I need to print all phrases from a file (phrases can end in '.', '?' or '!')

#include <stdio.h>
#include <string.h>
#include <stdlib.h>

char* read_file(char *name) {
    FILE *file;
    char *text;
    long num_bytes;

    file = fopen(name, "r");

    if(!file) {
        printf("File could not be opened!");
        exit(EXIT_FAILURE);
    }

    fseek(file, 0, SEEK_END);
    num_bytes = ftell(file);
    fseek(file, 0, SEEK_SET);

    text = (char*) malloc(num_bytes * sizeof(char));
    fread(text, 1, num_bytes, file);
    
    fclose(file);

    return text;
}

int main(int argc, char* argv[]) {
    char *text = read_file(argv[1]);
    unsigned int count = 0, index=0;
    char *line = (char*) malloc(sizeof(text));

    for(int i = 0; i < strlen(text); i  ) {
        line[index] = text[i];
        index  ;
        if(text[i] == '.' || text[i] == '?' || text[i] == '!') {
            count  ;
            printf("[%d] %s\n", count, line);
            memset(line, 0, index   1);
            index = 0;
        }
    }
    return EXIT_SUCCESS;
}

I have this piece of code that kind of works but if my file as the following text: "My name is Maria. I'm 19." the second phrase is printed with a ' ' in the beggining. Can someone please help finding a way to ignore those spaces? Thank you

CodePudding user response：

You can test for a whitespace character by comparing the char in question to ' '.

if(text[i] == ' ')
    // text[i] is whitespace

CodePudding user response：

One possible solution, advance to the next non-whitespace character when you find the end of the sentence. You also need to make sure you've mallocd enough memory for the current phrase:

#include <ctype.h>  // for isspace
... 

size_t textLength = strlen(text);
// malloc based on the text length here, plus 1 for the NUL terminator.
// sizeof(text) gives you the size of the pointer, not the size of the
// memory block it points to.
char *line = malloc(textLength 1);

for(size_t i = 0; i < textLength; i  ) {
    line[index] = text[i];
    index  ;
    if(text[i] == '.' || text[i] == '?' || text[i] == '!') {
        count  ;
        printf("[%d] %s\n", count, line);
        memset(line, 0, index   1);
        index = 0;
        // advance to the next non-whitespace char
        do
        {
            // advance to the next char (we know the current char is not a space)
            i  ;
        // keep advancing i while the next char is in range of the
        // text and the next char is a space.
        }while (i 1 < textLength && isspace(text[i 1]) != 0);
    }
}

Output:

[1] My name is Maria.
[2] I'm 19.

Demonstration

There's also no need to cast the return value of malloc