RetroSearch Browse

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://learn.microsoft.com/en-us/dotnet/api/system.globalization.stringinfo below:

StringInfo Class (System.Globalization) | Microsoft Learn

StringInfo Class Definition

Provides functionality to split a string into text elements and to iterate through those text elements.

public ref class StringInfo

public class StringInfo

[System.Serializable]
public class StringInfo

[System.Serializable]
[System.Runtime.InteropServices.ComVisible(true)]
public class StringInfo

type StringInfo = class

[<System.Serializable>]
type StringInfo = class

[<System.Serializable>]
[<System.Runtime.InteropServices.ComVisible(true)>]
type StringInfo = class

Public Class StringInfo

Inheritance

Attributes

Examples

This example uses the GetTextElementEnumerator and ParseCombiningCharacters methods of the StringInfo class to manipulate a string that contains surrogate and combining characters.

using System;
using System.Text;
using System.Globalization;

public sealed class App {
   static void Main() {
      // The string below contains combining characters.
      String s = "a\u0304\u0308bc\u0327";

      // Show each 'character' in the string.
      EnumTextElements(s);

      // Show the index in the string where each 'character' starts.
      EnumTextElementIndexes(s);
   }

   // Show how to enumerate each real character (honoring surrogates) in a string.
   static void EnumTextElements(String s) {
      // This StringBuilder holds the output results.
      StringBuilder sb = new StringBuilder();

      // Use the enumerator returned from GetTextElementEnumerator
      // method to examine each real character.
      TextElementEnumerator charEnum = StringInfo.GetTextElementEnumerator(s);
      while (charEnum.MoveNext()) {
         sb.AppendFormat(
           "Character at index {0} is '{1}'{2}",
           charEnum.ElementIndex, charEnum.GetTextElement(),
           Environment.NewLine);
      }

      // Show the results.
      Console.WriteLine("Result of GetTextElementEnumerator:");
      Console.WriteLine(sb);
   }

   // Show how to discover the index of each real character (honoring surrogates) in a string.
   static void EnumTextElementIndexes(String s) {
      // This StringBuilder holds the output results.
      StringBuilder sb = new StringBuilder();

      // Use the ParseCombiningCharacters method to
      // get the index of each real character in the string.
      Int32[] textElemIndex = StringInfo.ParseCombiningCharacters(s);

      // Iterate through each real character showing the character and the index where it was found.
      for (Int32 i = 0; i < textElemIndex.Length; i++) {
         sb.AppendFormat(
            "Character {0} starts at index {1}{2}",
            i, textElemIndex[i], Environment.NewLine);
      }

      // Show the results.
      Console.WriteLine("Result of ParseCombiningCharacters:");
      Console.WriteLine(sb);
   }
}

// This code produces the following output:
//
// Result of GetTextElementEnumerator:
// Character at index 0 is 'aÌÌ'
// Character at index 3 is 'b'
// Character at index 4 is 'cÌ§'
//
// Result of ParseCombiningCharacters:
// Character 0 starts at index 0
// Character 1 starts at index 3
// Character 2 starts at index 4

Imports System.Text
Imports System.Globalization

Public Module Example
   Public Sub Main()
      ' The string below contains combining characters.
      Dim s As String = "a" + ChrW(&h0304) + ChrW(&h0308) + "bc" + ChrW(&h0327)

      ' Show each 'character' in the string.
      EnumTextElements(s)

      ' Show the index in the string where each 'character' starts.
      EnumTextElementIndexes(s)
   End Sub

   ' Show how to enumerate each real character (honoring surrogates) in a string.
   Sub EnumTextElements(s As String)
      ' This StringBuilder holds the output results.
      Dim sb As New StringBuilder()

      ' Use the enumerator returned from GetTextElementEnumerator 
      ' method to examine each real character.
      Dim charEnum As TextElementEnumerator = StringInfo.GetTextElementEnumerator(s)
      Do While charEnum.MoveNext()
         sb.AppendFormat("Character at index {0} is '{1}'{2}",
                         charEnum.ElementIndex, 
                         charEnum.GetTextElement(),
                         Environment.NewLine)
      Loop

      ' Show the results.
      Console.WriteLine("Result of GetTextElementEnumerator:")
      Console.WriteLine(sb)
   End Sub

   ' Show how to discover the index of each real character (honoring surrogates) in a string.
   Sub EnumTextElementIndexes(s As String)
      ' This StringBuilder holds the output results.
      Dim sb As New StringBuilder()

      ' Use the ParseCombiningCharacters method to 
      ' get the index of each real character in the string.
      Dim textElemIndex() As Integer = StringInfo.ParseCombiningCharacters(s)

      ' Iterate through each real character showing the character and the index where it was found.
      For i As Int32 = 0 To textElemIndex.Length - 1
         sb.AppendFormat("Character {0} starts at index {1}{2}",
                         i, textElemIndex(i), Environment.NewLine)
      Next

      ' Show the results.
      Console.WriteLine("Result of ParseCombiningCharacters:")
      Console.WriteLine(sb)
   End Sub
End Module
' The example displays the following output:
'
'       Result of GetTextElementEnumerator:
'       Character at index 0 is 'aÌÌ'
'       Character at index 3 is 'b'
'       Character at index 4 is 'cÌ§'
'       
'       Result of ParseCombiningCharacters:
'       Character 0 starts at index 0
'       Character 1 starts at index 3
'       Character 2 starts at index 4

.NET defines a text element as a unit of text that is displayed as a single character, that is, a grapheme. A text element can be a base character, a surrogate pair, or a combining character sequence. The Unicode Standard defines a surrogate pair as a coded character representation for a single abstract character that consists of a sequence of two code units, where the first unit of the pair is a high surrogate and the second is a low surrogate. The Unicode Standard defines a combining character sequence as a combination of a base character and one or more combining characters. A surrogate pair can represent a base character or a combining character.

The StringInfo class enables you to work with a string as a series of textual elements rather than individual Char objects.

To instantiate a StringInfo object that represents a specified string, you can do either of the following:

Call the StringInfo(String) constructor and pass it the string that the StringInfo object is to represent as an argument.
Call the default StringInfo() constructor, and assign the string that the StringInfo object is to represent to the String property.

You can work with the individual text elements in a string in two ways:

By enumerating each text element. To do this, you call the GetTextElementEnumerator method, and then repeatedly call the MoveNext method on the returned TextElementEnumerator object until the method returns false.
By calling the ParseCombiningCharacters method to retrieve an array that contains the starting index of each text element. You can then retrieve individual text elements by passing these indexes to the SubstringByTextElements method.

The following example illustrates both ways of working with the text elements in a string. It creates two strings:

strCombining, which is a string of Arabic characters that includes three text elements with multiple Char objects. The first text element is the base character ARABIC LETTER ALEF (U+0627) followed by ARABIC HAMZA BELOW (U+0655) and ARABIC KASRA (U+0650). The second text element is ARABIC LETTER HEH (U+0647) followed by ARABIC FATHA (U+064E). The third text element is ARABIC LETTER BEH (U+0628) followed by ARABIC DAMMATAN (U+064C).
strSurrogates, which is a string that includes three surrogate pairs: GREEK ACROPHONIC FIVE TALENTS (U+10148) from the Supplementary Multilingual Plane, U+20026 from the Supplementary Ideographic Plane, and U+F1001 from the private user area. The UTF-16 encoding of each character is a surrogate pair that consists of a high surrogate followed by a low surrogate.

Each string is parsed once by the ParseCombiningCharacters method and then by the GetTextElementEnumerator method. Both methods correctly parse the text elements in the two strings and display the results of the parsing operation.

using System;
using System.Globalization;

public class Example
{
   public static void Main()
   {
      // The Unicode code points specify Arabic base characters and
      // combining character sequences.
      string strCombining = "\u0627\u0655\u0650\u064A\u0647\u064E" +
                            "\u0627\u0628\u064C";

      // The Unicode code points specify private surrogate pairs.
      string strSurrogates = Char.ConvertFromUtf32(0x10148) +
                             Char.ConvertFromUtf32(0x20026) + "a" +
                             Char.ConvertFromUtf32(0xF1001);

      EnumerateTextElements(strCombining);
      EnumerateTextElements(strSurrogates);
   }

   public static void EnumerateTextElements(string str)
   {
      // Get the Enumerator.
      TextElementEnumerator teEnum = null;

      // Parse the string using the ParseCombiningCharacters method.
      Console.WriteLine("\nParsing with ParseCombiningCharacters:");
      int[] teIndices = StringInfo.ParseCombiningCharacters(str);

      for (int i = 0; i < teIndices.Length; i++) {
         if (i < teIndices.Length - 1)
            Console.WriteLine("Text Element {0} ({1}..{2})= {3}", i,
               teIndices[i], teIndices[i + 1] - 1,
               ShowHexValues(str.Substring(teIndices[i], teIndices[i + 1] -
                             teIndices[i])));
         else
            Console.WriteLine("Text Element {0} ({1}..{2})= {3}", i,
               teIndices[i], str.Length - 1,
               ShowHexValues(str.Substring(teIndices[i])));
      }
      Console.WriteLine();

      // Parse the string with the GetTextElementEnumerator method.
      Console.WriteLine("Parsing with TextElementEnumerator:");
      teEnum = StringInfo.GetTextElementEnumerator(str);

      int teCount = - 1;

      while (teEnum.MoveNext()) {
         // Displays the current element.
         // Both GetTextElement() and Current retrieve the current
         // text element. The latter returns it as an Object.
         teCount++;
         Console.WriteLine("Text Element {0} ({1}..{2})= {3}", teCount,
            teEnum.ElementIndex, teEnum.ElementIndex +
            teEnum.GetTextElement().Length - 1, ShowHexValues((string)(teEnum.Current)));
      }
   }

   private static string ShowHexValues(string s)
   {
      string hexString = "";
      foreach (var ch in s)
         hexString += $"{(ushort)ch:X4} ";

      return hexString;
   }
}
// The example displays the following output:
//       Parsing with ParseCombiningCharacters:
//       Text Element 0 (0..2)= 0627 0655 0650
//       Text Element 1 (3..3)= 064A
//       Text Element 2 (4..5)= 0647 064E
//       Text Element 3 (6..6)= 0627
//       Text Element 4 (7..8)= 0628 064C
//
//       Parsing with TextElementEnumerator:
//       Text Element 0 (0..2)= 0627 0655 0650
//       Text Element 1 (3..3)= 064A
//       Text Element 2 (4..5)= 0647 064E
//       Text Element 3 (6..6)= 0627
//       Text Element 4 (7..8)= 0628 064C
//
//       Parsing with ParseCombiningCharacters:
//       Text Element 0 (0..1)= D800 DD48
//       Text Element 1 (2..3)= D840 DC26
//       Text Element 2 (4..4)= 0061
//       Text Element 3 (5..6)= DB84 DC01
//
//       Parsing with TextElementEnumerator:
//       Text Element 0 (0..1)= D800 DD48
//       Text Element 1 (2..3)= D840 DC26
//       Text Element 2 (4..4)= 0061
//       Text Element 3 (5..6)= DB84 DC01

Imports System.Globalization

Public Module Example
   Public Sub Main()
      ' The Unicode code points specify Arabic base characters and 
      ' combining character sequences.
      Dim strCombining As String = ChrW(&H627) & ChrW(&h0655) + ChrW(&H650) & 
              ChrW(&H64A) & ChrW(&H647) & ChrW(&H64E) & ChrW(&H627) & 
              ChrW(&H628) & ChrW(&H64C)

      ' The Unicode code points specify private surrogate pairs.
      Dim strSurrogates As String = Char.ConvertFromUtf32(&h10148) +
                                    Char.ConvertFromUtf32(&h20026) + "a" +
                                    Char.ConvertFromUtf32(&hF1001)
      
      EnumerateTextElements(strCombining)
      EnumerateTextElements(strSurrogates)
   End Sub

   Public Sub EnumerateTextElements(str As String)
      ' Get the Enumerator.
      Dim teEnum As TextElementEnumerator = Nothing      

      ' Parse the string using the ParseCombiningCharacters method.
      Console.WriteLine()
      Console.WriteLine("Parsing with ParseCombiningCharacters:")
      Dim teIndices As Integer() = StringInfo.ParseCombiningCharacters(str)
      
      For i As Integer = 0 To teIndices.Length - 1
         If i < teIndices.Length - 1 Then
            Console.WriteLine("Text Element {0} ({1}..{2})= {3}", i, 
               TEIndices(i), TEIndices((i + 1)) - 1, 
               ShowHexValues(str.Substring(TEIndices(i), TEIndices((i + 1)) - 
                             teIndices(i))))
         Else
            Console.WriteLine("Text Element {0} ({1}..{2})= {3}", i, 
               teIndices(i), str.Length - 1, 
               ShowHexValues(str.Substring(teIndices(i))))
         End If
      Next
      Console.WriteLine()

      ' Parse the string with the GetTextElementEnumerator method.
      Console.WriteLine("Parsing with TextElementEnumerator:")
      teEnum = StringInfo.GetTextElementEnumerator(str)

      Dim TECount As Integer = - 1

      While teEnum.MoveNext()
         ' Prints the current element.
         ' Both GetTextElement() and Current retrieve the current
         ' text element. The latter returns it as an Object.
         TECount += 1
         Console.WriteLine("Text Element {0} ({1}..{2})= {3}", teCount, 
            teEnum.ElementIndex, teEnum.ElementIndex + 
            teEnum.GetTextElement().Length - 1, ShowHexValues(CStr(teEnum.Current)))
      End While
   End Sub
   
   Private Function ShowHexValues(s As String) As String
      Dim hexString As String = ""
      For Each ch In s
         hexString += String.Format("{0:X4} ", Convert.ToUInt16(ch))
      Next
      Return hexString
   End Function
End Module
' The example displays the following output:
'       Parsing with ParseCombiningCharacters:
'       Text Element 0 (0..2)= 0627 0655 0650
'       Text Element 1 (3..3)= 064A
'       Text Element 2 (4..5)= 0647 064E
'       Text Element 3 (6..6)= 0627
'       Text Element 4 (7..8)= 0628 064C
'       
'       Parsing with TextElementEnumerator:
'       Text Element 0 (0..2)= 0627 0655 0650
'       Text Element 1 (3..3)= 064A
'       Text Element 2 (4..5)= 0647 064E
'       Text Element 3 (6..6)= 0627
'       Text Element 4 (7..8)= 0628 064C
'       
'       Parsing with ParseCombiningCharacters:
'       Text Element 0 (0..1)= D800 DD48
'       Text Element 1 (2..3)= D840 DC26
'       Text Element 2 (4..4)= 0061
'       Text Element 3 (5..6)= DB84 DC01
'       
'       Parsing with TextElementEnumerator:
'       Text Element 0 (0..1)= D800 DD48
'       Text Element 1 (2..3)= D840 DC26
'       Text Element 2 (4..4)= 0061
'       Text Element 3 (5..6)= DB84 DC01

Notes to Callers

Internally, the methods of the StringInfo class call the methods of the CharUnicodeInfo class to determine character categories. Starting with the .NET Framework 4.6.2, character classification is based on The Unicode Standard, Version 8.0.0. For the .NET Framework 4 through the .NET Framework 4.6.1, it is based on The Unicode Standard, Version 6.3.0. In .NET Core, it is based on The Unicode Standard, Version 8.0.0.

Constructors Properties Methods See also

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4