/// <summary>
/// Remove all vulnerable urls with all 0 for classification
/// </summary>
/// <remarks>
/// This doesn't seem correct. However, looking through many of the returned results are not acutally XSS vulns
/// Some were generic urls and some were SQL injections.
/// </remarks>
private static void cleanData() {
var falsePositive = new Classification("", "TRUE");
var data = File.ReadAllLines(FileManager.VULN_URL_LIST_FILE);
List<Classification> cl = data.Select(url => new Classification(url, "TRUE")).Where(c => c.AreIdentical(falsePositive)).ToList();
List<string> urls = cl.Select(c => c.url).ToList();
File.WriteAllLines("test.txt", urls);
}
/// <summary>
/// Compares two classifications and returns whether they are identical ignoring the source url
/// </summary>
/// <param name="c">The classification to compare with</param>
/// <returns>True if the two are identical</returns>
public bool AreIdentical(Classification c) {
if (c == null) return false;
if (c.Characters != this.Characters) return false;
if (c.Class != this.Class) return false;
if (c.DomEvents != this.DomEvents) return false;
if (c.EncodedCharacters != this.EncodedCharacters) return false;
if (c.JsEventHandlers != this.JsEventHandlers) return false;
if (c.ScriptCount != this.ScriptCount) return false;
return true;
}