Add Java and C++ code for the section hash algorithm (krahets#560)

SUT-student · Jun 21, 2023 · 1b1af8d · 1b1af8d
1 parent 0e2ddba
commit 1b1af8d
Show file tree

Hide file tree

Showing 6 changed files with 256 additions and 11 deletions.
diff --git a/codes/cpp/chapter_hashing/built_in_hash.cpp b/codes/cpp/chapter_hashing/built_in_hash.cpp
@@ -0,0 +1,29 @@
+/**
+ * File: built_in_hash.cpp
+ * Created Time: 2023-06-21
+ * Author: Krahets ([email protected])
+ */
+
+#include "../utils/common.hpp"
+
+/* Driver Code */
+int main() {
+    int num = 3;
+    size_t hashNum = hash<int>()(num);
+    cout << "整数 " << num << " 的哈希值为 " << hashNum << "\n";
+
+    bool bol = true;
+    size_t hashBol = hash<bool>()(bol);
+    cout << "布尔量 " << bol << " 的哈希值为 " << hashBol << "\n";
+
+    double dec = 3.14159;
+    size_t hashDec = hash<double>()(dec);
+    cout << "小数 " << dec << " 的哈希值为 " << hashDec << "\n";
+
+    string str = "Hello 算法";
+    size_t hashStr = hash<string>()(str);
+    cout << "字符串 " << str << " 的哈希值为 " << hashStr << "\n";
+
+    // 在 C++ 中，内置 std:hash() 仅提供基本数据类型的哈希值计算
+    // 数组、对象的哈希值计算需要自行实现
+}
diff --git a/codes/cpp/chapter_hashing/simple_hash.cpp b/codes/cpp/chapter_hashing/simple_hash.cpp
@@ -0,0 +1,67 @@
+/**
+ * File: simple_hash.cpp
+ * Created Time: 2023-06-21
+ * Author: Krahets ([email protected])
+ */
+
+#include "../utils/common.hpp"
+
+/* 加法哈希 */
+int addHash(string key) {
+    long long hash = 0;
+    const int MODULUS = 1000000007;
+    for (unsigned char c : key) {
+        hash = (hash + (int)c) % MODULUS;
+    }
+    return (int)hash;
+}
+
+/* 乘法哈希 */
+int mulHash(string key) {
+    long long hash = 0;
+    const int MODULUS = 1000000007;
+    for (unsigned char c : key) {
+        hash = (31 * hash + (int)c) % MODULUS;
+    }
+    return (int)hash;
+}
+
+/* 异或哈希 */
+int xorHash(string key) {
+    int hash = 0;
+    const int MODULUS = 1000000007;
+    for (unsigned char c : key) {
+        cout<<(int)c<<endl;
+        hash ^= (int)c;
+    }
+    return hash & MODULUS;
+}
+
+/* 旋转哈希 */
+int rotHash(string key) {
+    long long hash = 0;
+    const int MODULUS = 1000000007;
+    for (unsigned char c : key) {
+        hash = ((hash << 4) ^ (hash >> 28) ^ (int)c) % MODULUS;
+    }
+    return (int)hash;
+}
+
+/* Driver Code */
+int main() {
+    string key = "Hello dsad3241241dsa算123法";
+
+    int hash = addHash(key);
+    cout << "加法哈希值为 " << hash << endl;
+
+    hash = mulHash(key);
+    cout << "乘法哈希值为 " << hash << endl;
+
+    hash = xorHash(key);
+    cout << "异或哈希值为 " << hash << endl;
+
+    hash = rotHash(key);
+    cout << "旋转哈希值为 " << hash << endl;
+
+    return 0;
+}
diff --git a/codes/java/chapter_hashing/built_in_hash.java b/codes/java/chapter_hashing/built_in_hash.java
@@ -0,0 +1,38 @@
+/**
+ * File: built_in_hash.java
+ * Created Time: 2023-06-21
+ * Author: Krahets ([email protected])
+ */
+
+package chapter_hashing;
+
+import utils.*;
+import java.util.*;
+
+public class built_in_hash {
+    public static void main(String[] args) {
+        int num = 3;
+        int hashNum = Integer.hashCode(num);
+        System.out.println("整数 " + num + " 的哈希值为 " + hashNum);
+
+        boolean bol = true;
+        int hashBol = Boolean.hashCode(bol);
+        System.out.println("布尔量 " + bol + " 的哈希值为 " + hashBol);
+
+        double dec = 3.14159;
+        int hashDec = Double.hashCode(dec);
+        System.out.println("小数 " + dec + " 的哈希值为 " + hashDec);
+
+        String str = "Hello 算法";
+        int hashStr = str.hashCode();
+        System.out.println("字符串 " + str + " 的哈希值为 " + hashStr);
+
+        Object[] arr = { 12836, "小哈" };
+        int hashTup = Arrays.hashCode(arr);
+        System.out.println("数组 " + Arrays.toString(arr) + " 的哈希值为 " + hashTup);
+
+        ListNode obj = new ListNode(0);
+        int hashObj = obj.hashCode();
+        System.out.println("节点对象 " + obj + " 的哈希值为 " + hashObj);
+    }
+}
diff --git a/codes/java/chapter_hashing/simple_hash.java b/codes/java/chapter_hashing/simple_hash.java
@@ -0,0 +1,66 @@
+/**
+ * File: simple_hash.java
+ * Created Time: 2023-06-21
+ * Author: Krahets ([email protected])
+ */
+
+package chapter_hashing;
+
+public class simple_hash {
+    /* 加法哈希 */
+    static int addHash(String key) {
+        long hash = 0;
+        final int MODULUS = 1000000007;
+        for (char c : key.toCharArray()) {
+            hash = (hash + (int) c) % MODULUS;
+        }
+        return (int) hash;
+    }
+
+    /* 乘法哈希 */
+    static int mulHash(String key) {
+        long hash = 0;
+        final int MODULUS = 1000000007;
+        for (char c : key.toCharArray()) {
+            hash = (31 * hash + (int) c) % MODULUS;
+        }
+        return (int) hash;
+    }
+
+    /* 异或哈希 */
+    static int xorHash(String key) {
+        int hash = 0;
+        final int MODULUS = 1000000007;
+        for (char c : key.toCharArray()) {
+            System.out.println((int)c);
+            hash ^= (int) c;
+        }
+        return hash & MODULUS;
+    }
+
+    /* 旋转哈希 */
+    static int rotHash(String key) {
+        long hash = 0;
+        final int MODULUS = 1000000007;
+        for (char c : key.toCharArray()) {
+            hash = ((hash << 4) ^ (hash >> 28) ^ (int) c) % MODULUS;
+        }
+        return (int) hash;
+    }
+
+    public static void main(String[] args) {
+        String key = "Hello 算法";
+
+        int hash = addHash(key);
+        System.out.println("加法哈希值为 " + hash);
+
+        hash = mulHash(key);
+        System.out.println("乘法哈希值为 " + hash);
+
+        hash = xorHash(key);
+        System.out.println("异或哈希值为 " + hash);
+
+        hash = rotHash(key);
+        System.out.println("旋转哈希值为 " + hash);
+    }
+}
diff --git a/codes/python/chapter_hashing/simple_hash.py b/codes/python/chapter_hashing/simple_hash.py
@@ -43,14 +43,16 @@ def rot_hash(key: str) -> int:
 
 """Driver Code"""
 if __name__ == "__main__":
-    hash = add_hash("Hello 算法")
+    key = "Hello 算法"
+
+    hash = add_hash(key)
     print(f"加法哈希值为 {hash}")
 
-    hash = mul_hash("Hello 算法")
+    hash = mul_hash(key)
     print(f"乘法哈希值为 {hash}")
 
-    hash = xor_hash("Hello 算法")
+    hash = xor_hash(key)
     print(f"异或哈希值为 {hash}")
 
-    hash = rot_hash("Hello 算法")
+    hash = rot_hash(key)
     print(f"旋转哈希值为 {hash}")
diff --git a/docs/chapter_hashing/hash_algorithm.md b/docs/chapter_hashing/hash_algorithm.md
@@ -211,13 +211,13 @@ $$
 
 直至目前，MD5 和 SHA-1 已多次被成功攻击，因此它们被各类安全应用弃用。SHA-2 系列中的 SHA-256 是最安全的哈希算法之一，仍未出现成功的攻击案例，因此常被用在各类安全应用与协议中。SHA-3 相较 SHA-2 的实现开销更低、计算效率更高，但目前使用覆盖度不如 SHA-2 系列。
 
-|          | MD5                            | SHA-1                | SHA-2                        | SHA-3                |
-| -------- | ------------------------------ | -------------------- | ---------------------------- | -------------------- |
-| 推出时间 | 1992                           | 1995                 | 2002                         | 2008                 |
-| 输出长度 | 128 bits                       | 160 bits             | 256 / 512 bits               | 224/256/384/512 bits |
-| 哈希冲突 | 较多                           | 较多                 | 很少                         | 很少                 |
-| 安全等级 | 低，已被成功攻击           | 低，已被成功攻击 | 高                           | 高                   |
-| 应用     | 已被弃用，仍用于数据完整性检查 | 已被弃用             | 加密货币交易验证、数字签名等 | 可用于替代 SHA-2     |
+|          | MD5                            | SHA-1            | SHA-2                        | SHA-3                |
+| -------- | ------------------------------ | ---------------- | ---------------------------- | -------------------- |
+| 推出时间 | 1992                           | 1995             | 2002                         | 2008                 |
+| 输出长度 | 128 bits                       | 160 bits         | 256 / 512 bits               | 224/256/384/512 bits |
+| 哈希冲突 | 较多                           | 较多             | 很少                         | 很少                 |
+| 安全等级 | 低，已被成功攻击               | 低，已被成功攻击 | 高                           | 高                   |
+| 应用     | 已被弃用，仍用于数据完整性检查 | 已被弃用         | 加密货币交易验证、数字签名等 | 可用于替代 SHA-2     |
 
 ## 数据结构的哈希值
 
@@ -228,16 +228,59 @@ $$
 - 元组的哈希值是对其中每一个元素进行哈希，然后将这些哈希值组合起来，得到单一的哈希值。
 - 对象的哈希值基于其内存地址生成。通过重写对象的哈希方法，可实现基于内容生成哈希值。
 
+!!! tip
+
+    请注意，不同编程语言的内置哈希值计算函数的定义和方法不同。
+
 === "Java"
 
     ```java title="built_in_hash.java"
+    int num = 3;
+    int hashNum = Integer.hashCode(num);
+    // 整数 3 的哈希值为 3
+
+    boolean bol = true;
+    int hashBol = Boolean.hashCode(bol);
+    // 布尔量 true 的哈希值为 1231
+
+    double dec = 3.14159;
+    int hashDec = Double.hashCode(dec);
+    // 小数 3.14159 的哈希值为 -1340954729
+
+    String str = "Hello 算法";
+    int hashStr = str.hashCode();
+    // 字符串 Hello 算法 的哈希值为 -727081396
 
+    Object[] arr = { 12836, "小哈" };
+    int hashTup = Arrays.hashCode(arr);
+    // 数组 [12836, 小哈] 的哈希值为 1151158
+
+    ListNode obj = new ListNode(0);
+    int hashObj = obj.hashCode();
+    // 节点对象 utils.ListNode@7dc5e7b4 的哈希值为 2110121908
     ```
 
 === "C++"
 
     ```cpp title="built_in_hash.cpp"
+    int num = 3;
+    size_t hashNum = hash<int>()(num);
+    // 整数 3 的哈希值为 3
+
+    bool bol = true;
+    size_t hashBol = hash<bool>()(bol);
+    // 布尔量 1 的哈希值为 1
+
+    double dec = 3.14159;
+    size_t hashDec = hash<double>()(dec);
+    // 小数 3.14159 的哈希值为 4614256650576692846
+
+    string str = "Hello 算法";
+    size_t hashStr = hash<string>()(str);
+    // 字符串 Hello 算法 的哈希值为 15466937326284535026
 
+    // 在 C++ 中，内置 std:hash() 仅提供基本数据类型的哈希值计算
+    // 数组、对象的哈希值计算需要自行实现
     ```
 
 === "Python"