Spliting a string into an array of strings completly dynamicly allocated - c

Question

This question is really close to this to this topic but I prefer the lisibility and the pointers clarification I needed offered by this solution.
So I've got a data file and I get a very long array of char from it. I want to split this string into an array with, in each case, a string wich correspond to a line of this file.
I saw solutions but they all use limited arrays, since I don't know the lenght of each line, I really need to allocate all of them dynamicly but I can't find the lenght of the lines because strtokdoesn't put a null character \0at the end of each string.
What I've got for now is this two solutions but neither work:
int get_lines(char *file, char **lines) {
int nb_lines = 0;
char *token = strtok(file, "\n");
for(int i = 0; token != NULL; i++) {
token = strtok(NULL, "\n");
nb_lines = i;
}
nb_lines++;
lines = malloc((nb_lines + 1) * sizeof(char*));
lines[nb_lines] = '\0';
token = strtok(file, "\n");
for(int i = 0; token != NULL; i++) {
token = strtok(NULL, "\n");
int nb_char = 0;
for(int j = 0; token[j] != '\n'; j++) //This will cause SIGSEGV because strtok don't keep the '\n' at the end
nb_char = j;
nb_char++;
token[nb_char] = '\0'; //This cause SIGSEGV because token's allocation finish at [nb_char-1]
lines[i] = malloc(strlen(token) * sizeof(char)); //strlen cause SIGSEGV because I cannot place the '\0' at the end of token
printf("%s", token); //SIGSEGV because printf don't find the '\0'
lines[i] = token;
}
for(int i = 0; i < nb_lines; i++) {
printf("%s", lines[i]); //SIGSEGV
}
return nb_lines;
}
So you can see above the idea of what I want to do and why it doesn't work.
Below you will see an other try I made but I'm stuck at the same point:
int count_subtrings(char* string, char* separator) {
int nb_lines = 0;
char *token = strtok(string, separator);
for(int i = 0; token != NULL; i++) {
token = strtok(NULL, separator);
nb_lines = i;
}
return nb_lines + 1;
}
char** split_string(char* string, char* separator) {
char **sub_strings = malloc((count_subtrings(string, separator) + 1) * sizeof(char*));
for(int i = 0; string[i] != EOF; i++) {
//How to get the string[i] lenght to malloc them ?
}
}
My file is quite big and the lines can be too so I don't want to malloc an other table with a size of (strlen(file) + 1) * sizeof(char) to be sure each line won't SIGSEGV and I also find this solution quite dirty, if you guys had an other idea, I would be really happy.
(Sorry for the english mistakes, I'm not really good)

Answer 1

Your approach with strtok has two drawbacks: First, strtok modifies the string,so you can only pass the original string once. Second, it skips empty lines, because it tretas stretches of nelines as a single token separator.. (I don't know ehether that is a concern to you.)
You can countthe newlines with a single pass through the string. Allocate memory for your line array and make a second pass, where you split the string at newlines:
char **splitlines(char *msg)
{
char **line;
char *prev = msg;
char *p = msg;
size_t count = 0;
size_t n;
while (*p) {
if (*p== '\n') count++;
p++;
}
line = malloc((count + 2) * sizeof(*line));
if (line == NULL) return NULL;
p = msg;
n = 0;
while (*p) {
if (*p == '\n') {
line[n++] = prev;
*p = '\0';
prev = p + 1;
}
p++;
}
if (*prev) line[n++] = prev;
line[n++] = NULL;
return line;
}
I've allocated two more line pointers than the newlines count: One for the case that the last line doesn't end with a newline and another one to place a NULL sentinel at the end, so that you know where yourarray ends. (You could, of course, return the actual line count via a pointer to a size_t.)

Answer 2

the following proposed code:
cleanly compiles
(within the limits of the heap size) doesn't care about the input file size
echo's the resulting array of file lines, double spaced, just to show it worked. for single spacing, replace the puts() with printf()
and now the code
#include <stdio.h> // getline(), perror(), fopen(), fclose()
#include <stdlib.h> // exit(), EXIT_FAILURE, realloc(), free()
int main( void )
{
FILE *fp = fopen( "untitled1.c", "r" );
if( !fp )
{
perror( "fopen for reading untitled1.c failed" );
exit( EXIT_FAILURE );
}
// implied else, fopen successful
char **lines = NULL;
size_t availableLines = 0;
size_t usedLines = 0;
char *line = NULL;
size_t lineLen = 0;
while( -1 != getline( &line, &lineLen, fp ) )
{
if( usedLines >= availableLines )
{
availableLines = (availableLines)? availableLines*2 : 1;
char **temp = realloc( lines, sizeof( char* ) * availableLines );
if( !temp )
{
perror( "realloc failed" );
free( lines );
fclose( fp );
exit( EXIT_FAILURE );
}
// implied else realloc successful
lines = temp;
}
lines[ usedLines ] = line;
usedLines++;
line = NULL;
lineLen = 0;
}
fclose( fp );
for( size_t i = 0; i<usedLines; i++ )
{
puts( lines[i] );
}
free( lines );
}
Given the above code is in a file named: untitled1.c the following is the output.
#include <stdio.h> // getline(), perror(), fopen(), fclose()
#include <stdlib.h> // exit(), EXIT_FAILURE, realloc(), free()
int main( void )
{
FILE *fp = fopen( "untitled1.c", "r" );
if( !fp )
{
perror( "fopen for reading untitled1.c failed" );
exit( EXIT_FAILURE );
}
// implied else, fopen successful
char **lines = NULL;
size_t availableLines = 0;
size_t usedLines = 0;
char *line = NULL;
size_t lineLen = 0;
while( -1 != getline( &line, &lineLen, fp ) )
{
if( usedLines >= availableLines )
{
availableLines = (availableLines)? availableLines*2 : 1;
char **temp = realloc( lines, sizeof( char* ) * availableLines );
if( !temp )
{
perror( "realloc failed" );
free( lines );
fclose( fp );
exit( EXIT_FAILURE );
}
// implied else realloc successful
lines = temp;
}
lines[ usedLines ] = line;
usedLines++;
line = NULL;
lineLen = 0;
}
fclose( fp );
for( size_t i = 0; i<usedLines; i++ )
{
puts( lines[i] );
}
free( lines );
}