C: Occurrence of Letters in Text file - c

Question

Program takes an input file through the command line and outputs the occurrence of each letter in the text file. Not sure where I went wrong.
int main(int argc, char *argv[]) {
char word[1000];
int a = 0;
int b = 0;
int d = 0;
int c = 0;
int e = 0;
int f = 0;
int g = 0;
int h = 0;
int i = 0;
int j = 0;
int k = 0;
int l = 0;
int m = 0;
int n = 0;
int o = 0;
int p = 0;
int q = 0;
int r = 0;
int s = 0;
int t = 0;
int u = 0;
int v = 0;
int w = 0;
int x = 0;
int y = 0;
int z = 0;
int other = 0;
int counter, lenght;
FILE *fp = fopen(argv[1], "r");
fgets(word, 999, fp);
lenght = 1000;
for(counter = 0; counter < lenght; counter++) {
word[counter] = tolower(word[counter]);
if (word[counter] == 'a') {
a++;
}
else if (word[counter] == 'b') {
b++;
}
else if (word[counter] == 'c') {
c++;
}
else if (word[counter] == 'd') {
d++;
}
else if (word[counter] == 'e') {
e++;
}
else if (word[counter] == 'f') {
f++;
}
else if (word[counter] == 'g') {
g++;
}
else if (word[counter] == 'h') {
h++;
}
else if (word[counter] == 'i') {
i++;
}
else if (word[counter] == 'j') {
j++;
}
else if (word[counter] == 'k') {
k++;
}
else if (word[counter] == 'l') {
l++;
}
else if (word[counter] == 'm') {
m++;
}
else if (word[counter] == 'n') {
n++;
}
else if (word[counter] == 'o') {
o++;
}
else if (word[counter] == 'p') {
p++;
}
else if (word[counter] == 'q') {
q++;
}
else if (word[counter] == 'r') {
r++;
}
else if (word[counter] == 's') {
s++;
}
else if (word[counter] == 't') {
t++;
}
else if (word[counter] == 'u') {
u++;
}
else if (word[counter] == 'v') {
v++;
}
else if (word[counter] == 'w') {
w++;
}
else if (word[counter] == 'x') {
x++;
}
else if (word[counter] == 'y') {
y++;
}
else if (word[counter] == 'z') {
z++;
}
else {
other++;
}
}
printf("\nCharacter frequency in %s", argv[1]);
printf("\nCharacter Count");
printf("\na \t\t %d", a);
printf("\nb \t\t %d", b);
printf("\nc \t\t %d", c);
printf("\nd \t\t %d", d);
printf("\ne \t\t %d", e);
printf("\nf \t\t %d", f);
printf("\ng \t\t %d", g);
printf("\nh \t\t %d", h);
printf("\ni \t\t %d", i);
printf("\nj \t\t %d", j);
printf("\nk \t\t %d", k);
printf("\nl \t\t %d", l);
printf("\nm \t\t %d", m);
printf("\nn \t\t %d", n);
printf("\no \t\t %d", o);
printf("\np \t\t %d", p);
printf("\nq \t\t %d", q);
printf("\nr \t\t %d", r);
printf("\ns \t\t %d", s);
printf("\nt \t\t %d", t);
printf("\nu \t\t %d", u);
printf("\nv \t\t %d", v);
printf("\nw \t\t %d", w);
printf("\nx \t\t %d", x);
printf("\ny \t\t %d", y);
printf("\nz \t\t %d", z);
fclose(fp);
return 0;
}
Should output in two columns one being the letter and the next being the number of times that letter occurs

Answer 1

There are problems in your code:
you do not include <stdio.h> nor <ctype.h>
you only read one line and you do not even check if that succeeds. You should write a loop like while (fgets(word, sizeof word, fp)) {
you check all characters in the word array: you should stop at the end of the line: lenght = strlen(word);
tolower() should not be given a char argument, because on platforms where char is signed, negative values invoke undefined behavior. You can cast the argument as (unsigned char) to avoid this: word[counter] = tolower((unsigned char)word[counter]);
More room for improvement:
lenght is misspelt, it should be length.
you should use an array of counters to avoid all these tests and all these explicit printf statements.
check the argument count and fopen() success
no need to read line by line, handle one byte at a time read with getc(). However, reading one large chunk at a time can be faster because it uses fewer tests and locks.
the printf statements should output the newline at the end rather than at the beginning.
Here is a corrected and simplified version:
#include <ctype.h>
#include <limits.h>
#include <stdio.h>
int main(int argc, char *argv[]) {
int count[UCHAR_MAX + 1] = { 0 };
int other, total;
int c;
const char *s;
FILE *fp;
if (argc <= 1) {
fprintf(stderr, "missing input file\n");
return 1;
}
fp = fopen(argv[1], "r");
if (fp == NULL) {
fprintf(stderr, "cannot open input file %s\n", argv[1]);
return 1;
}
total = 0;
while ((c = getc(fp)) != EOF) {
count[tolower(c)] += 1;
total++;
}
printf("Character frequency in %s\n", argv[1]);
printf("Character Count\n");
other = total;
for (s = "abcdefghijklmnopqrstuvwxyz"; *s; s++) {
printf("%c:\t%9d\n", *s, count[(unsigned char)*s]);
other -= count[(unsigned char)*s];
}
printf("other:\t%9d\n", other);
fclose(fp);
return 0;
}
Reading the file by chunks instead of one byte at a time improves the speed dramatically with recent C libraries, because the support for multithreading has made the getc() macros inefficient. Using 64K buffers, the code below is fifty times faster (50X) for a 400MB file:
#include <ctype.h>
#include <limits.h>
#include <stdio.h>
#define BUFFER_SIZE 65536
int main(int argc, char *argv[]) {
unsigned char buffer[BUFFER_SIZE];
long count[UCHAR_MAX + 1] = { 0 };
long other;
size_t i, n;
const char *s;
FILE *fp;
if (argc <= 1) {
fprintf(stderr, "missing input file\n");
return 1;
}
fp = fopen(argv[1], "r");
if (fp == NULL) {
fprintf(stderr, "cannot open input file %s\n", argv[1]);
return 1;
}
while ((n = fread(buffer, 1, sizeof buffer, fp)) != 0) {
for (i = 0; i < n; i++) {
count[buffer[i]] += 1;
}
}
other = 0;
for (i = 0; i <= UCHAR_MAX; i++) {
if (isupper(i)) {
count[tolower(i)] += count[i];
} else {
if (!islower(i))
other += count[i];
}
}
printf("Character frequency in %s\n", argv[1]);
printf("Character Count\n");
for (s = "abcdefghijklmnopqrstuvwxyz"; *s; s++) {
printf("%c:\t%9ld\n", *s, count[(unsigned char)*s]);
}
printf("other:\t%9ld\n", other);
fclose(fp);
return 0;
}

Answer 2

Here's a quick implementation I wrote. It doesn't use fgets, but that is most definitely an option.
The flow of the program should be simple, but it is as follows:
Check for a proper argument count.
Declare the variables we'll need.
Declare the file pointer and attempt to open the file.
If the file doesn't open, we'll error out.
Read in every character from the file one at a time and store it into our variable c.
Using our ascii table, we'll alter the values to get them into the proper position in our array.
Print out all of our values.
Close the file.
#include <stdio.h>
int main(int argc, char **argv){
if (argc < 2){
printf("Not enough arguments!\n");
return -1;
}
int A[27] = {0}, c;
FILE *inFile = fopen(argv[1], "r");
if (inFile == NULL){
printf("The file \"%s\" could not be opened.\n", argv[1]);
return -2;
}
while((c = fgetc(inFile)) != EOF){
if ( c >= 'a' && c <= 'z' ){
/* C is a lowercase character */
c-='a';
A[c]++;
}
else if ( c >= 'A' && c <= 'Z' ){
/* C is an uppercase character */
c-='A';
A[c]++;
}
else if (c == '\n'){
/* we're not counting newlines */
continue;
}
else {
A[26]++;
}
}
/* Print out all the values except the "Other" count. */
for (c = 0; c < sizeof A / sizeof A[0] - 1; c++){
printf("%c: %d\n", c+'a', A[c]);
} printf("Other: %d\n", A[26]); //Print out "Other" count
/* Close our file */
fclose(inFile);
return 0;
}