The unified diff between revisions [69f6e5aa..] and [4e40e885..] is displayed below. It can also be downloaded as a raw diff.
This diff has been restricted to the following files: 'src/charset.cpp'
#
#
# patch "src/charset.cpp"
# from [14d1a75a91ab10610b89f57b7019bc173e4b2a32]
# to [ed45191ce62ae8c6bd98fa8cb040d82b1cd386ee]
#
============================================================
--- src/charset.cpp 14d1a75a91ab10610b89f57b7019bc173e4b2a32
+++ src/charset.cpp ed45191ce62ae8c6bd98fa8cb040d82b1cd386ee
@@ -1,25 +1,124 @@
/*************************************************
* Character Set Handling Source File *
-* (C) 1999-2006 The Botan Project *
+* (C) 1999-2007 Jack Lloyd *
*************************************************/
#include <botan/charset.h>
#include <botan/hex.h>
#include <botan/base64.h>
-#include <botan/libstate.h>
-#include <ctype.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)
{
- return global_state().transcode(str, to, 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));
}
/*************************************************
@@ -48,16 +147,19 @@ byte char2digit(char c)
*************************************************/
byte char2digit(char c)
{
- if(c == '0') return 0;
- if(c == '1') return 1;
- if(c == '2') return 2;
- if(c == '3') return 3;
- if(c == '4') return 4;
- if(c == '5') return 5;
- if(c == '6') return 6;
- if(c == '7') return 7;
- if(c == '8') return 8;
- if(c == '9') return 9;
+ 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");
}
@@ -67,16 +169,19 @@ char digit2char(byte b)
*************************************************/
char digit2char(byte b)
{
- if(b == 0) return '0';
- if(b == 1) return '1';
- if(b == 2) return '2';
- if(b == 3) return '3';
- if(b == 4) return '4';
- if(b == 5) return '5';
- if(b == 6) return '6';
- if(b == 7) return '7';
- if(b == 8) return '8';
- if(b == 9) return '9';
+ 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");
}
@@ -86,7 +191,8 @@ bool caseless_cmp(char a, char b)
*************************************************/
bool caseless_cmp(char a, char b)
{
- return (tolower((unsigned char)a) == tolower((unsigned char)b));
+ return (std::tolower(static_cast<unsigned char>(a)) ==
+ std::tolower(static_cast<unsigned char>(b)));
}
}