namespace SharepointToolbox.Services.Export;
///
/// CSV field sanitization. Adds RFC 4180 quoting plus formula-injection
/// protection: Excel and other spreadsheet apps treat cells starting with
/// '=', '+', '-', '@', tab, or CR as formulas. Prefixing with a single
/// quote neutralizes the formula while remaining readable.
///
internal static class CsvSanitizer
{
///
/// Escapes a value for inclusion in a CSV row. Always wraps in double
/// quotes. Doubles internal quotes per RFC 4180. Prepends an apostrophe
/// when the value begins with a character a spreadsheet would evaluate.
///
public static string Escape(string? value)
{
if (string.IsNullOrEmpty(value)) return "\"\"";
var safe = NeutralizeFormulaPrefix(value).Replace("\"", "\"\"");
return $"\"{safe}\"";
}
///
/// Minimal quoting variant: only wraps in quotes when the value contains
/// a delimiter, quote, or newline. Still guards against formula injection.
///
public static string EscapeMinimal(string? value)
{
if (string.IsNullOrEmpty(value)) return string.Empty;
var safe = NeutralizeFormulaPrefix(value);
if (safe.Contains(',') || safe.Contains('"') || safe.Contains('\n') || safe.Contains('\r'))
return $"\"{safe.Replace("\"", "\"\"")}\"";
return safe;
}
private static string NeutralizeFormulaPrefix(string value)
{
if (value.Length == 0) return value;
char first = value[0];
if (first == '=' || first == '+' || first == '-' || first == '@'
|| first == '\t' || first == '\r')
{
return "'" + value;
}
return value;
}
}