From 8b3febef2f96c35e9aad9db2ef499db040fdefae Mon Sep 17 00:00:00 2001 From: Guido van Rossum Date: Thu, 30 Aug 2007 01:15:14 +0000 Subject: [PATCH] Copying the email package back, despite its failings. --- Lib/email/__init__.py | 46 + Lib/email/_parseaddr.py | 480 +++ Lib/email/base64mime.py | 184 ++ Lib/email/charset.py | 389 +++ Lib/email/encoders.py | 88 + Lib/email/errors.py | 57 + Lib/email/feedparser.py | 480 +++ Lib/email/generator.py | 332 ++ Lib/email/header.py | 520 +++ Lib/email/iterators.py | 73 + Lib/email/message.py | 790 +++++ 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 | 95 + Lib/email/quoprimime.py | 307 ++ Lib/email/test/__init__.py | 0 Lib/email/test/data/PyBanner048.gif | Bin 0 -> 954 bytes Lib/email/test/data/audiotest.au | Bin 0 -> 23493 bytes Lib/email/test/data/msg_01.txt | 19 + Lib/email/test/data/msg_02.txt | 135 + Lib/email/test/data/msg_03.txt | 16 + Lib/email/test/data/msg_04.txt | 37 + Lib/email/test/data/msg_05.txt | 28 + Lib/email/test/data/msg_06.txt | 33 + Lib/email/test/data/msg_07.txt | 83 + Lib/email/test/data/msg_08.txt | 24 + Lib/email/test/data/msg_09.txt | 24 + Lib/email/test/data/msg_10.txt | 32 + Lib/email/test/data/msg_11.txt | 7 + Lib/email/test/data/msg_12.txt | 36 + Lib/email/test/data/msg_12a.txt | 38 + Lib/email/test/data/msg_13.txt | 94 + Lib/email/test/data/msg_14.txt | 23 + Lib/email/test/data/msg_15.txt | 52 + Lib/email/test/data/msg_16.txt | 123 + Lib/email/test/data/msg_17.txt | 12 + Lib/email/test/data/msg_18.txt | 6 + Lib/email/test/data/msg_19.txt | 43 + Lib/email/test/data/msg_20.txt | 22 + Lib/email/test/data/msg_21.txt | 20 + Lib/email/test/data/msg_22.txt | 46 + Lib/email/test/data/msg_23.txt | 8 + Lib/email/test/data/msg_24.txt | 10 + Lib/email/test/data/msg_25.txt | 117 + Lib/email/test/data/msg_26.txt | 45 + Lib/email/test/data/msg_27.txt | 15 + Lib/email/test/data/msg_28.txt | 25 + Lib/email/test/data/msg_29.txt | 22 + Lib/email/test/data/msg_30.txt | 23 + Lib/email/test/data/msg_31.txt | 15 + Lib/email/test/data/msg_32.txt | 14 + Lib/email/test/data/msg_33.txt | 29 + Lib/email/test/data/msg_34.txt | 19 + Lib/email/test/data/msg_35.txt | 4 + Lib/email/test/data/msg_36.txt | 40 + Lib/email/test/data/msg_37.txt | 22 + Lib/email/test/data/msg_38.txt | 101 + Lib/email/test/data/msg_39.txt | 83 + Lib/email/test/data/msg_40.txt | 10 + Lib/email/test/data/msg_41.txt | 8 + Lib/email/test/data/msg_42.txt | 20 + Lib/email/test/data/msg_43.txt | 217 ++ Lib/email/test/data/msg_44.txt | 35 + Lib/email/test/test_email.py | 3307 +++++++++++++++++++ Lib/email/test/test_email_codecs.py | 77 + Lib/email/test/test_email_codecs_renamed.py | 77 + Lib/email/test/test_email_torture.py | 136 + Lib/email/utils.py | 325 ++ 75 files changed, 9910 insertions(+) create mode 100644 Lib/email/__init__.py create mode 100644 Lib/email/_parseaddr.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 create mode 100644 Lib/email/quoprimime.py create mode 100644 Lib/email/test/__init__.py create mode 100644 Lib/email/test/data/PyBanner048.gif create mode 100644 Lib/email/test/data/audiotest.au create mode 100644 Lib/email/test/data/msg_01.txt create mode 100644 Lib/email/test/data/msg_02.txt create mode 100644 Lib/email/test/data/msg_03.txt create mode 100644 Lib/email/test/data/msg_04.txt create mode 100644 Lib/email/test/data/msg_05.txt create mode 100644 Lib/email/test/data/msg_06.txt create mode 100644 Lib/email/test/data/msg_07.txt create mode 100644 Lib/email/test/data/msg_08.txt create mode 100644 Lib/email/test/data/msg_09.txt create mode 100644 Lib/email/test/data/msg_10.txt create mode 100644 Lib/email/test/data/msg_11.txt create mode 100644 Lib/email/test/data/msg_12.txt create mode 100644 Lib/email/test/data/msg_12a.txt create mode 100644 Lib/email/test/data/msg_13.txt create mode 100644 Lib/email/test/data/msg_14.txt create mode 100644 Lib/email/test/data/msg_15.txt create mode 100644 Lib/email/test/data/msg_16.txt create mode 100644 Lib/email/test/data/msg_17.txt create mode 100644 Lib/email/test/data/msg_18.txt create mode 100644 Lib/email/test/data/msg_19.txt create mode 100644 Lib/email/test/data/msg_20.txt create mode 100644 Lib/email/test/data/msg_21.txt create mode 100644 Lib/email/test/data/msg_22.txt create mode 100644 Lib/email/test/data/msg_23.txt create mode 100644 Lib/email/test/data/msg_24.txt create mode 100644 Lib/email/test/data/msg_25.txt create mode 100644 Lib/email/test/data/msg_26.txt create mode 100644 Lib/email/test/data/msg_27.txt create mode 100644 Lib/email/test/data/msg_28.txt create mode 100644 Lib/email/test/data/msg_29.txt create mode 100644 Lib/email/test/data/msg_30.txt create mode 100644 Lib/email/test/data/msg_31.txt create mode 100644 Lib/email/test/data/msg_32.txt create mode 100644 Lib/email/test/data/msg_33.txt create mode 100644 Lib/email/test/data/msg_34.txt create mode 100644 Lib/email/test/data/msg_35.txt create mode 100644 Lib/email/test/data/msg_36.txt create mode 100644 Lib/email/test/data/msg_37.txt create mode 100644 Lib/email/test/data/msg_38.txt create mode 100644 Lib/email/test/data/msg_39.txt create mode 100644 Lib/email/test/data/msg_40.txt create mode 100644 Lib/email/test/data/msg_41.txt create mode 100644 Lib/email/test/data/msg_42.txt create mode 100644 Lib/email/test/data/msg_43.txt create mode 100644 Lib/email/test/data/msg_44.txt create mode 100644 Lib/email/test/test_email.py create mode 100644 Lib/email/test/test_email_codecs.py create mode 100644 Lib/email/test/test_email_codecs_renamed.py create mode 100644 Lib/email/test/test_email_torture.py create mode 100644 Lib/email/utils.py diff --git a/Lib/email/__init__.py b/Lib/email/__init__.py new file mode 100644 index 00000000000..8702212080c --- /dev/null +++ b/Lib/email/__init__.py @@ -0,0 +1,46 @@ +# Copyright (C) 2001-2007 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""A package for parsing, handling, and generating email messages.""" + +__version__ = '5.0.0' + +__all__ = [ + 'base64mime', + 'charset', + 'encoders', + 'errors', + 'generator', + 'header', + 'iterators', + 'message', + 'message_from_file', + 'message_from_string', + 'mime', + 'parser', + 'quoprimime', + 'utils', + ] + + + +# Some convenience routines. Don't import Parser and Message as side-effects +# of importing email since those cascadingly import most of the rest of the +# email package. +def message_from_string(s, *args, **kws): + """Parse a string into a Message object model. + + Optional _class and strict are passed to the Parser constructor. + """ + from email.parser import Parser + return Parser(*args, **kws).parsestr(s) + + +def message_from_file(fp, *args, **kws): + """Read a file and parse its contents into a Message object model. + + Optional _class and strict are passed to the Parser constructor. + """ + from email.parser import Parser + return Parser(*args, **kws).parse(fp) diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py new file mode 100644 index 00000000000..81913a38246 --- /dev/null +++ b/Lib/email/_parseaddr.py @@ -0,0 +1,480 @@ +# Copyright (C) 2002-2007 Python Software Foundation +# Contact: email-sig@python.org + +"""Email address parsing code. + +Lifted directly from rfc822.py. This should eventually be rewritten. +""" + +__all__ = [ + 'mktime_tz', + 'parsedate', + 'parsedate_tz', + 'quote', + ] + +import time + +SPACE = ' ' +EMPTYSTRING = '' +COMMASPACE = ', ' + +# Parse a date field +_monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', + 'aug', 'sep', 'oct', 'nov', 'dec', + 'january', 'february', 'march', 'april', 'may', 'june', 'july', + 'august', 'september', 'october', 'november', 'december'] + +_daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun'] + +# The timezone table does not include the military time zones defined +# in RFC822, other than Z. According to RFC1123, the description in +# RFC822 gets the signs wrong, so we can't rely on any such time +# zones. RFC1123 recommends that numeric timezone indicators be used +# instead of timezone names. + +_timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0, + 'AST': -400, 'ADT': -300, # Atlantic (used in Canada) + 'EST': -500, 'EDT': -400, # Eastern + 'CST': -600, 'CDT': -500, # Central + 'MST': -700, 'MDT': -600, # Mountain + 'PST': -800, 'PDT': -700 # Pacific + } + + +def parsedate_tz(data): + """Convert a date string to a time tuple. + + Accounts for military timezones. + """ + data = data.split() + # The FWS after the comma after the day-of-week is optional, so search and + # adjust for this. + if data[0].endswith(',') or data[0].lower() in _daynames: + # There's a dayname here. Skip it + del data[0] + else: + i = data[0].rfind(',') + if i >= 0: + data[0] = data[0][i+1:] + if len(data) == 3: # RFC 850 date, deprecated + stuff = data[0].split('-') + if len(stuff) == 3: + data = stuff + data[1:] + if len(data) == 4: + s = data[3] + i = s.find('+') + if i > 0: + data[3:] = [s[:i], s[i+1:]] + else: + data.append('') # Dummy tz + if len(data) < 5: + return None + data = data[:5] + [dd, mm, yy, tm, tz] = data + mm = mm.lower() + if mm not in _monthnames: + dd, mm = mm, dd.lower() + if mm not in _monthnames: + return None + mm = _monthnames.index(mm) + 1 + if mm > 12: + mm -= 12 + if dd[-1] == ',': + dd = dd[:-1] + i = yy.find(':') + if i > 0: + yy, tm = tm, yy + if yy[-1] == ',': + yy = yy[:-1] + if not yy[0].isdigit(): + yy, tz = tz, yy + if tm[-1] == ',': + tm = tm[:-1] + tm = tm.split(':') + if len(tm) == 2: + [thh, tmm] = tm + tss = '0' + elif len(tm) == 3: + [thh, tmm, tss] = tm + else: + return None + try: + yy = int(yy) + dd = int(dd) + thh = int(thh) + tmm = int(tmm) + tss = int(tss) + except ValueError: + return None + tzoffset = None + tz = tz.upper() + if tz in _timezones: + tzoffset = _timezones[tz] + else: + try: + tzoffset = int(tz) + except ValueError: + pass + # Convert a timezone offset into seconds ; -0500 -> -18000 + if tzoffset: + if tzoffset < 0: + tzsign = -1 + tzoffset = -tzoffset + else: + tzsign = 1 + tzoffset = tzsign * ( (tzoffset//100)*3600 + (tzoffset % 100)*60) + # Daylight Saving Time flag is set to -1, since DST is unknown. + return yy, mm, dd, thh, tmm, tss, 0, 1, -1, tzoffset + + +def parsedate(data): + """Convert a time string to a time tuple.""" + t = parsedate_tz(data) + if isinstance(t, tuple): + return t[:9] + else: + return t + + +def mktime_tz(data): + """Turn a 10-tuple as returned by parsedate_tz() into a UTC timestamp.""" + if data[9] is None: + # No zone info, so localtime is better assumption than GMT + return time.mktime(data[:8] + (-1,)) + else: + t = time.mktime(data[:8] + (0,)) + return t - data[9] - time.timezone + + +def quote(str): + """Add quotes around a string.""" + return str.replace('\\', '\\\\').replace('"', '\\"') + + +class AddrlistClass: + """Address parser class by Ben Escoto. + + To understand what this class does, it helps to have a copy of RFC 2822 in + front of you. + + Note: this class interface is deprecated and may be removed in the future. + Use rfc822.AddressList instead. + """ + + def __init__(self, field): + """Initialize a new instance. + + `field' is an unparsed address header field, containing + one or more addresses. + """ + self.specials = '()<>@,:;.\"[]' + self.pos = 0 + self.LWS = ' \t' + self.CR = '\r\n' + self.FWS = self.LWS + self.CR + self.atomends = self.specials + self.LWS + self.CR + # Note that RFC 2822 now specifies `.' as obs-phrase, meaning that it + # is obsolete syntax. RFC 2822 requires that we recognize obsolete + # syntax, so allow dots in phrases. + self.phraseends = self.atomends.replace('.', '') + self.field = field + self.commentlist = [] + + def gotonext(self): + """Parse up to the start of the next address.""" + while self.pos < len(self.field): + if self.field[self.pos] in self.LWS + '\n\r': + self.pos += 1 + elif self.field[self.pos] == '(': + self.commentlist.append(self.getcomment()) + else: + break + + def getaddrlist(self): + """Parse all addresses. + + Returns a list containing all of the addresses. + """ + result = [] + while self.pos < len(self.field): + ad = self.getaddress() + if ad: + result += ad + else: + result.append(('', '')) + return result + + def getaddress(self): + """Parse the next address.""" + self.commentlist = [] + self.gotonext() + + oldpos = self.pos + oldcl = self.commentlist + plist = self.getphraselist() + + self.gotonext() + returnlist = [] + + if self.pos >= len(self.field): + # Bad email address technically, no domain. + if plist: + returnlist = [(SPACE.join(self.commentlist), plist[0])] + + elif self.field[self.pos] in '.@': + # email address is just an addrspec + # this isn't very efficient since we start over + self.pos = oldpos + self.commentlist = oldcl + addrspec = self.getaddrspec() + returnlist = [(SPACE.join(self.commentlist), addrspec)] + + elif self.field[self.pos] == ':': + # address is a group + returnlist = [] + + fieldlen = len(self.field) + self.pos += 1 + while self.pos < len(self.field): + self.gotonext() + if self.pos < fieldlen and self.field[self.pos] == ';': + self.pos += 1 + break + returnlist = returnlist + self.getaddress() + + elif self.field[self.pos] == '<': + # Address is a phrase then a route addr + routeaddr = self.getrouteaddr() + + if self.commentlist: + returnlist = [(SPACE.join(plist) + ' (' + + ' '.join(self.commentlist) + ')', routeaddr)] + else: + returnlist = [(SPACE.join(plist), routeaddr)] + + else: + if plist: + returnlist = [(SPACE.join(self.commentlist), plist[0])] + elif self.field[self.pos] in self.specials: + self.pos += 1 + + self.gotonext() + if self.pos < len(self.field) and self.field[self.pos] == ',': + self.pos += 1 + return returnlist + + def getrouteaddr(self): + """Parse a route address (Return-path value). + + This method just skips all the route stuff and returns the addrspec. + """ + if self.field[self.pos] != '<': + return + + expectroute = False + self.pos += 1 + self.gotonext() + adlist = '' + while self.pos < len(self.field): + if expectroute: + self.getdomain() + expectroute = False + elif self.field[self.pos] == '>': + self.pos += 1 + break + elif self.field[self.pos] == '@': + self.pos += 1 + expectroute = True + elif self.field[self.pos] == ':': + self.pos += 1 + else: + adlist = self.getaddrspec() + self.pos += 1 + break + self.gotonext() + + return adlist + + def getaddrspec(self): + """Parse an RFC 2822 addr-spec.""" + aslist = [] + + self.gotonext() + while self.pos < len(self.field): + if self.field[self.pos] == '.': + aslist.append('.') + self.pos += 1 + elif self.field[self.pos] == '"': + aslist.append('"%s"' % self.getquote()) + elif self.field[self.pos] in self.atomends: + break + else: + aslist.append(self.getatom()) + self.gotonext() + + if self.pos >= len(self.field) or self.field[self.pos] != '@': + return EMPTYSTRING.join(aslist) + + aslist.append('@') + self.pos += 1 + self.gotonext() + return EMPTYSTRING.join(aslist) + self.getdomain() + + def getdomain(self): + """Get the complete domain name from an address.""" + sdlist = [] + while self.pos < len(self.field): + if self.field[self.pos] in self.LWS: + self.pos += 1 + elif self.field[self.pos] == '(': + self.commentlist.append(self.getcomment()) + elif self.field[self.pos] == '[': + sdlist.append(self.getdomainliteral()) + elif self.field[self.pos] == '.': + self.pos += 1 + sdlist.append('.') + elif self.field[self.pos] in self.atomends: + break + else: + sdlist.append(self.getatom()) + return EMPTYSTRING.join(sdlist) + + def getdelimited(self, beginchar, endchars, allowcomments=True): + """Parse a header fragment delimited by special characters. + + `beginchar' is the start character for the fragment. + If self is not looking at an instance of `beginchar' then + getdelimited returns the empty string. + + `endchars' is a sequence of allowable end-delimiting characters. + Parsing stops when one of these is encountered. + + If `allowcomments' is non-zero, embedded RFC 2822 comments are allowed + within the parsed fragment. + """ + if self.field[self.pos] != beginchar: + return '' + + slist = [''] + quote = False + self.pos += 1 + while self.pos < len(self.field): + if quote: + slist.append(self.field[self.pos]) + quote = False + elif self.field[self.pos] in endchars: + self.pos += 1 + break + elif allowcomments and self.field[self.pos] == '(': + slist.append(self.getcomment()) + continue # have already advanced pos from getcomment + elif self.field[self.pos] == '\\': + quote = True + else: + slist.append(self.field[self.pos]) + self.pos += 1 + + return EMPTYSTRING.join(slist) + + def getquote(self): + """Get a quote-delimited fragment from self's field.""" + return self.getdelimited('"', '"\r', False) + + def getcomment(self): + """Get a parenthesis-delimited fragment from self's field.""" + return self.getdelimited('(', ')\r', True) + + def getdomainliteral(self): + """Parse an RFC 2822 domain-literal.""" + return '[%s]' % self.getdelimited('[', ']\r', False) + + def getatom(self, atomends=None): + """Parse an RFC 2822 atom. + + Optional atomends specifies a different set of end token delimiters + (the default is to use self.atomends). This is used e.g. in + getphraselist() since phrase endings must not include the `.' (which + is legal in phrases).""" + atomlist = [''] + if atomends is None: + atomends = self.atomends + + while self.pos < len(self.field): + if self.field[self.pos] in atomends: + break + else: + atomlist.append(self.field[self.pos]) + self.pos += 1 + + return EMPTYSTRING.join(atomlist) + + def getphraselist(self): + """Parse a sequence of RFC 2822 phrases. + + A phrase is a sequence of words, which are in turn either RFC 2822 + atoms or quoted-strings. Phrases are canonicalized by squeezing all + runs of continuous whitespace into one space. + """ + plist = [] + + while self.pos < len(self.field): + if self.field[self.pos] in self.FWS: + self.pos += 1 + elif self.field[self.pos] == '"': + plist.append(self.getquote()) + elif self.field[self.pos] == '(': + self.commentlist.append(self.getcomment()) + elif self.field[self.pos] in self.phraseends: + break + else: + plist.append(self.getatom(self.phraseends)) + + return plist + +class AddressList(AddrlistClass): + """An AddressList encapsulates a list of parsed RFC 2822 addresses.""" + def __init__(self, field): + AddrlistClass.__init__(self, field) + if field: + self.addresslist = self.getaddrlist() + else: + self.addresslist = [] + + def __len__(self): + return len(self.addresslist) + + def __add__(self, other): + # Set union + newaddr = AddressList(None) + newaddr.addresslist = self.addresslist[:] + for x in other.addresslist: + if not x in self.addresslist: + newaddr.addresslist.append(x) + return newaddr + + def __iadd__(self, other): + # Set union, in-place + for x in other.addresslist: + if not x in self.addresslist: + self.addresslist.append(x) + return self + + def __sub__(self, other): + # Set difference + newaddr = AddressList(None) + for x in self.addresslist: + if not x in other.addresslist: + newaddr.addresslist.append(x) + return newaddr + + def __isub__(self, other): + # Set difference, in-place + for x in other.addresslist: + if x in self.addresslist: + self.addresslist.remove(x) + return self + + def __getitem__(self, index): + # Make indexing, slices, and 'in' work + return self.addresslist[index] diff --git a/Lib/email/base64mime.py b/Lib/email/base64mime.py new file mode 100644 index 00000000000..0319bbbf38f --- /dev/null +++ b/Lib/email/base64mime.py @@ -0,0 +1,184 @@ +# Copyright (C) 2002-2007 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 = str(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=False): + """Decode a raw base64 string, returning a bytes object. + + 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 00000000000..1435ee5749a --- /dev/null +++ b/Lib/email/charset.py @@ -0,0 +1,389 @@ +# Copyright (C) 2001-2007 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), + 'iso-8859-16': (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'), + } + +# 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', + 'latin_10':'iso-8859-16', + 'latin-10':'iso-8859-16', + '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, str): + input_charset.encode('ascii') + else: + input_charset = str(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: + rawbytes = bytes(ord(c) for c in s) + decoded = rawbytes.decode(self.input_codec) + encoded = decoded.encode(self.output_codec) + return str(encoded) + 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, str) or self.input_codec is None: + return s + try: + return str(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, str) or codec is None: + return ustr + try: + return str(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, string): + """Header-encode a string by converting it first to bytes. + + :param string: A unicode string for the header. This must be + encodable to bytes using the current character set's `output_codec`. + + The type of encoding (base64 or quoted-printable) will be based on + this charset's `header_encoding`. + """ + codec = self.output_codec or 'us-ascii' + charset = self.get_output_charset() + header_bytes = string.encode(codec) + # 7bit/8bit encodings return the string unchanged (modulo conversions) + if self.header_encoding == BASE64: + encoder = email.base64mime.header_encode + elif self.header_encoding == QP: + encoder = email.quoprimime.header_encode + elif self.header_encoding == SHORTEST: + lenb64 = email.base64mime.base64_len(header_bytes) + lenqp = email.quoprimime.header_quopri_len(header_bytes) + if lenb64 < lenqp: + encoder = email.base64mime.header_encode + else: + encoder = email.quoprimime.header_encode + else: + return string + return encoder(header_bytes, codec) + + 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 00000000000..06016cdea7c --- /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 00000000000..d52a624601f --- /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 00000000000..9ed8e4d3855 --- /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 00000000000..1352ede9e10 --- /dev/null +++ b/Lib/email/generator.py @@ -0,0 +1,332 @@ +# Copyright (C) 2001-2007 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 io import StringIO +from email.header import Header + +UNDERSCORE = '_' +NL = '\n' + +fcre = re.compile(r'^From ', re.MULTILINE) + + + +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(ufrom, file=self._fp) + 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('%s:' % h, end=' ', file=self._fp) + if self._maxheaderlen == 0: + # Explicit no-wrapping + print(v, file=self._fp) + elif isinstance(v, Header): + # Header instances know what to do + print(v.encode(), file=self._fp) + else: + # Header's got lots of smarts, so use it. + header = Header(v, maxlinelen=self._maxheaderlen, + header_name=h, continuation_ws='\t') + print(header.encode(), file=self._fp) + # A blank line always separates headers from body + print(file=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(msg.preamble, file=self._fp) + # dash-boundary transport-padding CRLF + print('--' + boundary, file=self._fp) + # 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('\n--' + boundary, file=self._fp) + # body-part + self._fp.write(body_part) + # close-delimiter transport-padding + self._fp.write('\n--' + boundary + '--') + if msg.epilogue is not None: + print(file=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(part.get_payload(decode=True), file=self) + elif maintype == 'multipart': + # Just skip this + pass + else: + print(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]'), + }, file=self) + + + +# 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) + '(--)?$', re.MULTILINE) + if not cre.search(text): + break + b = boundary + '.' + str(counter) + counter += 1 + return b diff --git a/Lib/email/header.py b/Lib/email/header.py new file mode 100644 index 00000000000..1d97f8f5ea1 --- /dev/null +++ b/Lib/email/header.py @@ -0,0 +1,520 @@ +# Copyright (C) 2002-2007 Python Software Foundation +# Author: Ben Gertzfield, Barry Warsaw +# Contact: email-sig@python.org + +"""Header encoding and decoding functionality.""" + +__all__ = [ + 'Header', + 'decode_header', + 'make_header', + ] + +import re +import binascii + +import email.quoprimime +import email.base64mime + +from email.errors import HeaderParseError +from email.charset import Charset + +NL = '\n' +SPACE = ' ' +BSPACE = b' ' +SPACE8 = ' ' * 8 +EMPTYSTRING = '' + +MAXLINELEN = 76 + +USASCII = Charset('us-ascii') +UTF8 = Charset('utf-8') + +# Match encoded-word strings in the form =?charset?q?Hello_World?= +ecre = re.compile(r''' + =\? # literal =? + (?P[^?]*?) # non-greedy up to the next ? is the charset + \? # literal ? + (?P[qb]) # either a "q" or a "b", case insensitive + \? # literal ? + (?P.*?) # non-greedy up to the next ?= is the encoded string + \?= # literal ?= + (?=[ \t]|$) # whitespace or the end of the string + ''', re.VERBOSE | re.IGNORECASE | re.MULTILINE) + +# 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 (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 with no charset. + if not ecre.search(header): + return [(header, None)] + # First step is to parse all the encoded parts into triplets of the form + # (encoded_string, encoding, charset). For unencoded strings, the last + # two parts will be None. + words = [] + for line in header.splitlines(): + parts = ecre.split(line) + while parts: + unencoded = parts.pop(0).strip() + if unencoded: + words.append((unencoded, None, None)) + if parts: + charset = parts.pop(0).lower() + encoding = parts.pop(0).lower() + encoded = parts.pop(0) + words.append((encoded, encoding, charset)) + # The next step is to decode each encoded word by applying the reverse + # base64 or quopri transformation. decoded_words is now a list of the + # form (decoded_word, charset). + decoded_words = [] + for encoded_string, encoding, charset in words: + if encoding is None: + # This is an unencoded word. + decoded_words.append((encoded_string, charset)) + elif encoding == 'q': + word = email.quoprimime.header_decode(encoded_string) + decoded_words.append((word, charset)) + elif encoding == 'b': + try: + word = email.base64mime.decode(encoded_string) + except binascii.Error: + raise HeaderParseError('Base64 decoding error') + else: + decoded_words.append((word, charset)) + else: + raise AssertionError('Unexpected encoding: ' + encoding) + # Now convert all words to bytes and collapse consecutive runs of + # similarly encoded words. + collapsed = [] + last_word = last_charset = None + for word, charset in decoded_words: + if isinstance(word, str): + word = bytes(ord(c) for c in word) + if last_word is None: + last_word = word + last_charset = charset + elif charset != last_charset: + collapsed.append((last_word, last_charset)) + last_word = word + last_charset = charset + elif last_charset is None: + last_word += BSPACE + word + else: + last_word += word + collapsed.append((last_word, last_charset)) + return collapsed + + + +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 + elif not isinstance(charset, Charset): + charset = Charset(charset) + self._charset = charset + self._continuation_ws = continuation_ws + self._chunks = [] + if s is not None: + self.append(s, charset, errors) + if maxlinelen is None: + maxlinelen = MAXLINELEN + self._maxlinelen = maxlinelen + if header_name is None: + self._headerlen = 0 + else: + # Take the separating colon and space into account. + self._headerlen = len(header_name) + 2 + + def __str__(self): + """Return the string value of the header.""" + 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(SPACE) + nextcs = None + elif nextcs not in (None, 'us-ascii'): + uchunks.append(SPACE) + lastcs = nextcs + uchunks.append(s) + return EMPTYSTRING.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 isinstance(s, str): + # Convert the string from the input character set to the output + # character set and store the resulting bytes and the charset for + # composition later. + input_charset = charset.input_codec or 'us-ascii' + input_bytes = s.encode(input_charset, errors) + else: + # We already have the bytes we will store internally. + input_bytes = s + # Ensure that the bytes we're storing can be decoded to the output + # character set, otherwise an early error is thrown. + output_charset = charset.output_codec or 'us-ascii' + output_string = input_bytes.decode(output_charset, errors) + self._chunks.append((output_string, charset)) + + def encode(self, splitchars=';, \t'): + """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. + """ + self._normalize() + formatter = _ValueFormatter(self._headerlen, self._maxlinelen, + self._continuation_ws, splitchars) + for string, charset in self._chunks: + lines = string.splitlines() + for line in lines: + formatter.feed(line, charset) + if len(lines) > 1: + formatter.newline() + return str(formatter) + + def _normalize(self): + # Normalize the chunks so that all runs of identical charsets get + # collapsed into a single unicode string. You need a space between + # encoded words, or between encoded and unencoded words. + chunks = [] + last_charset = None + last_chunk = [] + for string, charset in self._chunks: + if charset == last_charset: + last_chunk.append(string) + else: + if last_charset is not None: + chunks.append((SPACE.join(last_chunk), last_charset)) + if last_charset != USASCII or charset != USASCII: + chunks.append((' ', USASCII)) + last_chunk = [string] + last_charset = charset + if last_chunk: + chunks.append((SPACE.join(last_chunk), last_charset)) + self._chunks = chunks + + + +class _ValueFormatter: + def __init__(self, headerlen, maxlen, continuation_ws, splitchars): + self._maxlen = maxlen + self._continuation_ws = continuation_ws + self._continuation_ws_len = len(continuation_ws.replace('\t', SPACE8)) + self._splitchars = splitchars + self._lines = [] + self._current_line = _Accumulator(headerlen) + + def __str__(self): + self.newline() + return NL.join(self._lines) + + def newline(self): + if len(self._current_line) > 0: + self._lines.append(str(self._current_line)) + self._current_line.reset() + + def feed(self, string, charset): + # If the string itself fits on the current line in its encoded format, + # then add it now and be done with it. + encoded_string = charset.header_encode(string) + if len(encoded_string) + len(self._current_line) <= self._maxlen: + self._current_line.push(encoded_string) + return + # 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. Eventually, we'll allow this to be pluggable. + for ch in self._splitchars: + if ch in string: + break + else: + # We can't split the string to fit on the current line, so just + # put it on a line by itself. + self._lines.append(str(self._current_line)) + self._current_line.reset(self._continuation_ws) + self._current_line.push(encoded_string) + return + self._spliterate(string, ch, charset) + + def _spliterate(self, string, ch, charset): + holding = _Accumulator(transformfunc=charset.header_encode) + # Split the line on the split character, preserving it. If the split + # character is whitespace RFC 2822 $2.2.3 requires us to fold on the + # whitespace, so that the line leads with the original whitespace we + # split on. However, if a higher syntactic break is used instead + # (e.g. comma or semicolon), the folding should happen after the split + # character. But then in that case, we need to add our own + # continuation whitespace -- although won't that break unfolding? + for part, splitpart, nextpart in _spliterator(ch, string): + if not splitpart: + # No splitpart means this is the last chunk. Put this part + # either on the current line or the next line depending on + # whether it fits. + holding.push(part) + if len(holding) + len(self._current_line) <= self._maxlen: + # It fits, but we're done. + self._current_line.push(str(holding)) + else: + # It doesn't fit, but we're done. Before pushing a new + # line, watch out for the current line containing only + # whitespace. + holding.pop() + if len(self._current_line) == 0 and ( + len(holding) == 0 or str(holding).isspace()): + # Don't start a new line. + holding.push(part) + part = None + self._current_line.push(str(holding)) + self._lines.append(str(self._current_line)) + if part is None: + self._current_line.reset() + else: + holding.reset(part) + self._current_line.reset(str(holding)) + return + elif not nextpart: + # There must be some trailing split characters because we + # found a split character but no next part. In this case we + # must treat the thing to fit as the part + splitpart because + # if splitpart is whitespace it's not allowed to be the only + # thing on the line, and if it's not whitespace we must split + # after the syntactic break. In either case, we're done. + holding_prelen = len(holding) + holding.push(part + splitpart) + if len(holding) + len(self._current_line) <= self._maxlen: + self._current_line.push(str(holding)) + elif holding_prelen == 0: + # This is the only chunk left so it has to go on the + # current line. + self._current_line.push(str(holding)) + else: + save_part = holding.pop() + self._current_line.push(str(holding)) + self._lines.append(str(self._current_line)) + holding.reset(save_part) + self._current_line.reset(str(holding)) + return + elif not part: + # We're leading with a split character. See if the splitpart + # and nextpart fits on the current line. + holding.push(splitpart + nextpart) + holding_len = len(holding) + # We know we're not leaving the nextpart on the stack. + holding.pop() + if holding_len + len(self._current_line) <= self._maxlen: + holding.push(splitpart) + else: + # It doesn't fit. Since there's no current part really + # the best we can do is start a new line and push the + # split part onto it. + self._current_line.push(str(holding)) + holding.reset() + if len(self._current_line) > 0 and self._lines: + self._lines.append(str(self._current_line)) + self._current_line.reset() + holding.push(splitpart) + else: + # All three parts are present. First let's see if all three + # parts will fit on the current line. If so, we don't need to + # split it. + holding.push(part + splitpart + nextpart) + holding_len = len(holding) + # Pop the part because we'll push nextpart on the next + # iteration through the loop. + holding.pop() + if holding_len + len(self._current_line) <= self._maxlen: + holding.push(part + splitpart) + else: + # The entire thing doesn't fit. See if we need to split + # before or after the split characters. + if splitpart.isspace(): + # Split before whitespace. Remember that the + # whitespace becomes the continuation whitespace of + # the next line so it goes to current_line not holding. + holding.push(part) + self._current_line.push(str(holding)) + holding.reset() + self._lines.append(str(self._current_line)) + self._current_line.reset(splitpart) + else: + # Split after non-whitespace. The continuation + # whitespace comes from the instance variable. + holding.push(part + splitpart) + self._current_line.push(str(holding)) + holding.reset() + self._lines.append(str(self._current_line)) + if nextpart[0].isspace(): + self._current_line.reset() + else: + self._current_line.reset(self._continuation_ws) + # Get the last of the holding part + self._current_line.push(str(holding)) + + + +def _spliterator(character, string): + parts = list(reversed(re.split('(%s)' % character, string))) + while parts: + part = parts.pop() + splitparts = (parts.pop() if parts else None) + nextpart = (parts.pop() if parts else None) + yield (part, splitparts, nextpart) + if nextpart is not None: + parts.append(nextpart) + + +class _Accumulator: + def __init__(self, initial_size=0, transformfunc=None): + self._initial_size = initial_size + if transformfunc is None: + self._transformfunc = lambda string: string + else: + self._transformfunc = transformfunc + self._current = [] + + def push(self, string): + self._current.append(string) + + def pop(self): + return self._current.pop() + + def __len__(self): + return len(str(self)) + self._initial_size + + def __str__(self): + return self._transformfunc(EMPTYSTRING.join(self._current)) + + def reset(self, string=None): + self._current = [] + self._current_len = 0 + self._initial_size = 0 + if string is not None: + self.push(string) diff --git a/Lib/email/iterators.py b/Lib/email/iterators.py new file mode 100644 index 00000000000..e4476e3bd24 --- /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 io 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(tab + msg.get_content_type(), end='', file=fp) + if include_default: + print(' [%s]' % msg.get_default_type(), file=fp) + else: + print(file=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 00000000000..539af90a788 --- /dev/null +++ b/Lib/email/message.py @@ -0,0 +1,790 @@ +# Copyright (C) 2001-2007 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 io import BytesIO, 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() + + def as_string(self, unixfrom=False, maxheaderlen=0): + """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, mangle_from_=False, maxheaderlen=maxheaderlen) + 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 not decode: + return payload + # Decoded payloads always return bytes. XXX split this part out into + # a new method called .get_decoded_payload(). + 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 + pass + elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'): + in_file = BytesIO(bytes(payload + '\n')) + out_file = BytesIO() + try: + uu.decode(in_file, out_file, quiet=True) + return out_file.getvalue() + except uu.Error: + # Some decoding problem + pass + # Is there a better way to do this? We can't use the bytes + # constructor. + return bytes(ord(c) for c in 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, basestring): + 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 'MIME-Version' not in self: + self.add_header('MIME-Version', '1.0') + if 'Content-Type' not in self: + 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 'Content-Transfer-Encoding' not in self: + 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 __iter__(self): + for field, value in self._headers: + yield field + + def __len__(self): + return len(self._headers) + + 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 header not in self: + 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 header not in self 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 header not in self: + 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 header not in self: + 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' + try: + # LookupError will be raised if the charset isn't known to + # Python. UnicodeError will be raised if the encoded text + # contains a character not in the charset. + charset = str(bytes(charset[2]), pcharset) + except (LookupError, UnicodeError): + charset = charset[2] + # charset characters must be in us-ascii range + try: + charset.encode('us-ascii') + except UnicodeError: + return failobj + # 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 00000000000..e69de29bb2d diff --git a/Lib/email/mime/application.py b/Lib/email/mime/application.py new file mode 100644 index 00000000000..6f8bb8a823b --- /dev/null +++ b/Lib/email/mime/application.py @@ -0,0 +1,36 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Keith Dart +# Contact: email-sig@python.org + +"""Class representing application/* type MIME documents.""" + +__all__ = ["MIMEApplication"] + +from email import encoders +from email.mime.nonmultipart import MIMENonMultipart + + +class MIMEApplication(MIMENonMultipart): + """Class for generating application/* MIME documents.""" + + def __init__(self, _data, _subtype='octet-stream', + _encoder=encoders.encode_base64, **_params): + """Create an application/* type MIME document. + + _data is a string containing the raw applicatoin data. + + _subtype is the MIME content type subtype, defaulting to + 'octet-stream'. + + _encoder is a function which will perform the actual encoding for + transport of the application data, defaulting to base64 encoding. + + Any additional keyword arguments are passed to the base class + constructor, which turns them into parameters on the Content-Type + header. + """ + if _subtype is None: + raise TypeError('Invalid application MIME subtype') + MIMENonMultipart.__init__(self, 'application', _subtype, **_params) + self.set_payload(_data) + _encoder(self) diff --git a/Lib/email/mime/audio.py b/Lib/email/mime/audio.py new file mode 100644 index 00000000000..fbc118951ae --- /dev/null +++ b/Lib/email/mime/audio.py @@ -0,0 +1,73 @@ +# Copyright (C) 2001-2007 Python Software Foundation +# Author: Anthony Baxter +# Contact: email-sig@python.org + +"""Class representing audio/* type MIME documents.""" + +__all__ = ['MIMEAudio'] + +import sndhdr + +from io import BytesIO +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 = BytesIO(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 00000000000..ac919258b15 --- /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 00000000000..5563823239b --- /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 00000000000..275dbfd0886 --- /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 00000000000..5c8c9dbc4d4 --- /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 00000000000..dd280b51d03 --- /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 00000000000..5747db5d670 --- /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 00000000000..439a4a02ebe --- /dev/null +++ b/Lib/email/parser.py @@ -0,0 +1,95 @@ +# Copyright (C) 2001-2007 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 io 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 + # XXX When Guido fixes TextIOWrapper.read() to act just like + # .readlines(), this... + feedparser.feed(str(data)) + # ...gets reverted back to + #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 new file mode 100644 index 00000000000..ce624d95ee7 --- /dev/null +++ b/Lib/email/quoprimime.py @@ -0,0 +1,307 @@ +# 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 ascii_letters, digits, hexdigits +from email.utils import fix_eols + +CRLF = '\r\n' +NL = '\n' +EMPTYSTRING = '' + +# See also Charset.py +MISC_LEN = 7 + +HEADER_SAFE_BYTES = b'-!*+/ ' + bytes(ascii_letters) + bytes(digits) +BODY_SAFE_BYTES = (b' !"#$%&\'()*+,-./0123456789:;<>' + b'?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`' + b'abcdefghijklmnopqrstuvwxyz{|}~\t') + + + +# Helpers +def header_quopri_check(c): + """Return True if the character should be escaped with header quopri.""" + return c not in HEADER_SAFE_BYTES + + +def body_quopri_check(c): + """Return True if the character should be escaped with body quopri.""" + return c not in BODY_SAFE_BYTES + + +def header_quopri_len(bytearray): + """Return the length of bytearray when it is encoded with header quopri. + + Note that this does not include any RFC 2047 chrome added by + `header_encode()`. + """ + count = 0 + for c in bytearray: + count += (3 if header_quopri_check(c) else 1) + return count + + +def body_quopri_len(bytearray): + """Return the length of bytearray when it is encoded with body quopri.""" + count = 0 + for c in bytearray: + count += (3 if body_quopri_check(c) else 1) + return count + + +def _max_append(L, s, maxlen, extra=''): + if not isinstance(s, str): + s = chr(s) + 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_bytes, charset='iso-8859-1'): + """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 in the RFC 2046 header. It + defaults to iso-8859-1. + """ + # Return empty headers unchanged + if not header_bytes: + return str(header_bytes) + # Iterate over every byte, encoding if necessary. + encoded = [] + for character in header_bytes: + # Space may be represented as _ instead of =20 for readability + if character == ord(' '): + encoded.append('_') + # These characters can be included verbatim. + elif not header_quopri_check(character): + encoded.append(chr(character)) + # Otherwise, replace with hex value like =E2 + else: + encoded.append('=%02X' % character) + # Now add the RFC chrome to each encoded chunk and glue the chunks + # together. + return '=?%s?q?%s?=' % (charset, EMPTYSTRING.join(encoded)) + + + +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 body_quopri_check(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/__init__.py b/Lib/email/test/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/Lib/email/test/data/PyBanner048.gif b/Lib/email/test/data/PyBanner048.gif new file mode 100644 index 0000000000000000000000000000000000000000..1a5c87f647fbf33e5b46103119c9fd42afbe9e5d GIT binary patch literal 954 zcmZ?wbh9u|oW`KcaD;*3|NsAAfBbp<@yCPLU#~s+c;@cAL)TvKIRAX@$tQ~sJ(#)s zZvU2Bt!uAUEx%l_;C$N5GYljG9gupET@0-MA1L>wWX{W2wJzuNz5<=|CAs%2*1fNJ z|Np>(0uLRj{u4`zPUg(xU~Mb*(v@XkI=brNiYoco`%D2DvP|tC#8;NFu&`fKe77qr zlBuDtA!1D-SDhvwJ5wruaus8_I%gGImKHO^L=B#*8C}ery!HM;nrsXl3#*nWaZg^R z5nio3d1~*>RWn)V&Ql66(O_X<(dc8?t<1~DxLBQa>qgb8Gpef?n|RY_E~w8-(OTQ2 z(z#!wbGypk&F7Vl-_<}(vdYkSoBs$OmNTCiw3qwv!kKdqLh z%W$z)u`F1y?1cW0i zrga=;2CU7=Qr-d4nM{n!OgOm&0%ok#R5N)cwIixxD>TOHP&mQ zrv`_R!GjYE?idKxgg;q%WmQXa5%apY%cu(L z@w9n#%IA4EW5cdP);el8gun7|PupwVz&L+yfpnevg-6|t>UdmO^c7C6K()XX?E=|se$9uE<*?e4CIDNmgA zzs{WCVauO0^C5@Ms|u$CZHo;z6tz^8sMTiERh#ai)xO4Cy?RFYG$BLPKUHlWUjDMwcS%4#~szhHJl; zs)t%zEq^Vr?OQ?gMophdx_ZtNZXTX_ovA=?m*a&U%@H#vm22;@Igm3F&#|5EvW>p)=!6hL2%%!YfB_?hOiN-`lllUss(0VDkB{x+ zV>>gQt(|>lvK`LH%~5@2!8Sa5^#)cC+^0Yp?ZN&4&3u{`ddw zFMs(<^)G+1ukrhT`paJ`|Lfy#eByGPEX$HO&N9cg9UFh8xU$^FUs;kQDZV+mljpgE zC!~~Rk#cyLrI}?IhNfGlVcC|Q+m?yTGA&(IRZZ6oLpOEPGIU+T4Mib;*`{vTc!VMv zifAe+hBEkrd?(d(v;|^J(l#k$n1mP`?c+ihXw@)55$Lk;C+euGu9*tQx46hnLT{yc zqw(!zmD!1E$RgKl)GPH`xl(O51|pkBbALP>UR~YZ4=)~WFK6>0N@b4ji6YCJqOO`~ zjum)8U})Y@McMRh)Ay$H&`q>V75W2KqPl&S=d{?$11C?@B#NU9vA6%B_I-!c`x))ohp z6=lXMz^V()9#6Bnqve*wGu=w1({2ieCWfgX3QQd&4kSZ198FObno>B<%9DKIf`v_5 zHVr#k2EhVMtaE~)8j-sUMzb)=a#1sMBk{su6=$X?aF$}Gk(Z7ak(Y#;mMeA=%!AR? zbE8a4^K`WsPeu>!GKw@U(aktqrqe|hS`I^7oSLKR+|P4WYWL_4E2)~1g2niLqtk6s zyewO(t|(luMYX%4VrpRm4ip*+(Ve!Dqn z4^#!TIl8U#%^uzF>yCjfV3~=+3j>~2Z71@lZs4Y=q?wu?&b-OPaOKbJ+)`63cHQyf zZoF6|fhZfg7EZm%-DD9gbHk9qC1JP-?-o9`EF)^7nl7T*Xdb13BJz|f=&9po6Ev+E z?Y>BfdSco0#8eHYHRy4DCABb>b5jw^Yl&fl~rS@4p zvW#({tFlDa5O7e^*faV<{Noy^NJO%a4{FQ?QX3r$<>vTa7-@^q4Bk!*2%uWR!8 zJX(IQ1TN-_%; zv2Q94Ejm^(xtsd4+}350we$F9HbHY*Dsr|2Zb+<^Yzf$!DQC^oMV6|R-Wiy*6Rv#Q z*Htia&E#!2TA7}JwS-)kG|$LA)f|Y;s@j%wCr~4a6Pp4hYS!3XMUKPRHQHfAf3~vj zAqg0P)y!lVEM`e8o4rm(o6&S`4M7vF*KO9E8bjSz*}TN_RBn$Fe`0vNJZL!_#PwY? zO_Z!Hn_?0_xXGOviUQZRy7oN3!;JLvk|_5qXBa0BhRbtI+Ze=)U=;X)kT(Q%U?wv^ zpPG))kXVIDR!)Ky?~5&g?`8fZ4dR5->pI5>p&RSV#FVQ#CwH8=moIIaxAUOiHy+fa*-?3^=12GKF?+vl>>Tdh z7Y-AH8QN5(a@4+l`C%EB=8FH4uD>t-x%a^ketQ*-dPjo)?dgkc@u0IIzSTDNPR>uBJeajt(Xp~o`n>Ny z>zWVqv@L8}so!b$-grg2zHgRp&SR!|ChoMTM0g%&`(#!>g}w*y>&Bfbf^2_mN@;ecV-p~uNKF9o&M*j@}X~Q zyNh^7k{3zNZnfUbUv<>O-pl0~6**J>*V3P#eCsJcc%^lGQ`;%TG z<)??`3{s(x!m1uE>0IlVejO9rL=kSb^l3i zp3d_2?QCOL`S0Vw(@t<&)IX1>ojozzX?yQJJAdD`-rp5wtk3R-dQtW0Z^yf@*nD)_ zGLlz)uOsnv`Jc;QUrqA&^BvdQQPb{qxl;V{M|Zbycktt7lA4K7ohq+))c-nm|7uS^ zcpLPGXs}m3dbZQ}egE>WrNP^eyZ(|+cB_4d5+b<39qhEgZ z!K%F2n7utKZIll_`kU&x8#c5H@$ZGbe;i)_HQ)Gn*fcKq(PsHle)h8b=f~rhn=j9P zAC+$>dV6!a+uwYa2k(zJUp_m3f7`9JkLLAmTYlEF z{_F7JKL&fBKW?XD_pHCM+9}YrKR=v5-`pC#JK2>I^>~LG^frz1hY!b3s3-gH!}i|y zldC5K2`aC6`upY9?#Ai6$%dAV51*AKc2M0r{r$fDdgJcH)mC@tn=e_tPL7%!6d zoBLg6UwURLgSJ}uuz$RD|JU?WFtiKvhi5dSD~)IUfB2tY7hnH*Iz8F64@%```dZq3 z^~e6Oy7{-{kMB43*4^m~Ij{ITFQ;$E5%Zt)(YO1&UVgt>?-a{)vHRxB$)54+`KPZ} zv!@^Rr+Ra@|KwNdxAx_;r#q*2#&ApheYYX@RGVGBdH=_({rA(O>rrdt`*eF4=?~>! zcHV5C{^!%JA6K#W>#O&zo!(}#+_TUB>+sJ~`TIY=ety`zx+;_^O_6!}`fYw%EB@z0 zyQBW?xh8MbTl#XQo&294-j_Po`)|L0?}xwBT}!g!TKChR2d&;;?d$wxdrzJ0ZSEF3 zg}+zcxbuyTC-U@cS}A`PJ3l0ECU1KGG%t3avJXEF;xh9aU-K$Lu_NujKM6MeE*y{k z2)5l%y`JISc6VBDvp-%|{>IL`Kc4Jlf6n3!Th5=m|2X?bzuuS~f16ZGXIf>sVeyS$ zxi`r*|3X+sXU&a`xc-vfty4~V@_)VmQr=me@Ben3dLJg{4`$>@rQtb`K1!i-rHT_Yi{TRT5fee9=u&%|8jA{{np^vZ)el(T5ZrX zKE3_pa_5=&aQ^;>WqzCb{asBgKlKl~>=xgZxboSjTdgV-3)JH6_lwe#S6%aD z)+?>f4RuFpR0{Mz>;rydyBh9ahNX*#$?!?{b*W>S59 z_Q&U;^w&YP^|e~wb|z|Z2UFa#-W+{lcc1NL!xO%2mjC-~zqL^)PLEGk^nBzkx425BzWsUsolF0{;$-g>U!Cp`d-?W@t#bb6 z@K0&$Wo7o`^U|1%PiA|)LSd)y{q5Oh``1!C{}jgR^yq9%@9h=q!f$_k@$0`9)%a7A z>y!IryH$L#Tgv}=yRSXpu9)9$Qz0CmWv{niJ$qibd3SN&|J!a!-_IPuyS)?kUhh;I z&Exk6Bkfn+kUsJ=_wM3C>ukL!Rk=Stf3pj}76t7<&8_K;T5S}zOSJ#{=~wK{U61{y z$w4yBOU<3FBIp0}@J}6Iyz#+ZFdp8=rFMC*td0M9@;Tq#+PhN@eQBDGgJOMqtH>sA z&c5oews)iX!6+TizRx?%-cDJY{(f>`Y(3q4;PzEabshv(*EQ4INAHH+Bom^6mX0_jG&PIKMZq_3?w-sBY|4 z+UeV)Kf}GP&4~YMEhfRuWu^A=b*1E-zP&l>Y&3V(GvofjI&+t`!plmT%|Gn_xvIZ@ z9kf2@>FS>2Fq-P+W+nQ9|z+1}o)mAdN1m&1|pYNu7YvnNwwsi`&GFE+H3^P{}^YNJ^h`HNNV z##Fbo+bVOxmy^$aXXho;yMMSEx2MlNIi^``Riwp- z!#~_XVS{F`PS59V9DVq5>1;l)bdN4iXMM9XQnOaMP!N4AfVaE%ly=Sz?lp!| zt|hq!#iQN+{`EY4u~X`w-kr{ya&IzCF?W?-{Q2PXvbMRwN+)MywJ&I=YEmhc%i6>5 zC&$k7y{-P};e1t>dGAW=?roQv`ToIYx4!w5rp_;xdQZ|$IlZu3D9g9MpB`tg3a^{f z<@vH{()Wqc-`pv5mVcb>N7bDtyl{E4f_EwP#qO)U?V7#+`Rhd7eA=#`o?p#m+gv*R zSH;bWdHCt;owfUu>#9=0<-W z%_f66SH#R!=+oc7?you<&&%5N*F$$gO$No?VzDBAfA{skt#7<6Ti5%C!GsE891doS;# zE+y}ji#7H9_x;nXvb9s2j1L|Rzj0{;yVZ&v=iAqh!=U_>DxYAHHGA+~T~$hj@*w_l z_i162pNN&SA9pKNQ!Wg*Tq+e9>)`UsRBt{Ji`O^vxkw)PrBZR1mQRlNAJWRR?#^)O z&KX0$G}3ZuuR!y+pO4O#<(-|qMRNHd_|nMB2Zf!zYJc(dVn68Dp0adszKT;lxU==W za=FOrXJ0>G#ibXOy;*X1r!2KmX!mQowG!|_R4=|1Pp;514M-dtu0-|AHvWBBFn+$ndS3s!pVXcDaix!G&h z>OFOOFg%N^%m!mPXNe(qWH_y;O1W5Nqr=s?Q(-n(B{~ZowQsnI&$dg&ra0dpo#y4< zGhT_$6GvgK*eu!{J?B*b#QWH6^fnCc=534=FH@NWtWSkHXA>DKE2I~t#W@9-A5gxwY(3^;$ETL zGpC=fF0~T9t39kP0@dNCw}DYC?v=Xw{9t~r>~cHspdP^koGqB zFoW>B>q@SBb~Q}f?IvTcZpS03y1UUVrGD;GnR0tKkL$Jiz#0BHI$vsq?ON4?*el9y z*R|z65U0+5d^|f}R@kofeRAW|7L~+e_r$+h2W3Q8RSBh?KK7Kp=2G`5-Y#Dldo}`{B7s{=c z#L0f&ZtU(o+1spiijAruk0zO1W7T*uzWaQ8cy6CrFc+#tyq zsZgfq`NQbOyBnSzk35Q!3`bIvu2tQwzvy?R1d#(jKf7{6R?YI|X#RCEcFRt+p9#9& zp#;X2xK54L6aV`9QxSi*4Q|*?^ zWl@rH*$AWCWyW&~+$*cu)q|V$+x>xI!5b&(hL+G393%GU ze%focMZ-z;xpVDmd718t2nO*^>QAEnpe037=p@t8%x62bGDAs%Xr`-sS7BR1p2ewi zoBg=6rgeqa9T?Squ$-mcUWd<}Rqo%Ooc;i(bZyy?X-TkSwO-n(^cYn(hqL3e#hsL! zew291aygzvy;iLwvofbm$G}2Tt4h;?sK{`Dt_-T$9ta%Ir<2RunZ?o#iI){QTi)L+ zMY`Oe`ZU7^lkfM7tl6tjt#+^Fc;jKxYZXhaaqu7^!~xjk_U!m_7Ft}lT(0%} zj7UoM5@gMZQJ}eUYYAgsfz$k1b%Pl9fiw91dB5S7erA zW!;iNn8_s;3vX$RFpf+iRFi9x={UN~FiN!Y7kV5e%T(nVS;vAQ2nZLf#Im6=T_t`L zg6k-@D@InBf{QI(>0jGjY_%J9k8nCUS2#b z+pS7fS4>Gy7sG`V}mD>rq)JRbfScjS5(QCC$J!bK2rU5b}%OA&ghvznWHzeQty5jgVwRR*UZ zLqeepb(LMr+G?$@IEJKktvGN6j^-5vQni76x;&mX!g(uwse`pTbFPStGQ!2mW_uM@vwV>b*>DsIe68;* zu};fI7zdT+~Bt&fHB3rJdfJZv%cqIa~=_##J&&gvhB^_vA#1I)&ZpZ~GjxNuOrL zqIGkXMzNh#DioXZW?n0nKYn(?var;5_ssBk9L*)Yva3j@DEm+uM-SEs?@qI8zuvSsR-{W6uO}d=e>8tNoexI!*HKnVql_{Ji z{`FY9->#$`X0V>XpHXp>Soc;0o zYB>)2&w_p-n;w00tm&X!;bVrqRN2Dn>#sjXo>6&z-z`kfzFj!MtgzSPOxC<)+I#cU zUrxUpT?@!Rvt9(f6*tglA`MtJqO}TH9q|E`Qu*yyjL0sC-d+iY3r3{#qtLEce%-yyYHUdet6kF;x^NCbgvxPgRoPl zj9AQOoeozTynAx?VN3YZ-qy0kgYrqYyhgWaB&`1+uugUN_tvX7ObPD8+-L5zlWA=t z6l1|rwUyN2+q>uEU*682osKq4j}N2MQUAW#kjo~lnUG2OPW#<6`~9Z$g?l~rdv5w8 zr6;}eoX$DRZD|x$IvD@@#(#R?KDFm9b8+Ugr_DxMW_iU+1jndX-)zwDUa+6}7Z*t- z3Kz@4QfbWDLC%LVWAy9uFaP=RzCz16o~FjRTkDGRDYc}P_GD8729l}Be!rb$8m(s7P}kIfP*=v1V# z+T`r%*E_m*RH@Coo$Jfe*+eipW=%rCH{r$n>&E@5T0S**@A{44hZvtphNyN2qCp|! zLws13FBi6Q)8`$Yo%!m>H4R>*m`q2k+TyWGS1Z#RNyq_^+)PHKNzx^mM>+>!sAd>| z*|{EtnwqPKEE}dKAqgl`IVq7DL69;YT&?GGQ^`z8MY4dIYbp|r6anClLbPA7g9u47 zjtM|*s!Hf6Ch~7cQVwzupk>u8%b}%_&x9g6JRg>0np$qlR<2seAxTJj6!Ly7TSc6o zS5!%{Y*a`c$1q{<>UoY-kOT-J$#gTZG#DDTPI9M^#$+M_j)qCjm1Ek30$o>Z)3H;;ZUC@(E)zcibIJ$zNV1`rOh)oIUAU3iLkZ_ z0_xI0NZyRbLFA^klNv~r$ayJ43@^*TIf1G=mTVg!33))W<$Gfoe?b`gNK)e{nc@Si zh#{n=ry!Mvx0tytfvap+lwvG3Cs~8OM7PnVBb&Ji3L(VJR8yVI%5%dp^GV1@apGt8 zP0XYdnX;N)O0<#rX0e(k+m50ns$wOMo5op)1=e^`<{W{-;M2&O$Ep-sism>-=IYY% zTy;WA^~1=C^wdT68#aW5`~o_dD~oAj88qA@N@5zw^s#e=vkg&0Kwp9y*JLfzHRO_5 z5+{JovMdZ&UI2I>d$TZ&!J?WTYeo>JnT=)0G+pkSifP5Vm0>@Mye=`wFyKU1>U9-P zRPsz4kTf^b$d-2IrO1Q>uuWpik!4c@Z>q>WvlA>jxZSZ#8z!F}db81L?pju2AzKIQ z;W^170BB9-97j7^g`63*umf3@)VO`S@HdSM%9yI+;xui{)aqT6uWr z&fMk7UAms@hOXzk0kRE4WP3zu9FwF^CnHt|5ga7FQc)yH5Y}B|jzl;#U=q`yjAm)_ zom}{X+*yBTSeE5rQKOE8VT+(wL%Ju~x*!`#oFsvi+uF2pd5Zk&2>{GmGtpK$|}STQc*$T zI!#r`!EP~knQVM%ng*HWFs7TYtZU0IzC1b)$M%XYnM@l3N<6_u~;KI?KjsxocM z>b%|2td0ag)9F|F(Mf4A3QCpO^Tjj>+f=Nu!Q3%9x^G_ZQ`GIG(p-&J#@r7@EzFH< z7(>W#*`E)pc@!1Q*(4t?N08T%riSxXo^qVGA93!fQAnq$HClP8P8^A8g8X8h9^VP< z!)j1fGC1X&z@ikMfwDDio$E-8wBwBBcFSOUnFV;lB5My*2{eafCJxHjPQ?MucRMsE zDGV>M48seWA`T!2BwlkgUQ;ANGBwSz0d|lAj+}8D3MjLoYV9aDb0m|;fe)vKyOu+7 zdcgS7lp%%LTanv=YI z6d?)qgnm*KW!JTcIK)lJTT+c&XUQplw1P(Y~hD3Y;40#9@b$BQI+o=1wQ1P2_j zuc1MYgIstV0E+=vF(N_=LDKjJ0!Vbp_rIqDf$F7#b?83Rn^Uk=U*( zf+8A3Az+adL$TpjBwtYwaNAOB6=x%0eK@G6ky8?wAw@Ot%|x4683)rsmO+CdLk>P* zXhcmL8OG#*n*apX>p{#E5CN1=mej%UEdz)Rw=pA_VPZ=dIXDG<34}~ED7ub9M`~}!xzUyvmi{>VWR*b1H=PI zSr`g941fhg0s>HBEs%A_>|ytyLxM3ddE|3VAbAGfKz&exTNo6Ui*N{*6i-M6023@R z5hl1pwjw|UtReCNLhyi?7o_hs^RJr&OB0$&4bl?f4syPPFc?OTPfWmio zh2Q9o+{V_&sQ?rQ^V(L7{bRjG}i)tiD^gyw_W#AB?2c{=x>uNSJEXfWOsn-`Ae-Xl; z2L6}u%yhirEW{xM`!W2#jTFjSIH$loiWb_)JXt{@T zCfLH#!&;o5o)B8ne&^TfNkecS${+74Q6G{U9ru2MyKMz$JyBXFj zwt}LXGeicsR5ZoDrmx1UgdM<&kjY9SaYz2nLR1);4 zh>%S{>yOx$$S1fMNGF8%pj*fuHxO6=_hJ`ADde!dv9kc}9a0VdAh!t1Vi%IFXeBV% zApndF8i;I9@cx=vp{a2E$T9)p4II+4GAuCJJm51@A6^ppH?X`mI)jJd&*C+LLi zP6;_j=u)v{2&tS%H~4ypR|m=-4dS#CBpK9P3Y3xoWDv0k$&Q&;WRxKf@dIW-8AMF6 zR;DF^8iG*FG{fX#B~XxvK`g3F4$Gm`+Qb57aJaw`pyG@QrolvQ%qu8`(12eElc7jZ z=5QTAFq@zhD~9FASGaz#aHxX%klaK9l5bFpiUOGnJ@GhN;sYZ8(Kc38Lkl{DI|c-% zCRz~AFIFeEFd3DfP(7-eE>0_6Sq;F2!6s->uar|z~q>0 zkVg8zLK6W^#PnLBz+;6ju|$~Ff7K!LPJ{Hq^6RlQ%C5hY5AuyPO)k>+|L-EtAAA1)JbJA0^A>4=6eHJ~&h`Dr zdZbZ8|G#Nk7b6wO54qOW2x)8b$h|coYhZx8n4-sJd2AY`iA=yWlOeA;1k1N>{{J1{ zdKP|mio2u%Q~^`2Cw0vaSj?Z5)-C>|W!*U;Xx%Y7daOcjuPx%AUH$v{&yMh%jDr+@ zTv0Nw7zTlx_#yPIi;z-3C;ML&Fb+Z*84aoPuSHmsKnO*-HP8O50Wx}07@Ue>ktqNS z!45;SC=5mhBqAao(iNNu;jwPXNMVw|wG0=MLYUUnWR77i4~H-f9IF%%`A&Qbnu~|y z7?oiAnuBJ~j_314f&U%q$ABMIQDI2S{WiafeOtlVP|T+!DuOE8*W)GAY6@P6lZ!;s zr#jVRB-l)s^Ss?`DJy$vLH5R0D8svDW&Zp&ReN2@jBFo0Lb97|bD&s}b3RW8Ra%|p zF#a5br!%fG;1b)pzmLUEQxEbu1)9oZU+Q!y)Ej+|}F0)SJ zoleAZQF2F#jPrtuJxRG%O|+1ja+1(r5#3FrCV-#EFMMrJ0!!y4vO0&Gogo_1-jFg;{9F^@GCe1iU6ON-@x7$#Y zIpFltW+@)0X02Rm^rMrpU?{1H1W3nH}5tzL?7Z{Y76iz z1NfG>-;#4B%acirvzoSyR3l9gv}~5C0F@5YhlYSzwSayBR2RT5GSY13 ziDm~`#t(FhAp8}CJOH`?)|3zp2tr*6psslp4sy+j;D&`m8WigUDXJkj8v0ijpc^yG z4uI7V$55c^MG|fBEhEn2OhPaPe(lsJ(FOQ#VR-=!iuTIXBRjHK8Q30HRE*)k4#0q6 zR!gF@)U_zjR7OqVw1?@A3=-%xC{~=Z=J{+0=e?Cm13ko{<5ijq7UB{bsDquy@Y7kY zjBT4?(}<75g)NzxDX3`oQc-3rxEn znO%1pGqP{W#*+O^ja0(lIp?la=RwN1l<50#5HK6$9hk_*(SQ9$g0?q~H6o=S0 zW{2%FjOH$k@Lm>77O|rc5r`aTFNxV`n@F!=Ipe`drXG9{0P_Zp!QyB@UoaH~z)0j+ zK@LL0zfmm%9(MteDByWX1aL*&A1l#aXlA-3a%LLjB#SV|QCk=)fTV&xHLU4_ z6kz0{2<0Alp_U^&ro%^qOf1=1u+eR7`mrK2fS2Yfh*XjU1lPU@->wl^{NhfCgB&Lq zbAh#8ScRE}I0DDvw618+#N>V{%|cTWw49RzL~w6x4&XG?0zOy+D@gt|Y$9p|rayopc}}1TVjFmd z4hT#_V1}q4z{IusK&Sv%5D1BYcVe-Uzm!XP>VYz_hurXWxZ7Oe#Z0gPhCib`}a zl!*+F0lFuKF7P}c5O{!CsmL61G+RMd7S7M|=n$$*;Ziw7A%v22ghx=>v;k351;;gj z*dQZ94TB;N4OyDnqNmK5`H`bu>pI zXN@)D6#yIt#Me?4oBmPTk>Ow{2-*=8jDLx4WW;}vX+YnA<`@FNIbvNvqQH*edrT~p zjSeadxX0o=iitAD7*ri+;b9md-44Lt^xZrQGJ@Rzxv^v5SA;JeailEL(g}_-CpomA zDH@4^d6x0c1eTE;my2#f9CS7~$+i{MjTIvk8D3#1P9A2GduFI<%r=F-Z=U2v)2i zBC8ut6xd0)eheoh3l$@(aiBY14o#>@uq!mUreXgg_`}l_Z|D+o{IZ1$aR9Fo76fyS zc|lxTWHDQi{Xv)oE)r}o>+8K?;R}od;%CBJCP=6#i9DP{#yyyzu)Kl1!Oq0Dfi;6@ z$MzvHphqB0SQh_HJVh9YcvZoI*jq4#0M5}rF*Kl%NLMf~z*T4sO~8U!7Xa(yJ{kw} zVVnNMm*8}Q`PVIj`v`g@n}h6>#|r=y7eR%v13&?I46}t&cub6a)F6*xprR{63W}@? zk%DLs+nRv5^@S0TCh$Qn)B^`T7AM7iwgrm_h?4Bw#|Cg4#YivsMOYS}>+0n9`rEp- zpM9=-T(`Dv5R-vc*1+~>ucVnZU1UGt9~sK}2e%1P>pn;c^7mtRr2RED>%URPNP#aw z5o|74hX9kr;3J)`M}hlfI^e6sbga=annH_YfM^MFADb495YrEqIU$d9MQ&lJWRB1- z%Hs=`9vWdy$(lCwfpuG7U=b3{BbFHf?id~ElsH2%S%ePa?1aw3-JcK{79X6YctDth z7#MJh;FS)@j9Ax)ivYf4_-%<9}=4u z$pUy)2%;b41tXvf{uY5xqD7d%Z3d*GTK;^2gaphVcppu(JkkOZys`xOmXcrwbKgO7 z@!CxTxI#~q@RD^IIjpHA$YG_CRW*x% z(M05SL5AX`Dz^^_7u#Wmw{k@O%_=}Q{bqN7myh867~T&dE0 zn-Yc`pXYejh-tFLh8nrEX*9R+&KpVqu7LiyjB{#Yg;Kq#x&HllHc9#ZfFUoDfHWNY zdT*u2e61v;`Dli-Pz*&=w2T)ZSk~3l;wPyuRGY{}9?c)zoT2b)8-bUw^4~pm;AR0= zY~y_ycnA<6Fp!~0*|5!vnJv!prCw^mDKZUa3tI$$rv;8U9_M3A@|>Aj?;r`si>4Fb zcAy;)d4@nsuHktK{aC08s)EQc@(?VUh8Q869`F7!9M6G@ax%n=VA7&0 zbPC=Wp+tB$g^l;CKo-IF1D=L3N0tpQK#j?k6g!HMnur?2#M48BDv%5~mzSW8psJGu zg33x$NIUq^umM07(jGZZcHm?KR6!<4iq{C?1AZ2GM38JE0h`150ylGxy^z}}*-r_S zHlP9sLpTd84_nI2V2{Qr)GLH3r~o)x`(PA>_#lA}-~r6wx`G}zk@b_U!xA7L`w_H* z7`*)jW6B{6VC&ju3TqT#55Zc|E#h$_+6LMknfVX4%7F7M5kW&rz2;08_Fh~0fZFBuGuM&XnzUQ7bn zz|-}HymFI6D`}+_L!gq;)ScQ=ruLb7#|U!&G+}E(Pf_T6I6%6CdateeY5Z^|cQfR^Aas1cocbDGkb;y9eHB{Xfz8!(-?>k%fuEC`y=jDV+np zggY>IGr&vW8V6}czKfF<_BxKjF@5Z04jL^*#?c~-qma0h;TQ!(5MXJ6S2YRm1H+cp z2@=C?I35t!&4`N?AQg!@#5f_yC$}MI5p5$sF6`zH#_K#On)!_XL+h0(+y^9KeuQWI@#lqg2dnjRo+ z(c&^u;S@$8S&y)C5J3dsUcyLUX)E}ER$`)=u)JZZYiNOkpoLeNc%c0pSsQU;`tT}b zwh~LZ0O_MzG9(Gi8X^re*GXV2<#?4EfWD^6h%>COn(KOs#5+xk z5lhGsk<4I^06AbafSqB8!$$%niYD*{bx4>6`W>Q^_zjV#h_NDT9j9NS2rno?o+hys ziG-CExJ}@NO2RmCa@<+R0f3!M6(MRFAs9bdWVVF}!5V+Tq{AEPkZPwJi{%o>yaags zAyKp}jDg#g*))VZ1tMEj5wS{Ag<<2L;wfx3?#NL0yM}M zg>4{Vmc%}#q&@&MM`d}AG`Bdxn|Fc`?0{Pu-|4V2loQ^zh6G6jbz-ChL~#FLz&R3suoDea z6ljV?YAmr?Ok}pg!Gf3HdCS$>Rs#@#i-zo5L|fsDHDISB4H;oH*4yi?OyXmsZLFv$vtnzrV8<;uq7U;|K0^6h& zTBO>MnIXQ7>FlC$` zN;Mv@y0T18RI$NxScwLNrEW)Yw7T{jz9wU=kY-T|dzEvr-Js!daEl!vRXB0{2gecW z$aID!l1yU*hw2b9%WKq@$dm6 zW)46E!A-J~NWKmb*V=f)ViA*y7|1aGkwiow2-cd|J?kgLX+cm8d^8%29}*cPBE89P5wJ`gy@UWF z({T|Cnczn>NzCLlhk_#YK@X{mTkB%zfs`fIFE%~q03r2%+59ND?g_n-F3})9NJ&x< z>rWa(C*%$s0O%Qik`G+ull%!Ji{(wB8rM8Rx?T6Z?iTFS_g73!Z% z@Oq+AoK!_w!T@BFp#Lm%k2Qa61yhL5@CD% zCbPM2l5i6GKt!HwO#(mADk#K%6nrEV6HnU2ZX+v$QDtQO*fbbE8Uw-W7D=1y$;b4Q z?GCI6T5~ci=t>|DGAvS-3~ix5l51+hS8cA7_N z3KH=AkyyfWKdD7gLdAM;SbT5_#0%!&acc34^bQ&HI5M(9uocN9plp&81xCsc0q{7c z^>nRi_&EtMkC6n04S)+}ArH_cnNY$8k7Fa`5^4z_fVI{QV|q!mU_4ToupjA$)C0MX zO@qHk5(PH(dT^kTOxJqzfL!vGOxyax_;dqX0ERQDKuct+Vy}|I>v_ZQ*7etIlfn=x zkd8lFUi0dDP-HHCt~5IPId_nc7~j7qgSfBIJK;h!OW634C_**a`cEp>B%>iPB>)sCLu+_WARg=$ObDTSef?Y-@{rtxSi@k* zi0~AoVqmzvCVukwV?$ +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +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 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/email/test/data/msg_02.txt b/Lib/email/test/data/msg_02.txt new file mode 100644 index 00000000000..43f248038a8 --- /dev/null +++ b/Lib/email/test/data/msg_02.txt @@ -0,0 +1,135 @@ +MIME-version: 1.0 +From: ppp-request@zzz.org +Sender: ppp-admin@zzz.org +To: ppp@zzz.org +Subject: Ppp digest, Vol 1 #2 - 5 msgs +Date: Fri, 20 Apr 2001 20:18:00 -0400 (EDT) +X-Mailer: Mailman v2.0.4 +X-Mailman-Version: 2.0.4 +Content-Type: multipart/mixed; boundary="192.168.1.2.889.32614.987812255.500.21814" + +--192.168.1.2.889.32614.987812255.500.21814 +Content-type: text/plain; charset=us-ascii +Content-description: Masthead (Ppp digest, Vol 1 #2) + +Send Ppp mailing list submissions to + ppp@zzz.org + +To subscribe or unsubscribe via the World Wide Web, visit + http://www.zzz.org/mailman/listinfo/ppp +or, via email, send a message with subject or body 'help' to + ppp-request@zzz.org + +You can reach the person managing the list at + ppp-admin@zzz.org + +When replying, please edit your Subject line so it is more specific +than "Re: Contents of Ppp digest..." + + +--192.168.1.2.889.32614.987812255.500.21814 +Content-type: text/plain; charset=us-ascii +Content-description: Today's Topics (5 msgs) + +Today's Topics: + + 1. testing #1 (Barry A. Warsaw) + 2. testing #2 (Barry A. Warsaw) + 3. testing #3 (Barry A. Warsaw) + 4. testing #4 (Barry A. Warsaw) + 5. testing #5 (Barry A. Warsaw) + +--192.168.1.2.889.32614.987812255.500.21814 +Content-Type: multipart/digest; boundary="__--__--" + +--__--__-- + +Message: 1 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Date: Fri, 20 Apr 2001 20:16:13 -0400 +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #1 +Precedence: bulk + + +hello + + +--__--__-- + +Message: 2 +Date: Fri, 20 Apr 2001 20:16:21 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Precedence: bulk + + +hello + + +--__--__-- + +Message: 3 +Date: Fri, 20 Apr 2001 20:16:25 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #3 +Precedence: bulk + + +hello + + +--__--__-- + +Message: 4 +Date: Fri, 20 Apr 2001 20:16:28 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #4 +Precedence: bulk + + +hello + + +--__--__-- + +Message: 5 +Date: Fri, 20 Apr 2001 20:16:32 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #5 +Precedence: bulk + + +hello + + + + +--__--__---- +--192.168.1.2.889.32614.987812255.500.21814 +Content-type: text/plain; charset=us-ascii +Content-description: Digest Footer + +_______________________________________________ +Ppp mailing list +Ppp@zzz.org +http://www.zzz.org/mailman/listinfo/ppp + + +--192.168.1.2.889.32614.987812255.500.21814-- + +End of Ppp Digest + diff --git a/Lib/email/test/data/msg_03.txt b/Lib/email/test/data/msg_03.txt new file mode 100644 index 00000000000..c748ebf1176 --- /dev/null +++ b/Lib/email/test/data/msg_03.txt @@ -0,0 +1,16 @@ +Return-Path: +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +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 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/email/test/data/msg_04.txt b/Lib/email/test/data/msg_04.txt new file mode 100644 index 00000000000..1f633c4496f --- /dev/null +++ b/Lib/email/test/data/msg_04.txt @@ -0,0 +1,37 @@ +Return-Path: +Delivered-To: barry@python.org +Received: by mail.python.org (Postfix, from userid 889) + id C2BF0D37C6; Tue, 11 Sep 2001 00:05:05 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="h90VIIIKmx" +Content-Transfer-Encoding: 7bit +Message-ID: <15261.36209.358846.118674@anthem.python.org> +From: barry@python.org (Barry A. Warsaw) +To: barry@python.org +Subject: a simple multipart +Date: Tue, 11 Sep 2001 00:05:05 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Make a door into a window + + +--h90VIIIKmx +Content-Type: text/plain +Content-Disposition: inline; + filename="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx +Content-Type: text/plain +Content-Disposition: inline; + filename="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx-- + diff --git a/Lib/email/test/data/msg_05.txt b/Lib/email/test/data/msg_05.txt new file mode 100644 index 00000000000..87d5e9cbf8b --- /dev/null +++ b/Lib/email/test/data/msg_05.txt @@ -0,0 +1,28 @@ +From: foo +Subject: bar +To: baz +MIME-Version: 1.0 +Content-Type: multipart/report; report-type=delivery-status; + boundary="D1690A7AC1.996856090/mail.example.com" +Message-Id: <20010803162810.0CA8AA7ACC@mail.example.com> + +This is a MIME-encapsulated message. + +--D1690A7AC1.996856090/mail.example.com +Content-Type: text/plain + +Yadda yadda yadda + +--D1690A7AC1.996856090/mail.example.com + +Yadda yadda yadda + +--D1690A7AC1.996856090/mail.example.com +Content-Type: message/rfc822 + +From: nobody@python.org + +Yadda yadda yadda + +--D1690A7AC1.996856090/mail.example.com-- + diff --git a/Lib/email/test/data/msg_06.txt b/Lib/email/test/data/msg_06.txt new file mode 100644 index 00000000000..69f3a47ff42 --- /dev/null +++ b/Lib/email/test/data/msg_06.txt @@ -0,0 +1,33 @@ +Return-Path: +Delivered-To: barry@python.org +MIME-Version: 1.0 +Content-Type: message/rfc822 +Content-Description: forwarded message +Content-Transfer-Encoding: 7bit +Message-ID: <15265.9482.641338.555352@python.org> +From: barry@zope.com (Barry A. Warsaw) +Sender: barry@python.org +To: barry@python.org +Subject: forwarded message from Barry A. Warsaw +Date: Thu, 13 Sep 2001 17:28:42 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Be dirty +X-Url: http://barry.wooz.org + +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Return-Path: +Delivered-To: barry@python.org +Message-ID: <15265.9468.713530.98441@python.org> +From: barry@zope.com (Barry A. Warsaw) +Sender: barry@python.org +To: barry@python.org +Subject: testing +Date: Thu, 13 Sep 2001 17:28:28 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Spectrum analysis +X-Url: http://barry.wooz.org + + diff --git a/Lib/email/test/data/msg_07.txt b/Lib/email/test/data/msg_07.txt new file mode 100644 index 00000000000..721f3a0d316 --- /dev/null +++ b/Lib/email/test/data/msg_07.txt @@ -0,0 +1,83 @@ +MIME-Version: 1.0 +From: Barry +To: Dingus Lovers +Subject: Here is your dingus fish +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + +Hi there, + +This is the dingus fish. + +--BOUNDARY +Content-Type: image/gif; name="dingusfish.gif" +Content-Transfer-Encoding: base64 +content-disposition: attachment; filename="dingusfish.gif" + +R0lGODdhAAEAAfAAAP///wAAACwAAAAAAAEAAQAC/oSPqcvtD6OctNqLs968+w+G4kiW5omm6sq2 +7gvH8kzX9o3n+s73/g8MCofEovGITGICTKbyCV0FDNOo9SqpQqpOrJfXzTQj2vD3TGtqL+NtGQ2f +qTXmxzuOd7WXdcc9DyjU53ewFni4s0fGhdiYaEhGBelICTNoV1j5NUnFcrmUqemjNifJVWpaOqaI +oFq3SspZsSraE7sHq3jr1MZqWvi662vxV4tD+pvKW6aLDOCLyur8PDwbanyDeq0N3DctbQYeLDvR +RY6t95m6UB0d3mwIrV7e2VGNvjjffukeJp4w7F65KecGFsTHQGAygOrgrWs1jt28Rc88KESYcGLA +/obvTkH6p+CinWJiJmIMqXGQwH/y4qk0SYjgQTczT3ajKZGfuI0uJ4kkVI/DT5s3/ejkxI0aT4Y+ +YTYgWbImUaXk9nlLmnSh1qJiJFl0OpUqRK4oOy7NyRQtHWofhoYVxkwWXKUSn0YsS+fUV6lhqfYb +6ayd3Z5qQdG1B7bvQzaJjwUV2lixMUZ7JVsOlfjWVr/3NB/uFvnySBN6Dcb6rGwaRM3wsormw5cC +M9NxWy/bWdufudCvy8bOAjXjVVwta/uO21sE5RHBCzNFXtgq9ORtH4eYjVP4Yryo026nvkFmCeyA +B29efV6ravCMK5JwWd5897Qrx7ll38o6iHDZ/rXPR//feevhF4l7wjUGX3xq1eeRfM4RSJGBIV1D +z1gKPkfWag3mVBVvva1RlX5bAJTPR/2YqNtw/FkIYYEi/pIZiAdpcxpoHtmnYYoZtvhUftzdx5ZX +JSKDW405zkGcZzzGZ6KEv4FI224oDmijlEf+xp6MJK5ojY/ASeVUR+wsKRuJ+XFZ5o7ZeEime8t1 +ouUsU6YjF5ZtUihhkGfCdFQLWQFJ3UXxmElfhQnR+eCdcDbkFZp6vTRmj56ApCihn5QGpaToNZmR +n3NVSpZcQpZ2KEONusaiCsKAug0wkQbJSFO+PTSjneGxOuFjPlUk3ovWvdIerjUg9ZGIOtGq/qeX +eCYrrCX+1UPsgTKGGRSbzd5q156d/gpfbJxe66eD5iQKrXj7RGgruGxs62qebBHUKS32CKluCiqZ +qh+pmehmEb71noAUoe5e9Zm17S7773V10pjrtG4CmuurCV/n6zLK5turWNhqOvFXbjhZrMD0YhKe +wR0zOyuvsh6MWrGoIuzvyWu5y1WIFAqmJselypxXh6dKLNOKEB98L88bS2rkNqqlKzCNJp9c0G0j +Gzh0iRrCbHSXmPR643QS+4rWhgFmnSbSuXCjS0xAOWkU2UdLqyuUNfHSFdUouy3bm5i5GnDM3tG8 +doJ4r5tqu3pPbRSVfvs8uJzeNXhp3n4j/tZ42SwH7eaWUUOjc3qFV9453UHTXZfcLH+OeNs5g36x +lBnHvTm7EbMbLeuaLncao8vWCXimfo1o+843Ak6y4ChNeGntvAYvfLK4ezmoyNIbNCLTCXO9ZV3A +E8/s88RczPzDwI4Ob7XZyl7+9Miban29h+tJZPrE21wgvBphDfrrfPdCTPKJD/y98L1rZwHcV6Jq +Zab0metpuNIX/qAFPoz171WUaUb4HAhBSzHuHfjzHb3kha/2Cctis/ORArVHNYfFyYRH2pYIRzic +isVOfPWD1b6mRTqpCRBozzof6UZVvFXRxWIr3GGrEviGYgyPMfahheiSaLs/9QeFu7oZ/ndSY8DD +ya9x+uPed+7mxN2IzIISBOMLFYWVqC3Pew1T2nFuuCiwZS5/v6II10i4t1OJcUH2U9zxKodHsGGv +Oa+zkvNUYUOa/TCCRutF9MzDwdlUMJADTCGSbDQ5OV4PTamDoPEi6Ecc/RF5RWwkcdSXvSOaDWSn +I9LlvubFTQpuc6JKXLcKeb+xdbKRBnwREemXyjg6ME65aJiOuBgrktzykfPLJBKR9ClMavJ62/Ff +BlNIyod9yX9wcSXexnXFpvkrbXk64xsx5Db7wXKP5fSgsvwIMM/9631VLBfkmtbHRXpqmtei52hG +pUwSlo+BASQoeILDOBgREECxBBh5/iYmNsQ9dIv5+OI++QkqdsJPc3uykz5fkM+OraeekcQF7X4n +B5S67za5U967PmooGQhUXfF7afXyCD7ONdRe17QogYjVx38uLwtrS6nhTnm15LQUnu9E2uK6CNI/ +1HOABj0ESwOjut4FEpFQpdNAm4K2LHnDWHNcmKB2ioKBogysVZtMO2nSxUdZ8Yk2kJc7URioLVI0 +YgmtIwZj4LoeKemgnOnbUdGnzZ4Oa6scqiolBGqS6RgWNLu0RMhcaE6rhhU4hiuqFXPAG8fGwTPW +FKeLMtdVmXLSs5YJGF/YeVm7rREMlY3UYE+yCxbaMXX8y15m5zVHq6GOKDMynzII/jdUHdyVqIy0 +ifX2+r/EgtZcvRzSb72gU9ui87M2VecjKildW/aFqaYhKoryUjfB/g4qtyVuc60xFDGmCxwjW+qu +zjuwl2GkOWn66+3QiiEctvd04OVvcCVzjgT7lrkvjVGKKHmmlDUKowSeikb5kK/mJReuWOxONx+s +ULsl+Lqb0CVn0SrVyJ6wt4t6yTeSCafhPhAf0OXn6L60UMxiLolFAtmN35S2Ob1lZpQ1r/n0Qb5D +oQ1zJiRVDgF8N3Q8TYfbi3DyWCy3lT1nxyBs6FT3S2GOzWRlxwKvlRP0RPJA9SjxEy0UoEnkA+M4 +cnzLMJrBGWLFEaaUb5lvpqbq/loOaU5+DFuHPxo82/OZuM8FXG3oVNZhtWpMpb/0Xu5m/LfLhHZQ +7yuVI0MqZ7NE43imC8jH3IwGZlbPm0xkJYs7+2U48hXTsFSMqgGDvai0kLxyynKNT/waj+q1c1tz +GjOpPBgdCSq3UKZxCSsqFIY+O6JbAWGWcV1pwqLyj5sGqCF1xb1F3varUWqrJv6cN3PrUXzijtfZ +FshpBL3Xwr4GIPvU2N8EjrJgS1zl21rbXQMXeXc5jjFyrhpCzijSv/RQtyPSzHCFMhlME95fHglt +pRsX+dfSQjUeHAlpWzJ5iOo79Ldnaxai6bXTcGO3fp07ri7HLEmXXPlYi8bv/qVxvNcdra6m7Rlb +6JBTb5fd66VhFRjGArh2n7R1rDW4P5NOT9K0I183T2scYkeZ3q/VFyLb09U9ajzXBS8Kgkhc4mBS +kYY9cy3Vy9lUnuNJH8HGIclUilwnBtjUOH0gteGOZ4c/XNrhXLSYDyxfnD8z1pDy7rYRvDolhnbe +UMzxCZUs40s6s7UIvBnLgc0+vKuOkIXeOrDymlp+Zxra4MZLBbVrqD/jTJ597pDmnw5c4+DbyB88 +9Cg9DodYcSuMZT/114pptqc/EuTjRPvH/z5slzI3tluOEBBLqOXLOX+0I5929tO97wkvl/atCz+y +xJrdwteW2FNW/NSmBP+f/maYtVs/bYyBC7Ox3jsYZHL05CIrBa/nS+b3bHfiYm4Ueil1YZZSgAUI +fFZ1dxUmeA2oQRQ3RuGXNGLFV9/XbGFGPV6kfzk1TBBCd+izc7q1H+OHMJwmaBX2IQNYVAKHYepV +SSGCe6CnbYHHETKGNe43EDvFgZr0gB/nVHPHZ80VV1ojOiI3XDvYIkl4ayo4bxQIgrFXWTvBI0nH +VElWMuw2aLUWCRHHf8ymVCHjFlJnOSojfevCYyyyZDH0IcvHhrsnQ5O1OsWzONuVVKIxSxiFZ/tR +fKDAf6xFTnw4O9Qig2VCfW2hJQrmMOuHW0W3dLQmCMO2ccdUd/xyfflH/olTiHZVdGwb8nIwRzSE +J15jFlOJuBZBZ4CiyHyd2IFylFlB+HgHhYabhWOGwYO1ZH/Og1dtQlFMk352CGRSIFTapnWQEUtN +l4zv8S0aaCFDyGCBqDUxZYpxGHX01y/JuH1xhn7TOCnNCI4eKDs5WGX4R425F4vF1o3BJ4vO0otq +I3rimI7jJY1jISqnBxknCIvruF83mF5wN4X7qGLIhR8A2Vg0yFERSIXn9Vv3GHy3Vj/WIkKddlYi +yIMv2I/VMjTLpW7pt05SWIZR0RPyxpB4SIUM9lBPGBl0GC7oSEEwRYLe4pJpZY2P0zbI1n+Oc44w +qY3PUnmF0ixjVpDD/mJ9wpOBGTVgXlaCaZiPcIWK5NiKBIiPdGaQ0TWGvAiG7nMchdZb7Vgf8zNi +MuMyzRdy/lePe9iC4TRx7WhhOQI/QiSVNAmAa2lT/piFbuh7ofJoYSZzrSZ1bvmWw3eN2nKUPVky +uPN5/VRfohRd0VYZoqhKIlU6TXYhJxmPUIloAwc1bPmHEpaZYZORHNlXUJM07hATwHR8MJYqkwWR +WaIezFhxSFlc8/Fq82hEnpeRozg3ULhhr9lAGtVEkCg5ZNRuuVleBPaZadhG0ZgkyPmDOTOKzViM +YgOcpukKqQcbjAWS0IleQ2ROjdh6A+md1qWdBRSX7iSYgFRTtRmBpJioieXJiHfJiMGIR9fJOn8I +MSfXYhspn4ooSa2mSAj4n+8Bmg03fBJZoPOJgsVZRxu1oOMRPXYYjdqjihFaEoZpXBREanuJoRI6 +cibFinq4ngUKh/wQd/H5ofYCZ0HJXR62opZFaAT0iFIZo4DIiUojkjeqKiuoZirKo5Y1a7AWckGa +BkuYoD5lpDK6eUs6CkDqpETwl1EqpfhJpVeKpVl6EgUAADs= + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_08.txt b/Lib/email/test/data/msg_08.txt new file mode 100644 index 00000000000..b5630836c54 --- /dev/null +++ b/Lib/email/test/data/msg_08.txt @@ -0,0 +1,24 @@ +MIME-Version: 1.0 +From: Barry Warsaw +To: Dingus Lovers +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-2" + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_09.txt b/Lib/email/test/data/msg_09.txt new file mode 100644 index 00000000000..575c4c205a1 --- /dev/null +++ b/Lib/email/test/data/msg_09.txt @@ -0,0 +1,24 @@ +MIME-Version: 1.0 +From: Barry Warsaw +To: Dingus Lovers +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: text/plain + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_10.txt b/Lib/email/test/data/msg_10.txt new file mode 100644 index 00000000000..bd30d13ad1a --- /dev/null +++ b/Lib/email/test/data/msg_10.txt @@ -0,0 +1,32 @@ +MIME-Version: 1.0 +From: Barry Warsaw +To: Dingus Lovers +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +Content-Transfer-Encoding: 7bit + +This is a 7bit encoded message. + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" +Content-Transfer-Encoding: Quoted-Printable + +=A1This is a Quoted Printable encoded message! + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-1" +Content-Transfer-Encoding: Base64 + +VGhpcyBpcyBhIEJhc2U2NCBlbmNvZGVkIG1lc3NhZ2Uu + + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-1" + +This has no Content-Transfer-Encoding: header. + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_11.txt b/Lib/email/test/data/msg_11.txt new file mode 100644 index 00000000000..8f7f1991cbd --- /dev/null +++ b/Lib/email/test/data/msg_11.txt @@ -0,0 +1,7 @@ +Content-Type: message/rfc822 +MIME-Version: 1.0 +Subject: The enclosing message + +Subject: An enclosed message + +Here is the body of the message. diff --git a/Lib/email/test/data/msg_12.txt b/Lib/email/test/data/msg_12.txt new file mode 100644 index 00000000000..4bec8d94449 --- /dev/null +++ b/Lib/email/test/data/msg_12.txt @@ -0,0 +1,36 @@ +MIME-Version: 1.0 +From: Barry Warsaw +To: Dingus Lovers +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: multipart/mixed; boundary="ANOTHER" + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-2" + + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-3" + +--ANOTHER-- + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_12a.txt b/Lib/email/test/data/msg_12a.txt new file mode 100644 index 00000000000..e94224ecfe5 --- /dev/null +++ b/Lib/email/test/data/msg_12a.txt @@ -0,0 +1,38 @@ +MIME-Version: 1.0 +From: Barry Warsaw +To: Dingus Lovers +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: multipart/mixed; boundary="ANOTHER" + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-2" + + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-3" + + +--ANOTHER-- + + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_13.txt b/Lib/email/test/data/msg_13.txt new file mode 100644 index 00000000000..8e6d52d5bef --- /dev/null +++ b/Lib/email/test/data/msg_13.txt @@ -0,0 +1,94 @@ +MIME-Version: 1.0 +From: Barry +To: Dingus Lovers +Subject: Here is your dingus fish +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="OUTER" + +--OUTER +Content-Type: text/plain; charset="us-ascii" + +A text/plain part + +--OUTER +Content-Type: multipart/mixed; boundary=BOUNDARY + + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + +Hi there, + +This is the dingus fish. + +--BOUNDARY +Content-Type: image/gif; name="dingusfish.gif" +Content-Transfer-Encoding: base64 +content-disposition: attachment; filename="dingusfish.gif" + +R0lGODdhAAEAAfAAAP///wAAACwAAAAAAAEAAQAC/oSPqcvtD6OctNqLs968+w+G4kiW5omm6sq2 +7gvH8kzX9o3n+s73/g8MCofEovGITGICTKbyCV0FDNOo9SqpQqpOrJfXzTQj2vD3TGtqL+NtGQ2f +qTXmxzuOd7WXdcc9DyjU53ewFni4s0fGhdiYaEhGBelICTNoV1j5NUnFcrmUqemjNifJVWpaOqaI +oFq3SspZsSraE7sHq3jr1MZqWvi662vxV4tD+pvKW6aLDOCLyur8PDwbanyDeq0N3DctbQYeLDvR +RY6t95m6UB0d3mwIrV7e2VGNvjjffukeJp4w7F65KecGFsTHQGAygOrgrWs1jt28Rc88KESYcGLA +/obvTkH6p+CinWJiJmIMqXGQwH/y4qk0SYjgQTczT3ajKZGfuI0uJ4kkVI/DT5s3/ejkxI0aT4Y+ +YTYgWbImUaXk9nlLmnSh1qJiJFl0OpUqRK4oOy7NyRQtHWofhoYVxkwWXKUSn0YsS+fUV6lhqfYb +6ayd3Z5qQdG1B7bvQzaJjwUV2lixMUZ7JVsOlfjWVr/3NB/uFvnySBN6Dcb6rGwaRM3wsormw5cC +M9NxWy/bWdufudCvy8bOAjXjVVwta/uO21sE5RHBCzNFXtgq9ORtH4eYjVP4Yryo026nvkFmCeyA +B29efV6ravCMK5JwWd5897Qrx7ll38o6iHDZ/rXPR//feevhF4l7wjUGX3xq1eeRfM4RSJGBIV1D +z1gKPkfWag3mVBVvva1RlX5bAJTPR/2YqNtw/FkIYYEi/pIZiAdpcxpoHtmnYYoZtvhUftzdx5ZX +JSKDW405zkGcZzzGZ6KEv4FI224oDmijlEf+xp6MJK5ojY/ASeVUR+wsKRuJ+XFZ5o7ZeEime8t1 +ouUsU6YjF5ZtUihhkGfCdFQLWQFJ3UXxmElfhQnR+eCdcDbkFZp6vTRmj56ApCihn5QGpaToNZmR +n3NVSpZcQpZ2KEONusaiCsKAug0wkQbJSFO+PTSjneGxOuFjPlUk3ovWvdIerjUg9ZGIOtGq/qeX +eCYrrCX+1UPsgTKGGRSbzd5q156d/gpfbJxe66eD5iQKrXj7RGgruGxs62qebBHUKS32CKluCiqZ +qh+pmehmEb71noAUoe5e9Zm17S7773V10pjrtG4CmuurCV/n6zLK5turWNhqOvFXbjhZrMD0YhKe +wR0zOyuvsh6MWrGoIuzvyWu5y1WIFAqmJselypxXh6dKLNOKEB98L88bS2rkNqqlKzCNJp9c0G0j +Gzh0iRrCbHSXmPR643QS+4rWhgFmnSbSuXCjS0xAOWkU2UdLqyuUNfHSFdUouy3bm5i5GnDM3tG8 +doJ4r5tqu3pPbRSVfvs8uJzeNXhp3n4j/tZ42SwH7eaWUUOjc3qFV9453UHTXZfcLH+OeNs5g36x +lBnHvTm7EbMbLeuaLncao8vWCXimfo1o+843Ak6y4ChNeGntvAYvfLK4ezmoyNIbNCLTCXO9ZV3A +E8/s88RczPzDwI4Ob7XZyl7+9Miban29h+tJZPrE21wgvBphDfrrfPdCTPKJD/y98L1rZwHcV6Jq +Zab0metpuNIX/qAFPoz171WUaUb4HAhBSzHuHfjzHb3kha/2Cctis/ORArVHNYfFyYRH2pYIRzic +isVOfPWD1b6mRTqpCRBozzof6UZVvFXRxWIr3GGrEviGYgyPMfahheiSaLs/9QeFu7oZ/ndSY8DD +ya9x+uPed+7mxN2IzIISBOMLFYWVqC3Pew1T2nFuuCiwZS5/v6II10i4t1OJcUH2U9zxKodHsGGv +Oa+zkvNUYUOa/TCCRutF9MzDwdlUMJADTCGSbDQ5OV4PTamDoPEi6Ecc/RF5RWwkcdSXvSOaDWSn +I9LlvubFTQpuc6JKXLcKeb+xdbKRBnwREemXyjg6ME65aJiOuBgrktzykfPLJBKR9ClMavJ62/Ff +BlNIyod9yX9wcSXexnXFpvkrbXk64xsx5Db7wXKP5fSgsvwIMM/9631VLBfkmtbHRXpqmtei52hG +pUwSlo+BASQoeILDOBgREECxBBh5/iYmNsQ9dIv5+OI++QkqdsJPc3uykz5fkM+OraeekcQF7X4n +B5S67za5U967PmooGQhUXfF7afXyCD7ONdRe17QogYjVx38uLwtrS6nhTnm15LQUnu9E2uK6CNI/ +1HOABj0ESwOjut4FEpFQpdNAm4K2LHnDWHNcmKB2ioKBogysVZtMO2nSxUdZ8Yk2kJc7URioLVI0 +YgmtIwZj4LoeKemgnOnbUdGnzZ4Oa6scqiolBGqS6RgWNLu0RMhcaE6rhhU4hiuqFXPAG8fGwTPW +FKeLMtdVmXLSs5YJGF/YeVm7rREMlY3UYE+yCxbaMXX8y15m5zVHq6GOKDMynzII/jdUHdyVqIy0 +ifX2+r/EgtZcvRzSb72gU9ui87M2VecjKildW/aFqaYhKoryUjfB/g4qtyVuc60xFDGmCxwjW+qu +zjuwl2GkOWn66+3QiiEctvd04OVvcCVzjgT7lrkvjVGKKHmmlDUKowSeikb5kK/mJReuWOxONx+s +ULsl+Lqb0CVn0SrVyJ6wt4t6yTeSCafhPhAf0OXn6L60UMxiLolFAtmN35S2Ob1lZpQ1r/n0Qb5D +oQ1zJiRVDgF8N3Q8TYfbi3DyWCy3lT1nxyBs6FT3S2GOzWRlxwKvlRP0RPJA9SjxEy0UoEnkA+M4 +cnzLMJrBGWLFEaaUb5lvpqbq/loOaU5+DFuHPxo82/OZuM8FXG3oVNZhtWpMpb/0Xu5m/LfLhHZQ +7yuVI0MqZ7NE43imC8jH3IwGZlbPm0xkJYs7+2U48hXTsFSMqgGDvai0kLxyynKNT/waj+q1c1tz +GjOpPBgdCSq3UKZxCSsqFIY+O6JbAWGWcV1pwqLyj5sGqCF1xb1F3varUWqrJv6cN3PrUXzijtfZ +FshpBL3Xwr4GIPvU2N8EjrJgS1zl21rbXQMXeXc5jjFyrhpCzijSv/RQtyPSzHCFMhlME95fHglt +pRsX+dfSQjUeHAlpWzJ5iOo79Ldnaxai6bXTcGO3fp07ri7HLEmXXPlYi8bv/qVxvNcdra6m7Rlb +6JBTb5fd66VhFRjGArh2n7R1rDW4P5NOT9K0I183T2scYkeZ3q/VFyLb09U9ajzXBS8Kgkhc4mBS +kYY9cy3Vy9lUnuNJH8HGIclUilwnBtjUOH0gteGOZ4c/XNrhXLSYDyxfnD8z1pDy7rYRvDolhnbe +UMzxCZUs40s6s7UIvBnLgc0+vKuOkIXeOrDymlp+Zxra4MZLBbVrqD/jTJ597pDmnw5c4+DbyB88 +9Cg9DodYcSuMZT/114pptqc/EuTjRPvH/z5slzI3tluOEBBLqOXLOX+0I5929tO97wkvl/atCz+y +xJrdwteW2FNW/NSmBP+f/maYtVs/bYyBC7Ox3jsYZHL05CIrBa/nS+b3bHfiYm4Ueil1YZZSgAUI +fFZ1dxUmeA2oQRQ3RuGXNGLFV9/XbGFGPV6kfzk1TBBCd+izc7q1H+OHMJwmaBX2IQNYVAKHYepV +SSGCe6CnbYHHETKGNe43EDvFgZr0gB/nVHPHZ80VV1ojOiI3XDvYIkl4ayo4bxQIgrFXWTvBI0nH +VElWMuw2aLUWCRHHf8ymVCHjFlJnOSojfevCYyyyZDH0IcvHhrsnQ5O1OsWzONuVVKIxSxiFZ/tR +fKDAf6xFTnw4O9Qig2VCfW2hJQrmMOuHW0W3dLQmCMO2ccdUd/xyfflH/olTiHZVdGwb8nIwRzSE +J15jFlOJuBZBZ4CiyHyd2IFylFlB+HgHhYabhWOGwYO1ZH/Og1dtQlFMk352CGRSIFTapnWQEUtN +l4zv8S0aaCFDyGCBqDUxZYpxGHX01y/JuH1xhn7TOCnNCI4eKDs5WGX4R425F4vF1o3BJ4vO0otq +I3rimI7jJY1jISqnBxknCIvruF83mF5wN4X7qGLIhR8A2Vg0yFERSIXn9Vv3GHy3Vj/WIkKddlYi +yIMv2I/VMjTLpW7pt05SWIZR0RPyxpB4SIUM9lBPGBl0GC7oSEEwRYLe4pJpZY2P0zbI1n+Oc44w +qY3PUnmF0ixjVpDD/mJ9wpOBGTVgXlaCaZiPcIWK5NiKBIiPdGaQ0TWGvAiG7nMchdZb7Vgf8zNi +MuMyzRdy/lePe9iC4TRx7WhhOQI/QiSVNAmAa2lT/piFbuh7ofJoYSZzrSZ1bvmWw3eN2nKUPVky +uPN5/VRfohRd0VYZoqhKIlU6TXYhJxmPUIloAwc1bPmHEpaZYZORHNlXUJM07hATwHR8MJYqkwWR +WaIezFhxSFlc8/Fq82hEnpeRozg3ULhhr9lAGtVEkCg5ZNRuuVleBPaZadhG0ZgkyPmDOTOKzViM +YgOcpukKqQcbjAWS0IleQ2ROjdh6A+md1qWdBRSX7iSYgFRTtRmBpJioieXJiHfJiMGIR9fJOn8I +MSfXYhspn4ooSa2mSAj4n+8Bmg03fBJZoPOJgsVZRxu1oOMRPXYYjdqjihFaEoZpXBREanuJoRI6 +cibFinq4ngUKh/wQd/H5ofYCZ0HJXR62opZFaAT0iFIZo4DIiUojkjeqKiuoZirKo5Y1a7AWckGa +BkuYoD5lpDK6eUs6CkDqpETwl1EqpfhJpVeKpVl6EgUAADs= + +--BOUNDARY-- + +--OUTER-- diff --git a/Lib/email/test/data/msg_14.txt b/Lib/email/test/data/msg_14.txt new file mode 100644 index 00000000000..5d98d2fd145 --- /dev/null +++ b/Lib/email/test/data/msg_14.txt @@ -0,0 +1,23 @@ +Return-Path: +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text; charset=us-ascii +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 + + +Hi, + +I'm sorry but I'm using a drainbread ISP, which although big and +wealthy can't seem to generate standard compliant email. :( + +This message has a Content-Type: header with no subtype. I hope you +can still read it. + +-Me diff --git a/Lib/email/test/data/msg_15.txt b/Lib/email/test/data/msg_15.txt new file mode 100644 index 00000000000..33b8487aaf5 --- /dev/null +++ b/Lib/email/test/data/msg_15.txt @@ -0,0 +1,52 @@ +Return-Path: +Received: from fepD.post.tele.dk (195.41.46.149) by mail.groupcare.dk (LSMTP for Windows NT v1.1b) with SMTP id <0.0014F8A2@mail.groupcare.dk>; Mon, 30 Apr 2001 12:17:50 +0200 +User-Agent: Microsoft-Outlook-Express-Macintosh-Edition/5.02.2106 +Subject: XX +From: xx@xx.dk +To: XX +Message-ID: +Mime-version: 1.0 +Content-type: multipart/mixed; + boundary="MS_Mac_OE_3071477847_720252_MIME_Part" + +> Denne meddelelse er i MIME-format. Da dit postl¾sningsprogram ikke forstŒr dette format, kan del af eller hele meddelelsen v¾re ul¾selig. + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: multipart/alternative; + boundary="MS_Mac_OE_3071477847_720252_MIME_Part" + + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: text/plain; charset="ISO-8859-1" +Content-transfer-encoding: quoted-printable + +Some removed test. + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: text/html; charset="ISO-8859-1" +Content-transfer-encoding: quoted-printable + + + +Some removed HTML + + +Some removed text. + + + + +--MS_Mac_OE_3071477847_720252_MIME_Part-- + + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: image/gif; name="xx.gif"; + x-mac-creator="6F676C65"; + x-mac-type="47494666" +Content-disposition: attachment +Content-transfer-encoding: base64 + +Some removed base64 encoded chars. + +--MS_Mac_OE_3071477847_720252_MIME_Part-- + diff --git a/Lib/email/test/data/msg_16.txt b/Lib/email/test/data/msg_16.txt new file mode 100644 index 00000000000..56167e9f5b4 --- /dev/null +++ b/Lib/email/test/data/msg_16.txt @@ -0,0 +1,123 @@ +Return-Path: <> +Delivered-To: scr-admin@socal-raves.org +Received: from cougar.noc.ucla.edu (cougar.noc.ucla.edu [169.232.10.18]) + by babylon.socal-raves.org (Postfix) with ESMTP id CCC2C51B84 + for ; Sun, 23 Sep 2001 20:13:54 -0700 (PDT) +Received: from sims-ms-daemon by cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + id <0GK500B01D0B8Y@cougar.noc.ucla.edu> for scr-admin@socal-raves.org; Sun, + 23 Sep 2001 20:14:35 -0700 (PDT) +Received: from cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + id <0GK500B01D0B8X@cougar.noc.ucla.edu>; Sun, 23 Sep 2001 20:14:35 -0700 (PDT) +Date: Sun, 23 Sep 2001 20:14:35 -0700 (PDT) +From: Internet Mail Delivery +Subject: Delivery Notification: Delivery has failed +To: scr-admin@socal-raves.org +Message-id: <0GK500B04D0B8X@cougar.noc.ucla.edu> +MIME-version: 1.0 +Sender: scr-owner@socal-raves.org +Errors-To: scr-owner@socal-raves.org +X-BeenThere: scr@socal-raves.org +X-Mailman-Version: 2.1a3 +Precedence: bulk +List-Help: +List-Post: +List-Subscribe: , + +List-Id: SoCal-Raves +List-Unsubscribe: , + +List-Archive: +Content-Type: multipart/report; boundary="Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA)" + + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA) +Content-type: text/plain; charset=ISO-8859-1 + +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 + + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA) +Content-type: message/DELIVERY-STATUS + +Original-envelope-id: 0GK500B4HD0888@cougar.noc.ucla.edu +Reporting-MTA: dns; cougar.noc.ucla.edu + +Action: failed +Status: 5.0.0 (recipient reached disk quota) +Original-recipient: rfc822;jangel1@cougar.noc.ucla.edu +Final-recipient: rfc822;jangel1@cougar.noc.ucla.edu + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA) +Content-type: MESSAGE/RFC822 + +Return-path: scr-admin@socal-raves.org +Received: from sims-ms-daemon by cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + id <0GK500B01D0B8X@cougar.noc.ucla.edu>; Sun, 23 Sep 2001 20:14:35 -0700 (PDT) +Received: from panther.noc.ucla.edu by cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + with ESMTP id <0GK500B4GD0888@cougar.noc.ucla.edu> for jangel1@sims-ms-daemon; + Sun, 23 Sep 2001 20:14:33 -0700 (PDT) +Received: from babylon.socal-raves.org + (ip-209-85-222-117.dreamhost.com [209.85.222.117]) + by panther.noc.ucla.edu (8.9.1a/8.9.1) with ESMTP id UAA09793 for + ; Sun, 23 Sep 2001 20:14:32 -0700 (PDT) +Received: from babylon (localhost [127.0.0.1]) by babylon.socal-raves.org + (Postfix) with ESMTP id D3B2951B70; Sun, 23 Sep 2001 20:13:47 -0700 (PDT) +Received: by babylon.socal-raves.org (Postfix, from userid 60001) + id A611F51B82; Sun, 23 Sep 2001 20:13:46 -0700 (PDT) +Received: from tiger.cc.oxy.edu (tiger.cc.oxy.edu [134.69.3.112]) + by babylon.socal-raves.org (Postfix) with ESMTP id ADA7351B70 for + ; Sun, 23 Sep 2001 20:13:44 -0700 (PDT) +Received: from ent (n16h86.dhcp.oxy.edu [134.69.16.86]) + by tiger.cc.oxy.edu (8.8.8/8.8.8) with SMTP id UAA08100 for + ; Sun, 23 Sep 2001 20:14:24 -0700 (PDT) +Date: Sun, 23 Sep 2001 20:10:55 -0700 +From: "Ian T. Henry" +Subject: [scr] yeah for Ians!! +Sender: scr-admin@socal-raves.org +To: SoCal Raves +Errors-to: scr-admin@socal-raves.org +Message-id: <002001c144a6$8752e060$56104586@oxy.edu> +MIME-version: 1.0 +X-Mailer: Microsoft Outlook Express 5.50.4522.1200 +Content-type: text/plain; charset=us-ascii +Precedence: bulk +Delivered-to: scr-post@babylon.socal-raves.org +Delivered-to: scr@socal-raves.org +X-Converted-To-Plain-Text: from multipart/alternative by demime 0.98e +X-Converted-To-Plain-Text: Alternative section used was text/plain +X-BeenThere: scr@socal-raves.org +X-Mailman-Version: 2.1a3 +List-Help: +List-Post: +List-Subscribe: , + +List-Id: SoCal-Raves +List-Unsubscribe: , + +List-Archive: + +I always love to find more Ian's that are over 3 years old!! + +Ian +_______________________________________________ +For event info, list questions, or to unsubscribe, see http://www.socal-raves.org/ + + + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA)-- + diff --git a/Lib/email/test/data/msg_17.txt b/Lib/email/test/data/msg_17.txt new file mode 100644 index 00000000000..8d86e4180dd --- /dev/null +++ b/Lib/email/test/data/msg_17.txt @@ -0,0 +1,12 @@ +MIME-Version: 1.0 +From: Barry +To: Dingus Lovers +Subject: Here is your dingus fish +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +Hi there, + +This is the dingus fish. + +[Non-text (image/gif) part of message omitted, filename dingusfish.gif] diff --git a/Lib/email/test/data/msg_18.txt b/Lib/email/test/data/msg_18.txt new file mode 100644 index 00000000000..f9f4904d366 --- /dev/null +++ b/Lib/email/test/data/msg_18.txt @@ -0,0 +1,6 @@ +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"; + spooge="yummy"; hippos="gargantuan"; marshmallows="gooey" + diff --git a/Lib/email/test/data/msg_19.txt b/Lib/email/test/data/msg_19.txt new file mode 100644 index 00000000000..49bf7fccdd9 --- /dev/null +++ b/Lib/email/test/data/msg_19.txt @@ -0,0 +1,43 @@ +Send Ppp mailing list submissions to + ppp@zzz.org + +To subscribe or unsubscribe via the World Wide Web, visit + http://www.zzz.org/mailman/listinfo/ppp +or, via email, send a message with subject or body 'help' to + ppp-request@zzz.org + +You can reach the person managing the list at + ppp-admin@zzz.org + +When replying, please edit your Subject line so it is more specific +than "Re: Contents of Ppp digest..." + +Today's Topics: + + 1. testing #1 (Barry A. Warsaw) + 2. testing #2 (Barry A. Warsaw) + 3. testing #3 (Barry A. Warsaw) + 4. testing #4 (Barry A. Warsaw) + 5. testing #5 (Barry A. Warsaw) + +hello + + +hello + + +hello + + +hello + + +hello + + + +_______________________________________________ +Ppp mailing list +Ppp@zzz.org +http://www.zzz.org/mailman/listinfo/ppp + diff --git a/Lib/email/test/data/msg_20.txt b/Lib/email/test/data/msg_20.txt new file mode 100644 index 00000000000..1a6a88783ee --- /dev/null +++ b/Lib/email/test/data/msg_20.txt @@ -0,0 +1,22 @@ +Return-Path: +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Cc: ccc@zzz.org +CC: ddd@zzz.org +cc: eee@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/email/test/data/msg_21.txt b/Lib/email/test/data/msg_21.txt new file mode 100644 index 00000000000..23590b255dd --- /dev/null +++ b/Lib/email/test/data/msg_21.txt @@ -0,0 +1,20 @@ +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-- +End of MIME message diff --git a/Lib/email/test/data/msg_22.txt b/Lib/email/test/data/msg_22.txt new file mode 100644 index 00000000000..af9de5fa27b --- /dev/null +++ b/Lib/email/test/data/msg_22.txt @@ -0,0 +1,46 @@ +Mime-Version: 1.0 +Message-Id: +Date: Tue, 16 Oct 2001 13:59:25 +0300 +To: a@example.com +From: b@example.com +Content-Type: multipart/mixed; boundary="============_-1208892523==_============" + +--============_-1208892523==_============ +Content-Type: text/plain; charset="us-ascii" ; format="flowed" + +Text text text. +--============_-1208892523==_============ +Content-Id: +Content-Type: image/jpeg; name="wibble.JPG" + ; x-mac-type="4A504547" + ; x-mac-creator="474B4F4E" +Content-Disposition: attachment; filename="wibble.JPG" +Content-Transfer-Encoding: base64 + +/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEB +AQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/wAALCAXABIEBAREA +g6bCjjw/pIZSjO6FWFpldjySOmCNrO7DBZibUXhTwtCixw+GtAijVdqxxaPp0aKvmGXa +qrbBQvms0mAMeYS/3iTV1dG0hHaRNK01XblnWxtVdjkHLMIgTyqnk9VB7CrP2KzIINpa +4O7I+zxYO9WV8jZg71Zlb+8rMDkEirAVQFAUAKAFAAAUAYAUDgADgY6DjpRtXj5RxjHA +4wQRj0wQCMdCAewpaKKK/9k= +--============_-1208892523==_============ +Content-Id: +Content-Type: image/jpeg; name="wibble2.JPG" + ; x-mac-type="4A504547" + ; x-mac-creator="474B4F4E" +Content-Disposition: attachment; filename="wibble2.JPG" +Content-Transfer-Encoding: base64 + +/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEB +AQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/wAALCAXABJ0BAREA +/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQA +W6NFJJBEkU10kKGTcWMDwxuU+0JHvk8qAtOpNwqSR0n8c3BlDyXHlqsUltHEiTvdXLxR +7vMiGDNJAJWkAMk8ZkCFp5G2oo5W++INrbQtNfTQxJAuXlupz9oS4d5Y1W+E2XlWZJJE +Y7LWYQxTLE1zuMbfBPxw8X2fibVdIbSbI6nLZxX635t9TjtYreWR7WGKJTLJFFKSlozO +0ShxIXM43uC3/9k= +--============_-1208892523==_============ +Content-Type: text/plain; charset="us-ascii" ; format="flowed" + +Text text text. +--============_-1208892523==_============-- + diff --git a/Lib/email/test/data/msg_23.txt b/Lib/email/test/data/msg_23.txt new file mode 100644 index 00000000000..bb2e8ec36bb --- /dev/null +++ b/Lib/email/test/data/msg_23.txt @@ -0,0 +1,8 @@ +From: aperson@dom.ain +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain + +A message part +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_24.txt b/Lib/email/test/data/msg_24.txt new file mode 100644 index 00000000000..4e52339e86d --- /dev/null +++ b/Lib/email/test/data/msg_24.txt @@ -0,0 +1,10 @@ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY + + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_25.txt b/Lib/email/test/data/msg_25.txt new file mode 100644 index 00000000000..9e35275fe0d --- /dev/null +++ b/Lib/email/test/data/msg_25.txt @@ -0,0 +1,117 @@ +From MAILER-DAEMON Fri Apr 06 16:46:09 2001 +Received: from [204.245.199.98] (helo=zinfandel.lacita.com) + by www.linux.org.uk with esmtp (Exim 3.13 #1) + id 14lYR6-0008Iv-00 + for linuxuser-admin@www.linux.org.uk; Fri, 06 Apr 2001 16:46:09 +0100 +Received: from localhost (localhost) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with internal id JAB03225; Fri, 6 Apr 2001 09:23:06 -0800 (GMT-0800) +Date: Fri, 6 Apr 2001 09:23:06 -0800 (GMT-0800) +From: Mail Delivery Subsystem +Subject: Returned mail: Too many hops 19 (17 max): from via [199.164.235.226], to +Message-Id: <200104061723.JAB03225@zinfandel.lacita.com> +To: +To: postmaster@zinfandel.lacita.com +MIME-Version: 1.0 +Content-Type: multipart/report; report-type=delivery-status; + bo +Auto-Submitted: auto-generated (failure) + +This is a MIME-encapsulated message + +--JAB03225.986577786/zinfandel.lacita.com + +The original message was received at Fri, 6 Apr 2001 09:23:03 -0800 (GMT-0800) +from [199.164.235.226] + + ----- The following addresses have delivery notifications ----- + (unrecoverable error) + + ----- Transcript of session follows ----- +554 Too many hops 19 (17 max): from via [199.164.235.226], to + +--JAB03225.986577786/zinfandel.lacita.com +Content-Type: message/delivery-status + +Reporting-MTA: dns; zinfandel.lacita.com +Received-From-MTA: dns; [199.164.235.226] +Arrival-Date: Fri, 6 Apr 2001 09:23:03 -0800 (GMT-0800) + +Final-Recipient: rfc822; scoffman@wellpartner.com +Action: failed +Status: 5.4.6 +Last-Attempt-Date: Fri, 6 Apr 2001 09:23:06 -0800 (GMT-0800) + +--JAB03225.986577786/zinfandel.lacita.com +Content-Type: text/rfc822-headers + +Return-Path: linuxuser-admin@www.linux.org.uk +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03225 for ; Fri, 6 Apr 2001 09:23:03 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03221 for ; Fri, 6 Apr 2001 09:22:18 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03217 for ; Fri, 6 Apr 2001 09:21:37 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03213 for ; Fri, 6 Apr 2001 09:20:56 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03209 for ; Fri, 6 Apr 2001 09:20:15 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03205 for ; Fri, 6 Apr 2001 09:19:33 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03201 for ; Fri, 6 Apr 2001 09:18:52 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03197 for ; Fri, 6 Apr 2001 09:17:54 -0800 (GMT-0800) +Received: from www.linux.org.uk (parcelfarce.linux.theplanet.co.uk [195.92.249.252]) + by + fo +Received: from localhost.localdomain + ([ + by + id +Received: from [212.1.130.11] (helo=s1.uklinux.net ident=root) + by + id + fo +Received: from server (ppp-2-22.cvx4.telinco.net [212.1.149.22]) + by + fo +From: Daniel James +Organization: LinuxUser +To: linuxuser@www.linux.org.uk +X-Mailer: KMail [version 1.1.99] +Content-Type: text/plain; + c +MIME-Version: 1.0 +Message-Id: <01040616033903.00962@server> +Content-Transfer-Encoding: 8bit +Subject: [LinuxUser] bulletin no. 45 +Sender: linuxuser-admin@www.linux.org.uk +Errors-To: linuxuser-admin@www.linux.org.uk +X-BeenThere: linuxuser@www.linux.org.uk +X-Mailman-Version: 2.0.3 +Precedence: bulk +List-Help: +List-Post: +List-Subscribe: , + +List-Unsubscribe: , + +Date: Fri, 6 Apr 2001 16:03:39 +0100 + +--JAB03225.986577786/zinfandel.lacita.com-- + + diff --git a/Lib/email/test/data/msg_26.txt b/Lib/email/test/data/msg_26.txt new file mode 100644 index 00000000000..6c71bced9ac --- /dev/null +++ b/Lib/email/test/data/msg_26.txt @@ -0,0 +1,45 @@ +Received: from xcar [192.168.0.2] by jeeves.wooster.local + (SMTPD32-7.07 EVAL) id AFF92F0214; Sun, 12 May 2002 08:55:37 +0100 +Date: Sun, 12 May 2002 08:56:15 +0100 +From: Father Time +To: timbo@jeeves.wooster.local +Subject: IMAP file test +Message-ID: <6df65d354b.father.time@rpc.wooster.local> +X-Organization: Home +User-Agent: Messenger-Pro/2.50a (MsgServe/1.50) (RISC-OS/4.02) POPstar/2.03 +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="1618492860--2051301190--113853680" +Status: R +X-UIDL: 319998302 + +This message is in MIME format which your mailer apparently does not support. +You either require a newer version of your software which supports MIME, or +a separate MIME decoding utility. Alternatively, ask the sender of this +message to resend it in a different format. + +--1618492860--2051301190--113853680 +Content-Type: text/plain; charset=us-ascii + +Simple email with attachment. + + +--1618492860--2051301190--113853680 +Content-Type: application/riscos; name="clock.bmp,69c"; type=BMP; load=&fff69c4b; exec=&355dd4d1; access=&03 +Content-Disposition: attachment; filename="clock.bmp" +Content-Transfer-Encoding: base64 + +Qk12AgAAAAAAAHYAAAAoAAAAIAAAACAAAAABAAQAAAAAAAAAAADXDQAA1w0AAAAAAAAA +AAAAAAAAAAAAiAAAiAAAAIiIAIgAAACIAIgAiIgAALu7uwCIiIgAERHdACLuIgAz//8A +zAAAAN0R3QDu7iIA////AAAAAAAAAAAAAAAAAAAAAAAAAAi3AAAAAAAAADeAAAAAAAAA +C3ADMzMzMANwAAAAAAAAAAAHMAAAAANwAAAAAAAAAACAMAd3zPfwAwgAAAAAAAAIAwd/ +f8x/f3AwgAAAAAAAgDB0x/f3//zPAwgAAAAAAAcHfM9////8z/AwAAAAAAiwd/f3//// +////A4AAAAAAcEx/f///////zAMAAAAAiwfM9////3///8zwOAAAAAcHf3////B///// +8DAAAAALB/f3///wd3d3//AwAAAABwTPf//wCQAAD/zAMAAAAAsEx/f///B////8wDAA +AAAHB39////wf/////AwAAAACwf39///8H/////wMAAAAIcHfM9///B////M8DgAAAAA +sHTH///wf///xAMAAAAACHB3f3//8H////cDgAAAAAALB3zH//D//M9wMAAAAAAAgLB0 +z39///xHAwgAAAAAAAgLB3d3RHd3cDCAAAAAAAAAgLAHd0R3cAMIAAAAAAAAgAgLcAAA +AAMwgAgAAAAACDAAAAu7t7cwAAgDgAAAAABzcIAAAAAAAAgDMwAAAAAAN7uwgAAAAAgH +MzMAAAAACH97tzAAAAALu3c3gAAAAAAL+7tzDABAu7f7cAAAAAAACA+3MA7EQAv/sIAA +AAAAAAAIAAAAAAAAAIAAAAAA + +--1618492860--2051301190--113853680-- diff --git a/Lib/email/test/data/msg_27.txt b/Lib/email/test/data/msg_27.txt new file mode 100644 index 00000000000..d0191769d73 --- /dev/null +++ b/Lib/email/test/data/msg_27.txt @@ -0,0 +1,15 @@ +Return-Path: +Received: by mail.dom.ain (Postfix, from userid 889) + id B9D0AD35DB; Tue, 4 Jun 2002 21:46:59 -0400 (EDT) +Message-ID: <15613.28051.707126.569693@dom.ain> +Date: Tue, 4 Jun 2002 21:46:59 -0400 +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Subject: bug demonstration + 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 + more text +From: aperson@dom.ain (Anne P. Erson) +To: bperson@dom.ain (Barney P. Erson) + +test diff --git a/Lib/email/test/data/msg_28.txt b/Lib/email/test/data/msg_28.txt new file mode 100644 index 00000000000..1e4824cabb0 --- /dev/null +++ b/Lib/email/test/data/msg_28.txt @@ -0,0 +1,25 @@ +From: aperson@dom.ain +MIME-Version: 1.0 +Content-Type: multipart/digest; boundary=BOUNDARY + +--BOUNDARY +Content-Type: message/rfc822 + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 1 + +--BOUNDARY +Content-Type: message/rfc822 + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 2 + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_29.txt b/Lib/email/test/data/msg_29.txt new file mode 100644 index 00000000000..1fab5616173 --- /dev/null +++ b/Lib/email/test/data/msg_29.txt @@ -0,0 +1,22 @@ +Return-Path: +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii; + title*0*="us-ascii'en'This%20is%20even%20more%20"; + title*1*="%2A%2A%2Afun%2A%2A%2A%20"; + title*2="isn't it!" +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 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/email/test/data/msg_30.txt b/Lib/email/test/data/msg_30.txt new file mode 100644 index 00000000000..4334bb6e608 --- /dev/null +++ b/Lib/email/test/data/msg_30.txt @@ -0,0 +1,23 @@ +From: aperson@dom.ain +MIME-Version: 1.0 +Content-Type: multipart/digest; boundary=BOUNDARY + +--BOUNDARY + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 1 + +--BOUNDARY + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 2 + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_31.txt b/Lib/email/test/data/msg_31.txt new file mode 100644 index 00000000000..1e58e56cf52 --- /dev/null +++ b/Lib/email/test/data/msg_31.txt @@ -0,0 +1,15 @@ +From: aperson@dom.ain +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary=BOUNDARY_ + +--BOUNDARY +Content-Type: text/plain + +message 1 + +--BOUNDARY +Content-Type: text/plain + +message 2 + +--BOUNDARY-- diff --git a/Lib/email/test/data/msg_32.txt b/Lib/email/test/data/msg_32.txt new file mode 100644 index 00000000000..07ec5af9a3d --- /dev/null +++ b/Lib/email/test/data/msg_32.txt @@ -0,0 +1,14 @@ +Delivered-To: freebsd-isp@freebsd.org +Date: Tue, 26 Sep 2000 12:23:03 -0500 +From: Anne Person +To: Barney Dude +Subject: Re: Limiting Perl CPU Utilization... +Mime-Version: 1.0 +Content-Type: text/plain; charset*=ansi-x3.4-1968''us-ascii +Content-Disposition: inline +User-Agent: Mutt/1.3.8i +Sender: owner-freebsd-isp@FreeBSD.ORG +Precedence: bulk +X-Loop: FreeBSD.org + +Some message. diff --git a/Lib/email/test/data/msg_33.txt b/Lib/email/test/data/msg_33.txt new file mode 100644 index 00000000000..042787a4fd8 --- /dev/null +++ b/Lib/email/test/data/msg_33.txt @@ -0,0 +1,29 @@ +Delivered-To: freebsd-isp@freebsd.org +Date: Wed, 27 Sep 2000 11:11:09 -0500 +From: Anne Person +To: Barney Dude +Subject: Re: Limiting Perl CPU Utilization... +Mime-Version: 1.0 +Content-Type: multipart/signed; micalg*=ansi-x3.4-1968''pgp-md5; + protocol*=ansi-x3.4-1968''application%2Fpgp-signature; + boundary*="ansi-x3.4-1968''EeQfGwPcQSOJBaQU" +Content-Disposition: inline +Sender: owner-freebsd-isp@FreeBSD.ORG +Precedence: bulk +X-Loop: FreeBSD.org + + +--EeQfGwPcQSOJBaQU +Content-Type: text/plain; charset*=ansi-x3.4-1968''us-ascii +Content-Disposition: inline +Content-Transfer-Encoding: quoted-printable + +part 1 + +--EeQfGwPcQSOJBaQU +Content-Type: text/plain +Content-Disposition: inline + +part 2 + +--EeQfGwPcQSOJBaQU-- diff --git a/Lib/email/test/data/msg_34.txt b/Lib/email/test/data/msg_34.txt new file mode 100644 index 00000000000..055dfea5310 --- /dev/null +++ b/Lib/email/test/data/msg_34.txt @@ -0,0 +1,19 @@ +From: aperson@dom.ain +To: bperson@dom.ain +Content-Type: multipart/digest; boundary=XYZ + +--XYZ +Content-Type: text/plain + + +This is a text plain part that is counter to recommended practice in +RFC 2046, $5.1.5, but is not illegal + +--XYZ + +From: cperson@dom.ain +To: dperson@dom.ain + +A submessage + +--XYZ-- diff --git a/Lib/email/test/data/msg_35.txt b/Lib/email/test/data/msg_35.txt new file mode 100644 index 00000000000..be7d5a2f7b9 --- /dev/null +++ b/Lib/email/test/data/msg_35.txt @@ -0,0 +1,4 @@ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: here's something interesting +counter to RFC 2822, there's no separating newline here diff --git a/Lib/email/test/data/msg_36.txt b/Lib/email/test/data/msg_36.txt new file mode 100644 index 00000000000..5632c3062c9 --- /dev/null +++ b/Lib/email/test/data/msg_36.txt @@ -0,0 +1,40 @@ +Mime-Version: 1.0 +Content-Type: Multipart/Mixed; Boundary="NextPart" +To: IETF-Announce:; +From: Internet-Drafts@ietf.org +Subject: I-D ACTION:draft-ietf-mboned-mix-00.txt +Date: Tue, 22 Dec 1998 16:55:06 -0500 + +--NextPart + +Blah blah blah + +--NextPart +Content-Type: Multipart/Alternative; Boundary="OtherAccess" + +--OtherAccess +Content-Type: Message/External-body; + access-type="mail-server"; + server="mailserv@ietf.org" + +Content-Type: text/plain +Content-ID: <19981222151406.I-D@ietf.org> + +ENCODING mime +FILE /internet-drafts/draft-ietf-mboned-mix-00.txt + +--OtherAccess +Content-Type: Message/External-body; + name="draft-ietf-mboned-mix-00.txt"; + site="ftp.ietf.org"; + access-type="anon-ftp"; + directory="internet-drafts" + +Content-Type: text/plain +Content-ID: <19981222151406.I-D@ietf.org> + + +--OtherAccess-- + +--NextPart-- + diff --git a/Lib/email/test/data/msg_37.txt b/Lib/email/test/data/msg_37.txt new file mode 100644 index 00000000000..038d34a1a42 --- /dev/null +++ b/Lib/email/test/data/msg_37.txt @@ -0,0 +1,22 @@ +Content-Type: multipart/mixed; boundary=ABCDE + +--ABCDE +Content-Type: text/x-one + +Blah + +--ABCDE +--ABCDE +Content-Type: text/x-two + +Blah + +--ABCDE +--ABCDE +--ABCDE +--ABCDE +Content-Type: text/x-two + +Blah + +--ABCDE-- diff --git a/Lib/email/test/data/msg_38.txt b/Lib/email/test/data/msg_38.txt new file mode 100644 index 00000000000..006df81cb59 --- /dev/null +++ b/Lib/email/test/data/msg_38.txt @@ -0,0 +1,101 @@ +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa0" + +------- =_aaaaaaaaaa0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.1@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa2" +Content-ID: <20592.1022586929.2@example.com> + +------- =_aaaaaaaaaa2 +Content-Type: text/plain +Content-ID: <20592.1022586929.3@example.com> +Content-Description: very tricky +Content-Transfer-Encoding: 7bit + + +Unlike the test test_nested-multiples-with-internal-boundary, this +piece of text not only contains the outer boundary tags +------- =_aaaaaaaaaa1 +and +------- =_aaaaaaaaaa0 +but puts them at the start of a line! And, to be even nastier, it +even includes a couple of end tags, such as this one: + +------- =_aaaaaaaaaa1-- + +and this one, which is from a multipart we haven't even seen yet! + +------- =_aaaaaaaaaa4-- + +This will, I'm sure, cause much breakage of MIME parsers. But, as +far as I can tell, it's perfectly legal. I have not yet ever seen +a case of this in the wild, but I've seen *similar* things. + + +------- =_aaaaaaaaaa2 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.4@example.com> +Content-Description: patch2 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa2-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa3" +Content-ID: <20592.1022586929.6@example.com> + +------- =_aaaaaaaaaa3 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.7@example.com> +Content-Description: patch3 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa3 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.8@example.com> +Content-Description: patch4 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa3-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa4" +Content-ID: <20592.1022586929.10@example.com> + +------- =_aaaaaaaaaa4 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.11@example.com> +Content-Description: patch5 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa4 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.12@example.com> +Content-Description: patch6 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa4-- + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa0 +Content-Type: text/plain; charset="us-ascii" +Content-ID: <20592.1022586929.15@example.com> + +-- +It's never too late to have a happy childhood. + +------- =_aaaaaaaaaa0-- diff --git a/Lib/email/test/data/msg_39.txt b/Lib/email/test/data/msg_39.txt new file mode 100644 index 00000000000..124b2691927 --- /dev/null +++ b/Lib/email/test/data/msg_39.txt @@ -0,0 +1,83 @@ +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa0" + +------- =_aaaaaaaaaa0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.1@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.2@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.3@example.com> +Content-Description: patch1 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.4@example.com> +Content-Description: patch2 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.6@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.7@example.com> +Content-Description: patch3 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.8@example.com> +Content-Description: patch4 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.10@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.11@example.com> +Content-Description: patch5 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.12@example.com> +Content-Description: patch6 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa0 +Content-Type: text/plain; charset="us-ascii" +Content-ID: <20592.1022586929.15@example.com> + +-- +It's never too late to have a happy childhood. + +------- =_aaaaaaaaaa0-- diff --git a/Lib/email/test/data/msg_40.txt b/Lib/email/test/data/msg_40.txt new file mode 100644 index 00000000000..1435fa1e1a0 --- /dev/null +++ b/Lib/email/test/data/msg_40.txt @@ -0,0 +1,10 @@ +MIME-Version: 1.0 +Content-Type: text/html; boundary="--961284236552522269" + +----961284236552522269 +Content-Type: text/html; +Content-Transfer-Encoding: 7Bit + + + +----961284236552522269-- diff --git a/Lib/email/test/data/msg_41.txt b/Lib/email/test/data/msg_41.txt new file mode 100644 index 00000000000..76cdd1cb7f2 --- /dev/null +++ b/Lib/email/test/data/msg_41.txt @@ -0,0 +1,8 @@ +From: "Allison Dunlap" +To: yyy@example.com +Subject: 64423 +Date: Sun, 11 Jul 2004 16:09:27 -0300 +MIME-Version: 1.0 +Content-Type: multipart/alternative; + +Blah blah blah diff --git a/Lib/email/test/data/msg_42.txt b/Lib/email/test/data/msg_42.txt new file mode 100644 index 00000000000..a75f8f4a020 --- /dev/null +++ b/Lib/email/test/data/msg_42.txt @@ -0,0 +1,20 @@ +Content-Type: multipart/mixed; boundary="AAA" +From: Mail Delivery Subsystem +To: yyy@example.com + +This is a MIME-encapsulated message + +--AAA + +Stuff + +--AAA +Content-Type: message/rfc822 + +From: webmaster@python.org +To: zzz@example.com +Content-Type: multipart/mixed; boundary="BBB" + +--BBB-- + +--AAA-- diff --git a/Lib/email/test/data/msg_43.txt b/Lib/email/test/data/msg_43.txt new file mode 100644 index 00000000000..797d12c5688 --- /dev/null +++ b/Lib/email/test/data/msg_43.txt @@ -0,0 +1,217 @@ +From SRS0=aO/p=ON=bag.python.org=None@bounce2.pobox.com Fri Nov 26 21:40:36 2004 +X-VM-v5-Data: ([nil nil nil nil nil nil nil nil nil] + [nil nil nil nil nil nil nil "MAILER DAEMON <>" "MAILER DAEMON <>" nil nil "Banned file: auto__mail.python.bat in mail from you" "^From:" nil nil nil nil "Banned file: auto__mail.python.bat in mail from you" nil nil nil nil nil nil nil] + nil) +MIME-Version: 1.0 +Message-Id: +Content-Type: multipart/report; report-type=delivery-status; + charset=utf-8; + boundary="----------=_1101526904-1956-5" +X-Virus-Scanned: by XS4ALL Virus Scanner +X-UIDL: 4\G!!! +To: +Subject: Banned file: auto__mail.python.bat in mail from you +Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +This is a multi-part message in MIME format... + +------------=_1101526904-1956-5 +Content-Type: text/plain; charset="utf-8" +Content-Disposition: inline +Content-Transfer-Encoding: 7bit + +BANNED FILENAME ALERT + +Your message to: xxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxxxxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxx@dot.ca.gov, xxxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxx@dot.ca.gov, xxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxx@dot.ca.gov, xxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxxxxxxxx@dot.ca.gov +was blocked by our Spam Firewall. The email you sent with the following subject has NOT BEEN DELIVERED: + +Subject: Delivery_failure_notice + +An attachment in that mail was of a file type that the Spam Firewall is set to block. + + + +------------=_1101526904-1956-5 +Content-Type: message/delivery-status +Content-Disposition: inline +Content-Transfer-Encoding: 7bit +Content-Description: Delivery error report + +Reporting-MTA: dns; sacspam01.dot.ca.gov +Received-From-MTA: smtp; sacspam01.dot.ca.gov ([127.0.0.1]) +Arrival-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +------------=_1101526904-1956-5 +Content-Type: text/rfc822-headers +Content-Disposition: inline +Content-Transfer-Encoding: 7bit +Content-Description: Undelivered-message headers + +Received: from kgsav.org (ppp-70-242-162-63.dsl.spfdmo.swbell.net [70.242.162.63]) + by sacspam01.dot.ca.gov (Spam Firewall) with SMTP + id A232AD03DE3A; Fri, 26 Nov 2004 19:41:35 -0800 (PST) +From: webmaster@python.org +To: xxxxx@dot.ca.gov +Date: Sat, 27 Nov 2004 03:35:30 UTC +Subject: Delivery_failure_notice +Importance: Normal +X-Priority: 3 (Normal) +X-MSMail-Priority: Normal +Message-ID: +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="====67bd2b7a5.f99f7" +Content-Transfer-Encoding: 7bit + +------------=_1101526904-1956-5-- + diff --git a/Lib/email/test/data/msg_44.txt b/Lib/email/test/data/msg_44.txt new file mode 100644 index 00000000000..ae462a61be6 --- /dev/null +++ b/Lib/email/test/data/msg_44.txt @@ -0,0 +1,35 @@ +Return-Path: +Delivered-To: barry@python.org +Received: by mail.python.org (Postfix, from userid 889) + id C2BF0D37C6; Tue, 11 Sep 2001 00:05:05 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="h90VIIIKmx" +Content-Transfer-Encoding: 7bit +Message-ID: <15261.36209.358846.118674@anthem.python.org> +From: barry@python.org (Barry A. Warsaw) +To: barry@python.org +Subject: a simple multipart +Date: Tue, 11 Sep 2001 00:05:05 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Make a door into a window + + +--h90VIIIKmx +Content-Type: text/plain +Content-Disposition: inline; name="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx +Content-Type: text/plain +Content-Disposition: inline; name="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx-- + diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py new file mode 100644 index 00000000000..fc8224a602d --- /dev/null +++ b/Lib/email/test/test_email.py @@ -0,0 +1,3307 @@ +# Copyright (C) 2001-2007 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 io import StringIO +from itertools import chain + +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, *args, **kws): + path = os.path.join(os.path.dirname(landmark), 'data', filename) + return open(path, *args, **kws) + + + +# 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) + rfirst = [repr(line) for line in sfirst.splitlines()] + rsecond = [repr(line) for line in ssecond.splitlines()] + diff = difflib.ndiff(rfirst, rsecond) + raise self.failureException(NL + NL.join(diff)) + + def _msgobj(self, filename): + with openfile(findfile(filename)) as fp: + return email.message_from_file(fp) + + + +# 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), + b'This is a 7bit encoded message.\n') + # Subpart 2 is quopri + eq(msg.get_payload(1).get_payload(decode=True), + b'\xa1This is a Quoted Printable encoded message!\n') + # Subpart 3 is base64 + eq(msg.get_payload(2).get_payload(decode=True), + b'This is a Base64 encoded message.') + # Subpart 4 has no Content-Transfer-Encoding: header. + eq(msg.get_payload(3).get_payload(decode=True), + b'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), b'hello world') + # Now try some bogus data + msg.set_payload('foo') + eq(msg.get_payload(decode=True), b'foo') + + def test_decoded_generator(self): + eq = self.assertEqual + msg = self._msgobj('msg_07.txt') + with openfile('msg_17.txt') as fp: + text = fp.read() + 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.ndiffAssertEqual + msg = self._msgobj('msg_01.txt') + with openfile('msg_01.txt') as fp: + text = fp.read() + eq(text, str(msg)) + fullrepr = msg.as_string(unixfrom=True) + 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_field_containment(self): + unless = self.failUnless + msg = email.message_from_string('Header: exists') + unless('header' in msg) + unless('Header' in msg) + unless('HEADER' in msg) + self.failIf('headerx' in msg) + + 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), + bytes(ord(c) for c in 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.replace('\t', ' ')) + 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 = (b'Die Mieter treten hier ein werden mit einem Foerderband ' + b'komfortabel den Korridor entlang, an s\xfcdl\xfcndischen ' + b'Wandgem\xe4lden vorbei, gegen die rotierenden Klingen ' + b'bef\xf6rdert. ') + cz_head = (b'Finan\xe8ni metropole se hroutily pod tlakem jejich ' + b'd\xf9vtipu.. ') + utf8_head = ('\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') + 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_is_just_a_hint(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"; + 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";\t' + '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"; + spooge="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> + <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]); + 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)""") + + 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] + 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""") + + 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_gr=FCnes_Licht_f=FCr?= + =?iso-8859-1?q?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(maxheaderlen=78), '''\ +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.ndiffAssertEqual(msg.as_string(maxheaderlen=78), """\ +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.ndiffAssertEqual(msg.as_string(maxheaderlen=78), """\ +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(maxheaderlen=78), """\ +Face-1: iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 + locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/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(maxheaderlen=78), '''\ +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(maxheaderlen=78), """\ +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', '') + with open(findfile('audiotest.au', datadir), 'rb') as fp: + self._audiodata = fp.read() + 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): + with openfile('PyBanner048.gif', 'rb') as fp: + self._imgdata = fp.read() + 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): + with openfile('PyBanner048.gif', 'rb') as fp: + data = fp.read() + 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)) + + def test_first_line_is_continuation_header(self): + eq = self.assertEqual + m = ' Line 1\nLine 2\nLine 3' + msg = email.message_from_string(m) + eq(msg.keys(), []) + eq(msg.get_payload(), 'Line 2\nLine 3') + eq(len(msg.defects), 1) + self.failUnless(isinstance(msg.defects[0], + errors.FirstHeaderLineIsContinuationDefect)) + eq(msg.defects[0].line, ' Line 1\n') + + + +# 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, [ + (b'Re:', None), + (b'r\x8aksm\x9arg\x8cs', 'mac-iceland'), + (b'baz foo bar', None), + (b'r\x8aksm\x9arg\x8cs', 'mac-iceland')]) + header = make_header(dh) + eq(str(header), + 'Re: r\xe4ksm\xf6rg\xe5s baz foo bar r\xe4ksm\xf6rg\xe5s') + eq(header.encode(), + """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, [(b'Andr\xe9', 'iso-8859-1'), + (b'Pirard ', None)]) + header = str(make_header(dh)) + eq(header, '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, [(b'The', None), (b'quick brown fox', 'iso-8859-1'), + (b'jumped over the', None), (b'lazy dog', 'iso-8859-1')]) + hu = str(make_header(dh)) + eq(hu, 'The quick brown fox jumped over the lazy dog') + + def test_rfc2047_missing_whitespace(self): + s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord' + dh = decode_header(s) + self.assertEqual(dh, [(s, None)]) + + def test_rfc2047_with_whitespace(self): + s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord' + dh = decode_header(s) + self.assertEqual(dh, [(b'Sm', None), (b'\xf6', 'iso-8859-1'), + (b'rg', None), (b'\xe5', 'iso-8859-1'), + (b'sbord', None)]) + + + +# Test the MIMEMessage class +class TestMIMEMessage(TestEmailBase): + def setUp(self): + with openfile('msg_11.txt') as fp: + self._text = fp.read() + + 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 + with openfile('msg_21.txt') as fp: + text = fp.read() + 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 + with openfile('msg_30.txt') as fp: + msg = email.message_from_file(fp) + 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 + with openfile('msg_28.txt') as fp: + msg = email.message_from_file(fp) + 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): + with openfile(filename) as fp: + data = fp.read() + 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): + with openfile('msg_01.txt') as fp: + text = fp.read() + 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): + with openfile('msg_01.txt') as fp: + 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()) + + def test_message_from_string_with_class(self): + unless = self.failUnless + with openfile('msg_01.txt') as fp: + text = fp.read() + + # Create a subclass + class MyMessage(Message): + pass + + msg = email.message_from_string(text, MyMessage) + unless(isinstance(msg, MyMessage)) + # Try something more complicated + with openfile('msg_02.txt') as fp: + text = fp.read() + 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 + + with openfile('msg_01.txt') as fp: + msg = email.message_from_file(fp, MyMessage) + unless(isinstance(msg, MyMessage)) + # Try something more complicated + with openfile('msg_02.txt') as fp: + msg = email.message_from_file(fp, MyMessage) + 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, [ + 'base64mime', 'charset', 'encoders', 'errors', 'generator', + 'header', 'iterators', 'message', 'message_from_file', + 'message_from_string', 'mime', 'parser', + '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, -1, -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, -1, -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_multiline_from_comment(self): + x = """\ +Foo +\tBar """ + self.assertEqual(utils.parseaddr(x), ('Foo Bar', 'foo@example.com')) + + 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_getaddresses_embedded_comment(self): + """Test proper handling of a nested comment""" + eq = self.assertEqual + addrs = utils.getaddresses(['User ((nested comment)) ']) + eq(addrs[0][1], 'foo@bar.com') + + 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), b'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) + with openfile('msg_19.txt') as fp: + neq(EMPTYSTRING.join(lines), fp.read()) + + 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 + with openfile('msg_02.txt') as fp: + msg = HeaderParser().parse(fp) + 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 + # XXX When Guido fixes TextIOWrapper.read() to act just like + # .readlines(), open this in 'rb' mode with newlines='\n'. + with openfile('msg_26.txt', mode='rb') as fp: + msg = Parser().parse(fp) + 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 + with openfile('msg_28.txt') as fp: + msg = email.message_from_file(fp) + # 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='), b'hello') + eq(base64mime.decode('aGVsbG8=', 'X'), b'hello') + eq(base64mime.decode('aGVsbG8NCndvcmxk\n', 'X'), b'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=?=') + eq(he('hello\nworld'), '=?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): + # Set of characters (as byte integers) that don't need to be encoded + # in headers. + self.hlit = list(chain( + range(ord('a'), ord('z') + 1), + range(ord('A'), ord('Z') + 1), + range(ord('0'), ord('9') + 1), + (c for c in b'!*+-/ '))) + # Set of characters (as byte integers) that do need to be encoded in + # headers. + self.hnon = [c for c in range(256) if c not in self.hlit] + assert len(self.hlit) + len(self.hnon) == 256 + # Set of characters (as byte integers) that don't need to be encoded + # in bodies. + self.blit = list(range(ord(' '), ord('~') + 1)) + self.blit.append(ord('\t')) + self.blit.remove(ord('=')) + # Set of characters (as byte integers) that do need to be encoded in + # bodies. + self.bnon = [c for c in range(256) if c 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 + eq(quoprimime.header_quopri_len(b'hello'), 5) + # RFC 2047 chrome is not included in header_quopri_len(). + eq(len(quoprimime.header_encode(b'hello', charset='xxx')), + quoprimime.header_quopri_len(b'hello') + + # =?xxx?q?...?= means 10 extra characters + 10) + eq(quoprimime.header_quopri_len(b'h@e@l@l@o@'), 20) + # RFC 2047 chrome is not included in header_quopri_len(). + eq(len(quoprimime.header_encode(b'h@e@l@l@o@', charset='xxx')), + quoprimime.header_quopri_len(b'h@e@l@l@o@') + + # =?xxx?q?...?= means 10 extra characters + 10) + for c in self.hlit: + eq(quoprimime.header_quopri_len(bytes([c])), 1, + 'expected length 1 for %r' % chr(c)) + for c in self.hnon: + eq(quoprimime.header_quopri_len(bytes([c])), 3, + 'expected length 3 for %r' % chr(c)) + + 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(b'hello'), '=?iso-8859-1?q?hello?=') + eq(he(b'hello', charset='iso-8859-2'), '=?iso-8859-2?q?hello?=') + eq(he(b'hello\nworld'), '=?iso-8859-1?q?hello=0Aworld?=') + # Test a non-ASCII character + eq(he(b'hello\xc7there'), '=?iso-8859-1?q?hello=C7there?=') + + 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(b'hello w\xf6rld')) + # Try a charset with Base64 body encoding + c = Charset('utf-8') + eq('aGVsbG8gd29ybGQ=\n', c.body_encode(b'hello world')) + # Try a charset with None body encoding + c = Charset('us-ascii') + eq('hello world', c.body_encode(b'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(b'\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7')) + eq('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', + c.body_encode(b'\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(b'hello w\xf6rld')) + + def test_unicode_charset_name(self): + charset = Charset('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 = (b'Die Mieter treten hier ein werden mit einem ' + b'Foerderband komfortabel den Korridor entlang, ' + b'an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, ' + b'gegen die rotierenden Klingen bef\xf6rdert. ') + cz_head = (b'Finan\xe8ni metropole se hroutily pod tlakem jejich ' + b'd\xf9vtipu.. ') + utf8_head = ('\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') + 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 = str(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_empty_header_encode(self): + h = Header() + self.assertEqual(h.encode(), '') + + 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''') + eq(str(h), hstr) + 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''') + eq(str(h), hstr) + h = Header(hstr, maxlinelen=1024, header_name='Subject') + eq(h.encode(), hstr) + eq(str(h), hstr) + + def test_long_splittables_with_trailing_spaces(self): + eq = self.ndiffAssertEqual + h = Header(charset='iso-8859-1', maxlinelen=20) + h.append('xxxx ' * 20) + eq(h.encode(), """\ +=?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx?= + =?iso-8859-1?q?xxxx_?=""") + h = Header(charset='iso-8859-1', maxlinelen=40) + h.append('xxxx ' * 20) + eq(h.encode(), """\ +=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx?= + =?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx?= + =?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx?= + =?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx?= + =?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_?=""") + + 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('p\xf6stal', 'utf-8') + eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=') + h = Header('\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 = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big' + raises(UnicodeError, Header, x) + h = Header() + raises(UnicodeError, h.append, x) + e = x.decode('utf-8', 'replace') + eq(str(Header(x, errors='replace')), e) + h.append(x, errors='replace') + eq(str(h), e) + + 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, [(b'Subject:', None), (b'\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1 \xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), (b'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.ndiffAssertEqual + 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(maxheaderlen=78), """\ +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; + title*="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(maxheaderlen=78), """\ +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"; + title*="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) + param = msg.get_param('NAME') + self.failIf(isinstance(param, tuple)) + self.assertEqual( + param, + '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_filename_encoded(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_partly_encoded(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%20is%20even%20more%20***fun*** is it not.pdf') + + def test_rfc2231_partly_nonencoded(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%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20is 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_bad_encoding_in_filename(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0*="bogus'xx'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_bad_encoding_in_charset(self): + m = """\ +Content-Type: text/plain; charset*=bogus''utf-8%E2%80%9D + +""" + msg = email.message_from_string(m) + # This should return None because non-ascii characters in the charset + # are not allowed. + self.assertEqual(msg.get_content_charset(), None) + + def test_rfc2231_bad_character_in_charset(self): + m = """\ +Content-Type: text/plain; charset*=ascii''utf-8%E2%80%9D + +""" + msg = email.message_from_string(m) + # This should return None because non-ascii characters in the charset + # are not allowed. + self.assertEqual(msg.get_content_charset(), None) + + def test_rfc2231_bad_character_in_filename(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0*="ascii'xx'This%20is%20even%20more%20"; +\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2*="is it not.pdf%E2" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf\ufffd') + + def test_rfc2231_unknown_encoding(self): + m = """\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename*=X-UNKNOWN''myfile.txt + +""" + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), 'myfile.txt') + + def test_rfc2231_single_tick_in_filename_extended(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0*=\"Frank's\"; name*1*=\" Document\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, None) + eq(language, None) + eq(s, "Frank's Document") + + def test_rfc2231_single_tick_in_filename(self): + m = """\ +Content-Type: application/x-foo; name*0=\"Frank's\"; name*1=\" Document\" + +""" + msg = email.message_from_string(m) + param = msg.get_param('name') + self.failIf(isinstance(param, tuple)) + self.assertEqual(param, "Frank's Document") + + def test_rfc2231_tick_attack_extended(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0*=\"us-ascii'en-us'Frank's\"; name*1*=\" Document\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, 'us-ascii') + eq(language, 'en-us') + eq(s, "Frank's Document") + + def test_rfc2231_tick_attack(self): + m = """\ +Content-Type: application/x-foo; +\tname*0=\"us-ascii'en-us'Frank's\"; name*1=\" Document\" + +""" + msg = email.message_from_string(m) + param = msg.get_param('name') + self.failIf(isinstance(param, tuple)) + self.assertEqual(param, "us-ascii'en-us'Frank's Document") + + def test_rfc2231_no_extended_values(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; name=\"Frank's Document\" + +""" + msg = email.message_from_string(m) + eq(msg.get_param('name'), "Frank's Document") + + def test_rfc2231_encoded_then_unencoded_segments(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0*=\"us-ascii'en-us'My\"; +\tname*1=\" Document\"; +\tname*2*=\" For You\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, 'us-ascii') + eq(language, 'en-us') + eq(s, 'My Document For You') + + def test_rfc2231_unencoded_then_encoded_segments(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0=\"us-ascii'en-us'My\"; +\tname*1*=\" Document\"; +\tname*2*=\" For You\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, 'us-ascii') + eq(language, 'en-us') + eq(s, 'My Document For You') + + + +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/test/test_email_codecs.py b/Lib/email/test/test_email_codecs.py new file mode 100644 index 00000000000..1c773473bbf --- /dev/null +++ b/Lib/email/test/test_email_codecs.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: + str('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')]) + int = '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(int, 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'), int) + + 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 = str(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_codecs_renamed.py b/Lib/email/test/test_email_codecs_renamed.py new file mode 100644 index 00000000000..d190de313b5 --- /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: + str('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')]) + int = '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(int, 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'), int) + + 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 = str(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_torture.py b/Lib/email/test/test_email_torture.py new file mode 100644 index 00000000000..67f106acf38 --- /dev/null +++ b/Lib/email/test/test_email_torture.py @@ -0,0 +1,136 @@ +# Copyright (C) 2002-2004 Python Software Foundation +# +# A torture test of the email package. This should not be run as part of the +# standard Python test suite since it requires several meg of email messages +# collected in the wild. These source messages are not checked into the +# Python distro, but are available as part of the standalone email package at +# http://sf.net/projects/mimelib + +import sys +import os +import unittest +from io import StringIO +from types import ListType + +from email.test.test_email import TestEmailBase +from test.test_support import TestSkipped + +import email +from email import __file__ as testfile +from email.Iterators import _structure + +def openfile(filename): + from os.path import join, dirname, abspath + path = abspath(join(dirname(testfile), os.pardir, 'moredata', filename)) + return open(path, 'r') + +# Prevent this test from running in the Python distro +try: + openfile('crispin-torture.txt') +except IOError: + raise TestSkipped + + + +class TortureBase(TestEmailBase): + def _msgobj(self, filename): + fp = openfile(filename) + try: + msg = email.message_from_file(fp) + finally: + fp.close() + return msg + + + +class TestCrispinTorture(TortureBase): + # Mark Crispin's torture test from the SquirrelMail project + def test_mondo_message(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + msg = self._msgobj('crispin-torture.txt') + payload = msg.get_payload() + eq(type(payload), ListType) + eq(len(payload), 12) + eq(msg.preamble, None) + eq(msg.epilogue, '\n') + # Probably the best way to verify the message is parsed correctly is to + # dump its structure and compare it against the known structure. + fp = StringIO() + _structure(msg, fp=fp) + neq(fp.getvalue(), """\ +multipart/mixed + text/plain + message/rfc822 + multipart/alternative + text/plain + multipart/mixed + text/richtext + application/andrew-inset + message/rfc822 + audio/basic + audio/basic + image/pbm + message/rfc822 + multipart/mixed + multipart/mixed + text/plain + audio/x-sun + multipart/mixed + image/gif + image/gif + application/x-be2 + application/atomicmail + audio/x-sun + message/rfc822 + multipart/mixed + text/plain + image/pgm + text/plain + message/rfc822 + multipart/mixed + text/plain + image/pbm + message/rfc822 + application/postscript + image/gif + message/rfc822 + multipart/mixed + audio/basic + audio/basic + message/rfc822 + multipart/mixed + application/postscript + text/plain + message/rfc822 + multipart/mixed + text/plain + multipart/parallel + image/gif + audio/basic + application/atomicmail + message/rfc822 + audio/x-sun +""") + + +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(): + test_support.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 00000000000..404cd9698c5 --- /dev/null +++ b/Lib/email/utils.py @@ -0,0 +1,325 @@ +# Copyright (C) 2001-2007 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 urllib +import warnings +from io 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 = '' +CRLF = '\r\n' +TICK = "'" + +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""" + parts = s.split(TICK, 2) + if len(parts) <= 2: + return None, None, s + return parts + + +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 (param name, string value). + """ + # Copy params so we don't mess with the original + params = params[:] + new_params = [] + # Map parameter's name to a list of continuations. The values are a + # 3-tuple of the continuation number, the string value, and a flag + # specifying whether a particular segment is %-encoded. + rfc2231_params = {} + name, value = params.pop(0) + new_params.append((name, value)) + while params: + name, value = params.pop(0) + if name.endswith('*'): + encoded = True + else: + encoded = False + 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_params.setdefault(name, []).append((num, value, encoded)) + else: + new_params.append((name, '"%s"' % quote(value))) + if rfc2231_params: + for name, continuations in rfc2231_params.items(): + value = [] + extended = False + # Sort by number + continuations.sort() + # And now append all values in numerical order, converting + # %-encodings for the encoded segments. If any of the + # continuation names ends in a *, then the entire string, after + # decoding segments and concatenating, must have the charset and + # language specifiers at the beginning of the string. + for num, s, encoded in continuations: + if encoded: + s = urllib.unquote(s) + extended = True + value.append(s) + value = quote(EMPTYSTRING.join(value)) + if extended: + charset, language, value = decode_rfc2231(value) + new_params.append((name, (charset, language, '"%s"' % value))) + else: + new_params.append((name, '"%s"' % value)) + return new_params + +def collapse_rfc2231_value(value, errors='replace', + fallback_charset='us-ascii'): + if not isinstance(value, tuple) or len(value) != 3: + return unquote(value) + # While value comes to us as a unicode string, we need it to be a bytes + # object. We do not want bytes() normal utf-8 decoder, we want a straight + # interpretation of the string as character bytes. + charset, language, text = value + rawbytes = bytes(ord(c) for c in text) + try: + return str(rawbytes, charset, errors) + except LookupError: + # charset is not a known codec. + return unquote(text)