escape underscores and don't use abbreviations in text

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

diff --git a/src/common/fmapbase.cpp b/src/common/fmapbase.cpp
index e473054fe8e1de1239f8859fd9e7c04e9ad4335a..4ad527ddfe073cc995527db5b45f796e93bb260e 100644 (file)
--- a/src/common/fmapbase.cpp
+++ b/src/common/fmapbase.cpp
@@ -73,6 +73,7 @@ static wxFontEncoding gs_encodings[] =
     wxFONTENCODING_ISO8859_15,
     wxFONTENCODING_KOI8,
     wxFONTENCODING_KOI8_U,
     wxFONTENCODING_ISO8859_15,
     wxFONTENCODING_KOI8,
     wxFONTENCODING_KOI8_U,

+    wxFONTENCODING_CP874,

     wxFONTENCODING_CP932,
     wxFONTENCODING_CP936,
     wxFONTENCODING_CP949,
     wxFONTENCODING_CP932,
     wxFONTENCODING_CP936,
     wxFONTENCODING_CP949,


@@ -95,6 +96,10 @@ static wxFontEncoding gs_encodings[] =
     wxFONTENCODING_UTF32BE,
     wxFONTENCODING_UTF32LE,
     wxFONTENCODING_EUC_JP,
     wxFONTENCODING_UTF32BE,
     wxFONTENCODING_UTF32LE,
     wxFONTENCODING_EUC_JP,

+    wxFONTENCODING_DEFAULT,
+    wxFONTENCODING_BIG5,
+    wxFONTENCODING_SHIFT_JIS,
+    wxFONTENCODING_GB2312,

 };
 
 // the descriptions for them
 };
 
 // the descriptions for them


@@ -117,6 +122,7 @@ static const wxChar* gs_encodingDescs[] =
     wxTRANSLATE( "Western European with Euro (ISO-8859-15)" ),
     wxTRANSLATE( "KOI8-R" ),
     wxTRANSLATE( "KOI8-U" ),
     wxTRANSLATE( "Western European with Euro (ISO-8859-15)" ),
     wxTRANSLATE( "KOI8-R" ),
     wxTRANSLATE( "KOI8-U" ),

+    wxTRANSLATE( "Windows Thai (CP 874)" ),

     wxTRANSLATE( "Windows Japanese (CP 932)" ),
     wxTRANSLATE( "Windows Chinese Simplified (CP 936)" ),
     wxTRANSLATE( "Windows Korean (CP 949)" ),
     wxTRANSLATE( "Windows Japanese (CP 932)" ),
     wxTRANSLATE( "Windows Chinese Simplified (CP 936)" ),
     wxTRANSLATE( "Windows Korean (CP 949)" ),


@@ -139,55 +145,76 @@ static const wxChar* gs_encodingDescs[] =
     wxTRANSLATE( "Unicode 32 bit Big Endian (UTF-32BE)" ),
     wxTRANSLATE( "Unicode 32 bit Little Endian (UTF-32LE)" ),
     wxTRANSLATE( "Extended Unix Codepage for Japanese (EUC-JP)" ),
     wxTRANSLATE( "Unicode 32 bit Big Endian (UTF-32BE)" ),
     wxTRANSLATE( "Unicode 32 bit Little Endian (UTF-32LE)" ),
     wxTRANSLATE( "Extended Unix Codepage for Japanese (EUC-JP)" ),

+    wxTRANSLATE( "US-ASCII" ),
+    wxTRANSLATE( "BIG5" ),
+    wxTRANSLATE( "SHIFT-JIS" ),
+    wxTRANSLATE( "GB-2312" ),

 };
 
 // and the internal names (these are not translated on purpose!)
 };
 
 // and the internal names (these are not translated on purpose!)

-static const wxChar* gs_encodingNames[] =
+static const wxChar* gs_encodingNames[WXSIZEOF(gs_encodingDescs)][10] =

 {
 {

-    wxT( "iso-8859-1" ),
-    wxT( "iso-8859-2" ),
-    wxT( "iso-8859-3" ),
-    wxT( "iso-8859-4" ),
-    wxT( "iso-8859-5" ),
-    wxT( "iso-8859-6" ),
-    wxT( "iso-8859-7" ),
-    wxT( "iso-8859-8" ),
-    wxT( "iso-8859-9" ),
-    wxT( "iso-8859-10" ),
-    wxT( "iso-8859-11" ),
-    wxT( "iso-8859-12" ),
-    wxT( "iso-8859-13" ),
-    wxT( "iso-8859-14" ),
-    wxT( "iso-8859-15" ),
-    wxT( "koi8-r" ),
-    wxT( "koi8-u" ),
-    wxT( "windows-932" ),
-    wxT( "windows-936" ),
-    wxT( "windows-949" ),
-    wxT( "windows-950" ),
-    wxT( "windows-1250" ),
-    wxT( "windows-1251" ),
-    wxT( "windows-1252" ),
-    wxT( "windows-1253" ),
-    wxT( "windows-1254" ),
-    wxT( "windows-1255" ),
-    wxT( "windows-1256" ),
-    wxT( "windows-1257" ),
-    wxT( "windows-437" ),
-    wxT( "utf-7" ),
-    wxT( "utf-8" ),
-    wxT( "utf-16" ),
-    wxT( "utf-16be" ),
-    wxT( "utf-16le" ),
-    wxT( "utf-32" ),
-    wxT( "utf-32be" ),
-    wxT( "utf-32le" ),
-    wxT( "euc-jp" ),
+    // names from the first column are used under Linux, from the second one
+    // under Solaris and IRIX and from the third one -- under AIX
+    { wxT( "ISO-8859-1" ), wxT( "ISO8859-1" ), wxT( "8859-1" ), wxT("iso_8859_1"), NULL },
+    { wxT( "ISO-8859-2" ), wxT( "ISO8859-2" ), wxT( "8859-2" ), NULL },
+    { wxT( "ISO-8859-3" ), wxT( "ISO8859-3" ), wxT( "8859-3" ), NULL },
+    { wxT( "ISO-8859-4" ), wxT( "ISO8859-4" ), wxT( "8859-4" ), NULL },
+    { wxT( "ISO-8859-5" ), wxT( "ISO8859-5" ), wxT( "8859-5" ), NULL },
+    { wxT( "ISO-8859-6" ), wxT( "ISO8859-6" ), wxT( "8859-6" ), NULL },
+    { wxT( "ISO-8859-7" ), wxT( "ISO8859-7" ), wxT( "8859-7" ), NULL },
+    { wxT( "ISO-8859-8" ), wxT( "ISO8859-8" ), wxT( "8859-8" ), NULL },
+    { wxT( "ISO-8859-9" ), wxT( "ISO8859-9" ), wxT( "8859-9" ), NULL },
+    { wxT( "ISO-8859-10" ), wxT( "ISO8859-10" ), wxT( "8859-10" ), NULL },
+    { wxT( "ISO-8859-11" ), wxT( "ISO8859-11" ), wxT( "8859-11" ), NULL },
+    { wxT( "ISO-8859-12" ), wxT( "ISO8859-12" ), wxT( "8859-12" ), NULL },
+    { wxT( "ISO-8859-13" ), wxT( "ISO8859-13" ), wxT( "8859-13" ), NULL },
+    { wxT( "ISO-8859-14" ), wxT( "ISO8859-14" ), wxT( "8859-14" ), NULL },
+    { wxT( "ISO-8859-15" ), wxT( "ISO8859-15" ), wxT( "8859-15" ), NULL },
+
+    // although koi8-ru is not strictly speaking the same as koi8-r,
+    // they are similar enough to make mapping it to koi8 better than
+    // not recognizing it at all
+    { wxT( "KOI8-R" ), wxT( "KOI8-RU" ), NULL },
+    { wxT( "KOI8-U" ), NULL },
+
+    { wxT( "WINDOWS-874" ), wxT( "CP-874" ), NULL },
+    { wxT( "WINDOWS-932" ), wxT( "CP-932" ), NULL },
+    { wxT( "WINDOWS-936" ), wxT( "CP-936" ), NULL },
+    { wxT( "WINDOWS-949" ), wxT( "CP-949" ), wxT( "EUC-KR" ), wxT( "eucKR" ), wxT( "euc_kr" ), NULL },
+    { wxT( "WINDOWS-950" ), wxT( "CP-950" ), NULL },
+    { wxT( "WINDOWS-1250" ),wxT( "CP-1250" ), NULL },
+    { wxT( "WINDOWS-1251" ),wxT( "CP-1251" ), NULL },
+    { wxT( "WINDOWS-1252" ),wxT( "CP-1252" ), wxT("IBM-1252"), NULL },
+    { wxT( "WINDOWS-1253" ),wxT( "CP-1253" ), NULL },
+    { wxT( "WINDOWS-1254" ),wxT( "CP-1254" ), NULL },
+    { wxT( "WINDOWS-1255" ),wxT( "CP-1255" ), NULL },
+    { wxT( "WINDOWS-1256" ),wxT( "CP-1256" ), NULL },
+    { wxT( "WINDOWS-1257" ),wxT( "CP-1257" ), NULL },
+    { wxT( "WINDOWS-437" ), wxT( "CP-437" ), NULL },
+
+    { wxT( "UTF-7" ), NULL },
+    { wxT( "UTF-8" ), NULL },
+    { wxT( "UTF-16" ), wxT("UCS-2"), wxT("UCS2"), NULL },
+    { wxT( "UTF-16BE" ), wxT("UCS-2BE"), NULL },
+    { wxT( "UTF-16LE" ), wxT("UCS-2LE"), NULL },
+    { wxT( "UTF-32" ), wxT( "UCS-4" ), wxT("UCS4"), NULL },
+    { wxT( "UTF-32BE" ), wxT( "UCS-4BE" ), NULL },
+    { wxT( "UTF-32LE" ), wxT( "UCS-4LE" ), NULL },
+
+    { wxT( "EUC-JP" ), wxT( "eucJP" ), wxT( "euc_jp" ), wxT( "IBM-eucJP" ), NULL },
+
+    // 646 is for Solaris, roman8 -- for HP-UX
+    { wxT( "US-ASCII" ), wxT( "ASCII" ), wxT("C"), wxT("POSIX"), wxT("ANSI_X3.4-1968"),
+      wxT("646"), wxT("roman8"), wxT( "" ), NULL },
+
+    { wxT( "BIG5" ), NULL },
+    { wxT( "SJIS" ), wxT( "SHIFT-JIS" ), wxT( "SHIFT_JIS" ), NULL },
+    { wxT( "GB2312" ), NULL },

 };
 
 };
 

-wxCOMPILE_TIME_ASSERT( WXSIZEOF(gs_encodingDescs) == WXSIZEOF(gs_encodings) &&
-                       WXSIZEOF(gs_encodingNames) == WXSIZEOF(gs_encodings),
-                       EncodingsArraysNotInSync );
+wxCOMPILE_TIME_ASSERT( WXSIZEOF(gs_encodingDescs) == WXSIZEOF(gs_encodings), EncodingsArraysNotInSync );
+wxCOMPILE_TIME_ASSERT( WXSIZEOF(gs_encodingNames) == WXSIZEOF(gs_encodings), EncodingsArraysNotInSync );

 
 // ----------------------------------------------------------------------------
 // private classes
 
 // ----------------------------------------------------------------------------
 // private classes


@@ -465,81 +492,18 @@ wxFontMapperBase::NonInteractiveCharsetToEncoding(const wxString& charset)
             }
         }
 
             }
         }
 

-        cs.MakeUpper();
-
-        if ( cs.empty() || cs == _T("US-ASCII") )
-        {
-            encoding = wxFONTENCODING_DEFAULT;
-        }
-        else if ( cs == wxT("UTF-7") )
-        {
-            encoding = wxFONTENCODING_UTF7;
-        }
-        else if ( cs == wxT("UTF-8") )
-        {
-            encoding = wxFONTENCODING_UTF8;
-        }
-        else if ( cs == wxT("UTF-16") )
-        {
-            encoding = wxFONTENCODING_UTF16;
-        }
-        else if ( cs == wxT("UTF-16BE") )
-        {
-            encoding = wxFONTENCODING_UTF16BE;
-        }
-        else if ( cs == wxT("UTF-16LE") )
-        {
-            encoding = wxFONTENCODING_UTF16LE;
-        }
-        else if ( cs == wxT("UTF-32") || cs == wxT("UCS-4") )
-        {
-            encoding = wxFONTENCODING_UTF32;
-        }
-        else if ( cs == wxT("UTF-32BE") || cs == wxT("UCS-4BE") )
-        {
-            encoding = wxFONTENCODING_UTF32BE;
-        }
-        else if ( cs == wxT("UTF-32LE") || cs == wxT("UCS-4LE") )
-        {
-            encoding = wxFONTENCODING_UTF32LE;
-        }
-        else if ( cs == wxT("GB2312") )
-        {
-            encoding = wxFONTENCODING_GB2312;
-        }
-        else if ( cs == wxT("BIG5") )
-        {
-            encoding = wxFONTENCODING_BIG5;
-        }
-        else if ( cs == wxT("SJIS") ||
-                  cs == wxT("SHIFT_JIS") ||
-                  cs == wxT("SHIFT-JIS") )
-        {
-            encoding = wxFONTENCODING_SHIFT_JIS;
-        }
-        else if ( cs == wxT("EUC-JP") ||
-                  cs == wxT("EUC_JP") )
-        {
-            encoding = wxFONTENCODING_EUC_JP;
-        }
-        else if ( cs == wxT("EUC-KR") ||
-                  cs == wxT("EUC_KR") )
+        for ( size_t i = 0; i < WXSIZEOF(gs_encodingNames); ++i )

         {
         {

-            encoding = wxFONTENCODING_CP949;
-        }
-        else if ( cs == wxT("KOI8-R") ||
-                  cs == wxT("KOI8-RU") )
-        {
-            // although koi8-ru is not strictly speaking the same as koi8-r,
-            // they are similar enough to make mapping it to koi8 better than
-            // not recognizing it at all
-            encoding = wxFONTENCODING_KOI8;
-        }
-        else if ( cs == wxT("KOI8-U") )
-        {
-            encoding = wxFONTENCODING_KOI8_U;
+            for ( const wxChar** encName = gs_encodingNames[i]; *encName; ++encName )
+            {
+                if ( cs.CmpNoCase(*encName) == 0 )
+                    return gs_encodings[i];
+            }

         }
         }

-        else if ( cs.Left(3) == wxT("ISO") )
+
+        cs.MakeUpper();
+
+        if ( cs.Left(3) == wxT("ISO") )

         {
             // the dash is optional (or, to be exact, it is not, but
             // several brokenmails "forget" it)
         {
             // the dash is optional (or, to be exact, it is not, but
             // several brokenmails "forget" it)


@@ -609,7 +573,7 @@ wxFontMapperBase::NonInteractiveCharsetToEncoding(const wxString& charset)
                 if ( *p == wxT('-') )
                     p++;
 
                 if ( *p == wxT('-') )
                     p++;
 

-                int value;
+                unsigned int value;

                 if ( wxSscanf(p, wxT("%u"), &value) == 1 )
                 {
                     if ( value >= 1250 )
                 if ( wxSscanf(p, wxT("%u"), &value) == 1 )
                 {
                     if ( value >= 1250 )


@@ -626,6 +590,10 @@ wxFontMapperBase::NonInteractiveCharsetToEncoding(const wxString& charset)
 
                     switch ( value )
                     {
 
                     switch ( value )
                     {

+                        case 874:
+                            encoding = wxFONTENCODING_CP874;
+                            break;
+

                         case 932:
                             encoding = wxFONTENCODING_CP932;
                             break;
                         case 932:
                             encoding = wxFONTENCODING_CP932;
                             break;


@@ -704,7 +672,7 @@ wxString wxFontMapperBase::GetEncodingName(wxFontEncoding encoding)
     {
         if ( gs_encodings[i] == encoding )
         {
     {
         if ( gs_encodings[i] == encoding )
         {

-            return gs_encodingNames[i];
+            return gs_encodingNames[i][0];

         }
     }
 
         }
     }
 


@@ -715,21 +683,33 @@ wxString wxFontMapperBase::GetEncodingName(wxFontEncoding encoding)
 }
 
 /* static */
 }
 
 /* static */

-wxFontEncoding wxFontMapperBase::GetEncodingFromName(const wxString& name)
+const wxChar** wxFontMapperBase::GetAllEncodingNames(wxFontEncoding encoding)

 {
 {

-    const size_t count = WXSIZEOF(gs_encodingNames);
+    static const wxChar* dummy[] = { NULL };

 
 

-    for ( size_t i = 0; i < count; i++ )
+    for ( size_t i = 0; i < WXSIZEOF(gs_encodingNames); i++ )

     {
     {

-        if ( gs_encodingNames[i] == name )
+        if ( gs_encodings[i] == encoding )

         {
         {

-            return gs_encodings[i];
+            return gs_encodingNames[i];

         }
     }
 
         }
     }
 

-    if ( name == _("default") )
+    return dummy;
+}
+
+/* static */
+wxFontEncoding wxFontMapperBase::GetEncodingFromName(const wxString& name)
+{
+    const size_t count = WXSIZEOF(gs_encodingNames);
+
+    for ( size_t i = 0; i < count; i++ )

     {
     {

-        return wxFONTENCODING_DEFAULT;
+        for ( const wxChar** encName = gs_encodingNames[i]; *encName; ++encName )
+        {
+            if ( name.CmpNoCase(*encName) == 0 )
+                return gs_encodings[i];
+        }

     }
 
     return wxFONTENCODING_MAX;
     }
 
     return wxFONTENCODING_MAX;