X-Git-Url: https://git.saurik.com/wxWidgets.git/blobdiff_plain/c4b4f847e20cf495b55ddd67ff70ad95239b5aa3..855f31ebe72bef834a32df2c274b41fb282ad265:/src/common/fmapbase.cpp diff --git a/src/common/fmapbase.cpp b/src/common/fmapbase.cpp index e86e8b4902..48e1b2e148 100644 --- a/src/common/fmapbase.cpp +++ b/src/common/fmapbase.cpp @@ -181,33 +181,33 @@ static const wxChar* gs_encodingNames[WXSIZEOF(gs_encodingDescs)][9] = { 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" ), wxT("utf7"), NULL }, - { wxT( "UTF-8" ), wxT("utf8"), NULL }, + { wxT( "WINDOWS-874" ), wxT( "CP-874" ), wxT( "MS-874" ), wxT( "IBM-874" ), NULL }, + { wxT( "WINDOWS-932" ), wxT( "CP-932" ), wxT( "MS-932" ), wxT( "IBM-932" ), NULL }, + { wxT( "WINDOWS-936" ), wxT( "CP-936" ), wxT( "MS-936" ), wxT( "IBM-936" ), NULL }, + { wxT( "WINDOWS-949" ), wxT( "CP-949" ), wxT( "MS-949" ), wxT( "IBM-949" ), wxT( "EUC-KR" ), wxT( "eucKR" ), wxT( "euc_kr" ), NULL }, + { wxT( "WINDOWS-950" ), wxT( "CP-950" ), wxT( "MS-950" ), wxT( "IBM-950" ), NULL }, + { wxT( "WINDOWS-1250" ),wxT( "CP-1250" ),wxT( "MS-1250" ),wxT( "IBM-1250" ),NULL }, + { wxT( "WINDOWS-1251" ),wxT( "CP-1251" ),wxT( "MS-1251" ),wxT( "IBM-1251" ),NULL }, + { wxT( "WINDOWS-1252" ),wxT( "CP-1252" ),wxT( "MS-1252" ),wxT( "IBM-1252" ),NULL }, + { wxT( "WINDOWS-1253" ),wxT( "CP-1253" ),wxT( "MS-1253" ),wxT( "IBM-1253" ),NULL }, + { wxT( "WINDOWS-1254" ),wxT( "CP-1254" ),wxT( "MS-1254" ),wxT( "IBM-1254" ),NULL }, + { wxT( "WINDOWS-1255" ),wxT( "CP-1255" ),wxT( "MS-1255" ),wxT( "IBM-1255" ),NULL }, + { wxT( "WINDOWS-1256" ),wxT( "CP-1256" ),wxT( "MS-1256" ),wxT( "IBM-1256" ),NULL }, + { wxT( "WINDOWS-1257" ),wxT( "CP-1257" ),wxT( "MS-1257" ),wxT( "IBM-1257" ),NULL }, + { wxT( "WINDOWS-437" ), wxT( "CP-437" ), wxT( "MS-437" ), wxT( "IBM-437" ), NULL }, + + { wxT( "UTF-7" ), NULL }, + { wxT( "UTF-8" ), NULL }, #ifdef WORDS_BIGENDIAN - { wxT( "UTF-16BE" ), wxT("UCS-2BE"), wxT( "UTF-16" ), wxT("UCS-2"), wxT("UCS2"), NULL }, + { wxT( "UTF-16BE" ), wxT("UCS-2BE"), wxT( "UTF-16" ), wxT("UCS-2"), NULL }, { wxT( "UTF-16LE" ), wxT("UCS-2LE"), NULL }, - { wxT( "UTF-32BE" ), wxT( "UCS-4BE" ), wxT( "UTF-32" ), wxT( "UCS-4" ), wxT("UCS4"), NULL }, + { wxT( "UTF-32BE" ), wxT( "UCS-4BE" ), wxT( "UTF-32" ), wxT( "UCS-4" ), NULL }, { wxT( "UTF-32LE" ), wxT( "UCS-4LE" ), NULL }, #else // WORDS_BIGENDIAN { wxT( "UTF-16BE" ), wxT("UCS-2BE"), NULL }, - { wxT( "UTF-16LE" ), wxT("UCS-2LE"), wxT( "UTF-16" ), wxT("UCS-2"), wxT("UCS2"), NULL }, + { wxT( "UTF-16LE" ), wxT("UCS-2LE"), wxT( "UTF-16" ), wxT("UCS-2"), NULL }, { wxT( "UTF-32BE" ), wxT( "UCS-4BE" ), NULL }, - { wxT( "UTF-32LE" ), wxT( "UCS-4LE" ), wxT( "UTF-32" ), wxT( "UCS-4" ), wxT("UCS4"), NULL }, + { wxT( "UTF-32LE" ), wxT( "UCS-4LE" ), wxT( "UTF-32" ), wxT( "UCS-4" ), NULL }, #endif // WORDS_BIGENDIAN { wxT( "EUC-JP" ), wxT( "eucJP" ), wxT( "euc_jp" ), wxT( "IBM-eucJP" ), NULL }, @@ -507,32 +507,25 @@ wxFontMapperBase::NonInteractiveCharsetToEncoding(const wxString& charset) } } - for ( size_t i = 0; i < WXSIZEOF(gs_encodingNames); ++i ) - { - for ( const wxChar** encName = gs_encodingNames[i]; *encName; ++encName ) - { - if ( cs.CmpNoCase(*encName) == 0 ) - return gs_encodings[i]; - } - } + // check for known encoding name + const wxFontEncoding e = GetEncodingFromName(cs); + if ( e != wxFONTENCODING_MAX ) + return e; + // deal with general encoding names of the form FOO-xxx 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 many + // broken programs "forget" it in the output they generate) const wxChar *p = cs.c_str() + 3; if ( *p == wxT('-') ) p++; - // printf( "iso %s\n", (const char*) cs.ToAscii() ); - unsigned int value; if ( wxSscanf(p, wxT("8859-%u"), &value) == 1 ) { - // printf( "value %d\n", (int)value ); - // make it 0 based and check that it is strictly positive in // the process (no such thing as iso8859-0 encoding) if ( (value-- > 0) && @@ -552,8 +545,6 @@ wxFontMapperBase::NonInteractiveCharsetToEncoding(const wxString& charset) unsigned int value; if ( wxSscanf(p, wxT("8859-%u"), &value) == 1 ) { - // printf( "value %d\n", (int)value ); - // make it 0 based and check that it is strictly positive in // the process (no such thing as iso8859-0 encoding) if ( (value-- > 0) && @@ -722,12 +713,28 @@ wxFontEncoding wxFontMapperBase::GetEncodingFromName(const wxString& name) { const size_t count = WXSIZEOF(gs_encodingNames); + // many charsets use hyphens in their names but some systems use the + // same names without hyphens (e.g. "UTF-8" and "UTF8" are both common) + // so to avoid bloating gs_encodingNames array too much recognize both + // versions with and without hyphens here + wxString nameNoHyphens(name); + if ( !nameNoHyphens.Replace(_T("-"), _T("")) ) + { + // no replacement has been done, no need to compare twice + nameNoHyphens.clear(); + } + + for ( size_t i = 0; i < count; i++ ) { for ( const wxChar** encName = gs_encodingNames[i]; *encName; ++encName ) { - if ( name.CmpNoCase(*encName) == 0 ) + if ( name.CmpNoCase(*encName) == 0 || + (!nameNoHyphens.empty() && + nameNoHyphens.CmpNoCase(*encName) == 0) ) + { return gs_encodings[i]; + } } }