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 # ====================================================================
17 from lucene import Document, Field, StringReader
18 from lia.util.Streams import HTMLReader, InputStreamReader
21 class HTMLHandler(object):
23 def indexFile(self, writer, path):
27 string = HTMLReader(InputStreamReader(file, 'utf-8')).read()
33 doc.add(Field("contents", StringReader(string)))
34 doc.add(Field("filename", os.path.abspath(path),
35 Field.Store.YES, Field.Index.NOT_ANALYZED))
36 writer.addDocument(doc)