def test_epiLION_Converter_bad_input(self):
logger.debug('test bad input...')
result = convLION.main(self.fail_input_params)
if result is False:
logger.debug('test bad input... PASSED')
else:
raise Exception('test bad input... Failed')
def test_epiLION_Converter_good_input(self):
logger.debug('test sample data...')
result = convLION.main(self.pass_params)
if result is True:
logger.debug('test sample data... PASSED')
else:
raise Exception('test sample data... Failed')
def test_epiLION_Converter_help():
logger.debug('test help...')
result = convLION.main(['-h'])
if result is False:
logger.debug('test help... PASSED')
else:
raise Exception('test help... Failed')
def test_epiLION_Converter_bad_params():
logger.debug('test bad params...')
result = convLION.main(['-test'])
if result is False:
logger.debug('test bad parameter... PASSED')
else:
raise Exception('test bad parameter... Failed')
def setUp(self):
logger.debug('SETUP TESTS...')
in_file_lst = [
r'../test/TestInput/test_crosscheck.xlsx',
r'test/TestInput/test_crosscheck.xlsx',
r'../TestInput/test_crosscheck.xlsx',
r'TestInput/test_crosscheck.xlsx',
]
in_file = ''
for f in in_file_lst:
if os.path.isfile(f):
in_file = os.path.abspath(f)
break
logger.info(f'Input file {in_file}')
bad_in_file = r'test/TestInput/test_crosscheck_x.txt'
out_folder_lst = [
r'../test/TestOutput/',
r'test/TestOutput/',
r'../TestOutput/',
r'TestOutput/',
]
out_folder = ''
for p in out_folder_lst:
if os.path.isdir(p):
out_folder = os.path.abspath(p)
break
out_file = os.path.join(out_folder, 'test_crosscheck_output.csv')
logger.info(f'Out put file will be: {out_file}')
self.pass_params = ['-i', in_file, '-o', out_file]
self.fail_input_params = ['-i', bad_in_file, '-o', out_file]
def convert_table(self, input_file: str, output_file: str):
abbr_dct = self.load_file(input_file)
epilion_dct = {}
for k in abbr_dct:
tmp_abbr_lst = abbr_dct[k]
epilion_lst = []
for abbr in tmp_abbr_lst:
abbr = re.sub(r' ', '', abbr)
epilion_abbr = ''
# Try to parse to software generated abbreviations
abbr_epilion_lst = []
if self.abbr_parser.is_lpptiger(abbr):
epilion_lpptiger_abbr = self.abbr_parser.parse_lpptiger(
abbr)
logger.debug(
f'{k} - LPPtiger: {abbr} -> {epilion_lpptiger_abbr}')
abbr_epilion_lst.append(epilion_lpptiger_abbr)
if self.abbr_parser.is_lipostar(abbr)[0]:
epilion_lipostar_abbr = self.abbr_parser.parse_lipostar(
abbr)
logger.debug(
f'{k} - Lipostar: {abbr} -> {epilion_lipostar_abbr}')
abbr_epilion_lst.append(epilion_lipostar_abbr)
if self.abbr_parser.is_lipidmaps(abbr)[0]:
epilion_lipidmaps_abbr = self.abbr_parser.parse_lipidmaps(
abbr)
logger.debug(
f'{k} - LIPIDMAPS: {abbr} -> {epilion_lipidmaps_abbr}')
abbr_epilion_lst.append(epilion_lipidmaps_abbr)
if self.abbr_parser.is_legacy(abbr)[0]:
# logger.info(f'Try to parse in Legacy mode for {k} - {abbr}')
epilion_legacy_abbr = self.abbr_parser.parse_legacy(abbr)
logger.debug(
f'{k} - Legacy: {abbr} -> {epilion_legacy_abbr}')
abbr_epilion_lst.append(epilion_legacy_abbr)
if abbr_epilion_lst:
epilion_abbr = sorted(abbr_epilion_lst, key=len)[-1]
else:
epilion_abbr = ''
if not epilion_abbr:
logger.warning(f'! Can NOT convert Column {k} - {abbr}')
epilion_lst.append(epilion_abbr)
# logger.info(epilion_lst)
epilion_dct[k] = epilion_lst
# logger.info(epilion_dct)
out_df = pd.DataFrame.from_dict(epilion_dct, orient='index').T
if output_file.endswith('.xlsx'):
out_df.to_excel(output_file, index=False)
elif output_file.endswith('.csv'):
out_df.to_csv(output_file, index=False)
else:
out_df.to_excel(output_file + '.xlsx', index=False)
def convert_abbr(self, abbr: str) -> str:
abbr = re.sub(r' ', '', abbr)
# Try to parse to software generated abbreviations
abbr_epilion_lst = []
if self.abbr_parser.is_lpptiger(abbr):
epilion_lpptiger_abbr = self.abbr_parser.parse_lpptiger(abbr)
logger.debug(f'LPPtiger: {abbr} -> {epilion_lpptiger_abbr}')
abbr_epilion_lst.append(epilion_lpptiger_abbr)
if self.abbr_parser.is_lipostar(abbr)[0]:
epilion_lipostar_abbr = self.abbr_parser.parse_lipostar(abbr)
logger.debug(f'Lipostar: {abbr} -> {epilion_lipostar_abbr}')
abbr_epilion_lst.append(epilion_lipostar_abbr)
if self.abbr_parser.is_lipidmaps(abbr)[0]:
epilion_lipidmaps_abbr = self.abbr_parser.parse_lipidmaps(abbr)
logger.debug(f'LIPIDMAPS: {abbr} -> {epilion_lipidmaps_abbr}')
abbr_epilion_lst.append(epilion_lipidmaps_abbr)
if self.abbr_parser.is_legacy(abbr)[0]:
# logger.info(f'Try to parse in Legacy mode for {k} - {abbr}')
epilion_legacy_abbr = self.abbr_parser.parse_legacy(abbr)
logger.debug(f'Legacy: {abbr} -> {epilion_legacy_abbr}')
abbr_epilion_lst.append(epilion_legacy_abbr)
if abbr_epilion_lst:
epilion_abbr = sorted(abbr_epilion_lst, key=len)[-1]
else:
epilion_abbr = ''
if not epilion_abbr:
logger.warning(f'! Can NOT convert {abbr}')
return epilion_abbr
def decode_mod(self, abbr: str) -> list:
fin_mod_info_lst = []
mod_info_lst = self.find_all(abbr, 'mod')
for mod_dct in mod_info_lst:
if mod_dct['SITE_INFO']:
mod_dct['SITE'] = self.decode_site(mod_dct['SITE_INFO'])
else:
mod_dct['SITE'] = None
fin_mod_info_lst.append(mod_dct)
logger.debug('MOD info:')
logger.debug(fin_mod_info_lst)
return fin_mod_info_lst
def main(argv):
"""
:param argv: -i <input epiLION abbreviation file in .txt format>
"""
in_file = ''
out_file = ''
is_output = False
try:
opts, args = getopt.getopt(argv, "hi:o:", ["infile=", "outfile="])
logger.debug(f'User input: {opts}, {args}')
except getopt.GetoptError:
logger.info('epiLIONConverter.py -i <input_file> -o <output_file>')
return is_output
for opt, arg in opts:
if opt == '-h':
logger.info('epiLIONConverter.py -i <input_file> -o <output_file>')
return is_output
elif opt in ("-i", "--infile"):
in_file = arg
elif opt in ("-o", "--outfile"):
out_file = arg
if os.path.isfile(in_file):
logger.info(f'Load input file: {in_file}')
converter = Converter(abbr_cfg_path)
converter.convert_table(in_file, out_file)
logger.info(f'Save output file: {out_file}')
logger.info('FINISHED')
is_output = True
logger.info(f'is_output {is_output}')
else:
logger.error(f'Can NOT open input file:')
logger.error(in_file)
logger.error('!!! FAILED to PROCESS !!!')
return is_output
def main(argv):
"""
:param argv: -i <input epiLION abbreviation file in .txt format>
"""
in_file = ''
out_file = ''
is_output = False
try:
opts, args = getopt.getopt(argv, "hi:o:", ["infile=", "outfile="])
logger.debug(f'User input: {opts}, {args}')
except getopt.GetoptError:
logger.info('epiLION.py -i <input_file> -o <output_file>')
return is_output
for opt, arg in opts:
if opt == '-h':
logger.info('epiLION.py -i <input_file> -o <output_file>')
return is_output
elif opt in ("-i", "--infile"):
in_file = arg
elif opt in ("-o", "--outfile"):
out_file = arg
if os.path.isfile(in_file):
logger.info(f'Load input file: {in_file}')
with open(in_file, 'r') as in_obj:
in_lst = in_obj.readlines()
epilion2sdf(in_lst, out_file)
logger.info(f'Save output file: {out_file}')
logger.info('FINISHED')
is_output = True
else:
logger.error(f'Can NOT open input file:')
logger.error(in_file)
logger.error('!!! FAILED to PROCESS !!!')
return is_output
def decode_fa(self, abbr: str) -> dict:
fa_info_dct = {}
if abbr:
logger.debug(f'FA_ABBR: {abbr}')
fa_match = re.match(self.fa_rgx, abbr)
if fa_match:
fa_info_dct = fa_match.groupdict()
else:
logger.warning('FA abbreviation is None!')
mod_info = fa_info_dct['MOD_INFO']
if mod_info and isinstance(mod_info, str):
mod_info = mod_info.strip('[]')
logger.debug(mod_info)
mod_info_dct = self.mod_parser.decode_mod(mod_info)
else:
mod_info_dct = {}
fa_info_dct['MOD'] = mod_info_dct
return fa_info_dct
def tearDown(self):
logger.debug('TEST END!')
