How to convert an rtf string to text in C# - c#

Is there an easy way to extract text from an Rtf string without using RichTextBox?
Example:
{\rtf1\ansi\ansicpg1252\uc1\htmautsp\deff2{\fonttbl{\f0\fcharset0 Times New Roman;}{\f2\fcharset0 Segoe UI;}}{\colortbl\red0\green0\blue0;\red255\green255\blue255;}\loch\hich\dbch\pard\plain\ltrpar\itap0{\lang1033\fs18\f2\cf0 \cf0\ql{\f2 {\lang2070\ltrch foo}\li0\ri0\sa0\sb0\fi0\ql\par}
{\f2 {\lang2070\ltrch bar }\li0\ri0\sa0\sb0\fi0\ql\par}
}
}
should return:
foo
bar

How to do it in pure C# without any references to other libraries:
This guy wrote a class that strips RTF to plain text just as OP requested.
Here is the source
This is his code:
/// <summary>
/// Rich Text Stripper
/// </summary>
/// <remarks>
/// Translated from Python located at:
/// http://stackoverflow.com/a/188877/448
/// </remarks>
public static class RichTextStripper
{
private class StackEntry
{
public int NumberOfCharactersToSkip { get; set; }
public bool Ignorable { get; set; }
public StackEntry(int numberOfCharactersToSkip, bool ignorable)
{
NumberOfCharactersToSkip = numberOfCharactersToSkip;
Ignorable = ignorable;
}
}
private static readonly Regex _rtfRegex = new Regex(#"\\([a-z]{1,32})(-?\d{1,10})?[ ]?|\\'([0-9a-f]{2})|\\([^a-z])|([{}])|[\r\n]+|(.)", RegexOptions.Singleline | RegexOptions.IgnoreCase);
private static readonly List<string> destinations = new List<string>
{
"aftncn","aftnsep","aftnsepc","annotation","atnauthor","atndate","atnicn","atnid",
"atnparent","atnref","atntime","atrfend","atrfstart","author","background",
"bkmkend","bkmkstart","blipuid","buptim","category","colorschememapping",
"colortbl","comment","company","creatim","datafield","datastore","defchp","defpap",
"do","doccomm","docvar","dptxbxtext","ebcend","ebcstart","factoidname","falt",
"fchars","ffdeftext","ffentrymcr","ffexitmcr","ffformat","ffhelptext","ffl",
"ffname","ffstattext","field","file","filetbl","fldinst","fldrslt","fldtype",
"fname","fontemb","fontfile","fonttbl","footer","footerf","footerl","footerr",
"footnote","formfield","ftncn","ftnsep","ftnsepc","g","generator","gridtbl",
"header","headerf","headerl","headerr","hl","hlfr","hlinkbase","hlloc","hlsrc",
"hsv","htmltag","info","keycode","keywords","latentstyles","lchars","levelnumbers",
"leveltext","lfolevel","linkval","list","listlevel","listname","listoverride",
"listoverridetable","listpicture","liststylename","listtable","listtext",
"lsdlockedexcept","macc","maccPr","mailmerge","maln","malnScr","manager","margPr",
"mbar","mbarPr","mbaseJc","mbegChr","mborderBox","mborderBoxPr","mbox","mboxPr",
"mchr","mcount","mctrlPr","md","mdeg","mdegHide","mden","mdiff","mdPr","me",
"mendChr","meqArr","meqArrPr","mf","mfName","mfPr","mfunc","mfuncPr","mgroupChr",
"mgroupChrPr","mgrow","mhideBot","mhideLeft","mhideRight","mhideTop","mhtmltag",
"mlim","mlimloc","mlimlow","mlimlowPr","mlimupp","mlimuppPr","mm","mmaddfieldname",
"mmath","mmathPict","mmathPr","mmaxdist","mmc","mmcJc","mmconnectstr",
"mmconnectstrdata","mmcPr","mmcs","mmdatasource","mmheadersource","mmmailsubject",
"mmodso","mmodsofilter","mmodsofldmpdata","mmodsomappedname","mmodsoname",
"mmodsorecipdata","mmodsosort","mmodsosrc","mmodsotable","mmodsoudl",
"mmodsoudldata","mmodsouniquetag","mmPr","mmquery","mmr","mnary","mnaryPr",
"mnoBreak","mnum","mobjDist","moMath","moMathPara","moMathParaPr","mopEmu",
"mphant","mphantPr","mplcHide","mpos","mr","mrad","mradPr","mrPr","msepChr",
"mshow","mshp","msPre","msPrePr","msSub","msSubPr","msSubSup","msSubSupPr","msSup",
"msSupPr","mstrikeBLTR","mstrikeH","mstrikeTLBR","mstrikeV","msub","msubHide",
"msup","msupHide","mtransp","mtype","mvertJc","mvfmf","mvfml","mvtof","mvtol",
"mzeroAsc","mzeroDesc","mzeroWid","nesttableprops","nextfile","nonesttables",
"objalias","objclass","objdata","object","objname","objsect","objtime","oldcprops",
"oldpprops","oldsprops","oldtprops","oleclsid","operator","panose","password",
"passwordhash","pgp","pgptbl","picprop","pict","pn","pnseclvl","pntext","pntxta",
"pntxtb","printim","private","propname","protend","protstart","protusertbl","pxe",
"result","revtbl","revtim","rsidtbl","rxe","shp","shpgrp","shpinst",
"shppict","shprslt","shptxt","sn","sp","staticval","stylesheet","subject","sv",
"svb","tc","template","themedata","title","txe","ud","upr","userprops",
"wgrffmtfilter","windowcaption","writereservation","writereservhash","xe","xform",
"xmlattrname","xmlattrvalue","xmlclose","xmlname","xmlnstbl",
"xmlopen"
};
private static readonly Dictionary<string, string> specialCharacters = new Dictionary<string, string>
{
{ "par", "\n" },
{ "sect", "\n\n" },
{ "page", "\n\n" },
{ "line", "\n" },
{ "tab", "\t" },
{ "emdash", "\u2014" },
{ "endash", "\u2013" },
{ "emspace", "\u2003" },
{ "enspace", "\u2002" },
{ "qmspace", "\u2005" },
{ "bullet", "\u2022" },
{ "lquote", "\u2018" },
{ "rquote", "\u2019" },
{ "ldblquote", "\u201C" },
{ "rdblquote", "\u201D" },
};
/// <summary>
/// Strip RTF Tags from RTF Text
/// </summary>
/// <param name="inputRtf">RTF formatted text</param>
/// <returns>Plain text from RTF</returns>
public static string StripRichTextFormat(string inputRtf)
{
if (inputRtf == null)
{
return null;
}
string returnString;
var stack = new Stack<StackEntry>();
bool ignorable = false; // Whether this group (and all inside it) are "ignorable".
int ucskip = 1; // Number of ASCII characters to skip after a unicode character.
int curskip = 0; // Number of ASCII characters left to skip
var outList = new List<string>(); // Output buffer.
MatchCollection matches = _rtfRegex.Matches(inputRtf);
if (matches.Count > 0)
{
foreach (Match match in matches)
{
string word = match.Groups[1].Value;
string arg = match.Groups[2].Value;
string hex = match.Groups[3].Value;
string character = match.Groups[4].Value;
string brace = match.Groups[5].Value;
string tchar = match.Groups[6].Value;
if (!String.IsNullOrEmpty(brace))
{
curskip = 0;
if (brace == "{")
{
// Push state
stack.Push(new StackEntry(ucskip, ignorable));
}
else if (brace == "}")
{
// Pop state
StackEntry entry = stack.Pop();
ucskip = entry.NumberOfCharactersToSkip;
ignorable = entry.Ignorable;
}
}
else if (!String.IsNullOrEmpty(character)) // \x (not a letter)
{
curskip = 0;
if (character == "~")
{
if (!ignorable)
{
outList.Add("\xA0");
}
}
else if ("{}\\".Contains(character))
{
if (!ignorable)
{
outList.Add(character);
}
}
else if (character == "*")
{
ignorable = true;
}
}
else if (!String.IsNullOrEmpty(word)) // \foo
{
curskip = 0;
if (destinations.Contains(word))
{
ignorable = true;
}
else if (ignorable)
{
}
else if (specialCharacters.ContainsKey(word))
{
outList.Add(specialCharacters[word]);
}
else if (word == "uc")
{
ucskip = Int32.Parse(arg);
}
else if (word == "u")
{
int c = Int32.Parse(arg);
if (c < 0)
{
c += 0x10000;
}
outList.Add(Char.ConvertFromUtf32(c));
curskip = ucskip;
}
}
else if (!String.IsNullOrEmpty(hex)) // \'xx
{
if (curskip > 0)
{
curskip -= 1;
}
else if (!ignorable)
{
int c = Int32.Parse(hex, System.Globalization.NumberStyles.HexNumber);
outList.Add(Char.ConvertFromUtf32(c));
}
}
else if (!String.IsNullOrEmpty(tchar))
{
if (curskip > 0)
{
curskip -= 1;
}
else if (!ignorable)
{
outList.Add(tchar);
}
}
}
}
else
{
// Didn't match the regex
returnString = inputRtf;
}
returnString = String.Join(String.Empty, outList.ToArray());
return returnString;
}
}
EDIT 1:
In the meantime we had this code running for tests and adapted version in production. The new version does some additional safety checks & handles new lines better.
public static string StripRichTextFormat(string inputRtf)
{
if (inputRtf == null)
{
return null;
}
string returnString;
var stack = new Stack<StackEntry>();
bool ignorable = false; // Whether this group (and all inside it) are "ignorable".
int ucskip = 1; // Number of ASCII characters to skip after a unicode character.
int curskip = 0; // Number of ASCII characters left to skip
var outList = new List<string>(); // Output buffer.
MatchCollection matches = _rtfRegex.Matches(inputRtf);
if (matches.Count > 0)
{
foreach (Match match in matches)
{
string word = match.Groups[1].Value;
string arg = match.Groups[2].Value;
string hex = match.Groups[3].Value;
string character = match.Groups[4].Value;
string brace = match.Groups[5].Value;
string tchar = match.Groups[6].Value;
if (!String.IsNullOrEmpty(brace))
{
curskip = 0;
if (brace == "{")
{
// Push state
stack.Push(new StackEntry(ucskip, ignorable));
}
else if (brace == "}")
{
// Pop state
StackEntry entry = stack.Pop();
ucskip = entry.NumberOfCharactersToSkip;
ignorable = entry.Ignorable;
}
}
else if (!String.IsNullOrEmpty(character)) // \x (not a letter)
{
curskip = 0;
if (character == "~")
{
if (!ignorable)
{
outList.Add("\xA0");
}
}
else if ("{}\\".Contains(character))
{
if (!ignorable)
{
outList.Add(character);
}
}
else if (character == "*")
{
ignorable = true;
}
}
else if (!String.IsNullOrEmpty(word)) // \foo
{
curskip = 0;
if (destinations.Contains(word))
{
ignorable = true;
}
else if (ignorable)
{
}
else if (specialCharacters.ContainsKey(word))
{
outList.Add(specialCharacters[word]);
}
else if (word == "uc")
{
ucskip = Int32.Parse(arg);
}
else if (word == "u")
{
int c = Int32.Parse(arg);
if (c < 0)
{
c += 0x10000;
}
//Ein gültiger UTF32-Wert ist zwischen 0x000000 und 0x10ffff (einschließlich) und sollte keine Ersatzcodepunktwerte (0x00d800 ~ 0x00dfff)
if (c >= 0x000000 && c <= 0x10ffff && (c < 0x00d800 || c > 0x00dfff))
outList.Add(Char.ConvertFromUtf32(c));
else outList.Add("?");
curskip = ucskip;
}
}
else if (!String.IsNullOrEmpty(hex)) // \'xx
{
if (curskip > 0)
{
curskip -= 1;
}
else if (!ignorable)
{
int c = Int32.Parse(hex, System.Globalization.NumberStyles.HexNumber);
outList.Add(Char.ConvertFromUtf32(c));
}
}
else if (!String.IsNullOrEmpty(tchar))
{
if (curskip > 0)
{
curskip -= 1;
}
else if (!ignorable)
{
outList.Add(tchar);
}
}
}
}
else
{
// Didn't match the regex
returnString = inputRtf;
}
returnString = String.Join(String.Empty, outList.ToArray());
return returnString;
}

There's a simple article on MSDN to achieve what you want: http://msdn.microsoft.com/en-us/library/cc488002.aspx
class ConvertFromRTF
{
static void Main()
{
string path = #"test.rtf";
//Create the RichTextBox. (Requires a reference to System.Windows.Forms.dll.)
System.Windows.Forms.RichTextBox rtBox = new System.Windows.Forms.RichTextBox();
// Get the contents of the RTF file. Note that when it is
// stored in the string, it is encoded as UTF-16.
string s = System.IO.File.ReadAllText(path);
// Display the RTF text.
System.Windows.Forms.MessageBox.Show(s);
// Convert the RTF to plain text.
rtBox.Rtf = s;
string plainText = rtBox.Text;
// Display plain text output in MessageBox because console
// cannot display Greek letters.
System.Windows.Forms.MessageBox.Show(plainText);
// Output plain text to file, encoded as UTF-8.
System.IO.File.WriteAllText(#"output.txt", plainText);
}
}

Can't agree with using RichTextBox or any other controls in such kind of tasks. Here is another one approach:
public string RtfToPlainText(string rtf)
{
var flowDocument = new FlowDocument();
var textRange = new TextRange(flowDocument.ContentStart, flowDocument.ContentEnd);
using (var stream = new MemoryStream(Encoding.UTF8.GetBytes(rtf ?? string.Empty)))
{
textRange.Load(stream, DataFormats.Rtf);
}
return textRange.Text;
}

Related

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 (?)

Parsing CSV File with double quotes [duplicate]

Is there a default/official/recommended way to parse CSV files in C#? I don't want to roll my own parser.
Also, I've seen instances of people using ODBC/OLE DB to read CSV via the Text driver, and a lot of people discourage this due to its "drawbacks." What are these drawbacks?
Ideally, I'm looking for a way through which I can read the CSV by column name, using the first record as the header / field names. Some of the answers given are correct but work to basically deserialize the file into classes.
A CSV parser is now a part of .NET Framework.
Add a reference to Microsoft.VisualBasic.dll (works fine in C#, don't mind the name)
using (TextFieldParser parser = new TextFieldParser(#"c:\temp\test.csv"))
{
parser.TextFieldType = FieldType.Delimited;
parser.SetDelimiters(",");
while (!parser.EndOfData)
{
//Process row
string[] fields = parser.ReadFields();
foreach (string field in fields)
{
//TODO: Process field
}
}
}
The docs are here - TextFieldParser Class
P.S. If you need a CSV exporter, try CsvExport (discl: I'm one of the contributors)
CsvHelper (a library I maintain) will read a CSV file into custom objects.
using (var reader = new StreamReader("path\\to\\file.csv"))
using (var csv = new CsvReader(reader, CultureInfo.InvariantCulture))
{
var records = csv.GetRecords<Foo>();
}
Sometimes you don't own the objects you're trying to read into. In this case, you can use fluent mapping because you can't put attributes on the class.
public sealed class MyCustomObjectMap : CsvClassMap<MyCustomObject>
{
public MyCustomObjectMap()
{
Map( m => m.Property1 ).Name( "Column Name" );
Map( m => m.Property2 ).Index( 4 );
Map( m => m.Property3 ).Ignore();
Map( m => m.Property4 ).TypeConverter<MySpecialTypeConverter>();
}
}
Let a library handle all the nitty-gritty details for you! :-)
Check out FileHelpers and stay DRY - Don't Repeat Yourself - no need to re-invent the wheel a gazillionth time....
You basically just need to define that shape of your data - the fields in your individual line in the CSV - by means of a public class (and so well-thought out attributes like default values, replacements for NULL values and so forth), point the FileHelpers engine at a file, and bingo - you get back all the entries from that file. One simple operation - great performance!
In a business application, i use the Open Source project on codeproject.com, CSVReader.
It works well, and has good performance. There is some benchmarking on the link i provided.
A simple example, copied from the project page:
using (CsvReader csv = new CsvReader(new StreamReader("data.csv"), true))
{
int fieldCount = csv.FieldCount;
string[] headers = csv.GetFieldHeaders();
while (csv.ReadNextRecord())
{
for (int i = 0; i < fieldCount; i++)
Console.Write(string.Format("{0} = {1};", headers[i], csv[i]));
Console.WriteLine();
}
}
As you can see, it's very easy to work with.
I know its a bit late but just found a library Microsoft.VisualBasic.FileIO which has TextFieldParser class to process csv files.
Here is a helper class I use often, in case any one ever comes back to this thread (I wanted to share it).
I use this for the simplicity of porting it into projects ready to use:
public class CSVHelper : List<string[]>
{
protected string csv = string.Empty;
protected string separator = ",";
public CSVHelper(string csv, string separator = "\",\"")
{
this.csv = csv;
this.separator = separator;
foreach (string line in Regex.Split(csv, System.Environment.NewLine).ToList().Where(s => !string.IsNullOrEmpty(s)))
{
string[] values = Regex.Split(line, separator);
for (int i = 0; i < values.Length; i++)
{
//Trim values
values[i] = values[i].Trim('\"');
}
this.Add(values);
}
}
}
And use it like:
public List<Person> GetPeople(string csvContent)
{
List<Person> people = new List<Person>();
CSVHelper csv = new CSVHelper(csvContent);
foreach(string[] line in csv)
{
Person person = new Person();
person.Name = line[0];
person.TelephoneNo = line[1];
people.Add(person);
}
return people;
}
[Updated csv helper: bug fixed where the last new line character created a new line]
If you need only reading csv files then I recommend this library: A Fast CSV Reader
If you also need to generate csv files then use this one: FileHelpers
Both of them are free and opensource.
This solution is using the official Microsoft.VisualBasic assembly to parse CSV.
Advantages:
delimiter escaping
ignores Header
trim spaces
ignore comments
Code:
using Microsoft.VisualBasic.FileIO;
public static List<List<string>> ParseCSV (string csv)
{
List<List<string>> result = new List<List<string>>();
// To use the TextFieldParser a reference to the Microsoft.VisualBasic assembly has to be added to the project.
using (TextFieldParser parser = new TextFieldParser(new StringReader(csv)))
{
parser.CommentTokens = new string[] { "#" };
parser.SetDelimiters(new string[] { ";" });
parser.HasFieldsEnclosedInQuotes = true;
// Skip over header line.
//parser.ReadLine();
while (!parser.EndOfData)
{
var values = new List<string>();
var readFields = parser.ReadFields();
if (readFields != null)
values.AddRange(readFields);
result.Add(values);
}
}
return result;
}
I have written TinyCsvParser for .NET, which is one of the fastest .NET parsers around and highly configurable to parse almost any CSV format.
It is released under MIT License:
https://github.com/bytefish/TinyCsvParser
You can use NuGet to install it. Run the following command in the Package Manager Console.
PM> Install-Package TinyCsvParser
Usage
Imagine we have list of Persons in a CSV file persons.csv with their first name, last name and birthdate.
FirstName;LastName;BirthDate
Philipp;Wagner;1986/05/12
Max;Musterman;2014/01/02
The corresponding domain model in our system might look like this.
private class Person
{
public string FirstName { get; set; }
public string LastName { get; set; }
public DateTime BirthDate { get; set; }
}
When using TinyCsvParser you have to define the mapping between the columns in the CSV data and the property in you domain model.
private class CsvPersonMapping : CsvMapping<Person>
{
public CsvPersonMapping()
: base()
{
MapProperty(0, x => x.FirstName);
MapProperty(1, x => x.LastName);
MapProperty(2, x => x.BirthDate);
}
}
And then we can use the mapping to parse the CSV data with a CsvParser.
namespace TinyCsvParser.Test
{
[TestFixture]
public class TinyCsvParserTest
{
[Test]
public void TinyCsvTest()
{
CsvParserOptions csvParserOptions = new CsvParserOptions(true, new[] { ';' });
CsvPersonMapping csvMapper = new CsvPersonMapping();
CsvParser<Person> csvParser = new CsvParser<Person>(csvParserOptions, csvMapper);
var result = csvParser
.ReadFromFile(#"persons.csv", Encoding.ASCII)
.ToList();
Assert.AreEqual(2, result.Count);
Assert.IsTrue(result.All(x => x.IsValid));
Assert.AreEqual("Philipp", result[0].Result.FirstName);
Assert.AreEqual("Wagner", result[0].Result.LastName);
Assert.AreEqual(1986, result[0].Result.BirthDate.Year);
Assert.AreEqual(5, result[0].Result.BirthDate.Month);
Assert.AreEqual(12, result[0].Result.BirthDate.Day);
Assert.AreEqual("Max", result[1].Result.FirstName);
Assert.AreEqual("Mustermann", result[1].Result.LastName);
Assert.AreEqual(2014, result[1].Result.BirthDate.Year);
Assert.AreEqual(1, result[1].Result.BirthDate.Month);
Assert.AreEqual(1, result[1].Result.BirthDate.Day);
}
}
}
User Guide
A full User Guide is available at:
http://bytefish.github.io/TinyCsvParser/
Here is a short and simple solution.
using (TextFieldParser parser = new TextFieldParser(outputLocation))
{
parser.TextFieldType = FieldType.Delimited;
parser.SetDelimiters(",");
string[] headers = parser.ReadLine().Split(',');
foreach (string header in headers)
{
dataTable.Columns.Add(header);
}
while (!parser.EndOfData)
{
string[] fields = parser.ReadFields();
dataTable.Rows.Add(fields);
}
}
Here is my KISS implementation...
using System;
using System.Collections.Generic;
using System.Text;
class CsvParser
{
public static List<string> Parse(string line)
{
const char escapeChar = '"';
const char splitChar = ',';
bool inEscape = false;
bool priorEscape = false;
List<string> result = new List<string>();
StringBuilder sb = new StringBuilder();
for (int i = 0; i < line.Length; i++)
{
char c = line[i];
switch (c)
{
case escapeChar:
if (!inEscape)
inEscape = true;
else
{
if (!priorEscape)
{
if (i + 1 < line.Length && line[i + 1] == escapeChar)
priorEscape = true;
else
inEscape = false;
}
else
{
sb.Append(c);
priorEscape = false;
}
}
break;
case splitChar:
if (inEscape) //if in escape
sb.Append(c);
else
{
result.Add(sb.ToString());
sb.Length = 0;
}
break;
default:
sb.Append(c);
break;
}
}
if (sb.Length > 0)
result.Add(sb.ToString());
return result;
}
}
Some time ago I had wrote simple class for CSV read/write based on Microsoft.VisualBasic library. Using this simple class you will be able to work with CSV like with 2 dimensions array. You can find my class by the following link: https://github.com/ukushu/DataExporter
Simple example of usage:
Csv csv = new Csv("\t");//delimiter symbol
csv.FileOpen("c:\\file1.csv");
var row1Cell6Value = csv.Rows[0][5];
csv.AddRow("asdf","asdffffff","5")
csv.FileSave("c:\\file2.csv");
For reading header only you need is to read csv.Rows[0] cells :)
This code reads csv to DataTable:
public static DataTable ReadCsv(string path)
{
DataTable result = new DataTable("SomeData");
using (TextFieldParser parser = new TextFieldParser(path))
{
parser.TextFieldType = FieldType.Delimited;
parser.SetDelimiters(",");
bool isFirstRow = true;
//IList<string> headers = new List<string>();
while (!parser.EndOfData)
{
string[] fields = parser.ReadFields();
if (isFirstRow)
{
foreach (string field in fields)
{
result.Columns.Add(new DataColumn(field, typeof(string)));
}
isFirstRow = false;
}
else
{
int i = 0;
DataRow row = result.NewRow();
foreach (string field in fields)
{
row[i++] = field;
}
result.Rows.Add(row);
}
}
}
return result;
}
Single source file solution for straightforward parsing needs, useful. Deals with all the nasty edge cases. Such as new line normalization and handling new lines in quoted string literals. Your welcome!
If you CSV file has a header you just read out the column names (and compute column indexes) from the first row. Simple as that.
Note that Dump is a LINQPad method, you might want to remove that if you are not using LINQPad.
void Main()
{
var file1 = "a,b,c\r\nx,y,z";
CSV.ParseText(file1).Dump();
var file2 = "a,\"b\",c\r\nx,\"y,z\"";
CSV.ParseText(file2).Dump();
var file3 = "a,\"b\",c\r\nx,\"y\r\nz\"";
CSV.ParseText(file3).Dump();
var file4 = "\"\"\"\"";
CSV.ParseText(file4).Dump();
}
static class CSV
{
public struct Record
{
public readonly string[] Row;
public string this[int index] => Row[index];
public Record(string[] row)
{
Row = row;
}
}
public static List<Record> ParseText(string text)
{
return Parse(new StringReader(text));
}
public static List<Record> ParseFile(string fn)
{
using (var reader = File.OpenText(fn))
{
return Parse(reader);
}
}
public static List<Record> Parse(TextReader reader)
{
var data = new List<Record>();
var col = new StringBuilder();
var row = new List<string>();
for (; ; )
{
var ln = reader.ReadLine();
if (ln == null) break;
if (Tokenize(ln, col, row))
{
data.Add(new Record(row.ToArray()));
row.Clear();
}
}
return data;
}
public static bool Tokenize(string s, StringBuilder col, List<string> row)
{
int i = 0;
if (col.Length > 0)
{
col.AppendLine(); // continuation
if (!TokenizeQuote(s, ref i, col, row))
{
return false;
}
}
while (i < s.Length)
{
var ch = s[i];
if (ch == ',')
{
row.Add(col.ToString().Trim());
col.Length = 0;
i++;
}
else if (ch == '"')
{
i++;
if (!TokenizeQuote(s, ref i, col, row))
{
return false;
}
}
else
{
col.Append(ch);
i++;
}
}
if (col.Length > 0)
{
row.Add(col.ToString().Trim());
col.Length = 0;
}
return true;
}
public static bool TokenizeQuote(string s, ref int i, StringBuilder col, List<string> row)
{
while (i < s.Length)
{
var ch = s[i];
if (ch == '"')
{
// escape sequence
if (i + 1 < s.Length && s[i + 1] == '"')
{
col.Append('"');
i++;
i++;
continue;
}
i++;
return true;
}
else
{
col.Append(ch);
i++;
}
}
return false;
}
}
Another one to this list, Cinchoo ETL - an open source library to read and write multiple file formats (CSV, flat file, Xml, JSON etc)
Sample below shows how to read CSV file quickly (No POCO object required)
string csv = #"Id, Name
1, Carl
2, Tom
3, Mark";
using (var p = ChoCSVReader.LoadText(csv)
.WithFirstLineHeader()
)
{
foreach (var rec in p)
{
Console.WriteLine($"Id: {rec.Id}");
Console.WriteLine($"Name: {rec.Name}");
}
}
Sample below shows how to read CSV file using POCO object
public partial class EmployeeRec
{
public int Id { get; set; }
public string Name { get; set; }
}
static void CSVTest()
{
string csv = #"Id, Name
1, Carl
2, Tom
3, Mark";
using (var p = ChoCSVReader<EmployeeRec>.LoadText(csv)
.WithFirstLineHeader()
)
{
foreach (var rec in p)
{
Console.WriteLine($"Id: {rec.Id}");
Console.WriteLine($"Name: {rec.Name}");
}
}
}
Please check out articles at CodeProject on how to use it.
This parser supports nested commas and quotes in a column:
static class CSVParser
{
public static string[] ParseLine(string line)
{
List<string> cols = new List<string>();
string value = null;
for(int i = 0; i < line.Length; i++)
{
switch(line[i])
{
case ',':
cols.Add(value);
value = null;
if(i == line.Length - 1)
{// It ends with comma
cols.Add(null);
}
break;
case '"':
cols.Add(ParseEnclosedColumn(line, ref i));
i++;
break;
default:
value += line[i];
if (i == line.Length - 1)
{// Last character
cols.Add(value);
}
break;
}
}
return cols.ToArray();
}//ParseLine
static string ParseEnclosedColumn(string line, ref int index)
{// Example: "b"",bb"
string value = null;
int numberQuotes = 1;
int index2 = index;
for (int i = index + 1; i < line.Length; i++)
{
index2 = i;
switch (line[i])
{
case '"':
numberQuotes++;
if (numberQuotes % 2 == 0)
{
if (i < line.Length - 1 && line[i + 1] == ',')
{
index = i;
return value;
}
}
else if (i > index + 1 && line[i - 1] == '"')
{
value += '"';
}
break;
default:
value += line[i];
break;
}
}
index = index2;
return value;
}//ParseEnclosedColumn
}//class CSVParser
Based on unlimit's post on How to properly split a CSV using C# split() function? :
string[] tokens = System.Text.RegularExpressions.Regex.Split(paramString, ",");
NOTE: this doesn't handle escaped / nested commas, etc., and therefore is only suitable for certain simple CSV lists.
If anyone wants a snippet they can plop into their code without having to bind a library or download a package. Here is a version I wrote:
public static string FormatCSV(List<string> parts)
{
string result = "";
foreach (string s in parts)
{
if (result.Length > 0)
{
result += ",";
if (s.Length == 0)
continue;
}
if (s.Length > 0)
{
result += "\"" + s.Replace("\"", "\"\"") + "\"";
}
else
{
// cannot output double quotes since its considered an escape for a quote
result += ",";
}
}
return result;
}
enum CSVMode
{
CLOSED = 0,
OPENED_RAW = 1,
OPENED_QUOTE = 2
}
public static List<string> ParseCSV(string input)
{
List<string> results;
CSVMode mode;
char[] letters;
string content;
mode = CSVMode.CLOSED;
content = "";
results = new List<string>();
letters = input.ToCharArray();
for (int i = 0; i < letters.Length; i++)
{
char letter = letters[i];
char nextLetter = '\0';
if (i < letters.Length - 1)
nextLetter = letters[i + 1];
// If its a quote character
if (letter == '"')
{
// If that next letter is a quote
if (nextLetter == '"' && mode == CSVMode.OPENED_QUOTE)
{
// Then this quote is escaped and should be added to the content
content += letter;
// Skip the escape character
i++;
continue;
}
else
{
// otherwise its not an escaped quote and is an opening or closing one
// Character is skipped
// If it was open, then close it
if (mode == CSVMode.OPENED_QUOTE)
{
results.Add(content);
// reset the content
content = "";
mode = CSVMode.CLOSED;
// If there is a next letter available
if (nextLetter != '\0')
{
// If it is a comma
if (nextLetter == ',')
{
i++;
continue;
}
else
{
throw new Exception("Expected comma. Found: " + nextLetter);
}
}
}
else if (mode == CSVMode.OPENED_RAW)
{
// If it was opened raw, then just add the quote
content += letter;
}
else if (mode == CSVMode.CLOSED)
{
// Otherwise open it as a quote
mode = CSVMode.OPENED_QUOTE;
}
}
}
// If its a comma seperator
else if (letter == ',')
{
// If in quote mode
if (mode == CSVMode.OPENED_QUOTE)
{
// Just read it
content += letter;
}
// If raw, then close the content
else if (mode == CSVMode.OPENED_RAW)
{
results.Add(content);
content = "";
mode = CSVMode.CLOSED;
}
// If it was closed, then open it raw
else if (mode == CSVMode.CLOSED)
{
mode = CSVMode.OPENED_RAW;
results.Add(content);
content = "";
}
}
else
{
// If opened quote, just read it
if (mode == CSVMode.OPENED_QUOTE)
{
content += letter;
}
// If opened raw, then read it
else if (mode == CSVMode.OPENED_RAW)
{
content += letter;
}
// It closed, then open raw
else if (mode == CSVMode.CLOSED)
{
mode = CSVMode.OPENED_RAW;
content += letter;
}
}
}
// If it was still reading when the buffer finished
if (mode != CSVMode.CLOSED)
{
results.Add(content);
}
return results;
}
For smaller input CSV data LINQ is fully enough.
For example for the following CSV file content:
schema_name,description,utype
"IX_HE","High-Energy data","x"
"III_spectro","Spectrosopic data","d"
"VI_misc","Miscellaneous","f"
"vcds1","Catalogs only available in CDS","d"
"J_other","Publications from other journals","b"
when we read the whole content into single string called data, then
using System;
using System.IO;
using System.Linq;
var data = File.ReadAllText(Path2CSV);
// helper split characters
var newline = Environment.NewLine.ToCharArray();
var comma = ",".ToCharArray();
var quote = "\"".ToCharArray();
// split input string data to lines
var lines = data.Split(newline);
// first line is header, take the header fields
foreach (var col in lines.First().Split(comma)) {
// do something with "col"
}
// we skip the first line, all the rest are real data lines/fields
foreach (var line in lines.Skip(1)) {
// first we split the data line by comma character
// next we remove double qoutes from each splitted element using Trim()
// finally we make an array
var fields = line.Split(comma)
.Select(_ => { _ = _.Trim(quote); return _; })
.ToArray();
// do something with the "fields" array
}

Removing Invalid Characters From XML File Before Deserialization

I have some XML I am receiving from a server that sometimes has some invalid characters that I would like to remove before deserialization. I have no control over the XML file I receive so I need to check for the invalid characters myself.
Sample XML.....
<PrintStatus>N</PrintStatus>
<CustomerPO> >>>> pearl <<<<< </CustomerPO>
<Description>PO# pearl</Description>
<BranchID>4</BranchID>
<PostDate>
<Date>01/13/2015</Date>
</PostDate>
<ShipDate>
<Date>01/13/2015</Date>
</ShipDate>
As you can see, the customer po section has the invalid characters I need to remove. This sometimes occurs only in certain elements that include user typed data.
Here is my Response code.....
//configure http request
HttpWebRequest httpRequest = WebRequest.Create(url) as HttpWebRequest;
httpRequest.Method = "POST";
//prepare correct encoding for XML serialization
UTF8Encoding encoding = new UTF8Encoding();
//use Xml property to obtain serialized XML data
//convert into bytes using encoding specified above and get length
byte[] bodyBytes = encoding.GetBytes(Xml);
httpRequest.ContentLength = bodyBytes.Length;
//get http request stream for putting XML data into
Stream httpRequestBodyStream = httpRequest.GetRequestStream();
//fill stream with serialized XML data
httpRequestBodyStream.Write(bodyBytes, 0, bodyBytes.Length);
httpRequestBodyStream.Close();
//get http response
HttpWebResponse httpResponse = httpRequest.GetResponse() as HttpWebResponse;
StreamReader httpResponseStream = new StreamReader(httpResponse.GetResponseStream(), System.Text.Encoding.ASCII);
//extract XML from response
string httpResponseBody = httpResponseStream.ReadToEnd();
httpResponseStream.Close();
//ignore everything that isn't XML by removing headers
httpResponseBody = httpResponseBody.Substring(httpResponseBody.IndexOf("<?xml"));
//deserialize XML into ProductInquiryResponse
XmlSerializer serializer = new XmlSerializer(typeof(MyResponseClass));
StringReader responseReader = new StringReader(httpResponseBody);
//return MyResponseClass result
return serializer.Deserialize(responseReader) as MyResponseClass;
Does anyone happen to have any suggestions to check the XML? Should I just check the elements I am concerned with right before the xml string gets deserialized? Or is there a better way?
A general fix for your problem would be to recursively descend the XML, parsing as you go and comparing to the schema for that node. At any point if the input differs from the input expected from the schema, or is malformed in some way, allow an error handler to run to fix the input stream, rolling back to the most recent good state and proceeding forward with the fixed input.
The .Net XmlTextReader class is not flexible enough to do this. However, if you know in advance that from the schema that certain XML Elements cannot have children, then the following will read an XML input stream, and upon encountering an element whose fully qualified name matches the known names of leaf nodes, and "escape" the text of all such nodes:
public enum XmlDoctorStatus
{
NoFixNeeded,
FixMade,
FixFailed
}
public class XmlDoctor
{
internal class XmlFixData
{
public string InitialXml { get; private set; }
public string FixedXml { get; private set; }
public int LineNumber { get; private set; }
public int LinePosition { get; private set; }
public XmlFixData(string initialXml, string fixedXml, int lineNumber, int linePosition)
{
this.InitialXml = initialXml;
this.FixedXml = fixedXml;
this.LineNumber = lineNumber;
this.LinePosition = linePosition;
}
public bool ComesAfter(XmlFixData other)
{
if (LineNumber > other.LineNumber)
return true;
if (LineNumber == other.LineNumber && LinePosition > other.LinePosition)
return true;
return false;
}
}
internal class XmlFixedException : Exception
{
public XmlFixData XmlFixData { get; private set; }
public XmlFixedException(XmlFixData data)
{
this.XmlFixData = data;
}
}
readonly HashSet<XName> childlessNodes;
public string OriginalXml { get; private set; }
public XmlDoctor(string xml, IEnumerable<XName> childlessNodes)
{
if (xml == null)
throw new ArgumentNullException();
this.OriginalXml = xml;
this.childlessNodes = new HashSet<XName>(childlessNodes);
}
List<int> indices = null;
string passXml = string.Empty;
bool inPass = false;
void InitializePass(string xml)
{
if (inPass)
throw new Exception("nested pass");
ClearElementData();
TextHelper.NormalizeLines(xml, out passXml, out indices);
inPass = true;
}
void EndPass()
{
inPass = false;
indices = null;
passXml = string.Empty;
ClearElementData();
}
static int LineNumber(XmlReader reader)
{
return ((IXmlLineInfo)reader).LineNumber;
}
static int LinePosition(XmlReader reader)
{
return ((IXmlLineInfo)reader).LinePosition;
}
// Taken from https://stackoverflow.com/questions/1132494/string-escape-into-xml
public static string XmlEscape(string escaped)
{
var replacements = new KeyValuePair<string, string>[]
{
new KeyValuePair<string,string>("&", "&"),
new KeyValuePair<string,string>("\"", """),
new KeyValuePair<string,string>("'", "&apos;"),
new KeyValuePair<string,string>("<", "<"),
new KeyValuePair<string,string>(">", ">"),
};
foreach (var pair in replacements)
foreach (var index in escaped.IndexesOf(pair.Key, 0).Reverse())
if (!replacements.Any(other => string.Compare(other.Value, 0, escaped, index, other.Value.Length, StringComparison.Ordinal) == 0))
{
escaped = escaped.Substring(0, index) + pair.Value + escaped.Substring(index + 1, escaped.Length - index - 1);
}
return escaped;
}
void HandleNode(XmlReader reader)
{
// Adapted from http://blogs.msdn.com/b/mfussell/archive/2005/02/12/371546.aspx
if (reader == null)
{
throw new ArgumentNullException("reader");
}
switch (reader.NodeType)
{
case XmlNodeType.Element:
HandleStartElement(reader);
if (reader.IsEmptyElement)
{
HandleEndElement(reader);
}
break;
case XmlNodeType.Text:
HandleText(reader);
break;
case XmlNodeType.Whitespace:
case XmlNodeType.SignificantWhitespace:
break;
case XmlNodeType.CDATA:
break;
case XmlNodeType.EntityReference:
break;
case XmlNodeType.XmlDeclaration:
case XmlNodeType.ProcessingInstruction:
break;
case XmlNodeType.DocumentType:
break;
case XmlNodeType.Comment:
break;
case XmlNodeType.EndElement:
HandleEndElement(reader);
break;
}
}
private void HandleText(XmlReader reader)
{
if (string.IsNullOrEmpty(currentElementLocalName) || string.IsNullOrEmpty(currentElementName))
return;
var name = XName.Get(currentElementLocalName, currentElementNameSpace);
if (!childlessNodes.Contains(name))
return;
var lineIndex = LineNumber(reader) - 1;
var charIndex = LinePosition(reader) - 1;
if (lineIndex < 0 || charIndex < 0)
return;
int startIndex = indices[lineIndex] + charIndex;
// Scan forward in the input string until we find either the beginning of a CDATA section or the end of this element.
// Patterns to match: </Name
//
string pattern1 = "</" + currentElementName;
var index1 = FindElementEnd(passXml, startIndex, pattern1);
if (index1 < 0)
return; // BAD XML.
string pattern2 = "<![CDATA[";
var index2 = passXml.IndexOf(pattern2, startIndex);
int endIndex = (index2 < 0 ? index1 : Math.Min(index1, index2));
var text = passXml.Substring(startIndex, endIndex - startIndex);
var escapeText = XmlEscape(text);
if (escapeText != text)
{
if (escapeText != XmlEscape(escapeText))
{
Debug.Assert(escapeText == XmlEscape(escapeText));
throw new InvalidOperationException("Escaping error");
}
string fixedXml = passXml.Substring(0, startIndex) + escapeText + passXml.Substring(endIndex, passXml.Length - endIndex);
throw new XmlFixedException(new XmlFixData(passXml, fixedXml, lineIndex + 1, charIndex + 1));
}
}
static bool IsXmlSpace(char ch)
{
// http://www.w3.org/TR/2000/REC-xml-20001006#NT-S
// [3] S ::= (#x20 | #x9 | #xD | #xA)+
return ch == '\u0020' || ch == '\u0009' || ch == '\u000D' || ch == '\u000A';
}
private static int FindElementEnd(string passXml, int charPos, string tagEnd)
{
while (true)
{
var index = passXml.IndexOf(tagEnd, charPos);
if (index < 0)
return index;
int endPos = index + tagEnd.Length;
if (index + tagEnd.Length >= passXml.Length)
return -1; // Bad xml?
// Now we must have zero or more white space characters and a ">"
while (endPos < passXml.Length && IsXmlSpace(passXml[endPos]))
endPos++;
if (endPos >= passXml.Length)
return -1; // BAD XML;
if (passXml[endPos] == '>')
return index;
index = endPos;
// Spurious ending, keep searching.
}
}
string currentElementName = string.Empty;
string currentElementNameSpace = string.Empty;
string currentElementLocalName = string.Empty;
private void HandleStartElement(XmlReader reader)
{
currentElementName = reader.Name;
currentElementLocalName = reader.LocalName;
currentElementNameSpace = reader.NamespaceURI;
}
private void HandleEndElement(XmlReader reader)
{
ClearElementData();
}
private void ClearElementData()
{
currentElementName = string.Empty;
currentElementNameSpace = string.Empty;
currentElementLocalName = string.Empty;
}
public XmlDoctorStatus TryFix(out string newXml)
{
XmlFixData data = null;
while (true)
{
XmlFixData newData;
var status = TryFixOnePass((data == null ? OriginalXml : data.FixedXml), out newData);
switch (status)
{
case XmlDoctorStatus.FixFailed:
Debug.WriteLine("Could not fix XML");
newXml = OriginalXml;
return XmlDoctorStatus.FixFailed;
case XmlDoctorStatus.FixMade:
if (data != null && !newData.ComesAfter(data))
{
Debug.WriteLine("Warning -- possible infinite loop detected, aborting fix");
newXml = OriginalXml;
return XmlDoctorStatus.FixFailed;
}
data = newData;
break; // Try to fix more
case XmlDoctorStatus.NoFixNeeded:
if (data == null)
{
newXml = OriginalXml;
return XmlDoctorStatus.NoFixNeeded;
}
else
{
newXml = data.FixedXml;
return XmlDoctorStatus.FixMade;
}
}
}
}
XmlDoctorStatus TryFixOnePass(string xml, out XmlFixData data)
{
try
{
InitializePass(xml);
using (var textReader = new StringReader(passXml))
using (XmlReader reader = XmlReader.Create(textReader))
{
while (true)
{
bool read = reader.Read();
if (!read)
break;
HandleNode(reader);
}
}
}
catch (XmlFixedException ex)
{
// Success - a fix was made.
data = ex.XmlFixData;
return XmlDoctorStatus.FixMade;
}
catch (Exception ex)
{
// Failure - the file was not fixed and could not be parsed.
Debug.WriteLine("Fix Failed: " + ex.ToString());
data = null;
return XmlDoctorStatus.FixFailed;
}
finally
{
EndPass();
}
// No fix needed.
data = null;
return XmlDoctorStatus.NoFixNeeded;
}
}
public static class TextHelper
{
public static void NormalizeLines(string text, out string newText, out List<int> lineIndices)
{
var sb = new StringBuilder();
var indices = new List<int>();
using (var sr = new StringReader(text))
{
string line;
while ((line = sr.ReadLine()) != null)
{
indices.Add(sb.Length);
sb.AppendLine(line);
}
}
lineIndices = indices;
newText = sb.ToString();
}
public static IEnumerable<int> IndexesOf(this string str, string value, int startAt)
{
if (str == null)
yield break;
for (int index = startAt, valueLength = value.Length; ; index += valueLength)
{
index = str.IndexOf(value, index);
if (index == -1)
break;
yield return index;
}
}
}
Then use it like:
public static class TestXmlDoctor
{
public static void TestFix()
{
string xml1 = #"<?xml version=""1.0"" encoding=""UTF-8""?>
<MainClass>
<PrintStatus>N</PrintStatus>
<CustomerPO> >>>> pearl <<<<< </CustomerPO>
<Description>PO# pearl</Description>
<BranchID>4</BranchID>
<PostDate>
<Date>01/13/2015</Date>
</PostDate>
<ShipDate>
<Date>01/13/2015</Date>
</ShipDate>
</MainClass>
";
XName[] childlessNodes1 = new XName[]
{
XName.Get("CustomerPO", string.Empty),
};
try
{
TestFix(xml1, childlessNodes1);
}
catch (Exception ex)
{
Debug.WriteLine(ex);
}
}
public static string TestFix(string xml, IEnumerable<XName> childlessNodes)
{
string fixedXml;
var status = (new XmlDoctor(xml, childlessNodes).TryFix(out fixedXml));
switch (status)
{
case XmlDoctorStatus.NoFixNeeded:
return xml;
case XmlDoctorStatus.FixFailed:
Debug.WriteLine("Failed to fix xml");
return xml;
case XmlDoctorStatus.FixMade:
Debug.WriteLine("Fixed XML, new XML is as follows:");
Debug.WriteLine(fixedXml);
Debug.WriteLine(string.Empty);
return fixedXml;
default:
Debug.Assert(false, "Unknown fix status " + status.ToString());
return xml;
}
}
}
This with this, your XML fragment can be parsed, and becomes:
<?xml version="1.0" encoding="UTF-8"?>
<MainClass>
<PrintStatus>N</PrintStatus>
<CustomerPO> >>>> pearl <<<<< </CustomerPO>
<Description>PO# pearl</Description>
<BranchID>4</BranchID>
<PostDate>
<Date>01/13/2015</Date>
</PostDate>
<ShipDate>
<Date>01/13/2015</Date>
</ShipDate>
</MainClass>

Extract Embedded Image Object in RTF

I have rtf documents that include an embedded object (an image). I need to extract this as an Image object (or any other usable format). I have checked out this CodeProject article but the default apps don't render it correctly (They render the 'default image' image, not the image itself), so I moved on.
Here is a sample of the RTF Code (I had to shorten it because of size):
{\rtf1\ansi\deff0{\fonttbl{\f0\fnil\fcharset0 MS Sans Serif;}}
\viewkind4\uc1\pard\lang1033\f0\fs18{\object\objemb{\*\objclass Package}\objw855\objh810{\*\objdata
01050000
02000000
08000000
5061636b61676500
00000000
00000000
1f900000
02007369675f5f2e6a706700433a5c55736572735c726563657074696f6e5c4465736b746f705c
5369676e6174757265735c7369675f5f2e6a7067000000030034000000433a5c55736572735c52
45434550547e315c417070446174615c4c6f63616c5c54656d705c7369675f5f20283132292e6a
706700c18e0000ffd8ffe000104a46494600010101004800470000ffdb00430001010101010101
010101010101010101010101010101010101010101010101010101010101010101010101010101
010101010101010101010101010101010101ffdb00430101010101010101010101010101010101
010101010101010101010101010101010101010101010101010101010101010101010101010101
010101010101010101ffc0001108012c03e803012200021101031101ffc4001f00010002030002
0301000000000000000000090a07080b050602030401ffc4003f10000006030001040201030301
04070900000203040506010708090a11121314152116172223314118192532591a24576598d6d8
2933384651788497b7ffc4001a010101000301010000000000000000000000030204050106ffc4
002b11010003010100020103030402030000000002030401051112130614211522230731415124
32536162ffda000c03010002110311003f00bfc000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
000000000000000000000000000000000000000000000000000000000000000000000000000000
...
005c0072006500630065007000740069006f006e005c004400650073006b0074006f0070005c00
5300690067006e006100740075007200650073005c007300690067005f005f002e006a00700067
00
01050000
00000000
}{\result{\pict\wmetafile8\picw2010\pich1905\picwgoal855\pichgoal810
0100090000033b0700000200210600000000050000000b0200000000050000000c02350038001c
000000fb02f4ff000000000000900100000001000000005365676f65205549000e0a52104c2308
00dd1900d894ef758001f3758d0e664a040000002d010000050000000902000000000500000001
02ffffff00a5000000410bc600880020002000000000002000200000000c002800000020000000
400000000100010000000000000100000000000000000000000000000000000000000000ffffff
...
0021001c001c000000fb021000070000000000bc02000000000102022253797374656d00008d0e
664a00000a0022008a0100000000ffffffff8cdd1900040000002d010100030000000000
}}}\par
}
Here is a piece of code that can extract all objects ('Package' class objects) from an RTF stream:
public static void ExtractPackageObjects(string filePath)
{
using (StreamReader sr = new StreamReader(filePath))
{
RtfReader reader = new RtfReader(sr);
IEnumerator<RtfObject> enumerator = reader.Read().GetEnumerator();
while(enumerator.MoveNext())
{
if (enumerator.Current.Text == "object")
{
if (RtfReader.MoveToNextControlWord(enumerator, "objclass"))
{
string className = RtfReader.GetNextText(enumerator);
if (className == "Package")
{
if (RtfReader.MoveToNextControlWord(enumerator, "objdata"))
{
byte[] data = RtfReader.GetNextTextAsByteArray(enumerator);
using (MemoryStream packageData = new MemoryStream())
{
RtfReader.ExtractObjectData(new MemoryStream(data), packageData);
packageData.Position = 0;
PackagedObject po = PackagedObject.Extract(packageData);
File.WriteAllBytes(po.DisplayName, po.Data);
}
}
}
}
}
}
}
}
And here are the utility classes that this code uses. There is a simple stream-based RTF parser that allows to get to the interesting control words.
There is also a utility to extract data from a serialized Object Packager instance. Object Packager is an almost 20-years ago OLE1.0 thing and the serialized binary format is not documented (to my knowledge), but it's understandable.
This works fine on your provided sample, but you may have to adapt things around.
public class RtfReader
{
public RtfReader(TextReader reader)
{
if (reader == null)
throw new ArgumentNullException("reader");
Reader = reader;
}
public TextReader Reader { get; private set; }
public IEnumerable<RtfObject> Read()
{
StringBuilder controlWord = new StringBuilder();
StringBuilder text = new StringBuilder();
Stack<RtfParseState> stack = new Stack<RtfParseState>();
RtfParseState state = RtfParseState.Group;
do
{
int i = Reader.Read();
if (i < 0)
{
if (!string.IsNullOrWhiteSpace(controlWord.ToString()))
yield return new RtfControlWord(controlWord.ToString());
if (!string.IsNullOrWhiteSpace(text.ToString()))
yield return new RtfText(text.ToString());
yield break;
}
char c = (char)i;
// noise chars
if ((c == '\r') ||
(c == '\n'))
continue;
switch (state)
{
case RtfParseState.Group:
if (c == '{')
{
stack.Push(state);
break;
}
if (c == '\\')
{
state = RtfParseState.ControlWord;
break;
}
break;
case RtfParseState.ControlWord:
if (c == '\\')
{
// another controlWord
if (!string.IsNullOrWhiteSpace(controlWord.ToString()))
{
yield return new RtfControlWord(controlWord.ToString());
controlWord.Clear();
}
break;
}
if (c == '{')
{
// a new group
state = RtfParseState.Group;
if (!string.IsNullOrWhiteSpace(controlWord.ToString()))
{
yield return new RtfControlWord(controlWord.ToString());
controlWord.Clear();
}
break;
}
if (c == '}')
{
// close group
state = stack.Count > 0 ? stack.Pop() : RtfParseState.Group;
if (!string.IsNullOrWhiteSpace(controlWord.ToString()))
{
yield return new RtfControlWord(controlWord.ToString());
controlWord.Clear();
}
break;
}
if (!Char.IsLetterOrDigit(c))
{
state = RtfParseState.Text;
text.Append(c);
if (!string.IsNullOrWhiteSpace(controlWord.ToString()))
{
yield return new RtfControlWord(controlWord.ToString());
controlWord.Clear();
}
break;
}
controlWord.Append(c);
break;
case RtfParseState.Text:
if (c == '\\')
{
state = RtfParseState.EscapedText;
break;
}
if (c == '{')
{
if (!string.IsNullOrWhiteSpace(text.ToString()))
{
yield return new RtfText(text.ToString());
text.Clear();
}
// a new group
state = RtfParseState.Group;
break;
}
if (c == '}')
{
if (!string.IsNullOrWhiteSpace(text.ToString()))
{
yield return new RtfText(text.ToString());
text.Clear();
}
// close group
state = stack.Count > 0 ? stack.Pop() : RtfParseState.Group;
break;
}
text.Append(c);
break;
case RtfParseState.EscapedText:
if ((c == '\\') || (c == '}') || (c == '{'))
{
state = RtfParseState.Text;
text.Append(c);
break;
}
// ansi character escape
if (c == '\'')
{
text.Append(FromHexa((char)Reader.Read(), (char)Reader.Read()));
break;
}
if (!string.IsNullOrWhiteSpace(text.ToString()))
{
yield return new RtfText(text.ToString());
text.Clear();
}
// in fact, it's a normal controlWord
controlWord.Append(c);
state = RtfParseState.ControlWord;
break;
}
}
while (true);
}
public static bool MoveToNextControlWord(IEnumerator<RtfObject> enumerator, string word)
{
if (enumerator == null)
throw new ArgumentNullException("enumerator");
while (enumerator.MoveNext())
{
if (enumerator.Current.Text == word)
return true;
}
return false;
}
public static string GetNextText(IEnumerator<RtfObject> enumerator)
{
if (enumerator == null)
throw new ArgumentNullException("enumerator");
while (enumerator.MoveNext())
{
RtfText text = enumerator.Current as RtfText;
if (text != null)
return text.Text;
}
return null;
}
public static byte[] GetNextTextAsByteArray(IEnumerator<RtfObject> enumerator)
{
if (enumerator == null)
throw new ArgumentNullException("enumerator");
while (enumerator.MoveNext())
{
RtfText text = enumerator.Current as RtfText;
if (text != null)
{
List<byte> bytes = new List<byte>();
for (int i = 0; i < text.Text.Length; i += 2)
{
bytes.Add((byte)FromHexa(text.Text[i], text.Text[i + 1]));
}
return bytes.ToArray();
}
}
return null;
}
// Extracts an EmbeddedObject/ObjectHeader from a stream
// see [MS -OLEDS]: Object Linking and Embedding (OLE) Data Structures for more information
// chapter 2.2: OLE1.0 Format Structures
public static void ExtractObjectData(Stream inputStream, Stream outputStream)
{
if (inputStream == null)
throw new ArgumentNullException("inputStream");
if (outputStream == null)
throw new ArgumentNullException("outputStream");
BinaryReader reader = new BinaryReader(inputStream);
reader.ReadInt32(); // OLEVersion
int formatId = reader.ReadInt32(); // FormatID
if (formatId != 2) // see 2.2.4 Object Header. 2 means EmbeddedObject
throw new NotSupportedException();
ReadLengthPrefixedAnsiString(reader); // className
ReadLengthPrefixedAnsiString(reader); // topicName
ReadLengthPrefixedAnsiString(reader); // itemName
int nativeDataSize = reader.ReadInt32();
byte[] bytes = reader.ReadBytes(nativeDataSize);
outputStream.Write(bytes, 0, bytes.Length);
}
// see chapter 2.1.4 LengthPrefixedAnsiString
private static string ReadLengthPrefixedAnsiString(BinaryReader reader)
{
int length = reader.ReadInt32();
if (length == 0)
return string.Empty;
byte[] bytes = reader.ReadBytes(length);
return Encoding.Default.GetString(bytes, 0, length - 1);
}
private enum RtfParseState
{
ControlWord,
Text,
EscapedText,
Group
}
private static char FromHexa(char hi, char lo)
{
return (char)byte.Parse(hi.ToString() + lo, NumberStyles.HexNumber);
}
}
// Utility class to parse an OLE1.0 OLEOBJECT
public class PackagedObject
{
private PackagedObject()
{
}
public string DisplayName { get; private set; }
public string IconFilePath { get; private set; }
public int IconIndex { get; private set; }
public string FilePath { get; private set; }
public byte[] Data { get; private set; }
private static string ReadAnsiString(BinaryReader reader)
{
StringBuilder sb = new StringBuilder();
do
{
byte b = reader.ReadByte();
if (b == 0)
return sb.ToString();
sb.Append((char)b);
}
while (true);
}
public static PackagedObject Extract(Stream inputStream)
{
if (inputStream == null)
throw new ArgumentNullException("inputStream");
BinaryReader reader = new BinaryReader(inputStream);
reader.ReadUInt16(); // sig
PackagedObject po = new PackagedObject();
po.DisplayName = ReadAnsiString(reader);
po.IconFilePath = ReadAnsiString(reader);
po.IconIndex = reader.ReadUInt16();
int type = reader.ReadUInt16();
if (type != 3) // 3 is file, 1 is link
throw new NotSupportedException();
reader.ReadInt32(); // nextsize
po.FilePath = ReadAnsiString(reader);
int dataSize = reader.ReadInt32();
po.Data = reader.ReadBytes(dataSize);
// note after that, there may be unicode + long path info
return po;
}
}
public class RtfObject
{
public RtfObject(string text)
{
if (text == null)
throw new ArgumentNullException("text");
Text = text.Trim();
}
public string Text { get; private set; }
}
public class RtfText : RtfObject
{
public RtfText(string text)
: base(text)
{
}
}
public class RtfControlWord : RtfObject
{
public RtfControlWord(string name)
: base(name)
{
}
}
OK, this should work for you. To demonstrate my solution, I created a WinForms project with a PictureBox whose paint event handler was mapped to the following function:
private void rtfImage_Paint(object sender, PaintEventArgs e)
{
string rtfStr = System.IO.File.ReadAllText("MySampleFile.rtf");
string imageDataHex = ExtractImgHex(rtfStr);
byte[] imageBuffer = ToBinary(imageDataHex);
Image image;
using (MemoryStream stream = new MemoryStream(imageBuffer))
{
image = Image.FromStream(stream);
}
Rectangle rect = new Rectangle(0, 0, 100, 100);
e.Graphics.DrawImage(image, rect);
}
This code relies the on the System.Drawing.Image.FromStream() method, along with two "helper" functions:
A string extractor:
string ExtractImgHex(string s)
{
// I'm sure you could use regex here, but this works.
// This assumes one picture per file; loops required otherwise
int pictTagIdx = s.IndexOf("{\\pict\\");
int startIndex = s.IndexOf(" ", pictTagIdx)+1;
int endIndex = s.IndexOf("}", startIndex);
return s.Substring(startIndex, endIndex - startIndex);
}
... and a binary converter:
public static byte[] ToBinary(string imageDataHex)
{
//this function taken entirely from:
// http://www.codeproject.com/Articles/27431/Writing-Your-Own-RTF-Converter
if (imageDataHex == null)
{
throw new ArgumentNullException("imageDataHex");
}
int hexDigits = imageDataHex.Length;
int dataSize = hexDigits / 2;
byte[] imageDataBinary = new byte[dataSize];
StringBuilder hex = new StringBuilder(2);
int dataPos = 0;
for (int i = 0; i < hexDigits; i++)
{
char c = imageDataHex[i];
if (char.IsWhiteSpace(c))
{
continue;
}
hex.Append(imageDataHex[i]);
if (hex.Length == 2)
{
imageDataBinary[dataPos] = byte.Parse(hex.ToString(), System.Globalization.NumberStyles.HexNumber);
dataPos++;
hex.Remove(0, 2);
}
}
return imageDataBinary;
}
Below code can extract all type of embedded objects. including image/docs/mails etc with original file name. And save them in a local path.
string MyDir = #"E:\temp\";
Document doc = new Document(MyDir + "Requirement#4.rtf");
NodeCollection nodeColl = doc.GetChildNodes(NodeType.Shape, true);
foreach (var node in nodeColl)
{
Shape shape1 = (Shape)node;
if (shape1.OleFormat != null)
{
shape1.OleFormat.Save(MyDir + shape1.OleFormat.SuggestedFileName + shape1.OleFormat.SuggestedExtension);
}
}

Parsing CSV files in C#, with header

Is there a default/official/recommended way to parse CSV files in C#? I don't want to roll my own parser.
Also, I've seen instances of people using ODBC/OLE DB to read CSV via the Text driver, and a lot of people discourage this due to its "drawbacks." What are these drawbacks?
Ideally, I'm looking for a way through which I can read the CSV by column name, using the first record as the header / field names. Some of the answers given are correct but work to basically deserialize the file into classes.
A CSV parser is now a part of .NET Framework.
Add a reference to Microsoft.VisualBasic.dll (works fine in C#, don't mind the name)
using (TextFieldParser parser = new TextFieldParser(#"c:\temp\test.csv"))
{
parser.TextFieldType = FieldType.Delimited;
parser.SetDelimiters(",");
while (!parser.EndOfData)
{
//Process row
string[] fields = parser.ReadFields();
foreach (string field in fields)
{
//TODO: Process field
}
}
}
The docs are here - TextFieldParser Class
P.S. If you need a CSV exporter, try CsvExport (discl: I'm one of the contributors)
CsvHelper (a library I maintain) will read a CSV file into custom objects.
using (var reader = new StreamReader("path\\to\\file.csv"))
using (var csv = new CsvReader(reader, CultureInfo.InvariantCulture))
{
var records = csv.GetRecords<Foo>();
}
Sometimes you don't own the objects you're trying to read into. In this case, you can use fluent mapping because you can't put attributes on the class.
public sealed class MyCustomObjectMap : CsvClassMap<MyCustomObject>
{
public MyCustomObjectMap()
{
Map( m => m.Property1 ).Name( "Column Name" );
Map( m => m.Property2 ).Index( 4 );
Map( m => m.Property3 ).Ignore();
Map( m => m.Property4 ).TypeConverter<MySpecialTypeConverter>();
}
}
Let a library handle all the nitty-gritty details for you! :-)
Check out FileHelpers and stay DRY - Don't Repeat Yourself - no need to re-invent the wheel a gazillionth time....
You basically just need to define that shape of your data - the fields in your individual line in the CSV - by means of a public class (and so well-thought out attributes like default values, replacements for NULL values and so forth), point the FileHelpers engine at a file, and bingo - you get back all the entries from that file. One simple operation - great performance!
In a business application, i use the Open Source project on codeproject.com, CSVReader.
It works well, and has good performance. There is some benchmarking on the link i provided.
A simple example, copied from the project page:
using (CsvReader csv = new CsvReader(new StreamReader("data.csv"), true))
{
int fieldCount = csv.FieldCount;
string[] headers = csv.GetFieldHeaders();
while (csv.ReadNextRecord())
{
for (int i = 0; i < fieldCount; i++)
Console.Write(string.Format("{0} = {1};", headers[i], csv[i]));
Console.WriteLine();
}
}
As you can see, it's very easy to work with.
I know its a bit late but just found a library Microsoft.VisualBasic.FileIO which has TextFieldParser class to process csv files.
Here is a helper class I use often, in case any one ever comes back to this thread (I wanted to share it).
I use this for the simplicity of porting it into projects ready to use:
public class CSVHelper : List<string[]>
{
protected string csv = string.Empty;
protected string separator = ",";
public CSVHelper(string csv, string separator = "\",\"")
{
this.csv = csv;
this.separator = separator;
foreach (string line in Regex.Split(csv, System.Environment.NewLine).ToList().Where(s => !string.IsNullOrEmpty(s)))
{
string[] values = Regex.Split(line, separator);
for (int i = 0; i < values.Length; i++)
{
//Trim values
values[i] = values[i].Trim('\"');
}
this.Add(values);
}
}
}
And use it like:
public List<Person> GetPeople(string csvContent)
{
List<Person> people = new List<Person>();
CSVHelper csv = new CSVHelper(csvContent);
foreach(string[] line in csv)
{
Person person = new Person();
person.Name = line[0];
person.TelephoneNo = line[1];
people.Add(person);
}
return people;
}
[Updated csv helper: bug fixed where the last new line character created a new line]
If you need only reading csv files then I recommend this library: A Fast CSV Reader
If you also need to generate csv files then use this one: FileHelpers
Both of them are free and opensource.
This solution is using the official Microsoft.VisualBasic assembly to parse CSV.
Advantages:
delimiter escaping
ignores Header
trim spaces
ignore comments
Code:
using Microsoft.VisualBasic.FileIO;
public static List<List<string>> ParseCSV (string csv)
{
List<List<string>> result = new List<List<string>>();
// To use the TextFieldParser a reference to the Microsoft.VisualBasic assembly has to be added to the project.
using (TextFieldParser parser = new TextFieldParser(new StringReader(csv)))
{
parser.CommentTokens = new string[] { "#" };
parser.SetDelimiters(new string[] { ";" });
parser.HasFieldsEnclosedInQuotes = true;
// Skip over header line.
//parser.ReadLine();
while (!parser.EndOfData)
{
var values = new List<string>();
var readFields = parser.ReadFields();
if (readFields != null)
values.AddRange(readFields);
result.Add(values);
}
}
return result;
}
I have written TinyCsvParser for .NET, which is one of the fastest .NET parsers around and highly configurable to parse almost any CSV format.
It is released under MIT License:
https://github.com/bytefish/TinyCsvParser
You can use NuGet to install it. Run the following command in the Package Manager Console.
PM> Install-Package TinyCsvParser
Usage
Imagine we have list of Persons in a CSV file persons.csv with their first name, last name and birthdate.
FirstName;LastName;BirthDate
Philipp;Wagner;1986/05/12
Max;Musterman;2014/01/02
The corresponding domain model in our system might look like this.
private class Person
{
public string FirstName { get; set; }
public string LastName { get; set; }
public DateTime BirthDate { get; set; }
}
When using TinyCsvParser you have to define the mapping between the columns in the CSV data and the property in you domain model.
private class CsvPersonMapping : CsvMapping<Person>
{
public CsvPersonMapping()
: base()
{
MapProperty(0, x => x.FirstName);
MapProperty(1, x => x.LastName);
MapProperty(2, x => x.BirthDate);
}
}
And then we can use the mapping to parse the CSV data with a CsvParser.
namespace TinyCsvParser.Test
{
[TestFixture]
public class TinyCsvParserTest
{
[Test]
public void TinyCsvTest()
{
CsvParserOptions csvParserOptions = new CsvParserOptions(true, new[] { ';' });
CsvPersonMapping csvMapper = new CsvPersonMapping();
CsvParser<Person> csvParser = new CsvParser<Person>(csvParserOptions, csvMapper);
var result = csvParser
.ReadFromFile(#"persons.csv", Encoding.ASCII)
.ToList();
Assert.AreEqual(2, result.Count);
Assert.IsTrue(result.All(x => x.IsValid));
Assert.AreEqual("Philipp", result[0].Result.FirstName);
Assert.AreEqual("Wagner", result[0].Result.LastName);
Assert.AreEqual(1986, result[0].Result.BirthDate.Year);
Assert.AreEqual(5, result[0].Result.BirthDate.Month);
Assert.AreEqual(12, result[0].Result.BirthDate.Day);
Assert.AreEqual("Max", result[1].Result.FirstName);
Assert.AreEqual("Mustermann", result[1].Result.LastName);
Assert.AreEqual(2014, result[1].Result.BirthDate.Year);
Assert.AreEqual(1, result[1].Result.BirthDate.Month);
Assert.AreEqual(1, result[1].Result.BirthDate.Day);
}
}
}
User Guide
A full User Guide is available at:
http://bytefish.github.io/TinyCsvParser/
Here is a short and simple solution.
using (TextFieldParser parser = new TextFieldParser(outputLocation))
{
parser.TextFieldType = FieldType.Delimited;
parser.SetDelimiters(",");
string[] headers = parser.ReadLine().Split(',');
foreach (string header in headers)
{
dataTable.Columns.Add(header);
}
while (!parser.EndOfData)
{
string[] fields = parser.ReadFields();
dataTable.Rows.Add(fields);
}
}
Here is my KISS implementation...
using System;
using System.Collections.Generic;
using System.Text;
class CsvParser
{
public static List<string> Parse(string line)
{
const char escapeChar = '"';
const char splitChar = ',';
bool inEscape = false;
bool priorEscape = false;
List<string> result = new List<string>();
StringBuilder sb = new StringBuilder();
for (int i = 0; i < line.Length; i++)
{
char c = line[i];
switch (c)
{
case escapeChar:
if (!inEscape)
inEscape = true;
else
{
if (!priorEscape)
{
if (i + 1 < line.Length && line[i + 1] == escapeChar)
priorEscape = true;
else
inEscape = false;
}
else
{
sb.Append(c);
priorEscape = false;
}
}
break;
case splitChar:
if (inEscape) //if in escape
sb.Append(c);
else
{
result.Add(sb.ToString());
sb.Length = 0;
}
break;
default:
sb.Append(c);
break;
}
}
if (sb.Length > 0)
result.Add(sb.ToString());
return result;
}
}
Some time ago I had wrote simple class for CSV read/write based on Microsoft.VisualBasic library. Using this simple class you will be able to work with CSV like with 2 dimensions array. You can find my class by the following link: https://github.com/ukushu/DataExporter
Simple example of usage:
Csv csv = new Csv("\t");//delimiter symbol
csv.FileOpen("c:\\file1.csv");
var row1Cell6Value = csv.Rows[0][5];
csv.AddRow("asdf","asdffffff","5")
csv.FileSave("c:\\file2.csv");
For reading header only you need is to read csv.Rows[0] cells :)
This code reads csv to DataTable:
public static DataTable ReadCsv(string path)
{
DataTable result = new DataTable("SomeData");
using (TextFieldParser parser = new TextFieldParser(path))
{
parser.TextFieldType = FieldType.Delimited;
parser.SetDelimiters(",");
bool isFirstRow = true;
//IList<string> headers = new List<string>();
while (!parser.EndOfData)
{
string[] fields = parser.ReadFields();
if (isFirstRow)
{
foreach (string field in fields)
{
result.Columns.Add(new DataColumn(field, typeof(string)));
}
isFirstRow = false;
}
else
{
int i = 0;
DataRow row = result.NewRow();
foreach (string field in fields)
{
row[i++] = field;
}
result.Rows.Add(row);
}
}
}
return result;
}
Single source file solution for straightforward parsing needs, useful. Deals with all the nasty edge cases. Such as new line normalization and handling new lines in quoted string literals. Your welcome!
If you CSV file has a header you just read out the column names (and compute column indexes) from the first row. Simple as that.
Note that Dump is a LINQPad method, you might want to remove that if you are not using LINQPad.
void Main()
{
var file1 = "a,b,c\r\nx,y,z";
CSV.ParseText(file1).Dump();
var file2 = "a,\"b\",c\r\nx,\"y,z\"";
CSV.ParseText(file2).Dump();
var file3 = "a,\"b\",c\r\nx,\"y\r\nz\"";
CSV.ParseText(file3).Dump();
var file4 = "\"\"\"\"";
CSV.ParseText(file4).Dump();
}
static class CSV
{
public struct Record
{
public readonly string[] Row;
public string this[int index] => Row[index];
public Record(string[] row)
{
Row = row;
}
}
public static List<Record> ParseText(string text)
{
return Parse(new StringReader(text));
}
public static List<Record> ParseFile(string fn)
{
using (var reader = File.OpenText(fn))
{
return Parse(reader);
}
}
public static List<Record> Parse(TextReader reader)
{
var data = new List<Record>();
var col = new StringBuilder();
var row = new List<string>();
for (; ; )
{
var ln = reader.ReadLine();
if (ln == null) break;
if (Tokenize(ln, col, row))
{
data.Add(new Record(row.ToArray()));
row.Clear();
}
}
return data;
}
public static bool Tokenize(string s, StringBuilder col, List<string> row)
{
int i = 0;
if (col.Length > 0)
{
col.AppendLine(); // continuation
if (!TokenizeQuote(s, ref i, col, row))
{
return false;
}
}
while (i < s.Length)
{
var ch = s[i];
if (ch == ',')
{
row.Add(col.ToString().Trim());
col.Length = 0;
i++;
}
else if (ch == '"')
{
i++;
if (!TokenizeQuote(s, ref i, col, row))
{
return false;
}
}
else
{
col.Append(ch);
i++;
}
}
if (col.Length > 0)
{
row.Add(col.ToString().Trim());
col.Length = 0;
}
return true;
}
public static bool TokenizeQuote(string s, ref int i, StringBuilder col, List<string> row)
{
while (i < s.Length)
{
var ch = s[i];
if (ch == '"')
{
// escape sequence
if (i + 1 < s.Length && s[i + 1] == '"')
{
col.Append('"');
i++;
i++;
continue;
}
i++;
return true;
}
else
{
col.Append(ch);
i++;
}
}
return false;
}
}
Another one to this list, Cinchoo ETL - an open source library to read and write multiple file formats (CSV, flat file, Xml, JSON etc)
Sample below shows how to read CSV file quickly (No POCO object required)
string csv = #"Id, Name
1, Carl
2, Tom
3, Mark";
using (var p = ChoCSVReader.LoadText(csv)
.WithFirstLineHeader()
)
{
foreach (var rec in p)
{
Console.WriteLine($"Id: {rec.Id}");
Console.WriteLine($"Name: {rec.Name}");
}
}
Sample below shows how to read CSV file using POCO object
public partial class EmployeeRec
{
public int Id { get; set; }
public string Name { get; set; }
}
static void CSVTest()
{
string csv = #"Id, Name
1, Carl
2, Tom
3, Mark";
using (var p = ChoCSVReader<EmployeeRec>.LoadText(csv)
.WithFirstLineHeader()
)
{
foreach (var rec in p)
{
Console.WriteLine($"Id: {rec.Id}");
Console.WriteLine($"Name: {rec.Name}");
}
}
}
Please check out articles at CodeProject on how to use it.
This parser supports nested commas and quotes in a column:
static class CSVParser
{
public static string[] ParseLine(string line)
{
List<string> cols = new List<string>();
string value = null;
for(int i = 0; i < line.Length; i++)
{
switch(line[i])
{
case ',':
cols.Add(value);
value = null;
if(i == line.Length - 1)
{// It ends with comma
cols.Add(null);
}
break;
case '"':
cols.Add(ParseEnclosedColumn(line, ref i));
i++;
break;
default:
value += line[i];
if (i == line.Length - 1)
{// Last character
cols.Add(value);
}
break;
}
}
return cols.ToArray();
}//ParseLine
static string ParseEnclosedColumn(string line, ref int index)
{// Example: "b"",bb"
string value = null;
int numberQuotes = 1;
int index2 = index;
for (int i = index + 1; i < line.Length; i++)
{
index2 = i;
switch (line[i])
{
case '"':
numberQuotes++;
if (numberQuotes % 2 == 0)
{
if (i < line.Length - 1 && line[i + 1] == ',')
{
index = i;
return value;
}
}
else if (i > index + 1 && line[i - 1] == '"')
{
value += '"';
}
break;
default:
value += line[i];
break;
}
}
index = index2;
return value;
}//ParseEnclosedColumn
}//class CSVParser
Based on unlimit's post on How to properly split a CSV using C# split() function? :
string[] tokens = System.Text.RegularExpressions.Regex.Split(paramString, ",");
NOTE: this doesn't handle escaped / nested commas, etc., and therefore is only suitable for certain simple CSV lists.
If anyone wants a snippet they can plop into their code without having to bind a library or download a package. Here is a version I wrote:
public static string FormatCSV(List<string> parts)
{
string result = "";
foreach (string s in parts)
{
if (result.Length > 0)
{
result += ",";
if (s.Length == 0)
continue;
}
if (s.Length > 0)
{
result += "\"" + s.Replace("\"", "\"\"") + "\"";
}
else
{
// cannot output double quotes since its considered an escape for a quote
result += ",";
}
}
return result;
}
enum CSVMode
{
CLOSED = 0,
OPENED_RAW = 1,
OPENED_QUOTE = 2
}
public static List<string> ParseCSV(string input)
{
List<string> results;
CSVMode mode;
char[] letters;
string content;
mode = CSVMode.CLOSED;
content = "";
results = new List<string>();
letters = input.ToCharArray();
for (int i = 0; i < letters.Length; i++)
{
char letter = letters[i];
char nextLetter = '\0';
if (i < letters.Length - 1)
nextLetter = letters[i + 1];
// If its a quote character
if (letter == '"')
{
// If that next letter is a quote
if (nextLetter == '"' && mode == CSVMode.OPENED_QUOTE)
{
// Then this quote is escaped and should be added to the content
content += letter;
// Skip the escape character
i++;
continue;
}
else
{
// otherwise its not an escaped quote and is an opening or closing one
// Character is skipped
// If it was open, then close it
if (mode == CSVMode.OPENED_QUOTE)
{
results.Add(content);
// reset the content
content = "";
mode = CSVMode.CLOSED;
// If there is a next letter available
if (nextLetter != '\0')
{
// If it is a comma
if (nextLetter == ',')
{
i++;
continue;
}
else
{
throw new Exception("Expected comma. Found: " + nextLetter);
}
}
}
else if (mode == CSVMode.OPENED_RAW)
{
// If it was opened raw, then just add the quote
content += letter;
}
else if (mode == CSVMode.CLOSED)
{
// Otherwise open it as a quote
mode = CSVMode.OPENED_QUOTE;
}
}
}
// If its a comma seperator
else if (letter == ',')
{
// If in quote mode
if (mode == CSVMode.OPENED_QUOTE)
{
// Just read it
content += letter;
}
// If raw, then close the content
else if (mode == CSVMode.OPENED_RAW)
{
results.Add(content);
content = "";
mode = CSVMode.CLOSED;
}
// If it was closed, then open it raw
else if (mode == CSVMode.CLOSED)
{
mode = CSVMode.OPENED_RAW;
results.Add(content);
content = "";
}
}
else
{
// If opened quote, just read it
if (mode == CSVMode.OPENED_QUOTE)
{
content += letter;
}
// If opened raw, then read it
else if (mode == CSVMode.OPENED_RAW)
{
content += letter;
}
// It closed, then open raw
else if (mode == CSVMode.CLOSED)
{
mode = CSVMode.OPENED_RAW;
content += letter;
}
}
}
// If it was still reading when the buffer finished
if (mode != CSVMode.CLOSED)
{
results.Add(content);
}
return results;
}
For smaller input CSV data LINQ is fully enough.
For example for the following CSV file content:
schema_name,description,utype
"IX_HE","High-Energy data","x"
"III_spectro","Spectrosopic data","d"
"VI_misc","Miscellaneous","f"
"vcds1","Catalogs only available in CDS","d"
"J_other","Publications from other journals","b"
when we read the whole content into single string called data, then
using System;
using System.IO;
using System.Linq;
var data = File.ReadAllText(Path2CSV);
// helper split characters
var newline = Environment.NewLine.ToCharArray();
var comma = ",".ToCharArray();
var quote = "\"".ToCharArray();
// split input string data to lines
var lines = data.Split(newline);
// first line is header, take the header fields
foreach (var col in lines.First().Split(comma)) {
// do something with "col"
}
// we skip the first line, all the rest are real data lines/fields
foreach (var line in lines.Skip(1)) {
// first we split the data line by comma character
// next we remove double qoutes from each splitted element using Trim()
// finally we make an array
var fields = line.Split(comma)
.Select(_ => { _ = _.Trim(quote); return _; })
.ToArray();
// do something with the "fields" array
}

Categories