ci: lint and enforce linting (#829)

@eddyxu added instructions for linting here:


7af213801a/python/README.md (L45-L50)

However, we had a lot of failures and weren't checking this in CI. This
PR fixes all lints and adds a check to CI to keep us in compliance with
the lints.

python/tests/test_cli.py

@@ -15,11 +15,11 @@ def test_diagnostics():
     runner = CliRunner()
     result = runner.invoke(cli, ["diagnostics", "--disabled"])
     assert result.exit_code == 0  # Main check
-    assert CONFIG["diagnostics"] == False
+    assert not CONFIG["diagnostics"]
 
     result = runner.invoke(cli, ["diagnostics", "--enabled"])
     assert result.exit_code == 0  # Main check
-    assert CONFIG["diagnostics"] == True
+    assert CONFIG["diagnostics"]
 
 
 def test_config():
@@ -28,8 +28,5 @@ def test_config():
     assert result.exit_code == 0  # Main check
     cfg = CONFIG.copy()
     cfg.pop("uuid")
-    for (
-        item,
-        _,
-    ) in cfg.items():  # check for keys only as formatting is subject to change
+    for item in cfg:  # check for keys only as formatting is subject to change
         assert item in result.output

python/tests/test_db.py

@@ -130,7 +130,8 @@ def test_ingest_iterator(tmp_path):
                     PydanticSchema(vector=[3.1, 4.1], item="foo", price=10.0),
                     PydanticSchema(vector=[5.9, 26.5], item="bar", price=20.0),
                 ],
-                # TODO: test pydict separately. it is unique column number and names contraint
+                # TODO: test pydict separately. it is unique column number and
+                # name constraints
             ]
 
     def run_tests(schema):

python/tests/test_embeddings.py

@@ -18,7 +18,7 @@ import pyarrow as pa
 import pytest
 
 import lancedb
-from lancedb.conftest import MockRateLimitedEmbeddingFunction, MockTextEmbeddingFunction
+from lancedb.conftest import MockTextEmbeddingFunction
 from lancedb.embeddings import (
     EmbeddingFunctionConfig,
     EmbeddingFunctionRegistry,

python/tests/test_pydantic.py

@@ -13,7 +13,6 @@
 
 
 import json
-import pytz
 import sys
 from datetime import date, datetime
 from typing import List, Optional, Tuple
@@ -49,18 +48,19 @@ def test_pydantic_to_arrow():
         dt_with_tz: datetime = Field(json_schema_extra={"tz": "Asia/Shanghai"})
         # d: dict
 
-    m = TestModel(
-        id=1,
-        s="hello",
-        vec=[1.0, 2.0, 3.0],
-        li=[2, 3, 4],
-        lili=[[2.5, 1.5], [3.5, 4.5], [5.5, 6.5]],
-        litu=[(2.5, 1.5), (3.5, 4.5), (5.5, 6.5)],
-        st=StructModel(a="a", b=1.0),
-        dt=date.today(),
-        dtt=datetime.now(),
-        dt_with_tz=datetime.now(pytz.timezone("Asia/Shanghai")),
-    )
+    # TODO: test we can actually convert the model into data.
+    # m = TestModel(
+    #     id=1,
+    #     s="hello",
+    #     vec=[1.0, 2.0, 3.0],
+    #     li=[2, 3, 4],
+    #     lili=[[2.5, 1.5], [3.5, 4.5], [5.5, 6.5]],
+    #     litu=[(2.5, 1.5), (3.5, 4.5), (5.5, 6.5)],
+    #     st=StructModel(a="a", b=1.0),
+    #     dt=date.today(),
+    #     dtt=datetime.now(),
+    #     dt_with_tz=datetime.now(pytz.timezone("Asia/Shanghai")),
+    # )
 
     schema = pydantic_to_schema(TestModel)
 
@@ -133,18 +133,19 @@ def test_pydantic_to_arrow_py38():
         dt_with_tz: datetime = Field(json_schema_extra={"tz": "Asia/Shanghai"})
         # d: dict
 
-    m = TestModel(
-        id=1,
-        s="hello",
-        vec=[1.0, 2.0, 3.0],
-        li=[2, 3, 4],
-        lili=[[2.5, 1.5], [3.5, 4.5], [5.5, 6.5]],
-        litu=[(2.5, 1.5), (3.5, 4.5), (5.5, 6.5)],
-        st=StructModel(a="a", b=1.0),
-        dt=date.today(),
-        dtt=datetime.now(),
-        dt_with_tz=datetime.now(pytz.timezone("Asia/Shanghai")),
-    )
+    # TODO: test we can actually convert the model to Arrow data.
+    # m = TestModel(
+    #     id=1,
+    #     s="hello",
+    #     vec=[1.0, 2.0, 3.0],
+    #     li=[2, 3, 4],
+    #     lili=[[2.5, 1.5], [3.5, 4.5], [5.5, 6.5]],
+    #     litu=[(2.5, 1.5), (3.5, 4.5), (5.5, 6.5)],
+    #     st=StructModel(a="a", b=1.0),
+    #     dt=date.today(),
+    #     dtt=datetime.now(),
+    #     dt_with_tz=datetime.now(pytz.timezone("Asia/Shanghai")),
+    # )
 
     schema = pydantic_to_schema(TestModel)
 

python/tests/test_telemetry.py

@@ -46,7 +46,8 @@ def test_event_reporting(monkeypatch, request_log_path, tmp_path) -> None:
     with open(request_log_path, "r") as f:
         json_data = json.load(f)
 
-    # TODO: don't hardcode these here. Instead create a module level json scehma in lancedb.utils.events for better evolvability
+    # TODO: don't hardcode these here. Instead create a module level json scehma in
+    # lancedb.utils.events for better evolvability
     batch_keys = ["api_key", "distinct_id", "batch"]
     event_keys = ["event", "properties", "timestamp", "distinct_id"]
     property_keys = ["cli", "install", "platforms", "version", "session_id"]