StringInfo 类

定义

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

继承

Object

StringInfo

属性

SerializableAttribute ComVisibleAttribute

示例

此示例使用 GetTextElementEnumerator 类的 StringInfo 和 ParseCombiningCharacters 方法来操作包含代理和组合字符的字符串。

using namespace System;
using namespace System::Text;
using namespace System::Globalization;


// Show how to enumerate each real character (honoring surrogates)
// in a string.

void EnumTextElements(String^ combiningChars)
{
    // This StringBuilder holds the output results.
    StringBuilder^ sb = gcnew StringBuilder();

    // Use the enumerator returned from GetTextElementEnumerator
    // method to examine each real character.
    TextElementEnumerator^ charEnum =
        StringInfo::GetTextElementEnumerator(combiningChars);
    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.

void EnumTextElementIndexes(String^ combiningChars)
{
    // This StringBuilder holds the output results.
    StringBuilder^ sb = gcnew StringBuilder();

    // Use the ParseCombiningCharacters method to
    // get the index of each real character in the string.
    array <int>^ textElemIndex =
        StringInfo::ParseCombiningCharacters(combiningChars);

    // Iterate through each real character showing the character
    // and the index where it was found.
    for (int 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);
}

int main()
{

    // The string below contains combining characters.
    String^ combiningChars = L"a\u0304\u0308bc\u0327";

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

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

};

// This code produces the following output.
//
// Result of GetTextElementEnumerator:
// Character at index 0 is 'a-"'
// Character at index 3 is 'b'
// Character at index 4 is 'c,'
//
// Result of ParseCombiningCharacters:
// Character 0 starts at index 0
// Character 1 starts at index 3
// Character 2 starts at index 4

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 'ā̈'
// Character at index 3 is 'b'
// Character at index 4 is 'ç'
//
// 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 'ā̈'
'       Character at index 3 is 'b'
'       Character at index 4 is 'ç'
'       
'       Result of ParseCombiningCharacters:
'       Character 0 starts at index 0
'       Character 1 starts at index 3
'       Character 2 starts at index 4

注解

.NET 将文本元素定义为显示为单个字符（即 grapheme）的文本单元。 文本元素可以是基字符、代理项对或组合字符序列。 Unicode Standard 将代理项对定义为单个抽象字符的编码字符表示形式，该抽象字符由两个代码单元组成的序列组成，其中对的第一个单元是高代理项，第二个是低代理项。 Unicode 标准将组合字符序列定义为基字符和一个或多个组合字符的组合。 代理项对可以表示基字符或组合字符。

StringInfo 类使您能够将字符串作为一系列文本元素而不是单个 Char 对象进行处理。

若要实例化 StringInfo 表示指定字符串的对象，可以执行以下任一操作：

• StringInfo(String)调用构造函数，并向其传递对象要表示为参数的StringInfo字符串。

• 调用默认 StringInfo() 构造函数，并将 对象要表示的 StringInfo 字符串分配给 属性 String 。

可通过两种方式处理字符串中的单个文本元素：

• 通过枚举每个文本元素。 为此，您可以调用 GetTextElementEnumerator 方法，然后对返回的 MoveNext 对象重复调用 TextElementEnumerator 方法，直到此方法返回 false。

• 通过调用 ParseCombiningCharacters 方法检索包含每个文本元素的起始索引的数组。 然后可通过将这些索引传递给 SubstringByTextElements 方法来检索单个文本元素。

下面的示例阐释了两种处理字符串中的文本元素的方法。 它创建两个字符串：

• strCombining，它是一个阿拉伯语字符串，包含三个文本元素和多个 Char 对象。 第一个文本元素是基字符阿拉伯字母 ALEF (U+0627) ，后跟 (U+0655) 和阿拉伯语 KASRA (U+0650) 。 第二个文本元素是阿拉伯文字母 HEH (U+0647) ，后跟阿拉伯文 FATHA (U+064E) 。 第三个文本元素是阿拉伯文字母 BEH (U+0628) 后跟阿拉伯语 DAMMATAN (U+064C) 。

• strSurrogates，它是包含三个代理项对的字符串：来自补充多语言平面的希腊文 ACROPHONIC FIVE TALENTS (U+10148) 、来自补充象形平面的 U+20026 和来自专用用户区域的 U+F1001。 每个字符的 UTF-16 编码是一个代理项对，其中依次包含一个高代理项和一个低代理项。

每个字符串依次通过 ParseCombiningCharacters 方法和 GetTextElementEnumerator 方法分析一次。 两个方法都可正确分析两个字符串中的文本元素并显示分析操作的结果。

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

调用方说明

在内部，类的方法 StringInfo 调用 类的方法 CharUnicodeInfo 来确定字符类别。 从 .NET Framework 4.6.2 开始，字符分类基于 Unicode 标准版本 8.0.0。 对于 .NET Framework 4 到 .NET Framework 4.6.1，它基于 Unicode Standard 版本 6.3.0。 在 .NET Core 中，它基于 Unicode Standard 版本 8.0.0。

构造函数

属性

方法

适用于

另请参阅

• 对 Windows 操作系统的权重表进行排序
• Linux 和 macOS 的默认 Unicode 排序规则元素表