From 4f33d7bc342638389fc77aa177ab73cbd6d5a288 Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Thu, 1 Jun 2023 08:42:04 +0800 Subject: [PATCH] feat: forward publicMsg by srvId --- CMakeLists.txt | 2 +- src/api_route.h | 1 + src/db.cc | 37 +- src/db.h | 2 + src/http_handler.cc | 8 + src/lz4.c | 2751 +++++++++++++++++++++++++++++++++++ src/lz4.h | 862 +++++++++++ src/send_message_mgr.cc | 82 ++ src/send_message_mgr.h | 1 + src/tinyxml2.cpp | 2994 +++++++++++++++++++++++++++++++++++++++ src/tinyxml2.h | 2380 +++++++++++++++++++++++++++++++ 11 files changed, 9118 insertions(+), 2 deletions(-) create mode 100644 src/lz4.c create mode 100644 src/lz4.h create mode 100644 src/tinyxml2.cpp create mode 100644 src/tinyxml2.h diff --git a/CMakeLists.txt b/CMakeLists.txt index 1823e0f..8052cb1 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -10,7 +10,7 @@ set(CMAKE_POSITION_INDEPENDENT_CODE TRUE) set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /D '_UNICODE' /D 'UNICODE' ") -file(GLOB CPP_FILES ${PROJECT_SOURCE_DIR}/src/*.cc ${PROJECT_SOURCE_DIR}/src/*.cpp) +file(GLOB CPP_FILES ${PROJECT_SOURCE_DIR}/src/*.cc ${PROJECT_SOURCE_DIR}/src/*.cpp ${PROJECT_SOURCE_DIR}/src/*.c) diff --git a/src/api_route.h b/src/api_route.h index a40da7f..f62d96f 100644 --- a/src/api_route.h +++ b/src/api_route.h @@ -76,6 +76,7 @@ typedef enum HTTP_API_ROUTE { WECHAT_GET_MEMBER_PROFILE, WECHAT_REVOKE_MSG, WECHAT_FORWARD_PUBLIC_MSG, + WECHAT_FORWARD_PUBLIC_MSG_BY_SVRID, } WECHAT_HTTP_APIS, *PWECHAT_HTTP_APIS; diff --git a/src/db.cc b/src/db.cc index 0a4d1b6..bfdc003 100644 --- a/src/db.cc +++ b/src/db.cc @@ -421,8 +421,25 @@ std::vector DB::GetDbHandles() { } } + // publicMsgMedia.db + DWORD public_msg_media_ptr = *(DWORD *)(*(DWORD *)(public_msg_mgr_addr) + 0x8); + if (public_msg_media_ptr) { + DWORD public_msg_media_db_addr = *(DWORD *)(public_msg_media_ptr + 0x38); + DatabaseInfo public_msg_media_db{0}; + public_msg_media_db.db_name = (wchar_t *)(*(DWORD *)(public_msg_media_ptr + 0x4C)); + public_msg_media_db.db_name_len = *(DWORD *)(public_msg_media_ptr + 0x50); + public_msg_media_db.handle = public_msg_media_db_addr; + ExecuteSQL(public_msg_media_db_addr, + "select * from sqlite_master where type=\"table\";", + (DWORD)GetDbInfo, &public_msg_media_db); + dbs_.push_back(public_msg_media_db); + wstring public_msg_media_db_name = + wstring((wchar_t *)(*(DWORD *)(public_msg_media_ptr + 0x4C))); + dbmap_[public_msg_media_db_name] = public_msg_media_db; + } + // publicMsg.db - DWORD public_msg_ptr = *(DWORD *)(*(DWORD *)(public_msg_mgr_addr) + 0x8); + DWORD public_msg_ptr = *(DWORD *)(*(DWORD *)(public_msg_mgr_addr) + 0xc); if (public_msg_ptr) { DWORD public_msg_db_addr = *(DWORD *)(public_msg_ptr + 0x38); DatabaseInfo public_msg_db{0}; @@ -544,4 +561,22 @@ std::string DB::GetVoiceBuffByMsgId(ULONG64 msgid) { } return ""; } + +std::string DB::GetPublicMsgCompressContentByMsgId(ULONG64 msgid) { + char sql[260] = {0}; + sprintf_s(sql, "SELECT CompressContent from PublicMsg WHERE MsgSvrID=%llu;", msgid); + wchar_t dbname[20] = {0}; + swprintf_s( dbname, 20, L"%s", L"PublicMsg.db"); + DWORD handle = GetDbHandleByDbName(dbname); + if (handle == 0) { + return ""; + } + vector> result; + int ret = Select(handle, (const char *)sql, result); + if (result.size() == 0) { + return ""; + } + return result[1][0]; +} + } // namespace wxhelper \ No newline at end of file diff --git a/src/db.h b/src/db.h index f8927fe..1f607c0 100644 --- a/src/db.h +++ b/src/db.h @@ -23,6 +23,8 @@ class DB :public Singleton{ std::string GetVoiceBuffByMsgId(ULONG64 msgid); + std::string GetPublicMsgCompressContentByMsgId(ULONG64 msgid); + private: int SelectDataInner(DWORD db, const char *sql, std::vector> &data); diff --git a/src/http_handler.cc b/src/http_handler.cc index 7cb7d45..482c831 100644 --- a/src/http_handler.cc +++ b/src/http_handler.cc @@ -634,6 +634,14 @@ string Dispatch(struct mg_connection *c, struct mg_http_message *hm) { ret = ret_data.dump(); break; } + case WECHAT_FORWARD_PUBLIC_MSG_BY_SVRID:{ + wstring wxid = GetWStringParam(j_param, "wxid"); + ULONG64 msg_id = GetULong64Param(j_param, "msgId"); + int success= g_context.send_mgr->ForwardPublicMsgByMsgSvrId(WS2LPWS(wxid),msg_id); + json ret_data = {{"code", success}, {"result", "OK"}}; + ret = ret_data.dump(); + break; + } default: json ret_data = {{"result", "ERROR"}, {"msg", "not support api"}}; ret = ret_data.dump(); diff --git a/src/lz4.c b/src/lz4.c new file mode 100644 index 0000000..c7237ba --- /dev/null +++ b/src/lz4.c @@ -0,0 +1,2751 @@ +/* + LZ4 - Fast LZ compression algorithm + Copyright (C) 2011-2020, Yann Collet. + + BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions are + met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following disclaimer + in the documentation and/or other materials provided with the + distribution. + + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "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 COPYRIGHT + OWNER OR CONTRIBUTORS 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. + + You can contact the author at : + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 +*/ + +/*-************************************ +* Tuning parameters +**************************************/ +/* + * LZ4_HEAPMODE : + * Select how stateless compression functions like `LZ4_compress_default()` + * allocate memory for their hash table, + * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()). + */ +#ifndef LZ4_HEAPMODE +# define LZ4_HEAPMODE 0 +#endif + +/* + * LZ4_ACCELERATION_DEFAULT : + * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 + */ +#define LZ4_ACCELERATION_DEFAULT 1 +/* + * LZ4_ACCELERATION_MAX : + * Any "acceleration" value higher than this threshold + * get treated as LZ4_ACCELERATION_MAX instead (fix #876) + */ +#define LZ4_ACCELERATION_MAX 65537 + + +/*-************************************ +* CPU Feature Detection +**************************************/ +/* LZ4_FORCE_MEMORY_ACCESS + * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable. + * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal. + * The below switch allow to select different access method for improved performance. + * Method 0 (default) : use `memcpy()`. Safe and portable. + * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable). + * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. + * Method 2 : direct access. This method is portable but violate C standard. + * It can generate buggy code on targets which assembly generation depends on alignment. + * But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6) + * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. + * Prefer these methods in priority order (0 > 1 > 2) + */ +#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */ +# if defined(__GNUC__) && \ + ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \ + || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) +# define LZ4_FORCE_MEMORY_ACCESS 2 +# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__) +# define LZ4_FORCE_MEMORY_ACCESS 1 +# endif +#endif + +/* + * LZ4_FORCE_SW_BITCOUNT + * Define this parameter if your target system or compiler does not support hardware bit count + */ +#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */ +# undef LZ4_FORCE_SW_BITCOUNT /* avoid double def */ +# define LZ4_FORCE_SW_BITCOUNT +#endif + + + +/*-************************************ +* Dependency +**************************************/ +/* + * LZ4_SRC_INCLUDED: + * Amalgamation flag, whether lz4.c is included + */ +#ifndef LZ4_SRC_INCLUDED +# define LZ4_SRC_INCLUDED 1 +#endif + +#ifndef LZ4_STATIC_LINKING_ONLY +#define LZ4_STATIC_LINKING_ONLY +#endif + +#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS +#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */ +#endif + +#define LZ4_STATIC_LINKING_ONLY /* LZ4_DISTANCE_MAX */ +#include "lz4.h" +/* see also "memory routines" below */ + + +/*-************************************ +* Compiler Options +**************************************/ +#if defined(_MSC_VER) && (_MSC_VER >= 1400) /* Visual Studio 2005+ */ +# include /* only present in VS2005+ */ +# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ +# pragma warning(disable : 6237) /* disable: C6237: conditional expression is always 0 */ +#endif /* _MSC_VER */ + +#ifndef LZ4_FORCE_INLINE +# ifdef _MSC_VER /* Visual Studio */ +# define LZ4_FORCE_INLINE static __forceinline +# else +# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# ifdef __GNUC__ +# define LZ4_FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define LZ4_FORCE_INLINE static inline +# endif +# else +# define LZ4_FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +# endif /* _MSC_VER */ +#endif /* LZ4_FORCE_INLINE */ + +/* LZ4_FORCE_O2 and LZ4_FORCE_INLINE + * gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8, + * together with a simple 8-byte copy loop as a fall-back path. + * However, this optimization hurts the decompression speed by >30%, + * because the execution does not go to the optimized loop + * for typical compressible data, and all of the preamble checks + * before going to the fall-back path become useless overhead. + * This optimization happens only with the -O3 flag, and -O2 generates + * a simple 8-byte copy loop. + * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy8 + * functions are annotated with __attribute__((optimize("O2"))), + * and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute + * of LZ4_wildCopy8 does not affect the compression speed. + */ +#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__) +# define LZ4_FORCE_O2 __attribute__((optimize("O2"))) +# undef LZ4_FORCE_INLINE +# define LZ4_FORCE_INLINE static __inline __attribute__((optimize("O2"),always_inline)) +#else +# define LZ4_FORCE_O2 +#endif + +#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) +# define expect(expr,value) (__builtin_expect ((expr),(value)) ) +#else +# define expect(expr,value) (expr) +#endif + +#ifndef likely +#define likely(expr) expect((expr) != 0, 1) +#endif +#ifndef unlikely +#define unlikely(expr) expect((expr) != 0, 0) +#endif + +/* Should the alignment test prove unreliable, for some reason, + * it can be disabled by setting LZ4_ALIGN_TEST to 0 */ +#ifndef LZ4_ALIGN_TEST /* can be externally provided */ +# define LZ4_ALIGN_TEST 1 +#endif + + +/*-************************************ +* Memory routines +**************************************/ + +/*! LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION : + * Disable relatively high-level LZ4/HC functions that use dynamic memory + * allocation functions (malloc(), calloc(), free()). + * + * Note that this is a compile-time switch. And since it disables + * public/stable LZ4 v1 API functions, we don't recommend using this + * symbol to generate a library for distribution. + * + * The following public functions are removed when this symbol is defined. + * - lz4 : LZ4_createStream, LZ4_freeStream, + * LZ4_createStreamDecode, LZ4_freeStreamDecode, LZ4_create (deprecated) + * - lz4hc : LZ4_createStreamHC, LZ4_freeStreamHC, + * LZ4_createHC (deprecated), LZ4_freeHC (deprecated) + * - lz4frame, lz4file : All LZ4F_* functions + */ +#if defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +# define ALLOC(s) lz4_error_memory_allocation_is_disabled +# define ALLOC_AND_ZERO(s) lz4_error_memory_allocation_is_disabled +# define FREEMEM(p) lz4_error_memory_allocation_is_disabled +#elif defined(LZ4_USER_MEMORY_FUNCTIONS) +/* memory management functions can be customized by user project. + * Below functions must exist somewhere in the Project + * and be available at link time */ +void* LZ4_malloc(size_t s); +void* LZ4_calloc(size_t n, size_t s); +void LZ4_free(void* p); +# define ALLOC(s) LZ4_malloc(s) +# define ALLOC_AND_ZERO(s) LZ4_calloc(1,s) +# define FREEMEM(p) LZ4_free(p) +#else +# include /* malloc, calloc, free */ +# define ALLOC(s) malloc(s) +# define ALLOC_AND_ZERO(s) calloc(1,s) +# define FREEMEM(p) free(p) +#endif + +#if ! LZ4_FREESTANDING +# include /* memset, memcpy */ +#endif +#if !defined(LZ4_memset) +# define LZ4_memset(p,v,s) memset((p),(v),(s)) +#endif +#define MEM_INIT(p,v,s) LZ4_memset((p),(v),(s)) + + +/*-************************************ +* Common Constants +**************************************/ +#define MINMATCH 4 + +#define WILDCOPYLENGTH 8 +#define LASTLITERALS 5 /* see ../doc/lz4_Block_format.md#parsing-restrictions */ +#define MFLIMIT 12 /* see ../doc/lz4_Block_format.md#parsing-restrictions */ +#define MATCH_SAFEGUARD_DISTANCE ((2*WILDCOPYLENGTH) - MINMATCH) /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */ +#define FASTLOOP_SAFE_DISTANCE 64 +static const int LZ4_minLength = (MFLIMIT+1); + +#define KB *(1 <<10) +#define MB *(1 <<20) +#define GB *(1U<<30) + +#define LZ4_DISTANCE_ABSOLUTE_MAX 65535 +#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX) /* max supported by LZ4 format */ +# error "LZ4_DISTANCE_MAX is too big : must be <= 65535" +#endif + +#define ML_BITS 4 +#define ML_MASK ((1U<=1) +# include +#else +# ifndef assert +# define assert(condition) ((void)0) +# endif +#endif + +#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use after variable declarations */ + +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2) +# include + static int g_debuglog_enable = 1; +# define DEBUGLOG(l, ...) { \ + if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \ + fprintf(stderr, __FILE__ " %i: ", __LINE__); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, " \n"); \ + } } +#else +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif + +static int LZ4_isAligned(const void* ptr, size_t alignment) +{ + return ((size_t)ptr & (alignment -1)) == 0; +} + + +/*-************************************ +* Types +**************************************/ +#include +#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +# include + typedef uint8_t BYTE; + typedef uint16_t U16; + typedef uint32_t U32; + typedef int32_t S32; + typedef uint64_t U64; + typedef uintptr_t uptrval; +#else +# if UINT_MAX != 4294967295UL +# error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4" +# endif + typedef unsigned char BYTE; + typedef unsigned short U16; + typedef unsigned int U32; + typedef signed int S32; + typedef unsigned long long U64; + typedef size_t uptrval; /* generally true, except OpenVMS-64 */ +#endif + +#if defined(__x86_64__) + typedef U64 reg_t; /* 64-bits in x32 mode */ +#else + typedef size_t reg_t; /* 32-bits in x32 mode */ +#endif + +typedef enum { + notLimited = 0, + limitedOutput = 1, + fillOutput = 2 +} limitedOutput_directive; + + +/*-************************************ +* Reading and writing into memory +**************************************/ + +/** + * LZ4 relies on memcpy with a constant size being inlined. In freestanding + * environments, the compiler can't assume the implementation of memcpy() is + * standard compliant, so it can't apply its specialized memcpy() inlining + * logic. When possible, use __builtin_memcpy() to tell the compiler to analyze + * memcpy() as if it were standard compliant, so it can inline it in freestanding + * environments. This is needed when decompressing the Linux Kernel, for example. + */ +#if !defined(LZ4_memcpy) +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size) +# else +# define LZ4_memcpy(dst, src, size) memcpy(dst, src, size) +# endif +#endif + +#if !defined(LZ4_memmove) +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4_memmove __builtin_memmove +# else +# define LZ4_memmove memmove +# endif +#endif + +static unsigned LZ4_isLittleEndian(void) +{ + const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ + return one.c[0]; +} + + +#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2) +/* lie to the compiler about data alignment; use with caution */ + +static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; } +static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; } +static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; } + +static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } +static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } + +#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1) + +/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ +/* currently only defined for gcc and icc */ +typedef struct { U16 u16; } __attribute__((packed)) LZ4_unalign16; +typedef struct { U32 u32; } __attribute__((packed)) LZ4_unalign32; +typedef struct { reg_t uArch; } __attribute__((packed)) LZ4_unalignST; + +static U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign16*)ptr)->u16; } +static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign32*)ptr)->u32; } +static reg_t LZ4_read_ARCH(const void* ptr) { return ((const LZ4_unalignST*)ptr)->uArch; } + +static void LZ4_write16(void* memPtr, U16 value) { ((LZ4_unalign16*)memPtr)->u16 = value; } +static void LZ4_write32(void* memPtr, U32 value) { ((LZ4_unalign32*)memPtr)->u32 = value; } + +#else /* safe and portable access using memcpy() */ + +static U16 LZ4_read16(const void* memPtr) +{ + U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; +} + +static U32 LZ4_read32(const void* memPtr) +{ + U32 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; +} + +static reg_t LZ4_read_ARCH(const void* memPtr) +{ + reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; +} + +static void LZ4_write16(void* memPtr, U16 value) +{ + LZ4_memcpy(memPtr, &value, sizeof(value)); +} + +static void LZ4_write32(void* memPtr, U32 value) +{ + LZ4_memcpy(memPtr, &value, sizeof(value)); +} + +#endif /* LZ4_FORCE_MEMORY_ACCESS */ + + +static U16 LZ4_readLE16(const void* memPtr) +{ + if (LZ4_isLittleEndian()) { + return LZ4_read16(memPtr); + } else { + const BYTE* p = (const BYTE*)memPtr; + return (U16)((U16)p[0] + (p[1]<<8)); + } +} + +static void LZ4_writeLE16(void* memPtr, U16 value) +{ + if (LZ4_isLittleEndian()) { + LZ4_write16(memPtr, value); + } else { + BYTE* p = (BYTE*)memPtr; + p[0] = (BYTE) value; + p[1] = (BYTE)(value>>8); + } +} + +/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ +LZ4_FORCE_INLINE +void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; + + do { LZ4_memcpy(d,s,8); d+=8; s+=8; } while (d= 16. */ +LZ4_FORCE_INLINE void +LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; + + do { LZ4_memcpy(d,s,16); LZ4_memcpy(d+16,s+16,16); d+=32; s+=32; } while (d= dstPtr + MINMATCH + * - there is at least 8 bytes available to write after dstEnd */ +LZ4_FORCE_INLINE void +LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset) +{ + BYTE v[8]; + + assert(dstEnd >= dstPtr + MINMATCH); + + switch(offset) { + case 1: + MEM_INIT(v, *srcPtr, 8); + break; + case 2: + LZ4_memcpy(v, srcPtr, 2); + LZ4_memcpy(&v[2], srcPtr, 2); +#if defined(_MSC_VER) && (_MSC_VER <= 1936) /* MSVC 2022 ver 17.6 or earlier */ +# pragma warning(push) +# pragma warning(disable : 6385) /* warning C6385: Reading invalid data from 'v'. */ +#endif + LZ4_memcpy(&v[4], v, 4); +#if defined(_MSC_VER) && (_MSC_VER <= 1936) /* MSVC 2022 ver 17.6 or earlier */ +# pragma warning(pop) +#endif + break; + case 4: + LZ4_memcpy(v, srcPtr, 4); + LZ4_memcpy(&v[4], srcPtr, 4); + break; + default: + LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset); + return; + } + + LZ4_memcpy(dstPtr, v, 8); + dstPtr += 8; + while (dstPtr < dstEnd) { + LZ4_memcpy(dstPtr, v, 8); + dstPtr += 8; + } +} +#endif + + +/*-************************************ +* Common functions +**************************************/ +static unsigned LZ4_NbCommonBytes (reg_t val) +{ + assert(val != 0); + if (LZ4_isLittleEndian()) { + if (sizeof(val) == 8) { +# if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT) +/*-************************************************************************************************* +* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11. +* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics +* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC. +****************************************************************************************************/ +# if defined(__clang__) && (__clang_major__ < 10) + /* Avoid undefined clang-cl intrinsics issue. + * See https://github.com/lz4/lz4/pull/1017 for details. */ + return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3; +# else + /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */ + return (unsigned)_tzcnt_u64(val) >> 3; +# endif +# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanForward64(&r, (U64)val); + return (unsigned)r >> 3; +# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_ctzll((U64)val) >> 3; +# else + const U64 m = 0x0101010101010101ULL; + val ^= val - 1; + return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56); +# endif + } else /* 32 bits */ { +# if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r; + _BitScanForward(&r, (U32)val); + return (unsigned)r >> 3; +# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_ctz((U32)val) >> 3; +# else + const U32 m = 0x01010101; + return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24; +# endif + } + } else /* Big Endian CPU */ { + if (sizeof(val)==8) { +# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_clzll((U64)val) >> 3; +# else +#if 1 + /* this method is probably faster, + * but adds a 128 bytes lookup table */ + static const unsigned char ctz7_tab[128] = { + 7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + }; + U64 const mask = 0x0101010101010101ULL; + U64 const t = (((val >> 8) - mask) | val) & mask; + return ctz7_tab[(t * 0x0080402010080402ULL) >> 57]; +#else + /* this method doesn't consume memory space like the previous one, + * but it contains several branches, + * that may end up slowing execution */ + static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. + Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. + Note that this code path is never triggered in 32-bits mode. */ + unsigned r; + if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } + if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } + r += (!val); + return r; +#endif +# endif + } else /* 32 bits */ { +# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_clz((U32)val) >> 3; +# else + val >>= 8; + val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) | + (val + 0x00FF0000)) >> 24; + return (unsigned)val ^ 3; +# endif + } + } +} + + +#define STEPSIZE sizeof(reg_t) +LZ4_FORCE_INLINE +unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) +{ + const BYTE* const pStart = pIn; + + if (likely(pIn < pInLimit-(STEPSIZE-1))) { + reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); + if (!diff) { + pIn+=STEPSIZE; pMatch+=STEPSIZE; + } else { + return LZ4_NbCommonBytes(diff); + } } + + while (likely(pIn < pInLimit-(STEPSIZE-1))) { + reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); + if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; } + pIn += LZ4_NbCommonBytes(diff); + return (unsigned)(pIn - pStart); + } + + if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; } + if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; } + if ((pIn compression run slower on incompressible data */ + + +/*-************************************ +* Local Structures and types +**************************************/ +typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t; + +/** + * This enum distinguishes several different modes of accessing previous + * content in the stream. + * + * - noDict : There is no preceding content. + * - withPrefix64k : Table entries up to ctx->dictSize before the current blob + * blob being compressed are valid and refer to the preceding + * content (of length ctx->dictSize), which is available + * contiguously preceding in memory the content currently + * being compressed. + * - usingExtDict : Like withPrefix64k, but the preceding content is somewhere + * else in memory, starting at ctx->dictionary with length + * ctx->dictSize. + * - usingDictCtx : Everything concerning the preceding content is + * in a separate context, pointed to by ctx->dictCtx. + * ctx->dictionary, ctx->dictSize, and table entries + * in the current context that refer to positions + * preceding the beginning of the current compression are + * ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx + * ->dictSize describe the location and size of the preceding + * content, and matches are found by looking in the ctx + * ->dictCtx->hashTable. + */ +typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive; +typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; + + +/*-************************************ +* Local Utils +**************************************/ +int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } +const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; } +int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } +int LZ4_sizeofState(void) { return sizeof(LZ4_stream_t); } + + +/*-**************************************** +* Internal Definitions, used only in Tests +*******************************************/ +#if defined (__cplusplus) +extern "C" { +#endif + +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize); + +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, + int compressedSize, int maxOutputSize, + const void* dictStart, size_t dictSize); +int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest, + int compressedSize, int targetOutputSize, int dstCapacity, + const void* dictStart, size_t dictSize); +#if defined (__cplusplus) +} +#endif + +/*-****************************** +* Compression functions +********************************/ +LZ4_FORCE_INLINE U32 LZ4_hash4(U32 sequence, tableType_t const tableType) +{ + if (tableType == byU16) + return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); + else + return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); +} + +LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType) +{ + const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; + if (LZ4_isLittleEndian()) { + const U64 prime5bytes = 889523592379ULL; + return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog)); + } else { + const U64 prime8bytes = 11400714785074694791ULL; + return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog)); + } +} + +LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) +{ + if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType); + return LZ4_hash4(LZ4_read32(p), tableType); +} + +LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType) +{ + switch (tableType) + { + default: /* fallthrough */ + case clearedTable: { /* illegal! */ assert(0); return; } + case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; } + } +} + +LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) +{ + switch (tableType) + { + default: /* fallthrough */ + case clearedTable: /* fallthrough */ + case byPtr: { /* illegal! */ assert(0); return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; } + case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; } + } +} + +/* LZ4_putPosition*() : only used in byPtr mode */ +LZ4_FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, + void* tableBase, tableType_t const tableType) +{ + const BYTE** const hashTable = (const BYTE**)tableBase; + assert(tableType == byPtr); (void)tableType; + hashTable[h] = p; +} + +LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType) +{ + U32 const h = LZ4_hashPosition(p, tableType); + LZ4_putPositionOnHash(p, h, tableBase, tableType); +} + +/* LZ4_getIndexOnHash() : + * Index of match position registered in hash table. + * hash position must be calculated by using base+index, or dictBase+index. + * Assumption 1 : only valid if tableType == byU32 or byU16. + * Assumption 2 : h is presumed valid (within limits of hash table) + */ +LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType) +{ + LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2); + if (tableType == byU32) { + const U32* const hashTable = (const U32*) tableBase; + assert(h < (1U << (LZ4_MEMORY_USAGE-2))); + return hashTable[h]; + } + if (tableType == byU16) { + const U16* const hashTable = (const U16*) tableBase; + assert(h < (1U << (LZ4_MEMORY_USAGE-1))); + return hashTable[h]; + } + assert(0); return 0; /* forbidden case */ +} + +static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType) +{ + assert(tableType == byPtr); (void)tableType; + { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; } +} + +LZ4_FORCE_INLINE const BYTE* +LZ4_getPosition(const BYTE* p, + const void* tableBase, tableType_t tableType) +{ + U32 const h = LZ4_hashPosition(p, tableType); + return LZ4_getPositionOnHash(h, tableBase, tableType); +} + +LZ4_FORCE_INLINE void +LZ4_prepareTable(LZ4_stream_t_internal* const cctx, + const int inputSize, + const tableType_t tableType) { + /* If the table hasn't been used, it's guaranteed to be zeroed out, and is + * therefore safe to use no matter what mode we're in. Otherwise, we figure + * out if it's safe to leave as is or whether it needs to be reset. + */ + if ((tableType_t)cctx->tableType != clearedTable) { + assert(inputSize >= 0); + if ((tableType_t)cctx->tableType != tableType + || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU) + || ((tableType == byU32) && cctx->currentOffset > 1 GB) + || tableType == byPtr + || inputSize >= 4 KB) + { + DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx); + MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE); + cctx->currentOffset = 0; + cctx->tableType = (U32)clearedTable; + } else { + DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)"); + } + } + + /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back, + * is faster than compressing without a gap. + * However, compressing with currentOffset == 0 is faster still, + * so we preserve that case. + */ + if (cctx->currentOffset != 0 && tableType == byU32) { + DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset"); + cctx->currentOffset += 64 KB; + } + + /* Finally, clear history */ + cctx->dictCtx = NULL; + cctx->dictionary = NULL; + cctx->dictSize = 0; +} + +/** LZ4_compress_generic() : + * inlined, to ensure branches are decided at compilation time. + * The following conditions are presumed already validated: + * - source != NULL + * - inputSize > 0 + */ +LZ4_FORCE_INLINE int LZ4_compress_generic_validated( + LZ4_stream_t_internal* const cctx, + const char* const source, + char* const dest, + const int inputSize, + int* inputConsumed, /* only written when outputDirective == fillOutput */ + const int maxOutputSize, + const limitedOutput_directive outputDirective, + const tableType_t tableType, + const dict_directive dictDirective, + const dictIssue_directive dictIssue, + const int acceleration) +{ + int result; + const BYTE* ip = (const BYTE*)source; + + U32 const startIndex = cctx->currentOffset; + const BYTE* base = (const BYTE*)source - startIndex; + const BYTE* lowLimit; + + const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx; + const BYTE* const dictionary = + dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary; + const U32 dictSize = + dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize; + const U32 dictDelta = + (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0; /* make indexes in dictCtx comparable with indexes in current context */ + + int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx); + U32 const prefixIdxLimit = startIndex - dictSize; /* used when dictDirective == dictSmall */ + const BYTE* const dictEnd = dictionary ? dictionary + dictSize : dictionary; + const BYTE* anchor = (const BYTE*) source; + const BYTE* const iend = ip + inputSize; + const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1; + const BYTE* const matchlimit = iend - LASTLITERALS; + + /* the dictCtx currentOffset is indexed on the start of the dictionary, + * while a dictionary in the current context precedes the currentOffset */ + const BYTE* dictBase = (dictionary == NULL) ? NULL : + (dictDirective == usingDictCtx) ? + dictionary + dictSize - dictCtx->currentOffset : + dictionary + dictSize - startIndex; + + BYTE* op = (BYTE*) dest; + BYTE* const olimit = op + maxOutputSize; + + U32 offset = 0; + U32 forwardH; + + DEBUGLOG(5, "LZ4_compress_generic_validated: srcSize=%i, tableType=%u", inputSize, tableType); + assert(ip != NULL); + if (tableType == byU16) assert(inputSize= 1); + + lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0); + + /* Update context state */ + if (dictDirective == usingDictCtx) { + /* Subsequent linked blocks can't use the dictionary. */ + /* Instead, they use the block we just compressed. */ + cctx->dictCtx = NULL; + cctx->dictSize = (U32)inputSize; + } else { + cctx->dictSize += (U32)inputSize; + } + cctx->currentOffset += (U32)inputSize; + cctx->tableType = (U32)tableType; + + if (inputSizehashTable, byPtr); + } else { + LZ4_putIndexOnHash(startIndex, h, cctx->hashTable, tableType); + } } + ip++; forwardH = LZ4_hashPosition(ip, tableType); + + /* Main Loop */ + for ( ; ; ) { + const BYTE* match; + BYTE* token; + const BYTE* filledIp; + + /* Find a match */ + if (tableType == byPtr) { + const BYTE* forwardIp = ip; + int step = 1; + int searchMatchNb = acceleration << LZ4_skipTrigger; + do { + U32 const h = forwardH; + ip = forwardIp; + forwardIp += step; + step = (searchMatchNb++ >> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; + assert(ip < mflimitPlusOne); + + match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType); + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType); + + } while ( (match+LZ4_DISTANCE_MAX < ip) + || (LZ4_read32(match) != LZ4_read32(ip)) ); + + } else { /* byU32, byU16 */ + + const BYTE* forwardIp = ip; + int step = 1; + int searchMatchNb = acceleration << LZ4_skipTrigger; + do { + U32 const h = forwardH; + U32 const current = (U32)(forwardIp - base); + U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); + assert(matchIndex <= current); + assert(forwardIp - base < (ptrdiff_t)(2 GB - 1)); + ip = forwardIp; + forwardIp += step; + step = (searchMatchNb++ >> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; + assert(ip < mflimitPlusOne); + + if (dictDirective == usingDictCtx) { + if (matchIndex < startIndex) { + /* there was no match, try the dictionary */ + assert(tableType == byU32); + matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); + match = dictBase + matchIndex; + matchIndex += dictDelta; /* make dictCtx index comparable with current context */ + lowLimit = dictionary; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; + } + } else if (dictDirective == usingExtDict) { + if (matchIndex < startIndex) { + DEBUGLOG(7, "extDict candidate: matchIndex=%5u < startIndex=%5u", matchIndex, startIndex); + assert(startIndex - matchIndex >= MINMATCH); + assert(dictBase); + match = dictBase + matchIndex; + lowLimit = dictionary; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; + } + } else { /* single continuous memory segment */ + match = base + matchIndex; + } + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); + + DEBUGLOG(7, "candidate at pos=%u (offset=%u \n", matchIndex, current - matchIndex); + if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; } /* match outside of valid area */ + assert(matchIndex < current); + if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX)) + && (matchIndex+LZ4_DISTANCE_MAX < current)) { + continue; + } /* too far */ + assert((current - matchIndex) <= LZ4_DISTANCE_MAX); /* match now expected within distance */ + + if (LZ4_read32(match) == LZ4_read32(ip)) { + if (maybe_extMem) offset = current - matchIndex; + break; /* match found */ + } + + } while(1); + } + + /* Catch up */ + filledIp = ip; + while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } + + /* Encode Literals */ + { unsigned const litLength = (unsigned)(ip - anchor); + token = op++; + if ((outputDirective == limitedOutput) && /* Check output buffer overflow */ + (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) { + return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ + } + if ((outputDirective == fillOutput) && + (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) { + op--; + goto _last_literals; + } + if (litLength >= RUN_MASK) { + int len = (int)(litLength - RUN_MASK); + *token = (RUN_MASK<= 255 ; len-=255) *op++ = 255; + *op++ = (BYTE)len; + } + else *token = (BYTE)(litLength< olimit)) { + /* the match was too close to the end, rewind and go to last literals */ + op = token; + goto _last_literals; + } + + /* Encode Offset */ + if (maybe_extMem) { /* static test */ + DEBUGLOG(6, " with offset=%u (ext if > %i)", offset, (int)(ip - (const BYTE*)source)); + assert(offset <= LZ4_DISTANCE_MAX && offset > 0); + LZ4_writeLE16(op, (U16)offset); op+=2; + } else { + DEBUGLOG(6, " with offset=%u (same segment)", (U32)(ip - match)); + assert(ip-match <= LZ4_DISTANCE_MAX); + LZ4_writeLE16(op, (U16)(ip - match)); op+=2; + } + + /* Encode MatchLength */ + { unsigned matchCode; + + if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx) + && (lowLimit==dictionary) /* match within extDict */ ) { + const BYTE* limit = ip + (dictEnd-match); + assert(dictEnd > match); + if (limit > matchlimit) limit = matchlimit; + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); + ip += (size_t)matchCode + MINMATCH; + if (ip==limit) { + unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit); + matchCode += more; + ip += more; + } + DEBUGLOG(6, " with matchLength=%u starting in extDict", matchCode+MINMATCH); + } else { + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); + ip += (size_t)matchCode + MINMATCH; + DEBUGLOG(6, " with matchLength=%u", matchCode+MINMATCH); + } + + if ((outputDirective) && /* Check output buffer overflow */ + (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) { + if (outputDirective == fillOutput) { + /* Match description too long : reduce it */ + U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255; + ip -= matchCode - newMatchCode; + assert(newMatchCode < matchCode); + matchCode = newMatchCode; + if (unlikely(ip <= filledIp)) { + /* We have already filled up to filledIp so if ip ends up less than filledIp + * we have positions in the hash table beyond the current position. This is + * a problem if we reuse the hash table. So we have to remove these positions + * from the hash table. + */ + const BYTE* ptr; + DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip)); + for (ptr = ip; ptr <= filledIp; ++ptr) { + U32 const h = LZ4_hashPosition(ptr, tableType); + LZ4_clearHash(h, cctx->hashTable, tableType); + } + } + } else { + assert(outputDirective == limitedOutput); + return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ + } + } + if (matchCode >= ML_MASK) { + *token += ML_MASK; + matchCode -= ML_MASK; + LZ4_write32(op, 0xFFFFFFFF); + while (matchCode >= 4*255) { + op+=4; + LZ4_write32(op, 0xFFFFFFFF); + matchCode -= 4*255; + } + op += matchCode / 255; + *op++ = (BYTE)(matchCode % 255); + } else + *token += (BYTE)(matchCode); + } + /* Ensure we have enough space for the last literals. */ + assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit)); + + anchor = ip; + + /* Test end of chunk */ + if (ip >= mflimitPlusOne) break; + + /* Fill table */ + { U32 const h = LZ4_hashPosition(ip-2, tableType); + if (tableType == byPtr) { + LZ4_putPositionOnHash(ip-2, h, cctx->hashTable, byPtr); + } else { + U32 const idx = (U32)((ip-2) - base); + LZ4_putIndexOnHash(idx, h, cctx->hashTable, tableType); + } } + + /* Test next position */ + if (tableType == byPtr) { + + match = LZ4_getPosition(ip, cctx->hashTable, tableType); + LZ4_putPosition(ip, cctx->hashTable, tableType); + if ( (match+LZ4_DISTANCE_MAX >= ip) + && (LZ4_read32(match) == LZ4_read32(ip)) ) + { token=op++; *token=0; goto _next_match; } + + } else { /* byU32, byU16 */ + + U32 const h = LZ4_hashPosition(ip, tableType); + U32 const current = (U32)(ip-base); + U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); + assert(matchIndex < current); + if (dictDirective == usingDictCtx) { + if (matchIndex < startIndex) { + /* there was no match, try the dictionary */ + assert(tableType == byU32); + matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); + match = dictBase + matchIndex; + lowLimit = dictionary; /* required for match length counter */ + matchIndex += dictDelta; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; /* required for match length counter */ + } + } else if (dictDirective==usingExtDict) { + if (matchIndex < startIndex) { + assert(dictBase); + match = dictBase + matchIndex; + lowLimit = dictionary; /* required for match length counter */ + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; /* required for match length counter */ + } + } else { /* single memory segment */ + match = base + matchIndex; + } + LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); + assert(matchIndex < current); + if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1) + && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current)) + && (LZ4_read32(match) == LZ4_read32(ip)) ) { + token=op++; + *token=0; + if (maybe_extMem) offset = current - matchIndex; + DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", + (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source)); + goto _next_match; + } + } + + /* Prepare next loop */ + forwardH = LZ4_hashPosition(++ip, tableType); + + } + +_last_literals: + /* Encode Last Literals */ + { size_t lastRun = (size_t)(iend - anchor); + if ( (outputDirective) && /* Check output buffer overflow */ + (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) { + if (outputDirective == fillOutput) { + /* adapt lastRun to fill 'dst' */ + assert(olimit >= op); + lastRun = (size_t)(olimit-op) - 1/*token*/; + lastRun -= (lastRun + 256 - RUN_MASK) / 256; /*additional length tokens*/ + } else { + assert(outputDirective == limitedOutput); + return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ + } + } + DEBUGLOG(6, "Final literal run : %i literals", (int)lastRun); + if (lastRun >= RUN_MASK) { + size_t accumulator = lastRun - RUN_MASK; + *op++ = RUN_MASK << ML_BITS; + for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; + *op++ = (BYTE) accumulator; + } else { + *op++ = (BYTE)(lastRun< 0); + DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, result); + return result; +} + +/** LZ4_compress_generic() : + * inlined, to ensure branches are decided at compilation time; + * takes care of src == (NULL, 0) + * and forward the rest to LZ4_compress_generic_validated */ +LZ4_FORCE_INLINE int LZ4_compress_generic( + LZ4_stream_t_internal* const cctx, + const char* const src, + char* const dst, + const int srcSize, + int *inputConsumed, /* only written when outputDirective == fillOutput */ + const int dstCapacity, + const limitedOutput_directive outputDirective, + const tableType_t tableType, + const dict_directive dictDirective, + const dictIssue_directive dictIssue, + const int acceleration) +{ + DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, dstCapacity=%i", + srcSize, dstCapacity); + + if ((U32)srcSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; } /* Unsupported srcSize, too large (or negative) */ + if (srcSize == 0) { /* src == NULL supported if srcSize == 0 */ + if (outputDirective != notLimited && dstCapacity <= 0) return 0; /* no output, can't write anything */ + DEBUGLOG(5, "Generating an empty block"); + assert(outputDirective == notLimited || dstCapacity >= 1); + assert(dst != NULL); + dst[0] = 0; + if (outputDirective == fillOutput) { + assert (inputConsumed != NULL); + *inputConsumed = 0; + } + return 1; + } + assert(src != NULL); + + return LZ4_compress_generic_validated(cctx, src, dst, srcSize, + inputConsumed, /* only written into if outputDirective == fillOutput */ + dstCapacity, outputDirective, + tableType, dictDirective, dictIssue, acceleration); +} + + +int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +{ + LZ4_stream_t_internal* const ctx = & LZ4_initStream(state, sizeof(LZ4_stream_t)) -> internal_donotuse; + assert(ctx != NULL); + if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; + if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX; + if (maxOutputSize >= LZ4_compressBound(inputSize)) { + if (inputSize < LZ4_64Klimit) { + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + if (inputSize < LZ4_64Klimit) { + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } +} + +/** + * LZ4_compress_fast_extState_fastReset() : + * A variant of LZ4_compress_fast_extState(). + * + * Using this variant avoids an expensive initialization step. It is only safe + * to call if the state buffer is known to be correctly initialized already + * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of + * "correctly initialized"). + */ +int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) +{ + LZ4_stream_t_internal* const ctx = &((LZ4_stream_t*)state)->internal_donotuse; + if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; + if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX; + assert(ctx != NULL); + + if (dstCapacity >= LZ4_compressBound(srcSize)) { + if (srcSize < LZ4_64Klimit) { + const tableType_t tableType = byU16; + LZ4_prepareTable(ctx, srcSize, tableType); + if (ctx->currentOffset) { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration); + } else { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + LZ4_prepareTable(ctx, srcSize, tableType); + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + if (srcSize < LZ4_64Klimit) { + const tableType_t tableType = byU16; + LZ4_prepareTable(ctx, srcSize, tableType); + if (ctx->currentOffset) { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration); + } else { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + LZ4_prepareTable(ctx, srcSize, tableType); + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } +} + + +int LZ4_compress_fast(const char* src, char* dest, int srcSize, int dstCapacity, int acceleration) +{ + int result; +#if (LZ4_HEAPMODE) + LZ4_stream_t* const ctxPtr = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + if (ctxPtr == NULL) return 0; +#else + LZ4_stream_t ctx; + LZ4_stream_t* const ctxPtr = &ctx; +#endif + result = LZ4_compress_fast_extState(ctxPtr, src, dest, srcSize, dstCapacity, acceleration); + +#if (LZ4_HEAPMODE) + FREEMEM(ctxPtr); +#endif + return result; +} + + +int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity) +{ + return LZ4_compress_fast(src, dst, srcSize, dstCapacity, 1); +} + + +/* Note!: This function leaves the stream in an unclean/broken state! + * It is not safe to subsequently use the same state with a _fastReset() or + * _continue() call without resetting it. */ +static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize) +{ + void* const s = LZ4_initStream(state, sizeof (*state)); + assert(s != NULL); (void)s; + + if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) { /* compression success is guaranteed */ + return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1); + } else { + if (*srcSizePtr < LZ4_64Klimit) { + return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1); + } else { + tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1); + } } +} + + +int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) +{ +#if (LZ4_HEAPMODE) + LZ4_stream_t* const ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + if (ctx == NULL) return 0; +#else + LZ4_stream_t ctxBody; + LZ4_stream_t* const ctx = &ctxBody; +#endif + + int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); + +#if (LZ4_HEAPMODE) + FREEMEM(ctx); +#endif + return result; +} + + + +/*-****************************** +* Streaming functions +********************************/ + +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +LZ4_stream_t* LZ4_createStream(void) +{ + LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); + LZ4_STATIC_ASSERT(sizeof(LZ4_stream_t) >= sizeof(LZ4_stream_t_internal)); + DEBUGLOG(4, "LZ4_createStream %p", lz4s); + if (lz4s == NULL) return NULL; + LZ4_initStream(lz4s, sizeof(*lz4s)); + return lz4s; +} +#endif + +static size_t LZ4_stream_t_alignment(void) +{ +#if LZ4_ALIGN_TEST + typedef struct { char c; LZ4_stream_t t; } t_a; + return sizeof(t_a) - sizeof(LZ4_stream_t); +#else + return 1; /* effectively disabled */ +#endif +} + +LZ4_stream_t* LZ4_initStream (void* buffer, size_t size) +{ + DEBUGLOG(5, "LZ4_initStream"); + if (buffer == NULL) { return NULL; } + if (size < sizeof(LZ4_stream_t)) { return NULL; } + if (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL; + MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal)); + return (LZ4_stream_t*)buffer; +} + +/* resetStream is now deprecated, + * prefer initStream() which is more general */ +void LZ4_resetStream (LZ4_stream_t* LZ4_stream) +{ + DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream); + MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t_internal)); +} + +void LZ4_resetStream_fast(LZ4_stream_t* ctx) { + LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32); +} + +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +int LZ4_freeStream (LZ4_stream_t* LZ4_stream) +{ + if (!LZ4_stream) return 0; /* support free on NULL */ + DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream); + FREEMEM(LZ4_stream); + return (0); +} +#endif + + +#define HASH_UNIT sizeof(reg_t) +int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) +{ + LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse; + const tableType_t tableType = byU32; + const BYTE* p = (const BYTE*)dictionary; + const BYTE* const dictEnd = p + dictSize; + U32 idx32; + + DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict); + + /* It's necessary to reset the context, + * and not just continue it with prepareTable() + * to avoid any risk of generating overflowing matchIndex + * when compressing using this dictionary */ + LZ4_resetStream(LZ4_dict); + + /* We always increment the offset by 64 KB, since, if the dict is longer, + * we truncate it to the last 64k, and if it's shorter, we still want to + * advance by a whole window length so we can provide the guarantee that + * there are only valid offsets in the window, which allows an optimization + * in LZ4_compress_fast_continue() where it uses noDictIssue even when the + * dictionary isn't a full 64k. */ + dict->currentOffset += 64 KB; + + if (dictSize < (int)HASH_UNIT) { + return 0; + } + + if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; + dict->dictionary = p; + dict->dictSize = (U32)(dictEnd - p); + dict->tableType = (U32)tableType; + idx32 = dict->currentOffset - dict->dictSize; + + while (p <= dictEnd-HASH_UNIT) { + U32 const h = LZ4_hashPosition(p, tableType); + LZ4_putIndexOnHash(idx32, h, dict->hashTable, tableType); + p+=3; idx32+=3; + } + + return (int)dict->dictSize; +} + +void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream) +{ + const LZ4_stream_t_internal* dictCtx = (dictionaryStream == NULL) ? NULL : + &(dictionaryStream->internal_donotuse); + + DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)", + workingStream, dictionaryStream, + dictCtx != NULL ? dictCtx->dictSize : 0); + + if (dictCtx != NULL) { + /* If the current offset is zero, we will never look in the + * external dictionary context, since there is no value a table + * entry can take that indicate a miss. In that case, we need + * to bump the offset to something non-zero. + */ + if (workingStream->internal_donotuse.currentOffset == 0) { + workingStream->internal_donotuse.currentOffset = 64 KB; + } + + /* Don't actually attach an empty dictionary. + */ + if (dictCtx->dictSize == 0) { + dictCtx = NULL; + } + } + workingStream->internal_donotuse.dictCtx = dictCtx; +} + + +static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize) +{ + assert(nextSize >= 0); + if (LZ4_dict->currentOffset + (unsigned)nextSize > 0x80000000) { /* potential ptrdiff_t overflow (32-bits mode) */ + /* rescale hash table */ + U32 const delta = LZ4_dict->currentOffset - 64 KB; + const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; + int i; + DEBUGLOG(4, "LZ4_renormDictT"); + for (i=0; ihashTable[i] < delta) LZ4_dict->hashTable[i]=0; + else LZ4_dict->hashTable[i] -= delta; + } + LZ4_dict->currentOffset = 64 KB; + if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB; + LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize; + } +} + + +int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, + const char* source, char* dest, + int inputSize, int maxOutputSize, + int acceleration) +{ + const tableType_t tableType = byU32; + LZ4_stream_t_internal* const streamPtr = &LZ4_stream->internal_donotuse; + const char* dictEnd = streamPtr->dictSize ? (const char*)streamPtr->dictionary + streamPtr->dictSize : NULL; + + DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i, dictSize=%u)", inputSize, streamPtr->dictSize); + + LZ4_renormDictT(streamPtr, inputSize); /* fix index overflow */ + if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; + if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX; + + /* invalidate tiny dictionaries */ + if ( (streamPtr->dictSize < 4) /* tiny dictionary : not enough for a hash */ + && (dictEnd != source) /* prefix mode */ + && (inputSize > 0) /* tolerance : don't lose history, in case next invocation would use prefix mode */ + && (streamPtr->dictCtx == NULL) /* usingDictCtx */ + ) { + DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary); + /* remove dictionary existence from history, to employ faster prefix mode */ + streamPtr->dictSize = 0; + streamPtr->dictionary = (const BYTE*)source; + dictEnd = source; + } + + /* Check overlapping input/dictionary space */ + { const char* const sourceEnd = source + inputSize; + if ((sourceEnd > (const char*)streamPtr->dictionary) && (sourceEnd < dictEnd)) { + streamPtr->dictSize = (U32)(dictEnd - sourceEnd); + if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB; + if (streamPtr->dictSize < 4) streamPtr->dictSize = 0; + streamPtr->dictionary = (const BYTE*)dictEnd - streamPtr->dictSize; + } + } + + /* prefix mode : source data follows dictionary */ + if (dictEnd == source) { + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) + return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration); + else + return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration); + } + + /* external dictionary mode */ + { int result; + if (streamPtr->dictCtx) { + /* We depend here on the fact that dictCtx'es (produced by + * LZ4_loadDict) guarantee that their tables contain no references + * to offsets between dictCtx->currentOffset - 64 KB and + * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe + * to use noDictIssue even when the dict isn't a full 64 KB. + */ + if (inputSize > 4 KB) { + /* For compressing large blobs, it is faster to pay the setup + * cost to copy the dictionary's tables into the active context, + * so that the compression loop is only looking into one table. + */ + LZ4_memcpy(streamPtr, streamPtr->dictCtx, sizeof(*streamPtr)); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration); + } + } else { /* small data <= 4 KB */ + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); + } + } + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)inputSize; + return result; + } +} + + +/* Hidden debug function, to force-test external dictionary mode */ +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize) +{ + LZ4_stream_t_internal* const streamPtr = &LZ4_dict->internal_donotuse; + int result; + + LZ4_renormDictT(streamPtr, srcSize); + + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { + result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + } + + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)srcSize; + + return result; +} + + +/*! LZ4_saveDict() : + * If previously compressed data block is not guaranteed to remain available at its memory location, + * save it into a safer place (char* safeBuffer). + * Note : no need to call LZ4_loadDict() afterwards, dictionary is immediately usable, + * one can therefore call LZ4_compress_fast_continue() right after. + * @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. + */ +int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) +{ + LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse; + + DEBUGLOG(5, "LZ4_saveDict : dictSize=%i, safeBuffer=%p", dictSize, safeBuffer); + + if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */ + if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; } + + if (safeBuffer == NULL) assert(dictSize == 0); + if (dictSize > 0) { + const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize; + assert(dict->dictionary); + LZ4_memmove(safeBuffer, previousDictEnd - dictSize, (size_t)dictSize); + } + + dict->dictionary = (const BYTE*)safeBuffer; + dict->dictSize = (U32)dictSize; + + return dictSize; +} + + + +/*-******************************* + * Decompression functions + ********************************/ + +typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive; + +#undef MIN +#define MIN(a,b) ( (a) < (b) ? (a) : (b) ) + + +/* variant for decompress_unsafe() + * does not know end of input + * presumes input is well formed + * note : will consume at least one byte */ +static size_t read_long_length_no_check(const BYTE** pp) +{ + size_t b, l = 0; + do { b = **pp; (*pp)++; l += b; } while (b==255); + DEBUGLOG(6, "read_long_length_no_check: +length=%zu using %zu input bytes", l, l/255 + 1) + return l; +} + +/* core decoder variant for LZ4_decompress_fast*() + * for legacy support only : these entry points are deprecated. + * - Presumes input is correctly formed (no defense vs malformed inputs) + * - Does not know input size (presume input buffer is "large enough") + * - Decompress a full block (only) + * @return : nb of bytes read from input. + * Note : this variant is not optimized for speed, just for maintenance. + * the goal is to remove support of decompress_fast*() variants by v2.0 +**/ +LZ4_FORCE_INLINE int +LZ4_decompress_unsafe_generic( + const BYTE* const istart, + BYTE* const ostart, + int decompressedSize, + + size_t prefixSize, + const BYTE* const dictStart, /* only if dict==usingExtDict */ + const size_t dictSize /* note: =0 if dictStart==NULL */ + ) +{ + const BYTE* ip = istart; + BYTE* op = (BYTE*)ostart; + BYTE* const oend = ostart + decompressedSize; + const BYTE* const prefixStart = ostart - prefixSize; + + DEBUGLOG(5, "LZ4_decompress_unsafe_generic"); + if (dictStart == NULL) assert(dictSize == 0); + + while (1) { + /* start new sequence */ + unsigned token = *ip++; + + /* literals */ + { size_t ll = token >> ML_BITS; + if (ll==15) { + /* long literal length */ + ll += read_long_length_no_check(&ip); + } + if ((size_t)(oend-op) < ll) return -1; /* output buffer overflow */ + LZ4_memmove(op, ip, ll); /* support in-place decompression */ + op += ll; + ip += ll; + if ((size_t)(oend-op) < MFLIMIT) { + if (op==oend) break; /* end of block */ + DEBUGLOG(5, "invalid: literals end at distance %zi from end of block", oend-op); + /* incorrect end of block : + * last match must start at least MFLIMIT==12 bytes before end of output block */ + return -1; + } } + + /* match */ + { size_t ml = token & 15; + size_t const offset = LZ4_readLE16(ip); + ip+=2; + + if (ml==15) { + /* long literal length */ + ml += read_long_length_no_check(&ip); + } + ml += MINMATCH; + + if ((size_t)(oend-op) < ml) return -1; /* output buffer overflow */ + + { const BYTE* match = op - offset; + + /* out of range */ + if (offset > (size_t)(op - prefixStart) + dictSize) { + DEBUGLOG(6, "offset out of range"); + return -1; + } + + /* check special case : extDict */ + if (offset > (size_t)(op - prefixStart)) { + /* extDict scenario */ + const BYTE* const dictEnd = dictStart + dictSize; + const BYTE* extMatch = dictEnd - (offset - (size_t)(op-prefixStart)); + size_t const extml = (size_t)(dictEnd - extMatch); + if (extml > ml) { + /* match entirely within extDict */ + LZ4_memmove(op, extMatch, ml); + op += ml; + ml = 0; + } else { + /* match split between extDict & prefix */ + LZ4_memmove(op, extMatch, extml); + op += extml; + ml -= extml; + } + match = prefixStart; + } + + /* match copy - slow variant, supporting overlap copy */ + { size_t u; + for (u=0; u= ipmax before start of loop. Returns initial_error if so. + * @error (output) - error code. Must be set to 0 before call. +**/ +typedef size_t Rvl_t; +static const Rvl_t rvl_error = (Rvl_t)(-1); +LZ4_FORCE_INLINE Rvl_t +read_variable_length(const BYTE** ip, const BYTE* ilimit, + int initial_check) +{ + Rvl_t s, length = 0; + assert(ip != NULL); + assert(*ip != NULL); + assert(ilimit != NULL); + if (initial_check && unlikely((*ip) >= ilimit)) { /* read limit reached */ + return rvl_error; + } + do { + s = **ip; + (*ip)++; + length += s; + if (unlikely((*ip) > ilimit)) { /* read limit reached */ + return rvl_error; + } + /* accumulator overflow detection (32-bit mode only) */ + if ((sizeof(length)<8) && unlikely(length > ((Rvl_t)(-1)/2)) ) { + return rvl_error; + } + } while (s==255); + + return length; +} + +/*! LZ4_decompress_generic() : + * This generic decompression function covers all use cases. + * It shall be instantiated several times, using different sets of directives. + * Note that it is important for performance that this function really get inlined, + * in order to remove useless branches during compilation optimization. + */ +LZ4_FORCE_INLINE int +LZ4_decompress_generic( + const char* const src, + char* const dst, + int srcSize, + int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ + + earlyEnd_directive partialDecoding, /* full, partial */ + dict_directive dict, /* noDict, withPrefix64k, usingExtDict */ + const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */ + const BYTE* const dictStart, /* only if dict==usingExtDict */ + const size_t dictSize /* note : = 0 if noDict */ + ) +{ + if ((src == NULL) || (outputSize < 0)) { return -1; } + + { const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; + + BYTE* op = (BYTE*) dst; + BYTE* const oend = op + outputSize; + BYTE* cpy; + + const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize; + + const int checkOffset = (dictSize < (int)(64 KB)); + + + /* Set up the "end" pointers for the shortcut. */ + const BYTE* const shortiend = iend - 14 /*maxLL*/ - 2 /*offset*/; + const BYTE* const shortoend = oend - 14 /*maxLL*/ - 18 /*maxML*/; + + const BYTE* match; + size_t offset; + unsigned token; + size_t length; + + + DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize); + + /* Special cases */ + assert(lowPrefix <= op); + if (unlikely(outputSize==0)) { + /* Empty output buffer */ + if (partialDecoding) return 0; + return ((srcSize==1) && (*ip==0)) ? 0 : -1; + } + if (unlikely(srcSize==0)) { return -1; } + + /* LZ4_FAST_DEC_LOOP: + * designed for modern OoO performance cpus, + * where copying reliably 32-bytes is preferable to an unpredictable branch. + * note : fast loop may show a regression for some client arm chips. */ +#if LZ4_FAST_DEC_LOOP + if ((oend - op) < FASTLOOP_SAFE_DISTANCE) { + DEBUGLOG(6, "skip fast decode loop"); + goto safe_decode; + } + + /* Fast loop : decode sequences as long as output < oend-FASTLOOP_SAFE_DISTANCE */ + DEBUGLOG(6, "using fast decode loop"); + while (1) { + /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */ + assert(oend - op >= FASTLOOP_SAFE_DISTANCE); + assert(ip < iend); + token = *ip++; + length = token >> ML_BITS; /* literal length */ + + /* decode literal length */ + if (length == RUN_MASK) { + size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1); + if (addl == rvl_error) { + DEBUGLOG(6, "error reading long literal length"); + goto _output_error; + } + length += addl; + if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */ + if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */ + + /* copy literals */ + cpy = op+length; + LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); + if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; } + LZ4_wildCopy32(op, ip, cpy); + ip += length; op = cpy; + } else { + cpy = op+length; + DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length); + /* We don't need to check oend, since we check it once for each loop below */ + if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; } + /* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */ + LZ4_memcpy(op, ip, 16); + ip += length; op = cpy; + } + + /* get offset */ + offset = LZ4_readLE16(ip); ip+=2; + DEBUGLOG(6, " offset = %zu", offset); + match = op - offset; + assert(match <= op); /* overflow check */ + + /* get matchlength */ + length = token & ML_MASK; + + if (length == ML_MASK) { + size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0); + if (addl == rvl_error) { + DEBUGLOG(6, "error reading long match length"); + goto _output_error; + } + length += addl; + length += MINMATCH; + if (unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */ + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { + DEBUGLOG(6, "Error : offset outside buffers"); + goto _output_error; + } + if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { + goto safe_match_copy; + } + } else { + length += MINMATCH; + if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { + goto safe_match_copy; + } + + /* Fastpath check: skip LZ4_wildCopy32 when true */ + if ((dict == withPrefix64k) || (match >= lowPrefix)) { + if (offset >= 8) { + assert(match >= lowPrefix); + assert(match <= op); + assert(op + 18 <= oend); + + LZ4_memcpy(op, match, 8); + LZ4_memcpy(op+8, match+8, 8); + LZ4_memcpy(op+16, match+16, 2); + op += length; + continue; + } } } + + if ( checkOffset && (unlikely(match + dictSize < lowPrefix)) ) { + DEBUGLOG(6, "Error : pos=%zi, offset=%zi => outside buffers", op-lowPrefix, op-match); + goto _output_error; + } + /* match starting within external dictionary */ + if ((dict==usingExtDict) && (match < lowPrefix)) { + assert(dictEnd != NULL); + if (unlikely(op+length > oend-LASTLITERALS)) { + if (partialDecoding) { + DEBUGLOG(7, "partialDecoding: dictionary match, close to dstEnd"); + length = MIN(length, (size_t)(oend-op)); + } else { + DEBUGLOG(6, "end-of-block condition violated") + goto _output_error; + } } + + if (length <= (size_t)(lowPrefix-match)) { + /* match fits entirely within external dictionary : just copy */ + LZ4_memmove(op, dictEnd - (lowPrefix-match), length); + op += length; + } else { + /* match stretches into both external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix - match); + size_t const restSize = length - copySize; + LZ4_memcpy(op, dictEnd - copySize, copySize); + op += copySize; + if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ + BYTE* const endOfMatch = op + restSize; + const BYTE* copyFrom = lowPrefix; + while (op < endOfMatch) { *op++ = *copyFrom++; } + } else { + LZ4_memcpy(op, lowPrefix, restSize); + op += restSize; + } } + continue; + } + + /* copy match within block */ + cpy = op + length; + + assert((op <= oend) && (oend-op >= 32)); + if (unlikely(offset<16)) { + LZ4_memcpy_using_offset(op, match, cpy, offset); + } else { + LZ4_wildCopy32(op, match, cpy); + } + + op = cpy; /* wildcopy correction */ + } + safe_decode: +#endif + + /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */ + DEBUGLOG(6, "using safe decode loop"); + while (1) { + assert(ip < iend); + token = *ip++; + length = token >> ML_BITS; /* literal length */ + + /* A two-stage shortcut for the most common case: + * 1) If the literal length is 0..14, and there is enough space, + * enter the shortcut and copy 16 bytes on behalf of the literals + * (in the fast mode, only 8 bytes can be safely copied this way). + * 2) Further if the match length is 4..18, copy 18 bytes in a similar + * manner; but we ensure that there's enough space in the output for + * those 18 bytes earlier, upon entering the shortcut (in other words, + * there is a combined check for both stages). + */ + if ( (length != RUN_MASK) + /* strictly "less than" on input, to re-enter the loop with at least one byte */ + && likely((ip < shortiend) & (op <= shortoend)) ) { + /* Copy the literals */ + LZ4_memcpy(op, ip, 16); + op += length; ip += length; + + /* The second stage: prepare for match copying, decode full info. + * If it doesn't work out, the info won't be wasted. */ + length = token & ML_MASK; /* match length */ + offset = LZ4_readLE16(ip); ip += 2; + match = op - offset; + assert(match <= op); /* check overflow */ + + /* Do not deal with overlapping matches. */ + if ( (length != ML_MASK) + && (offset >= 8) + && (dict==withPrefix64k || match >= lowPrefix) ) { + /* Copy the match. */ + LZ4_memcpy(op + 0, match + 0, 8); + LZ4_memcpy(op + 8, match + 8, 8); + LZ4_memcpy(op +16, match +16, 2); + op += length + MINMATCH; + /* Both stages worked, load the next token. */ + continue; + } + + /* The second stage didn't work out, but the info is ready. + * Propel it right to the point of match copying. */ + goto _copy_match; + } + + /* decode literal length */ + if (length == RUN_MASK) { + size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1); + if (addl == rvl_error) { goto _output_error; } + length += addl; + if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */ + if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */ + } + + /* copy literals */ + cpy = op+length; +#if LZ4_FAST_DEC_LOOP + safe_literal_copy: +#endif + LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); + if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) { + /* We've either hit the input parsing restriction or the output parsing restriction. + * In the normal scenario, decoding a full block, it must be the last sequence, + * otherwise it's an error (invalid input or dimensions). + * In partialDecoding scenario, it's necessary to ensure there is no buffer overflow. + */ + if (partialDecoding) { + /* Since we are partial decoding we may be in this block because of the output parsing + * restriction, which is not valid since the output buffer is allowed to be undersized. + */ + DEBUGLOG(7, "partialDecoding: copying literals, close to input or output end") + DEBUGLOG(7, "partialDecoding: literal length = %u", (unsigned)length); + DEBUGLOG(7, "partialDecoding: remaining space in dstBuffer : %i", (int)(oend - op)); + DEBUGLOG(7, "partialDecoding: remaining space in srcBuffer : %i", (int)(iend - ip)); + /* Finishing in the middle of a literals segment, + * due to lack of input. + */ + if (ip+length > iend) { + length = (size_t)(iend-ip); + cpy = op + length; + } + /* Finishing in the middle of a literals segment, + * due to lack of output space. + */ + if (cpy > oend) { + cpy = oend; + assert(op<=oend); + length = (size_t)(oend-op); + } + } else { + /* We must be on the last sequence (or invalid) because of the parsing limitations + * so check that we exactly consume the input and don't overrun the output buffer. + */ + if ((ip+length != iend) || (cpy > oend)) { + DEBUGLOG(6, "should have been last run of literals") + DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend); + DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend); + goto _output_error; + } + } + LZ4_memmove(op, ip, length); /* supports overlapping memory regions, for in-place decompression scenarios */ + ip += length; + op += length; + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend-2))) { + break; + } + } else { + LZ4_wildCopy8(op, ip, cpy); /* can overwrite up to 8 bytes beyond cpy */ + ip += length; op = cpy; + } + + /* get offset */ + offset = LZ4_readLE16(ip); ip+=2; + match = op - offset; + + /* get matchlength */ + length = token & ML_MASK; + + _copy_match: + if (length == ML_MASK) { + size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0); + if (addl == rvl_error) { goto _output_error; } + length += addl; + if (unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ + } + length += MINMATCH; + +#if LZ4_FAST_DEC_LOOP + safe_match_copy: +#endif + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ + /* match starting within external dictionary */ + if ((dict==usingExtDict) && (match < lowPrefix)) { + assert(dictEnd != NULL); + if (unlikely(op+length > oend-LASTLITERALS)) { + if (partialDecoding) length = MIN(length, (size_t)(oend-op)); + else goto _output_error; /* doesn't respect parsing restriction */ + } + + if (length <= (size_t)(lowPrefix-match)) { + /* match fits entirely within external dictionary : just copy */ + LZ4_memmove(op, dictEnd - (lowPrefix-match), length); + op += length; + } else { + /* match stretches into both external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix - match); + size_t const restSize = length - copySize; + LZ4_memcpy(op, dictEnd - copySize, copySize); + op += copySize; + if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ + BYTE* const endOfMatch = op + restSize; + const BYTE* copyFrom = lowPrefix; + while (op < endOfMatch) *op++ = *copyFrom++; + } else { + LZ4_memcpy(op, lowPrefix, restSize); + op += restSize; + } } + continue; + } + assert(match >= lowPrefix); + + /* copy match within block */ + cpy = op + length; + + /* partialDecoding : may end anywhere within the block */ + assert(op<=oend); + if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + size_t const mlen = MIN(length, (size_t)(oend-op)); + const BYTE* const matchEnd = match + mlen; + BYTE* const copyEnd = op + mlen; + if (matchEnd > op) { /* overlap copy */ + while (op < copyEnd) { *op++ = *match++; } + } else { + LZ4_memcpy(op, match, mlen); + } + op = copyEnd; + if (op == oend) { break; } + continue; + } + + if (unlikely(offset<8)) { + LZ4_write32(op, 0); /* silence msan warning when offset==0 */ + op[0] = match[0]; + op[1] = match[1]; + op[2] = match[2]; + op[3] = match[3]; + match += inc32table[offset]; + LZ4_memcpy(op+4, match, 4); + match -= dec64table[offset]; + } else { + LZ4_memcpy(op, match, 8); + match += 8; + } + op += 8; + + if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1); + if (cpy > oend-LASTLITERALS) { goto _output_error; } /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ + if (op < oCopyLimit) { + LZ4_wildCopy8(op, match, oCopyLimit); + match += oCopyLimit - op; + op = oCopyLimit; + } + while (op < cpy) { *op++ = *match++; } + } else { + LZ4_memcpy(op, match, 8); + if (length > 16) { LZ4_wildCopy8(op+8, match+8, cpy); } + } + op = cpy; /* wildcopy correction */ + } + + /* end of decoding */ + DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst)); + return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ + + /* Overflow error detected */ + _output_error: + return (int) (-(((const char*)ip)-src))-1; + } +} + + +/*===== Instantiate the API decoding functions. =====*/ + +LZ4_FORCE_O2 +int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, + decode_full_block, noDict, + (BYTE*)dest, NULL, 0); +} + +LZ4_FORCE_O2 +int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, + partial_decode, + noDict, (BYTE*)dst, NULL, 0); +} + +LZ4_FORCE_O2 +int LZ4_decompress_fast(const char* source, char* dest, int originalSize) +{ + DEBUGLOG(5, "LZ4_decompress_fast"); + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + 0, NULL, 0); +} + +/*===== Instantiate a few more decoding cases, used more than once. =====*/ + +LZ4_FORCE_O2 /* Exported, an obsolete API function. */ +int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + decode_full_block, withPrefix64k, + (BYTE*)dest - 64 KB, NULL, 0); +} + +LZ4_FORCE_O2 +static int LZ4_decompress_safe_partial_withPrefix64k(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity, + partial_decode, withPrefix64k, + (BYTE*)dest - 64 KB, NULL, 0); +} + +/* Another obsolete API function, paired with the previous one. */ +int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) +{ + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + 64 KB, NULL, 0); +} + +LZ4_FORCE_O2 +static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize, + size_t prefixSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + decode_full_block, noDict, + (BYTE*)dest-prefixSize, NULL, 0); +} + +LZ4_FORCE_O2 +static int LZ4_decompress_safe_partial_withSmallPrefix(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, + size_t prefixSize) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity, + partial_decode, noDict, + (BYTE*)dest-prefixSize, NULL, 0); +} + +LZ4_FORCE_O2 +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, + int compressedSize, int maxOutputSize, + const void* dictStart, size_t dictSize) +{ + DEBUGLOG(5, "LZ4_decompress_safe_forceExtDict"); + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + decode_full_block, usingExtDict, + (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +LZ4_FORCE_O2 +int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest, + int compressedSize, int targetOutputSize, int dstCapacity, + const void* dictStart, size_t dictSize) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity, + partial_decode, usingExtDict, + (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +LZ4_FORCE_O2 +static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize, + const void* dictStart, size_t dictSize) +{ + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + 0, (const BYTE*)dictStart, dictSize); +} + +/* The "double dictionary" mode, for use with e.g. ring buffers: the first part + * of the dictionary is passed as prefix, and the second via dictStart + dictSize. + * These routines are used only once, in LZ4_decompress_*_continue(). + */ +LZ4_FORCE_INLINE +int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize, + size_t prefixSize, const void* dictStart, size_t dictSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + decode_full_block, usingExtDict, + (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); +} + +/*===== streaming decompression functions =====*/ + +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +LZ4_streamDecode_t* LZ4_createStreamDecode(void) +{ + LZ4_STATIC_ASSERT(sizeof(LZ4_streamDecode_t) >= sizeof(LZ4_streamDecode_t_internal)); + return (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t)); +} + +int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) +{ + if (LZ4_stream == NULL) { return 0; } /* support free on NULL */ + FREEMEM(LZ4_stream); + return 0; +} +#endif + +/*! LZ4_setStreamDecode() : + * Use this function to instruct where to find the dictionary. + * This function is not necessary if previous data is still available where it was decoded. + * Loading a size of 0 is allowed (same effect as no dictionary). + * @return : 1 if OK, 0 if error + */ +int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) +{ + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; + lz4sd->prefixSize = (size_t)dictSize; + if (dictSize) { + assert(dictionary != NULL); + lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + } else { + lz4sd->prefixEnd = (const BYTE*) dictionary; + } + lz4sd->externalDict = NULL; + lz4sd->extDictSize = 0; + return 1; +} + +/*! LZ4_decoderRingBufferSize() : + * when setting a ring buffer for streaming decompression (optional scenario), + * provides the minimum size of this ring buffer + * to be compatible with any source respecting maxBlockSize condition. + * Note : in a ring buffer scenario, + * blocks are presumed decompressed next to each other. + * When not enough space remains for next block (remainingSize < maxBlockSize), + * decoding resumes from beginning of ring buffer. + * @return : minimum ring buffer size, + * or 0 if there is an error (invalid maxBlockSize). + */ +int LZ4_decoderRingBufferSize(int maxBlockSize) +{ + if (maxBlockSize < 0) return 0; + if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0; + if (maxBlockSize < 16) maxBlockSize = 16; + return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize); +} + +/* +*_continue() : + These decoding functions allow decompression of multiple blocks in "streaming" mode. + Previously decoded blocks must still be available at the memory position where they were decoded. + If it's not possible, save the relevant part of decoded data into a safe buffer, + and indicate where it stands using LZ4_setStreamDecode() +*/ +LZ4_FORCE_O2 +int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) +{ + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; + int result; + + if (lz4sd->prefixSize == 0) { + /* The first call, no dictionary yet. */ + assert(lz4sd->extDictSize == 0); + result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); + if (result <= 0) return result; + lz4sd->prefixSize = (size_t)result; + lz4sd->prefixEnd = (BYTE*)dest + result; + } else if (lz4sd->prefixEnd == (BYTE*)dest) { + /* They're rolling the current segment. */ + if (lz4sd->prefixSize >= 64 KB - 1) + result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); + else if (lz4sd->extDictSize == 0) + result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, + lz4sd->prefixSize); + else + result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize, + lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += (size_t)result; + lz4sd->prefixEnd += result; + } else { + /* The buffer wraps around, or they're switching to another buffer. */ + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; + result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, + lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = (size_t)result; + lz4sd->prefixEnd = (BYTE*)dest + result; + } + + return result; +} + +LZ4_FORCE_O2 int +LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, + const char* source, char* dest, int originalSize) +{ + LZ4_streamDecode_t_internal* const lz4sd = + (assert(LZ4_streamDecode!=NULL), &LZ4_streamDecode->internal_donotuse); + int result; + + DEBUGLOG(5, "LZ4_decompress_fast_continue (toDecodeSize=%i)", originalSize); + assert(originalSize >= 0); + + if (lz4sd->prefixSize == 0) { + DEBUGLOG(5, "first invocation : no prefix nor extDict"); + assert(lz4sd->extDictSize == 0); + result = LZ4_decompress_fast(source, dest, originalSize); + if (result <= 0) return result; + lz4sd->prefixSize = (size_t)originalSize; + lz4sd->prefixEnd = (BYTE*)dest + originalSize; + } else if (lz4sd->prefixEnd == (BYTE*)dest) { + DEBUGLOG(5, "continue using existing prefix"); + result = LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + lz4sd->prefixSize, + lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += (size_t)originalSize; + lz4sd->prefixEnd += originalSize; + } else { + DEBUGLOG(5, "prefix becomes extDict"); + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; + result = LZ4_decompress_fast_extDict(source, dest, originalSize, + lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = (size_t)originalSize; + lz4sd->prefixEnd = (BYTE*)dest + originalSize; + } + + return result; +} + + +/* +Advanced decoding functions : +*_usingDict() : + These decoding functions work the same as "_continue" ones, + the dictionary must be explicitly provided within parameters +*/ + +int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) +{ + if (dictSize==0) + return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); + if (dictStart+dictSize == dest) { + if (dictSize >= 64 KB - 1) { + return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize); +} + +int LZ4_decompress_safe_partial_usingDict(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, const char* dictStart, int dictSize) +{ + if (dictSize==0) + return LZ4_decompress_safe_partial(source, dest, compressedSize, targetOutputSize, dstCapacity); + if (dictStart+dictSize == dest) { + if (dictSize >= 64 KB - 1) { + return LZ4_decompress_safe_partial_withPrefix64k(source, dest, compressedSize, targetOutputSize, dstCapacity); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_partial_withSmallPrefix(source, dest, compressedSize, targetOutputSize, dstCapacity, (size_t)dictSize); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_partial_forceExtDict(source, dest, compressedSize, targetOutputSize, dstCapacity, dictStart, (size_t)dictSize); +} + +int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) +{ + if (dictSize==0 || dictStart+dictSize == dest) + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + (size_t)dictSize, NULL, 0); + assert(dictSize >= 0); + return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize); +} + + +/*=************************************************* +* Obsolete Functions +***************************************************/ +/* obsolete compression functions */ +int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_compress_default(source, dest, inputSize, maxOutputSize); +} +int LZ4_compress(const char* src, char* dest, int srcSize) +{ + return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize)); +} +int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) +{ + return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); +} +int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) +{ + return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); +} +int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int dstCapacity) +{ + return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1); +} +int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) +{ + return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); +} + +/* +These decompression functions are deprecated and should no longer be used. +They are only provided here for compatibility with older user programs. +- LZ4_uncompress is totally equivalent to LZ4_decompress_fast +- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe +*/ +int LZ4_uncompress (const char* source, char* dest, int outputSize) +{ + return LZ4_decompress_fast(source, dest, outputSize); +} +int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) +{ + return LZ4_decompress_safe(source, dest, isize, maxOutputSize); +} + +/* Obsolete Streaming functions */ + +int LZ4_sizeofStreamState(void) { return sizeof(LZ4_stream_t); } + +int LZ4_resetStreamState(void* state, char* inputBuffer) +{ + (void)inputBuffer; + LZ4_resetStream((LZ4_stream_t*)state); + return 0; +} + +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +void* LZ4_create (char* inputBuffer) +{ + (void)inputBuffer; + return LZ4_createStream(); +} +#endif + +char* LZ4_slideInputBuffer (void* state) +{ + /* avoid const char * -> char * conversion warning */ + return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary; +} + +#endif /* LZ4_COMMONDEFS_ONLY */ \ No newline at end of file diff --git a/src/lz4.h b/src/lz4.h new file mode 100644 index 0000000..4bd2a57 --- /dev/null +++ b/src/lz4.h @@ -0,0 +1,862 @@ +/* + * LZ4 - Fast LZ compression algorithm + * Header File + * Copyright (C) 2011-2020, Yann Collet. + + BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions are + met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following disclaimer + in the documentation and/or other materials provided with the + distribution. + + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "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 COPYRIGHT + OWNER OR CONTRIBUTORS 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. + + You can contact the author at : + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 +*/ +#if defined (__cplusplus) +extern "C" { +#endif + +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 + +/* --- Dependency --- */ +#include /* size_t */ + + +/** + Introduction + + LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core, + scalable with multi-cores CPU. It features an extremely fast decoder, with speed in + multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. + + The LZ4 compression library provides in-memory compression and decompression functions. + It gives full buffer control to user. + Compression can be done in: + - a single step (described as Simple Functions) + - a single step, reusing a context (described in Advanced Functions) + - unbounded multiple steps (described as Streaming compression) + + lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md). + Decompressing such a compressed block requires additional metadata. + Exact metadata depends on exact decompression function. + For the typical case of LZ4_decompress_safe(), + metadata includes block's compressed size, and maximum bound of decompressed size. + Each application is free to encode and pass such metadata in whichever way it wants. + + lz4.h only handle blocks, it can not generate Frames. + + Blocks are different from Frames (doc/lz4_Frame_format.md). + Frames bundle both blocks and metadata in a specified manner. + Embedding metadata is required for compressed data to be self-contained and portable. + Frame format is delivered through a companion API, declared in lz4frame.h. + The `lz4` CLI can only manage frames. +*/ + +/*^*************************************************************** +* Export parameters +*****************************************************************/ +/* +* LZ4_DLL_EXPORT : +* Enable exporting of functions when building a Windows DLL +* LZ4LIB_VISIBILITY : +* Control library symbols visibility. +*/ +#ifndef LZ4LIB_VISIBILITY +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default"))) +# else +# define LZ4LIB_VISIBILITY +# endif +#endif +#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) +# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY +#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) +# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#else +# define LZ4LIB_API LZ4LIB_VISIBILITY +#endif + +/*! LZ4_FREESTANDING : + * When this macro is set to 1, it enables "freestanding mode" that is + * suitable for typical freestanding environment which doesn't support + * standard C library. + * + * - LZ4_FREESTANDING is a compile-time switch. + * - It requires the following macros to be defined: + * LZ4_memcpy, LZ4_memmove, LZ4_memset. + * - It only enables LZ4/HC functions which don't use heap. + * All LZ4F_* functions are not supported. + * - See tests/freestanding.c to check its basic setup. + */ +#if defined(LZ4_FREESTANDING) && (LZ4_FREESTANDING == 1) +# define LZ4_HEAPMODE 0 +# define LZ4HC_HEAPMODE 0 +# define LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION 1 +# if !defined(LZ4_memcpy) +# error "LZ4_FREESTANDING requires macro 'LZ4_memcpy'." +# endif +# if !defined(LZ4_memset) +# error "LZ4_FREESTANDING requires macro 'LZ4_memset'." +# endif +# if !defined(LZ4_memmove) +# error "LZ4_FREESTANDING requires macro 'LZ4_memmove'." +# endif +#elif ! defined(LZ4_FREESTANDING) +# define LZ4_FREESTANDING 0 +#endif + + +/*------ Version ------*/ +#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ +#define LZ4_VERSION_MINOR 9 /* for new (non-breaking) interface capabilities */ +#define LZ4_VERSION_RELEASE 4 /* for tweaks, bug-fixes, or development */ + +#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) + +#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE +#define LZ4_QUOTE(str) #str +#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) +#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) /* requires v1.7.3+ */ + +LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version; requires v1.3.0+ */ +LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version; requires v1.7.5+ */ + + +/*-************************************ +* Tuning parameter +**************************************/ +#define LZ4_MEMORY_USAGE_MIN 10 +#define LZ4_MEMORY_USAGE_DEFAULT 14 +#define LZ4_MEMORY_USAGE_MAX 20 + +/*! + * LZ4_MEMORY_USAGE : + * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; ) + * Increasing memory usage improves compression ratio, at the cost of speed. + * Reduced memory usage may improve speed at the cost of ratio, thanks to better cache locality. + * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache + */ +#ifndef LZ4_MEMORY_USAGE +# define LZ4_MEMORY_USAGE LZ4_MEMORY_USAGE_DEFAULT +#endif + +#if (LZ4_MEMORY_USAGE < LZ4_MEMORY_USAGE_MIN) +# error "LZ4_MEMORY_USAGE is too small !" +#endif + +#if (LZ4_MEMORY_USAGE > LZ4_MEMORY_USAGE_MAX) +# error "LZ4_MEMORY_USAGE is too large !" +#endif + +/*-************************************ +* Simple Functions +**************************************/ +/*! LZ4_compress_default() : + * Compresses 'srcSize' bytes from buffer 'src' + * into already allocated 'dst' buffer of size 'dstCapacity'. + * Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize). + * It also runs faster, so it's a recommended setting. + * If the function cannot compress 'src' into a more limited 'dst' budget, + * compression stops *immediately*, and the function result is zero. + * In which case, 'dst' content is undefined (invalid). + * srcSize : max supported value is LZ4_MAX_INPUT_SIZE. + * dstCapacity : size of buffer 'dst' (which must be already allocated) + * @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity) + * or 0 if compression fails + * Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer). + */ +LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity); + +/*! LZ4_decompress_safe() : + * @compressedSize : is the exact complete size of the compressed block. + * @dstCapacity : is the size of destination buffer (which must be already allocated), + * is an upper bound of decompressed size. + * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity) + * If destination buffer is not large enough, decoding will stop and output an error code (negative value). + * If the source stream is detected malformed, the function will stop decoding and return a negative result. + * Note 1 : This function is protected against malicious data packets : + * it will never writes outside 'dst' buffer, nor read outside 'source' buffer, + * even if the compressed block is maliciously modified to order the decoder to do these actions. + * In such case, the decoder stops immediately, and considers the compressed block malformed. + * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them. + * The implementation is free to send / store / derive this information in whichever way is most beneficial. + * If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead. + */ +LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity); + + +/*-************************************ +* Advanced Functions +**************************************/ +#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ +#define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) + +/*! LZ4_compressBound() : + Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible) + This function is primarily useful for memory allocation purposes (destination buffer size). + Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example). + Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize) + inputSize : max supported value is LZ4_MAX_INPUT_SIZE + return : maximum output size in a "worst case" scenario + or 0, if input size is incorrect (too large or negative) +*/ +LZ4LIB_API int LZ4_compressBound(int inputSize); + +/*! LZ4_compress_fast() : + Same as LZ4_compress_default(), but allows selection of "acceleration" factor. + The larger the acceleration value, the faster the algorithm, but also the lesser the compression. + It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed. + An acceleration value of "1" is the same as regular LZ4_compress_default() + Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT (currently == 1, see lz4.c). + Values > LZ4_ACCELERATION_MAX will be replaced by LZ4_ACCELERATION_MAX (currently == 65537, see lz4.c). +*/ +LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + + +/*! LZ4_compress_fast_extState() : + * Same as LZ4_compress_fast(), using an externally allocated memory space for its state. + * Use LZ4_sizeofState() to know how much memory must be allocated, + * and allocate it on 8-bytes boundaries (using `malloc()` typically). + * Then, provide this buffer as `void* state` to compression function. + */ +LZ4LIB_API int LZ4_sizeofState(void); +LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + + +/*! LZ4_compress_destSize() : + * Reverse the logic : compresses as much data as possible from 'src' buffer + * into already allocated buffer 'dst', of size >= 'targetDestSize'. + * This function either compresses the entire 'src' content into 'dst' if it's large enough, + * or fill 'dst' buffer completely with as much data as possible from 'src'. + * note: acceleration parameter is fixed to "default". + * + * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'. + * New value is necessarily <= input value. + * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize) + * or 0 if compression fails. + * + * Note : from v1.8.2 to v1.9.1, this function had a bug (fixed un v1.9.2+): + * the produced compressed content could, in specific circumstances, + * require to be decompressed into a destination buffer larger + * by at least 1 byte than the content to decompress. + * If an application uses `LZ4_compress_destSize()`, + * it's highly recommended to update liblz4 to v1.9.2 or better. + * If this can't be done or ensured, + * the receiving decompression function should provide + * a dstCapacity which is > decompressedSize, by at least 1 byte. + * See https://github.com/lz4/lz4/issues/859 for details + */ +LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize); + + +/*! LZ4_decompress_safe_partial() : + * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src', + * into destination buffer 'dst' of size 'dstCapacity'. + * Up to 'targetOutputSize' bytes will be decoded. + * The function stops decoding on reaching this objective. + * This can be useful to boost performance + * whenever only the beginning of a block is required. + * + * @return : the number of bytes decoded in `dst` (necessarily <= targetOutputSize) + * If source stream is detected malformed, function returns a negative result. + * + * Note 1 : @return can be < targetOutputSize, if compressed block contains less data. + * + * Note 2 : targetOutputSize must be <= dstCapacity + * + * Note 3 : this function effectively stops decoding on reaching targetOutputSize, + * so dstCapacity is kind of redundant. + * This is because in older versions of this function, + * decoding operation would still write complete sequences. + * Therefore, there was no guarantee that it would stop writing at exactly targetOutputSize, + * it could write more bytes, though only up to dstCapacity. + * Some "margin" used to be required for this operation to work properly. + * Thankfully, this is no longer necessary. + * The function nonetheless keeps the same signature, in an effort to preserve API compatibility. + * + * Note 4 : If srcSize is the exact size of the block, + * then targetOutputSize can be any value, + * including larger than the block's decompressed size. + * The function will, at most, generate block's decompressed size. + * + * Note 5 : If srcSize is _larger_ than block's compressed size, + * then targetOutputSize **MUST** be <= block's decompressed size. + * Otherwise, *silent corruption will occur*. + */ +LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity); + + +/*-********************************************* +* Streaming Compression Functions +***********************************************/ +typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ + +/** + Note about RC_INVOKED + + - RC_INVOKED is predefined symbol of rc.exe (the resource compiler which is part of MSVC/Visual Studio). + https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros + + - Since rc.exe is a legacy compiler, it truncates long symbol (> 30 chars) + and reports warning "RC4011: identifier truncated". + + - To eliminate the warning, we surround long preprocessor symbol with + "#if !defined(RC_INVOKED) ... #endif" block that means + "skip this block when rc.exe is trying to read it". +*/ +#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */ +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); +LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); +#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */ +#endif + +/*! LZ4_resetStream_fast() : v1.9.0+ + * Use this to prepare an LZ4_stream_t for a new chain of dependent blocks + * (e.g., LZ4_compress_fast_continue()). + * + * An LZ4_stream_t must be initialized once before usage. + * This is automatically done when created by LZ4_createStream(). + * However, should the LZ4_stream_t be simply declared on stack (for example), + * it's necessary to initialize it first, using LZ4_initStream(). + * + * After init, start any new stream with LZ4_resetStream_fast(). + * A same LZ4_stream_t can be re-used multiple times consecutively + * and compress multiple streams, + * provided that it starts each new stream with LZ4_resetStream_fast(). + * + * LZ4_resetStream_fast() is much faster than LZ4_initStream(), + * but is not compatible with memory regions containing garbage data. + * + * Note: it's only useful to call LZ4_resetStream_fast() + * in the context of streaming compression. + * The *extState* functions perform their own resets. + * Invoking LZ4_resetStream_fast() before is redundant, and even counterproductive. + */ +LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr); + +/*! LZ4_loadDict() : + * Use this function to reference a static dictionary into LZ4_stream_t. + * The dictionary must remain available during compression. + * LZ4_loadDict() triggers a reset, so any previous data will be forgotten. + * The same dictionary will have to be loaded on decompression side for successful decoding. + * Dictionary are useful for better compression of small data (KB range). + * While LZ4 accept any input as dictionary, + * results are generally better when using Zstandard's Dictionary Builder. + * Loading a size of 0 is allowed, and is the same as reset. + * @return : loaded dictionary size, in bytes (necessarily <= 64 KB) + */ +LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); + +/*! LZ4_compress_fast_continue() : + * Compress 'src' content using data from previously compressed blocks, for better compression ratio. + * 'dst' buffer must be already allocated. + * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * + * @return : size of compressed block + * or 0 if there is an error (typically, cannot fit into 'dst'). + * + * Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block. + * Each block has precise boundaries. + * Each block must be decompressed separately, calling LZ4_decompress_*() with relevant metadata. + * It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together. + * + * Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory ! + * + * Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB. + * Make sure that buffers are separated, by at least one byte. + * This construction ensures that each block only depends on previous block. + * + * Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. + * + * Note 5 : After an error, the stream status is undefined (invalid), it can only be reset or freed. + */ +LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + +/*! LZ4_saveDict() : + * If last 64KB data cannot be guaranteed to remain available at its current memory location, + * save it into a safer place (char* safeBuffer). + * This is schematically equivalent to a memcpy() followed by LZ4_loadDict(), + * but is much faster, because LZ4_saveDict() doesn't need to rebuild tables. + * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error. + */ +LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize); + + +/*-********************************************** +* Streaming Decompression Functions +* Bufferless synchronous API +************************************************/ +typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */ + +/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() : + * creation / destruction of streaming decompression tracking context. + * A tracking context can be re-used multiple times. + */ +#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */ +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); +LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); +#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */ +#endif + +/*! LZ4_setStreamDecode() : + * An LZ4_streamDecode_t context can be allocated once and re-used multiple times. + * Use this function to start decompression of a new stream of blocks. + * A dictionary can optionally be set. Use NULL or size 0 for a reset order. + * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression. + * @return : 1 if OK, 0 if error + */ +LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); + +/*! LZ4_decoderRingBufferSize() : v1.8.2+ + * Note : in a ring buffer scenario (optional), + * blocks are presumed decompressed next to each other + * up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize), + * at which stage it resumes from beginning of ring buffer. + * When setting such a ring buffer for streaming decompression, + * provides the minimum size of this ring buffer + * to be compatible with any source respecting maxBlockSize condition. + * @return : minimum ring buffer size, + * or 0 if there is an error (invalid maxBlockSize). + */ +LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize); +#define LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize) (65536 + 14 + (maxBlockSize)) /* for static allocation; maxBlockSize presumed valid */ + +/*! LZ4_decompress_safe_continue() : + * This decoding function allows decompression of consecutive blocks in "streaming" mode. + * The difference with the usual independent blocks is that + * new blocks are allowed to find references into former blocks. + * A block is an unsplittable entity, and must be presented entirely to the decompression function. + * LZ4_decompress_safe_continue() only accepts one block at a time. + * It's modeled after `LZ4_decompress_safe()` and behaves similarly. + * + * @LZ4_streamDecode : decompression state, tracking the position in memory of past data + * @compressedSize : exact complete size of one compressed block. + * @dstCapacity : size of destination buffer (which must be already allocated), + * must be an upper bound of decompressed size. + * @return : number of bytes decompressed into destination buffer (necessarily <= dstCapacity) + * If destination buffer is not large enough, decoding will stop and output an error code (negative value). + * If the source stream is detected malformed, the function will stop decoding and return a negative result. + * + * The last 64KB of previously decoded data *must* remain available and unmodified + * at the memory position where they were previously decoded. + * If less than 64KB of data has been decoded, all the data must be present. + * + * Special : if decompression side sets a ring buffer, it must respect one of the following conditions : + * - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize). + * maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes. + * In which case, encoding and decoding buffers do not need to be synchronized. + * Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize. + * - Synchronized mode : + * Decompression buffer size is _exactly_ the same as compression buffer size, + * and follows exactly same update rule (block boundaries at same positions), + * and decoding function is provided with exact decompressed size of each block (exception for last block of the stream), + * _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB). + * - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes. + * In which case, encoding and decoding buffers do not need to be synchronized, + * and encoding ring buffer can have any size, including small ones ( < 64 KB). + * + * Whenever these conditions are not possible, + * save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression, + * then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block. +*/ +LZ4LIB_API int +LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, + const char* src, char* dst, + int srcSize, int dstCapacity); + + +/*! LZ4_decompress_safe_usingDict() : + * Works the same as + * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_safe_continue() + * However, it's stateless: it doesn't need any LZ4_streamDecode_t state. + * Dictionary is presumed stable : it must remain accessible and unmodified during decompression. + * Performance tip : Decompression speed can be substantially increased + * when dst == dictStart + dictSize. + */ +LZ4LIB_API int +LZ4_decompress_safe_usingDict(const char* src, char* dst, + int srcSize, int dstCapacity, + const char* dictStart, int dictSize); + +/*! LZ4_decompress_safe_partial_usingDict() : + * Behaves the same as LZ4_decompress_safe_partial() + * with the added ability to specify a memory segment for past data. + * Performance tip : Decompression speed can be substantially increased + * when dst == dictStart + dictSize. + */ +LZ4LIB_API int +LZ4_decompress_safe_partial_usingDict(const char* src, char* dst, + int compressedSize, + int targetOutputSize, int maxOutputSize, + const char* dictStart, int dictSize); + +#endif /* LZ4_H_2983827168210 */ + + +/*^************************************* + * !!!!!! STATIC LINKING ONLY !!!!!! + ***************************************/ + +/*-**************************************************************************** + * Experimental section + * + * Symbols declared in this section must be considered unstable. Their + * signatures or semantics may change, or they may be removed altogether in the + * future. They are therefore only safe to depend on when the caller is + * statically linked against the library. + * + * To protect against unsafe usage, not only are the declarations guarded, + * the definitions are hidden by default + * when building LZ4 as a shared/dynamic library. + * + * In order to access these declarations, + * define LZ4_STATIC_LINKING_ONLY in your application + * before including LZ4's headers. + * + * In order to make their implementations accessible dynamically, you must + * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library. + ******************************************************************************/ + +#ifdef LZ4_STATIC_LINKING_ONLY + +#ifndef LZ4_STATIC_3504398509 +#define LZ4_STATIC_3504398509 + +#ifdef LZ4_PUBLISH_STATIC_FUNCTIONS +#define LZ4LIB_STATIC_API LZ4LIB_API +#else +#define LZ4LIB_STATIC_API +#endif + + +/*! LZ4_compress_fast_extState_fastReset() : + * A variant of LZ4_compress_fast_extState(). + * + * Using this variant avoids an expensive initialization step. + * It is only safe to call if the state buffer is known to be correctly initialized already + * (see above comment on LZ4_resetStream_fast() for a definition of "correctly initialized"). + * From a high level, the difference is that + * this function initializes the provided state with a call to something like LZ4_resetStream_fast() + * while LZ4_compress_fast_extState() starts with a call to LZ4_resetStream(). + */ +LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + +/*! LZ4_attach_dictionary() : + * This is an experimental API that allows + * efficient use of a static dictionary many times. + * + * Rather than re-loading the dictionary buffer into a working context before + * each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a + * working LZ4_stream_t, this function introduces a no-copy setup mechanism, + * in which the working stream references the dictionary stream in-place. + * + * Several assumptions are made about the state of the dictionary stream. + * Currently, only streams which have been prepared by LZ4_loadDict() should + * be expected to work. + * + * Alternatively, the provided dictionaryStream may be NULL, + * in which case any existing dictionary stream is unset. + * + * If a dictionary is provided, it replaces any pre-existing stream history. + * The dictionary contents are the only history that can be referenced and + * logically immediately precede the data compressed in the first subsequent + * compression call. + * + * The dictionary will only remain attached to the working stream through the + * first compression call, at the end of which it is cleared. The dictionary + * stream (and source buffer) must remain in-place / accessible / unchanged + * through the completion of the first compression call on the stream. + */ +LZ4LIB_STATIC_API void +LZ4_attach_dictionary(LZ4_stream_t* workingStream, + const LZ4_stream_t* dictionaryStream); + + +/*! In-place compression and decompression + * + * It's possible to have input and output sharing the same buffer, + * for highly constrained memory environments. + * In both cases, it requires input to lay at the end of the buffer, + * and decompression to start at beginning of the buffer. + * Buffer size must feature some margin, hence be larger than final size. + * + * |<------------------------buffer--------------------------------->| + * |<-----------compressed data--------->| + * |<-----------decompressed size------------------>| + * |<----margin---->| + * + * This technique is more useful for decompression, + * since decompressed size is typically larger, + * and margin is short. + * + * In-place decompression will work inside any buffer + * which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize). + * This presumes that decompressedSize > compressedSize. + * Otherwise, it means compression actually expanded data, + * and it would be more efficient to store such data with a flag indicating it's not compressed. + * This can happen when data is not compressible (already compressed, or encrypted). + * + * For in-place compression, margin is larger, as it must be able to cope with both + * history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX, + * and data expansion, which can happen when input is not compressible. + * As a consequence, buffer size requirements are much higher, + * and memory savings offered by in-place compression are more limited. + * + * There are ways to limit this cost for compression : + * - Reduce history size, by modifying LZ4_DISTANCE_MAX. + * Note that it is a compile-time constant, so all compressions will apply this limit. + * Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX, + * so it's a reasonable trick when inputs are known to be small. + * - Require the compressor to deliver a "maximum compressed size". + * This is the `dstCapacity` parameter in `LZ4_compress*()`. + * When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail, + * in which case, the return code will be 0 (zero). + * The caller must be ready for these cases to happen, + * and typically design a backup scheme to send data uncompressed. + * The combination of both techniques can significantly reduce + * the amount of margin required for in-place compression. + * + * In-place compression can work in any buffer + * which size is >= (maxCompressedSize) + * with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success. + * LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX, + * so it's possible to reduce memory requirements by playing with them. + */ + +#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32) +#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize) ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize)) /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */ + +#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */ +# define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */ +#endif + +#define LZ4_COMPRESS_INPLACE_MARGIN (LZ4_DISTANCE_MAX + 32) /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */ +#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize) ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN) /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */ + +#endif /* LZ4_STATIC_3504398509 */ +#endif /* LZ4_STATIC_LINKING_ONLY */ + + + +#ifndef LZ4_H_98237428734687 +#define LZ4_H_98237428734687 + +/*-************************************************************ + * Private Definitions + ************************************************************** + * Do not use these definitions directly. + * They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`. + * Accessing members will expose user code to API and/or ABI break in future versions of the library. + **************************************************************/ +#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) +#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) +#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */ + +#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +# include + typedef int8_t LZ4_i8; + typedef uint8_t LZ4_byte; + typedef uint16_t LZ4_u16; + typedef uint32_t LZ4_u32; +#else + typedef signed char LZ4_i8; + typedef unsigned char LZ4_byte; + typedef unsigned short LZ4_u16; + typedef unsigned int LZ4_u32; +#endif + +/*! LZ4_stream_t : + * Never ever use below internal definitions directly ! + * These definitions are not API/ABI safe, and may change in future versions. + * If you need static allocation, declare or allocate an LZ4_stream_t object. +**/ + +typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; +struct LZ4_stream_t_internal { + LZ4_u32 hashTable[LZ4_HASH_SIZE_U32]; + const LZ4_byte* dictionary; + const LZ4_stream_t_internal* dictCtx; + LZ4_u32 currentOffset; + LZ4_u32 tableType; + LZ4_u32 dictSize; + /* Implicit padding to ensure structure is aligned */ +}; + +#define LZ4_STREAM_MINSIZE ((1UL << LZ4_MEMORY_USAGE) + 32) /* static size, for inter-version compatibility */ +union LZ4_stream_u { + char minStateSize[LZ4_STREAM_MINSIZE]; + LZ4_stream_t_internal internal_donotuse; +}; /* previously typedef'd to LZ4_stream_t */ + + +/*! LZ4_initStream() : v1.9.0+ + * An LZ4_stream_t structure must be initialized at least once. + * This is automatically done when invoking LZ4_createStream(), + * but it's not when the structure is simply declared on stack (for example). + * + * Use LZ4_initStream() to properly initialize a newly declared LZ4_stream_t. + * It can also initialize any arbitrary buffer of sufficient size, + * and will @return a pointer of proper type upon initialization. + * + * Note : initialization fails if size and alignment conditions are not respected. + * In which case, the function will @return NULL. + * Note2: An LZ4_stream_t structure guarantees correct alignment and size. + * Note3: Before v1.9.0, use LZ4_resetStream() instead +**/ +LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size); + + +/*! LZ4_streamDecode_t : + * Never ever use below internal definitions directly ! + * These definitions are not API/ABI safe, and may change in future versions. + * If you need static allocation, declare or allocate an LZ4_streamDecode_t object. +**/ +typedef struct { + const LZ4_byte* externalDict; + const LZ4_byte* prefixEnd; + size_t extDictSize; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + +#define LZ4_STREAMDECODE_MINSIZE 32 +union LZ4_streamDecode_u { + char minStateSize[LZ4_STREAMDECODE_MINSIZE]; + LZ4_streamDecode_t_internal internal_donotuse; +} ; /* previously typedef'd to LZ4_streamDecode_t */ + + + +/*-************************************ +* Obsolete Functions +**************************************/ + +/*! Deprecation warnings + * + * Deprecated functions make the compiler generate a warning when invoked. + * This is meant to invite users to update their source code. + * Should deprecation warnings be a problem, it is generally possible to disable them, + * typically with -Wno-deprecated-declarations for gcc + * or _CRT_SECURE_NO_WARNINGS in Visual. + * + * Another method is to define LZ4_DISABLE_DEPRECATE_WARNINGS + * before including the header file. + */ +#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS +# define LZ4_DEPRECATED(message) /* disable deprecation warnings */ +#else +# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ +# define LZ4_DEPRECATED(message) [[deprecated(message)]] +# elif defined(_MSC_VER) +# define LZ4_DEPRECATED(message) __declspec(deprecated(message)) +# elif defined(__clang__) || (defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 45)) +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 31) +# define LZ4_DEPRECATED(message) __attribute__((deprecated)) +# else +# pragma message("WARNING: LZ4_DEPRECATED needs custom implementation for this compiler") +# define LZ4_DEPRECATED(message) /* disabled */ +# endif +#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */ + +/*! Obsolete compression functions (since v1.7.3) */ +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); + +/*! Obsolete decompression functions (since v1.8.0) */ +LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize); +LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); + +/* Obsolete streaming functions (since v1.7.0) + * degraded functionality; do not use! + * + * In order to perform streaming compression, these functions depended on data + * that is no longer tracked in the state. They have been preserved as well as + * possible: using them will still produce a correct output. However, they don't + * actually retain any history between compression calls. The compression ratio + * achieved will therefore be no better than compressing each chunk + * independently. + */ +LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer); +LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void); +LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer); +LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API char* LZ4_slideInputBuffer (void* state); + +/*! Obsolete streaming decoding functions (since v1.7.0) */ +LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); +LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); + +/*! Obsolete LZ4_decompress_fast variants (since v1.9.0) : + * These functions used to be faster than LZ4_decompress_safe(), + * but this is no longer the case. They are now slower. + * This is because LZ4_decompress_fast() doesn't know the input size, + * and therefore must progress more cautiously into the input buffer to not read beyond the end of block. + * On top of that `LZ4_decompress_fast()` is not protected vs malformed or malicious inputs, making it a security liability. + * As a consequence, LZ4_decompress_fast() is strongly discouraged, and deprecated. + * + * The last remaining LZ4_decompress_fast() specificity is that + * it can decompress a block without knowing its compressed size. + * Such functionality can be achieved in a more secure manner + * by employing LZ4_decompress_safe_partial(). + * + * Parameters: + * originalSize : is the uncompressed size to regenerate. + * `dst` must be already allocated, its size must be >= 'originalSize' bytes. + * @return : number of bytes read from source buffer (== compressed size). + * The function expects to finish at block's end exactly. + * If the source stream is detected malformed, the function stops decoding and returns a negative result. + * note : LZ4_decompress_fast*() requires originalSize. Thanks to this information, it never writes past the output buffer. + * However, since it doesn't know its 'src' size, it may read an unknown amount of input, past input buffer bounds. + * Also, since match offsets are not validated, match reads from 'src' may underflow too. + * These issues never happen if input (compressed) data is correct. + * But they may happen if input data is invalid (error or intentional tampering). + * As a consequence, use these functions in trusted environments with trusted data **only**. + */ +LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe() instead") +LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize); +LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_continue() instead") +LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize); +LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_usingDict() instead") +LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize); + +/*! LZ4_resetStream() : + * An LZ4_stream_t structure must be initialized at least once. + * This is done with LZ4_initStream(), or LZ4_resetStream(). + * Consider switching to LZ4_initStream(), + * invoking LZ4_resetStream() will trigger deprecation warnings in the future. + */ +LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); + + +#endif /* LZ4_H_98237428734687 */ + + +#if defined (__cplusplus) +} +#endif \ No newline at end of file diff --git a/src/send_message_mgr.cc b/src/send_message_mgr.cc index ee1ef5c..73ce467 100644 --- a/src/send_message_mgr.cc +++ b/src/send_message_mgr.cc @@ -4,6 +4,10 @@ #include "db.h" #include "contact_mgr.h" #include "spdlog/spdlog.h" +#include "base64.h" +#include "lz4.h" +#include "tinyxml2.h" + namespace wxhelper { SendMessageMgr::SendMessageMgr(DWORD base):BaseMgr(base) {} SendMessageMgr::~SendMessageMgr() {} @@ -289,4 +293,82 @@ int SendMessageMgr::ForwardPublicMsg(wchar_t* wxid, wchar_t* title, wchar_t* url } return success; } + +int SendMessageMgr::ForwardPublicMsgByMsgSvrId(wchar_t *wxid, unsigned long long msgid){ + + std::string compress_content =DB::GetInstance().GetPublicMsgCompressContentByMsgId(msgid); + if (compress_content.empty()) { + SPDLOG_INFO("Get compressContent is null from PublicMsg.db"); + return -3; + } + + std::string decode = base64_decode(compress_content); + size_t len = decode.size(); + const char* src = decode.c_str() ; + size_t dst_len = (len << 8) ; + char* dst = new char[dst_len]; + + int decompress_len = LZ4_decompress_safe_partial(src,dst,len,dst_len,dst_len); + if (decompress_len < 0) { + SPDLOG_INFO("decompress content size :{}",decompress_len); + return -1; + } + tinyxml2::XMLDocument doc; + if(doc.Parse(dst,decompress_len-1) != 0){ + SPDLOG_INFO("tinyxml2 parse error"); + return -2; + } + const char* title = doc.FirstChildElement( "msg" )->FirstChildElement( "appmsg" )->FirstChildElement("title")->GetText(); + const char* digest = doc.FirstChildElement( "msg" )->FirstChildElement( "appmsg" )->FirstChildElement("des")->GetText(); + + const char* url = doc.FirstChildElement("msg") + ->FirstChildElement("appmsg") + ->FirstChildElement("mmreader") + ->FirstChildElement("category") + ->FirstChildElement("item") + ->FirstChildElement("url") + ->GetText(); + const char* thumburl = doc.FirstChildElement("msg") + ->FirstChildElement("appmsg") + ->FirstChildElement("thumburl") + ->GetText(); + const char* username = doc.FirstChildElement("msg") + ->FirstChildElement("appmsg") + ->FirstChildElement("mmreader") + ->FirstChildElement("publisher") + ->FirstChildElement("username") + ->GetText(); + + const char* nickname = doc.FirstChildElement("msg") + ->FirstChildElement("appmsg") + ->FirstChildElement("mmreader") + ->FirstChildElement("publisher") + ->FirstChildElement("nickname") + ->GetText(); + + std::string stitle(title); + std::string sdigest(digest); + std::string surl(url); + std::string sthumburl(thumburl); + std::string susername(username); + std::string snickname(nickname); + + std::wstring wstitle =Utils::UTF8ToWstring(stitle); + std::wstring wsdigest =Utils::UTF8ToWstring(sdigest); + std::wstring wsurl =Utils::UTF8ToWstring(surl); + std::wstring wsthumburl =Utils::UTF8ToWstring(sthumburl); + std::wstring wsusername =Utils::UTF8ToWstring(susername); + std::wstring wsnickname =Utils::UTF8ToWstring(snickname); + + int code = ForwardPublicMsg(wxid, const_cast(wstitle.c_str()), + const_cast(wsurl.c_str()), + const_cast(wsthumburl.c_str()), + const_cast(wsusername.c_str()), + const_cast(wsnickname.c_str()), + const_cast(wsdigest.c_str()) + + ); + + return code; +} } // namespace wxhelper \ No newline at end of file diff --git a/src/send_message_mgr.h b/src/send_message_mgr.h index 55783dd..fbf3f22 100644 --- a/src/send_message_mgr.h +++ b/src/send_message_mgr.h @@ -12,6 +12,7 @@ class SendMessageMgr:public BaseMgr { int SendFile(wchar_t *wxid, wchar_t *file_path); int ForwardMsg(wchar_t *wxid, unsigned long long msgid); int ForwardPublicMsg(wchar_t* wxid, wchar_t* title, wchar_t* url, wchar_t* thumburl,wchar_t* senderId,wchar_t* senderName,wchar_t* digest); + int ForwardPublicMsgByMsgSvrId(wchar_t *wxid, unsigned long long msgid); private: }; diff --git a/src/tinyxml2.cpp b/src/tinyxml2.cpp new file mode 100644 index 0000000..feeb238 --- /dev/null +++ b/src/tinyxml2.cpp @@ -0,0 +1,2994 @@ +/* +Original code by Lee Thomason (www.grinninglizard.com) + +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. +*/ + +#include "tinyxml2.h" + +#include // yes, this one new style header, is in the Android SDK. +#if defined(ANDROID_NDK) || defined(__BORLANDC__) || defined(__QNXNTO__) +# include +# include +#else +# include +# include +#endif + +#if defined(_MSC_VER) && (_MSC_VER >= 1400 ) && (!defined WINCE) + // Microsoft Visual Studio, version 2005 and higher. Not WinCE. + /*int _snprintf_s( + char *buffer, + size_t sizeOfBuffer, + size_t count, + const char *format [, + argument] ... + );*/ + static inline int TIXML_SNPRINTF( char* buffer, size_t size, const char* format, ... ) + { + va_list va; + va_start( va, format ); + const int result = vsnprintf_s( buffer, size, _TRUNCATE, format, va ); + va_end( va ); + return result; + } + + static inline int TIXML_VSNPRINTF( char* buffer, size_t size, const char* format, va_list va ) + { + const int result = vsnprintf_s( buffer, size, _TRUNCATE, format, va ); + return result; + } + + #define TIXML_VSCPRINTF _vscprintf + #define TIXML_SSCANF sscanf_s +#elif defined _MSC_VER + // Microsoft Visual Studio 2003 and earlier or WinCE + #define TIXML_SNPRINTF _snprintf + #define TIXML_VSNPRINTF _vsnprintf + #define TIXML_SSCANF sscanf + #if (_MSC_VER < 1400 ) && (!defined WINCE) + // Microsoft Visual Studio 2003 and not WinCE. + #define TIXML_VSCPRINTF _vscprintf // VS2003's C runtime has this, but VC6 C runtime or WinCE SDK doesn't have. + #else + // Microsoft Visual Studio 2003 and earlier or WinCE. + static inline int TIXML_VSCPRINTF( const char* format, va_list va ) + { + int len = 512; + for (;;) { + len = len*2; + char* str = new char[len](); + const int required = _vsnprintf(str, len, format, va); + delete[] str; + if ( required != -1 ) { + TIXMLASSERT( required >= 0 ); + len = required; + break; + } + } + TIXMLASSERT( len >= 0 ); + return len; + } + #endif +#else + // GCC version 3 and higher + //#warning( "Using sn* functions." ) + #define TIXML_SNPRINTF snprintf + #define TIXML_VSNPRINTF vsnprintf + static inline int TIXML_VSCPRINTF( const char* format, va_list va ) + { + int len = vsnprintf( 0, 0, format, va ); + TIXMLASSERT( len >= 0 ); + return len; + } + #define TIXML_SSCANF sscanf +#endif + +#if defined(_WIN64) + #define TIXML_FSEEK _fseeki64 + #define TIXML_FTELL _ftelli64 +#elif defined(__APPLE__) || defined(__FreeBSD__) || defined(__OpenBSD__) || defined(__NetBSD__) || defined(__DragonFly__) || (__CYGWIN__) + #define TIXML_FSEEK fseeko + #define TIXML_FTELL ftello +#elif defined(__ANDROID__) + #if __ANDROID_API__ > 24 + #define TIXML_FSEEK fseeko64 + #define TIXML_FTELL ftello64 + #else + #define TIXML_FSEEK fseeko + #define TIXML_FTELL ftello + #endif +#elif defined(__unix__) && defined(__x86_64__) + #define TIXML_FSEEK fseeko64 + #define TIXML_FTELL ftello64 +#else + #define TIXML_FSEEK fseek + #define TIXML_FTELL ftell +#endif + + +static const char LINE_FEED = static_cast(0x0a); // all line endings are normalized to LF +static const char LF = LINE_FEED; +static const char CARRIAGE_RETURN = static_cast(0x0d); // CR gets filtered out +static const char CR = CARRIAGE_RETURN; +static const char SINGLE_QUOTE = '\''; +static const char DOUBLE_QUOTE = '\"'; + +// Bunch of unicode info at: +// http://www.unicode.org/faq/utf_bom.html +// ef bb bf (Microsoft "lead bytes") - designates UTF-8 + +static const unsigned char TIXML_UTF_LEAD_0 = 0xefU; +static const unsigned char TIXML_UTF_LEAD_1 = 0xbbU; +static const unsigned char TIXML_UTF_LEAD_2 = 0xbfU; + +namespace tinyxml2 +{ + +struct Entity { + const char* pattern; + int length; + char value; +}; + +static const int NUM_ENTITIES = 5; +static const Entity entities[NUM_ENTITIES] = { + { "quot", 4, DOUBLE_QUOTE }, + { "amp", 3, '&' }, + { "apos", 4, SINGLE_QUOTE }, + { "lt", 2, '<' }, + { "gt", 2, '>' } +}; + + +StrPair::~StrPair() +{ + Reset(); +} + + +void StrPair::TransferTo( StrPair* other ) +{ + if ( this == other ) { + return; + } + // This in effect implements the assignment operator by "moving" + // ownership (as in auto_ptr). + + TIXMLASSERT( other != 0 ); + TIXMLASSERT( other->_flags == 0 ); + TIXMLASSERT( other->_start == 0 ); + TIXMLASSERT( other->_end == 0 ); + + other->Reset(); + + other->_flags = _flags; + other->_start = _start; + other->_end = _end; + + _flags = 0; + _start = 0; + _end = 0; +} + + +void StrPair::Reset() +{ + if ( _flags & NEEDS_DELETE ) { + delete [] _start; + } + _flags = 0; + _start = 0; + _end = 0; +} + + +void StrPair::SetStr( const char* str, int flags ) +{ + TIXMLASSERT( str ); + Reset(); + size_t len = strlen( str ); + TIXMLASSERT( _start == 0 ); + _start = new char[ len+1 ]; + memcpy( _start, str, len+1 ); + _end = _start + len; + _flags = flags | NEEDS_DELETE; +} + + +char* StrPair::ParseText( char* p, const char* endTag, int strFlags, int* curLineNumPtr ) +{ + TIXMLASSERT( p ); + TIXMLASSERT( endTag && *endTag ); + TIXMLASSERT(curLineNumPtr); + + char* start = p; + const char endChar = *endTag; + size_t length = strlen( endTag ); + + // Inner loop of text parsing. + while ( *p ) { + if ( *p == endChar && strncmp( p, endTag, length ) == 0 ) { + Set( start, p, strFlags ); + return p + length; + } else if (*p == '\n') { + ++(*curLineNumPtr); + } + ++p; + TIXMLASSERT( p ); + } + return 0; +} + + +char* StrPair::ParseName( char* p ) +{ + if ( !p || !(*p) ) { + return 0; + } + if ( !XMLUtil::IsNameStartChar( (unsigned char) *p ) ) { + return 0; + } + + char* const start = p; + ++p; + while ( *p && XMLUtil::IsNameChar( (unsigned char) *p ) ) { + ++p; + } + + Set( start, p, 0 ); + return p; +} + + +void StrPair::CollapseWhitespace() +{ + // Adjusting _start would cause undefined behavior on delete[] + TIXMLASSERT( ( _flags & NEEDS_DELETE ) == 0 ); + // Trim leading space. + _start = XMLUtil::SkipWhiteSpace( _start, 0 ); + + if ( *_start ) { + const char* p = _start; // the read pointer + char* q = _start; // the write pointer + + while( *p ) { + if ( XMLUtil::IsWhiteSpace( *p )) { + p = XMLUtil::SkipWhiteSpace( p, 0 ); + if ( *p == 0 ) { + break; // don't write to q; this trims the trailing space. + } + *q = ' '; + ++q; + } + *q = *p; + ++q; + ++p; + } + *q = 0; + } +} + + +const char* StrPair::GetStr() +{ + TIXMLASSERT( _start ); + TIXMLASSERT( _end ); + if ( _flags & NEEDS_FLUSH ) { + *_end = 0; + _flags ^= NEEDS_FLUSH; + + if ( _flags ) { + const char* p = _start; // the read pointer + char* q = _start; // the write pointer + + while( p < _end ) { + if ( (_flags & NEEDS_NEWLINE_NORMALIZATION) && *p == CR ) { + // CR-LF pair becomes LF + // CR alone becomes LF + // LF-CR becomes LF + if ( *(p+1) == LF ) { + p += 2; + } + else { + ++p; + } + *q = LF; + ++q; + } + else if ( (_flags & NEEDS_NEWLINE_NORMALIZATION) && *p == LF ) { + if ( *(p+1) == CR ) { + p += 2; + } + else { + ++p; + } + *q = LF; + ++q; + } + else if ( (_flags & NEEDS_ENTITY_PROCESSING) && *p == '&' ) { + // Entities handled by tinyXML2: + // - special entities in the entity table [in/out] + // - numeric character reference [in] + // 中 or 中 + + if ( *(p+1) == '#' ) { + const int buflen = 10; + char buf[buflen] = { 0 }; + int len = 0; + const char* adjusted = const_cast( XMLUtil::GetCharacterRef( p, buf, &len ) ); + if ( adjusted == 0 ) { + *q = *p; + ++p; + ++q; + } + else { + TIXMLASSERT( 0 <= len && len <= buflen ); + TIXMLASSERT( q + len <= adjusted ); + p = adjusted; + memcpy( q, buf, len ); + q += len; + } + } + else { + bool entityFound = false; + for( int i = 0; i < NUM_ENTITIES; ++i ) { + const Entity& entity = entities[i]; + if ( strncmp( p + 1, entity.pattern, entity.length ) == 0 + && *( p + entity.length + 1 ) == ';' ) { + // Found an entity - convert. + *q = entity.value; + ++q; + p += entity.length + 2; + entityFound = true; + break; + } + } + if ( !entityFound ) { + // fixme: treat as error? + ++p; + ++q; + } + } + } + else { + *q = *p; + ++p; + ++q; + } + } + *q = 0; + } + // The loop below has plenty going on, and this + // is a less useful mode. Break it out. + if ( _flags & NEEDS_WHITESPACE_COLLAPSING ) { + CollapseWhitespace(); + } + _flags = (_flags & NEEDS_DELETE); + } + TIXMLASSERT( _start ); + return _start; +} + + + + +// --------- XMLUtil ----------- // + +const char* XMLUtil::writeBoolTrue = "true"; +const char* XMLUtil::writeBoolFalse = "false"; + +void XMLUtil::SetBoolSerialization(const char* writeTrue, const char* writeFalse) +{ + static const char* defTrue = "true"; + static const char* defFalse = "false"; + + writeBoolTrue = (writeTrue) ? writeTrue : defTrue; + writeBoolFalse = (writeFalse) ? writeFalse : defFalse; +} + + +const char* XMLUtil::ReadBOM( const char* p, bool* bom ) +{ + TIXMLASSERT( p ); + TIXMLASSERT( bom ); + *bom = false; + const unsigned char* pu = reinterpret_cast(p); + // Check for BOM: + if ( *(pu+0) == TIXML_UTF_LEAD_0 + && *(pu+1) == TIXML_UTF_LEAD_1 + && *(pu+2) == TIXML_UTF_LEAD_2 ) { + *bom = true; + p += 3; + } + TIXMLASSERT( p ); + return p; +} + + +void XMLUtil::ConvertUTF32ToUTF8( unsigned long input, char* output, int* length ) +{ + const unsigned long BYTE_MASK = 0xBF; + const unsigned long BYTE_MARK = 0x80; + const unsigned long FIRST_BYTE_MARK[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC }; + + if (input < 0x80) { + *length = 1; + } + else if ( input < 0x800 ) { + *length = 2; + } + else if ( input < 0x10000 ) { + *length = 3; + } + else if ( input < 0x200000 ) { + *length = 4; + } + else { + *length = 0; // This code won't convert this correctly anyway. + return; + } + + output += *length; + + // Scary scary fall throughs are annotated with carefully designed comments + // to suppress compiler warnings such as -Wimplicit-fallthrough in gcc + switch (*length) { + case 4: + --output; + *output = static_cast((input | BYTE_MARK) & BYTE_MASK); + input >>= 6; + //fall through + case 3: + --output; + *output = static_cast((input | BYTE_MARK) & BYTE_MASK); + input >>= 6; + //fall through + case 2: + --output; + *output = static_cast((input | BYTE_MARK) & BYTE_MASK); + input >>= 6; + //fall through + case 1: + --output; + *output = static_cast(input | FIRST_BYTE_MARK[*length]); + break; + default: + TIXMLASSERT( false ); + } +} + + +const char* XMLUtil::GetCharacterRef( const char* p, char* value, int* length ) +{ + // Presume an entity, and pull it out. + *length = 0; + + if ( *(p+1) == '#' && *(p+2) ) { + unsigned long ucs = 0; + TIXMLASSERT( sizeof( ucs ) >= 4 ); + ptrdiff_t delta = 0; + unsigned mult = 1; + static const char SEMICOLON = ';'; + + if ( *(p+2) == 'x' ) { + // Hexadecimal. + const char* q = p+3; + if ( !(*q) ) { + return 0; + } + + q = strchr( q, SEMICOLON ); + + if ( !q ) { + return 0; + } + TIXMLASSERT( *q == SEMICOLON ); + + delta = q-p; + --q; + + while ( *q != 'x' ) { + unsigned int digit = 0; + + if ( *q >= '0' && *q <= '9' ) { + digit = *q - '0'; + } + else if ( *q >= 'a' && *q <= 'f' ) { + digit = *q - 'a' + 10; + } + else if ( *q >= 'A' && *q <= 'F' ) { + digit = *q - 'A' + 10; + } + else { + return 0; + } + TIXMLASSERT( digit < 16 ); + TIXMLASSERT( digit == 0 || mult <= UINT_MAX / digit ); + const unsigned int digitScaled = mult * digit; + TIXMLASSERT( ucs <= ULONG_MAX - digitScaled ); + ucs += digitScaled; + TIXMLASSERT( mult <= UINT_MAX / 16 ); + mult *= 16; + --q; + } + } + else { + // Decimal. + const char* q = p+2; + if ( !(*q) ) { + return 0; + } + + q = strchr( q, SEMICOLON ); + + if ( !q ) { + return 0; + } + TIXMLASSERT( *q == SEMICOLON ); + + delta = q-p; + --q; + + while ( *q != '#' ) { + if ( *q >= '0' && *q <= '9' ) { + const unsigned int digit = *q - '0'; + TIXMLASSERT( digit < 10 ); + TIXMLASSERT( digit == 0 || mult <= UINT_MAX / digit ); + const unsigned int digitScaled = mult * digit; + TIXMLASSERT( ucs <= ULONG_MAX - digitScaled ); + ucs += digitScaled; + } + else { + return 0; + } + TIXMLASSERT( mult <= UINT_MAX / 10 ); + mult *= 10; + --q; + } + } + // convert the UCS to UTF-8 + ConvertUTF32ToUTF8( ucs, value, length ); + return p + delta + 1; + } + return p+1; +} + + +void XMLUtil::ToStr( int v, char* buffer, int bufferSize ) +{ + TIXML_SNPRINTF( buffer, bufferSize, "%d", v ); +} + + +void XMLUtil::ToStr( unsigned v, char* buffer, int bufferSize ) +{ + TIXML_SNPRINTF( buffer, bufferSize, "%u", v ); +} + + +void XMLUtil::ToStr( bool v, char* buffer, int bufferSize ) +{ + TIXML_SNPRINTF( buffer, bufferSize, "%s", v ? writeBoolTrue : writeBoolFalse); +} + +/* + ToStr() of a number is a very tricky topic. + https://github.com/leethomason/tinyxml2/issues/106 +*/ +void XMLUtil::ToStr( float v, char* buffer, int bufferSize ) +{ + TIXML_SNPRINTF( buffer, bufferSize, "%.8g", v ); +} + + +void XMLUtil::ToStr( double v, char* buffer, int bufferSize ) +{ + TIXML_SNPRINTF( buffer, bufferSize, "%.17g", v ); +} + + +void XMLUtil::ToStr( int64_t v, char* buffer, int bufferSize ) +{ + // horrible syntax trick to make the compiler happy about %lld + TIXML_SNPRINTF(buffer, bufferSize, "%lld", static_cast(v)); +} + +void XMLUtil::ToStr( uint64_t v, char* buffer, int bufferSize ) +{ + // horrible syntax trick to make the compiler happy about %llu + TIXML_SNPRINTF(buffer, bufferSize, "%llu", (long long)v); +} + +bool XMLUtil::ToInt(const char* str, int* value) +{ + if (IsPrefixHex(str)) { + unsigned v; + if (TIXML_SSCANF(str, "%x", &v) == 1) { + *value = static_cast(v); + return true; + } + } + else { + if (TIXML_SSCANF(str, "%d", value) == 1) { + return true; + } + } + return false; +} + +bool XMLUtil::ToUnsigned(const char* str, unsigned* value) +{ + if (TIXML_SSCANF(str, IsPrefixHex(str) ? "%x" : "%u", value) == 1) { + return true; + } + return false; +} + +bool XMLUtil::ToBool( const char* str, bool* value ) +{ + int ival = 0; + if ( ToInt( str, &ival )) { + *value = (ival==0) ? false : true; + return true; + } + static const char* TRUE_VALS[] = { "true", "True", "TRUE", 0 }; + static const char* FALSE_VALS[] = { "false", "False", "FALSE", 0 }; + + for (int i = 0; TRUE_VALS[i]; ++i) { + if (StringEqual(str, TRUE_VALS[i])) { + *value = true; + return true; + } + } + for (int i = 0; FALSE_VALS[i]; ++i) { + if (StringEqual(str, FALSE_VALS[i])) { + *value = false; + return true; + } + } + return false; +} + + +bool XMLUtil::ToFloat( const char* str, float* value ) +{ + if ( TIXML_SSCANF( str, "%f", value ) == 1 ) { + return true; + } + return false; +} + + +bool XMLUtil::ToDouble( const char* str, double* value ) +{ + if ( TIXML_SSCANF( str, "%lf", value ) == 1 ) { + return true; + } + return false; +} + + +bool XMLUtil::ToInt64(const char* str, int64_t* value) +{ + if (IsPrefixHex(str)) { + unsigned long long v = 0; // horrible syntax trick to make the compiler happy about %llx + if (TIXML_SSCANF(str, "%llx", &v) == 1) { + *value = static_cast(v); + return true; + } + } + else { + long long v = 0; // horrible syntax trick to make the compiler happy about %lld + if (TIXML_SSCANF(str, "%lld", &v) == 1) { + *value = static_cast(v); + return true; + } + } + return false; +} + + +bool XMLUtil::ToUnsigned64(const char* str, uint64_t* value) { + unsigned long long v = 0; // horrible syntax trick to make the compiler happy about %llu + if(TIXML_SSCANF(str, IsPrefixHex(str) ? "%llx" : "%llu", &v) == 1) { + *value = (uint64_t)v; + return true; + } + return false; +} + + +char* XMLDocument::Identify( char* p, XMLNode** node ) +{ + TIXMLASSERT( node ); + TIXMLASSERT( p ); + char* const start = p; + int const startLine = _parseCurLineNum; + p = XMLUtil::SkipWhiteSpace( p, &_parseCurLineNum ); + if( !*p ) { + *node = 0; + TIXMLASSERT( p ); + return p; + } + + // These strings define the matching patterns: + static const char* xmlHeader = { "( _commentPool ); + returnNode->_parseLineNum = _parseCurLineNum; + p += xmlHeaderLen; + } + else if ( XMLUtil::StringEqual( p, commentHeader, commentHeaderLen ) ) { + returnNode = CreateUnlinkedNode( _commentPool ); + returnNode->_parseLineNum = _parseCurLineNum; + p += commentHeaderLen; + } + else if ( XMLUtil::StringEqual( p, cdataHeader, cdataHeaderLen ) ) { + XMLText* text = CreateUnlinkedNode( _textPool ); + returnNode = text; + returnNode->_parseLineNum = _parseCurLineNum; + p += cdataHeaderLen; + text->SetCData( true ); + } + else if ( XMLUtil::StringEqual( p, dtdHeader, dtdHeaderLen ) ) { + returnNode = CreateUnlinkedNode( _commentPool ); + returnNode->_parseLineNum = _parseCurLineNum; + p += dtdHeaderLen; + } + else if ( XMLUtil::StringEqual( p, elementHeader, elementHeaderLen ) ) { + returnNode = CreateUnlinkedNode( _elementPool ); + returnNode->_parseLineNum = _parseCurLineNum; + p += elementHeaderLen; + } + else { + returnNode = CreateUnlinkedNode( _textPool ); + returnNode->_parseLineNum = _parseCurLineNum; // Report line of first non-whitespace character + p = start; // Back it up, all the text counts. + _parseCurLineNum = startLine; + } + + TIXMLASSERT( returnNode ); + TIXMLASSERT( p ); + *node = returnNode; + return p; +} + + +bool XMLDocument::Accept( XMLVisitor* visitor ) const +{ + TIXMLASSERT( visitor ); + if ( visitor->VisitEnter( *this ) ) { + for ( const XMLNode* node=FirstChild(); node; node=node->NextSibling() ) { + if ( !node->Accept( visitor ) ) { + break; + } + } + } + return visitor->VisitExit( *this ); +} + + +// --------- XMLNode ----------- // + +XMLNode::XMLNode( XMLDocument* doc ) : + _document( doc ), + _parent( 0 ), + _value(), + _parseLineNum( 0 ), + _firstChild( 0 ), _lastChild( 0 ), + _prev( 0 ), _next( 0 ), + _userData( 0 ), + _memPool( 0 ) +{ +} + + +XMLNode::~XMLNode() +{ + DeleteChildren(); + if ( _parent ) { + _parent->Unlink( this ); + } +} + +const char* XMLNode::Value() const +{ + // Edge case: XMLDocuments don't have a Value. Return null. + if ( this->ToDocument() ) + return 0; + return _value.GetStr(); +} + +void XMLNode::SetValue( const char* str, bool staticMem ) +{ + if ( staticMem ) { + _value.SetInternedStr( str ); + } + else { + _value.SetStr( str ); + } +} + +XMLNode* XMLNode::DeepClone(XMLDocument* target) const +{ + XMLNode* clone = this->ShallowClone(target); + if (!clone) return 0; + + for (const XMLNode* child = this->FirstChild(); child; child = child->NextSibling()) { + XMLNode* childClone = child->DeepClone(target); + TIXMLASSERT(childClone); + clone->InsertEndChild(childClone); + } + return clone; +} + +void XMLNode::DeleteChildren() +{ + while( _firstChild ) { + TIXMLASSERT( _lastChild ); + DeleteChild( _firstChild ); + } + _firstChild = _lastChild = 0; +} + + +void XMLNode::Unlink( XMLNode* child ) +{ + TIXMLASSERT( child ); + TIXMLASSERT( child->_document == _document ); + TIXMLASSERT( child->_parent == this ); + if ( child == _firstChild ) { + _firstChild = _firstChild->_next; + } + if ( child == _lastChild ) { + _lastChild = _lastChild->_prev; + } + + if ( child->_prev ) { + child->_prev->_next = child->_next; + } + if ( child->_next ) { + child->_next->_prev = child->_prev; + } + child->_next = 0; + child->_prev = 0; + child->_parent = 0; +} + + +void XMLNode::DeleteChild( XMLNode* node ) +{ + TIXMLASSERT( node ); + TIXMLASSERT( node->_document == _document ); + TIXMLASSERT( node->_parent == this ); + Unlink( node ); + TIXMLASSERT(node->_prev == 0); + TIXMLASSERT(node->_next == 0); + TIXMLASSERT(node->_parent == 0); + DeleteNode( node ); +} + + +XMLNode* XMLNode::InsertEndChild( XMLNode* addThis ) +{ + TIXMLASSERT( addThis ); + if ( addThis->_document != _document ) { + TIXMLASSERT( false ); + return 0; + } + InsertChildPreamble( addThis ); + + if ( _lastChild ) { + TIXMLASSERT( _firstChild ); + TIXMLASSERT( _lastChild->_next == 0 ); + _lastChild->_next = addThis; + addThis->_prev = _lastChild; + _lastChild = addThis; + + addThis->_next = 0; + } + else { + TIXMLASSERT( _firstChild == 0 ); + _firstChild = _lastChild = addThis; + + addThis->_prev = 0; + addThis->_next = 0; + } + addThis->_parent = this; + return addThis; +} + + +XMLNode* XMLNode::InsertFirstChild( XMLNode* addThis ) +{ + TIXMLASSERT( addThis ); + if ( addThis->_document != _document ) { + TIXMLASSERT( false ); + return 0; + } + InsertChildPreamble( addThis ); + + if ( _firstChild ) { + TIXMLASSERT( _lastChild ); + TIXMLASSERT( _firstChild->_prev == 0 ); + + _firstChild->_prev = addThis; + addThis->_next = _firstChild; + _firstChild = addThis; + + addThis->_prev = 0; + } + else { + TIXMLASSERT( _lastChild == 0 ); + _firstChild = _lastChild = addThis; + + addThis->_prev = 0; + addThis->_next = 0; + } + addThis->_parent = this; + return addThis; +} + + +XMLNode* XMLNode::InsertAfterChild( XMLNode* afterThis, XMLNode* addThis ) +{ + TIXMLASSERT( addThis ); + if ( addThis->_document != _document ) { + TIXMLASSERT( false ); + return 0; + } + + TIXMLASSERT( afterThis ); + + if ( afterThis->_parent != this ) { + TIXMLASSERT( false ); + return 0; + } + if ( afterThis == addThis ) { + // Current state: BeforeThis -> AddThis -> OneAfterAddThis + // Now AddThis must disappear from it's location and then + // reappear between BeforeThis and OneAfterAddThis. + // So just leave it where it is. + return addThis; + } + + if ( afterThis->_next == 0 ) { + // The last node or the only node. + return InsertEndChild( addThis ); + } + InsertChildPreamble( addThis ); + addThis->_prev = afterThis; + addThis->_next = afterThis->_next; + afterThis->_next->_prev = addThis; + afterThis->_next = addThis; + addThis->_parent = this; + return addThis; +} + + + + +const XMLElement* XMLNode::FirstChildElement( const char* name ) const +{ + for( const XMLNode* node = _firstChild; node; node = node->_next ) { + const XMLElement* element = node->ToElementWithName( name ); + if ( element ) { + return element; + } + } + return 0; +} + + +const XMLElement* XMLNode::LastChildElement( const char* name ) const +{ + for( const XMLNode* node = _lastChild; node; node = node->_prev ) { + const XMLElement* element = node->ToElementWithName( name ); + if ( element ) { + return element; + } + } + return 0; +} + + +const XMLElement* XMLNode::NextSiblingElement( const char* name ) const +{ + for( const XMLNode* node = _next; node; node = node->_next ) { + const XMLElement* element = node->ToElementWithName( name ); + if ( element ) { + return element; + } + } + return 0; +} + + +const XMLElement* XMLNode::PreviousSiblingElement( const char* name ) const +{ + for( const XMLNode* node = _prev; node; node = node->_prev ) { + const XMLElement* element = node->ToElementWithName( name ); + if ( element ) { + return element; + } + } + return 0; +} + + +char* XMLNode::ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr ) +{ + // This is a recursive method, but thinking about it "at the current level" + // it is a pretty simple flat list: + // + // + // + // With a special case: + // + // + // + // + // Where the closing element (/foo) *must* be the next thing after the opening + // element, and the names must match. BUT the tricky bit is that the closing + // element will be read by the child. + // + // 'endTag' is the end tag for this node, it is returned by a call to a child. + // 'parentEnd' is the end tag for the parent, which is filled in and returned. + + XMLDocument::DepthTracker tracker(_document); + if (_document->Error()) + return 0; + + while( p && *p ) { + XMLNode* node = 0; + + p = _document->Identify( p, &node ); + TIXMLASSERT( p ); + if ( node == 0 ) { + break; + } + + const int initialLineNum = node->_parseLineNum; + + StrPair endTag; + p = node->ParseDeep( p, &endTag, curLineNumPtr ); + if ( !p ) { + _document->DeleteNode( node ); + if ( !_document->Error() ) { + _document->SetError( XML_ERROR_PARSING, initialLineNum, 0); + } + break; + } + + const XMLDeclaration* const decl = node->ToDeclaration(); + if ( decl ) { + // Declarations are only allowed at document level + // + // Multiple declarations are allowed but all declarations + // must occur before anything else. + // + // Optimized due to a security test case. If the first node is + // a declaration, and the last node is a declaration, then only + // declarations have so far been added. + bool wellLocated = false; + + if (ToDocument()) { + if (FirstChild()) { + wellLocated = + FirstChild() && + FirstChild()->ToDeclaration() && + LastChild() && + LastChild()->ToDeclaration(); + } + else { + wellLocated = true; + } + } + if ( !wellLocated ) { + _document->SetError( XML_ERROR_PARSING_DECLARATION, initialLineNum, "XMLDeclaration value=%s", decl->Value()); + _document->DeleteNode( node ); + break; + } + } + + XMLElement* ele = node->ToElement(); + if ( ele ) { + // We read the end tag. Return it to the parent. + if ( ele->ClosingType() == XMLElement::CLOSING ) { + if ( parentEndTag ) { + ele->_value.TransferTo( parentEndTag ); + } + node->_memPool->SetTracked(); // created and then immediately deleted. + DeleteNode( node ); + return p; + } + + // Handle an end tag returned to this level. + // And handle a bunch of annoying errors. + bool mismatch = false; + if ( endTag.Empty() ) { + if ( ele->ClosingType() == XMLElement::OPEN ) { + mismatch = true; + } + } + else { + if ( ele->ClosingType() != XMLElement::OPEN ) { + mismatch = true; + } + else if ( !XMLUtil::StringEqual( endTag.GetStr(), ele->Name() ) ) { + mismatch = true; + } + } + if ( mismatch ) { + _document->SetError( XML_ERROR_MISMATCHED_ELEMENT, initialLineNum, "XMLElement name=%s", ele->Name()); + _document->DeleteNode( node ); + break; + } + } + InsertEndChild( node ); + } + return 0; +} + +/*static*/ void XMLNode::DeleteNode( XMLNode* node ) +{ + if ( node == 0 ) { + return; + } + TIXMLASSERT(node->_document); + if (!node->ToDocument()) { + node->_document->MarkInUse(node); + } + + MemPool* pool = node->_memPool; + node->~XMLNode(); + pool->Free( node ); +} + +void XMLNode::InsertChildPreamble( XMLNode* insertThis ) const +{ + TIXMLASSERT( insertThis ); + TIXMLASSERT( insertThis->_document == _document ); + + if (insertThis->_parent) { + insertThis->_parent->Unlink( insertThis ); + } + else { + insertThis->_document->MarkInUse(insertThis); + insertThis->_memPool->SetTracked(); + } +} + +const XMLElement* XMLNode::ToElementWithName( const char* name ) const +{ + const XMLElement* element = this->ToElement(); + if ( element == 0 ) { + return 0; + } + if ( name == 0 ) { + return element; + } + if ( XMLUtil::StringEqual( element->Name(), name ) ) { + return element; + } + return 0; +} + +// --------- XMLText ---------- // +char* XMLText::ParseDeep( char* p, StrPair*, int* curLineNumPtr ) +{ + if ( this->CData() ) { + p = _value.ParseText( p, "]]>", StrPair::NEEDS_NEWLINE_NORMALIZATION, curLineNumPtr ); + if ( !p ) { + _document->SetError( XML_ERROR_PARSING_CDATA, _parseLineNum, 0 ); + } + return p; + } + else { + int flags = _document->ProcessEntities() ? StrPair::TEXT_ELEMENT : StrPair::TEXT_ELEMENT_LEAVE_ENTITIES; + if ( _document->WhitespaceMode() == COLLAPSE_WHITESPACE ) { + flags |= StrPair::NEEDS_WHITESPACE_COLLAPSING; + } + + p = _value.ParseText( p, "<", flags, curLineNumPtr ); + if ( p && *p ) { + return p-1; + } + if ( !p ) { + _document->SetError( XML_ERROR_PARSING_TEXT, _parseLineNum, 0 ); + } + } + return 0; +} + + +XMLNode* XMLText::ShallowClone( XMLDocument* doc ) const +{ + if ( !doc ) { + doc = _document; + } + XMLText* text = doc->NewText( Value() ); // fixme: this will always allocate memory. Intern? + text->SetCData( this->CData() ); + return text; +} + + +bool XMLText::ShallowEqual( const XMLNode* compare ) const +{ + TIXMLASSERT( compare ); + const XMLText* text = compare->ToText(); + return ( text && XMLUtil::StringEqual( text->Value(), Value() ) ); +} + + +bool XMLText::Accept( XMLVisitor* visitor ) const +{ + TIXMLASSERT( visitor ); + return visitor->Visit( *this ); +} + + +// --------- XMLComment ---------- // + +XMLComment::XMLComment( XMLDocument* doc ) : XMLNode( doc ) +{ +} + + +XMLComment::~XMLComment() +{ +} + + +char* XMLComment::ParseDeep( char* p, StrPair*, int* curLineNumPtr ) +{ + // Comment parses as text. + p = _value.ParseText( p, "-->", StrPair::COMMENT, curLineNumPtr ); + if ( p == 0 ) { + _document->SetError( XML_ERROR_PARSING_COMMENT, _parseLineNum, 0 ); + } + return p; +} + + +XMLNode* XMLComment::ShallowClone( XMLDocument* doc ) const +{ + if ( !doc ) { + doc = _document; + } + XMLComment* comment = doc->NewComment( Value() ); // fixme: this will always allocate memory. Intern? + return comment; +} + + +bool XMLComment::ShallowEqual( const XMLNode* compare ) const +{ + TIXMLASSERT( compare ); + const XMLComment* comment = compare->ToComment(); + return ( comment && XMLUtil::StringEqual( comment->Value(), Value() )); +} + + +bool XMLComment::Accept( XMLVisitor* visitor ) const +{ + TIXMLASSERT( visitor ); + return visitor->Visit( *this ); +} + + +// --------- XMLDeclaration ---------- // + +XMLDeclaration::XMLDeclaration( XMLDocument* doc ) : XMLNode( doc ) +{ +} + + +XMLDeclaration::~XMLDeclaration() +{ + //printf( "~XMLDeclaration\n" ); +} + + +char* XMLDeclaration::ParseDeep( char* p, StrPair*, int* curLineNumPtr ) +{ + // Declaration parses as text. + p = _value.ParseText( p, "?>", StrPair::NEEDS_NEWLINE_NORMALIZATION, curLineNumPtr ); + if ( p == 0 ) { + _document->SetError( XML_ERROR_PARSING_DECLARATION, _parseLineNum, 0 ); + } + return p; +} + + +XMLNode* XMLDeclaration::ShallowClone( XMLDocument* doc ) const +{ + if ( !doc ) { + doc = _document; + } + XMLDeclaration* dec = doc->NewDeclaration( Value() ); // fixme: this will always allocate memory. Intern? + return dec; +} + + +bool XMLDeclaration::ShallowEqual( const XMLNode* compare ) const +{ + TIXMLASSERT( compare ); + const XMLDeclaration* declaration = compare->ToDeclaration(); + return ( declaration && XMLUtil::StringEqual( declaration->Value(), Value() )); +} + + + +bool XMLDeclaration::Accept( XMLVisitor* visitor ) const +{ + TIXMLASSERT( visitor ); + return visitor->Visit( *this ); +} + +// --------- XMLUnknown ---------- // + +XMLUnknown::XMLUnknown( XMLDocument* doc ) : XMLNode( doc ) +{ +} + + +XMLUnknown::~XMLUnknown() +{ +} + + +char* XMLUnknown::ParseDeep( char* p, StrPair*, int* curLineNumPtr ) +{ + // Unknown parses as text. + p = _value.ParseText( p, ">", StrPair::NEEDS_NEWLINE_NORMALIZATION, curLineNumPtr ); + if ( !p ) { + _document->SetError( XML_ERROR_PARSING_UNKNOWN, _parseLineNum, 0 ); + } + return p; +} + + +XMLNode* XMLUnknown::ShallowClone( XMLDocument* doc ) const +{ + if ( !doc ) { + doc = _document; + } + XMLUnknown* text = doc->NewUnknown( Value() ); // fixme: this will always allocate memory. Intern? + return text; +} + + +bool XMLUnknown::ShallowEqual( const XMLNode* compare ) const +{ + TIXMLASSERT( compare ); + const XMLUnknown* unknown = compare->ToUnknown(); + return ( unknown && XMLUtil::StringEqual( unknown->Value(), Value() )); +} + + +bool XMLUnknown::Accept( XMLVisitor* visitor ) const +{ + TIXMLASSERT( visitor ); + return visitor->Visit( *this ); +} + +// --------- XMLAttribute ---------- // + +const char* XMLAttribute::Name() const +{ + return _name.GetStr(); +} + +const char* XMLAttribute::Value() const +{ + return _value.GetStr(); +} + +char* XMLAttribute::ParseDeep( char* p, bool processEntities, int* curLineNumPtr ) +{ + // Parse using the name rules: bug fix, was using ParseText before + p = _name.ParseName( p ); + if ( !p || !*p ) { + return 0; + } + + // Skip white space before = + p = XMLUtil::SkipWhiteSpace( p, curLineNumPtr ); + if ( *p != '=' ) { + return 0; + } + + ++p; // move up to opening quote + p = XMLUtil::SkipWhiteSpace( p, curLineNumPtr ); + if ( *p != '\"' && *p != '\'' ) { + return 0; + } + + const char endTag[2] = { *p, 0 }; + ++p; // move past opening quote + + p = _value.ParseText( p, endTag, processEntities ? StrPair::ATTRIBUTE_VALUE : StrPair::ATTRIBUTE_VALUE_LEAVE_ENTITIES, curLineNumPtr ); + return p; +} + + +void XMLAttribute::SetName( const char* n ) +{ + _name.SetStr( n ); +} + + +XMLError XMLAttribute::QueryIntValue( int* value ) const +{ + if ( XMLUtil::ToInt( Value(), value )) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +XMLError XMLAttribute::QueryUnsignedValue( unsigned int* value ) const +{ + if ( XMLUtil::ToUnsigned( Value(), value )) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +XMLError XMLAttribute::QueryInt64Value(int64_t* value) const +{ + if (XMLUtil::ToInt64(Value(), value)) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +XMLError XMLAttribute::QueryUnsigned64Value(uint64_t* value) const +{ + if(XMLUtil::ToUnsigned64(Value(), value)) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +XMLError XMLAttribute::QueryBoolValue( bool* value ) const +{ + if ( XMLUtil::ToBool( Value(), value )) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +XMLError XMLAttribute::QueryFloatValue( float* value ) const +{ + if ( XMLUtil::ToFloat( Value(), value )) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +XMLError XMLAttribute::QueryDoubleValue( double* value ) const +{ + if ( XMLUtil::ToDouble( Value(), value )) { + return XML_SUCCESS; + } + return XML_WRONG_ATTRIBUTE_TYPE; +} + + +void XMLAttribute::SetAttribute( const char* v ) +{ + _value.SetStr( v ); +} + + +void XMLAttribute::SetAttribute( int v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + _value.SetStr( buf ); +} + + +void XMLAttribute::SetAttribute( unsigned v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + _value.SetStr( buf ); +} + + +void XMLAttribute::SetAttribute(int64_t v) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr(v, buf, BUF_SIZE); + _value.SetStr(buf); +} + +void XMLAttribute::SetAttribute(uint64_t v) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr(v, buf, BUF_SIZE); + _value.SetStr(buf); +} + + +void XMLAttribute::SetAttribute( bool v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + _value.SetStr( buf ); +} + +void XMLAttribute::SetAttribute( double v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + _value.SetStr( buf ); +} + +void XMLAttribute::SetAttribute( float v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + _value.SetStr( buf ); +} + + +// --------- XMLElement ---------- // +XMLElement::XMLElement( XMLDocument* doc ) : XMLNode( doc ), + _closingType( OPEN ), + _rootAttribute( 0 ) +{ +} + + +XMLElement::~XMLElement() +{ + while( _rootAttribute ) { + XMLAttribute* next = _rootAttribute->_next; + DeleteAttribute( _rootAttribute ); + _rootAttribute = next; + } +} + + +const XMLAttribute* XMLElement::FindAttribute( const char* name ) const +{ + for( XMLAttribute* a = _rootAttribute; a; a = a->_next ) { + if ( XMLUtil::StringEqual( a->Name(), name ) ) { + return a; + } + } + return 0; +} + + +const char* XMLElement::Attribute( const char* name, const char* value ) const +{ + const XMLAttribute* a = FindAttribute( name ); + if ( !a ) { + return 0; + } + if ( !value || XMLUtil::StringEqual( a->Value(), value )) { + return a->Value(); + } + return 0; +} + +int XMLElement::IntAttribute(const char* name, int defaultValue) const +{ + int i = defaultValue; + QueryIntAttribute(name, &i); + return i; +} + +unsigned XMLElement::UnsignedAttribute(const char* name, unsigned defaultValue) const +{ + unsigned i = defaultValue; + QueryUnsignedAttribute(name, &i); + return i; +} + +int64_t XMLElement::Int64Attribute(const char* name, int64_t defaultValue) const +{ + int64_t i = defaultValue; + QueryInt64Attribute(name, &i); + return i; +} + +uint64_t XMLElement::Unsigned64Attribute(const char* name, uint64_t defaultValue) const +{ + uint64_t i = defaultValue; + QueryUnsigned64Attribute(name, &i); + return i; +} + +bool XMLElement::BoolAttribute(const char* name, bool defaultValue) const +{ + bool b = defaultValue; + QueryBoolAttribute(name, &b); + return b; +} + +double XMLElement::DoubleAttribute(const char* name, double defaultValue) const +{ + double d = defaultValue; + QueryDoubleAttribute(name, &d); + return d; +} + +float XMLElement::FloatAttribute(const char* name, float defaultValue) const +{ + float f = defaultValue; + QueryFloatAttribute(name, &f); + return f; +} + +const char* XMLElement::GetText() const +{ + /* skip comment node */ + const XMLNode* node = FirstChild(); + while (node) { + if (node->ToComment()) { + node = node->NextSibling(); + continue; + } + break; + } + + if ( node && node->ToText() ) { + return node->Value(); + } + return 0; +} + + +void XMLElement::SetText( const char* inText ) +{ + if ( FirstChild() && FirstChild()->ToText() ) + FirstChild()->SetValue( inText ); + else { + XMLText* theText = GetDocument()->NewText( inText ); + InsertFirstChild( theText ); + } +} + + +void XMLElement::SetText( int v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + SetText( buf ); +} + + +void XMLElement::SetText( unsigned v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + SetText( buf ); +} + + +void XMLElement::SetText(int64_t v) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr(v, buf, BUF_SIZE); + SetText(buf); +} + +void XMLElement::SetText(uint64_t v) { + char buf[BUF_SIZE]; + XMLUtil::ToStr(v, buf, BUF_SIZE); + SetText(buf); +} + + +void XMLElement::SetText( bool v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + SetText( buf ); +} + + +void XMLElement::SetText( float v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + SetText( buf ); +} + + +void XMLElement::SetText( double v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + SetText( buf ); +} + + +XMLError XMLElement::QueryIntText( int* ival ) const +{ + if ( FirstChild() && FirstChild()->ToText() ) { + const char* t = FirstChild()->Value(); + if ( XMLUtil::ToInt( t, ival ) ) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + + +XMLError XMLElement::QueryUnsignedText( unsigned* uval ) const +{ + if ( FirstChild() && FirstChild()->ToText() ) { + const char* t = FirstChild()->Value(); + if ( XMLUtil::ToUnsigned( t, uval ) ) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + + +XMLError XMLElement::QueryInt64Text(int64_t* ival) const +{ + if (FirstChild() && FirstChild()->ToText()) { + const char* t = FirstChild()->Value(); + if (XMLUtil::ToInt64(t, ival)) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + + +XMLError XMLElement::QueryUnsigned64Text(uint64_t* uval) const +{ + if(FirstChild() && FirstChild()->ToText()) { + const char* t = FirstChild()->Value(); + if(XMLUtil::ToUnsigned64(t, uval)) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + + +XMLError XMLElement::QueryBoolText( bool* bval ) const +{ + if ( FirstChild() && FirstChild()->ToText() ) { + const char* t = FirstChild()->Value(); + if ( XMLUtil::ToBool( t, bval ) ) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + + +XMLError XMLElement::QueryDoubleText( double* dval ) const +{ + if ( FirstChild() && FirstChild()->ToText() ) { + const char* t = FirstChild()->Value(); + if ( XMLUtil::ToDouble( t, dval ) ) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + + +XMLError XMLElement::QueryFloatText( float* fval ) const +{ + if ( FirstChild() && FirstChild()->ToText() ) { + const char* t = FirstChild()->Value(); + if ( XMLUtil::ToFloat( t, fval ) ) { + return XML_SUCCESS; + } + return XML_CAN_NOT_CONVERT_TEXT; + } + return XML_NO_TEXT_NODE; +} + +int XMLElement::IntText(int defaultValue) const +{ + int i = defaultValue; + QueryIntText(&i); + return i; +} + +unsigned XMLElement::UnsignedText(unsigned defaultValue) const +{ + unsigned i = defaultValue; + QueryUnsignedText(&i); + return i; +} + +int64_t XMLElement::Int64Text(int64_t defaultValue) const +{ + int64_t i = defaultValue; + QueryInt64Text(&i); + return i; +} + +uint64_t XMLElement::Unsigned64Text(uint64_t defaultValue) const +{ + uint64_t i = defaultValue; + QueryUnsigned64Text(&i); + return i; +} + +bool XMLElement::BoolText(bool defaultValue) const +{ + bool b = defaultValue; + QueryBoolText(&b); + return b; +} + +double XMLElement::DoubleText(double defaultValue) const +{ + double d = defaultValue; + QueryDoubleText(&d); + return d; +} + +float XMLElement::FloatText(float defaultValue) const +{ + float f = defaultValue; + QueryFloatText(&f); + return f; +} + + +XMLAttribute* XMLElement::FindOrCreateAttribute( const char* name ) +{ + XMLAttribute* last = 0; + XMLAttribute* attrib = 0; + for( attrib = _rootAttribute; + attrib; + last = attrib, attrib = attrib->_next ) { + if ( XMLUtil::StringEqual( attrib->Name(), name ) ) { + break; + } + } + if ( !attrib ) { + attrib = CreateAttribute(); + TIXMLASSERT( attrib ); + if ( last ) { + TIXMLASSERT( last->_next == 0 ); + last->_next = attrib; + } + else { + TIXMLASSERT( _rootAttribute == 0 ); + _rootAttribute = attrib; + } + attrib->SetName( name ); + } + return attrib; +} + + +void XMLElement::DeleteAttribute( const char* name ) +{ + XMLAttribute* prev = 0; + for( XMLAttribute* a=_rootAttribute; a; a=a->_next ) { + if ( XMLUtil::StringEqual( name, a->Name() ) ) { + if ( prev ) { + prev->_next = a->_next; + } + else { + _rootAttribute = a->_next; + } + DeleteAttribute( a ); + break; + } + prev = a; + } +} + + +char* XMLElement::ParseAttributes( char* p, int* curLineNumPtr ) +{ + XMLAttribute* prevAttribute = 0; + + // Read the attributes. + while( p ) { + p = XMLUtil::SkipWhiteSpace( p, curLineNumPtr ); + if ( !(*p) ) { + _document->SetError( XML_ERROR_PARSING_ELEMENT, _parseLineNum, "XMLElement name=%s", Name() ); + return 0; + } + + // attribute. + if (XMLUtil::IsNameStartChar( (unsigned char) *p ) ) { + XMLAttribute* attrib = CreateAttribute(); + TIXMLASSERT( attrib ); + attrib->_parseLineNum = _document->_parseCurLineNum; + + const int attrLineNum = attrib->_parseLineNum; + + p = attrib->ParseDeep( p, _document->ProcessEntities(), curLineNumPtr ); + if ( !p || Attribute( attrib->Name() ) ) { + DeleteAttribute( attrib ); + _document->SetError( XML_ERROR_PARSING_ATTRIBUTE, attrLineNum, "XMLElement name=%s", Name() ); + return 0; + } + // There is a minor bug here: if the attribute in the source xml + // document is duplicated, it will not be detected and the + // attribute will be doubly added. However, tracking the 'prevAttribute' + // avoids re-scanning the attribute list. Preferring performance for + // now, may reconsider in the future. + if ( prevAttribute ) { + TIXMLASSERT( prevAttribute->_next == 0 ); + prevAttribute->_next = attrib; + } + else { + TIXMLASSERT( _rootAttribute == 0 ); + _rootAttribute = attrib; + } + prevAttribute = attrib; + } + // end of the tag + else if ( *p == '>' ) { + ++p; + break; + } + // end of the tag + else if ( *p == '/' && *(p+1) == '>' ) { + _closingType = CLOSED; + return p+2; // done; sealed element. + } + else { + _document->SetError( XML_ERROR_PARSING_ELEMENT, _parseLineNum, 0 ); + return 0; + } + } + return p; +} + +void XMLElement::DeleteAttribute( XMLAttribute* attribute ) +{ + if ( attribute == 0 ) { + return; + } + MemPool* pool = attribute->_memPool; + attribute->~XMLAttribute(); + pool->Free( attribute ); +} + +XMLAttribute* XMLElement::CreateAttribute() +{ + TIXMLASSERT( sizeof( XMLAttribute ) == _document->_attributePool.ItemSize() ); + XMLAttribute* attrib = new (_document->_attributePool.Alloc() ) XMLAttribute(); + TIXMLASSERT( attrib ); + attrib->_memPool = &_document->_attributePool; + attrib->_memPool->SetTracked(); + return attrib; +} + + +XMLElement* XMLElement::InsertNewChildElement(const char* name) +{ + XMLElement* node = _document->NewElement(name); + return InsertEndChild(node) ? node : 0; +} + +XMLComment* XMLElement::InsertNewComment(const char* comment) +{ + XMLComment* node = _document->NewComment(comment); + return InsertEndChild(node) ? node : 0; +} + +XMLText* XMLElement::InsertNewText(const char* text) +{ + XMLText* node = _document->NewText(text); + return InsertEndChild(node) ? node : 0; +} + +XMLDeclaration* XMLElement::InsertNewDeclaration(const char* text) +{ + XMLDeclaration* node = _document->NewDeclaration(text); + return InsertEndChild(node) ? node : 0; +} + +XMLUnknown* XMLElement::InsertNewUnknown(const char* text) +{ + XMLUnknown* node = _document->NewUnknown(text); + return InsertEndChild(node) ? node : 0; +} + + + +// +// +// foobar +// +char* XMLElement::ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr ) +{ + // Read the element name. + p = XMLUtil::SkipWhiteSpace( p, curLineNumPtr ); + + // The closing element is the form. It is + // parsed just like a regular element then deleted from + // the DOM. + if ( *p == '/' ) { + _closingType = CLOSING; + ++p; + } + + p = _value.ParseName( p ); + if ( _value.Empty() ) { + return 0; + } + + p = ParseAttributes( p, curLineNumPtr ); + if ( !p || !*p || _closingType != OPEN ) { + return p; + } + + p = XMLNode::ParseDeep( p, parentEndTag, curLineNumPtr ); + return p; +} + + + +XMLNode* XMLElement::ShallowClone( XMLDocument* doc ) const +{ + if ( !doc ) { + doc = _document; + } + XMLElement* element = doc->NewElement( Value() ); // fixme: this will always allocate memory. Intern? + for( const XMLAttribute* a=FirstAttribute(); a; a=a->Next() ) { + element->SetAttribute( a->Name(), a->Value() ); // fixme: this will always allocate memory. Intern? + } + return element; +} + + +bool XMLElement::ShallowEqual( const XMLNode* compare ) const +{ + TIXMLASSERT( compare ); + const XMLElement* other = compare->ToElement(); + if ( other && XMLUtil::StringEqual( other->Name(), Name() )) { + + const XMLAttribute* a=FirstAttribute(); + const XMLAttribute* b=other->FirstAttribute(); + + while ( a && b ) { + if ( !XMLUtil::StringEqual( a->Value(), b->Value() ) ) { + return false; + } + a = a->Next(); + b = b->Next(); + } + if ( a || b ) { + // different count + return false; + } + return true; + } + return false; +} + + +bool XMLElement::Accept( XMLVisitor* visitor ) const +{ + TIXMLASSERT( visitor ); + if ( visitor->VisitEnter( *this, _rootAttribute ) ) { + for ( const XMLNode* node=FirstChild(); node; node=node->NextSibling() ) { + if ( !node->Accept( visitor ) ) { + break; + } + } + } + return visitor->VisitExit( *this ); +} + + +// --------- XMLDocument ----------- // + +// Warning: List must match 'enum XMLError' +const char* XMLDocument::_errorNames[XML_ERROR_COUNT] = { + "XML_SUCCESS", + "XML_NO_ATTRIBUTE", + "XML_WRONG_ATTRIBUTE_TYPE", + "XML_ERROR_FILE_NOT_FOUND", + "XML_ERROR_FILE_COULD_NOT_BE_OPENED", + "XML_ERROR_FILE_READ_ERROR", + "XML_ERROR_PARSING_ELEMENT", + "XML_ERROR_PARSING_ATTRIBUTE", + "XML_ERROR_PARSING_TEXT", + "XML_ERROR_PARSING_CDATA", + "XML_ERROR_PARSING_COMMENT", + "XML_ERROR_PARSING_DECLARATION", + "XML_ERROR_PARSING_UNKNOWN", + "XML_ERROR_EMPTY_DOCUMENT", + "XML_ERROR_MISMATCHED_ELEMENT", + "XML_ERROR_PARSING", + "XML_CAN_NOT_CONVERT_TEXT", + "XML_NO_TEXT_NODE", + "XML_ELEMENT_DEPTH_EXCEEDED" +}; + + +XMLDocument::XMLDocument( bool processEntities, Whitespace whitespaceMode ) : + XMLNode( 0 ), + _writeBOM( false ), + _processEntities( processEntities ), + _errorID(XML_SUCCESS), + _whitespaceMode( whitespaceMode ), + _errorStr(), + _errorLineNum( 0 ), + _charBuffer( 0 ), + _parseCurLineNum( 0 ), + _parsingDepth(0), + _unlinked(), + _elementPool(), + _attributePool(), + _textPool(), + _commentPool() +{ + // avoid VC++ C4355 warning about 'this' in initializer list (C4355 is off by default in VS2012+) + _document = this; +} + + +XMLDocument::~XMLDocument() +{ + Clear(); +} + + +void XMLDocument::MarkInUse(const XMLNode* const node) +{ + TIXMLASSERT(node); + TIXMLASSERT(node->_parent == 0); + + for (int i = 0; i < _unlinked.Size(); ++i) { + if (node == _unlinked[i]) { + _unlinked.SwapRemove(i); + break; + } + } +} + +void XMLDocument::Clear() +{ + DeleteChildren(); + while( _unlinked.Size()) { + DeleteNode(_unlinked[0]); // Will remove from _unlinked as part of delete. + } + +#ifdef TINYXML2_DEBUG + const bool hadError = Error(); +#endif + ClearError(); + + delete [] _charBuffer; + _charBuffer = 0; + _parsingDepth = 0; + +#if 0 + _textPool.Trace( "text" ); + _elementPool.Trace( "element" ); + _commentPool.Trace( "comment" ); + _attributePool.Trace( "attribute" ); +#endif + +#ifdef TINYXML2_DEBUG + if ( !hadError ) { + TIXMLASSERT( _elementPool.CurrentAllocs() == _elementPool.Untracked() ); + TIXMLASSERT( _attributePool.CurrentAllocs() == _attributePool.Untracked() ); + TIXMLASSERT( _textPool.CurrentAllocs() == _textPool.Untracked() ); + TIXMLASSERT( _commentPool.CurrentAllocs() == _commentPool.Untracked() ); + } +#endif +} + + +void XMLDocument::DeepCopy(XMLDocument* target) const +{ + TIXMLASSERT(target); + if (target == this) { + return; // technically success - a no-op. + } + + target->Clear(); + for (const XMLNode* node = this->FirstChild(); node; node = node->NextSibling()) { + target->InsertEndChild(node->DeepClone(target)); + } +} + +XMLElement* XMLDocument::NewElement( const char* name ) +{ + XMLElement* ele = CreateUnlinkedNode( _elementPool ); + ele->SetName( name ); + return ele; +} + + +XMLComment* XMLDocument::NewComment( const char* str ) +{ + XMLComment* comment = CreateUnlinkedNode( _commentPool ); + comment->SetValue( str ); + return comment; +} + + +XMLText* XMLDocument::NewText( const char* str ) +{ + XMLText* text = CreateUnlinkedNode( _textPool ); + text->SetValue( str ); + return text; +} + + +XMLDeclaration* XMLDocument::NewDeclaration( const char* str ) +{ + XMLDeclaration* dec = CreateUnlinkedNode( _commentPool ); + dec->SetValue( str ? str : "xml version=\"1.0\" encoding=\"UTF-8\"" ); + return dec; +} + + +XMLUnknown* XMLDocument::NewUnknown( const char* str ) +{ + XMLUnknown* unk = CreateUnlinkedNode( _commentPool ); + unk->SetValue( str ); + return unk; +} + +static FILE* callfopen( const char* filepath, const char* mode ) +{ + TIXMLASSERT( filepath ); + TIXMLASSERT( mode ); +#if defined(_MSC_VER) && (_MSC_VER >= 1400 ) && (!defined WINCE) + FILE* fp = 0; + const errno_t err = fopen_s( &fp, filepath, mode ); + if ( err ) { + return 0; + } +#else + FILE* fp = fopen( filepath, mode ); +#endif + return fp; +} + +void XMLDocument::DeleteNode( XMLNode* node ) { + TIXMLASSERT( node ); + TIXMLASSERT(node->_document == this ); + if (node->_parent) { + node->_parent->DeleteChild( node ); + } + else { + // Isn't in the tree. + // Use the parent delete. + // Also, we need to mark it tracked: we 'know' + // it was never used. + node->_memPool->SetTracked(); + // Call the static XMLNode version: + XMLNode::DeleteNode(node); + } +} + + +XMLError XMLDocument::LoadFile( const char* filename ) +{ + if ( !filename ) { + TIXMLASSERT( false ); + SetError( XML_ERROR_FILE_COULD_NOT_BE_OPENED, 0, "filename=" ); + return _errorID; + } + + Clear(); + FILE* fp = callfopen( filename, "rb" ); + if ( !fp ) { + SetError( XML_ERROR_FILE_NOT_FOUND, 0, "filename=%s", filename ); + return _errorID; + } + LoadFile( fp ); + fclose( fp ); + return _errorID; +} + +XMLError XMLDocument::LoadFile( FILE* fp ) +{ + Clear(); + + TIXML_FSEEK( fp, 0, SEEK_SET ); + if ( fgetc( fp ) == EOF && ferror( fp ) != 0 ) { + SetError( XML_ERROR_FILE_READ_ERROR, 0, 0 ); + return _errorID; + } + + TIXML_FSEEK( fp, 0, SEEK_END ); + + unsigned long long filelength; + { + const long long fileLengthSigned = TIXML_FTELL( fp ); + TIXML_FSEEK( fp, 0, SEEK_SET ); + if ( fileLengthSigned == -1L ) { + SetError( XML_ERROR_FILE_READ_ERROR, 0, 0 ); + return _errorID; + } + TIXMLASSERT( fileLengthSigned >= 0 ); + filelength = static_cast(fileLengthSigned); + } + + const size_t maxSizeT = static_cast(-1); + // We'll do the comparison as an unsigned long long, because that's guaranteed to be at + // least 8 bytes, even on a 32-bit platform. + if ( filelength >= static_cast(maxSizeT) ) { + // Cannot handle files which won't fit in buffer together with null terminator + SetError( XML_ERROR_FILE_READ_ERROR, 0, 0 ); + return _errorID; + } + + if ( filelength == 0 ) { + SetError( XML_ERROR_EMPTY_DOCUMENT, 0, 0 ); + return _errorID; + } + + const size_t size = static_cast(filelength); + TIXMLASSERT( _charBuffer == 0 ); + _charBuffer = new char[size+1]; + const size_t read = fread( _charBuffer, 1, size, fp ); + if ( read != size ) { + SetError( XML_ERROR_FILE_READ_ERROR, 0, 0 ); + return _errorID; + } + + _charBuffer[size] = 0; + + Parse(); + return _errorID; +} + + +XMLError XMLDocument::SaveFile( const char* filename, bool compact ) +{ + if ( !filename ) { + TIXMLASSERT( false ); + SetError( XML_ERROR_FILE_COULD_NOT_BE_OPENED, 0, "filename=" ); + return _errorID; + } + + FILE* fp = callfopen( filename, "w" ); + if ( !fp ) { + SetError( XML_ERROR_FILE_COULD_NOT_BE_OPENED, 0, "filename=%s", filename ); + return _errorID; + } + SaveFile(fp, compact); + fclose( fp ); + return _errorID; +} + + +XMLError XMLDocument::SaveFile( FILE* fp, bool compact ) +{ + // Clear any error from the last save, otherwise it will get reported + // for *this* call. + ClearError(); + XMLPrinter stream( fp, compact ); + Print( &stream ); + return _errorID; +} + + +XMLError XMLDocument::Parse( const char* xml, size_t nBytes ) +{ + Clear(); + + if ( nBytes == 0 || !xml || !*xml ) { + SetError( XML_ERROR_EMPTY_DOCUMENT, 0, 0 ); + return _errorID; + } + if ( nBytes == static_cast(-1) ) { + nBytes = strlen( xml ); + } + TIXMLASSERT( _charBuffer == 0 ); + _charBuffer = new char[ nBytes+1 ]; + memcpy( _charBuffer, xml, nBytes ); + _charBuffer[nBytes] = 0; + + Parse(); + if ( Error() ) { + // clean up now essentially dangling memory. + // and the parse fail can put objects in the + // pools that are dead and inaccessible. + DeleteChildren(); + _elementPool.Clear(); + _attributePool.Clear(); + _textPool.Clear(); + _commentPool.Clear(); + } + return _errorID; +} + + +void XMLDocument::Print( XMLPrinter* streamer ) const +{ + if ( streamer ) { + Accept( streamer ); + } + else { + XMLPrinter stdoutStreamer( stdout ); + Accept( &stdoutStreamer ); + } +} + + +void XMLDocument::ClearError() { + _errorID = XML_SUCCESS; + _errorLineNum = 0; + _errorStr.Reset(); +} + + +void XMLDocument::SetError( XMLError error, int lineNum, const char* format, ... ) +{ + TIXMLASSERT( error >= 0 && error < XML_ERROR_COUNT ); + _errorID = error; + _errorLineNum = lineNum; + _errorStr.Reset(); + + const size_t BUFFER_SIZE = 1000; + char* buffer = new char[BUFFER_SIZE]; + + TIXMLASSERT(sizeof(error) <= sizeof(int)); + TIXML_SNPRINTF(buffer, BUFFER_SIZE, "Error=%s ErrorID=%d (0x%x) Line number=%d", ErrorIDToName(error), int(error), int(error), lineNum); + + if (format) { + size_t len = strlen(buffer); + TIXML_SNPRINTF(buffer + len, BUFFER_SIZE - len, ": "); + len = strlen(buffer); + + va_list va; + va_start(va, format); + TIXML_VSNPRINTF(buffer + len, BUFFER_SIZE - len, format, va); + va_end(va); + } + _errorStr.SetStr(buffer); + delete[] buffer; +} + + +/*static*/ const char* XMLDocument::ErrorIDToName(XMLError errorID) +{ + TIXMLASSERT( errorID >= 0 && errorID < XML_ERROR_COUNT ); + const char* errorName = _errorNames[errorID]; + TIXMLASSERT( errorName && errorName[0] ); + return errorName; +} + +const char* XMLDocument::ErrorStr() const +{ + return _errorStr.Empty() ? "" : _errorStr.GetStr(); +} + + +void XMLDocument::PrintError() const +{ + printf("%s\n", ErrorStr()); +} + +const char* XMLDocument::ErrorName() const +{ + return ErrorIDToName(_errorID); +} + +void XMLDocument::Parse() +{ + TIXMLASSERT( NoChildren() ); // Clear() must have been called previously + TIXMLASSERT( _charBuffer ); + _parseCurLineNum = 1; + _parseLineNum = 1; + char* p = _charBuffer; + p = XMLUtil::SkipWhiteSpace( p, &_parseCurLineNum ); + p = const_cast( XMLUtil::ReadBOM( p, &_writeBOM ) ); + if ( !*p ) { + SetError( XML_ERROR_EMPTY_DOCUMENT, 0, 0 ); + return; + } + ParseDeep(p, 0, &_parseCurLineNum ); +} + +void XMLDocument::PushDepth() +{ + _parsingDepth++; + if (_parsingDepth == TINYXML2_MAX_ELEMENT_DEPTH) { + SetError(XML_ELEMENT_DEPTH_EXCEEDED, _parseCurLineNum, "Element nesting is too deep." ); + } +} + +void XMLDocument::PopDepth() +{ + TIXMLASSERT(_parsingDepth > 0); + --_parsingDepth; +} + +XMLPrinter::XMLPrinter( FILE* file, bool compact, int depth ) : + _elementJustOpened( false ), + _stack(), + _firstElement( true ), + _fp( file ), + _depth( depth ), + _textDepth( -1 ), + _processEntities( true ), + _compactMode( compact ), + _buffer() +{ + for( int i=0; i(entityValue); + TIXMLASSERT( flagIndex < ENTITY_RANGE ); + _entityFlag[flagIndex] = true; + } + _restrictedEntityFlag[static_cast('&')] = true; + _restrictedEntityFlag[static_cast('<')] = true; + _restrictedEntityFlag[static_cast('>')] = true; // not required, but consistency is nice + _buffer.Push( 0 ); +} + + +void XMLPrinter::Print( const char* format, ... ) +{ + va_list va; + va_start( va, format ); + + if ( _fp ) { + vfprintf( _fp, format, va ); + } + else { + const int len = TIXML_VSCPRINTF( format, va ); + // Close out and re-start the va-args + va_end( va ); + TIXMLASSERT( len >= 0 ); + va_start( va, format ); + TIXMLASSERT( _buffer.Size() > 0 && _buffer[_buffer.Size() - 1] == 0 ); + char* p = _buffer.PushArr( len ) - 1; // back up over the null terminator. + TIXML_VSNPRINTF( p, len+1, format, va ); + } + va_end( va ); +} + + +void XMLPrinter::Write( const char* data, size_t size ) +{ + if ( _fp ) { + fwrite ( data , sizeof(char), size, _fp); + } + else { + char* p = _buffer.PushArr( static_cast(size) ) - 1; // back up over the null terminator. + memcpy( p, data, size ); + p[size] = 0; + } +} + + +void XMLPrinter::Putc( char ch ) +{ + if ( _fp ) { + fputc ( ch, _fp); + } + else { + char* p = _buffer.PushArr( sizeof(char) ) - 1; // back up over the null terminator. + p[0] = ch; + p[1] = 0; + } +} + + +void XMLPrinter::PrintSpace( int depth ) +{ + for( int i=0; i 0 && *q < ENTITY_RANGE ) { + // Check for entities. If one is found, flush + // the stream up until the entity, write the + // entity, and keep looking. + if ( flag[static_cast(*q)] ) { + while ( p < q ) { + const size_t delta = q - p; + const int toPrint = ( INT_MAX < delta ) ? INT_MAX : static_cast(delta); + Write( p, toPrint ); + p += toPrint; + } + bool entityPatternPrinted = false; + for( int i=0; i(delta); + Write( p, toPrint ); + } + } + else { + Write( p ); + } +} + + +void XMLPrinter::PushHeader( bool writeBOM, bool writeDec ) +{ + if ( writeBOM ) { + static const unsigned char bom[] = { TIXML_UTF_LEAD_0, TIXML_UTF_LEAD_1, TIXML_UTF_LEAD_2, 0 }; + Write( reinterpret_cast< const char* >( bom ) ); + } + if ( writeDec ) { + PushDeclaration( "xml version=\"1.0\"" ); + } +} + +void XMLPrinter::PrepareForNewNode( bool compactMode ) +{ + SealElementIfJustOpened(); + + if ( compactMode ) { + return; + } + + if ( _firstElement ) { + PrintSpace (_depth); + } else if ( _textDepth < 0) { + Putc( '\n' ); + PrintSpace( _depth ); + } + + _firstElement = false; +} + +void XMLPrinter::OpenElement( const char* name, bool compactMode ) +{ + PrepareForNewNode( compactMode ); + _stack.Push( name ); + + Write ( "<" ); + Write ( name ); + + _elementJustOpened = true; + ++_depth; +} + + +void XMLPrinter::PushAttribute( const char* name, const char* value ) +{ + TIXMLASSERT( _elementJustOpened ); + Putc ( ' ' ); + Write( name ); + Write( "=\"" ); + PrintString( value, false ); + Putc ( '\"' ); +} + + +void XMLPrinter::PushAttribute( const char* name, int v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + PushAttribute( name, buf ); +} + + +void XMLPrinter::PushAttribute( const char* name, unsigned v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + PushAttribute( name, buf ); +} + + +void XMLPrinter::PushAttribute(const char* name, int64_t v) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr(v, buf, BUF_SIZE); + PushAttribute(name, buf); +} + + +void XMLPrinter::PushAttribute(const char* name, uint64_t v) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr(v, buf, BUF_SIZE); + PushAttribute(name, buf); +} + + +void XMLPrinter::PushAttribute( const char* name, bool v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + PushAttribute( name, buf ); +} + + +void XMLPrinter::PushAttribute( const char* name, double v ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( v, buf, BUF_SIZE ); + PushAttribute( name, buf ); +} + + +void XMLPrinter::CloseElement( bool compactMode ) +{ + --_depth; + const char* name = _stack.Pop(); + + if ( _elementJustOpened ) { + Write( "/>" ); + } + else { + if ( _textDepth < 0 && !compactMode) { + Putc( '\n' ); + PrintSpace( _depth ); + } + Write ( "" ); + } + + if ( _textDepth == _depth ) { + _textDepth = -1; + } + if ( _depth == 0 && !compactMode) { + Putc( '\n' ); + } + _elementJustOpened = false; +} + + +void XMLPrinter::SealElementIfJustOpened() +{ + if ( !_elementJustOpened ) { + return; + } + _elementJustOpened = false; + Putc( '>' ); +} + + +void XMLPrinter::PushText( const char* text, bool cdata ) +{ + _textDepth = _depth-1; + + SealElementIfJustOpened(); + if ( cdata ) { + Write( "" ); + } + else { + PrintString( text, true ); + } +} + + +void XMLPrinter::PushText( int64_t value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( value, buf, BUF_SIZE ); + PushText( buf, false ); +} + + +void XMLPrinter::PushText( uint64_t value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr(value, buf, BUF_SIZE); + PushText(buf, false); +} + + +void XMLPrinter::PushText( int value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( value, buf, BUF_SIZE ); + PushText( buf, false ); +} + + +void XMLPrinter::PushText( unsigned value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( value, buf, BUF_SIZE ); + PushText( buf, false ); +} + + +void XMLPrinter::PushText( bool value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( value, buf, BUF_SIZE ); + PushText( buf, false ); +} + + +void XMLPrinter::PushText( float value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( value, buf, BUF_SIZE ); + PushText( buf, false ); +} + + +void XMLPrinter::PushText( double value ) +{ + char buf[BUF_SIZE]; + XMLUtil::ToStr( value, buf, BUF_SIZE ); + PushText( buf, false ); +} + + +void XMLPrinter::PushComment( const char* comment ) +{ + PrepareForNewNode( _compactMode ); + + Write( "" ); +} + + +void XMLPrinter::PushDeclaration( const char* value ) +{ + PrepareForNewNode( _compactMode ); + + Write( "" ); +} + + +void XMLPrinter::PushUnknown( const char* value ) +{ + PrepareForNewNode( _compactMode ); + + Write( "' ); +} + + +bool XMLPrinter::VisitEnter( const XMLDocument& doc ) +{ + _processEntities = doc.ProcessEntities(); + if ( doc.HasBOM() ) { + PushHeader( true, false ); + } + return true; +} + + +bool XMLPrinter::VisitEnter( const XMLElement& element, const XMLAttribute* attribute ) +{ + const XMLElement* parentElem = 0; + if ( element.Parent() ) { + parentElem = element.Parent()->ToElement(); + } + const bool compactMode = parentElem ? CompactMode( *parentElem ) : _compactMode; + OpenElement( element.Name(), compactMode ); + while ( attribute ) { + PushAttribute( attribute->Name(), attribute->Value() ); + attribute = attribute->Next(); + } + return true; +} + + +bool XMLPrinter::VisitExit( const XMLElement& element ) +{ + CloseElement( CompactMode(element) ); + return true; +} + + +bool XMLPrinter::Visit( const XMLText& text ) +{ + PushText( text.Value(), text.CData() ); + return true; +} + + +bool XMLPrinter::Visit( const XMLComment& comment ) +{ + PushComment( comment.Value() ); + return true; +} + +bool XMLPrinter::Visit( const XMLDeclaration& declaration ) +{ + PushDeclaration( declaration.Value() ); + return true; +} + + +bool XMLPrinter::Visit( const XMLUnknown& unknown ) +{ + PushUnknown( unknown.Value() ); + return true; +} + +} // namespace tinyxml2 \ No newline at end of file diff --git a/src/tinyxml2.h b/src/tinyxml2.h new file mode 100644 index 0000000..dcec8e7 --- /dev/null +++ b/src/tinyxml2.h @@ -0,0 +1,2380 @@ +/* +Original code by Lee Thomason (www.grinninglizard.com) + +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. +*/ + +#ifndef TINYXML2_INCLUDED +#define TINYXML2_INCLUDED + +#if defined(ANDROID_NDK) || defined(__BORLANDC__) || defined(__QNXNTO__) +# include +# include +# include +# include +# include +# if defined(__PS3__) +# include +# endif +#else +# include +# include +# include +# include +# include +#endif +#include + +/* + TODO: intern strings instead of allocation. +*/ +/* + gcc: + g++ -Wall -DTINYXML2_DEBUG tinyxml2.cpp xmltest.cpp -o gccxmltest.exe + + Formatting, Artistic Style: + AStyle.exe --style=1tbs --indent-switches --break-closing-brackets --indent-preprocessor tinyxml2.cpp tinyxml2.h +*/ + +#if defined( _DEBUG ) || defined (__DEBUG__) +# ifndef TINYXML2_DEBUG +# define TINYXML2_DEBUG +# endif +#endif + +#ifdef _MSC_VER +# pragma warning(push) +# pragma warning(disable: 4251) +#endif + +#ifdef _WIN32 +# ifdef TINYXML2_EXPORT +# define TINYXML2_LIB __declspec(dllexport) +# elif defined(TINYXML2_IMPORT) +# define TINYXML2_LIB __declspec(dllimport) +# else +# define TINYXML2_LIB +# endif +#elif __GNUC__ >= 4 +# define TINYXML2_LIB __attribute__((visibility("default"))) +#else +# define TINYXML2_LIB +#endif + + +#if !defined(TIXMLASSERT) +#if defined(TINYXML2_DEBUG) +# if defined(_MSC_VER) +# // "(void)0," is for suppressing C4127 warning in "assert(false)", "assert(true)" and the like +# define TIXMLASSERT( x ) do { if ( !((void)0,(x))) { __debugbreak(); } } while(false) +# elif defined (ANDROID_NDK) +# include +# define TIXMLASSERT( x ) do { if ( !(x)) { __android_log_assert( "assert", "grinliz", "ASSERT in '%s' at %d.", __FILE__, __LINE__ ); } } while(false) +# else +# include +# define TIXMLASSERT assert +# endif +#else +# define TIXMLASSERT( x ) do {} while(false) +#endif +#endif + +/* Versioning, past 1.0.14: + http://semver.org/ +*/ +static const int TIXML2_MAJOR_VERSION = 9; +static const int TIXML2_MINOR_VERSION = 0; +static const int TIXML2_PATCH_VERSION = 0; + +#define TINYXML2_MAJOR_VERSION 9 +#define TINYXML2_MINOR_VERSION 0 +#define TINYXML2_PATCH_VERSION 0 + +// A fixed element depth limit is problematic. There needs to be a +// limit to avoid a stack overflow. However, that limit varies per +// system, and the capacity of the stack. On the other hand, it's a trivial +// attack that can result from ill, malicious, or even correctly formed XML, +// so there needs to be a limit in place. +static const int TINYXML2_MAX_ELEMENT_DEPTH = 500; + +namespace tinyxml2 +{ +class XMLDocument; +class XMLElement; +class XMLAttribute; +class XMLComment; +class XMLText; +class XMLDeclaration; +class XMLUnknown; +class XMLPrinter; + +/* + A class that wraps strings. Normally stores the start and end + pointers into the XML file itself, and will apply normalization + and entity translation if actually read. Can also store (and memory + manage) a traditional char[] + + Isn't clear why TINYXML2_LIB is needed; but seems to fix #719 +*/ +class TINYXML2_LIB StrPair +{ +public: + enum Mode { + NEEDS_ENTITY_PROCESSING = 0x01, + NEEDS_NEWLINE_NORMALIZATION = 0x02, + NEEDS_WHITESPACE_COLLAPSING = 0x04, + + TEXT_ELEMENT = NEEDS_ENTITY_PROCESSING | NEEDS_NEWLINE_NORMALIZATION, + TEXT_ELEMENT_LEAVE_ENTITIES = NEEDS_NEWLINE_NORMALIZATION, + ATTRIBUTE_NAME = 0, + ATTRIBUTE_VALUE = NEEDS_ENTITY_PROCESSING | NEEDS_NEWLINE_NORMALIZATION, + ATTRIBUTE_VALUE_LEAVE_ENTITIES = NEEDS_NEWLINE_NORMALIZATION, + COMMENT = NEEDS_NEWLINE_NORMALIZATION + }; + + StrPair() : _flags( 0 ), _start( 0 ), _end( 0 ) {} + ~StrPair(); + + void Set( char* start, char* end, int flags ) { + TIXMLASSERT( start ); + TIXMLASSERT( end ); + Reset(); + _start = start; + _end = end; + _flags = flags | NEEDS_FLUSH; + } + + const char* GetStr(); + + bool Empty() const { + return _start == _end; + } + + void SetInternedStr( const char* str ) { + Reset(); + _start = const_cast(str); + } + + void SetStr( const char* str, int flags=0 ); + + char* ParseText( char* in, const char* endTag, int strFlags, int* curLineNumPtr ); + char* ParseName( char* in ); + + void TransferTo( StrPair* other ); + void Reset(); + +private: + void CollapseWhitespace(); + + enum { + NEEDS_FLUSH = 0x100, + NEEDS_DELETE = 0x200 + }; + + int _flags; + char* _start; + char* _end; + + StrPair( const StrPair& other ); // not supported + void operator=( const StrPair& other ); // not supported, use TransferTo() +}; + + +/* + A dynamic array of Plain Old Data. Doesn't support constructors, etc. + Has a small initial memory pool, so that low or no usage will not + cause a call to new/delete +*/ +template +class DynArray +{ +public: + DynArray() : + _mem( _pool ), + _allocated( INITIAL_SIZE ), + _size( 0 ) + { + } + + ~DynArray() { + if ( _mem != _pool ) { + delete [] _mem; + } + } + + void Clear() { + _size = 0; + } + + void Push( T t ) { + TIXMLASSERT( _size < INT_MAX ); + EnsureCapacity( _size+1 ); + _mem[_size] = t; + ++_size; + } + + T* PushArr( int count ) { + TIXMLASSERT( count >= 0 ); + TIXMLASSERT( _size <= INT_MAX - count ); + EnsureCapacity( _size+count ); + T* ret = &_mem[_size]; + _size += count; + return ret; + } + + T Pop() { + TIXMLASSERT( _size > 0 ); + --_size; + return _mem[_size]; + } + + void PopArr( int count ) { + TIXMLASSERT( _size >= count ); + _size -= count; + } + + bool Empty() const { + return _size == 0; + } + + T& operator[](int i) { + TIXMLASSERT( i>= 0 && i < _size ); + return _mem[i]; + } + + const T& operator[](int i) const { + TIXMLASSERT( i>= 0 && i < _size ); + return _mem[i]; + } + + const T& PeekTop() const { + TIXMLASSERT( _size > 0 ); + return _mem[ _size - 1]; + } + + int Size() const { + TIXMLASSERT( _size >= 0 ); + return _size; + } + + int Capacity() const { + TIXMLASSERT( _allocated >= INITIAL_SIZE ); + return _allocated; + } + + void SwapRemove(int i) { + TIXMLASSERT(i >= 0 && i < _size); + TIXMLASSERT(_size > 0); + _mem[i] = _mem[_size - 1]; + --_size; + } + + const T* Mem() const { + TIXMLASSERT( _mem ); + return _mem; + } + + T* Mem() { + TIXMLASSERT( _mem ); + return _mem; + } + +private: + DynArray( const DynArray& ); // not supported + void operator=( const DynArray& ); // not supported + + void EnsureCapacity( int cap ) { + TIXMLASSERT( cap > 0 ); + if ( cap > _allocated ) { + TIXMLASSERT( cap <= INT_MAX / 2 ); + const int newAllocated = cap * 2; + T* newMem = new T[newAllocated]; + TIXMLASSERT( newAllocated >= _size ); + memcpy( newMem, _mem, sizeof(T)*_size ); // warning: not using constructors, only works for PODs + if ( _mem != _pool ) { + delete [] _mem; + } + _mem = newMem; + _allocated = newAllocated; + } + } + + T* _mem; + T _pool[INITIAL_SIZE]; + int _allocated; // objects allocated + int _size; // number objects in use +}; + + +/* + Parent virtual class of a pool for fast allocation + and deallocation of objects. +*/ +class MemPool +{ +public: + MemPool() {} + virtual ~MemPool() {} + + virtual int ItemSize() const = 0; + virtual void* Alloc() = 0; + virtual void Free( void* ) = 0; + virtual void SetTracked() = 0; +}; + + +/* + Template child class to create pools of the correct type. +*/ +template< int ITEM_SIZE > +class MemPoolT : public MemPool +{ +public: + MemPoolT() : _blockPtrs(), _root(0), _currentAllocs(0), _nAllocs(0), _maxAllocs(0), _nUntracked(0) {} + ~MemPoolT() { + MemPoolT< ITEM_SIZE >::Clear(); + } + + void Clear() { + // Delete the blocks. + while( !_blockPtrs.Empty()) { + Block* lastBlock = _blockPtrs.Pop(); + delete lastBlock; + } + _root = 0; + _currentAllocs = 0; + _nAllocs = 0; + _maxAllocs = 0; + _nUntracked = 0; + } + + virtual int ItemSize() const { + return ITEM_SIZE; + } + int CurrentAllocs() const { + return _currentAllocs; + } + + virtual void* Alloc() { + if ( !_root ) { + // Need a new block. + Block* block = new Block; + _blockPtrs.Push( block ); + + Item* blockItems = block->items; + for( int i = 0; i < ITEMS_PER_BLOCK - 1; ++i ) { + blockItems[i].next = &(blockItems[i + 1]); + } + blockItems[ITEMS_PER_BLOCK - 1].next = 0; + _root = blockItems; + } + Item* const result = _root; + TIXMLASSERT( result != 0 ); + _root = _root->next; + + ++_currentAllocs; + if ( _currentAllocs > _maxAllocs ) { + _maxAllocs = _currentAllocs; + } + ++_nAllocs; + ++_nUntracked; + return result; + } + + virtual void Free( void* mem ) { + if ( !mem ) { + return; + } + --_currentAllocs; + Item* item = static_cast( mem ); +#ifdef TINYXML2_DEBUG + memset( item, 0xfe, sizeof( *item ) ); +#endif + item->next = _root; + _root = item; + } + void Trace( const char* name ) { + printf( "Mempool %s watermark=%d [%dk] current=%d size=%d nAlloc=%d blocks=%d\n", + name, _maxAllocs, _maxAllocs * ITEM_SIZE / 1024, _currentAllocs, + ITEM_SIZE, _nAllocs, _blockPtrs.Size() ); + } + + void SetTracked() { + --_nUntracked; + } + + int Untracked() const { + return _nUntracked; + } + + // This number is perf sensitive. 4k seems like a good tradeoff on my machine. + // The test file is large, 170k. + // Release: VS2010 gcc(no opt) + // 1k: 4000 + // 2k: 4000 + // 4k: 3900 21000 + // 16k: 5200 + // 32k: 4300 + // 64k: 4000 21000 + // Declared public because some compilers do not accept to use ITEMS_PER_BLOCK + // in private part if ITEMS_PER_BLOCK is private + enum { ITEMS_PER_BLOCK = (4 * 1024) / ITEM_SIZE }; + +private: + MemPoolT( const MemPoolT& ); // not supported + void operator=( const MemPoolT& ); // not supported + + union Item { + Item* next; + char itemData[ITEM_SIZE]; + }; + struct Block { + Item items[ITEMS_PER_BLOCK]; + }; + DynArray< Block*, 10 > _blockPtrs; + Item* _root; + + int _currentAllocs; + int _nAllocs; + int _maxAllocs; + int _nUntracked; +}; + + + +/** + Implements the interface to the "Visitor pattern" (see the Accept() method.) + If you call the Accept() method, it requires being passed a XMLVisitor + class to handle callbacks. For nodes that contain other nodes (Document, Element) + you will get called with a VisitEnter/VisitExit pair. Nodes that are always leafs + are simply called with Visit(). + + If you return 'true' from a Visit method, recursive parsing will continue. If you return + false, no children of this node or its siblings will be visited. + + All flavors of Visit methods have a default implementation that returns 'true' (continue + visiting). You need to only override methods that are interesting to you. + + Generally Accept() is called on the XMLDocument, although all nodes support visiting. + + You should never change the document from a callback. + + @sa XMLNode::Accept() +*/ +class TINYXML2_LIB XMLVisitor +{ +public: + virtual ~XMLVisitor() {} + + /// Visit a document. + virtual bool VisitEnter( const XMLDocument& /*doc*/ ) { + return true; + } + /// Visit a document. + virtual bool VisitExit( const XMLDocument& /*doc*/ ) { + return true; + } + + /// Visit an element. + virtual bool VisitEnter( const XMLElement& /*element*/, const XMLAttribute* /*firstAttribute*/ ) { + return true; + } + /// Visit an element. + virtual bool VisitExit( const XMLElement& /*element*/ ) { + return true; + } + + /// Visit a declaration. + virtual bool Visit( const XMLDeclaration& /*declaration*/ ) { + return true; + } + /// Visit a text node. + virtual bool Visit( const XMLText& /*text*/ ) { + return true; + } + /// Visit a comment node. + virtual bool Visit( const XMLComment& /*comment*/ ) { + return true; + } + /// Visit an unknown node. + virtual bool Visit( const XMLUnknown& /*unknown*/ ) { + return true; + } +}; + +// WARNING: must match XMLDocument::_errorNames[] +enum XMLError { + XML_SUCCESS = 0, + XML_NO_ATTRIBUTE, + XML_WRONG_ATTRIBUTE_TYPE, + XML_ERROR_FILE_NOT_FOUND, + XML_ERROR_FILE_COULD_NOT_BE_OPENED, + XML_ERROR_FILE_READ_ERROR, + XML_ERROR_PARSING_ELEMENT, + XML_ERROR_PARSING_ATTRIBUTE, + XML_ERROR_PARSING_TEXT, + XML_ERROR_PARSING_CDATA, + XML_ERROR_PARSING_COMMENT, + XML_ERROR_PARSING_DECLARATION, + XML_ERROR_PARSING_UNKNOWN, + XML_ERROR_EMPTY_DOCUMENT, + XML_ERROR_MISMATCHED_ELEMENT, + XML_ERROR_PARSING, + XML_CAN_NOT_CONVERT_TEXT, + XML_NO_TEXT_NODE, + XML_ELEMENT_DEPTH_EXCEEDED, + + XML_ERROR_COUNT +}; + + +/* + Utility functionality. +*/ +class TINYXML2_LIB XMLUtil +{ +public: + static const char* SkipWhiteSpace( const char* p, int* curLineNumPtr ) { + TIXMLASSERT( p ); + + while( IsWhiteSpace(*p) ) { + if (curLineNumPtr && *p == '\n') { + ++(*curLineNumPtr); + } + ++p; + } + TIXMLASSERT( p ); + return p; + } + static char* SkipWhiteSpace( char* const p, int* curLineNumPtr ) { + return const_cast( SkipWhiteSpace( const_cast(p), curLineNumPtr ) ); + } + + // Anything in the high order range of UTF-8 is assumed to not be whitespace. This isn't + // correct, but simple, and usually works. + static bool IsWhiteSpace( char p ) { + return !IsUTF8Continuation(p) && isspace( static_cast(p) ); + } + + inline static bool IsNameStartChar( unsigned char ch ) { + if ( ch >= 128 ) { + // This is a heuristic guess in attempt to not implement Unicode-aware isalpha() + return true; + } + if ( isalpha( ch ) ) { + return true; + } + return ch == ':' || ch == '_'; + } + + inline static bool IsNameChar( unsigned char ch ) { + return IsNameStartChar( ch ) + || isdigit( ch ) + || ch == '.' + || ch == '-'; + } + + inline static bool IsPrefixHex( const char* p) { + p = SkipWhiteSpace(p, 0); + return p && *p == '0' && ( *(p + 1) == 'x' || *(p + 1) == 'X'); + } + + inline static bool StringEqual( const char* p, const char* q, int nChar=INT_MAX ) { + if ( p == q ) { + return true; + } + TIXMLASSERT( p ); + TIXMLASSERT( q ); + TIXMLASSERT( nChar >= 0 ); + return strncmp( p, q, nChar ) == 0; + } + + inline static bool IsUTF8Continuation( const char p ) { + return ( p & 0x80 ) != 0; + } + + static const char* ReadBOM( const char* p, bool* hasBOM ); + // p is the starting location, + // the UTF-8 value of the entity will be placed in value, and length filled in. + static const char* GetCharacterRef( const char* p, char* value, int* length ); + static void ConvertUTF32ToUTF8( unsigned long input, char* output, int* length ); + + // converts primitive types to strings + static void ToStr( int v, char* buffer, int bufferSize ); + static void ToStr( unsigned v, char* buffer, int bufferSize ); + static void ToStr( bool v, char* buffer, int bufferSize ); + static void ToStr( float v, char* buffer, int bufferSize ); + static void ToStr( double v, char* buffer, int bufferSize ); + static void ToStr(int64_t v, char* buffer, int bufferSize); + static void ToStr(uint64_t v, char* buffer, int bufferSize); + + // converts strings to primitive types + static bool ToInt( const char* str, int* value ); + static bool ToUnsigned( const char* str, unsigned* value ); + static bool ToBool( const char* str, bool* value ); + static bool ToFloat( const char* str, float* value ); + static bool ToDouble( const char* str, double* value ); + static bool ToInt64(const char* str, int64_t* value); + static bool ToUnsigned64(const char* str, uint64_t* value); + // Changes what is serialized for a boolean value. + // Default to "true" and "false". Shouldn't be changed + // unless you have a special testing or compatibility need. + // Be careful: static, global, & not thread safe. + // Be sure to set static const memory as parameters. + static void SetBoolSerialization(const char* writeTrue, const char* writeFalse); + +private: + static const char* writeBoolTrue; + static const char* writeBoolFalse; +}; + + +/** XMLNode is a base class for every object that is in the + XML Document Object Model (DOM), except XMLAttributes. + Nodes have siblings, a parent, and children which can + be navigated. A node is always in a XMLDocument. + The type of a XMLNode can be queried, and it can + be cast to its more defined type. + + A XMLDocument allocates memory for all its Nodes. + When the XMLDocument gets deleted, all its Nodes + will also be deleted. + + @verbatim + A Document can contain: Element (container or leaf) + Comment (leaf) + Unknown (leaf) + Declaration( leaf ) + + An Element can contain: Element (container or leaf) + Text (leaf) + Attributes (not on tree) + Comment (leaf) + Unknown (leaf) + + @endverbatim +*/ +class TINYXML2_LIB XMLNode +{ + friend class XMLDocument; + friend class XMLElement; +public: + + /// Get the XMLDocument that owns this XMLNode. + const XMLDocument* GetDocument() const { + TIXMLASSERT( _document ); + return _document; + } + /// Get the XMLDocument that owns this XMLNode. + XMLDocument* GetDocument() { + TIXMLASSERT( _document ); + return _document; + } + + /// Safely cast to an Element, or null. + virtual XMLElement* ToElement() { + return 0; + } + /// Safely cast to Text, or null. + virtual XMLText* ToText() { + return 0; + } + /// Safely cast to a Comment, or null. + virtual XMLComment* ToComment() { + return 0; + } + /// Safely cast to a Document, or null. + virtual XMLDocument* ToDocument() { + return 0; + } + /// Safely cast to a Declaration, or null. + virtual XMLDeclaration* ToDeclaration() { + return 0; + } + /// Safely cast to an Unknown, or null. + virtual XMLUnknown* ToUnknown() { + return 0; + } + + virtual const XMLElement* ToElement() const { + return 0; + } + virtual const XMLText* ToText() const { + return 0; + } + virtual const XMLComment* ToComment() const { + return 0; + } + virtual const XMLDocument* ToDocument() const { + return 0; + } + virtual const XMLDeclaration* ToDeclaration() const { + return 0; + } + virtual const XMLUnknown* ToUnknown() const { + return 0; + } + + /** The meaning of 'value' changes for the specific type. + @verbatim + Document: empty (NULL is returned, not an empty string) + Element: name of the element + Comment: the comment text + Unknown: the tag contents + Text: the text string + @endverbatim + */ + const char* Value() const; + + /** Set the Value of an XML node. + @sa Value() + */ + void SetValue( const char* val, bool staticMem=false ); + + /// Gets the line number the node is in, if the document was parsed from a file. + int GetLineNum() const { return _parseLineNum; } + + /// Get the parent of this node on the DOM. + const XMLNode* Parent() const { + return _parent; + } + + XMLNode* Parent() { + return _parent; + } + + /// Returns true if this node has no children. + bool NoChildren() const { + return !_firstChild; + } + + /// Get the first child node, or null if none exists. + const XMLNode* FirstChild() const { + return _firstChild; + } + + XMLNode* FirstChild() { + return _firstChild; + } + + /** Get the first child element, or optionally the first child + element with the specified name. + */ + const XMLElement* FirstChildElement( const char* name = 0 ) const; + + XMLElement* FirstChildElement( const char* name = 0 ) { + return const_cast(const_cast(this)->FirstChildElement( name )); + } + + /// Get the last child node, or null if none exists. + const XMLNode* LastChild() const { + return _lastChild; + } + + XMLNode* LastChild() { + return _lastChild; + } + + /** Get the last child element or optionally the last child + element with the specified name. + */ + const XMLElement* LastChildElement( const char* name = 0 ) const; + + XMLElement* LastChildElement( const char* name = 0 ) { + return const_cast(const_cast(this)->LastChildElement(name) ); + } + + /// Get the previous (left) sibling node of this node. + const XMLNode* PreviousSibling() const { + return _prev; + } + + XMLNode* PreviousSibling() { + return _prev; + } + + /// Get the previous (left) sibling element of this node, with an optionally supplied name. + const XMLElement* PreviousSiblingElement( const char* name = 0 ) const ; + + XMLElement* PreviousSiblingElement( const char* name = 0 ) { + return const_cast(const_cast(this)->PreviousSiblingElement( name ) ); + } + + /// Get the next (right) sibling node of this node. + const XMLNode* NextSibling() const { + return _next; + } + + XMLNode* NextSibling() { + return _next; + } + + /// Get the next (right) sibling element of this node, with an optionally supplied name. + const XMLElement* NextSiblingElement( const char* name = 0 ) const; + + XMLElement* NextSiblingElement( const char* name = 0 ) { + return const_cast(const_cast(this)->NextSiblingElement( name ) ); + } + + /** + Add a child node as the last (right) child. + If the child node is already part of the document, + it is moved from its old location to the new location. + Returns the addThis argument or 0 if the node does not + belong to the same document. + */ + XMLNode* InsertEndChild( XMLNode* addThis ); + + XMLNode* LinkEndChild( XMLNode* addThis ) { + return InsertEndChild( addThis ); + } + /** + Add a child node as the first (left) child. + If the child node is already part of the document, + it is moved from its old location to the new location. + Returns the addThis argument or 0 if the node does not + belong to the same document. + */ + XMLNode* InsertFirstChild( XMLNode* addThis ); + /** + Add a node after the specified child node. + If the child node is already part of the document, + it is moved from its old location to the new location. + Returns the addThis argument or 0 if the afterThis node + is not a child of this node, or if the node does not + belong to the same document. + */ + XMLNode* InsertAfterChild( XMLNode* afterThis, XMLNode* addThis ); + + /** + Delete all the children of this node. + */ + void DeleteChildren(); + + /** + Delete a child of this node. + */ + void DeleteChild( XMLNode* node ); + + /** + Make a copy of this node, but not its children. + You may pass in a Document pointer that will be + the owner of the new Node. If the 'document' is + null, then the node returned will be allocated + from the current Document. (this->GetDocument()) + + Note: if called on a XMLDocument, this will return null. + */ + virtual XMLNode* ShallowClone( XMLDocument* document ) const = 0; + + /** + Make a copy of this node and all its children. + + If the 'target' is null, then the nodes will + be allocated in the current document. If 'target' + is specified, the memory will be allocated is the + specified XMLDocument. + + NOTE: This is probably not the correct tool to + copy a document, since XMLDocuments can have multiple + top level XMLNodes. You probably want to use + XMLDocument::DeepCopy() + */ + XMLNode* DeepClone( XMLDocument* target ) const; + + /** + Test if 2 nodes are the same, but don't test children. + The 2 nodes do not need to be in the same Document. + + Note: if called on a XMLDocument, this will return false. + */ + virtual bool ShallowEqual( const XMLNode* compare ) const = 0; + + /** Accept a hierarchical visit of the nodes in the TinyXML-2 DOM. Every node in the + XML tree will be conditionally visited and the host will be called back + via the XMLVisitor interface. + + This is essentially a SAX interface for TinyXML-2. (Note however it doesn't re-parse + the XML for the callbacks, so the performance of TinyXML-2 is unchanged by using this + interface versus any other.) + + The interface has been based on ideas from: + + - http://www.saxproject.org/ + - http://c2.com/cgi/wiki?HierarchicalVisitorPattern + + Which are both good references for "visiting". + + An example of using Accept(): + @verbatim + XMLPrinter printer; + tinyxmlDoc.Accept( &printer ); + const char* xmlcstr = printer.CStr(); + @endverbatim + */ + virtual bool Accept( XMLVisitor* visitor ) const = 0; + + /** + Set user data into the XMLNode. TinyXML-2 in + no way processes or interprets user data. + It is initially 0. + */ + void SetUserData(void* userData) { _userData = userData; } + + /** + Get user data set into the XMLNode. TinyXML-2 in + no way processes or interprets user data. + It is initially 0. + */ + void* GetUserData() const { return _userData; } + +protected: + explicit XMLNode( XMLDocument* ); + virtual ~XMLNode(); + + virtual char* ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr); + + XMLDocument* _document; + XMLNode* _parent; + mutable StrPair _value; + int _parseLineNum; + + XMLNode* _firstChild; + XMLNode* _lastChild; + + XMLNode* _prev; + XMLNode* _next; + + void* _userData; + +private: + MemPool* _memPool; + void Unlink( XMLNode* child ); + static void DeleteNode( XMLNode* node ); + void InsertChildPreamble( XMLNode* insertThis ) const; + const XMLElement* ToElementWithName( const char* name ) const; + + XMLNode( const XMLNode& ); // not supported + XMLNode& operator=( const XMLNode& ); // not supported +}; + + +/** XML text. + + Note that a text node can have child element nodes, for example: + @verbatim + This is bold + @endverbatim + + A text node can have 2 ways to output the next. "normal" output + and CDATA. It will default to the mode it was parsed from the XML file and + you generally want to leave it alone, but you can change the output mode with + SetCData() and query it with CData(). +*/ +class TINYXML2_LIB XMLText : public XMLNode +{ + friend class XMLDocument; +public: + virtual bool Accept( XMLVisitor* visitor ) const; + + virtual XMLText* ToText() { + return this; + } + virtual const XMLText* ToText() const { + return this; + } + + /// Declare whether this should be CDATA or standard text. + void SetCData( bool isCData ) { + _isCData = isCData; + } + /// Returns true if this is a CDATA text element. + bool CData() const { + return _isCData; + } + + virtual XMLNode* ShallowClone( XMLDocument* document ) const; + virtual bool ShallowEqual( const XMLNode* compare ) const; + +protected: + explicit XMLText( XMLDocument* doc ) : XMLNode( doc ), _isCData( false ) {} + virtual ~XMLText() {} + + char* ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr ); + +private: + bool _isCData; + + XMLText( const XMLText& ); // not supported + XMLText& operator=( const XMLText& ); // not supported +}; + + +/** An XML Comment. */ +class TINYXML2_LIB XMLComment : public XMLNode +{ + friend class XMLDocument; +public: + virtual XMLComment* ToComment() { + return this; + } + virtual const XMLComment* ToComment() const { + return this; + } + + virtual bool Accept( XMLVisitor* visitor ) const; + + virtual XMLNode* ShallowClone( XMLDocument* document ) const; + virtual bool ShallowEqual( const XMLNode* compare ) const; + +protected: + explicit XMLComment( XMLDocument* doc ); + virtual ~XMLComment(); + + char* ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr); + +private: + XMLComment( const XMLComment& ); // not supported + XMLComment& operator=( const XMLComment& ); // not supported +}; + + +/** In correct XML the declaration is the first entry in the file. + @verbatim + + @endverbatim + + TinyXML-2 will happily read or write files without a declaration, + however. + + The text of the declaration isn't interpreted. It is parsed + and written as a string. +*/ +class TINYXML2_LIB XMLDeclaration : public XMLNode +{ + friend class XMLDocument; +public: + virtual XMLDeclaration* ToDeclaration() { + return this; + } + virtual const XMLDeclaration* ToDeclaration() const { + return this; + } + + virtual bool Accept( XMLVisitor* visitor ) const; + + virtual XMLNode* ShallowClone( XMLDocument* document ) const; + virtual bool ShallowEqual( const XMLNode* compare ) const; + +protected: + explicit XMLDeclaration( XMLDocument* doc ); + virtual ~XMLDeclaration(); + + char* ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr ); + +private: + XMLDeclaration( const XMLDeclaration& ); // not supported + XMLDeclaration& operator=( const XMLDeclaration& ); // not supported +}; + + +/** Any tag that TinyXML-2 doesn't recognize is saved as an + unknown. It is a tag of text, but should not be modified. + It will be written back to the XML, unchanged, when the file + is saved. + + DTD tags get thrown into XMLUnknowns. +*/ +class TINYXML2_LIB XMLUnknown : public XMLNode +{ + friend class XMLDocument; +public: + virtual XMLUnknown* ToUnknown() { + return this; + } + virtual const XMLUnknown* ToUnknown() const { + return this; + } + + virtual bool Accept( XMLVisitor* visitor ) const; + + virtual XMLNode* ShallowClone( XMLDocument* document ) const; + virtual bool ShallowEqual( const XMLNode* compare ) const; + +protected: + explicit XMLUnknown( XMLDocument* doc ); + virtual ~XMLUnknown(); + + char* ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr ); + +private: + XMLUnknown( const XMLUnknown& ); // not supported + XMLUnknown& operator=( const XMLUnknown& ); // not supported +}; + + + +/** An attribute is a name-value pair. Elements have an arbitrary + number of attributes, each with a unique name. + + @note The attributes are not XMLNodes. You may only query the + Next() attribute in a list. +*/ +class TINYXML2_LIB XMLAttribute +{ + friend class XMLElement; +public: + /// The name of the attribute. + const char* Name() const; + + /// The value of the attribute. + const char* Value() const; + + /// Gets the line number the attribute is in, if the document was parsed from a file. + int GetLineNum() const { return _parseLineNum; } + + /// The next attribute in the list. + const XMLAttribute* Next() const { + return _next; + } + + /** IntValue interprets the attribute as an integer, and returns the value. + If the value isn't an integer, 0 will be returned. There is no error checking; + use QueryIntValue() if you need error checking. + */ + int IntValue() const { + int i = 0; + QueryIntValue(&i); + return i; + } + + int64_t Int64Value() const { + int64_t i = 0; + QueryInt64Value(&i); + return i; + } + + uint64_t Unsigned64Value() const { + uint64_t i = 0; + QueryUnsigned64Value(&i); + return i; + } + + /// Query as an unsigned integer. See IntValue() + unsigned UnsignedValue() const { + unsigned i=0; + QueryUnsignedValue( &i ); + return i; + } + /// Query as a boolean. See IntValue() + bool BoolValue() const { + bool b=false; + QueryBoolValue( &b ); + return b; + } + /// Query as a double. See IntValue() + double DoubleValue() const { + double d=0; + QueryDoubleValue( &d ); + return d; + } + /// Query as a float. See IntValue() + float FloatValue() const { + float f=0; + QueryFloatValue( &f ); + return f; + } + + /** QueryIntValue interprets the attribute as an integer, and returns the value + in the provided parameter. The function will return XML_SUCCESS on success, + and XML_WRONG_ATTRIBUTE_TYPE if the conversion is not successful. + */ + XMLError QueryIntValue( int* value ) const; + /// See QueryIntValue + XMLError QueryUnsignedValue( unsigned int* value ) const; + /// See QueryIntValue + XMLError QueryInt64Value(int64_t* value) const; + /// See QueryIntValue + XMLError QueryUnsigned64Value(uint64_t* value) const; + /// See QueryIntValue + XMLError QueryBoolValue( bool* value ) const; + /// See QueryIntValue + XMLError QueryDoubleValue( double* value ) const; + /// See QueryIntValue + XMLError QueryFloatValue( float* value ) const; + + /// Set the attribute to a string value. + void SetAttribute( const char* value ); + /// Set the attribute to value. + void SetAttribute( int value ); + /// Set the attribute to value. + void SetAttribute( unsigned value ); + /// Set the attribute to value. + void SetAttribute(int64_t value); + /// Set the attribute to value. + void SetAttribute(uint64_t value); + /// Set the attribute to value. + void SetAttribute( bool value ); + /// Set the attribute to value. + void SetAttribute( double value ); + /// Set the attribute to value. + void SetAttribute( float value ); + +private: + enum { BUF_SIZE = 200 }; + + XMLAttribute() : _name(), _value(),_parseLineNum( 0 ), _next( 0 ), _memPool( 0 ) {} + virtual ~XMLAttribute() {} + + XMLAttribute( const XMLAttribute& ); // not supported + void operator=( const XMLAttribute& ); // not supported + void SetName( const char* name ); + + char* ParseDeep( char* p, bool processEntities, int* curLineNumPtr ); + + mutable StrPair _name; + mutable StrPair _value; + int _parseLineNum; + XMLAttribute* _next; + MemPool* _memPool; +}; + + +/** The element is a container class. It has a value, the element name, + and can contain other elements, text, comments, and unknowns. + Elements also contain an arbitrary number of attributes. +*/ +class TINYXML2_LIB XMLElement : public XMLNode +{ + friend class XMLDocument; +public: + /// Get the name of an element (which is the Value() of the node.) + const char* Name() const { + return Value(); + } + /// Set the name of the element. + void SetName( const char* str, bool staticMem=false ) { + SetValue( str, staticMem ); + } + + virtual XMLElement* ToElement() { + return this; + } + virtual const XMLElement* ToElement() const { + return this; + } + virtual bool Accept( XMLVisitor* visitor ) const; + + /** Given an attribute name, Attribute() returns the value + for the attribute of that name, or null if none + exists. For example: + + @verbatim + const char* value = ele->Attribute( "foo" ); + @endverbatim + + The 'value' parameter is normally null. However, if specified, + the attribute will only be returned if the 'name' and 'value' + match. This allow you to write code: + + @verbatim + if ( ele->Attribute( "foo", "bar" ) ) callFooIsBar(); + @endverbatim + + rather than: + @verbatim + if ( ele->Attribute( "foo" ) ) { + if ( strcmp( ele->Attribute( "foo" ), "bar" ) == 0 ) callFooIsBar(); + } + @endverbatim + */ + const char* Attribute( const char* name, const char* value=0 ) const; + + /** Given an attribute name, IntAttribute() returns the value + of the attribute interpreted as an integer. The default + value will be returned if the attribute isn't present, + or if there is an error. (For a method with error + checking, see QueryIntAttribute()). + */ + int IntAttribute(const char* name, int defaultValue = 0) const; + /// See IntAttribute() + unsigned UnsignedAttribute(const char* name, unsigned defaultValue = 0) const; + /// See IntAttribute() + int64_t Int64Attribute(const char* name, int64_t defaultValue = 0) const; + /// See IntAttribute() + uint64_t Unsigned64Attribute(const char* name, uint64_t defaultValue = 0) const; + /// See IntAttribute() + bool BoolAttribute(const char* name, bool defaultValue = false) const; + /// See IntAttribute() + double DoubleAttribute(const char* name, double defaultValue = 0) const; + /// See IntAttribute() + float FloatAttribute(const char* name, float defaultValue = 0) const; + + /** Given an attribute name, QueryIntAttribute() returns + XML_SUCCESS, XML_WRONG_ATTRIBUTE_TYPE if the conversion + can't be performed, or XML_NO_ATTRIBUTE if the attribute + doesn't exist. If successful, the result of the conversion + will be written to 'value'. If not successful, nothing will + be written to 'value'. This allows you to provide default + value: + + @verbatim + int value = 10; + QueryIntAttribute( "foo", &value ); // if "foo" isn't found, value will still be 10 + @endverbatim + */ + XMLError QueryIntAttribute( const char* name, int* value ) const { + const XMLAttribute* a = FindAttribute( name ); + if ( !a ) { + return XML_NO_ATTRIBUTE; + } + return a->QueryIntValue( value ); + } + + /// See QueryIntAttribute() + XMLError QueryUnsignedAttribute( const char* name, unsigned int* value ) const { + const XMLAttribute* a = FindAttribute( name ); + if ( !a ) { + return XML_NO_ATTRIBUTE; + } + return a->QueryUnsignedValue( value ); + } + + /// See QueryIntAttribute() + XMLError QueryInt64Attribute(const char* name, int64_t* value) const { + const XMLAttribute* a = FindAttribute(name); + if (!a) { + return XML_NO_ATTRIBUTE; + } + return a->QueryInt64Value(value); + } + + /// See QueryIntAttribute() + XMLError QueryUnsigned64Attribute(const char* name, uint64_t* value) const { + const XMLAttribute* a = FindAttribute(name); + if(!a) { + return XML_NO_ATTRIBUTE; + } + return a->QueryUnsigned64Value(value); + } + + /// See QueryIntAttribute() + XMLError QueryBoolAttribute( const char* name, bool* value ) const { + const XMLAttribute* a = FindAttribute( name ); + if ( !a ) { + return XML_NO_ATTRIBUTE; + } + return a->QueryBoolValue( value ); + } + /// See QueryIntAttribute() + XMLError QueryDoubleAttribute( const char* name, double* value ) const { + const XMLAttribute* a = FindAttribute( name ); + if ( !a ) { + return XML_NO_ATTRIBUTE; + } + return a->QueryDoubleValue( value ); + } + /// See QueryIntAttribute() + XMLError QueryFloatAttribute( const char* name, float* value ) const { + const XMLAttribute* a = FindAttribute( name ); + if ( !a ) { + return XML_NO_ATTRIBUTE; + } + return a->QueryFloatValue( value ); + } + + /// See QueryIntAttribute() + XMLError QueryStringAttribute(const char* name, const char** value) const { + const XMLAttribute* a = FindAttribute(name); + if (!a) { + return XML_NO_ATTRIBUTE; + } + *value = a->Value(); + return XML_SUCCESS; + } + + + + /** Given an attribute name, QueryAttribute() returns + XML_SUCCESS, XML_WRONG_ATTRIBUTE_TYPE if the conversion + can't be performed, or XML_NO_ATTRIBUTE if the attribute + doesn't exist. It is overloaded for the primitive types, + and is a generally more convenient replacement of + QueryIntAttribute() and related functions. + + If successful, the result of the conversion + will be written to 'value'. If not successful, nothing will + be written to 'value'. This allows you to provide default + value: + + @verbatim + int value = 10; + QueryAttribute( "foo", &value ); // if "foo" isn't found, value will still be 10 + @endverbatim + */ + XMLError QueryAttribute( const char* name, int* value ) const { + return QueryIntAttribute( name, value ); + } + + XMLError QueryAttribute( const char* name, unsigned int* value ) const { + return QueryUnsignedAttribute( name, value ); + } + + XMLError QueryAttribute(const char* name, int64_t* value) const { + return QueryInt64Attribute(name, value); + } + + XMLError QueryAttribute(const char* name, uint64_t* value) const { + return QueryUnsigned64Attribute(name, value); + } + + XMLError QueryAttribute( const char* name, bool* value ) const { + return QueryBoolAttribute( name, value ); + } + + XMLError QueryAttribute( const char* name, double* value ) const { + return QueryDoubleAttribute( name, value ); + } + + XMLError QueryAttribute( const char* name, float* value ) const { + return QueryFloatAttribute( name, value ); + } + + XMLError QueryAttribute(const char* name, const char** value) const { + return QueryStringAttribute(name, value); + } + + /// Sets the named attribute to value. + void SetAttribute( const char* name, const char* value ) { + XMLAttribute* a = FindOrCreateAttribute( name ); + a->SetAttribute( value ); + } + /// Sets the named attribute to value. + void SetAttribute( const char* name, int value ) { + XMLAttribute* a = FindOrCreateAttribute( name ); + a->SetAttribute( value ); + } + /// Sets the named attribute to value. + void SetAttribute( const char* name, unsigned value ) { + XMLAttribute* a = FindOrCreateAttribute( name ); + a->SetAttribute( value ); + } + + /// Sets the named attribute to value. + void SetAttribute(const char* name, int64_t value) { + XMLAttribute* a = FindOrCreateAttribute(name); + a->SetAttribute(value); + } + + /// Sets the named attribute to value. + void SetAttribute(const char* name, uint64_t value) { + XMLAttribute* a = FindOrCreateAttribute(name); + a->SetAttribute(value); + } + + /// Sets the named attribute to value. + void SetAttribute( const char* name, bool value ) { + XMLAttribute* a = FindOrCreateAttribute( name ); + a->SetAttribute( value ); + } + /// Sets the named attribute to value. + void SetAttribute( const char* name, double value ) { + XMLAttribute* a = FindOrCreateAttribute( name ); + a->SetAttribute( value ); + } + /// Sets the named attribute to value. + void SetAttribute( const char* name, float value ) { + XMLAttribute* a = FindOrCreateAttribute( name ); + a->SetAttribute( value ); + } + + /** + Delete an attribute. + */ + void DeleteAttribute( const char* name ); + + /// Return the first attribute in the list. + const XMLAttribute* FirstAttribute() const { + return _rootAttribute; + } + /// Query a specific attribute in the list. + const XMLAttribute* FindAttribute( const char* name ) const; + + /** Convenience function for easy access to the text inside an element. Although easy + and concise, GetText() is limited compared to getting the XMLText child + and accessing it directly. + + If the first child of 'this' is a XMLText, the GetText() + returns the character string of the Text node, else null is returned. + + This is a convenient method for getting the text of simple contained text: + @verbatim + This is text + const char* str = fooElement->GetText(); + @endverbatim + + 'str' will be a pointer to "This is text". + + Note that this function can be misleading. If the element foo was created from + this XML: + @verbatim + This is text + @endverbatim + + then the value of str would be null. The first child node isn't a text node, it is + another element. From this XML: + @verbatim + This is text + @endverbatim + GetText() will return "This is ". + */ + const char* GetText() const; + + /** Convenience function for easy access to the text inside an element. Although easy + and concise, SetText() is limited compared to creating an XMLText child + and mutating it directly. + + If the first child of 'this' is a XMLText, SetText() sets its value to + the given string, otherwise it will create a first child that is an XMLText. + + This is a convenient method for setting the text of simple contained text: + @verbatim + This is text + fooElement->SetText( "Hullaballoo!" ); + Hullaballoo! + @endverbatim + + Note that this function can be misleading. If the element foo was created from + this XML: + @verbatim + This is text + @endverbatim + + then it will not change "This is text", but rather prefix it with a text element: + @verbatim + Hullaballoo!This is text + @endverbatim + + For this XML: + @verbatim + + @endverbatim + SetText() will generate + @verbatim + Hullaballoo! + @endverbatim + */ + void SetText( const char* inText ); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText( int value ); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText( unsigned value ); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText(int64_t value); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText(uint64_t value); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText( bool value ); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText( double value ); + /// Convenience method for setting text inside an element. See SetText() for important limitations. + void SetText( float value ); + + /** + Convenience method to query the value of a child text node. This is probably best + shown by example. Given you have a document is this form: + @verbatim + + 1 + 1.4 + + @endverbatim + + The QueryIntText() and similar functions provide a safe and easier way to get to the + "value" of x and y. + + @verbatim + int x = 0; + float y = 0; // types of x and y are contrived for example + const XMLElement* xElement = pointElement->FirstChildElement( "x" ); + const XMLElement* yElement = pointElement->FirstChildElement( "y" ); + xElement->QueryIntText( &x ); + yElement->QueryFloatText( &y ); + @endverbatim + + @returns XML_SUCCESS (0) on success, XML_CAN_NOT_CONVERT_TEXT if the text cannot be converted + to the requested type, and XML_NO_TEXT_NODE if there is no child text to query. + + */ + XMLError QueryIntText( int* ival ) const; + /// See QueryIntText() + XMLError QueryUnsignedText( unsigned* uval ) const; + /// See QueryIntText() + XMLError QueryInt64Text(int64_t* uval) const; + /// See QueryIntText() + XMLError QueryUnsigned64Text(uint64_t* uval) const; + /// See QueryIntText() + XMLError QueryBoolText( bool* bval ) const; + /// See QueryIntText() + XMLError QueryDoubleText( double* dval ) const; + /// See QueryIntText() + XMLError QueryFloatText( float* fval ) const; + + int IntText(int defaultValue = 0) const; + + /// See QueryIntText() + unsigned UnsignedText(unsigned defaultValue = 0) const; + /// See QueryIntText() + int64_t Int64Text(int64_t defaultValue = 0) const; + /// See QueryIntText() + uint64_t Unsigned64Text(uint64_t defaultValue = 0) const; + /// See QueryIntText() + bool BoolText(bool defaultValue = false) const; + /// See QueryIntText() + double DoubleText(double defaultValue = 0) const; + /// See QueryIntText() + float FloatText(float defaultValue = 0) const; + + /** + Convenience method to create a new XMLElement and add it as last (right) + child of this node. Returns the created and inserted element. + */ + XMLElement* InsertNewChildElement(const char* name); + /// See InsertNewChildElement() + XMLComment* InsertNewComment(const char* comment); + /// See InsertNewChildElement() + XMLText* InsertNewText(const char* text); + /// See InsertNewChildElement() + XMLDeclaration* InsertNewDeclaration(const char* text); + /// See InsertNewChildElement() + XMLUnknown* InsertNewUnknown(const char* text); + + + // internal: + enum ElementClosingType { + OPEN, // + CLOSED, // + CLOSING // + }; + ElementClosingType ClosingType() const { + return _closingType; + } + virtual XMLNode* ShallowClone( XMLDocument* document ) const; + virtual bool ShallowEqual( const XMLNode* compare ) const; + +protected: + char* ParseDeep( char* p, StrPair* parentEndTag, int* curLineNumPtr ); + +private: + XMLElement( XMLDocument* doc ); + virtual ~XMLElement(); + XMLElement( const XMLElement& ); // not supported + void operator=( const XMLElement& ); // not supported + + XMLAttribute* FindOrCreateAttribute( const char* name ); + char* ParseAttributes( char* p, int* curLineNumPtr ); + static void DeleteAttribute( XMLAttribute* attribute ); + XMLAttribute* CreateAttribute(); + + enum { BUF_SIZE = 200 }; + ElementClosingType _closingType; + // The attribute list is ordered; there is no 'lastAttribute' + // because the list needs to be scanned for dupes before adding + // a new attribute. + XMLAttribute* _rootAttribute; +}; + + +enum Whitespace { + PRESERVE_WHITESPACE, + COLLAPSE_WHITESPACE +}; + + +/** A Document binds together all the functionality. + It can be saved, loaded, and printed to the screen. + All Nodes are connected and allocated to a Document. + If the Document is deleted, all its Nodes are also deleted. +*/ +class TINYXML2_LIB XMLDocument : public XMLNode +{ + friend class XMLElement; + // Gives access to SetError and Push/PopDepth, but over-access for everything else. + // Wishing C++ had "internal" scope. + friend class XMLNode; + friend class XMLText; + friend class XMLComment; + friend class XMLDeclaration; + friend class XMLUnknown; +public: + /// constructor + XMLDocument( bool processEntities = true, Whitespace whitespaceMode = PRESERVE_WHITESPACE ); + ~XMLDocument(); + + virtual XMLDocument* ToDocument() { + TIXMLASSERT( this == _document ); + return this; + } + virtual const XMLDocument* ToDocument() const { + TIXMLASSERT( this == _document ); + return this; + } + + /** + Parse an XML file from a character string. + Returns XML_SUCCESS (0) on success, or + an errorID. + + You may optionally pass in the 'nBytes', which is + the number of bytes which will be parsed. If not + specified, TinyXML-2 will assume 'xml' points to a + null terminated string. + */ + XMLError Parse( const char* xml, size_t nBytes=static_cast(-1) ); + + /** + Load an XML file from disk. + Returns XML_SUCCESS (0) on success, or + an errorID. + */ + XMLError LoadFile( const char* filename ); + + /** + Load an XML file from disk. You are responsible + for providing and closing the FILE*. + + NOTE: The file should be opened as binary ("rb") + not text in order for TinyXML-2 to correctly + do newline normalization. + + Returns XML_SUCCESS (0) on success, or + an errorID. + */ + XMLError LoadFile( FILE* ); + + /** + Save the XML file to disk. + Returns XML_SUCCESS (0) on success, or + an errorID. + */ + XMLError SaveFile( const char* filename, bool compact = false ); + + /** + Save the XML file to disk. You are responsible + for providing and closing the FILE*. + + Returns XML_SUCCESS (0) on success, or + an errorID. + */ + XMLError SaveFile( FILE* fp, bool compact = false ); + + bool ProcessEntities() const { + return _processEntities; + } + Whitespace WhitespaceMode() const { + return _whitespaceMode; + } + + /** + Returns true if this document has a leading Byte Order Mark of UTF8. + */ + bool HasBOM() const { + return _writeBOM; + } + /** Sets whether to write the BOM when writing the file. + */ + void SetBOM( bool useBOM ) { + _writeBOM = useBOM; + } + + /** Return the root element of DOM. Equivalent to FirstChildElement(). + To get the first node, use FirstChild(). + */ + XMLElement* RootElement() { + return FirstChildElement(); + } + const XMLElement* RootElement() const { + return FirstChildElement(); + } + + /** Print the Document. If the Printer is not provided, it will + print to stdout. If you provide Printer, this can print to a file: + @verbatim + XMLPrinter printer( fp ); + doc.Print( &printer ); + @endverbatim + + Or you can use a printer to print to memory: + @verbatim + XMLPrinter printer; + doc.Print( &printer ); + // printer.CStr() has a const char* to the XML + @endverbatim + */ + void Print( XMLPrinter* streamer=0 ) const; + virtual bool Accept( XMLVisitor* visitor ) const; + + /** + Create a new Element associated with + this Document. The memory for the Element + is managed by the Document. + */ + XMLElement* NewElement( const char* name ); + /** + Create a new Comment associated with + this Document. The memory for the Comment + is managed by the Document. + */ + XMLComment* NewComment( const char* comment ); + /** + Create a new Text associated with + this Document. The memory for the Text + is managed by the Document. + */ + XMLText* NewText( const char* text ); + /** + Create a new Declaration associated with + this Document. The memory for the object + is managed by the Document. + + If the 'text' param is null, the standard + declaration is used.: + @verbatim + + @endverbatim + */ + XMLDeclaration* NewDeclaration( const char* text=0 ); + /** + Create a new Unknown associated with + this Document. The memory for the object + is managed by the Document. + */ + XMLUnknown* NewUnknown( const char* text ); + + /** + Delete a node associated with this document. + It will be unlinked from the DOM. + */ + void DeleteNode( XMLNode* node ); + + /// Clears the error flags. + void ClearError(); + + /// Return true if there was an error parsing the document. + bool Error() const { + return _errorID != XML_SUCCESS; + } + /// Return the errorID. + XMLError ErrorID() const { + return _errorID; + } + const char* ErrorName() const; + static const char* ErrorIDToName(XMLError errorID); + + /** Returns a "long form" error description. A hopefully helpful + diagnostic with location, line number, and/or additional info. + */ + const char* ErrorStr() const; + + /// A (trivial) utility function that prints the ErrorStr() to stdout. + void PrintError() const; + + /// Return the line where the error occurred, or zero if unknown. + int ErrorLineNum() const + { + return _errorLineNum; + } + + /// Clear the document, resetting it to the initial state. + void Clear(); + + /** + Copies this document to a target document. + The target will be completely cleared before the copy. + If you want to copy a sub-tree, see XMLNode::DeepClone(). + + NOTE: that the 'target' must be non-null. + */ + void DeepCopy(XMLDocument* target) const; + + // internal + char* Identify( char* p, XMLNode** node ); + + // internal + void MarkInUse(const XMLNode* const); + + virtual XMLNode* ShallowClone( XMLDocument* /*document*/ ) const { + return 0; + } + virtual bool ShallowEqual( const XMLNode* /*compare*/ ) const { + return false; + } + +private: + XMLDocument( const XMLDocument& ); // not supported + void operator=( const XMLDocument& ); // not supported + + bool _writeBOM; + bool _processEntities; + XMLError _errorID; + Whitespace _whitespaceMode; + mutable StrPair _errorStr; + int _errorLineNum; + char* _charBuffer; + int _parseCurLineNum; + int _parsingDepth; + // Memory tracking does add some overhead. + // However, the code assumes that you don't + // have a bunch of unlinked nodes around. + // Therefore it takes less memory to track + // in the document vs. a linked list in the XMLNode, + // and the performance is the same. + DynArray _unlinked; + + MemPoolT< sizeof(XMLElement) > _elementPool; + MemPoolT< sizeof(XMLAttribute) > _attributePool; + MemPoolT< sizeof(XMLText) > _textPool; + MemPoolT< sizeof(XMLComment) > _commentPool; + + static const char* _errorNames[XML_ERROR_COUNT]; + + void Parse(); + + void SetError( XMLError error, int lineNum, const char* format, ... ); + + // Something of an obvious security hole, once it was discovered. + // Either an ill-formed XML or an excessively deep one can overflow + // the stack. Track stack depth, and error out if needed. + class DepthTracker { + public: + explicit DepthTracker(XMLDocument * document) { + this->_document = document; + document->PushDepth(); + } + ~DepthTracker() { + _document->PopDepth(); + } + private: + XMLDocument * _document; + }; + void PushDepth(); + void PopDepth(); + + template + NodeType* CreateUnlinkedNode( MemPoolT& pool ); +}; + +template +inline NodeType* XMLDocument::CreateUnlinkedNode( MemPoolT& pool ) +{ + TIXMLASSERT( sizeof( NodeType ) == PoolElementSize ); + TIXMLASSERT( sizeof( NodeType ) == pool.ItemSize() ); + NodeType* returnNode = new (pool.Alloc()) NodeType( this ); + TIXMLASSERT( returnNode ); + returnNode->_memPool = &pool; + + _unlinked.Push(returnNode); + return returnNode; +} + +/** + A XMLHandle is a class that wraps a node pointer with null checks; this is + an incredibly useful thing. Note that XMLHandle is not part of the TinyXML-2 + DOM structure. It is a separate utility class. + + Take an example: + @verbatim + + + + + + + @endverbatim + + Assuming you want the value of "attributeB" in the 2nd "Child" element, it's very + easy to write a *lot* of code that looks like: + + @verbatim + XMLElement* root = document.FirstChildElement( "Document" ); + if ( root ) + { + XMLElement* element = root->FirstChildElement( "Element" ); + if ( element ) + { + XMLElement* child = element->FirstChildElement( "Child" ); + if ( child ) + { + XMLElement* child2 = child->NextSiblingElement( "Child" ); + if ( child2 ) + { + // Finally do something useful. + @endverbatim + + And that doesn't even cover "else" cases. XMLHandle addresses the verbosity + of such code. A XMLHandle checks for null pointers so it is perfectly safe + and correct to use: + + @verbatim + XMLHandle docHandle( &document ); + XMLElement* child2 = docHandle.FirstChildElement( "Document" ).FirstChildElement( "Element" ).FirstChildElement().NextSiblingElement(); + if ( child2 ) + { + // do something useful + @endverbatim + + Which is MUCH more concise and useful. + + It is also safe to copy handles - internally they are nothing more than node pointers. + @verbatim + XMLHandle handleCopy = handle; + @endverbatim + + See also XMLConstHandle, which is the same as XMLHandle, but operates on const objects. +*/ +class TINYXML2_LIB XMLHandle +{ +public: + /// Create a handle from any node (at any depth of the tree.) This can be a null pointer. + explicit XMLHandle( XMLNode* node ) : _node( node ) { + } + /// Create a handle from a node. + explicit XMLHandle( XMLNode& node ) : _node( &node ) { + } + /// Copy constructor + XMLHandle( const XMLHandle& ref ) : _node( ref._node ) { + } + /// Assignment + XMLHandle& operator=( const XMLHandle& ref ) { + _node = ref._node; + return *this; + } + + /// Get the first child of this handle. + XMLHandle FirstChild() { + return XMLHandle( _node ? _node->FirstChild() : 0 ); + } + /// Get the first child element of this handle. + XMLHandle FirstChildElement( const char* name = 0 ) { + return XMLHandle( _node ? _node->FirstChildElement( name ) : 0 ); + } + /// Get the last child of this handle. + XMLHandle LastChild() { + return XMLHandle( _node ? _node->LastChild() : 0 ); + } + /// Get the last child element of this handle. + XMLHandle LastChildElement( const char* name = 0 ) { + return XMLHandle( _node ? _node->LastChildElement( name ) : 0 ); + } + /// Get the previous sibling of this handle. + XMLHandle PreviousSibling() { + return XMLHandle( _node ? _node->PreviousSibling() : 0 ); + } + /// Get the previous sibling element of this handle. + XMLHandle PreviousSiblingElement( const char* name = 0 ) { + return XMLHandle( _node ? _node->PreviousSiblingElement( name ) : 0 ); + } + /// Get the next sibling of this handle. + XMLHandle NextSibling() { + return XMLHandle( _node ? _node->NextSibling() : 0 ); + } + /// Get the next sibling element of this handle. + XMLHandle NextSiblingElement( const char* name = 0 ) { + return XMLHandle( _node ? _node->NextSiblingElement( name ) : 0 ); + } + + /// Safe cast to XMLNode. This can return null. + XMLNode* ToNode() { + return _node; + } + /// Safe cast to XMLElement. This can return null. + XMLElement* ToElement() { + return ( _node ? _node->ToElement() : 0 ); + } + /// Safe cast to XMLText. This can return null. + XMLText* ToText() { + return ( _node ? _node->ToText() : 0 ); + } + /// Safe cast to XMLUnknown. This can return null. + XMLUnknown* ToUnknown() { + return ( _node ? _node->ToUnknown() : 0 ); + } + /// Safe cast to XMLDeclaration. This can return null. + XMLDeclaration* ToDeclaration() { + return ( _node ? _node->ToDeclaration() : 0 ); + } + +private: + XMLNode* _node; +}; + + +/** + A variant of the XMLHandle class for working with const XMLNodes and Documents. It is the + same in all regards, except for the 'const' qualifiers. See XMLHandle for API. +*/ +class TINYXML2_LIB XMLConstHandle +{ +public: + explicit XMLConstHandle( const XMLNode* node ) : _node( node ) { + } + explicit XMLConstHandle( const XMLNode& node ) : _node( &node ) { + } + XMLConstHandle( const XMLConstHandle& ref ) : _node( ref._node ) { + } + + XMLConstHandle& operator=( const XMLConstHandle& ref ) { + _node = ref._node; + return *this; + } + + const XMLConstHandle FirstChild() const { + return XMLConstHandle( _node ? _node->FirstChild() : 0 ); + } + const XMLConstHandle FirstChildElement( const char* name = 0 ) const { + return XMLConstHandle( _node ? _node->FirstChildElement( name ) : 0 ); + } + const XMLConstHandle LastChild() const { + return XMLConstHandle( _node ? _node->LastChild() : 0 ); + } + const XMLConstHandle LastChildElement( const char* name = 0 ) const { + return XMLConstHandle( _node ? _node->LastChildElement( name ) : 0 ); + } + const XMLConstHandle PreviousSibling() const { + return XMLConstHandle( _node ? _node->PreviousSibling() : 0 ); + } + const XMLConstHandle PreviousSiblingElement( const char* name = 0 ) const { + return XMLConstHandle( _node ? _node->PreviousSiblingElement( name ) : 0 ); + } + const XMLConstHandle NextSibling() const { + return XMLConstHandle( _node ? _node->NextSibling() : 0 ); + } + const XMLConstHandle NextSiblingElement( const char* name = 0 ) const { + return XMLConstHandle( _node ? _node->NextSiblingElement( name ) : 0 ); + } + + + const XMLNode* ToNode() const { + return _node; + } + const XMLElement* ToElement() const { + return ( _node ? _node->ToElement() : 0 ); + } + const XMLText* ToText() const { + return ( _node ? _node->ToText() : 0 ); + } + const XMLUnknown* ToUnknown() const { + return ( _node ? _node->ToUnknown() : 0 ); + } + const XMLDeclaration* ToDeclaration() const { + return ( _node ? _node->ToDeclaration() : 0 ); + } + +private: + const XMLNode* _node; +}; + + +/** + Printing functionality. The XMLPrinter gives you more + options than the XMLDocument::Print() method. + + It can: + -# Print to memory. + -# Print to a file you provide. + -# Print XML without a XMLDocument. + + Print to Memory + + @verbatim + XMLPrinter printer; + doc.Print( &printer ); + SomeFunction( printer.CStr() ); + @endverbatim + + Print to a File + + You provide the file pointer. + @verbatim + XMLPrinter printer( fp ); + doc.Print( &printer ); + @endverbatim + + Print without a XMLDocument + + When loading, an XML parser is very useful. However, sometimes + when saving, it just gets in the way. The code is often set up + for streaming, and constructing the DOM is just overhead. + + The Printer supports the streaming case. The following code + prints out a trivially simple XML file without ever creating + an XML document. + + @verbatim + XMLPrinter printer( fp ); + printer.OpenElement( "foo" ); + printer.PushAttribute( "foo", "bar" ); + printer.CloseElement(); + @endverbatim +*/ +class TINYXML2_LIB XMLPrinter : public XMLVisitor +{ +public: + /** Construct the printer. If the FILE* is specified, + this will print to the FILE. Else it will print + to memory, and the result is available in CStr(). + If 'compact' is set to true, then output is created + with only required whitespace and newlines. + */ + XMLPrinter( FILE* file=0, bool compact = false, int depth = 0 ); + virtual ~XMLPrinter() {} + + /** If streaming, write the BOM and declaration. */ + void PushHeader( bool writeBOM, bool writeDeclaration ); + /** If streaming, start writing an element. + The element must be closed with CloseElement() + */ + void OpenElement( const char* name, bool compactMode=false ); + /// If streaming, add an attribute to an open element. + void PushAttribute( const char* name, const char* value ); + void PushAttribute( const char* name, int value ); + void PushAttribute( const char* name, unsigned value ); + void PushAttribute( const char* name, int64_t value ); + void PushAttribute( const char* name, uint64_t value ); + void PushAttribute( const char* name, bool value ); + void PushAttribute( const char* name, double value ); + /// If streaming, close the Element. + virtual void CloseElement( bool compactMode=false ); + + /// Add a text node. + void PushText( const char* text, bool cdata=false ); + /// Add a text node from an integer. + void PushText( int value ); + /// Add a text node from an unsigned. + void PushText( unsigned value ); + /// Add a text node from a signed 64bit integer. + void PushText( int64_t value ); + /// Add a text node from an unsigned 64bit integer. + void PushText( uint64_t value ); + /// Add a text node from a bool. + void PushText( bool value ); + /// Add a text node from a float. + void PushText( float value ); + /// Add a text node from a double. + void PushText( double value ); + + /// Add a comment + void PushComment( const char* comment ); + + void PushDeclaration( const char* value ); + void PushUnknown( const char* value ); + + virtual bool VisitEnter( const XMLDocument& /*doc*/ ); + virtual bool VisitExit( const XMLDocument& /*doc*/ ) { + return true; + } + + virtual bool VisitEnter( const XMLElement& element, const XMLAttribute* attribute ); + virtual bool VisitExit( const XMLElement& element ); + + virtual bool Visit( const XMLText& text ); + virtual bool Visit( const XMLComment& comment ); + virtual bool Visit( const XMLDeclaration& declaration ); + virtual bool Visit( const XMLUnknown& unknown ); + + /** + If in print to memory mode, return a pointer to + the XML file in memory. + */ + const char* CStr() const { + return _buffer.Mem(); + } + /** + If in print to memory mode, return the size + of the XML file in memory. (Note the size returned + includes the terminating null.) + */ + int CStrSize() const { + return _buffer.Size(); + } + /** + If in print to memory mode, reset the buffer to the + beginning. + */ + void ClearBuffer( bool resetToFirstElement = true ) { + _buffer.Clear(); + _buffer.Push(0); + _firstElement = resetToFirstElement; + } + +protected: + virtual bool CompactMode( const XMLElement& ) { return _compactMode; } + + /** Prints out the space before an element. You may override to change + the space and tabs used. A PrintSpace() override should call Print(). + */ + virtual void PrintSpace( int depth ); + virtual void Print( const char* format, ... ); + virtual void Write( const char* data, size_t size ); + virtual void Putc( char ch ); + + inline void Write(const char* data) { Write(data, strlen(data)); } + + void SealElementIfJustOpened(); + bool _elementJustOpened; + DynArray< const char*, 10 > _stack; + +private: + /** + Prepares to write a new node. This includes sealing an element that was + just opened, and writing any whitespace necessary if not in compact mode. + */ + void PrepareForNewNode( bool compactMode ); + void PrintString( const char*, bool restrictedEntitySet ); // prints out, after detecting entities. + + bool _firstElement; + FILE* _fp; + int _depth; + int _textDepth; + bool _processEntities; + bool _compactMode; + + enum { + ENTITY_RANGE = 64, + BUF_SIZE = 200 + }; + bool _entityFlag[ENTITY_RANGE]; + bool _restrictedEntityFlag[ENTITY_RANGE]; + + DynArray< char, 20 > _buffer; + + // Prohibit cloning, intentionally not implemented + XMLPrinter( const XMLPrinter& ); + XMLPrinter& operator=( const XMLPrinter& ); +}; + + +} // tinyxml2 + +#if defined(_MSC_VER) +# pragma warning(pop) +#endif + +#endif // TINYXML2_INCLUDED \ No newline at end of file