dbsql/test/scr050/tcl_md5.c

/*
 * DBSQL uses this code for testing only.  It is not a part of
 * the DBSQL library.  This file implements two new TCL commands
 * "md5" and "md5file" that compute md5 checksums on arbitrary text
 * and on complete files.  These commands are used by the "testfixture"
 * program to help verify the correct operation of the DBSQL library.
 *
 * The original use of these TCL commands was to test the ROLLBACK
 * feature of DBSQL.  First compute the MD5-checksum of the database.
 * Then make some changes but rollback the changes rather than commit
 * them.  Compute a second MD5-checksum of the file and verify that the
 * two checksums are the same.  Such is the original use of this code.
 * New uses may have been added since this comment was written.
 */
/*
 * 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.
 */

#ifndef NO_SYSTEM_INCLUDES
#include <ctype.h>
#endif

#include <tcl.h>
#include <stdlib.h>
#include <string.h>
#include <dbsql.h>


/* The four core functions - F1 is optimized somewhat */
#define F1(x, y, z) (z ^ (x & (y ^ z))) /* F1(x, y, z) (x & y | ~x & 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 )

struct Context {
	u_int32_t buf[4];
	u_int32_t bits[2];
	unsigned char in[64];
};
typedef char MD5Context[88];

/*
 * Note: this code is harmless on little-endian machines.
 */
static void
byteReverse(buf, longs)
	unsigned char *buf;
	unsigned longs;
{
	u_int32_t t;
	do {
		t = (u_int32_t)((unsigned)buf[3] << 8 | buf[2]) << 16 |
			((unsigned)buf[1] << 8 | buf[0]);
		*(u_int32_t *)buf = t;
		buf += 4;
	} while (--longs);
}

/*
 * 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.
 */
static void
MD5Transform(buf, in)
	u_int32_t buf[4];
	const u_int32_t in[16];
{
	register u_int32_t a, b, c, d;

	a = buf[0];
	b = buf[1];
	c = buf[2];
	d = buf[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);

	buf[0] += a;
	buf[1] += b;
	buf[2] += c;
	buf[3] += d;
}

/*
 * Start MD5 accumulation.  Set bit count to 0 and buffer to mysterious
 * initialization constants.
 */
static void
MD5Init(pCtx)
	MD5Context *pCtx;
{
	struct Context *ctx = (struct Context *)pCtx;
	ctx->buf[0] = 0x67452301;
	ctx->buf[1] = 0xefcdab89;
	ctx->buf[2] = 0x98badcfe;
	ctx->buf[3] = 0x10325476;
	ctx->bits[0] = 0;
	ctx->bits[1] = 0;
}

/*
 * Update context to reflect the concatenation of another buffer full
 * of bytes.
 */
static void
MD5Update(pCtx, buf, len)
	MD5Context *pCtx;
	const unsigned char *buf;
	unsigned int len;
{
	struct Context *ctx = (struct Context *)pCtx;
	u_int32_t t;

	/* Update bitcount */

	t = ctx->bits[0];
	if ((ctx->bits[0] = t + ((u_int32_t)len << 3)) < t)
		ctx->bits[1]++; /* Carry from low to high */
	ctx->bits[1] += len >> 29;

	t = (t >> 3) & 0x3f;    /* Bytes already in shsInfo->data */

	/* Handle any leading odd-sized chunks */

	if ( t ) {
		unsigned char *p = (unsigned char *)ctx->in + t;

		t = 64-t;
		if (len < t) {
			memcpy(p, buf, len);
			return;
		}
		memcpy(p, buf, t);
		byteReverse(ctx->in, 16);
		MD5Transform(ctx->buf, (u_int32_t *)ctx->in);
		buf += t;
		len -= t;
	}

	/* Process data in 64-byte chunks */

	while (len >= 64) {
		memcpy(ctx->in, buf, 64);
		byteReverse(ctx->in, 16);
		MD5Transform(ctx->buf, (u_int32_t *)ctx->in);
		buf += 64;
		len -= 64;
	}

	/* Handle any remaining bytes of data. */

	memcpy(ctx->in, buf, len);
}

/*
 * Final wrapup - pad to 64-byte boundary with the bit pattern
 * 1 0* (64-bit count of bits processed, MSB-first)
 */
static void
MD5Final(digest, pCtx)
	unsigned char digest[16];
	MD5Context *pCtx;
{
	struct Context *ctx = (struct Context *)pCtx;
	unsigned count;
	unsigned char *p;

	/* Compute number of bytes mod 64 */
	count = (ctx->bits[0] >> 3) & 0x3F;

	/* Set the first char of padding to 0x80.  This is safe since there is
	   always at least one byte free */
	p = ctx->in + count;
	*p++ = 0x80;

	/* Bytes of padding needed to make 64 bytes */
	count = 64 - 1 - count;

	/* Pad out to 56 mod 64 */
	if (count < 8) {
		/* Two lots of padding:  Pad the first block to 64 bytes */
		memset(p, 0, count);
		byteReverse(ctx->in, 16);
		MD5Transform(ctx->buf, (u_int32_t *)ctx->in);

		/* Now fill the next block with 56 bytes */
		memset(ctx->in, 0, 56);
	} else {
		/* Pad block to 56 bytes */
		memset(p, 0, count-8);
	}
	byteReverse(ctx->in, 14);

	/* Append length in bits and transform */
	((u_int32_t *)ctx->in)[ 14 ] = ctx->bits[0];
	((u_int32_t *)ctx->in)[ 15 ] = ctx->bits[1];

	MD5Transform(ctx->buf, (u_int32_t *)ctx->in);
	byteReverse((unsigned char *)ctx->buf, 4);
	memcpy(digest, ctx->buf, 16);
	memset(ctx, 0, sizeof(ctx));    /* In case it's sensitive */
}

/*
 * Convert a digest into base-16.  digest should be declared as
 * "unsigned char digest[16]" in the calling function.  The MD5
 * digest is stored in the first 16 bytes.  zBuf should
 * be "char zBuf[33]".
 */
static void
DigestToBase16(digest, zBuf)
	unsigned char *digest;
	char *zBuf;
{
	static char const zEncode[] = "0123456789abcdef";
	int i, j;

	for(j=i=0; i<16; i++){
		int a = digest[i];
		zBuf[j++] = zEncode[(a>>4)&0xf];
		zBuf[j++] = zEncode[a & 0xf];
	}
	zBuf[j] = 0;
}

/*
 * A TCL command for md5.  The argument is the text to be hashed.  The
 * Result is the hash in base64.
 */
static int
md5_cmd(cd, interp, argc, argv)
	void *cd;
	Tcl_Interp *interp;
	int argc;
	const char **argv;
{
	MD5Context ctx;
	unsigned char digest[16];

	if( argc!=2 ){
		Tcl_AppendResult(interp,"wrong # args: should be \"",
				 argv[0], " TEXT\"", 0);
		return TCL_ERROR;
	}
	MD5Init(&ctx);
	MD5Update(&ctx, (unsigned char*)argv[1], (unsigned)strlen(argv[1]));
	MD5Final(digest, &ctx);
	DigestToBase16(digest, interp->result);
	return TCL_OK;
}

/*
 * A TCL command to take the md5 hash of a file.  The argument is the
 * name of the file.
 */
static int
md5file_cmd(cd, interp, argc, argv)
	void *cd;
	Tcl_Interp *interp;
	int argc;
	const char **argv;
{
	FILE *in;
	MD5Context ctx;
	unsigned char digest[16];
	char zBuf[10240];

	if( argc!=2 ){
		Tcl_AppendResult(interp,"wrong # args: should be \"", argv[0],
				 " FILENAME\"", 0);
		return TCL_ERROR;
	}
	in = fopen(argv[1],"rb");
	if( in==0 ){
		Tcl_AppendResult(interp,"unable to open file \"", argv[1],
				 "\" for reading", 0);
		return TCL_ERROR;
	}
	MD5Init(&ctx);
	for(;;){
		int n;
		n = fread(zBuf, 1, sizeof(zBuf), in);
		if( n<=0 ) break;
		MD5Update(&ctx, (unsigned char*)zBuf, (unsigned)n);
	}
	fclose(in);
	MD5Final(digest, &ctx);
	DigestToBase16(digest, interp->result);
	return TCL_OK;
}

/*
 * Register the two TCL commands above with the TCL interpreter.
 */
int
__testset_MD5_init(interp)
	Tcl_Interp *interp;
{
	Tcl_CreateCommand(interp, "md5", (Tcl_CmdProc*)md5_cmd, 0, 0);
	Tcl_CreateCommand(interp, "md5file", (Tcl_CmdProc*)md5file_cmd, 0, 0);
	return TCL_OK;
}

/*
 * During testing, the special md5sum() aggregate function is available.
 * inside DBSQL.  The following routines implement that function.
 */
void
__tcl_sql_func_md5step(context, argc, argv)
	dbsql_func_t *context;
	int argc;
	const char **argv;
{
	MD5Context *p;
	int i;
	if( argc<1 ) return;
	p = dbsql_aggregate_context(context, sizeof(*p));
	if( p==0 ) return;
	if( dbsql_aggregate_count(context)==1 ){
		MD5Init(p);
	}
	for(i=0; i<argc; i++){
		if( argv[i] ){
			MD5Update(p, (unsigned char*)argv[i], strlen(argv[i]));
		}
	}
}

void
__tcl_sql_func_md5finalize(context)
	dbsql_func_t *context;
{
	MD5Context *p;
	unsigned char digest[16];
	char zBuf[33];
	p = dbsql_aggregate_context(context, sizeof(*p));
	MD5Final(digest,p);
	DigestToBase16(digest, zBuf);
	dbsql_set_result_string(context, zBuf, strlen(zBuf));
}