def work():
while True:
url = in_queue.get()
content = requests.get(url).content.decode('iso8859-1')
container = {}
container["cazy"] = {}
container["taxonomy"] = {}
try:
container["name"] = re.findall(r'id="font_org">(.+)</font>',
content)[0]
#container["organism"] = re.findall(r'id="font_org">(.+)</font>', content)[0]
cazy_page_taxon_name = re.findall(
r'<font class="titre_cazome" id="font_org">(.+)<\/font>',
content)[0]
#print (cazy_page_taxon_name)
taxonomy_id = -1
if cazy_page_taxon_name:
taxonomy_id = int(
pyphy.getTaxidByName(cazy_page_taxon_name.strip())[0])
if taxonomy_id == -1:
taxonomy_id = re.findall(
r'http://www\.ncbi\.nlm\.nih\.gov/Taxonomy/Browser/wwwtax\.cgi\?id=(\d+)',
content)[0]
container["taxid"] = int(taxonomy_id)
#lineage = re.findall(r'<b>Lineage</b>\:(.+)<br><br />', content)[0].strip()
current_id = int(taxonomy_id)
while current_id != 1 and current_id != -1:
current_id = int(pyphy.getParentByTaxid(current_id))
if pyphy.getRankByTaxid(current_id) in desired_ranks:
container["taxonomy"][pyphy.getRankByTaxid(current_id)] = [
pyphy.getNameByTaxid(current_id), current_id
]
#container["total_gi"] = len(pyphy.getGiByTaxid(taxonomy_id))
cazies = re.findall(rx, content)
#print cazy
for cazy in cazies:
container["cazy"][cazy[0]] = int(cazy[1])
if len(container["cazy"]) != 0:
writeLock.acquire()
container["column"] = "genome"
print(json.dumps(container))
writeLock.release()
except Exception:
pass
in_queue.task_done()
def work():
while True:
content = in_queue.get()
nonsense = True
#print ("initial", content)
for line in content.split("\n"):
fields = line.split("\t")
temp_content = ["-1"] * 7
if nonsense == True:
search_taxon = rx_taxon.search(line)
if search_taxon:
taxon = search_taxon.group(1).replace("_", " ")
if "sp." in taxon:
taxon = taxon.split("sp.")[0] + "sp. " + taxon.split(
"sp.")[1].strip().replace(" ", "_")
if taxon not in taxon_content:
taxid = pyphy.getTaxidByName(taxon)[0]
path = pyphy.getPathByTaxid(taxid)
for item in path:
rank = pyphy.getRankByTaxid(item)
if rank in desired_ranks:
index = desired_ranks.index(rank)
temp_content[index] = pyphy.getNameByTaxid(
item)
dictLock.acquire()
taxon_content[taxon] = temp_content
dictLock.release()
else:
temp_content = taxon_content[taxon]
if temp_content.count("-1") < 7:
nonsense = False
writeLock.acquire()
#print ()
print(fields[0] + "\t" + "\t".join(temp_content))
writeLock.release()
in_queue.task_done()
def worker(one_query):
#print (taxid)
name_path = {}
query_name = ""
#print (one_query)
for query in one_query:
if len(name_path) == 0:
query_name, taxid, score, pident, qcovs, evalue = query
temp_name_path = {}
if cache.exists(taxid):
temp_name_path = cache.hgetall(taxid)
else:
path = pyphy.getDictPathByTaxid(taxid)
temp_name_path = {
rank: pyphy.getNameByTaxid(path[rank])
for rank in path
}
cache.hmset(taxid, temp_name_path)
if "phylum" in temp_name_path:
name_path = temp_name_path
if len(name_path) != 0:
content = "\t".join([query_name, taxid, score, pident, qcovs, evalue
]) + "\t"
for rank in desired_ranks:
if rank in name_path:
content += name_path[rank] + "\t"
else:
content += "\t"
print(content.strip())
for t in search_taxid:
taxid = int(t)
#print (file)
if taxid != -1:
dict_path = pyphy.getDictPathByTaxid(taxid)
dict_path["genome"] = taxid
quartett = [""] * 2
#print (dict_path)
if filter_rank in dict_path and pyphy.getNameByTaxid(dict_path[filter_rank]) == filter_taxon:
for rank in desired_rank:
if rank in dict_path:
name = definition.split(",")[0]
if rank != "genome":
name = pyphy.getNameByTaxid(dict_path[rank])
if rank == "superkingdom":
quartett[0] = dict_path[rank]
if dict_path[rank] not in taxid_taxon:
taxid_taxon[dict_path[rank]] = [name, rank]
else:
def test_TaxidToName(self):
self.assertEqual(pyphy.getNameByTaxid(2), "Bacteria")