From 573bd5bad7b125bd08f71e442e843294eab03b64 Mon Sep 17 00:00:00 2001 From: Celine Mercier Date: Mon, 6 Feb 2017 11:24:32 +0100 Subject: [PATCH] Removed deprecated code in ecoPCRFormat --- tools/ecoPCRFormat.py | 73 +++++-------------------------------------- 1 file changed, 7 insertions(+), 66 deletions(-) diff --git a/tools/ecoPCRFormat.py b/tools/ecoPCRFormat.py index 3884001..c829ec8 100755 --- a/tools/ecoPCRFormat.py +++ b/tools/ecoPCRFormat.py @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python2.7 import re import gzip @@ -7,11 +7,8 @@ import sys import time import getopt -try: - import psycopg2 - _dbenable=True -except ImportError: - _dbenable=False +_dbenable=False + ##### # @@ -221,56 +218,7 @@ def readTaxonomyDump(taxdir): return taxonomy,ranks,alternativeName,index -def readTaxonomyDB(dbname): - connection = psycopg2.connect(database=dbname) - - cursor = connection.cursor() - cursor.execute("select numid,rank,parent from ncbi_taxonomy.taxon") - taxonomy=[list(x) for x in cursor] - cursor.execute("select rank_class from ncbi_taxonomy.taxon_rank_class order by rank_class") - ranks=cursor.fetchall() - ranks = dict(map(None,(x[0] for x in ranks),xrange(len(ranks)))) - - print >>sys.stderr,"Sorting taxons..." - taxonomy.sort(taxonCmp) - - print >>sys.stderr,"Indexing taxonomy..." - index = {} - for t in taxonomy: - index[t[0]]=bsearchTaxon(taxonomy, t[0]) - - print >>sys.stderr,"Indexing parent and rank..." - for t in taxonomy: - t[1]=ranks[t[1]] - try: - t[2]=index[t[2]] - except KeyError,e: - if t[2] is None and t[0]==1: - t[2]=index[t[0]] - else: - raise e - - cursor.execute("select taxid,name,category from ncbi_taxonomy.name") - - alternativeName=[] - for taxid,name,classname in cursor: - alternativeName.append((name,classname,index[taxid])) - if classname == 'scientific name': - taxonomy[index[taxid]].append(name) - - cursor.execute("select old_numid,current_numid from ncbi_taxonomy.taxon_id_alias") - - print >>sys.stderr,"Adding taxid alias..." - for taxid,current in cursor: - if current is not None: - index[taxid]=index[current] - else: - index[taxid]=None - - - return taxonomy,ranks,alternativeName,index - ##### # # @@ -585,10 +533,9 @@ def ecoParseOptions(arguments): } o,filenames = getopt.getopt(arguments, - 'ht:T:n:gfe', + 'ht:n:gfe', ['help', 'taxonomy=', - 'taxonomy_db=', 'name=', 'genbank', 'fasta', @@ -601,9 +548,6 @@ def ecoParseOptions(arguments): elif name in ('-t','--taxonomy'): opt['taxmod']='dump' opt['taxdir']=value - elif name in ('-T','--taxonomy_db'): - opt['taxmod']='db' - opt['taxdb']=value elif name in ('-n','--name'): opt['prefix']=value elif name in ('-g','--genbank'): @@ -622,6 +566,7 @@ def ecoParseOptions(arguments): return opt,filenames + def printHelp(): print "-----------------------------------" print " ecoPCRFormat.py" @@ -641,11 +586,7 @@ if __name__ == '__main__': opt,filenames = ecoParseOptions(sys.argv[1:]) - if opt['taxmod']=='dump': - taxonomy = readTaxonomyDump(opt['taxdir']) - elif opt['taxmod']=='db': - taxonomy = readTaxonomyDB(opt['taxdb']) - - + taxonomy = readTaxonomyDump(opt['taxdir']) + ecoDBWriter(opt['prefix'], taxonomy, filenames, opt['parser'])