def construct_index(cls, opts, bases):
i = None
if opts is None:
# Inherit Index from base classes
for b in bases:
if getattr(b, "_index", DEFAULT_INDEX) is not DEFAULT_INDEX:
parent_index = b._index
i = Index(
parent_index._name,
doc_type=parent_index._mapping.doc_type,
using=parent_index._using,
)
i._settings = parent_index._settings.copy()
i._aliases = parent_index._aliases.copy()
i._analysis = parent_index._analysis.copy()
i._doc_types = parent_index._doc_types[:]
break
if i is None:
i = Index(
getattr(opts, "name", "*"),
doc_type=getattr(opts, "doc_type", "doc"),
using=getattr(opts, "using", "default"),
)
i.settings(**getattr(opts, "settings", {}))
i.aliases(**getattr(opts, "aliases", {}))
for a in getattr(opts, "analyzers", ()):
i.analyzer(a)
return i
def gen_suggests(index, info_tuple):
# 根据字符串生成搜索建议数组
used_words = set()
suggests = []
for text, weight in info_tuple:
if text:
# 调用es的analyze接口分析字符串
ik_analyzer = CustomAnalyzer("ik_max_word", filter=["lowercase"])
my_analyzer = analyzer('my_analyzer',
tokenizer=tokenizer('trigram',
'nGram',
min_gram=3,
max_gram=3),
filter=['lowercase'])
i = Index(index)
i._analysis = ik_analyzer
# i.analyzer(analyzer=ik_analyzer)
# i.analyzer.default.type: "ik_max_word"
a = i.analyze(params={'filter': ["lowercase"]}, body=text)
# i.analyzer(analyzer = "ik_max_word")
words = es.indices.analyze(index=index,
params={'filter': ["lowercase"]},
body=text)
anylyzed_words = set(
[r["token"] for r in words["tokens"] if len(r["token"]) > 1])
new_words = anylyzed_words - used_words
else:
new_words = set()
if new_words:
suggests.append({"input": list(new_words), "weight": weight})
return suggests
