We Keep Coding

How to parse nested parenthesis only in first level in C#

I would like to write C# code that parses nested parenthesis to array elements, but only on first level. An example is needed for sure:
I want this string:
"(example (to (parsing nested paren) but) (first lvl only))"
tp be parsed into:
["example", "(to (parsing nested paren) but)", "(first lvl only)"]
I was thinking about using regex but can't figure out how to properly use them without implementing this behaviour from scratch.
In the case of malformed inputs I would like to return an empty array, or an array ["error"]

I developed a parser for your example. I also checked some other examples which you can see in the code.
using System;
using System.Collections;
using System.Collections.Generic;
public class Program
{
public static void Main()
{
string str = "(example (to (parsing nested paren) but) (first lvl only))"; // => [example , (to (parsing nested paren) but) , (first lvl only)]
//string str = "(first)(second)(third)"; // => [first , second , third]
//string str = "(first(second)third)"; // => [first , (second) , third]
//string str = "(first(second)(third)fourth)"; // => [first , (second) , (third) , fourth]
//string str = "(first((second)(third))fourth)"; // => [first , ((second)(third)) , fourth]
//string str = "just Text"; // => [ERROR]
//string str = "start with Text (first , second)"; // => [ERROR]
//string str = "(first , second) end with text"; // => [ERROR]
//string str = ""; // => [ERROR]
//string str = "("; // => [ERROR]
//string str = "(first()(second)(third))fourth)"; // => [ERROR]
//string str = "(((extra close pareanthese))))"; // => [ERROR]
var res = Parser.parse(str);
showRes(res);
}
static void showRes(ArrayList res)
{
var strings = res.ToArray();
var theString = string.Join(" , ", strings);
Console.WriteLine("[" + theString + "]");
}
}
public class Parser
{
static Dictionary<TokenType, TokenType> getRules()
{
var rules = new Dictionary<TokenType, TokenType>();
rules.Add(TokenType.OPEN_PARENTHESE, TokenType.START | TokenType.OPEN_PARENTHESE | TokenType.CLOSE_PARENTHESE | TokenType.SIMPLE_TEXT);
rules.Add(TokenType.CLOSE_PARENTHESE, TokenType.SIMPLE_TEXT | TokenType.CLOSE_PARENTHESE);
rules.Add(TokenType.SIMPLE_TEXT, TokenType.SIMPLE_TEXT | TokenType.CLOSE_PARENTHESE | TokenType.OPEN_PARENTHESE);
rules.Add(TokenType.END, TokenType.CLOSE_PARENTHESE);
return rules;
}
static bool isValid(Token prev, Token cur)
{
var rules = Parser.getRules();
return rules.ContainsKey(cur.type) && ((prev.type & rules[cur.type]) == prev.type);
}
public static ArrayList parse(string sourceText)
{
ArrayList result = new ArrayList();
int openParenthesesCount = 0;
Lexer lexer = new Lexer(sourceText);
Token prevToken = lexer.getStartToken();
Token currentToken = lexer.readNextToken();
string tmpText = "";
while (currentToken.type != TokenType.END)
{
if (currentToken.type == TokenType.OPEN_PARENTHESE)
{
openParenthesesCount++;
if (openParenthesesCount > 1)
{
tmpText += currentToken.token;
}
}
else if (currentToken.type == TokenType.CLOSE_PARENTHESE)
{
openParenthesesCount--;
if (openParenthesesCount < 0)
{
return Parser.Error();
}
if (openParenthesesCount > 0)
{
tmpText += currentToken.token;
}
}
else if (currentToken.type == TokenType.SIMPLE_TEXT)
{
tmpText += currentToken.token;
}
if (!Parser.isValid(prevToken, currentToken))
{
return Parser.Error();
}
if (openParenthesesCount == 1 && tmpText.Trim() != "")
{
result.Add(tmpText);
tmpText = "";
}
prevToken = currentToken;
currentToken = lexer.readNextToken();
}
if (openParenthesesCount != 0)
{
return Parser.Error();
}
if (!Parser.isValid(prevToken, currentToken))
{
return Parser.Error();
}
if (tmpText.Trim() != "")
{
result.Add(tmpText);
}
return result;
}
static ArrayList Error()
{
var er = new ArrayList();
er.Add("ERROR");
return er;
}
}
class Lexer
{
string _txt;
int _index;
public Lexer(string text)
{
this._index = 0;
this._txt = text;
}
public Token getStartToken()
{
return new Token(-1, TokenType.START, "");
}
public Token readNextToken()
{
if (this._index >= this._txt.Length)
{
return new Token(-1, TokenType.END, "");
}
Token t = null;
string txt = "";
if (this._txt[this._index] == '(')
{
txt = "(";
t = new Token(this._index, TokenType.OPEN_PARENTHESE, txt);
}
else if (this._txt[this._index] == ')')
{
txt = ")";
t = new Token(this._index, TokenType.CLOSE_PARENTHESE, txt);
}
else
{
txt = this._readText();
t = new Token(this._index, TokenType.SIMPLE_TEXT, txt);
}
this._index += txt.Length;
return t;
}
private string _readText()
{
string txt = "";
int i = this._index;
while (i < this._txt.Length && this._txt[i] != '(' && this._txt[i] != ')')
{
txt = txt + this._txt[i];
i++;
}
return txt;
}
}
class Token
{
public int position
{
get;
private set;
}
public TokenType type
{
get;
private set;
}
public string token
{
get;
private set;
}
public Token(int position, TokenType type, string token)
{
this.position = position;
this.type = type;
this.token = token;
}
}
[Flags]
enum TokenType
{
START = 1,
OPEN_PARENTHESE = 2,
SIMPLE_TEXT = 4,
CLOSE_PARENTHESE = 8,
END = 16
}

well, regex will do the job:
var text = #"(example (to (parsing nested paren) but) (first lvl only))";
var pattern = #"\(([\w\s]+) (\([\w\s]+ \([\w\s]+\) [\w\s]+\)) (\([\w\s]+\))\)*";
try
{
Regex r = new Regex(pattern, RegexOptions.IgnoreCase);
Match m = r.Match(text);
string group_1 = m.Groups[1].Value; //example
string group_2 = m.Groups[2].Value; //(to (parsing nested paren) but)
string group_3 = m.Groups[3].Value; //(first lvl only)
return new string[]{group_1,group_2,group_3};
}
catch(Exception ex){
return new string[]{"error"};
}
hopefully this helps, tested here in dotnetfiddle
Edit:
this might get you started into building the right expression according to whatever patterns you are falling into and maybe build a recursive function to parse the rest into the desired output :)

RegEx is not recursive. You either count bracket level, or recurse.
An non-recursive parser loop I tested for the example you show is..
string SplitFirstLevel(string s)
{
List<string> result = new List<string>();
int p = 0, level = 0;
for (int i = 0; i < s.Length; i++)
{
if (s[i] == '(')
{
level++;
if (level == 1) p = i + 1;
if (level == 2)
{
result.Add('"' + s.Substring(p, i - p) + '"');
p = i;
}
}
if (s[i] == ')')
if (--level == 0)
result.Add('"' + s.Substring(p, i - p) + '"');
}
return "[" + String.Join(",", result) + "]";
}
Note: after some more testing, I see your specification is unclear. How to delimit orphaned level 1 terms, that is terms without bracketing ?
For example, my parser translates
(example (to (parsing nested paren) but) (first lvl only))
to:
["example ","(to (parsing nested paren) but) ","(first lvl only)"]
and
(example (to (parsing nested paren)) but (first lvl only))
to:
["example ","(to (parsing nested paren)) but ","(first lvl only)"]
In either case, "example" gets a separate term, while "but" is grouped with the first term. In the first example this is logical, it is in the bracketing, but it may be unwanted behaviour in the second case, where "but" should be separated, like "example", which also has no bracketing (?)

C# Character encoding issues

I'm trying to make a transport agent that parses the body of an email to find the pertinent pieces of information and replaces the generic subject line with specific details. My problem is that a subject line that should read like:
ABC Co Error: No status reason code (0123456)
instead shows up as
A B C C o E r r o r : N o s t a t u s r e a s o n c o d e ( 0 1 2 3 4 5 6 )
The email is plain text and encoded in us-ascii according to the email header. My problem is that It is my understanding from this question and this question that C# uses UTF-16 as the default string encoding. The spaces between each character lead me to believe that my code is somehow implicitly converting the ASCII to UTF-16, but I don't know where this would be happening. Any ideas on how to make this work properly?
void OnSubmittedMessageHandler(SubmittedMessageEventSource source, QueuedMessageEventArgs args)
{
this.mailItem = args.MailItem;
for (int intCounter = this.mailItem.Recipients.Count - 1; intCounter >= 0; intCounter--)
{
// Check if the email was sent to automated#mydomain.com
string msgRecipientP1 = this.mailItem.Recipients[intCounter].Address.LocalPart;
if (msgRecipientP1.ToLower() == "automated")
{
// Read the body of the email
string line = "";
Dictionary<string, string> EDIErrors = new Dictionary<string, string>();
Body body = this.mailItem.Message.Body;
Stream originalBodyContent = body.GetContentReadStream();
StreamReader streamReader = new StreamReader(originalBodyContent, System.Text.Encoding.ASCII, true);
while ((line = streamReader.ReadLine()) != null)
{
if (line.IndexOf("Partner:") > 0)
{
line.Replace(": ", ":");
string[] lineParts = line.Split(new[] { " " }, StringSplitOptions.None);
foreach (string EDIErrorPart in lineParts)
{
int idx = EDIErrorPart.IndexOf(':');
int qidx = EDIErrorPart.IndexOf('"');
if (idx > 0)
{
EDIErrors[EDIErrorPart.Substring(0, idx).ToLower()] = EDIErrorPart.Substring(idx + 1).ToLower();
}
else if (qidx > 0)
{
EDIErrors["Message"] = EDIErrorPart.Replace("\"", string.Empty);
}
}
}
}
if (originalBodyContent != null)
{
originalBodyContent.Close();
}
// Build the new Subject line and the recipient groups
string sOrder;
string sMessage;
string sDistroGroup;
EDIErrors.TryGetValue("Order", out sOrder);
EDIErrors.TryGetValue("Message", out sMessage);
EDIErrors.TryGetValue("Partner", out sDistroGroup);
string NewSubject = sPartner + " Error: " + sMessage + "(" + sOrder + ")";
this.mailItem.Message.Subject = NewSubject;
if (IsTicketable)
{
this.mailItem.Recipients.Add(new RoutingAddress("helpdesk#mydomain.com"));
}
}
}
return;
}

How to Get Data from index of String

I'm new in c#. and I have some Question...
I have String following this code
string taxNumber = "1222233333445";
I want to get data from This string like that
string a = "1"
string b = "2222"
string c = "33333"
string d = "44"
string e = "5"
Please Tell me about Method for get Data From String.
Thank You Very Much ^^

Use the String.Substring(int index, int length) method
string a = taxNumber.Substring(0, 1);
string b = taxNumber.Substring(1, 4);
// etc

Oh well, the best I can come up with is this:
IEnumerable<string> numbers
= taxNumber.ToCharArray()
.Distinct()
.Select(c => new string(c, taxNumber.Count(t => t == c)));
foreach (string numberGroup in numbers)
{
Console.WriteLine(numberGroup);
}
Outputs:
1
2222
33333
44
5

This can also do , you dont need to fix the no of characters, you can check by changing the no of 1's , 2's etc
string taxNumber = "1222233333445";
string s1 = taxNumber.Substring(taxNumber.IndexOf("1"), ((taxNumber.Length - taxNumber.IndexOf("1")) - (taxNumber.Length - taxNumber.LastIndexOf("1"))) + 1);
string s2 = taxNumber.Substring(taxNumber.IndexOf("2"), ((taxNumber.Length - taxNumber.IndexOf("2")) - (taxNumber.Length - taxNumber.LastIndexOf("2"))) + 1);
string s3 = taxNumber.Substring(taxNumber.IndexOf("3"), ((taxNumber.Length - taxNumber.IndexOf("3")) - (taxNumber.Length - taxNumber.LastIndexOf("3"))) + 1);

You can use Char.IsDigit to identify digits out of string, and may apply further logic as follows:
for (int i=0; i< taxNumber.Length; i++)
{
if (Char.IsDigit(taxNumber[i]))
{
if(taxNumber[i-1]==taxNumber[i])
{
/*Further assign values*/
}
}

Try this Code
string taxNumber = "1222233333445";
char[] aa = taxNumber.ToCharArray();
List<string> finals = new List<string>();
string temp = string.Empty;
for (int i = 0; i < aa.Length; i++)
{
if (i == 0)
{
temp = aa[i].ToString();
}
else
{
if (aa[i].ToString() == aa[i - 1].ToString())
{
temp += aa[i];
}
else
{
if (temp != string.Empty)
{
finals.Add(temp);
temp = aa[i].ToString();
}
}
if (i == aa.Length - 1)
{
if (aa[i].ToString() != aa[i - 1].ToString())
{
temp = aa[i].ToString();
finals.Add(temp);
}
else
{
finals.Add(temp);
}
}
}
}
and check value of finals string list

you may use regex:
string strRegex = #"(1+|2+|3+|4+|5+|6+|7+|8+|9+|0+)";
RegexOptions myRegexOptions = RegexOptions.None;
Regex myRegex = new Regex(strRegex, myRegexOptions);
string strTargetString = #"1222233333445";
return myRegex.Split(strTargetString);

How can i remove ids one by one from querystring in asp.net using c#?

I want remove "ids"one by one querystring from my url. How can i do this ? (using Asp.net4.0 , c#)
Default.aspx?ids=10,2,6,5
I want to remove"ids=6", but language would be the first,middle or last, so I will have this :
Default.aspx?ids=10,2,5,

Step 1. Have your ids in an array by:-
string[] idsarray = Request.QueryString["ids"].ToString().Split(',');
step 2. create a function to remove as per your language
string removeidat(string[] id, string at)
{
string toren = "";
int remat = -1;
if (at=="first")
{
remat = 0;
}
else if (at == "middle")
{
remat = id.Length / 2;
}
else
{
remat = id.GetUpperBound(0);
}
for (int i = 0; i < id.GetUpperBound(0); i++)
{
if (i!=remat)
{
toren += id[i] + ",";
}
}
if (toren.Length>0)
{
toren = toren.Substring(0, toren.Length - 1);
}
return toren;
}
Example : if you want to remove last id your code would be
string[] idsarray = Request.QueryString["ids"].ToString().Split(',');
string newids = removeidat(idsarray , "last")

string strIDs = Request.QueryString["ids"];
if(strIDs != null)
{
string[] ids = strIDs.Split(new[]{','}, StringSplitOptions.RemoveEmptyEntries);
var no6 = ids.Where(id => id != "6");
string newUrl = string.Format("Default.aspx?ids={0}", string.Join(",", no6));
Response.Redirect(newUrl);
}

Getting rid of *consecutive* periods in a filename

I was wondering how I'd get rid of periods in a filename if i have a filename like:
Test....1.txt to look like Test 1.txt ? I do NOT want files like : 1.0.1 Test.txt to be touched. Only files with consecutive periods should be replaced with a space. Any ideas?
This is my current code but as you can see, it replaces every period aside from periods in extension names:
public void DoublepCleanUp(List<string> doublepFiles)
{
Regex regExPattern2 = new Regex(#"\s{2,}");
Regex regExPattern4 = new Regex(#"\.+");
Regex regExPattern3 = new Regex(#"\.(?=.*\.)");
string replace = " ";
List<string> doublep = new List<string>();
var filesCount = new Dictionary<string, int>();
try
{
foreach (string invalidFiles in doublepFiles)
{
string fileOnly = System.IO.Path.GetFileName(invalidFiles);
string pathOnly = System.IO.Path.GetDirectoryName(fileOnly);
if (!System.IO.File.Exists(fileOnly))
{
string filewithDoublePName = System.IO.Path.GetFileName(invalidFiles);
string doublepPath = System.IO.Path.GetDirectoryName(invalidFiles);
string name = System.IO.Path.GetFileNameWithoutExtension(invalidFiles);
//string newName = name.Replace(".", " ");
string newName = regExPattern4.Replace(name, replace);
string newName2 = regExPattern2.Replace(newName, replace);
string filesDir = System.IO.Path.GetDirectoryName(invalidFiles);
string fileExt = System.IO.Path.GetExtension(invalidFiles);
string fileWithExt = newName2 + fileExt;
string newPath = System.IO.Path.Combine(filesDir, fileWithExt);
System.IO.File.Move(invalidFiles, newPath);
DataGridViewRow clean = new DataGridViewRow();
clean.CreateCells(dataGridView1);
clean.Cells[0].Value = doublepPath;
clean.Cells[1].Value = filewithDoublePName;
clean.Cells[2].Value = fileWithExt;
dataGridView1.Rows.Add(clean);
}
else
{
if (filesCount.ContainsKey(fileOnly))
{
filesCount[fileOnly]++;
}
else
{
filesCount.Add(fileOnly, 1);
string newFileName = String.Format("{0}{1}{2}",
System.IO.Path.GetFileNameWithoutExtension(fileOnly),
filesCount[fileOnly].ToString(),
System.IO.Path.GetExtension(fileOnly));
string newFilePath = System.IO.Path.Combine(System.IO.Path.GetDirectoryName(fileOnly), newFileName);
System.IO.File.Move(fileOnly, newFilePath);
DataGridViewRow clean = new DataGridViewRow();
clean.CreateCells(dataGridView1);
clean.Cells[0].Value = pathOnly;
clean.Cells[1].Value = fileOnly;
clean.Cells[2].Value = newFileName;
dataGridView1.Rows.Add(clean);
}
}
}
}
catch(Exception e)
{
//throw;
StreamWriter doublepcleanup = new StreamWriter(#"G:\DoublePeriodCleanup_Errors.txt");
doublepcleanup.Write("Double Period Error: " + e + "\r\n");
doublepcleanup.Close();
}
}

string name = "Text...1.txt";
Regex r = new Regex("[.][.]+");
string result = r.Replace(name, " ");

Well, to do that with a string:
string st = "asdf..asdf...asfd...asdf.asf.asdf.s.s";
Regex r = new Regex("\\.\\.+");
st = r.Replace(st, " ");
This will replace any instance of 2 or more '.'s with a space.
I would throw this into a method:
public static string StringReplace(string original,
string regexMatch, string replacement) {
Regex r = new Regex(regexMatch);
return r.Replace(original, replacement);
}

How about this?
string newFileName = String.Join(".", fileName.Split('.').Select(p => !String.IsNullOrEmpty(p) ? p : " ").ToArray())

Why not use something like this?
string newName = name;
while (newName.IndexOf("..") != -1)
newName = newName.Replace("..", " ");

static string CleanUpPeriods(string filename)
{
StringBuilder sb = new StringBuilder();
if (filename.Length > 0) sb.Append(filename[0]);
for (int i = 1; i < filename.Length; i++)
{
char last = filename[i - 1];
char current = filename[i];
if (current != '.' || last != '.') sb.Append(current);
}
return sb.ToString();
}

You could use use regular expressions, something like this
string fileName = new Regex(#"[.][.]+").Replace(oldFileName, "");

Continuing from dark_charlie's solution, isn't
string newName = name;
while (newName.IndexOf("..") != -1)
newName = newName.Replace("..", ".");
enough?

I have tested this code on a number of cases, and it appears to exhibit the requested behavior.
private static string RemoveExcessPeriods(string text)
{
if (string.IsNullOrEmpty(text))
return string.Empty;
// If there are no consecutive periods, then just get out of here.
if (!text.Contains(".."))
return text;
// To keep things simple, let's separate the file name from its extension.
string extension = Path.GetExtension(text);
string fileName = Path.GetFileNameWithoutExtension(text);
StringBuilder result = new StringBuilder(text.Length);
bool lastCharacterWasPeriod = false;
bool thisCharacterIsPeriod = fileName.Length > 0 && fileName[0] == '.';
bool nextCharacterIsPeriod;
for (int index = 0; index < fileName.Length; index++)
{
// Includes both the extension separator and other periods.
nextCharacterIsPeriod = fileName.Length == index + 1 || fileName[index + 1] == '.';
if (!thisCharacterIsPeriod)
result.Append(fileName[index]);
else if (thisCharacterIsPeriod && !lastCharacterWasPeriod && !nextCharacterIsPeriod)
result.Append('.');
else if (thisCharacterIsPeriod && !lastCharacterWasPeriod)
result.Append(' ');
lastCharacterWasPeriod = thisCharacterIsPeriod;
thisCharacterIsPeriod = nextCharacterIsPeriod;
}
return result.ToString() + extension;
}
I just made a change to handle some edge cases. Here are some test results for this version.
"Test....1.txt" => "Test 1.txt"
"1.0.1..Test.txt" => "1.0.1 Test.txt"
"Test......jpg" => "Test .jpg"
"Test.....jpg" => "Test .jpg"
"one.pic.jpg" => "one.pic.jpg"
"one..pic.jpg" => "one pic.jpg"
"one..two..three.pic.jpg" => "one two three.pic.jpg"
"one...two..three.pic.jpg" => "one two three.pic.jpg"
"one..two..three.pic..jpg" => "one two three.pic .jpg"
"one..two..three..pic.jpg" => "one two three pic.jpg"
"one..two..three...pic...jpg" => "one two three pic .jpg"

Combining some other answers...
static string CleanUpPeriods(string filename)
{
string extension = Path.GetExtension(filename);
string name = Path.GetFileNameWithoutExtension(filename);
Regex regex = new Regex(#"\.\.+");
string s = regex.Replace(name, " ").Trim();
if (s.EndsWith(".")) s = s.Substring(0, s.Length - 1);
return s + extension;
}
Sample Output
"Test........jpg" -> "Test.jpg"
"Test....1.jpg" -> "Test 1.jpg"
"Test 1.0.1.jpg" -> "Test 1.0.1.jpg"
"Test..jpg" -> "Test.jpg"

void ReplaceConsecutive(string src, int lenght, string replace)
{
char last;
int count = 0;
StringBuilder ret = new StringBuilder();
StringBuilder add = new StringBuilder();
foreach (char now in src)
{
if (now == last)
{
add.Append(now);
if (count > lenght)
{
ret.Append(replace);
add = new StringBuilder();
}
count++;
}
else
{
ret.Append(add);
add = new StringBuilder();
count = 0;
ret.Append(now);
}
}
return ret.ToString();
}
Untested, but this should work.
src is the string you want to check for consecutives, lenght is the number of equal chars followed by each other until they get replaced with replace.
This is AFAIK also possible in Regex, but I'm not that good with Regex's that I could do this.