chore: import upstream snapshot with attribution

pyrefly.toml

@@ -0,0 +1,79 @@
+# Ray's Python source lives under the python/ directory.
+# Without this, pyrefly infers the import root as src/ and fails to resolve any ray.* imports.
+search-path = ["python"]
+
+project-includes = [
+    "python/ray/data/**/*.py",
+]
+
+ignore-missing-imports = [
+    "IPython.*",
+    "PIL.*",
+    "bson.*",
+    "clickhouse_connect.*",
+    "cloudpickle.*",
+    "crc32c.*",
+    "daft.*",
+    "dask.*",
+    "datasets.*",
+    "datasketches.*",
+    "decord.*",
+    "delta_sharing.*",
+    "deltalake.*",
+    "fastavro.*",
+    "freezegun.*",
+    "fsspec.*",
+    "google.cloud.*",
+    "hudi.*",
+    "ipywidgets.*",
+    "kafka.*",
+    "lance.*",
+    "mars.*",
+    "mcap.*",
+    "modin.*",
+    "numpy.*",
+    "obstore.*",
+    "pandas.*",
+    "polars.*",
+    "psutil.*",
+    "pyarrow.*",
+    "pyiceberg.*",
+    "pymongo.*",
+    "pymongoarrow.*",
+    "pymysql.*",
+    "pyspark.*",
+    "pytest.*",
+    "pytest_lazy_fixtures.*",
+    "ray.core.generated.*",
+    "raydp.*",
+    "rich.*",
+    "snappy.*",
+    "snowflake.*",
+    "soundfile.*",
+    "tensorflow.*",
+    "tensorflow_datasets.*",
+    "tensorflow_metadata.*",
+    "testcontainers.*",
+    "torch.*",
+    "torchvision.*",
+    "tqdm.*",
+    "transformers.*",
+    "webdataset.*",
+    "cudf.*",
+    "pylibcudf.*",
+    "pynvml.*",
+    "rapidsmpf.*",
+    "rmm.*",
+    "confluent_kafka.*",
+    "zarr.*",
+]
+
+# numcodecs' ``abc.Codec`` ABC declares its abstract ``encode``/``decode`` with
+# empty bodies, so pyrefly infers their return type as ``None`` and flags any
+# real codec subclass (like the one in test_zarrv2) as an inconsistent override
+# -- a numcodecs typing defect we can't satisfy without lying about the return
+# type. So treat numcodecs as Any. (``ignore-missing-imports`` only covers
+# modules that can't be found, not installed ones, so it belongs here.)
+replace-imports-with-any = [
+    "numcodecs.*",
+]