#!/usr/bin/env python

'''

John Pellman, Chris Gorgolewski 2015/2016

--------------------------------------------------------------------------------------------

This script will take NifTI data stored locally and tracked in the database and re-organize

it in BIDS format.

Usage: Type -h to see usage.

'''

import os, sys, shutil

import re

from glob import glob

import argparse

from datetime import datetime

import csv

import yaml

import sqlite3

from nibabel.nicom import csareader

import nibabel as nib

import numpy as np

import dicom

import json

from tsv import *

from utils import mkdir_p, setup_logger

import logging

def get_phase_encode(dcm_file):

return ret_dirs[max_index][dcm_vec[max_index] > 0]

def get_slice_direction(dcm_file):

return ret_dirs[max_index][norm[max_index] > 0]

def get_effective_echo_spacing(dcm_file):

dcmobj = dicom.read_file(dcm_file)

return 1/(dcmobj[("0019", "1028")].value * dcmobj.AcquisitionMatrix[0])

def get_total_readout_time(dcm_file):

dcmobj = dicom.read_file(dcm_file)

return 1/(dcmobj[("0019", "1028")].value)

def nifti_sanity_check(nifti_path,bids_path,bids_log):

return sane

# mcverter adds a tiny amount of rounding error that don't want.

def nifti_copy(nifti_path,dicom_path,bids_path,bids_log):

nib.save(img,bids_path)

def compare_jsons(json_a,json_b):

return (not False in comp_results)

def extract_dicom_task_metadata(dicom_file, output_json, toplevel_json='', extra_fields={}):

sort_keys=True, indent=4, separators=(',', ': '))

def extract_dwi_metadata(dicom_file, output_json, toplevel_json='', extra_fields={}):

sort_keys=True, indent=4, separators=(',', ': '))

def extract_fmap_phasediff_metadata(dicom_file_e1, dicom_file_e2, output_json, toplevel_json='', extra_fields={}):

sort_keys=True, indent=4, separators=(',', ': '))

def img_to_bids(db_file,output_dir,bids_log,bids_nifti_sanity_log,series,ursi,study_name,anonmap={}):

conn.close()

def beh_to_bids(beh_warehouse, output_dir, bids_log, ursi, study_name, anonmap={}):

bids_log.info('='*50)

def anonymize_existing(bids_warehouse,anonmap,bids_log):

bids_log.info('%s is already anonymized' % nonanon_file)

if __name__ == '__main__':

parser = argparse.ArgumentParser(description=__doc__)

# Parameters for all functions

parser.add_argument('-b', '--bids_warehouse', required=True,

help='Path to the BIDS warehouse, where all the BIDSified data will be stored by release/anonymization status.')

parser.add_argument('-l', '--log_dir', required=True,

help='Path to the logs directory.')

# Parameters for both img_to_bids and beh_to_bids

parser.add_argument('-u', '--ursis', required=False,

help='A full path to a CSV file with the URSI in one column and the study name/visit (e.g., CLG4) in the second column.')

parser.add_argument('-s', '--series', required=False,

help='A YAML file containing the names of series and what their task names should be changed to (as well as their type in BIDS notation (e.g., anat, func).')

parser.add_argument('-a', '--anon_ursi', required=False,

help='A two-column CSV file with anonymous IDs in the first column and URSIs in the second column. Used to anonymize participant labels. If this is included the script will only generate the anonymized warehouse. Run again without this flag for the non-anonymized warehouse.')

# For img_to_bids only

parser.add_argument('-d', '--db_file', required=False,

help='Path to the database.')

# For beh_to_bids only

parser.add_argument('-t', '--beh_warehouse', required=False,

help='Path to the behavioral data warehouse, where all the behavioral data that needs to be BIDSified resides.')

# For participants.tsv and session tsvs.

parser.add_argument('-p', '--phenotype_file', required=False,

help='A csv containing phenotypic info for the release. Used to create participants.tsv')

# For copying inherited files.

parser.add_argument('-i', '--inherited', required=False,

help='A path to a directory containing task metadata in JSON format, as well as other files to be included at the top level of the BIDS directory (such as the dataset description). Some of this data will be inherited by all scans.')

args = parser.parse_args()

bids_warehouse = os.path.abspath(args.bids_warehouse)

log_dir = os.path.abspath(args.log_dir)

# Log errors

now = datetime.now()

bids_logs=os.path.join(log_dir,'bids_logs')

log_path=os.path.join(bids_logs,str(now.year),str(now.month),str(now.day))

if not os.path.exists(log_path):

mkdir_p(log_path)

bids_nifti_sanity_log=setup_logger('bids_nifti_sanity',os.path.join(log_path,'bids_nifti_sanity.log'), logging.INFO)

# Read anonymization key in as dictionary and define output directory.

anonmap={}

if args.anon_ursi:

with open(os.path.abspath(args.anon_ursi),'rU') as map_file:

csvreader = csv.reader(map_file,delimiter=',')

for row in csvreader:

anonmap[row[1]]=row[0]

output_dir=os.path.join(bids_warehouse,'Anonymized')

else:

output_dir=os.path.join(bids_warehouse,'Non-anonymized')

mkdir_p(output_dir)

if args.inherited:

bids_inherit_log=setup_logger('bids_inherit',os.path.join(log_path,'bids_inherit_jsons.log'), logging.INFO)

inherited = os.path.abspath(args.inherited)

inherit_jsons(output_dir,bids_inherit_log,inherited)

for toplevel in glob(os.path.join(inherited,'*')):

try:

shutil.copy(toplevel, os.path.join(output_dir,os.path.basename(toplevel)))

except:

bids_log.info('Unable to copy %s to %s.' % (toplevel, output_dir))

# Open the URSI csv, iterate through each row and BIDSify behavioral data, imaging data, or both.

if args.ursis and args.series and (args.db_file or args.beh_warehouse):

ursis = os.path.abspath(args.ursis)

series = os.path.abspath(args.series)

if args.db_file:

db_file = os.path.abspath(args.db_file)

if args.beh_warehouse:

beh_warehouse = os.path.abspath(args.beh_warehouse)

bids_csv_log=setup_logger('bids_csv',os.path.join(log_path,'bids_csv.log'), logging.INFO)

with open(ursis,'rU') as ursi_csv:

ursi_study = csv.reader(ursi_csv,delimiter=',')

for row in ursi_study:

ursi,study_name=row

if not ursi or not study_name:

bids_csv_log.info('URSI or study field blank in URSI csv: %s,%s' % (ursi,study_name))

bids_csv_log.info('This row of the URSI csv will not be BIDsified. Fix and re-run.')

continue

if args.db_file:

bids_nifti_log=setup_logger('bids_nifti',os.path.join(log_path,'bids_nifti.log'), logging.INFO)

if anonmap:

img_to_bids(db_file,output_dir,bids_nifti_log,bids_nifti_sanity_log,series,ursi,study_name,anonmap)

else:

img_to_bids(db_file,output_dir,bids_nifti_log,bids_nifti_sanity_log,series,ursi,study_name)

if args.beh_warehouse:

bids_beh_log=setup_logger('bids_beh',os.path.join(log_path,'bids_behavioral.log'), logging.INFO)

if anonmap:

beh_to_bids(beh_warehouse, output_dir, bids_beh_log, ursi, study_name,anonmap)

else:

beh_to_bids(beh_warehouse, output_dir, bids_beh_log, ursi, study_name)

# TODO Fix odd bug where anonymization on the fly produces a participants.tsv with no headers.

if args.phenotype_file and args.ursis:

bids_phenotype_log=setup_logger('bids_phenotype_tsvs',os.path.join(log_path,'bids_phenotype_tsv.log'), logging.INFO)

ursis = os.path.abspath(args.ursis)

phenotype_file = os.path.abspath(args.phenotype_file)

bids_phenotype_log.info('Generating participants.tsv and session tsvs using %s' % phenotype_file)

phenotype_dict=gen_phenotype_dict(phenotype_file)

with open(ursis,'rU') as ursi_csv:

ursi_study = csv.reader(ursi_csv,delimiter=',')

for row in ursi_study:

ursi,study_name=row

if anonmap:

sessions_tsv(output_dir,ursi,study_name,phenotype_dict,anonmap)

participants_tsv(output_dir,ursis,phenotype_dict,anonmap)

else:

sessions_tsv(output_dir,ursi,study_name,phenotype_dict)

participants_tsv(output_dir,ursi,phenotype_dict)

if anonmap and not (args.phenotype_file and args.ursis) and not (args.ursis and args.series and (args.db_file or args.beh_warehouse)):

bids_anon_log=setup_logger('bids_anon',os.path.join(log_path,'bids_anon.log'), logging.INFO)

anonymize_existing(bids_warehouse,anonmap,bids_anon_log)