Develop Reference

Find the maximum length of every column in a csv file

So, I was trying to present a csv document in a console application. However, due to the varying text size in it, the output was not in a presentable format.
To present it, I tried to count the maximum length of text for each column and then append white space to the remaining text in that column so that there's equal length of characters in each column.
I tried to get the character count, but can't seem to figure out how to proceed further.
var file = File.ReadAllLines(#"E:\File.csv");
var lineList = file.Select(x => x.Split(',').ToList()).ToList();
int maxColumn = lineList.Select(x => x.Count).Max(x => x);
List<int> maxElementSize = new List<int>();
for (int i = 0; i < maxColumn; i++)
{
//Some Logic
}
Any help would be highly appreciated.

Here's a sample console application to get maximum character length for each column :
static void Main(string[] args)
{
string CSVPath = #"D:\test.csv";
string outputText = "";
using (var reader = File.OpenText(CSVPath))
{
outputText = reader.ReadToEnd();
}
var colSplitter = ',';
var rowSplitter = new char[] { '\n' };
var rows = (from row in outputText.Split(rowSplitter, StringSplitOptions.RemoveEmptyEntries)
let cols = row.Split(colSplitter)
from col in cols
select new { totalCols = cols.Count(), cols = cols }).ToList();
int[] maxColLengths = new int[rows.Max(o => o.totalCols)];
for (int i = 0; i < rows.Count; i++)
{
for (int j = 0; j < rows[i].cols.Count(); j++)
{
int curLength = rows[i].cols[j].Trim().Length;
if (curLength > maxColLengths[j])
maxColLengths[j] = curLength;
}
}
Console.WriteLine(string.Join(", ", maxColLengths));
}
Hope this helped.

Try with a nested for loop:
var inputLines = File.ReadAllLines(#"E:\File.csv");
Dictionary<int,int> dictIndexLenght = new Dictionary<int,int>();
foreach(var line in inputLines)
{
List<string> columList = line.Split(',').ToList();
for (int i = 0; i < columList.Count; i++)
{
int tempVal = 0;
if(dictIndexLenght.TryGetValue(i,out tempVal))
{
if(tempVal<columList[i].Length)
{
dictIndexLenght[i]=columList[i].Length;
}
}
else
dictIndexLenght[i]=columList[i].Length;
}
}
Can check the result here or with this lines of code:
for(int i=0;i<dictIndexLenght.Count;i++)
{
Console.WriteLine("Column {0} : {1}", i, dictIndexLenght[i]);
}

Here's how I would do it, very similar to un-lucky's answer, only using a List<int> instead of a Dictionary<int, int>. I added dummy data for testing, but you can see the actual call to read the file is left in there, so you can just remove the dummy data and the line that reads it, and it should work ok:
static void Main(string[] args)
{
var fileLines = new List<string>
{
"Lorem, Ipsum, is, simply, dummy, text, of, the, printing, and, typesetting,",
"industry., Lorem, Ipsum, has, been, the, industry's, standard, dummy, text,",
"ever, since, the, 1500s, when, an, ",
"unknown, printer, took, a, galley, of, type, and, scrambled, it, to, make,",
"a, type, specimen, book.,",
"It, has, survived, not, only, five, centuries, but, also, the, leap,",
"into, electronic, typesetting, remaining, essentially, unchanged.,",
"It, was, popularised, in, the, 1960s, with, the, release,",
"of, Letraset, sheets, containing, Lorem, Ipsum, passages, and, more, ",
"recently, with, desktop, publishing,",
"software, like, Aldus, PageMaker, including, versions, of, Lorem, Ipsum."
};
var filePath = #"f:\public\temp\temp.csv";
var fileLinesColumns = File.ReadAllLines(filePath).Select(line => line.Split(','));
var colWidths = new List<int>();
// Remove this line to use file data
fileLinesColumns = fileLines.Select(line => line.Split(','));
// Get the max length of each column and add it to our list
foreach (var fileLineColumns in fileLinesColumns)
{
for (int i = 0; i < fileLineColumns.Length; i++)
{
if (i > colWidths.Count - 1)
{
colWidths.Add(fileLineColumns[i].Length);
}
else if (fileLineColumns[i].Length > colWidths[i])
{
colWidths[i] = fileLineColumns[i].Length;
}
}
}
// Write out our columns, padding each one to match the longest line
foreach (var fileLineColumns in fileLinesColumns)
{
for (int i = 0; i < fileLineColumns.Length; i++)
{
Console.Write(fileLineColumns[i].PadRight(colWidths[i]));
}
Console.WriteLine();
}
Console.Write("\nDone!\nPress any key to exit...");
Console.ReadKey();
}
Output

Initialise your list, then loop over your lines, and within that line, loop over your columns:
for (i = 0; i < lineList.Count; i++)
{
maxElementSize[i] = 0;
}
for (i = 0; i < lineList.Count; i++)
{
for (j = 0; j < maxColumn; j++)
{
if(lineList[i][j].Length > maxElementSize[j])
maxElementSize[j] = lineList[i][j].Length
}
}

I use the following code to make sure the columns in a database are large enough to take the csv input data...
#!/usr/bin/python3
import array as arr
from csv import reader
import argparse
def csv_getFldLens (in_file, has_header=0, delimiter=','):
# open file in read mode
fldMaxLens = arr.array('i')
headers = []
has_header = has_header
with open(in_file, 'r') as read_obj:
# pass the file object to reader() to get the reader object
csv_reader = reader(read_obj, delimiter=delimiter)
# Iterate over each row in the csv using reader object
rcnt = 0
lastIndx = 0
for row in csv_reader:
# row variable is a list that represents a row in csv
# print(row)
if has_header and rcnt == 0:
for fld in row:
headers.append(fld)
rcnt += 1
continue
j = 0
for fld in row:
fldLen = len(fld)
if (lastIndx == 0) or (lastIndx < j):
# print("if --- li, i: ", lastIndx, i, "\n")
fldMaxLens.append(fldLen)
lastIndx = j
else:
# print("else --- li, i: ", lastIndx, i, "\n")
v1 = fldMaxLens[j]
v2 = fldLen
fldMaxLens[j] = max(v1,v2)
j = j + 1
rcnt += 1
j = 0
if has_header:
for f in headers:
print(f,": ", fldMaxLens[j])
j += 1
else:
for i in fldMaxLens:
print("Col[",j+1,"]: ",fldMaxLens[j])
j += 1
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Get column lengths of CVS fields.')
parser.add_argument('--in_file', default='', help='The CSV input file')
parser.add_argument('--has_header', action='store_true', help='The CSV file has headers')
parser.add_argument('--delimiter', default=',', help='Sets the delimiter. Default is comma \',\'.')
args = parser.parse_args()
csv_getFldLens(in_file=args.in_file, has_header=args.has_header, delimiter=args.delimiter)

StreamWriter C# formatting output

Problem Statement
In order to run gene annotation software, I need to prepare two types of files, vcard files and coverage tables, and there has to be one-to-one match of vcard to coverage table. Since Im running 2k samples, its hard to identify which file is not one-to-one match. I know that both files have unique identifier numbers, hence, if both folders have files that have same unique numbers, i treat that as "same" file
I made a program that compares two folders and reports unique entries in each folder. To do so, I made two list that contains unique file names to each directory.
I want to format the report file (tab delimited .txt file) such that it looks something like below:
Unique in fdr1 Unique in fdr2
file x file a
file y file b
file z file c
I find this difficult to do because I have to iterate twice (since I have two lists), but there is no way of going back to the previous line in StreamWriter as far as I know. Basically, once I iterate through the first list and fill the first column, how can I fill the second column with the second list?
Can someone help me out with this?
Thanks
If design of the code has to change (i.e. one list instead of two), please let me know
As requested by some user, this is how I was going to do (not working version)
// Write report
using (StreamWriter sw = new StreamWriter(dest_txt.Text + #"\" + "Report.txt"))
{
// Write headers
sw.WriteLine("Unique Entries in Folder1" + "\t" + "Unique Entries in Folder2");
// Write unique entries in fdr1
foreach(string file in fdr1FileList)
{
sw.WriteLine(file + "\t");
}
// Write unique entries in fdr2
foreach (string file in fdr2FileList)
{
sw.WriteLine(file + "\t");
}
sw.Dispose();
}
As requested for my approach for finding unique entries, here's my code snippet
Dictionary<int, bool> fdr1Dict = new Dictionary<int, bool>();
Dictionary<int, bool> fdr2Dict = new Dictionary<int, bool>();
List<string> fdr1FileList = new List<string>();
List<string> fdr2FileList = new List<string>();
string fdr1Path = folder1_txt.Text;
string fdr2Path = folder2_txt.Text;
// File names in the specified directory; path not included
string[] fdr1FileNames = Directory.GetFiles(fdr1Path).Select(Path.GetFileName).ToArray();
string[] fdr2FileNames = Directory.GetFiles(fdr2Path).Select(Path.GetFileName).ToArray();
// Iterate through the first directory, and add GL number to dictionary
for(int i = 0; i < fdr1FileNames.Length; i++)
{
// Grabs only the number from the file name
string number = Regex.Match(fdr1FileNames[i], #"\d+").ToString();
int glNumber;
// Make sure it is a number
if(Int32.TryParse(number, out glNumber))
{
fdr1Dict[glNumber] = true;
}
// If number not present, raise exception
else
{
throw new Exception(String.Format("GL Number not found in: {0}", fdr1FileNames[i]));
}
}
// Iterate through the second directory, and add GL number to dictionary
for (int i = 0; i < fdr2FileNames.Length; i++)
{
// Grabs only the number from the file name
string number = Regex.Match(fdr2FileNames[i], #"\d+").ToString();
int glNumber;
// Make sure it is a number
if (Int32.TryParse(number, out glNumber))
{
fdr2Dict[glNumber] = true;
}
// If number not present, raise exception
else
{
throw new Exception(String.Format("GL Number not found in: {0}", fdr2FileNames[i]));
}
}
// Iterate through the first directory, and find files that are unique to it
for (int i = 0; i < fdr1FileNames.Length; i++)
{
int glNumber = Int32.Parse(Regex.Match(fdr1FileNames[i], #"\d+").Value);
// If same file is not present in the second folder add to the list
if(!fdr2Dict[glNumber])
{
fdr1FileList.Add(fdr1FileNames[i]);
}
}
// Iterate through the second directory, and find files that are unique to it
for (int i = 0; i < fdr2FileNames.Length; i++)
{
int glNumber = Int32.Parse(Regex.Match(fdr2FileNames[i], #"\d+").Value);
// If same file is not present in the first folder add to the list
if (!fdr1Dict[glNumber])
{
fdr2FileList.Add(fdr2FileNames[i]);
}

I am a quite confident that this will work as I've tested it:
static void Main(string[] args)
{
var firstDir = #"Path1";
var secondDir = #"Path2";
var firstDirFiles = System.IO.Directory.GetFiles(firstDir);
var secondDirFiles = System.IO.Directory.GetFiles(secondDir);
print2Dirs(firstDirFiles, secondDirFiles);
}
private static void print2Dirs(string[] firstDirFile, string[] secondDirFiles)
{
var maxIndex = Math.Max(firstDirFile.Length, secondDirFiles.Length);
using (StreamWriter streamWriter = new StreamWriter("result.txt"))
{
streamWriter.WriteLine(string.Format("{0,-150}{1,-150}", "Unique in fdr1", "Unique in fdr2"));
for (int i = 0; i < maxIndex; i++)
{
streamWriter.WriteLine(string.Format("{0,-150}{1,-150}",
firstDirFile.Length > i ? firstDirFile[i] : string.Empty,
secondDirFiles.Length > i ? secondDirFiles[i] : string.Empty));
}
}
}
It's a quite simple code but if you need help understanding it just let me know :)

I would construct each line at a time. Something like this:
int row = 0;
string[] fdr1FileList = new string[0];
string[] fdr2FileList = new string[0];
while (row < fdr1FileList.Length || row < fdr2FileList.Length)
{
string rowText = "";
rowText += (row >= fdr1FileList.Length ? "\t" : fdr1FileList[row] + "\t");
rowText += (row >= fdr2FileList.Length ? "\t" : fdr2FileList[row]);
row++;
}

Try something like this:
static void Main(string[] args)
{
Dictionary<int, string> fdr1Dict = FilesToDictionary(Directory.GetFiles("path1"));
Dictionary<int, string> fdr2Dict = FilesToDictionary(Directory.GetFiles("path2"));
var unique_f1 = fdr1Dict.Where(f1 => !fdr2Dict.ContainsKey(f1.Key)).ToArray();
var unique_f2 = fdr2Dict.Where(f2 => !fdr1Dict.ContainsKey(f2.Key)).ToArray();
int f1_size = unique_f1.Length;
int f2_size = unique_f2.Length;
int list_length = 0;
if (f1_size > f2_size)
{
list_length = f1_size;
Array.Resize(ref unique_f2, list_length);
}
else
{
list_length = f2_size;
Array.Resize(ref unique_f1, list_length);
}
using (StreamWriter writer = new StreamWriter("output.txt"))
{
writer.WriteLine(string.Format("{0,-30}{1,-30}", "Unique in fdr1", "Unique in fdr2"));
for (int i = 0; i < list_length; i++)
{
writer.WriteLine(string.Format("{0,-30}{1,-30}", unique_f1[i].Value, unique_f2[i].Value));
}
}
}
static Dictionary<int, string> FilesToDictionary(string[] filenames)
{
Dictionary<int, string> dict = new Dictionary<int, string>();
for (int i = 0; i < filenames.Length; i++)
{
int glNumber;
string filename = Path.GetFileName(filenames[i]);
string number = Regex.Match(filename, #"\d+").ToString();
if (int.TryParse(number, out glNumber))
dict.Add(glNumber, filename);
}
return dict;
}

C# DataTable column already exists issue

I'm attempting to import a CSV file into a DataTable, however the CSV contains headers that are the same. (For example, there are multiple "Date" headers for different form sections). To fix this, I decided to create a loop that will run through the headers and replace the duplicates or unwanted entries based on their position. I've replaced my replaceWith array with dummy entries, but my actual code does have the correct size to correlate with the replace array.
string[] columnNames = null;
string[] oStreamDataValues = null;
int[] error = {0,1,2,3,4,7,8,9,10,11,15,21,34,37,57,61,65,68,69,71,75,79,82,83,85,89,93,96,97,99,103,107,110,111,113,117,121,124,125,127,128,129,130,132,182,210,212,213,214,215,216,222,226,239};
int[] replace = {14,16,17,17,20,23,24,27,28,29,31,32,44,58,59,60,62,63,64,66,67,70,72,73,74,76,77,78,80,81,84,86,87,88,90,91,92,94,95,98,100,101,102,104,105,106,108,109,112,114,115,116,118,119,120,122,123,126,134,136,138,140,142,144,146,148,150,152,154,156,158,160,162,164,166,168,170,172,174,176,178,180,184,186,187,188,190,191,192,194,195,196,198,199,200,202,203,204,206,207,208,209,236,242,243,244};
string[] replaceWith = {"Replace 1", "Replace 2", "Replace 3"};
string fix = "ignore_";
int inc = 00;
string entry = "";
while (!oStreamReader.EndOfStream)
{
string oStreamRowData = oStreamReader.ReadLine().Trim();
if (oStreamRowData.Length > 0)
{
//oStreamDataValues = Regex.Split(oStreamRowData, ",(?=(?:[^']*'[^']*')*[^']*$)");
oStreamDataValues = oStreamRowData.Split(',');
if (rowCount == 0)
{
rowCount = 1;
columnNames = oStreamDataValues;
for (int i = 0; i < columnNames.Length; i++)
{
for (int j = 0; j < error.Length; j++)
{
if (error[j] == i)
{
entry = fix + inc++;
}
}
for (int k = 0; k < replace.Length; k++)
{
if (replace[i] == i)
{
int add = 0;
entry = replaceWith[add++];
}
}
DataColumn oDataColumn = new DataColumn(entry, typeof(string));
oDataColumn.DefaultValue = string.Empty;
oDataTable.Columns.Add(oDataColumn);
}
}
}
I'm no coding expert, so my syntax/decision making isn't perfect.
However the error that I get is that A column named 'ignore_4' already belongs to this DataTable.
I assume something is incorrect in my loop logic.

I think you have overcomplicated the loops. You just need to keep an index of the current position in the array of errors and array of replaces.
string rep = "replace_"; // base string for replace fields
string fix = "ignore_"; // base string for ignore fields
// For demonstation purpose I have commented out this array. If you
// want every 'replace' column have its specific name then prepare this
// array with exactly the number of names required by the number of
// elements in the replace array
//
// string[] replaceWith = {"Replace 1", "Replace 2", "Replace 3"};
int idxErrors = 0; // Current position in the error array
int idxReplace = 0; // Current position in the replace array
int fixCounter = 1;
int repCounter = 1;
string entry = "";
for (int i = 0; i < columnNames.Length; i++)
{
// Is this the index of a column that should be ignored?
if (idxErrors < error.Length && i == error[idxErrors])
{
entry = fix + fixCounter.ToString("D2");
idxErrors++;
fixCounter++;
}
// Is this the index of a column that should have a different name??
else if (idxReplace < replace.Length && i == replace[idxReplace])
{
entry = rep + repCounter.ToString("D2");
// entry = replaceWith[repCounter];
idxReplace++;
repCounter++;
}
else
entry = columnNames[i];
// Now create the column
DataColumn oDataColumn = new DataColumn(entry, typeof(string));
oDataColumn.DefaultValue = string.Empty;
oDataTable.Columns.Add(oDataColumn);
}
In this example I have used the same pattern used for the ignored column also for the columns that need to have the name changed. If you want to give each renamed column a proper name, then you need to prepare an array with these proper names and this array should be of the same length of the replace array. Then use the idxReplace to take the correct name from the array of possible proper names.

Array of string not working

I use a simple array: contentHouseOne[] that contains strings. But in the Do/While loop it isn't working! It seems like the code don't understand that it's a string when a new object is to be created!? It works when I hardcode the string like I show below. Help is preciated! Thanks!
This isn't working:
listHouseParts.Add(new HousePart(content, contentHouseOne[i], newPosition));
But this works:
listHouseParts.Add(new HousePart(content, "100x100", newPosition));
EDIT:
Here are some code to declare arrays
string[] contentHouseOne = new string[] { "ruta100x100Red",
"ruta100x100Grey",
"ruta100x100Green",
"ruta100x100Yellow",
"ruta100x100Blue" };
bool[,] occupiedPositions = new bool[500,500];
Here are some code to set all grid positions to false
for (int i = 0; i < gridCol; i++)
for (int ii = 0; ii < gridRow; ii++)
occupiedPositions[i, ii] = false;
And finally here are the code that I have the problem
int i = 0;
do
{
Vector2 newPosition = NewRandomPosition;
if (occupiedPositions[(int)newPosition.X, (int)newPosition.Y] == false)
{
listHouseParts.Add(new HousePart(content,
contentHouseOne[i], newPosition));
occupiedPositions[(int)newPosition.X, (int)newPosition.Y] = true;
i++;
}
}
while (i <= 5);

Your string array includes five elements:
string[] contentHouseOne = new string[] { "ruta100x100Red",
"ruta100x100Grey",
"ruta100x100Green",
"ruta100x100Yellow",
"ruta100x100Blue" };
But your while loop ends if your running variable i is greater than 5
while (i <= 5);
which causes a IndexOutOfBounds exception on contentHouseOne, because the 6th element at index 5 isn't defined.
You should change your while condition to (i < 5).

Try this so atleast you know if its empty or not
HousePart housePart = new HousePart();
housePart.Content = content;
if (!string.IsNullOrEmpty(contentHouseOne[i]))
housePart.ContentHouseOne = contentHouseOne[i];
else
housePart.ContentHouseOne = string.Empty;
housePart.NewPosition = newPosition;
listHouseParts.Add(housePart);

How to implement C# code for Order id separated by commas and range separated by hyphens, and display all info of order

Ex: 1,4-90, 292,123
It needs to display the whole order information of
1
4,5,6....90
292
123.
Whats the gud approach to solve this.
It is similar to tracking in UPS or fedex if multiple orders are given in search box.
I meant if in a search box I giv 1,4-90, 292,123 this string the result that needs to come back is a grid representation of all the data which is corresponding to each of the order id respectively. I want to know how to parse the string into collection and send them to the database and show the information in the grid for...
1
4,5,6....90
292
123.
as a different row...from where I can generate reports too (alternative)

Please try.
static ArrayList list;
static void Main(string[] args)
{
string str = "1,4-90,292,123";
string[] arr = str.Split(',');
list = new ArrayList();
for (int i = 0; i < arr.Length; i++)
{
string tmp = arr[i];
if (tmp.IndexOf('-') != -1)
{
Range(tmp);
}
else list.Add(int.Parse(tmp));
}
list.Sort();
object[] intResult = list.ToArray();
//print the final result
for (int i = 0; i < intResult.Length; i++)
{
Console.WriteLine(intResult[i].ToString());
}
Console.Read();
}
static void Range(string range)
{
string[] tmpArr = range.Split('-');
int stInt = int.Parse(tmpArr[0]);
int edInt = int.Parse(tmpArr[1]);
int[] intArr = new int[(edInt - stInt) + 1];
for (int i = 0; stInt <= edInt; i++)
{
list.Add(stInt++);
}
}