/* rmd.c - Functions to compute RipeMD-160 message digest
   of files or memory blocks.
   Copyright (C) 1995, 1996, 2000 Free Software Foundation, Inc.
   NOTE: The canonical source of this file is maintained with the GNU C
   Library.  Bugs can be reported to bug-glibc@prep.ai.mit.edu.

   This program is free software; you can redistribute it and/or modify it
   under the terms of the GNU General Public License as published by the
   Free Software Foundation; either version 2, or (at your option) any
   later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software Foundation,
   Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */

/* md5.c Written by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 1995.  */
/* modified for ripemd-160 by Stefan Bender, 2000.  */

#ifdef HAVE_CONFIG_H
# include <config.h>
#endif

#include <sys/types.h>

#if STDC_HEADERS || defined _LIBC
# include <stdlib.h>
# include <string.h>
#else
# ifndef HAVE_MEMCPY
#  define memcpy(d, s, n) bcopy ((s), (d), (n))
# endif
#endif

#include "rmd.h"

#ifdef _LIBC
# include <endian.h>
# if __BYTE_ORDER == __BIG_ENDIAN
#  define WORDS_BIGENDIAN 1
# endif
#endif

#ifdef WORDS_BIGENDIAN
# define SWAP(n)                                                        \
    (((n) << 24) | (((n) & 0xff00) << 8) | (((n) >> 8) & 0xff00) | ((n) >> 24))
#else
# define SWAP(n) (n)
#endif
	
/* Initialize structure containing state of computation.  */
void rmd_init_ctx (struct rmd_ctx *ctx)
{
	ctx->A = 0x67452301UL;
	ctx->B = 0xefcdab89UL;
	ctx->C = 0x98badcfeUL;
	ctx->D = 0x10325476UL;
	ctx->E = 0xc3d2e1f0UL;

	ctx->total[0] = ctx->total[1] = 0;
	ctx->buflen = 0;

	return;
}

void rmd_compress(struct rmd_ctx *ctx, rmd_uint32 *X)
{
   rmd_uint32 aa = ctx->A,  bb = ctx->B,  cc = ctx->C,
		dd = ctx->D,  ee = ctx->E;
   rmd_uint32 aaa = ctx->A, bbb = ctx->B, ccc = ctx->C,
        ddd = ctx->D, eee = ctx->E;

   /* round 1 */
   FF(aa, bb, cc, dd, ee, X[ 0], 11);
   FF(ee, aa, bb, cc, dd, X[ 1], 14);
   FF(dd, ee, aa, bb, cc, X[ 2], 15);
   FF(cc, dd, ee, aa, bb, X[ 3], 12);
   FF(bb, cc, dd, ee, aa, X[ 4],  5);
   FF(aa, bb, cc, dd, ee, X[ 5],  8);
   FF(ee, aa, bb, cc, dd, X[ 6],  7);
   FF(dd, ee, aa, bb, cc, X[ 7],  9);
   FF(cc, dd, ee, aa, bb, X[ 8], 11);
   FF(bb, cc, dd, ee, aa, X[ 9], 13);
   FF(aa, bb, cc, dd, ee, X[10], 14);
   FF(ee, aa, bb, cc, dd, X[11], 15);
   FF(dd, ee, aa, bb, cc, X[12],  6);
   FF(cc, dd, ee, aa, bb, X[13],  7);
   FF(bb, cc, dd, ee, aa, X[14],  9);
   FF(aa, bb, cc, dd, ee, X[15],  8);
                             
   /* round 2 */
   GG(ee, aa, bb, cc, dd, X[ 7],  7);
   GG(dd, ee, aa, bb, cc, X[ 4],  6);
   GG(cc, dd, ee, aa, bb, X[13],  8);
   GG(bb, cc, dd, ee, aa, X[ 1], 13);
   GG(aa, bb, cc, dd, ee, X[10], 11);
   GG(ee, aa, bb, cc, dd, X[ 6],  9);
   GG(dd, ee, aa, bb, cc, X[15],  7);
   GG(cc, dd, ee, aa, bb, X[ 3], 15);
   GG(bb, cc, dd, ee, aa, X[12],  7);
   GG(aa, bb, cc, dd, ee, X[ 0], 12);
   GG(ee, aa, bb, cc, dd, X[ 9], 15);
   GG(dd, ee, aa, bb, cc, X[ 5],  9);
   GG(cc, dd, ee, aa, bb, X[ 2], 11);
   GG(bb, cc, dd, ee, aa, X[14],  7);
   GG(aa, bb, cc, dd, ee, X[11], 13);
   GG(ee, aa, bb, cc, dd, X[ 8], 12);

   /* round 3 */
   HH(dd, ee, aa, bb, cc, X[ 3], 11);
   HH(cc, dd, ee, aa, bb, X[10], 13);
   HH(bb, cc, dd, ee, aa, X[14],  6);
   HH(aa, bb, cc, dd, ee, X[ 4],  7);
   HH(ee, aa, bb, cc, dd, X[ 9], 14);
   HH(dd, ee, aa, bb, cc, X[15],  9);
   HH(cc, dd, ee, aa, bb, X[ 8], 13);
   HH(bb, cc, dd, ee, aa, X[ 1], 15);
   HH(aa, bb, cc, dd, ee, X[ 2], 14);
   HH(ee, aa, bb, cc, dd, X[ 7],  8);
   HH(dd, ee, aa, bb, cc, X[ 0], 13);
   HH(cc, dd, ee, aa, bb, X[ 6],  6);
   HH(bb, cc, dd, ee, aa, X[13],  5);
   HH(aa, bb, cc, dd, ee, X[11], 12);
   HH(ee, aa, bb, cc, dd, X[ 5],  7);
   HH(dd, ee, aa, bb, cc, X[12],  5);

   /* round 4 */
   II(cc, dd, ee, aa, bb, X[ 1], 11);
   II(bb, cc, dd, ee, aa, X[ 9], 12);
   II(aa, bb, cc, dd, ee, X[11], 14);
   II(ee, aa, bb, cc, dd, X[10], 15);
   II(dd, ee, aa, bb, cc, X[ 0], 14);
   II(cc, dd, ee, aa, bb, X[ 8], 15);
   II(bb, cc, dd, ee, aa, X[12],  9);
   II(aa, bb, cc, dd, ee, X[ 4],  8);
   II(ee, aa, bb, cc, dd, X[13],  9);
   II(dd, ee, aa, bb, cc, X[ 3], 14);
   II(cc, dd, ee, aa, bb, X[ 7],  5);
   II(bb, cc, dd, ee, aa, X[15],  6);
   II(aa, bb, cc, dd, ee, X[14],  8);
   II(ee, aa, bb, cc, dd, X[ 5],  6);
   II(dd, ee, aa, bb, cc, X[ 6],  5);
   II(cc, dd, ee, aa, bb, X[ 2], 12);

   /* round 5 */
   JJ(bb, cc, dd, ee, aa, X[ 4],  9);
   JJ(aa, bb, cc, dd, ee, X[ 0], 15);
   JJ(ee, aa, bb, cc, dd, X[ 5],  5);
   JJ(dd, ee, aa, bb, cc, X[ 9], 11);
   JJ(cc, dd, ee, aa, bb, X[ 7],  6);
   JJ(bb, cc, dd, ee, aa, X[12],  8);
   JJ(aa, bb, cc, dd, ee, X[ 2], 13);
   JJ(ee, aa, bb, cc, dd, X[10], 12);
   JJ(dd, ee, aa, bb, cc, X[14],  5);
   JJ(cc, dd, ee, aa, bb, X[ 1], 12);
   JJ(bb, cc, dd, ee, aa, X[ 3], 13);
   JJ(aa, bb, cc, dd, ee, X[ 8], 14);
   JJ(ee, aa, bb, cc, dd, X[11], 11);
   JJ(dd, ee, aa, bb, cc, X[ 6],  8);
   JJ(cc, dd, ee, aa, bb, X[15],  5);
   JJ(bb, cc, dd, ee, aa, X[13],  6);

   /* parallel round 1 */
   JJJ(aaa, bbb, ccc, ddd, eee, X[ 5],  8);
   JJJ(eee, aaa, bbb, ccc, ddd, X[14],  9);
   JJJ(ddd, eee, aaa, bbb, ccc, X[ 7],  9);
   JJJ(ccc, ddd, eee, aaa, bbb, X[ 0], 11);
   JJJ(bbb, ccc, ddd, eee, aaa, X[ 9], 13);
   JJJ(aaa, bbb, ccc, ddd, eee, X[ 2], 15);
   JJJ(eee, aaa, bbb, ccc, ddd, X[11], 15);
   JJJ(ddd, eee, aaa, bbb, ccc, X[ 4],  5);
   JJJ(ccc, ddd, eee, aaa, bbb, X[13],  7);
   JJJ(bbb, ccc, ddd, eee, aaa, X[ 6],  7);
   JJJ(aaa, bbb, ccc, ddd, eee, X[15],  8);
   JJJ(eee, aaa, bbb, ccc, ddd, X[ 8], 11);
   JJJ(ddd, eee, aaa, bbb, ccc, X[ 1], 14);
   JJJ(ccc, ddd, eee, aaa, bbb, X[10], 14);
   JJJ(bbb, ccc, ddd, eee, aaa, X[ 3], 12);
   JJJ(aaa, bbb, ccc, ddd, eee, X[12],  6);

   /* parallel round 2 */
   III(eee, aaa, bbb, ccc, ddd, X[ 6],  9); 
   III(ddd, eee, aaa, bbb, ccc, X[11], 13);
   III(ccc, ddd, eee, aaa, bbb, X[ 3], 15);
   III(bbb, ccc, ddd, eee, aaa, X[ 7],  7);
   III(aaa, bbb, ccc, ddd, eee, X[ 0], 12);
   III(eee, aaa, bbb, ccc, ddd, X[13],  8);
   III(ddd, eee, aaa, bbb, ccc, X[ 5],  9);
   III(ccc, ddd, eee, aaa, bbb, X[10], 11);
   III(bbb, ccc, ddd, eee, aaa, X[14],  7);
   III(aaa, bbb, ccc, ddd, eee, X[15],  7);
   III(eee, aaa, bbb, ccc, ddd, X[ 8], 12);
   III(ddd, eee, aaa, bbb, ccc, X[12],  7);
   III(ccc, ddd, eee, aaa, bbb, X[ 4],  6);
   III(bbb, ccc, ddd, eee, aaa, X[ 9], 15);
   III(aaa, bbb, ccc, ddd, eee, X[ 1], 13);
   III(eee, aaa, bbb, ccc, ddd, X[ 2], 11);

   /* parallel round 3 */
   HHH(ddd, eee, aaa, bbb, ccc, X[15],  9);
   HHH(ccc, ddd, eee, aaa, bbb, X[ 5],  7);
   HHH(bbb, ccc, ddd, eee, aaa, X[ 1], 15);
   HHH(aaa, bbb, ccc, ddd, eee, X[ 3], 11);
   HHH(eee, aaa, bbb, ccc, ddd, X[ 7],  8);
   HHH(ddd, eee, aaa, bbb, ccc, X[14],  6);
   HHH(ccc, ddd, eee, aaa, bbb, X[ 6],  6);
   HHH(bbb, ccc, ddd, eee, aaa, X[ 9], 14);
   HHH(aaa, bbb, ccc, ddd, eee, X[11], 12);
   HHH(eee, aaa, bbb, ccc, ddd, X[ 8], 13);
   HHH(ddd, eee, aaa, bbb, ccc, X[12],  5);
   HHH(ccc, ddd, eee, aaa, bbb, X[ 2], 14);
   HHH(bbb, ccc, ddd, eee, aaa, X[10], 13);
   HHH(aaa, bbb, ccc, ddd, eee, X[ 0], 13);
   HHH(eee, aaa, bbb, ccc, ddd, X[ 4],  7);
   HHH(ddd, eee, aaa, bbb, ccc, X[13],  5);

   /* parallel round 4 */   
   GGG(ccc, ddd, eee, aaa, bbb, X[ 8], 15);
   GGG(bbb, ccc, ddd, eee, aaa, X[ 6],  5);
   GGG(aaa, bbb, ccc, ddd, eee, X[ 4],  8);
   GGG(eee, aaa, bbb, ccc, ddd, X[ 1], 11);
   GGG(ddd, eee, aaa, bbb, ccc, X[ 3], 14);
   GGG(ccc, ddd, eee, aaa, bbb, X[11], 14);
   GGG(bbb, ccc, ddd, eee, aaa, X[15],  6);
   GGG(aaa, bbb, ccc, ddd, eee, X[ 0], 14);
   GGG(eee, aaa, bbb, ccc, ddd, X[ 5],  6);
   GGG(ddd, eee, aaa, bbb, ccc, X[12],  9);
   GGG(ccc, ddd, eee, aaa, bbb, X[ 2], 12);
   GGG(bbb, ccc, ddd, eee, aaa, X[13],  9);
   GGG(aaa, bbb, ccc, ddd, eee, X[ 9], 12);
   GGG(eee, aaa, bbb, ccc, ddd, X[ 7],  5);
   GGG(ddd, eee, aaa, bbb, ccc, X[10], 15);
   GGG(ccc, ddd, eee, aaa, bbb, X[14],  8);

   /* parallel round 5 */
   FFF(bbb, ccc, ddd, eee, aaa, X[12] ,  8);
   FFF(aaa, bbb, ccc, ddd, eee, X[15] ,  5);
   FFF(eee, aaa, bbb, ccc, ddd, X[10] , 12);
   FFF(ddd, eee, aaa, bbb, ccc, X[ 4] ,  9);
   FFF(ccc, ddd, eee, aaa, bbb, X[ 1] , 12);
   FFF(bbb, ccc, ddd, eee, aaa, X[ 5] ,  5);
   FFF(aaa, bbb, ccc, ddd, eee, X[ 8] , 14);
   FFF(eee, aaa, bbb, ccc, ddd, X[ 7] ,  6);
   FFF(ddd, eee, aaa, bbb, ccc, X[ 6] ,  8);
   FFF(ccc, ddd, eee, aaa, bbb, X[ 2] , 13);
   FFF(bbb, ccc, ddd, eee, aaa, X[13] ,  6);
   FFF(aaa, bbb, ccc, ddd, eee, X[14] ,  5);
   FFF(eee, aaa, bbb, ccc, ddd, X[ 0] , 15);
   FFF(ddd, eee, aaa, bbb, ccc, X[ 3] , 13);
   FFF(ccc, ddd, eee, aaa, bbb, X[ 9] , 11);
   FFF(bbb, ccc, ddd, eee, aaa, X[11] , 11);

   /* combine results */
   ddd += cc + ctx->B;               /* final result for ctx[0] */
   ctx->B = ctx->C + dd + eee;
   ctx->C = ctx->D + ee + aaa;
   ctx->D = ctx->E + aa + bbb;
   ctx->E = ctx->A + bb + ccc;
   ctx->A = ddd;

   return;
}

/********************************************************************/

/*	functions modified from md5.c	*/

/*	Put result from CTX in first 16 bytes following RESBUF.  The result
	must be in little endian byte order.

	IMPORTANT: On some systems it is required that RESBUF is correctly
	aligned for a 32 bits value.  */
void *rmd_read_ctx (const struct rmd_ctx *ctx, void *resbuf)
{
	((rmd_uint32 *) resbuf)[0] = SWAP (ctx->A);
	((rmd_uint32 *) resbuf)[1] = SWAP (ctx->B);
	((rmd_uint32 *) resbuf)[2] = SWAP (ctx->C);
	((rmd_uint32 *) resbuf)[3] = SWAP (ctx->D);
	((rmd_uint32 *) resbuf)[4] = SWAP (ctx->E);

	return resbuf;
}

void *rmd_finish_ctx(struct rmd_ctx *ctx, void *resbuf)
{
   unsigned int i;                                 /* counter       */
   rmd_uint32	X[16];                             /* message words */
   rmd_uint32	lswlen = ctx->total[0], mswlen = ctx->total[1];
   byte			*strptr = ctx->buffer;
   
   memset(X, 0, 16*sizeof(rmd_uint32));

   /* put bytes from strptr into X */
   for (i=0; i<(lswlen&63); i++) {
      /* byte i goes into word X[i div 4] at pos.  8*(i mod 4)  */
      X[i>>2] ^= (rmd_uint32) *strptr++ << (8 * (i&3));
   }

   /* append the bit m_n == 1 */
   X[(lswlen>>2)&15] ^= (rmd_uint32)1 << (8*(lswlen&3) + 7);

   if ((lswlen & 63) > 55) {
      /* length goes to next block */
      rmd_compress(ctx, X);
      memset(X, 0, 16*sizeof(rmd_uint32));
   }

   /* append length in bits*/
   X[14] = lswlen << 3;
   X[15] = (lswlen >> 29) | (mswlen << 3);
   rmd_compress(ctx, X);

   return rmd_read_ctx(ctx, resbuf);;
}

void *rmd_buffer(void *buffer, size_t len, void *resblock)
{
	struct rmd_ctx	ctx;   				/* contains (A, B, C, D(, E))   */
     rmd_uint32		length;              /* length in bytes of message   */

   /* initialize */
   rmd_init_ctx(&ctx);
   length = (rmd_uint32)len;

	rmd_process_bytes(buffer, length, &ctx);
	
	return rmd_finish_ctx(&ctx, resblock);
}

void rmd_process_bytes(byte *buffer, rmd_uint32 len,
						struct rmd_ctx *ctx)
{
	rmd_uint32		X[16];              /* current 16-word chunk        */
	unsigned int	i;               	/* counter                      */
	rmd_uint32		nbytes;             /* # of bytes not yet processed */
	
	/* process message in 16-word chunks */
   for (nbytes=len; nbytes > 63; nbytes-=64) {
      for (i=0; i<16; i++) {
         X[i] = BYTES_TO_DWORD(buffer);
         buffer += 4;
      }
      rmd_compress(ctx, X);
   }                                    /* length mod 64 bytes left */
   
   ctx->total[0] += len;
   if(ctx->total[0] < len) ++ctx->total[1];
   
   if(nbytes > 0) {
	   memcpy(ctx->buffer, buffer, nbytes);
	   ctx->buflen = nbytes;
	}

   return;
}

int rmd_stream(FILE *stream, void *resblock)
{
	struct rmd_ctx	ctx;
	size_t			sum;
	char	buffer[BLOCKSIZE + 72];
	
  /* Initialize the computation context.  */
  rmd_init_ctx (&ctx);

  /* Iterate over full file contents.  */
  while (1)
    {
      /* We read the file in blocks of BLOCKSIZE bytes.  One call of the
         computation function processes the whole buffer so that with the
         next round of the loop another block can be read.  */
      size_t n;
      sum = 0;

      /* Read block.  Take care for partial reads.  */
      do
        {
          n = fread (buffer + sum, 1, BLOCKSIZE - sum, stream);
          sum += n;
        }
      while (sum < BLOCKSIZE && n != 0);
      if (n == 0 && ferror (stream))
        return 1;

      /* If end of file is reached, end the loop.  */
      if (n == 0)
        break;

      /* Process buffer with BLOCKSIZE bytes.  Note that
                        BLOCKSIZE % 64 == 0
       */
      rmd_process_bytes (buffer, BLOCKSIZE, &ctx);
    }

  /* Add the last bytes if necessary.  */
  if (sum > 0)
    rmd_process_bytes (buffer, sum, &ctx);

  /* Construct result in desired memory.  */
  rmd_finish_ctx (&ctx, resblock);

  return 0;
}
