Description:
EscapeString code does escaping by calling string.Replace a couple of times, this looks to me like a performance bottleneck because for every line a new string gets allocated and another one goes to the garbage collector.
I tried using a StringBuilder and, if my tests are correct, I got a great performance improvement.
How to repeat:
Here's a snippet class that computes time for 1milion strings using the provider and my version.
My results are 44 sec for the first version, 18 sec for the second:
using System;
using System.Collections.Generic;
using System.Text;
public class MyClass
{
public static void Main()
{
string s = @"wefdfmsad fsd fsd sdfsdf s fw eerf wef 45 tet h4687ir '' 45t4rg ' ' 'e rtg 45t45t "
+ "\"\"\"\"\"\"iunhoi\"ion\"oin\"oin\"\"oin \"\"\"\"p popompm \"\"\" wsrfs f we f34rfg 45gerg "
+ "\\popok\\pokpok \\ \\ \\ \\\\ po m \\\\ \\\\ompom rgt 4erg 45g`````oinp```ponpo`pom```````` "
+ "pomm´´´´´ ´ ´´pmpoom´´´´´pompom´´´´popio3m5rg 45 geh3 56htwge rt245g56ygergeggggggggge´´´´´´"
+ "’’’’’’’’ponpoompo’’’ ’ ’pom po lo kjbojb98inl ’’’pj09i op’09j’’’’09u0inuog’’’ ’’0o9unio o’’"
+ "fwr sdfe rtgefg e5 y4r gdfgdf ‘‘‘‘‘‘piojp p‘‘‘jpoj‘oi‘‘‘‘piojpu09j‘‘‘‘pojpoj09jhn‘‘‘09u0'9jp";
string s1, s2;
s1 = EscapeString(s);
s2 = EscapeStringNew(s);
WL(s1);
WL(s2);
if (s1 != s2)
{
WL("Strings are different!");
return;
}
DateTime dt1 = DateTime.Now;
for (int i = 0; i < 1000000; i++)
{
s1 = EscapeString(s);
}
WL(DateTime.Now - dt1);
DateTime dt2 = DateTime.Now;
for (int i = 0; i < 1000000; i++)
{
s1 = EscapeStringNew(s);
}
WL(DateTime.Now - dt2);
RL();
}
public static string EscapeString(string value)
{
value = value.Replace("\\", "\\\\");
value = value.Replace("\'", "\\\'");
value = value.Replace("\"", "\\\"");
value = value.Replace("`", "\\`");
value = value.Replace("´", "\\´");
value = value.Replace("’", "\\’");
value = value.Replace("‘", "\\‘");
return value;
}
public static string EscapeStringNew(string value)
{
StringBuilder sb = new StringBuilder();
for (int i = 0; i < value.Length; i++)
{
if (value[i] == '\\'
|| value[i] == '\''
|| value[i] == '\"'
|| value[i] == '`'
|| value[i] == '´'
|| value[i] == '’'
|| value[i] == '‘')
sb.Append("\\");
sb.Append(value[i]);
}
return sb.ToString();
}
#region Helper methods
private static void WL(object text, params object[] args)
{
Console.WriteLine(text.ToString(), args);
}
private static void RL()
{
Console.ReadLine();
}
private static void Break()
{
System.Diagnostics.Debugger.Break();
}
#endregion
}
Suggested fix:
Use a StringBuilder like this:
public static string EscapeStringNew(string value)
{
StringBuilder sb = new StringBuilder();
for (int i = 0; i < value.Length; i++)
{
if (value[i] == '\\'
|| value[i] == '\''
|| value[i] == '\"'
|| value[i] == '`'
|| value[i] == '´'
|| value[i] == '’'
|| value[i] == '‘')
sb.Append("\\");
sb.Append(value[i]);
}
return sb.ToString();
}
Description: EscapeString code does escaping by calling string.Replace a couple of times, this looks to me like a performance bottleneck because for every line a new string gets allocated and another one goes to the garbage collector. I tried using a StringBuilder and, if my tests are correct, I got a great performance improvement. How to repeat: Here's a snippet class that computes time for 1milion strings using the provider and my version. My results are 44 sec for the first version, 18 sec for the second: using System; using System.Collections.Generic; using System.Text; public class MyClass { public static void Main() { string s = @"wefdfmsad fsd fsd sdfsdf s fw eerf wef 45 tet h4687ir '' 45t4rg ' ' 'e rtg 45t45t " + "\"\"\"\"\"\"iunhoi\"ion\"oin\"oin\"\"oin \"\"\"\"p popompm \"\"\" wsrfs f we f34rfg 45gerg " + "\\popok\\pokpok \\ \\ \\ \\\\ po m \\\\ \\\\ompom rgt 4erg 45g`````oinp```ponpo`pom```````` " + "pomm´´´´´ ´ ´´pmpoom´´´´´pompom´´´´popio3m5rg 45 geh3 56htwge rt245g56ygergeggggggggge´´´´´´" + "’’’’’’’’ponpoompo’’’ ’ ’pom po lo kjbojb98inl ’’’pj09i op’09j’’’’09u0inuog’’’ ’’0o9unio o’’" + "fwr sdfe rtgefg e5 y4r gdfgdf ‘‘‘‘‘‘piojp p‘‘‘jpoj‘oi‘‘‘‘piojpu09j‘‘‘‘pojpoj09jhn‘‘‘09u0'9jp"; string s1, s2; s1 = EscapeString(s); s2 = EscapeStringNew(s); WL(s1); WL(s2); if (s1 != s2) { WL("Strings are different!"); return; } DateTime dt1 = DateTime.Now; for (int i = 0; i < 1000000; i++) { s1 = EscapeString(s); } WL(DateTime.Now - dt1); DateTime dt2 = DateTime.Now; for (int i = 0; i < 1000000; i++) { s1 = EscapeStringNew(s); } WL(DateTime.Now - dt2); RL(); } public static string EscapeString(string value) { value = value.Replace("\\", "\\\\"); value = value.Replace("\'", "\\\'"); value = value.Replace("\"", "\\\""); value = value.Replace("`", "\\`"); value = value.Replace("´", "\\´"); value = value.Replace("’", "\\’"); value = value.Replace("‘", "\\‘"); return value; } public static string EscapeStringNew(string value) { StringBuilder sb = new StringBuilder(); for (int i = 0; i < value.Length; i++) { if (value[i] == '\\' || value[i] == '\'' || value[i] == '\"' || value[i] == '`' || value[i] == '´' || value[i] == '’' || value[i] == '‘') sb.Append("\\"); sb.Append(value[i]); } return sb.ToString(); } #region Helper methods private static void WL(object text, params object[] args) { Console.WriteLine(text.ToString(), args); } private static void RL() { Console.ReadLine(); } private static void Break() { System.Diagnostics.Debugger.Break(); } #endregion } Suggested fix: Use a StringBuilder like this: public static string EscapeStringNew(string value) { StringBuilder sb = new StringBuilder(); for (int i = 0; i < value.Length; i++) { if (value[i] == '\\' || value[i] == '\'' || value[i] == '\"' || value[i] == '`' || value[i] == '´' || value[i] == '’' || value[i] == '‘') sb.Append("\\"); sb.Append(value[i]); } return sb.ToString(); }