1 # ====================================================================
2 # Licensed under the Apache License, Version 2.0 (the "License");
3 # you may not use this file except in compliance with the License.
4 # You may obtain a copy of the License at
6 # http://www.apache.org/licenses/LICENSE-2.0
8 # Unless required by applicable law or agreed to in writing, software
9 # distributed under the License is distributed on an "AS IS" BASIS,
10 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
11 # See the License for the specific language governing permissions and
12 # limitations under the License.
13 # ====================================================================
15 from lucene import PythonTokenFilter
18 # A TokenFilter extension
21 class PositionalStopFilter(PythonTokenFilter):
23 def __init__(self, tokenStream, stopWords):
25 super(PositionalStopFilter, self).__init__(tokenStream)
27 self.input = tokenStream
28 self.stopWords = stopWords
34 for token in self.input:
35 if not token.termText() in self.stopWords:
36 token.setPositionIncrement(token.getPositionIncrement() +