From bd8a6bd2d4a0c5e694b1af888df9cb364dbdd9dd Mon Sep 17 00:00:00 2001
From: Nick Frasser <1693461+nfrasser@users.noreply.github.com>
Date: Mon, 26 Aug 2024 17:03:56 -0400
Subject: [PATCH] Fix: correct pre-commit lint config (#94)

Ruff actually gets applied correctly now
---
 .pre-commit-config.yaml                       | 12 ++++++++++--
 cryosparc/dataset.py                          |  4 ++--
 docs/examples/connect_series_to_class3D.ipynb |  4 ++--
 tests/test_dataset.py                         |  4 ++--
 4 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index ea07f035..6c1b807c 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -10,13 +10,21 @@ repos:
       - id: check-yaml
       - id: check-added-large-files
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.6
+    rev: v0.6.2
     hooks:
       - id: ruff
+        name: ruff check
+        alias: check
+        args: [--fix]
+      - id: ruff
+        name: ruff check imports
+        alias: check-imports
         args: [--fix, --select, I, --exit-non-zero-on-fix]
       - id: ruff-format
+        name: ruff format
+        alias: format
   - repo: https://github.com/RobertCraigie/pyright-python
-    rev: v1.1.374
+    rev: v1.1.377
     hooks:
       - id: pyright
         additional_dependencies: [cython, httpretty, numpy, pytest]
diff --git a/cryosparc/dataset.py b/cryosparc/dataset.py
index 300d6626..4790cbfe 100644
--- a/cryosparc/dataset.py
+++ b/cryosparc/dataset.py
@@ -501,7 +501,7 @@ def innerjoin_many(cls, *datasets: "Dataset"):
         # [0,1,2]}), …]. This is faster than doing the innerjoin for all columns
         # and safer because we don't have to worry about not updating Python
         # string reference counts in the resulting dataset.
-        indexed_dsets = [Dataset({"uid": d["uid"], f"idx{i}": n.arange(len(d))}) for i, d in enumerate(datasets)]
+        indexed_dsets = [cls({"uid": d["uid"], f"idx{i}": n.arange(len(d))}) for i, d in enumerate(datasets)]
         indexed_dset = reduce(lambda dr, ds: cls(dr._data.innerjoin("uid", ds._data)), indexed_dsets)
         result = cls({"uid": indexed_dset["uid"]})
         result.add_fields(all_fields)
@@ -856,7 +856,7 @@ def __eq__(self, other: object):
         """
         return (
             isinstance(other, type(self))
-            and type(self) == type(other)
+            and type(self) is type(other)
             and len(self) == len(other)
             and self.descr() == other.descr()
             and all(n.array_equal(self[c1], other[c2]) for c1, c2 in zip(self, other))
diff --git a/docs/examples/connect_series_to_class3D.ipynb b/docs/examples/connect_series_to_class3D.ipynb
index 43f8b9e0..5bec5880 100644
--- a/docs/examples/connect_series_to_class3D.ipynb
+++ b/docs/examples/connect_series_to_class3D.ipynb
@@ -79,11 +79,11 @@
     }
    ],
    "source": [
+    "import zipfile\n",
+    "\n",
     "unzip_path = series_path[:-4]\n",
     "print(unzip_path)\n",
     "\n",
-    "import zipfile\n",
-    "\n",
     "with zipfile.ZipFile(series_path, \"r\") as z:\n",
     "    z.extractall(unzip_path)"
    ]
diff --git a/tests/test_dataset.py b/tests/test_dataset.py
index 8f713d38..2c09a082 100644
--- a/tests/test_dataset.py
+++ b/tests/test_dataset.py
@@ -254,8 +254,8 @@ def test_pickle_unpickle():
 
 
 def test_column_aggregation(t20s_dset):
-    assert type(t20s_dset["uid"]) == Column
-    assert type(n.max(t20s_dset["uid"])) == n.uint64
+    assert type(t20s_dset["uid"]) is Column
+    assert type(n.max(t20s_dset["uid"])) is n.uint64
     assert isinstance(n.mean(t20s_dset["uid"]), n.number)
     assert not isinstance(n.mean(t20s_dset["uid"]), n.ndarray)