C程序读取大文本文件并将信息存储在struct中

Question

I am working on a C program that requires me to read a fairly large text file and store the information in structs. THe file contains actors names and movies they've been in. I have searched my textbook and other online resources but still don't know how to proceed.

I have an older program that read a file kind of similar but formatted much better. I need to alter it to fit my needs for this project but don't know how.

My code:

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define SIZE 100
#define START 239
#define END 374

//method to find the index of a char c in a string
int indexOf(char c, char *string){
    ///iterating through char array, checking if any character matches c
    for(int i=0;string[i]!='\0';i++){
        if(string[i]==c){
        //found
        return i;
        }
    }
    //not found
    return -1;
}

//method to find the substring of a string between indices from and to
//and store the result in result

void substring(char *string, int from, int to, char *result){
    int index=0;
    //storing characters between from and to to result
    for(int i=from;i<to;i++){
        result[index]=string[i];
        index++;
    }
    //null terminating the array
    result[index]='\0';
}


//a structure to represent an actor

struct Actor{
    char lastName[20];
    char firstName[20];
    char movie[20];
};

//method to print name and movie of an actor in separate lines

void print(struct Actor actor) {
    printf("First name: %s\n",actor.firstName);
    printf("Last name: %s\n",actor.lastName);
    printf("Movie: %s\n\n",actor.movie);
}

int main(){

    //creating a file pointer, asking user for the file name
    FILE *fp;
    //opening file in read mode
    fp = fopen("./actors.txt","r");

    if(fp == NULL){
        //file can not be opened
        printf("File not found!\n");
        return 0;
    }

    //creating a char array to store each line, one at a time
    char buffer[100];
    //creating an Actor structure object
    struct Actor actor;
    //needed variables
    int index1 = 0, index2 = 0,index3 = 0, index4 = 0;
    //reading all lines one by one
    int i = 0;
    while(fgets(buffer, 100, fp)){
        i++;
        if(i > START && i < END ){
            getLen(buffer);
            ///finding index of comma (,)
            index1 = indexOf(',',buffer);
            //cutting the string between indices 0 and index1
            //and storing as actor's lastname
            substring(buffer,0,index1,actor.lastName);
            ///finding index of tab (\t)
            index2=indexOf('\t',buffer);
            //storing string between indices index1 and index2 in firstname
            substring(buffer,index1,index2,actor.firstName);
            ///finding year parentheses
            index3=indexOf('(', buffer);
            ///fetching movie title

            substring(buffer,index2,index3-1,actor.movie);
            //printing actor
            print(actor);
        }
    }
        //closing file
    fclose(fp);
}

The data in the text file is in the format:

lastname, firstname\t\tMovie (year) [role]
\t\t\tmore movies

I only need the actor name and movies they've been in. Here is a sample of the data I am trying to read and store.

Parr, Brian (I)     Blue Ice (1992)  [Stallholder]  <20>
        Eskimo Day (1996) (TV)  [Second cabbie]  <22>
        Summer in the Suburbs (2000) (TV)  [Neighbor #2]  <22>
        The fairy queen (La reine des fées) (1989) (TV)  [Snug]  <12>

Rogers, Marcus (II)     .357 (2005)  [Joshua]
        Streets (2004)  [Man in car]
        Summer in the Suburbs (2000) (TV)  [Bobby]  <16>
        "15 Storeys High" (2002) {The Sofa (#1.1)}  [Lawyer]  <5>

Here is my output:

First name: , Brian (I)
Last name: Parr
Movie:

First name:
Last name:
Movie:                   Eskimo Day

First name:
Last name:
Movie:                   Summer in the SubrnSw

First name: b
Last name:
Movie:                   The fairy queen

First name: b
Last name:
Movie:

First name: , Marcus (II)
Last name: Rogers
Movie:

First name: b
Last name:
Movie:                   Streets

First name: b
Last name:
Movie:                   Summer in the SubrnSw

First name: b
Last name:
Movie:                   "15 Storeys High"rnSw

How can I read these files and store them in my struct so that they don't print with extra tabs and characters? In addition, the struct needs an array of movies so I'm trying to get it to print like:

Actor Name
Movies
Movies
Movies
Movies

I tried adding a loop to do this but I had no luck. I am still very new to C and my textbook is aweful. I've searched online for additional resources but can't seem to find anything. Please, how can I fix this so I am only reading and storing the names and movies?

On another note, I am not concerned with TV shows which appear with double quotes "show"

Answer 1

You just need a little bit of checks to achieve your result. You need to keep the previous name until you find a line that is just "\\n". Also no need to redefine functions that already exist in C standard library (but you could re-implement them if you want):

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define SIZE 100
#define START 0
#define END 374

//a structure to represent an actor

struct Actor{
    char lastName[20];
    char firstName[20];
    char movie[50];
};

//method to print name and movie of an actor in separate lines

void print(struct Actor actor) {
    printf("First name: %s\n",actor.firstName);
    printf("Last name: %s\n",actor.lastName);
    printf("Movie: %s\n\n",actor.movie);
}

int main(){

    //creating a file pointer, asking user for the file name
    FILE *fp;
    //opening file in read mode
    fp = fopen("./actors.txt","r");

    if(fp == NULL){
        //file can not be opened
        printf("File not found!\n");
        return 0;
    }

    //creating a char array to store each line, one at a time
    char buffer[100];
    //creating an Actor structure object
    struct Actor actor;
    //reading all lines one by one
    int i = 0;
    int check=0;
    char *ptr;
    while(fgets(buffer, 100, fp)){
        i++;
        int len;
        if(i > START && i < END ){
            if ( strcmp( buffer, "\n") == 0)
            {
                check = 0;
                continue;
            }
            if( !check)
            {
                len = strchr(buffer, ',') - buffer - 1;
                strncpy( actor.lastName, buffer, len);
                actor.lastName[len] = '\0';
                if( (ptr = strchr(buffer, ',')))
                {
                    len = strchr(buffer, '\t') - ptr -1;
                    strncpy( actor.firstName, ptr+1, len);
                    actor.firstName[len] = '\0';
                }
                check = 1;
            }
            if( (ptr = strchr(buffer, '\t')))
            {
                len = strchr( ptr, '(') - ptr-2;
                strncpy( actor.movie, ptr+2, len);
                actor.movie[len] = '\0';
            }
            //printing actor
            print(actor);
        }
    }
        //closing file
    fclose(fp);
}

Output

First name:  Brian (I)
Last name: Par
Movie: Blue Ice 

First name:  Brian (I)
Last name: Par
Movie: Eskimo Day 

First name:  Brian (I)
Last name: Par
Movie: Summer in the Suburbs 

First name:  Brian (I)
Last name: Par
Movie: The fairy queen 

First name:  Marcus (II)
Last name: Roger
Movie: .357 

First name:  Marcus (II)
Last name: Roger
Movie: Streets 

First name:  Marcus (II)
Last name: Roger
Movie: Summer in the Suburbs 

First name:  Marcus (II)
Last name: Roger
Movie: "15 Storeys High"  

If you wanted you could also generalize this by creating a function like

void parse( char * dest, char * string, char delim, int offset1, int offset2)
{
    int len = strchr(string, delim) - string - 1 - offset1;
    strncpy( dest, string + 1 + offset2, len);
    dest[len] = '\0';
}

which would make the code look like this:

        if( !check)
        {
            parse(actor.lastName, buffer, ',', 0, -1);
            if( (ptr = strchr(buffer, ',')))
                parse( actor.firstName, ptr, '\t', 0,0);
            check = 1;
        }
        if( (ptr = strchr(buffer, '\t')))
            parse( actor.movie, ptr, '(', 1, 1);
        //printing actor
        print(actor);