Add coverage reports and more tests (#78)

.gitignore

@@ -2,6 +2,7 @@
 qa.db
 **/qa.db
 **/*qa*.db
+**/test-reports
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

haystack/retriever/tfidf.py

@@ -72,6 +72,8 @@ class TfidfRetriever(BaseRetriever):
         # get scores
         indices_and_scores = self._calc_scores(query)
 
+        print(indices_and_scores)
+
         # rank paragraphs
         df_sliced = self.df.loc[indices_and_scores.keys()]
         df_sliced = df_sliced[:top_k]

requirements.txt

@@ -9,4 +9,5 @@ sklearn
 elasticsearch
 elastic-apm
 tox
+coverage
 # optional: sentence-transformers

test/test_document.py

@@ -0,0 +1,7 @@
+from haystack.database.base import Document
+
+
+def test_document_data_access():
+    doc = Document(id=1, text="test")
+    assert doc.text == "test"
+    assert doc['text'] == "test"

test/test_farm_reader.py

@@ -0,0 +1,9 @@
+import pytest
+
+from haystack.reader.farm import FARMReader
+
+
+def test_farm_reader():
+    reader = FARMReader(model_name_or_path="deepset/bert-base-cased-squad2", use_gpu=False)
+    assert reader is not None
+    assert isinstance(reader, FARMReader)

test/test_tfidf_retriever.py

@@ -0,0 +1,19 @@
+from haystack.database.base import Document
+
+
+def test_tfidf_retriever():
+    from haystack.retriever.tfidf import TfidfRetriever
+
+    test_docs = [
+        {"name": "testing the finder 1", "text": "godzilla says hello"},
+        {"name": "testing the finder 2", "text": "optimus prime says bye"},
+        {"name": "testing the finder 3", "text": "alien says arghh"}
+    ]
+
+    from haystack.database.memory import InMemoryDocumentStore
+    document_store = InMemoryDocumentStore()
+    document_store.write_documents(test_docs)
+
+    retriever = TfidfRetriever(document_store)
+    retriever.fit()
+    assert retriever.retrieve("godzilla", top_k=1) == [Document(id='0', text='godzilla says hello', external_source_id=None, question=None, query_score=None, meta=None)]

tox.ini

@@ -5,6 +5,16 @@ envlist = py36,py37
 
 [testenv]
 changedir = test
-deps = pytest
+deps =
-       pandas
+    coverage
-commands = pytest --basetemp="{envtmpdir}" {posargs}
+    pytest
+    pandas
+setenv =
+    COVERAGE_FILE = test-reports/.coverage
+    PYTEST_ADDOPTS = --junitxml=test-reports/{envname}/junit.xml -vv
+commands =
+    coverage run --source haystack --parallel-mode -m pytest {posargs}
+    coverage combine
+    coverage report -m
+    coverage html -d test-reports/coverage-html
+    coverage xml -o test-reports/coverage.xml