Create a C program to sort the lines of an input file (or from standard input) a
ID: 3803207 • Letter: C
Question
Create a C program to sort the lines of an input file (or from standard input) and print the sorted lines to an output file (or standard output). Your program, called bstsort (binary search tree sort), will take the following command line arguments: % bstsort [-c] [-o output_file_name] [input_file_name] If -c is present, the program needs to compare the strings case sensitive; otherwise, it's case insensitive. If the output_file_name is given with the -o option, the program will output the sorted lines to the given output file; otherwise, the output shall be the standard output. Similarly, if the input_file_name is given, the program will read from the input file; otherwise, the input will be from the standard input. You must use getopt() to parse the command line arguments to determine the cases. All strings will be no more than 100 characters long. In addition to parsing and processing the command line arguments, your program needs to do the following:
1. You need to construct a binary search tree as you read from input. A binary search tree is a binary tree. Each node can have at most two child nodes (one on the left and one on the right), both or either one can be empty. If a child node exists, it's the root of a binary search tree (we call subtree). Each node contains a key (in our case, it's a string) and a count of how many of that string were included. If the left subtree of a node exists, it contains only nodes with keys less than the node's key. If the right subtree of a node exists, it contains only nodes with keys greater than the node's key. You can look up binary search tree on the web or in your Data Structure textbook. Note that you do not need to balance the binary search tree (that is, you can ignore all those rotation operations).
2. Initially the tree is empty (that is, the root is null). The program reads from the input file (or stdin) one line at a time; If the line is not an empty line and the line is not already in the tree, it should create a tree node that stores a pointer to the string (or optionally a copy of the string) and a count of 1 indicating this is the first occurrence of that string, and then insert the tree node to the binary search tree. An empty line would indicate the end of input for stdin, an empty line or end of file would indicate the end of input for an input file. If the line is not an empty line and the line is already in the tree, increase the count for that node indicating that there are multiple instances of that line.
3. You must develop two string comparison functions, one for case sensitive and the other for case insensitive. You must not use strcmp() and strcasecmp() functions provided by the C library. You must implement your own version.
4. Once the program has read all the input (when EOF is returned), the program then performs an in-order traversal of the binary search tree to print out all the strings one line at a time to the output file or stdout. If there are duplicates than include all duplicates.
5. Before the program ends, it must reclaim the tree! You can do this by performing a post-order traversal, i.e., reclaiming the children nodes before reclaiming the node itself. Make sure you also reclaim the memory occupied by the string as well.
6. It is required that you use getopt for processing the command line and use malloc/free functions for dynamically allocating and deallocating nodes and the buffers for the strings. It is required that you implement your own string comparison functions instead of using the corresponding libc functions.
Explanation / Answer
Given below is the code for the question along with different runs of the program. Please do rate the answer if it helped.
bst.h
#ifndef bst_h
#define bst_h
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
typedef struct bst_node
{
char *word;
int count;
struct bst_node *left;
struct bst_node *right;
}node;
int string_compare(char *s1, char *s2) //case sensitive comparision
{
int i = 0;
char ch1 , ch2;
while(s1[i] != '' && s2[i] != '')
{
ch1 = s1[i];
ch2 = s2[i];
if(ch1 != ch2)
return ch1-ch2;
i++;
}
if(s1[i] == '')
if(s2[i] == '')
return 0;
else
return s2[i];
else
return s1[i];
}
int string_ncompare(char *s1, char *s2) //case insensitive comparsion
{
int i = 0;
char ch1 , ch2;
while(s1[i] != '' && s2[i] != '')
{
ch1 = s1[i];
ch2 = s2[i];
if(ch1 >= 'A' && ch1 <='Z')
ch1 = ch1 - 'A' + 'a';
if(ch2 >= 'A' && ch2 <='Z')
ch2 = ch2 - 'A' + 'a';
if(ch1 != ch2)
return ch1-ch2;
i++;
}
if(s1[i] == '')
if(s2[i] == '')
return 0;
else
return s2[i];
else
return s1[i];
}
node* create_node(char *str)
{
node* n = (node*) malloc(sizeof(node));
n->word = (char *) malloc(strlen(str));
n->count = 1;
strcpy(n->word, str);
n->left = NULL;
n->right = NULL;
return n;
}
void insert(node **root, char *str, int case_sensitive)
{
node *curr;
int cmp;
if(*root == NULL)
*root = create_node(str);
else
{
curr = *root;
while(curr != NULL)
{
//printf("curr %s ", curr->word );
if(case_sensitive)
cmp = string_compare(str, curr->word);
else
cmp = string_ncompare(str, curr->word);
if(cmp == 0)
{
curr->count++;
return;
}
else if(cmp < 0)
{
//printf("go left ");
if(curr->left == NULL)
{
curr->left = create_node(str);
return;
}
curr = curr->left;
}
else
{
// printf("go right ");
if(curr->right == NULL)
{
curr->right = create_node(str);
return;
}
curr = curr->right;
}
}
}
}
void in_order(FILE *outfile, node *node)
{
if(node == NULL) return;
in_order(outfile, node->left);
fprintf(outfile, "%s[%d] ", node->word, node->count);
in_order(outfile, node->right);
}
void free_node(node *root)
{
if(root == NULL) return;
free_node(root->left);
free_node(root->right);
free(root->word);
free(root);
}
#endif /* bst_h */
bstsort.c
#include <stdio.h>
#include <unistd.h>
#include "bst.h"
int main(int argc, char **argv)
{
int case_sensitive = 0;
FILE *infile = stdin;
FILE *outfile = stdout;
char line[50];
node *root = NULL;
int c;
//process commandline arguments
while ((c = getopt (argc, argv, "co:")) != -1)
switch (c)
{
case 'c':
case_sensitive = 1;
printf("case sensitive ");
break;
case 'o':
outfile = fopen(optarg, "w");
printf("output file %s ", optarg);
if(outfile == NULL)
{
printf("Error opening output file %s ", optarg);
outfile = stdout;
}
break;
case '?':
printf("other %s", optarg);
if (optopt == 'o')
printf ("Option -%c requires an argument. ", optopt);
else
printf ("Unknown option character `\x%x'. ",
optopt);
return 1;
default:
break;
}
if(optind != argc)
{
infile = fopen(argv[optind], "r");
if(infile == NULL)
{
printf("Error opening input file %s ", argv[optind]);
infile = stdin;
}
}
while(fgets(line, 50, infile) != NULL)
{
if(string_compare(" ", line) == 0)
break;
//remove newline from the end of line
line[strlen(line) - 1] = '';
insert(&root, line, case_sensitive);
}
fclose(infile);
in_order(outfile, root);
fclose(outfile);
free_node(root);
}
input file : fruits.txt
mango
apple
guava
Apple
Mango
mango
guava
output
$ ./a.out
mango
apple
guava
pineapple
orange
watermelon
apple
grapes
orange
papaya
apple[2]
grapes[1]
guava[1]
mango[1]
orange[2]
papaya[1]
pineapple[1]
watermelon[1]
============================
$ ./a.out -c -o outfile.txt
case sensitive
output file outfile.txt
mango
apple
guava
Apple
Mango
mango
guava
============
$ cat outfile.txt
Apple[1]
Mango[1]
apple[1]
guava[2]
mango[2]
===========
$ ./a.out
mango
apple
guava
pineapple
apple[1]
guava[1]
mango[1]
pineapple[1]
===========
$ ./a.out -c -o outfile.txt fruits.txt
case sensitive
output file outfile.txt
amoeba-2:Test raji$ cat outfile.txt
Apple[1]
Mango[1]
apple[1]
guava[2]
mango[2]