mirror of
https://github.com/domainaware/parsedmarc.git
synced 2026-05-25 21:35:22 +00:00
Fabio Scaccabarozzi
327fcff2b9
Adds a PostgreSQL output backend as a lighter-weight alternative to Elasticsearch/OpenSearch, configured via a [postgresql] section (host/port/user/password/database or a libpq connection_string). Tables are created automatically on first run; a Grafana dashboard is included. - psycopg is an optional extra (pip install parsedmarc[postgresql]); the import is guarded so `import parsedmarc` works without it, and PostgreSQLClient raises a clear install hint when constructed without the driver. Binary wheels aren't available for every platform. - Schema captures the RFC 9990 / DMARCbis aggregate fields: np, testing, discovery_method, generator, xml_namespace, and per-result human_result on the DKIM/SPF auth-result tables. - forensic -> failure naming throughout (table dmarc_failure_report, save_failure_report_to_postgresql, dashboard, docs) to match #659. - Failure-report de-duplication mirrors the Elasticsearch backend exactly: arrival date + From + To + Subject (NULL-safe via IS NOT DISTINCT FROM; semantic JSONB equality). Aggregate and SMTP-TLS use ON CONFLICT. - PostgreSQLClient.close() for clean CLI shutdown; comment documents why the two timestamp helpers must stay distinct (report dates are local, record/SMTP-TLS dates are UTC). - CLI: config parse raises ConfigurationError on missing host/connection_string; wired into _init_output_clients + save loops. - Tests in tests/test_postgres.py (helpers, mocked-DB save assertions, create_tables, connect/error wrapping, dedup, real-sample round trip) and tests/test_cli.py (config parse + end-to-end save wiring incl. AlreadySaved/PostgreSQLError handling). postgres.py at 99% line coverage; only _main's output-client-init retry path is left. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
128 lines
3.8 KiB
TOML
128 lines
3.8 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 and forensic 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-ng>=2.2.2",
|
|
"lxml>=4.4.0",
|
|
"mailsuite[gmail,msgraph]>=2.0.2",
|
|
"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",
|
|
"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.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",
|
|
]
|