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 InputStreamReader
21 class PDFHandler(object):
23 def indexFile(self, writer, path):
28 process = popen2.Popen4(["pdfinfo", "-enc", "UTF-8", path])
33 line = process.fromchild.readline().strip()
36 name, value = line.split(':', 1)
37 doc.add(Field(name.strip(), value.strip(),
38 Field.Store.YES, Field.Index.NOT_ANALYZED))
40 exitCode = process.wait()
42 raise RuntimeError, "pdfinfo exit code %d" %(exitCode)
45 process = popen2.Popen4(["pdftotext", "-enc", "UTF-8", path, "-"])
46 string = InputStreamReader(process.fromchild, 'utf-8').read()
50 doc.add(Field("contents", StringReader(string)))
51 doc.add(Field("filename", os.path.abspath(path),
52 Field.Store.YES, Field.Index.NOT_ANALYZED))
53 writer.addDocument(doc)
55 exitCode = process.wait()
57 raise RuntimeError, "pdftotext exit code %d" %(exitCode)