delphi utf8解码

最新推荐文章于 2020-06-30 09:53:41 发布

原创最新推荐文章于 2020-06-30 09:53:41 发布 · 392 阅读

CC 4.0 BY-SA版权

这篇博客介绍了如何在 Delphi 中实现 UTF8 到 Unicode 的解码过程，包括两个函数Utf8ToUnicode1和Utf8Decode1的详细代码。这两个函数用于将UTF8编码的字符串转换为WideChar或WideString类型，处理了多字节字符和错误校验。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

function Utf8ToUnicode1(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 Utf8Decode1(const S: string): WideString;
var
L: Integer;
Temp: WideString;
begin
Result := '';
if S = '' then Exit;
SetLength(Temp, Length(S));

L := Utf8ToUnicode1(PWideChar(Temp), Length(Temp)+1, PChar(S), Length(S));
if L > 0 then
SetLength(Temp, L-1)
else
Temp := '';
Result := Temp;
end;
调用：
UTF8Decode1('乱码')

delphi&nbsp;utf8解码

delphi utf8解码