diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 67236fedcaa5a5826927b1123e4d311e34d099fd..ac31c7fc009546ecb6e5b22f0ab656da6a3155c7 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,13 +1,21 @@
repos:
+ - repo: https://github.com/pre-commit/mirrors-isort
+ rev: v5.10.1 # ↠Last known good tag
+ hooks:
+ - id: isort
+ args: ["--profile=black"]
+
- repo: https://github.com/psf/black
rev: 25.1.0
hooks:
- id: black
+ args: ["--target-version=py311", "--line-length=79"]
- repo: https://github.com/pycqa/flake8
- rev: 7.1.2
+ rev: 7.2.0
hooks:
- id: flake8
+ args: [--max-line-length=88]
- repo: https://github.com/pre-commit/mirrors-mypy
rev: v1.15.0
diff --git a/Makefile b/Makefile
index 58f95ed8c2ff2b2c159859699daacd1c506b3d00..d1f7a73a37af5867f6499ef5813499071a73c919 100644
--- a/Makefile
+++ b/Makefile
@@ -23,6 +23,9 @@ format:
isort --profile=black src
black -t py311 -l 79 src
+precommit:
+ pre-commit run --all-files
+
lint:
mypy --install-types --non-interactive
isort --check-only --profile=black src
diff --git a/setup.py b/setup.py
index c74514d524fdd8202ed9c80166cfdc97aa7abd7d..8c20d91fb7a1279c4f3a4a69ab6a44fd5cd25e09 100644
--- a/setup.py
+++ b/setup.py
@@ -1,30 +1,30 @@
-from setuptools import setup, find_packages
+from setuptools import find_packages, setup
setup(
- name='era5-tables',
- version='0.1',
- author='Etor E. Lucio Eceiza',
- author_email='lucio-eceiza@dkrz.de',
- license='MIT',
- url='https://gitlab.dkrz.de/bm1159/cosodax/era5-tables',
- packages=find_packages(where='src'),
+ name="era5-tables",
+ version="0.1",
+ author="Etor E. Lucio Eceiza",
+ author_email="lucio-eceiza@dkrz.de",
+ license="MIT",
+ url="https://gitlab.dkrz.de/bm1159/cosodax/era5-tables",
+ packages=find_packages(where="src"),
install_requires=[
- 'pandas>=2.0.0',
- 'openpyxl>=3.1.0',
- 'cfchecker>=4.1.0',
- 'netCDF4>=1.6.0',
- 'numpy>=1.20.0'
+ "pandas>=2.0.0",
+ "openpyxl>=3.1.0",
+ "cfchecker>=4.1.0",
+ "netCDF4>=1.6.0",
+ "numpy>=1.20.0",
],
extras_require={
- 'dev': [
- 'pytest',
- 'mypy',
- 'black',
- 'flake8',
- 'ipython',
- 'pre-commit',
- 'isort'
+ "dev": [
+ "pytest",
+ "mypy",
+ "black",
+ "flake8",
+ "ipython",
+ "pre-commit",
+ "isort",
]
},
- python_requires='>=3.9',
+ python_requires=">=3.9",
)
diff --git a/src/converter.py b/src/converter.py
index d730b7cde9d32746fb065e04043e6f67415c0bad..adf5cf670e1af7a2e277a7a0b9ee76eec195518e 100644
--- a/src/converter.py
+++ b/src/converter.py
@@ -20,12 +20,14 @@ from config import (
search_dirs,
)
+GridType = Literal["redGG-N1280", "redGG-N320", "specG-T639", ""]
today_date: str = datetime.today().strftime("%d %B %Y")
def _determine_level_category(level_type: str) -> str:
"""
- Determines the level category (e.g., 'sfc', 'pl', etc.) for a given level type.
+ Determines the level category (e.g., 'sfc', 'pl', etc.) for a given level
+ type.
Parameters:
level_type (str): The level type string from the dataset.
@@ -115,7 +117,8 @@ def _read_csv(csv_filepath: str) -> pd.DataFrame:
csv_filepath (str): Path to the .rc file.
Returns:
- pd.DataFrame: Cleaned DataFrame with column names and filled missing values.
+ pd.DataFrame: Cleaned DataFrame with column names and filled missing
+ values.
"""
with open(csv_filepath, "r", encoding="utf-8") as f:
lines: List[str] = f.readlines()
@@ -136,8 +139,8 @@ def _get_mapping_source(cmip_val, source_table: str = "") -> str:
Resolves the mapping origin for a variable (e.g., 'ECMWF', 'CMIP6').
The mapping goes as follows in order of priority: Obs4MIPs, CMIP6, CF, ECMWF
When possible it looks at Obs4MIPs tables, then CMIP6, if not it relies on
- the CF CV that was manually written in the csv file. Finally for new variables
- we resort to ECMWF naming.
+ the CF CV that was manually written in the csv file. Finally for new
+ variables we resort to ECMWF naming.
Parameters:
cmip_val (int or str): Mapping indicator value.
@@ -178,7 +181,6 @@ def _filter_level_grid(row: dict, level_type: str) -> dict:
Returns:
dict: Dictionary with keys 'level_type' and 'orig_grid'.
"""
-
all_level_types: list[str] = [
lt.strip() for lt in row.get("LTYPE", "").split(",") if lt.strip()
]
@@ -189,25 +191,20 @@ def _filter_level_grid(row: dict, level_type: str) -> dict:
if level_type not in all_level_types:
return {"level_type": "", "orig_grid": ""}
+ grid: GridType = ""
+
if level_type.startswith("sfc"):
- grid: Literal["redGG-N1280"] | Literal["redGG-N320"] = (
- "redGG-N1280" if "land" in level_type else "redGG-N320"
- )
+ grid = "redGG-N1280" if "land" in level_type else "redGG-N320"
elif level_type.startswith("ml"):
if "specG-T639" in all_grids:
grid = "specG-T639"
elif "redGG-N320" in all_grids:
grid = "redGG-N320"
- else:
- grid = ""
elif level_type.startswith("pl"):
grid = "redGG-N320"
- else:
- grid = ""
-
return {"level_type": level_type, "orig_grid": grid}
@@ -247,8 +244,8 @@ def _get_dimensions(
matched: Optional[Dict], frequency: str, level_type: str
) -> str:
"""
- Build dimensions string, resolving appropriate vertical level and ensuring no
- duplicates. Replaces time-like variants (e.g. time1, time2) with
+ Build dimensions string, resolving appropriate vertical level and ensuring
+ no duplicates. Replaces time-like variants (e.g. time1, time2) with
standard 'time'.
"""
default_dims: (
@@ -262,7 +259,7 @@ def _get_dimensions(
matched.get("dimensions", default_dims) if matched else default_dims
)
dims_parts = dims.split()
- dims_parts: list[str] = [
+ dims_parts = [
"time" if re.match(r"time\d*$", dim) else dim for dim in dims_parts
]
dims_parts = ["longitude" if dim == "site" else dim for dim in dims_parts]
@@ -317,9 +314,7 @@ def _get_cell_info(
elif "min" in var_name.lower():
extreme = "minimum"
if frequency == "mon":
- time_method: str = (
- f"time: {extreme} within days time: mean over days"
- )
+ time_method = f"time: {extreme} within days time: mean over days"
else:
time_method = f"time: {extreme}"
if "ocean" in realm_lc or "seaice" in realm_lc:
@@ -485,7 +480,7 @@ def _ensure_list(val) -> Optional[List[str]]:
def csv_to_cmor_json(
- csv_filepath: Path = csv_file,
+ csv_filepath: str = csv_file,
json_output_path: Path = json_output_path,
var: Optional[Union[str, List[str]]] = None,
freq: Optional[Union[str, List[str]]] = None,
@@ -504,9 +499,9 @@ def csv_to_cmor_json(
clean_output (bool): Whether to clean output directory before writing.
"""
- var: Optional[List[str]] = _ensure_list(var)
- freq: Optional[List[str]] = _ensure_list(freq)
- ltype: Optional[List[str]] = _ensure_list(ltype)
+ var = _ensure_list(var)
+ freq = _ensure_list(freq)
+ ltype = _ensure_list(ltype)
if clean_output:
for file in glob.glob(os.path.join(json_output_path, "*.json")):
@@ -550,7 +545,7 @@ def csv_to_cmor_json(
continue
print(f"{'-'*28}{frequency}{'-'*28}")
key: tuple[str, str] = (frequency, level_group)
- matched: dict = _find_best_matching_variable(
+ matched: dict[Any, Any] | None = _find_best_matching_variable(
var_name, frequency, search_dirs
)
cmor_entry: dict = _build_cmor_entry(