def filter_hits(hits_len, hits, prior_check = False, site_check = False, show_site = 0):
if not seg_hashes:
return hits_len, hits
if prior_check:
uniq = dict((seg_hashes[sid], sid)
for sid in ainodex.hit_contents(hits)
if ainopy.docinfo(ainopy.sid2did(sid))[1] == 1.0)
else:
uniq = dict((seg_hashes[sid], sid)
for sid in ainodex.hit_contents(hits))
if site_check:
if show_site:
for key, sid in uniq.items():
h = sites[ainopy.did2key(ainopy.sid2did(sid))]
if h != show_site:
del uniq[key]
else:
u = {}
for sid in uniq.itervalues():
h = sites[ainopy.did2key(ainopy.sid2did(sid))]
u[h] = sid
uniq = u
return len(uniq), ainodex.list_to_hits(uniq.values())
def filter_hits(hits_len,
hits,
prior_check=False,
site_check=False,
show_site=0):
if not seg_hashes:
return hits_len, hits
if prior_check:
uniq = dict((seg_hashes[sid], sid)
for sid in ainodex.hit_contents(hits)
if ainopy.docinfo(ainopy.sid2did(sid))[1] == 1.0)
else:
uniq = dict(
(seg_hashes[sid], sid) for sid in ainodex.hit_contents(hits))
if site_check:
if show_site:
for key, sid in uniq.items():
h = sites[ainopy.did2key(ainopy.sid2did(sid))]
if h != show_site:
del uniq[key]
else:
u = {}
for sid in uniq.itervalues():
h = sites[ainopy.did2key(ainopy.sid2did(sid))]
u[h] = sid
uniq = u
return len(uniq), ainodex.list_to_hits(uniq.values())
def read_sites():
last_key = ainopy.did2key(ainopy.info()["Number of documents"] - 1)
first_key = ainopy.did2key(0)
sites = {}
for l in file(NAME + ".sitehash"):
key, hash = map(int, l.split())
key -= 1
if key > last_key:
break
if key >= first_key:
sites[key] = hash
return sites
def read_sites():
last_key = ainopy.did2key(ainopy.info()["Number of documents"] - 1)
first_key = ainopy.did2key(0)
sites = {}
for l in file(NAME + ".sitehash"):
key, hash = map(int, l.split())
key -= 1
if key > last_key:
break
if key >= first_key:
sites[key] = hash
return sites