third_codes/jieba
1
0
Fork 0
mirror of https://github.com/fxsjy/jieba.git synced 2025-07-10 00:01:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

更新

Browse Source
This commit is contained in:
ZoeyYoung 2013-08-21 19:24:34 +08:00
parent dce353f88b
commit 6024497917
4 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
jieba/analyse/__init__.py
View File

@ -2,7 +2,7 @@ import jieba
import os import os
try: try:
from analyzer import ChineseAnalyzer from .analyzer import ChineseAnalyzer
except ImportError: except ImportError:
pass pass

2
jieba/finalseg/__init__.py
View File

@ -43,7 +43,7 @@ def load_model():
if sys.platform.startswith("java"): if sys.platform.startswith("java"):
start_P, trans_P, emit_P = load_model() start_P, trans_P, emit_P = load_model()
else: else:
import prob_start,prob_trans,prob_emit from . import prob_start,prob_trans,prob_emit
start_P, trans_P, emit_P = prob_start.P, prob_trans.P, prob_emit.P start_P, trans_P, emit_P = prob_start.P, prob_trans.P, prob_emit.P
def viterbi(obs, states, start_p, trans_p, emit_p): def viterbi(obs, states, start_p, trans_p, emit_p):

2
jieba/posseg/__init__.py
View File

@ -56,7 +56,7 @@ def load_model(f_name,isJython=True):
if sys.platform.startswith("java"): if sys.platform.startswith("java"):
char_state_tab_P, start_P, trans_P, emit_P, word_tag_tab = load_model(jieba.get_abs_path_dict()) char_state_tab_P, start_P, trans_P, emit_P, word_tag_tab = load_model(jieba.get_abs_path_dict())
else: else:
import char_state_tab, prob_start, prob_trans, prob_emit from . import char_state_tab, prob_start, prob_trans, prob_emit
char_state_tab_P, start_P, trans_P, emit_P = char_state_tab.P, prob_start.P, prob_trans.P, prob_emit.P char_state_tab_P, start_P, trans_P, emit_P = char_state_tab.P, prob_start.P, prob_trans.P, prob_emit.P
word_tag_tab = load_model(jieba.get_abs_path_dict(),isJython=False) word_tag_tab = load_model(jieba.get_abs_path_dict(),isJython=False)

14
test/test_whoosh.py
View File

@ -5,7 +5,7 @@ from whoosh.index import create_in,open_dir
from whoosh.fields import * from whoosh.fields import *
from whoosh.qparser import QueryParser from whoosh.qparser import QueryParser
from jieba.analyse.analyzer import ChineseAnalyzer from jieba.analyse import ChineseAnalyzer
analyzer = ChineseAnalyzer() analyzer = ChineseAnalyzer()
@ -18,31 +18,31 @@ ix = create_in("tmp", schema) # for create new index
writer = ix.writer() writer = ix.writer()
writer.add_document( writer.add_document(
title="document1", title="document1",
path="/a", path="/a",
content="This is the first document we’ve added!" content="This is the first document we’ve added!"
) )
writer.add_document( writer.add_document(
title="document2", title="document2",
path="/b", path="/b",
content="The second one 你 中文测试中文 is even more interesting! 吃水果" content="The second one 你 中文测试中文 is even more interesting! 吃水果"
) )
writer.add_document( writer.add_document(
title="document3", title="document3",
path="/c", path="/c",
content="买水果然后来世博园。" content="买水果然后来世博园。"
) )
writer.add_document( writer.add_document(
title="document4", title="document4",
path="/c", path="/c",
content="工信处女干事每月经过下属科室都要亲口交代24口交换机等技术性器件的安装工作" content="工信处女干事每月经过下属科室都要亲口交代24口交换机等技术性器件的安装工作"
) )
writer.add_document( writer.add_document(
title="document4", title="document4",
path="/c", path="/c",
content="咱俩交换一下吧。" content="咱俩交换一下吧。"
) )
@ -55,7 +55,7 @@ for keyword in ("水果世博园","你","first","中文","交换机","交换"):
print("result of ",keyword) print("result of ",keyword)
q = parser.parse(keyword) q = parser.parse(keyword)
results = searcher.search(q) results = searcher.search(q)
for hit in results: for hit in results:
print(hit.highlights("content")) print(hit.highlights("content"))
print("="*10) print("="*10)