I am trying to make a shell and one of the conditions i am looking out for is when the user enters a bunch of spaces. However, I get a segfault from fgets when I input any number of spaces in the terminal. It can be one space, or it can be a whole bunch of them followed by a random character. I keep getting a segfault.
Development:
I noticed that I don't get a segfault when I remove my tokenize function. Why would this be the case?
Here's my code:
#include <stdlib.h>
#include <assert.h>
#include <string.h>
#include <stdio.h>
/* Initialize variables and methods */
int status;
int i;
int one_nonspace = -1;
int on = 1;
char input[101];
char temp[101];
char* tokenized;
char operators[3] = {'>', '<', '|'};
char** tokens;
void getInput(char *prmpt, char *buff){
printf(">:");
fgets(buff, 101, stdin); //segfault here when input spaces.
/*printf("works!");*/
if(one_nonspace != -1){
printf("spaces");
memcpy( temp, &buff[i], (101-i) );
temp[100] = '\0';
}
if(buff[strlen(buff) -1] != '\n'){
int over = 0;
while(fgetc(stdin) != '\n')
over++;
if(over>0)
{
printf("Command is over 100 characters. Please try again\n");
status = 1;
}
}
else{
buff[strlen(buff) - 1] = '\0';
status = 0;
}
}
char** tokenize(char* a_str)
{
char** result = 0;
size_t count = 0;
char* tmp = a_str;
char* last = 0;
char delim[2];
delim[0] = ' ';
delim[1] = 0;
/* Count how many elements will be extracted. */
while (*tmp)
{
if (' ' == *tmp)
{
count++;
last = tmp;
}
tmp++;
}
/* Add space for trailing token. */
count += last < (a_str + strlen(a_str) - 1);
/* Add space for terminating null string so caller
knows where the list of returned strings ends. */
count++;
result = malloc(sizeof(char*) * count);
if (result)
{
size_t idx = 0;
char* token = strtok(a_str, delim);
while (token)
{
assert(idx < count);
*(result + idx++) = strdup(token);
token = strtok(0, delim);
}
assert(idx == count - 1);
*(result + idx) = 0;
}
return result;
}
/* Create a parser Feb 2*/
int main(int argc, char **argv){
while(on){
getInput(">: ", input);
tokenized = input;
if(status == 0){
/*printf("%s\n", input);*/
}
/*Split the line into tokens*/
if(input[0] != ' ')
tokens = tokenize(tokenized);
/*if tokens[0] == 'exit', then quit.
*/
if(strcmp(*(tokens),"exit") == 0){
break;}
/*2/3 Now we need to do something with the split up tokens*/
/*printf("input after token: %s\n", input);*/
/*Free the tokens at the end!!! Remember this!*/
if (tokens)
{
int i;
for (i = 0; *(tokens + i); i++)
{
printf("%s\n", *(tokens + i));
free(*(tokens + i));
}
free(tokens);
}
}
return 0;
}
Here's the problem:
/*Split the line into tokens*/
if(input[0] != ' ')
tokens = tokenize(tokenized);
/*if tokens[0] == 'exit', then quit.
*/
if(strcmp(*(tokens),"exit") == 0){
break;}
When input begins with a space character, you skip the tokenize function and attempt to dereference tokens - a NULL pointer.
Edit: you are trying to debug with print statements and that is a valid method, but remember to flush the buffers or you won't get an accurate idea of where the problem is if the crash happens before there's any output. You can flush them explicitly with fflush or simply use newline characters if you're on a terminal, as they are usually line buffered.
Related
I have a variable length string that I am trying to divide from plus signs and study on:
char string[] = "var1+vari2+varia3";
for (int i = 0; i != sizeof(string); i++) {
memcpy(buf, string[0], 4);
buf[9] = '\0';
}
since variables are different in size I am trying to write something that is going to take string into loop and extract (divide) variables. Any suggestions ? I am expecting result such as:
var1
vari2
varia3
You can use strtok() to break the string by delimiter
char string[]="var1+vari2+varia3";
const char delim[] = "+";
char *token;
/* get the first token */
token = strtok(string, delim);
/* walk through other tokens */
while( token != NULL ) {
printf( " %s\n", token );
token = strtok(NULL, delim);
}
More info about the strtok() here: https://man7.org/linux/man-pages/man3/strtok.3.html
It seems to me that you don't just want to want to print the individual strings but want to save the individual strings in some buffer.
Since you can't know the number of strings nor the length of the individual string, you should allocate memory dynamic, i.e. use functions like realloc, calloc and malloc.
It can be implemented in several ways. Below is one example. To keep the example simple, it's not performance optimized in anyway.
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <assert.h>
char** split_string(const char* string, const char* token, int* num)
{
assert(string != NULL);
assert(token != NULL);
assert(num != NULL);
assert(strlen(token) != 0);
char** data = NULL;
int num_strings = 0;
while(*string)
{
// Allocate memory for one more string pointer
char** ptemp = realloc(data, (num_strings + 1) * sizeof *data);
if (ptemp == NULL) exit(1);
data = ptemp;
// Look for token
char* tmp = strstr(string, token);
if (tmp == NULL)
{
// Last string
// Allocate memory for one more string and copy it
int len = strlen(string);
data[num_strings] = calloc(len + 1, 1);
if (data[num_strings] == NULL) exit(1);
memcpy(data[num_strings], string, len);
++num_strings;
break;
}
// Allocate memory for one more string and copy it
int len = tmp - string;
data[num_strings] = calloc(len + 1, 1);
if (data[num_strings] == NULL) exit(1);
memcpy(data[num_strings], string, len);
// Prepare to search for next string
++num_strings;
string = tmp + strlen(token);
}
*num = num_strings;
return data;
}
int main()
{
char string[]="var1+vari2+varia3";
// Split the string into dynamic allocated memory
int num_strings;
char** data = split_string(string, "+", &num_strings);
// Now data can be used as an array-of-strings
// Example: Print the strings
printf("Found %d strings:\n", num_strings);
for(int i = 0; i < num_strings; ++i) printf("%s\n", data[i]);
// Free the memory
for(int i = 0; i < num_strings; ++i) free(data[i]);
free(data);
}
Output
Found 3 strings:
var1
vari2
varia3
You can use a simple loop scanning the string for + signs:
char string[] = "var1+vari2+varia3";
char buf[sizeof(string)];
int start = 0;
for (int i = 0;;) {
if (string[i] == '+' || string[i] == '\0') {
memcpy(buf, string + start, i - start);
buf[i - start] = '\0';
// buf contains the substring, use it as a C string
printf("%s\n", buf);
if (string[i] == '\0')
break;
start = ++i;
} else {
i++;
}
}
Your code does not have any sense.
I wrote such a function for you. Analyse it as sometimes is good to have some code as a base
char *substr(const char *str, char *buff, const size_t start, const size_t len)
{
size_t srcLen;
char *result = buff;
if(str && buff)
{
if(*str)
{
srcLen = strlen(str);
if(srcLen < start + len)
{
if(start < srcLen) strcpy(buff, str + start);
else buff[0] = 0;
}
else
{
memcpy(buff, str + start, len);
buff[len] = 0;
}
}
else
{
buff[0] = 0;
}
}
return result;
}
https://godbolt.org/z/GjMEqx
I have a .csv file:
lp;imie;nazwisko;ulica;numer;kod;miejscowosc;telefon;email;data_ur
1;Jan;Kowalski;ul. Nowa;1a;11-234;Budry;123-123-456;jan#go.xxx;1980.05.13
2;Jerzy;Nowak;ul. Konopnicka;13a/3;00-900;Lichowice;(55)333-44-55;jer#wu.to;1990.03.23
And I need to read this in C. I have some code, but only for the connection.
Hopefully this would get you started
See it live on http://ideone.com/l23He (using stdin)
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
const char* getfield(char* line, int num)
{
const char* tok;
for (tok = strtok(line, ";");
tok && *tok;
tok = strtok(NULL, ";\n"))
{
if (!--num)
return tok;
}
return NULL;
}
int main()
{
FILE* stream = fopen("input", "r");
char line[1024];
while (fgets(line, 1024, stream))
{
char* tmp = strdup(line);
printf("Field 3 would be %s\n", getfield(tmp, 3));
// NOTE strtok clobbers tmp
free(tmp);
}
}
Output:
Field 3 would be nazwisko
Field 3 would be Kowalski
Field 3 would be Nowak
The following code is in plain c language and handles blank spaces.
It only allocates memory once, so one free() is needed, for each processed line.
http://ideone.com/mSCgPM
/* Tiny CSV Reader */
/* Copyright (C) 2015, Deligiannidis Konstantinos
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://w...content-available-to-author-only...u.org/licenses/>. */
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
/* For more that 100 columns or lines (when delimiter = \n), minor modifications are needed. */
int getcols( const char * const line, const char * const delim, char ***out_storage )
{
const char *start_ptr, *end_ptr, *iter;
char **out;
int i; //For "for" loops in the old c style.
int tokens_found = 1, delim_size, line_size; //Calculate "line_size" indirectly, without strlen() call.
int start_idx[100], end_idx[100]; //Store the indexes of tokens. Example "Power;": loc('P')=1, loc(';')=6
//Change 100 with MAX_TOKENS or use malloc() for more than 100 tokens. Example: "b1;b2;b3;...;b200"
if ( *out_storage != NULL ) return -4; //This SHOULD be NULL: Not Already Allocated
if ( !line || !delim ) return -1; //NULL pointers Rejected Here
if ( (delim_size = strlen( delim )) == 0 ) return -2; //Delimiter not provided
start_ptr = line; //Start visiting input. We will distinguish tokens in a single pass, for good performance.
//Then we are allocating one unified memory region & doing one memory copy.
while ( ( end_ptr = strstr( start_ptr, delim ) ) ) {
start_idx[ tokens_found -1 ] = start_ptr - line; //Store the Index of current token
end_idx[ tokens_found - 1 ] = end_ptr - line; //Store Index of first character that will be replaced with
//'\0'. Example: "arg1||arg2||end" -> "arg1\0|arg2\0|end"
tokens_found++; //Accumulate the count of tokens.
start_ptr = end_ptr + delim_size; //Set pointer to the next c-string within the line
}
for ( iter = start_ptr; (*iter!='\0') ; iter++ );
start_idx[ tokens_found -1 ] = start_ptr - line; //Store the Index of current token: of last token here.
end_idx[ tokens_found -1 ] = iter - line; //and the last element that will be replaced with \0
line_size = iter - line; //Saving CPU cycles: Indirectly Count the size of *line without using strlen();
int size_ptr_region = (1 + tokens_found)*sizeof( char* ); //The size to store pointers to c-strings + 1 (*NULL).
out = (char**) malloc( size_ptr_region + ( line_size + 1 ) + 5 ); //Fit everything there...it is all memory.
//It reserves a contiguous space for both (char**) pointers AND string region. 5 Bytes for "Out of Range" tests.
*out_storage = out; //Update the char** pointer of the caller function.
//"Out of Range" TEST. Verify that the extra reserved characters will not be changed. Assign Some Values.
//char *extra_chars = (char*) out + size_ptr_region + ( line_size + 1 );
//extra_chars[0] = 1; extra_chars[1] = 2; extra_chars[2] = 3; extra_chars[3] = 4; extra_chars[4] = 5;
for ( i = 0; i < tokens_found; i++ ) //Assign adresses first part of the allocated memory pointers that point to
out[ i ] = (char*) out + size_ptr_region + start_idx[ i ]; //the second part of the memory, reserved for Data.
out[ tokens_found ] = (char*) NULL; //[ ptr1, ptr2, ... , ptrN, (char*) NULL, ... ]: We just added the (char*) NULL.
//Now assign the Data: c-strings. (\0 terminated strings):
char *str_region = (char*) out + size_ptr_region; //Region inside allocated memory which contains the String Data.
memcpy( str_region, line, line_size ); //Copy input with delimiter characters: They will be replaced with \0.
//Now we should replace: "arg1||arg2||arg3" with "arg1\0|arg2\0|arg3". Don't worry for characters after '\0'
//They are not used in standard c lbraries.
for( i = 0; i < tokens_found; i++) str_region[ end_idx[ i ] ] = '\0';
//"Out of Range" TEST. Wait until Assigned Values are Printed back.
//for ( int i=0; i < 5; i++ ) printf("c=%x ", extra_chars[i] ); printf("\n");
// *out memory should now contain (example data):
//[ ptr1, ptr2,...,ptrN, (char*) NULL, "token1\0", "token2\0",...,"tokenN\0", 5 bytes for tests ]
// |__________________________________^ ^ ^ ^
// |_______________________________________| | |
// |_____________________________________________| These 5 Bytes should be intact.
return tokens_found;
}
int main()
{
char in_line[] = "Arg1;;Th;s is not Del;m;ter;;Arg3;;;;Final";
char delim[] = ";;";
char **columns;
int i;
printf("Example1:\n");
columns = NULL; //Should be NULL to indicate that it is not assigned to allocated memory. Otherwise return -4;
int cols_found = getcols( in_line, delim, &columns);
for ( i = 0; i < cols_found; i++ ) printf("Column[ %d ] = %s\n", i, columns[ i ] ); //<- (1st way).
// (2nd way) // for ( i = 0; columns[ i ]; i++) printf("start_idx[ %d ] = %s\n", i, columns[ i ] );
free( columns ); //Release the Single Contiguous Memory Space.
columns = NULL; //Pointer = NULL to indicate it does not reserve space and that is ready for the next malloc().
printf("\n\nExample2, Nested:\n\n");
char example_file[] = "ID;Day;Month;Year;Telephone;email;Date of registration\n"
"1;Sunday;january;2009;123-124-456;jitter#go.xyz;2015-05-13\n"
"2;Monday;March;2011;(+30)333-22-55;buffer#wl.it;2009-05-23";
char **rows;
int j;
rows = NULL; //getcols() requires it to be NULL. (Avoid dangling pointers, leaks e.t.c).
getcols( example_file, "\n", &rows);
for ( i = 0; rows[ i ]; i++) {
{
printf("Line[ %d ] = %s\n", i, rows[ i ] );
char **columnX = NULL;
getcols( rows[ i ], ";", &columnX);
for ( j = 0; columnX[ j ]; j++) printf(" Col[ %d ] = %s\n", j, columnX[ j ] );
free( columnX );
}
}
free( rows );
rows = NULL;
return 0;
}
A complete example which leaves the fields as NULL-terminated strings in the original input buffer and provides access to them via an array of char pointers. The CSV processor has been confirmed to work with fields enclosed in "double quotes", ignoring any delimiter chars within them.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
// adjust BUFFER_SIZE to suit longest line
#define BUFFER_SIZE 1024 * 1024
#define NUM_FIELDS 10
#define MAXERRS 5
#define RET_OK 0
#define RET_FAIL 1
#define FALSE 0
#define TRUE 1
// char* array will point to fields
char *pFields[NUM_FIELDS];
// field offsets into pFields array:
#define LP 0
#define IMIE 1
#define NAZWISKo 2
#define ULICA 3
#define NUMER 4
#define KOD 5
#define MIEJSCOw 6
#define TELEFON 7
#define EMAIL 8
#define DATA_UR 9
long loadFile(FILE *pFile, long *errcount);
static int loadValues(char *line, long lineno);
static char delim;
long loadFile(FILE *pFile, long *errcount){
char sInputBuf [BUFFER_SIZE];
long lineno = 0L;
if(pFile == NULL)
return RET_FAIL;
while (!feof(pFile)) {
// load line into static buffer
if(fgets(sInputBuf, BUFFER_SIZE-1, pFile)==NULL)
break;
// skip first line (headers)
if(++lineno==1)
continue;
// jump over empty lines
if(strlen(sInputBuf)==0)
continue;
// set pFields array pointers to null-terminated string fields in sInputBuf
if(loadValues(sInputBuf,lineno)==RET_FAIL){
(*errcount)++;
if(*errcount > MAXERRS)
break;
} else {
// On return pFields array pointers point to loaded fields ready for load into DB or whatever
// Fields can be accessed via pFields, e.g.
printf("lp=%s, imie=%s, data_ur=%s\n", pFields[LP], pFields[IMIE], pFields[DATA_UR]);
}
}
return lineno;
}
static int loadValues(char *line, long lineno){
if(line == NULL)
return RET_FAIL;
// chop of last char of input if it is a CR or LF (e.g.Windows file loading in Unix env.)
// can be removed if sure fgets has removed both CR and LF from end of line
if(*(line + strlen(line)-1) == '\r' || *(line + strlen(line)-1) == '\n')
*(line + strlen(line)-1) = '\0';
if(*(line + strlen(line)-1) == '\r' || *(line + strlen(line)-1 )== '\n')
*(line + strlen(line)-1) = '\0';
char *cptr = line;
int fld = 0;
int inquote = FALSE;
char ch;
pFields[fld]=cptr;
while((ch=*cptr) != '\0' && fld < NUM_FIELDS){
if(ch == '"') {
if(! inquote)
pFields[fld]=cptr+1;
else {
*cptr = '\0'; // zero out " and jump over it
}
inquote = ! inquote;
} else if(ch == delim && ! inquote){
*cptr = '\0'; // end of field, null terminate it
pFields[++fld]=cptr+1;
}
cptr++;
}
if(fld > NUM_FIELDS-1){
fprintf(stderr, "Expected field count (%d) exceeded on line %ld\n", NUM_FIELDS, lineno);
return RET_FAIL;
} else if (fld < NUM_FIELDS-1){
fprintf(stderr, "Expected field count (%d) not reached on line %ld\n", NUM_FIELDS, lineno);
return RET_FAIL;
}
return RET_OK;
}
int main(int argc, char **argv)
{
FILE *fp;
long errcount = 0L;
long lines = 0L;
if(argc!=3){
printf("Usage: %s csvfilepath delimiter\n", basename(argv[0]));
return (RET_FAIL);
}
if((delim=argv[2][0])=='\0'){
fprintf(stderr,"delimiter must be specified\n");
return (RET_FAIL);
}
fp = fopen(argv[1] , "r");
if(fp == NULL) {
fprintf(stderr,"Error opening file: %d\n",errno);
return(RET_FAIL);
}
lines=loadFile(fp,&errcount);
fclose(fp);
printf("Processed %ld lines, encountered %ld error(s)\n", lines, errcount);
if(errcount>0)
return(RET_FAIL);
return(RET_OK);
}
Use fscanf to read the file until you encounter ';' or \n, then just skip it with fscanf(f, "%*c").
int main()
{
char str[128];
int result;
FILE* f = fopen("test.txt", "r");
/*...*/
do {
result = fscanf(f, "%127[^;\n]", str);
if(result == 0)
{
result = fscanf(f, "%*c");
}
else
{
//Put here whatever you want to do with your value.
printf("%s\n", str);
}
} while(result != EOF);
return 0;
}
This code is fairly simple, but effective. It parses comma-separated files with parenthesis. You can easily modify it to suit your needs.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main(int argc, char *argv[])
{
// argv[1] path to csv file
// argv[2] number of lines to skip
// argv[3] length of longest value (in characters)
FILE *pfinput;
unsigned int nSkipLines, currentLine, lenLongestValue;
char *pTempValHolder;
int c;
unsigned int vcpm; // Value character marker
int QuotationOnOff; // 0 - off, 1 - on
nSkipLines = atoi(argv[2]);
lenLongestValue = atoi(argv[3]);
pTempValHolder = (char*)malloc(lenLongestValue);
if(pfinput = fopen(argv[1], "r")) {
rewind(pfinput);
currentLine = 1;
vcpm = 0;
QuotationOnOff = 0;
// currentLine > nSkipLines condition
// skips / ignores first argv[2] lines
while((c = fgetc(pfinput)) != EOF)
{
switch(c)
{
case ',':
if(!QuotationOnOff && currentLine > nSkipLines)
{
pTempValHolder[vcpm] = '\0';
printf("%s,", pTempValHolder);
vcpm = 0;
}
break;
case '\n':
if(currentLine > nSkipLines)
{
pTempValHolder[vcpm] = '\0';
printf("%s\n", pTempValHolder);
vcpm = 0;
}
currentLine++;
break;
case '\"':
if(currentLine > nSkipLines)
{
if(!QuotationOnOff) {
QuotationOnOff = 1;
pTempValHolder[vcpm] = c;
vcpm++;
} else {
QuotationOnOff = 0;
pTempValHolder[vcpm] = c;
vcpm++;
}
}
break;
default:
if(currentLine > nSkipLines)
{
pTempValHolder[vcpm] = c;
vcpm++;
}
break;
}
}
fclose(pfinput);
free(pTempValHolder);
}
return 0;
}
#include <conio.h>
#include <stdio.h>
#include <string.h>
// Driver Code
int main()
{
// Substitute the full file path
// for the string file_path
FILE* fp = fopen("Movie.csv", "r");
char *wrds[40];
if (!fp)
printf("Can't open file\n");
else {
// Here we have taken size of
// array 1024 you can modify it
char buffer[1024];
int row = 0;
int column = 0;
while (fgets(buffer, 1024, fp)) {
column = 0;
row++;
// To avoid printing of column
// names in file can be changed
// according to need
if (row == 1)
continue;
// Splitting the data
char* value = strtok(buffer, ", ");
while (value) {
// Column 1
if (column == 0) {
printf("Name :");
}
// Column 2
if (column == 1) {
printf("\tAccount No. :");
}
// Column 3
if (column == 2) {
printf("\tAmount :");
}
printf("%s", value);
wrds[column] = value;
value = strtok(NULL, ", ");
column++;
}
printf("\n");
}
// Close the file
fclose(fp);
}
getchar();
return 0;
}
I get a runtime error when running a C program,
Here is the C source (parsing.h header code a little lower):
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "parsing.h"
int main()
{
printf("Enter text seperated by single spaces :\n");
char *a = malloc(sizeof(char)*10);
gets(a);
char **aa = Split(a, ' ');
int k = SplitLen(a, ' ');
int i = 0;
for(;i<k;i++)
{
printf("%s\n", aa[i]);
}
free(a);
free(aa);
return 0;
}
and the parsing.h file:
#include <string.h>
#include <stdlib.h>
#include <malloc.h>
#include <assert.h>
char** Split(char* a_str, const char a_delim)
{
char** result = 0;
int count = 0;
char* tmp = a_str;
char* last_comma = 0;
/* Count how many elements will be extracted. */
while (*tmp)
{
if (a_delim == *tmp)
{
count++;
last_comma = tmp;
}
tmp++;
}
/* Add space for trailing token. */
count += last_comma < (a_str + strlen(a_str) - 1);
/* Add space for terminating null string so caller
knows where the list of returned strings ends. */
count++;
result = malloc(sizeof(char*) * count);
if (result)
{
size_t idx = 0;
char* token = strtok(a_str, ",");
while (token)
{
assert(idx < count);
*(result + idx++) = strdup(token);
token = strtok(0, ",");
}
assert(idx == count - 1);
*(result + idx) = 0;
}
return result;
}
int SplitLen(char *src, char sep)
{
int result = 0;
int i;
for(i = 0; i<strlen(src); i++)
{
if(src[i] == sep)
{
result += 1;
}
}
return result;
}
I'm sure most of the code is unneeded but I posted the whole lot in case there is some relevance, Here is the runtime error:
a.out: parsing.h:69: Split: Assertion `idx == count - 1' failed.
Aborted
Thanks in advance and for info I didn't program the whole lot but took some pieces from some places but most is my programming Thanks!.
The purpose of the assert function is that is will stop your program if the condition passed as an argument is false. What this tells you is that when you ran your program, idx != count - 1 at line 69. I didn't take the time to check what import that has on the execution of your program, but apparently (?) idx was intended to equal count - 1 there.
Does that help?
There are many problems. I'm ignoring the code split into two files; I'm treating it as a single file (see comments to question).
Do not use gets(). Never use gets(). Do not ever use gets(). I said it three times; it must be true. Note that gets() is no longer a Standard C function (it was removed from the C11 standard — ISO/IEC 9899:2011) because it cannot be used safely. Use fgets() or another safe function instead.
You don't need to use dynamic memory allocation for a string of 10 characters; use a local variable (it is simpler).
You need a bigger string — think about 4096.
You don't check whether you got any data; always check input function calls.
You don't free all the substrings at the end of main(), thus leaking memory.
One major problem the Split() code slices and dices the input string so that SplitLen() cannot give you the same answer that Split() does for the number of fields. The strtok() function is destructive. It also treats multiple adjacent delimiters as a single delimiter. Your code won't account for the difference.
Another major problem is that you analyze the strings based on the delimiter passed into the Split() function, but you use strtok(..., ',') to actually split on commas. This is more consistent with the commentary and names, but totally misleading to you. This is why your assertion fired.
You don't need to include <malloc.h> unless you are using the extra facilities it provides. You aren't, so you should not include it; <stdlib.h> declares malloc() and free() perfectly well.
This code works for me; I've annotated most of the places I made changes.
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
static int altSplitLen(char **array);
static char **Split(char *a_str, const char a_delim);
static int SplitLen(char *src, char sep);
int main(void)
{
printf("Enter text separated by single spaces:\n");
char a[4096]; // Simpler
if (fgets(a, sizeof(a), stdin) != 0) // Error checked!
{
char **aa = Split(a, ' ');
int k = SplitLen(a, ' ');
printf("SplitLen() says %d; altSplitLen() says %d\n", k, altSplitLen(aa));
for (int i = 0; i < k; i++)
{
printf("%s\n", aa[i]);
}
/* Workaround for broken SplitLen() */
{
puts("Loop to null pointer:");
char **data = aa;
while (*data != 0)
printf("[%s]\n", *data++);
}
{
// Fix for major leak!
char **data = aa;
while (*data != 0)
free(*data++);
}
free(aa); // Major leak!
}
return 0;
}
char **Split(char *a_str, const char a_delim)
{
char **result = 0;
size_t count = 0;
char *tmp = a_str;
char *last_comma = 0;
/* Count how many elements will be extracted. */
while (*tmp)
{
if (a_delim == *tmp)
{
count++;
last_comma = tmp;
}
tmp++;
}
/* Add space for trailing token. */
count += last_comma < (a_str + strlen(a_str) - 1);
/* Add space for terminating null string so caller
knows where the list of returned strings ends. */
count++;
result = malloc(sizeof(char *) * count);
if (result)
{
char delim[2] = { a_delim, '\0' }; // Fix for inconsistent splitting
size_t idx = 0;
char *token = strtok(a_str, delim);
while (token)
{
assert(idx < count);
*(result + idx++) = strdup(token);
token = strtok(0, delim);
}
assert(idx == count - 1);
*(result + idx) = 0;
}
return result;
}
int SplitLen(char *src, char sep)
{
int result = 0;
for (size_t i = 0; i < strlen(src); i++)
{
if (src[i] == sep)
{
result += 1;
}
}
return result;
}
static int altSplitLen(char **array)
{
int i = 0;
while (*array++ != 0)
i++;
return i;
}
Sample run:
$ parsing
Enter text separated by single spaces:
a b c d e f gg hhh iii jjjj exculpatory evidence
SplitLen() says 0; altSplitLen() says 12
Loop to null pointer:
[a]
[b]
[c]
[d]
[e]
[f]
[gg]
[hhh]
[iii]
[jjjj]
[exculpatory]
[evidence
]
$
Note that fgets() keeps the newline and gets() does not, so the newline was included in output. Note also how the printf() printing the data showed the limits of the strings; that is enormously helpful on many occasions.
I have a problem. I receive a response from a server as an array of chars. Ex: 555#200#. I split the array into 555 and 200 because that is my command. I want to save that command to another array but I get bad results. Here's my code:
void READ_FROM_SERVER(void) {
int read_vkluci = read(sock_descriptor, read_from_server, sizeof(read_from_server));
if (read_vkluci < 0)
printf("Failed reading bytes from server\n");
printf(" %s \n", read_from_server);
if(read_vkluci>0){
char** tokens;
printf("naredbi=%s \n\n", read_from_server);
tokens = str_split(read_from_server, '#');
if (tokens){
int i;
for (i = 0; *(tokens + i); i++){
printf("naredba=%s\n", *(tokens + i));
naredbi_odelno[i]= *(tokens + i);
printf("naredba_odelno=%s\n", naredbi_odelno[i]);
brojnacomandi++;
//free(*(tokens + i));
}
printf("\n");
//free(tokens);
}
}
int p;
for(p=0;p<brojnacomandi;p++){
if (naredbi_odelno[p]==201) {
nadvoresna_komanda = VKLUCI;
printf("VKLUCEN UVLEKUVAC!!!!");
}
if (naredbi_odelno[p]==200) {
nadvoresna_komanda = ISKLUCI;
printf("ISLKUCEN UVLEKUVAC!!!!");
}
if (naredbi_odelno[p]==96) {
printf("TCP_CONN_OK!!!\n");
}
if (naredbi_odelno[p]==211) {
makeTXpaket(STACK_1);
p_tx_buffer_ = &tx_buffer[1];
nbytes = write(fd, tx_buffer, *p_tx_buffer_);
if (nbytes != tx_buffer[1]) {
/* problem! */
printf("error writing on serial port!!!");
}
printf("PRIMAM....\n");
isprateno=0;
}
if (naredbi_odelno[p]==210) {
makeTXpaket( RETURN);
p_tx_buffer_ = &tx_buffer[1];
nbytes = write(fd, tx_buffer, *p_tx_buffer_);
if (nbytes != tx_buffer[1]) {
/* problem! */
printf("error writing on serial port!!!");
}
printf("VRAKAM....\n");
isprateno=0;
}
// else {
// printf("TCP_NOT_OK!!!!\n");
// close(sock_descriptor);
// CONECT_T0_SERVER();
// }
Clean_read_from_server_buff();
Clean_naredbi_odelno();
}
}
char** str_split(char* a_str, const char a_delim){
char** result = 0;
size_t count = 0;
char* tmp = a_str;
char* last_comma = 0;
/* Count how many elements will be extracted. */
while (*tmp){
if (a_delim == *tmp){
count++;
last_comma = tmp;
}
tmp++;
}
/* Add space for trailing token. */
count += last_comma < (a_str + strlen(a_str) - 1);
/* Add space for terminating null string so caller
knows where the list of returned strings ends. */
count++;
result = malloc(sizeof(char*) * count);
if (result){
size_t idx = 0;
char* token = strtok(a_str, "#");
while (token){
assert(idx < count);
*(result + idx++) = strdup(token);
token = strtok(0, "#");
}
assert(idx == count - 1);
*(result + idx) = 0;
}
return result;
}
The server sends me only 555#, but I get in naredba_odelno bad result! Any idea why that is happening?
How do I make naredba_odelno = naredba because naredba is good!
output:
naredbi=555#
naredba=555
naredbi_odelno= ...... bad results why?
My first guess is that you're reading off the end of the input data. Note that read does not nul-terminate the string, so your printf statement is immediately broken.
Try this:
int read_vkluci = read(sock_descriptor, read_from_server, sizeof(read_from_server)-1);
and this
read_from_server[read_vkluci] = '\0';
printf("naredbi=%s \n\n", read_from_server);
BTW, sizeof(read_from_server) will only work correctly if read_from_server is an array type. If it's a pointer to a buffer then that's broken too.
How to split a string into tokens by '&' in C?
strtok / strtok_r
char *token;
char *state;
for (token = strtok_r(input, "&", &state);
token != NULL;
token = strtok_r(NULL, "&", &state))
{
...
}
I would do it something like this (using strchr()):
#include <string.h>
char *data = "this&&that&other";
char *next;
char *curr = data;
while ((next = strchr(curr, '&')) != NULL) {
/* process curr to next-1 */
curr = next + 1;
}
/* process the remaining string (the last token) */
strchr(const char *s, int c) returns a pointer to the next location of c in s, or NULL if c isn't found in s.
You might be able to use strtok(), however, I don't like strtok(), because:
it modifies the string being tokenized, so it doesn't work for literal strings, or is not very useful when you want to keep the string for other purposes. In that case, you must copy the string to a temporary first.
it merges adjacent delimiters, so if your string was "a&&b&c", the returned tokens are "a", "b", and "c". Note that there is no empty token after "a".
it is not thread-safe.
You can use the strok() function as shown in the example below.
/// Function to parse a string in separate tokens
int parse_string(char pInputString[MAX_STRING_LENGTH],char *Delimiter,
char *pToken[MAX_TOKENS])
{
int i;
i = 0;
pToken[i] = strtok(pInputString, Delimiter);
i++;
while ((pToken[i] = strtok(NULL, Delimiter)) != NULL){
i++;
}
return i;
}
/// The array pTokens[] now contains the pointers to the start of each token in the (unchanged) original string.
sprintf(String,"Token1&Token2");
NrOfParameters = parse_string(String,"&",pTokens);
sprintf("%s, %s",pToken[0],pToken[1]);
For me, using strtok() function is unintuitive and too complicated, so I managed to create my own one. As arguments it accepts a string to split, character which determinates spaces between tokens and pointer representing number of found tokens (useful when printing these tokens in loop). A disadvantage of this function is fixed maximum lenght of each token.
#include <stdlib.h>
#include <string.h>
#define MAX_WORD_LEN 32
char **txtspt(const char *text, char split_char, int *w_count)
{
if(strlen(text) <= 1)
return NULL;
char **cpy0 = NULL;
int i, j = 0, k = 0, words = 1;
//Words counting
for(i = 0; i < strlen(text); ++i)
{
if(text[i] == split_char && text[i + 1] != '\0')
{
++words;
}
}
//Memory reservation
cpy0 = (char **) malloc(strlen(text) * words);
for(i = 0; i < words; ++i)
{
cpy0[i] = (char *) malloc(MAX_WORD_LEN);
}
//Splitting
for(i = 0; i < strlen(text) + 1; ++i)
{
if(text[i] == split_char)
{
cpy0[k++][j] = '\0';
j = 0;
}
else
{
if(text[i] != '\n') //Helpful, when using fgets()
cpy0[k][j++] = text[i]; //function
}
}
*w_count = words;
return cpy0;
}