Merge main: adopt icu_properties approach, drop unic-ucd-category fallback

* Update pstats from v3.14.5

* Update profile from v3.14.5

* Update tracemalloc from v3.14.5

* Update test_multibytecodec from v3.14.5

* Mark failing tests in test_pstats

* Mark failing test in test_profile

* Mark failing tests in test_cprofile

* Mark failing tests in test_tracemalloc

* Mark failing tests in test_multibytecodec

* Added comment marker to test_pstats.py

---------

Co-authored-by: CPython Developers <>

.cspell.dict/cpython.txt

@@ -4,6 +4,8 @@ argdefs
 argtypes
 asdl
 asname
+atopen
+atext
 attro
 augassign
 badcert
@@ -30,9 +32,12 @@ cellvar
 cellvars
 ceval
 cfield
+cfws
+CFWS
 CLASSDEREF
 classdict
 cmpop
+CNOTAB
 codedepth
 CODEUNIT
 CONIN
@@ -47,13 +52,16 @@ datastack
 defaultdict
 denom
 deopt
+deopts
 dictbytype
 DICTFLAG
 dictoffset
 distpoint
 dynload
 elts
+eooh
 eofs
+EOOH
 evalloop
 excepthandler
 exceptiontable
@@ -62,6 +70,7 @@ fastlocals
 fblock
 fblocks
 fdescr
+fdst
 ffi_argtypes
 fielddesc
 fieldlist
@@ -75,6 +84,7 @@ freelist
 freevar
 freevars
 fromlist
+fsrc
 getdict
 getfunc
 getiter
@@ -89,28 +99,39 @@ HASUNION
 heaptype
 hexdigit
 HIGHRES
+ialloc
 IFUNC
 IMMUTABLETYPE
 INCREF
 inlinedepth
 inplace
+inpos
+ioffset
+isbytecode
+ishidden
 ismine
 ISPOINTER
+isoctal
 iteminfo
 Itertool
+iused
 keeped
 kwnames
 kwonlyarg
 kwonlyargs
+kwonlydefaults
 lasti
 libffi
 linearise
+lineful
 lineiterator
 linetable
+LNOTAB
 loadfast
 localsplus
 localspluskinds
 Lshift
+lslpp
 lsprof
 MAXBLOCKS
 maxdepth
@@ -120,16 +141,23 @@ mult
 multibytecodec
 nameobj
 nameop
+nargsf
+nblocks
 ncells
+ncellsused
+ncellvars
 nconsts
 newargs
 newfree
 NEWLOCALS
 newsemlockobject
+nextop
 nfrees
 nkwargs
 nkwelts
 nlocalsplus
+nointerrupt
+noffsets
 Nondescriptor
 noninteger
 nops
@@ -137,6 +165,7 @@ noraise
 nseen
 NSIGNALS
 numer
+nvars
 opname
 opnames
 orelse
@@ -149,18 +178,22 @@ patma
 peepholer
 phcount
 platstdlib
+ploc
 posonlyarg
 posonlyargs
 prec
+preds
 preinitialized
 pybuilddir
 pycore
 pyinner
 pydecimal
+pyerrors
 Pyfunc
 pylifecycle
 pymain
 pyrepl
+pystate
 PYTHONTRACEMALLOC
 PYTHONUTF8
 pythonw
@@ -168,6 +201,7 @@ PYTHREAD_NAME
 releasebuffer
 repr
 resinfo
+retarget
 Rshift
 SA_ONSTACK
 saveall
@@ -179,6 +213,7 @@ SETREF
 setresult
 setslice
 settraceallthreads
+sget
 SLOTDEFINED
 SMALLBUF
 SOABI
@@ -189,13 +224,16 @@ staticbase
 stginfo
 storefast
 stringlib
+stringized
 structseq
 subkwargs
 subparams
 subscr
 sval
 swappedbytes
+swaptimize
 sysdict
+tbstderr
 templatelib
 testconsole
 threadstate
@@ -214,6 +252,7 @@ uncollectable
 Unhandle
 unparse
 unparser
+untargeted
 untracking
 VARKEYWORDS
 varkwarg

.cspell.dict/python-more.txt

@@ -67,6 +67,7 @@ fillchar
 fillvalue
 finallyhandler
 firstiter
+fobj
 firstlineno
 fnctl
 frombytes
@@ -111,12 +112,14 @@ idfunc
 idiv
 idxs
 impls
+infd
 indexgroup
 infj
 inittab
 Inittab
 instancecheck
 instanceof
+instrs
 interpchannels
 interpqueues
 irepeat
@@ -175,6 +178,7 @@ Nonprintable
 onceregistry
 origname
 ospath
+outfd
 pendingcr
 phello
 platlibdir
@@ -185,10 +189,12 @@ posonlyargcount
 prepending
 profilefunc
 pycache
+pycapsule
 pycodecs
 pycs
 pydatetime
 pyexpat
+PYGILSTATE
 pyio
 pymain
 PYTHONAPI

.cspell.json

@@ -49,20 +49,25 @@
   "ignorePaths": [
     "**/__pycache__/**",
     "target/**",
-    "Lib/**"
+    "Lib/**",
+    "crates/host_env/**"
   ],
   // words - list of words to be always considered correct
   // (compound words like pyarg, baseclass, microbenchmark are handled by allowCompoundWords)
   "words": [
     "aiterable",
     "alnum",
+    "csock",
     "coro",
     "dedentations",
     "dedents",
     "deduped",
+    "deoptimized",
     "deoptimize",
     "emscripten",
     "excs",
+    "fnfe",
+    "ifexp",
     "interps",
     "jitted",
     "jitting",
@@ -72,8 +77,13 @@
     "oparg",
     "opargs",
     "pyc",
+    "reborrow",
+    "reraises",
+    "reraising",
     "significand",
     "summands",
+    "TESTFN",
+    "TZPATH",
     "unraisable",
     "wasi",
     "weaked",

.gitattributes

@@ -58,13 +58,14 @@ Lib/venv/scripts/posix/* text eol=lf
 #
 [attr]generated linguist-generated=true diff=generated
 
-Lib/_opcode_metadata.py                             generated
+Lib/_opcode_metadata.py                                 generated
-Lib/keyword.py                                      generated
+Lib/keyword.py                                          generated
-Lib/idlelib/help.html                               generated
+Lib/idlelib/help.html                                   generated
-Lib/test/certdata/*.pem                             generated
+Lib/test/certdata/*.pem                                 generated
-Lib/test/certdata/*.0                               generated
+Lib/test/certdata/*.0                                   generated
-Lib/test/levenshtein_examples.json                  generated
+Lib/test/levenshtein_examples.json                      generated
-Lib/test/test_stable_abi_ctypes.py                  generated
+Lib/test/test_stable_abi_ctypes.py                      generated
-Lib/token.py                                        generated
+Lib/token.py                                            generated
+crates/compiler-core/src/bytecode/opcode_metadata.rs    generated
 
-.github/workflows/*.lock.yml linguist-generated=true merge=ours
+.github/workflows/*.lock.yml linguist-generated=true merge=ours

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,10 @@
+<!--
+Thanks for your contribution!
+-->
+
+- [ ] Closes #xxxx <!-- Replace xxxx with the GitHub issue number -->
+- [ ] This PR follows our [AI policy](https://github.com/RustPython/.github/blob/main/AI_POLICY.md)
+
+## Summary
+<!-- What's the purpose of the change? What does it do, and why? -->
+

.github/dependabot.yml

@@ -2,7 +2,9 @@
 version: 2
 updates:
   - package-ecosystem: cargo
-    directory: /
+    directories:
+      - "/"
+      - "crates/*"
     schedule:
       interval: weekly
     cooldown:
@@ -19,6 +21,7 @@ updates:
           - "digest"
           - "md-5"
           - "sha-1"
+          - "sha1"
           - "sha2"
           - "sha3"
           - "blake2"
@@ -120,6 +123,11 @@ updates:
       toml:
         patterns:
           - "toml*"
+      unix:
+        patterns:
+          - "mac_address"
+          - "nix"
+          - "rustyline"
       wasm-bindgen:
         patterns:
           - "wasm-bindgen*"

.github/workflows/ci.yaml

@@ -19,21 +19,63 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  CARGO_ARGS: --no-default-features --features stdlib,importlib,stdio,encodings,sqlite,ssl-rustls,host_env
+  CARGO_ARGS: --no-default-features --features stdlib,importlib,stdio,encodings,sqlite,ssl-rustls-aws-lc,host_env
   CARGO_ARGS_NO_SSL: --no-default-features --features stdlib,importlib,stdio,encodings,sqlite,host_env
   # Crates excluded from workspace builds:
   # - rustpython_wasm: requires wasm target
   # - rustpython-compiler-source: deprecated
   # - rustpython-venvlauncher: Windows-only
   WORKSPACE_EXCLUDES: --exclude rustpython_wasm --exclude rustpython-compiler-source --exclude rustpython-venvlauncher
-  # Python version targeted by the CI.
-  PYTHON_VERSION: "3.14.3"
   X86_64_PC_WINDOWS_MSVC_OPENSSL_LIB_DIR: C:\Program Files\OpenSSL\lib\VC\x64\MD
   X86_64_PC_WINDOWS_MSVC_OPENSSL_INCLUDE_DIR: C:\Program Files\OpenSSL\include
   CARGO_INCREMENTAL: 0
+  CARGO_PROFILE_TEST_DEBUG: 0
+  CARGO_PROFILE_DEV_DEBUG: 0
+  CARGO_PROFILE_RELEASE_DEBUG: 0
   CARGO_TERM_COLOR: always
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true # TODO: Remove on 2026/06/02
+  CI: true
 
 jobs:
+  determine_changes:
+    name: Determine changes
+    runs-on: ubuntu-slim
+    outputs:
+      # Flag that is raised when any rust code is changed.
+      rust_code: ${{ steps.check_rust_code.outputs.changed }}
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Determine merge base
+        id: merge_base
+        run: |
+          sha=$(git merge-base HEAD "origin/${BASE_REF}")
+          echo "sha=${sha}" >> "$GITHUB_OUTPUT"
+        env:
+          BASE_REF: ${{ github.event.pull_request.base.ref || 'main' }}
+
+      - name: Check if there was any code related change
+        id: check_rust_code
+        run: |
+          if git diff --quiet "${MERGE_BASE}...HEAD" -- \
+            ':Cargo.toml' \
+            ':Cargo.lock' \
+            ':rust-toolchain.toml' \
+            ':.cargo/config.toml' \
+            ':crates/**' \
+            ':src/**' \
+            ':.github/workflows/ci.yaml' \
+          ; then
+              echo "changed=false" >> "$GITHUB_OUTPUT"
+          else
+              echo "changed=true" >> "$GITHUB_OUTPUT"
+          fi
+        env:
+          MERGE_BASE: ${{ steps.merge_base.outputs.sha }}
+
   rust_tests:
     if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip:ci') }}
     env:
@@ -51,27 +93,35 @@ jobs:
           persist-credentials: false
 
       - uses: dtolnay/rust-toolchain@stable
-        with:
-          components: clippy
 
-      - uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
+          restore-keys: |
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
+        # Windows runners randomly crashes, https://github.com/actions/cache/issues/1754
+        continue-on-error: true
 
       - name: Install macOS dependencies
         uses: ./.github/actions/install-macos-deps
 
-      - name: run clippy
-        run: cargo clippy ${{ env.CARGO_ARGS }} --workspace --all-targets ${{ env.WORKSPACE_EXCLUDES }} -- -Dwarnings
-
       - name: run rust tests
-        run: cargo test --workspace ${{ env.WORKSPACE_EXCLUDES }} --verbose --features threading ${{ env.CARGO_ARGS }}
+        run: cargo test --workspace --exclude rustpython-capi ${{ env.WORKSPACE_EXCLUDES }} --features threading ${{ env.CARGO_ARGS }}
+        env:
+          INSTA_WORKSPACE_ROOT: ${{ github.workspace }}
 
-      - name: check compilation without threading
+      - name: run c-api tests
-        run: cargo check ${{ env.CARGO_ARGS }}
+        working-directory: crates/capi
-
+        run: cargo test
-      - run: cargo doc --locked
+        if: runner.os != 'Windows'  # Requires pyo3 0.29+ on Windows
-        if: runner.os == 'Linux'
 
       - name: check compilation without host_env (sandbox mode)
         run: |
@@ -90,6 +140,10 @@ jobs:
         run: cargo build --no-default-features --features ssl-openssl
         if: runner.os == 'Linux'
 
+      - name: Test vendored OpenSSL build
+        run: cargo build --no-default-features --features ssl-openssl-vendor
+        if: runner.os == 'Linux'
+
       # - name: Install tk-dev for tkinter build
       #   run: sudo apt-get update && sudo apt-get install -y tk-dev
       #   if: runner.os == 'Linux'
@@ -111,12 +165,18 @@ jobs:
         if: runner.os == 'Linux'
 
   cargo_check:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip:ci') }}
     name: cargo check
     runs-on: ${{ matrix.os }}
+    needs:
+      - determine_changes
+    if: |
+      (
+        !contains(github.event.pull_request.labels.*.name, 'skip:ci') &&
+        needs.determine_changes.outputs.rust_code == 'true'
+      ) || github.ref == 'refs/heads/main'
     strategy:
       matrix:
-        include: 
+        include:
         - os: ubuntu-latest
           target: aarch64-linux-android
         - os: ubuntu-latest
@@ -127,10 +187,13 @@ jobs:
           target: i686-unknown-linux-musl
           dependencies:
             musl-tools: true
+          skip_ssl: true
         - os: ubuntu-latest
           target: wasm32-wasip2
+          skip_ssl: true
         - os: ubuntu-latest
           target: x86_64-unknown-freebsd
+          skip_ssl: true
         - os: ubuntu-latest
           target: aarch64-unknown-linux-gnu
           dependencies:
@@ -155,8 +218,7 @@ jobs:
           gcc-aarch64-linux-gnu: ${{ matrix.dependencies.gcc-aarch64-linux-gnu || false }}
 
       - name: Restore cache
-        uses: actions/cache/restore@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
-        if: ${{ github.ref != 'refs/heads/main' }} # Never restore on main
         with:
           path: |
             ~/.cargo/bin/
@@ -165,9 +227,12 @@ jobs:
             ~/.cargo/git/db/
             target/
           # key won't match, will rely on restore-keys
-          key: cargo-check-${{ runner.os }}-${{ matrix.target }}
+          key: ${{ runner.os }}-${{ matrix.target }}
           restore-keys: |
-            cargo-check-${{ runner.os }}-${{ matrix.target }}-
+            ${{ runner.os }}-stable-${{ matrix.target }}-${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable-${{ matrix.target }}-
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
 
       - uses: dtolnay/rust-toolchain@stable
         with:
@@ -176,11 +241,25 @@ jobs:
       - name: Setup Android NDK
         if: ${{ matrix.target == 'aarch64-linux-android' }}
         id: setup-ndk
-        uses: nttld/setup-ndk@v1
+        uses: nttld/setup-ndk@ed92fe6cadad69be94a966a7ee3271275e62f779 # v1.6.0
         with:
           ndk-version: r27
           add-to-path: true
 
+      - name: Append env conf to cargo
+        if: ${{ matrix.target == 'aarch64-linux-android' }}
+        env:
+          NDK_PATH: ${{ steps.setup-ndk.outputs.ndk-path }}
+        run: |
+          {
+            echo "[env]"
+            echo "CC_aarch64_linux_android = \"${NDK_PATH}/toolchains/llvm/prebuilt/linux-x86_64/bin/aarch64-linux-android24-clang\""
+
+            echo "AR_aarch64_linux_android = \"${NDK_PATH}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-ar\""
+
+          echo "CARGO_TARGET_AARCH64_LINUX_ANDROID_LINKER = \"${NDK_PATH}/toolchains/llvm/prebuilt/linux-x86_64/bin/aarch64-linux-android24-clang\""
+          } >> .cargo/config.toml
+
       # - name: Prepare repository for redox compilation
       #   run: bash scripts/redox/uncomment-cargo.sh
       # - name: Check compilation for Redox
@@ -189,24 +268,12 @@ jobs:
       #     command: check
       #     args: --ignore-rust-version
 
-      - name: Check compilation
+      - name: Check compilation with threading
-        run: cargo check --target "${{ matrix.target }}" ${{ env.CARGO_ARGS_NO_SSL }}
+        run: cargo check --target "${{ matrix.target }}" ${{ env.CARGO_ARGS_NO_SSL }} --features threading
-        env:
-          CC_aarch64_linux_android: ${{ steps.setup-ndk.outputs.ndk-path }}/toolchains/llvm/prebuilt/linux-x86_64/bin/aarch64-linux-android24-clang
-          AR_aarch64_linux_android: ${{ steps.setup-ndk.outputs.ndk-path }}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-ar
-          CARGO_TARGET_AARCH64_LINUX_ANDROID_LINKER: ${{ steps.setup-ndk.outputs.ndk-path }}/toolchains/llvm/prebuilt/linux-x86_64/bin/aarch64-linux-android24-clang
 
-      - name: Save cache
+      - name: Check compilation with ssl
-        if: ${{ github.ref == 'refs/heads/main' }} # only save on main
+        if: ${{ !matrix.skip_ssl }}
-        uses: actions/cache/save@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        run: cargo check --target "${{ matrix.target }}" ${{ env.CARGO_ARGS }}
-        with:
-          path: |
-            ~/.cargo/bin/
-            ~/.cargo/registry/index/
-            ~/.cargo/registry/cache/
-            ~/.cargo/git/db/
-            target/
-          key: cargo-check-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('**/Cargo.toml') }}-${{ hashFiles('Cargo.lock') }}-${{ github.sha }}
 
   snippets_cpython:
     if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip:ci') }}
@@ -228,18 +295,21 @@ jobs:
         - os: macos-latest
           extra_test_args:
             - '-u all'
-          env_polluting_tests: []
+          env_polluting_tests:
+            - test_set
           skips: []
           timeout: 50
         - os: ubuntu-latest
           extra_test_args:
             - '-u all'
-          env_polluting_tests: []
+          env_polluting_tests:
+            - test_set
           skips: []
           timeout: 60
         - os: windows-2025
           extra_test_args: [] # TODO: Enable '-u all'
-          env_polluting_tests: []
+          env_polluting_tests:
+            - test_set
           skips:
             - test_rlcompleter
             - test_pathlib # panic by surrogate chars
@@ -254,13 +324,23 @@ jobs:
 
       - uses: dtolnay/rust-toolchain@stable
 
-      - uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
+          restore-keys: |
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
+        # Windows runners randomly crashes, https://github.com/actions/cache/issues/1754
+        continue-on-error: true
 
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
 
       - name: Install macOS dependencies
         uses: ./.github/actions/install-macos-deps
@@ -290,8 +370,24 @@ jobs:
 
       - name: Run flaky MP CPython tests
         run: |
-          target/release/rustpython -m test -j 1 ${{ join(matrix.extra_test_args, ' ') }} --slowest --fail-env-changed --timeout 600 -v ${{ env.FLAKY_MP_TESTS }}
+          for attempt in $(seq 1 5); do
+            echo "::group::Attempt ${attempt}"
+
+            set +e
+            target/release/rustpython -m test -j 1 ${{ join(matrix.extra_test_args, ' ') }} --slowest --fail-env-changed --timeout 600 -v ${{ env.FLAKY_MP_TESTS }}
+            status=$?
+            set -e
+
+            echo "::endgroup::"
+
+            if [ $status -eq 0 ]; then
+              exit 0
+            fi
+          done
+
+          exit 1
         timeout-minutes: ${{ matrix.timeout }}
+        shell: bash
         env:
           RUSTPYTHON_SKIP_ENV_POLLUTERS: true
 
@@ -348,12 +444,82 @@ jobs:
         shell: bash
         run: python -I scripts/whats_left.py ${{ env.CARGO_ARGS }} --features jit
 
+  clippy:
+    name: clippy
+    runs-on: ${{ matrix.os }}
+    needs:
+      - determine_changes
+    permissions:
+      contents: read
+    if: |
+      needs.determine_changes.outputs.rust_code == 'true' ||
+      github.ref == 'refs/heads/main'
+    strategy:
+      fail-fast: false
+      matrix:
+        os:
+          - macos-latest
+          - ubuntu-latest
+          - windows-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          components: clippy
+
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
+          restore-keys: |
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
+        # Windows runners randomly crashes, https://github.com/actions/cache/issues/1754
+        continue-on-error: true
+
+      - name: Clippy
+        run: cargo clippy --keep-going ${{ env.CARGO_ARGS }} --workspace --all-targets ${{ env.WORKSPACE_EXCLUDES }} -- -Dwarnings
+
+  cargo_shear:
+    name: cargo shear
+    runs-on: ubuntu-latest
+    needs:
+      - determine_changes
+    permissions:
+      contents: read
+    if: |
+      needs.determine_changes.outputs.rust_code == 'true' ||
+      github.ref == 'refs/heads/main'
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - uses: dtolnay/rust-toolchain@stable
+
+      - uses: cargo-bins/cargo-binstall@aaa84a43aec4955a42c5ffc65d258961e39f276e # v1.19.1
+
+      - name: cargo shear
+        run: |
+          cargo binstall --no-confirm cargo-shear
+          cargo shear
+
   lint:
     name: Lint
     runs-on: ubuntu-latest
     permissions:
       contents: read
       checks: write
+      issues: write
       pull-requests: write
       security-events: write # for zizmor
     steps:
@@ -362,54 +528,76 @@ jobs:
           persist-credentials: false
 
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
 
       - uses: dtolnay/rust-toolchain@stable
         with:
           components: rustfmt
 
-      - uses: cargo-bins/cargo-binstall@113a77a4ce971c41332f2129c3d995df993cf746 # v1.17.8
-
-      - name: cargo shear
-        run: |
-          cargo binstall --no-confirm cargo-shear
-          cargo shear
-
       - name: actionlint
-        uses: reviewdog/action-actionlint@0d952c597ef8459f634d7145b0b044a9699e5e43 # v1.71.0
+        uses: reviewdog/action-actionlint@6fb7acc99f4a1008869fa8a0f09cfca740837d9d # v1.72.0
 
       - name: zizmor
-        uses: zizmorcore/zizmor-action@71321a20a9ded102f6e9ce5718a2fcec2c4f70d8 # v0.5.2
+        uses: zizmorcore/zizmor-action@5f14fd08f7cf1cb1609c1e344975f152c7ee938d # v0.5.6
 
       - name: restore prek cache
-        if: ${{ github.ref != 'refs/heads/main' }} # never restore on main
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
-        uses: actions/cache/restore@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           key: prek-${{ hashFiles('.pre-commit-config.yaml') }}
           path: ~/.cache/prek
 
-      - name: prek
+      # TODO: Remove on 2026/06/02 when node24 is the default
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        with:
+          package-manager-cache: false
+          node-version: "24"
+
+      - name: install prek
         id: prek
-        uses: j178/prek-action@53276d8b0d10f8b6672aa85b4588c6921d0370cc # v2.0.1
+        uses: j178/prek-action@bdca6f102f98e2b4c7029491a53dfd366469e33d # v2.0.4
         with:
           cache: false
           show-verbose-logs: false
-        continue-on-error: true
+          install-only: true
+
+      - name: prek run
+        run: prek run --show-diff-on-failure --color=always --all-files
+
+      - name: Get target CPython version
+        id: cpython-version
+        run: |
+          version=$(cat .python-version)
+          echo "version=${version}" >> "$GITHUB_OUTPUT"
+
+      - name: Clone CPython
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          repository: python/cpython
+          path: cpython
+          ref: "v${{ steps.cpython-version.outputs.version }}"
+          persist-credentials: false
+
+      - name: prek run (manual stage)
+        run: prek run --show-diff-on-failure --color=always --all-files --hook-stage manual
+        env:
+          CPYTHON_ROOT: ${{ github.workspace }}/cpython
 
       - name: save prek cache
         if: ${{ github.ref == 'refs/heads/main' }} # only save on main
-        uses: actions/cache/save@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           key: prek-${{ hashFiles('.pre-commit-config.yaml') }}
           path: ~/.cache/prek
 
+      - name: restore git permissions
+        if: ${{ !cancelled() }}
+        run: sudo chown -R "$(id -u):$(id -g)" .git
+
       - name: reviewdog
-        uses: reviewdog/action-suggester@aa38384ceb608d00f84b4690cacc83a5aba307ff # 1.24.0
+        if: ${{ !cancelled() }}
+        uses: reviewdog/action-suggester@aa38384ceb608d00f84b4690cacc83a5aba307ff # v1.24.0
         with:
           level: warning
           fail_level: error
-          cleanup: false
 
   miri:
     if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip:ci') }}
@@ -428,9 +616,18 @@ jobs:
           toolchain: ${{ env.NIGHTLY_CHANNEL }}
           components: miri
 
-      - uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-
 
       - name: Run tests under miri
         run: cargo +${{ env.NIGHTLY_CHANNEL }} miri test -p rustpython-vm -- miri_test
@@ -453,12 +650,23 @@ jobs:
         with:
           components: clippy
 
-      - uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
+          restore-keys: |
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
+            ${{ runner.os }}-
 
       - name: cargo clippy
-        run: cargo clippy --manifest-path=crates/wasm/Cargo.toml -- -Dwarnings
+        run: cargo clippy --keep-going --manifest-path=crates/wasm/Cargo.toml -- -Dwarnings
 
       - name: install wasm-pack
         run: curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
@@ -469,15 +677,29 @@ jobs:
           tar -xzf geckodriver-v0.36.0-linux64.tar.gz -C geckodriver
 
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
 
       - run: python -m pip install -r requirements.txt
         working-directory: ./wasm/tests
-      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
-          cache: "npm"
+          package-manager-cache: false
-          cache-dependency-path: "wasm/demo/package-lock.json"
+
+      - name: Get npm cache directory
+        id: npm-cache-dir
+        shell: bash
+        run: echo "dir=$(npm config get cache)" >> "$GITHUB_OUTPUT"
+
+      - name: Restore npm cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        # don't restore on main or release
+        if: github.ref != 'refs/heads/main' && github.ref != 'refs/heads/release'
+        with:
+          path: ${{ steps.npm-cache-dir.outputs.dir }}
+          key: node-${{ runner.os }}-wasm-demo-
+          restore-keys: |
+            node-${{ runner.os }}-wasm-demo-
+
       - name: run test
         run: |
           driver_path="$(pwd)/../../geckodriver"
@@ -487,8 +709,11 @@ jobs:
         env:
           NODE_OPTIONS: "--openssl-legacy-provider"
         working-directory: ./wasm/demo
-      - uses: mwilliamson/setup-wabt-action@v3
+
-        with: { wabt-version: "1.0.36" }
+      - uses: mwilliamson/setup-wabt-action@427f2fdd70bc4dbc2e53c2eb4f19f66162d71bd2 # v4.0.0
+        with:
+          wabt-version: "1.0.36"
+
       - name: check wasm32-unknown without js
         run: |
           cd example_projects/wasm32_without_js/rustpython-without-js
@@ -498,6 +723,7 @@ jobs:
             echo "ERROR: wasm32-unknown module expects imports from the host environment" >&2
           fi
           cargo run --release --manifest-path wasm-runtime/Cargo.toml rustpython-without-js/target/wasm32-unknown-unknown/debug/rustpython_without_js.wasm
+
       - name: build notebook demo
         if: github.ref == 'refs/heads/release'
         run: |
@@ -507,15 +733,24 @@ jobs:
         env:
           NODE_OPTIONS: "--openssl-legacy-provider"
         working-directory: ./wasm/notebook
+
       - name: Deploy demo to Github Pages
         if: success() && github.ref == 'refs/heads/release'
-        uses: peaceiris/actions-gh-pages@v4
+        uses: peaceiris/actions-gh-pages@84c30a85c19949d7eee79c4ff27748b70285e453 # v4.1.0
         env:
           ACTIONS_DEPLOY_KEY: ${{ secrets.ACTIONS_DEMO_DEPLOY_KEY }}
           PUBLISH_DIR: ./wasm/demo/dist
           EXTERNAL_REPOSITORY: RustPython/demo
           PUBLISH_BRANCH: master
 
+      - name: Save npm cache
+        # Save only on main or release
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/release'
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        with:
+          path: ${{ steps.npm-cache-dir.outputs.dir }}
+          key: node-${{ runner.os }}-wasm-demo-${{ hashFiles('wasm/demo/package-lock.json') }}
+
   wasm-wasi:
     if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip:ci') }}
     name: Run snippets and cpython tests on wasm-wasi
@@ -530,12 +765,24 @@ jobs:
         with:
           target: wasm32-wasip1
 
-      - uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
+          restore-keys: |
+            ${{ runner.os }}-stable-wasm32-wasip1-${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable-wasm32-wasip1-
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
 
       - name: Setup Wasmer
-        uses: wasmerio/setup-wasmer@v3
+        uses: wasmerio/setup-wasmer@24b15c95293d23f89c68bd40dac76338f773e924 # v3.1
 
       - name: Install clang
         uses: ./.github/actions/install-linux-deps
@@ -543,8 +790,44 @@ jobs:
           clang: true
 
       - name: build rustpython
-        run: cargo build --release --target wasm32-wasip1 --features freeze-stdlib,stdlib --verbose
+        run: cargo build --release --target wasm32-wasip1 --no-default-features --features freeze-stdlib,stdlib,stdio,importlib,host_env --verbose
       - name: run snippets
         run: wasmer run --dir "$(pwd)" target/wasm32-wasip1/release/rustpython.wasm -- "$(pwd)/extra_tests/snippets/stdlib_random.py"
       - name: run cpython unittest
         run: wasmer run --dir "$(pwd)" target/wasm32-wasip1/release/rustpython.wasm -- "$(pwd)/Lib/test/test_int.py"
+
+  cargo_doc:
+    needs:
+      - determine_changes
+    if: |
+      (
+        !contains(github.event.pull_request.labels.*.name, 'skip:ci') &&
+        needs.determine_changes.outputs.rust_code == 'true'
+      ) || github.ref == 'refs/heads/main'
+    env:
+      RUST_BACKTRACE: full
+    name: cargo doc
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - uses: dtolnay/rust-toolchain@stable
+
+      - name: Restore cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
+          restore-keys: |
+            ${{ runner.os }}-stable--${{ hashFiles('**/Cargo.toml') }}-
+            ${{ runner.os }}-stable--
+
+      - name: cargo doc
+        run: cargo doc --locked

.github/workflows/cron-ci.yaml

@@ -1,3 +1,5 @@
+name: Periodic checks/tasks
+
 on:
   schedule:
     - cron: "0 0 * * 6"
@@ -5,15 +7,15 @@ on:
   push:
     paths:
       - .github/workflows/cron-ci.yaml
+    branches:
+      - main
   pull_request:
     paths:
       - .github/workflows/cron-ci.yaml
 
-name: Periodic checks/tasks
-
 env:
-  CARGO_ARGS: --no-default-features --features stdlib,importlib,stdio,encodings,ssl-rustls,jit,host_env
+  CARGO_ARGS: --no-default-features --features stdlib,importlib,stdio,encodings,ssl-rustls-aws-lc,jit,host_env
-  PYTHON_VERSION: "3.14.3"
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: 'true' # TODO: Remove on 2026/06/02
 
 jobs:
   # codecov collects code coverage data from the rust tests, python snippets and python test suite.
@@ -29,24 +31,32 @@ jobs:
           persist-credentials: false
 
       - uses: dtolnay/rust-toolchain@stable
-      - uses: taiki-e/install-action@cargo-llvm-cov
+
-      - uses: actions/setup-python@v6.2.0
+      - uses: taiki-e/install-action@b550161ef8a7bc4f2a671c0b03a18ac9ccedea1e # v2.79.1
         with:
-          python-version: ${{ env.PYTHON_VERSION }}
+          tool: cargo-llvm-cov
+
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+
       - run: sudo apt-get update && sudo apt-get -y install lcov
+
       - name: Run cargo-llvm-cov with Rust tests.
-        run: cargo llvm-cov --no-report --workspace --exclude rustpython_wasm --exclude rustpython-compiler-source --exclude rustpython-venvlauncher --verbose --no-default-features --features stdlib,importlib,stdio,encodings,ssl-rustls,jit,host_env
+        run: cargo llvm-cov --no-report --workspace --exclude rustpython_wasm --exclude rustpython-compiler-source --exclude rustpython-venvlauncher --verbose --no-default-features --features stdlib,importlib,stdio,encodings,ssl-rustls-aws-lc,jit,host_env
+
       - name: Run cargo-llvm-cov with Python snippets.
         run: python scripts/cargo-llvm-cov.py
         continue-on-error: true
+
       - name: Run cargo-llvm-cov with Python test suite.
         run: cargo llvm-cov --no-report run -- -m test -u all --slowest --fail-env-changed
         continue-on-error: true
+
       - name: Prepare code coverage data
         run: cargo llvm-cov report --lcov --output-path='codecov.lcov'
+
       - name: Upload to Codecov
         if: ${{ github.event_name != 'pull_request' }}
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
         with:
           files: ./codecov.lcov
 
@@ -61,12 +71,15 @@ jobs:
           persist-credentials: true
 
       - uses: dtolnay/rust-toolchain@stable
+
       - name: build rustpython
         run: cargo build --release --verbose
+
       - name: collect tests data
         run: cargo run --release extra_tests/jsontests.py
         env:
           RUSTPYTHONPATH: ${{ github.workspace }}/Lib
+
       - name: upload tests data to the website
         if: ${{ github.event_name != 'pull_request' }}
         env:
@@ -96,17 +109,19 @@ jobs:
           persist-credentials: true
 
       - uses: dtolnay/rust-toolchain@stable
-      - uses: actions/setup-python@v6.2.0
+
-        with:
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-          python-version: ${{ env.PYTHON_VERSION }}
+
       - name: build rustpython
         run: cargo build --release --verbose
+
       - name: Collect what is left data
         run: |
           chmod +x ./scripts/whats_left.py
           ./scripts/whats_left.py --features "ssl,sqlite" > whats_left.temp
         env:
           RUSTPYTHONPATH: ${{ github.workspace }}/Lib
+
       - name: Upload data to the website
         if: ${{ github.event_name != 'pull_request' }}
         env:
@@ -157,16 +172,20 @@ jobs:
           persist-credentials: true
 
       - uses: dtolnay/rust-toolchain@stable
-      - uses: actions/setup-python@v6.2.0
+
-        with:
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-          python-version: ${{ env.PYTHON_VERSION }}
+
       - run: cargo install cargo-criterion
+
       - name: build benchmarks
         run: cargo build --release --benches
+
       - name: collect execution benchmark data
         run: cargo criterion --bench execution
+
       - name: collect microbenchmarks data
         run: cargo criterion --bench microbenchmarks
+
       - name: restructure generated files
         run: |
           cd ./target/criterion/reports
@@ -179,6 +198,7 @@ jobs:
           cd ..
           mv reports/* .
           rmdir reports
+
       - name: upload benchmark data to the website
         if: ${{ github.event_name != 'pull_request' }}
         env:

.github/workflows/lib-deps-check.yaml

@@ -10,9 +10,6 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.event.pull_request.number }}
   cancel-in-progress: true
 
-env:
-  PYTHON_VERSION: "3.14.3"
-
 jobs:
   check_deps:
     permissions:
@@ -37,46 +34,71 @@ jobs:
           # Checkout only Lib/ directory from PR head for accurate comparison
           git checkout ${{ github.event.pull_request.head.sha }} -- Lib/
 
-      - name: Checkout CPython
+      - name: Get target CPython version
+        id: cpython-version
         run: |
-          git clone --depth 1 --branch "v${{ env.PYTHON_VERSION }}" https://github.com/python/cpython.git cpython
+          version=$(cat .python-version)
+          echo "version=${version}" >> "$GITHUB_OUTPUT"
+
+      - name: Checkout CPython
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          repository: python/cpython
+          path: cpython
+          ref: "v${{ steps.cpython-version.outputs.version }}"
+          fetch-depth: 1
+          persist-credentials: false
 
       - name: Get changed Lib files
-        id: changed-files
+        id: all-changed-files
         run: |
           # Get the list of changed files under Lib/
-          changed=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }} -- 'Lib/*.py' 'Lib/**/*.py' | head -50)
+          {
-          echo "Changed files:"
+            echo 'changed<<EOF'
-          echo "$changed"
 
-          # Extract unique module names
+            git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }} -- 'Lib/*.py' 'Lib/**/*.py'
-          modules=""
+
-          for file in $changed; do
+            echo 'EOF' 
-            if [[ "$file" == Lib/test/* ]]; then
+          } >> "$GITHUB_OUTPUT"
-              # Test files: Lib/test/test_pydoc.py -> test_pydoc, Lib/test/test_pydoc/foo.py -> test_pydoc
+
-              module=$(echo "$file" | sed -E 's|^Lib/test/||; s|\.py$||; s|/.*||')
+      - name: Parse changed files
-              # Skip non-test files in test/ (e.g., support.py, __init__.py)
+        id: changed-files
-              if [[ ! "$module" == test_* ]]; then
+        run: |
+          from os import environ
+
+          files = environ["FILES"]
+          modules = set()
+          for file in files.splitlines():
+            file = file.strip()
+
+            if file.startswith("Lib/test/"):
+              # Test files:
+              # Lib/test/test_pydoc.py -> test_pydoc
+              # Lib/test/test_pydoc/foo.py -> test_pydoc
+              module = file.removeprefix("Lib/test/").split("/")[0]
+              if not module.startswith("test_"):
                 continue
-              fi
+            else:
-            else
+              # Lib files:
-              # Lib files: Lib/foo.py -> foo, Lib/foo/__init__.py -> foo
+              # Lib/foo.py -> foo
-              module=$(echo "$file" | sed -E 's|^Lib/||; s|/__init__\.py$||; s|\.py$||; s|/.*||')
+              # Lib/foo/__init__.py -> foo
-            fi
+              module = file.removeprefix("Lib/").split("/")[0]
-            if [[ -n "$module" && ! " $modules " =~ " $module " ]]; then
+            
-              modules="$modules $module"
+            module = module.split(".")[0]
-            fi
+            modules.add(module)
-          done
 
-          modules=$(echo "$modules" | xargs)  # trim whitespace
+          print(f"{modules=}")
-          echo "Detected modules: $modules"
+          output = " ".join(sorted(modules))
-          echo "modules=$modules" >> $GITHUB_OUTPUT
+          output_file = environ["GITHUB_OUTPUT"]
+          with open(output_file, mode="a", encoding="utf-8") as fd:
+            fd.write(f"modules={output}\n")
+        env:
+          FILES: ${{ steps.all-changed-files.outputs.changed }}
+        shell: python
 
       - name: Setup Python
         if: steps.changed-files.outputs.modules != ''
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-        with:
-          python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Run deps check
         if: steps.changed-files.outputs.modules != ''
@@ -92,7 +114,7 @@ jobs:
 
       - name: Post comment
         if: steps.deps-check.outputs.deps_output != ''
-        uses: marocchino/sticky-pull-request-comment@v3
+        uses: marocchino/sticky-pull-request-comment@0ea0beb66eb9baf113663a64ec522f60e49231c0 # v3.0.4
         with:
           header: lib-deps-check
           number: ${{ github.event.pull_request.number }}
@@ -109,7 +131,7 @@ jobs:
 
       - name: Remove comment if no Lib changes
         if: steps.changed-files.outputs.modules == ''
-        uses: marocchino/sticky-pull-request-comment@v3
+        uses: marocchino/sticky-pull-request-comment@0ea0beb66eb9baf113663a64ec522f60e49231c0 # v3.0.4
         with:
           header: lib-deps-check
           number: ${{ github.event.pull_request.number }}

.github/workflows/release.yml

@@ -16,11 +16,15 @@ env:
   X86_64_PC_WINDOWS_MSVC_OPENSSL_LIB_DIR: C:\Program Files\OpenSSL\lib\VC\x64\MD
   X86_64_PC_WINDOWS_MSVC_OPENSSL_INCLUDE_DIR: C:\Program Files\OpenSSL\include
 
+permissions: {}
+
 jobs:
   build:
     runs-on: ${{ matrix.os }}
     # Disable this scheduled job when running on a fork.
     if: ${{ github.repository == 'RustPython/RustPython' || github.event_name != 'schedule' }}
+    permissions:
+      contents: read
     strategy:
       matrix:
         include:
@@ -64,7 +68,7 @@ jobs:
           libtool: true
 
       - name: Build RustPython
-        run: cargo build --release --target=${{ matrix.target }} --verbose --no-default-features --features stdlib,stdio,importlib,encodings,sqlite,host_env,ssl-rustls,threading,jit
+        run: cargo build --release --target=${{ matrix.target }} --verbose --no-default-features --features stdlib,stdio,importlib,encodings,sqlite,host_env,ssl-rustls-aws-lc,threading,jit
 
       - name: Rename Binary
         run: cp target/${{ matrix.target }}/release/rustpython target/rustpython-release-${{ runner.os }}-${{ matrix.target }}
@@ -75,7 +79,7 @@ jobs:
         if: runner.os == 'Windows'
 
       - name: Upload Binary Artifacts
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: rustpython-release-${{ runner.os }}-${{ matrix.target }}
           path: target/rustpython-release-${{ runner.os }}-${{ matrix.target }}*
@@ -84,6 +88,8 @@ jobs:
     runs-on: ubuntu-latest
     # Disable this scheduled job when running on a fork.
     if: ${{ github.repository == 'RustPython/RustPython' || github.event_name != 'schedule' }}
+    permissions:
+      contents: read
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
@@ -100,7 +106,7 @@ jobs:
         run: cp target/wasm32-wasip1/release/rustpython.wasm target/rustpython-release-wasm32-wasip1.wasm
 
       - name: Upload Binary Artifacts
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: rustpython-release-wasm32-wasip1
           path: target/rustpython-release-wasm32-wasip1.wasm
@@ -108,11 +114,11 @@ jobs:
       - name: install wasm-pack
         run: curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
 
-      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           package-manager-cache: false
 
-      - uses: mwilliamson/setup-wabt-action@febe2a12b7ccb999a6e5d953a8362a3b7ffcf148 # v3.2.0
+      - uses: mwilliamson/setup-wabt-action@427f2fdd70bc4dbc2e53c2eb4f19f66162d71bd2 # v4.0.0
         with:
           wabt-version: "1.0.30"
 
@@ -135,7 +141,7 @@ jobs:
 
       - name: Deploy demo to Github Pages
         if: ${{ github.repository == 'RustPython/RustPython' }}
-        uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0
+        uses: peaceiris/actions-gh-pages@84c30a85c19949d7eee79c4ff27748b70285e453 # v4.1.0
         with:
           deploy_key: ${{ secrets.ACTIONS_DEMO_DEPLOY_KEY }}
           publish_dir: ./wasm/demo/dist
@@ -147,6 +153,8 @@ jobs:
     # Disable this scheduled job when running on a fork.
     if: ${{ github.repository == 'RustPython/RustPython' || github.event_name != 'schedule' }}
     needs: [build, build-wasm]
+    permissions:
+      contents: write # for creating a release
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
@@ -187,7 +195,7 @@ jobs:
               $PRERELEASE_ARG \
               bin/rustpython-release-*
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GH_TOKEN: ${{ github.token }}
           tag: ${{ github.ref_name }}
           run: ${{ github.run_number }}
           PRE_RELEASE_INPUT: ${{ github.event.inputs.pre-release }}

.github/workflows/update-caches.yml

@@ -0,0 +1,77 @@
+name: Update Actions Caches
+
+permissions:
+  contents: read
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+
+concurrency:
+    group: ${{ github.workflow }}
+    cancel-in-progress: false
+
+env:
+  CARGO_INCREMENTAL: 0
+  CARGO_TERM_COLOR: always
+  CARGO_PROFILE_TEST_DEBUG: 0
+  CARGO_PROFILE_DEV_DEBUG: 0
+  CARGO_PROFILE_RELEASE_DEBUG: 0
+  CARGO_ARGS: --workspace --no-default-features --features stdlib,importlib,stdio,encodings,sqlite,ssl-rustls-aws-lc,host_env,threading,jit --exclude rustpython_wasm --exclude rustpython-compiler-source --exclude rustpython-venvlauncher
+
+jobs:
+  build-caches:
+    name: Build Caches
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        include:
+          - os: macos-latest
+            toolchain: stable
+            target: ""
+          - os: ubuntu-latest
+            toolchain: stable
+            target: ""
+          - os: windows-latest
+            toolchain: stable
+            target: ""
+    steps:
+      - name: Checkout RustPython main branch
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          repository: RustPython/RustPython
+          ref: main
+          persist-credentials: false
+
+      - name: Setup Rust
+        uses: dtolnay/rust-toolchain@3c5f7ea28cd621ae0bf5283f0e981fb97b8a7af9
+        with:
+          toolchain: ${{ matrix.toolchain }}
+          target: ${{ matrix.target }}
+
+      - name: Install macos dependencies
+        uses: ./.github/actions/install-macos-deps
+        with:
+          openssl: true
+
+      - name: Build dev cache # dev profile used by check & doc
+        run: cargo build --profile dev ${{ env.CARGO_ARGS }}
+
+      - name: Build test cache
+        run: cargo build --profile test ${{ env.CARGO_ARGS }}
+
+      - name: Build release cache
+        run: cargo build --profile release ${{ env.CARGO_ARGS }}
+
+      - name: Save cache
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ matrix.toolchain }}-${{ matrix.target }}-${{ hashFiles('**/Cargo.toml') }}-${{ hashFiles('Cargo.lock') }}-${{ github.sha }}

.github/workflows/update-doc-db.yml

@@ -43,7 +43,7 @@ jobs:
       - name: Generate docs
         run: python crates/doc/generate.py
 
-      - uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: doc-db-${{ inputs.python-version }}-${{ matrix.os }}
           path: "crates/doc/generated/*.json"
@@ -87,19 +87,18 @@ jobs:
 
           OUTPUT_FILE='crates/doc/src/data.inc.rs'
 
-          echo -n '' > $OUTPUT_FILE
+          # shellcheck disable=SC2016
+          {
+            echo '// This file was auto-generated by `.github/workflows/update-doc-db.yml`.'
+            echo "// CPython version: ${PYTHON_VERSION}"
+            echo '// spell-checker: disable'
+            echo ''
+            echo "pub static DB: phf::Map<&'static str, &'static str> = phf::phf_map! {"
+            cat crates/doc/generated/raw_entries.txt
+            echo '};'
+          } > "$OUTPUT_FILE"
 
-          echo '// This file was auto-generated by `.github/workflows/update-doc-db.yml`.' >> $OUTPUT_FILE
+      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-          echo "// CPython version: ${PYTHON_VERSION}" >> $OUTPUT_FILE
-          echo '// spell-checker: disable' >> $OUTPUT_FILE
-
-          echo '' >> $OUTPUT_FILE
-
-          echo "pub static DB: phf::Map<&'static str, &'static str> = phf::phf_map! {" >> $OUTPUT_FILE
-          cat crates/doc/generated/raw_entries.txt >> $OUTPUT_FILE
-          echo '};' >> $OUTPUT_FILE
-
-      - uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
         with:
           name: doc-db-${{ inputs.python-version }}
           path: "crates/doc/src/data.inc.rs"

.github/workflows/update-libs-status.yaml

@@ -13,7 +13,6 @@ permissions:
   issues: write
 
 env:
-  PYTHON_VERSION: "v3.14.3"
   ISSUE_ID: "6839"
 
 jobs:
@@ -29,13 +28,20 @@ jobs:
           sparse-checkout: |-
               Lib
               scripts/update_lib
+              .python-version
 
-      - name: Clone CPython ${{ env.PYTHON_VERSION }}
+      - name: Get target CPython version
+        id: cpython-version
+        run: |
+          version=$(cat rustpython/.python-version)
+          echo "version=${version}" >> "$GITHUB_OUTPUT"
+
+      - name: Clone CPython
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           repository: python/cpython
           path: cpython
-          ref: ${{ env.PYTHON_VERSION }}
+          ref: "v${{ steps.cpython-version.outputs.version }}"
           persist-credentials: false
           sparse-checkout: |
             Lib
@@ -56,14 +62,14 @@ jobs:
 
           ## Summary
 
-          Check \`scripts/update_lib\` for tools. As a note, the current latest Python version is \`${{ env.PYTHON_VERSION }}\`.
+          Check \`scripts/update_lib\` for tools. As a note, the current latest Python version is \`${{ steps.cpython-version.outputs.version }}\`.
 
           Previous versions' issues as reference
           - 3.13: #5529 
 
           <!-- 
           Quick guideline for Copilot:
-          # Clone \`github.com/python/cpython\` \`${{ env.PYTHON_VERSION }}\` tag under RustPython working dir with depth 1 option; never 3.14.0 or 3.14.1 or 3.14.2
+          # Clone \`github.com/python/cpython\` \`${{ steps.cpython-version.outputs.version }}\` tag under RustPython working dir with depth 1 option; never 3.14.0 or 3.14.1 or 3.14.2
           # Pick a library or test to update. Probably user give one.
           # Run \`python3 scripts/update_lib quick <name>\`
           # A commit is automatically created. push the commit.

.github/workflows/upgrade-pylib.lock.yml

@@ -58,11 +58,11 @@ jobs:
       comment_repo: ""
     steps:
       - name: Setup Scripts
-        uses: github/gh-aw/actions/setup@48d8fdfddc8cad854ac0c70ceb573f09fb8f9c9b # v0.62.5
+        uses: github/gh-aw/actions/setup@2c1a237d2048b0e2412e7d7528892ea1257840e2 # v0.74.4
         with:
           destination: /opt/gh-aw/actions
       - name: Check workflow file timestamps
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_WORKFLOW_FILE: "upgrade-pylib.lock.yml"
         with:
@@ -99,7 +99,7 @@ jobs:
       secret_verification_result: ${{ steps.validate-secret.outputs.verification_result }}
     steps:
       - name: Setup Scripts
-        uses: github/gh-aw/actions/setup@48d8fdfddc8cad854ac0c70ceb573f09fb8f9c9b # v0.62.5
+        uses: github/gh-aw/actions/setup@2c1a237d2048b0e2412e7d7528892ea1257840e2 # v0.74.4
         with:
           destination: /opt/gh-aw/actions
       - name: Checkout repository
@@ -114,7 +114,7 @@ jobs:
         run: bash /opt/gh-aw/actions/create_gh_aw_tmp_dir.sh
       # Cache configuration from frontmatter processed below
       - name: Cache (cpython-lib-${{ env.PYTHON_VERSION }})
-        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           key: cpython-lib-${{ env.PYTHON_VERSION }}
           path: cpython
@@ -135,7 +135,7 @@ jobs:
         id: checkout-pr
         if: |
           github.event.pull_request
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
         with:
@@ -147,7 +147,7 @@ jobs:
             await main();
       - name: Generate agentic run info
         id: generate_aw_info
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const fs = require('fs');
@@ -201,7 +201,7 @@ jobs:
         run: bash /opt/gh-aw/actions/install_awf_binary.sh v0.16.4
       - name: Determine automatic lockdown mode for GitHub MCP server
         id: determine-automatic-lockdown
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
           GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
@@ -484,7 +484,7 @@ jobs:
           }
           GH_AW_MCP_CONFIG_EOF
       - name: Generate workflow overview
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const { generateWorkflowOverview } = require('/opt/gh-aw/actions/generate_workflow_overview.cjs');
@@ -508,10 +508,11 @@ jobs:
           cat << 'GH_AW_PROMPT_EOF' > "$GH_AW_PROMPT"
           <system>
           GH_AW_PROMPT_EOF
-          cat "/opt/gh-aw/prompts/xpia.md" >> "$GH_AW_PROMPT"
+          {
-          cat "/opt/gh-aw/prompts/temp_folder_prompt.md" >> "$GH_AW_PROMPT"
+            cat "/opt/gh-aw/prompts/xpia.md"
-          cat "/opt/gh-aw/prompts/markdown.md" >> "$GH_AW_PROMPT"
+            cat "/opt/gh-aw/prompts/temp_folder_prompt.md"
-          cat << 'GH_AW_PROMPT_EOF' >> "$GH_AW_PROMPT"
+            cat "/opt/gh-aw/prompts/markdown.md"
+            cat << 'GH_AW_PROMPT_EOF'
           <safe-outputs>
           <description>GitHub API Access Instructions</description>
           <important>
@@ -569,14 +570,15 @@ jobs:
           </github-context>
           
           GH_AW_PROMPT_EOF
-          cat << 'GH_AW_PROMPT_EOF' >> "$GH_AW_PROMPT"
+            cat << 'GH_AW_PROMPT_EOF'
           </system>
           GH_AW_PROMPT_EOF
-          cat << 'GH_AW_PROMPT_EOF' >> "$GH_AW_PROMPT"
+            cat << 'GH_AW_PROMPT_EOF'
           {{#runtime-import .github/workflows/upgrade-pylib.md}}
           GH_AW_PROMPT_EOF
+          } >> "$GH_AW_PROMPT"
       - name: Substitute placeholders
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
           GH_AW_ENV_ISSUE_ID: ${{ env.ISSUE_ID }}
@@ -610,7 +612,7 @@ jobs:
               }
             });
       - name: Interpolate variables and render templates
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
           GH_AW_ENV_ISSUE_ID: ${{ env.ISSUE_ID }}
@@ -690,7 +692,7 @@ jobs:
           bash /opt/gh-aw/actions/stop_mcp_gateway.sh "$GATEWAY_PID"
       - name: Redact secrets in logs
         if: always()
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
@@ -705,14 +707,14 @@ jobs:
           SECRET_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: Upload Safe Outputs
         if: always()
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: safe-output
           path: ${{ env.GH_AW_SAFE_OUTPUTS }}
           if-no-files-found: warn
       - name: Ingest agent output
         id: collect_output
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_SAFE_OUTPUTS: ${{ env.GH_AW_SAFE_OUTPUTS }}
           GH_AW_ALLOWED_DOMAINS: "*.pythonhosted.org,anaconda.org,api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,binstar.org,bootstrap.pypa.io,conda.anaconda.org,conda.binstar.org,crates.io,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,files.pythonhosted.org,github.com,host.docker.internal,index.crates.io,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,pip.pypa.io,ppa.launchpad.net,pypi.org,pypi.python.org,raw.githubusercontent.com,registry.npmjs.org,repo.anaconda.com,repo.continuum.io,s.symcb.com,s.symcd.com,security.ubuntu.com,sh.rustup.rs,static.crates.io,static.rust-lang.org,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com"
@@ -726,13 +728,13 @@ jobs:
             await main();
       - name: Upload sanitized agent output
         if: always() && env.GH_AW_AGENT_OUTPUT
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: agent-output
           path: ${{ env.GH_AW_AGENT_OUTPUT }}
           if-no-files-found: warn
       - name: Upload engine output files
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: agent_outputs
           path: |
@@ -741,7 +743,7 @@ jobs:
           if-no-files-found: ignore
       - name: Parse agent logs for step summary
         if: always()
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/
         with:
@@ -752,7 +754,7 @@ jobs:
             await main();
       - name: Parse MCP gateway logs for step summary
         if: always()
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
@@ -772,7 +774,7 @@ jobs:
       - name: Upload agent artifacts
         if: always()
         continue-on-error: true
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: agent-artifacts
           path: |
@@ -804,7 +806,7 @@ jobs:
       total_count: ${{ steps.missing_tool.outputs.total_count }}
     steps:
       - name: Setup Scripts
-        uses: github/gh-aw/actions/setup@48d8fdfddc8cad854ac0c70ceb573f09fb8f9c9b # v0.62.5
+        uses: github/gh-aw/actions/setup@2c1a237d2048b0e2412e7d7528892ea1257840e2 # v0.74.4
         with:
           destination: /opt/gh-aw/actions
       - name: Download agent output artifact
@@ -820,7 +822,7 @@ jobs:
           echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/safeoutputs/agent_output.json" >> "$GITHUB_ENV"
       - name: Process No-Op Messages
         id: noop
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_NOOP_MAX: 1
@@ -834,7 +836,7 @@ jobs:
             await main();
       - name: Record Missing Tool
         id: missing_tool
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_WORKFLOW_NAME: "Upgrade Python Library"
@@ -847,7 +849,7 @@ jobs:
             await main();
       - name: Handle Agent Failure
         id: handle_agent_failure
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_WORKFLOW_NAME: "Upgrade Python Library"
@@ -865,7 +867,7 @@ jobs:
             await main();
       - name: Handle No-Op Message
         id: handle_noop_message
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_WORKFLOW_NAME: "Upgrade Python Library"
@@ -882,7 +884,7 @@ jobs:
             await main();
       - name: Handle Create Pull Request Error
         id: handle_create_pr_error
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_WORKFLOW_NAME: "Upgrade Python Library"
@@ -896,7 +898,7 @@ jobs:
             await main();
       - name: Update reaction comment with completion status
         id: conclusion
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_COMMENT_ID: ${{ needs.activation.outputs.comment_id }}
@@ -925,7 +927,7 @@ jobs:
       success: ${{ steps.parse_results.outputs.success }}
     steps:
       - name: Setup Scripts
-        uses: github/gh-aw/actions/setup@48d8fdfddc8cad854ac0c70ceb573f09fb8f9c9b # v0.62.5
+        uses: github/gh-aw/actions/setup@2c1a237d2048b0e2412e7d7528892ea1257840e2 # v0.74.4
         with:
           destination: /opt/gh-aw/actions
       - name: Download agent artifacts
@@ -946,7 +948,7 @@ jobs:
         run: |
           echo "Agent output-types: $AGENT_OUTPUT_TYPES"
       - name: Setup threat detection
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           WORKFLOW_NAME: "Upgrade Python Library"
           WORKFLOW_DESCRIPTION: "Pick an out-of-sync Python library from the todo list and upgrade it\nby running `scripts/update_lib quick`, then open a pull request."
@@ -999,7 +1001,7 @@ jobs:
           XDG_CONFIG_HOME: /home/runner
       - name: Parse threat detection results
         id: parse_results
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
@@ -1008,7 +1010,7 @@ jobs:
             await main();
       - name: Upload threat detection log
         if: always()
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: threat-detection.log
           path: /tmp/gh-aw/threat-detection/detection.log
@@ -1037,7 +1039,7 @@ jobs:
       process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }}
     steps:
       - name: Setup Scripts
-        uses: github/gh-aw/actions/setup@48d8fdfddc8cad854ac0c70ceb573f09fb8f9c9b # v0.62.5
+        uses: github/gh-aw/actions/setup@2c1a237d2048b0e2412e7d7528892ea1257840e2 # v0.74.4
         with:
           destination: /opt/gh-aw/actions
       - name: Download agent output artifact
@@ -1079,7 +1081,7 @@ jobs:
           echo "Git configured with standard GitHub Actions identity"
       - name: Process Safe Outputs
         id: process_safe_outputs
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
           GH_AW_SAFE_OUTPUTS_HANDLER_CONFIG: "{\"create_pull_request\":{\"base_branch\":\"${{ github.ref_name }}\",\"draft\":false,\"expires\":30,\"labels\":[\"pylib-sync\"],\"max\":1,\"max_patch_size\":1024,\"title_prefix\":\"Update \"},\"missing_data\":{},\"missing_tool\":{}}"

.github/workflows/upgrade-pylib.md

@@ -52,7 +52,7 @@ cache:
     - cpython-lib-
 
 env:
-  PYTHON_VERSION: "v3.14.3"
+  PYTHON_VERSION: "v3.14.4"
   ISSUE_ID: "6839"
 ---
 

.gitignore

@@ -10,7 +10,6 @@ __pycache__/
 wasm-pack.log
 .idea/
 .envrc
-.python-version
 
 flame-graph.html
 flame.txt
@@ -28,4 +27,4 @@ Lib/site-packages/*
 Lib/test/data/*
 !Lib/test/data/README
 cpython/
-
+.claude/scheduled_tasks.lock

.pre-commit-config.yaml

@@ -10,7 +10,7 @@ repos:
         priority: 0
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.7
+    rev: v0.15.12
     hooks:
       - id: ruff-format
         priority: 0
@@ -40,17 +40,30 @@ repos:
         types: [rust]
         priority: 0
 
-      - id: generate-opcode-metadata
+      - id: generate-rs-opcode-metadata
-        name: generate opcode metadata
+        name: generate rust opcode metadata
-        entry: python scripts/generate_opcode_metadata.py
+        entry: python tools/opcode_metadata/generate_rs_opcode_metadata.py
-        files: '^(crates/compiler-core/src/bytecode/instruction\.rs|scripts/generate_opcode_metadata\.py)$'
+        files: '^(crates/compiler-core/src/bytecode/instruction\.rs|tools/opcode_metadata/*)$'
         pass_filenames: false
         language: system
         require_serial: true
         priority: 1 # so rustfmt runs first
+        stages:
+          - manual
+
+      - id: generate-py-opcode-metadata
+        name: generate python opcode metadata
+        entry: python tools/opcode_metadata/generate_py_opcode_metadata.py
+        files: '^(crates/compiler-core/src/bytecode/instruction\.rs|tools/opcode_metadata/*)$'
+        pass_filenames: false
+        language: system
+        require_serial: true
+        priority: 1 # so rustfmt runs first
+        stages:
+          - manual
 
   - repo: https://github.com/streetsidesoftware/cspell-cli
-    rev: v9.7.0
+    rev: v10.0.0
     hooks:
       - id: cspell
         types: [rust]
@@ -64,7 +77,7 @@ repos:
         priority: 0
 
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: v3.8.1
+    rev: v3.8.3
     hooks:
       - id: prettier
         files: '^wasm/.*$'

.python-version

@@ -0,0 +1 @@
+3.14.5

AGENTS.md

@@ -38,6 +38,12 @@ RustPython is a Python 3 interpreter written in Rust, implementing Python 3.14.0
 - Always ask the user before performing any git operations that affect the remote repository
 - Commits can be created locally when requested, but pushing and PR creation require explicit approval
 
+**CRITICAL: Pre-commit Checks**
+- Before creating ANY commit, you MUST run `prek run --all-files` (or `pre-commit run --all-files`) AND the full test suite. Both must pass — do not commit if either fails.
+- Test commands are documented in the [Testing](#testing) section below. At minimum run `cargo test --workspace --exclude rustpython_wasm --exclude rustpython-venvlauncher`; if the change touches `extra_tests/snippets/` run `pytest -v` there too, and if it touches `Lib/` or interpreter behavior, run the relevant `cargo run --release -- -m test <module>` modules.
+- If a hook auto-fixes files (e.g. `ruff-format`, `rustfmt`), re-stage the fixes, re-run `prek` until it reports a clean pass, then re-run the tests, then commit.
+- NEVER bypass these checks with `--no-verify`, `--no-gpg-sign`, or by skipping tests "because the change is small". If a hook or test fails, fix the underlying issue and create a new commit — do not amend or force the failing commit through.
+
 ## Important Development Notes
 
 ### Running Python Code
@@ -81,6 +87,35 @@ The `Lib/` directory contains Python standard library files copied from the CPyt
   - `unittest.skip("TODO: RustPython <reason>")`
   - `unittest.expectedFailure` with `# TODO: RUSTPYTHON <reason>` comment
 
+#### Choosing the right marker
+
+When marking a test that fails on RustPython, prefer one of the following forms:
+
+```python
+@unittest.expectedFailure  # TODO: RUSTPYTHON; <reason>
+# or
+@unittest.expectedFailureIf(<condition>, "TODO: RUSTPYTHON; <reason>")
+```
+
+If the test would crash the interpreter (segfault, Rust panic, abort, infinite loop), use `skip` instead so the rest of the suite can still run:
+
+```python
+@unittest.skip("TODO: RUSTPYTHON; <reason>")
+# or
+@unittest.skipIf(<condition>, "TODO: RUSTPYTHON; <reason>")
+```
+
+**When to use which:**
+
+- **Prefer `expectedFailure` / `expectedFailureIf`** by default. The test body still runs, so if RustPython is later fixed, the unexpected pass surfaces immediately and the decorator can be removed. Use the conditional `*If` form when the failure is environment-specific (e.g., a platform or build flag).
+- **Use `skip` / `skipIf` only when running the test would take down the test process** — segfaults, Rust panics, aborts, or hangs that block subsequent tests. Skipping keeps the suite usable; `expectedFailure` cannot help here, because the test body still executes.
+
+To find WIP entries that are partly modified and may need follow-up:
+
+```bash
+grep -d recurse 'TODO: RUSTPYTHON' Lib/test/
+```
+
 ### Clean Build
 
 When you modify bytecode instructions, a full clean is required:
@@ -129,6 +164,7 @@ Run `./scripts/whats_left.py` to get a list of unimplemented methods, which is h
 
 - Do not delete or rewrite existing comments unless they are factually wrong or directly contradict the new code.
 - Do not add decorative section separators (e.g. `// -----------`, `// ===`, `/* *** */`). Use `///` doc-comments or short `//` comments only when they add value.
+- Do not put `///` doc comments on items annotated with `#[pyattr]`, `#[pyclass]`, or `#[pyfunction]`. The derive macros pull authoritative docstrings from CPython via the `rustpython-doc` crate; a Rust doc comment overrides that source, and on `#[pyattr]` it is silently dropped.
 
 #### Avoid Duplicate Code in Branches
 
@@ -258,9 +294,14 @@ See DEVELOPMENT.md "CPython Version Upgrade Checklist" section.
 - Document that it requires PEP 695 support
 - Focus on tests that can be fixed through Rust code changes only
 
+## CI Workflows
+
+If you modify any file under `.github/workflows/`, the change must pass a [zizmor](https://docs.zizmor.sh/) scan in CI.
+
 ## Documentation
 
 - Check the [architecture document](/architecture/architecture.md) for a high-level overview
 - Read the [development guide](/DEVELOPMENT.md) for detailed setup instructions
 - Generate documentation with `cargo doc --no-deps --all`
 - Online documentation is available at [docs.rs/rustpython](https://docs.rs/rustpython/)
+- [How to update test files](https://github.com/RustPython/RustPython/wiki/How-to-update-test-files#checkout-cpython-source-code-initial-setup) — guide for syncing test cases from upstream CPython into the `Lib/` directory

CONTRIBUTING.md

@@ -1,4 +1,28 @@
-# RustPython Development Guide and Tips
+# Contributing to RustPython
+
+Contributions are more than welcome, and in many cases we are happy to guide
+contributors through PRs or on [**Discord**](https://discord.gg/vru8NypEhv).
+
+## Finding ways to help
+
+We label issues that would be good for a first time contributor as [`good first issue`](https://github.com/RustPython/RustPython/issues?q=label%3A%22good+first+issue%22+is%3Aissue+is%3Aopen+).
+Also checkout the [issue tracker](https://github.com/RustPython/RustPython/issues) for all open issues. 
+
+You can enhance CPython compatibility by increasing our unittest coverage, you can see [This pinned issue](https://github.com/RustPython/RustPython/issues/6839) to see which libs and tests need be updated to our current supported python version.
+
+Another approach is to checkout the source code: builtin functions and object
+methods are often the simplest and easiest way to contribute.
+
+You can also simply run `python -I scripts/whats_left.py` to assist in finding any unimplemented method.
+
+## Use of AI
+
+We **require all use of AI in contributions to follow our
+[AI Policy](https://github.com/RustPython/.github/blob/main/AI_POLICY.md)**.
+
+If your contribution does not follow the policy, it will be closed.
+
+## RustPython Development Guide and Tips
 
 RustPython attracts developers with interest and experience in Rust, Python,
 or WebAssembly. Whether you are familiar with Rust, Python, or 

Cargo.toml

@@ -10,7 +10,8 @@ repository.workspace = true
 license.workspace = true
 
 [features]
-default = ["threading", "stdlib", "stdio", "importlib", "ssl-rustls", "host_env"]
+capi = ["dep:rustpython-capi", "threading"]
+default = ["threading", "stdlib", "stdio", "importlib", "ssl-rustls-aws-lc", "host_env"]
 host_env = ["rustpython-vm/host_env", "rustpython-stdlib?/host_env"]
 importlib = ["rustpython-vm/importlib"]
 encodings = ["rustpython-vm/encodings"]
@@ -21,30 +22,35 @@ freeze-stdlib = ["stdlib", "rustpython-vm/freeze-stdlib", "rustpython-pylib?/fre
 jit = ["rustpython-vm/jit"]
 threading = ["rustpython-vm/threading", "rustpython-stdlib/threading"]
 sqlite = ["rustpython-stdlib/sqlite"]
-ssl = []
+ssl = ["host_env"]
 ssl-rustls = ["ssl", "rustpython-stdlib/ssl-rustls"]
+ssl-rustls-aws-lc = ["ssl-rustls", "dep:rustls", "rustls/aws_lc_rs"]
+ssl-rustls-aws-lc-fips = ["ssl-rustls-aws-lc", "rustls/fips"]
 ssl-openssl = ["ssl", "rustpython-stdlib/ssl-openssl"]
-ssl-vendor = ["ssl-openssl", "rustpython-stdlib/ssl-vendor"]
+ssl-openssl-vendor = ["ssl-openssl", "rustpython-stdlib/ssl-openssl-vendor"]
 tkinter = ["rustpython-stdlib/tkinter"]
 
 [build-dependencies]
 winresource = "0.1"
 
 [dependencies]
+rustpython-capi = { workspace = true, optional = true }
 rustpython-compiler = { workspace = true }
 rustpython-pylib = { workspace = true, optional = true }
 rustpython-stdlib = { workspace = true, optional = true, features = ["compiler"] }
 rustpython-vm = { workspace = true, features = ["compiler", "gc"] }
 
-cfg-if = { workspace = true }
 log = { workspace = true }
 flame = { workspace = true, optional = true }
 
 lexopt = "0.3"
-dirs = { package = "dirs-next", version = "2.0" }
+dirs = "6"
 env_logger = "0.11"
 flamescope = { version = "0.1.2", optional = true }
 
+rustls = { workspace = true, optional = true }
+rustls-graviola = { workspace = true, optional = true }
+
 [target.'cfg(windows)'.dependencies]
 libc = { workspace = true }
 
@@ -53,7 +59,7 @@ rustyline = { workspace = true }
 
 [dev-dependencies]
 criterion = { workspace = true }
-pyo3 = { version = "0.28.2", features = ["auto-initialize"] }
+pyo3 = { workspace = true, features = ["auto-initialize"] }
 rustpython-stdlib = { workspace = true }
 ruff_python_parser = { workspace = true }
 
@@ -69,6 +75,17 @@ harness = false
 name = "rustpython"
 path = "src/main.rs"
 
+[[example]]
+name = "custom_tls_providers"
+path = "examples/custom_tls_providers.rs"
+required-features = [
+    "rustls-graviola",
+    "rustls/ring",
+    "rustpython-pylib/freeze-stdlib",
+    "rustpython-stdlib/ssl-rustls",
+    "rustpython-vm/freeze-stdlib",
+]
+
 [profile.dev.package."*"]
 opt-level = 3
 
@@ -136,15 +153,17 @@ exclude = ["pymath"]
 version = "0.5.0"
 authors = ["RustPython Team"]
 edition = "2024"
-rust-version = "1.93.0"
+rust-version = "1.95.0"
 repository = "https://github.com/RustPython/RustPython"
 license = "MIT"
 
 [workspace.dependencies]
+rustpython-capi = { path = "crates/capi", version = "0.5.0" }
 rustpython-compiler-core = { path = "crates/compiler-core", version = "0.5.0" }
 rustpython-compiler = { path = "crates/compiler", version = "0.5.0" }
 rustpython-codegen = { path = "crates/codegen", version = "0.5.0" }
 rustpython-common = { path = "crates/common", version = "0.5.0" }
+rustpython-host_env = { path = "crates/host_env", version = "0.5.0" }
 rustpython-derive = { path = "crates/derive", version = "0.5.0" }
 rustpython-derive-impl = { path = "crates/derive-impl", version = "0.5.0" }
 rustpython-jit = { path = "crates/jit", version = "0.5.0" }
@@ -170,66 +189,141 @@ ruff_source_file = { package = "rustpython-ruff_source_file", version = "0.15.8"
 # ruff_text_size = { git = "https://github.com/astral-sh/ruff.git", rev = "c2a8815842f9dc5d24ec19385eae0f1a7188b0d9" }
 # ruff_source_file = { git = "https://github.com/astral-sh/ruff.git", rev = "c2a8815842f9dc5d24ec19385eae0f1a7188b0d9" }
 
+der = { version = "0.8", features = ["alloc", "oid", "pem", "zeroize"] }
 phf = { version = "0.13.1", default-features = false, features = ["macros"]}
-ahash = "0.8.12"
+adler32 = "1.2.0"
+approx = "0.5.1"
 ascii = "1.1"
+base64 = "0.22"
+blake2 = "0.10.4"
 bitflags = "2.11.0"
 bitflagset = "0.0.3"
 bstr = "1"
-cfg-if = "1.0"
+bzip2 = "0.6"
-chrono = { version = "0.4.44", default-features = false, features = ["clock", "oldtime", "std"] }
+chrono = { version = "0.4.44", default-features = false, features = ["clock", "std"] }
+console_error_panic_hook = "0.1"
 constant_time_eq = "0.4"
+cranelift = "0.131.2"
+cranelift-jit = "0.131.2"
+cranelift-module = "0.131.0"
+crc32fast = "1.3.2"
 criterion = { version = "0.8", features = ["html_reports"] }
 crossbeam-utils = "0.8.21"
+csv-core = "0.1.11"
+digest = "0.10.7"
+dns-lookup = "3.0"
+dyn-clone = "1.0.10"
+exitcode = "1.1.2"
 flame = "0.2.2"
+flamer = "0.5"
+flate2 = { version = "1.1.9", default-features = false }
+# Bump only when the openssl crate bumps it
+foreign-types-shared = "0.1"
+gethostname = "1.0.2"
 getrandom = { version = "0.3", features = ["std"] }
 glob = "0.3"
+half = "2"
 hex = "0.4.3"
-indexmap = { version = "2.13.0", features = ["std"] }
+hexf-parse = "0.2.1"
-insta = "1.46"
+hmac = "0.12"
+indexmap = { version = "2.14.0", features = ["std"] }
+insta = "1.47"
 itertools = "0.14.0"
 is-macro = "0.3.7"
+js-sys = "0.3"
 junction = "1.4.2"
-libc = "0.2.183"
+lexical-parse-float = "1.0.6"
+libc = "0.2.186"
 libffi = "5"
+libloading = "0.9"
+liblzma = "0.4"
+liblzma-sys = "0.4"
+libsqlite3-sys = "0.37"
+libz-rs-sys = "0.6"
+lock_api = "0.4"
 log = "0.4.29"
-nix = { version = "0.30", features = ["fs", "user", "process", "term", "time", "signal", "ioctl", "socket", "sched", "zerocopy", "dir", "hostname", "net", "poll"] }
+lz4_flex = "0.13"
+nix = { version = "0.31", features = ["fs", "user", "process", "term", "time", "signal", "ioctl", "socket", "sched", "zerocopy", "dir", "hostname", "net", "poll"] }
+mac_address = "1.1.3"
 malachite-bigint = "0.9.1"
 malachite-q = "0.9.1"
 malachite-base = "0.9.1"
+md-5 = "0.10.1"
 memchr = "2.8.0"
+memmap2 = "0.9.10"
+mt19937 = "<=3.2"  # upgrade it once rand is upgraded
 num-complex = "0.4.6"
 num-integer = "0.1.46"
 num-traits = "0.2"
+num_cpus = "1.17.0"
 num_enum = { version = "0.7", default-features = false }
+oid-registry = "0.8"
+openssl = "0.10.80"
+openssl-sys = "0.9.110"
+openssl-probe = "0.2.1"
 optional = "0.5"
 parking_lot = "0.12.3"
 paste = "1.0.15"
+pbkdf2 = "0.12"
+pem-rfc7468 = "1.0"
+pkcs8 = "0.11"
 proc-macro2 = "1.0.105"
+psm = "0.1"
 pymath = { version = "0.2.0", features = ["mul_add", "malachite-bigint", "complex"] }
+pyo3 = "0.28"
 quote = "1.0.45"
 radium = "1.1.1"
 rand = "0.9"
 rand_core = { version = "0.9", features = ["os_rng"] }
-rustix = { version = "1.1", features = ["event"] }
+rapidhash = "4.4.1"
-rustyline = "17.0.1"
+result-like = "0.5.0"
+rustix = { version = "1.1", features = ["event", "param", "system"] }
+rustls = { version = "0.23.39", default-features = false }
+rustls-graviola = "0.3"
+rustls-native-certs = "0.8"
+rustls-pemfile = "2.2"
+rustls-platform-verifier = "0.7"
+rustyline = "18"
 serde = { package = "serde_core", version = "1.0.225", default-features = false, features = ["alloc"] }
 schannel = "0.1.29"
-scoped-tls = "1"
 scopeguard = "1"
+serde-wasm-bindgen = "0.6.5"
+sha-1 = "0.10.0"
+sha2 = "0.10.2"
+sha3 = "0.10.1"
+siphasher = "1"
+socket2 = "0.6.3"
 static_assertions = "1.1"
 strum = "0.28"
 strum_macros = "0.28"
 syn = "2"
+syn-ext = "0.5.0"
+system-configuration = "0.7.0"
+tcl-sys = { git = "https://github.com/arihant2math/tkinter.git", tag = "v0.2.0" }
+textwrap = { version = "0.16.2", default-features = false }
+termios = "0.3.3"
 thiserror = "2.0"
+timsort = "0.1.2"
+tk-sys = { git = "https://github.com/arihant2math/tkinter.git", tag = "v0.2.0" }
+icu_casemap = "2"
+icu_locale = "2"
 icu_properties = "2"
 icu_normalizer = "2"
-unicode-casing = "0.1.1"
+uuid = "1.23.1"
+ucd = "0.1.1"
 unic-ucd-age = "0.9.0"
 unicode_names2 = "2.0.0"
 widestring = "1.2.0"
 windows-sys = "0.61.2"
 wasm-bindgen = "0.2.106"
+wasm-bindgen-futures = "0.4"
+web-sys = "0.3"
+webpki-roots = "1.0"
+which = "8"
+x509-cert = "0.2.5"
+x509-parser = "0.18"
+xml = "1.2"
+writeable = "0.6"
 
 # Lints
 
@@ -237,13 +331,61 @@ wasm-bindgen = "0.2.106"
 unsafe_code = "allow"
 unsafe_op_in_unsafe_fn = "deny"
 elided_lifetimes_in_paths = "warn"
+unreachable_pub = "warn"
 
 [workspace.lints.clippy]
+correctness = { level = "warn", priority = -2 }
+suspicious = { level = "warn", priority = -2 }
+perf = { level = "warn", priority = -2 }
+style = { level = "warn", priority = -2 }
+complexity = { level = "warn", priority = -2 }
+# pedantic = { level = "warn", priority = -2 } # TODO: Enable this
+
+missing_errors_doc = "allow" # Too many errors. No auto-fix available
+missing_panics_doc = "allow" # Too many errors. No auto-fix available
+match_same_arms = "allow" # Not always more readable
+if_not_else = "allow" # Not always more readable
+single_match_else = "allow"
+similar_names = "allow"
+
+# restriction lints
 alloc_instead_of_core = "warn"
+cfg_not_test = "warn"
+redundant_test_prefix = "warn"
 std_instead_of_alloc = "warn"
 std_instead_of_core = "warn"
-perf = "warn"
+tests_outside_test_module = "warn"
-style = "warn"
+
-complexity = "warn"
+# nursery lints to enforce gradually
-suspicious = "warn"
+debug_assert_with_mut_call = "warn"
-correctness = "warn"
+derive_partial_eq_without_eq = "warn"
+imprecise_flops = "warn"
+or_fun_call = "warn"
+redundant_clone = "warn"
+search_is_some = "warn"
+single_option_map = "warn"
+trait_duplication_in_bounds = "warn"
+unused_peekable = "warn"
+unused_rounding = "warn"
+use_self = "warn"
+useless_let_if_seq = "warn"
+
+# pedantic lints to enforce gradually
+cloned_instead_of_copied = "warn"
+collapsible_else_if = "warn"
+comparison_chain = "warn"
+explicit_into_iter_loop = "warn"
+explicit_iter_loop = "warn"
+filter_map_next = "warn"
+flat_map_option = "warn"
+format_collect = "warn"
+from_iter_instead_of_collect = "warn"
+inconsistent_struct_constructor = "warn"
+inefficient_to_string = "warn"
+manual_is_variant_and = "warn"
+map_unwrap_or = "warn"
+must_use_candidate = "warn"
+redundant_else = "warn"
+uninlined_format_args = "warn"
+unnecessary_wraps = "warn"
+unnested_or_patterns = "warn"

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2025 RustPython Team
+Copyright (c) 2026 RustPython Team
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

Lib/_android_support.py

@@ -168,6 +168,13 @@ class Logcat:
         # message.
         message = message.replace(b"\x00", b"\xc0\x80")
 
+        # On API level 30 and higher, Logcat will strip any number of leading
+        # newlines. This is visible in all `logcat` modes, even --binary. Work
+        # around this by adding a leading space, which shouldn't make any
+        # difference to the log's usability.
+        if message.startswith(b"\n"):
+            message = b" " + message
+
         with self._lock:
             now = time()
             self._bucket_level += (

Lib/_opcode_metadata.py

@@ -1,4 +1,4 @@
-# This file is generated by scripts/generate_opcode_metadata.py
+# This file is generated by tools/opcode_metadata/generate_py_opcode_metadata.py
 # for RustPython bytecode format (CPython 3.14 compatible opcode numbers).
 # Do not edit!
 

Lib/annotationlib.py

@@ -47,6 +47,7 @@ _SLOTS = (
     "__cell__",
     "__owner__",
     "__stringifier_dict__",
+    "__resolved_str_cache__",
 )
 
 
@@ -94,6 +95,7 @@ class ForwardRef:
         # value later.
         self.__code__ = None
         self.__ast_node__ = None
+        self.__resolved_str_cache__ = None
 
     def __init_subclass__(cls, /, *args, **kwds):
         raise TypeError("Cannot subclass ForwardRef")
@@ -113,7 +115,7 @@ class ForwardRef:
         """
         match format:
             case Format.STRING:
-                return self.__forward_arg__
+                return self.__resolved_str__
             case Format.VALUE:
                 is_forwardref_format = False
             case Format.FORWARDREF:
@@ -258,6 +260,24 @@ class ForwardRef:
             "Attempted to access '__forward_arg__' on an uninitialized ForwardRef"
         )
 
+    @property
+    def __resolved_str__(self):
+        # __forward_arg__ with any names from __extra_names__ replaced
+        # with the type_repr of the value they represent
+        if self.__resolved_str_cache__ is None:
+            resolved_str = self.__forward_arg__
+            names = self.__extra_names__
+
+            if names:
+                visitor = _ExtraNameFixer(names)
+                ast_expr = ast.parse(resolved_str, mode="eval").body
+                node = visitor.visit(ast_expr)
+                resolved_str = ast.unparse(node)
+
+            self.__resolved_str_cache__ = resolved_str
+
+        return self.__resolved_str_cache__
+
     @property
     def __forward_code__(self):
         if self.__code__ is not None:
@@ -321,7 +341,7 @@ class ForwardRef:
             extra.append(", is_class=True")
         if self.__owner__ is not None:
             extra.append(f", owner={self.__owner__!r}")
-        return f"ForwardRef({self.__forward_arg__!r}{''.join(extra)})"
+        return f"ForwardRef({self.__resolved_str__!r}{''.join(extra)})"
 
 
 _Template = type(t"")
@@ -357,6 +377,7 @@ class _Stringifier:
         self.__cell__ = cell
         self.__owner__ = owner
         self.__stringifier_dict__ = stringifier_dict
+        self.__resolved_str_cache__ = None  # Needed for ForwardRef
 
     def __convert_to_ast(self, other):
         if isinstance(other, _Stringifier):
@@ -919,7 +940,7 @@ def get_annotations(
     does not exist, the __annotate__ function is called. The
     FORWARDREF format uses __annotations__ if it exists and can be
     evaluated, and otherwise falls back to calling the __annotate__ function.
-    The SOURCE format tries __annotate__ first, and falls back to
+    The STRING format tries __annotate__ first, and falls back to
     using __annotations__, stringified using annotations_to_string().
 
     This function handles several details for you:
@@ -1037,13 +1058,26 @@ def get_annotations(
             obj_globals = obj_locals = unwrap = None
 
         if unwrap is not None:
+            # Use an id-based visited set to detect cycles in the __wrapped__
+            # and functools.partial.func chain (e.g. f.__wrapped__ = f).
+            # On cycle detection we stop and use whatever __globals__ we have
+            # found so far, mirroring the approach of inspect.unwrap().
+            _seen_ids = {id(unwrap)}
             while True:
                 if hasattr(unwrap, "__wrapped__"):
-                    unwrap = unwrap.__wrapped__
+                    candidate = unwrap.__wrapped__
+                    if id(candidate) in _seen_ids:
+                        break
+                    _seen_ids.add(id(candidate))
+                    unwrap = candidate
                     continue
                 if functools := sys.modules.get("functools"):
                     if isinstance(unwrap, functools.partial):
-                        unwrap = unwrap.func
+                        candidate = unwrap.func
+                        if id(candidate) in _seen_ids:
+                            break
+                        _seen_ids.add(id(candidate))
+                        unwrap = candidate
                         continue
                 break
             if hasattr(unwrap, "__globals__"):
@@ -1150,3 +1184,14 @@ def _get_dunder_annotations(obj):
     if not isinstance(ann, dict):
         raise ValueError(f"{obj!r}.__annotations__ is neither a dict nor None")
     return ann
+
+
+class _ExtraNameFixer(ast.NodeTransformer):
+    """Fixer for __extra_names__ items in ForwardRef __repr__ and string evaluation"""
+    def __init__(self, extra_names):
+        self.extra_names = extra_names
+
+    def visit_Name(self, node: ast.Name):
+        if (new_name := self.extra_names.get(node.id, _sentinel)) is not _sentinel:
+            node = ast.Name(id=type_repr(new_name))
+        return node

Lib/argparse.py

@@ -149,6 +149,10 @@ def _copy_items(items):
     return copy.copy(items)
 
 
+def _identity(value):
+    return value
+
+
 # ===============
 # Formatting Help
 # ===============
@@ -200,7 +204,7 @@ class HelpFormatter(object):
             self._decolor = decolor
         else:
             self._theme = get_theme(force_no_color=True).argparse
-            self._decolor = lambda text: text
+            self._decolor = _identity
 
     # ===============================
     # Section and indentation methods
@@ -1903,9 +1907,7 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer):
         self._subparsers = None
 
         # register types
-        def identity(string):
+        self.register('type', None, _identity)
-            return string
-        self.register('type', None, identity)
 
         # add help argument if necessary
         # (using explicit default to override global argument_default)
@@ -2676,7 +2678,7 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer):
 
         if value not in choices:
             args = {'value': str(value),
-                    'choices': ', '.join(map(str, action.choices))}
+                    'choices': ', '.join(repr(str(choice)) for choice in action.choices)}
             msg = _('invalid choice: %(value)r (choose from %(choices)s)')
 
             if self.suggest_on_error and isinstance(value, str):

Lib/collections/_defaultdict.py

@@ -17,6 +17,10 @@ class defaultdict(dict):
             val = self.default_factory()
         else:
             raise KeyError(key)
+        # CPython parity: a recursive __missing__ via factory() may have
+        # already populated key; preserve that value instead of overwriting.
+        if key in self:
+            return self[key]
         self[key] = val
         return val
 

Lib/configparser.py

@@ -315,12 +315,15 @@ class ParsingError(Error):
 
     def append(self, lineno, line):
         self.errors.append((lineno, line))
-        self.message += '\n\t[line %2d]: %s' % (lineno, repr(line))
+        self.message += f'\n\t[line {lineno:2d}]: {line!r}'
 
     def combine(self, others):
+        messages = [self.message]
         for other in others:
-            for error in other.errors:
+            for lineno, line in other.errors:
-                self.append(*error)
+                self.errors.append((lineno, line))
+                messages.append(f'\n\t[line {lineno:2d}]: {line!r}')
+        self.message = "".join(messages)
         return self
 
     @staticmethod
@@ -613,7 +616,9 @@ class RawConfigParser(MutableMapping):
         \]                                 # ]
         """
     _OPT_TMPL = r"""
-        (?P<option>.*?)                    # very permissive!
+        (?P<option>                        # very permissive!
+            (?:(?!{delim})\S)*             # non-delimiter non-whitespace
+            (?:\s+(?:(?!{delim})\S)+)*)    # optionally more words
         \s*(?P<vi>{delim})\s*              # any number of space/tab,
                                            # followed by any of the
                                            # allowed delimiters,
@@ -621,7 +626,9 @@ class RawConfigParser(MutableMapping):
         (?P<value>.*)$                     # everything up to eol
         """
     _OPT_NV_TMPL = r"""
-        (?P<option>.*?)                    # very permissive!
+        (?P<option>                        # very permissive!
+            (?:(?!{delim})\S)*             # non-delimiter non-whitespace
+            (?:\s+(?:(?!{delim})\S)+)*)    # optionally more words
         \s*(?:                             # any number of space/tab,
         (?P<vi>{delim})\s*                 # optionally followed by
                                            # any of the allowed

Lib/ctypes/__init__.py

@@ -470,6 +470,8 @@ class CDLL(object):
                 if name and name.endswith(")") and ".a(" in name:
                     mode |= _os.RTLD_MEMBER | _os.RTLD_NOW
             self._name = name
+            if handle is not None:
+                return handle
             return _dlopen(name, mode)
 
     def __repr__(self):

Lib/ctypes/util.py

@@ -85,15 +85,10 @@ if os.name == "nt":
         wintypes.DWORD,
     )
 
-    _psapi = ctypes.WinDLL('psapi', use_last_error=True)
+    # gh-145307: We defer loading psapi.dll until _get_module_handles is called.
-    _enum_process_modules = _psapi["EnumProcessModules"]
+    # Loading additional DLLs at startup for functionality that may never be
-    _enum_process_modules.restype = wintypes.BOOL
+    # used is wasteful.
-    _enum_process_modules.argtypes = (
+    _enum_process_modules = None
-        wintypes.HANDLE,
-        ctypes.POINTER(wintypes.HMODULE),
-        wintypes.DWORD,
-        wintypes.LPDWORD,
-    )
 
     def _get_module_filename(module: wintypes.HMODULE):
         name = (wintypes.WCHAR * 32767)() # UNICODE_STRING_MAX_CHARS
@@ -101,8 +96,19 @@ if os.name == "nt":
             return name.value
         return None
 
-
     def _get_module_handles():
+        global _enum_process_modules
+        if _enum_process_modules is None:
+            _psapi = ctypes.WinDLL('psapi', use_last_error=True)
+            _enum_process_modules = _psapi["EnumProcessModules"]
+            _enum_process_modules.restype = wintypes.BOOL
+            _enum_process_modules.argtypes = (
+                wintypes.HANDLE,
+                ctypes.POINTER(wintypes.HMODULE),
+                wintypes.DWORD,
+                wintypes.LPDWORD,
+            )
+
         process = _get_current_process()
         space_needed = wintypes.DWORD()
         n = 1024

Lib/dataclasses.py

@@ -725,10 +725,10 @@ def _init_fn(fields, std_fields, kw_only_fields, frozen, has_post_init,
                         annotation_fields=annotation_fields)
 
 
-def _frozen_get_del_attr(cls, fields, func_builder):
+def _frozen_set_del_attr(cls, fields, func_builder):
-    locals = {'cls': cls,
+    locals = {'__class__': cls,
               'FrozenInstanceError': FrozenInstanceError}
-    condition = 'type(self) is cls'
+    condition = 'type(self) is __class__'
     if fields:
         condition += ' or name in {' + ', '.join(repr(f.name) for f in fields) + '}'
 
@@ -736,14 +736,14 @@ def _frozen_get_del_attr(cls, fields, func_builder):
                         ('self', 'name', 'value'),
                         (f'  if {condition}:',
                           '   raise FrozenInstanceError(f"cannot assign to field {name!r}")',
-                         f'  super(cls, self).__setattr__(name, value)'),
+                         f'  super(__class__, self).__setattr__(name, value)'),
                         locals=locals,
                         overwrite_error=True)
     func_builder.add_fn('__delattr__',
                         ('self', 'name'),
                         (f'  if {condition}:',
                           '   raise FrozenInstanceError(f"cannot delete field {name!r}")',
-                         f'  super(cls, self).__delattr__(name)'),
+                         f'  super(__class__, self).__delattr__(name)'),
                         locals=locals,
                         overwrite_error=True)
 
@@ -1199,7 +1199,7 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen,
                             overwrite_error='Consider using functools.total_ordering')
 
     if frozen:
-        _frozen_get_del_attr(cls, field_list, func_builder)
+        _frozen_set_del_attr(cls, field_list, func_builder)
 
     # Decide if/how we're going to create a hash function.
     hash_action = _hash_action[bool(unsafe_hash),
@@ -1292,10 +1292,18 @@ def _update_func_cell_for__class__(f, oldcls, newcls):
         # This function doesn't reference __class__, so nothing to do.
         return False
     # Fix the cell to point to the new class, if it's already pointing
-    # at the old class.  I'm not convinced that the "is oldcls" test
+    # at the old class.
-    # is needed, but other than performance can't hurt.
     closure = f.__closure__[idx]
-    if closure.cell_contents is oldcls:
+
+    try:
+        contents = closure.cell_contents
+    except ValueError:
+        # Cell is empty
+        return False
+
+    # This check makes it so we avoid updating an incorrect cell if the
+    # class body contains a function that was defined in a different class.
+    if contents is oldcls:
         closure.cell_contents = newcls
         return True
     return False

Lib/email/__init__.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2007 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/_encoded_words.py

@@ -219,7 +219,7 @@ def encode(string, charset='utf-8', encoding=None, lang=''):
 
     """
     if charset == 'unknown-8bit':
-        bstring = string.encode('ascii', 'surrogateescape')
+        bstring = string.encode('utf-8', 'surrogateescape')
     else:
         bstring = string.encode(charset)
     if encoding is None:

Lib/email/_header_value_parser.py

@@ -80,7 +80,8 @@ from email import utils
 # Useful constants and functions
 #
 
-WSP = set(' \t')
+_WSP = ' \t'
+WSP = set(_WSP)
 CFWS_LEADER = WSP | set('(')
 SPECIALS = set(r'()<>@,:;.\"[]')
 ATOM_ENDS = SPECIALS | WSP
@@ -101,6 +102,12 @@ def make_quoted_pairs(value):
     return str(value).replace('\\', '\\\\').replace('"', '\\"')
 
 
+def make_parenthesis_pairs(value):
+    """Escape parenthesis and backslash for use within a comment."""
+    return str(value).replace('\\', '\\\\') \
+        .replace('(', '\\(').replace(')', '\\)')
+
+
 def quote_string(value):
     escaped = make_quoted_pairs(value)
     return f'"{escaped}"'
@@ -632,11 +639,11 @@ class LocalPart(TokenList):
         for tok in self[0] + [DOT]:
             if tok.token_type == 'cfws':
                 continue
-            if (last_is_tl and tok.token_type == 'dot' and
+            if (last_is_tl and tok.token_type == 'dot' and last and
                     last[-1].token_type == 'cfws'):
                 res[-1] = TokenList(last[:-1])
             is_tl = isinstance(tok, TokenList)
-            if (is_tl and last.token_type == 'dot' and
+            if (is_tl and last.token_type == 'dot' and tok and
                     tok[0].token_type == 'cfws'):
                 res.append(TokenList(tok[1:]))
             else:
@@ -874,6 +881,12 @@ class MessageID(MsgID):
 class InvalidMessageID(MessageID):
     token_type = 'invalid-message-id'
 
+class MessageIDList(TokenList):
+    token_type = 'message-id-list'
+
+    @property
+    def message_ids(self):
+        return [x for x in self if x.token_type=='msg-id']
 
 class Header(TokenList):
     token_type = 'header'
@@ -933,7 +946,7 @@ class WhiteSpaceTerminal(Terminal):
         return ' '
 
     def startswith_fws(self):
-        return True
+        return self and self[0] in WSP
 
 
 class ValueTerminal(Terminal):
@@ -1232,8 +1245,7 @@ def get_bare_quoted_string(value):
     bare_quoted_string = BareQuotedString()
     value = value[1:]
     if value and value[0] == '"':
-        token, value = get_qcontent(value)
+        return bare_quoted_string, value[1:]
-        bare_quoted_string.append(token)
     while value and value[0] != '"':
         if value[0] in WSP:
             token, value = get_fws(value)
@@ -2046,12 +2058,10 @@ def get_address_list(value):
                 address_list.defects.append(errors.InvalidHeaderDefect(
                     "invalid address in address-list"))
         if value and value[0] != ',':
-            # Crap after address; treat it as an invalid mailbox.
+            # Crap after address: add it to the address list
-            # The mailbox info will still be available.
+            # as an invalid mailbox
-            mailbox = address_list[-1][0]
-            mailbox.token_type = 'invalid-mailbox'
             token, value = get_invalid_mailbox(value, ',')
-            mailbox.extend(token)
+            address_list.append(Address([token]))
             address_list.defects.append(errors.InvalidHeaderDefect(
                 "invalid address in address-list"))
         if value:  # Must be a , at this point.
@@ -2171,6 +2181,32 @@ def parse_message_id(value):
 
     return message_id
 
+def parse_message_ids(value):
+    """in-reply-to     =   "In-Reply-To:" 1*msg-id CRLF
+       references      =   "References:" 1*msg-id CRLF
+    """
+    message_id_list = MessageIDList()
+    while value:
+        if value[0] == ',':
+            # message id list separated with commas - this is invalid,
+            # but happens rather frequently in the wild
+            message_id_list.defects.append(
+                errors.InvalidHeaderDefect("comma in msg-id list"))
+            message_id_list.append(
+                WhiteSpaceTerminal(' ', 'invalid-comma-replacement'))
+            value = value[1:]
+            continue
+        try:
+            token, value = get_msg_id(value)
+            message_id_list.append(token)
+        except errors.HeaderParseError as ex:
+            token = get_unstructured(value)
+            message_id_list.append(InvalidMessageID(token))
+            message_id_list.defects.append(
+                errors.InvalidHeaderDefect("Invalid msg-id: {!r}".format(ex)))
+            break
+    return message_id_list
+
 #
 # XXX: As I begin to add additional header parsers, I'm realizing we probably
 # have two level of parser routines: the get_XXX methods that get a token in
@@ -2788,8 +2824,12 @@ def _steal_trailing_WSP_if_exists(lines):
     if lines and lines[-1] and lines[-1][-1] in WSP:
         wsp = lines[-1][-1]
         lines[-1] = lines[-1][:-1]
+        # gh-142006: if the line is now empty, remove it entirely.
+        if not lines[-1]:
+            lines.pop()
     return wsp
 
+
 def _refold_parse_tree(parse_tree, *, policy):
     """Return string of contents of parse_tree folded according to RFC rules.
 
@@ -2798,11 +2838,9 @@ def _refold_parse_tree(parse_tree, *, policy):
     maxlen = policy.max_line_length or sys.maxsize
     encoding = 'utf-8' if policy.utf8 else 'us-ascii'
     lines = ['']  # Folded lines to be output
-    leading_whitespace = ''  # When we have whitespace between two encoded
+    last_word_is_ew = False
-                             # words, we may need to encode the whitespace
+    last_ew = None  # if there is an encoded word in the last line of lines,
-                             # at the beginning of the second word.
+                    # points to the encoded word's first character
-    last_ew = None  # Points to the last encoded character if there's an ew on
-                    # the line
     last_charset = None
     wrap_as_ew_blocked = 0
     want_encoding = False  # This is set to True if we need to encode this part
@@ -2837,6 +2875,7 @@ def _refold_parse_tree(parse_tree, *, policy):
         if part.token_type == 'mime-parameters':
             # Mime parameter folding (using RFC2231) is extra special.
             _fold_mime_parameters(part, lines, maxlen, encoding)
+            last_word_is_ew = False
             continue
 
         if want_encoding and not wrap_as_ew_blocked:
@@ -2853,6 +2892,7 @@ def _refold_parse_tree(parse_tree, *, policy):
                             # XXX what if encoded_part has no leading FWS?
                             lines.append(newline)
                         lines[-1] += encoded_part
+                        last_word_is_ew = False
                         continue
                 # Either this is not a major syntactic break, so we don't
                 # want it on a line by itself even if it fits, or it
@@ -2871,11 +2911,16 @@ def _refold_parse_tree(parse_tree, *, policy):
                     (last_charset == 'unknown-8bit' or
                      last_charset == 'utf-8' and charset != 'us-ascii')):
                     last_ew = None
-                last_ew = _fold_as_ew(tstr, lines, maxlen, last_ew,
+                last_ew = _fold_as_ew(
-                                      part.ew_combine_allowed, charset, leading_whitespace)
+                    tstr,
-                # This whitespace has been added to the lines in _fold_as_ew()
+                    lines,
-                # so clear it now.
+                    maxlen,
-                leading_whitespace = ''
+                    last_ew,
+                    part.ew_combine_allowed,
+                    charset,
+                    last_word_is_ew,
+                )
+                last_word_is_ew = True
                 last_charset = charset
                 want_encoding = False
                 continue
@@ -2888,28 +2933,19 @@ def _refold_parse_tree(parse_tree, *, policy):
 
         if len(tstr) <= maxlen - len(lines[-1]):
             lines[-1] += tstr
+            last_word_is_ew = last_word_is_ew and not bool(tstr.strip(_WSP))
             continue
 
         # This part is too long to fit.  The RFC wants us to break at
         # "major syntactic breaks", so unless we don't consider this
         # to be one, check if it will fit on the next line by itself.
-        leading_whitespace = ''
         if (part.syntactic_break and
                 len(tstr) + 1 <= maxlen):
             newline = _steal_trailing_WSP_if_exists(lines)
             if newline or part.startswith_fws():
-                # We're going to fold the data onto a new line here.  Due to
-                # the way encoded strings handle continuation lines, we need to
-                # be prepared to encode any whitespace if the next line turns
-                # out to start with an encoded word.
                 lines.append(newline + tstr)
-
+                last_word_is_ew = (last_word_is_ew
-                whitespace_accumulator = []
+                                   and not bool(lines[-1].strip(_WSP)))
-                for char in lines[-1]:
-                    if char not in WSP:
-                        break
-                    whitespace_accumulator.append(char)
-                leading_whitespace = ''.join(whitespace_accumulator)
                 last_ew = None
                 continue
         if not hasattr(part, 'encode'):
@@ -2924,6 +2960,13 @@ def _refold_parse_tree(parse_tree, *, policy):
                     [ValueTerminal(make_quoted_pairs(p), 'ptext')
                      for p in newparts] +
                     [ValueTerminal('"', 'ptext')])
+            if part.token_type == 'comment':
+                newparts = (
+                    [ValueTerminal('(', 'ptext')] +
+                    [ValueTerminal(make_parenthesis_pairs(p), 'ptext')
+                     if p.token_type == 'ptext' else p
+                     for p in newparts] +
+                    [ValueTerminal(')', 'ptext')])
             if not part.as_ew_allowed:
                 wrap_as_ew_blocked += 1
                 newparts.append(end_ew_not_allowed)
@@ -2942,10 +2985,11 @@ def _refold_parse_tree(parse_tree, *, policy):
         else:
             # We can't fold it onto the next line either...
             lines[-1] += tstr
+        last_word_is_ew = last_word_is_ew and not bool(tstr.strip(_WSP))
 
     return policy.linesep.join(lines) + policy.linesep
 
-def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset, leading_whitespace):
+def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset, last_word_is_ew):
     """Fold string to_encode into lines as encoded word, combining if allowed.
     Return the new value for last_ew, or None if ew_combine_allowed is False.
 
@@ -2960,6 +3004,16 @@ def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset,
         to_encode = str(
             get_unstructured(lines[-1][last_ew:] + to_encode))
         lines[-1] = lines[-1][:last_ew]
+    elif last_word_is_ew:
+        # If we are following up an encoded word with another encoded word,
+        # any white space between the two will be ignored when decoded.
+        # Therefore, we encode all to-be-displayed whitespace in the second
+        # encoded word.
+        len_without_wsp = len(lines[-1].rstrip(_WSP))
+        leading_whitespace = lines[-1][len_without_wsp:]
+        lines[-1] = (lines[-1][:len_without_wsp]
+                     + (' ' if leading_whitespace else ''))
+        to_encode = leading_whitespace + to_encode
     elif to_encode[0] in WSP:
         # We're joining this to non-encoded text, so don't encode
         # the leading blank.
@@ -2988,20 +3042,13 @@ def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset,
 
     while to_encode:
         remaining_space = maxlen - len(lines[-1])
-        text_space = remaining_space - chrome_len - len(leading_whitespace)
+        text_space = remaining_space - chrome_len
         if text_space <= 0:
-            lines.append(' ')
+            newline = _steal_trailing_WSP_if_exists(lines)
+            lines.append(newline or ' ')
+            new_last_ew = len(lines[-1])
             continue
 
-        # If we are at the start of a continuation line, prepend whitespace
-        # (we only want to do this when the line starts with an encoded word
-        # but if we're folding in this helper function, then we know that we
-        # are going to be writing out an encoded word.)
-        if len(lines) > 1 and len(lines[-1]) == 1 and leading_whitespace:
-            encoded_word = _ew.encode(leading_whitespace, charset=encode_as)
-            lines[-1] += encoded_word
-            leading_whitespace = ''
-
         to_encode_word = to_encode[:text_space]
         encoded_word = _ew.encode(to_encode_word, charset=encode_as)
         excess = len(encoded_word) - remaining_space
@@ -3013,7 +3060,6 @@ def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset,
             excess = len(encoded_word) - remaining_space
         lines[-1] += encoded_word
         to_encode = to_encode[len(to_encode_word):]
-        leading_whitespace = ''
 
         if to_encode:
             lines.append(' ')

Lib/email/_parseaddr.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2002-2007 Python Software Foundation
+# Copyright (C) 2002 Python Software Foundation
 # Contact: email-sig@python.org
 
 """Email address parsing code.
@@ -225,7 +225,7 @@ class AddrlistClass:
     def __init__(self, field):
         """Initialize a new instance.
 
-        `field' is an unparsed address header field, containing
+        'field' is an unparsed address header field, containing
         one or more addresses.
         """
         self.specials = '()<>@,:;.\"[]'
@@ -426,14 +426,14 @@ class AddrlistClass:
     def getdelimited(self, beginchar, endchars, allowcomments=True):
         """Parse a header fragment delimited by special characters.
 
-        `beginchar' is the start character for the fragment.
+        'beginchar' is the start character for the fragment.
-        If self is not looking at an instance of `beginchar' then
+        If self is not looking at an instance of 'beginchar' then
         getdelimited returns the empty string.
 
-        `endchars' is a sequence of allowable end-delimiting characters.
+        'endchars' is a sequence of allowable end-delimiting characters.
         Parsing stops when one of these is encountered.
 
-        If `allowcomments' is non-zero, embedded RFC 2822 comments are allowed
+        If 'allowcomments' is non-zero, embedded RFC 2822 comments are allowed
         within the parsed fragment.
         """
         if self.field[self.pos] != beginchar:
@@ -477,7 +477,7 @@ class AddrlistClass:
 
         Optional atomends specifies a different set of end token delimiters
         (the default is to use self.atomends).  This is used e.g. in
-        getphraselist() since phrase endings must not include the `.' (which
+        getphraselist() since phrase endings must not include the '.' (which
         is legal in phrases)."""
         atomlist = ['']
         if atomends is None:

Lib/email/_policybase.py

@@ -4,6 +4,7 @@ Allows fine grained feature control of how the package parses and emits data.
 """
 
 import abc
+import re
 from email import header
 from email import charset as _charset
 from email.utils import _has_surrogates
@@ -14,6 +15,14 @@ __all__ = [
     'compat32',
     ]
 
+# validation regex from RFC 5322, equivalent to pattern re.compile("[!-9;-~]+$")
+valid_header_name_re = re.compile("[\041-\071\073-\176]+$")
+
+def validate_header_name(name):
+    # Validate header name according to RFC 5322
+    if not valid_header_name_re.match(name):
+        raise ValueError(
+            f"Header field name contains invalid characters: {name!r}")
 
 class _PolicyBase:
 
@@ -150,7 +159,7 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
                            wrapping is done.  Default is 78.
 
     mangle_from_        -- a flag that, when True escapes From_ lines in the
-                           body of the message by putting a `>' in front of
+                           body of the message by putting a '>' in front of
                            them. This is used when the message is being
                            serialized by a generator. Default: False.
 
@@ -314,6 +323,7 @@ class Compat32(Policy):
         """+
         The name and value are returned unmodified.
         """
+        validate_header_name(name)
         return (name, value)
 
     def header_fetch_parse(self, name, value):

Lib/email/base64mime.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2002-2007 Python Software Foundation
+# Copyright (C) 2002 Python Software Foundation
 # Author: Ben Gertzfield
 # Contact: email-sig@python.org
 
@@ -15,7 +15,7 @@ This module provides an interface to encode and decode both headers and bodies
 with Base64 encoding.
 
 RFC 2045 defines a method for including character set information in an
-`encoded-word' in a header.  This method is commonly used for 8-bit real names
+'encoded-word' in a header.  This method is commonly used for 8-bit real names
 in To:, From:, Cc:, etc. fields, as well as Subject: lines.
 
 This module does not do the line wrapping or end-of-line character conversion

Lib/email/charset.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2007 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Ben Gertzfield, Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -175,7 +175,7 @@ class Charset:
     module expose the following information about a character set:
 
     input_charset: The initial character set specified.  Common aliases
-                   are converted to their `official' email names (e.g. latin_1
+                   are converted to their 'official' email names (e.g. latin_1
                    is converted to iso-8859-1).  Defaults to 7-bit us-ascii.
 
     header_encoding: If the character set must be encoded before it can be
@@ -245,7 +245,7 @@ class Charset:
     def get_body_encoding(self):
         """Return the content-transfer-encoding used for body encoding.
 
-        This is either the string `quoted-printable' or `base64' depending on
+        This is either the string 'quoted-printable' or 'base64' depending on
         the encoding used, or it is a function in which case you should call
         the function with a single argument, the Message object being
         encoded.  The function should then set the Content-Transfer-Encoding

Lib/email/encoders.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/errors.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/feedparser.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2004-2006 Python Software Foundation
+# Copyright (C) 2004 Python Software Foundation
 # Authors: Baxter, Wouters and Warsaw
 # Contact: email-sig@python.org
 
@@ -30,7 +30,7 @@ from io import StringIO
 
 NLCRE = re.compile(r'\r\n|\r|\n')
 NLCRE_bol = re.compile(r'(\r\n|\r|\n)')
-NLCRE_eol = re.compile(r'(\r\n|\r|\n)\Z')
+NLCRE_eol = re.compile(r'(\r\n|\r|\n)\z')
 NLCRE_crack = re.compile(r'(\r\n|\r|\n)')
 # RFC 5322 section 3.6.8 Optional fields.  ftext is %d33-57 / %d59-126, Any character
 # except controls, SP, and ":".
@@ -504,10 +504,9 @@ class FeedParser:
                     self._input.unreadline(line)
                     return
                 else:
-                    # Weirdly placed unix-from line.  Note this as a defect
+                    # Weirdly placed unix-from line.
-                    # and ignore it.
                     defect = errors.MisplacedEnvelopeHeaderDefect(line)
-                    self._cur.defects.append(defect)
+                    self.policy.handle_defect(self._cur, defect)
                     continue
             # Split the line on the colon separating field name from value.
             # There will always be a colon, because if there wasn't the part of
@@ -519,7 +518,7 @@ class FeedParser:
             # message. Track the error but keep going.
             if i == 0:
                 defect = errors.InvalidHeaderDefect("Missing header name.")
-                self._cur.defects.append(defect)
+                self.policy.handle_defect(self._cur, defect)
                 continue
 
             assert i>0, "_parse_headers fed line with no : and no leading WS"

Lib/email/generator.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2010 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -22,6 +22,7 @@ NL = '\n'  # XXX: no longer used by the code below.
 NLCRE = re.compile(r'\r\n|\r|\n')
 fcre = re.compile(r'^From ', re.MULTILINE)
 NEWLINE_WITHOUT_FWSP = re.compile(r'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
+NEWLINE_WITHOUT_FWSP_BYTES = re.compile(br'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
 
 
 class Generator:
@@ -43,7 +44,7 @@ class Generator:
 
         Optional mangle_from_ is a flag that, when True (the default if policy
         is not set), escapes From_ lines in the body of the message by putting
-        a `>' in front of them.
+        a '>' in front of them.
 
         Optional maxheaderlen specifies the longest length for a non-continued
         header.  When a header line is longer (in characters, with tabs
@@ -76,7 +77,7 @@ class Generator:
 
         unixfrom is a flag that forces the printing of a Unix From_ delimiter
         before the first object in the message tree.  If the original message
-        has no From_ delimiter, a `standard' one is crafted.  By default, this
+        has no From_ delimiter, a 'standard' one is crafted.  By default, this
         is False to inhibit the printing of any From_ delimiter.
 
         Note that for subobjects, no From_ line is printed.
@@ -227,7 +228,7 @@ class Generator:
             folded = self.policy.fold(h, v)
             if self.policy.verify_generated_headers:
                 linesep = self.policy.linesep
-                if not folded.endswith(self.policy.linesep):
+                if not folded.endswith(linesep):
                     raise HeaderWriteError(
                         f'folded header does not end with {linesep!r}: {folded!r}')
                 if NEWLINE_WITHOUT_FWSP.search(folded.removesuffix(linesep)):
@@ -391,7 +392,7 @@ class Generator:
         b = boundary
         counter = 0
         while True:
-            cre = cls._compile_re('^--' + re.escape(b) + '(--)?$', re.MULTILINE)
+            cre = cls._compile_re('^--' + re.escape(b) + '(--)?\r?$', re.MULTILINE)
             if not cre.search(text):
                 break
             b = boundary + '.' + str(counter)
@@ -429,7 +430,16 @@ class BytesGenerator(Generator):
         # This is almost the same as the string version, except for handling
         # strings with 8bit bytes.
         for h, v in msg.raw_items():
-            self._fp.write(self.policy.fold_binary(h, v))
+            folded = self.policy.fold_binary(h, v)
+            if self.policy.verify_generated_headers:
+                linesep = self.policy.linesep.encode()
+                if not folded.endswith(linesep):
+                    raise HeaderWriteError(
+                        f'folded header does not end with {linesep!r}: {folded!r}')
+                if NEWLINE_WITHOUT_FWSP_BYTES.search(folded.removesuffix(linesep)):
+                    raise HeaderWriteError(
+                        f'folded header contains newline: {folded!r}')
+            self._fp.write(folded)
         # A blank line always separates headers from body
         self.write(self._NL)
 
@@ -467,7 +477,7 @@ class DecodedGenerator(Generator):
         argument is allowed.
 
         Walks through all subparts of a message.  If the subpart is of main
-        type `text', then it prints the decoded payload of the subpart.
+        type 'text', then it prints the decoded payload of the subpart.
 
         Otherwise, fmt is a format string that is used instead of the message
         payload.  fmt is expanded with the following keywords (in

Lib/email/header.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2002-2007 Python Software Foundation
+# Copyright (C) 2002 Python Software Foundation
 # Author: Ben Gertzfield, Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -201,7 +201,7 @@ class Header:
 
         The maximum line length can be specified explicitly via maxlinelen. For
         splitting the first line to a shorter value (to account for the field
-        header which isn't included in s, e.g. `Subject') pass in the name of
+        header which isn't included in s, e.g. 'Subject') pass in the name of
         the field in header_name.  The default maxlinelen is 78 as recommended
         by RFC 2822.
 
@@ -285,7 +285,7 @@ class Header:
         output codec of the charset.  If the string cannot be encoded to the
         output codec, a UnicodeError will be raised.
 
-        Optional `errors' is passed as the errors argument to the decode
+        Optional 'errors' is passed as the errors argument to the decode
         call if s is a byte string.
         """
         if charset is None:
@@ -335,7 +335,7 @@ class Header:
 
         Optional splitchars is a string containing characters which should be
         given extra weight by the splitting algorithm during normal header
-        wrapping.  This is in very rough support of RFC 2822's `higher level
+        wrapping.  This is in very rough support of RFC 2822's 'higher level
         syntactic breaks':  split points preceded by a splitchar are preferred
         during line splitting, with the characters preferred in the order in
         which they appear in the string.  Space and tab may be included in the

Lib/email/headerregistry.py

@@ -534,6 +534,18 @@ class MessageIDHeader:
         kwds['defects'].extend(parse_tree.all_defects)
 
 
+class ReferencesHeader:
+
+    max_count = 1
+    value_parser = staticmethod(parser.parse_message_ids)
+
+    @classmethod
+    def parse(cls, value, kwds):
+        kwds['parse_tree'] = parse_tree = cls.value_parser(value)
+        kwds['decoded'] = str(parse_tree)
+        kwds['defects'].extend(parse_tree.all_defects)
+
+
 # The header factory #
 
 _default_header_map = {
@@ -557,6 +569,8 @@ _default_header_map = {
     'content-disposition':          ContentDispositionHeader,
     'content-transfer-encoding':    ContentTransferEncodingHeader,
     'message-id':                   MessageIDHeader,
+    'in-reply-to':                  ReferencesHeader,
+    'references':                   ReferencesHeader,
     }
 
 class HeaderRegistry:

Lib/email/iterators.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -43,8 +43,8 @@ def body_line_iterator(msg, decode=False):
 def typed_subpart_iterator(msg, maintype='text', subtype=None):
     """Iterate over the subparts with a given MIME type.
 
-    Use `maintype' as the main MIME type to match against; this defaults to
+    Use 'maintype' as the main MIME type to match against; this defaults to
-    "text".  Optional `subtype' is the MIME subtype to match against; if
+    "text".  Optional 'subtype' is the MIME subtype to match against; if
     omitted, only the main type is matched.
     """
     for subpart in msg.walk():

Lib/email/message.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2007 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -21,7 +21,7 @@ Charset = _charset.Charset
 
 SEMISPACE = '; '
 
-# Regular expression that matches `special' characters in parameters, the
+# Regular expression that matches 'special' characters in parameters, the
 # existence of which force quoting of the parameter value.
 tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]')
 
@@ -147,7 +147,7 @@ class Message:
     multipart or a message/rfc822), then the payload is a list of Message
     objects, otherwise it is a string.
 
-    Message objects implement part of the `mapping' interface, which assumes
+    Message objects implement part of the 'mapping' interface, which assumes
     there is exactly one occurrence of the header per message.  Some headers
     do in fact appear multiple times (e.g. Received) and for those headers,
     you must use the explicit API to set or get all the headers.  Not all of
@@ -609,7 +609,7 @@ class Message:
         """Return the message's content type.
 
         The returned string is coerced to lower case of the form
-        `maintype/subtype'.  If there was no Content-Type header in the
+        'maintype/subtype'.  If there was no Content-Type header in the
         message, the default type as given by get_default_type() will be
         returned.  Since according to RFC 2045, messages always have a default
         type this will always return a value.
@@ -632,7 +632,7 @@ class Message:
     def get_content_maintype(self):
         """Return the message's main content type.
 
-        This is the `maintype' part of the string returned by
+        This is the 'maintype' part of the string returned by
         get_content_type().
         """
         ctype = self.get_content_type()
@@ -641,14 +641,14 @@ class Message:
     def get_content_subtype(self):
         """Returns the message's sub-content type.
 
-        This is the `subtype' part of the string returned by
+        This is the 'subtype' part of the string returned by
         get_content_type().
         """
         ctype = self.get_content_type()
         return ctype.split('/')[1]
 
     def get_default_type(self):
-        """Return the `default' content type.
+        """Return the 'default' content type.
 
         Most messages have a default content type of text/plain, except for
         messages that are subparts of multipart/digest containers.  Such
@@ -657,7 +657,7 @@ class Message:
         return self._default_type
 
     def set_default_type(self, ctype):
-        """Set the `default' content type.
+        """Set the 'default' content type.
 
         ctype should be either "text/plain" or "message/rfc822", although this
         is not enforced.  The default content type is not stored in the
@@ -690,8 +690,8 @@ class Message:
         """Return the message's Content-Type parameters, as a list.
 
         The elements of the returned list are 2-tuples of key/value pairs, as
-        split on the `=' sign.  The left hand side of the `=' is the key,
+        split on the '=' sign.  The left hand side of the '=' is the key,
-        while the right hand side is the value.  If there is no `=' sign in
+        while the right hand side is the value.  If there is no '=' sign in
         the parameter the value is the empty string.  The value is as
         described in the get_param() method.
 
@@ -851,9 +851,9 @@ class Message:
         """Return the filename associated with the payload if present.
 
         The filename is extracted from the Content-Disposition header's
-        `filename' parameter, and it is unquoted.  If that header is missing
+        'filename' parameter, and it is unquoted.  If that header is missing
-        the `filename' parameter, this method falls back to looking for the
+        the 'filename' parameter, this method falls back to looking for the
-        `name' parameter.
+        'name' parameter.
         """
         missing = object()
         filename = self.get_param('filename', missing, 'content-disposition')
@@ -866,7 +866,7 @@ class Message:
     def get_boundary(self, failobj=None):
         """Return the boundary associated with the payload if present.
 
-        The boundary is extracted from the Content-Type header's `boundary'
+        The boundary is extracted from the Content-Type header's 'boundary'
         parameter, and it is unquoted.
         """
         missing = object()

Lib/email/mime/application.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Keith Dart
 # Contact: email-sig@python.org
 

Lib/email/mime/audio.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2007 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Anthony Baxter
 # Contact: email-sig@python.org
 

Lib/email/mime/base.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/mime/image.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/mime/message.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/mime/multipart.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2002-2006 Python Software Foundation
+# Copyright (C) 2002 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -21,7 +21,7 @@ class MIMEMultipart(MIMEBase):
         Content-Type and MIME-Version headers.
 
         _subtype is the subtype of the multipart content type, defaulting to
-        `mixed'.
+        'mixed'.
 
         boundary is the multipart boundary string.  By default it is
         calculated as needed.

Lib/email/mime/nonmultipart.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2002-2006 Python Software Foundation
+# Copyright (C) 2002 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/mime/text.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 

Lib/email/parser.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2007 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw, Thomas Wouters, Anthony Baxter
 # Contact: email-sig@python.org
 

Lib/email/policy.py

@@ -4,7 +4,13 @@ code that adds all the email6 features.
 
 import re
 import sys
-from email._policybase import Policy, Compat32, compat32, _extend_docstrings
+from email._policybase import (
+    Compat32,
+    Policy,
+    _extend_docstrings,
+    compat32,
+    validate_header_name
+)
 from email.utils import _has_surrogates
 from email.headerregistry import HeaderRegistry as HeaderRegistry
 from email.contentmanager import raw_data_manager
@@ -138,6 +144,7 @@ class EmailPolicy(Policy):
         CR or LF characters.
 
         """
+        validate_header_name(name)
         if hasattr(value, 'name') and value.name.lower() == name.lower():
             return (name, value)
         if isinstance(value, str) and len(value.splitlines())>1:

Lib/email/quoprimime.py

@@ -1,11 +1,11 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Ben Gertzfield
 # Contact: email-sig@python.org
 
 """Quoted-printable content transfer encoding per RFCs 2045-2047.
 
 This module handles the content transfer encoding method defined in RFC 2045
-to encode US ASCII-like 8-bit data called `quoted-printable'.  It is used to
+to encode US ASCII-like 8-bit data called 'quoted-printable'.  It is used to
 safely encode text that is in a character set similar to the 7-bit US ASCII
 character set, but that includes some 8-bit characters that are normally not
 allowed in email bodies or headers.
@@ -17,7 +17,7 @@ This module provides an interface to encode and decode both headers and bodies
 with quoted-printable encoding.
 
 RFC 2045 defines a method for including character set information in an
-`encoded-word' in a header.  This method is commonly used for 8-bit real names
+'encoded-word' in a header.  This method is commonly used for 8-bit real names
 in To:/From:/Cc: etc. fields, as well as Subject: lines.
 
 This module does not do the line wrapping or end-of-line character
@@ -127,7 +127,7 @@ def quote(c):
 def header_encode(header_bytes, charset='iso-8859-1'):
     """Encode a single header line with quoted-printable (like) encoding.
 
-    Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
+    Defined in RFC 2045, this 'Q' encoding is similar to quoted-printable, but
     used specifically for email header fields to allow charsets with mostly 7
     bit characters (and some 8 bit) to remain more or less readable in non-RFC
     2045 aware mail clients.
@@ -272,7 +272,7 @@ def decode(encoded, eol=NL):
                 decoded += eol
     # Special case if original string did not end with eol
     if encoded[-1] not in '\r\n' and decoded.endswith(eol):
-        decoded = decoded[:-1]
+        decoded = decoded[:-len(eol)]
     return decoded
 
 
@@ -290,7 +290,7 @@ def _unquote_match(match):
 
 # Header decoding is done a bit differently
 def header_decode(s):
-    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.
+    """Decode a string encoded with RFC 2045 MIME header 'Q' encoding.
 
     This function does not parse a full MIME header value encoded with
     quoted-printable (like =?iso-8859-1?q?Hello_World?=) -- please use

Lib/email/utils.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2010 Python Software Foundation
+# Copyright (C) 2001 Python Software Foundation
 # Author: Barry Warsaw
 # Contact: email-sig@python.org
 
@@ -472,23 +472,15 @@ def collapse_rfc2231_value(value, errors='replace',
 # better than not having it.
 #
 
-def localtime(dt=None, isdst=None):
+def localtime(dt=None):
     """Return local time as an aware datetime object.
 
     If called without arguments, return current time.  Otherwise *dt*
     argument should be a datetime instance, and it is converted to the
     local time zone according to the system time zone database.  If *dt* is
     naive (that is, dt.tzinfo is None), it is assumed to be in local time.
-    The isdst parameter is ignored.
 
     """
-    if isdst is not None:
-        import warnings
-        warnings._deprecated(
-            "The 'isdst' parameter to 'localtime'",
-            message='{name} is deprecated and slated for removal in Python {remove}',
-            remove=(3, 14),
-            )
     if dt is None:
         dt = datetime.datetime.now()
     return dt.astimezone()

Lib/encodings/__init__.py

@@ -33,6 +33,7 @@ import sys
 from . import aliases
 
 _cache = {}
+_MAXCACHE = 500
 _unknown = '--unknown--'
 _import_tail = ['*']
 _aliases = aliases.aliases
@@ -115,6 +116,8 @@ def search_function(encoding):
 
     if mod is None:
         # Cache misses
+        if len(_cache) >= _MAXCACHE:
+            _cache.clear()
         _cache[encoding] = None
         return None
 
@@ -136,6 +139,8 @@ def search_function(encoding):
         entry = codecs.CodecInfo(*entry)
 
     # Cache the codec registry entry
+    if len(_cache) >= _MAXCACHE:
+        _cache.clear()
     _cache[encoding] = entry
 
     # Register its aliases (without overwriting previously registered

Lib/ensurepip/__init__.py

@@ -10,13 +10,14 @@ from shutil import copy2
 
 
 __all__ = ["version", "bootstrap"]
-_PIP_VERSION = "25.3"
+_PIP_VERSION = "26.1.1"
 
 # Directory of system wheel packages. Some Linux distribution packaging
 # policies recommend against bundling dependencies. For example, Fedora
 # installs wheel packages in the /usr/share/python-wheels/ directory and don't
 # install the ensurepip._bundled package.
-if (_pkg_dir := sysconfig.get_config_var('WHEEL_PKG_DIR')) is not None:
+_pkg_dir = sysconfig.get_config_var('WHEEL_PKG_DIR')
+if _pkg_dir:
     _WHEEL_PKG_DIR = Path(_pkg_dir).resolve()
 else:
     _WHEEL_PKG_DIR = None

Lib/glob.py

@@ -15,7 +15,7 @@ __all__ = ["glob", "iglob", "escape", "translate"]
 
 def glob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
         include_hidden=False):
-    """Return a list of paths matching a pathname pattern.
+    """Return a list of paths matching a `pathname` pattern.
 
     The pattern may contain simple shell-style wildcards a la
     fnmatch. Unlike fnmatch, filenames starting with a
@@ -25,6 +25,15 @@ def glob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
     The order of the returned list is undefined. Sort it if you need a
     particular order.
 
+    If `root_dir` is not None, it should be a path-like object specifying the
+    root directory for searching. It has the same effect as changing the
+    current directory before calling it (without actually
+    changing it). If pathname is relative, the result will contain
+    paths relative to `root_dir`.
+
+    If `dir_fd` is not None, it should be a file descriptor referring to a
+    directory, and paths will then be relative to that directory.
+
     If `include_hidden` is true, the patterns '*', '?', '**'  will match hidden
     directories.
 
@@ -36,7 +45,7 @@ def glob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
 
 def iglob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
           include_hidden=False):
-    """Return an iterator which yields the paths matching a pathname pattern.
+    """Return an iterator which yields the paths matching a `pathname` pattern.
 
     The pattern may contain simple shell-style wildcards a la
     fnmatch. However, unlike fnmatch, filenames starting with a
@@ -46,7 +55,19 @@ def iglob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
     The order of the returned paths is undefined. Sort them if you need a
     particular order.
 
-    If recursive is true, the pattern '**' will match any files and
+    If `root_dir` is not None, it should be a path-like object specifying
+    the root directory for searching. It has the same effect as changing
+    the current directory before calling it (without actually
+    changing it). If pathname is relative, the result will contain
+    paths relative to `root_dir`.
+
+    If `dir_fd` is not None, it should be a file descriptor referring to a
+    directory, and paths will then be relative to that directory.
+
+    If `include_hidden` is true, the patterns '*', '?', '**'  will match hidden
+    directories.
+
+    If `recursive` is true, the pattern '**' will match any files and
     zero or more directories and subdirectories.
     """
     sys.audit("glob.glob", pathname, recursive)

Lib/http/client.py

@@ -972,13 +972,22 @@ class HTTPConnection:
         return ip
 
     def _tunnel(self):
+        if _contains_disallowed_url_pchar_re.search(self._tunnel_host):
+            raise ValueError('Tunnel host can\'t contain control characters %r'
+                             % (self._tunnel_host,))
         connect = b"CONNECT %s:%d %s\r\n" % (
             self._wrap_ipv6(self._tunnel_host.encode("idna")),
             self._tunnel_port,
             self._http_vsn_str.encode("ascii"))
         headers = [connect]
         for header, value in self._tunnel_headers.items():
-            headers.append(f"{header}: {value}\r\n".encode("latin-1"))
+            header_bytes = header.encode("latin-1")
+            value_bytes = value.encode("latin-1")
+            if not _is_legal_header_name(header_bytes):
+                raise ValueError('Invalid header name %r' % (header_bytes,))
+            if _is_illegal_header_value(value_bytes):
+                raise ValueError('Invalid header value %r' % (value_bytes,))
+            headers.append(b"%s: %s\r\n" % (header_bytes, value_bytes))
         headers.append(b"\r\n")
         # Making a single send() call instead of one per line encourages
         # the host OS to use a more optimal packet size instead of

Lib/http/cookies.py

@@ -337,9 +337,16 @@ class Morsel(dict):
             key = key.lower()
             if key not in self._reserved:
                 raise CookieError("Invalid attribute %r" % (key,))
+            if _has_control_character(key, val):
+                raise CookieError("Control characters are not allowed in "
+                                  f"cookies {key!r} {val!r}")
             data[key] = val
         dict.update(self, data)
 
+    def __ior__(self, values):
+        self.update(values)
+        return self
+
     def isReservedKey(self, K):
         return K.lower() in self._reserved
 
@@ -365,9 +372,15 @@ class Morsel(dict):
         }
 
     def __setstate__(self, state):
-        self._key = state['key']
+        key = state['key']
-        self._value = state['value']
+        value = state['value']
-        self._coded_value = state['coded_value']
+        coded_value = state['coded_value']
+        if _has_control_character(key, value, coded_value):
+            raise CookieError("Control characters are not allowed in cookies "
+                              f"{key!r} {value!r} {coded_value!r}")
+        self._key = key
+        self._value = value
+        self._coded_value = coded_value
 
     def output(self, attrs=None, header="Set-Cookie:"):
         return "%s %s" % (header, self.OutputString(attrs))
@@ -378,14 +391,21 @@ class Morsel(dict):
         return '<%s: %s>' % (self.__class__.__name__, self.OutputString())
 
     def js_output(self, attrs=None):
+        import base64
         # 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")
         return """
         <script type="text/javascript">
         <!-- begin hiding
-        document.cookie = \"%s\";
+        document.cookie = atob(\"%s\");
         // end hiding -->
         </script>
-        """ % (self.OutputString(attrs).replace('"', r'\"'))
+        """ % (output_encoded,)
 
     def OutputString(self, attrs=None):
         # Build up our result

Lib/inspect.py

@@ -1,7 +1,7 @@
 """Get useful information from live Python objects.
 
 This module encapsulates the interface provided by the internal special
-attributes (co_*, im_*, tb_*, etc.) in a friendlier fashion.
+attributes (co_*, tb_*, etc.) in a friendlier fashion.
 It also provides some help for examining source code and class layout.
 
 Here are some of the useful functions provided by this module:
@@ -2660,11 +2660,12 @@ class Parameter:
         The annotation for the parameter if specified.  If the
         parameter has no annotation, this attribute is set to
         `Parameter.empty`.
-    * kind : str
+    * kind
         Describes how argument values are bound to the parameter.
         Possible values: `Parameter.POSITIONAL_ONLY`,
         `Parameter.POSITIONAL_OR_KEYWORD`, `Parameter.VAR_POSITIONAL`,
         `Parameter.KEYWORD_ONLY`, `Parameter.VAR_KEYWORD`.
+        Every value has a `description` attribute describing meaning.
     """
 
     __slots__ = ('_name', '_kind', '_default', '_annotation')

Lib/logging/__init__.py

@@ -1475,8 +1475,6 @@ class Logger(Filterer):
     level, and "input.csv", "input.xls" and "input.gnu" for the sub-levels.
     There is no arbitrary limit to the depth of nesting.
     """
-    _tls = threading.local()
-
     def __init__(self, name, level=NOTSET):
         """
         Initialize the logger with a name and an optional level.
@@ -1673,19 +1671,14 @@ class Logger(Filterer):
         This method is used for unpickled records received from a socket, as
         well as those created locally. Logger-level filtering is applied.
         """
-        if self._is_disabled():
+        if self.disabled:
             return
-
+        maybe_record = self.filter(record)
-        self._tls.in_progress = True
+        if not maybe_record:
-        try:
+            return
-            maybe_record = self.filter(record)
+        if isinstance(maybe_record, LogRecord):
-            if not maybe_record:
+            record = maybe_record
-                return
+        self.callHandlers(record)
-            if isinstance(maybe_record, LogRecord):
-                record = maybe_record
-            self.callHandlers(record)
-        finally:
-            self._tls.in_progress = False
 
     def addHandler(self, hdlr):
         """
@@ -1773,7 +1766,7 @@ class Logger(Filterer):
         """
         Is this logger enabled for level 'level'?
         """
-        if self._is_disabled():
+        if self.disabled:
             return False
 
         try:
@@ -1823,11 +1816,6 @@ class Logger(Filterer):
                        if isinstance(item, Logger) and item.parent is self and
                        _hierlevel(item) == 1 + _hierlevel(item.parent))
 
-    def _is_disabled(self):
-        # We need to use getattr as it will only be set the first time a log
-        # message is recorded on any given thread
-        return self.disabled or getattr(self._tls, 'in_progress', False)
-
     def __repr__(self):
         level = getLevelName(self.getEffectiveLevel())
         return '<%s %s (%s)>' % (self.__class__.__name__, self.name, level)
@@ -1864,9 +1852,9 @@ class LoggerAdapter(object):
 
     def __init__(self, logger, extra=None, merge_extra=False):
         """
-        Initialize the adapter with a logger and a dict-like object which
+        Initialize the adapter with a logger and an optional dict-like object
-        provides contextual information. This constructor signature allows
+        which provides contextual information. This constructor signature
-        easy stacking of LoggerAdapters, if so desired.
+        allows easy stacking of LoggerAdapters, if so desired.
 
         You can effectively pass keyword arguments as shown in the
         following example:
@@ -1897,8 +1885,9 @@ class LoggerAdapter(object):
         Normally, you'll only need to override this one method in a
         LoggerAdapter subclass for your specific needs.
         """
-        if self.merge_extra and "extra" in kwargs:
+        if self.merge_extra and kwargs.get("extra") is not None:
-            kwargs["extra"] = {**self.extra, **kwargs["extra"]}
+            if self.extra is not None:
+                kwargs["extra"] = {**self.extra, **kwargs["extra"]}
         else:
             kwargs["extra"] = self.extra
         return msg, kwargs

Lib/logging/config.py

@@ -865,6 +865,8 @@ class DictConfigurator(BaseConfigurator):
             else:
                 factory = klass
         kwargs = {k: config[k] for k in config if (k != '.' and valid_ident(k))}
+        # When deprecation ends for using the 'strm' parameter, remove the
+        # "except TypeError ..."
         try:
             result = factory(**kwargs)
         except TypeError as te:
@@ -876,6 +878,15 @@ class DictConfigurator(BaseConfigurator):
             #(e.g. by Django)
             kwargs['strm'] = kwargs.pop('stream')
             result = factory(**kwargs)
+
+            import warnings
+            warnings.warn(
+                "Support for custom logging handlers with the 'strm' argument "
+                "is deprecated and scheduled for removal in Python 3.16. "
+                "Define handlers with the 'stream' argument instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
         if formatter:
             result.setFormatter(formatter)
         if level is not None:
@@ -1006,7 +1017,8 @@ def listen(port=DEFAULT_LOGGING_CONFIG_PORT, verify=None):
         A simple TCP socket-based logging config receiver.
         """
 
-        allow_reuse_address = 1
+        allow_reuse_address = True
+        allow_reuse_port = False
 
         def __init__(self, host='localhost', port=DEFAULT_LOGGING_CONFIG_PORT,
                      handler=None, ready=None, verify=None):

Lib/logging/handlers.py

@@ -196,7 +196,11 @@ class RotatingFileHandler(BaseRotatingHandler):
         if self.stream is None:                 # delay was set...
             self.stream = self._open()
         if self.maxBytes > 0:                   # are we rolling over?
-            pos = self.stream.tell()
+            try:
+                pos = self.stream.tell()
+            except io.UnsupportedOperation:
+                # gh-143237: Never rollover a named pipe.
+                return False
             if not pos:
                 # gh-116263: Never rollover an empty file
                 return False
@@ -855,7 +859,7 @@ class SysLogHandler(logging.Handler):
     }
 
     def __init__(self, address=('localhost', SYSLOG_UDP_PORT),
-                 facility=LOG_USER, socktype=None):
+                 facility=LOG_USER, socktype=None, timeout=None):
         """
         Initialize a handler.
 
@@ -872,6 +876,7 @@ class SysLogHandler(logging.Handler):
         self.address = address
         self.facility = facility
         self.socktype = socktype
+        self.timeout = timeout
         self.socket = None
         self.createSocket()
 
@@ -933,6 +938,8 @@ class SysLogHandler(logging.Handler):
                 err = sock = None
                 try:
                     sock = socket.socket(af, socktype, proto)
+                    if self.timeout:
+                        sock.settimeout(self.timeout)
                     if socktype == socket.SOCK_STREAM:
                         sock.connect(sa)
                     break
@@ -1529,6 +1536,19 @@ class QueueListener(object):
         self._thread = None
         self.respect_handler_level = respect_handler_level
 
+    def __enter__(self):
+        """
+        For use as a context manager. Starts the listener.
+        """
+        self.start()
+        return self
+
+    def __exit__(self, *args):
+        """
+        For use as a context manager. Stops the listener.
+        """
+        self.stop()
+
     def dequeue(self, block):
         """
         Dequeue a record and return it, optionally blocking.

Lib/pickle.py

@@ -904,17 +904,11 @@ class _Pickler:
                     # Write data in-band
                     # XXX The C implementation avoids a copy here
                     buf = m.tobytes()
-                    in_memo = id(buf) in self.memo
                     if m.readonly:
-                        if in_memo:
+                        self._save_bytes_no_memo(buf)
-                            self._save_bytes_no_memo(buf)
-                        else:
-                            self.save_bytes(buf)
                     else:
-                        if in_memo:
+                        self._save_bytearray_no_memo(buf)
-                            self._save_bytearray_no_memo(buf)
+                    self.memoize(obj)
-                        else:
-                            self.save_bytearray(buf)
                 else:
                     # Write data out-of-band
                     self.write(NEXT_BUFFER)

Lib/platform.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python3
-
 """ This module tries to retrieve as much platform-identifying data as
     possible. It makes this information available via function APIs.
 
@@ -33,6 +31,7 @@
 #
 #    <see CVS and SVN checkin messages for history>
 #
+#    1.0.9 - added invalidate_caches() function to invalidate cached values
 #    1.0.8 - changed Windows support to read version from kernel32.dll
 #    1.0.7 - added DEV_NULL
 #    1.0.6 - added linux_distribution()
@@ -111,7 +110,7 @@ __copyright__ = """
 
 """
 
-__version__ = '1.0.8'
+__version__ = '1.0.9'
 
 import collections
 import os
@@ -174,6 +173,11 @@ def libc_ver(executable=None, lib='', version='', chunksize=16384):
 
     """
     if not executable:
+        if sys.platform == "emscripten":
+            # Emscripten's os.confstr reports that it is glibc, so special case
+            # it.
+            ver = ".".join(str(x) for x in sys._emscripten_info.emscripten_version)
+            return ("emscripten", ver)
         try:
             ver = os.confstr('CS_GNU_LIBC_VERSION')
             # parse 'glibc 2.28' as ('glibc', '2.28')
@@ -190,22 +194,26 @@ def libc_ver(executable=None, lib='', version='', chunksize=16384):
             # sys.executable is not set.
             return lib, version
 
-    libc_search = re.compile(b'(__libc_init)'
+    libc_search = re.compile(br"""
-                          b'|'
+          (__libc_init)
-                          b'(GLIBC_([0-9.]+))'
+        | (GLIBC_([0-9.]+))
-                          b'|'
+        | (libc(_\w+)?\.so(?:\.(\d[0-9.]*))?)
-                          br'(libc(_\w+)?\.so(?:\.(\d[0-9.]*))?)', re.ASCII)
+        | (musl-([0-9.]+))
+        | ((?:libc\.|ld-)musl(?:-\w+)?.so(?:\.(\d[0-9.]*))?)
+        """,
+        re.ASCII | re.VERBOSE)
 
     V = _comparable_version
     # We use os.path.realpath()
     # here to work around problems with Cygwin not being
     # able to open symlinks for reading
     executable = os.path.realpath(executable)
+    ver = None
     with open(executable, 'rb') as f:
         binary = f.read(chunksize)
         pos = 0
         while pos < len(binary):
-            if b'libc' in binary or b'GLIBC' in binary:
+            if b'libc' in binary or b'GLIBC' in binary or b'musl' in binary:
                 m = libc_search.search(binary, pos)
             else:
                 m = None
@@ -217,26 +225,35 @@ def libc_ver(executable=None, lib='', version='', chunksize=16384):
                     continue
                 if not m:
                     break
-            libcinit, glibc, glibcversion, so, threads, soversion = [
+            decoded_groups = [s.decode('latin1') if s is not None else s
-                s.decode('latin1') if s is not None else s
+                              for s in m.groups()]
-                for s in m.groups()]
+            (libcinit, glibc, glibcversion, so, threads, soversion,
+             musl, muslversion, musl_so, musl_sover) = decoded_groups
             if libcinit and not lib:
                 lib = 'libc'
             elif glibc:
                 if lib != 'glibc':
                     lib = 'glibc'
-                    version = glibcversion
+                    ver = glibcversion
-                elif V(glibcversion) > V(version):
+                elif V(glibcversion) > V(ver):
-                    version = glibcversion
+                    ver = glibcversion
             elif so:
-                if lib != 'glibc':
+                if lib not in ('glibc', 'musl'):
                     lib = 'libc'
-                    if soversion and (not version or V(soversion) > V(version)):
+                    if soversion and (not ver or V(soversion) > V(ver)):
-                        version = soversion
+                        ver = soversion
-                    if threads and version[-len(threads):] != threads:
+                    if threads and ver[-len(threads):] != threads:
-                        version = version + threads
+                        ver = ver + threads
+            elif musl:
+                lib = 'musl'
+                if not ver or V(muslversion) > V(ver):
+                    ver = muslversion
+            elif musl_so:
+                lib = 'musl'
+                if musl_sover and (not ver or V(musl_sover) > V(ver)):
+                    ver = musl_sover
             pos = m.end()
-    return lib, version
+    return lib, version if ver is None else ver
 
 def _norm_version(version, build=''):
 
@@ -549,7 +566,7 @@ def java_ver(release='', vendor='', vminfo=('', '', ''), osinfo=('', '', '')):
     warnings._deprecated('java_ver', remove=(3, 15))
     # Import the needed APIs
     try:
-        import java.lang
+        import java.lang  # noqa: F401
     except ImportError:
         return release, vendor, vminfo, osinfo
 
@@ -1192,7 +1209,7 @@ def _sys_version(sys_version=None):
         # CPython
         cpython_sys_version_parser = re.compile(
             r'([\w.+]+)\s*'  # "version<space>"
-            r'(?:experimental free-threading build\s+)?' # "free-threading-build<space>"
+            r'(?:free-threading build\s+)?' # "free-threading-build<space>"
             r'\(#?([^,]+)'  # "(#buildno"
             r'(?:,\s*([\w ]*)'  # ", builddate"
             r'(?:,\s*([\w :]*))?)?\)\s*'  # ", buildtime)<space>"
@@ -1449,11 +1466,55 @@ def freedesktop_os_release():
     return _os_release_cache.copy()
 
 
+def invalidate_caches():
+    """Invalidate the cached results."""
+    global _uname_cache
+    _uname_cache = None
+
+    global _os_release_cache
+    _os_release_cache = None
+
+    _sys_version_cache.clear()
+    _platform_cache.clear()
+
+
 ### Command line interface
 
-if __name__ == '__main__':
+def _parse_args(args: list[str] | None):
-    # Default is to print the aliased verbose platform string
+    import argparse
-    terse = ('terse' in sys.argv or '--terse' in sys.argv)
+
-    aliased = (not 'nonaliased' in sys.argv and not '--nonaliased' in sys.argv)
+    parser = argparse.ArgumentParser(color=True)
+    parser.add_argument("args", nargs="*", choices=["nonaliased", "terse"])
+    parser.add_argument(
+        "--terse",
+        action="store_true",
+        help=(
+            "return only the absolute minimum information needed "
+            "to identify the platform"
+        ),
+    )
+    parser.add_argument(
+        "--nonaliased",
+        dest="aliased",
+        action="store_false",
+        help=(
+            "disable system/OS name aliasing. If aliasing is enabled, "
+            "some platforms report system names different from "
+            "their common names, e.g. SunOS is reported as Solaris"
+        ),
+    )
+
+    return parser.parse_args(args)
+
+
+def _main(args: list[str] | None = None):
+    args = _parse_args(args)
+
+    terse = args.terse or ("terse" in args.args)
+    aliased = args.aliased and ('nonaliased' not in args.args)
+
     print(platform(aliased, terse))
-    sys.exit(0)
+
+
+if __name__ == "__main__":
+    _main()

Lib/plistlib.py

@@ -21,7 +21,7 @@ datetime.datetime objects.
 
 Generate Plist example:
 
-    import datetime
+    import datetime as dt
     import plistlib
 
     pl = dict(
@@ -37,7 +37,7 @@ Generate Plist example:
         ),
         someData = b"<binary gunk>",
         someMoreData = b"<lots of binary gunk>" * 10,
-        aDate = datetime.datetime.now()
+        aDate = dt.datetime.now()
     )
     print(plistlib.dumps(pl).decode())
 
@@ -384,7 +384,7 @@ class _PlistWriter(_DumbXMLWriter):
         self._indent_level -= 1
         maxlinelength = max(
             16,
-            76 - len(self.indent.replace(b"\t", b" " * 8) * self._indent_level))
+            76 - len((self.indent * self._indent_level).expandtabs()))
 
         for line in _encode_base64(data, maxlinelength).split(b"\n"):
             if line:

Lib/profile.py

@@ -0,0 +1,615 @@
+#
+# Class for profiling python code. rev 1.0  6/2/94
+#
+# Written by James Roskind
+# Based on prior profile module by Sjoerd Mullender...
+#   which was hacked somewhat by: Guido van Rossum
+
+"""Class for profiling Python code."""
+
+# Copyright Disney Enterprises, Inc.  All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
+# either express or implied.  See the License for the specific language
+# governing permissions and limitations under the License.
+
+
+import importlib.machinery
+import io
+import sys
+import time
+import marshal
+
+__all__ = ["run", "runctx", "Profile"]
+
+# Sample timer for use with
+#i_count = 0
+#def integer_timer():
+#       global i_count
+#       i_count = i_count + 1
+#       return i_count
+#itimes = integer_timer # replace with C coded timer returning integers
+
+class _Utils:
+    """Support class for utility functions which are shared by
+    profile.py and cProfile.py modules.
+    Not supposed to be used directly.
+    """
+
+    def __init__(self, profiler):
+        self.profiler = profiler
+
+    def run(self, statement, filename, sort):
+        prof = self.profiler()
+        try:
+            prof.run(statement)
+        except SystemExit:
+            pass
+        finally:
+            self._show(prof, filename, sort)
+
+    def runctx(self, statement, globals, locals, filename, sort):
+        prof = self.profiler()
+        try:
+            prof.runctx(statement, globals, locals)
+        except SystemExit:
+            pass
+        finally:
+            self._show(prof, filename, sort)
+
+    def _show(self, prof, filename, sort):
+        if filename is not None:
+            prof.dump_stats(filename)
+        else:
+            prof.print_stats(sort)
+
+
+#**************************************************************************
+# The following are the static member functions for the profiler class
+# Note that an instance of Profile() is *not* needed to call them.
+#**************************************************************************
+
+def run(statement, filename=None, sort=-1):
+    """Run statement under profiler optionally saving results in filename
+
+    This function takes a single argument that can be passed to the
+    "exec" statement, and an optional file name.  In all cases this
+    routine attempts to "exec" its first argument and gather profiling
+    statistics from the execution. If no file name is present, then this
+    function automatically prints a simple profiling report, sorted by the
+    standard name string (file/line/function-name) that is presented in
+    each line.
+    """
+    return _Utils(Profile).run(statement, filename, sort)
+
+def runctx(statement, globals, locals, filename=None, sort=-1):
+    """Run statement under profiler, supplying your own globals and locals,
+    optionally saving results in filename.
+
+    statement and filename have the same semantics as profile.run
+    """
+    return _Utils(Profile).runctx(statement, globals, locals, filename, sort)
+
+
+class Profile:
+    """Profiler class.
+
+    self.cur is always a tuple.  Each such tuple corresponds to a stack
+    frame that is currently active (self.cur[-2]).  The following are the
+    definitions of its members.  We use this external "parallel stack" to
+    avoid contaminating the program that we are profiling. (old profiler
+    used to write into the frames local dictionary!!) Derived classes
+    can change the definition of some entries, as long as they leave
+    [-2:] intact (frame and previous tuple).  In case an internal error is
+    detected, the -3 element is used as the function name.
+
+    [ 0] = Time that needs to be charged to the parent frame's function.
+           It is used so that a function call will not have to access the
+           timing data for the parent frame.
+    [ 1] = Total time spent in this frame's function, excluding time in
+           subfunctions (this latter is tallied in cur[2]).
+    [ 2] = Total time spent in subfunctions, excluding time executing the
+           frame's function (this latter is tallied in cur[1]).
+    [-3] = Name of the function that corresponds to this frame.
+    [-2] = Actual frame that we correspond to (used to sync exception handling).
+    [-1] = Our parent 6-tuple (corresponds to frame.f_back).
+
+    Timing data for each function is stored as a 5-tuple in the dictionary
+    self.timings[].  The index is always the name stored in self.cur[-3].
+    The following are the definitions of the members:
+
+    [0] = The number of times this function was called, not counting direct
+          or indirect recursion,
+    [1] = Number of times this function appears on the stack, minus one
+    [2] = Total time spent internal to this function
+    [3] = Cumulative time that this function was present on the stack.  In
+          non-recursive functions, this is the total execution time from start
+          to finish of each invocation of a function, including time spent in
+          all subfunctions.
+    [4] = A dictionary indicating for each function name, the number of times
+          it was called by us.
+    """
+
+    bias = 0  # calibration constant
+
+    def __init__(self, timer=None, bias=None):
+        self.timings = {}
+        self.cur = None
+        self.cmd = ""
+        self.c_func_name = ""
+
+        if bias is None:
+            bias = self.bias
+        self.bias = bias     # Materialize in local dict for lookup speed.
+
+        if not timer:
+            self.timer = self.get_time = time.process_time
+            self.dispatcher = self.trace_dispatch_i
+        else:
+            self.timer = timer
+            t = self.timer() # test out timer function
+            try:
+                length = len(t)
+            except TypeError:
+                self.get_time = timer
+                self.dispatcher = self.trace_dispatch_i
+            else:
+                if length == 2:
+                    self.dispatcher = self.trace_dispatch
+                else:
+                    self.dispatcher = self.trace_dispatch_l
+                # This get_time() implementation needs to be defined
+                # here to capture the passed-in timer in the parameter
+                # list (for performance).  Note that we can't assume
+                # the timer() result contains two values in all
+                # cases.
+                def get_time_timer(timer=timer, sum=sum):
+                    return sum(timer())
+                self.get_time = get_time_timer
+        self.t = self.get_time()
+        self.simulate_call('profiler')
+
+    # Heavily optimized dispatch routine for time.process_time() timer
+
+    def trace_dispatch(self, frame, event, arg):
+        timer = self.timer
+        t = timer()
+        t = t[0] + t[1] - self.t - self.bias
+
+        if event == "c_call":
+            self.c_func_name = arg.__name__
+
+        if self.dispatch[event](self, frame,t):
+            t = timer()
+            self.t = t[0] + t[1]
+        else:
+            r = timer()
+            self.t = r[0] + r[1] - t # put back unrecorded delta
+
+    # Dispatch routine for best timer program (return = scalar, fastest if
+    # an integer but float works too -- and time.process_time() relies on that).
+
+    def trace_dispatch_i(self, frame, event, arg):
+        timer = self.timer
+        t = timer() - self.t - self.bias
+
+        if event == "c_call":
+            self.c_func_name = arg.__name__
+
+        if self.dispatch[event](self, frame, t):
+            self.t = timer()
+        else:
+            self.t = timer() - t  # put back unrecorded delta
+
+    # Dispatch routine for macintosh (timer returns time in ticks of
+    # 1/60th second)
+
+    def trace_dispatch_mac(self, frame, event, arg):
+        timer = self.timer
+        t = timer()/60.0 - self.t - self.bias
+
+        if event == "c_call":
+            self.c_func_name = arg.__name__
+
+        if self.dispatch[event](self, frame, t):
+            self.t = timer()/60.0
+        else:
+            self.t = timer()/60.0 - t  # put back unrecorded delta
+
+    # SLOW generic dispatch routine for timer returning lists of numbers
+
+    def trace_dispatch_l(self, frame, event, arg):
+        get_time = self.get_time
+        t = get_time() - self.t - self.bias
+
+        if event == "c_call":
+            self.c_func_name = arg.__name__
+
+        if self.dispatch[event](self, frame, t):
+            self.t = get_time()
+        else:
+            self.t = get_time() - t # put back unrecorded delta
+
+    # In the event handlers, the first 3 elements of self.cur are unpacked
+    # into vrbls w/ 3-letter names.  The last two characters are meant to be
+    # mnemonic:
+    #     _pt  self.cur[0] "parent time"   time to be charged to parent frame
+    #     _it  self.cur[1] "internal time" time spent directly in the function
+    #     _et  self.cur[2] "external time" time spent in subfunctions
+
+    def trace_dispatch_exception(self, frame, t):
+        rpt, rit, ret, rfn, rframe, rcur = self.cur
+        if (rframe is not frame) and rcur:
+            return self.trace_dispatch_return(rframe, t)
+        self.cur = rpt, rit+t, ret, rfn, rframe, rcur
+        return 1
+
+
+    def trace_dispatch_call(self, frame, t):
+        if self.cur and frame.f_back is not self.cur[-2]:
+            rpt, rit, ret, rfn, rframe, rcur = self.cur
+            if not isinstance(rframe, Profile.fake_frame):
+                assert rframe.f_back is frame.f_back, ("Bad call", rfn,
+                                                       rframe, rframe.f_back,
+                                                       frame, frame.f_back)
+                self.trace_dispatch_return(rframe, 0)
+                assert (self.cur is None or \
+                        frame.f_back is self.cur[-2]), ("Bad call",
+                                                        self.cur[-3])
+        fcode = frame.f_code
+        fn = (fcode.co_filename, fcode.co_firstlineno, fcode.co_name)
+        self.cur = (t, 0, 0, fn, frame, self.cur)
+        timings = self.timings
+        if fn in timings:
+            cc, ns, tt, ct, callers = timings[fn]
+            timings[fn] = cc, ns + 1, tt, ct, callers
+        else:
+            timings[fn] = 0, 0, 0, 0, {}
+        return 1
+
+    def trace_dispatch_c_call (self, frame, t):
+        fn = ("", 0, self.c_func_name)
+        self.cur = (t, 0, 0, fn, frame, self.cur)
+        timings = self.timings
+        if fn in timings:
+            cc, ns, tt, ct, callers = timings[fn]
+            timings[fn] = cc, ns+1, tt, ct, callers
+        else:
+            timings[fn] = 0, 0, 0, 0, {}
+        return 1
+
+    def trace_dispatch_return(self, frame, t):
+        if frame is not self.cur[-2]:
+            assert frame is self.cur[-2].f_back, ("Bad return", self.cur[-3])
+            self.trace_dispatch_return(self.cur[-2], 0)
+
+        # Prefix "r" means part of the Returning or exiting frame.
+        # Prefix "p" means part of the Previous or Parent or older frame.
+
+        rpt, rit, ret, rfn, frame, rcur = self.cur
+        rit = rit + t
+        frame_total = rit + ret
+
+        ppt, pit, pet, pfn, pframe, pcur = rcur
+        self.cur = ppt, pit + rpt, pet + frame_total, pfn, pframe, pcur
+
+        timings = self.timings
+        cc, ns, tt, ct, callers = timings[rfn]
+        if not ns:
+            # This is the only occurrence of the function on the stack.
+            # Else this is a (directly or indirectly) recursive call, and
+            # its cumulative time will get updated when the topmost call to
+            # it returns.
+            ct = ct + frame_total
+            cc = cc + 1
+
+        if pfn in callers:
+            callers[pfn] = callers[pfn] + 1  # hack: gather more
+            # stats such as the amount of time added to ct courtesy
+            # of this specific call, and the contribution to cc
+            # courtesy of this call.
+        else:
+            callers[pfn] = 1
+
+        timings[rfn] = cc, ns - 1, tt + rit, ct, callers
+
+        return 1
+
+
+    dispatch = {
+        "call": trace_dispatch_call,
+        "exception": trace_dispatch_exception,
+        "return": trace_dispatch_return,
+        "c_call": trace_dispatch_c_call,
+        "c_exception": trace_dispatch_return,  # the C function returned
+        "c_return": trace_dispatch_return,
+        }
+
+
+    # The next few functions play with self.cmd. By carefully preloading
+    # our parallel stack, we can force the profiled result to include
+    # an arbitrary string as the name of the calling function.
+    # We use self.cmd as that string, and the resulting stats look
+    # very nice :-).
+
+    def set_cmd(self, cmd):
+        if self.cur[-1]: return   # already set
+        self.cmd = cmd
+        self.simulate_call(cmd)
+
+    class fake_code:
+        def __init__(self, filename, line, name):
+            self.co_filename = filename
+            self.co_line = line
+            self.co_name = name
+            self.co_firstlineno = 0
+
+        def __repr__(self):
+            return repr((self.co_filename, self.co_line, self.co_name))
+
+    class fake_frame:
+        def __init__(self, code, prior):
+            self.f_code = code
+            self.f_back = prior
+
+    def simulate_call(self, name):
+        code = self.fake_code('profile', 0, name)
+        if self.cur:
+            pframe = self.cur[-2]
+        else:
+            pframe = None
+        frame = self.fake_frame(code, pframe)
+        self.dispatch['call'](self, frame, 0)
+
+    # collect stats from pending stack, including getting final
+    # timings for self.cmd frame.
+
+    def simulate_cmd_complete(self):
+        get_time = self.get_time
+        t = get_time() - self.t
+        while self.cur[-1]:
+            # We *can* cause assertion errors here if
+            # dispatch_trace_return checks for a frame match!
+            self.dispatch['return'](self, self.cur[-2], t)
+            t = 0
+        self.t = get_time() - t
+
+
+    def print_stats(self, sort=-1):
+        import pstats
+        if not isinstance(sort, tuple):
+            sort = (sort,)
+        pstats.Stats(self).strip_dirs().sort_stats(*sort).print_stats()
+
+    def dump_stats(self, file):
+        with open(file, 'wb') as f:
+            self.create_stats()
+            marshal.dump(self.stats, f)
+
+    def create_stats(self):
+        self.simulate_cmd_complete()
+        self.snapshot_stats()
+
+    def snapshot_stats(self):
+        self.stats = {}
+        for func, (cc, ns, tt, ct, callers) in self.timings.items():
+            callers = callers.copy()
+            nc = 0
+            for callcnt in callers.values():
+                nc += callcnt
+            self.stats[func] = cc, nc, tt, ct, callers
+
+
+    # The following two methods can be called by clients to use
+    # a profiler to profile a statement, given as a string.
+
+    def run(self, cmd):
+        import __main__
+        dict = __main__.__dict__
+        return self.runctx(cmd, dict, dict)
+
+    def runctx(self, cmd, globals, locals):
+        self.set_cmd(cmd)
+        sys.setprofile(self.dispatcher)
+        try:
+            exec(cmd, globals, locals)
+        finally:
+            sys.setprofile(None)
+        return self
+
+    # This method is more useful to profile a single function call.
+    def runcall(self, func, /, *args, **kw):
+        self.set_cmd(repr(func))
+        sys.setprofile(self.dispatcher)
+        try:
+            return func(*args, **kw)
+        finally:
+            sys.setprofile(None)
+
+
+    #******************************************************************
+    # The following calculates the overhead for using a profiler.  The
+    # problem is that it takes a fair amount of time for the profiler
+    # to stop the stopwatch (from the time it receives an event).
+    # Similarly, there is a delay from the time that the profiler
+    # re-starts the stopwatch before the user's code really gets to
+    # continue.  The following code tries to measure the difference on
+    # a per-event basis.
+    #
+    # Note that this difference is only significant if there are a lot of
+    # events, and relatively little user code per event.  For example,
+    # code with small functions will typically benefit from having the
+    # profiler calibrated for the current platform.  This *could* be
+    # done on the fly during init() time, but it is not worth the
+    # effort.  Also note that if too large a value specified, then
+    # execution time on some functions will actually appear as a
+    # negative number.  It is *normal* for some functions (with very
+    # low call counts) to have such negative stats, even if the
+    # calibration figure is "correct."
+    #
+    # One alternative to profile-time calibration adjustments (i.e.,
+    # adding in the magic little delta during each event) is to track
+    # more carefully the number of events (and cumulatively, the number
+    # of events during sub functions) that are seen.  If this were
+    # done, then the arithmetic could be done after the fact (i.e., at
+    # display time).  Currently, we track only call/return events.
+    # These values can be deduced by examining the callees and callers
+    # vectors for each functions.  Hence we *can* almost correct the
+    # internal time figure at print time (note that we currently don't
+    # track exception event processing counts).  Unfortunately, there
+    # is currently no similar information for cumulative sub-function
+    # time.  It would not be hard to "get all this info" at profiler
+    # time.  Specifically, we would have to extend the tuples to keep
+    # counts of this in each frame, and then extend the defs of timing
+    # tuples to include the significant two figures. I'm a bit fearful
+    # that this additional feature will slow the heavily optimized
+    # event/time ratio (i.e., the profiler would run slower, fur a very
+    # low "value added" feature.)
+    #**************************************************************
+
+    def calibrate(self, m, verbose=0):
+        if self.__class__ is not Profile:
+            raise TypeError("Subclasses must override .calibrate().")
+
+        saved_bias = self.bias
+        self.bias = 0
+        try:
+            return self._calibrate_inner(m, verbose)
+        finally:
+            self.bias = saved_bias
+
+    def _calibrate_inner(self, m, verbose):
+        get_time = self.get_time
+
+        # Set up a test case to be run with and without profiling.  Include
+        # lots of calls, because we're trying to quantify stopwatch overhead.
+        # Do not raise any exceptions, though, because we want to know
+        # exactly how many profile events are generated (one call event, +
+        # one return event, per Python-level call).
+
+        def f1(n):
+            for i in range(n):
+                x = 1
+
+        def f(m, f1=f1):
+            for i in range(m):
+                f1(100)
+
+        f(m)    # warm up the cache
+
+        # elapsed_noprofile <- time f(m) takes without profiling.
+        t0 = get_time()
+        f(m)
+        t1 = get_time()
+        elapsed_noprofile = t1 - t0
+        if verbose:
+            print("elapsed time without profiling =", elapsed_noprofile)
+
+        # elapsed_profile <- time f(m) takes with profiling.  The difference
+        # is profiling overhead, only some of which the profiler subtracts
+        # out on its own.
+        p = Profile()
+        t0 = get_time()
+        p.runctx('f(m)', globals(), locals())
+        t1 = get_time()
+        elapsed_profile = t1 - t0
+        if verbose:
+            print("elapsed time with profiling =", elapsed_profile)
+
+        # reported_time <- "CPU seconds" the profiler charged to f and f1.
+        total_calls = 0.0
+        reported_time = 0.0
+        for (filename, line, funcname), (cc, ns, tt, ct, callers) in \
+                p.timings.items():
+            if funcname in ("f", "f1"):
+                total_calls += cc
+                reported_time += tt
+
+        if verbose:
+            print("'CPU seconds' profiler reported =", reported_time)
+            print("total # calls =", total_calls)
+        if total_calls != m + 1:
+            raise ValueError("internal error: total calls = %d" % total_calls)
+
+        # reported_time - elapsed_noprofile = overhead the profiler wasn't
+        # able to measure.  Divide by twice the number of calls (since there
+        # are two profiler events per call in this test) to get the hidden
+        # overhead per event.
+        mean = (reported_time - elapsed_noprofile) / 2.0 / total_calls
+        if verbose:
+            print("mean stopwatch overhead per profile event =", mean)
+        return mean
+
+#****************************************************************************
+
+def main():
+    import os
+    from optparse import OptionParser
+
+    usage = "profile.py [-o output_file_path] [-s sort] [-m module | scriptfile] [arg] ..."
+    parser = OptionParser(usage=usage)
+    parser.allow_interspersed_args = False
+    parser.add_option('-o', '--outfile', dest="outfile",
+        help="Save stats to <outfile>", default=None)
+    parser.add_option('-m', dest="module", action="store_true",
+        help="Profile a library module.", default=False)
+    parser.add_option('-s', '--sort', dest="sort",
+        help="Sort order when printing to stdout, based on pstats.Stats class",
+        default=-1)
+
+    if not sys.argv[1:]:
+        parser.print_usage()
+        sys.exit(2)
+
+    (options, args) = parser.parse_args()
+    sys.argv[:] = args
+
+    # The script that we're profiling may chdir, so capture the absolute path
+    # to the output file at startup.
+    if options.outfile is not None:
+        options.outfile = os.path.abspath(options.outfile)
+
+    if len(args) > 0:
+        if options.module:
+            import runpy
+            code = "run_module(modname, run_name='__main__')"
+            globs = {
+                'run_module': runpy.run_module,
+                'modname': args[0]
+            }
+        else:
+            progname = args[0]
+            sys.path.insert(0, os.path.dirname(progname))
+            with io.open_code(progname) as fp:
+                code = compile(fp.read(), progname, 'exec')
+            spec = importlib.machinery.ModuleSpec(name='__main__', loader=None,
+                                                  origin=progname)
+            globs = {
+                '__spec__': spec,
+                '__file__': spec.origin,
+                '__name__': spec.name,
+                '__package__': None,
+                '__cached__': None,
+            }
+        try:
+            runctx(code, globs, None, options.outfile, options.sort)
+        except BrokenPipeError as exc:
+            # Prevent "Exception ignored" during interpreter shutdown.
+            sys.stdout = None
+            sys.exit(exc.errno)
+    else:
+        parser.print_usage()
+    return parser
+
+# When invoked as main program, invoke the profiler on a script
+if __name__ == '__main__':
+    main()

Lib/pstats.py

@@ -0,0 +1,777 @@
+"""Class for printing reports on profiled python code."""
+
+# Written by James Roskind
+# Based on prior profile module by Sjoerd Mullender...
+#   which was hacked somewhat by: Guido van Rossum
+
+# Copyright Disney Enterprises, Inc.  All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
+# either express or implied.  See the License for the specific language
+# governing permissions and limitations under the License.
+
+
+import sys
+import os
+import time
+import marshal
+import re
+
+from enum import StrEnum, _simple_enum
+from functools import cmp_to_key
+from dataclasses import dataclass
+
+__all__ = ["Stats", "SortKey", "FunctionProfile", "StatsProfile"]
+
+@_simple_enum(StrEnum)
+class SortKey:
+    CALLS = 'calls', 'ncalls'
+    CUMULATIVE = 'cumulative', 'cumtime'
+    FILENAME = 'filename', 'module'
+    LINE = 'line'
+    NAME = 'name'
+    NFL = 'nfl'
+    PCALLS = 'pcalls'
+    STDNAME = 'stdname'
+    TIME = 'time', 'tottime'
+
+    def __new__(cls, *values):
+        value = values[0]
+        obj = str.__new__(cls, value)
+        obj._value_ = value
+        for other_value in values[1:]:
+            cls._value2member_map_[other_value] = obj
+        obj._all_values = values
+        return obj
+
+
+@dataclass(unsafe_hash=True)
+class FunctionProfile:
+    ncalls: str
+    tottime: float
+    percall_tottime: float
+    cumtime: float
+    percall_cumtime: float
+    file_name: str
+    line_number: int
+
+@dataclass(unsafe_hash=True)
+class StatsProfile:
+    '''Class for keeping track of an item in inventory.'''
+    total_tt: float
+    func_profiles: dict[str, FunctionProfile]
+
+class Stats:
+    """This class is used for creating reports from data generated by the
+    Profile class.  It is a "friend" of that class, and imports data either
+    by direct access to members of Profile class, or by reading in a dictionary
+    that was emitted (via marshal) from the Profile class.
+
+    The big change from the previous Profiler (in terms of raw functionality)
+    is that an "add()" method has been provided to combine Stats from
+    several distinct profile runs.  Both the constructor and the add()
+    method now take arbitrarily many file names as arguments.
+
+    All the print methods now take an argument that indicates how many lines
+    to print.  If the arg is a floating-point number between 0 and 1.0, then
+    it is taken as a decimal percentage of the available lines to be printed
+    (e.g., .1 means print 10% of all available lines).  If it is an integer,
+    it is taken to mean the number of lines of data that you wish to have
+    printed.
+
+    The sort_stats() method now processes some additional options (i.e., in
+    addition to the old -1, 0, 1, or 2 that are respectively interpreted as
+    'stdname', 'calls', 'time', and 'cumulative').  It takes either an
+    arbitrary number of quoted strings or SortKey enum to select the sort
+    order.
+
+    For example sort_stats('time', 'name') or sort_stats(SortKey.TIME,
+    SortKey.NAME) sorts on the major key of 'internal function time', and on
+    the minor key of 'the name of the function'.  Look at the two tables in
+    sort_stats() and get_sort_arg_defs(self) for more examples.
+
+    All methods return self, so you can string together commands like:
+        Stats('foo', 'goo').strip_dirs().sort_stats('calls').\
+                            print_stats(5).print_callers(5)
+    """
+
+    def __init__(self, *args, stream=None):
+        self.stream = stream or sys.stdout
+        if not len(args):
+            arg = None
+        else:
+            arg = args[0]
+            args = args[1:]
+        self.init(arg)
+        self.add(*args)
+
+    def init(self, arg):
+        self.all_callees = None  # calc only if needed
+        self.files = []
+        self.fcn_list = None
+        self.total_tt = 0
+        self.total_calls = 0
+        self.prim_calls = 0
+        self.max_name_len = 0
+        self.top_level = set()
+        self.stats = {}
+        self.sort_arg_dict = {}
+        self.load_stats(arg)
+        try:
+            self.get_top_level_stats()
+        except Exception:
+            print("Invalid timing data %s" %
+                  (self.files[-1] if self.files else ''), file=self.stream)
+            raise
+
+    def load_stats(self, arg):
+        if arg is None:
+            self.stats = {}
+            return
+        elif isinstance(arg, str):
+            with open(arg, 'rb') as f:
+                self.stats = marshal.load(f)
+            try:
+                file_stats = os.stat(arg)
+                arg = time.ctime(file_stats.st_mtime) + "    " + arg
+            except:  # in case this is not unix
+                pass
+            self.files = [arg]
+        elif hasattr(arg, 'create_stats'):
+            arg.create_stats()
+            self.stats = arg.stats
+            arg.stats = {}
+        if not self.stats:
+            raise TypeError("Cannot create or construct a %r object from %r"
+                            % (self.__class__, arg))
+        return
+
+    def get_top_level_stats(self):
+        for func, (cc, nc, tt, ct, callers) in self.stats.items():
+            self.total_calls += nc
+            self.prim_calls  += cc
+            self.total_tt    += tt
+            if ("jprofile", 0, "profiler") in callers:
+                self.top_level.add(func)
+            if len(func_std_string(func)) > self.max_name_len:
+                self.max_name_len = len(func_std_string(func))
+
+    def add(self, *arg_list):
+        if not arg_list:
+            return self
+        for item in reversed(arg_list):
+            if type(self) != type(item):
+                item = Stats(item)
+            self.files += item.files
+            self.total_calls += item.total_calls
+            self.prim_calls += item.prim_calls
+            self.total_tt += item.total_tt
+            for func in item.top_level:
+                self.top_level.add(func)
+
+            if self.max_name_len < item.max_name_len:
+                self.max_name_len = item.max_name_len
+
+            self.fcn_list = None
+
+            for func, stat in item.stats.items():
+                if func in self.stats:
+                    old_func_stat = self.stats[func]
+                else:
+                    old_func_stat = (0, 0, 0, 0, {},)
+                self.stats[func] = add_func_stats(old_func_stat, stat)
+        return self
+
+    def dump_stats(self, filename):
+        """Write the profile data to a file we know how to load back."""
+        with open(filename, 'wb') as f:
+            marshal.dump(self.stats, f)
+
+    # list the tuple indices and directions for sorting,
+    # along with some printable description
+    sort_arg_dict_default = {
+              "calls"     : (((1,-1),              ), "call count"),
+              "ncalls"    : (((1,-1),              ), "call count"),
+              "cumtime"   : (((3,-1),              ), "cumulative time"),
+              "cumulative": (((3,-1),              ), "cumulative time"),
+              "filename"  : (((4, 1),              ), "file name"),
+              "line"      : (((5, 1),              ), "line number"),
+              "module"    : (((4, 1),              ), "file name"),
+              "name"      : (((6, 1),              ), "function name"),
+              "nfl"       : (((6, 1),(4, 1),(5, 1),), "name/file/line"),
+              "pcalls"    : (((0,-1),              ), "primitive call count"),
+              "stdname"   : (((7, 1),              ), "standard name"),
+              "time"      : (((2,-1),              ), "internal time"),
+              "tottime"   : (((2,-1),              ), "internal time"),
+              }
+
+    def get_sort_arg_defs(self):
+        """Expand all abbreviations that are unique."""
+        if not self.sort_arg_dict:
+            self.sort_arg_dict = dict = {}
+            bad_list = {}
+            for word, tup in self.sort_arg_dict_default.items():
+                fragment = word
+                while fragment:
+                    if fragment in dict:
+                        bad_list[fragment] = 0
+                        break
+                    dict[fragment] = tup
+                    fragment = fragment[:-1]
+            for word in bad_list:
+                del dict[word]
+        return self.sort_arg_dict
+
+    def sort_stats(self, *field):
+        if not field:
+            self.fcn_list = 0
+            return self
+        if len(field) == 1 and isinstance(field[0], int):
+            # Be compatible with old profiler
+            field = [ {-1: "stdname",
+                       0:  "calls",
+                       1:  "time",
+                       2:  "cumulative"}[field[0]] ]
+        elif len(field) >= 2:
+            for arg in field[1:]:
+                if type(arg) != type(field[0]):
+                    raise TypeError("Can't have mixed argument type")
+
+        sort_arg_defs = self.get_sort_arg_defs()
+
+        sort_tuple = ()
+        self.sort_type = ""
+        connector = ""
+        for word in field:
+            if isinstance(word, SortKey):
+                word = word.value
+            sort_tuple = sort_tuple + sort_arg_defs[word][0]
+            self.sort_type += connector + sort_arg_defs[word][1]
+            connector = ", "
+
+        stats_list = []
+        for func, (cc, nc, tt, ct, callers) in self.stats.items():
+            stats_list.append((cc, nc, tt, ct) + func +
+                              (func_std_string(func), func))
+
+        stats_list.sort(key=cmp_to_key(TupleComp(sort_tuple).compare))
+
+        self.fcn_list = fcn_list = []
+        for tuple in stats_list:
+            fcn_list.append(tuple[-1])
+        return self
+
+    def reverse_order(self):
+        if self.fcn_list:
+            self.fcn_list.reverse()
+        return self
+
+    def strip_dirs(self):
+        oldstats = self.stats
+        self.stats = newstats = {}
+        max_name_len = 0
+        for func, (cc, nc, tt, ct, callers) in oldstats.items():
+            newfunc = func_strip_path(func)
+            if len(func_std_string(newfunc)) > max_name_len:
+                max_name_len = len(func_std_string(newfunc))
+            newcallers = {}
+            for func2, caller in callers.items():
+                newcallers[func_strip_path(func2)] = caller
+
+            if newfunc in newstats:
+                newstats[newfunc] = add_func_stats(
+                                        newstats[newfunc],
+                                        (cc, nc, tt, ct, newcallers))
+            else:
+                newstats[newfunc] = (cc, nc, tt, ct, newcallers)
+        old_top = self.top_level
+        self.top_level = new_top = set()
+        for func in old_top:
+            new_top.add(func_strip_path(func))
+
+        self.max_name_len = max_name_len
+
+        self.fcn_list = None
+        self.all_callees = None
+        return self
+
+    def calc_callees(self):
+        if self.all_callees:
+            return
+        self.all_callees = all_callees = {}
+        for func, (cc, nc, tt, ct, callers) in self.stats.items():
+            if not func in all_callees:
+                all_callees[func] = {}
+            for func2, caller in callers.items():
+                if not func2 in all_callees:
+                    all_callees[func2] = {}
+                all_callees[func2][func]  = caller
+        return
+
+    #******************************************************************
+    # The following functions support actual printing of reports
+    #******************************************************************
+
+    # Optional "amount" is either a line count, or a percentage of lines.
+
+    def eval_print_amount(self, sel, list, msg):
+        new_list = list
+        if isinstance(sel, str):
+            try:
+                rex = re.compile(sel)
+            except re.PatternError:
+                msg += "   <Invalid regular expression %r>\n" % sel
+                return new_list, msg
+            new_list = []
+            for func in list:
+                if rex.search(func_std_string(func)):
+                    new_list.append(func)
+        else:
+            count = len(list)
+            if isinstance(sel, float) and 0.0 <= sel < 1.0:
+                count = int(count * sel + .5)
+                new_list = list[:count]
+            elif isinstance(sel, int) and 0 <= sel < count:
+                count = sel
+                new_list = list[:count]
+        if len(list) != len(new_list):
+            msg += "   List reduced from %r to %r due to restriction <%r>\n" % (
+                len(list), len(new_list), sel)
+
+        return new_list, msg
+
+    def get_stats_profile(self):
+        """This method returns an instance of StatsProfile, which contains a mapping
+        of function names to instances of FunctionProfile. Each FunctionProfile
+        instance holds information related to the function's profile such as how
+        long the function took to run, how many times it was called, etc...
+        """
+        func_list = self.fcn_list[:] if self.fcn_list else list(self.stats.keys())
+        if not func_list:
+            return StatsProfile(0, {})
+
+        total_tt = float(f8(self.total_tt))
+        func_profiles = {}
+        stats_profile = StatsProfile(total_tt, func_profiles)
+
+        for func in func_list:
+            cc, nc, tt, ct, callers = self.stats[func]
+            file_name, line_number, func_name = func
+            ncalls = str(nc) if nc == cc else (str(nc) + '/' + str(cc))
+            tottime = float(f8(tt))
+            percall_tottime = -1 if nc == 0 else float(f8(tt/nc))
+            cumtime = float(f8(ct))
+            percall_cumtime = -1 if cc == 0 else float(f8(ct/cc))
+            func_profile = FunctionProfile(
+                ncalls,
+                tottime, # time spent in this function alone
+                percall_tottime,
+                cumtime, # time spent in the function plus all functions that this function called,
+                percall_cumtime,
+                file_name,
+                line_number
+            )
+            func_profiles[func_name] = func_profile
+
+        return stats_profile
+
+    def get_print_list(self, sel_list):
+        width = self.max_name_len
+        if self.fcn_list:
+            stat_list = self.fcn_list[:]
+            msg = "   Ordered by: " + self.sort_type + '\n'
+        else:
+            stat_list = list(self.stats.keys())
+            msg = "   Random listing order was used\n"
+
+        for selection in sel_list:
+            stat_list, msg = self.eval_print_amount(selection, stat_list, msg)
+
+        count = len(stat_list)
+
+        if not stat_list:
+            return 0, stat_list
+        print(msg, file=self.stream)
+        if count < len(self.stats):
+            width = 0
+            for func in stat_list:
+                if  len(func_std_string(func)) > width:
+                    width = len(func_std_string(func))
+        return width+2, stat_list
+
+    def print_stats(self, *amount):
+        for filename in self.files:
+            print(filename, file=self.stream)
+        if self.files:
+            print(file=self.stream)
+        indent = ' ' * 8
+        for func in self.top_level:
+            print(indent, func_get_function_name(func), file=self.stream)
+
+        print(indent, self.total_calls, "function calls", end=' ', file=self.stream)
+        if self.total_calls != self.prim_calls:
+            print("(%d primitive calls)" % self.prim_calls, end=' ', file=self.stream)
+        print("in %.3f seconds" % self.total_tt, file=self.stream)
+        print(file=self.stream)
+        width, list = self.get_print_list(amount)
+        if list:
+            self.print_title()
+            for func in list:
+                self.print_line(func)
+            print(file=self.stream)
+            print(file=self.stream)
+        return self
+
+    def print_callees(self, *amount):
+        width, list = self.get_print_list(amount)
+        if list:
+            self.calc_callees()
+
+            self.print_call_heading(width, "called...")
+            for func in list:
+                if func in self.all_callees:
+                    self.print_call_line(width, func, self.all_callees[func])
+                else:
+                    self.print_call_line(width, func, {})
+            print(file=self.stream)
+            print(file=self.stream)
+        return self
+
+    def print_callers(self, *amount):
+        width, list = self.get_print_list(amount)
+        if list:
+            self.print_call_heading(width, "was called by...")
+            for func in list:
+                cc, nc, tt, ct, callers = self.stats[func]
+                self.print_call_line(width, func, callers, "<-")
+            print(file=self.stream)
+            print(file=self.stream)
+        return self
+
+    def print_call_heading(self, name_size, column_title):
+        print("Function ".ljust(name_size) + column_title, file=self.stream)
+        # print sub-header only if we have new-style callers
+        subheader = False
+        for cc, nc, tt, ct, callers in self.stats.values():
+            if callers:
+                value = next(iter(callers.values()))
+                subheader = isinstance(value, tuple)
+                break
+        if subheader:
+            print(" "*name_size + "    ncalls  tottime  cumtime", file=self.stream)
+
+    def print_call_line(self, name_size, source, call_dict, arrow="->"):
+        print(func_std_string(source).ljust(name_size) + arrow, end=' ', file=self.stream)
+        if not call_dict:
+            print(file=self.stream)
+            return
+        clist = sorted(call_dict.keys())
+        indent = ""
+        for func in clist:
+            name = func_std_string(func)
+            value = call_dict[func]
+            if isinstance(value, tuple):
+                nc, cc, tt, ct = value
+                if nc != cc:
+                    substats = '%d/%d' % (nc, cc)
+                else:
+                    substats = '%d' % (nc,)
+                substats = '%s %s %s  %s' % (substats.rjust(7+2*len(indent)),
+                                             f8(tt), f8(ct), name)
+                left_width = name_size + 1
+            else:
+                substats = '%s(%r) %s' % (name, value, f8(self.stats[func][3]))
+                left_width = name_size + 3
+            print(indent*left_width + substats, file=self.stream)
+            indent = " "
+
+    def print_title(self):
+        print('   ncalls  tottime  percall  cumtime  percall', end=' ', file=self.stream)
+        print('filename:lineno(function)', file=self.stream)
+
+    def print_line(self, func):  # hack: should print percentages
+        cc, nc, tt, ct, callers = self.stats[func]
+        c = str(nc)
+        if nc != cc:
+            c = c + '/' + str(cc)
+        print(c.rjust(9), end=' ', file=self.stream)
+        print(f8(tt), end=' ', file=self.stream)
+        if nc == 0:
+            print(' '*8, end=' ', file=self.stream)
+        else:
+            print(f8(tt/nc), end=' ', file=self.stream)
+        print(f8(ct), end=' ', file=self.stream)
+        if cc == 0:
+            print(' '*8, end=' ', file=self.stream)
+        else:
+            print(f8(ct/cc), end=' ', file=self.stream)
+        print(func_std_string(func), file=self.stream)
+
+class TupleComp:
+    """This class provides a generic function for comparing any two tuples.
+    Each instance records a list of tuple-indices (from most significant
+    to least significant), and sort direction (ascending or descending) for
+    each tuple-index.  The compare functions can then be used as the function
+    argument to the system sort() function when a list of tuples need to be
+    sorted in the instances order."""
+
+    def __init__(self, comp_select_list):
+        self.comp_select_list = comp_select_list
+
+    def compare (self, left, right):
+        for index, direction in self.comp_select_list:
+            l = left[index]
+            r = right[index]
+            if l < r:
+                return -direction
+            if l > r:
+                return direction
+        return 0
+
+
+#**************************************************************************
+# func_name is a triple (file:string, line:int, name:string)
+
+def func_strip_path(func_name):
+    filename, line, name = func_name
+    return os.path.basename(filename), line, name
+
+def func_get_function_name(func):
+    return func[2]
+
+def func_std_string(func_name): # match what old profile produced
+    if func_name[:2] == ('~', 0):
+        # special case for built-in functions
+        name = func_name[2]
+        if name.startswith('<') and name.endswith('>'):
+            return '{%s}' % name[1:-1]
+        else:
+            return name
+    else:
+        return "%s:%d(%s)" % func_name
+
+#**************************************************************************
+# The following functions combine statistics for pairs functions.
+# The bulk of the processing involves correctly handling "call" lists,
+# such as callers and callees.
+#**************************************************************************
+
+def add_func_stats(target, source):
+    """Add together all the stats for two profile entries."""
+    cc, nc, tt, ct, callers = source
+    t_cc, t_nc, t_tt, t_ct, t_callers = target
+    return (cc+t_cc, nc+t_nc, tt+t_tt, ct+t_ct,
+              add_callers(t_callers, callers))
+
+def add_callers(target, source):
+    """Combine two caller lists in a single list."""
+    new_callers = {}
+    for func, caller in target.items():
+        new_callers[func] = caller
+    for func, caller in source.items():
+        if func in new_callers:
+            if isinstance(caller, tuple):
+                # format used by cProfile
+                new_callers[func] = tuple(i + j for i, j in zip(caller, new_callers[func]))
+            else:
+                # format used by profile
+                new_callers[func] += caller
+        else:
+            new_callers[func] = caller
+    return new_callers
+
+def count_calls(callers):
+    """Sum the caller statistics to get total number of calls received."""
+    nc = 0
+    for calls in callers.values():
+        nc += calls
+    return nc
+
+#**************************************************************************
+# The following functions support printing of reports
+#**************************************************************************
+
+def f8(x):
+    return "%8.3f" % x
+
+#**************************************************************************
+# Statistics browser added by ESR, April 2001
+#**************************************************************************
+
+if __name__ == '__main__':
+    import cmd
+    try:
+        import readline  # noqa: F401
+    except ImportError:
+        pass
+
+    class ProfileBrowser(cmd.Cmd):
+        def __init__(self, profile=None):
+            cmd.Cmd.__init__(self)
+            self.prompt = "% "
+            self.stats = None
+            self.stream = sys.stdout
+            if profile is not None:
+                self.do_read(profile)
+
+        def generic(self, fn, line):
+            args = line.split()
+            processed = []
+            for term in args:
+                try:
+                    processed.append(int(term))
+                    continue
+                except ValueError:
+                    pass
+                try:
+                    frac = float(term)
+                    if frac > 1 or frac < 0:
+                        print("Fraction argument must be in [0, 1]", file=self.stream)
+                        continue
+                    processed.append(frac)
+                    continue
+                except ValueError:
+                    pass
+                processed.append(term)
+            if self.stats:
+                getattr(self.stats, fn)(*processed)
+            else:
+                print("No statistics object is loaded.", file=self.stream)
+            return 0
+        def generic_help(self):
+            print("Arguments may be:", file=self.stream)
+            print("* An integer maximum number of entries to print.", file=self.stream)
+            print("* A decimal fractional number between 0 and 1, controlling", file=self.stream)
+            print("  what fraction of selected entries to print.", file=self.stream)
+            print("* A regular expression; only entries with function names", file=self.stream)
+            print("  that match it are printed.", file=self.stream)
+
+        def do_add(self, line):
+            if self.stats:
+                try:
+                    self.stats.add(line)
+                except OSError as e:
+                    print("Failed to load statistics for %s: %s" % (line, e), file=self.stream)
+            else:
+                print("No statistics object is loaded.", file=self.stream)
+            return 0
+        def help_add(self):
+            print("Add profile info from given file to current statistics object.", file=self.stream)
+
+        def do_callees(self, line):
+            return self.generic('print_callees', line)
+        def help_callees(self):
+            print("Print callees statistics from the current stat object.", file=self.stream)
+            self.generic_help()
+
+        def do_callers(self, line):
+            return self.generic('print_callers', line)
+        def help_callers(self):
+            print("Print callers statistics from the current stat object.", file=self.stream)
+            self.generic_help()
+
+        def do_EOF(self, line):
+            print("", file=self.stream)
+            return 1
+        def help_EOF(self):
+            print("Leave the profile browser.", file=self.stream)
+
+        def do_quit(self, line):
+            return 1
+        def help_quit(self):
+            print("Leave the profile browser.", file=self.stream)
+
+        def do_read(self, line):
+            if line:
+                try:
+                    self.stats = Stats(line)
+                except OSError as err:
+                    print(err.args[1], file=self.stream)
+                    return
+                except Exception as err:
+                    print(err.__class__.__name__ + ':', err, file=self.stream)
+                    return
+                self.prompt = line + "% "
+            elif len(self.prompt) > 2:
+                line = self.prompt[:-2]
+                self.do_read(line)
+            else:
+                print("No statistics object is current -- cannot reload.", file=self.stream)
+            return 0
+        def help_read(self):
+            print("Read in profile data from a specified file.", file=self.stream)
+            print("Without argument, reload the current file.", file=self.stream)
+
+        def do_reverse(self, line):
+            if self.stats:
+                self.stats.reverse_order()
+            else:
+                print("No statistics object is loaded.", file=self.stream)
+            return 0
+        def help_reverse(self):
+            print("Reverse the sort order of the profiling report.", file=self.stream)
+
+        def do_sort(self, line):
+            if not self.stats:
+                print("No statistics object is loaded.", file=self.stream)
+                return
+            abbrevs = self.stats.get_sort_arg_defs()
+            if line and all((x in abbrevs) for x in line.split()):
+                self.stats.sort_stats(*line.split())
+            else:
+                print("Valid sort keys (unique prefixes are accepted):", file=self.stream)
+                for (key, value) in Stats.sort_arg_dict_default.items():
+                    print("%s -- %s" % (key, value[1]), file=self.stream)
+            return 0
+        def help_sort(self):
+            print("Sort profile data according to specified keys.", file=self.stream)
+            print("(Typing `sort' without arguments lists valid keys.)", file=self.stream)
+        def complete_sort(self, text, *args):
+            return [a for a in Stats.sort_arg_dict_default if a.startswith(text)]
+
+        def do_stats(self, line):
+            return self.generic('print_stats', line)
+        def help_stats(self):
+            print("Print statistics from the current stat object.", file=self.stream)
+            self.generic_help()
+
+        def do_strip(self, line):
+            if self.stats:
+                self.stats.strip_dirs()
+            else:
+                print("No statistics object is loaded.", file=self.stream)
+        def help_strip(self):
+            print("Strip leading path information from filenames in the report.", file=self.stream)
+
+        def help_help(self):
+            print("Show help for a given command.", file=self.stream)
+
+        def postcmd(self, stop, line):
+            if stop:
+                return stop
+            return None
+
+    if len(sys.argv) > 1:
+        initprofile = sys.argv[1]
+    else:
+        initprofile = None
+    try:
+        browser = ProfileBrowser(initprofile)
+        for profile in sys.argv[2:]:
+            browser.do_add(profile)
+        print("Welcome to the profile statistics browser.", file=browser.stream)
+        browser.cmdloop()
+        print("Goodbye.", file=browser.stream)
+    except KeyboardInterrupt:
+        pass
+
+# That's all, folks.

Lib/pty.py

@@ -32,27 +32,18 @@ def openpty():
     except (AttributeError, OSError):
         pass
     master_fd, slave_name = _open_terminal()
-    slave_fd = slave_open(slave_name)
-    return master_fd, slave_fd
-
-def master_open():
-    """master_open() -> (master_fd, slave_name)
-    Open a pty master and return the fd, and the filename of the slave end.
-    Deprecated, use openpty() instead."""
-
-    import warnings
-    warnings.warn("Use pty.openpty() instead.", DeprecationWarning, stacklevel=2)  # Remove API in 3.14
 
+    slave_fd = os.open(slave_name, os.O_RDWR)
     try:
-        master_fd, slave_fd = os.openpty()
+        from fcntl import ioctl, I_PUSH
-    except (AttributeError, OSError):
+    except ImportError:
+         return master_fd, slave_fd
+    try:
+        ioctl(slave_fd, I_PUSH, "ptem")
+        ioctl(slave_fd, I_PUSH, "ldterm")
+    except OSError:
         pass
-    else:
+    return master_fd, slave_fd
-        slave_name = os.ttyname(slave_fd)
-        os.close(slave_fd)
-        return master_fd, slave_name
-
-    return _open_terminal()
 
 def _open_terminal():
     """Open pty master and return (master_fd, tty_name)."""
@@ -66,26 +57,6 @@ def _open_terminal():
             return (fd, '/dev/tty' + x + y)
     raise OSError('out of pty devices')
 
-def slave_open(tty_name):
-    """slave_open(tty_name) -> slave_fd
-    Open the pty slave and acquire the controlling terminal, returning
-    opened filedescriptor.
-    Deprecated, use openpty() instead."""
-
-    import warnings
-    warnings.warn("Use pty.openpty() instead.", DeprecationWarning, stacklevel=2)  # Remove API in 3.14
-
-    result = os.open(tty_name, os.O_RDWR)
-    try:
-        from fcntl import ioctl, I_PUSH
-    except ImportError:
-        return result
-    try:
-        ioctl(result, I_PUSH, "ptem")
-        ioctl(result, I_PUSH, "ldterm")
-    except OSError:
-        pass
-    return result
 
 def fork():
     """fork() -> (pid, master_fd)

Lib/pydoc_data/module_docs.py

@@ -1,4 +1,4 @@
-# Autogenerated by Sphinx on Tue Feb  3 17:32:13 2026
+# Autogenerated by Sphinx on Sun May 10 13:21:26 2026
 # as part of the release process.
 
 module_docs = {

Lib/random.py

@@ -836,7 +836,11 @@ class Random(_random.Random):
             if not c:
                 return x
             while True:
-                y += _floor(_log2(random()) / c) + 1
+                try:
+                    y += _floor(_log2(random()) / c) + 1
+                except ValueError:
+                    # Reject case where random() returned 0.0
+                    continue
                 if y > n:
                     return x
                 x += 1
@@ -844,8 +848,8 @@ class Random(_random.Random):
         # BTRS: Transformed rejection with squeeze method by Wolfgang Hörmann
         # https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.47.8407&rep=rep1&type=pdf
         assert n*p >= 10.0 and p <= 0.5
-        setup_complete = False
 
+        setup_complete = False
         spq = _sqrt(n * p * (1.0 - p))  # Standard deviation of the distribution
         b = 1.15 + 2.53 * spq
         a = -0.0873 + 0.0248 * b + 0.01 * p
@@ -860,22 +864,23 @@ class Random(_random.Random):
             k = _floor((2.0 * a / us + b) * u + c)
             if k < 0 or k > n:
                 continue
+            v = random()
 
             # The early-out "squeeze" test substantially reduces
             # the number of acceptance condition evaluations.
-            v = random()
             if us >= 0.07 and v <= vr:
                 return k
 
-            # Acceptance-rejection test.
-            # Note, the original paper erroneously omits the call to log(v)
-            # when comparing to the log of the rescaled binomial distribution.
             if not setup_complete:
                 alpha = (2.83 + 5.1 / b) * spq
                 lpq = _log(p / (1.0 - p))
                 m = _floor((n + 1) * p)         # Mode of the distribution
                 h = _lgamma(m + 1) + _lgamma(n - m + 1)
                 setup_complete = True           # Only needs to be done once
+
+            # Acceptance-rejection test.
+            # Note, the original paper erroneously omits the call to log(v)
+            # when comparing to the log of the rescaled binomial distribution.
             v *= alpha / (a / (us * us) + b)
             if _log(v) <= h - _lgamma(k + 1) - _lgamma(n - k + 1) + (k - m) * lpq:
                 return k

Lib/runpy.py

@@ -103,8 +103,10 @@ def _run_module_code(code, init_globals=None,
 
 # Helper to get the full name, spec and code for a module
 def _get_module_details(mod_name, error=ImportError):
+    # name= is only accepted by ImportError and its subclasses.
+    kwargs = {"name": mod_name} if issubclass(error, ImportError) else {}
     if mod_name.startswith("."):
-        raise error("Relative module names not supported")
+        raise error("Relative module names not supported", **kwargs)
     pkg_name, _, _ = mod_name.rpartition(".")
     if pkg_name:
         # Try importing the parent to avoid catching initialization errors
@@ -137,12 +139,13 @@ def _get_module_details(mod_name, error=ImportError):
         if mod_name.endswith(".py"):
             msg += (f". Try using '{mod_name[:-3]}' instead of "
                     f"'{mod_name}' as the module name.")
-        raise error(msg.format(mod_name, type(ex).__name__, ex)) from ex
+        raise error(msg.format(mod_name, type(ex).__name__, ex),
+                    **kwargs) from ex
     if spec is None:
-        raise error("No module named %s" % mod_name)
+        raise error("No module named %s" % mod_name, **kwargs)
     if spec.submodule_search_locations is not None:
         if mod_name == "__main__" or mod_name.endswith(".__main__"):
-            raise error("Cannot use package as __main__ module")
+            raise error("Cannot use package as __main__ module", **kwargs)
         try:
             pkg_main_name = mod_name + ".__main__"
             return _get_module_details(pkg_main_name, error)
@@ -150,17 +153,19 @@ def _get_module_details(mod_name, error=ImportError):
             if mod_name not in sys.modules:
                 raise  # No module loaded; being a package is irrelevant
             raise error(("%s; %r is a package and cannot " +
-                               "be directly executed") %(e, mod_name))
+                               "be directly executed") %(e, mod_name),
+                        **kwargs)
     loader = spec.loader
     if loader is None:
         raise error("%r is a namespace package and cannot be executed"
-                                                                 % mod_name)
+                                                                 % mod_name,
+                    **kwargs)
     try:
         code = loader.get_code(mod_name)
     except ImportError as e:
-        raise error(format(e)) from e
+        raise error(format(e), **kwargs) from e
     if code is None:
-        raise error("No code object available for %s" % mod_name)
+        raise error("No code object available for %s" % mod_name, **kwargs)
     return mod_name, spec, code
 
 class _Error(Exception):
@@ -234,6 +239,7 @@ def _get_main_module_details(error=ImportError):
     # Also moves the standard __main__ out of the way so that the
     # preexisting __loader__ entry doesn't cause issues
     main_name = "__main__"
+    kwargs = {"name": main_name} if issubclass(error, ImportError) else {}
     saved_main = sys.modules[main_name]
     del sys.modules[main_name]
     try:
@@ -241,7 +247,8 @@ def _get_main_module_details(error=ImportError):
     except ImportError as exc:
         if main_name in str(exc):
             raise error("can't find %r module in %r" %
-                              (main_name, sys.path[0])) from exc
+                              (main_name, sys.path[0]),
+                        **kwargs) from exc
         raise
     finally:
         sys.modules[main_name] = saved_main

Lib/shutil.py

@@ -1314,27 +1314,9 @@ def _unpack_zipfile(filename, extract_dir):
     if not zipfile.is_zipfile(filename):
         raise ReadError("%s is not a zip file" % filename)
 
-    zip = zipfile.ZipFile(filename)
+    with zipfile.ZipFile(filename) as zip:
-    try:
+        zip._ignore_invalid_names = True
-        for info in zip.infolist():
+        zip.extractall(extract_dir)
-            name = info.filename
-
-            # don't extract absolute paths or ones with .. in them
-            if name.startswith('/') or '..' in name:
-                continue
-
-            targetpath = os.path.join(extract_dir, *name.split('/'))
-            if not targetpath:
-                continue
-
-            _ensure_directory(targetpath)
-            if not name.endswith('/'):
-                # file
-                with zip.open(name, 'r') as source, \
-                        open(targetpath, 'wb') as target:
-                    copyfileobj(source, target)
-    finally:
-        zip.close()
 
 def _unpack_tarfile(filename, extract_dir, *, filter=None):
     """Unpack tar/tar.gz/tar.bz2/tar.xz/tar.zst `filename` to `extract_dir`

Lib/site.py

@@ -290,7 +290,7 @@ def check_enableusersite():
 
 # Copy of sysconfig._get_implementation()
 def _get_implementation():
-    return 'RustPython' # XXX: RustPython; for site-packages
+    return 'RustPython' # XXX: RUSTPYTHON; for site-packages
 
 # Copy of sysconfig._getuserbase()
 def _getuserbase():

Lib/smtplib.py

@@ -251,7 +251,6 @@ class SMTP:
         will be used.
 
         """
-        self._host = host
         self.timeout = timeout
         self.esmtp_features = {}
         self.command_encoding = 'ascii'
@@ -342,6 +341,7 @@ class SMTP:
                     port = int(port)
                 except ValueError:
                     raise OSError("nonnumeric port")
+        self._host = host
         if not port:
             port = self.default_port
         sys.audit("smtplib.connect", self, host, port)

Lib/socket.py

@@ -640,18 +640,22 @@ def _fallback_socketpair(family=AF_INET, type=SOCK_STREAM, proto=0):
     # Authenticating avoids using a connection from something else
     # able to connect to {host}:{port} instead of us.
     # We expect only AF_INET and AF_INET6 families.
-    try:
+    #
-        if (
+    # Note that we skip this on WASI because on that platorm the client socket
-            ssock.getsockname() != csock.getpeername()
+    # may not have finished connecting by the time we've reached this point (gh-146139).
-            or csock.getsockname() != ssock.getpeername()
+    if sys.platform != "wasi":
-        ):
+        try:
-            raise ConnectionError("Unexpected peer connection")
+            if (
-    except:
+                    ssock.getsockname() != csock.getpeername()
-        # getsockname() and getpeername() can fail
+                    or csock.getsockname() != ssock.getpeername()
-        # if either socket isn't connected.
+            ):
-        ssock.close()
+                raise ConnectionError("Unexpected peer connection")
-        csock.close()
+        except:
-        raise
+            # getsockname() and getpeername() can fail
+            # if either socket isn't connected.
+            ssock.close()
+            csock.close()
+            raise
 
     return (ssock, csock)
 

Lib/subprocess.py

@@ -351,15 +351,16 @@ def _args_from_interpreter_flags():
     # -X options
     if dev_mode:
         args.extend(('-X', 'dev'))
-    for opt in ('faulthandler', 'tracemalloc', 'importtime',
+    for opt in sorted(xoptions):
-                'frozen_modules', 'showrefcount', 'utf8', 'gil'):
+        if opt == 'dev':
-        if opt in xoptions:
+            # handled above via sys.flags.dev_mode
-            value = xoptions[opt]
+            continue
-            if value is True:
+        value = xoptions[opt]
-                arg = opt
+        if value is True:
-            else:
+            arg = opt
-                arg = '%s=%s' % (opt, value)
+        else:
-            args.extend(('-X', arg))
+            arg = '%s=%s' % (opt, value)
+        args.extend(('-X', arg))
 
     return args
 

Lib/sysconfig/__init__.py

@@ -107,7 +107,7 @@ else:
     _INSTALL_SCHEMES['venv'] = _INSTALL_SCHEMES['posix_venv']
 
 def _get_implementation():
-    return 'RustPython' # XXX: For site-packages
+    return 'RustPython'  # XXX: RUSTPYTHON; For site-packages
 
 # NOTE: site.py has copy of this function.
 # Sync it when modify this function.
@@ -698,11 +698,19 @@ def get_platform():
         release = get_config_var("ANDROID_API_LEVEL")
 
         # Wheel tags use the ABI names from Android's own tools.
+        # When Python is running on 32-bit ARM Android on a 64-bit ARM kernel,
+        # 'os.uname().machine' is 'armv8l'. Such devices run the same userspace
+        # code as 'armv7l' devices.
+        # During the build process of the Android testbed when targeting 32-bit ARM,
+        # '_PYTHON_HOST_PLATFORM' is 'arm-linux-androideabi', so 'machine' becomes
+        # 'arm'.
         machine = {
-            "x86_64": "x86_64",
-            "i686": "x86",
             "aarch64": "arm64_v8a",
+            "arm": "armeabi_v7a",
             "armv7l": "armeabi_v7a",
+            "armv8l": "armeabi_v7a",
+            "i686": "x86",
+            "x86_64": "x86_64",
         }[machine]
     elif osname == "linux":
         # At least on Linux/Intel, 'machine' is the processor --

Lib/tarfile.py

@@ -1278,6 +1278,20 @@ class TarInfo(object):
     @classmethod
     def frombuf(cls, buf, encoding, errors):
         """Construct a TarInfo object from a 512 byte bytes object.
+
+        To support the old v7 tar format AREGTYPE headers are
+        transformed to DIRTYPE headers if their name ends in '/'.
+        """
+        return cls._frombuf(buf, encoding, errors)
+
+    @classmethod
+    def _frombuf(cls, buf, encoding, errors, *, dircheck=True):
+        """Construct a TarInfo object from a 512 byte bytes object.
+
+        If ``dircheck`` is set to ``True`` then ``AREGTYPE`` headers will
+        be normalized to ``DIRTYPE`` if the name ends in a trailing slash.
+        ``dircheck`` must be set to ``False`` if this function is called
+        on a follow-up header such as ``GNUTYPE_LONGNAME``.
         """
         if len(buf) == 0:
             raise EmptyHeaderError("empty header")
@@ -1308,7 +1322,7 @@ class TarInfo(object):
 
         # Old V7 tar format represents a directory as a regular
         # file with a trailing slash.
-        if obj.type == AREGTYPE and obj.name.endswith("/"):
+        if dircheck and obj.type == AREGTYPE and obj.name.endswith("/"):
             obj.type = DIRTYPE
 
         # The old GNU sparse format occupies some of the unused
@@ -1343,8 +1357,15 @@ class TarInfo(object):
         """Return the next TarInfo object from TarFile object
            tarfile.
         """
+        return cls._fromtarfile(tarfile)
+
+    @classmethod
+    def _fromtarfile(cls, tarfile, *, dircheck=True):
+        """
+        See dircheck documentation in _frombuf().
+        """
         buf = tarfile.fileobj.read(BLOCKSIZE)
-        obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
+        obj = cls._frombuf(buf, tarfile.encoding, tarfile.errors, dircheck=dircheck)
         obj.offset = tarfile.fileobj.tell() - BLOCKSIZE
         return obj._proc_member(tarfile)
 
@@ -1402,7 +1423,7 @@ class TarInfo(object):
 
         # Fetch the next header and process it.
         try:
-            next = self.fromtarfile(tarfile)
+            next = self._fromtarfile(tarfile, dircheck=False)
         except HeaderError as e:
             raise SubsequentHeaderError(str(e)) from None
 
@@ -1537,7 +1558,7 @@ class TarInfo(object):
 
         # Fetch the next header.
         try:
-            next = self.fromtarfile(tarfile)
+            next = self._fromtarfile(tarfile, dircheck=False)
         except HeaderError as e:
             raise SubsequentHeaderError(str(e)) from None
 

Lib/tempfile.py

@@ -57,10 +57,11 @@ _bin_openflags = _text_openflags
 if hasattr(_os, 'O_BINARY'):
     _bin_openflags |= _os.O_BINARY
 
-if hasattr(_os, 'TMP_MAX'):
+# This is more than enough.
-    TMP_MAX = _os.TMP_MAX
+# Each name contains over 40 random bits.  Even with a million temporary
-else:
+# files, the chance of a conflict is less than 1 in a million, and with
-    TMP_MAX = 10000
+# 20 attempts, it is less than 1e-120.
+TMP_MAX = 20
 
 # This variable _was_ unused for legacy reasons, see issue 10354.
 # But as of 3.5 we actually use it at runtime so changing it would
@@ -196,8 +197,7 @@ def _get_default_tempdir(dirlist=None):
     for dir in dirlist:
         if dir != _os.curdir:
             dir = _os.path.abspath(dir)
-        # Try only a few names per directory.
+        for seq in range(TMP_MAX):
-        for seq in range(100):
             name = next(namer)
             filename = _os.path.join(dir, name)
             try:
@@ -213,10 +213,8 @@ def _get_default_tempdir(dirlist=None):
             except FileExistsError:
                 pass
             except PermissionError:
-                # This exception is thrown when a directory with the chosen name
+                # See the comment in mkdtemp().
-                # already exists on windows.
+                if _os.name == 'nt' and _os.path.isdir(dir):
-                if (_os.name == 'nt' and _os.path.isdir(dir) and
-                    _os.access(dir, _os.W_OK)):
                     continue
                 break   # no point trying more names in this directory
             except OSError:
@@ -258,10 +256,8 @@ def _mkstemp_inner(dir, pre, suf, flags, output_type):
         except FileExistsError:
             continue    # try again
         except PermissionError:
-            # This exception is thrown when a directory with the chosen name
+            # See the comment in mkdtemp().
-            # already exists on windows.
+            if _os.name == 'nt' and _os.path.isdir(dir) and seq < TMP_MAX - 1:
-            if (_os.name == 'nt' and _os.path.isdir(dir) and
-                _os.access(dir, _os.W_OK)):
                 continue
             else:
                 raise
@@ -386,10 +382,14 @@ def mkdtemp(suffix=None, prefix=None, dir=None):
         except FileExistsError:
             continue    # try again
         except PermissionError:
-            # This exception is thrown when a directory with the chosen name
+            # On Posix, this exception is raised when the user has no
-            # already exists on windows.
+            # write access to the parent directory.
-            if (_os.name == 'nt' and _os.path.isdir(dir) and
+            # On Windows, it is also raised when a directory with
-                _os.access(dir, _os.W_OK)):
+            # the chosen name already exists, or if the parent directory
+            # is not a directory.
+            # We cannot distinguish between "directory-exists-error" and
+            # "access-denied-error".
+            if _os.name == 'nt' and _os.path.isdir(dir) and seq < TMP_MAX - 1:
                 continue
             else:
                 raise

Lib/test/_test_embed_structseq.py

@@ -0,0 +1,62 @@
+import sys
+import types
+import unittest
+
+
+# bpo-46417: Test that structseq types used by the sys module are still
+# valid when Py_Finalize()/Py_Initialize() are called multiple times.
+class TestStructSeq(unittest.TestCase):
+    # test PyTypeObject members
+    def check_structseq(self, obj_type):
+        # ob_refcnt
+        self.assertGreaterEqual(sys.getrefcount(obj_type), 1)
+        # tp_base
+        self.assertIsSubclass(obj_type, tuple)
+        # tp_bases
+        self.assertEqual(obj_type.__bases__, (tuple,))
+        # tp_dict
+        self.assertIsInstance(obj_type.__dict__, types.MappingProxyType)
+        # tp_mro
+        self.assertEqual(obj_type.__mro__, (obj_type, tuple, object))
+        # tp_name
+        self.assertIsInstance(type.__name__, str)
+        # tp_subclasses
+        self.assertEqual(obj_type.__subclasses__(), [])
+
+    def test_sys_attrs(self):
+        for attr_name in (
+            'flags',          # FlagsType
+            'float_info',     # FloatInfoType
+            'hash_info',      # Hash_InfoType
+            'int_info',       # Int_InfoType
+            'thread_info',    # ThreadInfoType
+            'version_info',   # VersionInfoType
+        ):
+            with self.subTest(attr=attr_name):
+                attr = getattr(sys, attr_name)
+                self.check_structseq(type(attr))
+
+    def test_sys_funcs(self):
+        func_names = ['get_asyncgen_hooks']  # AsyncGenHooksType
+        if hasattr(sys, 'getwindowsversion'):
+            func_names.append('getwindowsversion')  # WindowsVersionType
+        for func_name in func_names:
+            with self.subTest(func=func_name):
+                func = getattr(sys, func_name)
+                obj = func()
+                self.check_structseq(type(obj))
+
+
+try:
+    unittest.main(
+        module=(
+            '__main__'
+            if __name__ == '__main__'
+            # Avoiding a circular import:
+            else sys.modules['test._test_embed_structseq']
+        )
+    )
+except SystemExit as exc:
+    if exc.args[0] != 0:
+        raise
+print("Tests passed")

Lib/test/audit-tests.py

@@ -0,0 +1,681 @@
+"""This script contains the actual auditing tests.
+
+It should not be imported directly, but should be run by the test_audit
+module with arguments identifying each test.
+
+"""
+
+import contextlib
+import os
+import sys
+
+
+class TestHook:
+    """Used in standard hook tests to collect any logged events.
+
+    Should be used in a with block to ensure that it has no impact
+    after the test completes.
+    """
+
+    def __init__(self, raise_on_events=None, exc_type=RuntimeError):
+        self.raise_on_events = raise_on_events or ()
+        self.exc_type = exc_type
+        self.seen = []
+        self.closed = False
+
+    def __enter__(self, *a):
+        sys.addaudithook(self)
+        return self
+
+    def __exit__(self, *a):
+        self.close()
+
+    def close(self):
+        self.closed = True
+
+    @property
+    def seen_events(self):
+        return [i[0] for i in self.seen]
+
+    def __call__(self, event, args):
+        if self.closed:
+            return
+        self.seen.append((event, args))
+        if event in self.raise_on_events:
+            raise self.exc_type("saw event " + event)
+
+
+# Simple helpers, since we are not in unittest here
+def assertEqual(x, y):
+    if x != y:
+        raise AssertionError(f"{x!r} should equal {y!r}")
+
+
+def assertIn(el, series):
+    if el not in series:
+        raise AssertionError(f"{el!r} should be in {series!r}")
+
+
+def assertNotIn(el, series):
+    if el in series:
+        raise AssertionError(f"{el!r} should not be in {series!r}")
+
+
+def assertSequenceEqual(x, y):
+    if len(x) != len(y):
+        raise AssertionError(f"{x!r} should equal {y!r}")
+    if any(ix != iy for ix, iy in zip(x, y)):
+        raise AssertionError(f"{x!r} should equal {y!r}")
+
+
+@contextlib.contextmanager
+def assertRaises(ex_type):
+    try:
+        yield
+        assert False, f"expected {ex_type}"
+    except BaseException as ex:
+        if isinstance(ex, AssertionError):
+            raise
+        assert type(ex) is ex_type, f"{ex} should be {ex_type}"
+
+
+def test_basic():
+    with TestHook() as hook:
+        sys.audit("test_event", 1, 2, 3)
+        assertEqual(hook.seen[0][0], "test_event")
+        assertEqual(hook.seen[0][1], (1, 2, 3))
+
+
+def test_block_add_hook():
+    # Raising an exception should prevent a new hook from being added,
+    # but will not propagate out.
+    with TestHook(raise_on_events="sys.addaudithook") as hook1:
+        with TestHook() as hook2:
+            sys.audit("test_event")
+            assertIn("test_event", hook1.seen_events)
+            assertNotIn("test_event", hook2.seen_events)
+
+
+def test_block_add_hook_baseexception():
+    # Raising BaseException will propagate out when adding a hook
+    with assertRaises(BaseException):
+        with TestHook(
+            raise_on_events="sys.addaudithook", exc_type=BaseException
+        ) as hook1:
+            # Adding this next hook should raise BaseException
+            with TestHook() as hook2:
+                pass
+
+
+def test_marshal():
+    import marshal
+    o = ("a", "b", "c", 1, 2, 3)
+    payload = marshal.dumps(o)
+
+    with TestHook() as hook:
+        assertEqual(o, marshal.loads(marshal.dumps(o)))
+
+        try:
+            with open("test-marshal.bin", "wb") as f:
+                marshal.dump(o, f)
+            with open("test-marshal.bin", "rb") as f:
+                assertEqual(o, marshal.load(f))
+        finally:
+            os.unlink("test-marshal.bin")
+
+    actual = [(a[0], a[1]) for e, a in hook.seen if e == "marshal.dumps"]
+    assertSequenceEqual(actual, [(o, marshal.version)] * 2)
+
+    actual = [a[0] for e, a in hook.seen if e == "marshal.loads"]
+    assertSequenceEqual(actual, [payload])
+
+    actual = [e for e, a in hook.seen if e == "marshal.load"]
+    assertSequenceEqual(actual, ["marshal.load"])
+
+
+def test_pickle():
+    import pickle
+
+    class PicklePrint:
+        def __reduce_ex__(self, p):
+            return str, ("Pwned!",)
+
+    payload_1 = pickle.dumps(PicklePrint())
+    payload_2 = pickle.dumps(("a", "b", "c", 1, 2, 3))
+
+    # Before we add the hook, ensure our malicious pickle loads
+    assertEqual("Pwned!", pickle.loads(payload_1))
+
+    with TestHook(raise_on_events="pickle.find_class") as hook:
+        with assertRaises(RuntimeError):
+            # With the hook enabled, loading globals is not allowed
+            pickle.loads(payload_1)
+        # pickles with no globals are okay
+        pickle.loads(payload_2)
+
+
+def test_monkeypatch():
+    class A:
+        pass
+
+    class B:
+        pass
+
+    class C(A):
+        pass
+
+    a = A()
+
+    with TestHook() as hook:
+        # Catch name changes
+        C.__name__ = "X"
+        # Catch type changes
+        C.__bases__ = (B,)
+        # Ensure bypassing __setattr__ is still caught
+        type.__dict__["__bases__"].__set__(C, (B,))
+        # Catch attribute replacement
+        C.__init__ = B.__init__
+        # Catch attribute addition
+        C.new_attr = 123
+        # Catch class changes
+        a.__class__ = B
+
+    actual = [(a[0], a[1]) for e, a in hook.seen if e == "object.__setattr__"]
+    assertSequenceEqual(
+        [(C, "__name__"), (C, "__bases__"), (C, "__bases__"), (a, "__class__")], actual
+    )
+
+
+def test_open(testfn):
+    # SSLContext.load_dh_params uses Py_fopen() rather than normal open()
+    try:
+        import ssl
+
+        load_dh_params = ssl.create_default_context().load_dh_params
+    except ImportError:
+        load_dh_params = None
+
+    try:
+        import readline
+    except ImportError:
+        readline = None
+
+    def rl(name):
+        if readline:
+            return getattr(readline, name, None)
+        else:
+            return None
+
+    # Try a range of "open" functions.
+    # All of them should fail
+    with TestHook(raise_on_events={"open"}) as hook:
+        for fn, *args in [
+            (open, testfn, "r"),
+            (open, sys.executable, "rb"),
+            (open, 3, "wb"),
+            (open, testfn, "w", -1, None, None, None, False, lambda *a: 1),
+            (load_dh_params, testfn),
+            (rl("read_history_file"), testfn),
+            (rl("read_history_file"), None),
+            (rl("write_history_file"), testfn),
+            (rl("write_history_file"), None),
+            (rl("append_history_file"), 0, testfn),
+            (rl("append_history_file"), 0, None),
+            (rl("read_init_file"), testfn),
+            (rl("read_init_file"), None),
+        ]:
+            if not fn:
+                continue
+            with assertRaises(RuntimeError):
+                try:
+                    fn(*args)
+                except NotImplementedError:
+                    if fn == load_dh_params:
+                        # Not callable in some builds
+                        load_dh_params = None
+                        raise RuntimeError
+                    else:
+                        raise
+
+    actual_mode = [(a[0], a[1]) for e, a in hook.seen if e == "open" and a[1]]
+    actual_flag = [(a[0], a[2]) for e, a in hook.seen if e == "open" and not a[1]]
+    assertSequenceEqual(
+        [
+            i
+            for i in [
+                (testfn, "r"),
+                (sys.executable, "r"),
+                (3, "w"),
+                (testfn, "w"),
+                (testfn, "rb") if load_dh_params else None,
+                (testfn, "r") if readline else None,
+                ("~/.history", "r") if readline else None,
+                (testfn, "w") if readline else None,
+                ("~/.history", "w") if readline else None,
+                (testfn, "a") if rl("append_history_file") else None,
+                ("~/.history", "a") if rl("append_history_file") else None,
+                (testfn, "r") if readline else None,
+                ("<readline_init_file>", "r") if readline else None,
+            ]
+            if i is not None
+        ],
+        actual_mode,
+    )
+    assertSequenceEqual([], actual_flag)
+
+
+def test_cantrace():
+    traced = []
+
+    def trace(frame, event, *args):
+        if frame.f_code == TestHook.__call__.__code__:
+            traced.append(event)
+
+    old = sys.settrace(trace)
+    try:
+        with TestHook() as hook:
+            # No traced call
+            eval("1")
+
+            # No traced call
+            hook.__cantrace__ = False
+            eval("2")
+
+            # One traced call
+            hook.__cantrace__ = True
+            eval("3")
+
+            # Two traced calls (writing to private member, eval)
+            hook.__cantrace__ = 1
+            eval("4")
+
+            # One traced call (writing to private member)
+            hook.__cantrace__ = 0
+    finally:
+        sys.settrace(old)
+
+    assertSequenceEqual(["call"] * 4, traced)
+
+
+def test_mmap():
+    import mmap
+
+    with TestHook() as hook:
+        mmap.mmap(-1, 8)
+        assertEqual(hook.seen[0][1][:2], (-1, 8))
+
+
+def test_ctypes_call_function():
+    import ctypes
+    import _ctypes
+
+    with TestHook() as hook:
+        _ctypes.call_function(ctypes._memmove_addr, (0, 0, 0))
+        assert ("ctypes.call_function", (ctypes._memmove_addr, (0, 0, 0))) in hook.seen, f"{ctypes._memmove_addr=} {hook.seen=}"
+
+        ctypes.CFUNCTYPE(ctypes.c_voidp)(ctypes._memset_addr)(1, 0, 0)
+        assert ("ctypes.call_function", (ctypes._memset_addr, (1, 0, 0))) in hook.seen, f"{ctypes._memset_addr=} {hook.seen=}"
+
+    with TestHook() as hook:
+        ctypes.cast(ctypes.c_voidp(0), ctypes.POINTER(ctypes.c_char))
+        assert "ctypes.call_function" in hook.seen_events
+
+    with TestHook() as hook:
+        ctypes.string_at(id("ctypes.string_at") + 40)
+        assert "ctypes.call_function" in hook.seen_events
+        assert "ctypes.string_at" in hook.seen_events
+
+
+def test_posixsubprocess():
+    import multiprocessing.util
+
+    exe = b"xxx"
+    args = [b"yyy", b"zzz"]
+    with TestHook() as hook:
+        multiprocessing.util.spawnv_passfds(exe, args, ())
+        assert ("_posixsubprocess.fork_exec", ([exe], args, None)) in hook.seen
+
+
+def test_excepthook():
+    def excepthook(exc_type, exc_value, exc_tb):
+        if exc_type is not RuntimeError:
+            sys.__excepthook__(exc_type, exc_value, exc_tb)
+
+    def hook(event, args):
+        if event == "sys.excepthook":
+            if not isinstance(args[2], args[1]):
+                raise TypeError(f"Expected isinstance({args[2]!r}, " f"{args[1]!r})")
+            if args[0] != excepthook:
+                raise ValueError(f"Expected {args[0]} == {excepthook}")
+            print(event, repr(args[2]))
+
+    sys.addaudithook(hook)
+    sys.excepthook = excepthook
+    raise RuntimeError("fatal-error")
+
+
+def test_unraisablehook():
+    from _testcapi import err_formatunraisable
+
+    def unraisablehook(hookargs):
+        pass
+
+    def hook(event, args):
+        if event == "sys.unraisablehook":
+            if args[0] != unraisablehook:
+                raise ValueError(f"Expected {args[0]} == {unraisablehook}")
+            print(event, repr(args[1].exc_value), args[1].err_msg)
+
+    sys.addaudithook(hook)
+    sys.unraisablehook = unraisablehook
+    err_formatunraisable(RuntimeError("nonfatal-error"),
+                         "Exception ignored for audit hook test")
+
+
+def test_winreg():
+    from winreg import OpenKey, EnumKey, CloseKey, HKEY_LOCAL_MACHINE
+
+    def hook(event, args):
+        if not event.startswith("winreg."):
+            return
+        print(event, *args)
+
+    sys.addaudithook(hook)
+
+    k = OpenKey(HKEY_LOCAL_MACHINE, "Software")
+    EnumKey(k, 0)
+    try:
+        EnumKey(k, 10000)
+    except OSError:
+        pass
+    else:
+        raise RuntimeError("Expected EnumKey(HKLM, 10000) to fail")
+
+    kv = k.Detach()
+    CloseKey(kv)
+
+
+def test_socket():
+    import socket
+
+    def hook(event, args):
+        if event.startswith("socket."):
+            print(event, *args)
+
+    sys.addaudithook(hook)
+
+    socket.gethostname()
+
+    # Don't care if this fails, we just want the audit message
+    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    try:
+        # Don't care if this fails, we just want the audit message
+        sock.bind(('127.0.0.1', 8080))
+    except Exception:
+        pass
+    finally:
+        sock.close()
+
+
+def test_gc():
+    import gc
+
+    def hook(event, args):
+        if event.startswith("gc."):
+            print(event, *args)
+
+    sys.addaudithook(hook)
+
+    gc.get_objects(generation=1)
+
+    x = object()
+    y = [x]
+
+    gc.get_referrers(x)
+    gc.get_referents(y)
+
+
+def test_http_client():
+    import http.client
+
+    def hook(event, args):
+        if event.startswith("http.client."):
+            print(event, *args[1:])
+
+    sys.addaudithook(hook)
+
+    conn = http.client.HTTPConnection('www.python.org')
+    try:
+        conn.request('GET', '/')
+    except OSError:
+        print('http.client.send', '[cannot send]')
+    finally:
+        conn.close()
+
+
+def test_sqlite3():
+    import sqlite3
+
+    def hook(event, *args):
+        if event.startswith("sqlite3."):
+            print(event, *args)
+
+    sys.addaudithook(hook)
+    cx1 = sqlite3.connect(":memory:")
+    cx2 = sqlite3.Connection(":memory:")
+
+    # Configured without --enable-loadable-sqlite-extensions
+    try:
+        if hasattr(sqlite3.Connection, "enable_load_extension"):
+            cx1.enable_load_extension(False)
+            try:
+                cx1.load_extension("test")
+            except sqlite3.OperationalError:
+                pass
+            else:
+                raise RuntimeError("Expected sqlite3.load_extension to fail")
+    finally:
+        cx1.close()
+        cx2.close()
+
+def test_sys_getframe():
+    import sys
+
+    def hook(event, args):
+        if event.startswith("sys."):
+            print(event, args[0].f_code.co_name)
+
+    sys.addaudithook(hook)
+    sys._getframe()
+
+
+def test_sys_getframemodulename():
+    import sys
+
+    def hook(event, args):
+        if event.startswith("sys."):
+            print(event, *args)
+
+    sys.addaudithook(hook)
+    sys._getframemodulename()
+
+
+def test_threading():
+    import _thread
+
+    def hook(event, args):
+        if event.startswith(("_thread.", "cpython.PyThreadState", "test.")):
+            print(event, args)
+
+    sys.addaudithook(hook)
+
+    lock = _thread.allocate_lock()
+    lock.acquire()
+
+    class test_func:
+        def __repr__(self): return "<test_func>"
+        def __call__(self):
+            sys.audit("test.test_func")
+            lock.release()
+
+    i = _thread.start_new_thread(test_func(), ())
+    lock.acquire()
+
+    handle = _thread.start_joinable_thread(test_func())
+    handle.join()
+
+
+def test_threading_abort():
+    # Ensures that aborting PyThreadState_New raises the correct exception
+    import _thread
+
+    class ThreadNewAbortError(Exception):
+        pass
+
+    def hook(event, args):
+        if event == "cpython.PyThreadState_New":
+            raise ThreadNewAbortError()
+
+    sys.addaudithook(hook)
+
+    try:
+        _thread.start_new_thread(lambda: None, ())
+    except ThreadNewAbortError:
+        # Other exceptions are raised and the test will fail
+        pass
+
+
+def test_wmi_exec_query():
+    import _wmi
+
+    def hook(event, args):
+        if event.startswith("_wmi."):
+            print(event, args[0])
+
+    sys.addaudithook(hook)
+    try:
+        _wmi.exec_query("SELECT * FROM Win32_OperatingSystem")
+    except WindowsError as e:
+        # gh-112278: WMI may be slow response when first called, but we still
+        # get the audit event, so just ignore the timeout
+        if e.winerror != 258:
+            raise
+
+def test_syslog():
+    import syslog
+
+    def hook(event, args):
+        if event.startswith("syslog."):
+            print(event, *args)
+
+    sys.addaudithook(hook)
+    syslog.openlog('python')
+    syslog.syslog('test')
+    syslog.setlogmask(syslog.LOG_DEBUG)
+    syslog.closelog()
+    # implicit open
+    syslog.syslog('test2')
+    # open with default ident
+    syslog.openlog(logoption=syslog.LOG_NDELAY, facility=syslog.LOG_LOCAL0)
+    sys.argv = None
+    syslog.openlog()
+    syslog.closelog()
+
+
+def test_not_in_gc():
+    import gc
+
+    hook = lambda *a: None
+    sys.addaudithook(hook)
+
+    for o in gc.get_objects():
+        if isinstance(o, list):
+            assert hook not in o
+
+
+def test_time(mode):
+    import time
+
+    def hook(event, args):
+        if event.startswith("time."):
+            if mode == 'print':
+                print(event, *args)
+            elif mode == 'fail':
+                raise AssertionError('hook failed')
+    sys.addaudithook(hook)
+
+    time.sleep(0)
+    time.sleep(0.0625)  # 1/16, a small exact float
+    try:
+        time.sleep(-1)
+    except ValueError:
+        pass
+
+def test_sys_monitoring_register_callback():
+    import sys
+
+    def hook(event, args):
+        if event.startswith("sys.monitoring"):
+            print(event, args)
+
+    sys.addaudithook(hook)
+    sys.monitoring.register_callback(1, 1, None)
+
+
+def test_winapi_createnamedpipe(pipe_name):
+    import _winapi
+
+    def hook(event, args):
+        if event == "_winapi.CreateNamedPipe":
+            print(event, args)
+
+    sys.addaudithook(hook)
+    _winapi.CreateNamedPipe(pipe_name, _winapi.PIPE_ACCESS_DUPLEX, 8, 2, 0, 0, 0, 0)
+
+
+def test_assert_unicode():
+    import sys
+    sys.addaudithook(lambda *args: None)
+    try:
+        sys.audit(9)
+    except TypeError:
+        pass
+    else:
+        raise RuntimeError("Expected sys.audit(9) to fail.")
+
+def test_sys_remote_exec():
+    import tempfile
+
+    pid = os.getpid()
+    event_pid = -1
+    event_script_path = ""
+    remote_event_script_path = ""
+    def hook(event, args):
+        if event not in ["sys.remote_exec", "cpython.remote_debugger_script"]:
+            return
+        print(event, args)
+        match event:
+            case "sys.remote_exec":
+                nonlocal event_pid, event_script_path
+                event_pid = args[0]
+                event_script_path = args[1]
+            case "cpython.remote_debugger_script":
+                nonlocal remote_event_script_path
+                remote_event_script_path = args[0]
+
+    sys.addaudithook(hook)
+    with tempfile.NamedTemporaryFile(mode='w+', delete=True) as tmp_file:
+        tmp_file.write("a = 1+1\n")
+        tmp_file.flush()
+        sys.remote_exec(pid, tmp_file.name)
+        assertEqual(event_pid, pid)
+        assertEqual(event_script_path, tmp_file.name)
+        assertEqual(remote_event_script_path, tmp_file.name)
+
+if __name__ == "__main__":
+    from test.support import suppress_msvcrt_asserts
+
+    suppress_msvcrt_asserts()
+
+    test = sys.argv[1]
+    globals()[test](*sys.argv[2:])

Lib/test/datetimetester.py

@@ -47,7 +47,11 @@ import _strptime
 try:
     import _pydatetime
 except ImportError:
-    pass
+    _pydatetime = None
+try:
+    import _datetime
+except ImportError:
+    _datetime = None
 #
 
 pickle_loads = {pickle.loads, pickle._loads}
@@ -3011,7 +3015,6 @@ class TestDateTime(TestDate):
             self.assertEqual(t.strftime("%z"), "-0200" + z)
             self.assertEqual(t.strftime("%:z"), "-02:00:" + z)
 
-    @unittest.skip("TODO: RUSTPYTHON")
     def test_strftime_special(self):
         t = self.theclass(2004, 12, 31, 6, 22, 33, 47)
         s1 = t.strftime('%c')
@@ -3879,7 +3882,6 @@ class TestTime(HarmlessMixedComparison, unittest.TestCase):
         # gh-85432: The parameter was named "fmt" in the pure-Python impl.
         t.strftime(format="%f")
 
-    @unittest.skip("TODO: RUSTPYTHON")
     def test_strftime_special(self):
         t = self.theclass(1, 2, 3, 4)
         s1 = t.strftime('%I%p%Z')
@@ -4360,7 +4362,6 @@ class TestTimeTZ(TestTime, TZInfoBase, unittest.TestCase):
         self.assertEqual(t.microsecond, 0)
         self.assertIsNone(t.tzinfo)
 
-    @unittest.skip("TODO: RUSTPYTHON")
     def test_zones(self):
         est = FixedOffset(-300, "EST", 1)
         utc = FixedOffset(0, "UTC", -2)

Lib/test/exception_hierarchy.txt

@@ -40,6 +40,7 @@ BaseException
       ├── ReferenceError
       ├── RuntimeError
       │    ├── NotImplementedError
+      │    ├── PythonFinalizationError
       │    └── RecursionError
       ├── StopAsyncIteration
       ├── StopIteration

Lib/test/picklecommon.py

@@ -0,0 +1,390 @@
+# Classes used for pickle testing.
+# They are moved to separate file, so they can be loaded
+# in other Python version for test_xpickle.
+
+import sys
+
+class C:
+    def __eq__(self, other):
+        return self.__dict__ == other.__dict__
+
+# For test_load_classic_instance
+class D(C):
+    def __init__(self, arg):
+        pass
+
+class E(C):
+    def __getinitargs__(self):
+        return ()
+
+import __main__
+__main__.C = C
+C.__module__ = "__main__"
+__main__.D = D
+D.__module__ = "__main__"
+__main__.E = E
+E.__module__ = "__main__"
+
+# Simple mutable object.
+class Object(object):
+    pass
+
+# Hashable immutable key object containing unheshable mutable data.
+class K:
+    def __init__(self, value):
+        self.value = value
+
+    def __reduce__(self):
+        # Shouldn't support the recursion itself
+        return K, (self.value,)
+
+class WithSlots(object):
+    __slots__ = ('a', 'b')
+
+class WithSlotsSubclass(WithSlots):
+    __slots__ = ('c',)
+
+class WithSlotsAndDict(object):
+    __slots__ = ('a', '__dict__')
+
+class WithPrivateAttrs(object):
+    def __init__(self, a):
+        self.__private = a
+    def get(self):
+        return self.__private
+
+class WithPrivateAttrsSubclass(WithPrivateAttrs):
+    def __init__(self, a, b):
+        super().__init__(a)
+        self.__private = b
+    def get2(self):
+        return self.__private
+
+class WithPrivateSlots(object):
+    __slots__ = ('__private',)
+    def __init__(self, a):
+        self.__private = a
+    def get(self):
+        return self.__private
+
+class WithPrivateSlotsSubclass(WithPrivateSlots):
+    __slots__ = ('__private',)
+    def __init__(self, a, b):
+        super().__init__(a)
+        self.__private = b
+    def get2(self):
+        return self.__private
+
+# For test_misc
+class myint(int):
+    def __init__(self, x):
+        self.str = str(x)
+
+# For test_misc and test_getinitargs
+class initarg(C):
+
+    def __init__(self, a, b):
+        self.a = a
+        self.b = b
+
+    def __getinitargs__(self):
+        return self.a, self.b
+
+# For test_metaclass
+class metaclass(type):
+    pass
+
+if sys.version_info >= (3,):
+    # Syntax not compatible with Python 2
+    exec('''
+class use_metaclass(object, metaclass=metaclass):
+    pass
+''')
+else:
+    class use_metaclass(object):
+        __metaclass__ = metaclass
+
+
+# Test classes for reduce_ex
+
+class R:
+    def __init__(self, reduce=None):
+        self.reduce = reduce
+    def __reduce__(self, proto):
+        return self.reduce
+
+class REX:
+    def __init__(self, reduce_ex=None):
+        self.reduce_ex = reduce_ex
+    def __reduce_ex__(self, proto):
+        return self.reduce_ex
+
+class REX_one(object):
+    """No __reduce_ex__ here, but inheriting it from object"""
+    _reduce_called = 0
+    def __reduce__(self):
+        self._reduce_called = 1
+        return REX_one, ()
+
+class REX_two(object):
+    """No __reduce__ here, but inheriting it from object"""
+    _proto = None
+    def __reduce_ex__(self, proto):
+        self._proto = proto
+        return REX_two, ()
+
+class REX_three(object):
+    _proto = None
+    def __reduce_ex__(self, proto):
+        self._proto = proto
+        return REX_two, ()
+    def __reduce__(self):
+        raise AssertionError("This __reduce__ shouldn't be called")
+
+class REX_four(object):
+    """Calling base class method should succeed"""
+    _proto = None
+    def __reduce_ex__(self, proto):
+        self._proto = proto
+        return object.__reduce_ex__(self, proto)
+
+class REX_five(object):
+    """This one used to fail with infinite recursion"""
+    _reduce_called = 0
+    def __reduce__(self):
+        self._reduce_called = 1
+        return object.__reduce__(self)
+
+class REX_six(object):
+    """This class is used to check the 4th argument (list iterator) of
+    the reduce protocol.
+    """
+    def __init__(self, items=None):
+        self.items = items if items is not None else []
+    def __eq__(self, other):
+        return type(self) is type(other) and self.items == other.items
+    def append(self, item):
+        self.items.append(item)
+    def __reduce__(self):
+        return type(self), (), None, iter(self.items), None
+
+class REX_seven(object):
+    """This class is used to check the 5th argument (dict iterator) of
+    the reduce protocol.
+    """
+    def __init__(self, table=None):
+        self.table = table if table is not None else {}
+    def __eq__(self, other):
+        return type(self) is type(other) and self.table == other.table
+    def __setitem__(self, key, value):
+        self.table[key] = value
+    def __reduce__(self):
+        return type(self), (), None, None, iter(self.table.items())
+
+class REX_state(object):
+    """This class is used to check the 3th argument (state) of
+    the reduce protocol.
+    """
+    def __init__(self, state=None):
+        self.state = state
+    def __eq__(self, other):
+        return type(self) is type(other) and self.state == other.state
+    def __setstate__(self, state):
+        self.state = state
+    def __reduce__(self):
+        return type(self), (), self.state
+
+# For test_reduce_ex_None
+class REX_None:
+    """ Setting __reduce_ex__ to None should fail """
+    __reduce_ex__ = None
+
+# For test_reduce_None
+class R_None:
+    """ Setting __reduce__ to None should fail """
+    __reduce__ = None
+
+# For test_pickle_setstate_None
+class C_None_setstate:
+    """  Setting __setstate__ to None should fail """
+    def __getstate__(self):
+        return 1
+
+    __setstate__ = None
+
+
+# Test classes for newobj
+
+# For test_newobj_generic and test_newobj_proxies
+
+class MyInt(int):
+    sample = 1
+
+if sys.version_info >= (3,):
+    class MyLong(int):
+        sample = 1
+else:
+    class MyLong(long):
+        sample = long(1)
+
+class MyFloat(float):
+    sample = 1.0
+
+class MyComplex(complex):
+    sample = 1.0 + 0.0j
+
+class MyStr(str):
+    sample = "hello"
+
+if sys.version_info >= (3,):
+    class MyUnicode(str):
+        sample = "hello \u1234"
+else:
+    class MyUnicode(unicode):
+        sample = unicode(r"hello \u1234", "raw-unicode-escape")
+
+class MyTuple(tuple):
+    sample = (1, 2, 3)
+
+class MyList(list):
+    sample = [1, 2, 3]
+
+class MyDict(dict):
+    sample = {"a": 1, "b": 2}
+
+class MySet(set):
+    sample = {"a", "b"}
+
+class MyFrozenSet(frozenset):
+    sample = frozenset({"a", "b"})
+
+myclasses = [MyInt, MyLong, MyFloat,
+             MyComplex,
+             MyStr, MyUnicode,
+             MyTuple, MyList, MyDict, MySet, MyFrozenSet]
+
+# For test_newobj_overridden_new
+class MyIntWithNew(int):
+    def __new__(cls, value):
+        raise AssertionError
+
+class MyIntWithNew2(MyIntWithNew):
+    __new__ = int.__new__
+
+
+# For test_newobj_list_slots
+class SlotList(MyList):
+    __slots__ = ["foo"]
+
+# Ruff "redefined while unused" false positive here due to `global` variables
+# being assigned (and then restored) from within test methods earlier in the file
+class SimpleNewObj(int):  # noqa: F811
+    def __init__(self, *args, **kwargs):
+        # raise an error, to make sure this isn't called
+        raise TypeError("SimpleNewObj.__init__() didn't expect to get called")
+    def __eq__(self, other):
+        return int(self) == int(other) and self.__dict__ == other.__dict__
+
+class ComplexNewObj(SimpleNewObj):
+    def __getnewargs__(self):
+        return ('%X' % self, 16)
+
+class ComplexNewObjEx(SimpleNewObj):
+    def __getnewargs_ex__(self):
+        return ('%X' % self,), {'base': 16}
+
+
+class ZeroCopyBytes(bytes):
+    readonly = True
+    c_contiguous = True
+    f_contiguous = True
+    zero_copy_reconstruct = True
+
+    def __reduce_ex__(self, protocol):
+        if protocol >= 5:
+            import pickle
+            return type(self)._reconstruct, (pickle.PickleBuffer(self),), None
+        else:
+            return type(self)._reconstruct, (bytes(self),)
+
+    def __repr__(self):
+        return "{}({!r})".format(self.__class__.__name__, bytes(self))
+
+    __str__ = __repr__
+
+    @classmethod
+    def _reconstruct(cls, obj):
+        with memoryview(obj) as m:
+            obj = m.obj
+            if type(obj) is cls:
+                # Zero-copy
+                return obj
+            else:
+                return cls(obj)
+
+
+class ZeroCopyBytearray(bytearray):
+    readonly = False
+    c_contiguous = True
+    f_contiguous = True
+    zero_copy_reconstruct = True
+
+    def __reduce_ex__(self, protocol):
+        if protocol >= 5:
+            import pickle
+            return type(self)._reconstruct, (pickle.PickleBuffer(self),), None
+        else:
+            return type(self)._reconstruct, (bytes(self),)
+
+    def __repr__(self):
+        return "{}({!r})".format(self.__class__.__name__, bytes(self))
+
+    __str__ = __repr__
+
+    @classmethod
+    def _reconstruct(cls, obj):
+        with memoryview(obj) as m:
+            obj = m.obj
+            if type(obj) is cls:
+                # Zero-copy
+                return obj
+            else:
+                return cls(obj)
+
+
+# For test_nested_names
+class Nested:
+    class A:
+        class B:
+            class C:
+                pass
+
+# For test_py_methods
+class PyMethodsTest:
+    @staticmethod
+    def cheese():
+        return "cheese"
+    @classmethod
+    def wine(cls):
+        assert cls is PyMethodsTest
+        return "wine"
+    def biscuits(self):
+        assert isinstance(self, PyMethodsTest)
+        return "biscuits"
+    class Nested:
+        "Nested class"
+        @staticmethod
+        def ketchup():
+            return "ketchup"
+        @classmethod
+        def maple(cls):
+            assert cls is PyMethodsTest.Nested
+            return "maple"
+        def pie(self):
+            assert isinstance(self, PyMethodsTest.Nested)
+            return "pie"
+
+# For test_c_methods
+class Subclass(tuple):
+    class Nested(str):
+        pass

Lib/test/re_tests.py

@@ -531,7 +531,7 @@ xyzabc
     (r'a[ ]*?\ (\d+).*', 'a   10', SUCCEED, 'found', 'a   10'),
     (r'a[ ]*?\ (\d+).*', 'a    10', SUCCEED, 'found', 'a    10'),
     # bug 127259: \Z shouldn't depend on multiline mode
-    (r'(?ms).*?x\s*\Z(.*)','xx\nx\n', SUCCEED, 'g1', ''),
+    (r'(?ms).*?x\s*\z(.*)','xx\nx\n', SUCCEED, 'g1', ''),
     # bug 128899: uppercase literals under the ignorecase flag
     (r'(?i)M+', 'MMM', SUCCEED, 'found', 'MMM'),
     (r'(?i)m+', 'MMM', SUCCEED, 'found', 'MMM'),

Lib/test/seq_tests.py

@@ -261,23 +261,20 @@ class CommonTest(unittest.TestCase):
         self.assertEqual(min(u), 0)
         self.assertEqual(max(u), 2)
 
-    def test_addmul(self):
+    def test_add(self):
         u1 = self.type2test([0])
         u2 = self.type2test([0, 1])
         self.assertEqual(u1, u1 + self.type2test())
         self.assertEqual(u1, self.type2test() + u1)
         self.assertEqual(u1 + self.type2test([1]), u2)
         self.assertEqual(self.type2test([-1]) + u1, self.type2test([-1, 0]))
-        self.assertEqual(self.type2test(), u2*0)
+
-        self.assertEqual(self.type2test(), 0*u2)
+    def test_mul(self):
+        u2 = self.type2test([0, 1])
         self.assertEqual(self.type2test(), u2*0)
         self.assertEqual(self.type2test(), 0*u2)
         self.assertEqual(u2, u2*1)
         self.assertEqual(u2, 1*u2)
-        self.assertEqual(u2, u2*1)
-        self.assertEqual(u2, 1*u2)
-        self.assertEqual(u2+u2, u2*2)
-        self.assertEqual(u2+u2, 2*u2)
         self.assertEqual(u2+u2, u2*2)
         self.assertEqual(u2+u2, 2*u2)
         self.assertEqual(u2+u2+u2, u2*3)
@@ -286,8 +283,9 @@ class CommonTest(unittest.TestCase):
         class subclass(self.type2test):
             pass
         u3 = subclass([0, 1])
-        self.assertEqual(u3, u3*1)
+        r = u3*1
-        self.assertIsNot(u3, u3*1)
+        self.assertEqual(r, u3)
+        self.assertIsNot(r, u3)
 
     def test_iadd(self):
         u = self.type2test([0, 1])
@@ -348,6 +346,21 @@ class CommonTest(unittest.TestCase):
         self.assertRaises(ValueError, a.__getitem__, slice(0, 10, 0))
         self.assertRaises(TypeError, a.__getitem__, 'x')
 
+    def _assert_cmp(self, a, b, r):
+        self.assertIs(a == b, r == 0)
+        self.assertIs(a != b, r != 0)
+        self.assertIs(a > b, r > 0)
+        self.assertIs(a <= b, r <= 0)
+        self.assertIs(a < b, r < 0)
+        self.assertIs(a >= b, r >= 0)
+
+    def test_cmp(self):
+        a = self.type2test([0, 1])
+        self._assert_cmp(a, a, 0)
+        self._assert_cmp(a, self.type2test([0, 1]), 0)
+        self._assert_cmp(a, self.type2test([0]), 1)
+        self._assert_cmp(a, self.type2test([0, 2]), -1)
+
     def test_count(self):
         a = self.type2test([0, 1, 2])*3
         self.assertEqual(a.count(0), 3)
@@ -426,7 +439,7 @@ class CommonTest(unittest.TestCase):
             self.assertEqual(lst2, lst)
             self.assertNotEqual(id(lst2), id(lst))
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON
+    @unittest.skip("TODO: RUSTPYTHON; hangs")
     def test_free_after_iterating(self):
         support.check_free_after_iterating(self, iter, self.type2test)
         support.check_free_after_iterating(self, reversed, self.type2test)

Lib/test/string_tests.py

@@ -90,6 +90,55 @@ class BaseTest:
         args = self.fixtype(args)
         getattr(obj, methodname)(*args)
 
+    def _get_teststrings(self, charset, digits):
+        base = len(charset)
+        teststrings = set()
+        for i in range(base ** digits):
+            entry = []
+            for j in range(digits):
+                i, m = divmod(i, base)
+                entry.append(charset[m])
+            teststrings.add(''.join(entry))
+        teststrings = [self.fixtype(ts) for ts in teststrings]
+        return teststrings
+
+    def test_add(self):
+        s = self.fixtype('ab')
+        self.assertEqual(s + self.fixtype(''), s)
+        self.assertEqual(self.fixtype('') + s, s)
+        self.assertEqual(s + self.fixtype('cd'), self.fixtype('abcd'))
+
+    def test_mul(self):
+        s = self.fixtype('ab')
+        self.assertEqual(s*0, self.fixtype(''))
+        self.assertEqual(0*s, self.fixtype(''))
+        self.assertEqual(s*1, s)
+        self.assertEqual(1*s, s)
+        self.assertEqual(s*2, self.fixtype('abab'))
+        self.assertEqual(2*s, self.fixtype('abab'))
+
+        class subclass(self.type2test):
+            pass
+        s = subclass(self.fixtype('ab'))
+        r = s*1
+        self.assertEqual(r, s)
+        self.assertIsNot(r, s)
+
+    def _assert_cmp(self, a, b, r):
+        self.assertIs(a == b, r == 0)
+        self.assertIs(a != b, r != 0)
+        self.assertIs(a > b, r > 0)
+        self.assertIs(a <= b, r <= 0)
+        self.assertIs(a < b, r < 0)
+        self.assertIs(a >= b, r >= 0)
+
+    def test_cmp(self):
+        a = self.fixtype('ab')
+        self._assert_cmp(a, a, 0)
+        self._assert_cmp(a, self.fixtype('ab'), 0)
+        self._assert_cmp(a, self.fixtype('a'), 1)
+        self._assert_cmp(a, self.fixtype('ac'), -1)
+
     def test_count(self):
         self.checkequal(3, 'aaa', 'count', 'a')
         self.checkequal(0, 'aaa', 'count', 'b')
@@ -130,17 +179,7 @@ class BaseTest:
         # For a variety of combinations,
         #    verify that str.count() matches an equivalent function
         #    replacing all occurrences and then differencing the string lengths
-        charset = ['', 'a', 'b']
+        teststrings = self._get_teststrings(['', 'a', 'b'], 7)
-        digits = 7
-        base = len(charset)
-        teststrings = set()
-        for i in range(base ** digits):
-            entry = []
-            for j in range(digits):
-                i, m = divmod(i, base)
-                entry.append(charset[m])
-            teststrings.add(''.join(entry))
-        teststrings = [self.fixtype(ts) for ts in teststrings]
         for i in teststrings:
             n = len(i)
             for j in teststrings:
@@ -197,17 +236,7 @@ class BaseTest:
         # For a variety of combinations,
         #    verify that str.find() matches __contains__
         #    and that the found substring is really at that location
-        charset = ['', 'a', 'b', 'c']
+        teststrings = self._get_teststrings(['', 'a', 'b', 'c'], 5)
-        digits = 5
-        base = len(charset)
-        teststrings = set()
-        for i in range(base ** digits):
-            entry = []
-            for j in range(digits):
-                i, m = divmod(i, base)
-                entry.append(charset[m])
-            teststrings.add(''.join(entry))
-        teststrings = [self.fixtype(ts) for ts in teststrings]
         for i in teststrings:
             for j in teststrings:
                 loc = i.find(j)
@@ -244,17 +273,7 @@ class BaseTest:
         # For a variety of combinations,
         #    verify that str.rfind() matches __contains__
         #    and that the found substring is really at that location
-        charset = ['', 'a', 'b', 'c']
+        teststrings = self._get_teststrings(['', 'a', 'b', 'c'], 5)
-        digits = 5
-        base = len(charset)
-        teststrings = set()
-        for i in range(base ** digits):
-            entry = []
-            for j in range(digits):
-                i, m = divmod(i, base)
-                entry.append(charset[m])
-            teststrings.add(''.join(entry))
-        teststrings = [self.fixtype(ts) for ts in teststrings]
         for i in teststrings:
             for j in teststrings:
                 loc = i.rfind(j)
@@ -295,6 +314,19 @@ class BaseTest:
         else:
             self.checkraises(TypeError, 'hello', 'index', 42)
 
+        # For a variety of combinations,
+        #    verify that str.index() matches __contains__
+        #    and that the found substring is really at that location
+        teststrings = self._get_teststrings(['', 'a', 'b', 'c'], 5)
+        for i in teststrings:
+            for j in teststrings:
+                if j in i:
+                    loc = i.index(j)
+                    self.assertGreaterEqual(loc, 0)
+                    self.assertEqual(i[loc:loc+len(j)], j)
+                else:
+                    self.assertRaises(ValueError, i.index, j)
+
     def test_rindex(self):
         self.checkequal(12, 'abcdefghiabc', 'rindex', '')
         self.checkequal(3,  'abcdefghiabc', 'rindex', 'def')
@@ -321,6 +353,19 @@ class BaseTest:
         else:
             self.checkraises(TypeError, 'hello', 'rindex', 42)
 
+        # For a variety of combinations,
+        #    verify that str.rindex() matches __contains__
+        #    and that the found substring is really at that location
+        teststrings = self._get_teststrings(['', 'a', 'b', 'c'], 5)
+        for i in teststrings:
+            for j in teststrings:
+                if j in i:
+                    loc = i.rindex(j)
+                    self.assertGreaterEqual(loc, 0)
+                    self.assertEqual(i[loc:loc+len(j)], j)
+                else:
+                    self.assertRaises(ValueError, i.rindex, j)
+
     def test_find_periodic_pattern(self):
         """Cover the special path for periodic patterns."""
         def reference_find(p, s):
@@ -437,8 +482,10 @@ class BaseTest:
         self.checkequal('  a\n b', ' \ta\n\tb', 'expandtabs', 1)
 
         self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)
+        # TODO: RUSTPYTHON; expandtabs overflow checks
+        # if sys.maxsize < (1 << 32) and struct.calcsize('P') == 4:
+        #
         # This test is only valid when sizeof(int) == sizeof(void*) == 4.
-        # XXX RUSTPYTHON TODO: expandtabs overflow checks
         if sys.maxsize < (1 << 32) and struct.calcsize('P') == 4 and False:
             self.checkraises(OverflowError,
                              '\ta\n\tb', 'expandtabs', sys.maxsize)
@@ -768,6 +815,15 @@ class BaseTest:
         self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
         self.checkraises(TypeError, 'hello', 'replace', 'h', 42)
 
+    def test_replacement_on_buffer_boundary(self):
+        # gh-127971: Check we don't read past the end of the buffer when a
+        # potential match misses on the last character.
+        any_3_nonblank_codepoints = '!!!'
+        seven_codepoints = any_3_nonblank_codepoints + ' ' + any_3_nonblank_codepoints
+        a = (' ' * 243) + seven_codepoints + (' ' * 7)
+        b = ' ' * 6 + chr(256)
+        a.replace(seven_codepoints, b)
+
     def test_replace_uses_two_way_maxcount(self):
         # Test that maxcount works in _two_way_count in fastsearch.h
         A, B = "A"*1000, "B"*1000
@@ -780,7 +836,7 @@ class BaseTest:
         self.checkequal(AABAA + "ccc",
                         AABAA + ABBA, 'replace', ABBA, "ccc", 2)
 
-    @unittest.skip("TODO: RUSTPYTHON, may only apply to 32-bit platforms")
+    @unittest.skip("TODO: RUSTPYTHON; may only apply to 32-bit platforms")
     @unittest.skipIf(sys.maxsize > (1 << 32) or struct.calcsize('P') != 4,
                      'only applies to 32-bit platforms')
     def test_replace_overflow(self):
@@ -1134,8 +1190,8 @@ class StringLikeTest(BaseTest):
         self.checkequal('\u2160\u2171\u2172',
                         '\u2170\u2171\u2172', 'capitalize')
         # check with Ll chars with no upper - nothing changes here
-        self.checkequal('\u019b\u1d00\u1d86\u0221\u1fb7',
+        self.checkequal('\u1d00\u1d86\u0221\u1fb7',
-                        '\u019b\u1d00\u1d86\u0221\u1fb7', 'capitalize')
+                        '\u1d00\u1d86\u0221\u1fb7', 'capitalize')
 
     def test_startswith(self):
         self.checkequal(True, 'hello', 'startswith', 'he')
@@ -1248,9 +1304,7 @@ class StringLikeTest(BaseTest):
         self.checkequal(False, 'asd', '__contains__', 'asdf')
         self.checkequal(False, '', '__contains__', 'asdf')
 
-
+    @unittest.expectedFailure  # TODO: RUSTPYTHON
-    # TODO: RUSTPYTHON
-    @unittest.expectedFailure
     def test_subscript(self):
         self.checkequal('a', 'abc', '__getitem__', 0)
         self.checkequal('c', 'abc', '__getitem__', -1)
@@ -1292,6 +1346,7 @@ class StringLikeTest(BaseTest):
                                     slice(start, stop, step))
 
     def test_mul(self):
+        super().test_mul()
         self.checkequal('', 'abc', '__mul__', -1)
         self.checkequal('', 'abc', '__mul__', 0)
         self.checkequal('abc', 'abc', '__mul__', 1)
@@ -1504,8 +1559,7 @@ class StringLikeTest(BaseTest):
         self.checkequal(True, s, 'startswith', 'h', None, -2)
         self.checkequal(False, s, 'startswith', 'x', None, None)
 
-    # TODO: RUSTPYTHON
+    @unittest.expectedFailure  # TODO: RUSTPYTHON
-    @unittest.expectedFailure
     def test_find_etc_raise_correct_error_messages(self):
         # issue 11828
         s = 'hello'

Lib/test/support/__init__.py

@@ -548,7 +548,6 @@ def requires_lzma(reason='requires lzma'):
         import lzma
     except ImportError:
         lzma = None
-    lzma = None # XXX: RUSTPYTHON; xz is not supported yet
     return unittest.skipUnless(lzma, reason)
 
 def requires_zstd(reason='requires zstd'):
@@ -856,8 +855,6 @@ def gc_collect():
     longer than expected.  This function tries its best to force all garbage
     objects to disappear.
     """
-    return # TODO: RUSTPYTHON
-
     import gc
     gc.collect()
     gc.collect()
@@ -865,13 +862,6 @@ def gc_collect():
 
 @contextlib.contextmanager
 def disable_gc():
-    # TODO: RUSTPYTHON; GC is not supported yet
-    try:
-        yield
-    finally:
-        pass
-    return
-
     import gc
     have_gc = gc.isenabled()
     gc.disable()
@@ -2004,10 +1994,6 @@ def _check_tracemalloc():
 
 
 def check_free_after_iterating(test, iter, cls, args=()):
-    # TODO: RUSTPYTHON; GC is not supported yet
-    test.assertTrue(False)
-    return
-
     done = False
     def wrapper():
         class A(cls):
@@ -3048,6 +3034,10 @@ def get_signal_name(exitcode):
     except KeyError:
         pass
 
+    # Format Windows exit status as hexadecimal
+    if 0xC0000000 <= exitcode:
+        return f"0x{exitcode:X}"
+
     return None
 
 class BrokenIter:

Lib/test/support/_hypothesis_stubs/__init__.py

@@ -1,6 +1,6 @@
+from enum import Enum
 import functools
 import unittest
-from enum import Enum
 
 __all__ = [
     "given",