Implement remaining file parsing tests

* Implement remaining file parsing tests and some helpers functions
  needed for ensuring the tests work.

3 files changed, 24 insertions, 14 deletions

diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..0cdba3e
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,9 @@
+from functools import reduce
+
+import pytest
+
+from quality_control.parsing import strain_names, parse_strains
+
+@pytest.fixture(scope="session")
+def strains():
+    return strain_names(parse_strains("strains.csv"))
diff --git a/tests/qc/test_parsing.py b/tests/qc/test_parsing.py
index 14cfbde..be13d9b 100644
--- a/tests/qc/test_parsing.py
+++ b/tests/qc/test_parsing.py
@@ -11,37 +11,38 @@ from quality_control.parsing import FileType, parse_file
      ("tests/test_data/average.tsv", FileType.STANDARD_ERROR),
      ("tests/test_data/standarderror_1_error_at_end.tsv", FileType.AVERAGE),
      ("tests/test_data/standarderror.tsv", FileType.AVERAGE),
-     ("tests/test_data/we_found_no_errors_in_your_file.tsv",
+     ("tests/test_data/duplicated_headers_no_data_errors.tsv",
       FileType.STANDARD_ERROR),))
-def test_parse_file_fails_with_wrong_filetype_declaration(filepath, filetype):
+def test_parse_file_fails_with_wrong_filetype_declaration(filepath, filetype, strains):
     with pytest.raises(ParseError):
-        for line in parse_file(filepath, filetype, "strains.csv"):
+        for line in parse_file(filepath, filetype, strains):
             pass
 
 @pytest.mark.parametrize(
     "filepath,filetype",
     (("tests/test_data/average_crlf.tsv", FileType.AVERAGE),
      ("tests/test_data/average.tsv", FileType.AVERAGE),
-     ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR),
-     ("tests/test_data/we_found_no_errors_in_your_file.tsv", FileType.AVERAGE)))
-def test_parse_file_passes_with_valid_files(filepath, filetype):
-    assert False, "Not Implemented"
+     ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR)))
+def test_parse_file_passes_with_valid_files(filepath, filetype, strains):
+    for line in parse_file(filepath, filetype, strains):
+        assert bool(line)
 
 @pytest.mark.parametrize(
     "filepath,filetype",
     (("tests/test_data/average_large.tsv", FileType.AVERAGE),
      ("tests/test_data/average.tsv", FileType.AVERAGE),
-     ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR),
-     ("tests/test_data/we_found_no_errors_in_your_file.tsv", FileType.AVERAGE)))
-def test_parse_file_works_with_large_files(filepath, filetype):
-    assert False, "Not Implemented"
+     ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR)))
+def test_parse_file_works_with_large_files(filepath, filetype, strains):
+    for line in parse_file(filepath, filetype, strains):
+        assert bool(line)
 
 
 @pytest.mark.parametrize(
     "filepath,filetype",
     (("tests/test_data/average_error_at_end_200MB.tsv", FileType.AVERAGE),
-     ("tests/test_data/standarderror_1_error_at_end.tsv", FileType.STANDARD_ERROR)))
-def test_parse_file_raises_exception_on_error_in_file(filepath, filetype):
+     ("tests/test_data/standarderror_1_error_at_end.tsv", FileType.STANDARD_ERROR),
+     ("tests/test_data/duplicated_headers_no_data_errors.tsv", FileType.AVERAGE)))
+def test_parse_file_raises_exception_on_error_in_file(filepath, filetype, strains):
     with pytest.raises(ParseError):
-        for line in parse_file(filepath, filetype, "strains.csv"):
+        for line in parse_file(filepath, filetype, strains):
             pass
diff --git a/tests/test_data/we_found_no_errors_in_your_file.tsv b/tests/test_data/duplicated_headers_no_data_errors.tsv
index a49ed1b..a49ed1b 100644
--- a/tests/test_data/we_found_no_errors_in_your_file.tsv
+++ b/tests/test_data/duplicated_headers_no_data_errors.tsv