import xarray as xr
import pandas as pd
import glob, os, sys
import numpy as np


if len(sys.argv)<2:
   sys.exit()


var=sys.argv[1]

lon1,lon2,lat1,lat2=13,25,-25,-36

outdir="/terra/projects/ctheatwave_2026/data/reanalysis/global/reanalysis/ECMWF/ERA5-Land/day/wcape/"

outfile="{}/{}_day_ECMWF_ERA5-Land_merged.nc".format(outdir,var)

if not os.path.exists(outfile):
    subset=[]
    lons=[]
    files=glob.glob("/terra/data/reanalysis/global/reanalysis/ECMWF/ERA5-Land/day/africa/{}_day_ECMWF_ERA5-Land_*".format(var))
    for file in files:
        print(file)
        ds=xr.open_mfdataset(file, chunks={"time": 50})
        ds["latitude"]=np.round(ds["latitude"],2).astype("float32")
        ds["longitude"]=np.round(ds["longitude"],2).astype("float32")
        #print(ds.longitude.data)
        ds=ds.drop_vars("time_bnds")
        ds1=ds.sel(latitude=slice(lat1,lat2), longitude=slice(lon1,lon2))
        #print(ds1.longitude.data)
    
        lons.append(ds1.longitude.data)
        subset.append(ds1)
        ds.close()
    
    merged=xr.concat(subset, dim="time").sortby("time").astype("float32")
    
    print(merged[var].shape)

    merged.to_netcdf(outfile)