Related
Is there a clean, preferably standard method of trimming leading and trailing whitespace from a string in C? I'd roll my own, but I would think this is a common problem with an equally common solution.
If you can modify the string:
// Note: This function returns a pointer to a substring of the original string.
// If the given string was allocated dynamically, the caller must not overwrite
// that pointer with the returned value, since the original pointer must be
// deallocated using the same allocator with which it was allocated. The return
// value must NOT be deallocated using free() etc.
char *trimwhitespace(char *str)
{
char *end;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
return str;
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
// Write new null terminator character
end[1] = '\0';
return str;
}
If you can't modify the string, then you can use basically the same method:
// Stores the trimmed input string into the given output buffer, which must be
// large enough to store the result. If it is too small, the output is
// truncated.
size_t trimwhitespace(char *out, size_t len, const char *str)
{
if(len == 0)
return 0;
const char *end;
size_t out_size;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
{
*out = 0;
return 1;
}
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
end++;
// Set output size to minimum of trimmed string length and buffer size minus 1
out_size = (end - str) < len-1 ? (end - str) : len-1;
// Copy trimmed string and add null terminator
memcpy(out, str, out_size);
out[out_size] = 0;
return out_size;
}
Here's one that shifts the string into the first position of your buffer. You might want this behavior so that if you dynamically allocated the string, you can still free it on the same pointer that trim() returns:
char *trim(char *str)
{
size_t len = 0;
char *frontp = str;
char *endp = NULL;
if( str == NULL ) { return NULL; }
if( str[0] == '\0' ) { return str; }
len = strlen(str);
endp = str + len;
/* Move the front and back pointers to address the first non-whitespace
* characters from each end.
*/
while( isspace((unsigned char) *frontp) ) { ++frontp; }
if( endp != frontp )
{
while( isspace((unsigned char) *(--endp)) && endp != frontp ) {}
}
if( frontp != str && endp == frontp )
*str = '\0';
else if( str + len - 1 != endp )
*(endp + 1) = '\0';
/* Shift the string so that it starts at str so that if it's dynamically
* allocated, we can still free it on the returned pointer. Note the reuse
* of endp to mean the front of the string buffer now.
*/
endp = str;
if( frontp != str )
{
while( *frontp ) { *endp++ = *frontp++; }
*endp = '\0';
}
return str;
}
Test for correctness:
#include <stdio.h>
#include <string.h>
#include <ctype.h>
/* Paste function from above here. */
int main()
{
/* The test prints the following:
[nothing to trim] -> [nothing to trim]
[ trim the front] -> [trim the front]
[trim the back ] -> [trim the back]
[ trim front and back ] -> [trim front and back]
[ trim one char front and back ] -> [trim one char front and back]
[ trim one char front] -> [trim one char front]
[trim one char back ] -> [trim one char back]
[ ] -> []
[ ] -> []
[a] -> [a]
[] -> []
*/
char *sample_strings[] =
{
"nothing to trim",
" trim the front",
"trim the back ",
" trim front and back ",
" trim one char front and back ",
" trim one char front",
"trim one char back ",
" ",
" ",
"a",
"",
NULL
};
char test_buffer[64];
char comparison_buffer[64];
size_t index, compare_pos;
for( index = 0; sample_strings[index] != NULL; ++index )
{
// Fill buffer with known value to verify we do not write past the end of the string.
memset( test_buffer, 0xCC, sizeof(test_buffer) );
strcpy( test_buffer, sample_strings[index] );
memcpy( comparison_buffer, test_buffer, sizeof(comparison_buffer));
printf("[%s] -> [%s]\n", sample_strings[index],
trim(test_buffer));
for( compare_pos = strlen(comparison_buffer);
compare_pos < sizeof(comparison_buffer);
++compare_pos )
{
if( test_buffer[compare_pos] != comparison_buffer[compare_pos] )
{
printf("Unexpected change to buffer # index %u: %02x (expected %02x)\n",
compare_pos, (unsigned char) test_buffer[compare_pos], (unsigned char) comparison_buffer[compare_pos]);
}
}
}
return 0;
}
Source file was trim.c. Compiled with 'cc -Wall trim.c -o trim'.
My solution. String must be changeable. The advantage above some of the other solutions that it moves the non-space part to the beginning so you can keep using the old pointer, in case you have to free() it later.
void trim(char * s) {
char * p = s;
int l = strlen(p);
while(isspace(p[l - 1])) p[--l] = 0;
while(* p && isspace(* p)) ++p, --l;
memmove(s, p, l + 1);
}
This version creates a copy of the string with strndup() instead of editing it in place. strndup() requires _GNU_SOURCE, so maybe you need to make your own strndup() with malloc() and strncpy().
char * trim(char * s) {
int l = strlen(s);
while(isspace(s[l - 1])) --l;
while(* s && isspace(* s)) ++s, --l;
return strndup(s, l);
}
Here's my C mini library for trimming left, right, both, all, in place and separate, and trimming a set of specified characters (or white space by default).
contents of strlib.h:
#ifndef STRLIB_H_
#define STRLIB_H_ 1
enum strtrim_mode_t {
STRLIB_MODE_ALL = 0,
STRLIB_MODE_RIGHT = 0x01,
STRLIB_MODE_LEFT = 0x02,
STRLIB_MODE_BOTH = 0x03
};
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
);
char *strtriml(char *d, char *s);
char *strtrimr(char *d, char *s);
char *strtrim(char *d, char *s);
char *strkill(char *d, char *s);
char *triml(char *s);
char *trimr(char *s);
char *trim(char *s);
char *kill(char *s);
#endif
contents of strlib.c:
#include <strlib.h>
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
) {
char *o = d; // save orig
char *e = 0; // end space ptr.
char dtab[256] = {0};
if (!s || !d) return 0;
if (!delim) delim = " \t\n\f";
while (*delim)
dtab[*delim++] = 1;
while ( (*d = *s++) != 0 ) {
if (!dtab[0xFF & (unsigned int)*d]) { // Not a match char
e = 0; // Reset end pointer
} else {
if (!e) e = d; // Found first match.
if ( mode == STRLIB_MODE_ALL || ((mode != STRLIB_MODE_RIGHT) && (d == o)) )
continue;
}
d++;
}
if (mode != STRLIB_MODE_LEFT && e) { // for everything but trim_left, delete trailing matches.
*e = 0;
}
return o;
}
// perhaps these could be inlined in strlib.h
char *strtriml(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_LEFT, 0); }
char *strtrimr(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_RIGHT, 0); }
char *strtrim(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_BOTH, 0); }
char *strkill(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_ALL, 0); }
char *triml(char *s) { return strcpytrim(s, s, STRLIB_MODE_LEFT, 0); }
char *trimr(char *s) { return strcpytrim(s, s, STRLIB_MODE_RIGHT, 0); }
char *trim(char *s) { return strcpytrim(s, s, STRLIB_MODE_BOTH, 0); }
char *kill(char *s) { return strcpytrim(s, s, STRLIB_MODE_ALL, 0); }
The one main routine does it all.
It trims in place if src == dst, otherwise,
it works like the strcpy routines.
It trims a set of characters specified in the string delim, or white space if null.
It trims left, right, both, and all (like tr).
There is not much to it, and it iterates over the string only once. Some folks might complain that trim right starts on the left, however, no strlen is needed which starts on the left anyway. (One way or another you have to get to the end of the string for right trims, so you might as well do the work as you go.) There may be arguments to be made about pipelining and cache sizes and such -- who knows. Since the solution works from left to right and iterates only once, it can be expanded to work on streams as well. Limitations: it does not work on unicode strings.
Here is my attempt at a simple, yet correct in-place trim function.
void trim(char *str)
{
int i;
int begin = 0;
int end = strlen(str) - 1;
while (isspace((unsigned char) str[begin]))
begin++;
while ((end >= begin) && isspace((unsigned char) str[end]))
end--;
// Shift all characters back to the start of the string array.
for (i = begin; i <= end; i++)
str[i - begin] = str[i];
str[i - begin] = '\0'; // Null terminate string.
}
Late to the trim party
Features:
1. Trim the beginning quickly, as in a number of other answers.
2. After going to the end, trimming the right with only 1 test per loop. Like #jfm3, but works for an all white-space string)
3. To avoid undefined behavior when char is a signed char, cast *s to unsigned char.
Character handling "In all cases the argument is an int, the value of which shall be representable as an unsigned char or shall equal the value of the macro EOF. If the argument has any other value, the behavior is undefined." C11 §7.4 1
#include <ctype.h>
// Return a pointer to the trimmed string
char *string_trim_inplace(char *s) {
while (isspace((unsigned char) *s)) s++;
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
}
// If desired, shift the trimmed string
return s;
}
#chqrlie commented the above does not shift the trimmed string. To do so....
// Return a pointer to the (shifted) trimmed string
char *string_trim_inplace(char *s) {
char *original = s;
size_t len = 0;
while (isspace((unsigned char) *s)) {
s++;
}
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
// len = (size_t) (p - s); // older errant code
len = (size_t) (p - s + 1); // Thanks to #theriver
}
return (s == original) ? s : memmove(original, s, len + 1);
}
Here's a solution similar to #adam-rosenfields in-place modification routine but without needlessly resorting to strlen(). Like #jkramer, the string is left-adjusted within the buffer so you can free the same pointer. Not optimal for large strings since it does not use memmove. Includes the ++/-- operators that #jfm3 mentions. FCTX-based unit tests included.
#include <ctype.h>
void trim(char * const a)
{
char *p = a, *q = a;
while (isspace(*q)) ++q;
while (*q) *p++ = *q++;
*p = '\0';
while (p > a && isspace(*--p)) *p = '\0';
}
/* See http://fctx.wildbearsoftware.com/ */
#include "fct.h"
FCT_BGN()
{
FCT_QTEST_BGN(trim)
{
{ char s[] = ""; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = " "; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "\t"; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "a"; trim(s); fct_chk_eq_str("a", s); } // NOP
{ char s[] = "abc"; trim(s); fct_chk_eq_str("abc", s); } // NOP
{ char s[] = " a"; trim(s); fct_chk_eq_str("a", s); } // Leading
{ char s[] = " a c"; trim(s); fct_chk_eq_str("a c", s); } // Leading
{ char s[] = "a "; trim(s); fct_chk_eq_str("a", s); } // Trailing
{ char s[] = "a c "; trim(s); fct_chk_eq_str("a c", s); } // Trailing
{ char s[] = " a "; trim(s); fct_chk_eq_str("a", s); } // Both
{ char s[] = " a c "; trim(s); fct_chk_eq_str("a c", s); } // Both
// Villemoes pointed out an edge case that corrupted memory. Thank you.
// http://stackoverflow.com/questions/122616/#comment23332594_4505533
{
char s[] = "a "; // Buffer with whitespace before s + 2
trim(s + 2); // Trim " " containing only whitespace
fct_chk_eq_str("", s + 2); // Ensure correct result from the trim
fct_chk_eq_str("a ", s); // Ensure preceding buffer not mutated
}
// doukremt suggested I investigate this test case but
// did not indicate the specific behavior that was objectionable.
// http://stackoverflow.com/posts/comments/33571430
{
char s[] = " foobar"; // Shifted across whitespace
trim(s); // Trim
fct_chk_eq_str("foobar", s); // Leading string is correct
// Here is what the algorithm produces:
char r[16] = { 'f', 'o', 'o', 'b', 'a', 'r', '\0', ' ',
' ', 'f', 'o', 'o', 'b', 'a', 'r', '\0'};
fct_chk_eq_int(0, memcmp(s, r, sizeof(s)));
}
}
FCT_QTEST_END();
}
FCT_END();
I'm not sure what you consider "painless."
C strings are pretty painful. We can find the first non-whitespace character position trivially:
while (isspace(* p)) p++;
We can find the last non-whitespace character position with two similar trivial moves:
while (* q) q++;
do { q--; } while (isspace(* q));
(I have spared you the pain of using the * and ++ operators at the same time.)
The question now is what do you do with this? The datatype at hand isn't really a big robust abstract String that is easy to think about, but instead really barely any more than an array of storage bytes. Lacking a robust data type, it is impossible to write a function that will do the same as PHperytonby's chomp function. What would such a function in C return?
Another one, with one line doing the real job:
#include <stdio.h>
int main()
{
const char *target = " haha ";
char buf[256];
sscanf(target, "%s", buf); // Trimming on both sides occurs here
printf("<%s>\n", buf);
}
If you're using glib, then you can use g_strstrip
I didn't like most of these answers because they did one or more of the following...
Returned a different pointer inside the original pointer's string (kind of a pain to juggle two different pointers to the same thing).
Made gratuitous use of things like strlen() that pre-iterate the entire string.
Used non-portable OS-specific lib functions.
Backscanned.
Used comparison to ' ' instead of isspace() so that TAB / CR / LF are preserved.
Wasted memory with large static buffers.
Wasted cycles with high-cost functions like sscanf/sprintf.
Here is my version:
void fnStrTrimInPlace(char *szWrite) {
const char *szWriteOrig = szWrite;
char *szLastSpace = szWrite, *szRead = szWrite;
int bNotSpace;
// SHIFT STRING, STARTING AT FIRST NON-SPACE CHAR, LEFTMOST
while( *szRead != '\0' ) {
bNotSpace = !isspace((unsigned char)(*szRead));
if( (szWrite != szWriteOrig) || bNotSpace ) {
*szWrite = *szRead;
szWrite++;
// TRACK POINTER TO LAST NON-SPACE
if( bNotSpace )
szLastSpace = szWrite;
}
szRead++;
}
// TERMINATE AFTER LAST NON-SPACE (OR BEGINNING IF THERE WAS NO NON-SPACE)
*szLastSpace = '\0';
}
Use a string library, for instance:
Ustr *s1 = USTR1(\7, " 12345 ");
ustr_sc_trim_cstr(&s1, " ");
assert(ustr_cmp_cstr_eq(s1, "12345"));
...as you say this is a "common" problem, yes you need to include a #include or so and it's not included in libc but don't go inventing your own hack job storing random pointers and size_t's that way only leads to buffer overflows.
A bit late to the game, but I'll throw my routines into the fray. They're probably not the most absolute efficient, but I believe they're correct and they're simple (with rtrim() pushing the complexity envelope):
#include <ctype.h>
#include <string.h>
/*
Public domain implementations of in-place string trim functions
Michael Burr
michael.burr#nth-element.com
2010
*/
char* ltrim(char* s)
{
char* newstart = s;
while (isspace( *newstart)) {
++newstart;
}
// newstart points to first non-whitespace char (which might be '\0')
memmove( s, newstart, strlen( newstart) + 1); // don't forget to move the '\0' terminator
return s;
}
char* rtrim( char* s)
{
char* end = s + strlen( s);
// find the last non-whitespace character
while ((end != s) && isspace( *(end-1))) {
--end;
}
// at this point either (end == s) and s is either empty or all whitespace
// so it needs to be made empty, or
// end points just past the last non-whitespace character (it might point
// at the '\0' terminator, in which case there's no problem writing
// another there).
*end = '\0';
return s;
}
char* trim( char* s)
{
return rtrim( ltrim( s));
}
Very late to the party...
Single-pass forward-scanning solution with no backtracking. Every character in the source string is tested exactly once twice. (So it should be faster than most of the other solutions here, especially if the source string has a lot of trailing spaces.)
This includes two solutions, one to copy and trim a source string into another destination string, and the other to trim the source string in place. Both functions use the same code.
The (modifiable) string is moved in-place, so the original pointer to it remains unchanged.
#include <stddef.h>
#include <ctype.h>
char * trim2(char *d, const char *s)
{
// Sanity checks
if (s == NULL || d == NULL)
return NULL;
// Skip leading spaces
const unsigned char * p = (const unsigned char *)s;
while (isspace(*p))
p++;
// Copy the string
unsigned char * dst = (unsigned char *)d; // d and s can be the same
unsigned char * end = dst;
while (*p != '\0')
{
if (!isspace(*dst++ = *p++))
end = dst;
}
// Truncate trailing spaces
*end = '\0';
return d;
}
char * trim(char *s)
{
return trim2(s, s);
}
Just to keep this growing, one more option with a modifiable string:
void trimString(char *string)
{
size_t i = 0, j = strlen(string);
while (j > 0 && isspace((unsigned char)string[j - 1])) string[--j] = '\0';
while (isspace((unsigned char)string[i])) i++;
if (i > 0) memmove(string, string + i, j - i + 1);
}
I know there have many answers, but I post my answer here to see if my solution is good enough.
// Trims leading whitespace chars in left `str`, then copy at almost `n - 1` chars
// into the `out` buffer in which copying might stop when the first '\0' occurs,
// and finally append '\0' to the position of the last non-trailing whitespace char.
// Reture the length the trimed string which '\0' is not count in like strlen().
size_t trim(char *out, size_t n, const char *str)
{
// do nothing
if(n == 0) return 0;
// ptr stop at the first non-leading space char
while(isspace(*str)) str++;
if(*str == '\0') {
out[0] = '\0';
return 0;
}
size_t i = 0;
// copy char to out until '\0' or i == n - 1
for(i = 0; i < n - 1 && *str != '\0'; i++){
out[i] = *str++;
}
// deal with the trailing space
while(isspace(out[--i]));
out[++i] = '\0';
return i;
}
The easiest way to skip leading spaces in a string is, imho,
#include <stdio.h>
int main()
{
char *foo=" teststring ";
char *bar;
sscanf(foo,"%s",bar);
printf("String is >%s<\n",bar);
return 0;
}
Ok this is my take on the question. I believe it's the most concise solution that modifies the string in place (free will work) and avoids any UB. For small strings, it's probably faster than a solution involving memmove.
void stripWS_LT(char *str)
{
char *a = str, *b = str;
while (isspace((unsigned char)*a)) a++;
while (*b = *a++) b++;
while (b > str && isspace((unsigned char)*--b)) *b = 0;
}
#include <ctype.h>
#include <string.h>
char *trim_space(char *in)
{
char *out = NULL;
int len;
if (in) {
len = strlen(in);
while(len && isspace(in[len - 1])) --len;
while(len && *in && isspace(*in)) ++in, --len;
if (len) {
out = strndup(in, len);
}
}
return out;
}
isspace helps to trim all white spaces.
Run a first loop to check from last byte for space character and reduce the length variable
Run a second loop to check from first byte for space character and reduce the length variable and increment char pointer.
Finally if length variable is more than 0, then use strndup to create new string buffer by excluding spaces.
This one is short and simple, uses for-loops and doesn't overwrite the string boundaries.
You can replace the test with isspace() if needed.
void trim (char *s) // trim leading and trailing spaces+tabs
{
int i,j,k, len;
j=k=0;
len = strlen(s);
// find start of string
for (i=0; i<len; i++) if ((s[i]!=32) && (s[i]!=9)) { j=i; break; }
// find end of string+1
for (i=len-1; i>=j; i--) if ((s[i]!=32) && (s[i]!=9)) { k=i+1; break;}
if (k<=j) {s[0]=0; return;} // all whitespace (j==k==0)
len=k-j;
for (i=0; i<len; i++) s[i] = s[j++]; // shift result to start of string
s[i]=0; // end the string
}//_trim
If, and ONLY IF there's only one contiguous block of text between whitespace, you can use a single call to strtok(3), like so:
char *trimmed = strtok(input, "\r\t\n ");
This works for strings like the following:
" +1.123.456.7890 "
" 01-01-2020\n"
"\t2.523"
This will not work for strings that contain whitespace between blocks of non-whitespace, like " hi there ". It's probably better to avoid this approach, but now it's here in your toolbox if you need it.
Personally, I'd roll my own. You can use strtok, but you need to take care with doing so (particularly if you're removing leading characters) that you know what memory is what.
Getting rid of trailing spaces is easy, and pretty safe, as you can just put a 0 in over the top of the last space, counting back from the end. Getting rid of leading spaces means moving things around. If you want to do it in place (probably sensible) you can just keep shifting everything back one character until there's no leading space. Or, to be more efficient, you could find the index of the first non-space character, and shift everything back by that number. Or, you could just use a pointer to the first non-space character (but then you need to be careful in the same way as you do with strtok).
#include "stdafx.h"
#include "malloc.h"
#include "string.h"
int main(int argc, char* argv[])
{
char *ptr = (char*)malloc(sizeof(char)*30);
strcpy(ptr," Hel lo wo rl d G eo rocks!!! by shahil sucks b i g tim e");
int i = 0, j = 0;
while(ptr[j]!='\0')
{
if(ptr[j] == ' ' )
{
j++;
ptr[i] = ptr[j];
}
else
{
i++;
j++;
ptr[i] = ptr[j];
}
}
printf("\noutput-%s\n",ptr);
return 0;
}
Most of the answers so far do one of the following:
Backtrack at the end of the string (i.e. find the end of the string and then seek backwards until a non-space character is found,) or
Call strlen() first, making a second pass through the whole string.
This version makes only one pass and does not backtrack. Hence it may perform better than the others, though only if it is common to have hundreds of trailing spaces (which is not unusual when dealing with the output of a SQL query.)
static char const WHITESPACE[] = " \t\n\r";
static void get_trim_bounds(char const *s,
char const **firstWord,
char const **trailingSpace)
{
char const *lastWord;
*firstWord = lastWord = s + strspn(s, WHITESPACE);
do
{
*trailingSpace = lastWord + strcspn(lastWord, WHITESPACE);
lastWord = *trailingSpace + strspn(*trailingSpace, WHITESPACE);
}
while (*lastWord != '\0');
}
char *copy_trim(char const *s)
{
char const *firstWord, *trailingSpace;
char *result;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
result = malloc(newLength + 1);
memcpy(result, firstWord, newLength);
result[newLength] = '\0';
return result;
}
void inplace_trim(char *s)
{
char const *firstWord, *trailingSpace;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
memmove(s, firstWord, newLength);
s[newLength] = '\0';
}
This is the shortest possible implementation I can think of:
static const char *WhiteSpace=" \n\r\t";
char* trim(char *t)
{
char *e=t+(t!=NULL?strlen(t):0); // *e initially points to end of string
if (t==NULL) return;
do --e; while (strchr(WhiteSpace, *e) && e>=t); // Find last char that is not \r\n\t
*(++e)=0; // Null-terminate
e=t+strspn (t,WhiteSpace); // Find first char that is not \t
return e>t?memmove(t,e,strlen(e)+1):t; // memmove string contents and terminator
}
These functions will modify the original buffer, so if dynamically allocated, the original
pointer can be freed.
#include <string.h>
void rstrip(char *string)
{
int l;
if (!string)
return;
l = strlen(string) - 1;
while (isspace(string[l]) && l >= 0)
string[l--] = 0;
}
void lstrip(char *string)
{
int i, l;
if (!string)
return;
l = strlen(string);
while (isspace(string[(i = 0)]))
while(i++ < l)
string[i-1] = string[i];
}
void strip(char *string)
{
lstrip(string);
rstrip(string);
}
What do you think about using StrTrim function defined in header Shlwapi.h.? It is straight forward rather defining on your own.
Details can be found on:
http://msdn.microsoft.com/en-us/library/windows/desktop/bb773454(v=vs.85).aspx
If you have
char ausCaptain[]="GeorgeBailey ";
StrTrim(ausCaptain," ");
This will give ausCaptain as "GeorgeBailey" not "GeorgeBailey ".
To trim my strings from the both sides I use the oldie but the gooody ;)
It can trim anything with ascii less than a space, meaning that the control chars will be trimmed also !
char *trimAll(char *strData)
{
unsigned int L = strlen(strData);
if(L > 0){ L--; }else{ return strData; }
size_t S = 0, E = L;
while((!(strData[S] > ' ') || !(strData[E] > ' ')) && (S >= 0) && (S <= L) && (E >= 0) && (E <= L))
{
if(strData[S] <= ' '){ S++; }
if(strData[E] <= ' '){ E--; }
}
if(S == 0 && E == L){ return strData; } // Nothing to be done
if((S >= 0) && (S <= L) && (E >= 0) && (E <= L)){
L = E - S + 1;
memmove(strData,&strData[S],L); strData[L] = '\0';
}else{ strData[0] = '\0'; }
return strData;
}
I'm only including code because the code posted so far seems suboptimal (and I don't have the rep to comment yet.)
void inplace_trim(char* s)
{
int start, end = strlen(s);
for (start = 0; isspace(s[start]); ++start) {}
if (s[start]) {
while (end > 0 && isspace(s[end-1]))
--end;
memmove(s, &s[start], end - start);
}
s[end - start] = '\0';
}
char* copy_trim(const char* s)
{
int start, end;
for (start = 0; isspace(s[start]); ++start) {}
for (end = strlen(s); end > 0 && isspace(s[end-1]); --end) {}
return strndup(s + start, end - start);
}
strndup() is a GNU extension. If you don't have it or something equivalent, roll your own. For example:
r = strdup(s + start);
r[end-start] = '\0';
Here i use the dynamic memory allocation to trim the input string to the function trimStr. First, we find how many non-empty characters exist in the input string. Then, we allocate a character array with that size and taking care of the null terminated character. When we use this function, we need to free the memory inside of main function.
#include<stdio.h>
#include<stdlib.h>
char *trimStr(char *str){
char *tmp = str;
printf("input string %s\n",str);
int nc = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
nc++;
}
tmp++;
}
printf("total nonempty characters are %d\n",nc);
char *trim = NULL;
trim = malloc(sizeof(char)*(nc+1));
if (trim == NULL) return NULL;
tmp = str;
int ne = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
trim[ne] = *tmp;
ne++;
}
tmp++;
}
trim[nc] = '\0';
printf("trimmed string is %s\n",trim);
return trim;
}
int main(void){
char str[] = " s ta ck ove r fl o w ";
char *trim = trimStr(str);
if (trim != NULL )free(trim);
return 0;
}
This code finds the next word in the string.
For example
given an input of " my cake" the function should return "my cake". as the expected output
If I use return then the output is (null), but I use printf then the code works
I would like to know how to get the expected output using return.
#include <stdio.h>
int main()
{
char* str[1000];
printf("enter:");
fgets(str,1000,stdin);
printf("%s",find_word_start(str));
}
char* find_word_start(char* str){
char* result[1000];
int c = 0, d = 0;
while(str[c] ==' ') {
c++;
}
while(str[c] != '\0'){
result[d++] = str[c++];
if(str[c]==' ') {
result[d++] = str[c++];
}
while(str[c]==' ') { //
c++;
}
}
result[d] = '\0';
//print or return char?
return result;
}
char* result[1000]; creates an array of 1000 pointers. That's wrong in a number of ways.
You want a block of 1000 chars, not pointers.
Actually, 1000 is not the number of characters you want. You usually want a smaller number, but you could also want a larger number.
You don't want to store the result in automatically allocated memory, because that will be freed as soon as you exit the function. Use malloc (or something that does a malloc such as strdup).
Fix:
// Returns a copy that needs to be freed.
char* find_word_start(const char* src) {
while (*src == ' ')
++src;
size_t len = 0;
while (str[len] != '\0')
++len;
++len; // Include NUL
result = malloc(len);
char* dst = result;
while (len--)
*(dst++) = *(src++);
return result;
}
Well, I was avoiding using string functions above like you did, but they greatly simplify the solution.
// Returns a copy that needs to be freed.
char* find_word_start(const char* src) {
while (*src == ' ')
++src;
return strdup(src);
}
That said, since you return the tail end of the string, you could simply return a pointer into the existing string.
// Returns a pointer into the provided string.
const char* find_word_start(const char* str) {
while (*str == ' ')
++str;
return str;
}
The following line allocates memory space in the stack but after the function ends everything is gone:
char result[1000];
You need to allocate memory in the heap like that:
char *result = malloc(sizeof(char) *1000);
Note: don't forget to free that memory space by free function.
My str_split function returns (or at least I think it does) a char** - so a list of strings essentially. It takes a string parameter, a char delimiter to split the string on, and a pointer to an int to place the number of strings detected.
The way I did it, which may be highly inefficient, is to make a buffer of x length (x = length of string), then copy element of string until we reach delimiter, or '\0' character. Then it copies the buffer to the char**, which is what we are returning (and has been malloced earlier, and can be freed from main()), then clears the buffer and repeats.
Although the algorithm may be iffy, the logic is definitely sound as my debug code (the _D) shows it's being copied correctly. The part I'm stuck on is when I make a char** in main, set it equal to my function. It doesn't return null, crash the program, or throw any errors, but it doesn't quite seem to work either. I'm assuming this is what is meant be the term Undefined Behavior.
Anyhow, after a lot of thinking (I'm new to all this) I tried something else, which you will see in the code, currently commented out. When I use malloc to copy the buffer to a new string, and pass that copy to aforementioned char**, it seems to work perfectly. HOWEVER, this creates an obvious memory leak as I can't free it later... so I'm lost.
When I did some research I found this post, which follows the idea of my code almost exactly and works, meaning there isn't an inherent problem with the format (return value, parameters, etc) of my str_split function. YET his only has 1 malloc, for the char**, and works just fine.
Below is my code. I've been trying to figure this out and it's scrambling my brain, so I'd really appreciate help!! Sorry in advance for the 'i', 'b', 'c' it's a bit convoluted I know.
Edit: should mention that with the following code,
ret[c] = buffer;
printf("Content of ret[%i] = \"%s\" \n", c, ret[c]);
it does indeed print correctly. It's only when I call the function from main that it gets weird. I'm guessing it's because it's out of scope ?
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#define DEBUG
#ifdef DEBUG
#define _D if (1)
#else
#define _D if (0)
#endif
char **str_split(char[], char, int*);
int count_char(char[], char);
int main(void) {
int num_strings = 0;
char **result = str_split("Helo_World_poopy_pants", '_', &num_strings);
if (result == NULL) {
printf("result is NULL\n");
return 0;
}
if (num_strings > 0) {
for (int i = 0; i < num_strings; i++) {
printf("\"%s\" \n", result[i]);
}
}
free(result);
return 0;
}
char **str_split(char string[], char delim, int *num_strings) {
int num_delim = count_char(string, delim);
*num_strings = num_delim + 1;
if (*num_strings < 2) {
return NULL;
}
//return value
char **ret = malloc((*num_strings) * sizeof(char*));
if (ret == NULL) {
_D printf("ret is null.\n");
return NULL;
}
int slen = strlen(string);
char buffer[slen];
/* b is the buffer index, c is the index for **ret */
int b = 0, c = 0;
for (int i = 0; i < slen + 1; i++) {
char cur = string[i];
if (cur == delim || cur == '\0') {
_D printf("Copying content of buffer to ret[%i]\n", c);
//char *tmp = malloc(sizeof(char) * slen + 1);
//strcpy(tmp, buffer);
//ret[c] = tmp;
ret[c] = buffer;
_D printf("Content of ret[%i] = \"%s\" \n", c, ret[c]);
//free(tmp);
c++;
b = 0;
continue;
}
//otherwise
_D printf("{%i} Copying char[%c] to index [%i] of buffer\n", c, cur, b);
buffer[b] = cur;
buffer[b+1] = '\0'; /* extend the null char */
b++;
_D printf("Buffer is now equal to: \"%s\"\n", buffer);
}
return ret;
}
int count_char(char base[], char c) {
int count = 0;
int i = 0;
while (base[i] != '\0') {
if (base[i++] == c) {
count++;
}
}
_D printf("Found %i occurence(s) of '%c'\n", count, c);
return count;
}
You are storing pointers to a buffer that exists on the stack. Using those pointers after returning from the function results in undefined behavior.
To get around this requires one of the following:
Allow the function to modify the input string (i.e. replace delimiters with null-terminator characters) and return pointers into it. The caller must be aware that this can happen. Note that supplying a string literal as you are doing here is illegal in C, so you would instead need to do:
char my_string[] = "Helo_World_poopy_pants";
char **result = str_split(my_string, '_', &num_strings);
In this case, the function should also make it clear that a string literal is not acceptable input, and define its first parameter as const char* string (instead of char string[]).
Allow the function to make a copy of the string and then modify the copy. You have expressed concerns about leaking this memory, but that concern is mostly to do with your program's design rather than a necessity.
It's perfectly valid to duplicate each string individually and then clean them all up later. The main issue is that it's inconvenient, and also slightly pointless.
Let's address the second point. You have several options, but if you insist that the result be easily cleaned-up with a call to free, then try this strategy:
When you allocate the pointer array, also make it large enough to hold a copy of the string:
// Allocate storage for `num_strings` pointers, plus a copy of the original string,
// then copy the string into memory immediately following the pointer storage.
char **ret = malloc((*num_strings) * sizeof(char*) + strlen(string) + 1);
char *buffer = (char*)&ret[*num_strings];
strcpy(buffer, string);
Now, do all your string operations on buffer. For example:
// Extract all delimited substrings. Here, buffer will always point at the
// current substring, and p will search for the delimiter. Once found,
// the substring is terminated, its pointer appended to the substring array,
// and then buffer is pointed at the next substring, if any.
int c = 0;
for(char *p = buffer; *buffer; ++p)
{
if (*p == delim || !*p) {
char *next = p;
if (*p) {
*p = '\0';
++next;
}
ret[c++] = buffer;
buffer = next;
}
}
When you need to clean up, it's just a single call to free, because everything was stored together.
The string pointers you store into the res with ret[c] = buffer; array point to an automatic array that goes out of scope when the function returns. The code subsequently has undefined behavior. You should allocate these strings with strdup().
Note also that it might not be appropriate to return NULL when the string does not contain a separator. Why not return an array with a single string?
Here is a simpler implementation:
#include <stdlib.h>
char **str_split(const char *string, char delim, int *num_strings) {
int i, n, from, to;
char **res;
for (n = 1, i = 0; string[i]; i++)
n += (string[i] == delim);
*num_strings = 0;
res = malloc(sizeof(*res) * n);
if (res == NULL)
return NULL;
for (i = from = to = 0;; from = to + 1) {
for (to = from; string[to] != delim && string[to] != '\0'; to++)
continue;
res[i] = malloc(to - from + 1);
if (res[i] == NULL) {
/* allocation failure: free memory allocated so far */
while (i > 0)
free(res[--i]);
free(res);
return NULL;
}
memcpy(res[i], string + from, to - from);
res[i][to - from] = '\0';
i++;
if (string[to] == '\0')
break;
}
*num_strings = n;
return res;
}
I want to write a program in C that displays each word of a whole sentence (taken as input) at a seperate line. This is what I have done so far:
void manipulate(char *buffer);
int get_words(char *buffer);
int main(){
char buff[100];
printf("sizeof %d\nstrlen %d\n", sizeof(buff), strlen(buff)); // Debugging reasons
bzero(buff, sizeof(buff));
printf("Give me the text:\n");
fgets(buff, sizeof(buff), stdin);
manipulate(buff);
return 0;
}
int get_words(char *buffer){ // Function that gets the word count, by counting the spaces.
int count;
int wordcount = 0;
char ch;
for (count = 0; count < strlen(buffer); count ++){
ch = buffer[count];
if((isblank(ch)) || (buffer[count] == '\0')){ // if the character is blank, or null byte add 1 to the wordcounter
wordcount += 1;
}
}
printf("%d\n\n", wordcount);
return wordcount;
}
void manipulate(char *buffer){
int words = get_words(buffer);
char *newbuff[words];
char *ptr;
int count = 0;
int count2 = 0;
char ch = '\n';
ptr = buffer;
bzero(newbuff, sizeof(newbuff));
for (count = 0; count < 100; count ++){
ch = buffer[count];
if (isblank(ch) || buffer[count] == '\0'){
buffer[count] = '\0';
if((newbuff[count2] = (char *)malloc(strlen(buffer))) == NULL) {
printf("MALLOC ERROR!\n");
exit(-1);
}
strcpy(newbuff[count2], ptr);
printf("\n%s\n",newbuff[count2]);
ptr = &buffer[count + 1];
count2 ++;
}
}
}
Although the output is what I want, I have really many black spaces after the final word displayed, and the malloc() returns NULL so the MALLOC ERROR! is displayed in the end.
I can understand that there is a mistake at my malloc() implementation, but I do not know what it is.
Is there another more elegant or generally better way to do it?
http://www.cplusplus.com/reference/clibrary/cstring/strtok/
Take a look at this, and use whitespace characters as the delimiter. If you need more hints let me know.
From the website:
char * strtok ( char * str, const char * delimiters );
On a first call, the function expects a C string as argument for str, whose first character is used as the starting location to scan for tokens. In subsequent calls, the function expects a null pointer and uses the position right after the end of last token as the new starting location for scanning.
Once the terminating null character of str is found in a call to strtok, all subsequent calls to this function (with a null pointer as the first argument) return a null pointer.
Parameters
str
C string to truncate.
Notice that this string is modified by being broken into smaller strings (tokens).
Alternativelly [sic], a null pointer may be specified, in which case the function continues scanning where a previous successful call to the function ended.
delimiters
C string containing the delimiter characters.
These may vary from one call to another.
Return Value
A pointer to the last token found in string.
A null pointer is returned if there are no tokens left to retrieve.
Example
/* strtok example */
#include <stdio.h>
#include <string.h>
int main ()
{
char str[] ="- This, a sample string.";
char * pch;
printf ("Splitting string \"%s\" into tokens:\n",str);
pch = strtok (str," ,.-");
while (pch != NULL)
{
printf ("%s\n",pch);
pch = strtok (NULL, " ,.-");
}
return 0;
}
For the fun of it here's an implementation based on the callback approach:
const char* find(const char* s,
const char* e,
int (*pred)(char))
{
while( s != e && !pred(*s) ) ++s;
return s;
}
void split_on_ws(const char* s,
const char* e,
void (*callback)(const char*, const char*))
{
const char* p = s;
while( s != e ) {
s = find(s, e, isspace);
callback(p, s);
p = s = find(s, e, isnotspace);
}
}
void handle_word(const char* s, const char* e)
{
// handle the word that starts at s and ends at e
}
int main()
{
split_on_ws(some_str, some_str + strlen(some_str), handle_word);
}
malloc(0) may (optionally) return NULL, depending on the implementation. Do you realize why you may be calling malloc(0)? Or more precisely, do you see where you are reading and writing beyond the size of your arrays?
Consider using strtok_r, as others have suggested, or something like:
void printWords(const char *string) {
// Make a local copy of the string that we can manipulate.
char * const copy = strdup(string);
char *space = copy;
// Find the next space in the string, and replace it with a newline.
while (space = strchr(space,' ')) *space = '\n';
// There are no more spaces in the string; print out our modified copy.
printf("%s\n", copy);
// Free our local copy
free(copy);
}
Something going wrong is get_words() always returning one less than the actual word count, so eventually you attempt to:
char *newbuff[words]; /* Words is one less than the actual number,
so this is declared to be too small. */
newbuff[count2] = (char *)malloc(strlen(buffer))
count2, eventually, is always one more than the number of elements you've declared for newbuff[]. Why malloc() isn't returning a valid ptr, though, I don't know.
You should be malloc'ing strlen(ptr), not strlen(buf). Also, your count2 should be limited to the number of words. When you get to the end of your string, you continue going over the zeros in your buffer and adding zero size strings to your array.
Just as an idea of a different style of string manipulation in C, here's an example which does not modify the source string, and does not use malloc. To find spaces I use the libc function strpbrk.
int print_words(const char *string, FILE *f)
{
static const char space_characters[] = " \t";
const char *next_space;
// Find the next space in the string
//
while ((next_space = strpbrk(string, space_characters)))
{
const char *p;
// If there are non-space characters between what we found
// and what we started from, print them.
//
if (next_space != string)
{
for (p=string; p<next_space; p++)
{
if(fputc(*p, f) == EOF)
{
return -1;
}
}
// Print a newline
//
if (fputc('\n', f) == EOF)
{
return -1;
}
}
// Advance next_space until we hit a non-space character
//
while (*next_space && strchr(space_characters, *next_space))
{
next_space++;
}
// Advance the string
//
string = next_space;
}
// Handle the case where there are no spaces left in the string
//
if (*string)
{
if (fprintf(f, "%s\n", string) < 0)
{
return -1;
}
}
return 0;
}
you can scan the char array looking for the token if you found it just print new line else print the char.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main()
{
char *s;
s = malloc(1024 * sizeof(char));
scanf("%[^\n]", s);
s = realloc(s, strlen(s) + 1);
int len = strlen(s);
char delim =' ';
for(int i = 0; i < len; i++) {
if(s[i] == delim) {
printf("\n");
}
else {
printf("%c", s[i]);
}
}
free(s);
return 0;
}
char arr[50];
gets(arr);
int c=0,i,l;
l=strlen(arr);
for(i=0;i<l;i++){
if(arr[i]==32){
printf("\n");
}
else
printf("%c",arr[i]);
}
Is there a clean, preferably standard method of trimming leading and trailing whitespace from a string in C? I'd roll my own, but I would think this is a common problem with an equally common solution.
If you can modify the string:
// Note: This function returns a pointer to a substring of the original string.
// If the given string was allocated dynamically, the caller must not overwrite
// that pointer with the returned value, since the original pointer must be
// deallocated using the same allocator with which it was allocated. The return
// value must NOT be deallocated using free() etc.
char *trimwhitespace(char *str)
{
char *end;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
return str;
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
// Write new null terminator character
end[1] = '\0';
return str;
}
If you can't modify the string, then you can use basically the same method:
// Stores the trimmed input string into the given output buffer, which must be
// large enough to store the result. If it is too small, the output is
// truncated.
size_t trimwhitespace(char *out, size_t len, const char *str)
{
if(len == 0)
return 0;
const char *end;
size_t out_size;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
{
*out = 0;
return 1;
}
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
end++;
// Set output size to minimum of trimmed string length and buffer size minus 1
out_size = (end - str) < len-1 ? (end - str) : len-1;
// Copy trimmed string and add null terminator
memcpy(out, str, out_size);
out[out_size] = 0;
return out_size;
}
Here's one that shifts the string into the first position of your buffer. You might want this behavior so that if you dynamically allocated the string, you can still free it on the same pointer that trim() returns:
char *trim(char *str)
{
size_t len = 0;
char *frontp = str;
char *endp = NULL;
if( str == NULL ) { return NULL; }
if( str[0] == '\0' ) { return str; }
len = strlen(str);
endp = str + len;
/* Move the front and back pointers to address the first non-whitespace
* characters from each end.
*/
while( isspace((unsigned char) *frontp) ) { ++frontp; }
if( endp != frontp )
{
while( isspace((unsigned char) *(--endp)) && endp != frontp ) {}
}
if( frontp != str && endp == frontp )
*str = '\0';
else if( str + len - 1 != endp )
*(endp + 1) = '\0';
/* Shift the string so that it starts at str so that if it's dynamically
* allocated, we can still free it on the returned pointer. Note the reuse
* of endp to mean the front of the string buffer now.
*/
endp = str;
if( frontp != str )
{
while( *frontp ) { *endp++ = *frontp++; }
*endp = '\0';
}
return str;
}
Test for correctness:
#include <stdio.h>
#include <string.h>
#include <ctype.h>
/* Paste function from above here. */
int main()
{
/* The test prints the following:
[nothing to trim] -> [nothing to trim]
[ trim the front] -> [trim the front]
[trim the back ] -> [trim the back]
[ trim front and back ] -> [trim front and back]
[ trim one char front and back ] -> [trim one char front and back]
[ trim one char front] -> [trim one char front]
[trim one char back ] -> [trim one char back]
[ ] -> []
[ ] -> []
[a] -> [a]
[] -> []
*/
char *sample_strings[] =
{
"nothing to trim",
" trim the front",
"trim the back ",
" trim front and back ",
" trim one char front and back ",
" trim one char front",
"trim one char back ",
" ",
" ",
"a",
"",
NULL
};
char test_buffer[64];
char comparison_buffer[64];
size_t index, compare_pos;
for( index = 0; sample_strings[index] != NULL; ++index )
{
// Fill buffer with known value to verify we do not write past the end of the string.
memset( test_buffer, 0xCC, sizeof(test_buffer) );
strcpy( test_buffer, sample_strings[index] );
memcpy( comparison_buffer, test_buffer, sizeof(comparison_buffer));
printf("[%s] -> [%s]\n", sample_strings[index],
trim(test_buffer));
for( compare_pos = strlen(comparison_buffer);
compare_pos < sizeof(comparison_buffer);
++compare_pos )
{
if( test_buffer[compare_pos] != comparison_buffer[compare_pos] )
{
printf("Unexpected change to buffer # index %u: %02x (expected %02x)\n",
compare_pos, (unsigned char) test_buffer[compare_pos], (unsigned char) comparison_buffer[compare_pos]);
}
}
}
return 0;
}
Source file was trim.c. Compiled with 'cc -Wall trim.c -o trim'.
My solution. String must be changeable. The advantage above some of the other solutions that it moves the non-space part to the beginning so you can keep using the old pointer, in case you have to free() it later.
void trim(char * s) {
char * p = s;
int l = strlen(p);
while(isspace(p[l - 1])) p[--l] = 0;
while(* p && isspace(* p)) ++p, --l;
memmove(s, p, l + 1);
}
This version creates a copy of the string with strndup() instead of editing it in place. strndup() requires _GNU_SOURCE, so maybe you need to make your own strndup() with malloc() and strncpy().
char * trim(char * s) {
int l = strlen(s);
while(isspace(s[l - 1])) --l;
while(* s && isspace(* s)) ++s, --l;
return strndup(s, l);
}
Here's my C mini library for trimming left, right, both, all, in place and separate, and trimming a set of specified characters (or white space by default).
contents of strlib.h:
#ifndef STRLIB_H_
#define STRLIB_H_ 1
enum strtrim_mode_t {
STRLIB_MODE_ALL = 0,
STRLIB_MODE_RIGHT = 0x01,
STRLIB_MODE_LEFT = 0x02,
STRLIB_MODE_BOTH = 0x03
};
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
);
char *strtriml(char *d, char *s);
char *strtrimr(char *d, char *s);
char *strtrim(char *d, char *s);
char *strkill(char *d, char *s);
char *triml(char *s);
char *trimr(char *s);
char *trim(char *s);
char *kill(char *s);
#endif
contents of strlib.c:
#include <strlib.h>
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
) {
char *o = d; // save orig
char *e = 0; // end space ptr.
char dtab[256] = {0};
if (!s || !d) return 0;
if (!delim) delim = " \t\n\f";
while (*delim)
dtab[*delim++] = 1;
while ( (*d = *s++) != 0 ) {
if (!dtab[0xFF & (unsigned int)*d]) { // Not a match char
e = 0; // Reset end pointer
} else {
if (!e) e = d; // Found first match.
if ( mode == STRLIB_MODE_ALL || ((mode != STRLIB_MODE_RIGHT) && (d == o)) )
continue;
}
d++;
}
if (mode != STRLIB_MODE_LEFT && e) { // for everything but trim_left, delete trailing matches.
*e = 0;
}
return o;
}
// perhaps these could be inlined in strlib.h
char *strtriml(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_LEFT, 0); }
char *strtrimr(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_RIGHT, 0); }
char *strtrim(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_BOTH, 0); }
char *strkill(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_ALL, 0); }
char *triml(char *s) { return strcpytrim(s, s, STRLIB_MODE_LEFT, 0); }
char *trimr(char *s) { return strcpytrim(s, s, STRLIB_MODE_RIGHT, 0); }
char *trim(char *s) { return strcpytrim(s, s, STRLIB_MODE_BOTH, 0); }
char *kill(char *s) { return strcpytrim(s, s, STRLIB_MODE_ALL, 0); }
The one main routine does it all.
It trims in place if src == dst, otherwise,
it works like the strcpy routines.
It trims a set of characters specified in the string delim, or white space if null.
It trims left, right, both, and all (like tr).
There is not much to it, and it iterates over the string only once. Some folks might complain that trim right starts on the left, however, no strlen is needed which starts on the left anyway. (One way or another you have to get to the end of the string for right trims, so you might as well do the work as you go.) There may be arguments to be made about pipelining and cache sizes and such -- who knows. Since the solution works from left to right and iterates only once, it can be expanded to work on streams as well. Limitations: it does not work on unicode strings.
Here is my attempt at a simple, yet correct in-place trim function.
void trim(char *str)
{
int i;
int begin = 0;
int end = strlen(str) - 1;
while (isspace((unsigned char) str[begin]))
begin++;
while ((end >= begin) && isspace((unsigned char) str[end]))
end--;
// Shift all characters back to the start of the string array.
for (i = begin; i <= end; i++)
str[i - begin] = str[i];
str[i - begin] = '\0'; // Null terminate string.
}
Late to the trim party
Features:
1. Trim the beginning quickly, as in a number of other answers.
2. After going to the end, trimming the right with only 1 test per loop. Like #jfm3, but works for an all white-space string)
3. To avoid undefined behavior when char is a signed char, cast *s to unsigned char.
Character handling "In all cases the argument is an int, the value of which shall be representable as an unsigned char or shall equal the value of the macro EOF. If the argument has any other value, the behavior is undefined." C11 §7.4 1
#include <ctype.h>
// Return a pointer to the trimmed string
char *string_trim_inplace(char *s) {
while (isspace((unsigned char) *s)) s++;
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
}
// If desired, shift the trimmed string
return s;
}
#chqrlie commented the above does not shift the trimmed string. To do so....
// Return a pointer to the (shifted) trimmed string
char *string_trim_inplace(char *s) {
char *original = s;
size_t len = 0;
while (isspace((unsigned char) *s)) {
s++;
}
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
// len = (size_t) (p - s); // older errant code
len = (size_t) (p - s + 1); // Thanks to #theriver
}
return (s == original) ? s : memmove(original, s, len + 1);
}
Here's a solution similar to #adam-rosenfields in-place modification routine but without needlessly resorting to strlen(). Like #jkramer, the string is left-adjusted within the buffer so you can free the same pointer. Not optimal for large strings since it does not use memmove. Includes the ++/-- operators that #jfm3 mentions. FCTX-based unit tests included.
#include <ctype.h>
void trim(char * const a)
{
char *p = a, *q = a;
while (isspace(*q)) ++q;
while (*q) *p++ = *q++;
*p = '\0';
while (p > a && isspace(*--p)) *p = '\0';
}
/* See http://fctx.wildbearsoftware.com/ */
#include "fct.h"
FCT_BGN()
{
FCT_QTEST_BGN(trim)
{
{ char s[] = ""; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = " "; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "\t"; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "a"; trim(s); fct_chk_eq_str("a", s); } // NOP
{ char s[] = "abc"; trim(s); fct_chk_eq_str("abc", s); } // NOP
{ char s[] = " a"; trim(s); fct_chk_eq_str("a", s); } // Leading
{ char s[] = " a c"; trim(s); fct_chk_eq_str("a c", s); } // Leading
{ char s[] = "a "; trim(s); fct_chk_eq_str("a", s); } // Trailing
{ char s[] = "a c "; trim(s); fct_chk_eq_str("a c", s); } // Trailing
{ char s[] = " a "; trim(s); fct_chk_eq_str("a", s); } // Both
{ char s[] = " a c "; trim(s); fct_chk_eq_str("a c", s); } // Both
// Villemoes pointed out an edge case that corrupted memory. Thank you.
// http://stackoverflow.com/questions/122616/#comment23332594_4505533
{
char s[] = "a "; // Buffer with whitespace before s + 2
trim(s + 2); // Trim " " containing only whitespace
fct_chk_eq_str("", s + 2); // Ensure correct result from the trim
fct_chk_eq_str("a ", s); // Ensure preceding buffer not mutated
}
// doukremt suggested I investigate this test case but
// did not indicate the specific behavior that was objectionable.
// http://stackoverflow.com/posts/comments/33571430
{
char s[] = " foobar"; // Shifted across whitespace
trim(s); // Trim
fct_chk_eq_str("foobar", s); // Leading string is correct
// Here is what the algorithm produces:
char r[16] = { 'f', 'o', 'o', 'b', 'a', 'r', '\0', ' ',
' ', 'f', 'o', 'o', 'b', 'a', 'r', '\0'};
fct_chk_eq_int(0, memcmp(s, r, sizeof(s)));
}
}
FCT_QTEST_END();
}
FCT_END();
I'm not sure what you consider "painless."
C strings are pretty painful. We can find the first non-whitespace character position trivially:
while (isspace(* p)) p++;
We can find the last non-whitespace character position with two similar trivial moves:
while (* q) q++;
do { q--; } while (isspace(* q));
(I have spared you the pain of using the * and ++ operators at the same time.)
The question now is what do you do with this? The datatype at hand isn't really a big robust abstract String that is easy to think about, but instead really barely any more than an array of storage bytes. Lacking a robust data type, it is impossible to write a function that will do the same as PHperytonby's chomp function. What would such a function in C return?
Another one, with one line doing the real job:
#include <stdio.h>
int main()
{
const char *target = " haha ";
char buf[256];
sscanf(target, "%s", buf); // Trimming on both sides occurs here
printf("<%s>\n", buf);
}
If you're using glib, then you can use g_strstrip
I didn't like most of these answers because they did one or more of the following...
Returned a different pointer inside the original pointer's string (kind of a pain to juggle two different pointers to the same thing).
Made gratuitous use of things like strlen() that pre-iterate the entire string.
Used non-portable OS-specific lib functions.
Backscanned.
Used comparison to ' ' instead of isspace() so that TAB / CR / LF are preserved.
Wasted memory with large static buffers.
Wasted cycles with high-cost functions like sscanf/sprintf.
Here is my version:
void fnStrTrimInPlace(char *szWrite) {
const char *szWriteOrig = szWrite;
char *szLastSpace = szWrite, *szRead = szWrite;
int bNotSpace;
// SHIFT STRING, STARTING AT FIRST NON-SPACE CHAR, LEFTMOST
while( *szRead != '\0' ) {
bNotSpace = !isspace((unsigned char)(*szRead));
if( (szWrite != szWriteOrig) || bNotSpace ) {
*szWrite = *szRead;
szWrite++;
// TRACK POINTER TO LAST NON-SPACE
if( bNotSpace )
szLastSpace = szWrite;
}
szRead++;
}
// TERMINATE AFTER LAST NON-SPACE (OR BEGINNING IF THERE WAS NO NON-SPACE)
*szLastSpace = '\0';
}
Use a string library, for instance:
Ustr *s1 = USTR1(\7, " 12345 ");
ustr_sc_trim_cstr(&s1, " ");
assert(ustr_cmp_cstr_eq(s1, "12345"));
...as you say this is a "common" problem, yes you need to include a #include or so and it's not included in libc but don't go inventing your own hack job storing random pointers and size_t's that way only leads to buffer overflows.
A bit late to the game, but I'll throw my routines into the fray. They're probably not the most absolute efficient, but I believe they're correct and they're simple (with rtrim() pushing the complexity envelope):
#include <ctype.h>
#include <string.h>
/*
Public domain implementations of in-place string trim functions
Michael Burr
michael.burr#nth-element.com
2010
*/
char* ltrim(char* s)
{
char* newstart = s;
while (isspace( *newstart)) {
++newstart;
}
// newstart points to first non-whitespace char (which might be '\0')
memmove( s, newstart, strlen( newstart) + 1); // don't forget to move the '\0' terminator
return s;
}
char* rtrim( char* s)
{
char* end = s + strlen( s);
// find the last non-whitespace character
while ((end != s) && isspace( *(end-1))) {
--end;
}
// at this point either (end == s) and s is either empty or all whitespace
// so it needs to be made empty, or
// end points just past the last non-whitespace character (it might point
// at the '\0' terminator, in which case there's no problem writing
// another there).
*end = '\0';
return s;
}
char* trim( char* s)
{
return rtrim( ltrim( s));
}
Very late to the party...
Single-pass forward-scanning solution with no backtracking. Every character in the source string is tested exactly once twice. (So it should be faster than most of the other solutions here, especially if the source string has a lot of trailing spaces.)
This includes two solutions, one to copy and trim a source string into another destination string, and the other to trim the source string in place. Both functions use the same code.
The (modifiable) string is moved in-place, so the original pointer to it remains unchanged.
#include <stddef.h>
#include <ctype.h>
char * trim2(char *d, const char *s)
{
// Sanity checks
if (s == NULL || d == NULL)
return NULL;
// Skip leading spaces
const unsigned char * p = (const unsigned char *)s;
while (isspace(*p))
p++;
// Copy the string
unsigned char * dst = (unsigned char *)d; // d and s can be the same
unsigned char * end = dst;
while (*p != '\0')
{
if (!isspace(*dst++ = *p++))
end = dst;
}
// Truncate trailing spaces
*end = '\0';
return d;
}
char * trim(char *s)
{
return trim2(s, s);
}
Just to keep this growing, one more option with a modifiable string:
void trimString(char *string)
{
size_t i = 0, j = strlen(string);
while (j > 0 && isspace((unsigned char)string[j - 1])) string[--j] = '\0';
while (isspace((unsigned char)string[i])) i++;
if (i > 0) memmove(string, string + i, j - i + 1);
}
I know there have many answers, but I post my answer here to see if my solution is good enough.
// Trims leading whitespace chars in left `str`, then copy at almost `n - 1` chars
// into the `out` buffer in which copying might stop when the first '\0' occurs,
// and finally append '\0' to the position of the last non-trailing whitespace char.
// Reture the length the trimed string which '\0' is not count in like strlen().
size_t trim(char *out, size_t n, const char *str)
{
// do nothing
if(n == 0) return 0;
// ptr stop at the first non-leading space char
while(isspace(*str)) str++;
if(*str == '\0') {
out[0] = '\0';
return 0;
}
size_t i = 0;
// copy char to out until '\0' or i == n - 1
for(i = 0; i < n - 1 && *str != '\0'; i++){
out[i] = *str++;
}
// deal with the trailing space
while(isspace(out[--i]));
out[++i] = '\0';
return i;
}
The easiest way to skip leading spaces in a string is, imho,
#include <stdio.h>
int main()
{
char *foo=" teststring ";
char *bar;
sscanf(foo,"%s",bar);
printf("String is >%s<\n",bar);
return 0;
}
Ok this is my take on the question. I believe it's the most concise solution that modifies the string in place (free will work) and avoids any UB. For small strings, it's probably faster than a solution involving memmove.
void stripWS_LT(char *str)
{
char *a = str, *b = str;
while (isspace((unsigned char)*a)) a++;
while (*b = *a++) b++;
while (b > str && isspace((unsigned char)*--b)) *b = 0;
}
#include <ctype.h>
#include <string.h>
char *trim_space(char *in)
{
char *out = NULL;
int len;
if (in) {
len = strlen(in);
while(len && isspace(in[len - 1])) --len;
while(len && *in && isspace(*in)) ++in, --len;
if (len) {
out = strndup(in, len);
}
}
return out;
}
isspace helps to trim all white spaces.
Run a first loop to check from last byte for space character and reduce the length variable
Run a second loop to check from first byte for space character and reduce the length variable and increment char pointer.
Finally if length variable is more than 0, then use strndup to create new string buffer by excluding spaces.
This one is short and simple, uses for-loops and doesn't overwrite the string boundaries.
You can replace the test with isspace() if needed.
void trim (char *s) // trim leading and trailing spaces+tabs
{
int i,j,k, len;
j=k=0;
len = strlen(s);
// find start of string
for (i=0; i<len; i++) if ((s[i]!=32) && (s[i]!=9)) { j=i; break; }
// find end of string+1
for (i=len-1; i>=j; i--) if ((s[i]!=32) && (s[i]!=9)) { k=i+1; break;}
if (k<=j) {s[0]=0; return;} // all whitespace (j==k==0)
len=k-j;
for (i=0; i<len; i++) s[i] = s[j++]; // shift result to start of string
s[i]=0; // end the string
}//_trim
If, and ONLY IF there's only one contiguous block of text between whitespace, you can use a single call to strtok(3), like so:
char *trimmed = strtok(input, "\r\t\n ");
This works for strings like the following:
" +1.123.456.7890 "
" 01-01-2020\n"
"\t2.523"
This will not work for strings that contain whitespace between blocks of non-whitespace, like " hi there ". It's probably better to avoid this approach, but now it's here in your toolbox if you need it.
Personally, I'd roll my own. You can use strtok, but you need to take care with doing so (particularly if you're removing leading characters) that you know what memory is what.
Getting rid of trailing spaces is easy, and pretty safe, as you can just put a 0 in over the top of the last space, counting back from the end. Getting rid of leading spaces means moving things around. If you want to do it in place (probably sensible) you can just keep shifting everything back one character until there's no leading space. Or, to be more efficient, you could find the index of the first non-space character, and shift everything back by that number. Or, you could just use a pointer to the first non-space character (but then you need to be careful in the same way as you do with strtok).
#include "stdafx.h"
#include "malloc.h"
#include "string.h"
int main(int argc, char* argv[])
{
char *ptr = (char*)malloc(sizeof(char)*30);
strcpy(ptr," Hel lo wo rl d G eo rocks!!! by shahil sucks b i g tim e");
int i = 0, j = 0;
while(ptr[j]!='\0')
{
if(ptr[j] == ' ' )
{
j++;
ptr[i] = ptr[j];
}
else
{
i++;
j++;
ptr[i] = ptr[j];
}
}
printf("\noutput-%s\n",ptr);
return 0;
}
Most of the answers so far do one of the following:
Backtrack at the end of the string (i.e. find the end of the string and then seek backwards until a non-space character is found,) or
Call strlen() first, making a second pass through the whole string.
This version makes only one pass and does not backtrack. Hence it may perform better than the others, though only if it is common to have hundreds of trailing spaces (which is not unusual when dealing with the output of a SQL query.)
static char const WHITESPACE[] = " \t\n\r";
static void get_trim_bounds(char const *s,
char const **firstWord,
char const **trailingSpace)
{
char const *lastWord;
*firstWord = lastWord = s + strspn(s, WHITESPACE);
do
{
*trailingSpace = lastWord + strcspn(lastWord, WHITESPACE);
lastWord = *trailingSpace + strspn(*trailingSpace, WHITESPACE);
}
while (*lastWord != '\0');
}
char *copy_trim(char const *s)
{
char const *firstWord, *trailingSpace;
char *result;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
result = malloc(newLength + 1);
memcpy(result, firstWord, newLength);
result[newLength] = '\0';
return result;
}
void inplace_trim(char *s)
{
char const *firstWord, *trailingSpace;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
memmove(s, firstWord, newLength);
s[newLength] = '\0';
}
This is the shortest possible implementation I can think of:
static const char *WhiteSpace=" \n\r\t";
char* trim(char *t)
{
char *e=t+(t!=NULL?strlen(t):0); // *e initially points to end of string
if (t==NULL) return;
do --e; while (strchr(WhiteSpace, *e) && e>=t); // Find last char that is not \r\n\t
*(++e)=0; // Null-terminate
e=t+strspn (t,WhiteSpace); // Find first char that is not \t
return e>t?memmove(t,e,strlen(e)+1):t; // memmove string contents and terminator
}
These functions will modify the original buffer, so if dynamically allocated, the original
pointer can be freed.
#include <string.h>
void rstrip(char *string)
{
int l;
if (!string)
return;
l = strlen(string) - 1;
while (isspace(string[l]) && l >= 0)
string[l--] = 0;
}
void lstrip(char *string)
{
int i, l;
if (!string)
return;
l = strlen(string);
while (isspace(string[(i = 0)]))
while(i++ < l)
string[i-1] = string[i];
}
void strip(char *string)
{
lstrip(string);
rstrip(string);
}
What do you think about using StrTrim function defined in header Shlwapi.h.? It is straight forward rather defining on your own.
Details can be found on:
http://msdn.microsoft.com/en-us/library/windows/desktop/bb773454(v=vs.85).aspx
If you have
char ausCaptain[]="GeorgeBailey ";
StrTrim(ausCaptain," ");
This will give ausCaptain as "GeorgeBailey" not "GeorgeBailey ".
To trim my strings from the both sides I use the oldie but the gooody ;)
It can trim anything with ascii less than a space, meaning that the control chars will be trimmed also !
char *trimAll(char *strData)
{
unsigned int L = strlen(strData);
if(L > 0){ L--; }else{ return strData; }
size_t S = 0, E = L;
while((!(strData[S] > ' ') || !(strData[E] > ' ')) && (S >= 0) && (S <= L) && (E >= 0) && (E <= L))
{
if(strData[S] <= ' '){ S++; }
if(strData[E] <= ' '){ E--; }
}
if(S == 0 && E == L){ return strData; } // Nothing to be done
if((S >= 0) && (S <= L) && (E >= 0) && (E <= L)){
L = E - S + 1;
memmove(strData,&strData[S],L); strData[L] = '\0';
}else{ strData[0] = '\0'; }
return strData;
}
I'm only including code because the code posted so far seems suboptimal (and I don't have the rep to comment yet.)
void inplace_trim(char* s)
{
int start, end = strlen(s);
for (start = 0; isspace(s[start]); ++start) {}
if (s[start]) {
while (end > 0 && isspace(s[end-1]))
--end;
memmove(s, &s[start], end - start);
}
s[end - start] = '\0';
}
char* copy_trim(const char* s)
{
int start, end;
for (start = 0; isspace(s[start]); ++start) {}
for (end = strlen(s); end > 0 && isspace(s[end-1]); --end) {}
return strndup(s + start, end - start);
}
strndup() is a GNU extension. If you don't have it or something equivalent, roll your own. For example:
r = strdup(s + start);
r[end-start] = '\0';
Here i use the dynamic memory allocation to trim the input string to the function trimStr. First, we find how many non-empty characters exist in the input string. Then, we allocate a character array with that size and taking care of the null terminated character. When we use this function, we need to free the memory inside of main function.
#include<stdio.h>
#include<stdlib.h>
char *trimStr(char *str){
char *tmp = str;
printf("input string %s\n",str);
int nc = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
nc++;
}
tmp++;
}
printf("total nonempty characters are %d\n",nc);
char *trim = NULL;
trim = malloc(sizeof(char)*(nc+1));
if (trim == NULL) return NULL;
tmp = str;
int ne = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
trim[ne] = *tmp;
ne++;
}
tmp++;
}
trim[nc] = '\0';
printf("trimmed string is %s\n",trim);
return trim;
}
int main(void){
char str[] = " s ta ck ove r fl o w ";
char *trim = trimStr(str);
if (trim != NULL )free(trim);
return 0;
}