From 54d32d4f1f01fb2cee3413c931fdca85fa68379a Mon Sep 17 00:00:00 2001
From: Stan Kirdey <skirdey@users.noreply.github.com>
Date: Tue, 28 Apr 2020 07:10:32 -0700
Subject: [PATCH] Add coverage reports and more tests (#78)

---
 .gitignore                   |  1 +
 haystack/retriever/tfidf.py  |  2 ++
 requirements.txt             |  1 +
 test/test_document.py        |  7 +++++++
 test/test_farm_reader.py     |  9 +++++++++
 test/test_tfidf_retriever.py | 19 +++++++++++++++++++
 tox.ini                      | 16 +++++++++++++---
 7 files changed, 52 insertions(+), 3 deletions(-)
 create mode 100644 test/test_document.py
 create mode 100644 test/test_farm_reader.py
 create mode 100644 test/test_tfidf_retriever.py

diff --git a/.gitignore b/.gitignore
index 824d052e3..238c92fe5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -2,6 +2,7 @@
 qa.db
 **/qa.db
 **/*qa*.db
+**/test-reports
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
diff --git a/haystack/retriever/tfidf.py b/haystack/retriever/tfidf.py
index 9a304ce24..03257c86a 100644
--- a/haystack/retriever/tfidf.py
+++ b/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]
diff --git a/requirements.txt b/requirements.txt
index 89bee887b..03c38b045 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -9,4 +9,5 @@ sklearn
 elasticsearch
 elastic-apm
 tox
+coverage
 # optional: sentence-transformers
diff --git a/test/test_document.py b/test/test_document.py
new file mode 100644
index 000000000..deb540c49
--- /dev/null
+++ b/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"
diff --git a/test/test_farm_reader.py b/test/test_farm_reader.py
new file mode 100644
index 000000000..bf8be081c
--- /dev/null
+++ b/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)
diff --git a/test/test_tfidf_retriever.py b/test/test_tfidf_retriever.py
new file mode 100644
index 000000000..577ac10c4
--- /dev/null
+++ b/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)]
\ No newline at end of file
diff --git a/tox.ini b/tox.ini
index c0d047ff2..475a64491 100644
--- a/tox.ini
+++ b/tox.ini
@@ -5,6 +5,16 @@ envlist = py36,py37
 
 [testenv]
 changedir = test
-deps = pytest
-       pandas
-commands = pytest --basetemp="{envtmpdir}" {posargs}
\ No newline at end of file
+deps =
+    coverage
+    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