def rank(msg):
t = time.time()
ret = {}
msg = cStringIO.StringIO(msg)
query_msg = decode_netstring_fd(msg)
layer_msg = decode_netstring_fd(msg)
erlay.report("Rank init took %dms" %\
((time.time() - t) * 1000.0))
print >> sys.stderr, "QUERY", query_msg
if query_msg['mods'] and query_msg['mods'].startswith("site:"):
ok_site = hash(query_msg['mods'][5:])
print >> sys.stderr, "SHOW SITE", query_msg['mods'], ok_site
else:
ok_site = 0
t = time.time()
hits_len, hits = ainodex.hits(map(int, query_msg['keys'].split()), 0)
ret['num_hits'] = str(hits_len)
hits_len, hits = filter_hits(hits_len, hits,\
site_check = True, prior_check=True, show_site=ok_site)
erlay.report("Hits took %dms" %\
((time.time() - t) * 1000.0))
print "HITS_LEN", hits_len
t = time.time()
layers = [None] * 10
for layer_str in layer_msg.itervalues():
ainodex.deserialize_layer(layer_str, layers)
erlay.report("Deser took %dms" %\
((time.time() - t) * 1000.0))
#kkeys = map(lambda x: ainopy.did2key(ainopy.sid2doc(x)[0]), ainodex.hit_contents(hits))
t = time.time()
ret['ranked'] = ainodex.rank(hits, layers)
print >> sys.stderr, "RANKED", array.array("I", ret["ranked"])[:20:2]
#for key in array.array("I", ret["ranked"])[:20:2]:
#if key not in okkeys:
# print >> sys.stderr, "NOT IN OK", key
print "LL", len(ret['ranked'])
erlay.report("Ranking <%s><%s> took %dms" %
(query_msg['keys'], query_msg['cues'],
(time.time() - t) * 1000.0))
return encode_netstring_fd(ret)
def rank(msg):
t = time.time()
ret = {}
msg = cStringIO.StringIO(msg)
query_msg = decode_netstring_fd(msg)
layer_msg = decode_netstring_fd(msg)
erlay.report("Rank init took %dms" %\
((time.time() - t) * 1000.0))
print >> sys.stderr, "QUERY", query_msg
if query_msg['mods'] and query_msg['mods'].startswith("site:"):
ok_site = hash(query_msg['mods'][5:])
print >> sys.stderr, "SHOW SITE", query_msg['mods'], ok_site
else:
ok_site = 0
t = time.time()
hits_len, hits = ainodex.hits(map(int, query_msg['keys'].split()), 0)
ret['num_hits'] = str(hits_len)
hits_len, hits = filter_hits(hits_len, hits,\
site_check = True, prior_check=True, show_site=ok_site)
erlay.report("Hits took %dms" %\
((time.time() - t) * 1000.0))
print "HITS_LEN", hits_len
t = time.time()
layers = [None] * 10
for layer_str in layer_msg.itervalues():
ainodex.deserialize_layer(layer_str, layers)
erlay.report("Deser took %dms" %\
((time.time() - t) * 1000.0))
#kkeys = map(lambda x: ainopy.did2key(ainopy.sid2doc(x)[0]), ainodex.hit_contents(hits))
t = time.time()
ret['ranked'] = ainodex.rank(hits, layers)
print >> sys.stderr, "RANKED", array.array("I", ret["ranked"])[:20:2]
#for key in array.array("I", ret["ranked"])[:20:2]:
#if key not in okkeys:
# print >> sys.stderr, "NOT IN OK", key
print "LL", len(ret['ranked'])
erlay.report("Ranking <%s><%s> took %dms" %
(query_msg['keys'], query_msg['cues'],
(time.time() - t) * 1000.0))
return encode_netstring_fd(ret)
def merge_scores(msg):
msg = cStringIO.StringIO(msg)
layers = [None] * 10
cueset_size = 0
while True:
try:
iblock_layers = decode_netstring_fd(msg)
except EOFError:
break
cueset_size += int(iblock_layers['cueset_size'])
del iblock_layers['cueset_size']
for layer_data in iblock_layers.itervalues():
offs, layer_id, layer =\
ainodex.deserialize_layer(
layer_data, layers)
#XXX: Since ixemes are allocated on different layers on each layer,
# we must make sure that the ixeme counts match on every layer. This
# could be easily avoided if ixemes were on the same layers on all
# iblocks. This should be easy to fix.
t = time.time()
ainodex.sync_layers(layers)
erlay.report("Syncing layers took %dms" %\
((time.time() - t) * 1000.0))
print "CUE", type(cueset_size), cueset_size
for layer in layers:
if layer:
ainodex.normalize_layer(layer, normtable, cueset_size)
layers = [(str(i), ainodex.serialize_layer(layer))
for i, layer in enumerate(layers) if layer]
return encode_netstring_fd(dict(layers))
if query_msg['mods']:
if query_msg['mods'].startswith("site"):
site_check = False
elif query_msg['mods'].startswith("score"):
show_score = True
except Exception, x:
erlay.report("Invalid or missing query string: %s" %
query_msg['query'])
traceback.print_exc()
offs = 0
query_q = ""
layers = [None] * 10
for layer_str in score_msg.itervalues():
ainodex.deserialize_layer(layer_str, layers)
ranked = array.array("I", rank_msg['merged'])[::2]
results = []
if show_score:
results.append(show_best_ix(layers))
hits = len(ranked) + 1
site_check = True
else:
hits = 0
valid_hits = 0
seen_sites = {}
seen_md5s = {}
while hits < len(ranked):
dockey = ranked[hits]
if query_msg['mods']:
if query_msg['mods'].startswith("site"):
site_check = False
elif query_msg['mods'].startswith("score"):
show_score = True
except Exception, x:
erlay.report("Invalid or missing query string: %s" %
query_msg['query'])
traceback.print_exc()
offs = 0
query_q = ""
layers = [None] * 10
for layer_str in score_msg.itervalues():
ainodex.deserialize_layer(layer_str, layers)
ranked = array.array("I", rank_msg['merged'])[::2]
results = []
if show_score:
results.append(show_best_ix(layers))
hits = len(ranked) + 1
site_check = True
else:
hits = 0
valid_hits = 0
seen_sites = {}
seen_md5s = {}
while hits < len(ranked):
dockey = ranked[hits]