在第一个代码示例中,您有两个错误,在第二个示例中,您有三个错误:
- 不要在内存中加载整个大文件,特别是在32位应用程序中。如果文件大小超过~1 GB,则始终会出现“内存不足”错误。
StringReplace
对于较大的字符串速度会变慢,因为需要反复进行内存重新分配。- 在第二个代码示例中,您没有使用文件的文本编码,因此(对于Windows),您的代码“认为”文件具有UCS2编码(每个字符两个字节)。但是,如果文件编码是Ansi(每个字符一个字节)或UTF8(字符大小可变),则会发生什么?
因此,为了正确地查找和替换,您必须使用文件编码并读取/写入文件部分,如LU RD所说:
interface
uses
System.Classes,
System.SysUtils;
type
TFileSearchReplace = class(TObject)
private
FSourceFile: TFileStream;
FtmpFile: TFileStream;
FEncoding: TEncoding;
public
constructor Create(const AFileName: string);
destructor Destroy; override;
procedure Replace(const AFrom, ATo: string; ReplaceFlags: TReplaceFlags);
end;
implementation
uses
System.IOUtils,
System.StrUtils;
function Max(const A, B: Integer): Integer;
begin
if A > B then
Result := A
else
Result := B;
end;
constructor TFileSearchReplace.Create(const AFileName: string);
begin
inherited Create;
FSourceFile := TFileStream.Create(AFileName, fmOpenReadWrite);
FtmpFile := TFileStream.Create(ChangeFileExt(AFileName, '.tmp'), fmCreate);
end;
destructor TFileSearchReplace.Destroy;
var
tmpFileName: string;
begin
if Assigned(FtmpFile) then
tmpFileName := FtmpFile.FileName;
FreeAndNil(FtmpFile);
FreeAndNil(FSourceFile);
TFile.Delete(tmpFileName);
inherited;
end;
procedure TFileSearchReplace.Replace(const AFrom, ATo: string;
ReplaceFlags: TReplaceFlags);
procedure CopyPreamble;
var
PreambleSize: Integer;
PreambleBuf: TBytes;
begin
SetLength(PreambleBuf, 100);
FSourceFile.Read(PreambleBuf, Length(PreambleBuf));
FSourceFile.Seek(0, soBeginning);
PreambleSize := TEncoding.GetBufferEncoding(PreambleBuf, FEncoding);
if PreambleSize <> 0 then
FtmpFile.CopyFrom(FSourceFile, PreambleSize);
end;
function GetLastIndex(const Str, SubStr: string): Integer;
var
i: Integer;
tmpSubStr, tmpStr: string;
begin
if not(rfIgnoreCase in ReplaceFlags) then
begin
i := Pos(SubStr, Str);
Result := i;
while i > 0 do
begin
i := PosEx(SubStr, Str, i + 1);
if i > 0 then
Result := i;
end;
if Result > 0 then
Inc(Result, Length(SubStr) - 1);
end
else
begin
tmpStr := UpperCase(Str);
tmpSubStr := UpperCase(SubStr);
i := Pos(tmpSubStr, tmpStr);
Result := i;
while i > 0 do
begin
i := PosEx(tmpSubStr, tmpStr, i + 1);
if i > 0 then
Result := i;
end;
if Result > 0 then
Inc(Result, Length(tmpSubStr) - 1);
end;
end;
var
SourceSize: int64;
procedure ParseBuffer(Buf: TBytes; var IsReplaced: Boolean);
var
i: Integer;
ReadedBufLen: Integer;
BufStr: string;
DestBytes: TBytes;
LastIndex: Integer;
begin
if IsReplaced and (not(rfReplaceAll in ReplaceFlags)) then
begin
FtmpFile.Write(Buf, Length(Buf));
Exit;
end;
ReadedBufLen := 0;
for i := Length(Buf) downto 0 do
if FEncoding.GetCharCount(Buf, 0, i) <> 0 then
begin
ReadedBufLen := i;
Break;
end;
if ReadedBufLen = 0 then
raise EEncodingError.Create('Cant convert bytes to str');
FSourceFile.Seek(ReadedBufLen - Length(Buf), soCurrent);
BufStr := FEncoding.GetString(Buf, 0, ReadedBufLen);
if rfIgnoreCase in ReplaceFlags then
IsReplaced := ContainsText(BufStr, AFrom)
else
IsReplaced := ContainsStr(BufStr, AFrom);
if IsReplaced then
begin
LastIndex := GetLastIndex(BufStr, AFrom);
LastIndex := Max(LastIndex, Length(BufStr) - Length(AFrom) + 1);
end
else
LastIndex := Length(BufStr);
SetLength(BufStr, LastIndex);
FSourceFile.Seek(FEncoding.GetByteCount(BufStr) - ReadedBufLen, soCurrent);
BufStr := StringReplace(BufStr, AFrom, ATo, ReplaceFlags);
DestBytes := FEncoding.GetBytes(BufStr);
FtmpFile.Write(DestBytes, Length(DestBytes));
end;
var
Buf: TBytes;
BufLen: Integer;
bReplaced: Boolean;
begin
FSourceFile.Seek(0, soBeginning);
FtmpFile.Size := 0;
CopyPreamble;
SourceSize := FSourceFile.Size;
BufLen := Max(FEncoding.GetByteCount(AFrom) * 5, 2048);
BufLen := Max(FEncoding.GetByteCount(ATo) * 5, BufLen);
SetLength(Buf, BufLen);
bReplaced := False;
while FSourceFile.Position < SourceSize do
begin
BufLen := FSourceFile.Read(Buf, Length(Buf));
SetLength(Buf, BufLen);
ParseBuffer(Buf, bReplaced);
end;
FSourceFile.Size := 0;
FSourceFile.CopyFrom(FtmpFile, 0);
end;
使用方法:
procedure TForm2.btn1Click(Sender: TObject);
var
Replacer: TFileSearchReplace;
StartTime: TDateTime;
begin
StartTime:=Now;
Replacer:=TFileSearchReplace.Create('c:\Temp\123.txt');
try
Replacer.Replace('some текст', 'some', [rfReplaceAll, rfIgnoreCase]);
finally
Replacer.Free;
end;
Caption:=FormatDateTime('nn:ss.zzz', Now - StartTime);
end;