#include <stdio.h>
#include <string.h>
#include <stdbool.h>
// A stopwords list is a collection of commonly used words in a language
// that are often removed during text processing tasks.
// Define stop words
const char* stopWords[] = {
"i","me","my","myself","we","our","ours","ourselves","you","your",
"yours","yourself","yourselves","he","him","his","himself","she","her",
"hers","herself","it","its","itself","they","them","their","theirs",
"themselves","what","which","who","whom","this","that","these","those",
"am","is","are","was","were","be","been","being","have","has","had",
"having","do","does","did","doing","a","an","the","and","but","if","or",
"because","as","until","while","of","at","by","for","with","about","against",
"between","into","through","to","from","in","out","on","off","over","further",
"then","here","there","when","where","why","how","all","any","both","each",
"few","more","most","other","some","such","no","nor","not","only","own",
"same","so","than","too","very","can","will","just","don","should","now"
};
int stopWordsCount = sizeof(stopWords) / sizeof(stopWords[0]);
bool isStopWord(const char* word) {
for (int i = 0; i < stopWordsCount; ++i) {
if (strcmp(word, stopWords[i]) == 0)
return true;
}
return false;
}
void removeStopWords(char* input) {
char* token = strtok(input, " ");
char output[1024] = "";
while (token != NULL) {
if (!isStopWord(token)) {
strcat(output, token);
strcat(output, " ");
}
token = strtok(NULL, " ");
}
// Trim trailing space
size_t len = strlen(output);
if (len > 0 && output[len - 1] == ' ')
output[len - 1] = '\0';
printf("%s\n", output);
}
int main() {
char input[] = "a c programming and java to python a we if c# then a and aa";
printf("%s\n", input);
removeStopWords(input);
return 0;
}
/*
run:
a c programming and java to python a we if c# then a and aa
c programming java python c# aa
*/
