1
1
# ====================================================================
2
# Copyright (c) 2004-2007 Open Source Applications Foundation.
4
# Permission is hereby granted, free of charge, to any person obtaining a
5
# copy of this software and associated documentation files (the "Software"),
6
# to deal in the Software without restriction, including without limitation
7
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
8
# and/or sell copies of the Software, and to permit persons to whom the
9
# Software is furnished to do so, subject to the following conditions:
11
# The above copyright notice and this permission notice shall be included
12
# in all copies or substantial portions of the Software.
14
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
15
# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
17
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
18
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
19
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
20
# DEALINGS IN THE SOFTWARE.
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.
21
13
# ====================================================================
24
15
# This sample illustrates how to write an Analyzer 'extension' in Python.
46
37
def tokenStream(self, fieldName, reader):
48
result = StandardTokenizer(reader)
39
result = StandardTokenizer(Version.LUCENE_CURRENT, reader)
49
40
result = StandardFilter(result)
50
41
result = LowerCaseFilter(result)
51
42
result = PorterStemFilter(result)
52
result = StopFilter(result, StopAnalyzer.ENGLISH_STOP_WORDS)
43
result = StopFilter(True, result, StopAnalyzer.ENGLISH_STOP_WORDS_SET)