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;
}
Currently I am working on a program that allows a user to enter a string that is then tokenized, then the tokens are printed to the screen by using an array of pointers. It is "supposed" to do this by calling my tokenize function which reads the input string until the first separator ( ' ', ',', '.', '?', '!'). It then changes that separator in my string to a NULL char. It then should return a pointer to the next character in my string.
In main after the string has been input, it should keep calling the tokenize function which returns pointers which are then stored in a array of pointers to later print my tokens. Once the tokenize() returns a pointer to a NULL character which is at the end of my string it breaks from that loop. Then I print the tokens out using my array of pointers.
//trying to be detailed
#include <stdio.h>
#include <string.h>
char *tokenize ( char *text, const char *separators );
int main ( void )
{
char text[30];
char separators[6] = { ' ','.',',','?','!','\0'};
char *pch = NULL;
int tokens[15];
int i = 0;
int j = 0;
printf("Enter a string: \n");
fgets( text, 30, stdin );
printf("%s", text );
pch = tokenize ( text, separators );
do
{
pch = tokenize ( pch, separators );
//printf("%c", *pch);
tokens[i] = pch;
i++;
}
while( *pch != NULL );
i--;
while( j != i )
{
printf("%s", tokens[i] );
j++;
}
return 0;
}
char *tokenize ( char *text, const char *separators )
{
while( text != NULL )
{
if( text != NULL )
{
while( separators != NULL )
{
if( text == separators )
{
text = '\0';
}
separators++;
}
}
text++;
}
return text;
}
3 big known problems currently.
1.When I compile, it reads the string then prints it, then gets stuck in a endless loop with nothing printing, still trying to get input.
2. Im pretty sure I am using the " * " for my pointers in the wrong place.
3. My function passes in a reference to my arrays, so I assumed i could just increment them as is.
I appreciate any feedback! I will be watching this post constantly. If i left something unclear, I can respecify. Thanks.
You had right idea for approaching the problem, but you had numerous pointer/int errors throughout your code. Make sure you compile your code with Warnings enabled, this will tell you where you have problems in your code. (don't expect your code to run correctly until you address and eliminate all warnings). At a minimum, compile with -Wall -Wextra options in your build command.
There are a lot easier ways to do this, but for the learning experience, this is a great exercise. Below is your code with the errors corrected. Where possible, I have left your original code commented so you can see where the issues were. I also include a bit of code to remove the newline included by fgets at the end of text. While this isn't required, it is good practice not to have stray newlines filter through your code.
Let me know if you have questions:
#include <stdio.h>
#include <string.h>
char *tokenize ( char *text, const char *separators );
int main ( void )
{
char text[30];
char separators[6] = { ' ','.',',','?','!','\0'};
char *pch = NULL;
char *tokens[15] = {0}; /* declare array of pointers */
int i = 0;
int j = 0;
printf("Enter a string: \n");
fgets( text, 30, stdin );
size_t len = strlen (text);
if (text[len-1] == '\n') /* strip newline from text */
text[--len] = 0;
pch = text; /* pch pointer to next string */
char *str = text; /* str pointer to current */
do
{
pch = tokenize ( str, separators ); /* pch points to next */
tokens[i++] = str; /* save ptr to token */
str = pch; /* new start of str */
}
while (pch != NULL && *pch != 0); /* test both pch & *pch */
printf ("\nTokens collected:\n\n");
while (tokens[j]) /* print each token */
{
printf(" token[%d]: %s\n", j, tokens[j] );
j++;
}
printf ("\n");
return 0;
}
char *tokenize ( char *text, const char *separators )
{
const char *s = separators; /* must use pointer to allow reset */
//while( text != NULL )
while( *text != '\0' )
{
s = separators; /* reset s */
while( *s != 0 ) /* 0 is the same as '\0' */
{
//if( text == separators )
if( *text == *s )
{
//text = '\0';
*text = '\0';
return ++text;
}
s++;
}
text++;
}
return text;
}
Example output:
$ ./bin/tokenizestr
Enter a string:
This is a test string
Tokens collected:
token[0]: This
token[1]: is
token[2]: a
token[3]: test
token[4]: string
Maybe you will want to take a look at
strsep and this post Split string with delimiters in C
If you need more reference points try searching "split string" it is what you want to do if I understood correctly.
Im trying to take a user input string and parse is into an array called char *entire_line[100]; where each word is put at a different index of the array but if a part of the string is encapsulated by a quote, that should be put in a single index.
So if I have
char buffer[1024]={0,};
fgets(buffer, 1024, stdin);
example input: "word filename.txt "this is a string that shoudl take up one index in an output array";
tokenizer=strtok(buffer," ");//break up by spaces
do{
if(strchr(tokenizer,'"')){//check is a word starts with a "
is_string=YES;
entire_line[i]=tokenizer;// if so, put that word into current index
tokenizer=strtok(NULL,"\""); //should get rest of string until end "
strcat(entire_line[i],tokenizer); //append the two together, ill take care of the missing space once i figure out this issue
}
entire_line[i]=tokenizer;
i++;
}while((tokenizer=strtok(NULL," \n"))!=NULL);
This clearly isn't working and only gets close if the double quote encapsulated string is at the end of the input string
but i could have
input: word "this is text that will be user entered" filename.txt
Been trying to figure this out for a while, always get stuck somewhere.
thanks
The strtok function is a terrible way to tokenize in C, except for one (admittedly common) case: simple whitespace-separated words. (Even then it's still not great due to lack of re-entrance and recursion ability, which is why we invented strsep for BSD way back when.)
Your best bet in this case is to build your own simple state-machine:
char *p;
int c;
enum states { DULL, IN_WORD, IN_STRING } state = DULL;
for (p = buffer; *p != '\0'; p++) {
c = (unsigned char) *p; /* convert to unsigned char for is* functions */
switch (state) {
case DULL: /* not in a word, not in a double quoted string */
if (isspace(c)) {
/* still not in a word, so ignore this char */
continue;
}
/* not a space -- if it's a double quote we go to IN_STRING, else to IN_WORD */
if (c == '"') {
state = IN_STRING;
start_of_word = p + 1; /* word starts at *next* char, not this one */
continue;
}
state = IN_WORD;
start_of_word = p; /* word starts here */
continue;
case IN_STRING:
/* we're in a double quoted string, so keep going until we hit a close " */
if (c == '"') {
/* word goes from start_of_word to p-1 */
... do something with the word ...
state = DULL; /* back to "not in word, not in string" state */
}
continue; /* either still IN_STRING or we handled the end above */
case IN_WORD:
/* we're in a word, so keep going until we get to a space */
if (isspace(c)) {
/* word goes from start_of_word to p-1 */
... do something with the word ...
state = DULL; /* back to "not in word, not in string" state */
}
continue; /* either still IN_WORD or we handled the end above */
}
}
Note that this does not account for the possibility of a double quote inside a word, e.g.:
"some text in quotes" plus four simple words p"lus something strange"
Work through the state machine above and you will see that "some text in quotes" turns into a single token (that ignores the double quotes), but p"lus is also a single token (that includes the quote), something is a single token, and strange" is a token. Whether you want this, or how you want to handle it, is up to you. For more complex but thorough lexical tokenization, you may want to use a code-building tool like flex.
Also, when the for loop exits, if state is not DULL, you need to handle the final word (I left this out of the code above) and decide what to do if state is IN_STRING (meaning there was no close-double-quote).
Torek's parts of parsing code are excellent but require little more work to use.
For my own purpose, I finished c function.
Here I share my work that is based on Torek's code.
#include <stdio.h>
#include <string.h>
#include <ctype.h>
size_t split(char *buffer, char *argv[], size_t argv_size)
{
char *p, *start_of_word;
int c;
enum states { DULL, IN_WORD, IN_STRING } state = DULL;
size_t argc = 0;
for (p = buffer; argc < argv_size && *p != '\0'; p++) {
c = (unsigned char) *p;
switch (state) {
case DULL:
if (isspace(c)) {
continue;
}
if (c == '"') {
state = IN_STRING;
start_of_word = p + 1;
continue;
}
state = IN_WORD;
start_of_word = p;
continue;
case IN_STRING:
if (c == '"') {
*p = 0;
argv[argc++] = start_of_word;
state = DULL;
}
continue;
case IN_WORD:
if (isspace(c)) {
*p = 0;
argv[argc++] = start_of_word;
state = DULL;
}
continue;
}
}
if (state != DULL && argc < argv_size)
argv[argc++] = start_of_word;
return argc;
}
void test_split(const char *s)
{
char buf[1024];
size_t i, argc;
char *argv[20];
strcpy(buf, s);
argc = split(buf, argv, 20);
printf("input: '%s'\n", s);
for (i = 0; i < argc; i++)
printf("[%u] '%s'\n", i, argv[i]);
}
int main(int ac, char *av[])
{
test_split("\"some text in quotes\" plus four simple words p\"lus something strange\"");
return 0;
}
See program output:
input: '"some text in quotes" plus four simple words p"lus something strange"'
[0] 'some text in quotes'
[1] 'plus'
[2] 'four'
[3] 'simple'
[4] 'words'
[5] 'p"lus'
[6] 'something'
[7] 'strange"'
I wrote a qtok function some time ago that reads quoted words from a string. It's not a state machine and it doesn't make you an array but it's trivial to put the resulting tokens into one. It also handles escaped quotes and trailing and leading spaces:
#include <stdio.h>
#include <ctype.h>
#include <assert.h>
// Strips backslashes from quotes
char *unescapeToken(char *token)
{
char *in = token;
char *out = token;
while (*in)
{
assert(in >= out);
if ((in[0] == '\\') && (in[1] == '"'))
{
*out = in[1];
out++;
in += 2;
}
else
{
*out = *in;
out++;
in++;
}
}
*out = 0;
return token;
}
// Returns the end of the token, without chaning it.
char *qtok(char *str, char **next)
{
char *current = str;
char *start = str;
int isQuoted = 0;
// Eat beginning whitespace.
while (*current && isspace(*current)) current++;
start = current;
if (*current == '"')
{
isQuoted = 1;
// Quoted token
current++; // Skip the beginning quote.
start = current;
for (;;)
{
// Go till we find a quote or the end of string.
while (*current && (*current != '"')) current++;
if (!*current)
{
// Reached the end of the string.
goto finalize;
}
if (*(current - 1) == '\\')
{
// Escaped quote keep going.
current++;
continue;
}
// Reached the ending quote.
goto finalize;
}
}
// Not quoted so run till we see a space.
while (*current && !isspace(*current)) current++;
finalize:
if (*current)
{
// Close token if not closed already.
*current = 0;
current++;
// Eat trailing whitespace.
while (*current && isspace(*current)) current++;
}
*next = current;
return isQuoted ? unescapeToken(start) : start;
}
int main()
{
char text[] = " \"some text in quotes\" plus four simple words p\"lus something strange\" \"Then some quoted \\\"words\\\", and backslashes: \\ \\ \" Escapes only work insi\\\"de q\\\"uoted strings\\\" ";
char *pText = text;
printf("Original: '%s'\n", text);
while (*pText)
{
printf("'%s'\n", qtok(pText, &pText));
}
}
Outputs:
Original: ' "some text in quotes" plus four simple words p"lus something strange" "Then some quoted \"words\", and backslashes: \ \ " Escapes only work insi\"de q\"uoted strings\" '
'some text in quotes'
'plus'
'four'
'simple'
'words'
'p"lus'
'something'
'strange"'
'Then some quoted "words", and backslashes: \ \ '
'Escapes'
'only'
'work'
'insi\"de'
'q\"uoted'
'strings\"'
I think the answer to your question is actually fairly simple, but I'm taking on an assumption where it seems the other responses have taken a different one. I'm assuming that you want any quoted block of text to be separated out on its own regardless of spacing with the rest of the text being separated by spaces.
So given the example:
"some text in quotes" plus four simple words p"lus something strange"
The output would be:
[0] some text in quotes
[1] plus
[2] four
[3] simple
[4] words
[5] p
[6] lus something strange
Given that this is the case, only a simple bit of code is required, and no complex machines. You would first check if there is a leading quote for the first character and if so tick a flag and remove the character. As well as removing any quotes at the end of the string. Then tokenize the string based on quotation marks. Then tokenize every other of the strings obtained previously by spaces. Tokenize starting with the first string obtained if there was no leading quote, or the second string obtained if there was a leading quote. Then each of the remaining strings from the first part will be added to an array of strings interspersed with the strings from the second part added in place of the strings they were tokenized from. In this way you can get the result listed above. In code this would look like:
#include<string.h>
#include<stdlib.h>
char ** parser(char * input, char delim, char delim2){
char ** output;
char ** quotes;
char * line = input;
int flag = 0;
if(strlen(input) > 0 && input[0] == delim){
flag = 1;
line = input + 1;
}
int i = 0;
char * pch = strchr(line, delim);
while(pch != NULL){
i++;
pch = strchr(pch+1, delim);
}
quotes = (char **) malloc(sizeof(char *)*i+1);
char * token = strtok(input, delim);
int n = 0;
while(token != NULL){
quotes[n] = strdup(token);
token = strtok(NULL, delim);
n++;
}
if(delim2 != NULL){
int j = 0, k = 0, l = 0;
for(n = 0; n < i+1; n++){
if(flag & n % 2 == 1 || !flag & n % 2 == 0){
char ** new = parser(delim2, NULL);
l = sizeof(new)/sizeof(char *);
for(k = 0; k < l; k++){
output[j] = new[k];
j++;
}
for(k = l; k > -1; k--){
free(new[n]);
}
free(new);
} else {
output[j] = quotes[n];
j++;
}
}
for(n = i; n > -1; n--){
free(quotes[n]);
}
free(quotes);
} else {
return quotes;
}
return output;
}
int main(){
char * input;
char ** result = parser(input, '\"', ' ');
return 0;
}
(May not be perfect, I haven't tested it)
This question already has answers here:
How do I trim leading/trailing whitespace in a standard way?
(40 answers)
Closed 5 years ago.
Briefly:
I'm after the equivalent of .NET's String.Trim in C using the win32 and standard C api (compiling with MSVC2008 so I have access to all the C++ stuff if needed, but I am just trying to trim a char*).
Given that there is strchr, strtok, and all manner of other string functions, surely there should be a trim function, or one that can be repurposed...
Thanks
There is no standard library function to do this, but it's not too hard to roll your own. There is an existing question on SO about doing this that was answered with source code.
This made me want to write my own - I didn't like the ones that had been provided. Seems to me there should be 3 functions.
char *ltrim(char *s)
{
while(isspace(*s)) s++;
return s;
}
char *rtrim(char *s)
{
char* back = s + strlen(s);
while(isspace(*--back));
*(back+1) = '\0';
return s;
}
char *trim(char *s)
{
return rtrim(ltrim(s));
}
You can use the standard isspace() function in ctype.h to achieve this. Simply compare the beginning and end characters of your character array until both ends no longer have spaces.
"spaces" include:
' ' (0x20) space (SPC)
'\t' (0x09) horizontal tab (TAB)
'\n' (0x0a) newline (LF)
'\v' (0x0b) vertical tab (VT)
'\f' (0x0c) feed (FF)
'\r' (0x0d) carriage return (CR)
although there is no function which will do all of the work for you, you will have to roll your own solution to compare each side of the given character array repeatedly until no spaces remain.
Edit:
Since you have access to C++, Boost has a trim implementation waiting for you to make your life a lot easier.
Surprised to see such implementations. I usually do trim like this:
char *trim(char *s) {
char *ptr;
if (!s)
return NULL; // handle NULL string
if (!*s)
return s; // handle empty string
for (ptr = s + strlen(s) - 1; (ptr >= s) && isspace(*ptr); --ptr);
ptr[1] = '\0';
return s;
}
It is fast and reliable - serves me many years.
/* Function to remove white spaces on both sides of a string i.e trim */
void trim (char *s)
{
int i;
while (isspace (*s)) s++; // skip left side white spaces
for (i = strlen (s) - 1; (isspace (s[i])); i--) ; // skip right side white spaces
s[i + 1] = '\0';
printf ("%s\n", s);
}
#include "stdafx.h"
#include <string.h>
#include <ctype.h>
char* trim(char* input);
int _tmain(int argc, _TCHAR* argv[])
{
char sz1[]=" MQRFH ";
char sz2[]=" MQRFH";
char sz3[]=" MQR FH";
char sz4[]="MQRFH ";
char sz5[]="MQRFH";
char sz6[]="M";
char sz7[]="M ";
char sz8[]=" M";
char sz9[]="";
char sz10[]=" ";
printf("sz1:[%s] %d\n",trim(sz1), strlen(sz1));
printf("sz2:[%s] %d\n",trim(sz2), strlen(sz2));
printf("sz3:[%s] %d\n",trim(sz3), strlen(sz3));
printf("sz4:[%s] %d\n",trim(sz4), strlen(sz4));
printf("sz5:[%s] %d\n",trim(sz5), strlen(sz5));
printf("sz6:[%s] %d\n",trim(sz6), strlen(sz6));
printf("sz7:[%s] %d\n",trim(sz7), strlen(sz7));
printf("sz8:[%s] %d\n",trim(sz8), strlen(sz8));
printf("sz9:[%s] %d\n",trim(sz9), strlen(sz9));
printf("sz10:[%s] %d\n",trim(sz10), strlen(sz10));
return 0;
}
char *ltrim(char *s)
{
while(isspace(*s)) s++;
return s;
}
char *rtrim(char *s)
{
char* back;
int len = strlen(s);
if(len == 0)
return(s);
back = s + len;
while(isspace(*--back));
*(back+1) = '\0';
return s;
}
char *trim(char *s)
{
return rtrim(ltrim(s));
}
Output:
sz1:[MQRFH] 9
sz2:[MQRFH] 6
sz3:[MQR FH] 8
sz4:[MQRFH] 7
sz5:[MQRFH] 5
sz6:[M] 1
sz7:[M] 2
sz8:[M] 2
sz9:[] 0
sz10:[] 8
I like it when the return value always equals the argument. This way, if the string array has been allocated with malloc(), it can safely be free() again.
/* Remove leading whitespaces */
char *ltrim(char *const s)
{
size_t len;
char *cur;
if(s && *s) {
len = strlen(s);
cur = s;
while(*cur && isspace(*cur))
++cur, --len;
if(s != cur)
memmove(s, cur, len + 1);
}
return s;
}
/* Remove trailing whitespaces */
char *rtrim(char *const s)
{
size_t len;
char *cur;
if(s && *s) {
len = strlen(s);
cur = s + len - 1;
while(cur != s && isspace(*cur))
--cur, --len;
cur[isspace(*cur) ? 0 : 1] = '\0';
}
return s;
}
/* Remove leading and trailing whitespaces */
char *trim(char *const s)
{
rtrim(s); // order matters
ltrim(s);
return s;
}
void ltrim(char str[PATH_MAX])
{
int i = 0, j = 0;
char buf[PATH_MAX];
strcpy(buf, str);
for(;str[i] == ' ';i++);
for(;str[i] != '\0';i++,j++)
buf[j] = str[i];
buf[j] = '\0';
strcpy(str, buf);
}
static inline void ut_trim(char * str) {
char * start = str;
char * end = start + strlen(str);
while (--end >= start) { /* trim right */
if (!isspace(*end))
break;
}
*(++end) = '\0';
while (isspace(*start)) /* trim left */
start++;
if (start != str) /* there is a string */
memmove(str, start, end - start + 1);
}
How about this... It only requires one iteration over the string (doesn't use strlen, which iterates over the string). When the function returns you get a pointer to the start of the trimmed string which is null terminated. The string is trimmed of spaces from the left (until the first character is found). The string is also trimmed of all trailing spaces after the last nonspace character.
char* trim(char* input) {
char* start = input;
while (isSpace(*start)) { //trim left
start++;
}
char* ptr = start;
char* end = start;
while (*ptr++ != '\0') { //trim right
if (!isSpace(*ptr)) { //only move end pointer if char isn't a space
end = ptr;
}
}
*end = '\0'; //terminate the trimmed string with a null
return start;
}
bool isSpace(char c) {
switch (c) {
case ' ':
case '\n':
case '\t':
case '\f':
case '\r':
return true;
break;
default:
return false;
break;
}
}
/* iMode 0:ALL, 1:Left, 2:Right*/
char* Trim(char* szStr,const char ch, int iMode)
{
if (szStr == NULL)
return NULL;
char szTmp[1024*10] = { 0x00 };
strcpy(szTmp, szStr);
int iLen = strlen(szTmp);
char* pStart = szTmp;
char* pEnd = szTmp+iLen;
int i;
for(i = 0;i < iLen;i++){
if (szTmp[i] == ch && pStart == szTmp+i && iMode != 2)
++pStart;
if (szTmp[iLen-i-1] == ch && pEnd == szTmp+iLen-i && iMode != 1)
*(--pEnd) = '\0';
}
strcpy(szStr, pStart);
return szStr;
}
Here's my implementation, behaving like the built-in string functions in libc (that is, it expects a c-string, it modifies it and returns it to the caller).
It trims leading spaces & shifts the remaining chars to the left, as it parses the string from left to right. It then marks a new end of string and starts parsing it backwards, replacing trailing spaces with '\0's until it finds either a non-space char or the start of the string. I believe those are the minimum possible iterations for this particular task.
// ----------------------------------------------------------------------------
// trim leading & trailing spaces from string s (return modified string s)
// alg:
// - skip leading spaces, via cp1
// - shift remaining *cp1's to the left, via cp2
// - mark a new end of string
// - replace trailing spaces with '\0', via cp2
// - return the trimmed s
//
char *s_trim(char *s)
{
char *cp1; // for parsing the whole s
char *cp2; // for shifting & padding
// skip leading spaces, shift remaining chars
for (cp1=s; isspace(*cp1); cp1++ ) // skip leading spaces, via cp1
;
for (cp2=s; *cp1; cp1++, cp2++) // shift left remaining chars, via cp2
*cp2 = *cp1;
*cp2-- = 0; // mark new end of string for s
// replace trailing spaces with '\0'
while ( cp2 > s && isspace(*cp2) )
*cp2-- = 0; // pad with '\0's
return s;
}
Not the best way but it works
char* Trim(char* str)
{
int len = strlen(str);
char* buff = new char[len];
int i = 0;
memset(buff,0,len*sizeof(char));
do{
if(isspace(*str)) continue;
buff[i] = *str; ++i;
} while(*(++str) != '\0');
return buff;
}
void inPlaceStrTrim(char* str) {
int k = 0;
int i = 0;
for (i=0; str[i] != '\0';) {
if (isspace(str[i])) {
// we have got a space...
k = i;
for (int j=i; j<strlen(str)-1; j++) {
str[j] = str[j+1];
}
str[strlen(str)-1] = '\0';
i = k; // start the loop again where we ended..
} else {
i++;
}
}
}
Easiest thing to do is a simple loop. I'm going to assume that you want the trimmed string returned in place.
char *
strTrim(char * s){
int ix, jx;
int len ;
char * buf
len = strlen(s); /* possibly should use strnlen */
buf = (char *) malloc(strlen(s)+1);
for(ix=0, jx=0; ix < len; ix++){
if(!isspace(s[ix]))
buf[jx++] = s[ix];
buf[jx] = '\0';
strncpy(s, buf, jx); /* always looks as far as the null, but who cares? */
free(buf); /* no good leak goes unpunished */
return s; /* modifies s in place *and* returns it for swank */
}
This gets rid of embedded blanks too, if String.Trim doesn't then it needs a bit more logic.
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;
}