我想逐行读取文本文件。我想知道我是否在。net c#范围内尽可能高效地完成它。
这是我目前正在尝试的:
var filestream = new System.IO.FileStream(textFilePath,
System.IO.FileMode.Open,
System.IO.FileAccess.Read,
System.IO.FileShare.ReadWrite);
var file = new System.IO.StreamReader(filestream, System.Text.Encoding.UTF8, true, 128);
while ((lineOfText = file.ReadLine()) != null)
{
//Do something with the lineOfText
}
当您需要有效地读取和处理一个巨大的文本文件时,ReadLines()和ReadAllLines()可能会抛出内存耗尽异常,这是我的情况。另一方面,单独阅读每一行会花费很长时间。解决方案是按块读取文件,如下所示。
类:
//can return empty lines sometimes
class LinePortionTextReader
{
private const int BUFFER_SIZE = 100000000; //100M characters
StreamReader sr = null;
string remainder = "";
public LinePortionTextReader(string filePath)
{
if (File.Exists(filePath))
{
sr = new StreamReader(filePath);
remainder = "";
}
}
~LinePortionTextReader()
{
if(null != sr) { sr.Close(); }
}
public string[] ReadBlock()
{
if(null==sr) { return new string[] { }; }
char[] buffer = new char[BUFFER_SIZE];
int charactersRead = sr.Read(buffer, 0, BUFFER_SIZE);
if (charactersRead < 1) { return new string[] { }; }
bool lastPart = (charactersRead < BUFFER_SIZE);
if (lastPart)
{
char[] buffer2 = buffer.Take<char>(charactersRead).ToArray();
buffer = buffer2;
}
string s = new string(buffer);
string[] sresult = s.Split(new string[] { "\r\n" }, StringSplitOptions.None);
sresult[0] = remainder + sresult[0];
if (!lastPart)
{
remainder = sresult[sresult.Length - 1];
sresult[sresult.Length - 1] = "";
}
return sresult;
}
public bool EOS
{
get
{
return (null == sr) ? true: sr.EndOfStream;
}
}
}
使用示例:
class Program
{
static void Main(string[] args)
{
if (args.Length < 3)
{
Console.WriteLine("multifind.exe <where to search> <what to look for, one value per line> <where to put the result>");
return;
}
if (!File.Exists(args[0]))
{
Console.WriteLine("source file not found");
return;
}
if (!File.Exists(args[1]))
{
Console.WriteLine("reference file not found");
return;
}
TextWriter tw = new StreamWriter(args[2], false);
string[] refLines = File.ReadAllLines(args[1]);
LinePortionTextReader lptr = new LinePortionTextReader(args[0]);
int blockCounter = 0;
while (!lptr.EOS)
{
string[] srcLines = lptr.ReadBlock();
for (int i = 0; i < srcLines.Length; i += 1)
{
string theLine = srcLines[i];
if (!string.IsNullOrEmpty(theLine)) //can return empty lines sometimes
{
for (int j = 0; j < refLines.Length; j += 1)
{
if (theLine.Contains(refLines[j]))
{
tw.WriteLine(theLine);
break;
}
}
}
}
blockCounter += 1;
Console.WriteLine(String.Format("100 Mb blocks processed: {0}", blockCounter));
}
tw.Close();
}
}
我相信拆分字符串和数组处理可以显著改善,
然而,这里的目标是最小化磁盘读取的数量。
在Stack Overflow的问题中有一个关于这个问题的好话题,“收益返回”比“老派”返回慢吗?
它说:
ReadAllLines loads all of the lines into memory and returns a
string[]. All well and good if the file is small. If the file is
larger than will fit in memory, you'll run out of memory.
ReadLines, on the other hand, uses yield return to return one line at
a time. With it, you can read any size file. It doesn't load the whole
file into memory.
Say you wanted to find the first line that contains the word "foo",
and then exit. Using ReadAllLines, you'd have to read the entire file
into memory, even if "foo" occurs on the first line. With ReadLines,
you only read one line. Which one would be faster?
当您需要有效地读取和处理一个巨大的文本文件时,ReadLines()和ReadAllLines()可能会抛出内存耗尽异常,这是我的情况。另一方面,单独阅读每一行会花费很长时间。解决方案是按块读取文件,如下所示。
类:
//can return empty lines sometimes
class LinePortionTextReader
{
private const int BUFFER_SIZE = 100000000; //100M characters
StreamReader sr = null;
string remainder = "";
public LinePortionTextReader(string filePath)
{
if (File.Exists(filePath))
{
sr = new StreamReader(filePath);
remainder = "";
}
}
~LinePortionTextReader()
{
if(null != sr) { sr.Close(); }
}
public string[] ReadBlock()
{
if(null==sr) { return new string[] { }; }
char[] buffer = new char[BUFFER_SIZE];
int charactersRead = sr.Read(buffer, 0, BUFFER_SIZE);
if (charactersRead < 1) { return new string[] { }; }
bool lastPart = (charactersRead < BUFFER_SIZE);
if (lastPart)
{
char[] buffer2 = buffer.Take<char>(charactersRead).ToArray();
buffer = buffer2;
}
string s = new string(buffer);
string[] sresult = s.Split(new string[] { "\r\n" }, StringSplitOptions.None);
sresult[0] = remainder + sresult[0];
if (!lastPart)
{
remainder = sresult[sresult.Length - 1];
sresult[sresult.Length - 1] = "";
}
return sresult;
}
public bool EOS
{
get
{
return (null == sr) ? true: sr.EndOfStream;
}
}
}
使用示例:
class Program
{
static void Main(string[] args)
{
if (args.Length < 3)
{
Console.WriteLine("multifind.exe <where to search> <what to look for, one value per line> <where to put the result>");
return;
}
if (!File.Exists(args[0]))
{
Console.WriteLine("source file not found");
return;
}
if (!File.Exists(args[1]))
{
Console.WriteLine("reference file not found");
return;
}
TextWriter tw = new StreamWriter(args[2], false);
string[] refLines = File.ReadAllLines(args[1]);
LinePortionTextReader lptr = new LinePortionTextReader(args[0]);
int blockCounter = 0;
while (!lptr.EOS)
{
string[] srcLines = lptr.ReadBlock();
for (int i = 0; i < srcLines.Length; i += 1)
{
string theLine = srcLines[i];
if (!string.IsNullOrEmpty(theLine)) //can return empty lines sometimes
{
for (int j = 0; j < refLines.Length; j += 1)
{
if (theLine.Contains(refLines[j]))
{
tw.WriteLine(theLine);
break;
}
}
}
}
blockCounter += 1;
Console.WriteLine(String.Format("100 Mb blocks processed: {0}", blockCounter));
}
tw.Close();
}
}
我相信拆分字符串和数组处理可以显著改善,
然而,这里的目标是最小化磁盘读取的数量。