C# csv loaded into datatable missing columns - c#

I've loaded a csv into a datatable but some of the columns are being read as blank when they're not blank. I initially posed this question only having an issue with the header, but I'm now also seeing this issue in my data rows so I need to reask... what is the problem with my dataset and why are some columns being read as a blank?
Currently, this setup will read data for columns 1-7 (I don't need 8-10). Data is populated for all columns correctly except column 4. Strangely, I have two files I've tested, both similar in structure, but one of them has values in column 4 and the other doesn't. The full code is setup to loop through many files, checking for start and end of data, then load to sql server.
Sample CSV:
By OrgID/Location
As of: December 6, 2017 at 10:13 AM
Date Range: summaryYM 2017M08 to 2017M08
"orgid=13778 medType=' '"
"col1","col2","col3","col4","col5","col6","col7","col8","col9","col10"
13778,140242,"2A","2017M08",0,0.058,78,".",".",
13778,140242,"2B","2017M08",0,0.014,19,".",".",
13778,140242,"2C","2017M08",0,0.083,133,".",".",
13778,140242,"2ICU","2017M08",0,0.099,114,".",".",
13778,140242,"3 ICU","2017M08",0,0.076,88,".",".",
code
//open connection to csv
string connStrCsv = string.Format(#"Provider=Microsoft.Jet.OleDb.4.0; Data Source={0};Extended Properties=""Text;HDR=NO;FMT=Delimited"""
, Path.GetDirectoryName(file));
OleDbConnection connCsv = new OleDbConnection(connStrCsv);
connCsv.Open();
//store csv data in datatable
string readCsv = "select * from [" + Path.GetFileName(file) + "]";
OleDbDataAdapter adapter = new OleDbDataAdapter(readCsv, connCsv);
DataSet ds = new DataSet();
adapter.Fill(ds, "sheet1");
DataTable table = ds.Tables["sheet1"];
connCsv.Close();
//find header to define start of data
int start = 0;
StreamReader headerSearch = null;
int incr = 0;
headerSearch = new StreamReader(file);
while (!headerSearch.EndOfStream)
{
incr++;
string line = headerSearch.ReadLine();
if (line.Contains("\"col1\",\"col2\",\"col3\",\"col4\",\"col5\",\"col6\""))
{
start = incr;
}
}
headerSearch.Close();
//load each row of excel into SQL server until first empty row
string sqlConnStr = "Data Source=mysource;Initial Catalog=mydatabase;Trusted_Connection=Yes;Integrated Security=SSPI;";
SqlConnection connSql = new SqlConnection(sqlConnStr);
connSql.Open();
int end = start;
while (table.Rows[end][0].ToString().Length != 0)
{
string sql = string.Format
(#"
delete from schema.table
where ss_col1 = {0}
and ss_col2 = '{1}'
and ss_col3 = '{2}'
and ss_col4 = '{3}';
insert into schema.table
values ({4}
,'{5}'
,'{6}'
,'{7}'
, {8}
,'{9}'
,'{10}'
,getdate()
,user_name()
,getdate()
,user_name());"
//delete statement variables
, table.Rows[end][0].ToString()
, table.Rows[end][2].ToString()
, table.Rows[end][3].ToString()
, infTypes[i]
//insert statement variables
, table.Rows[end][0].ToString()
, table.Rows[end][2].ToString()
, table.Rows[end][3].ToString()
, infTypes[i]
, table.Rows[end][4]
, table.Rows[end][5].ToString()
, table.Rows[end][6]
);
SqlCommand execSql = new SqlCommand(sql, connSql);
execSql.ExecuteNonQuery();
end++;
}
connSql.Close();

Do you have to load it into a datatable?
If "header1","header2","header3","header4","header5","header6" are unique would it not be easier just read the csv file until you find those?
Example...
StreamReader Reader = null;
string FilePath = "Your File Path";
try
{
Reader = new StreamReader(FilePath);
while(Reader.Peek() > 0)
{
string line = Reader.ReadLine();
bool HeaderFound = false;
if(line == "What ever your headers are")
{
HeaderFound = true;
}
if(HeaderFound)
{
//Here is all your data you were looking for.
//Do whatever you need to do with it now.
}
}
} catch(exception e)
{/*Deal with the issues*/}
finally
{
if(Reader != null)
{
Reader.Close();
Reader.Dispose();
}
}

Related

How to add conditional data from a datatable into another datatable. [error: " no row at position 0] . C#

I am new to programming and got this job to create a tool to convert .DBF table into a .csv file.
so here is the scenario;
The dbf table 'Poles' contain four fields 'pole_id', 'guy_hoa_1', 'guy_hoa_2','guy_hoa_3' and 'guy_hoa_4'.
And the final csv file should show the value in two columns only:'PoleId' and 'HOA' respectively, where PoleID will be == pole_id and HOA= guy_hoa_1 + '|' +guy_hoa_2+'|' +guy_hoa_3 +'|'+ guy_hoa_4.
for example, the Poles table will have data like;
Sample data of Poles table
And, the ouput csv file should show data as follows;
Sample Output CSV file
*The pole_id is the main field and based on it the values of other fields will be selected.
So far I managed to write following code:
enter code here
enter code here
string str = textBox1.Text;
string path = str.Substring(0, str.LastIndexOf("\\") + 1);
string conn = "Provider=Microsoft.Jet.OLEDB.4.0; Data Source = '" + path + "';Extended Properties=dBase IV;User ID=Admin;Password=;";
OleDbConnection connection = new OleDbConnection();
connection.ConnectionString = conn;
connection.Open();
CheckConnectionLabel.Text = "Connected Successfully";
OleDbDataAdapter adapter = new OleDbDataAdapter(#"SELECT pole_id, guy_hoa_1, guy_hoa_2,guy_hoa_3,guy_hoa_4 FROM poles" + ".dbf", connection);
DataSet ds = new DataSet();
DataTable dt = new DataTable();
adapter.Fill(dt);
DataTable dt1 = dt.AsEnumerable()
.Where(r=> r.Field<string>("pole_id")!= null)
.Where(r=> r.Field<string>("pole_id")!=" ")
.CopyToDataTable();
DataTable dtTemp = new DataTable();
dtTemp.Columns.Add("PoleId", typeof(String));
dtTemp.Columns.Add("HOA", typeof(string));
string x = string.Empty;
for (int i=0;i< dt1.Rows.Count;i++)
{
if(dt1.Rows[i]["pole_id"]!= null || dt1.Rows[i]["pole_id"].ToString()!= "")
{
if(dt1.Rows[i]["guy_hoa_1"]!=null && dt1.Rows[i]["guy_hoa_1"].ToString()!="")
{
x =dt1.Rows[i]["guy_hoa_1"].ToString();
}
if(dt1.Rows[i]["guy_hoa_2"]!= null && dt1.Rows[i]["guy_hoa_2"].ToString()!="")
{
x = x + "|" + dt1.Rows[i]["guy_hoa_2"].ToString();
}
if(dt1.Rows[i]["guy_hoa_3"]!=null && dt1.Rows[i]["guy_hoa_3"].ToString()!= "")
{
x = x + "|" + dt1.Rows[i]["guy_hoa_3"].ToString();
}
if(dt1.Rows[i]["guy_hoa_4"]!=null && dt1.Rows[i]["guy_hoa_4"].ToString()!= "")
{
x = x + "|" + dt1.Rows[i]["guy_hoa_4"].ToString();
}
dtTemp.Rows[i]["PoleId"] = dt1.Rows[i]["poles_id"].ToString();
dtTemp.Rows[i]["HOA"] = x ;
}
}
connection.Close();
dataGridView1.DataSource = dtTemp;
}
catch (Exception ex)
{
MessageBox.Show("Error " + ex.Message);
}
}
enter code here
So, through above code I am connected to the dbf table and collected required data in 'dt' table. Then I filtered the data by removing the rows where pole_id was blank/null and put it in another 'dt1' table. Now my purpose was to check the conditions in dt1 table and then fill rows in dtTemp table which would later display the data in datagridview.
The Code is fetching the value of x till last IF statement correctly however nothing is getting filled up in dtTemp datatable and then showing this error.
Please help me and let me know where I am wrong... many thanks in advance!!
I got the solution as follows;
enter code here
object y = dt1.Rows[i]["pole_id"].ToString();
dtTemp.NewRow();
dtTemp.Rows.Add(y ,x);

Unidata UniObjects for .NET - Write amendments back to unidata from modified table

I'm trying to write data back into a file on Unidata, after the contents have been adjusted in a datagridview.
I've tried various option based around the code below, but with no luck.
Within the foreach section I want to update my file.
The file consists of 10 single value attributes.
I tried fl.write(),but get an error relating to writing to a null value...
try
{
DataTable modifiedTable = m_DS.Tables[0].GetChanges(DataRowState.Modified);
if (modifiedTable.Rows.Count > 0)
{
U2Connection con = GetConnection();
Console.WriteLine("Connected.................");
UniSession lUniSession = con.UniSession;
UniFile fl = lUniSession.CreateUniFile("myTableName");
UniDynArray udr3 = new UniDynArray(lUniSession);
foreach (DataRow item in modifiedTable.Rows)
{
}
con.Close();
}
}
Thank you for using UniObjects’s API of U2 Toolkit for .NET (formerly known as standalone UO.NET).
Yesterday (June 10th, 2014) , we have Released U2 Toolkit for .NET v2.1.0. Main features of U2 Toolkit for .NET v2.1.0 is
Native Visual Studio Integration
For other features, see this link
http://blog.rocketsoftware.com/2014/05/access-nosql-data-using-sql-syntax-u2-toolkit-net-v2-1-0-beta/
Can you please try the same code ( 10 single value attributes) using SELECT and UPDATE. For your information, SELECT and UPDATE behind the scene calls UniFile Read and Write. These Samples are part of the installation. Go to these directories.
C:\Program Files (x86)\Rocket Software\U2 Toolkit for .NET\U2 Database Provider\samples\C#\UniData\NativeAccess\Select_SQL_Syntax
C:\Program Files (x86)\Rocket Software\U2 Toolkit for .NET\U2 Database Provider\samples\C#\UniData\NativeAccess\Update_SQL_Syntax
SELECT
private static void Select()
{
try
{
Console.WriteLine(Environment.NewLine + "Start...");
ConnectionStringSettingsCollection settings = ConfigurationManager.ConnectionStrings;
ConnectionStringSettings cs = settings["u2_connection"];
U2Connection lConn = new U2Connection();
lConn.ConnectionString = cs.ConnectionString;
lConn.Open();
Console.WriteLine("Connected...");
U2Command cmd = lConn.CreateCommand();
//ID,FNAME,LNAME : Single Value
//SEMESTER: Multi Value
//COURSE_NBR,COURSE_GRD: MS
cmd.CommandText = string.Format("SELECT ID,FNAME,LNAME,SEMESTER,COURSE_NBR,COURSE_GRD FROM STUDENT WHERE ID > 0 ORDER BY ID");
U2DataAdapter da = new U2DataAdapter(cmd);
DataSet ds = new DataSet();
da.Fill(ds);
Console.WriteLine(Environment.NewLine);
ds.WriteXml(Console.Out);
lConn.Close();
Console.WriteLine(Environment.NewLine + "End...");
Console.WriteLine(SUCCESS_MSG);
}
catch (Exception e2)
{
string lErr = e2.Message;
if (e2.InnerException != null)
{
lErr += lErr + e2.InnerException.Message;
}
Console.WriteLine(Environment.NewLine + lErr);
Console.WriteLine(FAIL_MSG);
}
}
Update
private static void Update_Using_DataSet()
{
try
{
Console.WriteLine(Environment.NewLine + "Start...");
ConnectionStringSettingsCollection settings = ConfigurationManager.ConnectionStrings;
ConnectionStringSettings cs = settings["u2_connection"];
U2Connection lConn = new U2Connection();
lConn.ConnectionString = cs.ConnectionString;
lConn.Open();
Console.WriteLine("Connected...");
U2Command cmd = lConn.CreateCommand();
//ID,FNAME,LNAME : Single Value
//SEMESTER: Multi Value
//COURSE_NBR,COURSE_GRD: MS
cmd.CommandText = string.Format("SELECT ID,FNAME,LNAME,SEMESTER,COURSE_NBR,COURSE_GRD FROM STUDENT WHERE ID={0} ORDER BY ID",ID);
U2DataAdapter da = new U2DataAdapter(cmd);
U2CommandBuilder builder = new U2CommandBuilder(da);
da.UpdateCommand = builder.GetUpdateCommand();
DataSet ds = new DataSet();
da.Fill(ds);
DataTable dt = ds.Tables[0];
DataRowCollection lDataRowCollection = dt.Rows;
int i = 1;
foreach (DataRow item in lDataRowCollection)
{
item["FNAME"] = item["FNAME"] + "3";// modify single value
item["SEMESTER"] = item["SEMESTER"] + "$";//modify multi-value
item["COURSE_GRD"] = item["COURSE_GRD"] + "$";
i++;
}
da.Update(ds);//use DataAdapter's Update() API
//print modified value
cmd.CommandText = string.Format("SELECT ID,FNAME,LNAME,SEMESTER,COURSE_NBR,COURSE_GRD FROM STUDENT WHERE ID={0} ORDER BY ID", ID); ;
//verify the change
U2DataAdapter da2 = new U2DataAdapter(cmd);
DataSet ds2 = new DataSet();
da2.Fill(ds2);
Console.WriteLine(Environment.NewLine);
ds2.WriteXml(Console.Out);
//close connection
lConn.Close();
Console.WriteLine(Environment.NewLine + "End...");
Console.WriteLine(SUCCESS_MSG);
}
catch (Exception e2)
{
Console.WriteLine(FAIL_MSG);
string lErr = e2.Message;
if (e2.InnerException != null)
{
lErr += lErr + e2.InnerException.Message;
}
Console.WriteLine(Environment.NewLine + lErr);
}
}
You will need to modify the UniDynArray (the record) for each row value in the table and then write the UniDynArray to the file and specific record id:
for (Int32 i=0; i < modifiedTable.Rows.Count; i++)
{
DataRow item = modifiedTable.Rows[i];
//Modify each attribute in the record from the rows in the table
udr3.Replace(i+1, (String)item[0]);
}
//Write the modified record to the file
fl.Write("MyRecordId", udr3);
The reason you got the null reference exception is because you didn't assign a value to fl.RecordId or fl.Record before calling fl.Write(). As you can see above, I prefer to use the overload of the Write method that takes record id and record data as parameters instead of setting the properties on the instance of UniFile.

MySQLBulkLoader not inserting any row in mysql db

var bl = new MySqlBulkLoader(mycon);
bl.TableName = "tblspmaster";
bl.FieldTerminator = ",";
bl.LineTerminator = "\r\n";
bl.FileName = "E://31october//SP//sp_files_sample1//400k sp00 6-19 E.csv";
bl.NumberOfLinesToSkip = 1;
var inserted = bl.Load();
I am using this code to upload a csv file in db but its not throwing any exception and inserted always show zero .
dotnetconnector for mysql is already installed and reference is also added .
Finally i have used this code and its working for me
string sql = #"load data infile 'E:/a1.csv' ignore into table tblspmaster fields terminated by '' enclosed by '' lines terminated by '\n' IGNORE 1 LINES (sp)";
MySqlCommand cmd = new MySqlCommand(sql, mycon);
cmd.CommandTimeout = 5000000;
cmd.ExecuteNonQuery();
It may not insert the data, if your csv file and the mysql table columns are not matched.
For example if your mysql table has a primary key column with identity key, and generally you won't have this column in csv file.
So in the above case the mysqlloader will not insert the data.
To solve this use columns property and add the columns mysql table column names
here is a sample code.
public async Task<bool> MySqlBulkLoaderAsync(string csvFilePath)
{
bool result = true;
try
{
using (var conn = new MySqlConnection(_connString + ";AllowLoadLocalInfile=True"))
{
var bl = new MySqlBulkLoader(conn)
{
TableName = "patientdetailstagings",
Timeout = 600,
FieldTerminator = ",",
LineTerminator = "\n",
FieldQuotationCharacter = '"',
FileName = csvFilePath,
NumberOfLinesToSkip = 1
};
bl.Columns.AddRange(new List<string>() {"Column1", "Column2"});
var numberOfInsertedRows = await bl.LoadAsync();
}
System.IO.File.Delete(csvFilePath);
}
catch (Exception ex)
{
result = false;
throw;
}
return result;
}
Note: the column mapping will be done based on the way you have added them in the columns property.
In the same order it will access the column value from csv file

Dataset to xml Null Values

I have the code below, where from 3 tables I take the data and write an xml.
I want write (when a record column has null value) the column on the xml with null value. For example if (Category_name == Null ) to write on the xml (Null) Right now the code skip the column and don’t even have this column on the xml.
string xmlFileData = "";
string[] tables = new string[] { "category", "company", "config" };
string query;
xmlFileData += "<MyXml>";
SqlConnection conn;
dbconnect obj;
obj = new dbconnect();//initailizing class object
for (int i = 0; i < tables.Length; i++)
{
string ifemptquery;
DataSet ds = new DataSet();
DataSet ds1 = new DataSet();
conn = obj.getConnection(); //calling connection function
ifemptquery = "SELECT * FROM " + tables[i] ";
SqlCommand cmd1 = new SqlCommand(ifemptquery, conn);
conn.Open();
SqlDataAdapter da1 = new SqlDataAdapter(cmd1);
DataTable dt1 = new DataTable();
da1.Fill(dt1);
conn.Close();
if (dt1.Rows.Count > 0)
{
query = "SELECT * FROM " + tables[i] ";
SqlCommand cmd = new SqlCommand(query, conn);
conn.Open();
SqlDataAdapter da = new SqlDataAdapter(cmd);
da.Fill(ds);
conn.Close();
conn.Dispose();
ds.DataSetName = tables[i];
string vartbname = tables[i];
string trimed_tbname = vartbname.Replace("_", "");
ds.Tables[0].TableName = trimed_tbname;
xmlFileData += ds.GetXml();
}
else
{
}
}
xmlFileData += "</MyXml>";
File.WriteAllText(Server.MapPath("~/xmlbackup/") + "Backup.xml", xmlFileData);
I have been searching the whole world for a solution of writing null fields to XML using DataSet.WriteXML(). The answer posted by Vlad is the one I also used in my project but I found that following works in a much more performance optimized way. I have created a function for your convenience. Change your dataset tables one after the other by calling the following function and replacing the tables.
private DataTable GetNullFilledDataTableForXML(DataTable dtSource)
{
// Create a target table with same structure as source and fields as strings
// We can change the column datatype as long as there is no data loaded
DataTable dtTarget = dtSource.Clone();
foreach (DataColumn col in dtTarget.Columns)
col.DataType = typeof(string);
// Start importing the source into target by ItemArray copying which
// is found to be reasonably fast for nulk operations. VS 2015 is reporting
// 500-525 milliseconds for loading 100,000 records x 10 columns
// after null conversion in every cell which may be usable in many
// circumstances.
// Machine config: i5 2nd Gen, 8 GB RAM, Windows 7 64bit, VS 2015 Update 1
int colCountInTarget = dtTarget.Columns.Count;
foreach (DataRow sourceRow in dtSource.Rows)
{
// Get a new row loaded with data from source row
DataRow targetRow = dtTarget.NewRow();
targetRow.ItemArray = sourceRow.ItemArray;
// Update DBNull.Values to empty string in the new (target) row
// We can safely assign empty string since the target table columns
// are all of string type
for (int ctr = 0; ctr < colCountInTarget; ctr++)
if (targetRow[ctr] == DBNull.Value)
targetRow[ctr] = String.Empty;
// Now add the null filled row to target datatable
dtTarget.Rows.Add(targetRow);
}
// Return the target datatable
return dtTarget;
}
Refer similar question here - dataSet.GetXml() doesn't return xml for null or blank columns
Apart from solutions mentioned there, you can also traverse through dataset and write XML using XmlTextWriter. This method is not recommended if you are dealing with huge data.

Getting the top row from a CSV when it is not a header row

In my website I am reading a CSV file and parsing it. Now the CSV does not have a column names. It is simply a raw list of comma seperated values.
I take this file and use the ODBCDataReader class to read the rows.
The problem is that when I retrieve the first value it skips the first row of the CSV. This is probably because it considers first row as column header. But in my case there are no column headers. So every time my first row is skipped.
How can I retrieve the first row of my CSV?
Here is the screenshot of my CSV:
Here is the code that I am using to parse the CSV.
public string CsvParser()
{
int _nNrRowsProccessed = 0;
string connectionString = #"Driver={Microsoft Text Driver (*.txt; *.csv)};Dbq=" + ConfigurationManager.AppSettings["CSVFolder"] + ";";
OdbcConnection conn = new OdbcConnection(connectionString);
try
{
conn.Open();
string strFileName = ConfigurationManager.AppSettings["CSVFile"];
string strSQL = "Select * from " + strFileName;
OdbcCommand cmd = new OdbcCommand();
cmd.Connection = conn;
cmd.CommandText = strSQL;
cmd.CommandType = CommandType.Text;
OdbcDataReader reader = cmd.ExecuteReader();
string strLine = null;
// MasterCalendar_DB.OpenMySQLConnection();
while (reader.Read())
{
// insert data into mastercalendar
strLine = reader[0].ToString();
string strLine1 = reader[1].ToString();
string strLine2 = reader[2].ToString();
string strLine3 = reader[3].ToString();
string[] arLine = strLine.Split(';');
// string strAgencyPropertyID = arLine[0];
// DateTime dt = DateTime.Parse(arLine[1]);
// Int64 nDate = (Int64)Util.ConvertToUnixTimestamp(dt);
// String strAvailability = (arLine[2]);
_nNrRowsProccessed++;
// MasterCalendar_DB.Insert(strAgencyPropertyID, nDate, strAvailability);
}
}
catch (Exception ex)
{
throw ex;
}
finally
{
conn.Close();
// MasterCalendar_DB.CloseMySQLConnection();
}
return "Success";
}
You want to have a look at the page of the Text-Driver over at connectionstrings.org.
Basically, you create a schema.ini in the same directory, which holds varies options. One of them is the ColNameHeader option, which takes a boolean.
Example from the site:
[customers.txt]
Format=TabDelimited
ColNameHeader=True
MaxScanRows=0
CharacterSet=ANSI
Check this: Schema.ini File (Text File Driver)
You may need to set ColNameHeader = false
Reference Microsoft.VisualBasic and you can use TextFieldParser, which almost certainly has less dependencies than your proposed method.
using (var parser =
new TextFieldParser(#"c:\data.csv")
{
TextFieldType = FieldType.Delimited,
Delimiters = new[] { "," }
})
{
while (!parser.EndOfData)
{
string[] fields;
fields = parser.ReadFields();
//go go go!
}
}
Quick and dirty solution:
string strLine = reader.GetName(0);
string strLine1 = reader.GetName(1);
string strLine2 = reader.GetName(2);
string strLine3 = reader.GetName(3);
reader.GetName(int i); // Gets the name of specified column.

Categories