Redis: search suggestions

[macbre]

$ redis-cli 
127.0.0.1:6379> ZADD autocomplete 0 poznańskiego 0 poznań 0 tej 0 tak
(integer) 4

127.0.0.1:6379> ZRANGEBYLEX autocomplete [poz "[poz\xff" LIMIT 0 10
1) "pozna\xc5\x84"
2) "pozna\xc5\x84skiego"

http://www.opensearch.org/Specifications/OpenSearch/Extensions/Suggestions/1.1

["sea",
  ["sears",
   "search engines",
   "search engine",
   "search",
   "sears.com",
   "seattle times"],
  ["7,390,000 results",
   "17,900,000 results",
   "25,700,000 results",
   "1,220,000,000 results",
   "1 result",
   "17,600,000 results"],
  ["http://example.com?q=sears",
   "http://example.com?q=search+engines",
   "http://example.com?q=search+engine",
   "http://example.com?q=search",
   "http://example.com?q=sears.com",
   "http://example.com?q=seattle+times"]]

[macbre]

$ make stopwords 
zcat ../wbc/106644.xml.gz | docker-compose run sphinx indexer wbc -c /opt/sphinx.conf --buildfreqs --buildstops /dev/stdout 250000 > stopwords.txt
cat stopwords.txt | docker-compose run app stopwords
INFO:get_redis:Connected to StrictRedis<ConnectionPool<Connection<host=redis,port=6379,db=0>>>
INFO:StopWords:Indexing stopwords...
INFO:StopWords:Indexed 145192 stopwords in 5.46 sec

[macbre]

d89f62a

[macbre]

[
"żeg",
[
"żegadło",
"żegierskich",
"żegierskie",
"żegierszczanie",
"żeglarska",
"żeglarski",
"żeglarskich",
"żeglarskie",
"żeglarskiego",
"żeglarskiej",
"żeglarską",
"żeglarstwa",
"żeglarstwo",
"żeglarz",
"żeglarza",
"żeglarze",
"żeglarzy",
"żeglownego",
"żegludze",
"żegluga"
]
]

[macbre]

INFO:StopWords:Indexing stopwords...
INFO:get_redis:Connected to StrictRedis<ConnectionPool<Connection<host=redis,port=6379,db=0>>>
INFO:StopWords:Indexed 235337 stopwords in 8.81 sec