correctionlib 2.7.0__tar.gz → 2.8.0__tar.gz

correctionlib-2.8.0/.github/dependabot.yml

@@ -0,0 +1,9 @@
+version: 2
+updates:
+  # Maintain dependencies for GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+    commit-message:
+      prefix: "ci: "

correctionlib-2.8.0/.github/scripts/summarize_benchmark.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+"""Generate a markdown summary from pytest-benchmark JSON output."""
+
+import json
+import pathlib
+import sys
+
+
+def main():
+    benchmark_json = pathlib.Path(".benchmarks/cvmfs-benchmark.json")
+    output_md = pathlib.Path(".benchmarks/pr-comment.md")
+
+    if not benchmark_json.exists():
+        output_md.write_text(
+            "### CVMFS benchmarks\n\nNo benchmark JSON was produced in this run."
+        )
+        return 0
+
+    data = json.loads(benchmark_json.read_text())
+    rows = []
+    for bench in data.get("benchmarks", []):
+        stats = bench.get("stats", {})
+        rows.append(
+            (
+                bench.get("name", "unknown"),
+                stats.get("mean", 0.0) * 1000.0,
+                stats.get("stddev", 0.0) * 1000.0,
+                stats.get("rounds", 0),
+            )
+        )
+
+    rows.sort(key=lambda row: row[1], reverse=True)
+    rows = rows[:25]
+
+    lines = [
+        "### CVMFS benchmarks",
+        "",
+        "Top 25 slowest-loading corrections, sorted by mean time:",
+        "",
+        "| Benchmark | Mean (ms) | Stddev (ms) | Rounds |",
+        "|---|---:|---:|---:|",
+    ]
+
+    if rows:
+        for name, mean_ms, stddev_ms, rounds in rows:
+            lines.append(f"| `{name}` | {mean_ms:.3f} | {stddev_ms:.3f} | {rounds} |")
+    else:
+        lines.append("| _No benchmark rows found_ | - | - | - |")
+
+    output_md.write_text("\n".join(lines) + "\n")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

correctionlib-2.8.0/.github/workflows/ci.yml

@@ -0,0 +1,150 @@
+name: CI
+
+on:
+  workflow_dispatch:
+  pull_request:
+  merge_group:
+  push:
+    branches:
+      - master
+      - main
+      - develop
+
+jobs:
+  pre-commit:
+    name: Format
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-depth: 0
+          fetch-tags: true
+      - uses: actions/setup-python@v6
+        with:
+          python-version: 3.12
+      - uses: pre-commit/action@v3.0.0
+        with:
+          extra_args: --hook-stage manual --all-files
+
+  checks:
+    name: Check Python ${{ matrix.python-version }} on ${{ matrix.runs-on }}
+    runs-on: ${{ matrix.runs-on }}
+    needs: [pre-commit]
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.13", "3.14", "3.14t"]
+        runs-on: [ubuntu-latest, macos-latest, windows-latest, windows-11-arm]
+        exclude:
+          - python-version: "3.9"
+            runs-on: windows-11-arm
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-depth: 0
+          fetch-tags: true
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package
+        run: python -m pip install . --group test
+
+      - name: Test package
+        if: ${{ !endsWith(matrix.python-version , 't') }}
+        run: python -m pytest
+
+      - name: Test package (parallel)
+        if: endsWith(matrix.python-version , 't')
+        run: python -m pytest --parallel-threads=16 --iterations=10
+
+  checkroot:
+    name: Check ROOT bindings
+    needs: [pre-commit]
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Set up Conda
+        uses: conda-incubator/setup-miniconda@v3
+        with:
+          python-version: 3.12
+          miniforge-version: latest
+
+      - name: Install ROOT
+        shell: bash -l {0}
+        run: |
+          mamba install root
+
+      - name: Install package
+        shell: bash -l {0}
+        run: python -m pip install . --group test
+
+      - name: Test package
+        shell: bash -l {0}
+        run: pytest
+
+  test-cvmfs:
+    name: Test latest corrections on CVMFS
+    needs: [checks]
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-depth: 0
+          fetch-tags: true
+
+      - uses: cvmfs-contrib/github-action-cvmfs@v4
+        with:
+          cvmfs_repositories: "cms-griddata.cern.ch"
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.10"
+
+      - name: Install package
+        run: python -m pip install . --group test
+
+      - name: Test package
+        run: |
+          mkdir -p .benchmarks
+          python -m pytest -m cvmfs --benchmark-json=.benchmarks/cvmfs-benchmark.json --benchmark-max-time 0.1
+
+      - name: Upload benchmark artifact
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: cvmfs-benchmark-json
+          path: .benchmarks/cvmfs-benchmark.json
+          if-no-files-found: ignore
+
+      - name: Build benchmark PR summary
+        if: always() && github.event_name == 'pull_request'
+        run: python .github/scripts/summarize_benchmark.py
+
+      - name: Comment benchmark summary on PR
+        if: always() && github.event_name == 'pull_request'
+        uses: marocchino/sticky-pull-request-comment@v2
+        with:
+          header: cvmfs-benchmark
+          path: .benchmarks/pr-comment.md
+
+  pass:
+    name: All tests passed
+    needs: [checks, checkroot, test-cvmfs]
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "All jobs passed"

correctionlib-2.8.0/.github/workflows/docs.yml

@@ -0,0 +1,40 @@
+name: Docs
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - master
+      - main
+
+jobs:
+  docs:
+    name: Build and deploy docs
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: 3.12
+
+      - name: Install pandoc
+        uses: r-lib/actions/setup-pandoc@v2
+
+      - name: Install package
+        run: python -m pip install . --group docs
+
+      - name: Build documentation
+        run: |
+          cd docs
+          make
+          touch build/html/.nojekyll
+
+      - name: Deploy documentation
+        uses: peaceiris/actions-gh-pages@v4.0.0
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./docs/build/html

correctionlib-2.8.0/.github/workflows/wheels.yml

@@ -0,0 +1,84 @@
+name: wheels
+
+on:
+  workflow_dispatch:
+  release:
+    types:
+      - published
+  pull_request:
+    paths:
+      - ".github/workflows/wheels.yml"
+      - "pyproject.toml"
+
+jobs:
+  make_sdist:
+    name: Make SDist
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-tags: true
+          fetch-depth: 0
+
+      - name: Build SDist
+        run: pipx run build --sdist
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: artifact-sdist
+          path: dist/*.tar.gz
+
+  build_wheels:
+    name: Wheel on ${{ matrix.os }} (${{ matrix.arch }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os:
+          [
+            ubuntu-latest,
+            ubuntu-24.04-arm,
+            windows-latest,
+            macos-latest,
+            windows-11-arm,
+          ]
+        arch: [auto64]
+        include:
+          - os: macos-latest
+            arch: universal2
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-tags: true
+          fetch-depth: 0
+
+      - uses: pypa/cibuildwheel@v3.3
+        env:
+          CIBW_ARCHS: ${{ matrix.arch }}
+          MACOSX_DEPLOYMENT_TARGET: 11.0
+
+      - name: Upload wheels
+        uses: actions/upload-artifact@v7
+        with:
+          name: artifact-wheel-${{ matrix.os }}-${{ matrix.arch }}
+          path: wheelhouse/*.whl
+
+  pypi-publish:
+    needs: [build_wheels, make_sdist]
+    name: Upload release to PyPI
+    runs-on: ubuntu-latest
+    if: github.event_name == 'release' && github.event.action == 'published'
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v8
+        with:
+          path: dist
+          pattern: artifact-*
+          merge-multiple: true
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

correctionlib-2.8.0/.gitignore

@@ -0,0 +1,149 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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/
+docs/_generated/
+
+# 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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+# setuptools_scm
+src/*/version.py
+
+_skbuild
+src/correctionlib/cmake
+src/correctionlib/include
+include/correctionlib_version.h
+
+.vscode

correctionlib-2.8.0/.gitmodules

@@ -0,0 +1,15 @@
+[submodule "pybind11"]
+	path = pybind11
+	url = https://github.com/pybind/pybind11.git
+[submodule "rapidjson"]
+	path = rapidjson
+	url = https://github.com/Tencent/rapidjson.git
+[submodule "cpp-peglib"]
+	path = cpp-peglib
+	url = https://github.com/yhirose/cpp-peglib.git
+[submodule "pcg-cpp"]
+	path = pcg-cpp
+	url = https://github.com/Total-Random/pcg-cpp.git
+[submodule "xxhash"]
+	path = xxhash
+	url = https://github.com/Cyan4973/xxHash.git

correctionlib-2.8.0/.pre-commit-config.yaml

@@ -0,0 +1,78 @@
+ci:
+  autofix_commit_msg: |
+    [pre-commit.ci] auto fixes from pre-commit.com hooks
+    for more information, see https://pre-commit.ci
+  autofix_prs: true
+  autoupdate_branch: ""
+  autoupdate_commit_msg: "chore: pre-commit autoupdate"
+  autoupdate_schedule: monthly
+  skip: []
+  submodules: false
+
+repos:
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: "1.20.0"
+    hooks:
+      - id: blacken-docs
+        additional_dependencies: [black==25.*]
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: "v6.0.0"
+    hooks:
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: check-yaml
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: name-tests-test
+        args: ["--pytest-test-first"]
+      - id: trailing-whitespace
+
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: "v3.8.1"
+    hooks:
+      - id: prettier
+        types_or: [yaml, markdown, html, css, scss, javascript, json]
+        args: [--prose-wrap=always]
+        exclude: binder/mycorrections.json
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.14.13"
+    hooks:
+      - id: ruff
+        args: ["--fix", "--show-fixes"]
+      - id: ruff-format
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: "v2.4.1"
+    hooks:
+      - id: codespell
+
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: "v0.24.1"
+    hooks:
+      - id: validate-pyproject
+        additional_dependencies: ["validate-pyproject-schema-store[all]"]
+
+  - repo: https://github.com/python-jsonschema/check-jsonschema
+    rev: "0.36.0"
+    hooks:
+      - id: check-dependabot
+      - id: check-github-workflows
+      - id: check-readthedocs
+
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.21.2
+    hooks:
+      - id: pyupgrade
+        args: ["--py39-plus"]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.19.1
+    hooks:
+      - id: mypy
+        pass_filenames: false # to allow mypy to respect pyproject.toml config
+        additional_dependencies: [uhi, pydantic, numpy]

correctionlib-2.8.0/ARCHITECTURE.md

@@ -0,0 +1,73 @@
+# Correctionlib architecture
+
+This document briefly describes the architecture of correctionlib. It is meant
+to provide a good starting point for new contributors to find their way around
+the codebase. It assumes some familiarity with correctionlib as a user.
+
+## Python modules
+
+- `schemav2` module: Pydantic models for correctionlib's data structures
+  - `CorrectionSet` is a list of `Correction`s
+  - `Correction` represents a single correction. Its `data` attribute is of
+    `Content` type and represents the root node of the computation graph for
+    this correction. Corrections also have a list of inputs as well as one
+    output of type `Variable` (basically a pair of a name and a type,
+    int/float/string) and
+  - `Content` is the type of a node in the computation graph of a `Correction`.
+    It's a `Union` of the various types of corrections available: `Binning`,
+    `MultiBinning`, `Category`, `Formula`, `FormulaRef`, `Transform`,
+    `HashPRNG`, float
+- `highlevel` module: user-facing types (`correctionlib.Correction` resolves to
+  `correctionlib.highlevel.Correction`, etc.)
+  - `CorrectionSet` is a list of `Correction`s (same as in `schemav2` but focus
+    is on user API rather than defining the schema/structure of the corrections)
+  - `Correction` and `CompoundCorrection` wrap the corresponding C++ evaluator
+    and expose the `evaluate` method
+- `_core` module: a small module that contains the Python facades for the
+  corresponding C++ types, in `__init__.pyi`.
+  - types are `CorrectionSet`, `Correction`, `CompoundCorrection` and `Variable`
+  - the bindings are declared in `src/python.cc`
+
+## C++ sources
+
+`include/correction.h` and `src/correction.cc` contain the the C++ types that
+perform the actual computations:
+
+- a `Variable` type with a name and a type (string, integer, real)
+- a `CorrectionSet` builds a list of `Corrections`
+- the `Correction` type, which builds a compute graph of correction nodes
+- types for the different types of nodes in a correction's compute graph, e.g.
+  `Binning`, `Formula`, each with its `evaluate` method. They are constructed by
+  deserializing a JSON object. `Formula::Formula`, for example, parses a
+  `TFormula` expression in the JSON and builds the corresponding `FormulaAST`
+
+## Typical call sequence to evaluate a correction
+
+![Diagram describing the call sequence that starts with `Correction.evaluate`](./docs/evaluate_call_sequence.png).
+
+## Building a Correction object
+
+In short, the C++ correction objects that perform the actual correction
+evaluations are constructed from the JSON representations of the Pydantic types
+defined in `schemav2`.
+
+Let's say the user calls `schemav2.Correction.to_evaluator`. This:
+
+- constructs a `schemav2.CorrectionSet` (the pydantic model)
+- constructs a `highlevel.CorrectionSet` from it and immediately extracts the
+  right `highlevel.Correction` from it, returning it
+
+The actual construction of the internal C++ correction evaluators happens in the
+construction of the `highlevel.CorrectionSet`, which converts the Pydantic
+`CorrectionSet` to JSON and uses it to construct a `_core.CorrectionSet` (using
+`CorrectionSet.from_string`)
+
+- `_core.CorrectionSet.from_string` constructs a rapidjson JSONObject and calls
+  `CorrectionSet(const JSONObject &)`
+- then for each object in JSONObject it constructs a Correction
+  (`Correction(const JSONObject&)`), and puts it in
+  `CorrectionSet::corrections_`
+- `Correction::Correction(const JSONObject&)` sets `data_` to the output of
+  `resolve_content`, passing the json
+- `resolve_content` (defined in correction.cc) constructs the appropriate type
+  depending on the JSON input (if/else-ing over the known correction types)