Adding some functions to LuaHttp, and including some basic math

functions, such as md5.

7 files changed, 2779 insertions, 18 deletions

diff --git a/lib/LuaHttp.cc b/lib/LuaHttp.cc
index 5d2cbb2..9d40d7e 100644
--- a/lib/LuaHttp.cc
+++ b/lib/LuaHttp.cc
@@ -17,12 +17,14 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
-/* $Id: LuaHttp.cc,v 1.13 2007-06-04 14:24:18 pixel Exp $ */
+/* $Id: LuaHttp.cc,v 1.14 2007-06-11 11:27:21 pixel Exp $ */
 
+#include "md5.h"
 #include "Domain.h"
 #include "LuaHttp.h"
 #include "LuaHandle.h"
 #include "LuaTask.h"
+#include "Base64.h"
 
 class LuaDomain;
 
@@ -95,6 +97,9 @@ enum HttpResponse_method_t {
 
 enum HttpResponse_functions_t {
     HTTPRESPONSE_NEWHTTPRESPONSE = 0,
+    HTTPRESPONSE_BASE64_ENCODE,
+    HTTPRESPONSE_BASE64_DECODE,
+    HTTPRESPONSE_MD5,
 };
 
 struct lua_functypes_t HttpResponse_methods[] = {
@@ -105,6 +110,9 @@ struct lua_functypes_t HttpResponse_methods[] = {
 
 struct lua_functypes_t HttpResponse_functions[] = {
     { HTTPRESPONSE_NEWHTTPRESPONSE, "HttpResponse",   0, 0, { } },
+    { HTTPRESPONSE_BASE64_ENCODE,   "Base64Encode",   1, 1, { LUA_STRING } },
+    { HTTPRESPONSE_BASE64_DECODE,   "Base64Decode",   1, 1, { LUA_STRING } },
+    { HTTPRESPONSE_MD5,             "MD5",            1, 1, { LUA_STRING } },
     { -1, 0, 0, 0, 0 }
 };
 
@@ -114,6 +122,9 @@ class sLua_HttpResponse : public Base {
     DECLARE_METHOD(HttpResponse, HTTPRESPONSE_NEWINDEX);
     
     DECLARE_FUNCTION(HttpResponse, HTTPRESPONSE_NEWHTTPRESPONSE);
+    DECLARE_FUNCTION(HttpResponse, HTTPRESPONSE_BASE64_ENCODE);
+    DECLARE_FUNCTION(HttpResponse, HTTPRESPONSE_BASE64_DECODE);
+    DECLARE_FUNCTION(HttpResponse, HTTPRESPONSE_MD5);
   private:
     static int HttpResponse_proceed(Lua * L, int n, HttpResponse * obj, int caller);
     static int HttpResponse_proceed_statics(Lua * L, int n, int caller);
@@ -131,6 +142,9 @@ void LuaHttpResponse::pushstatics(Lua * L) throw (GeneralException) {
     CHECK_FUNCTIONS(HttpResponse);
     
     PUSH_FUNCTION(HttpResponse, HTTPRESPONSE_NEWHTTPRESPONSE);
+    PUSH_FUNCTION(HttpResponse, HTTPRESPONSE_BASE64_ENCODE);
+    PUSH_FUNCTION(HttpResponse, HTTPRESPONSE_BASE64_DECODE);
+    PUSH_FUNCTION(HttpResponse, HTTPRESPONSE_MD5);
     
     export_enum(L, HTTP_200_OK);
     export_enum(L, HTTP_301_PERM_MOVED);
@@ -203,6 +217,58 @@ int sLua_HttpResponse::HttpResponse_proceed(Lua * L, int n, HttpResponse * res,
     return r;
 }
 
+int sLua_HttpResponse::HttpResponse_proceed_statics(Lua * L, int n, int caller) {
+    int r = 0, l, i;
+    String enc, dec;
+    char * enc_t;
+    const char * dec_t;
+    md5_context ctx;
+    unsigned char md5sum[16];
+    String md5sum_r;
+    static const char hconv[] = "0123456789ABCDEF";
+    
+    switch (caller) {
+    case HTTPRESPONSE_NEWHTTPRESPONSE:
+        {
+            LuaHttpResponse r(new HttpResponse());
+            r.pushdestruct(L);
+        }
+        r = 1;
+        break;
+        
+    case HTTPRESPONSE_BASE64_ENCODE:
+        dec = L->tostring();
+        dec_t = dec.to_charp();
+        L->push(Base64::encode(dec_t, dec.strlen()));
+        r = 1;
+        break;
+        
+    case HTTPRESPONSE_BASE64_DECODE:
+        enc_t = (char *) Base64::decode(L->tostring(), &l);
+        enc_t[l] = 0;
+        L->push(enc_t);
+        r = 1;
+        break;
+    
+    case HTTPRESPONSE_MD5:
+        dec = L->tostring();
+        dec_t = dec.to_charp();
+        md5_starts(&ctx);
+        md5_update(&ctx, (uint8 *) dec_t, dec.strlen());
+        md5_finish(&ctx, md5sum);
+        md5sum[16] = 0;
+        for (i = 0; i < 16; i++) {
+            md5sum_r = md5sum_r + hconv[md5sum[i] % 16];
+            md5sum_r = md5sum_r + hconv[md5sum[i] >> 4];
+        }
+        L->push(md5sum_r);
+        r = 1;
+        break;
+    }
+    
+    return r;
+}
+
 class LuaDomain : public Domain {
   public:
       LuaDomain(Lua * _L, String r) : Domain(r), L(_L->Father()) {
@@ -297,22 +363,6 @@ class LuaDomain : public Domain {
 
 int LuaDomain::max_id = 1;
 
-int sLua_HttpResponse::HttpResponse_proceed_statics(Lua * L, int n, int caller) {
-    int r = 0;
-    
-    switch (caller) {
-    case HTTPRESPONSE_NEWHTTPRESPONSE:
-        {
-            LuaHttpResponse r(new HttpResponse());
-            r.pushdestruct(L);
-        }
-        r = 1;
-        break;
-    }
-    
-    return r;
-}
-
 int sLua_LuaDomain::LuaDomain_proceed(Lua * L, int n, LuaDomain * obj, int caller) {
     int r = 0;
     
@@ -340,4 +390,3 @@ int sLua_LuaDomain::LuaDomain_proceed_statics(Lua * L, int n, int caller) {
     
     return r;
 }
-
diff --git a/lib/aes.c b/lib/aes.c
new file mode 100644
index 0000000..edc8da7
--- /dev/null
+++ b/lib/aes.c
@@ -0,0 +1,864 @@
+/*
+ *  FIPS-197 compliant AES implementation
+ *
+ *  Copyright (C) 2001-2004  Christophe Devine
+ *
+ *  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 of the License, 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
+ */
+
+#include "aes.h"
+
+/* uncomment the following line to run the test suite */
+
+/* #define TEST */
+
+/* uncomment the following line to use pre-computed tables */
+/* otherwise the tables will be generated at the first run */
+
+/* #define FIXED_TABLES */
+
+#ifndef FIXED_TABLES
+
+/* forward S-box & tables */
+
+uint32 FSb[256];
+uint32 FT0[256]; 
+uint32 FT1[256]; 
+uint32 FT2[256]; 
+uint32 FT3[256]; 
+
+/* reverse S-box & tables */
+
+uint32 RSb[256];
+uint32 RT0[256];
+uint32 RT1[256];
+uint32 RT2[256];
+uint32 RT3[256];
+
+/* round constants */
+
+uint32 RCON[10];
+
+/* tables generation flag */
+
+int do_init = 1;
+
+/* tables generation routine */
+
+#define ROTR8(x) ( ( ( x << 24 ) & 0xFFFFFFFF ) | \
+                   ( ( x & 0xFFFFFFFF ) >>  8 ) )
+
+#define XTIME(x) ( ( x <<  1 ) ^ ( ( x & 0x80 ) ? 0x1B : 0x00 ) )
+#define MUL(x,y) ( ( x &&  y ) ? pow[(log[x] + log[y]) % 255] : 0 )
+
+void aes_gen_tables( void )
+{
+    int i;
+    uint8 x, y;
+    uint8 pow[256];
+    uint8 log[256];
+
+    /* compute pow and log tables over GF(2^8) */
+
+    for( i = 0, x = 1; i < 256; i++, x ^= XTIME( x ) )
+    {
+        pow[i] = x;
+        log[x] = i;
+    }
+
+    /* calculate the round constants */
+
+    for( i = 0, x = 1; i < 10; i++, x = XTIME( x ) )
+    {
+        RCON[i] = (uint32) x << 24;
+    }
+
+    /* generate the forward and reverse S-boxes */
+
+    FSb[0x00] = 0x63;
+    RSb[0x63] = 0x00;
+
+    for( i = 1; i < 256; i++ )
+    {
+        x = pow[255 - log[i]];
+
+        y = x;  y = ( y << 1 ) | ( y >> 7 );
+        x ^= y; y = ( y << 1 ) | ( y >> 7 );
+        x ^= y; y = ( y << 1 ) | ( y >> 7 );
+        x ^= y; y = ( y << 1 ) | ( y >> 7 );
+        x ^= y ^ 0x63;
+
+        FSb[i] = x;
+        RSb[x] = i;
+    }
+
+    /* generate the forward and reverse tables */
+
+    for( i = 0; i < 256; i++ )
+    {
+        x = (unsigned char) FSb[i]; y = XTIME( x );
+
+        FT0[i] =   (uint32) ( x ^ y ) ^
+                 ( (uint32) x <<  8 ) ^
+                 ( (uint32) x << 16 ) ^
+                 ( (uint32) y << 24 );
+
+        FT0[i] &= 0xFFFFFFFF;
+
+        FT1[i] = ROTR8( FT0[i] );
+        FT2[i] = ROTR8( FT1[i] );
+        FT3[i] = ROTR8( FT2[i] );
+
+        y = (unsigned char) RSb[i];
+
+        RT0[i] = ( (uint32) MUL( 0x0B, y )       ) ^
+                 ( (uint32) MUL( 0x0D, y ) <<  8 ) ^
+                 ( (uint32) MUL( 0x09, y ) << 16 ) ^
+                 ( (uint32) MUL( 0x0E, y ) << 24 );
+
+        RT0[i] &= 0xFFFFFFFF;
+
+        RT1[i] = ROTR8( RT0[i] );
+        RT2[i] = ROTR8( RT1[i] );
+        RT3[i] = ROTR8( RT2[i] );
+    }
+}
+
+#else
+
+/* forward S-box */
+
+static const uint32 FSb[256] =
+{
+    0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5,
+    0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
+    0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0,
+    0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
+    0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC,
+    0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
+    0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A,
+    0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
+    0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0,
+    0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
+    0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B,
+    0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
+    0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85,
+    0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
+    0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5,
+    0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
+    0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17,
+    0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
+    0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88,
+    0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
+    0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C,
+    0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
+    0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9,
+    0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
+    0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6,
+    0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
+    0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E,
+    0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
+    0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94,
+    0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
+    0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68,
+    0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16
+};
+
+/* forward tables */
+
+#define FT \
+\
+    V(C6,63,63,A5), V(F8,7C,7C,84), V(EE,77,77,99), V(F6,7B,7B,8D), \
+    V(FF,F2,F2,0D), V(D6,6B,6B,BD), V(DE,6F,6F,B1), V(91,C5,C5,54), \
+    V(60,30,30,50), V(02,01,01,03), V(CE,67,67,A9), V(56,2B,2B,7D), \
+    V(E7,FE,FE,19), V(B5,D7,D7,62), V(4D,AB,AB,E6), V(EC,76,76,9A), \
+    V(8F,CA,CA,45), V(1F,82,82,9D), V(89,C9,C9,40), V(FA,7D,7D,87), \
+    V(EF,FA,FA,15), V(B2,59,59,EB), V(8E,47,47,C9), V(FB,F0,F0,0B), \
+    V(41,AD,AD,EC), V(B3,D4,D4,67), V(5F,A2,A2,FD), V(45,AF,AF,EA), \
+    V(23,9C,9C,BF), V(53,A4,A4,F7), V(E4,72,72,96), V(9B,C0,C0,5B), \
+    V(75,B7,B7,C2), V(E1,FD,FD,1C), V(3D,93,93,AE), V(4C,26,26,6A), \
+    V(6C,36,36,5A), V(7E,3F,3F,41), V(F5,F7,F7,02), V(83,CC,CC,4F), \
+    V(68,34,34,5C), V(51,A5,A5,F4), V(D1,E5,E5,34), V(F9,F1,F1,08), \
+    V(E2,71,71,93), V(AB,D8,D8,73), V(62,31,31,53), V(2A,15,15,3F), \
+    V(08,04,04,0C), V(95,C7,C7,52), V(46,23,23,65), V(9D,C3,C3,5E), \
+    V(30,18,18,28), V(37,96,96,A1), V(0A,05,05,0F), V(2F,9A,9A,B5), \
+    V(0E,07,07,09), V(24,12,12,36), V(1B,80,80,9B), V(DF,E2,E2,3D), \
+    V(CD,EB,EB,26), V(4E,27,27,69), V(7F,B2,B2,CD), V(EA,75,75,9F), \
+    V(12,09,09,1B), V(1D,83,83,9E), V(58,2C,2C,74), V(34,1A,1A,2E), \
+    V(36,1B,1B,2D), V(DC,6E,6E,B2), V(B4,5A,5A,EE), V(5B,A0,A0,FB), \
+    V(A4,52,52,F6), V(76,3B,3B,4D), V(B7,D6,D6,61), V(7D,B3,B3,CE), \
+    V(52,29,29,7B), V(DD,E3,E3,3E), V(5E,2F,2F,71), V(13,84,84,97), \
+    V(A6,53,53,F5), V(B9,D1,D1,68), V(00,00,00,00), V(C1,ED,ED,2C), \
+    V(40,20,20,60), V(E3,FC,FC,1F), V(79,B1,B1,C8), V(B6,5B,5B,ED), \
+    V(D4,6A,6A,BE), V(8D,CB,CB,46), V(67,BE,BE,D9), V(72,39,39,4B), \
+    V(94,4A,4A,DE), V(98,4C,4C,D4), V(B0,58,58,E8), V(85,CF,CF,4A), \
+    V(BB,D0,D0,6B), V(C5,EF,EF,2A), V(4F,AA,AA,E5), V(ED,FB,FB,16), \
+    V(86,43,43,C5), V(9A,4D,4D,D7), V(66,33,33,55), V(11,85,85,94), \
+    V(8A,45,45,CF), V(E9,F9,F9,10), V(04,02,02,06), V(FE,7F,7F,81), \
+    V(A0,50,50,F0), V(78,3C,3C,44), V(25,9F,9F,BA), V(4B,A8,A8,E3), \
+    V(A2,51,51,F3), V(5D,A3,A3,FE), V(80,40,40,C0), V(05,8F,8F,8A), \
+    V(3F,92,92,AD), V(21,9D,9D,BC), V(70,38,38,48), V(F1,F5,F5,04), \
+    V(63,BC,BC,DF), V(77,B6,B6,C1), V(AF,DA,DA,75), V(42,21,21,63), \
+    V(20,10,10,30), V(E5,FF,FF,1A), V(FD,F3,F3,0E), V(BF,D2,D2,6D), \
+    V(81,CD,CD,4C), V(18,0C,0C,14), V(26,13,13,35), V(C3,EC,EC,2F), \
+    V(BE,5F,5F,E1), V(35,97,97,A2), V(88,44,44,CC), V(2E,17,17,39), \
+    V(93,C4,C4,57), V(55,A7,A7,F2), V(FC,7E,7E,82), V(7A,3D,3D,47), \
+    V(C8,64,64,AC), V(BA,5D,5D,E7), V(32,19,19,2B), V(E6,73,73,95), \
+    V(C0,60,60,A0), V(19,81,81,98), V(9E,4F,4F,D1), V(A3,DC,DC,7F), \
+    V(44,22,22,66), V(54,2A,2A,7E), V(3B,90,90,AB), V(0B,88,88,83), \
+    V(8C,46,46,CA), V(C7,EE,EE,29), V(6B,B8,B8,D3), V(28,14,14,3C), \
+    V(A7,DE,DE,79), V(BC,5E,5E,E2), V(16,0B,0B,1D), V(AD,DB,DB,76), \
+    V(DB,E0,E0,3B), V(64,32,32,56), V(74,3A,3A,4E), V(14,0A,0A,1E), \
+    V(92,49,49,DB), V(0C,06,06,0A), V(48,24,24,6C), V(B8,5C,5C,E4), \
+    V(9F,C2,C2,5D), V(BD,D3,D3,6E), V(43,AC,AC,EF), V(C4,62,62,A6), \
+    V(39,91,91,A8), V(31,95,95,A4), V(D3,E4,E4,37), V(F2,79,79,8B), \
+    V(D5,E7,E7,32), V(8B,C8,C8,43), V(6E,37,37,59), V(DA,6D,6D,B7), \
+    V(01,8D,8D,8C), V(B1,D5,D5,64), V(9C,4E,4E,D2), V(49,A9,A9,E0), \
+    V(D8,6C,6C,B4), V(AC,56,56,FA), V(F3,F4,F4,07), V(CF,EA,EA,25), \
+    V(CA,65,65,AF), V(F4,7A,7A,8E), V(47,AE,AE,E9), V(10,08,08,18), \
+    V(6F,BA,BA,D5), V(F0,78,78,88), V(4A,25,25,6F), V(5C,2E,2E,72), \
+    V(38,1C,1C,24), V(57,A6,A6,F1), V(73,B4,B4,C7), V(97,C6,C6,51), \
+    V(CB,E8,E8,23), V(A1,DD,DD,7C), V(E8,74,74,9C), V(3E,1F,1F,21), \
+    V(96,4B,4B,DD), V(61,BD,BD,DC), V(0D,8B,8B,86), V(0F,8A,8A,85), \
+    V(E0,70,70,90), V(7C,3E,3E,42), V(71,B5,B5,C4), V(CC,66,66,AA), \
+    V(90,48,48,D8), V(06,03,03,05), V(F7,F6,F6,01), V(1C,0E,0E,12), \
+    V(C2,61,61,A3), V(6A,35,35,5F), V(AE,57,57,F9), V(69,B9,B9,D0), \
+    V(17,86,86,91), V(99,C1,C1,58), V(3A,1D,1D,27), V(27,9E,9E,B9), \
+    V(D9,E1,E1,38), V(EB,F8,F8,13), V(2B,98,98,B3), V(22,11,11,33), \
+    V(D2,69,69,BB), V(A9,D9,D9,70), V(07,8E,8E,89), V(33,94,94,A7), \
+    V(2D,9B,9B,B6), V(3C,1E,1E,22), V(15,87,87,92), V(C9,E9,E9,20), \
+    V(87,CE,CE,49), V(AA,55,55,FF), V(50,28,28,78), V(A5,DF,DF,7A), \
+    V(03,8C,8C,8F), V(59,A1,A1,F8), V(09,89,89,80), V(1A,0D,0D,17), \
+    V(65,BF,BF,DA), V(D7,E6,E6,31), V(84,42,42,C6), V(D0,68,68,B8), \
+    V(82,41,41,C3), V(29,99,99,B0), V(5A,2D,2D,77), V(1E,0F,0F,11), \
+    V(7B,B0,B0,CB), V(A8,54,54,FC), V(6D,BB,BB,D6), V(2C,16,16,3A)
+
+#define V(a,b,c,d) 0x##a##b##c##d
+static const uint32 FT0[256] = { FT };
+#undef V
+
+#define V(a,b,c,d) 0x##d##a##b##c
+static const uint32 FT1[256] = { FT };
+#undef V
+
+#define V(a,b,c,d) 0x##c##d##a##b
+static const uint32 FT2[256] = { FT };
+#undef V
+
+#define V(a,b,c,d) 0x##b##c##d##a
+static const uint32 FT3[256] = { FT };
+#undef V
+
+#undef FT
+
+/* reverse S-box */
+
+static const uint32 RSb[256] =
+{
+    0x52, 0x09, 0x6A, 0xD5, 0x30, 0x36, 0xA5, 0x38,
+    0xBF, 0x40, 0xA3, 0x9E, 0x81, 0xF3, 0xD7, 0xFB,
+    0x7C, 0xE3, 0x39, 0x82, 0x9B, 0x2F, 0xFF, 0x87,
+    0x34, 0x8E, 0x43, 0x44, 0xC4, 0xDE, 0xE9, 0xCB,
+    0x54, 0x7B, 0x94, 0x32, 0xA6, 0xC2, 0x23, 0x3D,
+    0xEE, 0x4C, 0x95, 0x0B, 0x42, 0xFA, 0xC3, 0x4E,
+    0x08, 0x2E, 0xA1, 0x66, 0x28, 0xD9, 0x24, 0xB2,
+    0x76, 0x5B, 0xA2, 0x49, 0x6D, 0x8B, 0xD1, 0x25,
+    0x72, 0xF8, 0xF6, 0x64, 0x86, 0x68, 0x98, 0x16,
+    0xD4, 0xA4, 0x5C, 0xCC, 0x5D, 0x65, 0xB6, 0x92,
+    0x6C, 0x70, 0x48, 0x50, 0xFD, 0xED, 0xB9, 0xDA,
+    0x5E, 0x15, 0x46, 0x57, 0xA7, 0x8D, 0x9D, 0x84,
+    0x90, 0xD8, 0xAB, 0x00, 0x8C, 0xBC, 0xD3, 0x0A,
+    0xF7, 0xE4, 0x58, 0x05, 0xB8, 0xB3, 0x45, 0x06,
+    0xD0, 0x2C, 0x1E, 0x8F, 0xCA, 0x3F, 0x0F, 0x02,
+    0xC1, 0xAF, 0xBD, 0x03, 0x01, 0x13, 0x8A, 0x6B,
+    0x3A, 0x91, 0x11, 0x41, 0x4F, 0x67, 0xDC, 0xEA,
+    0x97, 0xF2, 0xCF, 0xCE, 0xF0, 0xB4, 0xE6, 0x73,
+    0x96, 0xAC, 0x74, 0x22, 0xE7, 0xAD, 0x35, 0x85,
+    0xE2, 0xF9, 0x37, 0xE8, 0x1C, 0x75, 0xDF, 0x6E,
+    0x47, 0xF1, 0x1A, 0x71, 0x1D, 0x29, 0xC5, 0x89,
+    0x6F, 0xB7, 0x62, 0x0E, 0xAA, 0x18, 0xBE, 0x1B,
+    0xFC, 0x56, 0x3E, 0x4B, 0xC6, 0xD2, 0x79, 0x20,
+    0x9A, 0xDB, 0xC0, 0xFE, 0x78, 0xCD, 0x5A, 0xF4,
+    0x1F, 0xDD, 0xA8, 0x33, 0x88, 0x07, 0xC7, 0x31,
+    0xB1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xEC, 0x5F,
+    0x60, 0x51, 0x7F, 0xA9, 0x19, 0xB5, 0x4A, 0x0D,
+    0x2D, 0xE5, 0x7A, 0x9F, 0x93, 0xC9, 0x9C, 0xEF,
+    0xA0, 0xE0, 0x3B, 0x4D, 0xAE, 0x2A, 0xF5, 0xB0,
+    0xC8, 0xEB, 0xBB, 0x3C, 0x83, 0x53, 0x99, 0x61,
+    0x17, 0x2B, 0x04, 0x7E, 0xBA, 0x77, 0xD6, 0x26,
+    0xE1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0C, 0x7D
+};
+
+/* reverse tables */
+
+#define RT \
+\
+    V(51,F4,A7,50), V(7E,41,65,53), V(1A,17,A4,C3), V(3A,27,5E,96), \
+    V(3B,AB,6B,CB), V(1F,9D,45,F1), V(AC,FA,58,AB), V(4B,E3,03,93), \
+    V(20,30,FA,55), V(AD,76,6D,F6), V(88,CC,76,91), V(F5,02,4C,25), \
+    V(4F,E5,D7,FC), V(C5,2A,CB,D7), V(26,35,44,80), V(B5,62,A3,8F), \
+    V(DE,B1,5A,49), V(25,BA,1B,67), V(45,EA,0E,98), V(5D,FE,C0,E1), \
+    V(C3,2F,75,02), V(81,4C,F0,12), V(8D,46,97,A3), V(6B,D3,F9,C6), \
+    V(03,8F,5F,E7), V(15,92,9C,95), V(BF,6D,7A,EB), V(95,52,59,DA), \
+    V(D4,BE,83,2D), V(58,74,21,D3), V(49,E0,69,29), V(8E,C9,C8,44), \
+    V(75,C2,89,6A), V(F4,8E,79,78), V(99,58,3E,6B), V(27,B9,71,DD), \
+    V(BE,E1,4F,B6), V(F0,88,AD,17), V(C9,20,AC,66), V(7D,CE,3A,B4), \
+    V(63,DF,4A,18), V(E5,1A,31,82), V(97,51,33,60), V(62,53,7F,45), \
+    V(B1,64,77,E0), V(BB,6B,AE,84), V(FE,81,A0,1C), V(F9,08,2B,94), \
+    V(70,48,68,58), V(8F,45,FD,19), V(94,DE,6C,87), V(52,7B,F8,B7), \
+    V(AB,73,D3,23), V(72,4B,02,E2), V(E3,1F,8F,57), V(66,55,AB,2A), \
+    V(B2,EB,28,07), V(2F,B5,C2,03), V(86,C5,7B,9A), V(D3,37,08,A5), \
+    V(30,28,87,F2), V(23,BF,A5,B2), V(02,03,6A,BA), V(ED,16,82,5C), \
+    V(8A,CF,1C,2B), V(A7,79,B4,92), V(F3,07,F2,F0), V(4E,69,E2,A1), \
+    V(65,DA,F4,CD), V(06,05,BE,D5), V(D1,34,62,1F), V(C4,A6,FE,8A), \
+    V(34,2E,53,9D), V(A2,F3,55,A0), V(05,8A,E1,32), V(A4,F6,EB,75), \
+    V(0B,83,EC,39), V(40,60,EF,AA), V(5E,71,9F,06), V(BD,6E,10,51), \
+    V(3E,21,8A,F9), V(96,DD,06,3D), V(DD,3E,05,AE), V(4D,E6,BD,46), \
+    V(91,54,8D,B5), V(71,C4,5D,05), V(04,06,D4,6F), V(60,50,15,FF), \
+    V(19,98,FB,24), V(D6,BD,E9,97), V(89,40,43,CC), V(67,D9,9E,77), \
+    V(B0,E8,42,BD), V(07,89,8B,88), V(E7,19,5B,38), V(79,C8,EE,DB), \
+    V(A1,7C,0A,47), V(7C,42,0F,E9), V(F8,84,1E,C9), V(00,00,00,00), \
+    V(09,80,86,83), V(32,2B,ED,48), V(1E,11,70,AC), V(6C,5A,72,4E), \
+    V(FD,0E,FF,FB), V(0F,85,38,56), V(3D,AE,D5,1E), V(36,2D,39,27), \
+    V(0A,0F,D9,64), V(68,5C,A6,21), V(9B,5B,54,D1), V(24,36,2E,3A), \
+    V(0C,0A,67,B1), V(93,57,E7,0F), V(B4,EE,96,D2), V(1B,9B,91,9E), \
+    V(80,C0,C5,4F), V(61,DC,20,A2), V(5A,77,4B,69), V(1C,12,1A,16), \
+    V(E2,93,BA,0A), V(C0,A0,2A,E5), V(3C,22,E0,43), V(12,1B,17,1D), \
+    V(0E,09,0D,0B), V(F2,8B,C7,AD), V(2D,B6,A8,B9), V(14,1E,A9,C8), \
+    V(57,F1,19,85), V(AF,75,07,4C), V(EE,99,DD,BB), V(A3,7F,60,FD), \
+    V(F7,01,26,9F), V(5C,72,F5,BC), V(44,66,3B,C5), V(5B,FB,7E,34), \
+    V(8B,43,29,76), V(CB,23,C6,DC), V(B6,ED,FC,68), V(B8,E4,F1,63), \
+    V(D7,31,DC,CA), V(42,63,85,10), V(13,97,22,40), V(84,C6,11,20), \
+    V(85,4A,24,7D), V(D2,BB,3D,F8), V(AE,F9,32,11), V(C7,29,A1,6D), \
+    V(1D,9E,2F,4B), V(DC,B2,30,F3), V(0D,86,52,EC), V(77,C1,E3,D0), \
+    V(2B,B3,16,6C), V(A9,70,B9,99), V(11,94,48,FA), V(47,E9,64,22), \
+    V(A8,FC,8C,C4), V(A0,F0,3F,1A), V(56,7D,2C,D8), V(22,33,90,EF), \
+    V(87,49,4E,C7), V(D9,38,D1,C1), V(8C,CA,A2,FE), V(98,D4,0B,36), \
+    V(A6,F5,81,CF), V(A5,7A,DE,28), V(DA,B7,8E,26), V(3F,AD,BF,A4), \
+    V(2C,3A,9D,E4), V(50,78,92,0D), V(6A,5F,CC,9B), V(54,7E,46,62), \
+    V(F6,8D,13,C2), V(90,D8,B8,E8), V(2E,39,F7,5E), V(82,C3,AF,F5), \
+    V(9F,5D,80,BE), V(69,D0,93,7C), V(6F,D5,2D,A9), V(CF,25,12,B3), \
+    V(C8,AC,99,3B), V(10,18,7D,A7), V(E8,9C,63,6E), V(DB,3B,BB,7B), \
+    V(CD,26,78,09), V(6E,59,18,F4), V(EC,9A,B7,01), V(83,4F,9A,A8), \
+    V(E6,95,6E,65), V(AA,FF,E6,7E), V(21,BC,CF,08), V(EF,15,E8,E6), \
+    V(BA,E7,9B,D9), V(4A,6F,36,CE), V(EA,9F,09,D4), V(29,B0,7C,D6), \
+    V(31,A4,B2,AF), V(2A,3F,23,31), V(C6,A5,94,30), V(35,A2,66,C0), \
+    V(74,4E,BC,37), V(FC,82,CA,A6), V(E0,90,D0,B0), V(33,A7,D8,15), \
+    V(F1,04,98,4A), V(41,EC,DA,F7), V(7F,CD,50,0E), V(17,91,F6,2F), \
+    V(76,4D,D6,8D), V(43,EF,B0,4D), V(CC,AA,4D,54), V(E4,96,04,DF), \
+    V(9E,D1,B5,E3), V(4C,6A,88,1B), V(C1,2C,1F,B8), V(46,65,51,7F), \
+    V(9D,5E,EA,04), V(01,8C,35,5D), V(FA,87,74,73), V(FB,0B,41,2E), \
+    V(B3,67,1D,5A), V(92,DB,D2,52), V(E9,10,56,33), V(6D,D6,47,13), \
+    V(9A,D7,61,8C), V(37,A1,0C,7A), V(59,F8,14,8E), V(EB,13,3C,89), \
+    V(CE,A9,27,EE), V(B7,61,C9,35), V(E1,1C,E5,ED), V(7A,47,B1,3C), \
+    V(9C,D2,DF,59), V(55,F2,73,3F), V(18,14,CE,79), V(73,C7,37,BF), \
+    V(53,F7,CD,EA), V(5F,FD,AA,5B), V(DF,3D,6F,14), V(78,44,DB,86), \
+    V(CA,AF,F3,81), V(B9,68,C4,3E), V(38,24,34,2C), V(C2,A3,40,5F), \
+    V(16,1D,C3,72), V(BC,E2,25,0C), V(28,3C,49,8B), V(FF,0D,95,41), \
+    V(39,A8,01,71), V(08,0C,B3,DE), V(D8,B4,E4,9C), V(64,56,C1,90), \
+    V(7B,CB,84,61), V(D5,32,B6,70), V(48,6C,5C,74), V(D0,B8,57,42)
+
+#define V(a,b,c,d) 0x##a##b##c##d
+static const uint32 RT0[256] = { RT };
+#undef V
+
+#define V(a,b,c,d) 0x##d##a##b##c
+static const uint32 RT1[256] = { RT };
+#undef V
+
+#define V(a,b,c,d) 0x##c##d##a##b
+static const uint32 RT2[256] = { RT };
+#undef V
+
+#define V(a,b,c,d) 0x##b##c##d##a
+static const uint32 RT3[256] = { RT };
+#undef V
+
+#undef RT
+
+/* round constants */
+
+static const uint32 RCON[10] =
+{
+    0x01000000, 0x02000000, 0x04000000, 0x08000000,
+    0x10000000, 0x20000000, 0x40000000, 0x80000000,
+    0x1B000000, 0x36000000
+};
+
+int do_init = 0;
+
+void aes_gen_tables( void )
+{
+}
+
+#endif
+
+/* platform-independant 32-bit integer manipulation macros */
+
+#define GET_UINT32(n,b,i)                       \
+{                                               \
+    (n) = ( (uint32) (b)[(i)    ] << 24 )       \
+        | ( (uint32) (b)[(i) + 1] << 16 )       \
+        | ( (uint32) (b)[(i) + 2] <<  8 )       \
+        | ( (uint32) (b)[(i) + 3]       );      \
+}
+
+#define PUT_UINT32(n,b,i)                       \
+{                                               \
+    (b)[(i)    ] = (uint8) ( (n) >> 24 );       \
+    (b)[(i) + 1] = (uint8) ( (n) >> 16 );       \
+    (b)[(i) + 2] = (uint8) ( (n) >>  8 );       \
+    (b)[(i) + 3] = (uint8) ( (n)       );       \
+}
+
+/* decryption key schedule tables */
+
+int KT_init = 1;
+
+uint32 KT0[256];
+uint32 KT1[256];
+uint32 KT2[256];
+uint32 KT3[256];
+
+/* AES key scheduling routine */
+
+int aes_set_key( aes_context *ctx, uint8 *key, int nbits )
+{
+    int i;
+    uint32 *RK, *SK;
+
+    if( do_init )
+    {
+        aes_gen_tables();
+
+        do_init = 0;
+    }
+
+    switch( nbits )
+    {
+        case 128: ctx->nr = 10; break;
+        case 192: ctx->nr = 12; break;
+        case 256: ctx->nr = 14; break;
+        default : return( 1 );
+    }
+
+    RK = ctx->erk;
+
+    for( i = 0; i < (nbits >> 5); i++ )
+    {
+        GET_UINT32( RK[i], key, i * 4 );
+    }
+
+    /* setup encryption round keys */
+
+    switch( nbits )
+    {
+    case 128:
+
+        for( i = 0; i < 10; i++, RK += 4 )
+        {
+            RK[4]  = RK[0] ^ RCON[i] ^
+                        ( FSb[ (uint8) ( RK[3] >> 16 ) ] << 24 ) ^
+                        ( FSb[ (uint8) ( RK[3] >>  8 ) ] << 16 ) ^
+                        ( FSb[ (uint8) ( RK[3]       ) ] <<  8 ) ^
+                        ( FSb[ (uint8) ( RK[3] >> 24 ) ]       );
+
+            RK[5]  = RK[1] ^ RK[4];
+            RK[6]  = RK[2] ^ RK[5];
+            RK[7]  = RK[3] ^ RK[6];
+        }
+        break;
+
+    case 192:
+
+        for( i = 0; i < 8; i++, RK += 6 )
+        {
+            RK[6]  = RK[0] ^ RCON[i] ^
+                        ( FSb[ (uint8) ( RK[5] >> 16 ) ] << 24 ) ^
+                        ( FSb[ (uint8) ( RK[5] >>  8 ) ] << 16 ) ^
+                        ( FSb[ (uint8) ( RK[5]       ) ] <<  8 ) ^
+                        ( FSb[ (uint8) ( RK[5] >> 24 ) ]       );
+
+            RK[7]  = RK[1] ^ RK[6];
+            RK[8]  = RK[2] ^ RK[7];
+            RK[9]  = RK[3] ^ RK[8];
+            RK[10] = RK[4] ^ RK[9];
+            RK[11] = RK[5] ^ RK[10];
+        }
+        break;
+
+    case 256:
+
+        for( i = 0; i < 7; i++, RK += 8 )
+        {
+            RK[8]  = RK[0] ^ RCON[i] ^
+                        ( FSb[ (uint8) ( RK[7] >> 16 ) ] << 24 ) ^
+                        ( FSb[ (uint8) ( RK[7] >>  8 ) ] << 16 ) ^
+                        ( FSb[ (uint8) ( RK[7]       ) ] <<  8 ) ^
+                        ( FSb[ (uint8) ( RK[7] >> 24 ) ]       );
+
+            RK[9]  = RK[1] ^ RK[8];
+            RK[10] = RK[2] ^ RK[9];
+            RK[11] = RK[3] ^ RK[10];
+
+            RK[12] = RK[4] ^
+                        ( FSb[ (uint8) ( RK[11] >> 24 ) ] << 24 ) ^
+                        ( FSb[ (uint8) ( RK[11] >> 16 ) ] << 16 ) ^
+                        ( FSb[ (uint8) ( RK[11] >>  8 ) ] <<  8 ) ^
+                        ( FSb[ (uint8) ( RK[11]       ) ]       );
+
+            RK[13] = RK[5] ^ RK[12];
+            RK[14] = RK[6] ^ RK[13];
+            RK[15] = RK[7] ^ RK[14];
+        }
+        break;
+    }
+
+    /* setup decryption round keys */
+
+    if( KT_init )
+    {
+        for( i = 0; i < 256; i++ )
+        {
+            KT0[i] = RT0[ FSb[i] ];
+            KT1[i] = RT1[ FSb[i] ];
+            KT2[i] = RT2[ FSb[i] ];
+            KT3[i] = RT3[ FSb[i] ];
+        }
+
+        KT_init = 0;
+    }
+
+    SK = ctx->drk;
+
+    *SK++ = *RK++;
+    *SK++ = *RK++;
+    *SK++ = *RK++;
+    *SK++ = *RK++;
+
+    for( i = 1; i < ctx->nr; i++ )
+    {
+        RK -= 8;
+
+        *SK++ = KT0[ (uint8) ( *RK >> 24 ) ] ^
+                KT1[ (uint8) ( *RK >> 16 ) ] ^
+                KT2[ (uint8) ( *RK >>  8 ) ] ^
+                KT3[ (uint8) ( *RK       ) ]; RK++;
+
+        *SK++ = KT0[ (uint8) ( *RK >> 24 ) ] ^
+                KT1[ (uint8) ( *RK >> 16 ) ] ^
+                KT2[ (uint8) ( *RK >>  8 ) ] ^
+                KT3[ (uint8) ( *RK       ) ]; RK++;
+
+        *SK++ = KT0[ (uint8) ( *RK >> 24 ) ] ^
+                KT1[ (uint8) ( *RK >> 16 ) ] ^
+                KT2[ (uint8) ( *RK >>  8 ) ] ^
+                KT3[ (uint8) ( *RK       ) ]; RK++;
+
+        *SK++ = KT0[ (uint8) ( *RK >> 24 ) ] ^
+                KT1[ (uint8) ( *RK >> 16 ) ] ^
+                KT2[ (uint8) ( *RK >>  8 ) ] ^
+                KT3[ (uint8) ( *RK       ) ]; RK++;
+    }
+
+    RK -= 8;
+
+    *SK++ = *RK++;
+    *SK++ = *RK++;
+    *SK++ = *RK++;
+    *SK++ = *RK++;
+
+    return( 0 );
+}
+
+/* AES 128-bit block encryption routine */
+
+void aes_encrypt( aes_context *ctx, uint8 input[16], uint8 output[16] )
+{
+    uint32 *RK, X0, X1, X2, X3, Y0, Y1, Y2, Y3;
+
+    RK = ctx->erk;
+
+    GET_UINT32( X0, input,  0 ); X0 ^= RK[0];
+    GET_UINT32( X1, input,  4 ); X1 ^= RK[1];
+    GET_UINT32( X2, input,  8 ); X2 ^= RK[2];
+    GET_UINT32( X3, input, 12 ); X3 ^= RK[3];
+
+#define AES_FROUND(X0,X1,X2,X3,Y0,Y1,Y2,Y3)     \
+{                                               \
+    RK += 4;                                    \
+                                                \
+    X0 = RK[0] ^ FT0[ (uint8) ( Y0 >> 24 ) ] ^  \
+                 FT1[ (uint8) ( Y1 >> 16 ) ] ^  \
+                 FT2[ (uint8) ( Y2 >>  8 ) ] ^  \
+                 FT3[ (uint8) ( Y3       ) ];   \
+                                                \
+    X1 = RK[1] ^ FT0[ (uint8) ( Y1 >> 24 ) ] ^  \
+                 FT1[ (uint8) ( Y2 >> 16 ) ] ^  \
+                 FT2[ (uint8) ( Y3 >>  8 ) ] ^  \
+                 FT3[ (uint8) ( Y0       ) ];   \
+                                                \
+    X2 = RK[2] ^ FT0[ (uint8) ( Y2 >> 24 ) ] ^  \
+                 FT1[ (uint8) ( Y3 >> 16 ) ] ^  \
+                 FT2[ (uint8) ( Y0 >>  8 ) ] ^  \
+                 FT3[ (uint8) ( Y1       ) ];   \
+                                                \
+    X3 = RK[3] ^ FT0[ (uint8) ( Y3 >> 24 ) ] ^  \
+                 FT1[ (uint8) ( Y0 >> 16 ) ] ^  \
+                 FT2[ (uint8) ( Y1 >>  8 ) ] ^  \
+                 FT3[ (uint8) ( Y2       ) ];   \
+}
+
+    AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 1 */
+    AES_FROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 2 */
+    AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 3 */
+    AES_FROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 4 */
+    AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 5 */
+    AES_FROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 6 */
+    AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 7 */
+    AES_FROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 8 */
+    AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 9 */
+
+    if( ctx->nr > 10 )
+    {
+        AES_FROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );   /* round 10 */
+        AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );   /* round 11 */
+    }
+
+    if( ctx->nr > 12 )
+    {
+        AES_FROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );   /* round 12 */
+        AES_FROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );   /* round 13 */
+    }
+
+    /* last round */
+
+    RK += 4;
+
+    X0 = RK[0] ^ ( FSb[ (uint8) ( Y0 >> 24 ) ] << 24 ) ^
+                 ( FSb[ (uint8) ( Y1 >> 16 ) ] << 16 ) ^
+                 ( FSb[ (uint8) ( Y2 >>  8 ) ] <<  8 ) ^
+                 ( FSb[ (uint8) ( Y3       ) ]       );
+
+    X1 = RK[1] ^ ( FSb[ (uint8) ( Y1 >> 24 ) ] << 24 ) ^
+                 ( FSb[ (uint8) ( Y2 >> 16 ) ] << 16 ) ^
+                 ( FSb[ (uint8) ( Y3 >>  8 ) ] <<  8 ) ^
+                 ( FSb[ (uint8) ( Y0       ) ]       );
+
+    X2 = RK[2] ^ ( FSb[ (uint8) ( Y2 >> 24 ) ] << 24 ) ^
+                 ( FSb[ (uint8) ( Y3 >> 16 ) ] << 16 ) ^
+                 ( FSb[ (uint8) ( Y0 >>  8 ) ] <<  8 ) ^
+                 ( FSb[ (uint8) ( Y1       ) ]       );
+
+    X3 = RK[3] ^ ( FSb[ (uint8) ( Y3 >> 24 ) ] << 24 ) ^
+                 ( FSb[ (uint8) ( Y0 >> 16 ) ] << 16 ) ^
+                 ( FSb[ (uint8) ( Y1 >>  8 ) ] <<  8 ) ^
+                 ( FSb[ (uint8) ( Y2       ) ]       );
+
+    PUT_UINT32( X0, output,  0 );
+    PUT_UINT32( X1, output,  4 );
+    PUT_UINT32( X2, output,  8 );
+    PUT_UINT32( X3, output, 12 );
+}
+
+/* AES 128-bit block decryption routine */
+
+void aes_decrypt( aes_context *ctx, uint8 input[16], uint8 output[16] )
+{
+    uint32 *RK, X0, X1, X2, X3, Y0, Y1, Y2, Y3;
+
+    RK = ctx->drk;
+
+    GET_UINT32( X0, input,  0 ); X0 ^= RK[0];
+    GET_UINT32( X1, input,  4 ); X1 ^= RK[1];
+    GET_UINT32( X2, input,  8 ); X2 ^= RK[2];
+    GET_UINT32( X3, input, 12 ); X3 ^= RK[3];
+
+#define AES_RROUND(X0,X1,X2,X3,Y0,Y1,Y2,Y3)     \
+{                                               \
+    RK += 4;                                    \
+                                                \
+    X0 = RK[0] ^ RT0[ (uint8) ( Y0 >> 24 ) ] ^  \
+                 RT1[ (uint8) ( Y3 >> 16 ) ] ^  \
+                 RT2[ (uint8) ( Y2 >>  8 ) ] ^  \
+                 RT3[ (uint8) ( Y1       ) ];   \
+                                                \
+    X1 = RK[1] ^ RT0[ (uint8) ( Y1 >> 24 ) ] ^  \
+                 RT1[ (uint8) ( Y0 >> 16 ) ] ^  \
+                 RT2[ (uint8) ( Y3 >>  8 ) ] ^  \
+                 RT3[ (uint8) ( Y2       ) ];   \
+                                                \
+    X2 = RK[2] ^ RT0[ (uint8) ( Y2 >> 24 ) ] ^  \
+                 RT1[ (uint8) ( Y1 >> 16 ) ] ^  \
+                 RT2[ (uint8) ( Y0 >>  8 ) ] ^  \
+                 RT3[ (uint8) ( Y3       ) ];   \
+                                                \
+    X3 = RK[3] ^ RT0[ (uint8) ( Y3 >> 24 ) ] ^  \
+                 RT1[ (uint8) ( Y2 >> 16 ) ] ^  \
+                 RT2[ (uint8) ( Y1 >>  8 ) ] ^  \
+                 RT3[ (uint8) ( Y0       ) ];   \
+}
+
+    AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 1 */
+    AES_RROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 2 */
+    AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 3 */
+    AES_RROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 4 */
+    AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 5 */
+    AES_RROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 6 */
+    AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 7 */
+    AES_RROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );       /* round 8 */
+    AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );       /* round 9 */
+
+    if( ctx->nr > 10 )
+    {
+        AES_RROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );   /* round 10 */
+        AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );   /* round 11 */
+    }
+
+    if( ctx->nr > 12 )
+    {
+        AES_RROUND( X0, X1, X2, X3, Y0, Y1, Y2, Y3 );   /* round 12 */
+        AES_RROUND( Y0, Y1, Y2, Y3, X0, X1, X2, X3 );   /* round 13 */
+    }
+
+    /* last round */
+
+    RK += 4;
+
+    X0 = RK[0] ^ ( RSb[ (uint8) ( Y0 >> 24 ) ] << 24 ) ^
+                 ( RSb[ (uint8) ( Y3 >> 16 ) ] << 16 ) ^
+                 ( RSb[ (uint8) ( Y2 >>  8 ) ] <<  8 ) ^
+                 ( RSb[ (uint8) ( Y1       ) ]       );
+
+    X1 = RK[1] ^ ( RSb[ (uint8) ( Y1 >> 24 ) ] << 24 ) ^
+                 ( RSb[ (uint8) ( Y0 >> 16 ) ] << 16 ) ^
+                 ( RSb[ (uint8) ( Y3 >>  8 ) ] <<  8 ) ^
+                 ( RSb[ (uint8) ( Y2       ) ]       );
+
+    X2 = RK[2] ^ ( RSb[ (uint8) ( Y2 >> 24 ) ] << 24 ) ^
+                 ( RSb[ (uint8) ( Y1 >> 16 ) ] << 16 ) ^
+                 ( RSb[ (uint8) ( Y0 >>  8 ) ] <<  8 ) ^
+                 ( RSb[ (uint8) ( Y3       ) ]       );
+
+    X3 = RK[3] ^ ( RSb[ (uint8) ( Y3 >> 24 ) ] << 24 ) ^
+                 ( RSb[ (uint8) ( Y2 >> 16 ) ] << 16 ) ^
+                 ( RSb[ (uint8) ( Y1 >>  8 ) ] <<  8 ) ^
+                 ( RSb[ (uint8) ( Y0       ) ]       );
+
+    PUT_UINT32( X0, output,  0 );
+    PUT_UINT32( X1, output,  4 );
+    PUT_UINT32( X2, output,  8 );
+    PUT_UINT32( X3, output, 12 );
+}
+
+#ifdef TEST
+
+#include <string.h>
+#include <stdio.h>
+
+/*
+ * Rijndael Monte Carlo Test: ECB mode
+ * source: NIST - rijndael-vals.zip
+ */
+
+static unsigned char AES_enc_test[3][16] =
+{
+    { 0xA0, 0x43, 0x77, 0xAB, 0xE2, 0x59, 0xB0, 0xD0,
+      0xB5, 0xBA, 0x2D, 0x40, 0xA5, 0x01, 0x97, 0x1B },
+    { 0x4E, 0x46, 0xF8, 0xC5, 0x09, 0x2B, 0x29, 0xE2,
+      0x9A, 0x97, 0x1A, 0x0C, 0xD1, 0xF6, 0x10, 0xFB },
+    { 0x1F, 0x67, 0x63, 0xDF, 0x80, 0x7A, 0x7E, 0x70,
+      0x96, 0x0D, 0x4C, 0xD3, 0x11, 0x8E, 0x60, 0x1A }
+};
+    
+static unsigned char AES_dec_test[3][16] =
+{
+    { 0xF5, 0xBF, 0x8B, 0x37, 0x13, 0x6F, 0x2E, 0x1F,
+      0x6B, 0xEC, 0x6F, 0x57, 0x20, 0x21, 0xE3, 0xBA },
+    { 0xF1, 0xA8, 0x1B, 0x68, 0xF6, 0xE5, 0xA6, 0x27,
+      0x1A, 0x8C, 0xB2, 0x4E, 0x7D, 0x94, 0x91, 0xEF },
+    { 0x4D, 0xE0, 0xC6, 0xDF, 0x7C, 0xB1, 0x69, 0x72,
+      0x84, 0x60, 0x4D, 0x60, 0x27, 0x1B, 0xC5, 0x9A }
+};
+    
+int main( void )
+{
+    int m, n, i, j;
+    aes_context ctx;
+    unsigned char buf[16];
+    unsigned char key[32];
+
+    for( m = 0; m < 2; m++ )
+    {
+        printf( "\n Rijndael Monte Carlo Test (ECB mode) - " );
+
+        if( m == 0 ) printf( "encryption\n\n" );
+        if( m == 1 ) printf( "decryption\n\n" );
+
+        for( n = 0; n < 3; n++ )
+        {
+            printf( " Test %d, key size = %3d bits: ",
+                    n + 1, 128 + n * 64 );
+
+            fflush( stdout );
+
+            memset( buf, 0, 16 );
+            memset( key, 0, 16 + n * 8 );
+
+            for( i = 0; i < 400; i++ )
+            {
+                aes_set_key( &ctx, key, 128 + n * 64 );
+
+                for( j = 0; j < 9999; j++ )
+                {
+                    if( m == 0 ) aes_encrypt( &ctx, buf, buf );
+                    if( m == 1 ) aes_decrypt( &ctx, buf, buf );
+                }
+
+                if( n > 0 )
+                {
+                    for( j = 0; j < (n << 3); j++ )
+                    {
+                        key[j] ^= buf[j + 16 - (n << 3)];
+                    }
+                }
+
+                if( m == 0 ) aes_encrypt( &ctx, buf, buf );
+                if( m == 1 ) aes_decrypt( &ctx, buf, buf );
+
+                for( j = 0; j < 16; j++ )
+                {
+                    key[j + (n << 3)] ^= buf[j];
+                }
+            }
+
+            if( ( m == 0 && memcmp( buf, AES_enc_test[n], 16 ) != 0 ) ||
+                ( m == 1 && memcmp( buf, AES_dec_test[n], 16 ) != 0 ) )
+            {
+                printf( "failed!\n" );
+                return( 1 );
+            }
+
+            printf( "passed.\n" );
+        }
+    }
+
+    printf( "\n" );
+
+    return( 0 );
+}
+
+#endif
+
diff --git a/lib/des.c b/lib/des.c
new file mode 100644
index 0000000..eb22edc
--- /dev/null
+++ b/lib/des.c
@@ -0,0 +1,602 @@
+/*
+ *  FIPS-46-3 compliant 3DES implementation
+ *
+ *  Copyright (C) 2001-2003  Christophe Devine
+ *
+ *  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 of the License, 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
+ */
+
+#include "des.h"
+
+/* the eight DES S-boxes */
+
+uint32 SB1[64] =
+{
+    0x01010400, 0x00000000, 0x00010000, 0x01010404,
+    0x01010004, 0x00010404, 0x00000004, 0x00010000,
+    0x00000400, 0x01010400, 0x01010404, 0x00000400,
+    0x01000404, 0x01010004, 0x01000000, 0x00000004,
+    0x00000404, 0x01000400, 0x01000400, 0x00010400,
+    0x00010400, 0x01010000, 0x01010000, 0x01000404,
+    0x00010004, 0x01000004, 0x01000004, 0x00010004,
+    0x00000000, 0x00000404, 0x00010404, 0x01000000,
+    0x00010000, 0x01010404, 0x00000004, 0x01010000,
+    0x01010400, 0x01000000, 0x01000000, 0x00000400,
+    0x01010004, 0x00010000, 0x00010400, 0x01000004,
+    0x00000400, 0x00000004, 0x01000404, 0x00010404,
+    0x01010404, 0x00010004, 0x01010000, 0x01000404,
+    0x01000004, 0x00000404, 0x00010404, 0x01010400,
+    0x00000404, 0x01000400, 0x01000400, 0x00000000,
+    0x00010004, 0x00010400, 0x00000000, 0x01010004
+};
+
+static uint32 SB2[64] =
+{
+    0x80108020, 0x80008000, 0x00008000, 0x00108020,
+    0x00100000, 0x00000020, 0x80100020, 0x80008020,
+    0x80000020, 0x80108020, 0x80108000, 0x80000000,
+    0x80008000, 0x00100000, 0x00000020, 0x80100020,
+    0x00108000, 0x00100020, 0x80008020, 0x00000000,
+    0x80000000, 0x00008000, 0x00108020, 0x80100000,
+    0x00100020, 0x80000020, 0x00000000, 0x00108000,
+    0x00008020, 0x80108000, 0x80100000, 0x00008020,
+    0x00000000, 0x00108020, 0x80100020, 0x00100000,
+    0x80008020, 0x80100000, 0x80108000, 0x00008000,
+    0x80100000, 0x80008000, 0x00000020, 0x80108020,
+    0x00108020, 0x00000020, 0x00008000, 0x80000000,
+    0x00008020, 0x80108000, 0x00100000, 0x80000020,
+    0x00100020, 0x80008020, 0x80000020, 0x00100020,
+    0x00108000, 0x00000000, 0x80008000, 0x00008020,
+    0x80000000, 0x80100020, 0x80108020, 0x00108000
+};
+
+static uint32 SB3[64] =
+{
+    0x00000208, 0x08020200, 0x00000000, 0x08020008,
+    0x08000200, 0x00000000, 0x00020208, 0x08000200,
+    0x00020008, 0x08000008, 0x08000008, 0x00020000,
+    0x08020208, 0x00020008, 0x08020000, 0x00000208,
+    0x08000000, 0x00000008, 0x08020200, 0x00000200,
+    0x00020200, 0x08020000, 0x08020008, 0x00020208,
+    0x08000208, 0x00020200, 0x00020000, 0x08000208,
+    0x00000008, 0x08020208, 0x00000200, 0x08000000,
+    0x08020200, 0x08000000, 0x00020008, 0x00000208,
+    0x00020000, 0x08020200, 0x08000200, 0x00000000,
+    0x00000200, 0x00020008, 0x08020208, 0x08000200,
+    0x08000008, 0x00000200, 0x00000000, 0x08020008,
+    0x08000208, 0x00020000, 0x08000000, 0x08020208,
+    0x00000008, 0x00020208, 0x00020200, 0x08000008,
+    0x08020000, 0x08000208, 0x00000208, 0x08020000,
+    0x00020208, 0x00000008, 0x08020008, 0x00020200
+};
+
+static uint32 SB4[64] =
+{
+    0x00802001, 0x00002081, 0x00002081, 0x00000080,
+    0x00802080, 0x00800081, 0x00800001, 0x00002001,
+    0x00000000, 0x00802000, 0x00802000, 0x00802081,
+    0x00000081, 0x00000000, 0x00800080, 0x00800001,
+    0x00000001, 0x00002000, 0x00800000, 0x00802001,
+    0x00000080, 0x00800000, 0x00002001, 0x00002080,
+    0x00800081, 0x00000001, 0x00002080, 0x00800080,
+    0x00002000, 0x00802080, 0x00802081, 0x00000081,
+    0x00800080, 0x00800001, 0x00802000, 0x00802081,
+    0x00000081, 0x00000000, 0x00000000, 0x00802000,
+    0x00002080, 0x00800080, 0x00800081, 0x00000001,
+    0x00802001, 0x00002081, 0x00002081, 0x00000080,
+    0x00802081, 0x00000081, 0x00000001, 0x00002000,
+    0x00800001, 0x00002001, 0x00802080, 0x00800081,
+    0x00002001, 0x00002080, 0x00800000, 0x00802001,
+    0x00000080, 0x00800000, 0x00002000, 0x00802080
+};
+
+static uint32 SB5[64] =
+{
+    0x00000100, 0x02080100, 0x02080000, 0x42000100,
+    0x00080000, 0x00000100, 0x40000000, 0x02080000,
+    0x40080100, 0x00080000, 0x02000100, 0x40080100,
+    0x42000100, 0x42080000, 0x00080100, 0x40000000,
+    0x02000000, 0x40080000, 0x40080000, 0x00000000,
+    0x40000100, 0x42080100, 0x42080100, 0x02000100,
+    0x42080000, 0x40000100, 0x00000000, 0x42000000,
+    0x02080100, 0x02000000, 0x42000000, 0x00080100,
+    0x00080000, 0x42000100, 0x00000100, 0x02000000,
+    0x40000000, 0x02080000, 0x42000100, 0x40080100,
+    0x02000100, 0x40000000, 0x42080000, 0x02080100,
+    0x40080100, 0x00000100, 0x02000000, 0x42080000,
+    0x42080100, 0x00080100, 0x42000000, 0x42080100,
+    0x02080000, 0x00000000, 0x40080000, 0x42000000,
+    0x00080100, 0x02000100, 0x40000100, 0x00080000,
+    0x00000000, 0x40080000, 0x02080100, 0x40000100
+};
+
+static uint32 SB6[64] =
+{
+    0x20000010, 0x20400000, 0x00004000, 0x20404010,
+    0x20400000, 0x00000010, 0x20404010, 0x00400000,
+    0x20004000, 0x00404010, 0x00400000, 0x20000010,
+    0x00400010, 0x20004000, 0x20000000, 0x00004010,
+    0x00000000, 0x00400010, 0x20004010, 0x00004000,
+    0x00404000, 0x20004010, 0x00000010, 0x20400010,
+    0x20400010, 0x00000000, 0x00404010, 0x20404000,
+    0x00004010, 0x00404000, 0x20404000, 0x20000000,
+    0x20004000, 0x00000010, 0x20400010, 0x00404000,
+    0x20404010, 0x00400000, 0x00004010, 0x20000010,
+    0x00400000, 0x20004000, 0x20000000, 0x00004010,
+    0x20000010, 0x20404010, 0x00404000, 0x20400000,
+    0x00404010, 0x20404000, 0x00000000, 0x20400010,
+    0x00000010, 0x00004000, 0x20400000, 0x00404010,
+    0x00004000, 0x00400010, 0x20004010, 0x00000000,
+    0x20404000, 0x20000000, 0x00400010, 0x20004010
+};
+
+static uint32 SB7[64] =
+{
+    0x00200000, 0x04200002, 0x04000802, 0x00000000,
+    0x00000800, 0x04000802, 0x00200802, 0x04200800,
+    0x04200802, 0x00200000, 0x00000000, 0x04000002,
+    0x00000002, 0x04000000, 0x04200002, 0x00000802,
+    0x04000800, 0x00200802, 0x00200002, 0x04000800,
+    0x04000002, 0x04200000, 0x04200800, 0x00200002,
+    0x04200000, 0x00000800, 0x00000802, 0x04200802,
+    0x00200800, 0x00000002, 0x04000000, 0x00200800,
+    0x04000000, 0x00200800, 0x00200000, 0x04000802,
+    0x04000802, 0x04200002, 0x04200002, 0x00000002,
+    0x00200002, 0x04000000, 0x04000800, 0x00200000,
+    0x04200800, 0x00000802, 0x00200802, 0x04200800,
+    0x00000802, 0x04000002, 0x04200802, 0x04200000,
+    0x00200800, 0x00000000, 0x00000002, 0x04200802,
+    0x00000000, 0x00200802, 0x04200000, 0x00000800,
+    0x04000002, 0x04000800, 0x00000800, 0x00200002
+};
+
+static uint32 SB8[64] =
+{
+    0x10001040, 0x00001000, 0x00040000, 0x10041040,
+    0x10000000, 0x10001040, 0x00000040, 0x10000000,
+    0x00040040, 0x10040000, 0x10041040, 0x00041000,
+    0x10041000, 0x00041040, 0x00001000, 0x00000040,
+    0x10040000, 0x10000040, 0x10001000, 0x00001040,
+    0x00041000, 0x00040040, 0x10040040, 0x10041000,
+    0x00001040, 0x00000000, 0x00000000, 0x10040040,
+    0x10000040, 0x10001000, 0x00041040, 0x00040000,
+    0x00041040, 0x00040000, 0x10041000, 0x00001000,
+    0x00000040, 0x10040040, 0x00001000, 0x00041040,
+    0x10001000, 0x00000040, 0x10000040, 0x10040000,
+    0x10040040, 0x10000000, 0x00040000, 0x10001040,
+    0x00000000, 0x10041040, 0x00040040, 0x10000040,
+    0x10040000, 0x10001000, 0x10001040, 0x00000000,
+    0x10041040, 0x00041000, 0x00041000, 0x00001040,
+    0x00001040, 0x00040040, 0x10000000, 0x10041000
+};
+
+/* PC1: left and right halves bit-swap */
+
+static uint32 LHs[16] =
+{
+    0x00000000, 0x00000001, 0x00000100, 0x00000101,
+    0x00010000, 0x00010001, 0x00010100, 0x00010101,
+    0x01000000, 0x01000001, 0x01000100, 0x01000101,
+    0x01010000, 0x01010001, 0x01010100, 0x01010101
+};
+
+static uint32 RHs[16] =
+{
+    0x00000000, 0x01000000, 0x00010000, 0x01010000,
+    0x00000100, 0x01000100, 0x00010100, 0x01010100,
+    0x00000001, 0x01000001, 0x00010001, 0x01010001,
+    0x00000101, 0x01000101, 0x00010101, 0x01010101,
+};
+
+/* platform-independant 32-bit integer manipulation macros */
+
+#define GET_UINT32(n,b,i)                       \
+{                                               \
+    (n) = ( (uint32) (b)[(i)    ] << 24 )       \
+        | ( (uint32) (b)[(i) + 1] << 16 )       \
+        | ( (uint32) (b)[(i) + 2] <<  8 )       \
+        | ( (uint32) (b)[(i) + 3]       );      \
+}
+
+#define PUT_UINT32(n,b,i)                       \
+{                                               \
+    (b)[(i)    ] = (uint8) ( (n) >> 24 );       \
+    (b)[(i) + 1] = (uint8) ( (n) >> 16 );       \
+    (b)[(i) + 2] = (uint8) ( (n) >>  8 );       \
+    (b)[(i) + 3] = (uint8) ( (n)       );       \
+}
+
+/* Initial Permutation macro */
+
+#define DES_IP(X,Y)                                             \
+{                                                               \
+    T = ((X >>  4) ^ Y) & 0x0F0F0F0F; Y ^= T; X ^= (T <<  4);   \
+    T = ((X >> 16) ^ Y) & 0x0000FFFF; Y ^= T; X ^= (T << 16);   \
+    T = ((Y >>  2) ^ X) & 0x33333333; X ^= T; Y ^= (T <<  2);   \
+    T = ((Y >>  8) ^ X) & 0x00FF00FF; X ^= T; Y ^= (T <<  8);   \
+    Y = ((Y << 1) | (Y >> 31)) & 0xFFFFFFFF;                    \
+    T = (X ^ Y) & 0xAAAAAAAA; Y ^= T; X ^= T;                   \
+    X = ((X << 1) | (X >> 31)) & 0xFFFFFFFF;                    \
+}
+
+/* Final Permutation macro */
+
+#define DES_FP(X,Y)                                             \
+{                                                               \
+    X = ((X << 31) | (X >> 1)) & 0xFFFFFFFF;                    \
+    T = (X ^ Y) & 0xAAAAAAAA; X ^= T; Y ^= T;                   \
+    Y = ((Y << 31) | (Y >> 1)) & 0xFFFFFFFF;                    \
+    T = ((Y >>  8) ^ X) & 0x00FF00FF; X ^= T; Y ^= (T <<  8);   \
+    T = ((Y >>  2) ^ X) & 0x33333333; X ^= T; Y ^= (T <<  2);   \
+    T = ((X >> 16) ^ Y) & 0x0000FFFF; Y ^= T; X ^= (T << 16);   \
+    T = ((X >>  4) ^ Y) & 0x0F0F0F0F; Y ^= T; X ^= (T <<  4);   \
+}
+
+/* DES round macro */
+
+#define DES_ROUND(X,Y)                          \
+{                                               \
+    T = *SK++ ^ X;                              \
+    Y ^= SB8[ (T      ) & 0x3F ] ^              \
+         SB6[ (T >>  8) & 0x3F ] ^              \
+         SB4[ (T >> 16) & 0x3F ] ^              \
+         SB2[ (T >> 24) & 0x3F ];               \
+                                                \
+    T = *SK++ ^ ((X << 28) | (X >> 4));         \
+    Y ^= SB7[ (T      ) & 0x3F ] ^              \
+         SB5[ (T >>  8) & 0x3F ] ^              \
+         SB3[ (T >> 16) & 0x3F ] ^              \
+         SB1[ (T >> 24) & 0x3F ];               \
+}
+
+/* DES key schedule */
+
+int des_main_ks( uint32 SK[32], uint8 key[8] )
+{
+    int i;
+    uint32 X, Y, T;
+
+    GET_UINT32( X, key, 0 );
+    GET_UINT32( Y, key, 4 );
+
+    /* Permuted Choice 1 */
+
+    T =  ((Y >>  4) ^ X) & 0x0F0F0F0F;  X ^= T; Y ^= (T <<  4);
+    T =  ((Y      ) ^ X) & 0x10101010;  X ^= T; Y ^= (T      );
+
+    X =   (LHs[ (X      ) & 0xF] << 3) | (LHs[ (X >>  8) & 0xF ] << 2)
+        | (LHs[ (X >> 16) & 0xF] << 1) | (LHs[ (X >> 24) & 0xF ]     )
+        | (LHs[ (X >>  5) & 0xF] << 7) | (LHs[ (X >> 13) & 0xF ] << 6)
+        | (LHs[ (X >> 21) & 0xF] << 5) | (LHs[ (X >> 29) & 0xF ] << 4);
+
+    Y =   (RHs[ (Y >>  1) & 0xF] << 3) | (RHs[ (Y >>  9) & 0xF ] << 2)
+        | (RHs[ (Y >> 17) & 0xF] << 1) | (RHs[ (Y >> 25) & 0xF ]     )
+        | (RHs[ (Y >>  4) & 0xF] << 7) | (RHs[ (Y >> 12) & 0xF ] << 6)
+        | (RHs[ (Y >> 20) & 0xF] << 5) | (RHs[ (Y >> 28) & 0xF ] << 4);
+
+    X &= 0x0FFFFFFF;
+    Y &= 0x0FFFFFFF;
+
+    /* calculate subkeys */
+
+    for( i = 0; i < 16; i++ )
+    {
+        if( i < 2 || i == 8 || i == 15 )
+        {
+            X = ((X <<  1) | (X >> 27)) & 0x0FFFFFFF;
+            Y = ((Y <<  1) | (Y >> 27)) & 0x0FFFFFFF;
+        }
+        else
+        {
+            X = ((X <<  2) | (X >> 26)) & 0x0FFFFFFF;
+            Y = ((Y <<  2) | (Y >> 26)) & 0x0FFFFFFF;
+        }
+
+        *SK++ =   ((X <<  4) & 0x24000000) | ((X << 28) & 0x10000000)
+                | ((X << 14) & 0x08000000) | ((X << 18) & 0x02080000)
+                | ((X <<  6) & 0x01000000) | ((X <<  9) & 0x00200000)
+                | ((X >>  1) & 0x00100000) | ((X << 10) & 0x00040000)
+                | ((X <<  2) & 0x00020000) | ((X >> 10) & 0x00010000)
+                | ((Y >> 13) & 0x00002000) | ((Y >>  4) & 0x00001000)
+                | ((Y <<  6) & 0x00000800) | ((Y >>  1) & 0x00000400)
+                | ((Y >> 14) & 0x00000200) | ((Y      ) & 0x00000100)
+                | ((Y >>  5) & 0x00000020) | ((Y >> 10) & 0x00000010)
+                | ((Y >>  3) & 0x00000008) | ((Y >> 18) & 0x00000004)
+                | ((Y >> 26) & 0x00000002) | ((Y >> 24) & 0x00000001);
+
+        *SK++ =   ((X << 15) & 0x20000000) | ((X << 17) & 0x10000000)
+                | ((X << 10) & 0x08000000) | ((X << 22) & 0x04000000)
+                | ((X >>  2) & 0x02000000) | ((X <<  1) & 0x01000000)
+                | ((X << 16) & 0x00200000) | ((X << 11) & 0x00100000)
+                | ((X <<  3) & 0x00080000) | ((X >>  6) & 0x00040000)
+                | ((X << 15) & 0x00020000) | ((X >>  4) & 0x00010000)
+                | ((Y >>  2) & 0x00002000) | ((Y <<  8) & 0x00001000)
+                | ((Y >> 14) & 0x00000808) | ((Y >>  9) & 0x00000400)
+                | ((Y      ) & 0x00000200) | ((Y <<  7) & 0x00000100)
+                | ((Y >>  7) & 0x00000020) | ((Y >>  3) & 0x00000011)
+                | ((Y <<  2) & 0x00000004) | ((Y >> 21) & 0x00000002);
+    }
+
+    return( 0 );
+}
+
+int des_set_key( des_context *ctx, uint8 key[8] )
+{
+    int i;
+
+    /* setup encryption subkeys */
+
+    des_main_ks( ctx->esk, key );
+
+    /* setup decryption subkeys */
+
+    for( i = 0; i < 32; i += 2 )
+    {
+        ctx->dsk[i    ] = ctx->esk[30 - i];
+        ctx->dsk[i + 1] = ctx->esk[31 - i];
+    }
+
+    return( 0 );
+}
+
+/* DES 64-bit block encryption/decryption */
+
+void des_crypt( uint32 SK[32], uint8 input[8], uint8 output[8] )
+{
+    uint32 X, Y, T;
+
+    GET_UINT32( X, input, 0 );
+    GET_UINT32( Y, input, 4 );
+
+    DES_IP( X, Y );
+
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+
+    DES_FP( Y, X );
+
+    PUT_UINT32( Y, output, 0 );
+    PUT_UINT32( X, output, 4 );
+}
+
+void des_encrypt( des_context *ctx, uint8 input[8], uint8 output[8] )
+{
+    des_crypt( ctx->esk, input, output );
+}
+
+void des_decrypt( des_context *ctx, uint8 input[8], uint8 output[8] )
+{
+    des_crypt( ctx->dsk, input, output );
+}
+
+/* Triple-DES key schedule */
+
+int des3_set_2keys( des3_context *ctx, uint8 key1[8], uint8 key2[8] )
+{
+    int i;
+
+    des_main_ks( ctx->esk     , key1 );
+    des_main_ks( ctx->dsk + 32, key2 );
+
+    for( i = 0; i < 32; i += 2 )
+    {
+        ctx->dsk[i     ] = ctx->esk[30 - i];
+        ctx->dsk[i +  1] = ctx->esk[31 - i];
+
+        ctx->esk[i + 32] = ctx->dsk[62 - i];
+        ctx->esk[i + 33] = ctx->dsk[63 - i];
+
+        ctx->esk[i + 64] = ctx->esk[     i];
+        ctx->esk[i + 65] = ctx->esk[ 1 + i];
+
+        ctx->dsk[i + 64] = ctx->dsk[     i];
+        ctx->dsk[i + 65] = ctx->dsk[ 1 + i];
+    }
+
+    return( 0 );
+}
+
+int des3_set_3keys( des3_context *ctx, uint8 key1[8], uint8 key2[8],
+                                       uint8 key3[8] )
+{
+    int i;
+
+    des_main_ks( ctx->esk     , key1 );
+    des_main_ks( ctx->dsk + 32, key2 );
+    des_main_ks( ctx->esk + 64, key3 );
+
+    for( i = 0; i < 32; i += 2 )
+    {
+        ctx->dsk[i     ] = ctx->esk[94 - i];
+        ctx->dsk[i +  1] = ctx->esk[95 - i];
+
+        ctx->esk[i + 32] = ctx->dsk[62 - i];
+        ctx->esk[i + 33] = ctx->dsk[63 - i];
+
+        ctx->dsk[i + 64] = ctx->esk[30 - i];
+        ctx->dsk[i + 65] = ctx->esk[31 - i];
+    }
+
+    return( 0 );
+}
+
+/* Triple-DES 64-bit block encryption/decryption */
+
+void des3_crypt( uint32 SK[96], uint8 input[8], uint8 output[8] )
+{
+    uint32 X, Y, T;
+
+    GET_UINT32( X, input, 0 );
+    GET_UINT32( Y, input, 4 );
+
+    DES_IP( X, Y );
+
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+    DES_ROUND( X, Y );  DES_ROUND( Y, X );
+
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+    DES_ROUND( Y, X );  DES_ROUND( X, Y );
+
+    DES_FP( Y, X );
+
+    PUT_UINT32( Y, output, 0 );
+    PUT_UINT32( X, output, 4 );
+}
+
+void des3_encrypt( des3_context *ctx, uint8 input[8], uint8 output[8] )
+{
+    des3_crypt( ctx->esk, input, output );
+}
+
+void des3_decrypt( des3_context *ctx, uint8 input[8], uint8 output[8] )
+{
+    des3_crypt( ctx->dsk, input, output );
+}
+
+#ifdef TEST
+
+#include <string.h>
+#include <stdio.h>
+
+/*
+ * Triple-DES Monte Carlo Test: ECB mode
+ * source: NIST - tripledes-vectors.zip
+ */
+
+static unsigned char DES3_keys[3][8] =
+{
+    { 0x01, 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF },
+    { 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF, 0x01 },
+    { 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF, 0x01, 0x23 }
+};
+
+static unsigned char DES3_init[8] =
+{
+    0x4E, 0x6F, 0x77, 0x20, 0x69, 0x73, 0x20, 0x74
+};
+
+static unsigned char DES3_enc_test[3][8] =
+{
+    { 0x6A, 0x2A, 0x19, 0xF4, 0x1E, 0xCA, 0x85, 0x4B },
+    { 0x03, 0xE6, 0x9F, 0x5B, 0xFA, 0x58, 0xEB, 0x42 },
+    { 0xDD, 0x17, 0xE8, 0xB8, 0xB4, 0x37, 0xD2, 0x32 }
+};
+    
+static unsigned char DES3_dec_test[3][8] =
+{
+    { 0xCD, 0xD6, 0x4F, 0x2F, 0x94, 0x27, 0xC1, 0x5D },
+    { 0x69, 0x96, 0xC8, 0xFA, 0x47, 0xA2, 0xAB, 0xEB },
+    { 0x83, 0x25, 0x39, 0x76, 0x44, 0x09, 0x1A, 0x0A }
+};
+
+int main( void )
+{
+    int m, n, i;
+    des_context ctx;
+    des3_context ctx3;
+    unsigned char buf[8];
+
+    for( m = 0; m < 2; m++ )
+    {
+        printf( "\n Triple-DES Monte Carlo Test (ECB mode) - " );
+
+        if( m == 0 ) printf( "encryption\n\n" );
+        if( m == 1 ) printf( "decryption\n\n" );
+
+        for( n = 0; n < 3; n++ )
+        {
+            printf( " Test %d, key size = %3d bits: ",
+                    n + 1, 64 + n * 64 );
+
+            fflush( stdout );
+
+            memcpy( buf, DES3_init, 8 );
+
+            switch( n )
+            {
+                case 0:
+                    des_set_key( &ctx, DES3_keys[0] );
+                    break;
+
+                case 1:
+                    des3_set_2keys( &ctx3, DES3_keys[0],
+                                           DES3_keys[1] );
+                    break;
+
+                case 2:
+                    des3_set_3keys( &ctx3, DES3_keys[0],
+                                           DES3_keys[1],
+                                           DES3_keys[2] );
+                    break;
+            }
+
+            for( i = 0; i < 10000; i++ )
+            {
+                if( n == 0 )
+                {
+                    if( m == 0 ) des_encrypt( &ctx, buf, buf );
+                    if( m == 1 ) des_decrypt( &ctx, buf, buf );
+                }
+                else
+                {
+                    if( m == 0 ) des3_encrypt( &ctx3, buf, buf );
+                    if( m == 1 ) des3_decrypt( &ctx3, buf, buf );
+                }
+            }
+
+            if( ( m == 0 && memcmp( buf, DES3_enc_test[n], 8 ) ) ||
+                ( m == 1 && memcmp( buf, DES3_dec_test[n], 8 ) ) )
+            {
+                printf( "failed!\n" );
+                return( 1 );
+            }
+
+            printf( "passed.\n" );
+        }
+    }
+
+    printf( "\n" );
+
+    return( 0 );
+}
+
+#endif
diff --git a/lib/md5.c b/lib/md5.c
new file mode 100644
index 0000000..90d7566
--- /dev/null
+++ b/lib/md5.c
@@ -0,0 +1,344 @@
+/*
+ *  RFC 1321 compliant MD5 implementation
+ *
+ *  Copyright (C) 2001-2003  Christophe Devine
+ *
+ *  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 of the License, 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
+ */
+
+#include <string.h>
+
+#include "md5.h"
+
+#define GET_UINT32(n,b,i)                       \
+{                                               \
+    (n) = ( (uint32) (b)[(i)    ]       )       \
+        | ( (uint32) (b)[(i) + 1] <<  8 )       \
+        | ( (uint32) (b)[(i) + 2] << 16 )       \
+        | ( (uint32) (b)[(i) + 3] << 24 );      \
+}
+
+#define PUT_UINT32(n,b,i)                       \
+{                                               \
+    (b)[(i)    ] = (uint8) ( (n)       );       \
+    (b)[(i) + 1] = (uint8) ( (n) >>  8 );       \
+    (b)[(i) + 2] = (uint8) ( (n) >> 16 );       \
+    (b)[(i) + 3] = (uint8) ( (n) >> 24 );       \
+}
+
+void md5_starts( md5_context *ctx )
+{
+    ctx->total[0] = 0;
+    ctx->total[1] = 0;
+
+    ctx->state[0] = 0x67452301;
+    ctx->state[1] = 0xEFCDAB89;
+    ctx->state[2] = 0x98BADCFE;
+    ctx->state[3] = 0x10325476;
+}
+
+void md5_process( md5_context *ctx, uint8 data[64] )
+{
+    uint32 X[16], A, B, C, D;
+
+    GET_UINT32( X[0],  data,  0 );
+    GET_UINT32( X[1],  data,  4 );
+    GET_UINT32( X[2],  data,  8 );
+    GET_UINT32( X[3],  data, 12 );
+    GET_UINT32( X[4],  data, 16 );
+    GET_UINT32( X[5],  data, 20 );
+    GET_UINT32( X[6],  data, 24 );
+    GET_UINT32( X[7],  data, 28 );
+    GET_UINT32( X[8],  data, 32 );
+    GET_UINT32( X[9],  data, 36 );
+    GET_UINT32( X[10], data, 40 );
+    GET_UINT32( X[11], data, 44 );
+    GET_UINT32( X[12], data, 48 );
+    GET_UINT32( X[13], data, 52 );
+    GET_UINT32( X[14], data, 56 );
+    GET_UINT32( X[15], data, 60 );
+
+#define S(x,n) ((x << n) | ((x & 0xFFFFFFFF) >> (32 - n)))
+
+#define P(a,b,c,d,k,s,t)                                \
+{                                                       \
+    a += F(b,c,d) + X[k] + t; a = S(a,s) + b;           \
+}
+
+    A = ctx->state[0];
+    B = ctx->state[1];
+    C = ctx->state[2];
+    D = ctx->state[3];
+
+#define F(x,y,z) (z ^ (x & (y ^ z)))
+
+    P( A, B, C, D,  0,  7, 0xD76AA478 );
+    P( D, A, B, C,  1, 12, 0xE8C7B756 );
+    P( C, D, A, B,  2, 17, 0x242070DB );
+    P( B, C, D, A,  3, 22, 0xC1BDCEEE );
+    P( A, B, C, D,  4,  7, 0xF57C0FAF );
+    P( D, A, B, C,  5, 12, 0x4787C62A );
+    P( C, D, A, B,  6, 17, 0xA8304613 );
+    P( B, C, D, A,  7, 22, 0xFD469501 );
+    P( A, B, C, D,  8,  7, 0x698098D8 );
+    P( D, A, B, C,  9, 12, 0x8B44F7AF );
+    P( C, D, A, B, 10, 17, 0xFFFF5BB1 );
+    P( B, C, D, A, 11, 22, 0x895CD7BE );
+    P( A, B, C, D, 12,  7, 0x6B901122 );
+    P( D, A, B, C, 13, 12, 0xFD987193 );
+    P( C, D, A, B, 14, 17, 0xA679438E );
+    P( B, C, D, A, 15, 22, 0x49B40821 );
+
+#undef F
+
+#define F(x,y,z) (y ^ (z & (x ^ y)))
+
+    P( A, B, C, D,  1,  5, 0xF61E2562 );
+    P( D, A, B, C,  6,  9, 0xC040B340 );
+    P( C, D, A, B, 11, 14, 0x265E5A51 );
+    P( B, C, D, A,  0, 20, 0xE9B6C7AA );
+    P( A, B, C, D,  5,  5, 0xD62F105D );
+    P( D, A, B, C, 10,  9, 0x02441453 );
+    P( C, D, A, B, 15, 14, 0xD8A1E681 );
+    P( B, C, D, A,  4, 20, 0xE7D3FBC8 );
+    P( A, B, C, D,  9,  5, 0x21E1CDE6 );
+    P( D, A, B, C, 14,  9, 0xC33707D6 );
+    P( C, D, A, B,  3, 14, 0xF4D50D87 );
+    P( B, C, D, A,  8, 20, 0x455A14ED );
+    P( A, B, C, D, 13,  5, 0xA9E3E905 );
+    P( D, A, B, C,  2,  9, 0xFCEFA3F8 );
+    P( C, D, A, B,  7, 14, 0x676F02D9 );
+    P( B, C, D, A, 12, 20, 0x8D2A4C8A );
+
+#undef F
+    
+#define F(x,y,z) (x ^ y ^ z)
+
+    P( A, B, C, D,  5,  4, 0xFFFA3942 );
+    P( D, A, B, C,  8, 11, 0x8771F681 );
+    P( C, D, A, B, 11, 16, 0x6D9D6122 );
+    P( B, C, D, A, 14, 23, 0xFDE5380C );
+    P( A, B, C, D,  1,  4, 0xA4BEEA44 );
+    P( D, A, B, C,  4, 11, 0x4BDECFA9 );
+    P( C, D, A, B,  7, 16, 0xF6BB4B60 );
+    P( B, C, D, A, 10, 23, 0xBEBFBC70 );
+    P( A, B, C, D, 13,  4, 0x289B7EC6 );
+    P( D, A, B, C,  0, 11, 0xEAA127FA );
+    P( C, D, A, B,  3, 16, 0xD4EF3085 );
+    P( B, C, D, A,  6, 23, 0x04881D05 );
+    P( A, B, C, D,  9,  4, 0xD9D4D039 );
+    P( D, A, B, C, 12, 11, 0xE6DB99E5 );
+    P( C, D, A, B, 15, 16, 0x1FA27CF8 );
+    P( B, C, D, A,  2, 23, 0xC4AC5665 );
+
+#undef F
+
+#define F(x,y,z) (y ^ (x | ~z))
+
+    P( A, B, C, D,  0,  6, 0xF4292244 );
+    P( D, A, B, C,  7, 10, 0x432AFF97 );
+    P( C, D, A, B, 14, 15, 0xAB9423A7 );
+    P( B, C, D, A,  5, 21, 0xFC93A039 );
+    P( A, B, C, D, 12,  6, 0x655B59C3 );
+    P( D, A, B, C,  3, 10, 0x8F0CCC92 );
+    P( C, D, A, B, 10, 15, 0xFFEFF47D );
+    P( B, C, D, A,  1, 21, 0x85845DD1 );
+    P( A, B, C, D,  8,  6, 0x6FA87E4F );
+    P( D, A, B, C, 15, 10, 0xFE2CE6E0 );
+    P( C, D, A, B,  6, 15, 0xA3014314 );
+    P( B, C, D, A, 13, 21, 0x4E0811A1 );
+    P( A, B, C, D,  4,  6, 0xF7537E82 );
+    P( D, A, B, C, 11, 10, 0xBD3AF235 );
+    P( C, D, A, B,  2, 15, 0x2AD7D2BB );
+    P( B, C, D, A,  9, 21, 0xEB86D391 );
+
+#undef F
+
+    ctx->state[0] += A;
+    ctx->state[1] += B;
+    ctx->state[2] += C;
+    ctx->state[3] += D;
+}
+
+void md5_update( md5_context *ctx, uint8 *input, uint32 length )
+{
+    uint32 left, fill;
+
+    if( ! length ) return;
+
+    left = ctx->total[0] & 0x3F;
+    fill = 64 - left;
+
+    ctx->total[0] += length;
+    ctx->total[0] &= 0xFFFFFFFF;
+
+    if( ctx->total[0] < length )
+        ctx->total[1]++;
+
+    if( left && length >= fill )
+    {
+        memcpy( (void *) (ctx->buffer + left),
+                (void *) input, fill );
+        md5_process( ctx, ctx->buffer );
+        length -= fill;
+        input  += fill;
+        left = 0;
+    }
+
+    while( length >= 64 )
+    {
+        md5_process( ctx, input );
+        length -= 64;
+        input  += 64;
+    }
+
+    if( length )
+    {
+        memcpy( (void *) (ctx->buffer + left),
+                (void *) input, length );
+    }
+}
+
+static uint8 md5_padding[64] =
+{
+ 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
+};
+
+void md5_finish( md5_context *ctx, uint8 digest[16] )
+{
+    uint32 last, padn;
+    uint32 high, low;
+    uint8 msglen[8];
+
+    high = ( ctx->total[0] >> 29 )
+         | ( ctx->total[1] <<  3 );
+    low  = ( ctx->total[0] <<  3 );
+
+    PUT_UINT32( low,  msglen, 0 );
+    PUT_UINT32( high, msglen, 4 );
+
+    last = ctx->total[0] & 0x3F;
+    padn = ( last < 56 ) ? ( 56 - last ) : ( 120 - last );
+
+    md5_update( ctx, md5_padding, padn );
+    md5_update( ctx, msglen, 8 );
+
+    PUT_UINT32( ctx->state[0], digest,  0 );
+    PUT_UINT32( ctx->state[1], digest,  4 );
+    PUT_UINT32( ctx->state[2], digest,  8 );
+    PUT_UINT32( ctx->state[3], digest, 12 );
+}
+
+#ifdef TEST
+
+#include <stdlib.h>
+#include <stdio.h>
+
+/*
+ * those are the standard RFC 1321 test vectors
+ */
+
+static char *msg[] = 
+{
+    "",
+    "a",
+    "abc",
+    "message digest",
+    "abcdefghijklmnopqrstuvwxyz",
+    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789",
+    "12345678901234567890123456789012345678901234567890123456789012" \
+        "345678901234567890"
+};
+
+static char *val[] =
+{
+    "d41d8cd98f00b204e9800998ecf8427e",
+    "0cc175b9c0f1b6a831c399e269772661",
+    "900150983cd24fb0d6963f7d28e17f72",
+    "f96b697d7cb7938d525a2f31aaf161d0",
+    "c3fcd3d76192e4007dfb496cca67e13b",
+    "d174ab98d277d9f5a5611c2c9f419d9f",
+    "57edf4a22be3c955ac49da2e2107b67a"
+};
+
+int main( int argc, char *argv[] )
+{
+    FILE *f;
+    int i, j;
+    char output[33];
+    md5_context ctx;
+    unsigned char buf[1000];
+    unsigned char md5sum[16];
+
+    if( argc < 2 )
+    {
+        printf( "\n MD5 Validation Tests:\n\n" );
+
+        for( i = 0; i < 7; i++ )
+        {
+            printf( " Test %d ", i + 1 );
+
+            md5_starts( &ctx );
+            md5_update( &ctx, (uint8 *) msg[i], strlen( msg[i] ) );
+            md5_finish( &ctx, md5sum );
+
+            for( j = 0; j < 16; j++ )
+            {
+                sprintf( output + j * 2, "%02x", md5sum[j] );
+            }
+
+            if( memcmp( output, val[i], 32 ) )
+            {
+                printf( "failed!\n" );
+                return( 1 );
+            }
+
+            printf( "passed.\n" );
+        }
+
+        printf( "\n" );
+    }
+    else
+    {
+        if( ! ( f = fopen( argv[1], "rb" ) ) )
+        {
+            perror( "fopen" );
+            return( 1 );
+        }
+
+        md5_starts( &ctx );
+
+        while( ( i = fread( buf, 1, sizeof( buf ), f ) ) > 0 )
+        {
+            md5_update( &ctx, buf, i );
+        }
+
+        md5_finish( &ctx, md5sum );
+
+        for( j = 0; j < 16; j++ )
+        {
+            printf( "%02x", md5sum[j] );
+        }
+
+        printf( "  %s\n", argv[1] );
+    }
+
+    return( 0 );
+}
+
+#endif
diff --git a/lib/rc4.c b/lib/rc4.c
new file mode 100644
index 0000000..cada3e1
--- /dev/null
+++ b/lib/rc4.c
@@ -0,0 +1,148 @@
+/*
+ *  An implementation of the ARC4 algorithm
+ *
+ *  Copyright (C) 2001-2003  Christophe Devine
+ *
+ *  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 of the License, 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
+ */
+
+#include "rc4.h"
+
+void rc4_setup( struct rc4_state *s, unsigned char *key,  int length )
+{
+    int i, j, k, *m, a;
+
+    s->x = 0;
+    s->y = 0;
+    m = s->m;
+
+    for( i = 0; i < 256; i++ )
+    {
+        m[i] = i;
+    }
+
+    j = k = 0;
+
+    for( i = 0; i < 256; i++ )
+    {
+        a = m[i];
+        j = (unsigned char) ( j + a + key[k] );
+        m[i] = m[j]; m[j] = a;
+        if( ++k >= length ) k = 0;
+    }
+}
+
+void rc4_crypt( struct rc4_state *s, unsigned char *data, int length )
+{ 
+    int i, x, y, *m, a, b;
+
+    x = s->x;
+    y = s->y;
+    m = s->m;
+
+    for( i = 0; i < length; i++ )
+    {
+        x = (unsigned char) ( x + 1 ); a = m[x];
+        y = (unsigned char) ( y + a );
+        m[x] = b = m[y];
+        m[y] = a;
+        data[i] ^= m[(unsigned char) ( a + b )];
+    }
+
+    s->x = x;
+    s->y = y;
+}
+
+#ifdef TEST
+
+#include <string.h>
+#include <stdio.h>
+
+/*
+ * ARC4 tests vectors from OpenSSL (crypto/rc4/rc4test.c)
+ */
+
+static unsigned char keys[7][30]={
+        {8,0x01,0x23,0x45,0x67,0x89,0xab,0xcd,0xef},
+        {8,0x01,0x23,0x45,0x67,0x89,0xab,0xcd,0xef},
+        {8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00},
+        {4,0xef,0x01,0x23,0x45},
+        {8,0x01,0x23,0x45,0x67,0x89,0xab,0xcd,0xef},
+        {4,0xef,0x01,0x23,0x45},
+        };
+
+static unsigned char data_len[7]={8,8,8,20,28,10};
+static unsigned char data[7][30]={
+        {0x01,0x23,0x45,0x67,0x89,0xab,0xcd,0xef,0xff},
+        {0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xff},
+        {0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xff},
+        {0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+           0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+           0x00,0x00,0x00,0x00,0xff},
+        {0x12,0x34,0x56,0x78,0x9A,0xBC,0xDE,0xF0,
+           0x12,0x34,0x56,0x78,0x9A,0xBC,0xDE,0xF0,
+           0x12,0x34,0x56,0x78,0x9A,0xBC,0xDE,0xF0,
+           0x12,0x34,0x56,0x78,0xff},
+        {0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xff},
+        {0},
+        };
+
+static unsigned char output[7][30]={
+        {0x75,0xb7,0x87,0x80,0x99,0xe0,0xc5,0x96,0x00},
+        {0x74,0x94,0xc2,0xe7,0x10,0x4b,0x08,0x79,0x00},
+        {0xde,0x18,0x89,0x41,0xa3,0x37,0x5d,0x3a,0x00},
+        {0xd6,0xa1,0x41,0xa7,0xec,0x3c,0x38,0xdf,
+         0xbd,0x61,0x5a,0x11,0x62,0xe1,0xc7,0xba,
+         0x36,0xb6,0x78,0x58,0x00},
+        {0x66,0xa0,0x94,0x9f,0x8a,0xf7,0xd6,0x89,
+         0x1f,0x7f,0x83,0x2b,0xa8,0x33,0xc0,0x0c,
+         0x89,0x2e,0xbe,0x30,0x14,0x3c,0xe2,0x87,
+         0x40,0x01,0x1e,0xcf,0x00},
+        {0xd6,0xa1,0x41,0xa7,0xec,0x3c,0x38,0xdf,0xbd,0x61,0x00},
+        {0},
+        };
+
+int main( void )
+{
+    int i;
+    struct rc4_state s;
+    unsigned char buffer[30];
+
+    printf( "\n RC4 Validation Tests:\n\n" );
+
+    for( i = 0; i < 6; i++ )
+    {
+        printf( " Test %d ", i + 1 );
+
+        memcpy( buffer, data[i], data_len[i] );
+
+        rc4_setup( &s, &keys[i][1], keys[i][0] );
+        rc4_crypt( &s, buffer, data_len[i] );
+
+        if( memcmp( buffer, output[i], data_len[i] ) )
+        {
+            printf( "failed!\n" );
+            return( 1 );
+        }
+
+        printf( "passed.\n" );
+    }
+
+    printf( "\n" );
+
+    return( 0 );
+}
+
+#endif
diff --git a/lib/sha1.c b/lib/sha1.c
new file mode 100644
index 0000000..7064825
--- /dev/null
+++ b/lib/sha1.c
@@ -0,0 +1,385 @@
+/*
+ *  FIPS-180-1 compliant SHA-1 implementation
+ *
+ *  Copyright (C) 2001-2003  Christophe Devine
+ *
+ *  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 of the License, 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
+ */
+
+#include <string.h>
+
+#include "sha1.h"
+
+#define GET_UINT32(n,b,i)                       \
+{                                               \
+    (n) = ( (uint32) (b)[(i)    ] << 24 )       \
+        | ( (uint32) (b)[(i) + 1] << 16 )       \
+        | ( (uint32) (b)[(i) + 2] <<  8 )       \
+        | ( (uint32) (b)[(i) + 3]       );      \
+}
+
+#define PUT_UINT32(n,b,i)                       \
+{                                               \
+    (b)[(i)    ] = (uint8) ( (n) >> 24 );       \
+    (b)[(i) + 1] = (uint8) ( (n) >> 16 );       \
+    (b)[(i) + 2] = (uint8) ( (n) >>  8 );       \
+    (b)[(i) + 3] = (uint8) ( (n)       );       \
+}
+
+void sha1_starts( sha1_context *ctx )
+{
+    ctx->total[0] = 0;
+    ctx->total[1] = 0;
+
+    ctx->state[0] = 0x67452301;
+    ctx->state[1] = 0xEFCDAB89;
+    ctx->state[2] = 0x98BADCFE;
+    ctx->state[3] = 0x10325476;
+    ctx->state[4] = 0xC3D2E1F0;
+}
+
+void sha1_process( sha1_context *ctx, uint8 data[64] )
+{
+    uint32 temp, W[16], A, B, C, D, E;
+
+    GET_UINT32( W[0],  data,  0 );
+    GET_UINT32( W[1],  data,  4 );
+    GET_UINT32( W[2],  data,  8 );
+    GET_UINT32( W[3],  data, 12 );
+    GET_UINT32( W[4],  data, 16 );
+    GET_UINT32( W[5],  data, 20 );
+    GET_UINT32( W[6],  data, 24 );
+    GET_UINT32( W[7],  data, 28 );
+    GET_UINT32( W[8],  data, 32 );
+    GET_UINT32( W[9],  data, 36 );
+    GET_UINT32( W[10], data, 40 );
+    GET_UINT32( W[11], data, 44 );
+    GET_UINT32( W[12], data, 48 );
+    GET_UINT32( W[13], data, 52 );
+    GET_UINT32( W[14], data, 56 );
+    GET_UINT32( W[15], data, 60 );
+
+#define S(x,n) ((x << n) | ((x & 0xFFFFFFFF) >> (32 - n)))
+
+#define R(t)                                            \
+(                                                       \
+    temp = W[(t -  3) & 0x0F] ^ W[(t - 8) & 0x0F] ^     \
+           W[(t - 14) & 0x0F] ^ W[ t      & 0x0F],      \
+    ( W[t & 0x0F] = S(temp,1) )                         \
+)
+
+#define P(a,b,c,d,e,x)                                  \
+{                                                       \
+    e += S(a,5) + F(b,c,d) + K + x; b = S(b,30);        \
+}
+
+    A = ctx->state[0];
+    B = ctx->state[1];
+    C = ctx->state[2];
+    D = ctx->state[3];
+    E = ctx->state[4];
+
+#define F(x,y,z) (z ^ (x & (y ^ z)))
+#define K 0x5A827999
+
+    P( A, B, C, D, E, W[0]  );
+    P( E, A, B, C, D, W[1]  );
+    P( D, E, A, B, C, W[2]  );
+    P( C, D, E, A, B, W[3]  );
+    P( B, C, D, E, A, W[4]  );
+    P( A, B, C, D, E, W[5]  );
+    P( E, A, B, C, D, W[6]  );
+    P( D, E, A, B, C, W[7]  );
+    P( C, D, E, A, B, W[8]  );
+    P( B, C, D, E, A, W[9]  );
+    P( A, B, C, D, E, W[10] );
+    P( E, A, B, C, D, W[11] );
+    P( D, E, A, B, C, W[12] );
+    P( C, D, E, A, B, W[13] );
+    P( B, C, D, E, A, W[14] );
+    P( A, B, C, D, E, W[15] );
+    P( E, A, B, C, D, R(16) );
+    P( D, E, A, B, C, R(17) );
+    P( C, D, E, A, B, R(18) );
+    P( B, C, D, E, A, R(19) );
+
+#undef K
+#undef F
+
+#define F(x,y,z) (x ^ y ^ z)
+#define K 0x6ED9EBA1
+
+    P( A, B, C, D, E, R(20) );
+    P( E, A, B, C, D, R(21) );
+    P( D, E, A, B, C, R(22) );
+    P( C, D, E, A, B, R(23) );
+    P( B, C, D, E, A, R(24) );
+    P( A, B, C, D, E, R(25) );
+    P( E, A, B, C, D, R(26) );
+    P( D, E, A, B, C, R(27) );
+    P( C, D, E, A, B, R(28) );
+    P( B, C, D, E, A, R(29) );
+    P( A, B, C, D, E, R(30) );
+    P( E, A, B, C, D, R(31) );
+    P( D, E, A, B, C, R(32) );
+    P( C, D, E, A, B, R(33) );
+    P( B, C, D, E, A, R(34) );
+    P( A, B, C, D, E, R(35) );
+    P( E, A, B, C, D, R(36) );
+    P( D, E, A, B, C, R(37) );
+    P( C, D, E, A, B, R(38) );
+    P( B, C, D, E, A, R(39) );
+
+#undef K
+#undef F
+
+#define F(x,y,z) ((x & y) | (z & (x | y)))
+#define K 0x8F1BBCDC
+
+    P( A, B, C, D, E, R(40) );
+    P( E, A, B, C, D, R(41) );
+    P( D, E, A, B, C, R(42) );
+    P( C, D, E, A, B, R(43) );
+    P( B, C, D, E, A, R(44) );
+    P( A, B, C, D, E, R(45) );
+    P( E, A, B, C, D, R(46) );
+    P( D, E, A, B, C, R(47) );
+    P( C, D, E, A, B, R(48) );
+    P( B, C, D, E, A, R(49) );
+    P( A, B, C, D, E, R(50) );
+    P( E, A, B, C, D, R(51) );
+    P( D, E, A, B, C, R(52) );
+    P( C, D, E, A, B, R(53) );
+    P( B, C, D, E, A, R(54) );
+    P( A, B, C, D, E, R(55) );
+    P( E, A, B, C, D, R(56) );
+    P( D, E, A, B, C, R(57) );
+    P( C, D, E, A, B, R(58) );
+    P( B, C, D, E, A, R(59) );
+
+#undef K
+#undef F
+
+#define F(x,y,z) (x ^ y ^ z)
+#define K 0xCA62C1D6
+
+    P( A, B, C, D, E, R(60) );
+    P( E, A, B, C, D, R(61) );
+    P( D, E, A, B, C, R(62) );
+    P( C, D, E, A, B, R(63) );
+    P( B, C, D, E, A, R(64) );
+    P( A, B, C, D, E, R(65) );
+    P( E, A, B, C, D, R(66) );
+    P( D, E, A, B, C, R(67) );
+    P( C, D, E, A, B, R(68) );
+    P( B, C, D, E, A, R(69) );
+    P( A, B, C, D, E, R(70) );
+    P( E, A, B, C, D, R(71) );
+    P( D, E, A, B, C, R(72) );
+    P( C, D, E, A, B, R(73) );
+    P( B, C, D, E, A, R(74) );
+    P( A, B, C, D, E, R(75) );
+    P( E, A, B, C, D, R(76) );
+    P( D, E, A, B, C, R(77) );
+    P( C, D, E, A, B, R(78) );
+    P( B, C, D, E, A, R(79) );
+
+#undef K
+#undef F
+
+    ctx->state[0] += A;
+    ctx->state[1] += B;
+    ctx->state[2] += C;
+    ctx->state[3] += D;
+    ctx->state[4] += E;
+}
+
+void sha1_update( sha1_context *ctx, uint8 *input, uint32 length )
+{
+    uint32 left, fill;
+
+    if( ! length ) return;
+
+    left = ctx->total[0] & 0x3F;
+    fill = 64 - left;
+
+    ctx->total[0] += length;
+    ctx->total[0] &= 0xFFFFFFFF;
+
+    if( ctx->total[0] < length )
+        ctx->total[1]++;
+
+    if( left && length >= fill )
+    {
+        memcpy( (void *) (ctx->buffer + left),
+                (void *) input, fill );
+        sha1_process( ctx, ctx->buffer );
+        length -= fill;
+        input  += fill;
+        left = 0;
+    }
+
+    while( length >= 64 )
+    {
+        sha1_process( ctx, input );
+        length -= 64;
+        input  += 64;
+    }
+
+    if( length )
+    {
+        memcpy( (void *) (ctx->buffer + left),
+                (void *) input, length );
+    }
+}
+
+static uint8 sha1_padding[64] =
+{
+ 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
+};
+
+void sha1_finish( sha1_context *ctx, uint8 digest[20] )
+{
+    uint32 last, padn;
+    uint32 high, low;
+    uint8 msglen[8];
+
+    high = ( ctx->total[0] >> 29 )
+         | ( ctx->total[1] <<  3 );
+    low  = ( ctx->total[0] <<  3 );
+
+    PUT_UINT32( high, msglen, 0 );
+    PUT_UINT32( low,  msglen, 4 );
+
+    last = ctx->total[0] & 0x3F;
+    padn = ( last < 56 ) ? ( 56 - last ) : ( 120 - last );
+
+    sha1_update( ctx, sha1_padding, padn );
+    sha1_update( ctx, msglen, 8 );
+
+    PUT_UINT32( ctx->state[0], digest,  0 );
+    PUT_UINT32( ctx->state[1], digest,  4 );
+    PUT_UINT32( ctx->state[2], digest,  8 );
+    PUT_UINT32( ctx->state[3], digest, 12 );
+    PUT_UINT32( ctx->state[4], digest, 16 );
+}
+
+#ifdef TEST
+
+#include <stdlib.h>
+#include <stdio.h>
+
+/*
+ * those are the standard FIPS-180-1 test vectors
+ */
+
+static char *msg[] = 
+{
+    "abc",
+    "abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq",
+    NULL
+};
+
+static char *val[] =
+{
+    "a9993e364706816aba3e25717850c26c9cd0d89d",
+    "84983e441c3bd26ebaae4aa1f95129e5e54670f1",
+    "34aa973cd4c4daa4f61eeb2bdbad27316534016f"
+};
+
+int main( int argc, char *argv[] )
+{
+    FILE *f;
+    int i, j;
+    char output[41];
+    sha1_context ctx;
+    unsigned char buf[1000];
+    unsigned char sha1sum[20];
+
+    if( argc < 2 )
+    {
+        printf( "\n SHA-1 Validation Tests:\n\n" );
+
+        for( i = 0; i < 3; i++ )
+        {
+            printf( " Test %d ", i + 1 );
+
+            sha1_starts( &ctx );
+
+            if( i < 2 )
+            {
+                sha1_update( &ctx, (uint8 *) msg[i],
+                             strlen( msg[i] ) );
+            }
+            else
+            {
+                memset( buf, 'a', 1000 );
+
+                for( j = 0; j < 1000; j++ )
+                {
+                    sha1_update( &ctx, (uint8 *) buf, 1000 );
+                }
+            }
+
+            sha1_finish( &ctx, sha1sum );
+
+            for( j = 0; j < 20; j++ )
+            {
+                sprintf( output + j * 2, "%02x", sha1sum[j] );
+            }
+
+            if( memcmp( output, val[i], 40 ) )
+            {
+                printf( "failed!\n" );
+                return( 1 );
+            }
+
+            printf( "passed.\n" );
+        }
+
+        printf( "\n" );
+    }
+    else
+    {
+        if( ! ( f = fopen( argv[1], "rb" ) ) )
+        {
+            perror( "fopen" );
+            return( 1 );
+        }
+
+        sha1_starts( &ctx );
+
+        while( ( i = fread( buf, 1, sizeof( buf ), f ) ) > 0 )
+        {
+            sha1_update( &ctx, buf, i );
+        }
+
+        sha1_finish( &ctx, sha1sum );
+
+        for( j = 0; j < 20; j++ )
+        {
+            printf( "%02x", sha1sum[j] );
+        }
+
+        printf( "  %s\n", argv[1] );
+    }
+
+    return( 0 );
+}
+
+#endif
diff --git a/lib/sha256.c b/lib/sha256.c
new file mode 100644
index 0000000..0b94581
--- /dev/null
+++ b/lib/sha256.c
@@ -0,0 +1,369 @@
+/*
+ *  FIPS-180-2 compliant SHA-256 implementation
+ *
+ *  Copyright (C) 2001-2003  Christophe Devine
+ *
+ *  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 of the License, 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
+ */
+
+#include <string.h>
+
+#include "sha256.h"
+
+#define GET_UINT32(n,b,i)                       \
+{                                               \
+    (n) = ( (uint32) (b)[(i)    ] << 24 )       \
+        | ( (uint32) (b)[(i) + 1] << 16 )       \
+        | ( (uint32) (b)[(i) + 2] <<  8 )       \
+        | ( (uint32) (b)[(i) + 3]       );      \
+}
+
+#define PUT_UINT32(n,b,i)                       \
+{                                               \
+    (b)[(i)    ] = (uint8) ( (n) >> 24 );       \
+    (b)[(i) + 1] = (uint8) ( (n) >> 16 );       \
+    (b)[(i) + 2] = (uint8) ( (n) >>  8 );       \
+    (b)[(i) + 3] = (uint8) ( (n)       );       \
+}
+
+void sha256_starts( sha256_context *ctx )
+{
+    ctx->total[0] = 0;
+    ctx->total[1] = 0;
+
+    ctx->state[0] = 0x6A09E667;
+    ctx->state[1] = 0xBB67AE85;
+    ctx->state[2] = 0x3C6EF372;
+    ctx->state[3] = 0xA54FF53A;
+    ctx->state[4] = 0x510E527F;
+    ctx->state[5] = 0x9B05688C;
+    ctx->state[6] = 0x1F83D9AB;
+    ctx->state[7] = 0x5BE0CD19;
+}
+
+void sha256_process( sha256_context *ctx, uint8 data[64] )
+{
+    uint32 temp1, temp2, W[64];
+    uint32 A, B, C, D, E, F, G, H;
+
+    GET_UINT32( W[0],  data,  0 );
+    GET_UINT32( W[1],  data,  4 );
+    GET_UINT32( W[2],  data,  8 );
+    GET_UINT32( W[3],  data, 12 );
+    GET_UINT32( W[4],  data, 16 );
+    GET_UINT32( W[5],  data, 20 );
+    GET_UINT32( W[6],  data, 24 );
+    GET_UINT32( W[7],  data, 28 );
+    GET_UINT32( W[8],  data, 32 );
+    GET_UINT32( W[9],  data, 36 );
+    GET_UINT32( W[10], data, 40 );
+    GET_UINT32( W[11], data, 44 );
+    GET_UINT32( W[12], data, 48 );
+    GET_UINT32( W[13], data, 52 );
+    GET_UINT32( W[14], data, 56 );
+    GET_UINT32( W[15], data, 60 );
+
+#define  SHR(x,n) ((x & 0xFFFFFFFF) >> n)
+#define ROTR(x,n) (SHR(x,n) | (x << (32 - n)))
+
+#define S0(x) (ROTR(x, 7) ^ ROTR(x,18) ^  SHR(x, 3))
+#define S1(x) (ROTR(x,17) ^ ROTR(x,19) ^  SHR(x,10))
+
+#define S2(x) (ROTR(x, 2) ^ ROTR(x,13) ^ ROTR(x,22))
+#define S3(x) (ROTR(x, 6) ^ ROTR(x,11) ^ ROTR(x,25))
+
+#define F0(x,y,z) ((x & y) | (z & (x | y)))
+#define F1(x,y,z) (z ^ (x & (y ^ z)))
+
+#define R(t)                                    \
+(                                               \
+    W[t] = S1(W[t -  2]) + W[t -  7] +          \
+           S0(W[t - 15]) + W[t - 16]            \
+)
+
+#define P(a,b,c,d,e,f,g,h,x,K)                  \
+{                                               \
+    temp1 = h + S3(e) + F1(e,f,g) + K + x;      \
+    temp2 = S2(a) + F0(a,b,c);                  \
+    d += temp1; h = temp1 + temp2;              \
+}
+
+    A = ctx->state[0];
+    B = ctx->state[1];
+    C = ctx->state[2];
+    D = ctx->state[3];
+    E = ctx->state[4];
+    F = ctx->state[5];
+    G = ctx->state[6];
+    H = ctx->state[7];
+
+    P( A, B, C, D, E, F, G, H, W[ 0], 0x428A2F98 );
+    P( H, A, B, C, D, E, F, G, W[ 1], 0x71374491 );
+    P( G, H, A, B, C, D, E, F, W[ 2], 0xB5C0FBCF );
+    P( F, G, H, A, B, C, D, E, W[ 3], 0xE9B5DBA5 );
+    P( E, F, G, H, A, B, C, D, W[ 4], 0x3956C25B );
+    P( D, E, F, G, H, A, B, C, W[ 5], 0x59F111F1 );
+    P( C, D, E, F, G, H, A, B, W[ 6], 0x923F82A4 );
+    P( B, C, D, E, F, G, H, A, W[ 7], 0xAB1C5ED5 );
+    P( A, B, C, D, E, F, G, H, W[ 8], 0xD807AA98 );
+    P( H, A, B, C, D, E, F, G, W[ 9], 0x12835B01 );
+    P( G, H, A, B, C, D, E, F, W[10], 0x243185BE );
+    P( F, G, H, A, B, C, D, E, W[11], 0x550C7DC3 );
+    P( E, F, G, H, A, B, C, D, W[12], 0x72BE5D74 );
+    P( D, E, F, G, H, A, B, C, W[13], 0x80DEB1FE );
+    P( C, D, E, F, G, H, A, B, W[14], 0x9BDC06A7 );
+    P( B, C, D, E, F, G, H, A, W[15], 0xC19BF174 );
+    P( A, B, C, D, E, F, G, H, R(16), 0xE49B69C1 );
+    P( H, A, B, C, D, E, F, G, R(17), 0xEFBE4786 );
+    P( G, H, A, B, C, D, E, F, R(18), 0x0FC19DC6 );
+    P( F, G, H, A, B, C, D, E, R(19), 0x240CA1CC );
+    P( E, F, G, H, A, B, C, D, R(20), 0x2DE92C6F );
+    P( D, E, F, G, H, A, B, C, R(21), 0x4A7484AA );
+    P( C, D, E, F, G, H, A, B, R(22), 0x5CB0A9DC );
+    P( B, C, D, E, F, G, H, A, R(23), 0x76F988DA );
+    P( A, B, C, D, E, F, G, H, R(24), 0x983E5152 );
+    P( H, A, B, C, D, E, F, G, R(25), 0xA831C66D );
+    P( G, H, A, B, C, D, E, F, R(26), 0xB00327C8 );
+    P( F, G, H, A, B, C, D, E, R(27), 0xBF597FC7 );
+    P( E, F, G, H, A, B, C, D, R(28), 0xC6E00BF3 );
+    P( D, E, F, G, H, A, B, C, R(29), 0xD5A79147 );
+    P( C, D, E, F, G, H, A, B, R(30), 0x06CA6351 );
+    P( B, C, D, E, F, G, H, A, R(31), 0x14292967 );
+    P( A, B, C, D, E, F, G, H, R(32), 0x27B70A85 );
+    P( H, A, B, C, D, E, F, G, R(33), 0x2E1B2138 );
+    P( G, H, A, B, C, D, E, F, R(34), 0x4D2C6DFC );
+    P( F, G, H, A, B, C, D, E, R(35), 0x53380D13 );
+    P( E, F, G, H, A, B, C, D, R(36), 0x650A7354 );
+    P( D, E, F, G, H, A, B, C, R(37), 0x766A0ABB );
+    P( C, D, E, F, G, H, A, B, R(38), 0x81C2C92E );
+    P( B, C, D, E, F, G, H, A, R(39), 0x92722C85 );
+    P( A, B, C, D, E, F, G, H, R(40), 0xA2BFE8A1 );
+    P( H, A, B, C, D, E, F, G, R(41), 0xA81A664B );
+    P( G, H, A, B, C, D, E, F, R(42), 0xC24B8B70 );
+    P( F, G, H, A, B, C, D, E, R(43), 0xC76C51A3 );
+    P( E, F, G, H, A, B, C, D, R(44), 0xD192E819 );
+    P( D, E, F, G, H, A, B, C, R(45), 0xD6990624 );
+    P( C, D, E, F, G, H, A, B, R(46), 0xF40E3585 );
+    P( B, C, D, E, F, G, H, A, R(47), 0x106AA070 );
+    P( A, B, C, D, E, F, G, H, R(48), 0x19A4C116 );
+    P( H, A, B, C, D, E, F, G, R(49), 0x1E376C08 );
+    P( G, H, A, B, C, D, E, F, R(50), 0x2748774C );
+    P( F, G, H, A, B, C, D, E, R(51), 0x34B0BCB5 );
+    P( E, F, G, H, A, B, C, D, R(52), 0x391C0CB3 );
+    P( D, E, F, G, H, A, B, C, R(53), 0x4ED8AA4A );
+    P( C, D, E, F, G, H, A, B, R(54), 0x5B9CCA4F );
+    P( B, C, D, E, F, G, H, A, R(55), 0x682E6FF3 );
+    P( A, B, C, D, E, F, G, H, R(56), 0x748F82EE );
+    P( H, A, B, C, D, E, F, G, R(57), 0x78A5636F );
+    P( G, H, A, B, C, D, E, F, R(58), 0x84C87814 );
+    P( F, G, H, A, B, C, D, E, R(59), 0x8CC70208 );
+    P( E, F, G, H, A, B, C, D, R(60), 0x90BEFFFA );
+    P( D, E, F, G, H, A, B, C, R(61), 0xA4506CEB );
+    P( C, D, E, F, G, H, A, B, R(62), 0xBEF9A3F7 );
+    P( B, C, D, E, F, G, H, A, R(63), 0xC67178F2 );
+
+    ctx->state[0] += A;
+    ctx->state[1] += B;
+    ctx->state[2] += C;
+    ctx->state[3] += D;
+    ctx->state[4] += E;
+    ctx->state[5] += F;
+    ctx->state[6] += G;
+    ctx->state[7] += H;
+}
+
+void sha256_update( sha256_context *ctx, uint8 *input, uint32 length )
+{
+    uint32 left, fill;
+
+    if( ! length ) return;
+
+    left = ctx->total[0] & 0x3F;
+    fill = 64 - left;
+
+    ctx->total[0] += length;
+    ctx->total[0] &= 0xFFFFFFFF;
+
+    if( ctx->total[0] < length )
+        ctx->total[1]++;
+
+    if( left && length >= fill )
+    {
+        memcpy( (void *) (ctx->buffer + left),
+                (void *) input, fill );
+        sha256_process( ctx, ctx->buffer );
+        length -= fill;
+        input  += fill;
+        left = 0;
+    }
+
+    while( length >= 64 )
+    {
+        sha256_process( ctx, input );
+        length -= 64;
+        input  += 64;
+    }
+
+    if( length )
+    {
+        memcpy( (void *) (ctx->buffer + left),
+                (void *) input, length );
+    }
+}
+
+static uint8 sha256_padding[64] =
+{
+ 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
+};
+
+void sha256_finish( sha256_context *ctx, uint8 digest[32] )
+{
+    uint32 last, padn;
+    uint32 high, low;
+    uint8 msglen[8];
+
+    high = ( ctx->total[0] >> 29 )
+         | ( ctx->total[1] <<  3 );
+    low  = ( ctx->total[0] <<  3 );
+
+    PUT_UINT32( high, msglen, 0 );
+    PUT_UINT32( low,  msglen, 4 );
+
+    last = ctx->total[0] & 0x3F;
+    padn = ( last < 56 ) ? ( 56 - last ) : ( 120 - last );
+
+    sha256_update( ctx, sha256_padding, padn );
+    sha256_update( ctx, msglen, 8 );
+
+    PUT_UINT32( ctx->state[0], digest,  0 );
+    PUT_UINT32( ctx->state[1], digest,  4 );
+    PUT_UINT32( ctx->state[2], digest,  8 );
+    PUT_UINT32( ctx->state[3], digest, 12 );
+    PUT_UINT32( ctx->state[4], digest, 16 );
+    PUT_UINT32( ctx->state[5], digest, 20 );
+    PUT_UINT32( ctx->state[6], digest, 24 );
+    PUT_UINT32( ctx->state[7], digest, 28 );
+}
+
+#ifdef TEST
+
+#include <stdlib.h>
+#include <stdio.h>
+
+/*
+ * those are the standard FIPS-180-2 test vectors
+ */
+
+static char *msg[] = 
+{
+    "abc",
+    "abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq",
+    NULL
+};
+
+static char *val[] =
+{
+    "ba7816bf8f01cfea414140de5dae2223" \
+    "b00361a396177a9cb410ff61f20015ad",
+    "248d6a61d20638b8e5c026930c3e6039" \
+    "a33ce45964ff2167f6ecedd419db06c1",
+    "cdc76e5c9914fb9281a1c7e284d73e67" \
+    "f1809a48a497200e046d39ccc7112cd0"
+};
+
+int main( int argc, char *argv[] )
+{
+    FILE *f;
+    int i, j;
+    char output[65];
+    sha256_context ctx;
+    unsigned char buf[1000];
+    unsigned char sha256sum[32];
+
+    if( argc < 2 )
+    {
+        printf( "\n SHA-256 Validation Tests:\n\n" );
+
+        for( i = 0; i < 3; i++ )
+        {
+            printf( " Test %d ", i + 1 );
+
+            sha256_starts( &ctx );
+
+            if( i < 2 )
+            {
+                sha256_update( &ctx, (uint8 *) msg[i],
+                               strlen( msg[i] ) );
+            }
+            else
+            {
+                memset( buf, 'a', 1000 );
+
+                for( j = 0; j < 1000; j++ )
+                {
+                    sha256_update( &ctx, (uint8 *) buf, 1000 );
+                }
+            }
+
+            sha256_finish( &ctx, sha256sum );
+
+            for( j = 0; j < 32; j++ )
+            {
+                sprintf( output + j * 2, "%02x", sha256sum[j] );
+            }
+
+            if( memcmp( output, val[i], 64 ) )
+            {
+                printf( "failed!\n" );
+                return( 1 );
+            }
+
+            printf( "passed.\n" );
+        }
+
+        printf( "\n" );
+    }
+    else
+    {
+        if( ! ( f = fopen( argv[1], "rb" ) ) )
+        {
+            perror( "fopen" );
+            return( 1 );
+        }
+
+        sha256_starts( &ctx );
+
+        while( ( i = fread( buf, 1, sizeof( buf ), f ) ) > 0 )
+        {
+            sha256_update( &ctx, buf, i );
+        }
+
+        sha256_finish( &ctx, sha256sum );
+
+        for( j = 0; j < 32; j++ )
+        {
+            printf( "%02x", sha256sum[j] );
+        }
+
+        printf( "  %s\n", argv[1] );
+    }
+
+    return( 0 );
+}
+
+#endif