From 40ef0067ad5af2458c54cc0316831ddb701ea3fd Mon Sep 17 00:00:00 2001 From: Barry Warsaw Date: Sat, 18 Mar 2006 15:41:53 +0000 Subject: [PATCH] Merge email package 4.0 from the sandbox, including documentation, test cases, and NEWS updates. --- Doc/lib/email-dir.py | 127 +- Doc/lib/email-mime.py | 6 +- Doc/lib/email-simple.py | 2 +- Doc/lib/email-unpack.py | 63 +- Doc/lib/email.tex | 72 +- Doc/lib/emailcharsets.tex | 8 +- Doc/lib/emailencoders.tex | 4 +- Doc/lib/emailexc.tex | 6 +- Doc/lib/emailgenerator.tex | 25 +- Doc/lib/emailheaders.tex | 17 +- Doc/lib/emailiter.tex | 4 +- Doc/lib/emailmessage.tex | 73 +- Doc/lib/emailmimebase.tex | 65 +- Doc/lib/emailparser.tex | 26 +- Doc/lib/emailutil.tex | 6 +- Doc/lib/mimelib.tex | 17 +- Lib/email/__init__.py | 77 +- Lib/email/_parseaddr.py | 7 + Lib/email/{base64MIME.py => base64mime.py} | 16 +- Lib/email/{Charset.py => charset.py} | 52 +- Lib/email/{Encoders.py => encoders.py} | 12 +- Lib/email/{Errors.py => errors.py} | 6 +- Lib/email/{FeedParser.py => feedparser.py} | 21 +- Lib/email/{Generator.py => generator.py} | 12 +- Lib/email/{Header.py => header.py} | 23 +- Lib/email/{Iterators.py => iterators.py} | 10 +- Lib/email/{Message.py => message.py} | 79 +- Lib/email/mime/__init__.py | 0 Lib/email/mime/application.py | 36 + Lib/email/{MIMEAudio.py => mime/audio.py} | 15 +- Lib/email/{MIMEBase.py => mime/base.py} | 10 +- Lib/email/{MIMEImage.py => mime/image.py} | 11 +- Lib/email/{MIMEMessage.py => mime/message.py} | 12 +- .../{MIMEMultipart.py => mime/multipart.py} | 10 +- .../nonmultipart.py} | 12 +- Lib/email/{MIMEText.py => mime/text.py} | 8 +- Lib/email/{Parser.py => parser.py} | 9 +- Lib/email/{quopriMIME.py => quoprimime.py} | 22 +- Lib/email/test/test_email.py | 125 +- Lib/email/test/test_email_codecs.py | 7 + Lib/email/test/test_email_codecs_renamed.py | 77 + Lib/email/test/test_email_renamed.py | 3078 +++++++++++++++++ Lib/email/{Utils.py => utils.py} | 19 +- Lib/test/test_pyclbr.py | 2 +- 44 files changed, 3821 insertions(+), 468 deletions(-) rename Lib/email/{base64MIME.py => base64mime.py} (95%) rename Lib/email/{Charset.py => charset.py} (90%) rename Lib/email/{Encoders.py => encoders.py} (93%) rename Lib/email/{Errors.py => errors.py} (92%) rename Lib/email/{FeedParser.py => feedparser.py} (97%) rename Lib/email/{Generator.py => generator.py} (97%) rename Lib/email/{Header.py => header.py} (98%) rename Lib/email/{Iterators.py => iterators.py} (90%) rename Lib/email/{Message.py => message.py} (92%) create mode 100644 Lib/email/mime/__init__.py create mode 100644 Lib/email/mime/application.py rename Lib/email/{MIMEAudio.py => mime/audio.py} (91%) rename Lib/email/{MIMEBase.py => mime/base.py} (77%) rename Lib/email/{MIMEImage.py => mime/image.py} (87%) rename Lib/email/{MIMEMessage.py => mime/message.py} (80%) rename Lib/email/{MIMEMultipart.py => mime/multipart.py} (84%) rename Lib/email/{MIMENonMultipart.py => mime/nonmultipart.py} (69%) rename Lib/email/{MIMEText.py => mime/text.py} (82%) rename Lib/email/{Parser.py => parser.py} (94%) rename Lib/email/{quopriMIME.py => quoprimime.py} (96%) create mode 100644 Lib/email/test/test_email_codecs_renamed.py create mode 100644 Lib/email/test/test_email_renamed.py rename Lib/email/{Utils.py => utils.py} (96%) diff --git a/Doc/lib/email-dir.py b/Doc/lib/email-dir.py index 2d89a2fb7e5..c04f57d6414 100644 --- a/Doc/lib/email-dir.py +++ b/Doc/lib/email-dir.py @@ -1,83 +1,69 @@ #!/usr/bin/env python -"""Send the contents of a directory as a MIME message. +"""Send the contents of a directory as a MIME message.""" -Usage: dirmail [options] from to [to ...]* - -Options: - -h / --help - Print this message and exit. - - -d directory - --directory=directory - Mail the contents of the specified directory, otherwise use the - current directory. Only the regular files in the directory are sent, - and we don't recurse to subdirectories. - -`from' is the email address of the sender of the message. - -`to' is the email address of the recipient of the message, and multiple -recipients may be given. - -The email is sent by forwarding to your local SMTP server, which then does the -normal delivery process. Your local machine must be running an SMTP server. -""" - -import sys import os -import getopt +import sys import smtplib # For guessing MIME type based on file name extension import mimetypes -from email import Encoders -from email.Message import Message -from email.MIMEAudio import MIMEAudio -from email.MIMEBase import MIMEBase -from email.MIMEMultipart import MIMEMultipart -from email.MIMEImage import MIMEImage -from email.MIMEText import MIMEText +from optparse import OptionParser + +from email import encoders +from email.message import Message +from email.mime.audio import MIMEAudio +from email.mime.base import MIMEBase +from email.mime.image import MIMEImage +from email.mime.multipart import MIMEMultipart +from email.mime.text import MIMEText COMMASPACE = ', ' -def usage(code, msg=''): - print >> sys.stderr, __doc__ - if msg: - print >> sys.stderr, msg - sys.exit(code) - - def main(): - try: - opts, args = getopt.getopt(sys.argv[1:], 'hd:', ['help', 'directory=']) - except getopt.error, msg: - usage(1, msg) + parser = OptionParser(usage="""\ +Send the contents of a directory as a MIME message. - dir = os.curdir - for opt, arg in opts: - if opt in ('-h', '--help'): - usage(0) - elif opt in ('-d', '--directory'): - dir = arg - - if len(args) < 2: - usage(1) - - sender = args[0] - recips = args[1:] +Usage: %prog [options] +Unless the -o option is given, the email is sent by forwarding to your local +SMTP server, which then does the normal delivery process. Your local machine +must be running an SMTP server. +""") + parser.add_option('-d', '--directory', + type='string', action='store', + help="""Mail the contents of the specified directory, + otherwise use the current directory. Only the regular + files in the directory are sent, and we don't recurse to + subdirectories.""") + parser.add_option('-o', '--output', + type='string', action='store', metavar='FILE', + help="""Print the composed message to FILE instead of + sending the message to the SMTP server.""") + parser.add_option('-s', '--sender', + type='string', action='store', metavar='SENDER', + help='The value of the From: header (required)') + parser.add_option('-r', '--recipient', + type='string', action='append', metavar='RECIPIENT', + default=[], dest='recipients', + help='A To: header value (at least one required)') + opts, args = parser.parse_args() + if not opts.sender or not opts.recipients: + parser.print_help() + sys.exit(1) + directory = opts.directory + if not directory: + directory = '.' # Create the enclosing (outer) message outer = MIMEMultipart() - outer['Subject'] = 'Contents of directory %s' % os.path.abspath(dir) - outer['To'] = COMMASPACE.join(recips) - outer['From'] = sender + outer['Subject'] = 'Contents of directory %s' % os.path.abspath(directory) + outer['To'] = COMMASPACE.join(opts.recipients) + outer['From'] = opts.sender outer.preamble = 'You will not see this in a MIME-aware mail reader.\n' - # To guarantee the message ends with a newline - outer.epilogue = '' - for filename in os.listdir(dir): - path = os.path.join(dir, filename) + for filename in os.listdir(directory): + path = os.path.join(directory, filename) if not os.path.isfile(path): continue # Guess the content type based on the file's extension. Encoding @@ -108,16 +94,21 @@ def main(): msg.set_payload(fp.read()) fp.close() # Encode the payload using Base64 - Encoders.encode_base64(msg) + encoders.encode_base64(msg) # Set the filename parameter msg.add_header('Content-Disposition', 'attachment', filename=filename) outer.attach(msg) - - # Now send the message - s = smtplib.SMTP() - s.connect() - s.sendmail(sender, recips, outer.as_string()) - s.close() + # Now send or store the message + composed = outer.as_string() + if opts.output: + fp = open(opts.output, 'w') + fp.write(composed) + fp.close() + else: + s = smtplib.SMTP() + s.connect() + s.sendmail(opts.sender, opts.recipients, composed) + s.close() if __name__ == '__main__': diff --git a/Doc/lib/email-mime.py b/Doc/lib/email-mime.py index 048a59fddc4..5097253749a 100644 --- a/Doc/lib/email-mime.py +++ b/Doc/lib/email-mime.py @@ -2,8 +2,8 @@ import smtplib # Here are the email package modules we'll need -from email.MIMEImage import MIMEImage -from email.MIMEMultipart import MIMEMultipart +from email.mime.image import MIMEImage +from email.mime.multipart import MIMEMultipart COMMASPACE = ', ' @@ -15,8 +15,6 @@ msg['Subject'] = 'Our family reunion' msg['From'] = me msg['To'] = COMMASPACE.join(family) msg.preamble = 'Our family reunion' -# Guarantees the message ends in a newline -msg.epilogue = '' # Assume we know that the image files are all in PNG format for file in pngfiles: diff --git a/Doc/lib/email-simple.py b/Doc/lib/email-simple.py index a445f1bd1dd..44152a4839c 100644 --- a/Doc/lib/email-simple.py +++ b/Doc/lib/email-simple.py @@ -2,7 +2,7 @@ import smtplib # Import the email modules we'll need -from email.MIMEText import MIMEText +from email.mime.text import MIMEText # Open a plain text file for reading. For this example, assume that # the text file contains only ASCII characters. diff --git a/Doc/lib/email-unpack.py b/Doc/lib/email-unpack.py index b166fdba7dd..fc05d99109d 100644 --- a/Doc/lib/email-unpack.py +++ b/Doc/lib/email-unpack.py @@ -1,59 +1,44 @@ #!/usr/bin/env python -"""Unpack a MIME message into a directory of files. +"""Unpack a MIME message into a directory of files.""" -Usage: unpackmail [options] msgfile - -Options: - -h / --help - Print this message and exit. - - -d directory - --directory=directory - Unpack the MIME message into the named directory, which will be - created if it doesn't already exist. - -msgfile is the path to the file containing the MIME message. -""" - -import sys import os -import getopt +import sys +import email import errno import mimetypes -import email - -def usage(code, msg=''): - print >> sys.stderr, __doc__ - if msg: - print >> sys.stderr, msg - sys.exit(code) +from optparse import OptionParser def main(): - try: - opts, args = getopt.getopt(sys.argv[1:], 'hd:', ['help', 'directory=']) - except getopt.error, msg: - usage(1, msg) + parser = OptionParser(usage="""\ +Unpack a MIME message into a directory of files. - dir = os.curdir - for opt, arg in opts: - if opt in ('-h', '--help'): - usage(0) - elif opt in ('-d', '--directory'): - dir = arg +Usage: %prog [options] msgfile +""") + parser.add_option('-d', '--directory', + type='string', action='store', + help="""Unpack the MIME message into the named + directory, which will be created if it doesn't already + exist.""") + opts, args = parser.parse_args() + if not opts.directory: + parser.print_help() + sys.exit(1) try: msgfile = args[0] except IndexError: - usage(1) + parser.print_help() + sys.exit(1) try: - os.mkdir(dir) + os.mkdir(opts.directory) except OSError, e: # Ignore directory exists error - if e.errno <> errno.EEXIST: raise + if e.errno <> errno.EEXIST: + raise fp = open(msgfile) msg = email.message_from_file(fp) @@ -74,8 +59,8 @@ def main(): ext = '.bin' filename = 'part-%03d%s' % (counter, ext) counter += 1 - fp = open(os.path.join(dir, filename), 'wb') - fp.write(part.get_payload(decode=1)) + fp = open(os.path.join(opts.directory, filename), 'wb') + fp.write(part.get_payload(decode=True)) fp.close() diff --git a/Doc/lib/email.tex b/Doc/lib/email.tex index 3a90e22dd2d..68533254620 100644 --- a/Doc/lib/email.tex +++ b/Doc/lib/email.tex @@ -1,4 +1,4 @@ -% Copyright (C) 2001-2004 Python Software Foundation +% Copyright (C) 2001-2006 Python Software Foundation % Author: barry@python.org (Barry Warsaw) \section{\module{email} --- @@ -18,10 +18,10 @@ subsumes most of the functionality in several older standard modules such as \refmodule{rfc822}, \refmodule{mimetools}, \refmodule{multifile}, and other non-standard packages such as \module{mimecntl}. It is specifically \emph{not} designed to do any -sending of email messages to SMTP (\rfc{2821}) servers; that is the -function of the \refmodule{smtplib} module. The \module{email} -package attempts to be as RFC-compliant as possible, supporting in -addition to \rfc{2822}, such MIME-related RFCs as +sending of email messages to SMTP (\rfc{2821}), NNTP, or other servers; those +are functions of modules such as \refmodule{smtplib} and \refmodule{nntplib}. +The \module{email} package attempts to be as RFC-compliant as possible, +supporting in addition to \rfc{2822}, such MIME-related RFCs as \rfc{2045}, \rfc{2046}, \rfc{2047}, and \rfc{2231}. The primary distinguishing feature of the \module{email} package is @@ -41,7 +41,7 @@ The following sections describe the functionality of the should be common in applications: an email message is read as flat text from a file or other source, the text is parsed to produce the object structure of the email message, this structure is manipulated, -and finally rendered back into flat text. +and finally, the object tree is rendered back into flat text. It is perfectly feasible to create the object structure out of whole cloth --- i.e. completely from scratch. From there, a similar @@ -56,6 +56,7 @@ package, a section on differences and porting is provided. \begin{seealso} \seemodule{smtplib}{SMTP protocol client} + \seemodule{nntplib}{NNTP protocol client} \end{seealso} \subsection{Representing an email message} @@ -88,22 +89,51 @@ package, a section on differences and porting is provided. \subsection{Iterators} \input{emailiter} -\subsection{Package History} +\subsection{Package History\label{email-pkg-history}} -Version 1 of the \module{email} package was bundled with Python -releases up to Python 2.2.1. Version 2 was developed for the Python -2.3 release, and backported to Python 2.2.2. It was also available as -a separate distutils-based package, and is compatible back to Python 2.1. +This table describes the release history of the email package, corresponding +to the version of Python that the package was released with. For purposes of +this document, when you see a note about change or added versions, these refer +to the Python version the change was made it, \emph{not} the email package +version. This table also describes the Python compatibility of each version +of the package. -\module{email} version 3.0 was released with Python 2.4 and as a separate -distutils-based package. It is compatible back to Python 2.3. +\begin{tableiii}{l|l|l}{constant}{email version}{distributed with}{compatible with} +\lineiii{1.x}{Python 2.2.0 to Python 2.2.1}{\emph{no longer supported}} +\lineiii{2.5}{Python 2.2.2+ and Python 2.3}{Python 2.1 to 2.5} +\lineiii{3.0}{Python 2.4}{Python 2.3 to 2.5} +\lineiii{4.0}{Python 2.5}{Python 2.3 to 2.5} +\end{tableiii} -Here are the differences between \module{email} version 3 and version 2: +Here are the major differences between \module{email} verson 4 and version 3: + +\begin{itemize} +\item All modules have been renamed according to \pep{8} standards. For + example, the version 3 module \module{email.Message} was renamed to + \module{email.message} in version 4. + +\item A new subpackage \module{email.mime} was added and all the version 3 + \module{email.MIME*} modules were renamed and situated into the + \module{email.mime} subpackage. For example, the version 3 module + \module{email.MIMEText} was renamed to \module{email.mime.text}. + + \emph{Note that the version 3 names will continue to work until Python + 2.6}. + +\item The \module{email.mime.application} module was added, which contains the + \class{MIMEApplication} class. + +\item Methods that were deprecated in version 3 have been removed. These + include \method{Generator.__call__()}, \method{Message.get_type()}, + \method{Message.get_main_type()}, \method{Message.get_subtype()}. +\end{itemize} + +Here are the major differences between \module{email} version 3 and version 2: \begin{itemize} \item The \class{FeedParser} class was introduced, and the \class{Parser} class was implemented in terms of the \class{FeedParser}. All parsing - there for is non-strict, and parsing will make a best effort never to + therefore is non-strict, and parsing will make a best effort never to raise an exception. Problems found while parsing messages are stored in the message's \var{defect} attribute. @@ -117,7 +147,7 @@ Here are the differences between \module{email} version 3 and version 2: \method{Generator.__call__()}, \method{Message.get_type()}, \method{Message.get_main_type()}, \method{Message.get_subtype()}, and the \var{strict} argument to the \class{Parser} class. These are - expected to be removed in email 3.1. + expected to be removed in future versions. \item Support for Pythons earlier than 2.3 has been removed. \end{itemize} @@ -278,12 +308,12 @@ The \class{Message} class has the following differences: \item The method \method{getpayloadastext()} was removed. Similar functionality is supported by the \class{DecodedGenerator} class in the - \refmodule{email.Generator} module. + \refmodule{email.generator} module. \item The method \method{getbodyastext()} was removed. You can get similar functionality by creating an iterator with \function{typed_subpart_iterator()} in the - \refmodule{email.Iterators} module. + \refmodule{email.iterators} module. \end{itemize} The \class{Parser} class has no differences in its public interface. @@ -295,7 +325,7 @@ notification\footnote{Delivery Status Notifications (DSN) are defined in \rfc{1894}.}. The \class{Generator} class has no differences in its public -interface. There is a new class in the \refmodule{email.Generator} +interface. There is a new class in the \refmodule{email.generator} module though, called \class{DecodedGenerator} which provides most of the functionality previously available in the \method{Message.getpayloadastext()} method. @@ -329,11 +359,11 @@ The following modules and classes have been changed: \module{mimelib} provided some utility functions in its \module{address} and \module{date} modules. All of these functions -have been moved to the \refmodule{email.Utils} module. +have been moved to the \refmodule{email.utils} module. The \code{MsgReader} class/module has been removed. Its functionality is most closely supported in the \function{body_line_iterator()} -function in the \refmodule{email.Iterators} module. +function in the \refmodule{email.iterators} module. \subsection{Examples} diff --git a/Doc/lib/emailcharsets.tex b/Doc/lib/emailcharsets.tex index 18f2a016c00..e0be68ab7ee 100644 --- a/Doc/lib/emailcharsets.tex +++ b/Doc/lib/emailcharsets.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Charset} +\declaremodule{standard}{email.charset} \modulesynopsis{Character Sets} This module provides a class \class{Charset} for representing @@ -7,6 +7,8 @@ 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}} @@ -153,7 +155,7 @@ 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}. +\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. @@ -188,7 +190,7 @@ This method allows you to compare two \class{Charset} instances for equality. This method allows you to compare two \class{Charset} instances for inequality. \end{methoddesc} -The \module{email.Charset} module also provides the following +The \module{email.charset} module also provides the following functions for adding new entries to the global character set, alias, and codec registries: diff --git a/Doc/lib/emailencoders.tex b/Doc/lib/emailencoders.tex index a49e04d9b05..3d05c2ac334 100644 --- a/Doc/lib/emailencoders.tex +++ b/Doc/lib/emailencoders.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Encoders} +\declaremodule{standard}{email.encoders} \modulesynopsis{Encoders for email message payloads.} When creating \class{Message} objects from scratch, you often need to @@ -7,7 +7,7 @@ This is especially true for \mimetype{image/*} and \mimetype{text/*} type messages containing binary data. The \module{email} package provides some convenient encodings in its -\module{Encoders} module. These encoders are actually used by the +\module{encoders} module. These encoders are actually used by the \class{MIMEAudio} and \class{MIMEImage} class constructors to provide default encodings. All encoder functions take exactly one argument, the message object to encode. They usually extract the payload, encode it, and reset the diff --git a/Doc/lib/emailexc.tex b/Doc/lib/emailexc.tex index 6ac088949cd..3cef1d5e7e6 100644 --- a/Doc/lib/emailexc.tex +++ b/Doc/lib/emailexc.tex @@ -1,8 +1,8 @@ -\declaremodule{standard}{email.Errors} +\declaremodule{standard}{email.errors} \modulesynopsis{The exception classes used by the email package.} The following exception classes are defined in the -\module{email.Errors} module: +\module{email.errors} module: \begin{excclassdesc}{MessageError}{} This is the base class for all exceptions that the \module{email} @@ -59,7 +59,7 @@ problem was found, so for example, if a message nested inside a \mimetype{multipart/alternative} had a malformed header, that nested message object would have a defect, but the containing messages would not. -All defect classes are subclassed from \class{email.Errors.MessageDefect}, but +All defect classes are subclassed from \class{email.errors.MessageDefect}, but this class is \emph{not} an exception! \versionadded[All the defect classes were added]{2.4} diff --git a/Doc/lib/emailgenerator.tex b/Doc/lib/emailgenerator.tex index 330abc0d41e..3415442897f 100644 --- a/Doc/lib/emailgenerator.tex +++ b/Doc/lib/emailgenerator.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Generator} +\declaremodule{standard}{email.generator} \modulesynopsis{Generate flat text email messages from a message structure.} One of the most common tasks is to generate the flat text of the email @@ -8,7 +8,7 @@ module or the \refmodule{nntplib} module, or print the message on the console. Taking a message object structure and producing a flat text document is the job of the \class{Generator} class. -Again, as with the \refmodule{email.Parser} module, you aren't limited +Again, as with the \refmodule{email.parser} module, you aren't limited to the functionality of the bundled generator; you could write one from scratch yourself. However the bundled generator knows how to generate most email in a standards-compliant way, should handle MIME @@ -17,7 +17,8 @@ transformation from flat text, to a message structure via the \class{Parser} class, and back to flat text, is idempotent (the input is identical to the output). -Here are the public methods of the \class{Generator} class: +Here are the public methods of the \class{Generator} class, imported from the +\module{email.generator} module: \begin{classdesc}{Generator}{outfp\optional{, mangle_from_\optional{, maxheaderlen}}} @@ -40,7 +41,7 @@ mailbox format files. Optional \var{maxheaderlen} specifies the longest length for a non-continued header. When a header line is longer than \var{maxheaderlen} (in characters, with tabs expanded to 8 spaces), -the header will be split as defined in the \module{email.Header} +the header will be split as defined in the \module{email.header.Header} class. Set to zero to disable header wrapping. The default is 78, as recommended (but not required) by \rfc{2822}. \end{classdesc} @@ -81,9 +82,9 @@ be used in extended print statements. As a convenience, see the methods \method{Message.as_string()} and \code{str(aMessage)}, a.k.a. \method{Message.__str__()}, which simplify the generation of a formatted string representation of a -message object. For more detail, see \refmodule{email.Message}. +message object. For more detail, see \refmodule{email.message}. -The \module{email.Generator} module also provides a derived class, +The \module{email.generator} module also provides a derived class, called \class{DecodedGenerator} which is like the \class{Generator} base class, except that non-\mimetype{text} parts are substituted with a format string representing the part. @@ -128,13 +129,5 @@ The default value for \var{fmt} is \code{None}, meaning \versionadded{2.2.2} \end{classdesc} -\subsubsection{Deprecated methods} - -The following methods are deprecated in \module{email} version 2. -They are documented here for completeness. - -\begin{methoddesc}[Generator]{__call__}{msg\optional{, unixfrom}} -This method is identical to the \method{flatten()} method. - -\deprecated{2.2.2}{Use the \method{flatten()} method instead.} -\end{methoddesc} +\versionchanged[The previously deprecated method \method{__call__()} was +removed]{2.5} diff --git a/Doc/lib/emailheaders.tex b/Doc/lib/emailheaders.tex index 2795644b798..524d08c3782 100644 --- a/Doc/lib/emailheaders.tex +++ b/Doc/lib/emailheaders.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Header} +\declaremodule{standard}{email.header} \modulesynopsis{Representing non-ASCII headers} \rfc{2822} is the base standard that describes the format of email @@ -15,17 +15,18 @@ slew of RFCs have been written describing how to encode email containing non-\ASCII{} characters into \rfc{2822}-compliant format. These RFCs include \rfc{2045}, \rfc{2046}, \rfc{2047}, and \rfc{2231}. The \module{email} package supports these standards in its -\module{email.Header} and \module{email.Charset} modules. +\module{email.header} and \module{email.charset} modules. If you want to include non-\ASCII{} characters in your email headers, say in the \mailheader{Subject} or \mailheader{To} fields, you should use the \class{Header} class and assign the field in the \class{Message} object to an instance of \class{Header} instead of -using a string for the header value. For example: +using a string for the header value. Import the \class{Header} class from the +\module{email.header} module. For example: \begin{verbatim} ->>> from email.Message import Message ->>> from email.Header import Header +>>> from email.message import Message +>>> from email.header import Header >>> msg = Message() >>> h = Header('p\xf6stal', 'iso-8859-1') >>> msg['Subject'] = h @@ -87,7 +88,7 @@ Optional \var{errors} is passed straight through to the Append the string \var{s} to the MIME header. Optional \var{charset}, if given, should be a \class{Charset} instance -(see \refmodule{email.Charset}) or the name of a character set, which +(see \refmodule{email.charset}) or the name of a character set, which will be converted to a \class{Charset} instance. A value of \code{None} (the default) means that the \var{charset} given in the constructor is used. @@ -139,7 +140,7 @@ This method allows you to compare two \class{Header} instances for equality. This method allows you to compare two \class{Header} instances for inequality. \end{methoddesc} -The \module{email.Header} module also provides the following +The \module{email.header} module also provides the following convenient functions. \begin{funcdesc}{decode_header}{header} @@ -155,7 +156,7 @@ encoded string. Here's an example: \begin{verbatim} ->>> from email.Header import decode_header +>>> from email.header import decode_header >>> decode_header('=?iso-8859-1?q?p=F6stal?=') [('p\xf6stal', 'iso-8859-1')] \end{verbatim} diff --git a/Doc/lib/emailiter.tex b/Doc/lib/emailiter.tex index d1a8f98064b..ef8ef6f45ea 100644 --- a/Doc/lib/emailiter.tex +++ b/Doc/lib/emailiter.tex @@ -1,8 +1,8 @@ -\declaremodule{standard}{email.Iterators} +\declaremodule{standard}{email.iterators} \modulesynopsis{Iterate over a message object tree.} Iterating over a message object tree is fairly easy with the -\method{Message.walk()} method. The \module{email.Iterators} module +\method{Message.walk()} method. The \module{email.iterators} module provides some useful higher level iterations over message object trees. diff --git a/Doc/lib/emailmessage.tex b/Doc/lib/emailmessage.tex index 9b41852d78b..7bd7dd8b309 100644 --- a/Doc/lib/emailmessage.tex +++ b/Doc/lib/emailmessage.tex @@ -1,10 +1,11 @@ -\declaremodule{standard}{email.Message} +\declaremodule{standard}{email.message} \modulesynopsis{The base class representing email messages.} The central class in the \module{email} package is the -\class{Message} class; it is the base class for the \module{email} -object model. \class{Message} provides the core functionality for -setting and querying header fields, and for accessing message bodies. +\class{Message} class, imported from the \module{email.message} module. It is +the base class for the \module{email} object model. \class{Message} provides +the core functionality for setting and querying header fields, and for +accessing message bodies. Conceptually, a \class{Message} object consists of \emph{headers} and \emph{payloads}. Headers are \rfc{2822} style field names and @@ -45,7 +46,7 @@ begin with \code{From }. For more flexibility, instantiate a \begin{verbatim} from cStringIO import StringIO -from email.Generator import Generator +from email.generator import Generator fp = StringIO() g = Generator(fp, mangle_from_=False, maxheaderlen=60) g.flatten(msg) @@ -119,7 +120,7 @@ client's responsibility to ensure the payload invariants. Optional \begin{methoddesc}[Message]{set_charset}{charset} Set the character set of the payload to \var{charset}, which can -either be a \class{Charset} instance (see \refmodule{email.Charset}), a +either be a \class{Charset} instance (see \refmodule{email.charset}), a string naming a character set, or \code{None}. If it is a string, it will be converted to a \class{Charset} instance. If \var{charset} is \code{None}, the @@ -128,8 +129,8 @@ or \code{None}. If it is a string, it will be converted to a \exception{TypeError}. The message will be assumed to be of type \mimetype{text/*} encoded with -\code{charset.input_charset}. It will be converted to -\code{charset.output_charset} +\var{charset.input_charset}. It will be converted to +\var{charset.output_charset} and encoded properly, if needed, when generating the plain text representation of the message. MIME headers (\mailheader{MIME-Version}, \mailheader{Content-Type}, @@ -513,6 +514,9 @@ message/rfc822 \end{verbatim} \end{methoddesc} +\versionchanged[The previously deprecated methods \method{get_type()}, +\method{get_main_type()}, and \method{get_subtype()} were removed]{2.5} + \class{Message} objects can also optionally contain two instance attributes, which can be used when generating the plain text of a MIME message. @@ -532,7 +536,7 @@ to the message's \var{preamble} attribute. When the \class{Generator} is writing out the plain text representation of a MIME message, and it finds the message has a \var{preamble} attribute, it will write this text in the area between the headers and the first boundary. See -\refmodule{email.Parser} and \refmodule{email.Generator} for details. +\refmodule{email.parser} and \refmodule{email.generator} for details. Note that if the message object has no preamble, the \var{preamble} attribute will be \code{None}. @@ -543,58 +547,15 @@ The \var{epilogue} attribute acts the same way as the \var{preamble} attribute, except that it contains text that appears between the last boundary and the end of the message. -One note: when generating the flat text for a \mimetype{multipart} -message that has no \var{epilogue} (using the standard -\class{Generator} class), no newline is added after the closing -boundary line. If the message object has an \var{epilogue} and its -value does not start with a newline, a newline is printed after the -closing boundary. This seems a little clumsy, but it makes the most -practical sense. The upshot is that if you want to ensure that a -newline get printed after your closing \mimetype{multipart} boundary, -set the \var{epilogue} to the empty string. +\versionchanged[You do not need to set the epilogue to the empty string in +order for the \class{Generator} to print a newline at the end of the +file]{2.5} \end{datadesc} \begin{datadesc}{defects} The \var{defects} attribute contains a list of all the problems found when -parsing this message. See \refmodule{email.Errors} for a detailed description +parsing this message. See \refmodule{email.errors} for a detailed description of the possible parsing defects. \versionadded{2.4} \end{datadesc} - -\subsubsection{Deprecated methods} - -\versionchanged[The \method{add_payload()} method was removed; use the -\method{attach()} method instead]{2.4} - -The following methods are deprecated. They are documented here for -completeness. - -\begin{methoddesc}[Message]{get_type}{\optional{failobj}} -Return the message's content type, as a string of the form -\mimetype{maintype/subtype} as taken from the -\mailheader{Content-Type} header. -The returned string is coerced to lowercase. - -If there is no \mailheader{Content-Type} header in the message, -\var{failobj} is returned (defaults to \code{None}). - -\deprecated{2.2.2}{Use the \method{get_content_type()} method instead.} -\end{methoddesc} - -\begin{methoddesc}[Message]{get_main_type}{\optional{failobj}} -Return the message's \emph{main} content type. This essentially returns the -\var{maintype} part of the string returned by \method{get_type()}, with the -same semantics for \var{failobj}. - -\deprecated{2.2.2}{Use the \method{get_content_maintype()} method instead.} -\end{methoddesc} - -\begin{methoddesc}[Message]{get_subtype}{\optional{failobj}} -Return the message's sub-content type. This essentially returns the -\var{subtype} part of the string returned by \method{get_type()}, with the -same semantics for \var{failobj}. - -\deprecated{2.2.2}{Use the \method{get_content_subtype()} method instead.} -\end{methoddesc} - diff --git a/Doc/lib/emailmimebase.tex b/Doc/lib/emailmimebase.tex index 070c9a27b20..4735be3237f 100644 --- a/Doc/lib/emailmimebase.tex +++ b/Doc/lib/emailmimebase.tex @@ -1,3 +1,11 @@ +\declaremodule{standard}{email.mime} +\declaremodule{standard}{email.mime.base} +\declaremodule{standard}{email.mime.nonmultipart} +\declaremodule{standard}{email.mime.multipart} +\declaremodule{standard}{email.mime.audio} +\declaremodule{standard}{email.mime.image} +\declaremodule{standard}{email.mime.message} +\declaremodule{standard}{email.mime.text} Ordinarily, you get a message object structure by passing a file or some text to a parser, which parses the text and returns the root message object. However you can also build a complete message @@ -6,26 +14,16 @@ hand. In fact, you can also take an existing structure and add new \class{Message} objects, move them around, etc. This makes a very convenient interface for slicing-and-dicing MIME messages. -You can create a new object structure by creating \class{Message} -instances, adding attachments and all the appropriate headers manually. -For MIME messages though, the \module{email} package provides some -convenient subclasses to make things easier. Each of these classes -should be imported from a module with the same name as the class, from -within the \module{email} package. E.g.: - -\begin{verbatim} -import email.MIMEImage.MIMEImage -\end{verbatim} - -or - -\begin{verbatim} -from email.MIMEText import MIMEText -\end{verbatim} +You can create a new object structure by creating \class{Message} instances, +adding attachments and all the appropriate headers manually. For MIME +messages though, the \module{email} package provides some convenient +subclasses to make things easier. Here are the classes: \begin{classdesc}{MIMEBase}{_maintype, _subtype, **_params} +Module: \module{email.mime.base} + This is the base class for all the MIME-specific subclasses of \class{Message}. Ordinarily you won't create instances specifically of \class{MIMEBase}, although you could. \class{MIMEBase} is provided @@ -45,6 +43,8 @@ The \class{MIMEBase} class always adds a \mailheader{Content-Type} header \end{classdesc} \begin{classdesc}{MIMENonMultipart}{} +Module: \module{email.mime.nonmultipart} + A subclass of \class{MIMEBase}, this is an intermediate base class for MIME messages that are not \mimetype{multipart}. The primary purpose of this class is to prevent the use of the \method{attach()} method, @@ -57,6 +57,7 @@ exception is raised. \begin{classdesc}{MIMEMultipart}{\optional{subtype\optional{, boundary\optional{, _subparts\optional{, _params}}}}} +Module: \module{email.mime.multipart} A subclass of \class{MIMEBase}, this is an intermediate base class for MIME messages that are \mimetype{multipart}. Optional \var{_subtype} @@ -80,8 +81,31 @@ argument, which is a keyword dictionary. \versionadded{2.2.2} \end{classdesc} +\begin{classdesc}{MIMEApplication}{_data\optional{, _subtype\optional{, + _encoder\optional{, **_params}}}} +Module: \module{email.mime.application} + +A subclass of \class{MIMENonMultipart}, the \class{MIMEApplication} class is +used to represent MIME message objects of major type \mimetype{application}. +\var{_data} is a string containing the raw byte data. Optional \var{_subtype} +specifies the MIME subtype and defaults to \mimetype{octet-stream}. + +Optional \var{_encoder} is a callable (i.e. function) which will +perform the actual encoding of the data for transport. This +callable takes one argument, which is the \class{MIMEApplication} instance. +It should use \method{get_payload()} and \method{set_payload()} to +change the payload to encoded form. It should also add any +\mailheader{Content-Transfer-Encoding} or other headers to the message +object as necessary. The default encoding is base64. See the +\refmodule{email.encoders} module for a list of the built-in encoders. + +\var{_params} are passed straight through to the base class constructor. +\versionadded{2.5} +\end{classdesc} + \begin{classdesc}{MIMEAudio}{_audiodata\optional{, _subtype\optional{, _encoder\optional{, **_params}}}} +Module: \module{email.mime.audio} A subclass of \class{MIMENonMultipart}, the \class{MIMEAudio} class is used to create MIME message objects of major type \mimetype{audio}. @@ -100,13 +124,14 @@ It should use \method{get_payload()} and \method{set_payload()} to change the payload to encoded form. It should also add any \mailheader{Content-Transfer-Encoding} or other headers to the message object as necessary. The default encoding is base64. See the -\refmodule{email.Encoders} module for a list of the built-in encoders. +\refmodule{email.encoders} module for a list of the built-in encoders. \var{_params} are passed straight through to the base class constructor. \end{classdesc} \begin{classdesc}{MIMEImage}{_imagedata\optional{, _subtype\optional{, _encoder\optional{, **_params}}}} +Module: \module{email.mime.image} A subclass of \class{MIMENonMultipart}, the \class{MIMEImage} class is used to create MIME message objects of major type \mimetype{image}. @@ -125,13 +150,15 @@ It should use \method{get_payload()} and \method{set_payload()} to change the payload to encoded form. It should also add any \mailheader{Content-Transfer-Encoding} or other headers to the message object as necessary. The default encoding is base64. See the -\refmodule{email.Encoders} module for a list of the built-in encoders. +\refmodule{email.encoders} module for a list of the built-in encoders. \var{_params} are passed straight through to the \class{MIMEBase} constructor. \end{classdesc} \begin{classdesc}{MIMEMessage}{_msg\optional{, _subtype}} +Module: \module{email.mime.message} + A subclass of \class{MIMENonMultipart}, the \class{MIMEMessage} class is used to create MIME objects of main type \mimetype{message}. \var{_msg} is used as the payload, and must be an instance of class @@ -143,6 +170,8 @@ to \mimetype{rfc822}. \end{classdesc} \begin{classdesc}{MIMEText}{_text\optional{, _subtype\optional{, _charset}}} +Module: \module{email.mime.text} + A subclass of \class{MIMENonMultipart}, the \class{MIMEText} class is used to create MIME objects of major type \mimetype{text}. \var{_text} is the string for the payload. \var{_subtype} is the diff --git a/Doc/lib/emailparser.tex b/Doc/lib/emailparser.tex index 5fac92f41f9..609fa4008e3 100644 --- a/Doc/lib/emailparser.tex +++ b/Doc/lib/emailparser.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Parser} +\declaremodule{standard}{email.parser} \modulesynopsis{Parse flat text email messages to produce a message object structure.} @@ -41,9 +41,10 @@ message object trees any way it finds necessary. \versionadded{2.4} -The \class{FeedParser} provides an API that is conducive to incremental -parsing of email messages, such as would be necessary when reading the text of -an email message from a source that can block (e.g. a socket). The +The \class{FeedParser}, imported from the \module{email.feedparser} module, +provides an API that is conducive to incremental parsing of email messages, +such as would be necessary when reading the text of an email message from a +source that can block (e.g. a socket). The \class{FeedParser} can of course be used to parse an email message fully contained in a string or a file, but the classic \class{Parser} API may be more convenient for such use cases. The semantics and results of the two @@ -56,14 +57,14 @@ accurate when parsing standards-compliant messages, and it does a very good job of parsing non-compliant messages, providing information about how a message was deemed broken. It will populate a message object's \var{defects} attribute with a list of any problems it found in a message. See the -\refmodule{email.Errors} module for the list of defects that it can find. +\refmodule{email.errors} module for the list of defects that it can find. Here is the API for the \class{FeedParser}: \begin{classdesc}{FeedParser}{\optional{_factory}} Create a \class{FeedParser} instance. Optional \var{_factory} is a no-argument callable that will be called whenever a new message object is -needed. It defaults to the \class{email.Message.Message} class. +needed. It defaults to the \class{email.message.Message} class. \end{classdesc} \begin{methoddesc}[FeedParser]{feed}{data} @@ -82,21 +83,22 @@ more data to a closed \class{FeedParser}. \subsubsection{Parser class API} -The \class{Parser} provides an API that can be used to parse a message when -the complete contents of the message are available in a string or file. The -\module{email.Parser} module also provides a second class, called +The \class{Parser} class, imported from the \module{email.parser} module, +provides an API that can be used to parse a message when the complete contents +of the message are available in a string or file. The +\module{email.parser} module also provides a second class, called \class{HeaderParser} which can be used if you're only interested in the headers of the message. \class{HeaderParser} can be much faster in these situations, since it does not attempt to parse the message body, instead setting the payload to the raw body as a string. \class{HeaderParser} has the same API as the \class{Parser} class. -\begin{classdesc}{Parser}{\optional{_class\optional{, strict}}} +\begin{classdesc}{Parser}{\optional{_class}} The constructor for the \class{Parser} class takes an optional argument \var{_class}. This must be a callable factory (such as a function or a class), and it is used whenever a sub-message object needs to be created. It defaults to \class{Message} (see -\refmodule{email.Message}). The factory will be called without +\refmodule{email.message}). The factory will be called without arguments. The optional \var{strict} flag is ignored. \deprecated{2.4}{Because the @@ -201,6 +203,6 @@ Here are some notes on the parsing semantics: \method{is_multipart()} method may return \code{False}. If such messages were parsed with the \class{FeedParser}, they will have an instance of the \class{MultipartInvariantViolationDefect} class in their - \var{defects} attribute list. See \refmodule{email.Errors} for + \var{defects} attribute list. See \refmodule{email.errors} for details. \end{itemize} diff --git a/Doc/lib/emailutil.tex b/Doc/lib/emailutil.tex index 491a2b9d0ab..fe96473638f 100644 --- a/Doc/lib/emailutil.tex +++ b/Doc/lib/emailutil.tex @@ -1,7 +1,7 @@ -\declaremodule{standard}{email.Utils} +\declaremodule{standard}{email.utils} \modulesynopsis{Miscellaneous email package utilities.} -There are several useful utilities provided in the \module{email.Utils} +There are several useful utilities provided in the \module{email.utils} module: \begin{funcdesc}{quote}{str} @@ -38,7 +38,7 @@ 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 +from email.utils import getaddresses tos = msg.get_all('to', []) ccs = msg.get_all('cc', []) diff --git a/Doc/lib/mimelib.tex b/Doc/lib/mimelib.tex index 67de5975836..491d844eb6b 100644 --- a/Doc/lib/mimelib.tex +++ b/Doc/lib/mimelib.tex @@ -12,9 +12,9 @@ \authoraddress{\email{barry@python.org}} \date{\today} -\release{3.0} % software release, not documentation +\release{4.0} % software release, not documentation \setreleaseinfo{} % empty for final release -\setshortversion{3.0} % major.minor only for software +\setshortversion{4.0} % major.minor only for software \begin{document} @@ -38,11 +38,11 @@ The \module{email} package provides classes and utilities to create, parse, generate, and modify email messages, conforming to all the relevant email and MIME related RFCs. -This document describes version 3.0 of the \module{email} package, which is -distributed with Python 2.4 and is available as a standalone distutils-based -package for use with Python 2.3. \module{email} 3.0 is not compatible with -Python versions earlier than 2.3. For more information about the -\module{email} package, including download links and mailing lists, see +This document describes version 4.0 of the \module{email} package, which is +distributed with Python 2.5 and is available as a standalone distutils-based +package for use with earlier Python versions. \module{email} 4.0 is not +compatible with Python versions earlier than 2.3. For more information about +the \module{email} package, including download links and mailing lists, see \ulink{Python's email SIG}{http://www.python.org/sigs/email-sig}. The documentation that follows was written for the Python project, so @@ -51,7 +51,8 @@ package documentation, there are a few notes to be aware of: \begin{itemize} \item Deprecation and ``version added'' notes are relative to the - Python version a feature was added or deprecated. + Python version a feature was added or deprecated. See + the package history in section \ref{email-pkg-history} for details. \item If you're reading this documentation as part of the standalone \module{email} package, some of the internal links to diff --git a/Lib/email/__init__.py b/Lib/email/__init__.py index e5c0e2e9d58..0a6a72de80f 100644 --- a/Lib/email/__init__.py +++ b/Lib/email/__init__.py @@ -4,9 +4,10 @@ """A package for parsing, handling, and generating email messages.""" -__version__ = '3.0.1' +__version__ = '4.0a2' __all__ = [ + # Old names 'base64MIME', 'Charset', 'Encoders', @@ -27,6 +28,19 @@ __all__ = [ 'Utils', 'message_from_string', 'message_from_file', + # new names + 'base64mime', + 'charset', + 'encoders', + 'errors', + 'generator', + 'header', + 'iterators', + 'message', + 'mime', + 'parser', + 'quoprimime', + 'utils', ] @@ -39,7 +53,7 @@ def message_from_string(s, *args, **kws): Optional _class and strict are passed to the Parser constructor. """ - from email.Parser import Parser + from email.parser import Parser return Parser(*args, **kws).parsestr(s) @@ -48,5 +62,62 @@ def message_from_file(fp, *args, **kws): Optional _class and strict are passed to the Parser constructor. """ - from email.Parser import Parser + from email.parser import Parser return Parser(*args, **kws).parse(fp) + + + +# Lazy loading to provide name mapping from new-style names (PEP 8 compatible +# email 4.0 module names), to old-style names (email 3.0 module names). +import sys + +class LazyImporter(object): + def __init__(self, module_name): + self.__name__ = 'email.' + module_name + + def __getattr__(self, name): + __import__(self.__name__) + mod = sys.modules[self.__name__] + self.__dict__.update(mod.__dict__) + return getattr(mod, name) + + +_LOWERNAMES = [ + # email. -> email. + 'Charset', + 'Encoders', + 'Errors', + 'FeedParser', + 'Generator', + 'Header', + 'Iterators', + 'Message', + 'Parser', + 'Utils', + 'base64MIME', + 'quopriMIME', + ] + +_MIMENAMES = [ + # email.MIME -> email.mime. + 'Audio', + 'Base', + 'Image', + 'Message', + 'Multipart', + 'NonMultipart', + 'Text', + ] + +for _name in _LOWERNAMES: + importer = LazyImporter(_name.lower()) + sys.modules['email.' + _name] = importer + setattr(sys.modules['email'], _name, importer) + + +import email.mime +for _name in _MIMENAMES: + importer = LazyImporter('mime.' + _name.lower()) + sys.modules['email.MIME' + _name] = importer + setattr(sys.modules['email'], 'MIME' + _name, importer) + setattr(sys.modules['email.mime'], _name, importer) diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py index 7d759efbcff..109ff5f7c77 100644 --- a/Lib/email/_parseaddr.py +++ b/Lib/email/_parseaddr.py @@ -6,6 +6,13 @@ Lifted directly from rfc822.py. This should eventually be rewritten. """ +__all__ = [ + 'mktime_tz', + 'parsedate', + 'parsedate_tz', + 'quote', + ] + import time SPACE = ' ' diff --git a/Lib/email/base64MIME.py b/Lib/email/base64mime.py similarity index 95% rename from Lib/email/base64MIME.py rename to Lib/email/base64mime.py index 6ed1d535841..0129d9d4e66 100644 --- a/Lib/email/base64MIME.py +++ b/Lib/email/base64mime.py @@ -1,4 +1,4 @@ -# Copyright (C) 2002-2004 Python Software Foundation +# Copyright (C) 2002-2006 Python Software Foundation # Author: Ben Gertzfield # Contact: email-sig@python.org @@ -24,9 +24,21 @@ decoding. To deal with the various line wrapping issues, use the email.Header module. """ +__all__ = [ + 'base64_len', + 'body_decode', + 'body_encode', + 'decode', + 'decodestring', + 'encode', + 'encodestring', + 'header_encode', + ] + import re + from binascii import b2a_base64, a2b_base64 -from email.Utils import fix_eols +from email.utils import fix_eols CRLF = '\r\n' NL = '\n' diff --git a/Lib/email/Charset.py b/Lib/email/charset.py similarity index 90% rename from Lib/email/Charset.py rename to Lib/email/charset.py index fd4043bb87c..8f218b2095b 100644 --- a/Lib/email/Charset.py +++ b/Lib/email/charset.py @@ -2,9 +2,18 @@ # Author: Ben Gertzfield, Barry Warsaw # Contact: email-sig@python.org -import email.base64MIME -import email.quopriMIME -from email.Encoders import encode_7or8bit +__all__ = [ + 'Charset', + 'add_alias', + 'add_charset', + 'add_codec', + ] + +import email.base64mime +import email.quoprimime + +from email import errors +from email.encoders import encode_7or8bit @@ -186,8 +195,17 @@ class Charset: """ def __init__(self, input_charset=DEFAULT_CHARSET): # RFC 2046, $4.1.2 says charsets are not case sensitive. We coerce to - # unicode because its .lower() is locale insensitive. - input_charset = unicode(input_charset, 'ascii').lower() + # unicode because its .lower() is locale insensitive. If the argument + # is already a unicode, we leave it at that, but ensure that the + # charset is ASCII, as the standard (RFC XXX) requires. + try: + if isinstance(input_charset, unicode): + input_charset.encode('ascii') + else: + input_charset = unicode(input_charset, 'ascii') + except UnicodeError: + raise errors.CharsetError(input_charset) + input_charset = input_charset.lower() # Set the input charset after filtering through the aliases self.input_charset = ALIASES.get(input_charset, input_charset) # We can try to guess which encoding and conversion to use by the @@ -307,12 +325,12 @@ class Charset: cset = self.get_output_charset() # The len(s) of a 7bit encoding is len(s) if self.header_encoding == BASE64: - return email.base64MIME.base64_len(s) + len(cset) + MISC_LEN + return email.base64mime.base64_len(s) + len(cset) + MISC_LEN elif self.header_encoding == QP: - return email.quopriMIME.header_quopri_len(s) + len(cset) + MISC_LEN + return email.quoprimime.header_quopri_len(s) + len(cset) + MISC_LEN elif self.header_encoding == SHORTEST: - lenb64 = email.base64MIME.base64_len(s) - lenqp = email.quopriMIME.header_quopri_len(s) + lenb64 = email.base64mime.base64_len(s) + lenqp = email.quoprimime.header_quopri_len(s) return min(lenb64, lenqp) + len(cset) + MISC_LEN else: return len(s) @@ -335,16 +353,16 @@ class Charset: s = self.convert(s) # 7bit/8bit encodings return the string unchanged (modulo conversions) if self.header_encoding == BASE64: - return email.base64MIME.header_encode(s, cset) + return email.base64mime.header_encode(s, cset) elif self.header_encoding == QP: - return email.quopriMIME.header_encode(s, cset, maxlinelen=None) + return email.quoprimime.header_encode(s, cset, maxlinelen=None) elif self.header_encoding == SHORTEST: - lenb64 = email.base64MIME.base64_len(s) - lenqp = email.quopriMIME.header_quopri_len(s) + lenb64 = email.base64mime.base64_len(s) + lenqp = email.quoprimime.header_quopri_len(s) if lenb64 < lenqp: - return email.base64MIME.header_encode(s, cset) + return email.base64mime.header_encode(s, cset) else: - return email.quopriMIME.header_encode(s, cset, maxlinelen=None) + return email.quoprimime.header_encode(s, cset, maxlinelen=None) else: return s @@ -363,8 +381,8 @@ class Charset: s = self.convert(s) # 7bit/8bit encodings return the string unchanged (module conversions) if self.body_encoding is BASE64: - return email.base64MIME.body_encode(s) + return email.base64mime.body_encode(s) elif self.body_encoding is QP: - return email.quopriMIME.body_encode(s) + return email.quoprimime.body_encode(s) else: return s diff --git a/Lib/email/Encoders.py b/Lib/email/encoders.py similarity index 93% rename from Lib/email/Encoders.py rename to Lib/email/encoders.py index baac2a34588..06016cdea7c 100644 --- a/Lib/email/Encoders.py +++ b/Lib/email/encoders.py @@ -1,12 +1,22 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Encodings and related functions.""" +__all__ = [ + 'encode_7or8bit', + 'encode_base64', + 'encode_noop', + 'encode_quopri', + ] + import base64 + from quopri import encodestring as _encodestring + + def _qencode(s): enc = _encodestring(s, quotetabs=True) # Must encode spaces, which quopri.encodestring() doesn't do diff --git a/Lib/email/Errors.py b/Lib/email/errors.py similarity index 92% rename from Lib/email/Errors.py rename to Lib/email/errors.py index e13a2c75c8f..d52a624601f 100644 --- a/Lib/email/Errors.py +++ b/Lib/email/errors.py @@ -1,4 +1,4 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org @@ -26,6 +26,10 @@ class MultipartConversionError(MessageError, TypeError): """Conversion to a multipart is prohibited.""" +class CharsetError(MessageError): + """An illegal charset was given.""" + + # These are parsing defects which the parser was able to work around. class MessageDefect: diff --git a/Lib/email/FeedParser.py b/Lib/email/feedparser.py similarity index 97% rename from Lib/email/FeedParser.py rename to Lib/email/feedparser.py index a2130e27618..afb02b32b24 100644 --- a/Lib/email/FeedParser.py +++ b/Lib/email/feedparser.py @@ -19,9 +19,12 @@ the current message. Defects are just instances that live on the message object's .defects attribute. """ +__all__ = ['FeedParser'] + import re -from email import Errors -from email import Message + +from email import errors +from email import message NLCRE = re.compile('\r\n|\r|\n') NLCRE_bol = re.compile('(\r\n|\r|\n)') @@ -130,7 +133,7 @@ class BufferedSubFile(object): class FeedParser: """A feed-style parser of email.""" - def __init__(self, _factory=Message.Message): + def __init__(self, _factory=message.Message): """_factory is called with no arguments to create a new message obj""" self._factory = _factory self._input = BufferedSubFile() @@ -164,7 +167,7 @@ class FeedParser: # Look for final set of defects if root.get_content_maintype() == 'multipart' \ and not root.is_multipart(): - root.defects.append(Errors.MultipartInvariantViolationDefect()) + root.defects.append(errors.MultipartInvariantViolationDefect()) return root def _new_message(self): @@ -277,7 +280,7 @@ class FeedParser: # defined a boundary. That's a problem which we'll handle by # reading everything until the EOF and marking the message as # defective. - self._cur.defects.append(Errors.NoBoundaryInMultipartDefect()) + self._cur.defects.append(errors.NoBoundaryInMultipartDefect()) lines = [] for line in self._input: if line is NeedMoreData: @@ -381,7 +384,7 @@ class FeedParser: # that as a defect and store the captured text as the payload. # Everything from here to the EOF is epilogue. if capturing_preamble: - self._cur.defects.append(Errors.StartBoundaryNotFoundDefect()) + self._cur.defects.append(errors.StartBoundaryNotFoundDefect()) self._cur.set_payload(EMPTYSTRING.join(preamble)) epilogue = [] for line in self._input: @@ -432,7 +435,7 @@ class FeedParser: # The first line of the headers was a continuation. This # is illegal, so let's note the defect, store the illegal # line, and ignore it for purposes of headers. - defect = Errors.FirstHeaderLineIsContinuationDefect(line) + defect = errors.FirstHeaderLineIsContinuationDefect(line) self._cur.defects.append(defect) continue lastvalue.append(line) @@ -460,13 +463,13 @@ class FeedParser: else: # Weirdly placed unix-from line. Note this as a defect # and ignore it. - defect = Errors.MisplacedEnvelopeHeaderDefect(line) + defect = errors.MisplacedEnvelopeHeaderDefect(line) self._cur.defects.append(defect) continue # Split the line on the colon separating field name from value. i = line.find(':') if i < 0: - defect = Errors.MalformedHeaderDefect(line) + defect = errors.MalformedHeaderDefect(line) self._cur.defects.append(defect) continue lastheader = line[:i] diff --git a/Lib/email/Generator.py b/Lib/email/generator.py similarity index 97% rename from Lib/email/Generator.py rename to Lib/email/generator.py index 7969916ff96..6e7a515302f 100644 --- a/Lib/email/Generator.py +++ b/Lib/email/generator.py @@ -4,14 +4,16 @@ """Classes to generate plain text from a message object tree.""" +__all__ = ['Generator', 'DecodedGenerator'] + import re import sys import time import random import warnings -from cStringIO import StringIO -from email.Header import Header +from cStringIO import StringIO +from email.header import Header UNDERSCORE = '_' NL = '\n' @@ -81,12 +83,6 @@ class Generator: print >> self._fp, ufrom self._write(msg) - # For backwards compatibility, but this is slower - def __call__(self, msg, unixfrom=False): - warnings.warn('__call__() deprecated; use flatten()', - DeprecationWarning, 2) - self.flatten(msg, unixfrom) - def clone(self, fp): """Clone this generator with the exact same options.""" return self.__class__(fp, self._mangle_from_, self._maxheaderlen) diff --git a/Lib/email/Header.py b/Lib/email/header.py similarity index 98% rename from Lib/email/Header.py rename to Lib/email/header.py index 5e24afede01..183c337560d 100644 --- a/Lib/email/Header.py +++ b/Lib/email/header.py @@ -1,16 +1,23 @@ -# Copyright (C) 2002-2004 Python Software Foundation +# Copyright (C) 2002-2006 Python Software Foundation # Author: Ben Gertzfield, Barry Warsaw # Contact: email-sig@python.org """Header encoding and decoding functionality.""" +__all__ = [ + 'Header', + 'decode_header', + 'make_header', + ] + import re import binascii -import email.quopriMIME -import email.base64MIME -from email.Errors import HeaderParseError -from email.Charset import Charset +import email.quoprimime +import email.base64mime + +from email.errors import HeaderParseError +from email.charset import Charset NL = '\n' SPACE = ' ' @@ -42,7 +49,7 @@ fcre = re.compile(r'[\041-\176]+:$') # Helpers -_max_append = email.quopriMIME._max_append +_max_append = email.quoprimime._max_append @@ -82,10 +89,10 @@ def decode_header(header): encoded = parts[2] dec = None if encoding == 'q': - dec = email.quopriMIME.header_decode(encoded) + dec = email.quoprimime.header_decode(encoded) elif encoding == 'b': try: - dec = email.base64MIME.decode(encoded) + dec = email.base64mime.decode(encoded) except binascii.Error: # Turn this into a higher level exception. BAW: Right # now we throw the lower level exception away but diff --git a/Lib/email/Iterators.py b/Lib/email/iterators.py similarity index 90% rename from Lib/email/Iterators.py rename to Lib/email/iterators.py index 74a93c7b930..e99f2280da3 100644 --- a/Lib/email/Iterators.py +++ b/Lib/email/iterators.py @@ -1,9 +1,16 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Various types of useful iterators and generators.""" +__all__ = [ + 'body_line_iterator', + 'typed_subpart_iterator', + 'walk', + # Do not include _structure() since it's part of the debugging API. + ] + import sys from cStringIO import StringIO @@ -25,7 +32,6 @@ def walk(self): # These two functions are imported into the Iterators.py interface module. -# The Python 2.2 version uses generators for efficiency. def body_line_iterator(msg, decode=False): """Iterate over the parts, returning string payloads line-by-line. diff --git a/Lib/email/Message.py b/Lib/email/message.py similarity index 92% rename from Lib/email/Message.py rename to Lib/email/message.py index bc764163412..50d90b4560a 100644 --- a/Lib/email/Message.py +++ b/Lib/email/message.py @@ -4,6 +4,8 @@ """Basic message object for the email package object model.""" +__all__ = ['Message'] + import re import uu import binascii @@ -11,9 +13,9 @@ import warnings from cStringIO import StringIO # Intrapackage imports -from email import Utils -from email import Errors -from email import Charset +import email.charset +from email import utils +from email import errors SEMISPACE = '; ' @@ -41,11 +43,11 @@ def _formatparam(param, value=None, quote=True): if isinstance(value, tuple): # Encode as per RFC 2231 param += '*' - value = Utils.encode_rfc2231(value[2], value[0], value[1]) + value = utils.encode_rfc2231(value[2], value[0], value[1]) # BAW: Please check this. I think that if quote is set it should # force quoting even if not necessary. if quote or tspecials.search(value): - return '%s="%s"' % (param, Utils.quote(value)) + return '%s="%s"' % (param, utils.quote(value)) else: return '%s=%s' % (param, value) else: @@ -70,14 +72,14 @@ def _parseparam(s): def _unquotevalue(value): - # This is different than Utils.collapse_rfc2231_value() because it doesn't + # This is different than utils.collapse_rfc2231_value() because it doesn't # try to convert the value to a unicode. Message.get_param() and # Message.get_params() are both currently defined to return the tuple in # the face of RFC 2231 parameters. if isinstance(value, tuple): - return value[0], value[1], Utils.unquote(value[2]) + return value[0], value[1], utils.unquote(value[2]) else: - return Utils.unquote(value) + return utils.unquote(value) @@ -188,17 +190,17 @@ class Message: return None cte = self.get('content-transfer-encoding', '').lower() if cte == 'quoted-printable': - return Utils._qdecode(payload) + return utils._qdecode(payload) elif cte == 'base64': try: - return Utils._bdecode(payload) + return utils._bdecode(payload) except binascii.Error: # Incorrect padding return payload elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'): sfp = StringIO() try: - uu.decode(StringIO(payload+'\n'), sfp) + uu.decode(StringIO(payload+'\n'), sfp, quiet=True) payload = sfp.getvalue() except uu.Error: # Some decoding problem @@ -237,8 +239,8 @@ class Message: self._charset = None return if isinstance(charset, str): - charset = Charset.Charset(charset) - if not isinstance(charset, Charset.Charset): + charset = email.charset.Charset(charset) + if not isinstance(charset, email.charset.Charset): raise TypeError(charset) # BAW: should we accept strings that can serve as arguments to the # Charset constructor? @@ -412,49 +414,6 @@ class Message: else: raise KeyError(_name) - # - # Deprecated methods. These will be removed in email 3.1. - # - - def get_type(self, failobj=None): - """Returns the message's content type. - - The returned string is coerced to lowercase and returned as a single - string of the form `maintype/subtype'. If there was no Content-Type - header in the message, failobj is returned (defaults to None). - """ - warnings.warn('get_type() deprecated; use get_content_type()', - DeprecationWarning, 2) - missing = object() - value = self.get('content-type', missing) - if value is missing: - return failobj - return paramre.split(value)[0].lower().strip() - - def get_main_type(self, failobj=None): - """Return the message's main content type if present.""" - warnings.warn('get_main_type() deprecated; use get_content_maintype()', - DeprecationWarning, 2) - missing = object() - ctype = self.get_type(missing) - if ctype is missing: - return failobj - if ctype.count('/') <> 1: - return failobj - return ctype.split('/')[0] - - def get_subtype(self, failobj=None): - """Return the message's content subtype if present.""" - warnings.warn('get_subtype() deprecated; use get_content_subtype()', - DeprecationWarning, 2) - missing = object() - ctype = self.get_type(missing) - if ctype is missing: - return failobj - if ctype.count('/') <> 1: - return failobj - return ctype.split('/')[1] - # # Use these three methods instead of the three above. # @@ -537,7 +496,7 @@ class Message: name = p.strip() val = '' params.append((name, val)) - params = Utils.decode_params(params) + params = utils.decode_params(params) return params def get_params(self, failobj=None, header='content-type', unquote=True): @@ -714,7 +673,7 @@ class Message: filename = self.get_param('name', missing, 'content-disposition') if filename is missing: return failobj - return Utils.collapse_rfc2231_value(filename).strip() + return utils.collapse_rfc2231_value(filename).strip() def get_boundary(self, failobj=None): """Return the boundary associated with the payload if present. @@ -727,7 +686,7 @@ class Message: if boundary is missing: return failobj # RFC 2046 says that boundaries may begin but not end in w/s - return Utils.collapse_rfc2231_value(boundary).rstrip() + return utils.collapse_rfc2231_value(boundary).rstrip() def set_boundary(self, boundary): """Set the boundary parameter in Content-Type to 'boundary'. @@ -744,7 +703,7 @@ class Message: if params is missing: # There was no Content-Type header, and we don't know what type # to set it to, so raise an exception. - raise Errors.HeaderParseError, 'No Content-Type header found' + raise errors.HeaderParseError('No Content-Type header found') newparams = [] foundp = False for pk, pv in params: diff --git a/Lib/email/mime/__init__.py b/Lib/email/mime/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/Lib/email/mime/application.py b/Lib/email/mime/application.py new file mode 100644 index 00000000000..6f8bb8a823b --- /dev/null +++ b/Lib/email/mime/application.py @@ -0,0 +1,36 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Keith Dart +# Contact: email-sig@python.org + +"""Class representing application/* type MIME documents.""" + +__all__ = ["MIMEApplication"] + +from email import encoders +from email.mime.nonmultipart import MIMENonMultipart + + +class MIMEApplication(MIMENonMultipart): + """Class for generating application/* MIME documents.""" + + def __init__(self, _data, _subtype='octet-stream', + _encoder=encoders.encode_base64, **_params): + """Create an application/* type MIME document. + + _data is a string containing the raw applicatoin data. + + _subtype is the MIME content type subtype, defaulting to + 'octet-stream'. + + _encoder is a function which will perform the actual encoding for + transport of the application data, defaulting to base64 encoding. + + Any additional keyword arguments are passed to the base class + constructor, which turns them into parameters on the Content-Type + header. + """ + if _subtype is None: + raise TypeError('Invalid application MIME subtype') + MIMENonMultipart.__init__(self, 'application', _subtype, **_params) + self.set_payload(_data) + _encoder(self) diff --git a/Lib/email/MIMEAudio.py b/Lib/email/mime/audio.py similarity index 91% rename from Lib/email/MIMEAudio.py rename to Lib/email/mime/audio.py index 266ec4c4095..c7290c4b1c2 100644 --- a/Lib/email/MIMEAudio.py +++ b/Lib/email/mime/audio.py @@ -1,15 +1,16 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Anthony Baxter # Contact: email-sig@python.org """Class representing audio/* type MIME documents.""" -import sndhdr -from cStringIO import StringIO +__all__ = ['MIMEAudio'] -from email import Errors -from email import Encoders -from email.MIMENonMultipart import MIMENonMultipart +import sndhdr + +from cStringIO import StringIO +from email import encoders +from email.mime.nonmultipart import MIMENonMultipart @@ -42,7 +43,7 @@ class MIMEAudio(MIMENonMultipart): """Class for generating audio/* MIME documents.""" def __init__(self, _audiodata, _subtype=None, - _encoder=Encoders.encode_base64, **_params): + _encoder=encoders.encode_base64, **_params): """Create an audio/* type MIME document. _audiodata is a string containing the raw audio data. If this data diff --git a/Lib/email/MIMEBase.py b/Lib/email/mime/base.py similarity index 77% rename from Lib/email/MIMEBase.py rename to Lib/email/mime/base.py index 88691f802e3..ac919258b15 100644 --- a/Lib/email/MIMEBase.py +++ b/Lib/email/mime/base.py @@ -1,14 +1,16 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Base class for MIME specializations.""" -from email import Message +__all__ = ['MIMEBase'] + +from email import message -class MIMEBase(Message.Message): +class MIMEBase(message.Message): """Base class for MIME specializations.""" def __init__(self, _maintype, _subtype, **_params): @@ -18,7 +20,7 @@ class MIMEBase(Message.Message): arguments. Additional parameters for this header are taken from the keyword arguments. """ - Message.Message.__init__(self) + message.Message.__init__(self) ctype = '%s/%s' % (_maintype, _subtype) self.add_header('Content-Type', ctype, **_params) self['MIME-Version'] = '1.0' diff --git a/Lib/email/MIMEImage.py b/Lib/email/mime/image.py similarity index 87% rename from Lib/email/MIMEImage.py rename to Lib/email/mime/image.py index a658067839f..5563823239b 100644 --- a/Lib/email/MIMEImage.py +++ b/Lib/email/mime/image.py @@ -1,14 +1,15 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Class representing image/* type MIME documents.""" +__all__ = ['MIMEImage'] + import imghdr -from email import Errors -from email import Encoders -from email.MIMENonMultipart import MIMENonMultipart +from email import encoders +from email.mime.nonmultipart import MIMENonMultipart @@ -16,7 +17,7 @@ class MIMEImage(MIMENonMultipart): """Class for generating image/* type MIME documents.""" def __init__(self, _imagedata, _subtype=None, - _encoder=Encoders.encode_base64, **_params): + _encoder=encoders.encode_base64, **_params): """Create an image/* type MIME document. _imagedata is a string containing the raw image data. If this data diff --git a/Lib/email/MIMEMessage.py b/Lib/email/mime/message.py similarity index 80% rename from Lib/email/MIMEMessage.py rename to Lib/email/mime/message.py index 3021934ef99..275dbfd0886 100644 --- a/Lib/email/MIMEMessage.py +++ b/Lib/email/mime/message.py @@ -1,11 +1,13 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Class representing message/* MIME documents.""" -from email import Message -from email.MIMENonMultipart import MIMENonMultipart +__all__ = ['MIMEMessage'] + +from email import message +from email.mime.nonmultipart import MIMENonMultipart @@ -23,10 +25,10 @@ class MIMEMessage(MIMENonMultipart): the term "rfc822" is technically outdated by RFC 2822). """ MIMENonMultipart.__init__(self, 'message', _subtype) - if not isinstance(_msg, Message.Message): + if not isinstance(_msg, message.Message): raise TypeError('Argument is not an instance of Message') # It's convenient to use this base class method. We need to do it # this way or we'll get an exception - Message.Message.attach(self, _msg) + message.Message.attach(self, _msg) # And be sure our default type is set correctly self.set_default_type('message/rfc822') diff --git a/Lib/email/MIMEMultipart.py b/Lib/email/mime/multipart.py similarity index 84% rename from Lib/email/MIMEMultipart.py rename to Lib/email/mime/multipart.py index 9072a6421c9..5c8c9dbc4d4 100644 --- a/Lib/email/MIMEMultipart.py +++ b/Lib/email/mime/multipart.py @@ -1,14 +1,16 @@ -# Copyright (C) 2002-2004 Python Software Foundation +# Copyright (C) 2002-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Base class for MIME multipart/* type messages.""" -from email import MIMEBase +__all__ = ['MIMEMultipart'] + +from email.mime.base import MIMEBase -class MIMEMultipart(MIMEBase.MIMEBase): +class MIMEMultipart(MIMEBase): """Base class for MIME multipart/* type messages.""" def __init__(self, _subtype='mixed', boundary=None, _subparts=None, @@ -31,7 +33,7 @@ class MIMEMultipart(MIMEBase.MIMEBase): Additional parameters for the Content-Type header are taken from the keyword arguments (or passed into the _params argument). """ - MIMEBase.MIMEBase.__init__(self, 'multipart', _subtype, **_params) + MIMEBase.__init__(self, 'multipart', _subtype, **_params) if _subparts: for p in _subparts: self.attach(p) diff --git a/Lib/email/MIMENonMultipart.py b/Lib/email/mime/nonmultipart.py similarity index 69% rename from Lib/email/MIMENonMultipart.py rename to Lib/email/mime/nonmultipart.py index 4195d2a6689..dd280b51d03 100644 --- a/Lib/email/MIMENonMultipart.py +++ b/Lib/email/mime/nonmultipart.py @@ -1,15 +1,17 @@ -# Copyright (C) 2002-2004 Python Software Foundation +# Copyright (C) 2002-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Base class for MIME type messages that are not multipart.""" -from email import Errors -from email import MIMEBase +__all__ = ['MIMENonMultipart'] + +from email import errors +from email.mime.base import MIMEBase -class MIMENonMultipart(MIMEBase.MIMEBase): +class MIMENonMultipart(MIMEBase): """Base class for MIME multipart/* type messages.""" __pychecker__ = 'unusednames=payload' @@ -18,7 +20,7 @@ class MIMENonMultipart(MIMEBase.MIMEBase): # The public API prohibits attaching multiple subparts to MIMEBase # derived subtypes since none of them are, by definition, of content # type multipart/* - raise Errors.MultipartConversionError( + raise errors.MultipartConversionError( 'Cannot attach additional subparts to non-multipart/*') del __pychecker__ diff --git a/Lib/email/MIMEText.py b/Lib/email/mime/text.py similarity index 82% rename from Lib/email/MIMEText.py rename to Lib/email/mime/text.py index 5ef187673a1..5747db5d670 100644 --- a/Lib/email/MIMEText.py +++ b/Lib/email/mime/text.py @@ -1,11 +1,13 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Class representing text/* type MIME documents.""" -from email.MIMENonMultipart import MIMENonMultipart -from email.Encoders import encode_7or8bit +__all__ = ['MIMEText'] + +from email.encoders import encode_7or8bit +from email.mime.nonmultipart import MIMENonMultipart diff --git a/Lib/email/Parser.py b/Lib/email/parser.py similarity index 94% rename from Lib/email/Parser.py rename to Lib/email/parser.py index 0c05224489e..2fcaf254562 100644 --- a/Lib/email/Parser.py +++ b/Lib/email/parser.py @@ -1,13 +1,16 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw, Thomas Wouters, Anthony Baxter # Contact: email-sig@python.org """A parser of RFC 2822 and MIME email messages.""" +__all__ = ['Parser', 'HeaderParser'] + import warnings from cStringIO import StringIO -from email.FeedParser import FeedParser -from email.Message import Message + +from email.feedparser import FeedParser +from email.message import Message diff --git a/Lib/email/quopriMIME.py b/Lib/email/quoprimime.py similarity index 96% rename from Lib/email/quopriMIME.py rename to Lib/email/quoprimime.py index a9b5d490ae7..a5658dd3f72 100644 --- a/Lib/email/quopriMIME.py +++ b/Lib/email/quoprimime.py @@ -1,4 +1,4 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Ben Gertzfield # Contact: email-sig@python.org @@ -26,9 +26,27 @@ does dumb encoding and decoding. To deal with the various line wrapping issues, use the email.Header module. """ +__all__ = [ + 'body_decode', + 'body_encode', + 'body_quopri_check', + 'body_quopri_len', + 'decode', + 'decodestring', + 'encode', + 'encodestring', + 'header_decode', + 'header_encode', + 'header_quopri_check', + 'header_quopri_len', + 'quote', + 'unquote', + ] + import re + from string import hexdigits -from email.Utils import fix_eols +from email.utils import fix_eols CRLF = '\r\n' NL = '\n' diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py index 5a42c2272d0..d35e7704600 100644 --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -39,9 +39,6 @@ NL = '\n' EMPTYSTRING = '' SPACE = ' ' -# We don't care about DeprecationWarnings -warnings.filterwarnings('ignore', '', DeprecationWarning, __name__) - def openfile(filename, mode='r'): @@ -87,7 +84,7 @@ class TestMessageAPI(TestEmailBase): charset = Charset('iso-8859-1') msg.set_charset(charset) eq(msg['mime-version'], '1.0') - eq(msg.get_type(), 'text/plain') + eq(msg.get_content_type(), 'text/plain') eq(msg['content-type'], 'text/plain; charset="iso-8859-1"') eq(msg.get_param('charset'), 'iso-8859-1') eq(msg['content-transfer-encoding'], 'quoted-printable') @@ -211,6 +208,19 @@ class TestMessageAPI(TestEmailBase): msg.set_payload('foo') eq(msg.get_payload(decode=True), 'foo') + def test_decode_bogus_uu_payload_quietly(self): + msg = Message() + msg.set_payload('begin 664 foo.txt\n%') @@ -1706,16 +1716,16 @@ Two fp.close() container1 = msg.get_payload(0) eq(container1.get_default_type(), 'message/rfc822') - eq(container1.get_type(), None) + eq(container1.get_content_type(), 'message/rfc822') container2 = msg.get_payload(1) eq(container2.get_default_type(), 'message/rfc822') - eq(container2.get_type(), None) + eq(container2.get_content_type(), 'message/rfc822') container1a = container1.get_payload(0) eq(container1a.get_default_type(), 'text/plain') - eq(container1a.get_type(), 'text/plain') + eq(container1a.get_content_type(), 'text/plain') container2a = container2.get_payload(0) eq(container2a.get_default_type(), 'text/plain') - eq(container2a.get_type(), 'text/plain') + eq(container2a.get_content_type(), 'text/plain') def test_default_type_with_explicit_container_type(self): eq = self.assertEqual @@ -1726,16 +1736,16 @@ Two fp.close() container1 = msg.get_payload(0) eq(container1.get_default_type(), 'message/rfc822') - eq(container1.get_type(), 'message/rfc822') + eq(container1.get_content_type(), 'message/rfc822') container2 = msg.get_payload(1) eq(container2.get_default_type(), 'message/rfc822') - eq(container2.get_type(), 'message/rfc822') + eq(container2.get_content_type(), 'message/rfc822') container1a = container1.get_payload(0) eq(container1a.get_default_type(), 'text/plain') - eq(container1a.get_type(), 'text/plain') + eq(container1a.get_content_type(), 'text/plain') container2a = container2.get_payload(0) eq(container2a.get_default_type(), 'text/plain') - eq(container2a.get_type(), 'text/plain') + eq(container2a.get_content_type(), 'text/plain') def test_default_type_non_parsed(self): eq = self.assertEqual @@ -1750,9 +1760,9 @@ Two subpart2 = MIMEMessage(subpart2a) container.attach(subpart1) container.attach(subpart2) - eq(subpart1.get_type(), 'message/rfc822') + eq(subpart1.get_content_type(), 'message/rfc822') eq(subpart1.get_default_type(), 'message/rfc822') - eq(subpart2.get_type(), 'message/rfc822') + eq(subpart2.get_content_type(), 'message/rfc822') eq(subpart2.get_default_type(), 'message/rfc822') neq(container.as_string(0), '''\ Content-Type: multipart/digest; boundary="BOUNDARY" @@ -1784,9 +1794,9 @@ message 2 del subpart1['mime-version'] del subpart2['content-type'] del subpart2['mime-version'] - eq(subpart1.get_type(), None) + eq(subpart1.get_content_type(), 'message/rfc822') eq(subpart1.get_default_type(), 'message/rfc822') - eq(subpart2.get_type(), None) + eq(subpart2.get_content_type(), 'message/rfc822') eq(subpart2.get_default_type(), 'message/rfc822') neq(container.as_string(0), '''\ Content-Type: multipart/digest; boundary="BOUNDARY" @@ -1847,7 +1857,7 @@ class TestIdempotent(TestEmailBase): def test_parse_text_message(self): eq = self.assertEquals msg, text = self._msgobj('msg_01.txt') - eq(msg.get_type(), 'text/plain') + eq(msg.get_content_type(), 'text/plain') eq(msg.get_content_maintype(), 'text') eq(msg.get_content_subtype(), 'plain') eq(msg.get_params()[1], ('charset', 'us-ascii')) @@ -1859,7 +1869,7 @@ class TestIdempotent(TestEmailBase): def test_parse_untyped_message(self): eq = self.assertEquals msg, text = self._msgobj('msg_03.txt') - eq(msg.get_type(), None) + eq(msg.get_content_type(), 'text/plain') eq(msg.get_params(), None) eq(msg.get_param('charset'), None) self._idempotent(msg, text) @@ -1933,7 +1943,7 @@ class TestIdempotent(TestEmailBase): unless = self.failUnless # Get a message object and reset the seek pointer for other tests msg, text = self._msgobj('msg_05.txt') - eq(msg.get_type(), 'multipart/report') + eq(msg.get_content_type(), 'multipart/report') # Test the Content-Type: parameters params = {} for pk, pv in msg.get_params(): @@ -1945,13 +1955,13 @@ class TestIdempotent(TestEmailBase): eq(len(msg.get_payload()), 3) # Make sure the subparts are what we expect msg1 = msg.get_payload(0) - eq(msg1.get_type(), 'text/plain') + eq(msg1.get_content_type(), 'text/plain') eq(msg1.get_payload(), 'Yadda yadda yadda\n') msg2 = msg.get_payload(1) - eq(msg2.get_type(), None) + eq(msg2.get_content_type(), 'text/plain') eq(msg2.get_payload(), 'Yadda yadda yadda\n') msg3 = msg.get_payload(2) - eq(msg3.get_type(), 'message/rfc822') + eq(msg3.get_content_type(), 'message/rfc822') self.failUnless(isinstance(msg3, Message)) payload = msg3.get_payload() unless(isinstance(payload, list)) @@ -1965,7 +1975,7 @@ class TestIdempotent(TestEmailBase): unless = self.failUnless msg, text = self._msgobj('msg_06.txt') # Check some of the outer headers - eq(msg.get_type(), 'message/rfc822') + eq(msg.get_content_type(), 'message/rfc822') # Make sure the payload is a list of exactly one sub-Message, and that # that submessage has a type of text/plain payload = msg.get_payload() @@ -1973,7 +1983,7 @@ class TestIdempotent(TestEmailBase): eq(len(payload), 1) msg1 = payload[0] self.failUnless(isinstance(msg1, Message)) - eq(msg1.get_type(), 'text/plain') + eq(msg1.get_content_type(), 'text/plain') self.failUnless(isinstance(msg1.get_payload(), str)) eq(msg1.get_payload(), '\n') @@ -2058,13 +2068,19 @@ class TestMiscellaneous(TestEmailBase): module = __import__('email') all = module.__all__ all.sort() - self.assertEqual(all, ['Charset', 'Encoders', 'Errors', 'Generator', - 'Header', 'Iterators', 'MIMEAudio', 'MIMEBase', - 'MIMEImage', 'MIMEMessage', 'MIMEMultipart', - 'MIMENonMultipart', 'MIMEText', 'Message', - 'Parser', 'Utils', 'base64MIME', - 'message_from_file', 'message_from_string', - 'quopriMIME']) + self.assertEqual(all, [ + # Old names + 'Charset', 'Encoders', 'Errors', 'Generator', + 'Header', 'Iterators', 'MIMEAudio', 'MIMEBase', + 'MIMEImage', 'MIMEMessage', 'MIMEMultipart', + 'MIMENonMultipart', 'MIMEText', 'Message', + 'Parser', 'Utils', 'base64MIME', + # new names + 'base64mime', 'charset', 'encoders', 'errors', 'generator', + 'header', 'iterators', 'message', 'message_from_file', + 'message_from_string', 'mime', 'parser', + 'quopriMIME', 'quoprimime', 'utils', + ]) def test_formatdate(self): now = time.time() @@ -2356,7 +2372,7 @@ class TestParsers(TestEmailBase): fp.close() eq(msg['from'], 'ppp-request@zzz.org') eq(msg['to'], 'ppp@zzz.org') - eq(msg.get_type(), 'multipart/mixed') + eq(msg.get_content_type(), 'multipart/mixed') self.failIf(msg.is_multipart()) self.failUnless(isinstance(msg.get_payload(), str)) @@ -2405,10 +2421,10 @@ Here's the message body fp.close() eq(len(msg.get_payload()), 2) part1 = msg.get_payload(0) - eq(part1.get_type(), 'text/plain') + eq(part1.get_content_type(), 'text/plain') eq(part1.get_payload(), 'Simple email with attachment.\r\n\r\n') part2 = msg.get_payload(1) - eq(part2.get_type(), 'application/riscos') + eq(part2.get_content_type(), 'application/riscos') def test_multipart_digest_with_extra_mime_headers(self): eq = self.assertEqual @@ -2427,21 +2443,21 @@ Here's the message body eq(msg.is_multipart(), 1) eq(len(msg.get_payload()), 2) part1 = msg.get_payload(0) - eq(part1.get_type(), 'message/rfc822') + eq(part1.get_content_type(), 'message/rfc822') eq(part1.is_multipart(), 1) eq(len(part1.get_payload()), 1) part1a = part1.get_payload(0) eq(part1a.is_multipart(), 0) - eq(part1a.get_type(), 'text/plain') + eq(part1a.get_content_type(), 'text/plain') neq(part1a.get_payload(), 'message 1\n') # next message/rfc822 part2 = msg.get_payload(1) - eq(part2.get_type(), 'message/rfc822') + eq(part2.get_content_type(), 'message/rfc822') eq(part2.is_multipart(), 1) eq(len(part2.get_payload()), 1) part2a = part2.get_payload(0) eq(part2a.is_multipart(), 0) - eq(part2a.get_type(), 'text/plain') + eq(part2a.get_content_type(), 'text/plain') neq(part2a.get_payload(), 'message 2\n') def test_three_lines(self): @@ -2723,6 +2739,11 @@ class TestCharset(unittest.TestCase): c = Charset('fake') eq('hello w\xf6rld', c.body_encode('hello w\xf6rld')) + def test_unicode_charset_name(self): + charset = Charset(u'us-ascii') + self.assertEqual(str(charset), 'us-ascii') + self.assertRaises(Errors.CharsetError, Charset, 'asc\xffii') + # Test multilingual MIME headers. diff --git a/Lib/email/test/test_email_codecs.py b/Lib/email/test/test_email_codecs.py index 159989c9e2c..38b7d953925 100644 --- a/Lib/email/test/test_email_codecs.py +++ b/Lib/email/test/test_email_codecs.py @@ -10,6 +10,13 @@ from email.Charset import Charset from email.Header import Header, decode_header from email.Message import Message +# We're compatible with Python 2.3, but it doesn't have the built-in Asian +# codecs, so we have to skip all these tests. +try: + unicode('foo', 'euc-jp') +except LookupError: + raise TestSkipped + class TestEmailAsianCodecs(TestEmailBase): diff --git a/Lib/email/test/test_email_codecs_renamed.py b/Lib/email/test/test_email_codecs_renamed.py new file mode 100644 index 00000000000..56baccdca1b --- /dev/null +++ b/Lib/email/test/test_email_codecs_renamed.py @@ -0,0 +1,77 @@ +# Copyright (C) 2002-2006 Python Software Foundation +# Contact: email-sig@python.org +# email package unit tests for (optional) Asian codecs + +import unittest +from test.test_support import TestSkipped, run_unittest + +from email.test.test_email import TestEmailBase +from email.charset import Charset +from email.header import Header, decode_header +from email.message import Message + +# We're compatible with Python 2.3, but it doesn't have the built-in Asian +# codecs, so we have to skip all these tests. +try: + unicode('foo', 'euc-jp') +except LookupError: + raise TestSkipped + + + +class TestEmailAsianCodecs(TestEmailBase): + def test_japanese_codecs(self): + eq = self.ndiffAssertEqual + j = Charset("euc-jp") + g = Charset("iso-8859-1") + h = Header("Hello World!") + jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa' + ghello = 'Gr\xfc\xdf Gott!' + h.append(jhello, j) + h.append(ghello, g) + # BAW: This used to -- and maybe should -- fold the two iso-8859-1 + # chunks into a single encoded word. However it doesn't violate the + # standard to have them as two encoded chunks and maybe it's + # reasonable for each .append() call to result in a separate + # encoded word. + eq(h.encode(), """\ +Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?= + =?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""") + eq(decode_header(h.encode()), + [('Hello World!', None), + ('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'), + ('Gr\xfc\xdf Gott!', 'iso-8859-1')]) + long = 'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9' + h = Header(long, j, header_name="Subject") + # test a very long header + enc = h.encode() + # TK: splitting point may differ by codec design and/or Header encoding + eq(enc , """\ +=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?= + =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""") + # TK: full decode comparison + eq(h.__unicode__().encode('euc-jp'), long) + + def test_payload_encoding(self): + jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa' + jcode = 'euc-jp' + msg = Message() + msg.set_payload(jhello, jcode) + ustr = unicode(msg.get_payload(), msg.get_content_charset()) + self.assertEqual(jhello, ustr.encode(jcode)) + + + +def suite(): + suite = unittest.TestSuite() + suite.addTest(unittest.makeSuite(TestEmailAsianCodecs)) + return suite + + +def test_main(): + run_unittest(TestEmailAsianCodecs) + + + +if __name__ == '__main__': + unittest.main(defaultTest='suite') diff --git a/Lib/email/test/test_email_renamed.py b/Lib/email/test/test_email_renamed.py new file mode 100644 index 00000000000..ed186a09dda --- /dev/null +++ b/Lib/email/test/test_email_renamed.py @@ -0,0 +1,3078 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Contact: email-sig@python.org +# email package unit tests + +import os +import sys +import time +import base64 +import difflib +import unittest +import warnings +from cStringIO import StringIO + +import email + +from email.charset import Charset +from email.header import Header, decode_header, make_header +from email.parser import Parser, HeaderParser +from email.generator import Generator, DecodedGenerator +from email.message import Message +from email.mime.application import MIMEApplication +from email.mime.audio import MIMEAudio +from email.mime.text import MIMEText +from email.mime.image import MIMEImage +from email.mime.base import MIMEBase +from email.mime.message import MIMEMessage +from email.mime.multipart import MIMEMultipart +from email import utils +from email import errors +from email import encoders +from email import iterators +from email import base64mime +from email import quoprimime + +from test.test_support import findfile, run_unittest +from email.test import __file__ as landmark + + +NL = '\n' +EMPTYSTRING = '' +SPACE = ' ' + + + +def openfile(filename, mode='r'): + path = os.path.join(os.path.dirname(landmark), 'data', filename) + return open(path, mode) + + + +# Base test class +class TestEmailBase(unittest.TestCase): + def ndiffAssertEqual(self, first, second): + """Like failUnlessEqual except use ndiff for readable output.""" + if first <> second: + sfirst = str(first) + ssecond = str(second) + diff = difflib.ndiff(sfirst.splitlines(), ssecond.splitlines()) + fp = StringIO() + print >> fp, NL, NL.join(diff) + raise self.failureException, fp.getvalue() + + def _msgobj(self, filename): + fp = openfile(findfile(filename)) + try: + msg = email.message_from_file(fp) + finally: + fp.close() + return msg + + + +# Test various aspects of the Message class's API +class TestMessageAPI(TestEmailBase): + def test_get_all(self): + eq = self.assertEqual + msg = self._msgobj('msg_20.txt') + eq(msg.get_all('cc'), ['ccc@zzz.org', 'ddd@zzz.org', 'eee@zzz.org']) + eq(msg.get_all('xx', 'n/a'), 'n/a') + + def test_getset_charset(self): + eq = self.assertEqual + msg = Message() + eq(msg.get_charset(), None) + charset = Charset('iso-8859-1') + msg.set_charset(charset) + eq(msg['mime-version'], '1.0') + eq(msg.get_content_type(), 'text/plain') + eq(msg['content-type'], 'text/plain; charset="iso-8859-1"') + eq(msg.get_param('charset'), 'iso-8859-1') + eq(msg['content-transfer-encoding'], 'quoted-printable') + eq(msg.get_charset().input_charset, 'iso-8859-1') + # Remove the charset + msg.set_charset(None) + eq(msg.get_charset(), None) + eq(msg['content-type'], 'text/plain') + # Try adding a charset when there's already MIME headers present + msg = Message() + msg['MIME-Version'] = '2.0' + msg['Content-Type'] = 'text/x-weird' + msg['Content-Transfer-Encoding'] = 'quinted-puntable' + msg.set_charset(charset) + eq(msg['mime-version'], '2.0') + eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"') + eq(msg['content-transfer-encoding'], 'quinted-puntable') + + def test_set_charset_from_string(self): + eq = self.assertEqual + msg = Message() + msg.set_charset('us-ascii') + eq(msg.get_charset().input_charset, 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + + def test_set_payload_with_charset(self): + msg = Message() + charset = Charset('iso-8859-1') + msg.set_payload('This is a string payload', charset) + self.assertEqual(msg.get_charset().input_charset, 'iso-8859-1') + + def test_get_charsets(self): + eq = self.assertEqual + + msg = self._msgobj('msg_08.txt') + charsets = msg.get_charsets() + eq(charsets, [None, 'us-ascii', 'iso-8859-1', 'iso-8859-2', 'koi8-r']) + + msg = self._msgobj('msg_09.txt') + charsets = msg.get_charsets('dingbat') + eq(charsets, ['dingbat', 'us-ascii', 'iso-8859-1', 'dingbat', + 'koi8-r']) + + msg = self._msgobj('msg_12.txt') + charsets = msg.get_charsets() + eq(charsets, [None, 'us-ascii', 'iso-8859-1', None, 'iso-8859-2', + 'iso-8859-3', 'us-ascii', 'koi8-r']) + + def test_get_filename(self): + eq = self.assertEqual + + msg = self._msgobj('msg_04.txt') + filenames = [p.get_filename() for p in msg.get_payload()] + eq(filenames, ['msg.txt', 'msg.txt']) + + msg = self._msgobj('msg_07.txt') + subpart = msg.get_payload(1) + eq(subpart.get_filename(), 'dingusfish.gif') + + def test_get_filename_with_name_parameter(self): + eq = self.assertEqual + + msg = self._msgobj('msg_44.txt') + filenames = [p.get_filename() for p in msg.get_payload()] + eq(filenames, ['msg.txt', 'msg.txt']) + + def test_get_boundary(self): + eq = self.assertEqual + msg = self._msgobj('msg_07.txt') + # No quotes! + eq(msg.get_boundary(), 'BOUNDARY') + + def test_set_boundary(self): + eq = self.assertEqual + # This one has no existing boundary parameter, but the Content-Type: + # header appears fifth. + msg = self._msgobj('msg_01.txt') + msg.set_boundary('BOUNDARY') + header, value = msg.items()[4] + eq(header.lower(), 'content-type') + eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"') + # This one has a Content-Type: header, with a boundary, stuck in the + # middle of its headers. Make sure the order is preserved; it should + # be fifth. + msg = self._msgobj('msg_04.txt') + msg.set_boundary('BOUNDARY') + header, value = msg.items()[4] + eq(header.lower(), 'content-type') + eq(value, 'multipart/mixed; boundary="BOUNDARY"') + # And this one has no Content-Type: header at all. + msg = self._msgobj('msg_03.txt') + self.assertRaises(errors.HeaderParseError, + msg.set_boundary, 'BOUNDARY') + + def test_get_decoded_payload(self): + eq = self.assertEqual + msg = self._msgobj('msg_10.txt') + # The outer message is a multipart + eq(msg.get_payload(decode=True), None) + # Subpart 1 is 7bit encoded + eq(msg.get_payload(0).get_payload(decode=True), + 'This is a 7bit encoded message.\n') + # Subpart 2 is quopri + eq(msg.get_payload(1).get_payload(decode=True), + '\xa1This is a Quoted Printable encoded message!\n') + # Subpart 3 is base64 + eq(msg.get_payload(2).get_payload(decode=True), + 'This is a Base64 encoded message.') + # Subpart 4 has no Content-Transfer-Encoding: header. + eq(msg.get_payload(3).get_payload(decode=True), + 'This has no Content-Transfer-Encoding: header.\n') + + def test_get_decoded_uu_payload(self): + eq = self.assertEqual + msg = Message() + msg.set_payload('begin 666 -\n+:&5L;&\\@=V]R;&0 \n \nend\n') + for cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'): + msg['content-transfer-encoding'] = cte + eq(msg.get_payload(decode=True), 'hello world') + # Now try some bogus data + msg.set_payload('foo') + eq(msg.get_payload(decode=True), 'foo') + + def test_decoded_generator(self): + eq = self.assertEqual + msg = self._msgobj('msg_07.txt') + fp = openfile('msg_17.txt') + try: + text = fp.read() + finally: + fp.close() + s = StringIO() + g = DecodedGenerator(s) + g.flatten(msg) + eq(s.getvalue(), text) + + def test__contains__(self): + msg = Message() + msg['From'] = 'Me' + msg['to'] = 'You' + # Check for case insensitivity + self.failUnless('from' in msg) + self.failUnless('From' in msg) + self.failUnless('FROM' in msg) + self.failUnless('to' in msg) + self.failUnless('To' in msg) + self.failUnless('TO' in msg) + + def test_as_string(self): + eq = self.assertEqual + msg = self._msgobj('msg_01.txt') + fp = openfile('msg_01.txt') + try: + text = fp.read() + finally: + fp.close() + eq(text, msg.as_string()) + fullrepr = str(msg) + lines = fullrepr.split('\n') + self.failUnless(lines[0].startswith('From ')) + eq(text, NL.join(lines[1:])) + + def test_bad_param(self): + msg = email.message_from_string("Content-Type: blarg; baz; boo\n") + self.assertEqual(msg.get_param('baz'), '') + + def test_missing_filename(self): + msg = email.message_from_string("From: foo\n") + self.assertEqual(msg.get_filename(), None) + + def test_bogus_filename(self): + msg = email.message_from_string( + "Content-Disposition: blarg; filename\n") + self.assertEqual(msg.get_filename(), '') + + def test_missing_boundary(self): + msg = email.message_from_string("From: foo\n") + self.assertEqual(msg.get_boundary(), None) + + def test_get_params(self): + eq = self.assertEqual + msg = email.message_from_string( + 'X-Header: foo=one; bar=two; baz=three\n') + eq(msg.get_params(header='x-header'), + [('foo', 'one'), ('bar', 'two'), ('baz', 'three')]) + msg = email.message_from_string( + 'X-Header: foo; bar=one; baz=two\n') + eq(msg.get_params(header='x-header'), + [('foo', ''), ('bar', 'one'), ('baz', 'two')]) + eq(msg.get_params(), None) + msg = email.message_from_string( + 'X-Header: foo; bar="one"; baz=two\n') + eq(msg.get_params(header='x-header'), + [('foo', ''), ('bar', 'one'), ('baz', 'two')]) + + def test_get_param_liberal(self): + msg = Message() + msg['Content-Type'] = 'Content-Type: Multipart/mixed; boundary = "CPIMSSMTPC06p5f3tG"' + self.assertEqual(msg.get_param('boundary'), 'CPIMSSMTPC06p5f3tG') + + def test_get_param(self): + eq = self.assertEqual + msg = email.message_from_string( + "X-Header: foo=one; bar=two; baz=three\n") + eq(msg.get_param('bar', header='x-header'), 'two') + eq(msg.get_param('quuz', header='x-header'), None) + eq(msg.get_param('quuz'), None) + msg = email.message_from_string( + 'X-Header: foo; bar="one"; baz=two\n') + eq(msg.get_param('foo', header='x-header'), '') + eq(msg.get_param('bar', header='x-header'), 'one') + eq(msg.get_param('baz', header='x-header'), 'two') + # XXX: We are not RFC-2045 compliant! We cannot parse: + # msg["Content-Type"] = 'text/plain; weird="hey; dolly? [you] @ <\\"home\\">?"' + # msg.get_param("weird") + # yet. + + def test_get_param_funky_continuation_lines(self): + msg = self._msgobj('msg_22.txt') + self.assertEqual(msg.get_payload(1).get_param('name'), 'wibble.JPG') + + def test_get_param_with_semis_in_quotes(self): + msg = email.message_from_string( + 'Content-Type: image/pjpeg; name="Jim&&Jill"\n') + self.assertEqual(msg.get_param('name'), 'Jim&&Jill') + self.assertEqual(msg.get_param('name', unquote=False), + '"Jim&&Jill"') + + def test_has_key(self): + msg = email.message_from_string('Header: exists') + self.failUnless(msg.has_key('header')) + self.failUnless(msg.has_key('Header')) + self.failUnless(msg.has_key('HEADER')) + self.failIf(msg.has_key('headeri')) + + def test_set_param(self): + eq = self.assertEqual + msg = Message() + msg.set_param('charset', 'iso-2022-jp') + eq(msg.get_param('charset'), 'iso-2022-jp') + msg.set_param('importance', 'high value') + eq(msg.get_param('importance'), 'high value') + eq(msg.get_param('importance', unquote=False), '"high value"') + eq(msg.get_params(), [('text/plain', ''), + ('charset', 'iso-2022-jp'), + ('importance', 'high value')]) + eq(msg.get_params(unquote=False), [('text/plain', ''), + ('charset', '"iso-2022-jp"'), + ('importance', '"high value"')]) + msg.set_param('charset', 'iso-9999-xx', header='X-Jimmy') + eq(msg.get_param('charset', header='X-Jimmy'), 'iso-9999-xx') + + def test_del_param(self): + eq = self.assertEqual + msg = self._msgobj('msg_05.txt') + eq(msg.get_params(), + [('multipart/report', ''), ('report-type', 'delivery-status'), + ('boundary', 'D1690A7AC1.996856090/mail.example.com')]) + old_val = msg.get_param("report-type") + msg.del_param("report-type") + eq(msg.get_params(), + [('multipart/report', ''), + ('boundary', 'D1690A7AC1.996856090/mail.example.com')]) + msg.set_param("report-type", old_val) + eq(msg.get_params(), + [('multipart/report', ''), + ('boundary', 'D1690A7AC1.996856090/mail.example.com'), + ('report-type', old_val)]) + + def test_del_param_on_other_header(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', filename='bud.gif') + msg.del_param('filename', 'content-disposition') + self.assertEqual(msg['content-disposition'], 'attachment') + + def test_set_type(self): + eq = self.assertEqual + msg = Message() + self.assertRaises(ValueError, msg.set_type, 'text') + msg.set_type('text/plain') + eq(msg['content-type'], 'text/plain') + msg.set_param('charset', 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + msg.set_type('text/html') + eq(msg['content-type'], 'text/html; charset="us-ascii"') + + def test_set_type_on_other_header(self): + msg = Message() + msg['X-Content-Type'] = 'text/plain' + msg.set_type('application/octet-stream', 'X-Content-Type') + self.assertEqual(msg['x-content-type'], 'application/octet-stream') + + def test_get_content_type_missing(self): + msg = Message() + self.assertEqual(msg.get_content_type(), 'text/plain') + + def test_get_content_type_missing_with_default_type(self): + msg = Message() + msg.set_default_type('message/rfc822') + self.assertEqual(msg.get_content_type(), 'message/rfc822') + + def test_get_content_type_from_message_implicit(self): + msg = self._msgobj('msg_30.txt') + self.assertEqual(msg.get_payload(0).get_content_type(), + 'message/rfc822') + + def test_get_content_type_from_message_explicit(self): + msg = self._msgobj('msg_28.txt') + self.assertEqual(msg.get_payload(0).get_content_type(), + 'message/rfc822') + + def test_get_content_type_from_message_text_plain_implicit(self): + msg = self._msgobj('msg_03.txt') + self.assertEqual(msg.get_content_type(), 'text/plain') + + def test_get_content_type_from_message_text_plain_explicit(self): + msg = self._msgobj('msg_01.txt') + self.assertEqual(msg.get_content_type(), 'text/plain') + + def test_get_content_maintype_missing(self): + msg = Message() + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_maintype_missing_with_default_type(self): + msg = Message() + msg.set_default_type('message/rfc822') + self.assertEqual(msg.get_content_maintype(), 'message') + + def test_get_content_maintype_from_message_implicit(self): + msg = self._msgobj('msg_30.txt') + self.assertEqual(msg.get_payload(0).get_content_maintype(), 'message') + + def test_get_content_maintype_from_message_explicit(self): + msg = self._msgobj('msg_28.txt') + self.assertEqual(msg.get_payload(0).get_content_maintype(), 'message') + + def test_get_content_maintype_from_message_text_plain_implicit(self): + msg = self._msgobj('msg_03.txt') + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_maintype_from_message_text_plain_explicit(self): + msg = self._msgobj('msg_01.txt') + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_subtype_missing(self): + msg = Message() + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_get_content_subtype_missing_with_default_type(self): + msg = Message() + msg.set_default_type('message/rfc822') + self.assertEqual(msg.get_content_subtype(), 'rfc822') + + def test_get_content_subtype_from_message_implicit(self): + msg = self._msgobj('msg_30.txt') + self.assertEqual(msg.get_payload(0).get_content_subtype(), 'rfc822') + + def test_get_content_subtype_from_message_explicit(self): + msg = self._msgobj('msg_28.txt') + self.assertEqual(msg.get_payload(0).get_content_subtype(), 'rfc822') + + def test_get_content_subtype_from_message_text_plain_implicit(self): + msg = self._msgobj('msg_03.txt') + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_get_content_subtype_from_message_text_plain_explicit(self): + msg = self._msgobj('msg_01.txt') + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_get_content_maintype_error(self): + msg = Message() + msg['Content-Type'] = 'no-slash-in-this-string' + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_subtype_error(self): + msg = Message() + msg['Content-Type'] = 'no-slash-in-this-string' + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_replace_header(self): + eq = self.assertEqual + msg = Message() + msg.add_header('First', 'One') + msg.add_header('Second', 'Two') + msg.add_header('Third', 'Three') + eq(msg.keys(), ['First', 'Second', 'Third']) + eq(msg.values(), ['One', 'Two', 'Three']) + msg.replace_header('Second', 'Twenty') + eq(msg.keys(), ['First', 'Second', 'Third']) + eq(msg.values(), ['One', 'Twenty', 'Three']) + msg.add_header('First', 'Eleven') + msg.replace_header('First', 'One Hundred') + eq(msg.keys(), ['First', 'Second', 'Third', 'First']) + eq(msg.values(), ['One Hundred', 'Twenty', 'Three', 'Eleven']) + self.assertRaises(KeyError, msg.replace_header, 'Fourth', 'Missing') + + def test_broken_base64_payload(self): + x = 'AwDp0P7//y6LwKEAcPa/6Q=9' + msg = Message() + msg['content-type'] = 'audio/x-midi' + msg['content-transfer-encoding'] = 'base64' + msg.set_payload(x) + self.assertEqual(msg.get_payload(decode=True), x) + + + +# Test the email.encoders module +class TestEncoders(unittest.TestCase): + def test_encode_empty_payload(self): + eq = self.assertEqual + msg = Message() + msg.set_charset('us-ascii') + eq(msg['content-transfer-encoding'], '7bit') + + def test_default_cte(self): + eq = self.assertEqual + msg = MIMEText('hello world') + eq(msg['content-transfer-encoding'], '7bit') + + def test_default_cte(self): + eq = self.assertEqual + # With no explicit _charset its us-ascii, and all are 7-bit + msg = MIMEText('hello world') + eq(msg['content-transfer-encoding'], '7bit') + # Similar, but with 8-bit data + msg = MIMEText('hello \xf8 world') + eq(msg['content-transfer-encoding'], '8bit') + # And now with a different charset + msg = MIMEText('hello \xf8 world', _charset='iso-8859-1') + eq(msg['content-transfer-encoding'], 'quoted-printable') + + + +# Test long header wrapping +class TestLongHeaders(TestEmailBase): + def test_split_long_continuation(self): + eq = self.ndiffAssertEqual + msg = email.message_from_string("""\ +Subject: bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text + +test +""") + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), """\ +Subject: bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text + +test +""") + + def test_another_long_almost_unsplittable_header(self): + eq = self.ndiffAssertEqual + hstr = """\ +bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text""" + h = Header(hstr, continuation_ws='\t') + eq(h.encode(), """\ +bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text""") + h = Header(hstr) + eq(h.encode(), """\ +bug demonstration + 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 + more text""") + + def test_long_nonstring(self): + eq = self.ndiffAssertEqual + g = Charset("iso-8859-1") + cz = Charset("iso-8859-2") + utf8 = Charset("utf-8") + g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. " + cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. " + utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8") + h = Header(g_head, g, header_name='Subject') + h.append(cz_head, cz) + h.append(utf8_head, utf8) + msg = Message() + msg['Subject'] = h + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), """\ +Subject: =?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerd?= + =?iso-8859-1?q?erband_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndi?= + =?iso-8859-1?q?schen_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Kling?= + =?iso-8859-1?q?en_bef=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_met?= + =?iso-8859-2?q?ropole_se_hroutily_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= + =?utf-8?b?5q2j56K644Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE?= + =?utf-8?b?44G+44Gb44KT44CC5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB?= + =?utf-8?b?44GC44Go44Gv44Gn44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CM?= + =?utf-8?q?Wenn_ist_das_Nunstuck_git_und_Slotermeyer=3F_Ja!_Beiherhund_das?= + =?utf-8?b?IE9kZXIgZGllIEZsaXBwZXJ3YWxkdCBnZXJzcHV0LuOAjeOBqOiogOOBow==?= + =?utf-8?b?44Gm44GE44G+44GZ44CC?= + +""") + eq(h.encode(), """\ +=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerd?= + =?iso-8859-1?q?erband_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndi?= + =?iso-8859-1?q?schen_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Kling?= + =?iso-8859-1?q?en_bef=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_met?= + =?iso-8859-2?q?ropole_se_hroutily_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= + =?utf-8?b?5q2j56K644Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE?= + =?utf-8?b?44G+44Gb44KT44CC5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB?= + =?utf-8?b?44GC44Go44Gv44Gn44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CM?= + =?utf-8?q?Wenn_ist_das_Nunstuck_git_und_Slotermeyer=3F_Ja!_Beiherhund_das?= + =?utf-8?b?IE9kZXIgZGllIEZsaXBwZXJ3YWxkdCBnZXJzcHV0LuOAjeOBqOiogOOBow==?= + =?utf-8?b?44Gm44GE44G+44GZ44CC?=""") + + def test_long_header_encode(self): + eq = self.ndiffAssertEqual + h = Header('wasnipoop; giraffes="very-long-necked-animals"; ' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"', + header_name='X-Foobar-Spoink-Defrobnit') + eq(h.encode(), '''\ +wasnipoop; giraffes="very-long-necked-animals"; + spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''') + + def test_long_header_encode_with_tab_continuation(self): + eq = self.ndiffAssertEqual + h = Header('wasnipoop; giraffes="very-long-necked-animals"; ' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"', + header_name='X-Foobar-Spoink-Defrobnit', + continuation_ws='\t') + eq(h.encode(), '''\ +wasnipoop; giraffes="very-long-necked-animals"; +\tspooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''') + + def test_header_splitter(self): + eq = self.ndiffAssertEqual + msg = MIMEText('') + # It'd be great if we could use add_header() here, but that doesn't + # guarantee an order of the parameters. + msg['X-Foobar-Spoink-Defrobnit'] = ( + 'wasnipoop; giraffes="very-long-necked-animals"; ' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"') + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), '''\ +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +X-Foobar-Spoink-Defrobnit: wasnipoop; giraffes="very-long-necked-animals"; +\tspooge="yummy"; hippos="gargantuan"; marshmallows="gooey" + +''') + + def test_no_semis_header_splitter(self): + eq = self.ndiffAssertEqual + msg = Message() + msg['From'] = 'test@dom.ain' + msg['References'] = SPACE.join(['<%d@dom.ain>' % i for i in range(10)]) + msg.set_payload('Test') + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), """\ +From: test@dom.ain +References: <0@dom.ain> <1@dom.ain> <2@dom.ain> <3@dom.ain> <4@dom.ain> +\t<5@dom.ain> <6@dom.ain> <7@dom.ain> <8@dom.ain> <9@dom.ain> + +Test""") + + def test_no_split_long_header(self): + eq = self.ndiffAssertEqual + hstr = 'References: ' + 'x' * 80 + h = Header(hstr, continuation_ws='\t') + eq(h.encode(), """\ +References: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx""") + + def test_splitting_multiple_long_lines(self): + eq = self.ndiffAssertEqual + hstr = """\ +from babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for ; Sat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for ; Sat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for ; Sat, 2 Feb 2002 17:00:06 -0800 (PST) +""" + h = Header(hstr, continuation_ws='\t') + eq(h.encode(), """\ +from babylon.socal-raves.org (localhost [127.0.0.1]); +\tby babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; +\tfor ; +\tSat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); +\tby babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; +\tfor ; +\tSat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); +\tby babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; +\tfor ; +\tSat, 2 Feb 2002 17:00:06 -0800 (PST)""") + + def test_splitting_first_line_only_is_long(self): + eq = self.ndiffAssertEqual + hstr = """\ +from modemcable093.139-201-24.que.mc.videotron.ca ([24.201.139.93] helo=cthulhu.gerg.ca) +\tby kronos.mems-exchange.org with esmtp (Exim 4.05) +\tid 17k4h5-00034i-00 +\tfor test@mems-exchange.org; Wed, 28 Aug 2002 11:25:20 -0400""" + h = Header(hstr, maxlinelen=78, header_name='Received', + continuation_ws='\t') + eq(h.encode(), """\ +from modemcable093.139-201-24.que.mc.videotron.ca ([24.201.139.93] +\thelo=cthulhu.gerg.ca) +\tby kronos.mems-exchange.org with esmtp (Exim 4.05) +\tid 17k4h5-00034i-00 +\tfor test@mems-exchange.org; Wed, 28 Aug 2002 11:25:20 -0400""") + + def test_long_8bit_header(self): + eq = self.ndiffAssertEqual + msg = Message() + h = Header('Britische Regierung gibt', 'iso-8859-1', + header_name='Subject') + h.append('gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte') + msg['Subject'] = h + eq(msg.as_string(), """\ +Subject: =?iso-8859-1?q?Britische_Regierung_gibt?= =?iso-8859-1?q?gr=FCnes?= + =?iso-8859-1?q?_Licht_f=FCr_Offshore-Windkraftprojekte?= + +""") + + def test_long_8bit_header_no_charset(self): + eq = self.ndiffAssertEqual + msg = Message() + msg['Reply-To'] = 'Britische Regierung gibt gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte ' + eq(msg.as_string(), """\ +Reply-To: Britische Regierung gibt gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte + +""") + + def test_long_to_header(self): + eq = self.ndiffAssertEqual + to = '"Someone Test #A" ,,"Someone Test #B" , "Someone Test #C" , "Someone Test #D" ' + msg = Message() + msg['To'] = to + eq(msg.as_string(0), '''\ +To: "Someone Test #A" , , +\t"Someone Test #B" , +\t"Someone Test #C" , +\t"Someone Test #D" + +''') + + def test_long_line_after_append(self): + eq = self.ndiffAssertEqual + s = 'This is an example of string which has almost the limit of header length.' + h = Header(s) + h.append('Add another line.') + eq(h.encode(), """\ +This is an example of string which has almost the limit of header length. + Add another line.""") + + def test_shorter_line_with_append(self): + eq = self.ndiffAssertEqual + s = 'This is a shorter line.' + h = Header(s) + h.append('Add another sentence. (Surprise?)') + eq(h.encode(), + 'This is a shorter line. Add another sentence. (Surprise?)') + + def test_long_field_name(self): + eq = self.ndiffAssertEqual + fn = 'X-Very-Very-Very-Long-Header-Name' + gs = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. " + h = Header(gs, 'iso-8859-1', header_name=fn) + # BAW: this seems broken because the first line is too long + eq(h.encode(), """\ +=?iso-8859-1?q?Die_Mieter_treten_hier_?= + =?iso-8859-1?q?ein_werden_mit_einem_Foerderband_komfortabel_den_Korridor_?= + =?iso-8859-1?q?entlang=2C_an_s=FCdl=FCndischen_Wandgem=E4lden_vorbei=2C_g?= + =?iso-8859-1?q?egen_die_rotierenden_Klingen_bef=F6rdert=2E_?=""") + + def test_long_received_header(self): + h = 'from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP; Wed, 05 Mar 2003 18:10:18 -0700' + msg = Message() + msg['Received-1'] = Header(h, continuation_ws='\t') + msg['Received-2'] = h + self.assertEqual(msg.as_string(), """\ +Received-1: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by +\throthgar.la.mastaler.com (tmda-ofmipd) with ESMTP; +\tWed, 05 Mar 2003 18:10:18 -0700 +Received-2: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by +\throthgar.la.mastaler.com (tmda-ofmipd) with ESMTP; +\tWed, 05 Mar 2003 18:10:18 -0700 + +""") + + def test_string_headerinst_eq(self): + h = '<15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> (David Bremner\'s message of "Thu, 6 Mar 2003 13:58:21 +0100")' + msg = Message() + msg['Received-1'] = Header(h, header_name='Received-1', + continuation_ws='\t') + msg['Received-2'] = h + self.assertEqual(msg.as_string(), """\ +Received-1: <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> +\t(David Bremner's message of "Thu, 6 Mar 2003 13:58:21 +0100") +Received-2: <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> +\t(David Bremner's message of "Thu, 6 Mar 2003 13:58:21 +0100") + +""") + + def test_long_unbreakable_lines_with_continuation(self): + eq = self.ndiffAssertEqual + msg = Message() + t = """\ + iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 + locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp""" + msg['Face-1'] = t + msg['Face-2'] = Header(t, header_name='Face-2') + eq(msg.as_string(), """\ +Face-1: iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 +\tlocQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp +Face-2: iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 + locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp + +""") + + def test_another_long_multiline_header(self): + eq = self.ndiffAssertEqual + m = '''\ +Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with Microsoft SMTPSVC(5.0.2195.4905); +\tWed, 16 Oct 2002 07:41:11 -0700''' + msg = email.message_from_string(m) + eq(msg.as_string(), '''\ +Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with +\tMicrosoft SMTPSVC(5.0.2195.4905); Wed, 16 Oct 2002 07:41:11 -0700 + +''') + + def test_long_lines_with_different_header(self): + eq = self.ndiffAssertEqual + h = """\ +List-Unsubscribe: , + """ + msg = Message() + msg['List'] = h + msg['List'] = Header(h, header_name='List') + eq(msg.as_string(), """\ +List: List-Unsubscribe: , +\t +List: List-Unsubscribe: , + + +""") + + + +# Test mangling of "From " lines in the body of a message +class TestFromMangling(unittest.TestCase): + def setUp(self): + self.msg = Message() + self.msg['From'] = 'aaa@bbb.org' + self.msg.set_payload("""\ +From the desk of A.A.A.: +Blah blah blah +""") + + def test_mangled_from(self): + s = StringIO() + g = Generator(s, mangle_from_=True) + g.flatten(self.msg) + self.assertEqual(s.getvalue(), """\ +From: aaa@bbb.org + +>From the desk of A.A.A.: +Blah blah blah +""") + + def test_dont_mangle_from(self): + s = StringIO() + g = Generator(s, mangle_from_=False) + g.flatten(self.msg) + self.assertEqual(s.getvalue(), """\ +From: aaa@bbb.org + +From the desk of A.A.A.: +Blah blah blah +""") + + + +# Test the basic MIMEAudio class +class TestMIMEAudio(unittest.TestCase): + def setUp(self): + # Make sure we pick up the audiotest.au that lives in email/test/data. + # In Python, there's an audiotest.au living in Lib/test but that isn't + # included in some binary distros that don't include the test + # package. The trailing empty string on the .join() is significant + # since findfile() will do a dirname(). + datadir = os.path.join(os.path.dirname(landmark), 'data', '') + fp = open(findfile('audiotest.au', datadir), 'rb') + try: + self._audiodata = fp.read() + finally: + fp.close() + self._au = MIMEAudio(self._audiodata) + + def test_guess_minor_type(self): + self.assertEqual(self._au.get_content_type(), 'audio/basic') + + def test_encoding(self): + payload = self._au.get_payload() + self.assertEqual(base64.decodestring(payload), self._audiodata) + + def test_checkSetMinor(self): + au = MIMEAudio(self._audiodata, 'fish') + self.assertEqual(au.get_content_type(), 'audio/fish') + + def test_add_header(self): + eq = self.assertEqual + unless = self.failUnless + self._au.add_header('Content-Disposition', 'attachment', + filename='audiotest.au') + eq(self._au['content-disposition'], + 'attachment; filename="audiotest.au"') + eq(self._au.get_params(header='content-disposition'), + [('attachment', ''), ('filename', 'audiotest.au')]) + eq(self._au.get_param('filename', header='content-disposition'), + 'audiotest.au') + missing = [] + eq(self._au.get_param('attachment', header='content-disposition'), '') + unless(self._au.get_param('foo', failobj=missing, + header='content-disposition') is missing) + # Try some missing stuff + unless(self._au.get_param('foobar', missing) is missing) + unless(self._au.get_param('attachment', missing, + header='foobar') is missing) + + + +# Test the basic MIMEImage class +class TestMIMEImage(unittest.TestCase): + def setUp(self): + fp = openfile('PyBanner048.gif') + try: + self._imgdata = fp.read() + finally: + fp.close() + self._im = MIMEImage(self._imgdata) + + def test_guess_minor_type(self): + self.assertEqual(self._im.get_content_type(), 'image/gif') + + def test_encoding(self): + payload = self._im.get_payload() + self.assertEqual(base64.decodestring(payload), self._imgdata) + + def test_checkSetMinor(self): + im = MIMEImage(self._imgdata, 'fish') + self.assertEqual(im.get_content_type(), 'image/fish') + + def test_add_header(self): + eq = self.assertEqual + unless = self.failUnless + self._im.add_header('Content-Disposition', 'attachment', + filename='dingusfish.gif') + eq(self._im['content-disposition'], + 'attachment; filename="dingusfish.gif"') + eq(self._im.get_params(header='content-disposition'), + [('attachment', ''), ('filename', 'dingusfish.gif')]) + eq(self._im.get_param('filename', header='content-disposition'), + 'dingusfish.gif') + missing = [] + eq(self._im.get_param('attachment', header='content-disposition'), '') + unless(self._im.get_param('foo', failobj=missing, + header='content-disposition') is missing) + # Try some missing stuff + unless(self._im.get_param('foobar', missing) is missing) + unless(self._im.get_param('attachment', missing, + header='foobar') is missing) + + + +# Test the basic MIMEApplication class +class TestMIMEApplication(unittest.TestCase): + def test_headers(self): + eq = self.assertEqual + msg = MIMEApplication('\xfa\xfb\xfc\xfd\xfe\xff') + eq(msg.get_content_type(), 'application/octet-stream') + eq(msg['content-transfer-encoding'], 'base64') + + def test_body(self): + eq = self.assertEqual + bytes = '\xfa\xfb\xfc\xfd\xfe\xff' + msg = MIMEApplication(bytes) + eq(msg.get_payload(), '+vv8/f7/') + eq(msg.get_payload(decode=True), bytes) + + + +# Test the basic MIMEText class +class TestMIMEText(unittest.TestCase): + def setUp(self): + self._msg = MIMEText('hello there') + + def test_types(self): + eq = self.assertEqual + unless = self.failUnless + eq(self._msg.get_content_type(), 'text/plain') + eq(self._msg.get_param('charset'), 'us-ascii') + missing = [] + unless(self._msg.get_param('foobar', missing) is missing) + unless(self._msg.get_param('charset', missing, header='foobar') + is missing) + + def test_payload(self): + self.assertEqual(self._msg.get_payload(), 'hello there') + self.failUnless(not self._msg.is_multipart()) + + def test_charset(self): + eq = self.assertEqual + msg = MIMEText('hello there', _charset='us-ascii') + eq(msg.get_charset().input_charset, 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + + + +# Test complicated multipart/* messages +class TestMultipart(TestEmailBase): + def setUp(self): + fp = openfile('PyBanner048.gif') + try: + data = fp.read() + finally: + fp.close() + + container = MIMEBase('multipart', 'mixed', boundary='BOUNDARY') + image = MIMEImage(data, name='dingusfish.gif') + image.add_header('content-disposition', 'attachment', + filename='dingusfish.gif') + intro = MIMEText('''\ +Hi there, + +This is the dingus fish. +''') + container.attach(intro) + container.attach(image) + container['From'] = 'Barry ' + container['To'] = 'Dingus Lovers ' + container['Subject'] = 'Here is your dingus fish' + + now = 987809702.54848599 + timetuple = time.localtime(now) + if timetuple[-1] == 0: + tzsecs = time.timezone + else: + tzsecs = time.altzone + if tzsecs > 0: + sign = '-' + else: + sign = '+' + tzoffset = ' %s%04d' % (sign, tzsecs / 36) + container['Date'] = time.strftime( + '%a, %d %b %Y %H:%M:%S', + time.localtime(now)) + tzoffset + self._msg = container + self._im = image + self._txt = intro + + def test_hierarchy(self): + # convenience + eq = self.assertEqual + unless = self.failUnless + raises = self.assertRaises + # tests + m = self._msg + unless(m.is_multipart()) + eq(m.get_content_type(), 'multipart/mixed') + eq(len(m.get_payload()), 2) + raises(IndexError, m.get_payload, 2) + m0 = m.get_payload(0) + m1 = m.get_payload(1) + unless(m0 is self._txt) + unless(m1 is self._im) + eq(m.get_payload(), [m0, m1]) + unless(not m0.is_multipart()) + unless(not m1.is_multipart()) + + def test_empty_multipart_idempotent(self): + text = """\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + + +--BOUNDARY + + +--BOUNDARY-- +""" + msg = Parser().parsestr(text) + self.ndiffAssertEqual(text, msg.as_string()) + + def test_no_parts_in_a_multipart_with_none_epilogue(self): + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.set_boundary('BOUNDARY') + self.ndiffAssertEqual(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY + +--BOUNDARY--''') + + def test_no_parts_in_a_multipart_with_empty_epilogue(self): + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.preamble = '' + outer.epilogue = '' + outer.set_boundary('BOUNDARY') + self.ndiffAssertEqual(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + + +--BOUNDARY + +--BOUNDARY-- +''') + + def test_one_part_in_a_multipart(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.set_boundary('BOUNDARY') + msg = MIMEText('hello world') + outer.attach(msg) + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + def test_seq_parts_in_a_multipart_with_empty_preamble(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.preamble = '' + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + + def test_seq_parts_in_a_multipart_with_none_preamble(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.preamble = None + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + + def test_seq_parts_in_a_multipart_with_none_epilogue(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.epilogue = None + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + + def test_seq_parts_in_a_multipart_with_empty_epilogue(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.epilogue = '' + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY-- +''') + + + def test_seq_parts_in_a_multipart_with_nl_epilogue(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.epilogue = '\n' + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY-- + +''') + + def test_message_external_body(self): + eq = self.assertEqual + msg = self._msgobj('msg_36.txt') + eq(len(msg.get_payload()), 2) + msg1 = msg.get_payload(1) + eq(msg1.get_content_type(), 'multipart/alternative') + eq(len(msg1.get_payload()), 2) + for subpart in msg1.get_payload(): + eq(subpart.get_content_type(), 'message/external-body') + eq(len(subpart.get_payload()), 1) + subsubpart = subpart.get_payload(0) + eq(subsubpart.get_content_type(), 'text/plain') + + def test_double_boundary(self): + # msg_37.txt is a multipart that contains two dash-boundary's in a + # row. Our interpretation of RFC 2046 calls for ignoring the second + # and subsequent boundaries. + msg = self._msgobj('msg_37.txt') + self.assertEqual(len(msg.get_payload()), 3) + + def test_nested_inner_contains_outer_boundary(self): + eq = self.ndiffAssertEqual + # msg_38.txt has an inner part that contains outer boundaries. My + # interpretation of RFC 2046 (based on sections 5.1 and 5.1.2) say + # these are illegal and should be interpreted as unterminated inner + # parts. + msg = self._msgobj('msg_38.txt') + sfp = StringIO() + iterators._structure(msg, sfp) + eq(sfp.getvalue(), """\ +multipart/mixed + multipart/mixed + multipart/alternative + text/plain + text/plain + text/plain + text/plain +""") + + def test_nested_with_same_boundary(self): + eq = self.ndiffAssertEqual + # msg 39.txt is similarly evil in that it's got inner parts that use + # the same boundary as outer parts. Again, I believe the way this is + # parsed is closest to the spirit of RFC 2046 + msg = self._msgobj('msg_39.txt') + sfp = StringIO() + iterators._structure(msg, sfp) + eq(sfp.getvalue(), """\ +multipart/mixed + multipart/mixed + multipart/alternative + application/octet-stream + application/octet-stream + text/plain +""") + + def test_boundary_in_non_multipart(self): + msg = self._msgobj('msg_40.txt') + self.assertEqual(msg.as_string(), '''\ +MIME-Version: 1.0 +Content-Type: text/html; boundary="--961284236552522269" + +----961284236552522269 +Content-Type: text/html; +Content-Transfer-Encoding: 7Bit + + + +----961284236552522269-- +''') + + def test_boundary_with_leading_space(self): + eq = self.assertEqual + msg = email.message_from_string('''\ +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary=" XXXX" + +-- XXXX +Content-Type: text/plain + + +-- XXXX +Content-Type: text/plain + +-- XXXX-- +''') + self.failUnless(msg.is_multipart()) + eq(msg.get_boundary(), ' XXXX') + eq(len(msg.get_payload()), 2) + + def test_boundary_without_trailing_newline(self): + m = Parser().parsestr("""\ +Content-Type: multipart/mixed; boundary="===============0012394164==" +MIME-Version: 1.0 + +--===============0012394164== +Content-Type: image/file1.jpg +MIME-Version: 1.0 +Content-Transfer-Encoding: base64 + +YXNkZg== +--===============0012394164==--""") + self.assertEquals(m.get_payload(0).get_payload(), 'YXNkZg==') + + + +# Test some badly formatted messages +class TestNonConformant(TestEmailBase): + def test_parse_missing_minor_type(self): + eq = self.assertEqual + msg = self._msgobj('msg_14.txt') + eq(msg.get_content_type(), 'text/plain') + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + + def test_same_boundary_inner_outer(self): + unless = self.failUnless + msg = self._msgobj('msg_15.txt') + # XXX We can probably eventually do better + inner = msg.get_payload(0) + unless(hasattr(inner, 'defects')) + self.assertEqual(len(inner.defects), 1) + unless(isinstance(inner.defects[0], + errors.StartBoundaryNotFoundDefect)) + + def test_multipart_no_boundary(self): + unless = self.failUnless + msg = self._msgobj('msg_25.txt') + unless(isinstance(msg.get_payload(), str)) + self.assertEqual(len(msg.defects), 2) + unless(isinstance(msg.defects[0], errors.NoBoundaryInMultipartDefect)) + unless(isinstance(msg.defects[1], + errors.MultipartInvariantViolationDefect)) + + def test_invalid_content_type(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + msg = Message() + # RFC 2045, $5.2 says invalid yields text/plain + msg['Content-Type'] = 'text' + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + eq(msg.get_content_type(), 'text/plain') + # Clear the old value and try something /really/ invalid + del msg['content-type'] + msg['Content-Type'] = 'foo' + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + eq(msg.get_content_type(), 'text/plain') + # Still, make sure that the message is idempotently generated + s = StringIO() + g = Generator(s) + g.flatten(msg) + neq(s.getvalue(), 'Content-Type: foo\n\n') + + def test_no_start_boundary(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_31.txt') + eq(msg.get_payload(), """\ +--BOUNDARY +Content-Type: text/plain + +message 1 + +--BOUNDARY +Content-Type: text/plain + +message 2 + +--BOUNDARY-- +""") + + def test_no_separating_blank_line(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_35.txt') + eq(msg.as_string(), """\ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: here's something interesting + +counter to RFC 2822, there's no separating newline here +""") + + def test_lying_multipart(self): + unless = self.failUnless + msg = self._msgobj('msg_41.txt') + unless(hasattr(msg, 'defects')) + self.assertEqual(len(msg.defects), 2) + unless(isinstance(msg.defects[0], errors.NoBoundaryInMultipartDefect)) + unless(isinstance(msg.defects[1], + errors.MultipartInvariantViolationDefect)) + + def test_missing_start_boundary(self): + outer = self._msgobj('msg_42.txt') + # The message structure is: + # + # multipart/mixed + # text/plain + # message/rfc822 + # multipart/mixed [*] + # + # [*] This message is missing its start boundary + bad = outer.get_payload(1).get_payload(0) + self.assertEqual(len(bad.defects), 1) + self.failUnless(isinstance(bad.defects[0], + errors.StartBoundaryNotFoundDefect)) + + + +# Test RFC 2047 header encoding and decoding +class TestRFC2047(unittest.TestCase): + def test_rfc2047_multiline(self): + eq = self.assertEqual + s = """Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz + foo bar =?mac-iceland?q?r=8Aksm=9Arg=8Cs?=""" + dh = decode_header(s) + eq(dh, [ + ('Re:', None), + ('r\x8aksm\x9arg\x8cs', 'mac-iceland'), + ('baz foo bar', None), + ('r\x8aksm\x9arg\x8cs', 'mac-iceland')]) + eq(str(make_header(dh)), + """Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar + =?mac-iceland?q?r=8Aksm=9Arg=8Cs?=""") + + def test_whitespace_eater_unicode(self): + eq = self.assertEqual + s = '=?ISO-8859-1?Q?Andr=E9?= Pirard ' + dh = decode_header(s) + eq(dh, [('Andr\xe9', 'iso-8859-1'), ('Pirard ', None)]) + hu = unicode(make_header(dh)).encode('latin-1') + eq(hu, 'Andr\xe9 Pirard ') + + def test_whitespace_eater_unicode_2(self): + eq = self.assertEqual + s = 'The =?iso-8859-1?b?cXVpY2sgYnJvd24gZm94?= jumped over the =?iso-8859-1?b?bGF6eSBkb2c=?=' + dh = decode_header(s) + eq(dh, [('The', None), ('quick brown fox', 'iso-8859-1'), + ('jumped over the', None), ('lazy dog', 'iso-8859-1')]) + hu = make_header(dh).__unicode__() + eq(hu, u'The quick brown fox jumped over the lazy dog') + + + +# Test the MIMEMessage class +class TestMIMEMessage(TestEmailBase): + def setUp(self): + fp = openfile('msg_11.txt') + try: + self._text = fp.read() + finally: + fp.close() + + def test_type_error(self): + self.assertRaises(TypeError, MIMEMessage, 'a plain string') + + def test_valid_argument(self): + eq = self.assertEqual + unless = self.failUnless + subject = 'A sub-message' + m = Message() + m['Subject'] = subject + r = MIMEMessage(m) + eq(r.get_content_type(), 'message/rfc822') + payload = r.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + subpart = payload[0] + unless(subpart is m) + eq(subpart['subject'], subject) + + def test_bad_multipart(self): + eq = self.assertEqual + msg1 = Message() + msg1['Subject'] = 'subpart 1' + msg2 = Message() + msg2['Subject'] = 'subpart 2' + r = MIMEMessage(msg1) + self.assertRaises(errors.MultipartConversionError, r.attach, msg2) + + def test_generate(self): + # First craft the message to be encapsulated + m = Message() + m['Subject'] = 'An enclosed message' + m.set_payload('Here is the body of the message.\n') + r = MIMEMessage(m) + r['Subject'] = 'The enclosing message' + s = StringIO() + g = Generator(s) + g.flatten(r) + self.assertEqual(s.getvalue(), """\ +Content-Type: message/rfc822 +MIME-Version: 1.0 +Subject: The enclosing message + +Subject: An enclosed message + +Here is the body of the message. +""") + + def test_parse_message_rfc822(self): + eq = self.assertEqual + unless = self.failUnless + msg = self._msgobj('msg_11.txt') + eq(msg.get_content_type(), 'message/rfc822') + payload = msg.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + submsg = payload[0] + self.failUnless(isinstance(submsg, Message)) + eq(submsg['subject'], 'An enclosed message') + eq(submsg.get_payload(), 'Here is the body of the message.\n') + + def test_dsn(self): + eq = self.assertEqual + unless = self.failUnless + # msg 16 is a Delivery Status Notification, see RFC 1894 + msg = self._msgobj('msg_16.txt') + eq(msg.get_content_type(), 'multipart/report') + unless(msg.is_multipart()) + eq(len(msg.get_payload()), 3) + # Subpart 1 is a text/plain, human readable section + subpart = msg.get_payload(0) + eq(subpart.get_content_type(), 'text/plain') + eq(subpart.get_payload(), """\ +This report relates to a message you sent with the following header fields: + + Message-id: <002001c144a6$8752e060$56104586@oxy.edu> + Date: Sun, 23 Sep 2001 20:10:55 -0700 + From: "Ian T. Henry" + To: SoCal Raves + Subject: [scr] yeah for Ians!! + +Your message cannot be delivered to the following recipients: + + Recipient address: jangel1@cougar.noc.ucla.edu + Reason: recipient reached disk quota + +""") + # Subpart 2 contains the machine parsable DSN information. It + # consists of two blocks of headers, represented by two nested Message + # objects. + subpart = msg.get_payload(1) + eq(subpart.get_content_type(), 'message/delivery-status') + eq(len(subpart.get_payload()), 2) + # message/delivery-status should treat each block as a bunch of + # headers, i.e. a bunch of Message objects. + dsn1 = subpart.get_payload(0) + unless(isinstance(dsn1, Message)) + eq(dsn1['original-envelope-id'], '0GK500B4HD0888@cougar.noc.ucla.edu') + eq(dsn1.get_param('dns', header='reporting-mta'), '') + # Try a missing one + eq(dsn1.get_param('nsd', header='reporting-mta'), None) + dsn2 = subpart.get_payload(1) + unless(isinstance(dsn2, Message)) + eq(dsn2['action'], 'failed') + eq(dsn2.get_params(header='original-recipient'), + [('rfc822', ''), ('jangel1@cougar.noc.ucla.edu', '')]) + eq(dsn2.get_param('rfc822', header='final-recipient'), '') + # Subpart 3 is the original message + subpart = msg.get_payload(2) + eq(subpart.get_content_type(), 'message/rfc822') + payload = subpart.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + subsubpart = payload[0] + unless(isinstance(subsubpart, Message)) + eq(subsubpart.get_content_type(), 'text/plain') + eq(subsubpart['message-id'], + '<002001c144a6$8752e060$56104586@oxy.edu>') + + def test_epilogue(self): + eq = self.ndiffAssertEqual + fp = openfile('msg_21.txt') + try: + text = fp.read() + finally: + fp.close() + msg = Message() + msg['From'] = 'aperson@dom.ain' + msg['To'] = 'bperson@dom.ain' + msg['Subject'] = 'Test' + msg.preamble = 'MIME message' + msg.epilogue = 'End of MIME message\n' + msg1 = MIMEText('One') + msg2 = MIMEText('Two') + msg.add_header('Content-Type', 'multipart/mixed', boundary='BOUNDARY') + msg.attach(msg1) + msg.attach(msg2) + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), text) + + def test_no_nl_preamble(self): + eq = self.ndiffAssertEqual + msg = Message() + msg['From'] = 'aperson@dom.ain' + msg['To'] = 'bperson@dom.ain' + msg['Subject'] = 'Test' + msg.preamble = 'MIME message' + msg.epilogue = '' + msg1 = MIMEText('One') + msg2 = MIMEText('Two') + msg.add_header('Content-Type', 'multipart/mixed', boundary='BOUNDARY') + msg.attach(msg1) + msg.attach(msg2) + eq(msg.as_string(), """\ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: Test +Content-Type: multipart/mixed; boundary="BOUNDARY" + +MIME message +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +One +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +Two +--BOUNDARY-- +""") + + def test_default_type(self): + eq = self.assertEqual + fp = openfile('msg_30.txt') + try: + msg = email.message_from_file(fp) + finally: + fp.close() + container1 = msg.get_payload(0) + eq(container1.get_default_type(), 'message/rfc822') + eq(container1.get_content_type(), 'message/rfc822') + container2 = msg.get_payload(1) + eq(container2.get_default_type(), 'message/rfc822') + eq(container2.get_content_type(), 'message/rfc822') + container1a = container1.get_payload(0) + eq(container1a.get_default_type(), 'text/plain') + eq(container1a.get_content_type(), 'text/plain') + container2a = container2.get_payload(0) + eq(container2a.get_default_type(), 'text/plain') + eq(container2a.get_content_type(), 'text/plain') + + def test_default_type_with_explicit_container_type(self): + eq = self.assertEqual + fp = openfile('msg_28.txt') + try: + msg = email.message_from_file(fp) + finally: + fp.close() + container1 = msg.get_payload(0) + eq(container1.get_default_type(), 'message/rfc822') + eq(container1.get_content_type(), 'message/rfc822') + container2 = msg.get_payload(1) + eq(container2.get_default_type(), 'message/rfc822') + eq(container2.get_content_type(), 'message/rfc822') + container1a = container1.get_payload(0) + eq(container1a.get_default_type(), 'text/plain') + eq(container1a.get_content_type(), 'text/plain') + container2a = container2.get_payload(0) + eq(container2a.get_default_type(), 'text/plain') + eq(container2a.get_content_type(), 'text/plain') + + def test_default_type_non_parsed(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + # Set up container + container = MIMEMultipart('digest', 'BOUNDARY') + container.epilogue = '' + # Set up subparts + subpart1a = MIMEText('message 1\n') + subpart2a = MIMEText('message 2\n') + subpart1 = MIMEMessage(subpart1a) + subpart2 = MIMEMessage(subpart2a) + container.attach(subpart1) + container.attach(subpart2) + eq(subpart1.get_content_type(), 'message/rfc822') + eq(subpart1.get_default_type(), 'message/rfc822') + eq(subpart2.get_content_type(), 'message/rfc822') + eq(subpart2.get_default_type(), 'message/rfc822') + neq(container.as_string(0), '''\ +Content-Type: multipart/digest; boundary="BOUNDARY" +MIME-Version: 1.0 + +--BOUNDARY +Content-Type: message/rfc822 +MIME-Version: 1.0 + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 1 + +--BOUNDARY +Content-Type: message/rfc822 +MIME-Version: 1.0 + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 2 + +--BOUNDARY-- +''') + del subpart1['content-type'] + del subpart1['mime-version'] + del subpart2['content-type'] + del subpart2['mime-version'] + eq(subpart1.get_content_type(), 'message/rfc822') + eq(subpart1.get_default_type(), 'message/rfc822') + eq(subpart2.get_content_type(), 'message/rfc822') + eq(subpart2.get_default_type(), 'message/rfc822') + neq(container.as_string(0), '''\ +Content-Type: multipart/digest; boundary="BOUNDARY" +MIME-Version: 1.0 + +--BOUNDARY + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 1 + +--BOUNDARY + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 2 + +--BOUNDARY-- +''') + + def test_mime_attachments_in_constructor(self): + eq = self.assertEqual + text1 = MIMEText('') + text2 = MIMEText('') + msg = MIMEMultipart(_subparts=(text1, text2)) + eq(len(msg.get_payload()), 2) + eq(msg.get_payload(0), text1) + eq(msg.get_payload(1), text2) + + + +# A general test of parser->model->generator idempotency. IOW, read a message +# in, parse it into a message object tree, then without touching the tree, +# regenerate the plain text. The original text and the transformed text +# should be identical. Note: that we ignore the Unix-From since that may +# contain a changed date. +class TestIdempotent(TestEmailBase): + def _msgobj(self, filename): + fp = openfile(filename) + try: + data = fp.read() + finally: + fp.close() + msg = email.message_from_string(data) + return msg, data + + def _idempotent(self, msg, text): + eq = self.ndiffAssertEqual + s = StringIO() + g = Generator(s, maxheaderlen=0) + g.flatten(msg) + eq(text, s.getvalue()) + + def test_parse_text_message(self): + eq = self.assertEquals + msg, text = self._msgobj('msg_01.txt') + eq(msg.get_content_type(), 'text/plain') + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + eq(msg.get_params()[1], ('charset', 'us-ascii')) + eq(msg.get_param('charset'), 'us-ascii') + eq(msg.preamble, None) + eq(msg.epilogue, None) + self._idempotent(msg, text) + + def test_parse_untyped_message(self): + eq = self.assertEquals + msg, text = self._msgobj('msg_03.txt') + eq(msg.get_content_type(), 'text/plain') + eq(msg.get_params(), None) + eq(msg.get_param('charset'), None) + self._idempotent(msg, text) + + def test_simple_multipart(self): + msg, text = self._msgobj('msg_04.txt') + self._idempotent(msg, text) + + def test_MIME_digest(self): + msg, text = self._msgobj('msg_02.txt') + self._idempotent(msg, text) + + def test_long_header(self): + msg, text = self._msgobj('msg_27.txt') + self._idempotent(msg, text) + + def test_MIME_digest_with_part_headers(self): + msg, text = self._msgobj('msg_28.txt') + self._idempotent(msg, text) + + def test_mixed_with_image(self): + msg, text = self._msgobj('msg_06.txt') + self._idempotent(msg, text) + + def test_multipart_report(self): + msg, text = self._msgobj('msg_05.txt') + self._idempotent(msg, text) + + def test_dsn(self): + msg, text = self._msgobj('msg_16.txt') + self._idempotent(msg, text) + + def test_preamble_epilogue(self): + msg, text = self._msgobj('msg_21.txt') + self._idempotent(msg, text) + + def test_multipart_one_part(self): + msg, text = self._msgobj('msg_23.txt') + self._idempotent(msg, text) + + def test_multipart_no_parts(self): + msg, text = self._msgobj('msg_24.txt') + self._idempotent(msg, text) + + def test_no_start_boundary(self): + msg, text = self._msgobj('msg_31.txt') + self._idempotent(msg, text) + + def test_rfc2231_charset(self): + msg, text = self._msgobj('msg_32.txt') + self._idempotent(msg, text) + + def test_more_rfc2231_parameters(self): + msg, text = self._msgobj('msg_33.txt') + self._idempotent(msg, text) + + def test_text_plain_in_a_multipart_digest(self): + msg, text = self._msgobj('msg_34.txt') + self._idempotent(msg, text) + + def test_nested_multipart_mixeds(self): + msg, text = self._msgobj('msg_12a.txt') + self._idempotent(msg, text) + + def test_message_external_body_idempotent(self): + msg, text = self._msgobj('msg_36.txt') + self._idempotent(msg, text) + + def test_content_type(self): + eq = self.assertEquals + unless = self.failUnless + # Get a message object and reset the seek pointer for other tests + msg, text = self._msgobj('msg_05.txt') + eq(msg.get_content_type(), 'multipart/report') + # Test the Content-Type: parameters + params = {} + for pk, pv in msg.get_params(): + params[pk] = pv + eq(params['report-type'], 'delivery-status') + eq(params['boundary'], 'D1690A7AC1.996856090/mail.example.com') + eq(msg.preamble, 'This is a MIME-encapsulated message.\n') + eq(msg.epilogue, '\n') + eq(len(msg.get_payload()), 3) + # Make sure the subparts are what we expect + msg1 = msg.get_payload(0) + eq(msg1.get_content_type(), 'text/plain') + eq(msg1.get_payload(), 'Yadda yadda yadda\n') + msg2 = msg.get_payload(1) + eq(msg2.get_content_type(), 'text/plain') + eq(msg2.get_payload(), 'Yadda yadda yadda\n') + msg3 = msg.get_payload(2) + eq(msg3.get_content_type(), 'message/rfc822') + self.failUnless(isinstance(msg3, Message)) + payload = msg3.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + msg4 = payload[0] + unless(isinstance(msg4, Message)) + eq(msg4.get_payload(), 'Yadda yadda yadda\n') + + def test_parser(self): + eq = self.assertEquals + unless = self.failUnless + msg, text = self._msgobj('msg_06.txt') + # Check some of the outer headers + eq(msg.get_content_type(), 'message/rfc822') + # Make sure the payload is a list of exactly one sub-Message, and that + # that submessage has a type of text/plain + payload = msg.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + msg1 = payload[0] + self.failUnless(isinstance(msg1, Message)) + eq(msg1.get_content_type(), 'text/plain') + self.failUnless(isinstance(msg1.get_payload(), str)) + eq(msg1.get_payload(), '\n') + + + +# Test various other bits of the package's functionality +class TestMiscellaneous(TestEmailBase): + def test_message_from_string(self): + fp = openfile('msg_01.txt') + try: + text = fp.read() + finally: + fp.close() + msg = email.message_from_string(text) + s = StringIO() + # Don't wrap/continue long headers since we're trying to test + # idempotency. + g = Generator(s, maxheaderlen=0) + g.flatten(msg) + self.assertEqual(text, s.getvalue()) + + def test_message_from_file(self): + fp = openfile('msg_01.txt') + try: + text = fp.read() + fp.seek(0) + msg = email.message_from_file(fp) + s = StringIO() + # Don't wrap/continue long headers since we're trying to test + # idempotency. + g = Generator(s, maxheaderlen=0) + g.flatten(msg) + self.assertEqual(text, s.getvalue()) + finally: + fp.close() + + def test_message_from_string_with_class(self): + unless = self.failUnless + fp = openfile('msg_01.txt') + try: + text = fp.read() + finally: + fp.close() + # Create a subclass + class MyMessage(Message): + pass + + msg = email.message_from_string(text, MyMessage) + unless(isinstance(msg, MyMessage)) + # Try something more complicated + fp = openfile('msg_02.txt') + try: + text = fp.read() + finally: + fp.close() + msg = email.message_from_string(text, MyMessage) + for subpart in msg.walk(): + unless(isinstance(subpart, MyMessage)) + + def test_message_from_file_with_class(self): + unless = self.failUnless + # Create a subclass + class MyMessage(Message): + pass + + fp = openfile('msg_01.txt') + try: + msg = email.message_from_file(fp, MyMessage) + finally: + fp.close() + unless(isinstance(msg, MyMessage)) + # Try something more complicated + fp = openfile('msg_02.txt') + try: + msg = email.message_from_file(fp, MyMessage) + finally: + fp.close() + for subpart in msg.walk(): + unless(isinstance(subpart, MyMessage)) + + def test__all__(self): + module = __import__('email') + # Can't use sorted() here due to Python 2.3 compatibility + all = module.__all__[:] + all.sort() + self.assertEqual(all, [ + # Old names + 'Charset', 'Encoders', 'Errors', 'Generator', + 'Header', 'Iterators', 'MIMEAudio', 'MIMEBase', + 'MIMEImage', 'MIMEMessage', 'MIMEMultipart', + 'MIMENonMultipart', 'MIMEText', 'Message', + 'Parser', 'Utils', 'base64MIME', + # new names + 'base64mime', 'charset', 'encoders', 'errors', 'generator', + 'header', 'iterators', 'message', 'message_from_file', + 'message_from_string', 'mime', 'parser', + 'quopriMIME', 'quoprimime', 'utils', + ]) + + def test_formatdate(self): + now = time.time() + self.assertEqual(utils.parsedate(utils.formatdate(now))[:6], + time.gmtime(now)[:6]) + + def test_formatdate_localtime(self): + now = time.time() + self.assertEqual( + utils.parsedate(utils.formatdate(now, localtime=True))[:6], + time.localtime(now)[:6]) + + def test_formatdate_usegmt(self): + now = time.time() + self.assertEqual( + utils.formatdate(now, localtime=False), + time.strftime('%a, %d %b %Y %H:%M:%S -0000', time.gmtime(now))) + self.assertEqual( + utils.formatdate(now, localtime=False, usegmt=True), + time.strftime('%a, %d %b %Y %H:%M:%S GMT', time.gmtime(now))) + + def test_parsedate_none(self): + self.assertEqual(utils.parsedate(''), None) + + def test_parsedate_compact(self): + # The FWS after the comma is optional + self.assertEqual(utils.parsedate('Wed,3 Apr 2002 14:58:26 +0800'), + utils.parsedate('Wed, 3 Apr 2002 14:58:26 +0800')) + + def test_parsedate_no_dayofweek(self): + eq = self.assertEqual + eq(utils.parsedate_tz('25 Feb 2003 13:47:26 -0800'), + (2003, 2, 25, 13, 47, 26, 0, 1, 0, -28800)) + + def test_parsedate_compact_no_dayofweek(self): + eq = self.assertEqual + eq(utils.parsedate_tz('5 Feb 2003 13:47:26 -0800'), + (2003, 2, 5, 13, 47, 26, 0, 1, 0, -28800)) + + def test_parsedate_acceptable_to_time_functions(self): + eq = self.assertEqual + timetup = utils.parsedate('5 Feb 2003 13:47:26 -0800') + t = int(time.mktime(timetup)) + eq(time.localtime(t)[:6], timetup[:6]) + eq(int(time.strftime('%Y', timetup)), 2003) + timetup = utils.parsedate_tz('5 Feb 2003 13:47:26 -0800') + t = int(time.mktime(timetup[:9])) + eq(time.localtime(t)[:6], timetup[:6]) + eq(int(time.strftime('%Y', timetup[:9])), 2003) + + def test_parseaddr_empty(self): + self.assertEqual(utils.parseaddr('<>'), ('', '')) + self.assertEqual(utils.formataddr(utils.parseaddr('<>')), '') + + def test_noquote_dump(self): + self.assertEqual( + utils.formataddr(('A Silly Person', 'person@dom.ain')), + 'A Silly Person ') + + def test_escape_dump(self): + self.assertEqual( + utils.formataddr(('A (Very) Silly Person', 'person@dom.ain')), + r'"A \(Very\) Silly Person" ') + a = r'A \(Special\) Person' + b = 'person@dom.ain' + self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b)) + + def test_escape_backslashes(self): + self.assertEqual( + utils.formataddr(('Arthur \Backslash\ Foobar', 'person@dom.ain')), + r'"Arthur \\Backslash\\ Foobar" ') + a = r'Arthur \Backslash\ Foobar' + b = 'person@dom.ain' + self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b)) + + def test_name_with_dot(self): + x = 'John X. Doe ' + y = '"John X. Doe" ' + a, b = ('John X. Doe', 'jxd@example.com') + self.assertEqual(utils.parseaddr(x), (a, b)) + self.assertEqual(utils.parseaddr(y), (a, b)) + # formataddr() quotes the name if there's a dot in it + self.assertEqual(utils.formataddr((a, b)), y) + + def test_quote_dump(self): + self.assertEqual( + utils.formataddr(('A Silly; Person', 'person@dom.ain')), + r'"A Silly; Person" ') + + def test_fix_eols(self): + eq = self.assertEqual + eq(utils.fix_eols('hello'), 'hello') + eq(utils.fix_eols('hello\n'), 'hello\r\n') + eq(utils.fix_eols('hello\r'), 'hello\r\n') + eq(utils.fix_eols('hello\r\n'), 'hello\r\n') + eq(utils.fix_eols('hello\n\r'), 'hello\r\n\r\n') + + def test_charset_richcomparisons(self): + eq = self.assertEqual + ne = self.failIfEqual + cset1 = Charset() + cset2 = Charset() + eq(cset1, 'us-ascii') + eq(cset1, 'US-ASCII') + eq(cset1, 'Us-AsCiI') + eq('us-ascii', cset1) + eq('US-ASCII', cset1) + eq('Us-AsCiI', cset1) + ne(cset1, 'usascii') + ne(cset1, 'USASCII') + ne(cset1, 'UsAsCiI') + ne('usascii', cset1) + ne('USASCII', cset1) + ne('UsAsCiI', cset1) + eq(cset1, cset2) + eq(cset2, cset1) + + def test_getaddresses(self): + eq = self.assertEqual + eq(utils.getaddresses(['aperson@dom.ain (Al Person)', + 'Bud Person ']), + [('Al Person', 'aperson@dom.ain'), + ('Bud Person', 'bperson@dom.ain')]) + + def test_getaddresses_nasty(self): + eq = self.assertEqual + eq(utils.getaddresses(['foo: ;']), [('', '')]) + eq(utils.getaddresses( + ['[]*-- =~$']), + [('', ''), ('', ''), ('', '*--')]) + eq(utils.getaddresses( + ['foo: ;', '"Jason R. Mastaler" ']), + [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]) + + def test_utils_quote_unquote(self): + eq = self.assertEqual + msg = Message() + msg.add_header('content-disposition', 'attachment', + filename='foo\\wacky"name') + eq(msg.get_filename(), 'foo\\wacky"name') + + def test_get_body_encoding_with_bogus_charset(self): + charset = Charset('not a charset') + self.assertEqual(charset.get_body_encoding(), 'base64') + + def test_get_body_encoding_with_uppercase_charset(self): + eq = self.assertEqual + msg = Message() + msg['Content-Type'] = 'text/plain; charset=UTF-8' + eq(msg['content-type'], 'text/plain; charset=UTF-8') + charsets = msg.get_charsets() + eq(len(charsets), 1) + eq(charsets[0], 'utf-8') + charset = Charset(charsets[0]) + eq(charset.get_body_encoding(), 'base64') + msg.set_payload('hello world', charset=charset) + eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n') + eq(msg.get_payload(decode=True), 'hello world') + eq(msg['content-transfer-encoding'], 'base64') + # Try another one + msg = Message() + msg['Content-Type'] = 'text/plain; charset="US-ASCII"' + charsets = msg.get_charsets() + eq(len(charsets), 1) + eq(charsets[0], 'us-ascii') + charset = Charset(charsets[0]) + eq(charset.get_body_encoding(), encoders.encode_7or8bit) + msg.set_payload('hello world', charset=charset) + eq(msg.get_payload(), 'hello world') + eq(msg['content-transfer-encoding'], '7bit') + + def test_charsets_case_insensitive(self): + lc = Charset('us-ascii') + uc = Charset('US-ASCII') + self.assertEqual(lc.get_body_encoding(), uc.get_body_encoding()) + + def test_partial_falls_inside_message_delivery_status(self): + eq = self.ndiffAssertEqual + # The Parser interface provides chunks of data to FeedParser in 8192 + # byte gulps. SF bug #1076485 found one of those chunks inside + # message/delivery-status header block, which triggered an + # unreadline() of NeedMoreData. + msg = self._msgobj('msg_43.txt') + sfp = StringIO() + iterators._structure(msg, sfp) + eq(sfp.getvalue(), """\ +multipart/report + text/plain + message/delivery-status + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/rfc822-headers +""") + + + +# Test the iterator/generators +class TestIterators(TestEmailBase): + def test_body_line_iterator(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + # First a simple non-multipart message + msg = self._msgobj('msg_01.txt') + it = iterators.body_line_iterator(msg) + lines = list(it) + eq(len(lines), 6) + neq(EMPTYSTRING.join(lines), msg.get_payload()) + # Now a more complicated multipart + msg = self._msgobj('msg_02.txt') + it = iterators.body_line_iterator(msg) + lines = list(it) + eq(len(lines), 43) + fp = openfile('msg_19.txt') + try: + neq(EMPTYSTRING.join(lines), fp.read()) + finally: + fp.close() + + def test_typed_subpart_iterator(self): + eq = self.assertEqual + msg = self._msgobj('msg_04.txt') + it = iterators.typed_subpart_iterator(msg, 'text') + lines = [] + subparts = 0 + for subpart in it: + subparts += 1 + lines.append(subpart.get_payload()) + eq(subparts, 2) + eq(EMPTYSTRING.join(lines), """\ +a simple kind of mirror +to reflect upon our own +a simple kind of mirror +to reflect upon our own +""") + + def test_typed_subpart_iterator_default_type(self): + eq = self.assertEqual + msg = self._msgobj('msg_03.txt') + it = iterators.typed_subpart_iterator(msg, 'text', 'plain') + lines = [] + subparts = 0 + for subpart in it: + subparts += 1 + lines.append(subpart.get_payload()) + eq(subparts, 1) + eq(EMPTYSTRING.join(lines), """\ + +Hi, + +Do you like this message? + +-Me +""") + + + +class TestParsers(TestEmailBase): + def test_header_parser(self): + eq = self.assertEqual + # Parse only the headers of a complex multipart MIME document + fp = openfile('msg_02.txt') + try: + msg = HeaderParser().parse(fp) + finally: + fp.close() + eq(msg['from'], 'ppp-request@zzz.org') + eq(msg['to'], 'ppp@zzz.org') + eq(msg.get_content_type(), 'multipart/mixed') + self.failIf(msg.is_multipart()) + self.failUnless(isinstance(msg.get_payload(), str)) + + def test_whitespace_continuation(self): + eq = self.assertEqual + # This message contains a line after the Subject: header that has only + # whitespace, but it is not empty! + msg = email.message_from_string("""\ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: the next line has a space on it +\x20 +Date: Mon, 8 Apr 2002 15:09:19 -0400 +Message-ID: spam + +Here's the message body +""") + eq(msg['subject'], 'the next line has a space on it\n ') + eq(msg['message-id'], 'spam') + eq(msg.get_payload(), "Here's the message body\n") + + def test_whitespace_continuation_last_header(self): + eq = self.assertEqual + # Like the previous test, but the subject line is the last + # header. + msg = email.message_from_string("""\ +From: aperson@dom.ain +To: bperson@dom.ain +Date: Mon, 8 Apr 2002 15:09:19 -0400 +Message-ID: spam +Subject: the next line has a space on it +\x20 + +Here's the message body +""") + eq(msg['subject'], 'the next line has a space on it\n ') + eq(msg['message-id'], 'spam') + eq(msg.get_payload(), "Here's the message body\n") + + def test_crlf_separation(self): + eq = self.assertEqual + fp = openfile('msg_26.txt', mode='rb') + try: + msg = Parser().parse(fp) + finally: + fp.close() + eq(len(msg.get_payload()), 2) + part1 = msg.get_payload(0) + eq(part1.get_content_type(), 'text/plain') + eq(part1.get_payload(), 'Simple email with attachment.\r\n\r\n') + part2 = msg.get_payload(1) + eq(part2.get_content_type(), 'application/riscos') + + def test_multipart_digest_with_extra_mime_headers(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + fp = openfile('msg_28.txt') + try: + msg = email.message_from_file(fp) + finally: + fp.close() + # Structure is: + # multipart/digest + # message/rfc822 + # text/plain + # message/rfc822 + # text/plain + eq(msg.is_multipart(), 1) + eq(len(msg.get_payload()), 2) + part1 = msg.get_payload(0) + eq(part1.get_content_type(), 'message/rfc822') + eq(part1.is_multipart(), 1) + eq(len(part1.get_payload()), 1) + part1a = part1.get_payload(0) + eq(part1a.is_multipart(), 0) + eq(part1a.get_content_type(), 'text/plain') + neq(part1a.get_payload(), 'message 1\n') + # next message/rfc822 + part2 = msg.get_payload(1) + eq(part2.get_content_type(), 'message/rfc822') + eq(part2.is_multipart(), 1) + eq(len(part2.get_payload()), 1) + part2a = part2.get_payload(0) + eq(part2a.is_multipart(), 0) + eq(part2a.get_content_type(), 'text/plain') + neq(part2a.get_payload(), 'message 2\n') + + def test_three_lines(self): + # A bug report by Andrew McNamara + lines = ['From: Andrew Person From', 'From']) + eq(msg.get_payload(), 'body') + + def test_rfc2822_space_not_allowed_in_header(self): + eq = self.assertEqual + m = '>From foo@example.com 11:25:53\nFrom: bar\n!"#QUX;~: zoo\n\nbody' + msg = email.message_from_string(m) + eq(len(msg.keys()), 0) + + def test_rfc2822_one_character_header(self): + eq = self.assertEqual + m = 'A: first header\nB: second header\nCC: third header\n\nbody' + msg = email.message_from_string(m) + headers = msg.keys() + headers.sort() + eq(headers, ['A', 'B', 'CC']) + eq(msg.get_payload(), 'body') + + + +class TestBase64(unittest.TestCase): + def test_len(self): + eq = self.assertEqual + eq(base64mime.base64_len('hello'), + len(base64mime.encode('hello', eol=''))) + for size in range(15): + if size == 0 : bsize = 0 + elif size <= 3 : bsize = 4 + elif size <= 6 : bsize = 8 + elif size <= 9 : bsize = 12 + elif size <= 12: bsize = 16 + else : bsize = 20 + eq(base64mime.base64_len('x'*size), bsize) + + def test_decode(self): + eq = self.assertEqual + eq(base64mime.decode(''), '') + eq(base64mime.decode('aGVsbG8='), 'hello') + eq(base64mime.decode('aGVsbG8=', 'X'), 'hello') + eq(base64mime.decode('aGVsbG8NCndvcmxk\n', 'X'), 'helloXworld') + + def test_encode(self): + eq = self.assertEqual + eq(base64mime.encode(''), '') + eq(base64mime.encode('hello'), 'aGVsbG8=\n') + # Test the binary flag + eq(base64mime.encode('hello\n'), 'aGVsbG8K\n') + eq(base64mime.encode('hello\n', 0), 'aGVsbG8NCg==\n') + # Test the maxlinelen arg + eq(base64mime.encode('xxxx ' * 20, maxlinelen=40), """\ +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg +eHh4eCB4eHh4IA== +""") + # Test the eol argument + eq(base64mime.encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\ +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r +eHh4eCB4eHh4IA==\r +""") + + def test_header_encode(self): + eq = self.assertEqual + he = base64mime.header_encode + eq(he('hello'), '=?iso-8859-1?b?aGVsbG8=?=') + eq(he('hello\nworld'), '=?iso-8859-1?b?aGVsbG8NCndvcmxk?=') + # Test the charset option + eq(he('hello', charset='iso-8859-2'), '=?iso-8859-2?b?aGVsbG8=?=') + # Test the keep_eols flag + eq(he('hello\nworld', keep_eols=True), + '=?iso-8859-1?b?aGVsbG8Kd29ybGQ=?=') + # Test the maxlinelen argument + eq(he('xxxx ' * 20, maxlinelen=40), """\ +=?iso-8859-1?b?eHh4eCB4eHh4IHh4eHggeHg=?= + =?iso-8859-1?b?eHggeHh4eCB4eHh4IHh4eHg=?= + =?iso-8859-1?b?IHh4eHggeHh4eCB4eHh4IHg=?= + =?iso-8859-1?b?eHh4IHh4eHggeHh4eCB4eHg=?= + =?iso-8859-1?b?eCB4eHh4IHh4eHggeHh4eCA=?= + =?iso-8859-1?b?eHh4eCB4eHh4IHh4eHgg?=""") + # Test the eol argument + eq(he('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\ +=?iso-8859-1?b?eHh4eCB4eHh4IHh4eHggeHg=?=\r + =?iso-8859-1?b?eHggeHh4eCB4eHh4IHh4eHg=?=\r + =?iso-8859-1?b?IHh4eHggeHh4eCB4eHh4IHg=?=\r + =?iso-8859-1?b?eHh4IHh4eHggeHh4eCB4eHg=?=\r + =?iso-8859-1?b?eCB4eHh4IHh4eHggeHh4eCA=?=\r + =?iso-8859-1?b?eHh4eCB4eHh4IHh4eHgg?=""") + + + +class TestQuopri(unittest.TestCase): + def setUp(self): + self.hlit = [chr(x) for x in range(ord('a'), ord('z')+1)] + \ + [chr(x) for x in range(ord('A'), ord('Z')+1)] + \ + [chr(x) for x in range(ord('0'), ord('9')+1)] + \ + ['!', '*', '+', '-', '/', ' '] + self.hnon = [chr(x) for x in range(256) if chr(x) not in self.hlit] + assert len(self.hlit) + len(self.hnon) == 256 + self.blit = [chr(x) for x in range(ord(' '), ord('~')+1)] + ['\t'] + self.blit.remove('=') + self.bnon = [chr(x) for x in range(256) if chr(x) not in self.blit] + assert len(self.blit) + len(self.bnon) == 256 + + def test_header_quopri_check(self): + for c in self.hlit: + self.failIf(quoprimime.header_quopri_check(c)) + for c in self.hnon: + self.failUnless(quoprimime.header_quopri_check(c)) + + def test_body_quopri_check(self): + for c in self.blit: + self.failIf(quoprimime.body_quopri_check(c)) + for c in self.bnon: + self.failUnless(quoprimime.body_quopri_check(c)) + + def test_header_quopri_len(self): + eq = self.assertEqual + hql = quoprimime.header_quopri_len + enc = quoprimime.header_encode + for s in ('hello', 'h@e@l@l@o@'): + # Empty charset and no line-endings. 7 == RFC chrome + eq(hql(s), len(enc(s, charset='', eol=''))-7) + for c in self.hlit: + eq(hql(c), 1) + for c in self.hnon: + eq(hql(c), 3) + + def test_body_quopri_len(self): + eq = self.assertEqual + bql = quoprimime.body_quopri_len + for c in self.blit: + eq(bql(c), 1) + for c in self.bnon: + eq(bql(c), 3) + + def test_quote_unquote_idempotent(self): + for x in range(256): + c = chr(x) + self.assertEqual(quoprimime.unquote(quoprimime.quote(c)), c) + + def test_header_encode(self): + eq = self.assertEqual + he = quoprimime.header_encode + eq(he('hello'), '=?iso-8859-1?q?hello?=') + eq(he('hello\nworld'), '=?iso-8859-1?q?hello=0D=0Aworld?=') + # Test the charset option + eq(he('hello', charset='iso-8859-2'), '=?iso-8859-2?q?hello?=') + # Test the keep_eols flag + eq(he('hello\nworld', keep_eols=True), '=?iso-8859-1?q?hello=0Aworld?=') + # Test a non-ASCII character + eq(he('hello\xc7there'), '=?iso-8859-1?q?hello=C7there?=') + # Test the maxlinelen argument + eq(he('xxxx ' * 20, maxlinelen=40), """\ +=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xx?= + =?iso-8859-1?q?xx_xxxx_xxxx_xxxx_xxxx?= + =?iso-8859-1?q?_xxxx_xxxx_xxxx_xxxx_x?= + =?iso-8859-1?q?xxx_xxxx_xxxx_xxxx_xxx?= + =?iso-8859-1?q?x_xxxx_xxxx_?=""") + # Test the eol argument + eq(he('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\ +=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xx?=\r + =?iso-8859-1?q?xx_xxxx_xxxx_xxxx_xxxx?=\r + =?iso-8859-1?q?_xxxx_xxxx_xxxx_xxxx_x?=\r + =?iso-8859-1?q?xxx_xxxx_xxxx_xxxx_xxx?=\r + =?iso-8859-1?q?x_xxxx_xxxx_?=""") + + def test_decode(self): + eq = self.assertEqual + eq(quoprimime.decode(''), '') + eq(quoprimime.decode('hello'), 'hello') + eq(quoprimime.decode('hello', 'X'), 'hello') + eq(quoprimime.decode('hello\nworld', 'X'), 'helloXworld') + + def test_encode(self): + eq = self.assertEqual + eq(quoprimime.encode(''), '') + eq(quoprimime.encode('hello'), 'hello') + # Test the binary flag + eq(quoprimime.encode('hello\r\nworld'), 'hello\nworld') + eq(quoprimime.encode('hello\r\nworld', 0), 'hello\nworld') + # Test the maxlinelen arg + eq(quoprimime.encode('xxxx ' * 20, maxlinelen=40), """\ +xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx= + xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx= +x xxxx xxxx xxxx xxxx=20""") + # Test the eol argument + eq(quoprimime.encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\ +xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=\r + xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=\r +x xxxx xxxx xxxx xxxx=20""") + eq(quoprimime.encode("""\ +one line + +two line"""), """\ +one line + +two line""") + + + +# Test the Charset class +class TestCharset(unittest.TestCase): + def tearDown(self): + from email import charset as CharsetModule + try: + del CharsetModule.CHARSETS['fake'] + except KeyError: + pass + + def test_idempotent(self): + eq = self.assertEqual + # Make sure us-ascii = no Unicode conversion + c = Charset('us-ascii') + s = 'Hello World!' + sp = c.to_splittable(s) + eq(s, c.from_splittable(sp)) + # test 8-bit idempotency with us-ascii + s = '\xa4\xa2\xa4\xa4\xa4\xa6\xa4\xa8\xa4\xaa' + sp = c.to_splittable(s) + eq(s, c.from_splittable(sp)) + + def test_body_encode(self): + eq = self.assertEqual + # Try a charset with QP body encoding + c = Charset('iso-8859-1') + eq('hello w=F6rld', c.body_encode('hello w\xf6rld')) + # Try a charset with Base64 body encoding + c = Charset('utf-8') + eq('aGVsbG8gd29ybGQ=\n', c.body_encode('hello world')) + # Try a charset with None body encoding + c = Charset('us-ascii') + eq('hello world', c.body_encode('hello world')) + # Try the convert argument, where input codec <> output codec + c = Charset('euc-jp') + # With apologies to Tokio Kikuchi ;) + try: + eq('\x1b$B5FCO;~IW\x1b(B', + c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7')) + eq('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', + c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', False)) + except LookupError: + # We probably don't have the Japanese codecs installed + pass + # Testing SF bug #625509, which we have to fake, since there are no + # built-in encodings where the header encoding is QP but the body + # encoding is not. + from email import charset as CharsetModule + CharsetModule.add_charset('fake', CharsetModule.QP, None) + c = Charset('fake') + eq('hello w\xf6rld', c.body_encode('hello w\xf6rld')) + + def test_unicode_charset_name(self): + charset = Charset(u'us-ascii') + self.assertEqual(str(charset), 'us-ascii') + self.assertRaises(errors.CharsetError, Charset, 'asc\xffii') + + + +# Test multilingual MIME headers. +class TestHeader(TestEmailBase): + def test_simple(self): + eq = self.ndiffAssertEqual + h = Header('Hello World!') + eq(h.encode(), 'Hello World!') + h.append(' Goodbye World!') + eq(h.encode(), 'Hello World! Goodbye World!') + + def test_simple_surprise(self): + eq = self.ndiffAssertEqual + h = Header('Hello World!') + eq(h.encode(), 'Hello World!') + h.append('Goodbye World!') + eq(h.encode(), 'Hello World! Goodbye World!') + + def test_header_needs_no_decoding(self): + h = 'no decoding needed' + self.assertEqual(decode_header(h), [(h, None)]) + + def test_long(self): + h = Header("I am the very model of a modern Major-General; I've information vegetable, animal, and mineral; I know the kings of England, and I quote the fights historical from Marathon to Waterloo, in order categorical; I'm very well acquainted, too, with matters mathematical; I understand equations, both the simple and quadratical; about binomial theorem I'm teeming with a lot o' news, with many cheerful facts about the square of the hypotenuse.", + maxlinelen=76) + for l in h.encode(splitchars=' ').split('\n '): + self.failUnless(len(l) <= 76) + + def test_multilingual(self): + eq = self.ndiffAssertEqual + g = Charset("iso-8859-1") + cz = Charset("iso-8859-2") + utf8 = Charset("utf-8") + g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. " + cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. " + utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8") + h = Header(g_head, g) + h.append(cz_head, cz) + h.append(utf8_head, utf8) + enc = h.encode() + eq(enc, """\ +=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerderband_ko?= + =?iso-8859-1?q?mfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndischen_Wan?= + =?iso-8859-1?q?dgem=E4lden_vorbei=2C_gegen_die_rotierenden_Klingen_bef=F6?= + =?iso-8859-1?q?rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se_hroutily?= + =?iso-8859-2?q?_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= =?utf-8?b?5q2j56K6?= + =?utf-8?b?44Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb44KT44CC?= + =?utf-8?b?5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go44Gv44Gn?= + =?utf-8?b?44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBpc3QgZGFz?= + =?utf-8?q?_Nunstuck_git_und_Slotermeyer=3F_Ja!_Beiherhund_das_Oder_die_Fl?= + =?utf-8?b?aXBwZXJ3YWxkdCBnZXJzcHV0LuOAjeOBqOiogOOBo+OBpuOBhOOBvuOBmQ==?= + =?utf-8?b?44CC?=""") + eq(decode_header(enc), + [(g_head, "iso-8859-1"), (cz_head, "iso-8859-2"), + (utf8_head, "utf-8")]) + ustr = unicode(h) + eq(ustr.encode('utf-8'), + 'Die Mieter treten hier ein werden mit einem Foerderband ' + 'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen ' + 'Wandgem\xc3\xa4lden vorbei, gegen die rotierenden Klingen ' + 'bef\xc3\xb6rdert. Finan\xc4\x8dni metropole se hroutily pod ' + 'tlakem jejich d\xc5\xafvtipu.. \xe6\xad\xa3\xe7\xa2\xba\xe3\x81' + '\xab\xe8\xa8\x80\xe3\x81\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3' + '\xe3\x81\xaf\xe3\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3' + '\x81\xbe\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83' + '\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8\xaa\x9e' + '\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81\xe3\x81\x82\xe3' + '\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81\x9f\xe3\x82\x89\xe3\x82' + '\x81\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\xe5\xae\x9f\xe9\x9a\x9b' + '\xe3\x81\xab\xe3\x81\xaf\xe3\x80\x8cWenn ist das Nunstuck git ' + 'und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt ' + 'gersput.\xe3\x80\x8d\xe3\x81\xa8\xe8\xa8\x80\xe3\x81\xa3\xe3\x81' + '\xa6\xe3\x81\x84\xe3\x81\xbe\xe3\x81\x99\xe3\x80\x82') + # Test make_header() + newh = make_header(decode_header(enc)) + eq(newh, enc) + + def test_header_ctor_default_args(self): + eq = self.ndiffAssertEqual + h = Header() + eq(h, '') + h.append('foo', Charset('iso-8859-1')) + eq(h, '=?iso-8859-1?q?foo?=') + + def test_explicit_maxlinelen(self): + eq = self.ndiffAssertEqual + hstr = 'A very long line that must get split to something other than at the 76th character boundary to test the non-default behavior' + h = Header(hstr) + eq(h.encode(), '''\ +A very long line that must get split to something other than at the 76th + character boundary to test the non-default behavior''') + h = Header(hstr, header_name='Subject') + eq(h.encode(), '''\ +A very long line that must get split to something other than at the + 76th character boundary to test the non-default behavior''') + h = Header(hstr, maxlinelen=1024, header_name='Subject') + eq(h.encode(), hstr) + + def test_us_ascii_header(self): + eq = self.assertEqual + s = 'hello' + x = decode_header(s) + eq(x, [('hello', None)]) + h = make_header(x) + eq(s, h.encode()) + + def test_string_charset(self): + eq = self.assertEqual + h = Header() + h.append('hello', 'iso-8859-1') + eq(h, '=?iso-8859-1?q?hello?=') + +## def test_unicode_error(self): +## raises = self.assertRaises +## raises(UnicodeError, Header, u'[P\xf6stal]', 'us-ascii') +## raises(UnicodeError, Header, '[P\xf6stal]', 'us-ascii') +## h = Header() +## raises(UnicodeError, h.append, u'[P\xf6stal]', 'us-ascii') +## raises(UnicodeError, h.append, '[P\xf6stal]', 'us-ascii') +## raises(UnicodeError, Header, u'\u83ca\u5730\u6642\u592b', 'iso-8859-1') + + def test_utf8_shortest(self): + eq = self.assertEqual + h = Header(u'p\xf6stal', 'utf-8') + eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=') + h = Header(u'\u83ca\u5730\u6642\u592b', 'utf-8') + eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=') + + def test_bad_8bit_header(self): + raises = self.assertRaises + eq = self.assertEqual + x = 'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big' + raises(UnicodeError, Header, x) + h = Header() + raises(UnicodeError, h.append, x) + eq(str(Header(x, errors='replace')), x) + h.append(x, errors='replace') + eq(str(h), x) + + def test_encoded_adjacent_nonencoded(self): + eq = self.assertEqual + h = Header() + h.append('hello', 'iso-8859-1') + h.append('world') + s = h.encode() + eq(s, '=?iso-8859-1?q?hello?= world') + h = make_header(decode_header(s)) + eq(h.encode(), s) + + def test_whitespace_eater(self): + eq = self.assertEqual + s = 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztk=?= =?koi8-r?q?=CA?= zz.' + parts = decode_header(s) + eq(parts, [('Subject:', None), ('\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1 \xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), ('zz.', None)]) + hdr = make_header(parts) + eq(hdr.encode(), + 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztnK?= zz.') + + def test_broken_base64_header(self): + raises = self.assertRaises + s = 'Subject: =?EUC-KR?B?CSixpLDtKSC/7Liuvsax4iC6uLmwMcijIKHaILzSwd/H0SC8+LCjwLsgv7W/+Mj3IQ?=' + raises(errors.HeaderParseError, decode_header, s) + + + +# Test RFC 2231 header parameters (en/de)coding +class TestRFC2231(TestEmailBase): + def test_get_param(self): + eq = self.assertEqual + msg = self._msgobj('msg_29.txt') + eq(msg.get_param('title'), + ('us-ascii', 'en', 'This is even more ***fun*** isn\'t it!')) + eq(msg.get_param('title', unquote=False), + ('us-ascii', 'en', '"This is even more ***fun*** isn\'t it!"')) + + def test_set_param(self): + eq = self.assertEqual + msg = Message() + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii') + eq(msg.get_param('title'), + ('us-ascii', '', 'This is even more ***fun*** isn\'t it!')) + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii', language='en') + eq(msg.get_param('title'), + ('us-ascii', 'en', 'This is even more ***fun*** isn\'t it!')) + msg = self._msgobj('msg_01.txt') + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii', language='en') + eq(msg.as_string(), """\ +Return-Path: +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) +\tid 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 +Content-Type: text/plain; charset=us-ascii; +\ttitle*="us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21" + + +Hi, + +Do you like this message? + +-Me +""") + + def test_del_param(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_01.txt') + msg.set_param('foo', 'bar', charset='us-ascii', language='en') + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii', language='en') + msg.del_param('foo', header='Content-Type') + eq(msg.as_string(), """\ +Return-Path: +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) +\tid 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 +Content-Type: text/plain; charset="us-ascii"; +\ttitle*="us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21" + + +Hi, + +Do you like this message? + +-Me +""") + + def test_rfc2231_get_content_charset(self): + eq = self.assertEqual + msg = self._msgobj('msg_32.txt') + eq(msg.get_content_charset(), 'us-ascii') + + def test_rfc2231_no_language_or_charset(self): + m = '''\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename="file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm" +Content-Type: text/html; NAME*0=file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEM; NAME*1=P_nsmail.htm + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_param('NAME'), + (None, None, 'file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm')) + + def test_rfc2231_no_language_or_charset_in_filename(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0="This%20is%20even%20more%20"; +\tfilename*1="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + + def test_rfc2231_no_language_or_charset_in_boundary(self): + m = '''\ +Content-Type: multipart/alternative; +\tboundary*0="This%20is%20even%20more%20"; +\tboundary*1="%2A%2A%2Afun%2A%2A%2A%20"; +\tboundary*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_boundary(), + 'This is even more ***fun*** is it not.pdf') + + def test_rfc2231_no_language_or_charset_in_charset(self): + # This is a nonsensical charset value, but tests the code anyway + m = '''\ +Content-Type: text/plain; +\tcharset*0="This%20is%20even%20more%20"; +\tcharset*1="%2A%2A%2Afun%2A%2A%2A%20"; +\tcharset*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_content_charset(), + 'this is even more ***fun*** is it not.pdf') + + def test_rfc2231_unknown_encoding(self): + m = """\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename*0=X-UNKNOWN''myfile.txt + +""" + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), 'myfile.txt') + + + +def _testclasses(): + mod = sys.modules[__name__] + return [getattr(mod, name) for name in dir(mod) if name.startswith('Test')] + + +def suite(): + suite = unittest.TestSuite() + for testclass in _testclasses(): + suite.addTest(unittest.makeSuite(testclass)) + return suite + + +def test_main(): + for testclass in _testclasses(): + run_unittest(testclass) + + + +if __name__ == '__main__': + unittest.main(defaultTest='suite') diff --git a/Lib/email/Utils.py b/Lib/email/utils.py similarity index 96% rename from Lib/email/Utils.py rename to Lib/email/utils.py index 9ba76011615..250eb19d930 100644 --- a/Lib/email/Utils.py +++ b/Lib/email/utils.py @@ -1,9 +1,24 @@ -# Copyright (C) 2001-2004 Python Software Foundation +# Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Miscellaneous utilities.""" +__all__ = [ + 'collapse_rfc2231_value', + 'decode_params', + 'decode_rfc2231', + 'encode_rfc2231', + 'formataddr', + 'formatdate', + 'getaddresses', + 'make_msgid', + 'parseaddr', + 'parsedate', + 'parsedate_tz', + 'unquote', + ] + import os import re import time @@ -24,7 +39,7 @@ from email._parseaddr import parsedate_tz as _parsedate_tz from quopri import decodestring as _qdecode # Intrapackage imports -from email.Encoders import _bencode, _qencode +from email.encoders import _bencode, _qencode COMMASPACE = ', ' EMPTYSTRING = '' diff --git a/Lib/test/test_pyclbr.py b/Lib/test/test_pyclbr.py index ceb7a3d1707..87572ca038e 100644 --- a/Lib/test/test_pyclbr.py +++ b/Lib/test/test_pyclbr.py @@ -170,7 +170,7 @@ class PyclbrTest(TestCase): cm('pydoc') # Tests for modules inside packages - cm('email.Parser') + cm('email.parser') cm('test.test_pyclbr')