Skip to content

Prefer separator with more fields if there are more than one separato… #671

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
appel1 merged 1 commit into from
Jun 13, 2024
+36 −1
Merged

Prefer separator with more fields if there are more than one separato… #671

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion src/ExcelDataReader/Core/CsvFormat/CsvAnalyzer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,8 @@ public static void Analyze(Stream stream, char[] separators, Encoding fallbackEn
var average = separatorInfo.SumFieldCount / (double)separatorInfo.RowCount;
var dist = separatorInfo.MaxFieldCount - average;

if (dist < bestDistance)
// If more than one separator has the same number of fields for all sample rows prefer the one with the most fields
if (dist < bestDistance || (dist == bestDistance && dist == 0 && bestSeparatorInfo.MaxFieldCount < separatorInfo.MaxFieldCount))
{
bestDistance = dist;
bestSeparator = separator;
Expand Down
34 changes: 34 additions & 0 deletions test/ExcelDataReader.Tests/ExcelCsvReaderTest.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -423,5 +423,39 @@ public void GitIssue500_QuotedValueWithNewLine()
Assert.That(row2, Is.EqualTo(new object[] { "200212812", "$462.76", "Check", "06/06/2018", "Hash#hash" }));
});
}

[Test]
public void GitIssue463()
{
const string data = """
Name Currency Type Cost "Cost per 1,000 Items"
Test1 ABC XX "10,143.27" 0.00
Test2 EFG YY "10,143.27" 0.00
Test3 IJK ZZ "10,143.27" 0.00

""";

using var reader = ExcelReaderFactory.CreateCsvReader(new MemoryStream(Encoding.UTF8.GetBytes(data)));
reader.Read();
object[] row1 = new object[reader.FieldCount];
reader.GetValues(row1);
reader.Read();
object[] row2 = new object[reader.FieldCount];
reader.GetValues(row2);
reader.Read();
object[] row3 = new object[reader.FieldCount];
reader.GetValues(row3);
reader.Read();
object[] row4 = new object[reader.FieldCount];
reader.GetValues(row4);

Assert.Multiple(() =>
{
Assert.That(row1, Is.EqualTo(new object[] { "Name", "Currency", "Type", "Cost", "Cost per 1,000 Items" }));
Assert.That(row2, Is.EqualTo(new object[] { "Test1", "ABC", "XX", "10,143.27", "0.00" }));
Assert.That(row3, Is.EqualTo(new object[] { "Test2", "EFG", "YY", "10,143.27", "0.00" }));
Assert.That(row4, Is.EqualTo(new object[] { "Test3", "IJK", "ZZ", "10,143.27", "0.00" }));
});
}
}
}