Delphi System单元 Utf8ToAnsi、AnsiToUtf8、Utf8Decode、Utf8Encode、Utf8ToUnicode、UnicodeToUtf8 转换

Delphi System单元 Utf8ToAnsi、AnsiToUtf8、Utf8Decode、Utf8Encode、Utf8ToUnicode、UnicodeToUtf8 转换

单元：System

原型：

?

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 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 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185

function UnicodeToUtf8(Dest: PChar; MaxDestBytes: Cardinal; Source: PWideChar; SourceChars: Cardinal): Cardinal; var   i, count: Cardinal;   c: Cardinal; begin   Result := 0;   if Source = nil then Exit;   count := 0;   i := 0;   if Dest <> nil then   begin     while (i < SourceChars) and (count < MaxDestBytes) do     begin       c := Cardinal(Source[i]);       Inc(i);       if c <= $7F then       begin         Dest[count] := Char(c);         Inc(count);       end       else if c > $7FF then       begin         if count + 3 > MaxDestBytes then           break;         Dest[count] := Char($E0 or (c shr 12));         Dest[count+1] := Char($80 or ((c shr 6) and $3F));         Dest[count+2] := Char($80 or (c and $3F));         Inc(count,3);       end       else //  $7F < Source[i] <= $7FF       begin         if count + 2 > MaxDestBytes then           break;         Dest[count] := Char($C0 or (c shr 6));         Dest[count+1] := Char($80 or (c and $3F));         Inc(count,2);       end;     end;     if count >= MaxDestBytes then count := MaxDestBytes-1;     Dest[count] := #0;   end   else   begin     while i < SourceChars do     begin       c := Integer(Source[i]);       Inc(i);       if c > $7F then       begin         if c > $7FF then           Inc(count);         Inc(count);       end;       Inc(count);     end;   end;   Result := count+1;  // convert zero based index to byte count end;   function Utf8ToUnicode(Dest: PWideChar; Source: PChar; MaxChars: Integer): Integer; var   len: Cardinal; begin   len := 0;   if Source <> nil then     while Source[len] <> #0 do       Inc(len);   Result := Utf8ToUnicode(Dest, MaxChars, Source, len); end;   function Utf8ToUnicode(Dest: PWideChar; MaxDestChars: Cardinal; Source: PChar; SourceBytes: Cardinal): Cardinal; var   i, count: Cardinal;   c: Byte;   wc: Cardinal; begin   if Source = nil then   begin     Result := 0;     Exit;   end;   Result := Cardinal(-1);   count := 0;   i := 0;   if Dest <> nil then   begin     while (i < SourceBytes) and (count < MaxDestChars) do     begin       wc := Cardinal(Source[i]);       Inc(i);       if (wc and $80) <> 0 then       begin         if i >= SourceBytes then Exit;          // incomplete multibyte char         wc := wc and $3F;         if (wc and $20) <> 0 then         begin           c := Byte(Source[i]);           Inc(i);           if (c and $C0) <> $80 then Exit;      // malformed trail byte or out of range char           if i >= SourceBytes then Exit;        // incomplete multibyte char           wc := (wc shl 6) or (c and $3F);         end;         c := Byte(Source[i]);         Inc(i);         if (c and $C0) <> $80 then Exit;       // malformed trail byte           Dest[count] := WideChar((wc shl 6) or (c and $3F));       end       else         Dest[count] := WideChar(wc);       Inc(count);     end;     if count >= MaxDestChars then count := MaxDestChars-1;     Dest[count] := #0;   end   else   begin     while (i < SourceBytes) do     begin       c := Byte(Source[i]);       Inc(i);       if (c and $80) <> 0 then       begin         if i >= SourceBytes then Exit;          // incomplete multibyte char         c := c and $3F;         if (c and $20) <> 0 then         begin           c := Byte(Source[i]);           Inc(i);           if (c and $C0) <> $80 then Exit;      // malformed trail byte or out of range char           if i >= SourceBytes then Exit;        // incomplete multibyte char         end;         c := Byte(Source[i]);         Inc(i);         if (c and $C0) <> $80 then Exit;       // malformed trail byte       end;       Inc(count);     end;   end;   Result := count+1; end;   function Utf8Encode(const WS: WideString): UTF8String; var   L: Integer;   Temp: UTF8String; begin   Result := '';   if WS = '' then Exit;   SetLength(Temp, Length(WS) * 3); // SetLength includes space for null terminator     L := UnicodeToUtf8(PChar(Temp), Length(Temp)+1, PWideChar(WS), Length(WS));   if L > 0 then     SetLength(Temp, L-1)   else     Temp := '';   Result := Temp; end;   function Utf8Decode(const S: UTF8String): WideString; var   L: Integer;   Temp: WideString; begin   Result := '';   if S = '' then Exit;   SetLength(Temp, Length(S));     L := Utf8ToUnicode(PWideChar(Temp), Length(Temp)+1, PChar(S), Length(S));   if L > 0 then     SetLength(Temp, L-1)   else     Temp := '';   Result := Temp; end;   function AnsiToUtf8(const S: string): UTF8String; begin   Result := Utf8Encode(S); end;   function Utf8ToAnsi(const S: UTF8String): string; begin   Result := Utf8Decode(S); end;

从源码中可以看到 

• Utf8ToAnsi 调用了 Utf8Decode 函数
• AnsiToUtf8 调用了 Utf8Encode 函数

所以解码的时候用 Utf8ToAnsi 或 Utf8Decode 都可以的。

 

 

 

创建时间：2020.12.22　　更新时间：