From 97d8dda980fcddf88b782be343118257f483a864 Mon Sep 17 00:00:00 2001 From: Guo Ci Date: Tue, 4 Nov 2025 14:29:13 -0500 Subject: [PATCH 1/5] Docs: Fix typo in `email.headerregistry.rst` (#140965) Fix missing 'Header' suffix on header class name in `email.headerregistry.rst` --- Doc/library/email.headerregistry.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Doc/library/email.headerregistry.rst b/Doc/library/email.headerregistry.rst index 7f8044932fae993..ff8b601fe3d1bb1 100644 --- a/Doc/library/email.headerregistry.rst +++ b/Doc/library/email.headerregistry.rst @@ -294,7 +294,7 @@ variant, :attr:`~.BaseHeader.max_count` is set to 1. ``inline`` and ``attachment`` are the only valid values in common use. -.. class:: ContentTransferEncoding +.. class:: ContentTransferEncodingHeader Handles the :mailheader:`Content-Transfer-Encoding` header. From ce1bb85d286130f44b7e874430b0b12990d61dc1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Filip=20=C5=81ajszczak?= Date: Tue, 4 Nov 2025 20:46:07 +0100 Subject: [PATCH 2/5] gh-139434: Update selected RFC 2822 references to RFC 5322 (#139435) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update selected RFC 2822 references to RFC 5322 RFC 2822 was obsoleted by RFC 5322 in 2008. This updates references to use the current standard in documentation, docstrings, and comments. It preserves RFC 2822 references in legacy API components to maintain their historical context. RFC 822 → RFC 2822 → RFC 5322 progression is explained where relevant. In some places specific sections of RFC are referenced where it seems helpful. Scout rule was applied in some places and RFC mentions format was normalized in doc strings and comments. --- Doc/library/http.client.rst | 2 +- Doc/library/http.server.rst | 2 +- Doc/library/mailbox.rst | 2 +- Doc/library/time.rst | 5 ++-- Doc/tutorial/stdlib.rst | 2 +- Lib/email/_parseaddr.py | 13 +++++++---- Lib/email/_policybase.py | 2 +- Lib/email/feedparser.py | 4 ++-- Lib/email/generator.py | 2 +- Lib/email/message.py | 2 +- Lib/email/parser.py | 10 ++++---- Lib/http/client.py | 4 ++-- Lib/smtplib.py | 6 ++--- Lib/test/test_email/data/msg_35.txt | 2 +- Lib/test/test_email/test_email.py | 36 ++++++++++++++--------------- 15 files changed, 49 insertions(+), 45 deletions(-) diff --git a/Doc/library/http.client.rst b/Doc/library/http.client.rst index 589152f29686b61..7c258b324d98674 100644 --- a/Doc/library/http.client.rst +++ b/Doc/library/http.client.rst @@ -133,7 +133,7 @@ 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 063344e02842584..58f09634f95e0f0 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 e8a96f29ea185e6..62e289573c0c7e0 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 350ffade7af5fa6..69e6433e8987034 100644 --- a/Doc/library/time.rst +++ b/Doc/library/time.rst @@ -584,7 +584,7 @@ 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()) @@ -1066,4 +1066,5 @@ 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 d83ecca270b1602..49a3e370a4c018e 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 84917038874ba1f..6a7c5fa06d20b6e 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 @@ def __init__(self, field): 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 95e79b8938bb4c1..e23843df44881f3 100644 --- a/Lib/email/_policybase.py +++ b/Lib/email/_policybase.py @@ -380,7 +380,7 @@ def _fold(self, name, value, sanitize): 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 9d80a5822af48db..6479b9bab7ac5bd 100644 --- a/Lib/email/feedparser.py +++ b/Lib/email/feedparser.py @@ -32,7 +32,7 @@ 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 @@ def _parsegen(self): 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 ab5bd0653e440c4..03524c965591538 100644 --- a/Lib/email/generator.py +++ b/Lib/email/generator.py @@ -50,7 +50,7 @@ def __init__(self, outfp, mangle_from_=None, maxheaderlen=None, *, 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 4380e0ec50b46a3..641fb2e944d4311 100644 --- a/Lib/email/message.py +++ b/Lib/email/message.py @@ -141,7 +141,7 @@ 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 039f03cba74fa0c..c6a51dd8e377b81 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 @@ 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 @@ def parsestr(self, text, headersonly=True): 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 425d9bdad8cdb5c..4b9a61cfc1159f9 100644 --- a/Lib/http/client.py +++ b/Lib/http/client.py @@ -231,7 +231,7 @@ def _read_headers(fp, max_headers): 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 @@ -244,7 +244,7 @@ def _parse_header_lines(header_lines, _class=HTTPMessage): return email.parser.Parser(_class=_class).parsestr(hstring) def parse_headers(fp, _class=HTTPMessage, *, _max_headers=None): - """Parses only RFC2822 headers from a file pointer.""" + """Parses only RFC 5322 headers from a file pointer.""" headers = _read_headers(fp, _max_headers) return _parse_header_lines(headers, _class) diff --git a/Lib/smtplib.py b/Lib/smtplib.py index 808f0fd47e8b4ea..72093f7f8b0f2dd 100644 --- a/Lib/smtplib.py +++ b/Lib/smtplib.py @@ -917,7 +917,7 @@ def send_message(self, msg, from_addr=None, to_addrs=None, 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 @@ def send_message(self, msg, from_addr=None, to_addrs=None, 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 @@ def send_message(self, msg, from_addr=None, to_addrs=None, 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 be7d5a2f7b9d383..0e2bbcaf71816a3 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 b458d3f0efaabda..4cd587bcd760407 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -2373,7 +2373,7 @@ def test_no_separating_blank_line(self): 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 @@ -2529,49 +2529,49 @@ def test_rfc2047_Q_invalid_digits(self): [(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'), @@ -3273,8 +3273,8 @@ def test_parsedate_y2k(self): """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'), @@ -3325,7 +3325,7 @@ def test_escape_backslashes(self): 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?= " @@ -3335,7 +3335,7 @@ def test_quotes_unicode_names(self): 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?= " @@ -3350,7 +3350,7 @@ def header_encode(self, string): 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: @@ -3359,7 +3359,7 @@ def test_invalid_charset_like_object_raises_error(self): 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)) @@ -3380,7 +3380,7 @@ def test_parseaddr_preserves_quoted_pairs_in_addresses(self): # 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 @@ -3392,12 +3392,12 @@ def test_parseaddr_preserves_quoted_pairs_in_addresses(self): ('', '"\\\\"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"), From bfe54810c408ff066591d1af0411b1d9c10084b1 Mon Sep 17 00:00:00 2001 From: Stan Ulbrych <89152624+StanFromIreland@users.noreply.github.com> Date: Tue, 4 Nov 2025 21:19:06 +0000 Subject: [PATCH 3/5] gh-141004: Document `Py_UNICODE_{HIGH, LOW}_SURROGATE` functions (GH-141019) --- Doc/c-api/unicode.rst | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/Doc/c-api/unicode.rst b/Doc/c-api/unicode.rst index 22b0a6aff6e02e8..ca7c8bb11a5d78a 100644 --- a/Doc/c-api/unicode.rst +++ b/Doc/c-api/unicode.rst @@ -321,12 +321,22 @@ These APIs can be used to work with surrogates: Check if *ch* is a low surrogate (``0xDC00 <= ch <= 0xDFFF``). +.. c:function:: Py_UCS4 Py_UNICODE_HIGH_SURROGATE(Py_UCS4 ch) + + Return the high UTF-16 surrogate (``0xD800`` to ``0xDBFF``) for a Unicode + code point in the range ``[0x10000; 0x10FFFF]``. + +.. c:function:: Py_UCS4 Py_UNICODE_LOW_SURROGATE(Py_UCS4 ch) + + Return the low UTF-16 surrogate (``0xDC00`` to ``0xDFFF``) for a Unicode + code point in the range ``[0x10000; 0x10FFFF]``. + .. c:function:: Py_UCS4 Py_UNICODE_JOIN_SURROGATES(Py_UCS4 high, Py_UCS4 low) Join two surrogate code points and return a single :c:type:`Py_UCS4` value. *high* and *low* are respectively the leading and trailing surrogates in a - surrogate pair. *high* must be in the range [0xD800; 0xDBFF] and *low* must - be in the range [0xDC00; 0xDFFF]. + surrogate pair. *high* must be in the range ``[0xD800; 0xDBFF]`` and *low* must + be in the range ``[0xDC00; 0xDFFF]``. Creating and accessing Unicode strings From d81e1ef0f3a7c63f5d246e4cf918700016b72489 Mon Sep 17 00:00:00 2001 From: Petr Viktorin Date: Tue, 4 Nov 2025 22:58:53 +0100 Subject: [PATCH 4/5] gh-138189: Document type slots, and other constants, as part of Limited API (GH-138190) Co-authored-by: Peter Bierma --- Doc/c-api/typeobj.rst | 200 ++++++++++++++++++++++++++ Doc/data/stable_abi.dat | 153 ++++++++++++++++++++ Doc/tools/.nitignore | 1 - Doc/tools/extensions/c_annotations.py | 76 +++++++++- Misc/stable_abi.toml | 4 + Tools/build/stable_abi.py | 2 +- 6 files changed, 430 insertions(+), 6 deletions(-) diff --git a/Doc/c-api/typeobj.rst b/Doc/c-api/typeobj.rst index 59c26a713e4d85a..9d23aea5734ea39 100644 --- a/Doc/c-api/typeobj.rst +++ b/Doc/c-api/typeobj.rst @@ -676,6 +676,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: destructor PyTypeObject.tp_dealloc + .. corresponding-type-slot:: Py_tp_dealloc + A pointer to the instance destructor function. The function signature is:: void tp_dealloc(PyObject *self); @@ -860,6 +862,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: getattrfunc PyTypeObject.tp_getattr + .. corresponding-type-slot:: Py_tp_getattr + An optional pointer to the get-attribute-string function. This field is deprecated. When it is defined, it should point to a function @@ -877,6 +881,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: setattrfunc PyTypeObject.tp_setattr + .. corresponding-type-slot:: Py_tp_setattr + An optional pointer to the function for setting and deleting attributes. This field is deprecated. When it is defined, it should point to a function @@ -909,6 +915,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: reprfunc PyTypeObject.tp_repr + .. corresponding-type-slot:: Py_tp_repr + .. index:: pair: built-in function; repr An optional pointer to a function that implements the built-in function @@ -974,6 +982,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: hashfunc PyTypeObject.tp_hash + .. corresponding-type-slot:: Py_tp_hash + .. index:: pair: built-in function; hash An optional pointer to a function that implements the built-in function @@ -1015,6 +1025,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: ternaryfunc PyTypeObject.tp_call + .. corresponding-type-slot:: Py_tp_call + An optional pointer to a function that implements calling the object. This should be ``NULL`` if the object is not callable. The signature is the same as for :c:func:`PyObject_Call`:: @@ -1028,6 +1040,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: reprfunc PyTypeObject.tp_str + .. corresponding-type-slot:: Py_tp_str + An optional pointer to a function that implements the built-in operation :func:`str`. (Note that :class:`str` is a type now, and :func:`str` calls the constructor for that type. This constructor calls :c:func:`PyObject_Str` to do @@ -1053,6 +1067,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: getattrofunc PyTypeObject.tp_getattro + .. corresponding-type-slot:: Py_tp_getattro + An optional pointer to the get-attribute function. The signature is the same as for :c:func:`PyObject_GetAttr`:: @@ -1077,6 +1093,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: setattrofunc PyTypeObject.tp_setattro + .. corresponding-type-slot:: Py_tp_setattro + An optional pointer to the function for setting and deleting attributes. The signature is the same as for :c:func:`PyObject_SetAttr`:: @@ -1475,6 +1493,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: const char* PyTypeObject.tp_doc + .. corresponding-type-slot:: Py_tp_doc + An optional pointer to a NUL-terminated C string giving the docstring for this type object. This is exposed as the :attr:`~type.__doc__` attribute on the type and instances of the type. @@ -1486,6 +1506,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: traverseproc PyTypeObject.tp_traverse + .. corresponding-type-slot:: Py_tp_traverse + An optional pointer to a traversal function for the garbage collector. This is only used if the :c:macro:`Py_TPFLAGS_HAVE_GC` flag bit is set. The signature is:: @@ -1582,6 +1604,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: inquiry PyTypeObject.tp_clear + .. corresponding-type-slot:: Py_tp_clear + An optional pointer to a clear function. The signature is:: int tp_clear(PyObject *); @@ -1730,6 +1754,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: richcmpfunc PyTypeObject.tp_richcompare + .. corresponding-type-slot:: Py_tp_richcompare + An optional pointer to the rich comparison function, whose signature is:: PyObject *tp_richcompare(PyObject *self, PyObject *other, int op); @@ -1832,6 +1858,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: getiterfunc PyTypeObject.tp_iter + .. corresponding-type-slot:: Py_tp_iter + An optional pointer to a function that returns an :term:`iterator` for the object. Its presence normally signals that the instances of this type are :term:`iterable` (although sequences may be iterable without this function). @@ -1847,6 +1875,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: iternextfunc PyTypeObject.tp_iternext + .. corresponding-type-slot:: Py_tp_iternext + An optional pointer to a function that returns the next item in an :term:`iterator`. The signature is:: @@ -1870,6 +1900,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: struct PyMethodDef* PyTypeObject.tp_methods + .. corresponding-type-slot:: Py_tp_methods + An optional pointer to a static ``NULL``-terminated array of :c:type:`PyMethodDef` structures, declaring regular methods of this type. @@ -1884,6 +1916,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: struct PyMemberDef* PyTypeObject.tp_members + .. corresponding-type-slot:: Py_tp_members + An optional pointer to a static ``NULL``-terminated array of :c:type:`PyMemberDef` structures, declaring regular data members (fields or slots) of instances of this type. @@ -1899,6 +1933,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: struct PyGetSetDef* PyTypeObject.tp_getset + .. corresponding-type-slot:: Py_tp_getset + An optional pointer to a static ``NULL``-terminated array of :c:type:`PyGetSetDef` structures, declaring computed attributes of instances of this type. @@ -1913,6 +1949,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: PyTypeObject* PyTypeObject.tp_base + .. corresponding-type-slot:: Py_tp_base + An optional pointer to a base type from which type properties are inherited. At this level, only single inheritance is supported; multiple inheritance require dynamically creating a type object by calling the metatype. @@ -1985,6 +2023,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: descrgetfunc PyTypeObject.tp_descr_get + .. corresponding-type-slot:: Py_tp_descr_get + An optional pointer to a "descriptor get" function. The function signature is:: @@ -2000,6 +2040,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: descrsetfunc PyTypeObject.tp_descr_set + .. corresponding-type-slot:: Py_tp_descr_set + An optional pointer to a function for setting and deleting a descriptor's value. @@ -2060,6 +2102,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: initproc PyTypeObject.tp_init + .. corresponding-type-slot:: Py_tp_init + An optional pointer to an instance initialization function. This function corresponds to the :meth:`~object.__init__` method of classes. Like @@ -2095,6 +2139,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: allocfunc PyTypeObject.tp_alloc + .. corresponding-type-slot:: Py_tp_alloc + An optional pointer to an instance allocation function. The function signature is:: @@ -2118,6 +2164,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: newfunc PyTypeObject.tp_new + .. corresponding-type-slot:: Py_tp_new + An optional pointer to an instance creation function. The function signature is:: @@ -2157,6 +2205,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: freefunc PyTypeObject.tp_free + .. corresponding-type-slot:: Py_tp_free + An optional pointer to an instance deallocation function. Its signature is:: void tp_free(void *self); @@ -2186,6 +2236,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: inquiry PyTypeObject.tp_is_gc + .. corresponding-type-slot:: Py_tp_is_gc + An optional pointer to a function called by the garbage collector. The garbage collector needs to know whether a particular object is collectible @@ -2214,6 +2266,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: PyObject* PyTypeObject.tp_bases + .. corresponding-type-slot:: Py_tp_bases + Tuple of base types. This field should be set to ``NULL`` and treated as read-only. @@ -2294,6 +2348,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: destructor PyTypeObject.tp_del + .. corresponding-type-slot:: Py_tp_del + This field is deprecated. Use :c:member:`~PyTypeObject.tp_finalize` instead. @@ -2308,6 +2364,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: destructor PyTypeObject.tp_finalize + .. corresponding-type-slot:: Py_tp_finalize + An optional pointer to an instance finalization function. This is the C implementation of the :meth:`~object.__del__` special method. Its signature is:: @@ -2466,6 +2524,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: vectorcallfunc PyTypeObject.tp_vectorcall + .. corresponding-type-slot:: Py_tp_vectorcall + A :ref:`vectorcall function ` to use for calls of this type object (rather than instances). In other words, ``tp_vectorcall`` can be used to optimize ``type.__call__``, @@ -2631,42 +2691,148 @@ Number Object Structures Python 3.0.1. .. c:member:: binaryfunc PyNumberMethods.nb_add + + .. corresponding-type-slot:: Py_nb_add + .. c:member:: binaryfunc PyNumberMethods.nb_subtract + + .. corresponding-type-slot:: Py_nb_subtract + .. c:member:: binaryfunc PyNumberMethods.nb_multiply + + .. corresponding-type-slot:: Py_nb_multiply + .. c:member:: binaryfunc PyNumberMethods.nb_remainder + + .. corresponding-type-slot:: Py_nb_remainder + .. c:member:: binaryfunc PyNumberMethods.nb_divmod + + .. corresponding-type-slot:: Py_nb_divmod + .. c:member:: ternaryfunc PyNumberMethods.nb_power + + .. corresponding-type-slot:: Py_nb_power + .. c:member:: unaryfunc PyNumberMethods.nb_negative + + .. corresponding-type-slot:: Py_nb_negative + .. c:member:: unaryfunc PyNumberMethods.nb_positive + + .. corresponding-type-slot:: Py_nb_positive + .. c:member:: unaryfunc PyNumberMethods.nb_absolute + + .. corresponding-type-slot:: Py_nb_absolute + .. c:member:: inquiry PyNumberMethods.nb_bool + + .. corresponding-type-slot:: Py_nb_bool + .. c:member:: unaryfunc PyNumberMethods.nb_invert + + .. corresponding-type-slot:: Py_nb_invert + .. c:member:: binaryfunc PyNumberMethods.nb_lshift + + .. corresponding-type-slot:: Py_nb_lshift + .. c:member:: binaryfunc PyNumberMethods.nb_rshift + + .. corresponding-type-slot:: Py_nb_rshift + .. c:member:: binaryfunc PyNumberMethods.nb_and + + .. corresponding-type-slot:: Py_nb_and + .. c:member:: binaryfunc PyNumberMethods.nb_xor + + .. corresponding-type-slot:: Py_nb_xor + .. c:member:: binaryfunc PyNumberMethods.nb_or + + .. corresponding-type-slot:: Py_nb_or + .. c:member:: unaryfunc PyNumberMethods.nb_int + + .. corresponding-type-slot:: Py_nb_int + .. c:member:: void *PyNumberMethods.nb_reserved + .. c:member:: unaryfunc PyNumberMethods.nb_float + + .. corresponding-type-slot:: Py_nb_float + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_add + + .. corresponding-type-slot:: Py_nb_inplace_add + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_subtract + + .. corresponding-type-slot:: Py_nb_inplace_subtract + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_multiply + + .. corresponding-type-slot:: Py_nb_inplace_multiply + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_remainder + + .. corresponding-type-slot:: Py_nb_inplace_remainder + .. c:member:: ternaryfunc PyNumberMethods.nb_inplace_power + + .. corresponding-type-slot:: Py_nb_inplace_power + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_lshift + + .. corresponding-type-slot:: Py_nb_inplace_lshift + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_rshift + + .. corresponding-type-slot:: Py_nb_inplace_rshift + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_and + + .. corresponding-type-slot:: Py_nb_inplace_and + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_xor + + .. corresponding-type-slot:: Py_nb_inplace_xor + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_or + + .. corresponding-type-slot:: Py_nb_inplace_or + .. c:member:: binaryfunc PyNumberMethods.nb_floor_divide + + .. corresponding-type-slot:: Py_nb_floor_divide + .. c:member:: binaryfunc PyNumberMethods.nb_true_divide + + .. corresponding-type-slot:: Py_nb_true_divide + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_floor_divide + + .. corresponding-type-slot:: Py_nb_inplace_floor_divide + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_true_divide + + .. corresponding-type-slot:: Py_nb_inplace_true_divide + .. c:member:: unaryfunc PyNumberMethods.nb_index + + .. corresponding-type-slot:: Py_nb_index + .. c:member:: binaryfunc PyNumberMethods.nb_matrix_multiply + + .. corresponding-type-slot:: Py_nb_matrix_multiply + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_matrix_multiply + .. corresponding-type-slot:: Py_nb_inplace_matrix_multiply + + .. _mapping-structs: @@ -2683,12 +2849,16 @@ Mapping Object Structures .. c:member:: lenfunc PyMappingMethods.mp_length + .. corresponding-type-slot:: Py_mp_length + This function is used by :c:func:`PyMapping_Size` and :c:func:`PyObject_Size`, and has the same signature. This slot may be set to ``NULL`` if the object has no defined length. .. c:member:: binaryfunc PyMappingMethods.mp_subscript + .. corresponding-type-slot:: Py_mp_subscript + This function is used by :c:func:`PyObject_GetItem` and :c:func:`PySequence_GetSlice`, and has the same signature as :c:func:`!PyObject_GetItem`. This slot must be filled for the @@ -2697,6 +2867,8 @@ Mapping Object Structures .. c:member:: objobjargproc PyMappingMethods.mp_ass_subscript + .. corresponding-type-slot:: Py_mp_ass_subscript + This function is used by :c:func:`PyObject_SetItem`, :c:func:`PyObject_DelItem`, :c:func:`PySequence_SetSlice` and :c:func:`PySequence_DelSlice`. It has the same signature as @@ -2720,6 +2892,8 @@ Sequence Object Structures .. c:member:: lenfunc PySequenceMethods.sq_length + .. corresponding-type-slot:: Py_sq_length + This function is used by :c:func:`PySequence_Size` and :c:func:`PyObject_Size`, and has the same signature. It is also used for handling negative indices via the :c:member:`~PySequenceMethods.sq_item` @@ -2727,18 +2901,24 @@ Sequence Object Structures .. c:member:: binaryfunc PySequenceMethods.sq_concat + .. corresponding-type-slot:: Py_sq_concat + This function is used by :c:func:`PySequence_Concat` and has the same signature. It is also used by the ``+`` operator, after trying the numeric addition via the :c:member:`~PyNumberMethods.nb_add` slot. .. c:member:: ssizeargfunc PySequenceMethods.sq_repeat + .. corresponding-type-slot:: Py_sq_repeat + This function is used by :c:func:`PySequence_Repeat` and has the same signature. It is also used by the ``*`` operator, after trying numeric multiplication via the :c:member:`~PyNumberMethods.nb_multiply` slot. .. c:member:: ssizeargfunc PySequenceMethods.sq_item + .. corresponding-type-slot:: Py_sq_item + This function is used by :c:func:`PySequence_GetItem` and has the same signature. It is also used by :c:func:`PyObject_GetItem`, after trying the subscription via the :c:member:`~PyMappingMethods.mp_subscript` slot. @@ -2752,6 +2932,8 @@ Sequence Object Structures .. c:member:: ssizeobjargproc PySequenceMethods.sq_ass_item + .. corresponding-type-slot:: Py_sq_ass_item + This function is used by :c:func:`PySequence_SetItem` and has the same signature. It is also used by :c:func:`PyObject_SetItem` and :c:func:`PyObject_DelItem`, after trying the item assignment and deletion @@ -2761,6 +2943,8 @@ Sequence Object Structures .. c:member:: objobjproc PySequenceMethods.sq_contains + .. corresponding-type-slot:: Py_sq_contains + This function may be used by :c:func:`PySequence_Contains` and has the same signature. This slot may be left to ``NULL``, in this case :c:func:`!PySequence_Contains` simply traverses the sequence until it @@ -2768,6 +2952,8 @@ Sequence Object Structures .. c:member:: binaryfunc PySequenceMethods.sq_inplace_concat + .. corresponding-type-slot:: Py_sq_inplace_concat + This function is used by :c:func:`PySequence_InPlaceConcat` and has the same signature. It should modify its first operand, and return it. This slot may be left to ``NULL``, in this case :c:func:`!PySequence_InPlaceConcat` @@ -2777,6 +2963,8 @@ Sequence Object Structures .. c:member:: ssizeargfunc PySequenceMethods.sq_inplace_repeat + .. corresponding-type-slot:: Py_sq_inplace_repeat + This function is used by :c:func:`PySequence_InPlaceRepeat` and has the same signature. It should modify its first operand, and return it. This slot may be left to ``NULL``, in this case :c:func:`!PySequence_InPlaceRepeat` @@ -2802,6 +2990,8 @@ Buffer Object Structures .. c:member:: getbufferproc PyBufferProcs.bf_getbuffer + .. corresponding-type-slot:: Py_bf_getbuffer + The signature of this function is:: int (PyObject *exporter, Py_buffer *view, int flags); @@ -2851,6 +3041,8 @@ Buffer Object Structures .. c:member:: releasebufferproc PyBufferProcs.bf_releasebuffer + .. corresponding-type-slot:: Py_bf_releasebuffer + The signature of this function is:: void (PyObject *exporter, Py_buffer *view); @@ -2905,6 +3097,8 @@ Async Object Structures .. c:member:: unaryfunc PyAsyncMethods.am_await + .. corresponding-type-slot:: Py_am_await + The signature of this function is:: PyObject *am_await(PyObject *self); @@ -2916,6 +3110,8 @@ Async Object Structures .. c:member:: unaryfunc PyAsyncMethods.am_aiter + .. corresponding-type-slot:: Py_am_aiter + The signature of this function is:: PyObject *am_aiter(PyObject *self); @@ -2928,6 +3124,8 @@ Async Object Structures .. c:member:: unaryfunc PyAsyncMethods.am_anext + .. corresponding-type-slot:: Py_am_anext + The signature of this function is:: PyObject *am_anext(PyObject *self); @@ -2938,6 +3136,8 @@ Async Object Structures .. c:member:: sendfunc PyAsyncMethods.am_send + .. corresponding-type-slot:: Py_am_send + The signature of this function is:: PySendResult am_send(PyObject *self, PyObject *arg, PyObject **result); diff --git a/Doc/data/stable_abi.dat b/Doc/data/stable_abi.dat index 7ad5f3ecfab5b46..67b498c4268e2ec 100644 --- a/Doc/data/stable_abi.dat +++ b/Doc/data/stable_abi.dat @@ -1,7 +1,21 @@ role,name,added,ifdef_note,struct_abi_kind +macro,METH_CLASS,3.2,, +macro,METH_COEXIST,3.2,, +macro,METH_FASTCALL,3.7,, +macro,METH_METHOD,3.7,, +macro,METH_NOARGS,3.2,, +macro,METH_O,3.2,, +macro,METH_STATIC,3.2,, +macro,METH_VARARGS,3.2,, macro,PY_VECTORCALL_ARGUMENTS_OFFSET,3.12,, type,PyABIInfo,3.15,,full-abi func,PyABIInfo_Check,3.15,, +macro,PyABIInfo_DEFAULT_ABI_VERSION,3.15,, +macro,PyABIInfo_DEFAULT_FLAGS,3.15,, +macro,PyABIInfo_FREETHREADED,3.15,, +macro,PyABIInfo_FREETHREADING_AGNOSTIC,3.15,, +macro,PyABIInfo_GIL,3.15,, +macro,PyABIInfo_STABLE,3.15,, macro,PyABIInfo_VAR,3.15,, func,PyAIter_Check,3.10,, func,PyArg_Parse,3.2,, @@ -11,6 +25,26 @@ func,PyArg_UnpackTuple,3.2,, func,PyArg_VaParse,3.2,, func,PyArg_VaParseTupleAndKeywords,3.2,, func,PyArg_ValidateKeywordArguments,3.2,, +macro,PyBUF_ANY_CONTIGUOUS,3.11,, +macro,PyBUF_CONTIG,3.11,, +macro,PyBUF_CONTIG_RO,3.11,, +macro,PyBUF_C_CONTIGUOUS,3.11,, +macro,PyBUF_FORMAT,3.11,, +macro,PyBUF_FULL,3.11,, +macro,PyBUF_FULL_RO,3.11,, +macro,PyBUF_F_CONTIGUOUS,3.11,, +macro,PyBUF_INDIRECT,3.11,, +macro,PyBUF_MAX_NDIM,3.11,, +macro,PyBUF_ND,3.11,, +macro,PyBUF_READ,3.11,, +macro,PyBUF_RECORDS,3.11,, +macro,PyBUF_RECORDS_RO,3.11,, +macro,PyBUF_SIMPLE,3.11,, +macro,PyBUF_STRIDED,3.11,, +macro,PyBUF_STRIDED_RO,3.11,, +macro,PyBUF_STRIDES,3.11,, +macro,PyBUF_WRITABLE,3.11,, +macro,PyBUF_WRITE,3.11,, data,PyBaseObject_Type,3.2,, func,PyBool_FromLong,3.2,, data,PyBool_Type,3.2,, @@ -836,6 +870,14 @@ func,PyWeakref_NewRef,3.2,, data,PyWrapperDescr_Type,3.2,, func,PyWrapper_New,3.2,, data,PyZip_Type,3.2,, +macro,Py_ASNATIVEBYTES_ALLOW_INDEX,3.14,, +macro,Py_ASNATIVEBYTES_BIG_ENDIAN,3.14,, +macro,Py_ASNATIVEBYTES_DEFAULTS,3.14,, +macro,Py_ASNATIVEBYTES_LITTLE_ENDIAN,3.14,, +macro,Py_ASNATIVEBYTES_NATIVE_ENDIAN,3.14,, +macro,Py_ASNATIVEBYTES_REJECT_NEGATIVE,3.14,, +macro,Py_ASNATIVEBYTES_UNSIGNED_BUFFER,3.14,, +macro,Py_AUDIT_READ,3.12,, func,Py_AddPendingCall,3.2,, func,Py_AtExit,3.2,, macro,Py_BEGIN_ALLOW_THREADS,3.2,, @@ -882,22 +924,133 @@ func,Py_NewInterpreter,3.2,, func,Py_NewRef,3.10,, func,Py_PACK_FULL_VERSION,3.14,, func,Py_PACK_VERSION,3.14,, +macro,Py_READONLY,3.12,, func,Py_REFCNT,3.14,, +macro,Py_RELATIVE_OFFSET,3.12,, func,Py_ReprEnter,3.2,, func,Py_ReprLeave,3.2,, func,Py_SetProgramName,3.2,, func,Py_SetPythonHome,3.2,, func,Py_SetRecursionLimit,3.2,, +macro,Py_TPFLAGS_BASETYPE,3.2,, +macro,Py_TPFLAGS_DEFAULT,3.2,, +macro,Py_TPFLAGS_HAVE_GC,3.2,, +macro,Py_TPFLAGS_HAVE_VECTORCALL,3.12,, +macro,Py_TPFLAGS_ITEMS_AT_END,3.12,, +macro,Py_TPFLAGS_METHOD_DESCRIPTOR,3.8,, +macro,Py_TP_USE_SPEC,3.14,, func,Py_TYPE,3.14,, +macro,Py_T_BOOL,3.12,, +macro,Py_T_BYTE,3.12,, +macro,Py_T_CHAR,3.12,, +macro,Py_T_DOUBLE,3.12,, +macro,Py_T_FLOAT,3.12,, +macro,Py_T_INT,3.12,, +macro,Py_T_LONG,3.12,, +macro,Py_T_LONGLONG,3.12,, +macro,Py_T_OBJECT_EX,3.12,, +macro,Py_T_PYSSIZET,3.12,, +macro,Py_T_SHORT,3.12,, +macro,Py_T_STRING,3.12,, +macro,Py_T_STRING_INPLACE,3.12,, +macro,Py_T_UBYTE,3.12,, +macro,Py_T_UINT,3.12,, +macro,Py_T_ULONG,3.12,, +macro,Py_T_ULONGLONG,3.12,, +macro,Py_T_USHORT,3.12,, type,Py_UCS4,3.2,, macro,Py_UNBLOCK_THREADS,3.2,, data,Py_UTF8Mode,3.8,, func,Py_VaBuildValue,3.2,, data,Py_Version,3.11,, func,Py_XNewRef,3.10,, +macro,Py_am_aiter,3.5,, +macro,Py_am_anext,3.5,, +macro,Py_am_await,3.5,, +macro,Py_am_send,3.10,, +macro,Py_bf_getbuffer,3.11,, +macro,Py_bf_releasebuffer,3.11,, type,Py_buffer,3.11,,full-abi type,Py_intptr_t,3.2,, +macro,Py_mod_abi,3.15,, +macro,Py_mp_ass_subscript,3.2,, +macro,Py_mp_length,3.2,, +macro,Py_mp_subscript,3.2,, +macro,Py_nb_absolute,3.2,, +macro,Py_nb_add,3.2,, +macro,Py_nb_and,3.2,, +macro,Py_nb_bool,3.2,, +macro,Py_nb_divmod,3.2,, +macro,Py_nb_float,3.2,, +macro,Py_nb_floor_divide,3.2,, +macro,Py_nb_index,3.2,, +macro,Py_nb_inplace_add,3.2,, +macro,Py_nb_inplace_and,3.2,, +macro,Py_nb_inplace_floor_divide,3.2,, +macro,Py_nb_inplace_lshift,3.2,, +macro,Py_nb_inplace_matrix_multiply,3.5,, +macro,Py_nb_inplace_multiply,3.2,, +macro,Py_nb_inplace_or,3.2,, +macro,Py_nb_inplace_power,3.2,, +macro,Py_nb_inplace_remainder,3.2,, +macro,Py_nb_inplace_rshift,3.2,, +macro,Py_nb_inplace_subtract,3.2,, +macro,Py_nb_inplace_true_divide,3.2,, +macro,Py_nb_inplace_xor,3.2,, +macro,Py_nb_int,3.2,, +macro,Py_nb_invert,3.2,, +macro,Py_nb_lshift,3.2,, +macro,Py_nb_matrix_multiply,3.5,, +macro,Py_nb_multiply,3.2,, +macro,Py_nb_negative,3.2,, +macro,Py_nb_or,3.2,, +macro,Py_nb_positive,3.2,, +macro,Py_nb_power,3.2,, +macro,Py_nb_remainder,3.2,, +macro,Py_nb_rshift,3.2,, +macro,Py_nb_subtract,3.2,, +macro,Py_nb_true_divide,3.2,, +macro,Py_nb_xor,3.2,, +macro,Py_sq_ass_item,3.2,, +macro,Py_sq_concat,3.2,, +macro,Py_sq_contains,3.2,, +macro,Py_sq_inplace_concat,3.2,, +macro,Py_sq_inplace_repeat,3.2,, +macro,Py_sq_item,3.2,, +macro,Py_sq_length,3.2,, +macro,Py_sq_repeat,3.2,, type,Py_ssize_t,3.2,, +macro,Py_tp_alloc,3.2,, +macro,Py_tp_base,3.2,, +macro,Py_tp_bases,3.2,, +macro,Py_tp_call,3.2,, +macro,Py_tp_clear,3.2,, +macro,Py_tp_dealloc,3.2,, +macro,Py_tp_del,3.2,, +macro,Py_tp_descr_get,3.2,, +macro,Py_tp_descr_set,3.2,, +macro,Py_tp_doc,3.2,, +macro,Py_tp_finalize,3.5,, +macro,Py_tp_free,3.2,, +macro,Py_tp_getattr,3.2,, +macro,Py_tp_getattro,3.2,, +macro,Py_tp_getset,3.2,, +macro,Py_tp_hash,3.2,, +macro,Py_tp_init,3.2,, +macro,Py_tp_is_gc,3.2,, +macro,Py_tp_iter,3.2,, +macro,Py_tp_iternext,3.2,, +macro,Py_tp_members,3.2,, +macro,Py_tp_methods,3.2,, +macro,Py_tp_new,3.2,, +macro,Py_tp_repr,3.2,, +macro,Py_tp_richcompare,3.2,, +macro,Py_tp_setattr,3.2,, +macro,Py_tp_setattro,3.2,, +macro,Py_tp_str,3.2,, +macro,Py_tp_token,3.14,, +macro,Py_tp_traverse,3.2,, +macro,Py_tp_vectorcall,3.14,, type,Py_uintptr_t,3.2,, type,allocfunc,3.2,, type,binaryfunc,3.2,, diff --git a/Doc/tools/.nitignore b/Doc/tools/.nitignore index 6fee1c192c3aff7..04e8e5580fcd790 100644 --- a/Doc/tools/.nitignore +++ b/Doc/tools/.nitignore @@ -8,7 +8,6 @@ Doc/c-api/init_config.rst Doc/c-api/intro.rst Doc/c-api/module.rst Doc/c-api/stable.rst -Doc/c-api/type.rst Doc/c-api/typeobj.rst Doc/library/ast.rst Doc/library/asyncio-extending.rst diff --git a/Doc/tools/extensions/c_annotations.py b/Doc/tools/extensions/c_annotations.py index 089614a1f6c421d..e04a5f144c449bc 100644 --- a/Doc/tools/extensions/c_annotations.py +++ b/Doc/tools/extensions/c_annotations.py @@ -154,7 +154,10 @@ def add_annotations(app: Sphinx, doctree: nodes.document) -> None: node.insert(0, annotation) -def _stable_abi_annotation(record: StableABIEntry) -> nodes.emphasis: +def _stable_abi_annotation( + record: StableABIEntry, + is_corresponding_slot: bool = False, +) -> nodes.emphasis: """Create the Stable ABI annotation. These have two forms: @@ -168,9 +171,28 @@ def _stable_abi_annotation(record: StableABIEntry) -> nodes.emphasis: ... all of which can have "since version X.Y" appended. """ stable_added = record.added - message = sphinx_gettext("Part of the") - message = message.center(len(message) + 2) - emph_node = nodes.emphasis(message, message, classes=["stableabi"]) + emph_node = nodes.emphasis('', '', classes=["stableabi"]) + if is_corresponding_slot: + # See "Type slot annotations" in add_annotations + ref_node = addnodes.pending_xref( + "slot ID", + refdomain="c", + reftarget="PyType_Slot", + reftype="type", + refexplicit="True", + ) + ref_node += nodes.Text(sphinx_gettext("slot ID")) + + message = sphinx_gettext("The corresponding") + emph_node += nodes.Text(" " + message + " ") + emph_node += ref_node + emph_node += nodes.Text(" ") + emph_node += nodes.literal(record.name, record.name) + message = sphinx_gettext("is part of the") + emph_node += nodes.Text(" " + message + " ") + else: + message = sphinx_gettext("Part of the") + emph_node += nodes.Text(" " + message + " ") ref_node = addnodes.pending_xref( "Stable ABI", refdomain="std", @@ -265,6 +287,51 @@ def run(self) -> list[nodes.Node]: return [node] +class CorrespondingTypeSlot(SphinxDirective): + """Type slot annotations + + Docs for these are with the corresponding field, for example, + "Py_tp_repr" is documented under "PyTypeObject.tp_repr", with + only a stable ABI note mentioning "Py_tp_repr" (and linking to + docs on how this works). + + If there is no corresponding field, these should be documented as normal + macros. + """ + + has_content = False + + required_arguments = 1 + optional_arguments = 0 + + def run(self) -> list[nodes.Node]: + name = self.arguments[0] + state = self.env.domaindata["c_annotations"] + stable_abi_data = state["stable_abi_data"] + + try: + record = stable_abi_data[name] + except LookupError as err: + raise LookupError( + f"{name} is not part of stable ABI. " + + "Document it as `c:macro::` rather than " + + "`corresponding-type-slot::`." + ) from err + + annotation = _stable_abi_annotation(record, is_corresponding_slot=True) + + node = nodes.paragraph() + content = [ + ".. c:namespace:: NULL", + "", + ".. c:macro:: " + name, + " :no-typesetting:", + ] + self.state.nested_parse(StringList(content), 0, node) + node.insert(0, annotation) + return [node] + + def init_annotations(app: Sphinx) -> None: # Using domaindata is a bit hack-ish, # but allows storing state without a global variable or closure. @@ -281,6 +348,7 @@ def setup(app: Sphinx) -> ExtensionMetadata: app.add_config_value("refcount_file", "", "env", types={str}) app.add_config_value("stable_abi_file", "", "env", types={str}) app.add_directive("limited-api-list", LimitedAPIList) + app.add_directive("corresponding-type-slot", CorrespondingTypeSlot) app.connect("builder-inited", init_annotations) app.connect("doctree-read", add_annotations) diff --git a/Misc/stable_abi.toml b/Misc/stable_abi.toml index 4a03cc76f5e1e9f..ad0f370459910af 100644 --- a/Misc/stable_abi.toml +++ b/Misc/stable_abi.toml @@ -2306,6 +2306,10 @@ added = '3.11' [function.PyMemoryView_FromBuffer] added = '3.11' +[const.Py_bf_getbuffer] + added = '3.11' +[const.Py_bf_releasebuffer] + added = '3.11' # Constants for Py_buffer API added to this list in Python 3.11.1 (https://github.com/python/cpython/issues/98680) # (they were available with 3.11.0) diff --git a/Tools/build/stable_abi.py b/Tools/build/stable_abi.py index 1ddd76cdd9bf64d..39115b331ba6428 100644 --- a/Tools/build/stable_abi.py +++ b/Tools/build/stable_abi.py @@ -232,7 +232,7 @@ def sort_key(item): 'data': 'data', 'struct': 'type', 'macro': 'macro', - # 'const': 'const', # all undocumented + 'const': 'macro', 'typedef': 'type', } From d5b00c74b30a159d8d8c03e152c6cf8e8b1431b2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miro=20Hron=C4=8Dok?= Date: Tue, 4 Nov 2025 23:29:15 +0100 Subject: [PATCH 5/5] gh-140454: Normalize the JIT stencils filename on Linux to avoid mismatches between the Makefile and the generator (#140823) --- .../next/Build/2025-10-31-13-20-16.gh-issue-140454.gF6dCe.rst | 3 +++ configure | 4 ++-- configure.ac | 4 ++-- 3 files changed, 7 insertions(+), 4 deletions(-) create mode 100644 Misc/NEWS.d/next/Build/2025-10-31-13-20-16.gh-issue-140454.gF6dCe.rst diff --git a/Misc/NEWS.d/next/Build/2025-10-31-13-20-16.gh-issue-140454.gF6dCe.rst b/Misc/NEWS.d/next/Build/2025-10-31-13-20-16.gh-issue-140454.gF6dCe.rst new file mode 100644 index 000000000000000..4bb132ce01e1708 --- /dev/null +++ b/Misc/NEWS.d/next/Build/2025-10-31-13-20-16.gh-issue-140454.gF6dCe.rst @@ -0,0 +1,3 @@ +When building the JIT, match the jit_stencils filename expectations in +Makefile with the generator script. This avoid needless JIT recompilation +during ``make install``. diff --git a/configure b/configure index 605214927558201..8463b5b5e4a9d00 100755 --- a/configure +++ b/configure @@ -34327,10 +34327,10 @@ else case e in #( JIT_STENCILS_H="jit_stencils-x86_64-pc-windows-msvc.h" ;; aarch64-*-linux-gnu) - JIT_STENCILS_H="jit_stencils-$host.h" + JIT_STENCILS_H="jit_stencils-aarch64-unknown-linux-gnu.h" ;; x86_64-*-linux-gnu) - JIT_STENCILS_H="jit_stencils-$host.h" + JIT_STENCILS_H="jit_stencils-x86_64-unknown-linux-gnu.h" ;; esac ;; esac diff --git a/configure.ac b/configure.ac index 135492d82e08fd6..df94ae25e63561a 100644 --- a/configure.ac +++ b/configure.ac @@ -8219,10 +8219,10 @@ AS_VAR_IF([enable_experimental_jit], [no], JIT_STENCILS_H="jit_stencils-x86_64-pc-windows-msvc.h" ;; aarch64-*-linux-gnu) - JIT_STENCILS_H="jit_stencils-$host.h" + JIT_STENCILS_H="jit_stencils-aarch64-unknown-linux-gnu.h" ;; x86_64-*-linux-gnu) - JIT_STENCILS_H="jit_stencils-$host.h" + JIT_STENCILS_H="jit_stencils-x86_64-unknown-linux-gnu.h" ;; esac])