diff --git a/src/parser/parser.py b/src/parser/parser.py
index ba5436ec0c5e29f77571a328c87333dd0ac19390..fce83032190d92810f3e38014d46d29f16fb290c 100755
--- a/src/parser/parser.py
+++ b/src/parser/parser.py
@@ -5,7 +5,7 @@ Created on 27 dec. 2011
@author: Bertrand Néron
"""
-
+from __future__ import print_function
from collections import namedtuple
from couchdbkit.client import Server
from couchdbkit.exceptions import ResourceNotFound
@@ -14,7 +14,7 @@ from restkit import Resource, BasicAuth
import restkit.errors
-def replicon_parser( replicon_data ):
+def replicon_parser(replicon_data):
"""
parse a file containing the informations about replicons
@param replicon_data: the path of replicon information file
@@ -23,27 +23,31 @@ def replicon_parser( replicon_data ):
@rtype: dict
"""
replicon_db = {}
- Replicon_info = namedtuple('Replicon_info', 'name, taxid, strain, taxonomy, type')
- with open( replicon_data , 'r' ) as replicon_file :
+ Replicon_info = namedtuple('Replicon_info', ('name', 'taxid', 'strain', 'taxonomy', 'type'))
+ with open(replicon_data, 'r') as replicon_file:
for line in replicon_file:
if line[0] != '#':
line = line.strip()
- fields = line.split( '\t')
+ fields = line.split('\t')
if fields[0] in replicon_db:
- raise KeyError( "duplicate replicon:" + fields[0])
+ raise KeyError("duplicate replicon:" + fields[0])
else:
try:
- replicon_db[ fields[0] ] = Replicon_info( fields[0] , int(fields[1]) , fields[2] , fields[3].split('; ') , fields[4])
- except Exception, err:
- raise Exception( "Error during parsing line :"+line )
- #remove ending dot or semi-colon from the last term of taxonnomy
- if( replicon_db[ fields[0] ].taxonomy[-1].endswith('.') or replicon_db[ fields[0] ].taxonomy[-1].endswith(';')):
- replicon_db[ fields[0] ].taxonomy[-1] = replicon_db[ fields[0] ].taxonomy[-1][:-1]
+ replicon_db[fields[0]] = Replicon_info(fields[0],
+ int(fields[1]),
+ fields[2],
+ fields[3].split('; '),
+ fields[4])
+ except Exception as err:
+ raise Exception("Error during parsing line: {0}\n{1}".format(line, err))
+ # remove ending dot or semi-colon from the last term of taxonomy
+ tax_last_char = replicon_db[fields[0]].taxonomy[-1]
+ if tax_last_char.endswith('.') or tax_last_char.endswith(';'):
+ replicon_db[fields[0]].taxonomy[-1] = replicon_db[fields[0]].taxonomy[-1][:-1]
return replicon_db
-
-def system_parser( system_data ):
+def system_parser(system_data):
"""
@param system_data: the path of secretion system information file
@type system_data: string
@@ -51,44 +55,46 @@ def system_parser( system_data ):
@rtype: dict
"""
system_db = {}
- System_info = namedtuple('System_info', 'code, T3SS_family, replicon, genes' )
- Gene = namedtuple( 'Gene', 'code, id, protein_length, strand, begin, end, match, full_score, e_value, best_domain_score, best_domain_evalue, c_value, coverage_profile, match_begin, match_end, name, description')
+ System_info = namedtuple('System_info', 'code, T3SS_family, replicon, genes')
+ Gene = namedtuple('Gene', ('code', 'id', 'protein_length', 'strand', 'begin', 'end', 'match', 'full_score',
+ 'e_value', 'best_domain_score', 'best_domain_evalue', 'c_value', 'coverage_profile',
+ 'match_begin', 'match_end', 'name', 'description'))
- with open( system_data , 'r' ) as system_file :
+ with open(system_data, 'r') as system_file:
for line in system_file:
if line[0] != '#':
line = line.strip()
- fields = line.split( '\t')
+ fields = line.split('\t')
if fields[0] in system_db:
- raise KeyError( "duplicate replicon:" + fields[0])
+ raise KeyError("duplicate replicon:" + fields[0])
else:
- gene = Gene( fields[0],# code
- fields[1],# id
- int(fields[2]),# protein_length
- fields[3] if fields[3] != '-' else None,# strand
- int(fields[4]) if fields[4] != '-' else None ,# begin
- int(fields[5]) if fields[5] != '-' else None,# end
- fields[6] if fields[6] != '-' else None,# match
- float(fields[7].replace( ',' , '.')) if fields[7] != '-' else None , # full_score
- float(fields[8].replace( ',' , '.')) if fields[8] != '-' else None , # e_value
- float(fields[9].replace( ',' , '.')) if fields[9] != '-' else None , # best_domain_score
- float(fields[10].replace( ',' , '.')) if fields[10] != '-' else None ,# best_domain_evalue
- float(fields[11].replace( ',' , '.')) if fields[11] != '-' else None ,# c_value
- float(fields[12].replace( ',' , '.')) if fields[12] != '-' else None ,# coverage_profile
- int(fields[13]) if fields[13] != '-' else None ,# match_begin
- int(fields[14]) if fields[14] != '-' else None ,# match_end
- fields[18] if fields[18] else None, # name
- fields[19] if fields[19] else None, # description
- )
+ gene = Gene(fields[0], # code
+ fields[1], # id
+ int(fields[2]), # protein_length
+ fields[3] if fields[3] != '-' else None, # strand
+ int(fields[4]) if fields[4] != '-' else None, # begin
+ int(fields[5]) if fields[5] != '-' else None, # end
+ fields[6] if fields[6] != '-' else None, # match
+ float(fields[7].replace(',', '.')) if fields[7] != '-' else None, # full_score
+ float(fields[8].replace(',', '.')) if fields[8] != '-' else None, # e_value
+ float(fields[9].replace(',', '.')) if fields[9] != '-' else None, # best_domain_score
+ float(fields[10].replace(',', '.')) if fields[10] != '-' else None, # best_domain_evalue
+ float(fields[11].replace(',', '.')) if fields[11] != '-' else None, # c_value
+ float(fields[12].replace(',', '.')) if fields[12] != '-' else None, # coverage_profile
+ int(fields[13]) if fields[13] != '-' else None, # match_begin
+ int(fields[14]) if fields[14] != '-' else None, # match_end
+ fields[18] if fields[18] else None, # name
+ fields[19] if fields[19] else None, # description
+ )
if fields[16] in system_db:
- if gene.code in system_db[ fields[16] ]:
- raise KeyError( "duplicate gene:" + fields[16])
+ if gene.code in system_db[fields[16]]:
+ raise KeyError("duplicate gene:" + fields[16])
else:
- #append this gene to System_info genes
- system_db[ fields[16] ].genes[ gene.code ] = gene
+ # append this gene to System_info genes
+ system_db[fields[16]].genes[gene.code] = gene
else:
- #create a new Sysem_info entry
- system_db[ fields[16] ] = System_info( fields[16] , fields[17] , fields[15] , genes = { gene.code : gene } )
+ # create a new System_info entry
+ system_db[fields[16]] = System_info(fields[16], fields[17], fields[15], genes={gene.code: gene})
return system_db
@@ -96,17 +102,17 @@ from couchdbkit.schema import Document
from couchdbkit.schema.properties import *
-class SecretionSystem( Document ):
+class SecretionSystem(Document):
"""
a representation of a secretion System to be use with couchdb
"""
- code = StringProperty( required=True )
+ code = StringProperty(required=True)
T3SS_family = StringProperty()
- replicon = DictProperty()
- genes = ListProperty()
+ replicon = DictProperty()
+ genes = ListProperty()
-def fill_db( server_uri, db_name, user, passwd, replicon_db , system_db , force_update = False):
+def fill_db(server_uri, db_name, user, passwd, replicon_db, system_db, force_update=False):
"""
@param server_uri: the url of the couchdb server (with port)
@type server_uri: string
@@ -119,124 +125,117 @@ def fill_db( server_uri, db_name, user, passwd, replicon_db , system_db , force_
@param force_update: if true force the entry to be updated even if the _rev number is not provided
@type force_update: boolean
"""
- auth = BasicAuth(user , passwd )
- resource = CouchdbResource( server_uri , filters=[auth])
- server = Server( resource_instance= resource )
- secreton_db = server.get_or_create_db( db_name )
+ auth = BasicAuth(user, passwd )
+ resource = CouchdbResource(server_uri, filters=[auth])
+ server = Server(resource_instance=resource)
+ secreton_db = server.get_or_create_db(db_name)
system_codes = system_db.keys()
system_codes.sort()
for syst_code in system_codes:
system = system_db[syst_code]
- replicon = replicon_db[ system.replicon ]
+ replicon = replicon_db[system.replicon]
secretion_system = SecretionSystem()
- secretion_system._id = system.code
+ secretion_system._id = system.code
secretion_system.code = system.code
secretion_system.T3SS_family = system.T3SS_family
- secretion_system.replicon = { 'name' : replicon.name ,
- 'taxid' : replicon.taxid,
- 'strain' : replicon.strain,
- 'taxonomy' : replicon.taxonomy,
- 'type' : replicon.type
+ secretion_system.replicon = {'name': replicon.name,
+ 'taxid': replicon.taxid,
+ 'strain': replicon.strain,
+ 'taxonomy': replicon.taxonomy,
+ 'type': replicon.type
}
genes_code = system.genes.keys()
genes_code.sort()
genes = []
for gene_code in genes_code:
- gene = system.genes[ gene_code ]
+ gene = system.genes[gene_code]
g = {}
- for field in gene._fields:
- if getattr(gene , field ) is not None:
- g[ field ]= getattr( gene , field )
- genes.append( g )
+ for field in gene._fields:
+ if getattr(gene, field) is not None:
+ g[field] = getattr(gene, field)
+ genes.append(g)
secretion_system.genes = genes
- secreton_db.save_doc( secretion_system , force_update= force_update )
+ secreton_db.save_doc(secretion_system, force_update=force_update)
if __name__ == '__main__':
- from optparse import OptionParser , OptionGroup
+ import argparse
import sys
import getpass
def get_credentials():
- user = raw_input('login: ')
- password = getpass.getpass('password: ')
- return user, password
+ user = raw_input('login: ')
+ password = getpass.getpass('password: ')
+ return user, password
- usage="""
+ usage = """
%prog [options]
parse a file containing replicon informations and a file containing system informations
and fill a couchDB data base with these informations
"""
- parser = OptionParser( usage= usage )
- server_opt = OptionGroup(parser, "Server Options")
- server_opt.add_option( "-S" , "--server" ,
- action = "store",
- type= "string" ,
- dest = "server_url" ,
- help = "the url of the couchDB server (with the port)")
- server_opt.add_option( "-d" , "--database" ,
- action = "store",
- type= "string" ,
- dest = "db_name" ,
- help = "the name of the data base")
- parser.add_option_group( server_opt )
-
- parsing_opt = OptionGroup(parser, "Parsing Options")
- parsing_opt.add_option( "-r" , "--replicon" ,
- action = "store",
- type= "string" ,
- dest = "replicon_path" ,
- help = "the path to the replicon file to parse")
- parsing_opt.add_option( "-s" , "--system" ,
- action = "store",
- type= "string" ,
- dest = "system_path" ,
- help = "the path to the system secretion file to parse")
- parsing_opt.add_option( "-f" , "--force_update" ,
- action= "store_true",
- dest = "force_update" ,
- default = False,
- help = "")
- parser.add_option_group( parsing_opt )
-
+ parser = argparse.ArgumentParser(usage=usage)
+ server_opt = parser.add_argument_group(title="Server Options")
+ server_opt.add_argument("-S", "--server",
+ action="store",
+ type="string",
+ dest="server_url",
+ help="the url of the couchDB server (with the port)")
+ server_opt.add_argument("-d", "--database",
+ action="store",
+ type="string",
+ dest="db_name",
+ help="the name of the data base")
+ parsing_opt = parser.add_argument_group(title="Parsing Options")
+ parsing_opt.add_argument("-r", "--replicon",
+ action="store",
+ type="string",
+ dest="replicon_path",
+ help="the path to the replicon file to parse")
+ parsing_opt.add_argument("-s", "--system",
+ action="store",
+ type="string",
+ dest="system_path",
+ help="the path to the system secretion file to parse")
+ parsing_opt.add_argument("-f", "--force_update",
+ action="store_true",
+ dest="force_update",
+ default=False,
+ help="")
options, args = parser.parse_args()
if not options.server_url:
- print >> sys.stderr , "You must specify a server url"
+ print("You must specify a server url", file=sys.stderr)
parser.print_help(sys.stderr)
sys.exit(1)
if not options.db_name:
- print >> sys.stderr , "You must specify a data base name"
+ print("You must specify a data base name", file=sys.stderr)
parser.print_help(sys.stderr)
sys.exit(1)
if not options.replicon_path:
- print >> sys.stderr , "You must specify the path to the replicon information file"
+ print("You must specify the path to the replicon information file", file=sys.stderr)
parser.print_help(sys.stderr)
sys.exit(1)
if not options.system_path:
- print >> sys.stderr , "You must specify the path to the secretion system information file"
+ print("You must specify the path to the secretion system information file", file=sys.stderr)
parser.print_help(sys.stderr)
sys.exit(1)
-
- replicon_db = replicon_parser( options.replicon_path )
- system_db = system_parser( options.system_path )
+ replicon_db = replicon_parser(options.replicon_path)
+ system_db = system_parser(options.system_path)
try_again = 0
while True:
user, password = get_credentials()
try:
- fill_db(options.server_url, options.db_name, user, password, replicon_db, system_db, force_update = options.force_update)
+ fill_db(options.server_url, options.db_name, user, password, replicon_db, system_db,
+ force_update=options.force_update)
break
- except restkit.errors.Unauthorized, err:
- print >> sys.stderr, "Bad authentication, try again"
+ except restkit.errors.Unauthorized as err:
+ print("Bad authentication, try again", file=sys.stderr)
try_again += 1
if try_again > 2:
sys.exit("Authentication failure")
- except Exception, err:
- print >> sys.stderr, err
- sys.exit(2)
-
\ No newline at end of file
+