1
linux/lib/string.c
Michael Holzheu 66f6958e69 lib/string.c: fix strim() semantics for strings that have only blanks
Commit 84c95c9acf ("string: on strstrip(), first remove leading spaces
before running over str") improved the performance of the strim()
function.

Unfortunately this changed the semantics of strim() and broke my code.
Before the patch it was possible to use strim() without using the return
value for removing trailing spaces from strings that had either only
blanks or only trailing blanks.

Now this does not work any longer for strings that *only* have blanks.

Before patch: "   " -> ""    (empty string)
After patch:  "   " -> "   " (no change)

I think we should remove your patch to restore the old behavior.

The description (lib/string.c):

 * Note that the first trailing whitespace is replaced with a %NUL-terminator

=> The first trailing whitespace of a string that only has whitespace
   characters is the first whitespace

The patch restores the old strim() semantics.

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Andre Goddard Rosa <andre.goddard@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-10-31 17:30:56 -07:00

812 lines
16 KiB
C

/*
* linux/lib/string.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* stupid library routines.. The optimized versions should generally be found
* as inline code in <asm-xx/string.h>
*
* These are buggy as well..
*
* * Fri Jun 25 1999, Ingo Oeser <ioe@informatik.tu-chemnitz.de>
* - Added strsep() which will replace strtok() soon (because strsep() is
* reentrant and should be faster). Use only strsep() in new code, please.
*
* * Sat Feb 09 2002, Jason Thomas <jason@topic.com.au>,
* Matthew Hawkins <matt@mh.dropbear.id.au>
* - Kissed strtok() goodbye
*/
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/module.h>
#ifndef __HAVE_ARCH_STRNICMP
/**
* strnicmp - Case insensitive, length-limited string comparison
* @s1: One string
* @s2: The other string
* @len: the maximum number of characters to compare
*/
int strnicmp(const char *s1, const char *s2, size_t len)
{
/* Yes, Virginia, it had better be unsigned */
unsigned char c1, c2;
if (!len)
return 0;
do {
c1 = *s1++;
c2 = *s2++;
if (!c1 || !c2)
break;
if (c1 == c2)
continue;
c1 = tolower(c1);
c2 = tolower(c2);
if (c1 != c2)
break;
} while (--len);
return (int)c1 - (int)c2;
}
EXPORT_SYMBOL(strnicmp);
#endif
#ifndef __HAVE_ARCH_STRCASECMP
int strcasecmp(const char *s1, const char *s2)
{
int c1, c2;
do {
c1 = tolower(*s1++);
c2 = tolower(*s2++);
} while (c1 == c2 && c1 != 0);
return c1 - c2;
}
EXPORT_SYMBOL(strcasecmp);
#endif
#ifndef __HAVE_ARCH_STRNCASECMP
int strncasecmp(const char *s1, const char *s2, size_t n)
{
int c1, c2;
do {
c1 = tolower(*s1++);
c2 = tolower(*s2++);
} while ((--n > 0) && c1 == c2 && c1 != 0);
return c1 - c2;
}
EXPORT_SYMBOL(strncasecmp);
#endif
#ifndef __HAVE_ARCH_STRCPY
/**
* strcpy - Copy a %NUL terminated string
* @dest: Where to copy the string to
* @src: Where to copy the string from
*/
#undef strcpy
char *strcpy(char *dest, const char *src)
{
char *tmp = dest;
while ((*dest++ = *src++) != '\0')
/* nothing */;
return tmp;
}
EXPORT_SYMBOL(strcpy);
#endif
#ifndef __HAVE_ARCH_STRNCPY
/**
* strncpy - Copy a length-limited, %NUL-terminated string
* @dest: Where to copy the string to
* @src: Where to copy the string from
* @count: The maximum number of bytes to copy
*
* The result is not %NUL-terminated if the source exceeds
* @count bytes.
*
* In the case where the length of @src is less than that of
* count, the remainder of @dest will be padded with %NUL.
*
*/
char *strncpy(char *dest, const char *src, size_t count)
{
char *tmp = dest;
while (count) {
if ((*tmp = *src) != 0)
src++;
tmp++;
count--;
}
return dest;
}
EXPORT_SYMBOL(strncpy);
#endif
#ifndef __HAVE_ARCH_STRLCPY
/**
* strlcpy - Copy a %NUL terminated string into a sized buffer
* @dest: Where to copy the string to
* @src: Where to copy the string from
* @size: size of destination buffer
*
* Compatible with *BSD: the result is always a valid
* NUL-terminated string that fits in the buffer (unless,
* of course, the buffer size is zero). It does not pad
* out the result like strncpy() does.
*/
size_t strlcpy(char *dest, const char *src, size_t size)
{
size_t ret = strlen(src);
if (size) {
size_t len = (ret >= size) ? size - 1 : ret;
memcpy(dest, src, len);
dest[len] = '\0';
}
return ret;
}
EXPORT_SYMBOL(strlcpy);
#endif
#ifndef __HAVE_ARCH_STRCAT
/**
* strcat - Append one %NUL-terminated string to another
* @dest: The string to be appended to
* @src: The string to append to it
*/
#undef strcat
char *strcat(char *dest, const char *src)
{
char *tmp = dest;
while (*dest)
dest++;
while ((*dest++ = *src++) != '\0')
;
return tmp;
}
EXPORT_SYMBOL(strcat);
#endif
#ifndef __HAVE_ARCH_STRNCAT
/**
* strncat - Append a length-limited, %NUL-terminated string to another
* @dest: The string to be appended to
* @src: The string to append to it
* @count: The maximum numbers of bytes to copy
*
* Note that in contrast to strncpy(), strncat() ensures the result is
* terminated.
*/
char *strncat(char *dest, const char *src, size_t count)
{
char *tmp = dest;
if (count) {
while (*dest)
dest++;
while ((*dest++ = *src++) != 0) {
if (--count == 0) {
*dest = '\0';
break;
}
}
}
return tmp;
}
EXPORT_SYMBOL(strncat);
#endif
#ifndef __HAVE_ARCH_STRLCAT
/**
* strlcat - Append a length-limited, %NUL-terminated string to another
* @dest: The string to be appended to
* @src: The string to append to it
* @count: The size of the destination buffer.
*/
size_t strlcat(char *dest, const char *src, size_t count)
{
size_t dsize = strlen(dest);
size_t len = strlen(src);
size_t res = dsize + len;
/* This would be a bug */
BUG_ON(dsize >= count);
dest += dsize;
count -= dsize;
if (len >= count)
len = count-1;
memcpy(dest, src, len);
dest[len] = 0;
return res;
}
EXPORT_SYMBOL(strlcat);
#endif
#ifndef __HAVE_ARCH_STRCMP
/**
* strcmp - Compare two strings
* @cs: One string
* @ct: Another string
*/
#undef strcmp
int strcmp(const char *cs, const char *ct)
{
unsigned char c1, c2;
while (1) {
c1 = *cs++;
c2 = *ct++;
if (c1 != c2)
return c1 < c2 ? -1 : 1;
if (!c1)
break;
}
return 0;
}
EXPORT_SYMBOL(strcmp);
#endif
#ifndef __HAVE_ARCH_STRNCMP
/**
* strncmp - Compare two length-limited strings
* @cs: One string
* @ct: Another string
* @count: The maximum number of bytes to compare
*/
int strncmp(const char *cs, const char *ct, size_t count)
{
unsigned char c1, c2;
while (count) {
c1 = *cs++;
c2 = *ct++;
if (c1 != c2)
return c1 < c2 ? -1 : 1;
if (!c1)
break;
count--;
}
return 0;
}
EXPORT_SYMBOL(strncmp);
#endif
#ifndef __HAVE_ARCH_STRCHR
/**
* strchr - Find the first occurrence of a character in a string
* @s: The string to be searched
* @c: The character to search for
*/
char *strchr(const char *s, int c)
{
for (; *s != (char)c; ++s)
if (*s == '\0')
return NULL;
return (char *)s;
}
EXPORT_SYMBOL(strchr);
#endif
#ifndef __HAVE_ARCH_STRRCHR
/**
* strrchr - Find the last occurrence of a character in a string
* @s: The string to be searched
* @c: The character to search for
*/
char *strrchr(const char *s, int c)
{
const char *p = s + strlen(s);
do {
if (*p == (char)c)
return (char *)p;
} while (--p >= s);
return NULL;
}
EXPORT_SYMBOL(strrchr);
#endif
#ifndef __HAVE_ARCH_STRNCHR
/**
* strnchr - Find a character in a length limited string
* @s: The string to be searched
* @count: The number of characters to be searched
* @c: The character to search for
*/
char *strnchr(const char *s, size_t count, int c)
{
for (; count-- && *s != '\0'; ++s)
if (*s == (char)c)
return (char *)s;
return NULL;
}
EXPORT_SYMBOL(strnchr);
#endif
/**
* skip_spaces - Removes leading whitespace from @str.
* @str: The string to be stripped.
*
* Returns a pointer to the first non-whitespace character in @str.
*/
char *skip_spaces(const char *str)
{
while (isspace(*str))
++str;
return (char *)str;
}
EXPORT_SYMBOL(skip_spaces);
/**
* strim - Removes leading and trailing whitespace from @s.
* @s: The string to be stripped.
*
* Note that the first trailing whitespace is replaced with a %NUL-terminator
* in the given string @s. Returns a pointer to the first non-whitespace
* character in @s.
*/
char *strim(char *s)
{
size_t size;
char *end;
size = strlen(s);
if (!size)
return s;
end = s + size - 1;
while (end >= s && isspace(*end))
end--;
*(end + 1) = '\0';
return skip_spaces(s);
}
EXPORT_SYMBOL(strim);
#ifndef __HAVE_ARCH_STRLEN
/**
* strlen - Find the length of a string
* @s: The string to be sized
*/
size_t strlen(const char *s)
{
const char *sc;
for (sc = s; *sc != '\0'; ++sc)
/* nothing */;
return sc - s;
}
EXPORT_SYMBOL(strlen);
#endif
#ifndef __HAVE_ARCH_STRNLEN
/**
* strnlen - Find the length of a length-limited string
* @s: The string to be sized
* @count: The maximum number of bytes to search
*/
size_t strnlen(const char *s, size_t count)
{
const char *sc;
for (sc = s; count-- && *sc != '\0'; ++sc)
/* nothing */;
return sc - s;
}
EXPORT_SYMBOL(strnlen);
#endif
#ifndef __HAVE_ARCH_STRSPN
/**
* strspn - Calculate the length of the initial substring of @s which only contain letters in @accept
* @s: The string to be searched
* @accept: The string to search for
*/
size_t strspn(const char *s, const char *accept)
{
const char *p;
const char *a;
size_t count = 0;
for (p = s; *p != '\0'; ++p) {
for (a = accept; *a != '\0'; ++a) {
if (*p == *a)
break;
}
if (*a == '\0')
return count;
++count;
}
return count;
}
EXPORT_SYMBOL(strspn);
#endif
#ifndef __HAVE_ARCH_STRCSPN
/**
* strcspn - Calculate the length of the initial substring of @s which does not contain letters in @reject
* @s: The string to be searched
* @reject: The string to avoid
*/
size_t strcspn(const char *s, const char *reject)
{
const char *p;
const char *r;
size_t count = 0;
for (p = s; *p != '\0'; ++p) {
for (r = reject; *r != '\0'; ++r) {
if (*p == *r)
return count;
}
++count;
}
return count;
}
EXPORT_SYMBOL(strcspn);
#endif
#ifndef __HAVE_ARCH_STRPBRK
/**
* strpbrk - Find the first occurrence of a set of characters
* @cs: The string to be searched
* @ct: The characters to search for
*/
char *strpbrk(const char *cs, const char *ct)
{
const char *sc1, *sc2;
for (sc1 = cs; *sc1 != '\0'; ++sc1) {
for (sc2 = ct; *sc2 != '\0'; ++sc2) {
if (*sc1 == *sc2)
return (char *)sc1;
}
}
return NULL;
}
EXPORT_SYMBOL(strpbrk);
#endif
#ifndef __HAVE_ARCH_STRSEP
/**
* strsep - Split a string into tokens
* @s: The string to be searched
* @ct: The characters to search for
*
* strsep() updates @s to point after the token, ready for the next call.
*
* It returns empty tokens, too, behaving exactly like the libc function
* of that name. In fact, it was stolen from glibc2 and de-fancy-fied.
* Same semantics, slimmer shape. ;)
*/
char *strsep(char **s, const char *ct)
{
char *sbegin = *s;
char *end;
if (sbegin == NULL)
return NULL;
end = strpbrk(sbegin, ct);
if (end)
*end++ = '\0';
*s = end;
return sbegin;
}
EXPORT_SYMBOL(strsep);
#endif
/**
* sysfs_streq - return true if strings are equal, modulo trailing newline
* @s1: one string
* @s2: another string
*
* This routine returns true iff two strings are equal, treating both
* NUL and newline-then-NUL as equivalent string terminations. It's
* geared for use with sysfs input strings, which generally terminate
* with newlines but are compared against values without newlines.
*/
bool sysfs_streq(const char *s1, const char *s2)
{
while (*s1 && *s1 == *s2) {
s1++;
s2++;
}
if (*s1 == *s2)
return true;
if (!*s1 && *s2 == '\n' && !s2[1])
return true;
if (*s1 == '\n' && !s1[1] && !*s2)
return true;
return false;
}
EXPORT_SYMBOL(sysfs_streq);
/**
* strtobool - convert common user inputs into boolean values
* @s: input string
* @res: result
*
* This routine returns 0 iff the first character is one of 'Yy1Nn0'.
* Otherwise it will return -EINVAL. Value pointed to by res is
* updated upon finding a match.
*/
int strtobool(const char *s, bool *res)
{
switch (s[0]) {
case 'y':
case 'Y':
case '1':
*res = true;
break;
case 'n':
case 'N':
case '0':
*res = false;
break;
default:
return -EINVAL;
}
return 0;
}
EXPORT_SYMBOL(strtobool);
#ifndef __HAVE_ARCH_MEMSET
/**
* memset - Fill a region of memory with the given value
* @s: Pointer to the start of the area.
* @c: The byte to fill the area with
* @count: The size of the area.
*
* Do not use memset() to access IO space, use memset_io() instead.
*/
void *memset(void *s, int c, size_t count)
{
char *xs = s;
while (count--)
*xs++ = c;
return s;
}
EXPORT_SYMBOL(memset);
#endif
#ifndef __HAVE_ARCH_MEMCPY
/**
* memcpy - Copy one area of memory to another
* @dest: Where to copy to
* @src: Where to copy from
* @count: The size of the area.
*
* You should not use this function to access IO space, use memcpy_toio()
* or memcpy_fromio() instead.
*/
void *memcpy(void *dest, const void *src, size_t count)
{
char *tmp = dest;
const char *s = src;
while (count--)
*tmp++ = *s++;
return dest;
}
EXPORT_SYMBOL(memcpy);
#endif
#ifndef __HAVE_ARCH_MEMMOVE
/**
* memmove - Copy one area of memory to another
* @dest: Where to copy to
* @src: Where to copy from
* @count: The size of the area.
*
* Unlike memcpy(), memmove() copes with overlapping areas.
*/
void *memmove(void *dest, const void *src, size_t count)
{
char *tmp;
const char *s;
if (dest <= src) {
tmp = dest;
s = src;
while (count--)
*tmp++ = *s++;
} else {
tmp = dest;
tmp += count;
s = src;
s += count;
while (count--)
*--tmp = *--s;
}
return dest;
}
EXPORT_SYMBOL(memmove);
#endif
#ifndef __HAVE_ARCH_MEMCMP
/**
* memcmp - Compare two areas of memory
* @cs: One area of memory
* @ct: Another area of memory
* @count: The size of the area.
*/
#undef memcmp
int memcmp(const void *cs, const void *ct, size_t count)
{
const unsigned char *su1, *su2;
int res = 0;
for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--)
if ((res = *su1 - *su2) != 0)
break;
return res;
}
EXPORT_SYMBOL(memcmp);
#endif
#ifndef __HAVE_ARCH_MEMSCAN
/**
* memscan - Find a character in an area of memory.
* @addr: The memory area
* @c: The byte to search for
* @size: The size of the area.
*
* returns the address of the first occurrence of @c, or 1 byte past
* the area if @c is not found
*/
void *memscan(void *addr, int c, size_t size)
{
unsigned char *p = addr;
while (size) {
if (*p == c)
return (void *)p;
p++;
size--;
}
return (void *)p;
}
EXPORT_SYMBOL(memscan);
#endif
#ifndef __HAVE_ARCH_STRSTR
/**
* strstr - Find the first substring in a %NUL terminated string
* @s1: The string to be searched
* @s2: The string to search for
*/
char *strstr(const char *s1, const char *s2)
{
size_t l1, l2;
l2 = strlen(s2);
if (!l2)
return (char *)s1;
l1 = strlen(s1);
while (l1 >= l2) {
l1--;
if (!memcmp(s1, s2, l2))
return (char *)s1;
s1++;
}
return NULL;
}
EXPORT_SYMBOL(strstr);
#endif
#ifndef __HAVE_ARCH_STRNSTR
/**
* strnstr - Find the first substring in a length-limited string
* @s1: The string to be searched
* @s2: The string to search for
* @len: the maximum number of characters to search
*/
char *strnstr(const char *s1, const char *s2, size_t len)
{
size_t l2;
l2 = strlen(s2);
if (!l2)
return (char *)s1;
while (len >= l2) {
len--;
if (!memcmp(s1, s2, l2))
return (char *)s1;
s1++;
}
return NULL;
}
EXPORT_SYMBOL(strnstr);
#endif
#ifndef __HAVE_ARCH_MEMCHR
/**
* memchr - Find a character in an area of memory.
* @s: The memory area
* @c: The byte to search for
* @n: The size of the area.
*
* returns the address of the first occurrence of @c, or %NULL
* if @c is not found
*/
void *memchr(const void *s, int c, size_t n)
{
const unsigned char *p = s;
while (n-- != 0) {
if ((unsigned char)c == *p++) {
return (void *)(p - 1);
}
}
return NULL;
}
EXPORT_SYMBOL(memchr);
#endif
static void *check_bytes8(const u8 *start, u8 value, unsigned int bytes)
{
while (bytes) {
if (*start != value)
return (void *)start;
start++;
bytes--;
}
return NULL;
}
/**
* memchr_inv - Find an unmatching character in an area of memory.
* @start: The memory area
* @c: Find a character other than c
* @bytes: The size of the area.
*
* returns the address of the first character other than @c, or %NULL
* if the whole buffer contains just @c.
*/
void *memchr_inv(const void *start, int c, size_t bytes)
{
u8 value = c;
u64 value64;
unsigned int words, prefix;
if (bytes <= 16)
return check_bytes8(start, value, bytes);
value64 = value | value << 8 | value << 16 | value << 24;
value64 = (value64 & 0xffffffff) | value64 << 32;
prefix = 8 - ((unsigned long)start) % 8;
if (prefix) {
u8 *r = check_bytes8(start, value, prefix);
if (r)
return r;
start += prefix;
bytes -= prefix;
}
words = bytes / 8;
while (words) {
if (*(u64 *)start != value64)
return check_bytes8(start, value, 8);
start += 8;
words--;
}
return check_bytes8(start, value, bytes % 8);
}
EXPORT_SYMBOL(memchr_inv);