本文仅做理性上的愉悦，无实际用途。
scanf实际的调用
我们直接使用的scanf其实是这样写的
int __cdecl scanf (
const char *format,
...
)
{
va_list arglist;
va_start(arglist, format);
return vscanf_fn(_input_l, format, NULL, arglist);
}
我们可以看到，他其实是调用了这三个函数： va_list va_start vscanf_fn
我们跳转到vscanf_fn的实现
int __cdecl vscanf_fn (
INPUTFN inputfn,
const char *format,
_locale_t plocinfo,
va_list arglist
)
/*
* stdin 'SCAN', 'F'ormatted
*/
{
int retval = 0;
_VALIDATE_RETURN( (format != NULL), EINVAL, EOF);
_lock_str2(0, stdin);
__try {
retval = (inputfn(stdin, format, plocinfo, arglist));
}
__finally {
_unlock_str2(0, stdin);
}
return(retval);
}
/***
*int _input(stream, format, arglist), static int input(format, arglist)
*
*Purpose:
* get input items (data items or literal matches) from the input stream
* and assign them if appropriate to the items thru the arglist. this
* function is intended for internal library use only, not for the user
*
* The _input entry point is for the normal scanf() functions
* The input entry point is used when compiling for _cscanf() [CPRFLAF
* defined] and is a static function called only by _cscanf() -- reads from
* console.
*
* This code also defines _input_s, which works differently for %c, %s & %[.
* For these, _input_s first picks up the next argument from the variable
* argument list & uses it as the maximum size of the character array pointed
* to by the next argument in the list.
*
*Entry:
* FILE *stream - file to read from
* char *format - format string to determine the data to read
* arglist - list of pointer to data items
*
*Exit:
* returns number of items assigned and fills in data items
* returns EOF if error or EOF found on stream before 1st data item matched
*
*Exceptions:
*
*******************************************************************************/
有几个关键函数：
static _TINT __cdecl _inc(FILE* fileptr)
{
return (_gettc_nolock(fileptr));
}
_inc的功能是调出缓冲区第一个字符
static void __cdecl _un_inc(_TINT chr, FILE* fileptr)
{
if (_TEOF != chr) {
_ungettc_nolock(chr,fileptr);
}
}
_un_inc函数，将刚才_inc调出的函数重新放进缓冲区
static _TINT __cdecl _whiteout(int* counter, FILE* fileptr)
{
_TINT ch;
do
{
++*counter;
ch = _inc(fileptr);
if (ch == _TEOF)
{
break;
}
}
while(_istspace((_TUCHAR)ch));
return ch;
}
_whiteout函数，将从缓冲区开头开始的所有连续空白字符调出
最后一步检查缓冲区，如果缓冲区可读字符为0，那么清空缓冲区
while (*format) {
if (_istspace((_TUCHAR)*format)) {
UN_INC(EAT_WHITE()); /* put first non-space char back */
do {
tch = *++format;
} while (_istspace((_TUCHAR)tch));
continue;
………………
这里的UN_INC(EAT_WHITE())，是把当初EAT_WHITE读出的第一个非空白字符再放入缓冲区。
上面代码完成对键盘缓冲区中空白符的清理，直到正常读取第一个字符。
当读入%号，进行处理：
if (_T('%') == *format && _T('%') != *(format + 1))
解析完格式后，开始真正的实现，我们以%d做例子：
if (_T('^') == *scanptr) {
++scanptr;
--reject; /* set reject to 255 */
}
/* Allocate "table" on first %[] spec */
#if ALLOC_TABLE
if (table == NULL) {
table = (char*)_malloc_crt(TABLESIZE);
if ( table == NULL)
goto error_return;
malloc_flag = 1;
}zuolizi
#endif /* ALLOC_TABLE */
memset(table, 0, TABLESIZE);
if (LEFT_BRACKET == comchr)
if (_T(']') == *scanptr) {
prevchar = _T(']');
++scanptr;
table[ _T(']') >> 3] = 1 << (_T(']') & 7);
}
while (_T(']') != *scanptr) {
rngch = *scanptr++;
if (_T('-') != rngch ||
!prevchar || /* first char */
_T(']') == *scanptr) /* last char */
table[(prevchar = rngch) >> 3] |= 1 << (rngch & 7);
else { /* handle a-z type set */
rngch = *scanptr++; /* get end of range */
if (prevchar < rngch) /* %[a-z] */
last = rngch;
else { /* %[z-a] */
last = prevchar;
prevchar = rngch;
}
/* last could be 0xFF, so we handle it at the end of the for loop */
for (rngch = prevchar; rngch < last; ++rngch)
{
table[rngch >> 3] |= 1 << (rngch & 7);
}
table[last >> 3] |= 1 << (last & 7);
prevchar = 0;
}
}
reject反转标记，如果出现^ 则reject = FF; 其后方便进行 ^ 进行反转。
对于[ ]字符集，有一个char table[32]来保存256个ascii字符。(此处每个char为8bits,所以有32组可以完全包含256个ascii字符)
微软对table中字符做了这样的处理：
table[rngch >> 3] |= 1 << (rngch & 7);
即：将所读的字符串分到32组中【rngch>>3相当于除以8】，每个table[n]有8bits，每个bit中，出现的字符位会被置为1，未出现则为0，这样就完美囊括了256个ASCII字符。
判断字符是否存在，直接这样处理：
(table[ch >> 3] ^ reject) & (1 << (ch & 7))
%d跳过了
的读取，继续读取下一个字符。
if (_T('%') == *format && _T('%') != *(format + 1)) {
……………………
++format; /* skip to next char */
} else /* ('%' != *format) */
{
………………………
}
在读代码时候读到一个函数 hextodec
static _TINT __cdecl _hextodec ( _TCHAR chr)
{
return _ISDIGIT(chr) ? chr : (chr & ~(_T('a') - _T('A'))) - _T('A') + 10 + _T('0');
}
将读取的16进制字符 0 - F转成 10进制数，然后scanf就结束了
我们有一个非常简单的scanf的实现(臭不要脸的调用vscanf_fn)
#include<cstdio>
#include<cstdarg>
int my_scanf(char* fmt,...)
{
int ret=0;
va_list args;
va_start(args,fmt);
vscanf(fmt,args);
va_end(args);
return ret;
}
int main()
{
int a;
my_scanf("%d",&a);
printf("%d",a);
return 0;
}