#!/usr/bin/env python3

import pandas as pd
import subprocess
import sys
import argparse
import tempfile

def main(argv):
    parser = argparse.ArgumentParser()
    # we need to intercept these arguments
    parser.add_argument('--cutoff', type=float, default=100.0)
    parser.add_argument('--blacklist', required=True)
    parser.add_argument('--output', required=True)
    parser.add_argument('--output-format',  default='tsv')
    args, mirbooking_args = parser.parse_known_args(argv)
    target_cutoff = args.cutoff
    # this is generally a good starting point
    cutoff = 1000.0
    try:
        blacklist = pd.read_csv(args.blacklist, sep='\t')
    except FileNotFoundError:
        blacklist = pd.DataFrame(columns=['target_accession', 'position', 'mirna_accession'])
    while True:
        with tempfile.NamedTemporaryFile() as output:
            mirbooking_final_args =['mirbooking'] + mirbooking_args

            # generate a blacklist for this iteration
            blacklist.to_csv(args.blacklist, sep='\t', index=False)
            mirbooking_final_args.extend(['--blacklist', args.blacklist])

            mirbooking_final_args.extend(['--cutoff', str(cutoff)])

            if cutoff <= target_cutoff:
                # emit what the user is asking for
                mirbooking_final_args.extend(['--output', args.output, '--output-format', args.output_format])
            else:
                # emit an intermediate output model in TSV
                mirbooking_final_args.extend(['--output', output.name,  '--output-format', 'tsv'])

            print(f'Running mirbooking with cutoff of {cutoff:.2f}pM and {len(blacklist)} blacklisted interactions.')
            ret = subprocess.run(mirbooking_final_args)
            if ret.returncode != 0:
                break

            # done, this is the last model we want to calculate
            if cutoff <= target_cutoff:
                break

            # filter out interactions that do not meet the target cutoff from the intermediate output
            df = pd.read_csv(output.name, sep='\t')
            blacklist = blacklist.append(df[df.quantity < target_cutoff][blacklist.columns])
            cutoff /= 1.1

if __name__ == '__main__':
    sys.exit(main(sys.argv))
