c语言 对排序输入进行高效霍夫曼编码 | 贪婪算法（Efficient Huffman Coding for Sorted Input | Greedy Algo）

 排序输入的高效霍夫曼编码 示例图

建议先阅读下面的文章：

 c语言：c语言 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）_霍夫曼的贪婪c语言-CSDN博客

c++：c++ 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）_霍夫曼的贪婪算法设计核心代码-CSDN博客

c#：C# 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）-CSDN博客

c++ STL：c++ STL 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）-CSDN博客

java：java 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）-CSDN博客

python：python 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）-CSDN博客

javascript：JavaScript 霍夫曼编码 | 贪婪算法（Huffman Coding | Greedy Algo）-CSDN博客

        上面讨论的算法的时间复杂度是 O(nLogn)。如果我们知道给定的数组是排好序的（按频率非递减顺序），我们可以在 O(n) 时间内生成霍夫曼码。以下是针对已排序输入的 O(n) 算法。

1.创建两个空队列。

2.为每个唯一字符创建一个叶节点，并按频率非递减顺序将其入队到第一个队列。最初第二个队列是空的。

3.通过检查两个队列的前面，使两个频率最小的节点出队。重复以下步骤两次 
        1. 如果第二个队列为空，则从第一个队列出队。

2. 如果第一个队列为空，则从第二个队列出队。 
        3. 否则，比较两个队列的前面，并使最小的节点出队。 
        4.创建一个新的内部节点，其频率等于两个节点频率之和。将第一个出队节点设为其左子节点，将第二个出队节点设为右子节点。将此节点入队到第二个队列。
5.重复步骤 3 和 4，直到队列中有多个节点。剩下的节点就是根节点，树就完成了。 

示例代码： 

// C Program for Efficient Huffman Coding for Sorted input
#include <stdio.h>
#include <stdlib.h>
 
// This constant can be avoided by explicitly calculating
// height of Huffman Tree
#define MAX_TREE_HT 100
 
// A node of huffman tree
struct QueueNode {
    char data;
    unsigned freq;
    struct QueueNode *left, *right;
};
 
// Structure for Queue: collection of Huffman Tree nodes (or
// QueueNodes)
struct Queue {
    int front, rear;
    int capacity;
    struct QueueNode** array;
};
 
// A utility function to create a new Queuenode
struct QueueNode* newNode(char data, unsigned freq)
{
    struct QueueNode* temp = (struct QueueNode*)malloc(
        sizeof(struct QueueNode));
    temp->left = temp->right = NULL;
    temp->data = data;
    temp->freq = freq;
    return temp;
}
 
// A utility function to create a Queue of given capacity
struct Queue* createQueue(int capacity)
{
    struct Queue* queue
        = (struct Queue*)malloc(sizeof(struct Queue));
    queue->front = queue->rear = -1;
    queue->capacity = capacity;
    queue->array = (struct QueueNode**)malloc(
        queue->capacity * sizeof(struct QueueNode*));
    return queue;
}
 
// A utility function to check if size of given queue is 1
int isSizeOne(struct Queue* queue)
{
    return queue->front == queue->rear
           && queue->front != -1;
}
 
// A utility function to check if given queue is empty
int isEmpty(struct Queue* queue)
{
    return queue->front == -1;
}
 
// A utility function to check if given queue is full
int isFull(struct Queue* queue)
{
    return queue->rear == queue->capacity - 1;
}
 
// A utility function to add an item to queue
void enQueue(struct Queue* queue, struct QueueNode* item)
{
    if (isFull(queue))
        return;
    queue->array[++queue->rear] = item;
    if (queue->front == -1)
        ++queue->front;
}
 
// A utility function to remove an item from queue
struct QueueNode* deQueue(struct Queue* queue)
{
    if (isEmpty(queue))
        return NULL;
    struct QueueNode* temp = queue->array[queue->front];
    if (queue->front
        == queue
               ->rear) // If there is only one item in queue
        queue->front = queue->rear = -1;
    else
        ++queue->front;
    return temp;
}
 
// A utility function to get form of queue
struct QueueNode* getFront(struct Queue* queue)
{
    if (isEmpty(queue))
        return NULL;
    return queue->array[queue->front];
}
 
/* A function to get minimum item from two queues */
struct QueueNode* findMin(struct Queue* firstQueue,
                          struct Queue* secondQueue)
{
    // Step 3.a: If first queue is empty, dequeue from
    // second queue
    if (isEmpty(firstQueue))
        return deQueue(secondQueue);
 
    // Step 3.b: If second queue is empty, dequeue from
    // first queue
    if (isEmpty(secondQueue))
        return deQueue(firstQueue);
 
    // Step 3.c:  Else, compare the front of two queues and
    // dequeue minimum
    if (getFront(firstQueue)->freq
        < getFront(secondQueue)->freq)
        return deQueue(firstQueue);
 
    return deQueue(secondQueue);
}
 
// Utility function to check if this node is leaf
int isLeaf(struct QueueNode* root)
{
    return !(root->left) && !(root->right);
}
 
// A utility function to print an array of size n
void printArr(int arr[], int n)
{
    int i;
    for (i = 0; i < n; ++i)
        printf("%d", arr[i]);
    printf("\n");
}
 
// The main function that builds Huffman tree
struct QueueNode* buildHuffmanTree(char data[], int freq[],
                                   int size)
{
    struct QueueNode *left, *right, *top;
 
    // Step 1: Create two empty queues
    struct Queue* firstQueue = createQueue(size);
    struct Queue* secondQueue = createQueue(size);
 
    // Step 2:Create a leaf node for each unique character
    // and Enqueue it to the first queue in non-decreasing
    // order of frequency. Initially second queue is empty
    for (int i = 0; i < size; ++i)
        enQueue(firstQueue, newNode(data[i], freq[i]));
 
    // Run while Queues contain more than one node. Finally,
    // first queue will be empty and second queue will
    // contain only one node
    while (
        !(isEmpty(firstQueue) && isSizeOne(secondQueue))) {
        // Step 3: Dequeue two nodes with the minimum
        // frequency by examining the front of both queues
        left = findMin(firstQueue, secondQueue);
        right = findMin(firstQueue, secondQueue);
 
        // Step 4: Create a new internal node with frequency
        // equal to the sum of the two nodes frequencies.
        // Enqueue this node to second queue.
        top = newNode('$', left->freq + right->freq);
        top->left = left;
        top->right = right;
        enQueue(secondQueue, top);
    }
 
    return deQueue(secondQueue);
}
 
// Prints huffman codes from the root of Huffman Tree.  It
// uses arr[] to store codes
void printCodes(struct QueueNode* root, int arr[], int top)
{
    // Assign 0 to left edge and recur
    if (root->left) {
        arr[top] = 0;
        printCodes(root->left, arr, top + 1);
    }
 
    // Assign 1 to right edge and recur
    if (root->right) {
        arr[top] = 1;
        printCodes(root->right, arr, top + 1);
    }
 
    // If this is a leaf node, then it contains one of the
    // input characters, print the character and its code
    // from arr[]
    if (isLeaf(root)) {
        printf("%c: ", root->data);
        printArr(arr, top);
    }
}
 
// The main function that builds a Huffman Tree and print
// codes by traversing the built Huffman Tree
void HuffmanCodes(char data[], int freq[], int size)
{
    //  Construct Huffman Tree
    struct QueueNode* root
        = buildHuffmanTree(data, freq, size);
 
    // Print Huffman codes using the Huffman tree built
    // above
    int arr[MAX_TREE_HT], top = 0;
    printCodes(root, arr, top);
}
 
// Driver program to test above functions
int main()
{
    char arr[] = { 'a', 'b', 'c', 'd', 'e', 'f' };
    int freq[] = { 5, 9, 12, 13, 16, 45 };
    int size = sizeof(arr) / sizeof(arr[0]);
    HuffmanCodes(arr, freq, size);
    return 0;
} 

输出： 

f: 0 
c: 100 
d: 101 
a: 1100 
b: 1101 
e: 111

时间复杂度： O(n)
        如果输入未排序，则需要先对其进行排序，然后才能通过上述算法进行处理。排序可以使用堆排序或合并排序来完成，两者都在 Theta(nlogn) 中运行。因此，对于未排序的输入，总体时间复杂度变为 O(nlogn)。 
辅助空间： O(n)