I'm parsing a text file:
Hello, this is a text file.
and creating by turning the file into a char[]. Now I want to take the array, iterate through it, and create an array of arrays that splits the file into words:
string[0] = Hello
string[1] = this
string[2] = is
This is my code:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "TextReader.h"
#include <ctype.h>
void printWord(char *string) {
int i;
for (i = 0; i < strlen(string); i ++)
printf("%c", string[i]);
printf("\n");
}
void getWord(char *string) {
char sentences[5][4];
int i;
int letter_counter = 0;
int word_counter = 0;
for (i = 0; i < strlen(string); i ++) {
// Checks if the character is a letter
if (isalpha(string[i])) {
sentences[word_counter][letter_counter] = string[i];
letter_counter++;
} else {
sentences[word_counter][letter_counter + 1] = '\0';
word_counter++;
letter_counter = 0;
}
}
// This is the code to see what it returns:
i = 0;
for (i; i < 5; i ++) {
int a = 0;
for (a; a < 4; a++) {
printf("%c", sentences[i][a]);
}
printf("\n");
}
}
int main() {
// This just returns the character array. No errors or problems here.
char *string = readFile("test.txt");
getWord(string);
return 0;
}
This is what it returns:
Hell
o
this
is
a) w
I suspect this has something to do with pointers and stuff. I come from a strong Java background so I'm still getting used to C.
With sentences[5][4] you're limiting the number of sentences to 5 and the length of each word to 4. You'll need to make it bigger in order to process more and longer words. Try sentences[10][10]. You're also not checking if your input words aren't longer than what sentences can handle. With bigger inputs this can lead to heap-overflows & acces violations, remember that C does not check your pointers for you!
Of course, if you're going to use this method for bigger files with bigger words you'll need to make it bigger or allocate it dymanically.
sample that do not use strtok:
void getWord(char *string){
char buff[32];
int letter_counter = 0;
int word_counter = 0;
int i=0;
char ch;
while(!isalpha(string[i]))++i;//skip
while(ch=string[i]){
if(isalpha(ch)){
buff[letter_counter++] = ch;
++i;
} else {
buff[letter_counter] = '\0';
printf("string[%d] = %s\n", word_counter++, buff);//copy to dynamic allocate array
letter_counter = 0;
while(string[++i] && !isalpha(string[i]));//skip
}
}
}
use strtok version:
void getWord(const char *string){
char buff[1024];//Unnecessary if possible change
char *p;
int word_counter = 0;
strcpy(buff, string);
for(p=buff;NULL!=(p=strtok(p, " ,."));p=NULL){//delimiter != (not isaplha(ch))
printf("string[%d] = %s\n", word_counter++, p);//copy to dynamic allocate array
}
}
Related
So I created have a program that basically prints any given string like that:
Example:
Input:
Hello
Output:
Hello
ello
llo
lo
o
The problem is that for some reason if I use icdiff and compare my output with that output in a text file it says that I am missing elements and that I have more spaces than it should.
Icdiff output:
Hello
ello
llo
As you can see this is clearly different than what I have, but if I test it on the terminal I get the expected output.
Program:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
void print_array(char *p, int tamanho) {
int i;
for (i = 0; i < tamanho; i++) {
printf("%c", p[i]);
}
printf("\n");
}
void nova_str(char *p, char *s, int inicio, int tamanho) {
int i;
for (i = inicio; i < tamanho; i++) {
s[i] = p[i];
}
}
int main() {
char p[1001];
int len;
int j;
scanf("%s", p);
len = strlen(p);
print_array(p, len);
for (j = 1; j < len; j++) {
char *np = (char *)calloc(len + 1, sizeof(char));
nova_str(p, np, j, len);
print_array(np, len);
free(np);
}
return 0;
}
Really any help would be appreciated.
The problem is in the nova_str function: you use the same index into the source and the destination, so the destination array still starts with initcio null bytes which are printed by the print_array and appear as spaces on your system. The array is initialized to all bits zero by calloc().
Here is a much simpler version:
#include <stdio.h>
int main() {
char p[1001];
if (scanf("%1000s", p) == 1) {
for (int i = 0; p[i] != '\0'; i++) {
/* print the word starting at offset i */
printf("%s\n", p + i);
}
}
return 0;
}
calloc() is setting the memory to zero, so you are printing null characters in print_array() when it should be spaces. Replace those null characters with spaces there and this is solved, although I think there is an easier way to achieve what you are trying to do.
If you don't want the letters to be prepended by spaces, add an if (p[i] == '\0') continue; before printf() in print_array() instead.
Hello, let's say I got 2 strings, "Today is a nice day" and "ao". I want to delete the chars of the 2nd string that appear in the 1st one.
This is my issue:
char c[20];
char p[10];
int i,j;
int l1,l2;
printf("Enter a string \n");
scanf("%s",cd);
printf("Enter another string \n");
scanf("%s",car);
len1 = strlen(cd);
len2 = strlen(car);
for (i=0;i<len1;i++){
for (j=0;j<len2;j++){
if (cd[i]==car[j]){
cd[i]="";
}
}
}
What I want is the 1st string to be like "Tdy is nice dy". So I empty the positions where the elements are the same to reposition it later.
Apparently "cd[i]==car[j]" can't be done on C, I got "Invalid conversion from 'const char*' to 'char'.
So i'm pretty much stuck. I'll thank any help.
1) This is a solution matching your algorithm as close as possible.
All what you need is an extra loop and to replace cd[i]=""; which cannot be compiled with cd[i]=0;. The error given by the compiler relates to expression cd[i]=""; cd[i] is a character type and you cannot assign string "" which has a type const char * to char variable. cd[i] is a character "" is a pointer.
The operation cd[i]=0; gives you want you wanted: I empty the positions where the elements are the same to reposition it later. It replaces the unwanted characters with 0.
#include <stdio.h>
#include <string.h>
int main()
{
char cd[] = "Today is a nice day";
char tmp[] = "Today is a nice day";
char car[] = "ao";
int i;
int j;
int k;
int len1 = strlen(cd);
int len2 = strlen(car);
for (i=0;i<len1;i++){
for (j=0;j<len2;j++){
if (cd[i] == car[j]){
cd[i]=0;
}
}
}
k = 0;
for (i=0; i<len1; i++)
{
if(cd[i] == 0)
{
}
else
{
tmp[k] = cd[i];
k++;
}
}
tmp[k] = 0; /* remember to terminate the tmp */
printf("%s\n", tmp);
strcpy(cd,tmp);
printf("%s\n", cd);
return 0;
}
OUTPUT:
Tdy is nice dy
Tdy is nice dy
Alternatively, instead of clearing unwanted character with 0 you could just skip it. This solution is given below:
#include <stdio.h>
#include <string.h>
int main()
{
char cd[] = "Today is a nice day";
char car[] = "ao";
int i;
int j;
int k = 0;
int skip = 0;
int len1 = strlen(cd);
int len2 = strlen(car);
for (i=0; i<len1; i++)
{
for (j=0; j<len2; j++)
{
if (cd[i] == car[j])
{
skip++; // make note that this character is not needed
}
}
if(skip == 0)
{
cd[k] = cd[i]; // copy the character
k++; // increase the position index
}
else
{
// skip the copy of charcter; clear the skip marker
skip = 0;
}
}
cd[k] = 0; // remember to terminate the new ck string!
printf("%s\n", cd);
return 0;
}
OUTPUT:
Tdy is nice dy
I have made two functions that find a substring index and substitute that substring in the string. I'm glad I jury rigged this at all, given that similar questions previously asked were never answered/marked as closed without any help. Is there a cleaner method?
void destroy_substr(int index, int len)
{
int i;
for (i = index; i < len; i++)
{
string[i] = '~';
}
}
void find_substr_index(char* substr)
{
int i;
int j;
int k;
int count;
int len = strlen(substr);
for (i = 0; i < strlen(string); i++)
{
if (string[i] == substr[0])
{
for(j = i, k = 0; k < len; j++, k++)
{
if (string[j] == substr[k])
{
count++;
}
if (count == len)
destroy_substr((j - len + 1), len);
}
j = 0;
k = 0;
count = 0;
}
}
}
Your code seems like you're trying to re-inventing your own wheel.
By using standard C functions, which is strstr() and memset(), you can achieve the same result as you expected.
#include <stdio.h>
#include <string.h>
char string[] = "foobar foobar foobar";
char substr[] = "foo";
char replace = '~';
int main() {
int substr_size = strlen(substr);
// Make a copy of your `string` pointer.
// This is to ensure we can safely modify this pointer value, without 'touching' the original one.
char *ptr = string;
// while true (infinite loop)
while(1) {
// Find pointer to next substring
ptr = strstr(ptr, substr);
// If no substring found, then break from the loop
if(ptr == NULL) { break; }
// If found, then replace it with your character
memset(ptr, replace, substr_size);
// iIncrement our string pointer, pass replaced substring
ptr += substr_size;
}
printf("%s\n", string);
return 0;
}
How about this:
#include <stdio.h>
#include <string.h>
int main(int argc, char **argv)
{
char string[] = "HELLO hello WORLD world HELLO hello ell";
char substring[] = "ell";
int stringLength = strlen(string);
int substringLength = strlen(substring);
printf("Before: %s\n", string);
if(substringLength <= stringLength)
{
int i;
int j;
for(i = 0, j = stringLength - substringLength + 1; i < j; )
{
if(memcmp(&string[i], substring, substringLength) == 0)
{
memset(&string[i], '~', substringLength);
i += substringLength;
}
else
{
i++;
}
}
}
printf("After: %s\n", string);
return 0;
}
Key ideas are:
You only need to scan the string (stringLength - substringLength) times
You can use functions from string.h to do the comparison and to replace the substring
You can copy the new string in place. If you want to support insertion of longer strings you will need to manage memory with malloc()/realloc(). If you want to support insertion of smaller strings you'll need to advance the pointer to the beginning by the length of the replacement string, copy the rest of the string to that new location, then zero the new end of the string.
#include <stdio.h>
#include <string.h>
#include <err.h>
int main(int argc, char **argv)
{
char *str = strdup("The fox jumps the dog\n");
char *search = "fox";
char *replace = "cat";
size_t replace_len = strlen(replace);
char *begin = strstr(str, search);
if (begin == NULL)
errx(1, "substring not found");
if (strlen(begin) < replace_len)
errx(1, "replacement too long");
printf("%s", str);
memcpy(begin, replace, replace_len);
printf("%s", str);
return 0;
}
I've got a block of strings, say "aaa\0bbbb\0ccccccc\0"
and I want to turn them into an array of strings.
I've tried to do so using the following code:
void parsePath(char* pathString){
char *pathS = malloc(strlen(pathString));
strcpy(pathS, pathString);
printf(1,"33333\n");
pathCount = 0;
int i,charIndex;
printf(1,"44444\n");
for(i=0; i<strlen(pathString) ; i++){
if(pathS[i]=='\0')
{
char* ith = malloc(charIndex);
strcpy(ith,pathS+i-charIndex);
printf(1,"parsed string %s\n",ith);
exportPathList[pathCount] = ith;
pathCount++;
charIndex=0;
}
else{
charIndex++;
}
}
return;
}
exportPathList is a global variable defined earlier in the code by
char* exportPathList[32];
when using that function exportPathList[i] contains garbage.
What am I doing wrong?
The answer to this SO question:
Parse string into argv/argc
deals with a similar issue, you might have a look.
You need to know how many strings are there or agree for an "end of strings". The simplest would be to have an empty string at the end:
aaa\0bbbb\0ccccccc\0\0
^^
P.S. is this homework?
First of all, since your strings are delimited by a null char, '\0', strlen will only report the size of the string up to the first '\0'. strcpy will copy until the first null character as well.
Further, you cannot know where the input string ends with this information. You either need to pass in the whole size or, for example, end the input with double null characters:
#include <stdio.h>
#include <string.h>
void parsePath(const char* pathString){
char buf[256]; // some limit
while (1) {
strcpy(buf, pathString);
pathString+=strlen(buf) + 1;
if (strlen(buf) == 0)
break;
printf("%s\n", buf);
}
}
int main()
{
const char *str = "aaa\0bbbb\0ccccccc\0\0";
parsePath(str);
return 0;
}
And you need some realloc's to actually create the array.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define MAXSIZE 16
char* exportPathList[MAXSIZE] = {0};
size_t pathCount = 0;
void parsePath(char* pathString){
char *ptop, *pend;
ptop=pend=pathString;
while(*ptop){
while(*pend)++pend;
exportPathList[pathCount++]=strdup(ptop);
pend=ptop=pend+1;
}
}
int main(){
char textBlock[]= "aaa\0bbbb\0ccccccc\0";
//size_t size = sizeof(textBlock)/sizeof(char);
int i;
parsePath(textBlock);
for(i=0;i<pathCount;++i)
printf("%s\n", exportPathList[i]);
return 0;
}
The solution I've implemented was indeed adding double '\0' at the end of the string and using that in order to calculate the number of strings.
My new implementation (paths is the number of strings):
void parsePath(char* pathString,int paths){
int i=0;
while (i<paths) {
exportPathList[i] = malloc(strlen(pathString)+1);
strcpy(exportPathList[i], pathString);
pathString+=strlen(pathString);
i++;
}
}
I'd like to thank everyone that contributed.
My Implementation looks like this -> it follows the idea of argv and argc in a main funtion:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main(void){
char **args = (char**)malloc(100*sizeof(char));
char buff[100], input_string[100], letter;
for(int i = 0; i < 100; i++){
buff[i] = '\0';
input_string[i] = '\0';
}
for(int i = 0; (letter = getchar())!='\n'; i++){
input_string[i] = letter;
}
int args_num = 0;
for(int i = 0, j = 0; i < 100;i++){
if((input_string[i] == ' ')||(input_string[i]=='\0')){
//reset j = 0
j = 0;
args[args_num] = malloc(strlen(buff+1));
strcpy(args[args_num++],buff);
for(int i = 0; i < 100; i++)buff[i] = '\0';
}else buff[j++] = input_string[i];
}
for(int i = 0; i < args_num; i++){
printf("%s ",args[i]);
}
}
-> Every single word in your string can then be accessed with args[i]
For some reason, I can't get this to work! Can anyone tell me where I've gone wrong? This is supposed to reverse the words in a give string (i.e from "this is a test" to "test a is this")
#include <stdio.h>
#include <stdlib.h>
char *reverse(char const *input)
{
char *ret = (char *)malloc(sizeof(char) * strlen(input));
int length = 0;
int numWords = 1;
int i;
for(i=0; input[i]!=NULL; i++)
{
length++;
if(input[i]==' ')
numWords++;
}
char words[numWords];
int currentWord = numWords;
for(i=0; input[i]!=NULL; i++)
{
if (input[i]==' '){
currentWord--;
}else{
words[currentWord] = words[currentWord] + input[i];
}
}
for(i=0; i < numWords; i++)
{
ret = ret + words[i];
}
return ret;
}
int main(int argc, char **argv)
{
int nTestcase = 0;
int i = 0;
char inputstr[100];
char *reversedStr = NULL;
scanf("%d\n", &nTestcase);
for (i = 0; i < nTestcase; i++)
{
fgets(inputstr, 100, stdin);
reversedStr = reverse(inputstr);
printf("%s\n", reversedStr);
free(reversedStr);
memset(inputstr, 0, 100);
}
return 0;
}
words[currentWord] = words[currentWord] + input[i];
You can't add characters to each other like that expecting string concatenation. And I imagine you expect words to be an array of words (i.e. strings), but its type is not that, words is just an array of characters.
Like #Tom said, you're doing this again in the last for loop:
ret = ret + words[i];
Joseph, unlike other programming languages ( c# or PHP ), string handling functions of C are quite basic.
You cannot add strings directly, however there are a host of library functions you can use to accomplish the same task.
Check out,
strtok - Use it to split the string to words. strtok reference
strncat - Use to concatenate strings
strings in C are just byte arrays terminated with the null character ( byte with value 0).
Here is shorter/cleaner way
private char[] reverseWords(char[] words) {
int j = words.length - 1;
for (int i = 0; i < (words.length)/2; i++) {
if(i==j)
continue;
char temp = words[i];
words[i] = words[j];
words[j]=temp;
j--;
}
int lastIndex = 0;
for (int i=0;i<words.length;i++){
if(words[i]==' '){
words = reverseWord(words,lastIndex,i-1);
lastIndex=i+1;
}
}
words = reverseWord(words,lastIndex,words.length-1);
return words;
}
private char[] reverseWord(char[] words, int from, int to) {
int j=to;
for(int i=from;i<((to/2)+from/2);i++){
if(i==j) continue;
char temp = words[j];
words[j]=words[i];
words[i]=temp;
j--;
}
return words;
}