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.
40 Answers
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 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?
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);
}
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
strndupto 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).
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;
}
Here is how I do it. It trims the string in place, so no worry about deallocating a returned string or losing the pointer to an allocated string. It may not be the shortest answer possible, but it should be clear to most readers.
#include <ctype.h>
#include <string.h>
void trim_str(char *s)
{
const size_t s_len = strlen(s);
int i;
for (i = 0; i < s_len; i++)
{
if (!isspace( (unsigned char) s[i] )) break;
}
if (i == s_len)
{
// s is an empty string or contains only space characters
s[0] = '\0';
}
else
{
// s contains non-space characters
const char *non_space_beginning = s + i;
char *non_space_ending = s + s_len - 1;
while ( isspace( (unsigned char) *non_space_ending ) ) non_space_ending--;
size_t trimmed_s_len = non_space_ending - non_space_beginning + 1;
if (s != non_space_beginning)
{
// Non-space characters exist in the beginning of s
memmove(s, non_space_beginning, trimmed_s_len);
}
s[trimmed_s_len] = '\0';
}
}
char* strtrim(char* const str)
{
if (str != nullptr)
{
char const* begin{ str };
while (std::isspace(*begin))
{
++begin;
}
auto end{ begin };
auto scout{ begin };
while (*scout != '\0')
{
if (!std::isspace(*scout++))
{
end = scout;
}
}
auto /* std::ptrdiff_t */ const length{ end - begin };
if (begin != str)
{
std::memmove(str, begin, length);
}
str[length] = '\0';
}
return str;
}
As the other answers don't seem to mutate the string pointer directly, but rather rely on the return value, I thought I would provide this method which additionally does not use any libraries and so is appropriate for operating system style programming:
// only used for printf in main
#include <stdio.h>
// note the char ** means we can modify the address
char *trimws(char **strp) {
char *str;
// check if empty string
if(!*str)
return;
// go to the end of the string
for (str = *strp; *str; str++)
;
// back up one from the null terminator
str--;
// set trailing ws to null
for (; *str == ' '; str--)
*str = 0;
// increment past leading ws
for (str = *strp; *str == ' '; str++)
;
// set new begin address of string
*strp = str;
}
int main(void) {
char buf[256] = " whitespace ";
// pointer must be modifiable lvalue so we make bufp
char **bufp = &buf;
// pass in the address
trimws(&bufp);
// prints : XXXwhitespaceXXX
printf("XXX%sXXX\n", bufp);
return 0;
}
IMO, it can be done without strlen and isspace.
char *
trim (char * s, char c)
{
unsigned o = 0;
char * sb = s;
for (; *s == c; s++)
o++;
for (; *s != '\0'; s++)
continue;
for (; s - o > sb && *--s == c;)
continue;
if (o > 0)
memmove(sb, sb + o, s + 1 - o - sb);
if (*s != '\0')
*(s + 1 - o) = '\0';
return sb;
}
Here is a function to do what you want. It should take care of degenerate cases where the string is all whitespace. You must pass in an output buffer and the length of the buffer, which means that you have to pass in a buffer that you allocate.
void str_trim(char *output, const char *text, int32 max_len)
{
int32 i, j, length;
length = strlen(text);
if (max_len < 0) {
max_len = length + 1;
}
for (i=0; i<length; i++) {
if ( (text[i] != ' ') && (text[i] != '\t') && (text[i] != '\n') && (text[i] != '\r')) {
break;
}
}
if (i == length) {
// handle lines that are all whitespace
output[0] = 0;
return;
}
for (j=length-1; j>=0; j--) {
if ( (text[j] != ' ') && (text[j] != '\t') && (text[j] != '\n') && (text[j] != '\r')) {
break;
}
}
length = j + 1 - i;
strncpy(output, text + i, length);
output[length] = 0;
}
The if statements in the loops can probably be replaced with isspace(text[i]) or isspace(text[j]) to make the lines a little easier to read. I think that I had them set this way because there were some characters that I didn't want to test for, but it looks like I'm covering all whitespace now :-)
Related