1935746677

Build # 1935746677

Build Type

github

Committed by GitHub

Commit Message

Merge b2c329efa into 250bc4dd4

Pull Request Pull Request #24: Add CMIP file structure - WIP

Run Details

88 of 603 new or added lines in 23 files covered. (14.59%)

3 existing lines in 2 files now uncovered.

654 of 2999 relevant lines covered (21.81%)

0.65 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

25.64

/miranda/ecmwf/_namers.py

import logging
import os
import re
import shutil
from pathlib import Path
from typing import Union

import xarray as xr

__all__ = ["rename_ecmwf_files"]

ECMWF_PROJECT_NAMES = [
    "era5-land",
    "era5-land-monthly-means",
    "era5-pressure-levels",
    "era5-pressure-levels-preliminary-back-extension",
    "era5-single-levels",
    "era5-single-levels-preliminary-back-extension",
]


def rename_ecmwf_files(path: Union[os.PathLike, str]) -> None:
    files = [f for f in Path(path).glob("*.nc")]
    for f in files:
        file_name = str(f.stem)

        ds = xr.open_dataset(f, cache=False)
        var = [d for d in ds.data_vars]
        var_name = str(var[0])

        try:
            x = re.search(r"\d{6}", file_name)
            date = x.group()
        except AttributeError:
            year = int(ds.isel(time=0).time.dt.year)
            month = int(ds.isel(time=0).time.dt.month)
            date = f"{year}{str(month).zfill(2)}"

        names = file_name.split("_")
        projects = [name for name in names if name in ECMWF_PROJECT_NAMES]
        if len(projects) == 1:
            project = projects[0]
        elif len(projects) > 1:
            logging.warning(
                f"More than one project identified for file {f.name}. Verify file naming."
            )
            continue
        else:
            continue

        product = "reanalysis"
        freq = "1hr"
        domain = "NAM"
        institute = "ecmwf"

        new_name_parts = [
            var_name,
            freq,
            institute,
            project,
            product,
            domain,
            date,
        ]
        new_name = f"{'_'.join(new_name_parts)}.nc"
        logging.info(f"Moving {f.name} to {new_name}")

        shutil.move(f, Path(path).joinpath(new_name))

1	import logging	3✔
2	import os	3✔
3	import re	3✔
4	import shutil	3✔
5	from pathlib import Path	3✔
6	from typing import Union	3✔
7
8	import xarray as xr	3✔
9
10	__all__ = ["rename_ecmwf_files"]	3✔
11
12	ECMWF_PROJECT_NAMES = [	3✔
13	"era5-land",
14	"era5-land-monthly-means",
15	"era5-pressure-levels",
16	"era5-pressure-levels-preliminary-back-extension",
17	"era5-single-levels",
18	"era5-single-levels-preliminary-back-extension",
19	]
20
21
22	def rename_ecmwf_files(path: Union[os.PathLike, str]) -> None:	3✔
23	files = [f for f in Path(path).glob("*.nc")]	×
24	for f in files:	×
25	file_name = str(f.stem)	×
26
27	ds = xr.open_dataset(f, cache=False)	×
28	var = [d for d in ds.data_vars]	×
29	var_name = str(var[0])	×
30
31	try:	×
32	x = re.search(r"\d{6}", file_name)	×
33	date = x.group()	×
34	except AttributeError:	×
35	year = int(ds.isel(time=0).time.dt.year)	×
36	month = int(ds.isel(time=0).time.dt.month)	×
37	date = f"{year}{str(month).zfill(2)}"	×
38
39	names = file_name.split("_")	×
40	projects = [name for name in names if name in ECMWF_PROJECT_NAMES]	×
41	if len(projects) == 1:	×
42	project = projects[0]	×
NEW 43	elif len(projects) > 1:	×
NEW 44	logging.warning(	×
45	f"More than one project identified for file {f.name}. Verify file naming."
46	)
NEW 47	continue	×
48	else:
49	continue	×
50
51	product = "reanalysis"	×
52	freq = "1hr"	×
53	domain = "NAM"	×
54	institute = "ecmwf"	×
55
56	new_name_parts = [	×
57	var_name,
58	freq,
59	institute,
60	project,
61	product,
62	domain,
63	date,
64	]
65	new_name = f"{'_'.join(new_name_parts)}.nc"	×
NEW 66	logging.info(f"Moving {f.name} to {new_name}")	×
67
68	shutil.move(f, Path(path).joinpath(new_name))	×

Ouranosinc / miranda / 1935746677

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous