Page Menu
Home
Software Heritage
Search
Configure Global Search
Log In
Files
F7343109
D789.id.diff
No One
Temporary
Actions
View File
Edit File
Delete File
View Transforms
Subscribe
Mute Notifications
Award Token
Flag For Later
Size
4 KB
Subscribers
None
D789.id.diff
View Options
diff --git a/swh/indexer/storage/in_memory.py b/swh/indexer/storage/in_memory.py
--- a/swh/indexer/storage/in_memory.py
+++ b/swh/indexer/storage/in_memory.py
@@ -170,6 +170,7 @@
def __init__(self):
self._tools = {}
self._mimetypes = SubStorage(self._tools)
+ self._languages = SubStorage(self._tools)
self._content_ctags = SubStorage(self._tools)
self._licenses = SubStorage(self._tools)
self._content_metadata = SubStorage(self._tools)
@@ -253,6 +254,55 @@
"""
yield from self._mimetypes.get(ids)
+ def content_language_missing(self, languages):
+ """List languages missing from storage.
+
+ Args:
+ languages (iterable): dictionaries with keys:
+
+ - **id** (bytes): sha1 identifier
+ - **indexer_configuration_id** (int): tool used to compute
+ the results
+
+ Yields:
+ an iterable of missing id for the tuple (id,
+ indexer_configuration_id)
+
+ """
+ yield from self._languages.missing(languages)
+
+ def content_language_get(self, ids):
+ """Retrieve full content language per ids.
+
+ Args:
+ ids (iterable): sha1 identifier
+
+ Yields:
+ languages (iterable): dictionaries with keys:
+
+ - **id** (bytes): sha1 identifier
+ - **lang** (bytes): raw content's language
+ - **tool** (dict): Tool used to compute the language
+
+ """
+ yield from self._languages.get(ids)
+
+ def content_language_add(self, languages, conflict_update=False):
+ """Add languages not present in storage.
+
+ Args:
+ languages (iterable): dictionaries with keys:
+
+ - **id** (bytes): sha1
+ - **lang** (bytes): language detected
+
+ conflict_update (bool): Flag to determine if we want to
+ overwrite (true) or skip duplicates (false, the
+ default)
+
+ """
+ self._languages.add(languages, conflict_update)
+
def content_ctags_missing(self, ctags):
"""List ctags missing from storage.
diff --git a/swh/indexer/tests/storage/test_in_memory.py b/swh/indexer/tests/storage/test_in_memory.py
--- a/swh/indexer/tests/storage/test_in_memory.py
+++ b/swh/indexer/tests/storage/test_in_memory.py
@@ -21,22 +21,6 @@
pass
@pytest.mark.xfail
- def test_content_language_missing(self):
- pass
-
- @pytest.mark.xfail
- def test_content_language_get(self):
- pass
-
- @pytest.mark.xfail
- def test_content_language_add__drop_duplicate(self):
- pass
-
- @pytest.mark.xfail
- def test_content_language_add__update_in_place_duplicate(self):
- pass
-
- @pytest.mark.xfail
def test_origin_intrinsic_metadata_get(self):
pass
diff --git a/swh/indexer/tests/test_language.py b/swh/indexer/tests/test_language.py
--- a/swh/indexer/tests/test_language.py
+++ b/swh/indexer/tests/test_language.py
@@ -7,8 +7,8 @@
from swh.indexer import language
from swh.indexer.language import LanguageIndexer
from swh.indexer.tests.test_utils import (
- BasicMockIndexerStorage, MockObjStorage, CommonContentIndexerTest,
- CommonIndexerWithErrorsTest, CommonIndexerNoTool, BASE_TEST_CONFIG
+ CommonContentIndexerTest, CommonIndexerWithErrorsTest,
+ CommonIndexerNoTool, BASE_TEST_CONFIG, fill_storage, fill_obj_storage
)
@@ -30,12 +30,6 @@
}
}
- def prepare(self):
- super().prepare()
- self.idx_storage = BasicMockIndexerStorage()
- self.objstorage = MockObjStorage()
- self.tool_config = self.config['tools']['configuration']
-
class Language(unittest.TestCase):
"""Tests pygments tool for language detection
@@ -60,8 +54,14 @@
- Unknown sha1 in the input list are not indexed
"""
+
+ def get_indexer_results(self, ids):
+ yield from self.indexer.idx_storage.content_language_get(ids)
+
def setUp(self):
self.indexer = LanguageTestIndexer()
+ fill_storage(self.indexer.storage)
+ fill_obj_storage(self.indexer.objstorage)
self.id0 = '02fb2c89e14f7fab46701478c83779c7beb7b069'
self.id1 = '103bc087db1d26afc3a0283f38663d081e9b01e6'
File Metadata
Details
Attached
Mime Type
text/plain
Expires
Mar 17 2025, 7:26 PM (7 w, 3 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3220857
Attached To
D789: Remove languages mock.
Event Timeline
Log In to Comment