Use case for testing NWP model using a predefined WIGOS SI ready dataset.

'''
# Copyright 2005-2018 ECMWF.
# This software is licensed under the terms of the Apache Licence Version 2.0
# which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
# In applying this licence, ECMWF does not waive the privileges and immunities
# granted to it by virtue of its status as an intergovernmental organisation
# nor does it submit to any jurisdiction
   
This is a test program to encode Wigos Synop
requires
   
1) ecCodes version 2.14.1 or above (available at https://confluence.ecmwf.int/display/ECC/Releases)
2) python3.6.8-01
   
To run the program
   
   ./addWigosProg.py  -i synop_multi_subset.bufr -o out_synop_multisubset.bufr  -w WIGOS_TEMP_IDENT.csv
      
Uses BUFR version 4 template  and adds the WIGOS Identifier 301150
REQUIRES TablesVersionNumber above 28
   
Author : Roberto Ribas Garcia ECMWF 28/10/2019

Modifications
    performance improvement ( uses skipExtraKeyAttributes)  and codes_clone   04/11/2019
    changes for SYNOP and TEMP messages                                       05/11/2019
    fixed codes_clone issue                                                   05/11/2019

'''
from eccodes import *
import argparse 
import json 
import re 
import pandas as pd 
import numpy as np 
import logging 
import requests 
import os 

def read_cmd_line():
    p=argparse.ArgumentParser()
    p.add_argument("-i","--input",help="input bufr file")
    p.add_argument("-o","--output",help="output bufr file with wigos")
    p.add_argument("-m","--mode",choices=["web","json"],help=" wigos source [ json file or web ]")
    p.add_argument("-l","--logfile",help="log file ")
    args=p.parse_args()
    return args 
    
def read_oscar_json(jsonFile):
    with open(jsonFile,"r") as f:
        jtext=json.load(f)
    return jtext 

def read_oscar_web(oscarURL="https://oscar.wmo.int/surface/rest/api/search/station?"):
    r=requests.get(oscarURL)
    jtext=json.loads(r.text)
    return jtext 

def parse_json_into_dataframe(jtext):
    '''
    parses the JSON from the file wigosJsonFile
    filters the stations by wigosStationIdentifiers key in the dictionaries
    '''
    
    wigosStations=[]
    nowigosStations=[]
    for d in jtext:
        if "wigosStationIdentifiers" in d.keys():
            wigosStations.append(d)
        else:
            nowigosStations.append(d)
    
    '''
    uses only the wigos 0-20XXX-0-YYYYY (surface)
    '''
    p=re.compile("0-20\d{3}-0-\d{5}")

    fwigosStations=[]
    for d in wigosStations:
        wigosInfo=d["wigosStationIdentifiers"]
        for e in wigosInfo:
            if e["primary"]==True:
                wigosId=e["wigosStationIdentifier"]
                if p.match(wigosId):
                    wigosParts=wigosId.split("-")
                    d["wigosIdentifierSeries"]=wigosParts[0]
                    d["wigosIssuerOfIdentifier"]=wigosParts[1]
                    d["wigosIssueNumber"]=wigosParts[2]
                    d["wigosLocalIdentifierCharacter"]=wigosParts[3]
                    d["oldID"]=wigosParts[3][-5:]
                    fwigosStations.append(d)
                    
    df=pd.DataFrame(fwigosStations)
    df=df[["longitude","latitude","name","wigosStationIdentifiers","wigosIdentifierSeries","wigosIssuerOfIdentifier","wigosIssueNumber",
           "wigosLocalIdentifierCharacter","oldID"]]  
    return df

def get_ident(bid):
    '''
    gets the ident of the message by combining blockNumber and stationNumber keys from the input BUFR file
    the ident may be single valued or multivalued ( only single valued are considered further)
    
    '''
    ident=None 
    if ( codes_is_defined(bid, "blockNumber") and codes_is_defined(bid,"stationNumber") ):
        blockNumber=codes_get_array(bid,"blockNumber")
        stationNumber=codes_get_array(bid,"stationNumber")
        if len(blockNumber)==1 and len(stationNumber)==1:
            ident="{0:02d}{1:03d}".format(int(blockNumber),int(stationNumber))
        elif len(blockNumber)==1 and len(stationNumber)!=1:
            blockNumber=np.repeat(blockNumber,len(stationNumber))
            ident=[str("{0:02d}{1:03d}".format(b,s)) for b,s in zip(blockNumber,stationNumber) 
                   if b!=CODES_MISSING_LONG and s!=CODES_MISSING_LONG] 
        elif len(blockNumber)!=1 and len(stationNumber)!=1:
            ident=[str("{0:02d}{1:03d}".format(b,s)) for b,s in zip(blockNumber,stationNumber) 
                   if b!=CODES_MISSING_LONG and s!=CODES_MISSING_LONG]
        '''
        here only the first element of the list is returned to the main program
        this avoids lists being used in the dataframe query and breaking the logic
        '''
        if isinstance(ident,list):
            ident=ident[0]
    return ident 


    

def add_wigos_info(ident,bid,odf,obid):
    '''
    add the wigos information to the message ident pointed by bid
    the odf contains the WIGOS information for ident 
    obid is the output handle
    '''
   
    
    if codes_is_defined(bid, "shortDelayedDescriptorReplicationFactor"):
        shortDelayed=codes_get_array(bid,"shortDelayedDescriptorReplicationFactor")
    else:
        shortDelayed=None 

    if codes_is_defined(bid, "delayedDescriptorReplicationFactor"):
        delayedDesc=codes_get_array(bid,"delayedDescriptorReplicationFactor")
    else:
        delayedDesc=None 
        
    if codes_is_defined(bid, "extendedDelayedDescriptorReplicationFactor"):
        extDelayedDesc=codes_get_array(bid,"extendedDelayedDescriptorReplicationFactor")
    else:
        extDelayedDesc=None 

        
    nsubsets=codes_get(bid,"numberOfSubsets")
    compressed=codes_get(bid,"compressedData")
    
    masterTablesVersionNumber=codes_get(bid,"masterTablesVersionNumber")
    if masterTablesVersionNumber<28:
        masterTablesVersionNumber=28
        
    unexpandedDescriptors=codes_get_array(bid,"unexpandedDescriptors")
    outUD=list(unexpandedDescriptors)
    outUD.insert(0,301150)
        
    '''
    only treat the uncompressed messages with 1 subset 
    for future add treatment of compressed messages with more than 1 subset
    '''
    
    if compressed==0 and nsubsets==1:
        '''
        IMPORTANT, takes into account delayed replications ( all possible cases) to accommodate
        SYNOP + TEMP messages 
        '''
        if shortDelayed is not None:
            codes_set_array(obid,"inputShortDelayedDescriptorReplicationFactor",shortDelayed)
        if delayedDesc is not None:
            codes_set_array(obid,"inputDelayedDescriptorReplicationFactor",delayedDesc)
        if extDelayedDesc is not None:
            codes_set_array(obid,"inputExtendedDelayedDescriptorReplicationFactor",extDelayedDesc)
            

        codes_set(obid,"masterTablesVersionNumber",masterTablesVersionNumber)
        codes_set(obid,"numberOfSubsets",nsubsets)
        
        
        codes_set_array(obid, "unexpandedDescriptors",outUD)
        wis=odf["wigosIdentifierSeries"].values 
        if len(wis)!=1:
            wis=wis[0]
        codes_set(obid,"wigosIdentifierSeries",int(wis))
        wid=odf["wigosIssuerOfIdentifier"].values 
        if len(wid)!=1:
            wid=wid[0]
        codes_set(obid,"wigosIssuerOfIdentifier",int(wid))
        win=odf["wigosIssueNumber"].values 
        if len(win)!=1:
            win=win[0]
        codes_set(obid,"wigosIssueNumber",int(win))            
        wlid=odf["wigosLocalIdentifierCharacter"].values 
        wlid="{0:5}".format(wlid[0])
        logging.info(" wlid here {0}".format(wlid))
        codes_set(obid,"wigosLocalIdentifierCharacter",str(wlid))
        codes_bufr_copy_data(bid,obid)
    else:
        logging.info(" skipping compressed  message id {0} with {1} subsets ".format(ident,nsubsets))
    
    return 
    
     

def main():
    print("ecCodes version {0}".format(codes_get_api_version()))
    args=read_cmd_line()
    logfile=args.logfile 
    logging.basicConfig(filename=logfile,level=logging.INFO,filemode="w")
    
    infile=args.input 
    
    outfile=args.output 
   
    mode=args.mode 
    if mode=="web":
        jtext=read_oscar_web()
        cdirectory=os.getcwd()
        oscarFile=os.path.join(cdirectory,"oscar.json")
        with open(oscarFile,"w") as f:
            json.dump(jtext,f)
    else:
        cdirectory=os.getcwd()
        oscarFile=os.path.join(cdirectory,"oscar.json")
        with open(oscarFile,"r") as f:
            jtext=json.load(f)
           
       
        
    wigosDf=parse_json_into_dataframe(jtext)
    
    f=open(infile,"rb")
    nmsg=codes_count_in_file(f)
    fout=open(outfile,"wb")
    for i in range(0,nmsg):
        bid=codes_bufr_new_from_file(f)
        obid=codes_clone(bid)
        codes_set(bid, 'skipExtraKeyAttributes', 1)
        codes_set(bid,"unpack",1)
        ident=get_ident(bid)
       
        if ident:
            logging.info (" \t message {0} ident {1} ".format(i+1,ident))

            odf=wigosDf.query("oldID=='{0}'".format(ident))                
            if not odf.empty:
                add_wigos_info(ident,bid, odf,obid)
                codes_write(obid,fout)
            else:
                logging.info(" wigos {0} is empty for ident {1}".format(ident,odf["wigosLocalIdentifierCharacter"].values))
    
        else:
            logging.info ("message {0} rejected ".format(i+1))
        codes_release(obid)        
        codes_release(bid)
    f.close()    
   
    print (" finished")


if __name__ == '__main__':
    main()