diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,14 +1,15 @@
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v2.4.0
+  rev: fd9a0c6cfd9f74f38f05161de5e860ba924baf58
   hooks:
   - id: trailing-whitespace
   - id: flake8
+    args: [--ignore=TYP101]
   - id: check-json
   - id: check-yaml
 
 - repo: https://github.com/codespell-project/codespell
-  rev: v1.16.0
+  rev: 40ba097529c8a37e30184300b814c93bfd2e2a54
   hooks:
   - id: codespell
     exclude: ^(swh/indexer/data/codemeta/crosswalk.csv)$
diff --git a/swh/indexer/mimetype.py b/swh/indexer/mimetype.py
--- a/swh/indexer/mimetype.py
+++ b/swh/indexer/mimetype.py
@@ -1,11 +1,11 @@
-# Copyright (C) 2016-2018  The Software Heritage developers
+# Copyright (C) 2016-2020 The Software Heritage developers
 # See the AUTHORS file at the top-level directory of this distribution
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 import magic
 
-from typing import Optional
+from typing import Optional, Dict, Any, List, Tuple, Iterator
 
 from .indexer import ContentIndexer, ContentRangeIndexer
 
@@ -15,7 +15,7 @@
         'was imported instead.')
 
 
-def compute_mimetype_encoding(raw_content):
+def compute_mimetype_encoding(raw_content: bytes) -> Dict[str, bytes]:
     """Determine mimetype and encoding from the raw content.
 
     Args:
@@ -36,6 +36,8 @@
 
 
 class MixinMimetypeIndexer:
+    tool: Dict[str, Any]
+    idx_storage: Any
     """Mixin mimetype indexer.
 
     See :class:`MimetypeIndexer` and :class:`MimetypeRangeIndexer`
@@ -55,7 +57,7 @@
 
     CONFIG_BASE_FILENAME = 'indexer/mimetype'  # type: Optional[str]
 
-    def index(self, id, data):
+    def index(self, id: bytes, data: bytes) -> Dict[str, Any]:
         """Index sha1s' content and store result.
 
         Args:
@@ -74,10 +76,11 @@
         properties.update({
             'id': id,
             'indexer_configuration_id': self.tool['id'],
-            })
+        })
         return properties
 
-    def persist_index_computations(self, results, policy_update):
+    def persist_index_computations(self, results: List[Dict[str, Any]],
+                                   policy_update: List[str]) -> None:
         """Persist the results in storage.
 
         Args:
@@ -104,7 +107,8 @@
     - stores result in storage
 
     """
-    def filter(self, ids):
+    def filter(self, ids: Dict[str, bytes]) -> Iterator[Tuple
+                                                        [bytes, int]]:
         """Filter out known sha1s and return only missing ones.
 
         """
@@ -128,7 +132,11 @@
     - stores result in storage
 
     """
-    def indexed_contents_in_range(self, start, end):
+
+    def indexed_contents_in_range(self,
+                                  start: bytes,
+                                  end: bytes
+                                  ) -> Dict['str', Optional[bytes]]:
         """Retrieve indexed content id within range [start, end].
 
         Args: