Last active
August 29, 2015 14:03
-
-
Save sebgod/546440ec8fc7acb23ce2 to your computer and use it in GitHub Desktop.
A astral character safe first char method for C#
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
static class FirstCharUtf32 { | |
public static bool FirstChar(string Str, out int First) { | |
bool SUCCESS_INDICATOR; | |
int len = Str.Length; | |
if (len > 0) { | |
First = Str[0]; | |
if (char.IsSurrogate((char)First)) { | |
if (SUCCESS_INDICATOR = char.IsSurrogatePair(Str, 0)) { | |
First = char.ConvertToUtf32((char)First, Str[1]); | |
} | |
} else { | |
SUCCESS_INDICATOR = true; | |
} | |
} else { | |
First = 0; | |
SUCCESS_INDICATOR = false; | |
} | |
return SUCCESS_INDICATOR; | |
} | |
public static void TestFirstChar(char[] chars) { | |
int first; | |
string s = new string(chars); | |
bool success = FirstChar(s, out first); | |
string hex = ConvertStringToHex(s); | |
System.Console.WriteLine("First Char of {0} is {1:x} \t= {2}", hex, first, success); | |
} | |
public static void Main(string[] args) { | |
char c1 = (char)0xd800; | |
char c2 = (char)0xdc00; | |
TestFirstChar(new char[] {c1, c2}); | |
TestFirstChar(new char[] {c1}); | |
TestFirstChar(new char[] {c2}); | |
TestFirstChar(new char[] {}); | |
TestFirstChar(new char[] {'a'}); | |
} | |
public static string ConvertStringToHex(string str) | |
{ | |
System.Text.StringBuilder hex = new System.Text.StringBuilder(str.Length * 6 + 2); | |
hex.Append('"'); | |
foreach (int codeUnit in str) { | |
hex.AppendFormat("\\u{0:X2}", codeUnit); | |
} | |
hex.Append('"'); | |
return hex.ToString(); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment