bsnes/snesreader/7z_C/7zDecode.c

258 lines
7.4 KiB
C
Raw Normal View History

Include all the code from the bsnes v068 tarball. byuu describes the changes since v067: This release officially introduces the accuracy and performance cores, alongside the previously-existing compatibility core. The accuracy core allows the most accurate SNES emulation ever seen, with every last processor running at the lowest possible clock synchronization level. The performance core allows slower computers the chance to finally use bsnes. It is capable of attaining 60fps in standard games even on an entry-level Intel Atom processor, commonly found in netbooks. The accuracy core is absolutely not meant for casual gaming at all. It is meant solely for getting as close to 100% perfection as possible, no matter the cost to speed. It should only be used for testing, development or debugging. The compatibility core is identical to bsnes v067 and earlier, but is now roughly 10% faster. This is the default and recommended core for casual gaming. The performance core contains an entirely new S-CPU core, with range-tested IRQs; and uses blargg's heavily-optimized S-DSP core directly. Although there are very minor accuracy tradeoffs to increase speed, I am confident that the performance core is still more accurate and compatible than any other SNES emulator. The S-CPU, S-SMP, S-DSP, SuperFX and SA-1 processors are all clock-based, just as in the accuracy and compatibility cores; and as always, there are zero game-specific hacks. Its compatibility is still well above 99%, running even the most challenging games flawlessly. If you have held off from using bsnes in the past due to its system requirements, please give the performance core a try. I think you will be impressed. I'm also not finished: I believe performance can be increased even further. I would also strongly suggest Windows Vista and Windows 7 users to take advantage of the new XAudio2 driver by OV2. Not only does it give you a performance boost, it also lowers latency and provides better sound by way of skipping an API emulation layer. Changelog: - Split core into three profiles: accuracy, compatibility and performance - Accuracy core now takes advantage of variable-bitlength integers (eg uint24_t) - Performance core uses a new S-CPU core, written from scratch for speed - Performance core uses blargg's snes_dsp library for S-DSP emulation - Binaries are now compiled using GCC 4.5 - Added a workaround in the SA-1 core for a bug in GCC 4.5+ - The clock-based S-PPU renderer has greatly improved OAM emulation; fixing Winter Gold and Megalomania rendering issues - Corrected pseudo-hires color math in the clock-based S-PPU renderer; fixing Super Buster Bros backgrounds - Fixed a clamping bug in the Cx4 16-bit triangle operation [Jonas Quinn]; fixing Mega Man X2 "gained weapon" star background effect - Updated video renderer to properly handle mixed-resolution screens with interlace enabled; fixing Air Strike Patrol level briefing screen - Added mightymo's 2010-08-19 cheat code pack - Windows port: added XAudio2 output support [OV2] - Source: major code restructuring; virtual base classes for processor - cores removed, build system heavily modified, etc.
2010-08-22 01:02:42 +00:00
/* 7zDecode.c -- Decoding from 7z folder
2008-11-23 : Igor Pavlov : Public domain */
#include <string.h>
#include "Bcj2.h"
#include "Bra.h"
#include "LzmaDec.h"
#include "7zDecode.h"
#define k_Copy 0
#define k_LZMA 0x30101
#define k_BCJ 0x03030103
#define k_BCJ2 0x0303011B
static SRes SzDecodeLzma(CSzCoderInfo *coder, UInt64 inSize, ILookInStream *inStream,
Byte *outBuffer, SizeT outSize, ISzAlloc *allocMain)
{
CLzmaDec state;
SRes res = SZ_OK;
LzmaDec_Construct(&state);
RINOK(LzmaDec_AllocateProbs(&state, coder->Props.data, (unsigned)coder->Props.size, allocMain));
state.dic = outBuffer;
state.dicBufSize = outSize;
LzmaDec_Init(&state);
for (;;)
{
Byte *inBuf = NULL;
size_t lookahead = (1 << 18);
if (lookahead > inSize)
lookahead = (size_t)inSize;
res = inStream->Look((void *)inStream, (void **)&inBuf, &lookahead);
if (res != SZ_OK)
break;
{
SizeT inProcessed = (SizeT)lookahead, dicPos = state.dicPos;
ELzmaStatus status;
res = LzmaDec_DecodeToDic(&state, outSize, inBuf, &inProcessed, LZMA_FINISH_END, &status);
lookahead -= inProcessed;
inSize -= inProcessed;
if (res != SZ_OK)
break;
if (state.dicPos == state.dicBufSize || (inProcessed == 0 && dicPos == state.dicPos))
{
if (state.dicBufSize != outSize || lookahead != 0 ||
(status != LZMA_STATUS_FINISHED_WITH_MARK &&
status != LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK))
res = SZ_ERROR_DATA;
break;
}
res = inStream->Skip((void *)inStream, inProcessed);
if (res != SZ_OK)
break;
}
}
LzmaDec_FreeProbs(&state, allocMain);
return res;
}
static SRes SzDecodeCopy(UInt64 inSize, ILookInStream *inStream, Byte *outBuffer)
{
while (inSize > 0)
{
void *inBuf;
size_t curSize = (1 << 18);
if (curSize > inSize)
curSize = (size_t)inSize;
RINOK(inStream->Look((void *)inStream, (void **)&inBuf, &curSize));
if (curSize == 0)
return SZ_ERROR_INPUT_EOF;
memcpy(outBuffer, inBuf, curSize);
outBuffer += curSize;
inSize -= curSize;
RINOK(inStream->Skip((void *)inStream, curSize));
}
return SZ_OK;
}
#define IS_UNSUPPORTED_METHOD(m) ((m) != k_Copy && (m) != k_LZMA)
#define IS_UNSUPPORTED_CODER(c) (IS_UNSUPPORTED_METHOD(c.MethodID) || c.NumInStreams != 1 || c.NumOutStreams != 1)
#define IS_NO_BCJ(c) (c.MethodID != k_BCJ || c.NumInStreams != 1 || c.NumOutStreams != 1)
#define IS_NO_BCJ2(c) (c.MethodID != k_BCJ2 || c.NumInStreams != 4 || c.NumOutStreams != 1)
static
SRes CheckSupportedFolder(const CSzFolder *f)
{
if (f->NumCoders < 1 || f->NumCoders > 4)
return SZ_ERROR_UNSUPPORTED;
if (IS_UNSUPPORTED_CODER(f->Coders[0]))
return SZ_ERROR_UNSUPPORTED;
if (f->NumCoders == 1)
{
if (f->NumPackStreams != 1 || f->PackStreams[0] != 0 || f->NumBindPairs != 0)
return SZ_ERROR_UNSUPPORTED;
return SZ_OK;
}
if (f->NumCoders == 2)
{
if (IS_NO_BCJ(f->Coders[1]) ||
f->NumPackStreams != 1 || f->PackStreams[0] != 0 ||
f->NumBindPairs != 1 ||
f->BindPairs[0].InIndex != 1 || f->BindPairs[0].OutIndex != 0)
return SZ_ERROR_UNSUPPORTED;
return SZ_OK;
}
if (f->NumCoders == 4)
{
if (IS_UNSUPPORTED_CODER(f->Coders[1]) ||
IS_UNSUPPORTED_CODER(f->Coders[2]) ||
IS_NO_BCJ2(f->Coders[3]))
return SZ_ERROR_UNSUPPORTED;
if (f->NumPackStreams != 4 ||
f->PackStreams[0] != 2 ||
f->PackStreams[1] != 6 ||
f->PackStreams[2] != 1 ||
f->PackStreams[3] != 0 ||
f->NumBindPairs != 3 ||
f->BindPairs[0].InIndex != 5 || f->BindPairs[0].OutIndex != 0 ||
f->BindPairs[1].InIndex != 4 || f->BindPairs[1].OutIndex != 1 ||
f->BindPairs[2].InIndex != 3 || f->BindPairs[2].OutIndex != 2)
return SZ_ERROR_UNSUPPORTED;
return SZ_OK;
}
return SZ_ERROR_UNSUPPORTED;
}
static
UInt64 GetSum(const UInt64 *values, UInt32 index)
{
UInt64 sum = 0;
UInt32 i;
for (i = 0; i < index; i++)
sum += values[i];
return sum;
}
static
SRes SzDecode2(const UInt64 *packSizes, const CSzFolder *folder,
ILookInStream *inStream, UInt64 startPos,
Byte *outBuffer, SizeT outSize, ISzAlloc *allocMain,
Byte *tempBuf[])
{
UInt32 ci;
SizeT tempSizes[3] = { 0, 0, 0};
SizeT tempSize3 = 0;
Byte *tempBuf3 = 0;
RINOK(CheckSupportedFolder(folder));
for (ci = 0; ci < folder->NumCoders; ci++)
{
CSzCoderInfo *coder = &folder->Coders[ci];
if (coder->MethodID == k_Copy || coder->MethodID == k_LZMA)
{
UInt32 si = 0;
UInt64 offset;
UInt64 inSize;
Byte *outBufCur = outBuffer;
SizeT outSizeCur = outSize;
if (folder->NumCoders == 4)
{
UInt32 indices[] = { 3, 2, 0 };
UInt64 unpackSize = folder->UnpackSizes[ci];
si = indices[ci];
if (ci < 2)
{
Byte *temp;
outSizeCur = (SizeT)unpackSize;
if (outSizeCur != unpackSize)
return SZ_ERROR_MEM;
temp = (Byte *)IAlloc_Alloc(allocMain, outSizeCur);
if (temp == 0 && outSizeCur != 0)
return SZ_ERROR_MEM;
outBufCur = tempBuf[1 - ci] = temp;
tempSizes[1 - ci] = outSizeCur;
}
else if (ci == 2)
{
if (unpackSize > outSize) /* check it */
return SZ_ERROR_PARAM;
tempBuf3 = outBufCur = outBuffer + (outSize - (size_t)unpackSize);
tempSize3 = outSizeCur = (SizeT)unpackSize;
}
else
return SZ_ERROR_UNSUPPORTED;
}
offset = GetSum(packSizes, si);
inSize = packSizes[si];
RINOK(LookInStream_SeekTo(inStream, startPos + offset));
if (coder->MethodID == k_Copy)
{
if (inSize != outSizeCur) /* check it */
return SZ_ERROR_DATA;
RINOK(SzDecodeCopy(inSize, inStream, outBufCur));
}
else
{
RINOK(SzDecodeLzma(coder, inSize, inStream, outBufCur, outSizeCur, allocMain));
}
}
else if (coder->MethodID == k_BCJ)
{
UInt32 state;
if (ci != 1)
return SZ_ERROR_UNSUPPORTED;
x86_Convert_Init(state);
x86_Convert(outBuffer, outSize, 0, &state, 0);
}
else if (coder->MethodID == k_BCJ2)
{
UInt64 offset = GetSum(packSizes, 1);
UInt64 s3Size = packSizes[1];
SRes res;
if (ci != 3)
return SZ_ERROR_UNSUPPORTED;
RINOK(LookInStream_SeekTo(inStream, startPos + offset));
tempSizes[2] = (SizeT)s3Size;
if (tempSizes[2] != s3Size)
return SZ_ERROR_MEM;
tempBuf[2] = (Byte *)IAlloc_Alloc(allocMain, tempSizes[2]);
if (tempBuf[2] == 0 && tempSizes[2] != 0)
return SZ_ERROR_MEM;
res = SzDecodeCopy(s3Size, inStream, tempBuf[2]);
RINOK(res)
res = Bcj2_Decode(
tempBuf3, tempSize3,
tempBuf[0], tempSizes[0],
tempBuf[1], tempSizes[1],
tempBuf[2], tempSizes[2],
outBuffer, outSize);
RINOK(res)
}
else
return SZ_ERROR_UNSUPPORTED;
}
return SZ_OK;
}
SRes SzDecode(const UInt64 *packSizes, const CSzFolder *folder,
ILookInStream *inStream, UInt64 startPos,
Byte *outBuffer, size_t outSize, ISzAlloc *allocMain)
{
Byte *tempBuf[3] = { 0, 0, 0};
int i;
SRes res = SzDecode2(packSizes, folder, inStream, startPos,
outBuffer, (SizeT)outSize, allocMain, tempBuf);
for (i = 0; i < 3; i++)
IAlloc_Free(allocMain, tempBuf[i]);
return res;
}