Beispiel #1
0
 def test_articles_to_jsonl(self):
     """Serialize pubmedarticles objects into jsonl file."""
     articles: [PubMedArticle] = ArticleSetParser.extract_articles(
         self.SAMPLE_ARTICLE_SET1_PATH)
     target_file_name = "test_articles.jsonl"
     target_path = os.path.join(get_test_output_path(), target_file_name)
     ArticleSetParser.articles_to_jsonl(articles, target_path)
Beispiel #2
0
 def test_serialize_to_pipe_delimited(self):
     """Serialize pubmedarticles to csv file."""
     articles: [PubMedArticle] = ArticleSetParser.extract_articles(
         self.SAMPLE_ARTICLE_SET1_PATH)
     target_file_name = "test_articles.csv"
     target_path = os.path.join(get_test_output_path(), target_file_name)
     ArticleSetParser.articles_to_pipe(articles, target_path)
Beispiel #3
0
"""Pytest module to test Google BigQuery Repository."""
import os
import pytest
import tests.testdata as td
import geniepy.datamgmt.repositories as dr
from geniepy.datamgmt.tables import PUBMED_PROPTY, CTD_PROPTY, CLSFR_PROPTY
from geniepy.errors import DaoError
from tests import get_test_output_path
from tests.resources.mock import TEST_CHUNKSIZE

# Name of credential file (assumed to be in tests/tests_output dir)
CREDENTIALS_FILE = "genie_credentials.json"
CREDPATH = os.path.join(get_test_output_path(), CREDENTIALS_FILE)
# Google BigQuery Project Name
PROJNAME = "genie-275215"
DATASET = "test"

VALID_DF = td.PUBMED_VALID_DF
INVALID_SCHEMA = td.PUBMED_INVALID_SCHEMA


@pytest.mark.slow_integration_test
class TestGbqRepository:
    """Test db.pubmed_repository on Google BigQuery."""

    pubmed_repo: dr.BaseRepository = None
    ctd_repo: dr.BaseRepository = None
    clsfr_repo: dr.BaseRepository = None

    @classmethod
    def setup_class(cls):