# -*- coding: utf-8 -*-
#
################################################################################
from configparser import ConfigParser, ExtendedInterpolation
import re
import myutils
parser = ConfigParser(interpolation=ExtendedInterpolation(),
strict=True,
allow_no_value=False)
parser.SECTCRE = re.compile(r"\[ *(?P<header>[^]]+?) *\]")
with open('config1.cfg', encoding='utf-8') as f:
parser.read_file(f)
myutils.showconfig1(parser)
# -*- coding: utf-8 -*-
#
################################################################################
from configparser import ConfigParser, ExtendedInterpolation
import re
import myutils
parser = ConfigParser(interpolation=ExtendedInterpolation(), strict=True)
parser.SECTCRE = re.compile(r"\[ *(?P<header>[^]]+?) *\]")
with open('config1.cfg', encoding='utf-8') as f:
parser.read_file(f)
myutils.showconfig1(parser)
basename,
splitext,
dirname,
expanduser)
from glob import glob
import sys
from types import ModuleType
# print('__name__ is {}'.format(__name__))
# print('__file__ is {}'.format(abspath(__file__)))
# print('os.path.dirname is {}'.format(dirname(abspath(__file__))))
print('home folder is {}'.format(expanduser('~')))
pconfig = ConfigParser(interpolation=ExtendedInterpolation())
pconfig.SECTCRE = re.compile(r"\[ *(?P<header>[^]]+?) *\]")
pconfig.read('config1.cfg', encoding='utf-8')
############################
# pretty output
#
# column widths
columns = (20, 20, 50)
header_line = '|'.join(['{:^%s}' % i for i in columns])
data_line = '|'.join(['{:<%s}' % i for i in columns])
header = header_line.format('Section', 'Option', 'Value')
print('-' * len(header))
print(header)
print('-' * len(header))
def ss_file_parse(file_path):
cfg = ConfigParser(delimiters=('='),
allow_no_value=True,
empty_lines_in_values=True)
cfg.optionxform = str
cfg.SECTCRE = re.compile(r'\[\s*(?P<header>[^]]+?)\s*\]')
try:
cfg.read(file_path)
except MissingSectionHeaderError:
Log.err(
'Missing section header(s) in the provided "Search Strategies" file:',
file_path)
exit(1)
required_options = set(('organelle', 'min_query_length',
'max_query_length', 'max_query_identity',
'min_target_orf_length', 'max_target_orf_length'))
ret_dict = OrderedDict()
sections = cfg.sections()
for s in sections:
o = cfg.options(s)
if not required_options <= set(o):
missing = required_options - (required_options & set(o))
Log.err(
'Missing required option(s):' + ', '.join(missing) +
'for search strategy', s)
exit(1)
organelle = cfg[s]['organelle']
if organelle not in ('nucleus', 'plastid', 'mitochondrion'):
Log.err('Organelle "' + organelle + '" should be one of:',
'nucleus, plastid, or mitochondrion.')
exit(1)
min_query_length = int(cfg[s]['min_query_length'])
max_query_length = int(cfg[s]['max_query_length'])
max_query_identity = float(cfg[s]['max_query_identity'])
min_target_orf_length = int(cfg[s]['min_target_orf_length'])
max_target_orf_length = int(cfg[s]['max_target_orf_length'])
evalue = None
max_hsps = None
qcov_hsp_perc = None
best_hit_overhang = None
best_hit_score_edge = None
max_target_seqs = None
pfam_families = None
ncbi_accessions_aa = None
entrez_search_queries = None
fasta_files_aa = None
if cfg.has_option(s, 'evalue'):
evalue = float(cfg[s]['evalue'])
if cfg.has_option(s, 'max_hsps'):
max_hsps = int(cfg[s]['max_hsps'])
if cfg.has_option(s, 'qcov_hsp_perc'):
qcov_hsp_perc = float(cfg[s]['qcov_hsp_perc'])
if cfg.has_option(s, 'best_hit_overhang'):
best_hit_overhang = float(cfg[s]['best_hit_overhang'])
if cfg.has_option(s, 'best_hit_score_edge'):
best_hit_score_edge = float(cfg[s]['best_hit_score_edge'])
if cfg.has_option(s, 'max_target_seqs'):
max_target_seqs = int(cfg[s]['max_target_seqs'])
if cfg.has_option(s, 'pfam_families'):
pfam_families = str(cfg[s]['pfam_families'])
pfam_families = set(pfam_families.split('\n')) - \
set(('', 'None'))
pfam_families = _parse_pfam(pfam_entries=pfam_families,
config_file_path=file_path)
pfam_families = sorted(pfam_families)
if cfg.has_option(s, 'ncbi_accessions_aa'):
ncbi_accessions_aa = str(cfg[s]['ncbi_accessions_aa'])
ncbi_accessions_aa = sorted(
set(ncbi_accessions_aa.split('\n')) - set(('', 'None')))
if cfg.has_option(s, 'entrez_search_queries'):
entrez_search_queries = str(cfg[s]['entrez_search_queries'])
entrez_search_queries = sorted(
set(entrez_search_queries.split('\n')) - set(('', 'None')))
if cfg.has_option(s, 'fasta_files_aa'):
fasta_files_aa = str(cfg[s]['fasta_files_aa'])
fasta_files_aa = set(fasta_files_aa.split('\n')) - \
set(('', 'None'))
fasta_files_aa = [abspath(expanduser(x)) for x in fasta_files_aa]
fasta_files_aa = sorted(fasta_files_aa)
section_dict = OrderedDict({
'organelle': organelle,
'min_query_length': min_query_length,
'max_query_length': max_query_length,
'max_query_identity': max_query_identity,
'min_target_orf_length': min_target_orf_length,
'max_target_orf_length': max_target_orf_length,
'blast_2_evalue': evalue,
'blast_2_max_hsps': max_hsps,
'blast_2_qcov_hsp_perc': qcov_hsp_perc,
'blast_2_best_hit_overhang': best_hit_overhang,
'blast_2_best_hit_score_edge': best_hit_score_edge,
'blast_2_max_target_seqs': max_target_seqs,
'pfam_families': pfam_families,
'ncbi_accessions_aa': ncbi_accessions_aa,
'entrez_search_queries': entrez_search_queries,
'fasta_files_aa': fasta_files_aa
})
ret_dict[s] = section_dict
return ret_dict
