mirror of
https://github.com/domainaware/parsedmarc.git
synced 2026-06-18 00:04:18 +00:00
Sean Whalen
eaeea4f53d
* Make the whole codebase pass pyright cleanly and enforce it in CI Fix all 102 pyright (1.1.410, standard mode) errors across the library, tests, and maps scripts, then pin and enforce the zero-errors bar: - postgres.py: make the optional psycopg import TYPE_CHECKING-aware so the module is properly typed while keeping the runtime install-hint fallback; import psycopg.types.json explicitly as psycopg_json (the old psycopg_types.json attribute access only worked because psycopg imports the submodule eagerly); have _connect()/_ensure_connected() return the live connection so save methods use a non-Optional local; type the DDL list as list[LiteralString] to match psycopg's execute() overloads. - kafkaclient.py: resolve the kafka-python 2.x/3.x bootstrap-error fallback statically via TYPE_CHECKING (kafka-python 3.0 removed NoBrokersAvailable), which also fixes _BootstrapError's import resolution in tests. - syslog.py: go through getattr/setattr for SysLogHandler.socket (absent from typeshed); type the save_* methods with the report TypedDicts (single or list, matching cli.py call sites — gelf.py gets the same signatures); raise ValueError when retry_attempts < 1 instead of falling through and registering a None handler (bug fix, with a regression test and a CHANGELOG entry). - elastic.py / opensearch.py: human_result params are Optional[str]. - maps scripts: sort_csv declared a return type but never returned (now -> None); seen_sort_field_values was possibly unbound; convert_to_utf8's src_encoding is Optional[str]. - tests: cast sample-report dict helpers to their TypedDicts; mark deliberate wrong-type calls with targeted pyright ignores; add narrowing asserts for Optional results; access the mocked KafkaProducer through a cast helper; match the mailsuite fetch_message base signature (**kwargs); patch the renamed parsedmarc.postgres.psycopg_json in test_postgres's setUpModule. Enforcement: [tool.pyright] in pyproject.toml (include parsedmarc, tests, docs; standard mode), pyright==1.1.410 pinned in the [build] extra (pinned exactly so a new pyright release can't break CI without a code change), and a "Check types" step in the lint CI job — which now also runs ruff format --check and installs the [postgresql] extra so the optional psycopg import resolves. Documented in AGENTS.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Set session headers via update() instead of replacing the dict requests 2.34 ships inline type annotations, and Session.headers is a CaseInsensitiveDict[str] — assigning a plain dict fails pyright there (the CI runner resolved 2.34.2; the local venv's untyped 2.32.4 hid it). headers.update() is correctly typed against both versions, and is the documented requests idiom: it overrides User-Agent and the client-specific headers while keeping the session's defaults (Accept-Encoding, Connection) instead of wiping them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
141 lines
4.4 KiB
TOML
141 lines
4.4 KiB
TOML
[build-system]
|
|
requires = [
|
|
"hatchling>=1.27.0",
|
|
]
|
|
requires_python = ">=3.10,<3.15"
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "parsedmarc"
|
|
dynamic = [
|
|
"version",
|
|
]
|
|
description = "A Python package and CLI for parsing aggregate, failure, and SMTP TLS DMARC reports"
|
|
readme = "README.md"
|
|
license = "Apache-2.0"
|
|
authors = [
|
|
{ name = "Sean Whalen", email = "whalenster@gmail.com" },
|
|
]
|
|
keywords = [
|
|
"DMARC",
|
|
"parser",
|
|
"reporting",
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Information Technology",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python :: 3"
|
|
]
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
"azure-identity>=1.8.0",
|
|
"azure-monitor-ingestion>=1.0.0",
|
|
"boto3>=1.16.63",
|
|
"dateparser>=1.1.1",
|
|
"dnspython>=2.0.0",
|
|
"elasticsearch-dsl==7.4.0",
|
|
"elasticsearch<7.14.0",
|
|
"expiringdict>=1.1.4",
|
|
"kafka-python>=2.3.2",
|
|
"lxml>=4.4.0",
|
|
"mailsuite[gmail,msgraph]>=2.2.1",
|
|
"maxminddb>=2.0.0",
|
|
"opensearch-py>=2.4.2,<=4.0.0",
|
|
"publicsuffixlist>=0.10.0",
|
|
"pygelf>=0.4.2",
|
|
"requests>=2.22.0",
|
|
"tqdm>=4.31.1",
|
|
"urllib3>=1.25.7",
|
|
"xmltodict>=0.12.0",
|
|
"PyYAML>=6.0.3"
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
postgresql = [
|
|
# Optional output backend. psycopg ships prebuilt binary wheels via the
|
|
# [binary] extra, but those wheels don't exist for every platform/arch,
|
|
# so PostgreSQL support is opt-in rather than a mandatory dependency.
|
|
"psycopg[binary]>=3.1.0",
|
|
]
|
|
build = [
|
|
# Used only by maintainer tooling under parsedmarc/resources/maps/ —
|
|
# `collect_domain_info.py --use-search-fallback` falls back to a
|
|
# DuckDuckGo search when the homepage fetch returns a bot-block / parked
|
|
# / empty page. Optional import; the script runs without it as long as
|
|
# the fallback flag isn't passed.
|
|
"ddgs>=9.0.0",
|
|
"hatch>=1.14.0",
|
|
"myst-parser[linkify]",
|
|
"nose",
|
|
# Pinned exactly: pyright's checks evolve between releases, so an
|
|
# unpinned version could break CI without any code change. Bump
|
|
# deliberately (and fix any new findings) rather than implicitly.
|
|
"pyright==1.1.410",
|
|
"pytest",
|
|
"pytest-cov",
|
|
"ruff",
|
|
"sphinx",
|
|
"sphinx_rtd_theme",
|
|
]
|
|
|
|
[project.scripts]
|
|
parsedmarc = "parsedmarc.cli:_main"
|
|
|
|
[project.urls]
|
|
Homepage = "https://domainaware.github.io/parsedmarc"
|
|
|
|
[tool.hatch.version]
|
|
path = "parsedmarc/constants.py"
|
|
|
|
[tool.hatch.build.targets.sdist]
|
|
include = [
|
|
"/parsedmarc",
|
|
]
|
|
|
|
[tool.hatch.build]
|
|
exclude = [
|
|
"base_reverse_dns.csv",
|
|
"unknown_base_reverse_dns.csv",
|
|
"README.md",
|
|
"*.bak",
|
|
# Maintenance tooling: any Python file under parsedmarc/resources/maps/
|
|
# whose name doesn't start with `_` (i.e. everything except __init__.py,
|
|
# which must keep shipping for `importlib.resources.files()` lookups).
|
|
"parsedmarc/resources/maps/[!_]*.py",
|
|
]
|
|
|
|
[tool.pyright]
|
|
# The whole codebase passes pyright with zero errors and warnings; CI
|
|
# enforces this (see .github/workflows/python-tests.yml). Run locally with
|
|
# `pyright` from the repo root. Requires the [postgresql] extra to be
|
|
# installed so the optional psycopg import in parsedmarc/postgres.py
|
|
# resolves.
|
|
include = ["parsedmarc", "tests", "docs"]
|
|
typeCheckingMode = "standard"
|
|
|
|
[tool.pytest.ini_options]
|
|
# Default to the per-module test layout under tests/. New tests should go
|
|
# into tests/test_<module>.py to match the file they exercise; do not
|
|
# reintroduce a monolithic tests.py.
|
|
testpaths = ["tests"]
|
|
|
|
[tool.coverage.run]
|
|
# Coverage measures shipped code only. Master's reported ≈66.9% on
|
|
# Codecov was an artefact of the old monolithic tests.py having no
|
|
# [tool.coverage.run] block, which let coverage's default behaviour
|
|
# measure every file imported during the run — including the test file
|
|
# itself at ~99% "covered". That inflated the headline by ~8 percentage
|
|
# points without any actual testing signal. Restricting to the parsedmarc
|
|
# package gives a meaningful number that tracks how much of the shipped
|
|
# library the test suite actually exercises.
|
|
source = ["parsedmarc"]
|
|
# Maintainer-only batch scripts under parsedmarc/resources/maps/ ship
|
|
# out of the wheel (see the [tool.hatch.build] exclude block above) —
|
|
# omit them so the headline number reflects only installed library code.
|
|
omit = [
|
|
"*/parsedmarc/resources/maps/*.py",
|
|
]
|