Replace characters in a file (faster method)

Question

We often replace unnecessary characters in a file with another “good” character.

Interface:

procedure cleanfileASCII2(vfilename: string; vgood: integer; voutfilename: string);

To replace all unacceptable spaces that we could call cleanfileASCII2 (original.txt, 32, cleaned.txt)

The problem is that it takes quite a while. Here's a better way to do this than shown?

procedure cleanfileASCII2(vfilename: string; vgood: integer; voutfilename:
string);
var
  F1, F2: file of char;
  Ch: Char;
  tempfilename: string;
  i,n,dex: integer;
begin
   //original
    AssignFile(F1, vfilename);
    Reset(F1);
    //outputfile
    AssignFile(F2,voutfilename);
    Rewrite(F2);
      while not Eof(F1) do
      begin
        Read(F1, Ch);
        //
          n:=ord(ch);
          if ((n<32)or(n>127))and (not(n in [10,13])) then
             begin // bad char
               if vgood<> -1 then
                begin
                ch:=chr(vgood);
                Write(F2, Ch);
                end
             end
           else   //good char
            Write(F2, Ch);
      end;
    CloseFile(F2);
    CloseFile(F1);
end;

Answer 1

, . - . . , . , , . , - TCP/IP. gigE, , , - .

. blockread. 15 . 131 478 . 1024 258 .

procedure cleanfileASCII3(vfilename: string; vgood: integer; voutfilename:string);
const bufsize=1023;
var
  inFS, outFS:TFileStream;
  buffer: array[0..bufsize] of byte;
  readSize:integer;
  tempfilename: string;
  i: integer;
begin
   if not FileExists(vFileName) then exit;

   inFS:=TFileStream.Create(vFileName,fmOpenRead);
   inFS.Position:=0;
   outFS:=TFileStream.Create(vOutFileName,fmCreate);
   while not (inFS.Position>=inFS.Size) do
      begin
      readSize:=inFS.Read(buffer,sizeof(buffer));
      for I := 0 to readSize-1 do
          begin
          n:=buffer[i];
          if ((n<32)or(n>127)) and (not(n in [10,13])) and (vgood<>-1) then
             buffer[i]:=vgood;
          end;
      outFS.Write(buffer,readSize);
      end;
   inFS.Free;
   outFS.Free;
end;

Answer 2

:

• , 2k 16k .

, ( ):

procedure cleanfileASCII2(vfilename: string; vgood: integer; voutfilename: string);
var
    f1, f2: File;
    table: array[Char] of Char;
    index, inBuffer: Integer;
    buffer: array[0..2047] of Char;
    c: Char;
begin
    for c := #0 to #31 do
        table[c] := ' ';
    for c := #32 to #127 do
        table[c] := c;
    for c := #128 to #255 do
        table[c] := ' ';
    table[#10] := #10; // exception to spaces <32
    table[#13] := #13; // exception to spaces <32

    AssignFile(F1, vfilename);
    Reset(F1, 1);
    AssignFile(F2,voutfilename);
    Rewrite(F2, 1);
    while not Eof(F1) do
    begin
        BlockRead(f1, buffer, SizeOf(buffer), inBuffer);
        for index := 0 to inBuffer - 1 do
          buffer[index] := table[buffer[index]];
        BlockWrite(f2, buffer, inBuffer);
    end;
    Close(f2);
    Close(f1);
end;

Answer 3

, ( , ) , , .

IO , , .

Answer 4

- . , :

procedure cleanfileASCII2(vfilename: string; vgood: integer; voutfilename:
string);
var
  F1, F2: file;
  NumRead, NumWritten: Integer;
  Buf: array[1..2048] of Char;
  Ch: Char;
  i, n: integer;
begin
    AssignFile(F1, vfilename);
    Reset(F1, 1); // Record size = 1
    AssignFile(F2, voutfilename);
    Rewrite(F2, 1); // Record size = 1
    repeat
      BlockRead(F1, Buf, SizeOf(Buf), NumRead);
      for i := 1 to NumRead do
      begin
        Ch := Buf[i];
        //
        n := ord(ch);
        if ((n<32)or(n>127))and (not(n in [10,13])) then
        begin // bad char
         if vgood <> -1 then
         begin
           ch := chr(vgood);
           Buf[i] := Ch;
         end
        //else   //good char
         //Write(F2, Ch);
        end;
      end;
      BlockWrite(F2, Buf, NumRead, NumWritten);
    until (NumRead = 0) or (NumWritten <> NumRead);
    CloseFile(F1);
    CloseFile(F2);
end;

Answer 5

, , / . unicode, , null TStrings.

procedure TextStringToStringsAA( AStrings : TStrings; const AStr: Ansistring);
// A better routine than the stream 'SetTextStr'.
// Nulls (#0) which might be in the file e.g. from corruption in log files
// do not terminate the reading process.
var
  P, Start, VeryEnd: PansiChar;
  S: ansistring;
begin
  AStrings.BeginUpdate;
  try
    AStrings.Clear;

    P := Pansichar( AStr );
    VeryEnd := P + Length( AStr );

    if P <> nil then
      while P < VeryEnd do
      begin
        Start := P;
        while (P < VeryEnd) and not CharInSet(P^, [#10, #13]) do
         Inc(P);
        SetString(S, Start, P - Start);
        AStrings.Add(string(S));
        if P^ = #13 then Inc(P);
        if P^ = #10 then Inc(P);
      end;
  finally
    AStrings.EndUpdate;
  end;
end;


procedure TextStreamToStrings( AStream : TStream; AStrings : TStrings );
// An alternative to AStream.LoadFromStream
// Nulls (#0) which might be in the file e.g. from corruption in log files
// do not terminate the reading process.
var
  Size : Integer;
  S    : Ansistring;
begin
  AStrings.BeginUpdate;
  try
    // Make a big string with all of the text
    Size := AStream.Size - AStream.Position;
    SetString( S, nil, Size );
    AStream.Read(Pointer(S)^, Size);

    // Parse it
    TextStringToStringsAA( AStrings, S );
  finally
    AStrings.EndUpdate;
  end;
end;

procedure LoadStringsFromFile( AStrings : TStrings; const AFileName : string );
// Loads this strings from a text file
// Nulls (#0) which might be in the file e.g. from corruption in log files
// do not terminate the reading process.
var
  ST : TFileStream;
begin
  ST := TFileStream.Create( AFileName, fmOpenRead + fmShareDenyNone);
  // No attempt is made to prevent other applications from reading from or writing to the file.
  try
    ST.Position := 0;
    AStrings.BeginUpdate;
    try
      TextStreamToStrings( ST, AStrings );
    finally
      AStrings.EndUpdate;
    end;

  finally
    ST.Free;
  end;
end;

Answer 6

, , .

(delphitools.info), , . .

vgood chr .

, : Ord() Chr(). "Ch".

if not (ch in [#10, #13, #32..#127]) then

Answer 7

, :

• ()
• temp. ( )
• , , , .
• ( temp.)
• temp
• ( )
• temp
• !

vote for this post +1 if that helped