def __init__(self, version: str):
_DL_PAGE_URL = "http://202.120.12.135/TADB2/download.html"
self.describer = ReferenceDescriber()
self.describer.VERSION = version
self.describer.update_alias()
self.reference_dir = os.path.join("/data/reference", self.describer.NAME, self.describer.ALIAS)
links = [i for i in Utilities.scrap_links_from_web_page(_DL_PAGE_URL) if i.endswith(".fas")]
self._fasta_types = ["nucleotide", "protein"]
self._links_dict = {k: [i for i in links if i.split("/")[-2] == k] for k in self._fasta_types}
assert len(self._links_dict["nucleotide"]) + len(self._links_dict["protein"]) == len(links)
self.nfasta = os.path.join(self.reference_dir, "{}.fasta".format(self.describer.ALIAS))
self.pfasta = os.path.join(self.reference_dir, "{}_protein.fasta".format(self.describer.ALIAS))
self.index_dir = ""
def __init__(self):
self.describer = ReferenceDescriber()
self.describer.VERSION = self._get_last_friday()
self.reference_dir = os.path.join("/data/reference",
self.describer.NAME,
self.describer.ALIAS)
links = [
i for i in Utilities.scrap_links_from_web_page(self._DL_PAGE_URL)
if i.endswith(".gz")
]
self._dl_queue = []
for dl_link in links:
dl_dir = self.reference_dir
if "_pro" in dl_link:
dl_dir = os.path.join(dl_dir, "protein")
elif "_nt" in dl_link:
dl_dir = os.path.join(dl_dir, "nucleotide")
self._dl_queue.append((dl_link, dl_dir))
self.nfasta = os.path.join(self.reference_dir,
"{}.fasta".format(self.describer.ALIAS))
self.pfasta = os.path.join(
self.reference_dir,
"{}_protein.fasta".format(self.describer.ALIAS))
