在c#中是否有默认/官方/推荐的方法来解析CSV文件?我不想滚动自己的解析器。
另外,我也见过人们使用ODBC/OLE DB通过文本驱动程序读取CSV的实例,很多人因为它的“缺点”而不鼓励这样做。这些缺点是什么?
理想情况下,我正在寻找一种方法,通过它我可以通过列名读取CSV,使用第一个记录作为报头/字段名。给出的一些答案是正确的,但基本上是将文件反序列化为类。
在c#中是否有默认/官方/推荐的方法来解析CSV文件?我不想滚动自己的解析器。
另外,我也见过人们使用ODBC/OLE DB通过文本驱动程序读取CSV的实例,很多人因为它的“缺点”而不鼓励这样做。这些缺点是什么?
理想情况下,我正在寻找一种方法,通过它我可以通过列名读取CSV,使用第一个记录作为报头/字段名。给出的一些答案是正确的,但基本上是将文件反序列化为类。
当前回答
这是我的KISS实现…
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;
}
}
其他回答
如果任何人想要一个代码片段,他们可以直接输入自己的代码,而不必绑定库或下载包。以下是我写的一个版本:
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;
}
前段时间我写了一个基于微软的CSV读写简单类。VisualBasic图书馆。使用这个简单的类,您将能够像使用二维数组一样使用CSV。你可以通过以下链接找到我的课程:https://github.com/ukushu/DataExporter
用法的简单例子:
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");
对于读取头,你只需要读取csv。行[0]单元格:)
这个解决方案使用的是官方的微软。VisualBasic程序集来解析CSV。
优点:
分隔符逃离 忽略了头 装饰空间 忽略评论
代码:
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;
}
我知道有点晚了,但刚刚找到了Microsoft.VisualBasic.FileIO库,其中有TextFieldParser类来处理csv文件。
单源文件解决方案用于简单的解析需求,非常有用。处理所有令人讨厌的边缘情况。比如新行归一化和在带引号的字符串字面量中处理新行。你的欢迎!
如果您的CSV文件有一个标题,您只需从第一行读出列名(并计算列索引)。就这么简单。
注意Dump是一个LINQPad方法,如果你不使用LINQPad,你可能想要删除它。
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;
}
}