C# 如何拆分其列可能包含的csv,
给定C# 如何拆分其列可能包含的csv,,c#,.net,csv,C#,.net,Csv,给定 21016,7/31/2008 14:22,杰夫·达尔加斯,6/5/2011 22:21,http://stackoverflow.com,“Corvallis,或”,7679351,81,b437f461b3fd27387c5d8ab47a293d35,34 如何使用C#将上述信息拆分为以下字符串: 2 1016 7/31/2008 14:22 Geoff Dalgas 6/5/2011 22:21 http://stackoverflow.com Corvallis, OR 7679
21016,7/31/2008 14:22,杰夫·达尔加斯,6/5/2011 22:21,http://stackoverflow.com,“Corvallis,或”,7679351,81,b437f461b3fd27387c5d8ab47a293d35,34
如何使用C#将上述信息拆分为以下字符串:
2
1016
7/31/2008 14:22
Geoff Dalgas
6/5/2011 22:21
http://stackoverflow.com
Corvallis, OR
7679
351
81
b437f461b3fd27387c5d8ab47a293d35
34
using(StreamReader SR = new StreamReader(FileName))
{
while (SR.Peek() >-1)
myStringArray = parseCSVLine(SR.ReadLine());
}
正如您可以看到其中一列所包含的,使用类似于CSV的库进行读取。它将处理带有引号的字段,并且由于已经存在很长时间,因此总体上可能比您的自定义解决方案更健壮。使用类似于CSV读取的库。它将处理带有引号的字段,并且由于使用时间较长,总体上可能比您的自定义解决方案更健壮。您可以在所有引号后面有偶数个引号的逗号上拆分
您还希望在for CSV格式上查看有关处理逗号的信息
有用的链接:您可以在所有逗号后面有偶数引号的逗号上拆分
您还希望在for CSV格式上查看有关处理逗号的信息
有用的链接:我看到,如果您在Excel中粘贴csv分隔文本并执行“文本到列”,它会要求您提供“文本限定符”。它默认为双引号,因此它将双引号内的文本视为文本。我想象Excel通过一次执行一个字符来实现这一点,如果遇到“文本限定符”,它将继续执行下一个“限定符”。您可能可以使用for循环和布尔值来实现这一点,以表示您是否在文本中
public string[] CsvParser(string csvText)
{
List<string> tokens = new List<string>();
int last = -1;
int current = 0;
bool inText = false;
while(current < csvText.Length)
{
switch(csvText[current])
{
case '"':
inText = !inText; break;
case ',':
if (!inText)
{
tokens.Add(csvText.Substring(last + 1, (current - last)).Trim(' ', ','));
last = current;
}
break;
default:
break;
}
current++;
}
if (last != csvText.Length - 1)
{
tokens.Add(csvText.Substring(last+1).Trim());
}
return tokens.ToArray();
}
public string[]CsvParser(string csvText)
{
列表标记=新列表();
int last=-1;
int电流=0;
bool-inText=false;
while(当前
我看到,如果您在Excel中粘贴csv分隔文本并执行“文本到列”,它会要求您提供“文本限定符”。它默认为双引号,因此它将双引号内的文本视为文本。我设想Excel通过在遇到“文本限定符”时每次执行一个字符来实现这一点,它将继续进入下一个“限定符”。您可能可以使用for循环和布尔值来实现这一点,以表示您是否在文本中
public string[] CsvParser(string csvText)
{
List<string> tokens = new List<string>();
int last = -1;
int current = 0;
bool inText = false;
while(current < csvText.Length)
{
switch(csvText[current])
{
case '"':
inText = !inText; break;
case ',':
if (!inText)
{
tokens.Add(csvText.Substring(last + 1, (current - last)).Trim(' ', ','));
last = current;
}
break;
default:
break;
}
current++;
}
if (last != csvText.Length - 1)
{
tokens.Add(csvText.Substring(last+1).Trim());
}
return tokens.ToArray();
}
public string[]CsvParser(string csvText)
{
列表标记=新列表();
int last=-1;
int电流=0;
bool-inText=false;
while(当前
使用Microsoft.VisualBasic.FileIO.TextFieldParser
类。这将处理对带分隔符的文件、TextReader
或Stream
的解析,其中一些字段用引号括起来,而另一些字段则不用引号括起来
例如:
using Microsoft.VisualBasic.FileIO;
string csv = "2,1016,7/31/2008 14:22,Geoff Dalgas,6/5/2011 22:21,http://stackoverflow.com,\"Corvallis, OR\",7679,351,81,b437f461b3fd27387c5d8ab47a293d35,34";
TextFieldParser parser = new TextFieldParser(new StringReader(csv));
// You can also read from a file
// TextFieldParser parser = new TextFieldParser("mycsvfile.csv");
parser.HasFieldsEnclosedInQuotes = true;
parser.SetDelimiters(",");
string[] fields;
while (!parser.EndOfData)
{
fields = parser.ReadFields();
foreach (string field in fields)
{
Console.WriteLine(field);
}
}
parser.Close();
这将产生以下输出:
2
1016
7/31/2008 14:22
Geoff Dalgas
6/5/2011 22:21
http://stackoverflow.com
Corvallis, OR
7679
351
81
b437f461b3fd27387c5d8ab47a293d35
34
2.
1016
7/31/2008 14:22
杰夫·达尔加斯
6/5/2011 22:21
http://stackoverflow.com
科瓦利斯,或
7679
351
81
b437f461b3fd27387c5d8ab47a293d35
34
有关更多信息,请参阅
您需要在添加引用.NET选项卡中添加对Microsoft.VisualBasic的引用。使用
Microsoft.VisualBasic.FileIO.TextFieldParser
类。这将处理对分隔文件、TextReader
或Stream
的解析,其中一些字段用引号括起来,而另一些字段不用引号括起来
例如:
using Microsoft.VisualBasic.FileIO;
string csv = "2,1016,7/31/2008 14:22,Geoff Dalgas,6/5/2011 22:21,http://stackoverflow.com,\"Corvallis, OR\",7679,351,81,b437f461b3fd27387c5d8ab47a293d35,34";
TextFieldParser parser = new TextFieldParser(new StringReader(csv));
// You can also read from a file
// TextFieldParser parser = new TextFieldParser("mycsvfile.csv");
parser.HasFieldsEnclosedInQuotes = true;
parser.SetDelimiters(",");
string[] fields;
while (!parser.EndOfData)
{
fields = parser.ReadFields();
foreach (string field in fields)
{
Console.WriteLine(field);
}
}
parser.Close();
这将产生以下输出:
2
1016
7/31/2008 14:22
Geoff Dalgas
6/5/2011 22:21
http://stackoverflow.com
Corvallis, OR
7679
351
81
b437f461b3fd27387c5d8ab47a293d35
34
2.
1016
7/31/2008 14:22
杰夫·达尔加斯
6/5/2011 22:21
http://stackoverflow.com
科瓦利斯,或
7679
351
81
b437f461b3fd27387c5d8ab47a293d35
34
有关更多信息,请参阅
您需要在添加引用.NET选项卡中添加对Microsoft.VisualBasic的引用。当.csv文件可能是逗号分隔字符串、逗号分隔带引号的字符串或两者的混乱组合时,解析.csv文件是一件棘手的事。我提出的解决方案允许这三种可能性中的任何一种。 我创建了一个方法ParseCsvRow()它从csv字符串返回一个数组。我首先处理字符串中的双引号,方法是将双引号上的字符串拆分为一个名为quotesArray的数组。Quoted string.csv文件仅在双引号为偶数时有效。列值中的双引号应替换为一对双引号(这是Excel的方法)。只要.csv文件满足这些要求,就可以预期分隔符逗号仅出现在双引号对的外部。双引号对内部的逗号是列值的一部分,在将.csv拆分为数组时应忽略 我的方法将通过只查看quotesArray的偶数索引来测试双引号对之外的逗号。它还将从列值的开始和结束处删除双引号
public static string[] ParseCsvRow(string csvrow)
{
const string obscureCharacter = "ᖳ";
if (csvrow.Contains(obscureCharacter)) throw new Exception("Error: csv row may not contain the " + obscureCharacter + " character");
var unicodeSeparatedString = "";
var quotesArray = csvrow.Split('"'); // Split string on double quote character
if (quotesArray.Length > 1)
{
for (var i = 0; i < quotesArray.Length; i++)
{
// CSV must use double quotes to represent a quote inside a quoted cell
// Quotes must be paired up
// Test if a comma lays outside a pair of quotes. If so, replace the comma with an obscure unicode character
if (Math.Round(Math.Round((decimal) i/2)*2) == i)
{
var s = quotesArray[i].Trim();
switch (s)
{
case ",":
quotesArray[i] = obscureCharacter; // Change quoted comma seperated string to quoted "obscure character" seperated string
break;
}
}
// Build string and Replace quotes where quotes were expected.
unicodeSeparatedString += (i > 0 ? "\"" : "") + quotesArray[i].Trim();
}
}
else
{
// String does not have any pairs of double quotes. It should be safe to just replace the commas with the obscure character
unicodeSeparatedString = csvrow.Replace(",", obscureCharacter);
}
var csvRowArray = unicodeSeparatedString.Split(obscureCharacter[0]);
for (var i = 0; i < csvRowArray.Length; i++)
{
var s = csvRowArray[i].Trim();
if (s.StartsWith("\"") && s.EndsWith("\""))
{
csvRowArray[i] = s.Length > 2 ? s.Substring(1, s.Length - 2) : ""; // Remove start and end quotes.
}
}
return csvRowArray;
}
publicstaticstring[]ParseCsvRow(stringcsvrow)
{
常量字符串蒙蔽字符=”ᖳ";
如果(csvrow.Contains(
string csv = @"2,1016,7/31/2008 14:22,Geoff Dalgas,6/5/2011 22:21,http://stackoverflow.com,""Corvallis, OR"",7679,351,81,b437f461b3fd27387c5d8ab47a293d35,34";
using (var p = ChoCSVReader.LoadText(csv)
)
{
Console.WriteLine(p.Dump());
}
Key: Column1 [Type: String]
Value: 2
Key: Column2 [Type: String]
Value: 1016
Key: Column3 [Type: String]
Value: 7/31/2008 14:22
Key: Column4 [Type: String]
Value: Geoff Dalgas
Key: Column5 [Type: String]
Value: 6/5/2011 22:21
Key: Column6 [Type: String]
Value: http://stackoverflow.com
Key: Column7 [Type: String]
Value: Corvallis, OR
Key: Column8 [Type: String]
Value: 7679
Key: Column9 [Type: String]
Value: 351
Key: Column10 [Type: String]
Value: 81
Key: Column11 [Type: String]
Value: b437f461b3fd27387c5d8ab47a293d35
Key: Column12 [Type: String]
Value: 34
/// <summary>
/// Returns a collection of strings that are derived by splitting the given source string at
/// characters given by the 'delimiter' parameter. However, a substring may be enclosed between
/// pairs of the 'qualifier' character so that instances of the delimiter can be taken as literal
/// parts of the substring. The method was originally developed to split comma-separated text
/// where quotes could be used to qualify text that contains commas that are to be taken as literal
/// parts of the substring. For example, the following source:
/// A, B, "C, D", E, "F, G"
/// would be split into 5 substrings:
/// A
/// B
/// C, D
/// E
/// F, G
/// When enclosed inside of qualifiers, the literal for the qualifier character may be represented
/// by two consecutive qualifiers. The two consecutive qualifiers are distinguished from a closing
/// qualifier character. For example, the following source:
/// A, "B, ""C"""
/// would be split into 2 substrings:
/// A
/// B, "C"
/// </summary>
/// <remarks>Originally based on: https://stackoverflow.com/a/43284485/2998072</remarks>
/// <param name="source">The string that is to be split</param>
/// <param name="delimiter">The character that separates the substrings</param>
/// <param name="qualifier">The character that is used (in pairs) to enclose a substring</param>
/// <param name="toTrim">If true, then whitespace is removed from the beginning and end of each
/// substring. If false, then whitespace is preserved at the beginning and end of each substring.
/// </param>
public static List<String> SplitQualified(this String source, Char delimiter, Char qualifier,
Boolean toTrim)
{
// Avoid throwing exception if the source is null
if (String.IsNullOrEmpty(source))
return new List<String> { "" };
var results = new List<String>();
var result = new StringBuilder();
Boolean inQualifier = false;
// The algorithm is designed to expect a delimiter at the end of each substring, but the
// expectation of the caller is that the final substring is not terminated by delimiter.
// Therefore, we add an artificial delimiter at the end before looping through the source string.
String sourceX = source + delimiter;
// Loop through each character of the source
for (var idx = 0; idx < sourceX.Length; idx++)
{
// If current character is a delimiter
// (except if we're inside of qualifiers, we ignore the delimiter)
if (sourceX[idx] == delimiter && inQualifier == false)
{
// Terminate the current substring by adding it to the collection
// (trim if specified by the method parameter)
results.Add(toTrim ? result.ToString().Trim() : result.ToString());
result.Clear();
}
// If current character is a qualifier
else if (sourceX[idx] == qualifier)
{
// ...and we're already inside of qualifier
if (inQualifier)
{
// check for double-qualifiers, which is escape code for a single
// literal qualifier character.
if (idx + 1 < sourceX.Length && sourceX[idx + 1] == qualifier)
{
idx++;
result.Append(sourceX[idx]);
continue;
}
// Since we found only a single qualifier, that means that we've
// found the end of the enclosing qualifiers.
inQualifier = false;
continue;
}
else
// ...we found an opening qualifier
inQualifier = true;
}
// If current character is neither qualifier nor delimiter
else
result.Append(sourceX[idx]);
}
return results;
}
[TestMethod()]
public void SplitQualified_00()
{
// Example with no substrings
String s = "";
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "" }, substrings);
}
[TestMethod()]
public void SplitQualified_00A()
{
// just a single delimiter
String s = ",";
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "", "" }, substrings);
}
[TestMethod()]
public void SplitQualified_01()
{
// Example with no whitespace or qualifiers
String s = "1,2,3,1,2,3";
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" }, substrings);
}
[TestMethod()]
public void SplitQualified_02()
{
// Example with whitespace and no qualifiers
String s = " 1, 2 ,3, 1 ,2\t, 3 ";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" }, substrings);
}
[TestMethod()]
public void SplitQualified_03()
{
// Example with whitespace and no qualifiers
String s = " 1, 2 ,3, 1 ,2\t, 3 ";
// whitespace should be preserved
var substrings = s.SplitQualified(',', '"', false);
CollectionAssert.AreEquivalent(
new List<String> { " 1", " 2 ", "3", " 1 ", "2\t", " 3 " },
substrings);
}
[TestMethod()]
public void SplitQualified_04()
{
// Example with no whitespace and trivial qualifiers.
String s = "1,\"2\",3,1,2,\"3\"";
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" }, substrings);
s = "\"1\",\"2\",3,1,\"2\",3";
substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" }, substrings);
}
[TestMethod()]
public void SplitQualified_05()
{
// Example with no whitespace and qualifiers that enclose delimiters
String s = "1,\"2,2a\",3,1,2,\"3,3a\"";
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2,2a", "3", "1", "2", "3,3a" },
substrings);
s = "\"1,1a\",\"2,2b\",3,1,\"2,2c\",3";
substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1,1a", "2,2b", "3", "1", "2,2c", "3" },
substrings);
}
[TestMethod()]
public void SplitQualified_06()
{
// Example with qualifiers enclosing whitespace but no delimiter
String s = "\" 1 \",\"2 \",3,1,2,\"\t3\t\"";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" },
substrings);
}
[TestMethod()]
public void SplitQualified_07()
{
// Example with qualifiers enclosing whitespace but no delimiter
String s = "\" 1 \",\"2 \",3,1,2,\"\t3\t\"";
// whitespace should be preserved
var substrings = s.SplitQualified(',', '"', false);
CollectionAssert.AreEquivalent(new List<String> { " 1 ", "2 ", "3", "1", "2", "\t3\t" },
substrings);
}
[TestMethod()]
public void SplitQualified_08()
{
// Example with qualifiers enclosing whitespace but no delimiter; also whitespace btwn delimiters
String s = "\" 1 \", \"2 \" , 3,1, 2 ,\" 3 \"";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" },
substrings);
}
[TestMethod()]
public void SplitQualified_09()
{
// Example with qualifiers enclosing whitespace but no delimiter; also whitespace btwn delimiters
String s = "\" 1 \", \"2 \" , 3,1, 2 ,\" 3 \"";
// whitespace should be preserved
var substrings = s.SplitQualified(',', '"', false);
CollectionAssert.AreEquivalent(new List<String> { " 1 ", " 2 ", " 3", "1", " 2 ", " 3 " },
substrings);
}
[TestMethod()]
public void SplitQualified_10()
{
// Example with qualifiers enclosing whitespace and delimiter
String s = "\" 1 \",\"2 , 2b \",3,1,2,\" 3,3c \"";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2 , 2b", "3", "1", "2", "3,3c" },
substrings);
}
[TestMethod()]
public void SplitQualified_11()
{
// Example with qualifiers enclosing whitespace and delimiter; also whitespace btwn delimiters
String s = "\" 1 \", \"2 , 2b \" , 3,1, 2 ,\" 3,3c \"";
// whitespace should be preserved
var substrings = s.SplitQualified(',', '"', false);
CollectionAssert.AreEquivalent(new List<String> { " 1 ", " 2 , 2b ", " 3", "1", " 2 ", " 3,3c " },
substrings);
}
[TestMethod()]
public void SplitQualified_12()
{
// Example with tab characters between delimiters
String s = "\t1,\t2\t,3,1,\t2\t,\t3\t";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" }, substrings);
}
[TestMethod()]
public void SplitQualified_13()
{
// Example with newline characters between delimiters
String s = "\n1,\n2\n,3,1,\n2\n,\n3\n";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2", "3" }, substrings);
}
[TestMethod()]
public void SplitQualified_14()
{
// Example with qualifiers enclosing whitespace and delimiter, plus escaped qualifier
String s = "\" 1 \",\"\"\"2 , 2b \"\"\",3,1,2,\" \"\"3,3c \"";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "\"2 , 2b \"", "3", "1", "2", "\"3,3c" },
substrings);
}
[TestMethod()]
public void SplitQualified_14A()
{
// Example with qualifiers enclosing whitespace and delimiter, plus escaped qualifier
String s = "\"\"\"1\"\"\"";
// whitespace should be removed
var substrings = s.SplitQualified(',', '"', true);
CollectionAssert.AreEquivalent(new List<String> { "\"1\"" },
substrings);
}
[TestMethod()]
public void SplitQualified_15()
{
// Instead of comma-delimited and quote-qualified, use pipe and hash
// Example with no whitespace or qualifiers
String s = "1|2|3|1|2,2f|3";
var substrings = s.SplitQualified('|', '#', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2", "3", "1", "2,2f", "3" }, substrings);
}
[TestMethod()]
public void SplitQualified_16()
{
// Instead of comma-delimited and quote-qualified, use pipe and hash
// Example with qualifiers enclosing whitespace and delimiter
String s = "# 1 #|#2 | 2b #|3|1|2|# 3|3c #";
// whitespace should be removed
var substrings = s.SplitQualified('|', '#', true);
CollectionAssert.AreEquivalent(new List<String> { "1", "2 | 2b", "3", "1", "2", "3|3c" },
substrings);
}
[TestMethod()]
public void SplitQualified_17()
{
// Instead of comma-delimited and quote-qualified, use pipe and hash
// Example with qualifiers enclosing whitespace and delimiter; also whitespace btwn delimiters
String s = "# 1 #| #2 | 2b # | 3|1| 2 |# 3|3c #";
// whitespace should be preserved
var substrings = s.SplitQualified('|', '#', false);
CollectionAssert.AreEquivalent(new List<String> { " 1 ", " 2 | 2b ", " 3", "1", " 2 ", " 3|3c " },
substrings);
}