String.IsNormalized Метод

Ссылка

Определение

Пространство имен:: System

Сборка:: System.Runtime.dll

Сборка:: mscorlib.dll

Сборка:: netstandard.dll

Важно!

Некоторые сведения относятся к предварительной версии продукта, в которую до выпуска могут быть внесены существенные изменения. Майкрософт не предоставляет никаких гарантий, явных или подразумеваемых, относительно приведенных здесь сведений.

Указывает, находится ли данная строка в определенной форме нормализации Юникода.

Перегрузки

IsNormalized()	Указывает, находится ли данная строка в форме нормализации Юникода C.
IsNormalized(NormalizationForm)	Указывает, находится ли данная строка в заданной форме нормализации Юникода.

Примеры

В следующем примере определяется, успешно ли нормализуется строка в различных формах нормализации.

using namespace System;
using namespace System::Text;

void Show( String^ title, String^ s )
{
   Console::Write( "Characters in string {0} = ", title );
   for each (short x in s) {
      Console::Write("{0:X4} ", x);
   }
   Console::WriteLine();
}

int main()
{
   
   // Character c; combining characters acute and cedilla; character 3/4
   array<Char>^temp0 = {L'c',L'\u0301',L'\u0327',L'\u00BE'};
   String^ s1 = gcnew String( temp0 );
   String^ s2 = nullptr;
   String^ divider = gcnew String( '-',80 );
   divider = String::Concat( Environment::NewLine, divider, Environment::NewLine );

   Show( "s1", s1 );
   Console::WriteLine();
   Console::WriteLine( "U+0063 = LATIN SMALL LETTER C" );
   Console::WriteLine( "U+0301 = COMBINING ACUTE ACCENT" );
   Console::WriteLine( "U+0327 = COMBINING CEDILLA" );
   Console::WriteLine( "U+00BE = VULGAR FRACTION THREE QUARTERS" );
   Console::WriteLine( divider );
   Console::WriteLine( "A1) Is s1 normalized to the default form (Form C)?: {0}", s1->IsNormalized() );
   Console::WriteLine( "A2) Is s1 normalized to Form C?:  {0}", s1->IsNormalized( NormalizationForm::FormC ) );
   Console::WriteLine( "A3) Is s1 normalized to Form D?:  {0}", s1->IsNormalized( NormalizationForm::FormD ) );
   Console::WriteLine( "A4) Is s1 normalized to Form KC?: {0}", s1->IsNormalized( NormalizationForm::FormKC ) );
   Console::WriteLine( "A5) Is s1 normalized to Form KD?: {0}", s1->IsNormalized( NormalizationForm::FormKD ) );
   Console::WriteLine( divider );
   Console::WriteLine( "Set string s2 to each normalized form of string s1." );
   Console::WriteLine();
   Console::WriteLine( "U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE" );
   Console::WriteLine( "U+0033 = DIGIT THREE" );
   Console::WriteLine( "U+2044 = FRACTION SLASH" );
   Console::WriteLine( "U+0034 = DIGIT FOUR" );
   Console::WriteLine( divider );
   s2 = s1->Normalize();
   Console::Write( "B1) Is s2 normalized to the default form (Form C)?: " );
   Console::WriteLine( s2->IsNormalized() );
   Show( "s2", s2 );
   Console::WriteLine();
   s2 = s1->Normalize( NormalizationForm::FormC );
   Console::Write( "B2) Is s2 normalized to Form C?: " );
   Console::WriteLine( s2->IsNormalized( NormalizationForm::FormC ) );
   Show( "s2", s2 );
   Console::WriteLine();
   s2 = s1->Normalize( NormalizationForm::FormD );
   Console::Write( "B3) Is s2 normalized to Form D?: " );
   Console::WriteLine( s2->IsNormalized( NormalizationForm::FormD ) );
   Show( "s2", s2 );
   Console::WriteLine();
   s2 = s1->Normalize( NormalizationForm::FormKC );
   Console::Write( "B4) Is s2 normalized to Form KC?: " );
   Console::WriteLine( s2->IsNormalized( NormalizationForm::FormKC ) );
   Show( "s2", s2 );
   Console::WriteLine();
   s2 = s1->Normalize( NormalizationForm::FormKD );
   Console::Write( "B5) Is s2 normalized to Form KD?: " );
   Console::WriteLine( s2->IsNormalized( NormalizationForm::FormKD ) );
   Show( "s2", s2 );
   Console::WriteLine();
}

/*
This example produces the following results:

Characters in string s1 = 0063 0301 0327 00BE

U+0063 = LATIN SMALL LETTER C
U+0301 = COMBINING ACUTE ACCENT
U+0327 = COMBINING CEDILLA
U+00BE = VULGAR FRACTION THREE QUARTERS

--------------------------------------------------------------------------------

A1) Is s1 normalized to the default form (Form C)?: False
A2) Is s1 normalized to Form C?:  False
A3) Is s1 normalized to Form D?:  False
A4) Is s1 normalized to Form KC?: False
A5) Is s1 normalized to Form KD?: False

--------------------------------------------------------------------------------

Set string s2 to each normalized form of string s1.

U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
U+0033 = DIGIT THREE
U+2044 = FRACTION SLASH
U+0034 = DIGIT FOUR

--------------------------------------------------------------------------------

B1) Is s2 normalized to the default form (Form C)?: True
Characters in string s2 = 1E09 00BE

B2) Is s2 normalized to Form C?: True
Characters in string s2 = 1E09 00BE

B3) Is s2 normalized to Form D?: True
Characters in string s2 = 0063 0327 0301 00BE

B4) Is s2 normalized to Form KC?: True
Characters in string s2 = 1E09 0033 2044 0034

B5) Is s2 normalized to Form KD?: True
Characters in string s2 = 0063 0327 0301 0033 2044 0034

*/

using System;
using System.Text;

class Example
{
    public static void Main()
    {
       // Character c; combining characters acute and cedilla; character 3/4
       string s1 = new String( new char[] {'\u0063', '\u0301', '\u0327', '\u00BE'});
       string s2 = null;
       string divider = new String('-', 80);
       divider = String.Concat(Environment.NewLine, divider, Environment.NewLine);

       Show("s1", s1);
       Console.WriteLine();
       Console.WriteLine("U+0063 = LATIN SMALL LETTER C");
       Console.WriteLine("U+0301 = COMBINING ACUTE ACCENT");
       Console.WriteLine("U+0327 = COMBINING CEDILLA");
       Console.WriteLine("U+00BE = VULGAR FRACTION THREE QUARTERS");
       Console.WriteLine(divider);

       Console.WriteLine("A1) Is s1 normalized to the default form (Form C)?: {0}",
                                    s1.IsNormalized());
       Console.WriteLine("A2) Is s1 normalized to Form C?:  {0}",
                                    s1.IsNormalized(NormalizationForm.FormC));
       Console.WriteLine("A3) Is s1 normalized to Form D?:  {0}",
                                    s1.IsNormalized(NormalizationForm.FormD));
       Console.WriteLine("A4) Is s1 normalized to Form KC?: {0}",
                                    s1.IsNormalized(NormalizationForm.FormKC));
       Console.WriteLine("A5) Is s1 normalized to Form KD?: {0}",
                                    s1.IsNormalized(NormalizationForm.FormKD));

       Console.WriteLine(divider);

       Console.WriteLine("Set string s2 to each normalized form of string s1.");
       Console.WriteLine();
       Console.WriteLine("U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE");
       Console.WriteLine("U+0033 = DIGIT THREE");
       Console.WriteLine("U+2044 = FRACTION SLASH");
       Console.WriteLine("U+0034 = DIGIT FOUR");
       Console.WriteLine(divider);

       s2 = s1.Normalize();
       Console.Write("B1) Is s2 normalized to the default form (Form C)?: ");
       Console.WriteLine(s2.IsNormalized());
       Show("s2", s2);
       Console.WriteLine();

       s2 = s1.Normalize(NormalizationForm.FormC);
       Console.Write("B2) Is s2 normalized to Form C?: ");
       Console.WriteLine(s2.IsNormalized(NormalizationForm.FormC));
       Show("s2", s2);
       Console.WriteLine();

       s2 = s1.Normalize(NormalizationForm.FormD);
       Console.Write("B3) Is s2 normalized to Form D?: ");
       Console.WriteLine(s2.IsNormalized(NormalizationForm.FormD));
       Show("s2", s2);
       Console.WriteLine();

       s2 = s1.Normalize(NormalizationForm.FormKC);
       Console.Write("B4) Is s2 normalized to Form KC?: ");
       Console.WriteLine(s2.IsNormalized(NormalizationForm.FormKC));
       Show("s2", s2);
       Console.WriteLine();

       s2 = s1.Normalize(NormalizationForm.FormKD);
       Console.Write("B5) Is s2 normalized to Form KD?: ");
       Console.WriteLine(s2.IsNormalized(NormalizationForm.FormKD));
       Show("s2", s2);
       Console.WriteLine();
    }

    private static void Show(string title, string s)
    {
       Console.Write("Characters in string {0} = ", title);
       foreach(short x in s) {
           Console.Write("{0:X4} ", x);
       }
       Console.WriteLine();
    }
}
/*
This example produces the following results:

Characters in string s1 = 0063 0301 0327 00BE

U+0063 = LATIN SMALL LETTER C
U+0301 = COMBINING ACUTE ACCENT
U+0327 = COMBINING CEDILLA
U+00BE = VULGAR FRACTION THREE QUARTERS

--------------------------------------------------------------------------------

A1) Is s1 normalized to the default form (Form C)?: False
A2) Is s1 normalized to Form C?:  False
A3) Is s1 normalized to Form D?:  False
A4) Is s1 normalized to Form KC?: False
A5) Is s1 normalized to Form KD?: False

--------------------------------------------------------------------------------

Set string s2 to each normalized form of string s1.

U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
U+0033 = DIGIT THREE
U+2044 = FRACTION SLASH
U+0034 = DIGIT FOUR

--------------------------------------------------------------------------------

B1) Is s2 normalized to the default form (Form C)?: True
Characters in string s2 = 1E09 00BE

B2) Is s2 normalized to Form C?: True
Characters in string s2 = 1E09 00BE

B3) Is s2 normalized to Form D?: True
Characters in string s2 = 0063 0327 0301 00BE

B4) Is s2 normalized to Form KC?: True
Characters in string s2 = 1E09 0033 2044 0034

B5) Is s2 normalized to Form KD?: True
Characters in string s2 = 0063 0327 0301 0033 2044 0034

*/

open System
open System.Text

let show title (s: string) =
    printf $"Characters in string %s{title} = "
    for x in s do
        printf $"{int16 x:X4} "
    printfn ""


[<EntryPoint>]
let main _ =
    // Character c; combining characters acute and cedilla; character 3/4
    let s1 = String [| '\u0063'; '\u0301'; '\u0327'; '\u00BE' |]
    let divider = String('-', 80)
    let divider = String.Concat(Environment.NewLine, divider, Environment.NewLine)

    show "s1" s1
    printfn "\nU+0063 = LATIN SMALL LETTER C"
    printfn "U+0301 = COMBINING ACUTE ACCENT"
    printfn "U+0327 = COMBINING CEDILLA"
    printfn "U+00BE = VULGAR FRACTION THREE QUARTERS"
    printfn $"{divider}"

    printfn $"A1) Is s1 normalized to the default form (Form C)?: {s1.IsNormalized()}"
    printfn $"A2) Is s1 normalized to Form C?:  {s1.IsNormalized NormalizationForm.FormC}"
    printfn $"A3) Is s1 normalized to Form D?:  {s1.IsNormalized NormalizationForm.FormD}"
    printfn $"A4) Is s1 normalized to Form KC?: {s1.IsNormalized NormalizationForm.FormKC}"
    printfn $"A5) Is s1 normalized to Form KD?: {s1.IsNormalized NormalizationForm.FormKD}"

    printfn $"{divider}"

    printfn "Set string s2 to each normalized form of string s1.\n"
    printfn "U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE"
    printfn"U+0033 = DIGIT THREE"
    printfn"U+2044 = FRACTION SLASH"
    printfn"U+0034 = DIGIT FOUR"
    printfn $"{divider}"
 
    let s2 = s1.Normalize()
    printf "B1) Is s2 normalized to the default form (Form C)?: "
    printfn $"{s2.IsNormalized()}"
    show "s2" s2
    printfn ""

    let s2 = s1.Normalize NormalizationForm.FormC
    printf "B2) Is s2 normalized to Form C?: "
    printfn $"{s2.IsNormalized NormalizationForm.FormC}"
    show "s2" s2
    printfn ""

    let s2 = s1.Normalize NormalizationForm.FormD
    printf "B3) Is s2 normalized to Form D?: "
    printfn $"{s2.IsNormalized NormalizationForm.FormD}"
    show "s2" s2
    printfn ""

    let s2 = s1.Normalize(NormalizationForm.FormKC)
    printf "B4) Is s2 normalized to Form KC?: "
    printfn $"{s2.IsNormalized NormalizationForm.FormKC}"
    show "s2" s2
    printfn ""

    let s2 = s1.Normalize(NormalizationForm.FormKD)
    printf "B5) Is s2 normalized to Form KD?: "
    printfn $"{s2.IsNormalized NormalizationForm.FormKD}"
    show "s2" s2
    0

(*
This example produces the following results:

Characters in string s1 = 0063 0301 0327 00BE

U+0063 = LATIN SMALL LETTER C
U+0301 = COMBINING ACUTE ACCENT
U+0327 = COMBINING CEDILLA
U+00BE = VULGAR FRACTION THREE QUARTERS

--------------------------------------------------------------------------------

A1) Is s1 normalized to the default form (Form C)?: False
A2) Is s1 normalized to Form C?:  False
A3) Is s1 normalized to Form D?:  False
A4) Is s1 normalized to Form KC?: False
A5) Is s1 normalized to Form KD?: False

--------------------------------------------------------------------------------

Set string s2 to each normalized form of string s1.

U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
U+0033 = DIGIT THREE
U+2044 = FRACTION SLASH
U+0034 = DIGIT FOUR

--------------------------------------------------------------------------------

B1) Is s2 normalized to the default form (Form C)?: True
Characters in string s2 = 1E09 00BE

B2) Is s2 normalized to Form C?: True
Characters in string s2 = 1E09 00BE

B3) Is s2 normalized to Form D?: True
Characters in string s2 = 0063 0327 0301 00BE

B4) Is s2 normalized to Form KC?: True
Characters in string s2 = 1E09 0033 2044 0034

B5) Is s2 normalized to Form KD?: True
Characters in string s2 = 0063 0327 0301 0033 2044 0034

*)

Imports System.Text

Class Example
   Public Shared Sub Main()
      ' Character c; combining characters acute and cedilla; character 3/4
      Dim s1 = New [String](New Char() {ChrW(&H0063), ChrW(&H0301), ChrW(&H0327), ChrW(&H00BE)})
      Dim s2 As String = Nothing
      Dim divider = New [String]("-"c, 80)
      divider = [String].Concat(Environment.NewLine, divider, Environment.NewLine)
      
      Show("s1", s1)
      Console.WriteLine()
      Console.WriteLine("U+0063 = LATIN SMALL LETTER C")
      Console.WriteLine("U+0301 = COMBINING ACUTE ACCENT")
      Console.WriteLine("U+0327 = COMBINING CEDILLA")
      Console.WriteLine("U+00BE = VULGAR FRACTION THREE QUARTERS")

      Console.WriteLine(divider)
      
      Console.WriteLine("A1) Is s1 normalized to the default form (Form C)?: {0}", s1.IsNormalized())
      Console.WriteLine("A2) Is s1 normalized to Form C?:  {0}", s1.IsNormalized(NormalizationForm.FormC))
      Console.WriteLine("A3) Is s1 normalized to Form D?:  {0}", s1.IsNormalized(NormalizationForm.FormD))
      Console.WriteLine("A4) Is s1 normalized to Form KC?: {0}", s1.IsNormalized(NormalizationForm.FormKC))
      Console.WriteLine("A5) Is s1 normalized to Form KD?: {0}", s1.IsNormalized(NormalizationForm.FormKD))
      
      Console.WriteLine(divider)
      
      Console.WriteLine("Set string s2 to each normalized form of string s1.")
      Console.WriteLine()
      Console.WriteLine("U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE")
      Console.WriteLine("U+0033 = DIGIT THREE")
      Console.WriteLine("U+2044 = FRACTION SLASH")
      Console.WriteLine("U+0034 = DIGIT FOUR")
      Console.WriteLine(divider)
      
      s2 = s1.Normalize()
      Console.Write("B1) Is s2 normalized to the default form (Form C)?: ")
      Console.WriteLine(s2.IsNormalized())
      Show("s2", s2)
      Console.WriteLine()
      
      s2 = s1.Normalize(NormalizationForm.FormC)
      Console.Write("B2) Is s2 normalized to Form C?: ")
      Console.WriteLine(s2.IsNormalized(NormalizationForm.FormC))
      Show("s2", s2)
      Console.WriteLine()
      
      s2 = s1.Normalize(NormalizationForm.FormD)
      Console.Write("B3) Is s2 normalized to Form D?: ")
      Console.WriteLine(s2.IsNormalized(NormalizationForm.FormD))
      Show("s2", s2)
      Console.WriteLine()
      
      s2 = s1.Normalize(NormalizationForm.FormKC)
      Console.Write("B4) Is s2 normalized to Form KC?: ")
      Console.WriteLine(s2.IsNormalized(NormalizationForm.FormKC))
      Show("s2", s2)
      Console.WriteLine()
      
      s2 = s1.Normalize(NormalizationForm.FormKD)
      Console.Write("B5) Is s2 normalized to Form KD?: ")
      Console.WriteLine(s2.IsNormalized(NormalizationForm.FormKD))
      Show("s2", s2)
      Console.WriteLine()
   End Sub 
   
   Private Shared Sub Show(title As String, s As String)
      Console.Write("Characters in string {0} = ", title)
      For Each x As Char In s
         Console.Write("{0:X4} ", AscW(x))
      Next 
      Console.WriteLine()
   End Sub 
End Class 
'This example produces the following results:
'
'Characters in string s1 = 0063 0301 0327 00BE
'
'U+0063 = LATIN SMALL LETTER C
'U+0301 = COMBINING ACUTE ACCENT
'U+0327 = COMBINING CEDILLA
'U+00BE = VULGAR FRACTION THREE QUARTERS
'
'--------------------------------------------------------------------------------
'
'A1) Is s1 normalized to the default form (Form C)?: False
'A2) Is s1 normalized to Form C?:  False
'A3) Is s1 normalized to Form D?:  False
'A4) Is s1 normalized to Form KC?: False
'A5) Is s1 normalized to Form KD?: False
'
'--------------------------------------------------------------------------------
'
'Set string s2 to each normalized form of string s1.
'
'U+1E09 = LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
'U+0033 = DIGIT THREE
'U+2044 = FRACTION SLASH
'U+0034 = DIGIT FOUR
'
'--------------------------------------------------------------------------------
'
'B1) Is s2 normalized to the default form (Form C)?: True
'Characters in string s2 = 1E09 00BE
'
'B2) Is s2 normalized to Form C?: True
'Characters in string s2 = 1E09 00BE
'
'B3) Is s2 normalized to Form D?: True
'Characters in string s2 = 0063 0327 0301 00BE
'
'B4) Is s2 normalized to Form KC?: True
'Characters in string s2 = 1E09 0033 2044 0034
'
'B5) Is s2 normalized to Form KD?: True
'Characters in string s2 = 0063 0327 0301 0033 2044 0034
'

IsNormalized()

Исходный код:: String.cs

Исходный код:: String.cs

Исходный код:: String.cs

Указывает, находится ли данная строка в форме нормализации Юникода C.

public:
 bool IsNormalized();

public bool IsNormalized ();

member this.IsNormalized : unit -> bool

Public Function IsNormalized () As Boolean

Возвращаемое значение

Boolean

true, если данная строка находится в форме нормализации Юникода C; в противном случае — false.

Исключения

ArgumentException

Текущий экземпляр содержит недопустимые символы Юникода.

Некоторые символы Юникода имеют несколько эквивалентных двоичных представлений, состоящих из наборов комбинирующих и (или) составных символов Юникода. Наличие нескольких представлений для одного символа усложняет поиск, сортировку, сопоставление и другие операции.

Стандарт Юникода определяет процесс, называемый нормализацией, который возвращает одно двоичное представление при наличии любого из эквивалентных двоичных представлений символа. Нормализация может выполняться с помощью нескольких алгоритмов, называемых формами нормализации, которые подчиняются разным правилам. В настоящее время .NET поддерживает формы нормализации C, D, KC и KD.

Описание поддерживаемых форм нормализации Юникода см. в разделе System.Text.NormalizationForm.

Примечания для тех, кто вызывает этот метод

Метод IsNormalized возвращается false , как только обнаруживает первый ненормализованный символ в строке. Таким образом, если строка содержит ненормализованные символы, за которыми следуют недопустимые символы Юникода Normalize , метод вызывает исключение ArgumentException , хотя IsNormalized возвращает false.

См. также раздел

Normalize()

Применяется к

IsNormalized(NormalizationForm)

Исходный код:: String.cs

Исходный код:: String.cs

Исходный код:: String.cs

Указывает, находится ли данная строка в заданной форме нормализации Юникода.

public:
 bool IsNormalized(System::Text::NormalizationForm normalizationForm);

public bool IsNormalized (System.Text.NormalizationForm normalizationForm);

member this.IsNormalized : System.Text.NormalizationForm -> bool

Public Function IsNormalized (normalizationForm As NormalizationForm) As Boolean

Параметры

normalizationForm: NormalizationForm

Форма нормализации Юникода.

Возвращаемое значение

Boolean

true, если строка находится в форме нормализации, указанной в параметре normalizationForm; в противном случае — false.

Исключения

ArgumentException

Текущий экземпляр содержит недопустимые символы Юникода.

Примечания для тех, кто вызывает этот метод

См. также раздел

Normalize()

Применяется к

Поделиться через

String.IsNormalized Метод

Определение

Перегрузки

Примеры

IsNormalized()

Возвращаемое значение

Исключения

Комментарии

Примечания для тех, кто вызывает этот метод

См. также раздел

Применяется к

IsNormalized(NormalizationForm)

Параметры

Возвращаемое значение

Исключения

Комментарии

Примечания для тех, кто вызывает этот метод

См. также раздел

Применяется к

Дополнительные ресурсы