summaryrefslogtreecommitdiffstats
path: root/Lib/email/utils.py
blob: b82d5c578b0b797cb3cc4a01814600e9deb50f53 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
# Copyright (C) 2001-2010 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',
    'format_datetime',
    'getaddresses',
    'make_msgid',
    'mktime_tz',
    'parseaddr',
    'parsedate',
    'parsedate_tz',
    'parsedate_to_datetime',
    'unquote',
    ]

import os
import re
import time
import base64
import random
import socket
import datetime
import urllib.parse
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 email._parseaddr import _parsedate_tz as __parsedate_tz

from quopri import decodestring as _qdecode

# Intrapackage imports
from email.encoders import _bencode, _qencode
from email.charset import Charset

COMMASPACE = ', '
EMPTYSTRING = ''
UEMPTYSTRING = ''
CRLF = '\r\n'
TICK = "'"

specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')

# How to figure out if we are processing strings that come from a byte
# source with undecodable characters.
_has_surrogates = re.compile(
    '([^\ud800-\udbff]|\A)[\udc00-\udfff]([^\udc00-\udfff]|\Z)').search


# Helpers

def formataddr(pair, charset='utf-8'):
    """The inverse of parseaddr(), this takes a 2-tuple of the form
    (realname, email_address) and returns the string value suitable
    for an RFC 2822 From, To or Cc header.

    If the first element of pair is false, then the second element is
    returned unmodified.

    Optional charset if given is the character set that is used to encode
    realname in case realname is not ASCII safe.  Can be an instance of str or
    a Charset-like object which has a header_encode method.  Default is
    'utf-8'.
    """
    name, address = pair
    # The address MUST (per RFC) be ascii, so throw a UnicodeError if it isn't.
    address.encode('ascii')
    if name:
        try:
            name.encode('ascii')
        except UnicodeEncodeError:
            if isinstance(charset, str):
                charset = Charset(charset)
            encoded_name = charset.header_encode(name)
            return "%s <%s>" % (encoded_name, address)
        else:
            quotes = ''
            if specialsre.search(name):
                quotes = '"'
            name = escapesre.sub(r'\\\g<0>', 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<charset>[^?]*?)   # non-greedy up to the next ? is the charset
  \?                    # literal ?
  (?P<encoding>[qb])    # either a "q" or a "b", case insensitive
  \?                    # literal ?
  (?P<atom>.*?)         # non-greedy up to the next ?= is the atom
  \?=                   # literal ?=
  ''', re.VERBOSE | re.IGNORECASE)


def _format_timetuple_and_zone(timetuple, zone):
    return '%s, %02d %s %04d %02d:%02d:%02d %s' % (
        ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][timetuple[6]],
        timetuple[2],
        ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
         'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][timetuple[1] - 1],
        timetuple[0], timetuple[3], timetuple[4], timetuple[5],
        zone)

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 _format_timetuple_and_zone(now, zone)

def format_datetime(dt, usegmt=False):
    """Turn a datetime into a date string as specified in RFC 2822.

    If usegmt is True, dt must be an aware datetime with an offset of zero.  In
    this case 'GMT' will be rendered instead of the normal +0000 required by
    RFC2822.  This is to support HTTP headers involving date stamps.
    """
    now = dt.timetuple()
    if usegmt:
        if dt.tzinfo is None or dt.tzinfo != datetime.timezone.utc:
            raise ValueError("usegmt option requires a UTC datetime")
        zone = 'GMT'
    elif dt.tzinfo is None:
        zone = '-0000'
    else:
        zone = dt.strftime("%z")
    return _format_timetuple_and_zone(now, zone)


def make_msgid(idstring=None, domain=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.  Optional domain if given provides the
    portion of the message id after the '@'.  It defaults to the locally
    defined hostname.
    """
    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
    if domain is None:
        domain = socket.getfqdn()
    msgid = '<%s.%s.%s%s@%s>' % (utcdate, pid, randint, idstring, domain)
    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 parsedate_to_datetime(data):
    if not data:
        return None
    *dtuple, tz = __parsedate_tz(data)
    if tz is None:
        return datetime.datetime(*dtuple[:6])
    return datetime.datetime(*dtuple[:6],
            tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))


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.
    """
    s = urllib.parse.quote(s, safe='', encoding=charset or 'ascii')
    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<name>\w+)\*((?P<num>[0-9]+)\*?)?$',
    re.ASCII)

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:
                    # Decode as "latin-1", so the characters in s directly
                    # represent the percent-encoded octet values.
                    # collapse_rfc2231_value treats this as an octet sequence.
                    s = urllib.parse.unquote(s, encoding="latin-1")
                    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(text, 'raw-unicode-escape')
    try:
        return str(rawbytes, charset, errors)
    except LookupError:
        # charset is not a known codec.
        return unquote(text)