Merge remote-tracking branch 'origin/main' into python3.11-upperlimit

.github/workflows/test.yml

@@ -6,6 +6,9 @@ on:
     branches: [main]
   pull_request:
     branches: [main]
+  schedule:
+    # runs every Wednesday at 7 AM UTC
+    - cron: "0 7 * * 3"
 
 jobs:
   run_tests:
@@ -30,7 +33,5 @@ jobs:
         run: poetry install --no-interaction --no-ansi
       - name: Run sphinx-docs build test
         run: poetry run sphinx-build docs/source doctest -W
-      - name: Run citation file test
-        run: poetry run cffconvert --validate
       - name: Run pytest
         run: poetry run pytest

.pre-commit-config.yaml

@@ -11,6 +11,10 @@ repos:
       - id: check-yaml
       - id: check-added-large-files
       - id: check-toml
+  - repo: https://github.com/python-poetry/poetry
+    rev: 1.8.0
+    hooks:
+      - id: poetry-check
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.6
     hooks:
@@ -58,6 +62,10 @@ repos:
     rev: v1.8.0
     hooks:
       - id: mypy
+  - repo: https://github.com/citation-file-format/cffconvert
+    rev: 5295f87c0e261da61a7b919fc754e3a77edd98a7
+    hooks:
+      - id: validate-cff
   - repo: https://github.com/PyCQA/pylint
     rev: v3.0.3
     hooks:

cytotable/convert.py

@@ -2,7 +2,6 @@
 CytoTable: convert - transforming data for use with pyctyominer.
 """
 
-
 import itertools
 import logging
 import uuid
@@ -841,19 +840,6 @@ def _concat_join_sources(
     if pathlib.Path(dest_path).is_dir():
         shutil.rmtree(path=dest_path)
 
-    # write the concatted result as a parquet file
-    _write_parquet_table_with_metadata(
-        table=pa.concat_tables(
-            tables=[
-                parquet.read_table(
-                    table_path, memory_map=CYTOTABLE_ARROW_USE_MEMORY_MAPPING
-                )
-                for table_path in join_sources
-            ]
-        ),
-        where=dest_path,
-    )
-
     # build a parquet file writer which will be used to append files
     # as a single concatted parquet file, referencing the first file's schema
     # (all must be the same schema)

docs/source/contributing.md

@@ -137,7 +137,6 @@ Automated testing is performed using [GitHub Actions](https://docs.github.com/en
    Example test command: `% poetry run pytest`
 1. [sphinx-build](https://www.sphinx-doc.org/en/master/man/sphinx-build.html) provides documentation website build checks via [`-W`](https://www.sphinx-doc.org/en/master/man/sphinx-build.html#cmdoption-sphinx-build-W) (which turns warnings into errors).
    Example command: `% poetry run sphinx-build docs/source docs/build -W`
-1. [cffconvert](https://github.com/citation-file-format/cffconvert) provides [CITATION.cff file](https://citation-file-format.github.io/) formatting checks. Example command: `% poetry run cffconvert --validate`
 1. [pre-commit](https://pre-commit.com/) provides various checks which are treated as failures in automated testing.
    Example command `% pre-commit run -all-files`