diff --git a/test/test_whoosh.py b/test/test_whoosh.py index bb2fda6..1d7f747 100644 --- a/test/test_whoosh.py +++ b/test/test_whoosh.py @@ -1,5 +1,5 @@ # -*- coding: UTF-8 -*- -import sys +import sys,os sys.path.append("../") from whoosh.index import create_in,open_dir from whoosh.fields import * @@ -10,6 +10,9 @@ from jieba.analyse import ChineseAnalyzer analyzer = ChineseAnalyzer() schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer)) +if not os.path.exists("tmp"): + os.mkdir("tmp") + ix = create_in("tmp", schema) # for create new index #ix = open_dir("tmp") # for read only writer = ix.writer() diff --git a/test/test_whoosh_flie.py b/test/test_whoosh_flie.py index c843d6b..3610b49 100644 --- a/test/test_whoosh_flie.py +++ b/test/test_whoosh_flie.py @@ -1,5 +1,6 @@ # -*- coding: UTF-8 -*- import sys +import os sys.path.append("../") from whoosh.index import create_in from whoosh.fields import * @@ -10,6 +11,8 @@ from jieba.analyse import ChineseAnalyzer analyzer = ChineseAnalyzer() schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer)) +if not os.path.exists("tmp"): + os.mkdir("tmp") ix = create_in("tmp", schema) writer = ix.writer() diff --git a/test/test_whoosh_flie_read.py b/test/test_whoosh_flie_read.py new file mode 100644 index 0000000..4528ae4 --- /dev/null +++ b/test/test_whoosh_flie_read.py @@ -0,0 +1,27 @@ +# -*- coding: UTF-8 -*- +import sys +import os +sys.path.append("../") +from whoosh.index import create_in,open_dir +from whoosh.fields import * +from whoosh.qparser import QueryParser + +from jieba.analyse import ChineseAnalyzer + +analyzer = ChineseAnalyzer() + +schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer)) +if not os.path.exists("tmp"): + os.mkdir("tmp") +ix = open_dir("tmp") + +searcher = ix.searcher() +parser = QueryParser("content", schema=ix.schema) + +for keyword in (u"水果小姐",u"你",u"first",u"中文",u"交换机",u"交换",u"少林",u"乔峰"): + print "result of ",keyword + q = parser.parse(keyword) + results = searcher.search(q) + for hit in results: + print hit.highlights("content") + print "="*10