Benjamin Mako Hill
392211af17
The spark indexing pass is moving out of this repository, and src/wikiq_spark was never committed here: pyproject.toml declared a wikiq-spark console script and wheel package that do not exist in the tree, and pulled in pyspark for every install of a tool that never imports it. The --print-schema flag and its Spark-format schema converters remain, since they are pure Python and produce the schema the external indexing pass consumes. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
48 lines
1.1 KiB
TOML
48 lines
1.1 KiB
TOML
[project]
|
|
name = "mediawiki-dump-tools"
|
|
version = "0.1.1"
|
|
description = "Add your description here"
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
dependencies = [
|
|
"deltas>=0.7.0",
|
|
"mediawiki-utilities>=0.4.18",
|
|
"more-itertools>=10.7.0",
|
|
"mwparserfromhell>=0.6.0",
|
|
"mwpersistence>=0.2.4",
|
|
"mwreverts>=0.1.5",
|
|
"mwtypes>=0.4.0",
|
|
"mwxml>=0.3.6",
|
|
"pyarrow>=20.0.0",
|
|
"pywikidiff2",
|
|
"sortedcontainers>=2.4.0",
|
|
"yamlconf>=0.2.6",
|
|
]
|
|
|
|
[project.scripts]
|
|
wikiq = "wikiq:main"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/wikiq"]
|
|
|
|
[tool.uv.sources]
|
|
|
|
yamlconf = { git = "https://github.com/groceryheist/yamlconf" }
|
|
mwxml = { git = "https://github.com/groceryheist/python-mwxml" }
|
|
deltas = { git = "https://github.com/groceryheist/deltas" }
|
|
pywikidiff2 = { git = "ssh://gitea@gitea.communitydata.science:2200/groceryheist/pywikidiff2.git"}
|
|
|
|
[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",
|
|
]
|