Esempio n. 1
0
    def test_elastic_hash(self):
        """Can we reproduce a hash from elastic data alone?"""
        article = Article(**{
            "date": datetime.date(2015, 1, 1),
            "section": "\u6f22\u5b57",
            "pagenr": 1928390,
            "headline": "Headline hier.",
            "byline": "byline..",
            "length": 1928,
            "metastring": "Even more strange characters.. \x0C ..",
            "url": "https://example.com",
            "externalid": None,
            "author": None,
            "addressee": "Hmm",
            "text": "Contains invalid char \x08 woo",
            "medium": create_test_medium(name="abc."),
            "project": create_test_project()
        })

        article.save()

        es = ES()
        es.add_articles([article.id])
        hash = get_article_dict(article)["hash"]
        es.flush()

        es_articles = es.query_all(filters={"ids": [article.id]}, fields=HASH_FIELDS + ["hash"])
        es_article = list(es_articles)[0]

        self.assertEqual(article.id, es_article.id)
        self.assertEqual(hash, es_article.hash)
        self.assertEqual(_get_hash(es_article.to_dict()), hash)
Esempio n. 2
0
    def test_elastic_hash(self):
        """Can we reproduce a hash from elastic data alone?"""
        article = Article(**{
            "date": datetime.date(2015, 1, 1),
            "section": "\u6f22\u5b57",
            "pagenr": 1928390,
            "headline": "Headline hier.",
            "byline": "byline..",
            "length": 1928,
            "metastring": "Even more strange characters.. \x0C ..",
            "url": "https://example.com",
            "externalid": None,
            "author": None,
            "addressee": "Hmm",
            "text": "Contains invalid char \x08 woo",
            "medium": create_test_medium(name="abc."),
            "project": create_test_project()
        })

        article.save()

        es = ES()
        es.add_articles([article.id])
        hash = get_article_dict(article)["hash"]
        es.flush()

        es_articles = es.query_all(filters={"ids": [article.id]}, fields=HASH_FIELDS + ["hash"])
        es_article = list(es_articles)[0]

        self.assertEqual(article.id, es_article.id)
        self.assertEqual(hash, es_article.hash)
        self.assertEqual(_get_hash(es_article.to_dict()), hash)