def sql_parse_dna_seq(datafile):
'''Convert data into an SQL table insertion
input: file with each dna seq on a seperate line
output: read each line as seperate string and write to SQL format
'''
count=0
raw_data=[]
clean_data=''
acc_data=[]
acc_count=0
dna_count=0
with open(datafile, 'r') as f:
raw_data+=f.readlines()
for line in raw_data:
if acc_count==0:
clean_data+= "INSERT into CHROM8(ACCESSION, DNA_SEQUENCE) values ("+cl.clean_lines("'"+line+"',")
acc_count+=1
dna_count=0
elif dna_count==0:
clean_data+= cl.clean_lines("'"+line+"')ON DUPLICATE KEY UPDATE DNA_SEQUENCE = '"+line+"';")+"\n"
dna_count+=1
acc_count=0
return (clean_data)
def sql_parse_prot_trans(datafile):
'''This function converts the output of parse_prot_trans(),
input: text file with accession number and protein trnaslation in alternating lines
output: returns an SQL format insertion for a database
'''
count=0
raw_data=[]
clean_data=''
acc_data=[]
acc_count=0
trans_count=1
with open(datafile, 'r') as f:
raw_data+=f.readlines()
for line in raw_data:
if acc_count==0:
clean_data+= "INSERT into CHROM8(ACCESSION, TRANSLATION) values ("+cl.clean_lines("'"+line+"',")
acc_count+=1
trans_count=0
elif trans_count==0:
clean_data+= cl.clean_lines("'"+line+"')ON DUPLICATE KEY UPDATE TRANSLATION = '"+line+"';")+"\n"
trans_count+=1
acc_count=0
return (clean_data)