[c] Check substring exists in a string in C

I'm trying to check whether a string contains a substring in C like:

char *sent = "this is my sample example";
char *word = "sample";
if (/* sentence contains word */) {
    /* .. */
}

What is something to use instead of string::find in C++?

This question is related to c string

The answer is


And here is how to report the position of the first character off the found substring:

Replace this line in the above code:

printf("%s",substring,"\n");

with:

printf("substring %s was found at position %d \n", substring,((int) (substring - mainstring)));

Using C - No built in functions

string_contains() does all the heavy lifting and returns 1 based index. Rest are driver and helper codes.

Assign a pointer to the main string and the substring, increment substring pointer when matching, stop looping when substring pointer is equal to substring length.

read_line() - A little bonus code for reading the user input without predefining the size of input user should provide.

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

int string_len(char * string){
  int len = 0;
  while(*string!='\0'){
    len++;
    string++;
  }
  return len;
}

int string_contains(char *string, char *substring){
  int start_index = 0;
  int string_index=0, substring_index=0;
  int substring_len =string_len(substring);
  int s_len = string_len(string);
  while(substring_index<substring_len && string_index<s_len){
    if(*(string+string_index)==*(substring+substring_index)){
      substring_index++;
    }
    string_index++;
    if(substring_index==substring_len){
      return string_index-substring_len+1;
    }
  }

  return 0;

}

#define INPUT_BUFFER 64
char *read_line(){
  int buffer_len = INPUT_BUFFER;
  char *input = malloc(buffer_len*sizeof(char));
  int c, count=0;

  while(1){
    c = getchar();

    if(c==EOF||c=='\n'){
      input[count]='\0';
      return input;
    }else{
      input[count]=c;
      count++;
    }

    if(count==buffer_len){
      buffer_len+=INPUT_BUFFER;
      input = realloc(input, buffer_len*sizeof(char));
    }

  }
}

int main(void) {
  while(1){
    printf("\nEnter the string: ");
    char *string = read_line();
    printf("Enter the sub-string: ");
    char *substring = read_line(); 
    int position = string_contains(string,substring);
    if(position){ 
      printf("Found at position: %d\n", position);
    }else{
      printf("Not Found\n");
    }
  }
  return 0;
}

Use strstr for this.

http://www.cplusplus.com/reference/clibrary/cstring/strstr/

So, you'd write it like..

char *sent = "this is my sample example";
char *word = "sample";

char *pch = strstr(sent, word);

if(pch)
{
    ...
}

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

int findSubstr(char *inpText, char *pattern);
int main()
{
    printf("Hello, World!\n");
    char *Text = "This is my sample program";
    char *pattern = "sample";
    int pos = findSubstr(Text, pattern);
    if (pos > -1) {
        printf("Found the substring at position %d \n", pos);
    }
    else
        printf("No match found \n");

    return 0;
}

int findSubstr(char *inpText, char *pattern) {
    int inplen = strlen(inpText);
    while (inpText != NULL) {

        char *remTxt = inpText;
        char *remPat = pattern;

        if (strlen(remTxt) < strlen(remPat)) {
            /* printf ("length issue remTxt %s \nremPath %s \n", remTxt, remPat); */
            return -1;
        }

        while (*remTxt++ == *remPat++) {
            printf("remTxt %s \nremPath %s \n", remTxt, remPat);
            if (*remPat == '\0') {
                printf ("match found \n");
                return inplen - strlen(inpText+1);
            }
            if (remTxt == NULL) {
                return -1;
            }
        }
        remPat = pattern;

        inpText++;
    }
}

This code implements the logic of how search works (one of the ways) without using any ready-made function:

public int findSubString(char[] original, char[] searchString)
{
    int returnCode = 0; //0-not found, -1 -error in imput, 1-found
    int counter = 0;
    int ctr = 0;
    if (original.Length < 1 || (original.Length)<searchString.Length || searchString.Length<1)
    {
        returnCode = -1;
    }

    while (ctr <= (original.Length - searchString.Length) && searchString.Length > 0)
    {
        if ((original[ctr]) == searchString[0])
        {
            counter = 0;
            for (int count = ctr; count < (ctr + searchString.Length); count++)
            {
                if (original[count] == searchString[counter])
                {
                    counter++;
                }
                else
                {
                    counter = 0;
                    break;
                }
            }
            if (counter == (searchString.Length))
            {
                returnCode = 1;
            }
        }
        ctr++;
    }
    return returnCode;
}

My code to find out if substring is exist in string or not 
// input ( first line -->> string , 2nd lin ->>> no. of queries for substring
following n lines -->> string to check if substring or not..

#include <stdio.h>
int len,len1;
int isSubstring(char *s, char *sub,int i,int j)
{

        int ans =0;
         for(;i<len,j<len1;i++,j++)
        {
                if(s[i] != sub[j])
                {
                    ans =1;
                    break;
                }
        }
        if(j == len1 && ans ==0)
        {
            return 1;
        }
        else if(ans==1)
            return 0;
return 0;
}
int main(){
    char s[100001];
    char sub[100001];
    scanf("%s", &s);// Reading input from STDIN
    int no;
    scanf("%d",&no);
    int i ,j;
    i=0;
    j=0;
    int ans =0;
    len = strlen(s);
    while(no--)
    {
        i=0;
        j=0;
        ans=0;
        scanf("%s",&sub);
        len1=strlen(sub);
        int value;
        for(i=0;i<len;i++)
        {
                if(s[i]==sub[j])
                {
                    value = isSubstring(s,sub,i,j);
                    if(value)
                    {
                        printf("Yes\n");
                        ans = 1;
                        break;
                    }
                }
        }
        if(ans==0)
            printf("No\n");

    }
}

The same will be achived with this simpler code: Why use these:

int main(void)
{

    char mainstring[]="The quick brown fox jumps over the lazy dog";
    char substring[20];
    int i=0;
    puts("enter the sub stirng to find");
    fgets(substring, sizeof(substring), stdin);
    substring[strlen(substring)-1]='\0';
    if (strstr(mainstring,substring))
    {
            printf("substring is present\t");
    }
    printf("and the sub string is:::");
    printf("%s",substring,"\n");
   return 0;
}

But the tricky part would be to report at which position in original string the substring starts...


I believe that I have the simplest answer. You don't need the string.h library in this program, nor the stdbool.h library. Simply using pointers and pointer arithmetic will help you become a better C programmer.

Simply return 0 for False (no substring found), or 1 for True (yes, a substring "sub" is found within the overall string "str"):

#include <stdlib.h>

int is_substr(char *str, char *sub)
{
  int num_matches = 0;
  int sub_size = 0;
  // If there are as many matches as there are characters in sub, then a substring exists.
  while (*sub != '\0') {
    sub_size++;
    sub++;
  }

  sub = sub - sub_size;  // Reset pointer to original place.
  while (*str != '\0') {
    while (*sub == *str && *sub != '\0') {
      num_matches++;
      sub++;
      str++;
    }
    if (num_matches == sub_size) {
      return 1;
    }
    num_matches = 0;  // Reset counter to 0 whenever a difference is found. 
    str++;
  }
  return 0;
}

Try to use pointers...

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

int main()
{

  char str[] = "String1 subString1 Strinstrnd subStr ing1subString";
  char sub[] = "subString";

  char *p1, *p2, *p3;
  int i=0,j=0,flag=0;

  p1 = str;
  p2 = sub;

  for(i = 0; i<strlen(str); i++)
  {
    if(*p1 == *p2)
      {
          p3 = p1;
          for(j = 0;j<strlen(sub);j++)
          {
            if(*p3 == *p2)
            {
              p3++;p2++;
            } 
            else
              break;
          }
          p2 = sub;
          if(j == strlen(sub))
          {
             flag = 1;
            printf("\nSubstring found at index : %d\n",i);
          }
      }
    p1++; 
  }
  if(flag==0)
  {
       printf("Substring NOT found");
  }
return (0);
}

My own humble (case sensitive) solution:

uint8_t strContains(char* string, char* toFind)
{
    uint8_t slen = strlen(string);
    uint8_t tFlen = strlen(toFind);
    uint8_t found = 0;

    if( slen >= tFlen )
    {
        for(uint8_t s=0, t=0; s<slen; s++)
        {
            do{

                if( string[s] == toFind[t] )
                {
                    if( ++found == tFlen ) return 1;
                    s++;
                    t++;
                }
                else { s -= found; found=0; t=0; }

              }while(found);
        }
        return 0;
    }
    else return -1;
}

Results

strContains("this is my sample example", "th") // 1
strContains("this is my sample example", "sample") // 1
strContains("this is my sample example", "xam") // 1
strContains("this is my sample example", "ple") // 1
strContains("this is my sample example", "ssample") // 0
strContains("this is my sample example", "samplee") // 0
strContains("this is my sample example", "") // 0
strContains("str", "longer sentence") // -1
strContains("ssssssample", "sample") // 1
strContains("sample", "sample") // 1

Tested on ATmega328P (avr8-gnu-toolchain-3.5.4.1709) ;)


You can try this one for both finding the presence of the substring and to extract and print it:

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

int main(void)
{
    char mainstring[]="The quick brown fox jumps over the lazy dog";
    char substring[20], *ret;
    int i=0;
    puts("enter the sub string to find");
    fgets(substring, sizeof(substring), stdin);
    substring[strlen(substring)-1]='\0';
    ret=strstr(mainstring,substring);
    if(strcmp((ret=strstr(mainstring,substring)),substring))
    {
        printf("substring is present\t");
    }
    printf("and the sub string is:::");

    for(i=0;i<strlen(substring);i++)
    {
            printf("%c",*(ret+i));

    }
    puts("\n");
    return 0;
}