/*************************************************
* Character Set Handling Source File             *
* (C) 1999-2007 Jack Lloyd                       *
*************************************************/

#include <botan/charset.h>
#include <botan/hex.h>
#include <botan/base64.h>
#include <botan/parsing.h>
#include <cctype>

namespace Botan {

namespace Charset {

namespace {

/*************************************************
* Convert from UCS-2 to ISO 8859-1               *
*************************************************/
std::string ucs2_to_latin1(const std::string& ucs2)
   {
   if(ucs2.size() % 2 == 1)
      throw Decoding_Error("UCS-2 string has an odd number of bytes");

   std::string latin1;

   for(u32bit j = 0; j != ucs2.size(); j += 2)
      {
      const byte c1 = ucs2[j];
      const byte c2 = ucs2[j+1];

      if(c1 != 0)
         throw Decoding_Error("UCS-2 has non-Latin1 characters");

      latin1 += static_cast<char>(c2);
      }

   return latin1;
   }

/*************************************************
* Convert from UTF-8 to ISO 8859-1               *
*************************************************/
std::string utf8_to_latin1(const std::string& utf8)
   {
   std::string iso8859;

   u32bit position = 0;
   while(position != utf8.size())
      {
      const byte c1 = static_cast<byte>(utf8[position++]);

      if(c1 <= 0x7F)
         iso8859 += static_cast<char>(c1);
      else if(c1 >= 0xC0 && c1 <= 0xC7)
         {
         if(position == utf8.size())
            throw Decoding_Error("UTF-8: sequence truncated");

         const byte c2 = static_cast<byte>(utf8[position++]);
         const byte iso_char = ((c1 & 0x07) << 6) | (c2 & 0x3F);

         if(iso_char <= 0x7F)
            throw Decoding_Error("UTF-8: sequence longer than needed");

         iso8859 += static_cast<char>(iso_char);
         }
      else
         throw Decoding_Error("UTF-8: Unicode chars not in Latin1 used");
      }

   return iso8859;
   }

/*************************************************
* Convert from ISO 8859-1 to UTF-8               *
*************************************************/
std::string latin1_to_utf8(const std::string& iso8859)
   {
   std::string utf8;
   for(u32bit j = 0; j != iso8859.size(); ++j)
      {
      const byte c = static_cast<byte>(iso8859[j]);

      if(c <= 0x7F)
         utf8 += static_cast<char>(c);
      else
         {
         utf8 += static_cast<char>((0xC0 | (c >> 6)));
         utf8 += static_cast<char>((0x80 | (c & 0x3F)));
         }
      }
   return utf8;
   }

}

/*************************************************
* Perform character set transcoding              *
*************************************************/
std::string transcode(const std::string& str,
                      Character_Set to, Character_Set from)
   {
   if(to == LOCAL_CHARSET)
      to = LATIN1_CHARSET;
   if(from == LOCAL_CHARSET)
      from = LATIN1_CHARSET;

   if(to == from)
      return str;

   if(from == LATIN1_CHARSET && to == UTF8_CHARSET)
      return latin1_to_utf8(str);
   if(from == UTF8_CHARSET && to == LATIN1_CHARSET)
      return utf8_to_latin1(str);
   if(from == UCS2_CHARSET && to == LATIN1_CHARSET)
      return ucs2_to_latin1(str);

   throw Invalid_Argument("Unknown transcoding operation from " +
                          to_string(from) + " to " + to_string(to));
   }

/*************************************************
* Check if a character represents a digit        *
*************************************************/
bool is_digit(char c)
   {
   if(c == '0' || c == '1' || c == '2' || c == '3' || c == '4' ||
      c == '5' || c == '6' || c == '7' || c == '8' || c == '9')
      return true;
   return false;
   }

/*************************************************
* Check if a character represents whitespace     *
*************************************************/
bool is_space(char c)
   {
   if(c == ' ' || c == '\t' || c == '\n' || c == '\r')
      return true;
   return false;
   }

/*************************************************
* Convert a character to a digit                 *
*************************************************/
byte char2digit(char c)
   {
   switch(c)
      {
      case '0': return 0;
      case '1': return 1;
      case '2': return 2;
      case '3': return 3;
      case '4': return 4;
      case '5': return 5;
      case '6': return 6;
      case '7': return 7;
      case '8': return 8;
      case '9': return 9;
      }

   throw Invalid_Argument("char2digit: Input is not a digit character");
   }

/*************************************************
* Convert a digit to a character                 *
*************************************************/
char digit2char(byte b)
   {
   switch(b)
      {
      case 0: return '0';
      case 1: return '1';
      case 2: return '2';
      case 3: return '3';
      case 4: return '4';
      case 5: return '5';
      case 6: return '6';
      case 7: return '7';
      case 8: return '8';
      case 9: return '9';
      }

   throw Invalid_Argument("digit2char: Input is not a digit");
   }

/*************************************************
* Case-insensitive character comparison          *
*************************************************/
bool caseless_cmp(char a, char b)
   {
   return (std::tolower(static_cast<unsigned char>(a)) ==
           std::tolower(static_cast<unsigned char>(b)));
   }

}

/*************************************************
* Hex Encoder Lookup Tables                      *
*************************************************/
const byte Hex_Encoder::BIN_TO_HEX_UPPER[16] = {
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x41, 0x42, 0x43,
0x44, 0x45, 0x46 };

const byte Hex_Encoder::BIN_TO_HEX_LOWER[16] = {
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x61, 0x62, 0x63,
0x64, 0x65, 0x66 };

/*************************************************
* Base64 Encoder Lookup Table                    *
*************************************************/
const byte Base64_Encoder::BIN_TO_BASE64[64] = {
0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D,
0x4E, 0x4F, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A,
0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D,
0x6E, 0x6F, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A,
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x2B, 0x2F };

/*************************************************
* Hex Decoder Lookup Table                       *
*************************************************/
const byte Hex_Decoder::HEX_TO_BIN[256] = {
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x00, 0x01, 0x02, 0x03,
0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };

/*************************************************
* Base64 Decoder Lookup Table                    *
*************************************************/
const byte Base64_Decoder::BASE64_TO_BIN[256] = {
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x3E, 0x80, 0x80, 0x80, 0x3F, 0x34, 0x35, 0x36, 0x37,
0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0A, 0x0B, 0x0C,
0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F, 0x20,
0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D,
0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80,
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };

}