Kevin.py~

#coding: utf8

from typing import *
from eliot_main import get_genetic_code, write_csv, read_csv
from Theo import read_flat_file


def get_features(txt):
    """Extract features lines from flat text and return them
            This function is written by Kévin Merchadou.
            Args:
                txt: flat text with features to extract
            Returns:
                string of features
        """
    conc=txt.split("\n")
    for i in range(len(conc)):
        if conc[i]=="FEATURES             Location/Qualifiers":
            features = "".join(conc[i+1:])
            break
    return features


def get_genes(features):
    list_CDS=[]
    bloc=("").join(features.split("          "))
    bloc_cleaned=bloc.split("     ")
    for i in range(len(bloc_cleaned)):
        if bloc_cleaned[i][0:3]=="CDS":
            list_CDS.append(i)
    return list_CDS
    





                   
    # for line in features.split('\n'):
    #     if line[5:8] == "CDS":
    #         pos = line.split("             ")[1].split("..")
    #         product = line+7[22].split("=")[1]
    #         protein = 
    #         new_cds = {"start": pos[0], "stop" : pos[1], "frame" : pos[0]%3+1 "length": pos[1] - pos[0],"name" : "unknown", "protein" : "xxx", "product" : "unknown"}
    #     elif line[5] != " " and len(new_cds) > 1:
    #         list_genes.append(new_cds)
    #     else:
    #         new_cds = line[22].split('=')
            
            
            


#def read_gen_bank(filename: str) -> Dict[str, Union[str, List[dict]]]:
    # """Parse a GenBank file

    #         This function is written by Kévin Merchadou.

    #         Args:
    #             filename: .gb file to parse

    #         Returns:
    #             dictionary of :

    #                 features:
    #                         description: entry title (genbank descriptor DEFINITION)
    #                         type: myBio keywords only - dna, rna, or protein
    #                         data: sequence data only if available otherwise set to ‘xxx’. When the sequence is too large
    #                               the entry does not contain data.
    #                         ID: Identifier (locus)
    #                         length: sequence length
    #                         gbtype: molecule type as described in a genbank entry.
    #                         organism: organism²
    #                         codeTableID: NCBI genetic code table identifier

    #                 list of gene = ORF (dict)
    #                         start: start position (in bp)
    #                         stop: stop position (in bp)
    #                         frame: frame (1, 2, 3,- 1, -2, or -3)
    #                         length: gene length (in bp)
    #                         name: gene name if available. By default, ‘unknown’.
    #                         protein: translated protein sequence if available. By default, ‘xxx’.
    #                         product: product name if available. By default, ‘unknown’.
    #     """
#    pass

features=get_features(read_flat_file("sequence.gb"))
bloc=("").join(features.split("          "))
bloc_CDS=bloc.split("     ")
bloc_cleaned=bloc_CDS[7].split("/")
a=(bloc_cleaned[9][12:].split('"')[1]).split(" ")
print(a)
# a=(bloc_cleaned[0][17:].strip()).split("..")[1]
# print(a)
# print(int(a[:len(a)-1]))