From 057e9683852b2337eade066f304e65f9bfe508fe Mon Sep 17 00:00:00 2001
From: Shahar Naveh <50263213+ShaharNaveh@users.noreply.github.com>
Date: Fri, 12 Jun 2026 17:49:47 +0300
Subject: [PATCH] Update some of changed libs and tests from `3.14.5` ->
`3.14.6` (part 2) (#8085)
---
Lib/http/cookies.py | 6 +-
Lib/imaplib.py | 2 +-
Lib/json/__init__.py | 8 +-
Lib/json/tool.py | 3 +-
Lib/locale.py | 477 ++++++++++++++++++++--------
Lib/ntpath.py | 16 +-
Lib/os.py | 40 +--
Lib/pydoc_data/module_docs.py | 2 +-
Lib/pydoc_data/topics.py | 56 +++-
Lib/rlcompleter.py | 17 +-
Lib/shutil.py | 16 +-
Lib/tarfile.py | 51 +--
Lib/test/datetimetester.py | 30 ++
Lib/test/support/__init__.py | 15 +
Lib/test/test_http_cookies.py | 31 +-
Lib/test/test_json/json_lines.jsonl | 2 +
Lib/test/test_json/test_speedups.py | 63 ++++
Lib/test/test_json/test_tool.py | 9 +
Lib/test/test_os.py | 2 -
Lib/test/test_rlcompleter.py | 52 +++
Lib/test/test_shutil.py | 17 +
Lib/test/test_tarfile.py | 184 ++++++++---
22 files changed, 832 insertions(+), 267 deletions(-)
create mode 100644 Lib/test/test_json/json_lines.jsonl
diff --git a/Lib/http/cookies.py b/Lib/http/cookies.py
index 5c5b14788..abebb4b69 100644
--- a/Lib/http/cookies.py
+++ b/Lib/http/cookies.py
@@ -391,18 +391,18 @@ class Morsel(dict):
return '<%s: %s>' % (self.__class__.__name__, self.OutputString())
def js_output(self, attrs=None):
- import base64
+ import urllib.parse
# Print javascript
output_string = self.OutputString(attrs)
if _has_control_character(output_string):
raise CookieError("Control characters are not allowed in cookies")
# Base64-encode value to avoid template
# injection in cookie values.
- output_encoded = base64.b64encode(output_string.encode('utf-8')).decode("ascii")
+ output_encoded = urllib.parse.quote(output_string, safe='', encoding='utf-8')
return """
""" % (output_encoded,)
diff --git a/Lib/imaplib.py b/Lib/imaplib.py
index cbe129b3e..e84ffb2ee 100644
--- a/Lib/imaplib.py
+++ b/Lib/imaplib.py
@@ -706,7 +706,7 @@ class IMAP4:
"""
typ, dat = self._simple_command('LOGIN', user, self._quote(password))
if typ != 'OK':
- raise self.error(dat[-1])
+ raise self.error(dat[-1].decode('UTF-8', 'replace'))
self.state = 'AUTH'
return typ, dat
diff --git a/Lib/json/__init__.py b/Lib/json/__init__.py
index 9eaa4f3fb..800cc37f6 100644
--- a/Lib/json/__init__.py
+++ b/Lib/json/__init__.py
@@ -143,8 +143,8 @@ def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True,
If ``indent`` is a non-negative integer, then JSON array elements and
object members will be pretty-printed with that indent level. An indent
- level of 0 will only insert newlines. ``None`` is the most compact
- representation.
+ level of 0 will only insert newlines. ``None`` is the default and gives
+ a representation with no newlines inserted.
If specified, ``separators`` should be an ``(item_separator,
key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is
@@ -207,8 +207,8 @@ def dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True,
If ``indent`` is a non-negative integer, then JSON array elements and
object members will be pretty-printed with that indent level. An indent
- level of 0 will only insert newlines. ``None`` is the most compact
- representation.
+ level of 0 will only insert newlines. ``None`` is the default and gives
+ a representation with no newlines inserted.
If specified, ``separators`` should be an ``(item_separator,
key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is
diff --git a/Lib/json/tool.py b/Lib/json/tool.py
index 1967817ad..0cabbdba8 100644
--- a/Lib/json/tool.py
+++ b/Lib/json/tool.py
@@ -88,7 +88,8 @@ def main():
infile = open(options.infile, encoding='utf-8')
try:
if options.json_lines:
- objs = (json.loads(line) for line in infile)
+ lines = infile.readlines()
+ objs = (json.loads(line) for line in lines)
else:
objs = (json.load(infile),)
finally:
diff --git a/Lib/locale.py b/Lib/locale.py
index dfedc6386..498af0873 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -1496,8 +1496,8 @@ locale_alias = {
# This maps Windows language identifiers to locale strings.
#
# This list has been updated from
-# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
-# to include every locale up to Windows Vista.
+# https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-lcid/70feba9f-294e-491e-b6eb-56532684c37f
+# to include every locale up to protocol revision 16.0 (2024-04-23).
#
# NOTE: this mapping is incomplete. If your language is missing, please
# submit a bug report as detailed in the Python devguide at:
@@ -1507,10 +1507,15 @@ locale_alias = {
#
windows_locale = {
- 0x0436: "af_ZA", # Afrikaans
- 0x041c: "sq_AL", # Albanian
- 0x0484: "gsw_FR",# Alsatian - France
+ 0x0036: "af", # Afrikaans
+ 0x0436: "af_ZA", # Afrikaans - South Africa
+ 0x001c: "sq", # Albanian
+ 0x041c: "sq_AL", # Albanian - Albania
+ 0x0084: "gsw", # Alsatian
+ 0x0484: "gsw_FR", # Alsatian - France
+ 0x005e: "am", # Amharic
0x045e: "am_ET", # Amharic - Ethiopia
+ 0x0001: "ar", # Arabic
0x0401: "ar_SA", # Arabic - Saudi Arabia
0x0801: "ar_IQ", # Arabic - Iraq
0x0c01: "ar_EG", # Arabic - Egypt
@@ -1524,39 +1529,72 @@ windows_locale = {
0x2c01: "ar_JO", # Arabic - Jordan
0x3001: "ar_LB", # Arabic - Lebanon
0x3401: "ar_KW", # Arabic - Kuwait
- 0x3801: "ar_AE", # Arabic - United Arab Emirates
+ 0x3801: "ar_AE", # Arabic - U.A.E.
0x3c01: "ar_BH", # Arabic - Bahrain
0x4001: "ar_QA", # Arabic - Qatar
- 0x042b: "hy_AM", # Armenian
+ 0x002b: "hy", # Armenian
+ 0x042b: "hy_AM", # Armenian - Armenia
+ 0x004d: "as", # Assamese
0x044d: "as_IN", # Assamese - India
- 0x042c: "az_AZ", # Azeri - Latin
- 0x082c: "az_AZ", # Azeri - Cyrillic
- 0x046d: "ba_RU", # Bashkir
- 0x042d: "eu_ES", # Basque - Russia
- 0x0423: "be_BY", # Belarusian
- 0x0445: "bn_IN", # Begali
- 0x201a: "bs_BA", # Bosnian - Cyrillic
- 0x141a: "bs_BA", # Bosnian - Latin
+ 0x002c: "az", # Azerbaijani (Latin)
+ 0x742c: "az", # Azerbaijani (Cyrillic)
+ 0x782c: "az", # Azerbaijani (Latin)
+ 0x042c: "az_AZ", # Azerbaijani (Latin) - Azerbaijan
+ 0x0045: "bn", # Bangla
+ 0x0445: "bn_IN", # Bangla - India
+ 0x0845: "bn_BD", # Bangla - Bangladesh
+ 0x006d: "ba", # Bashkir
+ 0x046d: "ba_RU", # Bashkir - Russia
+ 0x002d: "eu", # Basque
+ 0x042d: "eu_ES", # Basque - Spain
+ 0x0023: "be", # Belarusian
+ 0x0423: "be_BY", # Belarusian - Belarus
+ 0x641a: "bs", # Bosnian (Cyrillic)
+ 0x681a: "bs", # Bosnian (Latin)
+ 0x141a: "bs_BA", # Bosnian (Latin) - Bosnia and Herzegovina
+ 0x201a: "bs_BA", # Bosnian (Cyrillic) - Bosnia and Herzegovina
+ 0x781a: "bs", # Bosnian (Latin)
+ 0x007e: "br", # Breton
0x047e: "br_FR", # Breton - France
- 0x0402: "bg_BG", # Bulgarian
-# 0x0455: "my_MM", # Burmese - Not supported
- 0x0403: "ca_ES", # Catalan
- 0x0004: "zh_CHS",# Chinese - Simplified
- 0x0404: "zh_TW", # Chinese - Taiwan
- 0x0804: "zh_CN", # Chinese - PRC
- 0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
- 0x1004: "zh_SG", # Chinese - Singapore
- 0x1404: "zh_MO", # Chinese - Macao S.A.R.
- 0x7c04: "zh_CHT",# Chinese - Traditional
+ 0x0002: "bg", # Bulgarian
+ 0x0402: "bg_BG", # Bulgarian - Bulgaria
+ 0x0055: "my", # Burmese
+ 0x0455: "my_MM", # Burmese - Myanmar
+ 0x0003: "ca", # Catalan
+ 0x0403: "ca_ES", # Catalan - Spain
+ 0x0803: "ca_ES", # Valencian - Spain
+ 0x0092: "ku", # Central Kurdish
+ 0x7c92: "ku", # Central Kurdish
+ 0x0492: "ku_IQ", # Central Kurdish - Iraq
+ 0x005c: "chr", # Cherokee
+ 0x7c5c: "chr", # Cherokee
+ 0x045c: "chr_US", # Cherokee - United States
+ 0x0004: "zh", # Chinese (Simplified)
+ 0x7804: "zh", # Chinese (Simplified)
+ 0x7c04: "zh", # Chinese (Traditional)
+ 0x0404: "zh_TW", # Chinese (Traditional) - Taiwan
+ 0x0804: "zh_CN", # Chinese (Simplified) - People's Republic of China
+ 0x0c04: "zh_HK", # Chinese (Traditional) - Hong Kong S.A.R.
+ 0x1004: "zh_SG", # Chinese (Simplified) - Singapore
+ 0x1404: "zh_MO", # Chinese (Traditional) - Macao S.A.R.
+ 0x0083: "co", # Corsican
0x0483: "co_FR", # Corsican - France
- 0x041a: "hr_HR", # Croatian
- 0x101a: "hr_BA", # Croatian - Bosnia
- 0x0405: "cs_CZ", # Czech
- 0x0406: "da_DK", # Danish
- 0x048c: "gbz_AF",# Dari - Afghanistan
- 0x0465: "div_MV",# Divehi - Maldives
- 0x0413: "nl_NL", # Dutch - The Netherlands
+ 0x001a: "hr", # Croatian
+ 0x041a: "hr_HR", # Croatian - Croatia
+ 0x101a: "hr_BA", # Croatian (Latin) - Bosnia and Herzegovina
+ 0x0005: "cs", # Czech
+ 0x0405: "cs_CZ", # Czech - Czech Republic
+ 0x0006: "da", # Danish
+ 0x0406: "da_DK", # Danish - Denmark
+ 0x008c: "prs", # Dari
+ 0x048c: "prs_AF", # Dari - Afghanistan
+ 0x0065: "dv", # Divehi
+ 0x0465: "dv_MV", # Divehi - Maldives
+ 0x0013: "nl", # Dutch
+ 0x0413: "nl_NL", # Dutch - Netherlands
0x0813: "nl_BE", # Dutch - Belgium
+ 0x0c51: "dz_BT", # Dzongkha - Bhutan
+ 0x0009: "en", # English
0x0409: "en_US", # English - United States
0x0809: "en_GB", # English - United Kingdom
0x0c09: "en_AU", # English - Australia
@@ -1564,122 +1602,248 @@ windows_locale = {
0x1409: "en_NZ", # English - New Zealand
0x1809: "en_IE", # English - Ireland
0x1c09: "en_ZA", # English - South Africa
- 0x2009: "en_JA", # English - Jamaica
- 0x2409: "en_CB", # English - Caribbean
+ 0x2009: "en_JM", # English - Jamaica
0x2809: "en_BZ", # English - Belize
- 0x2c09: "en_TT", # English - Trinidad
+ 0x2c09: "en_TT", # English - Trinidad and Tobago
0x3009: "en_ZW", # English - Zimbabwe
- 0x3409: "en_PH", # English - Philippines
+ 0x3409: "en_PH", # English - Republic of the Philippines
+ 0x3c09: "en_HK", # English - Hong Kong
0x4009: "en_IN", # English - India
0x4409: "en_MY", # English - Malaysia
- 0x4809: "en_IN", # English - Singapore
- 0x0425: "et_EE", # Estonian
- 0x0438: "fo_FO", # Faroese
- 0x0464: "fil_PH",# Filipino
- 0x040b: "fi_FI", # Finnish
+ 0x4809: "en_SG", # English - Singapore
+ 0x4c09: "en_AE", # English - United Arab Emirates
+ 0x0025: "et", # Estonian
+ 0x0425: "et_EE", # Estonian - Estonia
+ 0x0038: "fo", # Faroese
+ 0x0438: "fo_FO", # Faroese - Faroe Islands
+ 0x0064: "fil", # Filipino
+ 0x0464: "fil_PH", # Filipino - Philippines
+ 0x000b: "fi", # Finnish
+ 0x040b: "fi_FI", # Finnish - Finland
+ 0x000c: "fr", # French
0x040c: "fr_FR", # French - France
0x080c: "fr_BE", # French - Belgium
0x0c0c: "fr_CA", # French - Canada
0x100c: "fr_CH", # French - Switzerland
0x140c: "fr_LU", # French - Luxembourg
- 0x180c: "fr_MC", # French - Monaco
+ 0x180c: "fr_MC", # French - Principality of Monaco
+ 0x1c0c: "fr_029", # French - Caribbean
+ 0x200c: "fr_RE", # French - Reunion
+ 0x240c: "fr_CD", # French - Congo, DRC
+ 0x280c: "fr_SN", # French - Senegal
+ 0x2c0c: "fr_CM", # French - Cameroon
+ 0x300c: "fr_CI", # French - Côte d'Ivoire
+ 0x340c: "fr_ML", # French - Mali
+ 0x380c: "fr_MA", # French - Morocco
+ 0x3c0c: "fr_HT", # French - Haiti
+ 0x0062: "fy", # Frisian
0x0462: "fy_NL", # Frisian - Netherlands
- 0x0456: "gl_ES", # Galician
- 0x0437: "ka_GE", # Georgian
+ 0x0067: "ff", # Fulah
+ 0x7c67: "ff", # Fulah (Latin)
+ 0x0467: "ff_NG",
+ 0x0867: "ff_SN", # Fulah - Senegal
+ 0x0056: "gl", # Galician
+ 0x0456: "gl_ES", # Galician - Spain
+ 0x0037: "ka", # Georgian
+ 0x0437: "ka_GE", # Georgian - Georgia
+ 0x0007: "de", # German
0x0407: "de_DE", # German - Germany
0x0807: "de_CH", # German - Switzerland
0x0c07: "de_AT", # German - Austria
0x1007: "de_LU", # German - Luxembourg
0x1407: "de_LI", # German - Liechtenstein
- 0x0408: "el_GR", # Greek
+ 0x0008: "el", # Greek
+ 0x0408: "el_GR", # Greek - Greece
+ 0x006f: "kl", # Greenlandic
0x046f: "kl_GL", # Greenlandic - Greenland
- 0x0447: "gu_IN", # Gujarati
- 0x0468: "ha_NG", # Hausa - Latin
- 0x040d: "he_IL", # Hebrew
- 0x0439: "hi_IN", # Hindi
- 0x040e: "hu_HU", # Hungarian
- 0x040f: "is_IS", # Icelandic
- 0x0421: "id_ID", # Indonesian
- 0x045d: "iu_CA", # Inuktitut - Syllabics
- 0x085d: "iu_CA", # Inuktitut - Latin
+ 0x0074: "gn", # Guarani
+ 0x0474: "gn_PY", # Guarani - Paraguay
+ 0x0047: "gu", # Gujarati
+ 0x0447: "gu_IN", # Gujarati - India
+ 0x0068: "ha", # Hausa (Latin)
+ 0x7c68: "ha", # Hausa (Latin)
+ 0x0468: "ha_NG", # Hausa (Latin) - Nigeria
+ 0x0075: "haw", # Hawaiian
+ 0x0475: "haw_US", # Hawaiian - United States
+ 0x000d: "he", # Hebrew
+ 0x040d: "he_IL", # Hebrew - Israel
+ 0x0039: "hi", # Hindi
+ 0x0439: "hi_IN", # Hindi - India
+ 0x000e: "hu", # Hungarian
+ 0x040e: "hu_HU", # Hungarian - Hungary
+ 0x000f: "is", # Icelandic
+ 0x040f: "is_IS", # Icelandic - Iceland
+ 0x0070: "ig", # Igbo
+ 0x0470: "ig_NG", # Igbo - Nigeria
+ 0x0021: "id", # Indonesian
+ 0x0421: "id_ID", # Indonesian - Indonesia
+ 0x005d: "iu", # Inuktitut (Latin)
+ 0x785d: "iu", # Inuktitut (Syllabics)
+ 0x7c5d: "iu", # Inuktitut (Latin)
+ 0x045d: "iu_CA", # Inuktitut (Syllabics) - Canada
+ 0x085d: "iu_CA", # Inuktitut (Latin) - Canada
+ 0x003c: "ga", # Irish
0x083c: "ga_IE", # Irish - Ireland
+ 0x0010: "it", # Italian
0x0410: "it_IT", # Italian - Italy
0x0810: "it_CH", # Italian - Switzerland
- 0x0411: "ja_JP", # Japanese
+ 0x0011: "ja", # Japanese
+ 0x0411: "ja_JP", # Japanese - Japan
+ 0x004b: "kn", # Kannada
0x044b: "kn_IN", # Kannada - India
- 0x043f: "kk_KZ", # Kazakh
- 0x0453: "kh_KH", # Khmer - Cambodia
- 0x0486: "qut_GT",# K'iche - Guatemala
+ 0x0471: "kr_NG", # Kanuri (Latin) - Nigeria
+ 0x0060: "ks", # Kashmiri
+ 0x0460: "ks", # Kashmiri - Perso_Arabic
+ 0x0860: "ks_IN", # Kashmiri (Devanagari) - India
+ 0x003f: "kk", # Kazakh
+ 0x043f: "kk_KZ", # Kazakh - Kazakhstan
+ 0x0053: "km", # Khmer
+ 0x0453: "km_KH", # Khmer - Cambodia
+ 0x0087: "rw", # Kinyarwanda
0x0487: "rw_RW", # Kinyarwanda - Rwanda
- 0x0457: "kok_IN",# Konkani
- 0x0412: "ko_KR", # Korean
- 0x0440: "ky_KG", # Kyrgyz
- 0x0454: "lo_LA", # Lao - Lao PDR
- 0x0426: "lv_LV", # Latvian
- 0x0427: "lt_LT", # Lithuanian
- 0x082e: "dsb_DE",# Lower Sorbian - Germany
- 0x046e: "lb_LU", # Luxembourgish
- 0x042f: "mk_MK", # FYROM Macedonian
+ 0x0041: "sw", # Kiswahili
+ 0x0441: "sw_KE", # Kiswahili - Kenya
+ 0x0057: "kok", # Konkani
+ 0x0457: "kok_IN", # Konkani - India
+ 0x0012: "ko", # Korean
+ 0x0412: "ko_KR", # Korean - Korea
+ 0x0040: "ky", # Kyrgyz
+ 0x0440: "ky_KG", # Kyrgyz - Kyrgyzstan
+ 0x0054: "lo", # Lao
+ 0x0454: "lo_LA", # Lao - Lao P.D.R.
+ 0x0476: "la_VA", # Latin - Vatican City
+ 0x0026: "lv", # Latvian
+ 0x0426: "lv_LV", # Latvian - Latvia
+ 0x0027: "lt", # Lithuanian
+ 0x0427: "lt_LT", # Lithuanian - Lithuania
+ 0x7c2e: "dsb", # Lower Sorbian
+ 0x082e: "dsb_DE", # Lower Sorbian - Germany
+ 0x006e: "lb", # Luxembourgish
+ 0x046e: "lb_LU", # Luxembourgish - Luxembourg
+ 0x002f: "mk", # Macedonian
+ 0x042f: "mk_MK", # Macedonian - North Macedonia
+ 0x003e: "ms", # Malay
0x043e: "ms_MY", # Malay - Malaysia
0x083e: "ms_BN", # Malay - Brunei Darussalam
+ 0x004c: "ml", # Malayalam
0x044c: "ml_IN", # Malayalam - India
- 0x043a: "mt_MT", # Maltese
- 0x0481: "mi_NZ", # Maori
- 0x047a: "arn_CL",# Mapudungun
- 0x044e: "mr_IN", # Marathi
- 0x047c: "moh_CA",# Mohawk - Canada
- 0x0450: "mn_MN", # Mongolian - Cyrillic
- 0x0850: "mn_CN", # Mongolian - PRC
- 0x0461: "ne_NP", # Nepali
- 0x0414: "nb_NO", # Norwegian - Bokmal
- 0x0814: "nn_NO", # Norwegian - Nynorsk
+ 0x003a: "mt", # Maltese
+ 0x043a: "mt_MT", # Maltese - Malta
+ 0x0081: "mi", # Maori
+ 0x0481: "mi_NZ", # Maori - New Zealand
+ 0x007a: "arn", # Mapudungun
+ 0x047a: "arn_CL", # Mapudungun - Chile
+ 0x004e: "mr", # Marathi
+ 0x044e: "mr_IN", # Marathi - India
+ 0x007c: "moh", # Mohawk
+ 0x047c: "moh_CA", # Mohawk - Canada
+ 0x0050: "mn", # Mongolian (Cyrillic)
+ 0x7850: "mn", # Mongolian (Cyrillic)
+ 0x7c50: "mn", # Mongolian (Traditional Mongolian)
+ 0x0450: "mn_MN", # Mongolian (Cyrillic) - Mongolia
+ 0x0c50: "mn_MN", # Mongolian (Traditional Mongolian) - Mongolia
+ 0x0061: "ne", # Nepali
+ 0x0461: "ne_NP", # Nepali - Nepal
+ 0x0861: "ne_IN", # Nepali - India
+ 0x0014: "no", # Norwegian (Bokmal)
+ 0x0414: "nb_NO", # Norwegian (Bokmal) - Norway
+ 0x0814: "nn_NO", # Norwegian (Nynorsk) - Norway
+ 0x7814: "nn", # Norwegian (Nynorsk)
+ 0x7c14: "nb", # Norwegian (Bokmal)
+ 0x0082: "oc", # Occitan
0x0482: "oc_FR", # Occitan - France
- 0x0448: "or_IN", # Oriya - India
+ 0x0048: "or", # Odia
+ 0x0448: "or_IN", # Odia - India
+ 0x0072: "om", # Oromo
+ 0x0472: "om_ET", # Oromo - Ethiopia
+ 0x0063: "ps", # Pashto
0x0463: "ps_AF", # Pashto - Afghanistan
- 0x0429: "fa_IR", # Persian
- 0x0415: "pl_PL", # Polish
+ 0x0029: "fa", # Persian
+ 0x0429: "fa_IR", # Persian - Iran
+ 0x0015: "pl", # Polish
+ 0x0415: "pl_PL", # Polish - Poland
+ 0x0016: "pt", # Portuguese
0x0416: "pt_BR", # Portuguese - Brazil
0x0816: "pt_PT", # Portuguese - Portugal
- 0x0446: "pa_IN", # Punjabi
- 0x046b: "quz_BO",# Quechua (Bolivia)
- 0x086b: "quz_EC",# Quechua (Ecuador)
- 0x0c6b: "quz_PE",# Quechua (Peru)
+ 0x0046: "pa", # Punjabi
+ 0x7c46: "pa", # Punjabi
+ 0x0446: "pa_IN", # Punjabi - India
+ 0x0846: "pa_PK", # Punjabi - Islamic Republic of Pakistan
+ 0x006b: "quz", # Quechua
+ 0x046b: "quz_BO", # Quechua - Bolivia
+ 0x086b: "quz_EC", # Quechua - Ecuador
+ 0x0c6b: "quz_PE", # Quechua - Peru
+ 0x0018: "ro", # Romanian
0x0418: "ro_RO", # Romanian - Romania
- 0x0417: "rm_CH", # Romansh
- 0x0419: "ru_RU", # Russian
- 0x243b: "smn_FI",# Sami Finland
- 0x103b: "smj_NO",# Sami Norway
- 0x143b: "smj_SE",# Sami Sweden
- 0x043b: "se_NO", # Sami Northern Norway
- 0x083b: "se_SE", # Sami Northern Sweden
- 0x0c3b: "se_FI", # Sami Northern Finland
- 0x203b: "sms_FI",# Sami Skolt
- 0x183b: "sma_NO",# Sami Southern Norway
- 0x1c3b: "sma_SE",# Sami Southern Sweden
- 0x044f: "sa_IN", # Sanskrit
- 0x0c1a: "sr_SP", # Serbian - Cyrillic
- 0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
- 0x081a: "sr_SP", # Serbian - Latin
- 0x181a: "sr_BA", # Serbian - Bosnia Latin
+ 0x0818: "ro_MD", # Romanian - Moldova
+ 0x0017: "rm", # Romansh
+ 0x0417: "rm_CH", # Romansh - Switzerland
+ 0x0019: "ru", # Russian
+ 0x0419: "ru_RU", # Russian - Russia
+ 0x0819: "ru_MD", # Russian - Moldova
+ 0x0085: "sah", # Sakha
+ 0x0485: "sah_RU", # Sakha - Russia
+ 0x003b: "se", # Sami (Northern)
+ 0x043b: "se_NO", # Sami (Northern) - Norway
+ 0x083b: "se_SE", # Sami (Northern) - Sweden
+ 0x0c3b: "se_FI", # Sami (Northern) - Finland
+ 0x7c3b: "smj", # Sami (Lule)
+ 0x103b: "smj_NO", # Sami (Lule) - Norway
+ 0x143b: "smj_SE", # Sami (Lule) - Sweden
+ 0x783b: "sma", # Sami (Southern)
+ 0x183b: "sma_NO", # Sami (Southern) - Norway
+ 0x1c3b: "sma_SE", # Sami (Southern) - Sweden
+ 0x743b: "sms", # Sami (Skolt)
+ 0x203b: "sms_FI", # Sami (Skolt) - Finland
+ 0x703b: "smn", # Sami (Inari)
+ 0x243b: "smn_FI", # Sami (Inari) - Finland
+ 0x004f: "sa", # Sanskrit
+ 0x044f: "sa_IN", # Sanskrit - India
+ 0x0091: "gd", # Scottish Gaelic
+ 0x0491: "gd_GB", # Scottish Gaelic - United Kingdom
+ 0x6c1a: "sr", # Serbian (Cyrillic)
+ 0x701a: "sr", # Serbian (Latin)
+ 0x7c1a: "sr", # Serbian (Latin)
+ 0x081a: "sr_CS", # Serbian (Latin) - Serbia and Montenegro (Former)
+ 0x0c1a: "sr_CS", # Serbian (Cyrillic) - Serbia and Montenegro (Former)
+ 0x181a: "sr_BA", # Serbian (Latin) - Bosnia and Herzegovina
+ 0x1c1a: "sr_BA", # Serbian (Cyrillic) - Bosnia and Herzegovina
+ 0x241a: "sr_RS", # Serbian (Latin) - Serbia
+ 0x281a: "sr_RS", # Serbian (Cyrillic) - Serbia
+ 0x2c1a: "sr_ME", # Serbian (Latin) - Montenegro
+ 0x301a: "sr_ME", # Serbian (Cyrillic) - Montenegro
+ 0x006c: "nso", # Sesotho sa Leboa
+ 0x046c: "nso_ZA", # Sesotho sa Leboa - South Africa
+ 0x0032: "tn", # Setswana
+ 0x0432: "tn_ZA", # Setswana - South Africa
+ 0x0832: "tn_BW", # Setswana - Botswana
+ 0x0059: "sd", # Sindhi
+ 0x7c59: "sd", # Sindhi
+ 0x0859: "sd_PK", # Sindhi - Islamic Republic of Pakistan
+ 0x005b: "si", # Sinhala
0x045b: "si_LK", # Sinhala - Sri Lanka
- 0x046c: "ns_ZA", # Northern Sotho
- 0x0432: "tn_ZA", # Setswana - Southern Africa
- 0x041b: "sk_SK", # Slovak
- 0x0424: "sl_SI", # Slovenian
+ 0x001b: "sk", # Slovak
+ 0x041b: "sk_SK", # Slovak - Slovakia
+ 0x0024: "sl", # Slovenian
+ 0x0424: "sl_SI", # Slovenian - Slovenia
+ 0x0477: "so_SO", # Somali - Somalia
+ 0x0030: "st", # Sotho
+ 0x0430: "st_ZA", # Sotho - South Africa
+ 0x000a: "es", # Spanish
0x040a: "es_ES", # Spanish - Spain
0x080a: "es_MX", # Spanish - Mexico
- 0x0c0a: "es_ES", # Spanish - Spain (Modern)
+ 0x0c0a: "es_ES", # Spanish - Spain
0x100a: "es_GT", # Spanish - Guatemala
0x140a: "es_CR", # Spanish - Costa Rica
0x180a: "es_PA", # Spanish - Panama
0x1c0a: "es_DO", # Spanish - Dominican Republic
- 0x200a: "es_VE", # Spanish - Venezuela
+ 0x200a: "es_VE", # Spanish - Bolivarian Republic of Venezuela
0x240a: "es_CO", # Spanish - Colombia
0x280a: "es_PE", # Spanish - Peru
0x2c0a: "es_AR", # Spanish - Argentina
0x300a: "es_EC", # Spanish - Ecuador
0x340a: "es_CL", # Spanish - Chile
- 0x380a: "es_UR", # Spanish - Uruguay
+ 0x380a: "es_UY", # Spanish - Uruguay
0x3c0a: "es_PY", # Spanish - Paraguay
0x400a: "es_BO", # Spanish - Bolivia
0x440a: "es_SV", # Spanish - El Salvador
@@ -1687,36 +1851,87 @@ windows_locale = {
0x4c0a: "es_NI", # Spanish - Nicaragua
0x500a: "es_PR", # Spanish - Puerto Rico
0x540a: "es_US", # Spanish - United States
-# 0x0430: "", # Sutu - Not supported
- 0x0441: "sw_KE", # Swahili
+ 0x5c0a: "es_CU", # Spanish - Cuba
+ 0x001d: "sv", # Swedish
0x041d: "sv_SE", # Swedish - Sweden
0x081d: "sv_FI", # Swedish - Finland
- 0x045a: "syr_SY",# Syriac
- 0x0428: "tg_TJ", # Tajik - Cyrillic
- 0x085f: "tmz_DZ",# Tamazight - Latin
- 0x0449: "ta_IN", # Tamil
- 0x0444: "tt_RU", # Tatar
- 0x044a: "te_IN", # Telugu
- 0x041e: "th_TH", # Thai
- 0x0851: "bo_BT", # Tibetan - Bhutan
- 0x0451: "bo_CN", # Tibetan - PRC
- 0x041f: "tr_TR", # Turkish
- 0x0442: "tk_TM", # Turkmen - Cyrillic
- 0x0480: "ug_CN", # Uighur - Arabic
- 0x0422: "uk_UA", # Ukrainian
- 0x042e: "wen_DE",# Upper Sorbian - Germany
- 0x0420: "ur_PK", # Urdu
+ 0x005a: "syr", # Syriac
+ 0x045a: "syr_SY", # Syriac - Syria
+ 0x0028: "tg", # Tajik (Cyrillic)
+ 0x7c28: "tg", # Tajik (Cyrillic)
+ 0x0428: "tg_TJ", # Tajik (Cyrillic) - Tajikistan
+ 0x005f: "tzm", # Tamazight (Latin)
+ 0x785f: "tzm",
+ 0x7c5f: "tzm", # Tamazight (Latin)
+ 0x085f: "tzm_DZ", # Tamazight (Latin) - Algeria
+ 0x045f: "tzm_MA", # Central Atlas Tamazight (Arabic) - Morocco
+ 0x105f: "tzm_MA",
+ 0x0049: "ta", # Tamil
+ 0x0449: "ta_IN", # Tamil - India
+ 0x0849: "ta_LK", # Tamil - Sri Lanka
+ 0x0044: "tt", # Tatar
+ 0x0444: "tt_RU", # Tatar - Russia
+ 0x004a: "te", # Telugu
+ 0x044a: "te_IN", # Telugu - India
+ 0x001e: "th", # Thai
+ 0x041e: "th_TH", # Thai - Thailand
+ 0x0051: "bo", # Tibetan
+ 0x0451: "bo_CN", # Tibetan - People's Republic of China
+ 0x0073: "ti", # Tigrinya
+ 0x0473: "ti_ET", # Tigrinya - Ethiopia
+ 0x0873: "ti_ER", # Tigrinya - Eritrea
+ 0x0031: "ts", # Tsonga
+ 0x0431: "ts_ZA", # Tsonga - South Africa
+ 0x001f: "tr", # Turkish
+ 0x041f: "tr_TR", # Turkish - Turkey
+ 0x0042: "tk", # Turkmen
+ 0x0442: "tk_TM", # Turkmen - Turkmenistan
+ 0x0022: "uk", # Ukrainian
+ 0x0422: "uk_UA", # Ukrainian - Ukraine
+ 0x002e: "hsb", # Upper Sorbian
+ 0x042e: "hsb_DE", # Upper Sorbian - Germany
+ 0x0020: "ur", # Urdu
+ 0x0420: "ur_PK", # Urdu - Islamic Republic of Pakistan
0x0820: "ur_IN", # Urdu - India
- 0x0443: "uz_UZ", # Uzbek - Latin
- 0x0843: "uz_UZ", # Uzbek - Cyrillic
- 0x042a: "vi_VN", # Vietnamese
- 0x0452: "cy_GB", # Welsh
+ 0x0080: "ug", # Uyghur
+ 0x0480: "ug_CN", # Uyghur - People's Republic of China
+ 0x0043: "uz", # Uzbek (Latin)
+ 0x7843: "uz", # Uzbek (Cyrillic)
+ 0x7c43: "uz", # Uzbek (Latin)
+ 0x0443: "uz_UZ", # Uzbek (Latin) - Uzbekistan
+ 0x0033: "ve", # Venda
+ 0x0433: "ve_ZA", # Venda - South Africa
+ 0x002a: "vi", # Vietnamese
+ 0x042a: "vi_VN", # Vietnamese - Vietnam
+ 0x0052: "cy", # Welsh
+ 0x0452: "cy_GB", # Welsh - United Kingdom
+ 0x0088: "wo", # Wolof
0x0488: "wo_SN", # Wolof - Senegal
+ 0x0034: "xh", # Xhosa
0x0434: "xh_ZA", # Xhosa - South Africa
- 0x0485: "sah_RU",# Yakut - Cyrillic
- 0x0478: "ii_CN", # Yi - PRC
+ 0x0078: "ii", # Yi
+ 0x0478: "ii_CN", # Yi - People's Republic of China
+ 0x043d: "yi_001", # Yiddish - World
+ 0x006a: "yo", # Yoruba
0x046a: "yo_NG", # Yoruba - Nigeria
- 0x0435: "zu_ZA", # Zulu
+ 0x0035: "zu", # Zulu
+ 0x0435: "zu_ZA", # Zulu - South Africa
+ 0x0086: "qut",
+
+# 0x0001007f: "x-IV-mathan", # math alphanumeric sorting
+ 0x00010407: "de_DE",
+ 0x0001040e: "hu_HU",
+ 0x00010437: "ka_GE",
+ 0x00020804: "zh_CN",
+ 0x00021004: "zh_SG",
+ 0x00021404: "zh_MO",
+ 0x00030404: "zh_TW",
+ 0x00040404: "zh_TW",
+ 0x00040411: "ja_JP",
+ 0x00040c04: "zh_HK",
+ 0x00041404: "zh_MO",
+ 0x00050804: "zh_CN",
+ 0x00051004: "zh_SG",
}
def _print_locale():
diff --git a/Lib/ntpath.py b/Lib/ntpath.py
index 01f060e70..eb127ec26 100644
--- a/Lib/ntpath.py
+++ b/Lib/ntpath.py
@@ -152,12 +152,14 @@ def splitdrive(p):
It is always true that:
result[0] + result[1] == p
- If the path contained a drive letter, drive_or_unc will contain everything
- up to and including the colon. e.g. splitdrive("c:/dir") returns ("c:", "/dir")
+ If the path contained a drive letter, drive_or_unc will contain
+ everything up to and including the colon. e.g. splitdrive("c:/dir")
+ returns ("c:", "/dir")
- If the path contained a UNC path, the drive_or_unc will contain the host name
- and share up to but not including the fourth directory separator character.
- e.g. splitdrive("//host/computer/dir") returns ("//host/computer", "/dir")
+ If the path contained a UNC path, the drive_or_unc will contain the
+ host name and share up to but not including the fourth directory
+ separator character. e.g. splitdrive("//host/computer/dir") returns
+ ("//host/computer", "/dir")
Paths cannot contain both a drive letter and a UNC path.
@@ -222,8 +224,8 @@ except ImportError:
def split(p):
"""Split a pathname.
- Return tuple (head, tail) where tail is everything after the final slash.
- Either part may be empty."""
+ Return tuple (head, tail) where tail is everything after the final
+ slash. Either part may be empty."""
p = os.fspath(p)
seps = _get_bothseps(p)
d, r, p = splitroot(p)
diff --git a/Lib/os.py b/Lib/os.py
index ac03b4163..9bb00f45f 100644
--- a/Lib/os.py
+++ b/Lib/os.py
@@ -211,11 +211,11 @@ SEEK_END = 2
def makedirs(name, mode=0o777, exist_ok=False):
"""makedirs(name [, mode=0o777][, exist_ok=False])
- Super-mkdir; create a leaf directory and all intermediate ones. Works like
- mkdir, except that any intermediate path segment (not just the rightmost)
- will be created if it does not exist. If the target directory already
- exists, raise an OSError if exist_ok is False. Otherwise no exception is
- raised. This is recursive.
+ Super-mkdir; create a leaf directory and all intermediate ones. Works
+ like mkdir, except that any intermediate path segment (not just the
+ rightmost) will be created if it does not exist. If the target
+ directory already exists, raise an OSError if exist_ok is False.
+ Otherwise no exception is raised. This is recursive.
"""
head, tail = path.split(name)
@@ -303,12 +303,12 @@ def walk(top, topdown=True, onerror=None, followlinks=False):
dirpath, dirnames, filenames
dirpath is a string, the path to the directory. dirnames is a list of
- the names of the subdirectories in dirpath (including symlinks to directories,
- and excluding '.' and '..').
+ the names of the subdirectories in dirpath (including symlinks to
+ directories, and excluding '.' and '..').
filenames is a list of the names of the non-directory files in dirpath.
- Note that the names in the lists are just names, with no path components.
- To get a full path (which begins with top) to a file or directory in
- dirpath, do os.path.join(dirpath, name).
+ Note that the names in the lists are just names, with no path
+ components. To get a full path (which begins with top) to a file or
+ directory in dirpath, do os.path.join(dirpath, name).
If optional arg 'topdown' is true or not specified, the triple for a
directory is generated before the triples for any of its subdirectories
@@ -318,13 +318,13 @@ def walk(top, topdown=True, onerror=None, followlinks=False):
When topdown is true, the caller can modify the dirnames list in-place
(e.g., via del or slice assignment), and walk will only recurse into the
- subdirectories whose names remain in dirnames; this can be used to prune the
- search, or to impose a specific order of visiting. Modifying dirnames when
- topdown is false has no effect on the behavior of os.walk(), since the
- directories in dirnames have already been generated by the time dirnames
- itself is generated. No matter the value of topdown, the list of
- subdirectories is retrieved before the tuples for the directory and its
- subdirectories are generated.
+ subdirectories whose names remain in dirnames; this can be used to prune
+ the search, or to impose a specific order of visiting. Modifying
+ dirnames when topdown is false has no effect on the behavior of
+ os.walk(), since the directories in dirnames have already been generated
+ by the time dirnames itself is generated. No matter the value of
+ topdown, the list of subdirectories is retrieved before the tuples for
+ the directory and its subdirectories are generated.
By default errors from the os.scandir() call are ignored. If
optional arg 'onerror' is specified, it should be a function; it
@@ -449,9 +449,9 @@ if {open, stat} <= supports_dir_fd and {scandir, stat} <= supports_fd:
The advantage of fwalk() over walk() is that it's safe against symlink
races (when follow_symlinks is False).
- If dir_fd is not None, it should be a file descriptor open to a directory,
- and top should be relative; top will then be relative to that directory.
- (dir_fd is always supported for fwalk.)
+ If dir_fd is not None, it should be a file descriptor open to
+ a directory, and top should be relative; top will then be relative to
+ that directory. (dir_fd is always supported for fwalk.)
Caution:
Since fwalk() yields file descriptors, those are only valid until the
diff --git a/Lib/pydoc_data/module_docs.py b/Lib/pydoc_data/module_docs.py
index 67a1ba769..69b9046f4 100644
--- a/Lib/pydoc_data/module_docs.py
+++ b/Lib/pydoc_data/module_docs.py
@@ -1,4 +1,4 @@
-# Autogenerated by Sphinx on Sun May 10 13:21:26 2026
+# Autogenerated by Sphinx on Wed Jun 10 13:03:46 2026
# as part of the release process.
module_docs = {
diff --git a/Lib/pydoc_data/topics.py b/Lib/pydoc_data/topics.py
index e91c8a5cb..05d283c95 100644
--- a/Lib/pydoc_data/topics.py
+++ b/Lib/pydoc_data/topics.py
@@ -1,4 +1,4 @@
-# Autogenerated by Sphinx on Sun May 10 13:21:26 2026
+# Autogenerated by Sphinx on Wed Jun 10 13:03:46 2026
# as part of the release process.
topics = {
@@ -2227,9 +2227,9 @@ Added in version 3.10.
The match statement is used for pattern matching. Syntax:
match_stmt: 'match' subject_expr ":" NEWLINE INDENT case_block+ DEDENT
- subject_expr: `!star_named_expression` "," `!star_named_expressions`?
- | `!named_expression`
- case_block: 'case' patterns [guard] ":" `!block`
+ subject_expr: flexible_expression "," [flexible_expression_list [',']]
+ | assignment_expression
+ case_block: 'case' patterns [guard] ":" suite
Note:
@@ -2320,7 +2320,7 @@ section.
Guards
------
- guard: "if" `!named_expression`
+ guard: "if" assignment_expression
A "guard" (which is part of the "case") must succeed for code inside
the "case" block to execute. It takes the form: "if" followed by an
@@ -5772,7 +5772,8 @@ number respectively. It can be one of the following:
| | is not supported. |
+-----------+------------------------------------------------------------+
-For a locale aware separator, use the "'n'" presentation type instead.
+For a locale-aware separator, use the "'n'" float presentation type or
+integer presentation type instead.
Changed in version 3.1: Added the "','" option (see also **PEP 378**).
@@ -5818,7 +5819,10 @@ The available integer presentation types are:
+-----------+------------------------------------------------------------+
| "'n'" | Number. This is the same as "'d'", except that it uses the |
| | current locale setting to insert the appropriate digit |
- | | group separators. |
+ | | group separators. Note that the default locale is not the |
+ | | system locale. Depending on your use case, you may wish to |
+ | | set "LC_NUMERIC" with "locale.setlocale()" before using |
+ | | "'n'". |
+-----------+------------------------------------------------------------+
| None | The same as "'d'". |
+-----------+------------------------------------------------------------+
@@ -5892,7 +5896,10 @@ The available presentation types for "float" and "Decimal" values are:
+-----------+------------------------------------------------------------+
| "'n'" | Number. This is the same as "'g'", except that it uses the |
| | current locale setting to insert the appropriate digit |
- | | group separators for the integral part of a number. |
+ | | group separators for the integral part of a number. Note |
+ | | that the default locale is not the system locale. |
+ | | Depending on your use case, you may wish to set |
+ | | "LC_NUMERIC" with "locale.setlocale()" before using "'n'". |
+-----------+------------------------------------------------------------+
| "'%'" | Percentage. Multiplies the number by 100 and displays in |
| | fixed ("'f'") format, followed by a percent sign. |
@@ -10198,9 +10205,22 @@ str.isdigit()
decimal characters and digits that need special handling, such as
the compatibility superscript digits. This covers digits which
cannot be used to form numbers in base 10, like the Kharosthi
- numbers. Formally, a digit is a character that has the property
+ numbers. Formally, a digit is a character that has the property
value Numeric_Type=Digit or Numeric_Type=Decimal.
+ For example:
+
+ >>> '0123456789'.isdigit()
+ True
+ >>> '٠١٢٣٤٥٦٧٨٩'.isdigit() # Arabic-Indic digits zero to nine
+ True
+ >>> '⅕'.isdigit() # Vulgar fraction one fifth
+ False
+ >>> '²'.isdecimal(), '²'.isdigit(), '²'.isnumeric()
+ (False, True, True)
+
+ See also "isdecimal()" and "isnumeric()".
+
str.isidentifier()
Return "True" if the string is a valid identifier according to the
@@ -10236,15 +10256,14 @@ str.isnumeric()
>>> '0123456789'.isnumeric()
True
- >>> '٠١٢٣٤٥٦٧٨٩'.isnumeric() # Arabic-indic digit zero to nine
+ >>> '٠١٢٣٤٥٦٧٨٩'.isnumeric() # Arabic-Indic digits zero to nine
True
>>> '⅕'.isnumeric() # Vulgar fraction one fifth
True
>>> '²'.isdecimal(), '²'.isdigit(), '²'.isnumeric()
(False, True, True)
- See also "isdecimal()" and "isdigit()". Numeric characters are a
- superset of decimal numbers.
+ See also "isdecimal()" and "isdigit()".
str.isprintable()
@@ -10626,7 +10645,7 @@ str.split(sep=None, maxsplit=-1)
>>> " foo ".split(maxsplit=0)
['foo ']
- See also "join()".
+ See also "join()" and "rsplit()".
str.splitlines(keepends=False)
@@ -10716,6 +10735,8 @@ str.strip(chars=None, /)
not a prefix or suffix; rather, all combinations of its values are
stripped.
+ Whitespace characters are defined by "str.isspace()".
+
For example:
>>> ' spacious '.strip()
@@ -13311,6 +13332,9 @@ class dict(iterable, /, **kwargs)
insertion order. This behavior was an implementation detail of
CPython from 3.6.
+ Dictionaries are generic over two types, signifying (respectively)
+ the types of the dictionary’s keys and values.
+
These are the operations that dictionaries support (and therefore,
custom mapping types should support too):
@@ -14015,6 +14039,8 @@ class list(iterable=(), /)
Many other operations also produce lists, including the "sorted()"
built-in.
+ Lists are generic over the types of their items.
+
Lists implement all of the common and mutable sequence operations.
Lists also provide the following additional method:
@@ -14105,6 +14131,10 @@ class tuple(iterable=(), /)
Tuples implement all of the common sequence operations.
+ Tuples are generic over the types of their contents. For more
+ information, refer to the typing documentation on annotating
+ tuples.
+
For heterogeneous collections of data where access by name is clearer
than access by index, "collections.namedtuple()" may be a more
appropriate choice than a simple tuple object.
diff --git a/Lib/rlcompleter.py b/Lib/rlcompleter.py
index 23eb0020f..e75dd0a9e 100644
--- a/Lib/rlcompleter.py
+++ b/Lib/rlcompleter.py
@@ -34,6 +34,7 @@ import builtins
import inspect
import keyword
import re
+import types
import __main__
import warnings
@@ -178,14 +179,14 @@ class Completer:
if (word[:n] == attr and
not (noprefix and word[:n+1] == noprefix)):
match = "%s.%s" % (expr, word)
- if isinstance(getattr(type(thisobject), word, None),
- property):
- # bpo-44752: thisobject.word is a method decorated by
- # `@property`. What follows applies a postfix if
- # thisobject.word is callable, but know we know that
- # this is not callable (because it is a property).
- # Also, getattr(thisobject, word) will evaluate the
- # property method, which is not desirable.
+
+ class_attr = getattr(type(thisobject), word, None)
+ if isinstance(
+ class_attr,
+ (property, types.GetSetDescriptorType, types.MemberDescriptorType)
+ ) or (hasattr(class_attr, '__get__') and not callable(class_attr)):
+ # Avoid evaluating descriptors, which could run
+ # arbitrary code or raise exceptions.
matches.append(match)
continue
if (value := getattr(thisobject, word, None)) is not None:
diff --git a/Lib/shutil.py b/Lib/shutil.py
index b7608f7ed..a3a112f69 100644
--- a/Lib/shutil.py
+++ b/Lib/shutil.py
@@ -885,10 +885,14 @@ def move(src, dst, copy_function=copy2):
If dst already exists but is not a directory, it may be overwritten
depending on os.rename() semantics.
- If the destination is on our current filesystem, then rename() is used.
- Otherwise, src is copied to the destination and then removed. Symlinks are
- recreated under the new name if os.rename() fails because of cross
- filesystem renames.
+ os.rename() is preferably used if the source and destination are on the
+ same filesystem. In case os.rename() fails due to OSError (e.g. the user
+ has write permission to *dst* file but not to its parent directory),
+ this method falls back to using *copy_function* silently.
+ Symlinks are also recreated under the new name if os.rename() fails
+ because of cross filesystem renames.
+
+ It's recommended to use os.rename() if atomic move is strictly required.
The optional `copy_function` argument is a callable that will be used
to copy the source or it will be delegated to `copytree`.
@@ -940,8 +944,8 @@ def move(src, dst, copy_function=copy2):
return real_dst
def _destinsrc(src, dst):
- src = os.path.abspath(src)
- dst = os.path.abspath(dst)
+ src = os.path.realpath(src)
+ dst = os.path.realpath(dst)
if not src.endswith(os.path.sep):
src += os.path.sep
if not dst.endswith(os.path.sep):
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 414aefe97..e6734db24 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -498,7 +498,7 @@ class _Stream:
if flag & 4:
xlen = ord(self.__read(1)) + 256 * ord(self.__read(1))
- self.read(xlen)
+ self.__read(xlen)
if flag & 8:
while True:
s = self.__read(1)
@@ -830,16 +830,22 @@ def _get_filtered_attrs(member, dest_path, for_data=True):
if member.islnk() or member.issym():
if os.path.isabs(member.linkname):
raise AbsoluteLinkError(member)
+ # A link member that resolves to the destination directory itself
+ # would replace it with a (sym)link, redirecting the destination
+ # for all subsequent members.
+ if target_path == dest_path:
+ raise OutsideDestinationError(member, target_path)
normalized = os.path.normpath(member.linkname)
if normalized != member.linkname:
new_attrs['linkname'] = normalized
if member.issym():
- target_path = os.path.join(dest_path,
- os.path.dirname(name),
- member.linkname)
+ # The symlink is created at `name` with trailing separators
+ # stripped, so its target is relative to the directory
+ # containing that path.
+ link_dir = os.path.dirname(name.rstrip('/' + os.sep))
+ target_path = os.path.join(dest_path, link_dir, normalized)
else:
- target_path = os.path.join(dest_path,
- member.linkname)
+ target_path = os.path.join(dest_path, normalized)
target_path = os.path.realpath(target_path,
strict=os.path.ALLOW_MISSING)
if os.path.commonpath([target_path, dest_path]) != dest_path:
@@ -893,11 +899,14 @@ class TarInfo(object):
size = 'Size in bytes.',
mtime = 'Time of last modification.',
chksum = 'Header checksum.',
- type = ('File type. type is usually one of these constants: '
- 'REGTYPE, AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, '
- 'CONTTYPE, CHRTYPE, BLKTYPE, GNUTYPE_SPARSE.'),
+ type = ('File type. type is usually one of these constants: '
+ 'REGTYPE,\n'
+ 'AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, '
+ 'CONTTYPE, CHRTYPE,\n'
+ 'BLKTYPE, GNUTYPE_SPARSE.'),
linkname = ('Name of the target file name, which is only present '
- 'in TarInfo objects of type LNKTYPE and SYMTYPE.'),
+ 'in TarInfo\n'
+ 'objects of type LNKTYPE and SYMTYPE.'),
uname = 'User name.',
gname = 'Group name.',
devmajor = 'Device major number.',
@@ -905,7 +914,8 @@ class TarInfo(object):
offset = 'The tar header starts here.',
offset_data = "The file's data starts here.",
pax_headers = ('A dictionary containing key-value pairs of an '
- 'associated pax extended header.'),
+ 'associated pax\n'
+ 'extended header.'),
sparse = 'Sparse member information.',
_tarfile = None,
_sparse_structs = None,
@@ -2267,10 +2277,11 @@ class TarFile(object):
return tarinfo
def list(self, verbose=True, *, members=None):
- """Print a table of contents to sys.stdout. If 'verbose' is False, only
- the names of the members are printed. If it is True, an 'ls -l'-like
- output is produced. 'members' is optional and must be a subset of the
- list returned by getmembers().
+ """Print a table of contents to sys.stdout.
+
+ If 'verbose' is False, only the names of the members are printed.
+ If it is True, an 'ls -l'-like output is produced. 'members' is
+ optional and must be a subset of the list returned by getmembers().
"""
# Convert tarinfo type to stat type.
type2mode = {REGTYPE: stat.S_IFREG, SYMTYPE: stat.S_IFLNK,
@@ -2361,10 +2372,12 @@ class TarFile(object):
self.addfile(tarinfo)
def addfile(self, tarinfo, fileobj=None):
- """Add the TarInfo object 'tarinfo' to the archive. If 'tarinfo' represents
- a non zero-size regular file, the 'fileobj' argument should be a binary file,
- and tarinfo.size bytes are read from it and added to the archive.
- You can create TarInfo objects directly, or by using gettarinfo().
+ """Add the TarInfo object 'tarinfo' to the archive.
+
+ If 'tarinfo' represents a non zero-size regular file, the 'fileobj'
+ argument should be a binary file, and tarinfo.size bytes are read
+ from it and added to the archive. You can create TarInfo objects
+ directly, or by using gettarinfo().
"""
self._check("awx")
diff --git a/Lib/test/datetimetester.py b/Lib/test/datetimetester.py
index c6534adb1..c1bb6138a 100644
--- a/Lib/test/datetimetester.py
+++ b/Lib/test/datetimetester.py
@@ -7313,6 +7313,36 @@ class ExtensionModuleTests(unittest.TestCase):
self.assertEqual(out, b"a" * 8)
self.assertEqual(err, b"")
+ @support.cpython_only
+ @support.subTests(("setup", "call"), [
+ ("obj = _datetime.timedelta", "obj(seconds=2)"),
+ ("obj = _datetime.timedelta(seconds=2)", "obj.total_seconds()"),
+ ("obj = _datetime.date(2026, 6, 7)", "obj.isocalendar()"),
+ ])
+ def test_static_datetime_types_outlive_collected_module(self, setup, call):
+ # gh-151039: This code used to crash
+ script = f"""if True:
+ import sys, gc
+ import _datetime
+
+ {setup} # static C type, survives the module
+ del sys.modules['_datetime']
+ del _datetime
+ sys.modules['_datetime'] = None # block re-import
+ gc.collect() # module object is collected
+
+ try:
+ {call} # used to be a segmentation fault
+ except ImportError:
+ pass
+ else:
+ raise AssertionError("ImportError not raised")
+ """
+ rc, out, err = script_helper.assert_python_ok("-c", script)
+ self.assertEqual(rc, 0)
+ self.assertEqual(out, b'')
+ self.assertEqual(err, b'')
+
def load_tests(loader, standard_tests, pattern):
standard_tests.addTest(ZoneInfoCompleteTest())
diff --git a/Lib/test/support/__init__.py b/Lib/test/support/__init__.py
index 6635ec347..701d34bba 100644
--- a/Lib/test/support/__init__.py
+++ b/Lib/test/support/__init__.py
@@ -3227,3 +3227,18 @@ def control_characters_c0() -> list[str]:
C0 control characters defined as the byte range 0x00-0x1F, and 0x7F.
"""
return [chr(c) for c in range(0x00, 0x20)] + ["\x7F"]
+
+
+STATUS_DLL_INIT_FAILED = 0xC0000142
+def skip_on_low_desktop_heap_memory_subprocess(returncode):
+ if sys.platform not in ('win32', 'cygwin'):
+ return
+ # On Windows, STATUS_DLL_INIT_FAILED is a generic error code that could
+ # come from any of the DLLs being loaded when a new Python process is
+ # created. In practice, it's likely a memory allocation failure in the
+ # desktop heap memory which caused the DLL init failure, especially on
+ # process created with CREATE_NEW_CONSOLE creation flag. See the article:
+ # https://learn.microsoft.com/en-us/troubleshoot/windows-server/performance/desktop-heap-limitation-out-of-memory
+ if returncode == STATUS_DLL_INIT_FAILED:
+ raise unittest.SkipTest('gh-150436: DLL init failed, likely because '
+ 'of low desktop heap memory')
diff --git a/Lib/test/test_http_cookies.py b/Lib/test/test_http_cookies.py
index ab01d68d1..2379dad19 100644
--- a/Lib/test/test_http_cookies.py
+++ b/Lib/test/test_http_cookies.py
@@ -1,11 +1,11 @@
# Simple test suite for http/cookies.py
-import base64
import copy
import unittest
import doctest
from http import cookies
import pickle
from test import support
+import urllib.parse
class CookieTests(unittest.TestCase):
@@ -131,8 +131,8 @@ class CookieTests(unittest.TestCase):
@support.requires_resource('cpu')
def test_unquote_large(self):
- # n = 10**6
- n = 10**4 # XXX: RUSTPYTHON; This takes more than 10 minutes to run. lower to 4
+ n = 10**6
+ n = 10**4 # TODO: RUSTPYTHON; This takes more than 10 minutes to run. lower to 4
for encoded in r'\\', r'\134':
with self.subTest(encoded):
data = 'a="b=' + encoded*n + ';"'
@@ -153,19 +153,19 @@ class CookieTests(unittest.TestCase):
self.assertEqual(C.output(['path']),
'Set-Cookie: Customer="WILE_E_COYOTE"; Path=/acme')
- cookie_encoded = base64.b64encode(b'Customer="WILE_E_COYOTE"; Path=/acme; Version=1').decode('ascii')
+ cookie_encoded = urllib.parse.quote('Customer="WILE_E_COYOTE"; Path=/acme; Version=1', safe='', encoding='utf-8')
self.assertEqual(C.js_output(), fr"""
""")
- cookie_encoded = base64.b64encode(b'Customer="WILE_E_COYOTE"; Path=/acme').decode('ascii')
+ cookie_encoded = urllib.parse.quote('Customer="WILE_E_COYOTE"; Path=/acme', safe='', encoding='utf-8')
self.assertEqual(C.js_output(['path']), fr"""
""")
@@ -270,19 +270,19 @@ class CookieTests(unittest.TestCase):
self.assertEqual(C.output(['path']),
'Set-Cookie: Customer="WILE_E_COYOTE"; Path=/acme')
- expected_encoded_cookie = base64.b64encode(b'Customer=\"WILE_E_COYOTE\"; Path=/acme; Version=1').decode('ascii')
+ expected_encoded_cookie = urllib.parse.quote('Customer=\"WILE_E_COYOTE\"; Path=/acme; Version=1', safe='', encoding='utf-8')
self.assertEqual(C.js_output(), fr"""
""")
- expected_encoded_cookie = base64.b64encode(b'Customer=\"WILE_E_COYOTE\"; Path=/acme').decode('ascii')
+ expected_encoded_cookie = urllib.parse.quote('Customer=\"WILE_E_COYOTE\"; Path=/acme', safe='', encoding='utf-8')
self.assertEqual(C.js_output(['path']), fr"""
""")
@@ -373,13 +373,14 @@ class MorselTests(unittest.TestCase):
self.assertEqual(
M.output(),
"Set-Cookie: %s=%s; Path=/foo" % (i, "%s_coded_val" % i))
- expected_encoded_cookie = base64.b64encode(
- ("%s=%s; Path=/foo" % (i, "%s_coded_val" % i)).encode("ascii")
- ).decode('ascii')
+ expected_encoded_cookie = urllib.parse.quote(
+ "%s=%s; Path=/foo" % (i, "%s_coded_val" % i),
+ safe='', encoding='utf-8',
+ )
expected_js_output = """
""" % (expected_encoded_cookie,)
diff --git a/Lib/test/test_json/json_lines.jsonl b/Lib/test/test_json/json_lines.jsonl
new file mode 100644
index 000000000..d2f292111
--- /dev/null
+++ b/Lib/test/test_json/json_lines.jsonl
@@ -0,0 +1,2 @@
+{"ingredients":["frog", "water", "chocolate", "glucose"]}
+{"ingredients":["chocolate","steel bolts"]}
diff --git a/Lib/test/test_json/test_speedups.py b/Lib/test/test_json/test_speedups.py
index 370a2539d..64d210f4a 100644
--- a/Lib/test/test_json/test_speedups.py
+++ b/Lib/test/test_json/test_speedups.py
@@ -1,4 +1,5 @@
from test.test_json import CTest
+from test.support import gc_collect
import unittest # XXX: RUSTPYTHON; importing to be able to skip tests
@@ -117,3 +118,65 @@ class TestEncode(CTest):
self.assertEqual(enc(['spam', {'ham': 'eggs'}], 3)[0], expected2)
self.assertRaises(TypeError, enc, ['spam', {'ham': 'eggs'}], 3.0)
self.assertRaises(TypeError, enc, ['spam', {'ham': 'eggs'}])
+
+ @unittest.expectedFailure # TODO: RUSTPYTHON; TypeError: 'NoneType' object is not callable
+ def test_mutate_dict_items_during_encode(self):
+ # gh-142831: Clearing the items list via a re-entrant key encoder
+ # must not cause a use-after-free. BadDict.items() returns a
+ # mutable list; encode_str clears it while iterating.
+ items = None
+
+ class BadDict(dict):
+ def items(self):
+ nonlocal items
+ items = [("boom", object())]
+ return items
+
+ cleared = False
+ def encode_str(obj):
+ nonlocal items, cleared
+ if items is not None:
+ items.clear()
+ items = None
+ cleared = True
+ gc_collect()
+ return '"x"'
+
+ encoder = self.json.encoder.c_make_encoder(
+ None, lambda o: "null",
+ encode_str, None,
+ ": ", ", ", False,
+ False, True
+ )
+
+ # Must not crash (use-after-free under ASan before fix)
+ encoder(BadDict(real=1), 0)
+ self.assertTrue(cleared)
+
+ @unittest.expectedFailure # TODO: RUSTPYTHON; TypeError: 'NoneType' object is not callable
+ def test_mutate_list_during_encode(self):
+ # gh-142831: Clearing a list mid-iteration via the default
+ # callback must not cause a use-after-free.
+ call_count = 0
+ lst = [object() for _ in range(10)]
+
+ def default(obj):
+ nonlocal call_count
+ call_count += 1
+ if call_count == 3:
+ lst.clear()
+ gc_collect()
+ return None
+
+ encoder = self.json.encoder.c_make_encoder(
+ None, default,
+ self.json.encoder.c_encode_basestring, None,
+ ": ", ", ", False,
+ False, True
+ )
+
+ # Must not crash (use-after-free under ASan before fix)
+ encoder(lst, 0)
+ # Verify the mutation path was actually hit and the loop
+ # stopped iterating after the list was cleared.
+ self.assertEqual(call_count, 3)
diff --git a/Lib/test/test_json/test_tool.py b/Lib/test/test_json/test_tool.py
index 7b5d217a2..0a96b318b 100644
--- a/Lib/test/test_json/test_tool.py
+++ b/Lib/test/test_json/test_tool.py
@@ -1,4 +1,5 @@
import errno
+import pathlib
import os
import sys
import textwrap
@@ -157,6 +158,14 @@ class TestMain(unittest.TestCase):
self.assertEqual(process.stdout, self.jsonlines_expect)
self.assertEqual(process.stderr, '')
+ @force_not_colorized
+ def test_jsonlines_from_file(self):
+ jsonl = pathlib.Path(__file__).parent / 'json_lines.jsonl'
+ args = sys.executable, '-m', self.module, '--json-lines', jsonl
+ process = subprocess.run(args, capture_output=True, text=True, check=True)
+ self.assertEqual(process.stdout, self.jsonlines_expect)
+ self.assertEqual(process.stderr, '')
+
def test_help_flag(self):
rc, out, err = assert_python_ok('-m', self.module, '-h',
PYTHON_COLORS='0')
diff --git a/Lib/test/test_os.py b/Lib/test/test_os.py
index cfaf7429d..5ba6b3de2 100644
--- a/Lib/test/test_os.py
+++ b/Lib/test/test_os.py
@@ -4043,7 +4043,6 @@ class TestSendfile(unittest.IsolatedAsyncioTestCase):
@requires_headers_trailers
@requires_32b
async def test_headers_overflow_32bits(self):
- self.server.handler_instance.accumulate = False
with self.assertRaises(OSError) as cm:
await self.async_sendfile(self.sockno, self.fileno, 0, 0,
headers=[b"x" * 2**16] * 2**15)
@@ -4052,7 +4051,6 @@ class TestSendfile(unittest.IsolatedAsyncioTestCase):
@requires_headers_trailers
@requires_32b
async def test_trailers_overflow_32bits(self):
- self.server.handler_instance.accumulate = False
with self.assertRaises(OSError) as cm:
await self.async_sendfile(self.sockno, self.fileno, 0, 0,
trailers=[b"x" * 2**16] * 2**15)
diff --git a/Lib/test/test_rlcompleter.py b/Lib/test/test_rlcompleter.py
index 6db31df89..5ba183dfd 100644
--- a/Lib/test/test_rlcompleter.py
+++ b/Lib/test/test_rlcompleter.py
@@ -1,6 +1,7 @@
import unittest
from unittest.mock import patch
import builtins
+import types
import rlcompleter
from test.support import MISSING_C_DOCSTRINGS
@@ -136,6 +137,57 @@ class TestRlcompleter(unittest.TestCase):
self.assertEqual(completer.complete('f.b', 0), 'f.bar')
self.assertFalse(f.property_called)
+ def test_released_memoryview_completion_works(self):
+ mv = memoryview(b"abc")
+ mv.release()
+
+ self.assertIsInstance(type(mv).shape, types.GetSetDescriptorType)
+ self.assertIsInstance(type(mv).strides, types.GetSetDescriptorType)
+
+ completer = rlcompleter.Completer(dict(mv=mv))
+ matches = completer.attr_matches('mv.')
+
+ # These are getset descriptors on memoryview and should be completed
+ # without evaluating the released-memoryview getters.
+ self.assertIn('mv.shape', matches)
+ self.assertIn('mv.strides', matches)
+
+ def test_member_descriptor_not_evaluated(self):
+ class Foo:
+ __slots__ = ("boom",)
+ boom_accesses = 0
+
+ def __getattribute__(self, name):
+ if name == "boom":
+ type(self).boom_accesses += 1
+ raise RuntimeError("boom access should be skipped")
+ return super().__getattribute__(name)
+
+ self.assertIsInstance(Foo.boom, types.MemberDescriptorType)
+
+ completer = rlcompleter.Completer(dict(f=Foo()))
+ matches = completer.attr_matches('f.')
+ self.assertIn('f.boom', matches)
+ self.assertEqual(Foo.boom_accesses, 0)
+
+ def test_raising_descriptor_completion_works(self):
+ class ExplodingDescriptor:
+ def __init__(self):
+ self.instance_get_calls = 0
+
+ def __get__(self, obj, owner):
+ if obj is None:
+ return self
+ self.instance_get_calls += 1
+ raise RuntimeError("descriptor getter exploded")
+
+ class Foo:
+ boom = ExplodingDescriptor()
+
+ completer = rlcompleter.Completer(dict(f=Foo()))
+ matches = completer.attr_matches('f.')
+ self.assertIn('f.boom', matches)
+ self.assertEqual(Foo.boom.instance_get_calls, 0)
def test_uncreated_attr(self):
# Attributes like properties and slots should be completed even when
diff --git a/Lib/test/test_shutil.py b/Lib/test/test_shutil.py
index fb1a7d876..8813cc46c 100644
--- a/Lib/test/test_shutil.py
+++ b/Lib/test/test_shutil.py
@@ -2888,6 +2888,23 @@ class TestMove(BaseTest, unittest.TestCase):
finally:
os_helper.rmtree(TESTFN)
+ @os_helper.skip_unless_symlink
+ def test_destinsrc_symlink_bypass(self):
+ tmp = self.mkdtemp()
+ src = os.path.join(tmp, 'src')
+ os.makedirs(src)
+ # tmp/link -> tmp (one level up)
+ link = os.path.join(tmp, 'link')
+ os.symlink(tmp, link)
+ # raw path: tmp/link/src/sub - no src prefix in string space
+ # real path: tmp/src/sub - physically inside src
+ dst = os.path.join(link, 'src', 'sub')
+ self.assertTrue(
+ shutil._destinsrc(src, dst),
+ msg='_destinsrc failed to detect dst inside src via symlink '
+ '(dst=%s, src=%s)' % (dst, src),
+ )
+
@os_helper.skip_unless_symlink
@mock_rename
def test_move_file_symlink(self):
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index 8d9f8824f..d974c7d46 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -892,10 +892,39 @@ class MiscReadTestBase(CommonReadTest):
self._assert_on_file_content(hardlink_filepath, sha256_regtype)
+class GzipReadTestBase:
+
+ def test_read_with_extra_field(self):
+ with open(self.tarname, 'rb') as f:
+ data = bytearray(f.read())
+ flags = data[3]
+ self.assertEqual(flags, 8)
+ data[3] = flags | 4
+ data[10:10] = b'\x05\x00extra'
+ with open(tmpname, 'wb') as f:
+ f.write(data)
+ print(self.mode)
+ with tarfile.open(tmpname, mode=self.mode):
+ pass
+
+ def test_read_with_file_comment(self):
+ with open(self.tarname, 'rb') as f:
+ data = bytearray(f.read())
+ flags = data[3]
+ self.assertEqual(flags, 8)
+ data[3] = flags | 16
+ i = data.index(0, 10) + 1
+ data[i:i] = b'comment\x00'
+ with open(tmpname, 'wb') as f:
+ f.write(data)
+ with tarfile.open(tmpname, mode=self.mode):
+ pass
+
+
class MiscReadTest(MiscReadTestBase, unittest.TestCase):
test_fail_comp = None
-class GzipMiscReadTest(GzipTest, MiscReadTestBase, unittest.TestCase):
+class GzipMiscReadTest(GzipTest, GzipReadTestBase, MiscReadTestBase, unittest.TestCase):
pass
class Bz2MiscReadTest(Bz2Test, MiscReadTestBase, unittest.TestCase):
@@ -969,7 +998,7 @@ class StreamReadTest(CommonReadTest, unittest.TestCase):
finally:
tar1.close()
-class GzipStreamReadTest(GzipTest, StreamReadTest):
+class GzipStreamReadTest(GzipTest, GzipReadTestBase, StreamReadTest):
pass
class Bz2StreamReadTest(Bz2Test, StreamReadTest):
@@ -3682,6 +3711,39 @@ class TestExtractionFilters(unittest.TestCase):
# The destination for the extraction, within `outerdir`
destdir = outerdir / 'dest'
+ @classmethod
+ def setUpClass(cls):
+ # Posix and Windows have different pathname resolution:
+ # either symlink or a '..' component resolve first.
+ # Let's see which we are on.
+ if os_helper.can_symlink():
+ testpath = os.path.join(TEMPDIR, 'resolution_test')
+ os.mkdir(testpath)
+
+ # testpath/current links to `.` which is all of:
+ # - `testpath`
+ # - `testpath/current`
+ # - `testpath/current/current`
+ # - etc.
+ os.symlink('.', os.path.join(testpath, 'current'))
+
+ # we'll test where `testpath/current/../file` ends up
+ with open(os.path.join(testpath, 'current', '..', 'file'), 'w'):
+ pass
+
+ if os.path.exists(os.path.join(testpath, 'file')):
+ # Windows collapses 'current\..' to '.' first, leaving
+ # 'testpath\file'
+ cls.dotdot_resolves_early = True
+ elif os.path.exists(os.path.join(testpath, '..', 'file')):
+ # Posix resolves 'current' to '.' first, leaving
+ # 'testpath/../file'
+ cls.dotdot_resolves_early = False
+ else:
+ raise AssertionError('Could not determine link resolution')
+ else:
+ cls.dotdot_resolves_early = False
+
@contextmanager
def check_context(self, tar, filter, *, check_flag=True):
"""Extracts `tar` to `self.destdir` and allows checking the result
@@ -3853,10 +3915,19 @@ class TestExtractionFilters(unittest.TestCase):
+ "which is outside the destination")
with self.check_context(arc.open(), 'data'):
- self.expect_exception(
- tarfile.LinkOutsideDestinationError,
- """'parent' would link to ['"].*outerdir['"], """
- + "which is outside the destination")
+ if self.dotdot_resolves_early:
+ # 'current/../..' normalises to '..', which is rejected.
+ self.expect_exception(
+ tarfile.LinkOutsideDestinationError,
+ """'parent' would link to ['"].*outerdir['"], """
+ + "which is outside the destination")
+ else:
+ # 'current/..' normalises to '.'; the rewritten link is
+ # created and 'parent/evil' lands harmlessly inside the
+ # destination.
+ self.expect_file('current', symlink_to='.')
+ self.expect_file('parent', symlink_to='.')
+ self.expect_file('evil')
else:
# No symlink support. The symlinks are ignored.
@@ -3946,35 +4017,6 @@ class TestExtractionFilters(unittest.TestCase):
# Test interplaying symlinks
# Inspired by 'dirsymlink2b' in jwilk/traversal-archives
- # Posix and Windows have different pathname resolution:
- # either symlink or a '..' component resolve first.
- # Let's see which we are on.
- if os_helper.can_symlink():
- testpath = os.path.join(TEMPDIR, 'resolution_test')
- os.mkdir(testpath)
-
- # testpath/current links to `.` which is all of:
- # - `testpath`
- # - `testpath/current`
- # - `testpath/current/current`
- # - etc.
- os.symlink('.', os.path.join(testpath, 'current'))
-
- # we'll test where `testpath/current/../file` ends up
- with open(os.path.join(testpath, 'current', '..', 'file'), 'w'):
- pass
-
- if os.path.exists(os.path.join(testpath, 'file')):
- # Windows collapses 'current\..' to '.' first, leaving
- # 'testpath\file'
- dotdot_resolves_early = True
- elif os.path.exists(os.path.join(testpath, '..', 'file')):
- # Posix resolves 'current' to '.' first, leaving
- # 'testpath/../file'
- dotdot_resolves_early = False
- else:
- raise AssertionError('Could not determine link resolution')
-
with ArchiveMaker() as arc:
# `current` links to `.` which is both the destination directory
@@ -4010,7 +4052,7 @@ class TestExtractionFilters(unittest.TestCase):
with self.check_context(arc.open(), 'data'):
if os_helper.can_symlink():
- if dotdot_resolves_early:
+ if self.dotdot_resolves_early:
# Fail when extracting a file outside destination
self.expect_exception(
tarfile.OutsideDestinationError,
@@ -4130,6 +4172,76 @@ class TestExtractionFilters(unittest.TestCase):
+ """['"].*moo['"], which is outside the """
+ "destination")
+ @symlink_test
+ @os_helper.skip_unless_symlink
+ def test_normpath_realpath_mismatch(self):
+ # The link-target check must validate the value that will actually
+ # be written to disk (the normalised linkname), not the original.
+ # Here 'a' is a symlink to a deep nonexistent path, so realpath()
+ # of 'a/../../...' stays inside the destination while normpath()
+ # collapses 'a/..' lexically and escapes.
+ depth = len(self.destdir.parts) + 5
+ deep = '/'.join(f'p{i}' for i in range(depth))
+ sneaky = 'a/' + '../' * depth + 'flag'
+ for kind in 'symlink_to', 'hardlink_to':
+ with self.subTest(kind):
+ with ArchiveMaker() as arc:
+ arc.add('a', symlink_to=deep)
+ arc.add('escape', **{kind: sneaky})
+ with self.check_context(arc.open(), 'data'):
+ self.expect_exception(
+ tarfile.LinkOutsideDestinationError)
+
+ @symlink_test
+ @os_helper.skip_unless_symlink
+ def test_symlink_trailing_slash(self):
+ # A trailing slash on a symlink member's name must not cause the
+ # link target to be resolved relative to the wrong directory.
+ with ArchiveMaker() as arc:
+ t = tarfile.TarInfo('x/')
+ t.type = tarfile.SYMTYPE
+ t.linkname = '..'
+ arc.tar_w.addfile(t)
+ arc.add('x/escaped', content='hi')
+
+ with self.check_context(arc.open(), 'data'):
+ self.expect_exception(tarfile.LinkOutsideDestinationError)
+
+ @symlink_test
+ @os_helper.skip_unless_symlink
+ def test_link_at_destination(self):
+ # A link member whose name resolves to the destination directory
+ # itself must be rejected: otherwise the destination is replaced
+ # by a symlink and later members can be redirected through it.
+ for name in '', '.', './':
+ with ArchiveMaker() as arc:
+ t = tarfile.TarInfo(name)
+ t.type = tarfile.SYMTYPE
+ t.linkname = '.'
+ arc.tar_w.addfile(t)
+
+ with self.check_context(arc.open(), 'data'):
+ self.expect_exception(tarfile.OutsideDestinationError)
+
+ @symlink_test
+ @os_helper.skip_unless_symlink
+ def test_empty_name_symlink_chain(self):
+ # Regression test for a chain of empty-named symlinks that
+ # incrementally redirects the destination outwards.
+ with ArchiveMaker() as arc:
+ for name, target in [('', ''), ('a/', '..'),
+ ('', 'dummy'), ('', 'a'),
+ ('b/', '..'),
+ ('', 'dummy'), ('', 'a/b')]:
+ t = tarfile.TarInfo(name)
+ t.type = tarfile.SYMTYPE
+ t.linkname = target
+ arc.tar_w.addfile(t)
+ arc.add('escaped', content='hi')
+
+ with self.check_context(arc.open(), 'data'):
+ self.expect_exception(tarfile.FilterError)
+
@symlink_test
def test_deep_symlink(self):
# Test that symlinks and hardlinks inside a directory