Difference between revisions of "VarInt And VarLong"

From wiki.vg
Jump to navigation Jump to search
m (fixed spelling)
(Simplified the pseudocode and made it more efficient)
Line 6: Line 6:
  
 
<syntaxhighlight lang="java">
 
<syntaxhighlight lang="java">
public static int readVarInt() {
+
public int readVarInt() {
     int numRead = 0;
+
     int decodedInt = 0;
     int result = 0;
+
     int bitCount = 0;
     byte read;
+
     byte currentByte;
 
     do {
 
     do {
         read = readByte();
+
         currentByte = readByte();
         int value = (read & 0b01111111);
+
         decodedInt |= (currentByte & 0b01111111) << bitCount;
        result |= (value << (7 * numRead));
 
  
        numRead++;
+
         if (bitCount == 28) break;
         if (numRead > 5) {
 
            throw new RuntimeException("VarInt is too big");
 
        }
 
    } while ((read & 0b10000000) != 0);
 
  
     return result;
+
        bitCount += 7;
 +
    } while ((currentByte & 0b10000000) != 0);
 +
 
 +
     return decodedInt;
 
}
 
}
 
</syntaxhighlight>
 
</syntaxhighlight>
 
<syntaxhighlight lang="java">
 
<syntaxhighlight lang="java">
public static long readVarLong() {
+
public long readVarLong() {
     int numRead = 0;
+
     int decodedLong = 0;
     long result = 0;
+
     int bitCount = 0;
     byte read;
+
     byte currentByte;
 
     do {
 
     do {
         read = readByte();
+
         currentByte = readByte();
         long value = (read & 0b01111111);
+
         decodedLong |= (currentByte & 0b01111111) << bitCount;
         result |= (value << (7 * numRead));
+
 
 +
         if (bitCount == 63) break;
  
         numRead++;
+
         bitCount += 7;
        if (numRead > 10) {
+
     } while ((currentByte & 0b10000000) != 0);
            throw new RuntimeException("VarLong is too big");
 
        }
 
     } while ((read & 0b10000000) != 0);
 
  
     return result;
+
     return decodedLong;
 
}
 
}
 
</syntaxhighlight>
 
</syntaxhighlight>
 
<syntaxhighlight lang="java">
 
<syntaxhighlight lang="java">
public static void writeVarInt(int value) {
+
public void writeVarInt(int value) {
 
     do {
 
     do {
         byte temp = (byte)(value & 0b01111111);
+
         byte currentByte = (byte) (value & 0b01111111);
         // Note: >>> means that the sign bit is shifted with the rest of the number rather than being left alone
+
         writeByte((byte) ((value >>>= 7) == 0 ? currentByte : currentByte | 0b10000000));
        value >>>= 7;
 
        if (value != 0) {
 
            temp |= 0b10000000;
 
        }
 
        writeByte(temp);
 
 
     } while (value != 0);
 
     } while (value != 0);
 
}
 
}
 
</syntaxhighlight>
 
</syntaxhighlight>
 
<syntaxhighlight lang="java">
 
<syntaxhighlight lang="java">
public static void writeVarLong(long value) {
+
public void writeVarLong(long value) {
 
     do {
 
     do {
         byte temp = (byte)(value & 0b01111111);
+
         byte currentByte = (byte) (value & 0b01111111);
         // Note: >>> means that the sign bit is shifted with the rest of the number rather than being left alone
+
         writeByte((byte) ((value >>>= 7) == 0 ? currentByte : currentByte | 0b10000000));
        value >>>= 7;
 
        if (value != 0) {
 
            temp |= 0b10000000;
 
        }
 
        writeByte(temp);
 
 
     } while (value != 0);
 
     } while (value != 0);
 
}
 
}

Revision as of 09:39, 24 June 2021

Variable-length format such that smaller numbers use fewer bytes. These are very similar to Protocol Buffer Varints: the 7 least significant bits are used to encode the value and the most significant bit indicates whether there's another byte after it for the next part of the number. The least significant group is written first, followed by each of the more significant groups; thus, VarInts are effectively little endian (however, groups are 7 bits, not 8).

VarInts are never longer than 5 bytes, and VarLongs are never longer than 10 bytes.

Pseudocode to read and write VarInts and VarLongs:

public int readVarInt() {
    int decodedInt = 0;
    int bitCount = 0;
    byte currentByte;
    do {
        currentByte = readByte();
        decodedInt |= (currentByte & 0b01111111) << bitCount;

        if (bitCount == 28) break;

        bitCount += 7;
    } while ((currentByte & 0b10000000) != 0);

    return decodedInt;
}
public long readVarLong() {
    int decodedLong = 0;
    int bitCount = 0;
    byte currentByte;
    do {
        currentByte = readByte();
        decodedLong |= (currentByte & 0b01111111) << bitCount;

        if (bitCount == 63) break;

        bitCount += 7;
    } while ((currentByte & 0b10000000) != 0);

    return decodedLong;
}
public void writeVarInt(int value) {
    do {
        byte currentByte = (byte) (value & 0b01111111);
        writeByte((byte) ((value >>>= 7) == 0 ? currentByte : currentByte | 0b10000000));
    } while (value != 0);
}
public void writeVarLong(long value) {
    do {
        byte currentByte = (byte) (value & 0b01111111);
        writeByte((byte) ((value >>>= 7) == 0 ? currentByte : currentByte | 0b10000000));
    } while (value != 0);
}

Warning.png Note Minecraft's VarInts are identical to LEB128 with the slight change of throwing a exception if it goes over a set amount of bytes.

Warning.png Note that Minecraft's VarInts are not encoded using Protocol Buffers; it's just similar. If you try to use Protocol Buffers Varints with Minecraft's VarInts, you'll get incorrect results in some cases. The major differences:

  • Minecraft's VarInts are all signed, but do not use the ZigZag encoding. Protocol buffers have 3 types of Varints: uint32 (normal encoding, unsigned), sint32 (ZigZag encoding, signed), and int32 (normal encoding, signed). Minecraft's are the int32 variety. Because Minecraft uses the normal encoding instead of ZigZag encoding, negative values always use the maximum number of bytes.
  • Minecraft's VarInts are never longer than 5 bytes and its VarLongs will never be longer than 10 bytes, while Protocol Buffer Varints will always use 10 bytes when encoding negative numbers, even if it's an int32.

Sample VarInts:

Value Hex bytes Decimal bytes
0 0x00 0
1 0x01 1
2 0x02 2
127 0x7f 127
128 0x80 0x01 128 1
255 0xff 0x01 255 1
2097151 0xff 0xff 0x7f 255 255 127
2147483647 0xff 0xff 0xff 0xff 0x07 255 255 255 255 7
-1 0xff 0xff 0xff 0xff 0x0f 255 255 255 255 15
-2147483648 0x80 0x80 0x80 0x80 0x08 128 128 128 128 8

Sample VarLongs:

Value Hex bytes Decimal bytes
0 0x00 0
1 0x01 1
2 0x02 2
127 0x7f 127
128 0x80 0x01 128 1
255 0xff 0x01 255 1
2147483647 0xff 0xff 0xff 0xff 0x07 255 255 255 255 7
9223372036854775807 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0x7f 255 255 255 255 255 255 255 255 127
-1 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0x01 255 255 255 255 255 255 255 255 255 1
-2147483648 0x80 0x80 0x80 0x80 0xf8 0xff 0xff 0xff 0xff 0x01 128 128 128 128 248 255 255 255 255 1
-9223372036854775808 0x80 0x80 0x80 0x80 0x80 0x80 0x80 0x80 0x80 0x01 128 128 128 128 128 128 128 128 128 1