i have done a RPN class to calculate strings which end-user input like
"1.0+3/2-tan(45)/(1+1)+sin(30)*abs(-1)+Abs(-10)"
Then, I want to parsing conditional statements and multi-parameters function such as "if(1>2,3/3,2*1)","max(1,2,3,4)"
So, my questions how to use IF-ELSE in the RPN?
Here's my code: enter link description here
For if(1>2,3/3,2*1) you would first evaluate the three argument from right to left and push their resuls on the stack so that it looked like this:
top-of-stack->false
1
2
Then if would be implemented in the RPN engine something like (pseudo-code):
void DoIf()
{
if (pop()) // pop result of "if" evaluation
{
var result = pop(); // pop "true" result from stack
pop(); // discard "false" result
push(result); // push back "true" result
}
else
{
pop(); // discard "true" result, leaving "false" result on stack
}
}
As for multi-parameter functions, there should be no special handling needed. Just evaluate and push all arguments (right to left, typically). The implementation of the function should pop off the required number of arguments and then push its result (if any).
i try to parse multi-parameters function such as if\Max before RPN.Parse()
public class MultiParameterFunctionParser
{
public readonly List<string> Funcs = new List<string> {"IF", "MAX"};
public string Parse(string exp)
{
while (IsFunction(exp,out var index,out var funcName))//
{
var parameters = GetParameters(exp, index, funcName, out var before, out var after);
var list = GetParameterList(parameters);
var value = Evaluate(list, funcName);
exp= $"{before}({value}){after}";
}
return exp;
}
/// <summary>
/// Is Exp Contains a function?
/// </summary>
/// <param name="exp"></param>
/// <param name="index"></param>
/// <param name="funcName"></param>
/// <returns></returns>
private bool IsFunction(string exp, out int index, out string funcName)
{
index = -1;
funcName = "";
foreach (var func in Funcs)
{
var idx = exp.IndexOf($"{func}(", StringComparison.CurrentCultureIgnoreCase);
if (idx == -1 || idx + 3 >= exp.Length - 1)
continue;
index = idx;
funcName = func;
break;
}
return index != -1 && index + 3 < exp.Length - 1;
}
/// <summary>
/// Get Parameters' string
/// </summary>
/// <param name="exp">8+if(12,sin(90),0)+1.2</param>
/// <param name="index">2 if's start index</param>
/// <param name="before">8+</param>
/// <param name="after">+1.2</param>
/// <returns>12,sin(90),0</returns>
private static string GetParameters(string exp,int index, string funcName, out string before, out string after)
{
before = exp.Substring(0, index);
index += funcName.Length + 1;
var leftCount = 1; // '(' count
var rightCount = 0;// ')' count
var results = "";
while (index < exp.Length && leftCount != rightCount)
{
var c = exp[index];
if (c.Equals('('))
leftCount++;
else if (c.Equals(')'))
rightCount++;
if (leftCount > rightCount)
results += c;
else
break;
index++;
}
after = exp.Substring(index + 1, exp.Length - index - 1);
return results;
}
/// <summary>
/// Parse Parameter string to list.
/// </summary>
/// <param name="exp">MAX(1,-1),1,0</param>
/// <returns>{"MAX(1,-1)","1","0"}</returns>
private static List<string> GetParameterList(string exp)
{
var count = exp.Length;
for (var i = count - 1; i > -1 && exp.Length > 0; i--)
{
var c = exp[i];
if (c != ',')
continue;
var after = exp.Substring(i + 1);
var before = exp.Substring(0,i);
if (after.Count(a => a == '(').Equals(after.Count(a => a == ')')))
{
exp = before + '#' + after;
}
}
var results = exp.Split('#').ToList();
return results;
}
private static double Evaluate(List<string> parameters, string funcName)
{
if (funcName.Equals("MAX", StringComparison.CurrentCultureIgnoreCase))
return EvaluateMax(parameters);
if (funcName.Equals("IF", StringComparison.CurrentCultureIgnoreCase))
return EvaluateIF(parameters);
return 0;
}
private static double EvaluateIF(List<string> parameters)
{
if (parameters == null || parameters.Count != 3)
throw new Exception("EvaluateIF parameters.Count()!=3");
var results = new List<double>();
foreach (var parameter in parameters)
{
var rpn = new RPN();
rpn.Parse(parameter);
var obj = rpn.Evaluate();
if (obj == null)
{
throw new Exception("EvaluateIF Not Number!");
}
if (obj.ToString().Equals("true", StringComparison.CurrentCultureIgnoreCase))
{
results.Add(1);
}
else if (obj.ToString().Equals("false", StringComparison.CurrentCultureIgnoreCase))
{
results.Add(-1);
}
else
{
if (double.TryParse(obj.ToString(), out var d))
results.Add(d);
else
throw new Exception("EvaluateIF Not Number!");
}
}
return results[0] >= 0 ? results[1] : results[2];
}
private static double EvaluateMax(IEnumerable<string> parameters)
{
var results = new List<double>();
foreach (var parameter in parameters)
{
var rpn = new RPN();
rpn.Parse(parameter);
var obj = rpn.Evaluate();
if (double.TryParse(obj.ToString(), out var d))
results.Add(d);
}
return results.Count > 0 ? results.Max() : 0;
}
}
Related
I have this in my text file:
000000000:Carrots:$1.99:214:03/11/2015:03/11/2016:$0.99
000000001:Bananas:$1.99:872:03/11/2015:03/11/2016:$0.99
000000002:Chocolate:$2.99:083:03/11/2015:03/11/2016:$1.99
000000003:Spaghetti:$3.99:376:03/11/2015:03/11/2016:$2.99
000000004:Tomato Sauce:$1.99:437:03/11/2015:03/11/2016:$0.99
000000005:Lettuce:$0.99:279:03/11/2015:03/11/2016:$0.99
000000006:Orange Juice:$2.99:398:03/11/2015:03/11/2016:$1.99
000000007:Potatoes:$2.99:792:03/11/2015:03/11/2016:$1.99
000000008:Celery:$0.99:973:03/11/2015:03/11/2016:$0.99
000000009:Onions:$1.99:763:03/11/2015:03/11/2016:$0.99
000000010:Chicken:$8.99:345:03/11/2015:03/11/2016:$7.99
000000010:Chicken:$8.99:345:03/11/2015:03/11/2016:$7.99
I need to get the value of each of the "quantity" values from the position in bold.
EDIT:
I want to also compare the values that I got and give an error if the quantity is low.
Solution with minimal memory consumption in case of large input data.
In additional: there are not processing of incorrect data in quantity column. To do this just replace int.Parse block;
This is several methods to process file data using LINQ expressions
internal static class MyExtensions
{
/// <exception cref="OutOfMemoryException">There is insufficient memory to allocate a buffer for the returned string. </exception>
/// <exception cref="IOException">An I/O error occurs. </exception>
/// <exception cref="ArgumentException"><paramref name="stream" /> does not support reading. </exception>
/// <exception cref="ArgumentNullException"><paramref name="stream" /> is null. </exception>
public static IEnumerable<string> EnumerateLines(this Stream stream)
{
using (var reader = new StreamReader(stream))
{
do
{
var line = reader.ReadLine();
if (line == null) break;
yield return line;
} while (true);
}
}
/// <exception cref="ArgumentNullException"><paramref name="line"/> is <see langword="null" />.</exception>
public static IEnumerable<string> ChunkLine(this string line)
{
if (line == null) throw new ArgumentNullException("line");
return line.Split(':');
}
/// <exception cref="ArgumentNullException"><paramref name="chuckedData"/> is <see langword="null" />.</exception>
/// <exception cref="ArgumentException">Index should be not negative value</exception>
public static string GetColumnData(this IEnumerable<string> chuckedData, int columnIndex)
{
if (chuckedData == null) throw new ArgumentNullException("chuckedData");
if (columnIndex < 0) throw new ArgumentException("Column index should be >= 0", "columnIndex");
return chuckedData.Skip(columnIndex).FirstOrDefault();
}
}
This is example of usage:
private void button1_Click(object sender, EventArgs e)
{
var values = EnumerateQuantityValues("largefile.txt");
// do whatever you need
}
private IEnumerable<int> EnumerateQuantityValues(string fileName)
{
const int columnIndex = 3;
using (var stream = File.OpenRead(fileName))
{
IEnumerable<int> enumerable = stream
.EnumerateLines()
.Select(x => x.ChunkLine().GetColumnData(columnIndex))
.Select(int.Parse);
foreach (var value in enumerable)
{
yield return value;
}
}
}
just consider if you are managed to get all these lines in string array or list.
you can apply the below code to get the collection of quantity as IEnumerable<string>.
var quantity = arr.Select(c =>
{
var temp = c.Split('$');
if (temp.Length > 1)
{
temp = temp[1].Split(':');
if (temp.Length > 1)
{
return temp[1];
}
}
return null;
}).Where(c => c != null);
UPDATE
Check the Fiddle.
https://dotnetfiddle.net/HqKdeI
you simply need to split the string
string data = #"000000000:Carrots:$1.99:214:03/11/2015:03/11/2016:$0.99
000000001:Bananas:$1.99:872:03/11/2015:03/11/2016:$0.99
000000002:Chocolate:$2.99:083:03/11/2015:03/11/2016:$1.99
000000003:Spaghetti:$3.99:376:03/11/2015:03/11/2016:$2.99
000000004:Tomato Sauce:$1.99:437:03/11/2015:03/11/2016:$0.99
000000005:Lettuce:$0.99:279:03/11/2015:03/11/2016:$0.99
000000006:Orange Juice:$2.99:398:03/11/2015:03/11/2016:$1.99
000000007:Potatoes:$2.99:792:03/11/2015:03/11/2016:$1.99
000000008:Celery:$0.99:973:03/11/2015:03/11/2016:$0.99
000000009:Onions:$1.99:763:03/11/2015:03/11/2016:$0.99
000000010:Chicken:$8.99:345:03/11/2015:03/11/2016:$7.99";
string[] rows = data.split(Environment.Newline.ToCharArray());
foreach(var row in rows)
{
string[] cols = row.Split(':');
var quantity = cols[3];
}
You can use String.Split to do this.
// Read all lines into an array
string[] lines = File.ReadAllLines(#"C:\path\to\your\file.txt");
// Loop through each one
foreach (string line in lines)
{
// Split into an array based on the : symbol
string[] split = line.Split(':');
// Get the column based on index
Console.WriteLine(split[3]);
}
Check out the example code below. The string you care about is named theValueYouWantInTheString.
char[] delimiterChar = { ':' };
string input = #"000000010:Chicken:$8.99:345:03/11/2015:03/11/2016:$7.99";
string[] values = input.Split(delimiterChar);
string theValueYouWantInTheString = values[3];
If you have a problem, use regular expression. Now you have two problems.
Here is a program that uses your input as a txt file. The function GetQuantity returns a list with int that contains the quantity. With this approach you can define more groups to extract information from each line.
namespace RegExptester
{
class Program
{
private static List<int> GetQuantity(string txtFile)
{
string tempLineValue;
Regex regex = new Regex(#"[0-9]*:[a-zA-Z]*:\$[0-9]*\.[0-9]*:([0-9]*).*", RegexOptions.Compiled);
List<int> retValue = new List<int>();
using (StreamReader inputReader = new StreamReader(txtFile))
{
while (null != (tempLineValue = inputReader.ReadLine()))
{
Match match = regex.Match(tempLineValue);
if (match.Success)
{
if(match.Groups.Count == 2)
{
int numberValue;
if (int.TryParse(match.Groups[1].Value, out numberValue))
retValue.Add(numberValue);
}
}
}
}
return retValue;
}
static void Main(string[] args)
{
var tmp = GetQuantity("c:\\tmp\\junk.txt");
}
}
}
Apparently from each line you want the part between the 3th and the 4th colon. Linq can do that for you:
using (var textReader = new StreamReader(fileName))
{
// read all text and divide into lines:
var allText = textReader.ReadToEnd();
var allLines = textReader.Split(new char[] {'\r','\n'}, StringSplitIoptions.RemoveEmptyEntries);
// split each line based on ':', and take the fourth element
var myValues = allLines.Select(line => line.Split(new char[] {':'})
.Skip(3)
.FirstOrDefault();
}
If you want less readability, of course you can concatenate these statements into one line.
I'm trying to read the variable of the PLC.
In the Automation Platform, I have a plugin who start a my test (that I've write in C#).
When I execute the plugin for the first time, it always give me the same error. But if a execute it again it's good.
I use a List<IOnlineVarRef6> vars to read my variable. My error is that my vars's State is NotMonitoredYet.
Exemple :
private bool CompareValues(TestCase test, List<IOnlineVarRef6> vars)
{
// Stop here the first time
if (vars.First().State == VarRefState.NotMonitoredYet)
return false;
// Execute well the other times
List<Variable> initialVars = test.initialVariables;
for (int i = 0; i < vars.Count(); i++)
{
object initialValue = initialVars.Single(v => v.Name == vars[i].Expression.ToString()).Value;
if (!vars[i].Value.Equals(initialValue))
return false;
}
return true;
}
I think the problem is in the method who get my variable :
/// <summary>
/// Create a variable watch for each of the specified variable in the list
/// </summary>
/// <example>
/// Variable should include object hierarchy up to Device
/// GPX.Diesel_Control.CTRL.PB_CRANK1
/// </example>
public List<IOnlineVarRef6> CreateVariableWatch(List<string> vars)
{
IVarRef2 varref;
IOnlineVarRef6 iov;
IOnlineApplication17 onlineapp = (IOnlineApplication17)onlineMgr.GetApplication(SystemInstances.Engine.Projects.PrimaryProject.ActiveApplication);
List<IOnlineVarRef6> lstVarRef = new List<IOnlineVarRef6>();
foreach (string var in vars)
{
varref = (IVarRef2)SystemInstances.LanguageModelMgr.GetVarReference(var);
iov = (IOnlineVarRef6)onlineMgr.CreateWatch(varref);
lstVarRef.Add(iov);
}
return lstVarRef;
}
I have a method that wait before calling the CompareValues() and it retries 3 times and it wait before trying again :
public void SetIsTestPassed(TestCase test)
{
Thread.Sleep(test.delayedStart);
int retries = test.retries;
do
{
List<IOnlineVarRef6> vars = SetCurrentVars(test);
test.IsTestPassed = CompareValues(test, vars);
if (test.retryDelay > 0 && !test.IsTestPassed)
Thread.Sleep(test.retryDelay);
retries--;
} while (retries != 0 && !test.IsTestPassed);
}
private List<IOnlineVarRef6> SetCurrentVars(TestCase test)
{
OnlineManagerHelper OnlineMgr = new OnlineManagerHelper(true);
return OnlineMgr.CreateVariableWatch(
test.initialVariables
.Select(v => Settings.Default.InstancePath + v.Name)
.ToList());
}
I need to covert expressions like array_name[i, i*k, i-k] into Reverse Polish Notation.
What I'm basically doing is trying to translate the expression like this:
if(array_name[i, j+k]>=a+b) array_name[i, j*k] = a+2; else x = a / b;
into the RPN using regular expressions.
I already have quite an ugly huge regular expression, which matches: if, else, + - * / = == ( ) <= >= < > != and all the words that match this pattern: [a-zA-z][a-zA-z0-9_]*. And also I have the code that translates infix arithmetical expressions into RPN. Here it is:
/// <summary>
/// Returns the collection of all the lexemes of the expression
/// using Regex.
/// The Regex created works fine with 'if else' constructions and is good
///with
///any variable name possible in C#, with arithmetical expressions,
///like +, -, /, and all the boolean operators.
/// </summary>
/// <param name="input">String expression in infix notation.</param>
/// <returns>Collection of all the lexemes of the expression</returns>
private static MatchCollection GetMatchCollection(string input)
{
var rx =
new Regex(
#"/\bif\b|\belse\b|\(|\)|\+|\-|\*|\<=|\>=|\\|\>|\<|(?<![!=])[!=]=(?!=)|([a-zA-Z][a-zA-z0-9_]*)|(\d+\.?\d*)|(?<!=)=(?!=)|\/|/^/g");
return rx.Matches(input);
}
/// <summary>
/// Translates the infix expression into RPN
/// </summary>
/// <param name="input">String expression in infix notation.</param>
/// <returns>RPN expression</returns>
public static string Translate(string input)
{
var mc = GetMatchCollection(input);
var id = new Regex(#"[a-zA-z][a-zA-z0-9_]*"); // regex for identifiers
var num = new Regex(#"\d+\.?\d*"); // regex for decimals
var skobki = new Regex(#"\(|\)"); // regex for braces
object[] operators =
{
"(", ")", "else", "*", "/", "+", "-", "=", "<", ">", "<=", ">=", "==", "!=", "&&",
"||", "if"
}; // operators by priority
var opers = new Regex(#"\(|\)|\+|\-|\*|\/|<=?|>=?|!=|=|&&|\|\|\bif\b|\belse\b"); // regex for operators
var stOper = new Stack();
var expr = new ArrayList();
foreach (Match m in mc)
{
var m1 = id.Match(m.Value);
if (m1.Success) { expr.Add(m1.Value); continue; }
m1 = num.Match(m.Value);
if (m1.Success) { expr.Add(m1.Value); continue; }
m1 = skobki.Match(m.Value);
if (m1.Success)
{
if (m1.Value == "(") { stOper.Push(m1.Value); continue; }
var op = stOper.Pop().ToString();
while (op != "(")
{
expr.Add(op);
op = stOper.Pop().ToString();
}
continue;
}
m1 = opers.Match(m.Value);
if (m1.Success)
{
try
{
while (Array.IndexOf(operators, m1.Value) > Array.IndexOf(operators, stOper.Peek()))
{
if (stOper.Peek().ToString() == "(") break;
expr.Add(stOper.Pop().ToString());
}
}
catch (Exception)
{
// stack is empty
}
stOper.Push(m1.Value);
}
}
while (stOper.Count != 0)
{
expr.Add(stOper.Pop().ToString());
}
// Make the RPN expression string
// from the ArrayList expr.
var res = new StringBuilder();
foreach (var s in expr)
res.Append(s).Append(' ');
return res.ToString();
}
How can I modify the code to make the method public static string Translate(string input) translate simple expressions like array_name[i,k*i-1] into the RPN expression?
Note, that the public static string Translate(string input) method works fine only with simple arithmetical expressions, but not with the one I provided above (the if-else statement).
Regular expressions are not the way to go. Parse it, probably leveraging some parser generator, into an abstract syntax tree and the output it into RPN, which is trivial.
Solved the issue. Here is the algorithm.
class InfixToPostfixConverter
{
private readonly Stack<string> _stack;
private readonly string[] _input;
private readonly Dictionary<string, int> _priorities;
private readonly List<string> _poliz;
public InfixToPostfixConverter(string input)
{
_input = input.Split(new[] {' '}, StringSplitOptions.RemoveEmptyEntries);
_stack = new Stack<string>();
_poliz = new List<string>();
_priorities = new Dictionary<string, int>
{
{"(", 0},
{")", 0},
{"[", 0},
{"if", 0},
{"flag", 0},
{">", 1},
{"<", 1},
{"<=", 1},
{">=", 1},
{"=", 1},
{"==", 1},
{"!=", 1},
{"+", 2},
{"-", 2},
{"*", 3},
{"/", 3},
{"^", 4},
{"#", 5}
};
}
public string Translate()
{
return ConvertInfixToPostfix();
}
private string ConvertInfixToPostfix()
{
int countAts = 0;
bool reachedElse = false;
foreach (var lexeme in _input)
{
if (lexeme.Equals("if"))
{
_stack.Push(lexeme);
_stack.Push("flag");
}
else if (lexeme.Equals("else"))
{
_poliz.Add("null");
_poliz.Add("1B");
reachedElse = true;
_poliz[_poliz.FindIndex(x => x.Equals("null"))] = _poliz.Count.ToString();
}
else if (Regex.IsMatch(lexeme, #"[a-zA-Z][a-zA-z0-9_]*|\d+\.?\d*")
&& !lexeme.Equals("if") && !lexeme.Equals("else"))
{
_poliz.Add(lexeme);
}
else if (lexeme.Equals(";"))
{
if (!reachedElse)
{
while (_stack.Count != 0 && !_stack.Peek().Equals("if"))
{
_poliz.Add(_stack.Pop());
}
if (_stack.Count != 0)
{
_stack.Pop();
}
}
else
{
while (_stack.Count != 0)
{
_poliz.Add(_stack.Pop());
}
_poliz[_poliz.FindIndex(x => x.Equals("null"))] = _poliz.Count.ToString();
}
}
else if (lexeme.Equals(","))
{
countAts++;
while (_stack.Count != 0 && !_stack.Peek().Equals("["))
{
_poliz.Add(_stack.Pop());
}
}
else if (lexeme.Equals(")") || lexeme.Equals("]"))
{
var brace = lexeme.Equals(")") ? "(" : "[";
while (_stack.Count != 0 && !_stack.Peek().Equals(brace))
{
_poliz.Add(_stack.Pop());
}
_stack.Pop();
if (_stack.Peek().Equals("flag"))
{
_stack.Pop();
_poliz.Add((_poliz.Count + 3).ToString());
_poliz.Add("null");
_poliz.Add("3Y");
}
if (lexeme.Equals("]"))
{
countAts++;
_poliz.Add(countAts.ToString());
_poliz.Add(_stack.Pop());
countAts = 0;
}
}
else
{
if (_stack.Count != 0 && !lexeme.Equals("(") && !lexeme.Equals("["))
{
for (;
_stack.Count != 0 &&
_priorities[lexeme] <= _priorities[_stack.Peek()];
_poliz.Add(_stack.Pop())) {}
}
if (lexeme.Equals("["))
{
countAts++;
_stack.Push("#");
}
_stack.Push(lexeme);
}
}
return _poliz.Aggregate(string.Empty, (current, x) => current + (x + " "));
}
}
I have a C# list of objects with the following simplified data:
ID, Price
2, 80.0
8, 44.25
14, 43.5
30, 79.98
54, 44.24
74, 80.01
I am trying to GroupBy the lowest number while taking into account a tolerance factor.
for example, in a case of tolerance = 0.02, my expected result should be:
44.24 -> 8, 54
43.5 -> 14
79.98 -> 2, 30, 74
How can i do this while achieving a good performance for large datasets?
Is LINQ the way to go in this case?
It seemed to me that if you have a large data set you'll want to avoid the straightforward solution of sorting the values and then collecting them as you iterate through the sorted list, since sorting a large collection can be expensive. The most efficient solution I could think of which doesn't do any explicit sorting was to build a tree where each node contains the items where the key falls within a "contiguous" range (where all the keys are within tolerance of each other) - the range for each node expands every time an item is added which falls outside the range by less than tolerance. I implemented a solution - which turned out to be more complicated and interesting than I expected - and based on my rough benchmarking it looks like doing it this way takes about half as much time as the straightforward solution.
Here's my implementation as an extension method (so you can chain it, although like the normal Group method it'll iterate the source completely as soon as the result IEnumerable is iterated).
public static IEnumerable<IGrouping<double, TValue>> GroupWithTolerance<TValue>(
this IEnumerable<TValue> source,
double tolerance,
Func<TValue, double> keySelector)
{
if(source == null)
throw new ArgumentNullException("source");
return GroupWithToleranceHelper<TValue>.Group(source, tolerance, keySelector);
}
private static class GroupWithToleranceHelper<TValue>
{
public static IEnumerable<IGrouping<double, TValue>> Group(
IEnumerable<TValue> source,
double tolerance,
Func<TValue, double> keySelector)
{
Node root = null, current = null;
foreach (var item in source)
{
var key = keySelector(item);
if(root == null) root = new Node(key);
current = root;
while(true){
if(key < current.Min - tolerance) { current = (current.Left ?? (current.Left = new Node(key))); }
else if(key > current.Max + tolerance) {current = (current.Right ?? (current.Right = new Node(key)));}
else
{
current.Values.Add(item);
if(current.Max < key){
current.Max = key;
current.Redistribute(tolerance);
}
if(current.Min > key) {
current.Min = key;
current.Redistribute(tolerance);
}
break;
}
}
}
if (root != null)
{
foreach (var entry in InOrder(root))
{
yield return entry;
}
}
else
{
//Return an empty collection
yield break;
}
}
private static IEnumerable<IGrouping<double, TValue>> InOrder(Node node)
{
if(node.Left != null)
foreach (var element in InOrder(node.Left))
yield return element;
yield return node;
if(node.Right != null)
foreach (var element in InOrder(node.Right))
yield return element;
}
private class Node : IGrouping<double, TValue>
{
public double Min;
public double Max;
public readonly List<TValue> Values = new List<TValue>();
public Node Left;
public Node Right;
public Node(double key) {
Min = key;
Max = key;
}
public double Key { get { return Min; } }
IEnumerator IEnumerable.GetEnumerator() { return GetEnumerator(); }
public IEnumerator<TValue> GetEnumerator() { return Values.GetEnumerator(); }
public IEnumerable<TValue> GetLeftValues(){
return Left == null ? Values : Values.Concat(Left.GetLeftValues());
}
public IEnumerable<TValue> GetRightValues(){
return Right == null ? Values : Values.Concat(Right.GetRightValues());
}
public void Redistribute(double tolerance)
{
if(this.Left != null) {
this.Left.Redistribute(tolerance);
if(this.Left.Max + tolerance > this.Min){
this.Values.AddRange(this.Left.GetRightValues());
this.Min = this.Left.Min;
this.Left = this.Left.Left;
}
}
if(this.Right != null) {
this.Right.Redistribute(tolerance);
if(this.Right.Min - tolerance < this.Max){
this.Values.AddRange(this.Right.GetLeftValues());
this.Max = this.Right.Max;
this.Right = this.Right.Right;
}
}
}
}
}
You can switch double to another type if you need to (I so wish C# had a numeric generic constraint).
The most straight-forward approach is to design your own IEqualityComparer<double>.
public class ToleranceEqualityComparer : IEqualityComparer<double>
{
public double Tolerance { get; set; } = 0.02;
public bool Equals(double x, double y)
{
return x - Tolerance <= y && x + Tolerance > y;
}
//This is to force the use of Equals methods.
public int GetHashCode(double obj) => 1;
}
Which you should use like so
var dataByPrice = data.GroupBy(d => d.Price, new ToleranceEqualityComparer());
Here is a new implementation that ultimately passed unit tests that the other two solutions failed. It implements the same signature as the currently accepted answer. The unit tests checked to ensure no groups resulted in a min and max value larger than the tolerance and that the number of items grouped matched the items provided.
How to use
var values = new List<Tuple<double, string>>
{
new Tuple<double, string>(113.5, "Text Item 1"),
new Tuple<double, string>(109.62, "Text Item 2"),
new Tuple<double, string>(159.06, "Text Item 3"),
new Tuple<double, string>(114, "Text Item 4")
};
var groups = values.GroupWithTolerance(5, a => a.Item1).ToList();
Extension Method
/// <summary>
/// Groups items of an IEnumerable collection while allowing a tolerance that all items within the group will fall within
/// </summary>
/// <typeparam name="TValue"></typeparam>
/// <param name="source"></param>
/// <param name="tolerance"></param>
/// <param name="keySelector"></param>
/// <returns></returns>
/// <exception cref="ArgumentNullException"></exception>
public static IEnumerable<IGrouping<double, TValue>> GroupWithTolerance<TValue>(
this IEnumerable<TValue> source,
double tolerance,
Func<TValue, double> keySelector
)
{
var sortedValuesWithKey = source
.Select((a, i) => Tuple.Create(a, keySelector(a), i))
.OrderBy(a => a.Item2)
.ToList();
var diffsByIndex = sortedValuesWithKey
.Skip(1)
//i will start at 0 but we are targeting the diff between 0 and 1.
.Select((a, i) => Tuple.Create(i + 1, sortedValuesWithKey[i + 1].Item2 - sortedValuesWithKey[i].Item2))
.ToList();
var groupBreaks = diffsByIndex
.Where(a => a.Item2 > tolerance)
.Select(a => a.Item1)
.ToHashSet();
var groupKeys = new double[sortedValuesWithKey.Count];
void AddRange(int startIndex, int endIndex)
{
//If there is just one value in the group, take a short cut.
if (endIndex - startIndex == 0)
{
groupKeys[sortedValuesWithKey[startIndex].Item3] = sortedValuesWithKey[startIndex].Item2;
return;
}
var min = sortedValuesWithKey[startIndex].Item2;
var max = sortedValuesWithKey[endIndex].Item2;
//If the range is within tolerance, we are done with this group.
if (max - min < tolerance)
{
//Get the average value of the group and assign it to all elements.
var rangeValues = new List<double>(endIndex - startIndex);
for (var x = startIndex; x <= endIndex; x++)
rangeValues.Add(sortedValuesWithKey[x].Item2);
var average = rangeValues.Average();
for (var x = startIndex; x <= endIndex; x++)
groupKeys[sortedValuesWithKey[x].Item3] = average;
return;
}
//The range is not within tolerance and needs to be divided again.
//Find the largest gap and divide.
double maxDiff = -1;
var splitIndex = -1;
for (var i = startIndex; i < endIndex; i++)
{
var currentDif = diffsByIndex[i].Item2;
if (currentDif > maxDiff)
{
maxDiff = currentDif;
splitIndex = i;
}
}
AddRange(startIndex, splitIndex);
AddRange(splitIndex + 1, endIndex);
}
var groupStartIndex = 0;
for (var i = 1; i < sortedValuesWithKey.Count; i++)
{
//There isn't a group break here, at least not yet, so continue.
if (!groupBreaks.Contains(i))
continue;
AddRange(groupStartIndex, i - 1);
groupStartIndex = i;
}
//Add the last group's keys if we haven't already.
if (groupStartIndex < sortedValuesWithKey.Count)
AddRange(groupStartIndex, sortedValuesWithKey.Count - 1);
return sortedValuesWithKey.GroupBy(a => groupKeys[a.Item3], a => a.Item1);
}
I'm trying to use regex to convert a string like this "North Korea"
to a string like "northKorea" - does someone know how I might accomplish this in c# ?
Cheers
if you know all your input strings are in title case (like "North Korea") you can simply do:
string input = "North Korea";
input = input.Replace(" ",""); //remove spaces
string output = char.ToLower(input[0]) +
input.Substring(1); //make first char lowercase
// output = "northKorea"
if some of your input is not in title case you can use TextInfo.ToTitleCase
string input = "NoRtH kORea";
input = System.Globalization.CultureInfo.CurrentCulture.TextInfo.ToTitleCase(input);
input = input.Replace(" ",""); //remove spaces
string output = char.ToLower(input[0]) +
input.Substring(1); //make first char lowercase
// output = "northKorea"
Forget regex.
All you need is a camelCase conversion algorithm:
See here:
http://www.codekeep.net/snippets/096fea45-b426-40fd-8beb-dec49d8a8662.aspx
Use this one:
string camelCase = ConvertCaseString(a, Case.CamelCase);
Copy-pasted in case it goes offline:
void Main() {
string a = "background color-red.brown";
string camelCase = ConvertCaseString(a, Case.CamelCase);
string pascalCase = ConvertCaseString(a, Case.PascalCase);
}
/// <summary>
/// Converts the phrase to specified convention.
/// </summary>
/// <param name="phrase"></param>
/// <param name="cases">The cases.</param>
/// <returns>string</returns>
static string ConvertCaseString(string phrase, Case cases)
{
string[] splittedPhrase = phrase.Split(' ', '-', '.');
var sb = new StringBuilder();
if (cases == Case.CamelCase)
{
sb.Append(splittedPhrase[0].ToLower());
splittedPhrase[0] = string.Empty;
}
else if (cases == Case.PascalCase)
sb = new StringBuilder();
foreach (String s in splittedPhrase)
{
char[] splittedPhraseChars = s.ToCharArray();
if (splittedPhraseChars.Length > 0)
{
splittedPhraseChars[0] = ((new String(splittedPhraseChars[0], 1)).ToUpper().ToCharArray())[0];
}
sb.Append(new String(splittedPhraseChars));
}
return sb.ToString();
}
enum Case
{
PascalCase,
CamelCase
}
You could just split it and put it back together:
string[] split = ("North Korea").Split(' ');
StringBuilder sb = new StringBuilder();
for (int i = 0; i < split.Count(); i++)
{
if (i == 0)
sb.Append(split[i].ToLower());
else
sb.Append(split[i]);
}
Edit: Switched to a StringBuilder instead, like Bazzz suggested.
This builds on Paolo Falabella's answer as a String extension and handles a few boundary cases such as empty string. Since there is some confusion between CamelCase and camelCase, I called it LowerCamelCase as described on Wikipedia. I resisted the temptation to go with nerdCaps.
internal static string ToLowerCamelCase( this string input )
{
string output = "";
if( String.IsNullOrEmpty( input ) == false )
{
output = System.Globalization.CultureInfo.CurrentCulture.TextInfo.ToTitleCase( input ); //in case not Title Case
output = output.Replace( " ", "" ); //remove any white spaces between words
if( String.IsNullOrEmpty( output ) == false ) //handles the case where input is " "
{
output = char.ToLower( output[0] ) + output.Substring( 1 ); //lowercase first (even if 1 character string)
}
}
return output;
}
Use:
string test = "Foo Bar";
test = test.ToLowerCamelCase();
... //test is now "fooBar"
Update:
toong raised a good point in the comments - this will not work for graphemes. See the link provided by toong. There are also examples of iterating graphemes here and here if you want to tweak the above code for graphemes.
String::Split definitely is one of my pet peeves. Also, none of the other answers deal with:
Cultures
All forms of word seperators
Numbers
What happens when it starts with word seperators
I tried to get it as close as possible to what you would find in base class library code:
static string ToCamelCaseInvariant(string value) { return ToCamelCase(value, true, CultureInfo.InvariantCulture); }
static string ToCamelCaseInvariant(string value, bool changeWordCaps) { return ToCamelCase(value, changeWordCaps, CultureInfo.InvariantCulture); }
static string ToCamelCase(string value) { return ToCamelCase(value, true, CultureInfo.CurrentCulture); }
static string ToCamelCase(string value, bool changeWordCaps) { return ToCamelCase(value, changeWordCaps, CultureInfo.CurrentCulture); }
/// <summary>
/// Converts the given string value into camelCase.
/// </summary>
/// <param name="value">The value.</param>
/// <param name="changeWordCaps">If set to <c>true</c> letters in a word (apart from the first) will be lowercased.</param>
/// <param name="culture">The culture to use to change the case of the characters.</param>
/// <returns>
/// The camel case value.
/// </returns>
static string ToCamelCase(string value, bool changeWordCaps, CultureInfo culture)
{
if (culture == null)
throw new ArgumentNullException("culture");
if (string.IsNullOrEmpty(value))
return value;
var result = new StringBuilder(value.Length);
var lastWasBreak = true;
for (var i = 0; i < value.Length; i++)
{
var c = value[i];
if (char.IsWhiteSpace(c) || char.IsPunctuation(c) || char.IsSeparator(c))
{
lastWasBreak = true;
}
else if (char.IsNumber(c))
{
result.Append(c);
lastWasBreak = true;
}
else
{
if (result.Length == 0)
{
result.Append(char.ToLower(c, culture));
}
else if (lastWasBreak)
{
result.Append(char.ToUpper(c, culture));
}
else if (changeWordCaps)
{
result.Append(char.ToLower(c, culture));
}
else
{
result.Append(c);
}
lastWasBreak = false;
}
}
return result.ToString();
}
// Tests
' This is a test. 12345hello world' = 'thisIsATest12345HelloWorld'
'--north korea' = 'northKorea'
'!nOrTH koreA' = 'northKorea'
'System.Console.' = 'systemConsole'
Try the following:
var input = "Hi my name is Rony";
var subStrs = input.ToLower().Split(' ');
var output = "";
foreach(var s in subStrs)
{
if(s!=subStrs[0])
output += s.First().ToString().ToUpper() + String.Join("", s.Skip(1));
else
output += s;
}
should get "hiMyNameIsRony" as the output
string toCamelCase(string s)
{
if (s.Length < 2) return s.ToLower();
return Char.ToLowerInvariant(s[0]) + s.Substring(1);
}
similar to Paolo Falabella's code but survives empty strings and 1 char strings.