#ifndef _STRING_H_
#define _STRING_H_

#ifndef NULL
#define NULL ((void *) 0)
#endif

#ifndef _SIZE_T
#define _SIZE_T
typedef unsigned int size_t;
#endif

extern char * strerror(int errno);

/*
 * This string-include defines all string functions as inline
 * functions. Use gcc. It also assumes ds=es=data space, this should be
 * normal. Most of the string-functions are rather heavily hand-optimized,
 * see especially strtok,strstr,str[c]spn. They should work, but are not
 * very easy to understand. Everything is done entirely within the register
 * set, making the functions fast and clean. String instructions have been
 * used through-out, making for "slightly" unclear code :-)
 *
 *		(C) 1991 Linus Torvalds
 */
 
extern inline char * strcpy(char * dest,const char *src)
{
int d0, d1, d2;
__asm__ __volatile__("cld\n\t"
	"1:\tlodsb\n\t"
	"stosb\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b"
	: "=&S" (d0), "=&D" (d1), "=&a" (d2)
	:"0" (src),"1" (dest) : "memory");
return dest;
}

extern inline char * strncpy(char * dest,const char *src,int count)
{
int d0, d1, d2, d3;
__asm__ __volatile__("cld\n\t"
	"1:\tdecl %2\n\t"
	"js 2f\n\t"
	"lodsb\n\t"
	"stosb\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b\n\t"
	"rep\n\t"
	"stosb\n"
	"2:"
	: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
	:"0" (src),"1" (dest),"2" (count) : "memory");
return dest;
}

extern inline char * strcat(char * dest,const char * src)
{
int d0, d1, d2, d3;
__asm__ __volatile__("cld\n\t"
	"repne\n\t"
	"scasb\n\t"
	"decl %1\n"
	"1:\tlodsb\n\t"
	"stosb\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b"
	: "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
	: "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu):"memory");
return dest;
}

extern inline char * strncat(char * dest,const char * src,int count)
{
int d0, d1, d2, d3;
__asm__ __volatile__("cld\n\t"
	"repne\n\t"
	"scasb\n\t"
	"decl %1\n\t"
	"movl %8,%3\n"
	"1:\tdecl %3\n\t"
	"js 2f\n\t"
	"lodsb\n\t"
	"stosb\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b\n"
	"2:\txorl %2,%2\n\t"
	"stosb"
	: "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
	: "0" (src),"1" (dest),"2" (0),"3" (0xffffffffu), "g" (count)
	: "memory");
return dest;
}

extern inline int strcmp(const char * cs,const char * ct)
{
int d0, d1;
register int __res;
__asm__ __volatile__("cld\n\t"
	"1:\tlodsb\n\t"
	"scasb\n\t"
	"jne 2f\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b\n\t"
	"xorl %%eax,%%eax\n\t"
	"jmp 3f\n"
	"2:\tsbbl %%eax,%%eax\n\t"
	"orb $1,%%al\n"
	"3:"
	:"=a" (__res), "=&S" (d0), "=&D" (d1)
	:"1" (cs),"2" (ct)
	:"memory");
return __res;
}

extern inline int strncmp(const char * cs,const char * ct,int count)
{
register int __res;
int d0, d1, d2;
__asm__ __volatile__("cld\n\t"
	"1:\tdecl %3\n\t"
	"js 2f\n\t"
	"lodsb\n\t"
	"scasb\n\t"
	"jne 3f\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b\n"
	"2:\txorl %%eax,%%eax\n\t"
	"jmp 4f\n"
	"3:\tsbbl %%eax,%%eax\n\t"
	"orb $1,%%al\n"
	"4:"
	:"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
	:"1" (cs),"2" (ct),"3" (count)
	:"memory");
return __res;
}

extern inline char * strchr(const char * s,int c)
{
int d0;
register char * __res;
__asm__ __volatile__(
	"movb %%al,%%ah\n"
	"1:\tlodsb\n\t"
	"cmpb %%ah,%%al\n\t"
	"je 2f\n\t"
	"testb %%al,%%al\n\t"
	"jne 1b\n\t"
	"movl $1,%1\n"
	"2:\tmovl %1,%0\n\t"
	"decl %0"
	:"=a" (__res), "=&S" (d0)
	:"1" (s),"0" (c)
	:"memory");
return __res;
}

extern inline char * strrchr(const char * s,int c)
{
int d0, d1;
register char * __res;
__asm__ __volatile__("cld\n\t"
	"movb %%al,%%ah\n"
	"1:\tlodsb\n\t"
	"cmpb %%ah,%%al\n\t"
	"jne 2f\n\t"
	"leal -1(%%esi),%0\n"
	"2:\ttestb %%al,%%al\n\t"
	"jne 1b"
	:"=g" (__res), "=&S" (d0), "=&a" (d1)
	:"0" (0),"1" (s),"2" (c)
	:"memory");
return __res;
}

extern inline int strspn(const char * cs, const char * ct)
{
register char * __res;// __asm__("si");
__asm__("cld\n\t"
	"movl %4,%%edi\n\t"
	"repne\n\t"
	"scasb\n\t"
	"notl %%ecx\n\t"
	"decl %%ecx\n\t"
	"movl %%ecx,%%edx\n"
	"1:\tlodsb\n\t"
	"testb %%al,%%al\n\t"
	"je 2f\n\t"
	"movl %4,%%edi\n\t"
	"movl %%edx,%%ecx\n\t"
	"repne\n\t"
	"scasb\n\t"
	"je 1b\n"
	"2:\tdecl %0"
	:"=S" (__res):"a" (0),"c" (0xffffffff),"0" (cs),"g" (ct)
	:/*"ax","cx",*/"dx","di"); /* TODO : constraint may be wrong*/
return __res-cs;
}

extern inline int strcspn(const char * cs, const char * ct)
{
register char * __res;// __asm__("si");
__asm__("cld\n\t"
	"movl %4,%%edi\n\t"
	"repne\n\t"
	"scasb\n\t"
	"notl %%ecx\n\t"
	"decl %%ecx\n\t"
	"movl %%ecx,%%edx\n"
	"1:\tlodsb\n\t"
	"testb %%al,%%al\n\t"
	"je 2f\n\t"
	"movl %4,%%edi\n\t"
	"movl %%edx,%%ecx\n\t"
	"repne\n\t"
	"scasb\n\t"
	"jne 1b\n"
	"2:\tdecl %0"
	:"=S" (__res):"a" (0),"c" (0xffffffff),"0" (cs),"g" (ct)
	:/*"ax","cx",*/"dx","di"); /* TODO : constraint may be wrong*/
return __res-cs;
}

extern inline char * strpbrk(const char * cs,const char * ct)
{
register char * __res;// __asm__("si");
__asm__("cld\n\t"
	"movl %4,%%edi\n\t"
	"repne\n\t"
	"scasb\n\t"
	"notl %%ecx\n\t"
	"decl %%ecx\n\t"
	"movl %%ecx,%%edx\n"
	"1:\tlodsb\n\t"
	"testb %%al,%%al\n\t"
	"je 2f\n\t"
	"movl %4,%%edi\n\t"
	"movl %%edx,%%ecx\n\t"
	"repne\n\t"
	"scasb\n\t"
	"jne 1b\n\t"
	"decl %0\n\t"
	"jmp 3f\n"
	"2:\txorl %0,%0\n"
	"3:"
	:"=S" (__res):"a" (0),"c" (0xffffffff),"0" (cs),"g" (ct)
	:/*"ax","cx",*/"dx","di");/* TODO : constraint may be wrong*/
return __res;
}

extern inline char * strstr(const char * cs,const char * ct)
{
register char * __res;// __asm__("ax");
__asm__("cld\n\t" \
	"movl %4,%%edi\n\t"
	"repne\n\t"
	"scasb\n\t"
	"notl %%ecx\n\t"
	"decl %%ecx\n\t"	/* NOTE! This also sets Z if searchstring='' */
	"movl %%ecx,%%edx\n"
	"1:\tmovl %4,%%edi\n\t"
	"movl %%esi,%%eax\n\t"
	"movl %%edx,%%ecx\n\t"
	"repe\n\t"
	"cmpsb\n\t"
	"je 2f\n\t"		/* also works for empty string, see above */
	"xchgl %%eax,%%esi\n\t"
	"incl %%esi\n\t"
	"cmpb $0,-1(%%eax)\n\t"
	"jne 1b\n\t"
	"xorl %%eax,%%eax\n\t"
	"2:"
	:"=a" (__res):"0" (0),"c" (0xffffffff),"S" (cs),"g" (ct)
	:/*"cx",*/"dx","di"/*,"si"*/); /* TODO : constraint may be wrong*/
return __res;
}

extern inline int strlen(const char * s)
{
int d0;
register int __res;
__asm__ __volatile__("cld\n\t"
	"repne\n\t"
	"scasb\n\t"
	"notl %0\n\t"
	"decl %0"
	:"=c" (__res), "=&D" (d0)
	:"1" (s),"a" (0), "0" (0xffffffffu)
	:"memory");
return __res;
}

extern char * ___strtok;

extern inline char * strtok(char * s,const char * ct)
{
register char * __res;// __asm__("si");
__asm__("testl %1,%1\n\t"
	"jne 1f\n\t"
	"testl %0,%0\n\t"
	"je 8f\n\t"
	"movl %0,%1\n"
	"1:\txorl %0,%0\n\t"
	"movl $-1,%%ecx\n\t"
	"xorl %%eax,%%eax\n\t"
	"cld\n\t"
	"movl %4,%%edi\n\t"
	"repne\n\t"
	"scasb\n\t"
	"notl %%ecx\n\t"
	"decl %%ecx\n\t"
	"je 7f\n\t"			/* empty delimeter-string */
	"movl %%ecx,%%edx\n"
	"2:\tlodsb\n\t"
	"testb %%al,%%al\n\t"
	"je 7f\n\t"
	"movl %4,%%edi\n\t"
	"movl %%edx,%%ecx\n\t"
	"repne\n\t"
	"scasb\n\t"
	"je 2b\n\t"
	"decl %1\n\t"
	"cmpb $0,(%1)\n\t"
	"je 7f\n\t"
	"movl %1,%0\n"
	"3:\tlodsb\n\t"
	"testb %%al,%%al\n\t"
	"je 5f\n\t"
	"movl %4,%%edi\n\t"
	"movl %%edx,%%ecx\n\t"
	"repne\n\t"
	"scasb\n\t"
	"jne 3b\n\t"
	"decl %1\n\t"
	"cmpb $0,(%1)\n\t"
	"je 5f\n\t"
	"movb $0,(%1)\n\t"
	"incl %1\n\t"
	"jmp 6f\n"
	"5:\txorl %1,%1\n"
	"6:\tcmpb $0,(%0)\n\t"
	"jne 7f\n\t"
	"xorl %0,%0\n"
	"7:\ttestl %0,%0\n\t"
	"jne 8f\n\t"
	"movl %0,%1\n"
	"8:"
	:"=b" (__res),"=S" (___strtok)
	:"0" (___strtok),"1" (s),"g" (ct)
	:"ax","cx","dx","di"); /* TODO : constraint may be wrong*/
return __res;
}

extern inline void * memcpy(void * dest,const void * src, int n)
{
int d0,d1,d2;
__asm__ __volatile("cld\n\t"
	"rep\n\t"
	"movsb"
	:"=&c" (d0), "=&S" (d1), "=&D" (d2)
	:"0" (n),"1" (src),"2" (dest)
	:"memory");
return dest;
}

extern inline void * memmove(void * dest,const void * src, int n)
{
	int d0, d1, d2;

	if (dest < src) {
		memcpy(dest,src,n);
	} else {
		__asm__ __volatile__(
			"std\n\t"
			"rep\n\t"
			"movsb\n\t"
			"cld"
			: "=&c" (d0), "=&S" (d1), "=&D" (d2)
			:"0" (n),
			 "1" (n-1+(const char *)src),
			 "2" (n-1+(char *)dest)
			:"memory");
	}
	return dest;
}

extern inline int memcmp(const void * cs,const void * ct,int count)
{
register int __res;// __asm__("ax");
__asm__("cld\n\t"
	"repe\n\t"
	"cmpsb\n\t"
	"je 1f\n\t"
	"movl $1,%%eax\n\t"
	"jl 1f\n\t"
	"negl %%eax\n"
	"1:"
	:"=a" (__res):"0" (0),"D" (cs),"S" (ct),"c" (count)
	/*:"si","di","cx"*/); /* TODO : constraint may be wrong*/
return __res;
}

extern inline void * memchr(const void * cs,char c,int count)
{
int d0;
register void * __res;
if (!count)
	return NULL;
__asm__ __volatile__("cld\n\t"
	"repne\n\t"
	"scasb\n\t"
	"je 1f\n\t"
	"movl $1,%0\n"
	"1:\tdecl %0"
	:"=D" (__res), "=&c" (d0)
	:"a" (c),"0" (cs),"1" (count)
	:"memory");
return __res;
}

extern inline void * memset(void * s,int c,int count)
{
int d0, d1;
__asm__ __volatile__("cld\n\t"
	"rep\n\t"
	"stosb"
	: "=&c" (d0), "=&D" (d1)
	:"a" (c),"1" (s),"0" (count)
	:"memory");
return s;
}

#endif