在Windows程序中,将从GetCommandLine获取的命令行解析为多个参数的规范方法是什么,类似于Unix中的argv数组？似乎CommandLineToArgvW为Unicode命令行执行此操作,但我找不到非Unicode等效项.我应该使用Unicode吗？如果没有,我该如何解析命令行？
Syl*_*sne 16
这是CommandLineToArgvA的一个实现,它将工作委托给CommandLineToArgvW,MultiByteToWideChar和WideCharToMultiByte.
LPSTR* CommandLineToArgvA(LPSTR lpCmdLine, INT *pNumArgs)
{
int retval;
retval = MultiByteToWideChar(CP_ACP, MB_ERR_INVALID_CHARS, lpCmdLine, -1, NULL, 0);
if (!SUCCEEDED(retval))
return NULL;
LPWSTR lpWideCharStr = (LPWSTR)malloc(retval * sizeof(WCHAR));
if (lpWideCharStr == NULL)
return NULL;
retval = MultiByteToWideChar(CP_ACP, MB_ERR_INVALID_CHARS, lpCmdLine, -1, lpWideCharStr, retval);
if (!SUCCEEDED(retval))
{
free(lpWideCharStr);
return NULL;
}
int numArgs;
LPWSTR* args;
args = CommandLineToArgvW(lpWideCharStr, &numArgs);
free(lpWideCharStr);
if (args == NULL)
return NULL;
int storage = numArgs * sizeof(LPSTR);
for (int i = 0; i < numArgs; ++ i)
{
BOOL lpUsedDefaultChar = FALSE;
retval = WideCharToMultiByte(CP_ACP, 0, args[i], -1, NULL, 0, NULL, &lpUsedDefaultChar);
if (!SUCCEEDED(retval))
{
LocalFree(args);
return NULL;
}
storage += retval;
}
LPSTR* result = (LPSTR*)LocalAlloc(LMEM_FIXED, storage);
if (result == NULL)
{
LocalFree(args);
return NULL;
}
int bufLen = storage - numArgs * sizeof(LPSTR);
LPSTR buffer = ((LPSTR)result) + numArgs * sizeof(LPSTR);
for (int i = 0; i < numArgs; ++ i)
{
assert(bufLen > 0);
BOOL lpUsedDefaultChar = FALSE;
retval = WideCharToMultiByte(CP_ACP, 0, args[i], -1, buffer, bufLen, NULL, &lpUsedDefaultChar);
if (!SUCCEEDED(retval))
{
LocalFree(result);
LocalFree(args);
return NULL;
}
result[i] = buffer;
buffer += retval;
bufLen -= retval;
}
LocalFree(args);
*pNumArgs = numArgs;
return result;
}
小智 5
我遵循了 parse_cmd 的源代码（请参阅最新 SDK 中的“argv_parsing.cpp”）并对其进行了修改以匹配 CommandLineToArgW 的范例和操作，并开发了以下内容。注意：根据 Microsoft 的建议（请参阅https://msdn.microsoft.com/en-us/library/windows/desktop/aa366723(v=vs.85).aspx），我没有使用 LocalAlloc，而是使用了HeapAlloc。SAL 符号的另外一项更改。我稍微偏离_In_opt_了 lpCmdLine - 因为 CommandLineToArgvW 确实允许这样做NULL，在这种情况下它返回一个只包含程序名称的参数列表。
最后一个警告， parse_cmd 将解析命令行仅在一个方面与 CommandLineToArgvW 略有不同：当状态处于“引号”模式时，连续两个双引号字符被解释为转义的双引号字符。这两个函数都消耗第一个函数并输出第二个函数。不同之处在于，对于 CommandLineToArgvW，有一个脱离“in quote”模式的转换，而 parse_cmdline 保持在“in quote”模式。这在下面的函数中得到了正确的反映。
您将按如下方式使用以下函数：
int argc = 0;
LPSTR *argv = CommandLineToArgvA(GetCommandLineA(), &argc);
HeapFree(GetProcessHeap(), NULL, argv);
LPSTR* CommandLineToArgvA(_In_opt_ LPCSTR lpCmdLine, _Out_ int *pNumArgs)
{
if (!pNumArgs)
{
SetLastError(ERROR_INVALID_PARAMETER);
return NULL;
}
*pNumArgs = 0;
/*follow CommandLinetoArgvW and if lpCmdLine is NULL return the path to the executable.
Use 'programname' so that we don't have to allocate MAX_PATH * sizeof(CHAR) for argv
every time. Since this is ANSI the return can't be greater than MAX_PATH (260
characters)*/
CHAR programname[MAX_PATH] = {};
/*pnlength = the length of the string that is copied to the buffer, in characters, not
including the terminating null character*/
DWORD pnlength = GetModuleFileNameA(NULL, programname, MAX_PATH);
if (pnlength == 0) //error getting program name
{
//GetModuleFileNameA will SetLastError
return NULL;
}
if (*lpCmdLine == NULL)
{
/*In keeping with CommandLineToArgvW the caller should make a single call to HeapFree
to release the memory of argv. Allocate a single block of memory with space for two
pointers (representing argv[0] and argv[1]). argv[0] will contain a pointer to argv+2
where the actual program name will be stored. argv[1] will be nullptr per the C++
specifications for argv. Hence space required is the size of a LPSTR (char*) multiplied
by 2 [pointers] + the length of the program name (+1 for null terminating character)
multiplied by the sizeof CHAR. HeapAlloc is called with HEAP_GENERATE_EXCEPTIONS flag,
so if there is a failure on allocating memory an exception will be generated.*/
LPSTR *argv = static_cast<LPSTR*>(HeapAlloc(GetProcessHeap(),
HEAP_ZERO_MEMORY | HEAP_GENERATE_EXCEPTIONS,
(sizeof(LPSTR) * 2) + ((pnlength + 1) * sizeof(CHAR))));
memcpy(argv + 2, programname, pnlength+1); //add 1 for the terminating null character
argv[0] = reinterpret_cast<LPSTR>(argv + 2);
argv[1] = nullptr;
*pNumArgs = 1;
return argv;
}
/*We need to determine the number of arguments and the number of characters so that the
proper amount of memory can be allocated for argv. Our argument count starts at 1 as the
first "argument" is the program name even if there are no other arguments per specs.*/
int argc = 1;
int numchars = 0;
LPCSTR templpcl = lpCmdLine;
bool in_quotes = false; //'in quotes' mode is off (false) or on (true)
/*first scan the program name and copy it. The handling is much simpler than for other
arguments. Basically, whatever lies between the leading double-quote and next one, or a
terminal null character is simply accepted. Fancier handling is not required because the
program name must be a legal NTFS/HPFS file name. Note that the double-quote characters are
not copied.*/
do {
if (*templpcl == '"')
{
//don't add " to character count
in_quotes = !in_quotes;
templpcl++; //move to next character
continue;
}
++numchars; //count character
templpcl++; //move to next character
if (_ismbblead(*templpcl) != 0) //handle MBCS
{
++numchars;
templpcl++; //skip over trail byte
}
} while (*templpcl != '\0' && (in_quotes || (*templpcl != ' ' && *templpcl != '\t')));
//parsed first argument
if (*templpcl == '\0')
{
/*no more arguments, rewind and the next for statement will handle*/
templpcl--;
}
//loop through the remaining arguments
int slashcount = 0; //count of backslashes
bool countorcopychar = true; //count the character or not
for (;;)
{
if (*templpcl)
{
//next argument begins with next non-whitespace character
while (*templpcl == ' ' || *templpcl == '\t')
++templpcl;
}
if (*templpcl == '\0')
break; //end of arguments
++argc; //next argument - increment argument count
//loop through this argument
for (;;)
{
/*Rules:
2N backslashes + " ==> N backslashes and begin/end quote
2N + 1 backslashes + " ==> N backslashes + literal "
N backslashes ==> N backslashes*/
slashcount = 0;
countorcopychar = true;
while (*templpcl == '\\')
{
//count the number of backslashes for use below
++templpcl;
++slashcount;
}
if (*templpcl == '"')
{
//if 2N backslashes before, start/end quote, otherwise count.
if (slashcount % 2 == 0) //even number of backslashes
{
if (in_quotes && *(templpcl +1) == '"')
{
in_quotes = !in_quotes; //NB: parse_cmdline omits this line
templpcl++; //double quote inside quoted string
}
else
{
//skip first quote character and count second
countorcopychar = false;
in_quotes = !in_quotes;
}
}
slashcount /= 2;
}
//count slashes
while (slashcount--)
{
++numchars;
}
if (*templpcl == '\0' || (!in_quotes && (*templpcl == ' ' || *templpcl == '\t')))
{
//at the end of the argument - break
break;
}
if (countorcopychar)
{
if (_ismbblead(*templpcl) != 0) //should copy another character for MBCS
{
++templpcl; //skip over trail byte
++numchars;
}
++numchars;
}
++templpcl;
}
//add a count for the null-terminating character
++numchars;
}
/*allocate memory for argv. Allocate a single block of memory with space for argc number of
pointers. argv[0] will contain a pointer to argv+argc where the actual program name will be
stored. argv[argc] will be nullptr per the C++ specifications. Hence space required is the
size of a LPSTR (char*) multiplied by argc + 1 pointers + the number of characters counted
above multiplied by the sizeof CHAR. HeapAlloc is called with HEAP_GENERATE_EXCEPTIONS
flag, so if there is a failure on allocating memory an exception will be generated.*/
LPSTR *argv = static_cast<LPSTR*>(HeapAlloc(GetProcessHeap(),
HEAP_ZERO_MEMORY | HEAP_GENERATE_EXCEPTIONS,
(sizeof(LPSTR) * (argc+1)) + (numchars * sizeof(CHAR))));
//now loop through the commandline again and split out arguments
in_quotes = false;
templpcl = lpCmdLine;
argv[0] = reinterpret_cast<LPSTR>(argv + argc+1);
LPSTR tempargv = reinterpret_cast<LPSTR>(argv + argc+1);
do {
if (*templpcl == '"')
{
in_quotes = !in_quotes;
templpcl++; //move to next character
continue;
}
*tempargv++ = *templpcl;
templpcl++; //move to next character
if (_ismbblead(*templpcl) != 0) //should copy another character for MBCS
{
*tempargv++ = *templpcl; //copy second byte
templpcl++; //skip over trail byte
}
} while (*templpcl != '\0' && (in_quotes || (*templpcl != ' ' && *templpcl != '\t')));
//parsed first argument
if (*templpcl == '\0')
{
//no more arguments, rewind and the next for statement will handle
templpcl--;
}
else
{
//end of program name - add null terminator
*tempargv = '\0';
}
int currentarg = 1;
argv[currentarg] = ++tempargv;
//loop through the remaining arguments
slashcount = 0; //count of backslashes
countorcopychar = true; //count the character or not
for (;;)
{
if (*templpcl)
{
//next argument begins with next non-whitespace character
while (*templpcl == ' ' || *templpcl == '\t')
++templpcl;
}
if (*templpcl == '\0')
break; //end of arguments
argv[currentarg] = ++tempargv; //copy address of this argument string
//next argument - loop through it's characters
for (;;)
{
/*Rules:
2N backslashes + " ==> N backslashes and begin/end quote
2N + 1 backslashes + " ==> N backslashes + literal "
N backslashes ==> N backslashes*/
slashcount = 0;
countorcopychar = true;
while (*templpcl == '\\')
{
//count the number of backslashes for use below
++templpcl;
++slashcount;
}
if (*templpcl == '"')
{
//if 2N backslashes before, start/end quote, otherwise copy literally.
if (slashcount % 2 == 0) //even number of backslashes
{
if (in_quotes && *(templpcl+1) == '"')
{
in_quotes = !in_quotes; //NB: parse_cmdline omits this line
templpcl++; //double quote inside quoted string
}
else
{
//skip first quote character and count second
countorcopychar = false;
in_quotes = !in_quotes;
}
}
slashcount /= 2;
}
//copy slashes
while (slashcount--)
{
*tempargv++ = '\\';
}
if (*templpcl == '\0' || (!in_quotes && (*templpcl == ' ' || *templpcl == '\t')))
{
//at the end of the argument - break
break;
}
if (countorcopychar)
{
*tempargv++ = *templpcl;
if (_ismbblead(*templpcl) != 0) //should copy another character for MBCS
{
++templpcl; //skip over trail byte
*tempargv++ = *templpcl;
}
}
++templpcl;
}
//null-terminate the argument
*tempargv = '\0';
++currentarg;
}
argv[argc] = nullptr;
*pNumArgs = argc;
return argv;
}
CommandLineToArgvW()位于 shell32.dll 中。我猜测 Shell 开发人员创建了该函数供自己使用，并且将其公开是因为有人认为第 3 方开发人员会发现它有用，或者是因为某些法庭诉讼迫使他们这样做。
由于 Shell 开发人员只需要一个 Unicode 版本，这就是他们所编写的全部内容。为将 ANSI 转换为 Unicode 的函数编写一个 ANSI 包装器，调用该函数并将 Unicode 结果转换为 ANSI（如果 Shell32.dll 曾经提供过此 API 的 ANSI 变体，那可能正是如此）做）。