Benjamin Mako Hill
b073b038af
wikiq had no way to report which version produced a dataset, which matters when output columns change between runs that end up in the same analysis. Add a --version flag, and print the version to stderr on every run so it lands in job logs alongside the output. 0.3.0 is the first release published anywhere. The earlier 0.1.1 and 0.2.0 tags were internal markers that were never released, so the version numbering starts being meaningful to users here. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
97 lines
3.0 KiB
TOML
97 lines
3.0 KiB
TOML
[project]
|
|
name = "mediawiki-dump-tools"
|
|
version = "0.3.0"
|
|
description = "Convert MediaWiki XML database dumps into tabular datasets for research"
|
|
readme = "README.md"
|
|
license = "GPL-3.0-or-later"
|
|
license-files = ["COPYING"]
|
|
requires-python = ">=3.11"
|
|
authors = [
|
|
{ name = "Benjamin Mako Hill" },
|
|
{ name = "Nathan TeBlunthuis" },
|
|
{ name = "Will Beason" },
|
|
{ name = "Sohyeon Hwang" },
|
|
{ name = "Kaylea Champion" },
|
|
]
|
|
keywords = ["mediawiki", "wikipedia", "wiki", "dump", "xml", "revision", "research"]
|
|
classifiers = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Environment :: Console",
|
|
"Intended Audience :: Science/Research",
|
|
"License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
|
|
"Operating System :: POSIX",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Topic :: Scientific/Engineering :: Information Analysis",
|
|
"Topic :: Text Processing :: Markup",
|
|
]
|
|
dependencies = [
|
|
"deltas>=0.7.0",
|
|
"more-itertools>=10.7.0",
|
|
"mwparserfromhell>=0.6.0",
|
|
"mwpersistence>=0.2.4",
|
|
"mwreverts>=0.1.5",
|
|
"mwtypes>=0.4.0",
|
|
"mwxml>=0.3.8",
|
|
"pyarrow>=20.0.0",
|
|
"sortedcontainers>=2.4.0",
|
|
]
|
|
|
|
# Two features carry dependencies that are awkward enough to install that they
|
|
# are kept out of the base install: -p legacy needs mediawiki-utilities, a 2015
|
|
# package that also pulls in a MySQL client, and --diff and -p wikidiff2 need
|
|
# pywikidiff2, which compiles a C++ extension. Everything else, including the
|
|
# default -p sequence, works with neither.
|
|
[project.optional-dependencies]
|
|
legacy = ["mediawiki-utilities>=0.4.18"]
|
|
# A wikidiff2 extra belongs here too, but pywikidiff2 is not yet published to
|
|
# PyPI, so an extra naming it could not resolve. Until it is, wikiq reports the
|
|
# git install command when --diff or -p wikidiff2 is used without it.
|
|
|
|
# Duplicated from [dependency-groups] below, which is PEP 735 and so is visible
|
|
# only to uv. This is what makes `pip install -e '.[dev]'` work.
|
|
dev = [
|
|
"pandas>=2.1.0",
|
|
"pytest>=8.4.1",
|
|
"pytest-asyncio>=1.0.0",
|
|
"pytest-benchmark>=5.1.0",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://wiki.communitydata.science/"
|
|
Repository = "https://gitea.communitydata.science/collective/mediawiki_dump_tools"
|
|
|
|
[project.scripts]
|
|
wikiq = "wikiq:main"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/wikiq"]
|
|
|
|
# Without an explicit list hatchling walks the whole working tree, which sweeps
|
|
# in any local virtualenv and editor state while still omitting the test dumps,
|
|
# since those are gitignored. Tests run from a clone of the repository rather
|
|
# than from the sdist.
|
|
[tool.hatch.build.targets.sdist]
|
|
include = [
|
|
"src/wikiq",
|
|
"README.md",
|
|
"COPYING",
|
|
"pyproject.toml",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"ipython>=8.18.1",
|
|
"memray>=1.17.2",
|
|
"pandas>=2.1.0",
|
|
"pytest>=8.4.1",
|
|
"pytest-asyncio>=1.0.0",
|
|
"pytest-benchmark>=5.1.0",
|
|
]
|