From 5a9f91b425c0d1fcc6fcc43ff4c17e15e410d1ac Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Mon, 26 Jun 2023 18:23:47 +0800 Subject: [PATCH 1/8] =?UTF-8?q?feat:=203.9.5.81=20=E5=9F=BA=E7=A1=80?= =?UTF-8?q?=E6=94=B6=E5=8F=91=E5=8A=9F=E8=83=BD?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- CMakeLists.txt | 38 +- doc/3.9.5.81.md | 225 + source/CMakeLists.txt | 8 +- source/{ConsoleApplication.cc => injector.cc} | 22 +- src/base64.cpp | 312 + src/base64.h | 35 + src/config.cc | 14 + src/config.h | 17 + src/dllMain.cc | 28 + src/export.asm | 61 + src/export.h | 8 + src/global_context.cc | 37 + src/global_context.h | 41 + src/hooks.cc | 178 + src/hooks.h | 15 + src/http_client.cc | 65 + src/http_client.h | 24 + src/http_server.cc | 54 + src/http_server.h | 29 + src/http_server_callback.cc | 154 + src/http_server_callback.h | 17 + src/log.cc | 21 + src/log.h | 15 + src/lz4.c | 2751 ++++++ src/lz4.h | 862 ++ src/manager.cc | 218 + src/manager.h | 18 + src/mongoose.c | 8413 +++++++++++++++++ src/mongoose.h | 1729 ++++ src/pch.h | 26 + src/singleton.h | 21 + src/thread_pool.cc | 48 + src/thread_pool.h | 23 + src/tinyxml2.cpp | 2994 ++++++ src/tinyxml2.h | 2380 +++++ src/utils.cc | 305 + src/utils.h | 87 + src/wechat_function.h | 98 + 38 files changed, 21363 insertions(+), 28 deletions(-) create mode 100644 doc/3.9.5.81.md rename source/{ConsoleApplication.cc => injector.cc} (99%) create mode 100644 src/base64.cpp create mode 100644 src/base64.h create mode 100644 src/config.cc create mode 100644 src/config.h create mode 100644 src/dllMain.cc create mode 100644 src/export.asm create mode 100644 src/export.h create mode 100644 src/global_context.cc create mode 100644 src/global_context.h create mode 100644 src/hooks.cc create mode 100644 src/hooks.h create mode 100644 src/http_client.cc create mode 100644 src/http_client.h create mode 100644 src/http_server.cc create mode 100644 src/http_server.h create mode 100644 src/http_server_callback.cc create mode 100644 src/http_server_callback.h create mode 100644 src/log.cc create mode 100644 src/log.h create mode 100644 src/lz4.c create mode 100644 src/lz4.h create mode 100644 src/manager.cc create mode 100644 src/manager.h create mode 100644 src/mongoose.c create mode 100644 src/mongoose.h create mode 100644 src/pch.h create mode 100644 src/singleton.h create mode 100644 src/thread_pool.cc create mode 100644 src/thread_pool.h create mode 100644 src/tinyxml2.cpp create mode 100644 src/tinyxml2.h create mode 100644 src/utils.cc create mode 100644 src/utils.h create mode 100644 src/wechat_function.h diff --git a/CMakeLists.txt b/CMakeLists.txt index 3c264f8..5487e61 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1,36 +1,48 @@ cmake_minimum_required(VERSION 3.0.0) +# include(ExternalProject) project(wxhelper VERSION 1.0.0) +enable_language(ASM_MASM) + + + +# SET(CMAKE_ASM_NASM_FLAGS "-w0") set(CMAKE_CXX_STANDARD 17) set(CMAKE_CXX_STANDARD_REQUIRED True) +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 ${PROJECT_SOURCE_DIR}/src/*.cpp) +set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /D '_UNICODE' /D 'UNICODE' ") + +file(GLOB CPP_FILES ${PROJECT_SOURCE_DIR}/src/*.cc ${PROJECT_SOURCE_DIR}/src/*.cpp ${PROJECT_SOURCE_DIR}/src/*.c ) + +file(GLOB ASM_FILES ${PROJECT_SOURCE_DIR}/src/*.asm ) + +include_directories(${VCPKG_INSTALLED_DIR}/x64-windows/include ${PROJECT_SOURCE_DIR}/spdlog/include ${DETOURS_INCLUDE_DIRS}) +# include_directories(${VCPKG_INSTALLED_DIR}/x64-windows/include ${PROJECT_SOURCE_DIR}/spdlog/include ) -include_directories(c:/soft/vcpkg/installed/x86-windows/include) +add_subdirectory(spdlog) +add_subdirectory(source) -# add_subdirectory(3rd) -# add_subdirectory(source) +# find_package(spdlog CONFIG REQUIRED) find_package(nlohmann_json CONFIG REQUIRED) -find_package(unofficial-mongoose CONFIG REQUIRED) -# find_package(spdlog CONFIG REQUIRED) -# find_package(minhook CONFIG REQUIRED) + +find_path(DETOURS_INCLUDE_DIRS "detours/detours.h") +find_library(DETOURS_LIBRARY detours REQUIRED) -add_library(wxhelper SHARED ${CPP_FILES} ) +add_library(wxhelper SHARED ${CPP_FILES} ${ASM_FILES} ) -#target_include_directories(wxhelper PUBLIC 3rd/mongoose ) target_link_libraries(wxhelper PRIVATE nlohmann_json::nlohmann_json) -target_link_libraries(wxhelper PRIVATE unofficial::mongoose::mongoose) -# target_link_libraries(wxhelper PRIVATE spdlog::spdlog spdlog::spdlog_header_only) -# target_link_libraries(wxhelper PRIVATE minhook::minhook) +target_link_libraries(wxhelper PRIVATE spdlog::spdlog spdlog::spdlog_header_only) +target_link_libraries(wxhelper PRIVATE ${DETOURS_LIBRARY}) + SET_TARGET_PROPERTIES(wxhelper PROPERTIES LINKER_LANGUAGE C ARCHIVE_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/lib diff --git a/doc/3.9.5.81.md b/doc/3.9.5.81.md new file mode 100644 index 0000000..88ad50d --- /dev/null +++ b/doc/3.9.5.81.md @@ -0,0 +1,225 @@ +#### 编译构建 +环境: +cl.exe目录= c:/cl.exe +ml64.exe目录 =c:/ml64.exe +vcpkg目录 = c:/vcpkg +wxhelper目录 = c:/wxhelper +``` + +vcpkg install detours:x64-windows +vcpkg install nlohmann-json:x64-windows + +cd wxhelper +mkdir build +cd build +cmake -DCMAKE_C_COMPILER=cl.exe \ +-DCMAKE_CXX_COMPILER=cl.exe \ +-DCMAKE_ASM_MASM_COMPILER=ml64.exe \ +-DCMAKE_BUILD_TYPE=Debug \ +-DCMAKE_INSTALL_PREFIX=C:/wxhelper/install/x64-debug \ +-DCMAKE_TOOLCHAIN_FILE:FILEPATH=C:/vcpkg/scripts/buildsystems/vcpkg.cmake \ +-SC:c:/wxhelper \ +-BC:c:/wxhelper/build/x64-debug\ +-G Ninja +cmake --build .. +``` +如果有错误按错误提示修正即可。 + +## 3.9.5.81版本,http接口文档,文档仅供参考。 + +### 简单说明: + 所有接口只支持post方法。 + 全部使用json格式。 + 格式: http://host:port/api/xxxx + host: 绑定的host + port: 监听的端口 + xxxx: 对应的功能路径 + 返回结构的json格式: + ``` javascript + { + "code": 1, + "data": {}, + "msg": "success" +} +``` +code: 错误码 +msg: 成功/错误信息 +data: 接口返回的数据 + + +#### 0.检查微信登录** +###### 接口功能 +> 检查微信是否登录 + +###### 接口地址 +> [/api/checkLogin](/api/checkLogin) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| + + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,1 成功, 0失败| +|result|string|成功提示| +|data|string|响应内容| + +###### 接口示例 +入参: +``` javascript +``` +响应: +``` javascript +{ + "code": 1, + "result": "ok" +} +``` + +#### 1.获取登录用户信息** +###### 接口功能 +> 获取登录用户信息 + +###### 接口地址 +> [/api/userInfo](/api/userInfo) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| + + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,1 成功, 0失败| +|result|string|成功提示| +|data|object|响应内容| +|account|string|账号| +|headImage|string|头像| +|city|string|城市| +|country|string|国家| +|currentDataPath|string|当前数据目录,登录的账号目录| +|dataSavePath|string|微信保存目录| +|mobile|string|手机| +|name|string|昵称| +|province|string|省| +|wxid|string|wxid| +|signature|string|个人签名| +|dbKey|string|数据库的SQLCipher的加密key,可以使用该key配合decrypt.py解密数据库 + +###### 接口示例 +入参: +``` javascript +``` +响应: +``` javascript +{ + "code": 1, + "data": { + "account": "xxx", + "city": "Zhengzhou", + "country": "CN", + "currentDataPath": "C:\\WeChat Files\\wxid_xxx\\", + "dataSavePath": "C:\\wechatDir\\WeChat Files\\", + "dbKey": "965715e30e474da09250cb5aa047e3940ffa1c8f767c4263b132bb512933db49", + "headImage": "https://wx.qlogo.cn/mmhead/ver_1/MiblV0loY0GILewQ4u2121", + "mobile": "13949175447", + "name": "xxx", + "province": "Henan", + "signature": "xxx", + "wxid": "wxid_22222" + }, + "msg": "success" +} +``` + + + +#### 2.发送文本消息** +###### 接口功能 +> 发送文本消息 + +###### 接口地址 +> [/api/sendTextMsg](/api/sendTextMsg) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| +|wxid |true |string| 接收人wxid | +|msg|true |string|消息文本内容| + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,不为0成功, 0失败| +|result|string|成功提示| + + +###### 接口示例 + +入参: +``` javascript +{ + "wxid": "filehelper", + "msg": "1112222" +} +``` +响应: +``` javascript +{"code":345686720,"msg":"success","data":null} +``` + +#### 3.hook消息** +###### 接口功能 +> hook接收文本消息,图片消息,群消息.该接口将hook的消息通过tcp回传给本地的端口。 +enableHttp=1时,使用url,timeout参数配置服务端的接收地址。请求为post,Content-Type 为json。 +enableHttp=0时,使用ip,port的tcp服务回传消息。 + +###### 接口地址 +> [/api/hookSyncMsg](/api/hookSyncMsg) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| +|port |true |string| 本地服务端端口,用来接收消息内容 | +|ip |true |string| 服务端ip地址,用来接收消息内容,可以是任意ip,即tcp客户端连接的服务端的ip| +|url |true |string| http的请求地址,enableHttp=1时,不能为空 | +|timeout |true |string| 超时时间,单位ms| +|enableHttp |true |number| 0/1 :1.启用http 0.不启用http| + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,1成功, 0失败| +|result|string|成功提示| + + +###### 接口示例 +入参: +``` javascript +{ + "port": "19099" + "ip":"127.0.0.1", + "url":"http://localhost:8080", + "timeout":"3000", + "enableHttp":"0" +} +``` +响应: +``` javascript +{"code":200,"msg":"success","data":null} +``` \ No newline at end of file diff --git a/source/CMakeLists.txt b/source/CMakeLists.txt index 9e36448..a59d1c5 100644 --- a/source/CMakeLists.txt +++ b/source/CMakeLists.txt @@ -1,5 +1,5 @@ cmake_minimum_required(VERSION 3.0.0) -project(ConsoleApplication VERSION 1.0.0) +project(injector VERSION 1.0.0) set(CMAKE_CXX_STANDARD 17) @@ -9,12 +9,12 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /D '_UNICODE' /D 'UNICODE'") file(GLOB INJECT_CPP_FILES ${PROJECT_SOURCE_DIR}/*.cc ${PROJECT_SOURCE_DIR}/*.cpp) -add_executable (ConsoleApplication ${INJECT_CPP_FILES}) +add_executable (injector ${INJECT_CPP_FILES}) -SET_TARGET_PROPERTIES(ConsoleApplication PROPERTIES LINKER_LANGUAGE C +SET_TARGET_PROPERTIES(injector PROPERTIES LINKER_LANGUAGE C ARCHIVE_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin RUNTIME_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin - OUTPUT_NAME "ConsoleApplication" + OUTPUT_NAME "injector" PREFIX "") \ No newline at end of file diff --git a/source/ConsoleApplication.cc b/source/injector.cc similarity index 99% rename from source/ConsoleApplication.cc rename to source/injector.cc index c86dc6d..c009272 100644 --- a/source/ConsoleApplication.cc +++ b/source/injector.cc @@ -570,7 +570,7 @@ HMODULE GetDLLHandle(wchar_t* wDllName, DWORD dPid) return result; } -BOOL EnableDebugPrivilege() +BOOL EnableDebugPrivilege() { HANDLE TokenHandle = NULL; TOKEN_PRIVILEGES TokenPrivilege; @@ -649,7 +649,7 @@ LPVOID FillAsmCode(HANDLE handle) { int InjectDllAndStartHttp(wchar_t* szPName, wchar_t* szDllPath, DWORD port) { - if(!EnableDebugPrivilege()){ + if (!EnableDebugPrivilege()) { return 0; } int result = 0; @@ -662,7 +662,7 @@ int InjectDllAndStartHttp(wchar_t* szPName, wchar_t* szDllPath, DWORD port) size_t ulDllLength; wchar_t* dllName = (wchar_t*)L"wxhelper.dll"; size_t dllNameLen = wcslen(dllName) * 2 + 2; - char* funcName = (char* )"http_start"; + char* funcName = (char*)"http_start"; size_t funcNameLen = strlen(funcName) + 1; HANDLE hStartHttp = NULL; @@ -773,7 +773,7 @@ error: int InjectDllAndStartHttpByPid(unsigned int pid, wchar_t* szDllPath, DWORD port) { - if(!EnableDebugPrivilege()){ + if (!EnableDebugPrivilege()) { return 0; } int result = 0; @@ -785,7 +785,7 @@ int InjectDllAndStartHttpByPid(unsigned int pid, wchar_t* szDllPath, DWORD port size_t ulDllLength; wchar_t* dllName = (wchar_t*)L"wxhelper.dll"; size_t dllNameLen = wcslen(dllName) * 2 + 2; - char* funcName = (char* )"http_start"; + char* funcName = (char*)"http_start"; size_t funcNameLen = strlen(funcName) + 1; HANDLE hStartHttp = NULL; @@ -895,7 +895,7 @@ error: int InjectDll(wchar_t* szPName, wchar_t* szDllPath) { - if(!EnableDebugPrivilege()){ + if (!EnableDebugPrivilege()) { return 0; } int result = 0; @@ -949,7 +949,7 @@ int InjectDll(wchar_t* szPName, wchar_t* szDllPath) int InjectDllByPid(unsigned int pid, wchar_t* szDllPath) { - if(!EnableDebugPrivilege()){ + if (!EnableDebugPrivilege()) { return 0; } int result = 0; @@ -981,7 +981,7 @@ int InjectDllByPid(unsigned int pid, wchar_t* szDllPath) OutputDebugStringA("[DBG] dll inject success"); printf("dll inject success"); printf("dll path : %s ", szDllPath); - printf("pid : %d ", pid); + printf("dll path : %d ", pid); result = 1; } else @@ -1052,7 +1052,7 @@ int main(int argc, char** argv) int port = 0; ULONG pid = 0; - unsigned int injectPid =0; + unsigned int injectPid = 0; while ((param = getopt(argc, argv, "i:p:u:d:m:P:I:h")) != -1) { @@ -1105,7 +1105,7 @@ int main(int argc, char** argv) } if (injectPid != 0 && cDllPath[0] != 0) { - if(cDllPath[0] != '\0') + if (cDllPath[0] != '\0') { if (port == 0) { std::wstring wsPath = Utf8ToUnicode(cDllPath); @@ -1120,7 +1120,7 @@ int main(int argc, char** argv) } } } - + if (cInjectprogram[0] != 0 && cDllPath[0] != 0) { diff --git a/src/base64.cpp b/src/base64.cpp new file mode 100644 index 0000000..a9b11af --- /dev/null +++ b/src/base64.cpp @@ -0,0 +1,312 @@ +#include "pch.h" +/* + base64.cpp and base64.h + + base64 encoding and decoding with C++. + More information at + https://renenyffenegger.ch/notes/development/Base64/Encoding-and-decoding-base-64-with-cpp + + Version: 2.rc.08 (release candidate) + + Copyright (C) 2004-2017, 2020, 2021 Ren�� Nyffenegger + + This source code is provided 'as-is', without any express or implied + warranty. In no event will the author 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 source code must not be misrepresented; you must not + claim that you wrote the original source code. If you use this source code + 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 source code. + + 3. This notice may not be removed or altered from any source distribution. + + Ren�� Nyffenegger rene.nyffenegger@adp-gmbh.ch + +*/ + +#include "base64.h" + +#include +#include + +// +// Depending on the url parameter in base64_chars, one of +// two sets of base64 characters needs to be chosen. +// They differ in their last two characters. +// +static const char *base64_chars[2] = { + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "abcdefghijklmnopqrstuvwxyz" + "0123456789" + "+/", + + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "abcdefghijklmnopqrstuvwxyz" + "0123456789" + "-_"}; + +static unsigned int pos_of_char(const unsigned char chr) +{ + // + // Return the position of chr within base64_encode() + // + + if (chr >= 'A' && chr <= 'Z') + return chr - 'A'; + else if (chr >= 'a' && chr <= 'z') + return chr - 'a' + ('Z' - 'A') + 1; + else if (chr >= '0' && chr <= '9') + return chr - '0' + ('Z' - 'A') + ('z' - 'a') + 2; + else if (chr == '+' || chr == '-') + return 62; // Be liberal with input and accept both url ('-') and non-url ('+') base 64 characters ( + else if (chr == '/' || chr == '_') + return 63; // Ditto for '/' and '_' + else + // + // 2020-10-23: Throw std::exception rather than const char* + //(Pablo Martin-Gomez, https://github.com/Bouska) + // + throw std::runtime_error("Input is not valid base64-encoded data."); +} + +static std::string insert_linebreaks(std::string str, size_t distance) +{ + // + // Provided by https://github.com/JomaCorpFX, adapted by me. + // + if (!str.length()) + { + return ""; + } + + size_t pos = distance; + + while (pos < str.size()) + { + str.insert(pos, "\n"); + pos += distance + 1; + } + + return str; +} + +template +static std::string encode_with_line_breaks(String s) +{ + return insert_linebreaks(base64_encode(s, false), line_length); +} + +template +static std::string encode_pem(String s) +{ + return encode_with_line_breaks(s); +} + +template +static std::string encode_mime(String s) +{ + return encode_with_line_breaks(s); +} + +template +static std::string encode(String s, bool url) +{ + return base64_encode(reinterpret_cast(s.data()), s.length(), url); +} + +std::string base64_encode(unsigned char const *bytes_to_encode, size_t in_len, bool url) +{ + + size_t len_encoded = (in_len + 2) / 3 * 4; + + unsigned char trailing_char = url ? '.' : '='; + + // + // Choose set of base64 characters. They differ + // for the last two positions, depending on the url + // parameter. + // A bool (as is the parameter url) is guaranteed + // to evaluate to either 0 or 1 in C++ therefore, + // the correct character set is chosen by subscripting + // base64_chars with url. + // + const char *base64_chars_ = base64_chars[url]; + + std::string ret; + ret.reserve(len_encoded); + + unsigned int pos = 0; + + while (pos < in_len) + { + ret.push_back(base64_chars_[(bytes_to_encode[pos + 0] & 0xfc) >> 2]); + + if (pos + 1 < in_len) + { + ret.push_back(base64_chars_[((bytes_to_encode[pos + 0] & 0x03) << 4) + ((bytes_to_encode[pos + 1] & 0xf0) >> 4)]); + + if (pos + 2 < in_len) + { + ret.push_back(base64_chars_[((bytes_to_encode[pos + 1] & 0x0f) << 2) + ((bytes_to_encode[pos + 2] & 0xc0) >> 6)]); + ret.push_back(base64_chars_[bytes_to_encode[pos + 2] & 0x3f]); + } + else + { + ret.push_back(base64_chars_[(bytes_to_encode[pos + 1] & 0x0f) << 2]); + ret.push_back(trailing_char); + } + } + else + { + + ret.push_back(base64_chars_[(bytes_to_encode[pos + 0] & 0x03) << 4]); + ret.push_back(trailing_char); + ret.push_back(trailing_char); + } + + pos += 3; + } + + return ret; +} + +template +static std::string decode(String encoded_string, bool remove_linebreaks) +{ + // + // decode(��) is templated so that it can be used with String = const std::string& + // or std::string_view (requires at least C++17) + // + + if (encoded_string.empty()) + return std::string(); + + if (remove_linebreaks) + { + + std::string copy(encoded_string); + + copy.erase(std::remove(copy.begin(), copy.end(), '\n'), copy.end()); + + return base64_decode(copy, false); + } + + size_t length_of_string = encoded_string.length(); + size_t pos = 0; + + // + // The approximate length (bytes) of the decoded string might be one or + // two bytes smaller, depending on the amount of trailing equal signs + // in the encoded string. This approximation is needed to reserve + // enough space in the string to be returned. + // + size_t approx_length_of_decoded_string = length_of_string / 4 * 3; + std::string ret; + ret.reserve(approx_length_of_decoded_string); + + while (pos < length_of_string) + { + // + // Iterate over encoded input string in chunks. The size of all + // chunks except the last one is 4 bytes. + // + // The last chunk might be padded with equal signs or dots + // in order to make it 4 bytes in size as well, but this + // is not required as per RFC 2045. + // + // All chunks except the last one produce three output bytes. + // + // The last chunk produces at least one and up to three bytes. + // + + size_t pos_of_char_1 = pos_of_char(encoded_string[pos + 1]); + + // + // Emit the first output byte that is produced in each chunk: + // + ret.push_back(static_cast(((pos_of_char(encoded_string[pos + 0])) << 2) + ((pos_of_char_1 & 0x30) >> 4))); + + if ((pos + 2 < length_of_string) && // Check for data that is not padded with equal signs (which is allowed by RFC 2045) + encoded_string[pos + 2] != '=' && + encoded_string[pos + 2] != '.' // accept URL-safe base 64 strings, too, so check for '.' also. + ) + { + // + // Emit a chunk's second byte (which might not be produced in the last chunk). + // + unsigned int pos_of_char_2 = pos_of_char(encoded_string[pos + 2]); + ret.push_back(static_cast(((pos_of_char_1 & 0x0f) << 4) + ((pos_of_char_2 & 0x3c) >> 2))); + + if ((pos + 3 < length_of_string) && + encoded_string[pos + 3] != '=' && + encoded_string[pos + 3] != '.') + { + // + // Emit a chunk's third byte (which might not be produced in the last chunk). + // + ret.push_back(static_cast(((pos_of_char_2 & 0x03) << 6) + pos_of_char(encoded_string[pos + 3]))); + } + } + + pos += 4; + } + + return ret; +} + +std::string base64_decode(std::string const &s, bool remove_linebreaks) +{ + return decode(s, remove_linebreaks); +} + +std::string base64_encode(std::string const &s, bool url) +{ + return encode(s, url); +} + +std::string base64_encode_pem(std::string const &s) +{ + return encode_pem(s); +} + +std::string base64_encode_mime(std::string const &s) +{ + return encode_mime(s); +} + +#if __cplusplus >= 201703L +// +// Interface with std::string_view rather than const std::string& +// Requires C++17 +// Provided by Yannic Bonenberger (https://github.com/Yannic) +// + +std::string base64_encode(std::string_view s, bool url) +{ + return encode(s, url); +} + +std::string base64_encode_pem(std::string_view s) +{ + return encode_pem(s); +} + +std::string base64_encode_mime(std::string_view s) +{ + return encode_mime(s); +} + +std::string base64_decode(std::string_view s, bool remove_linebreaks) +{ + return decode(s, remove_linebreaks); +} + +#endif // __cplusplus >= 201703L \ No newline at end of file diff --git a/src/base64.h b/src/base64.h new file mode 100644 index 0000000..0e9b017 --- /dev/null +++ b/src/base64.h @@ -0,0 +1,35 @@ +// +// base64 encoding and decoding with C++. +// Version: 2.rc.08 (release candidate) +// +#pragma once +#ifndef BASE64_H_C0CE2A47_D10E_42C9_A27C_C883944E704A +#define BASE64_H_C0CE2A47_D10E_42C9_A27C_C883944E704A + +#include + +#if __cplusplus >= 201703L +#include +#endif // __cplusplus >= 201703L + +std::string base64_encode(std::string const &s, bool url = false); +std::string base64_encode_pem(std::string const &s); +std::string base64_encode_mime(std::string const &s); + +std::string base64_decode(std::string const &s, bool remove_linebreaks = false); +std::string base64_encode(unsigned char const *, size_t len, bool url = false); + +#if __cplusplus >= 201703L +// +// Interface with std::string_view rather than const std::string& +// Requires C++17 +// Provided by Yannic Bonenberger (https://github.com/Yannic) +// +std::string base64_encode(std::string_view s, bool url = false); +std::string base64_encode_pem(std::string_view s); +std::string base64_encode_mime(std::string_view s); + +std::string base64_decode(std::string_view s, bool remove_linebreaks = false); +#endif // __cplusplus >= 201703L + +#endif /* BASE64_H_C0CE2A47_D10E_42C9_A27C_C883944E704A */ \ No newline at end of file diff --git a/src/config.cc b/src/config.cc new file mode 100644 index 0000000..af61537 --- /dev/null +++ b/src/config.cc @@ -0,0 +1,14 @@ +#include "pch.h" +#include "config.h" + +namespace wxhelper { +Config::Config(/* args */) {} + +Config::~Config() {} + +void Config::Initialize() { + port_ = GetPrivateProfileInt("config", "Port", 19088, "./config.ini"); +} +int Config::GetPort() { return port_; } + +} // namespace wxhelper \ No newline at end of file diff --git a/src/config.h b/src/config.h new file mode 100644 index 0000000..a72c009 --- /dev/null +++ b/src/config.h @@ -0,0 +1,17 @@ +#ifndef WXHELPER_CONFIG_H_ +#define WXHELPER_CONFIG_H_ + +namespace wxhelper { + +class Config { + public: + Config(); + ~Config(); + void Initialize(); + int GetPort(); + + private: + int port_; +}; +} // namespace wxhelper +#endif \ No newline at end of file diff --git a/src/dllMain.cc b/src/dllMain.cc new file mode 100644 index 0000000..d78079b --- /dev/null +++ b/src/dllMain.cc @@ -0,0 +1,28 @@ +#include "pch.h" +#include "global_context.h" +#include "utils.h" + + +using namespace wxhelper; + +BOOL APIENTRY DllMain(HMODULE hModule, DWORD ul_reason_for_call, + LPVOID lpReserved) { + switch (ul_reason_for_call) { + case DLL_PROCESS_ATTACH: { + DisableThreadLibraryCalls(hModule); + GlobalContext::GetInstance().initialize(hModule); + break; + } + case DLL_THREAD_ATTACH: { + break; + } + case DLL_THREAD_DETACH: { + break; + } + case DLL_PROCESS_DETACH: { + GlobalContext::GetInstance().finally(); + break; + } + } + return TRUE; +} \ No newline at end of file diff --git a/src/export.asm b/src/export.asm new file mode 100644 index 0000000..b578c88 --- /dev/null +++ b/src/export.asm @@ -0,0 +1,61 @@ +;################################################################# + +.code + + +;################################################################# + + +;################################################################# + +;检测wechat登录状态 +;param: get_account_service_addr 函数地址 + +;################################################################# +_GetAccountService PROC, + get_account_service_addr:QWORD ; 函数地址 + sub rsp,28h + call rcx + add rsp,28h + ret +_GetAccountService ENDP + +;################################################################# + +;获取wechat数据保存路径 +;param: addr 函数地址 +;return:路径地址 + +;################################################################# +_GetDataSavePath PROC, + get_data_path_addr:QWORD, ; 函数地址 + out_path:QWORD ; 输出 + sub rsp,40h + mov rax,rcx + mov rcx,rdx + call rax + add rsp,40h + ret +_GetDataSavePath ENDP + + +;################################################################# + +;获取wechat当前数据保存路径 +;param: addr 函数地址 +;return:路径地址 + +;################################################################# +_GetCurrentDataPath PROC, + get_current_path_addr: QWORD, ; 函数地址 + out_path: QWORD ; 输出 + sub rsp,28h + mov rax,rcx + mov rcx,rdx + call rax + add rsp,28h + ret +_GetCurrentDataPath ENDP + + +END \ No newline at end of file diff --git a/src/export.h b/src/export.h new file mode 100644 index 0000000..c748f38 --- /dev/null +++ b/src/export.h @@ -0,0 +1,8 @@ +#ifndef WXHELPER_EXPORT_H_ +#define WXHELPER_EXPORT_H_ + +extern "C" UINT64 _GetAccountService(UINT64 addr); +extern "C" UINT64 _GetDataSavePath(UINT64 addr,ULONG_PTR out); +extern "C" UINT64 _GetCurrentDataPath(UINT64 addr,ULONG_PTR out); +extern "C" UINT64 _SendTextMsg(UINT64 mgr_addr,UINT64 send_text_addr,UINT64 free_addr,UINT64 receiver,UINT64 msg,UINT64 chat_msg); +#endif \ No newline at end of file diff --git a/src/global_context.cc b/src/global_context.cc new file mode 100644 index 0000000..d0a3507 --- /dev/null +++ b/src/global_context.cc @@ -0,0 +1,37 @@ +#include "pch.h" +#include "global_context.h" +#include "thread_pool.h" + +namespace wxhelper { + +GlobalContext::~GlobalContext() { + if (config.has_value()) { + config.reset(); + } + if (log.has_value()) { + log.reset(); + } + +} +void GlobalContext::initialize(HMODULE module) { + state =GlobalContextState::INITIALIZING; + module_ = module; + // Utils::Hide(module); + UINT64 base = Utils::GetWeChatWinBase(); + config.emplace(); + config->Initialize(); + log.emplace(); + log->Initialize(); + http_server = std::unique_ptr( new HttpServer(config->GetPort())); + http_server->HttpStart(); + ThreadPool::GetInstance().Create(2, 8); + mgr = std::unique_ptr(new Manager(base)); + state =GlobalContextState::INITIALIZED; +} + +void GlobalContext::finally() { + if (http_server) { + http_server->HttpClose(); + } +} +} // namespace wxhelper \ No newline at end of file diff --git a/src/global_context.h b/src/global_context.h new file mode 100644 index 0000000..8e7e332 --- /dev/null +++ b/src/global_context.h @@ -0,0 +1,41 @@ +#ifndef GLOBAL_CONTEXT_H_ +#define GLOBAL_CONTEXT_H_ +#include "config.h" +#include "http_server.h" +#include "log.h" +#include "singleton.h" +#include "manager.h" + +namespace wxhelper { + +enum class GlobalContextState { NOT_INITIALIZED, INITIALIZING, INITIALIZED }; + +class GlobalContext : public Singleton { + friend class Singleton; + ~GlobalContext(); + + public: + void initialize(HMODULE module); + void finally(); + + public: + std::optional config; + std::optional log; + std::unique_ptr http_server; + std::unique_ptr mgr; + + // std::optional contact_mgr; + // std::optional misc_mgr; + // std::optional send_mgr; + // std::optional account_mgr; + // std::optional chat_room_mgr; + // std::optional sns_mgr; + + GlobalContextState state = GlobalContextState::NOT_INITIALIZED; + + private: + HMODULE module_; +}; + +} // namespace wxhelper +#endif \ No newline at end of file diff --git a/src/hooks.cc b/src/hooks.cc new file mode 100644 index 0000000..3c74196 --- /dev/null +++ b/src/hooks.cc @@ -0,0 +1,178 @@ + +#include "pch.h" +#include "hooks.h" +#include "thread_pool.h" +#include "wechat_function.h" +#include +#include "base64.h" +#include "http_client.h" + +namespace offset = wxhelper::V3_9_5_81::offset; +namespace common = wxhelper::common; +namespace wxhelper { +namespace hooks { + +static int kServerPort = 19099; +static bool kMsgHookFlag = false; +static char kServerIp[16] = "127.0.0.1"; +static bool kEnableHttp = false; + + + +static UINT64 (*R_DoAddMsg)(UINT64, UINT64, UINT64) = (UINT64(*)( + UINT64, UINT64, UINT64))(Utils::GetWeChatWinBase() + offset::kDoAddMsg); + +VOID CALLBACK SendMsgCallback(PTP_CALLBACK_INSTANCE instance, PVOID context, + PTP_WORK Work) { + common::InnerMessageStruct *msg = (common::InnerMessageStruct *)context; + if (msg == NULL) { + SPDLOG_INFO("add work:msg is null"); + return; + } + std::unique_ptr sms(msg); + nlohmann::json j_msg = + nlohmann::json::parse(msg->buffer, msg->buffer + msg->length, nullptr, false); + if (j_msg.is_discarded() == true) { + return; + } + std::string jstr = j_msg.dump() + "\n"; + + if (kServerPort == 0) { + SPDLOG_ERROR("http server port error :{}", kServerPort); + return; + } + WSADATA was_data = {0}; + int ret = WSAStartup(MAKEWORD(2, 2), &was_data); + if (ret != 0) { + SPDLOG_ERROR("WSAStartup failed:{}", ret); + return; + } + + SOCKET client_socket = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + if (client_socket < 0) { + SPDLOG_ERROR("socket init fail"); + return; + } + BOOL status = false; + sockaddr_in client_addr; + memset(&client_addr, 0, sizeof(client_addr)); + client_addr.sin_family = AF_INET; + client_addr.sin_port = htons((u_short)kServerPort); + InetPtonA(AF_INET, kServerIp, &client_addr.sin_addr.s_addr); + if (connect(client_socket, reinterpret_cast(&client_addr), + sizeof(sockaddr)) < 0) { + SPDLOG_ERROR("socket connect fail"); + goto clean; + } + char recv_buf[1024] = {0}; + ret = send(client_socket, jstr.c_str(), jstr.size(), 0); + if (ret < 0) { + SPDLOG_ERROR("socket send fail ,ret:{}", ret); + goto clean; + } + ret = shutdown(client_socket, SD_SEND); + if (ret == SOCKET_ERROR) { + SPDLOG_ERROR("shutdown failed with erro:{}", ret); + goto clean; + } + ret = recv(client_socket, recv_buf, sizeof(recv_buf), 0); + if (ret < 0) { + SPDLOG_ERROR("socket recv fail ,ret:{}", ret); + goto clean; + } +clean: + closesocket(client_socket); + WSACleanup(); + return; +} + +VOID CALLBACK SendHttpMsgCallback(PTP_CALLBACK_INSTANCE instance, PVOID context, + PTP_WORK Work) { + common::InnerMessageStruct *msg = (common::InnerMessageStruct *)context; + if (msg == NULL) { + SPDLOG_INFO("http msg is null"); + return; + } + + std::unique_ptr sms(msg); + nlohmann::json j_msg = + nlohmann::json::parse(msg->buffer, msg->buffer + msg->length, nullptr, false); + if (j_msg.is_discarded() == true) { + return; + } + std::string jstr = j_msg.dump() + "\n"; + // HttpClient::GetInstance().SendRequest(jstr); +} + +void HandleSyncMsg(INT64 param1, INT64 param2, INT64 param3) { + nlohmann::json msg; + + msg["pid"] = GetCurrentProcessId(); + msg["fromUser"] = Utils::ReadSKBuiltinString(*(INT64 *)(param2 + 0x18)); + msg["toUser"] = Utils::ReadSKBuiltinString(*(INT64 *)(param2 + 0x28)); + msg["content"] = Utils::ReadSKBuiltinString(*(INT64 *)(param2 + 0x30)); + msg["signature"] = Utils::ReadWeChatStr(*(INT64 *)(param2 + 0x48)); + msg["msgId"] = *(INT64 *)(param2 + 0x58); + msg["msgSequence"] = *(DWORD *)(param2 + 0x20); + msg["fromUserName"] = Utils::ReadWeChatStr(*(INT64 *)(param2 + 0x50)); + DWORD type = *(DWORD *)(param2 + 0x24); + msg["type"] = type; + if (type == 3) { + int a = 1; + std::string img = + Utils::ReadSKBuiltinBuffer(*(INT64 *)(param2 + 0x40)); + SPDLOG_INFO("encode size:{}",img.size()); + msg["base64Img"] = base64_encode(img); + a = 2; + } + std::string jstr = msg.dump() + '\n'; + common::InnerMessageStruct *inner_msg = new common::InnerMessageStruct; + inner_msg->buffer = new char[jstr.size() + 1]; + memcpy(inner_msg->buffer, jstr.c_str(), jstr.size() + 1); + inner_msg->length = jstr.size(); + if(kEnableHttp){ + bool add = ThreadPool::GetInstance().AddWork(SendHttpMsgCallback,inner_msg); + SPDLOG_INFO("add http msg work:{}",add); + }else{ + bool add = ThreadPool::GetInstance().AddWork(SendMsgCallback,inner_msg); + SPDLOG_INFO("add msg work:{}",add); + } + R_DoAddMsg(param1,param2,param3); +} + +int HookSyncMsg(std::string client_ip, int port, std::string url, + uint64_t timeout, bool enable) { + if (kMsgHookFlag) { + SPDLOG_INFO("recv msg hook already called"); + return 2; + } + kEnableHttp = enable; + if (kEnableHttp) { + HttpClient::GetInstance().SetConfig(url, timeout); + } + if (client_ip.size() < 1) { + return -2; + } + + kServerPort = port; + strcpy_s(kServerIp, client_ip.c_str()); + UINT64 base = Utils::GetWeChatWinBase(); + if (!base) { + SPDLOG_INFO("base addr is null"); + return -1; + } + + DetourRestoreAfterWith(); + DetourTransactionBegin(); + DetourUpdateThread(GetCurrentThread()); + UINT64 do_add_msg_addr = base + offset::kDoAddMsg; + DetourAttach(&(PVOID&)R_DoAddMsg, &HandleSyncMsg); + LONG ret = DetourTransactionCommit(); + + return ret; +} + +int UnHookSyncMsg() { return 1; } + +} // namespace hooks +} // namespace wxhelper \ No newline at end of file diff --git a/src/hooks.h b/src/hooks.h new file mode 100644 index 0000000..d952f12 --- /dev/null +++ b/src/hooks.h @@ -0,0 +1,15 @@ +#ifndef WXHELPER_HOOKS_H_ +#define WXHELPER_HOOKS_H_ +#include "Windows.h" +#include "wechat_function.h" +namespace wxhelper { +namespace hooks { + +int HookSyncMsg(std::string client_ip, int port, std::string url, uint64_t timeout, + bool enable); + +int UnHookSyncMsg(); + +} // namespace hooks +} // namespace wxhelper +#endif \ No newline at end of file diff --git a/src/http_client.cc b/src/http_client.cc new file mode 100644 index 0000000..fbf1a2a --- /dev/null +++ b/src/http_client.cc @@ -0,0 +1,65 @@ +#include "pch.h" +#include "http_client.h" +namespace wxhelper { + + void HttpClient::SendRequest(std::string content) { + struct mg_mgr mgr; + Data data ; + data.done = false; + data.post_data = content; + mg_mgr_init(&mgr); + mg_http_connect(&mgr, url_.c_str(), OnHttpEvent, &data); + while (!data.done){ + mg_mgr_poll(&mgr, 500); + } + mg_mgr_free(&mgr); +} + + + void HttpClient::OnHttpEvent(struct mg_connection *c, int ev, void *ev_data, void *fn_data) { + const char * s_url = GetInstance().url_.c_str(); + Data data = *(Data*)fn_data; + if (ev == MG_EV_OPEN) { + // Connection created. Store connect expiration time in c->data + *(uint64_t *) c->data = mg_millis() + GetInstance().timeout_; + } else if (ev == MG_EV_POLL) { + if (mg_millis() > *(uint64_t *) c->data && + (c->is_connecting || c->is_resolving)) { + mg_error(c, "Connect timeout"); + } + } else if (ev == MG_EV_CONNECT) { + struct mg_str host = mg_url_host(s_url); + if (mg_url_is_ssl(s_url)) { + // no implement + } + + // Send request + int content_length = data.post_data.size(); + mg_printf(c, + "POST %s HTTP/1.0\r\n" + "Host: %.*s\r\n" + "Content-Type: application/json\r\n" + "Content-Length: %d\r\n" + "\r\n", + mg_url_uri(s_url), (int) host.len, + host.ptr, content_length); + mg_send(c, data.post_data.c_str(), content_length); + } else if (ev == MG_EV_HTTP_MSG) { + // Response is received. Print it + #ifdef _DEBUG + struct mg_http_message *hm = (struct mg_http_message *) ev_data; + printf("%.*s", (int) hm->message.len, hm->message.ptr); + #endif + c->is_closing = 1; // Tell mongoose to close this connection + data.done = true; // Tell event loop to stops + } else if (ev == MG_EV_ERROR) { + data.done = true; // Error, tell event loop to stop + } +} + +void HttpClient::SetConfig(std::string url,uint64_t timeout){ + url_=url; + timeout_=timeout; +} + +} // namespace wxhelper \ No newline at end of file diff --git a/src/http_client.h b/src/http_client.h new file mode 100644 index 0000000..4ab7fae --- /dev/null +++ b/src/http_client.h @@ -0,0 +1,24 @@ +#ifndef WXHELPER_HTTP_CLIENT_H_ +#define WXHELPER_HTTP_CLIENT_H_ +#include "mongoose.h" +#include "singleton.h" + +namespace wxhelper { +struct Data { + bool done; + std::string post_data; +}; +class HttpClient : public Singleton { + public: + void SendRequest(std::string content); + void SetConfig(std::string url,uint64_t timeout); + + static void OnHttpEvent(struct mg_connection *c, int ev, void *ev_data, + void *fn_data); + private: + std::string url_; + uint64_t timeout_; +}; + +} // namespace wxhelper +#endif \ No newline at end of file diff --git a/src/http_server.cc b/src/http_server.cc new file mode 100644 index 0000000..5f8ad5f --- /dev/null +++ b/src/http_server.cc @@ -0,0 +1,54 @@ +#include "pch.h" +#include "http_server_callback.h" +#include "http_server.h" + +namespace wxhelper { + +HttpServer::HttpServer(int port) { + port_ = port; + running_ = false; + mg_mgr_init(&mgr_); +} + +HttpServer::~HttpServer() { + if (thread_ != nullptr) { + CloseHandle(thread_); + } + mg_mgr_free(&mgr_); +} + +bool HttpServer::HttpStart() { + if (running_) { + return true; + } +#ifdef _DEBUG + Utils::CreateConsole(); +#endif + running_ = true; + thread_ = CreateThread(NULL, 0, (LPTHREAD_START_ROUTINE)StartHttpServer, this, + NULL, 0); + return true; +} + +bool HttpServer::HttpClose() { + if (!running_) { + return true; + } +#ifdef _DEBUG + Utils::CloseConsole(); +#endif + running_ = false; + if (thread_) { + WaitForSingleObject(thread_, -1); + CloseHandle(thread_); + thread_ = NULL; + } + return true; +} + +int HttpServer::GetPort() { return port_; } +bool HttpServer::GetRunning() { return running_; } + +const mg_mgr* HttpServer::GetMgr() { return &mgr_; } + +} // namespace wxhelper \ No newline at end of file diff --git a/src/http_server.h b/src/http_server.h new file mode 100644 index 0000000..242692b --- /dev/null +++ b/src/http_server.h @@ -0,0 +1,29 @@ +#ifndef WXHELPER_HTTP_SERVER_H_ +#define WXHELPER_HTTP_SERVER_H_ + +#include "mongoose.h" + +namespace wxhelper { +class HttpServer { + public: + explicit HttpServer(int port); + HttpServer(const HttpServer&) = delete; + HttpServer(HttpServer &&)=delete; + HttpServer& operator=(const HttpServer&) = delete; + ~HttpServer(); + + bool HttpStart(); + bool HttpClose(); + int GetPort(); + bool GetRunning(); + const mg_mgr* GetMgr(); + + private: + int port_; + bool running_; + struct mg_mgr mgr_; + HANDLE thread_; +}; +} // namespace wxhelper + +#endif \ No newline at end of file diff --git a/src/http_server_callback.cc b/src/http_server_callback.cc new file mode 100644 index 0000000..ff15f58 --- /dev/null +++ b/src/http_server_callback.cc @@ -0,0 +1,154 @@ +#include "pch.h" +#include "http_server_callback.h" +#include "http_server.h" +#include "export.h" +#include "global_context.h" +#include "hooks.h" +namespace common = wxhelper::common; + + +std::wstring GetWStringParam(nlohmann::json data, std::string key) { + return wxhelper::Utils::UTF8ToWstring(data[key].get()); +} + +void StartHttpServer(wxhelper::HttpServer *server) { + int port = server->GetPort(); + std::string lsten_addr = "http://0.0.0.0:" + std::to_string(port); + if (mg_http_listen(const_cast(server->GetMgr()), lsten_addr.c_str(), + EventHandler, + const_cast(server->GetMgr())) == NULL) { + SPDLOG_INFO("http server listen fail.port:{}", port); +#ifdef _DEBUG + MG_INFO(("http server listen fail.port: %d", port)); +#endif + return; + } + for (;;) { + mg_mgr_poll(const_cast(server->GetMgr()), 1000); + } +} + +void EventHandler(struct mg_connection *c, int ev, void *ev_data, + void *fn_data) { + if (ev == MG_EV_OPEN) { + } else if (ev == MG_EV_HTTP_MSG) { + struct mg_http_message *hm = (struct mg_http_message *)ev_data; + if (mg_http_match_uri(hm, "/websocket")) { + mg_ws_upgrade(c, hm, NULL); + } else if (mg_http_match_uri(hm, "/api/*")) { + HandleHttpRequest(c, hm); + } else { + nlohmann::json res = {{"code", 400}, + {"msg", "invalid url, please check url"}, + {"data", NULL}}; + std::string ret = res.dump(); + mg_http_reply(c, 200, "Content-Type: application/json\r\n", "%s\n", + ret.c_str()); + } + } else if (ev == MG_EV_WS_MSG) { + HandleWebsocketRequest(c, ev_data); + } + (void)fn_data; +} + +void HandleHttpRequest(struct mg_connection *c, void *ev_data) { + struct mg_http_message *hm = (struct mg_http_message *)ev_data; + std::string ret = R"({"code":200,"msg":"success"})"; + try { + ret = HttpDispatch(c, hm); + } catch (nlohmann::json::exception &e) { + nlohmann::json res = {{"code", "500"}, {"msg", e.what()}, {"data", NULL}}; + ret = res.dump(); + } + if (ret != "") { + mg_http_reply(c, 200, "Content-Type: application/json\r\n", "%s\n", + ret.c_str()); + } +} + +void HandleWebsocketRequest(struct mg_connection *c, void *ev_data) { + // Got websocket frame. Received data is wm->data. Echo it back! + struct mg_ws_message *wm = (struct mg_ws_message *)ev_data; + mg_ws_send(c, wm->data.ptr, wm->data.len, WEBSOCKET_OP_TEXT); +} + +std::string HttpDispatch(struct mg_connection *c, struct mg_http_message *hm) { + std::string ret; + if (mg_vcasecmp(&hm->method, "GET") == 0) { + nlohmann::json ret_data = {{"code", 200}, + {"data", {}}, + {"msg", "not support get method,use post."}}; + ret = ret_data.dump(); + return ret; + } + + nlohmann::json j_param = nlohmann::json::parse( + hm->body.ptr, hm->body.ptr + hm->body.len, nullptr, false); + if (hm->body.len != 0 && j_param.is_discarded() == true) { + nlohmann::json ret_data = { + {"code", 200}, {"data", {}}, {"msg", "json string is invalid."}}; + ret = ret_data.dump(); + return ret; + } + if (wxhelper::GlobalContext::GetInstance().state != + wxhelper::GlobalContextState::INITIALIZED) { + nlohmann::json ret_data = { + {"code", 200}, {"data", {}}, {"msg", "global context is initializing"}}; + ret = ret_data.dump(); + return ret; + } + if (mg_http_match_uri(hm, "/api/checkLogin")) { + INT64 success = wxhelper::GlobalContext::GetInstance().mgr->CheckLogin(); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + ret = ret_data.dump(); + return ret; + } else if (mg_http_match_uri(hm, "/api/userInfo")) { + common::SelfInfoInner self_info; + INT64 success = wxhelper::GlobalContext::GetInstance().mgr->GetSelfInfo(self_info); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + if (success) { + nlohmann::json j_info = { + {"name", self_info.name}, + {"city", self_info.city}, + {"province", self_info.province}, + {"country", self_info.country}, + {"account", self_info.account}, + {"wxid", self_info.wxid}, + {"mobile", self_info.mobile}, + {"headImage", self_info.head_img}, + {"signature", self_info.signature}, + {"dataSavePath", self_info.data_save_path}, + {"currentDataPath", self_info.current_data_path}, + {"dbKey", self_info.db_key}, + }; + ret_data["data"] = j_info; + } + ret = ret_data.dump(); + return ret; + } else if (mg_http_match_uri(hm, "/api/sendTextMsg")) { + std::wstring wxid = GetWStringParam(j_param, "wxid"); + std::wstring msg = GetWStringParam(j_param, "msg"); + INT64 success = wxhelper::GlobalContext::GetInstance().mgr->SendTextMsg(wxid, msg); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + ret = ret_data.dump(); + return ret; + } else if (mg_http_match_uri(hm, "/api/hookSyncMsg")) { + INT64 success = wxhelper::hooks::HookSyncMsg("127.0.0.1",19099,"",3000,false); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + ret = ret_data.dump(); + return ret; + } else { + nlohmann::json ret_data = { + {"code", 200}, {"data", {}}, {"msg", "not support url"}}; + ret = ret_data.dump(); + return ret; + } + nlohmann::json ret_data = { + {"code", 200}, {"data", {}}, {"msg", "unreachable code."}}; + ret = ret_data.dump(); + return ret; +} \ No newline at end of file diff --git a/src/http_server_callback.h b/src/http_server_callback.h new file mode 100644 index 0000000..e0060a2 --- /dev/null +++ b/src/http_server_callback.h @@ -0,0 +1,17 @@ +#ifndef WXHELPER_HTTP_SERVER_CALLBACK_H_ +#define WXHELPER_HTTP_SERVER_CALLBACK_H_ +#include + +#include "http_server.h" +#include "mongoose.h" + + +void StartHttpServer(wxhelper::HttpServer *server); + +void EventHandler(struct mg_connection *c, int ev, void *ev_data, + void *fn_data); +void HandleHttpRequest(struct mg_connection *c, void *ev_data); +void HandleWebsocketRequest(struct mg_connection *c, void *ev_data); +std::string HttpDispatch(struct mg_connection *c, struct mg_http_message *hm); + +#endif \ No newline at end of file diff --git a/src/log.cc b/src/log.cc new file mode 100644 index 0000000..f73e755 --- /dev/null +++ b/src/log.cc @@ -0,0 +1,21 @@ +#include "pch.h" +#include "log.h" + + +#define SPDLOG_ACTIVE_LEVEL SPDLOG_LEVEL_INFO +namespace wxhelper { +Log::Log() {} + +Log::~Log() {} + +void Log::Initialize() { + auto logger = + spdlog::daily_logger_mt("daily_logger", "logs/daily.txt", 23, 59); + logger->flush_on(spdlog::level::err); + spdlog::set_default_logger(logger); + spdlog::flush_every(std::chrono::seconds(3)); + spdlog::set_level(spdlog::level::debug); + spdlog::set_pattern("%Y-%m-%d %H:%M:%S [%l] [%t] - <%s>|<%#>|<%!>,%v"); +} + +} // namespace wxhelper \ No newline at end of file diff --git a/src/log.h b/src/log.h new file mode 100644 index 0000000..c24f1a6 --- /dev/null +++ b/src/log.h @@ -0,0 +1,15 @@ +#ifndef WXHELPER_LOG_H_ +#define WXHELPER_LOG_H_ +namespace wxhelper { +class Log { + private: + + public: + Log(); + ~Log(); + void Initialize(); +}; + +} // namespace wxhelper + +#endif \ No newline at end of file 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/manager.cc b/src/manager.cc new file mode 100644 index 0000000..cf30eab --- /dev/null +++ b/src/manager.cc @@ -0,0 +1,218 @@ +#include "pch.h" +#include "manager.h" + +#include "export.h" +#include "wechat_function.h" + +namespace offset = wxhelper::V3_9_5_81::offset; +namespace prototype = wxhelper::V3_9_5_81::prototype; +namespace func = wxhelper::V3_9_5_81::function; + + +namespace wxhelper { +Manager::Manager(UINT64 base) : base_addr_(base) {} +Manager::~Manager() {} +INT64 Manager::CheckLogin() { + INT64 success = -1; + UINT64 accout_service_addr = base_addr_ + offset::kGetAccountServiceMgr; + func::__GetAccountService GetSevice = (func::__GetAccountService)accout_service_addr; + // UINT64 service_addr = _GetAccountService(accout_service_addr); + UINT64 service_addr = GetSevice(); + if (service_addr) { + success = *(UINT64 *)(service_addr + 0x7F8); + } + return success; +} + +INT64 Manager::GetSelfInfo(common::SelfInfoInner &out) { + INT64 success = -1; + UINT64 accout_service_addr = base_addr_ + offset::kGetAccountServiceMgr; + UINT64 get_app_data_save_path_addr = base_addr_ + offset::kGetAppDataSavePath; + UINT64 get_current_data_path_addr = base_addr_ + offset::kGetCurrentDataPath; + // UINT64 service_addr = _GetAccountService(accout_service_addr); + func::__GetAccountService GetSevice = (func::__GetAccountService)accout_service_addr; + func::__GetDataSavePath GetDataSavePath = (func::__GetDataSavePath)get_app_data_save_path_addr; + func::__GetCurrentDataPath GetCurrentDataPath = (func::__GetCurrentDataPath)get_current_data_path_addr; + + UINT64 service_addr = GetSevice(); + if (service_addr) { + if (*(INT64 *)(service_addr + 0x80) == 0 || + *(INT64 *)(service_addr + 0x80 + 0x10) == 0) { + out.wxid = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x80 + 0x18) == 0xF) { + out.wxid = std::string((char *)(service_addr + 0x80), + *(INT64 *)(service_addr + 0x80 + 0x10)); + } else { + out.wxid = std::string(*(char **)(service_addr + 0x80), + *(INT64 *)(service_addr + 0x80 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x108) == 0 || + *(INT64 *)(service_addr + 0x108 + 0x10) == 0) { + out.account = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x108 + 0x18) == 0xF) { + out.account = std::string((char *)(service_addr + 0x108), + *(INT64 *)(service_addr + 0x108 + 0x10)); + } else { + out.account = std::string(*(char **)(service_addr + 0x108), + *(INT64 *)(service_addr + 0x108 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x128) == 0 || + *(INT64 *)(service_addr + 0x128 + 0x10) == 0) { + out.mobile = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x128 + 0x18) == 0xF) { + out.mobile = std::string((char *)(service_addr + 0x128), + *(INT64 *)(service_addr + 0x128 + 0x10)); + } else { + out.mobile = std::string(*(char **)(service_addr + 0x128), + *(INT64 *)(service_addr + 0x128 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x148) == 0 || + *(INT64 *)(service_addr + 0x148 + 0x10) == 0) { + out.signature = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x148 + 0x18) == 0xF) { + out.signature = std::string((char *)(service_addr + 0x148), + *(INT64 *)(service_addr + 0x148 + 0x10)); + } else { + out.signature = std::string(*(char **)(service_addr + 0x148), + *(INT64 *)(service_addr + 0x148 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x168) == 0 || + *(INT64 *)(service_addr + 0x168 + 0x10) == 0) { + out.country = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x168 + 0x18) == 0xF) { + out.country = std::string((char *)(service_addr + 0x168), + *(INT64 *)(service_addr + 0x168 + 0x10)); + } else { + out.country = std::string(*(char **)(service_addr + 0x168), + *(INT64 *)(service_addr + 0x168 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x188) == 0 || + *(INT64 *)(service_addr + 0x188 + 0x10) == 0) { + out.province = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x188 + 0x18) == 0xF) { + out.province = std::string((char *)(service_addr + 0x188), + *(INT64 *)(service_addr + 0x188 + 0x10)); + } else { + out.province = std::string(*(char **)(service_addr + 0x188), + *(INT64 *)(service_addr + 0x188 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x1A8) == 0 || + *(INT64 *)(service_addr + 0x1A8 + 0x10) == 0) { + out.city = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x1A8 + 0x18) == 0xF) { + out.city = std::string((char *)(service_addr + 0x1A8), + *(INT64 *)(service_addr + 0x1A8 + 0x10)); + } else { + out.city = std::string(*(char **)(service_addr + 0x1A8), + *(INT64 *)(service_addr + 0x1A8 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x1E8) == 0 || + *(INT64 *)(service_addr + 0x1E8 + 0x10) == 0) { + out.name = std::string(); + } else { + if (*(INT64 *)(service_addr + 0x1E8 + 0x18) == 0xF) { + out.name = std::string((char *)(service_addr + 0x1E8), + *(INT64 *)(service_addr + 0x1E8 + 0x10)); + } else { + out.name = std::string(*(char **)(service_addr + 0x1E8), + *(INT64 *)(service_addr + 0x1E8 + 0x10)); + } + } + + if (*(INT64 *)(service_addr + 0x450) == 0 || + *(INT64 *)(service_addr + 0x450 + 0x10) == 0) { + out.head_img = std::string(); + } else { + out.head_img = std::string(*(char **)(service_addr + 0x450), + *(INT64 *)(service_addr + 0x450 + 0x10)); + } + + if (*(INT64 *)(service_addr + 0x6E0) == 0 || + *(INT64 *)(service_addr + 0x6E8) == 0) { + out.db_key = std::string(); + } else { + INT64 byte_addr = *(INT64 *)(service_addr + 0x6E0); + INT64 len = *(INT64 *)(service_addr + 0x6E8); + out.db_key = Utils::Bytes2Hex((BYTE *)byte_addr, static_cast(len)); + } + + UINT64 flag = *(UINT64 *)(service_addr + 0x7F8); + if (flag == 1) { + prototype::WeChatString current_data_path; + // _GetCurrentDataPath(get_current_data_path_addr, + // reinterpret_cast(¤t_data_path)); + GetCurrentDataPath(reinterpret_cast(¤t_data_path)); + if (current_data_path.ptr) { + out.current_data_path = Utils::WstringToUTF8( + std::wstring(current_data_path.ptr, current_data_path.length)); + } else { + out.current_data_path = std::string(); + } + } + } + + prototype::WeChatString data_save_path; + // _GetDataSavePath(get_app_data_save_path_addr, + // reinterpret_cast(&data_save_path)); + GetCurrentDataPath(reinterpret_cast(&data_save_path)); + if (data_save_path.ptr) { + out.data_save_path = Utils::WstringToUTF8( + std::wstring(data_save_path.ptr, data_save_path.length)); + } else { + out.data_save_path = std::string(); + } + + success = 1; + return success; +} + + + +INT64 Manager::SendTextMsg(const std::wstring& wxid, const std::wstring& msg){ + INT64 success = -1; + prototype::WeChatString to_user(wxid); + prototype::WeChatString text_msg(msg); + wchar_t** msg_pptr = &text_msg.ptr; + UINT64 send_message_mgr_addr = base_addr_ + offset::kGetSendMessageMgr; + UINT64 send_text_msg_addr = base_addr_ + offset::kSendTextMsg; + UINT64 free_chat_msg_addr = base_addr_ + offset::kFreeChatMsg; + char chat_msg[0x460] = {0}; + UINT64 temp[3] ={0}; + func::__GetSendMessageMgr mgr; + mgr = (func::__GetSendMessageMgr)send_message_mgr_addr; + func::__SendTextMsg send; + send = (func::__SendTextMsg)send_text_msg_addr; + func::__FreeChatMsg free; + free = (func::__FreeChatMsg)free_chat_msg_addr; + mgr(); + send(reinterpret_cast(&chat_msg), reinterpret_cast(&to_user), + reinterpret_cast(&text_msg), reinterpret_cast(&temp), 1, + 1, 0, 0); + free(reinterpret_cast(&chat_msg)); + success = 1; + + return success; +} + +} // namespace wxhelper` \ No newline at end of file diff --git a/src/manager.h b/src/manager.h new file mode 100644 index 0000000..8e9d223 --- /dev/null +++ b/src/manager.h @@ -0,0 +1,18 @@ +#ifndef WXHELPER_MANAGER_H_ +#define WXHELPER_MANAGER_H_ +#include "Windows.h" +#include "wechat_function.h" +namespace wxhelper { +class Manager { + public: + explicit Manager(UINT64 base); + ~Manager(); + INT64 CheckLogin(); + INT64 GetSelfInfo(common::SelfInfoInner& out); + INT64 SendTextMsg(const std::wstring& wxid, const std::wstring& msg); + private: + UINT64 base_addr_; +}; + +} // namespace wxhelper +#endif \ No newline at end of file diff --git a/src/mongoose.c b/src/mongoose.c new file mode 100644 index 0000000..81807f7 --- /dev/null +++ b/src/mongoose.c @@ -0,0 +1,8413 @@ +// Copyright (c) 2004-2013 Sergey Lyubka +// Copyright (c) 2013-2022 Cesanta Software Limited +// All rights reserved +// +// This software is dual-licensed: you can redistribute it and/or modify +// it under the terms of the GNU General Public License version 2 as +// published by the Free Software Foundation. For the terms of this +// license, see http://www.gnu.org/licenses/ +// +// You are free to use this software under the terms of the GNU General +// Public License, but WITHOUT ANY WARRANTY; without even the implied +// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +// See the GNU General Public License for more details. +// +// Alternatively, you can license this software under a commercial +// license, as set out in https://www.mongoose.ws/licensing/ +// +// SPDX-License-Identifier: GPL-2.0-only or commercial + +#include "mongoose.h" + +#ifdef MG_ENABLE_LINES +#line 1 "src/base64.c" +#endif + + + +static int mg_b64idx(int c) { + if (c < 26) { + return c + 'A'; + } else if (c < 52) { + return c - 26 + 'a'; + } else if (c < 62) { + return c - 52 + '0'; + } else { + return c == 62 ? '+' : '/'; + } +} + +static int mg_b64rev(int c) { + if (c >= 'A' && c <= 'Z') { + return c - 'A'; + } else if (c >= 'a' && c <= 'z') { + return c + 26 - 'a'; + } else if (c >= '0' && c <= '9') { + return c + 52 - '0'; + } else if (c == '+') { + return 62; + } else if (c == '/') { + return 63; + } else if (c == '=') { + return 64; + } else { + return -1; + } +} + +int mg_base64_update(unsigned char ch, char *to, int n) { + int rem = (n & 3) % 3; + if (rem == 0) { + to[n] = (char) mg_b64idx(ch >> 2); + to[++n] = (char) ((ch & 3) << 4); + } else if (rem == 1) { + to[n] = (char) mg_b64idx(to[n] | (ch >> 4)); + to[++n] = (char) ((ch & 15) << 2); + } else { + to[n] = (char) mg_b64idx(to[n] | (ch >> 6)); + to[++n] = (char) mg_b64idx(ch & 63); + n++; + } + return n; +} + +int mg_base64_final(char *to, int n) { + int saved = n; + // printf("---[%.*s]\n", n, to); + if (n & 3) n = mg_base64_update(0, to, n); + if ((saved & 3) == 2) n--; + // printf(" %d[%.*s]\n", n, n, to); + while (n & 3) to[n++] = '='; + to[n] = '\0'; + return n; +} + +int mg_base64_encode(const unsigned char *p, int n, char *to) { + int i, len = 0; + for (i = 0; i < n; i++) len = mg_base64_update(p[i], to, len); + len = mg_base64_final(to, len); + return len; +} + +int mg_base64_decode(const char *src, int n, char *dst) { + const char *end = src == NULL ? NULL : src + n; // Cannot add to NULL + int len = 0; + while (src != NULL && src + 3 < end) { + int a = mg_b64rev(src[0]), b = mg_b64rev(src[1]), c = mg_b64rev(src[2]), + d = mg_b64rev(src[3]); + if (a == 64 || a < 0 || b == 64 || b < 0 || c < 0 || d < 0) return 0; + dst[len++] = (char) ((a << 2) | (b >> 4)); + if (src[2] != '=') { + dst[len++] = (char) ((b << 4) | (c >> 2)); + if (src[3] != '=') dst[len++] = (char) ((c << 6) | d); + } + src += 4; + } + dst[len] = '\0'; + return len; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/dns.c" +#endif + + + + + + + + +struct dns_data { + struct dns_data *next; + struct mg_connection *c; + uint64_t expire; + uint16_t txnid; +}; + +static void mg_sendnsreq(struct mg_connection *, struct mg_str *, int, + struct mg_dns *, bool); + +static void mg_dns_free(struct mg_connection *c, struct dns_data *d) { + LIST_DELETE(struct dns_data, + (struct dns_data **) &c->mgr->active_dns_requests, d); + free(d); +} + +void mg_resolve_cancel(struct mg_connection *c) { + struct dns_data *tmp, *d = (struct dns_data *) c->mgr->active_dns_requests; + for (; d != NULL; d = tmp) { + tmp = d->next; + if (d->c == c) mg_dns_free(c, d); + } +} + +static size_t mg_dns_parse_name_depth(const uint8_t *s, size_t len, size_t ofs, + char *to, size_t tolen, size_t j, + int depth) { + size_t i = 0; + if (tolen > 0 && depth == 0) to[0] = '\0'; + if (depth > 5) return 0; + // MG_INFO(("ofs %lx %x %x", (unsigned long) ofs, s[ofs], s[ofs + 1])); + while (ofs + i + 1 < len) { + size_t n = s[ofs + i]; + if (n == 0) { + i++; + break; + } + if (n & 0xc0) { + size_t ptr = (((n & 0x3f) << 8) | s[ofs + i + 1]); // 12 is hdr len + // MG_INFO(("PTR %lx", (unsigned long) ptr)); + if (ptr + 1 < len && (s[ptr] & 0xc0) == 0 && + mg_dns_parse_name_depth(s, len, ptr, to, tolen, j, depth + 1) == 0) + return 0; + i += 2; + break; + } + if (ofs + i + n + 1 >= len) return 0; + if (j > 0) { + if (j < tolen) to[j] = '.'; + j++; + } + if (j + n < tolen) memcpy(&to[j], &s[ofs + i + 1], n); + j += n; + i += n + 1; + if (j < tolen) to[j] = '\0'; // Zero-terminate this chunk + // MG_INFO(("--> [%s]", to)); + } + if (tolen > 0) to[tolen - 1] = '\0'; // Make sure make sure it is nul-term + return i; +} + +static size_t mg_dns_parse_name(const uint8_t *s, size_t n, size_t ofs, + char *dst, size_t dstlen) { + return mg_dns_parse_name_depth(s, n, ofs, dst, dstlen, 0, 0); +} + +size_t mg_dns_parse_rr(const uint8_t *buf, size_t len, size_t ofs, + bool is_question, struct mg_dns_rr *rr) { + const uint8_t *s = buf + ofs, *e = &buf[len]; + + memset(rr, 0, sizeof(*rr)); + if (len < sizeof(struct mg_dns_header)) return 0; // Too small + if (len > 512) return 0; // Too large, we don't expect that + if (s >= e) return 0; // Overflow + + if ((rr->nlen = (uint16_t) mg_dns_parse_name(buf, len, ofs, NULL, 0)) == 0) + return 0; + s += rr->nlen + 4; + if (s > e) return 0; + rr->atype = (uint16_t) (((uint16_t) s[-4] << 8) | s[-3]); + rr->aclass = (uint16_t) (((uint16_t) s[-2] << 8) | s[-1]); + if (is_question) return (size_t) (rr->nlen + 4); + + s += 6; + if (s > e) return 0; + rr->alen = (uint16_t) (((uint16_t) s[-2] << 8) | s[-1]); + if (s + rr->alen > e) return 0; + return (size_t) (rr->nlen + rr->alen + 10); +} + +bool mg_dns_parse(const uint8_t *buf, size_t len, struct mg_dns_message *dm) { + const struct mg_dns_header *h = (struct mg_dns_header *) buf; + struct mg_dns_rr rr; + size_t i, n, ofs = sizeof(*h); + memset(dm, 0, sizeof(*dm)); + + if (len < sizeof(*h)) return 0; // Too small, headers dont fit + if (mg_ntohs(h->num_questions) > 1) return 0; // Sanity + if (mg_ntohs(h->num_answers) > 10) return 0; // Sanity + dm->txnid = mg_ntohs(h->txnid); + + for (i = 0; i < mg_ntohs(h->num_questions); i++) { + if ((n = mg_dns_parse_rr(buf, len, ofs, true, &rr)) == 0) return false; + // MG_INFO(("Q %lu %lu %hu/%hu", ofs, n, rr.atype, rr.aclass)); + ofs += n; + } + for (i = 0; i < mg_ntohs(h->num_answers); i++) { + if ((n = mg_dns_parse_rr(buf, len, ofs, false, &rr)) == 0) return false; + // MG_INFO(("A -- %lu %lu %hu/%hu %s", ofs, n, rr.atype, rr.aclass, + // dm->name)); + mg_dns_parse_name(buf, len, ofs, dm->name, sizeof(dm->name)); + ofs += n; + + if (rr.alen == 4 && rr.atype == 1 && rr.aclass == 1) { + dm->addr.is_ip6 = false; + memcpy(&dm->addr.ip, &buf[ofs - 4], 4); + dm->resolved = true; + break; // Return success + } else if (rr.alen == 16 && rr.atype == 28 && rr.aclass == 1) { + dm->addr.is_ip6 = true; + memcpy(&dm->addr.ip6, &buf[ofs - 16], 16); + dm->resolved = true; + break; // Return success + } + } + return true; +} + +static void dns_cb(struct mg_connection *c, int ev, void *ev_data, + void *fn_data) { + struct dns_data *d, *tmp; + if (ev == MG_EV_POLL) { + uint64_t now = *(uint64_t *) ev_data; + for (d = (struct dns_data *) c->mgr->active_dns_requests; d != NULL; + d = tmp) { + tmp = d->next; + // MG_DEBUG ("%lu %lu dns poll", d->expire, now)); + if (now > d->expire) mg_error(d->c, "DNS timeout"); + } + } else if (ev == MG_EV_READ) { + struct mg_dns_message dm; + int resolved = 0; + if (mg_dns_parse(c->recv.buf, c->recv.len, &dm) == false) { + MG_ERROR(("Unexpected DNS response:")); + mg_hexdump(c->recv.buf, c->recv.len); + } else { + // MG_VERBOSE(("%s %d", dm.name, dm.resolved)); + for (d = (struct dns_data *) c->mgr->active_dns_requests; d != NULL; + d = tmp) { + tmp = d->next; + // MG_INFO(("d %p %hu %hu", d, d->txnid, dm.txnid)); + if (dm.txnid != d->txnid) continue; + if (d->c->is_resolving) { + if (dm.resolved) { + dm.addr.port = d->c->rem.port; // Save port + d->c->rem = dm.addr; // Copy resolved address + MG_DEBUG( + ("%lu %s is %M", d->c->id, dm.name, mg_print_ip, &d->c->rem)); + mg_connect_resolved(d->c); +#if MG_ENABLE_IPV6 + } else if (dm.addr.is_ip6 == false && dm.name[0] != '\0' && + c->mgr->use_dns6 == false) { + struct mg_str x = mg_str(dm.name); + mg_sendnsreq(d->c, &x, c->mgr->dnstimeout, &c->mgr->dns6, true); +#endif + } else { + mg_error(d->c, "%s DNS lookup failed", dm.name); + } + } else { + MG_ERROR(("%lu already resolved", d->c->id)); + } + mg_dns_free(c, d); + resolved = 1; + } + } + if (!resolved) MG_ERROR(("stray DNS reply")); + c->recv.len = 0; + } else if (ev == MG_EV_CLOSE) { + for (d = (struct dns_data *) c->mgr->active_dns_requests; d != NULL; + d = tmp) { + tmp = d->next; + mg_error(d->c, "DNS error"); + mg_dns_free(c, d); + } + } + (void) fn_data; +} + +static bool mg_dns_send(struct mg_connection *c, const struct mg_str *name, + uint16_t txnid, bool ipv6) { + struct { + struct mg_dns_header header; + uint8_t data[256]; + } pkt; + size_t i, n; + memset(&pkt, 0, sizeof(pkt)); + pkt.header.txnid = mg_htons(txnid); + pkt.header.flags = mg_htons(0x100); + pkt.header.num_questions = mg_htons(1); + for (i = n = 0; i < sizeof(pkt.data) - 5; i++) { + if (name->ptr[i] == '.' || i >= name->len) { + pkt.data[n] = (uint8_t) (i - n); + memcpy(&pkt.data[n + 1], name->ptr + n, i - n); + n = i + 1; + } + if (i >= name->len) break; + } + memcpy(&pkt.data[n], "\x00\x00\x01\x00\x01", 5); // A query + n += 5; + if (ipv6) pkt.data[n - 3] = 0x1c; // AAAA query + // memcpy(&pkt.data[n], "\xc0\x0c\x00\x1c\x00\x01", 6); // AAAA query + // n += 6; + return mg_send(c, &pkt, sizeof(pkt.header) + n); +} + +static void mg_sendnsreq(struct mg_connection *c, struct mg_str *name, int ms, + struct mg_dns *dnsc, bool ipv6) { + struct dns_data *d = NULL; + if (dnsc->url == NULL) { + mg_error(c, "DNS server URL is NULL. Call mg_mgr_init()"); + } else if (dnsc->c == NULL) { + dnsc->c = mg_connect(c->mgr, dnsc->url, NULL, NULL); + if (dnsc->c != NULL) { + dnsc->c->pfn = dns_cb; + // dnsc->c->is_hexdumping = 1; + } + } + if (dnsc->c == NULL) { + mg_error(c, "resolver"); + } else if ((d = (struct dns_data *) calloc(1, sizeof(*d))) == NULL) { + mg_error(c, "resolve OOM"); + } else { + struct dns_data *reqs = (struct dns_data *) c->mgr->active_dns_requests; + d->txnid = reqs ? (uint16_t) (reqs->txnid + 1) : 1; + d->next = (struct dns_data *) c->mgr->active_dns_requests; + c->mgr->active_dns_requests = d; + d->expire = mg_millis() + (uint64_t) ms; + d->c = c; + c->is_resolving = 1; + MG_VERBOSE(("%lu resolving %.*s @ %s, txnid %hu", c->id, (int) name->len, + name->ptr, dnsc->url, d->txnid)); + if (!mg_dns_send(dnsc->c, name, d->txnid, ipv6)) { + mg_error(dnsc->c, "DNS send"); + } + } +} + +void mg_resolve(struct mg_connection *c, const char *url) { + struct mg_str host = mg_url_host(url); + c->rem.port = mg_htons(mg_url_port(url)); + if (mg_aton(host, &c->rem)) { + // host is an IP address, do not fire name resolution + mg_connect_resolved(c); + } else { + // host is not an IP, send DNS resolution request + struct mg_dns *dns = c->mgr->use_dns6 ? &c->mgr->dns6 : &c->mgr->dns4; + mg_sendnsreq(c, &host, c->mgr->dnstimeout, dns, c->mgr->use_dns6); + } +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/event.c" +#endif + + + + + +void mg_call(struct mg_connection *c, int ev, void *ev_data) { + // Run user-defined handler first, in order to give it an ability + // to intercept processing (e.g. clean input buffer) before the + // protocol handler kicks in + if (c->fn != NULL) c->fn(c, ev, ev_data, c->fn_data); + if (c->pfn != NULL) c->pfn(c, ev, ev_data, c->pfn_data); +} + +void mg_error(struct mg_connection *c, const char *fmt, ...) { + char buf[64]; + va_list ap; + va_start(ap, fmt); + mg_vsnprintf(buf, sizeof(buf), fmt, &ap); + va_end(ap); + MG_ERROR(("%lu %p %s", c->id, c->fd, buf)); + c->is_closing = 1; // Set is_closing before sending MG_EV_CALL + mg_call(c, MG_EV_ERROR, buf); // Let user handler to override it +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/fmt.c" +#endif + + + + +static bool is_digit(int c) { + return c >= '0' && c <= '9'; +} + +static int addexp(char *buf, int e, int sign) { + int n = 0; + buf[n++] = 'e'; + buf[n++] = (char) sign; + if (e > 400) return 0; + if (e < 10) buf[n++] = '0'; + if (e >= 100) buf[n++] = (char) (e / 100 + '0'), e -= 100 * (e / 100); + if (e >= 10) buf[n++] = (char) (e / 10 + '0'), e -= 10 * (e / 10); + buf[n++] = (char) (e + '0'); + return n; +} + +static int xisinf(double x) { + union { + double f; + uint64_t u; + } ieee754 = {x}; + return ((unsigned) (ieee754.u >> 32) & 0x7fffffff) == 0x7ff00000 && + ((unsigned) ieee754.u == 0); +} + +static int xisnan(double x) { + union { + double f; + uint64_t u; + } ieee754 = {x}; + return ((unsigned) (ieee754.u >> 32) & 0x7fffffff) + + ((unsigned) ieee754.u != 0) > + 0x7ff00000; +} + +static size_t mg_dtoa(char *dst, size_t dstlen, double d, int width, bool tz) { + char buf[40]; + int i, s = 0, n = 0, e = 0; + double t, mul, saved; + if (d == 0.0) return mg_snprintf(dst, dstlen, "%s", "0"); + if (xisinf(d)) return mg_snprintf(dst, dstlen, "%s", d > 0 ? "inf" : "-inf"); + if (xisnan(d)) return mg_snprintf(dst, dstlen, "%s", "nan"); + if (d < 0.0) d = -d, buf[s++] = '-'; + + // Round + saved = d; + mul = 1.0; + while (d >= 10.0 && d / mul >= 10.0) mul *= 10.0; + while (d <= 1.0 && d / mul <= 1.0) mul /= 10.0; + for (i = 0, t = mul * 5; i < width; i++) t /= 10.0; + d += t; + // Calculate exponent, and 'mul' for scientific representation + mul = 1.0; + while (d >= 10.0 && d / mul >= 10.0) mul *= 10.0, e++; + while (d < 1.0 && d / mul < 1.0) mul /= 10.0, e--; + // printf(" --> %g %d %g %g\n", saved, e, t, mul); + + if (e >= width && width > 1) { + n = (int) mg_dtoa(buf, sizeof(buf), saved / mul, width, tz); + // printf(" --> %.*g %d [%.*s]\n", 10, d / t, e, n, buf); + n += addexp(buf + s + n, e, '+'); + return mg_snprintf(dst, dstlen, "%.*s", n, buf); + } else if (e <= -width && width > 1) { + n = (int) mg_dtoa(buf, sizeof(buf), saved / mul, width, tz); + // printf(" --> %.*g %d [%.*s]\n", 10, d / mul, e, n, buf); + n += addexp(buf + s + n, -e, '-'); + return mg_snprintf(dst, dstlen, "%.*s", n, buf); + } else { + for (i = 0, t = mul; t >= 1.0 && s + n < (int) sizeof(buf); i++) { + int ch = (int) (d / t); + if (n > 0 || ch > 0) buf[s + n++] = (char) (ch + '0'); + d -= ch * t; + t /= 10.0; + } + // printf(" --> [%g] -> %g %g (%d) [%.*s]\n", saved, d, t, n, s + n, buf); + if (n == 0) buf[s++] = '0'; + while (t >= 1.0 && n + s < (int) sizeof(buf)) buf[n++] = '0', t /= 10.0; + if (s + n < (int) sizeof(buf)) buf[n + s++] = '.'; + // printf(" 1--> [%g] -> [%.*s]\n", saved, s + n, buf); + for (i = 0, t = 0.1; s + n < (int) sizeof(buf) && n < width; i++) { + int ch = (int) (d / t); + buf[s + n++] = (char) (ch + '0'); + d -= ch * t; + t /= 10.0; + } + } + while (tz && n > 0 && buf[s + n - 1] == '0') n--; // Trim trailing zeroes + if (n > 0 && buf[s + n - 1] == '.') n--; // Trim trailing dot + n += s; + if (n >= (int) sizeof(buf)) n = (int) sizeof(buf) - 1; + buf[n] = '\0'; + return mg_snprintf(dst, dstlen, "%s", buf); +} + +static size_t mg_lld(char *buf, int64_t val, bool is_signed, bool is_hex) { + const char *letters = "0123456789abcdef"; + uint64_t v = (uint64_t) val; + size_t s = 0, n, i; + if (is_signed && val < 0) buf[s++] = '-', v = (uint64_t) (-val); + // This loop prints a number in reverse order. I guess this is because we + // write numbers from right to left: least significant digit comes last. + // Maybe because we use Arabic numbers, and Arabs write RTL? + if (is_hex) { + for (n = 0; v; v >>= 4) buf[s + n++] = letters[v & 15]; + } else { + for (n = 0; v; v /= 10) buf[s + n++] = letters[v % 10]; + } + // Reverse a string + for (i = 0; i < n / 2; i++) { + char t = buf[s + i]; + buf[s + i] = buf[s + n - i - 1], buf[s + n - i - 1] = t; + } + if (val == 0) buf[n++] = '0'; // Handle special case + return n + s; +} + +static size_t scpy(void (*out)(char, void *), void *ptr, char *buf, + size_t len) { + size_t i = 0; + while (i < len && buf[i] != '\0') out(buf[i++], ptr); + return i; +} + +size_t mg_xprintf(void (*out)(char, void *), void *ptr, const char *fmt, ...) { + size_t len = 0; + va_list ap; + va_start(ap, fmt); + len = mg_vxprintf(out, ptr, fmt, &ap); + va_end(ap); + return len; +} + +size_t mg_vxprintf(void (*out)(char, void *), void *param, const char *fmt, + va_list *ap) { + size_t i = 0, n = 0; + while (fmt[i] != '\0') { + if (fmt[i] == '%') { + size_t j, k, x = 0, is_long = 0, w = 0 /* width */, pr = ~0U /* prec */; + char pad = ' ', minus = 0, c = fmt[++i]; + if (c == '#') x++, c = fmt[++i]; + if (c == '-') minus++, c = fmt[++i]; + if (c == '0') pad = '0', c = fmt[++i]; + while (is_digit(c)) w *= 10, w += (size_t) (c - '0'), c = fmt[++i]; + if (c == '.') { + c = fmt[++i]; + if (c == '*') { + pr = (size_t) va_arg(*ap, int); + c = fmt[++i]; + } else { + pr = 0; + while (is_digit(c)) pr *= 10, pr += (size_t) (c - '0'), c = fmt[++i]; + } + } + while (c == 'h') c = fmt[++i]; // Treat h and hh as int + if (c == 'l') { + is_long++, c = fmt[++i]; + if (c == 'l') is_long++, c = fmt[++i]; + } + if (c == 'p') x = 1, is_long = 1; + if (c == 'd' || c == 'u' || c == 'x' || c == 'X' || c == 'p' || + c == 'g' || c == 'f') { + bool s = (c == 'd'), h = (c == 'x' || c == 'X' || c == 'p'); + char tmp[40]; + size_t xl = x ? 2 : 0; + if (c == 'g' || c == 'f') { + double v = va_arg(*ap, double); + if (pr == ~0U) pr = 6; + k = mg_dtoa(tmp, sizeof(tmp), v, (int) pr, c == 'g'); + } else if (is_long == 2) { + int64_t v = va_arg(*ap, int64_t); + k = mg_lld(tmp, v, s, h); + } else if (is_long == 1) { + long v = va_arg(*ap, long); + k = mg_lld(tmp, s ? (int64_t) v : (int64_t) (unsigned long) v, s, h); + } else { + int v = va_arg(*ap, int); + k = mg_lld(tmp, s ? (int64_t) v : (int64_t) (unsigned) v, s, h); + } + for (j = 0; j < xl && w > 0; j++) w--; + for (j = 0; pad == ' ' && !minus && k < w && j + k < w; j++) + n += scpy(out, param, &pad, 1); + n += scpy(out, param, (char *) "0x", xl); + for (j = 0; pad == '0' && k < w && j + k < w; j++) + n += scpy(out, param, &pad, 1); + n += scpy(out, param, tmp, k); + for (j = 0; pad == ' ' && minus && k < w && j + k < w; j++) + n += scpy(out, param, &pad, 1); + } else if (c == 'm' || c == 'M') { + mg_pm_t f = va_arg(*ap, mg_pm_t); + if (c == 'm') out('"', param); + n += f(out, param, ap); + if (c == 'm') n += 2, out('"', param); + } else if (c == 'c') { + int ch = va_arg(*ap, int); + out((char) ch, param); + n++; + } else if (c == 's') { + char *p = va_arg(*ap, char *); + if (pr == ~0U) pr = p == NULL ? 0 : strlen(p); + for (j = 0; !minus && pr < w && j + pr < w; j++) + n += scpy(out, param, &pad, 1); + n += scpy(out, param, p, pr); + for (j = 0; minus && pr < w && j + pr < w; j++) + n += scpy(out, param, &pad, 1); + } else if (c == '%') { + out('%', param); + n++; + } else { + out('%', param); + out(c, param); + n += 2; + } + i++; + } else { + out(fmt[i], param), n++, i++; + } + } + return n; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/fs.c" +#endif + + + +struct mg_fd *mg_fs_open(struct mg_fs *fs, const char *path, int flags) { + struct mg_fd *fd = (struct mg_fd *) calloc(1, sizeof(*fd)); + if (fd != NULL) { + fd->fd = fs->op(path, flags); + fd->fs = fs; + if (fd->fd == NULL) { + free(fd); + fd = NULL; + } + } + return fd; +} + +void mg_fs_close(struct mg_fd *fd) { + if (fd != NULL) { + fd->fs->cl(fd->fd); + free(fd); + } +} + +char *mg_file_read(struct mg_fs *fs, const char *path, size_t *sizep) { + struct mg_fd *fd; + char *data = NULL; + size_t size = 0; + fs->st(path, &size, NULL); + if ((fd = mg_fs_open(fs, path, MG_FS_READ)) != NULL) { + data = (char *) calloc(1, size + 1); + if (data != NULL) { + if (fs->rd(fd->fd, data, size) != size) { + free(data); + data = NULL; + } else { + data[size] = '\0'; + if (sizep != NULL) *sizep = size; + } + } + mg_fs_close(fd); + } + return data; +} + +bool mg_file_write(struct mg_fs *fs, const char *path, const void *buf, + size_t len) { + bool result = false; + struct mg_fd *fd; + char tmp[MG_PATH_MAX]; + mg_snprintf(tmp, sizeof(tmp), "%s..%d", path, rand()); + if ((fd = mg_fs_open(fs, tmp, MG_FS_WRITE)) != NULL) { + result = fs->wr(fd->fd, buf, len) == len; + mg_fs_close(fd); + if (result) { + fs->rm(path); + fs->mv(tmp, path); + } else { + fs->rm(tmp); + } + } + return result; +} + +bool mg_file_printf(struct mg_fs *fs, const char *path, const char *fmt, ...) { + va_list ap; + char *data; + bool result = false; + va_start(ap, fmt); + data = mg_vmprintf(fmt, &ap); + va_end(ap); + result = mg_file_write(fs, path, data, strlen(data)); + free(data); + return result; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/fs_fat.c" +#endif + + + +#if MG_ENABLE_FATFS +#include + +static int mg_days_from_epoch(int y, int m, int d) { + y -= m <= 2; + int era = y / 400; + int yoe = y - era * 400; + int doy = (153 * (m + (m > 2 ? -3 : 9)) + 2) / 5 + d - 1; + int doe = yoe * 365 + yoe / 4 - yoe / 100 + doy; + return era * 146097 + doe - 719468; +} + +static time_t mg_timegm(const struct tm *t) { + int year = t->tm_year + 1900; + int month = t->tm_mon; // 0-11 + if (month > 11) { + year += month / 12; + month %= 12; + } else if (month < 0) { + int years_diff = (11 - month) / 12; + year -= years_diff; + month += 12 * years_diff; + } + int x = mg_days_from_epoch(year, month + 1, t->tm_mday); + return 60 * (60 * (24L * x + t->tm_hour) + t->tm_min) + t->tm_sec; +} + +static time_t ff_time_to_epoch(uint16_t fdate, uint16_t ftime) { + struct tm tm; + memset(&tm, 0, sizeof(struct tm)); + tm.tm_sec = (ftime << 1) & 0x3e; + tm.tm_min = ((ftime >> 5) & 0x3f); + tm.tm_hour = ((ftime >> 11) & 0x1f); + tm.tm_mday = (fdate & 0x1f); + tm.tm_mon = ((fdate >> 5) & 0x0f) - 1; + tm.tm_year = ((fdate >> 9) & 0x7f) + 80; + return mg_timegm(&tm); +} + +static int ff_stat(const char *path, size_t *size, time_t *mtime) { + FILINFO fi; + if (path[0] == '\0') { + if (size) *size = 0; + if (mtime) *mtime = 0; + return MG_FS_DIR; + } else if (f_stat(path, &fi) == 0) { + if (size) *size = (size_t) fi.fsize; + if (mtime) *mtime = ff_time_to_epoch(fi.fdate, fi.ftime); + return MG_FS_READ | MG_FS_WRITE | ((fi.fattrib & AM_DIR) ? MG_FS_DIR : 0); + } else { + return 0; + } +} + +static void ff_list(const char *dir, void (*fn)(const char *, void *), + void *userdata) { + DIR d; + FILINFO fi; + if (f_opendir(&d, dir) == FR_OK) { + while (f_readdir(&d, &fi) == FR_OK && fi.fname[0] != '\0') { + if (!strcmp(fi.fname, ".") || !strcmp(fi.fname, "..")) continue; + fn(fi.fname, userdata); + } + f_closedir(&d); + } +} + +static void *ff_open(const char *path, int flags) { + FIL f; + unsigned char mode = FA_READ; + if (flags & MG_FS_WRITE) mode |= FA_WRITE | FA_OPEN_ALWAYS | FA_OPEN_APPEND; + if (f_open(&f, path, mode) == 0) { + FIL *fp; + if ((fp = calloc(1, sizeof(*fp))) != NULL) { + memcpy(fp, &f, sizeof(*fp)); + return fp; + } + } + return NULL; +} + +static void ff_close(void *fp) { + if (fp != NULL) { + f_close((FIL *) fp); + free(fp); + } +} + +static size_t ff_read(void *fp, void *buf, size_t len) { + UINT n = 0, misalign = ((size_t) buf) & 3; + if (misalign) { + char aligned[4]; + f_read((FIL *) fp, aligned, len > misalign ? misalign : len, &n); + memcpy(buf, aligned, n); + } else { + f_read((FIL *) fp, buf, len, &n); + } + return n; +} + +static size_t ff_write(void *fp, const void *buf, size_t len) { + UINT n = 0; + return f_write((FIL *) fp, (char *) buf, len, &n) == FR_OK ? n : 0; +} + +static size_t ff_seek(void *fp, size_t offset) { + f_lseek((FIL *) fp, offset); + return offset; +} + +static bool ff_rename(const char *from, const char *to) { + return f_rename(from, to) == FR_OK; +} + +static bool ff_remove(const char *path) { + return f_unlink(path) == FR_OK; +} + +static bool ff_mkdir(const char *path) { + return f_mkdir(path) == FR_OK; +} + +struct mg_fs mg_fs_fat = {ff_stat, ff_list, ff_open, ff_close, ff_read, + ff_write, ff_seek, ff_rename, ff_remove, ff_mkdir}; +#endif + +#ifdef MG_ENABLE_LINES +#line 1 "src/fs_packed.c" +#endif + + + + +struct packed_file { + const char *data; + size_t size; + size_t pos; +}; + +const char *mg_unpack(const char *path, size_t *size, time_t *mtime); +const char *mg_unlist(size_t no); + +#if MG_ENABLE_PACKED_FS +#else +const char *mg_unpack(const char *path, size_t *size, time_t *mtime) { + (void) path, (void) size, (void) mtime; + return NULL; +} +const char *mg_unlist(size_t no) { + (void) no; + return NULL; +} +#endif + +static int is_dir_prefix(const char *prefix, size_t n, const char *path) { + // MG_INFO(("[%.*s] [%s] %c", (int) n, prefix, path, path[n])); + return n < strlen(path) && strncmp(prefix, path, n) == 0 && + (n == 0 || path[n] == '/' || path[n - 1] == '/'); +} + +static int packed_stat(const char *path, size_t *size, time_t *mtime) { + const char *p; + size_t i, n = strlen(path); + if (mg_unpack(path, size, mtime)) return MG_FS_READ; // Regular file + // Scan all files. If `path` is a dir prefix for any of them, it's a dir + for (i = 0; (p = mg_unlist(i)) != NULL; i++) { + if (is_dir_prefix(path, n, p)) return MG_FS_DIR; + } + return 0; +} + +static void packed_list(const char *dir, void (*fn)(const char *, void *), + void *userdata) { + char buf[MG_PATH_MAX], tmp[sizeof(buf)]; + const char *path, *begin, *end; + size_t i, n = strlen(dir); + tmp[0] = '\0'; // Previously listed entry + for (i = 0; (path = mg_unlist(i)) != NULL; i++) { + if (!is_dir_prefix(dir, n, path)) continue; + begin = &path[n + 1]; + end = strchr(begin, '/'); + if (end == NULL) end = begin + strlen(begin); + mg_snprintf(buf, sizeof(buf), "%.*s", (int) (end - begin), begin); + buf[sizeof(buf) - 1] = '\0'; + // If this entry has been already listed, skip + // NOTE: we're assuming that file list is sorted alphabetically + if (strcmp(buf, tmp) == 0) continue; + fn(buf, userdata); // Not yet listed, call user function + strcpy(tmp, buf); // And save this entry as listed + } +} + +static void *packed_open(const char *path, int flags) { + size_t size = 0; + const char *data = mg_unpack(path, &size, NULL); + struct packed_file *fp = NULL; + if (data == NULL) return NULL; + if (flags & MG_FS_WRITE) return NULL; + if ((fp = (struct packed_file *) calloc(1, sizeof(*fp))) != NULL) { + fp->size = size; + fp->data = data; + } + return (void *) fp; +} + +static void packed_close(void *fp) { + if (fp != NULL) free(fp); +} + +static size_t packed_read(void *fd, void *buf, size_t len) { + struct packed_file *fp = (struct packed_file *) fd; + if (fp->pos + len > fp->size) len = fp->size - fp->pos; + memcpy(buf, &fp->data[fp->pos], len); + fp->pos += len; + return len; +} + +static size_t packed_write(void *fd, const void *buf, size_t len) { + (void) fd, (void) buf, (void) len; + return 0; +} + +static size_t packed_seek(void *fd, size_t offset) { + struct packed_file *fp = (struct packed_file *) fd; + fp->pos = offset; + if (fp->pos > fp->size) fp->pos = fp->size; + return fp->pos; +} + +static bool packed_rename(const char *from, const char *to) { + (void) from, (void) to; + return false; +} + +static bool packed_remove(const char *path) { + (void) path; + return false; +} + +static bool packed_mkdir(const char *path) { + (void) path; + return false; +} + +struct mg_fs mg_fs_packed = { + packed_stat, packed_list, packed_open, packed_close, packed_read, + packed_write, packed_seek, packed_rename, packed_remove, packed_mkdir}; + +#ifdef MG_ENABLE_LINES +#line 1 "src/fs_posix.c" +#endif + + +#if MG_ENABLE_FILE + +#ifndef MG_STAT_STRUCT +#define MG_STAT_STRUCT stat +#endif + +#ifndef MG_STAT_FUNC +#define MG_STAT_FUNC stat +#endif + +static int p_stat(const char *path, size_t *size, time_t *mtime) { +#if !defined(S_ISDIR) + MG_ERROR(("stat() API is not supported. %p %p %p", path, size, mtime)); + return 0; +#else +#if MG_ARCH == MG_ARCH_WIN32 + struct _stati64 st; + wchar_t tmp[MG_PATH_MAX]; + MultiByteToWideChar(CP_UTF8, 0, path, -1, tmp, sizeof(tmp) / sizeof(tmp[0])); + if (_wstati64(tmp, &st) != 0) return 0; + // If path is a symlink, windows reports 0 in st.st_size. + // Get a real file size by opening it and jumping to the end + if (st.st_size == 0 && (st.st_mode & _S_IFREG)) { + FILE *fp = _wfopen(tmp, L"rb"); + if (fp != NULL) { + fseek(fp, 0, SEEK_END); + if (ftell(fp) > 0) st.st_size = ftell(fp); // Use _ftelli64 on win10+ + fclose(fp); + } + } +#else + struct MG_STAT_STRUCT st; + if (MG_STAT_FUNC(path, &st) != 0) return 0; +#endif + if (size) *size = (size_t) st.st_size; + if (mtime) *mtime = st.st_mtime; + return MG_FS_READ | MG_FS_WRITE | (S_ISDIR(st.st_mode) ? MG_FS_DIR : 0); +#endif +} + +#if MG_ARCH == MG_ARCH_WIN32 +struct dirent { + char d_name[MAX_PATH]; +}; + +typedef struct win32_dir { + HANDLE handle; + WIN32_FIND_DATAW info; + struct dirent result; +} DIR; + +int gettimeofday(struct timeval *tv, void *tz) { + FILETIME ft; + unsigned __int64 tmpres = 0; + + if (tv != NULL) { + GetSystemTimeAsFileTime(&ft); + tmpres |= ft.dwHighDateTime; + tmpres <<= 32; + tmpres |= ft.dwLowDateTime; + tmpres /= 10; // convert into microseconds + tmpres -= (int64_t) 11644473600000000; + tv->tv_sec = (long) (tmpres / 1000000UL); + tv->tv_usec = (long) (tmpres % 1000000UL); + } + (void) tz; + return 0; +} + +static int to_wchar(const char *path, wchar_t *wbuf, size_t wbuf_len) { + int ret; + char buf[MAX_PATH * 2], buf2[MAX_PATH * 2], *p; + strncpy(buf, path, sizeof(buf)); + buf[sizeof(buf) - 1] = '\0'; + // Trim trailing slashes. Leave backslash for paths like "X:\" + p = buf + strlen(buf) - 1; + while (p > buf && p[-1] != ':' && (p[0] == '\\' || p[0] == '/')) *p-- = '\0'; + memset(wbuf, 0, wbuf_len * sizeof(wchar_t)); + ret = MultiByteToWideChar(CP_UTF8, 0, buf, -1, wbuf, (int) wbuf_len); + // Convert back to Unicode. If doubly-converted string does not match the + // original, something is fishy, reject. + WideCharToMultiByte(CP_UTF8, 0, wbuf, (int) wbuf_len, buf2, sizeof(buf2), + NULL, NULL); + if (strcmp(buf, buf2) != 0) { + wbuf[0] = L'\0'; + ret = 0; + } + return ret; +} + +DIR *opendir(const char *name) { + DIR *d = NULL; + wchar_t wpath[MAX_PATH]; + DWORD attrs; + + if (name == NULL) { + SetLastError(ERROR_BAD_ARGUMENTS); + } else if ((d = (DIR *) calloc(1, sizeof(*d))) == NULL) { + SetLastError(ERROR_NOT_ENOUGH_MEMORY); + } else { + to_wchar(name, wpath, sizeof(wpath) / sizeof(wpath[0])); + attrs = GetFileAttributesW(wpath); + if (attrs != 0Xffffffff && (attrs & FILE_ATTRIBUTE_DIRECTORY)) { + (void) wcscat(wpath, L"\\*"); + d->handle = FindFirstFileW(wpath, &d->info); + d->result.d_name[0] = '\0'; + } else { + free(d); + d = NULL; + } + } + return d; +} + +int closedir(DIR *d) { + int result = 0; + if (d != NULL) { + if (d->handle != INVALID_HANDLE_VALUE) + result = FindClose(d->handle) ? 0 : -1; + free(d); + } else { + result = -1; + SetLastError(ERROR_BAD_ARGUMENTS); + } + return result; +} + +struct dirent *readdir(DIR *d) { + struct dirent *result = NULL; + if (d != NULL) { + memset(&d->result, 0, sizeof(d->result)); + if (d->handle != INVALID_HANDLE_VALUE) { + result = &d->result; + WideCharToMultiByte(CP_UTF8, 0, d->info.cFileName, -1, result->d_name, + sizeof(result->d_name), NULL, NULL); + if (!FindNextFileW(d->handle, &d->info)) { + FindClose(d->handle); + d->handle = INVALID_HANDLE_VALUE; + } + } else { + SetLastError(ERROR_FILE_NOT_FOUND); + } + } else { + SetLastError(ERROR_BAD_ARGUMENTS); + } + return result; +} +#endif + +static void p_list(const char *dir, void (*fn)(const char *, void *), + void *userdata) { +#if MG_ENABLE_DIRLIST + struct dirent *dp; + DIR *dirp; + if ((dirp = (opendir(dir))) == NULL) return; + while ((dp = readdir(dirp)) != NULL) { + if (!strcmp(dp->d_name, ".") || !strcmp(dp->d_name, "..")) continue; + fn(dp->d_name, userdata); + } + closedir(dirp); +#else + (void) dir, (void) fn, (void) userdata; +#endif +} + +static void *p_open(const char *path, int flags) { + const char *mode = flags == MG_FS_READ ? "rb" : "a+b"; +#if MG_ARCH == MG_ARCH_WIN32 + wchar_t b1[MG_PATH_MAX], b2[10]; + MultiByteToWideChar(CP_UTF8, 0, path, -1, b1, sizeof(b1) / sizeof(b1[0])); + MultiByteToWideChar(CP_UTF8, 0, mode, -1, b2, sizeof(b2) / sizeof(b2[0])); + return (void *) _wfopen(b1, b2); +#else + return (void *) fopen(path, mode); +#endif +} + +static void p_close(void *fp) { + fclose((FILE *) fp); +} + +static size_t p_read(void *fp, void *buf, size_t len) { + return fread(buf, 1, len, (FILE *) fp); +} + +static size_t p_write(void *fp, const void *buf, size_t len) { + return fwrite(buf, 1, len, (FILE *) fp); +} + +static size_t p_seek(void *fp, size_t offset) { +#if (defined(_FILE_OFFSET_BITS) && _FILE_OFFSET_BITS == 64) || \ + (defined(_POSIX_C_SOURCE) && _POSIX_C_SOURCE >= 200112L) || \ + (defined(_XOPEN_SOURCE) && _XOPEN_SOURCE >= 600) + if (fseeko((FILE *) fp, (off_t) offset, SEEK_SET) != 0) (void) 0; +#else + if (fseek((FILE *) fp, (long) offset, SEEK_SET) != 0) (void) 0; +#endif + return (size_t) ftell((FILE *) fp); +} + +static bool p_rename(const char *from, const char *to) { + return rename(from, to) == 0; +} + +static bool p_remove(const char *path) { + return remove(path) == 0; +} + +static bool p_mkdir(const char *path) { + return mkdir(path, 0775) == 0; +} + +#else + +static int p_stat(const char *path, size_t *size, time_t *mtime) { + (void) path, (void) size, (void) mtime; + return 0; +} +static void p_list(const char *path, void (*fn)(const char *, void *), + void *userdata) { + (void) path, (void) fn, (void) userdata; +} +static void *p_open(const char *path, int flags) { + (void) path, (void) flags; + return NULL; +} +static void p_close(void *fp) { + (void) fp; +} +static size_t p_read(void *fd, void *buf, size_t len) { + (void) fd, (void) buf, (void) len; + return 0; +} +static size_t p_write(void *fd, const void *buf, size_t len) { + (void) fd, (void) buf, (void) len; + return 0; +} +static size_t p_seek(void *fd, size_t offset) { + (void) fd, (void) offset; + return (size_t) ~0; +} +static bool p_rename(const char *from, const char *to) { + (void) from, (void) to; + return false; +} +static bool p_remove(const char *path) { + (void) path; + return false; +} +static bool p_mkdir(const char *path) { + (void) path; + return false; +} +#endif + +struct mg_fs mg_fs_posix = {p_stat, p_list, p_open, p_close, p_read, + p_write, p_seek, p_rename, p_remove, p_mkdir}; + +#ifdef MG_ENABLE_LINES +#line 1 "src/http.c" +#endif + + + + + + + + + + + + + +// Chunk deletion marker is the MSB in the "processed" counter +#define MG_DMARK ((size_t) 1 << (sizeof(size_t) * 8 - 1)) + +// Multipart POST example: +// --xyz +// Content-Disposition: form-data; name="val" +// +// abcdef +// --xyz +// Content-Disposition: form-data; name="foo"; filename="a.txt" +// Content-Type: text/plain +// +// hello world +// +// --xyz-- +size_t mg_http_next_multipart(struct mg_str body, size_t ofs, + struct mg_http_part *part) { + struct mg_str cd = mg_str_n("Content-Disposition", 19); + const char *s = body.ptr; + size_t b = ofs, h1, h2, b1, b2, max = body.len; + + // Init part params + if (part != NULL) part->name = part->filename = part->body = mg_str_n(0, 0); + + // Skip boundary + while (b + 2 < max && s[b] != '\r' && s[b + 1] != '\n') b++; + if (b <= ofs || b + 2 >= max) return 0; + // MG_INFO(("B: %zu %zu [%.*s]", ofs, b - ofs, (int) (b - ofs), s)); + + // Skip headers + h1 = h2 = b + 2; + for (;;) { + while (h2 + 2 < max && s[h2] != '\r' && s[h2 + 1] != '\n') h2++; + if (h2 == h1) break; + if (h2 + 2 >= max) return 0; + // MG_INFO(("Header: [%.*s]", (int) (h2 - h1), &s[h1])); + if (part != NULL && h1 + cd.len + 2 < h2 && s[h1 + cd.len] == ':' && + mg_ncasecmp(&s[h1], cd.ptr, cd.len) == 0) { + struct mg_str v = mg_str_n(&s[h1 + cd.len + 2], h2 - (h1 + cd.len + 2)); + part->name = mg_http_get_header_var(v, mg_str_n("name", 4)); + part->filename = mg_http_get_header_var(v, mg_str_n("filename", 8)); + } + h1 = h2 = h2 + 2; + } + b1 = b2 = h2 + 2; + while (b2 + 2 + (b - ofs) + 2 < max && !(s[b2] == '\r' && s[b2 + 1] == '\n' && + memcmp(&s[b2 + 2], s, b - ofs) == 0)) + b2++; + + if (b2 + 2 >= max) return 0; + if (part != NULL) part->body = mg_str_n(&s[b1], b2 - b1); + // MG_INFO(("Body: [%.*s]", (int) (b2 - b1), &s[b1])); + return b2 + 2; +} + +void mg_http_bauth(struct mg_connection *c, const char *user, + const char *pass) { + struct mg_str u = mg_str(user), p = mg_str(pass); + size_t need = c->send.len + 36 + (u.len + p.len) * 2; + if (c->send.size < need) mg_iobuf_resize(&c->send, need); + if (c->send.size >= need) { + int i, n = 0; + char *buf = (char *) &c->send.buf[c->send.len]; + memcpy(buf, "Authorization: Basic ", 21); // DON'T use mg_send! + for (i = 0; i < (int) u.len; i++) { + n = mg_base64_update(((unsigned char *) u.ptr)[i], buf + 21, n); + } + if (p.len > 0) { + n = mg_base64_update(':', buf + 21, n); + for (i = 0; i < (int) p.len; i++) { + n = mg_base64_update(((unsigned char *) p.ptr)[i], buf + 21, n); + } + } + n = mg_base64_final(buf + 21, n); + c->send.len += 21 + (size_t) n + 2; + memcpy(&c->send.buf[c->send.len - 2], "\r\n", 2); + } else { + MG_ERROR(("%lu oom %d->%d ", c->id, (int) c->send.size, (int) need)); + } +} + +struct mg_str mg_http_var(struct mg_str buf, struct mg_str name) { + struct mg_str k, v, result = mg_str_n(NULL, 0); + while (mg_split(&buf, &k, &v, '&')) { + if (name.len == k.len && mg_ncasecmp(name.ptr, k.ptr, k.len) == 0) { + result = v; + break; + } + } + return result; +} + +int mg_http_get_var(const struct mg_str *buf, const char *name, char *dst, + size_t dst_len) { + int len; + if (dst == NULL || dst_len == 0) { + len = -2; // Bad destination + } else if (buf->ptr == NULL || name == NULL || buf->len == 0) { + len = -1; // Bad source + dst[0] = '\0'; + } else { + struct mg_str v = mg_http_var(*buf, mg_str(name)); + if (v.ptr == NULL) { + len = -4; // Name does not exist + } else { + len = mg_url_decode(v.ptr, v.len, dst, dst_len, 1); + if (len < 0) len = -3; // Failed to decode + } + } + return len; +} + +static bool isx(int c) { + return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || + (c >= 'A' && c <= 'F'); +} + +int mg_url_decode(const char *src, size_t src_len, char *dst, size_t dst_len, + int is_form_url_encoded) { + size_t i, j; + for (i = j = 0; i < src_len && j + 1 < dst_len; i++, j++) { + if (src[i] == '%') { + // Use `i + 2 < src_len`, not `i < src_len - 2`, note small src_len + if (i + 2 < src_len && isx(src[i + 1]) && isx(src[i + 2])) { + mg_unhex(src + i + 1, 2, (uint8_t *) &dst[j]); + i += 2; + } else { + return -1; + } + } else if (is_form_url_encoded && src[i] == '+') { + dst[j] = ' '; + } else { + dst[j] = src[i]; + } + } + if (j < dst_len) dst[j] = '\0'; // Null-terminate the destination + return i >= src_len && j < dst_len ? (int) j : -1; +} + +static bool isok(uint8_t c) { return c == '\n' || c == '\r' || c >= ' '; } + +int mg_http_get_request_len(const unsigned char *buf, size_t buf_len) { + size_t i; + for (i = 0; i < buf_len; i++) { + if (!isok(buf[i])) return -1; + if ((i > 0 && buf[i] == '\n' && buf[i - 1] == '\n') || + (i > 3 && buf[i] == '\n' && buf[i - 1] == '\r' && buf[i - 2] == '\n')) + return (int) i + 1; + } + return 0; +} + +static const char *skip(const char *s, const char *e, const char *d, + struct mg_str *v) { + v->ptr = s; + while (s < e && *s != '\n' && strchr(d, *s) == NULL) s++; + v->len = (size_t) (s - v->ptr); + while (s < e && strchr(d, *s) != NULL) s++; + return s; +} + +struct mg_str *mg_http_get_header(struct mg_http_message *h, const char *name) { + size_t i, n = strlen(name), max = sizeof(h->headers) / sizeof(h->headers[0]); + for (i = 0; i < max && h->headers[i].name.len > 0; i++) { + struct mg_str *k = &h->headers[i].name, *v = &h->headers[i].value; + if (n == k->len && mg_ncasecmp(k->ptr, name, n) == 0) return v; + } + return NULL; +} + +static void mg_http_parse_headers(const char *s, const char *end, + struct mg_http_header *h, int max_headers) { + int i; + for (i = 0; i < max_headers; i++) { + struct mg_str k, v, tmp; + const char *he = skip(s, end, "\n", &tmp); + s = skip(s, he, ": \r\n", &k); + s = skip(s, he, "\r\n", &v); + if (k.len == tmp.len) continue; + while (v.len > 0 && v.ptr[v.len - 1] == ' ') v.len--; // Trim spaces + if (k.len == 0) break; + // MG_INFO(("--HH [%.*s] [%.*s] [%.*s]", (int) tmp.len - 1, tmp.ptr, + //(int) k.len, k.ptr, (int) v.len, v.ptr)); + h[i].name = k; + h[i].value = v; + } +} + +int mg_http_parse(const char *s, size_t len, struct mg_http_message *hm) { + int is_response, req_len = mg_http_get_request_len((unsigned char *) s, len); + const char *end = s == NULL ? NULL : s + req_len, *qs; // Cannot add to NULL + struct mg_str *cl; + + memset(hm, 0, sizeof(*hm)); + if (req_len <= 0) return req_len; + + hm->message.ptr = hm->head.ptr = s; + hm->body.ptr = end; + hm->head.len = (size_t) req_len; + hm->chunk.ptr = end; + hm->message.len = hm->body.len = (size_t) ~0; // Set body length to infinite + + // Parse request line + s = skip(s, end, " ", &hm->method); + s = skip(s, end, " ", &hm->uri); + s = skip(s, end, "\r\n", &hm->proto); + + // Sanity check. Allow protocol/reason to be empty + if (hm->method.len == 0 || hm->uri.len == 0) return -1; + + // If URI contains '?' character, setup query string + if ((qs = (const char *) memchr(hm->uri.ptr, '?', hm->uri.len)) != NULL) { + hm->query.ptr = qs + 1; + hm->query.len = (size_t) (&hm->uri.ptr[hm->uri.len] - (qs + 1)); + hm->uri.len = (size_t) (qs - hm->uri.ptr); + } + + mg_http_parse_headers(s, end, hm->headers, + sizeof(hm->headers) / sizeof(hm->headers[0])); + if ((cl = mg_http_get_header(hm, "Content-Length")) != NULL) { + int64_t content_len = mg_to64(*cl); + if(content_len < 0) return -1; + hm->body.len = (size_t) content_len; + hm->message.len = (size_t) req_len + hm->body.len; + } + + // mg_http_parse() is used to parse both HTTP requests and HTTP + // responses. If HTTP response does not have Content-Length set, then + // body is read until socket is closed, i.e. body.len is infinite (~0). + // + // For HTTP requests though, according to + // http://tools.ietf.org/html/rfc7231#section-8.1.3, + // only POST and PUT methods have defined body semantics. + // Therefore, if Content-Length is not specified and methods are + // not one of PUT or POST, set body length to 0. + // + // So, if it is HTTP request, and Content-Length is not set, + // and method is not (PUT or POST) then reset body length to zero. + is_response = mg_ncasecmp(hm->method.ptr, "HTTP/", 5) == 0; + if (hm->body.len == (size_t) ~0 && !is_response && + mg_vcasecmp(&hm->method, "PUT") != 0 && + mg_vcasecmp(&hm->method, "POST") != 0) { + hm->body.len = 0; + hm->message.len = (size_t) req_len; + } + + // The 204 (No content) responses also have 0 body length + if (hm->body.len == (size_t) ~0 && is_response && + mg_vcasecmp(&hm->uri, "204") == 0) { + hm->body.len = 0; + hm->message.len = (size_t) req_len; + } + + return req_len; +} + +static void mg_http_vprintf_chunk(struct mg_connection *c, const char *fmt, + va_list *ap) { + size_t len = c->send.len; + mg_send(c, " \r\n", 10); + mg_vxprintf(mg_pfn_iobuf, &c->send, fmt, ap); + if (c->send.len >= len + 10) { + mg_snprintf((char *) c->send.buf + len, 9, "%08lx", c->send.len - len - 10); + c->send.buf[len + 8] = '\r'; + if (c->send.len == len + 10) c->is_resp = 0; // Last chunk, reset marker + } + mg_send(c, "\r\n", 2); +} + +void mg_http_printf_chunk(struct mg_connection *c, const char *fmt, ...) { + va_list ap; + va_start(ap, fmt); + mg_http_vprintf_chunk(c, fmt, &ap); + va_end(ap); +} + +void mg_http_write_chunk(struct mg_connection *c, const char *buf, size_t len) { + mg_printf(c, "%lx\r\n", (unsigned long) len); + mg_send(c, buf, len); + mg_send(c, "\r\n", 2); + if (len == 0) c->is_resp = 0; +} + +// clang-format off +static const char *mg_http_status_code_str(int status_code) { + switch (status_code) { + case 100: return "Continue"; + case 201: return "Created"; + case 202: return "Accepted"; + case 204: return "No Content"; + case 206: return "Partial Content"; + case 301: return "Moved Permanently"; + case 302: return "Found"; + case 304: return "Not Modified"; + case 400: return "Bad Request"; + case 401: return "Unauthorized"; + case 403: return "Forbidden"; + case 404: return "Not Found"; + case 418: return "I'm a teapot"; + case 500: return "Internal Server Error"; + case 501: return "Not Implemented"; + default: return "OK"; + } +} +// clang-format on + +void mg_http_reply(struct mg_connection *c, int code, const char *headers, + const char *fmt, ...) { + va_list ap; + size_t len; + mg_printf(c, "HTTP/1.1 %d %s\r\n%sContent-Length: \r\n\r\n", code, + mg_http_status_code_str(code), headers == NULL ? "" : headers); + len = c->send.len; + va_start(ap, fmt); + mg_vxprintf(mg_pfn_iobuf, &c->send, fmt, &ap); + va_end(ap); + if (c->send.len > 16) { + size_t n = mg_snprintf((char *) &c->send.buf[len - 15], 11, "%-10lu", + (unsigned long) (c->send.len - len)); + c->send.buf[len - 15 + n] = ' '; // Change ending 0 to space + } + c->is_resp = 0; +} + +static void http_cb(struct mg_connection *, int, void *, void *); +static void restore_http_cb(struct mg_connection *c) { + mg_fs_close((struct mg_fd *) c->pfn_data); + c->pfn_data = NULL; + c->pfn = http_cb; + c->is_resp = 0; +} + +char *mg_http_etag(char *buf, size_t len, size_t size, time_t mtime); +char *mg_http_etag(char *buf, size_t len, size_t size, time_t mtime) { + mg_snprintf(buf, len, "\"%lld.%lld\"", (int64_t) mtime, (int64_t) size); + return buf; +} + +static void static_cb(struct mg_connection *c, int ev, void *ev_data, + void *fn_data) { + if (ev == MG_EV_WRITE || ev == MG_EV_POLL) { + struct mg_fd *fd = (struct mg_fd *) fn_data; + // Read to send IO buffer directly, avoid extra on-stack buffer + size_t n, max = MG_IO_SIZE, space; + size_t *cl = (size_t *) &c->data[(sizeof(c->data) - sizeof(size_t)) / + sizeof(size_t) * sizeof(size_t)]; + if (c->send.size < max) mg_iobuf_resize(&c->send, max); + if (c->send.len >= c->send.size) return; // Rate limit + if ((space = c->send.size - c->send.len) > *cl) space = *cl; + n = fd->fs->rd(fd->fd, c->send.buf + c->send.len, space); + c->send.len += n; + *cl -= n; + if (n == 0) restore_http_cb(c); + } else if (ev == MG_EV_CLOSE) { + restore_http_cb(c); + } + (void) ev_data; +} + +// Known mime types. Keep it outside guess_content_type() function, since +// some environments don't like it defined there. +// clang-format off +static struct mg_str s_known_types[] = { + MG_C_STR("html"), MG_C_STR("text/html; charset=utf-8"), + MG_C_STR("htm"), MG_C_STR("text/html; charset=utf-8"), + MG_C_STR("css"), MG_C_STR("text/css; charset=utf-8"), + MG_C_STR("js"), MG_C_STR("text/javascript; charset=utf-8"), + MG_C_STR("gif"), MG_C_STR("image/gif"), + MG_C_STR("png"), MG_C_STR("image/png"), + MG_C_STR("jpg"), MG_C_STR("image/jpeg"), + MG_C_STR("jpeg"), MG_C_STR("image/jpeg"), + MG_C_STR("woff"), MG_C_STR("font/woff"), + MG_C_STR("ttf"), MG_C_STR("font/ttf"), + MG_C_STR("svg"), MG_C_STR("image/svg+xml"), + MG_C_STR("txt"), MG_C_STR("text/plain; charset=utf-8"), + MG_C_STR("avi"), MG_C_STR("video/x-msvideo"), + MG_C_STR("csv"), MG_C_STR("text/csv"), + MG_C_STR("doc"), MG_C_STR("application/msword"), + MG_C_STR("exe"), MG_C_STR("application/octet-stream"), + MG_C_STR("gz"), MG_C_STR("application/gzip"), + MG_C_STR("ico"), MG_C_STR("image/x-icon"), + MG_C_STR("json"), MG_C_STR("application/json"), + MG_C_STR("mov"), MG_C_STR("video/quicktime"), + MG_C_STR("mp3"), MG_C_STR("audio/mpeg"), + MG_C_STR("mp4"), MG_C_STR("video/mp4"), + MG_C_STR("mpeg"), MG_C_STR("video/mpeg"), + MG_C_STR("pdf"), MG_C_STR("application/pdf"), + MG_C_STR("shtml"), MG_C_STR("text/html; charset=utf-8"), + MG_C_STR("tgz"), MG_C_STR("application/tar-gz"), + MG_C_STR("wav"), MG_C_STR("audio/wav"), + MG_C_STR("webp"), MG_C_STR("image/webp"), + MG_C_STR("zip"), MG_C_STR("application/zip"), + MG_C_STR("3gp"), MG_C_STR("video/3gpp"), + {0, 0}, +}; +// clang-format on + +static struct mg_str guess_content_type(struct mg_str path, const char *extra) { + struct mg_str k, v, s = mg_str(extra); + size_t i = 0; + + // Shrink path to its extension only + while (i < path.len && path.ptr[path.len - i - 1] != '.') i++; + path.ptr += path.len - i; + path.len = i; + + // Process user-provided mime type overrides, if any + while (mg_commalist(&s, &k, &v)) { + if (mg_strcmp(path, k) == 0) return v; + } + + // Process built-in mime types + for (i = 0; s_known_types[i].ptr != NULL; i += 2) { + if (mg_strcmp(path, s_known_types[i]) == 0) return s_known_types[i + 1]; + } + + return mg_str("text/plain; charset=utf-8"); +} + +static int getrange(struct mg_str *s, int64_t *a, int64_t *b) { + size_t i, numparsed = 0; + // MG_INFO(("%.*s", (int) s->len, s->ptr)); + for (i = 0; i + 6 < s->len; i++) { + if (memcmp(&s->ptr[i], "bytes=", 6) == 0) { + struct mg_str p = mg_str_n(s->ptr + i + 6, s->len - i - 6); + if (p.len > 0 && p.ptr[0] >= '0' && p.ptr[0] <= '9') numparsed++; + *a = mg_to64(p); + // MG_INFO(("PPP [%.*s] %d", (int) p.len, p.ptr, numparsed)); + while (p.len && p.ptr[0] >= '0' && p.ptr[0] <= '9') p.ptr++, p.len--; + if (p.len && p.ptr[0] == '-') p.ptr++, p.len--; + *b = mg_to64(p); + if (p.len > 0 && p.ptr[0] >= '0' && p.ptr[0] <= '9') numparsed++; + // MG_INFO(("PPP [%.*s] %d", (int) p.len, p.ptr, numparsed)); + break; + } + } + return (int) numparsed; +} + +void mg_http_serve_file(struct mg_connection *c, struct mg_http_message *hm, + const char *path, + const struct mg_http_serve_opts *opts) { + char etag[64], tmp[MG_PATH_MAX]; + struct mg_fs *fs = opts->fs == NULL ? &mg_fs_posix : opts->fs; + struct mg_fd *fd = NULL; + size_t size = 0; + time_t mtime = 0; + struct mg_str *inm = NULL; + struct mg_str mime = guess_content_type(mg_str(path), opts->mime_types); + bool gzip = false; + + if (path != NULL) { + // If a browser sends us "Accept-Encoding: gzip", try to open .gz first + struct mg_str *ae = mg_http_get_header(hm, "Accept-Encoding"); + if (ae != NULL && mg_strstr(*ae, mg_str("gzip")) != NULL) { + mg_snprintf(tmp, sizeof(tmp), "%s.gz", path); + fd = mg_fs_open(fs, tmp, MG_FS_READ); + if (fd != NULL) gzip = true, path = tmp; + } + // No luck opening .gz? Open what we've told to open + if (fd == NULL) fd = mg_fs_open(fs, path, MG_FS_READ); + } + + // Failed to open, and page404 is configured? Open it, then + if (fd == NULL && opts->page404 != NULL) { + fd = mg_fs_open(fs, opts->page404, MG_FS_READ); + mime = guess_content_type(mg_str(path), opts->mime_types); + path = opts->page404; + } + + if (fd == NULL || fs->st(path, &size, &mtime) == 0) { + mg_http_reply(c, 404, opts->extra_headers, "Not found\n"); + mg_fs_close(fd); + // NOTE: mg_http_etag() call should go first! + } else if (mg_http_etag(etag, sizeof(etag), size, mtime) != NULL && + (inm = mg_http_get_header(hm, "If-None-Match")) != NULL && + mg_vcasecmp(inm, etag) == 0) { + mg_fs_close(fd); + mg_http_reply(c, 304, opts->extra_headers, ""); + } else { + int n, status = 200; + char range[100]; + int64_t r1 = 0, r2 = 0, cl = (int64_t) size; + + // Handle Range header + struct mg_str *rh = mg_http_get_header(hm, "Range"); + range[0] = '\0'; + if (rh != NULL && (n = getrange(rh, &r1, &r2)) > 0 && r1 >= 0 && r2 >= 0) { + // If range is specified like "400-", set second limit to content len + if (n == 1) r2 = cl - 1; + if (r1 > r2 || r2 >= cl) { + status = 416; + cl = 0; + mg_snprintf(range, sizeof(range), "Content-Range: bytes */%lld\r\n", + (int64_t) size); + } else { + status = 206; + cl = r2 - r1 + 1; + mg_snprintf(range, sizeof(range), + "Content-Range: bytes %lld-%lld/%lld\r\n", r1, r1 + cl - 1, + (int64_t) size); + fs->sk(fd->fd, (size_t) r1); + } + } + mg_printf(c, + "HTTP/1.1 %d %s\r\n" + "Content-Type: %.*s\r\n" + "Etag: %s\r\n" + "Content-Length: %llu\r\n" + "%s%s%s\r\n", + status, mg_http_status_code_str(status), (int) mime.len, mime.ptr, + etag, cl, gzip ? "Content-Encoding: gzip\r\n" : "", range, + opts->extra_headers ? opts->extra_headers : ""); + if (mg_vcasecmp(&hm->method, "HEAD") == 0) { + c->is_draining = 1; + c->is_resp = 0; + mg_fs_close(fd); + } else { + // Track to-be-sent content length at the end of c->data, aligned + size_t *clp = (size_t *) &c->data[(sizeof(c->data) - sizeof(size_t)) / + sizeof(size_t) * sizeof(size_t)]; + c->pfn = static_cb; + c->pfn_data = fd; + *clp = (size_t) cl; + } + } +} + +struct printdirentrydata { + struct mg_connection *c; + struct mg_http_message *hm; + const struct mg_http_serve_opts *opts; + const char *dir; +}; + +static void printdirentry(const char *name, void *userdata) { + struct printdirentrydata *d = (struct printdirentrydata *) userdata; + struct mg_fs *fs = d->opts->fs == NULL ? &mg_fs_posix : d->opts->fs; + size_t size = 0; + time_t t = 0; + char path[MG_PATH_MAX], sz[40], mod[40]; + int flags, n = 0; + + // MG_DEBUG(("[%s] [%s]", d->dir, name)); + if (mg_snprintf(path, sizeof(path), "%s%c%s", d->dir, '/', name) > + sizeof(path)) { + MG_ERROR(("%s truncated", name)); + } else if ((flags = fs->st(path, &size, &t)) == 0) { + MG_ERROR(("%lu stat(%s): %d", d->c->id, path, errno)); + } else { + const char *slash = flags & MG_FS_DIR ? "/" : ""; + if (flags & MG_FS_DIR) { + mg_snprintf(sz, sizeof(sz), "%s", "[DIR]"); + } else { + mg_snprintf(sz, sizeof(sz), "%lld", (uint64_t) size); + } +#if defined(MG_HTTP_DIRLIST_TIME_FMT) + { + char time_str[40]; + struct tm *time_info = localtime(&t); + strftime(time_str, sizeof time_str, "%Y/%m/%d %H:%M:%S", time_info); + mg_snprintf(mod, sizeof(mod), "%s", time_str); + } +#else + mg_snprintf(mod, sizeof(mod), "%lu", (unsigned long) t); +#endif + n = (int) mg_url_encode(name, strlen(name), path, sizeof(path)); + mg_printf(d->c, + " %s%s" + "%s%s\n", + n, path, slash, name, slash, (unsigned long) t, mod, + flags & MG_FS_DIR ? (int64_t) -1 : (int64_t) size, sz); + } +} + +static void listdir(struct mg_connection *c, struct mg_http_message *hm, + const struct mg_http_serve_opts *opts, char *dir) { + const char *sort_js_code = + ""; + struct mg_fs *fs = opts->fs == NULL ? &mg_fs_posix : opts->fs; + struct printdirentrydata d = {c, hm, opts, dir}; + char tmp[10], buf[MG_PATH_MAX]; + size_t off, n; + int len = mg_url_decode(hm->uri.ptr, hm->uri.len, buf, sizeof(buf), 0); + struct mg_str uri = len > 0 ? mg_str_n(buf, (size_t) len) : hm->uri; + + mg_printf(c, + "HTTP/1.1 200 OK\r\n" + "Content-Type: text/html; charset=utf-8\r\n" + "%s" + "Content-Length: \r\n\r\n", + opts->extra_headers == NULL ? "" : opts->extra_headers); + off = c->send.len; // Start of body + mg_printf(c, + "Index of %.*s%s%s" + "" + "

Index of %.*s

" + "" + "" + "" + "" + "\n", + (int) uri.len, uri.ptr, sort_js_code, sort_js_code2, (int) uri.len, + uri.ptr); + mg_printf(c, "%s", + " " + "\n"); + + fs->ls(dir, printdirentry, &d); + mg_printf(c, + "" + "
Name" + "ModifiedSize

..[DIR]

Mongoose v.%s
\n", + MG_VERSION); + n = mg_snprintf(tmp, sizeof(tmp), "%lu", (unsigned long) (c->send.len - off)); + if (n > sizeof(tmp)) n = 0; + memcpy(c->send.buf + off - 12, tmp, n); // Set content length + c->is_resp = 0; // Mark response end +} + +// Resolve requested file into `path` and return its fs->st() result +static int uri_to_path2(struct mg_connection *c, struct mg_http_message *hm, + struct mg_fs *fs, struct mg_str url, struct mg_str dir, + char *path, size_t path_size) { + int flags, tmp; + // Append URI to the root_dir, and sanitize it + size_t n = mg_snprintf(path, path_size, "%.*s", (int) dir.len, dir.ptr); + if (n > path_size) n = path_size; + path[path_size - 1] = '\0'; + if (n + 2 < path_size) path[n++] = '/', path[n] = '\0'; + mg_url_decode(hm->uri.ptr + url.len, hm->uri.len - url.len, path + n, + path_size - n, 0); + path[path_size - 1] = '\0'; // Double-check + mg_remove_double_dots(path); + n = strlen(path); + while (n > 1 && path[n - 1] == '/') path[--n] = 0; // Trim trailing slashes + flags = mg_vcmp(&hm->uri, "/") == 0 ? MG_FS_DIR : fs->st(path, NULL, NULL); + MG_VERBOSE(("%lu %.*s -> %s %d", c->id, (int) hm->uri.len, hm->uri.ptr, path, + flags)); + if (flags == 0) { + // Do nothing - let's caller decide + } else if ((flags & MG_FS_DIR) && hm->uri.len > 0 && + hm->uri.ptr[hm->uri.len - 1] != '/') { + mg_printf(c, + "HTTP/1.1 301 Moved\r\n" + "Location: %.*s/\r\n" + "Content-Length: 0\r\n" + "\r\n", + (int) hm->uri.len, hm->uri.ptr); + c->is_resp = 0; + flags = -1; + } else if (flags & MG_FS_DIR) { + if (((mg_snprintf(path + n, path_size - n, "/" MG_HTTP_INDEX) > 0 && + (tmp = fs->st(path, NULL, NULL)) != 0) || + (mg_snprintf(path + n, path_size - n, "/index.shtml") > 0 && + (tmp = fs->st(path, NULL, NULL)) != 0))) { + flags = tmp; + } else if ((mg_snprintf(path + n, path_size - n, "/" MG_HTTP_INDEX ".gz") > + 0 && + (tmp = fs->st(path, NULL, NULL)) != + 0)) { // check for gzipped index + flags = tmp; + path[n + 1 + strlen(MG_HTTP_INDEX)] = + '\0'; // Remove appended .gz in index file name + } else { + path[n] = '\0'; // Remove appended index file name + } + } + return flags; +} + +static int uri_to_path(struct mg_connection *c, struct mg_http_message *hm, + const struct mg_http_serve_opts *opts, char *path, + size_t path_size) { + struct mg_fs *fs = opts->fs == NULL ? &mg_fs_posix : opts->fs; + struct mg_str k, v, s = mg_str(opts->root_dir), u = {0, 0}, p = {0, 0}; + while (mg_commalist(&s, &k, &v)) { + if (v.len == 0) v = k, k = mg_str("/"); + if (hm->uri.len < k.len) continue; + if (mg_strcmp(k, mg_str_n(hm->uri.ptr, k.len)) != 0) continue; + u = k, p = v; + } + return uri_to_path2(c, hm, fs, u, p, path, path_size); +} + +void mg_http_serve_dir(struct mg_connection *c, struct mg_http_message *hm, + const struct mg_http_serve_opts *opts) { + char path[MG_PATH_MAX]; + const char *sp = opts->ssi_pattern; + int flags = uri_to_path(c, hm, opts, path, sizeof(path)); + if (flags < 0) { + // Do nothing: the response has already been sent by uri_to_path() + } else if (flags & MG_FS_DIR) { + listdir(c, hm, opts, path); + } else if (flags && sp != NULL && + mg_globmatch(sp, strlen(sp), path, strlen(path))) { + mg_http_serve_ssi(c, opts->root_dir, path); + } else { + mg_http_serve_file(c, hm, path, opts); + } +} + +static bool mg_is_url_safe(int c) { + return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'z') || + (c >= 'A' && c <= 'Z') || c == '.' || c == '_' || c == '-' || c == '~'; +} + +size_t mg_url_encode(const char *s, size_t sl, char *buf, size_t len) { + size_t i, n = 0; + for (i = 0; i < sl; i++) { + int c = *(unsigned char *) &s[i]; + if (n + 4 >= len) return 0; + if (mg_is_url_safe(c)) { + buf[n++] = s[i]; + } else { + buf[n++] = '%'; + mg_hex(&s[i], 1, &buf[n]); + n += 2; + } + } + if (len > 0 && n < len - 1) buf[n] = '\0'; // Null-terminate the destination + if (len > 0) buf[len - 1] = '\0'; // Always. + return n; +} + +void mg_http_creds(struct mg_http_message *hm, char *user, size_t userlen, + char *pass, size_t passlen) { + struct mg_str *v = mg_http_get_header(hm, "Authorization"); + user[0] = pass[0] = '\0'; + if (v != NULL && v->len > 6 && memcmp(v->ptr, "Basic ", 6) == 0) { + char buf[256]; + int n = mg_base64_decode(v->ptr + 6, (int) v->len - 6, buf); + const char *p = (const char *) memchr(buf, ':', n > 0 ? (size_t) n : 0); + if (p != NULL) { + mg_snprintf(user, userlen, "%.*s", (int) (p - buf), buf); + mg_snprintf(pass, passlen, "%.*s", n - (int) (p - buf) - 1, p + 1); + } + } else if (v != NULL && v->len > 7 && memcmp(v->ptr, "Bearer ", 7) == 0) { + mg_snprintf(pass, passlen, "%.*s", (int) v->len - 7, v->ptr + 7); + } else if ((v = mg_http_get_header(hm, "Cookie")) != NULL) { + struct mg_str t = mg_http_get_header_var(*v, mg_str_n("access_token", 12)); + if (t.len > 0) mg_snprintf(pass, passlen, "%.*s", (int) t.len, t.ptr); + } else { + mg_http_get_var(&hm->query, "access_token", pass, passlen); + } +} + +static struct mg_str stripquotes(struct mg_str s) { + return s.len > 1 && s.ptr[0] == '"' && s.ptr[s.len - 1] == '"' + ? mg_str_n(s.ptr + 1, s.len - 2) + : s; +} + +struct mg_str mg_http_get_header_var(struct mg_str s, struct mg_str v) { + size_t i; + for (i = 0; v.len > 0 && i + v.len + 2 < s.len; i++) { + if (s.ptr[i + v.len] == '=' && memcmp(&s.ptr[i], v.ptr, v.len) == 0) { + const char *p = &s.ptr[i + v.len + 1], *b = p, *x = &s.ptr[s.len]; + int q = p < x && *p == '"' ? 1 : 0; + while (p < x && + (q ? p == b || *p != '"' : *p != ';' && *p != ' ' && *p != ',')) + p++; + // MG_INFO(("[%.*s] [%.*s] [%.*s]", (int) s.len, s.ptr, (int) v.len, + // v.ptr, (int) (p - b), b)); + return stripquotes(mg_str_n(b, (size_t) (p - b + q))); + } + } + return mg_str_n(NULL, 0); +} + +bool mg_http_match_uri(const struct mg_http_message *hm, const char *glob) { + return mg_match(hm->uri, mg_str(glob), NULL); +} + +long mg_http_upload(struct mg_connection *c, struct mg_http_message *hm, + struct mg_fs *fs, const char *path, size_t max_size) { + char buf[20] = "0"; + long res = 0, offset; + mg_http_get_var(&hm->query, "offset", buf, sizeof(buf)); + offset = strtol(buf, NULL, 0); + if (hm->body.len == 0) { + mg_http_reply(c, 200, "", "%ld", res); // Nothing to write + } else { + struct mg_fd *fd; + size_t current_size = 0; + MG_DEBUG(("%s -> %d bytes @ %ld", path, (int) hm->body.len, offset)); + if (offset == 0) fs->rm(path); // If offset if 0, truncate file + fs->st(path, ¤t_size, NULL); + if (offset < 0) { + mg_http_reply(c, 400, "", "offset required"); + res = -1; + } else if (offset > 0 && current_size != (size_t) offset) { + mg_http_reply(c, 400, "", "%s: offset mismatch", path); + res = -2; + } else if ((size_t) offset + hm->body.len > max_size) { + mg_http_reply(c, 400, "", "%s: over max size of %lu", path, + (unsigned long) max_size); + res = -3; + } else if ((fd = mg_fs_open(fs, path, MG_FS_WRITE)) == NULL) { + mg_http_reply(c, 400, "", "open(%s): %d", path, errno); + res = -4; + } else { + res = offset + (long) fs->wr(fd->fd, hm->body.ptr, hm->body.len); + mg_fs_close(fd); + mg_http_reply(c, 200, "", "%ld", res); + } + } + return res; +} + +int mg_http_status(const struct mg_http_message *hm) { + return atoi(hm->uri.ptr); +} + +// If a server sends data to the client using chunked encoding, Mongoose strips +// off the chunking prefix (hex length and \r\n) and suffix (\r\n), appends the +// stripped data to the body, and fires the MG_EV_HTTP_CHUNK event. When zero +// chunk is received, we fire MG_EV_HTTP_MSG, and the body already has all +// chunking prefixes/suffixes stripped. +// +// If a server sends data without chunked encoding, we also fire a series of +// MG_EV_HTTP_CHUNK events for every received piece of data, and then we fire +// MG_EV_HTTP_MSG event in the end. +// +// We track total processed length in the c->pfn_data, which is a void * +// pointer: we store a size_t value there. +static bool getchunk(struct mg_str s, size_t *prefixlen, size_t *datalen) { + size_t i = 0, n; + while (i < s.len && s.ptr[i] != '\r' && s.ptr[i] != '\n') i++; + n = mg_unhexn(s.ptr, i); + // MG_INFO(("%d %d", (int) (i + n + 4), (int) s.len)); + if (s.len < i + n + 4) return false; // Chunk not yet fully buffered + if (s.ptr[i] != '\r' || s.ptr[i + 1] != '\n') return false; + if (s.ptr[i + n + 2] != '\r' || s.ptr[i + n + 3] != '\n') return false; + *prefixlen = i + 2; + *datalen = n; + return true; +} + +static bool mg_is_chunked(struct mg_http_message *hm) { + const char *needle = "chunked"; + struct mg_str *te = mg_http_get_header(hm, "Transfer-Encoding"); + return te != NULL && mg_vcasecmp(te, needle) == 0; +} + +void mg_http_delete_chunk(struct mg_connection *c, struct mg_http_message *hm) { + size_t ofs = (size_t) (hm->chunk.ptr - (char *) c->recv.buf); + mg_iobuf_del(&c->recv, ofs, hm->chunk.len); + c->pfn_data = (void *) ((size_t) c->pfn_data | MG_DMARK); +} + +static void deliver_chunked_chunks(struct mg_connection *c, size_t hlen, + struct mg_http_message *hm, bool *next) { + // | ... headers ... | HEXNUM\r\n ..data.. \r\n | ...... + // +------------------+--------------------------+---- + // | hlen | chunk1 | ...... + char *buf = (char *) &c->recv.buf[hlen], *p = buf; + size_t len = c->recv.len - hlen; + size_t processed = ((size_t) c->pfn_data) & ~MG_DMARK; + size_t mark, pl, dl, del = 0, ofs = 0; + bool last = false; + if (processed <= len) len -= processed, buf += processed; + while (!last && getchunk(mg_str_n(buf + ofs, len - ofs), &pl, &dl)) { + size_t saved = c->recv.len; + memmove(p + processed, buf + ofs + pl, dl); + // MG_INFO(("P2 [%.*s]", (int) (processed + dl), p)); + hm->chunk = mg_str_n(p + processed, dl); + mg_call(c, MG_EV_HTTP_CHUNK, hm); + ofs += pl + dl + 2, del += pl + 2; // 2 is for \r\n suffix + processed += dl; + if (c->recv.len != saved) processed -= dl, buf -= dl; + // mg_hexdump(c->recv.buf, hlen + processed); + last = (dl == 0); + } + mg_iobuf_del(&c->recv, hlen + processed, del); + mark = ((size_t) c->pfn_data) & MG_DMARK; + c->pfn_data = (void *) (processed | mark); + if (last) { + hm->body.len = processed; + hm->message.len = hlen + processed; + c->pfn_data = NULL; + if (mark) mg_iobuf_del(&c->recv, 0, hlen), *next = true; + // MG_INFO(("LAST, mark: %lx", mark)); + // mg_hexdump(c->recv.buf, c->recv.len); + } +} + +static void deliver_normal_chunks(struct mg_connection *c, size_t hlen, + struct mg_http_message *hm, bool *next) { + size_t left, processed = ((size_t) c->pfn_data) & ~MG_DMARK; + size_t deleted = ((size_t) c->pfn_data) & MG_DMARK; + hm->chunk = mg_str_n((char *) &c->recv.buf[hlen], c->recv.len - hlen); + if (processed <= hm->chunk.len && !deleted) { + hm->chunk.len -= processed; + hm->chunk.ptr += processed; + } + left = hm->body.len < processed ? 0 : hm->body.len - processed; + if (hm->chunk.len > left) hm->chunk.len = left; + if (hm->chunk.len > 0) mg_call(c, MG_EV_HTTP_CHUNK, hm); + processed += hm->chunk.len; + deleted = ((size_t) c->pfn_data) & MG_DMARK; // Re-evaluate after user call + if (processed >= hm->body.len) { // Last, 0-len chunk + hm->chunk.len = 0; // Reset length + mg_call(c, MG_EV_HTTP_CHUNK, hm); // Call user handler + c->pfn_data = NULL; // Reset processed counter + if (processed && deleted) mg_iobuf_del(&c->recv, 0, hlen), *next = true; + } else { + c->pfn_data = (void *) (processed | deleted); // if it is set + } +} + +static void http_cb(struct mg_connection *c, int ev, void *evd, void *fnd) { + if (ev == MG_EV_READ || ev == MG_EV_CLOSE) { + struct mg_http_message hm; + // mg_hexdump(c->recv.buf, c->recv.len); + while (c->recv.buf != NULL && c->recv.len > 0) { + bool next = false; + int hlen = mg_http_parse((char *) c->recv.buf, c->recv.len, &hm); + if (hlen < 0) { + mg_error(c, "HTTP parse:\n%.*s", (int) c->recv.len, c->recv.buf); + break; + } + if (c->is_resp) break; // Response is still generated + if (hlen == 0) break; // Request is not buffered yet + if (ev == MG_EV_CLOSE) { // If client did not set Content-Length + hm.message.len = c->recv.len; // and closes now, deliver a MSG + hm.body.len = hm.message.len - (size_t) (hm.body.ptr - hm.message.ptr); + } + if (mg_is_chunked(&hm)) { + deliver_chunked_chunks(c, (size_t) hlen, &hm, &next); + } else { + deliver_normal_chunks(c, (size_t) hlen, &hm, &next); + } + if (next) continue; // Chunks & request were deleted + // Chunk events are delivered. If we have full body, deliver MSG + if (c->recv.len < hm.message.len) break; + if (c->is_accepted) c->is_resp = 1; // Start generating response + mg_call(c, MG_EV_HTTP_MSG, &hm); // User handler can clear is_resp + mg_iobuf_del(&c->recv, 0, hm.message.len); + } + } + (void) evd, (void) fnd; +} + +static void mg_hfn(struct mg_connection *c, int ev, void *ev_data, void *fnd) { + if (ev == MG_EV_HTTP_MSG) { + struct mg_http_message *hm = (struct mg_http_message *) ev_data; + if (mg_http_match_uri(hm, "/quit")) { + mg_http_reply(c, 200, "", "ok\n"); + c->is_draining = 1; + c->data[0] = 'X'; + } else if (mg_http_match_uri(hm, "/debug")) { + int level = (int) mg_json_get_long(hm->body, "$.level", MG_LL_DEBUG); + mg_log_set(level); + mg_http_reply(c, 200, "", "Debug level set to %d\n", level); + } else { + mg_http_reply(c, 200, "", "hi\n"); + } + } else if (ev == MG_EV_CLOSE) { + if (c->data[0] == 'X') *(bool *) fnd = true; + } +} + +void mg_hello(const char *url) { + struct mg_mgr mgr; + bool done = false; + mg_mgr_init(&mgr); + if (mg_http_listen(&mgr, url, mg_hfn, &done) == NULL) done = true; + while (done == false) mg_mgr_poll(&mgr, 100); + mg_mgr_free(&mgr); +} + +struct mg_connection *mg_http_connect(struct mg_mgr *mgr, const char *url, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = mg_connect(mgr, url, fn, fn_data); + if (c != NULL) c->pfn = http_cb; + return c; +} + +struct mg_connection *mg_http_listen(struct mg_mgr *mgr, const char *url, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = mg_listen(mgr, url, fn, fn_data); + if (c != NULL) c->pfn = http_cb; + return c; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/iobuf.c" +#endif + + + + +// Not using memset for zeroing memory, cause it can be dropped by compiler +// See https://github.com/cesanta/mongoose/pull/1265 +static void zeromem(volatile unsigned char *buf, size_t len) { + if (buf != NULL) { + while (len--) *buf++ = 0; + } +} + +static size_t roundup(size_t size, size_t align) { + return align == 0 ? size : (size + align - 1) / align * align; +} + +int mg_iobuf_resize(struct mg_iobuf *io, size_t new_size) { + int ok = 1; + new_size = roundup(new_size, io->align); + if (new_size == 0) { + zeromem(io->buf, io->size); + free(io->buf); + io->buf = NULL; + io->len = io->size = 0; + } else if (new_size != io->size) { + // NOTE(lsm): do not use realloc here. Use calloc/free only, to ease the + // porting to some obscure platforms like FreeRTOS + void *p = calloc(1, new_size); + if (p != NULL) { + size_t len = new_size < io->len ? new_size : io->len; + if (len > 0 && io->buf != NULL) memmove(p, io->buf, len); + zeromem(io->buf, io->size); + free(io->buf); + io->buf = (unsigned char *) p; + io->size = new_size; + } else { + ok = 0; + MG_ERROR(("%lld->%lld", (uint64_t) io->size, (uint64_t) new_size)); + } + } + return ok; +} + +int mg_iobuf_init(struct mg_iobuf *io, size_t size, size_t align) { + io->buf = NULL; + io->align = align; + io->size = io->len = 0; + return mg_iobuf_resize(io, size); +} + +size_t mg_iobuf_add(struct mg_iobuf *io, size_t ofs, const void *buf, + size_t len) { + size_t new_size = roundup(io->len + len, io->align); + mg_iobuf_resize(io, new_size); // Attempt to resize + if (new_size != io->size) len = 0; // Resize failure, append nothing + if (ofs < io->len) memmove(io->buf + ofs + len, io->buf + ofs, io->len - ofs); + if (buf != NULL) memmove(io->buf + ofs, buf, len); + if (ofs > io->len) io->len += ofs - io->len; + io->len += len; + return len; +} + +size_t mg_iobuf_del(struct mg_iobuf *io, size_t ofs, size_t len) { + if (ofs > io->len) ofs = io->len; + if (ofs + len > io->len) len = io->len - ofs; + if (io->buf) memmove(io->buf + ofs, io->buf + ofs + len, io->len - ofs - len); + if (io->buf) zeromem(io->buf + io->len - len, len); + io->len -= len; + return len; +} + +void mg_iobuf_free(struct mg_iobuf *io) { + mg_iobuf_resize(io, 0); +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/json.c" +#endif + + + + +static const char *escapeseq(int esc) { + return esc ? "\b\f\n\r\t\\\"" : "bfnrt\\\""; +} + +static char json_esc(int c, int esc) { + const char *p, *esc1 = escapeseq(esc), *esc2 = escapeseq(!esc); + for (p = esc1; *p != '\0'; p++) { + if (*p == c) return esc2[p - esc1]; + } + return 0; +} + +static int mg_pass_string(const char *s, int len) { + int i; + for (i = 0; i < len; i++) { + if (s[i] == '\\' && i + 1 < len && json_esc(s[i + 1], 1)) { + i++; + } else if (s[i] == '\0') { + return MG_JSON_INVALID; + } else if (s[i] == '"') { + return i; + } + } + return MG_JSON_INVALID; +} + +static double mg_atod(const char *p, int len, int *numlen) { + double d = 0.0; + int i = 0, sign = 1; + + // Sign + if (i < len && *p == '-') { + sign = -1, i++; + } else if (i < len && *p == '+') { + i++; + } + + // Decimal + for (; i < len && p[i] >= '0' && p[i] <= '9'; i++) { + d *= 10.0; + d += p[i] - '0'; + } + d *= sign; + + // Fractional + if (i < len && p[i] == '.') { + double frac = 0.0, base = 0.1; + i++; + for (; i < len && p[i] >= '0' && p[i] <= '9'; i++) { + frac += base * (p[i] - '0'); + base /= 10.0; + } + d += frac * sign; + } + + // Exponential + if (i < len && (p[i] == 'e' || p[i] == 'E')) { + int j, exp = 0, minus = 0; + i++; + if (i < len && p[i] == '-') minus = 1, i++; + if (i < len && p[i] == '+') i++; + while (i < len && p[i] >= '0' && p[i] <= '9' && exp < 308) + exp = exp * 10 + (p[i++] - '0'); + if (minus) exp = -exp; + for (j = 0; j < exp; j++) d *= 10.0; + for (j = 0; j < -exp; j++) d /= 10.0; + } + + if (numlen != NULL) *numlen = i; + return d; +} + +int mg_json_get(struct mg_str json, const char *path, int *toklen) { + const char *s = json.ptr; + int len = (int) json.len; + enum { S_VALUE, S_KEY, S_COLON, S_COMMA_OR_EOO } expecting = S_VALUE; + unsigned char nesting[MG_JSON_MAX_DEPTH]; + int i = 0; // Current offset in `s` + int j = 0; // Offset in `s` we're looking for (return value) + int depth = 0; // Current depth (nesting level) + int ed = 0; // Expected depth + int pos = 1; // Current position in `path` + int ci = -1, ei = -1; // Current and expected index in array + + if (toklen) *toklen = 0; + if (path[0] != '$') return MG_JSON_INVALID; + +#define MG_CHECKRET(x) \ + do { \ + if (depth == ed && path[pos] == '\0' && ci == ei) { \ + if (toklen) *toklen = i - j + 1; \ + return j; \ + } \ + } while (0) + +// In the ascii table, the distance between `[` and `]` is 2. +// Ditto for `{` and `}`. Hence +2 in the code below. +#define MG_EOO(x) \ + do { \ + if (depth == ed && ci != ei) return MG_JSON_NOT_FOUND; \ + if (c != nesting[depth - 1] + 2) return MG_JSON_INVALID; \ + depth--; \ + MG_CHECKRET(x); \ + } while (0) + + for (i = 0; i < len; i++) { + unsigned char c = ((unsigned char *) s)[i]; + if (c == ' ' || c == '\t' || c == '\n' || c == '\r') continue; + switch (expecting) { + case S_VALUE: + // p("V %s [%.*s] %d %d %d %d\n", path, pos, path, depth, ed, ci, ei); + if (depth == ed) j = i; + if (c == '{') { + if (depth >= (int) sizeof(nesting)) return MG_JSON_TOO_DEEP; + if (depth == ed && path[pos] == '.' && ci == ei) { + // If we start the object, reset array indices + ed++, pos++, ci = ei = -1; + } + nesting[depth++] = c; + expecting = S_KEY; + break; + } else if (c == '[') { + if (depth >= (int) sizeof(nesting)) return MG_JSON_TOO_DEEP; + if (depth == ed && path[pos] == '[' && ei == ci) { + ed++, pos++, ci = 0; + for (ei = 0; path[pos] != ']' && path[pos] != '\0'; pos++) { + ei *= 10; + ei += path[pos] - '0'; + } + if (path[pos] != 0) pos++; + } + nesting[depth++] = c; + break; + } else if (c == ']' && depth > 0) { // Empty array + MG_EOO(']'); + } else if (c == 't' && i + 3 < len && memcmp(&s[i], "true", 4) == 0) { + i += 3; + } else if (c == 'n' && i + 3 < len && memcmp(&s[i], "null", 4) == 0) { + i += 3; + } else if (c == 'f' && i + 4 < len && memcmp(&s[i], "false", 5) == 0) { + i += 4; + } else if (c == '-' || ((c >= '0' && c <= '9'))) { + int numlen = 0; + mg_atod(&s[i], len - i, &numlen); + i += numlen - 1; + } else if (c == '"') { + int n = mg_pass_string(&s[i + 1], len - i - 1); + if (n < 0) return n; + i += n + 1; + } else { + return MG_JSON_INVALID; + } + MG_CHECKRET('V'); + if (depth == ed && ei >= 0) ci++; + expecting = S_COMMA_OR_EOO; + break; + + case S_KEY: + if (c == '"') { + int n = mg_pass_string(&s[i + 1], len - i - 1); + if (n < 0) return n; + if (i + 1 + n >= len) return MG_JSON_NOT_FOUND; + if (depth < ed) return MG_JSON_NOT_FOUND; + if (depth == ed && path[pos - 1] != '.') return MG_JSON_NOT_FOUND; + // printf("K %s [%.*s] [%.*s] %d %d %d\n", path, pos, path, n, + // &s[i + 1], n, depth, ed); + // NOTE(cpq): in the check sequence below is important. + // strncmp() must go first: it fails fast if the remaining length of + // the path is smaller than `n`. + if (depth == ed && path[pos - 1] == '.' && + strncmp(&s[i + 1], &path[pos], (size_t) n) == 0 && + (path[pos + n] == '\0' || path[pos + n] == '.' || + path[pos + n] == '[')) { + pos += n; + } + i += n + 1; + expecting = S_COLON; + } else if (c == '}') { // Empty object + MG_EOO('}'); + expecting = S_COMMA_OR_EOO; + } else { + return MG_JSON_INVALID; + } + break; + + case S_COLON: + if (c == ':') { + expecting = S_VALUE; + } else { + return MG_JSON_INVALID; + } + break; + + case S_COMMA_OR_EOO: + if (depth <= 0) { + return MG_JSON_INVALID; + } else if (c == ',') { + expecting = (nesting[depth - 1] == '{') ? S_KEY : S_VALUE; + } else if (c == ']' || c == '}') { + MG_EOO('O'); + if (depth == ed && ei >= 0) ci++; + } else { + return MG_JSON_INVALID; + } + break; + } + } + return MG_JSON_NOT_FOUND; +} + +bool mg_json_get_num(struct mg_str json, const char *path, double *v) { + int n, toklen, found = 0; + if ((n = mg_json_get(json, path, &toklen)) >= 0 && + (json.ptr[n] == '-' || (json.ptr[n] >= '0' && json.ptr[n] <= '9'))) { + if (v != NULL) *v = mg_atod(json.ptr + n, toklen, NULL); + found = 1; + } + return found; +} + +bool mg_json_get_bool(struct mg_str json, const char *path, bool *v) { + int found = 0, off = mg_json_get(json, path, NULL); + if (off >= 0 && (json.ptr[off] == 't' || json.ptr[off] == 'f')) { + if (v != NULL) *v = json.ptr[off] == 't'; + found = 1; + } + return found; +} + +static bool json_unescape(const char *s, size_t len, char *to, size_t n) { + size_t i, j; + for (i = 0, j = 0; i < len && j < n; i++, j++) { + if (s[i] == '\\' && i + 5 < len && s[i + 1] == 'u') { + // \uXXXX escape. We could process a simple one-byte chars + // \u00xx from the ASCII range. More complex chars would require + // dragging in a UTF8 library, which is too much for us + if (s[i + 2] != '0' || s[i + 3] != '0') return false; // Give up + ((unsigned char *) to)[j] = (unsigned char) mg_unhexn(s + i + 4, 2); + + i += 5; + } else if (s[i] == '\\' && i + 1 < len) { + char c = json_esc(s[i + 1], 0); + if (c == 0) return false; + to[j] = c; + i++; + } else { + to[j] = s[i]; + } + } + if (j >= n) return false; + if (n > 0) to[j] = '\0'; + return true; +} + +char *mg_json_get_str(struct mg_str json, const char *path) { + char *result = NULL; + int len = 0, off = mg_json_get(json, path, &len); + if (off >= 0 && len > 1 && json.ptr[off] == '"') { + if ((result = (char *) calloc(1, (size_t) len)) != NULL && + !json_unescape(json.ptr + off + 1, (size_t) (len - 2), result, + (size_t) len)) { + free(result); + result = NULL; + } + } + return result; +} + +char *mg_json_get_b64(struct mg_str json, const char *path, int *slen) { + char *result = NULL; + int len = 0, off = mg_json_get(json, path, &len); + if (off >= 0 && json.ptr[off] == '"' && len > 1 && + (result = (char *) calloc(1, (size_t) len)) != NULL) { + int k = mg_base64_decode(json.ptr + off + 1, len - 2, result); + if (slen != NULL) *slen = k; + } + return result; +} + +char *mg_json_get_hex(struct mg_str json, const char *path, int *slen) { + char *result = NULL; + int len = 0, off = mg_json_get(json, path, &len); + if (off >= 0 && json.ptr[off] == '"' && len > 1 && + (result = (char *) calloc(1, (size_t) len / 2)) != NULL) { + mg_unhex(json.ptr + off + 1, (size_t) (len - 2), (uint8_t *) result); + result[len / 2 - 1] = '\0'; + if (slen != NULL) *slen = len / 2 - 1; + } + return result; +} + +long mg_json_get_long(struct mg_str json, const char *path, long dflt) { + double dv; + long result = dflt; + if (mg_json_get_num(json, path, &dv)) result = (long) dv; + return result; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/log.c" +#endif + + + + + +static int s_level = MG_LL_INFO; +static mg_pfn_t s_log_func = mg_pfn_stdout; +static void *s_log_func_param = NULL; + +void mg_log_set_fn(mg_pfn_t fn, void *param) { + s_log_func = fn; + s_log_func_param = param; +} + +static void logc(unsigned char c) { + s_log_func((char) c, s_log_func_param); +} + +static void logs(const char *buf, size_t len) { + size_t i; + for (i = 0; i < len; i++) logc(((unsigned char *) buf)[i]); +} + +void mg_log_set(int log_level) { + MG_DEBUG(("Setting log level to %d", log_level)); + s_level = log_level; +} + +bool mg_log_prefix(int level, const char *file, int line, const char *fname) { + if (level <= s_level) { + const char *p = strrchr(file, '/'); + char buf[41]; + size_t n; + if (p == NULL) p = strrchr(file, '\\'); + n = mg_snprintf(buf, sizeof(buf), "%-6llx %d %s:%d:%s", mg_millis(), level, + p == NULL ? file : p + 1, line, fname); + if (n > sizeof(buf) - 2) n = sizeof(buf) - 2; + while (n < sizeof(buf)) buf[n++] = ' '; + logs(buf, n - 1); + return true; + } else { + return false; + } +} + +void mg_log(const char *fmt, ...) { + va_list ap; + va_start(ap, fmt); + mg_vxprintf(s_log_func, s_log_func_param, fmt, &ap); + va_end(ap); + logc((unsigned char) '\n'); +} + +static unsigned char nibble(unsigned c) { + return (unsigned char) (c < 10 ? c + '0' : c + 'W'); +} + +#define ISPRINT(x) ((x) >= ' ' && (x) <= '~') +void mg_hexdump(const void *buf, size_t len) { + const unsigned char *p = (const unsigned char *) buf; + unsigned char ascii[16], alen = 0; + size_t i; + for (i = 0; i < len; i++) { + if ((i % 16) == 0) { + // Print buffered ascii chars + if (i > 0) logs(" ", 2), logs((char *) ascii, 16), logc('\n'), alen = 0; + // Print hex address, then \t + logc(nibble((i >> 12) & 15)), logc(nibble((i >> 8) & 15)), + logc(nibble((i >> 4) & 15)), logc('0'), logs(" ", 3); + } + logc(nibble(p[i] >> 4)), logc(nibble(p[i] & 15)); // Two nibbles, e.g. c5 + logc(' '); // Space after hex number + ascii[alen++] = ISPRINT(p[i]) ? p[i] : '.'; // Add to the ascii buf + } + while (alen < 16) logs(" ", 3), ascii[alen++] = ' '; + logs(" ", 2), logs((char *) ascii, 16), logc('\n'); +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/md5.c" +#endif + + + +#if defined(MG_ENABLE_MD5) && MG_ENABLE_MD5 + +static void mg_byte_reverse(unsigned char *buf, unsigned longs) { + if (MG_BIG_ENDIAN) { + do { + uint32_t t = (uint32_t) ((unsigned) buf[3] << 8 | buf[2]) << 16 | + ((unsigned) buf[1] << 8 | buf[0]); + *(uint32_t *) buf = t; + buf += 4; + } while (--longs); + } else { + (void) buf, (void) longs; // Little endian. Do nothing + } +} + +#define F1(x, y, z) (z ^ (x & (y ^ z))) +#define F2(x, y, z) F1(z, x, y) +#define F3(x, y, z) (x ^ y ^ z) +#define F4(x, y, z) (y ^ (x | ~z)) + +#define MD5STEP(f, w, x, y, z, data, s) \ + (w += f(x, y, z) + data, w = w << s | w >> (32 - s), w += x) + +/* + * Start MD5 accumulation. Set bit count to 0 and buffer to mysterious + * initialization constants. + */ +void mg_md5_init(mg_md5_ctx *ctx) { + ctx->buf[0] = 0x67452301; + ctx->buf[1] = 0xefcdab89; + ctx->buf[2] = 0x98badcfe; + ctx->buf[3] = 0x10325476; + + ctx->bits[0] = 0; + ctx->bits[1] = 0; +} + +static void mg_md5_transform(uint32_t buf[4], uint32_t const in[16]) { + uint32_t a, b, c, d; + + a = buf[0]; + b = buf[1]; + c = buf[2]; + d = buf[3]; + + MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7); + MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12); + MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17); + MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22); + MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7); + MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12); + MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17); + MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22); + MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7); + MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12); + MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17); + MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22); + MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7); + MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12); + MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17); + MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22); + + MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5); + MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9); + MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14); + MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20); + MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5); + MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9); + MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14); + MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20); + MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5); + MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9); + MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14); + MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20); + MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5); + MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9); + MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14); + MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20); + + MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4); + MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11); + MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16); + MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23); + MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4); + MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11); + MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16); + MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23); + MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4); + MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11); + MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16); + MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23); + MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4); + MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11); + MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16); + MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23); + + MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6); + MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10); + MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15); + MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21); + MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6); + MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10); + MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15); + MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21); + MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6); + MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10); + MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15); + MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21); + MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6); + MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10); + MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15); + MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21); + + buf[0] += a; + buf[1] += b; + buf[2] += c; + buf[3] += d; +} + +void mg_md5_update(mg_md5_ctx *ctx, const unsigned char *buf, size_t len) { + uint32_t t; + + t = ctx->bits[0]; + if ((ctx->bits[0] = t + ((uint32_t) len << 3)) < t) ctx->bits[1]++; + ctx->bits[1] += (uint32_t) len >> 29; + + t = (t >> 3) & 0x3f; + + if (t) { + unsigned char *p = (unsigned char *) ctx->in + t; + + t = 64 - t; + if (len < t) { + memcpy(p, buf, len); + return; + } + memcpy(p, buf, t); + mg_byte_reverse(ctx->in, 16); + mg_md5_transform(ctx->buf, (uint32_t *) ctx->in); + buf += t; + len -= t; + } + + while (len >= 64) { + memcpy(ctx->in, buf, 64); + mg_byte_reverse(ctx->in, 16); + mg_md5_transform(ctx->buf, (uint32_t *) ctx->in); + buf += 64; + len -= 64; + } + + memcpy(ctx->in, buf, len); +} + +void mg_md5_final(mg_md5_ctx *ctx, unsigned char digest[16]) { + unsigned count; + unsigned char *p; + uint32_t *a; + + count = (ctx->bits[0] >> 3) & 0x3F; + + p = ctx->in + count; + *p++ = 0x80; + count = 64 - 1 - count; + if (count < 8) { + memset(p, 0, count); + mg_byte_reverse(ctx->in, 16); + mg_md5_transform(ctx->buf, (uint32_t *) ctx->in); + memset(ctx->in, 0, 56); + } else { + memset(p, 0, count - 8); + } + mg_byte_reverse(ctx->in, 14); + + a = (uint32_t *) ctx->in; + a[14] = ctx->bits[0]; + a[15] = ctx->bits[1]; + + mg_md5_transform(ctx->buf, (uint32_t *) ctx->in); + mg_byte_reverse((unsigned char *) ctx->buf, 4); + memcpy(digest, ctx->buf, 16); + memset((char *) ctx, 0, sizeof(*ctx)); +} +#endif + +#ifdef MG_ENABLE_LINES +#line 1 "src/mqtt.c" +#endif + + + + + + + + +#define MQTT_CLEAN_SESSION 0x02 +#define MQTT_HAS_WILL 0x04 +#define MQTT_WILL_RETAIN 0x20 +#define MQTT_HAS_PASSWORD 0x40 +#define MQTT_HAS_USER_NAME 0x80 + +struct mg_mqtt_pmap { + uint8_t id; + uint8_t type; +}; + +static const struct mg_mqtt_pmap s_prop_map[] = { + {MQTT_PROP_PAYLOAD_FORMAT_INDICATOR, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_MESSAGE_EXPIRY_INTERVAL, MQTT_PROP_TYPE_INT}, + {MQTT_PROP_CONTENT_TYPE, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_RESPONSE_TOPIC, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_CORRELATION_DATA, MQTT_PROP_TYPE_BINARY_DATA}, + {MQTT_PROP_SUBSCRIPTION_IDENTIFIER, MQTT_PROP_TYPE_VARIABLE_INT}, + {MQTT_PROP_SESSION_EXPIRY_INTERVAL, MQTT_PROP_TYPE_INT}, + {MQTT_PROP_ASSIGNED_CLIENT_IDENTIFIER, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_SERVER_KEEP_ALIVE, MQTT_PROP_TYPE_SHORT}, + {MQTT_PROP_AUTHENTICATION_METHOD, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_AUTHENTICATION_DATA, MQTT_PROP_TYPE_BINARY_DATA}, + {MQTT_PROP_REQUEST_PROBLEM_INFORMATION, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_WILL_DELAY_INTERVAL, MQTT_PROP_TYPE_INT}, + {MQTT_PROP_REQUEST_RESPONSE_INFORMATION, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_RESPONSE_INFORMATION, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_SERVER_REFERENCE, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_REASON_STRING, MQTT_PROP_TYPE_STRING}, + {MQTT_PROP_RECEIVE_MAXIMUM, MQTT_PROP_TYPE_SHORT}, + {MQTT_PROP_TOPIC_ALIAS_MAXIMUM, MQTT_PROP_TYPE_SHORT}, + {MQTT_PROP_TOPIC_ALIAS, MQTT_PROP_TYPE_SHORT}, + {MQTT_PROP_MAXIMUM_QOS, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_RETAIN_AVAILABLE, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_USER_PROPERTY, MQTT_PROP_TYPE_STRING_PAIR}, + {MQTT_PROP_MAXIMUM_PACKET_SIZE, MQTT_PROP_TYPE_INT}, + {MQTT_PROP_WILDCARD_SUBSCRIPTION_AVAILABLE, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_SUBSCRIPTION_IDENTIFIER_AVAILABLE, MQTT_PROP_TYPE_BYTE}, + {MQTT_PROP_SHARED_SUBSCRIPTION_AVAILABLE, MQTT_PROP_TYPE_BYTE}}; + +void mg_mqtt_send_header(struct mg_connection *c, uint8_t cmd, uint8_t flags, + uint32_t len) { + uint8_t buf[1 + sizeof(len)], *vlen = &buf[1]; + buf[0] = (uint8_t) ((cmd << 4) | flags); + do { + *vlen = len % 0x80; + len /= 0x80; + if (len > 0) *vlen |= 0x80; + vlen++; + } while (len > 0 && vlen < &buf[sizeof(buf)]); + mg_send(c, buf, (size_t) (vlen - buf)); +} + +static void mg_send_u16(struct mg_connection *c, uint16_t value) { + mg_send(c, &value, sizeof(value)); +} + +static void mg_send_u32(struct mg_connection *c, uint32_t value) { + mg_send(c, &value, sizeof(value)); +} + +static uint8_t compute_variable_length_size(size_t length) { + uint8_t bytes_needed = 0; + do { + bytes_needed++; + length /= 0x80; + } while (length > 0); + return bytes_needed; +} + +static int encode_variable_length(uint8_t *buf, size_t value) { + int len = 0; + + do { + uint8_t byte = (uint8_t) (value % 128); + value /= 128; + if (value > 0) byte |= 0x80; + buf[len++] = byte; + } while (value > 0); + + return len; +} + +static uint32_t decode_variable_length(const char *buf, + uint32_t *bytes_consumed) { + uint32_t value = 0, multiplier = 1, offset; + + for (offset = 0; offset < 4; offset++) { + uint8_t encoded_byte = ((uint8_t *) buf)[offset]; + value += (encoded_byte & 0x7F) * multiplier; + multiplier *= 128; + + if (!(encoded_byte & 0x80)) break; + } + + if (bytes_consumed != NULL) *bytes_consumed = offset + 1; + + return value; +} + +static int mqtt_prop_type_by_id(uint8_t prop_id) { + size_t i, num_properties = sizeof(s_prop_map) / sizeof(s_prop_map[0]); + for (i = 0; i < num_properties; ++i) { + if (s_prop_map[i].id == prop_id) return s_prop_map[i].type; + } + return -1; // Property ID not found +} + +// Returns the size of the properties section, without the +// size of the content's length +static size_t get_properties_length(struct mg_mqtt_prop *props, size_t count) { + size_t i, size = 0; + for (i = 0; i < count; i++) { + size++; // identifier + switch (mqtt_prop_type_by_id(props[i].id)) { + case MQTT_PROP_TYPE_STRING_PAIR: + size += (uint32_t) (props[i].val.len + props[i].key.len + + 2 * sizeof(uint16_t)); + break; + case MQTT_PROP_TYPE_STRING: + size += (uint32_t) (props[i].val.len + sizeof(uint16_t)); + break; + case MQTT_PROP_TYPE_BINARY_DATA: + size += (uint32_t) (props[i].val.len + sizeof(uint16_t)); + break; + case MQTT_PROP_TYPE_VARIABLE_INT: + size += compute_variable_length_size((uint32_t) props[i].iv); + break; + case MQTT_PROP_TYPE_INT: size += (uint32_t) sizeof(uint32_t); break; + case MQTT_PROP_TYPE_SHORT: size += (uint32_t) sizeof(uint16_t); break; + default: return size; // cannot parse further down + } + } + + return size; +} + +// returns the entire size of the properties section, including the +// size of the variable length of the content +static size_t get_props_size(struct mg_mqtt_prop *props, size_t count) { + size_t size = get_properties_length(props, count); + size += compute_variable_length_size(size); + return size; +} + +static void mg_send_mqtt_properties(struct mg_connection *c, + struct mg_mqtt_prop *props, size_t nprops) { + size_t total_size = get_properties_length(props, nprops); + uint8_t buf_v[4] = {0, 0, 0, 0}; + uint8_t buf[4] = {0, 0, 0, 0}; + int i, len = encode_variable_length(buf, total_size); + + mg_send(c, buf, (size_t) len); + for (i = 0; i < (int) nprops; i++) { + mg_send(c, &props[i].id, sizeof(props[i].id)); + switch (mqtt_prop_type_by_id(props[i].id)) { + case MQTT_PROP_TYPE_STRING_PAIR: + mg_send_u16(c, mg_htons((uint16_t) props[i].key.len)); + mg_send(c, props[i].key.ptr, props[i].key.len); + mg_send_u16(c, mg_htons((uint16_t) props[i].val.len)); + mg_send(c, props[i].val.ptr, props[i].val.len); + break; + case MQTT_PROP_TYPE_BYTE: + mg_send(c, &props[i].iv, sizeof(uint8_t)); + break; + case MQTT_PROP_TYPE_SHORT: + mg_send_u16(c, mg_htons((uint16_t) props[i].iv)); + break; + case MQTT_PROP_TYPE_INT: + mg_send_u32(c, mg_htonl((uint32_t) props[i].iv)); + break; + case MQTT_PROP_TYPE_STRING: + mg_send_u16(c, mg_htons((uint16_t) props[i].val.len)); + mg_send(c, props[i].val.ptr, props[i].val.len); + break; + case MQTT_PROP_TYPE_BINARY_DATA: + mg_send_u16(c, mg_htons((uint16_t) props[i].val.len)); + mg_send(c, props[i].val.ptr, props[i].val.len); + break; + case MQTT_PROP_TYPE_VARIABLE_INT: + len = encode_variable_length(buf_v, props[i].iv); + mg_send(c, buf_v, (size_t) len); + break; + } + } +} + +size_t mg_mqtt_next_prop(struct mg_mqtt_message *msg, struct mg_mqtt_prop *prop, + size_t ofs) { + uint8_t *i = (uint8_t *) msg->dgram.ptr + msg->props_start + ofs; + size_t new_pos = ofs; + uint32_t bytes_consumed; + prop->id = i[0]; + + if (ofs >= msg->dgram.len || ofs >= msg->props_start + msg->props_size) + return 0; + i++, new_pos++; + + switch (mqtt_prop_type_by_id(prop->id)) { + case MQTT_PROP_TYPE_STRING_PAIR: + prop->key.len = (uint16_t) ((((uint16_t) i[0]) << 8) | i[1]); + prop->key.ptr = (char *) i + 2; + i += 2 + prop->key.len; + prop->val.len = (uint16_t) ((((uint16_t) i[0]) << 8) | i[1]); + prop->val.ptr = (char *) i + 2; + new_pos += 2 * sizeof(uint16_t) + prop->val.len + prop->key.len; + break; + case MQTT_PROP_TYPE_BYTE: + prop->iv = (uint8_t) i[0]; + new_pos++; + break; + case MQTT_PROP_TYPE_SHORT: + prop->iv = (uint16_t) ((((uint16_t) i[0]) << 8) | i[1]); + new_pos += sizeof(uint16_t); + break; + case MQTT_PROP_TYPE_INT: + prop->iv = ((uint32_t) i[0] << 24) | ((uint32_t) i[1] << 16) | + ((uint32_t) i[2] << 8) | i[3]; + new_pos += sizeof(uint32_t); + break; + case MQTT_PROP_TYPE_STRING: + prop->val.len = (uint16_t) ((((uint16_t) i[0]) << 8) | i[1]); + prop->val.ptr = (char *) i + 2; + new_pos += 2 + prop->val.len; + break; + case MQTT_PROP_TYPE_BINARY_DATA: + prop->val.len = (uint16_t) ((((uint16_t) i[0]) << 8) | i[1]); + prop->val.ptr = (char *) i + 2; + new_pos += 2 + prop->val.len; + break; + case MQTT_PROP_TYPE_VARIABLE_INT: + prop->iv = decode_variable_length((char *) i, &bytes_consumed); + new_pos += bytes_consumed; + break; + default: new_pos = 0; + } + + return new_pos; +} + +void mg_mqtt_login(struct mg_connection *c, const struct mg_mqtt_opts *opts) { + char rnd[10], client_id[21]; + struct mg_str cid = opts->client_id; + size_t total_len = 7 + 1 + 2 + 2; + uint8_t hdr[8] = {0, 4, 'M', 'Q', 'T', 'T', opts->version, 0}; + + if (cid.len == 0) { + mg_random(rnd, sizeof(rnd)); + mg_hex(rnd, sizeof(rnd), client_id); + client_id[sizeof(client_id) - 1] = '\0'; + cid = mg_str(client_id); + } + + if (hdr[6] == 0) hdr[6] = 4; // If version is not set, use 4 (3.1.1) + c->is_mqtt5 = hdr[6] == 5; // Set version 5 flag + hdr[7] = (uint8_t) ((opts->qos & 3) << 3); // Connection flags + if (opts->user.len > 0) { + total_len += 2 + (uint32_t) opts->user.len; + hdr[7] |= MQTT_HAS_USER_NAME; + } + if (opts->pass.len > 0) { + total_len += 2 + (uint32_t) opts->pass.len; + hdr[7] |= MQTT_HAS_PASSWORD; + } + if (opts->topic.len > 0 && opts->message.len > 0) { + total_len += 4 + (uint32_t) opts->topic.len + (uint32_t) opts->message.len; + hdr[7] |= MQTT_HAS_WILL; + } + if (opts->clean || cid.len == 0) hdr[7] |= MQTT_CLEAN_SESSION; + if (opts->retain) hdr[7] |= MQTT_WILL_RETAIN; + total_len += (uint32_t) cid.len; + if (c->is_mqtt5) { + total_len += get_props_size(opts->props, opts->num_props); + if (hdr[7] & MQTT_HAS_WILL) + total_len += get_props_size(opts->will_props, opts->num_will_props); + } + + mg_mqtt_send_header(c, MQTT_CMD_CONNECT, 0, (uint32_t) total_len); + mg_send(c, hdr, sizeof(hdr)); + // keepalive == 0 means "do not disconnect us!" + mg_send_u16(c, mg_htons((uint16_t) opts->keepalive)); + + if (c->is_mqtt5) mg_send_mqtt_properties(c, opts->props, opts->num_props); + + mg_send_u16(c, mg_htons((uint16_t) cid.len)); + mg_send(c, cid.ptr, cid.len); + + if (hdr[7] & MQTT_HAS_WILL) { + if (c->is_mqtt5) + mg_send_mqtt_properties(c, opts->will_props, opts->num_will_props); + + mg_send_u16(c, mg_htons((uint16_t) opts->topic.len)); + mg_send(c, opts->topic.ptr, opts->topic.len); + mg_send_u16(c, mg_htons((uint16_t) opts->message.len)); + mg_send(c, opts->message.ptr, opts->message.len); + } + if (opts->user.len > 0) { + mg_send_u16(c, mg_htons((uint16_t) opts->user.len)); + mg_send(c, opts->user.ptr, opts->user.len); + } + if (opts->pass.len > 0) { + mg_send_u16(c, mg_htons((uint16_t) opts->pass.len)); + mg_send(c, opts->pass.ptr, opts->pass.len); + } +} + +void mg_mqtt_pub(struct mg_connection *c, const struct mg_mqtt_opts *opts) { + uint8_t flags = (uint8_t) (((opts->qos & 3) << 1) | (opts->retain ? 1 : 0)); + size_t len = 2 + opts->topic.len + opts->message.len; + MG_DEBUG(("%lu [%.*s] -> [%.*s]", c->id, (int) opts->topic.len, + (char *) opts->topic.ptr, (int) opts->message.len, + (char *) opts->message.ptr)); + if (opts->qos > 0) len += 2; + if (c->is_mqtt5) len += get_props_size(opts->props, opts->num_props); + + mg_mqtt_send_header(c, MQTT_CMD_PUBLISH, flags, (uint32_t) len); + mg_send_u16(c, mg_htons((uint16_t) opts->topic.len)); + mg_send(c, opts->topic.ptr, opts->topic.len); + if (opts->qos > 0) { + if (++c->mgr->mqtt_id == 0) ++c->mgr->mqtt_id; + mg_send_u16(c, mg_htons(c->mgr->mqtt_id)); + } + + if (c->is_mqtt5) mg_send_mqtt_properties(c, opts->props, opts->num_props); + + mg_send(c, opts->message.ptr, opts->message.len); +} + +void mg_mqtt_sub(struct mg_connection *c, const struct mg_mqtt_opts *opts) { + uint8_t qos_ = opts->qos & 3; + size_t plen = c->is_mqtt5 ? get_props_size(opts->props, opts->num_props) : 0; + size_t len = 2 + opts->topic.len + 2 + 1 + plen; + + mg_mqtt_send_header(c, MQTT_CMD_SUBSCRIBE, 2, (uint32_t) len); + if (++c->mgr->mqtt_id == 0) ++c->mgr->mqtt_id; + mg_send_u16(c, mg_htons(c->mgr->mqtt_id)); + if (c->is_mqtt5) mg_send_mqtt_properties(c, opts->props, opts->num_props); + + mg_send_u16(c, mg_htons((uint16_t) opts->topic.len)); + mg_send(c, opts->topic.ptr, opts->topic.len); + mg_send(c, &qos_, sizeof(qos_)); +} + +int mg_mqtt_parse(const uint8_t *buf, size_t len, uint8_t version, + struct mg_mqtt_message *m) { + uint8_t lc = 0, *p, *end; + uint32_t n = 0, len_len = 0; + + memset(m, 0, sizeof(*m)); + m->dgram.ptr = (char *) buf; + if (len < 2) return MQTT_INCOMPLETE; + m->cmd = (uint8_t) (buf[0] >> 4); + m->qos = (buf[0] >> 1) & 3; + + n = len_len = 0; + p = (uint8_t *) buf + 1; + while ((size_t) (p - buf) < len) { + lc = *((uint8_t *) p++); + n += (uint32_t) ((lc & 0x7f) << 7 * len_len); + len_len++; + if (!(lc & 0x80)) break; + if (len_len >= 4) return MQTT_MALFORMED; + } + end = p + n; + if ((lc & 0x80) || (end > buf + len)) return MQTT_INCOMPLETE; + m->dgram.len = (size_t) (end - buf); + + switch (m->cmd) { + case MQTT_CMD_CONNACK: + if (end - p < 2) return MQTT_MALFORMED; + m->ack = p[1]; + break; + case MQTT_CMD_PUBACK: + case MQTT_CMD_PUBREC: + case MQTT_CMD_PUBREL: + case MQTT_CMD_PUBCOMP: + case MQTT_CMD_SUBSCRIBE: + case MQTT_CMD_SUBACK: + case MQTT_CMD_UNSUBSCRIBE: + case MQTT_CMD_UNSUBACK: + if (p + 2 > end) return MQTT_MALFORMED; + m->id = (uint16_t) ((((uint16_t) p[0]) << 8) | p[1]); + p += 2; + break; + case MQTT_CMD_PUBLISH: { + if (p + 2 > end) return MQTT_MALFORMED; + m->topic.len = (uint16_t) ((((uint16_t) p[0]) << 8) | p[1]); + m->topic.ptr = (char *) p + 2; + p += 2 + m->topic.len; + if (p > end) return MQTT_MALFORMED; + if (m->qos > 0) { + if (p + 2 > end) return MQTT_MALFORMED; + m->id = (uint16_t) ((((uint16_t) p[0]) << 8) | p[1]); + p += 2; + } + if (p > end) return MQTT_MALFORMED; + if (version == 5 && p + 2 < end) { + m->props_size = decode_variable_length((char *) p, &len_len); + m->props_start = (size_t) (p + len_len - buf); + p += len_len + m->props_size; + } + if (p > end) return MQTT_MALFORMED; + m->data.ptr = (char *) p; + m->data.len = (size_t) (end - p); + break; + } + default: break; + } + return MQTT_OK; +} + +static void mqtt_cb(struct mg_connection *c, int ev, void *ev_data, + void *fn_data) { + if (ev == MG_EV_READ) { + for (;;) { + uint8_t version = c->is_mqtt5 ? 5 : 4; + struct mg_mqtt_message mm; + int rc = mg_mqtt_parse(c->recv.buf, c->recv.len, version, &mm); + if (rc == MQTT_MALFORMED) { + MG_ERROR(("%lu MQTT malformed message", c->id)); + c->is_closing = 1; + break; + } else if (rc == MQTT_OK) { + MG_VERBOSE(("%lu MQTT CMD %d len %d [%.*s]", c->id, mm.cmd, + (int) mm.dgram.len, (int) mm.data.len, mm.data.ptr)); + switch (mm.cmd) { + case MQTT_CMD_CONNACK: + mg_call(c, MG_EV_MQTT_OPEN, &mm.ack); + if (mm.ack == 0) { + MG_DEBUG(("%lu Connected", c->id)); + } else { + MG_ERROR(("%lu MQTT auth failed, code %d", c->id, mm.ack)); + c->is_closing = 1; + } + break; + case MQTT_CMD_PUBLISH: { + MG_DEBUG(("%lu [%.*s] -> [%.*s]", c->id, (int) mm.topic.len, + mm.topic.ptr, (int) mm.data.len, mm.data.ptr)); + if (mm.qos > 0) { + uint16_t id = mg_htons(mm.id); + uint32_t remaining_len = sizeof(id); + if (c->is_mqtt5) remaining_len += 1; + + mg_mqtt_send_header(c, MQTT_CMD_PUBACK, 0, remaining_len); + mg_send(c, &id, sizeof(id)); + + if (c->is_mqtt5) { + uint16_t zero = 0; + mg_send(c, &zero, sizeof(zero)); + } + } + mg_call(c, MG_EV_MQTT_MSG, &mm); + break; + } + } + mg_call(c, MG_EV_MQTT_CMD, &mm); + mg_iobuf_del(&c->recv, 0, mm.dgram.len); + } else { + break; + } + } + } + (void) ev_data; + (void) fn_data; +} + +void mg_mqtt_ping(struct mg_connection *nc) { + mg_mqtt_send_header(nc, MQTT_CMD_PINGREQ, 0, 0); +} + +void mg_mqtt_pong(struct mg_connection *nc) { + mg_mqtt_send_header(nc, MQTT_CMD_PINGRESP, 0, 0); +} + +void mg_mqtt_disconnect(struct mg_connection *c, + const struct mg_mqtt_opts *opts) { + size_t len = 0; + if (c->is_mqtt5) len = 1 + get_props_size(opts->props, opts->num_props); + mg_mqtt_send_header(c, MQTT_CMD_DISCONNECT, 0, (uint32_t) len); + + if (c->is_mqtt5) { + uint8_t zero = 0; + mg_send(c, &zero, sizeof(zero)); // reason code + mg_send_mqtt_properties(c, opts->props, opts->num_props); + } +} + +struct mg_connection *mg_mqtt_connect(struct mg_mgr *mgr, const char *url, + const struct mg_mqtt_opts *opts, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = mg_connect(mgr, url, fn, fn_data); + if (c != NULL) { + struct mg_mqtt_opts empty; + memset(&empty, 0, sizeof(empty)); + mg_mqtt_login(c, opts == NULL ? &empty : opts); + c->pfn = mqtt_cb; + } + return c; +} + +struct mg_connection *mg_mqtt_listen(struct mg_mgr *mgr, const char *url, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = mg_listen(mgr, url, fn, fn_data); + if (c != NULL) c->pfn = mqtt_cb, c->pfn_data = mgr; + return c; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/net.c" +#endif + + + + + + + + +size_t mg_vprintf(struct mg_connection *c, const char *fmt, va_list *ap) { + size_t old = c->send.len; + mg_vxprintf(mg_pfn_iobuf, &c->send, fmt, ap); + return c->send.len - old; +} + +size_t mg_printf(struct mg_connection *c, const char *fmt, ...) { + size_t len = 0; + va_list ap; + va_start(ap, fmt); + len = mg_vprintf(c, fmt, &ap); + va_end(ap); + return len; +} + +static bool mg_atonl(struct mg_str str, struct mg_addr *addr) { + if (mg_vcasecmp(&str, "localhost") != 0) return false; + addr->ip = mg_htonl(0x7f000001); + addr->is_ip6 = false; + return true; +} + +static bool mg_atone(struct mg_str str, struct mg_addr *addr) { + if (str.len > 0) return false; + addr->ip = 0; + addr->is_ip6 = false; + return true; +} + +static bool mg_aton4(struct mg_str str, struct mg_addr *addr) { + uint8_t data[4] = {0, 0, 0, 0}; + size_t i, num_dots = 0; + for (i = 0; i < str.len; i++) { + if (str.ptr[i] >= '0' && str.ptr[i] <= '9') { + int octet = data[num_dots] * 10 + (str.ptr[i] - '0'); + if (octet > 255) return false; + data[num_dots] = (uint8_t) octet; + } else if (str.ptr[i] == '.') { + if (num_dots >= 3 || i == 0 || str.ptr[i - 1] == '.') return false; + num_dots++; + } else { + return false; + } + } + if (num_dots != 3 || str.ptr[i - 1] == '.') return false; + memcpy(&addr->ip, data, sizeof(data)); + addr->is_ip6 = false; + return true; +} + +static bool mg_v4mapped(struct mg_str str, struct mg_addr *addr) { + int i; + if (str.len < 14) return false; + if (str.ptr[0] != ':' || str.ptr[1] != ':' || str.ptr[6] != ':') return false; + for (i = 2; i < 6; i++) { + if (str.ptr[i] != 'f' && str.ptr[i] != 'F') return false; + } + if (!mg_aton4(mg_str_n(&str.ptr[7], str.len - 7), addr)) return false; + memset(addr->ip6, 0, sizeof(addr->ip6)); + addr->ip6[10] = addr->ip6[11] = 255; + memcpy(&addr->ip6[12], &addr->ip, 4); + addr->is_ip6 = true; + return true; +} + +static bool mg_aton6(struct mg_str str, struct mg_addr *addr) { + size_t i, j = 0, n = 0, dc = 42; + if (str.len > 2 && str.ptr[0] == '[') str.ptr++, str.len -= 2; + if (mg_v4mapped(str, addr)) return true; + for (i = 0; i < str.len; i++) { + if ((str.ptr[i] >= '0' && str.ptr[i] <= '9') || + (str.ptr[i] >= 'a' && str.ptr[i] <= 'f') || + (str.ptr[i] >= 'A' && str.ptr[i] <= 'F')) { + unsigned long val; + if (i > j + 3) return false; + // MG_DEBUG(("%zu %zu [%.*s]", i, j, (int) (i - j + 1), &str.ptr[j])); + val = mg_unhexn(&str.ptr[j], i - j + 1); + addr->ip6[n] = (uint8_t) ((val >> 8) & 255); + addr->ip6[n + 1] = (uint8_t) (val & 255); + } else if (str.ptr[i] == ':') { + j = i + 1; + if (i > 0 && str.ptr[i - 1] == ':') { + dc = n; // Double colon + if (i > 1 && str.ptr[i - 2] == ':') return false; + } else if (i > 0) { + n += 2; + } + if (n > 14) return false; + addr->ip6[n] = addr->ip6[n + 1] = 0; // For trailing :: + } else { + return false; + } + } + if (n < 14 && dc == 42) return false; + if (n < 14) { + memmove(&addr->ip6[dc + (14 - n)], &addr->ip6[dc], n - dc + 2); + memset(&addr->ip6[dc], 0, 14 - n); + } + addr->is_ip6 = true; + return true; +} + +bool mg_aton(struct mg_str str, struct mg_addr *addr) { + // MG_INFO(("[%.*s]", (int) str.len, str.ptr)); + return mg_atone(str, addr) || mg_atonl(str, addr) || mg_aton4(str, addr) || + mg_aton6(str, addr); +} + +struct mg_connection *mg_alloc_conn(struct mg_mgr *mgr) { + struct mg_connection *c = + (struct mg_connection *) calloc(1, sizeof(*c) + mgr->extraconnsize); + if (c != NULL) { + c->mgr = mgr; + c->send.align = c->recv.align = MG_IO_SIZE; + c->id = ++mgr->nextid; + } + return c; +} + +void mg_close_conn(struct mg_connection *c) { + mg_resolve_cancel(c); // Close any pending DNS query + LIST_DELETE(struct mg_connection, &c->mgr->conns, c); + if (c == c->mgr->dns4.c) c->mgr->dns4.c = NULL; + if (c == c->mgr->dns6.c) c->mgr->dns6.c = NULL; + // Order of operations is important. `MG_EV_CLOSE` event must be fired + // before we deallocate received data, see #1331 + mg_call(c, MG_EV_CLOSE, NULL); + MG_DEBUG(("%lu %p closed", c->id, c->fd)); + + mg_tls_free(c); + mg_iobuf_free(&c->recv); + mg_iobuf_free(&c->send); + memset(c, 0, sizeof(*c)); + free(c); +} + +struct mg_connection *mg_connect(struct mg_mgr *mgr, const char *url, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = NULL; + if (url == NULL || url[0] == '\0') { + MG_ERROR(("null url")); + } else if ((c = mg_alloc_conn(mgr)) == NULL) { + MG_ERROR(("OOM")); + } else { + LIST_ADD_HEAD(struct mg_connection, &mgr->conns, c); + c->is_udp = (strncmp(url, "udp:", 4) == 0); + c->fd = (void *) (size_t) MG_INVALID_SOCKET; + c->fn = fn; + c->is_client = true; + c->fn_data = fn_data; + MG_DEBUG(("%lu %p %s", c->id, c->fd, url)); + mg_call(c, MG_EV_OPEN, NULL); + mg_resolve(c, url); + } + return c; +} + +struct mg_connection *mg_listen(struct mg_mgr *mgr, const char *url, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = NULL; + if ((c = mg_alloc_conn(mgr)) == NULL) { + MG_ERROR(("OOM %s", url)); + } else if (!mg_open_listener(c, url)) { + MG_ERROR(("Failed: %s, errno %d", url, errno)); + free(c); + c = NULL; + } else { + c->is_listening = 1; + c->is_udp = strncmp(url, "udp:", 4) == 0; + LIST_ADD_HEAD(struct mg_connection, &mgr->conns, c); + c->fn = fn; + c->fn_data = fn_data; + mg_call(c, MG_EV_OPEN, NULL); + MG_DEBUG(("%lu %p %s", c->id, c->fd, url)); + } + return c; +} + +struct mg_connection *mg_wrapfd(struct mg_mgr *mgr, int fd, + mg_event_handler_t fn, void *fn_data) { + struct mg_connection *c = mg_alloc_conn(mgr); + if (c != NULL) { + c->fd = (void *) (size_t) fd; + c->fn = fn; + c->fn_data = fn_data; + MG_EPOLL_ADD(c); + mg_call(c, MG_EV_OPEN, NULL); + LIST_ADD_HEAD(struct mg_connection, &mgr->conns, c); + } + return c; +} + +struct mg_timer *mg_timer_add(struct mg_mgr *mgr, uint64_t milliseconds, + unsigned flags, void (*fn)(void *), void *arg) { + struct mg_timer *t = (struct mg_timer *) calloc(1, sizeof(*t)); + if (t != NULL) { + mg_timer_init(&mgr->timers, t, milliseconds, flags, fn, arg); + t->id = mgr->timerid++; + } + return t; +} + +void mg_mgr_free(struct mg_mgr *mgr) { + struct mg_connection *c; + struct mg_timer *tmp, *t = mgr->timers; + while (t != NULL) tmp = t->next, free(t), t = tmp; + mgr->timers = NULL; // Important. Next call to poll won't touch timers + for (c = mgr->conns; c != NULL; c = c->next) c->is_closing = 1; + mg_mgr_poll(mgr, 0); +#if MG_ENABLE_FREERTOS_TCP + FreeRTOS_DeleteSocketSet(mgr->ss); +#endif + MG_DEBUG(("All connections closed")); +#if MG_ENABLE_EPOLL + if (mgr->epoll_fd >= 0) close(mgr->epoll_fd), mgr->epoll_fd = -1; +#endif +} + +void mg_mgr_init(struct mg_mgr *mgr) { + memset(mgr, 0, sizeof(*mgr)); +#if MG_ENABLE_EPOLL + if ((mgr->epoll_fd = epoll_create1(0)) < 0) MG_ERROR(("epoll: %d", errno)); +#else + mgr->epoll_fd = -1; +#endif +#if MG_ARCH == MG_ARCH_WIN32 && MG_ENABLE_WINSOCK + // clang-format off + { WSADATA data; WSAStartup(MAKEWORD(2, 2), &data); } + // clang-format on +#elif MG_ENABLE_FREERTOS_TCP + mgr->ss = FreeRTOS_CreateSocketSet(); +#elif defined(__unix) || defined(__unix__) || defined(__APPLE__) + // Ignore SIGPIPE signal, so if client cancels the request, it + // won't kill the whole process. + signal(SIGPIPE, SIG_IGN); +#endif + mgr->dnstimeout = 3000; + mgr->dns4.url = "udp://8.8.8.8:53"; + mgr->dns6.url = "udp://[2001:4860:4860::8888]:53"; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/printf.c" +#endif + + + + +size_t mg_queue_vprintf(struct mg_queue *q, const char *fmt, va_list *ap) { + size_t len = mg_snprintf(NULL, 0, fmt, ap); + char *buf; + if (len == 0 || mg_queue_book(q, &buf, len + 1) < len + 1) { + len = 0; // Nah. Not enough space + } else { + len = mg_vsnprintf((char *) buf, len + 1, fmt, ap); + mg_queue_add(q, len); + } + return len; +} + +size_t mg_queue_printf(struct mg_queue *q, const char *fmt, ...) { + va_list ap; + size_t len; + va_start(ap, fmt); + len = mg_queue_vprintf(q, fmt, &ap); + va_end(ap); + return len; +} + +static void mg_pfn_iobuf_private(char ch, void *param, bool expand) { + struct mg_iobuf *io = (struct mg_iobuf *) param; + if (expand && io->len + 2 > io->size) mg_iobuf_resize(io, io->len + 2); + if (io->len + 2 <= io->size) { + io->buf[io->len++] = (uint8_t) ch; + io->buf[io->len] = 0; + } else if (io->len < io->size) { + io->buf[io->len++] = 0; // Guarantee to 0-terminate + } +} + +static void mg_putchar_iobuf_static(char ch, void *param) { + mg_pfn_iobuf_private(ch, param, false); +} + +void mg_pfn_iobuf(char ch, void *param) { + mg_pfn_iobuf_private(ch, param, true); +} + +size_t mg_vsnprintf(char *buf, size_t len, const char *fmt, va_list *ap) { + struct mg_iobuf io = {(uint8_t *) buf, len, 0, 0}; + size_t n = mg_vxprintf(mg_putchar_iobuf_static, &io, fmt, ap); + if (n < len) buf[n] = '\0'; + return n; +} + +size_t mg_snprintf(char *buf, size_t len, const char *fmt, ...) { + va_list ap; + size_t n; + va_start(ap, fmt); + n = mg_vsnprintf(buf, len, fmt, &ap); + va_end(ap); + return n; +} + +char *mg_vmprintf(const char *fmt, va_list *ap) { + struct mg_iobuf io = {0, 0, 0, 256}; + mg_vxprintf(mg_pfn_iobuf, &io, fmt, ap); + return (char *) io.buf; +} + +char *mg_mprintf(const char *fmt, ...) { + char *s; + va_list ap; + va_start(ap, fmt); + s = mg_vmprintf(fmt, &ap); + va_end(ap); + return s; +} + +void mg_pfn_stdout(char c, void *param) { + putchar(c); + (void) param; +} + +static size_t print_ip4(void (*out)(char, void *), void *arg, uint8_t *p) { + return mg_xprintf(out, arg, "%d.%d.%d.%d", p[0], p[1], p[2], p[3]); +} + +static size_t print_ip6(void (*out)(char, void *), void *arg, uint16_t *p) { + return mg_xprintf(out, arg, "[%x:%x:%x:%x:%x:%x:%x:%x]", mg_ntohs(p[0]), + mg_ntohs(p[1]), mg_ntohs(p[2]), mg_ntohs(p[3]), + mg_ntohs(p[4]), mg_ntohs(p[5]), mg_ntohs(p[6]), + mg_ntohs(p[7])); +} + +size_t mg_print_ip4(void (*out)(char, void *), void *arg, va_list *ap) { + uint8_t *p = va_arg(*ap, uint8_t *); + return print_ip4(out, arg, p); +} + +size_t mg_print_ip6(void (*out)(char, void *), void *arg, va_list *ap) { + uint16_t *p = va_arg(*ap, uint16_t *); + return print_ip6(out, arg, p); +} + +size_t mg_print_ip(void (*out)(char, void *), void *arg, va_list *ap) { + struct mg_addr *addr = va_arg(*ap, struct mg_addr *); + if (addr->is_ip6) return print_ip6(out, arg, (uint16_t *) addr->ip6); + return print_ip4(out, arg, (uint8_t *) &addr->ip); +} + +size_t mg_print_ip_port(void (*out)(char, void *), void *arg, va_list *ap) { + struct mg_addr *a = va_arg(*ap, struct mg_addr *); + return mg_xprintf(out, arg, "%M:%hu", mg_print_ip, a, mg_ntohs(a->port)); +} + +size_t mg_print_mac(void (*out)(char, void *), void *arg, va_list *ap) { + uint8_t *p = va_arg(*ap, uint8_t *); + return mg_xprintf(out, arg, "%02x:%02x:%02x:%02x:%02x:%02x", p[0], p[1], p[2], + p[3], p[4], p[5]); +} + +static char mg_esc(int c, bool esc) { + const char *p, *esc1 = "\b\f\n\r\t\\\"", *esc2 = "bfnrt\\\""; + for (p = esc ? esc1 : esc2; *p != '\0'; p++) { + if (*p == c) return esc ? esc2[p - esc1] : esc1[p - esc2]; + } + return 0; +} + +static char mg_escape(int c) { + return mg_esc(c, true); +} + +static size_t qcpy(void (*out)(char, void *), void *ptr, char *buf, + size_t len) { + size_t i = 0, extra = 0; + for (i = 0; i < len && buf[i] != '\0'; i++) { + char c = mg_escape(buf[i]); + if (c) { + out('\\', ptr), out(c, ptr), extra++; + } else { + out(buf[i], ptr); + } + } + return i + extra; +} + +static size_t bcpy(void (*out)(char, void *), void *arg, uint8_t *buf, + size_t len) { + size_t i, j, n = 0; + const char *t = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; + for (i = 0; i < len; i += 3) { + uint8_t c1 = buf[i], c2 = i + 1 < len ? buf[i + 1] : 0, + c3 = i + 2 < len ? buf[i + 2] : 0; + char tmp[4] = {t[c1 >> 2], t[(c1 & 3) << 4 | (c2 >> 4)], '=', '='}; + if (i + 1 < len) tmp[2] = t[(c2 & 15) << 2 | (c3 >> 6)]; + if (i + 2 < len) tmp[3] = t[c3 & 63]; + for (j = 0; j < sizeof(tmp) && tmp[j] != '\0'; j++) out(tmp[j], arg); + n += j; + } + return n; +} + +size_t mg_print_hex(void (*out)(char, void *), void *arg, va_list *ap) { + size_t bl = (size_t) va_arg(*ap, int); + uint8_t *p = va_arg(*ap, uint8_t *); + const char *hex = "0123456789abcdef"; + size_t j; + for (j = 0; j < bl; j++) { + out(hex[(p[j] >> 4) & 0x0F], arg); + out(hex[p[j] & 0x0F], arg); + } + return 2 * bl; +} +size_t mg_print_base64(void (*out)(char, void *), void *arg, va_list *ap) { + size_t len = (size_t) va_arg(*ap, int); + uint8_t *buf = va_arg(*ap, uint8_t *); + return bcpy(out, arg, buf, len); +} + +size_t mg_print_esc(void (*out)(char, void *), void *arg, va_list *ap) { + size_t len = (size_t) va_arg(*ap, int); + char *p = va_arg(*ap, char *); + if (len == 0) len = p == NULL ? 0 : strlen(p); + return qcpy(out, arg, p, len); +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/queue.c" +#endif + + + +#if defined(__GNUC__) || defined(__clang__) +#define MG_MEMORY_BARRIER() __sync_synchronize() +#elif defined(_MSC_VER) && _MSC_VER >= 1700 +#define MG_MEMORY_BARRIER() MemoryBarrier() +#elif !defined(MG_MEMORY_BARRIER) +#define MG_MEMORY_BARRIER() +#endif + +// Every message in a queue is prepended by a 32-bit message length (ML). +// If ML is 0, then it is the end, and reader must wrap to the beginning. +// +// Queue when q->tail <= q->head: +// |----- free -----| ML | message1 | ML | message2 | ----- free ------| +// ^ ^ ^ ^ +// buf tail head len +// +// Queue when q->tail > q->head: +// | ML | message2 |----- free ------| ML | message1 | 0 |---- free ----| +// ^ ^ ^ ^ +// buf head tail len + +void mg_queue_init(struct mg_queue *q, char *buf, size_t size) { + q->size = size; + q->buf = buf; + q->head = q->tail = 0; +} + +static size_t mg_queue_read_len(struct mg_queue *q) { + uint32_t n = 0; + MG_MEMORY_BARRIER(); + memcpy(&n, q->buf + q->tail, sizeof(n)); + assert(q->tail + n + sizeof(n) <= q->size); + return n; +} + +static void mg_queue_write_len(struct mg_queue *q, size_t len) { + uint32_t n = (uint32_t) len; + memcpy(q->buf + q->head, &n, sizeof(n)); + MG_MEMORY_BARRIER(); +} + +size_t mg_queue_book(struct mg_queue *q, char **buf, size_t len) { + size_t space = 0, hs = sizeof(uint32_t) * 2; // *2 is for the 0 marker + if (q->head >= q->tail && q->head + len + hs <= q->size) { + space = q->size - q->head - hs; // There is enough space + } else if (q->head >= q->tail && q->tail > hs) { + mg_queue_write_len(q, 0); // Not enough space ahead + q->head = 0; // Wrap head to the beginning + } + if (q->head + hs + len < q->tail) space = q->tail - q->head - hs; + if (buf != NULL) *buf = q->buf + q->head + sizeof(uint32_t); + return space; +} + +size_t mg_queue_next(struct mg_queue *q, char **buf) { + size_t len = 0; + if (q->tail != q->head) { + len = mg_queue_read_len(q); + if (len == 0) { // Zero (head wrapped) ? + q->tail = 0; // Reset tail to the start + if (q->head > q->tail) len = mg_queue_read_len(q); // Read again + } + } + if (buf != NULL) *buf = q->buf + q->tail + sizeof(uint32_t); + assert(q->tail + len <= q->size); + return len; +} + +void mg_queue_add(struct mg_queue *q, size_t len) { + assert(len > 0); + mg_queue_write_len(q, len); + assert(q->head + sizeof(uint32_t) * 2 + len <= q->size); + q->head += len + sizeof(uint32_t); +} + +void mg_queue_del(struct mg_queue *q, size_t len) { + q->tail += len + sizeof(uint32_t); + assert(q->tail + sizeof(uint32_t) <= q->size); +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/rpc.c" +#endif + + + +void mg_rpc_add(struct mg_rpc **head, struct mg_str method, + void (*fn)(struct mg_rpc_req *), void *fn_data) { + struct mg_rpc *rpc = (struct mg_rpc *) calloc(1, sizeof(*rpc)); + if (rpc != NULL) { + rpc->method = mg_strdup(method), rpc->fn = fn, rpc->fn_data = fn_data; + rpc->next = *head, *head = rpc; + } +} + +void mg_rpc_del(struct mg_rpc **head, void (*fn)(struct mg_rpc_req *)) { + struct mg_rpc *r; + while ((r = *head) != NULL) { + if (r->fn == fn || fn == NULL) { + *head = r->next; + free((void *) r->method.ptr); + free(r); + } else { + head = &(*head)->next; + } + } +} + +static void mg_rpc_call(struct mg_rpc_req *r, struct mg_str method) { + struct mg_rpc *h = r->head == NULL ? NULL : *r->head; + while (h != NULL && !mg_match(method, h->method, NULL)) h = h->next; + if (h != NULL) { + r->rpc = h; + h->fn(r); + } else { + mg_rpc_err(r, -32601, "\"%.*s not found\"", (int) method.len, method.ptr); + } +} + +void mg_rpc_process(struct mg_rpc_req *r) { + int len, off = mg_json_get(r->frame, "$.method", &len); + if (off > 0 && r->frame.ptr[off] == '"') { + struct mg_str method = mg_str_n(&r->frame.ptr[off + 1], (size_t) len - 2); + mg_rpc_call(r, method); + } else if ((off = mg_json_get(r->frame, "$.result", &len)) > 0 || + (off = mg_json_get(r->frame, "$.error", &len)) > 0) { + mg_rpc_call(r, mg_str("")); // JSON response! call "" method handler + } else { + mg_rpc_err(r, -32700, "%m", mg_print_esc, (int) r->frame.len, + r->frame.ptr); // Invalid + } +} + +void mg_rpc_vok(struct mg_rpc_req *r, const char *fmt, va_list *ap) { + int len, off = mg_json_get(r->frame, "$.id", &len); + if (off > 0) { + mg_xprintf(r->pfn, r->pfn_data, "{%m:%.*s,%m:", mg_print_esc, 0, "id", len, + &r->frame.ptr[off], mg_print_esc, 0, "result"); + mg_vxprintf(r->pfn, r->pfn_data, fmt == NULL ? "null" : fmt, ap); + mg_xprintf(r->pfn, r->pfn_data, "}"); + } +} + +void mg_rpc_ok(struct mg_rpc_req *r, const char *fmt, ...) { + va_list ap; + va_start(ap, fmt); + mg_rpc_vok(r, fmt, &ap); + va_end(ap); +} + +void mg_rpc_verr(struct mg_rpc_req *r, int code, const char *fmt, va_list *ap) { + int len, off = mg_json_get(r->frame, "$.id", &len); + mg_xprintf(r->pfn, r->pfn_data, "{"); + if (off > 0) { + mg_xprintf(r->pfn, r->pfn_data, "%m:%.*s,", mg_print_esc, 0, "id", len, + &r->frame.ptr[off]); + } + mg_xprintf(r->pfn, r->pfn_data, "%m:{%m:%d,%m:", mg_print_esc, 0, "error", + mg_print_esc, 0, "code", code, mg_print_esc, 0, "message"); + mg_vxprintf(r->pfn, r->pfn_data, fmt == NULL ? "null" : fmt, ap); + mg_xprintf(r->pfn, r->pfn_data, "}}"); +} + +void mg_rpc_err(struct mg_rpc_req *r, int code, const char *fmt, ...) { + va_list ap; + va_start(ap, fmt); + mg_rpc_verr(r, code, fmt, &ap); + va_end(ap); +} + +static size_t print_methods(mg_pfn_t pfn, void *pfn_data, va_list *ap) { + struct mg_rpc *h, **head = (struct mg_rpc **) va_arg(*ap, void **); + size_t len = 0; + for (h = *head; h != NULL; h = h->next) { + if (h->method.len == 0) continue; // Ignore response handler + len += mg_xprintf(pfn, pfn_data, "%s%m", h == *head ? "" : ",", + mg_print_esc, (int) h->method.len, h->method.ptr); + } + return len; +} + +void mg_rpc_list(struct mg_rpc_req *r) { + mg_rpc_ok(r, "[%M]", print_methods, r->head); +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/sha1.c" +#endif +/* Copyright(c) By Steve Reid */ +/* 100% Public Domain */ + + + +union char64long16 { + unsigned char c[64]; + uint32_t l[16]; +}; + +#define rol(value, bits) (((value) << (bits)) | ((value) >> (32 - (bits)))) + +static uint32_t blk0(union char64long16 *block, int i) { + if (MG_BIG_ENDIAN) { + } else { + block->l[i] = (rol(block->l[i], 24) & 0xFF00FF00) | + (rol(block->l[i], 8) & 0x00FF00FF); + } + return block->l[i]; +} + +/* Avoid redefine warning (ARM /usr/include/sys/ucontext.h define R0~R4) */ +#undef blk +#undef R0 +#undef R1 +#undef R2 +#undef R3 +#undef R4 + +#define blk(i) \ + (block->l[i & 15] = rol(block->l[(i + 13) & 15] ^ block->l[(i + 8) & 15] ^ \ + block->l[(i + 2) & 15] ^ block->l[i & 15], \ + 1)) +#define R0(v, w, x, y, z, i) \ + z += ((w & (x ^ y)) ^ y) + blk0(block, i) + 0x5A827999 + rol(v, 5); \ + w = rol(w, 30); +#define R1(v, w, x, y, z, i) \ + z += ((w & (x ^ y)) ^ y) + blk(i) + 0x5A827999 + rol(v, 5); \ + w = rol(w, 30); +#define R2(v, w, x, y, z, i) \ + z += (w ^ x ^ y) + blk(i) + 0x6ED9EBA1 + rol(v, 5); \ + w = rol(w, 30); +#define R3(v, w, x, y, z, i) \ + z += (((w | x) & y) | (w & x)) + blk(i) + 0x8F1BBCDC + rol(v, 5); \ + w = rol(w, 30); +#define R4(v, w, x, y, z, i) \ + z += (w ^ x ^ y) + blk(i) + 0xCA62C1D6 + rol(v, 5); \ + w = rol(w, 30); + +static void mg_sha1_transform(uint32_t state[5], + const unsigned char *buffer) { + uint32_t a, b, c, d, e; + union char64long16 block[1]; + + memcpy(block, buffer, 64); + a = state[0]; + b = state[1]; + c = state[2]; + d = state[3]; + e = state[4]; + R0(a, b, c, d, e, 0); + R0(e, a, b, c, d, 1); + R0(d, e, a, b, c, 2); + R0(c, d, e, a, b, 3); + R0(b, c, d, e, a, 4); + R0(a, b, c, d, e, 5); + R0(e, a, b, c, d, 6); + R0(d, e, a, b, c, 7); + R0(c, d, e, a, b, 8); + R0(b, c, d, e, a, 9); + R0(a, b, c, d, e, 10); + R0(e, a, b, c, d, 11); + R0(d, e, a, b, c, 12); + R0(c, d, e, a, b, 13); + R0(b, c, d, e, a, 14); + R0(a, b, c, d, e, 15); + R1(e, a, b, c, d, 16); + R1(d, e, a, b, c, 17); + R1(c, d, e, a, b, 18); + R1(b, c, d, e, a, 19); + R2(a, b, c, d, e, 20); + R2(e, a, b, c, d, 21); + R2(d, e, a, b, c, 22); + R2(c, d, e, a, b, 23); + R2(b, c, d, e, a, 24); + R2(a, b, c, d, e, 25); + R2(e, a, b, c, d, 26); + R2(d, e, a, b, c, 27); + R2(c, d, e, a, b, 28); + R2(b, c, d, e, a, 29); + R2(a, b, c, d, e, 30); + R2(e, a, b, c, d, 31); + R2(d, e, a, b, c, 32); + R2(c, d, e, a, b, 33); + R2(b, c, d, e, a, 34); + R2(a, b, c, d, e, 35); + R2(e, a, b, c, d, 36); + R2(d, e, a, b, c, 37); + R2(c, d, e, a, b, 38); + R2(b, c, d, e, a, 39); + R3(a, b, c, d, e, 40); + R3(e, a, b, c, d, 41); + R3(d, e, a, b, c, 42); + R3(c, d, e, a, b, 43); + R3(b, c, d, e, a, 44); + R3(a, b, c, d, e, 45); + R3(e, a, b, c, d, 46); + R3(d, e, a, b, c, 47); + R3(c, d, e, a, b, 48); + R3(b, c, d, e, a, 49); + R3(a, b, c, d, e, 50); + R3(e, a, b, c, d, 51); + R3(d, e, a, b, c, 52); + R3(c, d, e, a, b, 53); + R3(b, c, d, e, a, 54); + R3(a, b, c, d, e, 55); + R3(e, a, b, c, d, 56); + R3(d, e, a, b, c, 57); + R3(c, d, e, a, b, 58); + R3(b, c, d, e, a, 59); + R4(a, b, c, d, e, 60); + R4(e, a, b, c, d, 61); + R4(d, e, a, b, c, 62); + R4(c, d, e, a, b, 63); + R4(b, c, d, e, a, 64); + R4(a, b, c, d, e, 65); + R4(e, a, b, c, d, 66); + R4(d, e, a, b, c, 67); + R4(c, d, e, a, b, 68); + R4(b, c, d, e, a, 69); + R4(a, b, c, d, e, 70); + R4(e, a, b, c, d, 71); + R4(d, e, a, b, c, 72); + R4(c, d, e, a, b, 73); + R4(b, c, d, e, a, 74); + R4(a, b, c, d, e, 75); + R4(e, a, b, c, d, 76); + R4(d, e, a, b, c, 77); + R4(c, d, e, a, b, 78); + R4(b, c, d, e, a, 79); + state[0] += a; + state[1] += b; + state[2] += c; + state[3] += d; + state[4] += e; + /* Erase working structures. The order of operations is important, + * used to ensure that compiler doesn't optimize those out. */ + memset(block, 0, sizeof(block)); + a = b = c = d = e = 0; + (void) a; + (void) b; + (void) c; + (void) d; + (void) e; +} + +void mg_sha1_init(mg_sha1_ctx *context) { + context->state[0] = 0x67452301; + context->state[1] = 0xEFCDAB89; + context->state[2] = 0x98BADCFE; + context->state[3] = 0x10325476; + context->state[4] = 0xC3D2E1F0; + context->count[0] = context->count[1] = 0; +} + +void mg_sha1_update(mg_sha1_ctx *context, const unsigned char *data, + size_t len) { + size_t i, j; + + j = context->count[0]; + if ((context->count[0] += (uint32_t) len << 3) < j) context->count[1]++; + context->count[1] += (uint32_t) (len >> 29); + j = (j >> 3) & 63; + if ((j + len) > 63) { + memcpy(&context->buffer[j], data, (i = 64 - j)); + mg_sha1_transform(context->state, context->buffer); + for (; i + 63 < len; i += 64) { + mg_sha1_transform(context->state, &data[i]); + } + j = 0; + } else + i = 0; + memcpy(&context->buffer[j], &data[i], len - i); +} + +void mg_sha1_final(unsigned char digest[20], mg_sha1_ctx *context) { + unsigned i; + unsigned char finalcount[8], c; + + for (i = 0; i < 8; i++) { + finalcount[i] = (unsigned char) ((context->count[(i >= 4 ? 0 : 1)] >> + ((3 - (i & 3)) * 8)) & + 255); + } + c = 0200; + mg_sha1_update(context, &c, 1); + while ((context->count[0] & 504) != 448) { + c = 0000; + mg_sha1_update(context, &c, 1); + } + mg_sha1_update(context, finalcount, 8); + for (i = 0; i < 20; i++) { + digest[i] = + (unsigned char) ((context->state[i >> 2] >> ((3 - (i & 3)) * 8)) & 255); + } + memset(context, '\0', sizeof(*context)); + memset(&finalcount, '\0', sizeof(finalcount)); +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/sntp.c" +#endif + + + + + + +#define SNTP_TIME_OFFSET 2208988800U // (1970 - 1900) in seconds +#define SNTP_MAX_FRAC 4294967295.0 // 2 ** 32 - 1 + +static int64_t gettimestamp(const uint32_t *data) { + uint32_t sec = mg_ntohl(data[0]), frac = mg_ntohl(data[1]); + if (sec) sec -= SNTP_TIME_OFFSET; + return ((int64_t) sec) * 1000 + (int64_t) (frac / SNTP_MAX_FRAC * 1000.0); +} + +int64_t mg_sntp_parse(const unsigned char *buf, size_t len) { + int64_t res = -1; + int mode = len > 0 ? buf[0] & 7 : 0; + int version = len > 0 ? (buf[0] >> 3) & 7 : 0; + if (len < 48) { + MG_ERROR(("%s", "corrupt packet")); + } else if (mode != 4 && mode != 5) { + MG_ERROR(("%s", "not a server reply")); + } else if (buf[1] == 0) { + MG_ERROR(("%s", "server sent a kiss of death")); + } else if (version == 4 || version == 3) { + // int64_t ref = gettimestamp((uint32_t *) &buf[16]); + int64_t t0 = gettimestamp((uint32_t *) &buf[24]); + int64_t t1 = gettimestamp((uint32_t *) &buf[32]); + int64_t t2 = gettimestamp((uint32_t *) &buf[40]); + int64_t t3 = (int64_t) mg_millis(); + int64_t delta = (t3 - t0) - (t2 - t1); + MG_VERBOSE(("%lld %lld %lld %lld delta:%lld", t0, t1, t2, t3, delta)); + res = t2 + delta / 2; + } else { + MG_ERROR(("unexpected version: %d", version)); + } + return res; +} + +static void sntp_cb(struct mg_connection *c, int ev, void *evd, void *fnd) { + if (ev == MG_EV_READ) { + int64_t milliseconds = mg_sntp_parse(c->recv.buf, c->recv.len); + if (milliseconds > 0) { + MG_INFO(("%lu got time: %lld ms from epoch", c->id, milliseconds)); + mg_call(c, MG_EV_SNTP_TIME, (uint64_t *) &milliseconds); + MG_VERBOSE(("%u.%u", (unsigned) (milliseconds / 1000), + (unsigned) (milliseconds % 1000))); + } + mg_iobuf_del(&c->recv, 0, c->recv.len); // Free receive buffer + } else if (ev == MG_EV_CONNECT) { + mg_sntp_request(c); + } else if (ev == MG_EV_CLOSE) { + } + (void) fnd; + (void) evd; +} + +void mg_sntp_request(struct mg_connection *c) { + if (c->is_resolving) { + MG_ERROR(("%lu wait until resolved", c->id)); + } else { + int64_t now = (int64_t) mg_millis(); // Use int64_t, for vc98 + uint8_t buf[48] = {0}; + uint32_t *t = (uint32_t *) &buf[40]; + double frac = ((double) (now % 1000)) / 1000.0 * SNTP_MAX_FRAC; + buf[0] = (0 << 6) | (4 << 3) | 3; + t[0] = mg_htonl((uint32_t) (now / 1000) + SNTP_TIME_OFFSET); + t[1] = mg_htonl((uint32_t) frac); + mg_send(c, buf, sizeof(buf)); + } +} + +struct mg_connection *mg_sntp_connect(struct mg_mgr *mgr, const char *url, + mg_event_handler_t fn, void *fnd) { + struct mg_connection *c = NULL; + if (url == NULL) url = "udp://time.google.com:123"; + if ((c = mg_connect(mgr, url, fn, fnd)) != NULL) c->pfn = sntp_cb; + return c; +} + +#ifdef MG_ENABLE_LINES +#line 1 "src/sock.c" +#endif + + + + + + + + + + + +#if MG_ENABLE_SOCKET + +#ifndef closesocket +#define closesocket(x) close(x) +#endif + +#define FD(c_) ((MG_SOCKET_TYPE) (size_t) (c_)->fd) +#define S2PTR(s_) ((void *) (size_t) (s_)) + +#ifndef MSG_NONBLOCKING +#define MSG_NONBLOCKING 0 +#endif + +#ifndef AF_INET6 +#define AF_INET6 10 +#endif + +#ifndef MG_SOCK_ERR +#define MG_SOCK_ERR(errcode) ((errcode) < 0 ? errno : 0) +#endif + +#ifndef MG_SOCK_INTR +#define MG_SOCK_INTR(fd) (fd == MG_INVALID_SOCKET && MG_SOCK_ERR(-1) == EINTR) +#endif + +#ifndef MG_SOCK_PENDING +#define MG_SOCK_PENDING(errcode) \ + (((errcode) < 0) && (errno == EINPROGRESS || errno == EWOULDBLOCK)) +#endif + +#ifndef MG_SOCK_RESET +#define MG_SOCK_RESET(errcode) \ + (((errcode) < 0) && (errno == EPIPE || errno == ECONNRESET)) +#endif + +union usa { + struct sockaddr sa; + struct sockaddr_in sin; +#if MG_ENABLE_IPV6 + struct sockaddr_in6 sin6; +#endif +}; + +static socklen_t tousa(struct mg_addr *a, union usa *usa) { + socklen_t len = sizeof(usa->sin); + memset(usa, 0, sizeof(*usa)); + usa->sin.sin_family = AF_INET; + usa->sin.sin_port = a->port; + *(uint32_t *) &usa->sin.sin_addr = a->ip; +#if MG_ENABLE_IPV6 + if (a->is_ip6) { + usa->sin.sin_family = AF_INET6; + usa->sin6.sin6_port = a->port; + memcpy(&usa->sin6.sin6_addr, a->ip6, sizeof(a->ip6)); + len = sizeof(usa->sin6); + } +#endif + return len; +} + +static void tomgaddr(union usa *usa, struct mg_addr *a, bool is_ip6) { + a->is_ip6 = is_ip6; + a->port = usa->sin.sin_port; + memcpy(&a->ip, &usa->sin.sin_addr, sizeof(a->ip)); +#if MG_ENABLE_IPV6 + if (is_ip6) { + memcpy(a->ip6, &usa->sin6.sin6_addr, sizeof(a->ip6)); + a->port = usa->sin6.sin6_port; + } +#endif +} + +static void setlocaddr(MG_SOCKET_TYPE fd, struct mg_addr *addr) { + union usa usa; + socklen_t n = sizeof(usa); + if (getsockname(fd, &usa.sa, &n) == 0) { + tomgaddr(&usa, addr, n != sizeof(usa.sin)); + } +} + +static void iolog(struct mg_connection *c, char *buf, long n, bool r) { + if (n == MG_IO_WAIT) { + // Do nothing + } else if (n <= 0) { + c->is_closing = 1; // Termination. Don't call mg_error(): #1529 + } else if (n > 0) { + if (c->is_hexdumping) { + union usa usa; + socklen_t slen = sizeof(usa.sin); + if (getsockname(FD(c), &usa.sa, &slen) < 0) (void) 0; // Ignore result + MG_INFO(("\n-- %lu %M %s %M %ld", c->id, mg_print_ip_port, &c->loc, + r ? "<-" : "->", mg_print_ip_port, &c->rem, n)); + + mg_hexdump(buf, (size_t) n); + } + if (r) { + c->recv.len += (size_t) n; + mg_call(c, MG_EV_READ, &n); + } else { + mg_iobuf_del(&c->send, 0, (size_t) n); + // if (c->send.len == 0) mg_iobuf_resize(&c->send, 0); + if (c->send.len == 0) { + MG_EPOLL_MOD(c, 0); + } + mg_call(c, MG_EV_WRITE, &n); + } + } +} + +long mg_io_send(struct mg_connection *c, const void *buf, size_t len) { + long n; + if (c->is_udp) { + union usa usa; + socklen_t slen = tousa(&c->rem, &usa); + n = sendto(FD(c), (char *) buf, len, 0, &usa.sa, slen); + if (n > 0) setlocaddr(FD(c), &c->loc); + } else { + n = send(FD(c), (char *) buf, len, MSG_NONBLOCKING); + } + if (MG_SOCK_PENDING(n)) return MG_IO_WAIT; + if (MG_SOCK_RESET(n)) return MG_IO_RESET; + if (n <= 0) return MG_IO_ERR; + return n; +} + +bool mg_send(struct mg_connection *c, const void *buf, size_t len) { + if (c->is_udp) { + long n = mg_io_send(c, buf, len); + MG_DEBUG(("%lu %p %d:%d %ld err %d", c->id, c->fd, (int) c->send.len, + (int) c->recv.len, n, MG_SOCK_ERR(n))); + iolog(c, (char *) buf, n, false); + return n > 0; + } else { + return mg_iobuf_add(&c->send, c->send.len, buf, len); + } +} + +static void mg_set_non_blocking_mode(MG_SOCKET_TYPE fd) { +#if defined(MG_CUSTOM_NONBLOCK) + MG_CUSTOM_NONBLOCK(fd); +#elif MG_ARCH == MG_ARCH_WIN32 && MG_ENABLE_WINSOCK + unsigned long on = 1; + ioctlsocket(fd, FIONBIO, &on); +#elif MG_ENABLE_RL + unsigned long on = 1; + ioctlsocket(fd, FIONBIO, &on); +#elif MG_ENABLE_FREERTOS_TCP + const BaseType_t off = 0; + if (setsockopt(fd, 0, FREERTOS_SO_RCVTIMEO, &off, sizeof(off)) != 0) (void) 0; + if (setsockopt(fd, 0, FREERTOS_SO_SNDTIMEO, &off, sizeof(off)) != 0) (void) 0; +#elif MG_ENABLE_LWIP + lwip_fcntl(fd, F_SETFL, O_NONBLOCK); +#elif MG_ARCH == MG_ARCH_AZURERTOS + fcntl(fd, F_SETFL, O_NONBLOCK); +#elif MG_ARCH == MG_ARCH_TIRTOS + int val = 0; + setsockopt(fd, SOL_SOCKET, SO_BLOCKING, &val, sizeof(val)); + // SPRU524J section 3.3.3 page 63, SO_SNDLOWAT + int sz = sizeof(val); + getsockopt(fd, SOL_SOCKET, SO_SNDBUF, &val, &sz); + val /= 2; // set send low-water mark at half send buffer size + setsockopt(fd, SOL_SOCKET, SO_SNDLOWAT, &val, sizeof(val)); +#else + fcntl(fd, F_SETFL, fcntl(fd, F_GETFL, 0) | O_NONBLOCK); // Non-blocking mode + fcntl(fd, F_SETFD, FD_CLOEXEC); // Set close-on-exec +#endif +} + +bool mg_open_listener(struct mg_connection *c, const char *url) { + MG_SOCKET_TYPE fd = MG_INVALID_SOCKET; + bool success = false; + c->loc.port = mg_htons(mg_url_port(url)); + if (!mg_aton(mg_url_host(url), &c->loc)) { + MG_ERROR(("invalid listening URL: %s", url)); + } else { + union usa usa; + socklen_t slen = tousa(&c->loc, &usa); + int rc, on = 1, af = c->loc.is_ip6 ? AF_INET6 : AF_INET; + int type = strncmp(url, "udp:", 4) == 0 ? SOCK_DGRAM : SOCK_STREAM; + int proto = type == SOCK_DGRAM ? IPPROTO_UDP : IPPROTO_TCP; + (void) on; + + if ((fd = socket(af, type, proto)) == MG_INVALID_SOCKET) { + MG_ERROR(("socket: %d", MG_SOCK_ERR(-1))); +#if defined(SO_EXCLUSIVEADDRUSE) + } else if ((rc = setsockopt(fd, SOL_SOCKET, SO_EXCLUSIVEADDRUSE, + (char *) &on, sizeof(on))) != 0) { + // "Using SO_REUSEADDR and SO_EXCLUSIVEADDRUSE" + MG_ERROR(("setsockopt(SO_EXCLUSIVEADDRUSE): %d %d", on, MG_SOCK_ERR(rc))); +#elif defined(SO_REUSEADDR) && (!defined(LWIP_SOCKET) || SO_REUSE) + } else if ((rc = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, (char *) &on, + sizeof(on))) != 0) { + // 1. SO_REUSEADDR semantics on UNIX and Windows is different. On + // Windows, SO_REUSEADDR allows to bind a socket to a port without error + // even if the port is already open by another program. This is not the + // behavior SO_REUSEADDR was designed for, and leads to hard-to-track + // failure scenarios. + // + // 2. For LWIP, SO_REUSEADDR should be explicitly enabled by defining + // SO_REUSE = 1 in lwipopts.h, otherwise the code below will compile but + // won't work! (setsockopt will return EINVAL) + MG_ERROR(("setsockopt(SO_REUSEADDR): %d", MG_SOCK_ERR(rc))); +#endif +#if defined(IPV6_V6ONLY) + } else if (c->loc.is_ip6 && + (rc = setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *) &on, + sizeof(on))) != 0) { + // See #2089. Allow to bind v4 and v6 sockets on the same port + MG_ERROR(("setsockopt(IPV6_V6ONLY): %d", MG_SOCK_ERR(rc))); +#endif + } else if ((rc = bind(fd, &usa.sa, slen)) != 0) { + MG_ERROR(("bind: %d", MG_SOCK_ERR(rc))); + } else if ((type == SOCK_STREAM && + (rc = listen(fd, MG_SOCK_LISTEN_BACKLOG_SIZE)) != 0)) { + // NOTE(lsm): FreeRTOS uses backlog value as a connection limit + // In case port was set to 0, get the real port number + MG_ERROR(("listen: %d", MG_SOCK_ERR(rc))); + } else { + setlocaddr(fd, &c->loc); + mg_set_non_blocking_mode(fd); + c->fd = S2PTR(fd); + MG_EPOLL_ADD(c); + success = true; + } + } + if (success == false && fd != MG_INVALID_SOCKET) closesocket(fd); + return success; +} + +long mg_io_recv(struct mg_connection *c, void *buf, size_t len) { + long n = 0; + if (c->is_udp) { + union usa usa; + socklen_t slen = tousa(&c->rem, &usa); + n = recvfrom(FD(c), (char *) buf, len, 0, &usa.sa, &slen); + if (n > 0) tomgaddr(&usa, &c->rem, slen != sizeof(usa.sin)); + } else { + n = recv(FD(c), (char *) buf, len, MSG_NONBLOCKING); + } + if (MG_SOCK_PENDING(n)) return MG_IO_WAIT; + if (MG_SOCK_RESET(n)) return MG_IO_RESET; + if (n <= 0) return MG_IO_ERR; + return n; +} + +// NOTE(lsm): do only one iteration of reads, cause some systems +// (e.g. FreeRTOS stack) return 0 instead of -1/EWOULDBLOCK when no data +static void read_conn(struct mg_connection *c) { + long n = -1; + if (c->recv.len >= MG_MAX_RECV_SIZE) { + mg_error(c, "max_recv_buf_size reached"); + } else if (c->recv.size <= c->recv.len && + !mg_iobuf_resize(&c->recv, c->recv.size + MG_IO_SIZE)) { + mg_error(c, "oom"); + } else { + char *buf = (char *) &c->recv.buf[c->recv.len]; + size_t len = c->recv.size - c->recv.len; + n = c->is_tls ? mg_tls_recv(c, buf, len) : mg_io_recv(c, buf, len); + MG_DEBUG(("%lu %p snd %ld/%ld rcv %ld/%ld n=%ld err=%d", c->id, c->fd, + (long) c->send.len, (long) c->send.size, (long) c->recv.len, + (long) c->recv.size, n, MG_SOCK_ERR(n))); + iolog(c, buf, n, true); + } +} + +static void write_conn(struct mg_connection *c) { + char *buf = (char *) c->send.buf; + size_t len = c->send.len; + long n = c->is_tls ? mg_tls_send(c, buf, len) : mg_io_send(c, buf, len); + MG_DEBUG(("%lu %p snd %ld/%ld rcv %ld/%ld n=%ld err=%d", c->id, c->fd, + (long) c->send.len, (long) c->send.size, (long) c->recv.len, + (long) c->recv.size, n, MG_SOCK_ERR(n))); + iolog(c, buf, n, false); +} + +static void close_conn(struct mg_connection *c) { + if (FD(c) != MG_INVALID_SOCKET) { +#if MG_ENABLE_EPOLL + epoll_ctl(c->mgr->epoll_fd, EPOLL_CTL_DEL, FD(c), NULL); +#endif + closesocket(FD(c)); +#if MG_ENABLE_FREERTOS_TCP + FreeRTOS_FD_CLR(c->fd, c->mgr->ss, eSELECT_ALL); +#endif + } + mg_close_conn(c); +} + +static void connect_conn(struct mg_connection *c) { + union usa usa; + socklen_t n = sizeof(usa); + // Use getpeername() to test whether we have connected + if (getpeername(FD(c), &usa.sa, &n) == 0) { + c->is_connecting = 0; + mg_call(c, MG_EV_CONNECT, NULL); + MG_EPOLL_MOD(c, 0); + if (c->is_tls_hs) mg_tls_handshake(c); + } else { + mg_error(c, "socket error"); + } +} + +static void setsockopts(struct mg_connection *c) { +#if MG_ENABLE_FREERTOS_TCP || MG_ARCH == MG_ARCH_AZURERTOS || \ + MG_ARCH == MG_ARCH_TIRTOS + (void) c; +#else + int on = 1; +#if !defined(SOL_TCP) +#define SOL_TCP IPPROTO_TCP +#endif + if (setsockopt(FD(c), SOL_TCP, TCP_NODELAY, (char *) &on, sizeof(on)) != 0) + (void) 0; + if (setsockopt(FD(c), SOL_SOCKET, SO_KEEPALIVE, (char *) &on, sizeof(on)) != + 0) + (void) 0; +#endif +} + +void mg_connect_resolved(struct mg_connection *c) { + int type = c->is_udp ? SOCK_DGRAM : SOCK_STREAM; + int rc, af = c->rem.is_ip6 ? AF_INET6 : AF_INET; // c->rem has resolved IP + c->fd = S2PTR(socket(af, type, 0)); // Create outbound socket + c->is_resolving = 0; // Clear resolving flag + if (FD(c) == MG_INVALID_SOCKET) { + mg_error(c, "socket(): %d", MG_SOCK_ERR(-1)); + } else if (c->is_udp) { + MG_EPOLL_ADD(c); +#if MG_ARCH == MG_ARCH_TIRTOS + union usa usa; // TI-RTOS NDK requires binding to receive on UDP sockets + socklen_t slen = tousa(&c->loc, &usa); + if ((rc = bind(c->fd, &usa.sa, slen)) != 0) + MG_ERROR(("bind: %d", MG_SOCK_ERR(rc))); +#endif + mg_call(c, MG_EV_RESOLVE, NULL); + mg_call(c, MG_EV_CONNECT, NULL); + } else { + union usa usa; + socklen_t slen = tousa(&c->rem, &usa); + mg_set_non_blocking_mode(FD(c)); + setsockopts(c); + MG_EPOLL_ADD(c); + mg_call(c, MG_EV_RESOLVE, NULL); + rc = connect(FD(c), &usa.sa, slen); // Attempt to connect + if (rc == 0) { // Success + mg_call(c, MG_EV_CONNECT, NULL); // Send MG_EV_CONNECT to the user + } else if (MG_SOCK_PENDING(rc)) { // Need to wait for TCP handshake + MG_DEBUG(("%lu %p -> %M pend", c->id, c->fd, mg_print_ip_port, &c->rem)); + c->is_connecting = 1; + } else { + mg_error(c, "connect: %d", MG_SOCK_ERR(rc)); + } + } +} + +static MG_SOCKET_TYPE raccept(MG_SOCKET_TYPE sock, union usa *usa, + socklen_t *len) { + MG_SOCKET_TYPE fd = MG_INVALID_SOCKET; + do { + memset(usa, 0, sizeof(*usa)); + fd = accept(sock, &usa->sa, len); + } while (MG_SOCK_INTR(fd)); + return fd; +} + +static void accept_conn(struct mg_mgr *mgr, struct mg_connection *lsn) { + struct mg_connection *c = NULL; + union usa usa; + socklen_t sa_len = sizeof(usa); + MG_SOCKET_TYPE fd = raccept(FD(lsn), &usa, &sa_len); + if (fd == MG_INVALID_SOCKET) { +#if MG_ARCH == MG_ARCH_AZURERTOS + // AzureRTOS, in non-block socket mode can mark listening socket readable + // even it is not. See comment for 'select' func implementation in + // nx_bsd.c That's not an error, just should try later + if (errno != EAGAIN) +#endif + MG_ERROR(("%lu accept failed, errno %d", lsn->id, MG_SOCK_ERR(-1))); +#if (MG_ARCH != MG_ARCH_WIN32) && !MG_ENABLE_FREERTOS_TCP && \ + (MG_ARCH != MG_ARCH_TIRTOS) && !MG_ENABLE_POLL + } else if ((long) fd >= FD_SETSIZE) { + MG_ERROR(("%ld > %ld", (long) fd, (long) FD_SETSIZE)); + closesocket(fd); +#endif + } else if ((c = mg_alloc_conn(mgr)) == NULL) { + MG_ERROR(("%lu OOM", lsn->id)); + closesocket(fd); + } else { + tomgaddr(&usa, &c->rem, sa_len != sizeof(usa.sin)); + LIST_ADD_HEAD(struct mg_connection, &mgr->conns, c); + c->fd = S2PTR(fd); + MG_EPOLL_ADD(c); + mg_set_non_blocking_mode(FD(c)); + setsockopts(c); + c->is_accepted = 1; + c->is_hexdumping = lsn->is_hexdumping; + c->loc = lsn->loc; + c->pfn = lsn->pfn; + c->pfn_data = lsn->pfn_data; + c->fn = lsn->fn; + c->fn_data = lsn->fn_data; + MG_DEBUG(("%lu %p accepted %M -> %M", c->id, c->fd, mg_print_ip_port, + &c->rem, mg_print_ip_port, &c->loc)); + mg_call(c, MG_EV_OPEN, NULL); + mg_call(c, MG_EV_ACCEPT, NULL); + } +} + +static bool mg_socketpair(MG_SOCKET_TYPE sp[2], union usa usa[2], bool udp) { + MG_SOCKET_TYPE sock; + socklen_t n = sizeof(usa[0].sin); + bool success = false; + + sock = sp[0] = sp[1] = MG_INVALID_SOCKET; + (void) memset(&usa[0], 0, sizeof(usa[0])); + usa[0].sin.sin_family = AF_INET; + *(uint32_t *) &usa->sin.sin_addr = mg_htonl(0x7f000001U); // 127.0.0.1 + usa[1] = usa[0]; + + if (udp && (sp[0] = socket(AF_INET, SOCK_DGRAM, 0)) != MG_INVALID_SOCKET && + (sp[1] = socket(AF_INET, SOCK_DGRAM, 0)) != MG_INVALID_SOCKET && + bind(sp[0], &usa[0].sa, n) == 0 && bind(sp[1], &usa[1].sa, n) == 0 && + getsockname(sp[0], &usa[0].sa, &n) == 0 && + getsockname(sp[1], &usa[1].sa, &n) == 0 && + connect(sp[0], &usa[1].sa, n) == 0 && + connect(sp[1], &usa[0].sa, n) == 0) { + success = true; + } else if (!udp && + (sock = socket(AF_INET, SOCK_STREAM, 0)) != MG_INVALID_SOCKET && + bind(sock, &usa[0].sa, n) == 0 && + listen(sock, MG_SOCK_LISTEN_BACKLOG_SIZE) == 0 && + getsockname(sock, &usa[0].sa, &n) == 0 && + (sp[0] = socket(AF_INET, SOCK_STREAM, 0)) != MG_INVALID_SOCKET && + connect(sp[0], &usa[0].sa, n) == 0 && + (sp[1] = raccept(sock, &usa[1], &n)) != MG_INVALID_SOCKET) { + success = true; + } + if (success) { + mg_set_non_blocking_mode(sp[1]); + } else { + if (sp[0] != MG_INVALID_SOCKET) closesocket(sp[0]); + if (sp[1] != MG_INVALID_SOCKET) closesocket(sp[1]); + sp[0] = sp[1] = MG_INVALID_SOCKET; + } + if (sock != MG_INVALID_SOCKET) closesocket(sock); + return success; +} + +int mg_mkpipe(struct mg_mgr *mgr, mg_event_handler_t fn, void *fn_data, + bool udp) { + union usa usa[2]; + MG_SOCKET_TYPE sp[2] = {MG_INVALID_SOCKET, MG_INVALID_SOCKET}; + struct mg_connection *c = NULL; + if (!mg_socketpair(sp, usa, udp)) { + MG_ERROR(("Cannot create socket pair")); + } else if ((c = mg_wrapfd(mgr, (int) sp[1], fn, fn_data)) == NULL) { + closesocket(sp[0]); + closesocket(sp[1]); + sp[0] = sp[1] = MG_INVALID_SOCKET; + } else { + tomgaddr(&usa[0], &c->rem, false); + MG_DEBUG(("%lu %p pipe %lu", c->id, c->fd, (unsigned long) sp[0])); + } + return (int) sp[0]; +} + +static bool can_read(const struct mg_connection *c) { + return c->is_full == false; +} + +static bool can_write(const struct mg_connection *c) { + return c->is_connecting || (c->send.len > 0 && c->is_tls_hs == 0); +} + +static bool skip_iotest(const struct mg_connection *c) { + return (c->is_closing || c->is_resolving || FD(c) == MG_INVALID_SOCKET) || + (can_read(c) == false && can_write(c) == false); +} + +static void mg_iotest(struct mg_mgr *mgr, int ms) { +#if MG_ENABLE_FREERTOS_TCP + struct mg_connection *c; + for (c = mgr->conns; c != NULL; c = c->next) { + c->is_readable = c->is_writable = 0; + if (skip_iotest(c)) continue; + if (can_read(c)) + FreeRTOS_FD_SET(c->fd, mgr->ss, eSELECT_READ | eSELECT_EXCEPT); + if (can_write(c)) FreeRTOS_FD_SET(c->fd, mgr->ss, eSELECT_WRITE); + } + FreeRTOS_select(mgr->ss, pdMS_TO_TICKS(ms)); + for (c = mgr->conns; c != NULL; c = c->next) { + EventBits_t bits = FreeRTOS_FD_ISSET(c->fd, mgr->ss); + c->is_readable = bits & (eSELECT_READ | eSELECT_EXCEPT) ? 1U : 0; + c->is_writable = bits & eSELECT_WRITE ? 1U : 0; + if (c->fd != MG_INVALID_SOCKET) + FreeRTOS_FD_CLR(c->fd, mgr->ss, + eSELECT_READ | eSELECT_EXCEPT | eSELECT_WRITE); + } +#elif MG_ENABLE_EPOLL + size_t max = 1; + for (struct mg_connection *c = mgr->conns; c != NULL; c = c->next) { + c->is_readable = c->is_writable = 0; + if (mg_tls_pending(c) > 0) ms = 1, c->is_readable = 1; + if (can_write(c)) MG_EPOLL_MOD(c, 1); + max++; + } + struct epoll_event *evs = (struct epoll_event *) alloca(max * sizeof(evs[0])); + int n = epoll_wait(mgr->epoll_fd, evs, (int) max, ms); + for (int i = 0; i < n; i++) { + struct mg_connection *c = (struct mg_connection *) evs[i].data.ptr; + if (evs[i].events & EPOLLERR) { + mg_error(c, "socket error"); + } else if (c->is_readable == 0) { + bool rd = evs[i].events & (EPOLLIN | EPOLLHUP); + bool wr = evs[i].events & EPOLLOUT; + c->is_readable = can_read(c) && rd ? 1U : 0; + c->is_writable = can_write(c) && wr ? 1U : 0; + } + } + (void) skip_iotest; +#elif MG_ENABLE_POLL + nfds_t n = 0; + for (struct mg_connection *c = mgr->conns; c != NULL; c = c->next) n++; + struct pollfd *fds = (struct pollfd *) alloca(n * sizeof(fds[0])); + memset(fds, 0, n * sizeof(fds[0])); + n = 0; + for (struct mg_connection *c = mgr->conns; c != NULL; c = c->next) { + c->is_readable = c->is_writable = 0; + if (skip_iotest(c)) { + // Socket not valid, ignore + } else if (mg_tls_pending(c) > 0) { + ms = 1; // Don't wait if TLS is ready + } else { + fds[n].fd = FD(c); + if (can_read(c)) fds[n].events |= POLLIN; + if (can_write(c)) fds[n].events |= POLLOUT; + n++; + } + } + + // MG_INFO(("poll n=%d ms=%d", (int) n, ms)); + if (poll(fds, n, ms) < 0) { +#if MG_ARCH == MG_ARCH_WIN32 + if (n == 0) Sleep(ms); // On Windows, poll fails if no sockets +#endif + memset(fds, 0, n * sizeof(fds[0])); + } + n = 0; + for (struct mg_connection *c = mgr->conns; c != NULL; c = c->next) { + if (skip_iotest(c)) { + // Socket not valid, ignore + } else if (mg_tls_pending(c) > 0) { + c->is_readable = 1; + } else { + if (fds[n].revents & POLLERR) { + mg_error(c, "socket error"); + } else { + c->is_readable = + (unsigned) (fds[n].revents & (POLLIN | POLLHUP) ? 1 : 0); + c->is_writable = (unsigned) (fds[n].revents & POLLOUT ? 1 : 0); + } + n++; + } + } +#else + struct timeval tv = {ms / 1000, (ms % 1000) * 1000}, tv_zero = {0, 0}, *tvp; + struct mg_connection *c; + fd_set rset, wset, eset; + MG_SOCKET_TYPE maxfd = 0; + int rc; + + FD_ZERO(&rset); + FD_ZERO(&wset); + FD_ZERO(&eset); + tvp = ms < 0 ? NULL : &tv; + for (c = mgr->conns; c != NULL; c = c->next) { + c->is_readable = c->is_writable = 0; + if (skip_iotest(c)) continue; + FD_SET(FD(c), &eset); + if (can_read(c)) FD_SET(FD(c), &rset); + if (can_write(c)) FD_SET(FD(c), &wset); + if (mg_tls_pending(c) > 0) tvp = &tv_zero; + if (FD(c) > maxfd) maxfd = FD(c); + } + + if ((rc = select((int) maxfd + 1, &rset, &wset, &eset, tvp)) < 0) { +#if MG_ARCH == MG_ARCH_WIN32 + if (maxfd == 0) Sleep(ms); // On Windows, select fails if no sockets +#else + MG_ERROR(("select: %d %d", rc, MG_SOCK_ERR(rc))); +#endif + FD_ZERO(&rset); + FD_ZERO(&wset); + FD_ZERO(&eset); + } + + for (c = mgr->conns; c != NULL; c = c->next) { + if (FD(c) != MG_INVALID_SOCKET && FD_ISSET(FD(c), &eset)) { + mg_error(c, "socket error"); + } else { + c->is_readable = FD(c) != MG_INVALID_SOCKET && FD_ISSET(FD(c), &rset); + c->is_writable = FD(c) != MG_INVALID_SOCKET && FD_ISSET(FD(c), &wset); + if (mg_tls_pending(c) > 0) c->is_readable = 1; + } + } +#endif +} + +void mg_mgr_poll(struct mg_mgr *mgr, int ms) { + struct mg_connection *c, *tmp; + uint64_t now; + + mg_iotest(mgr, ms); + now = mg_millis(); + mg_timer_poll(&mgr->timers, now); + + for (c = mgr->conns; c != NULL; c = tmp) { + bool is_resp = c->is_resp; + tmp = c->next; + mg_call(c, MG_EV_POLL, &now); + if (is_resp && !c->is_resp) { + long n = 0; + mg_call(c, MG_EV_READ, &n); + } + MG_VERBOSE(("%lu %c%c %c%c%c%c%c", c->id, c->is_readable ? 'r' : '-', + c->is_writable ? 'w' : '-', c->is_tls ? 'T' : 't', + c->is_connecting ? 'C' : 'c', c->is_tls_hs ? 'H' : 'h', + c->is_resolving ? 'R' : 'r', c->is_closing ? 'C' : 'c')); + if (c->is_resolving || c->is_closing) { + // Do nothing + } else if (c->is_listening && c->is_udp == 0) { + if (c->is_readable) accept_conn(mgr, c); + } else if (c->is_connecting) { + if (c->is_readable || c->is_writable) connect_conn(c); + } else if (c->is_tls_hs) { + if ((c->is_readable || c->is_writable)) mg_tls_handshake(c); + } else { + if (c->is_readable) read_conn(c); + if (c->is_writable) write_conn(c); + } + + if (c->is_draining && c->send.len == 0) c->is_closing = 1; + if (c->is_closing) close_conn(c); + } +} +#endif + +#ifdef MG_ENABLE_LINES +#line 1 "src/ssi.c" +#endif + + + + +#ifndef MG_MAX_SSI_DEPTH +#define MG_MAX_SSI_DEPTH 5 +#endif + +#ifndef MG_SSI_BUFSIZ +#define MG_SSI_BUFSIZ 1024 +#endif + +#if MG_ENABLE_SSI +static char *mg_ssi(const char *path, const char *root, int depth) { + struct mg_iobuf b = {NULL, 0, 0, MG_IO_SIZE}; + FILE *fp = fopen(path, "rb"); + if (fp != NULL) { + char buf[MG_SSI_BUFSIZ], arg[sizeof(buf)]; + int ch, intag = 0; + size_t len = 0; + buf[0] = arg[0] = '\0'; + while ((ch = fgetc(fp)) != EOF) { + if (intag && ch == '>' && buf[len - 1] == '-' && buf[len - 2] == '-') { + buf[len++] = (char) (ch & 0xff); + buf[len] = '\0'; + if (sscanf(buf, " + // + // 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 diff --git a/src/utils.cc b/src/utils.cc new file mode 100644 index 0000000..2cd7310 --- /dev/null +++ b/src/utils.cc @@ -0,0 +1,305 @@ +#include "pch.h" +#include "utils.h" +#include +#define BUFSIZE 1024 +#define JPEG0 0xFF +#define JPEG1 0xD8 +#define JPEG2 0xFF +#define PNG0 0x89 +#define PNG1 0x50 +#define PNG2 0x4E +#define BMP0 0x42 +#define BMP1 0x4D +#define GIF0 0x47 +#define GIF1 0x49 +#define GIF2 0x46 + +namespace wxhelper { +std::wstring Utils::UTF8ToWstring(const std::string &str) { + return Utils::AnsiToWstring(str, CP_UTF8); +} + +std::string Utils::WstringToUTF8(const std::wstring &str) { + return Utils::WstringToAnsi(str, CP_UTF8); +} + +std::wstring Utils::AnsiToWstring(const std::string &input, DWORD locale) { + int wchar_len = MultiByteToWideChar(locale, 0, input.c_str(), -1, NULL, 0); + if (wchar_len > 0) { + std::vector temp(wchar_len); + MultiByteToWideChar(CP_UTF8, 0, input.c_str(), -1, &temp[0], wchar_len); + return std::wstring(&temp[0]); + } + + return std::wstring(); +} + +std::string Utils::WstringToAnsi(const std::wstring &input, DWORD locale) { + int char_len = WideCharToMultiByte(locale, 0, input.c_str(), -1, 0, 0, 0, 0); + if (char_len > 0) { + std::vector temp(char_len); + WideCharToMultiByte(locale, 0, input.c_str(), -1, &temp[0], char_len, 0, 0); + return std::string(&temp[0]); + } + return std::string(); +} + +UINT64 Utils::GetWeChatWinBase() { + return (UINT64)GetModuleHandleA("WeChatWin.dll"); +} + +bool Utils::CreateConsole() { + if (AllocConsole()) { + AttachConsole(GetCurrentProcessId()); + FILE *retStream; + freopen_s(&retStream, "CONOUT$", "w", stdout); + if (!retStream) throw std::runtime_error("Stdout redirection failed."); + freopen_s(&retStream, "CONOUT$", "w", stderr); + if (!retStream) throw std::runtime_error("Stderr redirection failed."); + return false; + } + return true; +} + +void Utils::CloseConsole() { + fclose(stdin); + fclose(stdout); + fclose(stderr); + FreeConsole(); +} + +std::string Utils::EncodeHexString(const std::string &str) { + const std::string hex_table = "0123456789abcdef"; + std::string sb; + for (int i = 0; i < str.length(); i++) { + sb += hex_table.at((str[i] & 0xf0) >> 4); + sb += hex_table.at((str[i] & 0x0f) >> 0); + } + return sb; +} + +std::string Utils::Hex2String(const std::string &hex_str) { + std::string ret; + const std::string hex_table = "0123456789abcdef"; + for (int i = 0; i < hex_str.length(); i += 2) { + ret += BYTE(hex_table.find(hex_str.at(i)) << 4 | + hex_table.find(hex_str.at(i + 1))); + } + return ret; +} + +std::string Utils::Bytes2Hex(const BYTE *bytes, const int length) { + if (bytes == NULL) { + return ""; + } + std::string buff; + const int len = length; + for (int j = 0; j < len; j++) { + int high = bytes[j] / 16, low = bytes[j] % 16; + buff += (high < 10) ? ('0' + high) : ('a' + high - 10); + buff += (low < 10) ? ('0' + low) : ('a' + low - 10); + } + return buff; +} + +void Utils::Hex2Bytes(const std::string &hex, BYTE *bytes) { + int byte_len = hex.length() / 2; + std::string str; + unsigned int n; + for (int i = 0; i < byte_len; i++) { + str = hex.substr(i * 2, 2); + sscanf_s(str.c_str(), "%x", &n); + bytes[i] = n; + } +} + +bool Utils::IsDigit(std::string str) { + if (str.length() == 0) { + return false; + } + for (auto it : str) { + if (it < '0' || it > '9') { + return false; + } + } + return true; +} + +bool Utils::FindOrCreateDirectoryW(const wchar_t *path) { + WIN32_FIND_DATAW fd; + HANDLE hFind = ::FindFirstFileW(path, &fd); + if (hFind != INVALID_HANDLE_VALUE && + (fd.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)) { + FindClose(hFind); + return true; + } + + if (!::CreateDirectoryW(path, NULL)) { + return false; + } + return true; +} + +void Utils::HookAnyAddress(DWORD hook_addr, LPVOID jmp_addr, char *origin) { + BYTE jmp_code[5] = {0}; + jmp_code[0] = 0xE9; + *(DWORD *)&jmp_code[1] = (DWORD)jmp_addr - hook_addr - 5; + DWORD old_protext = 0; + VirtualProtect((LPVOID)hook_addr, 5, PAGE_EXECUTE_READWRITE, &old_protext); + ReadProcessMemory(GetCurrentProcess(), (LPVOID)hook_addr, origin, 5, 0); + memcpy((void *)hook_addr, jmp_code, 5); + VirtualProtect((LPVOID)hook_addr, 5, old_protext, &old_protext); +} + +void Utils::UnHookAnyAddress(DWORD hook_addr, char *origin) { + DWORD old_protext = 0; + VirtualProtect((LPVOID)hook_addr, 5, PAGE_EXECUTE_READWRITE, &old_protext); + WriteProcessMemory(GetCurrentProcess(), (LPVOID)hook_addr, origin, 5, 0); + VirtualProtect((LPVOID)hook_addr, 5, old_protext, &old_protext); +} + +std::wstring Utils::GetTimeW(long long timestamp) { + wchar_t *wstr = new wchar_t[20]; + memset(wstr, 0, 20 * 2); + tm tm_out; + localtime_s(&tm_out, ×tamp); + swprintf_s(wstr, 20, L"%04d-%02d-%02d %02d:%02d:%02d", 1900 + tm_out.tm_year, + tm_out.tm_mon + 1, tm_out.tm_mday, tm_out.tm_hour, tm_out.tm_min, + tm_out.tm_sec); + std::wstring str_time(wstr); + delete[] wstr; + return str_time; +} + +std::string Utils::WCharToUTF8(wchar_t *wstr) { + int c_size = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, FALSE); + if (c_size > 0) { + char *buffer = new char[c_size]; + WideCharToMultiByte(CP_UTF8, 0, wstr, -1, buffer, c_size, NULL, FALSE); + std::string str(buffer); + delete[] buffer; + buffer = NULL; + return str; + } + return std::string(); +} + +bool Utils::IsTextUtf8(const char *str,int length) { + char endian = 1; + bool littlen_endian = (*(char *)&endian == 1); + + size_t i; + int bytes_num; + unsigned char chr; + + i = 0; + bytes_num = 0; + while (i < length) { + if (littlen_endian) { + chr = *(str + i); + } else { // Big Endian + chr = (*(str + i) << 8) | *(str + i + 1); + i++; + } + + if (bytes_num == 0) { + if ((chr & 0x80) != 0) { + while ((chr & 0x80) != 0) { + chr <<= 1; + bytes_num++; + } + if ((bytes_num < 2) || (bytes_num > 6)) { + return false; + } + bytes_num--; + } + } else { + if ((chr & 0xC0) != 0x80) { + return false; + } + bytes_num--; + } + i++; + } + return (bytes_num == 0); +} + +void Utils::Hide(HMODULE module) { + PPEB peb = (PPEB)__readgsqword(0x60); + PPEB_LDR_DATA ldr = peb->Ldr; + + void *cur_ptr = *((void **)((unsigned char *)ldr + 0x18)); + void *next_ptr = cur_ptr; + do { + void *next = *((void **)((unsigned char *)next_ptr)); + void *last = *((void **)((unsigned char *)next_ptr + 0x8)); + void *base_addr = *((void **)((unsigned char *)next_ptr + 0x30)); + if (base_addr == module) { + *((void **)((unsigned char *)last)) = next; + *((void **)((unsigned char *)next + 0x8)) = last; + cur_ptr = next; + } + next_ptr = *((void **)next_ptr); + } while (cur_ptr != next_ptr); +} + +std::string Utils::ReadSKBuiltinString(INT64 addr) { + INT64 inner_string = *(INT64 *)(addr + 0x8); + if (inner_string == 0) { + return std::string(); + } + return ReadWeChatStr(inner_string); +} + +std::string Utils::ReadSKBuiltinBuffer(INT64 addr) { + INT64 len = *(INT64 *)(addr + 0x10); + if (len == 0) { + return std::string(); + } + INT64 inner_string = *(INT64 *)(addr + 0x8); + if (inner_string == 0) { + return std::string(); + } + return ReadWeChatStr(inner_string); +} + +std::string Utils::ReadWeChatStr(INT64 addr) { + INT64 len = *(INT64 *)(addr + 0x10); + if (len == 0) { + return std::string(); + } + INT64 max_len = *(INT64 *)(addr + 0x18); + if ((max_len | 0xF) == 0xF) { + return std::string((char *)addr, len); + } + char *char_from_user = *(char **)(addr); + return std::string(char_from_user, len); +} + +std::string Utils::ImageXor(std::string buf){ + const char *origin = buf.c_str(); + short key = 0; + if ((*origin ^ JPEG0) == (*(origin + 1) ^ JPEG1)) { + key = *origin ^ JPEG0; + } else if ((*origin ^ PNG1) == (*(origin + 1) ^ PNG2)) { + key = *origin ^ PNG1; + } else if ((*origin ^ GIF0) == (*(origin + 1) ^ GIF1)) { + key = *origin ^ GIF0; + } else if ((*origin ^ BMP0) == (*(origin + 1) ^ BMP1)) { + key = *origin ^ BMP0; + } else { + key = -1; + } + if (key > 0) { + char *img_buf = new char[buf.size()]; + for (unsigned int i = 0; i < buf.size(); i++) { + img_buf[i] = *(origin + i) ^ key; + } + std::string str(img_buf); + delete[] img_buf; + img_buf = NULL; + return str; + } + return std::string(); +} +} // namespace wxhelper \ No newline at end of file diff --git a/src/utils.h b/src/utils.h new file mode 100644 index 0000000..0226ffe --- /dev/null +++ b/src/utils.h @@ -0,0 +1,87 @@ +#ifndef WXHELPER_UTILS_H_ +#define WXHELPER_UTILS_H_ +#include + +#include +#include +#define STRING2INT(str) (Utils::IsDigit(str) ? stoi(str) : 0) +#define WS2LPWS(wstr) (LPWSTR) wstr.c_str() +#define READ_WSTRING(addr, offset) ((*(DWORD *)(addr + offset + 0x4) == 0) ? std::wstring(L"") : std::wstring((wchar_t *)(*(DWORD *)(addr + offset)), *(DWORD *)(addr + offset + 0x4))) + + +namespace wxhelper { + +class Utils { + public: + static std::wstring UTF8ToWstring(const std::string &str); + + static std::string WstringToUTF8(const std::wstring &str); + + static std::wstring AnsiToWstring(const std::string &input, + DWORD locale = CP_ACP); + + static std::string WstringToAnsi(const std::wstring &input, + DWORD locale = CP_ACP); + + static UINT64 GetWeChatWinBase(); + + static bool CreateConsole(); + + static void CloseConsole(); + + static std::string EncodeHexString(const std::string &str); + + static std::string Hex2String(const std::string &hex_str); + + static std::string Bytes2Hex(const BYTE *bytes, const int length); + + static void Hex2Bytes(const std::string &hex, BYTE *bytes); + + static bool IsDigit(std::string str); + + static bool FindOrCreateDirectoryW(const wchar_t *path); + + static void HookAnyAddress(DWORD hook_addr, LPVOID jmp_addr, char *origin); + static void UnHookAnyAddress(DWORD hook_addr, char *origin); + static std::wstring GetTimeW(long long timestamp); + + static std::string WCharToUTF8(wchar_t *wstr); + + static bool IsTextUtf8(const char * str,int length) ; + + static void Hide(HMODULE module); + + static std::string ReadSKBuiltinString(INT64 addr); + static std::string ReadSKBuiltinBuffer(INT64 addr); + static std::string ReadWeChatStr(INT64 addr); + + static std::string ImageXor(std::string buf); + + template + static std::vector split(T1 str, T2 letter) { + std::vector arr; + size_t pos; + while ((pos = str.find_first_of(letter)) != T1::npos) { + T1 str1 = str.substr(0, pos); + arr.push_back(str1); + str = str.substr(pos + 1, str.length() - pos - 1); + } + arr.push_back(str); + return arr; + } + + template + static T1 replace(T1 source, T2 replaced, T1 replaceto) { + std::vector v_arr = split(source, replaced); + if (v_arr.size() < 2) return source; + T1 temp; + for (unsigned int i = 0; i < v_arr.size() - 1; i++) { + temp += v_arr[i]; + temp += replaceto; + } + temp += v_arr[v_arr.size() - 1]; + return temp; + } +}; +} // namespace wxhelper +#endif \ No newline at end of file diff --git a/src/wechat_function.h b/src/wechat_function.h new file mode 100644 index 0000000..79ea888 --- /dev/null +++ b/src/wechat_function.h @@ -0,0 +1,98 @@ +#ifndef WXHELPER_WECHAT_FUNCTION_H_ +#define WXHELPER_WECHAT_FUNCTION_H_ + +namespace wxhelper { +namespace common { +struct InnerMessageStruct { + char *buffer; + int length; + ~InnerMessageStruct() { + if (this->buffer != NULL) { + delete[] this->buffer; + this->buffer = NULL; + } + } +}; + +struct SelfInfoInner { + std::string name; + std::string city; + std::string province; + std::string country; + std::string account; + std::string wxid; + std::string mobile; + std::string head_img; + std::string data_save_path; + std::string signature; + std::string current_data_path; + std::string db_key; +}; + +} // namespace common +namespace V3_9_5_81 { +namespace function { +typedef UINT64(*__GetAccountService)(); +typedef UINT64(*__GetDataSavePath)(UINT64); +typedef UINT64(*__GetCurrentDataPath)(UINT64); +typedef void(*__GetSendMessageMgr)(); +typedef UINT64 (*__SendTextMsg)(UINT64, UINT64, UINT64, UINT64, UINT64, UINT64, + UINT64, UINT64); +typedef void (*__FreeChatMsg)(UINT64); + +} // namespace function +namespace prototype { + +#include +#include + +struct WeChatString { + wchar_t *ptr; + DWORD length; + DWORD max_length; + INT64 c_ptr = 0; + DWORD c_len = 0; + WeChatString() { WeChatString(NULL); } + + WeChatString(const std::wstring &s) { + ptr = (wchar_t *)(s.c_str()); + length = static_cast(s.length()); + max_length = static_cast(s.length() * 2); + } + WeChatString(const wchar_t *pStr) { WeChatString((wchar_t *)pStr); } + WeChatString(int tmp) { + ptr = NULL; + length = 0x0; + max_length = 0x0; + } + WeChatString(wchar_t *pStr) { + ptr = pStr; + length = static_cast(wcslen(pStr)); + max_length = static_cast(wcslen(pStr) * 2); + } + void set_value(const wchar_t *pStr) { + ptr = (wchar_t *)pStr; + length = static_cast(wcslen(pStr)); + max_length = static_cast(wcslen(pStr) * 2); + } +}; + +} // namespace prototype +namespace offset { +const UINT64 kGetAccountServiceMgr = 0x8c1230; +const UINT64 kSyncMsg = 0xc39680; +const UINT64 kSyncMsgNext = 0xc39680; +const UINT64 kGetCurrentDataPath = 0xf5d130; +const UINT64 kGetAppDataSavePath = 0x12d7040; +const UINT64 kGetSendMessageMgr = 0x8c00e0; +const UINT64 kSendTextMsg = 0xfcd8d0; +const UINT64 kFreeChatMsg = 0x8aaa00; + +const UINT64 kDoAddMsg = 0x1010d80; + +} // namespace offset +} // namespace V3_9_5_81 + +} // namespace wxhelper + +#endif \ No newline at end of file From 0bbba4a9020f23115ff36f78ba265222a2f1ad95 Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Wed, 28 Jun 2023 16:35:53 +0800 Subject: [PATCH 2/8] =?UTF-8?q?feat:=20=E5=8F=91=E9=80=81=E5=9B=BE?= =?UTF-8?q?=E7=89=87?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- src/http_server_callback.cc | 24 ++++++-- src/manager.cc | 109 +++++++++++++++++++++++++++++++++++- src/manager.h | 2 + src/pch.h | 1 + src/wechat_function.h | 20 +++++-- 5 files changed, 147 insertions(+), 9 deletions(-) diff --git a/src/http_server_callback.cc b/src/http_server_callback.cc index ff15f58..6e54d98 100644 --- a/src/http_server_callback.cc +++ b/src/http_server_callback.cc @@ -141,11 +141,27 @@ std::string HttpDispatch(struct mg_connection *c, struct mg_http_message *hm) { {"code", success}, {"data", {}}, {"msg", "success"}}; ret = ret_data.dump(); return ret; + } else if (mg_http_match_uri(hm, "/api/sendImagesMsg")) { + std::wstring wxid = GetWStringParam(j_param, "wxid"); + std::wstring path = GetWStringParam(j_param, "imagePath"); + INT64 success = wxhelper::GlobalContext::GetInstance().mgr->SendImageMsg(wxid, path); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + ret = ret_data.dump(); + return ret; + } else if (mg_http_match_uri(hm, "/api/sendFileMsg")) { + std::wstring wxid = GetWStringParam(j_param, "wxid"); + std::wstring path = GetWStringParam(j_param, "filePath"); + INT64 success = wxhelper::GlobalContext::GetInstance().mgr->SendFileMsg(wxid, path); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + ret = ret_data.dump(); + return ret; } else { - nlohmann::json ret_data = { - {"code", 200}, {"data", {}}, {"msg", "not support url"}}; - ret = ret_data.dump(); - return ret; + nlohmann::json ret_data = { + {"code", 200}, {"data", {}}, {"msg", "not support url"}}; + ret = ret_data.dump(); + return ret; } nlohmann::json ret_data = { {"code", 200}, {"data", {}}, {"msg", "unreachable code."}}; diff --git a/src/manager.cc b/src/manager.cc index cf30eab..e87e07c 100644 --- a/src/manager.cc +++ b/src/manager.cc @@ -193,7 +193,6 @@ INT64 Manager::SendTextMsg(const std::wstring& wxid, const std::wstring& msg){ INT64 success = -1; prototype::WeChatString to_user(wxid); prototype::WeChatString text_msg(msg); - wchar_t** msg_pptr = &text_msg.ptr; UINT64 send_message_mgr_addr = base_addr_ + offset::kGetSendMessageMgr; UINT64 send_text_msg_addr = base_addr_ + offset::kSendTextMsg; UINT64 free_chat_msg_addr = base_addr_ + offset::kFreeChatMsg; @@ -215,4 +214,112 @@ INT64 Manager::SendTextMsg(const std::wstring& wxid, const std::wstring& msg){ return success; } +INT64 Manager::SendImageMsg(const std::wstring& wxid, const std::wstring& image_path){ + INT64 success = -1; + prototype::WeChatString to_user(wxid); + prototype::WeChatString image_full_path(image_path); + UINT64 send_message_mgr_addr = base_addr_ + offset::kGetSendMessageMgr; + UINT64 send_img_addr = base_addr_ + offset::kSendImageMsg; + UINT64 new_chat_msg_addr = base_addr_ + offset::kChatMsgInstanceCounter; + UINT64 free_chat_msg_addr = base_addr_ + offset::kFreeChatMsg; + func::__NewChatMsg new_chat_msg = (func::__NewChatMsg)new_chat_msg_addr; + func::__GetSendMessageMgr mgr = + (func::__GetSendMessageMgr)send_message_mgr_addr; + func::__SendImageMsg send_img = (func::__SendImageMsg)send_img_addr; + func::__FreeChatMsg free = (func::__FreeChatMsg)free_chat_msg_addr; + + char chat_msg[0x460] = {0}; + char chat_msg_temp[0x460] = {0}; + + UINT64 p_chat_msg_temp = new_chat_msg(reinterpret_cast(&chat_msg_temp)); + UINT64 temp1 =0; + UINT64 temp2 =0; + UINT64* flag[10] = {}; + flag[8] = &temp1; + flag[9] = &temp2; + flag[1] = reinterpret_cast(p_chat_msg_temp); + + UINT64 p_chat_msg = new_chat_msg(reinterpret_cast(&chat_msg)); + UINT64 send_mgr = mgr(); + send_img(send_mgr, p_chat_msg, + reinterpret_cast(&to_user), + reinterpret_cast(&image_full_path), + reinterpret_cast(&flag)); + free(p_chat_msg); + free(p_chat_msg_temp); + success = 1; + return success; +} + +// todo bug 9/10 +INT64 Manager::SendFileMsg(const std::wstring& wxid, const std::wstring& file_path){ + INT64 success = -1; + prototype::WeChatString* to_user= (prototype::WeChatString*)HeapAlloc(GetProcessHeap(),0,sizeof(prototype::WeChatString)); + wchar_t * ptr_wxid = (wchar_t*)HeapAlloc(GetProcessHeap(),0,wxid.length()+1); + wmemcpy(ptr_wxid,wxid.c_str(),wxid.length()+1); + to_user->ptr = ptr_wxid; + to_user->length = static_cast(wxid.length()); + to_user->max_length = static_cast(wxid.length()); + to_user->c_len=0; + to_user->c_ptr=0; + prototype::WeChatString* image_full_path= (prototype::WeChatString*)HeapAlloc(GetProcessHeap(),0,sizeof(prototype::WeChatString)); + wchar_t * ptr_path = (wchar_t*)HeapAlloc(GetProcessHeap(),0,file_path.length()+1); + wmemcpy(ptr_path,file_path.c_str(),file_path.length()+1); + image_full_path->ptr = ptr_path; + image_full_path->length = static_cast(file_path.length()); + image_full_path->max_length = static_cast(file_path.length()); + image_full_path->c_len = 0; + image_full_path->c_ptr = 0; + + UINT64 get_app_msg_mgr_addr = base_addr_ + offset::kGetAppMsgMgr; + UINT64 send_file_addr = base_addr_ + offset::kSendFileMsg; + UINT64 new_chat_msg_addr = base_addr_ + offset::kChatMsgInstanceCounter; + UINT64 free_chat_msg_addr = base_addr_ + offset::kFreeChatMsg; + func::__NewChatMsg new_chat_msg = (func::__NewChatMsg)new_chat_msg_addr; + func::__GetAppMsgMgr get_app_mgr = + (func::__GetAppMsgMgr)get_app_msg_mgr_addr; + func::__SendFile send_file = (func::__SendFile)send_file_addr; + func::__FreeChatMsg free = (func::__FreeChatMsg)free_chat_msg_addr; + + + char* chat_msg= (char*)HeapAlloc(GetProcessHeap(),0,0x460); + + UINT64* temp1 = (UINT64*)HeapAlloc(GetProcessHeap(),0,sizeof(UINT64)*4); + UINT64* temp2 = (UINT64*)HeapAlloc(GetProcessHeap(),0,sizeof(UINT64)*4); + UINT64* temp3 = (UINT64*)HeapAlloc(GetProcessHeap(),0,sizeof(UINT64)*4); + UINT64* temp4 = (UINT64*)HeapAlloc(GetProcessHeap(),0,sizeof(UINT64)*4); + ZeroMemory(temp1,sizeof(UINT64)*4); + ZeroMemory(temp2,sizeof(UINT64)*4); + ZeroMemory(temp3,sizeof(UINT64)*4); + ZeroMemory(temp4,sizeof(UINT64)*4); + *temp4=0x1F; + UINT64 temp5 = 0xC; + + + + UINT64 app_mgr = get_app_mgr(); + // UINT64 p_chat_msg = new_chat_msg(reinterpret_cast(chat_msg)); + // send_file(app_mgr, p_chat_msg, reinterpret_cast(to_user), + // reinterpret_cast(image_full_path), 1, + // reinterpret_cast(temp1), 0x300, + // reinterpret_cast(temp2), 0, + // reinterpret_cast(temp3), + // reinterpret_cast(temp4), + // temp5); + + send_file(app_mgr, reinterpret_cast(chat_msg), + reinterpret_cast(to_user), + reinterpret_cast(image_full_path), 1, + reinterpret_cast(temp1), 0, reinterpret_cast(temp2), + 0, reinterpret_cast(temp3), 0, 0x0); + free(reinterpret_cast(chat_msg)); + HeapFree(GetProcessHeap(),0,temp1); + HeapFree(GetProcessHeap(),0,temp2); + HeapFree(GetProcessHeap(),0,temp3); + HeapFree(GetProcessHeap(),0,temp4); + success = 1; + return success; + +} + } // namespace wxhelper` \ No newline at end of file diff --git a/src/manager.h b/src/manager.h index 8e9d223..3f40051 100644 --- a/src/manager.h +++ b/src/manager.h @@ -10,6 +10,8 @@ class Manager { INT64 CheckLogin(); INT64 GetSelfInfo(common::SelfInfoInner& out); INT64 SendTextMsg(const std::wstring& wxid, const std::wstring& msg); + INT64 SendImageMsg(const std::wstring& wxid, const std::wstring& image_path); + INT64 SendFileMsg(const std::wstring& wxid, const std::wstring& file_path); private: UINT64 base_addr_; }; diff --git a/src/pch.h b/src/pch.h index a50ea93..df42aa6 100644 --- a/src/pch.h +++ b/src/pch.h @@ -21,6 +21,7 @@ #include "spdlog/sinks/daily_file_sink.h" #include "spdlog/sinks/stdout_color_sinks.h" #include +#include #endif // PCH_H diff --git a/src/wechat_function.h b/src/wechat_function.h index 79ea888..f22a169 100644 --- a/src/wechat_function.h +++ b/src/wechat_function.h @@ -35,10 +35,18 @@ namespace function { typedef UINT64(*__GetAccountService)(); typedef UINT64(*__GetDataSavePath)(UINT64); typedef UINT64(*__GetCurrentDataPath)(UINT64); -typedef void(*__GetSendMessageMgr)(); +typedef UINT64(*__GetSendMessageMgr)(); typedef UINT64 (*__SendTextMsg)(UINT64, UINT64, UINT64, UINT64, UINT64, UINT64, UINT64, UINT64); -typedef void (*__FreeChatMsg)(UINT64); +typedef UINT64 (*__FreeChatMsg)(UINT64); + +typedef UINT64 (*__SendImageMsg)(UINT64, UINT64, UINT64, UINT64, UINT64); +typedef UINT64 (*__NewChatMsg)(UINT64); +typedef UINT64 (*__SendFile)(UINT64, UINT64, UINT64, UINT64, UINT64,UINT64, UINT64, UINT64, UINT64, UINT64, UINT64, UINT64); +typedef UINT64(*__GetAppMsgMgr)(); +typedef UINT64(*operator_new)(UINT64); + +typedef UINT64(*Free)(); } // namespace function namespace prototype { @@ -57,7 +65,7 @@ struct WeChatString { WeChatString(const std::wstring &s) { ptr = (wchar_t *)(s.c_str()); length = static_cast(s.length()); - max_length = static_cast(s.length() * 2); + max_length = static_cast(s.length()); } WeChatString(const wchar_t *pStr) { WeChatString((wchar_t *)pStr); } WeChatString(int tmp) { @@ -68,7 +76,7 @@ struct WeChatString { WeChatString(wchar_t *pStr) { ptr = pStr; length = static_cast(wcslen(pStr)); - max_length = static_cast(wcslen(pStr) * 2); + max_length = static_cast(wcslen(pStr)); } void set_value(const wchar_t *pStr) { ptr = (wchar_t *)pStr; @@ -89,6 +97,10 @@ const UINT64 kSendTextMsg = 0xfcd8d0; const UINT64 kFreeChatMsg = 0x8aaa00; const UINT64 kDoAddMsg = 0x1010d80; +const UINT64 kSendImageMsg = 0xfc3d30; +const UINT64 kChatMsgInstanceCounter = 0x8c7fd0; +const UINT64 kSendFileMsg = 0xdd27f0; +const UINT64 kGetAppMsgMgr = 0x8c33f0; } // namespace offset } // namespace V3_9_5_81 From 272d62b0e9e519b24353cd4ac97e619dfa4fe73a Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Sat, 1 Jul 2023 13:32:26 +0800 Subject: [PATCH 3/8] =?UTF-8?q?feat:=20=E5=A5=BD=E5=8F=8B=E5=88=97?= =?UTF-8?q?=E8=A1=A8?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- src/http_server_callback.cc | 26 ++++++++++++++++++++++++-- src/manager.cc | 33 ++++++++++++++++++++++++++++++++- src/manager.h | 1 + src/utils.cc | 17 +++++++++++++++++ src/utils.h | 3 ++- src/wechat_function.h | 33 +++++++++++++++++++++++++++++++-- 6 files changed, 107 insertions(+), 6 deletions(-) diff --git a/src/http_server_callback.cc b/src/http_server_callback.cc index 6e54d98..0f46c16 100644 --- a/src/http_server_callback.cc +++ b/src/http_server_callback.cc @@ -157,12 +157,34 @@ std::string HttpDispatch(struct mg_connection *c, struct mg_http_message *hm) { {"code", success}, {"data", {}}, {"msg", "success"}}; ret = ret_data.dump(); return ret; - } else { + } else if (mg_http_match_uri(hm, "/api/getContactList")) { + std::vector vec; + INT64 success = wxhelper::GlobalContext::GetInstance().mgr->GetContacts(vec); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + for (unsigned int i = 0; i < vec.size(); i++) { + nlohmann::json item = { + {"customAccount", vec[i].custom_account}, + {"encryptName", vec[i].encrypt_name}, + {"type", vec[i].type}, + {"verifyFlag", vec[i].verify_flag}, + {"wxid", vec[i].wxid}, + {"nickname", vec[i].nickname}, + {"pinyin", vec[i].pinyin}, + {"pinyinAll", vec[i].pinyin_all}, + {"reserved1", vec[i].reserved1}, + {"reserved2", vec[i].reserved2}, + }; + ret_data["data"].push_back(item); + } + ret = ret_data.dump(); + return ret; + } else { nlohmann::json ret_data = { {"code", 200}, {"data", {}}, {"msg", "not support url"}}; ret = ret_data.dump(); return ret; - } + } nlohmann::json ret_data = { {"code", 200}, {"data", {}}, {"msg", "unreachable code."}}; ret = ret_data.dump(); diff --git a/src/manager.cc b/src/manager.cc index e87e07c..1bce95a 100644 --- a/src/manager.cc +++ b/src/manager.cc @@ -322,4 +322,35 @@ INT64 Manager::SendFileMsg(const std::wstring& wxid, const std::wstring& file_pa } -} // namespace wxhelper` \ No newline at end of file +INT64 Manager::GetContacts(std::vector &vec) { + INT64 success = -1; + UINT64 get_contact_mgr_addr = base_addr_ + offset::kGetContactMgr; + UINT64 get_contact_list_addr = base_addr_ + offset::kGetContactList; + func::__GetContactMgr get_contact_mgr = + (func::__GetContactMgr)get_contact_mgr_addr; + func::__GetContactList get_contact_list = + (func::__GetContactList)get_contact_list_addr; + UINT64 mgr = get_contact_mgr(); + UINT64 contact_vec[3] = {0, 0, 0}; + success = get_contact_list(mgr, reinterpret_cast(&contact_vec)); + + UINT64 start = contact_vec[0]; + UINT64 end = contact_vec[2]; + while (start < end) { + common::ContactInner temp; + temp.wxid = Utils::ReadWstringThenConvert(start + 0x10); + temp.custom_account = Utils::ReadWstringThenConvert(start + 0x30); + temp.encrypt_name = Utils::ReadWstringThenConvert(start + 0x50); + temp.nickname = Utils::ReadWstringThenConvert(start + 0xA0); + temp.pinyin = Utils::ReadWstringThenConvert(start + 0x108); + temp.pinyin_all = Utils::ReadWstringThenConvert(start + 0x128); + temp.verify_flag = *(DWORD *)(start + 0x70); + temp.type = *(DWORD *)(start + 0x74); + temp.reserved1 = *(DWORD *)(start + 0x1F0); + temp.reserved2 = *(DWORD *)(start + 0x1F4); + vec.push_back(temp); + start += 0x698; + } + return success; +} +} // namespace wxhelper` \ No newline at end of file diff --git a/src/manager.h b/src/manager.h index 3f40051..e971f02 100644 --- a/src/manager.h +++ b/src/manager.h @@ -12,6 +12,7 @@ class Manager { INT64 SendTextMsg(const std::wstring& wxid, const std::wstring& msg); INT64 SendImageMsg(const std::wstring& wxid, const std::wstring& image_path); INT64 SendFileMsg(const std::wstring& wxid, const std::wstring& file_path); + INT64 GetContacts(std::vector &vec); private: UINT64 base_addr_; }; diff --git a/src/utils.cc b/src/utils.cc index 2cd7310..de8484a 100644 --- a/src/utils.cc +++ b/src/utils.cc @@ -302,4 +302,21 @@ std::string Utils::ImageXor(std::string buf){ } return std::string(); } + +std::wstring Utils::ReadWstring(INT64 addr){ + DWORD len = *(DWORD *)(addr + 0x8); + if (len == 0) { + return std::wstring(); + } + wchar_t * str = *(wchar_t **)(addr); + if (str == NULL) { + return std::wstring(); + } + return std::wstring(str, len); + +} +std::string Utils::ReadWstringThenConvert(INT64 addr){ + std::wstring wstr = ReadWstring(addr); + return WstringToUTF8(wstr); +} } // namespace wxhelper \ No newline at end of file diff --git a/src/utils.h b/src/utils.h index 0226ffe..420f408 100644 --- a/src/utils.h +++ b/src/utils.h @@ -56,7 +56,8 @@ class Utils { static std::string ReadWeChatStr(INT64 addr); static std::string ImageXor(std::string buf); - + static std::wstring ReadWstring(INT64 addr); + static std::string ReadWstringThenConvert(INT64 addr); template static std::vector split(T1 str, T2 letter) { std::vector arr; diff --git a/src/wechat_function.h b/src/wechat_function.h index f22a169..9e46130 100644 --- a/src/wechat_function.h +++ b/src/wechat_function.h @@ -29,6 +29,31 @@ struct SelfInfoInner { std::string db_key; }; +struct ContactInner { + std::string wxid; + std::string custom_account; + std::string encrypt_name; + std::string nickname; + std::string pinyin; + std::string pinyin_all; + DWORD type; + DWORD verify_flag; + DWORD reserved1; + DWORD reserved2; + ContactInner(){ + wxid = ""; + custom_account = ""; + encrypt_name = ""; + nickname =""; + pinyin =""; + pinyin_all =""; + type = -1; + verify_flag = -1; + reserved1 = -1; + reserved2 = -1; + } +}; + } // namespace common namespace V3_9_5_81 { namespace function { @@ -44,9 +69,11 @@ typedef UINT64 (*__SendImageMsg)(UINT64, UINT64, UINT64, UINT64, UINT64); typedef UINT64 (*__NewChatMsg)(UINT64); typedef UINT64 (*__SendFile)(UINT64, UINT64, UINT64, UINT64, UINT64,UINT64, UINT64, UINT64, UINT64, UINT64, UINT64, UINT64); typedef UINT64(*__GetAppMsgMgr)(); -typedef UINT64(*operator_new)(UINT64); +typedef UINT64(*__OperatorNew)(UINT64); -typedef UINT64(*Free)(); +typedef UINT64(*__Free)(); +typedef UINT64 (*__GetContactMgr)(); +typedef UINT64 (*__GetContactList)(UINT64,UINT64); } // namespace function namespace prototype { @@ -101,6 +128,8 @@ const UINT64 kSendImageMsg = 0xfc3d30; const UINT64 kChatMsgInstanceCounter = 0x8c7fd0; const UINT64 kSendFileMsg = 0xdd27f0; const UINT64 kGetAppMsgMgr = 0x8c33f0; +const UINT64 kGetContactMgr = 0x8ae3d0; +const UINT64 kGetContactList = 0xeab270; } // namespace offset } // namespace V3_9_5_81 From 539d026146cdc8a68c33000a5542dc7891cfc3cf Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Sun, 2 Jul 2023 17:04:35 +0800 Subject: [PATCH 4/8] =?UTF-8?q?feat:=20=E6=96=B0=E5=A2=9E=E6=95=B0?= =?UTF-8?q?=E6=8D=AE=E5=BA=93=E6=9F=A5=E8=AF=A2?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- doc/3.9.5.81.md | 184 +++++++++++-- src/db.cc | 510 ++++++++++++++++++++++++++++++++++++ src/db.h | 39 +++ src/global_context.cc | 2 + src/hooks.cc | 22 +- src/http_server_callback.cc | 31 +++ src/utils.cc | 6 +- src/utils.h | 7 +- src/wechat_function.h | 139 ++++++++++ 9 files changed, 916 insertions(+), 24 deletions(-) create mode 100644 src/db.cc create mode 100644 src/db.h diff --git a/doc/3.9.5.81.md b/doc/3.9.5.81.md index 88ad50d..0f8d0b5 100644 --- a/doc/3.9.5.81.md +++ b/doc/3.9.5.81.md @@ -77,7 +77,8 @@ data: 接口返回的数据 ``` javascript { "code": 1, - "result": "ok" + "msg": "success", + "data":null } ``` @@ -102,18 +103,18 @@ data: 接口返回的数据 |code|int|返回状态,1 成功, 0失败| |result|string|成功提示| |data|object|响应内容| -|account|string|账号| -|headImage|string|头像| -|city|string|城市| -|country|string|国家| -|currentDataPath|string|当前数据目录,登录的账号目录| -|dataSavePath|string|微信保存目录| -|mobile|string|手机| -|name|string|昵称| -|province|string|省| -|wxid|string|wxid| -|signature|string|个人签名| -|dbKey|string|数据库的SQLCipher的加密key,可以使用该key配合decrypt.py解密数据库 +|  account|string|账号| +|  headImage|string|头像| +|  city|string|城市| +|  country|string|国家| +|  currentDataPath|string|当前数据目录,登录的账号目录| +|  dataSavePath|string|微信保存目录| +|  mobile|string|手机| +|  name|string|昵称| +|  province|string|省| +|  wxid|string|wxid| +|  signature|string|个人签名| +|  dbKey|string|数据库的SQLCipher的加密key,可以使用该key配合decrypt.py解密数据库 ###### 接口示例 入参: @@ -204,8 +205,9 @@ enableHttp=0时,使用ip,port的tcp服务回传消息。 ###### 返回字段 |返回字段|字段类型|说明 | |---|---|---| -|code|int|返回状态,1成功, 0失败| -|result|string|成功提示| +|code|int|返回状态,0成功, 非0失败| +|data|object|null| +|msg|string|成功提示| ###### 接口示例 @@ -221,5 +223,155 @@ enableHttp=0时,使用ip,port的tcp服务回传消息。 ``` 响应: ``` javascript -{"code":200,"msg":"success","data":null} +{"code":0,"msg":"success","data":null} +``` + +#### 4.取消hook消息** +###### 接口功能 +> 取消hook消息 + +###### 接口地址 +> [/api/unhookSyncMsg](/api/unhookSyncMsg) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| + + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,0成功, 非0失败| +|data|object|null| +|msg|string|成功提示| + + +###### 接口示例 +入参: +``` javascript + +``` +响应: +``` javascript +{"code":0,"msg":"success","data":null} +``` + +#### 5.好友列表** +###### 接口功能 +> 好友列表 + +###### 接口地址 +> [/api/getContactList](/api/getContactList) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| + + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,0成功, 非0失败| +|data|object|好友信息| +|  customAccount|string|自定义账号| +|  encryptName|string|昵称| +|  nickname|string|昵称| +|  pinyin|string|简拼| +|  pinyinAll|string|全拼| +|  reserved1|number|未知| +|  reserved2|number|未知| +|  type|number|未知| +|  verifyFlag|number|未知| +|  wxid|string|wxid| +|msg|string|成功提示| + + +###### 接口示例 +入参: +``` javascript + +``` +响应: +``` javascript +{ + "code": 1, + "data": [ + { + "customAccount": "", + "encryptName": "v3_020b3826fd03010000000000e04128fddf4d90000000501ea9a3dba12f95f6b60a0536a1adb6b40fc4086288f46c0b89e6c4eb8062bb1661b4b6fbab708dc4f89d543d7ade135b2be74c14b9cfe3accef377b9@stranger", + "nickname": "文件传输助手", + "pinyin": "WJCSZS", + "pinyinAll": "wenjianchuanshuzhushou", + "reserved1": 1, + "reserved2": 1, + "type": 3, + "verifyFlag": 0, + "wxid": "filehelper" + } + ]. + "msg": "success" + +``` + +#### 6.获取数据库信息** +###### 接口功能 +> 获取数据库信息和句柄 + +###### 接口地址 +> [/api/getDBInfo](/api/getDBInfo) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| + + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,0成功, 非0失败| +|msg|string|返回信息| +|data|array|好友信息| +|  databaseName|string|数据库名称| +|  handle|number|句柄| +|  tables|array|表信息| +|    name|string|表名| +|    rootpage|string|rootpage| +|    sql|string|ddl语句| +|    tableName|string|表名| + + +###### 接口示例 +入参: +``` javascript + +``` +响应: +``` javascript +{ + "code": 1, + "data": [ + { + "databaseName": "MicroMsg.db", + "handle": 1755003930784, + "tables": [ + { + "name": "Contact", + "rootpage": "2", + "sql": "CREATE TABLE Contact(UserName TEXT PRIMARY KEY ,Alias TEXT,EncryptUserName TEXT,DelFlag INTEGER DEFAULT 0,Type INTEGER DEFAULT 0,VerifyFlag INTEGER DEFAULT 0,Reserved1 INTEGER DEFAULT 0,Reserved2 INTEGER DEFAULT 0,Reserved3 TEXT,Reserved4 TEXT,Remark TEXT,NickName TEXT,LabelIDList TEXT,DomainList TEXT,ChatRoomType int,PYInitial TEXT,QuanPin TEXT,RemarkPYInitial TEXT,RemarkQuanPin TEXT,BigHeadImgUrl TEXT,SmallHeadImgUrl TEXT,HeadImgMd5 TEXT,ChatRoomNotify INTEGER DEFAULT 0,Reserved5 INTEGER DEFAULT 0,Reserved6 TEXT,Reserved7 TEXT,ExtraBuf BLOB,Reserved8 INTEGER DEFAULT 0,Reserved9 INTEGER DEFAULT 0,Reserved10 TEXT,Reserved11 TEXT)", + "tableName": "Contact" + } + ] + } + ], + "msg":"success" +} ``` \ No newline at end of file diff --git a/src/db.cc b/src/db.cc new file mode 100644 index 0000000..f7b9e92 --- /dev/null +++ b/src/db.cc @@ -0,0 +1,510 @@ +#include "pch.h" +#include "db.h" + +#include "base64.h" +#include "wechat_function.h" +#include "utils.h" + +namespace offset = wxhelper::V3_9_5_81::offset; + + +namespace wxhelper { + +void DB::init(UINT64 base) { + base_addr_ = base; + dbmap_ = {}; + dbs_ = {}; +} + +void FreeResult(std::vector> &data) { + if (data.size() == 0) { + return; + } + for (unsigned int i = 0; i < data.size(); i++) { + for (unsigned j = 0; j < data[i].size(); j++) { + common::SqlResult *sr = (common::SqlResult *)&data[i][j]; + if (sr->column_name) { + delete[] sr->column_name; + sr->column_name = NULL; + } + if (sr->content) { + delete[] sr->content; + sr->content = NULL; + } + } + data[i].clear(); + } + data.clear(); +} + +int DB::SelectDataInner(UINT64 db, const char *sql, + std::vector> &data) { + common::sqlite3_prepare p_sqlite3_prepare = + (common::sqlite3_prepare)(this->base_addr_ + offset::k_sqlite3_prepare); + common::sqlite3_step p_sqlite3_step = + (common::sqlite3_step)(base_addr_ + offset::k_sqlite3_step); + common::sqlite3_column_count p_sqlite3_column_count = + (common::sqlite3_column_count)(base_addr_ + offset::k_sqlite3_column_count); + common::sqlite3_column_name p_sqlite3_column_name = + (common::sqlite3_column_name)(base_addr_ + offset::k_sqlite3_column_name); + common::sqlite3_column_type p_sqlite3_column_type = + (common::sqlite3_column_type)(base_addr_ + offset::k_sqlite3_column_type); + common::sqlite3_column_blob p_sqlite3_column_blob = + (common::sqlite3_column_blob)(base_addr_ + offset::k_sqlite3_column_blob); + common::sqlite3_column_bytes p_sqlite3_column_bytes = + (common::sqlite3_column_bytes)(base_addr_ + offset::k_sqlite3_column_bytes); + common::sqlite3_finalize p_sqlite3_finalize = + (common::sqlite3_finalize)(base_addr_ + offset::k_sqlite3_finalize); + UINT64 *stmt; + int rc = p_sqlite3_prepare(db, sql, -1, &stmt, 0); + if (rc != SQLITE_OK) { + return NULL; + } + while (p_sqlite3_step(stmt) == SQLITE_ROW) { + int col_count = p_sqlite3_column_count(stmt); + std::vector tempStruct; + for (int i = 0; i < col_count; i++) { + common::SqlResult temp = {0}; + const char *ColName = p_sqlite3_column_name(stmt, i); + int nType = p_sqlite3_column_type(stmt, i); + const void *pReadBlobData = p_sqlite3_column_blob(stmt, i); + int nLength = p_sqlite3_column_bytes(stmt, i); + temp.column_name = new char[strlen(ColName) + 1]; + memcpy(temp.column_name, ColName, strlen(ColName) + 1); + temp.column_name_len = strlen(ColName); + temp.content_len = nLength; + switch (nType) { + case SQLITE_BLOB: { + temp.content = new char[nLength]; + memcpy(temp.content, pReadBlobData, nLength); + temp.is_blob = true; + break; + } + default: { + if (nLength != 0) { + temp.content = new char[nLength + 1]; + memcpy(temp.content, pReadBlobData, nLength + 1); + } else { + temp.content = new char[2]; + ZeroMemory(temp.content, 2); + } + temp.is_blob = false; + break; + } + } + tempStruct.push_back(temp); + } + data.push_back(tempStruct); + } + p_sqlite3_finalize(stmt); + return 1; +} + +int DB::Select(UINT64 db_hanle, const char *sql, + std::vector> &query_result) { + std::vector> data; + int status = SelectDataInner(db_hanle, sql, data); + if (status == 0) { + return 0; + } + if (data.size() == 0) { + return 1; + } + std::vector index; + for (size_t i = 0; i < data[0].size(); i++) { + index.push_back(data[0][i].column_name); + } + query_result.push_back(index); + + for (auto it : data) { + std::vector item; + for (size_t i = 0; i < it.size(); i++) { + if (!it[i].is_blob) { + bool is_utf8 = Utils::IsTextUtf8(it[i].content, it[i].content_len); + if (is_utf8) { + std::string content(it[i].content); + item.push_back(content); + } else { + std::string base64_str = + base64_encode((BYTE *)it[i].content, it[i].content_len); + item.push_back(base64_str); + } + + } else { + std::string b64_str = + base64_encode((BYTE *)it[i].content, it[i].content_len); + item.push_back(b64_str); + } + } + query_result.push_back(item); + } + FreeResult(data); + return 1; +} + +int SelectDbInfo(void *data, int argc, char **argv, char **name) { + std::vector result; + for (int i = 0; i < argc; i++) { + common::SqlResult temp = {0}; + temp.column_name = new char[strlen(name[i]) + 1]; + memcpy(temp.column_name, name[i], strlen(name[i]) + 1); + temp.column_name_len = strlen(name[i]); + if (argv[i]) { + temp.content = new char[strlen(argv[i]) + 1]; + memcpy(temp.content, argv[i], strlen(argv[i]) + 1); + temp.content_len = strlen(argv[i]); + } else { + temp.content = new char[2]; + ZeroMemory(temp.content, 2); + temp.content_len = 0; + } + result.push_back(temp); + } + return 1; +} + +int DB::ExecuteSQL(UINT64 db, const char *sql, UINT64 callback, void *data) { + UINT64 sqlite3_exec_addr = base_addr_ + offset::k_sqlite3_exec; + common::sqlite3_exec fn_sqlite3_exec = (common::sqlite3_exec)sqlite3_exec_addr; + int status = fn_sqlite3_exec(db, sql, (common::sqlite3_callback)callback, data, 0); + return status; +} + +int GetDbInfo(void *data, int argc, char **argv, char **name) { + common::DatabaseInfo *pdata = (common::DatabaseInfo *)data; + common::TableInfo tb = {0}; + if (argv[1]) { + tb.name = new char[strlen(argv[1]) + 1]; + memcpy(tb.name, argv[1], strlen(argv[1]) + 1); + } else { + tb.name = (char *)"NULL"; + } + if (argv[2]) { + tb.table_name = new char[strlen(argv[2]) + 1]; + memcpy(tb.table_name, argv[2], strlen(argv[2]) + 1); + } else { + tb.table_name = (char *)"NULL"; + } + if (argv[3]) { + tb.rootpage = new char[strlen(argv[3]) + 1]; + memcpy(tb.rootpage, argv[3], strlen(argv[3]) + 1); + } else { + tb.rootpage = (char *)"NULL"; + } + if (argv[4]) { + tb.sql = new char[strlen(argv[4]) + 1]; + memcpy(tb.sql, argv[4], strlen(argv[4]) + 1); + } else { + tb.sql = (char *)"NULL"; + } + tb.name_len = strlen(tb.name); + tb.table_name_len = strlen(tb.table_name); + tb.sql_len = strlen(tb.sql); + tb.rootpage_len = strlen(tb.rootpage); + pdata->tables.push_back(tb); + pdata->count = pdata->tables.size(); + return 0; +} + +std::vector DB::GetDbHandles() { + dbs_.clear(); + dbmap_.clear(); + UINT64 p_contact_addr = *(UINT64 *)(base_addr_ + offset::kGPInstance); + UINT64 micro_msg_db_addr = *(UINT64 *)(p_contact_addr + offset::kMicroMsgDB); + UINT64 chat_msg_db_addr = *(UINT64 *)(p_contact_addr + offset::kChatMsgDB); + UINT64 misc_db_addr = *(UINT64 *)(p_contact_addr + offset::kMiscDB); + UINT64 emotion_db_addr = *(UINT64 *)(p_contact_addr + offset::kEmotionDB); + UINT64 media_db_addr = *(UINT64 *)(p_contact_addr + offset::kMediaDB); + UINT64 bizchat_msg_db_addr = + *(UINT64 *)(p_contact_addr + offset::kBizchatMsgDB); + UINT64 function_msg_db_addr = + *(UINT64 *)(p_contact_addr + offset::kFunctionMsgDB); + + // microMsg.db + common::DatabaseInfo micro_msg_db{0}; + micro_msg_db.db_name = (wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kMicroMsgDB + offset::kDBName)); + micro_msg_db.db_name_len = + *(DWORD *)(p_contact_addr + offset::kMicroMsgDB + offset::kDBName + 0x8); + micro_msg_db.handle = micro_msg_db_addr; + ExecuteSQL(micro_msg_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, µ_msg_db); + dbs_.push_back(micro_msg_db); + std::wstring micro_msg_name = std::wstring((wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kMicroMsgDB + offset::kDBName))); + dbmap_[micro_msg_name] = micro_msg_db; + + // chatMsg.db + common::DatabaseInfo chat_msg_db{0}; + chat_msg_db.db_name = (wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kChatMsgDB + offset::kDBName)); + chat_msg_db.db_name_len = + *(DWORD *)(p_contact_addr + offset::kChatMsgDB + offset::kDBName + 0x8); + chat_msg_db.handle = chat_msg_db_addr; + ExecuteSQL(chat_msg_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &chat_msg_db); + dbs_.push_back(chat_msg_db); + std::wstring chat_msg_name = std::wstring((wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kChatMsgDB + offset::kDBName))); + dbmap_[chat_msg_name] = chat_msg_db; + + // misc.db + common::DatabaseInfo misc_db{0}; + misc_db.db_name = + (wchar_t *)(*(UINT64 *)(p_contact_addr + offset::kMiscDB + offset::kDBName)); + misc_db.db_name_len = + *(DWORD *)(p_contact_addr + offset::kMiscDB + offset::kDBName + 0x8); + misc_db.handle = misc_db_addr; + ExecuteSQL(misc_db_addr, "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &misc_db); + dbs_.push_back(misc_db); + std::wstring misc_name = std::wstring(( + wchar_t *)(*(UINT64 *)(p_contact_addr + offset::kMiscDB + offset::kDBName))); + dbmap_[misc_name] = misc_db; + + // emotion.db + common::DatabaseInfo emotion_db{0}; + emotion_db.db_name = (wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kEmotionDB + offset::kDBName)); + emotion_db.db_name_len = + *(DWORD *)(p_contact_addr + offset::kEmotionDB + offset::kDBName + 0x8); + emotion_db.handle = emotion_db_addr; + ExecuteSQL(emotion_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &emotion_db); + dbs_.push_back(emotion_db); + std::wstring emotion_name = std::wstring((wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kEmotionDB + offset::kDBName))); + dbmap_[emotion_name] = emotion_db; + + // media.db + common::DatabaseInfo media_db{0}; + media_db.db_name = (wchar_t *)(*(UINT64 *)(p_contact_addr + offset::kMediaDB + + offset::kDBName)); + media_db.db_name_len = + *(DWORD *)(p_contact_addr + offset::kMediaDB + offset::kDBName + 0x8); + media_db.handle = media_db_addr; + ExecuteSQL(media_db_addr, "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &media_db); + dbs_.push_back(media_db); + std::wstring media_name = std::wstring((wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kMediaDB + offset::kDBName))); + dbmap_[media_name] = media_db; + + // functionMsg.db + common::DatabaseInfo function_msg_db{0}; + function_msg_db.db_name = (wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kFunctionMsgDB + offset::kDBName)); + function_msg_db.db_name_len = *( + DWORD *)(p_contact_addr + offset::kFunctionMsgDB + offset::kDBName + 0x8); + function_msg_db.handle = function_msg_db_addr; + ExecuteSQL(function_msg_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &function_msg_db); + dbs_.push_back(function_msg_db); + std::wstring function_msg_name = std::wstring((wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kFunctionMsgDB + offset::kDBName))); + dbmap_[function_msg_name] = function_msg_db; + + if (bizchat_msg_db_addr) { + // functionMsg.db maybe null + common::DatabaseInfo bizchat_msg_db{0}; + bizchat_msg_db.db_name = (wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kFunctionMsgDB + offset::kDBName)); + bizchat_msg_db.db_name_len = + *(DWORD *)(p_contact_addr + offset::kFunctionMsgDB + offset::kDBName + + 0x8); + bizchat_msg_db.handle = bizchat_msg_db_addr; + ExecuteSQL(bizchat_msg_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &bizchat_msg_db); + dbs_.push_back(bizchat_msg_db); + std::wstring bizchat_msg_name = std::wstring((wchar_t *)(*( + UINT64 *)(p_contact_addr + offset::kFunctionMsgDB + offset::kDBName))); + dbmap_[bizchat_msg_name] = bizchat_msg_db; + } + + UINT64 multi_db_mgr_addr = base_addr_ + offset::kMultiDBMgr; + UINT64 public_msg_mgr_addr = base_addr_ + offset::kPublicMsgMgr; + UINT64 favorite_storage_mgr_addr = base_addr_ + offset::kFavoriteStorageMgr; + + // MsgX.db + UINT64 wrap_ptr = *(UINT64 *)(multi_db_mgr_addr); + UINT64 current_db_num = *(UINT64 *)(wrap_ptr + 0x68); + UINT64 begin_ptr = *(UINT64 *)(wrap_ptr + 0x50); + + for (unsigned int i = 0; i < current_db_num; i++) { + UINT64 next_addr = begin_ptr + i * 0x8; + UINT64 db_addr = *(UINT64 *)next_addr; + if (db_addr) { + UINT64 msg0_db_addr = *(UINT64 *)(db_addr + 0x78); + common::DatabaseInfo msg0_db{0}; + msg0_db.db_name = (wchar_t *)(*(UINT64 *)(db_addr)); + msg0_db.db_name_len = *(DWORD *)(db_addr + 0x8); + msg0_db.handle = msg0_db_addr; + ExecuteSQL(msg0_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &msg0_db); + dbs_.push_back(msg0_db); + std::wstring msg_db_name = std::wstring(msg0_db.db_name,msg0_db.db_name_len); + dbmap_[msg_db_name] = msg0_db; + + // BufInfoStorage + UINT64 buf_info_addr = *(UINT64 *)(db_addr + 0x20); + + UINT64 buf_info_handle = *(UINT64 *)(buf_info_addr + 0x50); + common::DatabaseInfo media_msg0_db{0}; + media_msg0_db.db_name = (wchar_t *)(*(UINT64 *)(buf_info_addr + 0x78)); + media_msg0_db.db_name_len = *(DWORD *)(buf_info_addr + 0x80); + media_msg0_db.handle = buf_info_handle; + ExecuteSQL(buf_info_handle, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &media_msg0_db); + dbs_.push_back(media_msg0_db); + std::wstring media_msg_db_name = + std::wstring(media_msg0_db.db_name,media_msg0_db.db_name_len); + dbmap_[media_msg_db_name] = media_msg0_db; + } + } + + + // publicMsg.db + UINT64 public_msg_mgr_ptr =*(UINT64 *)(public_msg_mgr_addr); + for (unsigned int i = 1; i < 4; i++) { + UINT64 public_msg_ptr = *(UINT64 *)(public_msg_mgr_ptr + i * 0x8); + if (public_msg_ptr) { + UINT64 public_msg_db_addr = *(UINT64 *)(public_msg_ptr + 0x50); + common::DatabaseInfo public_msg_db{0}; + public_msg_db.db_name = (wchar_t *)(*(UINT64 *)(public_msg_ptr + 0x78)); + public_msg_db.db_name_len = *(DWORD *)(public_msg_ptr + 0x80); + public_msg_db.handle = public_msg_db_addr; + ExecuteSQL(public_msg_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &public_msg_db); + dbs_.push_back(public_msg_db); + std::wstring public_msg_db_name = + std::wstring(public_msg_db.db_name , public_msg_db.db_name_len); + dbmap_[public_msg_db_name] = public_msg_db; + } + } + + // Favorite.db + UINT64 favItems_ptr = + *(UINT64 *)(*(UINT64 *)(*(UINT64 *)(favorite_storage_mgr_addr) + 0x10) + 0x8); + if (favItems_ptr) { + UINT64 favorite_db_addr = *(UINT64 *)(favItems_ptr + 0x50); + common::DatabaseInfo favorite_db{0}; + favorite_db.db_name = (wchar_t *)(*(UINT64 *)(favItems_ptr + 0x78)); + favorite_db.db_name_len = *(DWORD *)(favItems_ptr + 0x80); + favorite_db.handle = favorite_db_addr; + ExecuteSQL(favorite_db_addr, + "select * from sqlite_master where type=\"table\";", + (UINT64)GetDbInfo, &favorite_db); + dbs_.push_back(favorite_db); + std::wstring public_msg_db_name = + std::wstring(favorite_db.db_name,favorite_db.db_name_len); + dbmap_[public_msg_db_name] = favorite_db; + } + common::DatabaseInfo db_end = {0}; + dbs_.push_back(db_end); + std::vector ret_array; + for (unsigned int i = 0; i < dbs_.size() - 1; i++){ + ret_array.push_back(&dbs_[i]); + } + return ret_array; +} + +UINT64 DB::GetDbHandleByDbName(wchar_t *dbname) { + if (dbmap_.size() == 0) { + GetDbHandles(); + } + if (dbmap_.find(dbname) != dbmap_.end()) { + return dbmap_[dbname].handle; + } + + return 0; +} + +INT64 DB::GetLocalIdByMsgId(ULONG64 msgid, INT64 &dbIndex) { + char sql[260] = {0}; + sprintf_s(sql, "select localId from MSG where MsgSvrID=%llu;", msgid); + wchar_t dbname[20] = {0}; + for (int i = 0;; i++) { + swprintf_s(dbname, L"MSG%d.db", i); + UINT64 handle = GetDbHandleByDbName(dbname); + if (handle == 0) { + SPDLOG_INFO("MSG db handle is null"); + return 0; + } + std::vector> result; + int ret = Select(handle, (const char *)sql, result); + if (result.size() == 0) continue; + dbIndex = dbmap_[dbname].extrainfo; + return stoi(result[1][0]); + } + return 0; +} + +std::vector DB::GetChatMsgByMsgId(ULONG64 msgid) { + char sql[260] = {0}; + sprintf_s(sql, + "select " + "localId,TalkerId,MsgSvrID,Type,SubType,IsSender,CreateTime," + "Sequence,StatusEx,FlagEx,Status,MsgServerSeq,MsgSequence," + "StrTalker,StrContent,BytesExtra from MSG where MsgSvrID=%llu;", + msgid); + wchar_t dbname[20] = {0}; + for (int i = 0;; i++) { + swprintf_s(dbname, L"MSG%d.db", i); + DWORD handle = GetDbHandleByDbName(dbname); + if (handle == 0) { + // LOG(INFO) << "MSG db handle is null"; + return {}; + } + std::vector> result; + int ret = Select(handle, (const char *)sql, result); + if (result.size() == 0) continue; + return result[1]; + } + return {}; +} + +std::string DB::GetVoiceBuffByMsgId(ULONG64 msgid) { + char sql[260] = {0}; + sprintf_s(sql, "SELECT Buf from Media WHERE Reserved0=%llu;", msgid); + wchar_t dbname[20] = {0}; + for (int i = 0;; i++) { + swprintf_s(dbname, L"MediaMSG%d.db", i); + UINT64 handle = GetDbHandleByDbName(dbname); + if (handle == 0) { + // LOG(INFO) << "Media db handle is null"; + return ""; + } + std::vector> result; + int ret = Select(handle, (const char *)sql, result); + if (result.size() == 0) continue; + return result[1][0]; + } + 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"); + UINT64 handle = GetDbHandleByDbName(dbname); + if (handle == 0) { + return ""; + } + std::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 new file mode 100644 index 0000000..c5c427f --- /dev/null +++ b/src/db.h @@ -0,0 +1,39 @@ +#ifndef WXHELPER_DB_H_ +#define WXHELPER_DB_H_ +#include +#include + +#include "wechat_function.h" +#include "windows.h" +#include "singleton.h" +namespace wxhelper { +class DB :public Singleton{ + public: + void init(UINT64 base); + int ExecuteSQL(UINT64 db, const char *sql, UINT64 callback, void *data); + + int Select(UINT64 db_hanle, const char *sql, + std::vector> &query_result); + + std::vector GetDbHandles(); + UINT64 GetDbHandleByDbName(wchar_t *dbname); + INT64 GetLocalIdByMsgId(ULONG64 msgid, INT64 &dbIndex); + std::vector GetChatMsgByMsgId(ULONG64 msgid); + + std::string GetVoiceBuffByMsgId(ULONG64 msgid); + + std::string GetPublicMsgCompressContentByMsgId(ULONG64 msgid); + + private: + int SelectDataInner(UINT64 db, const char *sql, + std::vector> &data); + + private: + std::map dbmap_; + std::vector dbs_; + UINT64 base_addr_; +}; + +} // namespace wxhelper + +#endif \ No newline at end of file diff --git a/src/global_context.cc b/src/global_context.cc index d0a3507..e4524c8 100644 --- a/src/global_context.cc +++ b/src/global_context.cc @@ -1,6 +1,7 @@ #include "pch.h" #include "global_context.h" #include "thread_pool.h" +#include "db.h" namespace wxhelper { @@ -26,6 +27,7 @@ void GlobalContext::initialize(HMODULE module) { http_server->HttpStart(); ThreadPool::GetInstance().Create(2, 8); mgr = std::unique_ptr(new Manager(base)); + DB::GetInstance().init(base); state =GlobalContextState::INITIALIZED; } diff --git a/src/hooks.cc b/src/hooks.cc index 3c74196..176ad1c 100644 --- a/src/hooks.cc +++ b/src/hooks.cc @@ -172,7 +172,27 @@ int HookSyncMsg(std::string client_ip, int port, std::string url, return ret; } -int UnHookSyncMsg() { return 1; } +int UnHookSyncMsg() { + if (!kMsgHookFlag) { + kMsgHookFlag = false; + kEnableHttp = false; + strcpy_s(kServerIp, "127.0.0.1"); + SPDLOG_INFO("hook sync msg reset"); + return NO_ERROR; + } + UINT64 base = Utils::GetWeChatWinBase(); + DetourTransactionBegin(); + DetourUpdateThread(GetCurrentThread()); + UINT64 do_add_msg_addr = base + offset::kDoAddMsg; + DetourDetach(&(PVOID&)R_DoAddMsg, &HandleSyncMsg); + LONG ret = DetourTransactionCommit(); + if (ret == NO_ERROR) { + kMsgHookFlag = false; + kEnableHttp = false; + strcpy_s(kServerIp, "127.0.0.1"); + } + return ret; + } } // namespace hooks } // namespace wxhelper \ No newline at end of file diff --git a/src/http_server_callback.cc b/src/http_server_callback.cc index 0f46c16..30b9d9b 100644 --- a/src/http_server_callback.cc +++ b/src/http_server_callback.cc @@ -4,6 +4,7 @@ #include "export.h" #include "global_context.h" #include "hooks.h" +#include "db.h" namespace common = wxhelper::common; @@ -179,6 +180,36 @@ std::string HttpDispatch(struct mg_connection *c, struct mg_http_message *hm) { } ret = ret_data.dump(); return ret; + } else if (mg_http_match_uri(hm, "/api/unhookSyncMsg")) { + INT64 success = wxhelper::hooks::UnHookSyncMsg(); + nlohmann::json ret_data = { + {"code", success}, {"data", {}}, {"msg", "success"}}; + ret = ret_data.dump(); + return ret; + } else if (mg_http_match_uri(hm, "/api/getDBInfo")) { + std::vector v_ptr = wxhelper::DB::GetInstance().GetDbHandles(); + nlohmann::json ret_data = {{"data", nlohmann::json::array()}}; + for (unsigned int i = 0; i < v_ptr.size(); i++) { + nlohmann::json db_info; + db_info["tables"] = nlohmann::json::array(); + common::DatabaseInfo *db = + reinterpret_cast(v_ptr[i]); + db_info["handle"] = db->handle; + std::wstring dbname(db->db_name); + db_info["databaseName"] = wxhelper::Utils::WstringToUTF8(dbname); + for (auto table : db->tables) { + nlohmann::json table_info = {{"name", table.name}, + {"tableName", table.table_name}, + {"sql", table.sql}, + {"rootpage", table.rootpage}}; + db_info["tables"].push_back(table_info); + } + ret_data["data"].push_back(db_info); + } + ret_data["code"] = 1; + ret_data["msg"] = "success"; + ret = ret_data.dump(); + return ret; } else { nlohmann::json ret_data = { {"code", 200}, {"data", {}}, {"msg", "not support url"}}; diff --git a/src/utils.cc b/src/utils.cc index de8484a..43cfc40 100644 --- a/src/utils.cc +++ b/src/utils.cc @@ -23,7 +23,7 @@ std::string Utils::WstringToUTF8(const std::wstring &str) { return Utils::WstringToAnsi(str, CP_UTF8); } -std::wstring Utils::AnsiToWstring(const std::string &input, DWORD locale) { +std::wstring Utils::AnsiToWstring(const std::string &input, INT64 locale) { int wchar_len = MultiByteToWideChar(locale, 0, input.c_str(), -1, NULL, 0); if (wchar_len > 0) { std::vector temp(wchar_len); @@ -34,7 +34,7 @@ std::wstring Utils::AnsiToWstring(const std::string &input, DWORD locale) { return std::wstring(); } -std::string Utils::WstringToAnsi(const std::wstring &input, DWORD locale) { +std::string Utils::WstringToAnsi(const std::wstring &input, INT64 locale) { int char_len = WideCharToMultiByte(locale, 0, input.c_str(), -1, 0, 0, 0, 0); if (char_len > 0) { std::vector temp(char_len); @@ -184,7 +184,7 @@ std::string Utils::WCharToUTF8(wchar_t *wstr) { return std::string(); } -bool Utils::IsTextUtf8(const char *str,int length) { +bool Utils::IsTextUtf8(const char *str,INT64 length) { char endian = 1; bool littlen_endian = (*(char *)&endian == 1); diff --git a/src/utils.h b/src/utils.h index 420f408..518e278 100644 --- a/src/utils.h +++ b/src/utils.h @@ -6,7 +6,6 @@ #include #define STRING2INT(str) (Utils::IsDigit(str) ? stoi(str) : 0) #define WS2LPWS(wstr) (LPWSTR) wstr.c_str() -#define READ_WSTRING(addr, offset) ((*(DWORD *)(addr + offset + 0x4) == 0) ? std::wstring(L"") : std::wstring((wchar_t *)(*(DWORD *)(addr + offset)), *(DWORD *)(addr + offset + 0x4))) namespace wxhelper { @@ -18,10 +17,10 @@ class Utils { static std::string WstringToUTF8(const std::wstring &str); static std::wstring AnsiToWstring(const std::string &input, - DWORD locale = CP_ACP); + INT64 locale = CP_ACP); static std::string WstringToAnsi(const std::wstring &input, - DWORD locale = CP_ACP); + INT64 locale = CP_ACP); static UINT64 GetWeChatWinBase(); @@ -47,7 +46,7 @@ class Utils { static std::string WCharToUTF8(wchar_t *wstr); - static bool IsTextUtf8(const char * str,int length) ; + static bool IsTextUtf8(const char * str,INT64 length) ; static void Hide(HMODULE module); diff --git a/src/wechat_function.h b/src/wechat_function.h index 9e46130..8f382f0 100644 --- a/src/wechat_function.h +++ b/src/wechat_function.h @@ -3,6 +3,113 @@ namespace wxhelper { namespace common { + /***************************sqlite3***************************************/ +#define SQLITE_OK 0 /* Successful result */ +/* beginning-of-error-codes */ +#define SQLITE_ERROR 1 /* Generic error */ +#define SQLITE_INTERNAL 2 /* Internal logic error in SQLite */ +#define SQLITE_PERM 3 /* Access permission denied */ +#define SQLITE_ABORT 4 /* Callback routine requested an abort */ +#define SQLITE_BUSY 5 /* The database file is locked */ +#define SQLITE_LOCKED 6 /* A table in the database is locked */ +#define SQLITE_NOMEM 7 /* A malloc() failed */ +#define SQLITE_READONLY 8 /* Attempt to write a readonly database */ +#define SQLITE_INTERRUPT 9 /* Operation terminated by sqlite3_interrupt()*/ +#define SQLITE_IOERR 10 /* Some kind of disk I/O error occurred */ +#define SQLITE_CORRUPT 11 /* The database disk image is malformed */ +#define SQLITE_NOTFOUND 12 /* Unknown opcode in sqlite3_file_control() */ +#define SQLITE_FULL 13 /* Insertion failed because database is full */ +#define SQLITE_CANTOPEN 14 /* Unable to open the database file */ +#define SQLITE_PROTOCOL 15 /* Database lock protocol error */ +#define SQLITE_EMPTY 16 /* Internal use only */ +#define SQLITE_SCHEMA 17 /* The database schema changed */ +#define SQLITE_TOOBIG 18 /* String or BLOB exceeds size limit */ +#define SQLITE_CONSTRAINT 19 /* Abort due to constraint violation */ +#define SQLITE_MISMATCH 20 /* Data type mismatch */ +#define SQLITE_MISUSE 21 /* Library used incorrectly */ +#define SQLITE_NOLFS 22 /* Uses OS features not supported on host */ +#define SQLITE_AUTH 23 /* Authorization denied */ +#define SQLITE_FORMAT 24 /* Not used */ +#define SQLITE_RANGE 25 /* 2nd parameter to sqlite3_bind out of range */ +#define SQLITE_NOTADB 26 /* File opened that is not a database file */ +#define SQLITE_NOTICE 27 /* Notifications from sqlite3_log() */ +#define SQLITE_WARNING 28 /* Warnings from sqlite3_log() */ +#define SQLITE_ROW 100 /* sqlite3_step() has another row ready */ +#define SQLITE_DONE 101 /* sqlite3_step() has finished executing */ +/* end-of-error-codes */ + +#define SQLITE_INTEGER 1 +#define SQLITE_FLOAT 2 +#define SQLITE_BLOB 4 +#define SQLITE_NULL 5 +#define SQLITE_TEXT 3 + + + + +typedef int (*sqlite3_callback)(void*, int, char**, char**); + +typedef int(__cdecl* sqlite3_exec)(UINT64, /* An open database */ + const char* sql, /* SQL to be evaluated */ + sqlite3_callback, /* Callback function */ + void*, /* 1st argument to callback */ + char** errmsg /* Error msg written here */ +); + +typedef int(__cdecl* sqlite3_prepare)( + UINT64 db, /* Database handle */ + const char* zSql, /* SQL statement, UTF-8 encoded */ + int nByte, /* Maximum length of zSql in bytes. */ + UINT64** ppStmt, /* OUT: Statement handle */ + const char** pzTail /* OUT: Pointer to unused portion of zSql */ +); +typedef int(__cdecl* sqlite3_open)(const char* filename, UINT64** ppDb); + +typedef int(__cdecl* sqlite3_sleep)(int); +typedef int(__cdecl* sqlite3_errcode)(UINT64* db); +typedef int(__cdecl* sqlite3_close)(UINT64*); + +typedef int(__cdecl* sqlite3_step)(UINT64*); +typedef int(__cdecl* sqlite3_column_count)(UINT64* pStmt); +typedef const char*(__cdecl* sqlite3_column_name)(UINT64*, int N); +typedef int(__cdecl* sqlite3_column_type)(UINT64*, int iCol); +typedef const void*(__cdecl* sqlite3_column_blob)(UINT64*, int iCol); +typedef int(__cdecl* sqlite3_column_bytes)(UINT64*, int iCol); +typedef int(__cdecl* sqlite3_finalize)(UINT64* pStmt); + + +/***************************sqlite3 end*************************************/ + +struct TableInfo { + char *name; + INT64 name_len; + char *table_name; + INT64 table_name_len; + char *sql; + INT64 sql_len; + char *rootpage; + INT64 rootpage_len; +}; + +struct DatabaseInfo { + UINT64 handle = 0; + wchar_t *db_name = NULL; + INT64 db_name_len = 0; + std::vector tables; + INT64 count = 0; + INT64 extrainfo = 0; +}; + + +struct SqlResult { + char *column_name; + INT64 column_name_len; + char *content; + INT64 content_len; + BOOL is_blob; +}; + + struct InnerMessageStruct { char *buffer; int length; @@ -57,6 +164,8 @@ struct ContactInner { } // namespace common namespace V3_9_5_81 { namespace function { + + typedef UINT64(*__GetAccountService)(); typedef UINT64(*__GetDataSavePath)(UINT64); typedef UINT64(*__GetCurrentDataPath)(UINT64); @@ -131,6 +240,36 @@ const UINT64 kGetAppMsgMgr = 0x8c33f0; const UINT64 kGetContactMgr = 0x8ae3d0; const UINT64 kGetContactList = 0xeab270; +const UINT64 k_sqlite3_exec = 0x252e340; +const UINT64 k_sqlite3_prepare = 0x2535eb0; +const UINT64 k_sqlite3_open = 0x256d6b0; +const UINT64 k_sqlite3_backup_init= 0x24e8450; +const UINT64 k_sqlite3_errcode = 0x256bfb0; +const UINT64 k_sqlite3_close = 0x256a110; +const UINT64 k_sqlite3_step = 0x24f2350; +const UINT64 k_sqlite3_column_count = 0x1df3c80; +const UINT64 k_sqlite3_column_name = 0x24f3570; +const UINT64 k_sqlite3_column_type = 0x24f33c0; +const UINT64 k_sqlite3_column_blob = 0x24f2ba0; +const UINT64 k_sqlite3_column_bytes = 0x24f2c90; +const UINT64 k_sqlite3_finalize = 0x24f1400; + +const UINT64 kGPInstance = 0x3a6f908; +const UINT64 kMicroMsgDB= 0xb8; +const UINT64 kChatMsgDB = 0x2c8; +const UINT64 kMiscDB = 0x5f0; +const UINT64 kEmotionDB = 0x838; +const UINT64 kMediaDB = 0xef8; +const UINT64 kBizchatMsgDB = 0x1a70; +const UINT64 kFunctionMsgDB = 0x1b48; +const UINT64 kDBName = 0x28; +const UINT64 kStorageStart = 0x0; +const UINT64 kStorageEnd= 0x0; +const UINT64 kMultiDBMgr= 0x3acfb68; +const UINT64 kPublicMsgMgr= 0x3acc268; +const UINT64 kFavoriteStorageMgr= 0x3acf0d0; +const UINT64 kFTSFavoriteMgr= 0x24f1400; + } // namespace offset } // namespace V3_9_5_81 From 7ab8d4733fe835e012eb5c08989034791219fd10 Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Sun, 2 Jul 2023 17:13:20 +0800 Subject: [PATCH 5/8] fix: hook flag --- src/hooks.cc | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/hooks.cc b/src/hooks.cc index 176ad1c..84d56cc 100644 --- a/src/hooks.cc +++ b/src/hooks.cc @@ -168,7 +168,9 @@ int HookSyncMsg(std::string client_ip, int port, std::string url, UINT64 do_add_msg_addr = base + offset::kDoAddMsg; DetourAttach(&(PVOID&)R_DoAddMsg, &HandleSyncMsg); LONG ret = DetourTransactionCommit(); - + if(ret == NO_ERROR){ + kMsgHookFlag = true; + } return ret; } From 9b643901cdf52acfb0a37c31019ac2451ffe5e68 Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Tue, 4 Jul 2023 17:17:01 +0800 Subject: [PATCH 6/8] =?UTF-8?q?feat:=20=E6=96=B0=E5=A2=9E=E6=95=B0?= =?UTF-8?q?=E6=8D=AE=E5=BA=93=E6=9F=A5=E8=AF=A2?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- doc/3.9.5.81.md | 100 ++++++++++++++++++++++++++++++++++++ src/db.cc | 2 +- src/http_server_callback.cc | 38 ++++++++++++++ src/wechat_function.h | 3 +- 4 files changed, 140 insertions(+), 3 deletions(-) diff --git a/doc/3.9.5.81.md b/doc/3.9.5.81.md index 0f8d0b5..f5694b8 100644 --- a/doc/3.9.5.81.md +++ b/doc/3.9.5.81.md @@ -374,4 +374,104 @@ enableHttp=0时,使用ip,port的tcp服务回传消息。 ], "msg":"success" } +``` + + +#### 7.查询数据库** +###### 接口功能 +> 查询数据库 + +###### 接口地址 +> [/api/execSql](/api/execSql) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| +|dbHandle |true |number| | +|sql |true |string| 执行的sql | + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,0成功, 非0失败| +|msg|string|返回信息| +|data|array|sqlite返回的结果| + + + +###### 接口示例 +入参: +``` javascript +{ + "dbHandle":2006119800400, + "sql":"select * from MSG where localId =301;" +} +``` +响应: +``` javascript +{ + "code": 1, + "data": [ + [ + "localId", + "TalkerId", + "MsgSvrID", + "Type", + "SubType", + "IsSender", + "CreateTime", + "Sequence", + "StatusEx", + "FlagEx", + "Status", + "MsgServerSeq", + "MsgSequence", + "StrTalker", + "StrContent", + "DisplayContent", + "Reserved0", + "Reserved1", + "Reserved2", + "Reserved3", + "Reserved4", + "Reserved5", + "Reserved6", + "CompressContent", + "BytesExtra", + "BytesTrans" + ], + [ + "301", + "1", + "8824834301214701891", + "1", + "0", + "0", + "1685401473", + "1685401473000", + "0", + "0", + "2", + "1", + "795781866", + "wxid_123", + "testtest", + "", + "0", + "2", + "", + "", + "", + "", + "", + "", + "CgQIEBAAGo0BCAcSiAE8bXNnc291cmNlPJPHNpZ25hdHVyZT52MV9wd12bTZyRzwvc2lnbmF0dXJPgoJPHRtcF9ub2RlPgoJCTxwsaXNoZXItaWQ+Jmx0OyFbQ0RBVEFbXV0mZ3Q7PC9wdWJsaXNoZXItaWQ+Cgk8L3RtcF9ub2RlPgo8L21zZ3NvdXJjZT4KGiQIAhIgNDE1MDA0NjRhZTRmMjk2NjhjMzY2ZjFkOTdmMjAwNDg=", + "" + ] + ], + "msg": "success" +} ``` \ No newline at end of file diff --git a/src/db.cc b/src/db.cc index f7b9e92..bee18c0 100644 --- a/src/db.cc +++ b/src/db.cc @@ -40,7 +40,7 @@ void FreeResult(std::vector> &data) { int DB::SelectDataInner(UINT64 db, const char *sql, std::vector> &data) { common::sqlite3_prepare p_sqlite3_prepare = - (common::sqlite3_prepare)(this->base_addr_ + offset::k_sqlite3_prepare); + (common::sqlite3_prepare)(base_addr_ + offset::k_sqlite3_prepare); common::sqlite3_step p_sqlite3_step = (common::sqlite3_step)(base_addr_ + offset::k_sqlite3_step); common::sqlite3_column_count p_sqlite3_column_count = diff --git a/src/http_server_callback.cc b/src/http_server_callback.cc index 30b9d9b..700a27e 100644 --- a/src/http_server_callback.cc +++ b/src/http_server_callback.cc @@ -5,9 +5,26 @@ #include "global_context.h" #include "hooks.h" #include "db.h" + +#define STR2LL(str) (wxhelper::Utils::IsDigit(str) ? stoll(str) : 0) namespace common = wxhelper::common; + +INT64 GetINT64Param(nlohmann::json data, std::string key) { + INT64 result; + try { + result = data[key].get(); + } catch (nlohmann::json::exception) { + result = STR2LL(data[key].get()); + } + return result; +} + +std::string GetStringParam(nlohmann::json data, std::string key) { + return data[key].get(); +} + std::wstring GetWStringParam(nlohmann::json data, std::string key) { return wxhelper::Utils::UTF8ToWstring(data[key].get()); } @@ -210,6 +227,27 @@ std::string HttpDispatch(struct mg_connection *c, struct mg_http_message *hm) { ret_data["msg"] = "success"; ret = ret_data.dump(); return ret; + } else if (mg_http_match_uri(hm, "/api/execSql")) { + UINT64 db_handle = GetINT64Param(j_param, "dbHandle"); + std::string sql = GetStringParam(j_param, "sql"); + std::vector> items; + int success = wxhelper::DB::GetInstance().Select(db_handle, sql.c_str(), items); + nlohmann::json ret_data = { + {"data", nlohmann::json::array()}, {"code", success}, {"msg", "success"}}; + if (success == 0) { + ret_data["msg"] = "no data"; + ret = ret_data.dump(); + return ret; + } + for (auto it : items) { + nlohmann::json temp_arr = nlohmann::json::array(); + for (size_t i = 0; i < it.size(); i++) { + temp_arr.push_back(it[i]); + } + ret_data["data"].push_back(temp_arr); + } + ret = ret_data.dump(); + return ret; } else { nlohmann::json ret_data = { {"code", 200}, {"data", {}}, {"msg", "not support url"}}; diff --git a/src/wechat_function.h b/src/wechat_function.h index 8f382f0..b57e911 100644 --- a/src/wechat_function.h +++ b/src/wechat_function.h @@ -247,7 +247,7 @@ const UINT64 k_sqlite3_backup_init= 0x24e8450; const UINT64 k_sqlite3_errcode = 0x256bfb0; const UINT64 k_sqlite3_close = 0x256a110; const UINT64 k_sqlite3_step = 0x24f2350; -const UINT64 k_sqlite3_column_count = 0x1df3c80; +const UINT64 k_sqlite3_column_count = 0x24f2b70; const UINT64 k_sqlite3_column_name = 0x24f3570; const UINT64 k_sqlite3_column_type = 0x24f33c0; const UINT64 k_sqlite3_column_blob = 0x24f2ba0; @@ -268,7 +268,6 @@ const UINT64 kStorageEnd= 0x0; const UINT64 kMultiDBMgr= 0x3acfb68; const UINT64 kPublicMsgMgr= 0x3acc268; const UINT64 kFavoriteStorageMgr= 0x3acf0d0; -const UINT64 kFTSFavoriteMgr= 0x24f1400; } // namespace offset } // namespace V3_9_5_81 From 53a7938335acc058a6f797b8776403bc91a4a236 Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Thu, 6 Jul 2023 21:15:56 +0800 Subject: [PATCH 7/8] fix: free heap bug --- src/manager.cc | 37 +++++++++++++------------------------ 1 file changed, 13 insertions(+), 24 deletions(-) diff --git a/src/manager.cc b/src/manager.cc index 1bce95a..697495f 100644 --- a/src/manager.cc +++ b/src/manager.cc @@ -251,25 +251,25 @@ INT64 Manager::SendImageMsg(const std::wstring& wxid, const std::wstring& image_ return success; } -// todo bug 9/10 + INT64 Manager::SendFileMsg(const std::wstring& wxid, const std::wstring& file_path){ INT64 success = -1; prototype::WeChatString* to_user= (prototype::WeChatString*)HeapAlloc(GetProcessHeap(),0,sizeof(prototype::WeChatString)); - wchar_t * ptr_wxid = (wchar_t*)HeapAlloc(GetProcessHeap(),0,wxid.length()+1); + wchar_t * ptr_wxid = (wchar_t*)HeapAlloc(GetProcessHeap(),0,(wxid.length()+1)*2); wmemcpy(ptr_wxid,wxid.c_str(),wxid.length()+1); to_user->ptr = ptr_wxid; to_user->length = static_cast(wxid.length()); to_user->max_length = static_cast(wxid.length()); to_user->c_len=0; to_user->c_ptr=0; - prototype::WeChatString* image_full_path= (prototype::WeChatString*)HeapAlloc(GetProcessHeap(),0,sizeof(prototype::WeChatString)); - wchar_t * ptr_path = (wchar_t*)HeapAlloc(GetProcessHeap(),0,file_path.length()+1); + prototype::WeChatString* file_full_path= (prototype::WeChatString*)HeapAlloc(GetProcessHeap(),0,sizeof(prototype::WeChatString)); + wchar_t * ptr_path = (wchar_t*)HeapAlloc(GetProcessHeap(),0,(file_path.length()+1)*2); wmemcpy(ptr_path,file_path.c_str(),file_path.length()+1); - image_full_path->ptr = ptr_path; - image_full_path->length = static_cast(file_path.length()); - image_full_path->max_length = static_cast(file_path.length()); - image_full_path->c_len = 0; - image_full_path->c_ptr = 0; + file_full_path->ptr = ptr_path; + file_full_path->length = static_cast(file_path.length()); + file_full_path->max_length = static_cast(file_path.length()); + file_full_path->c_len = 0; + file_full_path->c_ptr = 0; UINT64 get_app_msg_mgr_addr = base_addr_ + offset::kGetAppMsgMgr; UINT64 send_file_addr = base_addr_ + offset::kSendFileMsg; @@ -293,26 +293,15 @@ INT64 Manager::SendFileMsg(const std::wstring& wxid, const std::wstring& file_pa ZeroMemory(temp3,sizeof(UINT64)*4); ZeroMemory(temp4,sizeof(UINT64)*4); *temp4=0x1F; - UINT64 temp5 = 0xC; - - - UINT64 app_mgr = get_app_mgr(); - // UINT64 p_chat_msg = new_chat_msg(reinterpret_cast(chat_msg)); - // send_file(app_mgr, p_chat_msg, reinterpret_cast(to_user), - // reinterpret_cast(image_full_path), 1, - // reinterpret_cast(temp1), 0x300, - // reinterpret_cast(temp2), 0, - // reinterpret_cast(temp3), - // reinterpret_cast(temp4), - // temp5); - send_file(app_mgr, reinterpret_cast(chat_msg), reinterpret_cast(to_user), - reinterpret_cast(image_full_path), 1, + reinterpret_cast(file_full_path), 1, reinterpret_cast(temp1), 0, reinterpret_cast(temp2), - 0, reinterpret_cast(temp3), 0, 0x0); + 0, reinterpret_cast(temp3), 0, 0); free(reinterpret_cast(chat_msg)); + HeapFree(GetProcessHeap(),0,to_user); + HeapFree(GetProcessHeap(),0,file_full_path); HeapFree(GetProcessHeap(),0,temp1); HeapFree(GetProcessHeap(),0,temp2); HeapFree(GetProcessHeap(),0,temp3); From a9029e4a3d710bd0872af57e424c3b28a0a63590 Mon Sep 17 00:00:00 2001 From: hugy <504650082@qq.com> Date: Thu, 6 Jul 2023 21:20:14 +0800 Subject: [PATCH 8/8] =?UTF-8?q?doc:=20=E5=8F=91=E9=80=81=E6=96=87=E4=BB=B6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- doc/3.9.5.81.md | 43 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 2 deletions(-) diff --git a/doc/3.9.5.81.md b/doc/3.9.5.81.md index f5694b8..39be27d 100644 --- a/doc/3.9.5.81.md +++ b/doc/3.9.5.81.md @@ -164,7 +164,8 @@ data: 接口返回的数据 |返回字段|字段类型|说明 | |---|---|---| |code|int|返回状态,不为0成功, 0失败| -|result|string|成功提示| +|msg|string|成功提示| +|data|object|null| ###### 接口示例 @@ -474,4 +475,42 @@ enableHttp=0时,使用ip,port的tcp服务回传消息。 ], "msg": "success" } -``` \ No newline at end of file +``` + + +#### 8.发送文件消息** +###### 接口功能 +> 发送文件消息 + +###### 接口地址 +> [/api/sendFileMsg](/api/sendFileMsg) + +###### HTTP请求方式 +> POST JSON + +###### 请求参数 +|参数|必选|类型|说明| +|---|---|---|---| +|wxid |true |string| 接收人wxid | +|filePath|true |string|文件绝对路径| + +###### 返回字段 +|返回字段|字段类型|说明 | +|---|---|---| +|code|int|返回状态,不为0成功, 0失败| +|msg|string|成功提示| +|data|object|null| + +###### 接口示例 + +入参: +``` javascript +{ + "wxid": "filehelper", + "filePath": "c:\\test.zip" +} +``` +响应: +``` javascript +{"code":345686720,"msg":"success","data":null} +```