wbnews 1.55.8__py2.py3-none-any.whl → 1.55.10rc0__py2.py3-none-any.whl

wbnews/import_export/parsers/emails/utils.py

@@ -22,10 +22,10 @@ class EmlContentParser:
         html = self.get_html(self.message)
         return html.decode(self.encoding) if html else None
 
-    def get_html(cls, parsed: message.Message) -> bytes | None:
+    def get_html(self, parsed: message.Message) -> bytes | None:
         if parsed.is_multipart():
             for item in parsed.get_payload():  # type:message.Message
-                if html := cls.get_html(item):
+                if html := self.get_html(item):
                     return html
         elif parsed.get_content_type() == "text/html":
             return parsed.get_payload(decode=True)

wbnews/models/news.py

@@ -81,7 +81,8 @@ class News(ImportMixin, WBModel):
         """
         tasks = []
         for sender, task_signature in create_news_relationships.send(sender=News, instance=self):
-            assert isinstance(task_signature, Signature), self.errors["relationship_signal"].format(sender)
+            if not isinstance(task_signature, Signature):
+                raise AssertionError(self.errors["relationship_signal"].format(sender))
             tasks.append(task_signature)
         if tasks:
             res = chord(tasks, create_relationship.s(self.id))

wbnews/tests/parsers/test_emails.py

@@ -1,5 +1,4 @@
-from unittest import mock
-from unittest.mock import patch, PropertyMock
+from unittest.mock import PropertyMock, patch
 
 import pytest
 
@@ -7,19 +6,20 @@ from wbnews.import_export.parsers.emails.utils import EmlContentParser
 
 
 class TestEmlContentParser:
-
     @pytest.fixture
     def content_parser(self):
-        parser = EmlContentParser(b'')
+        parser = EmlContentParser(b"")
         parser.message = {"From": "main@acme.com"}
         return parser
 
     @patch.object(EmlContentParser, "text", new_callable=PropertyMock)
     def test_source_from_in_text(self, mock_text, content_parser):
-        mock_text.return_value = "some random email content with a From field From: source name <email@test.com> and the rest of the email"
+        mock_text.return_value = (
+            "some random email content with a From field From: source name <email@test.com> and the rest of the email"
+        )
         assert content_parser.source == {"title": "Source Name", "endpoint": "email@test.com", "type": "EMAIL"}
 
     @patch.object(EmlContentParser, "text", new_callable=PropertyMock)
-    def test_source_from_in_text(self, mock_text, content_parser):
+    def test_source_from_in_text_alt(self, mock_text, content_parser):
         mock_text.return_value = "some random email content without a From field"
         assert content_parser.source == {"title": "Acme.Com", "endpoint": "main@acme.com", "type": "EMAIL"}

wbnews/tests/test_models.py

@@ -1,14 +1,15 @@
-from datetime import timedelta, datetime, timezone
-from django.utils import timezone as django_timezone
+from datetime import timedelta, timezone
 from unittest.mock import patch
 
 import pytest
+from django.utils import timezone as django_timezone
+from faker import Faker
 
 from wbnews.models import News, NewsSource
-from faker import Faker
 
 fake = Faker()
 
+
 @pytest.mark.django_db
 class TestSource:
     @pytest.mark.parametrize("news_source__title", ["source1"])
@@ -19,17 +20,19 @@ class TestSource:
         ns1 = news_source_factory.create()
         ns2 = news_source_factory.create()
 
-        assert NewsSource.source_dict_to_model({"id": ns1.id, "identifier": ns2.identifier}) == ns1 # priority to "id"
-        assert NewsSource.source_dict_to_model({"endpoint": ns1.endpoint, "identifier": ns2.identifier}) == ns2 # priority to "identifier"
-        assert NewsSource.source_dict_to_model({"endpoint": ns2.endpoint}) == ns2 # exact match on endpoint
+        assert NewsSource.source_dict_to_model({"id": ns1.id, "identifier": ns2.identifier}) == ns1  # priority to "id"
+        assert (
+            NewsSource.source_dict_to_model({"endpoint": ns1.endpoint, "identifier": ns2.identifier}) == ns2
+        )  # priority to "identifier"
+        assert NewsSource.source_dict_to_model({"endpoint": ns2.endpoint}) == ns2  # exact match on endpoint
 
         ns1.endpoint = ".*@test.com"
         ns1.save()
-        assert NewsSource.source_dict_to_model({"endpoint": "abc@test.com"}) == ns1 # regex match on endpoint
+        assert NewsSource.source_dict_to_model({"endpoint": "abc@test.com"}) == ns1  # regex match on endpoint
 
         new_source = NewsSource.source_dict_to_model({"endpoint": "abc@main_source.com", "title": "New Source"})
         assert new_source not in [ns1, ns2]
-        assert new_source.endpoint == ".*@main_source\.com"
+        assert new_source.endpoint == r".*@main_source\.com"
         assert new_source.title == "New Source"
         assert new_source.author == "Main Source"
 
@@ -45,24 +48,31 @@ class TestNews:
 
     def test_get_default_guid(self):
         assert News.get_default_guid("This is a title", None) == "this-is-a-title"
-        assert News.get_default_guid("This is a title", "http://mylink.com") == "http://mylink.com" # link takes precendence
+        assert (
+            News.get_default_guid("This is a title", "http://mylink.com") == "http://mylink.com"
+        )  # link takes precendence
         assert News.get_default_guid("a" * 24, None, max_length=20) == "a" * 20
 
     def test_future_news(self, news_factory):
         # ensure a future datetime always default to now
         now = django_timezone.now()
         future_news = news_factory.create(datetime=now + timedelta(days=1))
-        assert (future_news.datetime - now).seconds < 1 # we do that to account for clock difference
+        assert (future_news.datetime - now).seconds < 1  # we do that to account for clock difference
 
     @patch("wbnews.models.news.detect_near_duplicates")
     def test_handle_duplicates(self, mock_fct, news_factory):
         val_date = fake.date_time(tzinfo=timezone.utc)
-        n0 = news_factory.create(datetime=val_date - timedelta(days=1)) # we exclude this news from the duplicate search
+        n0 = news_factory.create(
+            datetime=val_date - timedelta(days=1)
+        )  # we exclude this news from the duplicate search
         n1 = news_factory.create(datetime=val_date)
         n2 = news_factory.create(datetime=val_date)
         n3 = news_factory.create(datetime=val_date)
 
-        mock_fct.return_value = [n0.id, n3.id] # n0 is considered as duplicate but does not fall within the specified daterange so it will not be marked
+        mock_fct.return_value = [
+            n0.id,
+            n3.id,
+        ]  # n0 is considered as duplicate but does not fall within the specified daterange so it will not be marked
         News.handle_duplicates(val_date, val_date)
 
         n3.refresh_from_db()

wbnews/utils.py

@@ -11,7 +11,7 @@ logger = logging.getLogger("news")
 
 def _get_similarity_matrix_df(data: dict[int, str]) -> pd.DataFrame:
     # Convert texts to TF-IDF vectors
-    ids, texts = zip(*data.items())
+    ids, texts = zip(*data.items(), strict=False)
     vectorizer = TfidfVectorizer()
     tfidf_matrix = vectorizer.fit_transform(texts)
     # Compute pairwise cosine similarity...

{wbnews-1.55.8.dist-info → wbnews-1.55.10rc0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wbnews
-Version: 1.55.8
+Version: 1.55.10rc0
 Summary: A workbench module for managing news.
 Author-email: Christopher Wittlinger <c.wittlinger@stainly.com>
 Requires-Dist: feedparser==6.*

{wbnews-1.55.8.dist-info → wbnews-1.55.10rc0.dist-info}/RECORD

@@ -7,7 +7,7 @@ wbnews/serializers.py,sha256=KihExQ_GS1fNZnojryEcfU32xlTiPn-K2WGO0Zc84Cw,4732
 wbnews/signals.py,sha256=eqipwffwJnDQWUZ9VTKr5Jp-OMXLmVSNwoIsawnCKvM,192
 wbnews/tasks.py,sha256=ce9JbXKnJnf7La74h0LPwm3yrygHNe1BKZju_4m1itw,384
 wbnews/urls.py,sha256=2Gs9RGU8x6tNOLJiuG17n_ik82QVb8jlw7bU07Lk_S4,1008
-wbnews/utils.py,sha256=LFB9vDP4j5DK040drwHeNHK5Dl8Mf4NvDOVrjPjTXhw,1941
+wbnews/utils.py,sha256=h4TdMbUL0qQ2h3o3jEpGuGwT90TWiryVRtBXc7avLW0,1955
 wbnews/filters/__init__.py,sha256=FXJcPsLQePCU-fzjpIu44Dsdu9vCckLHr0Kr-8Z_-C4,59
 wbnews/filters/news.py,sha256=dUBe9H7gvkwOmHb6roCeu9b_0mZdhnRCvaHuUGGESTA,1725
 wbnews/fixtures/wbnews.yaml,sha256=cDu1UWYwIFxz-hdivW7rxLYsNOweBm4GdN1GDsycN90,173164
@@ -19,7 +19,7 @@ wbnews/import_export/handlers/news.py,sha256=cdrtWIP3XOU8NMYZKF8VLYH5qHmPLboUm_G
 wbnews/import_export/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wbnews/import_export/parsers/emails/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wbnews/import_export/parsers/emails/news.py,sha256=8fSgjSPuSmdfGKV1IxLMWriqGhDAG-tiZUyAgWpjZ_M,1236
-wbnews/import_export/parsers/emails/utils.py,sha256=cdlq1hMbVYDzhB7qyXOvZNBPBeKhKwmuSHvfW18bWxM,2205
+wbnews/import_export/parsers/emails/utils.py,sha256=k7R1HZx18FKXRq10COARFgHjjBadsWe1DY3AHCrwHRs,2207
 wbnews/import_export/parsers/rss/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wbnews/import_export/parsers/rss/news.py,sha256=H89avqOU_AUAyHiIXd_tfoMbcqy67GgDQ2-ucihDpks,2076
 wbnews/locale/de/LC_MESSAGES/django.mo,sha256=M70N6el-I7EymxHLw9n773Bimbztf8s8equWa9SydBs,1283
@@ -41,18 +41,18 @@ wbnews/migrations/0013_alter_news_datetime.py,sha256=q4Gbxo25jClsv9b1kfTqBLmpPNH
 wbnews/migrations/0014_newsrelationship_unique_news_relationship.py,sha256=aZUHLMKRMaXHJrrbnV9O2ZJRDVjbpkb9NjVPB7VKVW0,1073
 wbnews/migrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wbnews/models/__init__.py,sha256=KKIcQbpCPCVNJUPJs2MtpN9Q2Wb34Qdk-C7w6AAOy7w,99
-wbnews/models/news.py,sha256=PJFcG5WFBkEkfnxkLLMqyCz9cLq0fkwuPlgYVyK2i44,5165
+wbnews/models/news.py,sha256=yRbOpVG69yssvJPzv9bZJGMoFcb9n2uLaG2mz2j8oxM,5203
 wbnews/models/relationships.py,sha256=bcQbRa-ObS9h67pIuIrodD63RnkzbaOaRT4L6ctBoI0,1841
 wbnews/models/sources.py,sha256=N3-rBg4myeGG_stHvKiNnSoH0yS-LS_Zr_UeKPMBr5s,2629
 wbnews/models/utils.py,sha256=1JQxV4WxmmFGl7MdVtJoEeao3vnqqVwCi7mhSToaUvM,600
 wbnews/models/llm/cleaned_news.py,sha256=PA0McsgMmR0TOZUNWs55sBnsCXGbaC61VtVFbJ8vx28,2226
 wbnews/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wbnews/tests/conftest.py,sha256=UEZOYH5Av-Cqqq5t8WQCR7QJdNnajhthBPpF8AnwQjY,186
-wbnews/tests/test_models.py,sha256=99npnSWhqfspxizaWa5Ay4JY84ziGy64_BnKj8Tmol8,3173
+wbnews/tests/test_models.py,sha256=op79cYyz9f5dX1uRBztw-E0J4HYAY8K-7cz4kBCN0qk,3278
 wbnews/tests/test_utils.py,sha256=PsyHH_F_y-Uy3mdVgDINH19bPEd1bmZT_UQ7yu87BNU,278
 wbnews/tests/tests.py,sha256=OADY-vbKZBe0bjjVEO1KNzRYAP2JA9mWkO9pZuh1TSs,280
 wbnews/tests/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wbnews/tests/parsers/test_emails.py,sha256=uFg9eErF3gzyc6zULnUq-3p6O3rg1HBAlb59Lw4CWSk,1072
+wbnews/tests/parsers/test_emails.py,sha256=dStdTPI7Ns1jSw5PDbDEc84FJaoNPnBHC4BskWDDMxY,1073
 wbnews/viewsets/__init__.py,sha256=2OhRiJy0MVK9TdMpFmS9x9jl_gM-CjBxUoUHlZB3_8U,531
 wbnews/viewsets/buttons.py,sha256=6m_IdRYCQgTH4mD51DUoOa8Vx1y1-2zPQydUdvL_nF4,1788
 wbnews/viewsets/display.py,sha256=fwMZLlwxHcNHM4AppwYpYTOicLD_pXaQ4QeFeIl4whk,5315
@@ -60,6 +60,6 @@ wbnews/viewsets/endpoints.py,sha256=2slGDJin_SA2heWsIaMdNTUN46FqZJvusbY1jhAaeZM,
 wbnews/viewsets/menu.py,sha256=XTShfTIykN9t7oclosPfFVb1r6o46QyglEEe1C7QCMk,979
 wbnews/viewsets/titles.py,sha256=iMyiGBMBpzng8s2ySVLqEOwueHRnAoEuc75dt9nCPjc,1367
 wbnews/viewsets/views.py,sha256=SMCDT6bJMQblyqX5cQ7X3qDe0zxTVWh1q7Aqj0fBo2Q,6795
-wbnews-1.55.8.dist-info/METADATA,sha256=OJtbdn_uIlBNiF-D8vM-V1lLqG__8Vx4wq2gm5e8o8M,215
-wbnews-1.55.8.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-wbnews-1.55.8.dist-info/RECORD,,
+wbnews-1.55.10rc0.dist-info/METADATA,sha256=YC09A_gCfCr-QWF6MLLeF2wvCddlQA-XKMPtF4zBVlA,219
+wbnews-1.55.10rc0.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+wbnews-1.55.10rc0.dist-info/RECORD,,