How do you search a large text file for a string without going line by line in C#?

Question

I have a large text file that I need to search for a specific string. Is there a fast way to do this without reading line by line?

This method is extremely slow beca

Answer 1

Here is my solution that uses a stream to read in one character at a time. I created a custom class to search for the value one character at a time until the entire value is found.

I ran some tests with a 100MB file saved on a network drive and the speed was totally dependent on how fast it could read in the file. If the file was buffered in Windows a search of the entire file took less than 3 seconds. Otherwise it could take anywhere from 7 seconds to 60 seconds, depending on network speed.

The search itself took less than a second if run against a String in memory and there were no matching characters. If a lot of the leading characters found matches the search could take a lot longer.

public static int FindInFile(string fileName, string value)
{   // returns complement of number of characters in file if not found
    // else returns index where value found
    int index = 0;
    using (System.IO.StreamReader reader = new System.IO.StreamReader(fileName))
    {
        if (String.IsNullOrEmpty(value))
            return 0;
        StringSearch valueSearch = new StringSearch(value);
        int readChar;
        while ((readChar = reader.Read()) >= 0)
        {
            ++index;
            if (valueSearch.Found(readChar))
                return index - value.Length;
        }
    }
    return ~index;
}
public class StringSearch
{   // Call Found one character at a time until string found
    private readonly string value;
    private readonly List indexList = new List();
    public StringSearch(string value)
    {
        this.value = value;
    }
    public bool Found(int nextChar)
    {
        for (int index = 0; index < indexList.Count; )
        {
            int valueIndex = indexList[index];
            if (value[valueIndex] == nextChar)
            {
                ++valueIndex;
                if (valueIndex == value.Length)
                {
                    indexList[index] = indexList[indexList.Count - 1];
                    indexList.RemoveAt(indexList.Count - 1);
                    return true;
                }
                else
                {
                    indexList[index] = valueIndex;
                    ++index;
                }
            }
            else
            {   // next char does not match
                indexList[index] = indexList[indexList.Count - 1];
                indexList.RemoveAt(indexList.Count - 1);
            }
        }
        if (value[0] == nextChar)
        {
            if (value.Length == 1)
                return true;
            indexList.Add(1);
        }
        return false;
    }
    public void Reset()
    {
        indexList.Clear();
    }
}