include: "scripts/shared.py"

from snakemake.utils import validate

#Validate configuration files

configfile: "config.yaml"
validate(config, "schemas/config.schema.yaml")


#Generate Input/Output Files from specified folder

kmer_lengths = config['kmers']
dataset_inputIDs = {}

#kmer_lengths = [24]
def get_general_inputs(wildcards):
	run_dir = wildcards.dataset
	inputIDs, = glob_wildcards('data/input/'+wildcards.dataset+'/{id}'+config["datasets"][wildcards.dataset]['input_read_1_ending'])
	dataset_inputIDs[wildcards.dataset] = inputIDs

	possible_params = {
	'assembly_model': expand('data/output/'+run_dir+'/{id}/exactMatches.tsv',id=inputIDs),
	'calc_strand_bias': expand('data/output/'+run_dir+'/{id}/strandbias.txt',id=inputIDs),
	'mapping_diff_analysis': expand('data/output/'+run_dir+'/methodAnalysis/{id}/mapping.comparison',id=inputIDs),
	'map_filtered_reads': expand('data/output/'+run_dir+'/methodAnalysis/{id}/alignmentToGroundTruthType.sorted.bam.bai',id=inputIDs),
	'verifyUniqueness': expand('data/output/kmers/{kmer}/uniquenessTest.tsv',kmer=kmer_lengths),
	'kmer_stats_analysis': expand('data/auxiliary/'+run_dir+'/kmers/{kmer}/{id}/stats.tsv',kmer=kmer_lengths,id=inputIDs)
	}

	return [item for k in possible_params.keys() if config[k] for item in possible_params[k]]

def get_iterset_inputs(wildcards):
	inputIDs, = glob_wildcards('data/input/'+wildcards.dataset+'/{id}'+config["datasets"][wildcards.dataset]['input_read_1_ending'])
	possible_params = {
		'generative_model': expand('data/output/' + wildcards.dataset +'/' + wildcards.iterset +'/kmers/{kmer}/predictions.probabilistic_gen.tsv',kmer=kmer_lengths),
		'distance_model': expand('data/output/' + wildcards.dataset +'/' + wildcards.iterset +'/kmers/{kmer}/predictions.euclidean.tsv',kmer=kmer_lengths),
		'probabilistic_model': expand('data/output/' + wildcards.dataset +'/' + wildcards.iterset + '/kmers/{kmer}/predictions.probabilistic_cov.tsv',kmer=kmer_lengths),
		# if above:
		'plot_top3_fit': expand('data/output/' + wildcards.dataset +'/' + wildcards.iterset + '/kmers/{kmer}/{id}_top3fit.svg',kmer=kmer_lengths,id=inputIDs),
		'kmer_stats_analysis': expand('data/output/' + wildcards.dataset + '/' + wildcards.iterset +'/kmers/{kmer}/{id}/spaTypesGroundTruthVennDia.svg',kmer=kmer_lengths,id=inputIDs)
	}
	return [item for k in possible_params.keys() if config[k] for item in possible_params[k]]

def use_itersets():
	if config['probabilistic_model'] and config['itersets']:
		return config['itersets']
	return ['O']

rule all:
	input:
		run_datasets = expand('data/output/{dataset}_summary.md', dataset=config['datasets'].keys())

rule run_dataset:
	input:
		general = get_general_inputs,
		summarys = expand('data/auxiliary/{dataset}/{iterset}_summary.md', iterset=use_itersets(), allow_missing=True)
	output:
		summary = 'data/output/{dataset}_summary.md'
	#  TODO create summary
	shell:
		'touch {output.out}'

rule run_iterset:
	input:
		get_iterset_inputs
	output:
		out = 'data/auxiliary/{dataset}/{iterset}_summary.md'
	# TODO create summary
	shell:
		'touch {output.out}'

##### load rules #####
include: "rules/assembly.smk"
include: "rules/shared.smk"
include: "rules/kmerApproach.smk"
include: "rules/coverageBased.smk"
include: "rules/probabilistic.smk"
include: "rules/euclidean.smk"