gigatoken 0.3.0__tar.gz

gigatoken-0.3.0/.cargo/config.toml

@@ -0,0 +1,5 @@
+# Allow per-profile `rustflags` (nightly-only). This lets the `profiling`
+# profile in Cargo.toml set `force-frame-pointers` without affecting normal
+# release/dev builds.
+[unstable]
+profile-rustflags = true

gigatoken-0.3.0/.github/workflows/CI.yml

@@ -0,0 +1,181 @@
+# This file is autogenerated by maturin v1.9.5
+# To update, run
+#
+#    maturin generate-ci github
+#
+name: CI
+
+on:
+  push:
+    branches:
+      - main
+      - master
+    tags:
+      - '*'
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  linux:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - runner: ubuntu-22.04
+            target: x86_64
+          - runner: ubuntu-22.04
+            target: x86
+          - runner: ubuntu-22.04
+            target: aarch64
+          - runner: ubuntu-22.04
+            target: armv7
+          - runner: ubuntu-22.04
+            target: s390x
+          - runner: ubuntu-22.04
+            target: ppc64le
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: ${{ !startsWith(github.ref, 'refs/tags/') }}
+          manylinux: auto
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-linux-${{ matrix.platform.target }}
+          path: dist
+
+  musllinux:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - runner: ubuntu-22.04
+            target: x86_64
+          - runner: ubuntu-22.04
+            target: x86
+          - runner: ubuntu-22.04
+            target: aarch64
+          - runner: ubuntu-22.04
+            target: armv7
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: ${{ !startsWith(github.ref, 'refs/tags/') }}
+          manylinux: musllinux_1_2
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-musllinux-${{ matrix.platform.target }}
+          path: dist
+
+  windows:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - runner: windows-latest
+            target: x64
+          - runner: windows-latest
+            target: x86
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+          architecture: ${{ matrix.platform.target }}
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: ${{ !startsWith(github.ref, 'refs/tags/') }}
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-windows-${{ matrix.platform.target }}
+          path: dist
+
+  macos:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - runner: macos-13
+            target: x86_64
+          - runner: macos-14
+            target: aarch64
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: ${{ !startsWith(github.ref, 'refs/tags/') }}
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-macos-${{ matrix.platform.target }}
+          path: dist
+
+  sdist:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Build sdist
+        uses: PyO3/maturin-action@v1
+        with:
+          command: sdist
+          args: --out dist
+      - name: Upload sdist
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-sdist
+          path: dist
+
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    if: ${{ startsWith(github.ref, 'refs/tags/') || github.event_name == 'workflow_dispatch' }}
+    needs: [linux, musllinux, windows, macos, sdist]
+    permissions:
+      # Use to sign the release artifacts
+      id-token: write
+      # Used to upload release artifacts
+      contents: write
+      # Used to generate artifact attestation
+      attestations: write
+    steps:
+      - uses: actions/download-artifact@v4
+      - name: Generate artifact attestation
+        uses: actions/attest-build-provenance@v2
+        with:
+          subject-path: 'wheels-*/*'
+      - name: Publish to PyPI
+        if: ${{ startsWith(github.ref, 'refs/tags/') }}
+        uses: PyO3/maturin-action@v1
+        env:
+          MATURIN_PYPI_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
+        with:
+          command: upload
+          args: --non-interactive --skip-existing wheels-*/*

gigatoken-0.3.0/.github/workflows/wheels.yml

@@ -0,0 +1,156 @@
+name: Manual release build
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  build-wheels:
+    name: Build ${{ matrix.target }}
+    runs-on: ${{ matrix.runner }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: ubuntu-24.04
+            target: x86_64-unknown-linux-gnu
+            manylinux: "2014"
+            artifact: wheels-linux-x86_64
+          - runner: ubuntu-24.04
+            target: aarch64-unknown-linux-gnu
+            manylinux: "2014"
+            artifact: wheels-linux-aarch64
+          - runner: windows-2022
+            target: x86_64-pc-windows-msvc
+            manylinux: "off"
+            artifact: wheels-windows-x86_64
+          - runner: windows-2022
+            target: aarch64-pc-windows-msvc
+            manylinux: "off"
+            artifact: wheels-windows-aarch64
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Build abi3 wheel
+        uses: PyO3/maturin-action@3e2bdf6ba6453a61e649744019b8a2d906c7eb38 # v1.51.0
+        with:
+          maturin-version: v1.14.1
+          rust-toolchain: nightly
+          target: ${{ matrix.target }}
+          manylinux: ${{ matrix.manylinux }}
+          args: --release --locked --out dist --compatibility pypi
+
+      - name: Upload wheel
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.artifact }}
+          path: dist/*.whl
+          if-no-files-found: error
+
+  build-sdist:
+    name: Build source distribution
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Build sdist
+        uses: PyO3/maturin-action@3e2bdf6ba6453a61e649744019b8a2d906c7eb38 # v1.51.0
+        with:
+          command: sdist
+          maturin-version: v1.14.1
+          rust-toolchain: nightly
+          args: --out dist
+
+      - name: Upload sdist
+        uses: actions/upload-artifact@v4
+        with:
+          name: sdist
+          path: dist/*.tar.gz
+          if-no-files-found: error
+
+  bundle-release:
+    name: Bundle release artifacts
+    needs:
+      - build-wheels
+      - build-sdist
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v5
+        with:
+          pattern: wheels-*
+          path: dist
+          merge-multiple: true
+
+      - name: Download sdist
+        uses: actions/download-artifact@v5
+        with:
+          name: sdist
+          path: dist
+
+      - name: Upload release bundle
+        uses: actions/upload-artifact@v4
+        with:
+          name: gigatoken-release
+          path: |
+            dist/*.whl
+            dist/*.tar.gz
+          if-no-files-found: error
+
+  test-wheels:
+    name: Test ${{ matrix.platform }} / Python ${{ matrix.python-version }}
+    needs: build-wheels
+    runs-on: ${{ matrix.runner }}
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux-x86_64
+          - linux-aarch64
+          - windows-x86_64
+          - windows-aarch64
+        python-version:
+          - "3.10"
+          - "3.11"
+          - "3.12"
+          - "3.13"
+          - "3.14"
+        # actions/setup-python has no CPython 3.10 Windows ARM64 runtime.
+        exclude:
+          - platform: windows-aarch64
+            python-version: "3.10"
+        include:
+          - platform: linux-x86_64
+            runner: ubuntu-24.04
+            artifact: wheels-linux-x86_64
+          - platform: linux-aarch64
+            runner: ubuntu-24.04-arm
+            artifact: wheels-linux-aarch64
+          - platform: windows-x86_64
+            runner: windows-2022
+            artifact: wheels-windows-x86_64
+          - platform: windows-aarch64
+            runner: windows-11-arm
+            artifact: wheels-windows-aarch64
+
+    steps:
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Download wheel
+        uses: actions/download-artifact@v5
+        with:
+          name: ${{ matrix.artifact }}
+          path: ${{ runner.temp }}/dist
+
+      - name: Install and smoke-test wheel
+        working-directory: ${{ runner.temp }}
+        run: |
+          python -m pip install --only-binary=:all: numpy awkward
+          python -m pip install --no-index --find-links dist gigatoken
+          python -c 'import gigatoken; tokens = list(gigatoken.pretokenizer(b"Hello, world!")); assert b"".join(tokens) == b"Hello, world!", tokens'

gigatoken-0.3.0/.gitignore

@@ -0,0 +1,252 @@
+# Generated by Cargo
+# will have compiled files and executables
+debug
+target
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb
+
+# Generated by cargo mutants
+# Contains mutation testing data
+**/mutants.out*/
+
+# RustRover
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+# Added by cargo
+
+/target
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+.idea/
+
+# Downloaded test data
+/data/
+
+.DS_Store
+
+*.trace/

gigatoken-0.3.0/.python-version

@@ -0,0 +1 @@
+3.13

gigatoken-0.3.0/.vscode/settings.json

@@ -0,0 +1,7 @@
+{
+    "python.testing.pytestArgs": [
+        "tests"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true
+}