def main():
from desc.prof import profile_me
# clean updated annos
#clean_dupes(get_annos, repr_issues=True)
#return
# fetching
annos = get_annos()
#_annos = annos
#annos = [a for a in annos if a.updated > '2017-10-15']
# loading
#@profile_me
#def load():
#for a in annos:
#rrcu(a, annos)
#load()
#rc = list(rrcu.objects.values())
rc = [rrcu(a, annos) for a in annos]
# id all the things
#from joblib import Parallel, delayed
#id_annos = []
#for purl in rrcu._papers:
#resp = idPaper(purl)
#id_annos.append(resp)
#id_annos = Parallel(n_jobs=5)(delayed(idPaper)(url)
#for url in sorted(rrcu._papers))
#embed()
#return
# sanity checks
#print('repr everything')
#_ = [repr(r) for r in rc] # exorcise the spirits (this is the slow bit, joblib breaks...)
try:
stats = sanity_and_stats(rc, annos)
except AssertionError as e:
print(e)
embed()
评论列表
文章目录