commit 0f9dddcc529dd4421f6a5dd08359e16cc38a4e0d Author: King_DuckZ Date: Tue May 5 20:22:29 2020 +0200 v0.20 diff --git a/Makefile.win b/Makefile.win new file mode 100644 index 0000000..7f97f6b --- /dev/null +++ b/Makefile.win @@ -0,0 +1,86 @@ +# Project: unalz +# Makefile created by Dev-C++ 4.9.9.0 + +CPP = g++.exe +CC = gcc.exe +WINDRES = windres.exe +RES = +OBJ = main.o UnAlz.o UnAlzBz2decompress.o UnAlzBzip2.o UnAlzbzlib.o zlib/adler32.o zlib/crc32.o zlib/infblock.o zlib/infcodes.o zlib/inffast.o zlib/inflate.o zlib/inftrees.o zlib/infutil.o zlib/uncompr.o zlib/zutil.o bzip2/blocksort.o bzip2/compress.o bzip2/crctable.o bzip2/huffman.o bzip2/randtable.o $(RES) +LINKOBJ = main.o UnAlz.o UnAlzBz2decompress.o UnAlzBzip2.o UnAlzbzlib.o zlib/adler32.o zlib/crc32.o zlib/infblock.o zlib/infcodes.o zlib/inffast.o zlib/inflate.o zlib/inftrees.o zlib/infutil.o zlib/uncompr.o zlib/zutil.o bzip2/blocksort.o bzip2/compress.o bzip2/crctable.o bzip2/huffman.o bzip2/randtable.o $(RES) +LIBS = -L"C:/Dev-Cpp/lib" -lkernel32 -luser32 -lgdi32 -lwinspool -lcomdlg32 -ladvapi32 -lshell32 -lole32 -loleaut32 -luuid -lodbc32 -lodbccp32 -lkernel32 -luser32 -lgdi32 -lwinspool -lcomdlg32 -ladvapi32 -lshell32 -lole32 -loleaut32 -luuid -lodbc32 -lodbccp32 +INCS = -I"C:/Dev-Cpp/include" +CXXINCS = -I"C:/Dev-Cpp/include/c++/3.3.1" -I"C:/Dev-Cpp/include/c++/3.3.1/mingw32" -I"C:/Dev-Cpp/include/c++/3.3.1/backward" -I"C:/Dev-Cpp/lib/gcc-lib/mingw32/3.3.1/include" -I"C:/Dev-Cpp/include" +BIN = bin/unalz.exe +CXXFLAGS = $(CXXINCS) -D__GNUWIN32__ -W -DWIN32 -DNDEBUG -D_CONSOLE -D_MBCS +CFLAGS = $(INCS) -D__GNUWIN32__ -W -DWIN32 -DNDEBUG -D_CONSOLE -D_MBCS + +.PHONY: all all-before all-after clean clean-custom + +all: all-before bin/unalz.exe all-after + + +clean: clean-custom + rm -f $(OBJ) $(BIN) + +$(BIN): $(OBJ) + $(CPP) $(LINKOBJ) -o "bin\unalz.exe" $(LIBS) + +main.o: main.cpp + $(CPP) -c main.cpp -o main.o $(CXXFLAGS) + +UnAlz.o: UnAlz.cpp + $(CPP) -c UnAlz.cpp -o UnAlz.o $(CXXFLAGS) + +UnAlzBz2decompress.o: UnAlzBz2decompress.c + $(CC) -c UnAlzBz2decompress.c -o UnAlzBz2decompress.o $(CFLAGS) + +UnAlzBzip2.o: UnAlzBzip2.cpp + $(CPP) -c UnAlzBzip2.cpp -o UnAlzBzip2.o $(CXXFLAGS) + +UnAlzbzlib.o: UnAlzbzlib.c + $(CC) -c UnAlzbzlib.c -o UnAlzbzlib.o $(CFLAGS) + +zlib/adler32.o: zlib/adler32.c + $(CC) -c zlib/adler32.c -o zlib/adler32.o $(CFLAGS) + +zlib/crc32.o: zlib/crc32.c + $(CC) -c zlib/crc32.c -o zlib/crc32.o $(CFLAGS) + +zlib/infblock.o: zlib/infblock.c + $(CC) -c zlib/infblock.c -o zlib/infblock.o $(CFLAGS) + +zlib/infcodes.o: zlib/infcodes.c + $(CC) -c zlib/infcodes.c -o zlib/infcodes.o $(CFLAGS) + +zlib/inffast.o: zlib/inffast.c + $(CC) -c zlib/inffast.c -o zlib/inffast.o $(CFLAGS) + +zlib/inflate.o: zlib/inflate.c + $(CC) -c zlib/inflate.c -o zlib/inflate.o $(CFLAGS) + +zlib/inftrees.o: zlib/inftrees.c + $(CC) -c zlib/inftrees.c -o zlib/inftrees.o $(CFLAGS) + +zlib/infutil.o: zlib/infutil.c + $(CC) -c zlib/infutil.c -o zlib/infutil.o $(CFLAGS) + +zlib/uncompr.o: zlib/uncompr.c + $(CC) -c zlib/uncompr.c -o zlib/uncompr.o $(CFLAGS) + +zlib/zutil.o: zlib/zutil.c + $(CC) -c zlib/zutil.c -o zlib/zutil.o $(CFLAGS) + +bzip2/blocksort.o: bzip2/blocksort.c + $(CC) -c bzip2/blocksort.c -o bzip2/blocksort.o $(CFLAGS) + +bzip2/compress.o: bzip2/compress.c + $(CC) -c bzip2/compress.c -o bzip2/compress.o $(CFLAGS) + +bzip2/crctable.o: bzip2/crctable.c + $(CC) -c bzip2/crctable.c -o bzip2/crctable.o $(CFLAGS) + +bzip2/huffman.o: bzip2/huffman.c + $(CC) -c bzip2/huffman.c -o bzip2/huffman.o $(CFLAGS) + +bzip2/randtable.o: bzip2/randtable.c + $(CC) -c bzip2/randtable.c -o bzip2/randtable.o $(CFLAGS) diff --git a/UnAlz.cpp b/UnAlz.cpp new file mode 100644 index 0000000..35c150c --- /dev/null +++ b/UnAlz.cpp @@ -0,0 +1,1276 @@ +//#include "stdafx.h" +#include "zlib/zlib.h" +#include "bzip2/bzlib.h" +#include "UnAlz.h" +#ifdef _WIN32 +#include // mkdir +#else +#include +#endif + +#ifndef MAX_PATH +#define MAX_PATH 260 +#endif + +#ifdef _WIN32 + #define PATHSEP "\\" + #define PATHSEPC '\\' +#else + #define PATHSEP "/" + #define PATHSEPC '/' +#endif + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// ctor +/// @date 2004-03-06 오후 11:19:49 +//////////////////////////////////////////////////////////////////////////////////////////////////// +CUnAlz::CUnAlz() +{ + memset(m_files, 0, sizeof(m_files)); + m_nErr = ERR_NOERR; + m_posCur = (FileList::iterator)NULL; + m_pFuncCallBack = NULL; + m_pCallbackParam = NULL; + m_bHalt = FALSE; + m_nFileCount = 0; + m_nCurFile = -1; + m_nVirtualFilePos = 0; + m_nCurFilePos = 0; + m_bIsEOF = FALSE; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// dtor +/// @date 2004-03-06 오후 11:19:52 +//////////////////////////////////////////////////////////////////////////////////////////////////// +CUnAlz::~CUnAlz() +{ + Close(); +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// progress callback func setting +/// @date 2004-03-01 오전 6:02:05 +//////////////////////////////////////////////////////////////////////////////////////////////////// +void CUnAlz::SetCallback(_UnAlzCallback* pFunc, void* param) +{ + m_pFuncCallBack = pFunc; + m_pCallbackParam = param; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 파일 열기 +/// @param szPathName +/// @return +/// @date 2004-03-06 오후 11:03:59 +//////////////////////////////////////////////////////////////////////////////////////////////////// +#ifdef _WIN32 +/* +BOOL CUnAlz::Open(LPCWSTR szPathName) +{ + USES_CONVERSION; + return Open(W2A(szPathName)); +} +*/ +#endif // _WIN32 + +BOOL CUnAlz::Open(const char* szPathName) +{ + if(FOpen(szPathName)==FALSE) + { + m_nErr = ERR_CANT_OPEN_FILE; + return FALSE; + } + + // file 분석시작.. + for(;;) + { + SIGNATURE sig; + BOOL ret; + + if(FEof()) break; + //int pos = ftell(m_fp); + sig = ReadSignature(); + if(sig==SIG_EOF) + { + break; + } + if(sig==SIG_ERR) + { + return FALSE; // 깨진 파일.. + } + + if(sig==SIG_ALZ_FILE_HEADER) ret = ReadAlzFileHeader(); + else if(sig==SIG_LOCAL_FILE_HEADER) ret = ReadLocalFileheader(); + else if(sig==SIG_CENTRAL_DIRECTORY_STRUCTURE) ret = ReadCentralDirectoryStructure(); + else if(sig==SIG_ENDOF_CENTRAL_DIRECTORY_RECORD) ret = ReadEndofCentralDirectoryRecord(); + else + { + // 미구현된 signature + ASSERT(0); + return FALSE; + } + + if(ret==FALSE) + { + return FALSE; + } + + if(FEof()) break; + } + + return TRUE; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 파일 닫기.. +/// @return +/// @date 2004-03-06 오후 11:04:21 +//////////////////////////////////////////////////////////////////////////////////////////////////// +void CUnAlz::Close() +{ + FClose(); + + // 목록 날리기.. + FileList::iterator i; + + for(i=m_fileList.begin(); iClear(); + } + + m_posCur = (FileList::iterator)NULL; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// FILE 내의 SIGNATURE 읽기 +/// @return +/// @date 2004-03-06 오후 11:04:47 +//////////////////////////////////////////////////////////////////////////////////////////////////// +CUnAlz::SIGNATURE CUnAlz::ReadSignature() +{ + DWORD dwSig; + if(FRead(&dwSig, sizeof(dwSig))==FALSE) + { +//int pos = ftell(m_fp); + if(FEof()) + return SIG_EOF; + m_nErr = ERR_CANT_READ_SIG; + return SIG_ERR; + } + + return (SIGNATURE)dwSig; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// ALZ HEADER SIGNATURE 읽기 +/// @return +/// @date 2004-03-06 오후 11:05:11 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ReadAlzFileHeader() +{ + SAlzHeader header; + if(FRead(&header, sizeof(header))==FALSE) + { + ASSERT(0); + m_nErr = ERR_CANT_READ_FILE; + return FALSE; + } + + return TRUE; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 각각의 파일 헤더 읽기 +/// @return +/// @date 2004-03-06 오후 11:05:18 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ReadLocalFileheader() +{ + SLocalFileHeader zipHeader; + int ret; + + ret = FRead(&(zipHeader.head), sizeof(zipHeader.head)); + if(ret==FALSE) + { + m_nErr = ERR_AT_READ_HEADER; + return FALSE; + } + + // ALZ 확장.. + int byteLen = zipHeader.head.fileSizeByte/0x10; + + if(byteLen) + { + FRead(&(zipHeader.compressionMethod), sizeof(zipHeader.compressionMethod)); + FRead(&(zipHeader.unknown3), sizeof(zipHeader.unknown3)); + FRead(&(zipHeader.maybeCRC), sizeof(zipHeader.maybeCRC)); + + FRead(&(zipHeader.compressedSize), byteLen); + FRead(&(zipHeader.uncompressedSize), byteLen); // 압축 사이즈가 없다. + } + + + // FILE NAME + zipHeader.fileName = (char*)malloc(zipHeader.head.fileNameLength+1); + if(zipHeader.fileName==NULL) + { + m_nErr = ERR_INVALID_FILENAME_LENGTH; + return FALSE; + } + FRead(zipHeader.fileName, zipHeader.head.fileNameLength); + zipHeader.fileName[zipHeader.head.fileNameLength] = (CHAR)NULL; + + /* + // EXTRA FIELD LENGTH + if(zipHeader.head.extraFieldLength) + { + zipHeader.extraField = (BYTE*)malloc(zipHeader.head.extraFieldLength); + if(zipHeader.extraField==NULL) + { + m_nErr = ERR_INVALID_EXTRAFIELD_LENGTH; + return FALSE; + } + FRead(zipHeader.extraField, 1, zipHeader.head.extraFieldLength); + } + */ + + // SKIP FILE DATA + zipHeader.dwFileDataPos = FTell(); // data 의 위치 저장하기.. + FSeek(FTell()+zipHeader.compressedSize); + + // DATA DESCRIPTOR + /* + if(zipHeader.head.generalPurposeBitFlag.bit1) + { + FRead(zipHeader.extraField, 1, sizeof(zipHeader.extraField),); + } + */ + +#ifdef _DEBUG + printf("NAME:%s COMPRESSED SIZE:%d UNCOMPRESSED SIZE:%d COMP METHOD:%d\n", + zipHeader.fileName, + zipHeader.compressedSize, + zipHeader.uncompressedSize, + zipHeader.compressionMethod + ); +#endif + + // 파일을 목록에 추가한다.. + m_fileList.push_back(zipHeader); + + return TRUE; +} + + +BOOL CUnAlz::ReadCentralDirectoryStructure() +{ + SCentralDirectoryStructure header; + + if(FRead(&header, sizeof(header.head))==FALSE) + { + m_nErr = ERR_CANT_READ_CENTRAL_DIRECTORY_STRUCTURE_HEAD; + return FALSE; + } + + /* + // read file name + if(header.head.fileNameLength) + { + header.fileName = (char*)malloc(header.head.fileNameLength+1); + if(header.fileName==NULL) + { + m_nErr = ERR_INVALID_FILENAME_SIZE; + return FALSE; + } + FRead(header.fileName, 1, header.head.fileNameLength, m_fp); + header.fileName[header.head.fileNameLength] = NULL; + } + + // extra field; + if(header.head.extraFieldLength) + { + header.extraField = (BYTE*)malloc(header.head.extraFieldLength); + if(header.extraField==NULL) + { + m_nErr = ERR_INVALID_EXTRAFIELD_SIZE; + return FALSE; + } + FRead(header.extraField, 1, header.head.extraFieldLength, m_fp); + } + + // file comment; + if(header.head.fileCommentLength) + { + header.fileComment = (char*)malloc(header.head.fileCommentLength+1); + if(header.fileComment==NULL) + { + m_nErr = ERR_INVALID_FILECOMMENT_SIZE; + return FALSE; + } + FRead(header.fileComment, 1, header.head.fileCommentLength, m_fp); + header.fileComment[header.head.fileCommentLength] = NULL; + } + + */ + + return TRUE; +} + + +BOOL CUnAlz::ReadEndofCentralDirectoryRecord() +{ + /* + SEndOfCentralDirectoryRecord header; + + if(FRead(&header, sizeof(header.head), 1, m_fp)!=1) + { + m_nErr = ERR_CANT_READ_HEADER; + return FALSE; + } + + if(header.head.zipFileCommentLength) + { + header.fileComment = (char*)malloc(header.head.zipFileCommentLength+1); + if(header.fileComment==NULL) + { + m_nErr = ERR_INVALID_FILECOMMENT_SIZE; + return FALSE; + } + FRead(header.fileComment, 1, header.head.zipFileCommentLength, m_fp); + header.fileComment[header.head.zipFileCommentLength] = NULL; + } + */ + + return TRUE; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 대상 파일 세팅하기. +/// @param szFileName +/// @return +/// @date 2004-03-06 오후 11:06:20 +//////////////////////////////////////////////////////////////////////////////////////////////////// +#ifdef _WIN32 +/* +BOOL CUnAlz::SetCurrentFile(LPCWSTR szFileName) +{ + USES_CONVERSION; + return SetCurrentFile(W2A(szFileName)); +} +*/ +#endif // _WIN32 + +BOOL CUnAlz::SetCurrentFile(const char* szFileName) +{ + FileList::iterator i; + + // 순차적으로 찾는다. + for(i=m_fileList.begin(); ifileName, szFileName)==0) +#else + if(strcmp(i->fileName, szFileName)==0) +#endif + { + m_posCur = i; + return TRUE; + } + } + + m_posCur = (FileList::iterator)NULL; + + return FALSE; +} + +#ifndef MAX_WBITS +# define MAX_WBITS 15 /* 32K LZ77 window */ +#endif + + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 버퍼에 압축 풀기. 버퍼는 당근 충분한 크기가 준비되어 있어야 한다. +/// @param pDestBuf +/// @return +/// @date 2004-03-07 오전 12:26:13 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ExtractCurrentFileToBuf(BYTE* pDestBuf, int nBufSize) +{ + SExtractDest dest; + dest.nType = ET_MEM; + dest.buf = pDestBuf; + dest.bufpos = 0; + dest.bufsize = nBufSize; + return ExtractTo(&dest); +} + + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 현재 파일 (SetCurrentFile로 지)을 대상 경로에 대상 파일로 푼다. +/// @param szDestPathName - 대상 경로 +/// @param szDestFileName - 대상 파일명, NULL 이면 원래 파일명 사용 +/// @return +/// @date 2004-03-06 오후 11:06:59 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ExtractCurrentFile(const char* szDestPathName, const char* szDestFileName) +{ + if(m_posCur==(FileList::iterator)NULL) {ASSERT(0); return FALSE;} + + BOOL ret=FALSE; + + SExtractDest dest; + char szDestPathFileName[MAX_PATH]; + + // 경로명 + strcpy(szDestPathFileName, szDestPathName); + if(szDestPathFileName[strlen(szDestPathFileName)]!=PATHSEPC) + strcat(szDestPathFileName, PATHSEP); + + // 파일명 + if(szDestFileName) strcat(szDestPathFileName, szDestFileName); + else strcat(szDestPathFileName, m_posCur->fileName); + + // 압축풀 대상 ( 파일 ) + dest.nType = ET_FILE; + dest.fp = fopen(szDestPathFileName, "wb"); + + if(dest.fp==NULL) + { + DigPath(szDestPathFileName); // 경로명에 / 가 있을 경우.. + dest.fp = fopen(szDestPathFileName, "wb"); + } + + if(dest.fp==NULL) + { + ASSERT(0); + if(m_pFuncCallBack) + { + CHAR buf[1024]; + sprintf(buf, "파일 열기 실패 : %s", szDestPathFileName); + m_pFuncCallBack(buf, 0,0,m_pCallbackParam, NULL); + } + return FALSE; + } + + // CALLBACK 세팅 + if(m_pFuncCallBack) m_pFuncCallBack(m_posCur->fileName, 0,0,m_pCallbackParam, NULL); + + ret = ExtractTo(&dest); + fclose(dest.fp); + return ret; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 대상에 압축 풀기.. +/// @param dest +/// @return +/// @date 2004-03-07 오전 12:44:36 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ExtractTo(SExtractDest* dest) +{ + BOOL ret = FALSE; + // 압축 방법에 따라서 압축 풀기 + if(m_posCur->compressionMethod==COMP_NOCOMP) + { + ret = ExtractRawfile(dest, *m_posCur); + } + else if(m_posCur->compressionMethod==COMP_BZIP2) + { + ret = ExtractBzip2(dest, *m_posCur); // bzip2 + } + else if(m_posCur->compressionMethod==COMP_DEFLATE) + { + ret = ExtractDeflate2(dest, *m_posCur); // deflate + } + else + { + ASSERT(0); // 새로운 방법 ??? + ret = FALSE; + } + return ret; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// DEFLATE 로 풀기 - 테스트용 함수. 모든 파일을 한꺼번에 읽어서 푼다. 실제 사용 안함. +/// @param fp - 대상 파일 +/// @param file - 소스 파일 정보 +/// @return +/// @date 2004-03-06 오후 11:09:17 +//////////////////////////////////////////////////////////////////////////////////////////////////// +/* +BOOL CUnAlz::ExtractDeflate(FILE* fp, SLocalFileHeader& file) +{ + z_stream stream; + BYTE* pInBuf=NULL; + BYTE* pOutBuf=NULL; + int nInBufSize = file.compressedSize; + int nOutBufSize = file.uncompressedSize; + int err; + int flush=Z_SYNC_FLUSH; + BOOL ret = FALSE; + + memset(&stream, 0, sizeof(stream)); + + pInBuf = (BYTE*)malloc(nInBufSize); + if(pInBuf==NULL) + { + m_nErr = ERR_MEM_ALLOC_FAILED; + goto END; + } + + pOutBuf = (BYTE*)malloc(nOutBufSize); + if(pOutBuf==NULL) + { + m_nErr = ERR_MEM_ALLOC_FAILED; + goto END; + } + + // 한번에 읽어서 + fseek(m_fp, file.dwFileDataPos, SEEK_SET); + if(FRead(pInBuf, nInBufSize, 1, m_fp)!=1) + { + m_nErr = ERR_FILE_READ_ERROR; + goto END; + } + + // 초기화.. + inflateInit2(&stream, -MAX_WBITS); + + stream.next_out = pOutBuf; + stream.avail_out = nOutBufSize; + stream.next_in = pInBuf; + stream.avail_in = nInBufSize; + + err = inflate(&stream, flush); + + if(err!=Z_OK && err!=Z_STREAM_END ) + { + m_nErr = ERR_INFLATE_FAILED; + goto END; + } + + fwrite(pOutBuf, 1, nOutBufSize, fp); + + ret = TRUE; + +END : + inflateEnd(&stream); + + if(pInBuf) free(pInBuf); + if(pOutBuf) free(pOutBuf); + return ret; +} +*/ + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 대상 폴더에 현재 압축파일을 전부 풀기 +/// @param szDestPathName - 대상 경로 +/// @return +/// @date 2004-03-06 오후 11:09:49 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ExtractAll(const char* szDestPathName) +{ + FileList::iterator i; + + for(i=m_fileList.begin(); inType==ET_FILE) + { + return fwrite(buf, 1, nSize, dest->fp); + } + else if(dest->nType==ET_MEM) + { + if(dest->bufpos+nSize >dest->bufsize) // 에러.. 버퍼가 넘쳤다. + { + ASSERT(0); + return -1; + } + // memcpy + memcpy(dest->buf + dest->bufpos, buf, nSize); + dest->bufpos += nSize; + return nSize; + } + else + { + ASSERT(0); + } + return -1; +} + +/* 실패한 방법.. 고생한게 아까워서 못지움. +#define ALZDLZ_HEADER_SIZE 4 // alz 파일의 bzip2 헤더 크기 +#define BZIP2_HEADER_SIZE 10 // bzip 파일의 헤더 크기 +#define BZIP2_CRC_SIZE 4 // bzip2 의 crc +#define BZIP2_TAIL_SIZE 10 // 대충 4+5 정도.? +BYTE bzip2Header[BZIP2_HEADER_SIZE] = {0x42, 0x5a, 0x68, 0x39, 0x31, 0x41, 0x59, 0x26, 0x53, 0x59}; + +BOOL CUnAlz::ExtractBzip2_bak(FILE* fp, SLocalFileHeader& file) +{ + bz_stream stream; + BYTE* pInBuf=NULL; + BYTE* pOutBuf=NULL; + int nInBufSize = file.compressedSize; + int nOutBufSize = file.uncompressedSize; + //int err; + int flush=Z_SYNC_FLUSH; + BOOL ret = FALSE; + DWORD crc = 0xffffffff; + + //BYTE temp[100]; + + memset(&stream, 0, sizeof(stream)); + + pInBuf = (BYTE*)malloc(nInBufSize + BZIP2_HEADER_SIZE + BZIP2_CRC_SIZE - ALZDLZ_HEADER_SIZE + BZIP2_TAIL_SIZE); + if(pInBuf==NULL) + { + m_nErr = ERR_MEM_ALLOC_FAILED; + goto END; + } + + pOutBuf = (BYTE*)malloc(nOutBufSize); + if(pOutBuf==NULL) + { + m_nErr = ERR_MEM_ALLOC_FAILED; + goto END; + } + + // ALZ 의 BZIP 헤더 ("DLZ.") 스킵하기. + fseek(m_fp, ALZDLZ_HEADER_SIZE, SEEK_CUR); + // BZIP2 헤더 삽입 + memcpy(pInBuf, bzip2Header, BZIP2_HEADER_SIZE); + // BZIP2 CRC + memcpy(pInBuf+BZIP2_HEADER_SIZE, &(crc), BZIP2_CRC_SIZE); + + // 진짜 압축된 데이타를 한번에 읽어서 + fseek(m_fp, file.dwFileDataPos+ALZDLZ_HEADER_SIZE, SEEK_SET); + if(FRead(pInBuf+BZIP2_HEADER_SIZE+BZIP2_CRC_SIZE, nInBufSize-ALZDLZ_HEADER_SIZE, 1, m_fp)!=1) + { + m_nErr = ERR_FILE_READ_ERROR; + goto END; + } + + + // 초기화.. + stream.bzalloc = NULL; + stream.bzfree = NULL; + stream.opaque = NULL; + ret = BZ2_bzDecompressInit ( &stream, 3,0 ); + if (ret != BZ_OK) goto END; + + + //memcpy(temp, pInBuf, 100); + + stream.next_in = (char*)pInBuf; + stream.next_out = (char*)pOutBuf; + stream.avail_in = nInBufSize+BZIP2_HEADER_SIZE+BZIP2_CRC_SIZE+BZIP2_TAIL_SIZE; + stream.avail_out = nOutBufSize; + + + ret = BZ2_bzDecompress ( &stream ); + + // BZ_DATA_ERROR 가 리턴될 수 있다.. + //if (ret == BZ_OK) goto END; + //if (ret != BZ_STREAM_END) goto END; + + BZ2_bzDecompressEnd(&stream); + + fwrite(pOutBuf, 1, nOutBufSize, fp); + + ret = TRUE; + +END : + + if(pInBuf) free(pInBuf); + if(pOutBuf) free(pOutBuf); + + if(ret==FALSE) BZ2_bzDecompressEnd(&stream); + + return ret; +} +*/ + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// RAW 로 압축된 파일 풀기 +/// @param fp - 대상 파일 +/// @param file - 소스 파일 +/// @return +/// @date 2004-03-06 오후 11:10:53 +//////////////////////////////////////////////////////////////////////////////////////////////////// +#define BUF_LEN (4096*2) +BOOL CUnAlz::ExtractRawfile(SExtractDest* dest, SLocalFileHeader& file) +{ + BOOL ret = FALSE; + BYTE buf[BUF_LEN]; + INT64 read; + INT64 sizeToRead; + INT64 bufLen = BUF_LEN; + INT64 nWritten = 0; + BOOL bHalt = FALSE; + + // 위치 잡고. + FSeek(file.dwFileDataPos); + + sizeToRead = file.compressedSize; // 읽을 크기. + + while(sizeToRead) + { + read = min(sizeToRead, bufLen); + if(FRead(buf, (int)read)==FALSE) + { + break; + } + WriteToDest(dest, buf, (int)read); + //fwrite(buf, read, 1, fp); + sizeToRead -= read; + + nWritten+=read; + + // progress callback + if(m_pFuncCallBack) + { + m_pFuncCallBack(NULL, nWritten, file.uncompressedSize, m_pCallbackParam, &bHalt); + if(bHalt) + { + break; + } + } + } + + m_bHalt = bHalt; + ret = TRUE; + return ret; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// BZIP2 압축 풀기.. +/// @param fp_w - 대상 파일 +/// @param file - 소스 파일 정보 +/// @return +/// @date 2004-03-01 오전 5:47:36 +//////////////////////////////////////////////////////////////////////////////////////////////////// +#define BZIP2_EXTRACT_BUF_SIZE 0x2000 +BOOL CUnAlz::ExtractBzip2(SExtractDest* dest, SLocalFileHeader& file) +{ + BZFILE *bzfp = NULL; + int smallMode = 0; + int verbosity = 1; + int bzerr; + INT64 len; + char buff[BZIP2_EXTRACT_BUF_SIZE]; + INT64 nWritten = 0; + BOOL bHalt = FALSE; + + FSeek(file.dwFileDataPos); + + bzfp = BZ2_bzReadOpen(&bzerr,this,verbosity,smallMode,0,0); + + if(bzfp==NULL){ASSERT(0); return FALSE;} + + while((len=BZ2_bzread(bzfp,buff,BZIP2_EXTRACT_BUF_SIZE))>0) + { + WriteToDest(dest, (BYTE*)buff, (int)len); + //fwrite(buff,1,len,fp_w); + + nWritten+=len; + + // progress callback + if(m_pFuncCallBack) + { + m_pFuncCallBack(NULL, nWritten, file.uncompressedSize, m_pCallbackParam, &bHalt); + if(bHalt) + { + break; + } + } + } + + BZ2_bzReadClose( &bzerr, bzfp); + + m_bHalt = bHalt; + + /* + // FILE* 를 사용할경우 사용하던 코드. - 멀티 볼륨 지원 안함.. + BZFILE *bzfp = NULL; + int smallMode = 0; + int verbosity = 1; + int bzerr; + int len; + char buff[BZIP2_EXTRACT_BUF_SIZE]; + INT64 nWritten = 0; + BOOL bHalt = FALSE; + + FSeek(file.dwFileDataPos, SEEK_SET); + + bzfp = BZ2_bzReadOpen(&bzerr,m_fp,verbosity,smallMode,0,0); + + while((len=BZ2_bzread(bzfp,buff,BZIP2_EXTRACT_BUF_SIZE))>0) + { + WriteToDest(dest, (BYTE*)buff, len); + //fwrite(buff,1,len,fp_w); + + nWritten+=len; + + // progress callback + if(m_pFuncCallBack) + { + m_pFuncCallBack(NULL, nWritten, file.uncompressedSize, m_pCallbackParam, &bHalt); + if(bHalt) + { + break; + } + } + } + + BZ2_bzReadClose( &bzerr, bzfp); + + m_bHalt = bHalt; + */ + + return TRUE; +} + + +#ifndef UNZ_BUFSIZE +#define UNZ_BUFSIZE 0x1000 // (16384) +#endif + +#define IN_BUF_SIZE UNZ_BUFSIZE +#define OUT_BUF_SIZE 0x1000 //IN_BUF_SIZE + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// deflate 로 압축 풀기. ExtractDeflate() 와 달리 조금씩 읽어서 푼다. +/// @param fp +/// @param file +/// @return +/// @date 2004-03-06 오후 11:11:36 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::ExtractDeflate2(SExtractDest* dest, SLocalFileHeader& file) +{ + z_stream stream; + BYTE pInBuf[IN_BUF_SIZE]; + BYTE pOutBuf[OUT_BUF_SIZE]; + int nInBufSize = IN_BUF_SIZE; + int nOutBufSize = OUT_BUF_SIZE; + int err; + int flush=Z_SYNC_FLUSH; + BOOL ret = FALSE; + INT64 nRestReadCompressed; + DWORD dwCRC32= 0; + INT64 rest_read_uncompressed; + UINT iRead = 0; + INT64 nWritten = 0; + BOOL bHalt = FALSE; + + memset(&stream, 0, sizeof(stream)); + + FSeek(file.dwFileDataPos); + + inflateInit2(&stream, -MAX_WBITS); + nRestReadCompressed = file.compressedSize; + rest_read_uncompressed = file.uncompressedSize; + + // 출력 부분. + stream.next_out = pOutBuf; + stream.avail_out = OUT_BUF_SIZE; + + while(stream.avail_out>0) + { + if(stream.avail_in==0 && nRestReadCompressed>0) + { + UINT uReadThis = UNZ_BUFSIZE; + if (nRestReadCompressed<(int)uReadThis) + uReadThis = (UINT)nRestReadCompressed; // 읽을 크기. + + if (uReadThis == 0) + break; // 중지 + + if(FRead(pInBuf, uReadThis)==FALSE) + { + m_nErr = ERR_CANT_READ_FILE; + goto END; + } + + nRestReadCompressed -= uReadThis; + stream.next_in = pInBuf; + stream.avail_in = uReadThis; + } + + UINT uTotalOutBefore,uTotalOutAfter; + const BYTE *bufBefore; + UINT uOutThis; + int flush=Z_SYNC_FLUSH; + + uTotalOutBefore = stream.total_out; + bufBefore = stream.next_out; + + err=inflate(&stream,flush); + + uTotalOutAfter = stream.total_out; + uOutThis = uTotalOutAfter-uTotalOutBefore; + + dwCRC32 = crc32(dwCRC32,bufBefore, (UINT)(uOutThis)); + + rest_read_uncompressed -= uOutThis; + + iRead += (UINT)(uTotalOutAfter - uTotalOutBefore); + + WriteToDest(dest, pOutBuf, uOutThis); + //fwrite(pOutBuf, uOutThis, 1, fp); // file 에 쓰기. + stream.next_out = pOutBuf; + stream.avail_out = OUT_BUF_SIZE; + + nWritten+=uOutThis; + + // progress callback + if(m_pFuncCallBack) + { + m_pFuncCallBack(NULL, nWritten, file.uncompressedSize, m_pCallbackParam, &bHalt); + if(bHalt) + { + break; + } + } + + if (err==Z_STREAM_END) + break; + //if(iRead==0) break; // UNZ_EOF; + if (err!=Z_OK) + { + m_nErr = ERR_INFLATE_FAILED; + goto END; + } + } + + m_bHalt = bHalt; + + ret = TRUE; + +END : + inflateEnd(&stream); + + return ret; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 파일 열기 +/// @param szPathName +/// @return +/// @date 2004-10-02 오후 11:47:14 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::FOpen(const char* szPathName) +{ + char* temp = strdup(szPathName); // 파일명 복사.. + int i; + int nLen = strlen(szPathName); + DWORD dwFileSizeLow,dwFileSizeHigh; + m_nFileCount = 0; + m_nCurFile = 0; + m_nVirtualFilePos = 0; + m_nCurFilePos = 0; + m_bIsEOF = FALSE; + for(i=0;i0) sprintf(temp+nLen-3, "%c%02d", (i-1)/100+'a', (i-1)%100); +#ifdef _WIN32 + m_files[i].fp = CreateFileA(temp, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, FILE_FLAG_SEQUENTIAL_SCAN, NULL); + if(m_files[i].fp==INVALID_HANDLE_VALUE) break; + dwFileSizeLow = GetFileSize(m_files[i].fp, &dwFileSizeHigh); +#else + m_files[i].fp = fopen(temp, "rb"); + if(m_files[i].fp==NULL) break; + dwFileSizeHigh=0; + fseek(m_files[i].fp,0,SEEK_END); + dwFileSizeLow=ftell(m_files[i].fp); + fseek(m_files[i].fp,0,SEEK_SET); +#endif + m_nFileCount++; + m_files[i].nFileSize = ((INT64)dwFileSizeLow) + (((INT64)dwFileSizeHigh)<<32); + if(i==0) m_files[i].nMultivolHeaderSize = 0; + else m_files[i].nMultivolHeaderSize = MULTIVOL_HEAD_SIZE; + m_files[i].nMultivolTailSize = MULTIVOL_TAIL_SIZE; + } + free(temp); + if(m_nFileCount==0) return FALSE; + m_files[m_nFileCount-1].nMultivolTailSize = 0; // 마지막 파일은 꼴랑지가 없다.. + return TRUE; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 파일 닫기 +/// @return +/// @date 2004-10-02 오후 11:48:53 +//////////////////////////////////////////////////////////////////////////////////////////////////// +void CUnAlz::FClose() +{ + int i; +#ifdef _WIN32 + for(i=0;i>32)&0xffffffff); +#ifdef _WIN32 + SetFilePointer(m_files[i].fp, LONG(m_nCurFilePos), &remainHigh, FILE_BEGIN); +#else + fseek(m_files[i].fp, m_nCurFilePos, SEEK_SET); +#endif + return TRUE; + } + remain -= (m_files[i].nFileSize-m_files[i].nMultivolHeaderSize-m_files[i].nMultivolTailSize); + } + + // 실패..? + ASSERT(0); + return FALSE; +} + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// 파일 읽기 +/// @param buffer +/// @param size +/// @param count +/// @return +/// @date 2004-10-02 오후 11:44:05 +//////////////////////////////////////////////////////////////////////////////////////////////////// +BOOL CUnAlz::FRead(void* buffer, DWORD nBytesToRead, int* pTotRead ) +{ + BOOL ret; + DWORD nNumOfBytesRead; + INT64 dwRemain; + DWORD dwRead; + DWORD dwTotRead; + + dwRemain = nBytesToRead; + dwTotRead = 0; + if(pTotRead) *pTotRead=0; + + while(dwRemain) + { + dwRead = (DWORD)min(dwRemain, (m_files[m_nCurFile].nFileSize-m_nCurFilePos-m_files[m_nCurFile].nMultivolTailSize)); + if(dwRead==0) { + m_bIsEOF = TRUE;return FALSE; + } +#ifdef _WIN32 + ret = ReadFile(m_files[m_nCurFile].fp, ((BYTE*)buffer)+dwTotRead, dwRead, &nNumOfBytesRead, NULL); + if(ret==FALSE && GetLastError()==ERROR_HANDLE_EOF) + { + m_bIsEOF = TRUE;return FALSE; + } +#else + nNumOfBytesRead = fread(((BYTE*)buffer)+dwTotRead, 1,dwRead ,m_files[m_nCurFile].fp); + if(nNumOfBytesRead<=0) + { + m_bIsEOF = TRUE;return FALSE; + } + ret=TRUE; +#endif + if(dwRead!=nNumOfBytesRead) // 발생하면 안된다.. + { + ASSERT(0); return FALSE; + } + + m_nVirtualFilePos += nNumOfBytesRead; // virtual 파일 위치.. + + m_nCurFilePos+=nNumOfBytesRead; // 물리적 파일 위치. + dwRemain-=nNumOfBytesRead; + dwTotRead+=nNumOfBytesRead; + if(pTotRead) *pTotRead=dwTotRead; + + if(m_nCurFilePos==m_files[m_nCurFile].nFileSize-m_files[m_nCurFile].nMultivolTailSize) // overflow + { + m_nCurFile++; + +#ifdef _WIN32 + if(m_files[m_nCurFile].fp==INVALID_HANDLE_VALUE) +#else + if(m_files[m_nCurFile].fp==NULL) +#endif + { + m_bIsEOF = TRUE; + if(dwRemain==0) return TRUE; // 완전히 끝까지 읽었다.. + return FALSE; + } + + m_nCurFilePos = m_files[m_nCurFile].nMultivolHeaderSize; // header skip +#ifdef _WIN32 + SetFilePointer(m_files[m_nCurFile].fp, (int)m_nCurFilePos, NULL, FILE_BEGIN); +#else + fseek(m_files[m_nCurFile].fp, m_nCurFilePos, SEEK_SET); +#endif + } + else + if(m_nCurFilePos>m_files[m_nCurFile].nFileSize-m_files[m_nCurFile].nMultivolTailSize) ASSERT(0); + } + + return ret; +} + diff --git a/UnAlz.h b/UnAlz.h new file mode 100644 index 0000000..ec1af8f --- /dev/null +++ b/UnAlz.h @@ -0,0 +1,428 @@ +/* + + COPYRIGHT(C) 2004 hardkoder@gmail.com / http://www.kipple.pe.kr + 저작권 정보 : + - 이 소스는 자유로이 사용/수정/재배포 가능합니다. + - 단, 당신이 만들었다고 주장하거나 거짓말하면 안됨. + - 소스의 오류를 찾았거나, 문제점을 수정하였을 경우 이에 대한 내용을 알려주면 정말 고마울껄.. + - 자신의 프로그램에 이 소스를 사용하였을 경우 원 저작자에게 알려주면 원 저작자가 고마워 할껄.. + + 소스 설명 : + - .ALZ 의 압축을 해제하기 위한 모듈. + - ALZ는 BZIP2변형(변형이라고 뭐 개선한게 아니고, 헤더나 CRC 정보등을 빼서 크기를 줄인 것임)과, + DEFLATE 압축 알고리즘에 ZIP과 유사한 헤더를 만들어서 씌운 포맷임. + ( bzip2 는 4.9x 에서 사용하였고, deflate 는 5.x 부터 사용하였음. 5.x 부터는 bzip2는 너무 느려서 사용 안함 ) + - UnAlzBz2decompress.c 와 UnAlzbzlib.c 는 원래의 bzip2 소스에서 alz 용으로 수정된 파일임 + ( deflate 는 변형이 안되었기 때문에 그냥 zlib 를 써도 되지만.. bzip2 는 변형이 되어서 + 원래의 bzip2 소스를 그대로 쓰면 안된다. ) + - 이 소스는 4칸 탭을 사용 하였음. + + 참고 : + - 원래 소스는 다중 플랫폼에서 사용할수 있게 하기 위해서 stdio 를 사용하였지만 + 2GB 이상의 파일을 처리하기 위해서 어쩔수 없이 WINDOWS I/O 함수로 전부 바꾸었음. + - 리눅스등에서 사용하기 위해서 소스 수정이 필요하다면, 공동 작업을 요청해 주셈. + + 개발 순서 : + 2004/02/06 - http://www.wotsit.org/ 에서 ZIP File Format Specification version 4.5 [PKWARE Inc.] 를 + 다운로드 받아서 분석. + 2004/02/07 - 도큐먼트로 unzip 클래스 대충 구현 + 2004/02/08 - unzip 클래스를 alzip 포맷에 맞추어 변형 및 테스트 + - deflate, rawdata 압축 해제 구현. + - 다이알로그 박스 껍데기 씌움. + 2004/02/08 - bzip2 대충 지원 + 2004/03/01 - bzip2 거의 완벽 지원 乃 + - callback 구현.. + 2004/03/07 - 유틸 함수 추가 ( ExtractCurrentFileToBuf() ) + 2004/10/03 - 분할 압축 해제 기능 추가 ( FILE I/O 에 대한 래퍼 클래스 구현 ) + - 2GB 이상의 파일 처리 지원 + + 할일 : + - bzip2 로 압축된 파일의 압축 해제 + - UI 개선 ( PROGRESS, 에러 메시지 출력, 압축 해제 결과 ) + - 분할 압축 파일 지원 + + - 암호 걸린 파일 지원 + - 손상된 파일에서의 좀더 많은 테스트 + - 파일 CRC 체크 + + 할일중 한일 : + - bzip2 로 압축된 파일의 압축 해제 + - UI 개선 ( PROGRESS, 에러 메시지 출력, 압축 해제 결과 ) + - 분할 압축 파일 지원 +*/ + + +#ifndef _UNALZ_H_ +#define _UNALZ_H_ + +#include +#include +using namespace std; + + +#ifndef INT64 +#ifdef _WIN32 +# define INT64 __int64 +#else +# define INT64 long long +#endif +#endif + +#ifndef DWORD + typedef unsigned long DWORD; +#endif // DWORD +#ifndef SHORT + typedef short SHORT; +#endif +#ifndef BYTE + typedef unsigned char BYTE; +#endif +#ifndef CHAR + typedef char CHAR; +#endif +#ifndef BYTE + typedef unsigned char BYTE; +#endif +#ifndef UINT + typedef unsigned int UINT; +#endif +#ifndef LONG + typedef long LONG; +#endif +#ifndef BOOL + typedef int BOOL; +#endif +#ifndef FALSE +# define FALSE 0 +#endif +#ifndef TRUE +# define TRUE 1 +#endif +#ifndef LPCTSTR + typedef const char* LPCSTR; +#endif +#ifndef HANDLE +# ifdef _WIN32 + typedef void *HANDLE; +# else + typedef FILE *HANDLE; +# endif +#endif +#ifndef ASSERT +# include +# define ASSERT(x) assert(x) +#endif + + + + + + + +namespace UNALZ +{ + +#ifdef _WIN32 +# pragma pack(push, UNALZ, 1) // structure packing +#else +# pragma pack(1) +#endif + +static const char UNALZ_VERSION[] = "CUnAlz0.2"; +static const char UNALZ_COPYRIGHT[] = "Copyright(C) 2004 hardkoder@gmail.com"; + + +// 맨 파일 앞.. +struct SAlzHeader +{ + DWORD unknown; // ?? +}; + +/* +union _UGeneralPurposeBitFlag // zip 에서만 사용.. +{ + SHORT data; + struct + { + BYTE bit0 : 1; + BYTE bit1 : 1; + BYTE bit2 : 1; + BYTE bit3 : 1; + BYTE bit4 : 1; + BYTE bit5 : 1; + }; +}; +*/ + +enum COMPRESSION_METHOD ///< 압축 방법.. +{ + COMP_NOCOMP = 0, + COMP_BZIP2 = 1, + COMP_DEFLATE = 2, +}; + +struct _SLocalFileHeaderHead ///< 고정 헤더. +{ + SHORT fileNameLength; + BYTE unknown[5]; ///< ??? + BYTE fileSizeByte; ///< 파일 크기 필드의 크기 : 0x10, 0x20, 0x40, 0x80 각각 1byte, 2byte, 4byte, 8byte + BYTE unknown2[1]; ///< ??? + + /* + SHORT versionNeededToExtract; + _UGeneralPurposeBitFlag generalPurposeBitFlag; + SHORT compressionMethod; + SHORT lastModFileTime; + SHORT lastModFileDate; + DWORD crc32; + DWORD compressedSize; + DWORD uncompressedSize; + SHORT fileNameLength; + SHORT extraFieldLength; + */ +}; + +struct _SDataDescriptor +{ + DWORD crc32; + DWORD compressed; + DWORD uncompressed; +}; + +struct SLocalFileHeader +{ + SLocalFileHeader() { memset(this, 0, sizeof(*this)); } + //~SLocalFileHeader() { if(fileName) free(fileName); if(extraField) free(extraField); } + void Clear() { if(fileName) free(fileName); fileName=NULL; if(extraField) free(extraField);extraField=NULL; } + _SLocalFileHeaderHead head; + + BYTE compressionMethod; ///< 압축 방법 : 2 - deflate, 1 - bzip2(?), 0 - 압축 안함. + BYTE unknown3[1]; ///< ??? + DWORD maybeCRC; ///< 아마도 crc + + INT64 compressedSize; + INT64 uncompressedSize; + + CHAR* fileName; + BYTE* extraField; + _SDataDescriptor dataDescriptor; + INT64 dwFileDataPos; ///< file data 가 저장된 위치.. +}; + +struct _SCentralDirectoryStructureHead +{ + DWORD dwUnknown; ///< 항상 NULL 이던데.. + DWORD dwMaybeCRC; ///< 아마도 crc + DWORD dwCLZ03; ///< "CLZ0x03" - 0x035a4c43 끝을 표시하는듯. + /* + SHORT versionMadeBy; + SHORT versionNeededToExtract; + _UGeneralPurposeBitFlag generalPurposeBitFlag; + SHORT compressionMethod; + SHORT lastModFileTime; + SHORT lastModFileDate; + DWORD crc32; + DWORD compressedSize; + DWORD uncompressedSize; + SHORT fileNameLength; + SHORT extraFieldLength; + SHORT fileCommentLength; + SHORT diskNumberStart; + SHORT internalFileAttributes; + DWORD externalFileAttributes; + DWORD relativeOffsetOfLocalHeader; + */ +}; + +struct SCentralDirectoryStructure +{ + SCentralDirectoryStructure() { memset(this, 0, sizeof(*this)); } + //~SCentralDirectoryStructure() { if(fileName) free(fileName); if(extraField) free(extraField);if(fileComment)free(fileComment); } + _SCentralDirectoryStructureHead head; + /* + CHAR* fileName; + BYTE* extraField; + CHAR* fileComment; + */ +}; + + +/* +struct _SEndOfCentralDirectoryRecordHead +{ + SHORT numberOfThisDisk; + SHORT numberOfTheDiskWithTheStartOfTheCentralDirectory; + SHORT centralDirectoryOnThisDisk; + SHORT totalNumberOfEntriesInTheCentralDirectoryOnThisDisk; + DWORD sizeOfTheCentralDirectory; + DWORD offsetOfStartOfCentralDirectoryWithREspectoTotheStartingDiskNumber; + SHORT zipFileCommentLength; +}; +*/ + +/* +struct SEndOfCentralDirectoryRecord +{ + SEndOfCentralDirectoryRecord() { memset(this, 0, sizeof(*this)); } + ~SEndOfCentralDirectoryRecord() { if(fileComment) free(fileComment); } + _SEndOfCentralDirectoryRecordHead head; + CHAR* fileComment; +}; +*/ + +#ifdef _WIN32 +#pragma pack(pop, UNALZ) ///< PACKING 원상 복구 +#else +#pragma pack(4) +#endif + + +///< PROGRESS CALLBACK FUNCTION - 압축 해제 진행 상황을 알고 싶으면 이걸 쓰면 된다. +typedef void (_UnAlzCallback)(const char* szMessage, INT64 nCurrent, INT64 nRange, void* param, BOOL* bHalt); + + +class CUnAlz +{ +public: + CUnAlz(); + ~CUnAlz(); + BOOL Open(const char* szPathName); + void Close(); + BOOL SetCurrentFile(const char* szFileName); + BOOL ExtractCurrentFile(const char* szDestPathName, const char* szDestFileName=NULL); + BOOL ExtractCurrentFileToBuf(BYTE* pDestBuf, int nBufSize); + BOOL ExtractAll(const char* szDestPathName); + void SetCallback(_UnAlzCallback* pFunc, void* param=NULL); + +public : ///< WIN32 전용 ( UNICODE 처리용 ) +/* +#ifdef _WIN32 + BOOL Open(LPCWSTR szPathName); + BOOL SetCurrentFile(LPCWSTR szFileName); + static BOOL IsFolder(LPCWSTR szPathName); +#endif +*/ + +public : + typedef vector FileList; ///< 파일 목록. + const FileList& GetFileList() { return m_fileList; }; ///< file 목록 리턴 + FileList::iterator GetCurFileHeader() { return m_posCur; }; ///< 현재 (SetCurrentFile() 로 세팅된) 파일 정보 +// const SLocalFileHeader* GetCurFileHeader() { return _posCur; }; ///< 현재 (SetCurrentFile() 로 세팅된) 파일 정보 + +public : + enum ERR ///< 에러 코드 - 정리 필요.. + { + ERR_NOERR, + ERR_CANT_OPEN_FILE, ///< 파일 열기 실패 + ERR_CANT_READ_SIG, ///< signature 읽기 실패 + ERR_CANT_READ_FILE, + + ERR_AT_READ_HEADER, + ERR_INVALID_FILENAME_LENGTH, + ERR_INVALID_EXTRAFIELD_LENGTH, + ERR_CANT_READ_CENTRAL_DIRECTORY_STRUCTURE_HEAD, + ERR_INVALID_FILENAME_SIZE, + ERR_INVALID_EXTRAFIELD_SIZE, + ERR_INVALID_FILECOMMENT_SIZE, + ERR_CANT_READ_HEADER, + ERR_MEM_ALLOC_FAILED, + ERR_FILE_READ_ERROR, + ERR_INFLATE_FAILED, + }; + ERR GetLastErr(){return m_nErr;} + + enum SIGNATURE ///< zip file signature + { + SIG_ERR = 0x00, + SIG_EOF = 0x01, + SIG_ALZ_FILE_HEADER = 0x015a4c41, ///< ALZ 0x01 + SIG_LOCAL_FILE_HEADER = 0x015a4c42, ///< BLZ 0x01 + SIG_CENTRAL_DIRECTORY_STRUCTURE = 0x015a4c43, ///< CLZ 0x01 + SIG_ENDOF_CENTRAL_DIRECTORY_RECORD = 0x025a4c43, ///< CLZ 0x02 + }; + +public : + static BOOL DigPath(const char* szPathName); + static BOOL IsFolder(LPCSTR szPathName); + static const char* GetVersion() { return UNALZ_VERSION; } + static const char* GetCopyright() { return UNALZ_COPYRIGHT; } + +private : + SIGNATURE ReadSignature(); + BOOL ReadAlzFileHeader(); + BOOL ReadLocalFileheader(); + BOOL ReadCentralDirectoryStructure(); + BOOL ReadEndofCentralDirectoryRecord(); + +private : + enum EXTRACT_TYPE ///< 압축 해제 타입. + { + ET_FILE, ///< FILE* + ET_MEM, ///< memory buffer + }; + struct SExtractDest ///< 압축 해제 대상. + { + SExtractDest() { memset(this, 0, sizeof(SExtractDest)); } + EXTRACT_TYPE nType; ///< 대상이 파일인가 메모리 인가.. + FILE* fp; ///< ET_FILE 일 경우 대상 FILE* + BYTE* buf; ///< ET_MEM 일 경우 대상 포인터 + DWORD bufsize; ///< ET_MEM 일 경우 대상 버퍼의 크기 + DWORD bufpos; ///< ET_MEM 일 경우 대상 버퍼에 쓰고 있는 위치 + }; + int WriteToDest(SExtractDest* dest, BYTE* buf, int nSize); + +private : + BOOL ExtractTo(SExtractDest* dest); + + //BOOL ExtractDeflate(FILE* fp, SLocalFileHeader& file); + //BOOL ExtractBzip2_bak(FILE* fp, SLocalFileHeader& file); - 실패한(잘못된) 방법 + BOOL ExtractDeflate2(SExtractDest* dest, SLocalFileHeader& file); + BOOL ExtractBzip2(SExtractDest* dest, SLocalFileHeader& file); + BOOL ExtractRawfile(SExtractDest* dest, SLocalFileHeader& file); + +private : // bzip2 파일 처리 함수.. + typedef void MYBZFILE; + MYBZFILE* BZ2_bzReadOpen(int* bzerror, CUnAlz* f, int verbosity, int _small, void* unused, int nUnused); + int BZ2_bzread(MYBZFILE* b, void* buf, int len ); + int BZ2_bzRead(int* bzerror, MYBZFILE* b, void* buf, int len); + void BZ2_bzReadClose( int *bzerror, MYBZFILE *b ); + +private : // 분할 압축 파일 처리를 위한 래퍼(lapper?) 클래스 + BOOL FOpen(const char* szPathName); + void FClose(); + INT64 FTell(); + BOOL FEof(); + BOOL FSeek(INT64 offset); + BOOL FRead(void* buffer, DWORD nBytesToRead, int* pTotRead=NULL); + + enum {MAX_FILES=1000}; ///< 처리 가능한 분할 압축 파일 수. + enum {MULTIVOL_TAIL_SIZE=16,MULTIVOL_HEAD_SIZE=8}; ///< 분할 압축시 꼴랑지, 헤더 크기 + struct SFile ///< 분할 파일 정보 + { + HANDLE fp; + INT64 nFileSize; + int nMultivolHeaderSize; + int nMultivolTailSize; + }; + + SFile m_files[MAX_FILES]; ///< 분할 파일 저장 array - 무식한가? + int m_nCurFile; ///< m_files 에서 현재 처리중인 파일의 위치. + int m_nFileCount; ///< 분할 파일 갯수.. + INT64 m_nVirtualFilePos; ///< 멀티볼륨에서의 가상의 위치 + INT64 m_nCurFilePos; ///< 현재 파일의 물리적 위치. + BOOL m_bIsEOF; ///< 파일의 끝까지 (분할 파일 포함해서) 왔나? + + +private : + FileList m_fileList; ///< 압축파일 내의 파일 목록 + ERR m_nErr; + FileList::iterator m_posCur; ///< 현재 파일 + _UnAlzCallback* m_pFuncCallBack; + void* m_pCallbackParam; + BOOL m_bHalt; +}; +} + +using namespace UNALZ; + +#endif diff --git a/UnAlzBz2decompress.c b/UnAlzBz2decompress.c new file mode 100644 index 0000000..920c22a --- /dev/null +++ b/UnAlzBz2decompress.c @@ -0,0 +1,728 @@ +// ALZ 압축 해제를 위해서 수정된 bzip2 소스 +// [ALZ] 라고 표시된 부분이 수정된 부분이다. + + +/*-------------------------------------------------------------*/ +/*--- Decompression machinery ---*/ +/*--- decompress.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + + +#include "bzip2/bzlib_private.h" + + +/*---------------------------------------------------*/ +static +void makeMaps_d ( DState* s ) +{ + Int32 i; + s->nInUse = 0; + for (i = 0; i < 256; i++) + if (s->inUse[i]) { + s->seqToUnseq[s->nInUse] = i; + s->nInUse++; + } +} + + +/*---------------------------------------------------*/ +#define RETURN(rrr) \ + { retVal = rrr; goto save_state_and_return; }; + +#define GET_BITS(lll,vvv,nnn) \ + case lll: s->state = lll; \ + while (True) { \ + if (s->bsLive >= nnn) { \ + UInt32 v; \ + v = (s->bsBuff >> \ + (s->bsLive-nnn)) & ((1 << nnn)-1); \ + s->bsLive -= nnn; \ + vvv = v; \ + break; \ + } \ + if (s->strm->avail_in == 0) RETURN(BZ_OK); \ + s->bsBuff \ + = (s->bsBuff << 8) | \ + ((UInt32) \ + (*((UChar*)(s->strm->next_in)))); \ + s->bsLive += 8; \ + s->strm->next_in++; \ + s->strm->avail_in--; \ + s->strm->total_in_lo32++; \ + if (s->strm->total_in_lo32 == 0) \ + s->strm->total_in_hi32++; \ + } + +#define GET_UCHAR(lll,uuu) \ + GET_BITS(lll,uuu,8) + +#define GET_BIT(lll,uuu) \ + GET_BITS(lll,uuu,1) + +/*---------------------------------------------------*/ +#define GET_MTF_VAL(label1,label2,lval) \ +{ \ + if (groupPos == 0) { \ + groupNo++; \ + if (groupNo >= nSelectors) \ + RETURN(BZ_DATA_ERROR); \ + groupPos = BZ_G_SIZE; \ + gSel = s->selector[groupNo]; \ + gMinlen = s->minLens[gSel]; \ + gLimit = &(s->limit[gSel][0]); \ + gPerm = &(s->perm[gSel][0]); \ + gBase = &(s->base[gSel][0]); \ + } \ + groupPos--; \ + zn = gMinlen; \ + GET_BITS(label1, zvec, zn); \ + while (1) { \ + if (zn > 20 /* the longest code */) \ + RETURN(BZ_DATA_ERROR); \ + if (zvec <= gLimit[zn]) break; \ + zn++; \ + GET_BIT(label2, zj); \ + zvec = (zvec << 1) | zj; \ + }; \ + if (zvec - gBase[zn] < 0 \ + || zvec - gBase[zn] >= BZ_MAX_ALPHA_SIZE) \ + RETURN(BZ_DATA_ERROR); \ + lval = gPerm[zvec - gBase[zn]]; \ +} + + +/*---------------------------------------------------*/ +Int32 BZ2_decompress ( DState* s ) +{ + UChar uc; + Int32 retVal; + Int32 minLen, maxLen; + bz_stream* strm = s->strm; + + /* stuff that needs to be saved/restored */ + Int32 i; + Int32 j; + Int32 t; + Int32 alphaSize; + Int32 nGroups; + Int32 nSelectors; + Int32 EOB; + Int32 groupNo; + Int32 groupPos; + Int32 nextSym; + Int32 nblockMAX; + Int32 nblock; + Int32 es; + Int32 N; + Int32 curr; + Int32 zt; + Int32 zn; + Int32 zvec; + Int32 zj; + Int32 gSel; + Int32 gMinlen; + Int32* gLimit; + Int32* gBase; + Int32* gPerm; + + if (s->state == BZ_X_MAGIC_1) { + /*initialise the save area*/ + s->save_i = 0; + s->save_j = 0; + s->save_t = 0; + s->save_alphaSize = 0; + s->save_nGroups = 0; + s->save_nSelectors = 0; + s->save_EOB = 0; + s->save_groupNo = 0; + s->save_groupPos = 0; + s->save_nextSym = 0; + s->save_nblockMAX = 0; + s->save_nblock = 0; + s->save_es = 0; + s->save_N = 0; + s->save_curr = 0; + s->save_zt = 0; + s->save_zn = 0; + s->save_zvec = 0; + s->save_zj = 0; + s->save_gSel = 0; + s->save_gMinlen = 0; + s->save_gLimit = NULL; + s->save_gBase = NULL; + s->save_gPerm = NULL; + } + + /*restore from the save area*/ + i = s->save_i; + j = s->save_j; + t = s->save_t; + alphaSize = s->save_alphaSize; + nGroups = s->save_nGroups; + nSelectors = s->save_nSelectors; + EOB = s->save_EOB; + groupNo = s->save_groupNo; + groupPos = s->save_groupPos; + nextSym = s->save_nextSym; + nblockMAX = s->save_nblockMAX; + nblock = s->save_nblock; + es = s->save_es; + N = s->save_N; + curr = s->save_curr; + zt = s->save_zt; + zn = s->save_zn; + zvec = s->save_zvec; + zj = s->save_zj; + gSel = s->save_gSel; + gMinlen = s->save_gMinlen; + gLimit = s->save_gLimit; + gBase = s->save_gBase; + gPerm = s->save_gPerm; + + retVal = BZ_OK; + + switch (s->state) { + + // [ALZ] - 머리 떼기 + /* + GET_UCHAR(BZ_X_MAGIC_1, uc); + if (uc != BZ_HDR_B) + RETURN(BZ_DATA_ERROR_MAGIC); + + GET_UCHAR(BZ_X_MAGIC_2, uc); + if (uc != BZ_HDR_Z) + RETURN(BZ_DATA_ERROR_MAGIC); + + GET_UCHAR(BZ_X_MAGIC_3, uc) + if (uc != BZ_HDR_h) + RETURN(BZ_DATA_ERROR_MAGIC); + */ + + case BZ_X_MAGIC_1 : // 없어진 헤더 인식 대신 + + // [ALZ] - blocksize 지정 없음 + //GET_BITS(BZ_X_MAGIC_4, s->blockSize100k, 8) + s->blockSize100k = 0x39; // static 할당. + + if (s->blockSize100k < (BZ_HDR_0 + 1) || + s->blockSize100k > (BZ_HDR_0 + 9)) + RETURN(BZ_DATA_ERROR_MAGIC); + s->blockSize100k -= BZ_HDR_0; + + if (s->smallDecompress) { + s->ll16 = BZALLOC( s->blockSize100k * 100000 * sizeof(UInt16) ); + s->ll4 = BZALLOC( + ((1 + s->blockSize100k * 100000) >> 1) * sizeof(UChar) + ); + if (s->ll16 == NULL || s->ll4 == NULL) + RETURN(BZ_MEM_ERROR); + } else { + s->tt = BZALLOC( s->blockSize100k * 100000 * sizeof(Int32) ); + if (s->tt == NULL) + RETURN(BZ_MEM_ERROR); + } + + GET_UCHAR(BZ_X_BLKHDR_1, uc); + + // [ALZ] - 변형된 헤더 + + if (uc != 'D') + RETURN(BZ_DATA_ERROR_MAGIC); + + GET_UCHAR(BZ_X_BLKHDR_2, uc); + if (uc != 'L') + RETURN(BZ_DATA_ERROR_MAGIC); + + GET_UCHAR(BZ_X_BLKHDR_3, uc) + if (uc != 'Z') + RETURN(BZ_DATA_ERROR_MAGIC); + + GET_UCHAR(BZ_X_BLKHDR_4, uc) + + if (uc == 0x02) + goto endhdr_2; + + if (uc != 0x01) + RETURN(BZ_DATA_ERROR_MAGIC); + + /* [ALZ] - 원래 헤더 + if (uc == 0x17) goto endhdr_2; + if (uc != 0x31) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_BLKHDR_2, uc); + if (uc != 0x41) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_BLKHDR_3, uc); + if (uc != 0x59) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_BLKHDR_4, uc); + if (uc != 0x26) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_BLKHDR_5, uc); + if (uc != 0x53) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_BLKHDR_6, uc); + if (uc != 0x59) + RETURN(BZ_DATA_ERROR); + */ + + s->currBlockNo++; + if (s->verbosity >= 2) + VPrintf1 ( "\n [%d: huff+mtf ", s->currBlockNo ); + + s->storedBlockCRC = 0; + + /* [ALZ] - crc 빼기 + GET_UCHAR(BZ_X_BCRC_1, uc); + s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc); + GET_UCHAR(BZ_X_BCRC_2, uc); + s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc); + GET_UCHAR(BZ_X_BCRC_3, uc); + s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc); + GET_UCHAR(BZ_X_BCRC_4, uc); + s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc); + */ + + // [ALZ] - 1bit 아끼기 + //GET_BITS(BZ_X_RANDBIT, s->blockRandomised, 1); + + s->origPtr = 0; + GET_UCHAR(BZ_X_ORIGPTR_1, uc); + s->origPtr = (s->origPtr << 8) | ((Int32)uc); + GET_UCHAR(BZ_X_ORIGPTR_2, uc); + s->origPtr = (s->origPtr << 8) | ((Int32)uc); + GET_UCHAR(BZ_X_ORIGPTR_3, uc); + s->origPtr = (s->origPtr << 8) | ((Int32)uc); + + if (s->origPtr < 0) + RETURN(BZ_DATA_ERROR); + if (s->origPtr > 10 + 100000*s->blockSize100k) + RETURN(BZ_DATA_ERROR); + + /*--- Receive the mapping table ---*/ + for (i = 0; i < 16; i++) { + GET_BIT(BZ_X_MAPPING_1, uc); + if (uc == 1) + s->inUse16[i] = True; else + s->inUse16[i] = False; + } + + for (i = 0; i < 256; i++) s->inUse[i] = False; + + for (i = 0; i < 16; i++) + if (s->inUse16[i]) + for (j = 0; j < 16; j++) { + GET_BIT(BZ_X_MAPPING_2, uc); + if (uc == 1) s->inUse[i * 16 + j] = True; + } + makeMaps_d ( s ); + if (s->nInUse == 0) + RETURN(BZ_DATA_ERROR); + alphaSize = s->nInUse+2; + + /*--- Now the selectors ---*/ + GET_BITS(BZ_X_SELECTOR_1, nGroups, 3); + if (nGroups < 2 || nGroups > 6) + RETURN(BZ_DATA_ERROR); + GET_BITS(BZ_X_SELECTOR_2, nSelectors, 15); + if (nSelectors < 1) + RETURN(BZ_DATA_ERROR); + for (i = 0; i < nSelectors; i++) { + j = 0; + while (True) { + GET_BIT(BZ_X_SELECTOR_3, uc); + if (uc == 0) break; + j++; + if (j >= nGroups) + RETURN(BZ_DATA_ERROR); + } + s->selectorMtf[i] = j; + } + + /*--- Undo the MTF values for the selectors. ---*/ + { + UChar pos[BZ_N_GROUPS], tmp, v; + for (v = 0; v < nGroups; v++) pos[v] = v; + + for (i = 0; i < nSelectors; i++) { + v = s->selectorMtf[i]; + tmp = pos[v]; + while (v > 0) { pos[v] = pos[v-1]; v--; } + pos[0] = tmp; + s->selector[i] = tmp; + } + } + + /*--- Now the coding tables ---*/ + for (t = 0; t < nGroups; t++) { + GET_BITS(BZ_X_CODING_1, curr, 5); + for (i = 0; i < alphaSize; i++) { + while (True) { + if (curr < 1 || curr > 20) + RETURN(BZ_DATA_ERROR); + GET_BIT(BZ_X_CODING_2, uc); + if (uc == 0) break; + GET_BIT(BZ_X_CODING_3, uc); + if (uc == 0) curr++; else curr--; + } + s->len[t][i] = curr; + } + } + + /*--- Create the Huffman decoding tables ---*/ + for (t = 0; t < nGroups; t++) { + minLen = 32; + maxLen = 0; + for (i = 0; i < alphaSize; i++) { + if (s->len[t][i] > maxLen) maxLen = s->len[t][i]; + if (s->len[t][i] < minLen) minLen = s->len[t][i]; + } + BZ2_hbCreateDecodeTables ( + &(s->limit[t][0]), + &(s->base[t][0]), + &(s->perm[t][0]), + &(s->len[t][0]), + minLen, maxLen, alphaSize + ); + s->minLens[t] = minLen; + } + + /*--- Now the MTF values ---*/ + + EOB = s->nInUse+1; + nblockMAX = 100000 * s->blockSize100k; + groupNo = -1; + groupPos = 0; + + for (i = 0; i <= 255; i++) s->unzftab[i] = 0; + + /*-- MTF init --*/ + { + Int32 ii, jj, kk; + kk = MTFA_SIZE-1; + for (ii = 256 / MTFL_SIZE - 1; ii >= 0; ii--) { + for (jj = MTFL_SIZE-1; jj >= 0; jj--) { + s->mtfa[kk] = (UChar)(ii * MTFL_SIZE + jj); + kk--; + } + s->mtfbase[ii] = kk + 1; + } + } + /*-- end MTF init --*/ + + nblock = 0; + GET_MTF_VAL(BZ_X_MTF_1, BZ_X_MTF_2, nextSym); + + while (True) { + + if (nextSym == EOB) break; + + if (nextSym == BZ_RUNA || nextSym == BZ_RUNB) { + + es = -1; + N = 1; + do { + if (nextSym == BZ_RUNA) es = es + (0+1) * N; else + if (nextSym == BZ_RUNB) es = es + (1+1) * N; + N = N * 2; + GET_MTF_VAL(BZ_X_MTF_3, BZ_X_MTF_4, nextSym); + } + while (nextSym == BZ_RUNA || nextSym == BZ_RUNB); + + es++; + uc = s->seqToUnseq[ s->mtfa[s->mtfbase[0]] ]; + s->unzftab[uc] += es; + + if (s->smallDecompress) + while (es > 0) { + if (nblock >= nblockMAX) + RETURN(BZ_DATA_ERROR); + s->ll16[nblock] = (UInt16)uc; + nblock++; + es--; + } + else + while (es > 0) { + if (nblock >= nblockMAX) + RETURN(BZ_DATA_ERROR); + s->tt[nblock] = (UInt32)uc; + nblock++; + es--; + }; + + continue; + + } else { + + if (nblock >= nblockMAX) + RETURN(BZ_DATA_ERROR); + + /*-- uc = MTF ( nextSym-1 ) --*/ + { + Int32 ii, jj, kk, pp, lno, off; + UInt32 nn; + nn = (UInt32)(nextSym - 1); + + if (nn < MTFL_SIZE) { + /* avoid general-case expense */ + pp = s->mtfbase[0]; + uc = s->mtfa[pp+nn]; + while (nn > 3) { + Int32 z = pp+nn; + s->mtfa[(z) ] = s->mtfa[(z)-1]; + s->mtfa[(z)-1] = s->mtfa[(z)-2]; + s->mtfa[(z)-2] = s->mtfa[(z)-3]; + s->mtfa[(z)-3] = s->mtfa[(z)-4]; + nn -= 4; + } + while (nn > 0) { + s->mtfa[(pp+nn)] = s->mtfa[(pp+nn)-1]; nn--; + }; + s->mtfa[pp] = uc; + } else { + /* general case */ + lno = nn / MTFL_SIZE; + off = nn % MTFL_SIZE; + pp = s->mtfbase[lno] + off; + uc = s->mtfa[pp]; + while (pp > s->mtfbase[lno]) { + s->mtfa[pp] = s->mtfa[pp-1]; pp--; + }; + s->mtfbase[lno]++; + while (lno > 0) { + s->mtfbase[lno]--; + s->mtfa[s->mtfbase[lno]] + = s->mtfa[s->mtfbase[lno-1] + MTFL_SIZE - 1]; + lno--; + } + s->mtfbase[0]--; + s->mtfa[s->mtfbase[0]] = uc; + if (s->mtfbase[0] == 0) { + kk = MTFA_SIZE-1; + for (ii = 256 / MTFL_SIZE-1; ii >= 0; ii--) { + for (jj = MTFL_SIZE-1; jj >= 0; jj--) { + s->mtfa[kk] = s->mtfa[s->mtfbase[ii] + jj]; + kk--; + } + s->mtfbase[ii] = kk + 1; + } + } + } + } + /*-- end uc = MTF ( nextSym-1 ) --*/ + + s->unzftab[s->seqToUnseq[uc]]++; + if (s->smallDecompress) + s->ll16[nblock] = (UInt16)(s->seqToUnseq[uc]); else + s->tt[nblock] = (UInt32)(s->seqToUnseq[uc]); + nblock++; + + GET_MTF_VAL(BZ_X_MTF_5, BZ_X_MTF_6, nextSym); + continue; + } + } + + /* Now we know what nblock is, we can do a better sanity + check on s->origPtr. + */ + if (s->origPtr < 0 || s->origPtr >= nblock) + RETURN(BZ_DATA_ERROR); + + s->state_out_len = 0; + s->state_out_ch = 0; + BZ_INITIALISE_CRC ( s->calculatedBlockCRC ); + s->state = BZ_X_OUTPUT; + if (s->verbosity >= 2) VPrintf0 ( "rt+rld" ); + + /*-- Set up cftab to facilitate generation of T^(-1) --*/ + s->cftab[0] = 0; + for (i = 1; i <= 256; i++) s->cftab[i] = s->unzftab[i-1]; + for (i = 1; i <= 256; i++) s->cftab[i] += s->cftab[i-1]; + + if (s->smallDecompress) { + + /*-- Make a copy of cftab, used in generation of T --*/ + for (i = 0; i <= 256; i++) s->cftabCopy[i] = s->cftab[i]; + + /*-- compute the T vector --*/ + for (i = 0; i < nblock; i++) { + uc = (UChar)(s->ll16[i]); + SET_LL(i, s->cftabCopy[uc]); + s->cftabCopy[uc]++; + } + + /*-- Compute T^(-1) by pointer reversal on T --*/ + i = s->origPtr; + j = GET_LL(i); + do { + Int32 tmp = GET_LL(j); + SET_LL(j, i); + i = j; + j = tmp; + } + while (i != s->origPtr); + + s->tPos = s->origPtr; + s->nblock_used = 0; + if (s->blockRandomised) { + BZ_RAND_INIT_MASK; + BZ_GET_SMALL(s->k0); s->nblock_used++; + BZ_RAND_UPD_MASK; s->k0 ^= BZ_RAND_MASK; + } else { + BZ_GET_SMALL(s->k0); s->nblock_used++; + } + + } else { + + /*-- compute the T^(-1) vector --*/ + for (i = 0; i < nblock; i++) { + uc = (UChar)(s->tt[i] & 0xff); + s->tt[s->cftab[uc]] |= (i << 8); + s->cftab[uc]++; + } + + s->tPos = s->tt[s->origPtr] >> 8; + s->nblock_used = 0; + // [ALZ] - s->blockRandomised 는 생략 되었다. + /* + if (s->blockRandomised) { + BZ_RAND_INIT_MASK; + BZ_GET_FAST(s->k0); s->nblock_used++; + BZ_RAND_UPD_MASK; s->k0 ^= BZ_RAND_MASK; + } else*/ { + BZ_GET_FAST(s->k0); s->nblock_used++; + } + + } + + RETURN(BZ_OK); + + + + endhdr_2: + + // [ALZ] - 꼬리 떼기 + /* + GET_UCHAR(BZ_X_ENDHDR_2, uc); + if (uc != 0x72) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_ENDHDR_3, uc); + if (uc != 0x45) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_ENDHDR_4, uc); + if (uc != 0x38) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_ENDHDR_5, uc); + if (uc != 0x50) + RETURN(BZ_DATA_ERROR); + GET_UCHAR(BZ_X_ENDHDR_6, uc); + if (uc != 0x90) + RETURN(BZ_DATA_ERROR); + + s->storedCombinedCRC = 0; + GET_UCHAR(BZ_X_CCRC_1, uc); + s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc); + GET_UCHAR(BZ_X_CCRC_2, uc); + s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc); + GET_UCHAR(BZ_X_CCRC_3, uc); + s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc); + GET_UCHAR(BZ_X_CCRC_4, uc); + s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc); + */ + + s->state = BZ_X_IDLE; + RETURN(BZ_STREAM_END); + + default: AssertH ( False, 4001 ); + } + + AssertH ( False, 4002 ); + + save_state_and_return: + + s->save_i = i; + s->save_j = j; + s->save_t = t; + s->save_alphaSize = alphaSize; + s->save_nGroups = nGroups; + s->save_nSelectors = nSelectors; + s->save_EOB = EOB; + s->save_groupNo = groupNo; + s->save_groupPos = groupPos; + s->save_nextSym = nextSym; + s->save_nblockMAX = nblockMAX; + s->save_nblock = nblock; + s->save_es = es; + s->save_N = N; + s->save_curr = curr; + s->save_zt = zt; + s->save_zn = zn; + s->save_zvec = zvec; + s->save_zj = zj; + s->save_gSel = gSel; + s->save_gMinlen = gMinlen; + s->save_gLimit = gLimit; + s->save_gBase = gBase; + s->save_gPerm = gPerm; + + return retVal; +} + + +/*-------------------------------------------------------------*/ +/*--- end decompress.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/UnAlzBzip2.cpp b/UnAlzBzip2.cpp new file mode 100644 index 0000000..0f81958 --- /dev/null +++ b/UnAlzBzip2.cpp @@ -0,0 +1,180 @@ +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// +/// bzip2 관련 file i/o 함수들 - 원래 UnAlzbzlib.c (bzlib.c) 에 있던 함수들은 분할 압축 처리를 위해서 +/// 약간의 수정을 가한 소스들이다.. +/// FILE* handle 관련 부분들이 수정되었다. +/// +/// @author hardkoder@gmail.com +/// @date 2004-10-03 오후 3:09:11 +/// +//////////////////////////////////////////////////////////////////////////////////////////////////// + +//#include "stdafx.h" +#include "zlib/zlib.h" +#include "bzip2/bzlib.h" +#include "bzip2/bzlib_private.h" +#include "UnAlz.h" + + +typedef struct { + CUnAlz* handle; + Char buf[BZ_MAX_UNUSED]; + Int32 bufN; + Bool writing; + bz_stream strm; + Int32 lastErr; + Bool initialisedOk; +} +MybzFile; + +#define BZ_SETERR(eee) \ +{ \ + if (bzerror != NULL) *bzerror = eee; \ + if (bzf != NULL) bzf->lastErr = eee; \ +} + + + +//////////////////////////////////////////////////////////////////////////////////////////////////// +/// BZIP2 파일 처리 함수 +/// @param bzerror +/// @param f +/// @param verbosity +/// @param _small +/// @param unused +/// @param nUnused +/// @return +/// @date 2004-10-03 오전 3:16:45 +//////////////////////////////////////////////////////////////////////////////////////////////////// +CUnAlz::MYBZFILE* CUnAlz::BZ2_bzReadOpen(int* bzerror, CUnAlz* f, int verbosity, int _small,void* unused, int nUnused) +{ + MybzFile* bzf = NULL; + int ret; + + BZ_SETERR(BZ_OK); + + if (f == NULL || + (_small != 0 && _small != 1) || + (verbosity < 0 || verbosity > 4) || + (unused == NULL && nUnused != 0) || + (unused != NULL && (nUnused < 0 || nUnused > BZ_MAX_UNUSED))) + { BZ_SETERR(BZ_PARAM_ERROR); return NULL; }; + +// if (f->FEof()) +// { BZ_SETERR(BZ_IO_ERROR); return NULL; }; + + bzf = (MybzFile*)malloc ( sizeof(MybzFile) ); + if (bzf == NULL) + { BZ_SETERR(BZ_MEM_ERROR); return NULL; }; + + BZ_SETERR(BZ_OK); + + bzf->initialisedOk = False; + bzf->handle = f; + bzf->bufN = 0; + bzf->writing = False; + bzf->strm.bzalloc = NULL; + bzf->strm.bzfree = NULL; + bzf->strm.opaque = NULL; + + while (nUnused > 0) { + bzf->buf[bzf->bufN] = *((UChar*)(unused)); bzf->bufN++; + unused = ((void*)( 1 + ((UChar*)(unused)) )); + nUnused--; + } + + ret = BZ2_bzDecompressInit ( &(bzf->strm), verbosity, _small ); + if (ret != BZ_OK) + { BZ_SETERR(ret); free(bzf); return NULL; }; + + bzf->strm.avail_in = bzf->bufN; + bzf->strm.next_in = bzf->buf; + + bzf->initialisedOk = True; + return bzf; +} + + +int CUnAlz::BZ2_bzread(MYBZFILE* b, void* buf, int len ) +{ + int bzerr, nread; + if (((MybzFile*)b)->lastErr == BZ_STREAM_END) return 0; + nread = BZ2_bzRead(&bzerr,b,buf,len); + if (bzerr == BZ_OK || bzerr == BZ_STREAM_END) { + return nread; + } else { + return -1; + } +} + + +int CUnAlz::BZ2_bzRead(int* bzerror, MYBZFILE* b, void* buf, int len) +{ + Int32 n, ret; + MybzFile* bzf = (MybzFile*)b; + + BZ_SETERR(BZ_OK); + + if (bzf == NULL || buf == NULL || len < 0) + { BZ_SETERR(BZ_PARAM_ERROR); return 0; }; + + if (bzf->writing) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return 0; }; + + if (len == 0) + { BZ_SETERR(BZ_OK); return 0; }; + + bzf->strm.avail_out = len; + bzf->strm.next_out = (char*)buf; + + while (True) { + +// if (ferror(bzf->handle)) +// { BZ_SETERR(BZ_IO_ERROR); return 0; }; + + if (bzf->strm.avail_in == 0 && !bzf->handle->FEof()) { + bzf->handle->FRead(bzf->buf, sizeof(UChar)*BZ_MAX_UNUSED, &n); + + if(n==0) + { BZ_SETERR(BZ_IO_ERROR); return 0; }; + bzf->bufN = n; + bzf->strm.avail_in = bzf->bufN; + bzf->strm.next_in = bzf->buf; + } + + ret = BZ2_bzDecompress ( &(bzf->strm) ); + + if (ret != BZ_OK && ret != BZ_STREAM_END) + { BZ_SETERR(ret); return 0; }; + + if (ret == BZ_OK && bzf->handle->FEof() && + bzf->strm.avail_in == 0 && bzf->strm.avail_out > 0) + { BZ_SETERR(BZ_UNEXPECTED_EOF); return 0; }; + + if (ret == BZ_STREAM_END) + { BZ_SETERR(BZ_STREAM_END); + return len - bzf->strm.avail_out; }; + if (bzf->strm.avail_out == 0) + { BZ_SETERR(BZ_OK); return len; }; + + } + + return 0; /*not reached*/ +} + +void CUnAlz::BZ2_bzReadClose( int *bzerror, MYBZFILE *b ) +{ + MybzFile* bzf = (MybzFile*)b; + + BZ_SETERR(BZ_OK); + if (bzf == NULL) + { BZ_SETERR(BZ_OK); return; }; + + if (bzf->writing) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return; }; + + if (bzf->initialisedOk) + (void)BZ2_bzDecompressEnd ( &(bzf->strm) ); + free ( bzf ); +} + diff --git a/UnAlzbzlib.c b/UnAlzbzlib.c new file mode 100644 index 0000000..82abd35 --- /dev/null +++ b/UnAlzbzlib.c @@ -0,0 +1,1601 @@ +// ALZ 압축 해제를 위해서 수정된 bzip2 소스 +// [ALZ] 라고 표시된 부분이 수정된 부분이다. + + +/*-------------------------------------------------------------*/ +/*--- Library top-level functions. ---*/ +/*--- bzlib.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + +/*-- + CHANGES + ~~~~~~~ + 0.9.0 -- original version. + + 0.9.0a/b -- no changes in this file. + + 0.9.0c + * made zero-length BZ_FLUSH work correctly in bzCompress(). + * fixed bzWrite/bzRead to ignore zero-length requests. + * fixed bzread to correctly handle read requests after EOF. + * wrong parameter order in call to bzDecompressInit in + bzBuffToBuffDecompress. Fixed. +--*/ + +#include "bzip2/bzlib_private.h" + + +/*---------------------------------------------------*/ +/*--- Compression stuff ---*/ +/*---------------------------------------------------*/ + + +/*---------------------------------------------------*/ +#ifndef BZ_NO_STDIO +void BZ2_bz__AssertH__fail ( int errcode ) +{ + fprintf(stderr, + "\n\nbzip2/libbzip2: internal error number %d.\n" + "This is a bug in bzip2/libbzip2, %s.\n" + "Please report it to me at: jseward@acm.org. If this happened\n" + "when you were using some program which uses libbzip2 as a\n" + "component, you should also report this bug to the author(s)\n" + "of that program. Please make an effort to report this bug;\n" + "timely and accurate bug reports eventually lead to higher\n" + "quality software. Thanks. Julian Seward, 30 December 2001.\n\n", + errcode, + BZ2_bzlibVersion() + ); + + if (errcode == 1007) { + fprintf(stderr, + "\n*** A special note about internal error number 1007 ***\n" + "\n" + "Experience suggests that a common cause of i.e. 1007\n" + "is unreliable memory or other hardware. The 1007 assertion\n" + "just happens to cross-check the results of huge numbers of\n" + "memory reads/writes, and so acts (unintendedly) as a stress\n" + "test of your memory system.\n" + "\n" + "I suggest the following: try compressing the file again,\n" + "possibly monitoring progress in detail with the -vv flag.\n" + "\n" + "* If the error cannot be reproduced, and/or happens at different\n" + " points in compression, you may have a flaky memory system.\n" + " Try a memory-test program. I have used Memtest86\n" + " (www.memtest86.com). At the time of writing it is free (GPLd).\n" + " Memtest86 tests memory much more thorougly than your BIOSs\n" + " power-on test, and may find failures that the BIOS doesn't.\n" + "\n" + "* If the error can be repeatably reproduced, this is a bug in\n" + " bzip2, and I would very much like to hear about it. Please\n" + " let me know, and, ideally, save a copy of the file causing the\n" + " problem -- without which I will be unable to investigate it.\n" + "\n" + ); + } + + exit(3); +} +#endif + + +/*---------------------------------------------------*/ +static +int bz_config_ok ( void ) +{ + if (sizeof(int) != 4) return 0; + if (sizeof(short) != 2) return 0; + if (sizeof(char) != 1) return 0; + return 1; +} + + +/*---------------------------------------------------*/ +static +void* default_bzalloc ( void* opaque, Int32 items, Int32 size ) +{ + void* v = malloc ( items * size ); + return v; +} + +static +void default_bzfree ( void* opaque, void* addr ) +{ + if (addr != NULL) free ( addr ); +} + + +/*---------------------------------------------------*/ +static +void prepare_new_block ( EState* s ) +{ + Int32 i; + s->nblock = 0; + s->numZ = 0; + s->state_out_pos = 0; + BZ_INITIALISE_CRC ( s->blockCRC ); + for (i = 0; i < 256; i++) s->inUse[i] = False; + s->blockNo++; +} + + +/*---------------------------------------------------*/ +static +void init_RL ( EState* s ) +{ + s->state_in_ch = 256; + s->state_in_len = 0; +} + + +static +Bool isempty_RL ( EState* s ) +{ + if (s->state_in_ch < 256 && s->state_in_len > 0) + return False; else + return True; +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzCompressInit) + ( bz_stream* strm, + int blockSize100k, + int verbosity, + int workFactor ) +{ + Int32 n; + EState* s; + + if (!bz_config_ok()) return BZ_CONFIG_ERROR; + + if (strm == NULL || + blockSize100k < 1 || blockSize100k > 9 || + workFactor < 0 || workFactor > 250) + return BZ_PARAM_ERROR; + + if (workFactor == 0) workFactor = 30; + if (strm->bzalloc == NULL) strm->bzalloc = default_bzalloc; + if (strm->bzfree == NULL) strm->bzfree = default_bzfree; + + s = BZALLOC( sizeof(EState) ); + if (s == NULL) return BZ_MEM_ERROR; + s->strm = strm; + + s->arr1 = NULL; + s->arr2 = NULL; + s->ftab = NULL; + + n = 100000 * blockSize100k; + s->arr1 = BZALLOC( n * sizeof(UInt32) ); + s->arr2 = BZALLOC( (n+BZ_N_OVERSHOOT) * sizeof(UInt32) ); + s->ftab = BZALLOC( 65537 * sizeof(UInt32) ); + + if (s->arr1 == NULL || s->arr2 == NULL || s->ftab == NULL) { + if (s->arr1 != NULL) BZFREE(s->arr1); + if (s->arr2 != NULL) BZFREE(s->arr2); + if (s->ftab != NULL) BZFREE(s->ftab); + if (s != NULL) BZFREE(s); + return BZ_MEM_ERROR; + } + + s->blockNo = 0; + s->state = BZ_S_INPUT; + s->mode = BZ_M_RUNNING; + s->combinedCRC = 0; + s->blockSize100k = blockSize100k; + s->nblockMAX = 100000 * blockSize100k - 19; + s->verbosity = verbosity; + s->workFactor = workFactor; + + s->block = (UChar*)s->arr2; + s->mtfv = (UInt16*)s->arr1; + s->zbits = NULL; + s->ptr = (UInt32*)s->arr1; + + strm->state = s; + strm->total_in_lo32 = 0; + strm->total_in_hi32 = 0; + strm->total_out_lo32 = 0; + strm->total_out_hi32 = 0; + init_RL ( s ); + prepare_new_block ( s ); + return BZ_OK; +} + + +/*---------------------------------------------------*/ +static +void add_pair_to_block ( EState* s ) +{ + Int32 i; + UChar ch = (UChar)(s->state_in_ch); + for (i = 0; i < s->state_in_len; i++) { + BZ_UPDATE_CRC( s->blockCRC, ch ); + } + s->inUse[s->state_in_ch] = True; + switch (s->state_in_len) { + case 1: + s->block[s->nblock] = (UChar)ch; s->nblock++; + break; + case 2: + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = (UChar)ch; s->nblock++; + break; + case 3: + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = (UChar)ch; s->nblock++; + break; + default: + s->inUse[s->state_in_len-4] = True; + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = (UChar)ch; s->nblock++; + s->block[s->nblock] = ((UChar)(s->state_in_len-4)); + s->nblock++; + break; + } +} + + +/*---------------------------------------------------*/ +static +void flush_RL ( EState* s ) +{ + if (s->state_in_ch < 256) add_pair_to_block ( s ); + init_RL ( s ); +} + + +/*---------------------------------------------------*/ +#define ADD_CHAR_TO_BLOCK(zs,zchh0) \ +{ \ + UInt32 zchh = (UInt32)(zchh0); \ + /*-- fast track the common case --*/ \ + if (zchh != zs->state_in_ch && \ + zs->state_in_len == 1) { \ + UChar ch = (UChar)(zs->state_in_ch); \ + BZ_UPDATE_CRC( zs->blockCRC, ch ); \ + zs->inUse[zs->state_in_ch] = True; \ + zs->block[zs->nblock] = (UChar)ch; \ + zs->nblock++; \ + zs->state_in_ch = zchh; \ + } \ + else \ + /*-- general, uncommon cases --*/ \ + if (zchh != zs->state_in_ch || \ + zs->state_in_len == 255) { \ + if (zs->state_in_ch < 256) \ + add_pair_to_block ( zs ); \ + zs->state_in_ch = zchh; \ + zs->state_in_len = 1; \ + } else { \ + zs->state_in_len++; \ + } \ +} + + +/*---------------------------------------------------*/ +static +Bool copy_input_until_stop ( EState* s ) +{ + Bool progress_in = False; + + if (s->mode == BZ_M_RUNNING) { + + /*-- fast track the common case --*/ + while (True) { + /*-- block full? --*/ + if (s->nblock >= s->nblockMAX) break; + /*-- no input? --*/ + if (s->strm->avail_in == 0) break; + progress_in = True; + ADD_CHAR_TO_BLOCK ( s, (UInt32)(*((UChar*)(s->strm->next_in))) ); + s->strm->next_in++; + s->strm->avail_in--; + s->strm->total_in_lo32++; + if (s->strm->total_in_lo32 == 0) s->strm->total_in_hi32++; + } + + } else { + + /*-- general, uncommon case --*/ + while (True) { + /*-- block full? --*/ + if (s->nblock >= s->nblockMAX) break; + /*-- no input? --*/ + if (s->strm->avail_in == 0) break; + /*-- flush/finish end? --*/ + if (s->avail_in_expect == 0) break; + progress_in = True; + ADD_CHAR_TO_BLOCK ( s, (UInt32)(*((UChar*)(s->strm->next_in))) ); + s->strm->next_in++; + s->strm->avail_in--; + s->strm->total_in_lo32++; + if (s->strm->total_in_lo32 == 0) s->strm->total_in_hi32++; + s->avail_in_expect--; + } + } + return progress_in; +} + + +/*---------------------------------------------------*/ +static +Bool copy_output_until_stop ( EState* s ) +{ + Bool progress_out = False; + + while (True) { + + /*-- no output space? --*/ + if (s->strm->avail_out == 0) break; + + /*-- block done? --*/ + if (s->state_out_pos >= s->numZ) break; + + progress_out = True; + *(s->strm->next_out) = s->zbits[s->state_out_pos]; + s->state_out_pos++; + s->strm->avail_out--; + s->strm->next_out++; + s->strm->total_out_lo32++; + if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++; + } + + return progress_out; +} + + +/*---------------------------------------------------*/ +static +Bool handle_compress ( bz_stream* strm ) +{ + Bool progress_in = False; + Bool progress_out = False; + EState* s = strm->state; + + while (True) { + + if (s->state == BZ_S_OUTPUT) { + progress_out |= copy_output_until_stop ( s ); + if (s->state_out_pos < s->numZ) break; + if (s->mode == BZ_M_FINISHING && + s->avail_in_expect == 0 && + isempty_RL(s)) break; + prepare_new_block ( s ); + s->state = BZ_S_INPUT; + if (s->mode == BZ_M_FLUSHING && + s->avail_in_expect == 0 && + isempty_RL(s)) break; + } + + if (s->state == BZ_S_INPUT) { + progress_in |= copy_input_until_stop ( s ); + if (s->mode != BZ_M_RUNNING && s->avail_in_expect == 0) { + flush_RL ( s ); + BZ2_compressBlock ( s, (Bool)(s->mode == BZ_M_FINISHING) ); + s->state = BZ_S_OUTPUT; + } + else + if (s->nblock >= s->nblockMAX) { + BZ2_compressBlock ( s, False ); + s->state = BZ_S_OUTPUT; + } + else + if (s->strm->avail_in == 0) { + break; + } + } + + } + + return progress_in || progress_out; +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzCompress) ( bz_stream *strm, int action ) +{ + Bool progress; + EState* s; + if (strm == NULL) return BZ_PARAM_ERROR; + s = strm->state; + if (s == NULL) return BZ_PARAM_ERROR; + if (s->strm != strm) return BZ_PARAM_ERROR; + + preswitch: + switch (s->mode) { + + case BZ_M_IDLE: + return BZ_SEQUENCE_ERROR; + + case BZ_M_RUNNING: + if (action == BZ_RUN) { + progress = handle_compress ( strm ); + return progress ? BZ_RUN_OK : BZ_PARAM_ERROR; + } + else + if (action == BZ_FLUSH) { + s->avail_in_expect = strm->avail_in; + s->mode = BZ_M_FLUSHING; + goto preswitch; + } + else + if (action == BZ_FINISH) { + s->avail_in_expect = strm->avail_in; + s->mode = BZ_M_FINISHING; + goto preswitch; + } + else + return BZ_PARAM_ERROR; + + case BZ_M_FLUSHING: + if (action != BZ_FLUSH) return BZ_SEQUENCE_ERROR; + if (s->avail_in_expect != s->strm->avail_in) + return BZ_SEQUENCE_ERROR; + progress = handle_compress ( strm ); + if (s->avail_in_expect > 0 || !isempty_RL(s) || + s->state_out_pos < s->numZ) return BZ_FLUSH_OK; + s->mode = BZ_M_RUNNING; + return BZ_RUN_OK; + + case BZ_M_FINISHING: + if (action != BZ_FINISH) return BZ_SEQUENCE_ERROR; + if (s->avail_in_expect != s->strm->avail_in) + return BZ_SEQUENCE_ERROR; + progress = handle_compress ( strm ); + if (!progress) return BZ_SEQUENCE_ERROR; + if (s->avail_in_expect > 0 || !isempty_RL(s) || + s->state_out_pos < s->numZ) return BZ_FINISH_OK; + s->mode = BZ_M_IDLE; + return BZ_STREAM_END; + } + return BZ_OK; /*--not reached--*/ +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzCompressEnd) ( bz_stream *strm ) +{ + EState* s; + if (strm == NULL) return BZ_PARAM_ERROR; + s = strm->state; + if (s == NULL) return BZ_PARAM_ERROR; + if (s->strm != strm) return BZ_PARAM_ERROR; + + if (s->arr1 != NULL) BZFREE(s->arr1); + if (s->arr2 != NULL) BZFREE(s->arr2); + if (s->ftab != NULL) BZFREE(s->ftab); + BZFREE(strm->state); + + strm->state = NULL; + + return BZ_OK; +} + + +/*---------------------------------------------------*/ +/*--- Decompression stuff ---*/ +/*---------------------------------------------------*/ + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzDecompressInit) + ( bz_stream* strm, + int verbosity, + int small ) +{ + DState* s; + + if (!bz_config_ok()) return BZ_CONFIG_ERROR; + + if (strm == NULL) return BZ_PARAM_ERROR; + if (small != 0 && small != 1) return BZ_PARAM_ERROR; + if (verbosity < 0 || verbosity > 4) return BZ_PARAM_ERROR; + + if (strm->bzalloc == NULL) strm->bzalloc = default_bzalloc; + if (strm->bzfree == NULL) strm->bzfree = default_bzfree; + + s = BZALLOC( sizeof(DState) ); + if (s == NULL) return BZ_MEM_ERROR; + s->strm = strm; + strm->state = s; + s->state = BZ_X_MAGIC_1; + s->bsLive = 0; + s->bsBuff = 0; + s->calculatedCombinedCRC = 0; + strm->total_in_lo32 = 0; + strm->total_in_hi32 = 0; + strm->total_out_lo32 = 0; + strm->total_out_hi32 = 0; + s->smallDecompress = (Bool)small; + s->ll4 = NULL; + s->ll16 = NULL; + s->tt = NULL; + s->currBlockNo = 0; + s->verbosity = verbosity; + + return BZ_OK; +} + + +/*---------------------------------------------------*/ +static +void unRLE_obuf_to_output_FAST ( DState* s ) +{ + UChar k1; + + if (s->blockRandomised) { + + while (True) { + /* try to finish existing run */ + while (True) { + if (s->strm->avail_out == 0) return; + if (s->state_out_len == 0) break; + *( (UChar*)(s->strm->next_out) ) = s->state_out_ch; + BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch ); + s->state_out_len--; + s->strm->next_out++; + s->strm->avail_out--; + s->strm->total_out_lo32++; + if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++; + } + + /* can a new run be started? */ + if (s->nblock_used == s->save_nblock+1) return; + + + s->state_out_len = 1; + s->state_out_ch = s->k0; + BZ_GET_FAST(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + s->state_out_len = 2; + BZ_GET_FAST(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + s->state_out_len = 3; + BZ_GET_FAST(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + BZ_GET_FAST(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + s->state_out_len = ((Int32)k1) + 4; + BZ_GET_FAST(s->k0); BZ_RAND_UPD_MASK; + s->k0 ^= BZ_RAND_MASK; s->nblock_used++; + } + + } else { + + /* restore */ + UInt32 c_calculatedBlockCRC = s->calculatedBlockCRC; + UChar c_state_out_ch = s->state_out_ch; + Int32 c_state_out_len = s->state_out_len; + Int32 c_nblock_used = s->nblock_used; + Int32 c_k0 = s->k0; + UInt32* c_tt = s->tt; + UInt32 c_tPos = s->tPos; + char* cs_next_out = s->strm->next_out; + unsigned int cs_avail_out = s->strm->avail_out; + /* end restore */ + + UInt32 avail_out_INIT = cs_avail_out; + Int32 s_save_nblockPP = s->save_nblock+1; + unsigned int total_out_lo32_old; + + while (True) { + + /* try to finish existing run */ + if (c_state_out_len > 0) { + while (True) { + if (cs_avail_out == 0) goto return_notr; + if (c_state_out_len == 1) break; + *( (UChar*)(cs_next_out) ) = c_state_out_ch; + BZ_UPDATE_CRC ( c_calculatedBlockCRC, c_state_out_ch ); + c_state_out_len--; + cs_next_out++; + cs_avail_out--; + } + s_state_out_len_eq_one: + { + if (cs_avail_out == 0) { + c_state_out_len = 1; goto return_notr; + }; + *( (UChar*)(cs_next_out) ) = c_state_out_ch; + BZ_UPDATE_CRC ( c_calculatedBlockCRC, c_state_out_ch ); + cs_next_out++; + cs_avail_out--; + } + } + /* can a new run be started? */ + if (c_nblock_used == s_save_nblockPP) { + c_state_out_len = 0; goto return_notr; + }; + c_state_out_ch = c_k0; + BZ_GET_FAST_C(k1); c_nblock_used++; + if (k1 != c_k0) { + c_k0 = k1; goto s_state_out_len_eq_one; + }; + if (c_nblock_used == s_save_nblockPP) + goto s_state_out_len_eq_one; + + c_state_out_len = 2; + BZ_GET_FAST_C(k1); c_nblock_used++; + if (c_nblock_used == s_save_nblockPP) continue; + if (k1 != c_k0) { c_k0 = k1; continue; }; + + c_state_out_len = 3; + BZ_GET_FAST_C(k1); c_nblock_used++; + if (c_nblock_used == s_save_nblockPP) continue; + if (k1 != c_k0) { c_k0 = k1; continue; }; + + BZ_GET_FAST_C(k1); c_nblock_used++; + c_state_out_len = ((Int32)k1) + 4; + BZ_GET_FAST_C(c_k0); c_nblock_used++; + } + + return_notr: + total_out_lo32_old = s->strm->total_out_lo32; + s->strm->total_out_lo32 += (avail_out_INIT - cs_avail_out); + if (s->strm->total_out_lo32 < total_out_lo32_old) + s->strm->total_out_hi32++; + + /* save */ + s->calculatedBlockCRC = c_calculatedBlockCRC; + s->state_out_ch = c_state_out_ch; + s->state_out_len = c_state_out_len; + s->nblock_used = c_nblock_used; + s->k0 = c_k0; + s->tt = c_tt; + s->tPos = c_tPos; + s->strm->next_out = cs_next_out; + s->strm->avail_out = cs_avail_out; + /* end save */ + } +} + + + +/*---------------------------------------------------*/ +__inline__ Int32 BZ2_indexIntoF ( Int32 indx, Int32 *cftab ) +{ + Int32 nb, na, mid; + nb = 0; + na = 256; + do { + mid = (nb + na) >> 1; + if (indx >= cftab[mid]) nb = mid; else na = mid; + } + while (na - nb != 1); + return nb; +} + + +/*---------------------------------------------------*/ +static +void unRLE_obuf_to_output_SMALL ( DState* s ) +{ + UChar k1; + + if (s->blockRandomised) { + + while (True) { + /* try to finish existing run */ + while (True) { + if (s->strm->avail_out == 0) return; + if (s->state_out_len == 0) break; + *( (UChar*)(s->strm->next_out) ) = s->state_out_ch; + BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch ); + s->state_out_len--; + s->strm->next_out++; + s->strm->avail_out--; + s->strm->total_out_lo32++; + if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++; + } + + /* can a new run be started? */ + if (s->nblock_used == s->save_nblock+1) return; + + + s->state_out_len = 1; + s->state_out_ch = s->k0; + BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + s->state_out_len = 2; + BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + s->state_out_len = 3; + BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + BZ_GET_SMALL(k1); BZ_RAND_UPD_MASK; + k1 ^= BZ_RAND_MASK; s->nblock_used++; + s->state_out_len = ((Int32)k1) + 4; + BZ_GET_SMALL(s->k0); BZ_RAND_UPD_MASK; + s->k0 ^= BZ_RAND_MASK; s->nblock_used++; + } + + } else { + + while (True) { + /* try to finish existing run */ + while (True) { + if (s->strm->avail_out == 0) return; + if (s->state_out_len == 0) break; + *( (UChar*)(s->strm->next_out) ) = s->state_out_ch; + BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch ); + s->state_out_len--; + s->strm->next_out++; + s->strm->avail_out--; + s->strm->total_out_lo32++; + if (s->strm->total_out_lo32 == 0) s->strm->total_out_hi32++; + } + + /* can a new run be started? */ + if (s->nblock_used == s->save_nblock+1) return; + + s->state_out_len = 1; + s->state_out_ch = s->k0; + BZ_GET_SMALL(k1); s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + s->state_out_len = 2; + BZ_GET_SMALL(k1); s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + s->state_out_len = 3; + BZ_GET_SMALL(k1); s->nblock_used++; + if (s->nblock_used == s->save_nblock+1) continue; + if (k1 != s->k0) { s->k0 = k1; continue; }; + + BZ_GET_SMALL(k1); s->nblock_used++; + s->state_out_len = ((Int32)k1) + 4; + BZ_GET_SMALL(s->k0); s->nblock_used++; + } + + } +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzDecompress) ( bz_stream *strm ) +{ + DState* s; + if (strm == NULL) return BZ_PARAM_ERROR; + s = strm->state; + if (s == NULL) return BZ_PARAM_ERROR; + if (s->strm != strm) return BZ_PARAM_ERROR; + + while (True) { + if (s->state == BZ_X_IDLE) + return BZ_SEQUENCE_ERROR; + if (s->state == BZ_X_OUTPUT) { + if (s->smallDecompress) + unRLE_obuf_to_output_SMALL ( s ); else + unRLE_obuf_to_output_FAST ( s ); + if (s->nblock_used == s->save_nblock+1 && s->state_out_len == 0) { + BZ_FINALISE_CRC ( s->calculatedBlockCRC ); + if (s->verbosity >= 3) + VPrintf2 ( " {0x%x, 0x%x}", s->storedBlockCRC, + s->calculatedBlockCRC ); + if (s->verbosity >= 2) VPrintf0 ( "]" ); + +// [ALZ] +// if (s->calculatedBlockCRC != s->storedBlockCRC) +// return BZ_DATA_ERROR; + s->calculatedCombinedCRC + = (s->calculatedCombinedCRC << 1) | + (s->calculatedCombinedCRC >> 31); + s->calculatedCombinedCRC ^= s->calculatedBlockCRC; + s->state = BZ_X_BLKHDR_1; + } else { + return BZ_OK; + } + } + if (s->state >= BZ_X_MAGIC_1) { + Int32 r = BZ2_decompress ( s ); + if (r == BZ_STREAM_END) { + if (s->verbosity >= 3) + VPrintf2 ( "\n combined CRCs: stored = 0x%x, computed = 0x%x", + s->storedCombinedCRC, s->calculatedCombinedCRC ); +// [ALZ] +// if (s->calculatedCombinedCRC != s->storedCombinedCRC) +// return BZ_DATA_ERROR; + return r; + } + if (s->state != BZ_X_OUTPUT) + return r; + } + } + + AssertH ( 0, 6001 ); + + return 0; /*NOTREACHED*/ +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzDecompressEnd) ( bz_stream *strm ) +{ + DState* s; + if (strm == NULL) return BZ_PARAM_ERROR; + s = strm->state; + if (s == NULL) return BZ_PARAM_ERROR; + if (s->strm != strm) return BZ_PARAM_ERROR; + + if (s->tt != NULL) BZFREE(s->tt); + if (s->ll16 != NULL) BZFREE(s->ll16); + if (s->ll4 != NULL) BZFREE(s->ll4); + + BZFREE(strm->state); + strm->state = NULL; + + return BZ_OK; +} + + +#ifndef BZ_NO_STDIO +/*---------------------------------------------------*/ +/*--- File I/O stuff ---*/ +/*---------------------------------------------------*/ + +#define BZ_SETERR(eee) \ +{ \ + if (bzerror != NULL) *bzerror = eee; \ + if (bzf != NULL) bzf->lastErr = eee; \ +} + +typedef + struct { + FILE* handle; + Char buf[BZ_MAX_UNUSED]; + Int32 bufN; + Bool writing; + bz_stream strm; + Int32 lastErr; + Bool initialisedOk; + } + bzFile; + + +/*---------------------------------------------*/ +static Bool myfeof ( FILE* f ) +{ + Int32 c = fgetc ( f ); + if (c == EOF) return True; + ungetc ( c, f ); + return False; +} + + +/*---------------------------------------------------*/ +BZFILE* BZ_API(BZ2_bzWriteOpen) + ( int* bzerror, + FILE* f, + int blockSize100k, + int verbosity, + int workFactor ) +{ + Int32 ret; + bzFile* bzf = NULL; + + BZ_SETERR(BZ_OK); + + if (f == NULL || + (blockSize100k < 1 || blockSize100k > 9) || + (workFactor < 0 || workFactor > 250) || + (verbosity < 0 || verbosity > 4)) + { BZ_SETERR(BZ_PARAM_ERROR); return NULL; }; + + if (ferror(f)) + { BZ_SETERR(BZ_IO_ERROR); return NULL; }; + + bzf = malloc ( sizeof(bzFile) ); + if (bzf == NULL) + { BZ_SETERR(BZ_MEM_ERROR); return NULL; }; + + BZ_SETERR(BZ_OK); + bzf->initialisedOk = False; + bzf->bufN = 0; + bzf->handle = f; + bzf->writing = True; + bzf->strm.bzalloc = NULL; + bzf->strm.bzfree = NULL; + bzf->strm.opaque = NULL; + + if (workFactor == 0) workFactor = 30; + ret = BZ2_bzCompressInit ( &(bzf->strm), blockSize100k, + verbosity, workFactor ); + if (ret != BZ_OK) + { BZ_SETERR(ret); free(bzf); return NULL; }; + + bzf->strm.avail_in = 0; + bzf->initialisedOk = True; + return bzf; +} + + + +/*---------------------------------------------------*/ +void BZ_API(BZ2_bzWrite) + ( int* bzerror, + BZFILE* b, + void* buf, + int len ) +{ + Int32 n, n2, ret; + bzFile* bzf = (bzFile*)b; + + BZ_SETERR(BZ_OK); + if (bzf == NULL || buf == NULL || len < 0) + { BZ_SETERR(BZ_PARAM_ERROR); return; }; + if (!(bzf->writing)) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return; }; + if (ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return; }; + + if (len == 0) + { BZ_SETERR(BZ_OK); return; }; + + bzf->strm.avail_in = len; + bzf->strm.next_in = buf; + + while (True) { + bzf->strm.avail_out = BZ_MAX_UNUSED; + bzf->strm.next_out = bzf->buf; + ret = BZ2_bzCompress ( &(bzf->strm), BZ_RUN ); + if (ret != BZ_RUN_OK) + { BZ_SETERR(ret); return; }; + + if (bzf->strm.avail_out < BZ_MAX_UNUSED) { + n = BZ_MAX_UNUSED - bzf->strm.avail_out; + n2 = fwrite ( (void*)(bzf->buf), sizeof(UChar), + n, bzf->handle ); + if (n != n2 || ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return; }; + } + + if (bzf->strm.avail_in == 0) + { BZ_SETERR(BZ_OK); return; }; + } +} + + +/*---------------------------------------------------*/ +void BZ_API(BZ2_bzWriteClose) + ( int* bzerror, + BZFILE* b, + int abandon, + unsigned int* nbytes_in, + unsigned int* nbytes_out ) +{ + BZ2_bzWriteClose64 ( bzerror, b, abandon, + nbytes_in, NULL, nbytes_out, NULL ); +} + + +void BZ_API(BZ2_bzWriteClose64) + ( int* bzerror, + BZFILE* b, + int abandon, + unsigned int* nbytes_in_lo32, + unsigned int* nbytes_in_hi32, + unsigned int* nbytes_out_lo32, + unsigned int* nbytes_out_hi32 ) +{ + Int32 n, n2, ret; + bzFile* bzf = (bzFile*)b; + + if (bzf == NULL) + { BZ_SETERR(BZ_OK); return; }; + if (!(bzf->writing)) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return; }; + if (ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return; }; + + if (nbytes_in_lo32 != NULL) *nbytes_in_lo32 = 0; + if (nbytes_in_hi32 != NULL) *nbytes_in_hi32 = 0; + if (nbytes_out_lo32 != NULL) *nbytes_out_lo32 = 0; + if (nbytes_out_hi32 != NULL) *nbytes_out_hi32 = 0; + + if ((!abandon) && bzf->lastErr == BZ_OK) { + while (True) { + bzf->strm.avail_out = BZ_MAX_UNUSED; + bzf->strm.next_out = bzf->buf; + ret = BZ2_bzCompress ( &(bzf->strm), BZ_FINISH ); + if (ret != BZ_FINISH_OK && ret != BZ_STREAM_END) + { BZ_SETERR(ret); return; }; + + if (bzf->strm.avail_out < BZ_MAX_UNUSED) { + n = BZ_MAX_UNUSED - bzf->strm.avail_out; + n2 = fwrite ( (void*)(bzf->buf), sizeof(UChar), + n, bzf->handle ); + if (n != n2 || ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return; }; + } + + if (ret == BZ_STREAM_END) break; + } + } + + if ( !abandon && !ferror ( bzf->handle ) ) { + fflush ( bzf->handle ); + if (ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return; }; + } + + if (nbytes_in_lo32 != NULL) + *nbytes_in_lo32 = bzf->strm.total_in_lo32; + if (nbytes_in_hi32 != NULL) + *nbytes_in_hi32 = bzf->strm.total_in_hi32; + if (nbytes_out_lo32 != NULL) + *nbytes_out_lo32 = bzf->strm.total_out_lo32; + if (nbytes_out_hi32 != NULL) + *nbytes_out_hi32 = bzf->strm.total_out_hi32; + + BZ_SETERR(BZ_OK); + BZ2_bzCompressEnd ( &(bzf->strm) ); + free ( bzf ); +} + + +/*---------------------------------------------------*/ +BZFILE* BZ_API(BZ2_bzReadOpen) + ( int* bzerror, + FILE* f, + int verbosity, + int small, + void* unused, + int nUnused ) +{ + bzFile* bzf = NULL; + int ret; + + BZ_SETERR(BZ_OK); + + if (f == NULL || + (small != 0 && small != 1) || + (verbosity < 0 || verbosity > 4) || + (unused == NULL && nUnused != 0) || + (unused != NULL && (nUnused < 0 || nUnused > BZ_MAX_UNUSED))) + { BZ_SETERR(BZ_PARAM_ERROR); return NULL; }; + + if (ferror(f)) + { BZ_SETERR(BZ_IO_ERROR); return NULL; }; + + bzf = malloc ( sizeof(bzFile) ); + if (bzf == NULL) + { BZ_SETERR(BZ_MEM_ERROR); return NULL; }; + + BZ_SETERR(BZ_OK); + + bzf->initialisedOk = False; + bzf->handle = f; + bzf->bufN = 0; + bzf->writing = False; + bzf->strm.bzalloc = NULL; + bzf->strm.bzfree = NULL; + bzf->strm.opaque = NULL; + + while (nUnused > 0) { + bzf->buf[bzf->bufN] = *((UChar*)(unused)); bzf->bufN++; + unused = ((void*)( 1 + ((UChar*)(unused)) )); + nUnused--; + } + + ret = BZ2_bzDecompressInit ( &(bzf->strm), verbosity, small ); + if (ret != BZ_OK) + { BZ_SETERR(ret); free(bzf); return NULL; }; + + bzf->strm.avail_in = bzf->bufN; + bzf->strm.next_in = bzf->buf; + + bzf->initialisedOk = True; + return bzf; +} + + +/*---------------------------------------------------*/ +void BZ_API(BZ2_bzReadClose) ( int *bzerror, BZFILE *b ) +{ + bzFile* bzf = (bzFile*)b; + + BZ_SETERR(BZ_OK); + if (bzf == NULL) + { BZ_SETERR(BZ_OK); return; }; + + if (bzf->writing) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return; }; + + if (bzf->initialisedOk) + (void)BZ2_bzDecompressEnd ( &(bzf->strm) ); + free ( bzf ); +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzRead) + ( int* bzerror, + BZFILE* b, + void* buf, + int len ) +{ + Int32 n, ret; + bzFile* bzf = (bzFile*)b; + + BZ_SETERR(BZ_OK); + + if (bzf == NULL || buf == NULL || len < 0) + { BZ_SETERR(BZ_PARAM_ERROR); return 0; }; + + if (bzf->writing) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return 0; }; + + if (len == 0) + { BZ_SETERR(BZ_OK); return 0; }; + + bzf->strm.avail_out = len; + bzf->strm.next_out = buf; + + while (True) { + + if (ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return 0; }; + + if (bzf->strm.avail_in == 0 && !myfeof(bzf->handle)) { + n = fread ( bzf->buf, sizeof(UChar), + BZ_MAX_UNUSED, bzf->handle ); + if (ferror(bzf->handle)) + { BZ_SETERR(BZ_IO_ERROR); return 0; }; + bzf->bufN = n; + bzf->strm.avail_in = bzf->bufN; + bzf->strm.next_in = bzf->buf; + } + + ret = BZ2_bzDecompress ( &(bzf->strm) ); + + if (ret != BZ_OK && ret != BZ_STREAM_END) + { BZ_SETERR(ret); return 0; }; + + if (ret == BZ_OK && myfeof(bzf->handle) && + bzf->strm.avail_in == 0 && bzf->strm.avail_out > 0) + { BZ_SETERR(BZ_UNEXPECTED_EOF); return 0; }; + + if (ret == BZ_STREAM_END) + { BZ_SETERR(BZ_STREAM_END); + return len - bzf->strm.avail_out; }; + if (bzf->strm.avail_out == 0) + { BZ_SETERR(BZ_OK); return len; }; + + } + + return 0; /*not reached*/ +} + + +/*---------------------------------------------------*/ +void BZ_API(BZ2_bzReadGetUnused) + ( int* bzerror, + BZFILE* b, + void** unused, + int* nUnused ) +{ + bzFile* bzf = (bzFile*)b; + if (bzf == NULL) + { BZ_SETERR(BZ_PARAM_ERROR); return; }; + if (bzf->lastErr != BZ_STREAM_END) + { BZ_SETERR(BZ_SEQUENCE_ERROR); return; }; + if (unused == NULL || nUnused == NULL) + { BZ_SETERR(BZ_PARAM_ERROR); return; }; + + BZ_SETERR(BZ_OK); + *nUnused = bzf->strm.avail_in; + *unused = bzf->strm.next_in; +} +#endif + + +/*---------------------------------------------------*/ +/*--- Misc convenience stuff ---*/ +/*---------------------------------------------------*/ + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzBuffToBuffCompress) + ( char* dest, + unsigned int* destLen, + char* source, + unsigned int sourceLen, + int blockSize100k, + int verbosity, + int workFactor ) +{ + bz_stream strm; + int ret; + + if (dest == NULL || destLen == NULL || + source == NULL || + blockSize100k < 1 || blockSize100k > 9 || + verbosity < 0 || verbosity > 4 || + workFactor < 0 || workFactor > 250) + return BZ_PARAM_ERROR; + + if (workFactor == 0) workFactor = 30; + strm.bzalloc = NULL; + strm.bzfree = NULL; + strm.opaque = NULL; + ret = BZ2_bzCompressInit ( &strm, blockSize100k, + verbosity, workFactor ); + if (ret != BZ_OK) return ret; + + strm.next_in = source; + strm.next_out = dest; + strm.avail_in = sourceLen; + strm.avail_out = *destLen; + + ret = BZ2_bzCompress ( &strm, BZ_FINISH ); + if (ret == BZ_FINISH_OK) goto output_overflow; + if (ret != BZ_STREAM_END) goto errhandler; + + /* normal termination */ + *destLen -= strm.avail_out; + BZ2_bzCompressEnd ( &strm ); + return BZ_OK; + + output_overflow: + BZ2_bzCompressEnd ( &strm ); + return BZ_OUTBUFF_FULL; + + errhandler: + BZ2_bzCompressEnd ( &strm ); + return ret; +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzBuffToBuffDecompress) + ( char* dest, + unsigned int* destLen, + char* source, + unsigned int sourceLen, + int small, + int verbosity ) +{ + bz_stream strm; + int ret; + + if (dest == NULL || destLen == NULL || + source == NULL || + (small != 0 && small != 1) || + verbosity < 0 || verbosity > 4) + return BZ_PARAM_ERROR; + + strm.bzalloc = NULL; + strm.bzfree = NULL; + strm.opaque = NULL; + ret = BZ2_bzDecompressInit ( &strm, verbosity, small ); + if (ret != BZ_OK) return ret; + + strm.next_in = source; + strm.next_out = dest; + strm.avail_in = sourceLen; + strm.avail_out = *destLen; + + ret = BZ2_bzDecompress ( &strm ); + if (ret == BZ_OK) goto output_overflow_or_eof; + if (ret != BZ_STREAM_END) goto errhandler; + + /* normal termination */ + *destLen -= strm.avail_out; + BZ2_bzDecompressEnd ( &strm ); + return BZ_OK; + + output_overflow_or_eof: + if (strm.avail_out > 0) { + BZ2_bzDecompressEnd ( &strm ); + return BZ_UNEXPECTED_EOF; + } else { + BZ2_bzDecompressEnd ( &strm ); + return BZ_OUTBUFF_FULL; + }; + + errhandler: + BZ2_bzDecompressEnd ( &strm ); + return ret; +} + + +/*---------------------------------------------------*/ +/*-- + Code contributed by Yoshioka Tsuneo + (QWF00133@niftyserve.or.jp/tsuneo-y@is.aist-nara.ac.jp), + to support better zlib compatibility. + This code is not _officially_ part of libbzip2 (yet); + I haven't tested it, documented it, or considered the + threading-safeness of it. + If this code breaks, please contact both Yoshioka and me. +--*/ +/*---------------------------------------------------*/ + +/*---------------------------------------------------*/ +/*-- + return version like "0.9.0c". +--*/ +const char * BZ_API(BZ2_bzlibVersion)(void) +{ + return BZ_VERSION; +} + + +#ifndef BZ_NO_STDIO +/*---------------------------------------------------*/ + +#if defined(_WIN32) || defined(OS2) || defined(MSDOS) +# include +# include +# define SET_BINARY_MODE(file) setmode(fileno(file),O_BINARY) +#else +# define SET_BINARY_MODE(file) +#endif +static +BZFILE * bzopen_or_bzdopen + ( const char *path, /* no use when bzdopen */ + int fd, /* no use when bzdopen */ + const char *mode, + int open_mode) /* bzopen: 0, bzdopen:1 */ +{ + int bzerr; + char unused[BZ_MAX_UNUSED]; + int blockSize100k = 9; + int writing = 0; + char mode2[10] = ""; + FILE *fp = NULL; + BZFILE *bzfp = NULL; + int verbosity = 0; + int workFactor = 30; + int smallMode = 0; + int nUnused = 0; + + if (mode == NULL) return NULL; + while (*mode) { + switch (*mode) { + case 'r': + writing = 0; break; + case 'w': + writing = 1; break; + case 's': + smallMode = 1; break; + default: + if (isdigit((int)(*mode))) { + blockSize100k = *mode-BZ_HDR_0; + } + } + mode++; + } + strcat(mode2, writing ? "w" : "r" ); + strcat(mode2,"b"); /* binary mode */ + + if (open_mode==0) { + if (path==NULL || strcmp(path,"")==0) { + fp = (writing ? stdout : stdin); + SET_BINARY_MODE(fp); + } else { + fp = fopen(path,mode2); + } + } else { +#ifdef BZ_STRICT_ANSI + fp = NULL; +#else + fp = fdopen(fd,mode2); +#endif + } + if (fp == NULL) return NULL; + + if (writing) { + /* Guard against total chaos and anarchy -- JRS */ + if (blockSize100k < 1) blockSize100k = 1; + if (blockSize100k > 9) blockSize100k = 9; + bzfp = BZ2_bzWriteOpen(&bzerr,fp,blockSize100k, + verbosity,workFactor); + } else { + bzfp = BZ2_bzReadOpen(&bzerr,fp,verbosity,smallMode, + unused,nUnused); + } + if (bzfp == NULL) { + if (fp != stdin && fp != stdout) fclose(fp); + return NULL; + } + return bzfp; +} + + +/*---------------------------------------------------*/ +/*-- + open file for read or write. + ex) bzopen("file","w9") + case path="" or NULL => use stdin or stdout. +--*/ +BZFILE * BZ_API(BZ2_bzopen) + ( const char *path, + const char *mode ) +{ + return bzopen_or_bzdopen(path,-1,mode,/*bzopen*/0); +} + + +/*---------------------------------------------------*/ +BZFILE * BZ_API(BZ2_bzdopen) + ( int fd, + const char *mode ) +{ + return bzopen_or_bzdopen(NULL,fd,mode,/*bzdopen*/1); +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzread) (BZFILE* b, void* buf, int len ) +{ + int bzerr, nread; + if (((bzFile*)b)->lastErr == BZ_STREAM_END) return 0; + nread = BZ2_bzRead(&bzerr,b,buf,len); + if (bzerr == BZ_OK || bzerr == BZ_STREAM_END) { + return nread; + } else { + return -1; + } +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzwrite) (BZFILE* b, void* buf, int len ) +{ + int bzerr; + + BZ2_bzWrite(&bzerr,b,buf,len); + if(bzerr == BZ_OK){ + return len; + }else{ + return -1; + } +} + + +/*---------------------------------------------------*/ +int BZ_API(BZ2_bzflush) (BZFILE *b) +{ + /* do nothing now... */ + return 0; +} + + +/*---------------------------------------------------*/ +void BZ_API(BZ2_bzclose) (BZFILE* b) +{ + int bzerr; + FILE *fp = ((bzFile *)b)->handle; + + if (b==NULL) {return;} + if(((bzFile*)b)->writing){ + BZ2_bzWriteClose(&bzerr,b,0,NULL,NULL); + if(bzerr != BZ_OK){ + BZ2_bzWriteClose(NULL,b,1,NULL,NULL); + } + }else{ + BZ2_bzReadClose(&bzerr,b); + } + if(fp!=stdin && fp!=stdout){ + fclose(fp); + } +} + + +/*---------------------------------------------------*/ +/*-- + return last error code +--*/ +static char *bzerrorstrings[] = { + "OK" + ,"SEQUENCE_ERROR" + ,"PARAM_ERROR" + ,"MEM_ERROR" + ,"DATA_ERROR" + ,"DATA_ERROR_MAGIC" + ,"IO_ERROR" + ,"UNEXPECTED_EOF" + ,"OUTBUFF_FULL" + ,"CONFIG_ERROR" + ,"???" /* for future */ + ,"???" /* for future */ + ,"???" /* for future */ + ,"???" /* for future */ + ,"???" /* for future */ + ,"???" /* for future */ +}; + + +const char * BZ_API(BZ2_bzerror) (BZFILE *b, int *errnum) +{ + int err = ((bzFile *)b)->lastErr; + + if(err>0) err = 0; + *errnum = err; + return bzerrorstrings[err*-1]; +} +#endif + + +/*-------------------------------------------------------------*/ +/*--- end bzlib.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/blocksort.c b/bzip2/blocksort.c new file mode 100644 index 0000000..aba3efc --- /dev/null +++ b/bzip2/blocksort.c @@ -0,0 +1,1141 @@ + +/*-------------------------------------------------------------*/ +/*--- Block sorting machinery ---*/ +/*--- blocksort.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. + + To get some idea how the block sorting algorithms in this file + work, read my paper + On the Performance of BWT Sorting Algorithms + in Proceedings of the IEEE Data Compression Conference 2000, + Snowbird, Utah, USA, 27-30 March 2000. The main sort in this + file implements the algorithm called cache in the paper. +--*/ + + +#include "bzlib_private.h" + +/*---------------------------------------------*/ +/*--- Fallback O(N log(N)^2) sorting ---*/ +/*--- algorithm, for repetitive blocks ---*/ +/*---------------------------------------------*/ + +/*---------------------------------------------*/ +static +__inline__ +void fallbackSimpleSort ( UInt32* fmap, + UInt32* eclass, + Int32 lo, + Int32 hi ) +{ + Int32 i, j, tmp; + UInt32 ec_tmp; + + if (lo == hi) return; + + if (hi - lo > 3) { + for ( i = hi-4; i >= lo; i-- ) { + tmp = fmap[i]; + ec_tmp = eclass[tmp]; + for ( j = i+4; j <= hi && ec_tmp > eclass[fmap[j]]; j += 4 ) + fmap[j-4] = fmap[j]; + fmap[j-4] = tmp; + } + } + + for ( i = hi-1; i >= lo; i-- ) { + tmp = fmap[i]; + ec_tmp = eclass[tmp]; + for ( j = i+1; j <= hi && ec_tmp > eclass[fmap[j]]; j++ ) + fmap[j-1] = fmap[j]; + fmap[j-1] = tmp; + } +} + + +/*---------------------------------------------*/ +#define fswap(zz1, zz2) \ + { Int32 zztmp = zz1; zz1 = zz2; zz2 = zztmp; } + +#define fvswap(zzp1, zzp2, zzn) \ +{ \ + Int32 yyp1 = (zzp1); \ + Int32 yyp2 = (zzp2); \ + Int32 yyn = (zzn); \ + while (yyn > 0) { \ + fswap(fmap[yyp1], fmap[yyp2]); \ + yyp1++; yyp2++; yyn--; \ + } \ +} + + +#define fmin(a,b) ((a) < (b)) ? (a) : (b) + +#define fpush(lz,hz) { stackLo[sp] = lz; \ + stackHi[sp] = hz; \ + sp++; } + +#define fpop(lz,hz) { sp--; \ + lz = stackLo[sp]; \ + hz = stackHi[sp]; } + +#define FALLBACK_QSORT_SMALL_THRESH 10 +#define FALLBACK_QSORT_STACK_SIZE 100 + + +static +void fallbackQSort3 ( UInt32* fmap, + UInt32* eclass, + Int32 loSt, + Int32 hiSt ) +{ + Int32 unLo, unHi, ltLo, gtHi, n, m; + Int32 sp, lo, hi; + UInt32 med, r, r3; + Int32 stackLo[FALLBACK_QSORT_STACK_SIZE]; + Int32 stackHi[FALLBACK_QSORT_STACK_SIZE]; + + r = 0; + + sp = 0; + fpush ( loSt, hiSt ); + + while (sp > 0) { + + AssertH ( sp < FALLBACK_QSORT_STACK_SIZE, 1004 ); + + fpop ( lo, hi ); + if (hi - lo < FALLBACK_QSORT_SMALL_THRESH) { + fallbackSimpleSort ( fmap, eclass, lo, hi ); + continue; + } + + /* Random partitioning. Median of 3 sometimes fails to + avoid bad cases. Median of 9 seems to help but + looks rather expensive. This too seems to work but + is cheaper. Guidance for the magic constants + 7621 and 32768 is taken from Sedgewick's algorithms + book, chapter 35. + */ + r = ((r * 7621) + 1) % 32768; + r3 = r % 3; + if (r3 == 0) med = eclass[fmap[lo]]; else + if (r3 == 1) med = eclass[fmap[(lo+hi)>>1]]; else + med = eclass[fmap[hi]]; + + unLo = ltLo = lo; + unHi = gtHi = hi; + + while (1) { + while (1) { + if (unLo > unHi) break; + n = (Int32)eclass[fmap[unLo]] - (Int32)med; + if (n == 0) { + fswap(fmap[unLo], fmap[ltLo]); + ltLo++; unLo++; + continue; + }; + if (n > 0) break; + unLo++; + } + while (1) { + if (unLo > unHi) break; + n = (Int32)eclass[fmap[unHi]] - (Int32)med; + if (n == 0) { + fswap(fmap[unHi], fmap[gtHi]); + gtHi--; unHi--; + continue; + }; + if (n < 0) break; + unHi--; + } + if (unLo > unHi) break; + fswap(fmap[unLo], fmap[unHi]); unLo++; unHi--; + } + + AssertD ( unHi == unLo-1, "fallbackQSort3(2)" ); + + if (gtHi < ltLo) continue; + + n = fmin(ltLo-lo, unLo-ltLo); fvswap(lo, unLo-n, n); + m = fmin(hi-gtHi, gtHi-unHi); fvswap(unLo, hi-m+1, m); + + n = lo + unLo - ltLo - 1; + m = hi - (gtHi - unHi) + 1; + + if (n - lo > hi - m) { + fpush ( lo, n ); + fpush ( m, hi ); + } else { + fpush ( m, hi ); + fpush ( lo, n ); + } + } +} + +#undef fmin +#undef fpush +#undef fpop +#undef fswap +#undef fvswap +#undef FALLBACK_QSORT_SMALL_THRESH +#undef FALLBACK_QSORT_STACK_SIZE + + +/*---------------------------------------------*/ +/* Pre: + nblock > 0 + eclass exists for [0 .. nblock-1] + ((UChar*)eclass) [0 .. nblock-1] holds block + ptr exists for [0 .. nblock-1] + + Post: + ((UChar*)eclass) [0 .. nblock-1] holds block + All other areas of eclass destroyed + fmap [0 .. nblock-1] holds sorted order + bhtab [ 0 .. 2+(nblock/32) ] destroyed +*/ + +#define SET_BH(zz) bhtab[(zz) >> 5] |= (1 << ((zz) & 31)) +#define CLEAR_BH(zz) bhtab[(zz) >> 5] &= ~(1 << ((zz) & 31)) +#define ISSET_BH(zz) (bhtab[(zz) >> 5] & (1 << ((zz) & 31))) +#define WORD_BH(zz) bhtab[(zz) >> 5] +#define UNALIGNED_BH(zz) ((zz) & 0x01f) + +static +void fallbackSort ( UInt32* fmap, + UInt32* eclass, + UInt32* bhtab, + Int32 nblock, + Int32 verb ) +{ + Int32 ftab[257]; + Int32 ftabCopy[256]; + Int32 H, i, j, k, l, r, cc, cc1; + Int32 nNotDone; + Int32 nBhtab; + UChar* eclass8 = (UChar*)eclass; + + /*-- + Initial 1-char radix sort to generate + initial fmap and initial BH bits. + --*/ + if (verb >= 4) + VPrintf0 ( " bucket sorting ...\n" ); + for (i = 0; i < 257; i++) ftab[i] = 0; + for (i = 0; i < nblock; i++) ftab[eclass8[i]]++; + for (i = 0; i < 256; i++) ftabCopy[i] = ftab[i]; + for (i = 1; i < 257; i++) ftab[i] += ftab[i-1]; + + for (i = 0; i < nblock; i++) { + j = eclass8[i]; + k = ftab[j] - 1; + ftab[j] = k; + fmap[k] = i; + } + + nBhtab = 2 + (nblock / 32); + for (i = 0; i < nBhtab; i++) bhtab[i] = 0; + for (i = 0; i < 256; i++) SET_BH(ftab[i]); + + /*-- + Inductively refine the buckets. Kind-of an + "exponential radix sort" (!), inspired by the + Manber-Myers suffix array construction algorithm. + --*/ + + /*-- set sentinel bits for block-end detection --*/ + for (i = 0; i < 32; i++) { + SET_BH(nblock + 2*i); + CLEAR_BH(nblock + 2*i + 1); + } + + /*-- the log(N) loop --*/ + H = 1; + while (1) { + + if (verb >= 4) + VPrintf1 ( " depth %6d has ", H ); + + j = 0; + for (i = 0; i < nblock; i++) { + if (ISSET_BH(i)) j = i; + k = fmap[i] - H; if (k < 0) k += nblock; + eclass[k] = j; + } + + nNotDone = 0; + r = -1; + while (1) { + + /*-- find the next non-singleton bucket --*/ + k = r + 1; + while (ISSET_BH(k) && UNALIGNED_BH(k)) k++; + if (ISSET_BH(k)) { + while (WORD_BH(k) == 0xffffffff) k += 32; + while (ISSET_BH(k)) k++; + } + l = k - 1; + if (l >= nblock) break; + while (!ISSET_BH(k) && UNALIGNED_BH(k)) k++; + if (!ISSET_BH(k)) { + while (WORD_BH(k) == 0x00000000) k += 32; + while (!ISSET_BH(k)) k++; + } + r = k - 1; + if (r >= nblock) break; + + /*-- now [l, r] bracket current bucket --*/ + if (r > l) { + nNotDone += (r - l + 1); + fallbackQSort3 ( fmap, eclass, l, r ); + + /*-- scan bucket and generate header bits-- */ + cc = -1; + for (i = l; i <= r; i++) { + cc1 = eclass[fmap[i]]; + if (cc != cc1) { SET_BH(i); cc = cc1; }; + } + } + } + + if (verb >= 4) + VPrintf1 ( "%6d unresolved strings\n", nNotDone ); + + H *= 2; + if (H > nblock || nNotDone == 0) break; + } + + /*-- + Reconstruct the original block in + eclass8 [0 .. nblock-1], since the + previous phase destroyed it. + --*/ + if (verb >= 4) + VPrintf0 ( " reconstructing block ...\n" ); + j = 0; + for (i = 0; i < nblock; i++) { + while (ftabCopy[j] == 0) j++; + ftabCopy[j]--; + eclass8[fmap[i]] = (UChar)j; + } + AssertH ( j < 256, 1005 ); +} + +#undef SET_BH +#undef CLEAR_BH +#undef ISSET_BH +#undef WORD_BH +#undef UNALIGNED_BH + + +/*---------------------------------------------*/ +/*--- The main, O(N^2 log(N)) sorting ---*/ +/*--- algorithm. Faster for "normal" ---*/ +/*--- non-repetitive blocks. ---*/ +/*---------------------------------------------*/ + +/*---------------------------------------------*/ +static +__inline__ +Bool mainGtU ( UInt32 i1, + UInt32 i2, + UChar* block, + UInt16* quadrant, + UInt32 nblock, + Int32* budget ) +{ + Int32 k; + UChar c1, c2; + UInt16 s1, s2; + + AssertD ( i1 != i2, "mainGtU" ); + /* 1 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 2 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 3 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 4 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 5 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 6 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 7 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 8 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 9 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 10 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 11 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + /* 12 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + i1++; i2++; + + k = nblock + 8; + + do { + /* 1 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 2 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 3 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 4 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 5 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 6 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 7 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + /* 8 */ + c1 = block[i1]; c2 = block[i2]; + if (c1 != c2) return (c1 > c2); + s1 = quadrant[i1]; s2 = quadrant[i2]; + if (s1 != s2) return (s1 > s2); + i1++; i2++; + + if (i1 >= nblock) i1 -= nblock; + if (i2 >= nblock) i2 -= nblock; + + k -= 8; + (*budget)--; + } + while (k >= 0); + + return False; +} + + +/*---------------------------------------------*/ +/*-- + Knuth's increments seem to work better + than Incerpi-Sedgewick here. Possibly + because the number of elems to sort is + usually small, typically <= 20. +--*/ +static +Int32 incs[14] = { 1, 4, 13, 40, 121, 364, 1093, 3280, + 9841, 29524, 88573, 265720, + 797161, 2391484 }; + +static +void mainSimpleSort ( UInt32* ptr, + UChar* block, + UInt16* quadrant, + Int32 nblock, + Int32 lo, + Int32 hi, + Int32 d, + Int32* budget ) +{ + Int32 i, j, h, bigN, hp; + UInt32 v; + + bigN = hi - lo + 1; + if (bigN < 2) return; + + hp = 0; + while (incs[hp] < bigN) hp++; + hp--; + + for (; hp >= 0; hp--) { + h = incs[hp]; + + i = lo + h; + while (True) { + + /*-- copy 1 --*/ + if (i > hi) break; + v = ptr[i]; + j = i; + while ( mainGtU ( + ptr[j-h]+d, v+d, block, quadrant, nblock, budget + ) ) { + ptr[j] = ptr[j-h]; + j = j - h; + if (j <= (lo + h - 1)) break; + } + ptr[j] = v; + i++; + + /*-- copy 2 --*/ + if (i > hi) break; + v = ptr[i]; + j = i; + while ( mainGtU ( + ptr[j-h]+d, v+d, block, quadrant, nblock, budget + ) ) { + ptr[j] = ptr[j-h]; + j = j - h; + if (j <= (lo + h - 1)) break; + } + ptr[j] = v; + i++; + + /*-- copy 3 --*/ + if (i > hi) break; + v = ptr[i]; + j = i; + while ( mainGtU ( + ptr[j-h]+d, v+d, block, quadrant, nblock, budget + ) ) { + ptr[j] = ptr[j-h]; + j = j - h; + if (j <= (lo + h - 1)) break; + } + ptr[j] = v; + i++; + + if (*budget < 0) return; + } + } +} + + +/*---------------------------------------------*/ +/*-- + The following is an implementation of + an elegant 3-way quicksort for strings, + described in a paper "Fast Algorithms for + Sorting and Searching Strings", by Robert + Sedgewick and Jon L. Bentley. +--*/ + +#define mswap(zz1, zz2) \ + { Int32 zztmp = zz1; zz1 = zz2; zz2 = zztmp; } + +#define mvswap(zzp1, zzp2, zzn) \ +{ \ + Int32 yyp1 = (zzp1); \ + Int32 yyp2 = (zzp2); \ + Int32 yyn = (zzn); \ + while (yyn > 0) { \ + mswap(ptr[yyp1], ptr[yyp2]); \ + yyp1++; yyp2++; yyn--; \ + } \ +} + +static +__inline__ +UChar mmed3 ( UChar a, UChar b, UChar c ) +{ + UChar t; + if (a > b) { t = a; a = b; b = t; }; + if (b > c) { + b = c; + if (a > b) b = a; + } + return b; +} + +#define mmin(a,b) ((a) < (b)) ? (a) : (b) + +#define mpush(lz,hz,dz) { stackLo[sp] = lz; \ + stackHi[sp] = hz; \ + stackD [sp] = dz; \ + sp++; } + +#define mpop(lz,hz,dz) { sp--; \ + lz = stackLo[sp]; \ + hz = stackHi[sp]; \ + dz = stackD [sp]; } + + +#define mnextsize(az) (nextHi[az]-nextLo[az]) + +#define mnextswap(az,bz) \ + { Int32 tz; \ + tz = nextLo[az]; nextLo[az] = nextLo[bz]; nextLo[bz] = tz; \ + tz = nextHi[az]; nextHi[az] = nextHi[bz]; nextHi[bz] = tz; \ + tz = nextD [az]; nextD [az] = nextD [bz]; nextD [bz] = tz; } + + +#define MAIN_QSORT_SMALL_THRESH 20 +#define MAIN_QSORT_DEPTH_THRESH (BZ_N_RADIX + BZ_N_QSORT) +#define MAIN_QSORT_STACK_SIZE 100 + +static +void mainQSort3 ( UInt32* ptr, + UChar* block, + UInt16* quadrant, + Int32 nblock, + Int32 loSt, + Int32 hiSt, + Int32 dSt, + Int32* budget ) +{ + Int32 unLo, unHi, ltLo, gtHi, n, m, med; + Int32 sp, lo, hi, d; + + Int32 stackLo[MAIN_QSORT_STACK_SIZE]; + Int32 stackHi[MAIN_QSORT_STACK_SIZE]; + Int32 stackD [MAIN_QSORT_STACK_SIZE]; + + Int32 nextLo[3]; + Int32 nextHi[3]; + Int32 nextD [3]; + + sp = 0; + mpush ( loSt, hiSt, dSt ); + + while (sp > 0) { + + AssertH ( sp < MAIN_QSORT_STACK_SIZE, 1001 ); + + mpop ( lo, hi, d ); + if (hi - lo < MAIN_QSORT_SMALL_THRESH || + d > MAIN_QSORT_DEPTH_THRESH) { + mainSimpleSort ( ptr, block, quadrant, nblock, lo, hi, d, budget ); + if (*budget < 0) return; + continue; + } + + med = (Int32) + mmed3 ( block[ptr[ lo ]+d], + block[ptr[ hi ]+d], + block[ptr[ (lo+hi)>>1 ]+d] ); + + unLo = ltLo = lo; + unHi = gtHi = hi; + + while (True) { + while (True) { + if (unLo > unHi) break; + n = ((Int32)block[ptr[unLo]+d]) - med; + if (n == 0) { + mswap(ptr[unLo], ptr[ltLo]); + ltLo++; unLo++; continue; + }; + if (n > 0) break; + unLo++; + } + while (True) { + if (unLo > unHi) break; + n = ((Int32)block[ptr[unHi]+d]) - med; + if (n == 0) { + mswap(ptr[unHi], ptr[gtHi]); + gtHi--; unHi--; continue; + }; + if (n < 0) break; + unHi--; + } + if (unLo > unHi) break; + mswap(ptr[unLo], ptr[unHi]); unLo++; unHi--; + } + + AssertD ( unHi == unLo-1, "mainQSort3(2)" ); + + if (gtHi < ltLo) { + mpush(lo, hi, d+1 ); + continue; + } + + n = mmin(ltLo-lo, unLo-ltLo); mvswap(lo, unLo-n, n); + m = mmin(hi-gtHi, gtHi-unHi); mvswap(unLo, hi-m+1, m); + + n = lo + unLo - ltLo - 1; + m = hi - (gtHi - unHi) + 1; + + nextLo[0] = lo; nextHi[0] = n; nextD[0] = d; + nextLo[1] = m; nextHi[1] = hi; nextD[1] = d; + nextLo[2] = n+1; nextHi[2] = m-1; nextD[2] = d+1; + + if (mnextsize(0) < mnextsize(1)) mnextswap(0,1); + if (mnextsize(1) < mnextsize(2)) mnextswap(1,2); + if (mnextsize(0) < mnextsize(1)) mnextswap(0,1); + + AssertD (mnextsize(0) >= mnextsize(1), "mainQSort3(8)" ); + AssertD (mnextsize(1) >= mnextsize(2), "mainQSort3(9)" ); + + mpush (nextLo[0], nextHi[0], nextD[0]); + mpush (nextLo[1], nextHi[1], nextD[1]); + mpush (nextLo[2], nextHi[2], nextD[2]); + } +} + +#undef mswap +#undef mvswap +#undef mpush +#undef mpop +#undef mmin +#undef mnextsize +#undef mnextswap +#undef MAIN_QSORT_SMALL_THRESH +#undef MAIN_QSORT_DEPTH_THRESH +#undef MAIN_QSORT_STACK_SIZE + + +/*---------------------------------------------*/ +/* Pre: + nblock > N_OVERSHOOT + block32 exists for [0 .. nblock-1 +N_OVERSHOOT] + ((UChar*)block32) [0 .. nblock-1] holds block + ptr exists for [0 .. nblock-1] + + Post: + ((UChar*)block32) [0 .. nblock-1] holds block + All other areas of block32 destroyed + ftab [0 .. 65536 ] destroyed + ptr [0 .. nblock-1] holds sorted order + if (*budget < 0), sorting was abandoned +*/ + +#define BIGFREQ(b) (ftab[((b)+1) << 8] - ftab[(b) << 8]) +#define SETMASK (1 << 21) +#define CLEARMASK (~(SETMASK)) + +static +void mainSort ( UInt32* ptr, + UChar* block, + UInt16* quadrant, + UInt32* ftab, + Int32 nblock, + Int32 verb, + Int32* budget ) +{ + Int32 i, j, k, ss, sb; + Int32 runningOrder[256]; + Bool bigDone[256]; + Int32 copyStart[256]; + Int32 copyEnd [256]; + UChar c1; + Int32 numQSorted; + UInt16 s; + if (verb >= 4) VPrintf0 ( " main sort initialise ...\n" ); + + /*-- set up the 2-byte frequency table --*/ + for (i = 65536; i >= 0; i--) ftab[i] = 0; + + j = block[0] << 8; + i = nblock-1; + for (; i >= 3; i -= 4) { + quadrant[i] = 0; + j = (j >> 8) | ( ((UInt16)block[i]) << 8); + ftab[j]++; + quadrant[i-1] = 0; + j = (j >> 8) | ( ((UInt16)block[i-1]) << 8); + ftab[j]++; + quadrant[i-2] = 0; + j = (j >> 8) | ( ((UInt16)block[i-2]) << 8); + ftab[j]++; + quadrant[i-3] = 0; + j = (j >> 8) | ( ((UInt16)block[i-3]) << 8); + ftab[j]++; + } + for (; i >= 0; i--) { + quadrant[i] = 0; + j = (j >> 8) | ( ((UInt16)block[i]) << 8); + ftab[j]++; + } + + /*-- (emphasises close relationship of block & quadrant) --*/ + for (i = 0; i < BZ_N_OVERSHOOT; i++) { + block [nblock+i] = block[i]; + quadrant[nblock+i] = 0; + } + + if (verb >= 4) VPrintf0 ( " bucket sorting ...\n" ); + + /*-- Complete the initial radix sort --*/ + for (i = 1; i <= 65536; i++) ftab[i] += ftab[i-1]; + + s = block[0] << 8; + i = nblock-1; + for (; i >= 3; i -= 4) { + s = (s >> 8) | (block[i] << 8); + j = ftab[s] -1; + ftab[s] = j; + ptr[j] = i; + s = (s >> 8) | (block[i-1] << 8); + j = ftab[s] -1; + ftab[s] = j; + ptr[j] = i-1; + s = (s >> 8) | (block[i-2] << 8); + j = ftab[s] -1; + ftab[s] = j; + ptr[j] = i-2; + s = (s >> 8) | (block[i-3] << 8); + j = ftab[s] -1; + ftab[s] = j; + ptr[j] = i-3; + } + for (; i >= 0; i--) { + s = (s >> 8) | (block[i] << 8); + j = ftab[s] -1; + ftab[s] = j; + ptr[j] = i; + } + + /*-- + Now ftab contains the first loc of every small bucket. + Calculate the running order, from smallest to largest + big bucket. + --*/ + for (i = 0; i <= 255; i++) { + bigDone [i] = False; + runningOrder[i] = i; + } + + { + Int32 vv; + Int32 h = 1; + do h = 3 * h + 1; while (h <= 256); + do { + h = h / 3; + for (i = h; i <= 255; i++) { + vv = runningOrder[i]; + j = i; + while ( BIGFREQ(runningOrder[j-h]) > BIGFREQ(vv) ) { + runningOrder[j] = runningOrder[j-h]; + j = j - h; + if (j <= (h - 1)) goto zero; + } + zero: + runningOrder[j] = vv; + } + } while (h != 1); + } + + /*-- + The main sorting loop. + --*/ + + numQSorted = 0; + + for (i = 0; i <= 255; i++) { + + /*-- + Process big buckets, starting with the least full. + Basically this is a 3-step process in which we call + mainQSort3 to sort the small buckets [ss, j], but + also make a big effort to avoid the calls if we can. + --*/ + ss = runningOrder[i]; + + /*-- + Step 1: + Complete the big bucket [ss] by quicksorting + any unsorted small buckets [ss, j], for j != ss. + Hopefully previous pointer-scanning phases have already + completed many of the small buckets [ss, j], so + we don't have to sort them at all. + --*/ + for (j = 0; j <= 255; j++) { + if (j != ss) { + sb = (ss << 8) + j; + if ( ! (ftab[sb] & SETMASK) ) { + Int32 lo = ftab[sb] & CLEARMASK; + Int32 hi = (ftab[sb+1] & CLEARMASK) - 1; + if (hi > lo) { + if (verb >= 4) + VPrintf4 ( " qsort [0x%x, 0x%x] " + "done %d this %d\n", + ss, j, numQSorted, hi - lo + 1 ); + mainQSort3 ( + ptr, block, quadrant, nblock, + lo, hi, BZ_N_RADIX, budget + ); + numQSorted += (hi - lo + 1); + if (*budget < 0) return; + } + } + ftab[sb] |= SETMASK; + } + } + + AssertH ( !bigDone[ss], 1006 ); + + /*-- + Step 2: + Now scan this big bucket [ss] so as to synthesise the + sorted order for small buckets [t, ss] for all t, + including, magically, the bucket [ss,ss] too. + This will avoid doing Real Work in subsequent Step 1's. + --*/ + { + for (j = 0; j <= 255; j++) { + copyStart[j] = ftab[(j << 8) + ss] & CLEARMASK; + copyEnd [j] = (ftab[(j << 8) + ss + 1] & CLEARMASK) - 1; + } + for (j = ftab[ss << 8] & CLEARMASK; j < copyStart[ss]; j++) { + k = ptr[j]-1; if (k < 0) k += nblock; + c1 = block[k]; + if (!bigDone[c1]) + ptr[ copyStart[c1]++ ] = k; + } + for (j = (ftab[(ss+1) << 8] & CLEARMASK) - 1; j > copyEnd[ss]; j--) { + k = ptr[j]-1; if (k < 0) k += nblock; + c1 = block[k]; + if (!bigDone[c1]) + ptr[ copyEnd[c1]-- ] = k; + } + } + + AssertH ( (copyStart[ss]-1 == copyEnd[ss]) + || + /* Extremely rare case missing in bzip2-1.0.0 and 1.0.1. + Necessity for this case is demonstrated by compressing + a sequence of approximately 48.5 million of character + 251; 1.0.0/1.0.1 will then die here. */ + (copyStart[ss] == 0 && copyEnd[ss] == nblock-1), + 1007 ) + + for (j = 0; j <= 255; j++) ftab[(j << 8) + ss] |= SETMASK; + + /*-- + Step 3: + The [ss] big bucket is now done. Record this fact, + and update the quadrant descriptors. Remember to + update quadrants in the overshoot area too, if + necessary. The "if (i < 255)" test merely skips + this updating for the last bucket processed, since + updating for the last bucket is pointless. + + The quadrant array provides a way to incrementally + cache sort orderings, as they appear, so as to + make subsequent comparisons in fullGtU() complete + faster. For repetitive blocks this makes a big + difference (but not big enough to be able to avoid + the fallback sorting mechanism, exponential radix sort). + + The precise meaning is: at all times: + + for 0 <= i < nblock and 0 <= j <= nblock + + if block[i] != block[j], + + then the relative values of quadrant[i] and + quadrant[j] are meaningless. + + else { + if quadrant[i] < quadrant[j] + then the string starting at i lexicographically + precedes the string starting at j + + else if quadrant[i] > quadrant[j] + then the string starting at j lexicographically + precedes the string starting at i + + else + the relative ordering of the strings starting + at i and j has not yet been determined. + } + --*/ + bigDone[ss] = True; + + if (i < 255) { + Int32 bbStart = ftab[ss << 8] & CLEARMASK; + Int32 bbSize = (ftab[(ss+1) << 8] & CLEARMASK) - bbStart; + Int32 shifts = 0; + + while ((bbSize >> shifts) > 65534) shifts++; + + for (j = bbSize-1; j >= 0; j--) { + Int32 a2update = ptr[bbStart + j]; + UInt16 qVal = (UInt16)(j >> shifts); + quadrant[a2update] = qVal; + if (a2update < BZ_N_OVERSHOOT) + quadrant[a2update + nblock] = qVal; + } + AssertH ( ((bbSize-1) >> shifts) <= 65535, 1002 ); + } + + } + + if (verb >= 4) + VPrintf3 ( " %d pointers, %d sorted, %d scanned\n", + nblock, numQSorted, nblock - numQSorted ); +} + +#undef BIGFREQ +#undef SETMASK +#undef CLEARMASK + + +/*---------------------------------------------*/ +/* Pre: + nblock > 0 + arr2 exists for [0 .. nblock-1 +N_OVERSHOOT] + ((UChar*)arr2) [0 .. nblock-1] holds block + arr1 exists for [0 .. nblock-1] + + Post: + ((UChar*)arr2) [0 .. nblock-1] holds block + All other areas of block destroyed + ftab [ 0 .. 65536 ] destroyed + arr1 [0 .. nblock-1] holds sorted order +*/ +void BZ2_blockSort ( EState* s ) +{ + UInt32* ptr = s->ptr; + UChar* block = s->block; + UInt32* ftab = s->ftab; + Int32 nblock = s->nblock; + Int32 verb = s->verbosity; + Int32 wfact = s->workFactor; + UInt16* quadrant; + Int32 budget; + Int32 budgetInit; + Int32 i; + + if (nblock < 10000) { + fallbackSort ( s->arr1, s->arr2, ftab, nblock, verb ); + } else { + /* Calculate the location for quadrant, remembering to get + the alignment right. Assumes that &(block[0]) is at least + 2-byte aligned -- this should be ok since block is really + the first section of arr2. + */ + i = nblock+BZ_N_OVERSHOOT; + if (i & 1) i++; + quadrant = (UInt16*)(&(block[i])); + + /* (wfact-1) / 3 puts the default-factor-30 + transition point at very roughly the same place as + with v0.1 and v0.9.0. + Not that it particularly matters any more, since the + resulting compressed stream is now the same regardless + of whether or not we use the main sort or fallback sort. + */ + if (wfact < 1 ) wfact = 1; + if (wfact > 100) wfact = 100; + budgetInit = nblock * ((wfact-1) / 3); + budget = budgetInit; + + mainSort ( ptr, block, quadrant, ftab, nblock, verb, &budget ); + if (verb >= 3) + VPrintf3 ( " %d work, %d block, ratio %5.2f\n", + budgetInit - budget, + nblock, + (float)(budgetInit - budget) / + (float)(nblock==0 ? 1 : nblock) ); + if (budget < 0) { + if (verb >= 2) + VPrintf0 ( " too repetitive; using fallback" + " sorting algorithm\n" ); + fallbackSort ( s->arr1, s->arr2, ftab, nblock, verb ); + } + } + + s->origPtr = -1; + for (i = 0; i < s->nblock; i++) + if (ptr[i] == 0) + { s->origPtr = i; break; }; + + AssertH( s->origPtr != -1, 1003 ); +} + + +/*-------------------------------------------------------------*/ +/*--- end blocksort.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/bzlib.h b/bzip2/bzlib.h new file mode 100644 index 0000000..4a451e0 --- /dev/null +++ b/bzip2/bzlib.h @@ -0,0 +1,321 @@ + +/*-------------------------------------------------------------*/ +/*--- Public header file for the library. ---*/ +/*--- bzlib.h ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + + +#ifndef _BZLIB_H +#define _BZLIB_H + +#ifdef __cplusplus +extern "C" { +#endif + +#define BZ_RUN 0 +#define BZ_FLUSH 1 +#define BZ_FINISH 2 + +#define BZ_OK 0 +#define BZ_RUN_OK 1 +#define BZ_FLUSH_OK 2 +#define BZ_FINISH_OK 3 +#define BZ_STREAM_END 4 +#define BZ_SEQUENCE_ERROR (-1) +#define BZ_PARAM_ERROR (-2) +#define BZ_MEM_ERROR (-3) +#define BZ_DATA_ERROR (-4) +#define BZ_DATA_ERROR_MAGIC (-5) +#define BZ_IO_ERROR (-6) +#define BZ_UNEXPECTED_EOF (-7) +#define BZ_OUTBUFF_FULL (-8) +#define BZ_CONFIG_ERROR (-9) + +typedef + struct { + char *next_in; + unsigned int avail_in; + unsigned int total_in_lo32; + unsigned int total_in_hi32; + + char *next_out; + unsigned int avail_out; + unsigned int total_out_lo32; + unsigned int total_out_hi32; + + void *state; + + void *(*bzalloc)(void *,int,int); + void (*bzfree)(void *,void *); + void *opaque; + } + bz_stream; + + +#ifndef BZ_IMPORT +#define BZ_EXPORT +#endif + +/* Need a definitition for FILE */ +#include + +#ifdef _WIN32 +# include +# ifdef small + /* windows.h define small to char */ +# undef small +# endif +# ifdef BZ_EXPORT +# define BZ_API(func) WINAPI func +# define BZ_EXTERN extern +# else + /* import windows dll dynamically */ +# define BZ_API(func) (WINAPI * func) +# define BZ_EXTERN +# endif +#else +# define BZ_API(func) func +# define BZ_EXTERN extern +#endif + + +/*-- Core (low-level) library functions --*/ + +BZ_EXTERN int BZ_API(BZ2_bzCompressInit) ( + bz_stream* strm, + int blockSize100k, + int verbosity, + int workFactor + ); + +BZ_EXTERN int BZ_API(BZ2_bzCompress) ( + bz_stream* strm, + int action + ); + +BZ_EXTERN int BZ_API(BZ2_bzCompressEnd) ( + bz_stream* strm + ); + +BZ_EXTERN int BZ_API(BZ2_bzDecompressInit) ( + bz_stream *strm, + int verbosity, + int small + ); + +BZ_EXTERN int BZ_API(BZ2_bzDecompress) ( + bz_stream* strm + ); + +BZ_EXTERN int BZ_API(BZ2_bzDecompressEnd) ( + bz_stream *strm + ); + + + +/*-- High(er) level library functions --*/ + +#ifndef BZ_NO_STDIO +#define BZ_MAX_UNUSED 5000 + +typedef void BZFILE; + +BZ_EXTERN BZFILE* BZ_API(BZ2_bzReadOpen) ( + int* bzerror, + FILE* f, + int verbosity, + int small, + void* unused, + int nUnused + ); + +BZ_EXTERN void BZ_API(BZ2_bzReadClose) ( + int* bzerror, + BZFILE* b + ); + +BZ_EXTERN void BZ_API(BZ2_bzReadGetUnused) ( + int* bzerror, + BZFILE* b, + void** unused, + int* nUnused + ); + +BZ_EXTERN int BZ_API(BZ2_bzRead) ( + int* bzerror, + BZFILE* b, + void* buf, + int len + ); + +BZ_EXTERN BZFILE* BZ_API(BZ2_bzWriteOpen) ( + int* bzerror, + FILE* f, + int blockSize100k, + int verbosity, + int workFactor + ); + +BZ_EXTERN void BZ_API(BZ2_bzWrite) ( + int* bzerror, + BZFILE* b, + void* buf, + int len + ); + +BZ_EXTERN void BZ_API(BZ2_bzWriteClose) ( + int* bzerror, + BZFILE* b, + int abandon, + unsigned int* nbytes_in, + unsigned int* nbytes_out + ); + +BZ_EXTERN void BZ_API(BZ2_bzWriteClose64) ( + int* bzerror, + BZFILE* b, + int abandon, + unsigned int* nbytes_in_lo32, + unsigned int* nbytes_in_hi32, + unsigned int* nbytes_out_lo32, + unsigned int* nbytes_out_hi32 + ); +#endif + + +/*-- Utility functions --*/ + +BZ_EXTERN int BZ_API(BZ2_bzBuffToBuffCompress) ( + char* dest, + unsigned int* destLen, + char* source, + unsigned int sourceLen, + int blockSize100k, + int verbosity, + int workFactor + ); + +BZ_EXTERN int BZ_API(BZ2_bzBuffToBuffDecompress) ( + char* dest, + unsigned int* destLen, + char* source, + unsigned int sourceLen, + int small, + int verbosity + ); + + +/*-- + Code contributed by Yoshioka Tsuneo + (QWF00133@niftyserve.or.jp/tsuneo-y@is.aist-nara.ac.jp), + to support better zlib compatibility. + This code is not _officially_ part of libbzip2 (yet); + I haven't tested it, documented it, or considered the + threading-safeness of it. + If this code breaks, please contact both Yoshioka and me. +--*/ + +BZ_EXTERN const char * BZ_API(BZ2_bzlibVersion) ( + void + ); + +#ifndef BZ_NO_STDIO +BZ_EXTERN BZFILE * BZ_API(BZ2_bzopen) ( + const char *path, + const char *mode + ); + +BZ_EXTERN BZFILE * BZ_API(BZ2_bzdopen) ( + int fd, + const char *mode + ); + +BZ_EXTERN int BZ_API(BZ2_bzread) ( + BZFILE* b, + void* buf, + int len + ); + +BZ_EXTERN int BZ_API(BZ2_bzwrite) ( + BZFILE* b, + void* buf, + int len + ); + +BZ_EXTERN int BZ_API(BZ2_bzflush) ( + BZFILE* b + ); + +BZ_EXTERN void BZ_API(BZ2_bzclose) ( + BZFILE* b + ); + +BZ_EXTERN const char * BZ_API(BZ2_bzerror) ( + BZFILE *b, + int *errnum + ); +#endif + +#ifdef __cplusplus +} +#endif + +#endif + +/*-------------------------------------------------------------*/ +/*--- end bzlib.h ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/bzlib_private.h b/bzip2/bzlib_private.h new file mode 100644 index 0000000..ff973c3 --- /dev/null +++ b/bzip2/bzlib_private.h @@ -0,0 +1,537 @@ + +/*-------------------------------------------------------------*/ +/*--- Private header file for the library. ---*/ +/*--- bzlib_private.h ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + + +#ifndef _BZLIB_PRIVATE_H +#define _BZLIB_PRIVATE_H + +#include + +#ifndef BZ_NO_STDIO +#include +#include +#include +#endif + +#include "bzlib.h" + + + +/*-- General stuff. --*/ + +#define BZ_VERSION "1.0.2, 30-Dec-2001" + +typedef char Char; +typedef unsigned char Bool; +typedef unsigned char UChar; +typedef int Int32; +typedef unsigned int UInt32; +typedef short Int16; +typedef unsigned short UInt16; + +#define True ((Bool)1) +#define False ((Bool)0) + +#ifndef __GNUC__ +#define __inline__ /* */ +#endif + +#ifndef BZ_NO_STDIO +extern void BZ2_bz__AssertH__fail ( int errcode ); +#define AssertH(cond,errcode) \ + { if (!(cond)) BZ2_bz__AssertH__fail ( errcode ); } +#if BZ_DEBUG +#define AssertD(cond,msg) \ + { if (!(cond)) { \ + fprintf ( stderr, \ + "\n\nlibbzip2(debug build): internal error\n\t%s\n", msg );\ + exit(1); \ + }} +#else +#define AssertD(cond,msg) /* */ +#endif +#define VPrintf0(zf) \ + fprintf(stderr,zf) +#define VPrintf1(zf,za1) \ + fprintf(stderr,zf,za1) +#define VPrintf2(zf,za1,za2) \ + fprintf(stderr,zf,za1,za2) +#define VPrintf3(zf,za1,za2,za3) \ + fprintf(stderr,zf,za1,za2,za3) +#define VPrintf4(zf,za1,za2,za3,za4) \ + fprintf(stderr,zf,za1,za2,za3,za4) +#define VPrintf5(zf,za1,za2,za3,za4,za5) \ + fprintf(stderr,zf,za1,za2,za3,za4,za5) +#else +extern void bz_internal_error ( int errcode ); +#define AssertH(cond,errcode) \ + { if (!(cond)) bz_internal_error ( errcode ); } +#define AssertD(cond,msg) /* */ +#define VPrintf0(zf) /* */ +#define VPrintf1(zf,za1) /* */ +#define VPrintf2(zf,za1,za2) /* */ +#define VPrintf3(zf,za1,za2,za3) /* */ +#define VPrintf4(zf,za1,za2,za3,za4) /* */ +#define VPrintf5(zf,za1,za2,za3,za4,za5) /* */ +#endif + + +#define BZALLOC(nnn) (strm->bzalloc)(strm->opaque,(nnn),1) +#define BZFREE(ppp) (strm->bzfree)(strm->opaque,(ppp)) + + +/*-- Header bytes. --*/ + +#define BZ_HDR_B 0x42 /* 'B' */ +#define BZ_HDR_Z 0x5a /* 'Z' */ +#define BZ_HDR_h 0x68 /* 'h' */ +#define BZ_HDR_0 0x30 /* '0' */ + +/*-- Constants for the back end. --*/ + +#define BZ_MAX_ALPHA_SIZE 258 +#define BZ_MAX_CODE_LEN 23 + +#define BZ_RUNA 0 +#define BZ_RUNB 1 + +#define BZ_N_GROUPS 6 +#define BZ_G_SIZE 50 +#define BZ_N_ITERS 4 + +#define BZ_MAX_SELECTORS (2 + (900000 / BZ_G_SIZE)) + + + +/*-- Stuff for randomising repetitive blocks. --*/ + +extern Int32 BZ2_rNums[512]; + +#define BZ_RAND_DECLS \ + Int32 rNToGo; \ + Int32 rTPos \ + +#define BZ_RAND_INIT_MASK \ + s->rNToGo = 0; \ + s->rTPos = 0 \ + +#define BZ_RAND_MASK ((s->rNToGo == 1) ? 1 : 0) + +#define BZ_RAND_UPD_MASK \ + if (s->rNToGo == 0) { \ + s->rNToGo = BZ2_rNums[s->rTPos]; \ + s->rTPos++; \ + if (s->rTPos == 512) s->rTPos = 0; \ + } \ + s->rNToGo--; + + + +/*-- Stuff for doing CRCs. --*/ + +extern UInt32 BZ2_crc32Table[256]; + +#define BZ_INITIALISE_CRC(crcVar) \ +{ \ + crcVar = 0xffffffffL; \ +} + +#define BZ_FINALISE_CRC(crcVar) \ +{ \ + crcVar = ~(crcVar); \ +} + +#define BZ_UPDATE_CRC(crcVar,cha) \ +{ \ + crcVar = (crcVar << 8) ^ \ + BZ2_crc32Table[(crcVar >> 24) ^ \ + ((UChar)cha)]; \ +} + + + +/*-- States and modes for compression. --*/ + +#define BZ_M_IDLE 1 +#define BZ_M_RUNNING 2 +#define BZ_M_FLUSHING 3 +#define BZ_M_FINISHING 4 + +#define BZ_S_OUTPUT 1 +#define BZ_S_INPUT 2 + +#define BZ_N_RADIX 2 +#define BZ_N_QSORT 12 +#define BZ_N_SHELL 18 +#define BZ_N_OVERSHOOT (BZ_N_RADIX + BZ_N_QSORT + BZ_N_SHELL + 2) + + + + +/*-- Structure holding all the compression-side stuff. --*/ + +typedef + struct { + /* pointer back to the struct bz_stream */ + bz_stream* strm; + + /* mode this stream is in, and whether inputting */ + /* or outputting data */ + Int32 mode; + Int32 state; + + /* remembers avail_in when flush/finish requested */ + UInt32 avail_in_expect; + + /* for doing the block sorting */ + UInt32* arr1; + UInt32* arr2; + UInt32* ftab; + Int32 origPtr; + + /* aliases for arr1 and arr2 */ + UInt32* ptr; + UChar* block; + UInt16* mtfv; + UChar* zbits; + + /* for deciding when to use the fallback sorting algorithm */ + Int32 workFactor; + + /* run-length-encoding of the input */ + UInt32 state_in_ch; + Int32 state_in_len; + BZ_RAND_DECLS; + + /* input and output limits and current posns */ + Int32 nblock; + Int32 nblockMAX; + Int32 numZ; + Int32 state_out_pos; + + /* map of bytes used in block */ + Int32 nInUse; + Bool inUse[256]; + UChar unseqToSeq[256]; + + /* the buffer for bit stream creation */ + UInt32 bsBuff; + Int32 bsLive; + + /* block and combined CRCs */ + UInt32 blockCRC; + UInt32 combinedCRC; + + /* misc administratium */ + Int32 verbosity; + Int32 blockNo; + Int32 blockSize100k; + + /* stuff for coding the MTF values */ + Int32 nMTF; + Int32 mtfFreq [BZ_MAX_ALPHA_SIZE]; + UChar selector [BZ_MAX_SELECTORS]; + UChar selectorMtf[BZ_MAX_SELECTORS]; + + UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + Int32 code [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + Int32 rfreq [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + /* second dimension: only 3 needed; 4 makes index calculations faster */ + UInt32 len_pack[BZ_MAX_ALPHA_SIZE][4]; + + } + EState; + + + +/*-- externs for compression. --*/ + +extern void +BZ2_blockSort ( EState* ); + +extern void +BZ2_compressBlock ( EState*, Bool ); + +extern void +BZ2_bsInitWrite ( EState* ); + +extern void +BZ2_hbAssignCodes ( Int32*, UChar*, Int32, Int32, Int32 ); + +extern void +BZ2_hbMakeCodeLengths ( UChar*, Int32*, Int32, Int32 ); + + + +/*-- states for decompression. --*/ + +#define BZ_X_IDLE 1 +#define BZ_X_OUTPUT 2 + +#define BZ_X_MAGIC_1 10 +#define BZ_X_MAGIC_2 11 +#define BZ_X_MAGIC_3 12 +#define BZ_X_MAGIC_4 13 +#define BZ_X_BLKHDR_1 14 +#define BZ_X_BLKHDR_2 15 +#define BZ_X_BLKHDR_3 16 +#define BZ_X_BLKHDR_4 17 +#define BZ_X_BLKHDR_5 18 +#define BZ_X_BLKHDR_6 19 +#define BZ_X_BCRC_1 20 +#define BZ_X_BCRC_2 21 +#define BZ_X_BCRC_3 22 +#define BZ_X_BCRC_4 23 +#define BZ_X_RANDBIT 24 +#define BZ_X_ORIGPTR_1 25 +#define BZ_X_ORIGPTR_2 26 +#define BZ_X_ORIGPTR_3 27 +#define BZ_X_MAPPING_1 28 +#define BZ_X_MAPPING_2 29 +#define BZ_X_SELECTOR_1 30 +#define BZ_X_SELECTOR_2 31 +#define BZ_X_SELECTOR_3 32 +#define BZ_X_CODING_1 33 +#define BZ_X_CODING_2 34 +#define BZ_X_CODING_3 35 +#define BZ_X_MTF_1 36 +#define BZ_X_MTF_2 37 +#define BZ_X_MTF_3 38 +#define BZ_X_MTF_4 39 +#define BZ_X_MTF_5 40 +#define BZ_X_MTF_6 41 +#define BZ_X_ENDHDR_2 42 +#define BZ_X_ENDHDR_3 43 +#define BZ_X_ENDHDR_4 44 +#define BZ_X_ENDHDR_5 45 +#define BZ_X_ENDHDR_6 46 +#define BZ_X_CCRC_1 47 +#define BZ_X_CCRC_2 48 +#define BZ_X_CCRC_3 49 +#define BZ_X_CCRC_4 50 + + + +/*-- Constants for the fast MTF decoder. --*/ + +#define MTFA_SIZE 4096 +#define MTFL_SIZE 16 + + + +/*-- Structure holding all the decompression-side stuff. --*/ + +typedef + struct { + /* pointer back to the struct bz_stream */ + bz_stream* strm; + + /* state indicator for this stream */ + Int32 state; + + /* for doing the final run-length decoding */ + UChar state_out_ch; + Int32 state_out_len; + Bool blockRandomised; + BZ_RAND_DECLS; + + /* the buffer for bit stream reading */ + UInt32 bsBuff; + Int32 bsLive; + + /* misc administratium */ + Int32 blockSize100k; + Bool smallDecompress; + Int32 currBlockNo; + Int32 verbosity; + + /* for undoing the Burrows-Wheeler transform */ + Int32 origPtr; + UInt32 tPos; + Int32 k0; + Int32 unzftab[256]; + Int32 nblock_used; + Int32 cftab[257]; + Int32 cftabCopy[257]; + + /* for undoing the Burrows-Wheeler transform (FAST) */ + UInt32 *tt; + + /* for undoing the Burrows-Wheeler transform (SMALL) */ + UInt16 *ll16; + UChar *ll4; + + /* stored and calculated CRCs */ + UInt32 storedBlockCRC; + UInt32 storedCombinedCRC; + UInt32 calculatedBlockCRC; + UInt32 calculatedCombinedCRC; + + /* map of bytes used in block */ + Int32 nInUse; + Bool inUse[256]; + Bool inUse16[16]; + UChar seqToUnseq[256]; + + /* for decoding the MTF values */ + UChar mtfa [MTFA_SIZE]; + Int32 mtfbase[256 / MTFL_SIZE]; + UChar selector [BZ_MAX_SELECTORS]; + UChar selectorMtf[BZ_MAX_SELECTORS]; + UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + + Int32 limit [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + Int32 base [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + Int32 perm [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + Int32 minLens[BZ_N_GROUPS]; + + /* save area for scalars in the main decompress code */ + Int32 save_i; + Int32 save_j; + Int32 save_t; + Int32 save_alphaSize; + Int32 save_nGroups; + Int32 save_nSelectors; + Int32 save_EOB; + Int32 save_groupNo; + Int32 save_groupPos; + Int32 save_nextSym; + Int32 save_nblockMAX; + Int32 save_nblock; + Int32 save_es; + Int32 save_N; + Int32 save_curr; + Int32 save_zt; + Int32 save_zn; + Int32 save_zvec; + Int32 save_zj; + Int32 save_gSel; + Int32 save_gMinlen; + Int32* save_gLimit; + Int32* save_gBase; + Int32* save_gPerm; + + } + DState; + + + +/*-- Macros for decompression. --*/ + +#define BZ_GET_FAST(cccc) \ + s->tPos = s->tt[s->tPos]; \ + cccc = (UChar)(s->tPos & 0xff); \ + s->tPos >>= 8; + +#define BZ_GET_FAST_C(cccc) \ + c_tPos = c_tt[c_tPos]; \ + cccc = (UChar)(c_tPos & 0xff); \ + c_tPos >>= 8; + +#define SET_LL4(i,n) \ + { if (((i) & 0x1) == 0) \ + s->ll4[(i) >> 1] = (s->ll4[(i) >> 1] & 0xf0) | (n); else \ + s->ll4[(i) >> 1] = (s->ll4[(i) >> 1] & 0x0f) | ((n) << 4); \ + } + +#define GET_LL4(i) \ + ((((UInt32)(s->ll4[(i) >> 1])) >> (((i) << 2) & 0x4)) & 0xF) + +#define SET_LL(i,n) \ + { s->ll16[i] = (UInt16)(n & 0x0000ffff); \ + SET_LL4(i, n >> 16); \ + } + +#define GET_LL(i) \ + (((UInt32)s->ll16[i]) | (GET_LL4(i) << 16)) + +#define BZ_GET_SMALL(cccc) \ + cccc = BZ2_indexIntoF ( s->tPos, s->cftab ); \ + s->tPos = GET_LL(s->tPos); + + +/*-- externs for decompression. --*/ + +extern Int32 +BZ2_indexIntoF ( Int32, Int32* ); + +extern Int32 +BZ2_decompress ( DState* ); + +extern void +BZ2_hbCreateDecodeTables ( Int32*, Int32*, Int32*, UChar*, + Int32, Int32, Int32 ); + + +#endif + + +/*-- BZ_NO_STDIO seems to make NULL disappear on some platforms. --*/ + +#ifdef BZ_NO_STDIO +#ifndef NULL +#define NULL 0 +#endif +#endif + + +/*-------------------------------------------------------------*/ +/*--- end bzlib_private.h ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/compress.c b/bzip2/compress.c new file mode 100644 index 0000000..56501c1 --- /dev/null +++ b/bzip2/compress.c @@ -0,0 +1,714 @@ + +/*-------------------------------------------------------------*/ +/*--- Compression machinery (not incl block sorting) ---*/ +/*--- compress.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + +/*-- + CHANGES + ~~~~~~~ + 0.9.0 -- original version. + + 0.9.0a/b -- no changes in this file. + + 0.9.0c + * changed setting of nGroups in sendMTFValues() so as to + do a bit better on small files +--*/ + +#include "bzlib_private.h" + + +/*---------------------------------------------------*/ +/*--- Bit stream I/O ---*/ +/*---------------------------------------------------*/ + +/*---------------------------------------------------*/ +void BZ2_bsInitWrite ( EState* s ) +{ + s->bsLive = 0; + s->bsBuff = 0; +} + + +/*---------------------------------------------------*/ +static +void bsFinishWrite ( EState* s ) +{ + while (s->bsLive > 0) { + s->zbits[s->numZ] = (UChar)(s->bsBuff >> 24); + s->numZ++; + s->bsBuff <<= 8; + s->bsLive -= 8; + } +} + + +/*---------------------------------------------------*/ +#define bsNEEDW(nz) \ +{ \ + while (s->bsLive >= 8) { \ + s->zbits[s->numZ] \ + = (UChar)(s->bsBuff >> 24); \ + s->numZ++; \ + s->bsBuff <<= 8; \ + s->bsLive -= 8; \ + } \ +} + + +/*---------------------------------------------------*/ +static +__inline__ +void bsW ( EState* s, Int32 n, UInt32 v ) +{ + bsNEEDW ( n ); + s->bsBuff |= (v << (32 - s->bsLive - n)); + s->bsLive += n; +} + + +/*---------------------------------------------------*/ +static +void bsPutUInt32 ( EState* s, UInt32 u ) +{ + bsW ( s, 8, (u >> 24) & 0xffL ); + bsW ( s, 8, (u >> 16) & 0xffL ); + bsW ( s, 8, (u >> 8) & 0xffL ); + bsW ( s, 8, u & 0xffL ); +} + + +/*---------------------------------------------------*/ +static +void bsPutUChar ( EState* s, UChar c ) +{ + bsW( s, 8, (UInt32)c ); +} + + +/*---------------------------------------------------*/ +/*--- The back end proper ---*/ +/*---------------------------------------------------*/ + +/*---------------------------------------------------*/ +static +void makeMaps_e ( EState* s ) +{ + Int32 i; + s->nInUse = 0; + for (i = 0; i < 256; i++) + if (s->inUse[i]) { + s->unseqToSeq[i] = s->nInUse; + s->nInUse++; + } +} + + +/*---------------------------------------------------*/ +static +void generateMTFValues ( EState* s ) +{ + UChar yy[256]; + Int32 i, j; + Int32 zPend; + Int32 wr; + Int32 EOB; + + /* + After sorting (eg, here), + s->arr1 [ 0 .. s->nblock-1 ] holds sorted order, + and + ((UChar*)s->arr2) [ 0 .. s->nblock-1 ] + holds the original block data. + + The first thing to do is generate the MTF values, + and put them in + ((UInt16*)s->arr1) [ 0 .. s->nblock-1 ]. + Because there are strictly fewer or equal MTF values + than block values, ptr values in this area are overwritten + with MTF values only when they are no longer needed. + + The final compressed bitstream is generated into the + area starting at + (UChar*) (&((UChar*)s->arr2)[s->nblock]) + + These storage aliases are set up in bzCompressInit(), + except for the last one, which is arranged in + compressBlock(). + */ + UInt32* ptr = s->ptr; + UChar* block = s->block; + UInt16* mtfv = s->mtfv; + + makeMaps_e ( s ); + EOB = s->nInUse+1; + + for (i = 0; i <= EOB; i++) s->mtfFreq[i] = 0; + + wr = 0; + zPend = 0; + for (i = 0; i < s->nInUse; i++) yy[i] = (UChar) i; + + for (i = 0; i < s->nblock; i++) { + UChar ll_i; + AssertD ( wr <= i, "generateMTFValues(1)" ); + j = ptr[i]-1; if (j < 0) j += s->nblock; + ll_i = s->unseqToSeq[block[j]]; + AssertD ( ll_i < s->nInUse, "generateMTFValues(2a)" ); + + if (yy[0] == ll_i) { + zPend++; + } else { + + if (zPend > 0) { + zPend--; + while (True) { + if (zPend & 1) { + mtfv[wr] = BZ_RUNB; wr++; + s->mtfFreq[BZ_RUNB]++; + } else { + mtfv[wr] = BZ_RUNA; wr++; + s->mtfFreq[BZ_RUNA]++; + } + if (zPend < 2) break; + zPend = (zPend - 2) / 2; + }; + zPend = 0; + } + { + register UChar rtmp; + register UChar* ryy_j; + register UChar rll_i; + rtmp = yy[1]; + yy[1] = yy[0]; + ryy_j = &(yy[1]); + rll_i = ll_i; + while ( rll_i != rtmp ) { + register UChar rtmp2; + ryy_j++; + rtmp2 = rtmp; + rtmp = *ryy_j; + *ryy_j = rtmp2; + }; + yy[0] = rtmp; + j = ryy_j - &(yy[0]); + mtfv[wr] = j+1; wr++; s->mtfFreq[j+1]++; + } + + } + } + + if (zPend > 0) { + zPend--; + while (True) { + if (zPend & 1) { + mtfv[wr] = BZ_RUNB; wr++; + s->mtfFreq[BZ_RUNB]++; + } else { + mtfv[wr] = BZ_RUNA; wr++; + s->mtfFreq[BZ_RUNA]++; + } + if (zPend < 2) break; + zPend = (zPend - 2) / 2; + }; + zPend = 0; + } + + mtfv[wr] = EOB; wr++; s->mtfFreq[EOB]++; + + s->nMTF = wr; +} + + +/*---------------------------------------------------*/ +#define BZ_LESSER_ICOST 0 +#define BZ_GREATER_ICOST 15 + +static +void sendMTFValues ( EState* s ) +{ + Int32 v, t, i, j, gs, ge, totc, bt, bc, iter; + Int32 nSelectors, alphaSize, minLen, maxLen, selCtr; + Int32 nGroups, nBytes; + + /*-- + UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + is a global since the decoder also needs it. + + Int32 code[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + Int32 rfreq[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE]; + are also globals only used in this proc. + Made global to keep stack frame size small. + --*/ + + + UInt16 cost[BZ_N_GROUPS]; + Int32 fave[BZ_N_GROUPS]; + + UInt16* mtfv = s->mtfv; + + if (s->verbosity >= 3) + VPrintf3( " %d in block, %d after MTF & 1-2 coding, " + "%d+2 syms in use\n", + s->nblock, s->nMTF, s->nInUse ); + + alphaSize = s->nInUse+2; + for (t = 0; t < BZ_N_GROUPS; t++) + for (v = 0; v < alphaSize; v++) + s->len[t][v] = BZ_GREATER_ICOST; + + /*--- Decide how many coding tables to use ---*/ + AssertH ( s->nMTF > 0, 3001 ); + if (s->nMTF < 200) nGroups = 2; else + if (s->nMTF < 600) nGroups = 3; else + if (s->nMTF < 1200) nGroups = 4; else + if (s->nMTF < 2400) nGroups = 5; else + nGroups = 6; + + /*--- Generate an initial set of coding tables ---*/ + { + Int32 nPart, remF, tFreq, aFreq; + + nPart = nGroups; + remF = s->nMTF; + gs = 0; + while (nPart > 0) { + tFreq = remF / nPart; + ge = gs-1; + aFreq = 0; + while (aFreq < tFreq && ge < alphaSize-1) { + ge++; + aFreq += s->mtfFreq[ge]; + } + + if (ge > gs + && nPart != nGroups && nPart != 1 + && ((nGroups-nPart) % 2 == 1)) { + aFreq -= s->mtfFreq[ge]; + ge--; + } + + if (s->verbosity >= 3) + VPrintf5( " initial group %d, [%d .. %d], " + "has %d syms (%4.1f%%)\n", + nPart, gs, ge, aFreq, + (100.0 * (float)aFreq) / (float)(s->nMTF) ); + + for (v = 0; v < alphaSize; v++) + if (v >= gs && v <= ge) + s->len[nPart-1][v] = BZ_LESSER_ICOST; else + s->len[nPart-1][v] = BZ_GREATER_ICOST; + + nPart--; + gs = ge+1; + remF -= aFreq; + } + } + + /*--- + Iterate up to BZ_N_ITERS times to improve the tables. + ---*/ + for (iter = 0; iter < BZ_N_ITERS; iter++) { + + for (t = 0; t < nGroups; t++) fave[t] = 0; + + for (t = 0; t < nGroups; t++) + for (v = 0; v < alphaSize; v++) + s->rfreq[t][v] = 0; + + /*--- + Set up an auxiliary length table which is used to fast-track + the common case (nGroups == 6). + ---*/ + if (nGroups == 6) { + for (v = 0; v < alphaSize; v++) { + s->len_pack[v][0] = (s->len[1][v] << 16) | s->len[0][v]; + s->len_pack[v][1] = (s->len[3][v] << 16) | s->len[2][v]; + s->len_pack[v][2] = (s->len[5][v] << 16) | s->len[4][v]; + } + } + + nSelectors = 0; + totc = 0; + gs = 0; + while (True) { + + /*--- Set group start & end marks. --*/ + if (gs >= s->nMTF) break; + ge = gs + BZ_G_SIZE - 1; + if (ge >= s->nMTF) ge = s->nMTF-1; + + /*-- + Calculate the cost of this group as coded + by each of the coding tables. + --*/ + for (t = 0; t < nGroups; t++) cost[t] = 0; + + if (nGroups == 6 && 50 == ge-gs+1) { + /*--- fast track the common case ---*/ + register UInt32 cost01, cost23, cost45; + register UInt16 icv; + cost01 = cost23 = cost45 = 0; + +# define BZ_ITER(nn) \ + icv = mtfv[gs+(nn)]; \ + cost01 += s->len_pack[icv][0]; \ + cost23 += s->len_pack[icv][1]; \ + cost45 += s->len_pack[icv][2]; \ + + BZ_ITER(0); BZ_ITER(1); BZ_ITER(2); BZ_ITER(3); BZ_ITER(4); + BZ_ITER(5); BZ_ITER(6); BZ_ITER(7); BZ_ITER(8); BZ_ITER(9); + BZ_ITER(10); BZ_ITER(11); BZ_ITER(12); BZ_ITER(13); BZ_ITER(14); + BZ_ITER(15); BZ_ITER(16); BZ_ITER(17); BZ_ITER(18); BZ_ITER(19); + BZ_ITER(20); BZ_ITER(21); BZ_ITER(22); BZ_ITER(23); BZ_ITER(24); + BZ_ITER(25); BZ_ITER(26); BZ_ITER(27); BZ_ITER(28); BZ_ITER(29); + BZ_ITER(30); BZ_ITER(31); BZ_ITER(32); BZ_ITER(33); BZ_ITER(34); + BZ_ITER(35); BZ_ITER(36); BZ_ITER(37); BZ_ITER(38); BZ_ITER(39); + BZ_ITER(40); BZ_ITER(41); BZ_ITER(42); BZ_ITER(43); BZ_ITER(44); + BZ_ITER(45); BZ_ITER(46); BZ_ITER(47); BZ_ITER(48); BZ_ITER(49); + +# undef BZ_ITER + + cost[0] = cost01 & 0xffff; cost[1] = cost01 >> 16; + cost[2] = cost23 & 0xffff; cost[3] = cost23 >> 16; + cost[4] = cost45 & 0xffff; cost[5] = cost45 >> 16; + + } else { + /*--- slow version which correctly handles all situations ---*/ + for (i = gs; i <= ge; i++) { + UInt16 icv = mtfv[i]; + for (t = 0; t < nGroups; t++) cost[t] += s->len[t][icv]; + } + } + + /*-- + Find the coding table which is best for this group, + and record its identity in the selector table. + --*/ + bc = 999999999; bt = -1; + for (t = 0; t < nGroups; t++) + if (cost[t] < bc) { bc = cost[t]; bt = t; }; + totc += bc; + fave[bt]++; + s->selector[nSelectors] = bt; + nSelectors++; + + /*-- + Increment the symbol frequencies for the selected table. + --*/ + if (nGroups == 6 && 50 == ge-gs+1) { + /*--- fast track the common case ---*/ + +# define BZ_ITUR(nn) s->rfreq[bt][ mtfv[gs+(nn)] ]++ + + BZ_ITUR(0); BZ_ITUR(1); BZ_ITUR(2); BZ_ITUR(3); BZ_ITUR(4); + BZ_ITUR(5); BZ_ITUR(6); BZ_ITUR(7); BZ_ITUR(8); BZ_ITUR(9); + BZ_ITUR(10); BZ_ITUR(11); BZ_ITUR(12); BZ_ITUR(13); BZ_ITUR(14); + BZ_ITUR(15); BZ_ITUR(16); BZ_ITUR(17); BZ_ITUR(18); BZ_ITUR(19); + BZ_ITUR(20); BZ_ITUR(21); BZ_ITUR(22); BZ_ITUR(23); BZ_ITUR(24); + BZ_ITUR(25); BZ_ITUR(26); BZ_ITUR(27); BZ_ITUR(28); BZ_ITUR(29); + BZ_ITUR(30); BZ_ITUR(31); BZ_ITUR(32); BZ_ITUR(33); BZ_ITUR(34); + BZ_ITUR(35); BZ_ITUR(36); BZ_ITUR(37); BZ_ITUR(38); BZ_ITUR(39); + BZ_ITUR(40); BZ_ITUR(41); BZ_ITUR(42); BZ_ITUR(43); BZ_ITUR(44); + BZ_ITUR(45); BZ_ITUR(46); BZ_ITUR(47); BZ_ITUR(48); BZ_ITUR(49); + +# undef BZ_ITUR + + } else { + /*--- slow version which correctly handles all situations ---*/ + for (i = gs; i <= ge; i++) + s->rfreq[bt][ mtfv[i] ]++; + } + + gs = ge+1; + } + if (s->verbosity >= 3) { + VPrintf2 ( " pass %d: size is %d, grp uses are ", + iter+1, totc/8 ); + for (t = 0; t < nGroups; t++) + VPrintf1 ( "%d ", fave[t] ); + VPrintf0 ( "\n" ); + } + + /*-- + Recompute the tables based on the accumulated frequencies. + --*/ + for (t = 0; t < nGroups; t++) + BZ2_hbMakeCodeLengths ( &(s->len[t][0]), &(s->rfreq[t][0]), + alphaSize, 20 ); + } + + + AssertH( nGroups < 8, 3002 ); + AssertH( nSelectors < 32768 && + nSelectors <= (2 + (900000 / BZ_G_SIZE)), + 3003 ); + + + /*--- Compute MTF values for the selectors. ---*/ + { + UChar pos[BZ_N_GROUPS], ll_i, tmp2, tmp; + for (i = 0; i < nGroups; i++) pos[i] = i; + for (i = 0; i < nSelectors; i++) { + ll_i = s->selector[i]; + j = 0; + tmp = pos[j]; + while ( ll_i != tmp ) { + j++; + tmp2 = tmp; + tmp = pos[j]; + pos[j] = tmp2; + }; + pos[0] = tmp; + s->selectorMtf[i] = j; + } + }; + + /*--- Assign actual codes for the tables. --*/ + for (t = 0; t < nGroups; t++) { + minLen = 32; + maxLen = 0; + for (i = 0; i < alphaSize; i++) { + if (s->len[t][i] > maxLen) maxLen = s->len[t][i]; + if (s->len[t][i] < minLen) minLen = s->len[t][i]; + } + AssertH ( !(maxLen > 20), 3004 ); + AssertH ( !(minLen < 1), 3005 ); + BZ2_hbAssignCodes ( &(s->code[t][0]), &(s->len[t][0]), + minLen, maxLen, alphaSize ); + } + + /*--- Transmit the mapping table. ---*/ + { + Bool inUse16[16]; + for (i = 0; i < 16; i++) { + inUse16[i] = False; + for (j = 0; j < 16; j++) + if (s->inUse[i * 16 + j]) inUse16[i] = True; + } + + nBytes = s->numZ; + for (i = 0; i < 16; i++) + if (inUse16[i]) bsW(s,1,1); else bsW(s,1,0); + + for (i = 0; i < 16; i++) + if (inUse16[i]) + for (j = 0; j < 16; j++) { + if (s->inUse[i * 16 + j]) bsW(s,1,1); else bsW(s,1,0); + } + + if (s->verbosity >= 3) + VPrintf1( " bytes: mapping %d, ", s->numZ-nBytes ); + } + + /*--- Now the selectors. ---*/ + nBytes = s->numZ; + bsW ( s, 3, nGroups ); + bsW ( s, 15, nSelectors ); + for (i = 0; i < nSelectors; i++) { + for (j = 0; j < s->selectorMtf[i]; j++) bsW(s,1,1); + bsW(s,1,0); + } + if (s->verbosity >= 3) + VPrintf1( "selectors %d, ", s->numZ-nBytes ); + + /*--- Now the coding tables. ---*/ + nBytes = s->numZ; + + for (t = 0; t < nGroups; t++) { + Int32 curr = s->len[t][0]; + bsW ( s, 5, curr ); + for (i = 0; i < alphaSize; i++) { + while (curr < s->len[t][i]) { bsW(s,2,2); curr++; /* 10 */ }; + while (curr > s->len[t][i]) { bsW(s,2,3); curr--; /* 11 */ }; + bsW ( s, 1, 0 ); + } + } + + if (s->verbosity >= 3) + VPrintf1 ( "code lengths %d, ", s->numZ-nBytes ); + + /*--- And finally, the block data proper ---*/ + nBytes = s->numZ; + selCtr = 0; + gs = 0; + while (True) { + if (gs >= s->nMTF) break; + ge = gs + BZ_G_SIZE - 1; + if (ge >= s->nMTF) ge = s->nMTF-1; + AssertH ( s->selector[selCtr] < nGroups, 3006 ); + + if (nGroups == 6 && 50 == ge-gs+1) { + /*--- fast track the common case ---*/ + UInt16 mtfv_i; + UChar* s_len_sel_selCtr + = &(s->len[s->selector[selCtr]][0]); + Int32* s_code_sel_selCtr + = &(s->code[s->selector[selCtr]][0]); + +# define BZ_ITAH(nn) \ + mtfv_i = mtfv[gs+(nn)]; \ + bsW ( s, \ + s_len_sel_selCtr[mtfv_i], \ + s_code_sel_selCtr[mtfv_i] ) + + BZ_ITAH(0); BZ_ITAH(1); BZ_ITAH(2); BZ_ITAH(3); BZ_ITAH(4); + BZ_ITAH(5); BZ_ITAH(6); BZ_ITAH(7); BZ_ITAH(8); BZ_ITAH(9); + BZ_ITAH(10); BZ_ITAH(11); BZ_ITAH(12); BZ_ITAH(13); BZ_ITAH(14); + BZ_ITAH(15); BZ_ITAH(16); BZ_ITAH(17); BZ_ITAH(18); BZ_ITAH(19); + BZ_ITAH(20); BZ_ITAH(21); BZ_ITAH(22); BZ_ITAH(23); BZ_ITAH(24); + BZ_ITAH(25); BZ_ITAH(26); BZ_ITAH(27); BZ_ITAH(28); BZ_ITAH(29); + BZ_ITAH(30); BZ_ITAH(31); BZ_ITAH(32); BZ_ITAH(33); BZ_ITAH(34); + BZ_ITAH(35); BZ_ITAH(36); BZ_ITAH(37); BZ_ITAH(38); BZ_ITAH(39); + BZ_ITAH(40); BZ_ITAH(41); BZ_ITAH(42); BZ_ITAH(43); BZ_ITAH(44); + BZ_ITAH(45); BZ_ITAH(46); BZ_ITAH(47); BZ_ITAH(48); BZ_ITAH(49); + +# undef BZ_ITAH + + } else { + /*--- slow version which correctly handles all situations ---*/ + for (i = gs; i <= ge; i++) { + bsW ( s, + s->len [s->selector[selCtr]] [mtfv[i]], + s->code [s->selector[selCtr]] [mtfv[i]] ); + } + } + + + gs = ge+1; + selCtr++; + } + AssertH( selCtr == nSelectors, 3007 ); + + if (s->verbosity >= 3) + VPrintf1( "codes %d\n", s->numZ-nBytes ); +} + + +/*---------------------------------------------------*/ +void BZ2_compressBlock ( EState* s, Bool is_last_block ) +{ + if (s->nblock > 0) { + + BZ_FINALISE_CRC ( s->blockCRC ); + s->combinedCRC = (s->combinedCRC << 1) | (s->combinedCRC >> 31); + s->combinedCRC ^= s->blockCRC; + if (s->blockNo > 1) s->numZ = 0; + + if (s->verbosity >= 2) + VPrintf4( " block %d: crc = 0x%8x, " + "combined CRC = 0x%8x, size = %d\n", + s->blockNo, s->blockCRC, s->combinedCRC, s->nblock ); + + BZ2_blockSort ( s ); + } + + s->zbits = (UChar*) (&((UChar*)s->arr2)[s->nblock]); + + /*-- If this is the first block, create the stream header. --*/ + if (s->blockNo == 1) { + BZ2_bsInitWrite ( s ); + bsPutUChar ( s, BZ_HDR_B ); + bsPutUChar ( s, BZ_HDR_Z ); + bsPutUChar ( s, BZ_HDR_h ); + bsPutUChar ( s, (UChar)(BZ_HDR_0 + s->blockSize100k) ); + } + + if (s->nblock > 0) { + + bsPutUChar ( s, 0x31 ); bsPutUChar ( s, 0x41 ); + bsPutUChar ( s, 0x59 ); bsPutUChar ( s, 0x26 ); + bsPutUChar ( s, 0x53 ); bsPutUChar ( s, 0x59 ); + + /*-- Now the block's CRC, so it is in a known place. --*/ + bsPutUInt32 ( s, s->blockCRC ); + + /*-- + Now a single bit indicating (non-)randomisation. + As of version 0.9.5, we use a better sorting algorithm + which makes randomisation unnecessary. So always set + the randomised bit to 'no'. Of course, the decoder + still needs to be able to handle randomised blocks + so as to maintain backwards compatibility with + older versions of bzip2. + --*/ + bsW(s,1,0); + + bsW ( s, 24, s->origPtr ); + generateMTFValues ( s ); + sendMTFValues ( s ); + } + + + /*-- If this is the last block, add the stream trailer. --*/ + if (is_last_block) { + + bsPutUChar ( s, 0x17 ); bsPutUChar ( s, 0x72 ); + bsPutUChar ( s, 0x45 ); bsPutUChar ( s, 0x38 ); + bsPutUChar ( s, 0x50 ); bsPutUChar ( s, 0x90 ); + bsPutUInt32 ( s, s->combinedCRC ); + if (s->verbosity >= 2) + VPrintf1( " final combined CRC = 0x%x\n ", s->combinedCRC ); + bsFinishWrite ( s ); + } +} + + +/*-------------------------------------------------------------*/ +/*--- end compress.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/crctable.c b/bzip2/crctable.c new file mode 100644 index 0000000..9ae07f9 --- /dev/null +++ b/bzip2/crctable.c @@ -0,0 +1,144 @@ + +/*-------------------------------------------------------------*/ +/*--- Table for doing CRCs ---*/ +/*--- crctable.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + + +#include "bzlib_private.h" + +/*-- + I think this is an implementation of the AUTODIN-II, + Ethernet & FDDI 32-bit CRC standard. Vaguely derived + from code by Rob Warnock, in Section 51 of the + comp.compression FAQ. +--*/ + +UInt32 BZ2_crc32Table[256] = { + + /*-- Ugly, innit? --*/ + + 0x00000000L, 0x04c11db7L, 0x09823b6eL, 0x0d4326d9L, + 0x130476dcL, 0x17c56b6bL, 0x1a864db2L, 0x1e475005L, + 0x2608edb8L, 0x22c9f00fL, 0x2f8ad6d6L, 0x2b4bcb61L, + 0x350c9b64L, 0x31cd86d3L, 0x3c8ea00aL, 0x384fbdbdL, + 0x4c11db70L, 0x48d0c6c7L, 0x4593e01eL, 0x4152fda9L, + 0x5f15adacL, 0x5bd4b01bL, 0x569796c2L, 0x52568b75L, + 0x6a1936c8L, 0x6ed82b7fL, 0x639b0da6L, 0x675a1011L, + 0x791d4014L, 0x7ddc5da3L, 0x709f7b7aL, 0x745e66cdL, + 0x9823b6e0L, 0x9ce2ab57L, 0x91a18d8eL, 0x95609039L, + 0x8b27c03cL, 0x8fe6dd8bL, 0x82a5fb52L, 0x8664e6e5L, + 0xbe2b5b58L, 0xbaea46efL, 0xb7a96036L, 0xb3687d81L, + 0xad2f2d84L, 0xa9ee3033L, 0xa4ad16eaL, 0xa06c0b5dL, + 0xd4326d90L, 0xd0f37027L, 0xddb056feL, 0xd9714b49L, + 0xc7361b4cL, 0xc3f706fbL, 0xceb42022L, 0xca753d95L, + 0xf23a8028L, 0xf6fb9d9fL, 0xfbb8bb46L, 0xff79a6f1L, + 0xe13ef6f4L, 0xe5ffeb43L, 0xe8bccd9aL, 0xec7dd02dL, + 0x34867077L, 0x30476dc0L, 0x3d044b19L, 0x39c556aeL, + 0x278206abL, 0x23431b1cL, 0x2e003dc5L, 0x2ac12072L, + 0x128e9dcfL, 0x164f8078L, 0x1b0ca6a1L, 0x1fcdbb16L, + 0x018aeb13L, 0x054bf6a4L, 0x0808d07dL, 0x0cc9cdcaL, + 0x7897ab07L, 0x7c56b6b0L, 0x71159069L, 0x75d48ddeL, + 0x6b93dddbL, 0x6f52c06cL, 0x6211e6b5L, 0x66d0fb02L, + 0x5e9f46bfL, 0x5a5e5b08L, 0x571d7dd1L, 0x53dc6066L, + 0x4d9b3063L, 0x495a2dd4L, 0x44190b0dL, 0x40d816baL, + 0xaca5c697L, 0xa864db20L, 0xa527fdf9L, 0xa1e6e04eL, + 0xbfa1b04bL, 0xbb60adfcL, 0xb6238b25L, 0xb2e29692L, + 0x8aad2b2fL, 0x8e6c3698L, 0x832f1041L, 0x87ee0df6L, + 0x99a95df3L, 0x9d684044L, 0x902b669dL, 0x94ea7b2aL, + 0xe0b41de7L, 0xe4750050L, 0xe9362689L, 0xedf73b3eL, + 0xf3b06b3bL, 0xf771768cL, 0xfa325055L, 0xfef34de2L, + 0xc6bcf05fL, 0xc27dede8L, 0xcf3ecb31L, 0xcbffd686L, + 0xd5b88683L, 0xd1799b34L, 0xdc3abdedL, 0xd8fba05aL, + 0x690ce0eeL, 0x6dcdfd59L, 0x608edb80L, 0x644fc637L, + 0x7a089632L, 0x7ec98b85L, 0x738aad5cL, 0x774bb0ebL, + 0x4f040d56L, 0x4bc510e1L, 0x46863638L, 0x42472b8fL, + 0x5c007b8aL, 0x58c1663dL, 0x558240e4L, 0x51435d53L, + 0x251d3b9eL, 0x21dc2629L, 0x2c9f00f0L, 0x285e1d47L, + 0x36194d42L, 0x32d850f5L, 0x3f9b762cL, 0x3b5a6b9bL, + 0x0315d626L, 0x07d4cb91L, 0x0a97ed48L, 0x0e56f0ffL, + 0x1011a0faL, 0x14d0bd4dL, 0x19939b94L, 0x1d528623L, + 0xf12f560eL, 0xf5ee4bb9L, 0xf8ad6d60L, 0xfc6c70d7L, + 0xe22b20d2L, 0xe6ea3d65L, 0xeba91bbcL, 0xef68060bL, + 0xd727bbb6L, 0xd3e6a601L, 0xdea580d8L, 0xda649d6fL, + 0xc423cd6aL, 0xc0e2d0ddL, 0xcda1f604L, 0xc960ebb3L, + 0xbd3e8d7eL, 0xb9ff90c9L, 0xb4bcb610L, 0xb07daba7L, + 0xae3afba2L, 0xaafbe615L, 0xa7b8c0ccL, 0xa379dd7bL, + 0x9b3660c6L, 0x9ff77d71L, 0x92b45ba8L, 0x9675461fL, + 0x8832161aL, 0x8cf30badL, 0x81b02d74L, 0x857130c3L, + 0x5d8a9099L, 0x594b8d2eL, 0x5408abf7L, 0x50c9b640L, + 0x4e8ee645L, 0x4a4ffbf2L, 0x470cdd2bL, 0x43cdc09cL, + 0x7b827d21L, 0x7f436096L, 0x7200464fL, 0x76c15bf8L, + 0x68860bfdL, 0x6c47164aL, 0x61043093L, 0x65c52d24L, + 0x119b4be9L, 0x155a565eL, 0x18197087L, 0x1cd86d30L, + 0x029f3d35L, 0x065e2082L, 0x0b1d065bL, 0x0fdc1becL, + 0x3793a651L, 0x3352bbe6L, 0x3e119d3fL, 0x3ad08088L, + 0x2497d08dL, 0x2056cd3aL, 0x2d15ebe3L, 0x29d4f654L, + 0xc5a92679L, 0xc1683bceL, 0xcc2b1d17L, 0xc8ea00a0L, + 0xd6ad50a5L, 0xd26c4d12L, 0xdf2f6bcbL, 0xdbee767cL, + 0xe3a1cbc1L, 0xe760d676L, 0xea23f0afL, 0xeee2ed18L, + 0xf0a5bd1dL, 0xf464a0aaL, 0xf9278673L, 0xfde69bc4L, + 0x89b8fd09L, 0x8d79e0beL, 0x803ac667L, 0x84fbdbd0L, + 0x9abc8bd5L, 0x9e7d9662L, 0x933eb0bbL, 0x97ffad0cL, + 0xafb010b1L, 0xab710d06L, 0xa6322bdfL, 0xa2f33668L, + 0xbcb4666dL, 0xb8757bdaL, 0xb5365d03L, 0xb1f740b4L +}; + + +/*-------------------------------------------------------------*/ +/*--- end crctable.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/huffman.c b/bzip2/huffman.c new file mode 100644 index 0000000..293095c --- /dev/null +++ b/bzip2/huffman.c @@ -0,0 +1,228 @@ + +/*-------------------------------------------------------------*/ +/*--- Huffman coding low-level stuff ---*/ +/*--- huffman.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + + +#include "bzlib_private.h" + +/*---------------------------------------------------*/ +#define WEIGHTOF(zz0) ((zz0) & 0xffffff00) +#define DEPTHOF(zz1) ((zz1) & 0x000000ff) +#define MYMAX(zz2,zz3) ((zz2) > (zz3) ? (zz2) : (zz3)) + +#define ADDWEIGHTS(zw1,zw2) \ + (WEIGHTOF(zw1)+WEIGHTOF(zw2)) | \ + (1 + MYMAX(DEPTHOF(zw1),DEPTHOF(zw2))) + +#define UPHEAP(z) \ +{ \ + Int32 zz, tmp; \ + zz = z; tmp = heap[zz]; \ + while (weight[tmp] < weight[heap[zz >> 1]]) { \ + heap[zz] = heap[zz >> 1]; \ + zz >>= 1; \ + } \ + heap[zz] = tmp; \ +} + +#define DOWNHEAP(z) \ +{ \ + Int32 zz, yy, tmp; \ + zz = z; tmp = heap[zz]; \ + while (True) { \ + yy = zz << 1; \ + if (yy > nHeap) break; \ + if (yy < nHeap && \ + weight[heap[yy+1]] < weight[heap[yy]]) \ + yy++; \ + if (weight[tmp] < weight[heap[yy]]) break; \ + heap[zz] = heap[yy]; \ + zz = yy; \ + } \ + heap[zz] = tmp; \ +} + + +/*---------------------------------------------------*/ +void BZ2_hbMakeCodeLengths ( UChar *len, + Int32 *freq, + Int32 alphaSize, + Int32 maxLen ) +{ + /*-- + Nodes and heap entries run from 1. Entry 0 + for both the heap and nodes is a sentinel. + --*/ + Int32 nNodes, nHeap, n1, n2, i, j, k; + Bool tooLong; + + Int32 heap [ BZ_MAX_ALPHA_SIZE + 2 ]; + Int32 weight [ BZ_MAX_ALPHA_SIZE * 2 ]; + Int32 parent [ BZ_MAX_ALPHA_SIZE * 2 ]; + + for (i = 0; i < alphaSize; i++) + weight[i+1] = (freq[i] == 0 ? 1 : freq[i]) << 8; + + while (True) { + + nNodes = alphaSize; + nHeap = 0; + + heap[0] = 0; + weight[0] = 0; + parent[0] = -2; + + for (i = 1; i <= alphaSize; i++) { + parent[i] = -1; + nHeap++; + heap[nHeap] = i; + UPHEAP(nHeap); + } + + AssertH( nHeap < (BZ_MAX_ALPHA_SIZE+2), 2001 ); + + while (nHeap > 1) { + n1 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1); + n2 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1); + nNodes++; + parent[n1] = parent[n2] = nNodes; + weight[nNodes] = ADDWEIGHTS(weight[n1], weight[n2]); + parent[nNodes] = -1; + nHeap++; + heap[nHeap] = nNodes; + UPHEAP(nHeap); + } + + AssertH( nNodes < (BZ_MAX_ALPHA_SIZE * 2), 2002 ); + + tooLong = False; + for (i = 1; i <= alphaSize; i++) { + j = 0; + k = i; + while (parent[k] >= 0) { k = parent[k]; j++; } + len[i-1] = j; + if (j > maxLen) tooLong = True; + } + + if (! tooLong) break; + + for (i = 1; i < alphaSize; i++) { + j = weight[i] >> 8; + j = 1 + (j / 2); + weight[i] = j << 8; + } + } +} + + +/*---------------------------------------------------*/ +void BZ2_hbAssignCodes ( Int32 *code, + UChar *length, + Int32 minLen, + Int32 maxLen, + Int32 alphaSize ) +{ + Int32 n, vec, i; + + vec = 0; + for (n = minLen; n <= maxLen; n++) { + for (i = 0; i < alphaSize; i++) + if (length[i] == n) { code[i] = vec; vec++; }; + vec <<= 1; + } +} + + +/*---------------------------------------------------*/ +void BZ2_hbCreateDecodeTables ( Int32 *limit, + Int32 *base, + Int32 *perm, + UChar *length, + Int32 minLen, + Int32 maxLen, + Int32 alphaSize ) +{ + Int32 pp, i, j, vec; + + pp = 0; + for (i = minLen; i <= maxLen; i++) + for (j = 0; j < alphaSize; j++) + if (length[j] == i) { perm[pp] = j; pp++; }; + + for (i = 0; i < BZ_MAX_CODE_LEN; i++) base[i] = 0; + for (i = 0; i < alphaSize; i++) base[length[i]+1]++; + + for (i = 1; i < BZ_MAX_CODE_LEN; i++) base[i] += base[i-1]; + + for (i = 0; i < BZ_MAX_CODE_LEN; i++) limit[i] = 0; + vec = 0; + + for (i = minLen; i <= maxLen; i++) { + vec += (base[i+1] - base[i]); + limit[i] = vec-1; + vec <<= 1; + } + for (i = minLen + 1; i <= maxLen; i++) + base[i] = ((limit[i-1] + 1) << 1) - base[i]; +} + + +/*-------------------------------------------------------------*/ +/*--- end huffman.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/bzip2/randtable.c b/bzip2/randtable.c new file mode 100644 index 0000000..14fe1f6 --- /dev/null +++ b/bzip2/randtable.c @@ -0,0 +1,124 @@ + +/*-------------------------------------------------------------*/ +/*--- Table for randomising repetitive blocks ---*/ +/*--- randtable.c ---*/ +/*-------------------------------------------------------------*/ + +/*-- + This file is a part of bzip2 and/or libbzip2, a program and + library for lossless, block-sorting data compression. + + Copyright (C) 1996-2002 Julian R Seward. All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. The origin of this software must not be misrepresented; you must + not claim that you wrote the original software. If you use this + software in a product, an acknowledgment in the product + documentation would be appreciated but is not required. + + 3. Altered source versions must be plainly marked as such, and must + not be misrepresented as being the original software. + + 4. The name of the author may not be used to endorse or promote + products derived from this software without specific prior written + permission. + + THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS + OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE + GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + Julian Seward, Cambridge, UK. + jseward@acm.org + bzip2/libbzip2 version 1.0 of 21 March 2000 + + This program is based on (at least) the work of: + Mike Burrows + David Wheeler + Peter Fenwick + Alistair Moffat + Radford Neal + Ian H. Witten + Robert Sedgewick + Jon L. Bentley + + For more information on these sources, see the manual. +--*/ + + +#include "bzlib_private.h" + + +/*---------------------------------------------*/ +Int32 BZ2_rNums[512] = { + 619, 720, 127, 481, 931, 816, 813, 233, 566, 247, + 985, 724, 205, 454, 863, 491, 741, 242, 949, 214, + 733, 859, 335, 708, 621, 574, 73, 654, 730, 472, + 419, 436, 278, 496, 867, 210, 399, 680, 480, 51, + 878, 465, 811, 169, 869, 675, 611, 697, 867, 561, + 862, 687, 507, 283, 482, 129, 807, 591, 733, 623, + 150, 238, 59, 379, 684, 877, 625, 169, 643, 105, + 170, 607, 520, 932, 727, 476, 693, 425, 174, 647, + 73, 122, 335, 530, 442, 853, 695, 249, 445, 515, + 909, 545, 703, 919, 874, 474, 882, 500, 594, 612, + 641, 801, 220, 162, 819, 984, 589, 513, 495, 799, + 161, 604, 958, 533, 221, 400, 386, 867, 600, 782, + 382, 596, 414, 171, 516, 375, 682, 485, 911, 276, + 98, 553, 163, 354, 666, 933, 424, 341, 533, 870, + 227, 730, 475, 186, 263, 647, 537, 686, 600, 224, + 469, 68, 770, 919, 190, 373, 294, 822, 808, 206, + 184, 943, 795, 384, 383, 461, 404, 758, 839, 887, + 715, 67, 618, 276, 204, 918, 873, 777, 604, 560, + 951, 160, 578, 722, 79, 804, 96, 409, 713, 940, + 652, 934, 970, 447, 318, 353, 859, 672, 112, 785, + 645, 863, 803, 350, 139, 93, 354, 99, 820, 908, + 609, 772, 154, 274, 580, 184, 79, 626, 630, 742, + 653, 282, 762, 623, 680, 81, 927, 626, 789, 125, + 411, 521, 938, 300, 821, 78, 343, 175, 128, 250, + 170, 774, 972, 275, 999, 639, 495, 78, 352, 126, + 857, 956, 358, 619, 580, 124, 737, 594, 701, 612, + 669, 112, 134, 694, 363, 992, 809, 743, 168, 974, + 944, 375, 748, 52, 600, 747, 642, 182, 862, 81, + 344, 805, 988, 739, 511, 655, 814, 334, 249, 515, + 897, 955, 664, 981, 649, 113, 974, 459, 893, 228, + 433, 837, 553, 268, 926, 240, 102, 654, 459, 51, + 686, 754, 806, 760, 493, 403, 415, 394, 687, 700, + 946, 670, 656, 610, 738, 392, 760, 799, 887, 653, + 978, 321, 576, 617, 626, 502, 894, 679, 243, 440, + 680, 879, 194, 572, 640, 724, 926, 56, 204, 700, + 707, 151, 457, 449, 797, 195, 791, 558, 945, 679, + 297, 59, 87, 824, 713, 663, 412, 693, 342, 606, + 134, 108, 571, 364, 631, 212, 174, 643, 304, 329, + 343, 97, 430, 751, 497, 314, 983, 374, 822, 928, + 140, 206, 73, 263, 980, 736, 876, 478, 430, 305, + 170, 514, 364, 692, 829, 82, 855, 953, 676, 246, + 369, 970, 294, 750, 807, 827, 150, 790, 288, 923, + 804, 378, 215, 828, 592, 281, 565, 555, 710, 82, + 896, 831, 547, 261, 524, 462, 293, 465, 502, 56, + 661, 821, 976, 991, 658, 869, 905, 758, 745, 193, + 768, 550, 608, 933, 378, 286, 215, 979, 792, 961, + 61, 688, 793, 644, 986, 403, 106, 366, 905, 644, + 372, 567, 466, 434, 645, 210, 389, 550, 919, 135, + 780, 773, 635, 389, 707, 100, 626, 958, 165, 504, + 920, 176, 193, 713, 857, 265, 203, 50, 668, 108, + 645, 990, 626, 197, 510, 357, 358, 850, 858, 364, + 936, 638 +}; + + +/*-------------------------------------------------------------*/ +/*--- end randtable.c ---*/ +/*-------------------------------------------------------------*/ diff --git a/clear.bat b/clear.bat new file mode 100644 index 0000000..48c615a --- /dev/null +++ b/clear.bat @@ -0,0 +1 @@ +del *.plg *.obj *.o *.sbr *.pch *.pdb *.res *.bsc *.pcc *.idb *.pdb *.ncb *.aps *.ilk 2*.log *.map *.opt *.exp *.sup *.dpbcd gebug.txt *_d.exe *_d.dll *_d.lib *_debug.dll *_debug.exe *.tlh *.tli /s \ No newline at end of file diff --git a/main.cpp b/main.cpp new file mode 100644 index 0000000..bd6a1ec --- /dev/null +++ b/main.cpp @@ -0,0 +1,89 @@ +#include +#include "UnAlz.h" + + +void Usage() +{ + printf("\n"); + printf("USAGE : unalz sourcefile.alz [dest path] \n"); +} + +void UnAlzCallback(const char* szMessage, INT64 nCurrent, INT64 nRange, void* param, BOOL* bHalt) +{ + // progress + char buf[1000]; + INT64 percent; + static INT64 nPrevPercent = -1; + int buflen; + int i; + + // 파일명 출력.. + if(szMessage) + { + printf("\n"); + printf("Extracting : %s ", szMessage); + nPrevPercent = -1; + return ; + } + + + percent = nCurrent*100/nRange; + + if(nPrevPercent==percent) return; // 너무 잦은 업데이트 방지.. + nPrevPercent = percent; +#ifdef _WIN32 + sprintf(buf, "%I64d/%I64d (%I64d%%)", nCurrent, nRange, percent); +#else + sprintf(buf, "%d/%d (%d%%)", (int)nCurrent, (int)nRange, (int)percent); +#endif + printf("%s", buf); + buflen = strlen(buf); + fflush(stdout); + + for(i=0;i +# Microsoft Developer Studio Generated Build File, Format Version 6.00 +# ** DO NOT EDIT ** + +# TARGTYPE "Win32 (x86) Console Application" 0x0103 + +CFG=unalz - Win32 Debug +!MESSAGE This is not a valid makefile. To build this project using NMAKE, +!MESSAGE use the Export Makefile command and run +!MESSAGE +!MESSAGE NMAKE /f "unalz.mak". +!MESSAGE +!MESSAGE You can specify a configuration when running NMAKE +!MESSAGE by defining the macro CFG on the command line. For example: +!MESSAGE +!MESSAGE NMAKE /f "unalz.mak" CFG="unalz - Win32 Debug" +!MESSAGE +!MESSAGE Possible choices for configuration are: +!MESSAGE +!MESSAGE "unalz - Win32 Release" (based on "Win32 (x86) Console Application") +!MESSAGE "unalz - Win32 Debug" (based on "Win32 (x86) Console Application") +!MESSAGE + +# Begin Project +# PROP AllowPerConfigDependencies 0 +# PROP Scc_ProjName ""$/Home/unalz", VXBAAAAA" +# PROP Scc_LocalPath "." +CPP=cl.exe +RSC=rc.exe + +!IF "$(CFG)" == "unalz - Win32 Release" + +# PROP BASE Use_MFC 0 +# PROP BASE Use_Debug_Libraries 0 +# PROP BASE Output_Dir "Release" +# PROP BASE Intermediate_Dir "Release" +# PROP BASE Target_Dir "" +# PROP Use_MFC 0 +# PROP Use_Debug_Libraries 0 +# PROP Output_Dir "Release" +# PROP Intermediate_Dir "Release" +# PROP Ignore_Export_Lib 0 +# PROP Target_Dir "" +# ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c +# ADD CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c +# ADD BASE RSC /l 0x412 /d "NDEBUG" +# ADD RSC /l 0x412 /d "NDEBUG" +BSC32=bscmake.exe +# ADD BASE BSC32 /nologo +# ADD BSC32 /nologo +LINK32=link.exe +# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 +# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 /out:"bin/unalz.exe" + +!ELSEIF "$(CFG)" == "unalz - Win32 Debug" + +# PROP BASE Use_MFC 0 +# PROP BASE Use_Debug_Libraries 1 +# PROP BASE Output_Dir "Debug" +# PROP BASE Intermediate_Dir "Debug" +# PROP BASE Target_Dir "" +# PROP Use_MFC 0 +# PROP Use_Debug_Libraries 1 +# PROP Output_Dir "Debug" +# PROP Intermediate_Dir "Debug" +# PROP Ignore_Export_Lib 0 +# PROP Target_Dir "" +# ADD BASE CPP /nologo /W3 /Gm /GX /ZI /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /GZ /c +# ADD CPP /nologo /W3 /Gm /GX /ZI /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /GZ /c +# ADD BASE RSC /l 0x412 /d "_DEBUG" +# ADD RSC /l 0x412 /d "_DEBUG" +BSC32=bscmake.exe +# ADD BASE BSC32 /nologo +# ADD BSC32 /nologo +LINK32=link.exe +# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept +# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /out:"bin/unalz_d.exe" /pdbtype:sept + +!ENDIF + +# Begin Target + +# Name "unalz - Win32 Release" +# Name "unalz - Win32 Debug" +# Begin Group "main" + +# PROP Default_Filter "" +# Begin Source File + +SOURCE=.\main.cpp +# End Source File +# Begin Source File + +SOURCE=.\readme.txt +# End Source File +# End Group +# Begin Group "bzip2" + +# PROP Default_Filter "" +# Begin Source File + +SOURCE=.\bzip2\blocksort.c +# End Source File +# Begin Source File + +SOURCE=.\bzip2\bzlib.h +# End Source File +# Begin Source File + +SOURCE=.\bzip2\bzlib_private.h +# End Source File +# Begin Source File + +SOURCE=.\bzip2\compress.c +# End Source File +# Begin Source File + +SOURCE=.\bzip2\crctable.c +# End Source File +# Begin Source File + +SOURCE=.\bzip2\huffman.c +# End Source File +# Begin Source File + +SOURCE=.\bzip2\randtable.c +# End Source File +# End Group +# Begin Group "zlib" + +# PROP Default_Filter "" +# Begin Source File + +SOURCE=.\zlib\adler32.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\crc32.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\infblock.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\infblock.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\infcodes.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\infcodes.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\inffast.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\inffast.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\inffixed.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\inflate.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\inftrees.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\inftrees.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\infutil.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\infutil.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\zconf.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\zlib.h +# End Source File +# Begin Source File + +SOURCE=.\zlib\zutil.c +# End Source File +# Begin Source File + +SOURCE=.\zlib\zutil.h +# End Source File +# End Group +# Begin Group "unalz" + +# PROP Default_Filter "" +# Begin Source File + +SOURCE=.\UnAlz.cpp +# End Source File +# Begin Source File + +SOURCE=.\UnAlz.h +# End Source File +# Begin Source File + +SOURCE=.\UnAlzBz2decompress.c +# End Source File +# Begin Source File + +SOURCE=.\UnAlzBzip2.cpp +# End Source File +# Begin Source File + +SOURCE=.\UnAlzbzlib.c +# End Source File +# End Group +# End Target +# End Project diff --git a/unalz.dsw b/unalz.dsw new file mode 100644 index 0000000..53235b2 --- /dev/null +++ b/unalz.dsw @@ -0,0 +1,33 @@ +Microsoft Developer Studio Workspace File, Format Version 6.00 +# WARNING: DO NOT EDIT OR DELETE THIS WORKSPACE FILE! + +############################################################################### + +Project: "unalz"=.\unalz.dsp - Package Owner=<4> + +Package=<5> +{{{ + begin source code control + "$/Home/unalz", VXBAAAAA + . + end source code control +}}} + +Package=<4> +{{{ +}}} + +############################################################################### + +Global: + +Package=<5> +{{{ +}}} + +Package=<3> +{{{ +}}} + +############################################################################### + diff --git a/unalz.sln b/unalz.sln new file mode 100644 index 0000000..3862ee4 --- /dev/null +++ b/unalz.sln @@ -0,0 +1,29 @@ +Microsoft Visual Studio Solution File, Format Version 8.00 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "unalz", "unalz.vcproj", "{E92968E8-DF95-411B-80E2-23F17B3DDFF8}" + ProjectSection(ProjectDependencies) = postProject + EndProjectSection +EndProject +Global + GlobalSection(SourceCodeControl) = preSolution + SccNumberOfProjects = 1 + SccProjectUniqueName0 = unalz.vcproj + SccProjectName0 = \u0022$/Home/unalz\u0022,\u0020VXBAAAAA + SccLocalPath0 = . + SccProvider0 = MSSCCI:Microsoft\u0020Visual\u0020SourceSafe + CanCheckoutShared = false + EndGlobalSection + GlobalSection(SolutionConfiguration) = preSolution + Debug = Debug + Release = Release + EndGlobalSection + GlobalSection(ProjectConfiguration) = postSolution + {E92968E8-DF95-411B-80E2-23F17B3DDFF8}.Debug.ActiveCfg = Debug|Win32 + {E92968E8-DF95-411B-80E2-23F17B3DDFF8}.Debug.Build.0 = Debug|Win32 + {E92968E8-DF95-411B-80E2-23F17B3DDFF8}.Release.ActiveCfg = Release|Win32 + {E92968E8-DF95-411B-80E2-23F17B3DDFF8}.Release.Build.0 = Release|Win32 + EndGlobalSection + GlobalSection(ExtensibilityGlobals) = postSolution + EndGlobalSection + GlobalSection(ExtensibilityAddIns) = postSolution + EndGlobalSection +EndGlobal diff --git a/unalz.vcproj b/unalz.vcproj new file mode 100644 index 0000000..ff87f59 --- /dev/null +++ b/unalz.vcproj @@ -0,0 +1,532 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/zlib/adler32.c b/zlib/adler32.c new file mode 100644 index 0000000..fae88b6 --- /dev/null +++ b/zlib/adler32.c @@ -0,0 +1,48 @@ +/* adler32.c -- compute the Adler-32 checksum of a data stream + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* @(#) $Id$ */ + +#include "zlib.h" + +#define BASE 65521L /* largest prime smaller than 65536 */ +#define NMAX 5552 +/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */ + +#define DO1(buf,i) {s1 += buf[i]; s2 += s1;} +#define DO2(buf,i) DO1(buf,i); DO1(buf,i+1); +#define DO4(buf,i) DO2(buf,i); DO2(buf,i+2); +#define DO8(buf,i) DO4(buf,i); DO4(buf,i+4); +#define DO16(buf) DO8(buf,0); DO8(buf,8); + +/* ========================================================================= */ +uLong ZEXPORT adler32(adler, buf, len) + uLong adler; + const Bytef *buf; + uInt len; +{ + unsigned long s1 = adler & 0xffff; + unsigned long s2 = (adler >> 16) & 0xffff; + int k; + + if (buf == Z_NULL) return 1L; + + while (len > 0) { + k = len < NMAX ? len : NMAX; + len -= k; + while (k >= 16) { + DO16(buf); + buf += 16; + k -= 16; + } + if (k != 0) do { + s1 += *buf++; + s2 += s1; + } while (--k); + s1 %= BASE; + s2 %= BASE; + } + return (s2 << 16) | s1; +} diff --git a/zlib/crc32.c b/zlib/crc32.c new file mode 100644 index 0000000..d2e0492 --- /dev/null +++ b/zlib/crc32.c @@ -0,0 +1,162 @@ +/* crc32.c -- compute the CRC-32 of a data stream + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* @(#) $Id$ */ + +#include "zlib.h" + +#define local static + +#ifdef DYNAMIC_CRC_TABLE + +local int crc_table_empty = 1; +local uLongf crc_table[256]; +local void make_crc_table OF((void)); + +/* + Generate a table for a byte-wise 32-bit CRC calculation on the polynomial: + x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x+1. + + Polynomials over GF(2) are represented in binary, one bit per coefficient, + with the lowest powers in the most significant bit. Then adding polynomials + is just exclusive-or, and multiplying a polynomial by x is a right shift by + one. If we call the above polynomial p, and represent a byte as the + polynomial q, also with the lowest power in the most significant bit (so the + byte 0xb1 is the polynomial x^7+x^3+x+1), then the CRC is (q*x^32) mod p, + where a mod b means the remainder after dividing a by b. + + This calculation is done using the shift-register method of multiplying and + taking the remainder. The register is initialized to zero, and for each + incoming bit, x^32 is added mod p to the register if the bit is a one (where + x^32 mod p is p+x^32 = x^26+...+1), and the register is multiplied mod p by + x (which is shifting right by one and adding x^32 mod p if the bit shifted + out is a one). We start with the highest power (least significant bit) of + q and repeat for all eight bits of q. + + The table is simply the CRC of all possible eight bit values. This is all + the information needed to generate CRC's on data a byte at a time for all + combinations of CRC register values and incoming bytes. +*/ +local void make_crc_table() +{ + uLong c; + int n, k; + uLong poly; /* polynomial exclusive-or pattern */ + /* terms of polynomial defining this crc (except x^32): */ + static const Byte p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26}; + + /* make exclusive-or pattern from polynomial (0xedb88320L) */ + poly = 0L; + for (n = 0; n < sizeof(p)/sizeof(Byte); n++) + poly |= 1L << (31 - p[n]); + + for (n = 0; n < 256; n++) + { + c = (uLong)n; + for (k = 0; k < 8; k++) + c = c & 1 ? poly ^ (c >> 1) : c >> 1; + crc_table[n] = c; + } + crc_table_empty = 0; +} +#else +/* ======================================================================== + * Table of CRC-32's of all single-byte values (made by make_crc_table) + */ +local const uLongf crc_table[256] = { + 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L, + 0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L, + 0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, + 0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL, + 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L, + 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L, + 0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, + 0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL, + 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L, + 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL, + 0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, + 0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L, + 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L, + 0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL, + 0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, + 0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L, + 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL, + 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L, + 0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, + 0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L, + 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL, + 0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L, + 0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L, + 0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL, + 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L, + 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L, + 0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L, + 0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L, + 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L, + 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL, + 0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, + 0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L, + 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L, + 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL, + 0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, + 0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L, + 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL, + 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L, + 0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, + 0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L, + 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL, + 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L, + 0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, + 0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL, + 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L, + 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L, + 0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, + 0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L, + 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L, + 0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L, + 0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, + 0x2d02ef8dL +}; +#endif + +/* ========================================================================= + * This function can be used by asm versions of crc32() + */ +const uLongf * ZEXPORT get_crc_table() +{ +#ifdef DYNAMIC_CRC_TABLE + if (crc_table_empty) make_crc_table(); +#endif + return (const uLongf *)crc_table; +} + +/* ========================================================================= */ +#define DO1(buf) crc = crc_table[((int)crc ^ (*buf++)) & 0xff] ^ (crc >> 8); +#define DO2(buf) DO1(buf); DO1(buf); +#define DO4(buf) DO2(buf); DO2(buf); +#define DO8(buf) DO4(buf); DO4(buf); + +/* ========================================================================= */ +uLong ZEXPORT crc32(crc, buf, len) + uLong crc; + const Bytef *buf; + uInt len; +{ + if (buf == Z_NULL) return 0L; +#ifdef DYNAMIC_CRC_TABLE + if (crc_table_empty) + make_crc_table(); +#endif + crc = crc ^ 0xffffffffL; + while (len >= 8) + { + DO8(buf); + len -= 8; + } + if (len) do { + DO1(buf); + } while (--len); + return crc ^ 0xffffffffL; +} diff --git a/zlib/infblock.c b/zlib/infblock.c new file mode 100644 index 0000000..dd7a6d4 --- /dev/null +++ b/zlib/infblock.c @@ -0,0 +1,403 @@ +/* infblock.c -- interpret and process block types to last block + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "infblock.h" +#include "inftrees.h" +#include "infcodes.h" +#include "infutil.h" + +struct inflate_codes_state {int dummy;}; /* for buggy compilers */ + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + +/* Table for deflate from PKZIP's appnote.txt. */ +local const uInt border[] = { /* Order of the bit length code lengths */ + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; + +/* + Notes beyond the 1.93a appnote.txt: + + 1. Distance pointers never point before the beginning of the output + stream. + 2. Distance pointers can point back across blocks, up to 32k away. + 3. There is an implied maximum of 7 bits for the bit length table and + 15 bits for the actual data. + 4. If only one code exists, then it is encoded using one bit. (Zero + would be more efficient, but perhaps a little confusing.) If two + codes exist, they are coded using one bit each (0 and 1). + 5. There is no way of sending zero distance codes--a dummy must be + sent if there are none. (History: a pre 2.0 version of PKZIP would + store blocks with no distance codes, but this was discovered to be + too harsh a criterion.) Valid only for 1.93a. 2.04c does allow + zero distance codes, which is sent as one code of zero bits in + length. + 6. There are up to 286 literal/length codes. Code 256 represents the + end-of-block. Note however that the static length tree defines + 288 codes just to fill out the Huffman codes. Codes 286 and 287 + cannot be used though, since there is no length base or extra bits + defined for them. Similarily, there are up to 30 distance codes. + However, static trees define 32 codes (all 5 bits) to fill out the + Huffman codes, but the last two had better not show up in the data. + 7. Unzip can check dynamic Huffman blocks for complete code sets. + The exception is that a single code would not be complete (see #4). + 8. The five bits following the block type is really the number of + literal codes sent minus 257. + 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits + (1+6+6). Therefore, to output three times the length, you output + three codes (1+1+1), whereas to output four times the same length, + you only need two codes (1+3). Hmm. + 10. In the tree reconstruction algorithm, Code = Code + Increment + only if BitLength(i) is not zero. (Pretty obvious.) + 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) + 12. Note: length code 284 can represent 227-258, but length code 285 + really is 258. The last length deserves its own, short code + since it gets used a lot in very redundant files. The length + 258 is special since 258 - 3 (the min match length) is 255. + 13. The literal/length and distance code bit lengths are read as a + single stream of lengths. It is possible (and advantageous) for + a repeat code (16, 17, or 18) to go across the boundary between + the two sets of lengths. + */ + + +void inflate_blocks_reset(s, z, c) +inflate_blocks_statef *s; +z_streamp z; +uLongf *c; +{ + if (c != Z_NULL) + *c = s->check; + if (s->mode == BTREE || s->mode == DTREE) + ZFREE(z, s->sub.trees.blens); + if (s->mode == CODES) + inflate_codes_free(s->sub.decode.codes, z); + s->mode = TYPE; + s->bitk = 0; + s->bitb = 0; + s->read = s->write = s->window; + if (s->checkfn != Z_NULL) + z->adler = s->check = (*s->checkfn)(0L, (const Bytef *)Z_NULL, 0); + Tracev((stderr, "inflate: blocks reset\n")); +} + + +inflate_blocks_statef *inflate_blocks_new(z, c, w) +z_streamp z; +check_func c; +uInt w; +{ + inflate_blocks_statef *s; + + if ((s = (inflate_blocks_statef *)ZALLOC + (z,1,sizeof(struct inflate_blocks_state))) == Z_NULL) + return s; + if ((s->hufts = + (inflate_huft *)ZALLOC(z, sizeof(inflate_huft), MANY)) == Z_NULL) + { + ZFREE(z, s); + return Z_NULL; + } + if ((s->window = (Bytef *)ZALLOC(z, 1, w)) == Z_NULL) + { + ZFREE(z, s->hufts); + ZFREE(z, s); + return Z_NULL; + } + s->end = s->window + w; + s->checkfn = c; + s->mode = TYPE; + Tracev((stderr, "inflate: blocks allocated\n")); + inflate_blocks_reset(s, z, Z_NULL); + return s; +} + + +int inflate_blocks(s, z, r) +inflate_blocks_statef *s; +z_streamp z; +int r; +{ + uInt t; /* temporary storage */ + uLong b; /* bit buffer */ + uInt k; /* bits in bit buffer */ + Bytef *p; /* input data pointer */ + uInt n; /* bytes available there */ + Bytef *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + + /* copy input/output information to locals (UPDATE macro restores) */ + LOAD + + /* process input based on current state */ + while (1) switch (s->mode) + { + case TYPE: + NEEDBITS(3) + t = (uInt)b & 7; + s->last = t & 1; + switch (t >> 1) + { + case 0: /* stored */ + Tracev((stderr, "inflate: stored block%s\n", + s->last ? " (last)" : "")); + DUMPBITS(3) + t = k & 7; /* go to byte boundary */ + DUMPBITS(t) + s->mode = LENS; /* get length of stored block */ + break; + case 1: /* fixed */ + Tracev((stderr, "inflate: fixed codes block%s\n", + s->last ? " (last)" : "")); + { + uInt bl, bd; + inflate_huft *tl, *td; + + inflate_trees_fixed(&bl, &bd, &tl, &td, z); + s->sub.decode.codes = inflate_codes_new(bl, bd, tl, td, z); + if (s->sub.decode.codes == Z_NULL) + { + r = Z_MEM_ERROR; + LEAVE + } + } + DUMPBITS(3) + s->mode = CODES; + break; + case 2: /* dynamic */ + Tracev((stderr, "inflate: dynamic codes block%s\n", + s->last ? " (last)" : "")); + DUMPBITS(3) + s->mode = TABLE; + break; + case 3: /* illegal */ + DUMPBITS(3) + s->mode = BAD; + z->msg = (char*)"invalid block type"; + r = Z_DATA_ERROR; + LEAVE + } + break; + case LENS: + NEEDBITS(32) + if ((((~b) >> 16) & 0xffff) != (b & 0xffff)) + { + s->mode = BAD; + z->msg = (char*)"invalid stored block lengths"; + r = Z_DATA_ERROR; + LEAVE + } + s->sub.left = (uInt)b & 0xffff; + b = k = 0; /* dump bits */ + Tracev((stderr, "inflate: stored length %u\n", s->sub.left)); + s->mode = s->sub.left ? STORED : (s->last ? DRY : TYPE); + break; + case STORED: + if (n == 0) + LEAVE + NEEDOUT + t = s->sub.left; + if (t > n) t = n; + if (t > m) t = m; + zmemcpy(q, p, t); + p += t; n -= t; + q += t; m -= t; + if ((s->sub.left -= t) != 0) + break; + Tracev((stderr, "inflate: stored end, %lu total out\n", + z->total_out + (q >= s->read ? q - s->read : + (s->end - s->read) + (q - s->window)))); + s->mode = s->last ? DRY : TYPE; + break; + case TABLE: + NEEDBITS(14) + s->sub.trees.table = t = (uInt)b & 0x3fff; +#ifndef PKZIP_BUG_WORKAROUND + if ((t & 0x1f) > 29 || ((t >> 5) & 0x1f) > 29) + { + s->mode = BAD; + z->msg = (char*)"too many length or distance symbols"; + r = Z_DATA_ERROR; + LEAVE + } +#endif + t = 258 + (t & 0x1f) + ((t >> 5) & 0x1f); + if ((s->sub.trees.blens = (uIntf*)ZALLOC(z, t, sizeof(uInt))) == Z_NULL) + { + r = Z_MEM_ERROR; + LEAVE + } + DUMPBITS(14) + s->sub.trees.index = 0; + Tracev((stderr, "inflate: table sizes ok\n")); + s->mode = BTREE; + case BTREE: + while (s->sub.trees.index < 4 + (s->sub.trees.table >> 10)) + { + NEEDBITS(3) + s->sub.trees.blens[border[s->sub.trees.index++]] = (uInt)b & 7; + DUMPBITS(3) + } + while (s->sub.trees.index < 19) + s->sub.trees.blens[border[s->sub.trees.index++]] = 0; + s->sub.trees.bb = 7; + t = inflate_trees_bits(s->sub.trees.blens, &s->sub.trees.bb, + &s->sub.trees.tb, s->hufts, z); + if (t != Z_OK) + { + r = t; + if (r == Z_DATA_ERROR) + { + ZFREE(z, s->sub.trees.blens); + s->mode = BAD; + } + LEAVE + } + s->sub.trees.index = 0; + Tracev((stderr, "inflate: bits tree ok\n")); + s->mode = DTREE; + case DTREE: + while (t = s->sub.trees.table, + s->sub.trees.index < 258 + (t & 0x1f) + ((t >> 5) & 0x1f)) + { + inflate_huft *h; + uInt i, j, c; + + t = s->sub.trees.bb; + NEEDBITS(t) + h = s->sub.trees.tb + ((uInt)b & inflate_mask[t]); + t = h->bits; + c = h->base; + if (c < 16) + { + DUMPBITS(t) + s->sub.trees.blens[s->sub.trees.index++] = c; + } + else /* c == 16..18 */ + { + i = c == 18 ? 7 : c - 14; + j = c == 18 ? 11 : 3; + NEEDBITS(t + i) + DUMPBITS(t) + j += (uInt)b & inflate_mask[i]; + DUMPBITS(i) + i = s->sub.trees.index; + t = s->sub.trees.table; + if (i + j > 258 + (t & 0x1f) + ((t >> 5) & 0x1f) || + (c == 16 && i < 1)) + { + ZFREE(z, s->sub.trees.blens); + s->mode = BAD; + z->msg = (char*)"invalid bit length repeat"; + r = Z_DATA_ERROR; + LEAVE + } + c = c == 16 ? s->sub.trees.blens[i - 1] : 0; + do { + s->sub.trees.blens[i++] = c; + } while (--j); + s->sub.trees.index = i; + } + } + s->sub.trees.tb = Z_NULL; + { + uInt bl, bd; + inflate_huft *tl, *td; + inflate_codes_statef *c; + + bl = 9; /* must be <= 9 for lookahead assumptions */ + bd = 6; /* must be <= 9 for lookahead assumptions */ + t = s->sub.trees.table; + t = inflate_trees_dynamic(257 + (t & 0x1f), 1 + ((t >> 5) & 0x1f), + s->sub.trees.blens, &bl, &bd, &tl, &td, + s->hufts, z); + if (t != Z_OK) + { + if (t == (uInt)Z_DATA_ERROR) + { + ZFREE(z, s->sub.trees.blens); + s->mode = BAD; + } + r = t; + LEAVE + } + Tracev((stderr, "inflate: trees ok\n")); + if ((c = inflate_codes_new(bl, bd, tl, td, z)) == Z_NULL) + { + r = Z_MEM_ERROR; + LEAVE + } + s->sub.decode.codes = c; + } + ZFREE(z, s->sub.trees.blens); + s->mode = CODES; + case CODES: + UPDATE + if ((r = inflate_codes(s, z, r)) != Z_STREAM_END) + return inflate_flush(s, z, r); + r = Z_OK; + inflate_codes_free(s->sub.decode.codes, z); + LOAD + Tracev((stderr, "inflate: codes end, %lu total out\n", + z->total_out + (q >= s->read ? q - s->read : + (s->end - s->read) + (q - s->window)))); + if (!s->last) + { + s->mode = TYPE; + break; + } + s->mode = DRY; + case DRY: + FLUSH + if (s->read != s->write) + LEAVE + s->mode = DONE; + case DONE: + r = Z_STREAM_END; + LEAVE + case BAD: + r = Z_DATA_ERROR; + LEAVE + default: + r = Z_STREAM_ERROR; + LEAVE + } +} + + +int inflate_blocks_free(s, z) +inflate_blocks_statef *s; +z_streamp z; +{ + inflate_blocks_reset(s, z, Z_NULL); + ZFREE(z, s->window); + ZFREE(z, s->hufts); + ZFREE(z, s); + Tracev((stderr, "inflate: blocks freed\n")); + return Z_OK; +} + + +void inflate_set_dictionary(s, d, n) +inflate_blocks_statef *s; +const Bytef *d; +uInt n; +{ + zmemcpy(s->window, d, n); + s->read = s->write = s->window + n; +} + + +/* Returns true if inflate is currently at the end of a block generated + * by Z_SYNC_FLUSH or Z_FULL_FLUSH. + * IN assertion: s != Z_NULL + */ +int inflate_blocks_sync_point(s) +inflate_blocks_statef *s; +{ + return s->mode == LENS; +} diff --git a/zlib/infblock.h b/zlib/infblock.h new file mode 100644 index 0000000..4cf0fa9 --- /dev/null +++ b/zlib/infblock.h @@ -0,0 +1,39 @@ +/* infblock.h -- header to use infblock.c + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +struct inflate_blocks_state; +typedef struct inflate_blocks_state FAR inflate_blocks_statef; + +extern inflate_blocks_statef * inflate_blocks_new OF(( + z_streamp z, + check_func c, /* check function */ + uInt w)); /* window size */ + +extern int inflate_blocks OF(( + inflate_blocks_statef *, + z_streamp , + int)); /* initial return code */ + +extern void inflate_blocks_reset OF(( + inflate_blocks_statef *, + z_streamp , + uLongf *)); /* check value on output */ + +extern int inflate_blocks_free OF(( + inflate_blocks_statef *, + z_streamp)); + +extern void inflate_set_dictionary OF(( + inflate_blocks_statef *s, + const Bytef *d, /* dictionary */ + uInt n)); /* dictionary length */ + +extern int inflate_blocks_sync_point OF(( + inflate_blocks_statef *s)); diff --git a/zlib/infcodes.c b/zlib/infcodes.c new file mode 100644 index 0000000..aa7b3a0 --- /dev/null +++ b/zlib/infcodes.c @@ -0,0 +1,251 @@ +/* infcodes.c -- process literals and length/distance pairs + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "inftrees.h" +#include "infblock.h" +#include "infcodes.h" +#include "infutil.h" +#include "inffast.h" + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + +typedef enum { /* waiting for "i:"=input, "o:"=output, "x:"=nothing */ + START, /* x: set up for LEN */ + LEN, /* i: get length/literal/eob next */ + LENEXT, /* i: getting length extra (have base) */ + DIST, /* i: get distance next */ + DISTEXT, /* i: getting distance extra */ + COPY, /* o: copying bytes in window, waiting for space */ + LIT, /* o: got literal, waiting for output space */ + WASH, /* o: got eob, possibly still output waiting */ + END, /* x: got eob and all data flushed */ + BADCODE} /* x: got error */ +inflate_codes_mode; + +/* inflate codes private state */ +struct inflate_codes_state { + + /* mode */ + inflate_codes_mode mode; /* current inflate_codes mode */ + + /* mode dependent information */ + uInt len; + union { + struct { + inflate_huft *tree; /* pointer into tree */ + uInt need; /* bits needed */ + } code; /* if LEN or DIST, where in tree */ + uInt lit; /* if LIT, literal */ + struct { + uInt get; /* bits to get for extra */ + uInt dist; /* distance back to copy from */ + } copy; /* if EXT or COPY, where and how much */ + } sub; /* submode */ + + /* mode independent information */ + Byte lbits; /* ltree bits decoded per branch */ + Byte dbits; /* dtree bits decoder per branch */ + inflate_huft *ltree; /* literal/length/eob tree */ + inflate_huft *dtree; /* distance tree */ + +}; + + +inflate_codes_statef *inflate_codes_new(bl, bd, tl, td, z) +uInt bl, bd; +inflate_huft *tl; +inflate_huft *td; /* need separate declaration for Borland C++ */ +z_streamp z; +{ + inflate_codes_statef *c; + + if ((c = (inflate_codes_statef *) + ZALLOC(z,1,sizeof(struct inflate_codes_state))) != Z_NULL) + { + c->mode = START; + c->lbits = (Byte)bl; + c->dbits = (Byte)bd; + c->ltree = tl; + c->dtree = td; + Tracev((stderr, "inflate: codes new\n")); + } + return c; +} + + +int inflate_codes(s, z, r) +inflate_blocks_statef *s; +z_streamp z; +int r; +{ + uInt j; /* temporary storage */ + inflate_huft *t; /* temporary pointer */ + uInt e; /* extra bits or operation */ + uLong b; /* bit buffer */ + uInt k; /* bits in bit buffer */ + Bytef *p; /* input data pointer */ + uInt n; /* bytes available there */ + Bytef *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + Bytef *f; /* pointer to copy strings from */ + inflate_codes_statef *c = s->sub.decode.codes; /* codes state */ + + /* copy input/output information to locals (UPDATE macro restores) */ + LOAD + + /* process input and output based on current state */ + while (1) switch (c->mode) + { /* waiting for "i:"=input, "o:"=output, "x:"=nothing */ + case START: /* x: set up for LEN */ +#ifndef SLOW + if (m >= 258 && n >= 10) + { + UPDATE + r = inflate_fast(c->lbits, c->dbits, c->ltree, c->dtree, s, z); + LOAD + if (r != Z_OK) + { + c->mode = r == Z_STREAM_END ? WASH : BADCODE; + break; + } + } +#endif /* !SLOW */ + c->sub.code.need = c->lbits; + c->sub.code.tree = c->ltree; + c->mode = LEN; + case LEN: /* i: get length/literal/eob next */ + j = c->sub.code.need; + NEEDBITS(j) + t = c->sub.code.tree + ((uInt)b & inflate_mask[j]); + DUMPBITS(t->bits) + e = (uInt)(t->exop); + if (e == 0) /* literal */ + { + c->sub.lit = t->base; + Tracevv((stderr, t->base >= 0x20 && t->base < 0x7f ? + "inflate: literal '%c'\n" : + "inflate: literal 0x%02x\n", t->base)); + c->mode = LIT; + break; + } + if (e & 16) /* length */ + { + c->sub.copy.get = e & 15; + c->len = t->base; + c->mode = LENEXT; + break; + } + if ((e & 64) == 0) /* next table */ + { + c->sub.code.need = e; + c->sub.code.tree = t + t->base; + break; + } + if (e & 32) /* end of block */ + { + Tracevv((stderr, "inflate: end of block\n")); + c->mode = WASH; + break; + } + c->mode = BADCODE; /* invalid code */ + z->msg = (char*)"invalid literal/length code"; + r = Z_DATA_ERROR; + LEAVE + case LENEXT: /* i: getting length extra (have base) */ + j = c->sub.copy.get; + NEEDBITS(j) + c->len += (uInt)b & inflate_mask[j]; + DUMPBITS(j) + c->sub.code.need = c->dbits; + c->sub.code.tree = c->dtree; + Tracevv((stderr, "inflate: length %u\n", c->len)); + c->mode = DIST; + case DIST: /* i: get distance next */ + j = c->sub.code.need; + NEEDBITS(j) + t = c->sub.code.tree + ((uInt)b & inflate_mask[j]); + DUMPBITS(t->bits) + e = (uInt)(t->exop); + if (e & 16) /* distance */ + { + c->sub.copy.get = e & 15; + c->sub.copy.dist = t->base; + c->mode = DISTEXT; + break; + } + if ((e & 64) == 0) /* next table */ + { + c->sub.code.need = e; + c->sub.code.tree = t + t->base; + break; + } + c->mode = BADCODE; /* invalid code */ + z->msg = (char*)"invalid distance code"; + r = Z_DATA_ERROR; + LEAVE + case DISTEXT: /* i: getting distance extra */ + j = c->sub.copy.get; + NEEDBITS(j) + c->sub.copy.dist += (uInt)b & inflate_mask[j]; + DUMPBITS(j) + Tracevv((stderr, "inflate: distance %u\n", c->sub.copy.dist)); + c->mode = COPY; + case COPY: /* o: copying bytes in window, waiting for space */ + f = q - c->sub.copy.dist; + while (f < s->window) /* modulo window size-"while" instead */ + f += s->end - s->window; /* of "if" handles invalid distances */ + while (c->len) + { + NEEDOUT + OUTBYTE(*f++) + if (f == s->end) + f = s->window; + c->len--; + } + c->mode = START; + break; + case LIT: /* o: got literal, waiting for output space */ + NEEDOUT + OUTBYTE(c->sub.lit) + c->mode = START; + break; + case WASH: /* o: got eob, possibly more output */ + if (k > 7) /* return unused byte, if any */ + { + Assert(k < 16, "inflate_codes grabbed too many bytes") + k -= 8; + n++; + p--; /* can always return one */ + } + FLUSH + if (s->read != s->write) + LEAVE + c->mode = END; + case END: + r = Z_STREAM_END; + LEAVE + case BADCODE: /* x: got error */ + r = Z_DATA_ERROR; + LEAVE + default: + r = Z_STREAM_ERROR; + LEAVE + } +#ifdef NEED_DUMMY_RETURN + return Z_STREAM_ERROR; /* Some dumb compilers complain without this */ +#endif +} + + +void inflate_codes_free(c, z) +inflate_codes_statef *c; +z_streamp z; +{ + ZFREE(z, c); + Tracev((stderr, "inflate: codes free\n")); +} diff --git a/zlib/infcodes.h b/zlib/infcodes.h new file mode 100644 index 0000000..531d419 --- /dev/null +++ b/zlib/infcodes.h @@ -0,0 +1,27 @@ +/* infcodes.h -- header to use infcodes.c + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +struct inflate_codes_state; +typedef struct inflate_codes_state FAR inflate_codes_statef; + +extern inflate_codes_statef *inflate_codes_new OF(( + uInt, uInt, + inflate_huft *, inflate_huft *, + z_streamp )); + +extern int inflate_codes OF(( + inflate_blocks_statef *, + z_streamp , + int)); + +extern void inflate_codes_free OF(( + inflate_codes_statef *, + z_streamp )); + diff --git a/zlib/inffast.c b/zlib/inffast.c new file mode 100644 index 0000000..655eaf0 --- /dev/null +++ b/zlib/inffast.c @@ -0,0 +1,183 @@ +/* inffast.c -- process literals and length/distance pairs fast + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "inftrees.h" +#include "infblock.h" +#include "infcodes.h" +#include "infutil.h" +#include "inffast.h" + +struct inflate_codes_state {int dummy;}; /* for buggy compilers */ + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + +/* macros for bit input with no checking and for returning unused bytes */ +#define GRABBITS(j) {while(k<(j)){b|=((uLong)NEXTBYTE)<avail_in-n;c=(k>>3)>3:c;n+=c;p-=c;k-=c<<3;} + +/* Called with number of bytes left to write in window at least 258 + (the maximum string length) and number of input bytes available + at least ten. The ten bytes are six bytes for the longest length/ + distance pair plus four bytes for overloading the bit buffer. */ + +int inflate_fast(bl, bd, tl, td, s, z) +uInt bl, bd; +inflate_huft *tl; +inflate_huft *td; /* need separate declaration for Borland C++ */ +inflate_blocks_statef *s; +z_streamp z; +{ + inflate_huft *t; /* temporary pointer */ + uInt e; /* extra bits or operation */ + uLong b; /* bit buffer */ + uInt k; /* bits in bit buffer */ + Bytef *p; /* input data pointer */ + uInt n; /* bytes available there */ + Bytef *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + uInt ml; /* mask for literal/length tree */ + uInt md; /* mask for distance tree */ + uInt c; /* bytes to copy */ + uInt d; /* distance back to copy from */ + Bytef *r; /* copy source pointer */ + + /* load input, output, bit values */ + LOAD + + /* initialize masks */ + ml = inflate_mask[bl]; + md = inflate_mask[bd]; + + /* do until not enough input or output space for fast loop */ + do { /* assume called with m >= 258 && n >= 10 */ + /* get literal/length code */ + GRABBITS(20) /* max bits for literal/length code */ + if ((e = (t = tl + ((uInt)b & ml))->exop) == 0) + { + DUMPBITS(t->bits) + Tracevv((stderr, t->base >= 0x20 && t->base < 0x7f ? + "inflate: * literal '%c'\n" : + "inflate: * literal 0x%02x\n", t->base)); + *q++ = (Byte)t->base; + m--; + continue; + } + do { + DUMPBITS(t->bits) + if (e & 16) + { + /* get extra bits for length */ + e &= 15; + c = t->base + ((uInt)b & inflate_mask[e]); + DUMPBITS(e) + Tracevv((stderr, "inflate: * length %u\n", c)); + + /* decode distance base of block to copy */ + GRABBITS(15); /* max bits for distance code */ + e = (t = td + ((uInt)b & md))->exop; + do { + DUMPBITS(t->bits) + if (e & 16) + { + /* get extra bits to add to distance base */ + e &= 15; + GRABBITS(e) /* get extra bits (up to 13) */ + d = t->base + ((uInt)b & inflate_mask[e]); + DUMPBITS(e) + Tracevv((stderr, "inflate: * distance %u\n", d)); + + /* do the copy */ + m -= c; + r = q - d; + if (r < s->window) /* wrap if needed */ + { + do { + r += s->end - s->window; /* force pointer in window */ + } while (r < s->window); /* covers invalid distances */ + e = s->end - r; + if (c > e) + { + c -= e; /* wrapped copy */ + do { + *q++ = *r++; + } while (--e); + r = s->window; + do { + *q++ = *r++; + } while (--c); + } + else /* normal copy */ + { + *q++ = *r++; c--; + *q++ = *r++; c--; + do { + *q++ = *r++; + } while (--c); + } + } + else /* normal copy */ + { + *q++ = *r++; c--; + *q++ = *r++; c--; + do { + *q++ = *r++; + } while (--c); + } + break; + } + else if ((e & 64) == 0) + { + t += t->base; + e = (t += ((uInt)b & inflate_mask[e]))->exop; + } + else + { + z->msg = (char*)"invalid distance code"; + UNGRAB + UPDATE + return Z_DATA_ERROR; + } + } while (1); + break; + } + if ((e & 64) == 0) + { + t += t->base; + if ((e = (t += ((uInt)b & inflate_mask[e]))->exop) == 0) + { + DUMPBITS(t->bits) + Tracevv((stderr, t->base >= 0x20 && t->base < 0x7f ? + "inflate: * literal '%c'\n" : + "inflate: * literal 0x%02x\n", t->base)); + *q++ = (Byte)t->base; + m--; + break; + } + } + else if (e & 32) + { + Tracevv((stderr, "inflate: * end of block\n")); + UNGRAB + UPDATE + return Z_STREAM_END; + } + else + { + z->msg = (char*)"invalid literal/length code"; + UNGRAB + UPDATE + return Z_DATA_ERROR; + } + } while (1); + } while (m >= 258 && n >= 10); + + /* not enough input or output--restore pointers and return */ + UNGRAB + UPDATE + return Z_OK; +} diff --git a/zlib/inffast.h b/zlib/inffast.h new file mode 100644 index 0000000..ac643b3 --- /dev/null +++ b/zlib/inffast.h @@ -0,0 +1,17 @@ +/* inffast.h -- header to use inffast.c + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +extern int inflate_fast OF(( + uInt, + uInt, + inflate_huft *, + inflate_huft *, + inflate_blocks_statef *, + z_streamp )); diff --git a/zlib/inffixed.h b/zlib/inffixed.h new file mode 100644 index 0000000..e997507 --- /dev/null +++ b/zlib/inffixed.h @@ -0,0 +1,151 @@ +/* inffixed.h -- table for decoding fixed codes + * Generated automatically by the maketree.c program + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +local uInt fixed_bl = 9; +local uInt fixed_bd = 5; +local inflate_huft fixed_tl[] = { + {{{96,7}},256}, {{{0,8}},80}, {{{0,8}},16}, {{{84,8}},115}, + {{{82,7}},31}, {{{0,8}},112}, {{{0,8}},48}, {{{0,9}},192}, + {{{80,7}},10}, {{{0,8}},96}, {{{0,8}},32}, {{{0,9}},160}, + {{{0,8}},0}, {{{0,8}},128}, {{{0,8}},64}, {{{0,9}},224}, + {{{80,7}},6}, {{{0,8}},88}, {{{0,8}},24}, {{{0,9}},144}, + {{{83,7}},59}, {{{0,8}},120}, {{{0,8}},56}, {{{0,9}},208}, + {{{81,7}},17}, {{{0,8}},104}, {{{0,8}},40}, {{{0,9}},176}, + {{{0,8}},8}, {{{0,8}},136}, {{{0,8}},72}, {{{0,9}},240}, + {{{80,7}},4}, {{{0,8}},84}, {{{0,8}},20}, {{{85,8}},227}, + {{{83,7}},43}, {{{0,8}},116}, {{{0,8}},52}, {{{0,9}},200}, + {{{81,7}},13}, {{{0,8}},100}, {{{0,8}},36}, {{{0,9}},168}, + {{{0,8}},4}, {{{0,8}},132}, {{{0,8}},68}, {{{0,9}},232}, + {{{80,7}},8}, {{{0,8}},92}, {{{0,8}},28}, {{{0,9}},152}, + {{{84,7}},83}, {{{0,8}},124}, {{{0,8}},60}, {{{0,9}},216}, + {{{82,7}},23}, {{{0,8}},108}, {{{0,8}},44}, {{{0,9}},184}, + {{{0,8}},12}, {{{0,8}},140}, {{{0,8}},76}, {{{0,9}},248}, + {{{80,7}},3}, {{{0,8}},82}, {{{0,8}},18}, {{{85,8}},163}, + {{{83,7}},35}, {{{0,8}},114}, {{{0,8}},50}, {{{0,9}},196}, + {{{81,7}},11}, {{{0,8}},98}, {{{0,8}},34}, {{{0,9}},164}, + {{{0,8}},2}, {{{0,8}},130}, {{{0,8}},66}, {{{0,9}},228}, + {{{80,7}},7}, {{{0,8}},90}, {{{0,8}},26}, {{{0,9}},148}, + {{{84,7}},67}, {{{0,8}},122}, {{{0,8}},58}, {{{0,9}},212}, + {{{82,7}},19}, {{{0,8}},106}, {{{0,8}},42}, {{{0,9}},180}, + {{{0,8}},10}, {{{0,8}},138}, {{{0,8}},74}, {{{0,9}},244}, + {{{80,7}},5}, {{{0,8}},86}, {{{0,8}},22}, {{{192,8}},0}, + {{{83,7}},51}, {{{0,8}},118}, {{{0,8}},54}, {{{0,9}},204}, + {{{81,7}},15}, {{{0,8}},102}, {{{0,8}},38}, {{{0,9}},172}, + {{{0,8}},6}, {{{0,8}},134}, {{{0,8}},70}, {{{0,9}},236}, + {{{80,7}},9}, {{{0,8}},94}, {{{0,8}},30}, {{{0,9}},156}, + {{{84,7}},99}, {{{0,8}},126}, {{{0,8}},62}, {{{0,9}},220}, + {{{82,7}},27}, {{{0,8}},110}, {{{0,8}},46}, {{{0,9}},188}, + {{{0,8}},14}, {{{0,8}},142}, {{{0,8}},78}, {{{0,9}},252}, + {{{96,7}},256}, {{{0,8}},81}, {{{0,8}},17}, {{{85,8}},131}, + {{{82,7}},31}, {{{0,8}},113}, {{{0,8}},49}, {{{0,9}},194}, + {{{80,7}},10}, {{{0,8}},97}, {{{0,8}},33}, {{{0,9}},162}, + {{{0,8}},1}, {{{0,8}},129}, {{{0,8}},65}, {{{0,9}},226}, + {{{80,7}},6}, {{{0,8}},89}, {{{0,8}},25}, {{{0,9}},146}, + {{{83,7}},59}, {{{0,8}},121}, {{{0,8}},57}, {{{0,9}},210}, + {{{81,7}},17}, {{{0,8}},105}, {{{0,8}},41}, {{{0,9}},178}, + {{{0,8}},9}, {{{0,8}},137}, {{{0,8}},73}, {{{0,9}},242}, + {{{80,7}},4}, {{{0,8}},85}, {{{0,8}},21}, {{{80,8}},258}, + {{{83,7}},43}, {{{0,8}},117}, {{{0,8}},53}, {{{0,9}},202}, + {{{81,7}},13}, {{{0,8}},101}, {{{0,8}},37}, {{{0,9}},170}, + {{{0,8}},5}, {{{0,8}},133}, {{{0,8}},69}, {{{0,9}},234}, + {{{80,7}},8}, {{{0,8}},93}, {{{0,8}},29}, {{{0,9}},154}, + {{{84,7}},83}, {{{0,8}},125}, {{{0,8}},61}, {{{0,9}},218}, + {{{82,7}},23}, {{{0,8}},109}, {{{0,8}},45}, {{{0,9}},186}, + {{{0,8}},13}, {{{0,8}},141}, {{{0,8}},77}, {{{0,9}},250}, + {{{80,7}},3}, {{{0,8}},83}, {{{0,8}},19}, {{{85,8}},195}, + {{{83,7}},35}, {{{0,8}},115}, {{{0,8}},51}, {{{0,9}},198}, + {{{81,7}},11}, {{{0,8}},99}, {{{0,8}},35}, {{{0,9}},166}, + {{{0,8}},3}, {{{0,8}},131}, {{{0,8}},67}, {{{0,9}},230}, + {{{80,7}},7}, {{{0,8}},91}, {{{0,8}},27}, {{{0,9}},150}, + {{{84,7}},67}, {{{0,8}},123}, {{{0,8}},59}, {{{0,9}},214}, + {{{82,7}},19}, {{{0,8}},107}, {{{0,8}},43}, {{{0,9}},182}, + {{{0,8}},11}, {{{0,8}},139}, {{{0,8}},75}, {{{0,9}},246}, + {{{80,7}},5}, {{{0,8}},87}, {{{0,8}},23}, {{{192,8}},0}, + {{{83,7}},51}, {{{0,8}},119}, {{{0,8}},55}, {{{0,9}},206}, + {{{81,7}},15}, {{{0,8}},103}, {{{0,8}},39}, {{{0,9}},174}, + {{{0,8}},7}, {{{0,8}},135}, {{{0,8}},71}, {{{0,9}},238}, + {{{80,7}},9}, {{{0,8}},95}, {{{0,8}},31}, {{{0,9}},158}, + {{{84,7}},99}, {{{0,8}},127}, {{{0,8}},63}, {{{0,9}},222}, + {{{82,7}},27}, {{{0,8}},111}, {{{0,8}},47}, {{{0,9}},190}, + {{{0,8}},15}, {{{0,8}},143}, {{{0,8}},79}, {{{0,9}},254}, + {{{96,7}},256}, {{{0,8}},80}, {{{0,8}},16}, {{{84,8}},115}, + {{{82,7}},31}, {{{0,8}},112}, {{{0,8}},48}, {{{0,9}},193}, + {{{80,7}},10}, {{{0,8}},96}, {{{0,8}},32}, {{{0,9}},161}, + {{{0,8}},0}, {{{0,8}},128}, {{{0,8}},64}, {{{0,9}},225}, + {{{80,7}},6}, {{{0,8}},88}, {{{0,8}},24}, {{{0,9}},145}, + {{{83,7}},59}, {{{0,8}},120}, {{{0,8}},56}, {{{0,9}},209}, + {{{81,7}},17}, {{{0,8}},104}, {{{0,8}},40}, {{{0,9}},177}, + {{{0,8}},8}, {{{0,8}},136}, {{{0,8}},72}, {{{0,9}},241}, + {{{80,7}},4}, {{{0,8}},84}, {{{0,8}},20}, {{{85,8}},227}, + {{{83,7}},43}, {{{0,8}},116}, {{{0,8}},52}, {{{0,9}},201}, + {{{81,7}},13}, {{{0,8}},100}, {{{0,8}},36}, {{{0,9}},169}, + {{{0,8}},4}, {{{0,8}},132}, {{{0,8}},68}, {{{0,9}},233}, + {{{80,7}},8}, {{{0,8}},92}, {{{0,8}},28}, {{{0,9}},153}, + {{{84,7}},83}, {{{0,8}},124}, {{{0,8}},60}, {{{0,9}},217}, + {{{82,7}},23}, {{{0,8}},108}, {{{0,8}},44}, {{{0,9}},185}, + {{{0,8}},12}, {{{0,8}},140}, {{{0,8}},76}, {{{0,9}},249}, + {{{80,7}},3}, {{{0,8}},82}, {{{0,8}},18}, {{{85,8}},163}, + {{{83,7}},35}, {{{0,8}},114}, {{{0,8}},50}, {{{0,9}},197}, + {{{81,7}},11}, {{{0,8}},98}, {{{0,8}},34}, {{{0,9}},165}, + {{{0,8}},2}, {{{0,8}},130}, {{{0,8}},66}, {{{0,9}},229}, + {{{80,7}},7}, {{{0,8}},90}, {{{0,8}},26}, {{{0,9}},149}, + {{{84,7}},67}, {{{0,8}},122}, {{{0,8}},58}, {{{0,9}},213}, + {{{82,7}},19}, {{{0,8}},106}, {{{0,8}},42}, {{{0,9}},181}, + {{{0,8}},10}, {{{0,8}},138}, {{{0,8}},74}, {{{0,9}},245}, + {{{80,7}},5}, {{{0,8}},86}, {{{0,8}},22}, {{{192,8}},0}, + {{{83,7}},51}, {{{0,8}},118}, {{{0,8}},54}, {{{0,9}},205}, + {{{81,7}},15}, {{{0,8}},102}, {{{0,8}},38}, {{{0,9}},173}, + {{{0,8}},6}, {{{0,8}},134}, {{{0,8}},70}, {{{0,9}},237}, + {{{80,7}},9}, {{{0,8}},94}, {{{0,8}},30}, {{{0,9}},157}, + {{{84,7}},99}, {{{0,8}},126}, {{{0,8}},62}, {{{0,9}},221}, + {{{82,7}},27}, {{{0,8}},110}, {{{0,8}},46}, {{{0,9}},189}, + {{{0,8}},14}, {{{0,8}},142}, {{{0,8}},78}, {{{0,9}},253}, + {{{96,7}},256}, {{{0,8}},81}, {{{0,8}},17}, {{{85,8}},131}, + {{{82,7}},31}, {{{0,8}},113}, {{{0,8}},49}, {{{0,9}},195}, + {{{80,7}},10}, {{{0,8}},97}, {{{0,8}},33}, {{{0,9}},163}, + {{{0,8}},1}, {{{0,8}},129}, {{{0,8}},65}, {{{0,9}},227}, + {{{80,7}},6}, {{{0,8}},89}, {{{0,8}},25}, {{{0,9}},147}, + {{{83,7}},59}, {{{0,8}},121}, {{{0,8}},57}, {{{0,9}},211}, + {{{81,7}},17}, {{{0,8}},105}, {{{0,8}},41}, {{{0,9}},179}, + {{{0,8}},9}, {{{0,8}},137}, {{{0,8}},73}, {{{0,9}},243}, + {{{80,7}},4}, {{{0,8}},85}, {{{0,8}},21}, {{{80,8}},258}, + {{{83,7}},43}, {{{0,8}},117}, {{{0,8}},53}, {{{0,9}},203}, + {{{81,7}},13}, {{{0,8}},101}, {{{0,8}},37}, {{{0,9}},171}, + {{{0,8}},5}, {{{0,8}},133}, {{{0,8}},69}, {{{0,9}},235}, + {{{80,7}},8}, {{{0,8}},93}, {{{0,8}},29}, {{{0,9}},155}, + {{{84,7}},83}, {{{0,8}},125}, {{{0,8}},61}, {{{0,9}},219}, + {{{82,7}},23}, {{{0,8}},109}, {{{0,8}},45}, {{{0,9}},187}, + {{{0,8}},13}, {{{0,8}},141}, {{{0,8}},77}, {{{0,9}},251}, + {{{80,7}},3}, {{{0,8}},83}, {{{0,8}},19}, {{{85,8}},195}, + {{{83,7}},35}, {{{0,8}},115}, {{{0,8}},51}, {{{0,9}},199}, + {{{81,7}},11}, {{{0,8}},99}, {{{0,8}},35}, {{{0,9}},167}, + {{{0,8}},3}, {{{0,8}},131}, {{{0,8}},67}, {{{0,9}},231}, + {{{80,7}},7}, {{{0,8}},91}, {{{0,8}},27}, {{{0,9}},151}, + {{{84,7}},67}, {{{0,8}},123}, {{{0,8}},59}, {{{0,9}},215}, + {{{82,7}},19}, {{{0,8}},107}, {{{0,8}},43}, {{{0,9}},183}, + {{{0,8}},11}, {{{0,8}},139}, {{{0,8}},75}, {{{0,9}},247}, + {{{80,7}},5}, {{{0,8}},87}, {{{0,8}},23}, {{{192,8}},0}, + {{{83,7}},51}, {{{0,8}},119}, {{{0,8}},55}, {{{0,9}},207}, + {{{81,7}},15}, {{{0,8}},103}, {{{0,8}},39}, {{{0,9}},175}, + {{{0,8}},7}, {{{0,8}},135}, {{{0,8}},71}, {{{0,9}},239}, + {{{80,7}},9}, {{{0,8}},95}, {{{0,8}},31}, {{{0,9}},159}, + {{{84,7}},99}, {{{0,8}},127}, {{{0,8}},63}, {{{0,9}},223}, + {{{82,7}},27}, {{{0,8}},111}, {{{0,8}},47}, {{{0,9}},191}, + {{{0,8}},15}, {{{0,8}},143}, {{{0,8}},79}, {{{0,9}},255} + }; +local inflate_huft fixed_td[] = { + {{{80,5}},1}, {{{87,5}},257}, {{{83,5}},17}, {{{91,5}},4097}, + {{{81,5}},5}, {{{89,5}},1025}, {{{85,5}},65}, {{{93,5}},16385}, + {{{80,5}},3}, {{{88,5}},513}, {{{84,5}},33}, {{{92,5}},8193}, + {{{82,5}},9}, {{{90,5}},2049}, {{{86,5}},129}, {{{192,5}},24577}, + {{{80,5}},2}, {{{87,5}},385}, {{{83,5}},25}, {{{91,5}},6145}, + {{{81,5}},7}, {{{89,5}},1537}, {{{85,5}},97}, {{{93,5}},24577}, + {{{80,5}},4}, {{{88,5}},769}, {{{84,5}},49}, {{{92,5}},12289}, + {{{82,5}},13}, {{{90,5}},3073}, {{{86,5}},193}, {{{192,5}},24577} + }; diff --git a/zlib/inflate.c b/zlib/inflate.c new file mode 100644 index 0000000..5577e02 --- /dev/null +++ b/zlib/inflate.c @@ -0,0 +1,366 @@ +/* inflate.c -- zlib interface to inflate modules + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "infblock.h" + +struct inflate_blocks_state {int dummy;}; /* for buggy compilers */ + +typedef enum { + METHOD, /* waiting for method byte */ + FLAG, /* waiting for flag byte */ + DICT4, /* four dictionary check bytes to go */ + DICT3, /* three dictionary check bytes to go */ + DICT2, /* two dictionary check bytes to go */ + DICT1, /* one dictionary check byte to go */ + DICT0, /* waiting for inflateSetDictionary */ + BLOCKS, /* decompressing blocks */ + CHECK4, /* four check bytes to go */ + CHECK3, /* three check bytes to go */ + CHECK2, /* two check bytes to go */ + CHECK1, /* one check byte to go */ + DONE, /* finished check, done */ + BAD} /* got an error--stay here */ +inflate_mode; + +/* inflate private state */ +struct internal_state { + + /* mode */ + inflate_mode mode; /* current inflate mode */ + + /* mode dependent information */ + union { + uInt method; /* if FLAGS, method byte */ + struct { + uLong was; /* computed check value */ + uLong need; /* stream check value */ + } check; /* if CHECK, check values to compare */ + uInt marker; /* if BAD, inflateSync's marker bytes count */ + } sub; /* submode */ + + /* mode independent information */ + int nowrap; /* flag for no wrapper */ + uInt wbits; /* log2(window size) (8..15, defaults to 15) */ + inflate_blocks_statef + *blocks; /* current inflate_blocks state */ + +}; + + +int ZEXPORT inflateReset(z) +z_streamp z; +{ + if (z == Z_NULL || z->state == Z_NULL) + return Z_STREAM_ERROR; + z->total_in = z->total_out = 0; + z->msg = Z_NULL; + z->state->mode = z->state->nowrap ? BLOCKS : METHOD; + inflate_blocks_reset(z->state->blocks, z, Z_NULL); + Tracev((stderr, "inflate: reset\n")); + return Z_OK; +} + + +int ZEXPORT inflateEnd(z) +z_streamp z; +{ + if (z == Z_NULL || z->state == Z_NULL || z->zfree == Z_NULL) + return Z_STREAM_ERROR; + if (z->state->blocks != Z_NULL) + inflate_blocks_free(z->state->blocks, z); + ZFREE(z, z->state); + z->state = Z_NULL; + Tracev((stderr, "inflate: end\n")); + return Z_OK; +} + + +int ZEXPORT inflateInit2_(z, w, version, stream_size) +z_streamp z; +int w; +const char *version; +int stream_size; +{ + if (version == Z_NULL || version[0] != ZLIB_VERSION[0] || + stream_size != sizeof(z_stream)) + return Z_VERSION_ERROR; + + /* initialize state */ + if (z == Z_NULL) + return Z_STREAM_ERROR; + z->msg = Z_NULL; + if (z->zalloc == Z_NULL) + { + z->zalloc = zcalloc; + z->opaque = (voidpf)0; + } + if (z->zfree == Z_NULL) z->zfree = zcfree; + if ((z->state = (struct internal_state FAR *) + ZALLOC(z,1,sizeof(struct internal_state))) == Z_NULL) + return Z_MEM_ERROR; + z->state->blocks = Z_NULL; + + /* handle undocumented nowrap option (no zlib header or check) */ + z->state->nowrap = 0; + if (w < 0) + { + w = - w; + z->state->nowrap = 1; + } + + /* set window size */ + if (w < 8 || w > 15) + { + inflateEnd(z); + return Z_STREAM_ERROR; + } + z->state->wbits = (uInt)w; + + /* create inflate_blocks state */ + if ((z->state->blocks = + inflate_blocks_new(z, z->state->nowrap ? Z_NULL : adler32, (uInt)1 << w)) + == Z_NULL) + { + inflateEnd(z); + return Z_MEM_ERROR; + } + Tracev((stderr, "inflate: allocated\n")); + + /* reset state */ + inflateReset(z); + return Z_OK; +} + + +int ZEXPORT inflateInit_(z, version, stream_size) +z_streamp z; +const char *version; +int stream_size; +{ + return inflateInit2_(z, DEF_WBITS, version, stream_size); +} + + +#define NEEDBYTE {if(z->avail_in==0)return r;r=f;} +#define NEXTBYTE (z->avail_in--,z->total_in++,*z->next_in++) + +int ZEXPORT inflate(z, f) +z_streamp z; +int f; +{ + int r; + uInt b; + + if (z == Z_NULL || z->state == Z_NULL || z->next_in == Z_NULL) + return Z_STREAM_ERROR; + f = f == Z_FINISH ? Z_BUF_ERROR : Z_OK; + r = Z_BUF_ERROR; + while (1) switch (z->state->mode) + { + case METHOD: + NEEDBYTE + if (((z->state->sub.method = NEXTBYTE) & 0xf) != Z_DEFLATED) + { + z->state->mode = BAD; + z->msg = (char*)"unknown compression method"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + if ((z->state->sub.method >> 4) + 8 > z->state->wbits) + { + z->state->mode = BAD; + z->msg = (char*)"invalid window size"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + z->state->mode = FLAG; + case FLAG: + NEEDBYTE + b = NEXTBYTE; + if (((z->state->sub.method << 8) + b) % 31) + { + z->state->mode = BAD; + z->msg = (char*)"incorrect header check"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + Tracev((stderr, "inflate: zlib header ok\n")); + if (!(b & PRESET_DICT)) + { + z->state->mode = BLOCKS; + break; + } + z->state->mode = DICT4; + case DICT4: + NEEDBYTE + z->state->sub.check.need = (uLong)NEXTBYTE << 24; + z->state->mode = DICT3; + case DICT3: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 16; + z->state->mode = DICT2; + case DICT2: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 8; + z->state->mode = DICT1; + case DICT1: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE; + z->adler = z->state->sub.check.need; + z->state->mode = DICT0; + return Z_NEED_DICT; + case DICT0: + z->state->mode = BAD; + z->msg = (char*)"need dictionary"; + z->state->sub.marker = 0; /* can try inflateSync */ + return Z_STREAM_ERROR; + case BLOCKS: + r = inflate_blocks(z->state->blocks, z, r); + if (r == Z_DATA_ERROR) + { + z->state->mode = BAD; + z->state->sub.marker = 0; /* can try inflateSync */ + break; + } + if (r == Z_OK) + r = f; + if (r != Z_STREAM_END) + return r; + r = f; + inflate_blocks_reset(z->state->blocks, z, &z->state->sub.check.was); + if (z->state->nowrap) + { + z->state->mode = DONE; + break; + } + z->state->mode = CHECK4; + case CHECK4: + NEEDBYTE + z->state->sub.check.need = (uLong)NEXTBYTE << 24; + z->state->mode = CHECK3; + case CHECK3: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 16; + z->state->mode = CHECK2; + case CHECK2: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 8; + z->state->mode = CHECK1; + case CHECK1: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE; + + if (z->state->sub.check.was != z->state->sub.check.need) + { + z->state->mode = BAD; + z->msg = (char*)"incorrect data check"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + Tracev((stderr, "inflate: zlib check ok\n")); + z->state->mode = DONE; + case DONE: + return Z_STREAM_END; + case BAD: + return Z_DATA_ERROR; + default: + return Z_STREAM_ERROR; + } +#ifdef NEED_DUMMY_RETURN + return Z_STREAM_ERROR; /* Some dumb compilers complain without this */ +#endif +} + + +int ZEXPORT inflateSetDictionary(z, dictionary, dictLength) +z_streamp z; +const Bytef *dictionary; +uInt dictLength; +{ + uInt length = dictLength; + + if (z == Z_NULL || z->state == Z_NULL || z->state->mode != DICT0) + return Z_STREAM_ERROR; + + if (adler32(1L, dictionary, dictLength) != z->adler) return Z_DATA_ERROR; + z->adler = 1L; + + if (length >= ((uInt)1<state->wbits)) + { + length = (1<state->wbits)-1; + dictionary += dictLength - length; + } + inflate_set_dictionary(z->state->blocks, dictionary, length); + z->state->mode = BLOCKS; + return Z_OK; +} + + +int ZEXPORT inflateSync(z) +z_streamp z; +{ + uInt n; /* number of bytes to look at */ + Bytef *p; /* pointer to bytes */ + uInt m; /* number of marker bytes found in a row */ + uLong r, w; /* temporaries to save total_in and total_out */ + + /* set up */ + if (z == Z_NULL || z->state == Z_NULL) + return Z_STREAM_ERROR; + if (z->state->mode != BAD) + { + z->state->mode = BAD; + z->state->sub.marker = 0; + } + if ((n = z->avail_in) == 0) + return Z_BUF_ERROR; + p = z->next_in; + m = z->state->sub.marker; + + /* search */ + while (n && m < 4) + { + static const Byte mark[4] = {0, 0, 0xff, 0xff}; + if (*p == mark[m]) + m++; + else if (*p) + m = 0; + else + m = 4 - m; + p++, n--; + } + + /* restore */ + z->total_in += p - z->next_in; + z->next_in = p; + z->avail_in = n; + z->state->sub.marker = m; + + /* return no joy or set up to restart on a new block */ + if (m != 4) + return Z_DATA_ERROR; + r = z->total_in; w = z->total_out; + inflateReset(z); + z->total_in = r; z->total_out = w; + z->state->mode = BLOCKS; + return Z_OK; +} + + +/* Returns true if inflate is currently at the end of a block generated + * by Z_SYNC_FLUSH or Z_FULL_FLUSH. This function is used by one PPP + * implementation to provide an additional safety check. PPP uses Z_SYNC_FLUSH + * but removes the length bytes of the resulting empty stored block. When + * decompressing, PPP checks that at the end of input packet, inflate is + * waiting for these length bytes. + */ +int ZEXPORT inflateSyncPoint(z) +z_streamp z; +{ + if (z == Z_NULL || z->state == Z_NULL || z->state->blocks == Z_NULL) + return Z_STREAM_ERROR; + return inflate_blocks_sync_point(z->state->blocks); +} diff --git a/zlib/inftrees.c b/zlib/inftrees.c new file mode 100644 index 0000000..f89e801 --- /dev/null +++ b/zlib/inftrees.c @@ -0,0 +1,454 @@ +/* inftrees.c -- generate Huffman trees for efficient decoding + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "inftrees.h" + +#if !defined(BUILDFIXED) && !defined(STDC) +# define BUILDFIXED /* non ANSI compilers may not accept inffixed.h */ +#endif + +const char inflate_copyright[] = + " inflate 1.1.4 Copyright 1995-2002 Mark Adler "; +/* + If you use the zlib library in a product, an acknowledgment is welcome + in the documentation of your product. If for some reason you cannot + include such an acknowledgment, I would appreciate that you keep this + copyright string in the executable of your product. + */ +struct internal_state {int dummy;}; /* for buggy compilers */ + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + + +local int huft_build OF(( + uIntf *, /* code lengths in bits */ + uInt, /* number of codes */ + uInt, /* number of "simple" codes */ + const uIntf *, /* list of base values for non-simple codes */ + const uIntf *, /* list of extra bits for non-simple codes */ + inflate_huft * FAR*,/* result: starting table */ + uIntf *, /* maximum lookup bits (returns actual) */ + inflate_huft *, /* space for trees */ + uInt *, /* hufts used in space */ + uIntf * )); /* space for values */ + +/* Tables for deflate from PKZIP's appnote.txt. */ +local const uInt cplens[31] = { /* Copy lengths for literal codes 257..285 */ + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, + 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; + /* see note #13 above about 258 */ +local const uInt cplext[31] = { /* Extra bits for literal codes 257..285 */ + 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, + 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 112, 112}; /* 112==invalid */ +local const uInt cpdist[30] = { /* Copy offsets for distance codes 0..29 */ + 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, + 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, + 8193, 12289, 16385, 24577}; +local const uInt cpdext[30] = { /* Extra bits for distance codes */ + 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, + 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, + 12, 12, 13, 13}; + +/* + Huffman code decoding is performed using a multi-level table lookup. + The fastest way to decode is to simply build a lookup table whose + size is determined by the longest code. However, the time it takes + to build this table can also be a factor if the data being decoded + is not very long. The most common codes are necessarily the + shortest codes, so those codes dominate the decoding time, and hence + the speed. The idea is you can have a shorter table that decodes the + shorter, more probable codes, and then point to subsidiary tables for + the longer codes. The time it costs to decode the longer codes is + then traded against the time it takes to make longer tables. + + This results of this trade are in the variables lbits and dbits + below. lbits is the number of bits the first level table for literal/ + length codes can decode in one step, and dbits is the same thing for + the distance codes. Subsequent tables are also less than or equal to + those sizes. These values may be adjusted either when all of the + codes are shorter than that, in which case the longest code length in + bits is used, or when the shortest code is *longer* than the requested + table size, in which case the length of the shortest code in bits is + used. + + There are two different values for the two tables, since they code a + different number of possibilities each. The literal/length table + codes 286 possible values, or in a flat code, a little over eight + bits. The distance table codes 30 possible values, or a little less + than five bits, flat. The optimum values for speed end up being + about one bit more than those, so lbits is 8+1 and dbits is 5+1. + The optimum values may differ though from machine to machine, and + possibly even between compilers. Your mileage may vary. + */ + + +/* If BMAX needs to be larger than 16, then h and x[] should be uLong. */ +#define BMAX 15 /* maximum bit length of any code */ + +local int huft_build(b, n, s, d, e, t, m, hp, hn, v) +uIntf *b; /* code lengths in bits (all assumed <= BMAX) */ +uInt n; /* number of codes (assumed <= 288) */ +uInt s; /* number of simple-valued codes (0..s-1) */ +const uIntf *d; /* list of base values for non-simple codes */ +const uIntf *e; /* list of extra bits for non-simple codes */ +inflate_huft * FAR *t; /* result: starting table */ +uIntf *m; /* maximum lookup bits, returns actual */ +inflate_huft *hp; /* space for trees */ +uInt *hn; /* hufts used in space */ +uIntf *v; /* working area: values in order of bit length */ +/* Given a list of code lengths and a maximum table size, make a set of + tables to decode that set of codes. Return Z_OK on success, Z_BUF_ERROR + if the given code set is incomplete (the tables are still built in this + case), or Z_DATA_ERROR if the input is invalid. */ +{ + + uInt a; /* counter for codes of length k */ + uInt c[BMAX+1]; /* bit length count table */ + uInt f; /* i repeats in table every f entries */ + int g; /* maximum code length */ + int h; /* table level */ + register uInt i; /* counter, current code */ + register uInt j; /* counter */ + register int k; /* number of bits in current code */ + int l; /* bits per table (returned in m) */ + uInt mask; /* (1 << w) - 1, to avoid cc -O bug on HP */ + register uIntf *p; /* pointer into c[], b[], or v[] */ + inflate_huft *q; /* points to current table */ + struct inflate_huft_s r; /* table entry for structure assignment */ + inflate_huft *u[BMAX]; /* table stack */ + register int w; /* bits before this table == (l * h) */ + uInt x[BMAX+1]; /* bit offsets, then code stack */ + uIntf *xp; /* pointer into x */ + int y; /* number of dummy codes added */ + uInt z; /* number of entries in current table */ + + + /* Generate counts for each bit length */ + p = c; +#define C0 *p++ = 0; +#define C2 C0 C0 C0 C0 +#define C4 C2 C2 C2 C2 + C4 /* clear c[]--assume BMAX+1 is 16 */ + p = b; i = n; + do { + c[*p++]++; /* assume all entries <= BMAX */ + } while (--i); + if (c[0] == n) /* null input--all zero length codes */ + { + *t = (inflate_huft *)Z_NULL; + *m = 0; + return Z_OK; + } + + + /* Find minimum and maximum length, bound *m by those */ + l = *m; + for (j = 1; j <= BMAX; j++) + if (c[j]) + break; + k = j; /* minimum code length */ + if ((uInt)l < j) + l = j; + for (i = BMAX; i; i--) + if (c[i]) + break; + g = i; /* maximum code length */ + if ((uInt)l > i) + l = i; + *m = l; + + + /* Adjust last length count to fill out codes, if needed */ + for (y = 1 << j; j < i; j++, y <<= 1) + if ((y -= c[j]) < 0) + return Z_DATA_ERROR; + if ((y -= c[i]) < 0) + return Z_DATA_ERROR; + c[i] += y; + + + /* Generate starting offsets into the value table for each length */ + x[1] = j = 0; + p = c + 1; xp = x + 2; + while (--i) { /* note that i == g from above */ + *xp++ = (j += *p++); + } + + + /* Make a table of values in order of bit lengths */ + p = b; i = 0; + do { + if ((j = *p++) != 0) + v[x[j]++] = i; + } while (++i < n); + n = x[g]; /* set n to length of v */ + + + /* Generate the Huffman codes and for each, make the table entries */ + x[0] = i = 0; /* first Huffman code is zero */ + p = v; /* grab values in bit order */ + h = -1; /* no tables yet--level -1 */ + w = -l; /* bits decoded == (l * h) */ + u[0] = (inflate_huft *)Z_NULL; /* just to keep compilers happy */ + q = (inflate_huft *)Z_NULL; /* ditto */ + z = 0; /* ditto */ + + /* go through the bit lengths (k already is bits in shortest code) */ + for (; k <= g; k++) + { + a = c[k]; + while (a--) + { + /* here i is the Huffman code of length k bits for value *p */ + /* make tables up to required level */ + while (k > w + l) + { + h++; + w += l; /* previous table always l bits */ + + /* compute minimum size table less than or equal to l bits */ + z = g - w; + z = z > (uInt)l ? l : z; /* table size upper limit */ + if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ + { /* too few codes for k-w bit table */ + f -= a + 1; /* deduct codes from patterns left */ + xp = c + k; + if (j < z) + while (++j < z) /* try smaller tables up to z bits */ + { + if ((f <<= 1) <= *++xp) + break; /* enough codes to use up j bits */ + f -= *xp; /* else deduct codes from patterns */ + } + } + z = 1 << j; /* table entries for j-bit table */ + + /* allocate new table */ + if (*hn + z > MANY) /* (note: doesn't matter for fixed) */ + return Z_DATA_ERROR; /* overflow of MANY */ + u[h] = q = hp + *hn; + *hn += z; + + /* connect to last table, if there is one */ + if (h) + { + x[h] = i; /* save pattern for backing up */ + r.bits = (Byte)l; /* bits to dump before this table */ + r.exop = (Byte)j; /* bits in this table */ + j = i >> (w - l); + r.base = (uInt)(q - u[h-1] - j); /* offset to this table */ + u[h-1][j] = r; /* connect to last table */ + } + else + *t = q; /* first table is returned result */ + } + + /* set up table entry in r */ + r.bits = (Byte)(k - w); + if (p >= v + n) + r.exop = 128 + 64; /* out of values--invalid code */ + else if (*p < s) + { + r.exop = (Byte)(*p < 256 ? 0 : 32 + 64); /* 256 is end-of-block */ + r.base = *p++; /* simple code is just the value */ + } + else + { + r.exop = (Byte)(e[*p - s] + 16 + 64);/* non-simple--look up in lists */ + r.base = d[*p++ - s]; + } + + /* fill code-like entries with r */ + f = 1 << (k - w); + for (j = i >> w; j < z; j += f) + q[j] = r; + + /* backwards increment the k-bit code i */ + for (j = 1 << (k - 1); i & j; j >>= 1) + i ^= j; + i ^= j; + + /* backup over finished tables */ + mask = (1 << w) - 1; /* needed on HP, cc -O bug */ + while ((i & mask) != x[h]) + { + h--; /* don't need to update q */ + w -= l; + mask = (1 << w) - 1; + } + } + } + + + /* Return Z_BUF_ERROR if we were given an incomplete table */ + return y != 0 && g != 1 ? Z_BUF_ERROR : Z_OK; +} + + +int inflate_trees_bits(c, bb, tb, hp, z) +uIntf *c; /* 19 code lengths */ +uIntf *bb; /* bits tree desired/actual depth */ +inflate_huft * FAR *tb; /* bits tree result */ +inflate_huft *hp; /* space for trees */ +z_streamp z; /* for messages */ +{ + int r; + uInt hn = 0; /* hufts used in space */ + uIntf *v; /* work area for huft_build */ + + if ((v = (uIntf*)ZALLOC(z, 19, sizeof(uInt))) == Z_NULL) + return Z_MEM_ERROR; + r = huft_build(c, 19, 19, (uIntf*)Z_NULL, (uIntf*)Z_NULL, + tb, bb, hp, &hn, v); + if (r == Z_DATA_ERROR) + z->msg = (char*)"oversubscribed dynamic bit lengths tree"; + else if (r == Z_BUF_ERROR || *bb == 0) + { + z->msg = (char*)"incomplete dynamic bit lengths tree"; + r = Z_DATA_ERROR; + } + ZFREE(z, v); + return r; +} + + +int inflate_trees_dynamic(nl, nd, c, bl, bd, tl, td, hp, z) +uInt nl; /* number of literal/length codes */ +uInt nd; /* number of distance codes */ +uIntf *c; /* that many (total) code lengths */ +uIntf *bl; /* literal desired/actual bit depth */ +uIntf *bd; /* distance desired/actual bit depth */ +inflate_huft * FAR *tl; /* literal/length tree result */ +inflate_huft * FAR *td; /* distance tree result */ +inflate_huft *hp; /* space for trees */ +z_streamp z; /* for messages */ +{ + int r; + uInt hn = 0; /* hufts used in space */ + uIntf *v; /* work area for huft_build */ + + /* allocate work area */ + if ((v = (uIntf*)ZALLOC(z, 288, sizeof(uInt))) == Z_NULL) + return Z_MEM_ERROR; + + /* build literal/length tree */ + r = huft_build(c, nl, 257, cplens, cplext, tl, bl, hp, &hn, v); + if (r != Z_OK || *bl == 0) + { + if (r == Z_DATA_ERROR) + z->msg = (char*)"oversubscribed literal/length tree"; + else if (r != Z_MEM_ERROR) + { + z->msg = (char*)"incomplete literal/length tree"; + r = Z_DATA_ERROR; + } + ZFREE(z, v); + return r; + } + + /* build distance tree */ + r = huft_build(c + nl, nd, 0, cpdist, cpdext, td, bd, hp, &hn, v); + if (r != Z_OK || (*bd == 0 && nl > 257)) + { + if (r == Z_DATA_ERROR) + z->msg = (char*)"oversubscribed distance tree"; + else if (r == Z_BUF_ERROR) { +#ifdef PKZIP_BUG_WORKAROUND + r = Z_OK; + } +#else + z->msg = (char*)"incomplete distance tree"; + r = Z_DATA_ERROR; + } + else if (r != Z_MEM_ERROR) + { + z->msg = (char*)"empty distance tree with lengths"; + r = Z_DATA_ERROR; + } + ZFREE(z, v); + return r; +#endif + } + + /* done */ + ZFREE(z, v); + return Z_OK; +} + + +/* build fixed tables only once--keep them here */ +#ifdef BUILDFIXED +local int fixed_built = 0; +#define FIXEDH 544 /* number of hufts used by fixed tables */ +local inflate_huft fixed_mem[FIXEDH]; +local uInt fixed_bl; +local uInt fixed_bd; +local inflate_huft *fixed_tl; +local inflate_huft *fixed_td; +#else +#include "inffixed.h" +#endif + + +int inflate_trees_fixed(bl, bd, tl, td, z) +uIntf *bl; /* literal desired/actual bit depth */ +uIntf *bd; /* distance desired/actual bit depth */ +inflate_huft * FAR *tl; /* literal/length tree result */ +inflate_huft * FAR *td; /* distance tree result */ +z_streamp z; /* for memory allocation */ +{ +#ifdef BUILDFIXED + /* build fixed tables if not already */ + if (!fixed_built) + { + int k; /* temporary variable */ + uInt f = 0; /* number of hufts used in fixed_mem */ + uIntf *c; /* length list for huft_build */ + uIntf *v; /* work area for huft_build */ + + /* allocate memory */ + if ((c = (uIntf*)ZALLOC(z, 288, sizeof(uInt))) == Z_NULL) + return Z_MEM_ERROR; + if ((v = (uIntf*)ZALLOC(z, 288, sizeof(uInt))) == Z_NULL) + { + ZFREE(z, c); + return Z_MEM_ERROR; + } + + /* literal table */ + for (k = 0; k < 144; k++) + c[k] = 8; + for (; k < 256; k++) + c[k] = 9; + for (; k < 280; k++) + c[k] = 7; + for (; k < 288; k++) + c[k] = 8; + fixed_bl = 9; + huft_build(c, 288, 257, cplens, cplext, &fixed_tl, &fixed_bl, + fixed_mem, &f, v); + + /* distance table */ + for (k = 0; k < 30; k++) + c[k] = 5; + fixed_bd = 5; + huft_build(c, 30, 0, cpdist, cpdext, &fixed_td, &fixed_bd, + fixed_mem, &f, v); + + /* done */ + ZFREE(z, v); + ZFREE(z, c); + fixed_built = 1; + } +#endif + *bl = fixed_bl; + *bd = fixed_bd; + *tl = fixed_tl; + *td = fixed_td; + return Z_OK; +} diff --git a/zlib/inftrees.h b/zlib/inftrees.h new file mode 100644 index 0000000..affbb3b --- /dev/null +++ b/zlib/inftrees.h @@ -0,0 +1,58 @@ +/* inftrees.h -- header to use inftrees.c + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +/* Huffman code lookup table entry--this entry is four bytes for machines + that have 16-bit pointers (e.g. PC's in the small or medium model). */ + +typedef struct inflate_huft_s FAR inflate_huft; + +struct inflate_huft_s { + union { + struct { + Byte Exop; /* number of extra bits or operation */ + Byte Bits; /* number of bits in this code or subcode */ + } what; + uInt pad; /* pad structure to a power of 2 (4 bytes for */ + } word; /* 16-bit, 8 bytes for 32-bit int's) */ + uInt base; /* literal, length base, distance base, + or table offset */ +}; + +/* Maximum size of dynamic tree. The maximum found in a long but non- + exhaustive search was 1004 huft structures (850 for length/literals + and 154 for distances, the latter actually the result of an + exhaustive search). The actual maximum is not known, but the + value below is more than safe. */ +#define MANY 1440 + +extern int inflate_trees_bits OF(( + uIntf *, /* 19 code lengths */ + uIntf *, /* bits tree desired/actual depth */ + inflate_huft * FAR *, /* bits tree result */ + inflate_huft *, /* space for trees */ + z_streamp)); /* for messages */ + +extern int inflate_trees_dynamic OF(( + uInt, /* number of literal/length codes */ + uInt, /* number of distance codes */ + uIntf *, /* that many (total) code lengths */ + uIntf *, /* literal desired/actual bit depth */ + uIntf *, /* distance desired/actual bit depth */ + inflate_huft * FAR *, /* literal/length tree result */ + inflate_huft * FAR *, /* distance tree result */ + inflate_huft *, /* space for trees */ + z_streamp)); /* for messages */ + +extern int inflate_trees_fixed OF(( + uIntf *, /* literal desired/actual bit depth */ + uIntf *, /* distance desired/actual bit depth */ + inflate_huft * FAR *, /* literal/length tree result */ + inflate_huft * FAR *, /* distance tree result */ + z_streamp)); /* for memory allocation */ diff --git a/zlib/infutil.c b/zlib/infutil.c new file mode 100644 index 0000000..976d5e5 --- /dev/null +++ b/zlib/infutil.c @@ -0,0 +1,87 @@ +/* inflate_util.c -- data and routines common to blocks and codes + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "infblock.h" +#include "inftrees.h" +#include "infcodes.h" +#include "infutil.h" + +struct inflate_codes_state {int dummy;}; /* for buggy compilers */ + +/* And'ing with mask[n] masks the lower n bits */ +uInt inflate_mask[17] = { + 0x0000, + 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, + 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff +}; + + +/* copy as much as possible from the sliding window to the output area */ +int inflate_flush(s, z, r) +inflate_blocks_statef *s; +z_streamp z; +int r; +{ + uInt n; + Bytef *p; + Bytef *q; + + /* local copies of source and destination pointers */ + p = z->next_out; + q = s->read; + + /* compute number of bytes to copy as far as end of window */ + n = (uInt)((q <= s->write ? s->write : s->end) - q); + if (n > z->avail_out) n = z->avail_out; + if (n && r == Z_BUF_ERROR) r = Z_OK; + + /* update counters */ + z->avail_out -= n; + z->total_out += n; + + /* update check information */ + if (s->checkfn != Z_NULL) + z->adler = s->check = (*s->checkfn)(s->check, q, n); + + /* copy as far as end of window */ + zmemcpy(p, q, n); + p += n; + q += n; + + /* see if more to copy at beginning of window */ + if (q == s->end) + { + /* wrap pointers */ + q = s->window; + if (s->write == s->end) + s->write = s->window; + + /* compute bytes to copy */ + n = (uInt)(s->write - q); + if (n > z->avail_out) n = z->avail_out; + if (n && r == Z_BUF_ERROR) r = Z_OK; + + /* update counters */ + z->avail_out -= n; + z->total_out += n; + + /* update check information */ + if (s->checkfn != Z_NULL) + z->adler = s->check = (*s->checkfn)(s->check, q, n); + + /* copy */ + zmemcpy(p, q, n); + p += n; + q += n; + } + + /* update pointers */ + z->next_out = p; + s->read = q; + + /* done */ + return r; +} diff --git a/zlib/infutil.h b/zlib/infutil.h new file mode 100644 index 0000000..0c0ace3 --- /dev/null +++ b/zlib/infutil.h @@ -0,0 +1,98 @@ +/* infutil.h -- types and macros common to blocks and codes + * Copyright (C) 1995-2002 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +#ifndef _INFUTIL_H +#define _INFUTIL_H + +typedef enum { + TYPE, /* get type bits (3, including end bit) */ + LENS, /* get lengths for stored */ + STORED, /* processing stored block */ + TABLE, /* get table lengths */ + BTREE, /* get bit lengths tree for a dynamic block */ + DTREE, /* get length, distance trees for a dynamic block */ + CODES, /* processing fixed or dynamic block */ + DRY, /* output remaining window bytes */ + DONE, /* finished last block, done */ + BAD} /* got a data error--stuck here */ +inflate_block_mode; + +/* inflate blocks semi-private state */ +struct inflate_blocks_state { + + /* mode */ + inflate_block_mode mode; /* current inflate_block mode */ + + /* mode dependent information */ + union { + uInt left; /* if STORED, bytes left to copy */ + struct { + uInt table; /* table lengths (14 bits) */ + uInt index; /* index into blens (or border) */ + uIntf *blens; /* bit lengths of codes */ + uInt bb; /* bit length tree depth */ + inflate_huft *tb; /* bit length decoding tree */ + } trees; /* if DTREE, decoding info for trees */ + struct { + inflate_codes_statef + *codes; + } decode; /* if CODES, current state */ + } sub; /* submode */ + uInt last; /* true if this block is the last block */ + + /* mode independent information */ + uInt bitk; /* bits in bit buffer */ + uLong bitb; /* bit buffer */ + inflate_huft *hufts; /* single malloc for tree space */ + Bytef *window; /* sliding window */ + Bytef *end; /* one byte after sliding window */ + Bytef *read; /* window read pointer */ + Bytef *write; /* window write pointer */ + check_func checkfn; /* check function */ + uLong check; /* check on output */ + +}; + + +/* defines for inflate input/output */ +/* update pointers and return */ +#define UPDBITS {s->bitb=b;s->bitk=k;} +#define UPDIN {z->avail_in=n;z->total_in+=p-z->next_in;z->next_in=p;} +#define UPDOUT {s->write=q;} +#define UPDATE {UPDBITS UPDIN UPDOUT} +#define LEAVE {UPDATE return inflate_flush(s,z,r);} +/* get bytes and bits */ +#define LOADIN {p=z->next_in;n=z->avail_in;b=s->bitb;k=s->bitk;} +#define NEEDBYTE {if(n)r=Z_OK;else LEAVE} +#define NEXTBYTE (n--,*p++) +#define NEEDBITS(j) {while(k<(j)){NEEDBYTE;b|=((uLong)NEXTBYTE)<>=(j);k-=(j);} +/* output bytes */ +#define WAVAIL (uInt)(qread?s->read-q-1:s->end-q) +#define LOADOUT {q=s->write;m=(uInt)WAVAIL;} +#define WRAP {if(q==s->end&&s->read!=s->window){q=s->window;m=(uInt)WAVAIL;}} +#define FLUSH {UPDOUT r=inflate_flush(s,z,r); LOADOUT} +#define NEEDOUT {if(m==0){WRAP if(m==0){FLUSH WRAP if(m==0) LEAVE}}r=Z_OK;} +#define OUTBYTE(a) {*q++=(Byte)(a);m--;} +/* load local pointers */ +#define LOAD {LOADIN LOADOUT} + +/* masks for lower bits (size given to avoid silly warnings with Visual C++) */ +extern uInt inflate_mask[17]; + +/* copy as much as possible from the sliding window to the output area */ +extern int inflate_flush OF(( + inflate_blocks_statef *, + z_streamp , + int)); + +struct internal_state {int dummy;}; /* for buggy compilers */ + +#endif diff --git a/zlib/zconf.h b/zlib/zconf.h new file mode 100644 index 0000000..b2dbeaf --- /dev/null +++ b/zlib/zconf.h @@ -0,0 +1,280 @@ +/* zconf.h -- configuration of the zlib compression library + * Copyright (C) 1995-2002 Jean-loup Gailly. + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* @(#) $Id$ */ + +#ifndef _ZCONF_H +#define _ZCONF_H + +/* + * If you *really* need a unique prefix for all types and library functions, + * compile with -DZ_PREFIX. The "standard" zlib should be compiled without it. + */ +#ifdef Z_PREFIX +# define deflateInit_ z_deflateInit_ +# define deflate z_deflate +# define deflateEnd z_deflateEnd +# define inflateInit_ z_inflateInit_ +# define inflate z_inflate +# define inflateEnd z_inflateEnd +# define deflateInit2_ z_deflateInit2_ +# define deflateSetDictionary z_deflateSetDictionary +# define deflateCopy z_deflateCopy +# define deflateReset z_deflateReset +# define deflateParams z_deflateParams +# define inflateInit2_ z_inflateInit2_ +# define inflateSetDictionary z_inflateSetDictionary +# define inflateSync z_inflateSync +# define inflateSyncPoint z_inflateSyncPoint +# define inflateReset z_inflateReset +# define compress z_compress +# define compress2 z_compress2 +# define uncompress z_uncompress +# define adler32 z_adler32 +# define crc32 z_crc32 +# define get_crc_table z_get_crc_table + +# define Byte z_Byte +# define uInt z_uInt +# define uLong z_uLong +# define Bytef z_Bytef +# define charf z_charf +# define intf z_intf +# define uIntf z_uIntf +# define uLongf z_uLongf +# define voidpf z_voidpf +# define voidp z_voidp +#endif + +#if (defined(_WIN32) || defined(__WIN32__)) && !defined(WIN32) +# define WIN32 +#endif +#if defined(__GNUC__) || defined(WIN32) || defined(__386__) || defined(i386) +# ifndef __32BIT__ +# define __32BIT__ +# endif +#endif +#if defined(__MSDOS__) && !defined(MSDOS) +# define MSDOS +#endif + +/* + * Compile with -DMAXSEG_64K if the alloc function cannot allocate more + * than 64k bytes at a time (needed on systems with 16-bit int). + */ +#if defined(MSDOS) && !defined(__32BIT__) +# define MAXSEG_64K +#endif +#ifdef MSDOS +# define UNALIGNED_OK +#endif + +#if (defined(MSDOS) || defined(_WINDOWS) || defined(WIN32)) && !defined(STDC) +# define STDC +#endif +#if defined(__STDC__) || defined(__cplusplus) || defined(__OS2__) +# ifndef STDC +# define STDC +# endif +#endif + +#ifndef STDC +# ifndef const /* cannot use !defined(STDC) && !defined(const) on Mac */ +# define const +# endif +#endif + +/* Some Mac compilers merge all .h files incorrectly: */ +#if defined(__MWERKS__) || defined(applec) ||defined(THINK_C) ||defined(__SC__) +# define NO_DUMMY_DECL +#endif + +/* Old Borland C incorrectly complains about missing returns: */ +#if defined(__BORLANDC__) && (__BORLANDC__ < 0x500) +# define NEED_DUMMY_RETURN +#endif + + +/* Maximum value for memLevel in deflateInit2 */ +#ifndef MAX_MEM_LEVEL +# ifdef MAXSEG_64K +# define MAX_MEM_LEVEL 8 +# else +# define MAX_MEM_LEVEL 9 +# endif +#endif + +/* Maximum value for windowBits in deflateInit2 and inflateInit2. + * WARNING: reducing MAX_WBITS makes minigzip unable to extract .gz files + * created by gzip. (Files created by minigzip can still be extracted by + * gzip.) + */ +#ifndef MAX_WBITS +# define MAX_WBITS 15 /* 32K LZ77 window */ +#endif + +/* The memory requirements for deflate are (in bytes): + (1 << (windowBits+2)) + (1 << (memLevel+9)) + that is: 128K for windowBits=15 + 128K for memLevel = 8 (default values) + plus a few kilobytes for small objects. For example, if you want to reduce + the default memory requirements from 256K to 128K, compile with + make CFLAGS="-O -DMAX_WBITS=14 -DMAX_MEM_LEVEL=7" + Of course this will generally degrade compression (there's no free lunch). + + The memory requirements for inflate are (in bytes) 1 << windowBits + that is, 32K for windowBits=15 (default value) plus a few kilobytes + for small objects. +*/ + + /* Type declarations */ + +#ifndef OF /* function prototypes */ +# ifdef STDC +# define OF(args) args +# else +# define OF(args) () +# endif +#endif + +/* The following definitions for FAR are needed only for MSDOS mixed + * model programming (small or medium model with some far allocations). + * This was tested only with MSC; for other MSDOS compilers you may have + * to define NO_MEMCPY in zutil.h. If you don't need the mixed model, + * just define FAR to be empty. + */ +#if (defined(M_I86SM) || defined(M_I86MM)) && !defined(__32BIT__) + /* MSC small or medium model */ +# define SMALL_MEDIUM +# ifdef _MSC_VER +# define FAR _far +# else +# define FAR far +# endif +#endif +#if defined(__BORLANDC__) && (defined(__SMALL__) || defined(__MEDIUM__)) +# ifndef __32BIT__ +# define SMALL_MEDIUM +# define FAR _far +# endif +#endif + +/* Compile with -DZLIB_DLL for Windows DLL support */ +#if defined(ZLIB_DLL) +# if defined(_WINDOWS) || defined(WINDOWS) +# ifdef FAR +# undef FAR +# endif +# include +# define ZEXPORT WINAPI +# define ZEXTERN __declspec(dllexport) // dll export 를 위해서 추가.. +# ifdef WIN32 +# define ZEXPORTVA WINAPIV +# else +# define ZEXPORTVA FAR _cdecl _export +# endif +# endif +# if defined (__BORLANDC__) +# if (__BORLANDC__ >= 0x0500) && defined (WIN32) +# include +# define ZEXPORT __declspec(dllexport) WINAPI +# define ZEXPORTRVA __declspec(dllexport) WINAPIV +# else +# if defined (_Windows) && defined (__DLL__) +# define ZEXPORT _export +# define ZEXPORTVA _export +# endif +# endif +# endif +#endif + +#if defined (__BEOS__) +# if defined (ZLIB_DLL) +# define ZEXTERN extern __declspec(dllexport) +# else +# define ZEXTERN extern __declspec(dllimport) +# endif +#endif + +#ifndef ZEXPORT +# define ZEXPORT +#endif +#ifndef ZEXPORTVA +# define ZEXPORTVA +#endif +#ifndef ZEXTERN +# define ZEXTERN ///extern STATIC lib 를 위해서 막아버림.. +#endif + +#ifndef FAR +# define FAR +#endif + +#if !defined(MACOS) && !defined(TARGET_OS_MAC) +typedef unsigned char Byte; /* 8 bits */ +#endif +typedef unsigned int uInt; /* 16 bits or more */ +typedef unsigned long uLong; /* 32 bits or more */ + +#ifdef SMALL_MEDIUM + /* Borland C/C++ and some old MSC versions ignore FAR inside typedef */ +# define Bytef Byte FAR +#else + typedef Byte FAR Bytef; +#endif +typedef char FAR charf; +typedef int FAR intf; +typedef uInt FAR uIntf; +typedef uLong FAR uLongf; + +#ifdef STDC + typedef void FAR *voidpf; + typedef void *voidp; +#else + typedef Byte FAR *voidpf; + typedef Byte *voidp; +#endif + +#ifdef HAVE_UNISTD_H +# include /* for off_t */ +# include /* for SEEK_* and off_t */ +# define z_off_t off_t +#endif +#ifndef SEEK_SET +# define SEEK_SET 0 /* Seek from beginning of file. */ +# define SEEK_CUR 1 /* Seek from current position. */ +# define SEEK_END 2 /* Set file pointer to EOF plus "offset" */ +#endif +#ifndef z_off_t +# define z_off_t long +#endif + +/* MVS linker does not support external names larger than 8 bytes */ +#if defined(__MVS__) +# pragma map(deflateInit_,"DEIN") +# pragma map(deflateInit2_,"DEIN2") +# pragma map(deflateEnd,"DEEND") +# pragma map(inflateInit_,"ININ") +# pragma map(inflateInit2_,"ININ2") +# pragma map(inflateEnd,"INEND") +# pragma map(inflateSync,"INSY") +# pragma map(inflateSetDictionary,"INSEDI") +# pragma map(inflate_blocks,"INBL") +# pragma map(inflate_blocks_new,"INBLNE") +# pragma map(inflate_blocks_free,"INBLFR") +# pragma map(inflate_blocks_reset,"INBLRE") +# pragma map(inflate_codes_free,"INCOFR") +# pragma map(inflate_codes,"INCO") +# pragma map(inflate_fast,"INFA") +# pragma map(inflate_flush,"INFLU") +# pragma map(inflate_mask,"INMA") +# pragma map(inflate_set_dictionary,"INSEDI2") +# pragma map(inflate_copyright,"INCOPY") +# pragma map(inflate_trees_bits,"INTRBI") +# pragma map(inflate_trees_dynamic,"INTRDY") +# pragma map(inflate_trees_fixed,"INTRFI") +# pragma map(inflate_trees_free,"INTRFR") +#endif + +#endif /* _ZCONF_H */ diff --git a/zlib/zlib.h b/zlib/zlib.h new file mode 100644 index 0000000..3d563f7 --- /dev/null +++ b/zlib/zlib.h @@ -0,0 +1,888 @@ +/* zlib.h -- interface of the 'zlib' general purpose compression library + version 1.1.4, March 11th, 2002 + + Copyright (C) 1995-2002 Jean-loup Gailly and Mark Adler + + This software is provided 'as-is', without any express or implied + warranty. In no event will the authors be held liable for any damages + arising from the use of this software. + + Permission is granted to anyone to use this software for any purpose, + including commercial applications, and to alter it and redistribute it + freely, subject to the following restrictions: + + 1. The origin of this software must not be misrepresented; you must not + claim that you wrote the original software. If you use this software + in a product, an acknowledgment in the product documentation would be + appreciated but is not required. + 2. Altered source versions must be plainly marked as such, and must not be + misrepresented as being the original software. + 3. This notice may not be removed or altered from any source distribution. + + Jean-loup Gailly Mark Adler + jloup@gzip.org madler@alumni.caltech.edu + + + The data format used by the zlib library is described by RFCs (Request for + Comments) 1950 to 1952 in the files ftp://ds.internic.net/rfc/rfc1950.txt + (zlib format), rfc1951.txt (deflate format) and rfc1952.txt (gzip format). +*/ + +#ifndef _ZLIB_H +#define _ZLIB_H + +#include "zconf.h" + +#ifdef __cplusplus +extern "C" { +#endif + +#define ZLIB_VERSION "1.1.4" + +/* + The 'zlib' compression library provides in-memory compression and + decompression functions, including integrity checks of the uncompressed + data. This version of the library supports only one compression method + (deflation) but other algorithms will be added later and will have the same + stream interface. + + Compression can be done in a single step if the buffers are large + enough (for example if an input file is mmap'ed), or can be done by + repeated calls of the compression function. In the latter case, the + application must provide more input and/or consume the output + (providing more output space) before each call. + + The library also supports reading and writing files in gzip (.gz) format + with an interface similar to that of stdio. + + The library does not install any signal handler. The decoder checks + the consistency of the compressed data, so the library should never + crash even in case of corrupted input. +*/ + +typedef voidpf (*alloc_func) OF((voidpf opaque, uInt items, uInt size)); +typedef void (*free_func) OF((voidpf opaque, voidpf address)); + +struct internal_state; + +typedef struct z_stream_s { + Bytef *next_in; /* next input byte */ + uInt avail_in; /* number of bytes available at next_in */ + uLong total_in; /* total nb of input bytes read so far */ + + Bytef *next_out; /* next output byte should be put there */ + uInt avail_out; /* remaining free space at next_out */ + uLong total_out; /* total nb of bytes output so far */ + + char *msg; /* last error message, NULL if no error */ + struct internal_state FAR *state; /* not visible by applications */ + + alloc_func zalloc; /* used to allocate the internal state */ + free_func zfree; /* used to free the internal state */ + voidpf opaque; /* private data object passed to zalloc and zfree */ + + int data_type; /* best guess about the data type: ascii or binary */ + uLong adler; /* adler32 value of the uncompressed data */ + uLong reserved; /* reserved for future use */ +} z_stream; + +typedef z_stream FAR *z_streamp; + +/* + The application must update next_in and avail_in when avail_in has + dropped to zero. It must update next_out and avail_out when avail_out + has dropped to zero. The application must initialize zalloc, zfree and + opaque before calling the init function. All other fields are set by the + compression library and must not be updated by the application. + + The opaque value provided by the application will be passed as the first + parameter for calls of zalloc and zfree. This can be useful for custom + memory management. The compression library attaches no meaning to the + opaque value. + + zalloc must return Z_NULL if there is not enough memory for the object. + If zlib is used in a multi-threaded application, zalloc and zfree must be + thread safe. + + On 16-bit systems, the functions zalloc and zfree must be able to allocate + exactly 65536 bytes, but will not be required to allocate more than this + if the symbol MAXSEG_64K is defined (see zconf.h). WARNING: On MSDOS, + pointers returned by zalloc for objects of exactly 65536 bytes *must* + have their offset normalized to zero. The default allocation function + provided by this library ensures this (see zutil.c). To reduce memory + requirements and avoid any allocation of 64K objects, at the expense of + compression ratio, compile the library with -DMAX_WBITS=14 (see zconf.h). + + The fields total_in and total_out can be used for statistics or + progress reports. After compression, total_in holds the total size of + the uncompressed data and may be saved for use in the decompressor + (particularly if the decompressor wants to decompress everything in + a single step). +*/ + + /* constants */ + +#define Z_NO_FLUSH 0 +#define Z_PARTIAL_FLUSH 1 /* will be removed, use Z_SYNC_FLUSH instead */ +#define Z_SYNC_FLUSH 2 +#define Z_FULL_FLUSH 3 +#define Z_FINISH 4 +/* Allowed flush values; see deflate() below for details */ + +#define Z_OK 0 +#define Z_STREAM_END 1 +#define Z_NEED_DICT 2 +#define Z_ERRNO (-1) +#define Z_STREAM_ERROR (-2) +#define Z_DATA_ERROR (-3) +#define Z_MEM_ERROR (-4) +#define Z_BUF_ERROR (-5) +#define Z_VERSION_ERROR (-6) +/* Return codes for the compression/decompression functions. Negative + * values are errors, positive values are used for special but normal events. + */ + +#define Z_NO_COMPRESSION 0 +#define Z_BEST_SPEED 1 +#define Z_BEST_COMPRESSION 9 +#define Z_DEFAULT_COMPRESSION (-1) +/* compression levels */ + +#define Z_FILTERED 1 +#define Z_HUFFMAN_ONLY 2 +#define Z_DEFAULT_STRATEGY 0 +/* compression strategy; see deflateInit2() below for details */ + +#define Z_BINARY 0 +#define Z_ASCII 1 +#define Z_UNKNOWN 2 +/* Possible values of the data_type field */ + +#define Z_DEFLATED 8 +/* The deflate compression method (the only one supported in this version) */ + +#define Z_NULL 0 /* for initializing zalloc, zfree, opaque */ + +#define zlib_version zlibVersion() +/* for compatibility with versions < 1.0.2 */ + + /* basic functions */ + +ZEXTERN const char * ZEXPORT zlibVersion OF((void)); +/* The application can compare zlibVersion and ZLIB_VERSION for consistency. + If the first character differs, the library code actually used is + not compatible with the zlib.h header file used by the application. + This check is automatically made by deflateInit and inflateInit. + */ + +/* +ZEXTERN int ZEXPORT deflateInit OF((z_streamp strm, int level)); + + Initializes the internal stream state for compression. The fields + zalloc, zfree and opaque must be initialized before by the caller. + If zalloc and zfree are set to Z_NULL, deflateInit updates them to + use default allocation functions. + + The compression level must be Z_DEFAULT_COMPRESSION, or between 0 and 9: + 1 gives best speed, 9 gives best compression, 0 gives no compression at + all (the input data is simply copied a block at a time). + Z_DEFAULT_COMPRESSION requests a default compromise between speed and + compression (currently equivalent to level 6). + + deflateInit returns Z_OK if success, Z_MEM_ERROR if there was not + enough memory, Z_STREAM_ERROR if level is not a valid compression level, + Z_VERSION_ERROR if the zlib library version (zlib_version) is incompatible + with the version assumed by the caller (ZLIB_VERSION). + msg is set to null if there is no error message. deflateInit does not + perform any compression: this will be done by deflate(). +*/ + + +ZEXTERN int ZEXPORT deflate OF((z_streamp strm, int flush)); +/* + deflate compresses as much data as possible, and stops when the input + buffer becomes empty or the output buffer becomes full. It may introduce some + output latency (reading input without producing any output) except when + forced to flush. + + The detailed semantics are as follows. deflate performs one or both of the + following actions: + + - Compress more input starting at next_in and update next_in and avail_in + accordingly. If not all input can be processed (because there is not + enough room in the output buffer), next_in and avail_in are updated and + processing will resume at this point for the next call of deflate(). + + - Provide more output starting at next_out and update next_out and avail_out + accordingly. This action is forced if the parameter flush is non zero. + Forcing flush frequently degrades the compression ratio, so this parameter + should be set only when necessary (in interactive applications). + Some output may be provided even if flush is not set. + + Before the call of deflate(), the application should ensure that at least + one of the actions is possible, by providing more input and/or consuming + more output, and updating avail_in or avail_out accordingly; avail_out + should never be zero before the call. The application can consume the + compressed output when it wants, for example when the output buffer is full + (avail_out == 0), or after each call of deflate(). If deflate returns Z_OK + and with zero avail_out, it must be called again after making room in the + output buffer because there might be more output pending. + + If the parameter flush is set to Z_SYNC_FLUSH, all pending output is + flushed to the output buffer and the output is aligned on a byte boundary, so + that the decompressor can get all input data available so far. (In particular + avail_in is zero after the call if enough output space has been provided + before the call.) Flushing may degrade compression for some compression + algorithms and so it should be used only when necessary. + + If flush is set to Z_FULL_FLUSH, all output is flushed as with + Z_SYNC_FLUSH, and the compression state is reset so that decompression can + restart from this point if previous compressed data has been damaged or if + random access is desired. Using Z_FULL_FLUSH too often can seriously degrade + the compression. + + If deflate returns with avail_out == 0, this function must be called again + with the same value of the flush parameter and more output space (updated + avail_out), until the flush is complete (deflate returns with non-zero + avail_out). + + If the parameter flush is set to Z_FINISH, pending input is processed, + pending output is flushed and deflate returns with Z_STREAM_END if there + was enough output space; if deflate returns with Z_OK, this function must be + called again with Z_FINISH and more output space (updated avail_out) but no + more input data, until it returns with Z_STREAM_END or an error. After + deflate has returned Z_STREAM_END, the only possible operations on the + stream are deflateReset or deflateEnd. + + Z_FINISH can be used immediately after deflateInit if all the compression + is to be done in a single step. In this case, avail_out must be at least + 0.1% larger than avail_in plus 12 bytes. If deflate does not return + Z_STREAM_END, then it must be called again as described above. + + deflate() sets strm->adler to the adler32 checksum of all input read + so far (that is, total_in bytes). + + deflate() may update data_type if it can make a good guess about + the input data type (Z_ASCII or Z_BINARY). In doubt, the data is considered + binary. This field is only for information purposes and does not affect + the compression algorithm in any manner. + + deflate() returns Z_OK if some progress has been made (more input + processed or more output produced), Z_STREAM_END if all input has been + consumed and all output has been produced (only when flush is set to + Z_FINISH), Z_STREAM_ERROR if the stream state was inconsistent (for example + if next_in or next_out was NULL), Z_BUF_ERROR if no progress is possible + (for example avail_in or avail_out was zero). +*/ + + +ZEXTERN int ZEXPORT deflateEnd OF((z_streamp strm)); +/* + All dynamically allocated data structures for this stream are freed. + This function discards any unprocessed input and does not flush any + pending output. + + deflateEnd returns Z_OK if success, Z_STREAM_ERROR if the + stream state was inconsistent, Z_DATA_ERROR if the stream was freed + prematurely (some input or output was discarded). In the error case, + msg may be set but then points to a static string (which must not be + deallocated). +*/ + + +/* +ZEXTERN int ZEXPORT inflateInit OF((z_streamp strm)); + + Initializes the internal stream state for decompression. The fields + next_in, avail_in, zalloc, zfree and opaque must be initialized before by + the caller. If next_in is not Z_NULL and avail_in is large enough (the exact + value depends on the compression method), inflateInit determines the + compression method from the zlib header and allocates all data structures + accordingly; otherwise the allocation will be deferred to the first call of + inflate. If zalloc and zfree are set to Z_NULL, inflateInit updates them to + use default allocation functions. + + inflateInit returns Z_OK if success, Z_MEM_ERROR if there was not enough + memory, Z_VERSION_ERROR if the zlib library version is incompatible with the + version assumed by the caller. msg is set to null if there is no error + message. inflateInit does not perform any decompression apart from reading + the zlib header if present: this will be done by inflate(). (So next_in and + avail_in may be modified, but next_out and avail_out are unchanged.) +*/ + + +ZEXTERN int ZEXPORT inflate OF((z_streamp strm, int flush)); +/* + inflate decompresses as much data as possible, and stops when the input + buffer becomes empty or the output buffer becomes full. It may some + introduce some output latency (reading input without producing any output) + except when forced to flush. + + The detailed semantics are as follows. inflate performs one or both of the + following actions: + + - Decompress more input starting at next_in and update next_in and avail_in + accordingly. If not all input can be processed (because there is not + enough room in the output buffer), next_in is updated and processing + will resume at this point for the next call of inflate(). + + - Provide more output starting at next_out and update next_out and avail_out + accordingly. inflate() provides as much output as possible, until there + is no more input data or no more space in the output buffer (see below + about the flush parameter). + + Before the call of inflate(), the application should ensure that at least + one of the actions is possible, by providing more input and/or consuming + more output, and updating the next_* and avail_* values accordingly. + The application can consume the uncompressed output when it wants, for + example when the output buffer is full (avail_out == 0), or after each + call of inflate(). If inflate returns Z_OK and with zero avail_out, it + must be called again after making room in the output buffer because there + might be more output pending. + + If the parameter flush is set to Z_SYNC_FLUSH, inflate flushes as much + output as possible to the output buffer. The flushing behavior of inflate is + not specified for values of the flush parameter other than Z_SYNC_FLUSH + and Z_FINISH, but the current implementation actually flushes as much output + as possible anyway. + + inflate() should normally be called until it returns Z_STREAM_END or an + error. However if all decompression is to be performed in a single step + (a single call of inflate), the parameter flush should be set to + Z_FINISH. In this case all pending input is processed and all pending + output is flushed; avail_out must be large enough to hold all the + uncompressed data. (The size of the uncompressed data may have been saved + by the compressor for this purpose.) The next operation on this stream must + be inflateEnd to deallocate the decompression state. The use of Z_FINISH + is never required, but can be used to inform inflate that a faster routine + may be used for the single inflate() call. + + If a preset dictionary is needed at this point (see inflateSetDictionary + below), inflate sets strm-adler to the adler32 checksum of the + dictionary chosen by the compressor and returns Z_NEED_DICT; otherwise + it sets strm->adler to the adler32 checksum of all output produced + so far (that is, total_out bytes) and returns Z_OK, Z_STREAM_END or + an error code as described below. At the end of the stream, inflate() + checks that its computed adler32 checksum is equal to that saved by the + compressor and returns Z_STREAM_END only if the checksum is correct. + + inflate() returns Z_OK if some progress has been made (more input processed + or more output produced), Z_STREAM_END if the end of the compressed data has + been reached and all uncompressed output has been produced, Z_NEED_DICT if a + preset dictionary is needed at this point, Z_DATA_ERROR if the input data was + corrupted (input stream not conforming to the zlib format or incorrect + adler32 checksum), Z_STREAM_ERROR if the stream structure was inconsistent + (for example if next_in or next_out was NULL), Z_MEM_ERROR if there was not + enough memory, Z_BUF_ERROR if no progress is possible or if there was not + enough room in the output buffer when Z_FINISH is used. In the Z_DATA_ERROR + case, the application may then call inflateSync to look for a good + compression block. +*/ + + +ZEXTERN int ZEXPORT inflateEnd OF((z_streamp strm)); +/* + All dynamically allocated data structures for this stream are freed. + This function discards any unprocessed input and does not flush any + pending output. + + inflateEnd returns Z_OK if success, Z_STREAM_ERROR if the stream state + was inconsistent. In the error case, msg may be set but then points to a + static string (which must not be deallocated). +*/ + + /* Advanced functions */ + +/* + The following functions are needed only in some special applications. +*/ + +/* +ZEXTERN int ZEXPORT deflateInit2 OF((z_streamp strm, + int level, + int method, + int windowBits, + int memLevel, + int strategy)); + + This is another version of deflateInit with more compression options. The + fields next_in, zalloc, zfree and opaque must be initialized before by + the caller. + + The method parameter is the compression method. It must be Z_DEFLATED in + this version of the library. + + The windowBits parameter is the base two logarithm of the window size + (the size of the history buffer). It should be in the range 8..15 for this + version of the library. Larger values of this parameter result in better + compression at the expense of memory usage. The default value is 15 if + deflateInit is used instead. + + The memLevel parameter specifies how much memory should be allocated + for the internal compression state. memLevel=1 uses minimum memory but + is slow and reduces compression ratio; memLevel=9 uses maximum memory + for optimal speed. The default value is 8. See zconf.h for total memory + usage as a function of windowBits and memLevel. + + The strategy parameter is used to tune the compression algorithm. Use the + value Z_DEFAULT_STRATEGY for normal data, Z_FILTERED for data produced by a + filter (or predictor), or Z_HUFFMAN_ONLY to force Huffman encoding only (no + string match). Filtered data consists mostly of small values with a + somewhat random distribution. In this case, the compression algorithm is + tuned to compress them better. The effect of Z_FILTERED is to force more + Huffman coding and less string matching; it is somewhat intermediate + between Z_DEFAULT and Z_HUFFMAN_ONLY. The strategy parameter only affects + the compression ratio but not the correctness of the compressed output even + if it is not set appropriately. + + deflateInit2 returns Z_OK if success, Z_MEM_ERROR if there was not enough + memory, Z_STREAM_ERROR if a parameter is invalid (such as an invalid + method). msg is set to null if there is no error message. deflateInit2 does + not perform any compression: this will be done by deflate(). +*/ + +ZEXTERN int ZEXPORT deflateSetDictionary OF((z_streamp strm, + const Bytef *dictionary, + uInt dictLength)); +/* + Initializes the compression dictionary from the given byte sequence + without producing any compressed output. This function must be called + immediately after deflateInit, deflateInit2 or deflateReset, before any + call of deflate. The compressor and decompressor must use exactly the same + dictionary (see inflateSetDictionary). + + The dictionary should consist of strings (byte sequences) that are likely + to be encountered later in the data to be compressed, with the most commonly + used strings preferably put towards the end of the dictionary. Using a + dictionary is most useful when the data to be compressed is short and can be + predicted with good accuracy; the data can then be compressed better than + with the default empty dictionary. + + Depending on the size of the compression data structures selected by + deflateInit or deflateInit2, a part of the dictionary may in effect be + discarded, for example if the dictionary is larger than the window size in + deflate or deflate2. Thus the strings most likely to be useful should be + put at the end of the dictionary, not at the front. + + Upon return of this function, strm->adler is set to the Adler32 value + of the dictionary; the decompressor may later use this value to determine + which dictionary has been used by the compressor. (The Adler32 value + applies to the whole dictionary even if only a subset of the dictionary is + actually used by the compressor.) + + deflateSetDictionary returns Z_OK if success, or Z_STREAM_ERROR if a + parameter is invalid (such as NULL dictionary) or the stream state is + inconsistent (for example if deflate has already been called for this stream + or if the compression method is bsort). deflateSetDictionary does not + perform any compression: this will be done by deflate(). +*/ + +ZEXTERN int ZEXPORT deflateCopy OF((z_streamp dest, + z_streamp source)); +/* + Sets the destination stream as a complete copy of the source stream. + + This function can be useful when several compression strategies will be + tried, for example when there are several ways of pre-processing the input + data with a filter. The streams that will be discarded should then be freed + by calling deflateEnd. Note that deflateCopy duplicates the internal + compression state which can be quite large, so this strategy is slow and + can consume lots of memory. + + deflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not + enough memory, Z_STREAM_ERROR if the source stream state was inconsistent + (such as zalloc being NULL). msg is left unchanged in both source and + destination. +*/ + +ZEXTERN int ZEXPORT deflateReset OF((z_streamp strm)); +/* + This function is equivalent to deflateEnd followed by deflateInit, + but does not free and reallocate all the internal compression state. + The stream will keep the same compression level and any other attributes + that may have been set by deflateInit2. + + deflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source + stream state was inconsistent (such as zalloc or state being NULL). +*/ + +ZEXTERN int ZEXPORT deflateParams OF((z_streamp strm, + int level, + int strategy)); +/* + Dynamically update the compression level and compression strategy. The + interpretation of level and strategy is as in deflateInit2. This can be + used to switch between compression and straight copy of the input data, or + to switch to a different kind of input data requiring a different + strategy. If the compression level is changed, the input available so far + is compressed with the old level (and may be flushed); the new level will + take effect only at the next call of deflate(). + + Before the call of deflateParams, the stream state must be set as for + a call of deflate(), since the currently available input may have to + be compressed and flushed. In particular, strm->avail_out must be non-zero. + + deflateParams returns Z_OK if success, Z_STREAM_ERROR if the source + stream state was inconsistent or if a parameter was invalid, Z_BUF_ERROR + if strm->avail_out was zero. +*/ + +/* +ZEXTERN int ZEXPORT inflateInit2 OF((z_streamp strm, + int windowBits)); + + This is another version of inflateInit with an extra parameter. The + fields next_in, avail_in, zalloc, zfree and opaque must be initialized + before by the caller. + + The windowBits parameter is the base two logarithm of the maximum window + size (the size of the history buffer). It should be in the range 8..15 for + this version of the library. The default value is 15 if inflateInit is used + instead. If a compressed stream with a larger window size is given as + input, inflate() will return with the error code Z_DATA_ERROR instead of + trying to allocate a larger window. + + inflateInit2 returns Z_OK if success, Z_MEM_ERROR if there was not enough + memory, Z_STREAM_ERROR if a parameter is invalid (such as a negative + memLevel). msg is set to null if there is no error message. inflateInit2 + does not perform any decompression apart from reading the zlib header if + present: this will be done by inflate(). (So next_in and avail_in may be + modified, but next_out and avail_out are unchanged.) +*/ + +ZEXTERN int ZEXPORT inflateSetDictionary OF((z_streamp strm, + const Bytef *dictionary, + uInt dictLength)); +/* + Initializes the decompression dictionary from the given uncompressed byte + sequence. This function must be called immediately after a call of inflate + if this call returned Z_NEED_DICT. The dictionary chosen by the compressor + can be determined from the Adler32 value returned by this call of + inflate. The compressor and decompressor must use exactly the same + dictionary (see deflateSetDictionary). + + inflateSetDictionary returns Z_OK if success, Z_STREAM_ERROR if a + parameter is invalid (such as NULL dictionary) or the stream state is + inconsistent, Z_DATA_ERROR if the given dictionary doesn't match the + expected one (incorrect Adler32 value). inflateSetDictionary does not + perform any decompression: this will be done by subsequent calls of + inflate(). +*/ + +ZEXTERN int ZEXPORT inflateSync OF((z_streamp strm)); +/* + Skips invalid compressed data until a full flush point (see above the + description of deflate with Z_FULL_FLUSH) can be found, or until all + available input is skipped. No output is provided. + + inflateSync returns Z_OK if a full flush point has been found, Z_BUF_ERROR + if no more input was provided, Z_DATA_ERROR if no flush point has been found, + or Z_STREAM_ERROR if the stream structure was inconsistent. In the success + case, the application may save the current current value of total_in which + indicates where valid compressed data was found. In the error case, the + application may repeatedly call inflateSync, providing more input each time, + until success or end of the input data. +*/ + +ZEXTERN int ZEXPORT inflateReset OF((z_streamp strm)); +/* + This function is equivalent to inflateEnd followed by inflateInit, + but does not free and reallocate all the internal decompression state. + The stream will keep attributes that may have been set by inflateInit2. + + inflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source + stream state was inconsistent (such as zalloc or state being NULL). +*/ + + + /* utility functions */ + +/* + The following utility functions are implemented on top of the + basic stream-oriented functions. To simplify the interface, some + default options are assumed (compression level and memory usage, + standard memory allocation functions). The source code of these + utility functions can easily be modified if you need special options. +*/ + +ZEXTERN int ZEXPORT compress OF((Bytef *dest, uLongf *destLen, + const Bytef *source, uLong sourceLen)); +/* + Compresses the source buffer into the destination buffer. sourceLen is + the byte length of the source buffer. Upon entry, destLen is the total + size of the destination buffer, which must be at least 0.1% larger than + sourceLen plus 12 bytes. Upon exit, destLen is the actual size of the + compressed buffer. + This function can be used to compress a whole file at once if the + input file is mmap'ed. + compress returns Z_OK if success, Z_MEM_ERROR if there was not + enough memory, Z_BUF_ERROR if there was not enough room in the output + buffer. +*/ + +ZEXTERN int ZEXPORT compress2 OF((Bytef *dest, uLongf *destLen, + const Bytef *source, uLong sourceLen, + int level)); +/* + Compresses the source buffer into the destination buffer. The level + parameter has the same meaning as in deflateInit. sourceLen is the byte + length of the source buffer. Upon entry, destLen is the total size of the + destination buffer, which must be at least 0.1% larger than sourceLen plus + 12 bytes. Upon exit, destLen is the actual size of the compressed buffer. + + compress2 returns Z_OK if success, Z_MEM_ERROR if there was not enough + memory, Z_BUF_ERROR if there was not enough room in the output buffer, + Z_STREAM_ERROR if the level parameter is invalid. +*/ + +ZEXTERN int ZEXPORT uncompress OF((Bytef *dest, uLongf *destLen, + const Bytef *source, uLong sourceLen)); +/* + Decompresses the source buffer into the destination buffer. sourceLen is + the byte length of the source buffer. Upon entry, destLen is the total + size of the destination buffer, which must be large enough to hold the + entire uncompressed data. (The size of the uncompressed data must have + been saved previously by the compressor and transmitted to the decompressor + by some mechanism outside the scope of this compression library.) + Upon exit, destLen is the actual size of the compressed buffer. + This function can be used to decompress a whole file at once if the + input file is mmap'ed. + + uncompress returns Z_OK if success, Z_MEM_ERROR if there was not + enough memory, Z_BUF_ERROR if there was not enough room in the output + buffer, or Z_DATA_ERROR if the input data was corrupted. +*/ + + +typedef voidp gzFile; + +ZEXTERN gzFile ZEXPORT gzopen OF((const char *path, const char *mode)); +/* + Opens a gzip (.gz) file for reading or writing. The mode parameter + is as in fopen ("rb" or "wb") but can also include a compression level + ("wb9") or a strategy: 'f' for filtered data as in "wb6f", 'h' for + Huffman only compression as in "wb1h". (See the description + of deflateInit2 for more information about the strategy parameter.) + + gzopen can be used to read a file which is not in gzip format; in this + case gzread will directly read from the file without decompression. + + gzopen returns NULL if the file could not be opened or if there was + insufficient memory to allocate the (de)compression state; errno + can be checked to distinguish the two cases (if errno is zero, the + zlib error is Z_MEM_ERROR). */ + +ZEXTERN gzFile ZEXPORT gzdopen OF((int fd, const char *mode)); +/* + gzdopen() associates a gzFile with the file descriptor fd. File + descriptors are obtained from calls like open, dup, creat, pipe or + fileno (in the file has been previously opened with fopen). + The mode parameter is as in gzopen. + The next call of gzclose on the returned gzFile will also close the + file descriptor fd, just like fclose(fdopen(fd), mode) closes the file + descriptor fd. If you want to keep fd open, use gzdopen(dup(fd), mode). + gzdopen returns NULL if there was insufficient memory to allocate + the (de)compression state. +*/ + +ZEXTERN int ZEXPORT gzsetparams OF((gzFile file, int level, int strategy)); +/* + Dynamically update the compression level or strategy. See the description + of deflateInit2 for the meaning of these parameters. + gzsetparams returns Z_OK if success, or Z_STREAM_ERROR if the file was not + opened for writing. +*/ + +ZEXTERN int ZEXPORT gzread OF((gzFile file, voidp buf, unsigned len)); +/* + Reads the given number of uncompressed bytes from the compressed file. + If the input file was not in gzip format, gzread copies the given number + of bytes into the buffer. + gzread returns the number of uncompressed bytes actually read (0 for + end of file, -1 for error). */ + +ZEXTERN int ZEXPORT gzwrite OF((gzFile file, + const voidp buf, unsigned len)); +/* + Writes the given number of uncompressed bytes into the compressed file. + gzwrite returns the number of uncompressed bytes actually written + (0 in case of error). +*/ + +ZEXTERN int ZEXPORTVA gzprintf OF((gzFile file, const char *format, ...)); +/* + Converts, formats, and writes the args to the compressed file under + control of the format string, as in fprintf. gzprintf returns the number of + uncompressed bytes actually written (0 in case of error). +*/ + +ZEXTERN int ZEXPORT gzputs OF((gzFile file, const char *s)); +/* + Writes the given null-terminated string to the compressed file, excluding + the terminating null character. + gzputs returns the number of characters written, or -1 in case of error. +*/ + +ZEXTERN char * ZEXPORT gzgets OF((gzFile file, char *buf, int len)); +/* + Reads bytes from the compressed file until len-1 characters are read, or + a newline character is read and transferred to buf, or an end-of-file + condition is encountered. The string is then terminated with a null + character. + gzgets returns buf, or Z_NULL in case of error. +*/ + +ZEXTERN int ZEXPORT gzputc OF((gzFile file, int c)); +/* + Writes c, converted to an unsigned char, into the compressed file. + gzputc returns the value that was written, or -1 in case of error. +*/ + +ZEXTERN int ZEXPORT gzgetc OF((gzFile file)); +/* + Reads one byte from the compressed file. gzgetc returns this byte + or -1 in case of end of file or error. +*/ + +ZEXTERN int ZEXPORT gzflush OF((gzFile file, int flush)); +/* + Flushes all pending output into the compressed file. The parameter + flush is as in the deflate() function. The return value is the zlib + error number (see function gzerror below). gzflush returns Z_OK if + the flush parameter is Z_FINISH and all output could be flushed. + gzflush should be called only when strictly necessary because it can + degrade compression. +*/ + +ZEXTERN z_off_t ZEXPORT gzseek OF((gzFile file, + z_off_t offset, int whence)); +/* + Sets the starting position for the next gzread or gzwrite on the + given compressed file. The offset represents a number of bytes in the + uncompressed data stream. The whence parameter is defined as in lseek(2); + the value SEEK_END is not supported. + If the file is opened for reading, this function is emulated but can be + extremely slow. If the file is opened for writing, only forward seeks are + supported; gzseek then compresses a sequence of zeroes up to the new + starting position. + + gzseek returns the resulting offset location as measured in bytes from + the beginning of the uncompressed stream, or -1 in case of error, in + particular if the file is opened for writing and the new starting position + would be before the current position. +*/ + +ZEXTERN int ZEXPORT gzrewind OF((gzFile file)); +/* + Rewinds the given file. This function is supported only for reading. + + gzrewind(file) is equivalent to (int)gzseek(file, 0L, SEEK_SET) +*/ + +ZEXTERN z_off_t ZEXPORT gztell OF((gzFile file)); +/* + Returns the starting position for the next gzread or gzwrite on the + given compressed file. This position represents a number of bytes in the + uncompressed data stream. + + gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR) +*/ + +ZEXTERN int ZEXPORT gzeof OF((gzFile file)); +/* + Returns 1 when EOF has previously been detected reading the given + input stream, otherwise zero. +*/ + +ZEXTERN int ZEXPORT gzclose OF((gzFile file)); +/* + Flushes all pending output if necessary, closes the compressed file + and deallocates all the (de)compression state. The return value is the zlib + error number (see function gzerror below). +*/ + +ZEXTERN const char * ZEXPORT gzerror OF((gzFile file, int *errnum)); +/* + Returns the error message for the last error which occurred on the + given compressed file. errnum is set to zlib error number. If an + error occurred in the file system and not in the compression library, + errnum is set to Z_ERRNO and the application may consult errno + to get the exact error code. +*/ + + /* checksum functions */ + +/* + These functions are not related to compression but are exported + anyway because they might be useful in applications using the + compression library. +*/ + +ZEXTERN uLong ZEXPORT adler32 OF((uLong adler, const Bytef *buf, uInt len)); + +/* + Update a running Adler-32 checksum with the bytes buf[0..len-1] and + return the updated checksum. If buf is NULL, this function returns + the required initial value for the checksum. + An Adler-32 checksum is almost as reliable as a CRC32 but can be computed + much faster. Usage example: + + uLong adler = adler32(0L, Z_NULL, 0); + + while (read_buffer(buffer, length) != EOF) { + adler = adler32(adler, buffer, length); + } + if (adler != original_adler) error(); +*/ + +ZEXTERN uLong ZEXPORT crc32 OF((uLong crc, const Bytef *buf, uInt len)); +/* + Update a running crc with the bytes buf[0..len-1] and return the updated + crc. If buf is NULL, this function returns the required initial value + for the crc. Pre- and post-conditioning (one's complement) is performed + within this function so it shouldn't be done by the application. + Usage example: + + uLong crc = crc32(0L, Z_NULL, 0); + + while (read_buffer(buffer, length) != EOF) { + crc = crc32(crc, buffer, length); + } + if (crc != original_crc) error(); +*/ + + + /* various hacks, don't look :) */ + +/* deflateInit and inflateInit are macros to allow checking the zlib version + * and the compiler's view of z_stream: + */ +ZEXTERN int ZEXPORT deflateInit_ OF((z_streamp strm, int level, + const char *version, int stream_size)); +ZEXTERN int ZEXPORT inflateInit_ OF((z_streamp strm, + const char *version, int stream_size)); +ZEXTERN int ZEXPORT deflateInit2_ OF((z_streamp strm, int level, int method, + int windowBits, int memLevel, + int strategy, const char *version, + int stream_size)); +ZEXTERN int ZEXPORT inflateInit2_ OF((z_streamp strm, int windowBits, + const char *version, int stream_size)); +#define deflateInit(strm, level) deflateInit_((strm), (level), ZLIB_VERSION, sizeof(z_stream)) +#define inflateInit(strm) inflateInit_((strm), ZLIB_VERSION, sizeof(z_stream)) +#define deflateInit2(strm, level, method, windowBits, memLevel, strategy) deflateInit2_((strm),(level),(method),(windowBits),(memLevel), (strategy), ZLIB_VERSION, sizeof(z_stream)) +#define inflateInit2(strm, windowBits) inflateInit2_((strm), (windowBits), ZLIB_VERSION, sizeof(z_stream)) + + +#if !defined(_Z_UTIL_H) && !defined(NO_DUMMY_DECL) + struct internal_state {int dummy;}; /* hack for buggy compilers */ +#endif + +ZEXTERN const char * ZEXPORT zError OF((int err)); +ZEXTERN int ZEXPORT inflateSyncPoint OF((z_streamp z)); +ZEXTERN const uLongf * ZEXPORT get_crc_table OF((void)); + +#ifdef __cplusplus +} +#endif + +#endif /* _ZLIB_H */ diff --git a/zlib/zutil.c b/zlib/zutil.c new file mode 100644 index 0000000..20b60fd --- /dev/null +++ b/zlib/zutil.c @@ -0,0 +1,225 @@ +/* zutil.c -- target dependent utility functions for the compression library + * Copyright (C) 1995-2002 Jean-loup Gailly. + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* @(#) $Id$ */ + +#include "zutil.h" + +struct internal_state {int dummy;}; /* for buggy compilers */ + +#ifndef STDC +extern void exit OF((int)); +#endif + +const char *z_errmsg[10] = { +"need dictionary", /* Z_NEED_DICT 2 */ +"stream end", /* Z_STREAM_END 1 */ +"", /* Z_OK 0 */ +"file error", /* Z_ERRNO (-1) */ +"stream error", /* Z_STREAM_ERROR (-2) */ +"data error", /* Z_DATA_ERROR (-3) */ +"insufficient memory", /* Z_MEM_ERROR (-4) */ +"buffer error", /* Z_BUF_ERROR (-5) */ +"incompatible version",/* Z_VERSION_ERROR (-6) */ +""}; + + +const char * ZEXPORT zlibVersion() +{ + return ZLIB_VERSION; +} + +#ifdef DEBUG + +# ifndef verbose +# define verbose 0 +# endif +int z_verbose = verbose; + +void z_error (m) + char *m; +{ + fprintf(stderr, "%s\n", m); + exit(1); +} +#endif + +/* exported to allow conversion of error code to string for compress() and + * uncompress() + */ +const char * ZEXPORT zError(err) + int err; +{ + return ERR_MSG(err); +} + + +#ifndef HAVE_MEMCPY + +void zmemcpy(dest, source, len) + Bytef* dest; + const Bytef* source; + uInt len; +{ + if (len == 0) return; + do { + *dest++ = *source++; /* ??? to be unrolled */ + } while (--len != 0); +} + +int zmemcmp(s1, s2, len) + const Bytef* s1; + const Bytef* s2; + uInt len; +{ + uInt j; + + for (j = 0; j < len; j++) { + if (s1[j] != s2[j]) return 2*(s1[j] > s2[j])-1; + } + return 0; +} + +void zmemzero(dest, len) + Bytef* dest; + uInt len; +{ + if (len == 0) return; + do { + *dest++ = 0; /* ??? to be unrolled */ + } while (--len != 0); +} +#endif + +#ifdef __TURBOC__ +#if (defined( __BORLANDC__) || !defined(SMALL_MEDIUM)) && !defined(__32BIT__) +/* Small and medium model in Turbo C are for now limited to near allocation + * with reduced MAX_WBITS and MAX_MEM_LEVEL + */ +# define MY_ZCALLOC + +/* Turbo C malloc() does not allow dynamic allocation of 64K bytes + * and farmalloc(64K) returns a pointer with an offset of 8, so we + * must fix the pointer. Warning: the pointer must be put back to its + * original form in order to free it, use zcfree(). + */ + +#define MAX_PTR 10 +/* 10*64K = 640K */ + +local int next_ptr = 0; + +typedef struct ptr_table_s { + voidpf org_ptr; + voidpf new_ptr; +} ptr_table; + +local ptr_table table[MAX_PTR]; +/* This table is used to remember the original form of pointers + * to large buffers (64K). Such pointers are normalized with a zero offset. + * Since MSDOS is not a preemptive multitasking OS, this table is not + * protected from concurrent access. This hack doesn't work anyway on + * a protected system like OS/2. Use Microsoft C instead. + */ + +voidpf zcalloc (voidpf opaque, unsigned items, unsigned size) +{ + voidpf buf = opaque; /* just to make some compilers happy */ + ulg bsize = (ulg)items*size; + + /* If we allocate less than 65520 bytes, we assume that farmalloc + * will return a usable pointer which doesn't have to be normalized. + */ + if (bsize < 65520L) { + buf = farmalloc(bsize); + if (*(ush*)&buf != 0) return buf; + } else { + buf = farmalloc(bsize + 16L); + } + if (buf == NULL || next_ptr >= MAX_PTR) return NULL; + table[next_ptr].org_ptr = buf; + + /* Normalize the pointer to seg:0 */ + *((ush*)&buf+1) += ((ush)((uch*)buf-0) + 15) >> 4; + *(ush*)&buf = 0; + table[next_ptr++].new_ptr = buf; + return buf; +} + +void zcfree (voidpf opaque, voidpf ptr) +{ + int n; + if (*(ush*)&ptr != 0) { /* object < 64K */ + farfree(ptr); + return; + } + /* Find the original pointer */ + for (n = 0; n < next_ptr; n++) { + if (ptr != table[n].new_ptr) continue; + + farfree(table[n].org_ptr); + while (++n < next_ptr) { + table[n-1] = table[n]; + } + next_ptr--; + return; + } + ptr = opaque; /* just to make some compilers happy */ + Assert(0, "zcfree: ptr not found"); +} +#endif +#endif /* __TURBOC__ */ + + +#if defined(M_I86) && !defined(__32BIT__) +/* Microsoft C in 16-bit mode */ + +# define MY_ZCALLOC + +#if (!defined(_MSC_VER) || (_MSC_VER <= 600)) +# define _halloc halloc +# define _hfree hfree +#endif + +voidpf zcalloc (voidpf opaque, unsigned items, unsigned size) +{ + if (opaque) opaque = 0; /* to make compiler happy */ + return _halloc((long)items, size); +} + +void zcfree (voidpf opaque, voidpf ptr) +{ + if (opaque) opaque = 0; /* to make compiler happy */ + _hfree(ptr); +} + +#endif /* MSC */ + + +#ifndef MY_ZCALLOC /* Any system without a special alloc function */ + +#ifndef STDC +extern voidp calloc OF((uInt items, uInt size)); +extern void free OF((voidpf ptr)); +#endif + +voidpf zcalloc (opaque, items, size) + voidpf opaque; + unsigned items; + unsigned size; +{ + if (opaque) items += size - size; /* make compiler happy */ + return (voidpf)calloc(items, size); +} + +void zcfree (opaque, ptr) + voidpf opaque; + voidpf ptr; +{ + free(ptr); + if (opaque) return; /* make compiler happy */ +} + +#endif /* MY_ZCALLOC */ diff --git a/zlib/zutil.h b/zlib/zutil.h new file mode 100644 index 0000000..718ebc1 --- /dev/null +++ b/zlib/zutil.h @@ -0,0 +1,220 @@ +/* zutil.h -- internal interface and configuration of the compression library + * Copyright (C) 1995-2002 Jean-loup Gailly. + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +/* @(#) $Id$ */ + +#ifndef _Z_UTIL_H +#define _Z_UTIL_H + +#include "zlib.h" + +#ifdef STDC +# include +# include +# include +#endif +#ifdef NO_ERRNO_H + extern int errno; +#else +# include +#endif + +#ifndef local +# define local static +#endif +/* compile with -Dlocal if your debugger can't find static symbols */ + +typedef unsigned char uch; +typedef uch FAR uchf; +typedef unsigned short ush; +typedef ush FAR ushf; +typedef unsigned long ulg; + +extern const char *z_errmsg[10]; /* indexed by 2-zlib_error */ +/* (size given to avoid silly warnings with Visual C++) */ + +#define ERR_MSG(err) z_errmsg[Z_NEED_DICT-(err)] + +#define ERR_RETURN(strm,err) \ + return (strm->msg = (char*)ERR_MSG(err), (err)) +/* To be used only when the state is known to be valid */ + + /* common constants */ + +#ifndef DEF_WBITS +# define DEF_WBITS MAX_WBITS +#endif +/* default windowBits for decompression. MAX_WBITS is for compression only */ + +#if MAX_MEM_LEVEL >= 8 +# define DEF_MEM_LEVEL 8 +#else +# define DEF_MEM_LEVEL MAX_MEM_LEVEL +#endif +/* default memLevel */ + +#define STORED_BLOCK 0 +#define STATIC_TREES 1 +#define DYN_TREES 2 +/* The three kinds of block type */ + +#define MIN_MATCH 3 +#define MAX_MATCH 258 +/* The minimum and maximum match lengths */ + +#define PRESET_DICT 0x20 /* preset dictionary flag in zlib header */ + + /* target dependencies */ + +#ifdef MSDOS +# define OS_CODE 0x00 +# if defined(__TURBOC__) || defined(__BORLANDC__) +# if(__STDC__ == 1) && (defined(__LARGE__) || defined(__COMPACT__)) + /* Allow compilation with ANSI keywords only enabled */ + void _Cdecl farfree( void *block ); + void *_Cdecl farmalloc( unsigned long nbytes ); +# else +# include +# endif +# else /* MSC or DJGPP */ +# include +# endif +#endif + +#ifdef OS2 +# define OS_CODE 0x06 +#endif + +#ifdef WIN32 /* Window 95 & Windows NT */ +# define OS_CODE 0x0b +#endif + +#if defined(VAXC) || defined(VMS) +# define OS_CODE 0x02 +# define F_OPEN(name, mode) \ + fopen((name), (mode), "mbc=60", "ctx=stm", "rfm=fix", "mrs=512") +#endif + +#ifdef AMIGA +# define OS_CODE 0x01 +#endif + +#if defined(ATARI) || defined(atarist) +# define OS_CODE 0x05 +#endif + +#if defined(MACOS) || defined(TARGET_OS_MAC) +# define OS_CODE 0x07 +# if defined(__MWERKS__) && __dest_os != __be_os && __dest_os != __win32_os +# include /* for fdopen */ +# else +# ifndef fdopen +# define fdopen(fd,mode) NULL /* No fdopen() */ +# endif +# endif +#endif + +#ifdef __50SERIES /* Prime/PRIMOS */ +# define OS_CODE 0x0F +#endif + +#ifdef TOPS20 +# define OS_CODE 0x0a +#endif + +#if defined(_BEOS_) || defined(RISCOS) +# define fdopen(fd,mode) NULL /* No fdopen() */ +#endif + +#if (defined(_MSC_VER) && (_MSC_VER > 600)) +# define fdopen(fd,type) _fdopen(fd,type) +#endif + + + /* Common defaults */ + +#ifndef OS_CODE +# define OS_CODE 0x03 /* assume Unix */ +#endif + +#ifndef F_OPEN +# define F_OPEN(name, mode) fopen((name), (mode)) +#endif + + /* functions */ + +#ifdef HAVE_STRERROR + extern char *strerror OF((int)); +# define zstrerror(errnum) strerror(errnum) +#else +# define zstrerror(errnum) "" +#endif + +#if defined(pyr) +# define NO_MEMCPY +#endif +#if defined(SMALL_MEDIUM) && !defined(_MSC_VER) && !defined(__SC__) + /* Use our own functions for small and medium model with MSC <= 5.0. + * You may have to use the same strategy for Borland C (untested). + * The __SC__ check is for Symantec. + */ +# define NO_MEMCPY +#endif +#if defined(STDC) && !defined(HAVE_MEMCPY) && !defined(NO_MEMCPY) +# define HAVE_MEMCPY +#endif +#ifdef HAVE_MEMCPY +# ifdef SMALL_MEDIUM /* MSDOS small or medium model */ +# define zmemcpy _fmemcpy +# define zmemcmp _fmemcmp +# define zmemzero(dest, len) _fmemset(dest, 0, len) +# else +# define zmemcpy memcpy +# define zmemcmp memcmp +# define zmemzero(dest, len) memset(dest, 0, len) +# endif +#else + extern void zmemcpy OF((Bytef* dest, const Bytef* source, uInt len)); + extern int zmemcmp OF((const Bytef* s1, const Bytef* s2, uInt len)); + extern void zmemzero OF((Bytef* dest, uInt len)); +#endif + +/* Diagnostic functions */ +#ifdef DEBUG +# include + extern int z_verbose; + extern void z_error OF((char *m)); +# define Assert(cond,msg) {if(!(cond)) z_error(msg);} +# define Trace(x) {if (z_verbose>=0) fprintf x ;} +# define Tracev(x) {if (z_verbose>0) fprintf x ;} +# define Tracevv(x) {if (z_verbose>1) fprintf x ;} +# define Tracec(c,x) {if (z_verbose>0 && (c)) fprintf x ;} +# define Tracecv(c,x) {if (z_verbose>1 && (c)) fprintf x ;} +#else +# define Assert(cond,msg) +# define Trace(x) +# define Tracev(x) +# define Tracevv(x) +# define Tracec(c,x) +# define Tracecv(c,x) +#endif + + +typedef uLong (ZEXPORT *check_func) OF((uLong check, const Bytef *buf, + uInt len)); +voidpf zcalloc OF((voidpf opaque, unsigned items, unsigned size)); +void zcfree OF((voidpf opaque, voidpf ptr)); + +#define ZALLOC(strm, items, size) \ + (*((strm)->zalloc))((strm)->opaque, (items), (size)) +#define ZFREE(strm, addr) (*((strm)->zfree))((strm)->opaque, (voidpf)(addr)) +#define TRY_FREE(s, p) {if (p) ZFREE(s, p);} + +#endif /* _Z_UTIL_H */