *  <li>
 *   {@link MessageUtils#STRICT_ERROR}: ignore non ASCII characters if encountered
 *   </li>
 * </ul>
 * @param out the OutputStream to write to
 * @param mode compatibility mode:
 *   {@link MessageUtils#LENIENT}, {@link MessageUtils#STRICT_ERROR}, {@link MessageUtils#STRICT_IGNORE}  
 * 
 * @throws IOException if case of an I/O error
 * @throws MimeException if case of a MIME protocol violation
 */
public void writeTo(final OutputStream out, int mode) throws IOException, MimeException {
    Charset charset = null;
    if (mode == MessageUtils.LENIENT) {
        final ContentTypeField contentTypeField = ((ContentTypeField) getField(Field.CONTENT_TYPE));
        if (contentTypeField == null) {
            charset = MessageUtils.DEFAULT_CHARSET;
        } else {
            final String contentTypeFieldCharset = contentTypeField.getCharset();
            if (contentTypeField != null && contentTypeFieldCharset != null) {
                charset = CharsetUtil.getCharset(contentTypeFieldCharset);
            } else {
                charset = MessageUtils.ISO_8859_1;
            }
        }
    } else {
        charset = MessageUtils.DEFAULT_CHARSET;
    }
    BufferedWriter writer = new BufferedWriter(
            new OutputStreamWriter(out, charset), 8192);
    for (Iterator it = fields.iterator(); it.hasNext();) {
        Field field = (Field) it.next();
        String fs = field.toString();
        if (mode == MessageUtils.STRICT_ERROR && !MessageUtils.isASCII(fs)) {
            throw new MimeException("Header '" + fs + "' violates RFC 822");
        }
        writer.write(fs);
        writer.write(MessageUtils.CRLF);
    }
    writer.write(MessageUtils.CRLF);
    writer.flush();
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
/**
 * @see org.apache.james.mime4j.message.TextBody#getReader()
 */
public Reader getReader() throws UnsupportedEncodingException, IOException {
    String javaCharset = null;
    if (mimeCharset != null) {
        javaCharset = CharsetUtil.toJavaCharset(mimeCharset);
    }
    
    if (javaCharset == null) {
        javaCharset = "ISO-8859-1";
    }

    return new InputStreamReader(tempFile.getInputStream(), javaCharset);
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
/**
 * Decodes a string containing encoded words as defined by RFC 2047.
 * Encoded words in have the form
 * =?charset?enc?Encoded word?= where enc is either 'Q' or 'q' for
 * quoted-printable and 'B' or 'b' for Base64.
 *
 * ANDROID:  COPIED FROM A NEWER VERSION OF MIME4J
 *
 * @param body the string to decode.
 * @param message the message which has the string.
 * @return the decoded string.
 */
public static String decodeEncodedWords(String body, Message message) {

    // ANDROID:  Most strings will not include "=?" so a quick test can prevent unneeded
    // object creation.  This could also be handled via lazy creation of the StringBuilder.
    if (!body.contains("=?")) {
        return body;
    }

    int previousEnd = 0;
    boolean previousWasEncoded = false;

    StringBuilder sb = new StringBuilder();

    while (true) {
        int begin = body.indexOf("=?", previousEnd);
        if (begin == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }

        // ANDROID:  The mime4j original version has an error here.  It gets confused if
        // the encoded string begins with an '=' (just after "?Q?").  This patch seeks forward
        // to find the two '?' in the "header", before looking for the final "?=".
        int qm1 = body.indexOf('?', begin + 2);
        if (qm1 == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }

        int qm2 = body.indexOf('?', qm1 + 1);
        if (qm2 == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }

        int end = body.indexOf("?=", qm2 + 1);
        if (end == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }
        end += 2;

        String sep = body.substring(previousEnd, begin);

        String decoded = decodeEncodedWord(body, begin, end, message);
        if (decoded == null) {
            sb.append(sep);
            sb.append(body.substring(begin, end));
        } else {
            if (!previousWasEncoded || !CharsetUtil.isWhitespace(sep)) {
                sb.append(sep);
            }
            sb.append(decoded);
        }

        previousEnd = end;
        previousWasEncoded = decoded != null;
    }
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
private static ContentDispositionHeaderValue decodeContentDisposition(
		String headerValue) throws MimeException {
	ContentDispositionHeaderValue contentDispositionHeaderValue = new ContentDispositionHeaderValue();
	contentDispositionHeaderValue.setValue(headerValue);
	try {
		int i = headerValue.indexOf('\'');
		if (i <= 0) {
			if (decodeParametersStrict) {
				throw new MimeException(
						"Missing charset in encoded value: " + headerValue);
			}
			return contentDispositionHeaderValue;
		}
		
		String charset = headerValue.substring(0, i);
		charset = Common.getFallbackCharset(charset);
		if (CharsetUtil.lookup(charset) == null) {
			return contentDispositionHeaderValue;
		}	
		
		int li = headerValue.indexOf('\'', i + 1);
		if (li < 0) {
			if (decodeParametersStrict) {
				throw new MimeException(
						"Missing language in encoded value: " + headerValue);
			}
			return contentDispositionHeaderValue;
		}
		headerValue = headerValue.substring(li + 1);
		contentDispositionHeaderValue.setCharset(charset);
		contentDispositionHeaderValue.setValue(decodeBytes(headerValue, charset));
	} catch (NumberFormatException nex) {
		if (decodeParametersStrict) {
			throw new MimeException(nex);
		}
	} catch (StringIndexOutOfBoundsException ex) {
		if (decodeParametersStrict) {
			throw new MimeException(ex);
		}
	}
	return contentDispositionHeaderValue;
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
/**
 * Decodes a string containing encoded words as defined by RFC 2047.
 * Encoded words in have the form
 * =?charset?enc?Encoded word?= where enc is either 'Q' or 'q' for
 * quoted-printable and 'B' or 'b' for Base64.
 *
 * ANDROID:  COPIED FROM A NEWER VERSION OF MIME4J
 *
 * @param body the string to decode.
 * @param message the message which has the string.
 * @return the decoded string.
 */
public static String decodeEncodedWords(String body, Message message) {

    // ANDROID:  Most strings will not include "=?" so a quick test can prevent unneeded
    // object creation.  This could also be handled via lazy creation of the StringBuilder.
    if (body.indexOf("=?") == -1) {
        return body;
    }

    int previousEnd = 0;
    boolean previousWasEncoded = false;

    StringBuilder sb = new StringBuilder();

    while (true) {
        int begin = body.indexOf("=?", previousEnd);
        if (begin == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }

        // ANDROID:  The mime4j original version has an error here.  It gets confused if
        // the encoded string begins with an '=' (just after "?Q?").  This patch seeks forward
        // to find the two '?' in the "header", before looking for the final "?=".
        int qm1 = body.indexOf('?', begin + 2);
        if (qm1 == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }

        int qm2 = body.indexOf('?', qm1 + 1);
        if (qm2 == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }

        int end = body.indexOf("?=", qm2 + 1);
        if (end == -1) {
            sb.append(body.substring(previousEnd));
            return sb.toString();
        }
        end += 2;

        String sep = body.substring(previousEnd, begin);

        String decoded = decodeEncodedWord(body, begin, end, message);
        if (decoded == null) {
            sb.append(sep);
            sb.append(body.substring(begin, end));
        } else {
            if (!previousWasEncoded || !CharsetUtil.isWhitespace(sep)) {
                sb.append(sep);
            }
            sb.append(decoded);
        }

        previousEnd = end;
        previousWasEncoded = decoded != null;
    }
}
 

import org.apache.james.mime4j.util.CharsetUtil; //导入依赖的package包/类
/**
 * Write the Multipart to the given OutputStream. 
 * 
 * @param out the OutputStream to write to
 * @param mode compatibility mode
 * 
 * @throws IOException if case of an I/O error
 * @throws MimeException if case of a MIME protocol violation
 */
public void writeTo(final OutputStream out, int mode) throws IOException, MimeException {
    Entity e = getParent();
    
    ContentTypeField cField = (ContentTypeField) e.getHeader().getField(
            Field.CONTENT_TYPE);
    if (cField == null || cField.getBoundary() == null) {
        throw new MimeException("Multipart boundary not specified");
    }
    String boundary = cField.getBoundary();

    Charset charset = null;
    if (mode == MessageUtils.LENIENT) {
        if (cField != null && cField.getCharset() != null) {
            charset = CharsetUtil.getCharset(cField.getCharset());
        } else {
            charset = MessageUtils.ISO_8859_1;
        }
    } else {
        charset = MessageUtils.DEFAULT_CHARSET;
    }
    
    BufferedWriter writer = new BufferedWriter(
            new OutputStreamWriter(out, charset), 8192);
    
    List bodyParts = getBodyParts();

    writer.write(getPreamble());
    writer.write(MessageUtils.CRLF);

    for (int i = 0; i < bodyParts.size(); i++) {
        writer.write("--");
        writer.write(boundary);
        writer.write(MessageUtils.CRLF);
        writer.flush();
        final BodyPart bodyPart = (BodyPart) bodyParts.get(i);
        bodyPart.writeTo(out, mode);
        writer.write(MessageUtils.CRLF);
    }

    writer.write("--");
    writer.write(boundary);
    writer.write("--");
    writer.write(MessageUtils.CRLF);
    final String epilogue = getEpilogue();
    writer.write(epilogue);
    writer.flush();
}