def search(query, page = 1, size=10):
lasttime = time.clock()
suggestor.add_query(query)
tokens = stop_and_stem_seq(parse(query, ''))
result = get_doc_list(query, tokens)
result = collect(result[(page - 1)*size:page*size], tokens, len(result), lasttime)
return result
def search(query, page=1, size=10):
lasttime = time.clock()
suggestor.add_query(query)
tokens = stop_and_stem_seq(parse(query, ''))
result = get_doc_list(query, tokens)
result = collect(result[(page - 1) * size:page * size], tokens,
len(result), lasttime)
return result
def save_and_segment(doc_id, html, url):
import suggestor
title, text, words = analyze(html)
l = len(words)
r.hmset('doc:%s'%doc_id, {'title': title, 'text': text, 'len': l, 'url': url})
r.incrbyfloat('total_len', l)
for token in words:
suggestor.add_query(token.word, token.weight)
r.zadd(u'word:%s'%token.word, token.weight, doc_id)
r.hmset(u'dw:%s:%s:%s'%(doc_id, token.word, token.fieldname), {
'pos': token.pos,
'len': token.len,
'weight': token.weight,
})
def save_and_segment(doc_id, html, url):
import suggestor
title, text, words = analyze(html)
l = len(words)
r.hmset('doc:%s' % doc_id, {
'title': title,
'text': text,
'len': l,
'url': url
})
r.incrbyfloat('total_len', l)
for token in words:
suggestor.add_query(token.word, token.weight)
r.zadd(u'word:%s' % token.word, token.weight, doc_id)
r.hmset(u'dw:%s:%s:%s' % (doc_id, token.word, token.fieldname), {
'pos': token.pos,
'len': token.len,
'weight': token.weight,
})
