随笔 - 2146  文章 - 97 评论 - 11767 trackbacks - 253


{从字符串中提取单词的函数}
procedure StrToWordList(str: string; var List: TStringList);
var
  p: PChar;
  i: Integer;
begin
  if List = nil then List := TStringList.Create;
  List.Clear;
  {去除重复}
  List.Sorted := True;
  List.Duplicates := dupIgnore;
  
  p := PChar(str);

  {把单词以外的字符转为空格, 并把大写字母转小写}
  while p^ <> #0 do
  begin
    case p^ of
      'A'..'Z': p^ := Chr(Ord(p^) + 32);
      'a'..'z', '0'..'9', '''', '-': ;
      else p^ := #32;
    end;
    Inc(p);
  end;

  {用空格分离单词到列表}
  List.Delimiter := #32;
  List.DelimitedText := str;

  {单词的开头应该是字母, 去除其他}
  for i := List.Count - 1 downto 0 do
  begin
    if CharInSet(List[i][1], ['0'..'9', '-', '''']) then
    List.Delete(i);
  end;
end;

{从字符串中提取汉字的函数}
procedure StrToHanZiList(str: string; var List: TStringList);
var
  p: PWideChar;
begin
  if List = nil then List := TStringList.Create;
  List.Clear;
  {去除重复}
  List.Sorted := True;
  List.Duplicates := dupIgnore;
  
  p := PWideChar(str);
  while p^ <> #0 do
  begin
    case p^ of
      #$4E00..#$9FA5: List.Add(p^);
    end;
    Inc(p);
  end;
end;

posted on 2009-04-14 15:55  万一  阅读(...)  评论(...编辑  收藏