From 40ef0067ad5af2458c54cc0316831ddb701ea3fd Mon Sep 17 00:00:00 2001 From: Barry Warsaw Date: Sat, 18 Mar 2006 15:41:53 +0000 Subject: Merge email package 4.0 from the sandbox, including documentation, test cases, and NEWS updates. --- Doc/lib/email-dir.py | 131 +- Doc/lib/email-mime.py | 6 +- Doc/lib/email-simple.py | 2 +- Doc/lib/email-unpack.py | 65 +- 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/Charset.py | 370 ---- Lib/email/Encoders.py | 78 - Lib/email/Errors.py | 53 - Lib/email/FeedParser.py | 477 ----- Lib/email/Generator.py | 352 --- Lib/email/Header.py | 495 ----- Lib/email/Iterators.py | 67 - Lib/email/MIMEAudio.py | 72 - Lib/email/MIMEBase.py | 24 - Lib/email/MIMEImage.py | 45 - Lib/email/MIMEMessage.py | 32 - Lib/email/MIMEMultipart.py | 39 - Lib/email/MIMENonMultipart.py | 24 - Lib/email/MIMEText.py | 28 - Lib/email/Message.py | 814 ------- Lib/email/Parser.py | 88 - Lib/email/Utils.py | 291 --- Lib/email/__init__.py | 77 +- Lib/email/_parseaddr.py | 7 + Lib/email/base64MIME.py | 172 -- Lib/email/base64mime.py | 184 ++ Lib/email/charset.py | 388 ++++ Lib/email/encoders.py | 88 + Lib/email/errors.py | 57 + Lib/email/feedparser.py | 480 +++++ Lib/email/generator.py | 348 +++ Lib/email/header.py | 502 +++++ Lib/email/iterators.py | 73 + Lib/email/message.py | 773 +++++++ Lib/email/mime/__init__.py | 0 Lib/email/mime/application.py | 36 + Lib/email/mime/audio.py | 73 + Lib/email/mime/base.py | 26 + Lib/email/mime/image.py | 46 + Lib/email/mime/message.py | 34 + Lib/email/mime/multipart.py | 41 + Lib/email/mime/nonmultipart.py | 26 + Lib/email/mime/text.py | 30 + Lib/email/parser.py | 91 + Lib/email/quopriMIME.py | 318 --- Lib/email/quoprimime.py | 336 +++ 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 | 306 +++ Lib/test/test_pyclbr.py | 2 +- 63 files changed, 7515 insertions(+), 4162 deletions(-) delete mode 100644 Lib/email/Charset.py delete mode 100644 Lib/email/Encoders.py delete mode 100644 Lib/email/Errors.py delete mode 100644 Lib/email/FeedParser.py delete mode 100644 Lib/email/Generator.py delete mode 100644 Lib/email/Header.py delete mode 100644 Lib/email/Iterators.py delete mode 100644 Lib/email/MIMEAudio.py delete mode 100644 Lib/email/MIMEBase.py delete mode 100644 Lib/email/MIMEImage.py delete mode 100644 Lib/email/MIMEMessage.py delete mode 100644 Lib/email/MIMEMultipart.py delete mode 100644 Lib/email/MIMENonMultipart.py delete mode 100644 Lib/email/MIMEText.py delete mode 100644 Lib/email/Message.py delete mode 100644 Lib/email/Parser.py delete mode 100644 Lib/email/Utils.py delete mode 100644 Lib/email/base64MIME.py create mode 100644 Lib/email/base64mime.py create mode 100644 Lib/email/charset.py create mode 100644 Lib/email/encoders.py create mode 100644 Lib/email/errors.py create mode 100644 Lib/email/feedparser.py create mode 100644 Lib/email/generator.py create mode 100644 Lib/email/header.py create mode 100644 Lib/email/iterators.py create mode 100644 Lib/email/message.py create mode 100644 Lib/email/mime/__init__.py create mode 100644 Lib/email/mime/application.py create mode 100644 Lib/email/mime/audio.py create mode 100644 Lib/email/mime/base.py create mode 100644 Lib/email/mime/image.py create mode 100644 Lib/email/mime/message.py create mode 100644 Lib/email/mime/multipart.py create mode 100644 Lib/email/mime/nonmultipart.py create mode 100644 Lib/email/mime/text.py create mode 100644 Lib/email/parser.py delete mode 100644 Lib/email/quopriMIME.py create mode 100644 Lib/email/quoprimime.py create mode 100644 Lib/email/test/test_email_codecs_renamed.py create mode 100644 Lib/email/test/test_email_renamed.py create mode 100644 Lib/email/utils.py diff --git a/Doc/lib/email-dir.py b/Doc/lib/email-dir.py index 2d89a2f..c04f57d 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 - -COMMASPACE = ', ' +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 -def usage(code, msg=''): - print >> sys.stderr, __doc__ - if msg: - print >> sys.stderr, msg - sys.exit(code) +COMMASPACE = ', ' def main(): - try: - opts, args = getopt.getopt(sys.argv[1:], 'hd:', ['help', 'directory=']) - except getopt.error, msg: - usage(1, msg) - - 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:] - + parser = OptionParser(usage="""\ +Send the contents of a directory as a MIME message. + +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 048a59f..5097253 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 a445f1b..44152a4 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 b166fdb..fc05d99 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) - - dir = os.curdir - for opt, arg in opts: - if opt in ('-h', '--help'): - usage(0) - elif opt in ('-d', '--directory'): - dir = arg + parser = OptionParser(usage="""\ +Unpack a MIME message into a directory of files. + +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 3a90e22..6853325 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 18f2a01..e0be68a 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 a49e04d..3d05c2a 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 6ac0889..3cef1d5 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 330abc0..3415442 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 2795644b..524d08c 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 d1a8f98..ef8ef6f 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 9b41852..7bd7dd8 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 070c9a2..4735be3 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 5fac92f..609fa40 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 491a2b9..fe96473 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 67de597..491d844 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/Charset.py b/Lib/email/Charset.py deleted file mode 100644 index fd4043b..0000000 --- a/Lib/email/Charset.py +++ /dev/null @@ -1,370 +0,0 @@ -# Copyright (C) 2001-2006 Python Software Foundation -# Author: Ben Gertzfield, Barry Warsaw -# Contact: email-sig@python.org - -import email.base64MIME -import email.quopriMIME -from email.Encoders import encode_7or8bit - - - -# Flags for types of header encodings -QP = 1 # Quoted-Printable -BASE64 = 2 # Base64 -SHORTEST = 3 # the shorter of QP and base64, but only for headers - -# In "=?charset?q?hello_world?=", the =?, ?q?, and ?= add up to 7 -MISC_LEN = 7 - -DEFAULT_CHARSET = 'us-ascii' - - - -# Defaults -CHARSETS = { - # input header enc body enc output conv - 'iso-8859-1': (QP, QP, None), - 'iso-8859-2': (QP, QP, None), - 'iso-8859-3': (QP, QP, None), - 'iso-8859-4': (QP, QP, None), - # iso-8859-5 is Cyrillic, and not especially used - # iso-8859-6 is Arabic, also not particularly used - # iso-8859-7 is Greek, QP will not make it readable - # iso-8859-8 is Hebrew, QP will not make it readable - 'iso-8859-9': (QP, QP, None), - 'iso-8859-10': (QP, QP, None), - # iso-8859-11 is Thai, QP will not make it readable - 'iso-8859-13': (QP, QP, None), - 'iso-8859-14': (QP, QP, None), - 'iso-8859-15': (QP, QP, None), - 'windows-1252':(QP, QP, None), - 'viscii': (QP, QP, None), - 'us-ascii': (None, None, None), - 'big5': (BASE64, BASE64, None), - 'gb2312': (BASE64, BASE64, None), - 'euc-jp': (BASE64, None, 'iso-2022-jp'), - 'shift_jis': (BASE64, None, 'iso-2022-jp'), - 'iso-2022-jp': (BASE64, None, None), - 'koi8-r': (BASE64, BASE64, None), - 'utf-8': (SHORTEST, BASE64, 'utf-8'), - # We're making this one up to represent raw unencoded 8-bit - '8bit': (None, BASE64, 'utf-8'), - } - -# Aliases for other commonly-used names for character sets. Map -# them to the real ones used in email. -ALIASES = { - 'latin_1': 'iso-8859-1', - 'latin-1': 'iso-8859-1', - 'latin_2': 'iso-8859-2', - 'latin-2': 'iso-8859-2', - 'latin_3': 'iso-8859-3', - 'latin-3': 'iso-8859-3', - 'latin_4': 'iso-8859-4', - 'latin-4': 'iso-8859-4', - 'latin_5': 'iso-8859-9', - 'latin-5': 'iso-8859-9', - 'latin_6': 'iso-8859-10', - 'latin-6': 'iso-8859-10', - 'latin_7': 'iso-8859-13', - 'latin-7': 'iso-8859-13', - 'latin_8': 'iso-8859-14', - 'latin-8': 'iso-8859-14', - 'latin_9': 'iso-8859-15', - 'latin-9': 'iso-8859-15', - 'cp949': 'ks_c_5601-1987', - 'euc_jp': 'euc-jp', - 'euc_kr': 'euc-kr', - 'ascii': 'us-ascii', - } - - -# Map charsets to their Unicode codec strings. -CODEC_MAP = { - 'gb2312': 'eucgb2312_cn', - 'big5': 'big5_tw', - # Hack: We don't want *any* conversion for stuff marked us-ascii, as all - # sorts of garbage might be sent to us in the guise of 7-bit us-ascii. - # Let that stuff pass through without conversion to/from Unicode. - 'us-ascii': None, - } - - - -# Convenience functions for extending the above mappings -def add_charset(charset, header_enc=None, body_enc=None, output_charset=None): - """Add character set properties to the global registry. - - charset is the input character set, and must be the canonical name of a - character set. - - Optional header_enc and body_enc is either Charset.QP for - quoted-printable, Charset.BASE64 for base64 encoding, Charset.SHORTEST for - the shortest of qp or base64 encoding, or None for no encoding. SHORTEST - is only valid for header_enc. It describes how message headers and - message bodies in the input charset are to be encoded. Default is no - encoding. - - Optional output_charset is the character set that the output should be - in. Conversions will proceed from input charset, to Unicode, to the - output charset when the method Charset.convert() is called. The default - is to output in the same character set as the input. - - Both input_charset and output_charset must have Unicode codec entries in - the module's charset-to-codec mapping; use add_codec(charset, codecname) - to add codecs the module does not know about. See the codecs module's - documentation for more information. - """ - if body_enc == SHORTEST: - raise ValueError('SHORTEST not allowed for body_enc') - CHARSETS[charset] = (header_enc, body_enc, output_charset) - - -def add_alias(alias, canonical): - """Add a character set alias. - - alias is the alias name, e.g. latin-1 - canonical is the character set's canonical name, e.g. iso-8859-1 - """ - ALIASES[alias] = canonical - - -def add_codec(charset, codecname): - """Add a codec that map characters in the given charset to/from Unicode. - - charset is the canonical name of a character set. codecname is the name - of a Python codec, as appropriate for the second argument to the unicode() - built-in, or to the encode() method of a Unicode string. - """ - CODEC_MAP[charset] = codecname - - - -class Charset: - """Map character sets to their email properties. - - This class provides information about the requirements imposed on email - for a specific character set. It also provides convenience routines for - converting between character sets, given the availability of the - applicable codecs. Given a character set, it will do its best to provide - information on how to use that character set in an email in an - RFC-compliant way. - - Certain character sets must be encoded with quoted-printable or base64 - when used in email headers or bodies. Certain character sets must be - converted outright, and are not allowed in email. Instances of this - module expose the following information about a character set: - - input_charset: The initial character set specified. Common aliases - are converted to their `official' email names (e.g. latin_1 - is converted to iso-8859-1). Defaults to 7-bit us-ascii. - - header_encoding: If the character set must be encoded before it can be - used in an email header, this attribute will be set to - Charset.QP (for quoted-printable), Charset.BASE64 (for - base64 encoding), or Charset.SHORTEST for the shortest of - QP or BASE64 encoding. Otherwise, it will be None. - - body_encoding: Same as header_encoding, but describes the encoding for the - mail message's body, which indeed may be different than the - header encoding. Charset.SHORTEST is not allowed for - body_encoding. - - output_charset: Some character sets must be converted before the can be - used in email headers or bodies. If the input_charset is - one of them, this attribute will contain the name of the - charset output will be converted to. Otherwise, it will - be None. - - input_codec: The name of the Python codec used to convert the - input_charset to Unicode. If no conversion codec is - necessary, this attribute will be None. - - output_codec: The name of the Python codec used to convert Unicode - to the output_charset. If no conversion codec is necessary, - this attribute will have the same value as the input_codec. - """ - 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() - # 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 - # charset_map dictionary. Try that first, but let the user override - # it. - henc, benc, conv = CHARSETS.get(self.input_charset, - (SHORTEST, BASE64, None)) - if not conv: - conv = self.input_charset - # Set the attributes, allowing the arguments to override the default. - self.header_encoding = henc - self.body_encoding = benc - self.output_charset = ALIASES.get(conv, conv) - # Now set the codecs. If one isn't defined for input_charset, - # guess and try a Unicode codec with the same name as input_codec. - self.input_codec = CODEC_MAP.get(self.input_charset, - self.input_charset) - self.output_codec = CODEC_MAP.get(self.output_charset, - self.output_charset) - - def __str__(self): - return self.input_charset.lower() - - __repr__ = __str__ - - def __eq__(self, other): - return str(self) == str(other).lower() - - def __ne__(self, other): - return not self.__eq__(other) - - def get_body_encoding(self): - """Return the content-transfer-encoding used for body encoding. - - This is either the string `quoted-printable' or `base64' depending on - the encoding used, or it is a function in which case you should call - the function with a single argument, the Message object being - encoded. The function should then set the Content-Transfer-Encoding - header itself to whatever is appropriate. - - Returns "quoted-printable" if self.body_encoding is QP. - Returns "base64" if self.body_encoding is BASE64. - Returns "7bit" otherwise. - """ - assert self.body_encoding <> SHORTEST - if self.body_encoding == QP: - return 'quoted-printable' - elif self.body_encoding == BASE64: - return 'base64' - else: - return encode_7or8bit - - def convert(self, s): - """Convert a string from the input_codec to the output_codec.""" - if self.input_codec <> self.output_codec: - return unicode(s, self.input_codec).encode(self.output_codec) - else: - return s - - def to_splittable(self, s): - """Convert a possibly multibyte string to a safely splittable format. - - Uses the input_codec to try and convert the string to Unicode, so it - can be safely split on character boundaries (even for multibyte - characters). - - Returns the string as-is if it isn't known how to convert it to - Unicode with the input_charset. - - Characters that could not be converted to Unicode will be replaced - with the Unicode replacement character U+FFFD. - """ - if isinstance(s, unicode) or self.input_codec is None: - return s - try: - return unicode(s, self.input_codec, 'replace') - except LookupError: - # Input codec not installed on system, so return the original - # string unchanged. - return s - - def from_splittable(self, ustr, to_output=True): - """Convert a splittable string back into an encoded string. - - Uses the proper codec to try and convert the string from Unicode back - into an encoded format. Return the string as-is if it is not Unicode, - or if it could not be converted from Unicode. - - Characters that could not be converted from Unicode will be replaced - with an appropriate character (usually '?'). - - If to_output is True (the default), uses output_codec to convert to an - encoded format. If to_output is False, uses input_codec. - """ - if to_output: - codec = self.output_codec - else: - codec = self.input_codec - if not isinstance(ustr, unicode) or codec is None: - return ustr - try: - return ustr.encode(codec, 'replace') - except LookupError: - # Output codec not installed - return ustr - - def get_output_charset(self): - """Return the output character set. - - This is self.output_charset if that is not None, otherwise it is - self.input_charset. - """ - return self.output_charset or self.input_charset - - def encoded_header_len(self, s): - """Return the length of the encoded header string.""" - 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 - elif self.header_encoding == QP: - 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) - return min(lenb64, lenqp) + len(cset) + MISC_LEN - else: - return len(s) - - def header_encode(self, s, convert=False): - """Header-encode a string, optionally converting it to output_charset. - - If convert is True, the string will be converted from the input - charset to the output charset automatically. This is not useful for - multibyte character sets, which have line length issues (multibyte - characters must be split on a character, not a byte boundary); use the - high-level Header class to deal with these issues. convert defaults - to False. - - The type of encoding (base64 or quoted-printable) will be based on - self.header_encoding. - """ - cset = self.get_output_charset() - if convert: - 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) - elif self.header_encoding == QP: - 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) - if lenb64 < lenqp: - return email.base64MIME.header_encode(s, cset) - else: - return email.quopriMIME.header_encode(s, cset, maxlinelen=None) - else: - return s - - def body_encode(self, s, convert=True): - """Body-encode a string and convert it to output_charset. - - If convert is True (the default), the string will be converted from - the input charset to output charset automatically. Unlike - header_encode(), there are no issues with byte boundaries and - multibyte charsets in email bodies, so this is usually pretty safe. - - The type of encoding (base64 or quoted-printable) will be based on - self.body_encoding. - """ - if convert: - 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) - elif self.body_encoding is QP: - return email.quopriMIME.body_encode(s) - else: - return s diff --git a/Lib/email/Encoders.py b/Lib/email/Encoders.py deleted file mode 100644 index baac2a3..0000000 --- a/Lib/email/Encoders.py +++ /dev/null @@ -1,78 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Encodings and related functions.""" - -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 - return enc.replace(' ', '=20') - - -def _bencode(s): - # We can't quite use base64.encodestring() since it tacks on a "courtesy - # newline". Blech! - if not s: - return s - hasnewline = (s[-1] == '\n') - value = base64.encodestring(s) - if not hasnewline and value[-1] == '\n': - return value[:-1] - return value - - - -def encode_base64(msg): - """Encode the message's payload in Base64. - - Also, add an appropriate Content-Transfer-Encoding header. - """ - orig = msg.get_payload() - encdata = _bencode(orig) - msg.set_payload(encdata) - msg['Content-Transfer-Encoding'] = 'base64' - - - -def encode_quopri(msg): - """Encode the message's payload in quoted-printable. - - Also, add an appropriate Content-Transfer-Encoding header. - """ - orig = msg.get_payload() - encdata = _qencode(orig) - msg.set_payload(encdata) - msg['Content-Transfer-Encoding'] = 'quoted-printable' - - - -def encode_7or8bit(msg): - """Set the Content-Transfer-Encoding header to 7bit or 8bit.""" - orig = msg.get_payload() - if orig is None: - # There's no payload. For backwards compatibility we use 7bit - msg['Content-Transfer-Encoding'] = '7bit' - return - # We play a trick to make this go fast. If encoding to ASCII succeeds, we - # know the data must be 7bit, otherwise treat it as 8bit. - try: - orig.encode('ascii') - except UnicodeError: - # iso-2022-* is non-ASCII but still 7-bit - charset = msg.get_charset() - output_cset = charset and charset.output_charset - if output_cset and output_cset.lower().startswith('iso-2202-'): - msg['Content-Transfer-Encoding'] = '7bit' - else: - msg['Content-Transfer-Encoding'] = '8bit' - else: - msg['Content-Transfer-Encoding'] = '7bit' - - - -def encode_noop(msg): - """Do nothing.""" diff --git a/Lib/email/Errors.py b/Lib/email/Errors.py deleted file mode 100644 index e13a2c7..0000000 --- a/Lib/email/Errors.py +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""email package exception classes.""" - - - -class MessageError(Exception): - """Base class for errors in the email package.""" - - -class MessageParseError(MessageError): - """Base class for message parsing errors.""" - - -class HeaderParseError(MessageParseError): - """Error while parsing headers.""" - - -class BoundaryError(MessageParseError): - """Couldn't find terminating boundary.""" - - -class MultipartConversionError(MessageError, TypeError): - """Conversion to a multipart is prohibited.""" - - - -# These are parsing defects which the parser was able to work around. -class MessageDefect: - """Base class for a message defect.""" - - def __init__(self, line=None): - self.line = line - -class NoBoundaryInMultipartDefect(MessageDefect): - """A message claimed to be a multipart but had no boundary parameter.""" - -class StartBoundaryNotFoundDefect(MessageDefect): - """The claimed start boundary was never found.""" - -class FirstHeaderLineIsContinuationDefect(MessageDefect): - """A message had a continuation line as its first header line.""" - -class MisplacedEnvelopeHeaderDefect(MessageDefect): - """A 'Unix-from' header was found in the middle of a header block.""" - -class MalformedHeaderDefect(MessageDefect): - """Found a header that was missing a colon, or was otherwise malformed.""" - -class MultipartInvariantViolationDefect(MessageDefect): - """A message claimed to be a multipart but no subparts were found.""" diff --git a/Lib/email/FeedParser.py b/Lib/email/FeedParser.py deleted file mode 100644 index a2130e2..0000000 --- a/Lib/email/FeedParser.py +++ /dev/null @@ -1,477 +0,0 @@ -# Copyright (C) 2004-2006 Python Software Foundation -# Authors: Baxter, Wouters and Warsaw -# Contact: email-sig@python.org - -"""FeedParser - An email feed parser. - -The feed parser implements an interface for incrementally parsing an email -message, line by line. This has advantages for certain applications, such as -those reading email messages off a socket. - -FeedParser.feed() is the primary interface for pushing new data into the -parser. It returns when there's nothing more it can do with the available -data. When you have no more data to push into the parser, call .close(). -This completes the parsing and returns the root message object. - -The other advantage of this parser is that it will never throw a parsing -exception. Instead, when it finds something unexpected, it adds a 'defect' to -the current message. Defects are just instances that live on the message -object's .defects attribute. -""" - -import re -from email import Errors -from email import Message - -NLCRE = re.compile('\r\n|\r|\n') -NLCRE_bol = re.compile('(\r\n|\r|\n)') -NLCRE_eol = re.compile('(\r\n|\r|\n)$') -NLCRE_crack = re.compile('(\r\n|\r|\n)') -# RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character -# except controls, SP, and ":". -headerRE = re.compile(r'^(From |[\041-\071\073-\176]{1,}:|[\t ])') -EMPTYSTRING = '' -NL = '\n' - -NeedMoreData = object() - - - -class BufferedSubFile(object): - """A file-ish object that can have new data loaded into it. - - You can also push and pop line-matching predicates onto a stack. When the - current predicate matches the current line, a false EOF response - (i.e. empty string) is returned instead. This lets the parser adhere to a - simple abstraction -- it parses until EOF closes the current message. - """ - def __init__(self): - # The last partial line pushed into this object. - self._partial = '' - # The list of full, pushed lines, in reverse order - self._lines = [] - # The stack of false-EOF checking predicates. - self._eofstack = [] - # A flag indicating whether the file has been closed or not. - self._closed = False - - def push_eof_matcher(self, pred): - self._eofstack.append(pred) - - def pop_eof_matcher(self): - return self._eofstack.pop() - - def close(self): - # Don't forget any trailing partial line. - self._lines.append(self._partial) - self._partial = '' - self._closed = True - - def readline(self): - if not self._lines: - if self._closed: - return '' - return NeedMoreData - # Pop the line off the stack and see if it matches the current - # false-EOF predicate. - line = self._lines.pop() - # RFC 2046, section 5.1.2 requires us to recognize outer level - # boundaries at any level of inner nesting. Do this, but be sure it's - # in the order of most to least nested. - for ateof in self._eofstack[::-1]: - if ateof(line): - # We're at the false EOF. But push the last line back first. - self._lines.append(line) - return '' - return line - - def unreadline(self, line): - # Let the consumer push a line back into the buffer. - assert line is not NeedMoreData - self._lines.append(line) - - def push(self, data): - """Push some new data into this object.""" - # Handle any previous leftovers - data, self._partial = self._partial + data, '' - # Crack into lines, but preserve the newlines on the end of each - parts = NLCRE_crack.split(data) - # The *ahem* interesting behaviour of re.split when supplied grouping - # parentheses is that the last element of the resulting list is the - # data after the final RE. In the case of a NL/CR terminated string, - # this is the empty string. - self._partial = parts.pop() - # parts is a list of strings, alternating between the line contents - # and the eol character(s). Gather up a list of lines after - # re-attaching the newlines. - lines = [] - for i in range(len(parts) // 2): - lines.append(parts[i*2] + parts[i*2+1]) - self.pushlines(lines) - - def pushlines(self, lines): - # Reverse and insert at the front of the lines. - self._lines[:0] = lines[::-1] - - def is_closed(self): - return self._closed - - def __iter__(self): - return self - - def next(self): - line = self.readline() - if line == '': - raise StopIteration - return line - - - -class FeedParser: - """A feed-style parser of email.""" - - def __init__(self, _factory=Message.Message): - """_factory is called with no arguments to create a new message obj""" - self._factory = _factory - self._input = BufferedSubFile() - self._msgstack = [] - self._parse = self._parsegen().next - self._cur = None - self._last = None - self._headersonly = False - - # Non-public interface for supporting Parser's headersonly flag - def _set_headersonly(self): - self._headersonly = True - - def feed(self, data): - """Push more data into the parser.""" - self._input.push(data) - self._call_parse() - - def _call_parse(self): - try: - self._parse() - except StopIteration: - pass - - def close(self): - """Parse all remaining data and return the root message object.""" - self._input.close() - self._call_parse() - root = self._pop_message() - assert not self._msgstack - # Look for final set of defects - if root.get_content_maintype() == 'multipart' \ - and not root.is_multipart(): - root.defects.append(Errors.MultipartInvariantViolationDefect()) - return root - - def _new_message(self): - msg = self._factory() - if self._cur and self._cur.get_content_type() == 'multipart/digest': - msg.set_default_type('message/rfc822') - if self._msgstack: - self._msgstack[-1].attach(msg) - self._msgstack.append(msg) - self._cur = msg - self._last = msg - - def _pop_message(self): - retval = self._msgstack.pop() - if self._msgstack: - self._cur = self._msgstack[-1] - else: - self._cur = None - return retval - - def _parsegen(self): - # Create a new message and start by parsing headers. - self._new_message() - headers = [] - # Collect the headers, searching for a line that doesn't match the RFC - # 2822 header or continuation pattern (including an empty line). - for line in self._input: - if line is NeedMoreData: - yield NeedMoreData - continue - if not headerRE.match(line): - # If we saw the RFC defined header/body separator - # (i.e. newline), just throw it away. Otherwise the line is - # part of the body so push it back. - if not NLCRE.match(line): - self._input.unreadline(line) - break - headers.append(line) - # Done with the headers, so parse them and figure out what we're - # supposed to see in the body of the message. - self._parse_headers(headers) - # Headers-only parsing is a backwards compatibility hack, which was - # necessary in the older parser, which could throw errors. All - # remaining lines in the input are thrown into the message body. - if self._headersonly: - lines = [] - while True: - line = self._input.readline() - if line is NeedMoreData: - yield NeedMoreData - continue - if line == '': - break - lines.append(line) - self._cur.set_payload(EMPTYSTRING.join(lines)) - return - if self._cur.get_content_type() == 'message/delivery-status': - # message/delivery-status contains blocks of headers separated by - # a blank line. We'll represent each header block as a separate - # nested message object, but the processing is a bit different - # than standard message/* types because there is no body for the - # nested messages. A blank line separates the subparts. - while True: - self._input.push_eof_matcher(NLCRE.match) - for retval in self._parsegen(): - if retval is NeedMoreData: - yield NeedMoreData - continue - break - msg = self._pop_message() - # We need to pop the EOF matcher in order to tell if we're at - # the end of the current file, not the end of the last block - # of message headers. - self._input.pop_eof_matcher() - # The input stream must be sitting at the newline or at the - # EOF. We want to see if we're at the end of this subpart, so - # first consume the blank line, then test the next line to see - # if we're at this subpart's EOF. - while True: - line = self._input.readline() - if line is NeedMoreData: - yield NeedMoreData - continue - break - while True: - line = self._input.readline() - if line is NeedMoreData: - yield NeedMoreData - continue - break - if line == '': - break - # Not at EOF so this is a line we're going to need. - self._input.unreadline(line) - return - if self._cur.get_content_maintype() == 'message': - # The message claims to be a message/* type, then what follows is - # another RFC 2822 message. - for retval in self._parsegen(): - if retval is NeedMoreData: - yield NeedMoreData - continue - break - self._pop_message() - return - if self._cur.get_content_maintype() == 'multipart': - boundary = self._cur.get_boundary() - if boundary is None: - # The message /claims/ to be a multipart but it has not - # 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()) - lines = [] - for line in self._input: - if line is NeedMoreData: - yield NeedMoreData - continue - lines.append(line) - self._cur.set_payload(EMPTYSTRING.join(lines)) - return - # Create a line match predicate which matches the inter-part - # boundary as well as the end-of-multipart boundary. Don't push - # this onto the input stream until we've scanned past the - # preamble. - separator = '--' + boundary - boundaryre = re.compile( - '(?P' + re.escape(separator) + - r')(?P--)?(?P[ \t]*)(?P\r\n|\r|\n)?$') - capturing_preamble = True - preamble = [] - linesep = False - while True: - line = self._input.readline() - if line is NeedMoreData: - yield NeedMoreData - continue - if line == '': - break - mo = boundaryre.match(line) - if mo: - # If we're looking at the end boundary, we're done with - # this multipart. If there was a newline at the end of - # the closing boundary, then we need to initialize the - # epilogue with the empty string (see below). - if mo.group('end'): - linesep = mo.group('linesep') - break - # We saw an inter-part boundary. Were we in the preamble? - if capturing_preamble: - if preamble: - # According to RFC 2046, the last newline belongs - # to the boundary. - lastline = preamble[-1] - eolmo = NLCRE_eol.search(lastline) - if eolmo: - preamble[-1] = lastline[:-len(eolmo.group(0))] - self._cur.preamble = EMPTYSTRING.join(preamble) - capturing_preamble = False - self._input.unreadline(line) - continue - # We saw a boundary separating two parts. Consume any - # multiple boundary lines that may be following. Our - # interpretation of RFC 2046 BNF grammar does not produce - # body parts within such double boundaries. - while True: - line = self._input.readline() - if line is NeedMoreData: - yield NeedMoreData - continue - mo = boundaryre.match(line) - if not mo: - self._input.unreadline(line) - break - # Recurse to parse this subpart; the input stream points - # at the subpart's first line. - self._input.push_eof_matcher(boundaryre.match) - for retval in self._parsegen(): - if retval is NeedMoreData: - yield NeedMoreData - continue - break - # Because of RFC 2046, the newline preceding the boundary - # separator actually belongs to the boundary, not the - # previous subpart's payload (or epilogue if the previous - # part is a multipart). - if self._last.get_content_maintype() == 'multipart': - epilogue = self._last.epilogue - if epilogue == '': - self._last.epilogue = None - elif epilogue is not None: - mo = NLCRE_eol.search(epilogue) - if mo: - end = len(mo.group(0)) - self._last.epilogue = epilogue[:-end] - else: - payload = self._last.get_payload() - if isinstance(payload, basestring): - mo = NLCRE_eol.search(payload) - if mo: - payload = payload[:-len(mo.group(0))] - self._last.set_payload(payload) - self._input.pop_eof_matcher() - self._pop_message() - # Set the multipart up for newline cleansing, which will - # happen if we're in a nested multipart. - self._last = self._cur - else: - # I think we must be in the preamble - assert capturing_preamble - preamble.append(line) - # We've seen either the EOF or the end boundary. If we're still - # capturing the preamble, we never saw the start boundary. Note - # 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.set_payload(EMPTYSTRING.join(preamble)) - epilogue = [] - for line in self._input: - if line is NeedMoreData: - yield NeedMoreData - continue - self._cur.epilogue = EMPTYSTRING.join(epilogue) - return - # If the end boundary ended in a newline, we'll need to make sure - # the epilogue isn't None - if linesep: - epilogue = [''] - else: - epilogue = [] - for line in self._input: - if line is NeedMoreData: - yield NeedMoreData - continue - epilogue.append(line) - # Any CRLF at the front of the epilogue is not technically part of - # the epilogue. Also, watch out for an empty string epilogue, - # which means a single newline. - if epilogue: - firstline = epilogue[0] - bolmo = NLCRE_bol.match(firstline) - if bolmo: - epilogue[0] = firstline[len(bolmo.group(0)):] - self._cur.epilogue = EMPTYSTRING.join(epilogue) - return - # Otherwise, it's some non-multipart type, so the entire rest of the - # file contents becomes the payload. - lines = [] - for line in self._input: - if line is NeedMoreData: - yield NeedMoreData - continue - lines.append(line) - self._cur.set_payload(EMPTYSTRING.join(lines)) - - def _parse_headers(self, lines): - # Passed a list of lines that make up the headers for the current msg - lastheader = '' - lastvalue = [] - for lineno, line in enumerate(lines): - # Check for continuation - if line[0] in ' \t': - if not lastheader: - # 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) - self._cur.defects.append(defect) - continue - lastvalue.append(line) - continue - if lastheader: - # XXX reconsider the joining of folded lines - lhdr = EMPTYSTRING.join(lastvalue)[:-1].rstrip('\r\n') - self._cur[lastheader] = lhdr - lastheader, lastvalue = '', [] - # Check for envelope header, i.e. unix-from - if line.startswith('From '): - if lineno == 0: - # Strip off the trailing newline - mo = NLCRE_eol.search(line) - if mo: - line = line[:-len(mo.group(0))] - self._cur.set_unixfrom(line) - continue - elif lineno == len(lines) - 1: - # Something looking like a unix-from at the end - it's - # probably the first line of the body, so push back the - # line and stop. - self._input.unreadline(line) - return - else: - # Weirdly placed unix-from line. Note this as a defect - # and ignore it. - 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) - self._cur.defects.append(defect) - continue - lastheader = line[:i] - lastvalue = [line[i+1:].lstrip()] - # Done with all the lines, so handle the last header. - if lastheader: - # XXX reconsider the joining of folded lines - self._cur[lastheader] = EMPTYSTRING.join(lastvalue).rstrip('\r\n') diff --git a/Lib/email/Generator.py b/Lib/email/Generator.py deleted file mode 100644 index 7969916..0000000 --- a/Lib/email/Generator.py +++ /dev/null @@ -1,352 +0,0 @@ -# Copyright (C) 2001-2006 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Classes to generate plain text from a message object tree.""" - -import re -import sys -import time -import random -import warnings -from cStringIO import StringIO - -from email.Header import Header - -UNDERSCORE = '_' -NL = '\n' - -fcre = re.compile(r'^From ', re.MULTILINE) - -def _is8bitstring(s): - if isinstance(s, str): - try: - unicode(s, 'us-ascii') - except UnicodeError: - return True - return False - - - -class Generator: - """Generates output from a Message object tree. - - This basic generator writes the message to the given file object as plain - text. - """ - # - # Public interface - # - - def __init__(self, outfp, mangle_from_=True, maxheaderlen=78): - """Create the generator for message flattening. - - outfp is the output file-like object for writing the message to. It - must have a write() method. - - Optional mangle_from_ is a flag that, when True (the default), escapes - From_ lines in the body of the message by putting a `>' in front of - them. - - Optional maxheaderlen specifies the longest length for a non-continued - header. When a header line is longer (in characters, with tabs - expanded to 8 spaces) than maxheaderlen, the header will split as - defined in the Header class. Set maxheaderlen to zero to disable - header wrapping. The default is 78, as recommended (but not required) - by RFC 2822. - """ - self._fp = outfp - self._mangle_from_ = mangle_from_ - self._maxheaderlen = maxheaderlen - - def write(self, s): - # Just delegate to the file object - self._fp.write(s) - - def flatten(self, msg, unixfrom=False): - """Print the message object tree rooted at msg to the output file - specified when the Generator instance was created. - - unixfrom is a flag that forces the printing of a Unix From_ delimiter - before the first object in the message tree. If the original message - has no From_ delimiter, a `standard' one is crafted. By default, this - is False to inhibit the printing of any From_ delimiter. - - Note that for subobjects, no From_ line is printed. - """ - if unixfrom: - ufrom = msg.get_unixfrom() - if not ufrom: - ufrom = 'From nobody ' + time.ctime(time.time()) - 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) - - # - # Protected interface - undocumented ;/ - # - - def _write(self, msg): - # We can't write the headers yet because of the following scenario: - # say a multipart message includes the boundary string somewhere in - # its body. We'd have to calculate the new boundary /before/ we write - # the headers so that we can write the correct Content-Type: - # parameter. - # - # The way we do this, so as to make the _handle_*() methods simpler, - # is to cache any subpart writes into a StringIO. The we write the - # headers and the StringIO contents. That way, subpart handlers can - # Do The Right Thing, and can still modify the Content-Type: header if - # necessary. - oldfp = self._fp - try: - self._fp = sfp = StringIO() - self._dispatch(msg) - finally: - self._fp = oldfp - # Write the headers. First we see if the message object wants to - # handle that itself. If not, we'll do it generically. - meth = getattr(msg, '_write_headers', None) - if meth is None: - self._write_headers(msg) - else: - meth(self) - self._fp.write(sfp.getvalue()) - - def _dispatch(self, msg): - # Get the Content-Type: for the message, then try to dispatch to - # self._handle__(). If there's no handler for the - # full MIME type, then dispatch to self._handle_(). If - # that's missing too, then dispatch to self._writeBody(). - main = msg.get_content_maintype() - sub = msg.get_content_subtype() - specific = UNDERSCORE.join((main, sub)).replace('-', '_') - meth = getattr(self, '_handle_' + specific, None) - if meth is None: - generic = main.replace('-', '_') - meth = getattr(self, '_handle_' + generic, None) - if meth is None: - meth = self._writeBody - meth(msg) - - # - # Default handlers - # - - def _write_headers(self, msg): - for h, v in msg.items(): - print >> self._fp, '%s:' % h, - if self._maxheaderlen == 0: - # Explicit no-wrapping - print >> self._fp, v - elif isinstance(v, Header): - # Header instances know what to do - print >> self._fp, v.encode() - elif _is8bitstring(v): - # If we have raw 8bit data in a byte string, we have no idea - # what the encoding is. There is no safe way to split this - # string. If it's ascii-subset, then we could do a normal - # ascii split, but if it's multibyte then we could break the - # string. There's no way to know so the least harm seems to - # be to not split the string and risk it being too long. - print >> self._fp, v - else: - # Header's got lots of smarts, so use it. - print >> self._fp, Header( - v, maxlinelen=self._maxheaderlen, - header_name=h, continuation_ws='\t').encode() - # A blank line always separates headers from body - print >> self._fp - - # - # Handlers for writing types and subtypes - # - - def _handle_text(self, msg): - payload = msg.get_payload() - if payload is None: - return - if not isinstance(payload, basestring): - raise TypeError('string payload expected: %s' % type(payload)) - if self._mangle_from_: - payload = fcre.sub('>From ', payload) - self._fp.write(payload) - - # Default body handler - _writeBody = _handle_text - - def _handle_multipart(self, msg): - # The trick here is to write out each part separately, merge them all - # together, and then make sure that the boundary we've chosen isn't - # present in the payload. - msgtexts = [] - subparts = msg.get_payload() - if subparts is None: - subparts = [] - elif isinstance(subparts, basestring): - # e.g. a non-strict parse of a message with no starting boundary. - self._fp.write(subparts) - return - elif not isinstance(subparts, list): - # Scalar payload - subparts = [subparts] - for part in subparts: - s = StringIO() - g = self.clone(s) - g.flatten(part, unixfrom=False) - msgtexts.append(s.getvalue()) - # Now make sure the boundary we've selected doesn't appear in any of - # the message texts. - alltext = NL.join(msgtexts) - # BAW: What about boundaries that are wrapped in double-quotes? - boundary = msg.get_boundary(failobj=_make_boundary(alltext)) - # If we had to calculate a new boundary because the body text - # contained that string, set the new boundary. We don't do it - # unconditionally because, while set_boundary() preserves order, it - # doesn't preserve newlines/continuations in headers. This is no big - # deal in practice, but turns out to be inconvenient for the unittest - # suite. - if msg.get_boundary() <> boundary: - msg.set_boundary(boundary) - # If there's a preamble, write it out, with a trailing CRLF - if msg.preamble is not None: - print >> self._fp, msg.preamble - # dash-boundary transport-padding CRLF - print >> self._fp, '--' + boundary - # body-part - if msgtexts: - self._fp.write(msgtexts.pop(0)) - # *encapsulation - # --> delimiter transport-padding - # --> CRLF body-part - for body_part in msgtexts: - # delimiter transport-padding CRLF - print >> self._fp, '\n--' + boundary - # body-part - self._fp.write(body_part) - # close-delimiter transport-padding - self._fp.write('\n--' + boundary + '--') - if msg.epilogue is not None: - print >> self._fp - self._fp.write(msg.epilogue) - - def _handle_message_delivery_status(self, msg): - # We can't just write the headers directly to self's file object - # because this will leave an extra newline between the last header - # block and the boundary. Sigh. - blocks = [] - for part in msg.get_payload(): - s = StringIO() - g = self.clone(s) - g.flatten(part, unixfrom=False) - text = s.getvalue() - lines = text.split('\n') - # Strip off the unnecessary trailing empty line - if lines and lines[-1] == '': - blocks.append(NL.join(lines[:-1])) - else: - blocks.append(text) - # Now join all the blocks with an empty line. This has the lovely - # effect of separating each block with an empty line, but not adding - # an extra one after the last one. - self._fp.write(NL.join(blocks)) - - def _handle_message(self, msg): - s = StringIO() - g = self.clone(s) - # The payload of a message/rfc822 part should be a multipart sequence - # of length 1. The zeroth element of the list should be the Message - # object for the subpart. Extract that object, stringify it, and - # write it out. - g.flatten(msg.get_payload(0), unixfrom=False) - self._fp.write(s.getvalue()) - - - -_FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]' - -class DecodedGenerator(Generator): - """Generator a text representation of a message. - - Like the Generator base class, except that non-text parts are substituted - with a format string representing the part. - """ - def __init__(self, outfp, mangle_from_=True, maxheaderlen=78, fmt=None): - """Like Generator.__init__() except that an additional optional - argument is allowed. - - Walks through all subparts of a message. If the subpart is of main - type `text', then it prints the decoded payload of the subpart. - - Otherwise, fmt is a format string that is used instead of the message - payload. fmt is expanded with the following keywords (in - %(keyword)s format): - - type : Full MIME type of the non-text part - maintype : Main MIME type of the non-text part - subtype : Sub-MIME type of the non-text part - filename : Filename of the non-text part - description: Description associated with the non-text part - encoding : Content transfer encoding of the non-text part - - The default value for fmt is None, meaning - - [Non-text (%(type)s) part of message omitted, filename %(filename)s] - """ - Generator.__init__(self, outfp, mangle_from_, maxheaderlen) - if fmt is None: - self._fmt = _FMT - else: - self._fmt = fmt - - def _dispatch(self, msg): - for part in msg.walk(): - maintype = part.get_content_maintype() - if maintype == 'text': - print >> self, part.get_payload(decode=True) - elif maintype == 'multipart': - # Just skip this - pass - else: - print >> self, self._fmt % { - 'type' : part.get_content_type(), - 'maintype' : part.get_content_maintype(), - 'subtype' : part.get_content_subtype(), - 'filename' : part.get_filename('[no filename]'), - 'description': part.get('Content-Description', - '[no description]'), - 'encoding' : part.get('Content-Transfer-Encoding', - '[no encoding]'), - } - - - -# Helper -_width = len(repr(sys.maxint-1)) -_fmt = '%%0%dd' % _width - -def _make_boundary(text=None): - # Craft a random boundary. If text is given, ensure that the chosen - # boundary doesn't appear in the text. - token = random.randrange(sys.maxint) - boundary = ('=' * 15) + (_fmt % token) + '==' - if text is None: - return boundary - b = boundary - counter = 0 - while True: - cre = re.compile('^--' + re.escape(b) + '(--)?$', re.MULTILINE) - if not cre.search(text): - break - b = boundary + '.' + str(counter) - counter += 1 - return b diff --git a/Lib/email/Header.py b/Lib/email/Header.py deleted file mode 100644 index 5e24afe..0000000 --- a/Lib/email/Header.py +++ /dev/null @@ -1,495 +0,0 @@ -# Copyright (C) 2002-2004 Python Software Foundation -# Author: Ben Gertzfield, Barry Warsaw -# Contact: email-sig@python.org - -"""Header encoding and decoding functionality.""" - -import re -import binascii - -import email.quopriMIME -import email.base64MIME -from email.Errors import HeaderParseError -from email.Charset import Charset - -NL = '\n' -SPACE = ' ' -USPACE = u' ' -SPACE8 = ' ' * 8 -UEMPTYSTRING = u'' - -MAXLINELEN = 76 - -USASCII = Charset('us-ascii') -UTF8 = Charset('utf-8') - -# Match encoded-word strings in the form =?charset?q?Hello_World?= -ecre = re.compile(r''' - =\? # literal =? - (?P[^?]*?) # non-greedy up to the next ? is the charset - \? # literal ? - (?P[qb]) # either a "q" or a "b", case insensitive - \? # literal ? - (?P.*?) # non-greedy up to the next ?= is the encoded string - \?= # literal ?= - ''', re.VERBOSE | re.IGNORECASE) - -# Field name regexp, including trailing colon, but not separating whitespace, -# according to RFC 2822. Character range is from tilde to exclamation mark. -# For use with .match() -fcre = re.compile(r'[\041-\176]+:$') - - - -# Helpers -_max_append = email.quopriMIME._max_append - - - -def decode_header(header): - """Decode a message header value without converting charset. - - Returns a list of (decoded_string, charset) pairs containing each of the - decoded parts of the header. Charset is None for non-encoded parts of the - header, otherwise a lower-case string containing the name of the character - set specified in the encoded string. - - An email.Errors.HeaderParseError may be raised when certain decoding error - occurs (e.g. a base64 decoding exception). - """ - # If no encoding, just return the header - header = str(header) - if not ecre.search(header): - return [(header, None)] - decoded = [] - dec = '' - for line in header.splitlines(): - # This line might not have an encoding in it - if not ecre.search(line): - decoded.append((line, None)) - continue - parts = ecre.split(line) - while parts: - unenc = parts.pop(0).strip() - if unenc: - # Should we continue a long line? - if decoded and decoded[-1][1] is None: - decoded[-1] = (decoded[-1][0] + SPACE + unenc, None) - else: - decoded.append((unenc, None)) - if parts: - charset, encoding = [s.lower() for s in parts[0:2]] - encoded = parts[2] - dec = None - if encoding == 'q': - dec = email.quopriMIME.header_decode(encoded) - elif encoding == 'b': - try: - 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 - # when/if we get exception chaining, we'll preserve it. - raise HeaderParseError - if dec is None: - dec = encoded - - if decoded and decoded[-1][1] == charset: - decoded[-1] = (decoded[-1][0] + dec, decoded[-1][1]) - else: - decoded.append((dec, charset)) - del parts[0:3] - return decoded - - - -def make_header(decoded_seq, maxlinelen=None, header_name=None, - continuation_ws=' '): - """Create a Header from a sequence of pairs as returned by decode_header() - - decode_header() takes a header value string and returns a sequence of - pairs of the format (decoded_string, charset) where charset is the string - name of the character set. - - This function takes one of those sequence of pairs and returns a Header - instance. Optional maxlinelen, header_name, and continuation_ws are as in - the Header constructor. - """ - h = Header(maxlinelen=maxlinelen, header_name=header_name, - continuation_ws=continuation_ws) - for s, charset in decoded_seq: - # None means us-ascii but we can simply pass it on to h.append() - if charset is not None and not isinstance(charset, Charset): - charset = Charset(charset) - h.append(s, charset) - return h - - - -class Header: - def __init__(self, s=None, charset=None, - maxlinelen=None, header_name=None, - continuation_ws=' ', errors='strict'): - """Create a MIME-compliant header that can contain many character sets. - - Optional s is the initial header value. If None, the initial header - value is not set. You can later append to the header with .append() - method calls. s may be a byte string or a Unicode string, but see the - .append() documentation for semantics. - - Optional charset serves two purposes: it has the same meaning as the - charset argument to the .append() method. It also sets the default - character set for all subsequent .append() calls that omit the charset - argument. If charset is not provided in the constructor, the us-ascii - charset is used both as s's initial charset and as the default for - subsequent .append() calls. - - The maximum line length can be specified explicit via maxlinelen. For - splitting the first line to a shorter value (to account for the field - header which isn't included in s, e.g. `Subject') pass in the name of - the field in header_name. The default maxlinelen is 76. - - continuation_ws must be RFC 2822 compliant folding whitespace (usually - either a space or a hard tab) which will be prepended to continuation - lines. - - errors is passed through to the .append() call. - """ - if charset is None: - charset = USASCII - if not isinstance(charset, Charset): - charset = Charset(charset) - self._charset = charset - self._continuation_ws = continuation_ws - cws_expanded_len = len(continuation_ws.replace('\t', SPACE8)) - # BAW: I believe `chunks' and `maxlinelen' should be non-public. - self._chunks = [] - if s is not None: - self.append(s, charset, errors) - if maxlinelen is None: - maxlinelen = MAXLINELEN - if header_name is None: - # We don't know anything about the field header so the first line - # is the same length as subsequent lines. - self._firstlinelen = maxlinelen - else: - # The first line should be shorter to take into account the field - # header. Also subtract off 2 extra for the colon and space. - self._firstlinelen = maxlinelen - len(header_name) - 2 - # Second and subsequent lines should subtract off the length in - # columns of the continuation whitespace prefix. - self._maxlinelen = maxlinelen - cws_expanded_len - - def __str__(self): - """A synonym for self.encode().""" - return self.encode() - - def __unicode__(self): - """Helper for the built-in unicode function.""" - uchunks = [] - lastcs = None - for s, charset in self._chunks: - # We must preserve spaces between encoded and non-encoded word - # boundaries, which means for us we need to add a space when we go - # from a charset to None/us-ascii, or from None/us-ascii to a - # charset. Only do this for the second and subsequent chunks. - nextcs = charset - if uchunks: - if lastcs not in (None, 'us-ascii'): - if nextcs in (None, 'us-ascii'): - uchunks.append(USPACE) - nextcs = None - elif nextcs not in (None, 'us-ascii'): - uchunks.append(USPACE) - lastcs = nextcs - uchunks.append(unicode(s, str(charset))) - return UEMPTYSTRING.join(uchunks) - - # Rich comparison operators for equality only. BAW: does it make sense to - # have or explicitly disable <, <=, >, >= operators? - def __eq__(self, other): - # other may be a Header or a string. Both are fine so coerce - # ourselves to a string, swap the args and do another comparison. - return other == self.encode() - - def __ne__(self, other): - return not self == other - - def append(self, s, charset=None, errors='strict'): - """Append a string to the MIME header. - - Optional charset, if given, should be a Charset instance or the name - of a character set (which will be converted to a Charset instance). A - value of None (the default) means that the charset given in the - constructor is used. - - s may be a byte string or a Unicode string. If it is a byte string - (i.e. isinstance(s, str) is true), then charset is the encoding of - that byte string, and a UnicodeError will be raised if the string - cannot be decoded with that charset. If s is a Unicode string, then - charset is a hint specifying the character set of the characters in - the string. In this case, when producing an RFC 2822 compliant header - using RFC 2047 rules, the Unicode string will be encoded using the - following charsets in order: us-ascii, the charset hint, utf-8. The - first character set not to provoke a UnicodeError is used. - - Optional `errors' is passed as the third argument to any unicode() or - ustr.encode() call. - """ - if charset is None: - charset = self._charset - elif not isinstance(charset, Charset): - charset = Charset(charset) - # If the charset is our faux 8bit charset, leave the string unchanged - if charset <> '8bit': - # We need to test that the string can be converted to unicode and - # back to a byte string, given the input and output codecs of the - # charset. - if isinstance(s, str): - # Possibly raise UnicodeError if the byte string can't be - # converted to a unicode with the input codec of the charset. - incodec = charset.input_codec or 'us-ascii' - ustr = unicode(s, incodec, errors) - # Now make sure that the unicode could be converted back to a - # byte string with the output codec, which may be different - # than the iput coded. Still, use the original byte string. - outcodec = charset.output_codec or 'us-ascii' - ustr.encode(outcodec, errors) - elif isinstance(s, unicode): - # Now we have to be sure the unicode string can be converted - # to a byte string with a reasonable output codec. We want to - # use the byte string in the chunk. - for charset in USASCII, charset, UTF8: - try: - outcodec = charset.output_codec or 'us-ascii' - s = s.encode(outcodec, errors) - break - except UnicodeError: - pass - else: - assert False, 'utf-8 conversion failed' - self._chunks.append((s, charset)) - - def _split(self, s, charset, maxlinelen, splitchars): - # Split up a header safely for use with encode_chunks. - splittable = charset.to_splittable(s) - encoded = charset.from_splittable(splittable, True) - elen = charset.encoded_header_len(encoded) - # If the line's encoded length first, just return it - if elen <= maxlinelen: - return [(encoded, charset)] - # If we have undetermined raw 8bit characters sitting in a byte - # string, we really don't know what the right thing to do is. We - # can't really split it because it might be multibyte data which we - # could break if we split it between pairs. The least harm seems to - # be to not split the header at all, but that means they could go out - # longer than maxlinelen. - if charset == '8bit': - return [(s, charset)] - # BAW: I'm not sure what the right test here is. What we're trying to - # do is be faithful to RFC 2822's recommendation that ($2.2.3): - # - # "Note: Though structured field bodies are defined in such a way that - # folding can take place between many of the lexical tokens (and even - # within some of the lexical tokens), folding SHOULD be limited to - # placing the CRLF at higher-level syntactic breaks." - # - # For now, I can only imagine doing this when the charset is us-ascii, - # although it's possible that other charsets may also benefit from the - # higher-level syntactic breaks. - elif charset == 'us-ascii': - return self._split_ascii(s, charset, maxlinelen, splitchars) - # BAW: should we use encoded? - elif elen == len(s): - # We can split on _maxlinelen boundaries because we know that the - # encoding won't change the size of the string - splitpnt = maxlinelen - first = charset.from_splittable(splittable[:splitpnt], False) - last = charset.from_splittable(splittable[splitpnt:], False) - else: - # Binary search for split point - first, last = _binsplit(splittable, charset, maxlinelen) - # first is of the proper length so just wrap it in the appropriate - # chrome. last must be recursively split. - fsplittable = charset.to_splittable(first) - fencoded = charset.from_splittable(fsplittable, True) - chunk = [(fencoded, charset)] - return chunk + self._split(last, charset, self._maxlinelen, splitchars) - - def _split_ascii(self, s, charset, firstlen, splitchars): - chunks = _split_ascii(s, firstlen, self._maxlinelen, - self._continuation_ws, splitchars) - return zip(chunks, [charset]*len(chunks)) - - def _encode_chunks(self, newchunks, maxlinelen): - # MIME-encode a header with many different charsets and/or encodings. - # - # Given a list of pairs (string, charset), return a MIME-encoded - # string suitable for use in a header field. Each pair may have - # different charsets and/or encodings, and the resulting header will - # accurately reflect each setting. - # - # Each encoding can be email.Utils.QP (quoted-printable, for - # ASCII-like character sets like iso-8859-1), email.Utils.BASE64 - # (Base64, for non-ASCII like character sets like KOI8-R and - # iso-2022-jp), or None (no encoding). - # - # Each pair will be represented on a separate line; the resulting - # string will be in the format: - # - # =?charset1?q?Mar=EDa_Gonz=E1lez_Alonso?=\n - # =?charset2?b?SvxyZ2VuIEL2aW5n?=" - chunks = [] - for header, charset in newchunks: - if not header: - continue - if charset is None or charset.header_encoding is None: - s = header - else: - s = charset.header_encode(header) - # Don't add more folding whitespace than necessary - if chunks and chunks[-1].endswith(' '): - extra = '' - else: - extra = ' ' - _max_append(chunks, s, maxlinelen, extra) - joiner = NL + self._continuation_ws - return joiner.join(chunks) - - def encode(self, splitchars=';, '): - """Encode a message header into an RFC-compliant format. - - There are many issues involved in converting a given string for use in - an email header. Only certain character sets are readable in most - email clients, and as header strings can only contain a subset of - 7-bit ASCII, care must be taken to properly convert and encode (with - Base64 or quoted-printable) header strings. In addition, there is a - 75-character length limit on any given encoded header field, so - line-wrapping must be performed, even with double-byte character sets. - - This method will do its best to convert the string to the correct - character set used in email, and encode and line wrap it safely with - the appropriate scheme for that character set. - - If the given charset is not known or an error occurs during - conversion, this function will return the header untouched. - - Optional splitchars is a string containing characters to split long - ASCII lines on, in rough support of RFC 2822's `highest level - syntactic breaks'. This doesn't affect RFC 2047 encoded lines. - """ - newchunks = [] - maxlinelen = self._firstlinelen - lastlen = 0 - for s, charset in self._chunks: - # The first bit of the next chunk should be just long enough to - # fill the next line. Don't forget the space separating the - # encoded words. - targetlen = maxlinelen - lastlen - 1 - if targetlen < charset.encoded_header_len(''): - # Stick it on the next line - targetlen = maxlinelen - newchunks += self._split(s, charset, targetlen, splitchars) - lastchunk, lastcharset = newchunks[-1] - lastlen = lastcharset.encoded_header_len(lastchunk) - return self._encode_chunks(newchunks, maxlinelen) - - - -def _split_ascii(s, firstlen, restlen, continuation_ws, splitchars): - lines = [] - maxlen = firstlen - for line in s.splitlines(): - # Ignore any leading whitespace (i.e. continuation whitespace) already - # on the line, since we'll be adding our own. - line = line.lstrip() - if len(line) < maxlen: - lines.append(line) - maxlen = restlen - continue - # Attempt to split the line at the highest-level syntactic break - # possible. Note that we don't have a lot of smarts about field - # syntax; we just try to break on semi-colons, then commas, then - # whitespace. - for ch in splitchars: - if ch in line: - break - else: - # There's nothing useful to split the line on, not even spaces, so - # just append this line unchanged - lines.append(line) - maxlen = restlen - continue - # Now split the line on the character plus trailing whitespace - cre = re.compile(r'%s\s*' % ch) - if ch in ';,': - eol = ch - else: - eol = '' - joiner = eol + ' ' - joinlen = len(joiner) - wslen = len(continuation_ws.replace('\t', SPACE8)) - this = [] - linelen = 0 - for part in cre.split(line): - curlen = linelen + max(0, len(this)-1) * joinlen - partlen = len(part) - onfirstline = not lines - # We don't want to split after the field name, if we're on the - # first line and the field name is present in the header string. - if ch == ' ' and onfirstline and \ - len(this) == 1 and fcre.match(this[0]): - this.append(part) - linelen += partlen - elif curlen + partlen > maxlen: - if this: - lines.append(joiner.join(this) + eol) - # If this part is longer than maxlen and we aren't already - # splitting on whitespace, try to recursively split this line - # on whitespace. - if partlen > maxlen and ch <> ' ': - subl = _split_ascii(part, maxlen, restlen, - continuation_ws, ' ') - lines.extend(subl[:-1]) - this = [subl[-1]] - else: - this = [part] - linelen = wslen + len(this[-1]) - maxlen = restlen - else: - this.append(part) - linelen += partlen - # Put any left over parts on a line by themselves - if this: - lines.append(joiner.join(this)) - return lines - - - -def _binsplit(splittable, charset, maxlinelen): - i = 0 - j = len(splittable) - while i < j: - # Invariants: - # 1. splittable[:k] fits for all k <= i (note that we *assume*, - # at the start, that splittable[:0] fits). - # 2. splittable[:k] does not fit for any k > j (at the start, - # this means we shouldn't look at any k > len(splittable)). - # 3. We don't know about splittable[:k] for k in i+1..j. - # 4. We want to set i to the largest k that fits, with i <= k <= j. - # - m = (i+j+1) >> 1 # ceiling((i+j)/2); i < m <= j - chunk = charset.from_splittable(splittable[:m], True) - chunklen = charset.encoded_header_len(chunk) - if chunklen <= maxlinelen: - # m is acceptable, so is a new lower bound. - i = m - else: - # m is not acceptable, so final i must be < m. - j = m - 1 - # i == j. Invariant #1 implies that splittable[:i] fits, and - # invariant #2 implies that splittable[:i+1] does not fit, so i - # is what we're looking for. - first = charset.from_splittable(splittable[:i], False) - last = charset.from_splittable(splittable[i:], False) - return first, last diff --git a/Lib/email/Iterators.py b/Lib/email/Iterators.py deleted file mode 100644 index 74a93c7..0000000 --- a/Lib/email/Iterators.py +++ /dev/null @@ -1,67 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Various types of useful iterators and generators.""" - -import sys -from cStringIO import StringIO - - - -# This function will become a method of the Message class -def walk(self): - """Walk over the message tree, yielding each subpart. - - The walk is performed in depth-first order. This method is a - generator. - """ - yield self - if self.is_multipart(): - for subpart in self.get_payload(): - for subsubpart in subpart.walk(): - yield subsubpart - - - -# 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. - - Optional decode (default False) is passed through to .get_payload(). - """ - for subpart in msg.walk(): - payload = subpart.get_payload(decode=decode) - if isinstance(payload, basestring): - for line in StringIO(payload): - yield line - - -def typed_subpart_iterator(msg, maintype='text', subtype=None): - """Iterate over the subparts with a given MIME type. - - Use `maintype' as the main MIME type to match against; this defaults to - "text". Optional `subtype' is the MIME subtype to match against; if - omitted, only the main type is matched. - """ - for subpart in msg.walk(): - if subpart.get_content_maintype() == maintype: - if subtype is None or subpart.get_content_subtype() == subtype: - yield subpart - - - -def _structure(msg, fp=None, level=0, include_default=False): - """A handy debugging aid""" - if fp is None: - fp = sys.stdout - tab = ' ' * (level * 4) - print >> fp, tab + msg.get_content_type(), - if include_default: - print >> fp, '[%s]' % msg.get_default_type() - else: - print >> fp - if msg.is_multipart(): - for subpart in msg.get_payload(): - _structure(subpart, fp, level+1, include_default) diff --git a/Lib/email/MIMEAudio.py b/Lib/email/MIMEAudio.py deleted file mode 100644 index 266ec4c..0000000 --- a/Lib/email/MIMEAudio.py +++ /dev/null @@ -1,72 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Anthony Baxter -# Contact: email-sig@python.org - -"""Class representing audio/* type MIME documents.""" - -import sndhdr -from cStringIO import StringIO - -from email import Errors -from email import Encoders -from email.MIMENonMultipart import MIMENonMultipart - - - -_sndhdr_MIMEmap = {'au' : 'basic', - 'wav' :'x-wav', - 'aiff':'x-aiff', - 'aifc':'x-aiff', - } - -# There are others in sndhdr that don't have MIME types. :( -# Additional ones to be added to sndhdr? midi, mp3, realaudio, wma?? -def _whatsnd(data): - """Try to identify a sound file type. - - sndhdr.what() has a pretty cruddy interface, unfortunately. This is why - we re-do it here. It would be easier to reverse engineer the Unix 'file' - command and use the standard 'magic' file, as shipped with a modern Unix. - """ - hdr = data[:512] - fakefile = StringIO(hdr) - for testfn in sndhdr.tests: - res = testfn(hdr, fakefile) - if res is not None: - return _sndhdr_MIMEmap.get(res[0]) - return None - - - -class MIMEAudio(MIMENonMultipart): - """Class for generating audio/* MIME documents.""" - - def __init__(self, _audiodata, _subtype=None, - _encoder=Encoders.encode_base64, **_params): - """Create an audio/* type MIME document. - - _audiodata is a string containing the raw audio data. If this data - can be decoded by the standard Python `sndhdr' module, then the - subtype will be automatically included in the Content-Type header. - Otherwise, you can specify the specific audio subtype via the - _subtype parameter. If _subtype is not given, and no subtype can be - guessed, a TypeError is raised. - - _encoder is a function which will perform the actual encoding for - transport of the image data. It takes one argument, which is this - Image instance. It should use get_payload() and set_payload() to - change the payload to the encoded form. It should also add any - Content-Transfer-Encoding or other headers to the message as - necessary. The default encoding is Base64. - - 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: - _subtype = _whatsnd(_audiodata) - if _subtype is None: - raise TypeError('Could not find audio MIME subtype') - MIMENonMultipart.__init__(self, 'audio', _subtype, **_params) - self.set_payload(_audiodata) - _encoder(self) diff --git a/Lib/email/MIMEBase.py b/Lib/email/MIMEBase.py deleted file mode 100644 index 88691f8..0000000 --- a/Lib/email/MIMEBase.py +++ /dev/null @@ -1,24 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Base class for MIME specializations.""" - -from email import Message - - - -class MIMEBase(Message.Message): - """Base class for MIME specializations.""" - - def __init__(self, _maintype, _subtype, **_params): - """This constructor adds a Content-Type: and a MIME-Version: header. - - The Content-Type: header is taken from the _maintype and _subtype - arguments. Additional parameters for this header are taken from the - keyword arguments. - """ - 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/MIMEImage.py deleted file mode 100644 index a658067..0000000 --- a/Lib/email/MIMEImage.py +++ /dev/null @@ -1,45 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Class representing image/* type MIME documents.""" - -import imghdr - -from email import Errors -from email import Encoders -from email.MIMENonMultipart import MIMENonMultipart - - - -class MIMEImage(MIMENonMultipart): - """Class for generating image/* type MIME documents.""" - - def __init__(self, _imagedata, _subtype=None, - _encoder=Encoders.encode_base64, **_params): - """Create an image/* type MIME document. - - _imagedata is a string containing the raw image data. If this data - can be decoded by the standard Python `imghdr' module, then the - subtype will be automatically included in the Content-Type header. - Otherwise, you can specify the specific image subtype via the _subtype - parameter. - - _encoder is a function which will perform the actual encoding for - transport of the image data. It takes one argument, which is this - Image instance. It should use get_payload() and set_payload() to - change the payload to the encoded form. It should also add any - Content-Transfer-Encoding or other headers to the message as - necessary. The default encoding is Base64. - - 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: - _subtype = imghdr.what(None, _imagedata) - if _subtype is None: - raise TypeError('Could not guess image MIME subtype') - MIMENonMultipart.__init__(self, 'image', _subtype, **_params) - self.set_payload(_imagedata) - _encoder(self) diff --git a/Lib/email/MIMEMessage.py b/Lib/email/MIMEMessage.py deleted file mode 100644 index 3021934..0000000 --- a/Lib/email/MIMEMessage.py +++ /dev/null @@ -1,32 +0,0 @@ -# Copyright (C) 2001-2004 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 - - - -class MIMEMessage(MIMENonMultipart): - """Class representing message/* MIME documents.""" - - def __init__(self, _msg, _subtype='rfc822'): - """Create a message/* type MIME document. - - _msg is a message object and must be an instance of Message, or a - derived class of Message, otherwise a TypeError is raised. - - Optional _subtype defines the subtype of the contained message. The - default is "rfc822" (this is defined by the MIME standard, even though - the term "rfc822" is technically outdated by RFC 2822). - """ - MIMENonMultipart.__init__(self, 'message', _subtype) - 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) - # 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/MIMEMultipart.py deleted file mode 100644 index 9072a64..0000000 --- a/Lib/email/MIMEMultipart.py +++ /dev/null @@ -1,39 +0,0 @@ -# Copyright (C) 2002-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Base class for MIME multipart/* type messages.""" - -from email import MIMEBase - - - -class MIMEMultipart(MIMEBase.MIMEBase): - """Base class for MIME multipart/* type messages.""" - - def __init__(self, _subtype='mixed', boundary=None, _subparts=None, - **_params): - """Creates a multipart/* type message. - - By default, creates a multipart/mixed message, with proper - Content-Type and MIME-Version headers. - - _subtype is the subtype of the multipart content type, defaulting to - `mixed'. - - boundary is the multipart boundary string. By default it is - calculated as needed. - - _subparts is a sequence of initial subparts for the payload. It - must be an iterable object, such as a list. You can always - attach new subparts to the message by using the attach() method. - - 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) - if _subparts: - for p in _subparts: - self.attach(p) - if boundary: - self.set_boundary(boundary) diff --git a/Lib/email/MIMENonMultipart.py b/Lib/email/MIMENonMultipart.py deleted file mode 100644 index 4195d2a..0000000 --- a/Lib/email/MIMENonMultipart.py +++ /dev/null @@ -1,24 +0,0 @@ -# Copyright (C) 2002-2004 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 - - - -class MIMENonMultipart(MIMEBase.MIMEBase): - """Base class for MIME multipart/* type messages.""" - - __pychecker__ = 'unusednames=payload' - - def attach(self, payload): - # 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( - 'Cannot attach additional subparts to non-multipart/*') - - del __pychecker__ diff --git a/Lib/email/MIMEText.py b/Lib/email/MIMEText.py deleted file mode 100644 index 5ef1876..0000000 --- a/Lib/email/MIMEText.py +++ /dev/null @@ -1,28 +0,0 @@ -# Copyright (C) 2001-2004 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 - - - -class MIMEText(MIMENonMultipart): - """Class for generating text/* type MIME documents.""" - - def __init__(self, _text, _subtype='plain', _charset='us-ascii'): - """Create a text/* type MIME document. - - _text is the string for this message object. - - _subtype is the MIME sub content type, defaulting to "plain". - - _charset is the character set parameter added to the Content-Type - header. This defaults to "us-ascii". Note that as a side-effect, the - Content-Transfer-Encoding header will also be set. - """ - MIMENonMultipart.__init__(self, 'text', _subtype, - **{'charset': _charset}) - self.set_payload(_text, _charset) diff --git a/Lib/email/Message.py b/Lib/email/Message.py deleted file mode 100644 index bc76416..0000000 --- a/Lib/email/Message.py +++ /dev/null @@ -1,814 +0,0 @@ -# Copyright (C) 2001-2006 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Basic message object for the email package object model.""" - -import re -import uu -import binascii -import warnings -from cStringIO import StringIO - -# Intrapackage imports -from email import Utils -from email import Errors -from email import Charset - -SEMISPACE = '; ' - -# Regular expression used to split header parameters. BAW: this may be too -# simple. It isn't strictly RFC 2045 (section 5.1) compliant, but it catches -# most headers found in the wild. We may eventually need a full fledged -# parser eventually. -paramre = re.compile(r'\s*;\s*') -# Regular expression that matches `special' characters in parameters, the -# existance of which force quoting of the parameter value. -tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]') - - - -# Helper functions -def _formatparam(param, value=None, quote=True): - """Convenience function to format and return a key=value pair. - - This will quote the value if needed or if quote is true. - """ - if value is not None and len(value) > 0: - # A tuple is used for RFC 2231 encoded parameter values where items - # are (charset, language, value). charset is a string, not a Charset - # instance. - if isinstance(value, tuple): - # Encode as per RFC 2231 - param += '*' - 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)) - else: - return '%s=%s' % (param, value) - else: - return param - -def _parseparam(s): - plist = [] - while s[:1] == ';': - s = s[1:] - end = s.find(';') - while end > 0 and s.count('"', 0, end) % 2: - end = s.find(';', end + 1) - if end < 0: - end = len(s) - f = s[:end] - if '=' in f: - i = f.index('=') - f = f[:i].strip().lower() + '=' + f[i+1:].strip() - plist.append(f.strip()) - s = s[end:] - return plist - - -def _unquotevalue(value): - # 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]) - else: - return Utils.unquote(value) - - - -class Message: - """Basic message object. - - A message object is defined as something that has a bunch of RFC 2822 - headers and a payload. It may optionally have an envelope header - (a.k.a. Unix-From or From_ header). If the message is a container (i.e. a - multipart or a message/rfc822), then the payload is a list of Message - objects, otherwise it is a string. - - Message objects implement part of the `mapping' interface, which assumes - there is exactly one occurrance of the header per message. Some headers - do in fact appear multiple times (e.g. Received) and for those headers, - you must use the explicit API to set or get all the headers. Not all of - the mapping methods are implemented. - """ - def __init__(self): - self._headers = [] - self._unixfrom = None - self._payload = None - self._charset = None - # Defaults for multipart messages - self.preamble = self.epilogue = None - self.defects = [] - # Default content type - self._default_type = 'text/plain' - - def __str__(self): - """Return the entire formatted message as a string. - This includes the headers, body, and envelope header. - """ - return self.as_string(unixfrom=True) - - def as_string(self, unixfrom=False): - """Return the entire formatted message as a string. - Optional `unixfrom' when True, means include the Unix From_ envelope - header. - - This is a convenience method and may not generate the message exactly - as you intend because by default it mangles lines that begin with - "From ". For more flexibility, use the flatten() method of a - Generator instance. - """ - from email.Generator import Generator - fp = StringIO() - g = Generator(fp) - g.flatten(self, unixfrom=unixfrom) - return fp.getvalue() - - def is_multipart(self): - """Return True if the message consists of multiple parts.""" - return isinstance(self._payload, list) - - # - # Unix From_ line - # - def set_unixfrom(self, unixfrom): - self._unixfrom = unixfrom - - def get_unixfrom(self): - return self._unixfrom - - # - # Payload manipulation. - # - def attach(self, payload): - """Add the given payload to the current payload. - - The current payload will always be a list of objects after this method - is called. If you want to set the payload to a scalar object, use - set_payload() instead. - """ - if self._payload is None: - self._payload = [payload] - else: - self._payload.append(payload) - - def get_payload(self, i=None, decode=False): - """Return a reference to the payload. - - The payload will either be a list object or a string. If you mutate - the list object, you modify the message's payload in place. Optional - i returns that index into the payload. - - Optional decode is a flag indicating whether the payload should be - decoded or not, according to the Content-Transfer-Encoding header - (default is False). - - When True and the message is not a multipart, the payload will be - decoded if this header's value is `quoted-printable' or `base64'. If - some other encoding is used, or the header is missing, or if the - payload has bogus data (i.e. bogus base64 or uuencoded data), the - payload is returned as-is. - - If the message is a multipart and the decode flag is True, then None - is returned. - """ - if i is None: - payload = self._payload - elif not isinstance(self._payload, list): - raise TypeError('Expected list, got %s' % type(self._payload)) - else: - payload = self._payload[i] - if decode: - if self.is_multipart(): - return None - cte = self.get('content-transfer-encoding', '').lower() - if cte == 'quoted-printable': - return Utils._qdecode(payload) - elif cte == 'base64': - try: - 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) - payload = sfp.getvalue() - except uu.Error: - # Some decoding problem - return payload - # Everything else, including encodings with 8bit or 7bit are returned - # unchanged. - return payload - - def set_payload(self, payload, charset=None): - """Set the payload to the given value. - - Optional charset sets the message's default character set. See - set_charset() for details. - """ - self._payload = payload - if charset is not None: - self.set_charset(charset) - - def set_charset(self, charset): - """Set the charset of the payload to a given character set. - - charset can be a Charset instance, a string naming a character set, or - None. If it is a string it will be converted to a Charset instance. - If charset is None, the charset parameter will be removed from the - Content-Type field. Anything else will generate a TypeError. - - The message will be assumed to be of type text/* encoded with - charset.input_charset. It will be converted to charset.output_charset - and encoded properly, if needed, when generating the plain text - representation of the message. MIME headers (MIME-Version, - Content-Type, Content-Transfer-Encoding) will be added as needed. - - """ - if charset is None: - self.del_param('charset') - self._charset = None - return - if isinstance(charset, str): - charset = Charset.Charset(charset) - if not isinstance(charset, Charset.Charset): - raise TypeError(charset) - # BAW: should we accept strings that can serve as arguments to the - # Charset constructor? - self._charset = charset - if not self.has_key('MIME-Version'): - self.add_header('MIME-Version', '1.0') - if not self.has_key('Content-Type'): - self.add_header('Content-Type', 'text/plain', - charset=charset.get_output_charset()) - else: - self.set_param('charset', charset.get_output_charset()) - if str(charset) <> charset.get_output_charset(): - self._payload = charset.body_encode(self._payload) - if not self.has_key('Content-Transfer-Encoding'): - cte = charset.get_body_encoding() - try: - cte(self) - except TypeError: - self._payload = charset.body_encode(self._payload) - self.add_header('Content-Transfer-Encoding', cte) - - def get_charset(self): - """Return the Charset instance associated with the message's payload. - """ - return self._charset - - # - # MAPPING INTERFACE (partial) - # - def __len__(self): - """Return the total number of headers, including duplicates.""" - return len(self._headers) - - def __getitem__(self, name): - """Get a header value. - - Return None if the header is missing instead of raising an exception. - - Note that if the header appeared multiple times, exactly which - occurrance gets returned is undefined. Use get_all() to get all - the values matching a header field name. - """ - return self.get(name) - - def __setitem__(self, name, val): - """Set the value of a header. - - Note: this does not overwrite an existing header with the same field - name. Use __delitem__() first to delete any existing headers. - """ - self._headers.append((name, val)) - - def __delitem__(self, name): - """Delete all occurrences of a header, if present. - - Does not raise an exception if the header is missing. - """ - name = name.lower() - newheaders = [] - for k, v in self._headers: - if k.lower() <> name: - newheaders.append((k, v)) - self._headers = newheaders - - def __contains__(self, name): - return name.lower() in [k.lower() for k, v in self._headers] - - def has_key(self, name): - """Return true if the message contains the header.""" - missing = object() - return self.get(name, missing) is not missing - - def keys(self): - """Return a list of all the message's header field names. - - These will be sorted in the order they appeared in the original - message, or were added to the message, and may contain duplicates. - Any fields deleted and re-inserted are always appended to the header - list. - """ - return [k for k, v in self._headers] - - def values(self): - """Return a list of all the message's header values. - - These will be sorted in the order they appeared in the original - message, or were added to the message, and may contain duplicates. - Any fields deleted and re-inserted are always appended to the header - list. - """ - return [v for k, v in self._headers] - - def items(self): - """Get all the message's header fields and values. - - These will be sorted in the order they appeared in the original - message, or were added to the message, and may contain duplicates. - Any fields deleted and re-inserted are always appended to the header - list. - """ - return self._headers[:] - - def get(self, name, failobj=None): - """Get a header value. - - Like __getitem__() but return failobj instead of None when the field - is missing. - """ - name = name.lower() - for k, v in self._headers: - if k.lower() == name: - return v - return failobj - - # - # Additional useful stuff - # - - def get_all(self, name, failobj=None): - """Return a list of all the values for the named field. - - These will be sorted in the order they appeared in the original - message, and may contain duplicates. Any fields deleted and - re-inserted are always appended to the header list. - - If no such fields exist, failobj is returned (defaults to None). - """ - values = [] - name = name.lower() - for k, v in self._headers: - if k.lower() == name: - values.append(v) - if not values: - return failobj - return values - - def add_header(self, _name, _value, **_params): - """Extended header setting. - - name is the header field to add. keyword arguments can be used to set - additional parameters for the header field, with underscores converted - to dashes. Normally the parameter will be added as key="value" unless - value is None, in which case only the key will be added. - - Example: - - msg.add_header('content-disposition', 'attachment', filename='bud.gif') - """ - parts = [] - for k, v in _params.items(): - if v is None: - parts.append(k.replace('_', '-')) - else: - parts.append(_formatparam(k.replace('_', '-'), v)) - if _value is not None: - parts.insert(0, _value) - self._headers.append((_name, SEMISPACE.join(parts))) - - def replace_header(self, _name, _value): - """Replace a header. - - Replace the first matching header found in the message, retaining - header order and case. If no matching header was found, a KeyError is - raised. - """ - _name = _name.lower() - for i, (k, v) in zip(range(len(self._headers)), self._headers): - if k.lower() == _name: - self._headers[i] = (k, _value) - break - 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. - # - - def get_content_type(self): - """Return the message's content type. - - The returned string is coerced to lower case of the form - `maintype/subtype'. If there was no Content-Type header in the - message, the default type as given by get_default_type() will be - returned. Since according to RFC 2045, messages always have a default - type this will always return a value. - - RFC 2045 defines a message's default type to be text/plain unless it - appears inside a multipart/digest container, in which case it would be - message/rfc822. - """ - missing = object() - value = self.get('content-type', missing) - if value is missing: - # This should have no parameters - return self.get_default_type() - ctype = paramre.split(value)[0].lower().strip() - # RFC 2045, section 5.2 says if its invalid, use text/plain - if ctype.count('/') <> 1: - return 'text/plain' - return ctype - - def get_content_maintype(self): - """Return the message's main content type. - - This is the `maintype' part of the string returned by - get_content_type(). - """ - ctype = self.get_content_type() - return ctype.split('/')[0] - - def get_content_subtype(self): - """Returns the message's sub-content type. - - This is the `subtype' part of the string returned by - get_content_type(). - """ - ctype = self.get_content_type() - return ctype.split('/')[1] - - def get_default_type(self): - """Return the `default' content type. - - Most messages have a default content type of text/plain, except for - messages that are subparts of multipart/digest containers. Such - subparts have a default content type of message/rfc822. - """ - return self._default_type - - def set_default_type(self, ctype): - """Set the `default' content type. - - ctype should be either "text/plain" or "message/rfc822", although this - is not enforced. The default content type is not stored in the - Content-Type header. - """ - self._default_type = ctype - - def _get_params_preserve(self, failobj, header): - # Like get_params() but preserves the quoting of values. BAW: - # should this be part of the public interface? - missing = object() - value = self.get(header, missing) - if value is missing: - return failobj - params = [] - for p in _parseparam(';' + value): - try: - name, val = p.split('=', 1) - name = name.strip() - val = val.strip() - except ValueError: - # Must have been a bare attribute - name = p.strip() - val = '' - params.append((name, val)) - params = Utils.decode_params(params) - return params - - def get_params(self, failobj=None, header='content-type', unquote=True): - """Return the message's Content-Type parameters, as a list. - - The elements of the returned list are 2-tuples of key/value pairs, as - split on the `=' sign. The left hand side of the `=' is the key, - while the right hand side is the value. If there is no `=' sign in - the parameter the value is the empty string. The value is as - described in the get_param() method. - - Optional failobj is the object to return if there is no Content-Type - header. Optional header is the header to search instead of - Content-Type. If unquote is True, the value is unquoted. - """ - missing = object() - params = self._get_params_preserve(missing, header) - if params is missing: - return failobj - if unquote: - return [(k, _unquotevalue(v)) for k, v in params] - else: - return params - - def get_param(self, param, failobj=None, header='content-type', - unquote=True): - """Return the parameter value if found in the Content-Type header. - - Optional failobj is the object to return if there is no Content-Type - header, or the Content-Type header has no such parameter. Optional - header is the header to search instead of Content-Type. - - Parameter keys are always compared case insensitively. The return - value can either be a string, or a 3-tuple if the parameter was RFC - 2231 encoded. When it's a 3-tuple, the elements of the value are of - the form (CHARSET, LANGUAGE, VALUE). Note that both CHARSET and - LANGUAGE can be None, in which case you should consider VALUE to be - encoded in the us-ascii charset. You can usually ignore LANGUAGE. - - Your application should be prepared to deal with 3-tuple return - values, and can convert the parameter to a Unicode string like so: - - param = msg.get_param('foo') - if isinstance(param, tuple): - param = unicode(param[2], param[0] or 'us-ascii') - - In any case, the parameter value (either the returned string, or the - VALUE item in the 3-tuple) is always unquoted, unless unquote is set - to False. - """ - if not self.has_key(header): - return failobj - for k, v in self._get_params_preserve(failobj, header): - if k.lower() == param.lower(): - if unquote: - return _unquotevalue(v) - else: - return v - return failobj - - def set_param(self, param, value, header='Content-Type', requote=True, - charset=None, language=''): - """Set a parameter in the Content-Type header. - - If the parameter already exists in the header, its value will be - replaced with the new value. - - If header is Content-Type and has not yet been defined for this - message, it will be set to "text/plain" and the new parameter and - value will be appended as per RFC 2045. - - An alternate header can specified in the header argument, and all - parameters will be quoted as necessary unless requote is False. - - If charset is specified, the parameter will be encoded according to RFC - 2231. Optional language specifies the RFC 2231 language, defaulting - to the empty string. Both charset and language should be strings. - """ - if not isinstance(value, tuple) and charset: - value = (charset, language, value) - - if not self.has_key(header) and header.lower() == 'content-type': - ctype = 'text/plain' - else: - ctype = self.get(header) - if not self.get_param(param, header=header): - if not ctype: - ctype = _formatparam(param, value, requote) - else: - ctype = SEMISPACE.join( - [ctype, _formatparam(param, value, requote)]) - else: - ctype = '' - for old_param, old_value in self.get_params(header=header, - unquote=requote): - append_param = '' - if old_param.lower() == param.lower(): - append_param = _formatparam(param, value, requote) - else: - append_param = _formatparam(old_param, old_value, requote) - if not ctype: - ctype = append_param - else: - ctype = SEMISPACE.join([ctype, append_param]) - if ctype <> self.get(header): - del self[header] - self[header] = ctype - - def del_param(self, param, header='content-type', requote=True): - """Remove the given parameter completely from the Content-Type header. - - The header will be re-written in place without the parameter or its - value. All values will be quoted as necessary unless requote is - False. Optional header specifies an alternative to the Content-Type - header. - """ - if not self.has_key(header): - return - new_ctype = '' - for p, v in self.get_params(header=header, unquote=requote): - if p.lower() <> param.lower(): - if not new_ctype: - new_ctype = _formatparam(p, v, requote) - else: - new_ctype = SEMISPACE.join([new_ctype, - _formatparam(p, v, requote)]) - if new_ctype <> self.get(header): - del self[header] - self[header] = new_ctype - - def set_type(self, type, header='Content-Type', requote=True): - """Set the main type and subtype for the Content-Type header. - - type must be a string in the form "maintype/subtype", otherwise a - ValueError is raised. - - This method replaces the Content-Type header, keeping all the - parameters in place. If requote is False, this leaves the existing - header's quoting as is. Otherwise, the parameters will be quoted (the - default). - - An alternative header can be specified in the header argument. When - the Content-Type header is set, we'll always also add a MIME-Version - header. - """ - # BAW: should we be strict? - if not type.count('/') == 1: - raise ValueError - # Set the Content-Type, you get a MIME-Version - if header.lower() == 'content-type': - del self['mime-version'] - self['MIME-Version'] = '1.0' - if not self.has_key(header): - self[header] = type - return - params = self.get_params(header=header, unquote=requote) - del self[header] - self[header] = type - # Skip the first param; it's the old type. - for p, v in params[1:]: - self.set_param(p, v, header, requote) - - def get_filename(self, failobj=None): - """Return the filename associated with the payload if present. - - The filename is extracted from the Content-Disposition header's - `filename' parameter, and it is unquoted. If that header is missing - the `filename' parameter, this method falls back to looking for the - `name' parameter. - """ - missing = object() - filename = self.get_param('filename', missing, 'content-disposition') - if filename is missing: - filename = self.get_param('name', missing, 'content-disposition') - if filename is missing: - return failobj - return Utils.collapse_rfc2231_value(filename).strip() - - def get_boundary(self, failobj=None): - """Return the boundary associated with the payload if present. - - The boundary is extracted from the Content-Type header's `boundary' - parameter, and it is unquoted. - """ - missing = object() - boundary = self.get_param('boundary', missing) - 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() - - def set_boundary(self, boundary): - """Set the boundary parameter in Content-Type to 'boundary'. - - This is subtly different than deleting the Content-Type header and - adding a new one with a new boundary parameter via add_header(). The - main difference is that using the set_boundary() method preserves the - order of the Content-Type header in the original message. - - HeaderParseError is raised if the message has no Content-Type header. - """ - missing = object() - params = self._get_params_preserve(missing, 'content-type') - 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' - newparams = [] - foundp = False - for pk, pv in params: - if pk.lower() == 'boundary': - newparams.append(('boundary', '"%s"' % boundary)) - foundp = True - else: - newparams.append((pk, pv)) - if not foundp: - # The original Content-Type header had no boundary attribute. - # Tack one on the end. BAW: should we raise an exception - # instead??? - newparams.append(('boundary', '"%s"' % boundary)) - # Replace the existing Content-Type header with the new value - newheaders = [] - for h, v in self._headers: - if h.lower() == 'content-type': - parts = [] - for k, v in newparams: - if v == '': - parts.append(k) - else: - parts.append('%s=%s' % (k, v)) - newheaders.append((h, SEMISPACE.join(parts))) - - else: - newheaders.append((h, v)) - self._headers = newheaders - - def get_content_charset(self, failobj=None): - """Return the charset parameter of the Content-Type header. - - The returned string is always coerced to lower case. If there is no - Content-Type header, or if that header has no charset parameter, - failobj is returned. - """ - missing = object() - charset = self.get_param('charset', missing) - if charset is missing: - return failobj - if isinstance(charset, tuple): - # RFC 2231 encoded, so decode it, and it better end up as ascii. - pcharset = charset[0] or 'us-ascii' - charset = unicode(charset[2], pcharset).encode('us-ascii') - # RFC 2046, $4.1.2 says charsets are not case sensitive - return charset.lower() - - def get_charsets(self, failobj=None): - """Return a list containing the charset(s) used in this message. - - The returned list of items describes the Content-Type headers' - charset parameter for this message and all the subparts in its - payload. - - Each item will either be a string (the value of the charset parameter - in the Content-Type header of that part) or the value of the - 'failobj' parameter (defaults to None), if the part does not have a - main MIME type of "text", or the charset is not defined. - - The list will contain one string for each part of the message, plus - one for the container message (i.e. self), so that a non-multipart - message will still return a list of length 1. - """ - return [part.get_content_charset(failobj) for part in self.walk()] - - # I.e. def walk(self): ... - from email.Iterators import walk diff --git a/Lib/email/Parser.py b/Lib/email/Parser.py deleted file mode 100644 index 0c05224..0000000 --- a/Lib/email/Parser.py +++ /dev/null @@ -1,88 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw, Thomas Wouters, Anthony Baxter -# Contact: email-sig@python.org - -"""A parser of RFC 2822 and MIME email messages.""" - -import warnings -from cStringIO import StringIO -from email.FeedParser import FeedParser -from email.Message import Message - - - -class Parser: - def __init__(self, *args, **kws): - """Parser of RFC 2822 and MIME email messages. - - Creates an in-memory object tree representing the email message, which - can then be manipulated and turned over to a Generator to return the - textual representation of the message. - - The string must be formatted as a block of RFC 2822 headers and header - continuation lines, optionally preceeded by a `Unix-from' header. The - header block is terminated either by the end of the string or by a - blank line. - - _class is the class to instantiate for new message objects when they - must be created. This class must have a constructor that can take - zero arguments. Default is Message.Message. - """ - if len(args) >= 1: - if '_class' in kws: - raise TypeError("Multiple values for keyword arg '_class'") - kws['_class'] = args[0] - if len(args) == 2: - if 'strict' in kws: - raise TypeError("Multiple values for keyword arg 'strict'") - kws['strict'] = args[1] - if len(args) > 2: - raise TypeError('Too many arguments') - if '_class' in kws: - self._class = kws['_class'] - del kws['_class'] - else: - self._class = Message - if 'strict' in kws: - warnings.warn("'strict' argument is deprecated (and ignored)", - DeprecationWarning, 2) - del kws['strict'] - if kws: - raise TypeError('Unexpected keyword arguments') - - def parse(self, fp, headersonly=False): - """Create a message structure from the data in a file. - - Reads all the data from the file and returns the root of the message - structure. Optional headersonly is a flag specifying whether to stop - parsing after reading the headers or not. The default is False, - meaning it parses the entire contents of the file. - """ - feedparser = FeedParser(self._class) - if headersonly: - feedparser._set_headersonly() - while True: - data = fp.read(8192) - if not data: - break - feedparser.feed(data) - return feedparser.close() - - def parsestr(self, text, headersonly=False): - """Create a message structure from a string. - - Returns the root of the message structure. Optional headersonly is a - flag specifying whether to stop parsing after reading the headers or - not. The default is False, meaning it parses the entire contents of - the file. - """ - return self.parse(StringIO(text), headersonly=headersonly) - - - -class HeaderParser(Parser): - def parse(self, fp, headersonly=True): - return Parser.parse(self, fp, True) - - def parsestr(self, text, headersonly=True): - return Parser.parsestr(self, text, True) diff --git a/Lib/email/Utils.py b/Lib/email/Utils.py deleted file mode 100644 index 9ba7601..0000000 --- a/Lib/email/Utils.py +++ /dev/null @@ -1,291 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Barry Warsaw -# Contact: email-sig@python.org - -"""Miscellaneous utilities.""" - -import os -import re -import time -import base64 -import random -import socket -import warnings -from cStringIO import StringIO - -from email._parseaddr import quote -from email._parseaddr import AddressList as _AddressList -from email._parseaddr import mktime_tz - -# We need wormarounds for bugs in these methods in older Pythons (see below) -from email._parseaddr import parsedate as _parsedate -from email._parseaddr import parsedate_tz as _parsedate_tz - -from quopri import decodestring as _qdecode - -# Intrapackage imports -from email.Encoders import _bencode, _qencode - -COMMASPACE = ', ' -EMPTYSTRING = '' -UEMPTYSTRING = u'' -CRLF = '\r\n' - -specialsre = re.compile(r'[][\\()<>@,:;".]') -escapesre = re.compile(r'[][\\()"]') - - - -# Helpers - -def _identity(s): - return s - - -def _bdecode(s): - # We can't quite use base64.encodestring() since it tacks on a "courtesy - # newline". Blech! - if not s: - return s - value = base64.decodestring(s) - if not s.endswith('\n') and value.endswith('\n'): - return value[:-1] - return value - - - -def fix_eols(s): - """Replace all line-ending characters with \r\n.""" - # Fix newlines with no preceding carriage return - s = re.sub(r'(?', name) - return '%s%s%s <%s>' % (quotes, name, quotes, address) - return address - - - -def getaddresses(fieldvalues): - """Return a list of (REALNAME, EMAIL) for each fieldvalue.""" - all = COMMASPACE.join(fieldvalues) - a = _AddressList(all) - return a.addresslist - - - -ecre = re.compile(r''' - =\? # literal =? - (?P[^?]*?) # non-greedy up to the next ? is the charset - \? # literal ? - (?P[qb]) # either a "q" or a "b", case insensitive - \? # literal ? - (?P.*?) # non-greedy up to the next ?= is the atom - \?= # literal ?= - ''', re.VERBOSE | re.IGNORECASE) - - - -def formatdate(timeval=None, localtime=False, usegmt=False): - """Returns a date string as specified by RFC 2822, e.g.: - - Fri, 09 Nov 2001 01:08:47 -0000 - - Optional timeval if given is a floating point time value as accepted by - gmtime() and localtime(), otherwise the current time is used. - - Optional localtime is a flag that when True, interprets timeval, and - returns a date relative to the local timezone instead of UTC, properly - taking daylight savings time into account. - - Optional argument usegmt means that the timezone is written out as - an ascii string, not numeric one (so "GMT" instead of "+0000"). This - is needed for HTTP, and is only used when localtime==False. - """ - # Note: we cannot use strftime() because that honors the locale and RFC - # 2822 requires that day and month names be the English abbreviations. - if timeval is None: - timeval = time.time() - if localtime: - now = time.localtime(timeval) - # Calculate timezone offset, based on whether the local zone has - # daylight savings time, and whether DST is in effect. - if time.daylight and now[-1]: - offset = time.altzone - else: - offset = time.timezone - hours, minutes = divmod(abs(offset), 3600) - # Remember offset is in seconds west of UTC, but the timezone is in - # minutes east of UTC, so the signs differ. - if offset > 0: - sign = '-' - else: - sign = '+' - zone = '%s%02d%02d' % (sign, hours, minutes // 60) - else: - now = time.gmtime(timeval) - # Timezone offset is always -0000 - if usegmt: - zone = 'GMT' - else: - zone = '-0000' - return '%s, %02d %s %04d %02d:%02d:%02d %s' % ( - ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][now[6]], - now[2], - ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', - 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][now[1] - 1], - now[0], now[3], now[4], now[5], - zone) - - - -def make_msgid(idstring=None): - """Returns a string suitable for RFC 2822 compliant Message-ID, e.g: - - <20020201195627.33539.96671@nightshade.la.mastaler.com> - - Optional idstring if given is a string used to strengthen the - uniqueness of the message id. - """ - timeval = time.time() - utcdate = time.strftime('%Y%m%d%H%M%S', time.gmtime(timeval)) - pid = os.getpid() - randint = random.randrange(100000) - if idstring is None: - idstring = '' - else: - idstring = '.' + idstring - idhost = socket.getfqdn() - msgid = '<%s.%s.%s%s@%s>' % (utcdate, pid, randint, idstring, idhost) - return msgid - - - -# These functions are in the standalone mimelib version only because they've -# subsequently been fixed in the latest Python versions. We use this to worm -# around broken older Pythons. -def parsedate(data): - if not data: - return None - return _parsedate(data) - - -def parsedate_tz(data): - if not data: - return None - return _parsedate_tz(data) - - -def parseaddr(addr): - addrs = _AddressList(addr).addresslist - if not addrs: - return '', '' - return addrs[0] - - -# rfc822.unquote() doesn't properly de-backslash-ify in Python pre-2.3. -def unquote(str): - """Remove quotes from a string.""" - if len(str) > 1: - if str.startswith('"') and str.endswith('"'): - return str[1:-1].replace('\\\\', '\\').replace('\\"', '"') - if str.startswith('<') and str.endswith('>'): - return str[1:-1] - return str - - - -# RFC2231-related functions - parameter encoding and decoding -def decode_rfc2231(s): - """Decode string according to RFC 2231""" - import urllib - parts = s.split("'", 2) - if len(parts) == 1: - return None, None, urllib.unquote(s) - charset, language, s = parts - return charset, language, urllib.unquote(s) - - -def encode_rfc2231(s, charset=None, language=None): - """Encode string according to RFC 2231. - - If neither charset nor language is given, then s is returned as-is. If - charset is given but not language, the string is encoded using the empty - string for language. - """ - import urllib - s = urllib.quote(s, safe='') - if charset is None and language is None: - return s - if language is None: - language = '' - return "%s'%s'%s" % (charset, language, s) - - -rfc2231_continuation = re.compile(r'^(?P\w+)\*((?P[0-9]+)\*?)?$') - -def decode_params(params): - """Decode parameters list according to RFC 2231. - - params is a sequence of 2-tuples containing (content type, string value). - """ - new_params = [] - # maps parameter's name to a list of continuations - rfc2231_params = {} - # params is a sequence of 2-tuples containing (content_type, string value) - name, value = params[0] - new_params.append((name, value)) - # Cycle through each of the rest of the parameters. - for name, value in params[1:]: - value = unquote(value) - mo = rfc2231_continuation.match(name) - if mo: - name, num = mo.group('name', 'num') - if num is not None: - num = int(num) - rfc2231_param1 = rfc2231_params.setdefault(name, []) - rfc2231_param1.append((num, value)) - else: - new_params.append((name, '"%s"' % quote(value))) - if rfc2231_params: - for name, continuations in rfc2231_params.items(): - value = [] - # Sort by number - continuations.sort() - # And now append all values in num order - for num, continuation in continuations: - value.append(continuation) - charset, language, value = decode_rfc2231(EMPTYSTRING.join(value)) - new_params.append( - (name, (charset, language, '"%s"' % quote(value)))) - return new_params - -def collapse_rfc2231_value(value, errors='replace', - fallback_charset='us-ascii'): - if isinstance(value, tuple): - rawval = unquote(value[2]) - charset = value[0] or 'us-ascii' - try: - return unicode(rawval, charset, errors) - except LookupError: - # XXX charset is unknown to Python. - return unicode(rawval, fallback_charset, errors) - else: - return unquote(value) diff --git a/Lib/email/__init__.py b/Lib/email/__init__.py index e5c0e2e..0a6a72d 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 7d759ef..109ff5f 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 deleted file mode 100644 index 6ed1d53..0000000 --- a/Lib/email/base64MIME.py +++ /dev/null @@ -1,172 +0,0 @@ -# Copyright (C) 2002-2004 Python Software Foundation -# Author: Ben Gertzfield -# Contact: email-sig@python.org - -"""Base64 content transfer encoding per RFCs 2045-2047. - -This module handles the content transfer encoding method defined in RFC 2045 -to encode arbitrary 8-bit data using the three 8-bit bytes in four 7-bit -characters encoding known as Base64. - -It is used in the MIME standards for email to attach images, audio, and text -using some 8-bit character sets to messages. - -This module provides an interface to encode and decode both headers and bodies -with Base64 encoding. - -RFC 2045 defines a method for including character set information in an -`encoded-word' in a header. This method is commonly used for 8-bit real names -in To:, From:, Cc:, etc. fields, as well as Subject: lines. - -This module does not do the line wrapping or end-of-line character conversion -necessary for proper internationalized headers; it only does dumb encoding and -decoding. To deal with the various line wrapping issues, use the email.Header -module. -""" - -import re -from binascii import b2a_base64, a2b_base64 -from email.Utils import fix_eols - -CRLF = '\r\n' -NL = '\n' -EMPTYSTRING = '' - -# See also Charset.py -MISC_LEN = 7 - - - -# Helpers -def base64_len(s): - """Return the length of s when it is encoded with base64.""" - groups_of_3, leftover = divmod(len(s), 3) - # 4 bytes out for each 3 bytes (or nonzero fraction thereof) in. - # Thanks, Tim! - n = groups_of_3 * 4 - if leftover: - n += 4 - return n - - - -def header_encode(header, charset='iso-8859-1', keep_eols=False, - maxlinelen=76, eol=NL): - """Encode a single header line with Base64 encoding in a given charset. - - Defined in RFC 2045, this Base64 encoding is identical to normal Base64 - encoding, except that each line must be intelligently wrapped (respecting - the Base64 encoding), and subsequent lines must start with a space. - - charset names the character set to use to encode the header. It defaults - to iso-8859-1. - - End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted - to the canonical email line separator \\r\\n unless the keep_eols - parameter is True (the default is False). - - Each line of the header will be terminated in the value of eol, which - defaults to "\\n". Set this to "\\r\\n" if you are using the result of - this function directly in email. - - The resulting string will be in the form: - - "=?charset?b?WW/5ciBtYXp66XLrIHf8eiBhIGhhbXBzdGHuciBBIFlv+XIgbWF6euly?=\\n - =?charset?b?6yB3/HogYSBoYW1wc3Rh7nIgQkMgWW/5ciBtYXp66XLrIHf8eiBhIGhh?=" - - with each line wrapped at, at most, maxlinelen characters (defaults to 76 - characters). - """ - # Return empty headers unchanged - if not header: - return header - - if not keep_eols: - header = fix_eols(header) - - # Base64 encode each line, in encoded chunks no greater than maxlinelen in - # length, after the RFC chrome is added in. - base64ed = [] - max_encoded = maxlinelen - len(charset) - MISC_LEN - max_unencoded = max_encoded * 3 // 4 - - for i in range(0, len(header), max_unencoded): - base64ed.append(b2a_base64(header[i:i+max_unencoded])) - - # Now add the RFC chrome to each encoded chunk - lines = [] - for line in base64ed: - # Ignore the last character of each line if it is a newline - if line.endswith(NL): - line = line[:-1] - # Add the chrome - lines.append('=?%s?b?%s?=' % (charset, line)) - # Glue the lines together and return it. BAW: should we be able to - # specify the leading whitespace in the joiner? - joiner = eol + ' ' - return joiner.join(lines) - - - -def encode(s, binary=True, maxlinelen=76, eol=NL): - """Encode a string with base64. - - Each line will be wrapped at, at most, maxlinelen characters (defaults to - 76 characters). - - If binary is False, end-of-line characters will be converted to the - canonical email end-of-line sequence \\r\\n. Otherwise they will be left - verbatim (this is the default). - - Each line of encoded text will end with eol, which defaults to "\\n". Set - this to "\r\n" if you will be using the result of this function directly - in an email. - """ - if not s: - return s - - if not binary: - s = fix_eols(s) - - encvec = [] - max_unencoded = maxlinelen * 3 // 4 - for i in range(0, len(s), max_unencoded): - # BAW: should encode() inherit b2a_base64()'s dubious behavior in - # adding a newline to the encoded string? - enc = b2a_base64(s[i:i + max_unencoded]) - if enc.endswith(NL) and eol <> NL: - enc = enc[:-1] + eol - encvec.append(enc) - return EMPTYSTRING.join(encvec) - - -# For convenience and backwards compatibility w/ standard base64 module -body_encode = encode -encodestring = encode - - - -def decode(s, convert_eols=None): - """Decode a raw base64 string. - - If convert_eols is set to a string value, all canonical email linefeeds, - e.g. "\\r\\n", in the decoded text will be converted to the value of - convert_eols. os.linesep is a good choice for convert_eols if you are - decoding a text attachment. - - This function does not parse a full MIME header value encoded with - base64 (like =?iso-8895-1?b?bmloISBuaWgh?=) -- please use the high - level email.Header class for that functionality. - """ - if not s: - return s - - dec = a2b_base64(s) - if convert_eols: - return dec.replace(CRLF, convert_eols) - return dec - - -# For convenience and backwards compatibility w/ standard base64 module -body_decode = decode -decodestring = decode diff --git a/Lib/email/base64mime.py b/Lib/email/base64mime.py new file mode 100644 index 0000000..0129d9d --- /dev/null +++ b/Lib/email/base64mime.py @@ -0,0 +1,184 @@ +# Copyright (C) 2002-2006 Python Software Foundation +# Author: Ben Gertzfield +# Contact: email-sig@python.org + +"""Base64 content transfer encoding per RFCs 2045-2047. + +This module handles the content transfer encoding method defined in RFC 2045 +to encode arbitrary 8-bit data using the three 8-bit bytes in four 7-bit +characters encoding known as Base64. + +It is used in the MIME standards for email to attach images, audio, and text +using some 8-bit character sets to messages. + +This module provides an interface to encode and decode both headers and bodies +with Base64 encoding. + +RFC 2045 defines a method for including character set information in an +`encoded-word' in a header. This method is commonly used for 8-bit real names +in To:, From:, Cc:, etc. fields, as well as Subject: lines. + +This module does not do the line wrapping or end-of-line character conversion +necessary for proper internationalized headers; it only does dumb encoding and +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 + +CRLF = '\r\n' +NL = '\n' +EMPTYSTRING = '' + +# See also Charset.py +MISC_LEN = 7 + + + +# Helpers +def base64_len(s): + """Return the length of s when it is encoded with base64.""" + groups_of_3, leftover = divmod(len(s), 3) + # 4 bytes out for each 3 bytes (or nonzero fraction thereof) in. + # Thanks, Tim! + n = groups_of_3 * 4 + if leftover: + n += 4 + return n + + + +def header_encode(header, charset='iso-8859-1', keep_eols=False, + maxlinelen=76, eol=NL): + """Encode a single header line with Base64 encoding in a given charset. + + Defined in RFC 2045, this Base64 encoding is identical to normal Base64 + encoding, except that each line must be intelligently wrapped (respecting + the Base64 encoding), and subsequent lines must start with a space. + + charset names the character set to use to encode the header. It defaults + to iso-8859-1. + + End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted + to the canonical email line separator \\r\\n unless the keep_eols + parameter is True (the default is False). + + Each line of the header will be terminated in the value of eol, which + defaults to "\\n". Set this to "\\r\\n" if you are using the result of + this function directly in email. + + The resulting string will be in the form: + + "=?charset?b?WW/5ciBtYXp66XLrIHf8eiBhIGhhbXBzdGHuciBBIFlv+XIgbWF6euly?=\\n + =?charset?b?6yB3/HogYSBoYW1wc3Rh7nIgQkMgWW/5ciBtYXp66XLrIHf8eiBhIGhh?=" + + with each line wrapped at, at most, maxlinelen characters (defaults to 76 + characters). + """ + # Return empty headers unchanged + if not header: + return header + + if not keep_eols: + header = fix_eols(header) + + # Base64 encode each line, in encoded chunks no greater than maxlinelen in + # length, after the RFC chrome is added in. + base64ed = [] + max_encoded = maxlinelen - len(charset) - MISC_LEN + max_unencoded = max_encoded * 3 // 4 + + for i in range(0, len(header), max_unencoded): + base64ed.append(b2a_base64(header[i:i+max_unencoded])) + + # Now add the RFC chrome to each encoded chunk + lines = [] + for line in base64ed: + # Ignore the last character of each line if it is a newline + if line.endswith(NL): + line = line[:-1] + # Add the chrome + lines.append('=?%s?b?%s?=' % (charset, line)) + # Glue the lines together and return it. BAW: should we be able to + # specify the leading whitespace in the joiner? + joiner = eol + ' ' + return joiner.join(lines) + + + +def encode(s, binary=True, maxlinelen=76, eol=NL): + """Encode a string with base64. + + Each line will be wrapped at, at most, maxlinelen characters (defaults to + 76 characters). + + If binary is False, end-of-line characters will be converted to the + canonical email end-of-line sequence \\r\\n. Otherwise they will be left + verbatim (this is the default). + + Each line of encoded text will end with eol, which defaults to "\\n". Set + this to "\r\n" if you will be using the result of this function directly + in an email. + """ + if not s: + return s + + if not binary: + s = fix_eols(s) + + encvec = [] + max_unencoded = maxlinelen * 3 // 4 + for i in range(0, len(s), max_unencoded): + # BAW: should encode() inherit b2a_base64()'s dubious behavior in + # adding a newline to the encoded string? + enc = b2a_base64(s[i:i + max_unencoded]) + if enc.endswith(NL) and eol <> NL: + enc = enc[:-1] + eol + encvec.append(enc) + return EMPTYSTRING.join(encvec) + + +# For convenience and backwards compatibility w/ standard base64 module +body_encode = encode +encodestring = encode + + + +def decode(s, convert_eols=None): + """Decode a raw base64 string. + + If convert_eols is set to a string value, all canonical email linefeeds, + e.g. "\\r\\n", in the decoded text will be converted to the value of + convert_eols. os.linesep is a good choice for convert_eols if you are + decoding a text attachment. + + This function does not parse a full MIME header value encoded with + base64 (like =?iso-8895-1?b?bmloISBuaWgh?=) -- please use the high + level email.Header class for that functionality. + """ + if not s: + return s + + dec = a2b_base64(s) + if convert_eols: + return dec.replace(CRLF, convert_eols) + return dec + + +# For convenience and backwards compatibility w/ standard base64 module +body_decode = decode +decodestring = decode diff --git a/Lib/email/charset.py b/Lib/email/charset.py new file mode 100644 index 0000000..8f218b2 --- /dev/null +++ b/Lib/email/charset.py @@ -0,0 +1,388 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Ben Gertzfield, Barry Warsaw +# Contact: email-sig@python.org + +__all__ = [ + 'Charset', + 'add_alias', + 'add_charset', + 'add_codec', + ] + +import email.base64mime +import email.quoprimime + +from email import errors +from email.encoders import encode_7or8bit + + + +# Flags for types of header encodings +QP = 1 # Quoted-Printable +BASE64 = 2 # Base64 +SHORTEST = 3 # the shorter of QP and base64, but only for headers + +# In "=?charset?q?hello_world?=", the =?, ?q?, and ?= add up to 7 +MISC_LEN = 7 + +DEFAULT_CHARSET = 'us-ascii' + + + +# Defaults +CHARSETS = { + # input header enc body enc output conv + 'iso-8859-1': (QP, QP, None), + 'iso-8859-2': (QP, QP, None), + 'iso-8859-3': (QP, QP, None), + 'iso-8859-4': (QP, QP, None), + # iso-8859-5 is Cyrillic, and not especially used + # iso-8859-6 is Arabic, also not particularly used + # iso-8859-7 is Greek, QP will not make it readable + # iso-8859-8 is Hebrew, QP will not make it readable + 'iso-8859-9': (QP, QP, None), + 'iso-8859-10': (QP, QP, None), + # iso-8859-11 is Thai, QP will not make it readable + 'iso-8859-13': (QP, QP, None), + 'iso-8859-14': (QP, QP, None), + 'iso-8859-15': (QP, QP, None), + 'windows-1252':(QP, QP, None), + 'viscii': (QP, QP, None), + 'us-ascii': (None, None, None), + 'big5': (BASE64, BASE64, None), + 'gb2312': (BASE64, BASE64, None), + 'euc-jp': (BASE64, None, 'iso-2022-jp'), + 'shift_jis': (BASE64, None, 'iso-2022-jp'), + 'iso-2022-jp': (BASE64, None, None), + 'koi8-r': (BASE64, BASE64, None), + 'utf-8': (SHORTEST, BASE64, 'utf-8'), + # We're making this one up to represent raw unencoded 8-bit + '8bit': (None, BASE64, 'utf-8'), + } + +# Aliases for other commonly-used names for character sets. Map +# them to the real ones used in email. +ALIASES = { + 'latin_1': 'iso-8859-1', + 'latin-1': 'iso-8859-1', + 'latin_2': 'iso-8859-2', + 'latin-2': 'iso-8859-2', + 'latin_3': 'iso-8859-3', + 'latin-3': 'iso-8859-3', + 'latin_4': 'iso-8859-4', + 'latin-4': 'iso-8859-4', + 'latin_5': 'iso-8859-9', + 'latin-5': 'iso-8859-9', + 'latin_6': 'iso-8859-10', + 'latin-6': 'iso-8859-10', + 'latin_7': 'iso-8859-13', + 'latin-7': 'iso-8859-13', + 'latin_8': 'iso-8859-14', + 'latin-8': 'iso-8859-14', + 'latin_9': 'iso-8859-15', + 'latin-9': 'iso-8859-15', + 'cp949': 'ks_c_5601-1987', + 'euc_jp': 'euc-jp', + 'euc_kr': 'euc-kr', + 'ascii': 'us-ascii', + } + + +# Map charsets to their Unicode codec strings. +CODEC_MAP = { + 'gb2312': 'eucgb2312_cn', + 'big5': 'big5_tw', + # Hack: We don't want *any* conversion for stuff marked us-ascii, as all + # sorts of garbage might be sent to us in the guise of 7-bit us-ascii. + # Let that stuff pass through without conversion to/from Unicode. + 'us-ascii': None, + } + + + +# Convenience functions for extending the above mappings +def add_charset(charset, header_enc=None, body_enc=None, output_charset=None): + """Add character set properties to the global registry. + + charset is the input character set, and must be the canonical name of a + character set. + + Optional header_enc and body_enc is either Charset.QP for + quoted-printable, Charset.BASE64 for base64 encoding, Charset.SHORTEST for + the shortest of qp or base64 encoding, or None for no encoding. SHORTEST + is only valid for header_enc. It describes how message headers and + message bodies in the input charset are to be encoded. Default is no + encoding. + + Optional output_charset is the character set that the output should be + in. Conversions will proceed from input charset, to Unicode, to the + output charset when the method Charset.convert() is called. The default + is to output in the same character set as the input. + + Both input_charset and output_charset must have Unicode codec entries in + the module's charset-to-codec mapping; use add_codec(charset, codecname) + to add codecs the module does not know about. See the codecs module's + documentation for more information. + """ + if body_enc == SHORTEST: + raise ValueError('SHORTEST not allowed for body_enc') + CHARSETS[charset] = (header_enc, body_enc, output_charset) + + +def add_alias(alias, canonical): + """Add a character set alias. + + alias is the alias name, e.g. latin-1 + canonical is the character set's canonical name, e.g. iso-8859-1 + """ + ALIASES[alias] = canonical + + +def add_codec(charset, codecname): + """Add a codec that map characters in the given charset to/from Unicode. + + charset is the canonical name of a character set. codecname is the name + of a Python codec, as appropriate for the second argument to the unicode() + built-in, or to the encode() method of a Unicode string. + """ + CODEC_MAP[charset] = codecname + + + +class Charset: + """Map character sets to their email properties. + + This class provides information about the requirements imposed on email + for a specific character set. It also provides convenience routines for + converting between character sets, given the availability of the + applicable codecs. Given a character set, it will do its best to provide + information on how to use that character set in an email in an + RFC-compliant way. + + Certain character sets must be encoded with quoted-printable or base64 + when used in email headers or bodies. Certain character sets must be + converted outright, and are not allowed in email. Instances of this + module expose the following information about a character set: + + input_charset: The initial character set specified. Common aliases + are converted to their `official' email names (e.g. latin_1 + is converted to iso-8859-1). Defaults to 7-bit us-ascii. + + header_encoding: If the character set must be encoded before it can be + used in an email header, this attribute will be set to + Charset.QP (for quoted-printable), Charset.BASE64 (for + base64 encoding), or Charset.SHORTEST for the shortest of + QP or BASE64 encoding. Otherwise, it will be None. + + body_encoding: Same as header_encoding, but describes the encoding for the + mail message's body, which indeed may be different than the + header encoding. Charset.SHORTEST is not allowed for + body_encoding. + + output_charset: Some character sets must be converted before the can be + used in email headers or bodies. If the input_charset is + one of them, this attribute will contain the name of the + charset output will be converted to. Otherwise, it will + be None. + + input_codec: The name of the Python codec used to convert the + input_charset to Unicode. If no conversion codec is + necessary, this attribute will be None. + + output_codec: The name of the Python codec used to convert Unicode + to the output_charset. If no conversion codec is necessary, + this attribute will have the same value as the input_codec. + """ + 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. 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 + # charset_map dictionary. Try that first, but let the user override + # it. + henc, benc, conv = CHARSETS.get(self.input_charset, + (SHORTEST, BASE64, None)) + if not conv: + conv = self.input_charset + # Set the attributes, allowing the arguments to override the default. + self.header_encoding = henc + self.body_encoding = benc + self.output_charset = ALIASES.get(conv, conv) + # Now set the codecs. If one isn't defined for input_charset, + # guess and try a Unicode codec with the same name as input_codec. + self.input_codec = CODEC_MAP.get(self.input_charset, + self.input_charset) + self.output_codec = CODEC_MAP.get(self.output_charset, + self.output_charset) + + def __str__(self): + return self.input_charset.lower() + + __repr__ = __str__ + + def __eq__(self, other): + return str(self) == str(other).lower() + + def __ne__(self, other): + return not self.__eq__(other) + + def get_body_encoding(self): + """Return the content-transfer-encoding used for body encoding. + + This is either the string `quoted-printable' or `base64' depending on + the encoding used, or it is a function in which case you should call + the function with a single argument, the Message object being + encoded. The function should then set the Content-Transfer-Encoding + header itself to whatever is appropriate. + + Returns "quoted-printable" if self.body_encoding is QP. + Returns "base64" if self.body_encoding is BASE64. + Returns "7bit" otherwise. + """ + assert self.body_encoding <> SHORTEST + if self.body_encoding == QP: + return 'quoted-printable' + elif self.body_encoding == BASE64: + return 'base64' + else: + return encode_7or8bit + + def convert(self, s): + """Convert a string from the input_codec to the output_codec.""" + if self.input_codec <> self.output_codec: + return unicode(s, self.input_codec).encode(self.output_codec) + else: + return s + + def to_splittable(self, s): + """Convert a possibly multibyte string to a safely splittable format. + + Uses the input_codec to try and convert the string to Unicode, so it + can be safely split on character boundaries (even for multibyte + characters). + + Returns the string as-is if it isn't known how to convert it to + Unicode with the input_charset. + + Characters that could not be converted to Unicode will be replaced + with the Unicode replacement character U+FFFD. + """ + if isinstance(s, unicode) or self.input_codec is None: + return s + try: + return unicode(s, self.input_codec, 'replace') + except LookupError: + # Input codec not installed on system, so return the original + # string unchanged. + return s + + def from_splittable(self, ustr, to_output=True): + """Convert a splittable string back into an encoded string. + + Uses the proper codec to try and convert the string from Unicode back + into an encoded format. Return the string as-is if it is not Unicode, + or if it could not be converted from Unicode. + + Characters that could not be converted from Unicode will be replaced + with an appropriate character (usually '?'). + + If to_output is True (the default), uses output_codec to convert to an + encoded format. If to_output is False, uses input_codec. + """ + if to_output: + codec = self.output_codec + else: + codec = self.input_codec + if not isinstance(ustr, unicode) or codec is None: + return ustr + try: + return ustr.encode(codec, 'replace') + except LookupError: + # Output codec not installed + return ustr + + def get_output_charset(self): + """Return the output character set. + + This is self.output_charset if that is not None, otherwise it is + self.input_charset. + """ + return self.output_charset or self.input_charset + + def encoded_header_len(self, s): + """Return the length of the encoded header string.""" + 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 + elif self.header_encoding == QP: + 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) + return min(lenb64, lenqp) + len(cset) + MISC_LEN + else: + return len(s) + + def header_encode(self, s, convert=False): + """Header-encode a string, optionally converting it to output_charset. + + If convert is True, the string will be converted from the input + charset to the output charset automatically. This is not useful for + multibyte character sets, which have line length issues (multibyte + characters must be split on a character, not a byte boundary); use the + high-level Header class to deal with these issues. convert defaults + to False. + + The type of encoding (base64 or quoted-printable) will be based on + self.header_encoding. + """ + cset = self.get_output_charset() + if convert: + 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) + elif self.header_encoding == QP: + 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) + if lenb64 < lenqp: + return email.base64mime.header_encode(s, cset) + else: + return email.quoprimime.header_encode(s, cset, maxlinelen=None) + else: + return s + + def body_encode(self, s, convert=True): + """Body-encode a string and convert it to output_charset. + + If convert is True (the default), the string will be converted from + the input charset to output charset automatically. Unlike + header_encode(), there are no issues with byte boundaries and + multibyte charsets in email bodies, so this is usually pretty safe. + + The type of encoding (base64 or quoted-printable) will be based on + self.body_encoding. + """ + if convert: + 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) + elif self.body_encoding is QP: + return email.quoprimime.body_encode(s) + else: + return s diff --git a/Lib/email/encoders.py b/Lib/email/encoders.py new file mode 100644 index 0000000..06016cd --- /dev/null +++ b/Lib/email/encoders.py @@ -0,0 +1,88 @@ +# 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 + return enc.replace(' ', '=20') + + +def _bencode(s): + # We can't quite use base64.encodestring() since it tacks on a "courtesy + # newline". Blech! + if not s: + return s + hasnewline = (s[-1] == '\n') + value = base64.encodestring(s) + if not hasnewline and value[-1] == '\n': + return value[:-1] + return value + + + +def encode_base64(msg): + """Encode the message's payload in Base64. + + Also, add an appropriate Content-Transfer-Encoding header. + """ + orig = msg.get_payload() + encdata = _bencode(orig) + msg.set_payload(encdata) + msg['Content-Transfer-Encoding'] = 'base64' + + + +def encode_quopri(msg): + """Encode the message's payload in quoted-printable. + + Also, add an appropriate Content-Transfer-Encoding header. + """ + orig = msg.get_payload() + encdata = _qencode(orig) + msg.set_payload(encdata) + msg['Content-Transfer-Encoding'] = 'quoted-printable' + + + +def encode_7or8bit(msg): + """Set the Content-Transfer-Encoding header to 7bit or 8bit.""" + orig = msg.get_payload() + if orig is None: + # There's no payload. For backwards compatibility we use 7bit + msg['Content-Transfer-Encoding'] = '7bit' + return + # We play a trick to make this go fast. If encoding to ASCII succeeds, we + # know the data must be 7bit, otherwise treat it as 8bit. + try: + orig.encode('ascii') + except UnicodeError: + # iso-2022-* is non-ASCII but still 7-bit + charset = msg.get_charset() + output_cset = charset and charset.output_charset + if output_cset and output_cset.lower().startswith('iso-2202-'): + msg['Content-Transfer-Encoding'] = '7bit' + else: + msg['Content-Transfer-Encoding'] = '8bit' + else: + msg['Content-Transfer-Encoding'] = '7bit' + + + +def encode_noop(msg): + """Do nothing.""" diff --git a/Lib/email/errors.py b/Lib/email/errors.py new file mode 100644 index 0000000..d52a624 --- /dev/null +++ b/Lib/email/errors.py @@ -0,0 +1,57 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""email package exception classes.""" + + + +class MessageError(Exception): + """Base class for errors in the email package.""" + + +class MessageParseError(MessageError): + """Base class for message parsing errors.""" + + +class HeaderParseError(MessageParseError): + """Error while parsing headers.""" + + +class BoundaryError(MessageParseError): + """Couldn't find terminating boundary.""" + + +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: + """Base class for a message defect.""" + + def __init__(self, line=None): + self.line = line + +class NoBoundaryInMultipartDefect(MessageDefect): + """A message claimed to be a multipart but had no boundary parameter.""" + +class StartBoundaryNotFoundDefect(MessageDefect): + """The claimed start boundary was never found.""" + +class FirstHeaderLineIsContinuationDefect(MessageDefect): + """A message had a continuation line as its first header line.""" + +class MisplacedEnvelopeHeaderDefect(MessageDefect): + """A 'Unix-from' header was found in the middle of a header block.""" + +class MalformedHeaderDefect(MessageDefect): + """Found a header that was missing a colon, or was otherwise malformed.""" + +class MultipartInvariantViolationDefect(MessageDefect): + """A message claimed to be a multipart but no subparts were found.""" diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py new file mode 100644 index 0000000..afb02b3 --- /dev/null +++ b/Lib/email/feedparser.py @@ -0,0 +1,480 @@ +# Copyright (C) 2004-2006 Python Software Foundation +# Authors: Baxter, Wouters and Warsaw +# Contact: email-sig@python.org + +"""FeedParser - An email feed parser. + +The feed parser implements an interface for incrementally parsing an email +message, line by line. This has advantages for certain applications, such as +those reading email messages off a socket. + +FeedParser.feed() is the primary interface for pushing new data into the +parser. It returns when there's nothing more it can do with the available +data. When you have no more data to push into the parser, call .close(). +This completes the parsing and returns the root message object. + +The other advantage of this parser is that it will never throw a parsing +exception. Instead, when it finds something unexpected, it adds a 'defect' to +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 + +NLCRE = re.compile('\r\n|\r|\n') +NLCRE_bol = re.compile('(\r\n|\r|\n)') +NLCRE_eol = re.compile('(\r\n|\r|\n)$') +NLCRE_crack = re.compile('(\r\n|\r|\n)') +# RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character +# except controls, SP, and ":". +headerRE = re.compile(r'^(From |[\041-\071\073-\176]{1,}:|[\t ])') +EMPTYSTRING = '' +NL = '\n' + +NeedMoreData = object() + + + +class BufferedSubFile(object): + """A file-ish object that can have new data loaded into it. + + You can also push and pop line-matching predicates onto a stack. When the + current predicate matches the current line, a false EOF response + (i.e. empty string) is returned instead. This lets the parser adhere to a + simple abstraction -- it parses until EOF closes the current message. + """ + def __init__(self): + # The last partial line pushed into this object. + self._partial = '' + # The list of full, pushed lines, in reverse order + self._lines = [] + # The stack of false-EOF checking predicates. + self._eofstack = [] + # A flag indicating whether the file has been closed or not. + self._closed = False + + def push_eof_matcher(self, pred): + self._eofstack.append(pred) + + def pop_eof_matcher(self): + return self._eofstack.pop() + + def close(self): + # Don't forget any trailing partial line. + self._lines.append(self._partial) + self._partial = '' + self._closed = True + + def readline(self): + if not self._lines: + if self._closed: + return '' + return NeedMoreData + # Pop the line off the stack and see if it matches the current + # false-EOF predicate. + line = self._lines.pop() + # RFC 2046, section 5.1.2 requires us to recognize outer level + # boundaries at any level of inner nesting. Do this, but be sure it's + # in the order of most to least nested. + for ateof in self._eofstack[::-1]: + if ateof(line): + # We're at the false EOF. But push the last line back first. + self._lines.append(line) + return '' + return line + + def unreadline(self, line): + # Let the consumer push a line back into the buffer. + assert line is not NeedMoreData + self._lines.append(line) + + def push(self, data): + """Push some new data into this object.""" + # Handle any previous leftovers + data, self._partial = self._partial + data, '' + # Crack into lines, but preserve the newlines on the end of each + parts = NLCRE_crack.split(data) + # The *ahem* interesting behaviour of re.split when supplied grouping + # parentheses is that the last element of the resulting list is the + # data after the final RE. In the case of a NL/CR terminated string, + # this is the empty string. + self._partial = parts.pop() + # parts is a list of strings, alternating between the line contents + # and the eol character(s). Gather up a list of lines after + # re-attaching the newlines. + lines = [] + for i in range(len(parts) // 2): + lines.append(parts[i*2] + parts[i*2+1]) + self.pushlines(lines) + + def pushlines(self, lines): + # Reverse and insert at the front of the lines. + self._lines[:0] = lines[::-1] + + def is_closed(self): + return self._closed + + def __iter__(self): + return self + + def next(self): + line = self.readline() + if line == '': + raise StopIteration + return line + + + +class FeedParser: + """A feed-style parser of email.""" + + def __init__(self, _factory=message.Message): + """_factory is called with no arguments to create a new message obj""" + self._factory = _factory + self._input = BufferedSubFile() + self._msgstack = [] + self._parse = self._parsegen().next + self._cur = None + self._last = None + self._headersonly = False + + # Non-public interface for supporting Parser's headersonly flag + def _set_headersonly(self): + self._headersonly = True + + def feed(self, data): + """Push more data into the parser.""" + self._input.push(data) + self._call_parse() + + def _call_parse(self): + try: + self._parse() + except StopIteration: + pass + + def close(self): + """Parse all remaining data and return the root message object.""" + self._input.close() + self._call_parse() + root = self._pop_message() + assert not self._msgstack + # Look for final set of defects + if root.get_content_maintype() == 'multipart' \ + and not root.is_multipart(): + root.defects.append(errors.MultipartInvariantViolationDefect()) + return root + + def _new_message(self): + msg = self._factory() + if self._cur and self._cur.get_content_type() == 'multipart/digest': + msg.set_default_type('message/rfc822') + if self._msgstack: + self._msgstack[-1].attach(msg) + self._msgstack.append(msg) + self._cur = msg + self._last = msg + + def _pop_message(self): + retval = self._msgstack.pop() + if self._msgstack: + self._cur = self._msgstack[-1] + else: + self._cur = None + return retval + + def _parsegen(self): + # Create a new message and start by parsing headers. + self._new_message() + headers = [] + # Collect the headers, searching for a line that doesn't match the RFC + # 2822 header or continuation pattern (including an empty line). + for line in self._input: + if line is NeedMoreData: + yield NeedMoreData + continue + if not headerRE.match(line): + # If we saw the RFC defined header/body separator + # (i.e. newline), just throw it away. Otherwise the line is + # part of the body so push it back. + if not NLCRE.match(line): + self._input.unreadline(line) + break + headers.append(line) + # Done with the headers, so parse them and figure out what we're + # supposed to see in the body of the message. + self._parse_headers(headers) + # Headers-only parsing is a backwards compatibility hack, which was + # necessary in the older parser, which could throw errors. All + # remaining lines in the input are thrown into the message body. + if self._headersonly: + lines = [] + while True: + line = self._input.readline() + if line is NeedMoreData: + yield NeedMoreData + continue + if line == '': + break + lines.append(line) + self._cur.set_payload(EMPTYSTRING.join(lines)) + return + if self._cur.get_content_type() == 'message/delivery-status': + # message/delivery-status contains blocks of headers separated by + # a blank line. We'll represent each header block as a separate + # nested message object, but the processing is a bit different + # than standard message/* types because there is no body for the + # nested messages. A blank line separates the subparts. + while True: + self._input.push_eof_matcher(NLCRE.match) + for retval in self._parsegen(): + if retval is NeedMoreData: + yield NeedMoreData + continue + break + msg = self._pop_message() + # We need to pop the EOF matcher in order to tell if we're at + # the end of the current file, not the end of the last block + # of message headers. + self._input.pop_eof_matcher() + # The input stream must be sitting at the newline or at the + # EOF. We want to see if we're at the end of this subpart, so + # first consume the blank line, then test the next line to see + # if we're at this subpart's EOF. + while True: + line = self._input.readline() + if line is NeedMoreData: + yield NeedMoreData + continue + break + while True: + line = self._input.readline() + if line is NeedMoreData: + yield NeedMoreData + continue + break + if line == '': + break + # Not at EOF so this is a line we're going to need. + self._input.unreadline(line) + return + if self._cur.get_content_maintype() == 'message': + # The message claims to be a message/* type, then what follows is + # another RFC 2822 message. + for retval in self._parsegen(): + if retval is NeedMoreData: + yield NeedMoreData + continue + break + self._pop_message() + return + if self._cur.get_content_maintype() == 'multipart': + boundary = self._cur.get_boundary() + if boundary is None: + # The message /claims/ to be a multipart but it has not + # 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()) + lines = [] + for line in self._input: + if line is NeedMoreData: + yield NeedMoreData + continue + lines.append(line) + self._cur.set_payload(EMPTYSTRING.join(lines)) + return + # Create a line match predicate which matches the inter-part + # boundary as well as the end-of-multipart boundary. Don't push + # this onto the input stream until we've scanned past the + # preamble. + separator = '--' + boundary + boundaryre = re.compile( + '(?P' + re.escape(separator) + + r')(?P--)?(?P[ \t]*)(?P\r\n|\r|\n)?$') + capturing_preamble = True + preamble = [] + linesep = False + while True: + line = self._input.readline() + if line is NeedMoreData: + yield NeedMoreData + continue + if line == '': + break + mo = boundaryre.match(line) + if mo: + # If we're looking at the end boundary, we're done with + # this multipart. If there was a newline at the end of + # the closing boundary, then we need to initialize the + # epilogue with the empty string (see below). + if mo.group('end'): + linesep = mo.group('linesep') + break + # We saw an inter-part boundary. Were we in the preamble? + if capturing_preamble: + if preamble: + # According to RFC 2046, the last newline belongs + # to the boundary. + lastline = preamble[-1] + eolmo = NLCRE_eol.search(lastline) + if eolmo: + preamble[-1] = lastline[:-len(eolmo.group(0))] + self._cur.preamble = EMPTYSTRING.join(preamble) + capturing_preamble = False + self._input.unreadline(line) + continue + # We saw a boundary separating two parts. Consume any + # multiple boundary lines that may be following. Our + # interpretation of RFC 2046 BNF grammar does not produce + # body parts within such double boundaries. + while True: + line = self._input.readline() + if line is NeedMoreData: + yield NeedMoreData + continue + mo = boundaryre.match(line) + if not mo: + self._input.unreadline(line) + break + # Recurse to parse this subpart; the input stream points + # at the subpart's first line. + self._input.push_eof_matcher(boundaryre.match) + for retval in self._parsegen(): + if retval is NeedMoreData: + yield NeedMoreData + continue + break + # Because of RFC 2046, the newline preceding the boundary + # separator actually belongs to the boundary, not the + # previous subpart's payload (or epilogue if the previous + # part is a multipart). + if self._last.get_content_maintype() == 'multipart': + epilogue = self._last.epilogue + if epilogue == '': + self._last.epilogue = None + elif epilogue is not None: + mo = NLCRE_eol.search(epilogue) + if mo: + end = len(mo.group(0)) + self._last.epilogue = epilogue[:-end] + else: + payload = self._last.get_payload() + if isinstance(payload, basestring): + mo = NLCRE_eol.search(payload) + if mo: + payload = payload[:-len(mo.group(0))] + self._last.set_payload(payload) + self._input.pop_eof_matcher() + self._pop_message() + # Set the multipart up for newline cleansing, which will + # happen if we're in a nested multipart. + self._last = self._cur + else: + # I think we must be in the preamble + assert capturing_preamble + preamble.append(line) + # We've seen either the EOF or the end boundary. If we're still + # capturing the preamble, we never saw the start boundary. Note + # 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.set_payload(EMPTYSTRING.join(preamble)) + epilogue = [] + for line in self._input: + if line is NeedMoreData: + yield NeedMoreData + continue + self._cur.epilogue = EMPTYSTRING.join(epilogue) + return + # If the end boundary ended in a newline, we'll need to make sure + # the epilogue isn't None + if linesep: + epilogue = [''] + else: + epilogue = [] + for line in self._input: + if line is NeedMoreData: + yield NeedMoreData + continue + epilogue.append(line) + # Any CRLF at the front of the epilogue is not technically part of + # the epilogue. Also, watch out for an empty string epilogue, + # which means a single newline. + if epilogue: + firstline = epilogue[0] + bolmo = NLCRE_bol.match(firstline) + if bolmo: + epilogue[0] = firstline[len(bolmo.group(0)):] + self._cur.epilogue = EMPTYSTRING.join(epilogue) + return + # Otherwise, it's some non-multipart type, so the entire rest of the + # file contents becomes the payload. + lines = [] + for line in self._input: + if line is NeedMoreData: + yield NeedMoreData + continue + lines.append(line) + self._cur.set_payload(EMPTYSTRING.join(lines)) + + def _parse_headers(self, lines): + # Passed a list of lines that make up the headers for the current msg + lastheader = '' + lastvalue = [] + for lineno, line in enumerate(lines): + # Check for continuation + if line[0] in ' \t': + if not lastheader: + # 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) + self._cur.defects.append(defect) + continue + lastvalue.append(line) + continue + if lastheader: + # XXX reconsider the joining of folded lines + lhdr = EMPTYSTRING.join(lastvalue)[:-1].rstrip('\r\n') + self._cur[lastheader] = lhdr + lastheader, lastvalue = '', [] + # Check for envelope header, i.e. unix-from + if line.startswith('From '): + if lineno == 0: + # Strip off the trailing newline + mo = NLCRE_eol.search(line) + if mo: + line = line[:-len(mo.group(0))] + self._cur.set_unixfrom(line) + continue + elif lineno == len(lines) - 1: + # Something looking like a unix-from at the end - it's + # probably the first line of the body, so push back the + # line and stop. + self._input.unreadline(line) + return + else: + # Weirdly placed unix-from line. Note this as a defect + # and ignore it. + 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) + self._cur.defects.append(defect) + continue + lastheader = line[:i] + lastvalue = [line[i+1:].lstrip()] + # Done with all the lines, so handle the last header. + if lastheader: + # XXX reconsider the joining of folded lines + self._cur[lastheader] = EMPTYSTRING.join(lastvalue).rstrip('\r\n') diff --git a/Lib/email/generator.py b/Lib/email/generator.py new file mode 100644 index 0000000..6e7a515 --- /dev/null +++ b/Lib/email/generator.py @@ -0,0 +1,348 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""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 + +UNDERSCORE = '_' +NL = '\n' + +fcre = re.compile(r'^From ', re.MULTILINE) + +def _is8bitstring(s): + if isinstance(s, str): + try: + unicode(s, 'us-ascii') + except UnicodeError: + return True + return False + + + +class Generator: + """Generates output from a Message object tree. + + This basic generator writes the message to the given file object as plain + text. + """ + # + # Public interface + # + + def __init__(self, outfp, mangle_from_=True, maxheaderlen=78): + """Create the generator for message flattening. + + outfp is the output file-like object for writing the message to. It + must have a write() method. + + Optional mangle_from_ is a flag that, when True (the default), escapes + From_ lines in the body of the message by putting a `>' in front of + them. + + Optional maxheaderlen specifies the longest length for a non-continued + header. When a header line is longer (in characters, with tabs + expanded to 8 spaces) than maxheaderlen, the header will split as + defined in the Header class. Set maxheaderlen to zero to disable + header wrapping. The default is 78, as recommended (but not required) + by RFC 2822. + """ + self._fp = outfp + self._mangle_from_ = mangle_from_ + self._maxheaderlen = maxheaderlen + + def write(self, s): + # Just delegate to the file object + self._fp.write(s) + + def flatten(self, msg, unixfrom=False): + """Print the message object tree rooted at msg to the output file + specified when the Generator instance was created. + + unixfrom is a flag that forces the printing of a Unix From_ delimiter + before the first object in the message tree. If the original message + has no From_ delimiter, a `standard' one is crafted. By default, this + is False to inhibit the printing of any From_ delimiter. + + Note that for subobjects, no From_ line is printed. + """ + if unixfrom: + ufrom = msg.get_unixfrom() + if not ufrom: + ufrom = 'From nobody ' + time.ctime(time.time()) + print >> self._fp, ufrom + self._write(msg) + + def clone(self, fp): + """Clone this generator with the exact same options.""" + return self.__class__(fp, self._mangle_from_, self._maxheaderlen) + + # + # Protected interface - undocumented ;/ + # + + def _write(self, msg): + # We can't write the headers yet because of the following scenario: + # say a multipart message includes the boundary string somewhere in + # its body. We'd have to calculate the new boundary /before/ we write + # the headers so that we can write the correct Content-Type: + # parameter. + # + # The way we do this, so as to make the _handle_*() methods simpler, + # is to cache any subpart writes into a StringIO. The we write the + # headers and the StringIO contents. That way, subpart handlers can + # Do The Right Thing, and can still modify the Content-Type: header if + # necessary. + oldfp = self._fp + try: + self._fp = sfp = StringIO() + self._dispatch(msg) + finally: + self._fp = oldfp + # Write the headers. First we see if the message object wants to + # handle that itself. If not, we'll do it generically. + meth = getattr(msg, '_write_headers', None) + if meth is None: + self._write_headers(msg) + else: + meth(self) + self._fp.write(sfp.getvalue()) + + def _dispatch(self, msg): + # Get the Content-Type: for the message, then try to dispatch to + # self._handle__(). If there's no handler for the + # full MIME type, then dispatch to self._handle_(). If + # that's missing too, then dispatch to self._writeBody(). + main = msg.get_content_maintype() + sub = msg.get_content_subtype() + specific = UNDERSCORE.join((main, sub)).replace('-', '_') + meth = getattr(self, '_handle_' + specific, None) + if meth is None: + generic = main.replace('-', '_') + meth = getattr(self, '_handle_' + generic, None) + if meth is None: + meth = self._writeBody + meth(msg) + + # + # Default handlers + # + + def _write_headers(self, msg): + for h, v in msg.items(): + print >> self._fp, '%s:' % h, + if self._maxheaderlen == 0: + # Explicit no-wrapping + print >> self._fp, v + elif isinstance(v, Header): + # Header instances know what to do + print >> self._fp, v.encode() + elif _is8bitstring(v): + # If we have raw 8bit data in a byte string, we have no idea + # what the encoding is. There is no safe way to split this + # string. If it's ascii-subset, then we could do a normal + # ascii split, but if it's multibyte then we could break the + # string. There's no way to know so the least harm seems to + # be to not split the string and risk it being too long. + print >> self._fp, v + else: + # Header's got lots of smarts, so use it. + print >> self._fp, Header( + v, maxlinelen=self._maxheaderlen, + header_name=h, continuation_ws='\t').encode() + # A blank line always separates headers from body + print >> self._fp + + # + # Handlers for writing types and subtypes + # + + def _handle_text(self, msg): + payload = msg.get_payload() + if payload is None: + return + if not isinstance(payload, basestring): + raise TypeError('string payload expected: %s' % type(payload)) + if self._mangle_from_: + payload = fcre.sub('>From ', payload) + self._fp.write(payload) + + # Default body handler + _writeBody = _handle_text + + def _handle_multipart(self, msg): + # The trick here is to write out each part separately, merge them all + # together, and then make sure that the boundary we've chosen isn't + # present in the payload. + msgtexts = [] + subparts = msg.get_payload() + if subparts is None: + subparts = [] + elif isinstance(subparts, basestring): + # e.g. a non-strict parse of a message with no starting boundary. + self._fp.write(subparts) + return + elif not isinstance(subparts, list): + # Scalar payload + subparts = [subparts] + for part in subparts: + s = StringIO() + g = self.clone(s) + g.flatten(part, unixfrom=False) + msgtexts.append(s.getvalue()) + # Now make sure the boundary we've selected doesn't appear in any of + # the message texts. + alltext = NL.join(msgtexts) + # BAW: What about boundaries that are wrapped in double-quotes? + boundary = msg.get_boundary(failobj=_make_boundary(alltext)) + # If we had to calculate a new boundary because the body text + # contained that string, set the new boundary. We don't do it + # unconditionally because, while set_boundary() preserves order, it + # doesn't preserve newlines/continuations in headers. This is no big + # deal in practice, but turns out to be inconvenient for the unittest + # suite. + if msg.get_boundary() <> boundary: + msg.set_boundary(boundary) + # If there's a preamble, write it out, with a trailing CRLF + if msg.preamble is not None: + print >> self._fp, msg.preamble + # dash-boundary transport-padding CRLF + print >> self._fp, '--' + boundary + # body-part + if msgtexts: + self._fp.write(msgtexts.pop(0)) + # *encapsulation + # --> delimiter transport-padding + # --> CRLF body-part + for body_part in msgtexts: + # delimiter transport-padding CRLF + print >> self._fp, '\n--' + boundary + # body-part + self._fp.write(body_part) + # close-delimiter transport-padding + self._fp.write('\n--' + boundary + '--') + if msg.epilogue is not None: + print >> self._fp + self._fp.write(msg.epilogue) + + def _handle_message_delivery_status(self, msg): + # We can't just write the headers directly to self's file object + # because this will leave an extra newline between the last header + # block and the boundary. Sigh. + blocks = [] + for part in msg.get_payload(): + s = StringIO() + g = self.clone(s) + g.flatten(part, unixfrom=False) + text = s.getvalue() + lines = text.split('\n') + # Strip off the unnecessary trailing empty line + if lines and lines[-1] == '': + blocks.append(NL.join(lines[:-1])) + else: + blocks.append(text) + # Now join all the blocks with an empty line. This has the lovely + # effect of separating each block with an empty line, but not adding + # an extra one after the last one. + self._fp.write(NL.join(blocks)) + + def _handle_message(self, msg): + s = StringIO() + g = self.clone(s) + # The payload of a message/rfc822 part should be a multipart sequence + # of length 1. The zeroth element of the list should be the Message + # object for the subpart. Extract that object, stringify it, and + # write it out. + g.flatten(msg.get_payload(0), unixfrom=False) + self._fp.write(s.getvalue()) + + + +_FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]' + +class DecodedGenerator(Generator): + """Generator a text representation of a message. + + Like the Generator base class, except that non-text parts are substituted + with a format string representing the part. + """ + def __init__(self, outfp, mangle_from_=True, maxheaderlen=78, fmt=None): + """Like Generator.__init__() except that an additional optional + argument is allowed. + + Walks through all subparts of a message. If the subpart is of main + type `text', then it prints the decoded payload of the subpart. + + Otherwise, fmt is a format string that is used instead of the message + payload. fmt is expanded with the following keywords (in + %(keyword)s format): + + type : Full MIME type of the non-text part + maintype : Main MIME type of the non-text part + subtype : Sub-MIME type of the non-text part + filename : Filename of the non-text part + description: Description associated with the non-text part + encoding : Content transfer encoding of the non-text part + + The default value for fmt is None, meaning + + [Non-text (%(type)s) part of message omitted, filename %(filename)s] + """ + Generator.__init__(self, outfp, mangle_from_, maxheaderlen) + if fmt is None: + self._fmt = _FMT + else: + self._fmt = fmt + + def _dispatch(self, msg): + for part in msg.walk(): + maintype = part.get_content_maintype() + if maintype == 'text': + print >> self, part.get_payload(decode=True) + elif maintype == 'multipart': + # Just skip this + pass + else: + print >> self, self._fmt % { + 'type' : part.get_content_type(), + 'maintype' : part.get_content_maintype(), + 'subtype' : part.get_content_subtype(), + 'filename' : part.get_filename('[no filename]'), + 'description': part.get('Content-Description', + '[no description]'), + 'encoding' : part.get('Content-Transfer-Encoding', + '[no encoding]'), + } + + + +# Helper +_width = len(repr(sys.maxint-1)) +_fmt = '%%0%dd' % _width + +def _make_boundary(text=None): + # Craft a random boundary. If text is given, ensure that the chosen + # boundary doesn't appear in the text. + token = random.randrange(sys.maxint) + boundary = ('=' * 15) + (_fmt % token) + '==' + if text is None: + return boundary + b = boundary + counter = 0 + while True: + cre = re.compile('^--' + re.escape(b) + '(--)?$', re.MULTILINE) + if not cre.search(text): + break + b = boundary + '.' + str(counter) + counter += 1 + return b diff --git a/Lib/email/header.py b/Lib/email/header.py new file mode 100644 index 0000000..183c337 --- /dev/null +++ b/Lib/email/header.py @@ -0,0 +1,502 @@ +# Copyright (C) 2002-2006 Python Software Foundation +# Author: Ben Gertzfield, Barry Warsaw +# Contact: email-sig@python.org + +"""Header encoding and decoding functionality.""" + +__all__ = [ + 'Header', + 'decode_header', + 'make_header', + ] + +import re +import binascii + +import email.quoprimime +import email.base64mime + +from email.errors import HeaderParseError +from email.charset import Charset + +NL = '\n' +SPACE = ' ' +USPACE = u' ' +SPACE8 = ' ' * 8 +UEMPTYSTRING = u'' + +MAXLINELEN = 76 + +USASCII = Charset('us-ascii') +UTF8 = Charset('utf-8') + +# Match encoded-word strings in the form =?charset?q?Hello_World?= +ecre = re.compile(r''' + =\? # literal =? + (?P[^?]*?) # non-greedy up to the next ? is the charset + \? # literal ? + (?P[qb]) # either a "q" or a "b", case insensitive + \? # literal ? + (?P.*?) # non-greedy up to the next ?= is the encoded string + \?= # literal ?= + ''', re.VERBOSE | re.IGNORECASE) + +# Field name regexp, including trailing colon, but not separating whitespace, +# according to RFC 2822. Character range is from tilde to exclamation mark. +# For use with .match() +fcre = re.compile(r'[\041-\176]+:$') + + + +# Helpers +_max_append = email.quoprimime._max_append + + + +def decode_header(header): + """Decode a message header value without converting charset. + + Returns a list of (decoded_string, charset) pairs containing each of the + decoded parts of the header. Charset is None for non-encoded parts of the + header, otherwise a lower-case string containing the name of the character + set specified in the encoded string. + + An email.Errors.HeaderParseError may be raised when certain decoding error + occurs (e.g. a base64 decoding exception). + """ + # If no encoding, just return the header + header = str(header) + if not ecre.search(header): + return [(header, None)] + decoded = [] + dec = '' + for line in header.splitlines(): + # This line might not have an encoding in it + if not ecre.search(line): + decoded.append((line, None)) + continue + parts = ecre.split(line) + while parts: + unenc = parts.pop(0).strip() + if unenc: + # Should we continue a long line? + if decoded and decoded[-1][1] is None: + decoded[-1] = (decoded[-1][0] + SPACE + unenc, None) + else: + decoded.append((unenc, None)) + if parts: + charset, encoding = [s.lower() for s in parts[0:2]] + encoded = parts[2] + dec = None + if encoding == 'q': + dec = email.quoprimime.header_decode(encoded) + elif encoding == 'b': + try: + 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 + # when/if we get exception chaining, we'll preserve it. + raise HeaderParseError + if dec is None: + dec = encoded + + if decoded and decoded[-1][1] == charset: + decoded[-1] = (decoded[-1][0] + dec, decoded[-1][1]) + else: + decoded.append((dec, charset)) + del parts[0:3] + return decoded + + + +def make_header(decoded_seq, maxlinelen=None, header_name=None, + continuation_ws=' '): + """Create a Header from a sequence of pairs as returned by decode_header() + + decode_header() takes a header value string and returns a sequence of + pairs of the format (decoded_string, charset) where charset is the string + name of the character set. + + This function takes one of those sequence of pairs and returns a Header + instance. Optional maxlinelen, header_name, and continuation_ws are as in + the Header constructor. + """ + h = Header(maxlinelen=maxlinelen, header_name=header_name, + continuation_ws=continuation_ws) + for s, charset in decoded_seq: + # None means us-ascii but we can simply pass it on to h.append() + if charset is not None and not isinstance(charset, Charset): + charset = Charset(charset) + h.append(s, charset) + return h + + + +class Header: + def __init__(self, s=None, charset=None, + maxlinelen=None, header_name=None, + continuation_ws=' ', errors='strict'): + """Create a MIME-compliant header that can contain many character sets. + + Optional s is the initial header value. If None, the initial header + value is not set. You can later append to the header with .append() + method calls. s may be a byte string or a Unicode string, but see the + .append() documentation for semantics. + + Optional charset serves two purposes: it has the same meaning as the + charset argument to the .append() method. It also sets the default + character set for all subsequent .append() calls that omit the charset + argument. If charset is not provided in the constructor, the us-ascii + charset is used both as s's initial charset and as the default for + subsequent .append() calls. + + The maximum line length can be specified explicit via maxlinelen. For + splitting the first line to a shorter value (to account for the field + header which isn't included in s, e.g. `Subject') pass in the name of + the field in header_name. The default maxlinelen is 76. + + continuation_ws must be RFC 2822 compliant folding whitespace (usually + either a space or a hard tab) which will be prepended to continuation + lines. + + errors is passed through to the .append() call. + """ + if charset is None: + charset = USASCII + if not isinstance(charset, Charset): + charset = Charset(charset) + self._charset = charset + self._continuation_ws = continuation_ws + cws_expanded_len = len(continuation_ws.replace('\t', SPACE8)) + # BAW: I believe `chunks' and `maxlinelen' should be non-public. + self._chunks = [] + if s is not None: + self.append(s, charset, errors) + if maxlinelen is None: + maxlinelen = MAXLINELEN + if header_name is None: + # We don't know anything about the field header so the first line + # is the same length as subsequent lines. + self._firstlinelen = maxlinelen + else: + # The first line should be shorter to take into account the field + # header. Also subtract off 2 extra for the colon and space. + self._firstlinelen = maxlinelen - len(header_name) - 2 + # Second and subsequent lines should subtract off the length in + # columns of the continuation whitespace prefix. + self._maxlinelen = maxlinelen - cws_expanded_len + + def __str__(self): + """A synonym for self.encode().""" + return self.encode() + + def __unicode__(self): + """Helper for the built-in unicode function.""" + uchunks = [] + lastcs = None + for s, charset in self._chunks: + # We must preserve spaces between encoded and non-encoded word + # boundaries, which means for us we need to add a space when we go + # from a charset to None/us-ascii, or from None/us-ascii to a + # charset. Only do this for the second and subsequent chunks. + nextcs = charset + if uchunks: + if lastcs not in (None, 'us-ascii'): + if nextcs in (None, 'us-ascii'): + uchunks.append(USPACE) + nextcs = None + elif nextcs not in (None, 'us-ascii'): + uchunks.append(USPACE) + lastcs = nextcs + uchunks.append(unicode(s, str(charset))) + return UEMPTYSTRING.join(uchunks) + + # Rich comparison operators for equality only. BAW: does it make sense to + # have or explicitly disable <, <=, >, >= operators? + def __eq__(self, other): + # other may be a Header or a string. Both are fine so coerce + # ourselves to a string, swap the args and do another comparison. + return other == self.encode() + + def __ne__(self, other): + return not self == other + + def append(self, s, charset=None, errors='strict'): + """Append a string to the MIME header. + + Optional charset, if given, should be a Charset instance or the name + of a character set (which will be converted to a Charset instance). A + value of None (the default) means that the charset given in the + constructor is used. + + s may be a byte string or a Unicode string. If it is a byte string + (i.e. isinstance(s, str) is true), then charset is the encoding of + that byte string, and a UnicodeError will be raised if the string + cannot be decoded with that charset. If s is a Unicode string, then + charset is a hint specifying the character set of the characters in + the string. In this case, when producing an RFC 2822 compliant header + using RFC 2047 rules, the Unicode string will be encoded using the + following charsets in order: us-ascii, the charset hint, utf-8. The + first character set not to provoke a UnicodeError is used. + + Optional `errors' is passed as the third argument to any unicode() or + ustr.encode() call. + """ + if charset is None: + charset = self._charset + elif not isinstance(charset, Charset): + charset = Charset(charset) + # If the charset is our faux 8bit charset, leave the string unchanged + if charset <> '8bit': + # We need to test that the string can be converted to unicode and + # back to a byte string, given the input and output codecs of the + # charset. + if isinstance(s, str): + # Possibly raise UnicodeError if the byte string can't be + # converted to a unicode with the input codec of the charset. + incodec = charset.input_codec or 'us-ascii' + ustr = unicode(s, incodec, errors) + # Now make sure that the unicode could be converted back to a + # byte string with the output codec, which may be different + # than the iput coded. Still, use the original byte string. + outcodec = charset.output_codec or 'us-ascii' + ustr.encode(outcodec, errors) + elif isinstance(s, unicode): + # Now we have to be sure the unicode string can be converted + # to a byte string with a reasonable output codec. We want to + # use the byte string in the chunk. + for charset in USASCII, charset, UTF8: + try: + outcodec = charset.output_codec or 'us-ascii' + s = s.encode(outcodec, errors) + break + except UnicodeError: + pass + else: + assert False, 'utf-8 conversion failed' + self._chunks.append((s, charset)) + + def _split(self, s, charset, maxlinelen, splitchars): + # Split up a header safely for use with encode_chunks. + splittable = charset.to_splittable(s) + encoded = charset.from_splittable(splittable, True) + elen = charset.encoded_header_len(encoded) + # If the line's encoded length first, just return it + if elen <= maxlinelen: + return [(encoded, charset)] + # If we have undetermined raw 8bit characters sitting in a byte + # string, we really don't know what the right thing to do is. We + # can't really split it because it might be multibyte data which we + # could break if we split it between pairs. The least harm seems to + # be to not split the header at all, but that means they could go out + # longer than maxlinelen. + if charset == '8bit': + return [(s, charset)] + # BAW: I'm not sure what the right test here is. What we're trying to + # do is be faithful to RFC 2822's recommendation that ($2.2.3): + # + # "Note: Though structured field bodies are defined in such a way that + # folding can take place between many of the lexical tokens (and even + # within some of the lexical tokens), folding SHOULD be limited to + # placing the CRLF at higher-level syntactic breaks." + # + # For now, I can only imagine doing this when the charset is us-ascii, + # although it's possible that other charsets may also benefit from the + # higher-level syntactic breaks. + elif charset == 'us-ascii': + return self._split_ascii(s, charset, maxlinelen, splitchars) + # BAW: should we use encoded? + elif elen == len(s): + # We can split on _maxlinelen boundaries because we know that the + # encoding won't change the size of the string + splitpnt = maxlinelen + first = charset.from_splittable(splittable[:splitpnt], False) + last = charset.from_splittable(splittable[splitpnt:], False) + else: + # Binary search for split point + first, last = _binsplit(splittable, charset, maxlinelen) + # first is of the proper length so just wrap it in the appropriate + # chrome. last must be recursively split. + fsplittable = charset.to_splittable(first) + fencoded = charset.from_splittable(fsplittable, True) + chunk = [(fencoded, charset)] + return chunk + self._split(last, charset, self._maxlinelen, splitchars) + + def _split_ascii(self, s, charset, firstlen, splitchars): + chunks = _split_ascii(s, firstlen, self._maxlinelen, + self._continuation_ws, splitchars) + return zip(chunks, [charset]*len(chunks)) + + def _encode_chunks(self, newchunks, maxlinelen): + # MIME-encode a header with many different charsets and/or encodings. + # + # Given a list of pairs (string, charset), return a MIME-encoded + # string suitable for use in a header field. Each pair may have + # different charsets and/or encodings, and the resulting header will + # accurately reflect each setting. + # + # Each encoding can be email.Utils.QP (quoted-printable, for + # ASCII-like character sets like iso-8859-1), email.Utils.BASE64 + # (Base64, for non-ASCII like character sets like KOI8-R and + # iso-2022-jp), or None (no encoding). + # + # Each pair will be represented on a separate line; the resulting + # string will be in the format: + # + # =?charset1?q?Mar=EDa_Gonz=E1lez_Alonso?=\n + # =?charset2?b?SvxyZ2VuIEL2aW5n?=" + chunks = [] + for header, charset in newchunks: + if not header: + continue + if charset is None or charset.header_encoding is None: + s = header + else: + s = charset.header_encode(header) + # Don't add more folding whitespace than necessary + if chunks and chunks[-1].endswith(' '): + extra = '' + else: + extra = ' ' + _max_append(chunks, s, maxlinelen, extra) + joiner = NL + self._continuation_ws + return joiner.join(chunks) + + def encode(self, splitchars=';, '): + """Encode a message header into an RFC-compliant format. + + There are many issues involved in converting a given string for use in + an email header. Only certain character sets are readable in most + email clients, and as header strings can only contain a subset of + 7-bit ASCII, care must be taken to properly convert and encode (with + Base64 or quoted-printable) header strings. In addition, there is a + 75-character length limit on any given encoded header field, so + line-wrapping must be performed, even with double-byte character sets. + + This method will do its best to convert the string to the correct + character set used in email, and encode and line wrap it safely with + the appropriate scheme for that character set. + + If the given charset is not known or an error occurs during + conversion, this function will return the header untouched. + + Optional splitchars is a string containing characters to split long + ASCII lines on, in rough support of RFC 2822's `highest level + syntactic breaks'. This doesn't affect RFC 2047 encoded lines. + """ + newchunks = [] + maxlinelen = self._firstlinelen + lastlen = 0 + for s, charset in self._chunks: + # The first bit of the next chunk should be just long enough to + # fill the next line. Don't forget the space separating the + # encoded words. + targetlen = maxlinelen - lastlen - 1 + if targetlen < charset.encoded_header_len(''): + # Stick it on the next line + targetlen = maxlinelen + newchunks += self._split(s, charset, targetlen, splitchars) + lastchunk, lastcharset = newchunks[-1] + lastlen = lastcharset.encoded_header_len(lastchunk) + return self._encode_chunks(newchunks, maxlinelen) + + + +def _split_ascii(s, firstlen, restlen, continuation_ws, splitchars): + lines = [] + maxlen = firstlen + for line in s.splitlines(): + # Ignore any leading whitespace (i.e. continuation whitespace) already + # on the line, since we'll be adding our own. + line = line.lstrip() + if len(line) < maxlen: + lines.append(line) + maxlen = restlen + continue + # Attempt to split the line at the highest-level syntactic break + # possible. Note that we don't have a lot of smarts about field + # syntax; we just try to break on semi-colons, then commas, then + # whitespace. + for ch in splitchars: + if ch in line: + break + else: + # There's nothing useful to split the line on, not even spaces, so + # just append this line unchanged + lines.append(line) + maxlen = restlen + continue + # Now split the line on the character plus trailing whitespace + cre = re.compile(r'%s\s*' % ch) + if ch in ';,': + eol = ch + else: + eol = '' + joiner = eol + ' ' + joinlen = len(joiner) + wslen = len(continuation_ws.replace('\t', SPACE8)) + this = [] + linelen = 0 + for part in cre.split(line): + curlen = linelen + max(0, len(this)-1) * joinlen + partlen = len(part) + onfirstline = not lines + # We don't want to split after the field name, if we're on the + # first line and the field name is present in the header string. + if ch == ' ' and onfirstline and \ + len(this) == 1 and fcre.match(this[0]): + this.append(part) + linelen += partlen + elif curlen + partlen > maxlen: + if this: + lines.append(joiner.join(this) + eol) + # If this part is longer than maxlen and we aren't already + # splitting on whitespace, try to recursively split this line + # on whitespace. + if partlen > maxlen and ch <> ' ': + subl = _split_ascii(part, maxlen, restlen, + continuation_ws, ' ') + lines.extend(subl[:-1]) + this = [subl[-1]] + else: + this = [part] + linelen = wslen + len(this[-1]) + maxlen = restlen + else: + this.append(part) + linelen += partlen + # Put any left over parts on a line by themselves + if this: + lines.append(joiner.join(this)) + return lines + + + +def _binsplit(splittable, charset, maxlinelen): + i = 0 + j = len(splittable) + while i < j: + # Invariants: + # 1. splittable[:k] fits for all k <= i (note that we *assume*, + # at the start, that splittable[:0] fits). + # 2. splittable[:k] does not fit for any k > j (at the start, + # this means we shouldn't look at any k > len(splittable)). + # 3. We don't know about splittable[:k] for k in i+1..j. + # 4. We want to set i to the largest k that fits, with i <= k <= j. + # + m = (i+j+1) >> 1 # ceiling((i+j)/2); i < m <= j + chunk = charset.from_splittable(splittable[:m], True) + chunklen = charset.encoded_header_len(chunk) + if chunklen <= maxlinelen: + # m is acceptable, so is a new lower bound. + i = m + else: + # m is not acceptable, so final i must be < m. + j = m - 1 + # i == j. Invariant #1 implies that splittable[:i] fits, and + # invariant #2 implies that splittable[:i+1] does not fit, so i + # is what we're looking for. + first = charset.from_splittable(splittable[:i], False) + last = charset.from_splittable(splittable[i:], False) + return first, last diff --git a/Lib/email/iterators.py b/Lib/email/iterators.py new file mode 100644 index 0000000..e99f228 --- /dev/null +++ b/Lib/email/iterators.py @@ -0,0 +1,73 @@ +# 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 + + + +# This function will become a method of the Message class +def walk(self): + """Walk over the message tree, yielding each subpart. + + The walk is performed in depth-first order. This method is a + generator. + """ + yield self + if self.is_multipart(): + for subpart in self.get_payload(): + for subsubpart in subpart.walk(): + yield subsubpart + + + +# These two functions are imported into the Iterators.py interface module. +def body_line_iterator(msg, decode=False): + """Iterate over the parts, returning string payloads line-by-line. + + Optional decode (default False) is passed through to .get_payload(). + """ + for subpart in msg.walk(): + payload = subpart.get_payload(decode=decode) + if isinstance(payload, basestring): + for line in StringIO(payload): + yield line + + +def typed_subpart_iterator(msg, maintype='text', subtype=None): + """Iterate over the subparts with a given MIME type. + + Use `maintype' as the main MIME type to match against; this defaults to + "text". Optional `subtype' is the MIME subtype to match against; if + omitted, only the main type is matched. + """ + for subpart in msg.walk(): + if subpart.get_content_maintype() == maintype: + if subtype is None or subpart.get_content_subtype() == subtype: + yield subpart + + + +def _structure(msg, fp=None, level=0, include_default=False): + """A handy debugging aid""" + if fp is None: + fp = sys.stdout + tab = ' ' * (level * 4) + print >> fp, tab + msg.get_content_type(), + if include_default: + print >> fp, '[%s]' % msg.get_default_type() + else: + print >> fp + if msg.is_multipart(): + for subpart in msg.get_payload(): + _structure(subpart, fp, level+1, include_default) diff --git a/Lib/email/message.py b/Lib/email/message.py new file mode 100644 index 0000000..50d90b4 --- /dev/null +++ b/Lib/email/message.py @@ -0,0 +1,773 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Basic message object for the email package object model.""" + +__all__ = ['Message'] + +import re +import uu +import binascii +import warnings +from cStringIO import StringIO + +# Intrapackage imports +import email.charset +from email import utils +from email import errors + +SEMISPACE = '; ' + +# Regular expression used to split header parameters. BAW: this may be too +# simple. It isn't strictly RFC 2045 (section 5.1) compliant, but it catches +# most headers found in the wild. We may eventually need a full fledged +# parser eventually. +paramre = re.compile(r'\s*;\s*') +# Regular expression that matches `special' characters in parameters, the +# existance of which force quoting of the parameter value. +tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]') + + + +# Helper functions +def _formatparam(param, value=None, quote=True): + """Convenience function to format and return a key=value pair. + + This will quote the value if needed or if quote is true. + """ + if value is not None and len(value) > 0: + # A tuple is used for RFC 2231 encoded parameter values where items + # are (charset, language, value). charset is a string, not a Charset + # instance. + if isinstance(value, tuple): + # Encode as per RFC 2231 + param += '*' + 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)) + else: + return '%s=%s' % (param, value) + else: + return param + +def _parseparam(s): + plist = [] + while s[:1] == ';': + s = s[1:] + end = s.find(';') + while end > 0 and s.count('"', 0, end) % 2: + end = s.find(';', end + 1) + if end < 0: + end = len(s) + f = s[:end] + if '=' in f: + i = f.index('=') + f = f[:i].strip().lower() + '=' + f[i+1:].strip() + plist.append(f.strip()) + s = s[end:] + return plist + + +def _unquotevalue(value): + # 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]) + else: + return utils.unquote(value) + + + +class Message: + """Basic message object. + + A message object is defined as something that has a bunch of RFC 2822 + headers and a payload. It may optionally have an envelope header + (a.k.a. Unix-From or From_ header). If the message is a container (i.e. a + multipart or a message/rfc822), then the payload is a list of Message + objects, otherwise it is a string. + + Message objects implement part of the `mapping' interface, which assumes + there is exactly one occurrance of the header per message. Some headers + do in fact appear multiple times (e.g. Received) and for those headers, + you must use the explicit API to set or get all the headers. Not all of + the mapping methods are implemented. + """ + def __init__(self): + self._headers = [] + self._unixfrom = None + self._payload = None + self._charset = None + # Defaults for multipart messages + self.preamble = self.epilogue = None + self.defects = [] + # Default content type + self._default_type = 'text/plain' + + def __str__(self): + """Return the entire formatted message as a string. + This includes the headers, body, and envelope header. + """ + return self.as_string(unixfrom=True) + + def as_string(self, unixfrom=False): + """Return the entire formatted message as a string. + Optional `unixfrom' when True, means include the Unix From_ envelope + header. + + This is a convenience method and may not generate the message exactly + as you intend because by default it mangles lines that begin with + "From ". For more flexibility, use the flatten() method of a + Generator instance. + """ + from email.Generator import Generator + fp = StringIO() + g = Generator(fp) + g.flatten(self, unixfrom=unixfrom) + return fp.getvalue() + + def is_multipart(self): + """Return True if the message consists of multiple parts.""" + return isinstance(self._payload, list) + + # + # Unix From_ line + # + def set_unixfrom(self, unixfrom): + self._unixfrom = unixfrom + + def get_unixfrom(self): + return self._unixfrom + + # + # Payload manipulation. + # + def attach(self, payload): + """Add the given payload to the current payload. + + The current payload will always be a list of objects after this method + is called. If you want to set the payload to a scalar object, use + set_payload() instead. + """ + if self._payload is None: + self._payload = [payload] + else: + self._payload.append(payload) + + def get_payload(self, i=None, decode=False): + """Return a reference to the payload. + + The payload will either be a list object or a string. If you mutate + the list object, you modify the message's payload in place. Optional + i returns that index into the payload. + + Optional decode is a flag indicating whether the payload should be + decoded or not, according to the Content-Transfer-Encoding header + (default is False). + + When True and the message is not a multipart, the payload will be + decoded if this header's value is `quoted-printable' or `base64'. If + some other encoding is used, or the header is missing, or if the + payload has bogus data (i.e. bogus base64 or uuencoded data), the + payload is returned as-is. + + If the message is a multipart and the decode flag is True, then None + is returned. + """ + if i is None: + payload = self._payload + elif not isinstance(self._payload, list): + raise TypeError('Expected list, got %s' % type(self._payload)) + else: + payload = self._payload[i] + if decode: + if self.is_multipart(): + return None + cte = self.get('content-transfer-encoding', '').lower() + if cte == 'quoted-printable': + return utils._qdecode(payload) + elif cte == 'base64': + try: + 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, quiet=True) + payload = sfp.getvalue() + except uu.Error: + # Some decoding problem + return payload + # Everything else, including encodings with 8bit or 7bit are returned + # unchanged. + return payload + + def set_payload(self, payload, charset=None): + """Set the payload to the given value. + + Optional charset sets the message's default character set. See + set_charset() for details. + """ + self._payload = payload + if charset is not None: + self.set_charset(charset) + + def set_charset(self, charset): + """Set the charset of the payload to a given character set. + + charset can be a Charset instance, a string naming a character set, or + None. If it is a string it will be converted to a Charset instance. + If charset is None, the charset parameter will be removed from the + Content-Type field. Anything else will generate a TypeError. + + The message will be assumed to be of type text/* encoded with + charset.input_charset. It will be converted to charset.output_charset + and encoded properly, if needed, when generating the plain text + representation of the message. MIME headers (MIME-Version, + Content-Type, Content-Transfer-Encoding) will be added as needed. + + """ + if charset is None: + self.del_param('charset') + self._charset = None + return + if isinstance(charset, str): + 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? + self._charset = charset + if not self.has_key('MIME-Version'): + self.add_header('MIME-Version', '1.0') + if not self.has_key('Content-Type'): + self.add_header('Content-Type', 'text/plain', + charset=charset.get_output_charset()) + else: + self.set_param('charset', charset.get_output_charset()) + if str(charset) <> charset.get_output_charset(): + self._payload = charset.body_encode(self._payload) + if not self.has_key('Content-Transfer-Encoding'): + cte = charset.get_body_encoding() + try: + cte(self) + except TypeError: + self._payload = charset.body_encode(self._payload) + self.add_header('Content-Transfer-Encoding', cte) + + def get_charset(self): + """Return the Charset instance associated with the message's payload. + """ + return self._charset + + # + # MAPPING INTERFACE (partial) + # + def __len__(self): + """Return the total number of headers, including duplicates.""" + return len(self._headers) + + def __getitem__(self, name): + """Get a header value. + + Return None if the header is missing instead of raising an exception. + + Note that if the header appeared multiple times, exactly which + occurrance gets returned is undefined. Use get_all() to get all + the values matching a header field name. + """ + return self.get(name) + + def __setitem__(self, name, val): + """Set the value of a header. + + Note: this does not overwrite an existing header with the same field + name. Use __delitem__() first to delete any existing headers. + """ + self._headers.append((name, val)) + + def __delitem__(self, name): + """Delete all occurrences of a header, if present. + + Does not raise an exception if the header is missing. + """ + name = name.lower() + newheaders = [] + for k, v in self._headers: + if k.lower() <> name: + newheaders.append((k, v)) + self._headers = newheaders + + def __contains__(self, name): + return name.lower() in [k.lower() for k, v in self._headers] + + def has_key(self, name): + """Return true if the message contains the header.""" + missing = object() + return self.get(name, missing) is not missing + + def keys(self): + """Return a list of all the message's header field names. + + These will be sorted in the order they appeared in the original + message, or were added to the message, and may contain duplicates. + Any fields deleted and re-inserted are always appended to the header + list. + """ + return [k for k, v in self._headers] + + def values(self): + """Return a list of all the message's header values. + + These will be sorted in the order they appeared in the original + message, or were added to the message, and may contain duplicates. + Any fields deleted and re-inserted are always appended to the header + list. + """ + return [v for k, v in self._headers] + + def items(self): + """Get all the message's header fields and values. + + These will be sorted in the order they appeared in the original + message, or were added to the message, and may contain duplicates. + Any fields deleted and re-inserted are always appended to the header + list. + """ + return self._headers[:] + + def get(self, name, failobj=None): + """Get a header value. + + Like __getitem__() but return failobj instead of None when the field + is missing. + """ + name = name.lower() + for k, v in self._headers: + if k.lower() == name: + return v + return failobj + + # + # Additional useful stuff + # + + def get_all(self, name, failobj=None): + """Return a list of all the values for the named field. + + These will be sorted in the order they appeared in the original + message, and may contain duplicates. Any fields deleted and + re-inserted are always appended to the header list. + + If no such fields exist, failobj is returned (defaults to None). + """ + values = [] + name = name.lower() + for k, v in self._headers: + if k.lower() == name: + values.append(v) + if not values: + return failobj + return values + + def add_header(self, _name, _value, **_params): + """Extended header setting. + + name is the header field to add. keyword arguments can be used to set + additional parameters for the header field, with underscores converted + to dashes. Normally the parameter will be added as key="value" unless + value is None, in which case only the key will be added. + + Example: + + msg.add_header('content-disposition', 'attachment', filename='bud.gif') + """ + parts = [] + for k, v in _params.items(): + if v is None: + parts.append(k.replace('_', '-')) + else: + parts.append(_formatparam(k.replace('_', '-'), v)) + if _value is not None: + parts.insert(0, _value) + self._headers.append((_name, SEMISPACE.join(parts))) + + def replace_header(self, _name, _value): + """Replace a header. + + Replace the first matching header found in the message, retaining + header order and case. If no matching header was found, a KeyError is + raised. + """ + _name = _name.lower() + for i, (k, v) in zip(range(len(self._headers)), self._headers): + if k.lower() == _name: + self._headers[i] = (k, _value) + break + else: + raise KeyError(_name) + + # + # Use these three methods instead of the three above. + # + + def get_content_type(self): + """Return the message's content type. + + The returned string is coerced to lower case of the form + `maintype/subtype'. If there was no Content-Type header in the + message, the default type as given by get_default_type() will be + returned. Since according to RFC 2045, messages always have a default + type this will always return a value. + + RFC 2045 defines a message's default type to be text/plain unless it + appears inside a multipart/digest container, in which case it would be + message/rfc822. + """ + missing = object() + value = self.get('content-type', missing) + if value is missing: + # This should have no parameters + return self.get_default_type() + ctype = paramre.split(value)[0].lower().strip() + # RFC 2045, section 5.2 says if its invalid, use text/plain + if ctype.count('/') <> 1: + return 'text/plain' + return ctype + + def get_content_maintype(self): + """Return the message's main content type. + + This is the `maintype' part of the string returned by + get_content_type(). + """ + ctype = self.get_content_type() + return ctype.split('/')[0] + + def get_content_subtype(self): + """Returns the message's sub-content type. + + This is the `subtype' part of the string returned by + get_content_type(). + """ + ctype = self.get_content_type() + return ctype.split('/')[1] + + def get_default_type(self): + """Return the `default' content type. + + Most messages have a default content type of text/plain, except for + messages that are subparts of multipart/digest containers. Such + subparts have a default content type of message/rfc822. + """ + return self._default_type + + def set_default_type(self, ctype): + """Set the `default' content type. + + ctype should be either "text/plain" or "message/rfc822", although this + is not enforced. The default content type is not stored in the + Content-Type header. + """ + self._default_type = ctype + + def _get_params_preserve(self, failobj, header): + # Like get_params() but preserves the quoting of values. BAW: + # should this be part of the public interface? + missing = object() + value = self.get(header, missing) + if value is missing: + return failobj + params = [] + for p in _parseparam(';' + value): + try: + name, val = p.split('=', 1) + name = name.strip() + val = val.strip() + except ValueError: + # Must have been a bare attribute + name = p.strip() + val = '' + params.append((name, val)) + params = utils.decode_params(params) + return params + + def get_params(self, failobj=None, header='content-type', unquote=True): + """Return the message's Content-Type parameters, as a list. + + The elements of the returned list are 2-tuples of key/value pairs, as + split on the `=' sign. The left hand side of the `=' is the key, + while the right hand side is the value. If there is no `=' sign in + the parameter the value is the empty string. The value is as + described in the get_param() method. + + Optional failobj is the object to return if there is no Content-Type + header. Optional header is the header to search instead of + Content-Type. If unquote is True, the value is unquoted. + """ + missing = object() + params = self._get_params_preserve(missing, header) + if params is missing: + return failobj + if unquote: + return [(k, _unquotevalue(v)) for k, v in params] + else: + return params + + def get_param(self, param, failobj=None, header='content-type', + unquote=True): + """Return the parameter value if found in the Content-Type header. + + Optional failobj is the object to return if there is no Content-Type + header, or the Content-Type header has no such parameter. Optional + header is the header to search instead of Content-Type. + + Parameter keys are always compared case insensitively. The return + value can either be a string, or a 3-tuple if the parameter was RFC + 2231 encoded. When it's a 3-tuple, the elements of the value are of + the form (CHARSET, LANGUAGE, VALUE). Note that both CHARSET and + LANGUAGE can be None, in which case you should consider VALUE to be + encoded in the us-ascii charset. You can usually ignore LANGUAGE. + + Your application should be prepared to deal with 3-tuple return + values, and can convert the parameter to a Unicode string like so: + + param = msg.get_param('foo') + if isinstance(param, tuple): + param = unicode(param[2], param[0] or 'us-ascii') + + In any case, the parameter value (either the returned string, or the + VALUE item in the 3-tuple) is always unquoted, unless unquote is set + to False. + """ + if not self.has_key(header): + return failobj + for k, v in self._get_params_preserve(failobj, header): + if k.lower() == param.lower(): + if unquote: + return _unquotevalue(v) + else: + return v + return failobj + + def set_param(self, param, value, header='Content-Type', requote=True, + charset=None, language=''): + """Set a parameter in the Content-Type header. + + If the parameter already exists in the header, its value will be + replaced with the new value. + + If header is Content-Type and has not yet been defined for this + message, it will be set to "text/plain" and the new parameter and + value will be appended as per RFC 2045. + + An alternate header can specified in the header argument, and all + parameters will be quoted as necessary unless requote is False. + + If charset is specified, the parameter will be encoded according to RFC + 2231. Optional language specifies the RFC 2231 language, defaulting + to the empty string. Both charset and language should be strings. + """ + if not isinstance(value, tuple) and charset: + value = (charset, language, value) + + if not self.has_key(header) and header.lower() == 'content-type': + ctype = 'text/plain' + else: + ctype = self.get(header) + if not self.get_param(param, header=header): + if not ctype: + ctype = _formatparam(param, value, requote) + else: + ctype = SEMISPACE.join( + [ctype, _formatparam(param, value, requote)]) + else: + ctype = '' + for old_param, old_value in self.get_params(header=header, + unquote=requote): + append_param = '' + if old_param.lower() == param.lower(): + append_param = _formatparam(param, value, requote) + else: + append_param = _formatparam(old_param, old_value, requote) + if not ctype: + ctype = append_param + else: + ctype = SEMISPACE.join([ctype, append_param]) + if ctype <> self.get(header): + del self[header] + self[header] = ctype + + def del_param(self, param, header='content-type', requote=True): + """Remove the given parameter completely from the Content-Type header. + + The header will be re-written in place without the parameter or its + value. All values will be quoted as necessary unless requote is + False. Optional header specifies an alternative to the Content-Type + header. + """ + if not self.has_key(header): + return + new_ctype = '' + for p, v in self.get_params(header=header, unquote=requote): + if p.lower() <> param.lower(): + if not new_ctype: + new_ctype = _formatparam(p, v, requote) + else: + new_ctype = SEMISPACE.join([new_ctype, + _formatparam(p, v, requote)]) + if new_ctype <> self.get(header): + del self[header] + self[header] = new_ctype + + def set_type(self, type, header='Content-Type', requote=True): + """Set the main type and subtype for the Content-Type header. + + type must be a string in the form "maintype/subtype", otherwise a + ValueError is raised. + + This method replaces the Content-Type header, keeping all the + parameters in place. If requote is False, this leaves the existing + header's quoting as is. Otherwise, the parameters will be quoted (the + default). + + An alternative header can be specified in the header argument. When + the Content-Type header is set, we'll always also add a MIME-Version + header. + """ + # BAW: should we be strict? + if not type.count('/') == 1: + raise ValueError + # Set the Content-Type, you get a MIME-Version + if header.lower() == 'content-type': + del self['mime-version'] + self['MIME-Version'] = '1.0' + if not self.has_key(header): + self[header] = type + return + params = self.get_params(header=header, unquote=requote) + del self[header] + self[header] = type + # Skip the first param; it's the old type. + for p, v in params[1:]: + self.set_param(p, v, header, requote) + + def get_filename(self, failobj=None): + """Return the filename associated with the payload if present. + + The filename is extracted from the Content-Disposition header's + `filename' parameter, and it is unquoted. If that header is missing + the `filename' parameter, this method falls back to looking for the + `name' parameter. + """ + missing = object() + filename = self.get_param('filename', missing, 'content-disposition') + if filename is missing: + filename = self.get_param('name', missing, 'content-disposition') + if filename is missing: + return failobj + return utils.collapse_rfc2231_value(filename).strip() + + def get_boundary(self, failobj=None): + """Return the boundary associated with the payload if present. + + The boundary is extracted from the Content-Type header's `boundary' + parameter, and it is unquoted. + """ + missing = object() + boundary = self.get_param('boundary', missing) + 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() + + def set_boundary(self, boundary): + """Set the boundary parameter in Content-Type to 'boundary'. + + This is subtly different than deleting the Content-Type header and + adding a new one with a new boundary parameter via add_header(). The + main difference is that using the set_boundary() method preserves the + order of the Content-Type header in the original message. + + HeaderParseError is raised if the message has no Content-Type header. + """ + missing = object() + params = self._get_params_preserve(missing, 'content-type') + 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') + newparams = [] + foundp = False + for pk, pv in params: + if pk.lower() == 'boundary': + newparams.append(('boundary', '"%s"' % boundary)) + foundp = True + else: + newparams.append((pk, pv)) + if not foundp: + # The original Content-Type header had no boundary attribute. + # Tack one on the end. BAW: should we raise an exception + # instead??? + newparams.append(('boundary', '"%s"' % boundary)) + # Replace the existing Content-Type header with the new value + newheaders = [] + for h, v in self._headers: + if h.lower() == 'content-type': + parts = [] + for k, v in newparams: + if v == '': + parts.append(k) + else: + parts.append('%s=%s' % (k, v)) + newheaders.append((h, SEMISPACE.join(parts))) + + else: + newheaders.append((h, v)) + self._headers = newheaders + + def get_content_charset(self, failobj=None): + """Return the charset parameter of the Content-Type header. + + The returned string is always coerced to lower case. If there is no + Content-Type header, or if that header has no charset parameter, + failobj is returned. + """ + missing = object() + charset = self.get_param('charset', missing) + if charset is missing: + return failobj + if isinstance(charset, tuple): + # RFC 2231 encoded, so decode it, and it better end up as ascii. + pcharset = charset[0] or 'us-ascii' + charset = unicode(charset[2], pcharset).encode('us-ascii') + # RFC 2046, $4.1.2 says charsets are not case sensitive + return charset.lower() + + def get_charsets(self, failobj=None): + """Return a list containing the charset(s) used in this message. + + The returned list of items describes the Content-Type headers' + charset parameter for this message and all the subparts in its + payload. + + Each item will either be a string (the value of the charset parameter + in the Content-Type header of that part) or the value of the + 'failobj' parameter (defaults to None), if the part does not have a + main MIME type of "text", or the charset is not defined. + + The list will contain one string for each part of the message, plus + one for the container message (i.e. self), so that a non-multipart + message will still return a list of length 1. + """ + return [part.get_content_charset(failobj) for part in self.walk()] + + # I.e. def walk(self): ... + from email.Iterators import walk diff --git a/Lib/email/mime/__init__.py b/Lib/email/mime/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/Lib/email/mime/application.py b/Lib/email/mime/application.py new file mode 100644 index 0000000..6f8bb8a --- /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/mime/audio.py b/Lib/email/mime/audio.py new file mode 100644 index 0000000..c7290c4 --- /dev/null +++ b/Lib/email/mime/audio.py @@ -0,0 +1,73 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Anthony Baxter +# Contact: email-sig@python.org + +"""Class representing audio/* type MIME documents.""" + +__all__ = ['MIMEAudio'] + +import sndhdr + +from cStringIO import StringIO +from email import encoders +from email.mime.nonmultipart import MIMENonMultipart + + + +_sndhdr_MIMEmap = {'au' : 'basic', + 'wav' :'x-wav', + 'aiff':'x-aiff', + 'aifc':'x-aiff', + } + +# There are others in sndhdr that don't have MIME types. :( +# Additional ones to be added to sndhdr? midi, mp3, realaudio, wma?? +def _whatsnd(data): + """Try to identify a sound file type. + + sndhdr.what() has a pretty cruddy interface, unfortunately. This is why + we re-do it here. It would be easier to reverse engineer the Unix 'file' + command and use the standard 'magic' file, as shipped with a modern Unix. + """ + hdr = data[:512] + fakefile = StringIO(hdr) + for testfn in sndhdr.tests: + res = testfn(hdr, fakefile) + if res is not None: + return _sndhdr_MIMEmap.get(res[0]) + return None + + + +class MIMEAudio(MIMENonMultipart): + """Class for generating audio/* MIME documents.""" + + def __init__(self, _audiodata, _subtype=None, + _encoder=encoders.encode_base64, **_params): + """Create an audio/* type MIME document. + + _audiodata is a string containing the raw audio data. If this data + can be decoded by the standard Python `sndhdr' module, then the + subtype will be automatically included in the Content-Type header. + Otherwise, you can specify the specific audio subtype via the + _subtype parameter. If _subtype is not given, and no subtype can be + guessed, a TypeError is raised. + + _encoder is a function which will perform the actual encoding for + transport of the image data. It takes one argument, which is this + Image instance. It should use get_payload() and set_payload() to + change the payload to the encoded form. It should also add any + Content-Transfer-Encoding or other headers to the message as + necessary. The default encoding is Base64. + + 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: + _subtype = _whatsnd(_audiodata) + if _subtype is None: + raise TypeError('Could not find audio MIME subtype') + MIMENonMultipart.__init__(self, 'audio', _subtype, **_params) + self.set_payload(_audiodata) + _encoder(self) diff --git a/Lib/email/mime/base.py b/Lib/email/mime/base.py new file mode 100644 index 0000000..ac91925 --- /dev/null +++ b/Lib/email/mime/base.py @@ -0,0 +1,26 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Base class for MIME specializations.""" + +__all__ = ['MIMEBase'] + +from email import message + + + +class MIMEBase(message.Message): + """Base class for MIME specializations.""" + + def __init__(self, _maintype, _subtype, **_params): + """This constructor adds a Content-Type: and a MIME-Version: header. + + The Content-Type: header is taken from the _maintype and _subtype + arguments. Additional parameters for this header are taken from the + keyword arguments. + """ + 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/mime/image.py b/Lib/email/mime/image.py new file mode 100644 index 0000000..5563823 --- /dev/null +++ b/Lib/email/mime/image.py @@ -0,0 +1,46 @@ +# 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 encoders +from email.mime.nonmultipart import MIMENonMultipart + + + +class MIMEImage(MIMENonMultipart): + """Class for generating image/* type MIME documents.""" + + def __init__(self, _imagedata, _subtype=None, + _encoder=encoders.encode_base64, **_params): + """Create an image/* type MIME document. + + _imagedata is a string containing the raw image data. If this data + can be decoded by the standard Python `imghdr' module, then the + subtype will be automatically included in the Content-Type header. + Otherwise, you can specify the specific image subtype via the _subtype + parameter. + + _encoder is a function which will perform the actual encoding for + transport of the image data. It takes one argument, which is this + Image instance. It should use get_payload() and set_payload() to + change the payload to the encoded form. It should also add any + Content-Transfer-Encoding or other headers to the message as + necessary. The default encoding is Base64. + + 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: + _subtype = imghdr.what(None, _imagedata) + if _subtype is None: + raise TypeError('Could not guess image MIME subtype') + MIMENonMultipart.__init__(self, 'image', _subtype, **_params) + self.set_payload(_imagedata) + _encoder(self) diff --git a/Lib/email/mime/message.py b/Lib/email/mime/message.py new file mode 100644 index 0000000..275dbfd --- /dev/null +++ b/Lib/email/mime/message.py @@ -0,0 +1,34 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Class representing message/* MIME documents.""" + +__all__ = ['MIMEMessage'] + +from email import message +from email.mime.nonmultipart import MIMENonMultipart + + + +class MIMEMessage(MIMENonMultipart): + """Class representing message/* MIME documents.""" + + def __init__(self, _msg, _subtype='rfc822'): + """Create a message/* type MIME document. + + _msg is a message object and must be an instance of Message, or a + derived class of Message, otherwise a TypeError is raised. + + Optional _subtype defines the subtype of the contained message. The + default is "rfc822" (this is defined by the MIME standard, even though + the term "rfc822" is technically outdated by RFC 2822). + """ + MIMENonMultipart.__init__(self, 'message', _subtype) + 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) + # And be sure our default type is set correctly + self.set_default_type('message/rfc822') diff --git a/Lib/email/mime/multipart.py b/Lib/email/mime/multipart.py new file mode 100644 index 0000000..5c8c9db --- /dev/null +++ b/Lib/email/mime/multipart.py @@ -0,0 +1,41 @@ +# Copyright (C) 2002-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Base class for MIME multipart/* type messages.""" + +__all__ = ['MIMEMultipart'] + +from email.mime.base import MIMEBase + + + +class MIMEMultipart(MIMEBase): + """Base class for MIME multipart/* type messages.""" + + def __init__(self, _subtype='mixed', boundary=None, _subparts=None, + **_params): + """Creates a multipart/* type message. + + By default, creates a multipart/mixed message, with proper + Content-Type and MIME-Version headers. + + _subtype is the subtype of the multipart content type, defaulting to + `mixed'. + + boundary is the multipart boundary string. By default it is + calculated as needed. + + _subparts is a sequence of initial subparts for the payload. It + must be an iterable object, such as a list. You can always + attach new subparts to the message by using the attach() method. + + Additional parameters for the Content-Type header are taken from the + keyword arguments (or passed into the _params argument). + """ + MIMEBase.__init__(self, 'multipart', _subtype, **_params) + if _subparts: + for p in _subparts: + self.attach(p) + if boundary: + self.set_boundary(boundary) diff --git a/Lib/email/mime/nonmultipart.py b/Lib/email/mime/nonmultipart.py new file mode 100644 index 0000000..dd280b5 --- /dev/null +++ b/Lib/email/mime/nonmultipart.py @@ -0,0 +1,26 @@ +# 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.""" + +__all__ = ['MIMENonMultipart'] + +from email import errors +from email.mime.base import MIMEBase + + + +class MIMENonMultipart(MIMEBase): + """Base class for MIME multipart/* type messages.""" + + __pychecker__ = 'unusednames=payload' + + def attach(self, payload): + # 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( + 'Cannot attach additional subparts to non-multipart/*') + + del __pychecker__ diff --git a/Lib/email/mime/text.py b/Lib/email/mime/text.py new file mode 100644 index 0000000..5747db5 --- /dev/null +++ b/Lib/email/mime/text.py @@ -0,0 +1,30 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Class representing text/* type MIME documents.""" + +__all__ = ['MIMEText'] + +from email.encoders import encode_7or8bit +from email.mime.nonmultipart import MIMENonMultipart + + + +class MIMEText(MIMENonMultipart): + """Class for generating text/* type MIME documents.""" + + def __init__(self, _text, _subtype='plain', _charset='us-ascii'): + """Create a text/* type MIME document. + + _text is the string for this message object. + + _subtype is the MIME sub content type, defaulting to "plain". + + _charset is the character set parameter added to the Content-Type + header. This defaults to "us-ascii". Note that as a side-effect, the + Content-Transfer-Encoding header will also be set. + """ + MIMENonMultipart.__init__(self, 'text', _subtype, + **{'charset': _charset}) + self.set_payload(_text, _charset) diff --git a/Lib/email/parser.py b/Lib/email/parser.py new file mode 100644 index 0000000..2fcaf25 --- /dev/null +++ b/Lib/email/parser.py @@ -0,0 +1,91 @@ +# 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 + + + +class Parser: + def __init__(self, *args, **kws): + """Parser of RFC 2822 and MIME email messages. + + Creates an in-memory object tree representing the email message, which + can then be manipulated and turned over to a Generator to return the + textual representation of the message. + + The string must be formatted as a block of RFC 2822 headers and header + continuation lines, optionally preceeded by a `Unix-from' header. The + header block is terminated either by the end of the string or by a + blank line. + + _class is the class to instantiate for new message objects when they + must be created. This class must have a constructor that can take + zero arguments. Default is Message.Message. + """ + if len(args) >= 1: + if '_class' in kws: + raise TypeError("Multiple values for keyword arg '_class'") + kws['_class'] = args[0] + if len(args) == 2: + if 'strict' in kws: + raise TypeError("Multiple values for keyword arg 'strict'") + kws['strict'] = args[1] + if len(args) > 2: + raise TypeError('Too many arguments') + if '_class' in kws: + self._class = kws['_class'] + del kws['_class'] + else: + self._class = Message + if 'strict' in kws: + warnings.warn("'strict' argument is deprecated (and ignored)", + DeprecationWarning, 2) + del kws['strict'] + if kws: + raise TypeError('Unexpected keyword arguments') + + def parse(self, fp, headersonly=False): + """Create a message structure from the data in a file. + + Reads all the data from the file and returns the root of the message + structure. Optional headersonly is a flag specifying whether to stop + parsing after reading the headers or not. The default is False, + meaning it parses the entire contents of the file. + """ + feedparser = FeedParser(self._class) + if headersonly: + feedparser._set_headersonly() + while True: + data = fp.read(8192) + if not data: + break + feedparser.feed(data) + return feedparser.close() + + def parsestr(self, text, headersonly=False): + """Create a message structure from a string. + + Returns the root of the message structure. Optional headersonly is a + flag specifying whether to stop parsing after reading the headers or + not. The default is False, meaning it parses the entire contents of + the file. + """ + return self.parse(StringIO(text), headersonly=headersonly) + + + +class HeaderParser(Parser): + def parse(self, fp, headersonly=True): + return Parser.parse(self, fp, True) + + def parsestr(self, text, headersonly=True): + return Parser.parsestr(self, text, True) diff --git a/Lib/email/quopriMIME.py b/Lib/email/quopriMIME.py deleted file mode 100644 index a9b5d49..0000000 --- a/Lib/email/quopriMIME.py +++ /dev/null @@ -1,318 +0,0 @@ -# Copyright (C) 2001-2004 Python Software Foundation -# Author: Ben Gertzfield -# Contact: email-sig@python.org - -"""Quoted-printable content transfer encoding per RFCs 2045-2047. - -This module handles the content transfer encoding method defined in RFC 2045 -to encode US ASCII-like 8-bit data called `quoted-printable'. It is used to -safely encode text that is in a character set similar to the 7-bit US ASCII -character set, but that includes some 8-bit characters that are normally not -allowed in email bodies or headers. - -Quoted-printable is very space-inefficient for encoding binary files; use the -email.base64MIME module for that instead. - -This module provides an interface to encode and decode both headers and bodies -with quoted-printable encoding. - -RFC 2045 defines a method for including character set information in an -`encoded-word' in a header. This method is commonly used for 8-bit real names -in To:/From:/Cc: etc. fields, as well as Subject: lines. - -This module does not do the line wrapping or end-of-line character -conversion necessary for proper internationalized headers; it only -does dumb encoding and decoding. To deal with the various line -wrapping issues, use the email.Header module. -""" - -import re -from string import hexdigits -from email.Utils import fix_eols - -CRLF = '\r\n' -NL = '\n' - -# See also Charset.py -MISC_LEN = 7 - -hqre = re.compile(r'[^-a-zA-Z0-9!*+/ ]') -bqre = re.compile(r'[^ !-<>-~\t]') - - - -# Helpers -def header_quopri_check(c): - """Return True if the character should be escaped with header quopri.""" - return bool(hqre.match(c)) - - -def body_quopri_check(c): - """Return True if the character should be escaped with body quopri.""" - return bool(bqre.match(c)) - - -def header_quopri_len(s): - """Return the length of str when it is encoded with header quopri.""" - count = 0 - for c in s: - if hqre.match(c): - count += 3 - else: - count += 1 - return count - - -def body_quopri_len(str): - """Return the length of str when it is encoded with body quopri.""" - count = 0 - for c in str: - if bqre.match(c): - count += 3 - else: - count += 1 - return count - - -def _max_append(L, s, maxlen, extra=''): - if not L: - L.append(s.lstrip()) - elif len(L[-1]) + len(s) <= maxlen: - L[-1] += extra + s - else: - L.append(s.lstrip()) - - -def unquote(s): - """Turn a string in the form =AB to the ASCII character with value 0xab""" - return chr(int(s[1:3], 16)) - - -def quote(c): - return "=%02X" % ord(c) - - - -def header_encode(header, charset="iso-8859-1", keep_eols=False, - maxlinelen=76, eol=NL): - """Encode a single header line with quoted-printable (like) encoding. - - Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but - used specifically for email header fields to allow charsets with mostly 7 - bit characters (and some 8 bit) to remain more or less readable in non-RFC - 2045 aware mail clients. - - charset names the character set to use to encode the header. It defaults - to iso-8859-1. - - The resulting string will be in the form: - - "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n - =?charset?q?Silly_=C8nglish_Kn=EEghts?=" - - with each line wrapped safely at, at most, maxlinelen characters (defaults - to 76 characters). If maxlinelen is None, the entire string is encoded in - one chunk with no splitting. - - End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted - to the canonical email line separator \\r\\n unless the keep_eols - parameter is True (the default is False). - - Each line of the header will be terminated in the value of eol, which - defaults to "\\n". Set this to "\\r\\n" if you are using the result of - this function directly in email. - """ - # Return empty headers unchanged - if not header: - return header - - if not keep_eols: - header = fix_eols(header) - - # Quopri encode each line, in encoded chunks no greater than maxlinelen in - # length, after the RFC chrome is added in. - quoted = [] - if maxlinelen is None: - # An obnoxiously large number that's good enough - max_encoded = 100000 - else: - max_encoded = maxlinelen - len(charset) - MISC_LEN - 1 - - for c in header: - # Space may be represented as _ instead of =20 for readability - if c == ' ': - _max_append(quoted, '_', max_encoded) - # These characters can be included verbatim - elif not hqre.match(c): - _max_append(quoted, c, max_encoded) - # Otherwise, replace with hex value like =E2 - else: - _max_append(quoted, "=%02X" % ord(c), max_encoded) - - # Now add the RFC chrome to each encoded chunk and glue the chunks - # together. BAW: should we be able to specify the leading whitespace in - # the joiner? - joiner = eol + ' ' - return joiner.join(['=?%s?q?%s?=' % (charset, line) for line in quoted]) - - - -def encode(body, binary=False, maxlinelen=76, eol=NL): - """Encode with quoted-printable, wrapping at maxlinelen characters. - - If binary is False (the default), end-of-line characters will be converted - to the canonical email end-of-line sequence \\r\\n. Otherwise they will - be left verbatim. - - Each line of encoded text will end with eol, which defaults to "\\n". Set - this to "\\r\\n" if you will be using the result of this function directly - in an email. - - Each line will be wrapped at, at most, maxlinelen characters (defaults to - 76 characters). Long lines will have the `soft linefeed' quoted-printable - character "=" appended to them, so the decoded text will be identical to - the original text. - """ - if not body: - return body - - if not binary: - body = fix_eols(body) - - # BAW: We're accumulating the body text by string concatenation. That - # can't be very efficient, but I don't have time now to rewrite it. It - # just feels like this algorithm could be more efficient. - encoded_body = '' - lineno = -1 - # Preserve line endings here so we can check later to see an eol needs to - # be added to the output later. - lines = body.splitlines(1) - for line in lines: - # But strip off line-endings for processing this line. - if line.endswith(CRLF): - line = line[:-2] - elif line[-1] in CRLF: - line = line[:-1] - - lineno += 1 - encoded_line = '' - prev = None - linelen = len(line) - # Now we need to examine every character to see if it needs to be - # quopri encoded. BAW: again, string concatenation is inefficient. - for j in range(linelen): - c = line[j] - prev = c - if bqre.match(c): - c = quote(c) - elif j+1 == linelen: - # Check for whitespace at end of line; special case - if c not in ' \t': - encoded_line += c - prev = c - continue - # Check to see to see if the line has reached its maximum length - if len(encoded_line) + len(c) >= maxlinelen: - encoded_body += encoded_line + '=' + eol - encoded_line = '' - encoded_line += c - # Now at end of line.. - if prev and prev in ' \t': - # Special case for whitespace at end of file - if lineno + 1 == len(lines): - prev = quote(prev) - if len(encoded_line) + len(prev) > maxlinelen: - encoded_body += encoded_line + '=' + eol + prev - else: - encoded_body += encoded_line + prev - # Just normal whitespace at end of line - else: - encoded_body += encoded_line + prev + '=' + eol - encoded_line = '' - # Now look at the line we just finished and it has a line ending, we - # need to add eol to the end of the line. - if lines[lineno].endswith(CRLF) or lines[lineno][-1] in CRLF: - encoded_body += encoded_line + eol - else: - encoded_body += encoded_line - encoded_line = '' - return encoded_body - - -# For convenience and backwards compatibility w/ standard base64 module -body_encode = encode -encodestring = encode - - - -# BAW: I'm not sure if the intent was for the signature of this function to be -# the same as base64MIME.decode() or not... -def decode(encoded, eol=NL): - """Decode a quoted-printable string. - - Lines are separated with eol, which defaults to \\n. - """ - if not encoded: - return encoded - # BAW: see comment in encode() above. Again, we're building up the - # decoded string with string concatenation, which could be done much more - # efficiently. - decoded = '' - - for line in encoded.splitlines(): - line = line.rstrip() - if not line: - decoded += eol - continue - - i = 0 - n = len(line) - while i < n: - c = line[i] - if c <> '=': - decoded += c - i += 1 - # Otherwise, c == "=". Are we at the end of the line? If so, add - # a soft line break. - elif i+1 == n: - i += 1 - continue - # Decode if in form =AB - elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits: - decoded += unquote(line[i:i+3]) - i += 3 - # Otherwise, not in form =AB, pass literally - else: - decoded += c - i += 1 - - if i == n: - decoded += eol - # Special case if original string did not end with eol - if not encoded.endswith(eol) and decoded.endswith(eol): - decoded = decoded[:-1] - return decoded - - -# For convenience and backwards compatibility w/ standard base64 module -body_decode = decode -decodestring = decode - - - -def _unquote_match(match): - """Turn a match in the form =AB to the ASCII character with value 0xab""" - s = match.group(0) - return unquote(s) - - -# Header decoding is done a bit differently -def header_decode(s): - """Decode a string encoded with RFC 2045 MIME header `Q' encoding. - - This function does not parse a full MIME header value encoded with - quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use - the high level email.Header class for that functionality. - """ - s = s.replace('_', ' ') - return re.sub(r'=\w{2}', _unquote_match, s) diff --git a/Lib/email/quoprimime.py b/Lib/email/quoprimime.py new file mode 100644 index 0000000..a5658dd --- /dev/null +++ b/Lib/email/quoprimime.py @@ -0,0 +1,336 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Ben Gertzfield +# Contact: email-sig@python.org + +"""Quoted-printable content transfer encoding per RFCs 2045-2047. + +This module handles the content transfer encoding method defined in RFC 2045 +to encode US ASCII-like 8-bit data called `quoted-printable'. It is used to +safely encode text that is in a character set similar to the 7-bit US ASCII +character set, but that includes some 8-bit characters that are normally not +allowed in email bodies or headers. + +Quoted-printable is very space-inefficient for encoding binary files; use the +email.base64MIME module for that instead. + +This module provides an interface to encode and decode both headers and bodies +with quoted-printable encoding. + +RFC 2045 defines a method for including character set information in an +`encoded-word' in a header. This method is commonly used for 8-bit real names +in To:/From:/Cc: etc. fields, as well as Subject: lines. + +This module does not do the line wrapping or end-of-line character +conversion necessary for proper internationalized headers; it only +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 + +CRLF = '\r\n' +NL = '\n' + +# See also Charset.py +MISC_LEN = 7 + +hqre = re.compile(r'[^-a-zA-Z0-9!*+/ ]') +bqre = re.compile(r'[^ !-<>-~\t]') + + + +# Helpers +def header_quopri_check(c): + """Return True if the character should be escaped with header quopri.""" + return bool(hqre.match(c)) + + +def body_quopri_check(c): + """Return True if the character should be escaped with body quopri.""" + return bool(bqre.match(c)) + + +def header_quopri_len(s): + """Return the length of str when it is encoded with header quopri.""" + count = 0 + for c in s: + if hqre.match(c): + count += 3 + else: + count += 1 + return count + + +def body_quopri_len(str): + """Return the length of str when it is encoded with body quopri.""" + count = 0 + for c in str: + if bqre.match(c): + count += 3 + else: + count += 1 + return count + + +def _max_append(L, s, maxlen, extra=''): + if not L: + L.append(s.lstrip()) + elif len(L[-1]) + len(s) <= maxlen: + L[-1] += extra + s + else: + L.append(s.lstrip()) + + +def unquote(s): + """Turn a string in the form =AB to the ASCII character with value 0xab""" + return chr(int(s[1:3], 16)) + + +def quote(c): + return "=%02X" % ord(c) + + + +def header_encode(header, charset="iso-8859-1", keep_eols=False, + maxlinelen=76, eol=NL): + """Encode a single header line with quoted-printable (like) encoding. + + Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but + used specifically for email header fields to allow charsets with mostly 7 + bit characters (and some 8 bit) to remain more or less readable in non-RFC + 2045 aware mail clients. + + charset names the character set to use to encode the header. It defaults + to iso-8859-1. + + The resulting string will be in the form: + + "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n + =?charset?q?Silly_=C8nglish_Kn=EEghts?=" + + with each line wrapped safely at, at most, maxlinelen characters (defaults + to 76 characters). If maxlinelen is None, the entire string is encoded in + one chunk with no splitting. + + End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted + to the canonical email line separator \\r\\n unless the keep_eols + parameter is True (the default is False). + + Each line of the header will be terminated in the value of eol, which + defaults to "\\n". Set this to "\\r\\n" if you are using the result of + this function directly in email. + """ + # Return empty headers unchanged + if not header: + return header + + if not keep_eols: + header = fix_eols(header) + + # Quopri encode each line, in encoded chunks no greater than maxlinelen in + # length, after the RFC chrome is added in. + quoted = [] + if maxlinelen is None: + # An obnoxiously large number that's good enough + max_encoded = 100000 + else: + max_encoded = maxlinelen - len(charset) - MISC_LEN - 1 + + for c in header: + # Space may be represented as _ instead of =20 for readability + if c == ' ': + _max_append(quoted, '_', max_encoded) + # These characters can be included verbatim + elif not hqre.match(c): + _max_append(quoted, c, max_encoded) + # Otherwise, replace with hex value like =E2 + else: + _max_append(quoted, "=%02X" % ord(c), max_encoded) + + # Now add the RFC chrome to each encoded chunk and glue the chunks + # together. BAW: should we be able to specify the leading whitespace in + # the joiner? + joiner = eol + ' ' + return joiner.join(['=?%s?q?%s?=' % (charset, line) for line in quoted]) + + + +def encode(body, binary=False, maxlinelen=76, eol=NL): + """Encode with quoted-printable, wrapping at maxlinelen characters. + + If binary is False (the default), end-of-line characters will be converted + to the canonical email end-of-line sequence \\r\\n. Otherwise they will + be left verbatim. + + Each line of encoded text will end with eol, which defaults to "\\n". Set + this to "\\r\\n" if you will be using the result of this function directly + in an email. + + Each line will be wrapped at, at most, maxlinelen characters (defaults to + 76 characters). Long lines will have the `soft linefeed' quoted-printable + character "=" appended to them, so the decoded text will be identical to + the original text. + """ + if not body: + return body + + if not binary: + body = fix_eols(body) + + # BAW: We're accumulating the body text by string concatenation. That + # can't be very efficient, but I don't have time now to rewrite it. It + # just feels like this algorithm could be more efficient. + encoded_body = '' + lineno = -1 + # Preserve line endings here so we can check later to see an eol needs to + # be added to the output later. + lines = body.splitlines(1) + for line in lines: + # But strip off line-endings for processing this line. + if line.endswith(CRLF): + line = line[:-2] + elif line[-1] in CRLF: + line = line[:-1] + + lineno += 1 + encoded_line = '' + prev = None + linelen = len(line) + # Now we need to examine every character to see if it needs to be + # quopri encoded. BAW: again, string concatenation is inefficient. + for j in range(linelen): + c = line[j] + prev = c + if bqre.match(c): + c = quote(c) + elif j+1 == linelen: + # Check for whitespace at end of line; special case + if c not in ' \t': + encoded_line += c + prev = c + continue + # Check to see to see if the line has reached its maximum length + if len(encoded_line) + len(c) >= maxlinelen: + encoded_body += encoded_line + '=' + eol + encoded_line = '' + encoded_line += c + # Now at end of line.. + if prev and prev in ' \t': + # Special case for whitespace at end of file + if lineno + 1 == len(lines): + prev = quote(prev) + if len(encoded_line) + len(prev) > maxlinelen: + encoded_body += encoded_line + '=' + eol + prev + else: + encoded_body += encoded_line + prev + # Just normal whitespace at end of line + else: + encoded_body += encoded_line + prev + '=' + eol + encoded_line = '' + # Now look at the line we just finished and it has a line ending, we + # need to add eol to the end of the line. + if lines[lineno].endswith(CRLF) or lines[lineno][-1] in CRLF: + encoded_body += encoded_line + eol + else: + encoded_body += encoded_line + encoded_line = '' + return encoded_body + + +# For convenience and backwards compatibility w/ standard base64 module +body_encode = encode +encodestring = encode + + + +# BAW: I'm not sure if the intent was for the signature of this function to be +# the same as base64MIME.decode() or not... +def decode(encoded, eol=NL): + """Decode a quoted-printable string. + + Lines are separated with eol, which defaults to \\n. + """ + if not encoded: + return encoded + # BAW: see comment in encode() above. Again, we're building up the + # decoded string with string concatenation, which could be done much more + # efficiently. + decoded = '' + + for line in encoded.splitlines(): + line = line.rstrip() + if not line: + decoded += eol + continue + + i = 0 + n = len(line) + while i < n: + c = line[i] + if c <> '=': + decoded += c + i += 1 + # Otherwise, c == "=". Are we at the end of the line? If so, add + # a soft line break. + elif i+1 == n: + i += 1 + continue + # Decode if in form =AB + elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits: + decoded += unquote(line[i:i+3]) + i += 3 + # Otherwise, not in form =AB, pass literally + else: + decoded += c + i += 1 + + if i == n: + decoded += eol + # Special case if original string did not end with eol + if not encoded.endswith(eol) and decoded.endswith(eol): + decoded = decoded[:-1] + return decoded + + +# For convenience and backwards compatibility w/ standard base64 module +body_decode = decode +decodestring = decode + + + +def _unquote_match(match): + """Turn a match in the form =AB to the ASCII character with value 0xab""" + s = match.group(0) + return unquote(s) + + +# Header decoding is done a bit differently +def header_decode(s): + """Decode a string encoded with RFC 2045 MIME header `Q' encoding. + + This function does not parse a full MIME header value encoded with + quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use + the high level email.Header class for that functionality. + """ + s = s.replace('_', ' ') + return re.sub(r'=\w{2}', _unquote_match, s) diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py index 5a42c227..d35e770 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 159989c..38b7d95 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 0000000..56baccd --- /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 0000000..ed186a0 --- /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 new file mode 100644 index 0000000..250eb19 --- /dev/null +++ b/Lib/email/utils.py @@ -0,0 +1,306 @@ +# 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 +import base64 +import random +import socket +import warnings +from cStringIO import StringIO + +from email._parseaddr import quote +from email._parseaddr import AddressList as _AddressList +from email._parseaddr import mktime_tz + +# We need wormarounds for bugs in these methods in older Pythons (see below) +from email._parseaddr import parsedate as _parsedate +from email._parseaddr import parsedate_tz as _parsedate_tz + +from quopri import decodestring as _qdecode + +# Intrapackage imports +from email.encoders import _bencode, _qencode + +COMMASPACE = ', ' +EMPTYSTRING = '' +UEMPTYSTRING = u'' +CRLF = '\r\n' + +specialsre = re.compile(r'[][\\()<>@,:;".]') +escapesre = re.compile(r'[][\\()"]') + + + +# Helpers + +def _identity(s): + return s + + +def _bdecode(s): + # We can't quite use base64.encodestring() since it tacks on a "courtesy + # newline". Blech! + if not s: + return s + value = base64.decodestring(s) + if not s.endswith('\n') and value.endswith('\n'): + return value[:-1] + return value + + + +def fix_eols(s): + """Replace all line-ending characters with \r\n.""" + # Fix newlines with no preceding carriage return + s = re.sub(r'(?', name) + return '%s%s%s <%s>' % (quotes, name, quotes, address) + return address + + + +def getaddresses(fieldvalues): + """Return a list of (REALNAME, EMAIL) for each fieldvalue.""" + all = COMMASPACE.join(fieldvalues) + a = _AddressList(all) + return a.addresslist + + + +ecre = re.compile(r''' + =\? # literal =? + (?P[^?]*?) # non-greedy up to the next ? is the charset + \? # literal ? + (?P[qb]) # either a "q" or a "b", case insensitive + \? # literal ? + (?P.*?) # non-greedy up to the next ?= is the atom + \?= # literal ?= + ''', re.VERBOSE | re.IGNORECASE) + + + +def formatdate(timeval=None, localtime=False, usegmt=False): + """Returns a date string as specified by RFC 2822, e.g.: + + Fri, 09 Nov 2001 01:08:47 -0000 + + Optional timeval if given is a floating point time value as accepted by + gmtime() and localtime(), otherwise the current time is used. + + Optional localtime is a flag that when True, interprets timeval, and + returns a date relative to the local timezone instead of UTC, properly + taking daylight savings time into account. + + Optional argument usegmt means that the timezone is written out as + an ascii string, not numeric one (so "GMT" instead of "+0000"). This + is needed for HTTP, and is only used when localtime==False. + """ + # Note: we cannot use strftime() because that honors the locale and RFC + # 2822 requires that day and month names be the English abbreviations. + if timeval is None: + timeval = time.time() + if localtime: + now = time.localtime(timeval) + # Calculate timezone offset, based on whether the local zone has + # daylight savings time, and whether DST is in effect. + if time.daylight and now[-1]: + offset = time.altzone + else: + offset = time.timezone + hours, minutes = divmod(abs(offset), 3600) + # Remember offset is in seconds west of UTC, but the timezone is in + # minutes east of UTC, so the signs differ. + if offset > 0: + sign = '-' + else: + sign = '+' + zone = '%s%02d%02d' % (sign, hours, minutes // 60) + else: + now = time.gmtime(timeval) + # Timezone offset is always -0000 + if usegmt: + zone = 'GMT' + else: + zone = '-0000' + return '%s, %02d %s %04d %02d:%02d:%02d %s' % ( + ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][now[6]], + now[2], + ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', + 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][now[1] - 1], + now[0], now[3], now[4], now[5], + zone) + + + +def make_msgid(idstring=None): + """Returns a string suitable for RFC 2822 compliant Message-ID, e.g: + + <20020201195627.33539.96671@nightshade.la.mastaler.com> + + Optional idstring if given is a string used to strengthen the + uniqueness of the message id. + """ + timeval = time.time() + utcdate = time.strftime('%Y%m%d%H%M%S', time.gmtime(timeval)) + pid = os.getpid() + randint = random.randrange(100000) + if idstring is None: + idstring = '' + else: + idstring = '.' + idstring + idhost = socket.getfqdn() + msgid = '<%s.%s.%s%s@%s>' % (utcdate, pid, randint, idstring, idhost) + return msgid + + + +# These functions are in the standalone mimelib version only because they've +# subsequently been fixed in the latest Python versions. We use this to worm +# around broken older Pythons. +def parsedate(data): + if not data: + return None + return _parsedate(data) + + +def parsedate_tz(data): + if not data: + return None + return _parsedate_tz(data) + + +def parseaddr(addr): + addrs = _AddressList(addr).addresslist + if not addrs: + return '', '' + return addrs[0] + + +# rfc822.unquote() doesn't properly de-backslash-ify in Python pre-2.3. +def unquote(str): + """Remove quotes from a string.""" + if len(str) > 1: + if str.startswith('"') and str.endswith('"'): + return str[1:-1].replace('\\\\', '\\').replace('\\"', '"') + if str.startswith('<') and str.endswith('>'): + return str[1:-1] + return str + + + +# RFC2231-related functions - parameter encoding and decoding +def decode_rfc2231(s): + """Decode string according to RFC 2231""" + import urllib + parts = s.split("'", 2) + if len(parts) == 1: + return None, None, urllib.unquote(s) + charset, language, s = parts + return charset, language, urllib.unquote(s) + + +def encode_rfc2231(s, charset=None, language=None): + """Encode string according to RFC 2231. + + If neither charset nor language is given, then s is returned as-is. If + charset is given but not language, the string is encoded using the empty + string for language. + """ + import urllib + s = urllib.quote(s, safe='') + if charset is None and language is None: + return s + if language is None: + language = '' + return "%s'%s'%s" % (charset, language, s) + + +rfc2231_continuation = re.compile(r'^(?P\w+)\*((?P[0-9]+)\*?)?$') + +def decode_params(params): + """Decode parameters list according to RFC 2231. + + params is a sequence of 2-tuples containing (content type, string value). + """ + new_params = [] + # maps parameter's name to a list of continuations + rfc2231_params = {} + # params is a sequence of 2-tuples containing (content_type, string value) + name, value = params[0] + new_params.append((name, value)) + # Cycle through each of the rest of the parameters. + for name, value in params[1:]: + value = unquote(value) + mo = rfc2231_continuation.match(name) + if mo: + name, num = mo.group('name', 'num') + if num is not None: + num = int(num) + rfc2231_param1 = rfc2231_params.setdefault(name, []) + rfc2231_param1.append((num, value)) + else: + new_params.append((name, '"%s"' % quote(value))) + if rfc2231_params: + for name, continuations in rfc2231_params.items(): + value = [] + # Sort by number + continuations.sort() + # And now append all values in num order + for num, continuation in continuations: + value.append(continuation) + charset, language, value = decode_rfc2231(EMPTYSTRING.join(value)) + new_params.append( + (name, (charset, language, '"%s"' % quote(value)))) + return new_params + +def collapse_rfc2231_value(value, errors='replace', + fallback_charset='us-ascii'): + if isinstance(value, tuple): + rawval = unquote(value[2]) + charset = value[0] or 'us-ascii' + try: + return unicode(rawval, charset, errors) + except LookupError: + # XXX charset is unknown to Python. + return unicode(rawval, fallback_charset, errors) + else: + return unquote(value) diff --git a/Lib/test/test_pyclbr.py b/Lib/test/test_pyclbr.py index ceb7a3d..87572ca 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') -- cgit v0.12