我创建了一个小代码,用于搜索正则表达式字符串并将其替换为其他字符串,然后创建一个包含所做更改的新输出文件.代码似乎适用于较小的文件,但对于100 MB或更大的文件,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);
Run Code Online (Sandbox Code Playgroud)
Visual Studio突出了该string text = File.ReadAllText(textBox1.Text);部分.我认为也许使用File.ReadAllLines可以更好地工作,但我无法使其与正则表达式一起工作.
有人可以帮我这个吗?我是C#的新手,可能我的代码不是最好的.
我担心你必须自己实施更换.以下是使用状态机来代替示例代码<seg\b[^>*]>用<seg>.唯一的问题是,如果文件结束<seg attr="",则只会<seg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;
}
}
}
Run Code Online (Sandbox Code Playgroud)
用法:
using (StreamReader reader = new StreamReader("input.txt"))
using (StreamWriter writer = new StreamWriter("temp.txt"))
TruncateSeg(reader, writer);
Run Code Online (Sandbox Code Playgroud)
生成后temp.txt,将其用作下一个方法的输入,这会添加缺少的</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;
}
}
}
Run Code Online (Sandbox Code Playgroud)
用法:
using (StreamReader reader = new StreamReader("temp.txt"))
using (StreamWriter writer = new StreamWriter("output.txt"))
ReplaceSegTuv(reader, writer);
Run Code Online (Sandbox Code Playgroud)