C histogram of words printing problems - c

I have this code, what i want it to do is print the string that represents the word, and print the number of times it occurred in the file, instead it outprints something liek this: (a load of blank space) and then this number -1076720020, which i have no idea where it came from, how would i go about fixing this?
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <stdlib.h>
struct podatki {
char beseda[1000];
int frekvenca;
};
void zamenjaj(char *str1, char *str2) {
char *beseda2 = (char *)malloc((strlen(str1) + 1) * sizeof(char));
strcpy(beseda2, str1);
strcpy(str1, str2);
strcpy(str2, beseda2);
free(beseda2);
}
int posodobi(struct podatki s[], const char unit[], int count) {
int i =0;
for (i = 0; i < count; i++) {
if (strcmp(s[i].beseda, unit) == 0) {
s[i].frekvenca++;
return count;
}
}
strcpy(s[count].beseda, unit);
s[count].frekvenca++;
return (count + 1);
}
int main() {
int stBes;
scanf("%d", &stBes);
//zacetne deklaracije
struct podatki s[1000];
char string[1000], unit[2000], c;
int i = 0;
int frekvenca = 0;
int j = 0;
int count = 0;
int num = 0;
//branje
for (i = 0; i < 1000; i++) {
s[i].frekvenca = 0;
}
i = 0;
do {
fflush(stdin);
c = getchar();
string[i++] = c;
} while (c != '\n');
//pretvori v majhne crke
char *p;
for (p = string; *p != '\0'; ++p) {
*p = tolower(*p);
}
string[i - 1] = '\0';
for (i = 0; i < strlen(string); i++) {
while (i < strlen(string) && string[i] != ' ' && !ispunct(string[i])) {
unit[j++] = string[i++];
}
if (j != 0) {
unit[j] = '\0';
count = posodobi(s, unit, count);
j = 0;
}
}
int a;
for (i = 0; i < count; ++i) {
for (j = i + 1; j < count; ++j) {
if (s[i].frekvenca < s[j].frekvenca) {
a = s[i].frekvenca;
s[i].frekvenca = s[j].frekvenca;
s[j].frekvenca = a;
zamenjaj(s[i].beseda, s[j].beseda);
}
}
}
for (i = 0; i < count; i++) {
for (j = 1; j < count; j++) {
if (s[i].frekvenca == s[j].frekvenca){
if (strcmp(s[i].beseda, s[j].beseda) < 0) {
a = s[i].frekvenca;
s[i].frekvenca = s[j].frekvenca;
s[j].frekvenca = a;
zamenjaj(s[i].beseda, s[j].beseda);
}
}
}
}
//printanje
for (i = 0; i < stBes; i++) {
printf("%s\t %d\n", s[i].beseda, s[i].beseda);
if (s[i].frekvenca > 1) {
num++;
}
}
return 0;
}

The problem is that you convert the string to lower case before nul terminating it.
Here
i = 0;
do {
fflush(stdin);
c = getchar();
string[i++] = c;
} while (c != '\n');
/* Goes here <---------------------+ */
/* | */
//pretvori v majhne crke | */
char *p; /* | */
for (p = string; *p != '\0'; ++p) {/* | */
*p = tolower(*p);/* | */
} /* | */
/* | */
string[i - 1] = '\0'; /* ---------------------+ */
You should also remove the fflush(stdin) and instead use getchar() to fetch the white space characters ignored by the previous scanf(), and please use scanf() correctly and check it's returned value.

Related

passing char array to function from scanf in c

I have following function in c code
void analyze_text(char text[]) {
...
for (int i = 0; i < text_length || text[i] != '\0'; i++) {
...
}
}
In main function i would like to pass some string to it. If i do something like this
char text[4000] = "some text here";
analyze_text(text);
this is cool and do the goal, but i would like to have some user input present and I am not sure how to get char[] out of it. I tried following 2 and none of them seemed to work:
char text[4000];
scanf("%s",text);
analyze_text(text);
OR
char text[4000];
int c;
int count=0;
c = getchar();
count = 0;
while ((count < 4000) && (c != EOF)) {
text[count] = c;
++count;
c = getchar();
}
analyze_text(text);
I know that the first one should return pointer to char array, but second one should return char array itself, or not?
Its been like 10 years since i havent been working with c/c++. Can anybody give me some hint please?
update (whole function):
void analyze_text(char text[]) {
int printable_text_length = 0;
int text_length = strlen(text);
int word_count = 0;
int sentence_count = 0;
int in_sentence = 0;
int in_word = 0;
int count[ASCII_SIZE] = { 0 };
for (int i = 0; i < text_length || text[i] != '\0'; i++) {
int c = text[i];
if (!isspace(c)) {
printable_text_length++;
}
if (isalpha(c)) {
in_word = 1;
in_sentence = 1;
count[tolower(c)]++;
}
if (text[i] == ' ' && text[i + 1] != ' ' && in_word==1) {
word_count++;
in_word = 0;
}
if (text[i] == '.' && in_sentence==1) {
sentence_count++;
in_sentence = 0;
}
}
if (in_word == 1) { word_count++; }
if (in_sentence == 1) { sentence_count++; }
char charIndexes[ASCII_SIZE];
for (int i = 97; i <= 122; i++) {
charIndexes[i] = i;
}
for (int i=97; i <= 122; i++) {
for (int j = i + 1; j <= 122; j++) {
if (count[i] > count[j]) {
int temp = count[j];
count[j] = count[i];
count[i] = temp;
int temp2 = charIndexes[j];
charIndexes[j] = charIndexes[i];
charIndexes[i] = temp2;
}
}
}
...printf...
}
The issue with
char text[4000];
scanf("%s",text);
analyze_text(text);
is that scanf identifies space-separated chunks, so you'll only read the first one.
In order to read up to a whole line from the user, try fgets:
char text[4000];
fgets(text, 4000, stdin);
analyze_text(text);
You may want to check the return value of fgets for error detection.
You can use dyanamic array of char to pass it into the function.
Here is the code
#include <stdio.h>
#include <stdlib.h>
void analyze_text(char* text) {
for (int i = 0; text[i] != '\0'; i++) {
printf("%c\n",text[i] );
}
}
int main() {
char* text = (char *)malloc(4000 * sizeof(char));
scanf("%s", text);
analyze_text(text);
return 0;
}
and here is the output with input = 'abhishek'
a
b
h
i
s
h
e
k
remember that strlen in dyanamc array will not give the length of input array.

C - How to input and insert a string into an array of strings?

I want to insert string to the array until I type "ok". Why I am getting just "ok" and original array at the output?
int main(void)
{
char b[20];
char* str[10] = { "1","2" };
int i = 2;
while (1) {
gets(b);
if (strcmp(b, "ok") == 0) break;
str[i] = b;
i++;
}
for (int j = 0; j < i; j++)
printf("%s ", str[j]);
return 0;
}
You need to allocate a string on each iteration:
int main(void)
{
char* b;
char* str[10] = { "1","2" };
int i = 2;
while (1) {
b = malloc(20);
gets(b);
if (strcmp(b, "ok") == 0) break;
str[i] = b;
i++;
}
for (int j = 0; j < i; j++)
printf("%s ", str[j]);
// free allocated strings
while (i > 2)
free(str[--i]);
return 0;
}
They all point to b, which gets overwritten in each iteration.
You need to create a copy of the string when you assign it:
str[i] = strdup(b);
You also may consider using fgets instead of gets; however, you will need to remove the newline:
size_t size;
fgets(str, 20, stdin);
size = strlen(str);
if(str[size-1] == '\n')
str[size-1] = '\0';
Also, print a newline at the end of your program, so it won't interfere with the shell:
putchar('\n');
Full code:
int main(void)
{
char b[20];
char* str[10] = { "1","2" };
int i = 2;
while (1) {
size_t size;
fgets(str, 20, stdin);
size = strlen(str);
if(str[size-1] == '\n')
str[size-1] = '\0';
if (strcmp(b, "ok") == 0)
break;
str[i] = strdup(b);
i++;
}
for (int j = 0; j < i; j++)
printf("%s ", str[j]);
putchar('\n');
return 0;
}
You need to make a copy of the input string, then save a pointer to the copy of the input string in your array. Something like:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main(void)
{
char b[20];
char *str[10] = { "1","2" };
int i = 2;
char *p;
size_t lenb;
for(i = 2 ; i < 10 ; ++i)
{
fgets(b, sizeof(b), stdin);
lenb = strlen(b);
if(lenb > 0 && *(b+lenb-1) == '\n')
{
*(b+lenb-1) = '\0'; /* overwrite the trailing \n */
lenb = strlen(b);
}
if (strcmp(b, "ok") == 0)
break;
p = malloc(lenb+1);
strcpy(p, b);
str[i] = p;
}
for (int j = 0; j < i; j++)
printf("%s\n", str[j]);
return 0;
}

Inserting a value into an array and arranging array according to value c

char num = '5';
strcpy(array, "2,3,7,9")
Hi guys, any ideas if want to insert 5 into the array according to the value which will result in, how would i go about doing this?
array = "2,3,5,7,9"
#include <stdio.h>
#include <string.h>
void insert_string(char *target, const char *to_insert, int index) {
int count = 0;
int i;
int move_dst;
int insert_comma = 0;
int to_len = strlen(to_insert);
if (index < 0) index = 0;
if (index <= 0) {
i = 0;
} else {
for (i = 0; target[i] != '\0'; i++) {
if (target[i] == ',') {
count++;
if (count >= index) {
i++;
break;
}
}
}
}
/* i is where to insert the string */
if (target[i] == '\0') {
/* the insertion target was end of the string */
target[i] = ',';
target[++i] = '\0';
}
move_dst = i + to_len;
if (target[i] != '\0') {
/* the sequence continues after insertion point */
move_dst++;
insert_comma = 1;
}
memmove(&target[move_dst], &target[i], strlen(&target[i]) + 1); /* copy includes termination '\0' */
memcpy(&target[i], to_insert, to_len);
if (insert_comma) target[i + to_len] = ',';
}
int main(void) {
char array[1024];
char num = '5';
char num_string[2] = {num, '\0'};
int c = 2;
strcpy(array, "2,3,7,9");
puts(array);
insert_string(array, num_string, c);
puts(array);
return 0;
}

Anagram Solver, array[26] not working correctly

I've nearly finished my anagram solver program where I input two strings and get the result of whether they are anagrams of each other. For this example i'm using 'Payment received' and 'Every cent paid me'.
The problem i'm getting is when I output the letterCount arrays, letterCount1 is incorrect (it doesn't think there is a character 'd' but there is.) but letterCount2 is correct.
Can anyone see a problem with this because i'm completely baffled?
#include <stdio.h>
#include <string.h>
int checkAnagram(char string1[], char string2[])
{
int i;
int count = 0, count2 = 0;
int letterCount1[26] = {0};
int letterCount2[26] = {0};
for(i = 0; i < strlen(string1); i++)
{
if(!isspace(string1[i]))
{
string1[i] = tolower(string1[i]);
count++;
}
}
for(i = 0; i < strlen(string2); i++)
{
if(!isspace(string2[i]))
{
string2[i] = tolower(string2[i]);
count2++;
}
}
if(count == count2)
{
for(i = 0; i < count; i++)
{
if(string1[i] >='a' && string1[i] <= 'z')
{
letterCount1[string1[i] - 'a'] ++;
}
if(string2[i] >='a' && string2[i] <= 'z')
{
letterCount2[string2[i] - 'a'] ++;
}
}
printf("%s\n", string1);
for(i = 0; i < 26; i++)
{
printf("%d ", letterCount1[i]);
printf("%d ", letterCount2[i]);
}
}
}
main()
{
char string1[100];
char string2[100];
gets(string1);
gets(string2);
if(checkAnagram(string1, string2) == 1)
{
printf("%s", "Yes");
} else
{
printf("%s", "No");
}
}
That's because your count holds the count of non-space characters, but you keep the strings with the spaces.
For example, the string "hello world" has 11 characters, but if you run it through the loops your count will be 10 (you don't count the space). However, when you later go over the strings and count the appearance of each letter, you will go over the first 10 characters, therefore completely ignoring the last character - a 'd'.
To fix it, you need to go over all characters of the string, and only count the alphanumeric ones.
I fixed it for you:
#include <stdio.h>
#include <string.h>
int checkAnagram(char string1[], char string2[])
{
int i;
int count = 0, count2 = 0;
int letterCount1[26] = {0};
int letterCount2[26] = {0};
int len1 = strlen(string1);
int len2 = strlen(string2);
for(i = 0; i < len1; i++)
{
if(!isspace(string1[i]))
{
string1[i] = tolower(string1[i]);
count++;
}
}
for(i = 0; i < len2; i++)
{
if(!isspace(string2[i]))
{
string2[i] = tolower(string2[i]);
count2++;
}
}
if(count == count2)
{
for (i=0; i<len1; i++)
if (!isspace(string1[i]))
letterCount1[string1[i]-'a']++;
for (i=0; i<len2; i++)
if (!isspace(string2[i]))
letterCount2[string2[i]-'a']++;
int flag = 1;
for(i = 0; flag && i < 26; i++)
if (letterCount1[i] != letterCount2[i])
flag = 0;
return flag;
}
return 0;
}
main()
{
char string1[100];
char string2[100];
gets(string1);
gets(string2);
if(checkAnagram(string1, string2) == 1)
{
printf("%s", "Yes");
} else
{
printf("%s", "No");
}
}
First, don't calculate an string's length inside a loop. I extracted them into len1 and len2 variables.
Second, your loop was wrong! You shouldn't go up to count, you should go up to that string's length.
Third, you didn't return anything from checkAnagram function.

Trying to compare two strings

It is sufficient to say that I am new to C so please have show some mercy ;).
I'm trying to compare two strings. The output shouldn't contain common characters. Sadly it does.
Here is the code:
#include <stdio.h>
#include <stdlib.h>
int main(void)
{
const char msg[15] = "blueberry";
int c;
int s[15];
int j = 0;
int i = 0;
int k= 0;
int ok = 0;
int t = 0;
while (i < 15 && (c = getchar()) != '\n')
{
s[i] = c;
++i;
}
for (t=j=0; t < 15; ++t)
{
ok = 1;
//printf ("%c", s[t]);
}
for (k=0; msg[k] != '\0'; ++k)
{
if (s[t] == msg[k])
{
ok = 0;
}
}
if (ok == 1)
{
s[j] = s[t];
j++;
}
s[j] = '\0';
for (j = 0; j < 15; ++j)
printf ("%c ", s[j]);
}
The input from the keyboard is blackberry, expected output should've been U but sadly it is not. Any help please. Also why is it entering the nested for loop irrespective of condition?
My big thanks to everyone, it helped me a lot. I've figured out a way & am ok with the output. I've borrowed some ideas from A4L :).
To compare two string, you can use strcmp().
The following is a string compare program that you can use for your reference. I has both array and pointer version for better understanding.
#include <stdio.h>
int strcmp1(char a[], char b[])
{
int i=0;
while (a[i] == b[i]) {
if (a[i] == '\0')
return 0;
i++;
}
return a[i]-b[i];
}
int strcmp2(char *a, char *b)
{
while (*a == *b) {
if (*a == '\0')
return 0;
a++; b++;
}
return *a-*b;
}
int main()
{
char s1[] = "test string1";
char s2[] = "test string";
char s3[] = "aaa";
char s4[] = "bbb";
printf("strcmp1(%s, %s) = %d \n", s1, s2, strcmp1(s1, s2));
printf("strcmp2(%s, %s) = %d \n", s3, s4, strcmp2(s3, s4));
return 0;
}
given that msg contains "blueberry" and s contains "blackberry" this should do it
for (int i=0; i < strlen(msg); i++) {
for (int j = 0; j < strlen(s); j++) {
if (msg[i] != s[j]) {
printf ("%c", msg[i]);
}
}
}
yes it's ugly (using the strlen in the for gives me the chills, but I'm still low on coffeine today ^^)
i guess you want to find the first letter where the input differs from message
here is your own code with some fixes
#include <stdio.h>
#include <stdlib.h>
int main(void) {
const char msg[15] = "blueberry";
int c;
char s[15];
int i = 0;
int k= 0;
int ok = 0;
while (i < 15 && (c = getchar()) != '\n')
{
s[i] = (char) c;
++i;
}
// make sure to terminate the string after hitting enter
s[i] = '\0';
printf("input: %s\n", s);
printf("messg: %s\n", msg);
// run through both input and message with one counter
for (k=0; ok == 0 && msg[k] != '\0' && s[k] != '\0'; )
{
// if different chars stop
if (s[k] != msg[k]){
ok = 1;
} else {
// next char
k++;
}
}
if (ok == 1)
{
printf ("diff # index %d -> %c\n", k, msg[k]);
}
else
{
printf ("no diff\n");
}
return 0;
}
#include <stdio.h>
#include <string.h>
//Length to match
int comm(char* s1, char* s2){
int len = 0;
while(*s1 && *s2 && *s1++ == *s2++)
++len;
return len;
}
//commdiffcomm
/*
int commr(char* s1, char* s2){
int len = 0, limit;
int len1,len2;
len1 = strlen(s1);
len2 = strlen(s2);
limit = len1 > len2 ? len2 : len1;
s1 = s1 + len1;
s2 = s2 + len2;
while(limit-- && *--s1 == *--s2)
++len;
return len;
}
//bad
int diff(char* s1, char* s2, int* len1, int* len2){
int len, lenr, s1_len, s2_len, wk_max, i, j;
len = comm(s1, s2);
if(strcmp(s1, s2)==0){
*len1 = *len2 = 0;
return len;
}
lenr = commr(s1, s2);
*len1 = strlen(s1) - len - lenr;
*len2 = strlen(s2) - len - lenr;
return len;
}
*/
int diff(char* s1, char* s2, int* len1, int* len2){
int len, s1_len, s2_len, wk_max, i, j;
len = comm(s1, s2);
if(strcmp(s1, s2)==0){
*len1 = *len2 = 0;
return len;
}
s1_len = strlen(s1 + len + 1);
s2_len = strlen(s2 + len);
wk_max = 0;
for(i = 1; i < s1_len ; i++){
for(j = 0; j < s2_len; j++){
int com_len;
com_len = comm(s1 + len + i, s2 + len + j);
if(wk_max < com_len){
wk_max = com_len;
*len1 = i;
*len2 = j;
}
}
}
return len;
}
int main(){
char str1[16] = "blueberry";
char str2[16] = "blackberry";
char dif1[16] = "";
char dif2[16] = "";
int len0;//length of top to diff pos
int len1;
int len2;
len0 = diff(str1, str2, &len1, &len2);
strncpy(dif1, str1 + len0, len1);
strncpy(dif2, str2 + len0, len2);
if(len1 !=0 && len2 != 0){
printf("%s different %s at position %d length %d (\"%s\")\n", str1, str2, len0, len1, dif1);
printf("%s different %s at position %d length %d (\"%s\")\n", str2, str1, len0, len2, dif2);
} else {
printf("two string is same.");
}
return 0;
}
/*
blueberry different blackberry at position 2 length 2 ("ue")
blackberry different blueberry at position 2 length 3 ("ack")
*/
There are a few problems with the code as is:
You don't null-terminate your input string. Attempting to use it with c string functons would spell trouble. To fix that, change
while (i < 15 && (c = getchar()) != '\n')
{
s[i] = c;
++i;
}
to
while (i < 14 && (c = getchar()) != '\n')
{
s[i] = c;
++i;
}
s[i] = '\0';
Your specification is unclear as to whether you want your program to print the letters unique to msg, or to both s and msg. (i.e, do you want msg-s or (msg ∪ s)-(msg ∩ s) Assuming the first, the important part of your program goes like this:
k=0;
for(i=0;i<strlen(msg);i++){
int exists = 0;
for(j=0;!exists && j<strlen(s);j++){
if(msg[j] == s[i])
exists = 1;
}
if(!exists)
msg[k++] = msg[i];
}
s[k] = '\0';
The inner loop checks if s contains the current character in msg. If it does, we don't do anything, but if it doesn't, we append it to the end of a sublist we're creating on top of the bits of msg we've already processed.
your code is a mess even after the rewrite - there are too many errors to describe in detail
/*
blackbery
b l u e b e r r y
. . a c k b e . .
result = non-equal
*/
#include <stdio.h>
#include <stdlib.h>
int main(void) {
const char msg[15] = "blueberry";
int c, s[15], i,j,k, ok;
for (i=0; i < 15; i++) s[i] = 0;
for (i=0; i < 15 && (c = getchar()) != '\n'; i++) s[i] = c;
for (ok=1, k=0; msg[k] != '\0'; ++k)
if (s[k] != msg[k]) ok = 0; else s[k] = '.';
for (j = 0; j < 15; ++j) printf ("%c ", msg[j]);
printf("\n");
for (j = 0; j < 15; ++j) printf ("%c ", s[j]);
printf("\nresult = %s\n", ok ? "equal" : "non-equal");
}

Resources