I'm writing the following method in C# to parse a CSV file and write values to a SQL Server database.
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading.Tasks;
public List<Entity> ParseEntityExclusionFile(List<string> entries, string urlFile)
{
entries.RemoveAt(0);
List<Entity> entities = new List<Entity>();
foreach (string line in entries)
{
Entity exclusionEntity = new Entity();
string[] lineParts = line.Split(',').Select(p => p.Trim('\"')).ToArray();
exclusionEntity.Id = 1000;
exclusionEntity.Names = lineParts[3];
exclusionEntity.Identifier = $"{lineParts[25]}" + $" | " + $"Classification: " + ${lineParts[0]}";
entities.Add(exclusionEntity);
}
return entities;
}
The data in some columns of the csv file are comma-separated values inside a set of parentheses, meant to represent one value for that column. So for any values like that, I need to capture it as one value to go into one field in the database. How would I adjust/add-to the line of code string[] lineParts = line.Split(',').Select(p => p.Trim('\"')).ToArray(); to instruct the application that if it encounters a column with open parenthesis, capture all the data after the open parenthesis, including the commas, until the close parenthesis, all as one value?
EDIT: it seems the Select(p => p.Trim('\"')).ToArray(); part of the above line of code is confusing some folks - don't worry about that part - I just need to know how I would go about adding 'exception' code to create a condition where Split(',') is ignored if the commas happen to be in between a set of parentheses. One field in the csv file looks like this (1,2,3,4) - currently the code parses it as four fields, whereas I need that parsed as one field like 1,2,3,4 OR (1,2,3,4) it actually doesn't matter whether the resulting fields contain the parentheses or not.
EDIT 2: I appreciate the suggestions of using a .NET CSV library - however, everything is working perfectly in this project outside of this one field in the csv file containing a set of parentheses with comma-separated values inside - I feel as though it's a bit overkill to install and configure an entire library, including having to set up new models and properties, just for this one column of data.
Try this code:
public static class Ex
{
private static string Peek(this string source, int peek) => (source == null || peek < 0) ? null : source.Substring(0, source.Length < peek ? source.Length : peek);
private static (string, string) Pop(this string source, int pop) => (source == null || pop < 0) ? (null, source) : (source.Substring(0, source.Length < pop ? source.Length : pop), source.Length < pop ? String.Empty : source.Substring(pop));
public static string[] ParseCsvLine(this string line)
{
return ParseCsvLineImpl(line).ToArray();
IEnumerable<string> ParseCsvLineImpl(string l)
{
string remainder = line;
string field;
while (remainder.Peek(1) != "")
{
(field, remainder) = ParseField(remainder);
yield return field;
}
}
}
private const string DQ = "\"";
private static (string field, string remainder) ParseField(string line)
{
if (line.Peek(1) == DQ)
{
var (_, split) = line.Pop(1);
return ParseFieldQuoted(split);
}
else
{
var field = "";
var (head, tail) = line.Pop(1);
while (head != "," && head != "")
{
field += head;
(head, tail) = tail.Pop(1);
}
return (field, tail);
}
}
private static (string field, string remainder) ParseFieldQuoted(string line)
{
var field = "";
var head = "";
var tail = line;
while (tail.Peek(1) != "" && (tail.Peek(1) != DQ || tail.Peek(2) == DQ + DQ))
{
if (tail.Peek(2) == DQ + DQ)
{
(head, tail) = tail.Pop(2);
field += DQ;
}
else
{
(head, tail) = tail.Pop(1);
field += head;
}
}
if (tail.Peek(2) == DQ + ",")
{
(head, tail) = tail.Pop(2);
}
else if (tail.Peek(1) == DQ)
{
(head, tail) = tail.Pop(1);
}
return (field, tail);
}
}
It handles double-quotes, and double-double-quotes.
You can then do this:
string line = "45,\"23\"\",34\",66"; // 45,"23"",34",66
string[] fields = line.ParseCsvLine();
That produces:
45
23",34
66
Here's an updated version of my code that deals with ( and ) as delimiters. It deals with nested delimiters and treats them as part of the field string.
You would need to remove the " as you see fit - I'm not entirely sure why you are doing this.
Also, this is no longer CSV. The parenthesis are not a normal part of CSV. I've changed the name of the method to ParseLine as a result.
public static class Ex
{
private static string Peek(this string source, int peek) => (source == null || peek < 0) ? null : source.Substring(0, source.Length < peek ? source.Length : peek);
private static (string, string) Pop(this string source, int pop) => (source == null || pop < 0) ? (null, source) : (source.Substring(0, source.Length < pop ? source.Length : pop), source.Length < pop ? String.Empty : source.Substring(pop));
public static string[] ParseLine(this string line)
{
return ParseLineImpl(line).ToArray();
IEnumerable<string> ParseLineImpl(string l)
{
string remainder = line;
string field;
while (remainder.Peek(1) != "")
{
(field, remainder) = ParseField(remainder);
yield return field;
}
}
}
private const string GroupOpen = "(";
private const string GroupClose = ")";
private static (string field, string remainder) ParseField(string line)
{
if (line.Peek(1) == GroupOpen)
{
var (_, split) = line.Pop(1);
return ParseFieldQuoted(split);
}
else
{
var field = "";
var (head, tail) = line.Pop(1);
while (head != "," && head != "")
{
field += head;
(head, tail) = tail.Pop(1);
}
return (field, tail);
}
}
private static (string field, string remainder) ParseFieldQuoted(string line) => ParseFieldQuoted(line, false);
private static (string field, string remainder) ParseFieldQuoted(string line, bool isNested)
{
var field = "";
var head = "";
var tail = line;
while (tail.Peek(1) != "" && tail.Peek(1) != GroupClose)
{
if (tail.Peek(1) == GroupOpen)
{
(head, tail) = tail.Pop(1);
(head, tail) = ParseFieldQuoted(tail, true);
field += GroupOpen + head + GroupClose;
}
else
{
(head, tail) = tail.Pop(1);
field += head;
}
}
if (tail.Peek(2) == GroupClose + ",")
{
(head, tail) = tail.Pop(isNested ? 1 : 2);
}
else if (tail.Peek(1) == GroupClose)
{
(head, tail) = tail.Pop(1);
}
return (field, tail);
}
}
It's used like this:
string line = "45,(23(Fo(,,(,)),(\"Bar\")o),34),66"; // 45,(23(Fo(,,(,)),("Bar")o),34),66
string[] fields = line.ParseLine();
Console.WriteLine(fields.All(f => line.Contains(f))); // True == maybe code is right, False == code is WRONG
And it gives me:
45
23(Fo(,,(,)),("Bar")o),34
66
First, calling line.Trim('\"') will not strip "any existing double-quotes"; it will only remove all leading and trailing instances of the '\"' char.
var line = "\"\"example \"goes here\"";
var trimmed = line.Trim('\"');
Console.WriteLine(trimmed); //output: example "goes here
Here's how you strip all of the '\"' char:
var line = "\"\"example \"goes here\"";
var trimmed = string.Join(string.Empty, line.Split('"'));
Console.WriteLine(trimmed); //output: example goes here
Notice you can also nix the escape because the " is inside of single quotes.
I'm making an assumption that what your string inputs look like this:
"OneValue,TwoValue,(OneB,TwoB),FiveValue"
or if you have quotes (I'm also assuming you won't actually have quotes inside, but we'll solve for that anyway:
"\"OneValue,TwoValue,(OneB,TwoB),FiveValue\"\""
And I'm expecting your final string[] lineparts variable to have the values in this hard declaration after processing:
var lineparts = new string[] { "OneValue", "TwoValue", "OneB, TwoB", "FiveValue" };
The first solution I can think of is to first split by '(', then iterate over the collection, conditionally splitting by ')' or ',', depending on which side of the opening parenthesis the current element is on. Pretty sure this is linear, so that's neat:
const string l = ",(";
const string r = "),";
const char c = ',';
const char a = '"';
var line = "\"One,Two,(OneB,TwoB),Five\"";
line = string.Join(string.Empty, line.Split(a)); //Strip "
var splitL = line.Split(l); //,(
var partsList = new List<string>();
foreach (var value in splitL)
{
if (value.Contains(r))//),
{
//inside of parentheses, so we keep the values before the ),
var splitR = value.Split(r);//),
//I don't like literal indexes, but we know we have at least one element because we have a value.
partsList.Add(splitR[0]);
//Everything else is after the closing parenthesis for this group, and before the parenthesis after that
//so we'll parse it all into different values.
//The literal index is safe here because split always returns two values if any value is found.
partsList.AddRange(splitR[1].Split(c));//,
}
else
{
//before the parentheses, so these are all different values
partsList.AddRange(value.Split(c));//,
}
}
var lineparts = partsList.ToArray();//{ "One", "Two", "OneB, TwoB", "Five" };
Here's a better example of a tighter integration with the code in your question, not considering the specific intended values of your Entity properties or the need to trim for quotations:
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading.Tasks;
public List<Entity> ParseEntityExclusionFile(List<string> entries, string urlFile)
{
entries.RemoveAt(0);
const char l = '(';
const char r = ')';
const char c = ',';
const char a = '"';
List<Entity> entities = new List<Entity>();
foreach (string line in entries)
{
var splitL = line.Split(l); //(
var partsList = new List<string>();
foreach (var value in splitL)
{
if (value.Contains(r))//)
{
var splitR = value.Split(r);//)
partsList.Add(splitR[0]);
if (!line.EndsWith(r))
{
partsList.AddRange(splitR[1].Remove(0, 1).Split(c));//,
}
}
else
{
if (!line.StartsWith(l))
{
partsList.AddRange(value.Remove(value.Length - 1).Split(c));//,
}
}
}
var lineParts = partsList.ToArray();//{ "One", "Two", "OneB, TwoB", "Five" };
entities.Add(new Entity
{
Id = 1000,
Names = lineParts[3],
Identifier = $"{lineParts[25]} | Classification: {lineParts[0]}";
});
}
return entities;
}
This solution may get hairy if your groups contain other groups, i.e...
"OneValue,TwoValue,(OneB,(TwoB, ThreeB)),SixValue"
Related
I am trying to convert camel case to snake case.
Like this:
"LiveKarma" -> "live_karma"
"youGO" -> "you_g_o"
I cannot seem to get the second example working like that. It always outputs as 'you_go' . How can I get it to output 'you_g_o'
My code:
(Regex.Replace(line, "(?<=[a-z0-9])[A-Z]", "_$0", RegexOptions.Compiled)).ToLowerInvariant()
Here is an extension method that transforms the text into a snake case:
using System.Text;
public static string ToSnakeCase(this string text)
{
if(text == null) {
throw new ArgumentNullException(nameof(text));
}
if(text.Length < 2) {
return text;
}
var sb = new StringBuilder();
sb.Append(char.ToLowerInvariant(text[0]));
for(int i = 1; i < text.Length; ++i) {
char c = text[i];
if(char.IsUpper(c)) {
sb.Append('_');
sb.Append(char.ToLowerInvariant(c));
} else {
sb.Append(c);
}
}
return sb.ToString();
}
Put it into a static class somewhere (named for example StringExtensions) and use it like this:
string text = "LiveKarma";
string snakeCaseText = text.ToSnakeCase();
// snakeCaseText => "live_karma"
Since the option that converts abbreviations as separate words is not suitable for many, I found a complete solution in the EF Core codebase.
Here are a couple of examples of how the code works:
TestSC -> test_sc
testSC -> test_sc
TestSnakeCase -> test_snake_case
testSnakeCase -> test_snake_case
TestSnakeCase123 -> test_snake_case123
_testSnakeCase123 -> _test_snake_case123
test_SC -> test_sc
I rewrote it a bit so you can copy it as a ready-to-use string extension:
using System;
using System.Globalization;
using System.Text;
namespace Extensions
{
public static class StringExtensions
{
public static string ToSnakeCase(this string text)
{
if (string.IsNullOrEmpty(text))
{
return text;
}
var builder = new StringBuilder(text.Length + Math.Min(2, text.Length / 5));
var previousCategory = default(UnicodeCategory?);
for (var currentIndex = 0; currentIndex < text.Length; currentIndex++)
{
var currentChar = text[currentIndex];
if (currentChar == '_')
{
builder.Append('_');
previousCategory = null;
continue;
}
var currentCategory = char.GetUnicodeCategory(currentChar);
switch (currentCategory)
{
case UnicodeCategory.UppercaseLetter:
case UnicodeCategory.TitlecaseLetter:
if (previousCategory == UnicodeCategory.SpaceSeparator ||
previousCategory == UnicodeCategory.LowercaseLetter ||
previousCategory != UnicodeCategory.DecimalDigitNumber &&
previousCategory != null &&
currentIndex > 0 &&
currentIndex + 1 < text.Length &&
char.IsLower(text[currentIndex + 1]))
{
builder.Append('_');
}
currentChar = char.ToLower(currentChar, CultureInfo.InvariantCulture);
break;
case UnicodeCategory.LowercaseLetter:
case UnicodeCategory.DecimalDigitNumber:
if (previousCategory == UnicodeCategory.SpaceSeparator)
{
builder.Append('_');
}
break;
default:
if (previousCategory != null)
{
previousCategory = UnicodeCategory.SpaceSeparator;
}
continue;
}
builder.Append(currentChar);
previousCategory = currentCategory;
}
return builder.ToString();
}
}
}
You can find the original code here:
https://github.com/efcore/EFCore.NamingConventions/blob/main/EFCore.NamingConventions/Internal/SnakeCaseNameRewriter.cs
UPD 27.04.2022:
Also, you can use Newtonsoft library if you're looking for a ready to use third party solution. The output of the code is the same as the code above.
// using Newtonsoft.Json.Serialization;
var snakeCaseStrategy = new SnakeCaseNamingStrategy();
var snakeCaseResult = snakeCaseStrategy.GetPropertyName(text, false);
Simple Linq based solution... no idea if its faster or not. basically ignores consecutive uppercases
public static string ToUnderscoreCase(this string str)
=> string.Concat((str ?? string.Empty).Select((x, i) => i > 0 && i < str.Length - 1 && char.IsUpper(x) && !char.IsUpper(str[i-1]) ? $"_{x}" : x.ToString())).ToLower();
using Newtonsoft package
public static string? ToCamelCase(this string? str) => str is null
? null
: new DefaultContractResolver() { NamingStrategy = new CamelCaseNamingStrategy() }.GetResolvedPropertyName(str);
public static string? ToSnakeCase(this string? str) => str is null
? null
: new DefaultContractResolver() { NamingStrategy = new SnakeCaseNamingStrategy() }.GetResolvedPropertyName(str);
RegEx Solution
A quick internet search turned up this site which has an answer using RegEx, which I had to modify to grab the Value portion in order for it to work on my machine (but it has the RegEx you're looking for). I also modified it to handle null input, rather than throwing an exception:
public static string ToSnakeCase2(string str)
{
var pattern =
new Regex(#"[A-Z]{2,}(?=[A-Z][a-z]+[0-9]*|\b)|[A-Z]?[a-z]+[0-9]*|[A-Z]|[0-9]+");
return str == null
? null
: string
.Join("_", pattern.Matches(str).Cast<Match>().Select(m => m.Value))
.ToLower();
}
Non-RegEx Solution
For a non-regex solution, we can do the following:
Reduce all whitespace to a single space by
using string.Split to split with an empty array as the first parameter to split on all whitespace
joining those parts back together with the '_' character
Prefix all upper-case characters with '_' and lower-case them
Split and re-join the resulting string on the _ character to remove any instances of multiple concurrent underscores ("__") and to remove any leading or trailing instances of the character.
For example:
public static string ToSnakeCase(string str)
{
return str == null
? null
: string.Join("_", string.Concat(string.Join("_", str.Split(new char[] {},
StringSplitOptions.RemoveEmptyEntries))
.Select(c => char.IsUpper(c)
? $"_{c}".ToLower()
: $"{c}"))
.Split(new[] {'_'}, StringSplitOptions.RemoveEmptyEntries));
}
pseudo code below. In essence check if each char is upper case, then if it is add a _, then add the char to lower case
var newString = s.subString(0,1).ToLower();
foreach (char c in s.SubString(1,s.length-1))
{
if (char.IsUpper(c))
{
newString = newString + "_";
}
newString = newString + c.ToLower();
}
if you're into micro-optimaizations and want to prevent unneccessary conversions wherever possible, this one might also work:
public static string ToSnakeCase(this string text)
{
static IEnumerable<char> Convert(CharEnumerator e)
{
if (!e.MoveNext()) yield break;
yield return char.ToLower(e.Current);
while (e.MoveNext())
{
if (char.IsUpper(e.Current))
{
yield return '_';
yield return char.ToLower(e.Current);
}
else
{
yield return e.Current;
}
}
}
return new string(Convert(text.GetEnumerator()).ToArray());
}
There is a well maintained EF Core community project that implements a number of naming convention rewriters called EFCore.NamingConventions. The rewriters don't have any internal dependencies, so if you don't want to bring in an EF Core related package you can just copy the rewriter code out.
Here is the snake case rewriter: https://github.com/efcore/EFCore.NamingConventions/blob/main/EFCore.NamingConventions/Internal/SnakeCaseNameRewriter.cs
May has well toss this one out. Very simple and worked for me.
public static string ToSnakeCase(this string text)
{
text = Regex.Replace(text, "(.)([A-Z][a-z]+)", "$1_$2");
text = Regex.Replace(text, "([a-z0-9])([A-Z])", "$1_$2");
return text.ToLower();
}
Testing it with some samples (borrowed from #GeekInside's answer):
var samples = new List<string>() { "TestSC", "testSC", "TestSnakeCase", "testSnakeCase", "TestSnakeCase123", "_testSnakeCase123", "test_SC" };
var results = new List<string>() { "test_sc", "test_sc", "test_snake_case", "test_snake_case", "test_snake_case123", "_test_snake_case123", "test_sc" };
for (int i = 0; i < samples.Count; i++)
{
Console.WriteLine("Test success: " + (val.ToSnakeCase() == results[i] ? "true" : "false"));
}
Produced the following output:
Test success: true
Test success: true
Test success: true
Test success: true
Test success: true
Test success: true
Test success: true
This question already has answers here:
How can I Split(',') a string while ignore commas in between quotes?
(3 answers)
C# Regex Split - commas outside quotes
(7 answers)
Closed 5 years ago.
I need to split a csv file by comma apart from where the columns is between quote marks. However, what I have here does not seem to be achieving what I need and comma's in columns are being split into separate array items.
public List<string> GetData(string dataFile, int row)
{
try
{
var lines = File.ReadAllLines(dataFile).Select(a => a.Split(';'));
var csv = from line in lines select (from piece in line select piece.Split(',')).ToList();
var foo = csv.ToList();
var result = foo[row][0].ToList();
return result;
}
catch
{
return null;
}
}
private const string QUOTE = "\"";
private const string ESCAPED_QUOTE = "\"\"";
private static char[] CHARACTERS_THAT_MUST_BE_QUOTED = { ',', '"', '\n' };
public static string Escape(string s)
{
if (s.Contains(QUOTE))
s = s.Replace(QUOTE, ESCAPED_QUOTE);
if (s.IndexOfAny(CHARACTERS_THAT_MUST_BE_QUOTED) > -1)
s = QUOTE + s + QUOTE;
return s;
}
I am not sure where I can use my escape function in this case.
Example:
Degree,Graduate,08-Dec-17,Level 1,"Advanced, Maths"
The string Advanced, Maths are being split into two different array items which I don't want
You could use regex, linq or just loop through each character and use Booleans to figure out what the current behaviour should be. This question actually got me thinking, as I'd previously just looped through and acted on each character. Here is Linq way of breaking an entire csv document up, assuming the end of line can be found with ';':
private static void Main(string[] args)
{
string example = "\"Hello World, My name is Gumpy!\",20,male;My sister's name is Amy,29,female";
var result1 = example.Split(';')
.Select(s => s.Split('"')) // This will leave anything in abbreviation marks at odd numbers
.Select(sl => sl.Select((ss, index) => index % 2 == 0 ? ss.Split(',') : new string[] { ss })) // if it's an even number split by a comma
.Select(sl => sl.SelectMany(sc => sc));
Console.WriteLine("Press any key to continue.");
Console.ReadKey();
}
Not sure how this performes - but you can solve that with Linq.Aggregate like this:
using System;
using System.Linq;
using System.Collections.Generic;
public class Program
{
public static IEnumerable<string> SplitIt(
char[] splitters,
string text,
StringSplitOptions opt = StringSplitOptions.None)
{
bool inside = false;
var result = text.Aggregate(new List<string>(), (acc, c) =>
{
// this will check each char of your given text
// and accumulate it in the (empty starting) string list
// your splitting chars will lead to a new item put into
// the list if they are not inside. inside starst as false
// and is flipped anytime it hits a "
// at end we either return all that was parsed or only those
// that are neither null nor "" depending on given opt's
if (!acc.Any()) // nothing in yet
{
if (c != '"' && (!splitters.Contains(c) || inside))
acc.Add("" + c);
else if (c == '"')
inside = !inside;
else if (!inside && splitters.Contains(c)) // ",bla"
acc.Add(null);
return acc;
}
if (c != '"' && (!splitters.Contains(c) || inside))
acc[acc.Count - 1] = (acc[acc.Count - 1] ?? "") + c;
else if (c == '"')
inside = !inside;
else if (!inside && splitters.Contains(c)) // ",bla"
acc.Add(null);
return acc;
}
);
if (opt == StringSplitOptions.RemoveEmptyEntries)
return result.Where(r => !string.IsNullOrEmpty(r));
return result;
}
public static void Main()
{
var s = ",,Degree,Graduate,08-Dec-17,Level 1,\"Advanced, Maths\",,";
var spl = SplitIt(new[]{','}, s);
var spl2 = SplitIt(new[]{','}, s, StringSplitOptions.RemoveEmptyEntries);
Console.WriteLine(string.Join("|", spl));
Console.WriteLine(string.Join("|", spl2));
}
}
Output:
|Degree|Graduate|08-Dec-17|Level 1|Advanced, Maths||
Degree|Graduate|08-Dec-17|Level 1|Advanced, Maths
The function gets comma separated fields within a string, excluding commas embedded in a quoted field
The assumptions
It should return empty fields ,,
There are no quotes within a quote field (as per the example)
The method
I uses a for loop with i as a place holder of the current field
It scans for the next comma or quote and if it finds a quote it scans for the next comma to create the field
It needed to be efficient otherwise we would use regex or Linq
The OP didn't want to use a CSV library
Note : There is no error checking, and scanning each character would be faster this was just easy to understand
Code
public List<string> GetFields(string line)
{
var list = new List<string>();
for (var i = 0; i < line.Length; i++)
{
var firstQuote = line.IndexOf('"', i);
var firstComma = line.IndexOf(',', i);
if (firstComma >= 0)
{
// first comma is before the first quote, then its just a standard field
if (firstComma < firstQuote || firstQuote == -1)
{
list.Add(line.Substring(i, firstComma - i));
i = firstComma;
continue;
}
// We have found quote so look for the next comma afterwards
var nextQuote = line.IndexOf('"', firstQuote + 1);
var nextComma = line.IndexOf(',', nextQuote + 1);
// if we found a comma, then we have found the end of this field
if (nextComma >= 0)
{
list.Add(line.Substring(i, nextComma - i));
i = nextComma;
continue;
}
}
list.Add(line.Substring(i)); // if were are here there are no more fields
break;
}
return list;
}
Tests 1
Degree,Graduate,08-Dec-17,Level 1,"Advanced, Maths",another
Degree
Graduate
08-Dec-17
Level 1
"Advanced, Maths"
another
Tests 2
,Degree,Graduate,08-Dec-17,\"asdasd\",Level 1,\"Advanced, Maths\",another
<Empty Line>
Degree
Graduate
08-Dec-17
"asdasd"
Level 1
"Advanced, Maths"
another
I'm trying to develop a method that will match all strings between two strings:
I've tried this but it returns only the first match:
string ExtractString(string s, string start,string end)
{
// You should check for errors in real-world code, omitted for brevity
int startIndex = s.IndexOf(start) + start.Length;
int endIndex = s.IndexOf(end, startIndex);
return s.Substring(startIndex, endIndex - startIndex);
}
Let's suppose we have this string
String Text = "A1FIRSTSTRINGA2A1SECONDSTRINGA2akslakhflkshdflhksdfA1THIRDSTRINGA2"
I would like a c# function doing the following :
public List<string> ExtractFromString(String Text,String Start, String End)
{
List<string> Matched = new List<string>();
.
.
.
return Matched;
}
// Example of use
ExtractFromString("A1FIRSTSTRINGA2A1SECONDSTRINGA2akslakhflkshdflhksdfA1THIRDSTRINGA2","A1","A2")
// Will return :
// FIRSTSTRING
// SECONDSTRING
// THIRDSTRING
Thank you for your help !
private static List<string> ExtractFromBody(string body, string start, string end)
{
List<string> matched = new List<string>();
int indexStart = 0;
int indexEnd = 0;
bool exit = false;
while (!exit)
{
indexStart = body.IndexOf(start);
if (indexStart != -1)
{
indexEnd = indexStart + body.Substring(indexStart).IndexOf(end);
matched.Add(body.Substring(indexStart + start.Length, indexEnd - indexStart - start.Length));
body = body.Substring(indexEnd + end.Length);
}
else
{
exit = true;
}
}
return matched;
}
Here is a solution using RegEx. Don't forget to include the following using statement.
using System.Text.RegularExpressions
It will correctly return only text between the start and end strings given.
Will not be returned:
akslakhflkshdflhksdf
Will be returned:
FIRSTSTRING
SECONDSTRING
THIRDSTRING
It uses the regular expression pattern [start string].+?[end string]
The start and end strings are escaped in case they contain regular expression special characters.
private static List<string> ExtractFromString(string source, string start, string end)
{
var results = new List<string>();
string pattern = string.Format(
"{0}({1}){2}",
Regex.Escape(start),
".+?",
Regex.Escape(end));
foreach (Match m in Regex.Matches(source, pattern))
{
results.Add(m.Groups[1].Value);
}
return results;
}
You could make that into an extension method of String like this:
public static class StringExtensionMethods
{
public static List<string> EverythingBetween(this string source, string start, string end)
{
var results = new List<string>();
string pattern = string.Format(
"{0}({1}){2}",
Regex.Escape(start),
".+?",
Regex.Escape(end));
foreach (Match m in Regex.Matches(source, pattern))
{
results.Add(m.Groups[1].Value);
}
return results;
}
}
Usage:
string source = "A1FIRSTSTRINGA2A1SECONDSTRINGA2akslakhflkshdflhksdfA1THIRDSTRINGA2";
string start = "A1";
string end = "A2";
List<string> results = source.EverythingBetween(start, end);
text.Split(new[] {"A1", "A2"}, StringSplitOptions.RemoveEmptyEntries);
You can split the string into an array using the start identifier in following code:
String str = "A1FIRSTSTRINGA2A1SECONDSTRINGA2akslakhflkshdflhksdfA1THIRDSTRINGA2";
String[] arr = str.Split("A1");
Then iterate through your array and remove the last 2 characters of each string (to remove the A2). You'll also need to discard the first array element as it will be empty assuming the string starts with A1.
Code is untested, currently on a mobile
This is a generic solution, and I believe more readable code. Not tested, so beware.
public static IEnumerable<IList<T>> SplitBy<T>(this IEnumerable<T> source,
Func<T, bool> startPredicate,
Func<T, bool> endPredicate,
bool includeDelimiter)
{
var l = new List<T>();
foreach (var s in source)
{
if (startPredicate(s))
{
if (l.Any())
{
l = new List<T>();
}
l.Add(s);
}
else if (l.Any())
{
l.Add(s);
}
if (endPredicate(s))
{
if (includeDelimiter)
yield return l;
else
yield return l.GetRange(1, l.Count - 2);
l = new List<T>();
}
}
}
In your case you can call,
var text = "A1FIRSTSTRINGA2A1SECONDSTRINGA2akslakhflkshdflhksdfA1THIRDSTRINGA2";
var splits = text.SplitBy(x => x == "A1", x => x == "A2", false);
This is not the most efficient when you do not want the delimiter to be included (like your case) in result but efficient for opposite cases. To speed up your case one can directly call the GetEnumerator and make use of MoveNext.
i have string with date , i want to split it with date and string
For example :
I have this type of strings data
9/23/2013/marking abandoned based on notes below/DB
12/8/2012/I think the thid is string/SG
and i want to make it like as
9/23/2013 marking abandoned based on notes below/DB
12/8/2013 I think the thid is string/SG
so, i don't know how to split these strings and store in different columns of table.
pls help me.
string[] vals = { "9/23/2013/marking abandoned based on notes below/DB",
"12/8/2012/I think the thid is string/SG" };
var regex = #"(\d{1,2}/\d{1,2}/\d{4})/(.*)";
var matches = vals.Select(val => Regex.Match(vals, regex));
foreach (var match in matches)
{
Console.WriteLine ("{0} {1}", match.Groups[1], match.Groups[2]);
}
prints:
9/23/2013 marking abandoned based on notes below/DB
12/8/2012 I think the thid is string/SG
(\d{1,2}/\d{1,2}/\d{4})/(.*) breaks down to
(\d{1,2}/\d{1,2}/\d{4}):
\d{1,2} - matches any one or two digit number
/ - matches to one / symbol
\d{4} - matches to four digit number
(...) - denotes first group
(.*) - matches everything else and creates second group
Another way to do it with LINQ:
var inputs = new[]{
"9/23/2013/marking abandoned based on notes below/DB",
"12/8/2012/I think the thid is string/SG"
};
foreach (var item in inputs)
{
int counter = 0;
var r = item.Split('/')
.Aggregate("", (a, b) =>
a + ((counter++ == 3) ? "\t" : ((counter == 1) ? "" : "/")) + b);
Console.WriteLine(r);
}
Or you may use the IndexOf and Substring methods:
foreach (var item in inputs)
{
var lastPos =
item.IndexOf('/',
1 + item.IndexOf('/',
1 + item.IndexOf('/')));
if (lastPos != -1)
{
var r = String.Join("\t",
item.Substring(0, lastPos),
item.Substring(lastPos + 1, item.Length - lastPos - 1));
Console.WriteLine(r);
}
}
Perhaps with pure string methods, the third slash separates the date and the text:
string line = "9/23/2013/marking abandoned based on notes below/DB";
int slashIndex = line.IndexOf('/');
if(slashIndex >= 0)
{
int slashCount = 1;
while(slashCount < 3 && slashIndex >= 0)
{
slashIndex = line.IndexOf('/', slashIndex + 1);
if(slashIndex >= 0) slashCount++;
}
if(slashCount == 3)
{
Console.WriteLine("Date:{0} Text: {1}"
, line.Substring(0, slashIndex)
, line.Substring(slashIndex +1));
}
}
For what it's worth, here is a extension method to "break" a string in half on nth occurence of astring:
public static class StringExtensions
{
public static string[] BreakOnNthIndexOf(this string input, string value, int breakOn, StringComparison comparison)
{
if (breakOn <= 0)
throw new ArgumentException("breakOn must be greater than 0", "breakOn");
if (value == null) value = " "; // fallback on white-space
int slashIndex = input.IndexOf(value, comparison);
if (slashIndex >= 0)
{
int slashCount = 1;
while (slashCount < breakOn && slashIndex >= 0)
{
slashIndex = input.IndexOf(value, slashIndex + value.Length, comparison);
if (slashIndex >= 0) slashCount++;
}
if (slashCount == breakOn)
{
return new[] {
input.Substring(0, slashIndex),
input.Substring(slashIndex + value.Length)
};
}
}
return new[]{ input };
}
}
Use it in this way:
string line1 = "9/23/2013/marking abandoned based on notes below/DB";
string line2 = "12/8/2012/I think the thid is string/SG";
string[] res1 = line1.BreakOnNthIndexOf("/", 3, StringComparison.OrdinalIgnoreCase);
string[] res2 = line2.BreakOnNthIndexOf("/", 3, StringComparison.OrdinalIgnoreCase);
This is all asp.net c#.
I have an enum
public enum ControlSelectionType
{
NotApplicable = 1,
SingleSelectRadioButtons = 2,
SingleSelectDropDownList = 3,
MultiSelectCheckBox = 4,
MultiSelectListBox = 5
}
The numerical value of this is stored in my database. I display this value in a datagrid.
<asp:boundcolumn datafield="ControlSelectionTypeId" headertext="Control Type"></asp:boundcolumn>
The ID means nothing to a user so I have changed the boundcolumn to a template column with the following.
<asp:TemplateColumn>
<ItemTemplate>
<%# Enum.Parse(typeof(ControlSelectionType), DataBinder.Eval(Container.DataItem, "ControlSelectionTypeId").ToString()).ToString()%>
</ItemTemplate>
</asp:TemplateColumn>
This is a lot better... However, it would be great if there was a simple function I can put around the Enum to split it by Camel case so that the words wrap nicely in the datagrid.
Note: I am fully aware that there are better ways of doing all this. This screen is purely used internally and I just want a quick hack in place to display it a little better.
I used:
public static string SplitCamelCase(string input)
{
return System.Text.RegularExpressions.Regex.Replace(input, "([A-Z])", " $1", System.Text.RegularExpressions.RegexOptions.Compiled).Trim();
}
Taken from http://weblogs.asp.net/jgalloway/archive/2005/09/27/426087.aspx
vb.net:
Public Shared Function SplitCamelCase(ByVal input As String) As String
Return System.Text.RegularExpressions.Regex.Replace(input, "([A-Z])", " $1", System.Text.RegularExpressions.RegexOptions.Compiled).Trim()
End Function
Here is a dotnet Fiddle for online execution of the c# code.
Indeed a regex/replace is the way to go as described in the other answer, however this might also be of use to you if you wanted to go a different direction
using System.ComponentModel;
using System.Reflection;
...
public static string GetDescription(System.Enum value)
{
FieldInfo fi = value.GetType().GetField(value.ToString());
DescriptionAttribute[] attributes = (DescriptionAttribute[])fi.GetCustomAttributes(typeof(DescriptionAttribute), false);
if (attributes.Length > 0)
return attributes[0].Description;
else
return value.ToString();
}
this will allow you define your Enums as
public enum ControlSelectionType
{
[Description("Not Applicable")]
NotApplicable = 1,
[Description("Single Select Radio Buttons")]
SingleSelectRadioButtons = 2,
[Description("Completely Different Display Text")]
SingleSelectDropDownList = 3,
}
Taken from
http://www.codeguru.com/forum/archive/index.php/t-412868.html
This regex (^[a-z]+|[A-Z]+(?![a-z])|[A-Z][a-z]+) can be used to extract all words from the camelCase or PascalCase name. It also works with abbreviations anywhere inside the name.
MyHTTPServer will contain exactly 3 matches: My, HTTP, Server
myNewXMLFile will contain 4 matches: my, New, XML, File
You could then join them into a single string using string.Join.
string name = "myNewUIControl";
string[] words = Regex.Matches(name, "(^[a-z]+|[A-Z]+(?![a-z])|[A-Z][a-z]+)")
.OfType<Match>()
.Select(m => m.Value)
.ToArray();
string result = string.Join(" ", words);
As #DanielB noted in the comments, that regex won't work for numbers (and with underscores), so here is an improved version that supports any identifier with words, acronyms, numbers, underscores (slightly modified #JoeJohnston's version), see online demo (fiddle):
([A-Z]+(?![a-z])|[A-Z][a-z]+|[0-9]+|[a-z]+)
Extreme example: __snake_case12_camelCase_TLA1ABC → snake, case, 12, camel, Case, TLA, 1, ABC
Tillito's answer does not handle strings already containing spaces well, or Acronyms. This fixes it:
public static string SplitCamelCase(string input)
{
return Regex.Replace(input, "(?<=[a-z])([A-Z])", " $1", RegexOptions.Compiled);
}
If C# 3.0 is an option you can use the following one-liner to do the job:
Regex.Matches(YOUR_ENUM_VALUE_NAME, "[A-Z][a-z]+").OfType<Match>().Select(match => match.Value).Aggregate((acc, b) => acc + " " + b).TrimStart(' ');
Here's an extension method that handles numbers and multiple uppercase characters sanely, and also allows for upper-casing specific acronyms in the final string:
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Globalization;
using System.Text.RegularExpressions;
using System.Web.Configuration;
namespace System
{
/// <summary>
/// Extension methods for the string data type
/// </summary>
public static class ConventionBasedFormattingExtensions
{
/// <summary>
/// Turn CamelCaseText into Camel Case Text.
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
/// <remarks>Use AppSettings["SplitCamelCase_AllCapsWords"] to specify a comma-delimited list of words that should be ALL CAPS after split</remarks>
/// <example>
/// wordWordIDWord1WordWORDWord32Word2
/// Word Word ID Word 1 Word WORD Word 32 Word 2
///
/// wordWordIDWord1WordWORDWord32WordID2ID
/// Word Word ID Word 1 Word WORD Word 32 Word ID 2 ID
///
/// WordWordIDWord1WordWORDWord32Word2Aa
/// Word Word ID Word 1 Word WORD Word 32 Word 2 Aa
///
/// wordWordIDWord1WordWORDWord32Word2A
/// Word Word ID Word 1 Word WORD Word 32 Word 2 A
/// </example>
public static string SplitCamelCase(this string input)
{
if (input == null) return null;
if (string.IsNullOrWhiteSpace(input)) return "";
var separated = input;
separated = SplitCamelCaseRegex.Replace(separated, #" $1").Trim();
//Set ALL CAPS words
if (_SplitCamelCase_AllCapsWords.Any())
foreach (var word in _SplitCamelCase_AllCapsWords)
separated = SplitCamelCase_AllCapsWords_Regexes[word].Replace(separated, word.ToUpper());
//Capitalize first letter
var firstChar = separated.First(); //NullOrWhiteSpace handled earlier
if (char.IsLower(firstChar))
separated = char.ToUpper(firstChar) + separated.Substring(1);
return separated;
}
private static readonly Regex SplitCamelCaseRegex = new Regex(#"
(
(?<=[a-z])[A-Z0-9] (?# lower-to-other boundaries )
|
(?<=[0-9])[a-zA-Z] (?# number-to-other boundaries )
|
(?<=[A-Z])[0-9] (?# cap-to-number boundaries; handles a specific issue with the next condition )
|
(?<=[A-Z])[A-Z](?=[a-z]) (?# handles longer strings of caps like ID or CMS by splitting off the last capital )
)"
, RegexOptions.Compiled | RegexOptions.IgnorePatternWhitespace
);
private static readonly string[] _SplitCamelCase_AllCapsWords =
(WebConfigurationManager.AppSettings["SplitCamelCase_AllCapsWords"] ?? "")
.Split(new[] { ',' }, StringSplitOptions.RemoveEmptyEntries)
.Select(a => a.ToLowerInvariant().Trim())
.ToArray()
;
private static Dictionary<string, Regex> _SplitCamelCase_AllCapsWords_Regexes;
private static Dictionary<string, Regex> SplitCamelCase_AllCapsWords_Regexes
{
get
{
if (_SplitCamelCase_AllCapsWords_Regexes == null)
{
_SplitCamelCase_AllCapsWords_Regexes = new Dictionary<string,Regex>();
foreach(var word in _SplitCamelCase_AllCapsWords)
_SplitCamelCase_AllCapsWords_Regexes.Add(word, new Regex(#"\b" + word + #"\b", RegexOptions.Compiled | RegexOptions.IgnoreCase));
}
return _SplitCamelCase_AllCapsWords_Regexes;
}
}
}
}
You can use C# extension methods
public static string SpacesFromCamel(this string value)
{
if (value.Length > 0)
{
var result = new List<char>();
char[] array = value.ToCharArray();
foreach (var item in array)
{
if (char.IsUpper(item) && result.Count > 0)
{
result.Add(' ');
}
result.Add(item);
}
return new string(result.ToArray());
}
return value;
}
Then you can use it like
var result = "TestString".SpacesFromCamel();
Result will be
Test String
Using LINQ:
var chars = ControlSelectionType.NotApplicable.ToString().SelectMany((x, i) => i > 0 && char.IsUpper(x) ? new char[] { ' ', x } : new char[] { x });
Console.WriteLine(new string(chars.ToArray()));
I also have an enum which I had to separate. In my case this method solved the problem-
string SeparateCamelCase(string str)
{
for (int i = 1; i < str.Length; i++)
{
if (char.IsUpper(str[i]))
{
str = str.Insert(i, " ");
i++;
}
}
return str;
}
public enum ControlSelectionType
{
NotApplicable = 1,
SingleSelectRadioButtons = 2,
SingleSelectDropDownList = 3,
MultiSelectCheckBox = 4,
MultiSelectListBox = 5
}
public class NameValue
{
public string Name { get; set; }
public object Value { get; set; }
}
public static List<NameValue> EnumToList<T>(bool camelcase)
{
var array = (T[])(Enum.GetValues(typeof(T)).Cast<T>());
var array2 = Enum.GetNames(typeof(T)).ToArray<string>();
List<NameValue> lst = null;
for (int i = 0; i < array.Length; i++)
{
if (lst == null)
lst = new List<NameValue>();
string name = "";
if (camelcase)
{
name = array2[i].CamelCaseFriendly();
}
else
name = array2[i];
T value = array[i];
lst.Add(new NameValue { Name = name, Value = value });
}
return lst;
}
public static string CamelCaseFriendly(this string pascalCaseString)
{
Regex r = new Regex("(?<=[a-z])(?<x>[A-Z])|(?<=.)(?<x>[A-Z])(?=[a-z])");
return r.Replace(pascalCaseString, " ${x}");
}
//In your form
protected void Button1_Click1(object sender, EventArgs e)
{
DropDownList1.DataSource = GeneralClass.EnumToList<ControlSelectionType >(true); ;
DropDownList1.DataTextField = "Name";
DropDownList1.DataValueField = "Value";
DropDownList1.DataBind();
}
The solution from Eoin Campbell works good except if you have a Web Service.
You would need to do the Following as the Description Attribute is not serializable.
[DataContract]
public enum ControlSelectionType
{
[EnumMember(Value = "Not Applicable")]
NotApplicable = 1,
[EnumMember(Value = "Single Select Radio Buttons")]
SingleSelectRadioButtons = 2,
[EnumMember(Value = "Completely Different Display Text")]
SingleSelectDropDownList = 3,
}
public static string GetDescriptionFromEnumValue(Enum value)
{
EnumMemberAttribute attribute = value.GetType()
.GetField(value.ToString())
.GetCustomAttributes(typeof(EnumMemberAttribute), false)
.SingleOrDefault() as EnumMemberAttribute;
return attribute == null ? value.ToString() : attribute.Value;
}
And if you don't fancy using regex - try this:
public static string SeperateByCamelCase(this string text, char splitChar = ' ') {
var output = new StringBuilder();
for (int i = 0; i < text.Length; i++)
{
var c = text[i];
//if not the first and the char is upper
if (i > 0 && char.IsUpper(c)) {
var wasLastLower = char.IsLower(text[i - 1]);
if (i + 1 < text.Length) //is there a next
{
var isNextUpper = char.IsUpper(text[i + 1]);
if (!isNextUpper) //if next is not upper (start of a word).
{
output.Append(splitChar);
}
else if (wasLastLower) //last was lower but i'm upper and my next is an upper (start of an achromin). 'abcdHTTP' 'abcd HTTP'
{
output.Append(splitChar);
}
}
else
{
//last letter - if its upper and the last letter was lower 'abcd' to 'abcd A'
if (wasLastLower)
{
output.Append(splitChar);
}
}
}
output.Append(c);
}
return output.ToString();
}
Passes these tests, it doesn't like numbers but i didn't need it to.
[TestMethod()]
public void ToCamelCaseTest()
{
var testData = new string[] { "AAACamel", "AAA", "SplitThisByCamel", "AnA", "doesnothing", "a", "A", "aasdasdAAA" };
var expectedData = new string[] { "AAA Camel", "AAA", "Split This By Camel", "An A", "doesnothing", "a", "A", "aasdasd AAA" };
for (int i = 0; i < testData.Length; i++)
{
var actual = testData[i].SeperateByCamelCase();
var expected = expectedData[i];
Assert.AreEqual(actual, expected);
}
}
#JustSayNoToRegex
Takes a C# identifier, with uderscores and numbers, and converts it to space-separated string.
public static class StringExtensions
{
public static string SplitOnCase(this string identifier)
{
if (identifier == null || identifier.Length == 0) return string.Empty;
var sb = new StringBuilder();
if (identifier.Length == 1) sb.Append(char.ToUpperInvariant(identifier[0]));
else if (identifier.Length == 2) sb.Append(char.ToUpperInvariant(identifier[0])).Append(identifier[1]);
else {
if (identifier[0] != '_') sb.Append(char.ToUpperInvariant(identifier[0]));
for (int i = 1; i < identifier.Length; i++) {
var current = identifier[i];
var previous = identifier[i - 1];
if (current == '_' && previous == '_') continue;
else if (current == '_') {
sb.Append(' ');
}
else if (char.IsLetter(current) && previous == '_') {
sb.Append(char.ToUpperInvariant(current));
}
else if (char.IsDigit(current) && char.IsLetter(previous)) {
sb.Append(' ').Append(current);
}
else if (char.IsLetter(current) && char.IsDigit(previous)) {
sb.Append(' ').Append(char.ToUpperInvariant(current));
}
else if (char.IsUpper(current) && char.IsLower(previous)
&& (i < identifier.Length - 1 && char.IsUpper(identifier[i + 1]) || i == identifier.Length - 1)) {
sb.Append(' ').Append(current);
}
else if (char.IsUpper(current) && i < identifier.Length - 1 && char.IsLower(identifier[i + 1])) {
sb.Append(' ').Append(current);
}
else {
sb.Append(current);
}
}
}
return sb.ToString();
}
}
Tests:
[TestFixture]
static class HelpersTests
{
[Test]
public static void Basic()
{
Assert.AreEqual("Foo", "foo".SplitOnCase());
Assert.AreEqual("Foo", "_foo".SplitOnCase());
Assert.AreEqual("Foo", "__foo".SplitOnCase());
Assert.AreEqual("Foo", "___foo".SplitOnCase());
Assert.AreEqual("Foo 2", "foo2".SplitOnCase());
Assert.AreEqual("Foo 23", "foo23".SplitOnCase());
Assert.AreEqual("Foo 23 A", "foo23A".SplitOnCase());
Assert.AreEqual("Foo 23 Ab", "foo23Ab".SplitOnCase());
Assert.AreEqual("Foo 23 Ab", "foo23_ab".SplitOnCase());
Assert.AreEqual("Foo 23 Ab", "foo23___ab".SplitOnCase());
Assert.AreEqual("Foo 23", "foo__23".SplitOnCase());
Assert.AreEqual("Foo Bar", "Foo_bar".SplitOnCase());
Assert.AreEqual("Foo Bar", "Foo____bar".SplitOnCase());
Assert.AreEqual("AAA", "AAA".SplitOnCase());
Assert.AreEqual("Foo A Aa", "fooAAa".SplitOnCase());
Assert.AreEqual("Foo AAA", "fooAAA".SplitOnCase());
Assert.AreEqual("Foo Bar", "FooBar".SplitOnCase());
Assert.AreEqual("Mn M", "MnM".SplitOnCase());
Assert.AreEqual("AS", "aS".SplitOnCase());
Assert.AreEqual("As", "as".SplitOnCase());
Assert.AreEqual("A", "a".SplitOnCase());
Assert.AreEqual("_", "_".SplitOnCase());
}
}
Simple version similar to some of the above, but with logic to not auto-insert the separator (which is by default, a space, but can be any char) if there's already one at the current position.
Uses a StringBuilder rather than 'mutating' strings.
public static string SeparateCamelCase(this string value, char separator = ' ') {
var sb = new StringBuilder();
var lastChar = separator;
foreach (var currentChar in value) {
if (char.IsUpper(currentChar) && lastChar != separator)
sb.Append(separator);
sb.Append(currentChar);
lastChar = currentChar;
}
return sb.ToString();
}
Example:
Input : 'ThisIsATest'
Output : 'This Is A Test'
Input : 'This IsATest'
Output : 'This Is A Test' (Note: Still only one space between 'This' and 'Is')
Input : 'ThisIsATest' (with separator '_')
Output : 'This_Is_A_Test'
Try this:
using System;
using System.Linq;
using System.Collections.Generic;
public class Program
{
public static void Main()
{
Console
.WriteLine(
SeparateByCamelCase("TestString") == "Test String" // True
);
}
public static string SeparateByCamelCase(string str)
{
return String.Join(" ", SplitByCamelCase(str));
}
public static IEnumerable<string> SplitByCamelCase(string str)
{
if (str.Length == 0)
return new List<string>();
return
new List<string>
{
Head(str)
}
.Concat(
SplitByCamelCase(
Tail(str)
)
);
}
public static string Head(string str)
{
return new String(
str
.Take(1)
.Concat(
str
.Skip(1)
.TakeWhile(IsLower)
)
.ToArray()
);
}
public static string Tail(string str)
{
return new String(
str
.Skip(
Head(str).Length
)
.ToArray()
);
}
public static bool IsLower(char ch)
{
return ch >= 'a' && ch <= 'z';
}
}
See sample online