def func_pic(command):
global vm_env
vm_env = lucene.getVMEnv()
vm_env.attachCurrentThread()
STORE_DIR = "index for pic"
directory = SimpleFSDirectory(File(STORE_DIR))
searcher = IndexSearcher(directory, True)
analyzer = lucene.WhitespaceAnalyzer(Version.LUCENE_CURRENT)
imgurl = []
url = []
urltitle = []
imgurl, url, urltitle = run_pic(command, searcher, analyzer)
searcher.close()
return imgurl, url, urltitle
def func(command):
global vm_env
vm_env = lucene.getVMEnv()
vm_env.attachCurrentThread()
STORE_DIR = "index for website"
directory = SimpleFSDirectory(File(STORE_DIR))
searcher = IndexSearcher(directory, True)
analyzer = lucene.WhitespaceAnalyzer(Version.LUCENE_CURRENT)
title = []
url = []
surround = []
title, url, surround = run(searcher, analyzer, command)
searcher.close()
return title, url, surround
print "Searching for:", command
query = QueryParser(Version.LUCENE_CURRENT, "contents",
analyzer).parse(command)
#用analyzer来对查询语句进行词法分析和语言处理。
#QueryParser调用parser进行语法分析，形成查询语法树，放到Query中。
scoreDocs = searcher.search(query, 50).scoreDocs
#IndexSearcher调用search对查询语法树Query进行搜索，得到结果
print "%s total matching documents." % len(scoreDocs), '\n'
for scoreDoc in scoreDocs:
doc = searcher.doc(scoreDoc.doc)
print "------------------------"
print 'path:', doc.get("path")
print 'title:', doc.get("title")
print 'url:', doc.get("url")
print 'name:', doc.get("name")
if __name__ == '__main__':
STORE_DIR = "index"
initVM()
print 'lucene', VERSION
directory = SimpleFSDirectory(File(STORE_DIR)) #索引文件存放的位置
searcher = IndexSearcher(directory, True) #索引信息读入到内存，创建IndexSearcher准备进行搜索
analyzer = lucene.WhitespaceAnalyzer(
Version.LUCENE_CURRENT
) #analyzer用来对查询语句进行词法分析和语言处理的，和IndexFiles.py中使用同样的analyzer。
run(searcher, analyzer)
searcher.close()
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
qestion.add(
lucene.Field("qst_follow", qst_follow,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
qestion.add(
lucene.Field("qst_ans", qst_ans, lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
qestion.add(
lucene.Field("qst_num", qst_num, lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
writer.addDocument(qestion)
except Exception, e:
print "Failed in indexDocs:", e
f.close()
if __name__ == '__main__':
lucene.initVM()
print 'lucene', lucene.VERSION
start = datetime.now()
try:
IndexFiles('analyzed_zhihu', "index_qst",
lucene.WhitespaceAnalyzer(lucene.Version.LUCENE_CURRENT))
end = datetime.now()
print end - start
except Exception, e:
print "Failed: ", e
lucene.Field.Index.ANALYZED))
doc.add(lucene.Field("url", url,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
doc.add(lucene.Field("urltitle", title,
lucene.Field.Store.YES,
lucene.Field.Index.NOT_ANALYZED))
writer.addDocument(doc) #IndexWriter调用函数addDocument将索引写到索引文件夹中
print "----------------------------------------------------"
except Exception, e:
print "Failed in indexDocs:", e
else:
break
t.close()
if __name__ == '__main__':
## if len(sys.argv) < 2:
## print IndexFiles.__doc__
## sys.exit(1)
lucene.initVM() #初始化Java虚拟机
print 'lucene', lucene.VERSION
start = datetime.now()
try:
## IndexFiles(sys.argv[1], "index", lucene.StandardAnalyzer(lucene.Version.LUCENE_CURRENT))
# IndexFiles('html', "index", lucene.StandardAnalyzer(lucene.Version.LUCENE_CURRENT))
IndexFiles('html', "index for pic", lucene.WhitespaceAnalyzer(lucene.Version.LUCENE_CURRENT))
end = datetime.now()
print end - start
except Exception, e:
print "Failed: ", e
