西北工业大学计算机大作业——压缩算法

既然发了几篇课题b的，那也发几篇课题a的吧！

压缩算法通常用于减小数据文件的体积，其中两种常见的压缩算法是 Huffman 编码和Lempel-Ziv 算法。下面分别给出这两种算法的简单实现（使用 C++ 语言）：

Huffman 编码

#include <iostream>
#include <queue>
#include <unordered_map>
#include <vector>
#include <string>
using namespace std;

struct TreeNode {
    char data;
    int frequency;
    TreeNode* left;
    TreeNode* right;

    TreeNode(char d, int f) : data(d), frequency(f), left(nullptr), right(nullptr) {}
};

struct Compare {
    bool operator()(TreeNode* a, TreeNode* b) {
        return a->frequency > b->frequency;
    }
};

unordered_map<char, string> huffmanCodes;

void generateHuffmanCodes(TreeNode* root, string code) {
    if (root->left == nullptr && root->right == nullptr) {
        huffmanCodes[root->data] = code;
        return;
    }

    if (root->left != nullptr) {
        generateHuffmanCodes(root->left, code + "0");
    }

    if (root->right != nullptr) {
        generateHuffmanCodes(root->right, code + "1");
    }
}

void buildHuffmanTree(string text) {
    unordered_map<char, int> frequencyMap;
    for (char c : text) {
        frequencyMap[c]++;
    }

    priority_queue<TreeNode*, vector<TreeNode*>, Compare> pq;
    for (auto& entry : frequencyMap) {
        pq.push(new TreeNode(entry.first, entry.second));
    }

    while (pq.size() > 1) {
        TreeNode* left = pq.top();
        pq.pop();
        TreeNode* right = pq.top();
        pq.pop();

        TreeNode* internalNode = new TreeNode('$', left->frequency + right->frequency);
        internalNode->left = left;
        internalNode->right = right;

        pq.push(internalNode);
    }

    generateHuffmanCodes(pq.top(), "");
}

string compressHuffman(string text) {
    buildHuffmanTree(text);

    string compressedText = "";
    for (char c : text) {
        compressedText += huffmanCodes[c];
    }

    return compressedText;
}

int main() {
    string text = "abracadabra";
    string compressedText = compressHuffman(text);

    cout << "Original text: " << text << endl;
    cout << "Compressed text: " << compressedText << endl;

    return 0;
}

Lempel-Ziv 算法

#include <iostream>
#include <unordered_map>
#include <vector>
using namespace std;

string compressLZ(string text) {
    unordered_map<string, int> dictionary;
    vector<string> result;
    string current = "";

    for (char c : text) {
        string currentPlusC = current + c;
        if (dictionary.find(currentPlusC) != dictionary.end()) {
            current = currentPlusC;
        } else {
            result.push_back(to_string(dictionary[current]));
            dictionary[currentPlusC] = dictionary.size();
            current = c;
        }
    }

    result.push_back(to_string(dictionary[current]));

    string compressedText = "";
    for (string code : result) {
        compressedText += code + " ";
    }

    return compressedText;
}

int main() {
    string text = "ababababcabcabc";
    string compressedText = compressLZ(text);

    cout << "Original text: " << text << endl;
    cout << "Compressed text: " << compressedText << endl;

    return 0;
}

这两个示例只是非常非常基础的实现，实际的压缩算法要复杂得多。在实际应用中，常常使用专业的库（如 zlib）或者其他高效的实现。