We Keep Coding

Array.Contains() is always false

I've been smashing my head against this problem for days and have tried a tons of different things. I've been all over the forums, tried everything I've seen with no luck. My issue could be that I don't have an override, but I can't figure out how to get that to work.
I want to check if an array of 5,000+ elements contains a user-entered word. The word gets entered character by character and combined into a string(guessString). And then I use .Contains() to see if that word is in an array.
***EDIT please see screenshots for debug logs WordArray Elements -- Debug Output -- Debug With whitespace detection -- Code that doesnt work
using System.Collections;
using System.Collections.Generic;
using UnityEngine;
using TMPro;
using UnityEngine.EventSystems;
using UnityEngine.UI;
using UnityEngine.SceneManagement;
using System.Linq;
public class WordAction : MonoBehaviour
{
TMP_Text m_textComponent;
TMP_Text m_currentSquare;
public TMP_Text[] squareArray;
List<string> dupKey = new List<string>();
public string[] WordArray;
public List<string> DictionaryList = new List<string>();
public TextAsset file;
[SerializeField]
Color correctColor, wrongColor, maybeColor;
[SerializeField]
float colorFadeSpeed, colorFadeTime; // 2f, 1f
public float waitTime;
public string levelID;
public string key;
public AudioSource revealSFX;
bool guess;
string guessString;
int guessRegulator;
int guessCount = 1;
int lessGuessCount; // Starts variable at value of first current row element
int maxGuessCount;
string[] guessStringArray = new string[1];
void Start()
{
for (int i = 0; i < 5; i++) // Duplicate key
{
dupKey.Add(key[i].ToString());
}
var content = file.text;
string[] AllWords = content.Split('\n');
WordArray = AllWords;
}
public void Magic()
{
StartCoroutine(CompareKey());
}
IEnumerator CompareKey()
{
guessRegulator++;
GuessRegulatorFunction();
lessGuessCount = (guessCount * 5) - 5; // Starts variable at value of first current row element
maxGuessCount = guessCount * 5;
guessCount++; // Moves to next row
int k = 0; // Indexer for key[]
int cW = 0; // Indexer for CombineWord()
GameObject keyGO; // Keyboard GO
for (int i = lessGuessCount; i < maxGuessCount; i++)
{
if (cW < 1)
{
CombineWord(i);
cW++;
}
bool match = WordArray.Contains(guessString); // not working
Debug.Log(match);
if (match)
{
//do stuff
}
//compare stuff
string guessStr = squareArray[i].text.ToString();
string keyStr = key[k].ToString();
bool result = guessStr == keyStr;
if (!result && !dupKey.Contains(guessStr))
{
//wrong stuff
GameObject parentGO = squareArray[i].transform.parent.gameObject; // Gets parent of SquareArray element
Image parentImage = parentGO.GetComponent<Image>(); // Gets Image component of parent game object
keyGO = GameObject.Find(squareArray[i].text); // Keyboard
Image keyParentImage = keyGO.GetComponent<Image>(); // Keyboard
wrongColor.a = 255;
keyParentImage.color = wrongColor;
parentImage.color = wrongColor;
yield return null;
}
if (result)
{
//correct stuff
dupKey[k] = "";
GameObject parentGO = squareArray[i].transform.parent.gameObject; // Gets parent of SquareArray element
Image parentImage = parentGO.GetComponent<Image>(); // Gets Image component of parent game object
keyGO = GameObject.Find(squareArray[i].text); // Keyboard
Image keyParentImage = keyGO.GetComponent<Image>(); // Keyboard
correctColor.a = 255;
keyParentImage.color = correctColor;
parentImage.color = correctColor;
yield return null;
}
if (!result && dupKey.Contains(guessStr))
{
//yellow stuff
for (int x = 0; x < 5; x++) // Duplicate key
{
if (guessStr == dupKey[x])
{
dupKey[x] = "";
}
}
GameObject parentGO = squareArray[i].transform.parent.gameObject; // Gets parent of SquareArray element
Image parentImage = parentGO.GetComponent<Image>(); // Gets Image component of parent game object
keyGO = GameObject.Find(squareArray[i].text); // Keyboard
Image keyParentImage = keyGO.GetComponent<Image>(); // Keyboard
maybeColor.a = 255;
keyParentImage.color = maybeColor;
parentImage.color = maybeColor;
yield return null;
}
revealSFX.Play();
k++;
yield return new WaitForSeconds(waitTime);
}
dupKey.Clear();
for (int i = 0; i < 5; i++) // Duplicate key
{
dupKey.Add(key[i].ToString());
}
}
void GuessRegulatorFunction()
{
guessRegulator++; // Stops multiple guess attempts
for (int i = 0; i < (guessCount * 5); i++) // Checks if row is blank when guessing
{
if (squareArray[i].text == "")
{
guess = false;
guessRegulator = 0; // Resets guess regulator
break;
}
else
{
guess = true;
}
}
if (guessRegulator > 1 || guess == false) // Stops multiple guess attempts
{
return;
}
}
public void BackSpace()
{
for (int i = guessCount * 5; i > (guessCount * 5) - 6; i--)
{
if (squareArray[i].text != "")
{
squareArray[i].text = "";
break;
}
}
}
public void InputLetter()
{
guessRegulator = 0;
for (int i = 0; i < guessCount * 5; i++)
{
if (squareArray[i].text == "")
{
squareArray[i].text = EventSystem.current.currentSelectedGameObject.name.ToString();
break;
}
}
}
void CombineWord(int i)
{
var string1 = squareArray[i].text.ToString();
var string2 = squareArray[i + 1].text.ToString();
var string3 = squareArray[i + 2].text.ToString();
var string4 = squareArray[i + 3].text.ToString();
var string5 = squareArray[i + 4].text.ToString();
guessString = string1 + string2 + string3 + string4 + string5;
//Debug.Log(guessString);
}
}

I've taken your line of code that isn't working and copied it verbatim. I've then taken the data that you say is in the WordArray and guessString variables and set those up. Then I ran this:
var WordArray = new [] { "WHICH", "THERE", "THEIR", "ABOUT" };
var guessString= "THERE";
bool match = WordArray.Contains(guessString);
Console.WriteLine(match);
match comes out True.
Your variables do not contain the data you think they do.
It's likely that the content that you call .Split('\n') on actually contains Windows end of line markers, so a combination of "\r\n". Since you only split on '\n' it's likely that the '\r' remains in your strings and hence "THERE" does not match "THERE\r".
Try this instead:
.Split(new[] { Environment.NewLine }, StringSplitOptions.None);
If your code is run on either Windows or on Linux the above line works. Just watch out for files that mix the endings.

Well, your WordArray is always empty. You put your file content into a local variable called AllWords.
Your word will never be found in an empty array.

Importing and removing duplicates from a massive amount of text files using C# and Redis

This is a bit of a doozy and it's been a while since I worked with C#, so bear with me:
I'm running a jruby script to iterate through 900 files (5 Mb - 1500 Mb in size) to figure out how many dupes STILL exist within these (already uniq'd) files. I had little luck with awk.
My latest idea was to insert them into a local MongoDB instance like so:
db.collection('hashes').update({ :_id => hash}, { $inc: { count: 1} }, { upsert: true)
... so that later I could just query it like db.collection.where({ count: { $gt: 1 } }) to get all the dupes.
This is working great except it's been over 24 hours and at the time of writing I'm at 72,532,927 Mongo entries and growing.
I think Ruby's .each_line is bottlnecking the IO hardcore:
So what I'm thinking now is compiling a C# program which fires up a thread PER EACH FILE and inserts the line (md5 hash) into a Redis list.
From there, I could have another compiled C# program simply pop the values off and ignore the save if the count is 1.
So the questions are:
Will using a compiled file reader and multithreading the file reads significantly improve performance?
Is using Redis even necessary? With a tremendous amount of AWS memory, could I not just use the threads to fill some sort of a list atomically and proceed from there?
Thanks in advance.

Updated
New solution. Old solution. The main idea is to calculate dummy hashes(just sum of all chars in string) of each line and store it in Dictionary<ulong, List<LinePosition>> _hash2LinePositions. It's possible to have multiple hashes in the same stream and it solves by List in Dictionary Value. When the hashes are the same, we read and compare the strings from the streams. LinePosition is using for storing info about line - position in stream and its length. I don't have such huge files as you, but my tests shows that it works. Here is the full code:
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
public class Solution
{
struct LinePosition
{
public long Start;
public long Length;
public LinePosition(long start, long count)
{
Start = start;
Length = count;
}
public override string ToString()
{
return string.Format("Start: {0}, Length: {1}", Start, Length);
}
}
class TextFileHasher : IDisposable
{
readonly Dictionary<ulong, List<LinePosition>> _hash2LinePositions;
readonly Stream _stream;
bool _isDisposed;
public HashSet<ulong> Hashes { get; private set; }
public string Name { get; private set; }
public TextFileHasher(string name, Stream stream)
{
Name = name;
_stream = stream;
_hash2LinePositions = new Dictionary<ulong, List<LinePosition>>();
Hashes = new HashSet<ulong>();
}
public override string ToString()
{
return Name;
}
public void CalculateFileHash()
{
int readByte = -1;
ulong dummyLineHash = 0;
// Line start position in file
long startPosition = 0;
while ((readByte = _stream.ReadByte()) != -1) {
// Read until new line
if (readByte == '\r' || readByte == '\n') {
// If there was data
if (dummyLineHash != 0) {
// Add line hash and line position to the dict
AddToDictAndHash(dummyLineHash, startPosition, _stream.Position - 1 - startPosition);
// Reset line hash
dummyLineHash = 0;
}
}
else {
// Was it new line ?
if (dummyLineHash == 0)
startPosition = _stream.Position - 1;
// Calculate dummy hash
dummyLineHash += (uint)readByte;
}
}
if (dummyLineHash != 0) {
// Add line hash and line position to the dict
AddToDictAndHash(dummyLineHash, startPosition, _stream.Position - startPosition);
// Reset line hash
dummyLineHash = 0;
}
}
public List<LinePosition> GetLinePositions(ulong hash)
{
return _hash2LinePositions[hash];
}
public List<string> GetDuplicates()
{
List<string> duplicates = new List<string>();
foreach (var key in _hash2LinePositions.Keys) {
List<LinePosition> linesPos = _hash2LinePositions[key];
if (linesPos.Count > 1) {
duplicates.AddRange(FindExactDuplicates(linesPos));
}
}
return duplicates;
}
public void Dispose()
{
if (_isDisposed)
return;
_stream.Dispose();
_isDisposed = true;
}
private void AddToDictAndHash(ulong hash, long start, long count)
{
List<LinePosition> linesPosition;
if (!_hash2LinePositions.TryGetValue(hash, out linesPosition)) {
linesPosition = new List<LinePosition>() { new LinePosition(start, count) };
_hash2LinePositions.Add(hash, linesPosition);
}
else {
linesPosition.Add(new LinePosition(start, count));
}
Hashes.Add(hash);
}
public byte[] GetLineAsByteArray(LinePosition prevPos)
{
long len = prevPos.Length;
byte[] lineBytes = new byte[len];
_stream.Seek(prevPos.Start, SeekOrigin.Begin);
_stream.Read(lineBytes, 0, (int)len);
return lineBytes;
}
private List<string> FindExactDuplicates(List<LinePosition> linesPos)
{
List<string> duplicates = new List<string>();
linesPos.Sort((x, y) => x.Length.CompareTo(y.Length));
LinePosition prevPos = linesPos[0];
for (int i = 1; i < linesPos.Count; i++) {
if (prevPos.Length == linesPos[i].Length) {
var prevLineArray = GetLineAsByteArray(prevPos);
var thisLineArray = GetLineAsByteArray(linesPos[i]);
if (prevLineArray.SequenceEqual(thisLineArray)) {
var line = System.Text.Encoding.Default.GetString(prevLineArray);
duplicates.Add(line);
}
#if false
string prevLine = System.Text.Encoding.Default.GetString(prevLineArray);
string thisLine = System.Text.Encoding.Default.GetString(thisLineArray);
Console.WriteLine("PrevLine: {0}\r\nThisLine: {1}", prevLine, thisLine);
StringBuilder sb = new StringBuilder();
sb.Append(prevPos);
sb.Append(" is '");
sb.Append(prevLine);
sb.Append("'. ");
sb.AppendLine();
sb.Append(linesPos[i]);
sb.Append(" is '");
sb.Append(thisLine);
sb.AppendLine("'. ");
sb.Append("Equals => ");
sb.Append(prevLine.CompareTo(thisLine) == 0);
Console.WriteLine(sb.ToString());
#endif
}
else {
prevPos = linesPos[i];
}
}
return duplicates;
}
}
public static void Main(String[] args)
{
List<TextFileHasher> textFileHashers = new List<TextFileHasher>();
string text1 = "abc\r\ncba\r\nabc";
TextFileHasher tfh1 = new TextFileHasher("Text1", new MemoryStream(System.Text.Encoding.Default.GetBytes(text1)));
tfh1.CalculateFileHash();
textFileHashers.Add(tfh1);
string text2 = "def\r\ncba\r\nwet";
TextFileHasher tfh2 = new TextFileHasher("Text2", new MemoryStream(System.Text.Encoding.Default.GetBytes(text2)));
tfh2.CalculateFileHash();
textFileHashers.Add(tfh2);
string text3 = "def\r\nbla\r\nwat";
TextFileHasher tfh3 = new TextFileHasher("Text3", new MemoryStream(System.Text.Encoding.Default.GetBytes(text3)));
tfh3.CalculateFileHash();
textFileHashers.Add(tfh3);
List<string> totalDuplicates = new List<string>();
Dictionary<ulong, Dictionary<TextFileHasher, List<LinePosition>>> totalHashes = new Dictionary<ulong, Dictionary<TextFileHasher, List<LinePosition>>>();
textFileHashers.ForEach(tfh => {
foreach(var dummyHash in tfh.Hashes) {
Dictionary<TextFileHasher, List<LinePosition>> tfh2LinePositions = null;
if (!totalHashes.TryGetValue(dummyHash, out tfh2LinePositions))
totalHashes[dummyHash] = new Dictionary<TextFileHasher, List<LinePosition>>() { { tfh, tfh.GetLinePositions(dummyHash) } };
else {
List<LinePosition> linePositions = null;
if (!tfh2LinePositions.TryGetValue(tfh, out linePositions))
tfh2LinePositions[tfh] = tfh.GetLinePositions(dummyHash);
else
linePositions.AddRange(tfh.GetLinePositions(dummyHash));
}
}
});
HashSet<TextFileHasher> alreadyGotDuplicates = new HashSet<TextFileHasher>();
foreach(var hash in totalHashes.Keys) {
var tfh2LinePositions = totalHashes[hash];
var tfh = tfh2LinePositions.Keys.FirstOrDefault();
// Get duplicates in the TextFileHasher itself
if (tfh != null && !alreadyGotDuplicates.Contains(tfh)) {
totalDuplicates.AddRange(tfh.GetDuplicates());
alreadyGotDuplicates.Add(tfh);
}
if (tfh2LinePositions.Count <= 1) {
continue;
}
// Algo to get duplicates in more than 1 TextFileHashers
var tfhs = tfh2LinePositions.Keys.ToArray();
for (int i = 0; i < tfhs.Length; i++) {
var tfh1Positions = tfhs[i].GetLinePositions(hash);
for (int j = i + 1; j < tfhs.Length; j++) {
var tfh2Positions = tfhs[j].GetLinePositions(hash);
for (int k = 0; k < tfh1Positions.Count; k++) {
var tfh1Pos = tfh1Positions[k];
var tfh1ByteArray = tfhs[i].GetLineAsByteArray(tfh1Pos);
for (int m = 0; m < tfh2Positions.Count; m++) {
var tfh2Pos = tfh2Positions[m];
if (tfh1Pos.Length != tfh2Pos.Length)
continue;
var tfh2ByteArray = tfhs[j].GetLineAsByteArray(tfh2Pos);
if (tfh1ByteArray.SequenceEqual(tfh2ByteArray)) {
var line = System.Text.Encoding.Default.GetString(tfh1ByteArray);
totalDuplicates.Add(line);
}
}
}
}
}
}
Console.WriteLine();
if (totalDuplicates.Count > 0) {
Console.WriteLine("Total number of duplicates: {0}", totalDuplicates.Count);
Console.WriteLine("#######################");
totalDuplicates.ForEach(x => Console.WriteLine("{0}", x));
Console.WriteLine("#######################");
}
// Free resources
foreach (var tfh in textFileHashers)
tfh.Dispose();
}
}

If you have tons of ram... You guys are overthinking it...
var fileLines = File.ReadAllLines(#"c:\file.csv").Distinct();

Parse unique string from complicated serial data C#

I need to parse this string from serial:-
!00037,00055#
00037 as one string, 00055 as another string
However this string is came out when the robot's tire is rotated and some other string may also display before and after the string that I need to parse. For example this is the some of the transmission received:-
11,00085#R-STOPR-STOP!00011,00095#!00001,00015#R-STOP!00001,00085#!00003,00075#!00006,00015#R-STOP!00009,00025#!00011,00035#!00011,00085#R-STOPR-STOP!00011,00095#!00001,00015#R-STOP!00001,00085#!00003,00075#!00006,00015#R-STOP!00009,00025#!00011,00035#R-STOP!00001,00085#!00003,00075#!00006,00015#R-STOP!00009,00025#!00011,00035#R-STOP!00037,00055#!00023,00075#R-STOPR-STOP!00022,00065#!00011,00085#R-STOPR-STOP!00011,00095#!00001,00015#R-STOP!00001,00085#!00003,00075#!00006,00015#R-STOP!00009,00025#!00011,00035#R-STOP!00037,00055#!00023,00075#R-STOPR-STOP!00022,00065#!00011,00085#R-STOPR-STOP!00011,00095#!00001,00015#
So far I'm stuck at what to do next after SerialPort.ReadExisting()
Here is some code to retrieve the serial data:-
private void serialCom_DataReceived(object sender, SerialDataReceivedEventArgs e)
{
try
{
InputData = serialCom.ReadExisting();
if (InputData != String.Empty)
{
this.BeginInvoke(new SetTextCallback(IncomingData), new object[] { InputData });
}
}
catch
{
MessageBox.Show("Error");
}
}
and display incoming serial data inside textbox
private void IncomingData(string data)
{
tb_incomingData.AppendText(data);
tb_incomingData.ScrollToCaret();
}
This code is using .NET Framework 4.0 and Windows Form.

Finally solve it using indexof and substring.
private void IncomingData(string data)
{
//Show received data in textbox
tb_incomingData.AppendText(data);
tb_incomingData.ScrollToCaret();
//Append data inside longdata (string)
longData = longData + data;
if (longData.Contains('#') && longData.Contains(',') && longData.Contains('!'))
{
try
{
indexSeru = longData.IndexOf('!'); //retrieve index number of the symbol !
indexComma = longData.IndexOf(','); //retrieve index number of the symbol ,
indexAlias = longData.IndexOf('#'); //retrieve index number of the symbol ,
rotation = longData.Substring(indexSeru + 1, 5); //first string is taken after symbol ! and 5 next char
subRotation = longData.Substring(indexComma + 1, 5); //second string is taken after symbol ! and 5 next char
//tss_distance.Text = rotation + "," + subRotation;
longData = null; //clear longdata string
}
catch
{
indexSeru = 0;
indexComma = 0;
indexAlias = 0;
}
}
}

You can determine your pattern to transform this string into a array using SPLIT function.
This code, send "!00037,00055#" returns two itens: 00037 and 00055.
static void Main(string[] args)
{
string k = "!00037,00055#";
var array = k.ToString().Split(',');
Console.WriteLine("Dirty Itens");
for (var x = 0; x <= array.Length - 1; x++)
{
var linha = "Item " + x.ToString() + " = " + array[x];
Console.WriteLine(linha);
}
Console.WriteLine("Cleaned Itens");
for (var x = 0; x <= array.Length - 1; x++)
{
var linha = "Item " + x.ToString() + " = " + CleanString(array[x]);
Console.WriteLine(linha);
}
Console.ReadLine();
}
public static string CleanString(string inputString)
{
string resultString = "";
Regex regexObj = new Regex(#"[^\d]");
resultString = regexObj.Replace(inputString, "");
return resultString;
}

C# - A faster alternative to Convert.ToSingle()

I'm working on a program which reads millions of floating point numbers from a text file. This program runs inside of a game that I'm designing, so I need it to be fast (I'm loading an obj file). So far, loading a relatively small file takes about a minute (without precompilation) because of the slow speed of Convert.ToSingle(). Is there a faster way to do this?
EDIT: Here's the code I use to parse the Obj file
http://pastebin.com/TfgEge9J
using System;
using System.IO;
using System.Collections.Generic;
using OpenTK.Math;
using System.Drawing;
using PlatformLib;
public class ObjMeshLoader
{
public static StreamReader[] LoadMeshes(string fileName)
{
StreamReader mreader = new StreamReader(PlatformLib.Platform.openFile(fileName));
MemoryStream current = null;
List<MemoryStream> mstreams = new List<MemoryStream>();
StreamWriter mwriter = null;
if (!mreader.ReadLine().Contains("#"))
{
mreader.BaseStream.Close();
throw new Exception("Invalid header");
}
while (!mreader.EndOfStream)
{
string cmd = mreader.ReadLine();
string line = cmd;
line = line.Trim(splitCharacters);
line = line.Replace(" ", " ");
string[] parameters = line.Split(splitCharacters);
if (parameters[0] == "mtllib")
{
loadMaterials(parameters[1]);
}
if (parameters[0] == "o")
{
if (mwriter != null)
{
mwriter.Flush();
current.Position = 0;
}
current = new MemoryStream();
mwriter = new StreamWriter(current);
mwriter.WriteLine(parameters[1]);
mstreams.Add(current);
}
else
{
if (mwriter != null)
{
mwriter.WriteLine(cmd);
mwriter.Flush();
}
}
}
mwriter.Flush();
current.Position = 0;
List<StreamReader> readers = new List<StreamReader>();
foreach (MemoryStream e in mstreams)
{
e.Position = 0;
StreamReader sreader = new StreamReader(e);
readers.Add(sreader);
}
return readers.ToArray();
}
public static bool Load(ObjMesh mesh, string fileName)
{
try
{
using (StreamReader streamReader = new StreamReader(Platform.openFile(fileName)))
{
Load(mesh, streamReader);
streamReader.Close();
return true;
}
}
catch { return false; }
}
public static bool Load2(ObjMesh mesh, StreamReader streamReader, ObjMesh prevmesh)
{
if (prevmesh != null)
{
//mesh.Vertices = prevmesh.Vertices;
}
try
{
//streamReader.BaseStream.Position = 0;
Load(mesh, streamReader);
streamReader.Close();
#if DEBUG
Console.WriteLine("Loaded "+mesh.Triangles.Length.ToString()+" triangles and"+mesh.Quads.Length.ToString()+" quadrilaterals parsed, with a grand total of "+mesh.Vertices.Length.ToString()+" vertices.");
#endif
return true;
}
catch (Exception er) { Console.WriteLine(er); return false; }
}
static char[] splitCharacters = new char[] { ' ' };
static List<Vector3> vertices;
static List<Vector3> normals;
static List<Vector2> texCoords;
static Dictionary<ObjMesh.ObjVertex, int> objVerticesIndexDictionary;
static List<ObjMesh.ObjVertex> objVertices;
static List<ObjMesh.ObjTriangle> objTriangles;
static List<ObjMesh.ObjQuad> objQuads;
static Dictionary<string, Bitmap> materials = new Dictionary<string, Bitmap>();
static void loadMaterials(string path)
{
StreamReader mreader = new StreamReader(Platform.openFile(path));
string current = "";
bool isfound = false;
while (!mreader.EndOfStream)
{
string line = mreader.ReadLine();
line = line.Trim(splitCharacters);
line = line.Replace(" ", " ");
string[] parameters = line.Split(splitCharacters);
if (parameters[0] == "newmtl")
{
if (materials.ContainsKey(parameters[1]))
{
isfound = true;
}
else
{
current = parameters[1];
}
}
if (parameters[0] == "map_Kd")
{
if (!isfound)
{
string filename = "";
for (int i = 1; i < parameters.Length; i++)
{
filename += parameters[i];
}
string searcher = "\\" + "\\";
filename.Replace(searcher, "\\");
Bitmap mymap = new Bitmap(filename);
materials.Add(current, mymap);
isfound = false;
}
}
}
}
static float parsefloat(string val)
{
return Convert.ToSingle(val);
}
int remaining = 0;
static string GetLine(string text, ref int pos)
{
string retval = text.Substring(pos, text.IndexOf(Environment.NewLine, pos));
pos = text.IndexOf(Environment.NewLine, pos);
return retval;
}
static void Load(ObjMesh mesh, StreamReader textReader)
{
//try {
//vertices = null;
//objVertices = null;
if (vertices == null)
{
vertices = new List<Vector3>();
}
if (normals == null)
{
normals = new List<Vector3>();
}
if (texCoords == null)
{
texCoords = new List<Vector2>();
}
if (objVerticesIndexDictionary == null)
{
objVerticesIndexDictionary = new Dictionary<ObjMesh.ObjVertex, int>();
}
if (objVertices == null)
{
objVertices = new List<ObjMesh.ObjVertex>();
}
objTriangles = new List<ObjMesh.ObjTriangle>();
objQuads = new List<ObjMesh.ObjQuad>();
mesh.vertexPositionOffset = vertices.Count;
string line;
string alltext = textReader.ReadToEnd();
int pos = 0;
while ((line = GetLine(alltext, pos)) != null)
{
if (line.Length < 2)
{
break;
}
//line = line.Trim(splitCharacters);
//line = line.Replace(" ", " ");
string[] parameters = line.Split(splitCharacters);
switch (parameters[0])
{
case "usemtl":
//Material specification
try
{
mesh.Material = materials[parameters[1]];
}
catch (KeyNotFoundException)
{
Console.WriteLine("WARNING: Texture parse failure: " + parameters[1]);
}
break;
case "p": // Point
break;
case "v": // Vertex
float x = parsefloat(parameters[1]);
float y = parsefloat(parameters[2]);
float z = parsefloat(parameters[3]);
vertices.Add(new Vector3(x, y, z));
break;
case "vt": // TexCoord
float u = parsefloat(parameters[1]);
float v = parsefloat(parameters[2]);
texCoords.Add(new Vector2(u, v));
break;
case "vn": // Normal
float nx = parsefloat(parameters[1]);
float ny = parsefloat(parameters[2]);
float nz = parsefloat(parameters[3]);
normals.Add(new Vector3(nx, ny, nz));
break;
case "f":
switch (parameters.Length)
{
case 4:
ObjMesh.ObjTriangle objTriangle = new ObjMesh.ObjTriangle();
objTriangle.Index0 = ParseFaceParameter(parameters[1]);
objTriangle.Index1 = ParseFaceParameter(parameters[2]);
objTriangle.Index2 = ParseFaceParameter(parameters[3]);
objTriangles.Add(objTriangle);
break;
case 5:
ObjMesh.ObjQuad objQuad = new ObjMesh.ObjQuad();
objQuad.Index0 = ParseFaceParameter(parameters[1]);
objQuad.Index1 = ParseFaceParameter(parameters[2]);
objQuad.Index2 = ParseFaceParameter(parameters[3]);
objQuad.Index3 = ParseFaceParameter(parameters[4]);
objQuads.Add(objQuad);
break;
}
break;
}
}
//}catch(Exception er) {
// Console.WriteLine(er);
// Console.WriteLine("Successfully recovered. Bounds/Collision checking may fail though");
//}
mesh.Vertices = objVertices.ToArray();
mesh.Triangles = objTriangles.ToArray();
mesh.Quads = objQuads.ToArray();
textReader.BaseStream.Close();
}
public static void Clear()
{
objVerticesIndexDictionary = null;
vertices = null;
normals = null;
texCoords = null;
objVertices = null;
objTriangles = null;
objQuads = null;
}
static char[] faceParamaterSplitter = new char[] { '/' };
static int ParseFaceParameter(string faceParameter)
{
Vector3 vertex = new Vector3();
Vector2 texCoord = new Vector2();
Vector3 normal = new Vector3();
string[] parameters = faceParameter.Split(faceParamaterSplitter);
int vertexIndex = Convert.ToInt32(parameters[0]);
if (vertexIndex < 0) vertexIndex = vertices.Count + vertexIndex;
else vertexIndex = vertexIndex - 1;
//Hmm. This seems to be broken.
try
{
vertex = vertices[vertexIndex];
}
catch (Exception)
{
throw new Exception("Vertex recognition failure at " + vertexIndex.ToString());
}
if (parameters.Length > 1)
{
int texCoordIndex = Convert.ToInt32(parameters[1]);
if (texCoordIndex < 0) texCoordIndex = texCoords.Count + texCoordIndex;
else texCoordIndex = texCoordIndex - 1;
try
{
texCoord = texCoords[texCoordIndex];
}
catch (Exception)
{
Console.WriteLine("ERR: Vertex " + vertexIndex + " not found. ");
throw new DllNotFoundException(vertexIndex.ToString());
}
}
if (parameters.Length > 2)
{
int normalIndex = Convert.ToInt32(parameters[2]);
if (normalIndex < 0) normalIndex = normals.Count + normalIndex;
else normalIndex = normalIndex - 1;
normal = normals[normalIndex];
}
return FindOrAddObjVertex(ref vertex, ref texCoord, ref normal);
}
static int FindOrAddObjVertex(ref Vector3 vertex, ref Vector2 texCoord, ref Vector3 normal)
{
ObjMesh.ObjVertex newObjVertex = new ObjMesh.ObjVertex();
newObjVertex.Vertex = vertex;
newObjVertex.TexCoord = texCoord;
newObjVertex.Normal = normal;
int index;
if (objVerticesIndexDictionary.TryGetValue(newObjVertex, out index))
{
return index;
}
else
{
objVertices.Add(newObjVertex);
objVerticesIndexDictionary[newObjVertex] = objVertices.Count - 1;
return objVertices.Count - 1;
}
}
}

Based on your description and the code you've posted, I'm going to bet that your problem isn't with the reading, the parsing, or the way you're adding things to your collections. The most likely problem is that your ObjMesh.Objvertex structure doesn't override GetHashCode. (I'm assuming that you're using code similar to http://www.opentk.com/files/ObjMesh.cs.
If you're not overriding GetHashCode, then your objVerticesIndexDictionary is going to perform very much like a linear list. That would account for the performance problem that you're experiencing.
I suggest that you look into providing a good GetHashCode method for your ObjMesh.Objvertex class.
See Why is ValueType.GetHashCode() implemented like it is? for information about the default GetHashCode implementation for value types and why it's not suitable for use in a hash table or dictionary.

Edit 3: The problem is NOT with the parsing.
It's with how you read the file. If you read it properly, it would be faster; however, it seems like your reading is unusually slow. My original suspicion was that it was because of excess allocations, but it seems like there might be other problems with your code too, since that doesn't explain the entire slowdown.
Nevertheless, here's a piece of code I made that completely avoids all object allocations:
static void Main(string[] args)
{
long counter = 0;
var sw = Stopwatch.StartNew();
var sb = new StringBuilder();
var text = File.ReadAllText("spacestation.obj");
for (int i = 0; i < text.Length; i++)
{
int start = i;
while (i < text.Length &&
(char.IsDigit(text[i]) || text[i] == '-' || text[i] == '.'))
{ i++; }
if (i > start)
{
sb.Append(text, start, i - start); //Copy data to the buffer
float value = Parse(sb); //Parse the data
sb.Remove(0, sb.Length); //Clear the buffer
counter++;
}
}
sw.Stop();
Console.WriteLine("{0:N0}", sw.Elapsed.TotalSeconds); //Only a few ms
}
with this parser:
const int MIN_POW_10 = -16, int MAX_POW_10 = 16,
NUM_POWS_10 = MAX_POW_10 - MIN_POW_10 + 1;
static readonly float[] pow10 = GenerateLookupTable();
static float[] GenerateLookupTable()
{
var result = new float[(-MIN_POW_10 + MAX_POW_10) * 10];
for (int i = 0; i < result.Length; i++)
result[i] = (float)((i / NUM_POWS_10) *
Math.Pow(10, i % NUM_POWS_10 + MIN_POW_10));
return result;
}
static float Parse(StringBuilder str)
{
float result = 0;
bool negate = false;
int len = str.Length;
int decimalIndex = str.Length;
for (int i = len - 1; i >= 0; i--)
if (str[i] == '.')
{ decimalIndex = i; break; }
int offset = -MIN_POW_10 + decimalIndex;
for (int i = 0; i < decimalIndex; i++)
if (i != decimalIndex && str[i] != '-')
result += pow10[(str[i] - '0') * NUM_POWS_10 + offset - i - 1];
else if (str[i] == '-')
negate = true;
for (int i = decimalIndex + 1; i < len; i++)
if (i != decimalIndex)
result += pow10[(str[i] - '0') * NUM_POWS_10 + offset - i];
if (negate)
result = -result;
return result;
}
it happens in a small fraction of a second.
Of course, this parser is poorly tested and has these current restrictions (and more):
Don't try parsing more digits (decimal and whole) than provided for in the array.
No error handling whatsoever.
Only parses decimals, not exponents! i.e. it can parse 1234.56 but not 1.23456E3.
Doesn't care about globalization/localization. Your file is only in a single format, so there's no point caring about that kind of stuff because you're probably using English to store it anyway.
It seems like you won't necessarily need this much overkill, but take a look at your code and try to figure out the bottleneck. It seems to be neither the reading nor the parsing.

Have you measured that the speed problem is really caused by Convert.ToSingle?
In the code you included, I see you create lists and dictionaries like this:
normals = new List<Vector3>();
texCoords = new List<Vector2>();
objVerticesIndexDictionary = new Dictionary<ObjMesh.ObjVertex, int>();
And then when you read the file, you add in the collection one item at a time.
One of the possible optimizations would be to save total number of normals, texCoords, indexes and everything at the start of the file, and then initialize these collections by these numbers. This will pre-allocate the buffers used by collections, so adding items to the them will be pretty fast.
So the collection creation should look like this:
// These values should be stored at the beginning of the file
int totalNormals = Convert.ToInt32(textReader.ReadLine());
int totalTexCoords = Convert.ToInt32(textReader.ReadLine());
int totalIndexes = Convert.ToInt32(textReader.ReadLine());
normals = new List<Vector3>(totalNormals);
texCoords = new List<Vector2>(totalTexCoords);
objVerticesIndexDictionary = new Dictionary<ObjMesh.ObjVertex, int>(totalIndexes);
See List<T> Constructor (Int32) and Dictionary<TKey, TValue> Constructor (Int32).

This related question is for C++, but is definitely worth a read.
For reading as fast as possible, you're probably going to want to map the file into memory and then parse using some custom floating point parser, especially if you know the numbers are always in a specific format (i.e. you're the one generating the input files in the first place).

I tested .Net string parsing once and the fastest function to parse text was the old VB Val() function. You could pull the relevant parts out of Microsoft.VisualBasic.Conversion Val(string)
Converting String to numbers
Comparison of relative test times (ms / 100000 conversions)
Double Single Integer Int(w/ decimal point)
14 13 6 16 Val(Str)
14 14 6 16 Cxx(Val(Str)) e.g., CSng(Val(str))
22 21 17 e! Convert.To(str)
23 21 16 e! XX.Parse(str) e.g. Single.Parse()
30 31 31 32 Cxx(str)
Val: fastest, part of VisualBasic dll, skips non-numeric,
ConvertTo and Parse: slower, part of core, exception on bad format (including decimal point)
Cxx: slowest (for strings), part of core, consistent times across formats

FileReader class in C#

I am looking for fast class for to work with text files and comfortable reading different object (methods like NextInt32, NextDouble, NextLine, etc). Can you advice me something?
Edit: BinaryReader is bad class in my case. Format of my data is not binary. I have file like
1 2 3
FirstToken NextToken
1.23 2,34
And I want read this file with code like:
int a = FileReader.NextInt32();
int b = FileReader.NextInt32();
int c = FileReader.NextInt32();
int d = FileReader.NextString();
int e = FileReader.NextString();
int f = FileReader.NextDouble();
int g = FileReader.NextDouble();
Edit2: I am looking for analog Scanner from Java

I believe this extension method for TextReader would do the trick:
public static class TextReaderTokenizer
{
// Adjust as needed. -1 is EOF.
private static int[] whitespace = { -1, ' ', '\r' , '\n', '\t' };
public static T ReadToken<T>(this TextReader reader)
{
StringBuilder sb = new StringBuilder();
while (Array.IndexOf(whitespace, reader.Peek()) < 0)
{
sb.Append((char)reader.Read());
}
return (T)Convert.ChangeType(sb.ToString(), typeof(T));
}
}
It can be used thus:
TextReader reader = File.OpenText("foo.txt");
int n = reader.ReadToken<int>();
string s = reader.ReadToken<string>();
[EDIT] As requested in question comments, here's an instance wrapper version of the above that is parametrized with delimiters and CultureInfo:
public class TextTokenizer
{
private TextReader reader;
private Predicate<char> isDelim;
private CultureInfo cultureInfo;
public TextTokenizer(TextReader reader, Predicate<char> isDelim, CultureInfo cultureInfo)
{
this.reader = reader;
this.isDelim = isDelim;
this.cultureInfo = cultureInfo;
}
public TextTokenizer(TextReader reader, char[] delims, CultureInfo cultureInfo)
{
this.reader = reader;
this.isDelim = c => Array.IndexOf(delims, c) >= 0;
this.cultureInfo = cultureInfo;
}
public TextReader BaseReader
{
get { return reader; }
}
public T ReadToken<T>()
{
StringBuilder sb = new StringBuilder();
while (true)
{
int c = reader.Peek();
if (c < 0 || isDelim((char)c))
{
break;
}
sb.Append((char)reader.Read());
}
return (T)Convert.ChangeType(sb.ToString(), typeof(T));
}
}
Sample usage:
TextReader reader = File.OpenText("foo.txt");
TextTokenizer tokenizer = new TextTokenizer(
reader,
new[] { ' ', '\r', '\n', '\t' },
CultureInfo.InvariantCulture);
int n = tokenizer.ReadToken<int>();
string s = tokenizer.ReadToken<string>();

I'm going to add this as a separate answer because it's quite distinct from the answer I already gave. Here's how you could start creating your own Scanner class:
class Scanner : System.IO.StringReader
{
string currentWord;
public Scanner(string source) : base(source)
{
readNextWord();
}
private void ReadNextWord()
{
System.Text.StringBuilder sb = new StringBuilder();
char nextChar;
int next;
do
{
next = this.Read();
if (next < 0)
break;
nextChar = (char)next;
if (char.IsWhiteSpace(nextChar))
break;
sb.Append(nextChar);
} while (true);
while((this.Peek() >= 0) && (char.IsWhiteSpace((char)this.Peek())))
this.Read();
if (sb.Length > 0)
currentWord = sb.ToString();
else
currentWord = null;
}
public bool HasNextInt()
{
if (currentWord == null)
return false;
int dummy;
return int.TryParse(currentWord, out dummy);
}
public int NextInt()
{
try
{
return int.Parse(currentWord);
}
finally
{
readNextWord();
}
}
public bool HasNextDouble()
{
if (currentWord == null)
return false;
double dummy;
return double.TryParse(currentWord, out dummy);
}
public double NextDouble()
{
try
{
return double.Parse(currentWord);
}
finally
{
readNextWord();
}
}
public bool HasNext()
{
return currentWord != null;
}
}

You should define exactly what your file format is meant to look like. How would you represent a string with a space in it? What determines where the line terminators go?
In general you can use TextReader and its ReadLine method, followed by double.TryParse, int.TryParse etc - but you'll need to pin the format down more first.

Have you checked out the BinaryReader class? Yes it's a text file but there is nothing stopping you from treating it as binary data and hence using BinaryReader. It has all of the methods that you are looking for with the exception of ReadLine. However it wouldn't be too difficult to implement that method on top of BinaryReader.

If you do need text files (ie UTF-8 or ASCII encoding) then the binary writer will not work.
You can use the TextReader, but unlike the BinaryReader and the TextWriter it does not support any types other than Line and char. You will have to define what separators are allowed and parse the Line base data yourself.

The System.IO.BinaryReader class is what you need.
Example of implementation of a ReadLine method:
public static class Extensions
{
public static String ReadLine(this BinaryReader binaryReader)
{
var bytes = new List<Byte>();
byte temp;
while ((temp = (byte)binaryReader.Read()) < 10)
bytes.Add(temp);
return Encoding.Default.GetString(bytes.ToArray());
}
}
Example for using this class:
using System;
using System.IO;
using System.Security.Permissions;
class Test
{
static void Main()
{
// Load application settings.
AppSettings appSettings = new AppSettings();
Console.WriteLine("App settings:\nAspect Ratio: {0}, " +
"Lookup directory: {1},\nAuto save time: {2} minutes, " +
"Show status bar: {3}\n",
new Object[4]{appSettings.AspectRatio.ToString(),
appSettings.LookupDir, appSettings.AutoSaveTime.ToString(),
appSettings.ShowStatusBar.ToString()});
// Change the settings.
appSettings.AspectRatio = 1.250F;
appSettings.LookupDir = #"C:\Temp";
appSettings.AutoSaveTime = 10;
appSettings.ShowStatusBar = true;
// Save the new settings.
appSettings.Close();
}
}
// Store and retrieve application settings.
class AppSettings
{
const string fileName = "AppSettings####.dat";
float aspectRatio;
string lookupDir;
int autoSaveTime;
bool showStatusBar;
public float AspectRatio
{
get{ return aspectRatio; }
set{ aspectRatio = value; }
}
public string LookupDir
{
get{ return lookupDir; }
set{ lookupDir = value; }
}
public int AutoSaveTime
{
get{ return autoSaveTime; }
set{ autoSaveTime = value; }
}
public bool ShowStatusBar
{
get{ return showStatusBar; }
set{ showStatusBar = value; }
}
public AppSettings()
{
// Create default application settings.
aspectRatio = 1.3333F;
lookupDir = #"C:\AppDirectory";
autoSaveTime = 30;
showStatusBar = false;
if(File.Exists(fileName))
{
BinaryReader binReader =
new BinaryReader(File.Open(fileName, FileMode.Open));
try
{
// If the file is not empty,
// read the application settings.
// First read 4 bytes into a buffer to
// determine if the file is empty.
byte[] testArray = new byte[3];
int count = binReader.Read(testArray, 0, 3);
if (count != 0)
{
// Reset the position in the stream to zero.
binReader.BaseStream.Seek(0, SeekOrigin.Begin);
aspectRatio = binReader.ReadSingle();
lookupDir = binReader.ReadString();
autoSaveTime = binReader.ReadInt32();
showStatusBar = binReader.ReadBoolean();
}
}
// If the end of the stream is reached before reading
// the four data values, ignore the error and use the
// default settings for the remaining values.
catch(EndOfStreamException e)
{
Console.WriteLine("{0} caught and ignored. " +
"Using default values.", e.GetType().Name);
}
finally
{
binReader.Close();
}
}
}
// Create a file and store the application settings.
public void Close()
{
using(BinaryWriter binWriter =
new BinaryWriter(File.Open(fileName, FileMode.Create)))
{
binWriter.Write(aspectRatio);
binWriter.Write(lookupDir);
binWriter.Write(autoSaveTime);
binWriter.Write(showStatusBar);
}
}
}

You can probably use the System.IO.File Class to read the file and System.Convert to parse the strings you read from the file.
string line = String.Empty;
while( (line = file.ReadLine()).IsNullOrEmpty() == false )
{
TYPE value = Convert.ToTYPE( line );
}
Where TYPE is whatever type you're dealing with at that particular line / file.
If there are multiple values on one line you could do a split and read the individual values e.g.
string[] parts = line.Split(' ');
if( parts.Length > 1 )
{
foreach( string item in parts )
{
TYPE value = Convert.ToTYPE( item );
}
}
else
{
// Use the code from before
}