From 09e748fa4c1785ba8a21ccac13bb693555d6c57b Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Thu, 21 Jun 2018 23:02:41 +0200
Subject: Refactor how offices files are handled

- xml files are no longer considered harmless
- Factorization of the `remove_all` method for office files
- Explicit whitelist are used
- Blacklist are used to skip files completely
  - Non-blacklisted files are _still cleaned_
  - Unsupported files are still triggering an error
---
 libmat2/harmless.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'libmat2/harmless.py')

diff --git a/libmat2/harmless.py b/libmat2/harmless.py
index 54737a8..2878571 100644
--- a/libmat2/harmless.py
+++ b/libmat2/harmless.py
@@ -4,7 +4,7 @@ from . import abstract
 
 class HarmlessParser(abstract.AbstractParser):
     """ This is the parser for filetypes that do not contain metadata. """
-    mimetypes = {'application/xml', 'text/plain', 'text/xml', 'application/rdf+xml'}
+    mimetypes = {'text/plain', }
 
     def __init__(self, filename: str) -> None:
         super().__init__(filename)
-- 
cgit v1.3