How to read a text file reversely with iterator in C#

Question

I need to process a large file, around 400K lines and 200 M. But sometimes I have to process from bottom up. How can I use iterator (yield return) here? Basically I don\'t l

Answer 1

I wanted to do the similar thing. Here is my code. This class will create temporary files containing chunks of the big file. This will avoid memory bloating. User can specify whether s/he wants the file reversed. Accordingly it will return the content in reverse manner.

This class can also be used to write big data in a single file without bloating memory.

Please provide feedback.

        using System;
        using System.Collections.Generic;
        using System.Diagnostics;
        using System.IO;
        using System.Linq;
        using System.Text;
        using System.Threading.Tasks;

        namespace BigFileService
        {    
            public class BigFileDumper
            {
                /// <summary>
                /// Buffer that will store the lines until it is full.
                /// Then it will dump it to temp files.
                /// </summary>
                public int CHUNK_SIZE = 1000;
                public bool ReverseIt { get; set; }
                public long TotalLineCount { get { return totalLineCount; } }
                private long totalLineCount;
                private int BufferCount = 0;
                private StreamWriter Writer;
                /// <summary>
                /// List of files that would store the chunks.
                /// </summary>
                private List<string> LstTempFiles;
                private string ParentDirectory;
                private char[] trimchars = { '/', '\\'};


                public BigFileDumper(string FolderPathToWrite)
                {
                    this.LstTempFiles = new List<string>();
                    this.ParentDirectory = FolderPathToWrite.TrimEnd(trimchars) + "\\" + "BIG_FILE_DUMP";
                    this.totalLineCount = 0;
                    this.BufferCount = 0;
                    this.Initialize();
                }

                private void Initialize()
                {
                    // Delete existing directory.
                    if (Directory.Exists(this.ParentDirectory))
                    {
                        Directory.Delete(this.ParentDirectory, true);
                    }

                    // Create a new directory.
                    Directory.CreateDirectory(this.ParentDirectory);
                }

                public void WriteLine(string line)
                {
                    if (this.BufferCount == 0)
                    {
                        string newFile = "DumpFile_" + LstTempFiles.Count();
                        LstTempFiles.Add(newFile);
                        Writer = new StreamWriter(this.ParentDirectory + "\\" + newFile);
                    }
                    // Keep on adding in the buffer as long as size is okay.
                    if (this.BufferCount < this.CHUNK_SIZE)
                    {
                        this.totalLineCount++; // main count
                        this.BufferCount++; // Chunk count.
                        Writer.WriteLine(line);
                    }
                    else
                    {
                        // Buffer is full, time to create a new file.
                        // Close the existing file first.
                        Writer.Close();
                        // Make buffer count 0 again.
                        this.BufferCount = 0;
                        this.WriteLine(line);
                    }
                }

                public void Close()
                {
                    if (Writer != null)
                        Writer.Close();
                }

                public string GetFullFile()
                {
                    if (LstTempFiles.Count <= 0)
                    {
                        Debug.Assert(false, "There are no files created.");
                        return "";
                    }
                    string returnFilename = this.ParentDirectory + "\\" + "FullFile";
                    if (File.Exists(returnFilename) == false)
                    {
                        // Create a consolidated file from the existing small dump files.
                        // Now this is interesting. We will open the small dump files one by one.
                        // Depending on whether the user require inverted file, we will read them in descending order & reverted, 
                        // or ascending order in normal way.

                        if (this.ReverseIt)
                            this.LstTempFiles.Reverse();

                        foreach (var fileName in LstTempFiles)
                        {
                            string fullFileName = this.ParentDirectory + "\\" + fileName;
// FileLines will use small memory depending on size of CHUNK. User has control.
                            var fileLines = File.ReadAllLines(fullFileName);

                            // Time to write in the writer.
                            if (this.ReverseIt)
                                fileLines = fileLines.Reverse().ToArray();

                            // Write the lines 
                            File.AppendAllLines(returnFilename, fileLines);
                        }
                    }

                    return returnFilename;
                }
            }
        }

This service can be used as follows -

void TestBigFileDump_File(string BIG_FILE, string FOLDER_PATH_FOR_CHUNK_FILES)
        {
            // Start processing the input Big file.
            StreamReader reader = new StreamReader(BIG_FILE);
            // Create a dump file class object to handle efficient memory management.
            var bigFileDumper = new BigFileDumper(FOLDER_PATH_FOR_CHUNK_FILES);
            // Set to reverse the output file.
            bigFileDumper.ReverseIt = true;
            bigFileDumper.CHUNK_SIZE = 100; // How much at a time to keep in RAM before dumping to local file.

            while (reader.EndOfStream == false)
            {
                string line = reader.ReadLine();
                bigFileDumper.WriteLine(line);
            }
            bigFileDumper.Close();
            reader.Close();

            // Get back full reversed file.
            var reversedFilename = bigFileDumper.GetFullFile();
            Console.WriteLine("Check output file - " + reversedFilename);
        }

Answer 2

In case anyone else comes across this, I solved it with the following PowerShell script which can easily be modified into a C# script with a small amount of effort.

[System.IO.FileStream]$fileStream = [System.IO.File]::Open("C:\Name_of_very_large_file.log", [System.IO.FileMode]::Open, [System.IO.FileAccess]::Read, [System.IO.FileShare]::ReadWrite)
[System.IO.BufferedStream]$bs = New-Object System.IO.BufferedStream $fileStream;
[System.IO.StreamReader]$sr = New-Object System.IO.StreamReader $bs;


$buff = New-Object char[] 20;
$seek = $bs.Seek($fileStream.Length - 10000, [System.IO.SeekOrigin]::Begin);

while(($line = $sr.ReadLine()) -ne $null)
{
     $line;
}

This basically starts reading from the last 10,000 characters of a file, outputting each line.

Answer 3

I also add my solution. After reading some answers, nothing really fit to my case. I'm reading byte by byte from from behind until I find a LineFeed, then I'm returing the collected bytes as string, without using buffering.

Usage:

var reader = new ReverseTextReader(path);
while (!reader.EndOfStream)
{
    Console.WriteLine(reader.ReadLine());  
}

Implementation:

public class ReverseTextReader
{
    private const int LineFeedLf = 10;
    private const int LineFeedCr = 13;
    private readonly Stream _stream;
    private readonly Encoding _encoding;

    public bool EndOfStream => _stream.Position == 0;

    public ReverseTextReader(Stream stream, Encoding encoding)
    {
        _stream = stream;
        _encoding = encoding;
        _stream.Position = _stream.Length;
    }

    public string ReadLine()
    {
        if (_stream.Position == 0) return null;

        var line = new List<byte>();
        var endOfLine = false;
        while (!endOfLine)
        {
            var b = _stream.ReadByteFromBehind();

            if (b == -1 || b == LineFeedLf)
            {
                endOfLine = true;
            } 
            line.Add(Convert.ToByte(b));
        }

        line.Reverse();
        return _encoding.GetString(line.ToArray());
    }
}

public static class StreamExtensions
{
    public static int ReadByteFromBehind(this Stream stream)
    {
        if (stream.Position == 0) return -1;

        stream.Position = stream.Position - 1;
        var value = stream.ReadByte();
        stream.Position = stream.Position - 1;
        return value;
    }
}

Answer 4

I put the file into a list line by line, then used List.Reverse();

        StreamReader objReader = new StreamReader(filename);
        string sLine = "";
        ArrayList arrText = new ArrayList();

        while (sLine != null)
        {
            sLine = objReader.ReadLine();
            if (sLine != null)
                arrText.Add(sLine);
        }
        objReader.Close();


        arrText.Reverse();

        foreach (string sOutput in arrText)
        {

...

Answer 5

Reading text files backwards is really tricky unless you're using a fixed-size encoding (e.g. ASCII). When you've got variable-size encoding (such as UTF-8) you will keep having to check whether you're in the middle of a character or not when you fetch data.

There's nothing built into the framework, and I suspect you'd have to do separate hard coding for each variable-width encoding.

EDIT: This has been somewhat tested - but that's not to say it doesn't still have some subtle bugs around. It uses StreamUtil from MiscUtil, but I've included just the necessary (new) method from there at the bottom. Oh, and it needs refactoring - there's one pretty hefty method, as you'll see:

using System;
using System.Collections;
using System.Collections.Generic;
using System.IO;
using System.Text;

namespace MiscUtil.IO
{
    /// <summary>
    /// Takes an encoding (defaulting to UTF-8) and a function which produces a seekable stream
    /// (or a filename for convenience) and yields lines from the end of the stream backwards.
    /// Only single byte encodings, and UTF-8 and Unicode, are supported. The stream
    /// returned by the function must be seekable.
    /// </summary>
    public sealed class ReverseLineReader : IEnumerable<string>
    {
        /// <summary>
        /// Buffer size to use by default. Classes with internal access can specify
        /// a different buffer size - this is useful for testing.
        /// </summary>
        private const int DefaultBufferSize = 4096;

        /// <summary>
        /// Means of creating a Stream to read from.
        /// </summary>
        private readonly Func<Stream> streamSource;

        /// <summary>
        /// Encoding to use when converting bytes to text
        /// </summary>
        private readonly Encoding encoding;

        /// <summary>
        /// Size of buffer (in bytes) to read each time we read from the
        /// stream. This must be at least as big as the maximum number of
        /// bytes for a single character.
        /// </summary>
        private readonly int bufferSize;

        /// <summary>
        /// Function which, when given a position within a file and a byte, states whether
        /// or not the byte represents the start of a character.
        /// </summary>
        private Func<long,byte,bool> characterStartDetector;

        /// <summary>
        /// Creates a LineReader from a stream source. The delegate is only
        /// called when the enumerator is fetched. UTF-8 is used to decode
        /// the stream into text.
        /// </summary>
        /// <param name="streamSource">Data source</param>
        public ReverseLineReader(Func<Stream> streamSource)
            : this(streamSource, Encoding.UTF8)
        {
        }

        /// <summary>
        /// Creates a LineReader from a filename. The file is only opened
        /// (or even checked for existence) when the enumerator is fetched.
        /// UTF8 is used to decode the file into text.
        /// </summary>
        /// <param name="filename">File to read from</param>
        public ReverseLineReader(string filename)
            : this(filename, Encoding.UTF8)
        {
        }

        /// <summary>
        /// Creates a LineReader from a filename. The file is only opened
        /// (or even checked for existence) when the enumerator is fetched.
        /// </summary>
        /// <param name="filename">File to read from</param>
        /// <param name="encoding">Encoding to use to decode the file into text</param>
        public ReverseLineReader(string filename, Encoding encoding)
            : this(() => File.OpenRead(filename), encoding)
        {
        }

        /// <summary>
        /// Creates a LineReader from a stream source. The delegate is only
        /// called when the enumerator is fetched.
        /// </summary>
        /// <param name="streamSource">Data source</param>
        /// <param name="encoding">Encoding to use to decode the stream into text</param>
        public ReverseLineReader(Func<Stream> streamSource, Encoding encoding)
            : this(streamSource, encoding, DefaultBufferSize)
        {
        }

        internal ReverseLineReader(Func<Stream> streamSource, Encoding encoding, int bufferSize)
        {
            this.streamSource = streamSource;
            this.encoding = encoding;
            this.bufferSize = bufferSize;
            if (encoding.IsSingleByte)
            {
                // For a single byte encoding, every byte is the start (and end) of a character
                characterStartDetector = (pos, data) => true;
            }
            else if (encoding is UnicodeEncoding)
            {
                // For UTF-16, even-numbered positions are the start of a character.
                // TODO: This assumes no surrogate pairs. More work required
                // to handle that.
                characterStartDetector = (pos, data) => (pos & 1) == 0;
            }
            else if (encoding is UTF8Encoding)
            {
                // For UTF-8, bytes with the top bit clear or the second bit set are the start of a character
                // See http://www.cl.cam.ac.uk/~mgk25/unicode.html
                characterStartDetector = (pos, data) => (data & 0x80) == 0 || (data & 0x40) != 0;
            }
            else
            {
                throw new ArgumentException("Only single byte, UTF-8 and Unicode encodings are permitted");
            }
        }

        /// <summary>
        /// Returns the enumerator reading strings backwards. If this method discovers that
        /// the returned stream is either unreadable or unseekable, a NotSupportedException is thrown.
        /// </summary>
        public IEnumerator<string> GetEnumerator()
        {
            Stream stream = streamSource();
            if (!stream.CanSeek)
            {
                stream.Dispose();
                throw new NotSupportedException("Unable to seek within stream");
            }
            if (!stream.CanRead)
            {
                stream.Dispose();
                throw new NotSupportedException("Unable to read within stream");
            }
            return GetEnumeratorImpl(stream);
        }

        private IEnumerator<string> GetEnumeratorImpl(Stream stream)
        {
            try
            {
                long position = stream.Length;

                if (encoding is UnicodeEncoding && (position & 1) != 0)
                {
                    throw new InvalidDataException("UTF-16 encoding provided, but stream has odd length.");
                }

                // Allow up to two bytes for data from the start of the previous
                // read which didn't quite make it as full characters
                byte[] buffer = new byte[bufferSize + 2];
                char[] charBuffer = new char[encoding.GetMaxCharCount(buffer.Length)];
                int leftOverData = 0;
                String previousEnd = null;
                // TextReader doesn't return an empty string if there's line break at the end
                // of the data. Therefore we don't return an empty string if it's our *first*
                // return.
                bool firstYield = true;

                // A line-feed at the start of the previous buffer means we need to swallow
                // the carriage-return at the end of this buffer - hence this needs declaring
                // way up here!
                bool swallowCarriageReturn = false;

                while (position > 0)
                {
                    int bytesToRead = Math.Min(position > int.MaxValue ? bufferSize : (int)position, bufferSize);

                    position -= bytesToRead;
                    stream.Position = position;
                    StreamUtil.ReadExactly(stream, buffer, bytesToRead);
                    // If we haven't read a full buffer, but we had bytes left
                    // over from before, copy them to the end of the buffer
                    if (leftOverData > 0 && bytesToRead != bufferSize)
                    {
                        // Buffer.BlockCopy doesn't document its behaviour with respect
                        // to overlapping data: we *might* just have read 7 bytes instead of
                        // 8, and have two bytes to copy...
                        Array.Copy(buffer, bufferSize, buffer, bytesToRead, leftOverData);
                    }
                    // We've now *effectively* read this much data.
                    bytesToRead += leftOverData;

                    int firstCharPosition = 0;
                    while (!characterStartDetector(position + firstCharPosition, buffer[firstCharPosition]))
                    {
                        firstCharPosition++;
                        // Bad UTF-8 sequences could trigger this. For UTF-8 we should always
                        // see a valid character start in every 3 bytes, and if this is the start of the file
                        // so we've done a short read, we should have the character start
                        // somewhere in the usable buffer.
                        if (firstCharPosition == 3 || firstCharPosition == bytesToRead)
                        {
                            throw new InvalidDataException("Invalid UTF-8 data");
                        }
                    }
                    leftOverData = firstCharPosition;

                    int charsRead = encoding.GetChars(buffer, firstCharPosition, bytesToRead - firstCharPosition, charBuffer, 0);
                    int endExclusive = charsRead;

                    for (int i = charsRead - 1; i >= 0; i--)
                    {
                        char lookingAt = charBuffer[i];
                        if (swallowCarriageReturn)
                        {
                            swallowCarriageReturn = false;
                            if (lookingAt == '\r')
                            {
                                endExclusive--;
                                continue;
                            }
                        }
                        // Anything non-line-breaking, just keep looking backwards
                        if (lookingAt != '\n' && lookingAt != '\r')
                        {
                            continue;
                        }
                        // End of CRLF? Swallow the preceding CR
                        if (lookingAt == '\n')
                        {
                            swallowCarriageReturn = true;
                        }
                        int start = i + 1;
                        string bufferContents = new string(charBuffer, start, endExclusive - start);
                        endExclusive = i;
                        string stringToYield = previousEnd == null ? bufferContents : bufferContents + previousEnd;
                        if (!firstYield || stringToYield.Length != 0)
                        {
                            yield return stringToYield;
                        }
                        firstYield = false;
                        previousEnd = null;
                    }

                    previousEnd = endExclusive == 0 ? null : (new string(charBuffer, 0, endExclusive) + previousEnd);

                    // If we didn't decode the start of the array, put it at the end for next time
                    if (leftOverData != 0)
                    {
                        Buffer.BlockCopy(buffer, 0, buffer, bufferSize, leftOverData);
                    }
                }
                if (leftOverData != 0)
                {
                    // At the start of the final buffer, we had the end of another character.
                    throw new InvalidDataException("Invalid UTF-8 data at start of stream");
                }
                if (firstYield && string.IsNullOrEmpty(previousEnd))
                {
                    yield break;
                }
                yield return previousEnd ?? "";
            }
            finally
            {
                stream.Dispose();
            }
        }

        IEnumerator IEnumerable.GetEnumerator()
        {
            return GetEnumerator();
        }
    }
}


// StreamUtil.cs:
public static class StreamUtil
{
    public static void ReadExactly(Stream input, byte[] buffer, int bytesToRead)
    {
        int index = 0;
        while (index < bytesToRead)
        {
            int read = input.Read(buffer, index, bytesToRead - index);
            if (read == 0)
            {
                throw new EndOfStreamException
                    (String.Format("End of stream reached with {0} byte{1} left to read.",
                                   bytesToRead - index,
                                   bytesToRead - index == 1 ? "s" : ""));
            }
            index += read;
        }
    }
}

Feedback very welcome. This was fun :)