=encoding utf-8

=head1 NAME

ngx_http_charset_module - Module ngx_http_charset_module




=head1



The C<ngx_http_charset_module> module adds the specified
charset to the C<Content-Type> response header field.
In addition, the module can convert data from one charset to another,
with some limitations:

=over




=item *

conversion is performed one way — from server to client,



=item *

only single-byte charsets can be converted



=item *

or single-byte charsets toE<sol>from UTF-8.



=back






=head1 Example Configuration




    
    include        conf/koi-win;
    
    charset        windows-1251;
    source_charset koi8-r;






=head1 Directives

=head2 charset


B<syntax:> charset I<I<C<charset>> E<verbar> C<off>>


B<default:> I<off>


B<context:> I<http>


B<context:> I<server>


B<context:> I<location>


B<context:> I<if in location>





Adds the specified charset to the C<Content-Type>
response header field.
If this charset is different from the charset specified
in the L</source_charset> directive, a conversion is performed.





The parameter C<off> cancels the addition of charset
to the C<Content-Type> response header field.





A charset can be defined with a variable:

    
    charset $charset;


In such a case, all possible values of a variable need to be present
in the configuration at least once in the form of the
L</charset_map>, L</charset>, or
L</source_charset> directives.
For C<utf-8>, C<windows-1251>, and
C<koi8-r> charsets, it is sufficient to include the files
F<confE<sol>koi-win>, F<confE<sol>koi-utf>, and
F<confE<sol>win-utf> into configuration.
For other charsets, simply making a fictitious conversion table works,
for example:

    
    charset_map iso-8859-5 _ { }







In addition, a charset can be set in the
C<X-Accel-Charset> response header field.
This capability can be disabled using the
L<ngx_http_proxy_module>,
L<ngx_http_fastcgi_module>,
L<ngx_http_uwsgi_module>,
and
L<ngx_http_scgi_module>
directives.







=head2 charset_map


B<syntax:> charset_map I<I<C<charset1>> I<C<charset2>> { B<...> } >



B<context:> I<http>





Describes the conversion table from one charset to another.
A reverse conversion table is built using the same data.
Character codes are given in hexadecimal.
Missing characters in the range 80-FF are replaced with “C<?>”.
When converting from UTF-8, characters missing in a one-byte charset
are replaced with “C<E<amp>#XXXX;>”.





Example:

    
    charset_map koi8-r windows-1251 {
        C0 FE ; # small yu
        C1 E0 ; # small a
        C2 E1 ; # small b
        C3 F6 ; # small ts
        ...
    }







When describing a conversion table to UTF-8, codes for the UTF-8 charset should
be given in the second column, for example:

    
    charset_map koi8-r utf-8 {
        C0 D18E ; # small yu
        C1 D0B0 ; # small a
        C2 D0B1 ; # small b
        C3 D186 ; # small ts
        ...
    }







Full conversion tables from C<koi8-r> to
C<windows-1251>, and from C<koi8-r> and
C<windows-1251> to C<utf-8>
are provided in the distribution files F<confE<sol>koi-win>,
F<confE<sol>koi-utf>, and F<confE<sol>win-utf>.







=head2 charset_types


B<syntax:> charset_types I<I<C<mime-type>> ...>


B<default:> I<textE<sol>html textE<sol>xml textE<sol>plain textE<sol>vnd.wap.wml
applicationE<sol>javascript applicationE<sol>rss+xml>


B<context:> I<http>


B<context:> I<server>


B<context:> I<location>



This directive appeared in version 0.7.9.





Enables module processing in responses with the specified MIME types
in addition to “C<textE<sol>html>”.
The special value “C<*>” matches any MIME type (0.8.29).






B<NOTE>

Until version 1.5.4, “C<applicationE<sol>x-javascript>” was used
as the default MIME type instead of “C<applicationE<sol>javascript>”.








=head2 override_charset


B<syntax:> override_charset I<C<on> E<verbar> C<off>>


B<default:> I<off>


B<context:> I<http>


B<context:> I<server>


B<context:> I<location>


B<context:> I<if in location>





Determines whether a conversion should be performed for answers
received from a proxied or a FastCGIE<sol>uwsgiE<sol>SCGI server
when the answers already carry a charset in the C<Content-Type>
response header field.
If conversion is enabled, a charset specified in the received
response is used as a source charset.

B<NOTE>

It should be noted that if a response is received in a subrequest
then the conversion from the response charset to the main request charset
is always performed, regardless of the C<override_charset>
directive setting.








=head2 source_charset


B<syntax:> source_charset I<I<C<charset>>>



B<context:> I<http>


B<context:> I<server>


B<context:> I<location>


B<context:> I<if in location>





Defines the source charset of a response.
If this charset is different from the charset specified
in the L</charset> directive, a conversion is performed.