fat_nls.c

嵌入式FAT文件系统

#include <cyg/infra/cyg_type.h>   
#include <cyg/infra/cyg_trac.h>        // tracing macros
#include <cyg/infra/cyg_ass.h>         // assertion macros
#include <errno.h>
#include <string.h>
#include "nls.h"
#include "stdlib.h"
#define _U	0x01	/* upper */
#define _L	0x02	/* lower */
#define _D	0x04	/* digit */
#define _C	0x08	/* cntrl */
#define _P	0x10	/* punct */
#define _S	0x20	/* white space (space/lf/tab) */
#define _X	0x40	/* hex digit */
#define _SP	0x80	/* hard space (0x20) */

static unsigned char _ctype[] = {
_C,_C,_C,_C,_C,_C,_C,_C,			/* 0-7 */
_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C,		/* 8-15 */
_C,_C,_C,_C,_C,_C,_C,_C,			/* 16-23 */
_C,_C,_C,_C,_C,_C,_C,_C,			/* 24-31 */
_S|_SP,_P,_P,_P,_P,_P,_P,_P,			/* 32-39 */
_P,_P,_P,_P,_P,_P,_P,_P,			/* 40-47 */
_D,_D,_D,_D,_D,_D,_D,_D,			/* 48-55 */
_D,_D,_P,_P,_P,_P,_P,_P,			/* 56-63 */
_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U,	/* 64-71 */
_U,_U,_U,_U,_U,_U,_U,_U,			/* 72-79 */
_U,_U,_U,_U,_U,_U,_U,_U,			/* 80-87 */
_U,_U,_U,_P,_P,_P,_P,_P,			/* 88-95 */
_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L,	/* 96-103 */
_L,_L,_L,_L,_L,_L,_L,_L,			/* 104-111 */
_L,_L,_L,_L,_L,_L,_L,_L,			/* 112-119 */
_L,_L,_L,_P,_P,_P,_P,_C,			/* 120-127 */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 128-143 */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 144-159 */
_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,   /* 160-175 */
_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,       /* 176-191 */
_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,       /* 192-207 */
_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L,       /* 208-223 */
_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,       /* 224-239 */
_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L};      /* 240-255 */

#define __ismask(x) (_ctype[(int)(unsigned char)(x)])

#define isalnum(c)	((__ismask(c)&(_U|_L|_D)) != 0)
#define isalpha(c)	((__ismask(c)&(_U|_L)) != 0)
#define iscntrl(c)	((__ismask(c)&(_C)) != 0)
#define isdigit(c)	((__ismask(c)&(_D)) != 0)
#define isgraph(c)	((__ismask(c)&(_P|_U|_L|_D)) != 0)
#define islower(c)	((__ismask(c)&(_L)) != 0)
#define isprint(c)	((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
#define ispunct(c)	((__ismask(c)&(_P)) != 0)
#define isspace(c)	((__ismask(c)&(_S)) != 0)
#define isupper(c)	((__ismask(c)&(_U)) != 0)
#define isxdigit(c)	((__ismask(c)&(_D|_X)) != 0)

#define isascii(c) (((unsigned char)(c))<=0x7f)
#define toascii(c) (((unsigned char)(c))&0x7f)
static cyg_uint16 fat_bad_char(cyg_uint16 w)
{
	return (w < 0x0020)
	    || (w == '*') || (w == '?') || (w == '<') || (w == '>')
	    || (w == '|') || (w == '"') || (w == ':') || (w == '/')
	    || (w == '\\');
	
}
static  cyg_uint16 fat_replace_char( cyg_uint16 w)
{
	return (w == '[') || (w == ']') || (w == ';') || (w == ',')
	    || (w == '+') || (w == '=');
}

static  cyg_uint16 fat_skip_char( cyg_uint16 w)
{
	return (w == '.') || (w == ' ');
}

static inline int fat_is_used_badchars(const cyg_uint16 *s, int len)
{
	int i;

	for (i = 0; i < len; i++)
		if (fat_bad_char(s[i]))
			return -EINVAL;
	return 0;
}
static int fat_valid_longname(const cyg_uint8 *name, cyg_uint32 len)
{
	if (name[len - 1] == ' ')
		return -EINVAL;
	if (len >= 256)
		return -ENAMETOOLONG;
	return 0;
}
struct shortname_info {
	unsigned char lower:1,
		      upper:1,
		      valid:1;
};
#define INIT_SHORTNAME_INFO(x)	do {		\
	(x)->lower = 1;				\
	(x)->upper = 1;				\
	(x)->valid = 1;				\
} while (0)

static cyg_uint32 to_shortname_char(struct nls_table *nls,
				    cyg_uint8 *buf, cyg_uint32 buf_size,
				    cyg_uint16 *src, struct shortname_info *info)
{
	int len;

	if (fat_skip_char(*src)) {
		info->valid = 0;
		return 0;
	}
	if (fat_replace_char(*src)) {
		info->valid = 0;
		buf[0] = '_';
		return 1;
	}

	len = nls->uni2char(*src, buf, buf_size);
	if (len <= 0) {
		info->valid = 0;
		buf[0] = '_';
		len = 1;
	} else if (len == 1) {
		unsigned char prev = buf[0];

		if (buf[0] >= 0x7F) {
			info->lower = 0;
			info->upper = 0;
		}

		buf[0] = nls_toupper(nls, buf[0]);
		if (isalpha(buf[0])) {
			if (buf[0] == prev)
				info->lower = 0;
			else
				info->upper = 0;
		}
	} else {
		info->lower = 0;
		info->upper = 0;
	}

	return len;
}
int create_shortname(void *dir,
                         fatfs_disk_t *disk,
                        struct nls_table *nls,
			const char *name,int len,
			cyg_uint8 *name_res)
{
	cyg_uint16 *ip, *ext_start, *end, *name_start;
	cyg_uint8 base[9], ext[4], buf[8], *p;
	cyg_uint8 charbuf[NLS_MAX_CHARSET_SIZE];
	cyg_uint16 uname[256]={0};
	int ret,ulen=0;
	int chl, chi;
	cyg_uint32 jiffies;
	int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen;
	int is_shortname;
	fatfs_dirsearch_t ds;
	struct shortname_info base_info, ext_info;
	jiffies=rand();
	is_shortname = 1;
	INIT_SHORTNAME_INFO(&base_info);
	INIT_SHORTNAME_INFO(&ext_info);
        for(i=0;i<len;)
        {
	        ret=fatfs_utf8_table->char2uni(name+i, len, uname[ulen]);
		if(ret<0)  return ret;
		if(ulen>=256) return -1;
		i+=ret;
		ulen++;
	}
	/* Now, we need to create a shortname from the long name */
	ext_start = end = &uname[ulen];
	while (--ext_start >= uname) {
		if (*ext_start == 0x002E) {	/* is `.' */
			if (ext_start == end - 1) {
				sz = ulen;
				ext_start = NULL;
			}
			break;
		}
	}
		if (ext_start == uname - 1) {
		sz = ulen;
		ext_start = NULL;
	} else if (ext_start) {
		/*
		 * Names which start with a dot could be just
		 * an extension eg. "...test".  In this case Win95
		 * uses the extension as the name and sets no extension.
		 */
		name_start = &uname[0];
		while (name_start < ext_start) {
			if (!fat_skip_char(*name_start))
				break;
			name_start++;
		}
		if (name_start != ext_start) {
			sz = ext_start - uname;
			ext_start++;
		} else {
			sz = ulen;
			ext_start = NULL;
		}
	}

	numtail_baselen = 6;
	numtail2_baselen = 2;
	for (baselen = i = 0, p = base, ip = uname; i < sz; i++, ip++) {
		chl = to_shortname_char(nls, charbuf, sizeof(charbuf),
					ip, &base_info);
		if (chl == 0)
			continue;

		if (baselen < 2 && (baselen + chl) > 2)
			numtail2_baselen = baselen;
		if (baselen < 6 && (baselen + chl) > 6)
			numtail_baselen = baselen;
		for (chi = 0; chi < chl; chi++) {
			*p++ = charbuf[chi];
			baselen++;
			if (baselen >= 8)
				break;
		}
		if (baselen >= 8) {
			if ((chi < chl - 1) || (ip + 1) - uname < sz)
				is_shortname = 0;
			break;
		}
	}
	if (baselen == 0) {
		return -EINVAL;
	}

	extlen = 0;
	if (ext_start) {
		for (p = ext, ip = ext_start; extlen < 3 && ip < end; ip++) {
			chl = to_shortname_char(nls, charbuf, sizeof(charbuf),
						ip, &ext_info);
			if (chl == 0)
				continue;

			if ((extlen + chl) > 3) {
				is_shortname = 0;
				break;
			}
			for (chi = 0; chi < chl; chi++) {
				*p++ = charbuf[chi];
				extlen++;
			}
			if (extlen >= 3) {
				if (ip + 1 != end)
					is_shortname = 0;
				break;
			}
		}
	}
	ext[extlen] = '\0';
	base[baselen] = '\0';

	/* Yes, it can happen. ".\xe5" would do it. */
	if (base[0] == 0xe5)
		base[0] = 0x05;

	/* OK, at this point we know that base is not longer than 8 symbols,
	 * ext is not longer than 3, base is nonempty, both don't contain
	 * any bad symbols (lowercase transformed to uppercase).
	 */

	memset(name_res, ' ', 11);
	memcpy(name_res, base, baselen);
	memcpy(name_res + 8, ext, extlen);

	if (is_shortname && base_info.valid && ext_info.valid) {
		init_dirsearch(&ds,disk,(fatfs_node_t*)dir,name_res);
		if (fatfs_find(&ds)!=)
			return EEXIST;
	}

	/*
	 * Try to find a unique extension.  This used to
	 * iterate through all possibilities sequentially,
	 * but that gave extremely bad performance.  Windows
	 * only tries a few cases before using random
	 * values for part of the base.
	 */

	if (baselen > 6) {
		baselen = numtail_baselen;
		name_res[7] = ' ';
	}
	name_res[baselen] = '~';
	for (i = 1; i < 10; i++) {
		name_res[baselen + 1] = i + '0';
		init_dirsearch(&ds,disk,(fatfs_node_t*)dir,name_res);
		if (fatfs_find(&ds)!=ENOERR)
			return EEXIST;
	}

	i = jiffies & 0xffff;
	sz = (jiffies >> 16) & 0x7;
	if (baselen > 2) {
		baselen = numtail2_baselen;
		name_res[7] = ' ';
	}
	name_res[baselen + 4] = '~';
	name_res[baselen + 5] = '1' + sz;
	while (1) {
		sprintf(buf, "%04X", i);
		memcpy(&name_res[baselen], buf, 4);

		init_dirsearch(&ds,disk,(fatfs_node_t*)dir,name_res);
		if (fatfs_find(&ds)!=ENOERR)
			return EEXIST;
		i -= 11;
	}
	return 0;
}
/* Translate a string, including coded sequences into Unicode */
int
xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
	     int *longlen, int *outlen)
{
	const unsigned char *ip;
	unsigned char nc;
	unsigned char *op;
	unsigned int ec;
	int i, k, fill;
	int charlen;


		int name_len = strlen(name);

		*outlen = utf8_mbstowcs((wchar_t *)outname, name, PAGE_SIZE);

		/*
		 * We stripped '.'s before and set len appropriately,
		 * but utf8_mbstowcs doesn't care about len
		 */
		*outlen -= (name_len - len);

		op = &outname[*outlen * sizeof(wchar_t)];
	
	
	if (*outlen > 260)
		return -ENAMETOOLONG;

	*longlen = *outlen;
	if (*outlen % 13) {
		*op++ = 0;
		*op++ = 0;
		*outlen += 1;
		if (*outlen % 13) {
			fill = 13 - (*outlen % 13);
			for (i = 0; i < fill; i++) {
				*op++ = 0xff;
				*op++ = 0xff;
			}
			*outlen += fill;
		}
	}

	return 0;
}