django全文搜索学习心得（三）whoosh篇

HAYSTACK_COnNECTIONS= {
    'default': {
        'ENGINE': 'haystack.backends.whoosh_cn_backend.WhooshEngine',
        'PATH': os.path.join(os.path.dirname(__file__), 'whoosh_index'),
        },
    }

import jieba
from whoosh.analysis import RegexAnalyzer
from whoosh.analysis import Tokenizer,Token

class ChineseTokenizer(Tokenizer):
    def __call__(self, value, positiOns=False, chars=False,
                 keeporiginal=False, removestops=True,
                 start_pos=0, start_char=0, mode='', **kwargs):
        #assert isinstance(value, text_type), "%r is not unicode" % value
        t = Token(positions, chars, removestops=removestops, mode=mode,
            **kwargs)
        seglist=jieba.cut(value,cut_all=True)
        for w in seglist:
            t.original = t.text = w
            t.boost = 1.0
            if positions:
                t.pos=start_pos+value.find(w)
            if chars:
                t.startchar=start_char+value.find(w)
                t.endchar=start_char+value.find(w)+len(w)
            yield t

def ChineseAnalyzer():
    return ChineseTokenizer()

#在whoosh_cn_backend.py里面
.........
from ChineseAnalyzer import ChineseAnalyzer
.............
#然后找到build_schema函数处，这是一个构建分词模式的
#找到
schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=StemmingAnalyzer(), field_boost=field_class.boost)

python manage.py rebuild_index  创建索引
python manage.py runserver 运行