搜索并替换大文件中的正则表达式，而不会得到OutOfMemoryException

本文关键字：OutOfMemoryException 正则表达式替换文件搜索 | 更新日期: 2023-09-27 18:06:49

我创建了一小段代码，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。代码似乎可以很好地处理较小的文件，但对于100 MB或更大的文件，我给系统。OutOfMemoryException"错误。

下面是我的代码:

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突出显示了string text = File.ReadAllText(textBox1.Text);部分。我想也许用File。ReadAllLines会更好地工作，但我无法使它与regex一起工作。

有谁能帮我一下吗?我是c#的新手，可能我的代码不是最好的。

搜索并替换大文件中的正则表达式，而不会得到OutOfMemoryException

恐怕您必须自己实现替换。下面是使用状态机将<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，那么只有<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之后，将其用作下一个方法的输入，该方法将添加缺失的</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);

尝试查看内存管理文件;MSDN: http://msdn.microsoft.com/en-us/library/dd997372.aspx

它们似乎是处理非常大的文件的推荐方法。