--- ibx/trunk/runtime/IBCodePage.pas 2016/07/16 12:25:48 42 +++ ibx/trunk/runtime/IBCodePage.pas 2016/09/22 17:10:15 43 @@ -11,103 +11,190 @@ interface uses Classes, SysUtils; -{$IFDEF HAS_ANSISTRING_CODEPAGE} -function IBGetCodePage(IBCP_Name: string): TSystemCodePage; -function IBGetCharacterSetName(CodePage: TSystemCodePage): RawByteString; -{$ENDIF} +type + TFirebirdCharacterSets = class + public + class function GetCharsetName(CharSetID: integer): string; + {$IFDEF HAS_ANSISTRING_CODEPAGE} + class function CharSetID2CodePage(CharSetID: integer; var CodePage: TSystemCodePage): boolean; + class function CodePage2CharSetID(CodePage: TSystemCodePage; var CharSetID: integer): boolean; + {$ENDIF} + class function CharSetName2CharSetID(CharSetName: string; var CharSetID: integer): boolean; + class function CharSetWidth(CharSetID: integer; var Width: integer): boolean; + end; + implementation -{$IFDEF HAS_ANSISTRING_CODEPAGE} type - TIBCodePage = record - IBCharacterSetName: string; - cp: TSystemCodePage; + TCharsetMap = record + CharsetID: integer; + CharSetName: string; + CharSetWidth: integer; + {$IFDEF HAS_ANSISTRING_CODEPAGE} + CodePage: TSystemCodePage; + {$ELSE} + CodePage: integer; + {$ENDIF} end; -{ Code Page numbers should align with CodePageNames array in Sysutils} +{$IFNDEF HAS_ANSISTRING_CODEPAGE} +{necessary to ensure compilation} const - IBCodePages: array [0..51] of TIBCodePage = ( - (IBCharacterSetName: 'UTF8'; cp: CP_UTF8), - (IBCharacterSetName: 'NONE'; cp: CP_NONE), - (IBCharacterSetName: 'OCTETS'; cp: CP_NONE), - (IBCharacterSetName: 'ASCII'; cp: CP_ASCII), - (IBCharacterSetName: 'SJIS_0208'; cp: 932), - (IBCharacterSetName: 'WIN1250'; cp: 1250), - (IBCharacterSetName: 'WIN1251'; cp: 1251), - (IBCharacterSetName: 'WIN1252'; cp: 1252), - (IBCharacterSetName: 'WIN1253'; cp: 1253), - (IBCharacterSetName: 'WIN1254'; cp: 1254), - (IBCharacterSetName: 'WIN1255'; cp: 1255), - (IBCharacterSetName: 'WIN1256'; cp: 1256), - (IBCharacterSetName: 'WIN1257'; cp: 1257), - (IBCharacterSetName: 'WIN1258'; cp: 1258), - (IBCharacterSetName: 'ISO8859_1'; cp: 28591), - (IBCharacterSetName: 'ISO8859_2'; cp: 28592), - (IBCharacterSetName: 'ISO8859_3'; cp: 28593), - (IBCharacterSetName: 'ISO8859_4'; cp: 28594), - (IBCharacterSetName: 'ISO8859_5'; cp: 28595), - (IBCharacterSetName: 'ISO8859_6'; cp: 28596), - (IBCharacterSetName: 'ISO8859_7'; cp: 28597), - (IBCharacterSetName: 'ISO8859_8'; cp: 28598), - (IBCharacterSetName: 'ISO8859_9'; cp: 28599), - (IBCharacterSetName: 'ISO8859_13'; cp: 28603), - (IBCharacterSetName: 'EUCJ_0208'; cp: 20932), - (IBCharacterSetName: 'DOS437'; cp: 437), - (IBCharacterSetName: 'DOS850'; cp: 850), - (IBCharacterSetName: 'DOS865'; cp: 865), - (IBCharacterSetName: 'DOS852'; cp: 852), - (IBCharacterSetName: 'DOS857'; cp: 857), - (IBCharacterSetName: 'DOS860'; cp: 860), - (IBCharacterSetName: 'DOS861'; cp: 861), - (IBCharacterSetName: 'DOS863'; cp: 863), - (IBCharacterSetName: 'CYRL'; cp: 28595), - (IBCharacterSetName: 'DOS737'; cp: 737), - (IBCharacterSetName: 'DOS775'; cp: 775), - (IBCharacterSetName: 'DOS858'; cp: 858), - (IBCharacterSetName: 'DOS862'; cp: 862), - (IBCharacterSetName: 'DOS864'; cp: 864), - (IBCharacterSetName: 'DOS866'; cp: 866), - (IBCharacterSetName: 'DOS869'; cp: 869), - (IBCharacterSetName: 'NEXT'; cp: CP_NONE), - (IBCharacterSetName: 'KSC_5601'; cp: 949), - (IBCharacterSetName: 'BIG_5'; cp: 950), - (IBCharacterSetName: 'GB_2312'; cp: 52936), - (IBCharacterSetName: 'KOI8R'; cp: 20866), - (IBCharacterSetName: 'KOI8U'; cp: 21866), - (IBCharacterSetName: 'TIS620'; cp: 20838), - (IBCharacterSetName: 'GBK'; cp: 936), - (IBCharacterSetName: 'CP943C'; cp: 50220), - (IBCharacterSetName: 'UNICODE_FSS'; cp: CP_UTF8), - (IBCharacterSetName: 'GB18030' ; cp: 54936) - ); - -function IBGetCodePage(IBCP_Name: string): TSystemCodePage; -var I: integer; -begin - Result := CP_NONE; - for I := Low(IBCodePages) to High(IBCodePages) do - if IBCodePages[I].IBCharacterSetName = IBCP_Name then - begin - Result := IBCodePages[I].cp; - Exit; - end; -end; - -function IBGetCharacterSetName(CodePage: TSystemCodePage): RawByteString; -var I: integer; -begin - Result := 'UTF8'; - for I := Low(IBCodePages) to High(IBCodePages) do - if IBCodePages[I].cp = CodePage then - begin - Result := IBCodePages[I].IBCharacterSetName; - Exit; - end; -end; + CP_ACP = 0; // default to ANSI code page + CP_OEMCP = 1; // default to OEM (console) code page + CP_UTF16 = 1200; // utf-16 + CP_UTF16BE = 1201; // unicodeFFFE + CP_UTF7 = 65000; // utf-7 + CP_UTF8 = 65001; // utf-8 + CP_ASCII = 20127; // us-ascii + CP_NONE = $FFFF; // rawbytestring encoding +{$ENDIF} +const + CharSetMap: array [0..69] of TCharsetMap = ( + (CharsetID: 0; CharSetName: 'NONE'; CharSetWidth: 1; CodePage: CP_NONE), + (CharsetID: 1; CharSetName: 'OCTETS'; CharSetWidth: 1; CodePage: CP_NONE), + (CharsetID: 2; CharSetName: 'ASCII'; CharSetWidth: 1; CodePage: CP_ASCII), + (CharsetID: 3; CharSetName: 'UNICODE_FSS'; CharSetWidth: 3; CodePage: CP_UTF8), + (CharsetID: 4; CharSetName: 'UTF8'; CharSetWidth: 4; CodePage: CP_UTF8), + (CharsetID: 5; CharSetName: 'SJIS_0208'; CharSetWidth: 2; CodePage: 20932), + (CharsetID: 6; CharSetName: 'EUCJ_0208'; CharSetWidth: 2; CodePage: 20932), + (CharsetID: 7; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 8; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 9; CharSetName: 'DOS737'; CharSetWidth: 1; CodePage: 737), + (CharsetID: 10; CharSetName: 'DOS437'; CharSetWidth: 1; CodePage: 437), + (CharsetID: 11; CharSetName: 'DOS850'; CharSetWidth: 1; CodePage: 850), + (CharsetID: 12; CharSetName: 'DOS865'; CharSetWidth: 1; CodePage: 865), + (CharsetID: 13; CharSetName: 'DOS860'; CharSetWidth: 1; CodePage: 860), + (CharsetID: 14; CharSetName: 'DOS863'; CharSetWidth: 1; CodePage: 863), + (CharsetID: 15; CharSetName: 'DOS775'; CharSetWidth: 1; CodePage: 775), + (CharsetID: 16; CharSetName: 'DOS858'; CharSetWidth: 1; CodePage: 858), + (CharsetID: 17; CharSetName: 'DOS862'; CharSetWidth: 1; CodePage: 862), + (CharsetID: 18; CharSetName: 'DOS864'; CharSetWidth: 1; CodePage: 864), + (CharsetID: 19; CharSetName: 'NEXT'; CharSetWidth: 1; CodePage: CP_NONE), + (CharsetID: 20; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 21; CharSetName: 'ISO8859_1'; CharSetWidth: 1; CodePage: 28591), + (CharsetID: 22; CharSetName: 'ISO8859_2'; CharSetWidth: 1; CodePage: 28592), + (CharsetID: 23; CharSetName: 'ISO8859_3'; CharSetWidth: 1; CodePage: 28593), + (CharsetID: 24; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 25; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 26; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 27; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 28; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 29; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 30; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 31; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 32; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 33; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 34; CharSetName: 'ISO8859_4'; CharSetWidth: 1; CodePage: 28594), + (CharsetID: 35; CharSetName: 'ISO8859_5'; CharSetWidth: 1; CodePage: 28595), + (CharsetID: 36; CharSetName: 'ISO8859_6'; CharSetWidth: 1; CodePage: 28596), + (CharsetID: 37; CharSetName: 'ISO8859_7'; CharSetWidth: 1; CodePage: 28597), + (CharsetID: 38; CharSetName: 'ISO8859_8'; CharSetWidth: 1; CodePage: 28598), + (CharsetID: 39; CharSetName: 'ISO8859_9'; CharSetWidth: 1; CodePage: 28599), + (CharsetID: 40; CharSetName: 'ISO8859_13'; CharSetWidth: 1; CodePage: 28603), + (CharsetID: 41; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 42; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 43; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 44; CharSetName: 'KSC_5601'; CharSetWidth: 2; CodePage: 949), + (CharsetID: 45; CharSetName: 'DOS852'; CharSetWidth: 1; CodePage: 852), + (CharsetID: 46; CharSetName: 'DOS857'; CharSetWidth: 1; CodePage: 857), + (CharsetID: 47; CharSetName: 'DOS861'; CharSetWidth: 1; CodePage: 861), + (CharsetID: 48; CharSetName: 'DOS866'; CharSetWidth: 1; CodePage: 866), + (CharsetID: 49; CharSetName: 'DOS869'; CharSetWidth: 1; CodePage: 869), + (CharsetID: 50; CharSetName: 'CYRL'; CharSetWidth: 1; CodePage: 1251), + (CharsetID: 51; CharSetName: 'WIN1250'; CharSetWidth: 1; CodePage: 1250), + (CharsetID: 52; CharSetName: 'WIN1251'; CharSetWidth: 1; CodePage: 1251), + (CharsetID: 53; CharSetName: 'WIN1252'; CharSetWidth: 1; CodePage: 1252), + (CharsetID: 54; CharSetName: 'WIN1253'; CharSetWidth: 1; CodePage: 1253), + (CharsetID: 55; CharSetName: 'WIN1254'; CharSetWidth: 1; CodePage: 1254), + (CharsetID: 56; CharSetName: 'BIG_5'; CharSetWidth: 2; CodePage: 950), + (CharsetID: 57; CharSetName: 'GB_2312'; CharSetWidth: 2; CodePage: 936), + (CharsetID: 58; CharSetName: 'WIN1255'; CharSetWidth: 1; CodePage: 1255), + (CharsetID: 59; CharSetName: 'WIN1256'; CharSetWidth: 1; CodePage: 1256), + (CharsetID: 60; CharSetName: 'WIN1257'; CharSetWidth: 1; CodePage: 1257), + (CharsetID: 61; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 62; CharSetName: 'Unknown'; CharSetWidth: 0; CodePage: CP_NONE), + (CharsetID: 63; CharSetName: 'KOI8R'; CharSetWidth: 1; CodePage: 20866), + (CharsetID: 64; CharSetName: 'KOI8U'; CharSetWidth: 1; CodePage: 21866), + (CharsetID: 65; CharSetName: 'WIN1258'; CharSetWidth: 1; CodePage: 1258), + (CharsetID: 66; CharSetName: 'TIS620'; CharSetWidth: 1; CodePage: 874), + (CharsetID: 67; CharSetName: 'GBK'; CharSetWidth: 2; CodePage: 936), + (CharsetID: 68; CharSetName: 'CP943C'; CharSetWidth: 2; CodePage: 943), + (CharsetID: 69; CharSetName: 'GB18030'; CharSetWidth: 4; CodePage: 54936) +); + + class function TFirebirdCharacterSets.GetCharsetName(CharSetID: integer): string; + begin + Result := ''; + if (CharSetID >= Low(CharSetMap)) and (CharSetID <= High(CharSetMap)) and + (CharSetMap[CharSetID].CharSetID = CharSetID) then + begin + Result := CharSetMap[CharSetID].CharSetName; + Exit; + end; + end; + +{$IFDEF HAS_ANSISTRING_CODEPAGE} +class function TFirebirdCharacterSets.CharSetID2CodePage(CharSetID: integer; + var CodePage: TSystemCodePage): boolean; + begin + Result := (CharSetID >= Low(CharSetMap)) and (CharSetID <= High(CharSetMap)) + and (CharSetMap[CharSetID].CharSetID = CharSetID); + if Result then + begin + CodePage := CharSetMap[CharSetID].CodePage; + Result := true; + Exit; + end; + end; + + class function TFirebirdCharacterSets.CodePage2CharSetID(CodePage: TSystemCodePage; + var CharSetID: integer): boolean; + var i: integer; + begin + Result := false; + for i := Low(CharSetMap) to High(CharSetMap) do + if CharSetMap[i].CodePage = CodePage then + begin + CharSetID := CharSetMap[i].CharSetID; + Result := true; + Exit; + end; + end; {$ENDIF} + class function TFirebirdCharacterSets.CharSetName2CharSetID(CharSetName: string; + var CharSetID: integer): boolean; + var i: integer; + begin + Result := false; + for i := Low(CharSetMap) to High(CharSetMap) do + if CompareStr(CharSetMap[i].CharSetName, CharSetName) = 0 then + begin + CharSetID := CharSetMap[i].CharSetID; + Result := true; + Exit; + end; + end; + + class function TFirebirdCharacterSets.CharSetWidth(CharSetID: integer; var Width: integer + ): boolean; + begin + Result := (CharSetID >= Low(CharSetMap)) and (CharSetID <= High(CharSetMap)) + and (CharSetMap[CharSetID].CharSetID = CharSetID); + if Result then + begin + Width := CharSetMap[CharSetID].CharSetWidth; + Result := true; + Exit; + end; + end; + + + + end.