def test_unique_uuid(self):
test_file = settings.PROJECT_DIR + "/sb_news/tests/sample_json/" \
"uuid_unique.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
self.assertEqual(len(NewsArticle.nodes.all()), 2)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "862248ce467c25d9fa20d66e43f13d7f0800882b"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c11407c888ddbfedca4a56b1aac482d153ad6039"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
def test_too_close_to_another_article_title(self):
test_file = settings.PROJECT_DIR + \
"/sb_news/tests/sample_json/" \
"too_close_to_another_article_title.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
self.assertEqual(len(NewsArticle.nodes.all()), 2)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "862248ce467c25d9fa20d66e43f13d7f0800882b"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "682408ea92f61d5a44de67ed2aaef7369c401bce"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
def test_too_close_to_another_article_content(self):
test_file = settings.PROJECT_DIR + \
"/sb_news/tests/sample_json/" \
"too_close_to_another_article_content.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
self.assertEqual(len(NewsArticle.nodes.all()), 2)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "188ed9cfc6e2214c067ad8e46ec6cd10e392646e"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c11407c888ddbfedca4a56b1aac482d153ad6039"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c11407c888ddbfedca4a56b1aac482d153ad6039"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNotNone(res.one)
def test_title_unique(self):
test_file = settings.PROJECT_DIR + "/sb_news/tests/sample_json/" \
"title_unique.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
query = 'MATCH (a:NewsArticle {title: ' \
'"Sanders\' American Dream Is In Denmark"}) RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(len(res), 1)
query = 'MATCH (a:NewsArticle {title: ' \
'"ISIS Inc: How Oil Fuels The Jihadi Terrorists - ' \
'ft.com"}) RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(len(res), 1)
query = 'MATCH (a:NewsArticle {title: ' \
'"Breaking: Donald Trump Stuns With ' \
'Announcement Of Foreign Policy Dream Team"}) RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(len(res), 1)
def test_detail(self):
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
self.client.force_authenticate(user=self.user)
url = reverse('news-list')
data = {
"provider":
"sb_crawler",
"external_id":
str(uuid1()),
"url":
"https://www.sagebrew.com",
"site_full":
"https://www.sagebrew.com",
"site_section":
"site_section",
"title":
"This is the title",
"content":
"This is some fake content",
"title_full":
"A full title",
"language":
"en",
"published":
datetime.now(pytz.utc),
"country":
"US",
"spam_score":
0.0,
"image":
"https://sagebrew-master.s3.amazonaws.com/"
"profile_pictures/"
"8a274be8-71ee-259c-32fc-c3269a5adf9b-198x200.png",
"performance_score":
10,
"crawled":
datetime.now(pytz.utc),
}
response = self.client.post(url, data=data, format='json')
url = reverse('news-detail',
kwargs={"object_uuid": response.data['id']})
response = self.client.get(url, format='json')
self.assertEqual(response.data['title'], 'This Is The Title')
self.assertEqual(response.status_code, status.HTTP_200_OK)
def test_excluded_titles(self):
test_file = settings.PROJECT_DIR + "/sb_news/tests/sample_json/" \
"exclude_titles.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
self.assertEqual(len(NewsArticle.nodes.all()), 0)
def test_title_reformat(self):
test_file = settings.PROJECT_DIR + "/sb_news/tests/sample_json/" \
"title_reformat.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c7dd81cf775476d17fd9effe3a43d13d060eb2c8"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(
res.one['title'], "Obama's Team Welcomes Castro "
"& Cuba To America & To Receive "
"Criticism: 'Wouldn't Disagree'..."
"DNC; DNC: DNC. Dncabc DNC")
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c294037cba0aad280b655614c5c776f1c5b453ce"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(res.one['title'], "Friends Of Israel - "
"The New Yorker")
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c6dd81cf775476d17fd9effe3a43d13d060eb2c8"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(
res.one['title'], "What's This Another New "
"US USA U.S. U.S.A. Title It's A "
"Miracle...")
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c8dd81cf775476d17fd9effe3a43d13d060eb2c8"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(res.one['title'], "Yet Another Title! What Is This!")
def test_site_not_supported(self):
test_file = settings.PROJECT_DIR + "/sb_news/tests/sample_json/" \
"site_not_supported.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
query = 'MATCH (a:NewsArticle) RETURN a'
res, _ = db.cypher_query(query)
self.assertIsNone(res.one)
def test_quote_query(self):
test_file = settings.PROJECT_DIR + "/sb_news/tests/sample_json/" \
"quote_query.json"
query = 'MATCH (a:NewsArticle) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query2 = 'MATCH (a:Tag) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
query3 = 'MATCH (a:UploadedObject) OPTIONAL MATCH (a)-[r]-() ' \
'DELETE a, r'
db.cypher_batch_query([(query, {}), (query2, {}), (query3, {})])
tag = Tag(name="science").save()
results = gather_news_results(None, test_file)
query_webhose(results, tag)
tag.delete()
query = 'MATCH (a:NewsArticle ' \
'{external_id: "c8a3179934b6d4609632383add7fb27ddf3d3842"}) ' \
'RETURN a'
res, _ = db.cypher_query(query)
self.assertEqual(
res.one['title'], "Breaking: Donald Trump Stuns "
"With Announcement Of Foreign "
"Policy Dream Team")