diff options
Diffstat (limited to 'modules/language/python/module/email')
-rw-r--r-- | modules/language/python/module/email/_parseaddr.py | 541 | ||||
-rw-r--r-- | modules/language/python/module/email/base64mime.py | 119 | ||||
-rw-r--r-- | modules/language/python/module/email/charset.py | 408 | ||||
-rw-r--r-- | modules/language/python/module/email/encoders.py | 67 | ||||
-rw-r--r-- | modules/language/python/module/email/errors.py | 111 | ||||
-rw-r--r-- | modules/language/python/module/email/header.py | 579 | ||||
-rw-r--r-- | modules/language/python/module/email/quoprimime.py | 300 |
7 files changed, 2125 insertions, 0 deletions
diff --git a/modules/language/python/module/email/_parseaddr.py b/modules/language/python/module/email/_parseaddr.py new file mode 100644 index 0000000..0f53dab --- /dev/null +++ b/modules/language/python/module/email/_parseaddr.py @@ -0,0 +1,541 @@ +module(email,_parseaddr) +# 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, calendar + +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. + """ + res = _parsedate_tz(data) + if not res: + return + if res[9] is None: + res[9] = 0 + return tuple(res) + +def _parsedate_tz(data): + """Convert date to extended time tuple. + + The last (additional) element is the time zone offset in seconds, except if + the timezone was specified as -0000. In that case the last element is + None. This indicates a UTC timestamp that explicitly declaims knowledge of + the source timezone, as opposed to a +0000 timestamp that indicates the + source timezone really was UTC. + + """ + if not data: + return + 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 == -1: + i = s.find('-') + if i > 0: + data[3:] = [s[:i], s[i:]] + 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 + elif len(tm) == 1 and '.' in tm[0]: + # Some non-compliant MUAs use '.' to separate time elements. + tm = tm[0].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 + # Check for a yy specified in two-digit format, then convert it to the + # appropriate four-digit format, according to the POSIX standard. RFC 822 + # calls for a two-digit yy, but RFC 2822 (which obsoletes RFC 822) + # mandates a 4-digit yy. For more information, see the documentation for + # the time module. + if yy < 100: + # The year is between 1969 and 1999 (inclusive). + if yy > 68: + yy += 1900 + # The year is between 2000 and 2068 (inclusive). + else: + yy += 2000 + tzoffset = None + tz = tz.upper() + if tz in _timezones: + tzoffset = _timezones[tz] + else: + try: + tzoffset = int(tz) + except ValueError: + pass + if tzoffset==0 and tz.startswith('-'): + tzoffset = None + # 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 POSIX timestamp.""" + if data[9] is None: + # No zone info, so localtime is better assumption than GMT + return time.mktime(data[:8] + (-1,)) + else: + t = calendar.timegm(data) + return t - data[9] + + +def quote(str): + """Prepare string to be used in a quoted string. + + Turns backslash and double quote characters into quoted pairs. These + are the only characters that need to be quoted inside a quoted string. + Does not add the surrounding double quotes. + """ + 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 email.utils.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): + """Skip white space and extract comments.""" + wslist = [] + while self.pos < len(self.field): + if self.field[self.pos] in self.LWS + '\n\r': + if self.field[self.pos] not in '\n\r': + wslist.append(self.field[self.pos]) + self.pos += 1 + elif self.field[self.pos] == '(': + self.commentlist.append(self.getcomment()) + else: + break + return EMPTYSTRING.join(wslist) + + 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): + preserve_ws = True + if self.field[self.pos] == '.': + if aslist and not aslist[-1].strip(): + aslist.pop() + aslist.append('.') + self.pos += 1 + preserve_ws = False + elif self.field[self.pos] == '"': + aslist.append('"%s"' % quote(self.getquote())) + elif self.field[self.pos] in self.atomends: + if aslist and not aslist[-1].strip(): + aslist.pop() + break + else: + aslist.append(self.getatom()) + ws = self.gotonext() + if preserve_ws and ws: + aslist.append(ws) + + 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/modules/language/python/module/email/base64mime.py b/modules/language/python/module/email/base64mime.py new file mode 100644 index 0000000..26eb1ad --- /dev/null +++ b/modules/language/python/module/email/base64mime.py @@ -0,0 +1,119 @@ +module(email,base64mime) + +# 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__ = [ + 'body_decode', + 'body_encode', + 'decode', + 'decodestring', + 'header_encode', + 'header_length', + ] + +from base64 import b64encode +from binascii import b2a_base64, a2b_base64 + +CRLF = '\r\n' +NL = '\n' +EMPTYSTRING = '' + +# See also Charset.py +MISC_LEN = 7 + + +# Helpers +def header_length(bytearray): + """Return the length of s when it is encoded with base64.""" + groups_of_3, leftover = divmod(len(bytearray), 3) + # 4 bytes out for each 3 bytes (or nonzero fraction thereof) in. + n = groups_of_3 * 4 + if leftover: + n += 4 + return n + + + +def header_encode(header_bytes, charset='iso-8859-1'): + """Encode a single header line with Base64 encoding in a given charset. + + charset names the character set to use to encode the header. It defaults + to iso-8859-1. Base64 encoding is defined in RFC 2045. + """ + if not header_bytes: + return "" + if isinstance(header_bytes, str): + header_bytes = header_bytes.encode(charset) + encoded = b64encode(header_bytes).decode("ascii") + return '=?%s?b?%s?=' % (charset, encoded) + + + +def body_encode(s, maxlinelen=76, eol=NL): + r"""Encode a string with base64. + + Each line will be wrapped at, at most, maxlinelen characters (defaults to + 76 characters). + + 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 + + encvec = [] + max_unencoded = maxlinelen * 3 // 4 + for i in range(0, len(s), max_unencoded): + # BAW: should encode() inherit b2a_base64()'s dubious behavior in + # adding a newline to the encoded string? + enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii") + if enc.endswith(NL) and eol != NL: + enc = enc[:-1] + eol + encvec.append(enc) + return EMPTYSTRING.join(encvec) + + + +def decode(string): + """Decode a raw base64 string, returning a bytes object. + + This function does not parse a full MIME header value encoded with + base64 (like =?iso-8859-1?b?bmloISBuaWgh?=) -- please use the high + level email.header class for that functionality. + """ + if not string: + return bytes() + elif isinstance(string, str): + return a2b_base64(string.encode('raw-unicode-escape')) + else: + return a2b_base64(string) + + +# For convenience and backwards compatibility w/ standard base64 module +body_decode = decode +decodestring = decode diff --git a/modules/language/python/module/email/charset.py b/modules/language/python/module/email/charset.py new file mode 100644 index 0000000..ba5a444 --- /dev/null +++ b/modules/language/python/module/email/charset.py @@ -0,0 +1,408 @@ +module(email,charset) + +# 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', + ] + +from functools import partial + +import email.base64mime as base64mime +import email.quoprimime as quoprimime + +import email.errors as 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 +RFC2047_CHROME_LEN = 7 + +DEFAULT_CHARSET = 'us-ascii' +UNKNOWN8BIT = 'unknown-8bit' +EMPTYSTRING = '' + + + +# 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 + + + +# Convenience function for encoding strings, taking into account +# that they might be unknown-8bit (ie: have surrogate-escaped bytes) +def _encode(string, codec): + if codec == UNKNOWN8BIT: + return string.encode('ascii', 'surrogateescape') + else: + return string.encode(codec) + + + +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 they 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 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 conversion function 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 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 header_encode(self, string): + """Header-encode a string by converting it first to bytes. + + The type of encoding (base64 or quoted-printable) will be based on + this charset's `header_encoding`. + + :param string: A unicode string for the header. It must be possible + to encode this string to bytes using the character set's + output codec. + :return: The encoded string, with RFC 2047 chrome. + """ + codec = self.output_codec or 'us-ascii' + header_bytes = _encode(string, codec) + # 7bit/8bit encodings return the string unchanged (modulo conversions) + encoder_module = self._get_encoder(header_bytes) + if encoder_module is None: + return string + return encoder_module.header_encode(header_bytes, codec) + + def header_encode_lines(self, string, maxlengths): + """Header-encode a string by converting it first to bytes. + + This is similar to `header_encode()` except that the string is fit + into maximum line lengths as given by the argument. + + :param string: A unicode string for the header. It must be possible + to encode this string to bytes using the character set's + output codec. + :param maxlengths: Maximum line length iterator. Each element + returned from this iterator will provide the next maximum line + length. This parameter is used as an argument to built-in next() + and should never be exhausted. The maximum line lengths should + not count the RFC 2047 chrome. These line lengths are only a + hint; the splitter does the best it can. + :return: Lines of encoded strings, each with RFC 2047 chrome. + """ + # See which encoding we should use. + codec = self.output_codec or 'us-ascii' + header_bytes = _encode(string, codec) + encoder_module = self._get_encoder(header_bytes) + encoder = partial(encoder_module.header_encode, charset=codec) + # Calculate the number of characters that the RFC 2047 chrome will + # contribute to each line. + charset = self.get_output_charset() + extra = len(charset) + RFC2047_CHROME_LEN + # Now comes the hard part. We must encode bytes but we can't split on + # bytes because some character sets are variable length and each + # encoded word must stand on its own. So the problem is you have to + # encode to bytes to figure out this word's length, but you must split + # on characters. This causes two problems: first, we don't know how + # many octets a specific substring of unicode characters will get + # encoded to, and second, we don't know how many ASCII characters + # those octets will get encoded to. Unless we try it. Which seems + # inefficient. In the interest of being correct rather than fast (and + # in the hope that there will be few encoded headers in any such + # message), brute force it. :( + lines = [] + current_line = [] + maxlen = next(maxlengths) - extra + for character in string: + current_line.append(character) + this_line = EMPTYSTRING.join(current_line) + length = encoder_module.header_length(_encode(this_line, charset)) + if length > maxlen: + # This last character doesn't fit so pop it off. + current_line.pop() + # Does nothing fit on the first line? + if not lines and not current_line: + lines.append(None) + else: + separator = (' ' if lines else '') + joined_line = EMPTYSTRING.join(current_line) + header_bytes = _encode(joined_line, codec) + lines.append(encoder(header_bytes)) + current_line = [character] + maxlen = next(maxlengths) - extra + joined_line = EMPTYSTRING.join(current_line) + header_bytes = _encode(joined_line, codec) + lines.append(encoder(header_bytes)) + return lines + + def _get_encoder(self, header_bytes): + if self.header_encoding == BASE64: + return base64mime + elif self.header_encoding == QP: + return quoprimime + elif self.header_encoding == SHORTEST: + len64 = base64mime.header_length(header_bytes) + lenqp = quoprimime.header_length(header_bytes) + if len64 < lenqp: + return base64mime + else: + return quoprimime + else: + return None + + def body_encode(self, string): + """Body-encode a string by converting it first to bytes. + + The type of encoding (base64 or quoted-printable) will be based on + self.body_encoding. If body_encoding is None, we assume the + output charset is a 7bit encoding, so re-encoding the decoded + string using the ascii codec produces the correct string version + of the content. + """ + if not string: + return string + if self.body_encoding is BASE64: + if isinstance(string, str): + string = string.encode(self.output_charset) + return base64mime.body_encode(string) + elif self.body_encoding is QP: + # quopromime.body_encode takes a string, but operates on it as if + # it were a list of byte codes. For a (minimal) history on why + # this is so, see changeset 0cf700464177. To correctly encode a + # character set, then, we must turn it into pseudo bytes via the + # latin1 charset, which will encode any byte as a single code point + # between 0 and 255, which is what body_encode is expecting. + if isinstance(string, str): + string = string.encode(self.output_charset) + string = string.decode('latin1') + return quoprimime.body_encode(string) + else: + if isinstance(string, str): + string = string.encode(self.output_charset).decode('ascii') + return string diff --git a/modules/language/python/module/email/encoders.py b/modules/language/python/module/email/encoders.py new file mode 100644 index 0000000..e4eb928 --- /dev/null +++ b/modules/language/python/module/email/encoders.py @@ -0,0 +1,67 @@ +module(email,encoders) + +# 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', + ] + + +from base64 import encodebytes as _bencode +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(b' ', b'=20') + + +def encode_base64(msg): + """Encode the message's payload in Base64. + + Also, add an appropriate Content-Transfer-Encoding header. + """ + orig = msg.get_payload(decode=True) + encdata = str(_bencode(orig), 'ascii') + 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(decode=True) + 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(decode=True) + 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 decoding from ASCII succeeds, + # we know the data must be 7bit, otherwise treat it as 8bit. + try: + orig.decode('ascii') + except UnicodeError: + msg['Content-Transfer-Encoding'] = '8bit' + else: + msg['Content-Transfer-Encoding'] = '7bit' + + +def encode_noop(msg): + """Do nothing.""" diff --git a/modules/language/python/module/email/errors.py b/modules/language/python/module/email/errors.py new file mode 100644 index 0000000..c877442 --- /dev/null +++ b/modules/language/python/module/email/errors.py @@ -0,0 +1,111 @@ +module(email,errors) +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""email package exception classes.""" + +__all__=['MessageError', + 'MessageParseError', + 'HeaderParseError'] + +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(ValueError): + """Base class for a message defect.""" + + def __init__(self, line=None): + if line is not None: + super().__init__(line) + 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 CloseBoundaryNotFoundDefect(MessageDefect): + """A start boundary was found, but not the corresponding close boundary.""" + +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 MissingHeaderBodySeparatorDefect(MessageDefect): + """Found line with no leading whitespace and no colon before blank line.""" +# XXX: backward compatibility, just in case (it was never emitted). +MalformedHeaderDefect = MissingHeaderBodySeparatorDefect + +class MultipartInvariantViolationDefect(MessageDefect): + """A message claimed to be a multipart but no subparts were found.""" + +class InvalidMultipartContentTransferEncodingDefect(MessageDefect): + """An invalid content transfer encoding was set on the multipart itself.""" + +class UndecodableBytesDefect(MessageDefect): + """Header contained bytes that could not be decoded""" + +class InvalidBase64PaddingDefect(MessageDefect): + """base64 encoded sequence had an incorrect length""" + +class InvalidBase64CharactersDefect(MessageDefect): + """base64 encoded sequence had characters not in base64 alphabet""" + +# These errors are specific to header parsing. + +class HeaderDefect(MessageDefect): + """Base class for a header defect.""" + + def __init__(self, *args, **kw): + super().__init__(*args, **kw) + +class InvalidHeaderDefect(HeaderDefect): + """Header is not valid, message gives details.""" + +class HeaderMissingRequiredValue(HeaderDefect): + """A header that must have a value had none""" + +class NonPrintableDefect(HeaderDefect): + """ASCII characters outside the ascii-printable range found""" + + def __init__(self, non_printables): + super().__init__(non_printables) + self.non_printables = non_printables + + def __str__(self): + return ("the following ASCII non-printables found in header: " + "{}".format(self.non_printables)) + +class ObsoleteHeaderDefect(HeaderDefect): + """Header uses syntax declared obsolete by RFC 5322""" + +class NonASCIILocalPartDefect(HeaderDefect): + """local_part contains non-ASCII characters""" + # This defect only occurs during unicode parsing, not when + # parsing messages decoded from binary. diff --git a/modules/language/python/module/email/header.py b/modules/language/python/module/email/header.py new file mode 100644 index 0000000..ac3f46c --- /dev/null +++ b/modules/language/python/module/email/header.py @@ -0,0 +1,579 @@ +module(email,header) +# 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 as quoprimime +import email.base64mime as base64mime + +from email.errors import HeaderParseError +import email.charset as _charset +Charset = _charset.Charset + +NL = '\n' +SPACE = ' ' +BSPACE = b' ' +SPACE8 = ' ' * 8 +EMPTYSTRING = '' +MAXLINELEN = 78 +FWS = ' \t' + +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<charset>[^?]*?) # non-greedy up to the next ? is the charset + \? # literal ? + (?P<encoding>[qb]) # either a "q" or a "b", case insensitive + \? # literal ? + (?P<encoded>.*?) # non-greedy up to the next ?= is the encoded string + \?= # literal ?= + ''', 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]+:$') + +# Find a header embedded in a putative header value. Used to check for +# header injection attack. +_embedded_header = re.compile(r'\n[^ \t]+:') + + + +# Helpers +_max_append = 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. + + header may be a string that may or may not contain RFC2047 encoded words, + or it may be a Header object. + + An email.errors.HeaderParseError may be raised when certain decoding error + occurs (e.g. a base64 decoding exception). + """ + # If it is a Header object, we can just return the encoded chunks. + if hasattr(header, '_chunks'): + return [(_charset._encode(string, str(charset)), str(charset)) + for string, charset in header._chunks] + # 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) + first = True + while parts: + unencoded = parts.pop(0) + if first: + unencoded = unencoded.lstrip() + first = False + 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)) + # Now loop over words and remove words that consist of whitespace + # between two encoded strings. + droplist = [] + for n, w in enumerate(words): + if n>1 and w[1] and words[n-2][1] and words[n-1][0].isspace(): + droplist.append(n-1) + for d in reversed(droplist): + del words[d] + + # 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 = quoprimime.header_decode(encoded_string) + decoded_words.append((word, charset)) + elif encoding == 'b': + paderr = len(encoded_string) % 4 # Postel's law: add missing padding + if paderr: + encoded_string += '==='[:4 - paderr] + try: + word = 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(word, 'raw-unicode-escape') + 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 explicitly 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 78 as recommended + by RFC 2822. + + 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.""" + self._normalize() + uchunks = [] + lastcs = None + lastspace = None + for string, 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. + # Don't add a space if the None/us-ascii string already has + # a space (trailing or leading depending on transition) + nextcs = charset + if nextcs == _charset.UNKNOWN8BIT: + original_bytes = string.encode('ascii', 'surrogateescape') + string = original_bytes.decode('ascii', 'replace') + if uchunks: + hasspace = string and self._nonctext(string[0]) + if lastcs not in (None, 'us-ascii'): + if nextcs in (None, 'us-ascii') and not hasspace: + uchunks.append(SPACE) + nextcs = None + elif nextcs not in (None, 'us-ascii') and not lastspace: + uchunks.append(SPACE) + lastspace = string and self._nonctext(string[-1]) + lastcs = nextcs + uchunks.append(string) + 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 unicode (of the unencoded header value), swap the + # args and do another comparison. + return other == str(self) + + 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 false), 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 either case, when producing an RFC 2822 compliant + header using RFC 2047 rules, the string will be encoded using the + output codec of the charset. If the string cannot be encoded to the + output codec, a UnicodeError will be raised. + + Optional `errors' is passed as the errors argument to the decode + call if s is a byte string. + """ + if charset is None: + charset = self._charset + elif not isinstance(charset, Charset): + charset = Charset(charset) + if not isinstance(s, str): + input_charset = charset.input_codec or 'us-ascii' + if input_charset == _charset.UNKNOWN8BIT: + s = s.decode('us-ascii', 'surrogateescape') + else: + s = s.decode(input_charset, errors) + # Ensure that the bytes we're storing can be decoded to the output + # character set, otherwise an early error is raised. + output_charset = charset.output_codec or 'us-ascii' + if output_charset != _charset.UNKNOWN8BIT: + try: + s.encode(output_charset, errors) + except UnicodeEncodeError: + if output_charset!='us-ascii': + raise + charset = UTF8 + self._chunks.append((s, charset)) + + def _nonctext(self, s): + """True if string s is not a ctext character of RFC822. + """ + return s.isspace() or s in ('(', ')', '\\') + + def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'): + r"""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. + + Optional maxlinelen specifies the maximum length of each generated + line, exclusive of the linesep string. Individual lines may be longer + than maxlinelen if a folding point cannot be found. The first line + will be shorter by the length of the header name plus ": " if a header + name was specified at Header construction time. The default value for + maxlinelen is determined at header construction time. + + Optional splitchars is a string containing characters which should be + given extra weight by the splitting algorithm during normal header + wrapping. This is in very rough support of RFC 2822's `higher level + syntactic breaks': split points preceded by a splitchar are preferred + during line splitting, with the characters preferred in the order in + which they appear in the string. Space and tab may be included in the + string to indicate whether preference should be given to one over the + other as a split point when other split chars do not appear in the line + being split. Splitchars does not affect RFC 2047 encoded lines. + + Optional linesep is a string to be used to separate the lines of + the value. The default value is the most useful for typical + Python applications, but it can be set to \r\n to produce RFC-compliant + line separators when needed. + """ + self._normalize() + if maxlinelen is None: + maxlinelen = self._maxlinelen + # A maxlinelen of 0 means don't wrap. For all practical purposes, + # choosing a huge number here accomplishes that and makes the + # _ValueFormatter algorithm much simpler. + if maxlinelen == 0: + maxlinelen = 1000000 + formatter = _ValueFormatter(self._headerlen, maxlinelen, + self._continuation_ws, splitchars) + lastcs = None + hasspace = lastspace = None + for string, charset in self._chunks: + if hasspace is not None: + hasspace = string and self._nonctext(string[0]) + if lastcs not in (None, 'us-ascii'): + if not hasspace or charset not in (None, 'us-ascii'): + formatter.add_transition() + elif charset not in (None, 'us-ascii') and not lastspace: + formatter.add_transition() + lastspace = string and self._nonctext(string[-1]) + lastcs = charset + hasspace = False + lines = string.splitlines() + if lines: + formatter.feed('', lines[0], charset) + else: + formatter.feed('', '', charset) + for line in lines[1:]: + formatter.newline() + if charset.header_encoding is not None: + formatter.feed(self._continuation_ws, ' ' + line.lstrip(), + charset) + else: + sline = line.lstrip() + fws = line[:len(line)-len(sline)] + formatter.feed(fws, sline, charset) + if len(lines) > 1: + formatter.newline() + if self._chunks: + formatter.add_transition() + value = formatter._str(linesep) + if _embedded_header.search(value): + raise HeaderParseError("header value appears to contain " + "an embedded header: {!r}".format(value)) + return value + + def _normalize(self): + # Step 1: Normalize the chunks so that all runs of identical charsets + # get collapsed into a single unicode string. + 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)) + 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) + self._splitchars = splitchars + self._lines = [] + self._current_line = _Accumulator(headerlen) + + def _str(self, linesep): + self.newline() + return linesep.join(self._lines) + + def __str__(self): + return self._str(NL) + + def newline(self): + end_of_line = self._current_line.pop() + if end_of_line != (' ', ''): + self._current_line.push(*end_of_line) + if len(self._current_line) > 0: + if self._current_line.is_onlyws(): + self._lines[-1] += str(self._current_line) + else: + self._lines.append(str(self._current_line)) + self._current_line.reset() + + def add_transition(self): + self._current_line.push(' ', '') + + def feed(self, fws, string, charset): + # If the charset has no header encoding (i.e. it is an ASCII encoding) + # then we must split the header 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, this should be pluggable. + if charset.header_encoding is None: + self._ascii_split(fws, string, self._splitchars) + return + # Otherwise, we're doing either a Base64 or a quoted-printable + # encoding which means we don't need to split the line on syntactic + # breaks. We can basically just find enough characters to fit on the + # current line, minus the RFC 2047 chrome. What makes this trickier + # though is that we have to split at octet boundaries, not character + # boundaries but it's only safe to split at character boundaries so at + # best we can only get close. + encoded_lines = charset.header_encode_lines(string, self._maxlengths()) + # The first element extends the current line, but if it's None then + # nothing more fit on the current line so start a new line. + try: + first_line = encoded_lines.pop(0) + except IndexError: + # There are no encoded lines, so we're done. + return + if first_line is not None: + self._append_chunk(fws, first_line) + try: + last_line = encoded_lines.pop() + except IndexError: + # There was only one line. + return + self.newline() + self._current_line.push(self._continuation_ws, last_line) + # Everything else are full lines in themselves. + for line in encoded_lines: + self._lines.append(self._continuation_ws + line) + + def _maxlengths(self): + # The first line's length. + yield self._maxlen - len(self._current_line) + while True: + yield self._maxlen - self._continuation_ws_len + + def _ascii_split(self, fws, string, splitchars): + # The RFC 2822 header folding algorithm is simple in principle but + # complex in practice. Lines may be folded any place where "folding + # white space" appears by inserting a linesep character in front of the + # FWS. The complication is that not all spaces or tabs qualify as FWS, + # and we are also supposed to prefer to break at "higher level + # syntactic breaks". We can't do either of these without intimate + # knowledge of the structure of structured headers, which we don't have + # here. So the best we can do here is prefer to break at the specified + # splitchars, and hope that we don't choose any spaces or tabs that + # aren't legal FWS. (This is at least better than the old algorithm, + # where we would sometimes *introduce* FWS after a splitchar, or the + # algorithm before that, where we would turn all white space runs into + # single spaces or tabs.) + parts = re.split("(["+FWS+"]+)", fws+string) + if parts[0]: + parts[:0] = [''] + else: + parts.pop(0) + for fws, part in zip(*[iter(parts)]*2): + self._append_chunk(fws, part) + + def _append_chunk(self, fws, string): + self._current_line.push(fws, string) + if len(self._current_line) > self._maxlen: + # Find the best split point, working backward from the end. + # There might be none, on a long first line. + for ch in self._splitchars: + for i in range(self._current_line.part_count()-1, 0, -1): + if ch.isspace(): + fws = self._current_line[i][0] + if fws and fws[0]==ch: + break + prevpart = self._current_line[i-1][1] + if prevpart and prevpart[-1]==ch: + break + else: + continue + break + else: + fws, part = self._current_line.pop() + if self._current_line._initial_size > 0: + # There will be a header, so leave it on a line by itself. + self.newline() + if not fws: + # We don't use continuation_ws here because the whitespace + # after a header should always be a space. + fws = ' ' + self._current_line.push(fws, part) + return + remainder = self._current_line.pop_from(i) + self._lines.append(str(self._current_line)) + self._current_line.reset(remainder) + + +class _Accumulator(list): + + def __init__(self, initial_size=0): + self._initial_size = initial_size + super().__init__() + + def push(self, fws, string): + self.append((fws, string)) + + def pop_from(self, i=0): + popped = self[i:] + self[i:] = [] + return popped + + def pop(self): + if self.part_count()==0: + return ('', '') + return super().pop() + + def __len__(self): + return sum((len(fws)+len(part) for fws, part in self), + self._initial_size) + + def __str__(self): + return EMPTYSTRING.join((EMPTYSTRING.join((fws, part)) + for fws, part in self)) + + def reset(self, startval=None): + if startval is None: + startval = [] + self[:] = startval + self._initial_size = 0 + + def is_onlyws(self): + return self._initial_size==0 and (not self or str(self).isspace()) + + def part_count(self): + return super().__len__() diff --git a/modules/language/python/module/email/quoprimime.py b/modules/language/python/module/email/quoprimime.py new file mode 100644 index 0000000..21b6a6b --- /dev/null +++ b/modules/language/python/module/email/quoprimime.py @@ -0,0 +1,300 @@ +module(email,quoprimime) +# 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_length', + 'decode', + 'decodestring', + 'header_decode', + 'header_encode', + 'header_length', + 'quote', + 'unquote', + ] + +import re + +from string import ascii_letters, digits, hexdigits + +CRLF = '\r\n' +NL = '\n' +EMPTYSTRING = '' + +# Build a mapping of octets to the expansion of that octet. Since we're only +# going to have 256 of these things, this isn't terribly inefficient +# space-wise. Remember that headers and bodies have different sets of safe +# characters. Initialize both maps with the full expansion, and then override +# the safe bytes with the more compact form. +_QUOPRI_MAP = ['=%02X' % c for c in range(256)] +_QUOPRI_HEADER_MAP = _QUOPRI_MAP[:] +_QUOPRI_BODY_MAP = _QUOPRI_MAP[:] + +# Safe header bytes which need no encoding. +for c in b'-!*+/' + ascii_letters.encode('ascii') + digits.encode('ascii'): + _QUOPRI_HEADER_MAP[c] = chr(c) +# Headers have one other special encoding; spaces become underscores. +_QUOPRI_HEADER_MAP[ord(' ')] = '_' + +# Safe body bytes which need no encoding. +for c in (b' !"#$%&\'()*+,-./0123456789:;<>' + b'?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`' + b'abcdefghijklmnopqrstuvwxyz{|}~\t'): + _QUOPRI_BODY_MAP[c] = chr(c) + + + +# Helpers +def header_check(octet): + """Return True if the octet should be escaped with header quopri.""" + return chr(octet) != _QUOPRI_HEADER_MAP[octet] + + +def body_check(octet): + """Return True if the octet should be escaped with body quopri.""" + return chr(octet) != _QUOPRI_BODY_MAP[octet] + + +def header_length(bytearray): + """Return a header quoted-printable encoding length. + + Note that this does not include any RFC 2047 chrome added by + `header_encode()`. + + :param bytearray: An array of bytes (a.k.a. octets). + :return: The length in bytes of the byte array when it is encoded with + quoted-printable for headers. + """ + return sum(len(_QUOPRI_HEADER_MAP[octet]) for octet in bytearray) + + +def body_length(bytearray): + """Return a body quoted-printable encoding length. + + :param bytearray: An array of bytes (a.k.a. octets). + :return: The length in bytes of the byte array when it is encoded with + quoted-printable for bodies. + """ + return sum(len(_QUOPRI_BODY_MAP[octet]) for octet in bytearray) + + +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 _QUOPRI_MAP[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 as an empty string. + if not header_bytes: + return '' + # Iterate over every byte, encoding if necessary. + encoded = header_bytes.decode('latin1').translate(_QUOPRI_HEADER_MAP) + # Now add the RFC chrome to each encoded chunk and glue the chunks + # together. + return '=?%s?q?%s?=' % (charset, encoded) + + +_QUOPRI_BODY_ENCODE_MAP = _QUOPRI_BODY_MAP[:] +for c in b'\r\n': + _QUOPRI_BODY_ENCODE_MAP[c] = chr(c) + +def body_encode(body, maxlinelen=76, eol=NL): + """Encode with quoted-printable, wrapping at maxlinelen characters. + + 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 before the + eol string (maxlinelen defaults to 76 characters, the maximum value + permitted by RFC 2045). Long lines will have the 'soft line break' + quoted-printable character "=" appended to them, so the decoded text will + be identical to the original text. + + The minimum maxlinelen is 4 to have room for a quoted character ("=XX") + followed by a soft line break. Smaller values will generate a + ValueError. + + """ + + if maxlinelen < 4: + raise ValueError("maxlinelen must be at least 4") + if not body: + return body + + # quote special characters + body = body.translate(_QUOPRI_BODY_ENCODE_MAP) + + soft_break = '=' + eol + # leave space for the '=' at the end of a line + maxlinelen1 = maxlinelen - 1 + + encoded_body = [] + append = encoded_body.append + + for line in body.splitlines(): + # break up the line into pieces no longer than maxlinelen - 1 + start = 0 + laststart = len(line) - 1 - maxlinelen + while start <= laststart: + stop = start + maxlinelen1 + # make sure we don't break up an escape sequence + if line[stop - 2] == '=': + append(line[start:stop - 1]) + start = stop - 2 + elif line[stop - 1] == '=': + append(line[start:stop]) + start = stop - 1 + else: + append(line[start:stop] + '=') + start = stop + + # handle rest of line, special case if line ends in whitespace + if line and line[-1] in ' \t': + room = start - laststart + if room >= 3: + # It's a whitespace character at end-of-line, and we have room + # for the three-character quoted encoding. + q = quote(line[-1]) + elif room == 2: + # There's room for the whitespace character and a soft break. + q = line[-1] + soft_break + else: + # There's room only for a soft break. The quoted whitespace + # will be the only content on the subsequent line. + q = soft_break + quote(line[-1]) + append(line[start:-1] + q) + else: + append(line[start:]) + + # add back final newline if present + if body[-1] in CRLF: + append('') + + return eol.join(encoded_body) + + + +# 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 encoded[-1] not in '\r\n' 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-8859-1?q?Hello_World?=) -- please use + the high level email.header class for that functionality. + """ + s = s.replace('_', ' ') + return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, flags=re.ASCII) |