前一段时间做东西用到了pylucene,包括建立索引,检索,高亮显示等等。贴两段代码,希望对大家有用。
pylucene的安装就不多说了,我用的版本是PyLucene-1.9.1。
建立索引:
#
!/usr/bin/env python
import os
import PyLucene
class IndexFiles:
"""
create index by PyLucene, just need your dir path,
the result files saved in the directory index in
current path
"""
def __init__ (self, root, storeDir, analyzer):
if not os.path.exists(storeDir):
os.mkdir(storeDir)
analyzer = PyLucene.StandardAnalyzer()
store = PyLucene.FSDirectory.getDirectory(storeDir , True)
writer = PyLucene.IndexWriter(store, analyzer, True)
self.indexDocs(root, writer)
print ' optimizing index ' ,
writer.optimize()
writer.close()
print ' done '
def indexDocs(self, root, writer):
for root, dirnames, filenames in os.walk(root):
for filename in filenames:
if no
import os
import PyLucene
class IndexFiles:
"""
create index by PyLucene, just need your dir path,
the result files saved in the directory index in
current path
"""
def __init__ (self, root, storeDir, analyzer):
if not os.path.exists(storeDir):
os.mkdir(storeDir)
analyzer = PyLucene.StandardAnalyzer()
store = PyLucene.FSDirectory.getDirectory(storeDir , True)
writer = PyLucene.IndexWriter(store, analyzer, True)
self.indexDocs(root, writer)
print ' optimizing index ' ,
writer.optimize()
writer.close()
print ' done '
def indexDocs(self, root, writer):
for root, dirnames, filenames in os.walk(root):
for filename in filenames:
if no