下面的代码应该可以工作,使用基本的两遍算法来查找匹配位置,然后进行替换。
请注意,对于 10MB 的文件,在我的笔记本电脑上大约需要 10 秒。如果你想让它跑得更快,你可以使用字节数组和掩码来实现它,而不是笨拙且不那么强大的 BitArray 抽象。
更好的是,您可以使用不安全的代码,在那里您可以使用指针和更快的复制...但是由于这是一个 C# 问题并且您已经在使用 BitArray 抽象,我想我会告诉您如何可以按原样实现。
private static BitArray Replace(BitArray input, BitArray pattern, BitArray replacement)
{
var replacementPositions = GetReplacementPositions(input, pattern);
return PerformReplacements(input, pattern.Length, replacement, replacementPositions);
}
private static List<int> GetReplacementPositions(BitArray input, BitArray pattern)
{
if (pattern.Length == 0) throw new Exception("Pattern cannot have 0 length");
var matchIndicies = new List<int>();
var maxCheckIndex = input.Length - pattern.Length;
var i = 0;
while (i <= maxCheckIndex)
{
if (MatchesAt(input, pattern, i))
{
matchIndicies.Add(i);
i += pattern.Length;
continue;
}
i++;
}
return matchIndicies;
}
private static bool MatchesAt(BitArray input, BitArray pattern, int index)
{
for (var j = 0; j < pattern.Length; j++)
{
if (input[index + j] != pattern[j]) return false;
}
return true;
}
private static BitArray PerformReplacements(BitArray input, int patternLength, BitArray replacement, List<int> replacementPositions)
{
var outLength = input.Length + replacementPositions.Count * (replacement.Length - patternLength);
var output = new BitArray(outLength);
var currentReadIndex = 0;
var currentWriteIndex = 0;
foreach (var matchPosition in replacementPositions)
{
var inputSubstringLength = matchPosition - currentReadIndex;
CopyFromTo(input, output, currentReadIndex, inputSubstringLength, currentWriteIndex);
currentReadIndex = matchPosition + patternLength;
currentWriteIndex += inputSubstringLength;
CopyFromTo(replacement, output, 0, replacement.Length, currentWriteIndex);
currentWriteIndex += replacement.Length;
}
CopyFromTo(input, output, currentReadIndex, input.Length - currentReadIndex, currentWriteIndex);
return output;
}
private static void CopyFromTo(BitArray from, BitArray to, int fromIndex, int fromLength, int toIndex)
{
for (var i = 0; i < fromLength; i++)
{
to.Set(toIndex + i, from.Get(fromIndex + i));
}
}