Fetch sample/case names from database

Fetch the sample/case names from the database rather than from a
static file in the repository.

Issue:
https://issues.genenetwork.org/issues/quality-control/read-samples-from-database-by-species

1 files changed, 13 insertions, 2 deletions

diff --git a/tests/conftest.py b/tests/conftest.py
index 41dcac1..d441cb9 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -11,13 +11,24 @@ import pytest
 import jsonpickle
 
 from qc_app import create_app
-from quality_control.parsing import strain_names
 from quality_control.errors import InvalidValue, DuplicateHeading
 
 @pytest.fixture(scope="session")
 def strains():
     """Parse the strains once every test session"""
-    return strain_names("etc/strains.csv")
+    stainnames = set()
+    with open("etc/strains.csv", encoding="utf8") as strains_file:
+        for idx, line in enumerate(strains_file.readlines()):
+            if idx > 0:
+                parts = line.split()
+                for name in (parts[1], parts[2]):
+                    stainnames.add(name.strip())
+                    if len(parts) >= 6:
+                        alias = parts[5].strip()
+                        if alias != "" and alias not in ("P", "\\N"):
+                            stainnames.add(alias)
+
+    return tuple(stainnames)
 
 def is_port_in_use(port: int) -> bool:
     "Check whether `port` is in use"