Commit 994674c0 authored by unknown's avatar unknown
Browse files

Bug#8321 - myisampack bug in compression algorithm 

This is the second of three changesets. It contains the pure bug fix.
It also contains the second after-review fixes.
The problem was that with gcc on x86, shifts are done modulo word size. 
'value' is 32 bits wide and shifting it by 32 bits is a no-op.
This was triggered by an evil distribution of character incidences. 
A distribution of 2917027827 characters made of 202 distinct values led to
34 occurrences of 32-bit Huffman codes.
This might have been the first time ever that write_bits() had to write
32-bit values. Since it can be expected that one day even 32 bits might
be insufficient, the third changeset suggests to enlarge some variables
to 64 bits.
parent f63c8f53

myisam/myisampack.c

+7 −2
Original line number Diff line number Diff line
@@ -31,6 +31,7 @@ 
#define __GNU_LIBRARY__			/* Skip warnings in getopt.h */

#endif

#include <my_getopt.h>

#include <assert.h>



#if INT_MAX > 32767

#define BITS_SAVED 32
@@ -1975,7 +1976,9 @@ static void write_bits (register ulong value, register uint bits) 
  {

    reg3 uint byte_buff;

    bits= (uint) -file_buffer.bits;

    byte_buff=file_buffer.byte | (uint) (value >> bits);

    DBUG_ASSERT(bits <= 8 * sizeof(value));

    byte_buff= (file_buffer.byte |

               ((bits != 8 * sizeof(value)) ? (uint) (value >> bits) : 0));

#if BITS_SAVED == 32

    *file_buffer.pos++= (byte) (byte_buff >> 24) ;

    *file_buffer.pos++= (byte) (byte_buff >> 16) ;
@@ -1983,7 +1986,9 @@ static void write_bits (register ulong value, register uint bits) 
    *file_buffer.pos++= (byte) (byte_buff >> 8) ;

    *file_buffer.pos++= (byte) byte_buff;



    value&=(1 << bits)-1;

    DBUG_ASSERT(bits <= 8 * sizeof(ulong));

    if (bits != 8 * sizeof(value))

      value&= (((ulong) 1) << bits) - 1;

#if BITS_SAVED == 16

    if (bits >= sizeof(uint))

    {