Md5Sum.cc

Go to the documentation of this file.

#include <utl/Md5Sum.h>
#include <string>
#include <sstream>
#include <utility>
#include <algorithm>

using namespace std;


namespace utl {

  // details that are in defines in the original RSA code. They are mostly
  // copied literally to reduce the risk of bugs.
  namespace {

    const unsigned char gPadding[Md5Sum::kBufferSize] = { 0x80 };

    const unsigned int s11 = 7;
    const unsigned int s12 = 12;
    const unsigned int s13 = 17;
    const unsigned int s14 = 22;
    const unsigned int s21 = 5;
    const unsigned int s22 = 9;
    const unsigned int s23 = 14;
    const unsigned int s24 = 20;
    const unsigned int s31 = 4;
    const unsigned int s32 = 11;
    const unsigned int s33 = 16;
    const unsigned int s34 = 23;
    const unsigned int s41 = 6;
    const unsigned int s42 = 10;
    const unsigned int s43 = 15;
    const unsigned int s44 = 21;


    inline
    unsigned int
    F(const unsigned int x, const unsigned int y, const unsigned int z)
    {
      return (x & y) | (~x & z);
    }


    inline
    unsigned int
    G(const unsigned int x, const unsigned int y, const unsigned int z)
    {
      return (x & z) | (y & ~z);
    }


    inline
    unsigned int
    H(const unsigned int x, const unsigned int y, const unsigned int z)
    {
      return x ^ y ^ z;
    }


    inline
    unsigned int
    I(const unsigned int x, const unsigned int y, const unsigned int z)
    {
      return y ^ (x | ~z);
    }


    inline
    unsigned int
    RotateLeft(const unsigned int x, const unsigned int n)
    {
      return (x << n) | (x >> (32-n));
    }


    inline
    void
    FF(unsigned int& a,
       const unsigned int b,
       const unsigned int c,
       const unsigned int d,
       const unsigned int x,
       const unsigned int s,
       const unsigned int ac)
    {
      a += F(b, c, d) + x + ac;
      a = RotateLeft(a, s);
      a += b;
    }


    inline
    void
    GG(unsigned int& a,
       const unsigned int b,
       const unsigned int c,
       const unsigned int d,
       const unsigned int x,
       const unsigned int s,
       const unsigned int ac)
    {
      a += G(b, c, d) + x + ac;
      a = RotateLeft(a, s);
      a += b;
    }


    inline
    void
    HH(unsigned int& a,
       const unsigned int b,
       const unsigned int c,
       const unsigned int d,
       const unsigned int x,
       const unsigned int s,
       const unsigned int ac)
    {
      a += H(b, c, d) + x + ac;
      a = RotateLeft(a, s);
      a += b;
    }


    inline
    void
    II(unsigned int& a,
       const unsigned int b,
       const unsigned int c,
       const unsigned int d,
       const unsigned int x,
       const unsigned int s,
       const unsigned int ac)
    {
      a += I(b, c, d) + x + ac;
      a = RotateLeft(a, s);
      a += b;
    }


    inline
    void
    UIntToUChar(unsigned char* const outBuffer, const unsigned int input)
    {
      outBuffer[0] = input & 0xff;
      outBuffer[1] = (input >> 8) & 0xff;
      outBuffer[2] = (input >> 16) & 0xff;
      outBuffer[3] = (input >> 24) & 0xff;
    }


    const char gHexTable[] = "0123456789abcdef";

  }


  void
  Md5Sum::Clear()
  {
    fFinalized = false;

    fCountLow = 0;
    fCountHigh = 0;

    // initialize with magic numbers
    fStateA = 0x67452301;
    fStateB = 0xefcdab89;
    fStateC = 0x98badcfe;
    fStateD = 0x10325476;
  }


  void
  Md5Sum::AddDataRange(const unsigned char* const begin, const unsigned char* const end)
  {
    if (fFinalized)
      throw WrongStageException("Cannot add data to Md5Sum object after extracting digest");

    if (begin > end)
      throw InvalidIteratorException("begin > end");

    // bytecount mod buffer size from bitcount
    unsigned int index = BufferIndex();

    // update number of bits
    const unsigned int length = end - begin;
    const unsigned int bits = (length << 3);
    fCountLow += bits;
    if (fCountLow < bits) // overflow
      ++fCountHigh;
    fCountHigh += (length >> 29); // top 3 bits are carried over

    for (const unsigned char* p = begin; p < end; ++p) {
      fBuffer[index] = *p;
      ++index;
      if (index == kBufferSize) {
        ProcessBuffer();
        index = 0;
      }
    }
  }


  void
  Md5Sum::ProcessBuffer()
  {
    const unsigned int scratchSize = 16; // buffer size / 4
    unsigned int x[scratchSize];

    for (unsigned int i = 0; i < scratchSize; ++i) {
      const unsigned int i4 = 4*i;
      x[i] = fBuffer[i4] |
             fBuffer[i4+1] << 8 |
             fBuffer[i4+2] << 16 |
             fBuffer[i4+3] << 24;
    }

    unsigned int a = fStateA;
    unsigned int b = fStateB;
    unsigned int c = fStateC;
    unsigned int d = fStateD;

    /* Round 1 */
    FF(a, b, c, d, x[ 0], s11, 0xd76aa478); /* 1 */
    FF(d, a, b, c, x[ 1], s12, 0xe8c7b756); /* 2 */
    FF(c, d, a, b, x[ 2], s13, 0x242070db); /* 3 */
    FF(b, c, d, a, x[ 3], s14, 0xc1bdceee); /* 4 */
    FF(a, b, c, d, x[ 4], s11, 0xf57c0faf); /* 5 */
    FF(d, a, b, c, x[ 5], s12, 0x4787c62a); /* 6 */
    FF(c, d, a, b, x[ 6], s13, 0xa8304613); /* 7 */
    FF(b, c, d, a, x[ 7], s14, 0xfd469501); /* 8 */
    FF(a, b, c, d, x[ 8], s11, 0x698098d8); /* 9 */
    FF(d, a, b, c, x[ 9], s12, 0x8b44f7af); /* 10 */
    FF(c, d, a, b, x[10], s13, 0xffff5bb1); /* 11 */
    FF(b, c, d, a, x[11], s14, 0x895cd7be); /* 12 */
    FF(a, b, c, d, x[12], s11, 0x6b901122); /* 13 */
    FF(d, a, b, c, x[13], s12, 0xfd987193); /* 14 */
    FF(c, d, a, b, x[14], s13, 0xa679438e); /* 15 */
    FF(b, c, d, a, x[15], s14, 0x49b40821); /* 16 */

   /* Round 2 */
    GG(a, b, c, d, x[ 1], s21, 0xf61e2562); /* 17 */
    GG(d, a, b, c, x[ 6], s22, 0xc040b340); /* 18 */
    GG(c, d, a, b, x[11], s23, 0x265e5a51); /* 19 */
    GG(b, c, d, a, x[ 0], s24, 0xe9b6c7aa); /* 20 */
    GG(a, b, c, d, x[ 5], s21, 0xd62f105d); /* 21 */
    GG(d, a, b, c, x[10], s22, 0x02441453); /* 22 */
    GG(c, d, a, b, x[15], s23, 0xd8a1e681); /* 23 */
    GG(b, c, d, a, x[ 4], s24, 0xe7d3fbc8); /* 24 */
    GG(a, b, c, d, x[ 9], s21, 0x21e1cde6); /* 25 */
    GG(d, a, b, c, x[14], s22, 0xc33707d6); /* 26 */
    GG(c, d, a, b, x[ 3], s23, 0xf4d50d87); /* 27 */
    GG(b, c, d, a, x[ 8], s24, 0x455a14ed); /* 28 */
    GG(a, b, c, d, x[13], s21, 0xa9e3e905); /* 29 */
    GG(d, a, b, c, x[ 2], s22, 0xfcefa3f8); /* 30 */
    GG(c, d, a, b, x[ 7], s23, 0x676f02d9); /* 31 */
    GG(b, c, d, a, x[12], s24, 0x8d2a4c8a); /* 32 */

    /* Round 3 */
    HH(a, b, c, d, x[ 5], s31, 0xfffa3942); /* 33 */
    HH(d, a, b, c, x[ 8], s32, 0x8771f681); /* 34 */
    HH(c, d, a, b, x[11], s33, 0x6d9d6122); /* 35 */
    HH(b, c, d, a, x[14], s34, 0xfde5380c); /* 36 */
    HH(a, b, c, d, x[ 1], s31, 0xa4beea44); /* 37 */
    HH(d, a, b, c, x[ 4], s32, 0x4bdecfa9); /* 38 */
    HH(c, d, a, b, x[ 7], s33, 0xf6bb4b60); /* 39 */
    HH(b, c, d, a, x[10], s34, 0xbebfbc70); /* 40 */
    HH(a, b, c, d, x[13], s31, 0x289b7ec6); /* 41 */
    HH(d, a, b, c, x[ 0], s32, 0xeaa127fa); /* 42 */
    HH(c, d, a, b, x[ 3], s33, 0xd4ef3085); /* 43 */
    HH(b, c, d, a, x[ 6], s34, 0x04881d05); /* 44 */
    HH(a, b, c, d, x[ 9], s31, 0xd9d4d039); /* 45 */
    HH(d, a, b, c, x[12], s32, 0xe6db99e5); /* 46 */
    HH(c, d, a, b, x[15], s33, 0x1fa27cf8); /* 47 */
    HH(b, c, d, a, x[ 2], s34, 0xc4ac5665); /* 48 */

    /* Round 4 */
    II(a, b, c, d, x[ 0], s41, 0xf4292244); /* 49 */
    II(d, a, b, c, x[ 7], s42, 0x432aff97); /* 50 */
    II(c, d, a, b, x[14], s43, 0xab9423a7); /* 51 */
    II(b, c, d, a, x[ 5], s44, 0xfc93a039); /* 52 */
    II(a, b, c, d, x[12], s41, 0x655b59c3); /* 53 */
    II(d, a, b, c, x[ 3], s42, 0x8f0ccc92); /* 54 */
    II(c, d, a, b, x[10], s43, 0xffeff47d); /* 55 */
    II(b, c, d, a, x[ 1], s44, 0x85845dd1); /* 56 */
    II(a, b, c, d, x[ 8], s41, 0x6fa87e4f); /* 57 */
    II(d, a, b, c, x[15], s42, 0xfe2ce6e0); /* 58 */
    II(c, d, a, b, x[ 6], s43, 0xa3014314); /* 59 */
    II(b, c, d, a, x[13], s44, 0x4e0811a1); /* 60 */
    II(a, b, c, d, x[ 4], s41, 0xf7537e82); /* 61 */
    II(d, a, b, c, x[11], s42, 0xbd3af235); /* 62 */
    II(c, d, a, b, x[ 2], s43, 0x2ad7d2bb); /* 63 */
    II(b, c, d, a, x[ 9], s44, 0xeb86d391); /* 64 */

    fStateA += a;
    fStateB += b;
    fStateC += c;
    fStateD += d;
  }


  Md5Sum::IteratorPair
  Md5Sum::GetRawDigest()
  {
    if (!fFinalized) {
      unsigned char bitCountBuffer[8];

      UIntToUChar(bitCountBuffer, fCountLow);
      UIntToUChar(bitCountBuffer + 4, fCountHigh);

      int length = int(kBufferSize - 8) - int(BufferIndex());
      // message always has to be padded with one bit (0x80)
      if (length < 1)
        length += kBufferSize;
      AddDataRange(gPadding, gPadding + length);
      // the remaining 8 bits are for the bitcount
      AddDataRange(bitCountBuffer, bitCountBuffer + 8);

      UIntToUChar(fDigest, fStateA);
      UIntToUChar(fDigest + 4, fStateB);
      UIntToUChar(fDigest + 8, fStateC);
      UIntToUChar(fDigest + 12, fStateD);

      // wipe out state
      Clear();
      fFinalized = true;
    }

    return make_pair(fDigest, fDigest + kDigestSize);
  }


  string
  Md5Sum::GetHexDigest()
  {
    string digest;
    IteratorPair iters = GetRawDigest();

    for (Iterator cur = iters.first; cur != iters.second; ++cur) {
      digest.push_back(gHexTable[(*cur >> 4) % 16]);
      digest.push_back(gHexTable[*cur % 16]);
    }

    return digest;
  }

}