Removed 3.9 artifacts, updated syntax (#261)

.github/workflows/ci.yml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
 
     steps:
       - name: Checkout source

src/access_nri_intake/catalog/manager.py

@@ -4,7 +4,6 @@
 """Manager for adding/updating intake sources in an intake-dataframe-catalog like the ACCESS-NRI catalog"""
 
 import os
-from typing import Optional, Union
 
 import intake
 from intake_dataframe_catalog.core import DfFileCatalog, DfFileCatalogError
@@ -63,10 +62,10 @@ def build_esm(
         name: str,
         description: str,
         builder,
-        path: Union[str, list[str]],
+        path: str | list[str],
         translator=DefaultTranslator,
-        metadata: Optional[dict] = None,
-        directory: Optional[str] = None,
+        metadata: dict | None = None,
+        directory: str | None = None,
         overwrite: bool = False,
         **kwargs,
     ):
@@ -131,7 +130,7 @@ def load(
         path: str,
         driver: str = "esm_datastore",
         translator=DefaultTranslator,
-        metadata: Optional[dict] = None,
+        metadata: dict | None = None,
         **kwargs,
     ):
         """

src/access_nri_intake/catalog/translators.py

@@ -8,7 +8,7 @@
 
 from dataclasses import dataclass
 from functools import partial
-from typing import Callable, Optional
+from typing import Callable
 
 import pandas as pd
 import tlz
@@ -120,7 +120,7 @@ def _default_translator(self, column: str) -> pd.Series:
 
         return pd.Series([val] * len_df)
 
-    def translate(self, groupby: Optional[list[str]] = None) -> pd.DataFrame:
+    def translate(self, groupby: list[str] | None = None) -> pd.DataFrame:
         """
         Return the translated :py:class:`~pandas.DataFrame` of metadata and merge into set of
         set of rows with unique values of the columns specified.
@@ -168,7 +168,7 @@ def _unique_values(series):
         return df[self.columns]  # Preserve ordering
 
     def set_dispatch(
-        self, core_colname: str, func: Callable, input_name: Optional[str] = None
+        self, core_colname: str, func: Callable, input_name: str | None = None
     ):
         """
         Set a dispatch function for a column. Typically only required when either:
@@ -549,10 +549,10 @@ class _DispatchKeys:
     Data class to store the keys for the dispatch dictionary in the Translator classes
     """
 
-    model: Optional[str] = None
-    realm: Optional[str] = None
-    frequency: Optional[str] = None
-    variable: Optional[str] = None
+    model: str | None = None
+    realm: str | None = None
+    frequency: str | None = None
+    variable: str | None = None
 
 
 def _cmip_realm_translator(series) -> pd.Series:

src/access_nri_intake/source/builders.py

@@ -7,7 +7,6 @@
 import re
 import traceback
 from pathlib import Path
-from typing import Optional, Union
 
 import xarray as xr
 from ecgtools.builder import INVALID_ASSET, TRACEBACK, Builder
@@ -58,14 +57,14 @@ class BaseBuilder(Builder):
 
     def __init__(
         self,
-        path: Union[str, list[str]],
+        path: str | list[str],
         depth: int = 0,
-        exclude_patterns: Optional[list[str]] = None,
-        include_patterns: Optional[list[str]] = None,
+        exclude_patterns: list[str] | None = None,
+        include_patterns: list[str] | None = None,
         data_format: str = "netcdf",
-        groupby_attrs: Optional[list[str]] = None,
-        aggregations: Optional[list[dict]] = None,
-        storage_options: Optional[dict] = None,
+        groupby_attrs: list[str] | None = None,
+        aggregations: list[dict] | None = None,
+        storage_options: dict | None = None,
         joblib_parallel_kwargs: dict = {"n_jobs": multiprocessing.cpu_count()},
     ):
         """
@@ -120,7 +119,7 @@ def parse(self):
         self._parse()
         return self
 
-    def _save(self, name: str, description: str, directory: Optional[str]):
+    def _save(self, name: str, description: str, directory: str | None):
         super().save(
             name=name,
             path_column_name=PATH_COLUMN,
@@ -135,9 +134,7 @@ def _save(self, name: str, description: str, directory: Optional[str]):
             to_csv_kwargs={"compression": "gzip"},
         )
 
-    def save(
-        self, name: str, description: str, directory: Optional[str] = None
-    ) -> None:
+    def save(self, name: str, description: str, directory: str | None = None) -> None:
         """
         Save datastore contents to a file.
 
@@ -221,10 +218,10 @@ def parser(file):
     def parse_access_filename(
         cls,
         filename: str,
-        patterns: Optional[list[str]] = None,
+        patterns: list[str] | None = None,
         frequencies: dict = FREQUENCIES,
         redaction_fill: str = "X",
-    ) -> tuple[str, Optional[str], Optional[str]]:
+    ) -> tuple[str, str | None, str | None]:
         """
         Parse an ACCESS model filename and return a file id and any time information
 

src/access_nri_intake/source/utils.py

@@ -7,7 +7,6 @@
 from dataclasses import asdict, dataclass, field
 from datetime import timedelta
 from pathlib import Path
-from typing import Optional, Union
 
 import cftime
 import xarray as xr
@@ -30,10 +29,10 @@ class _AccessNCFileInfo:
     more explicit tests are probably more important than the slight redundancy.
     """
 
-    filename: Union[str, Path]
+    filename: str | Path
     file_id: str
     path: str
-    filename_timestamp: Optional[str]
+    filename_timestamp: str | None
     frequency: str
     start_date: str
     end_date: str
@@ -43,7 +42,7 @@ class _AccessNCFileInfo:
     variable_cell_methods: list[str]
     variable_units: list[str]
 
-    def to_dict(self) -> dict[str, Union[str, list[str]]]:
+    def to_dict(self) -> dict[str, str | list[str]]:
         """
         Return a dictionary representation of the NcFileInfo object
         """
@@ -139,7 +138,7 @@ def _guess_start_end_dates(ts, te, frequency):
 
 def get_timeinfo(
     ds: xr.Dataset,
-    filename_frequency: Optional[str],
+    filename_frequency: str | None,
     time_dim: str,
 ) -> tuple[str, str, str]:
     """
@@ -177,7 +176,7 @@ def _todate(t):
     time_format = "%Y-%m-%d, %H:%M:%S"
     ts = None
     te = None
-    frequency: Union[str, tuple[Optional[int], str]] = "fx"
+    frequency: str | tuple[int | None, str] = "fx"
     has_time = time_dim in ds
 
     if has_time: