Difference between revisions of "YAZ0 (File Format)"

From Custom Mario Kart
Jump to navigation Jump to search
Line 74: Line 74:
 
u8 * dest_end      = // pointer to end of destination (last byte +1)
 
u8 * dest_end      = // pointer to end of destination (last byte +1)
  
u8  code            = 0; // code ...
+
u8  group_head      = 0; // group header byte ...
int code_len        = 0; // ... and code_len used to manage groups
+
int group_head_len  = 0; // ... and it's length to manage groups
  
while ( src < src_end && dest < dest_end )  
+
while ( src < src_end && dest < dest_end )
{  
+
{
     if (!code_len--)
+
     if (!group_head_len)
     {  
+
     {
         code = *src++;
+
//*** start a now data group and read the group header byte.
         code_len = 7;  
+
 
     }  
+
         group_head = *src++;
 +
         group_head_len = 8;
 +
     }
  
     if ( code & 0x80 )
+
    group_head_len--;
 +
     if ( group_head & 0x80 )
 
     {
 
     {
         // copy 1 byte direct
+
         //*** bit in group header byte is set -> copy 1 byte direct
 +
 
 
         *dest++ = *src++;
 
         *dest++ = *src++;
 
     }
 
     }
     else  
+
     else
     {  
+
     {
         // rle part
+
         //*** bit in group header byte is not set -> run length encoding
  
 +
// read the first 2 bytes of the chunk
 
         const u8 b1 = *src++;
 
         const u8 b1 = *src++;
 
         const u8 b2 = *src++;
 
         const u8 b2 = *src++;
 +
       
 +
// calculate the source position
 
         const u8 * copy_src = dest - (( b1 & 0x0f ) << 8 | b2 ) - 1;
 
         const u8 * copy_src = dest - (( b1 & 0x0f ) << 8 | b2 ) - 1;
  
         int n = b1 >> 4;  
+
// calculate the number of bytes to copy.
         if (!n)  
+
         int n = b1 >> 4;
             n = *src++ + 0x12;  
+
 
 +
         if (!n)
 +
             n = *src++ + 0x12; // N==0 -> read third byte
 
         else
 
         else
             n += 2;
+
             n += 2; // add 2 to length
 
         ASSERT( n >= 3 && n <= 0x111 );
 
         ASSERT( n >= 3 && n <= 0x111 );
  
 +
// a validity check
 
         if ( copy_src < szs->data || dest + n > dest_end )
 
         if ( copy_src < szs->data || dest + n > dest_end )
 
             return ERROR("Corrupted data!\n");
 
             return ERROR("Corrupted data!\n");
  
 +
// copy chunk data.
 
         // don't use memcpy() or memmove() here because
 
         // don't use memcpy() or memmove() here because
 
         // they don't work with self referencing chunks.
 
         // they don't work with self referencing chunks.
Line 113: Line 124:
 
             *dest++ = *copy_src++;
 
             *dest++ = *copy_src++;
 
     }
 
     }
     code <<= 1;
+
 
 +
     // shift group header byte
 +
    group_head <<= 1;
 
}
 
}
 +
 +
// some assertions to find errors in debugging mode
 
ASSERT( src <= src_end );
 
ASSERT( src <= src_end );
 
ASSERT( dest <= dest_end );
 
ASSERT( dest <= dest_end );

Revision as of 14:36, 11 November 2011

Yaz0 is a run length encoding (RLE compression) method. In Mario Kart Wii most of the SZS files are Yaz0 compressed U8 files.

Data structure

Header

The header of a Yaz0 file is always 16 bytes long. All numeric values stored as big endian values.

Offset Type Description
0x00 char[4] always "Yaz0"
0x04 u32 size of the uncompressed data
0x08 char[8] always zero (padding)
GNU C example
typedef struct yaz0_header_t
{
    char	magic[4];		// always "Yaz0"
    be32_t	uncompressed_size;	// total size of uncompressed data
    char	padding[8];		// always 0?
}
__attribute__ ((packed)) yaz0_header_t;

Data Groups

The complete compressed data is organized in data groups. Each data group consists of 1 group header byte and 8 chunks:

N Size Description
1 1 byte the group header byte
8 1-3 bytes 8 chunks

Each bit of the group header corespondents to one chunk:

  • The MSB (most significant bit, 0x80) corespondents to chunk 1
  • The LSB (lowest significant bit, 0x01) corespondents to chunk 8

A set bit (=1) in the group header means, that the chunk is exact 1 byte long. This byte must be copied to the output stream 1:1. A cleared bit (=0) defines, that the chunk is 2 or 3 bytes long interpreted as a back reference to already decompressed data that must be copied.

Size Data Bytes Size Calculation
2 bytes NR RR N = 1..f SIZE = N+2 (=3..0x11)
3 bytes 0R RR NN N = 00..ff SIZE = N+0x12 (=0x12..0x111)
  • RRR is a value between 0x000 and 0xfff. Go back RRR+1 bytes in the output stream to find the start of the data to be copied.
  • SIZE is calculated from N (see above) and declares the number of bytes to be copied.
  • It is important to know the a chunk may reference itself. For example if RRR=1 (go back 1+1=2) and SIZE=10 the previous 2 bytes are copied 10/2=5 times.

Decoding data groups and chunks is done until the end of the destination data is reached.

Examples

Decompression

GNU C example
const u8 * src      = // pointer to start of source
const u8 * src_end  = // pointer to end of source (last byte +1)
u8 * dest           = // pointer to start of destination
u8 * dest_end       = // pointer to end of destination (last byte +1)

u8  group_head      = 0; // group header byte ...
int group_head_len  = 0; // ... and it's length to manage groups

while ( src < src_end && dest < dest_end )
{
    if (!group_head_len)
    {
	//*** start a now data group and read the group header byte.

        group_head = *src++;
        group_head_len = 8;
    }

    group_head_len--;
    if ( group_head & 0x80 )
    {
        //*** bit in group header byte is set -> copy 1 byte direct

        *dest++ = *src++;
    }
    else
    {
        //*** bit in group header byte is not set -> run length encoding

	// read the first 2 bytes of the chunk
        const u8 b1 = *src++;
        const u8 b2 = *src++;
        
	// calculate the source position
        const u8 * copy_src = dest - (( b1 & 0x0f ) << 8 | b2 ) - 1;

	// calculate the number of bytes to copy.
        int n = b1 >> 4;

        if (!n)
            n = *src++ + 0x12; // N==0 -> read third byte
        else
            n += 2; // add 2 to length
        ASSERT( n >= 3 && n <= 0x111 );

	// a validity check
        if ( copy_src < szs->data || dest + n > dest_end )
            return ERROR("Corrupted data!\n");

	// copy chunk data.
        // don't use memcpy() or memmove() here because
        // they don't work with self referencing chunks.
        while ( n-- > 0 )
            *dest++ = *copy_src++;
    }

    // shift group header byte
    group_head <<= 1;
}

// some assertions to find errors in debugging mode
ASSERT( src <= src_end );
ASSERT( dest <= dest_end );

This code example is taken from Wiimms SZS Tools: SVN repository lib-szs.c line 162

Tools

The following tools can handle compressed U8 files (=SZS files):

Wiimms SZS Tools are able to (de-)compress any kind of Yaz0-files. SZS Modifier and CTools can this only with U8 files (remember: a compressed U8 is a SZS).