diff --git a/aosstower/level_b1/nc.py b/aosstower/level_b1/nc.py
index 14fee4aa22c9a2f91d29f325d064c6d1cc2d4596..701945b00fd2ced93d9d90f4436c54a581c75dd5 100644
--- a/aosstower/level_b1/nc.py
+++ b/aosstower/level_b1/nc.py
@@ -1,10 +1,10 @@
-#!/usr/bin/env python
"""Generate AOSS Tower NetCDF4 files from Level 00 ASCII files."""
import logging
import os
import platform
import sys
from datetime import datetime
+from pathlib import Path
import numpy as np
import pandas as pd
@@ -37,7 +37,8 @@ def _get_data(input_files):
bad_files += 1
continue
if bad_files == len(input_files):
- raise ValueError("No valid input data files found")
+ msg = "No valid input data files found"
+ raise ValueError(msg)
def get_data(input_files):
@@ -75,14 +76,14 @@ def write_global_attributes(nc_file, input_sources, interval=None, datastream=No
nc_file.command_line = " ".join(sys.argv)
# generate history
- nc_file.history = " ".join(platform.uname()) + " " + os.path.basename(__file__)
+ nc_file.history = " ".join(platform.uname()) + " " + Path(__file__).name
nc_file.input_source = input_sources[0]
nc_file.input_sources = ", ".join(input_sources)
def create_giant_netcdf(
- input_files,
- output_fn,
+ input_files: list[Path],
+ output_fn: Path,
zlib,
chunk_size,
start=None,
@@ -94,13 +95,15 @@ def create_giant_netcdf(
):
frame = get_data(input_files)
if frame.empty:
- raise ValueError("No data found from input files: {}".format(", ".join(input_files)))
+ in_files_str = ", ".join(str(in_file) for in_file in input_files)
+ msg = f"No data found from input files: {in_files_str}"
+ raise ValueError(msg)
# Add wind direction components so we can average wind direction properly
frame["wind_east"], frame["wind_north"], _ = calc.wind_vector_components(frame["wind_speed"], frame["wind_dir"])
if "air_temp" in frame and "rh" in frame and ("dewpoint" in database or "dewpoint_mean" in database):
- LOG.info("'dewpoint' is missing from the input file, will calculate " "it from air temp and relative humidity")
+ LOG.info("'dewpoint' is missing from the input file, will calculate it from air temp and relative humidity")
frame["dewpoint"] = calc.dewpoint(frame["air_temp"], frame["rh"])
# round up each 1 minute group so data at time T is the average of data
@@ -128,7 +131,7 @@ def create_giant_netcdf(
if start and end:
frame = frame[start.strftime("%Y-%m-%d %H:%M:%S") : end.strftime("%Y-%m-%d %H:%M:%S")]
- chunk_sizes = [chunk_size] if chunk_size and not isinstance(chunk_size, (list, tuple)) else [frame.shape[0]]
+ chunk_sizes = [chunk_size] if chunk_size and not isinstance(chunk_size, list | tuple) else [frame.shape[0]]
first_stamp = datetime.strptime(str(frame.index[0]), "%Y-%m-%d %H:%M:%S")
# NETCDF4_CLASSIC was chosen so that MFDataset reading would work. See:
@@ -147,7 +150,7 @@ def create_giant_netcdf(
write_global_attributes(
nc_file,
- [os.path.basename(x) for x in input_files],
+ [x.name for x in input_files],
interval=interval_width,
datastream=datastream,
)
@@ -195,13 +198,13 @@ def main():
"--start-time",
type=_dt_convert,
help="Start time of massive netcdf file, if only -s is given, a netcdf file for only that day is given"
- + ". Formats allowed: 'YYYY-MM-DDTHH:MM:SS', 'YYYY-MM-DD'",
+ ". Formats allowed: 'YYYY-MM-DDTHH:MM:SS', 'YYYY-MM-DD'",
)
parser.add_argument(
"-e",
"--end-time",
type=_dt_convert,
- help="End time of massive netcdf file. Formats allowed:" + "'YYYY-MM-DDTHH:MM:SS', 'YYYY-MM-DD'",
+ help="End time of massive netcdf file. Formats allowed: 'YYYY-MM-DDTHH:MM:SS', 'YYYY-MM-DD'",
)
parser.add_argument(
"-n",
@@ -257,7 +260,8 @@ each input file is mapped to the corresponding output file.
if args.start_time and not args.end_time:
args.end_time = args.start_time.replace(hour=23, minute=59, second=59)
elif not args.start_time and args.end_time:
- raise ValueError("start time must be specified when end time is specified")
+ msg = "start time must be specified when end time is specified"
+ raise ValueError(msg)
mini_database = {k: schema.database_dict[k] for k in args.fields}
if args.summary:
@@ -266,18 +270,19 @@ each input file is mapped to the corresponding output file.
# Case 1: All inputs to 1 output file
# Case 2: Each input in to a separate output file
if args.output_files and len(args.output_files) not in [1, len(args.input_files)]:
- raise ValueError("Output filenames must be 1 or the same length as input files")
- elif args.output_files and len(args.output_files) == len(args.input_files):
+ msg = "Output filenames must be 1 or the same length as input files"
+ raise ValueError(msg)
+ if args.output_files and len(args.output_files) == len(args.input_files):
args.input_files = [[i] for i in args.input_files]
else:
args.input_files = [args.input_files]
success = False
- for in_files, out_fn in zip(args.input_files, args.output_files):
+ for in_files, out_fn in zip(args.input_files, args.output_files, strict=True):
try:
create_giant_netcdf(
- in_files,
- out_fn,
+ [Path(in_file) for in_file in in_files],
+ Path(out_fn),
args.zlib,
args.chunk_size,
args.start_time,
@@ -291,7 +296,8 @@ each input file is mapped to the corresponding output file.
except (ValueError, TypeError):
LOG.error(f"Could not generate NetCDF file for {in_files}", exc_info=True)
if not success:
- raise OSError("All ASCII files were empty or could not be read")
+ msg = "All ASCII files were empty or could not be read"
+ raise OSError(msg)
if __name__ == "__main__":
diff --git a/pyproject.toml b/pyproject.toml
index 20dc9efb3f89f5edc13032a71193025c220d2d0c..e8dff0b77f433f53ea892584582940d6e3dd2bbc 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -39,6 +39,7 @@ ignore = ["D100", "D101", "D102", "D103", "D104", "D105", "D106", "D107", "D203"
[tool.ruff.per-file-ignores]
"aosstower/tests/*" = ["S", "PLR2004"]
"aosstower/level_b1/quicklook.py" = ["PLR0913"]
+"aosstower/level_b1/nc.py" = ["PLR0913"]
[tool.ruff.pydocstyle]
convention = "google"