test_module_genbankfixer.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-


import pytest
from pydna.readers      import read


def test_pydna_gbtext_clean():
    from pydna.genbankfixer import gbtext_clean

    files = [    ("sequence.gb", "j2yAlBCZ-txSTCkakAmykAielRI"),
                 ("NCBI_example.gb", "j2yAlBCZ-txSTCkakAmykAielRI"),
                 ("YEplac181.txt", "lbnQtxi5LyDONRswRdG88-l8NF0"),
                 ("pGADT7-Rec.gb", "rhnYE78wGKdqAZWiyVJzQ7HXXys"),
                 ("P30350%20(2013-10-11%2013_49_14).dna.txt", "_aEPoGLctHcOZdQdZIh-KyBt5WY"),
                 ("ApE_example.gb", "c47i2ifiNZVvvnLQbX5anTVVoPE"),
                 ("VectorNTI_example.gb", "bDPbx5P4yigGWh1zK7FiG_SF8qQ"),
                 ("hej.txt", "lbnQtxi5LyDONRswRdG88-l8NF0"), ]

    for file_, seg in files:             
        with open("broken_genbank_files/"+file_, "r") as f:
            infile = f.read()
        if file_ == "hej.txt":
            from Bio import BiopythonParserWarning
            with pytest.warns(BiopythonParserWarning):
                assert read( gbtext_clean(infile).gbtext ).seguid() == seg
        else:
            assert read( gbtext_clean(infile).gbtext ).seguid() == seg


def test_wrapstring():
    from pydna.genbankfixer import wrapstring
    assert wrapstring("0123456789",0,5,)=='01234\n56789\n\n'
    assert wrapstring("0123456789",1,5,padfirst=False) == '0123\n 4567\n 89\n'


if __name__ == '__main__':
    pytest.cmdline.main([__file__, "-v", "-s"])