Pre-commit hooks (#193)

* Add pre-commit hooks

* Specify explicitly all exportable names from tiledbsc and remove the flake8 per-file-ignore

Reason: per-file-ignores paths are treated relative to the current directory, not the config file.
This breaks the flake8 pre-commit hook that is invoked from the project root.
See PyCQA/flake8#693

* Lint Python scripts outside of apis/python

.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+repos:
+  - repo: https://github.com/ambv/black
+    rev: 22.3.0
+    hooks:
+    - id: black
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+    - id: isort
+      args: ["--profile", "black"]
+  - repo: https://github.com/pycqa/flake8
+    rev: 4.0.1
+    hooks:
+    - id: flake8
+      args: ["--config", "apis/python/setup.cfg"]

apis/python/setup.cfg

@@ -53,5 +53,3 @@ known_third_party = anndata
 statistics = true
 ignore = E203,E501,W503,B950
 select = B,C,E,F,W,T4,B9
-per-file-ignores =
-    src/tiledbsc/__init__.py: F401

apis/python/src/tiledbsc/__init__.py

@@ -50,3 +50,23 @@
 from .uns_group import UnsGroup
 from .util_ann import describe_ann_file
 from .util_tiledb import show_soma_schemas
+
+__all__ = [
+    "AnnotationMatrix",
+    "AnnotationMatrixGroup",
+    "AnnotationPairwiseMatrixGroup",
+    "AssayMatrix",
+    "AssayMatrixGroup",
+    "RawGroup",
+    "SOMA",
+    "SOMACollection",
+    "SOMAOptions",
+    "SOMASlice",
+    "TileDBArray",
+    "TileDBGroup",
+    "TileDBObject",
+    "UnsArray",
+    "UnsGroup",
+    "describe_ann_file",
+    "show_soma_schemas",
+]

data/simple/ij_test1/gen.py

@@ -1,23 +1,21 @@
-import tiledb, numpy as np
-from tiledb import *
+import numpy as np
+import tiledb
 
 # Reference/label array
 
-s1 = ArraySchema(
-    domain=Domain(
-        *[
-            Dim(name="z_name", tile=None, dtype="ascii"),
-        ]
+s1 = tiledb.ArraySchema(
+    domain=tiledb.Domain(
+        tiledb.Dim(name="z_name", tile=None, dtype="ascii"),
     ),
     attrs=[
-        Attr(name="z_idx", dtype="uint32", var=False, nullable=False),
+        tiledb.Attr(name="z_idx", dtype="uint32", var=False, nullable=False),
     ],
     cell_order="row-major",
     tile_order="row-major",
     capacity=10000,
     sparse=True,
     allows_duplicates=True,
-    coords_filters=FilterList([ZstdFilter(level=-1)]),
+    coords_filters=tiledb.FilterList([tiledb.ZstdFilter(level=-1)]),
 )
 
 tiledb.Array.create("ref", s1)
@@ -39,21 +37,19 @@
 
 # Target array
 
-s2 = ArraySchema(
-    domain=Domain(
-        *[
-            Dim(name="z_idx", domain=(0, 99), tile=10, dtype="uint32"),
-        ]
+s2 = tiledb.ArraySchema(
+    domain=tiledb.Domain(
+        tiledb.Dim(name="z_idx", domain=(0, 99), tile=10, dtype="uint32"),
     ),
     attrs=[
-        Attr(name="data", dtype="int32", var=False, nullable=False),
+        tiledb.Attr(name="data", dtype="int32", var=False, nullable=False),
     ],
     cell_order="row-major",
     tile_order="row-major",
     capacity=10000,
     sparse=True,
     allows_duplicates=False,
-    coords_filters=FilterList([ZstdFilter(level=-1)]),
+    coords_filters=tiledb.FilterList([tiledb.ZstdFilter(level=-1)]),
 )
 
 tiledb.Array.create("tgt", s2)

scripts/update-tiledb-version.py

@@ -48,7 +48,7 @@ def main(args):
     filepath = os.path.realpath(filepath)
     print(f"Updating {filepath}")
     print(f"  new version = {args.version}-{new_hash}")
-    print(f"  computing SHA1 hashes...")
+    print("  computing SHA1 hashes...")
 
     # all "print" statements in this "with" block go to the "fp" file
     with FileInput(filepath, inplace=True) as fp: