这个答案现在已经完成并且适用于区分大小写的模式,但不适用于不区分大小写的模式,并且可能还有其他错误,因为它没有经过很好的单元测试,并且可能会进一步优化,例如我重复了本地函数 __SameChar而不是使用更快的比较函数回调,实际上,允许用户为所有这些传递一个比较函数对于想要提供一些额外逻辑的 Unicode 用户来说非常棒(某些语言的等效 Unicode 字形集)。
基于 Dorin Dominica 的代码,我构建了以下内容。
{ _FindStringBoyer:
Boyer-Moore search algorith using regular String instead of AnsiSTring, and no ASM.
Credited to Dorin Duminica.
}
function _FindStringBoyer(const sString, sPattern: string;
const bCaseSensitive: Boolean = True; const fromPos: Integer = 1): Integer;
function __SameChar(StringIndex, PatternIndex: Integer): Boolean;
begin
if bCaseSensitive then
Result := (sString[StringIndex] = sPattern[PatternIndex])
else
Result := (CompareText(sString[StringIndex], sPattern[PatternIndex]) = 0);
end; // function __SameChar(StringIndex, PatternIndex: Integer): Boolean;
var
SkipTable: array [Char] of Integer;
LengthPattern: Integer;
LengthString: Integer;
Index: Integer;
kIndex: Integer;
LastMarker: Integer;
Large: Integer;
chPattern: Char;
begin
if fromPos < 1 then
raise Exception.CreateFmt('Invalid search start position: %d.', [fromPos]);
LengthPattern := Length(sPattern);
LengthString := Length(sString);
for chPattern := Low(Char) to High(Char) do
SkipTable[chPattern] := LengthPattern;
for Index := 1 to LengthPattern -1 do
SkipTable[sPattern[Index]] := LengthPattern - Index;
Large := LengthPattern + LengthString + 1;
LastMarker := SkipTable[sPattern[LengthPattern]];
SkipTable[sPattern[LengthPattern]] := Large;
Index := fromPos + LengthPattern -1;
Result := 0;
while Index <= LengthString do begin
repeat
Index := Index + SkipTable[sString[Index]];
until Index > LengthString;
if Index <= Large then
Break
else
Index := Index - Large;
kIndex := 1;
while (kIndex < LengthPattern) and __SameChar(Index - kIndex, LengthPattern - kIndex) do
Inc(kIndex);
if kIndex = LengthPattern then begin
// Found, return.
Result := Index - kIndex + 1;
Index := Index + LengthPattern;
exit;
end else begin
if __SameChar(Index, LengthPattern) then
Index := Index + LastMarker
else
Index := Index + SkipTable[sString[Index]];
end; // if kIndex = LengthPattern then begin
end; // while Index <= LengthString do begin
end;
{ Written by Warren, using the above code as a starter, we calculate the SkipTable once, and then count the number of instances of
a substring inside the main string, at a much faster rate than we
could have done otherwise. Another thing that would be great is
to have a function that returns an array of find-locations,
which would be way faster to do than repeatedly calling Pos.
}
function _StringCountBoyer(const aSourceString, aFindString : String; Const CaseSensitive : Boolean = TRUE) : Integer;
var
foundPos:Integer;
fromPos:Integer;
Limit:Integer;
guard:Integer;
SkipTable: array [Char] of Integer;
LengthPattern: Integer;
LengthString: Integer;
Index: Integer;
kIndex: Integer;
LastMarker: Integer;
Large: Integer;
chPattern: Char;
function __SameChar(StringIndex, PatternIndex: Integer): Boolean;
begin
if CaseSensitive then
Result := (aSourceString[StringIndex] = aFindString[PatternIndex])
else
Result := (CompareText(aSourceString[StringIndex], aFindString[PatternIndex]) = 0);
end; // function __SameChar(StringIndex, PatternIndex: Integer): Boolean;
begin
result := 0;
foundPos := 1;
fromPos := 1;
Limit := Length(aSourceString);
guard := Length(aFindString);
Index := 0;
LengthPattern := Length(aFindString);
LengthString := Length(aSourceString);
for chPattern := Low(Char) to High(Char) do
SkipTable[chPattern] := LengthPattern;
for Index := 1 to LengthPattern -1 do
SkipTable[aFindString[Index]] := LengthPattern - Index;
Large := LengthPattern + LengthString + 1;
LastMarker := SkipTable[aFindString[LengthPattern]];
SkipTable[aFindString[LengthPattern]] := Large;
while (foundPos>=1) and (fromPos < Limit) and (Index<Limit) do begin
Index := fromPos + LengthPattern -1;
if Index>Limit then
break;
kIndex := 0;
while Index <= LengthString do begin
repeat
Index := Index + SkipTable[aSourceString[Index]];
until Index > LengthString;
if Index <= Large then
Break
else
Index := Index - Large;
kIndex := 1;
while (kIndex < LengthPattern) and __SameChar(Index - kIndex, LengthPattern - kIndex) do
Inc(kIndex);
if kIndex = LengthPattern then begin
// Found, return.
//Result := Index - kIndex + 1;
Index := Index + LengthPattern;
fromPos := Index;
Inc(Result);
break;
end else begin
if __SameChar(Index, LengthPattern) then
Index := Index + LastMarker
else
Index := Index + SkipTable[aSourceString[Index]];
end; // if kIndex = LengthPattern then begin
end; // while Index <= LengthString do begin
end;
end;
这确实是一个不错的算法,因为:
- 以这种方式计算字符串 Y 中子字符串 X 的实例要快得多,非常棒。
- 仅仅替换 Pos() _FindStringBoyer() 比由 FastCode 项目人员贡献给 Delphi 的 Pos() 的纯 asm 版本更快,目前用于 Pos,如果你需要不区分大小写,你可以想象性能当我们不必在 100 兆字节的字符串上调用大写时提升。(好吧,你的字符串不会那么大。但是,高效算法仍然是一件美丽的事情。)
好的,我用 Boyer-Moore 风格写了一个字符串替换:
function _StringReplaceBoyer(const aSourceString, aFindString,aReplaceString : String; Flags: TReplaceFlags) : String;
var
errors:Integer;
fromPos:Integer;
Limit:Integer;
guard:Integer;
SkipTable: array [Char] of Integer;
LengthPattern: Integer;
LengthString: Integer;
Index: Integer;
kIndex: Integer;
LastMarker: Integer;
Large: Integer;
chPattern: Char;
CaseSensitive:Boolean;
foundAt:Integer;
lastFoundAt:Integer;
copyStartsAt:Integer;
copyLen:Integer;
function __SameChar(StringIndex, PatternIndex: Integer): Boolean;
begin
if CaseSensitive then
Result := (aSourceString[StringIndex] = aFindString[PatternIndex])
else
Result := (CompareText(aSourceString[StringIndex], aFindString[PatternIndex]) = 0);
end; // function __SameChar(StringIndex, PatternIndex: Integer): Boolean;
begin
result := '';
lastFoundAt := 0;
fromPos := 1;
errors := 0;
CaseSensitive := rfIgnoreCase in Flags;
Limit := Length(aSourceString);
guard := Length(aFindString);
Index := 0;
LengthPattern := Length(aFindString);
LengthString := Length(aSourceString);
for chPattern := Low(Char) to High(Char) do
SkipTable[chPattern] := LengthPattern;
for Index := 1 to LengthPattern -1 do
SkipTable[aFindString[Index]] := LengthPattern - Index;
Large := LengthPattern + LengthString + 1;
LastMarker := SkipTable[aFindString[LengthPattern]];
SkipTable[aFindString[LengthPattern]] := Large;
while (fromPos>=1) and (fromPos <= Limit) and (Index<=Limit) do begin
Index := fromPos + LengthPattern -1;
if Index>Limit then
break;
kIndex := 0;
foundAt := 0;
while Index <= LengthString do begin
repeat
Index := Index + SkipTable[aSourceString[Index]];
until Index > LengthString;
if Index <= Large then
Break
else
Index := Index - Large;
kIndex := 1;
while (kIndex < LengthPattern) and __SameChar(Index - kIndex, LengthPattern - kIndex) do
Inc(kIndex);
if kIndex = LengthPattern then begin
foundAt := Index - kIndex + 1;
Index := Index + LengthPattern;
//fromPos := Index;
fromPos := (foundAt+LengthPattern);
if lastFoundAt=0 then begin
copyStartsAt := 1;
copyLen := foundAt-copyStartsAt;
end else begin
copyStartsAt := lastFoundAt+LengthPattern;
copyLen := foundAt-copyStartsAt;
end;
if (copyLen<=0)or(copyStartsAt<=0) then begin
Inc(errors);
end;
Result := Result + Copy(aSourceString, copyStartsAt, copyLen ) + aReplaceString;
lastFoundAt := foundAt;
if not (rfReplaceAll in Flags) then
fromPos := 0; // break out of outer while loop too!
break;
end else begin
if __SameChar(Index, LengthPattern) then
Index := Index + LastMarker
else
Index := Index + SkipTable[aSourceString[Index]];
end; // if kIndex = LengthPattern then begin
end; // while Index <= LengthString do begin
end;
if (lastFoundAt=0) then
begin
// nothing was found, just return whole original string
Result := aSourceString;
end
else
if (lastFoundAt+LengthPattern < Limit) then begin
// the part that didn't require any replacing, because nothing more was found,
// or rfReplaceAll flag was not specified, is copied at the
// end as the final step.
copyStartsAt := lastFoundAt+LengthPattern;
copyLen := Limit; { this number can be larger than needed to be, and it is harmless }
Result := Result + Copy(aSourceString, copyStartsAt, copyLen );
end;
end;
好的,问题:这个的堆栈足迹:
var
skiptable : array [Char] of Integer; // 65536*4 bytes stack usage on Unicode delphi
再见 CPU 地狱,你好堆栈地狱。如果我选择动态数组,那么我必须在运行时调整它的大小。所以这个东西基本上很快,因为你计算机上的虚拟内存系统在堆栈上的 256K 时不会闪烁,但这并不总是一段最佳代码。尽管如此,我的电脑并不会在这样的大堆栈上眨眼。它不会成为 Delphi 标准库的默认设置,也不会在未来赢得任何 fastcode 挑战,具有那种足迹。我认为重复搜索是一种情况,上面的代码应该写成一个类,而skiptable应该是那个类中的一个数据字段。然后,您可以构建一次 boyer-moore 表,并且随着时间的推移,如果字符串是不变的,则重复使用该对象进行快速查找。