#include "strutils.hxx"
+#include <simgear/debug/logstream.hxx>
+
using std::string;
using std::vector;
using std::stringstream;
namespace simgear {
namespace strutils {
+ /*
+ * utf8ToLatin1() convert utf8 to latin, useful for accent character (i.e éâàîè...)
+ */
+ template <typename Iterator> size_t get_length (Iterator p) {
+ unsigned char c = static_cast<unsigned char> (*p);
+ if (c < 0x80) return 1;
+ else if (!(c & 0x20)) return 2;
+ else if (!(c & 0x10)) return 3;
+ else if (!(c & 0x08)) return 4;
+ else if (!(c & 0x04)) return 5;
+ else return 6;
+ }
+
+ typedef unsigned int value_type;
+ template <typename Iterator> value_type get_value (Iterator p) {
+ size_t len = get_length (p);
+ if (len == 1) return *p;
+ value_type res = static_cast<unsigned char> ( *p & (0xff >> (len + 1))) << ((len - 1) * 6 );
+ for (--len; len; --len)
+ res |= (static_cast<unsigned char> (*(++p)) - 0x80) << ((len - 1) * 6);
+ return res;
+ }
+
+ string utf8ToLatin1( string& s_utf8 ) {
+ string s_latin1;
+ for (string::iterator p = s_utf8.begin(); p != s_utf8.end(); ++p) {
+ value_type value = get_value<string::iterator&>(p);
+ if (value > 0xff) SG_LOG(SG_IO, SG_WARN, "utf8ToLatin1: wrong char value: " << value);
+ s_latin1 += static_cast<char>(value);
+ }
+ return s_latin1;
+ }
+
/**
*
*/
return rslt;
}
+ string lowercase(const string &s) {
+ string rslt(s);
+ for(string::iterator p = rslt.begin(); p != rslt.end(); p++){
+ *p = tolower(*p);
+ }
+ return rslt;
+ }
+
+ void lowercase(string &s) {
+ for(string::iterator p = s.begin(); p != s.end(); p++){
+ *p = tolower(*p);
+ }
+ }
+
+#if defined(SG_WINDOWS)
+
+#include <windows.h>
+
+static WCharVec convertMultiByteToWString(DWORD encoding, const std::string& a)
+{
+ WCharVec result;
+ DWORD flags = 0;
+ int requiredWideChars = MultiByteToWideChar(encoding, flags,
+ a.c_str(), a.size(),
+ NULL, 0);
+ result.resize(requiredWideChars);
+ MultiByteToWideChar(encoding, flags, a.c_str(), a.size(),
+ result.data(), result.size());
+ return result;
+}
+
+WCharVec convertUtf8ToWString(const std::string& a)
+{
+ return convertMultiByteToWString(CP_UTF8, a);
+}
-#ifdef SG_WINDOWS
- #include <windows.h>
#endif
-
+
std::string convertWindowsLocal8BitToUtf8(const std::string& a)
{
#ifdef SG_WINDOWS
DWORD flags = 0;
- std::vector<wchar_t> wideString;
-
- // call to query transform size
- int requiredWideChars = MultiByteToWideChar(CP_ACP, flags, a.c_str(), a.size(),
- NULL, 0);
- // allocate storage and call for real
- wideString.resize(requiredWideChars);
- MultiByteToWideChar(CP_ACP, flags, a.c_str(), a.size(),
- wideString.data(), wideString.size());
-
- // now convert back down to UTF-8
+ WCharVec wideString = convertMultiByteToWString(CP_ACP, a);
+
+ // convert down to UTF-8
std::vector<char> result;
int requiredUTF8Chars = WideCharToMultiByte(CP_UTF8, flags,
wideString.data(), wideString.size(),
#endif
}
+
+
static const std::string base64_chars =
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz"
"0123456789+/";
-
+static const unsigned char base64_decode_map[128] =
+{
+ 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,
+ 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,
+ 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,
+ 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,
+ 127, 127, 127, 62, 127, 127, 127, 63, 52, 53,
+ 54, 55, 56, 57, 58, 59, 60, 61, 127, 127,
+ 127, 64, 127, 127, 127, 0, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
+ 25, 127, 127, 127, 127, 127, 127, 26, 27, 28,
+ 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
+ 39, 40, 41, 42, 43, 44, 45, 46, 47, 48,
+ 49, 50, 51, 127, 127, 127, 127, 127
+};
+
+
static inline bool is_base64(unsigned char c) {
return (isalnum(c) || (c == '+') || (c == '/'));
}
return ((c == ' ') || (c == '\r') || (c == '\n'));
}
-std::string decodeBase64(const std::string& encoded_string)
+void decodeBase64(const std::string& encoded_string, std::vector<unsigned char>& ret)
{
int in_len = encoded_string.size();
int i = 0;
int j = 0;
int in_ = 0;
unsigned char char_array_4[4], char_array_3[3];
- std::string ret;
while (in_len-- && ( encoded_string[in_] != '=')) {
if (is_whitespace( encoded_string[in_])) {
char_array_4[i++] = encoded_string[in_]; in_++;
if (i ==4) {
for (i = 0; i <4; i++)
- char_array_4[i] = base64_chars.find(char_array_4[i]);
+ char_array_4[i] = base64_decode_map[char_array_4[i]];
char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
for (i = 0; (i < 3); i++)
- ret += char_array_3[i];
+ ret.push_back(char_array_3[i]);
i = 0;
}
}
char_array_4[j] = 0;
for (j = 0; j <4; j++)
- char_array_4[j] = base64_chars.find(char_array_4[j]);
+ char_array_4[j] = base64_decode_map[char_array_4[j]];
char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
- for (j = 0; (j < i - 1); j++) ret += char_array_3[j];
+ for (j = 0; (j < i - 1); j++) ret.push_back(char_array_3[j]);
}
-
- return ret;
}
const char hexChar[] = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f'};
return r;
}
+string sanitizePrintfFormat(const string& input)
+{
+ string::size_type i = input.find("%n");
+ if (i != string::npos) {
+ SG_LOG(SG_IO, SG_WARN, "sanitizePrintfFormat: bad format string:" << input);
+ return string();
+ }
+
+ return input;
+}
+
} // end namespace strutils
} // end namespace simgear