我有一个unsigned char变量中存储的二进制数据。 我需要将它们转换为C语言中的PEM base64格式。 我查阅了openssl库,但没有找到任何函数。 请问有人有什么想法吗?
#include <stdint.h>
#include <stdlib.h>
static char encoding_table[] = {'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H',
'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P',
'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',
'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f',
'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
'o', 'p', 'q', 'r', 's', 't', 'u', 'v',
'w', 'x', 'y', 'z', '0', '1', '2', '3',
'4', '5', '6', '7', '8', '9', '+', '/'};
static char *decoding_table = NULL;
static int mod_table[] = {0, 2, 1};
char *base64_encode(const unsigned char *data,
size_t input_length,
size_t *output_length) {
*output_length = 4 * ((input_length + 2) / 3);
char *encoded_data = malloc(*output_length);
if (encoded_data == NULL) return NULL;
for (int i = 0, j = 0; i < input_length;) {
uint32_t octet_a = i < input_length ? (unsigned char)data[i++] : 0;
uint32_t octet_b = i < input_length ? (unsigned char)data[i++] : 0;
uint32_t octet_c = i < input_length ? (unsigned char)data[i++] : 0;
uint32_t triple = (octet_a << 0x10) + (octet_b << 0x08) + octet_c;
encoded_data[j++] = encoding_table[(triple >> 3 * 6) & 0x3F];
encoded_data[j++] = encoding_table[(triple >> 2 * 6) & 0x3F];
encoded_data[j++] = encoding_table[(triple >> 1 * 6) & 0x3F];
encoded_data[j++] = encoding_table[(triple >> 0 * 6) & 0x3F];
}
for (int i = 0; i < mod_table[input_length % 3]; i++)
encoded_data[*output_length - 1 - i] = '=';
return encoded_data;
}
unsigned char *base64_decode(const char *data,
size_t input_length,
size_t *output_length) {
if (decoding_table == NULL) build_decoding_table();
if (input_length % 4 != 0) return NULL;
*output_length = input_length / 4 * 3;
if (data[input_length - 1] == '=') (*output_length)--;
if (data[input_length - 2] == '=') (*output_length)--;
unsigned char *decoded_data = malloc(*output_length);
if (decoded_data == NULL) return NULL;
for (int i = 0, j = 0; i < input_length;) {
uint32_t sextet_a = data[i] == '=' ? 0 & i++ : decoding_table[data[i++]];
uint32_t sextet_b = data[i] == '=' ? 0 & i++ : decoding_table[data[i++]];
uint32_t sextet_c = data[i] == '=' ? 0 & i++ : decoding_table[data[i++]];
uint32_t sextet_d = data[i] == '=' ? 0 & i++ : decoding_table[data[i++]];
uint32_t triple = (sextet_a << 3 * 6)
+ (sextet_b << 2 * 6)
+ (sextet_c << 1 * 6)
+ (sextet_d << 0 * 6);
if (j < *output_length) decoded_data[j++] = (triple >> 2 * 8) & 0xFF;
if (j < *output_length) decoded_data[j++] = (triple >> 1 * 8) & 0xFF;
if (j < *output_length) decoded_data[j++] = (triple >> 0 * 8) & 0xFF;
}
return decoded_data;
}
void build_decoding_table() {
decoding_table = malloc(256);
for (int i = 0; i < 64; i++)
decoding_table[(unsigned char) encoding_table[i]] = i;
}
void base64_cleanup() {
free(decoding_table);
}
请注意,这种方法在解码时不进行任何错误检查——非base64编码的数据也会被处理。
*output_length = ((input_length - 1) / 3) * 4 + 4;
可以跳过libm和math.h的依赖,也不需要使用浮点数运算(在某些硬件上速度较慢)。请注意,这句话的意思是输出长度可以根据输入长度计算出来。 - Fabian Henzebuild_decoding_table
中存在数组越界问题。encoding_table[64]
到 encoding_table[255]
不存在。 - bobobobo我知道这个问题很古老,但是由于提供的解决方案数量众多,并且每个解决方案都声称自己更快、更好,所以我感到困惑。我在github上创建了一个项目来比较base64编码器和解码器:https://github.com/gaspardpetit/base64/
目前为止,我并没有局限于C算法——如果一个实现在C++中表现良好,它很容易被移植到C中。此外,测试是使用Visual Studio 2015进行的。如果有人想要用clang/gcc更新这个答案的结果,请随意参与。
最快的编码器: 我发现的两个最快的编码器实现分别是Jouni Malinen的http://web.mit.edu/freebsd/head/contrib/wpa/src/utils/base64.c和Apache的https://opensource.apple.com/source/QuickTimeStreamingServer/QuickTimeStreamingServer-452/CommonUtilitiesLib/base64.c。
以下是我目前测试过的不同算法对32K数据进行编码所需的时间(以微秒为单位):
jounimalinen 25.1544
apache 25.5309
NibbleAndAHalf 38.4165
internetsoftwareconsortium 48.2879
polfosol 48.7955
wikibooks_org_c 51.9659
gnome 74.8188
elegantdice 118.899
libb64 120.601
manuelmartinez 120.801
arduino 126.262
daedalusalpha 126.473
CppCodec 151.866
wikibooks_org_cpp 343.2
adp_gmbh 381.523
LihO 406.693
libcurl 3246.39
user152949 4828.21
(René Nyffenegger的解决方案,另一个回答已经给出了他的名字,这里列出作为adp_gmbh)。
这是Jouni Malinen的一个解决方案,我稍微修改了一下以返回一个std::string:
/*
* Base64 encoding/decoding (RFC1341)
* Copyright (c) 2005-2011, Jouni Malinen <j@w1.fi>
*
* This software may be distributed under the terms of the BSD license.
* See README for more details.
*/
// 2016-12-12 - Gaspard Petit : Slightly modified to return a std::string
// instead of a buffer allocated with malloc.
#include <string>
static const unsigned char base64_table[65] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
/**
* base64_encode - Base64 encode
* @src: Data to be encoded
* @len: Length of the data to be encoded
* @out_len: Pointer to output length variable, or %NULL if not used
* Returns: Allocated buffer of out_len bytes of encoded data,
* or empty string on failure
*/
std::string base64_encode(const unsigned char *src, size_t len)
{
unsigned char *out, *pos;
const unsigned char *end, *in;
size_t olen;
olen = 4*((len + 2) / 3); /* 3-byte blocks to 4-byte */
if (olen < len)
return std::string(); /* integer overflow */
std::string outStr;
outStr.resize(olen);
out = (unsigned char*)&outStr[0];
end = src + len;
in = src;
pos = out;
while (end - in >= 3) {
*pos++ = base64_table[in[0] >> 2];
*pos++ = base64_table[((in[0] & 0x03) << 4) | (in[1] >> 4)];
*pos++ = base64_table[((in[1] & 0x0f) << 2) | (in[2] >> 6)];
*pos++ = base64_table[in[2] & 0x3f];
in += 3;
}
if (end - in) {
*pos++ = base64_table[in[0] >> 2];
if (end - in == 1) {
*pos++ = base64_table[(in[0] & 0x03) << 4];
*pos++ = '=';
}
else {
*pos++ = base64_table[((in[0] & 0x03) << 4) |
(in[1] >> 4)];
*pos++ = base64_table[(in[1] & 0x0f) << 2];
}
*pos++ = '=';
}
return outStr;
}
最快的解码器:以下是解码结果,我必须承认我有点惊讶:
polfosol 45.2335
wikibooks_org_c 74.7347
apache 77.1438
libb64 100.332
gnome 114.511
manuelmartinez 126.579
elegantdice 138.514
daedalusalpha 151.561
jounimalinen 206.163
arduino 335.95
wikibooks_org_cpp 350.437
CppCodec 526.187
internetsoftwareconsortium 862.833
libcurl 1280.27
LihO 1852.4
adp_gmbh 1934.43
user152949 5332.87
Polfosol从base64解码c++代码段中摘取的片段是快速的,大约比其他代码块快了将近两倍。
为了完整起见,这里附上代码:
static const int B64index[256] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 62, 63, 62, 62, 63, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 0, 0, 0, 0, 0, 0, 0, 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, 0,
0, 0, 0, 63, 0, 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 };
std::string b64decode(const void* data, const size_t len)
{
unsigned char* p = (unsigned char*)data;
int pad = len > 0 && (len % 4 || p[len - 1] == '=');
const size_t L = ((len + 3) / 4 - pad) * 4;
std::string str(L / 4 * 3 + pad, '\0');
for (size_t i = 0, j = 0; i < L; i += 4)
{
int n = B64index[p[i]] << 18 | B64index[p[i + 1]] << 12 | B64index[p[i + 2]] << 6 | B64index[p[i + 3]];
str[j++] = n >> 16;
str[j++] = n >> 8 & 0xFF;
str[j++] = n & 0xFF;
}
if (pad)
{
int n = B64index[p[L]] << 18 | B64index[p[L + 1]] << 12;
str[str.size() - 1] = n >> 16;
if (len > L + 2 && p[L + 2] != '=')
{
n |= B64index[p[L + 2]] << 6;
str.push_back(n >> 8 & 0xFF);
}
}
return str;
}
你也可以使用openssl执行此操作(openssl enc
命令可以实现...),查看BIO_f_base64()
函数。
这是我使用OpenSSL的解决方案。
/* A BASE-64 ENCODER AND DECODER USING OPENSSL */
#include <openssl/pem.h>
#include <string.h> //Only needed for strlen().
char *base64encode (const void *b64_encode_this, int encode_this_many_bytes){
BIO *b64_bio, *mem_bio; //Declares two OpenSSL BIOs: a base64 filter and a memory BIO.
BUF_MEM *mem_bio_mem_ptr; //Pointer to a "memory BIO" structure holding our base64 data.
b64_bio = BIO_new(BIO_f_base64()); //Initialize our base64 filter BIO.
mem_bio = BIO_new(BIO_s_mem()); //Initialize our memory sink BIO.
BIO_push(b64_bio, mem_bio); //Link the BIOs by creating a filter-sink BIO chain.
BIO_set_flags(b64_bio, BIO_FLAGS_BASE64_NO_NL); //No newlines every 64 characters or less.
BIO_write(b64_bio, b64_encode_this, encode_this_many_bytes); //Records base64 encoded data.
BIO_flush(b64_bio); //Flush data. Necessary for b64 encoding, because of pad characters.
BIO_get_mem_ptr(mem_bio, &mem_bio_mem_ptr); //Store address of mem_bio's memory structure.
BIO_set_close(mem_bio, BIO_NOCLOSE); //Permit access to mem_ptr after BIOs are destroyed.
BIO_free_all(b64_bio); //Destroys all BIOs in chain, starting with b64 (i.e. the 1st one).
BUF_MEM_grow(mem_bio_mem_ptr, (*mem_bio_mem_ptr).length + 1); //Makes space for end null.
(*mem_bio_mem_ptr).data[(*mem_bio_mem_ptr).length] = '\0'; //Adds null-terminator to tail.
return (*mem_bio_mem_ptr).data; //Returns base-64 encoded data. (See: "buf_mem_st" struct).
}
char *base64decode (const void *b64_decode_this, int decode_this_many_bytes){
BIO *b64_bio, *mem_bio; //Declares two OpenSSL BIOs: a base64 filter and a memory BIO.
char *base64_decoded = calloc( (decode_this_many_bytes*3)/4+1, sizeof(char) ); //+1 = null.
b64_bio = BIO_new(BIO_f_base64()); //Initialize our base64 filter BIO.
mem_bio = BIO_new(BIO_s_mem()); //Initialize our memory source BIO.
BIO_write(mem_bio, b64_decode_this, decode_this_many_bytes); //Base64 data saved in source.
BIO_push(b64_bio, mem_bio); //Link the BIOs by creating a filter-source BIO chain.
BIO_set_flags(b64_bio, BIO_FLAGS_BASE64_NO_NL); //Don't require trailing newlines.
int decoded_byte_index = 0; //Index where the next base64_decoded byte should be written.
while ( 0 < BIO_read(b64_bio, base64_decoded+decoded_byte_index, 1) ){ //Read byte-by-byte.
decoded_byte_index++; //Increment the index until read of BIO decoded data is complete.
} //Once we're done reading decoded data, BIO_read returns -1 even though there's no error.
BIO_free_all(b64_bio); //Destroys all BIOs in chain, starting with b64 (i.e. the 1st one).
return base64_decoded; //Returns base-64 decoded data with trailing null terminator.
}
/*Here's one way to base64 encode/decode using the base64encode() and base64decode functions.*/
int main(void){
char data_to_encode[] = "Base64 encode this string!"; //The string we will base-64 encode.
int bytes_to_encode = strlen(data_to_encode); //Number of bytes in string to base64 encode.
char *base64_encoded = base64encode(data_to_encode, bytes_to_encode); //Base-64 encoding.
int bytes_to_decode = strlen(base64_encoded); //Number of bytes in string to base64 decode.
char *base64_decoded = base64decode(base64_encoded, bytes_to_decode); //Base-64 decoding.
printf("Original character string is: %s\n", data_to_encode); //Prints our initial string.
printf("Base-64 encoded string is: %s\n", base64_encoded); //Prints base64 encoded string.
printf("Base-64 decoded string is: %s\n", base64_decoded); //Prints base64 decoded string.
free(base64_encoded); //Frees up the memory holding our base64 encoded data.
free(base64_decoded); //Frees up the memory holding our base64 decoded data.
}
cc -o base base.c -lssl -lcrypto
编译它,没有错误。它产生了以下输出:原始字符字符串为:Base64 encode this string! Base-64编码字符串为:QmFzZTY0IGVuY29kZSB0aGlzIHN0cmluZyE= Base-64解码字符串为:Base64 encode this string!
- clearlightlibb64 有C和C++的API。它非常轻量级,也可能是目前最快的公开实现之一。它还是一个专用的独立的base64编码库,如果您不需要使用较大的库(如OpenSSL或glib)中的所有其他内容,那么这可能会很好。
GLib提供了用于base64编码的函数:https://developer.gnome.org/glib/stable/glib-Base64-Encoding.html
GNU coreutils中的lib/base64库包含相关内容。尽管有些臃肿但可以处理像EBCDIC这样的东西。您也可以自行尝试,例如:
char base64_digit (n) unsigned n; {
if (n < 10) return n - '0';
else if (n < 10 + 26) return n - 'a';
else if (n < 10 + 26 + 26) return n - 'A';
else assert(0);
return 0;
}
unsigned char base64_decode_digit(char c) {
switch (c) {
case '=' : return 62;
case '.' : return 63;
default :
if (isdigit(c)) return c - '0';
else if (islower(c)) return c - 'a' + 10;
else if (isupper(c)) return c - 'A' + 10 + 26;
else assert(0);
}
return 0xff;
}
unsigned base64_decode(char *s) {
char *p;
unsigned n = 0;
for (p = s; *p; p++)
n = 64 * n + base64_decode_digit(*p);
return n;
}
特此知悉:您不应将“自己玩耍”与“实施标准”混淆。天啊。
'+'
对应 62,'/'
对应 63。在 base64编码的变种 列表中,没有发现使用您所用字符排序的 base64 编码变种。但是,该算法背后的数学是正确的。请注意不要修改原文意思。 - Patrickhttp://www.adp-gmbh.ch/cpp/common/base64.html
代码的制作归功于René Nyffenegger。base64.cpp
/*
base64.cpp and base64.h
Copyright (C) 2004-2008 René Nyffenegger
This source code is provided 'as-is', without any express or implied
warranty. In no event will the author be held liable for any damages
arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it
freely, subject to the following restrictions:
1. The origin of this source code must not be misrepresented; you must not
claim that you wrote the original source code. If you use this source code
in a product, an acknowledgment in the product documentation would be
appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original source code.
3. This notice may not be removed or altered from any source distribution.
René Nyffenegger rene.nyffenegger@adp-gmbh.ch
*/
#include "base64.h"
#include <iostream>
static const std::string base64_chars =
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz"
"0123456789+/";
static inline bool is_base64(unsigned char c) {
return (isalnum(c) || (c == '+') || (c == '/'));
}
std::string base64_encode(unsigned char const* bytes_to_encode, unsigned int in_len) {
std::string ret;
int i = 0;
int j = 0;
unsigned char char_array_3[3];
unsigned char char_array_4[4];
while (in_len--) {
char_array_3[i++] = *(bytes_to_encode++);
if (i == 3) {
char_array_4[0] = (char_array_3[0] & 0xfc) >> 2;
char_array_4[1] = ((char_array_3[0] & 0x03) << 4) + ((char_array_3[1] & 0xf0) >> 4);
char_array_4[2] = ((char_array_3[1] & 0x0f) << 2) + ((char_array_3[2] & 0xc0) >> 6);
char_array_4[3] = char_array_3[2] & 0x3f;
for(i = 0; (i <4) ; i++)
ret += base64_chars[char_array_4[i]];
i = 0;
}
}
if (i)
{
for(j = i; j < 3; j++)
char_array_3[j] = '\0';
char_array_4[0] = (char_array_3[0] & 0xfc) >> 2;
char_array_4[1] = ((char_array_3[0] & 0x03) << 4) + ((char_array_3[1] & 0xf0) >> 4);
char_array_4[2] = ((char_array_3[1] & 0x0f) << 2) + ((char_array_3[2] & 0xc0) >> 6);
char_array_4[3] = char_array_3[2] & 0x3f;
for (j = 0; (j < i + 1); j++)
ret += base64_chars[char_array_4[j]];
while((i++ < 3))
ret += '=';
}
return ret;
}
std::string base64_decode(std::string const& encoded_string) {
int in_len = encoded_string.size();
int i = 0;
int j = 0;
int in_ = 0;
unsigned char char_array_4[4], char_array_3[3];
std::string ret;
while (in_len-- && ( encoded_string[in_] != '=') && is_base64(encoded_string[in_])) {
char_array_4[i++] = encoded_string[in_]; in_++;
if (i ==4) {
for (i = 0; i <4; i++)
char_array_4[i] = base64_chars.find(char_array_4[i]);
char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
for (i = 0; (i < 3); i++)
ret += char_array_3[i];
i = 0;
}
}
if (i) {
for (j = i; j <4; j++)
char_array_4[j] = 0;
for (j = 0; j <4; j++)
char_array_4[j] = base64_chars.find(char_array_4[j]);
char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
for (j = 0; (j < i - 1); j++) ret += char_array_3[j];
}
return ret;
}
base64.h
#include <string>
std::string base64_encode(unsigned char const* , unsigned int len);
std::string base64_decode(std::string const& s);
Usage
const std::string s = "test";
std::string encoded = base64_encode(reinterpret_cast<const unsigned char*>(s.c_str()), s.length());
std::string decoded = base64_decode(encoded);
使用EVP_EncodeBlock
和EVP_DecodeBlock
函数非常简单:
#include <stdio.h>
#include <stdlib.h>
#include <openssl/evp.h>
char *base64(const unsigned char *input, int length) {
const int pl = 4*((length+2)/3);
char *output = calloc(pl+1, 1); //+1 for the terminating null that EVP_EncodeBlock adds on
const int ol = EVP_EncodeBlock(output, input, length);
if (ol != pl) { fprintf(stderr, "Whoops, encode predicted %d but we got %d\n", pl, ol); }
return output;
}
unsigned char *decode64(const char *input, int length) {
const int pl = 3*length/4;
unsigned char *output = calloc(pl+1, 1);
const int ol = EVP_DecodeBlock(output, input, length);
if (pl != ol) { fprintf(stderr, "Whoops, decode predicted %d but we got %d\n", pl, ol); }
return output;
}
这是我多年来一直在使用的解码器...
static const char table[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static const int BASE64_INPUT_SIZE = 57;
BOOL isbase64(char c)
{
return c && strchr(table, c) != NULL;
}
inline char value(char c)
{
const char *p = strchr(table, c);
if(p) {
return p-table;
} else {
return 0;
}
}
int UnBase64(unsigned char *dest, const unsigned char *src, int srclen)
{
*dest = 0;
if(*src == 0)
{
return 0;
}
unsigned char *p = dest;
do
{
char a = value(src[0]);
char b = value(src[1]);
char c = value(src[2]);
char d = value(src[3]);
*p++ = (a << 2) | (b >> 4);
*p++ = (b << 4) | (c >> 2);
*p++ = (c << 6) | d;
if(!isbase64(src[1]))
{
p -= 2;
break;
}
else if(!isbase64(src[2]))
{
p -= 2;
break;
}
else if(!isbase64(src[3]))
{
p--;
break;
}
src += 4;
while(*src && (*src == 13 || *src == 10)) src++;
}
while(srclen-= 4);
*p = 0;
return p-dest;
}
UnBase64
函数可能会损坏目标缓冲区之后的内存。例如,尝试将以下Base64编码字符串“BQ==”解码为单个BYTE(即unsigned char Result = 0; UnBase64(&Result, "BQ==", 4);
)时,它将破坏堆栈!请注意修复此问题。 - Mike Dinescu
libb64
本身是用c++实现的,我认为答案也可以被视为不相关。 - malat