# -*- coding: utf-8 -*-
"""
Created on Tue Nov 13 22:53:33 2018

@author: Lenovo
"""
from whoosh.fields import Schema,TEXT,ID
from jieba.analyse import ChineseAnalyzer
schema = Schema(title=TEXT,path=ID,content=TEXT(stored=True,analyzer=ChineseAnalyzer()))

import os
from whoosh.index import create_in
if not os.path.exists('index'):
    os.mkdir('index')
idx = create_in("index",schema)

writer = idx.writer()
writer.add_document(title="哈哈哈哈哈，嘻嘻",
                    path="99",
                    content="少時誦詩書大撒所三生三世十里桃花")

writer.commit()

from whoosh.qparser import QueryParser
with idx.searcher() as searcher:
    parser = QueryParser("content",schema=idx.schema)
    q = parser.parse('我是來自中國科學技術大學')
    results = searcher.search(q)
    print(results)    

 

接下來看一看ChineseAnalyzer的原始碼：

# encoding=utf-8
from __future__ import unicode_literals
from whoosh.analysis import RegexAnalyzer, LowercaseFilter, StopFilter, StemFilter
from whoosh.analysis import Tokenizer, Token
from whoosh.lang.porter import stem

import jieba
import re

STOP_WORDS = frozenset(('a', 'an', 'and', 'are', 'as', 'at', 'be', 'by', 'can',
                        'for', 'from', 'have', 'if', 'in', 'is', 'it', 'may',
                        'not', 'of', 'on', 'or', 'tbd', 'that', 'the', 'this',
                        'to', 'us', 'we', 'when', 'will', 'with', 'yet',
                        'you', 'your', '的', '了', '和','我'))

accepted_chars = re.compile(r"[\u4E00-\u9FD5]+")


class ChineseTokenizer(Tokenizer):

    def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
#            print(token)
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token


def ChineseAnalyzer(stoplist=STOP_WORDS, minsize=1, stemfn=stem, cachesize=50000):
    return (ChineseTokenizer() | LowercaseFilter() |
            StopFilter(stoplist=stoplist, minsize=minsize) |
            StemFilter(stemfn=stemfn, ignore=None, cachesize=cachesize))
 

看到我們可以在STOP_WORDS里加入自己的停用詞，但是如何指定Dictionary好像還不具備這個功能，我們來對原始碼進行改造

通過層層追蹤，我們發現在Tokenizer中可以通過初始化指定詞典

# encoding=utf-8
from __future__ import unicode_literals
from whoosh.analysis import RegexAnalyzer, LowercaseFilter, StopFilter, StemFilter
from whoosh.analysis import Tokenizer, Token
from whoosh.lang.porter import stem

import jieba
import re
tk = jieba.Tokenizer(dictionary=None)
STOP_WORDS = frozenset(('a', 'an', 'and', 'are', 'as', 'at', 'be', 'by', 'can',
                        'for', 'from', 'have', 'if', 'in', 'is', 'it', 'may',
                        'not', 'of', 'on', 'or', 'tbd', 'that', 'the', 'this',
                        'to', 'us', 'we', 'when', 'will', 'with', 'yet',
                        'you', 'your', '的', '了', '和','我'))

accepted_chars = re.compile(r"[\u4E00-\u9FD5]+")


class ChineseTokenizer(Tokenizer):

    def __call__(self, text, **kargs):
        words = tk.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
#            print(token)
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token


def ChineseAnalyzer(stoplist=STOP_WORDS, minsize=1, stemfn=stem, cachesize=50000):
    return (ChineseTokenizer() | LowercaseFilter() |
            StopFilter(stoplist=stoplist, minsize=minsize) |
            StemFilter(stemfn=stemfn, ignore=None, cachesize=cachesize))
 

把初始化Tokenizer的操作作為全域性變數，這樣可以做到常駐記憶體，避免重複載入詞典耗時