/* * Character Set Handling * (C) 1999-2007 Jack Lloyd * * Distributed under the terms of the Botan license */ #include <botan/charset.h> #include <botan/parsing.h> #include <botan/exceptn.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))); } } }