Question

Description:

Overview: You will write a program (says wordcountfreq.c) to find out the number of words and how many times each word appears (i.e., the frequency) in multiple text files. Specifically, the program will first determine the number of files to be processed. Then, the program will createmultiple threads where each thread is responsible for one file to count the number of words appeared in the file and report the number of time each word appears in a global linked-list. The typical format to run the program with input parameters is as follows:

./wordcountfreq File_1  File_2 ... File_n

Details: First, the program needs to determine the number of files to be processed. This can be done with the argc parameter of the main function; Then, the argv parameter can be used to retrieve the name for each file.
After that, you need to use pthread create() to create multiple threads (one for each file). Each thread needs to count the number of words in its file and keeps tracks of how many times each word appears in all the files using a global linked-list, where each node represented a different word in any file. When a thread finishes, it should print out the number of words it found as follows:

Thread x: number of words in File_x is XXX

At the end, the main thread needs to get the number of words from each thread and report the total number of words found by all threads as well as frequency of each word in all files as follows:

All n files have been counted and the total of xxx words found !
aaa appears XXX times
bbb appears YYY times
...

zzz appears MMM times

Here, words should appear in the dictionary order in the report!

For word counting, you could simply use the space character as the delimiter. Anything that are not separated by the space will be counted as a single word. For instance, the example “The first program is a Hello-world.” will be reported as 6 words (where Hello-world is counted as a single word). You could compare your results using the wc utility that is available on Linux machines.

Answer 1

#include <stdio.h>

#include <stdlib.h>

#include <stdbool.h>

#include <string.h>

#include <pthread.h>

struct thread_info { /* Used as argument to thread_start() */

pthread_t thread_id; /* ID returned by pthread_create() */

int thread_num; /* Application-defined thread # */

char *argv_string; /* From command-line argument filename */

};

// A linked list node

struct Node

{

char *data;

int count;

struct Node *next;

};

struct Node *head = NULL;

int totalWordCount = 0;

void push(char *new_data)

{

/* 1. allocate node */

struct Node *new_node = (struct Node *)malloc(sizeof(struct Node));

/* 2. put in the data */

new_node->data = new_data;

new_node->count = 1;

/* 3. Make next of new node as head */

new_node->next = (head);

/* 4. move the head to point to the new node */

(head) = new_node;

}

bool search(char *x)

{

struct Node *current = head; // Initialize current

while (current != NULL)

{

if (current->data == x)

{

current->count++;

return true;

}

current = current->next;

}

return false;

}

void AddWord(char *word)

{

if (search(word))

{

//update the count

}

else

{

push(word);

}

}

// This function prints contents of linked list starting from head

void printList()

{

struct Node *node = head;

while (node != NULL)

{

printf("%s appears %d times\n", node->data, node->count);

node = node->next;

}

}

void *processFile(void *vargp)

{

int noOfWords = 0;

// Store the value argument passed to this thread

struct thread_info *tinfo = vargp;

FILE *fp;

fp = fopen(tinfo->argv_string, "r"); // read mode

if (fp == NULL)

{

perror("Error while opening the file.\n");

exit(EXIT_FAILURE);

}

char line[256]; /* or other suitable maximum line size */

while (fgets(line, sizeof line, fp) != NULL) /* read a line */

{

//fputs ( line, stdout ); /* write the line */

char *token = strtok(line, " ");

while (token != NULL)

{

AddWord(token);

token = strtok(NULL, " ");

}

}

printf("Thread %d: number of words in %s is %d", tinfo->thread_num, tinfo->argv_string, noOfWords);

totalWordCount += noOfWords;

fclose(fp);

}

int main(int argc, char const *argv[])

{

pthread_t thread_id;

char ch, file_name[25];

int noOfFiles = argc - 1;

for (size_t i = 0; i < noOfFiles; i++)

{

struct thread_info tinfo;

tinfo.thread_num = i + 1;

tinfo.argv_string = argv[i + 1];

pthread_create(&tinfo.thread_id, NULL, processFile, &tinfo);

}

printf("All %d files have been counted and the total of %d words found !", noOfFiles, totalWordCount);

printList();

return 0;

}

//output:

Language: C (gcc) Editor CodeMirror Layout Vertical struct thread info *tinfo-vargp; FILE *fp 82 83 84 fp fopen(tinfo->argv-string, 85 if (fpNULL) "r..); // read mode 86 87 perror("Error while opening the file.\n) exit (EXIT FAILURE); 89 90 91 92 93 94 95 96 97 98 char line[256]; while (fgets(line, sizeof line, fp) != NULL) /* read a line */ f* or other suitable maximum line size //fputs (line, stdout); write the line/ char *token strtok (line, " "); while (token I= NULL) Addword (token); token strtok (NULL, " "); 100 101 02 103 104 105 106 07 printf("Thread %d: totalWordCount noofWords; fclose(fp); number of words in %s is %d", tinfo-thread-num, tinfo->argv-string, noOfWords); return uargv; Live cooperation Put on a wallF Run it (F8) Fork it Show compiler warnings Compiler args Show input Compilation time: 0.12 sec, absolute running time: 0.07 sec, cpu time: 0.01 sec, memory peak: 3 Mb, absolute service time: 0,2 sec latest | hi All e files have been counted and the total of e words found!