visual studio cyrillic text c++ - c++

Question

I am using Visual Studio 2013, running on windows 7 64 bit.
I am trying to display a language different than English. My code is:
#include <iostream>
#include <string>
using namespace std;
typedef char byte;
byte text[] = "текст";
int text_len;
struct Huf {
byte id;
int wh;
Huf *left, *right;
};
struct List {
List *next;
Huf *tree;
};
List *head;
char code[256];
void createList();
void writeList();
void delList(List *);
void addList(Huf *);
Huf *findDels();
void createTree();
void rlrootTree(Huf *, unsigned);
int main()
{
text_len = strlen(text);
createList();
writeList();
createTree();
cout << "writeCodes\n";
rlrootTree(head->tree, 0);
cout << endl;
system("pause");
return 0;
}
void createList()
{
int i;
int ch[256] = { 0 };
for (i = 0; i<text_len; i++) ch[text[i]]++;
List *l;
Huf *h;
head = 0;
for (i = 0; i<255; i++) if (ch[i]>0)
{
h = new Huf;
h->id = i; h->wh = ch[i];
h->left = 0; h->right = 0;
l = new List;
l->tree = h;
l->next = head; head = l;
}
}
void writeList()
{
cout << "writeList\n";
List *l = head;
while (l)
{
cout << (l->tree)->id << " ";
l = l->next;
}
cout << endl;
l = head;
while (l)
{
cout << (l->tree)->wh << " ";
l = l->next;
}
cout << endl;
}
void delList(List *l)
{
List *lp, *lc;
if (l == head) { head = l->next; delete l; }
else
{
lp = head; lc = lp->next;
while (lc != l) { lp = lc; lc = lc->next; }
lp->next = lc->next; delete lc;
}
}
void addList(Huf *h)
{
List *l = new List;
l->tree = h;
l->next = head;
head = l;
}
Huf *findDels()
{
List *l = head, *sm = head;
Huf *h;
while (l)
{
if ((l->tree)->wh < (sm->tree)->wh) sm = l;
l = l->next;
}
h = sm->tree;
delList(sm);
return h;
}
void createTree()
{
Huf *h, *h1, *h2;
while (head->next)
{
h1 = findDels();
h2 = findDels();
h = new Huf;
h->id = ' '; h->wh = h1->wh + h2->wh;
h->left = h1; h->right = h2;
addList(h);
}
}
void rlrootTree(Huf *h, unsigned index)
{
if (h)
{
code[index] = '0';
rlrootTree(h->right, index + 1);
if (h->left == 0)
{
code[index] = '\0';
cout << h->id << "->" << code << " ";
}
code[index] = '1';
rlrootTree(h->left, index + 1);
}
}
I have tried adding <locale> and <windows.h> includes with AnsiToOem() but it doesnt seem to compile - I get character errors.

Answer 1

You are iterating through the text byte by byte. But each letter (grapheme) consists of two code units, that is two bytes.
To make this simple I would store the string as an array of char32_t, because then the whole codepoint (one grapheme) would fit in one element of the array.
If you want to be able to handle absolutely every international "character" you would also have to handle grapheme clusters then you would have have a look at the ICU library or similar.
A dangerously simplified suggestion:
#include <iostream>
#include <string>
#include <cstring>
using namespace std;
typedef char32_t byte;
byte text[] = U"текст";
int text_len;
struct Huf {
byte id;
int wh;
Huf *left, *right;
};
struct List {
List *next;
Huf *tree;
};
List *head;
char code[16000];
void createList();
void writeList();
void delList(List *);
void addList(Huf *);
Huf *findDels();
void createTree();
void rlrootTree(Huf *, unsigned);
unsigned strlen(char32_t* st) {
unsigned len = 0;
while (*(st+len) != 0) ++len;
return len;
}
int main()
{
text_len = strlen(text);
std::cout << "len = " << text_len << std::endl;
createList();
writeList();
createTree();
cout << "writeCodes\n";
rlrootTree(head->tree, 0);
cout << endl;
system("pause");
return 0;
}
void createList()
{
int i;
int ch[16000] = { 0 }; //you really need more here
for (i = 0; i<text_len; i++) ch[text[i]]++;
List *l;
Huf *h;
head = 0;
for (i = 0; i<16000; i++) if (ch[i]>0)
{
h = new Huf;
h->id = i; h->wh = ch[i];
h->left = 0; h->right = 0;
l = new List;
l->tree = h;
l->next = head; head = l;
}
}
void writeList()
{
cout << "writeList\n";
List *l = head;
while (l)
{
cout << (l->tree)->id << " ";
l = l->next;
}
cout << endl;
l = head;
while (l)
{
cout << (l->tree)->wh << " ";
l = l->next;
}
cout << endl;
}
void delList(List *l)
{
List *lp, *lc;
if (l == head) { head = l->next; delete l; }
else
{
lp = head; lc = lp->next;
while (lc != l) { lp = lc; lc = lc->next; }
lp->next = lc->next; delete lc;
}
}
void addList(Huf *h)
{
List *l = new List;
l->tree = h;
l->next = head;
head = l;
}
Huf *findDels()
{
List *l = head, *sm = head;
Huf *h;
while (l)
{
if ((l->tree)->wh < (sm->tree)->wh) sm = l;
l = l->next;
}
h = sm->tree;
delList(sm);
return h;
}
void createTree()
{
Huf *h, *h1, *h2;
while (head->next)
{
h1 = findDels();
h2 = findDels();
h = new Huf;
h->id = ' '; h->wh = h1->wh + h2->wh;
h->left = h1; h->right = h2;
addList(h);
}
}
void rlrootTree(Huf *h, unsigned index)
{
if (h)
{
code[index] = '0';
rlrootTree(h->right, index + 1);
if (h->left == 0)
{
code[index] = '\0';
cout << h->id << "->" << code << " ";
}
code[index] = '1';
rlrootTree(h->left, index + 1);
}
}