Develop a C program which reads and processes an input text file like this textdata.txt. It retrieves the following information.

• number of lines
• number of words
• number of distinct words
• words and their frequencies

The program outputs the retrieved information to a file like this result.txt.

Specifically, write C programs myword.h containing the following structure definitions and function headers, and myword.c containing the implementations of the functions. It is required to use your trim() and lower_case() functions from Q1, and it is allowed to use other string functions such as strcat() and strstr() from string library. string.h:

#ifndef SRC_MYWORD_H_ #define SRC_MYWORD_H_

#define MAX_WORD 30 #define MAX_LINE_LEN 1000 #define MAX_WORDS 1000

typedef struct word { char word[30]; int frequency; } WORD;

typedef struct words { WORD word_array[1000]; int line_count; int word_count; int distinct_word_count; } WORDINFO;

int process_word(char *filename, WORDINFO *wordinfo); int save_to_file(char *filename, WORDINFO *wordinfo);

#endif /* SRC_MYWORD_H_ */

Use the provided main function file myword_main.c to test your programs as the following.

Public test

gcc mystring.c myword.c myword_main.c -o q2 q2 word processing:done line count:2 word count:10 distinct word count:6 this:2 is:2 the:2 first:1 test:2 second:1 saving result to file:done

myword.c:

#include  #include  #include "mystring.h" #include "myword.h"

int process_word(char *infilename, WORDINFO *wip) { const char delimiters[] = " .,;:!()&?- \t \"\'"; // your implementation }

int save_to_file(char *outfilename, WORDINFO *wip) { // your implementation }

myword_main.c:

#include #include #include "mystring.h" #include "myword.h"

void display_word_summary(WORDINFO *wip) { printf("%s:%d ", "line count", wip->line_count); printf("%s:%d ", "word count", wip->word_count); printf("%s:%d ", "distinct word count", wip->distinct_word_count); int i; for (i = 0; i < wip->distinct_word_count; i++) { printf("%s:%d ", wip->word_array[i].word, wip->word_array[i].frequency); } }

int main(int argc, char *args[]) { char infilename[40] = "textdata.txt"; //default input file name char outfilename[40] = "result.txt"; //default output file name

if (argc > 1) { if (argc >= 2) strcpy(infilename, args[1]); if (argc >= 3) strcpy(outfilename, args[2]); }

WORDINFO wordinfo = { 0 }; process_word(infilename, &wordinfo); printf("word processing:done "); display_word_summary(&wordinfo); save_to_file(outfilename, &wordinfo); printf("saving result to file:done ");

return 0; }

result.txt:

line count:2 word count:10 distinct word count:6 this:2 is:2 the:2 first:1 test:2 second:1

textdata.txt:

THIS IS THE FIRST TEST. This is the second test.