wxMac uses wxStandardPathsCF to mean wxStandardPaths in its wxBase

[wxWidgets.git] / src / common / strconv.cpp

diff --git a/src/common/strconv.cpp b/src/common/strconv.cpp
index e0e0def4dab52144752101e38bb899fc744842eb..83c06de9c69e3d7cc7f1a5c05d1ecd1394a3234e 100644 (file)
--- a/src/common/strconv.cpp
+++ b/src/common/strconv.cpp
@@ -1,12 +1,14 @@
 /////////////////////////////////////////////////////////////////////////////
 // Name:        strconv.cpp
 // Purpose:     Unicode conversion classes
 /////////////////////////////////////////////////////////////////////////////
 // Name:        strconv.cpp
 // Purpose:     Unicode conversion classes

-// Author:      Ove Kaaven, Robert Roebling, Vadim Zeitlin, Vaclav Slavik
+// Author:      Ove Kaaven, Robert Roebling, Vadim Zeitlin, Vaclav Slavik,
+//              Ryan Norton, Fredrik Roubert (UTF7)

 // Modified by:
 // Created:     29/01/98
 // RCS-ID:      $Id$
 // Copyright:   (c) 1999 Ove Kaaven, Robert Roebling, Vaclav Slavik
 //              (c) 2000-2003 Vadim Zeitlin
 // Modified by:
 // Created:     29/01/98
 // RCS-ID:      $Id$
 // Copyright:   (c) 1999 Ove Kaaven, Robert Roebling, Vaclav Slavik
 //              (c) 2000-2003 Vadim Zeitlin

+//              (c) 2004 Ryan Norton, Fredrik Roubert

 // Licence:     wxWindows licence
 /////////////////////////////////////////////////////////////////////////////
 
 // Licence:     wxWindows licence
 /////////////////////////////////////////////////////////////////////////////
 


@@ -168,7 +170,7 @@ static size_t decode_utf16(const wxUint16* input, wxUint32& output)
 
 wxMBConv::~wxMBConv()
 {
 
 wxMBConv::~wxMBConv()
 {

-    // nothing to do here
+    // nothing to do here (necessary for Darwin linking probably)

 }
 
 const wxWCharBuffer wxMBConv::cMB2WC(const char *psz) const
 }
 
 const wxWCharBuffer wxMBConv::cMB2WC(const char *psz) const


@@ -228,34 +230,210 @@ size_t wxMBConvLibc::WC2MB(char *buf, const wchar_t *psz, size_t n) const
 {
     return wxWC2MB(buf, psz, n);
 }
 {
     return wxWC2MB(buf, psz, n);
 }

-

 // ----------------------------------------------------------------------------
 // ----------------------------------------------------------------------------

-// UTF-7
+// UTF-7 

 // ----------------------------------------------------------------------------
 
 // ----------------------------------------------------------------------------
 

-#if 0
-static char utf7_setD[]="ABCDEFGHIJKLMNOPQRSTUVWXYZ"
-                        "abcdefghijklmnopqrstuvwxyz"
-                        "0123456789'(),-./:?";
-static char utf7_setO[]="!\"#$%&*;<=>@[]^_`{|}";
-static char utf7_setB[]="ABCDEFGHIJKLMNOPQRSTUVWXYZ"
-                        "abcdefghijklmnopqrstuvwxyz"
-                        "0123456789+/";
-#endif
+// Implementation (C) 2004 Fredrik Roubert
+
+//
+// BASE64 decoding table
+//
+static const unsigned char utf7unb64[] =
+{
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0x3e, 0xff, 0xff, 0xff, 0x3f,
+    0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b,
+    0x3c, 0x3d, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 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, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 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, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};

 
 

-// TODO: write actual implementations of UTF-7 here
-size_t wxMBConvUTF7::MB2WC(wchar_t * WXUNUSED(buf),
-                           const char * WXUNUSED(psz),
-                           size_t WXUNUSED(n)) const
+size_t wxMBConvUTF7::MB2WC(wchar_t *buf, const char *psz, size_t n) const

 {
 {

-  return 0;
+
+    size_t len = 0;
+
+    while (*psz && ((!buf) || (len < n)))
+    {
+        unsigned char cc = *psz++;
+        if (cc != '+')
+        {
+            // plain ASCII char
+            if (buf)
+                *buf++ = cc;
+            len++;
+        }
+        else if (*psz == '-')
+        {
+            // encoded plus sign
+            if (buf)
+                *buf++ = cc;
+            len++;
+            psz++;
+        }
+        else
+        {
+            // BASE64 encoded string
+            bool lsb;
+            unsigned char c;
+            unsigned int d, l;
+            for (lsb = false, d = 0, l = 0;
+                (cc = utf7unb64[(unsigned char)*psz]) != 0xff; psz++)
+            {
+                d <<= 6;
+                d += cc;
+                for (l += 6; l >= 8; lsb = !lsb)
+                {
+                    c = (d >> (l -= 8)) % 256;
+                    if (lsb)
+                    {
+                        if (buf)
+                            *buf++ |= c;
+                        len ++;
+                    }
+                    else
+                        if (buf)
+                            *buf = c << 8;
+                }
+            }
+            if (*psz == '-')
+                psz++;
+        }
+    }
+    if (buf && (len < n))
+        *buf = 0;
+    return len;

 }
 
 }
 

-size_t wxMBConvUTF7::WC2MB(char * WXUNUSED(buf),
-                           const wchar_t * WXUNUSED(psz),
-                           size_t WXUNUSED(n)) const
+//
+// BASE64 encoding table
+//
+static const unsigned char utf7enb64[] =

 {
 {

-  return 0;
+    'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H',
+    'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P',
+    'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',
+    'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f',
+    'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
+    'o', 'p', 'q', 'r', 's', 't', 'u', 'v',
+    'w', 'x', 'y', 'z', '0', '1', '2', '3',
+    '4', '5', '6', '7', '8', '9', '+', '/'
+};
+
+//
+// UTF-7 encoding table
+//
+// 0 - Set D (directly encoded characters)
+// 1 - Set O (optional direct characters)
+// 2 - whitespace characters (optional)
+// 3 - special characters
+//
+static const unsigned char utf7encode[128] =
+{
+    3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 3, 3, 2, 3, 3,
+    3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
+    2, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 3, 0, 0, 0, 3,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,
+    1, 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, 1, 3, 1, 1, 1,
+    1, 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, 1, 1, 1, 3, 3
+};
+
+size_t wxMBConvUTF7::WC2MB(char *buf, const wchar_t 
+*psz, size_t n) const
+{
+
+
+    size_t len = 0;
+
+    while (*psz && ((!buf) || (len < n)))
+    {
+        wchar_t cc = *psz++;
+        if (cc < 0x80 && utf7encode[cc] < 1)
+        {
+            // plain ASCII char
+            if (buf)
+                *buf++ = (char)cc;
+            len++;
+        }
+#ifndef WC_UTF16
+        else if (cc > 0xffff)
+        {
+            // no surrogate pair generation (yet?)
+            return (size_t)-1;
+        }
+#endif
+        else
+        {
+            if (buf)
+                *buf++ = '+';
+            len++;
+            if (cc != '+')
+            {
+                // BASE64 encode string
+                unsigned int lsb, d, l;
+                for (d = 0, l = 0;; psz++)
+                {
+                    for (lsb = 0; lsb < 2; lsb ++)
+                    {
+                        d <<= 8;
+                        d += lsb ? cc & 0xff : (cc & 0xff00) >> 8;
+
+                        for (l += 8; l >= 6; )
+                        {
+                            l -= 6;
+                            if (buf)
+                                *buf++ = utf7enb64[(d >> l) % 64];
+                            len++;
+                        }
+                    }
+                    cc = *psz;
+                    if (!(cc) || (cc < 0x80 && utf7encode[cc] < 1))
+                        break;
+                }
+                if (l != 0)
+                {
+                    if (buf)
+                        *buf++ = utf7enb64[((d % 16) << (6 - l)) % 64];
+                    len++;
+                }
+            }
+            if (buf)
+                *buf++ = '-';
+            len++;
+        }
+    }
+    if (buf && (len < n))
+        *buf = 0;
+    return len;

 }
 
 // ----------------------------------------------------------------------------
 }
 
 // ----------------------------------------------------------------------------


@@ -1292,7 +1470,7 @@ private:
 
 #if defined(__WXCOCOA__)
 
 
 #if defined(__WXCOCOA__)
 

-// RN:  There is no UTF-32 support in either Core Foundation or 
+// RN:  There is no UTF-32 support in either Core Foundation or

 // Cocoa.  Strangely enough, internally Core Foundation uses
 // UTF 32 internally quite a bit - its just not public (yet).
 
 // Cocoa.  Strangely enough, internally Core Foundation uses
 // UTF 32 internally quite a bit - its just not public (yet).
 


@@ -1300,139 +1478,139 @@ private:
 #include <CoreFoundation/CFStringEncodingExt.h>
 
 CFStringEncoding wxCFStringEncFromFontEnc(wxFontEncoding encoding)
 #include <CoreFoundation/CFStringEncodingExt.h>
 
 CFStringEncoding wxCFStringEncFromFontEnc(wxFontEncoding encoding)

-{      
-       CFStringEncoding enc = 0 ;
-       if ( encoding == wxFONTENCODING_DEFAULT )
-       {
+{
+    CFStringEncoding enc = 0 ;
+    if ( encoding == wxFONTENCODING_DEFAULT )
+    {

 #if wxUSE_GUI
 #if wxUSE_GUI

-               encoding = wxFont::GetDefaultEncoding() ;
+        encoding = wxFont::GetDefaultEncoding() ;

 #else
 #else

-               encoding = wxLocale::GetSystemEncoding() ;
+        encoding = wxLocale::GetSystemEncoding() ;

 #endif
 #endif

-       }
-       else switch( encoding)
-       {
-               case wxFONTENCODING_ISO8859_1 :
-               enc = kCFStringEncodingISOLatin1 ;
-               break ;
-               case wxFONTENCODING_ISO8859_2 :
-               enc = kCFStringEncodingISOLatin2;
-               break ;
-               case wxFONTENCODING_ISO8859_3 :
-               enc = kCFStringEncodingISOLatin3 ;
-               break ;
-               case wxFONTENCODING_ISO8859_4 :
-               enc = kCFStringEncodingISOLatin4;
-               break ;
-               case wxFONTENCODING_ISO8859_5 :
-               enc = kCFStringEncodingISOLatinCyrillic;
-               break ;
-               case wxFONTENCODING_ISO8859_6 :
-               enc = kCFStringEncodingISOLatinArabic;
-               break ;
-               case wxFONTENCODING_ISO8859_7 :
-               enc = kCFStringEncodingISOLatinGreek;
-               break ;
-               case wxFONTENCODING_ISO8859_8 :
-               enc = kCFStringEncodingISOLatinHebrew;
-               break ;
-               case wxFONTENCODING_ISO8859_9 :
-               enc = kCFStringEncodingISOLatin5;
-               break ;
-               case wxFONTENCODING_ISO8859_10 :
-               enc = kCFStringEncodingISOLatin6;
-               break ;
-               case wxFONTENCODING_ISO8859_11 :
-               enc = kCFStringEncodingISOLatinThai;
-               break ;
-               case wxFONTENCODING_ISO8859_13 :
-               enc = kCFStringEncodingISOLatin7;
-               break ;
-               case wxFONTENCODING_ISO8859_14 :
-               enc = kCFStringEncodingISOLatin8;
-               break ;
-               case wxFONTENCODING_ISO8859_15 :
-               enc = kCFStringEncodingISOLatin9;
-               break ;
-
-               case wxFONTENCODING_KOI8 :
-               enc = kCFStringEncodingKOI8_R;
-               break ;
-               case wxFONTENCODING_ALTERNATIVE : // MS-DOS CP866
-               enc = kCFStringEncodingDOSRussian;
-               break ;
-
-//             case wxFONTENCODING_BULGARIAN : 
-//             enc = ;
-//             break ;
-                       
-               case wxFONTENCODING_CP437 : 
-               enc =kCFStringEncodingDOSLatinUS ;
-               break ;
-               case wxFONTENCODING_CP850 :
-               enc = kCFStringEncodingDOSLatin1;
-               break ;
-               case wxFONTENCODING_CP852 : 
-               enc = kCFStringEncodingDOSLatin2;
-               break ;
-               case wxFONTENCODING_CP855 :
-               enc = kCFStringEncodingDOSCyrillic;
-               break ;
-               case wxFONTENCODING_CP866 :
-               enc =kCFStringEncodingDOSRussian ;
-               break ;
-               case wxFONTENCODING_CP874 :
-               enc = kCFStringEncodingDOSThai;
-               break ;
-               case wxFONTENCODING_CP932 : 
-               enc = kCFStringEncodingDOSJapanese;
-               break ;
-               case wxFONTENCODING_CP936 : 
-               enc =kCFStringEncodingDOSChineseSimplif ;
-               break ;
-               case wxFONTENCODING_CP949 : 
-               enc = kCFStringEncodingDOSKorean;
-               break ;
-               case wxFONTENCODING_CP950 : 
-               enc = kCFStringEncodingDOSChineseTrad;
-               break ;
-               
-               case wxFONTENCODING_CP1250 : 
-               enc = kCFStringEncodingWindowsLatin2;
-               break ;
-               case wxFONTENCODING_CP1251 : 
-               enc =kCFStringEncodingWindowsCyrillic ;
-               break ;
-               case wxFONTENCODING_CP1252 : 
-               enc =kCFStringEncodingWindowsLatin1 ;
-               break ;
-               case wxFONTENCODING_CP1253 : 
-               enc = kCFStringEncodingWindowsGreek;
-               break ;
-               case wxFONTENCODING_CP1254 : 
-               enc = kCFStringEncodingWindowsLatin5;
-               break ;
-               case wxFONTENCODING_CP1255 : 
-               enc =kCFStringEncodingWindowsHebrew ;
-               break ;
-               case wxFONTENCODING_CP1256 : 
-               enc =kCFStringEncodingWindowsArabic ;
-               break ;
-               case wxFONTENCODING_CP1257 : 
-               enc = kCFStringEncodingWindowsBalticRim;
-               break ;
-               case wxFONTENCODING_UTF7 : 
-               enc = kCFStringEncodingNonLossyASCII ;
-               break ;
-               case wxFONTENCODING_UTF8 : 
-               enc = kCFStringEncodingUTF8 ;
-               break ;
-               case wxFONTENCODING_EUC_JP : 
-               enc = kCFStringEncodingEUC_JP;
-               break ;
-               case wxFONTENCODING_UTF16 : 
+    }
+    else switch( encoding)
+    {
+        case wxFONTENCODING_ISO8859_1 :
+            enc = kCFStringEncodingISOLatin1 ;
+            break ;
+        case wxFONTENCODING_ISO8859_2 :
+            enc = kCFStringEncodingISOLatin2;
+            break ;
+        case wxFONTENCODING_ISO8859_3 :
+            enc = kCFStringEncodingISOLatin3 ;
+            break ;
+        case wxFONTENCODING_ISO8859_4 :
+            enc = kCFStringEncodingISOLatin4;
+            break ;
+        case wxFONTENCODING_ISO8859_5 :
+            enc = kCFStringEncodingISOLatinCyrillic;
+            break ;
+        case wxFONTENCODING_ISO8859_6 :
+            enc = kCFStringEncodingISOLatinArabic;
+            break ;
+        case wxFONTENCODING_ISO8859_7 :
+            enc = kCFStringEncodingISOLatinGreek;
+            break ;
+        case wxFONTENCODING_ISO8859_8 :
+            enc = kCFStringEncodingISOLatinHebrew;
+            break ;
+        case wxFONTENCODING_ISO8859_9 :
+            enc = kCFStringEncodingISOLatin5;
+            break ;
+        case wxFONTENCODING_ISO8859_10 :
+            enc = kCFStringEncodingISOLatin6;
+            break ;
+        case wxFONTENCODING_ISO8859_11 :
+            enc = kCFStringEncodingISOLatinThai;
+            break ;
+        case wxFONTENCODING_ISO8859_13 :
+            enc = kCFStringEncodingISOLatin7;
+            break ;
+        case wxFONTENCODING_ISO8859_14 :
+            enc = kCFStringEncodingISOLatin8;
+            break ;
+        case wxFONTENCODING_ISO8859_15 :
+            enc = kCFStringEncodingISOLatin9;
+            break ;
+
+        case wxFONTENCODING_KOI8 :
+            enc = kCFStringEncodingKOI8_R;
+            break ;
+        case wxFONTENCODING_ALTERNATIVE : // MS-DOS CP866
+            enc = kCFStringEncodingDOSRussian;
+            break ;
+
+//      case wxFONTENCODING_BULGARIAN :
+//          enc = ;
+//          break ;
+
+        case wxFONTENCODING_CP437 :
+            enc =kCFStringEncodingDOSLatinUS ;
+            break ;
+        case wxFONTENCODING_CP850 :
+            enc = kCFStringEncodingDOSLatin1;
+            break ;
+        case wxFONTENCODING_CP852 :
+            enc = kCFStringEncodingDOSLatin2;
+            break ;
+        case wxFONTENCODING_CP855 :
+            enc = kCFStringEncodingDOSCyrillic;
+            break ;
+        case wxFONTENCODING_CP866 :
+            enc =kCFStringEncodingDOSRussian ;
+            break ;
+        case wxFONTENCODING_CP874 :
+            enc = kCFStringEncodingDOSThai;
+            break ;
+        case wxFONTENCODING_CP932 :
+            enc = kCFStringEncodingDOSJapanese;
+            break ;
+        case wxFONTENCODING_CP936 :
+            enc =kCFStringEncodingDOSChineseSimplif ;
+            break ;
+        case wxFONTENCODING_CP949 :
+            enc = kCFStringEncodingDOSKorean;
+            break ;
+        case wxFONTENCODING_CP950 :
+            enc = kCFStringEncodingDOSChineseTrad;
+            break ;
+
+        case wxFONTENCODING_CP1250 :
+            enc = kCFStringEncodingWindowsLatin2;
+            break ;
+        case wxFONTENCODING_CP1251 :
+            enc =kCFStringEncodingWindowsCyrillic ;
+            break ;
+        case wxFONTENCODING_CP1252 :
+            enc =kCFStringEncodingWindowsLatin1 ;
+            break ;
+        case wxFONTENCODING_CP1253 :
+            enc = kCFStringEncodingWindowsGreek;
+            break ;
+        case wxFONTENCODING_CP1254 :
+            enc = kCFStringEncodingWindowsLatin5;
+            break ;
+        case wxFONTENCODING_CP1255 :
+            enc =kCFStringEncodingWindowsHebrew ;
+            break ;
+        case wxFONTENCODING_CP1256 :
+            enc =kCFStringEncodingWindowsArabic ;
+            break ;
+        case wxFONTENCODING_CP1257 :
+            enc = kCFStringEncodingWindowsBalticRim;
+            break ;
+        case wxFONTENCODING_UTF7 :
+            enc = kCFStringEncodingNonLossyASCII ;
+            break ;
+        case wxFONTENCODING_UTF8 :
+            enc = kCFStringEncodingUTF8 ;
+            break ;
+        case wxFONTENCODING_EUC_JP :
+            enc = kCFStringEncodingEUC_JP;
+            break ;
+        case wxFONTENCODING_UTF16 :

             enc = kCFStringEncodingUnicode ;
             enc = kCFStringEncodingUnicode ;

-               break ;            
+            break ;

         case wxFONTENCODING_MACROMAN :
             enc = kCFStringEncodingMacRoman ;
             break ;
         case wxFONTENCODING_MACROMAN :
             enc = kCFStringEncodingMacRoman ;
             break ;


@@ -1550,128 +1728,128 @@ CFStringEncoding wxCFStringEncFromFontEnc(wxFontEncoding encoding)
         case wxFONTENCODING_MACGAELIC :
             enc = kCFStringEncodingMacGaelic ;
             break ;
         case wxFONTENCODING_MACGAELIC :
             enc = kCFStringEncodingMacGaelic ;
             break ;

-//        case wxFONTENCODING_MACKEYBOARD :
-//            enc = kCFStringEncodingMacKeyboardGlyphs ;
-//            break ;    
-               default :
-                       // because gcc is picky
-                       break ;
-       } ;
-       return enc ;
+//      case wxFONTENCODING_MACKEYBOARD :
+//          enc = kCFStringEncodingMacKeyboardGlyphs ;
+//          break ;
+        default :
+            // because gcc is picky
+            break ;
+    } ;
+    return enc ;

 }
 
 wxFontEncoding wxFontEncFromCFStringEnc(CFStringEncoding encoding)
 }
 
 wxFontEncoding wxFontEncFromCFStringEnc(CFStringEncoding encoding)

-{      
-       wxFontEncoding enc = wxFONTENCODING_DEFAULT ;
-
-       switch( encoding)
-       {
-               case kCFStringEncodingISOLatin1  :
-               enc = wxFONTENCODING_ISO8859_1 ;
-               break ;
-               case kCFStringEncodingISOLatin2 :
-               enc = wxFONTENCODING_ISO8859_2;
-               break ;
-               case kCFStringEncodingISOLatin3 :
-               enc = wxFONTENCODING_ISO8859_3 ;
-               break ;
-               case kCFStringEncodingISOLatin4 :
-               enc = wxFONTENCODING_ISO8859_4;
-               break ;
-               case kCFStringEncodingISOLatinCyrillic :
-               enc = wxFONTENCODING_ISO8859_5;
-               break ;
-               case kCFStringEncodingISOLatinArabic :
-               enc = wxFONTENCODING_ISO8859_6;
-               break ;
-               case kCFStringEncodingISOLatinGreek :
-               enc = wxFONTENCODING_ISO8859_7;
-               break ;
-               case kCFStringEncodingISOLatinHebrew :
-               enc = wxFONTENCODING_ISO8859_8;
-               break ;
-               case kCFStringEncodingISOLatin5 :
-               enc = wxFONTENCODING_ISO8859_9;
-               break ;
-               case kCFStringEncodingISOLatin6 :
-               enc = wxFONTENCODING_ISO8859_10;
-               break ;
-               case kCFStringEncodingISOLatin7 :
-               enc = wxFONTENCODING_ISO8859_13;
-               break ;
-               case kCFStringEncodingISOLatin8 :
-               enc = wxFONTENCODING_ISO8859_14;
-               break ;
-               case kCFStringEncodingISOLatin9 :
-               enc =wxFONTENCODING_ISO8859_15 ;
-               break ;
-
-               case kCFStringEncodingKOI8_R :
-               enc = wxFONTENCODING_KOI8;
-               break ;
-
-//             case  : 
-//             enc = wxFONTENCODING_BULGARIAN;
-//             break ;
-
-               case kCFStringEncodingDOSLatinUS : 
-               enc = wxFONTENCODING_CP437;
-               break ;
-               case kCFStringEncodingDOSLatin1 :
-               enc = wxFONTENCODING_CP850;
-               break ;
-               case kCFStringEncodingDOSLatin2 : 
-               enc =wxFONTENCODING_CP852 ;
-               break ;
-               case kCFStringEncodingDOSCyrillic :
-               enc = wxFONTENCODING_CP855;
-               break ;
-               case kCFStringEncodingDOSRussian :
-               enc = wxFONTENCODING_CP866;
-               break ;
-               case kCFStringEncodingDOSThai :
-               enc =wxFONTENCODING_CP874 ;
-               break ;
-               case kCFStringEncodingDOSJapanese : 
-               enc = wxFONTENCODING_CP932;
-               break ;
-               case kCFStringEncodingDOSChineseSimplif : 
-               enc = wxFONTENCODING_CP936;
-               break ;
-               case kCFStringEncodingDOSKorean : 
-               enc = wxFONTENCODING_CP949;
-               break ;
-               case kCFStringEncodingDOSChineseTrad : 
-               enc = wxFONTENCODING_CP950;
-               break ;
-               
-               case kCFStringEncodingWindowsLatin2 : 
-               enc = wxFONTENCODING_CP1250;
-               break ;
-               case kCFStringEncodingWindowsCyrillic : 
-               enc = wxFONTENCODING_CP1251;
-               break ;
-               case kCFStringEncodingWindowsLatin1 : 
-               enc = wxFONTENCODING_CP1252;
-               break ;
-               case kCFStringEncodingWindowsGreek : 
-               enc = wxFONTENCODING_CP1253;
-               break ;
-               case kCFStringEncodingWindowsLatin5 : 
-               enc = wxFONTENCODING_CP1254;
-               break ;
-               case kCFStringEncodingWindowsHebrew : 
-               enc = wxFONTENCODING_CP1255;
-               break ;
-               case kCFStringEncodingWindowsArabic : 
-               enc = wxFONTENCODING_CP1256;
-               break ;
-               case kCFStringEncodingWindowsBalticRim : 
-               enc =wxFONTENCODING_CP1257 ;
-               break ;
-               case kCFStringEncodingEUC_JP : 
-               enc = wxFONTENCODING_EUC_JP;
-               break ;
+{
+    wxFontEncoding enc = wxFONTENCODING_DEFAULT ;
+
+    switch( encoding)
+    {
+        case kCFStringEncodingISOLatin1  :
+            enc = wxFONTENCODING_ISO8859_1 ;
+            break ;
+        case kCFStringEncodingISOLatin2 :
+            enc = wxFONTENCODING_ISO8859_2;
+            break ;
+        case kCFStringEncodingISOLatin3 :
+            enc = wxFONTENCODING_ISO8859_3 ;
+            break ;
+        case kCFStringEncodingISOLatin4 :
+            enc = wxFONTENCODING_ISO8859_4;
+            break ;
+        case kCFStringEncodingISOLatinCyrillic :
+            enc = wxFONTENCODING_ISO8859_5;
+            break ;
+        case kCFStringEncodingISOLatinArabic :
+            enc = wxFONTENCODING_ISO8859_6;
+            break ;
+        case kCFStringEncodingISOLatinGreek :
+            enc = wxFONTENCODING_ISO8859_7;
+            break ;
+        case kCFStringEncodingISOLatinHebrew :
+            enc = wxFONTENCODING_ISO8859_8;
+            break ;
+        case kCFStringEncodingISOLatin5 :
+            enc = wxFONTENCODING_ISO8859_9;
+            break ;
+        case kCFStringEncodingISOLatin6 :
+            enc = wxFONTENCODING_ISO8859_10;
+            break ;
+        case kCFStringEncodingISOLatin7 :
+            enc = wxFONTENCODING_ISO8859_13;
+            break ;
+        case kCFStringEncodingISOLatin8 :
+            enc = wxFONTENCODING_ISO8859_14;
+            break ;
+        case kCFStringEncodingISOLatin9 :
+            enc =wxFONTENCODING_ISO8859_15 ;
+            break ;
+
+        case kCFStringEncodingKOI8_R :
+            enc = wxFONTENCODING_KOI8;
+            break ;
+
+//      case  :
+//          enc = wxFONTENCODING_BULGARIAN;
+//          break ;
+
+        case kCFStringEncodingDOSLatinUS :
+            enc = wxFONTENCODING_CP437;
+            break ;
+        case kCFStringEncodingDOSLatin1 :
+            enc = wxFONTENCODING_CP850;
+            break ;
+        case kCFStringEncodingDOSLatin2 :
+            enc =wxFONTENCODING_CP852 ;
+            break ;
+        case kCFStringEncodingDOSCyrillic :
+            enc = wxFONTENCODING_CP855;
+            break ;
+        case kCFStringEncodingDOSRussian :
+            enc = wxFONTENCODING_CP866;
+            break ;
+        case kCFStringEncodingDOSThai :
+            enc =wxFONTENCODING_CP874 ;
+            break ;
+        case kCFStringEncodingDOSJapanese :
+            enc = wxFONTENCODING_CP932;
+            break ;
+        case kCFStringEncodingDOSChineseSimplif :
+            enc = wxFONTENCODING_CP936;
+            break ;
+        case kCFStringEncodingDOSKorean :
+            enc = wxFONTENCODING_CP949;
+            break ;
+        case kCFStringEncodingDOSChineseTrad :
+            enc = wxFONTENCODING_CP950;
+            break ;
+
+        case kCFStringEncodingWindowsLatin2 :
+            enc = wxFONTENCODING_CP1250;
+            break ;
+        case kCFStringEncodingWindowsCyrillic :
+            enc = wxFONTENCODING_CP1251;
+            break ;
+        case kCFStringEncodingWindowsLatin1 :
+            enc = wxFONTENCODING_CP1252;
+            break ;
+        case kCFStringEncodingWindowsGreek :
+            enc = wxFONTENCODING_CP1253;
+            break ;
+        case kCFStringEncodingWindowsLatin5 :
+            enc = wxFONTENCODING_CP1254;
+            break ;
+        case kCFStringEncodingWindowsHebrew :
+            enc = wxFONTENCODING_CP1255;
+            break ;
+        case kCFStringEncodingWindowsArabic :
+            enc = wxFONTENCODING_CP1256;
+            break ;
+        case kCFStringEncodingWindowsBalticRim :
+            enc =wxFONTENCODING_CP1257 ;
+            break ;
+        case kCFStringEncodingEUC_JP :
+            enc = wxFONTENCODING_EUC_JP;
+            break ;

         case kCFStringEncodingUnicode :
             enc = wxFONTENCODING_UTF16;
             break;
         case kCFStringEncodingUnicode :
             enc = wxFONTENCODING_UTF16;
             break;


@@ -1794,9 +1972,9 @@ wxFontEncoding wxFontEncFromCFStringEnc(CFStringEncoding encoding)
             break ;
 //        case kCFStringEncodingMacKeyboardGlyphs :
 //            enc = wxFONTENCODING_MACKEYBOARD ;
             break ;
 //        case kCFStringEncodingMacKeyboardGlyphs :
 //            enc = wxFONTENCODING_MACKEYBOARD ;

-//            break ;       
-       } ;
-       return enc ;
+//            break ;
+    } ;
+    return enc ;

 }
 
 class wxMBConv_cocoa : public wxMBConv
 }
 
 class wxMBConv_cocoa : public wxMBConv


@@ -1830,13 +2008,13 @@ public:
     size_t MB2WC(wchar_t * szOut, const char * szUnConv, size_t nOutSize) const
     {
         wxASSERT(szUnConv);
     size_t MB2WC(wchar_t * szOut, const char * szUnConv, size_t nOutSize) const
     {
         wxASSERT(szUnConv);

-        
+

         size_t nBufSize = strlen(szUnConv) + 1;
         size_t nRealOutSize;
 
         size_t nBufSize = strlen(szUnConv) + 1;
         size_t nRealOutSize;
 

-        UniChar* szUniCharBuffer       = (UniChar*) szOut; 
-        wchar_t* szConvBuffer          = szOut;
-        
+        UniChar* szUniCharBuffer    = (UniChar*) szOut;
+        wchar_t* szConvBuffer       = szOut;
+

         if (szConvBuffer == NULL && nOutSize != 0)
         {
             szConvBuffer = new wchar_t[nOutSize] ;
         if (szConvBuffer == NULL && nOutSize != 0)
         {
             szConvBuffer = new wchar_t[nOutSize] ;


@@ -1847,18 +2025,18 @@ public:
 #endif
 
         CFDataRef theData = CFDataCreateWithBytesNoCopy (
 #endif
 
         CFDataRef theData = CFDataCreateWithBytesNoCopy (

-                                            NULL,      //allocator 
-                                            (const UInt8*)szUnConv, 
+                                            NULL,     //allocator
+                                            (const UInt8*)szUnConv,

                                             nBufSize - 1,
                                             nBufSize - 1,

-                                            NULL       //deallocator
-                                            ); 
+                                            NULL      //deallocator
+                                            );

 
         wxASSERT(theData);
 
         CFStringRef theString = CFStringCreateFromExternalRepresentation (
                                                 NULL,
                                                 theData,
 
         wxASSERT(theData);
 
         CFStringRef theString = CFStringCreateFromExternalRepresentation (
                                                 NULL,
                                                 theData,

-                                                m_char_encoding 
+                                                m_char_encoding

                                                 );
 
         wxASSERT(theString);
                                                 );
 
         wxASSERT(theString);


@@ -1869,16 +2047,16 @@ public:
             CFRelease(theString);
             return nRealOutSize - 1;
         }
             CFRelease(theString);
             return nRealOutSize - 1;
         }

-        
+

         CFRange theRange = { 0, CFStringGetLength(theString) };
         CFRange theRange = { 0, CFStringGetLength(theString) };

-        
+

         CFStringGetCharacters(theString, theRange, szUniCharBuffer);
         CFStringGetCharacters(theString, theRange, szUniCharBuffer);

-        
-        
+
+

         nRealOutSize = (CFStringGetLength(theString) + 1);
         nRealOutSize = (CFStringGetLength(theString) + 1);

-        
+

         CFRelease(theString);
         CFRelease(theString);

-        
+

         szUniCharBuffer[nRealOutSize-1] = '\0' ;
 
 #if SIZEOF_WCHAR_T == 4
         szUniCharBuffer[nRealOutSize-1] = '\0' ;
 
 #if SIZEOF_WCHAR_T == 4


@@ -1898,11 +2076,11 @@ public:
         size_t nRealOutSize;
         char* szBuffer = szOut;
         UniChar* szUniBuffer = (UniChar*) szUnConv;
         size_t nRealOutSize;
         char* szBuffer = szOut;
         UniChar* szUniBuffer = (UniChar*) szUnConv;

-        
+

         if (szOut == NULL)
         {
             // worst case
         if (szOut == NULL)
         {
             // worst case

-            nRealOutSize = ((nBufSize - 1) << 1)+1 ;
+            nRealOutSize = wxString::WorstEncodingCase(nBufSize - 1, *this)+1 ;

             szBuffer = new char[ nRealOutSize ] ;
         }
         else
             szBuffer = new char[ nRealOutSize ] ;
         }
         else


@@ -1923,9 +2101,9 @@ public:
                                 nBufSize,
                                 NULL //deallocator
                             );
                                 nBufSize,
                                 NULL //deallocator
                             );

-        
+

         wxASSERT(theString);
         wxASSERT(theString);

-        
+

         //Note that CER puts a BOM when converting to unicode
         //so we may want to check and use getchars instead in that case
         CFDataRef theData = CFStringCreateExternalRepresentation(
         //Note that CER puts a BOM when converting to unicode
         //so we may want to check and use getchars instead in that case
         CFDataRef theData = CFStringCreateExternalRepresentation(


@@ -1938,9 +2116,9 @@ public:
 
         if(!theData)
             return (size_t)-1;
 
         if(!theData)
             return (size_t)-1;

-        
+

         CFRelease(theString);
         CFRelease(theString);

-        
+

         nRealOutSize = CFDataGetLength(theData);
 
         if ( szOut == NULL )
         nRealOutSize = CFDataGetLength(theData);
 
         if ( szOut == NULL )


@@ -1955,12 +2133,12 @@ public:
             CFRelease(theData);
             return nRealOutSize - 1;
         }
             CFRelease(theData);
             return nRealOutSize - 1;
         }

-        
+

         CFRange theRange = {0, CFDataGetLength(theData) };
         CFDataGetBytes(theData, theRange, (UInt8*) szBuffer);
         CFRange theRange = {0, CFDataGetLength(theData) };
         CFDataGetBytes(theData, theRange, (UInt8*) szBuffer);

-            
-        CFRelease(theData);    
-        
+
+        CFRelease(theData);
+

 //TODO: This gets flagged as a non-malloced address by the debugger...
 //#if SIZEOF_WCHAR_T == 4
 //        delete[] szUniBuffer;
 //TODO: This gets flagged as a non-malloced address by the debugger...
 //#if SIZEOF_WCHAR_T == 4
 //        delete[] szUniBuffer;


@@ -1969,9 +2147,9 @@ public:
     }
 
     bool IsOk() const
     }
 
     bool IsOk() const

-    { 
+    {

         //TODO: check for invalid en/de/coding
         //TODO: check for invalid en/de/coding

-        return true; 
+        return true;

     }
 
 private:
     }
 
 private:


@@ -2079,7 +2257,7 @@ public:
         if (buf == NULL)
         {
             // worst case
         if (buf == NULL)
         {
             // worst case

-            n = byteInLen * 2 ;
+            n = wxString::WorstEncodingCase(byteInLen / SIZEOF_WCHAR_T, *this) + SIZEOF_WCHAR_T;

             tbuf = (char*) malloc( n ) ;
         }
 
             tbuf = (char*) malloc( n ) ;
         }