[Data] Create unit test directory for fast, isolated tests (#58445)

## Summary
Creates a dedicated `tests/unit/` directory for unit tests that don't
require Ray runtime or external dependencies.

## Changes
- Created `tests/unit/` directory structure
- Moved 13 pure unit tests to `tests/unit/`
- Added `conftest.py` with fixtures to prevent `ray.init()` and
`time.sleep()`
- Added `README.md` documenting unit test requirements
- Updated `BUILD.bazel` to run unit tests with "small" size tag

## Test Files Moved
1. test_arrow_type_conversion.py
2. test_block.py
3. test_block_boundaries.py
4. test_data_batch_conversion.py
5. test_datatype.py
6. test_deduping_schema.py
7. test_expression_evaluator.py
8. test_expressions.py
9. test_filename_provider.py
10. test_logical_plan.py
11. test_object_extension.py
12. test_path_util.py
13. test_ruleset.py

These tests are fast (<1s each), isolated (no Ray runtime), and
deterministic (no time.sleep or randomness).

---------

Signed-off-by: Balaji Veeramani <bveeramani@berkeley.edu>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Author: bveeramani

python/ray/data/BUILD.bazel

@@ -27,6 +27,19 @@ py_library(
     deps = ["//python/ray/tests:conftest"],
 )
 
+py_test_module_list(
+    size = "small",
+    files = glob(["tests/unit/**/test_*.py"]),
+    tags = [
+        "exclusive",
+        "team:data",
+    ],
+    deps = [
+        ":conftest",
+        "//:ray_lib",
+    ],
+)
+
 py_test_module_list(
     size = "medium",
     files = glob(["tests/block_batching/test_*.py"]),
@@ -124,16 +137,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_datatype",
-    size = "small",
-    srcs = ["tests/test_datatype.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-)
-
 py_test(
     name = "test_sql",
     size = "small",
@@ -207,22 +210,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_arrow_type_conversion",
-    size = "small",
-    srcs = [
-        "tests/test_arrow_type_conversion.py",
-    ],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_arrow_serialization",
     size = "small",
@@ -295,20 +282,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_block",
-    size = "small",
-    srcs = ["tests/test_block.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_block_batching",
     size = "medium",
@@ -365,20 +338,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_expressions",
-    size = "small",
-    srcs = ["tests/test_expressions.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_avro",
     size = "small",
@@ -605,31 +564,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_data_batch_conversion",
-    size = "small",
-    srcs = ["tests/test_data_batch_conversion.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
-py_test(
-    name = "test_deduping_schema",
-    size = "small",
-    srcs = ["tests/test_deduping_schema.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [],
-)
-
 py_test(
     name = "test_ecosystem_modin",
     size = "small",
@@ -688,20 +622,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_filename_provider",
-    size = "small",
-    srcs = ["tests/test_filename_provider.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_hash_shuffle",
     size = "small",
@@ -941,20 +861,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_path_util",
-    size = "small",
-    srcs = ["tests/test_path_util.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_task_pool_map_operator",
     size = "small",
@@ -1237,20 +1143,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_object_extension",
-    size = "small",
-    srcs = ["tests/test_object_extension.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_object_gc",
     size = "large",
@@ -1378,20 +1270,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_ruleset",
-    size = "small",
-    srcs = ["tests/test_ruleset.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_size_estimation",
     size = "medium",
@@ -1715,20 +1593,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_logical_plan",
-    size = "small",
-    srcs = ["tests/test_logical_plan.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_mcap",
     size = "medium",
@@ -1785,34 +1649,6 @@ py_test(
     ],
 )
 
-py_test(
-    name = "test_expression_evaluator",
-    size = "small",
-    srcs = ["tests/test_expression_evaluator.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
-py_test(
-    name = "test_block_boundaries",
-    size = "small",
-    srcs = ["tests/test_block_boundaries.py"],
-    tags = [
-        "exclusive",
-        "team:data",
-    ],
-    deps = [
-        ":conftest",
-        "//:ray_lib",
-    ],
-)
-
 py_test(
     name = "test_telemetry",
     size = "medium",

python/ray/data/tests/unit/README.md

@@ -0,0 +1,26 @@
+# Unit Tests
+
+This directory contains unit tests that do not depend on distributed infrastructure or external dependencies.
+
+## Requirements
+
+Unit tests in this directory must be:
+- **Fast**: Execute in milliseconds, not seconds
+- **Isolated**: No dependencies on Ray runtime, external services, or file I/O
+- **Deterministic**: No randomness or time-based behavior
+
+## Restrictions
+
+Tests should NOT:
+- Initialize or use the Ray distributed runtime
+- Use `time.sleep()` or other time-based delays
+- Depend on external services, databases, or file systems
+- Make network calls
+
+## Enforcement
+
+The `conftest.py` in this directory enforces these restrictions by preventing:
+- `ray.init()` from being called
+- `time.sleep()` from being used
+
+If a test requires any of these, it should be moved to the main test directory instead.

python/ray/data/tests/unit/__init__.py

@@ -0,0 +1,24 @@
+import time
+
+import pytest
+
+import ray
+
+
+@pytest.fixture(autouse=True)
+def disallow_ray_init(monkeypatch):
+    def raise_on_init(*args, **kwargs):
+        raise RuntimeError("Unit tests should not depend on Ray being initialized.")
+
+    monkeypatch.setattr(ray, "init", raise_on_init)
+
+
+@pytest.fixture(autouse=True)
+def disallow_time_sleep(monkeypatch):
+    def raise_on_sleep(seconds):
+        raise RuntimeError(
+            f"Unit tests should not use time.sleep({seconds}). "
+            "Unit tests should be fast and deterministic."
+        )
+
+    monkeypatch.setattr(time, "sleep", raise_on_sleep)