delphi - 从字符串中删除所有非标准文本characers

Question

I need to strip out all non standard text characers from a string. I need remove all non ascii and control characters (except line feeds/carriage returns).

Answer 1

And here's a variant of Cosmin's that only walks the string once, but uses an efficient allocation pattern:

function StrippedOfNonAscii(const s: string): string;
var
  i, Count: Integer;
begin
  SetLength(Result, Length(s));
  Count := 0;
  for i := 1 to Length(s) do begin
    if ((s[i] >= #32) and (s[i] <= #127)) or (s[i] in [#10, #13]) then begin
      inc(Count);
      Result[Count] := s[i];
    end;
  end;
  SetLength(Result, Count);
end;

Answer 2

Something like this should do:

// For those who need a disclaimer: 
// This code is meant as a sample to show you how the basic check for non-ASCII characters goes
// It will give low performance with long strings that are called often.
// Use a TStringBuilder, or SetLength & Integer loop index to optimize.
// If you need really optimized code, pass this on to the FastCode people.
function StripNonAsciiExceptCRLF(const Value: AnsiString): AnsiString;
var
  AnsiCh: AnsiChar;
begin
  for AnsiCh in Value do
    if (AnsiCh >= #32) and (AnsiCh <= #127) and (AnsiCh <> #13) and (AnsiCh <> #10) then
      Result := Result + AnsiCh;
end;

For UnicodeString you can do something similar.

Answer 3

if you don't need to do it in-place, but generating a copy of the string, try this code

 type CharSet=Set of Char;

 function StripCharsInSet(s:string; c:CharSet):string;
  var i:Integer;
  begin
     result:='';
     for i:=1 to Length(s) do
       if not (s[i] in c) then 
         result:=result+s[i];
  end;  

and use it like this

 s := StripCharsInSet(s,[#0..#9,#11,#12,#14..#31,#127]);

EDIT : added #127 for DEL ctrl char.

EDIT2 : this is a faster version, thanks ldsandon

 function StripCharsInSet(s:string; c:CharSet):string;
  var i,j:Integer;
  begin
     SetLength(result,Length(s));
     j:=0;
     for i:=1 to Length(s) do
       if not (s[i] in c) then 
        begin
         inc(j);
         result[j]:=s[i];
        end;
     SetLength(result,j);
  end;  

Answer 4

Here's a version that doesn't build the string by appending char-by-char, but allocates the whole string in one go. It requires going over the string twice, once to count the "good" char, once to effectively copy those chars, but it's worth it because it doesn't do multiple reallocations:

function StripNonAscii(s:string):string;
var Count, i:Integer;
begin
  Count := 0;
  for i:=1 to Length(s) do
    if ((s[i] >= #32) and (s[i] <= #127)) or (s[i] in [#10, #13]) then
      Inc(Count);
  if Count = Length(s) then
    Result := s // No characters need to be removed, return the original string (no mem allocation!)
  else
    begin
      SetLength(Result, Count);
      Count := 1;
      for i:=1 to Length(s) do
        if ((s[i] >= #32) and (s[i] <= #127)) or (s[i] in [#10, #13]) then
        begin
          Result[Count] := s[i];
          Inc(Count);
        end;
    end;
end;

Answer 5

my performance solution;

function StripNonAnsiChars(const AStr: String; const AIgnoreChars: TSysCharSet): string;
var
  lBuilder: TStringBuilder;
  I: Integer;
begin
  lBuilder := TStringBuilder.Create;
  try
    for I := 1 to AStr.Length do
      if CharInSet(AStr[I], [#32..#127] + AIgnoreChars) then
        lBuilder.Append(AStr[I]);
    Result := lBuilder.ToString;
  finally
    FreeAndNil(lBuilder);
  end;
end;

I wrote by delphi xe7

Answer 6

my version with Result array of byte :

interface

type
  TSBox = array of byte;

and the function :

function StripNonAscii(buf: array of byte): TSBox;
var temp: TSBox;
    countr, countr2: integer;
const validchars : TSysCharSet = [#32..#127];
begin
if Length(buf) = 0 then exit;
countr2:= 0;
SetLength(temp, Length(buf)); //setze temp auf länge buff
for countr := 0 to Length(buf) do if CharInSet(chr(buf[countr]), validchars) then
  begin
    temp[countr2] := buf[countr];
    inc(countr2); //count valid chars
  end;
SetLength(temp, countr2);
Result := temp;
end;