Mailman 3 January 2025 - Python-checkins

[3.12] GH-125722: Increase minimum supported Sphinx to 8.1.3 (GH-128922) (#129038)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/6f19c6a705d4bdbf01f4e704e42f38d375… commit: 6f19c6a705d4bdbf01f4e704e42f38d37597b60b branch: 3.12 author: Miss Islington (bot) <31488909+miss-islington(a)users.noreply.github.com> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:46:05Z summary: [3.12] GH-125722: Increase minimum supported Sphinx to 8.1.3 (GH-128922) (#129038) (cherry picked from commit d46b577ec026c2e700a9f920f81cfbf698e53eb6) Co-authored-by: Adam Turner <9087854+AA-Turner(a)users.noreply.github.com> files: A Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst D Doc/requirements-oldest-sphinx.txt M .github/workflows/reusable-docs.yml M Doc/conf.py M Doc/constraints.txt M Doc/requirements.txt M Doc/tools/extensions/c_annotations.py diff --git a/.github/workflows/reusable-docs.yml b/.github/workflows/reusable-docs.yml index c5f71831a005fd..6ac7d40c4aec27 100644 --- a/.github/workflows/reusable-docs.yml +++ b/.github/workflows/reusable-docs.yml @@ -73,26 +73,6 @@ jobs: --fail-if-improved \ --fail-if-new-news-nit - # This build doesn't use problem matchers or check annotations - build_doc_oldest_supported_sphinx: - name: 'Docs (Oldest Sphinx)' - runs-on: ubuntu-latest - timeout-minutes: 60 - steps: - - uses: actions/checkout@v4 - with: - persist-credentials: false - - name: 'Set up Python' - uses: actions/setup-python@v5 - with: - python-version: '3.13' # known to work with Sphinx 7.2.6 - cache: 'pip' - cache-dependency-path: 'Doc/requirements-oldest-sphinx.txt' - - name: 'Install build dependencies' - run: make -C Doc/ venv REQUIREMENTS="requirements-oldest-sphinx.txt" - - name: 'Build HTML documentation' - run: make -C Doc/ SPHINXOPTS="-q" SPHINXERRORHANDLING="-W --keep-going" html - # Run "doctest" on HEAD as new syntax doesn't exist in the latest stable release doctest: name: 'Doctest' diff --git a/Doc/conf.py b/Doc/conf.py index 4b18d02a943f62..4c74040976959c 100644 --- a/Doc/conf.py +++ b/Doc/conf.py @@ -9,9 +9,6 @@ import importlib import os import sys -import time - -import sphinx # Make our custom extensions available to Sphinx sys.path.append(os.path.abspath('tools/extensions')) @@ -61,10 +58,7 @@ # General substitutions. project = 'Python' -if sphinx.version_info[:2] >= (8, 1): - copyright = "2001-%Y, Python Software Foundation" -else: - copyright = f"2001-{time.strftime('%Y')}, Python Software Foundation" +copyright = "2001-%Y, Python Software Foundation" # We look for the Include/patchlevel.h file in the current Python source tree # and replace the values accordingly. @@ -85,7 +79,8 @@ highlight_language = 'python3' # Minimum version of sphinx required -needs_sphinx = '7.2.6' +# Keep this version in sync with ``Doc/requirements.txt``. +needs_sphinx = '8.1.3' # Create table of contents entries for domain objects (e.g. functions, classes, # attributes, etc.). Default is True. @@ -350,13 +345,7 @@ # This 'Last updated on:' timestamp is inserted at the bottom of every page. html_last_updated_fmt = '%b %d, %Y (%H:%M UTC)' -if sphinx.version_info[:2] >= (8, 1): - html_last_updated_use_utc = True -else: - html_time = int(os.environ.get('SOURCE_DATE_EPOCH', time.time())) - html_last_updated_fmt = time.strftime( - html_last_updated_fmt, time.gmtime(html_time) - ) +html_last_updated_use_utc = True # Path to find HTML templates to override theme templates_path = ['tools/templates'] @@ -594,16 +583,6 @@ } extlinks_detect_hardcoded_links = True -if sphinx.version_info[:2] < (8, 1): - # Sphinx 8.1 has in-built CVE and CWE roles. - extlinks |= { - "cve": ( - "https://www.cve.org/CVERecord?id=CVE-%s", - "CVE-%s", - ), - "cwe": ("https://cwe.mitre.org/data/definitions/%s.html", "CWE-%s"), - } - # Options for c_annotations extension # ----------------------------------- diff --git a/Doc/constraints.txt b/Doc/constraints.txt index 26ac1862dbac0b..29cd4be1d3c8db 100644 --- a/Doc/constraints.txt +++ b/Doc/constraints.txt @@ -13,14 +13,12 @@ packaging<25 Pygments<3 requests<3 snowballstemmer<3 -# keep lower-bounds until Sphinx 8.1 is released -# https://github.com/sphinx-doc/sphinx/pull/12756 -sphinxcontrib-applehelp>=1.0.7,<3 -sphinxcontrib-devhelp>=1.0.6,<3 -sphinxcontrib-htmlhelp>=2.0.6,<3 -sphinxcontrib-jsmath>=1.0.1,<2 -sphinxcontrib-qthelp>=1.0.6,<3 -sphinxcontrib-serializinghtml>=1.1.9,<3 +sphinxcontrib-applehelp<3 +sphinxcontrib-devhelp<3 +sphinxcontrib-htmlhelp<3 +sphinxcontrib-jsmath<2 +sphinxcontrib-qthelp<3 +sphinxcontrib-serializinghtml<3 # Direct dependencies of Jinja2 (Jinja is a dependency of Sphinx, see above) MarkupSafe<3 diff --git a/Doc/requirements-oldest-sphinx.txt b/Doc/requirements-oldest-sphinx.txt deleted file mode 100644 index c8027a05706c21..00000000000000 --- a/Doc/requirements-oldest-sphinx.txt +++ /dev/null @@ -1,35 +0,0 @@ -# Requirements to build the Python documentation, for the oldest supported -# Sphinx version. -# -# We pin Sphinx and all of its dependencies to ensure a consistent environment. - -blurb -python-docs-theme>=2022.1 - -# Generated from: -# pip install "Sphinx~=7.2.6" -# pip freeze -# -# Sphinx 7.2.6 comes from ``needs_sphinx = '7.2.6'`` in ``Doc/conf.py``. - -alabaster==0.7.16 -babel==2.16.0 -certifi==2024.12.14 -charset-normalizer==3.4.0 -docutils==0.20.1 -idna==3.10 -imagesize==1.4.1 -Jinja2==3.1.5 -MarkupSafe==3.0.2 -packaging==24.2 -Pygments==2.18.0 -requests==2.32.3 -snowballstemmer==2.2.0 -Sphinx==7.2.6 -sphinxcontrib-applehelp==2.0.0 -sphinxcontrib-devhelp==2.0.0 -sphinxcontrib-htmlhelp==2.1.0 -sphinxcontrib-jsmath==1.0.1 -sphinxcontrib-qthelp==2.0.0 -sphinxcontrib-serializinghtml==2.0.0 -urllib3==2.3.0 diff --git a/Doc/requirements.txt b/Doc/requirements.txt index 5105786ccf283c..32ff8f74d05bb6 100644 --- a/Doc/requirements.txt +++ b/Doc/requirements.txt @@ -3,9 +3,10 @@ # Note that when updating this file, you will likely also have to update # the Doc/constraints.txt file. -# Sphinx version is pinned so that new versions that introduce new warnings +# The Sphinx version is pinned so that new versions that introduce new warnings # won't suddenly cause build failures. Updating the version is fine as long # as no warnings are raised by doing so. +# Keep this version in sync with ``Doc/conf.py``. sphinx~=8.1.0 blurb diff --git a/Doc/tools/extensions/c_annotations.py b/Doc/tools/extensions/c_annotations.py index 50065d34a2c27a..089614a1f6c421 100644 --- a/Doc/tools/extensions/c_annotations.py +++ b/Doc/tools/extensions/c_annotations.py @@ -16,7 +16,6 @@ from pathlib import Path from typing import TYPE_CHECKING -import sphinx from docutils import nodes from docutils.statemachine import StringList from sphinx import addnodes @@ -285,16 +284,6 @@ def setup(app: Sphinx) -> ExtensionMetadata: app.connect("builder-inited", init_annotations) app.connect("doctree-read", add_annotations) - if sphinx.version_info[:2] < (7, 2): - from docutils.parsers.rst import directives - from sphinx.domains.c import CObject - - # monkey-patch C object... - CObject.option_spec |= { - "no-index-entry": directives.flag, - "no-contents-entry": directives.flag, - } - return { "version": "1.0", "parallel_read_safe": True, diff --git a/Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst b/Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst new file mode 100644 index 00000000000000..bf6253eed2eb90 --- /dev/null +++ b/Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst @@ -0,0 +1,2 @@ +Require Sphinx 8.1.3 or later to build the Python documentation. Patch by +Adam Turner.

1 0

GH-125722: Increase minimum supported Sphinx to 8.1.3 (#128922)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/d46b577ec026c2e700a9f920f81cfbf698… commit: d46b577ec026c2e700a9f920f81cfbf698e53eb6 branch: main author: Adam Turner <9087854+AA-Turner(a)users.noreply.github.com> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:26:24Z summary: GH-125722: Increase minimum supported Sphinx to 8.1.3 (#128922) files: A Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst D Doc/requirements-oldest-sphinx.txt M .github/workflows/reusable-docs.yml M Doc/conf.py M Doc/constraints.txt M Doc/requirements.txt M Doc/tools/extensions/c_annotations.py diff --git a/.github/workflows/reusable-docs.yml b/.github/workflows/reusable-docs.yml index 88da55bf08b8fe..84675fa62e1516 100644 --- a/.github/workflows/reusable-docs.yml +++ b/.github/workflows/reusable-docs.yml @@ -76,26 +76,6 @@ jobs: --fail-if-improved \ --fail-if-new-news-nit - # This build doesn't use problem matchers or check annotations - build_doc_oldest_supported_sphinx: - name: 'Docs (Oldest Sphinx)' - runs-on: ubuntu-latest - timeout-minutes: 60 - steps: - - uses: actions/checkout@v4 - with: - persist-credentials: false - - name: 'Set up Python' - uses: actions/setup-python@v5 - with: - python-version: '3.13' # known to work with Sphinx 7.2.6 - cache: 'pip' - cache-dependency-path: 'Doc/requirements-oldest-sphinx.txt' - - name: 'Install build dependencies' - run: make -C Doc/ venv REQUIREMENTS="requirements-oldest-sphinx.txt" - - name: 'Build HTML documentation' - run: make -C Doc/ SPHINXOPTS="-q" SPHINXERRORHANDLING="-W --keep-going" html - # Run "doctest" on HEAD as new syntax doesn't exist in the latest stable release doctest: name: 'Doctest' diff --git a/Doc/conf.py b/Doc/conf.py index ae08c7fa288080..b4a924b7bf0857 100644 --- a/Doc/conf.py +++ b/Doc/conf.py @@ -9,9 +9,6 @@ import importlib import os import sys -import time - -import sphinx # Make our custom extensions available to Sphinx sys.path.append(os.path.abspath('tools/extensions')) @@ -97,7 +94,8 @@ highlight_language = 'python3' # Minimum version of sphinx required -needs_sphinx = '7.2.6' +# Keep this version in sync with ``Doc/requirements.txt``. +needs_sphinx = '8.1.3' # Create table of contents entries for domain objects (e.g. functions, classes, # attributes, etc.). Default is True. @@ -376,13 +374,7 @@ # This 'Last updated on:' timestamp is inserted at the bottom of every page. html_last_updated_fmt = '%b %d, %Y (%H:%M UTC)' -if sphinx.version_info[:2] >= (8, 1): - html_last_updated_use_utc = True -else: - html_time = int(os.environ.get('SOURCE_DATE_EPOCH', time.time())) - html_last_updated_fmt = time.strftime( - html_last_updated_fmt, time.gmtime(html_time) - ) +html_last_updated_use_utc = True # Path to find HTML templates to override theme templates_path = ['tools/templates'] @@ -619,16 +611,6 @@ } extlinks_detect_hardcoded_links = True -if sphinx.version_info[:2] < (8, 1): - # Sphinx 8.1 has in-built CVE and CWE roles. - extlinks |= { - "cve": ( - "https://www.cve.org/CVERecord?id=CVE-%s", - "CVE-%s", - ), - "cwe": ("https://cwe.mitre.org/data/definitions/%s.html", "CWE-%s"), - } - # Options for c_annotations extension # ----------------------------------- diff --git a/Doc/constraints.txt b/Doc/constraints.txt index 26ac1862dbac0b..29cd4be1d3c8db 100644 --- a/Doc/constraints.txt +++ b/Doc/constraints.txt @@ -13,14 +13,12 @@ packaging<25 Pygments<3 requests<3 snowballstemmer<3 -# keep lower-bounds until Sphinx 8.1 is released -# https://github.com/sphinx-doc/sphinx/pull/12756 -sphinxcontrib-applehelp>=1.0.7,<3 -sphinxcontrib-devhelp>=1.0.6,<3 -sphinxcontrib-htmlhelp>=2.0.6,<3 -sphinxcontrib-jsmath>=1.0.1,<2 -sphinxcontrib-qthelp>=1.0.6,<3 -sphinxcontrib-serializinghtml>=1.1.9,<3 +sphinxcontrib-applehelp<3 +sphinxcontrib-devhelp<3 +sphinxcontrib-htmlhelp<3 +sphinxcontrib-jsmath<2 +sphinxcontrib-qthelp<3 +sphinxcontrib-serializinghtml<3 # Direct dependencies of Jinja2 (Jinja is a dependency of Sphinx, see above) MarkupSafe<3 diff --git a/Doc/requirements-oldest-sphinx.txt b/Doc/requirements-oldest-sphinx.txt deleted file mode 100644 index c8027a05706c21..00000000000000 --- a/Doc/requirements-oldest-sphinx.txt +++ /dev/null @@ -1,35 +0,0 @@ -# Requirements to build the Python documentation, for the oldest supported -# Sphinx version. -# -# We pin Sphinx and all of its dependencies to ensure a consistent environment. - -blurb -python-docs-theme>=2022.1 - -# Generated from: -# pip install "Sphinx~=7.2.6" -# pip freeze -# -# Sphinx 7.2.6 comes from ``needs_sphinx = '7.2.6'`` in ``Doc/conf.py``. - -alabaster==0.7.16 -babel==2.16.0 -certifi==2024.12.14 -charset-normalizer==3.4.0 -docutils==0.20.1 -idna==3.10 -imagesize==1.4.1 -Jinja2==3.1.5 -MarkupSafe==3.0.2 -packaging==24.2 -Pygments==2.18.0 -requests==2.32.3 -snowballstemmer==2.2.0 -Sphinx==7.2.6 -sphinxcontrib-applehelp==2.0.0 -sphinxcontrib-devhelp==2.0.0 -sphinxcontrib-htmlhelp==2.1.0 -sphinxcontrib-jsmath==1.0.1 -sphinxcontrib-qthelp==2.0.0 -sphinxcontrib-serializinghtml==2.0.0 -urllib3==2.3.0 diff --git a/Doc/requirements.txt b/Doc/requirements.txt index 5105786ccf283c..32ff8f74d05bb6 100644 --- a/Doc/requirements.txt +++ b/Doc/requirements.txt @@ -3,9 +3,10 @@ # Note that when updating this file, you will likely also have to update # the Doc/constraints.txt file. -# Sphinx version is pinned so that new versions that introduce new warnings +# The Sphinx version is pinned so that new versions that introduce new warnings # won't suddenly cause build failures. Updating the version is fine as long # as no warnings are raised by doing so. +# Keep this version in sync with ``Doc/conf.py``. sphinx~=8.1.0 blurb diff --git a/Doc/tools/extensions/c_annotations.py b/Doc/tools/extensions/c_annotations.py index 50065d34a2c27a..089614a1f6c421 100644 --- a/Doc/tools/extensions/c_annotations.py +++ b/Doc/tools/extensions/c_annotations.py @@ -16,7 +16,6 @@ from pathlib import Path from typing import TYPE_CHECKING -import sphinx from docutils import nodes from docutils.statemachine import StringList from sphinx import addnodes @@ -285,16 +284,6 @@ def setup(app: Sphinx) -> ExtensionMetadata: app.connect("builder-inited", init_annotations) app.connect("doctree-read", add_annotations) - if sphinx.version_info[:2] < (7, 2): - from docutils.parsers.rst import directives - from sphinx.domains.c import CObject - - # monkey-patch C object... - CObject.option_spec |= { - "no-index-entry": directives.flag, - "no-contents-entry": directives.flag, - } - return { "version": "1.0", "parallel_read_safe": True, diff --git a/Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst b/Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst new file mode 100644 index 00000000000000..bf6253eed2eb90 --- /dev/null +++ b/Misc/NEWS.d/next/Documentation/2025-01-16-18-59-11.gh-issue-125722.eHHRga.rst @@ -0,0 +1,2 @@ +Require Sphinx 8.1.3 or later to build the Python documentation. Patch by +Adam Turner.

1 0

[3.12] gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (GH-129021) (#129036)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/22c1d895fc73c3142795d2b5e62579e8a5… commit: 22c1d895fc73c3142795d2b5e62579e8a5225d1e branch: 3.12 author: Miss Islington (bot) <31488909+miss-islington(a)users.noreply.github.com> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:12:39Z summary: [3.12] gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (GH-129021) (#129036) gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (GH-129021) (cherry picked from commit bca35f0e782848ae2acdcfbfb000cd4a2af49fbd) Co-authored-by: Tomas R <tomas.roun8(a)gmail.com> files: M Doc/library/tokenize.rst diff --git a/Doc/library/tokenize.rst b/Doc/library/tokenize.rst index f719319a302a23..b80917eae66f8b 100644 --- a/Doc/library/tokenize.rst +++ b/Doc/library/tokenize.rst @@ -91,11 +91,10 @@ write back the modified script. sequences with at least two elements, the token type and the token string. Any additional sequence elements are ignored. - The reconstructed script is returned as a single string. The result is - guaranteed to tokenize back to match the input so that the conversion is - lossless and round-trips are assured. The guarantee applies only to the - token type and token string as the spacing between tokens (column - positions) may change. + The result is guaranteed to tokenize back to match the input so that the + conversion is lossless and round-trips are assured. The guarantee applies + only to the token type and token string as the spacing between tokens + (column positions) may change. It returns bytes, encoded using the :data:`~token.ENCODING` token, which is the first token sequence output by :func:`.tokenize`. If there is no

1 0

[3.13] gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (GH-129021) (#129035)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/080d17e9453d1a4fc77025eb14a5dcf49b… commit: 080d17e9453d1a4fc77025eb14a5dcf49b4f379c branch: 3.13 author: Miss Islington (bot) <31488909+miss-islington(a)users.noreply.github.com> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:11:27Z summary: [3.13] gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (GH-129021) (#129035) gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (GH-129021) (cherry picked from commit bca35f0e782848ae2acdcfbfb000cd4a2af49fbd) Co-authored-by: Tomas R <tomas.roun8(a)gmail.com> files: M Doc/library/tokenize.rst diff --git a/Doc/library/tokenize.rst b/Doc/library/tokenize.rst index f719319a302a23..b80917eae66f8b 100644 --- a/Doc/library/tokenize.rst +++ b/Doc/library/tokenize.rst @@ -91,11 +91,10 @@ write back the modified script. sequences with at least two elements, the token type and the token string. Any additional sequence elements are ignored. - The reconstructed script is returned as a single string. The result is - guaranteed to tokenize back to match the input so that the conversion is - lossless and round-trips are assured. The guarantee applies only to the - token type and token string as the spacing between tokens (column - positions) may change. + The result is guaranteed to tokenize back to match the input so that the + conversion is lossless and round-trips are assured. The guarantee applies + only to the token type and token string as the spacing between tokens + (column positions) may change. It returns bytes, encoded using the :data:`~token.ENCODING` token, which is the first token sequence output by :func:`.tokenize`. If there is no

1 0

gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (#129021)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/bca35f0e782848ae2acdcfbfb000cd4a2a… commit: bca35f0e782848ae2acdcfbfb000cd4a2af49fbd branch: main author: Tomas R. <tomas.roun8(a)gmail.com> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:05:22Z summary: gh-129020: Remove ambiguous sentence from `tokenize.untokenize` docs (#129021) files: M Doc/library/tokenize.rst diff --git a/Doc/library/tokenize.rst b/Doc/library/tokenize.rst index f719319a302a23..b80917eae66f8b 100644 --- a/Doc/library/tokenize.rst +++ b/Doc/library/tokenize.rst @@ -91,11 +91,10 @@ write back the modified script. sequences with at least two elements, the token type and the token string. Any additional sequence elements are ignored. - The reconstructed script is returned as a single string. The result is - guaranteed to tokenize back to match the input so that the conversion is - lossless and round-trips are assured. The guarantee applies only to the - token type and token string as the spacing between tokens (column - positions) may change. + The result is guaranteed to tokenize back to match the input so that the + conversion is lossless and round-trips are assured. The guarantee applies + only to the token type and token string as the spacing between tokens + (column positions) may change. It returns bytes, encoded using the :data:`~token.ENCODING` token, which is the first token sequence output by :func:`.tokenize`. If there is no

1 0

gh-118761: Redudce the import time of ``optparse`` (#128899)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/3b6a27c5607d2b199f127c2a5ef5316bbc… commit: 3b6a27c5607d2b199f127c2a5ef5316bbc30ae42 branch: main author: Eli Schwartz <eschwartz(a)gentoo.org> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:03:19Z summary: gh-118761: Redudce the import time of ``optparse`` (#128899) The same change was made, and for the same reason, by ``argparse`` back in 2017. The ``textwrap`` module is only used when printing help text, so most invocations will never need it imported. Co-authored-by: Adam Turner <9087854+AA-Turner(a)users.noreply.github.com> files: A Misc/NEWS.d/next/Library/2025-01-15-18-54-48.gh-issue-118761.G1dv6E.rst M Lib/optparse.py diff --git a/Lib/optparse.py b/Lib/optparse.py index cbe3451ced8bc3..38cf16d21efffa 100644 --- a/Lib/optparse.py +++ b/Lib/optparse.py @@ -74,7 +74,6 @@ """ import sys, os -import textwrap from gettext import gettext as _, ngettext @@ -252,6 +251,7 @@ def _format_text(self, text): Format a paragraph of free-form text for inclusion in the help output at the current indentation level. """ + import textwrap text_width = max(self.width - self.current_indent, 11) indent = " "*self.current_indent return textwrap.fill(text, @@ -308,6 +308,7 @@ def format_option(self, option): indent_first = 0 result.append(opts) if option.help: + import textwrap help_text = self.expand_default(option) help_lines = textwrap.wrap(help_text, self.help_width) result.append("%*s%s\n" % (indent_first, "", help_lines[0])) diff --git a/Misc/NEWS.d/next/Library/2025-01-15-18-54-48.gh-issue-118761.G1dv6E.rst b/Misc/NEWS.d/next/Library/2025-01-15-18-54-48.gh-issue-118761.G1dv6E.rst new file mode 100644 index 00000000000000..4144ef8f40e6dd --- /dev/null +++ b/Misc/NEWS.d/next/Library/2025-01-15-18-54-48.gh-issue-118761.G1dv6E.rst @@ -0,0 +1,2 @@ +Reduce the import time of :mod:`optparse` when no help text is printed. +Patch by Eli Schwartz.

1 0

gh-118761: Improve the import time of ``gettext`` (#128898)
by AA-Turner Jan. 20, 2025

Jan. 20, 2025

https://github.com/python/cpython/commit/c9c9fcb8fcc3ef43e1d8bd71ae0ed3d423… commit: c9c9fcb8fcc3ef43e1d8bd71ae0ed3d4231a6013 branch: main author: Eli Schwartz <eschwartz(a)gentoo.org> committer: AA-Turner <9087854+AA-Turner(a)users.noreply.github.com> date: 2025-01-20T00:01:20Z summary: gh-118761: Improve the import time of ``gettext`` (#128898) ``gettext`` is often imported in programs that may not end up translating anything. In fact, the ``struct`` module already has a delayed import when parsing ``GNUTranslations`` to speed up the no ``.mo`` files case. The re module is also used in the same situation, but behind a function chain only called by ``GNUTranslations``. Cache the compiled regex globally the first time it is used. The finditer function is converted to a method call on the compiled object which is slightly more efficient, and necessary for the delayed re import. files: A Misc/NEWS.d/next/Library/2025-01-15-19-16-50.gh-issue-118761.cbW2ZL.rst M Lib/gettext.py diff --git a/Lib/gettext.py b/Lib/gettext.py index a0d81cf846a05c..4c1f9427459b14 100644 --- a/Lib/gettext.py +++ b/Lib/gettext.py @@ -48,7 +48,6 @@ import operator import os -import re import sys @@ -70,22 +69,26 @@ # https://www.gnu.org/software/gettext/manual/gettext.html#Plural-forms # http://git.savannah.gnu.org/cgit/gettext.git/tree/gettext-runtime/intl/plur… -_token_pattern = re.compile(r""" - (?P<WHITESPACES>[ \t]+) | # spaces and horizontal tabs - (?P<NUMBER>[0-9]+\b) | # decimal integer - (?P<NAME>n\b) | # only n is allowed - (?P<PARENTHESIS>[()]) | - (?P<OPERATOR>[-*/%+?:]|[><!]=?|==|&&|\|\|) | # !, *, /, %, +, -, <, >, - # <=, >=, ==, !=, &&, ||, - # ? : - # unary and bitwise ops - # not allowed - (?P<INVALID>\w+|.) # invalid token - """, re.VERBOSE|re.DOTALL) - +_token_pattern = None def _tokenize(plural): - for mo in re.finditer(_token_pattern, plural): + global _token_pattern + if _token_pattern is None: + import re + _token_pattern = re.compile(r""" + (?P<WHITESPACES>[ \t]+) | # spaces and horizontal tabs + (?P<NUMBER>[0-9]+\b) | # decimal integer + (?P<NAME>n\b) | # only n is allowed + (?P<PARENTHESIS>[()]) | + (?P<OPERATOR>[-*/%+?:]|[><!]=?|==|&&|\|\|) | # !, *, /, %, +, -, <, >, + # <=, >=, ==, !=, &&, ||, + # ? : + # unary and bitwise ops + # not allowed + (?P<INVALID>\w+|.) # invalid token + """, re.VERBOSE|re.DOTALL) + + for mo in _token_pattern.finditer(plural): kind = mo.lastgroup if kind == 'WHITESPACES': continue diff --git a/Misc/NEWS.d/next/Library/2025-01-15-19-16-50.gh-issue-118761.cbW2ZL.rst b/Misc/NEWS.d/next/Library/2025-01-15-19-16-50.gh-issue-118761.cbW2ZL.rst new file mode 100644 index 00000000000000..0eef8777512dd8 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2025-01-15-19-16-50.gh-issue-118761.cbW2ZL.rst @@ -0,0 +1,3 @@ +Reduce import time of :mod:`gettext` by up to ten times, by importing +:mod:`re` on demand. In particular, ``re`` is no longer implicitly +exposed as ``gettext.re``. Patch by Eli Schwartz.

1 0

Complete doc of pending C API removals in Python 3.15 (#129032)
by vstinner Jan. 19, 2025

Jan. 19, 2025

https://github.com/python/cpython/commit/bbeb219354764aef85e660be6570f0f329… commit: bbeb219354764aef85e660be6570f0f329e7227e branch: main author: Victor Stinner <vstinner(a)python.org> committer: vstinner <vstinner(a)python.org> date: 2025-01-19T22:47:05+01:00 summary: Complete doc of pending C API removals in Python 3.15 (#129032) files: M Doc/c-api/init.rst M Doc/deprecations/c-api-pending-removal-in-3.15.rst diff --git a/Doc/c-api/init.rst b/Doc/c-api/init.rst index 97996a6f69dd22..dc44f3eaf87765 100644 --- a/Doc/c-api/init.rst +++ b/Doc/c-api/init.rst @@ -109,7 +109,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-b` option. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_DebugFlag @@ -123,7 +123,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-d` option and the :envvar:`PYTHONDEBUG` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_DontWriteBytecodeFlag @@ -137,7 +137,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-B` option and the :envvar:`PYTHONDONTWRITEBYTECODE` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_FrozenFlag @@ -150,7 +150,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Private flag used by ``_freeze_module`` and ``frozenmain`` programs. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_HashRandomizationFlag @@ -165,7 +165,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. If the flag is non-zero, read the :envvar:`PYTHONHASHSEED` environment variable to initialize the secret hash seed. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_IgnoreEnvironmentFlag @@ -178,7 +178,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-E` and :option:`-I` options. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_InspectFlag @@ -193,7 +193,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-i` option and the :envvar:`PYTHONINSPECT` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_InteractiveFlag @@ -218,7 +218,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. .. versionadded:: 3.4 - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_LegacyWindowsFSEncodingFlag @@ -237,7 +237,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. .. availability:: Windows. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_LegacyWindowsStdioFlag @@ -255,7 +255,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. .. availability:: Windows. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_NoSiteFlag @@ -270,7 +270,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-S` option. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_NoUserSiteDirectory @@ -284,7 +284,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-s` and :option:`-I` options, and the :envvar:`PYTHONNOUSERSITE` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_OptimizeFlag @@ -295,7 +295,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-O` option and the :envvar:`PYTHONOPTIMIZE` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_QuietFlag @@ -309,7 +309,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. .. versionadded:: 3.2 - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_UnbufferedStdioFlag @@ -322,7 +322,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-u` option and the :envvar:`PYTHONUNBUFFERED` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 .. c:var:: int Py_VerboseFlag @@ -338,7 +338,7 @@ to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. Set by the :option:`-v` option and the :envvar:`PYTHONVERBOSE` environment variable. - .. deprecated-removed:: 3.12 3.14 + .. deprecated-removed:: 3.12 3.15 Initializing and finalizing the interpreter @@ -606,7 +606,7 @@ Process-wide parameters Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a :c:expr:`wchar_*` string. - .. deprecated:: 3.11 + .. deprecated-removed:: 3.11 3.15 .. c:function:: wchar_t* Py_GetProgramName() @@ -868,7 +868,7 @@ Process-wide parameters .. XXX impl. doesn't seem consistent in allowing ``0``/``NULL`` for the params; check w/ Guido. - .. deprecated:: 3.11 + .. deprecated-removed:: 3.11 3.15 .. c:function:: void PySys_SetArgv(int argc, wchar_t **argv) @@ -889,7 +889,7 @@ Process-wide parameters .. versionchanged:: 3.4 The *updatepath* value depends on :option:`-I`. - .. deprecated:: 3.11 + .. deprecated-removed:: 3.11 3.15 .. c:function:: void Py_SetPythonHome(const wchar_t *home) @@ -910,7 +910,7 @@ Process-wide parameters Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a :c:expr:`wchar_*` string. - .. deprecated:: 3.11 + .. deprecated-removed:: 3.11 3.15 .. c:function:: wchar_t* Py_GetPythonHome() diff --git a/Doc/deprecations/c-api-pending-removal-in-3.15.rst b/Doc/deprecations/c-api-pending-removal-in-3.15.rst index ba908f81b7f800..ac31b3cc8cd451 100644 --- a/Doc/deprecations/c-api-pending-removal-in-3.15.rst +++ b/Doc/deprecations/c-api-pending-removal-in-3.15.rst @@ -5,7 +5,9 @@ Pending removal in Python 3.15 * The :c:func:`PyImport_ImportModuleNoBlock`: Use :c:func:`PyImport_ImportModule` instead. * :c:func:`PyWeakref_GetObject` and :c:func:`PyWeakref_GET_OBJECT`: - Use :c:func:`PyWeakref_GetRef` instead. + Use :c:func:`PyWeakref_GetRef` instead. The `pythoncapi-compat project + <https://github.com/python/pythoncapi-compat/>`__ can be used to get + :c:func:`PyWeakref_GetRef` on Python 3.12 and older. * :c:type:`Py_UNICODE` type and the :c:macro:`!Py_UNICODE_WIDE` macro: Use :c:type:`wchar_t` instead. * Python initialization functions: @@ -23,9 +25,11 @@ Pending removal in Python 3.15 * :c:func:`Py_GetProgramName`: Get :data:`sys.executable` instead. * :c:func:`Py_GetPythonHome`: - Get :c:member:`PyConfig.home` + Get :c:func:`PyConfig_Get("home") <PyConfig_Get>` or the :envvar:`PYTHONHOME` environment variable instead. + See also the :c:func:`PyConfig_Get` function. + * Functions to configure Python's initialization, deprecated in Python 3.11: * :c:func:`!PySys_SetArgvEx()`:

1 0

[3.12] gh-80222: Fix email address header folding with long quoted-string (GH-122753) (#129008)
by bitdancer Jan. 19, 2025

Jan. 19, 2025

https://github.com/python/cpython/commit/b8170e58849a7728ebc9b58e222aa5bd05… commit: b8170e58849a7728ebc9b58e222aa5bd051cf7c4 branch: 3.12 author: Miss Islington (bot) <31488909+miss-islington(a)users.noreply.github.com> committer: bitdancer <rdmurray(a)bitdance.com> date: 2025-01-19T16:07:39-05:00 summary: [3.12] gh-80222: Fix email address header folding with long quoted-string (GH-122753) (#129008) gh-80222: Fix email address header folding with long quoted-string (GH-122753) Email generators using email.policy.default could incorrectly omit the quote ('"') characters from a quoted-string during header refolding, leading to invalid address headers and enabling header spoofing. This change restores the quote characters on a bare-quoted-string as the header is refolded, and escapes backslash and quote chars in the string. (cherry picked from commit 5aaf41685834901e4ed0a40f4c055b92991a0bb5) Co-authored-by: Mike Edmunds <medmunds(a)gmail.com> files: A Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst M Lib/email/_header_value_parser.py M Lib/test/test_email/test__header_value_parser.py diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index ec2215a5e5f33c..3d845c09d415f6 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -95,8 +95,16 @@ NLSET = {'\n', '\r'} SPECIALSNL = SPECIALS | NLSET + +def make_quoted_pairs(value): + """Escape dquote and backslash for use within a quoted-string.""" + return str(value).replace('\\', '\\\\').replace('"', '\\"') + + def quote_string(value): - return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"' + escaped = make_quoted_pairs(value) + return f'"{escaped}"' + # Match a RFC 2047 word, looks like =?utf-8?q?someword?= rfc2047_matcher = re.compile(r''' @@ -2905,6 +2913,15 @@ def _refold_parse_tree(parse_tree, *, policy): if not hasattr(part, 'encode'): # It's not a terminal, try folding the subparts. newparts = list(part) + if part.token_type == 'bare-quoted-string': + # To fold a quoted string we need to create a list of terminal + # tokens that will render the leading and trailing quotes + # and use quoted pairs in the value as appropriate. + newparts = ( + [ValueTerminal('"', 'ptext')] + + [ValueTerminal(make_quoted_pairs(p), 'ptext') + for p in newparts] + + [ValueTerminal('"', 'ptext')]) if not part.as_ew_allowed: wrap_as_ew_blocked += 1 newparts.append(end_ew_not_allowed) diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 5413319a414a62..efd1695711d7c1 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -3082,13 +3082,40 @@ def test_address_list_with_list_separator_after_fold(self): self._test(parser.get_address_list(to)[0], f'{a},\n =?utf-8?q?H=C3=BCbsch?= Kaktus <beautiful(a)example.com>\n') - a = '.' * 79 + a = '.' * 79 # ('.' is a special, so must be in quoted-string.) to = f'"{a}" <xyz(a)example.com>, "Hübsch Kaktus" <beautiful(a)example.com>' self._test(parser.get_address_list(to)[0], - f'{a}\n' + f'"{a}"\n' ' <xyz(a)example.com>, =?utf-8?q?H=C3=BCbsch?= Kaktus ' '<beautiful(a)example.com>\n') + def test_address_list_with_specials_in_long_quoted_string(self): + # Regression for gh-80222. + policy = self.policy.clone(max_line_length=40) + cases = [ + # (to, folded) + ('"Exfiltrator <spy(a)example.org> (unclosed comment?" <to(a)example.com>', + '"Exfiltrator <spy(a)example.org> (unclosed\n' + ' comment?" <to(a)example.com>\n'), + ('"Escaped \\" chars \\\\ in quoted-string stay escaped" <to(a)example.com>', + '"Escaped \\" chars \\\\ in quoted-string\n' + ' stay escaped" <to(a)example.com>\n'), + ('This long display name does not need quotes <to(a)example.com>', + 'This long display name does not need\n' + ' quotes <to(a)example.com>\n'), + ('"Quotes are not required but are retained here" <to(a)example.com>', + '"Quotes are not required but are\n' + ' retained here" <to(a)example.com>\n'), + ('"A quoted-string, it can be a valid local-part"@example.com', + '"A quoted-string, it can be a valid\n' + ' local-part"@example.com\n'), + ('"local-part-with-specials(a)but-no-fws.cannot-fold"@example.com', + '"local-part-with-specials(a)but-no-fws.cannot-fold"@example.com\n'), + ] + for (to, folded) in cases: + with self.subTest(to=to): + self._test(parser.get_address_list(to)[0], folded, policy=policy) + # XXX Need tests with comments on various sides of a unicode token, # and with unicode tokens in the comments. Spaces inside the quotes # currently don't do the right thing. diff --git a/Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst b/Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst new file mode 100644 index 00000000000000..0f0661d0b1cf4a --- /dev/null +++ b/Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst @@ -0,0 +1,6 @@ +Fix bug in the folding of quoted strings when flattening an email message using +a modern email policy. Previously when a quoted string was folded so that +it spanned more than one line, the surrounding quotes and internal escapes +would be omitted. This could theoretically be used to spoof header lines +using a carefully constructed quoted string if the resulting rendered email +was transmitted or re-parsed.

1 0

[3.13] gh-80222: Fix email address header folding with long quoted-string (GH-122753) (#129007)
by bitdancer Jan. 19, 2025

Jan. 19, 2025

https://github.com/python/cpython/commit/21200895478b8076fc0bda6ee2c26f0d87… commit: 21200895478b8076fc0bda6ee2c26f0d87c9404b branch: 3.13 author: Miss Islington (bot) <31488909+miss-islington(a)users.noreply.github.com> committer: bitdancer <rdmurray(a)bitdance.com> date: 2025-01-19T16:06:28-05:00 summary: [3.13] gh-80222: Fix email address header folding with long quoted-string (GH-122753) (#129007) gh-80222: Fix email address header folding with long quoted-string (GH-122753) Email generators using email.policy.default could incorrectly omit the quote ('"') characters from a quoted-string during header refolding, leading to invalid address headers and enabling header spoofing. This change restores the quote characters on a bare-quoted-string as the header is refolded, and escapes backslash and quote chars in the string. (cherry picked from commit 5aaf41685834901e4ed0a40f4c055b92991a0bb5) Co-authored-by: Mike Edmunds <medmunds(a)gmail.com> files: A Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst M Lib/email/_header_value_parser.py M Lib/test/test_email/test__header_value_parser.py diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index ec2215a5e5f33c..3d845c09d415f6 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -95,8 +95,16 @@ NLSET = {'\n', '\r'} SPECIALSNL = SPECIALS | NLSET + +def make_quoted_pairs(value): + """Escape dquote and backslash for use within a quoted-string.""" + return str(value).replace('\\', '\\\\').replace('"', '\\"') + + def quote_string(value): - return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"' + escaped = make_quoted_pairs(value) + return f'"{escaped}"' + # Match a RFC 2047 word, looks like =?utf-8?q?someword?= rfc2047_matcher = re.compile(r''' @@ -2905,6 +2913,15 @@ def _refold_parse_tree(parse_tree, *, policy): if not hasattr(part, 'encode'): # It's not a terminal, try folding the subparts. newparts = list(part) + if part.token_type == 'bare-quoted-string': + # To fold a quoted string we need to create a list of terminal + # tokens that will render the leading and trailing quotes + # and use quoted pairs in the value as appropriate. + newparts = ( + [ValueTerminal('"', 'ptext')] + + [ValueTerminal(make_quoted_pairs(p), 'ptext') + for p in newparts] + + [ValueTerminal('"', 'ptext')]) if not part.as_ew_allowed: wrap_as_ew_blocked += 1 newparts.append(end_ew_not_allowed) diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 5413319a414a62..efd1695711d7c1 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -3082,13 +3082,40 @@ def test_address_list_with_list_separator_after_fold(self): self._test(parser.get_address_list(to)[0], f'{a},\n =?utf-8?q?H=C3=BCbsch?= Kaktus <beautiful(a)example.com>\n') - a = '.' * 79 + a = '.' * 79 # ('.' is a special, so must be in quoted-string.) to = f'"{a}" <xyz(a)example.com>, "Hübsch Kaktus" <beautiful(a)example.com>' self._test(parser.get_address_list(to)[0], - f'{a}\n' + f'"{a}"\n' ' <xyz(a)example.com>, =?utf-8?q?H=C3=BCbsch?= Kaktus ' '<beautiful(a)example.com>\n') + def test_address_list_with_specials_in_long_quoted_string(self): + # Regression for gh-80222. + policy = self.policy.clone(max_line_length=40) + cases = [ + # (to, folded) + ('"Exfiltrator <spy(a)example.org> (unclosed comment?" <to(a)example.com>', + '"Exfiltrator <spy(a)example.org> (unclosed\n' + ' comment?" <to(a)example.com>\n'), + ('"Escaped \\" chars \\\\ in quoted-string stay escaped" <to(a)example.com>', + '"Escaped \\" chars \\\\ in quoted-string\n' + ' stay escaped" <to(a)example.com>\n'), + ('This long display name does not need quotes <to(a)example.com>', + 'This long display name does not need\n' + ' quotes <to(a)example.com>\n'), + ('"Quotes are not required but are retained here" <to(a)example.com>', + '"Quotes are not required but are\n' + ' retained here" <to(a)example.com>\n'), + ('"A quoted-string, it can be a valid local-part"@example.com', + '"A quoted-string, it can be a valid\n' + ' local-part"@example.com\n'), + ('"local-part-with-specials(a)but-no-fws.cannot-fold"@example.com', + '"local-part-with-specials(a)but-no-fws.cannot-fold"@example.com\n'), + ] + for (to, folded) in cases: + with self.subTest(to=to): + self._test(parser.get_address_list(to)[0], folded, policy=policy) + # XXX Need tests with comments on various sides of a unicode token, # and with unicode tokens in the comments. Spaces inside the quotes # currently don't do the right thing. diff --git a/Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst b/Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst new file mode 100644 index 00000000000000..0f0661d0b1cf4a --- /dev/null +++ b/Misc/NEWS.d/next/Security/2024-08-06-11-43-08.gh-issue-80222.wfR4BU.rst @@ -0,0 +1,6 @@ +Fix bug in the folding of quoted strings when flattening an email message using +a modern email policy. Previously when a quoted string was folded so that +it spanned more than one line, the surrounding quotes and internal escapes +would be omitted. This could theoretically be used to spoof header lines +using a carefully constructed quoted string if the resulting rendered email +was transmitted or re-parsed.

1 0