def __init__(self,
whoosh_index_dir,
model=2,
implicit_or=True,
pval=None,
frag_type=2,
frag_size=2,
frag_surround=40,
host=None,
port=0):
super(WhooshSearchInterface, self).__init__()
log.debug("Whoosh Index to open: {0}".format(whoosh_index_dir))
self.__index = open_dir(whoosh_index_dir)
self.__reader = self.__index.reader()
self.__redis_conn = None
if host is None:
self.__engine = Whooshtrec(whoosh_index_dir=whoosh_index_dir,
model=model,
implicit_or=implicit_or)
else:
self.__engine = Whooshtrec(whoosh_index_dir=whoosh_index_dir,
model=model,
implicit_or=implicit_or,
cache='engine',
host=host,
port=port)
# Update (2017-05-02) for snippet fragment tweaking.
# SIGIR Study (2017) uses frag_type==1 (2 doesn't give sensible results), surround==40, snippet_sizes==2,0,1,4
self.__engine.snippet_size = frag_size
self.__engine.set_fragmenter(frag_type=frag_type,
surround=frag_surround)
if pval:
self.__engine.set_model(model, pval)
