无法找到霍夫曼编码分段错误的原因,无法在c中进行熵编解码

fivyi3re  于 2023-01-29  发布在  其他
关注(0)|答案(2)|浏览(95)

我一直在看用c语言进行霍夫曼编码的熵编码和解码的代码,我似乎找不到为什么我总是得到分割错误的原因。

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

const int MAX_TREE_HT = 100;

struct MinHeapNode {
    char data;
    unsigned freq;
    struct MinHeapNode* left, * right;
};

struct MinHeap {
    unsigned size;
    unsigned capacity;
    struct MinHeapNode** array;
};

struct MinHeapNode* newNode(char data, unsigned freq) {
    struct MinHeapNode* temp = (struct MinHeapNode*)malloc(sizeof(struct MinHeapNode));
    temp->left = temp->right = NULL;
    temp->data = data;
    temp->freq = freq;
    return temp;
}

struct MinHeap* createMinHeap(unsigned capacity) {
    struct MinHeap* minHeap = (struct MinHeap*)malloc(sizeof(struct MinHeap));
    minHeap->size = 0;
    minHeap->capacity = capacity;
    minHeap->array = (struct MinHeapNode**)malloc(minHeap->capacity * sizeof(struct MinHeapNode*));
    return minHeap;
}

void swapMinHeapNode(struct MinHeapNode** a, struct MinHeapNode** b) {
    struct MinHeapNode* t = *a;
    *a = *b;
    *b = t;
}

void minHeapify(struct MinHeap* minHeap, int idx) {
    int smallest = idx;
    int left = 2 * idx + 1;
    int right = 2 * idx + 2;

    if (left < minHeap->size && minHeap->array[left]->freq < minHeap->array[smallest]->freq)
        smallest = left;

    if (right < minHeap->size && minHeap->array[right]->freq < minHeap->array[smallest]->freq)
        smallest = right;

    if (smallest != idx) {
        swapMinHeapNode(&minHeap->array[smallest], &minHeap->array[idx]);
        minHeapify(minHeap, smallest);
    }
}

int isSizeOne(struct MinHeap* minHeap) {
    return (minHeap->size == 1);
}

struct MinHeapNode* extractMin(struct MinHeap* minHeap) {
    struct MinHeapNode* temp = minHeap->array[0];
    minHeap->array[0] = minHeap->array[minHeap->size - 1];
    --minHeap->size;
    minHeapify(minHeap, 0);
    return temp;
}

void insertMinHeap(struct MinHeap* minHeap, struct MinHeapNode* minHeapNode) {
    ++minHeap->size;
    int i = minHeap->size - 1;
    minHeap->array[i] = minHeapNode;
    while (i && minHeap->array[i]->freq < minHeap->array[(i - 1) / 2]->freq) {
        swapMinHeapNode(&minHeap->array[i], &minHeap->array[(i - 1) / 2]);
        i = (i - 1) / 2;
    }
}

void buildMinHeap(struct MinHeap* minHeap) {
    int n = minHeap->size - 1;
    int i;
    for (i = (n - 1) / 2; i >= 0; --i)
        minHeapify(minHeap, i);
}

void printArr(int arr[], int n) {
    int i;
    for (i = 0; i < n; ++i)
        printf("%d", arr[i]);
    printf("\n");
}

int isLeaf(struct MinHeapNode* root) {
    return !(root->left) && !(root->right);
}

struct MinHeap* createAndBuildMinHeap(char data[], int freq[], int size) {
    struct MinHeap* minHeap = createMinHeap(size);
    int i;
    for (i = 0; i < size; ++i)
        minHeap->array[i] = newNode(data[i], freq[i]);
    minHeap->size = size;
    buildMinHeap(minHeap);
    return minHeap;
}

struct MinHeapNode* buildHuffmanTree(char data[], int freq[], int size) {
    struct MinHeapNode *left, *right, *top;
    struct MinHeap* minHeap = createAndBuildMinHeap(data, freq, size);
    while (!isSizeOne(minHeap)) {
        left = extractMin(minHeap);
        right = extractMin(minHeap);
        top = newNode('$', left->freq + right->freq);
        top->left = left;
        top->right = right;
        insertMinHeap(minHeap, top);
    }
    return extractMin(minHeap);
}

void printCodes(struct MinHeapNode* root, int arr[], int top) {
    if (root->left) {
        arr[top] = 0;
        printCodes(root->left, arr, top + 1);
    }
    if (root->right) {
        arr[top] = 1;
        printCodes(root->right, arr, top + 1);
    }
    if (isLeaf(root)) {
        printf("%c: ", root->data);
        printArr(arr, top);
    }
}

void HuffmanCodes(char data[], int freq[], int size) {
    struct MinHeapNode* root = buildHuffmanTree(data, freq, size);
    int arr[MAX_TREE_HT], top = 0;
    printCodes(root, arr, top);
}

void encode(char* str, char* encoded_str, struct MinHeapNode* root) {
    if (root == NULL)
        return;
    if (isLeaf(root)) {
        while (*str != root->data)
            str++;
        while (*str == root->data) {
            *encoded_str = '1';
            encoded_str++;
            str++;
        }
        return encode(str, encoded_str, root);
    }
    if (*str == root->data) {
        *encoded_str = '0';
        encoded_str++;

        encode(str + 1, encoded_str, root->left);
    } else {
        encode(str, encoded_str, root->right);
    }
}

void decode(char* encoded_str, struct MinHeapNode* root, char* decoded_str) {
    struct MinHeapNode* curr = root;
    while (*encoded_str) {
        if (*encoded_str == '0')
            curr = curr->left;
        else
            curr = curr->right;
        if (isLeaf(curr)) {
            *decoded_str = curr->data;
            decoded_str++;
            curr = root;
        }
        encoded_str++;
    }
}

int main() {
    char str[] = "this is a test";
    int freq[256] = { 0 };
    int size = 0, i;
    for (i = 0; str[i]; i++) {
        freq[str[i]]++;
        size++;
    }
    int unique = 0;
    char data[size];
    for (i = 0; i < 256; i++) {
        if (freq[i]) {
            data[unique] = (char)i;
            unique++;
        }
    }
    HuffmanCodes(data, freq, unique);
    char encoded_str[100], decoded_str[100];
    struct MinHeapNode* root = buildHuffmanTree(data, freq, unique);
    encode(str, encoded_str, root);
    printf("Encoded string: %s\n", encoded_str);
    decode(encoded_str, root, decoded_str);
    printf("Decoded string: %s\n", decoded_str);
    return 0;
}

经过几次逐节注解的尝试和错误,我们发现它是在编码函数内部的某个地方引起的。这不是我自己写的代码,是用一些在线参考编写的。输出应该是下面的。

: 00
a: 010
e: 011
h: 100
i: 1010
s: 1011
t: 110
Encoded string: 0101110101011101110111111001101
Decoded string: this is a test

相反,我得到了以下内容。

a: 0
e: 10
h: 110
i: 1110
s: 11110
 : 111110
t: 111111
zsh: segmentation fault

先谢谢你的帮助。

np8igboo

np8igboo1#

void encode(char* str, char* encoded_str, struct MinHeapNode* root) {
if (root == NULL)
    return;
if (isLeaf(root)) {
    while (*str != root->data)
    {
        printf("str[]=%c", *str); // Here you can see that you have an overflow *******
        str++;
    }
    while (*str == root->data) {
        *encoded_str = '1';
        encoded_str++;
        str++;
    }
    return encode(str, encoded_str, root);
}
if (*str == root->data) {
    *encoded_str = '0';
    encoded_str++;

    encode(str + 1, encoded_str, root->left);
} else {
    encode(str, encoded_str, root->right);
}

}
只需在while循环中添加一个条件,以确保字符串不会溢出:

while (*str  && *str != root->data) // HERE and in all other loops
{
    str++;
}

但是!首先你需要解决的事实是:字符编码字符串[100]、解码字符串[100];都是空的并且以非空结尾,所以你可以在一个循环中遍历它们:

encoded_str[end_index] = '\0';
while (*str ....) // it will stop at the '/0' in case you dont find *str == root->data.

你的编码函数的问题是你永远不会走出递归。希望这对你有帮助:)。

gr8qqesn

gr8qqesn2#

忘记错误。你的代码都错了。先让它工作起来。(注解掉HuffmanCodes()后面的main()中的内容。)
问题是你所有的频率都是零!为什么?因为你用相同的索引来索引两个完全不同的东西,期望它们是相关的。data[i]是字符串中出现的第i个唯一字符。另一方面,freq[i]是 * 字符 * i的频率。然后你拉取前七个字节值的频率,0..6,它们都是零。
从那以后一切都完了。所以先把它修好。
反正你不需要data[]unique,只要用freq[]调用buildHuffmanTree(),遍历所有freq[]一次,然后直接构建堆的初始元素,每个元素都是freq[i] != 0,那么字符就是i,频率就是freq[i]
其他意见:
1.您没有检查malloc()故障。
1.没有free() s!
1.你两次构建同一棵哈夫曼树。为什么?
1.为什么MAX_TREE_HT是100,以及编码和解码字符串的大小?
1.正如注解中所指出的,您的freq[str[i]]++;需要是freq[str[i] & 0xff]++;char是带符号的,因此您将尝试在没有& 0xff的情况下访问freq中大于127的字节的负索引元素。
1.您的encode()函数没有任何意义。请删除它并重新开始。(您的decode()函数看起来很好。)提示:遍历哈夫曼树建立一个代码表,然后用它来编码。
1.你的"应该是"输出是错误的。忽略它,不管它是你想出的或找到的。

相关问题