Bump minimum tested Python version to 3.10 and use pyupgrade in pre-c…

…ommit

- [pre-commit.ci] auto fixes from pre-commit.com hooks
  for more information, see https://pre-commit.ci

- pre-commit autoupdate

.github/workflows/ci.yml

@@ -56,7 +56,7 @@ jobs:
       fail-fast: false
       max-parallel: 2
       matrix:
-        python-version: ["3.9", "3.10"]
+        python-version: ["3.10", "3.11"]
 
     steps:
       - uses: actions/checkout@v3

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: mixed-line-ending
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.1.4"
+    rev: "v0.1.13"
     hooks:
       - id: ruff
         args: [--fix]
@@ -36,8 +36,13 @@ repos:
       - id: prettier
         types_or: [javascript, jsx, vue, html, yaml]
 
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.15.0
+    hooks:
+      - id: pyupgrade
+
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.6.1
+    rev: v1.8.0
     hooks:
       - id: mypy
         additional_dependencies: ["types-all", "pydantic~=1.10"]

pydatalab/pydatalab/apps/nmr/utils.py

@@ -53,7 +53,7 @@ def read_bruker_1d(
     p_dic, p_data = ng.fileio.bruker.read_pdata(str(processed_data_dir))  # processing data
 
     try:
-        with open(os.path.join(processed_data_dir, "title"), "r") as f:
+        with open(os.path.join(processed_data_dir, "title")) as f:
             topspin_title = f.read()
     except FileNotFoundError:
         topspin_title = None
@@ -101,7 +101,7 @@ def read_topspin_txt(filename, sample_mass_mg=None, nscans=None):
     LEFTRIGHT_REGEX = r"# LEFT = (-?\d+\.\d+) ppm. RIGHT = (-?\d+\.\d+) ppm\."
     SIZE_REGEX = r"SIZE = (\d+)"
 
-    with open(filename, "r") as f:
+    with open(filename) as f:
         header = "".join(itertools.islice(f, MAX_HEADER_LINES))  # read the first 10 lines
     # print(header)
 

pydatalab/pydatalab/apps/raman/blocks.py

@@ -33,7 +33,7 @@ def load(self, location: str | Path) -> tuple[pd.DataFrame, dict, list[str]]:
         if ext == ".txt":
             try:
                 header = []
-                with open(location, "r", encoding="cp1252") as f:
+                with open(location, encoding="cp1252") as f:
                     for line in f:
                         if line.startswith("#"):
                             header.append(line)

pydatalab/pydatalab/apps/tga/parsers.py

@@ -27,7 +27,7 @@ def parse_mt_mass_spec_ascii(path: Path) -> Dict[str, Union[pd.DataFrame, Dict]]
     if not path.exists():
         raise RuntimeError(f"Provided path does not exist: {path!r}")
 
-    with open(path, "r") as f:
+    with open(path) as f:
         # Read start of file until all header keys have been found
         max_header_lines = 8
         reads = 0

pydatalab/pydatalab/apps/xrd/utils.py

@@ -24,7 +24,7 @@ def parse_xrdml(filename: str) -> pd.DataFrame:
         filename: The file to parse.
 
     """
-    with open(filename, "r") as f:
+    with open(filename) as f:
         s = f.read()
 
     start, end = getStartEnd(s)  # extract first and last angle
@@ -70,7 +70,7 @@ def convertSinglePattern(
             )
             return outfn
 
-    with open(filename, "r") as f:
+    with open(filename) as f:
         s = f.read()
 
     print(f"Processing file {filename}")

pydatalab/pydatalab/backups.py

@@ -179,7 +179,7 @@ def create_backup(strategy: BackupStrategy) -> bool:
         sftp = client.open_sftp()
         try:
             sftp.chdir(path=str(strategy.location))
-        except IOError:
+        except OSError:
             sftp.mkdir(path=str(strategy.location))
             sftp.chdir(path=str(strategy.location))
 

pydatalab/pydatalab/config.py

@@ -123,7 +123,7 @@ class ServerConfig(BaseSettings):
     """A model that provides settings for deploying the API."""
 
     SECRET_KEY: str = Field(
-        hashlib.sha512(((platform.platform() + str(platform.python_build)).encode())).hexdigest(),
+        hashlib.sha512((platform.platform() + str(platform.python_build)).encode()).hexdigest(),
         description="The secret key to use for Flask. This value should be changed and/or loaded from an environment variable for production deployments.",
     )
 

pydatalab/pydatalab/file_utils.py

@@ -256,7 +256,7 @@ def get_file_info_by_id(
         {"_id": file_id, **get_default_permissions(user_only=False)}
     )
     if not file_info:
-        raise IOError(f"could not find file with id: {file_id} in db")
+        raise OSError(f"could not find file with id: {file_id} in db")
 
     file_info = File(**file_info)
 
@@ -291,7 +291,7 @@ def update_uploaded_file(file, file_id, last_modified=None, size_bytes=None):
     )
 
     if not updated_file_entry:
-        raise IOError(f"Issue with db update uploaded file {file.name} id {file_id}")
+        raise OSError(f"Issue with db update uploaded file {file.name} id {file_id}")
 
     updated_file_entry = File(**updated_file_entry)
 
@@ -422,7 +422,7 @@ def save_uploaded_file(
             {"$push": {"file_ObjectIds": inserted_id}},
         )
         if sample_update_result.modified_count != 1:
-            raise IOError(
+            raise OSError(
                 f"db operation failed when trying to insert new file ObjectId into sample: {item_id}"
             )
 
@@ -496,7 +496,7 @@ def add_file_from_remote_directory(
 
     result = file_collection.insert_one(new_file_document.dict())
     if not result.acknowledged:
-        raise IOError(f"db operation failed when trying to insert new file. Result: {result}")
+        raise OSError(f"db operation failed when trying to insert new file. Result: {result}")
 
     inserted_id = result.inserted_id
 
@@ -521,7 +521,7 @@ def add_file_from_remote_directory(
         {"$push": {"file_ObjectIds": inserted_id}},
     )
     if sample_update_result.modified_count != 1:
-        raise IOError(
+        raise OSError(
             f"db operation failed when trying to insert new file ObjectId into sample: {item_id}"
         )
 
@@ -562,7 +562,7 @@ def remove_file_from_sample(item_id: Union[str, ObjectId], file_id: Union[str, O
     )
 
     if sample_result.modified_count < 1:
-        raise IOError(
+        raise OSError(
             f"Failed to remove {file_id!r} from item {item_id!r}. Result: {sample_result.raw_result}"
         )
 

pydatalab/pydatalab/models/cells.py

@@ -82,11 +82,11 @@ def add_missing_electrode_relationships(cls, values):
 
         existing_parthood_relationship_ids = set()
         if values.get("relationships") is not None:
-            existing_parthood_relationship_ids = set(
+            existing_parthood_relationship_ids = {
                 relationship.item_id
                 for relationship in values["relationships"]
                 if relationship.relation == RelationshipType.PARTHOOD
-            )
+            }
         else:
             values["relationships"] = []
 

pydatalab/pydatalab/models/samples.py

@@ -29,11 +29,11 @@ def add_missing_synthesis_relationships(cls, values):
         if values.get("synthesis_constituents") is not None:
             existing_parent_relationship_ids = set()
             if values.get("relationships") is not None:
-                existing_parent_relationship_ids = set(
+                existing_parent_relationship_ids = {
                     relationship.item_id or relationship.refcode
                     for relationship in values["relationships"]
                     if relationship.relation == RelationshipType.PARENT
-                )
+                }
             else:
                 values["relationships"] = []
 

pydatalab/pydatalab/models/traits.py

@@ -45,14 +45,14 @@ def add_missing_collection_relationships(cls, values):
         from pydatalab.models.relationships import TypedRelationship
 
         if values.get("collections") is not None:
-            new_ids = set(coll.immutable_id for coll in values["collections"])
+            new_ids = {coll.immutable_id for coll in values["collections"]}
             existing_collection_relationship_ids = set()
             if values.get("relationships") is not None:
-                existing_collection_relationship_ids = set(
+                existing_collection_relationship_ids = {
                     relationship.immutable_id
                     for relationship in values["relationships"]
                     if relationship.type == "collections"
-                )
+                }
             else:
                 values["relationships"] = []
 

pydatalab/pydatalab/routes/v0_1/collections.py

@@ -164,7 +164,7 @@ def create_collection():
 
     errors = []
     if starting_members:
-        item_ids = set(d.get("item_id") for d in starting_members)
+        item_ids = {d.get("item_id") for d in starting_members}
         if None in item_ids:
             item_ids.remove(None)
 

pydatalab/pydatalab/routes/v0_1/items.py

@@ -669,9 +669,9 @@ def get_item_data(item_id, load_blocks: bool = False):
     return_dict = json.loads(doc.json(exclude_unset=True))
 
     # create the files_data dictionary keyed by file ObjectId
-    files_data: Dict[ObjectId, Dict] = dict(
-        [(f["immutable_id"], f) for f in return_dict.get("files") or []]
-    )
+    files_data: Dict[ObjectId, Dict] = {
+        f["immutable_id"]: f for f in return_dict.get("files") or []
+    }
 
     return jsonify(
         {

pydatalab/scripts/migrate_files_to_files_ObjectId_v2.py

@@ -65,7 +65,7 @@
 
         result = file_collection.insert_one(new_file_document)
         if not result.acknowledged:
-            raise IOError(f"db operation failed when trying to insert new file. Result: {result}")
+            raise OSError(f"db operation failed when trying to insert new file. Result: {result}")
 
         inserted_id = result.inserted_id
 
@@ -89,6 +89,6 @@
             {"sample_id": sample_id}, {"$push": {"file_ObjectIds": inserted_id}}
         )
         if sample_update_result.modified_count != 1:
-            raise IOError(
+            raise OSError(
                 f"mdb operation failed when trying to insert new file ObjectId into sample: {sample_id}"
             )

pydatalab/tasks.py

@@ -23,7 +23,7 @@ def update_file(filename: str, sub_line: Tuple[str, str], strip: str | None = No
     Modified from optimade-python-tools.
 
     """
-    with open(filename, "r") as handle:
+    with open(filename) as handle:
         lines = [re.sub(sub_line[0], sub_line[1], line.rstrip(strip)) for line in handle]
 
     with open(filename, "w") as handle:

pydatalab/tests/apps/test_echem_block.py

@@ -70,9 +70,7 @@ def test_filter_df_by_cycle_index(reduced_echem_dataframe):
     cycle_lists = ([1, 2, 3], [4.0, 6.0, 10.0], [-1, 5, 2])
     for cycle_list in cycle_lists:
         filtered_df = filter_df_by_cycle_index(reduced_echem_dataframe, cycle_list)
-        assert set(int(i) for i in filtered_df["full cycle"]).issubset(
-            set(int(i) for i in cycle_list)
-        )
+        assert {int(i) for i in filtered_df["full cycle"]}.issubset({int(i) for i in cycle_list})
 
 
 def test_plot(reduced_echem_dataframe):