wtf/MD5.cpp

   1 // The original file was copied from sqlite, and was in the public domain.
   2 // Modifications Copyright 2006 Google Inc. All Rights Reserved
   3 /*
   4  * Copyright (C) 2010 Google Inc. All rights reserved.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions are
   8  * met:
   9  *
  10  *     * Redistributions of source code must retain the above copyright
  11  * notice, this list of conditions and the following disclaimer.
  12  *     * Redistributions in binary form must reproduce the above
  13  * copyright notice, this list of conditions and the following disclaimer
  14  * in the documentation and/or other materials provided with the
  15  * distribution.
  16  *     * Neither the name of Google Inc. nor the names of its
  17  * contributors may be used to endorse or promote products derived from
  18  * this software without specific prior written permission.
  19  *
  20  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  21  * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  22  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  23  * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  24  * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  25  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  26  * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  27  * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  28  * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  29  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  30  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  31  */
  32 /*
  33  * This code implements the MD5 message-digest algorithm.
  34  * The algorithm is due to Ron Rivest.  This code was
  35  * written by Colin Plumb in 1993, no copyright is claimed.
  36  * This code is in the public domain; do with it what you wish.
  37  *
  38  * Equivalent code is available from RSA Data Security, Inc.
  39  * This code has been tested against that, and is equivalent,
  40  * except that you don't need to include two pages of legalese
  41  * with every copy.
  42  *
  43  * To compute the message digest of a chunk of bytes, construct an
  44  * MD5 instance, call addBytes as needed on buffers full of bytes,
  45  * and then call checksum, which will fill a supplied 16-byte array
  46  * with the digest.
  47  */
  48
  49 #include "config.h"
  50 #include "MD5.h"
  51
  52 #include "Assertions.h"
  53 #ifndef NDEBUG
  54 #include "StringExtras.h"
  55 #include "text/CString.h"
  56 #endif
  57
  58 namespace WTF {
  59
  60 #ifdef NDEBUG
  61 static inline void testMD5() { }
  62 #else
  63 // MD5 test case.
  64 static bool isTestMD5Done;
  65
  66 static void expectMD5(CString input, CString expected)
  67 {
  68     MD5 md5;
  69     md5.addBytes(reinterpret_cast<const uint8_t*>(input.data()), input.length());
  70     Vector<uint8_t, 16> digest = md5.checksum();
  71     char* buf = 0;
  72     CString actual = CString::newUninitialized(32, buf);
  73     for (size_t i = 0; i < 16; i++) {
  74         snprintf(buf, 3, "%02x", digest.at(i));
  75         buf += 2;
  76     }
  77     ASSERT_WITH_MESSAGE(actual == expected, "input:%s[%d] actual:%s expected:%s", input.data(), input.length(), actual.data(), expected.data());
  78 }
  79
  80 static void testMD5()
  81 {
  82     if (isTestMD5Done)
  83         return;
  84     isTestMD5Done = true;
  85
  86     // MD5 Test suite from http://www.ietf.org/rfc/rfc1321.txt
  87     expectMD5("", "d41d8cd98f00b204e9800998ecf8427e");
  88     expectMD5("a", "0cc175b9c0f1b6a831c399e269772661");
  89     expectMD5("abc", "900150983cd24fb0d6963f7d28e17f72");
  90     expectMD5("message digest", "f96b697d7cb7938d525a2f31aaf161d0");
  91     expectMD5("abcdefghijklmnopqrstuvwxyz", "c3fcd3d76192e4007dfb496cca67e13b");
  92     expectMD5("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789", "d174ab98d277d9f5a5611c2c9f419d9f");
  93     expectMD5("12345678901234567890123456789012345678901234567890123456789012345678901234567890", "57edf4a22be3c955ac49da2e2107b67a");
  94 }
  95 #endif
  96
  97 // Note: this code is harmless on little-endian machines.
  98
  99 static void reverseBytes(uint8_t* buf, unsigned longs)
 100 {
 101     ASSERT(longs > 0);
 102     do {
 103         uint32_t t = static_cast<uint32_t>(buf[3] << 8 | buf[2]) << 16 | buf[1] << 8 | buf[0];
 104         ASSERT_WITH_MESSAGE(!(reinterpret_cast<uintptr_t>(buf) % sizeof(t)), "alignment error of buf");
 105         *reinterpret_cast<uint32_t *>(buf) = t;
 106         buf += 4;
 107     } while (--longs);
 108 }
 109
 110 // The four core functions.
 111 // F1 is originally defined as (x & y | ~x & z), but optimized somewhat: 4 bit ops -> 3 bit ops.
 112 #define F1(x, y, z) (z ^ (x & (y ^ z)))
 113 #define F2(x, y, z) F1(z, x, y)
 114 #define F3(x, y, z) (x ^ y ^ z)
 115 #define F4(x, y, z) (y ^ (x | ~z))
 116
 117 // This is the central step in the MD5 algorithm.
 118 #define MD5STEP(f, w, x, y, z, data, s) \
 119     (w += f(x, y, z) + data, w = w << s | w >> (32 - s), w += x)
 120
 121 static void MD5Transform(uint32_t buf[4], const uint32_t in[16])
 122 {
 123     uint32_t a = buf[0];
 124     uint32_t b = buf[1];
 125     uint32_t c = buf[2];
 126     uint32_t d = buf[3];
 127
 128     MD5STEP(F1, a, b, c, d, in[ 0]+0xd76aa478,  7);
 129     MD5STEP(F1, d, a, b, c, in[ 1]+0xe8c7b756, 12);
 130     MD5STEP(F1, c, d, a, b, in[ 2]+0x242070db, 17);
 131     MD5STEP(F1, b, c, d, a, in[ 3]+0xc1bdceee, 22);
 132     MD5STEP(F1, a, b, c, d, in[ 4]+0xf57c0faf,  7);
 133     MD5STEP(F1, d, a, b, c, in[ 5]+0x4787c62a, 12);
 134     MD5STEP(F1, c, d, a, b, in[ 6]+0xa8304613, 17);
 135     MD5STEP(F1, b, c, d, a, in[ 7]+0xfd469501, 22);
 136     MD5STEP(F1, a, b, c, d, in[ 8]+0x698098d8,  7);
 137     MD5STEP(F1, d, a, b, c, in[ 9]+0x8b44f7af, 12);
 138     MD5STEP(F1, c, d, a, b, in[10]+0xffff5bb1, 17);
 139     MD5STEP(F1, b, c, d, a, in[11]+0x895cd7be, 22);
 140     MD5STEP(F1, a, b, c, d, in[12]+0x6b901122,  7);
 141     MD5STEP(F1, d, a, b, c, in[13]+0xfd987193, 12);
 142     MD5STEP(F1, c, d, a, b, in[14]+0xa679438e, 17);
 143     MD5STEP(F1, b, c, d, a, in[15]+0x49b40821, 22);
 144
 145     MD5STEP(F2, a, b, c, d, in[ 1]+0xf61e2562,  5);
 146     MD5STEP(F2, d, a, b, c, in[ 6]+0xc040b340,  9);
 147     MD5STEP(F2, c, d, a, b, in[11]+0x265e5a51, 14);
 148     MD5STEP(F2, b, c, d, a, in[ 0]+0xe9b6c7aa, 20);
 149     MD5STEP(F2, a, b, c, d, in[ 5]+0xd62f105d,  5);
 150     MD5STEP(F2, d, a, b, c, in[10]+0x02441453,  9);
 151     MD5STEP(F2, c, d, a, b, in[15]+0xd8a1e681, 14);
 152     MD5STEP(F2, b, c, d, a, in[ 4]+0xe7d3fbc8, 20);
 153     MD5STEP(F2, a, b, c, d, in[ 9]+0x21e1cde6,  5);
 154     MD5STEP(F2, d, a, b, c, in[14]+0xc33707d6,  9);
 155     MD5STEP(F2, c, d, a, b, in[ 3]+0xf4d50d87, 14);
 156     MD5STEP(F2, b, c, d, a, in[ 8]+0x455a14ed, 20);
 157     MD5STEP(F2, a, b, c, d, in[13]+0xa9e3e905,  5);
 158     MD5STEP(F2, d, a, b, c, in[ 2]+0xfcefa3f8,  9);
 159     MD5STEP(F2, c, d, a, b, in[ 7]+0x676f02d9, 14);
 160     MD5STEP(F2, b, c, d, a, in[12]+0x8d2a4c8a, 20);
 161
 162     MD5STEP(F3, a, b, c, d, in[ 5]+0xfffa3942,  4);
 163     MD5STEP(F3, d, a, b, c, in[ 8]+0x8771f681, 11);
 164     MD5STEP(F3, c, d, a, b, in[11]+0x6d9d6122, 16);
 165     MD5STEP(F3, b, c, d, a, in[14]+0xfde5380c, 23);
 166     MD5STEP(F3, a, b, c, d, in[ 1]+0xa4beea44,  4);
 167     MD5STEP(F3, d, a, b, c, in[ 4]+0x4bdecfa9, 11);
 168     MD5STEP(F3, c, d, a, b, in[ 7]+0xf6bb4b60, 16);
 169     MD5STEP(F3, b, c, d, a, in[10]+0xbebfbc70, 23);
 170     MD5STEP(F3, a, b, c, d, in[13]+0x289b7ec6,  4);
 171     MD5STEP(F3, d, a, b, c, in[ 0]+0xeaa127fa, 11);
 172     MD5STEP(F3, c, d, a, b, in[ 3]+0xd4ef3085, 16);
 173     MD5STEP(F3, b, c, d, a, in[ 6]+0x04881d05, 23);
 174     MD5STEP(F3, a, b, c, d, in[ 9]+0xd9d4d039,  4);
 175     MD5STEP(F3, d, a, b, c, in[12]+0xe6db99e5, 11);
 176     MD5STEP(F3, c, d, a, b, in[15]+0x1fa27cf8, 16);
 177     MD5STEP(F3, b, c, d, a, in[ 2]+0xc4ac5665, 23);
 178
 179     MD5STEP(F4, a, b, c, d, in[ 0]+0xf4292244,  6);
 180     MD5STEP(F4, d, a, b, c, in[ 7]+0x432aff97, 10);
 181     MD5STEP(F4, c, d, a, b, in[14]+0xab9423a7, 15);
 182     MD5STEP(F4, b, c, d, a, in[ 5]+0xfc93a039, 21);
 183     MD5STEP(F4, a, b, c, d, in[12]+0x655b59c3,  6);
 184     MD5STEP(F4, d, a, b, c, in[ 3]+0x8f0ccc92, 10);
 185     MD5STEP(F4, c, d, a, b, in[10]+0xffeff47d, 15);
 186     MD5STEP(F4, b, c, d, a, in[ 1]+0x85845dd1, 21);
 187     MD5STEP(F4, a, b, c, d, in[ 8]+0x6fa87e4f,  6);
 188     MD5STEP(F4, d, a, b, c, in[15]+0xfe2ce6e0, 10);
 189     MD5STEP(F4, c, d, a, b, in[ 6]+0xa3014314, 15);
 190     MD5STEP(F4, b, c, d, a, in[13]+0x4e0811a1, 21);
 191     MD5STEP(F4, a, b, c, d, in[ 4]+0xf7537e82,  6);
 192     MD5STEP(F4, d, a, b, c, in[11]+0xbd3af235, 10);
 193     MD5STEP(F4, c, d, a, b, in[ 2]+0x2ad7d2bb, 15);
 194     MD5STEP(F4, b, c, d, a, in[ 9]+0xeb86d391, 21);
 195
 196     buf[0] += a;
 197     buf[1] += b;
 198     buf[2] += c;
 199     buf[3] += d;
 200 }
 201
 202 MD5::MD5()
 203 {
 204     testMD5();
 205     m_buf[0] = 0x67452301;
 206     m_buf[1] = 0xefcdab89;
 207     m_buf[2] = 0x98badcfe;
 208     m_buf[3] = 0x10325476;
 209     m_bits[0] = 0;
 210     m_bits[1] = 0;
 211     memset(m_in, 0, sizeof(m_in));
 212     ASSERT_WITH_MESSAGE(!(reinterpret_cast<uintptr_t>(m_in) % sizeof(uint32_t)), "alignment error of m_in");
 213 }
 214
 215 void MD5::addBytes(const uint8_t* input, size_t length)
 216 {
 217     const uint8_t* buf = input;
 218
 219     // Update bitcount
 220     uint32_t t = m_bits[0];
 221     m_bits[0] = t + (length << 3);
 222     if (m_bits[0] < t)
 223         m_bits[1]++; // Carry from low to high
 224     m_bits[1] += length >> 29;
 225
 226     t = (t >> 3) & 0x3f; // Bytes already in shsInfo->data
 227
 228     // Handle any leading odd-sized chunks
 229
 230     if (t) {
 231         uint8_t* p = m_in + t;
 232
 233         t = 64 - t;
 234         if (length < t) {
 235             memcpy(p, buf, length);
 236             return;
 237         }
 238         memcpy(p, buf, t);
 239         reverseBytes(m_in, 16);
 240         MD5Transform(m_buf, reinterpret_cast<uint32_t*>(m_in)); // m_in is 4-byte aligned.
 241         buf += t;
 242         length -= t;
 243     }
 244
 245     // Process data in 64-byte chunks
 246
 247     while (length >= 64) {
 248         memcpy(m_in, buf, 64);
 249         reverseBytes(m_in, 16);
 250         MD5Transform(m_buf, reinterpret_cast<uint32_t*>(m_in)); // m_in is 4-byte aligned.
 251         buf += 64;
 252         length -= 64;
 253     }
 254
 255     // Handle any remaining bytes of data.
 256     memcpy(m_in, buf, length);
 257 }
 258
 259 Vector<uint8_t, 16> MD5::checksum()
 260 {
 261     // Compute number of bytes mod 64
 262     unsigned count = (m_bits[0] >> 3) & 0x3F;
 263
 264     // Set the first char of padding to 0x80.  This is safe since there is
 265     // always at least one byte free
 266     uint8_t* p = m_in + count;
 267     *p++ = 0x80;
 268
 269     // Bytes of padding needed to make 64 bytes
 270     count = 64 - 1 - count;
 271
 272     // Pad out to 56 mod 64
 273     if (count < 8) {
 274         // Two lots of padding:  Pad the first block to 64 bytes
 275         memset(p, 0, count);
 276         reverseBytes(m_in, 16);
 277         MD5Transform(m_buf, reinterpret_cast<uint32_t *>(m_in)); // m_in is 4-byte aligned.
 278
 279         // Now fill the next block with 56 bytes
 280         memset(m_in, 0, 56);
 281     } else {
 282         // Pad block to 56 bytes
 283         memset(p, 0, count - 8);
 284     }
 285     reverseBytes(m_in, 14);
 286
 287     // Append length in bits and transform
 288     // m_in is 4-byte aligned.
 289     (reinterpret_cast<uint32_t*>(m_in))[14] = m_bits[0];
 290     (reinterpret_cast<uint32_t*>(m_in))[15] = m_bits[1];
 291
 292     MD5Transform(m_buf, reinterpret_cast<uint32_t*>(m_in));
 293     reverseBytes(reinterpret_cast<uint8_t*>(m_buf), 4);
 294     Vector<uint8_t, 16> digest;
 295     digest.append(reinterpret_cast<uint8_t*>(m_buf), 16);
 296
 297     // In case it's sensitive
 298     memset(m_buf, 0, sizeof(m_buf));
 299     memset(m_bits, 0, sizeof(m_bits));
 300     memset(m_in, 0, sizeof(m_in));
 301     return digest;
 302 }
 303
 304 } // namespace WTF