#!/usr/bin/env python3
"""
Super simple wrapper to run nagg & aggregate any data
we need aggregated. Adapted from the SDR code.

Copyright (C) 2017-2018 University of Wisconsin Space Science and Engineering Center

This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program.  If not, see <http://www.gnu.org/licenses/>.
"""

import os
import subprocess
import glob

import logging
LOG = logging.getLogger(__name__)


geo_product_ids = \
    ["GATMO", "GCRSO", "GAERO", "GCLDO", "GDNBO", "GNCCO", "GIGTO", "GIMGO", "GITCO", "GMGTO",
     "GMODO", "GMTCO", "GNHFO", "GOTCO", "GOSCO", "GONPO", "GONCO", "GCRIO", "GATRO", "ICDBG","GOTCO"]


edr_product_ids = \
    ["ICALI", "ICALM", "ICCCR", "ICISE", "ICMSE", "ICSTT", "ICTLI", "ICTLM", "IICMO", "IICMS", "SATMR", "SATMS",
     "SCRIS", "SOMPS", "SOMTC", "SOMSC", "SOMNC", "SVDNB", "SVI01", "SVI02", "SVI03", "SVI04", "SVI05", "SVM01",
     "SVM02", "SVM03", "SVM04", "SVM05", "SVM06", "SVM07", "SVM08", "SVM09", "SVM10", "SVM11", "SVM12", "SVM13",
     "SVM14", "SVM15", "SVM16", "TATMS", "REDRO", "OOTCO", "VAOOO", "VCBHO", "VCCLO", "VCEPO", "VCOTO", "VCTHO",
     "VCTPO", "VCTTO", "VI1BO", "VI2BO", "VI3BO", "VI4BO", "VI5BO", "VISTO", "VLSTO", "VM01O", "VM02O", "VM03O",
     "VM04O", "VM05O", "VM06O", "VNCCO", "VNHFO", "VOCCO", "VISAO", "VSCDO", "VSCMO", "VSICO", "VSSTO", "VSTYO",
     "VSUMO", "VIVIO", "REDRS", "OOTCS", "VAOOS", "VCBHS", "VCCLS", "VCEPS", "VCOTS", "VCTHS", "VCTPS", "VCTTS",
     "VISTS", "VLSTS", "VNCCS", "VNHFS", "VOCCS", "VISAS", "VSCDS", "VSCMS", "VSICS", "VSSTS", "VSTPS", "VSUMS",
     "VIVIS", "INCTO", "INPAK", "IIROO", "IIROS", "IMOPO", "IMOPS", "IVAMI", "IVAOT", "IVBPX", "IVCBH", "IVCDB",
     "IVCLT", "IVCOP", "IVCTP", "IVICC", "IVIIC", "IVIIW", "IVIQF", "IVIRT", "IVISR", "IVIWT", "IVPCM", "IVPCP",
     "IVPTP", "IVSIC", "IVSTP"]


NAGG = "nagg" # FIXME: is it ok to assume this is in $PATH?


def nagg(input_dir, datasets, required):
    """
    datasets: list of dataset strings (from geo_product_ids and edr_product_ids)
    required: list of required datasets (processing will fail if any of these are missing)
    """
    LOG.info("Aggregating datasets:")
    LOG.info(datasets)
    for dataset in datasets:
        if dataset in geo_product_ids:
            args = [NAGG, "-g", dataset, "--onefile", "-O", "cspp", "-D", "dev", "-S"]
        elif dataset in edr_product_ids:
            args = [NAGG, "-g", "no", "--onefile", "-O", "cspp", "-D", "dev", "-S", "-t", dataset]
        else:
            raise RuntimeError("dataset %s not recognized!" % (dataset))
        
        input_glob = os.path.join(input_dir, "%s*.h5" % (dataset))
        input_files = glob.glob(input_glob)
        if len(input_files) == 0:
            if dataset not in required:
                LOG.warning("%s missing, but not required. Continuing..." % (dataset))
                continue
            else:
                LOG.error("%s missing, processing cannot continue." % (dataset))
                raise RuntimeError("%s missing, processing cannot continue." % (dataset))

#        if len(input_files) == 1:
#            LOG.info("%s only has one file; doesn't need aggregation just a link from the working dir." % (dataset))
#            os.symlink(input_files[0], os.path.basename(input_files[0]))
#            continue

        args = args + input_files
        LOG.debug(" ".join(args))
        subprocess.check_call(args=args)


if __name__ == "__main__":
    """
    Simple aggregate everything in a provided directory test.
    """
    DATASET_KEYS = ['GITCO', 'GMTCO', 'IICMO', 
                    'SVI01', 'SVI02', 'SVI03',
                    'SVI04', 'SVI05']
    import sys
    nagg(sys.argv[1], DATASET_KEYS, DATASET_KEYS)