Collect all the errors

Build a function to collect all the parsing errors into a "sequence"
of dict objects containing the issues found.

1 files changed, 30 insertions, 0 deletions

diff --git a/tests/qc/test_error_collection.py b/tests/qc/test_error_collection.py
new file mode 100644
index 0000000..c45803a
--- /dev/null
+++ b/tests/qc/test_error_collection.py
@@ -0,0 +1,30 @@
+import pytest
+
+from quality_control.parsing import FileType, parse_errors
+
+@pytest.mark.slow
+@pytest.mark.parametrize(
+    "filepath,filetype,seek_pos",
+    (("tests/test_data/average_crlf.tsv", FileType.AVERAGE, 0),
+     ("tests/test_data/average_error_at_end_200MB.tsv", FileType.AVERAGE,
+      205500004 # Skip first 500K lines
+      ),
+     ("tests/test_data/average.tsv", FileType.AVERAGE, 0),
+     ("tests/test_data/standarderror_1_error_at_end.tsv",
+      FileType.STANDARD_ERROR, 0),
+     ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR, 0),
+     ("tests/test_data/duplicated_headers_no_data_errors.tsv",
+      FileType.AVERAGE),
+     ))
+def test_parse_errors(filepath, filetype, strains, seek_pos):
+    """
+    Check that only errors are returned, and that certain properties hold for
+    said errors.
+    """
+    for error in parse_errors(filepath, filetype, strains, seek_pos):
+        assert isinstance(error, dict)
+        assert "filepath" in error
+        assert "filetype" in error
+        assert "position" in error
+        assert "error" in error and isinstance(error["error"], str)
+        assert "message" in error