utf8reader.java

精通tomcat书籍原代码,希望大家共同学习

            if ((b0 & 0xF0) == 0xE0) {
                int b1 = -1;
                if (++in < total) { 
                    b1 = fBuffer[in] & 0x00FF; 
                }
                else {
                    b1 = fInputStream.read();
                    if (b1 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fOffset = 1;
                            return out - offset;
                        }
                        expectedByte(2, 3);
                    }
                    count++;
                }
                if ((b1 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fOffset = 2;
                        return out - offset;
                    }
                    invalidByte(2, 3, b1);
                }
                int b2 = -1;
                if (++in < total) { 
                    b2 = fBuffer[in] & 0x00FF; 
                }
                else {
                    b2 = fInputStream.read();
                    if (b2 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fBuffer[1] = (byte)b1;
                            fOffset = 2;
                            return out - offset;
                        }
                        expectedByte(3, 3);
                    }
                    count++;
                }
                if ((b2 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fBuffer[2] = (byte)b2;
                        fOffset = 3;
                        return out - offset;
                    }
                    invalidByte(3, 3, b2);
                }
                int c = ((b0 << 12) & 0xF000) | ((b1 << 6) & 0x0FC0) |
                        (b2 & 0x003F);
                ch[out++] = (char)c;
                count -= 2;
                continue;
            }

            // UTF-8:   [1111 0uuu] [10uu zzzz] [10yy yyyy] [10xx xxxx]*
            // Unicode: [1101 10ww] [wwzz zzyy] (high surrogate)
            //          [1101 11yy] [yyxx xxxx] (low surrogate)
            //          * uuuuu = wwww + 1
            if ((b0 & 0xF8) == 0xF0) {
                int b1 = -1;
                if (++in < total) { 
                    b1 = fBuffer[in] & 0x00FF; 
                }
                else {
                    b1 = fInputStream.read();
                    if (b1 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fOffset = 1;
                            return out - offset;
                        }
                        expectedByte(2, 4);
                    }
                    count++;
                }
                if ((b1 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fOffset = 2;
                        return out - offset;
                    }
                    invalidByte(2, 4, b1);
                }
                int b2 = -1;
                if (++in < total) { 
                    b2 = fBuffer[in] & 0x00FF; 
                }
                else {
                    b2 = fInputStream.read();
                    if (b2 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fBuffer[1] = (byte)b1;
                            fOffset = 2;
                            return out - offset;
                        }
                        expectedByte(3, 4);
                    }
                    count++;
                }
                if ((b2 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fBuffer[2] = (byte)b2;
                        fOffset = 3;
                        return out - offset;
                    }
                    invalidByte(3, 4, b2);
                }
                int b3 = -1;
                if (++in < total) { 
                    b3 = fBuffer[in] & 0x00FF; 
                }
                else {
                    b3 = fInputStream.read();
                    if (b3 == -1) {
                        if (out > offset) {
                            fBuffer[0] = (byte)b0;
                            fBuffer[1] = (byte)b1;
                            fBuffer[2] = (byte)b2;
                            fOffset = 3;
                            return out - offset;
                        }
                        expectedByte(4, 4);
                    }
                    count++;
                }
                if ((b3 & 0xC0) != 0x80) {
                    if (out > offset) {
                        fBuffer[0] = (byte)b0;
                        fBuffer[1] = (byte)b1;
                        fBuffer[2] = (byte)b2;
                        fBuffer[3] = (byte)b3;
                        fOffset = 4;
                        return out - offset;
                    }
                    invalidByte(4, 4, b2);
                }

                // decode bytes into surrogate characters
                int uuuuu = ((b0 << 2) & 0x001C) | ((b1 >> 4) & 0x0003);
                if (uuuuu > 0x10) {
                    invalidSurrogate(uuuuu);
                }
                int wwww = uuuuu - 1;
                int zzzz = b1 & 0x000F;
                int yyyyyy = b2 & 0x003F;
                int xxxxxx = b3 & 0x003F;
                int hs = 0xD800 | ((wwww << 6) & 0x03C0) | (zzzz << 2) | (yyyyyy >> 4);
                int ls = 0xDC00 | ((yyyyyy << 6) & 0x03C0) | xxxxxx;

                // set characters
                ch[out++] = (char)hs;
                ch[out++] = (char)ls;
                count -= 2;
                continue;
            }

            // error
            if (out > offset) {
                fBuffer[0] = (byte)b0;
                fOffset = 1;
                return out - offset;
            }
            invalidByte(1, 1, b0);
        }

        // return number of characters converted
        if (DEBUG_READ) {
            if (log.isDebugEnabled())
                log.debug("read(char[],"+offset+','+length+"): count="+count);
        }
        return count;

    } // read(char[],int,int)

    /**
     * Skip characters.  This method will block until some characters are
     * available, an I/O error occurs, or the end of the stream is reached.
     *
     * @param  n  The number of characters to skip
     *
     * @return    The number of characters actually skipped
     *
     * @exception  IOException  If an I/O error occurs
     */
    public long skip(long n) throws IOException {

        long remaining = n;
        final char[] ch = new char[fBuffer.length];
        do {
            int length = ch.length < remaining ? ch.length : (int)remaining;
            int count = read(ch, 0, length);
            if (count > 0) {
                remaining -= count;
            }
            else {
                break;
            }
        } while (remaining > 0);

        long skipped = n - remaining;
        return skipped;

    } // skip(long):long

    /**
     * Tell whether this stream is ready to be read.
     *
     * @return True if the next read() is guaranteed not to block for input,
     * false otherwise.  Note that returning false does not guarantee that the
     * next read will block.
     *
     * @exception  IOException  If an I/O error occurs
     */
    public boolean ready() throws IOException {
	    return false;
    } // ready()

    /**
     * Tell whether this stream supports the mark() operation.
     */
    public boolean markSupported() {
	    return false;
    } // markSupported()

    /**
     * Mark the present position in the stream.  Subsequent calls to reset()
     * will attempt to reposition the stream to this point.  Not all
     * character-input streams support the mark() operation.
     *
     * @param  readAheadLimit  Limit on the number of characters that may be
     *                         read while still preserving the mark.  After
     *                         reading this many characters, attempting to
     *                         reset the stream may fail.
     *
     * @exception  IOException  If the stream does not support mark(),
     *                          or if some other I/O error occurs
     */
    public void mark(int readAheadLimit) throws IOException {
	throw new IOException(
                Localizer.getMessage("jsp.error.xml.operationNotSupported",
				     "mark()", "UTF-8"));
    }

    /**
     * Reset the stream.  If the stream has been marked, then attempt to
     * reposition it at the mark.  If the stream has not been marked, then
     * attempt to reset it in some way appropriate to the particular stream,
     * for example by repositioning it to its starting point.  Not all
     * character-input streams support the reset() operation, and some support
     * reset() without supporting mark().
     *
     * @exception  IOException  If the stream has not been marked,
     *                          or if the mark has been invalidated,
     *                          or if the stream does not support reset(),
     *                          or if some other I/O error occurs
     */
    public void reset() throws IOException {
        fOffset = 0;
        fSurrogate = -1;
    } // reset()

    /**
     * Close the stream.  Once a stream has been closed, further read(),
     * ready(), mark(), or reset() invocations will throw an IOException.
     * Closing a previously-closed stream, however, has no effect.
     *
     * @exception  IOException  If an I/O error occurs
     */
    public void close() throws IOException {
        fInputStream.close();
    } // close()

    //
    // Private methods
    //

    /** Throws an exception for expected byte. */
    private void expectedByte(int position, int count)
        throws UTFDataFormatException {

        throw new UTFDataFormatException(
                Localizer.getMessage("jsp.error.xml.expectedByte",
				     Integer.toString(position),
				     Integer.toString(count)));

    } // expectedByte(int,int,int)

    /** Throws an exception for invalid byte. */
    private void invalidByte(int position, int count, int c) 
        throws UTFDataFormatException {

        throw new UTFDataFormatException(
                Localizer.getMessage("jsp.error.xml.invalidByte",
				     Integer.toString(position),
				     Integer.toString(count)));
    } // invalidByte(int,int,int,int)

    /** Throws an exception for invalid surrogate bits. */
    private void invalidSurrogate(int uuuuu) throws UTFDataFormatException {
        
        throw new UTFDataFormatException(
                Localizer.getMessage("jsp.error.xml.invalidHighSurrogate",
				     Integer.toHexString(uuuuu)));
    } // invalidSurrogate(int)

} // class UTF8Reader