Develop Reference

C# no duplicates in array

I have a file with allot of sentences. I need to make a dictionary with the words from that file. Until now I've separated the words and sort them using Split() and Sort() methods. My problem is to make a list without duplicate words. How can I do that?
static int n = 0;
public static string[] NoDuplicate(string[] array)
{
int i;
string[] res = (string[])array.Clone();
for (i = 0; i < array.Length-1; i++)
{
if (array[i + 1] != array[i])
res[n++] = (string)array[i];
}
return res;
}
how can I do it more neat?
I don't like that method because is
initialized using Clone() and the length is too big.

You can also use HashSet beside the .Distinct() feature of LINQ:
HashSet:
This is an optimized set collection. It helps eliminates
duplicate strings or elements in an array. It is a set that hashes its
contents.
public static string[] NoDuplicate(string[] array)
{
string[] result = new HashSet<string>(array).ToArray();
return result;
}
If you want to eliminate the duplicate with case-insensitive, you can pass an IEqualityComparer argument like this:
Using HashSet:
public static string[] NoDuplicate(string[] array)
{
string[] result = new HashSet<string>(array, StringComparer.OrdinalIgnoreCase)
.ToArray();
return result;
}
Using LINQ's Distict feature:
public static string[] NoDuplicate(string[] array)
{
string[] result = array.Distinct(StringComparer.OrdinalIgnoreCase)
.ToArray();
return result;
}

Try this:
private static string[] NoDuplicate(string[] inputArray)
{
var result = inputArray.Distinct().ToArray();
return result;
}

Instead of dictionary create a trie of words.
At each level keep a count of sameWord if it repeats. This way you can avoid using too much space and it will be faster to search any word O(log(n))
where n is number of distinct words
public class WordList {
private int sameWord = 0;
String name = "";
WordList [] child = new WordList[26];
public void add( String s, WordList c, int index )
{
sameWord++;
if(index > 0)
{
name += ""+s.charAt(index-1);
}
if(index == s.length())
{
return;
}
if(c.child[s.charAt(index)-'a'] ==null)
{
c.child[s.charAt(index)-'a'] = new WordList();
}
add(s,c.child[s.charAt(index)-'a'],index+1);
}
public static WordList findChar(char c)
{
return child[(int)(c-'a')];
}
}

You can try below solution:
private static string[] NoDuplicate(string[] inputArray)
{
List<string> stringList = new List<string>();
foreach (string s in inputArray)
{
if (!stringList.Contains(s))
{
stringList.Add(s);
}
}
return stringList.ToArray();
}

C# Console App -- Trying to access a list from else statement

This is for a data structures and algorithms class. We're just starting out with bubble sort. The instructions were to generate random, unique integers and sort them using the sorting technique of the lecture. It will be required to add different sorting techniques as well.
To generate the list of random numbers, I generated a list and then shuffled the list using the fisher-yates algorithm. So I have my unique, sorted list of whatever size I choose.
I'm getting stuck because after I generate the random list, I am having problems accessing the list to run it through BubbleSort.
Is there any way I can do this?
class Algorithms
{
static void Main(string[] args)
{
string response = "";
//Main Console Menu
while (response != "exit")
{
Console.WriteLine("Type help for list of commands");
response = Console.ReadLine();
//List<int> toSort = new List<int>();
if (response.StartsWith("exit"))
{
Environment.Exit(0);
}
else if (response.ToLower().StartsWith("help"))
{
Help(response);
}
else if (response.ToLower().StartsWith("generate"))
{
// Shuffle(Generate(response));
// have been using the line above but adding next line for
//an idea of my problem
List<int> toSort = Shuffle(Generate(response));
}
else if (response.ToLower().StartsWith("bubble"))
{
//This doesn't work and I'm trying to figure out how it can
BubbleSort(toSort);
}
}
}
//Displays help information
public static void Help(string input)
{
Console.WriteLine("\ngenerate <integer> -- Generates a data set of intended amount of integers\n"+
"algorithm <algorithm type> -- Choose which algorithm to sort data\nexit -- exit application\n" );
}
//Generates List of integers from 0 to number choosen by user
public static List<int> Generate(string size)
{
int cutString = size.Length - 9;
string sizeSubset = size.Substring(9, cutString);
List<int> numGen = new List<int>();
int dataSetSize = Convert.ToInt32(sizeSubset);
for(int i = 0; i <= dataSetSize; i++)
{
numGen.Add(i);
// Console.WriteLine(numGen[i]);
}
return numGen;
}
//Use Fisher-Yates algorithm to shuffle the list.
static Random randomize = new Random();
public static List<int> Shuffle(List<int>makeRandom)
{
List<int> shuffled = new List<int>();
int n = makeRandom.Count;
while (n > 1)
{
n--;
int k = randomize.Next(n + 1);
int value = makeRandom[k];
makeRandom[k] = makeRandom[n];
makeRandom[n] = value;
shuffled.Add(value);
Console.WriteLine(value);
}
return shuffled;
}
public static void BubbleSort(List<int>input)
{
for(int i = 0; i <= input.Count; i++)
{
for (int j = 0; j <= (input.Count - 1); j++)
{
if (input[j] > input[j + 1])
{
int temp = input[j];
input[j] = input[j + 1];
input[j + 1] = temp;
Console.WriteLine("hello");
}
}
}
}
}
}

You defined list in scope of else if (response.ToLower().StartsWith("generate")) code block, so it is not accessible outside of that block. Move declaration to Main method scope, like this:
static void Main(string[] args)
{
string response = "";
//define your list here.
List<int> toSort = new List<int>();
//Main Console Menu
while (response != "exit")
{
Console.WriteLine("Type help for list of commands");
response = Console.ReadLine();
if (response.StartsWith("exit"))
{
Environment.Exit(0);
}
else if (response.ToLower().StartsWith("help"))
{
Help(response);
}
else if (response.ToLower().StartsWith("generate"))
{
toSort = Shuffle(Generate(response));
}
else if (response.ToLower().StartsWith("bubble"))
{
List<int> sortedList = BubbleSort(toSort);
}
}
}

Split list in foreach loop to add new line each iteration

I want to print all the data line by line where each line contains "n" number of digits, n being user defined.
Something like:
void Print(List<int> list, int charactersPerLine)
{
// TODO: magic here
}
Usage
List<int> list = new List<int> { 1, 2, 3, 4, 5, 6, 7, 8 }
Print(list, 4);
Desired output:
1234
5678
So far I tried:
List.AddRange(array);
List.Add(array2);
List.Add(array3);
foreach (int i in List)
{
Console.Write("{0}", i);
}
and when the loop writes to the console everything in the List<int> is written in a line, and the output is like:
12345678
Is this possible?

Use:
foreach (int i in List)
{
Console.WriteLine("{0}", i);
}
If your input is in {1,2,3,4,5,6,7,8} format you have to use some condition when to use Console.WriteLine() or Console.Write()
const int LineCharacterLimit = 4;
int i = 0;
foreach (int i in List)
{
i++;
if (i == LineCharacterLimit)
{
Console.WriteLine("{0}", i);
i=0;
}
else
{
Console.Write("{0}", i);
}
}

You could use String Builder first. Then just put a \n after each line.
StringBuilder str = new StringBuilder();
int count = 1;
foreach (int i in List)
{
str.Append(i.ToString());
if(count%4 ==0)
str.Append("\n");
count++;
}
Console.Write(str.ToString());

More generic version:
static class LinqExtensions
{
public static IEnumerable<IEnumerable<T>> Batch<T>(this IEnumerable<T> source, int batchSize)
{
int currentBatchSize = 0;
List<T> batch = new List<T>();
foreach (var e in source)
{
batch.Add(e);
if (++currentBatchSize % batchSize == 0)
{
yield return batch;
batch.Clear();
}
}
yield return batch;
}
}
I'm sure you can find something like this in morelinq package.
Usage:
static void Print(List<int> list, int charactersPerLine)
{
foreach (var batch in list.Batch(charactersPerLine))
{
var strBatch = batch.Select(e => e.ToString()).ToArray();
Console.WriteLine(string.Join(",", strBatch));
}
}

Read double value from a file C#

I have a txt file that the format is:
0.32423 1.3453 3.23423
0.12332 3.1231 9.23432432
9.234324234 -1.23432 12.23432
...
Each line has three double value. There are more than 10000 lines in this file. I can use the ReadStream.ReadLine and use the String.Split, then convert it.
I want to know is there any faster method to do it.
Best Regards,

StreamReader.ReadLine, String.Split and Double.TryParse sounds like a good solution here.
No need for improvement.

There may be some little micro-optimisations you can perform, but the way you've suggested sounds about as simple as you'll get.
10000 lines shouldn't take very long - have you tried it and found you've actually got a performance problem? For example, here are two short programs - one creates a 10,000 line file and the other reads it:
CreateFile.cs:
using System;
using System.IO;
public class Test
{
static void Main()
{
Random rng = new Random();
using (TextWriter writer = File.CreateText("test.txt"))
{
for (int i = 0; i < 10000; i++)
{
writer.WriteLine("{0} {1} {2}", rng.NextDouble(),
rng.NextDouble(), rng.NextDouble());
}
}
}
}
ReadFile.cs:
using System;
using System.Diagnostics;
using System.IO;
using System.Linq;
public class Test
{
static void Main()
{
Stopwatch sw = Stopwatch.StartNew();
using (TextReader reader = File.OpenText("test.txt"))
{
string line;
while ((line = reader.ReadLine()) != null)
{
string[] bits = line.Split(' ');
foreach (string bit in bits)
{
double value;
if (!double.TryParse(bit, out value))
{
Console.WriteLine("Bad value");
}
}
}
}
sw.Stop();
Console.WriteLine("Total time: {0}ms",
sw.ElapsedMilliseconds);
}
}
On my netbook (which admittedly has an SSD in) it only takes 82ms to read the file. I would suggest that's probably not a problem :)

I would suggest reading all your lines at once with
string[] lines = System.IO.File.ReadAllLines(fileName);
This wold ensure that the I/O is done with the maximum efficiency. You woul have to measure (profile) but I would expect the conversions to take far less time.

your method is already good!
you can improve it by writing a readline function that returns an array of double and you reuse this function in other programs.

This solution is a little bit slower (see benchmarks at the end), but its nicer to read. It should also be more memory efficient because only the current character is buffered at the time (instead of the whole file or line).
Reading arrays is an additional feature in this reader which assumes that the size of the array always comes first as an int-value.
IParsable is another feature, that makes it easy to implement Parse methods for various types.
class StringSteamReader {
private StreamReader sr;
public StringSteamReader(StreamReader sr) {
this.sr = sr;
this.Separator = ' ';
}
private StringBuilder sb = new StringBuilder();
public string ReadWord() {
eol = false;
sb.Clear();
char c;
while (!sr.EndOfStream) {
c = (char)sr.Read();
if (c == Separator) break;
if (IsNewLine(c)) {
eol = true;
char nextch = (char)sr.Peek();
while (IsNewLine(nextch)) {
sr.Read(); // consume all newlines
nextch = (char)sr.Peek();
}
break;
}
sb.Append(c);
}
return sb.ToString();
}
private bool IsNewLine(char c) {
return c == '\r' || c == '\n';
}
public int ReadInt() {
return int.Parse(ReadWord());
}
public double ReadDouble() {
return double.Parse(ReadWord());
}
public bool EOF {
get { return sr.EndOfStream; }
}
public char Separator { get; set; }
bool eol;
public bool EOL {
get { return eol || sr.EndOfStream; }
}
public T ReadObject<T>() where T : IParsable, new() {
var obj = new T();
obj.Parse(this);
return obj;
}
public int[] ReadIntArray() {
int size = ReadInt();
var a = new int[size];
for (int i = 0; i < size; i++) {
a[i] = ReadInt();
}
return a;
}
public double[] ReadDoubleArray() {
int size = ReadInt();
var a = new double[size];
for (int i = 0; i < size; i++) {
a[i] = ReadDouble();
}
return a;
}
public T[] ReadObjectArray<T>() where T : IParsable, new() {
int size = ReadInt();
var a = new T[size];
for (int i = 0; i < size; i++) {
a[i] = ReadObject<T>();
}
return a;
}
internal void NextLine() {
eol = false;
}
}
interface IParsable {
void Parse(StringSteamReader r);
}
It can be used like this:
public void Parse(StringSteamReader r) {
double x = r.ReadDouble();
int y = r.ReadInt();
string z = r.ReadWord();
double[] arr = r.ReadDoubleArray();
MyParsableObject o = r.ReadObject<MyParsableObject>();
MyParsableObject [] oarr = r.ReadObjectArray<MyParsableObject>();
}
I did some benchmarking, comparing StringStreamReader with some other approaches, already proposed (StreamReader.ReadLine and File.ReadAllLines). Here are the methods I used for benchmarking:
private static void Test_StringStreamReader(string filename) {
var sw = new Stopwatch();
sw.Start();
using (var sr = new StreamReader(new FileStream(filename, FileMode.Open, FileAccess.Read))) {
var r = new StringSteamReader(sr);
r.Separator = ' ';
while (!r.EOF) {
var dbls = new List<double>();
while (!r.EOF) {
dbls.Add(r.ReadDouble());
}
}
}
sw.Stop();
Console.WriteLine("elapsed: {0}", sw.Elapsed);
}
private static void Test_ReadLine(string filename) {
var sw = new Stopwatch();
sw.Start();
using (var sr = new StreamReader(new FileStream(filename, FileMode.Open, FileAccess.Read))) {
var dbls = new List<double>();
while (!sr.EndOfStream) {
string line = sr.ReadLine();
string[] bits = line.Split(' ');
foreach(string bit in bits) {
dbls.Add(double.Parse(bit));
}
}
}
sw.Stop();
Console.WriteLine("elapsed: {0}", sw.Elapsed);
}
private static void Test_ReadAllLines(string filename) {
var sw = new Stopwatch();
sw.Start();
string[] lines = System.IO.File.ReadAllLines(filename);
var dbls = new List<double>();
foreach(var line in lines) {
string[] bits = line.Split(' ');
foreach (string bit in bits) {
dbls.Add(double.Parse(bit));
}
}
sw.Stop();
Console.WriteLine("Test_ReadAllLines: {0}", sw.Elapsed);
}
I used a file with 1.000.000 lines of double values (3 values each line). File is located on a SSD disk and each test was repeated multiple times in release-mode. These are the results (on average):
Test_StringStreamReader: 00:00:01.1980975
Test_ReadLine: 00:00:00.9117553
Test_ReadAllLines: 00:00:01.1362452
So, as mentioned StringStreamReader is a bit slower than the other approaches. For 10.000 lines, the performance is around (120ms / 95ms / 100ms).

Parse CSV string into Array of Integers

I have a text box field inputs 123,145,125 I to separate this field into an array of integers. And validate this field true or false if everything is parsed right.
CODE:
private bool chkID(out int[] val)
{
char[] delimiters = new char[] { ',' };
string[] strSplit = iconeID.Text.Split(delimiters);
int[] intArr = null;
foreach (string s in strSplit) //splits the new parsed characters
{
int tmp;
tmp = 0;
if (Int32.TryParse(s, out tmp))
{
if (intArr == null)
{
intArr = new int[1];
}
else
{
Array.Resize(ref intArr, intArr.Length + 1);
}
intArr[intArr.Length - 1] = tmp;
}
if (Int32.TryParse(iconeID.Text, out tmp))
{
iconeID.BorderColor = Color.Empty;
iconeID.BorderWidth = Unit.Empty;
tmp = int.Parse(iconeID.Text);
val = new int[1];
val[0] = tmp;
return true;
}
}
val = null;
ID.BorderColor = Color.Red;
ID.BorderWidth = 2;
return false;
}
//new Code:
private bool chkID(out int[] val) //bool satus for checkID function
{
string[] split = srtID.Text.Split(new char[1] {','});
List numbers = new List();
int parsed;
bool isOk = true;
foreach( string n in split){
if(Int32.TryParse( n , out parsed))
numbers.Add(parsed);
else
isOk = false;
}
if (isOk){
strID.BorderColor=Color.Empty;
strID.BorderWidth=Unit.Empty;
return true;
} else{
strID.BorderColor=Color.Red;
strID.BorderWidth=2;
return false;
}
return numbers.ToArray();
}

The given function seems to do too much. Here's one that answers the question implied by your title:
//int[] x = SplitStringIntoInts("1,2,3, 4, 5");
static int[] SplitStringIntoInts(string list)
{
string[] split = list.Split(new char[1] { ',' });
List<int> numbers = new List<int>();
int parsed;
foreach (string n in split)
{
if (int.TryParse(n, out parsed))
numbers.Add(parsed);
}
return numbers.ToArray();
}
EDIT (based on your comment on the question)
You've defined the three things this function needs to do. Now you just need to create methods for each. Below are my guesses for how you could implement them.
int[] ValidateIDs(int[] allIDs)
{
List<int> validIDs = new List<int>(allIDs);
//remove invalid IDs
return validIDs.ToArray();
}
void DownloadXmlData(int[] ids)
{
...
}
Now you just execute your new functions:
void CheckIconeID(string ids)
{
int[] allIDs = SplitStringIntoInts(ids);
int[] validIDs = ValidateIDs(allIDs);
DownloadXmlData(validIDs);
}

I really wanted to comment on #Austin Salonen's answer, but it didn't fit. It is a great answer for the question asked, but i wanted to expand the discussion a bit more generally on csv/int conversion part.
It's small point, not worth much debate but I would consider swapping the foreach loop for a plain for loop. You'll likely end up with simpler IL (read faster). See (http://www.codeproject.com/KB/cs/foreach.aspx, http://msdn.microsoft.com/en-us/library/ms973839.aspx [Use For Loops for String Iteration—version 1]).
I would create two methods -- one that is safe and uses TryParse and only adds the "good" values, another that is not as safe, but faster.
Proposed "safe" function (with overload in case you don't want to know the bad values)...
public static int[] SplitAsIntSafe (this string csvString) {
List<string> badVals;
return SplitAsIntSafe(csvString, ',', out badVals);
}
public static int[] SplitAsIntSafe (this string delimitedString, char splitChar, out List<string> badVals) {
int parsed;
string[] split = delimitedString.Split(new char[1] { ',' });
List<int> numbers = new List<int>();
badVals = new List<string>();
for (var i = 0; i < split.Length; i++) {
if (int.TryParse(split[i], out parsed)) {
numbers.Add(parsed);
} else {
badVals.Add(split[i]);
}
}
return numbers.ToArray();
}
Proposed "fast" function ....
public static int[] SplitAsIntFast (this string delimitedString, char splitChar) {
string[] strArray = delimitedString.Split(splitChar);
int[] intArray = new int[strArray.Length];
if(delimitedString == null) {
return new int[0];
}
for (var i = 0; i < strArray.Length; i++) {
intArray[i] = int.Parse(strArray[i]);
}
return intArray;
}
Anyway, hope this helps someone.

It might be worth your while to check out this FileHelper and also CSV Reader
Hope they will help you...
Take care,
Tom

There is a good free library for parsing CSV files: FileHelpers
using FileHelpers;
// First declare the record class
[Delimitedrecord(";")]
public class SampleType
{
public string Field1;
public int Field2;
}
public void ReadExample()
{
FileHelperEngine engine = new FileHelperEngine(typeof(SampleType));
SampleType[] records;
records = (SampleType[]) engine.ReadFile("source.txt");
// Now "records" array contains all the records in the
// sourcefile and can be acceded like this:
int sum = records[0].Field2 + records[1].Field2;
}

public bool ParseAndCheck(string source,
out IList<int> goodItems, out IList<string> badItems)
{
goodItems = new List<int>();
badItems = new List<string>();
foreach (string item in source.Split(','))
{
int temp;
if (int.TryParse(item, out temp))
goodItems.Add(temp);
else
badItems.Add(item);
}
return (badItems.Count < 1);
}

In .NET 2.0 you could write
string test = "123,14.5,125,151,1.55,477,777,888";
bool isParsingOk = true;
int[] results = Array.ConvertAll<string,int>(test.Split(','),
new Converter<string,int>(
delegate(string num)
{
int r;
isParsingOk &= int.TryParse(num, out r);
return r;
}));

This is simple and I think works pretty well. It only return valid numbers:
static int[] SplitStringIntoInts(string list)
{
int dummy;
return (from x in list.Split(',')
where int.TryParse(x.ToString(), out dummy)
select int.Parse(x.ToString())).ToArray();
}