In 1953, David A. Huffman published his paper "A Method for the Construction of Minimum-Redundancy Codes", and hence printed his name in the history of computer science. As a professor who gives the final exam problem on Huffman codes, I am encountering a big problem: the Huffman codes are NOT unique. For example, given a string "aaaxuaxz", we can observe that the frequencies of the characters 'a', 'x', 'u' and 'z' are 4, 2, 1 and 1, respectively. We may either encode the symbols as {'a'=0, 'x'=10, 'u'=110, 'z'=111}, or in another way as {'a'=1, 'x'=01, 'u'=001, 'z'=000}, both compress the string into 14 bits. Another set of code can be given as {'a'=0, 'x'=11, 'u'=100, 'z'=101}, but {'a'=0, 'x'=01, 'u'=011, 'z'=001} is NOT correct since "aaaxuaxz" and "aazuaxax" can both be decoded from the code 00001011001001. The students are submitting all kinds of codes, and I need a computer program to help me determine which ones are correct and which ones are not.
Input Specification:
Each input file contains one test case. For each case, the first line gives an integer N (2≤N≤63), then followed by a line that contains all the N distinct characters and their frequencies in the following format:
c[1] f[1] c[2] f[2] ... c[N] f[N]
where c[i]
is a character chosen from {'0' - '9', 'a' - 'z', 'A' - 'Z', '_'}, and f[i]
is the frequency of c[i]
and is an integer no more than 1000. The next line gives a positive integer M (≤1000), then followed by M student submissions. Each student submission consists of N lines, each in the format:
c[i] code[i]
where c[i]
is the i
-th character and code[i]
is an non-empty string of no more than 63 '0's and '1's.
Output Specification:
For each test case, print in each line either "Yes" if the student's submission is correct, or "No" if not.
Note: The optimal solution is not necessarily generated by Huffman algorithm. Any prefix code with code length being optimal is considered correct.
Sample Input:
7
A 1 B 1 C 1 D 3 E 3 F 6 G 6
4
A 00000
B 00001
C 0001
D 001
E 01
F 10
G 11
A 01010
B 01011
C 0100
D 011
E 10
F 11
G 00
A 000
B 001
C 010
D 011
E 100
F 101
G 110
A 00000
B 00001
C 0001
D 001
E 00
F 10
G 11
结尾无空行
Sample Output:
Yes
Yes
No
No
结尾无空行
STL优先队列解法:
#include <bits/stdc++.h>
using namespace std;
priority_queue<int,vector<int>,greater<int> >q; //优先队列,最小堆
unordered_map<char,int> mapp; // 散列表O(1)查找
int n,m,WPL=0;
int cmp(string &a,string &b)
{
return a.size() < b.size();
}
// 判断是否为前缀
int isPrefix(string code[])
{
// 按字符串长度从小到大排序
sort(code,code+n,cmp);
for(int i=0; i<n; i++)
{
for(int j=i+1; j<n; j++) // 查找之后全部字符
{
// 如果短字符串与长字符串截取相同长度相等,即为前缀
if(code[j].substr(0,code[i].size()) == code[i])
return 1;
}
}
return 0;
}
int main()
{
cin.tie(0);
cout.tie(0);
// freopen("C:/Users/zhaochen/Desktop/input.txt", "r", stdin);
cin>>n;
for(int i=0; i<n; i++)
{
char ch;
int frequency;
cin>>ch>>frequency;
mapp[ch] = frequency;
q.push(frequency);
}
while(q.size() > 1)
{
// 取出两个最小的元素
int x = q.top();
q.pop();
int y = q.top();
q.pop();
q.push(x+y);
WPL += x+y;
// 因为所有叶结点的权值加起来等于根节点,所以WLP也等于所有非叶结点的权值之和
}
cin>>m;
while(m--)
{
int res = 0;
string code[64];
char ch;
for(int i=0; i<n; i++)
{
cin>>ch>>code[i];
res += code[i].size()*mapp[ch]; // 长度*频率的总和
}
if(res != WPL || isPrefix(code))
{
if(m==0)
cout<< "No";
else
cout<< "No"<< endl;
}
else
{
if(m==0)
cout<< "Yes";
else
cout<< "Yes"<< endl;
}
}
return 0;
}
手动建哈夫曼树:
#include <bits/stdc++.h>
#define x first
#define y second
using namespace std;
typedef long long ll;
unordered_map<char,int>mapp; // 散列表O(1)查找
typedef struct Tnode* HuffmanTree;
struct Tnode
{
int weight;
HuffmanTree left,right;
};
int N,WPL=0;
int heapsize=0;
int heap[64]= {0}; // 最小堆
void Insert(int x) // 在最小堆中插入x
{
if(heapsize > 64)
return;
int i=++heapsize;
for(; heap[i/2] > x; i/=2)
{
heap[i] = heap[i/2];
}
heap[i] = x;
}
int deleteMin()
{
int top=heap[1];
int last=heap[heapsize--];
int parent,child;
for(parent=1; parent*2<=heapsize; parent=child) // 不要写parent*=2
{
child=parent*2;
if(child < heapsize && heap[child+1] < heap[child])
{
child++;
}
if(last < heap[child])
{
break;
}
heap[parent] = heap[child];
}
heap[parent] = last;
return top;
}
HuffmanTree creatANode()
{
HuffmanTree t = (HuffmanTree)malloc(sizeof(struct Tnode));
t->left = NULL;
t->right = NULL;
t->weight = 0;
return t;
}
int check()
{
HuffmanTree root = creatANode();
int res=0,flag=1;
for(int i=0; i<N; i++) // N个结点
{
HuffmanTree cur = root;
char ch;
string code;
cin>>ch>>code;
if(flag)
{
for(int j=0; j<code.size(); j++)
{
if(code[j]=='0')
{
if(cur->left == NULL)
{
cur->left = creatANode();
}
cur = cur->left;
}
else
{
if(cur->right == NULL)
{
cur->right = creatANode();
}
cur = cur->right;
}
if(cur->weight != 0)
{
flag=0;
}
}
if(cur->left || cur->right)
{
flag=0;
}
cur->weight = mapp[ch];
res += cur->weight*code.size();
}
}
if(res != WPL)
{
flag=0;
}
return flag;
}
int main()
{
// system("chcp 65001");
cin.tie(0);
cout.tie(0);
// freopen("C:/Users/zhaochen/Desktop/input.txt", "r", stdin);
heap[0] = -1;
cin>>N;
for(int i=0; i<N; i++)
{
char ch;
int frequency;
cin>>ch>>frequency;
mapp[ch]=frequency;
Insert(frequency);
}
while(heapsize > 1)
{
int left = deleteMin();
int right = deleteMin();
Insert(left+right);
WPL += left+right;
}
int M;
cin>>M;
while(M--)
{
if(check())
{
if(M == 0)
cout<< "Yes";
else
cout<< "Yes"<< endl;
}
else
{
if(M == 0)
cout<< "No";
else
cout<< "No"<< endl;
}
}
return 0;
}