#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Denes Turei EMBL 2018
# turei.denes@gmail.com

import os
import itertools

from lipyd import sample

basedir = ('/', 'home', 'denes' , 'archive', 'cihan')
mgfpath = ('data', 'mgf')
skip = {'blanks and standards'}

fractions = [
    (('A8', 'A9', 'A10'),             ('A11', 'A12')),
    (('A6', 'A7', 'A8', 'A9', 'A12'), ('A10', 'A11')),
    (('A6', 'A7', 'A8', 'A9', 'A10'), ('A11', 'A12')),
    (('A9', 'A10', 'B2'),             ('A11', 'A12', 'B1')),
]

fractions = [
    (('A8', 'A9'),             ('A11', 'A12')),
    (('A6', 'A7', 'A8'),       ('A10', 'A11')),
    (('A6', 'A7', 'A8', 'A9'), ('A11', 'A12')),
    (('A9', ),                 ('A11', 'A12', 'B1')),
]

experiments = [
    os.path.join(*(basedir + (dir0, dir1)))
    for dir0 in os.listdir(os.path.join(*basedir))
    for dir1 in os.listdir(os.path.join(*(basedir + (dir0,))))
    if dir0 not in skip
]

peaksfiles = [
    os.path.join(expdirs, 'feature.csv')
    for expdirs in experiments
]

mgfdirs = [
    os.path.join(*((expdirs,) + mgfpath))
    for expdirs in experiments
]


for i in range(len(peaksfiles)):
    
    reader = sample.SampleReader(
        input_type = 'peaks',
        fname = peaksfiles[i]
    )
    
    samples = reader.get_sampleset(
        sampleset_args = {
            'ms2_param': {
                'mgfdir': mgfdirs[i]
            },
            'ms2_format': 'mgf',
        }
    )
    samples.basic_filters()
    samples.peak_size_filter(*fractions[i // 2])
    samples.database_lookup()
    samples.ms2_identify()
    samples.export_table(
        fname = '%s.results.tsv' % peaksfiles[i],
        variables = ['peaksize']
    )
    
    for f in range(len(samples)):
        
        if any(
            ms2i.hg.main in {'BMP', 'PG'}
            for ms2iii in samples.feattrs.ms2_identities[f]
            for ms2ii in ms2iii.values()
            for ms2i in ms2ii
        ):
            
            print(peaksfiles[i])
            print(samples.mzs[f])