Geek asks and answers

How to read a binary file to calculate the frequency of the Huffman tree?

I need to calculate the frequency of the Huffman tree from the “binary” as the only argument. I have a doubt that binaries are files containing only "0" and "1".

While the frequency is a repetition of the number of alphabets (for example, abbacdd here the frequency is a = 2, b = 2, c = 1, d = 2). And my structure should be like this:

struct Node
{
unsigned char symbol;   /* the symbol or alphabets */
int freq;               /* related frequency */
struct Node *left,*right; /* Left and right leafs */
};

But I don’t understand at all how I can get the character from the “.bin” file (which consists of only “0” and “1”)?

When I try to see the contents of the file, I get:

hp@ubuntu:~/Desktop/Internship_Xav/Huf_pointer$ xxd -b out.bin 
0000000: 00000000 00000000 00000000 00000000 00000000 00000000  ......
0000006: 00000000 00000000 00000000 00000000 00000000 00000000  ......
000000c: 00000000 00000000 00000000 00000000 00000000 00000000  ......
0000012: 00000000 00000000 00000000 00000000 00000000 00000000  ......
0000018: 00000000 00000000 00000000 00000000 00000000 00000000  ......
000001e: 00000000 00000000 00000000 00000000 00000000 00000000  ......
0000024: 00000000 00000000 00000000 00000000 00000000 00000000  ......
000002a: 00000000 00000000 00000000 00000000 00000000 00000000  ......
0000030: 00000000 00000000 00000000 00000000 00000000 00000000  ......
.........//Here also there is similar kind of data    ................
00008ca: 00010011 00010011 00010011 00010011 00010011 00010011  ......
00008d0: 00010011 00010011 00010011 00010011 00010011 00010011  ......
00008d6: 00010011 00010011 00010011 00010011 00010011 00010011  .....

, , . . , HUffman, .

+3
2

- .
std::map.
- :

#include <algorithm>
#include <fstream>
#include <map>
#include <string>

std::map <unsigned char, int> CreateFrequencyTable (const std::string &strFile)
{
    std::map <unsigned char, int> char_freqs ; // character frequencies

    std::ifstream file (strFile) ;

    int next = 0 ;
    while ((next = file.get ()) != EOF) {
        unsigned char uc = static_cast <unsigned char> (next) ;

        std::map <unsigned char, int>::iterator iter ;
        iter = char_freqs.find (uc) ;

        // This character is in our map.
        if (iter != char_freqs.end ()) {
            iter->second += 1 ;
        }

        // This character is not in our map yet.
        else {
            char_freqs [uc] = 1 ;
        }
    }

    return char_freqs ;
}

:

std::map <unsigned char, int> char_freqs = CreateFrequencyTable ("file") ;

:

std::map <unsigned char, int>::iterator iter = std::max_element (
    char_freqs.begin (), 
    char_freqs.end (), 
    std::map <unsigned char, int>::value_comp
) ;

.
, - , .

, :

// Make sure to #include <iterator>
std::ifstream file ("test.txt") ;
std::istream_iterator <unsigned char> begin = file ;
std::vector<unsigned char> vecBuffer (begin, std::istream_iterator <unsigned char> ()) ;

.

+2

,
unsigned char
, , ?
, 0 1, 0 1 .

00010011 - xxd
xxd -b 0/1 .
0 255,
0123456789abcdef
, ,
.

, C/++,
unsigned char,
, , . .

, , ,
256 (0,1,2... 255).
, 256 ( Node)

, .

+1

More articles:


All Articles