Is there a freely available Base64 decoding code snippet in C++?
13 Answers
See Encoding and decoding base 64 with C++.
Here is the implementation from that page:
/*
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
*/
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;
}
My version is a simple fast encoder (decoder) of Base64 for C++Builder.
// ---------------------------------------------------------------------------
UnicodeString __fastcall TExample::Base64Encode(void *data, int length)
{
if (length <= 0)
return L"";
static const char set[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
unsigned char *in = (unsigned char*)data;
char *pos, *out = pos = new char[((length - 1) / 3 + 1) << 2];
while ((length -= 3) >= 0)
{
pos[0] = set[in[0] >> 2];
pos[1] = set[((in[0] & 0x03) << 4) | (in[1] >> 4)];
pos[2] = set[((in[1] & 0x0F) << 2) | (in[2] >> 6)];
pos[3] = set[in[2] & 0x3F];
pos += 4;
in += 3;
};
if ((length & 2) != 0)
{
pos[0] = set[in[0] >> 2];
if ((length & 1) != 0)
{
pos[1] = set[((in[0] & 0x03) << 4) | (in[1] >> 4)];
pos[2] = set[(in[1] & 0x0F) << 2];
}
else
{
pos[1] = set[(in[0] & 0x03) << 4];
pos[2] = '=';
};
pos[3] = '=';
pos += 4;
};
UnicodeString code = UnicodeString(out, pos - out);
delete[] out;
return code;
};
// ---------------------------------------------------------------------------
int __fastcall TExample::Base64Decode(const UnicodeString &code, unsigned char **data)
{
int length;
if (((length = code.Length()) == 0) || ((length & 3) != 0))
return 0;
wchar_t *str = code.c_str();
unsigned char *pos, *out = pos = new unsigned char[(length >> 2) * 3];
while (*str != 0)
{
length = -1;
int shift = 18, bits = 0;
do
{
wchar_t s = str[++length];
if ((s >= L'A') && (s <= L'Z'))
bits |= (s - L'A') << shift;
else if ((s >= L'a') && (s <= L'z'))
bits |= (s - (L'a' - 26)) << shift;
else if (((s >= L'0') && (s <= L'9')))
bits |= (s - (L'0' - 52)) << shift;
else if (s == L'+')
bits |= 62 << shift;
else if (s == L'/')
bits |= 63 << shift;
else if (s == L'=')
{
length--;
break;
}
else
{
delete[] out;
return 0;
};
}
while ((shift -= 6) >= 0);
pos[0] = bits >> 16;
pos[1] = bits >> 8;
pos[2] = bits;
pos += length;
str += 4;
};
*data = out;
return pos - out;
};
//---------------------------------------------------------------------------
I use this:
class BinaryVector {
public:
std::vector<char> bytes;
uint64_t bit_count = 0;
public:
/* Add a bit to the end */
void push_back(bool bit);
/* Return false if character is unrecognized */
bool pushBase64Char(char b64_c);
};
void BinaryVector::push_back(bool bit)
{
if (!bit_count || bit_count % 8 == 0) {
bytes.push_back(bit << 7);
}
else {
uint8_t next_bit = 8 - (bit_count % 8) - 1;
bytes[bit_count / 8] |= bit << next_bit;
}
bit_count++;
}
/* Converts one Base64 character to 6 bits */
bool BinaryVector::pushBase64Char(char c)
{
uint8_t d;
// A to Z
if (c > 0x40 && c < 0x5b) {
d = c - 65; // Base64 A is 0
}
// a to z
else if (c > 0x60 && c < 0x7b) {
d = c - 97 + 26; // Base64 a is 26
}
// 0 to 9
else if (c > 0x2F && c < 0x3a) {
d = c - 48 + 52; // Base64 0 is 52
}
else if (c == '+') {
d = 0b111110;
}
else if (c == '/') {
d = 0b111111;
}
else if (c == '=') {
d = 0;
}
else {
return false;
}
push_back(d & 0b100000);
push_back(d & 0b010000);
push_back(d & 0b001000);
push_back(d & 0b000100);
push_back(d & 0b000010);
push_back(d & 0b000001);
return true;
}
bool loadBase64(std::vector<char>& b64_bin, BinaryVector& vec)
{
for (char& c : b64_bin) {
if (!vec.pushBase64Char(c)) {
return false;
}
}
return true;
}
Use vec.bytes to access converted data.
I firstly made my own version and then found this topic.
Why does my version look simpler than others presented here? Am I doing something wrong? I didn't test it for speed.
inline char const* b64units = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
inline char* b64encode(void const* a, int64_t b) {
ASSERT(a != nullptr);
if (b > 0) {
uint8_t const* aa = static_cast<uint8_t const*>(a);
uint8_t v = 0;
int64_t bp = 0;
int64_t sb = 0;
int8_t off = 0;
int64_t nt = ((b + 2) / 3) * 4;
int64_t nd = (b * 8) / 6;
int64_t tl = ((b * 8) % 6) ? 1 : 0;
int64_t nf = nt - nd - tl;
int64_t ri = 0;
char* r = new char[nt + 1]();
for (int64_t i = 0; i < nd; i++) {
v = (aa[sb] << off) | (aa[sb + 1] >> (8 - off));
v >>= 2;
r[ri] = b64units[v];
ri += 1;
bp += 6;
sb = (bp / 8);
off = (bp % 8);
}
if (tl > 0) {
v = (aa[sb] << off);
v >>= 2;
r[ri] = b64units[v];
ri += 1;
}
for (int64_t i = 0; i < nf; i++) {
r[ri] = '=';
ri += 1;
}
return r;
} else return nullptr;
}
P.S.: My method works well. I tested it with Node.js:
let data = 'stackabuse.com';
let buff = new Buffer(data);
let base64data = buff.toString('base64');
I liked this solution on GitHub.
It is a single hpp file and it uses the vector<byte> type for raw data unlike the accepted answer.
#pragma once
#include <string>
#include <vector>
#include <stdexcept>
#include <cstdint>
namespace base64
{
inline static const char kEncodeLookup[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
inline static const char kPadCharacter = '=';
using byte = std::uint8_t;
inline std::string encode(const std::vector<byte>& input)
{
std::string encoded;
encoded.reserve(((input.size() / 3) + (input.size() % 3 > 0)) * 4);
std::uint32_t temp{};
auto it = input.begin();
for(std::size_t i = 0; i < input.size() / 3; ++i)
{
temp = (*it++) << 16;
temp += (*it++) << 8;
temp += (*it++);
encoded.append(1, kEncodeLookup[(temp & 0x00FC0000) >> 18]);
encoded.append(1, kEncodeLookup[(temp & 0x0003F000) >> 12]);
encoded.append(1, kEncodeLookup[(temp & 0x00000FC0) >> 6 ]);
encoded.append(1, kEncodeLookup[(temp & 0x0000003F) ]);
}
switch(input.size() % 3)
{
case 1:
temp = (*it++) << 16;
encoded.append(1, kEncodeLookup[(temp & 0x00FC0000) >> 18]);
encoded.append(1, kEncodeLookup[(temp & 0x0003F000) >> 12]);
encoded.append(2, kPadCharacter);
break;
case 2:
temp = (*it++) << 16;
temp += (*it++) << 8;
encoded.append(1, kEncodeLookup[(temp & 0x00FC0000) >> 18]);
encoded.append(1, kEncodeLookup[(temp & 0x0003F000) >> 12]);
encoded.append(1, kEncodeLookup[(temp & 0x00000FC0) >> 6 ]);
encoded.append(1, kPadCharacter);
break;
}
return encoded;
}
std::vector<byte> decode(const std::string& input)
{
if(input.length() % 4)
throw std::runtime_error("Invalid base64 length!");
std::size_t padding{};
if(input.length())
{
if(input[input.length() - 1] == kPadCharacter) padding++;
if(input[input.length() - 2] == kPadCharacter) padding++;
}
std::vector<byte> decoded;
decoded.reserve(((input.length() / 4) * 3) - padding);
std::uint32_t temp{};
auto it = input.begin();
while(it < input.end())
{
for(std::size_t i = 0; i < 4; ++i)
{
temp <<= 6;
if (*it >= 0x41 && *it <= 0x5A) temp |= *it - 0x41;
else if(*it >= 0x61 && *it <= 0x7A) temp |= *it - 0x47;
else if(*it >= 0x30 && *it <= 0x39) temp |= *it + 0x04;
else if(*it == 0x2B) temp |= 0x3E;
else if(*it == 0x2F) temp |= 0x3F;
else if(*it == kPadCharacter)
{
switch(input.end() - it)
{
case 1:
decoded.push_back((temp >> 16) & 0x000000FF);
decoded.push_back((temp >> 8 ) & 0x000000FF);
return decoded;
case 2:
decoded.push_back((temp >> 10) & 0x000000FF);
return decoded;
default:
throw std::runtime_error("Invalid padding in base64!");
}
}
else throw std::runtime_error("Invalid character in base64!");
++it;
}
decoded.push_back((temp >> 16) & 0x000000FF);
decoded.push_back((temp >> 8 ) & 0x000000FF);
decoded.push_back((temp ) & 0x000000FF);
}
return decoded;
}
}
Here is one written by me which uses unions and bit fields for maximum efficiency and readibility.
const char PADDING_CHAR = '=';
const char* ALPHABET = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
const uint8_t DECODED_ALPHBET[128]={0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,62,0,0,0,63,52,53,54,55,56,57,58,59,60,61,0,0,0,0,0,0,0,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,0,0,0,0,0,0,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,0,0,0,0,0};
/**
* Given a string, this function will encode it in 64b (with padding)
*/
std::string encodeBase64(const std::string& binaryText)
{
std::string encoded((binaryText.size()/3 + (binaryText.size()%3 > 0)) << 2, PADDING_CHAR);
const char* bytes = binaryText.data();
union
{
uint32_t temp = 0;
struct
{
uint32_t first : 6, second : 6, third : 6, fourth : 6;
} tempBytes;
};
std::string::iterator currEncoding = encoded.begin();
for(uint32_t i = 0, lim = binaryText.size() / 3; i < lim; ++i, bytes+=3)
{
temp = bytes[0] << 16 | bytes[1] << 8 | bytes[2];
(*currEncoding++) = ALPHABET[tempBytes.fourth];
(*currEncoding++) = ALPHABET[tempBytes.third];
(*currEncoding++) = ALPHABET[tempBytes.second];
(*currEncoding++) = ALPHABET[tempBytes.first];
}
switch(binaryText.size() % 3)
{
case 1:
temp = bytes[0] << 16;
(*currEncoding++) = ALPHABET[tempBytes.fourth];
(*currEncoding++) = ALPHABET[tempBytes.third];
break;
case 2:
temp = bytes[0] << 16 | bytes[1] << 8;
(*currEncoding++) = ALPHABET[tempBytes.fourth];
(*currEncoding++) = ALPHABET[tempBytes.third];
(*currEncoding++) = ALPHABET[tempBytes.second];
break;
}
return encoded;
}
/**
* Given a 64b padding-encoded string, this function will decode it.
*/
std::string decodeBase64(const std::string& base64Text)
{
if( base64Text.empty() )
return "";
assert((base64Text.size()&3) == 0 && "The base64 text to be decoded must have a length devisible by 4!");
uint32_t numPadding = (*std::prev(base64Text.end(),1) == PADDING_CHAR) + (*std::prev(base64Text.end(),2) == PADDING_CHAR);
std::string decoded((base64Text.size()*3>>2) - numPadding, '.');
union
{
uint32_t temp;
char tempBytes[4];
};
const uint8_t* bytes = reinterpret_cast<const uint8_t*>(base64Text.data());
std::string::iterator currDecoding = decoded.begin();
for(uint32_t i = 0, lim = (base64Text.size() >> 2) - (numPadding!=0); i < lim; ++i, bytes+=4)
{
temp = DECODED_ALPHBET[bytes[0]] << 18 | DECODED_ALPHBET[bytes[1]] << 12 | DECODED_ALPHBET[bytes[2]] << 6 | DECODED_ALPHBET[bytes[3]];
(*currDecoding++) = tempBytes[2];
(*currDecoding++) = tempBytes[1];
(*currDecoding++) = tempBytes[0];
}
switch (numPadding)
{
case 2:
temp = DECODED_ALPHBET[bytes[0]] << 18 | DECODED_ALPHBET[bytes[1]] << 12;
(*currDecoding++) = tempBytes[2];
break;
case 1:
temp = DECODED_ALPHBET[bytes[0]] << 18 | DECODED_ALPHBET[bytes[1]] << 12 | DECODED_ALPHBET[bytes[2]] << 6;
(*currDecoding++) = tempBytes[2];
(*currDecoding++) = tempBytes[1];
break;
}
return decoded;
}
Related