在大文件中搜索和替换正则表达式而不会出现OutOfMemoryException

Question

我创建了一个小代码，用于搜索Regex字符串，并将其替换为其他内容，然后使用所做的更改创建一个新的输出文件。 该代码似乎适用于较小的文件，但是对于100 MB或较大的文件，我给出了System.OutOfMemoryException错误。

这是我的代码：

string foldername = Path.Combine(
    Environment.GetFolderPath(Environment.SpecialFolder.Desktop),
    String.Format("FIXED_{0}.tmx",
        Path.GetFileNameWithoutExtension(textBox1.Text)));

string text = File.ReadAllText(textBox1.Text);
text = Regex.Replace(text, @"<seg\b[^>]*>", "<seg>", RegexOptions.Multiline);
text = Regex.Replace(text, @"<seg>
                    </tuv>", "<seg></seg></tuv>", RegexOptions.Multiline);

File.WriteAllText(foldername, text);

Visual Studio突出显示string text = File.ReadAllText(textBox1.Text); 部分。 我认为也许使用File.ReadAllLines会更好，但是我无法使其与正则表达式一起使用。

有人可以帮我吗？ 我是C＃的新手，可能我的代码不是最好的代码。

Answer 1

恐怕您必须自己实施替换。 以下是使用状态机将<seg\\b[^>*]>替换为<seg>的示例代码。 唯一的问题是，如果文件以<seg attr=""结尾，则仅<seg将被写入输出。

enum TruncateSegState
{
    Idle,
    TagStart,
    TagStartS,
    TagStartSE,
    TagStartSEG,
    TagSEG
}

static void TruncateSeg(StreamReader input, StreamWriter output)
{
    TruncateSegState state = TruncateSegState.Idle;
    while (!input.EndOfStream)
    {
        char ch = (char)input.Read();
        switch (state)
        {
            case TruncateSegState.Idle:
                if (ch == '<')
                    state = TruncateSegState.TagStart;
                output.Write(ch);
                break;
            case TruncateSegState.TagStart:
                if (ch == 's')
                    state = TruncateSegState.TagStartS;
                else
                    state = TruncateSegState.Idle;
                output.Write(ch);
                break;
            case TruncateSegState.TagStartS:
                if (ch == 'e')
                    state = TruncateSegState.TagStartSE;
                else
                    state = TruncateSegState.Idle;
                output.Write(ch);
                break;
            case TruncateSegState.TagStartSE:
                if (ch == 'g')
                    state = TruncateSegState.TagStartSEG;
                else
                    state = TruncateSegState.Idle;
                output.Write(ch);
                break;
            case TruncateSegState.TagStartSEG:
                if (char.IsWhiteSpace(ch))
                    state = TruncateSegState.TagSEG;
                else
                {
                    state = TruncateSegState.Idle;
                    output.Write(ch);
                }
                break;
            case TruncateSegState.TagSEG:
                if (ch == '>')
                {
                    state = TruncateSegState.Idle;
                    output.Write(ch);
                }
                break;
        }
    }
}

用法：

using (StreamReader reader = new StreamReader("input.txt"))
using (StreamWriter writer = new StreamWriter("temp.txt"))
    TruncateSeg(reader, writer);

生成temp.txt ，将其用作下一个方法的输入，该方法将添加缺少的</seg>标记。

enum ReplaceSegTuvState
{
    Idle,
    InsideSEG
}

static void ReplaceSegTuv(StreamReader input, StreamWriter output)
{
    ReplaceSegTuvState state = ReplaceSegTuvState.Idle;
    StringBuilder segBuffer = new StringBuilder();
    while (!input.EndOfStream)
    {
        char ch = (char)input.Read();
        switch (state)
        {
            case ReplaceSegTuvState.Idle:
                if (ch == '<')
                {
                    char[] buffer = new char[4];
                    int bufferActualLength = input.ReadBlock(buffer, 0, buffer.Length);
                    output.Write('<');
                    output.Write(buffer, 0, bufferActualLength);
                    if (bufferActualLength == buffer.Length && "seg>".SequenceEqual(buffer))
                    {
                        segBuffer.Clear();
                        state = ReplaceSegTuvState.InsideSEG;
                    }
                }
                else
                    output.Write(ch);
                break;
            case ReplaceSegTuvState.InsideSEG:
                if (ch == '<')
                {
                    char[] buffer = new char[5];
                    int bufferActualLength = input.ReadBlock(buffer, 0, buffer.Length);
                    if (bufferActualLength == buffer.Length && "/tuv>".SequenceEqual(buffer))
                    {
                        output.Write("</seg>");
                        output.Write("</tuv>");
                        state = ReplaceSegTuvState.Idle;
                    }
                    else
                    {
                        output.Write(segBuffer.ToString());
                        output.Write('<');
                        output.Write(buffer, 0, bufferActualLength);
                        state = ReplaceSegTuvState.Idle;
                    }
                }
                else if (!char.IsWhiteSpace(ch))
                {
                    output.Write(segBuffer.ToString());
                    output.Write(ch);
                    state = ReplaceSegTuvState.Idle;
                }
                else
                    segBuffer.Append(ch);
                break;
        }
    }
}

用法：

using (StreamReader reader = new StreamReader("temp.txt"))
using (StreamWriter writer = new StreamWriter("output.txt"))
    ReplaceSegTuv(reader, writer);

Answer 2

尝试查看内存托管文件； MSDN： http : //msdn.microsoft.com/en-us/library/dd997372.aspx

他们似乎是处理超大文件的推荐方法。