Start removing mocks for the mimetype indexer.

swh/indexer/storage/in_memory.py

@@ -102,10 +102,62 @@ class IndexerStorage:
 
     def __init__(self):
         self._tools = {}
+        self._mimetypes = SubStorage(self._tools)
         self._content_ctags = SubStorage(self._tools)
         self._content_metadata = SubStorage(self._tools)
         self._revision_metadata = SubStorage(self._tools)
 
+    def content_mimetype_missing(self, mimetypes):
+        """Generate mimetypes missing from storage.
+
+        Args:
+            mimetypes (iterable): iterable of dict with keys:
+
+              - **id** (bytes): sha1 identifier
+              - **indexer_configuration_id** (int): tool used to compute the
+                results
+
+        Yields:
+            tuple (id, indexer_configuration_id): missing id
+
+        """
+        yield from self._mimetypes.missing(mimetypes)
+
+    def content_mimetype_add(self, mimetypes, conflict_update=False):
+        """Add mimetypes not present in storage.
+
+        Args:
+            mimetypes (iterable): dictionaries with keys:
+
+              - **id** (bytes): sha1 identifier
+              - **mimetype** (bytes): raw content's mimetype
+              - **encoding** (bytes): raw content's encoding
+              - **indexer_configuration_id** (int): tool's id used to
+                compute the results
+              - **conflict_update** (bool): Flag to determine if we want to
+                overwrite (``True``) or skip duplicates (``False``, the
+                default)
+
+        """
+        self._mimetypes.add(mimetypes, conflict_update)
+
+    def content_mimetype_get(self, ids, db=None, cur=None):
+        """Retrieve full content mimetype per ids.
+
+        Args:
+            ids (iterable): sha1 identifier
+
+        Yields:
+            mimetypes (iterable): dictionaries with keys:
+
+                - **id** (bytes): sha1 identifier
+                - **mimetype** (bytes): raw content's mimetype
+                - **encoding** (bytes): raw content's encoding
+                - **tool** (dict): Tool used to compute the language
+
+        """
+        yield from self._mimetypes.get(ids)
+
     def content_ctags_missing(self, ctags):
         """List ctags missing from storage.
 

swh/indexer/tests/storage/test_in_memory.py

@@ -17,22 +17,6 @@ class IndexerTestInMemoryStorage(CommonTestStorage, TestCase):
     def test_check_config(self):
         pass
 
-    @pytest.mark.xfail
-    def test_content_mimetype_missing(self):
-        pass
-
-    @pytest.mark.xfail
-    def test_content_mimetype_add__drop_duplicate(self):
-        pass
-
-    @pytest.mark.xfail
-    def test_content_mimetype_add__update_in_place_duplicate(self):
-        pass
-
-    @pytest.mark.xfail
-    def test_content_mimetype_get(self):
-        pass
-
     @pytest.mark.xfail
     def test_content_language_missing(self):
         pass

swh/indexer/tests/test_mimetype.py

@@ -4,7 +4,6 @@
 # See top-level LICENSE file for more information
 
 import unittest
-import logging
 
 from unittest.mock import patch
 
@@ -61,12 +60,6 @@ class MimetypeTestIndexer(MimetypeIndexer):
             },
         }
 
-    def prepare(self):
-        super().prepare()
-        self.idx_storage = BasicMockIndexerStorage()
-        self.log = logging.getLogger('swh.indexer')
-        self.objstorage = MockObjStorage()
-
 
 class TestMimetypeIndexer(CommonContentIndexerTest, unittest.TestCase):
     """Mimetype indexer test scenarios:
@@ -75,8 +68,13 @@ class TestMimetypeIndexer(CommonContentIndexerTest, unittest.TestCase):
     - Unknown sha1 in the input list are not indexed
 
     """
+
+    def get_indexer_results(self, ids):
+        yield from self.idx_storage.content_mimetype_get(ids)
+
     def setUp(self):
         self.indexer = MimetypeTestIndexer()
+        self.idx_storage = self.indexer.idx_storage
 
         self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5'
         self.id1 = '688a5ef812c53907562fe379d4b3851e69c7cb15'