字符串索引
更新:2007 年 11 月
System.Globalization.StringInfo 类提供了一些方法,可用于将字符串拆分为文本元素,并循环访问这些文本元素。文本元素是显示为单字符的文本单元,称作字素。文本元素可以是基字符、代理项对或组合字符序列。有关代理项对和组合字符序列的更多信息,请参见代理项对和组合字符序列的 Unicode 支持。
使用 StringInfo.GetTextElementEnumerator 方法可以创建可循环访问字符串元素的枚举数。使用 StringInfo.ParseCombiningCharacters 方法可返回指定字符串中每一个基字符、高代理项或控制字符的索引。
在下面的代码示例中,将创建一个包含组合字符序列的阿拉伯字符串。例如,在 strCombining 中,Unicode 代码 U+0625 表示一个阿拉伯基字符(后面带有 Hamza 的阿拉伯文字母 Alef),Unicode 代码 U+0650 表示一个阿拉伯组合字符(阿拉伯文 Kasra)。这两个代码合在一起表示一个组合字符序列,因此必须被分析为单个文本元素。接下来,创建一个包含代理项对的字符串。例如,在 strSurrogates 中,Unicode 代码 U+DACE 表示一个高代理项,Unicode 代码 U+DEFF 表示一个低代理项。这两个代码合在一起表示一个代理项对,并且必须被分析为单个文本元素。每一个字符串用 ParseCombiningCharacters 方法分析一次,再用 GetTextElementEnumerator 方法分析一次。这两个方法都将正确分析 strCombining 中位于索引 0、2、3、5 和 6 处的文本元素。这两个方法都将正确分析 strSurrogates 中位于索引 0、2、4、5 和 6 处的文本元素。分析操作的结果将显示出来。
Imports System
Imports System.IO
Imports System.Globalization
Imports System.Text
Imports Microsoft.VisualBasic
Public Class StringInfoSample
Public Shared Sub Main()
' Creates a string with text elements at <0;2;3;5;6>.
' The Unicode code points specify Arabic
' combining character sequences.
Dim strCombining As String = ChrW(&H625) & ChrW(&H650) & _
ChrW(&H64A) & ChrW(&H647) & ChrW(&H64E) & ChrW(&H627) & _
ChrW(&H628) & ChrW(&H64C)
' Creates a string with text elements at <0;2;4;5;6>.
'The Unicode code points specify private surrogate pairs.
Dim strSurrogates As String = ChrW(&HDACE) & ChrW(&HDEFF) & _
ChrW(&HDAAF) & ChrW(&HDEFC) & "a" & ChrW(&HD8BF) & ChrW(&HDD99)
EnumerateTextElements(strCombining)
EnumerateTextElements(strSurrogates)
End Sub
Public Shared Sub EnumerateTextElements(str As String)
' Creates a TextElementEnumerator.
Dim TEIndices As Integer() = Nothing
Dim TEEnum As TextElementEnumerator = Nothing
' Parses the string using the ParseCombiningCharacters() method.
Console.WriteLine(ControlChars.Newline + "Parsing '{0}' Using _
ParseCombiningCharacters()...", str)
Dim i As Integer
TEIndices = StringInfo.ParseCombiningCharacters(str)
For i = 0 To (TEIndices.Length - 1) - 1
Console.WriteLine("Text Element {0} ({1}..{2})= {3}", i, _
TEIndices(i), TEIndices((i + 1)) - 1, _
str.Substring(TEIndices(i), TEIndices((i + 1)) - _
TEIndices(i)))
Next i
Console.WriteLine("Text Element {0} ({1}..{2})= {3}", i, _
TEIndices(i), str.Length - 1, str.Substring(TEIndices(i)))
' Parses the string using the GetTextElementEnumerator method.
Console.WriteLine(ControlChars.Newline + "Parsing '{0}' Using _
TextElementEnumerator...", str)
TEEnum = StringInfo.GetTextElementEnumerator(str)
Dim Continue As Boolean = False
Dim TECount As Integer = - 1
' Note: Begins at element -1 (none).
Continue = TEEnum.MoveNext()
While Continue
' 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, TEEnum.Current)
' Moves to the next element.
Continue = TEEnum.MoveNext()
End While
End Sub
End Class
using System;
using System.IO;
using System.Globalization;
using System.Text;
public class StringInfoSample
{
public static void Main()
{
// Creates a string with text elements at <0;2;3;5;6>.
// The Unicode code points specify Arabic
// combining character sequences.
string strCombining =
"\u0625\u0650\u064A\u0647\u064E\u0627\u0628\u064C";
// Creates a string with text elements at <0;2;4;5;6>.
// The Unicode code points specify private surrogate pairs.
string strSurrogates = "\uDACE\uDEFF\uDAAF\uDEFCa\uD8BF\uDD99";
EnumerateTextElements(strCombining);
EnumerateTextElements(strSurrogates);
}
public static void EnumerateTextElements(string str)
{
// Creates a TextElementEnumerator.
int[] TEIndices = null;
TextElementEnumerator TEEnum = null;
// Parses the string using the ParseCombiningCharacters() method.
Console.WriteLine
("\r\nParsing '{0}' Using ParseCombiningCharacters()...",str);
int i;
TEIndices = StringInfo.ParseCombiningCharacters(str);
for (i = 0; i < (TEIndices.Length - 1); i++)
{
Console.WriteLine
("Text Element {0} ({1}..{2})=
{3}",i,TEIndices[i],TEIndices[i+1] - 1,
str.Substring(TEIndices[i],TEIndices[i+1] - TEIndices[i]));
}
Console.WriteLine
("Text Element {0} ({1}..{2})= {3}",i,TEIndices[i],str.Length -
1, str.Substring(TEIndices[i]));
// Parses the string using the GetTextElementEnumerator method.
Console.WriteLine
("\r\nParsing '{0}' Using TextElementEnumerator...",str);
TEEnum = StringInfo.GetTextElementEnumerator(str);
bool Continue = false;
int TECount = -1;
// Note: Begins at element -1 (none).
Continue = TEEnum.MoveNext();
while (Continue)
{
// Prints 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,
TEEnum.Current);
// Moves to the next element.
Continue = TEEnum.MoveNext();
}
}
}
说明: |
---|
如果在控制台应用程序中执行此代码,则指定的 Unicode 文本元素将不会正确显示,因为控制台环境并不支持所有的 Unicode 字符。 |