Mailman 3 April 2022 - Python-checkins

bpo-43323: Fix UnicodeEncodeError in the email module (GH-32137)
by miss-islington April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/19a079690c29cd6a9f3fc3cb6aeb9f5a11… commit: 19a079690c29cd6a9f3fc3cb6aeb9f5a11c491e3 branch: 3.10 author: Miss Islington (bot) <31488909+miss-islington(a)users.noreply.github.com> committer: miss-islington <31488909+miss-islington(a)users.noreply.github.com> date: 2022-04-30T05:31:28-07:00 summary: bpo-43323: Fix UnicodeEncodeError in the email module (GH-32137) It was raised if the charset itself contains characters not encodable in UTF-8 (in particular \udcxx characters representing non-decodable bytes in the source). (cherry picked from commit e91dee87edcf6dee5dd78053004d76e5f05456d4) Co-authored-by: Serhiy Storchaka <storchaka(a)gmail.com> files: A Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst M Lib/email/_encoded_words.py M Lib/email/_header_value_parser.py M Lib/test/test_email/test__encoded_words.py M Lib/test/test_email/test_email.py M Lib/test/test_email/test_headerregistry.py diff --git a/Lib/email/_encoded_words.py b/Lib/email/_encoded_words.py index 295ae7eb21237..6795a606de037 100644 --- a/Lib/email/_encoded_words.py +++ b/Lib/email/_encoded_words.py @@ -179,15 +179,15 @@ def decode(ew): # Turn the CTE decoded bytes into unicode. try: string = bstring.decode(charset) - except UnicodeError: + except UnicodeDecodeError: defects.append(errors.UndecodableBytesDefect("Encoded word " - "contains bytes not decodable using {} charset".format(charset))) + f"contains bytes not decodable using {charset!r} charset")) string = bstring.decode(charset, 'surrogateescape') - except LookupError: + except (LookupError, UnicodeEncodeError): string = bstring.decode('ascii', 'surrogateescape') if charset.lower() != 'unknown-8bit': - defects.append(errors.CharsetError("Unknown charset {} " - "in encoded word; decoded as unknown bytes".format(charset))) + defects.append(errors.CharsetError(f"Unknown charset {charset!r} " + f"in encoded word; decoded as unknown bytes")) return string, charset, lang, defects diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 51d355fbb0abc..8a8fb8bc42a95 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -781,7 +781,7 @@ def params(self): else: try: value = value.decode(charset, 'surrogateescape') - except LookupError: + except (LookupError, UnicodeEncodeError): # XXX: there should really be a custom defect for # unknown character set to make it easy to find, # because otherwise unknown charset is a silent diff --git a/Lib/test/test_email/test__encoded_words.py b/Lib/test/test_email/test__encoded_words.py index 0b8b1de3359aa..1713962f94cae 100644 --- a/Lib/test/test_email/test__encoded_words.py +++ b/Lib/test/test_email/test__encoded_words.py @@ -130,6 +130,13 @@ def test_unknown_charset(self): # XXX Should this be a new Defect instead? defects = [errors.CharsetError]) + def test_invalid_character_in_charset(self): + self._test('=?utf-8\udce2\udc80\udc9d?q?foo=ACbar?=', + b'foo\xacbar'.decode('ascii', 'surrogateescape'), + charset = 'utf-8\udce2\udc80\udc9d', + # XXX Should this be a new Defect instead? + defects = [errors.CharsetError]) + def test_q_nonascii(self): self._test('=?utf-8?q?=C3=89ric?=', 'Éric', diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py index a3ccbbbabfb32..af0ea03fedf0c 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -5323,6 +5323,15 @@ def test_rfc2231_unknown_encoding(self): Content-Transfer-Encoding: 8bit Content-Disposition: inline; filename*=X-UNKNOWN''myfile.txt +""" + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), 'myfile.txt') + + def test_rfc2231_bad_character_in_encoding(self): + m = """\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename*=utf-8\udce2\udc80\udc9d''myfile.txt + """ msg = email.message_from_string(m) self.assertEqual(msg.get_filename(), 'myfile.txt') diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py index 59fcd932e0ec4..25347ef13c214 100644 --- a/Lib/test/test_email/test_headerregistry.py +++ b/Lib/test/test_email/test_headerregistry.py @@ -714,6 +714,18 @@ def content_type_as_value(self, " charset*=unknown-8bit''utf-8%E2%80%9D\n", ), + 'rfc2231_nonascii_in_charset_of_charset_parameter_value': ( + "text/plain; charset*=utf-8”''utf-8%E2%80%9D", + 'text/plain', + 'text', + 'plain', + {'charset': 'utf-8”'}, + [], + 'text/plain; charset="utf-8”"', + "Content-Type: text/plain;" + " charset*=utf-8''utf-8%E2%80%9D\n", + ), + 'rfc2231_encoded_then_unencoded_segments': ( ('application/x-foo;' '\tname*0*="us-ascii\'en-us\'My";' diff --git a/Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst b/Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst new file mode 100644 index 0000000000000..98d73101d3ee5 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst @@ -0,0 +1,2 @@ +Fix errors in the :mod:`email` module if the charset itself contains +undecodable/unencodable characters.

1 0

bpo-43323: Fix UnicodeEncodeError in the email module (GH-32137)
by serhiy-storchaka April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/e91dee87edcf6dee5dd78053004d76e5f0… commit: e91dee87edcf6dee5dd78053004d76e5f05456d4 branch: main author: Serhiy Storchaka <storchaka(a)gmail.com> committer: serhiy-storchaka <storchaka(a)gmail.com> date: 2022-04-30T13:17:23+03:00 summary: bpo-43323: Fix UnicodeEncodeError in the email module (GH-32137) It was raised if the charset itself contains characters not encodable in UTF-8 (in particular \udcxx characters representing non-decodable bytes in the source). files: A Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst M Lib/email/_encoded_words.py M Lib/email/_header_value_parser.py M Lib/test/test_email/test__encoded_words.py M Lib/test/test_email/test_email.py M Lib/test/test_email/test_headerregistry.py diff --git a/Lib/email/_encoded_words.py b/Lib/email/_encoded_words.py index 295ae7eb21237..6795a606de037 100644 --- a/Lib/email/_encoded_words.py +++ b/Lib/email/_encoded_words.py @@ -179,15 +179,15 @@ def decode(ew): # Turn the CTE decoded bytes into unicode. try: string = bstring.decode(charset) - except UnicodeError: + except UnicodeDecodeError: defects.append(errors.UndecodableBytesDefect("Encoded word " - "contains bytes not decodable using {} charset".format(charset))) + f"contains bytes not decodable using {charset!r} charset")) string = bstring.decode(charset, 'surrogateescape') - except LookupError: + except (LookupError, UnicodeEncodeError): string = bstring.decode('ascii', 'surrogateescape') if charset.lower() != 'unknown-8bit': - defects.append(errors.CharsetError("Unknown charset {} " - "in encoded word; decoded as unknown bytes".format(charset))) + defects.append(errors.CharsetError(f"Unknown charset {charset!r} " + f"in encoded word; decoded as unknown bytes")) return string, charset, lang, defects diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 51d355fbb0abc..8a8fb8bc42a95 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -781,7 +781,7 @@ def params(self): else: try: value = value.decode(charset, 'surrogateescape') - except LookupError: + except (LookupError, UnicodeEncodeError): # XXX: there should really be a custom defect for # unknown character set to make it easy to find, # because otherwise unknown charset is a silent diff --git a/Lib/test/test_email/test__encoded_words.py b/Lib/test/test_email/test__encoded_words.py index 0b8b1de3359aa..1713962f94cae 100644 --- a/Lib/test/test_email/test__encoded_words.py +++ b/Lib/test/test_email/test__encoded_words.py @@ -130,6 +130,13 @@ def test_unknown_charset(self): # XXX Should this be a new Defect instead? defects = [errors.CharsetError]) + def test_invalid_character_in_charset(self): + self._test('=?utf-8\udce2\udc80\udc9d?q?foo=ACbar?=', + b'foo\xacbar'.decode('ascii', 'surrogateescape'), + charset = 'utf-8\udce2\udc80\udc9d', + # XXX Should this be a new Defect instead? + defects = [errors.CharsetError]) + def test_q_nonascii(self): self._test('=?utf-8?q?=C3=89ric?=', 'Éric', diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py index 933aa4cbc1959..69f883a3673f2 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -5356,6 +5356,15 @@ def test_rfc2231_unknown_encoding(self): Content-Transfer-Encoding: 8bit Content-Disposition: inline; filename*=X-UNKNOWN''myfile.txt +""" + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), 'myfile.txt') + + def test_rfc2231_bad_character_in_encoding(self): + m = """\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename*=utf-8\udce2\udc80\udc9d''myfile.txt + """ msg = email.message_from_string(m) self.assertEqual(msg.get_filename(), 'myfile.txt') diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py index 59fcd932e0ec4..25347ef13c214 100644 --- a/Lib/test/test_email/test_headerregistry.py +++ b/Lib/test/test_email/test_headerregistry.py @@ -714,6 +714,18 @@ def content_type_as_value(self, " charset*=unknown-8bit''utf-8%E2%80%9D\n", ), + 'rfc2231_nonascii_in_charset_of_charset_parameter_value': ( + "text/plain; charset*=utf-8”''utf-8%E2%80%9D", + 'text/plain', + 'text', + 'plain', + {'charset': 'utf-8”'}, + [], + 'text/plain; charset="utf-8”"', + "Content-Type: text/plain;" + " charset*=utf-8''utf-8%E2%80%9D\n", + ), + 'rfc2231_encoded_then_unencoded_segments': ( ('application/x-foo;' '\tname*0*="us-ascii\'en-us\'My";' diff --git a/Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst b/Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst new file mode 100644 index 0000000000000..98d73101d3ee5 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2022-03-27-12-40-16.bpo-43323.9mFPuI.rst @@ -0,0 +1,2 @@ +Fix errors in the :mod:`email` module if the charset itself contains +undecodable/unencodable characters.

1 0

gh-81548: Deprecate octal escape sequences with value larger than 0o377 (GH-91668)
by serhiy-storchaka April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/3483299a24e41a7f2e958369cb3573d7c2… commit: 3483299a24e41a7f2e958369cb3573d7c2253e33 branch: main author: Serhiy Storchaka <storchaka(a)gmail.com> committer: serhiy-storchaka <storchaka(a)gmail.com> date: 2022-04-30T13:16:27+03:00 summary: gh-81548: Deprecate octal escape sequences with value larger than 0o377 (GH-91668) files: A Misc/NEWS.d/next/Core and Builtins/2022-04-18-20-25-01.gh-issue-81548.n3VYgp.rst M Doc/reference/lexical_analysis.rst M Doc/whatsnew/3.11.rst M Lib/test/test_codecs.py M Lib/test/test_string_literals.py M Objects/bytesobject.c M Objects/unicodeobject.c M Parser/string_parser.c diff --git a/Doc/reference/lexical_analysis.rst b/Doc/reference/lexical_analysis.rst index dba1a9dd2e15a..0e64a056a6eb2 100644 --- a/Doc/reference/lexical_analysis.rst +++ b/Doc/reference/lexical_analysis.rst @@ -596,6 +596,11 @@ Notes: (1) As in Standard C, up to three octal digits are accepted. + .. versionchanged:: 3.11 + Octal escapes with value larger than ``0o377`` produce a :exc:`DeprecationWarning`. + In a future Python version they will be a :exc:`SyntaxWarning` and + eventually a :exc:`SyntaxError`. + (2) Unlike in Standard C, exactly two hex digits are required. diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst index 1a692f2fe7f60..59c8dd6e44732 100644 --- a/Doc/whatsnew/3.11.rst +++ b/Doc/whatsnew/3.11.rst @@ -1055,6 +1055,12 @@ CPython bytecode changes Deprecated ========== +* Octal escapes with value larger than ``0o377`` now produce + a :exc:`DeprecationWarning`. + In a future Python version they will be a :exc:`SyntaxWarning` and + eventually a :exc:`SyntaxError`. + (Contributed by Serhiy Storchaka in :issue:`81548`.) + * The :mod:`lib2to3` package and ``2to3`` tool are now deprecated and may not be able to parse Python 3.10 or newer. See the :pep:`617` (New PEG parser for CPython). (Contributed by Victor Stinner in :issue:`40360`.) diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 5853e08819715..42c600dcb00de 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -1193,7 +1193,6 @@ def test_escape(self): check(br"[\418]", b"[!8]") check(br"[\101]", b"[A]") check(br"[\1010]", b"[A0]") - check(br"[\501]", b"[A]") check(br"[\x41]", b"[A]") check(br"[\x410]", b"[A0]") for i in range(97, 123): @@ -1209,6 +1208,9 @@ def test_escape(self): check(br"\9", b"\\9") with self.assertWarns(DeprecationWarning): check(b"\\\xfa", b"\\\xfa") + for i in range(0o400, 0o1000): + with self.assertWarns(DeprecationWarning): + check(rb'\%o' % i, bytes([i & 0o377])) def test_errors(self): decode = codecs.escape_decode @@ -2435,6 +2437,9 @@ def test_escape_decode(self): check(br"\9", "\\9") with self.assertWarns(DeprecationWarning): check(b"\\\xfa", "\\\xfa") + for i in range(0o400, 0o1000): + with self.assertWarns(DeprecationWarning): + check(rb'\%o' % i, chr(i)) def test_decode_errors(self): decode = codecs.unicode_escape_decode diff --git a/Lib/test/test_string_literals.py b/Lib/test/test_string_literals.py index 7231970acf19d..3a3830bcb6e96 100644 --- a/Lib/test/test_string_literals.py +++ b/Lib/test/test_string_literals.py @@ -116,6 +116,7 @@ def test_eval_str_invalid_escape(self): warnings.simplefilter('always', category=DeprecationWarning) eval("'''\n\\z'''") self.assertEqual(len(w), 1) + self.assertEqual(str(w[0].message), r"invalid escape sequence '\z'") self.assertEqual(w[0].filename, '<string>') self.assertEqual(w[0].lineno, 1) @@ -125,6 +126,32 @@ def test_eval_str_invalid_escape(self): eval("'''\n\\z'''") exc = cm.exception self.assertEqual(w, []) + self.assertEqual(exc.msg, r"invalid escape sequence '\z'") + self.assertEqual(exc.filename, '<string>') + self.assertEqual(exc.lineno, 1) + self.assertEqual(exc.offset, 1) + + def test_eval_str_invalid_octal_escape(self): + for i in range(0o400, 0o1000): + with self.assertWarns(DeprecationWarning): + self.assertEqual(eval(r"'\%o'" % i), chr(i)) + + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('always', category=DeprecationWarning) + eval("'''\n\\407'''") + self.assertEqual(len(w), 1) + self.assertEqual(str(w[0].message), + r"invalid octal escape sequence '\407'") + self.assertEqual(w[0].filename, '<string>') + self.assertEqual(w[0].lineno, 1) + + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('error', category=DeprecationWarning) + with self.assertRaises(SyntaxError) as cm: + eval("'''\n\\407'''") + exc = cm.exception + self.assertEqual(w, []) + self.assertEqual(exc.msg, r"invalid octal escape sequence '\407'") self.assertEqual(exc.filename, '<string>') self.assertEqual(exc.lineno, 1) self.assertEqual(exc.offset, 1) @@ -166,6 +193,7 @@ def test_eval_bytes_invalid_escape(self): warnings.simplefilter('always', category=DeprecationWarning) eval("b'''\n\\z'''") self.assertEqual(len(w), 1) + self.assertEqual(str(w[0].message), r"invalid escape sequence '\z'") self.assertEqual(w[0].filename, '<string>') self.assertEqual(w[0].lineno, 1) @@ -175,6 +203,31 @@ def test_eval_bytes_invalid_escape(self): eval("b'''\n\\z'''") exc = cm.exception self.assertEqual(w, []) + self.assertEqual(exc.msg, r"invalid escape sequence '\z'") + self.assertEqual(exc.filename, '<string>') + self.assertEqual(exc.lineno, 1) + + def test_eval_bytes_invalid_octal_escape(self): + for i in range(0o400, 0o1000): + with self.assertWarns(DeprecationWarning): + self.assertEqual(eval(r"b'\%o'" % i), bytes([i & 0o377])) + + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('always', category=DeprecationWarning) + eval("b'''\n\\407'''") + self.assertEqual(len(w), 1) + self.assertEqual(str(w[0].message), + r"invalid octal escape sequence '\407'") + self.assertEqual(w[0].filename, '<string>') + self.assertEqual(w[0].lineno, 1) + + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('error', category=DeprecationWarning) + with self.assertRaises(SyntaxError) as cm: + eval("b'''\n\\407'''") + exc = cm.exception + self.assertEqual(w, []) + self.assertEqual(exc.msg, r"invalid octal escape sequence '\407'") self.assertEqual(exc.filename, '<string>') self.assertEqual(exc.lineno, 1) diff --git a/Misc/NEWS.d/next/Core and Builtins/2022-04-18-20-25-01.gh-issue-81548.n3VYgp.rst b/Misc/NEWS.d/next/Core and Builtins/2022-04-18-20-25-01.gh-issue-81548.n3VYgp.rst new file mode 100644 index 0000000000000..56b1fd63b71c0 --- /dev/null +++ b/Misc/NEWS.d/next/Core and Builtins/2022-04-18-20-25-01.gh-issue-81548.n3VYgp.rst @@ -0,0 +1,3 @@ +Octal escapes with value larger than ``0o377`` now produce a +:exc:`DeprecationWarning`. In a future Python version they will be a +:exc:`SyntaxWarning` and eventually a :exc:`SyntaxError`. diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c index 510a836e6b152..b5066d0986c7b 100644 --- a/Objects/bytesobject.c +++ b/Objects/bytesobject.c @@ -1113,6 +1113,12 @@ PyObject *_PyBytes_DecodeEscape(const char *s, if (s < end && '0' <= *s && *s <= '7') c = (c<<3) + *s++ - '0'; } + if (c > 0377) { + if (*first_invalid_escape == NULL) { + *first_invalid_escape = s-3; /* Back up 3 chars, since we've + already incremented s. */ + } + } *p++ = c; break; case 'x': @@ -1179,11 +1185,24 @@ PyObject *PyBytes_DecodeEscape(const char *s, if (result == NULL) return NULL; if (first_invalid_escape != NULL) { - if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, - "invalid escape sequence '\\%c'", - (unsigned char)*first_invalid_escape) < 0) { - Py_DECREF(result); - return NULL; + unsigned char c = *first_invalid_escape; + if ('4' <= c && c <= '7') { + if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, + "invalid octal escape sequence '\\%.3s'", + first_invalid_escape) < 0) + { + Py_DECREF(result); + return NULL; + } + } + else { + if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, + "invalid escape sequence '\\%c'", + c) < 0) + { + Py_DECREF(result); + return NULL; + } } } return result; diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index 7768f66c95655..493307556529b 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -6404,6 +6404,12 @@ _PyUnicode_DecodeUnicodeEscapeInternal(const char *s, ch = (ch<<3) + *s++ - '0'; } } + if (ch > 0377) { + if (*first_invalid_escape == NULL) { + *first_invalid_escape = s-3; /* Back up 3 chars, since we've + already incremented s. */ + } + } WRITE_CHAR(ch); continue; @@ -6554,11 +6560,24 @@ _PyUnicode_DecodeUnicodeEscapeStateful(const char *s, if (result == NULL) return NULL; if (first_invalid_escape != NULL) { - if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, - "invalid escape sequence '\\%c'", - (unsigned char)*first_invalid_escape) < 0) { - Py_DECREF(result); - return NULL; + unsigned char c = *first_invalid_escape; + if ('4' <= c && c <= '7') { + if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, + "invalid octal escape sequence '\\%.3s'", + first_invalid_escape) < 0) + { + Py_DECREF(result); + return NULL; + } + } + else { + if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, + "invalid escape sequence '\\%c'", + c) < 0) + { + Py_DECREF(result); + return NULL; + } } } return result; diff --git a/Parser/string_parser.c b/Parser/string_parser.c index 65ddd46874b20..9c12d8ca101d0 100644 --- a/Parser/string_parser.c +++ b/Parser/string_parser.c @@ -9,10 +9,15 @@ //// STRING HANDLING FUNCTIONS //// static int -warn_invalid_escape_sequence(Parser *p, unsigned char first_invalid_escape_char, Token *t) +warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token *t) { + unsigned char c = *first_invalid_escape; + int octal = ('4' <= c && c <= '7'); PyObject *msg = - PyUnicode_FromFormat("invalid escape sequence '\\%c'", first_invalid_escape_char); + octal + ? PyUnicode_FromFormat("invalid octal escape sequence '\\%.3s'", + first_invalid_escape) + : PyUnicode_FromFormat("invalid escape sequence '\\%c'", c); if (msg == NULL) { return -1; } @@ -27,7 +32,13 @@ warn_invalid_escape_sequence(Parser *p, unsigned char first_invalid_escape_char, since _PyPegen_raise_error uses p->tokens[p->fill - 1] for the error location, if p->known_err_token is not set. */ p->known_err_token = t; - RAISE_SYNTAX_ERROR("invalid escape sequence '\\%c'", first_invalid_escape_char); + if (octal) { + RAISE_SYNTAX_ERROR("invalid octal escape sequence '\\%.3s'", + first_invalid_escape); + } + else { + RAISE_SYNTAX_ERROR("invalid escape sequence '\\%c'", c); + } } Py_DECREF(msg); return -1; @@ -118,7 +129,7 @@ decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t) v = _PyUnicode_DecodeUnicodeEscapeInternal(s, len, NULL, NULL, &first_invalid_escape); if (v != NULL && first_invalid_escape != NULL) { - if (warn_invalid_escape_sequence(parser, *first_invalid_escape, t) < 0) { + if (warn_invalid_escape_sequence(parser, first_invalid_escape, t) < 0) { /* We have not decref u before because first_invalid_escape points inside u. */ Py_XDECREF(u); @@ -140,7 +151,7 @@ decode_bytes_with_escapes(Parser *p, const char *s, Py_ssize_t len, Token *t) } if (first_invalid_escape != NULL) { - if (warn_invalid_escape_sequence(p, *first_invalid_escape, t) < 0) { + if (warn_invalid_escape_sequence(p, first_invalid_escape, t) < 0) { Py_DECREF(result); return NULL; } @@ -357,7 +368,7 @@ fstring_compile_expr(Parser *p, const char *expr_start, const char *expr_end, break; } } - + if (s == expr_end) { if (*expr_end == '!' || *expr_end == ':' || *expr_end == '=') { RAISE_SYNTAX_ERROR("f-string: expression required before '%c'", *expr_end); @@ -465,7 +476,7 @@ fstring_find_literal(Parser *p, const char **str, const char *end, int raw, decode_unicode_with_escapes(). */ continue; } - if (ch == '{' && warn_invalid_escape_sequence(p, ch, t) < 0) { + if (ch == '{' && warn_invalid_escape_sequence(p, s-1, t) < 0) { return -1; } }

1 0

gh-91583: AC: Fix regression for functions with defining_class (GH-91739)
by serhiy-storchaka April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/a055dac0b45031878a8196a8735522de01… commit: a055dac0b45031878a8196a8735522de018491e3 branch: main author: Serhiy Storchaka <storchaka(a)gmail.com> committer: serhiy-storchaka <storchaka(a)gmail.com> date: 2022-04-30T13:15:02+03:00 summary: gh-91583: AC: Fix regression for functions with defining_class (GH-91739) Argument Clinic now generates the same efficient code as before adding the defining_class parameter. files: A Misc/NEWS.d/next/Tools-Demos/2022-04-20-14-26-14.gh-issue-91583.200qI0.rst M Modules/_sqlite/clinic/connection.c.h M Modules/_sre/clinic/sre.c.h M Modules/cjkcodecs/clinic/multibytecodec.c.h M Modules/clinic/_curses_panel.c.h M Modules/clinic/_dbmmodule.c.h M Modules/clinic/_gdbmmodule.c.h M Modules/clinic/_lsprof.c.h M Modules/clinic/_queuemodule.c.h M Modules/clinic/_testmultiphase.c.h M Modules/clinic/arraymodule.c.h M Modules/clinic/md5module.c.h M Modules/clinic/posixmodule.c.h M Modules/clinic/pyexpat.c.h M Modules/clinic/sha1module.c.h M Modules/clinic/sha256module.c.h M Modules/clinic/sha512module.c.h M Modules/clinic/zlibmodule.c.h M Tools/clinic/clinic.py diff --git a/Misc/NEWS.d/next/Tools-Demos/2022-04-20-14-26-14.gh-issue-91583.200qI0.rst b/Misc/NEWS.d/next/Tools-Demos/2022-04-20-14-26-14.gh-issue-91583.200qI0.rst new file mode 100644 index 0000000000000..bdfa71100f95a --- /dev/null +++ b/Misc/NEWS.d/next/Tools-Demos/2022-04-20-14-26-14.gh-issue-91583.200qI0.rst @@ -0,0 +1,2 @@ +Fix regression in the code generated by Argument Clinic for functions with +the ``defining_class`` parameter. diff --git a/Modules/_sqlite/clinic/connection.c.h b/Modules/_sqlite/clinic/connection.c.h index d4597086f4c9a..b012c4d4bbfa3 100644 --- a/Modules/_sqlite/clinic/connection.c.h +++ b/Modules/_sqlite/clinic/connection.c.h @@ -323,16 +323,44 @@ pysqlite_connection_create_function(pysqlite_Connection *self, PyTypeObject *cls { PyObject *return_value = NULL; static const char * const _keywords[] = {"name", "narg", "func", "deterministic", NULL}; - static _PyArg_Parser _parser = {"siO|$p:create_function", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "create_function", 0}; + PyObject *argsbuf[4]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 3; const char *name; int narg; PyObject *func; int deterministic = 0; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &name, &narg, &func, &deterministic)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 3, 3, 0, argsbuf); + if (!args) { + goto exit; + } + if (!PyUnicode_Check(args[0])) { + _PyArg_BadArgument("create_function", "argument 'name'", "str", args[0]); + goto exit; + } + Py_ssize_t name_length; + name = PyUnicode_AsUTF8AndSize(args[0], &name_length); + if (name == NULL) { + goto exit; + } + if (strlen(name) != (size_t)name_length) { + PyErr_SetString(PyExc_ValueError, "embedded null character"); + goto exit; + } + narg = _PyLong_AsInt(args[1]); + if (narg == -1 && PyErr_Occurred()) { + goto exit; + } + func = args[2]; + if (!noptargs) { + goto skip_optional_kwonly; + } + deterministic = PyObject_IsTrue(args[3]); + if (deterministic < 0) { goto exit; } +skip_optional_kwonly: return_value = pysqlite_connection_create_function_impl(self, cls, name, narg, func, deterministic); exit: @@ -369,15 +397,34 @@ create_window_function(pysqlite_Connection *self, PyTypeObject *cls, PyObject *c { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "", "", NULL}; - static _PyArg_Parser _parser = {"siO:create_window_function", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "create_window_function", 0}; + PyObject *argsbuf[3]; const char *name; int num_params; PyObject *aggregate_class; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &name, &num_params, &aggregate_class)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 3, 3, 0, argsbuf); + if (!args) { + goto exit; + } + if (!PyUnicode_Check(args[0])) { + _PyArg_BadArgument("create_window_function", "argument 1", "str", args[0]); + goto exit; + } + Py_ssize_t name_length; + name = PyUnicode_AsUTF8AndSize(args[0], &name_length); + if (name == NULL) { + goto exit; + } + if (strlen(name) != (size_t)name_length) { + PyErr_SetString(PyExc_ValueError, "embedded null character"); goto exit; } + num_params = _PyLong_AsInt(args[1]); + if (num_params == -1 && PyErr_Occurred()) { + goto exit; + } + aggregate_class = args[2]; return_value = create_window_function_impl(self, cls, name, num_params, aggregate_class); exit: @@ -406,15 +453,34 @@ pysqlite_connection_create_aggregate(pysqlite_Connection *self, PyTypeObject *cl { PyObject *return_value = NULL; static const char * const _keywords[] = {"name", "n_arg", "aggregate_class", NULL}; - static _PyArg_Parser _parser = {"siO:create_aggregate", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "create_aggregate", 0}; + PyObject *argsbuf[3]; const char *name; int n_arg; PyObject *aggregate_class; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &name, &n_arg, &aggregate_class)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 3, 3, 0, argsbuf); + if (!args) { + goto exit; + } + if (!PyUnicode_Check(args[0])) { + _PyArg_BadArgument("create_aggregate", "argument 'name'", "str", args[0]); + goto exit; + } + Py_ssize_t name_length; + name = PyUnicode_AsUTF8AndSize(args[0], &name_length); + if (name == NULL) { + goto exit; + } + if (strlen(name) != (size_t)name_length) { + PyErr_SetString(PyExc_ValueError, "embedded null character"); + goto exit; + } + n_arg = _PyLong_AsInt(args[1]); + if (n_arg == -1 && PyErr_Occurred()) { goto exit; } + aggregate_class = args[2]; return_value = pysqlite_connection_create_aggregate_impl(self, cls, name, n_arg, aggregate_class); exit: @@ -440,13 +506,15 @@ pysqlite_connection_set_authorizer(pysqlite_Connection *self, PyTypeObject *cls, { PyObject *return_value = NULL; static const char * const _keywords[] = {"authorizer_callback", NULL}; - static _PyArg_Parser _parser = {"O:set_authorizer", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "set_authorizer", 0}; + PyObject *argsbuf[1]; PyObject *callable; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &callable)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + callable = args[0]; return_value = pysqlite_connection_set_authorizer_impl(self, cls, callable); exit: @@ -472,12 +540,18 @@ pysqlite_connection_set_progress_handler(pysqlite_Connection *self, PyTypeObject { PyObject *return_value = NULL; static const char * const _keywords[] = {"progress_handler", "n", NULL}; - static _PyArg_Parser _parser = {"Oi:set_progress_handler", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "set_progress_handler", 0}; + PyObject *argsbuf[2]; PyObject *callable; int n; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &callable, &n)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 2, 2, 0, argsbuf); + if (!args) { + goto exit; + } + callable = args[0]; + n = _PyLong_AsInt(args[1]); + if (n == -1 && PyErr_Occurred()) { goto exit; } return_value = pysqlite_connection_set_progress_handler_impl(self, cls, callable, n); @@ -505,13 +579,15 @@ pysqlite_connection_set_trace_callback(pysqlite_Connection *self, PyTypeObject * { PyObject *return_value = NULL; static const char * const _keywords[] = {"trace_callback", NULL}; - static _PyArg_Parser _parser = {"O:set_trace_callback", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "set_trace_callback", 0}; + PyObject *argsbuf[1]; PyObject *callable; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &callable)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + callable = args[0]; return_value = pysqlite_connection_set_trace_callback_impl(self, cls, callable); exit: @@ -830,14 +906,29 @@ pysqlite_connection_create_collation(pysqlite_Connection *self, PyTypeObject *cl { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "", NULL}; - static _PyArg_Parser _parser = {"sO:create_collation", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "create_collation", 0}; + PyObject *argsbuf[2]; const char *name; PyObject *callable; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &name, &callable)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 2, 2, 0, argsbuf); + if (!args) { + goto exit; + } + if (!PyUnicode_Check(args[0])) { + _PyArg_BadArgument("create_collation", "argument 1", "str", args[0]); + goto exit; + } + Py_ssize_t name_length; + name = PyUnicode_AsUTF8AndSize(args[0], &name_length); + if (name == NULL) { + goto exit; + } + if (strlen(name) != (size_t)name_length) { + PyErr_SetString(PyExc_ValueError, "embedded null character"); goto exit; } + callable = args[1]; return_value = pysqlite_connection_create_collation_impl(self, cls, name, callable); exit: @@ -1145,4 +1236,4 @@ getlimit(pysqlite_Connection *self, PyObject *arg) #ifndef DESERIALIZE_METHODDEF #define DESERIALIZE_METHODDEF #endif /* !defined(DESERIALIZE_METHODDEF) */ -/*[clinic end generated code: output=be2f526e78fa65b1 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=6c9432a9fe0a4f5e input=a9049054013a1b77]*/ diff --git a/Modules/_sre/clinic/sre.c.h b/Modules/_sre/clinic/sre.c.h index 34cbe21f14071..c1b247ef7e9dd 100644 --- a/Modules/_sre/clinic/sre.c.h +++ b/Modules/_sre/clinic/sre.c.h @@ -176,15 +176,51 @@ _sre_SRE_Pattern_match(PatternObject *self, PyTypeObject *cls, PyObject *const * { PyObject *return_value = NULL; static const char * const _keywords[] = {"string", "pos", "endpos", NULL}; - static _PyArg_Parser _parser = {"O|nn:match", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "match", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1; PyObject *string; Py_ssize_t pos = 0; Py_ssize_t endpos = PY_SSIZE_T_MAX; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &string, &pos, &endpos)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 3, 0, argsbuf); + if (!args) { goto exit; } + string = args[0]; + if (!noptargs) { + goto skip_optional_pos; + } + if (args[1]) { + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + pos = ival; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + endpos = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_match_impl(self, cls, string, pos, endpos); exit: @@ -210,15 +246,51 @@ _sre_SRE_Pattern_fullmatch(PatternObject *self, PyTypeObject *cls, PyObject *con { PyObject *return_value = NULL; static const char * const _keywords[] = {"string", "pos", "endpos", NULL}; - static _PyArg_Parser _parser = {"O|nn:fullmatch", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "fullmatch", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1; PyObject *string; Py_ssize_t pos = 0; Py_ssize_t endpos = PY_SSIZE_T_MAX; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &string, &pos, &endpos)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 3, 0, argsbuf); + if (!args) { goto exit; } + string = args[0]; + if (!noptargs) { + goto skip_optional_pos; + } + if (args[1]) { + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + pos = ival; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + endpos = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_fullmatch_impl(self, cls, string, pos, endpos); exit: @@ -246,15 +318,51 @@ _sre_SRE_Pattern_search(PatternObject *self, PyTypeObject *cls, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"string", "pos", "endpos", NULL}; - static _PyArg_Parser _parser = {"O|nn:search", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "search", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1; PyObject *string; Py_ssize_t pos = 0; Py_ssize_t endpos = PY_SSIZE_T_MAX; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &string, &pos, &endpos)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 3, 0, argsbuf); + if (!args) { goto exit; } + string = args[0]; + if (!noptargs) { + goto skip_optional_pos; + } + if (args[1]) { + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + pos = ival; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + endpos = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_search_impl(self, cls, string, pos, endpos); exit: @@ -351,15 +459,51 @@ _sre_SRE_Pattern_finditer(PatternObject *self, PyTypeObject *cls, PyObject *cons { PyObject *return_value = NULL; static const char * const _keywords[] = {"string", "pos", "endpos", NULL}; - static _PyArg_Parser _parser = {"O|nn:finditer", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "finditer", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1; PyObject *string; Py_ssize_t pos = 0; Py_ssize_t endpos = PY_SSIZE_T_MAX; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &string, &pos, &endpos)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 3, 0, argsbuf); + if (!args) { goto exit; } + string = args[0]; + if (!noptargs) { + goto skip_optional_pos; + } + if (args[1]) { + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + pos = ival; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + endpos = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_finditer_impl(self, cls, string, pos, endpos); exit: @@ -384,15 +528,51 @@ _sre_SRE_Pattern_scanner(PatternObject *self, PyTypeObject *cls, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"string", "pos", "endpos", NULL}; - static _PyArg_Parser _parser = {"O|nn:scanner", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "scanner", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1; PyObject *string; Py_ssize_t pos = 0; Py_ssize_t endpos = PY_SSIZE_T_MAX; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &string, &pos, &endpos)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 3, 0, argsbuf); + if (!args) { goto exit; } + string = args[0]; + if (!noptargs) { + goto skip_optional_pos; + } + if (args[1]) { + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + pos = ival; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + endpos = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_scanner_impl(self, cls, string, pos, endpos); exit: @@ -468,15 +648,35 @@ _sre_SRE_Pattern_sub(PatternObject *self, PyTypeObject *cls, PyObject *const *ar { PyObject *return_value = NULL; static const char * const _keywords[] = {"repl", "string", "count", NULL}; - static _PyArg_Parser _parser = {"OO|n:sub", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "sub", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 2; PyObject *repl; PyObject *string; Py_ssize_t count = 0; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &repl, &string, &count)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 2, 3, 0, argsbuf); + if (!args) { goto exit; } + repl = args[0]; + string = args[1]; + if (!noptargs) { + goto skip_optional_pos; + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + count = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_sub_impl(self, cls, repl, string, count); exit: @@ -502,15 +702,35 @@ _sre_SRE_Pattern_subn(PatternObject *self, PyTypeObject *cls, PyObject *const *a { PyObject *return_value = NULL; static const char * const _keywords[] = {"repl", "string", "count", NULL}; - static _PyArg_Parser _parser = {"OO|n:subn", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "subn", 0}; + PyObject *argsbuf[3]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 2; PyObject *repl; PyObject *string; Py_ssize_t count = 0; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &repl, &string, &count)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 2, 3, 0, argsbuf); + if (!args) { goto exit; } + repl = args[0]; + string = args[1]; + if (!noptargs) { + goto skip_optional_pos; + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[2]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + count = ival; + } +skip_optional_pos: return_value = _sre_SRE_Pattern_subn_impl(self, cls, repl, string, count); exit: @@ -882,18 +1102,11 @@ _sre_SRE_Scanner_match_impl(ScannerObject *self, PyTypeObject *cls); static PyObject * _sre_SRE_Scanner_match(ScannerObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":match", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "match() takes no arguments"); + return NULL; } - return_value = _sre_SRE_Scanner_match_impl(self, cls); - -exit: - return return_value; + return _sre_SRE_Scanner_match_impl(self, cls); } PyDoc_STRVAR(_sre_SRE_Scanner_search__doc__, @@ -910,17 +1123,10 @@ _sre_SRE_Scanner_search_impl(ScannerObject *self, PyTypeObject *cls); static PyObject * _sre_SRE_Scanner_search(ScannerObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":search", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "search() takes no arguments"); + return NULL; } - return_value = _sre_SRE_Scanner_search_impl(self, cls); - -exit: - return return_value; + return _sre_SRE_Scanner_search_impl(self, cls); } -/*[clinic end generated code: output=9d7510a57a157a38 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=8d8200b2177cd667 input=a9049054013a1b77]*/ diff --git a/Modules/cjkcodecs/clinic/multibytecodec.c.h b/Modules/cjkcodecs/clinic/multibytecodec.c.h index 1dfb9a1224827..60515245490f7 100644 --- a/Modules/cjkcodecs/clinic/multibytecodec.c.h +++ b/Modules/cjkcodecs/clinic/multibytecodec.c.h @@ -493,13 +493,15 @@ _multibytecodec_MultibyteStreamWriter_write(MultibyteStreamWriterObject *self, P { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:write", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "write", 0}; + PyObject *argsbuf[1]; PyObject *strobj; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &strobj)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + strobj = args[0]; return_value = _multibytecodec_MultibyteStreamWriter_write_impl(self, cls, strobj); exit: @@ -524,13 +526,15 @@ _multibytecodec_MultibyteStreamWriter_writelines(MultibyteStreamWriterObject *se { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:writelines", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "writelines", 0}; + PyObject *argsbuf[1]; PyObject *lines; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &lines)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + lines = args[0]; return_value = _multibytecodec_MultibyteStreamWriter_writelines_impl(self, cls, lines); exit: @@ -552,18 +556,11 @@ _multibytecodec_MultibyteStreamWriter_reset_impl(MultibyteStreamWriterObject *se static PyObject * _multibytecodec_MultibyteStreamWriter_reset(MultibyteStreamWriterObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":reset", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "reset() takes no arguments"); + return NULL; } - return_value = _multibytecodec_MultibyteStreamWriter_reset_impl(self, cls); - -exit: - return return_value; + return _multibytecodec_MultibyteStreamWriter_reset_impl(self, cls); } PyDoc_STRVAR(_multibytecodec___create_codec__doc__, @@ -573,4 +570,4 @@ PyDoc_STRVAR(_multibytecodec___create_codec__doc__, #define _MULTIBYTECODEC___CREATE_CODEC_METHODDEF \ {"__create_codec", (PyCFunction)_multibytecodec___create_codec, METH_O, _multibytecodec___create_codec__doc__}, -/*[clinic end generated code: output=8813c05077580bda input=a9049054013a1b77]*/ +/*[clinic end generated code: output=0ee00c9f6883afe9 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/_curses_panel.c.h b/Modules/clinic/_curses_panel.c.h index 45898070b1f54..e4642b58332de 100644 --- a/Modules/clinic/_curses_panel.c.h +++ b/Modules/clinic/_curses_panel.c.h @@ -17,18 +17,11 @@ _curses_panel_panel_bottom_impl(PyCursesPanelObject *self, PyTypeObject *cls); static PyObject * _curses_panel_panel_bottom(PyCursesPanelObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":bottom", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "bottom() takes no arguments"); + return NULL; } - return_value = _curses_panel_panel_bottom_impl(self, cls); - -exit: - return return_value; + return _curses_panel_panel_bottom_impl(self, cls); } PyDoc_STRVAR(_curses_panel_panel_hide__doc__, @@ -48,18 +41,11 @@ _curses_panel_panel_hide_impl(PyCursesPanelObject *self, PyTypeObject *cls); static PyObject * _curses_panel_panel_hide(PyCursesPanelObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":hide", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "hide() takes no arguments"); + return NULL; } - return_value = _curses_panel_panel_hide_impl(self, cls); - -exit: - return return_value; + return _curses_panel_panel_hide_impl(self, cls); } PyDoc_STRVAR(_curses_panel_panel_show__doc__, @@ -77,18 +63,11 @@ _curses_panel_panel_show_impl(PyCursesPanelObject *self, PyTypeObject *cls); static PyObject * _curses_panel_panel_show(PyCursesPanelObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":show", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "show() takes no arguments"); + return NULL; } - return_value = _curses_panel_panel_show_impl(self, cls); - -exit: - return return_value; + return _curses_panel_panel_show_impl(self, cls); } PyDoc_STRVAR(_curses_panel_panel_top__doc__, @@ -106,18 +85,11 @@ _curses_panel_panel_top_impl(PyCursesPanelObject *self, PyTypeObject *cls); static PyObject * _curses_panel_panel_top(PyCursesPanelObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":top", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "top() takes no arguments"); + return NULL; } - return_value = _curses_panel_panel_top_impl(self, cls); - -exit: - return return_value; + return _curses_panel_panel_top_impl(self, cls); } PyDoc_STRVAR(_curses_panel_panel_above__doc__, @@ -192,12 +164,21 @@ _curses_panel_panel_move(PyCursesPanelObject *self, PyTypeObject *cls, PyObject { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "", NULL}; - static _PyArg_Parser _parser = {"ii:move", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "move", 0}; + PyObject *argsbuf[2]; int y; int x; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &y, &x)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 2, 2, 0, argsbuf); + if (!args) { + goto exit; + } + y = _PyLong_AsInt(args[0]); + if (y == -1 && PyErr_Occurred()) { + goto exit; + } + x = _PyLong_AsInt(args[1]); + if (x == -1 && PyErr_Occurred()) { goto exit; } return_value = _curses_panel_panel_move_impl(self, cls, y, x); @@ -243,13 +224,19 @@ _curses_panel_panel_replace(PyCursesPanelObject *self, PyTypeObject *cls, PyObje { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O!:replace", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "replace", 0}; + PyObject *argsbuf[1]; PyCursesWindowObject *win; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &PyCursesWindow_Type, &win)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { + goto exit; + } + if (!PyObject_TypeCheck(args[0], &PyCursesWindow_Type)) { + _PyArg_BadArgument("replace", "argument 1", (&PyCursesWindow_Type)->tp_name, args[0]); goto exit; } + win = (PyCursesWindowObject *)args[0]; return_value = _curses_panel_panel_replace_impl(self, cls, win); exit: @@ -274,13 +261,15 @@ _curses_panel_panel_set_userptr(PyCursesPanelObject *self, PyTypeObject *cls, Py { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:set_userptr", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "set_userptr", 0}; + PyObject *argsbuf[1]; PyObject *obj; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &obj)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + obj = args[0]; return_value = _curses_panel_panel_set_userptr_impl(self, cls, obj); exit: @@ -303,18 +292,11 @@ _curses_panel_panel_userptr_impl(PyCursesPanelObject *self, static PyObject * _curses_panel_panel_userptr(PyCursesPanelObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":userptr", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "userptr() takes no arguments"); + return NULL; } - return_value = _curses_panel_panel_userptr_impl(self, cls); - -exit: - return return_value; + return _curses_panel_panel_userptr_impl(self, cls); } PyDoc_STRVAR(_curses_panel_bottom_panel__doc__, @@ -401,4 +383,4 @@ _curses_panel_update_panels(PyObject *module, PyObject *Py_UNUSED(ignored)) { return _curses_panel_update_panels_impl(module); } -/*[clinic end generated code: output=3081ef24e5560cb0 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=c552457e8067bb0a input=a9049054013a1b77]*/ diff --git a/Modules/clinic/_dbmmodule.c.h b/Modules/clinic/_dbmmodule.c.h index f0b8220e7fee2..a8b41607221f6 100644 --- a/Modules/clinic/_dbmmodule.c.h +++ b/Modules/clinic/_dbmmodule.c.h @@ -35,18 +35,11 @@ _dbm_dbm_keys_impl(dbmobject *self, PyTypeObject *cls); static PyObject * _dbm_dbm_keys(dbmobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":keys", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "keys() takes no arguments"); + return NULL; } - return_value = _dbm_dbm_keys_impl(self, cls); - -exit: - return return_value; + return _dbm_dbm_keys_impl(self, cls); } PyDoc_STRVAR(_dbm_dbm_get__doc__, @@ -179,4 +172,4 @@ dbmopen(PyObject *module, PyObject *const *args, Py_ssize_t nargs) exit: return return_value; } -/*[clinic end generated code: output=32ef6c0f8f2d3db9 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=492be70729515fe3 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/_gdbmmodule.c.h b/Modules/clinic/_gdbmmodule.c.h index a40e80d8e1a7b..ced48b99ed325 100644 --- a/Modules/clinic/_gdbmmodule.c.h +++ b/Modules/clinic/_gdbmmodule.c.h @@ -104,18 +104,11 @@ _gdbm_gdbm_keys_impl(gdbmobject *self, PyTypeObject *cls); static PyObject * _gdbm_gdbm_keys(gdbmobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":keys", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "keys() takes no arguments"); + return NULL; } - return_value = _gdbm_gdbm_keys_impl(self, cls); - -exit: - return return_value; + return _gdbm_gdbm_keys_impl(self, cls); } PyDoc_STRVAR(_gdbm_gdbm_firstkey__doc__, @@ -137,18 +130,11 @@ _gdbm_gdbm_firstkey_impl(gdbmobject *self, PyTypeObject *cls); static PyObject * _gdbm_gdbm_firstkey(gdbmobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":firstkey", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "firstkey() takes no arguments"); + return NULL; } - return_value = _gdbm_gdbm_firstkey_impl(self, cls); - -exit: - return return_value; + return _gdbm_gdbm_firstkey_impl(self, cls); } PyDoc_STRVAR(_gdbm_gdbm_nextkey__doc__, @@ -212,18 +198,11 @@ _gdbm_gdbm_reorganize_impl(gdbmobject *self, PyTypeObject *cls); static PyObject * _gdbm_gdbm_reorganize(gdbmobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":reorganize", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "reorganize() takes no arguments"); + return NULL; } - return_value = _gdbm_gdbm_reorganize_impl(self, cls); - -exit: - return return_value; + return _gdbm_gdbm_reorganize_impl(self, cls); } PyDoc_STRVAR(_gdbm_gdbm_sync__doc__, @@ -244,18 +223,11 @@ _gdbm_gdbm_sync_impl(gdbmobject *self, PyTypeObject *cls); static PyObject * _gdbm_gdbm_sync(gdbmobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":sync", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "sync() takes no arguments"); + return NULL; } - return_value = _gdbm_gdbm_sync_impl(self, cls); - -exit: - return return_value; + return _gdbm_gdbm_sync_impl(self, cls); } PyDoc_STRVAR(dbmopen__doc__, @@ -333,4 +305,4 @@ dbmopen(PyObject *module, PyObject *const *args, Py_ssize_t nargs) exit: return return_value; } -/*[clinic end generated code: output=63c507f93d84a3a4 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=fe7a0812eb560b23 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/_lsprof.c.h b/Modules/clinic/_lsprof.c.h index 5d9c209eab856..b0adb746974ab 100644 --- a/Modules/clinic/_lsprof.c.h +++ b/Modules/clinic/_lsprof.c.h @@ -39,17 +39,10 @@ _lsprof_Profiler_getstats_impl(ProfilerObject *self, PyTypeObject *cls); static PyObject * _lsprof_Profiler_getstats(ProfilerObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":getstats", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "getstats() takes no arguments"); + return NULL; } - return_value = _lsprof_Profiler_getstats_impl(self, cls); - -exit: - return return_value; + return _lsprof_Profiler_getstats_impl(self, cls); } -/*[clinic end generated code: output=b4727cfebecdd22d input=a9049054013a1b77]*/ +/*[clinic end generated code: output=57c7b6b0b8666429 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/_queuemodule.c.h b/Modules/clinic/_queuemodule.c.h index 22d2e992b6398..056a8ef52e00f 100644 --- a/Modules/clinic/_queuemodule.c.h +++ b/Modules/clinic/_queuemodule.c.h @@ -146,14 +146,30 @@ _queue_SimpleQueue_get(simplequeueobject *self, PyTypeObject *cls, PyObject *con { PyObject *return_value = NULL; static const char * const _keywords[] = {"block", "timeout", NULL}; - static _PyArg_Parser _parser = {"|pO:get", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "get", 0}; + PyObject *argsbuf[2]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; int block = 1; PyObject *timeout_obj = Py_None; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &block, &timeout_obj)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 2, 0, argsbuf); + if (!args) { goto exit; } + if (!noptargs) { + goto skip_optional_pos; + } + if (args[0]) { + block = PyObject_IsTrue(args[0]); + if (block < 0) { + goto exit; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } + timeout_obj = args[1]; +skip_optional_pos: return_value = _queue_SimpleQueue_get_impl(self, cls, block, timeout_obj); exit: @@ -179,18 +195,11 @@ _queue_SimpleQueue_get_nowait_impl(simplequeueobject *self, static PyObject * _queue_SimpleQueue_get_nowait(simplequeueobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":get_nowait", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "get_nowait() takes no arguments"); + return NULL; } - return_value = _queue_SimpleQueue_get_nowait_impl(self, cls); - -exit: - return return_value; + return _queue_SimpleQueue_get_nowait_impl(self, cls); } PyDoc_STRVAR(_queue_SimpleQueue_empty__doc__, @@ -248,4 +257,4 @@ _queue_SimpleQueue_qsize(simplequeueobject *self, PyObject *Py_UNUSED(ignored)) exit: return return_value; } -/*[clinic end generated code: output=acfaf0191d8935db input=a9049054013a1b77]*/ +/*[clinic end generated code: output=36301c405a858f39 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/_testmultiphase.c.h b/Modules/clinic/_testmultiphase.c.h index b8ee93c6e19ea..753670934bf81 100644 --- a/Modules/clinic/_testmultiphase.c.h +++ b/Modules/clinic/_testmultiphase.c.h @@ -21,18 +21,11 @@ _testmultiphase_StateAccessType_get_defining_module_impl(StateAccessTypeObject * static PyObject * _testmultiphase_StateAccessType_get_defining_module(StateAccessTypeObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":get_defining_module", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "get_defining_module() takes no arguments"); + return NULL; } - return_value = _testmultiphase_StateAccessType_get_defining_module_impl(self, cls); - -exit: - return return_value; + return _testmultiphase_StateAccessType_get_defining_module_impl(self, cls); } PyDoc_STRVAR(_testmultiphase_StateAccessType_getmodulebydef_bad_def__doc__, @@ -51,18 +44,11 @@ _testmultiphase_StateAccessType_getmodulebydef_bad_def_impl(StateAccessTypeObjec static PyObject * _testmultiphase_StateAccessType_getmodulebydef_bad_def(StateAccessTypeObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":getmodulebydef_bad_def", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "getmodulebydef_bad_def() takes no arguments"); + return NULL; } - return_value = _testmultiphase_StateAccessType_getmodulebydef_bad_def_impl(self, cls); - -exit: - return return_value; + return _testmultiphase_StateAccessType_getmodulebydef_bad_def_impl(self, cls); } PyDoc_STRVAR(_testmultiphase_StateAccessType_increment_count_clinic__doc__, @@ -88,14 +74,37 @@ _testmultiphase_StateAccessType_increment_count_clinic(StateAccessTypeObject *se { PyObject *return_value = NULL; static const char * const _keywords[] = {"n", "twice", NULL}; - static _PyArg_Parser _parser = {"|i$p:increment_count_clinic", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "increment_count_clinic", 0}; + PyObject *argsbuf[2]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; int n = 1; int twice = 0; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &n, &twice)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 1, 0, argsbuf); + if (!args) { goto exit; } + if (!noptargs) { + goto skip_optional_pos; + } + if (args[0]) { + n = _PyLong_AsInt(args[0]); + if (n == -1 && PyErr_Occurred()) { + goto exit; + } + if (!--noptargs) { + goto skip_optional_pos; + } + } +skip_optional_pos: + if (!noptargs) { + goto skip_optional_kwonly; + } + twice = PyObject_IsTrue(args[1]); + if (twice < 0) { + goto exit; + } +skip_optional_kwonly: return_value = _testmultiphase_StateAccessType_increment_count_clinic_impl(self, cls, n, twice); exit: @@ -118,17 +127,10 @@ _testmultiphase_StateAccessType_get_count_impl(StateAccessTypeObject *self, static PyObject * _testmultiphase_StateAccessType_get_count(StateAccessTypeObject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":get_count", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "get_count() takes no arguments"); + return NULL; } - return_value = _testmultiphase_StateAccessType_get_count_impl(self, cls); - -exit: - return return_value; + return _testmultiphase_StateAccessType_get_count_impl(self, cls); } -/*[clinic end generated code: output=e8d074b4e6437438 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=b41a400ef84f50af input=a9049054013a1b77]*/ diff --git a/Modules/clinic/arraymodule.c.h b/Modules/clinic/arraymodule.c.h index 583ff28bf3287..030c6e7e1a487 100644 --- a/Modules/clinic/arraymodule.c.h +++ b/Modules/clinic/arraymodule.c.h @@ -155,13 +155,15 @@ array_array_extend(arrayobject *self, PyTypeObject *cls, PyObject *const *args, { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:extend", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "extend", 0}; + PyObject *argsbuf[1]; PyObject *bb; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &bb)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + bb = args[0]; return_value = array_array_extend_impl(self, cls, bb); exit: @@ -296,14 +298,28 @@ array_array_fromfile(arrayobject *self, PyTypeObject *cls, PyObject *const *args { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "", NULL}; - static _PyArg_Parser _parser = {"On:fromfile", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "fromfile", 0}; + PyObject *argsbuf[2]; PyObject *f; Py_ssize_t n; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &f, &n)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 2, 2, 0, argsbuf); + if (!args) { goto exit; } + f = args[0]; + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + n = ival; + } return_value = array_array_fromfile_impl(self, cls, f, n); exit: @@ -327,13 +343,15 @@ array_array_tofile(arrayobject *self, PyTypeObject *cls, PyObject *const *args, { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:tofile", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "tofile", 0}; + PyObject *argsbuf[1]; PyObject *f; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &f)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + f = args[0]; return_value = array_array_tofile_impl(self, cls, f); exit: @@ -567,13 +585,15 @@ array_array___reduce_ex__(arrayobject *self, PyTypeObject *cls, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:__reduce_ex__", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "__reduce_ex__", 0}; + PyObject *argsbuf[1]; PyObject *value; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &value)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + value = args[0]; return_value = array_array___reduce_ex___impl(self, cls, value); exit: @@ -595,18 +615,11 @@ array_arrayiterator___reduce___impl(arrayiterobject *self, PyTypeObject *cls); static PyObject * array_arrayiterator___reduce__(arrayiterobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":__reduce__", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "__reduce__() takes no arguments"); + return NULL; } - return_value = array_arrayiterator___reduce___impl(self, cls); - -exit: - return return_value; + return array_arrayiterator___reduce___impl(self, cls); } PyDoc_STRVAR(array_arrayiterator___setstate____doc__, @@ -617,4 +630,4 @@ PyDoc_STRVAR(array_arrayiterator___setstate____doc__, #define ARRAY_ARRAYITERATOR___SETSTATE___METHODDEF \ {"__setstate__", (PyCFunction)array_arrayiterator___setstate__, METH_O, array_arrayiterator___setstate____doc__}, -/*[clinic end generated code: output=1db6decd8492bf91 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=7f48d1691fa27442 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/md5module.c.h b/Modules/clinic/md5module.c.h index 4762f2800d4b8..0ff09b0050a56 100644 --- a/Modules/clinic/md5module.c.h +++ b/Modules/clinic/md5module.c.h @@ -17,18 +17,11 @@ MD5Type_copy_impl(MD5object *self, PyTypeObject *cls); static PyObject * MD5Type_copy(MD5object *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":copy", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "copy() takes no arguments"); + return NULL; } - return_value = MD5Type_copy_impl(self, cls); - -exit: - return return_value; + return MD5Type_copy_impl(self, cls); } PyDoc_STRVAR(MD5Type_digest__doc__, @@ -126,4 +119,4 @@ _md5_md5(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kw exit: return return_value; } -/*[clinic end generated code: output=53ff7f22dbaaea36 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=3061297a669c645c input=a9049054013a1b77]*/ diff --git a/Modules/clinic/posixmodule.c.h b/Modules/clinic/posixmodule.c.h index 282a5410f7020..352dadc9b5627 100644 --- a/Modules/clinic/posixmodule.c.h +++ b/Modules/clinic/posixmodule.c.h @@ -8290,12 +8290,10 @@ static PyObject * os_DirEntry_is_symlink(DirEntry *self, PyTypeObject *defining_class, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":is_symlink", _keywords, 0}; int _return_value; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { + if (nargs) { + PyErr_SetString(PyExc_TypeError, "is_symlink() takes no arguments"); goto exit; } _return_value = os_DirEntry_is_symlink_impl(self, defining_class); @@ -8326,13 +8324,23 @@ os_DirEntry_stat(DirEntry *self, PyTypeObject *defining_class, PyObject *const * { PyObject *return_value = NULL; static const char * const _keywords[] = {"follow_symlinks", NULL}; - static _PyArg_Parser _parser = {"|$p:stat", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "stat", 0}; + PyObject *argsbuf[1]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; int follow_symlinks = 1; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &follow_symlinks)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 0, 0, argsbuf); + if (!args) { goto exit; } + if (!noptargs) { + goto skip_optional_kwonly; + } + follow_symlinks = PyObject_IsTrue(args[0]); + if (follow_symlinks < 0) { + goto exit; + } +skip_optional_kwonly: return_value = os_DirEntry_stat_impl(self, defining_class, follow_symlinks); exit: @@ -8357,14 +8365,24 @@ os_DirEntry_is_dir(DirEntry *self, PyTypeObject *defining_class, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"follow_symlinks", NULL}; - static _PyArg_Parser _parser = {"|$p:is_dir", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "is_dir", 0}; + PyObject *argsbuf[1]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; int follow_symlinks = 1; int _return_value; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &follow_symlinks)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 0, 0, argsbuf); + if (!args) { goto exit; } + if (!noptargs) { + goto skip_optional_kwonly; + } + follow_symlinks = PyObject_IsTrue(args[0]); + if (follow_symlinks < 0) { + goto exit; + } +skip_optional_kwonly: _return_value = os_DirEntry_is_dir_impl(self, defining_class, follow_symlinks); if ((_return_value == -1) && PyErr_Occurred()) { goto exit; @@ -8393,14 +8411,24 @@ os_DirEntry_is_file(DirEntry *self, PyTypeObject *defining_class, PyObject *cons { PyObject *return_value = NULL; static const char * const _keywords[] = {"follow_symlinks", NULL}; - static _PyArg_Parser _parser = {"|$p:is_file", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "is_file", 0}; + PyObject *argsbuf[1]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; int follow_symlinks = 1; int _return_value; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &follow_symlinks)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 0, 0, argsbuf); + if (!args) { goto exit; } + if (!noptargs) { + goto skip_optional_kwonly; + } + follow_symlinks = PyObject_IsTrue(args[0]); + if (follow_symlinks < 0) { + goto exit; + } +skip_optional_kwonly: _return_value = os_DirEntry_is_file_impl(self, defining_class, follow_symlinks); if ((_return_value == -1) && PyErr_Occurred()) { goto exit; @@ -9303,4 +9331,4 @@ os_waitstatus_to_exitcode(PyObject *module, PyObject *const *args, Py_ssize_t na #ifndef OS_WAITSTATUS_TO_EXITCODE_METHODDEF #define OS_WAITSTATUS_TO_EXITCODE_METHODDEF #endif /* !defined(OS_WAITSTATUS_TO_EXITCODE_METHODDEF) */ -/*[clinic end generated code: output=d95ba7b0b9c52685 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=c8c5b148b96068b4 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/pyexpat.c.h b/Modules/clinic/pyexpat.c.h index 7c56d6a8b2591..bee2ee66950a5 100644 --- a/Modules/clinic/pyexpat.c.h +++ b/Modules/clinic/pyexpat.c.h @@ -22,14 +22,24 @@ pyexpat_xmlparser_Parse(xmlparseobject *self, PyTypeObject *cls, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "", NULL}; - static _PyArg_Parser _parser = {"O|i:Parse", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "Parse", 0}; + PyObject *argsbuf[2]; PyObject *data; int isfinal = 0; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &data, &isfinal)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 2, 0, argsbuf); + if (!args) { + goto exit; + } + data = args[0]; + if (nargs < 2) { + goto skip_optional_posonly; + } + isfinal = _PyLong_AsInt(args[1]); + if (isfinal == -1 && PyErr_Occurred()) { goto exit; } +skip_optional_posonly: return_value = pyexpat_xmlparser_Parse_impl(self, cls, data, isfinal); exit: @@ -54,13 +64,15 @@ pyexpat_xmlparser_ParseFile(xmlparseobject *self, PyTypeObject *cls, PyObject *c { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:ParseFile", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "ParseFile", 0}; + PyObject *argsbuf[1]; PyObject *file; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &file)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + file = args[0]; return_value = pyexpat_xmlparser_ParseFile_impl(self, cls, file); exit: @@ -164,14 +176,50 @@ pyexpat_xmlparser_ExternalEntityParserCreate(xmlparseobject *self, PyTypeObject { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "", NULL}; - static _PyArg_Parser _parser = {"z|s:ExternalEntityParserCreate", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "ExternalEntityParserCreate", 0}; + PyObject *argsbuf[2]; const char *context; const char *encoding = NULL; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &context, &encoding)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 2, 0, argsbuf); + if (!args) { + goto exit; + } + if (args[0] == Py_None) { + context = NULL; + } + else if (PyUnicode_Check(args[0])) { + Py_ssize_t context_length; + context = PyUnicode_AsUTF8AndSize(args[0], &context_length); + if (context == NULL) { + goto exit; + } + if (strlen(context) != (size_t)context_length) { + PyErr_SetString(PyExc_ValueError, "embedded null character"); + goto exit; + } + } + else { + _PyArg_BadArgument("ExternalEntityParserCreate", "argument 1", "str or None", args[0]); + goto exit; + } + if (nargs < 2) { + goto skip_optional_posonly; + } + if (!PyUnicode_Check(args[1])) { + _PyArg_BadArgument("ExternalEntityParserCreate", "argument 2", "str", args[1]); goto exit; } + Py_ssize_t encoding_length; + encoding = PyUnicode_AsUTF8AndSize(args[1], &encoding_length); + if (encoding == NULL) { + goto exit; + } + if (strlen(encoding) != (size_t)encoding_length) { + PyErr_SetString(PyExc_ValueError, "embedded null character"); + goto exit; + } +skip_optional_posonly: return_value = pyexpat_xmlparser_ExternalEntityParserCreate_impl(self, cls, context, encoding); exit: @@ -235,13 +283,22 @@ pyexpat_xmlparser_UseForeignDTD(xmlparseobject *self, PyTypeObject *cls, PyObjec { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"|p:UseForeignDTD", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "UseForeignDTD", 0}; + PyObject *argsbuf[1]; int flag = 1; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &flag)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 1, 0, argsbuf); + if (!args) { + goto exit; + } + if (nargs < 1) { + goto skip_optional_posonly; + } + flag = PyObject_IsTrue(args[0]); + if (flag < 0) { goto exit; } +skip_optional_posonly: return_value = pyexpat_xmlparser_UseForeignDTD_impl(self, cls, flag); exit: @@ -368,4 +425,4 @@ pyexpat_ErrorString(PyObject *module, PyObject *arg) #ifndef PYEXPAT_XMLPARSER_USEFOREIGNDTD_METHODDEF #define PYEXPAT_XMLPARSER_USEFOREIGNDTD_METHODDEF #endif /* !defined(PYEXPAT_XMLPARSER_USEFOREIGNDTD_METHODDEF) */ -/*[clinic end generated code: output=612b9d6a17a679a7 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=5d60049d385d5d56 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/sha1module.c.h b/Modules/clinic/sha1module.c.h index 3a3ab58c1233c..d9a2e150f6d41 100644 --- a/Modules/clinic/sha1module.c.h +++ b/Modules/clinic/sha1module.c.h @@ -17,18 +17,11 @@ SHA1Type_copy_impl(SHA1object *self, PyTypeObject *cls); static PyObject * SHA1Type_copy(SHA1object *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":copy", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "copy() takes no arguments"); + return NULL; } - return_value = SHA1Type_copy_impl(self, cls); - -exit: - return return_value; + return SHA1Type_copy_impl(self, cls); } PyDoc_STRVAR(SHA1Type_digest__doc__, @@ -126,4 +119,4 @@ _sha1_sha1(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject * exit: return return_value; } -/*[clinic end generated code: output=abf1ab2545cea5a2 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=93ced3c8f8fa4f21 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/sha256module.c.h b/Modules/clinic/sha256module.c.h index 89205c4f14f4e..619fab1a6fe2f 100644 --- a/Modules/clinic/sha256module.c.h +++ b/Modules/clinic/sha256module.c.h @@ -17,18 +17,11 @@ SHA256Type_copy_impl(SHAobject *self, PyTypeObject *cls); static PyObject * SHA256Type_copy(SHAobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":copy", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "copy() takes no arguments"); + return NULL; } - return_value = SHA256Type_copy_impl(self, cls); - -exit: - return return_value; + return SHA256Type_copy_impl(self, cls); } PyDoc_STRVAR(SHA256Type_digest__doc__, @@ -177,4 +170,4 @@ _sha256_sha224(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObje exit: return return_value; } -/*[clinic end generated code: output=b7283f75c9d08f30 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=4f9fe3ca546b0c58 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/sha512module.c.h b/Modules/clinic/sha512module.c.h index f1192d74f9a1a..fada35eff2261 100644 --- a/Modules/clinic/sha512module.c.h +++ b/Modules/clinic/sha512module.c.h @@ -17,18 +17,11 @@ SHA512Type_copy_impl(SHAobject *self, PyTypeObject *cls); static PyObject * SHA512Type_copy(SHAobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":copy", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "copy() takes no arguments"); + return NULL; } - return_value = SHA512Type_copy_impl(self, cls); - -exit: - return return_value; + return SHA512Type_copy_impl(self, cls); } PyDoc_STRVAR(SHA512Type_digest__doc__, @@ -177,4 +170,4 @@ _sha512_sha384(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObje exit: return return_value; } -/*[clinic end generated code: output=9ff9f11937fabf35 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=26d2fe27b9673ac2 input=a9049054013a1b77]*/ diff --git a/Modules/clinic/zlibmodule.c.h b/Modules/clinic/zlibmodule.c.h index 71136d31db0e0..deadf872d0cf7 100644 --- a/Modules/clinic/zlibmodule.c.h +++ b/Modules/clinic/zlibmodule.c.h @@ -352,11 +352,19 @@ zlib_Compress_compress(compobject *self, PyTypeObject *cls, PyObject *const *arg { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"y*:compress", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "compress", 0}; + PyObject *argsbuf[1]; Py_buffer data = {NULL, NULL}; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &data)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { + goto exit; + } + if (PyObject_GetBuffer(args[0], &data, PyBUF_SIMPLE) != 0) { + goto exit; + } + if (!PyBuffer_IsContiguous(&data, 'C')) { + _PyArg_BadArgument("compress", "argument 1", "contiguous buffer", args[0]); goto exit; } return_value = zlib_Compress_compress_impl(self, cls, &data); @@ -399,14 +407,39 @@ zlib_Decompress_decompress(compobject *self, PyTypeObject *cls, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"", "max_length", NULL}; - static _PyArg_Parser _parser = {"y*|n:decompress", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "decompress", 0}; + PyObject *argsbuf[2]; + Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1; Py_buffer data = {NULL, NULL}; Py_ssize_t max_length = 0; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &data, &max_length)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 2, 0, argsbuf); + if (!args) { + goto exit; + } + if (PyObject_GetBuffer(args[0], &data, PyBUF_SIMPLE) != 0) { + goto exit; + } + if (!PyBuffer_IsContiguous(&data, 'C')) { + _PyArg_BadArgument("decompress", "argument 1", "contiguous buffer", args[0]); goto exit; } + if (!noptargs) { + goto skip_optional_pos; + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[1]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + max_length = ival; + } +skip_optional_pos: return_value = zlib_Decompress_decompress_impl(self, cls, &data, max_length); exit: @@ -441,13 +474,22 @@ zlib_Compress_flush(compobject *self, PyTypeObject *cls, PyObject *const *args, { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"|i:flush", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "flush", 0}; + PyObject *argsbuf[1]; int mode = Z_FINISH; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &mode)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 1, 0, argsbuf); + if (!args) { + goto exit; + } + if (nargs < 1) { + goto skip_optional_posonly; + } + mode = _PyLong_AsInt(args[0]); + if (mode == -1 && PyErr_Occurred()) { goto exit; } +skip_optional_posonly: return_value = zlib_Compress_flush_impl(self, cls, mode); exit: @@ -471,18 +513,11 @@ zlib_Compress_copy_impl(compobject *self, PyTypeObject *cls); static PyObject * zlib_Compress_copy(compobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":copy", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "copy() takes no arguments"); + return NULL; } - return_value = zlib_Compress_copy_impl(self, cls); - -exit: - return return_value; + return zlib_Compress_copy_impl(self, cls); } #endif /* defined(HAVE_ZLIB_COPY) */ @@ -503,18 +538,11 @@ zlib_Compress___copy___impl(compobject *self, PyTypeObject *cls); static PyObject * zlib_Compress___copy__(compobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":__copy__", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "__copy__() takes no arguments"); + return NULL; } - return_value = zlib_Compress___copy___impl(self, cls); - -exit: - return return_value; + return zlib_Compress___copy___impl(self, cls); } #endif /* defined(HAVE_ZLIB_COPY) */ @@ -538,13 +566,15 @@ zlib_Compress___deepcopy__(compobject *self, PyTypeObject *cls, PyObject *const { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:__deepcopy__", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "__deepcopy__", 0}; + PyObject *argsbuf[1]; PyObject *memo; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &memo)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + memo = args[0]; return_value = zlib_Compress___deepcopy___impl(self, cls, memo); exit: @@ -570,18 +600,11 @@ zlib_Decompress_copy_impl(compobject *self, PyTypeObject *cls); static PyObject * zlib_Decompress_copy(compobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":copy", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "copy() takes no arguments"); + return NULL; } - return_value = zlib_Decompress_copy_impl(self, cls); - -exit: - return return_value; + return zlib_Decompress_copy_impl(self, cls); } #endif /* defined(HAVE_ZLIB_COPY) */ @@ -602,18 +625,11 @@ zlib_Decompress___copy___impl(compobject *self, PyTypeObject *cls); static PyObject * zlib_Decompress___copy__(compobject *self, PyTypeObject *cls, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) { - PyObject *return_value = NULL; - static const char * const _keywords[] = { NULL}; - static _PyArg_Parser _parser = {":__copy__", _keywords, 0}; - - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser - )) { - goto exit; + if (nargs) { + PyErr_SetString(PyExc_TypeError, "__copy__() takes no arguments"); + return NULL; } - return_value = zlib_Decompress___copy___impl(self, cls); - -exit: - return return_value; + return zlib_Decompress___copy___impl(self, cls); } #endif /* defined(HAVE_ZLIB_COPY) */ @@ -637,13 +653,15 @@ zlib_Decompress___deepcopy__(compobject *self, PyTypeObject *cls, PyObject *cons { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"O:__deepcopy__", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "__deepcopy__", 0}; + PyObject *argsbuf[1]; PyObject *memo; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &memo)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf); + if (!args) { goto exit; } + memo = args[0]; return_value = zlib_Decompress___deepcopy___impl(self, cls, memo); exit: @@ -673,13 +691,30 @@ zlib_Decompress_flush(compobject *self, PyTypeObject *cls, PyObject *const *args { PyObject *return_value = NULL; static const char * const _keywords[] = {"", NULL}; - static _PyArg_Parser _parser = {"|n:flush", _keywords, 0}; + static _PyArg_Parser _parser = {NULL, _keywords, "flush", 0}; + PyObject *argsbuf[1]; Py_ssize_t length = DEF_BUF_SIZE; - if (!_PyArg_ParseStackAndKeywords(args, nargs, kwnames, &_parser, - &length)) { + args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 0, 1, 0, argsbuf); + if (!args) { goto exit; } + if (nargs < 1) { + goto skip_optional_posonly; + } + { + Py_ssize_t ival = -1; + PyObject *iobj = _PyNumber_Index(args[0]); + if (iobj != NULL) { + ival = PyLong_AsSsize_t(iobj); + Py_DECREF(iobj); + } + if (ival == -1 && PyErr_Occurred()) { + goto exit; + } + length = ival; + } +skip_optional_posonly: return_value = zlib_Decompress_flush_impl(self, cls, length); exit: @@ -820,4 +855,4 @@ zlib_crc32(PyObject *module, PyObject *const *args, Py_ssize_t nargs) #ifndef ZLIB_DECOMPRESS___DEEPCOPY___METHODDEF #define ZLIB_DECOMPRESS___DEEPCOPY___METHODDEF #endif /* !defined(ZLIB_DECOMPRESS___DEEPCOPY___METHODDEF) */ -/*[clinic end generated code: output=f009d194565416d1 input=a9049054013a1b77]*/ +/*[clinic end generated code: output=bb1e27d8b2198a86 input=a9049054013a1b77]*/ diff --git a/Tools/clinic/clinic.py b/Tools/clinic/clinic.py index 14252b2514ea8..f660474da94a0 100755 --- a/Tools/clinic/clinic.py +++ b/Tools/clinic/clinic.py @@ -639,6 +639,10 @@ def output_templates(self, f): assert parameters assert isinstance(parameters[0].converter, self_converter) del parameters[0] + requires_defining_class = False + if parameters and isinstance(parameters[0].converter, defining_class_converter): + requires_defining_class = True + del parameters[0] converters = [p.converter for p in parameters] has_option_groups = parameters and (parameters[0].group or parameters[-1].group) @@ -667,10 +671,6 @@ def output_templates(self, f): if not p.is_optional(): min_pos = i - requires_defining_class = any( - isinstance(p.converter, defining_class_converter) - for p in parameters) - meth_o = (len(parameters) == 1 and parameters[0].is_positional_only() and not converters[0].is_optional() and @@ -773,24 +773,40 @@ def parser_body(prototype, *fields, declarations=''): return linear_format(output(), parser_declarations=declarations) if not parameters: - # no parameters, METH_NOARGS + if not requires_defining_class: + # no parameters, METH_NOARGS + flags = "METH_NOARGS" - flags = "METH_NOARGS" + parser_prototype = normalize_snippet(""" + static PyObject * + {c_basename}({self_type}{self_name}, PyObject *Py_UNUSED(ignored)) + """) + parser_code = [] - parser_prototype = normalize_snippet(""" - static PyObject * - {c_basename}({self_type}{self_name}, PyObject *Py_UNUSED(ignored)) - """) - parser_definition = parser_prototype + else: + assert not new_or_init - if default_return_converter: - parser_definition = parser_prototype + '\n' + normalize_snippet(""" - {{ - return {c_basename}_impl({impl_arguments}); + flags = "METH_METHOD|METH_FASTCALL|METH_KEYWORDS" + + parser_prototype = parser_prototype_def_class + return_error = ('return NULL;' if default_return_converter + else 'goto exit;') + parser_code = [normalize_snippet(""" + if (nargs) {{ + PyErr_SetString(PyExc_TypeError, "{name}() takes no arguments"); + %s }} - """) + """ % return_error, indent=4)] + + if default_return_converter: + parser_definition = '\n'.join([ + parser_prototype, + '{{', + *parser_code, + ' return {c_basename}_impl({impl_arguments});', + '}}']) else: - parser_definition = parser_body(parser_prototype) + parser_definition = parser_body(parser_prototype, *parser_code) elif meth_o: flags = "METH_O" @@ -993,6 +1009,9 @@ def parser_body(prototype, *fields, declarations=''): add_label = None for i, p in enumerate(parameters): + if isinstance(p.converter, defining_class_converter): + raise ValueError("defining_class should be the first " + "parameter (after self)") displayname = p.get_displayname(i+1) parsearg = p.converter.parse_arg(argname_fmt % i, displayname) if parsearg is None:

1 0

gh-91760: Deprecate group names and numbers which will be invalid in future (GH-91794)
by serhiy-storchaka April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/19dca041212f9f58ee11833bff3f8c157d… commit: 19dca041212f9f58ee11833bff3f8c157d4fd3e8 branch: main author: Serhiy Storchaka <storchaka(a)gmail.com> committer: serhiy-storchaka <storchaka(a)gmail.com> date: 2022-04-30T13:13:46+03:00 summary: gh-91760: Deprecate group names and numbers which will be invalid in future (GH-91794) Only sequence of ASCII digits will be accepted as a numerical reference. The group name in bytes patterns and replacement strings could only contain ASCII letters and digits and underscore. files: A Misc/NEWS.d/next/Library/2022-04-21-19-46-03.gh-issue-91760.zDtv1E.rst M Doc/library/re.rst M Doc/whatsnew/3.11.rst M Lib/re/_parser.py M Lib/test/test_re.py diff --git a/Doc/library/re.rst b/Doc/library/re.rst index 89de9286ace79..3cd9f252fee6f 100644 --- a/Doc/library/re.rst +++ b/Doc/library/re.rst @@ -417,6 +417,9 @@ The special characters are: | | * ``\1`` | +---------------------------------------+----------------------------------+ + .. deprecated:: 3.11 + Group names containing non-ASCII characters in bytes patterns. + .. index:: single: (?P=; in regular expressions ``(?P=name)`` @@ -486,6 +489,9 @@ The special characters are: will match with ``'<user(a)host.com>'`` as well as ``'user(a)host.com'``, but not with ``'<user(a)host.com'`` nor ``'user(a)host.com>'``. + .. deprecated:: 3.11 + Group *id* containing anything except ASCII digits. + The special sequences consist of ``'\'`` and a character from the list below. If the ordinary character is not an ASCII digit or an ASCII letter, then the @@ -995,6 +1001,10 @@ form. Empty matches for the pattern are replaced when adjacent to a previous non-empty match. + .. deprecated:: 3.11 + Group *id* containing anything except ASCII digits. + Group names containing non-ASCII characters in bytes replacement strings. + .. function:: subn(pattern, repl, string, count=0, flags=0) diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst index fdd35ce14317e..1a692f2fe7f60 100644 --- a/Doc/whatsnew/3.11.rst +++ b/Doc/whatsnew/3.11.rst @@ -1151,6 +1151,14 @@ Deprecated (Contributed by Brett Cannon in :issue:`47061` and Victor Stinner in :gh:`68966`.) +* More strict rules will be applied now applied for numerical group references + and group names in regular expressions in future Python versions. + Only sequence of ASCII digits will be now accepted as a numerical reference. + The group name in bytes patterns and replacement strings could only + contain ASCII letters and digits and underscore. + For now, a deprecation warning is raised for such syntax. + (Contributed by Serhiy Storchaka in :gh:`91760`.) + Removed ======= diff --git a/Lib/re/_parser.py b/Lib/re/_parser.py index 933d51589f46c..a393c508d86e5 100644 --- a/Lib/re/_parser.py +++ b/Lib/re/_parser.py @@ -287,8 +287,22 @@ def seek(self, index): self.__next() def error(self, msg, offset=0): + if not self.istext: + msg = msg.encode('ascii', 'backslashreplace').decode('ascii') return error(msg, self.string, self.tell() - offset) + def checkgroupname(self, name, offset, nested): + if not name.isidentifier(): + msg = "bad character in group name %r" % name + raise self.error(msg, len(name) + offset) + if not (self.istext or name.isascii()): + import warnings + warnings.warn( + "bad character in group name %a at position %d" % + (name, self.tell() - len(name) - offset), + DeprecationWarning, stacklevel=nested + 7 + ) + def _class_escape(source, escape): # handle escape code inside character class code = ESCAPES.get(escape) @@ -703,15 +717,11 @@ def _parse(source, state, verbose, nested, first=False): if sourcematch("<"): # named group: skip forward to end of name name = source.getuntil(">", "group name") - if not name.isidentifier(): - msg = "bad character in group name %r" % name - raise source.error(msg, len(name) + 1) + source.checkgroupname(name, 1, nested) elif sourcematch("="): # named backreference name = source.getuntil(")", "group name") - if not name.isidentifier(): - msg = "bad character in group name %r" % name - raise source.error(msg, len(name) + 1) + source.checkgroupname(name, 1, nested) gid = state.groupdict.get(name) if gid is None: msg = "unknown group name %r" % name @@ -773,6 +783,7 @@ def _parse(source, state, verbose, nested, first=False): # conditional backreference group condname = source.getuntil(")", "group name") if condname.isidentifier(): + source.checkgroupname(condname, 1, nested) condgroup = state.groupdict.get(condname) if condgroup is None: msg = "unknown group name %r" % condname @@ -795,6 +806,14 @@ def _parse(source, state, verbose, nested, first=False): state.grouprefpos[condgroup] = ( source.tell() - len(condname) - 1 ) + if not (condname.isdecimal() and condname.isascii()): + import warnings + warnings.warn( + "bad character in group name %s at position %d" % + (repr(condname) if source.istext else ascii(condname), + source.tell() - len(condname) - 1), + DeprecationWarning, stacklevel=nested + 6 + ) state.checklookbehindgroup(condgroup, source) item_yes = _parse(source, state, verbose, nested + 1) if source.match("|"): @@ -1000,11 +1019,11 @@ def addgroup(index, pos): # group c = this[1] if c == "g": - name = "" if not s.match("<"): raise s.error("missing <") name = s.getuntil(">", "group name") if name.isidentifier(): + s.checkgroupname(name, 1, -1) try: index = groupindex[name] except KeyError: @@ -1020,6 +1039,14 @@ def addgroup(index, pos): if index >= MAXGROUPS: raise s.error("invalid group reference %d" % index, len(name) + 1) + if not (name.isdecimal() and name.isascii()): + import warnings + warnings.warn( + "bad character in group name %s at position %d" % + (repr(name) if s.istext else ascii(name), + s.tell() - len(name) - 1), + DeprecationWarning, stacklevel=5 + ) addgroup(index, len(name) + 1) elif c == "0": if s.next in OCTDIGITS: diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py index a4c2f1f3e4ba3..c1014753802c9 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -135,6 +135,7 @@ def test_basic_re_sub(self): self.assertEqual(re.sub('(?P<a>x)', r'\g<a>\g<1>', 'xx'), 'xxxx') self.assertEqual(re.sub('(?P<unk>x)', r'\g<unk>\g<unk>', 'xx'), 'xxxx') self.assertEqual(re.sub('(?P<unk>x)', r'\g<1>\g<1>', 'xx'), 'xxxx') + self.assertEqual(re.sub('()x', r'\g<0>\g<0>', 'xx'), 'xxxx') self.assertEqual(re.sub('a', r'\t\n\v\r\f\a\b', 'a'), '\t\n\v\r\f\a\b') self.assertEqual(re.sub('a', '\t\n\v\r\f\a\b', 'a'), '\t\n\v\r\f\a\b') @@ -274,6 +275,21 @@ def test_symbolic_groups_errors(self): self.checkPatternError('(?P<©>x)', "bad character in group name '©'", 4) self.checkPatternError('(?P=©)', "bad character in group name '©'", 4) self.checkPatternError('(?(©)y)', "bad character in group name '©'", 3) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '\\xc2\\xb5' " + r"at position 4") as w: + re.compile(b'(?P<\xc2\xb5>x)') + self.assertEqual(w.filename, __file__) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '\\xc2\\xb5' " + r"at position 4"): + self.checkPatternError(b'(?P=\xc2\xb5)', + r"unknown group name '\xc2\xb5'", 4) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '\\xc2\\xb5' " + r"at position 3"): + self.checkPatternError(b'(?(\xc2\xb5)y)', + r"unknown group name '\xc2\xb5'", 3) def test_symbolic_refs(self): self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\g<b>', 'xx'), '') @@ -306,12 +322,35 @@ def test_symbolic_refs_errors(self): re.sub('(?P<a>x)', r'\g<ab>', 'xx') self.checkTemplateError('(?P<a>x)', r'\g<-1>', 'xx', "bad character in group name '-1'", 3) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '\+1' " + r"at position 3") as w: + re.sub('(?P<a>x)', r'\g<+1>', 'xx') + self.assertEqual(w.filename, __file__) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '1_0' " + r"at position 3"): + re.sub('()'*10, r'\g<1_0>', 'xx') + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name ' 1 ' " + r"at position 3"): + re.sub('(?P<a>x)', r'\g< 1 >', 'xx') self.checkTemplateError('(?P<a>x)', r'\g<©>', 'xx', "bad character in group name '©'", 3) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '\\xc2\\xb5' " + r"at position 3") as w: + with self.assertRaisesRegex(IndexError, "unknown group name '\xc2\xb5'"): + re.sub(b'(?P<a>x)', b'\\g<\xc2\xb5>', b'xx') + self.assertEqual(w.filename, __file__) self.checkTemplateError('(?P<a>x)', r'\g<㊀>', 'xx', "bad character in group name '㊀'", 3) self.checkTemplateError('(?P<a>x)', r'\g<¹>', 'xx', "bad character in group name '¹'", 3) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '१' " + r"at position 3"): + re.sub('(?P<a>x)', r'\g<१>', 'xx') def test_re_subn(self): self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2)) @@ -577,10 +616,27 @@ def test_re_groupref_exists_errors(self): self.checkPatternError(r'(?P<a>)(?(0)a|b)', 'bad group number', 10) self.checkPatternError(r'()(?(-1)a|b)', "bad character in group name '-1'", 5) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '\+1' " + r"at position 5") as w: + re.compile(r'()(?(+1)a|b)') + self.assertEqual(w.filename, __file__) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '1_0' " + r"at position 23"): + re.compile(r'()'*10 + r'(?(1_0)a|b)') + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name ' 1 ' " + r"at position 5"): + re.compile(r'()(?( 1 )a|b)') self.checkPatternError(r'()(?(㊀)a|b)', "bad character in group name '㊀'", 5) self.checkPatternError(r'()(?(¹)a|b)', "bad character in group name '¹'", 5) + with self.assertWarnsRegex(DeprecationWarning, + r"bad character in group name '१' " + r"at position 5"): + re.compile(r'()(?(१)a|b)') self.checkPatternError(r'()(?(1', "missing ), unterminated name", 5) self.checkPatternError(r'()(?(1)a', diff --git a/Misc/NEWS.d/next/Library/2022-04-21-19-46-03.gh-issue-91760.zDtv1E.rst b/Misc/NEWS.d/next/Library/2022-04-21-19-46-03.gh-issue-91760.zDtv1E.rst new file mode 100644 index 0000000000000..0bddbbe093144 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2022-04-21-19-46-03.gh-issue-91760.zDtv1E.rst @@ -0,0 +1,4 @@ +More strict rules will be applied for numerical group references and group +names in regular expressions. For now, a deprecation warning is emitted for +group references and group names which will be errors in future Python +versions.

1 0

gh-92049: Forbid pickling constants re._constants.SUCCESS etc (GH-92070)
by serhiy-storchaka April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/6d0d547033e295f91f05030322acfbb0e2… commit: 6d0d547033e295f91f05030322acfbb0e280fc1f branch: main author: Serhiy Storchaka <storchaka(a)gmail.com> committer: serhiy-storchaka <storchaka(a)gmail.com> date: 2022-04-30T13:03:23+03:00 summary: gh-92049: Forbid pickling constants re._constants.SUCCESS etc (GH-92070) Previously, pickling did not fail, but the result could not be unpickled. files: A Misc/NEWS.d/next/Library/2022-04-30-10-53-10.gh-issue-92049.5SEKoh.rst M Lib/re/_constants.py diff --git a/Lib/re/_constants.py b/Lib/re/_constants.py index c45ce409e21b8..71204d903b322 100644 --- a/Lib/re/_constants.py +++ b/Lib/re/_constants.py @@ -62,6 +62,8 @@ def __new__(cls, value, name): def __repr__(self): return self.name + __reduce__ = None + MAXREPEAT = _NamedIntConstant(MAXREPEAT, 'MAXREPEAT') def _makecodes(*names): diff --git a/Misc/NEWS.d/next/Library/2022-04-30-10-53-10.gh-issue-92049.5SEKoh.rst b/Misc/NEWS.d/next/Library/2022-04-30-10-53-10.gh-issue-92049.5SEKoh.rst new file mode 100644 index 0000000000000..cad4621c65096 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2022-04-30-10-53-10.gh-issue-92049.5SEKoh.rst @@ -0,0 +1,2 @@ +Forbid pickling constants ``re._constants.SUCCESS`` etc. Previously, +pickling did not fail, but the result could not be unpickled.

1 0

gh-91954: Emit EncodingWarning from locale and subprocess (GH-91977)
by methane April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/354ace8b07e7d445fd2de713b6af127153… commit: 354ace8b07e7d445fd2de713b6af1271536adce0 branch: main author: Inada Naoki <songofacandy(a)gmail.com> committer: methane <songofacandy(a)gmail.com> date: 2022-04-30T15:53:29+09:00 summary: gh-91954: Emit EncodingWarning from locale and subprocess (GH-91977) locale.getpreferredencoding() and subprocess.Popen() emit EncodingWarning files: A Misc/NEWS.d/next/Library/2022-04-27-13-30-26.gh-issue-91954.cC7ga_.rst M Doc/library/subprocess.rst M Lib/locale.py M Lib/subprocess.py M Lib/test/test_subprocess.py diff --git a/Doc/library/subprocess.rst b/Doc/library/subprocess.rst index fca5549649268..6a334acc5a17c 100644 --- a/Doc/library/subprocess.rst +++ b/Doc/library/subprocess.rst @@ -619,7 +619,7 @@ functions. If *encoding* or *errors* are specified, or *text* is true, the file objects *stdin*, *stdout* and *stderr* are opened in text mode with the specified - encoding and *errors*, as described above in :ref:`frequently-used-arguments`. + *encoding* and *errors*, as described above in :ref:`frequently-used-arguments`. The *universal_newlines* argument is equivalent to *text* and is provided for backwards compatibility. By default, file objects are opened in binary mode. @@ -1445,12 +1445,13 @@ This module also provides the following legacy functions from the 2.x none of the guarantees described above regarding security and exception handling consistency are valid for these functions. -.. function:: getstatusoutput(cmd) +.. function:: getstatusoutput(cmd, *, encoding=None, errors=None) Return ``(exitcode, output)`` of executing *cmd* in a shell. Execute the string *cmd* in a shell with :meth:`Popen.check_output` and - return a 2-tuple ``(exitcode, output)``. The locale encoding is used; + return a 2-tuple ``(exitcode, output)``. + *encoding* and *errors* are used to decode output; see the notes on :ref:`frequently-used-arguments` for more details. A trailing newline is stripped from the output. @@ -1475,8 +1476,10 @@ handling consistency are valid for these functions. as it did in Python 3.3.3 and earlier. exitcode has the same value as :attr:`~Popen.returncode`. + .. versionadded:: 3.11 + Added *encoding* and *errors* arguments. -.. function:: getoutput(cmd) +.. function:: getoutput(cmd, *, encoding=None, errors=None) Return output (stdout and stderr) of executing *cmd* in a shell. @@ -1491,6 +1494,9 @@ handling consistency are valid for these functions. .. versionchanged:: 3.3.4 Windows support added + .. versionadded:: 3.11 + Added *encoding* and *errors* arguments. + Notes ----- diff --git a/Lib/locale.py b/Lib/locale.py index 170e5eea45b8c..25eb75ac65a32 100644 --- a/Lib/locale.py +++ b/Lib/locale.py @@ -655,6 +655,11 @@ def getencoding(): except NameError: def getpreferredencoding(do_setlocale=True): """Return the charset that the user is likely using.""" + if sys.flags.warn_default_encoding: + import warnings + warnings.warn( + "UTF-8 Mode affects locale.getpreferredencoding(). Consider locale.getencoding() instead.", + EncodingWarning, 2) if sys.flags.utf8_mode: return 'utf-8' return getencoding() @@ -663,6 +668,12 @@ def getpreferredencoding(do_setlocale=True): def getpreferredencoding(do_setlocale=True): """Return the charset that the user is likely using, according to the system configuration.""" + + if sys.flags.warn_default_encoding: + import warnings + warnings.warn( + "UTF-8 Mode affects locale.getpreferredencoding(). Consider locale.getencoding() instead.", + EncodingWarning, 2) if sys.flags.utf8_mode: return 'utf-8' diff --git a/Lib/subprocess.py b/Lib/subprocess.py index a5fa152715c14..968cfc14ddf91 100644 --- a/Lib/subprocess.py +++ b/Lib/subprocess.py @@ -43,6 +43,7 @@ import builtins import errno import io +import locale import os import time import signal @@ -344,6 +345,26 @@ def _args_from_interpreter_flags(): return args +def _text_encoding(): + # Return default text encoding and emit EncodingWarning if + # sys.flags.warn_default_encoding is true. + if sys.flags.warn_default_encoding: + f = sys._getframe() + filename = f.f_code.co_filename + stacklevel = 2 + while f := f.f_back: + if f.f_code.co_filename != filename: + break + stacklevel += 1 + warnings.warn("'encoding' argument not specified.", + EncodingWarning, stacklevel) + + if sys.flags.utf8_mode: + return "utf-8" + else: + return locale.getencoding() + + def call(*popenargs, timeout=None, **kwargs): """Run command with arguments. Wait for command to complete or timeout, then return the returncode attribute. @@ -610,7 +631,7 @@ def list2cmdline(seq): # Various tools for executing commands and looking at their output and status. # -def getstatusoutput(cmd): +def getstatusoutput(cmd, *, encoding=None, errors=None): """Return (exitcode, output) of executing cmd in a shell. Execute the string 'cmd' in a shell with 'check_output' and @@ -632,7 +653,8 @@ def getstatusoutput(cmd): (-15, '') """ try: - data = check_output(cmd, shell=True, text=True, stderr=STDOUT) + data = check_output(cmd, shell=True, text=True, stderr=STDOUT, + encoding=encoding, errors=errors) exitcode = 0 except CalledProcessError as ex: data = ex.output @@ -641,7 +663,7 @@ def getstatusoutput(cmd): data = data[:-1] return exitcode, data -def getoutput(cmd): +def getoutput(cmd, *, encoding=None, errors=None): """Return output (stdout or stderr) of executing cmd in a shell. Like getstatusoutput(), except the exit status is ignored and the return @@ -651,7 +673,8 @@ def getoutput(cmd): >>> subprocess.getoutput('ls /bin/ls') '/bin/ls' """ - return getstatusoutput(cmd)[1] + return getstatusoutput(cmd, encoding=encoding, errors=errors)[1] + def _use_posix_spawn(): @@ -858,13 +881,8 @@ def __init__(self, args, bufsize=-1, executable=None, errread = msvcrt.open_osfhandle(errread.Detach(), 0) self.text_mode = encoding or errors or text or universal_newlines - - # PEP 597: We suppress the EncodingWarning in subprocess module - # for now (at Python 3.10), because we focus on files for now. - # This will be changed to encoding = io.text_encoding(encoding) - # in the future. if self.text_mode and encoding is None: - self.encoding = encoding = "locale" + self.encoding = encoding = _text_encoding() # How long to resume waiting on a child after the first ^C. # There is no right value for this. The purpose is to be polite diff --git a/Lib/test/test_subprocess.py b/Lib/test/test_subprocess.py index 99b5947e54be6..5814a6d924e12 100644 --- a/Lib/test/test_subprocess.py +++ b/Lib/test/test_subprocess.py @@ -1733,6 +1733,20 @@ def test_run_with_shell_timeout_and_capture_output(self): msg="TimeoutExpired was delayed! Bad traceback:\n```\n" f"{stacks}```") + def test_encoding_warning(self): + code = textwrap.dedent("""\ + from subprocess import * + args = ["echo", "hello"] + run(args, text=True) + check_output(args, text=True) + """) + cp = subprocess.run([sys.executable, "-Xwarn_default_encoding", "-c", code], + capture_output=True) + lines = cp.stderr.splitlines() + self.assertEqual(len(lines), 2) + self.assertTrue(lines[0].startswith(b"<string>:3: EncodingWarning: ")) + self.assertTrue(lines[1].startswith(b"<string>:4: EncodingWarning: ")) + def _get_test_grp_name(): for name_group in ('staff', 'nogroup', 'grp', 'nobody', 'nfsnobody'): diff --git a/Misc/NEWS.d/next/Library/2022-04-27-13-30-26.gh-issue-91954.cC7ga_.rst b/Misc/NEWS.d/next/Library/2022-04-27-13-30-26.gh-issue-91954.cC7ga_.rst new file mode 100644 index 0000000000000..b63db25f32a4f --- /dev/null +++ b/Misc/NEWS.d/next/Library/2022-04-27-13-30-26.gh-issue-91954.cC7ga_.rst @@ -0,0 +1,2 @@ +Add *encoding* and *errors* arguments to :func:`subprocess.getoutput` and +:func:`subprocess.getstatusoutput`.

1 0

gh-91880 - fix typo (GH-92069)
by miss-islington April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/c7b7f12b8609f932a23a9bc96a5de7cd9e… commit: c7b7f12b8609f932a23a9bc96a5de7cd9ecd5723 branch: main author: David Hewitt <1939362+davidhewitt(a)users.noreply.github.com> committer: miss-islington <31488909+miss-islington(a)users.noreply.github.com> date: 2022-04-29T22:23:54-07:00 summary: gh-91880 - fix typo (GH-92069) https://github.com/python/cpython/issues/91880#issuecomment-1113914241 - With thanks to @MojoVampire for spotting this. Automerge-Triggered-By: GH:gvanrossum files: M Lib/asyncio/runners.py diff --git a/Lib/asyncio/runners.py b/Lib/asyncio/runners.py index d274576b10134..065691bed9928 100644 --- a/Lib/asyncio/runners.py +++ b/Lib/asyncio/runners.py @@ -106,7 +106,7 @@ def run(self, coro, *, context=None): # `signal.signal` may throw if `threading.main_thread` does # not support signals (e.g. embedded interpreter with signals # not registered - see gh-91880) - signal_handler = None + sigint_handler = None else: sigint_handler = None

1 0

bpo-43224: Implement substitution of unpacked TypeVarTuple in C (GH-31828)
by serhiy-storchaka April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/e8c2f72b94ae5dfba50c0f2e2c06b7ee97… commit: e8c2f72b94ae5dfba50c0f2e2c06b7ee975c8acb branch: main author: Serhiy Storchaka <storchaka(a)gmail.com> committer: serhiy-storchaka <storchaka(a)gmail.com> date: 2022-04-30T08:22:46+03:00 summary: bpo-43224: Implement substitution of unpacked TypeVarTuple in C (GH-31828) Co-authored-by: Matthew Rahtz <mrahtz(a)gmail.com> files: M Include/internal/pycore_global_strings.h M Include/internal/pycore_runtime_init.h M Lib/test/test_typing.py M Lib/typing.py M Objects/genericaliasobject.c diff --git a/Include/internal/pycore_global_strings.h b/Include/internal/pycore_global_strings.h index cc94662256e87..28fffa95071a0 100644 --- a/Include/internal/pycore_global_strings.h +++ b/Include/internal/pycore_global_strings.h @@ -202,6 +202,7 @@ struct _Py_global_strings { STRUCT_FOR_ID(__truediv__) STRUCT_FOR_ID(__trunc__) STRUCT_FOR_ID(__typing_subst__) + STRUCT_FOR_ID(__typing_unpacked__) STRUCT_FOR_ID(__warningregistry__) STRUCT_FOR_ID(__weakref__) STRUCT_FOR_ID(__xor__) diff --git a/Include/internal/pycore_runtime_init.h b/Include/internal/pycore_runtime_init.h index 9a3a9d04324ba..941badfc8cb6a 100644 --- a/Include/internal/pycore_runtime_init.h +++ b/Include/internal/pycore_runtime_init.h @@ -825,6 +825,7 @@ extern "C" { INIT_ID(__truediv__), \ INIT_ID(__trunc__), \ INIT_ID(__typing_subst__), \ + INIT_ID(__typing_unpacked__), \ INIT_ID(__warningregistry__), \ INIT_ID(__weakref__), \ INIT_ID(__xor__), \ diff --git a/Lib/test/test_typing.py b/Lib/test/test_typing.py index 412d117c238da..88be2850acb1c 100644 --- a/Lib/test/test_typing.py +++ b/Lib/test/test_typing.py @@ -754,89 +754,89 @@ class C(Generic[*Ts]): pass tests = [ # Alias # Args # Expected result ('C[*Ts]', '[()]', 'C[()]'), - ('tuple[*Ts]', '[()]', 'TypeError'), # Should be tuple[()] + ('tuple[*Ts]', '[()]', 'tuple[()]'), ('Tuple[*Ts]', '[()]', 'Tuple[()]'), ('C[*Ts]', '[int]', 'C[int]'), - ('tuple[*Ts]', '[int]', 'tuple[(int,),]'), # Should be tuple[int] + ('tuple[*Ts]', '[int]', 'tuple[int]'), ('Tuple[*Ts]', '[int]', 'Tuple[int]'), ('C[*Ts]', '[int, str]', 'C[int, str]'), - ('tuple[*Ts]', '[int, str]', 'TypeError'), # Should be tuple[int, str] + ('tuple[*Ts]', '[int, str]', 'tuple[int, str]'), ('Tuple[*Ts]', '[int, str]', 'Tuple[int, str]'), ('C[*Ts]', '[*tuple_type[int]]', 'C[*tuple_type[int]]'), # Should be C[int] - ('tuple[*Ts]', '[*tuple_type[int]]', 'tuple[(*tuple_type[int],),]'), # Should be tuple[int] + ('tuple[*Ts]', '[*tuple_type[int]]', 'tuple[*tuple_type[int]]'), # Should be tuple[int] ('Tuple[*Ts]', '[*tuple_type[int]]', 'Tuple[*tuple_type[int]]'), # Should be Tuple[int] ('C[*Ts]', '[*tuple_type[*Ts]]', 'C[*tuple_type[*Ts]]'), # Should be C[*Ts] - ('tuple[*Ts]', '[*tuple_type[*Ts]]', 'tuple[(*tuple_type[*Ts],),]'), # Should be tuple[*Ts] + ('tuple[*Ts]', '[*tuple_type[*Ts]]', 'tuple[*tuple_type[*Ts]]'), # Should be tuple[*Ts] ('Tuple[*Ts]', '[*tuple_type[*Ts]]', 'Tuple[*tuple_type[*Ts]]'), # Should be Tuple[*Ts] ('C[*Ts]', '[*tuple_type[int, str]]', 'C[*tuple_type[int, str]]'), # Should be C[int, str] - ('tuple[*Ts]', '[*tuple_type[int, str]]', 'tuple[(*tuple_type[int, str],),]'), # Should be tuple[int, str] + ('tuple[*Ts]', '[*tuple_type[int, str]]', 'tuple[*tuple_type[int, str]]'), # Should be tuple[int, str] ('Tuple[*Ts]', '[*tuple_type[int, str]]', 'Tuple[*tuple_type[int, str]]'), # Should be Tuple[int, str] ('C[*Ts]', '[tuple_type[int, ...]]', 'C[tuple_type[int, ...]]'), - ('tuple[*Ts]', '[tuple_type[int, ...]]', 'tuple[(tuple_type[int, ...],),]'), # Should be tuple[tuple_type[int, ...]] + ('tuple[*Ts]', '[tuple_type[int, ...]]', 'tuple[tuple_type[int, ...]]'), ('Tuple[*Ts]', '[tuple_type[int, ...]]', 'Tuple[tuple_type[int, ...]]'), ('C[*Ts]', '[tuple_type[int, ...], tuple_type[str, ...]]', 'C[tuple_type[int, ...], tuple_type[str, ...]]'), - ('tuple[*Ts]', '[tuple_type[int, ...], tuple_type[str, ...]]', 'TypeError'), # Should be tuple[tuple_type[int, ...], tuple_type[str, ...]] + ('tuple[*Ts]', '[tuple_type[int, ...], tuple_type[str, ...]]', 'tuple[tuple_type[int, ...], tuple_type[str, ...]]'), ('Tuple[*Ts]', '[tuple_type[int, ...], tuple_type[str, ...]]', 'Tuple[tuple_type[int, ...], tuple_type[str, ...]]'), ('C[*Ts]', '[*tuple_type[int, ...]]', 'C[*tuple_type[int, ...]]'), - ('tuple[*Ts]', '[*tuple_type[int, ...]]', 'tuple[(*tuple_type[int, ...],),]'), # Should be tuple[*tuple_type[int, ...]] + ('tuple[*Ts]', '[*tuple_type[int, ...]]', 'tuple[*tuple_type[int, ...]]'), ('Tuple[*Ts]', '[*tuple_type[int, ...]]', 'Tuple[*tuple_type[int, ...]]'), # Technically, multiple unpackings are forbidden by PEP 646, but we # choose to be less restrictive at runtime, to allow folks room # to experiment. So all three of these should be valid. ('C[*Ts]', '[*tuple_type[int, ...], *tuple_type[str, ...]]', 'C[*tuple_type[int, ...], *tuple_type[str, ...]]'), - # Should be tuple[*tuple_type[int, ...], *tuple_type[str, ...]], to match the other two. - ('tuple[*Ts]', '[*tuple_type[int, ...], *tuple_type[str, ...]]', 'TypeError'), + ('tuple[*Ts]', '[*tuple_type[int, ...], *tuple_type[str, ...]]', 'tuple[*tuple_type[int, ...], *tuple_type[str, ...]]'), ('Tuple[*Ts]', '[*tuple_type[int, ...], *tuple_type[str, ...]]', 'Tuple[*tuple_type[int, ...], *tuple_type[str, ...]]'), ('C[*Ts]', '[*Ts]', 'C[*Ts]'), - ('tuple[*Ts]', '[*Ts]', 'tuple[(*Ts,),]'), # Should be tuple[*Ts] + ('tuple[*Ts]', '[*Ts]', 'tuple[*Ts]'), ('Tuple[*Ts]', '[*Ts]', 'Tuple[*Ts]'), ('C[*Ts]', '[T, *Ts]', 'C[T, *Ts]'), - ('tuple[*Ts]', '[T, *Ts]', 'TypeError'), # Should be tuple[T, *Ts] + ('tuple[*Ts]', '[T, *Ts]', 'tuple[T, *Ts]'), ('Tuple[*Ts]', '[T, *Ts]', 'Tuple[T, *Ts]'), ('C[*Ts]', '[*Ts, T]', 'C[*Ts, T]'), - ('tuple[*Ts]', '[*Ts, T]', 'TypeError'), # Should be tuple[*Ts, T] + ('tuple[*Ts]', '[*Ts, T]', 'tuple[*Ts, T]'), ('Tuple[*Ts]', '[*Ts, T]', 'Tuple[*Ts, T]'), ('C[T, *Ts]', '[int]', 'C[int]'), - ('tuple[T, *Ts]', '[int]', 'TypeError'), # Should be tuple[int] + ('tuple[T, *Ts]', '[int]', 'tuple[int]'), ('Tuple[T, *Ts]', '[int]', 'Tuple[int]'), ('C[T, *Ts]', '[int, str]', 'C[int, str]'), - ('tuple[T, *Ts]', '[int, str]', 'tuple[int, (str,)]'), # Should be tuple[int, str] + ('tuple[T, *Ts]', '[int, str]', 'tuple[int, str]'), ('Tuple[T, *Ts]', '[int, str]', 'Tuple[int, str]'), ('C[T, *Ts]', '[int, str, bool]', 'C[int, str, bool]'), - ('tuple[T, *Ts]', '[int, str, bool]', 'TypeError'), # Should be tuple[int, str, bool] + ('tuple[T, *Ts]', '[int, str, bool]', 'tuple[int, str, bool]'), ('Tuple[T, *Ts]', '[int, str, bool]', 'Tuple[int, str, bool]'), ('C[T, *Ts]', '[*tuple[int, ...]]', 'C[*tuple[int, ...]]'), # Should be C[int, *tuple[int, ...]] ('C[T, *Ts]', '[*Tuple[int, ...]]', 'TypeError'), # Ditto - ('tuple[T, *Ts]', '[*tuple_type[int, ...]]', 'TypeError'), # Should be tuple[int, *tuple[int, ...]] - ('Tuple[T, *Ts]', '[*tuple[int, ...]]', 'Tuple[*tuple[int, ...]]'), # Ditto - ('Tuple[T, *Ts]', '[*Tuple[int, ...]]', 'TypeError'), # Ditto + ('tuple[T, *Ts]', '[*tuple[int, ...]]', 'tuple[*tuple[int, ...]]'), # Should be tuple[int, *tuple[int, ...]] + ('tuple[T, *Ts]', '[*Tuple[int, ...]]', 'TypeError'), # Should be tuple[int, *Tuple[int, ...]] + ('Tuple[T, *Ts]', '[*tuple[int, ...]]', 'Tuple[*tuple[int, ...]]'), # Should be Tuple[int, *tuple[int, ...]] + ('Tuple[T, *Ts]', '[*Tuple[int, ...]]', 'TypeError'), # Should be Tuple[int, *Tuple[int, ...]] ('C[*Ts, T]', '[int]', 'C[int]'), - ('tuple[*Ts, T]', '[int]', 'TypeError'), # Should be tuple[int] + ('tuple[*Ts, T]', '[int]', 'tuple[int]'), ('Tuple[*Ts, T]', '[int]', 'Tuple[int]'), ('C[*Ts, T]', '[int, str]', 'C[int, str]'), - ('tuple[*Ts, T]', '[int, str]', 'tuple[(int,), str]'), # Should be tuple[int, str] + ('tuple[*Ts, T]', '[int, str]', 'tuple[int, str]'), ('Tuple[*Ts, T]', '[int, str]', 'Tuple[int, str]'), ('C[*Ts, T]', '[int, str, bool]', 'C[int, str, bool]'), - ('tuple[*Ts, T]', '[int, str, bool]', 'TypeError'), # Should be tuple[int, str, bool] + ('tuple[*Ts, T]', '[int, str, bool]', 'tuple[int, str, bool]'), ('Tuple[*Ts, T]', '[int, str, bool]', 'Tuple[int, str, bool]'), ('generic[T, *tuple_type[int, ...]]', '[str]', 'generic[str, *tuple_type[int, ...]]'), @@ -945,7 +945,7 @@ def test_var_substitution(self): T2 = TypeVar('T2') class G(Generic[Unpack[Ts]]): pass - for A in G, Tuple: + for A in G, Tuple, tuple: B = A[Unpack[Ts]] self.assertEqual(B[()], A[()]) self.assertEqual(B[float], A[float]) @@ -984,6 +984,21 @@ def test_bad_var_substitution(self): T2 = TypeVar('T2') class G(Generic[Unpack[Ts]]): pass + for A in G, Tuple, tuple: + B = A[Ts] + with self.assertRaises(TypeError): + B[int, str] + + C = A[T, T2] + with self.assertRaises(TypeError): + C[Unpack[Ts]] + + def test_repr_is_correct(self): + Ts = TypeVarTuple('Ts') + T = TypeVar('T') + T2 = TypeVar('T2') + class G(Generic[Unpack[Ts]]): pass + for A in G, Tuple: B = A[T, Unpack[Ts], str, T2] with self.assertRaises(TypeError): diff --git a/Lib/typing.py b/Lib/typing.py index b250f2992dfff..35deb32220eb8 100644 --- a/Lib/typing.py +++ b/Lib/typing.py @@ -1019,7 +1019,7 @@ def __repr__(self): return self.__name__ def __typing_subst__(self, arg): - raise AssertionError + raise TypeError("Substitution of bare TypeVarTuple is not supported") class ParamSpecArgs(_Final, _Immutable, _root=True): @@ -1686,11 +1686,15 @@ def __repr__(self): return '*' + repr(self.__args__[0]) def __getitem__(self, args): - if (len(self.__parameters__) == 1 and - isinstance(self.__parameters__[0], TypeVarTuple)): + if self.__typing_unpacked__(): return args return super().__getitem__(args) + def __typing_unpacked__(self): + # If x is Unpack[tuple[...]], __parameters__ will be empty. + return bool(self.__parameters__ and + isinstance(self.__parameters__[0], TypeVarTuple)) + class Generic: """Abstract base class for generic types. diff --git a/Objects/genericaliasobject.c b/Objects/genericaliasobject.c index 7059c4018303e..7b689912dffc1 100644 --- a/Objects/genericaliasobject.c +++ b/Objects/genericaliasobject.c @@ -190,6 +190,23 @@ tuple_add(PyObject *self, Py_ssize_t len, PyObject *item) return 0; } +static Py_ssize_t +tuple_extend(PyObject **dst, Py_ssize_t dstindex, + PyObject **src, Py_ssize_t count) +{ + assert(count >= 0); + if (_PyTuple_Resize(dst, PyTuple_GET_SIZE(*dst) + count - 1) != 0) { + return -1; + } + assert(dstindex + count <= PyTuple_GET_SIZE(*dst)); + for (Py_ssize_t i = 0; i < count; ++i) { + PyObject *item = src[i]; + Py_INCREF(item); + PyTuple_SET_ITEM(*dst, dstindex + i, item); + } + return dstindex + count; +} + PyObject * _Py_make_parameters(PyObject *args) { @@ -251,7 +268,8 @@ _Py_make_parameters(PyObject *args) If obj doesn't have a __parameters__ attribute or that's not a non-empty tuple, return a new reference to obj. */ static PyObject * -subs_tvars(PyObject *obj, PyObject *params, PyObject **argitems) +subs_tvars(PyObject *obj, PyObject *params, + PyObject **argitems, Py_ssize_t nargs, Py_ssize_t varparam) { PyObject *subparams; if (_PyObject_LookupAttr(obj, &_Py_ID(__parameters__), &subparams) < 0) { @@ -265,14 +283,27 @@ subs_tvars(PyObject *obj, PyObject *params, PyObject **argitems) Py_DECREF(subparams); return NULL; } - for (Py_ssize_t i = 0; i < nsubargs; ++i) { + for (Py_ssize_t i = 0, j = 0; i < nsubargs; ++i) { PyObject *arg = PyTuple_GET_ITEM(subparams, i); Py_ssize_t iparam = tuple_index(params, nparams, arg); - if (iparam >= 0) { - arg = argitems[iparam]; + if (iparam == varparam) { + j = tuple_extend(&subargs, j, + argitems + iparam, nargs - nparams + 1); + if (j < 0) { + return NULL; + } + } + else { + if (iparam >= 0) { + if (iparam > varparam) { + iparam += nargs - nsubargs; + } + arg = argitems[iparam]; + } + Py_INCREF(arg); + PyTuple_SET_ITEM(subargs, j, arg); + j++; } - Py_INCREF(arg); - PyTuple_SET_ITEM(subargs, i, arg); } obj = PyObject_GetItem(obj, subargs); @@ -286,6 +317,23 @@ subs_tvars(PyObject *obj, PyObject *params, PyObject **argitems) return obj; } +static int +_is_unpacked_typevartuple(PyObject *arg) +{ + PyObject *meth; + int res = _PyObject_LookupAttr(arg, &_Py_ID(__typing_unpacked__), &meth); + if (res > 0) { + PyObject *tmp = PyObject_CallNoArgs(meth); + Py_DECREF(meth); + if (tmp == NULL) { + return -1; + } + res = PyObject_IsTrue(tmp); + Py_DECREF(tmp); + } + return res; +} + PyObject * _Py_subs_parameters(PyObject *self, PyObject *args, PyObject *parameters, PyObject *item) { @@ -298,11 +346,27 @@ _Py_subs_parameters(PyObject *self, PyObject *args, PyObject *parameters, PyObje int is_tuple = PyTuple_Check(item); Py_ssize_t nitems = is_tuple ? PyTuple_GET_SIZE(item) : 1; PyObject **argitems = is_tuple ? &PyTuple_GET_ITEM(item, 0) : &item; - if (nitems != nparams) { - return PyErr_Format(PyExc_TypeError, - "Too %s arguments for %R", - nitems > nparams ? "many" : "few", - self); + Py_ssize_t varparam = 0; + for (; varparam < nparams; varparam++) { + PyObject *param = PyTuple_GET_ITEM(parameters, varparam); + if (Py_TYPE(param)->tp_iter) { // TypeVarTuple + break; + } + } + if (varparam < nparams) { + if (nitems < nparams - 1) { + return PyErr_Format(PyExc_TypeError, + "Too few arguments for %R", + self); + } + } + else { + if (nitems != nparams) { + return PyErr_Format(PyExc_TypeError, + "Too %s arguments for %R", + nitems > nparams ? "many" : "few", + self); + } } /* Replace all type variables (specified by parameters) with corresponding values specified by argitems. @@ -315,8 +379,13 @@ _Py_subs_parameters(PyObject *self, PyObject *args, PyObject *parameters, PyObje if (newargs == NULL) { return NULL; } - for (Py_ssize_t iarg = 0; iarg < nargs; iarg++) { + for (Py_ssize_t iarg = 0, jarg = 0; iarg < nargs; iarg++) { PyObject *arg = PyTuple_GET_ITEM(args, iarg); + int unpack = _is_unpacked_typevartuple(arg); + if (unpack < 0) { + Py_DECREF(newargs); + return NULL; + } PyObject *subst; if (_PyObject_LookupAttr(arg, &_Py_ID(__typing_subst__), &subst) < 0) { Py_DECREF(newargs); @@ -325,17 +394,38 @@ _Py_subs_parameters(PyObject *self, PyObject *args, PyObject *parameters, PyObje if (subst) { Py_ssize_t iparam = tuple_index(parameters, nparams, arg); assert(iparam >= 0); + if (iparam == varparam) { + Py_DECREF(subst); + Py_DECREF(newargs); + PyErr_SetString(PyExc_TypeError, + "Substitution of bare TypeVarTuple is not supported"); + return NULL; + } + if (iparam > varparam) { + iparam += nitems - nparams; + } arg = PyObject_CallOneArg(subst, argitems[iparam]); Py_DECREF(subst); } else { - arg = subs_tvars(arg, parameters, argitems); + arg = subs_tvars(arg, parameters, argitems, nitems, varparam); } if (arg == NULL) { Py_DECREF(newargs); return NULL; } - PyTuple_SET_ITEM(newargs, iarg, arg); + if (unpack) { + jarg = tuple_extend(&newargs, jarg, + &PyTuple_GET_ITEM(arg, 0), PyTuple_GET_SIZE(arg)); + Py_DECREF(arg); + if (jarg < 0) { + return NULL; + } + } + else { + PyTuple_SET_ITEM(newargs, jarg, arg); + jarg++; + } } return newargs;

1 0

gh-92064: Fix global variable name collision in test_typing (#92067)
by JelleZijlstra April 30, 2022

April 30, 2022

https://github.com/python/cpython/commit/a29aa76a3ff8e5a4ee85961bb37a163f6b… commit: a29aa76a3ff8e5a4ee85961bb37a163f6b75a034 branch: main author: Dennis Sweeney <36520290+sweeneyde(a)users.noreply.github.com> committer: JelleZijlstra <jelle.zijlstra(a)gmail.com> date: 2022-04-29T21:18:38-06:00 summary: gh-92064: Fix global variable name collision in test_typing (#92067) Fixes #92064 files: M Lib/test/test_typing.py diff --git a/Lib/test/test_typing.py b/Lib/test/test_typing.py index 929f0df960ae0..412d117c238da 100644 --- a/Lib/test/test_typing.py +++ b/Lib/test/test_typing.py @@ -1332,16 +1332,16 @@ class TypeVarTuplePicklingTests(BaseTestCase): @all_pickle_protocols def test_pickling_then_unpickling_results_in_same_identity(self, proto): - global Ts1 # See explanation at start of class. - Ts1 = TypeVarTuple('Ts1') - Ts2 = pickle.loads(pickle.dumps(Ts1, proto)) - self.assertIs(Ts1, Ts2) + global global_Ts1 # See explanation at start of class. + global_Ts1 = TypeVarTuple('global_Ts1') + global_Ts2 = pickle.loads(pickle.dumps(global_Ts1, proto)) + self.assertIs(global_Ts1, global_Ts2) @all_pickle_protocols def test_pickling_then_unpickling_unpacked_results_in_same_identity(self, proto): - global Ts # See explanation at start of class. - Ts = TypeVarTuple('Ts') - unpacked1 = Unpack[Ts] + global global_Ts # See explanation at start of class. + global_Ts = TypeVarTuple('global_Ts') + unpacked1 = Unpack[global_Ts] unpacked2 = pickle.loads(pickle.dumps(unpacked1, proto)) self.assertIs(unpacked1, unpacked2) @@ -1349,19 +1349,19 @@ def test_pickling_then_unpickling_unpacked_results_in_same_identity(self, proto) def test_pickling_then_unpickling_tuple_with_typevartuple_equality( self, proto ): - global T, Ts # See explanation at start of class. - T = TypeVar('T') - Ts = TypeVarTuple('Ts') + global global_T, global_Ts # See explanation at start of class. + global_T = TypeVar('global_T') + global_Ts = TypeVarTuple('global_Ts') - a1 = Tuple[Unpack[Ts]] + a1 = Tuple[Unpack[global_Ts]] a2 = pickle.loads(pickle.dumps(a1, proto)) self.assertEqual(a1, a2) - a1 = Tuple[T, Unpack[Ts]] + a1 = Tuple[T, Unpack[global_Ts]] a2 = pickle.loads(pickle.dumps(a1, proto)) self.assertEqual(a1, a2) - a1 = Tuple[int, Unpack[Ts]] + a1 = Tuple[int, Unpack[global_Ts]] a2 = pickle.loads(pickle.dumps(a1, proto)) self.assertEqual(a1, a2)

1 0