delphi 检查字符串是不是 包含 中文和获取中文字符个数

本文整理自网络，侵删。

 
function IsChineseText(const AStr:{$IFDEF UNICODE}string{$ELSE}WideString{$ENDIF};
      const OutCharecterCountValAddr: PInteger = nil;
      const OutWideCharCountValAddr: PInteger = nil;
      const CheckAllChar: Boolean = False;
      const IncludeCharacters: Boolean = True;
      const IncludeRadicals: Boolean = False;
      const IncludePUAParts: Boolean = False;
      const IncludeStrokes: Boolean = False;
      const IncludePhoneticNotation: Boolean = False;
      const IncludeAllCharacters: Boolean = False): Boolean;
var
  I, F, C: Integer;
  IsHasNext,
  IsDoubleWideChar,
  IsNoCheckNext,
  IsFound,
  IsAllTrue: Boolean;
  UTF32: DWORD;
  FFindCoundMode: Boolean;
begin
  Result := False;
  FFindCoundMode := ((OutCharecterCountValAddr <> nil) or (OutWideCharCountValAddr <> nil));
  IsAllTrue := Length(AStr) <> 0;
{$IFDEF UNICODE}
  F := Low(AStr);
  C := High(AStr);
{$ELSE}
  F := 1;
  C := Length(AStr);
{$ENDIF}
  IsNoCheckNext := False;
  for I := F to C do
  begin
    IsHasNext := I < C;
    if IsNoCheckNext then Continue;
    IsNoCheckNext := False;
    IsDoubleWideChar := False;
    if ((AStr[I] >= #$D800) and (AStr[I] <= #$DFFF)) and IsHasNext then
    begin
      UTF32 := (Cardinal(AStr[I]) and $000003FF) shl 10 or (Cardinal(AStr[I + 1]) and $000003FF) + $00010000;
      IsDoubleWideChar := True;
      IsNoCheckNext := True;
    end
    else
      UTF32 := Ord(AStr[I]);
//https://www.qqxiuzi.cn/zh/hanzi-unicode-bianma.php
//字符集字数Unicode 编码
//基本汉字20902字4E00-9FA5
//基本汉字补充38字9FA6-9FCB
//扩展A6582字3400-4DB5
//扩展B42711字20000-2A6D6
//扩展C4149字2A700-2B734
//扩展D222字2B740-2B81D
//康熙部首214字2F00-2FD5
//部首扩展115字2E80-2EF3
//兼容汉字477字F900-FAD9
//兼容扩展542字2F800-2FA1D
//PUA(GBK)部件81字E815-E86F
//部件扩展452字E400-E5E8
//PUA增补207字E600-E6CF
//汉字笔画36字31C0-31E3
//汉字结构12字2FF0-2FFB
//汉语注音22字3105-3120
//注音扩展22字31A0-31BA
//?1字3007
//http://www.unicode.org/cgi-bin/GetUnihanData.pl?codepoint=UnicodeHexCode
    IsFound := False;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $4E00) and (UTF32 <= $9FA5);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $9FA6) and (UTF32 <= $9FCB);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $3400) and (UTF32 <= $4DB5);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $20000) and (UTF32 <= $2A6D6);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $2A700) and (UTF32 <= $2B734);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $2B740) and (UTF32 <= $2B81D);
    end;
    if (not IsFound) and IncludeRadicals then
    begin
      IsFound := (UTF32 >= $2F00) and (UTF32 <= $2FD5);
    end;
    if (not IsFound) and IncludeRadicals then
    begin
      IsFound := (UTF32 >= $2E80) and (UTF32 <= $2EF3);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $F900) and (UTF32 <= $FAD9);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 >= $2F800) and (UTF32 <= $2FA1D);
    end;
    if (not IsFound) and IncludePUAParts then
    begin
      IsFound := (UTF32 >= $E815) and (UTF32 <= $E86F);
    end;
    if (not IsFound) and IncludePUAParts then
    begin
      IsFound := (UTF32 >= $E400) and (UTF32 <= $E5E8);
    end;
    if (not IsFound) and IncludePUAParts then
    begin
      IsFound := (UTF32 >= $E600) and (UTF32 <= $E6CF);
    end;
    if (not IsFound) and IncludeStrokes then
    begin
      IsFound := (UTF32 >= $31C0) and (UTF32 <= $31E3);
    end;
    if (not IsFound) and IncludeStrokes then
    begin
      IsFound := (UTF32 >= $2FF0) and (UTF32 <= $2FFB);
    end;
    if (not IsFound) and IncludePhoneticNotation then
    begin
      IsFound := (UTF32 >= $3105) and (UTF32 <= $3120);
    end;
    if (not IsFound) and IncludePhoneticNotation then
    begin
      IsFound := (UTF32 >= $31A0) and (UTF32 <= $31BA);
    end;
    if (not IsFound) and IncludeCharacters then
    begin
      IsFound := (UTF32 = $3007)
    end;
    if (not IsFound) and IncludeAllCharacters then
    begin
      IsFound := (UTF32 >= $0391) and (UTF32 <= $FFE5);
    end;

    if IsFound then
    begin
      if (not CheckAllChar) then
      begin
        Result := True;
      end;
      if (OutCharecterCountValAddr <> nil) then
      begin
        Inc(OutCharecterCountValAddr^);
      end;
      if (OutWideCharCountValAddr <> nil) then
      begin
        Inc(OutWideCharCountValAddr^);
        if IsDoubleWideChar then
          Inc(OutWideCharCountValAddr^);
      end;
      if (not CheckAllChar) and (not FFindCoundMode) then
      begin
        Break;
      end;
    end
    else
      IsAllTrue := False;
  end;
  if CheckAllChar then
    Result := IsAllTrue;
end;


procedure TForm1.FormCreate(Sender: TObject);
begin
if IsChineseText('dfafa中国dfas') then
begin
text:='包含';
end
else
begin
text:='不包含';
end;
end;
 

相关阅读 >>

Delphi 内存修改的实现

Delphi android 拨打电话

Delphi跨平台的字符串代码标准

Delphi判断字符串中是否包含汉字，并返回汉字位置

Delphi和outputdebugstring

Delphi根据网络链接截取域名

Delphi 调用ie隐藏的命令

Delphi 关于虚拟的desktop的编程

Delphi 从文件中读取图像类型

Delphi 从给定字符串中截取n个字节的字符（解决汉字截取乱码问题）

更多相关阅读请进入《Delphi》频道 >>

转载请注明出处：木庄网络博客 » delphi 检查字符串是不是 包含 中文和获取中文字符个数