# coding: utf-8

# In[1]:

#import packages:
import os
from os import listdir
import sys
import pandas as pd

##specify path and define directory with all the queries
path= "/Users/asd/CODES/test/proteins_human"

protein_directory=os.listdir(path)
#iterate each protein_folder and select new_exonerate_final_scaffold.gff files
for protein_folder in protein_directory:
    if protein_folder == '.DS_store':
        pass
    else:
        files=os.listdir('{}/{}'.format(path,protein_folder))
        #select files with exonerate fnal inside
        exonerate_files= [k for k in files if 'new_exonerate_final_' in k]
        #opens and reads files
        for file_ in exonerate_files:
            if os.path.getsize('{}/{}/{}'.format(path,protein_folder,file_))== 0:
                pass
            else:
                exonerate_file=open('{}/{}/{}'.format(path,protein_folder,file_)).read()
                #define_name and fake start
                #print(exonerate_file)
                name=exonerate_file.split(':',1)[0]
                fake_start=int(exonerate_file.split('subseq(',1)[1].split(',',1)[0])
                #print(name,fake_start)
                exonerate_exons=exonerate_file.splitlines()
                #print(exonerate_exons)
                sequence_starts=[]
                sequence_ends=[]
                for exon in exonerate_exons:
                    if exon == '':
                        pass
                    else:
                        #print(exon)
                        tabulated=exon.split('\t')
                        exon_start= int(tabulated[3])
                        exon_end=int(tabulated[4])
                        sequence_starts.append(exon_start)
                        sequence_ends.append(exon_end)

                sequence_starts_sorted=sorted(sequence_starts)
                sequence_ends_sorted=sorted(sequence_ends)
                #print(sequence_starts_sorted,sequence_ends_sorted)
                real_start=fake_start+sequence_starts_sorted[0]
                end=real_start+sequence_ends_sorted[-1]-sequence_starts_sorted[0]
                print('%s \t %s \t %s \t %s \t'%(protein_folder,name,real_start,end))



# In[ ]:


        
    


# In[ ]: