Base64编解码C代码GCC正常cl.exe异常的原因及编译器差异

问题描述 #

使用以下C语言实现的Base64编解码代码测试时，GCC编译的程序运行正常：编码结果为MTIzNDU2，解码输出123456，长度为6；但cl.exe编译的程序解码异常，输出为123456?，长度为7。

/**
 * Copyright (c) 2006-2018 Apple Inc. All rights reserved.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 **/

#include "base64.h"

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

 // base64 tables
static const char basis_64[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static const signed char index_64[128] = {
    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62,
    -1, -1, -1, 63, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, -1, 0,
    1,  2,  3,  4,  5,  6,  7,  8,  9,  10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22,
    23, 24, 25, -1, -1, -1, -1, -1, -1, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
    39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, -1, -1, -1, -1, -1 };
#define CHAR64(c) (((c) < 0 || (c) > 127) ? -1 : index_64[(c)])

// base64_encode    :    base64 encode
//
// value            :    data to encode
// vlen             :    length of data
// (result)         :    new char[] - c-str of result
char* base64_encode(const unsigned char* value, size_t vlen) {
    char* result = (char*)malloc((vlen * 4) / 3 + 5);
    if (result == NULL) {
        return NULL;
    }
    char* out = result;
    while (vlen >= 3) {
        *out++ = basis_64[value[0] >> 2];
        *out++ = basis_64[((value[0] << 4) & 0x30) | (value[1] >> 4)];
        *out++ = basis_64[((value[1] << 2) & 0x3C) | (value[2] >> 6)];
        *out++ = basis_64[value[2] & 0x3F];
        value += 3;
        vlen -= 3;
    }
    if (vlen > 0) {
        *out++ = basis_64[value[0] >> 2];
        unsigned char oval = (value[0] << 4) & 0x30;
        if (vlen > 1)
            oval |= value[1] >> 4;
        *out++ = basis_64[oval];
        *out++ = (vlen < 2) ? '=' : basis_64[(value[1] << 2) & 0x3C];
        *out++ = '=';
    }
    *out = '\0';

    return result;
}

// base64_decode    :    base64 decode
//
// value            :    c-str to decode
// rlen             :    length of decoded result
// (result)         :    new unsigned char[] - decoded result
unsigned char* base64_decode(const char* value, size_t* rlen) {
    *rlen = 0;
    int c1, c2, c3, c4;

    size_t vlen = strlen(value);
    unsigned char* result = (unsigned char*)malloc((vlen * 3) / 4 + 1);
    if (result == NULL) {
        return NULL;
    }
    unsigned char* out = result;

    while (1) {
        if (value[0] == 0) {
            //*out = '\0';
            return result;
        }
        c1 = value[0];
        if (CHAR64(c1) == -1) {
            goto base64_decode_error;
            ;
        }
        c2 = value[1];
        if (CHAR64(c2) == -1) {
            goto base64_decode_error;
            ;
        }
        c3 = value[2];
        if ((c3 != '=') && (CHAR64(c3) == -1)) {
            goto base64_decode_error;
            ;
        }
        c4 = value[3];
        if ((c4 != '=') && (CHAR64(c4) == -1)) {
            goto base64_decode_error;
            ;
        }

        value += 4;
        *out++ = (CHAR64(c1) << 2) | (CHAR64(c2) >> 4);
        *rlen += 1;

        if (c3 != '=') {
            *out++ = ((CHAR64(c2) << 4) & 0xf0) | (CHAR64(c3) >> 2);
            *rlen += 1;

            if (c4 != '=') {
                *out++ = ((CHAR64(c3) << 6) & 0xc0) | CHAR64(c4);
                *rlen += 1;
            }
        }
    }

base64_decode_error:
    *result = 0;
    *rlen = 0;

    return result;
}
// Below is my test.
int main() {
    char str[] = "123456";
    char* encoded = base64_encode(str, strlen(str));
    printf("encode : %s\n", encoded);
    int rlen = 3;
    char* decoded = base64_decode(encoded, &rlen);
    printf("decode : %s\n", decoded);
    printf("len: %d\n", strlen(decoded));
    return 0;
}

问题原因与编译器差异 #

• 核心问题：解码结果未添加字符串终止符
  base64_decode函数中，解码完成返回结果时，没有在解码后的字节数组末尾添加'\0'终止符。strlen和printf都依赖这个终止符来确定字符串的结束位置。
• GCC与cl.exe的行为差异
  • GCC默认会对malloc分配的内存进行初始化（通常填充为0），所以解码后的数组末尾恰好存在一个'\0'，strlen和printf能正常工作。
  • cl.exe（MSVC编译器）默认不会初始化malloc分配的内存，内存中保留随机垃圾值。解码完成后数组末尾无'\0'，strlen会持续读取直到遇到内存中的第一个0字节，导致输出包含额外垃圾字符，长度计算也出现错误。

修复方案 #

在base64_decode函数的返回语句前添加终止符：

if (value[0] == 0) {
    *out = '\0'; // 取消注释该行或手动添加
    return result;
}

或者根据*rlen的值手动添加：

result[*rlen] = '\0';

内容的提问来源于stack exchange，提问作者Zmz