\declaremodule{standard}{email.charset}
\modulesynopsis{Character Sets}

This module provides a class \class{Charset} for representing
character sets and character set conversions in email messages, as
well as a character set registry and several convenience methods for
manipulating this registry.  Instances of \class{Charset} are used in
several other modules within the \module{email} package.

Import this class from the \module{email.charset} module.

\versionadded{2.2.2}

\begin{classdesc}{Charset}{\optional{input_charset}}
Map character sets to their email properties.

This class provides information about the requirements imposed on
email for a specific character set.  It also provides convenience
routines for converting between character sets, given the availability
of the applicable codecs.  Given a character set, it will do its best
to provide information on how to use that character set in an email
message in an RFC-compliant way.

Certain character sets must be encoded with quoted-printable or base64
when used in email headers or bodies.  Certain character sets must be
converted outright, and are not allowed in email.

Optional \var{input_charset} is as described below; it is always
coerced to lower case.  After being alias normalized it is also used
as a lookup into the registry of character sets to find out the header
encoding, body encoding, and output conversion codec to be used for
the character set.  For example, if
\var{input_charset} is \code{iso-8859-1}, then headers and bodies will
be encoded using quoted-printable and no output conversion codec is
necessary.  If \var{input_charset} is \code{euc-jp}, then headers will
be encoded with base64, bodies will not be encoded, but output text
will be converted from the \code{euc-jp} character set to the
\code{iso-2022-jp} character set.
\end{classdesc}

\class{Charset} instances have the following data attributes:

\begin{datadesc}{input_charset}
The initial character set specified.  Common aliases are converted to
their \emph{official} email names (e.g. \code{latin_1} is converted to
\code{iso-8859-1}).  Defaults to 7-bit \code{us-ascii}.
\end{datadesc}

\begin{datadesc}{header_encoding}
If the character set must be encoded before it can be used in an
email header, this attribute will be set to \code{Charset.QP} (for
quoted-printable), \code{Charset.BASE64} (for base64 encoding), or
\code{Charset.SHORTEST} for the shortest of QP or BASE64 encoding.
Otherwise, it will be \code{None}.
\end{datadesc}

\begin{datadesc}{body_encoding}
Same as \var{header_encoding}, but describes the encoding for the
mail message's body, which indeed may be different than the header
encoding.  \code{Charset.SHORTEST} is not allowed for
\var{body_encoding}.
\end{datadesc}

\begin{datadesc}{output_charset}
Some character sets must be converted before they can be used in
email headers or bodies.  If the \var{input_charset} is one of
them, this attribute will contain the name of the character set
output will be converted to.  Otherwise, it will be \code{None}.
\end{datadesc}

\begin{datadesc}{input_codec}
The name of the Python codec used to convert the \var{input_charset} to
Unicode.  If no conversion codec is necessary, this attribute will be
\code{None}.
\end{datadesc}

\begin{datadesc}{output_codec}
The name of the Python codec used to convert Unicode to the
\var{output_charset}.  If no conversion codec is necessary, this
attribute will have the same value as the \var{input_codec}.
\end{datadesc}

\class{Charset} instances also have the following methods:

\begin{methoddesc}[Charset]{get_body_encoding}{}
Return the content transfer encoding used for body encoding.

This is either the string \samp{quoted-printable} or \samp{base64}
depending on the encoding used, or it is a function, in which case you
should call the function with a single argument, the Message object
being encoded.  The function should then set the
\mailheader{Content-Transfer-Encoding} header itself to whatever is
appropriate.

Returns the string \samp{quoted-printable} if
\var{body_encoding} is \code{QP}, returns the string
\samp{base64} if \var{body_encoding} is \code{BASE64}, and returns the
string \samp{7bit} otherwise.
\end{methoddesc}

\begin{methoddesc}{convert}{s}
Convert the string \var{s} from the \var{input_codec} to the
\var{output_codec}.
\end{methoddesc}

\begin{methoddesc}{to_splittable}{s}
Convert a possibly multibyte string to a safely splittable format.
\var{s} is the string to split.

Uses the \var{input_codec} to try and convert the string to Unicode,
so it can be safely split on character boundaries (even for multibyte
characters).

Returns the string as-is if it isn't known how to convert \var{s} to
Unicode with the \var{input_charset}.

Characters that could not be converted to Unicode will be replaced
with the Unicode replacement character \character{U+FFFD}.
\end{methoddesc}

\begin{methoddesc}{from_splittable}{ustr\optional{, to_output}}
Convert a splittable string back into an encoded string.  \var{ustr}
is a Unicode string to ``unsplit''.

This method uses the proper codec to try and convert the string from
Unicode back into an encoded format.  Return the string as-is if it is
not Unicode, or if it could not be converted from Unicode.

Characters that could not be converted from Unicode will be replaced
with an appropriate character (usually \character{?}).

If \var{to_output} is \code{True} (the default), uses
\var{output_codec} to convert to an 
encoded format.  If \var{to_output} is \code{False}, it uses
\var{input_codec}.
\end{methoddesc}

\begin{methoddesc}{get_output_charset}{}
Return the output character set.

This is the \var{output_charset} attribute if that is not \code{None},
otherwise it is \var{input_charset}.
\end{methoddesc}

\begin{methoddesc}{encoded_header_len}{}
Return the length of the encoded header string, properly calculating
for quoted-printable or base64 encoding.
\end{methoddesc}

\begin{methoddesc}{header_encode}{s\optional{, convert}}
Header-encode the string \var{s}.

If \var{convert} is \code{True}, the string will be converted from the
input charset to the output charset automatically.  This is not useful
for multibyte character sets, which have line length issues (multibyte
characters must be split on a character, not a byte boundary); use the
higher-level \class{Header} class to deal with these issues (see
\refmodule{email.header}).  \var{convert} defaults to \code{False}.

The type of encoding (base64 or quoted-printable) will be based on
the \var{header_encoding} attribute.
\end{methoddesc}

\begin{methoddesc}{body_encode}{s\optional{, convert}}
Body-encode the string \var{s}.

If \var{convert} is \code{True} (the default), the string will be
converted from the input charset to output charset automatically.
Unlike \method{header_encode()}, there are no issues with byte
boundaries and multibyte charsets in email bodies, so this is usually
pretty safe.

The type of encoding (base64 or quoted-printable) will be based on
the \var{body_encoding} attribute.
\end{methoddesc}

The \class{Charset} class also provides a number of methods to support
standard operations and built-in functions.

\begin{methoddesc}[Charset]{__str__}{}
Returns \var{input_charset} as a string coerced to lower case.
\method{__repr__()} is an alias for \method{__str__()}.
\end{methoddesc}

\begin{methoddesc}[Charset]{__eq__}{other}
This method allows you to compare two \class{Charset} instances for equality.
\end{methoddesc}

\begin{methoddesc}[Header]{__ne__}{other}
This method allows you to compare two \class{Charset} instances for inequality.
\end{methoddesc}

The \module{email.charset} module also provides the following
functions for adding new entries to the global character set, alias,
and codec registries:

\begin{funcdesc}{add_charset}{charset\optional{, header_enc\optional{,
    body_enc\optional{, output_charset}}}}
Add character properties to the global registry.

\var{charset} is the input character set, and must be the canonical
name of a character set.

Optional \var{header_enc} and \var{body_enc} is either
\code{Charset.QP} for quoted-printable, \code{Charset.BASE64} for
base64 encoding, \code{Charset.SHORTEST} for the shortest of
quoted-printable or base64 encoding, or \code{None} for no encoding.
\code{SHORTEST} is only valid for \var{header_enc}. The default is
\code{None} for no encoding.

Optional \var{output_charset} is the character set that the output
should be in.  Conversions will proceed from input charset, to
Unicode, to the output charset when the method
\method{Charset.convert()} is called.  The default is to output in the
same character set as the input.

Both \var{input_charset} and \var{output_charset} must have Unicode
codec entries in the module's character set-to-codec mapping; use
\function{add_codec()} to add codecs the module does
not know about.  See the \refmodule{codecs} module's documentation for
more information.

The global character set registry is kept in the module global
dictionary \code{CHARSETS}.
\end{funcdesc}

\begin{funcdesc}{add_alias}{alias, canonical}
Add a character set alias.  \var{alias} is the alias name,
e.g. \code{latin-1}.  \var{canonical} is the character set's canonical
name, e.g. \code{iso-8859-1}.

The global charset alias registry is kept in the module global
dictionary \code{ALIASES}.
\end{funcdesc}

\begin{funcdesc}{add_codec}{charset, codecname}
Add a codec that map characters in the given character set to and from
Unicode.

\var{charset} is the canonical name of a character set.
\var{codecname} is the name of a Python codec, as appropriate for the
second argument to the \function{unicode()} built-in, or to the
\method{encode()} method of a Unicode string.
\end{funcdesc}