recoll/src/utils/md5.cpp
Jean-Francois Dockes b8be14bd7b shared
2020-07-15 10:48:08 +02:00

300 lines
9.9 KiB
C++

/* $OpenBSD: md5.c,v 1.4 2014/12/28 10:04:35 tedu Exp $ */
/*
* This code implements the MD5 message-digest algorithm.
* The algorithm is due to Ron Rivest. This code was
* written by Colin Plumb in 1993, no copyright is claimed.
* This code is in the public domain; do with it what you wish.
*
* Equivalent code is available from RSA Data Security, Inc.
* This code has been tested against that, and is equivalent,
* except that you don't need to include two pages of legalese
* with every copy.
*
* To compute the message digest of a chunk of bytes, declare an
* MD5Context structure, pass it to MD5Init, call MD5Update as
* needed on buffers full of bytes, and then call MD5Final, which
* will fill a supplied 16-byte array with the digest.
*/
#ifdef BUILDING_RECOLL
#include "autoconfig.h"
#else
#include "config.h"
#endif
#include "md5.h"
#include <cstring>
#define PUT_BIT_LE(i, cp, value) do { \
(cp)[i] = (uint8_t)(((value) >> 8 * i) & 0xFF); \
} while (0)
#define PUT_64BIT_LE(cp, value) do { \
PUT_BIT_LE(7, cp, value); \
PUT_BIT_LE(6, cp, value); \
PUT_BIT_LE(5, cp, value); \
PUT_BIT_LE(4, cp, value); \
PUT_BIT_LE(3, cp, value); \
PUT_BIT_LE(2, cp, value); \
PUT_BIT_LE(1, cp, value); \
PUT_BIT_LE(0, cp, value); \
} while (0)
#define PUT_32BIT_LE(cp, value) do { \
PUT_BIT_LE(3, cp, value); \
PUT_BIT_LE(2, cp, value); \
PUT_BIT_LE(1, cp, value); \
PUT_BIT_LE(0, cp, value); \
} while (0)
static uint8_t PADDING[MD5_BLOCK_LENGTH] = {
0x80, 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, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
/*
* Start MD5 accumulation. Set bit count to 0 and buffer to mysterious
* initialization constants.
*/
void
MD5Init(MD5_CTX *ctx)
{
ctx->count = 0;
ctx->state[0] = 0x67452301;
ctx->state[1] = 0xefcdab89;
ctx->state[2] = 0x98badcfe;
ctx->state[3] = 0x10325476;
}
/*
* Update context to reflect the concatenation of another buffer full
* of bytes.
*/
void
MD5Update(MD5_CTX *ctx, const void *inputptr, size_t len)
{
auto input = static_cast<const uint8_t *>(inputptr);
size_t have, need;
/* Check how many bytes we already have and how many more we need. */
have = static_cast<size_t>((ctx->count >> 3) & (MD5_BLOCK_LENGTH - 1));
need = MD5_BLOCK_LENGTH - have;
/* Update bitcount */
ctx->count += static_cast<uint64_t>(len) << 3;
if (len >= need) {
if (have != 0) {
memcpy(ctx->buffer + have, input, need);
MD5Transform(ctx->state, ctx->buffer);
input += need;
len -= need;
have = 0;
}
/* Process data in MD5_BLOCK_LENGTH-byte chunks. */
while (len >= MD5_BLOCK_LENGTH) {
MD5Transform(ctx->state, input);
input += MD5_BLOCK_LENGTH;
len -= MD5_BLOCK_LENGTH;
}
}
/* Handle any remaining bytes of data. */
if (len != 0)
memcpy(ctx->buffer + have, input, len);
}
/*
* Final wrapup - pad to 64-byte boundary with the bit pattern
* 1 0* (64-bit count of bits processed, MSB-first)
*/
void
MD5Final(unsigned char digest[MD5_DIGEST_LENGTH], MD5_CTX *ctx)
{
uint8_t count[8];
size_t padlen;
int i;
/* Convert count to 8 bytes in little endian order. */
PUT_64BIT_LE(count, ctx->count);
/* Pad out to 56 mod 64. */
padlen = MD5_BLOCK_LENGTH -
((ctx->count >> 3) & (MD5_BLOCK_LENGTH - 1));
if (padlen < 1 + 8)
padlen += MD5_BLOCK_LENGTH;
MD5Update(ctx, PADDING, padlen - 8); /* padlen - 8 <= 64 */
MD5Update(ctx, count, 8);
for (i = 0; i < 4; i++)
PUT_32BIT_LE(digest + i * 4, ctx->state[i]);
memset(ctx, 0, sizeof(*ctx)); /* in case it's sensitive */
}
/* The four core functions - F1 is optimized somewhat */
/* #define F1(x, y, z) (x & y | ~x & z) */
#define F1(x, y, z) (z ^ (x & (y ^ z)))
#define F2(x, y, z) F1(z, x, y)
#define F3(x, y, z) (x ^ y ^ z)
#define F4(x, y, z) (y ^ (x | ~z))
/* This is the central step in the MD5 algorithm. */
#define MD5STEP(f, w, x, y, z, data, s) \
( w += f(x, y, z) + data, w = w<<s | w>>(32-s), w += x )
/*
* The core of the MD5 algorithm, this alters an existing MD5 hash to
* reflect the addition of 16 longwords of new data. MD5Update blocks
* the data and converts bytes into longwords for this routine.
*/
void
MD5Transform(uint32_t state[4], const uint8_t block[MD5_BLOCK_LENGTH])
{
uint32_t a, b, c, d, in[MD5_BLOCK_LENGTH / 4];
#if BYTE_ORDER == LITTLE_ENDIAN
memcpy(in, block, sizeof(in));
#else
for (a = 0; a < MD5_BLOCK_LENGTH / 4; a++) {
in[a] = (uint32_t)(
(uint32_t)(block[a * 4 + 0]) |
(uint32_t)(block[a * 4 + 1]) << 8 |
(uint32_t)(block[a * 4 + 2]) << 16 |
(uint32_t)(block[a * 4 + 3]) << 24);
}
#endif
a = state[0];
b = state[1];
c = state[2];
d = state[3];
MD5STEP(F1, a, b, c, d, in[ 0] + 0xd76aa478, 7);
MD5STEP(F1, d, a, b, c, in[ 1] + 0xe8c7b756, 12);
MD5STEP(F1, c, d, a, b, in[ 2] + 0x242070db, 17);
MD5STEP(F1, b, c, d, a, in[ 3] + 0xc1bdceee, 22);
MD5STEP(F1, a, b, c, d, in[ 4] + 0xf57c0faf, 7);
MD5STEP(F1, d, a, b, c, in[ 5] + 0x4787c62a, 12);
MD5STEP(F1, c, d, a, b, in[ 6] + 0xa8304613, 17);
MD5STEP(F1, b, c, d, a, in[ 7] + 0xfd469501, 22);
MD5STEP(F1, a, b, c, d, in[ 8] + 0x698098d8, 7);
MD5STEP(F1, d, a, b, c, in[ 9] + 0x8b44f7af, 12);
MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
MD5STEP(F2, a, b, c, d, in[ 1] + 0xf61e2562, 5);
MD5STEP(F2, d, a, b, c, in[ 6] + 0xc040b340, 9);
MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
MD5STEP(F2, b, c, d, a, in[ 0] + 0xe9b6c7aa, 20);
MD5STEP(F2, a, b, c, d, in[ 5] + 0xd62f105d, 5);
MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
MD5STEP(F2, b, c, d, a, in[ 4] + 0xe7d3fbc8, 20);
MD5STEP(F2, a, b, c, d, in[ 9] + 0x21e1cde6, 5);
MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
MD5STEP(F2, c, d, a, b, in[ 3] + 0xf4d50d87, 14);
MD5STEP(F2, b, c, d, a, in[ 8] + 0x455a14ed, 20);
MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
MD5STEP(F2, d, a, b, c, in[ 2] + 0xfcefa3f8, 9);
MD5STEP(F2, c, d, a, b, in[ 7] + 0x676f02d9, 14);
MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
MD5STEP(F3, a, b, c, d, in[ 5] + 0xfffa3942, 4);
MD5STEP(F3, d, a, b, c, in[ 8] + 0x8771f681, 11);
MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
MD5STEP(F3, a, b, c, d, in[ 1] + 0xa4beea44, 4);
MD5STEP(F3, d, a, b, c, in[ 4] + 0x4bdecfa9, 11);
MD5STEP(F3, c, d, a, b, in[ 7] + 0xf6bb4b60, 16);
MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
MD5STEP(F3, d, a, b, c, in[ 0] + 0xeaa127fa, 11);
MD5STEP(F3, c, d, a, b, in[ 3] + 0xd4ef3085, 16);
MD5STEP(F3, b, c, d, a, in[ 6] + 0x04881d05, 23);
MD5STEP(F3, a, b, c, d, in[ 9] + 0xd9d4d039, 4);
MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
MD5STEP(F3, b, c, d, a, in[2 ] + 0xc4ac5665, 23);
MD5STEP(F4, a, b, c, d, in[ 0] + 0xf4292244, 6);
MD5STEP(F4, d, a, b, c, in[7 ] + 0x432aff97, 10);
MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
MD5STEP(F4, b, c, d, a, in[5 ] + 0xfc93a039, 21);
MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
MD5STEP(F4, d, a, b, c, in[3 ] + 0x8f0ccc92, 10);
MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
MD5STEP(F4, b, c, d, a, in[1 ] + 0x85845dd1, 21);
MD5STEP(F4, a, b, c, d, in[8 ] + 0x6fa87e4f, 6);
MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
MD5STEP(F4, c, d, a, b, in[6 ] + 0xa3014314, 15);
MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
MD5STEP(F4, a, b, c, d, in[4 ] + 0xf7537e82, 6);
MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
MD5STEP(F4, c, d, a, b, in[2 ] + 0x2ad7d2bb, 15);
MD5STEP(F4, b, c, d, a, in[9 ] + 0xeb86d391, 21);
state[0] += a;
state[1] += b;
state[2] += c;
state[3] += d;
}
// C++ utilities
using std::string;
void MD5Final(string &digest, MD5_CTX *context)
{
unsigned char d[16];
MD5Final (d, context);
digest.assign(reinterpret_cast<const char*>(d), 16);
}
string& MD5String(const string& data, string& digest)
{
MD5_CTX ctx;
MD5Init(&ctx);
MD5Update(&ctx, reinterpret_cast<const unsigned char*>(data.c_str()), data.length());
MD5Final(digest, &ctx);
return digest;
}
string& MD5HexPrint(const string& digest, string &out)
{
out.erase();
out.reserve(33);
static const char hex[]="0123456789abcdef";
auto hash = reinterpret_cast<const unsigned char*>(digest.c_str());
for (int i = 0; i < 16; i++) {
out.append(1, hex[hash[i] >> 4]);
out.append(1, hex[hash[i] & 0x0f]);
}
return out;
}
string& MD5HexScan(const string& xdigest, string& digest)
{
digest.erase();
if (xdigest.length() != 32) {
return digest;
}
for (unsigned int i = 0; i < 16; i++) {
unsigned int val;
if (sscanf(xdigest.c_str() + 2*i, "%2x", &val) != 1) {
digest.erase();
return digest;
}
digest.append(1, static_cast<unsigned char>(val));
}
return digest;
}