Namespaces
Variants
Views
Actions

Difference between revisions of "cpp/locale/codecvt utf8 utf16"

From cppreference.com
< cpp‎ | locale
m (Update links.)
m (P2871R2)
 
(18 intermediate revisions by 8 users not shown)
Line 1: Line 1:
−
{{cpp/title | codecvt_utf8_utf16 }}
+
{{cpp/title|codecvt_utf8_utf16}}
 
{{cpp/locale/navbar}}
 
{{cpp/locale/navbar}}
 +
{{ddcl|header=codecvt|since=c++11|deprecated=c++17|removed=c++26|1=
 +
template<
 +
    class Elem,
 +
    unsigned long Maxcode = 0x10ffff,
 +
    std::codecvt_mode Mode = (std::codecvt_mode)0 >
 +
class codecvt_utf8_utf16
 +
    : public std::codecvt<Elem, char, std::mbstate_t>;
 +
}}
 +
 +
{{tt|std::codecvt_utf8_utf16}} is a {{lc|std::codecvt}} facet which encapsulates conversion between a UTF-8 encoded byte string and UTF-16 encoded character string. If {{tt|Elem}} is a 32-bit type, one UTF-16 code unit will be stored in each 32-bit character of the output sequence.
 +
 +
This is an N:M conversion facet, and cannot be used with {{lc|std::basic_filebuf}} (which only permits 1:N conversions, such as UTF-32/UTF-8, between the internal and the external encodings). This facet can be used with {{lc|std::wstring_convert}}.
 +
 +
===Template Parameters===
 +
{{par begin}}
 +
{{par|Elem|either {{c/core|char16_t}}, {{c/core|char32_t}}, or {{c/core|wchar_t}}}}
 +
{{par|Maxcode|the largest value of {{tt|Elem}} that this facet will read or write without error}}
 +
{{par|Mode|a constant of type {{lc|std::codecvt_mode}}}}
 +
{{par end}}
 +
 +
===Member functions===
 +
{{dsc begin}}
 +
{{dsc mem ctor|cpp/locale/codecvt_utf8_utf16|inlinemem=true|constructs a new {{tt|codecvt_utf8_utf16}} facet}}
 +
{{dsc mem dtor|cpp/locale/codecvt_utf8_utf16|inlinemem=true|destroys a {{tt|codecvt_utf8_utf16}} facet}}
 +
{{dsc end}}
 +
 +
{{member|{{small|std::codecvt_utf8_utf16::}}codecvt_utf8_utf16|
 
{{dcl begin}}
 
{{dcl begin}}
−
{{dcl header | codecvt }}
+
{{dcl|1=
−
{{dcl | 1=
+
explicit codecvt_utf8_utf16( std::size_t refs = 0 );
−
template< class Elem,
+
−
          unsigned long Maxcode = 0x10ffff,
+
−
          std::codecvt_mode Mode = (std::codecvt_mode)0 >
+
−
class codecvt_utf8_utf16 : public std::codecvt<Elem, char, std::mbstate_t>;
+
 
}}
 
}}
 
{{dcl end}}
 
{{dcl end}}
  
−
{{lc|std::codecvt_utf8_utf16}} is a {{lc|std::codecvt}} facet which encapsulates conversion between a UTF-8 encoded byte string and UTF-16 encoded character string. If {{tt|Elem}} is a 32-bit type, one UTF-16 codepoint will be stored in each 32-bit character of the output sequence. This codecvt facet can be used to read and write UTF-8 files, both text and binary.
+
Constructs a new {{tt|std::codecvt_utf8_utf16}} facet, passes the initial reference counter {{c|refs}} to the base class.
  
−
===Template Parameters===
+
===Parameters===
 
{{par begin}}
 
{{par begin}}
−
{{par | Elem | either {{c|char16_t}}, {{c|char32_t}}, or {{c|wchar_t}} }}
+
{{par|refs|the number of references that link to the facet}}
−
{{par | Maxcode | the largest value of {{tt|Elem}} that this facet will read or write without error }}
+
{{par end}}
−
{{par | Mode | a constant of type {{lc|std::codecvt_mode}} }}
+
}}
−
{{par end}}  
+
 
 +
{{member|{{small|std::codecvt_utf8_utf16::}}~codecvt_utf8_utf16|
 +
{{dcl begin}}
 +
{{dcl|1=
 +
~codecvt_utf8_utf16();
 +
}}
 +
{{dcl end}}
 +
 
 +
Destroys the facet. Unlike the locale-managed facets, this facet's destructor is public.
 +
}}
  
 
{{cpp/locale/codecvt/inherit}}
 
{{cpp/locale/codecvt/inherit}}
Line 25: Line 57:
 
===Example===
 
===Example===
 
{{example
 
{{example
−
| The following example demonstrates reading a UTF-8 file into a UTF-16 string on a system with 32-bit {{c|wchar_t}}
+
|code=
−
| code=
+
#include <cassert>
−
#include <fstream>
+
#include <codecvt>
 +
#include <cstdint>
 
#include <iostream>
 
#include <iostream>
−
#include <string>
 
 
#include <locale>
 
#include <locale>
−
#include <codecvt>
+
#include <string>
  
 
int main()
 
int main()
 
{
 
{
−
     std::ofstream("text.txt") << u8"z\u6c34\U0001d10b";
+
     std::string u8 = "z\u00df\u6c34\U0001f34c";
 +
    std::u16string u16 = u"z\u00df\u6c34\U0001f34c";
  
−
     std::wifstream file1("text.txt");
+
    // UTF-8 to UTF-16/char16_t
−
     file1.imbue(std::locale("en_US.UTF8"));
+
     std::u16string u16_conv = std::wstring_convert<
−
     std::cout << "Normal read from file (using default UTF-8/UTF-32 codecvt)\n";
+
        std::codecvt_utf8_utf16<char16_t>, char16_t>{}.from_bytes(u8);
−
     for(wchar_t c; file1 >> c; )
+
     assert(u16 == u16_conv);
−
         std::cout << std::hex << std::showbase << c << '\n';
+
     std::cout << "UTF-8 to UTF-16 conversion produced " << u16_conv.size()
 +
              << " code units:\n" << std::showbase << std::hex;
 +
     for (char16_t c : u16_conv)
 +
         std::cout << static_cast<std::uint16_t>(c) << ' ';
  
−
     std::wifstream file2("text.txt");
+
    // UTF-16/char16_t to UTF-8
−
    file2.imbue(std::locale(file2.getloc(), new std::codecvt_utf8_utf16<wchar_t>));
+
     std::string u8_conv = std::wstring_convert<
−
     std::cout << "UTF-16 read from the same file (using codecvt_utf8_utf16)\n";
+
        std::codecvt_utf8_utf16<char16_t>, char16_t>{}.to_bytes(u16);
−
     for(wchar_t c; file2 >> c; )
+
    assert(u8 == u8_conv);
−
         std::cout << std::hex << std::showbase << c << '\n';
+
     std::cout << "\nUTF-16 to UTF-8 conversion produced "
 +
              << std::dec << u8_conv.size() << " bytes:\n" << std::hex;
 +
     for (char c : u8_conv)
 +
         std::cout << +static_cast<unsigned char>(c) << ' ';
 +
    std::cout << '\n';
 
}
 
}
−
| output=
+
|output=
−
Normal read from file (using default UTF-8/UTF-32 codecvt)
+
UTF-8 to UTF-16 conversion produced 5 code units:
−
0x7a
+
0x7a 0xdf 0x6c34 0xd83c 0xdf4c
−
0x6c34
+
UTF-16 to UTF-8 conversion produced 10 bytes:
−
0x1d10b
+
0x7a 0xc3 0x9f 0xe6 0xb0 0xb4 0xf0 0x9f 0x8d 0x8c
−
UTF-16 read from the same file (using codecvt_utf8_utf16)
+
−
0x7a
+
−
0x6c34
+
−
0xd834
+
−
0xdd0b
+
 
}}
 
}}
  
Line 64: Line 99:
 
{{cpp/locale/unicode string conversions}}
 
{{cpp/locale/unicode string conversions}}
 
{{dsc begin}}
 
{{dsc begin}}
−
{{dsc inc | cpp/locale/dsc codecvt}}
+
{{dsc inc|cpp/locale/dsc codecvt}}
−
{{dsc inc | cpp/locale/dsc codecvt_mode}}
+
{{dsc inc|cpp/locale/dsc codecvt_mode}}
−
{{dsc inc | cpp/locale/dsc codecvt_utf8}}
+
{{dsc inc|cpp/locale/dsc codecvt_utf8}}
−
{{dsc inc | cpp/locale/dsc codecvt_utf16}}
+
{{dsc inc|cpp/locale/dsc codecvt_utf16}}
 
{{dsc end}}
 
{{dsc end}}
  
−
[[de:cpp/locale/codecvt utf8 utf16]]
+
{{langlinks|de|es|fr|it|ja|pt|ru|zh}}
−
[[es:cpp/locale/codecvt utf8 utf16]]
+
−
[[fr:cpp/locale/codecvt utf8 utf16]]
+
−
[[it:cpp/locale/codecvt utf8 utf16]]
+
−
[[ja:cpp/locale/codecvt utf8 utf16]]
+
−
[[pt:cpp/locale/codecvt utf8 utf16]]
+
−
[[ru:cpp/locale/codecvt utf8 utf16]]
+
−
[[zh:cpp/locale/codecvt utf8 utf16]]
+

Latest revision as of 10:19, 22 November 2023

 
C++
 
Localization library
 
Defined in header <codecvt>
template<

    class Elem,
    unsigned long Maxcode = 0x10ffff,
    std::codecvt_mode Mode = (std::codecvt_mode)0 >
class codecvt_utf8_utf16

    : public std::codecvt<Elem, char, std::mbstate_t>;
 (since C++11)
(deprecated in C++17)
(removed in C++26)

std::codecvt_utf8_utf16 is a std::codecvt facet which encapsulates conversion between a UTF-8 encoded byte string and UTF-16 encoded character string. If Elem is a 32-bit type, one UTF-16 code unit will be stored in each 32-bit character of the output sequence.

This is an N:M conversion facet, and cannot be used with std::basic_filebuf (which only permits 1:N conversions, such as UTF-32/UTF-8, between the internal and the external encodings). This facet can be used with std::wstring_convert.

Contents

[edit] Template Parameters

Elem - either char16_t, char32_t, or wchar_t
Maxcode - the largest value of Elem that this facet will read or write without error
Mode - a constant of type std::codecvt_mode

[edit] Member functions

(constructor)
 constructs a new codecvt_utf8_utf16 facet
(public member function)
(destructor)
 destroys a codecvt_utf8_utf16 facet
(public member function)

std::codecvt_utf8_utf16::codecvt_utf8_utf16

explicit codecvt_utf8_utf16( std::size_t refs = 0 );

Constructs a new std::codecvt_utf8_utf16 facet, passes the initial reference counter refs to the base class.

Parameters

refs - the number of references that link to the facet

std::codecvt_utf8_utf16::~codecvt_utf8_utf16

~codecvt_utf8_utf16();

Destroys the facet. Unlike the locale-managed facets, this facet's destructor is public.

Inherited from std::codecvt

Member types

Member name Definition
intern_type internT
extern_type externT
state_type stateT

Member objects

Member name Type
id (static) std::locale::id

Member functions

 invokes do_out
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]
invokes do_in
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]
invokes do_unshift
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]
invokes do_encoding
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]
invokes do_always_noconv
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]
invokes do_length
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]
invokes do_max_length
(public member function of std::codecvt<InternT,ExternT,StateT>) [edit]

Protected member functions

[virtual]
 converts a string from InternT to ExternT, such as when writing to file
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]
[virtual]
 converts a string from ExternT to InternT, such as when reading from file
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]
[virtual]
 generates the termination character sequence of ExternT characters for incomplete conversion
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]
[virtual]
 returns the number of ExternT characters necessary to produce one InternT character, if constant
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]
[virtual]
 tests if the facet encodes an identity conversion for all valid argument values
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]
[virtual]
 calculates the length of the ExternT string that would be consumed by conversion into given InternT buffer
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]
[virtual]
 returns the maximum number of ExternT characters that could be converted into a single InternT character
(virtual protected member function of std::codecvt<InternT,ExternT,StateT>) [edit]

Inherited from std::codecvt_base

Member type Definition
enum result { ok, partial, error, noconv }; Unscoped enumeration type
Enumeration constant Definition
ok conversion was completed with no error
partial not all source characters were converted
error encountered an invalid character
noconv no conversion required, input and output types are the same

[edit] Example

Run this code
#include <cassert>
#include <codecvt>
#include <cstdint>
#include <iostream>
#include <locale>
#include <string>
 
int main()
{
    std::string u8 = "z\u00df\u6c34\U0001f34c";
    std::u16string u16 = u"z\u00df\u6c34\U0001f34c";
 
    // UTF-8 to UTF-16/char16_t
    std::u16string u16_conv = std::wstring_convert<
        std::codecvt_utf8_utf16<char16_t>, char16_t>{}.from_bytes(u8);
    assert(u16 == u16_conv);
    std::cout << "UTF-8 to UTF-16 conversion produced " << u16_conv.size()
              << " code units:\n" << std::showbase << std::hex;
    for (char16_t c : u16_conv)
        std::cout << static_cast<std::uint16_t>(c) << ' ';
 
    // UTF-16/char16_t to UTF-8
    std::string u8_conv = std::wstring_convert<
        std::codecvt_utf8_utf16<char16_t>, char16_t>{}.to_bytes(u16);
    assert(u8 == u8_conv);
    std::cout << "\nUTF-16 to UTF-8 conversion produced "
              << std::dec << u8_conv.size() << " bytes:\n" << std::hex;
    for (char c : u8_conv)
        std::cout << +static_cast<unsigned char>(c) << ' ';
    std::cout << '\n';
}

Output: 

UTF-8 to UTF-16 conversion produced 5 code units:
0x7a 0xdf 0x6c34 0xd83c 0xdf4c
UTF-16 to UTF-8 conversion produced 10 bytes:
0x7a 0xc3 0x9f 0xe6 0xb0 0xb4 0xf0 0x9f 0x8d 0x8c

[edit] See also

Character
conversions 		locale-defined multibyte
(UTF-8, GB18030) 		UTF-8
 UTF-16
UTF-16 mbrtoc16 / c16rtomb (with C11's DR488)

codecvt<char16_t,char,mbstate_t>
codecvt_utf8_utf16<char16_t>
codecvt_utf8_utf16<char32_t>
codecvt_utf8_utf16<wchar_t>

N/A
UCS-2 c16rtomb (without C11's DR488) codecvt_utf8<char16_t> codecvt_utf16<char16_t>
UTF-32

mbrtoc32 / c32rtomb

codecvt<char32_t,char,mbstate_t>
codecvt_utf8<char32_t>

codecvt_utf16<char32_t>

system wchar_t:

UTF-32 (non-Windows)
UCS-2 (Windows)

mbsrtowcs / wcsrtombs
use_facet<codecvt
<wchar_t,char,mbstate_t>>(locale)

codecvt_utf8<wchar_t> codecvt_utf16<wchar_t>
converts between character encodings, including UTF-8, UTF-16, UTF-32
(class template) [edit]
(C++11)(deprecated in C++17)(removed in C++26)
 tags to alter behavior of the standard codecvt facets
(enum) [edit]
(C++11)(deprecated in C++17)(removed in C++26)
 converts between UTF-8 and UCS-2/UCS-4
(class template) [edit]
(C++11)(deprecated in C++17)(removed in C++26)
 converts between UTF-16 and UCS-2/UCS-4
(class template) [edit]
Retrieved from "https://en.cppreference.com/mwiki/index.php?title=cpp/locale/codecvt_utf8_utf16&oldid=163395"