diff --git a/Doc/library/http.client.rst b/Doc/library/http.client.rst index 2835c8d0eb7..75aa818ab9f 100644 --- a/Doc/library/http.client.rst +++ b/Doc/library/http.client.rst @@ -125,7 +125,7 @@ This module provides the following function: Parse the headers from a file pointer *fp* representing a HTTP request/response. The file has to be a :class:`~io.BufferedIOBase` reader - (i.e. not text) and must provide a valid :rfc:`2822` style header. + (i.e. not text) and must provide a valid :rfc:`5322` style header. This function returns an instance of :class:`http.client.HTTPMessage` that holds the header fields, but no payload diff --git a/Doc/library/http.server.rst b/Doc/library/http.server.rst index 02016c789b2..41026e2b303 100644 --- a/Doc/library/http.server.rst +++ b/Doc/library/http.server.rst @@ -154,7 +154,7 @@ instantiation, of which this module provides three different variants: variable. This instance parses and manages the headers in the HTTP request. The :func:`~http.client.parse_headers` function from :mod:`http.client` is used to parse the headers and it requires that the - HTTP request provide a valid :rfc:`2822` style header. + HTTP request provide a valid :rfc:`5322` style header. .. attribute:: rfile diff --git a/Doc/library/mailbox.rst b/Doc/library/mailbox.rst index e8a96f29ea1..62e289573c0 100644 --- a/Doc/library/mailbox.rst +++ b/Doc/library/mailbox.rst @@ -917,7 +917,7 @@ Supported mailbox formats are Maildir, mbox, MH, Babyl, and MMDF. copied; furthermore, any format-specific information is converted insofar as possible if *message* is a :class:`!Message` instance. If *message* is a string, a byte string, - or a file, it should contain an :rfc:`2822`\ -compliant message, which is read + or a file, it should contain an :rfc:`5322`\ -compliant message, which is read and parsed. Files should be open in binary mode, but text mode files are accepted for backward compatibility. diff --git a/Doc/library/time.rst b/Doc/library/time.rst index a9901010570..43e402a4bf9 100644 --- a/Doc/library/time.rst +++ b/Doc/library/time.rst @@ -570,7 +570,7 @@ Functions calculations when the day of the week and the year are specified. Here is an example, a format for dates compatible with that specified in the - :rfc:`2822` Internet email standard. [1]_ :: + :rfc:`5322` Internet email standard. [1]_ :: >>> from time import gmtime, strftime >>> strftime("%a, %d %b %Y %H:%M:%S +0000", gmtime()) @@ -1052,4 +1052,5 @@ Timezone Constants strict reading of the original 1982 :rfc:`822` standard calls for a two-digit year (``%y`` rather than ``%Y``), but practice moved to 4-digit years long before the year 2000. After that, :rfc:`822` became obsolete and the 4-digit year has - been first recommended by :rfc:`1123` and then mandated by :rfc:`2822`. + been first recommended by :rfc:`1123` and then mandated by :rfc:`2822`, + with :rfc:`5322` continuing this requirement. diff --git a/Doc/tutorial/stdlib.rst b/Doc/tutorial/stdlib.rst index 4b3eef313e7..fc98ffaadee 100644 --- a/Doc/tutorial/stdlib.rst +++ b/Doc/tutorial/stdlib.rst @@ -335,7 +335,7 @@ sophisticated and robust capabilities of its larger packages. For example: names, no direct knowledge or handling of XML is needed. * The :mod:`email` package is a library for managing email messages, including - MIME and other :rfc:`2822`-based message documents. Unlike :mod:`smtplib` and + MIME and other :rfc:`5322`-based message documents. Unlike :mod:`smtplib` and :mod:`poplib` which actually send and receive messages, the email package has a complete toolset for building or decoding complex message structures (including attachments) and for implementing internet encoding and header diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py index 84917038874..6a7c5fa06d2 100644 --- a/Lib/email/_parseaddr.py +++ b/Lib/email/_parseaddr.py @@ -146,8 +146,9 @@ def _parsedate_tz(data): 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 + # calls for a two-digit yy, but RFC 2822 (which obsoletes RFC 822) already + # mandated a 4-digit yy, and RFC 5322 (which obsoletes RFC 2822) continues + # this requirement. For more information, see the documentation for # the time module. if yy < 100: # The year is between 1969 and 1999 (inclusive). @@ -233,9 +234,11 @@ class AddrlistClass: 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. + # Note that RFC 2822 section 4.1 introduced '.' as obs-phrase to handle + # existing practice (periods in display names), even though it was not + # allowed in RFC 822. RFC 5322 section 4.1 (which obsoletes RFC 2822) + # continues this requirement. We must recognize obsolete syntax, so + # allow dots in phrases. self.phraseends = self.atomends.replace('.', '') self.field = field self.commentlist = [] diff --git a/Lib/email/_policybase.py b/Lib/email/_policybase.py index 95e79b8938b..e23843df448 100644 --- a/Lib/email/_policybase.py +++ b/Lib/email/_policybase.py @@ -380,7 +380,7 @@ class Compat32(Policy): h = value if h is not None: # The Header class interprets a value of None for maxlinelen as the - # default value of 78, as recommended by RFC 2822. + # default value of 78, as recommended by RFC 5322 section 2.1.1. maxlinelen = 0 if self.max_line_length is not None: maxlinelen = self.max_line_length diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py index 9d80a5822af..6479b9bab7a 100644 --- a/Lib/email/feedparser.py +++ b/Lib/email/feedparser.py @@ -32,7 +32,7 @@ NLCRE = re.compile(r'\r\n|\r|\n') NLCRE_bol = re.compile(r'(\r\n|\r|\n)') NLCRE_eol = re.compile(r'(\r\n|\r|\n)\z') NLCRE_crack = re.compile(r'(\r\n|\r|\n)') -# RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character +# RFC 5322 section 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]*:|[\t ])') EMPTYSTRING = '' @@ -294,7 +294,7 @@ class FeedParser: return if self._cur.get_content_maintype() == 'message': # The message claims to be a message/* type, then what follows is - # another RFC 2822 message. + # another RFC 5322 message. for retval in self._parsegen(): if retval is NeedMoreData: yield NeedMoreData diff --git a/Lib/email/generator.py b/Lib/email/generator.py index ab5bd0653e4..03524c96559 100644 --- a/Lib/email/generator.py +++ b/Lib/email/generator.py @@ -50,7 +50,7 @@ class Generator: 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. + by RFC 5322 section 2.1.1. The policy keyword specifies a policy object that controls a number of aspects of the generator's operation. If no policy is specified, diff --git a/Lib/email/message.py b/Lib/email/message.py index 36e4b4a9f0b..2505d17ef15 100644 --- a/Lib/email/message.py +++ b/Lib/email/message.py @@ -135,7 +135,7 @@ def _decode_uu(encoded): class Message: """Basic message object. - A message object is defined as something that has a bunch of RFC 2822 + A message object is defined as something that has a bunch of RFC 5322 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 diff --git a/Lib/email/parser.py b/Lib/email/parser.py index 039f03cba74..c6a51dd8e37 100644 --- a/Lib/email/parser.py +++ b/Lib/email/parser.py @@ -2,7 +2,7 @@ # Author: Barry Warsaw, Thomas Wouters, Anthony Baxter # Contact: email-sig@python.org -"""A parser of RFC 2822 and MIME email messages.""" +"""A parser of RFC 5322 and MIME email messages.""" __all__ = ['Parser', 'HeaderParser', 'BytesParser', 'BytesHeaderParser', 'FeedParser', 'BytesFeedParser'] @@ -15,13 +15,13 @@ from email._policybase import compat32 class Parser: def __init__(self, _class=None, *, policy=compat32): - """Parser of RFC 2822 and MIME email messages. + """Parser of RFC 5322 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 + The string must be formatted as a block of RFC 5322 headers and header continuation lines, optionally preceded by a 'Unix-from' header. The header block is terminated either by the end of the string or by a blank line. @@ -75,13 +75,13 @@ class HeaderParser(Parser): class BytesParser: def __init__(self, *args, **kw): - """Parser of binary RFC 2822 and MIME email messages. + """Parser of binary RFC 5322 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 input must be formatted as a block of RFC 2822 headers and header + The input must be formatted as a block of RFC 5322 headers and header continuation lines, optionally preceded by a 'Unix-from' header. The header block is terminated either by the end of the input or by a blank line. diff --git a/Lib/http/client.py b/Lib/http/client.py index 33a858d34ae..cf19440f7b0 100644 --- a/Lib/http/client.py +++ b/Lib/http/client.py @@ -230,7 +230,7 @@ def _read_headers(fp): def _parse_header_lines(header_lines, _class=HTTPMessage): """ - Parses only RFC2822 headers from header lines. + Parses only RFC 5322 headers from header lines. email Parser wants to see strings rather than bytes. But a TextIOWrapper around self.rfile would buffer too many bytes @@ -243,7 +243,7 @@ def _parse_header_lines(header_lines, _class=HTTPMessage): return email.parser.Parser(_class=_class).parsestr(hstring) def parse_headers(fp, _class=HTTPMessage): - """Parses only RFC2822 headers from a file pointer.""" + """Parses only RFC 5322 headers from a file pointer.""" headers = _read_headers(fp) return _parse_header_lines(headers, _class) diff --git a/Lib/smtplib.py b/Lib/smtplib.py index 808f0fd47e8..72093f7f8b0 100644 --- a/Lib/smtplib.py +++ b/Lib/smtplib.py @@ -917,7 +917,7 @@ class SMTP: The arguments are as for sendmail, except that msg is an email.message.Message object. If from_addr is None or to_addrs is None, these arguments are taken from the headers of the Message as - described in RFC 2822 (a ValueError is raised if there is more than + described in RFC 5322 (a ValueError is raised if there is more than one set of 'Resent-' headers). Regardless of the values of from_addr and to_addr, any Bcc field (or Resent-Bcc field, when the Message is a resent) of the Message object won't be transmitted. The Message @@ -931,7 +931,7 @@ class SMTP: policy. """ - # 'Resent-Date' is a mandatory field if the Message is resent (RFC 2822 + # 'Resent-Date' is a mandatory field if the Message is resent (RFC 5322 # Section 3.6.6). In such a case, we use the 'Resent-*' fields. However, # if there is more than one 'Resent-' block there's no way to # unambiguously determine which one is the most recent in all cases, @@ -950,7 +950,7 @@ class SMTP: else: raise ValueError("message has more than one 'Resent-' header block") if from_addr is None: - # Prefer the sender field per RFC 2822:3.6.2. + # Prefer the sender field per RFC 5322 section 3.6.2. from_addr = (msg[header_prefix + 'Sender'] if (header_prefix + 'Sender') in msg else msg[header_prefix + 'From']) diff --git a/Lib/test/test_email/data/msg_35.txt b/Lib/test/test_email/data/msg_35.txt index be7d5a2f7b9..0e2bbcaf718 100644 --- a/Lib/test/test_email/data/msg_35.txt +++ b/Lib/test/test_email/data/msg_35.txt @@ -1,4 +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 +counter to RFC 5322, there's no separating newline here diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py index b8116d073a2..9f2dc1bb7e6 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -2352,7 +2352,7 @@ From: aperson@dom.ain To: bperson@dom.ain Subject: here's something interesting -counter to RFC 2822, there's no separating newline here +counter to RFC 5322, there's no separating newline here """) # test_defect_handling @@ -2508,49 +2508,49 @@ Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar =?mac-iceland?q?r=8Aksm?= [(b'andr\xe9=zz', 'iso-8859-1')]) def test_rfc2047_rfc2047_1(self): - # 1st testcase at end of rfc2047 + # 1st testcase at end of RFC 2047 s = '(=?ISO-8859-1?Q?a?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'a', 'iso-8859-1'), (b')', None)]) def test_rfc2047_rfc2047_2(self): - # 2nd testcase at end of rfc2047 + # 2nd testcase at end of RFC 2047 s = '(=?ISO-8859-1?Q?a?= b)' self.assertEqual(decode_header(s), [(b'(', None), (b'a', 'iso-8859-1'), (b' b)', None)]) def test_rfc2047_rfc2047_3(self): - # 3rd testcase at end of rfc2047 + # 3rd testcase at end of RFC 2047 s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)]) def test_rfc2047_rfc2047_4(self): - # 4th testcase at end of rfc2047 + # 4th testcase at end of RFC 2047 s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)]) def test_rfc2047_rfc2047_5a(self): - # 5th testcase at end of rfc2047 newline is \r\n + # 5th testcase at end of RFC 2047 newline is \r\n s = '(=?ISO-8859-1?Q?a?=\r\n =?ISO-8859-1?Q?b?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)]) def test_rfc2047_rfc2047_5b(self): - # 5th testcase at end of rfc2047 newline is \n + # 5th testcase at end of RFC 2047 newline is \n s = '(=?ISO-8859-1?Q?a?=\n =?ISO-8859-1?Q?b?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)]) def test_rfc2047_rfc2047_6(self): - # 6th testcase at end of rfc2047 + # 6th testcase at end of RFC 2047 s = '(=?ISO-8859-1?Q?a_b?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'a b', 'iso-8859-1'), (b')', None)]) def test_rfc2047_rfc2047_7(self): - # 7th testcase at end of rfc2047 + # 7th testcase at end of RFC 2047 s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)' self.assertEqual(decode_header(s), [(b'(', None), (b'a', 'iso-8859-1'), (b' b', 'iso-8859-2'), @@ -3252,8 +3252,8 @@ class TestMiscellaneous(TestEmailBase): """Test for parsing a date with a two-digit year. Parsing a date with a two-digit year should return the correct - four-digit year. RFC822 allows two-digit years, but RFC2822 (which - obsoletes RFC822) requires four-digit years. + four-digit year. RFC 822 allows two-digit years, but RFC 5322 (which + obsoletes RFC 2822, which obsoletes RFC 822) requires four-digit years. """ self.assertEqual(utils.parsedate_tz('25 Feb 03 13:47:26 -0800'), @@ -3304,7 +3304,7 @@ class TestMiscellaneous(TestEmailBase): self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b)) def test_quotes_unicode_names(self): - # issue 1690608. email.utils.formataddr() should be rfc2047 aware. + # issue 1690608. email.utils.formataddr() should be RFC 2047 aware. name = "H\u00e4ns W\u00fcrst" addr = 'person@dom.ain' utf8_base64 = "=?utf-8?b?SMOkbnMgV8O8cnN0?= " @@ -3314,7 +3314,7 @@ class TestMiscellaneous(TestEmailBase): latin1_quopri) def test_accepts_any_charset_like_object(self): - # issue 1690608. email.utils.formataddr() should be rfc2047 aware. + # issue 1690608. email.utils.formataddr() should be RFC 2047 aware. name = "H\u00e4ns W\u00fcrst" addr = 'person@dom.ain' utf8_base64 = "=?utf-8?b?SMOkbnMgV8O8cnN0?= " @@ -3329,7 +3329,7 @@ class TestMiscellaneous(TestEmailBase): utf8_base64) def test_invalid_charset_like_object_raises_error(self): - # issue 1690608. email.utils.formataddr() should be rfc2047 aware. + # issue 1690608. email.utils.formataddr() should be RFC 2047 aware. name = "H\u00e4ns W\u00fcrst" addr = 'person@dom.ain' # An object without a header_encode method: @@ -3338,7 +3338,7 @@ class TestMiscellaneous(TestEmailBase): bad_charset) def test_unicode_address_raises_error(self): - # issue 1690608. email.utils.formataddr() should be rfc2047 aware. + # issue 1690608. email.utils.formataddr() should be RFC 2047 aware. addr = 'pers\u00f6n@dom.in' self.assertRaises(UnicodeError, utils.formataddr, (None, addr)) self.assertRaises(UnicodeError, utils.formataddr, ("Name", addr)) @@ -3359,7 +3359,7 @@ class TestMiscellaneous(TestEmailBase): # string containing a quoted backslash, followed by 'example' and two # backslashes, followed by another quoted string containing a space and # the word 'example'. parseaddr copies those two backslashes - # literally. Per rfc5322 this is not technically correct since a \ may + # literally. Per RFC 5322 this is not technically correct since a \ may # not appear in an address outside of a quoted string. It is probably # a sensible Postel interpretation, though. eq = self.assertEqual @@ -3371,12 +3371,12 @@ class TestMiscellaneous(TestEmailBase): ('', '"\\\\"example\\\\" example"@example.com')) def test_parseaddr_preserves_spaces_in_local_part(self): - # issue 9286. A normal RFC5322 local part should not contain any + # issue 9286. A normal RFC 5322 local part should not contain any # folding white space, but legacy local parts can (they are a sequence # of atoms, not dotatoms). On the other hand we strip whitespace from # before the @ and around dots, on the assumption that the whitespace # around the punctuation is a mistake in what would otherwise be - # an RFC5322 local part. Leading whitespace is, usual, stripped as well. + # an RFC 5322 local part. Leading whitespace is, usual, stripped as well. self.assertEqual(('', "merwok wok@xample.com"), utils.parseaddr("merwok wok@xample.com")) self.assertEqual(('', "merwok wok@xample.com"),