added file type checks to the parsers to prevent temporary files from being consumed. Also: parsers announce file types they wish to use as default for each mime type.

src/documents/models.py

@@ -1,7 +1,6 @@
 # coding=utf-8
 
 import logging
-import mimetypes
 import os
 import re
 from collections import OrderedDict
@@ -12,6 +11,8 @@ from django.db import models
 from django.utils import timezone
 from django.utils.text import slugify
 
+from documents.parsers import get_default_file_extension
+
 
 class MatchingModel(models.Model):
 
@@ -230,8 +231,7 @@ class Document(models.Model):
 
     @property
     def file_type(self):
-        # TODO: this is not stable across python versions
-        return mimetypes.guess_extension(str(self.mime_type))
+        return get_default_file_extension(self.mime_type)
 
     @property
     def thumbnail_path(self):