Java vs. Python

readutf.java

/**
 * Reads from the
 * stream <code>in</code> a representation
 * of a Unicode  character string encoded in
 * <a href="DataInput.html#modified-utf-8">modified UTF-8</a> format;
 * this string of characters is then returned as a <code>String</code>.
 * The details of the modified UTF-8 representation
 * are  exactly the same as for the <code>readUTF</code>
 * method of <code>DataInput</code>.
 *
 * @param      in   a data input stream.
 * @return     a Unicode string.
 * @exception  EOFException            if the input stream reaches the end
 *               before all the bytes.
 * @exception  IOException   the stream has been closed and the contained
 *             input stream does not support reading after close, or
 *             another I/O error occurs.
 * @exception  UTFDataFormatException  if the bytes do not represent a
 *               valid modified UTF-8 encoding of a Unicode string.
 * @see        java.io.DataInputStream#readUnsignedShort()
 */
public final static String readUTF(DataInput in) throws IOException {
    int utflen = in.readUnsignedShort();
    byte[] bytearr = null;
    char[] chararr = null;
    if (in instanceof DataInputStream) {
        DataInputStream dis = (DataInputStream)in;
        if (dis.bytearr.length < utflen){
            dis.bytearr = new byte[utflen*2];
            dis.chararr = new char[utflen*2];
        }
        chararr = dis.chararr;
        bytearr = dis.bytearr;
    } else {
        bytearr = new byte[utflen];
        chararr = new char[utflen];
    }
    int c, char2, char3;
    int count = 0;
    int chararr_count=0;
    in.readFully(bytearr, 0, utflen);
    while (count < utflen) {
        c = (int) bytearr[count] & 0xff;
        if (c > 127) break;
        count++;
        chararr[chararr_count++]=(char)c;
    }   
    while (count < utflen) {
        c = (int) bytearr[count] & 0xff;

        switch (c >> 4) {
            case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
                /* 0xxxxxxx*/
                count++;
                chararr[chararr_count++]=(char)c;
                break;
            case 12: case 13:
                /* 110x xxxx   10xx xxxx*/
                count += 2;
                if (count > utflen)
                    throw new UTFDataFormatException(
                        "malformed input: partial character at end");
                char2 = (int) bytearr[count-1];
                if ((char2 & 0xC0) != 0x80)
                    throw new UTFDataFormatException(
                        "malformed input around byte " + count);
                chararr[chararr_count++]=(char)(((c & 0x1F) << 6) |
                                                (char2 & 0x3F));
                break;
            case 14:
                /* 1110 xxxx  10xx xxxx  10xx xxxx */
                count += 3;
                if (count > utflen)
                    throw new UTFDataFormatException(
                        "malformed input: partial character at end");
                char2 = (int) bytearr[count-2];
                char3 = (int) bytearr[count-1];
                if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80))
                    throw new UTFDataFormatException(
                        "malformed input around byte " + (count-1));
                chararr[chararr_count++]=(char)(((c     & 0x0F) << 12) |
                                                ((char2 & 0x3F) << 6)  |
                                                ((char3 & 0x3F) << 0));
                break;
            default:
                /* 10xx xxxx,  1111 xxxx */
                throw new UTFDataFormatException(
                    "malformed input around byte " + count);
        }
    }
    // The number of chars produced may be less than utflen
    return new String(chararr, 0, chararr_count);
}

readutf.py

import struct

def read_utf(fd):
    "Python implementation of Java's DataInputStream.readUTF method."
    length = struct.unpack('>H', fd.read(2))[0]
    return fd.read(length).decode('utf8')