Develop Reference

truncating an existing JSON string at a given level of depth - Performance optimization

i am currently searching for a way to truncate a JSON string in order to improve logging performance and file size.
My plan is truncating the JSON string at a certain level of depth by appending "..." instead of actual data to a StringBuilder, so for example
{
"data":{
"1":"test",
"2":"test"
}
}
will become:
{
"data":{...}
}
The JSON payload i am trying to log has a length of around 20000 characters. The function i have already written truncates it to around 1000, which is fine for me.
Here's the code:
int c = 0;
int max = 3; //in the actual code, this is configurable of course.
bool locked = false;
char current;
bool inc = true;
bool insideString = false;
bool escaped = false;
for (int i = 0; i < text.Length; i++)
//foreach(char current in text) does not seem to improve performance in any meaningful way
{
inc = false;
current = text[i];
if (current == '{') inc = true;
else if (current == '}') c--;
if (c < max)
{
//handle braces inside strings as suggested by Jeremy Lakeman
if (!escaped && current == '\"') insideString = !insideString;
else if (current == '\\') escaped = true;
builder.Append(current);
locked = false;
}
else
{
if (!locked)
{
builder.Append("...");
locked = true;
}
}
if (inc) c++;
}
I have kept the variables outside of the loop in order to avoid any performance overhead that could be created through variable initialization.
Do you think there any way this code's performance could be improved any further?
I'm looking forward to hearing your opinions!
Edit: I've created two methods for benchmarking, one using substrings, one using pure character parsing. Here are the results:
[Benchmark]
public void Variant1()
{
var builder = new StringBuilder();
var c = 0;
char current;
int max = 3;
bool insideString = false;
int next;
for (int i = 0; i < text.Length; i++)
{
current = text[i];
if (current == '\"' && text[i - 1] != '\\')
{
insideString = !insideString;
}
if (!insideString && (current == '{' || current == '}'))
{
int mod = 124 - current;
c += mod;
if (c == max - 1 && mod == -1)
{
builder.Append("{...");
continue;
}
}
if (c >= max)
{
next = text.IndexOfAny(chars, i + 1);
if (next >= 0) i = next - 1;
continue;
}
builder.Append(current);
}
}
[Benchmark]
public void Variant2()
{
var builder = new StringBuilder();
var c = 0;
char current;
int max = 3;
bool insideString = false;
int next = -1;
int prev = 0;
while ((next = text.IndexOfAny(chars, next + 1)) >= 0)
{
current = text[next];
if (current == '\"' && text[next - 1] != '\\')
{
insideString = !insideString;
}
if (c < max) builder.Append(text[prev..next]);
if (!insideString && (current == '{' || current == '}'))
{
int mod = 124 - current;
c += mod;
if (c == max && mod == 1)
{
builder.Append("{...");
continue;
}
}
prev = next;
}
}
| Method | Mean | Error | StdDev |
|--------- |---------:|---------:|---------:|
| Variant1 | 30.94 us | 0.443 us | 0.392 us |
| Variant2 | 30.16 us | 0.582 us | 0.454 us |
as you can see, both methods are nearly identical in speed.

How to write a code for my decrypt without special character

I am only able to encrypt, but i do not how to decrypt. Someone please help. Do I have to declare a bool variable?
Or is that any other better way to do it?
string UserInput = "";
int shift;
Shift OBSHIFT = new Shift();
Console.Write("\nType a string to encrypt:");
UserInput = Console.ReadLine();
Console.Write("How many chars would you like to shift?: ");
shift = int.Parse(Console.ReadLine());
Console.WriteLine("\nApplying Caesar cipher ... ");
Console.Write("Your encrypted string is: ");
Console.WriteLine(OBSHIFT.Cshift(UserInput, shift));
Console.Read();
}
}
class Shift
{
public string Cshift(string str, int shift )
{
string UserOutput = "";
char[] A = null;
A = str.ToCharArray();
int temp;
for (int i = 0; i < str.Length; i++)
{
char c = A[i];
if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'))
{
temp = (int)(A[i] + shift);
if ((c >= 'A' && c <= 'Z' && temp > 'Z') || (c >= 'a' && c <= 'z' && temp > 'z'))
temp = temp - 26;
else
temp = (int)(A[i] + (shift));
}
else
temp = c;
UserOutput += (char)temp;
}
return UserOutput;
}
}
}
}

Talking about Caesar cipher, you can simply negate the shift and get the original string.
I.e., cshift(cshift(string, x), -x) == string.
Using your Shift class:
int sh = 17;
string original = "abcdefgh";
string encrypted = shift.Cshift(original, sh);
string decrypted = shift.Cshift(shifted, -sh);
Console.WriteLine(decrypted == original); // true
For convenience, you can create a method Decrypt, which will do this:
class Shift
{
public string Encrypt(string originalString, int shift)
{
string userOutput = "";
char[] a = originalString.ToCharArray();
for (int i = 0; i < originalString.Length; i++)
{
char c = a[i];
int temp;
if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'))
{
temp = (int)(a[i] + shift);
if ((c >= 'A' && c <= 'Z' && temp > 'Z') || (c >= 'a' && c <= 'z' && temp > 'z'))
temp = temp - 26;
else
temp = (int)(a[i] + (shift));
}
else
temp = c;
userOutput += (char)temp;
}
return userOutput;
}
public string Decrypt(string cipherString, int shift)
{
return Encrypt(cipherString, -shift);
}
}
Note that I have also done some little code improvements like:
combined declaration and assignment of A
moved temp into the inner scope
gave the proper names to the local variables (lower-case)

find common substrings in 2 string in c#

I have strings like:
1) Cookie:ystat_tw_ss376223=9_16940400_234398;
2) Cookie:zynga_toolbar_fb_uid=1018132522
3) GET /2009/visuels/Metaboli_120x600_UK.gif HTTP/1.1
4) GET /2010/07/15/ipad-3hk-smv-price-hk/ HTTP/1.1
1 ad 2 have common substtring{cookie:}
3 and 4 have common substtring{GET /20, HTTP/1.1}
I want to find all common substrings that have the length more than three characters(contain space character) between 2 strings.(like 1 and 2)
i want to code in c#. i have a program but it has some problems.
Could anyone help me?
public static string[] MyMCS2(string a, string b)
{
string[] st = new string[100];
// List<string> st = new List<string>();
List<char> f = new List<char>();
int ctr = 0;
char[] str1 = a.ToCharArray();
char[] str2 = b.ToCharArray();
int m = 0;
int n = 0;
while (m < str1.Length)
{
for (n = 0; n < str2.Length; n++)
{
if (m < str1.Length)
{
if (str1[m] == str2[n])
{
if ((m > 1) && (n > 1) &&(str1[m - 1] == str2[n - 1]) && (str1[m - 2] == str2[n - 2]))
{
//f[m]= str1[m];
f.Add(str1[m]);
char[] ff = f.ToArray();
string aaa = new string(ff);
if (aaa.Length >= 3)
{
st[ctr] = aaa + "()";
//st.Add(aaa);
ctr++;
}
kk = m;
m++;
}
else if ((n == 0) ||(n == 1))
{
f.Add(str1[m]);
kk = m;
m++;
}
else
f.Clear();
}
//else if ((str1[m] == str2[n]) && (m == str1.Length - 1) && (n == str2.Length - 1))
//{
// f.Add(str1[m]);
// char[] ff = f.ToArray();
// string aaa = new string(ff);
// if (aaa.Length >= 3)
// {
// st[ctr] = aaa;
// ctr++;
// }
// // m++;
//}
else if ((str1[m] != str2[n]) && (n == (str2.Length - 1)))
{
m++;
}
else if ((m > 1) && (n > 1) && (str1[m] != str2[n]) && (str1[m - 1] == str2[n - 1]) && (str1[m - 2] == str2[n - 2]) && (str1[m - 3] == str2[n - 3]))
{
//
char[] ff = f.ToArray();
string aaa = new string(ff);
if (aaa.Length >= 3)
{
st[ctr] = aaa + "()" ;
//st.Add(aaa);
ctr++;
f.Clear();
}
//f.Clear();
//for (int h = 0; h < ff.Length; h++)
//{
// f[h] = '\0';
//}
}
else if (str1[m] != str2[n])
continue;
}
}
}
//int gb = st.Length;
return st;
}

This is an exact matching problem not a substring. You can solve it with aho-corasick algorithm. Use the first string and compute a finite state machine. Then process the search string. You can extend the aho-corasick algorithm to use a wildcard and search also for substrings. You can try this animated example: http://blog.ivank.net/aho-corasick-algorithm-in-as3.html

Compare string using bitwise shift operation

So i am new to csharp and i cant seem to find a logical error here in this program.i am learning the bitwise shift operators as i am new to these operators. I need help tracing a fault in my code. the program encodes an input String and decodes the encoded String after.After that i compare the string to see if they are equal.They seem to be equal to me but i keep getting a false when i compare them. Here is my code:
class Program
{
static char[] transcode = new char[64];
private static void prep()
{
for (int i = 0; i < transcode.Length; i++)
{
transcode[i] = (char)((int)'A' + i);
if (i > 25 && i <= 51)
{
transcode[i] = (char)((int)transcode[i] + 6);
}
else if (i > 51)
{
transcode[i] = (char)((int)transcode[i] - 0x4b);
}
}
transcode[transcode.Length - 3] = '+';
transcode[transcode.Length - 2] = '/';
transcode[transcode.Length - 1] = '=';
}
static void Main(string[] args)
{
prep();
string test_string = "a";
if (Convert.ToBoolean(String.Compare(test_string, decode(encode(test_string)))))
{
Console.WriteLine("Test succeeded");
}
else
{
Console.WriteLine("Test failed");
}
}
private static string encode(string input)
{
int l = input.Length;
int cb = (l / 3 + (Convert.ToBoolean(l % 3) ? 1 : 0)) * 4;// (0 +(1))*4 =4
char[] output = new char[cb];
for (int i = 0; i < cb; i++)
{
output[i] = '=';
}
int c = 0;
int reflex = 0;
const int s = 0x3f;
for (int j = 0; j < l; j++)
{
reflex <<= 8;
reflex &= 0x00ffff00;
reflex += input[j];
int x = ((j % 3) + 1) * 2;
int mask = s << x;
while (mask >= s)
{
int pivot = (reflex & mask) >> x;
output[c++] = transcode[pivot];
char alpha = transcode[pivot];
int invert = ~mask;
reflex &= invert;
mask >>= 6;
x -= 6; //-4
}
}
switch (l % 3)
{
case 1:
reflex <<= 4; //16
output[c++] = transcode[reflex];
char at16 = transcode[16];
// Console.WriteLine("Character at 16 is: " + at16);
break;
case 2:
reflex <<= 2;
output[c++] = transcode[reflex];
break;
}
return new string(output);//final value is: YQ== (Encoded String.)
}
private static string decode(string input)//input is YQ== which has a length of 4
{
int l = input.Length;
int cb = (l / 4 + ((Convert.ToBoolean(l % 4)) ? 1 : 0)) * 3 + 1; // (1 + (0))*4
char[] output = new char[cb]; //4 in length
int c = 0;
int bits = 0;
int reflex = 0;
for (int j = 0; j < l; j++)
{
reflex <<= 6;
bits += 6;
bool fTerminate = ('=' == input[j]);
if (!fTerminate)
{
reflex += indexOf(input[j]);
while (bits >= 8)
{
int mask = 0x000000ff << (bits % 8);
output[c++] = (char)((reflex & mask) >> (bits % 8)); //convert issue cannot implicitly convert to proper data type.so will have to explicitly convert.
int invert = ~mask;
reflex &= invert;
bits -= 8;
}
}
else
{
break;
}
}
return new string(output);
}
private static int indexOf(char ch)
{
int index;
for (index = 0; index < transcode.Length; index++)
if (ch == transcode[index])
break;
return index;
}
}

Read the docs for String.Compare then read the docs for Convert.ToBoolean. Pay particular attention to the value returned by String.Compare when two strings are equal. Then compare with how that value gets converted to a boolean by ToBoolean
String.Compare is designed for sorting strings. It returns 0 when two strings are equal. ToBoolean will convert that 0 to false. So when you strings are equal, your if evaluates to false and not true.
A simple change would be:
if (String.Compare(test_string, decode(encode(test_string)))==0)
{
Console.WriteLine("Test succeeded");
}
else
{
Console.WriteLine("Test failed");
}
#Tom's comment about the trailing nulls also applies, but it seems that String.Compare just ignores them.

ByteArrayOutputStream in C#

I have the following code in Java:
public static byte[] hex(String hex) {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
int nexti = 0;
int nextb = 0;
boolean highoc = true;
outer:
while (true)
{
int number = -1;
while (number == -1) {
if (nexti == hex.length()) {
break outer;
}
char chr = hex.charAt(nexti);
if ((chr >= '0') && (chr <= '9'))
number = chr - '0';
else if ((chr >= 'a') && (chr <= 'f'))
number = chr - 'a' + 10;
else if ((chr >= 'A') && (chr <= 'F'))
number = chr - 'A' + 10;
else {
number = -1;
}
nexti++;
}
if (highoc) {
nextb = number << 4;
highoc = false;
} else {
nextb |= number;
highoc = true;
baos.write(nextb);
}
}
label161: return baos.toByteArray();
}
I'm trying to convert it to C#, and failing, because MemoryStream is the only option, and I don't have a buffer.
This is what I have now:
public static byte[] fromString(string hex)
{
MemoryStream baos = new MemoryStream();
int nexti = 0;
int nextb = 0;
bool highoc = true;
for (; ; )
{
int number = -1;
while (number == -1)
{
if (nexti == hex.Length)
{
goto END;
}
char chr = hex.ToCharArray()[nexti];
if (chr >= '0' && chr <= '9')
{
number = chr - '0';
}
else if (chr >= 'a' && chr <= 'f')
{
number = chr - 'a' + 10;
}
else if (chr >= 'A' && chr <= 'F')
{
number = chr - 'A' + 10;
}
else
{
number = -1;
}
nexti++;
}
if (highoc)
{
nextb = number << 4;
highoc = false;
}
else
{
nextb |= number;
highoc = true;
baos.Write(nextb);
}
}
END:
return baos.toByteArray();
}
What else can I do to make it work like the way in Java?.. Thanks.

Here is something similar
public static byte[] StringToByteArrayFastest(string hex) {
if (hex.Length % 2 == 1)
throw new Exception("The binary key cannot have an odd number of digits");
byte[] arr = new byte[hex.Length >> 1];
for (int i = 0; i < hex.Length >> 1; ++i)
{
arr[i] = (byte)((GetHexVal(hex[i << 1]) << 4) + (GetHexVal(hex[(i << 1) + 1])));
}
return arr;
}
public static int GetHexVal(char hex) {
int val = (int)hex;
//For uppercase A-F letters:
return val - (val < 58 ? 48 : 55);
//For lowercase a-f letters:
//return val - (val < 58 ? 48 : 87);
//Or the two combined, but a bit slower:
//return val - (val < 58 ? 48 : (val < 97 ? 55 : 87));
}
or
public static byte[] StringToByteArray(String hex)
{
int NumberChars = hex.Length;
byte[] bytes = new byte[NumberChars / 2];
for (int i = 0; i < NumberChars; i += 2)
bytes[i / 2] = Convert.ToByte(hex.Substring(i, 2), 16);
return bytes;
}
or
private byte[] HexStringToByteArray(string hexString)
{
int hexStringLength = hexString.Length;
byte[] b = new byte[hexStringLength / 2];
for (int i = 0; i < hexStringLength; i += 2)
{
int topChar = (hexString[i] > 0x40 ? hexString[i] - 0x37 : hexString[i] - 0x30) << 4;
int bottomChar = hexString[i + 1] > 0x40 ? hexString[i + 1] - 0x37 : hexString[i + 1] - 0x30;
b[i / 2] = Convert.ToByte(topChar + bottomChar);
}
return b;
}
Here is alot more of them.
How do you convert Byte Array to Hexadecimal String, and vice versa?