mirror of https://github.com/python/cpython
158 lines
6.7 KiB
TeX
158 lines
6.7 KiB
TeX
\declaremodule{standard}{email.Utils}
|
|
\modulesynopsis{Miscellaneous email package utilities.}
|
|
|
|
There are several useful utilities provided in the \module{email.Utils}
|
|
module:
|
|
|
|
\begin{funcdesc}{quote}{str}
|
|
Return a new string with backslashes in \var{str} replaced by two
|
|
backslashes, and double quotes replaced by backslash-double quote.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{unquote}{str}
|
|
Return a new string which is an \emph{unquoted} version of \var{str}.
|
|
If \var{str} ends and begins with double quotes, they are stripped
|
|
off. Likewise if \var{str} ends and begins with angle brackets, they
|
|
are stripped off.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{parseaddr}{address}
|
|
Parse address -- which should be the value of some address-containing
|
|
field such as \mailheader{To} or \mailheader{Cc} -- into its constituent
|
|
\emph{realname} and \emph{email address} parts. Returns a tuple of that
|
|
information, unless the parse fails, in which case a 2-tuple of
|
|
\code{('', '')} is returned.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{formataddr}{pair}
|
|
The inverse of \method{parseaddr()}, this takes a 2-tuple of the form
|
|
\code{(realname, email_address)} and returns the string value suitable
|
|
for a \mailheader{To} or \mailheader{Cc} header. If the first element of
|
|
\var{pair} is false, then the second element is returned unmodified.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{getaddresses}{fieldvalues}
|
|
This method returns a list of 2-tuples of the form returned by
|
|
\code{parseaddr()}. \var{fieldvalues} is a sequence of header field
|
|
values as might be returned by \method{Message.get_all()}. Here's a
|
|
simple example that gets all the recipients of a message:
|
|
|
|
\begin{verbatim}
|
|
from email.Utils import getaddresses
|
|
|
|
tos = msg.get_all('to', [])
|
|
ccs = msg.get_all('cc', [])
|
|
resent_tos = msg.get_all('resent-to', [])
|
|
resent_ccs = msg.get_all('resent-cc', [])
|
|
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{parsedate}{date}
|
|
Attempts to parse a date according to the rules in \rfc{2822}.
|
|
however, some mailers don't follow that format as specified, so
|
|
\function{parsedate()} tries to guess correctly in such cases.
|
|
\var{date} is a string containing an \rfc{2822} date, such as
|
|
\code{"Mon, 20 Nov 1995 19:12:08 -0500"}. If it succeeds in parsing
|
|
the date, \function{parsedate()} returns a 9-tuple that can be passed
|
|
directly to \function{time.mktime()}; otherwise \code{None} will be
|
|
returned. Note that fields 6, 7, and 8 of the result tuple are not
|
|
usable.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{parsedate_tz}{date}
|
|
Performs the same function as \function{parsedate()}, but returns
|
|
either \code{None} or a 10-tuple; the first 9 elements make up a tuple
|
|
that can be passed directly to \function{time.mktime()}, and the tenth
|
|
is the offset of the date's timezone from UTC (which is the official
|
|
term for Greenwich Mean Time)\footnote{Note that the sign of the timezone
|
|
offset is the opposite of the sign of the \code{time.timezone}
|
|
variable for the same timezone; the latter variable follows the
|
|
\POSIX{} standard while this module follows \rfc{2822}.}. If the input
|
|
string has no timezone, the last element of the tuple returned is
|
|
\code{None}. Note that fields 6, 7, and 8 of the result tuple are not
|
|
usable.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{mktime_tz}{tuple}
|
|
Turn a 10-tuple as returned by \function{parsedate_tz()} into a UTC
|
|
timestamp. It the timezone item in the tuple is \code{None}, assume
|
|
local time. Minor deficiency: \function{mktime_tz()} interprets the
|
|
first 8 elements of \var{tuple} as a local time and then compensates
|
|
for the timezone difference. This may yield a slight error around
|
|
changes in daylight savings time, though not worth worrying about for
|
|
common use.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{formatdate}{\optional{timeval\optional{, localtime}\optional{, usegmt}}}
|
|
Returns a date string as per \rfc{2822}, e.g.:
|
|
|
|
\begin{verbatim}
|
|
Fri, 09 Nov 2001 01:08:47 -0000
|
|
\end{verbatim}
|
|
|
|
Optional \var{timeval} if given is a floating point time value as
|
|
accepted by \function{time.gmtime()} and \function{time.localtime()},
|
|
otherwise the current time is used.
|
|
|
|
Optional \var{localtime} is a flag that when \code{True}, interprets
|
|
\var{timeval}, and returns a date relative to the local timezone
|
|
instead of UTC, properly taking daylight savings time into account.
|
|
The default is \code{False} meaning UTC is used.
|
|
|
|
Optional \var{usegmt} is a flag that when \code{True}, outputs a
|
|
date string with the timezone as an ascii string \code{GMT}, rather
|
|
than a numeric \code{-0000}. This is needed for some protocols (such
|
|
as HTTP). This only applies when \var{localtime} is \code{False}.
|
|
\versionadded{2.4}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{make_msgid}{\optional{idstring}}
|
|
Returns a string suitable for an \rfc{2822}-compliant
|
|
\mailheader{Message-ID} header. Optional \var{idstring} if given, is
|
|
a string used to strengthen the uniqueness of the message id.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{decode_rfc2231}{s}
|
|
Decode the string \var{s} according to \rfc{2231}.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{encode_rfc2231}{s\optional{, charset\optional{, language}}}
|
|
Encode the string \var{s} according to \rfc{2231}. Optional
|
|
\var{charset} and \var{language}, if given is the character set name
|
|
and language name to use. If neither is given, \var{s} is returned
|
|
as-is. If \var{charset} is given but \var{language} is not, the
|
|
string is encoded using the empty string for \var{language}.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{collapse_rfc2231_value}{value\optional{, errors\optional{,
|
|
fallback_charset}}}
|
|
When a header parameter is encoded in \rfc{2231} format,
|
|
\method{Message.get_param()} may return a 3-tuple containing the character
|
|
set, language, and value. \function{collapse_rfc2231_value()} turns this into
|
|
a unicode string. Optional \var{errors} is passed to the \var{errors}
|
|
argument of the built-in \function{unicode()} function; it defaults to
|
|
\code{replace}. Optional \var{fallback_charset} specifies the character set
|
|
to use if the one in the \rfc{2231} header is not known by Python; it defaults
|
|
to \code{us-ascii}.
|
|
|
|
For convenience, if the \var{value} passed to
|
|
\function{collapse_rfc2231_value()} is not a tuple, it should be a string and
|
|
it is returned unquoted.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{decode_params}{params}
|
|
Decode parameters list according to \rfc{2231}. \var{params} is a
|
|
sequence of 2-tuples containing elements of the form
|
|
\code{(content-type, string-value)}.
|
|
\end{funcdesc}
|
|
|
|
\versionchanged[The \function{dump_address_pair()} function has been removed;
|
|
use \function{formataddr()} instead]{2.4}
|
|
|
|
\versionchanged[The \function{decode()} function has been removed; use the
|
|
\method{Header.decode_header()} method instead]{2.4}
|
|
|
|
\versionchanged[The \function{encode()} function has been removed; use the
|
|
\method{Header.encode()} method instead]{2.4}
|