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
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;
}
其他回答
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;
}
}
对于较小的CSV输入数据,LINQ是完全足够的。 以以下CSV文件内容为例:
schema_name、描述utype “IX_HE”、“高能量数据”,“x” “III_spectro”、“Spectrosopic数据”、“d” “VI_misc”、“杂”、“f” “vcds1”,“目录只在cd上提供”,“d” “J_other”,“其他期刊发表的文章”,“b”
当我们将整个内容读入一个名为data的字符串时,则
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
}
这里有一个我经常使用的helper类,以防有人回到这个线程(我想分享它)。
我这样做是为了简单地将它移植到可以使用的项目中:
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);
}
}
}
像这样使用它:
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;
}
[更新的csv helper:修复了最后一个新行字符创建新行的错误]
让一个库为你处理所有的细节!: -)
检查FileHelpers和保持干燥-不重复自己-不需要重新发明轮子的亿万次....
基本上,您只需要定义数据的形状——CSV中各个行中的字段——通过一个公共类(以及诸如默认值、NULL值替换等经过精心考虑的属性),将FileHelpers引擎指向一个文件,然后就可以从该文件中获得所有条目。一个简单的操作-卓越的性能!
如果你只需要读取csv文件,那么我推荐这个库:一个快速csv阅读器 如果你还需要生成csv文件,那么使用FileHelpers
它们都是免费和开源的。